1443 files changed, 43206 insertions, 15585 deletions

diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block
index 2b5d561..c1eb41c 100644
--- a/Documentation/ABI/testing/sysfs-block
+++ b/Documentation/ABI/testing/sysfs-block
@@ -206,16 +206,3 @@ Description:
 		when a discarded area is read the discard_zeroes_data
 		parameter will be set to one. Otherwise it will be 0 and
 		the result of reading a discarded area is undefined.
-What:		/sys/block/<disk>/alias
-Date:		Aug 2011
-Contact:	Nao Nishijima <nao.nishijima.xt@hitachi.com>
-Description:
-		A raw device name of a disk does not always point a same disk
-		each boot-up time. Therefore, users have to use persistent
-		device names, which udev creates when the kernel finds a disk,
-		instead of raw device name. However, kernel doesn't show those
-		persistent names on its messages (e.g. dmesg).
-		This file can store an alias of the disk and it would be
-		appeared in kernel messages if it is set. A disk can have an
-		alias which length is up to 255bytes. Users can use alphabets,
-		numbers, "-" and "_" in alias name. This file is writeonce.
diff --git a/Documentation/DocBook/uio-howto.tmpl b/Documentation/DocBook/uio-howto.tmpl
index 54883de..ac3d001 100644
--- a/Documentation/DocBook/uio-howto.tmpl
+++ b/Documentation/DocBook/uio-howto.tmpl
@@ -521,6 +521,11 @@ Here's a description of the fields of <varname>struct uio_mem</varname>:
 
 <itemizedlist>
 <listitem><para>
+<varname>const char *name</varname>: Optional. Set this to help identify
+the memory region, it will show up in the corresponding sysfs node.
+</para></listitem>
+
+<listitem><para>
 <varname>int memtype</varname>: Required if the mapping is used. Set this to
 <varname>UIO_MEM_PHYS</varname> if you you have physical memory on your
 card to be mapped. Use <varname>UIO_MEM_LOGICAL</varname> for logical
@@ -553,7 +558,7 @@ instead to remember such an address.
 </itemizedlist>
 
 <para>
-Please do not touch the <varname>kobj</varname> element of
+Please do not touch the <varname>map</varname> element of
 <varname>struct uio_mem</varname>! It is used by the UIO framework
 to set up sysfs files for this mapping. Simply leave it alone.
 </para>
diff --git a/Documentation/blockdev/cciss.txt b/Documentation/blockdev/cciss.txt
index 71464e0..b79d0a1 100644
--- a/Documentation/blockdev/cciss.txt
+++ b/Documentation/blockdev/cciss.txt
@@ -98,14 +98,12 @@ You must enable "SCSI tape drive support for Smart Array 5xxx" and
 "SCSI support" in your kernel configuration to be able to use SCSI
 tape drives with your Smart Array 5xxx controller.
 
-Additionally, note that the driver will not engage the SCSI core at init 
-time.  The driver must be directed to dynamically engage the SCSI core via 
-the /proc filesystem entry which the "block" side of the driver creates as 
-/proc/driver/cciss/cciss* at runtime.  This is because at driver init time, 
-the SCSI core may not yet be initialized (because the driver is a block 
-driver) and attempting to register it with the SCSI core in such a case 
-would cause a hang.  This is best done via an initialization script 
-(typically in /etc/init.d, but could vary depending on distribution). 
+Additionally, note that the driver will engage the SCSI core at init
+time if any tape drives or medium changers are detected.  The driver may
+also be directed to dynamically engage the SCSI core via the /proc filesystem
+entry which the "block" side of the driver creates as
+/proc/driver/cciss/cciss* at runtime.  This is best done via a script.
+
 For example:
 
 	for x in /proc/driver/cciss/cciss[0-9]*
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index cc0ebc5..6922b6c 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -44,8 +44,9 @@ Features:
  - oom-killer disable knob and oom-notifier
  - Root cgroup has no limit controls.
 
- Kernel memory and Hugepages are not under control yet. We just manage
- pages on LRU. To add more controls, we have to take care of performance.
+ Hugepages is not under control yet. We just manage pages on LRU. To add more
+ controls, we have to take care of performance. Kernel memory support is work
+ in progress, and the current version provides basically functionality.
 
 Brief summary of control files.
 
@@ -56,8 +57,11 @@ Brief summary of control files.
 				 (See 5.5 for details)
  memory.memsw.usage_in_bytes	 # show current res_counter usage for memory+Swap
 				 (See 5.5 for details)
+ memory.kmem.usage_in_bytes	 # show current res_counter usage for kmem only.
+				 (See 2.7 for details)
  memory.limit_in_bytes		 # set/show limit of memory usage
  memory.memsw.limit_in_bytes	 # set/show limit of memory+Swap usage
+ memory.kmem.limit_in_bytes	 # if allowed, set/show limit of kernel memory
  memory.failcnt			 # show the number of memory usage hits limits
  memory.memsw.failcnt		 # show the number of memory+Swap hits limits
  memory.max_usage_in_bytes	 # show max memory usage recorded
@@ -72,6 +76,11 @@ Brief summary of control files.
  memory.oom_control		 # set/show oom controls.
  memory.numa_stat		 # show the number of memory usage per numa node
 
+ memory.independent_kmem_limit	 # select whether or not kernel memory limits are
+				   independent of user limits
+ memory.kmem.tcp.limit_in_bytes  # set/show hard limit for tcp buf memory
+ memory.kmem.tcp.usage_in_bytes  # show current tcp buf memory allocation
+
 1. History
 
 The memory controller has a long history. A request for comments for the memory
@@ -255,6 +264,39 @@ When oom event notifier is registered, event will be delivered.
   per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by
   zone->lru_lock, it has no lock of its own.
 
+2.7 Kernel Memory Extension (CONFIG_CGROUP_MEM_RES_CTLR_KMEM)
+
+With the Kernel memory extension, the Memory Controller is able to limit
+the amount of kernel memory used by the system. Kernel memory is fundamentally
+different than user memory, since it can't be swapped out, which makes it
+possible to DoS the system by consuming too much of this precious resource.
+
+Some kernel memory resources may be accounted and limited separately from the
+main "kmem" resource. For instance, a slab cache that is considered important
+enough to be limited separately may have its own knobs.
+
+Kernel memory limits are not imposed for the root cgroup. Usage for the root
+cgroup may or may not be accounted.
+
+Memory limits as specified by the standard Memory Controller may or may not
+take kernel memory into consideration. This is achieved through the file
+memory.independent_kmem_limit. A Value different than 0 will allow for kernel
+memory to be controlled separately.
+
+When kernel memory limits are not independent, the limit values set in
+memory.kmem files are ignored.
+
+Currently no soft limit is implemented for kernel memory. It is future work
+to trigger slab reclaim when those limits are reached.
+
+2.7.1 Current Kernel Memory resources accounted
+
+* sockets memory pressure: some sockets protocols have memory pressure
+thresholds. The Memory Controller allows them to be controlled individually
+per cgroup, instead of globally.
+
+* tcp memory pressure: sockets memory pressure for the tcp protocol.
+
 3. User Interface
 
 0. Configuration
diff --git a/Documentation/cgroups/net_prio.txt b/Documentation/cgroups/net_prio.txt
new file mode 100644
index 0000000..01b3226
--- /dev/null
+++ b/Documentation/cgroups/net_prio.txt
@@ -0,0 +1,53 @@
+Network priority cgroup
+-------------------------
+
+The Network priority cgroup provides an interface to allow an administrator to
+dynamically set the priority of network traffic generated by various
+applications
+
+Nominally, an application would set the priority of its traffic via the
+SO_PRIORITY socket option.  This however, is not always possible because:
+
+1) The application may not have been coded to set this value
+2) The priority of application traffic is often a site-specific administrative
+   decision rather than an application defined one.
+
+This cgroup allows an administrator to assign a process to a group which defines
+the priority of egress traffic on a given interface. Network priority groups can
+be created by first mounting the cgroup filesystem.
+
+# mount -t cgroup -onet_prio none /sys/fs/cgroup/net_prio
+
+With the above step, the initial group acting as the parent accounting group
+becomes visible at '/sys/fs/cgroup/net_prio'.  This group includes all tasks in
+the system. '/sys/fs/cgroup/net_prio/tasks' lists the tasks in this cgroup.
+
+Each net_prio cgroup contains two files that are subsystem specific
+
+net_prio.prioidx
+This file is read-only, and is simply informative.  It contains a unique integer
+value that the kernel uses as an internal representation of this cgroup.
+
+net_prio.ifpriomap
+This file contains a map of the priorities assigned to traffic originating from
+processes in this group and egressing the system on various interfaces. It
+contains a list of tuples in the form <ifname priority>.  Contents of this file
+can be modified by echoing a string into the file using the same tuple format.
+for example:
+
+echo "eth0 5" > /sys/fs/cgroups/net_prio/iscsi/net_prio.ifpriomap
+
+This command would force any traffic originating from processes belonging to the
+iscsi net_prio cgroup and egressing on interface eth0 to have the priority of
+said traffic set to the value 5. The parent accounting group also has a
+writeable 'net_prio.ifpriomap' file that can be used to set a system default
+priority.
+
+Priorities are set immediately prior to queueing a frame to the device
+queueing discipline (qdisc) so priorities will be assigned prior to the hardware
+queue selection being made.
+
+One usage for the net_prio cgroup is with mqprio qdisc allowing application
+traffic to be steered to hardware/driver based traffic classes. These mappings
+can then be managed by administrators or other networking protocols such as
+DCBX.
diff --git a/Documentation/devicetree/bindings/net/calxeda-xgmac.txt b/Documentation/devicetree/bindings/net/calxeda-xgmac.txt
new file mode 100644
index 0000000..411727a
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/calxeda-xgmac.txt
@@ -0,0 +1,15 @@
+* Calxeda Highbank 10Gb XGMAC Ethernet
+
+Required properties:
+- compatible : Should be "calxeda,hb-xgmac"
+- reg : Address and length of the register set for the device
+- interrupts : Should contain 3 xgmac interrupts. The 1st is main interrupt.
+  The 2nd is pwr mgt interrupt. The 3rd is low power state interrupt.
+
+Example:
+
+ethernet@fff50000 {
+        compatible = "calxeda,hb-xgmac";
+        reg = <0xfff50000 0x1000>;
+        interrupts = <0 77 4  0 78 4  0 79 4>;
+};
diff --git a/Documentation/devicetree/bindings/net/can/cc770.txt b/Documentation/devicetree/bindings/net/can/cc770.txt
new file mode 100644
index 0000000..77027bf
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/can/cc770.txt
@@ -0,0 +1,53 @@
+Memory mapped Bosch CC770 and Intel AN82527 CAN controller
+
+Note: The CC770 is a CAN controller from Bosch, which is 100%
+compatible with the old AN82527 from Intel, but with "bugs" being fixed.
+
+Required properties:
+
+- compatible : should be "bosch,cc770" for the CC770 and "intc,82527"
+	for the AN82527.
+
+- reg : should specify the chip select, address offset and size required
+	to map the registers of the controller. The size is usually 0x80.
+
+- interrupts : property with a value describing the interrupt source
+	(number and sensitivity) required for the controller.
+
+Optional properties:
+
+- bosch,external-clock-frequency : frequency of the external oscillator
+	clock in Hz. Note that the internal clock frequency used by the
+	controller is half of that value. If not specified, a default
+	value of 16000000 (16 MHz) is used.
+
+- bosch,clock-out-frequency : slock frequency in Hz on the CLKOUT pin.
+	If not specified or if the specified value is 0, the CLKOUT pin
+	will be disabled.
+
+- bosch,slew-rate : slew rate of the CLKOUT signal. If not specified,
+	a resonable value will be calculated.
+
+- bosch,disconnect-rx0-input : see data sheet.
+
+- bosch,disconnect-rx1-input : see data sheet.
+
+- bosch,disconnect-tx1-output : see data sheet.
+
+- bosch,polarity-dominant : see data sheet.
+
+- bosch,divide-memory-clock : see data sheet.
+
+- bosch,iso-low-speed-mux : see data sheet.
+
+For further information, please have a look to the CC770 or AN82527.
+
+Examples:
+
+can@3,100 {
+	compatible = "bosch,cc770";
+	reg = <3 0x100 0x80>;
+	interrupts = <2 0>;
+	interrupt-parent = <&mpic>;
+	bosch,external-clock-frequency = <16000000>;
+};
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index e855278..874921e 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -33,6 +33,7 @@ qcom	Qualcomm, Inc.
 ramtron	Ramtron International
 samsung	Samsung Semiconductor
 schindler	Schindler
+sil	Silicon Image
 simtek
 sirf	SiRF Technology, Inc.
 stericsson	ST-Ericsson
diff --git a/Documentation/filesystems/btrfs.txt b/Documentation/filesystems/btrfs.txt
index 64087c3..7671352 100644
--- a/Documentation/filesystems/btrfs.txt
+++ b/Documentation/filesystems/btrfs.txt
@@ -63,8 +63,8 @@ IRC network.
 Userspace tools for creating and manipulating Btrfs file systems are
 available from the git repository at the following location:
 
- http://git.kernel.org/?p=linux/kernel/git/mason/btrfs-progs-unstable.git
- git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-progs-unstable.git
+ http://git.kernel.org/?p=linux/kernel/git/mason/btrfs-progs.git
+ git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-progs.git
 
 These include the following tools:
 
diff --git a/Documentation/i2c/ten-bit-addresses b/Documentation/i2c/ten-bit-addresses
index e989070..cdfe139 100644
--- a/Documentation/i2c/ten-bit-addresses
+++ b/Documentation/i2c/ten-bit-addresses
@@ -1,22 +1,24 @@
 The I2C protocol knows about two kinds of device addresses: normal 7 bit
 addresses, and an extended set of 10 bit addresses. The sets of addresses
 do not intersect: the 7 bit address 0x10 is not the same as the 10 bit
-address 0x10 (though a single device could respond to both of them). You
-select a 10 bit address by adding an extra byte after the address
-byte:
-  S Addr7 Rd/Wr ....
-becomes
-  S 11110 Addr10 Rd/Wr
-S is the start bit, Rd/Wr the read/write bit, and if you count the number
-of bits, you will see the there are 8 after the S bit for 7 bit addresses,
-and 16 after the S bit for 10 bit addresses.
+address 0x10 (though a single device could respond to both of them).
 
-WARNING! The current 10 bit address support is EXPERIMENTAL. There are
-several places in the code that will cause SEVERE PROBLEMS with 10 bit
-addresses, even though there is some basic handling and hooks. Also,
-almost no supported adapter handles the 10 bit addresses correctly.
+I2C messages to and from 10-bit address devices have a different format.
+See the I2C specification for the details.
 
-As soon as a real 10 bit address device is spotted 'in the wild', we
-can and will add proper support. Right now, 10 bit address devices
-are defined by the I2C protocol, but we have never seen a single device
-which supports them.
+The current 10 bit address support is minimal. It should work, however
+you can expect some problems along the way:
+* Not all bus drivers support 10-bit addresses. Some don't because the
+  hardware doesn't support them (SMBus doesn't require 10-bit address
+  support for example), some don't because nobody bothered adding the
+  code (or it's there but not working properly.) Software implementation
+  (i2c-algo-bit) is known to work.
+* Some optional features do not support 10-bit addresses. This is the
+  case of automatic detection and instantiation of devices by their,
+  drivers, for example.
+* Many user-space packages (for example i2c-tools) lack support for
+  10-bit addresses.
+
+Note that 10-bit address devices are still pretty rare, so the limitations
+listed above could stay for a long time, maybe even forever if nobody
+needs them to be fixed.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index a0c5c5f..5e22c3f 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -315,8 +315,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			CPU-intensive style benchmark, and it can vary highly in
 			a microbenchmark depending on workload and compiler.
 
-			1: only for 32-bit processes
-			2: only for 64-bit processes
+			32: only for 32-bit processes
+			64: only for 64-bit processes
 			on: enable for both 32- and 64-bit processes
 			off: disable for both 32- and 64-bit processes
 
diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX
index bbce121..9ad9dde 100644
--- a/Documentation/networking/00-INDEX
+++ b/Documentation/networking/00-INDEX
@@ -144,6 +144,8 @@ nfc.txt
 	- The Linux Near Field Communication (NFS) subsystem.
 olympic.txt
 	- IBM PCI Pit/Pit-Phy/Olympic Token Ring driver info.
+openvswitch.txt
+	- Open vSwitch developer documentation.
 operstates.txt
 	- Overview of network interface operational states.
 packet_mmap.txt
diff --git a/Documentation/networking/batman-adv.txt b/Documentation/networking/batman-adv.txt
index c86d03f..221ad0c 100644
--- a/Documentation/networking/batman-adv.txt
+++ b/Documentation/networking/batman-adv.txt
@@ -200,15 +200,16 @@ abled  during run time. Following log_levels are defined:
 
 0 - All  debug  output  disabled
 1 - Enable messages related to routing / flooding / broadcasting
-2 - Enable route or tt entry added / changed / deleted
-3 - Enable all messages
+2 - Enable messages related to route added / changed / deleted
+4 - Enable messages related to translation table operations
+7 - Enable all messages
 
 The debug output can be changed at runtime  using  the  file
 /sys/class/net/bat0/mesh/log_level. e.g.
 
 # echo 2 > /sys/class/net/bat0/mesh/log_level
 
-will enable debug messages for when routes or TTs change.
+will enable debug messages for when routes change.
 
 
 BATCTL
diff --git a/Documentation/networking/ieee802154.txt b/Documentation/networking/ieee802154.txt
index f41ea24..1dc1c24 100644
--- a/Documentation/networking/ieee802154.txt
+++ b/Documentation/networking/ieee802154.txt
@@ -78,3 +78,30 @@ in software. This is currently WIP.
 
 See header include/net/mac802154.h and several drivers in drivers/ieee802154/.
 
+6LoWPAN Linux implementation
+============================
+
+The IEEE 802.15.4 standard specifies an MTU of 128 bytes, yielding about 80
+octets of actual MAC payload once security is turned on, on a wireless link
+with a link throughput of 250 kbps or less.  The 6LoWPAN adaptation format
+[RFC4944] was specified to carry IPv6 datagrams over such constrained links,
+taking into account limited bandwidth, memory, or energy resources that are
+expected in applications such as wireless Sensor Networks.  [RFC4944] defines
+a Mesh Addressing header to support sub-IP forwarding, a Fragmentation header
+to support the IPv6 minimum MTU requirement [RFC2460], and stateless header
+compression for IPv6 datagrams (LOWPAN_HC1 and LOWPAN_HC2) to reduce the
+relatively large IPv6 and UDP headers down to (in the best case) several bytes.
+
+In Semptember 2011 the standard update was published - [RFC6282].
+It deprecates HC1 and HC2 compression and defines IPHC encoding format which is
+used in this Linux implementation.
+
+All the code related to 6lowpan you may find in files: net/ieee802154/6lowpan.*
+
+To setup 6lowpan interface you need (busybox release > 1.17.0):
+1. Add IEEE802.15.4 interface and initialize PANid;
+2. Add 6lowpan interface by command like:
+   # ip link add link wpan0 name lowpan0 type lowpan
+3. Set MAC (if needs):
+   # ip link set lowpan0 address de:ad:be:ef:ca:fe:ba:be
+4. Bring up 'lowpan0' interface
diff --git a/Documentation/networking/ifenslave.c b/Documentation/networking/ifenslave.c
index 65968fb..ac5debb 100644
--- a/Documentation/networking/ifenslave.c
+++ b/Documentation/networking/ifenslave.c
@@ -539,12 +539,14 @@ static int if_getconfig(char *ifname)
 		metric = 0;
 	} else
 		metric = ifr.ifr_metric;
+	printf("The result of SIOCGIFMETRIC is %d\n", metric);
 
 	strcpy(ifr.ifr_name, ifname);
 	if (ioctl(skfd, SIOCGIFMTU, &ifr) < 0)
 		mtu = 0;
 	else
 		mtu = ifr.ifr_mtu;
+	printf("The result of SIOCGIFMTU is %d\n", mtu);
 
 	strcpy(ifr.ifr_name, ifname);
 	if (ioctl(skfd, SIOCGIFDSTADDR, &ifr) < 0) {
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index cb7f314..ad3e80e 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -20,7 +20,7 @@ ip_no_pmtu_disc - BOOLEAN
 	default FALSE
 
 min_pmtu - INTEGER
-	default 562 - minimum discovered Path MTU
+	default 552 - minimum discovered Path MTU
 
 route/max_size - INTEGER
 	Maximum number of routes allowed in the kernel.  Increase
@@ -31,6 +31,16 @@ neigh/default/gc_thresh3 - INTEGER
 	when using large numbers of interfaces and when communicating
 	with large numbers of directly-connected peers.
 
+neigh/default/unres_qlen_bytes - INTEGER
+	The maximum number of bytes which may be used by packets
+	queued for each	unresolved address by other network layers.
+	(added in linux 3.3)
+
+neigh/default/unres_qlen - INTEGER
+	The maximum number of packets which may be queued for each
+	unresolved address by other network layers.
+	(deprecated in linux 3.3) : use unres_qlen_bytes instead.
+
 mtu_expires - INTEGER
 	Time, in seconds, that cached PMTU information is kept.
 
@@ -165,6 +175,9 @@ tcp_congestion_control - STRING
 	connections. The algorithm "reno" is always available, but
 	additional choices may be available based on kernel configuration.
 	Default is set as part of kernel configuration.
+	For passive connections, the listener congestion control choice
+	is inherited.
+	[see setsockopt(listenfd, SOL_TCP, TCP_CONGESTION, "name" ...) ]
 
 tcp_cookie_size - INTEGER
 	Default size of TCP Cookie Transactions (TCPCT) option, that may be
@@ -282,11 +295,11 @@ tcp_max_ssthresh - INTEGER
 	Default: 0 (off)
 
 tcp_max_syn_backlog - INTEGER
-	Maximal number of remembered connection requests, which are
-	still did not receive an acknowledgment from connecting client.
-	Default value is 1024 for systems with more than 128Mb of memory,
-	and 128 for low memory machines. If server suffers of overload,
-	try to increase this number.
+	Maximal number of remembered connection requests, which have not
+	received an acknowledgment from connecting client.
+	The minimal value is 128 for low memory machines, and it will
+	increase in proportion to the memory of machine.
+	If server suffers from overload, try increasing this number.
 
 tcp_max_tw_buckets - INTEGER
 	Maximal number of timewait sockets held by system simultaneously.
diff --git a/Documentation/networking/openvswitch.txt b/Documentation/networking/openvswitch.txt
new file mode 100644
index 0000000..b8a048b
--- /dev/null
+++ b/Documentation/networking/openvswitch.txt
@@ -0,0 +1,195 @@
+Open vSwitch datapath developer documentation
+=============================================
+
+The Open vSwitch kernel module allows flexible userspace control over
+flow-level packet processing on selected network devices.  It can be
+used to implement a plain Ethernet switch, network device bonding,
+VLAN processing, network access control, flow-based network control,
+and so on.
+
+The kernel module implements multiple "datapaths" (analogous to
+bridges), each of which can have multiple "vports" (analogous to ports
+within a bridge).  Each datapath also has associated with it a "flow
+table" that userspace populates with "flows" that map from keys based
+on packet headers and metadata to sets of actions.  The most common
+action forwards the packet to another vport; other actions are also
+implemented.
+
+When a packet arrives on a vport, the kernel module processes it by
+extracting its flow key and looking it up in the flow table.  If there
+is a matching flow, it executes the associated actions.  If there is
+no match, it queues the packet to userspace for processing (as part of
+its processing, userspace will likely set up a flow to handle further
+packets of the same type entirely in-kernel).
+
+
+Flow key compatibility
+----------------------
+
+Network protocols evolve over time.  New protocols become important
+and existing protocols lose their prominence.  For the Open vSwitch
+kernel module to remain relevant, it must be possible for newer
+versions to parse additional protocols as part of the flow key.  It
+might even be desirable, someday, to drop support for parsing
+protocols that have become obsolete.  Therefore, the Netlink interface
+to Open vSwitch is designed to allow carefully written userspace
+applications to work with any version of the flow key, past or future.
+
+To support this forward and backward compatibility, whenever the
+kernel module passes a packet to userspace, it also passes along the
+flow key that it parsed from the packet.  Userspace then extracts its
+own notion of a flow key from the packet and compares it against the
+kernel-provided version:
+
+    - If userspace's notion of the flow key for the packet matches the
+      kernel's, then nothing special is necessary.
+
+    - If the kernel's flow key includes more fields than the userspace
+      version of the flow key, for example if the kernel decoded IPv6
+      headers but userspace stopped at the Ethernet type (because it
+      does not understand IPv6), then again nothing special is
+      necessary.  Userspace can still set up a flow in the usual way,
+      as long as it uses the kernel-provided flow key to do it.
+
+    - If the userspace flow key includes more fields than the
+      kernel's, for example if userspace decoded an IPv6 header but
+      the kernel stopped at the Ethernet type, then userspace can
+      forward the packet manually, without setting up a flow in the
+      kernel.  This case is bad for performance because every packet
+      that the kernel considers part of the flow must go to userspace,
+      but the forwarding behavior is correct.  (If userspace can
+      determine that the values of the extra fields would not affect
+      forwarding behavior, then it could set up a flow anyway.)
+
+How flow keys evolve over time is important to making this work, so
+the following sections go into detail.
+
+
+Flow key format
+---------------
+
+A flow key is passed over a Netlink socket as a sequence of Netlink
+attributes.  Some attributes represent packet metadata, defined as any
+information about a packet that cannot be extracted from the packet
+itself, e.g. the vport on which the packet was received.  Most
+attributes, however, are extracted from headers within the packet,
+e.g. source and destination addresses from Ethernet, IP, or TCP
+headers.
+
+The <linux/openvswitch.h> header file defines the exact format of the
+flow key attributes.  For informal explanatory purposes here, we write
+them as comma-separated strings, with parentheses indicating arguments
+and nesting.  For example, the following could represent a flow key
+corresponding to a TCP packet that arrived on vport 1:
+
+    in_port(1), eth(src=e0:91:f5:21:d0:b2, dst=00:02:e3:0f:80:a4),
+    eth_type(0x0800), ipv4(src=172.16.0.20, dst=172.18.0.52, proto=17, tos=0,
+    frag=no), tcp(src=49163, dst=80)
+
+Often we ellipsize arguments not important to the discussion, e.g.:
+
+    in_port(1), eth(...), eth_type(0x0800), ipv4(...), tcp(...)
+
+
+Basic rule for evolving flow keys
+---------------------------------
+
+Some care is needed to really maintain forward and backward
+compatibility for applications that follow the rules listed under
+"Flow key compatibility" above.
+
+The basic rule is obvious:
+
+    ------------------------------------------------------------------
+    New network protocol support must only supplement existing flow
+    key attributes.  It must not change the meaning of already defined
+    flow key attributes.
+    ------------------------------------------------------------------
+
+This rule does have less-obvious consequences so it is worth working
+through a few examples.  Suppose, for example, that the kernel module
+did not already implement VLAN parsing.  Instead, it just interpreted
+the 802.1Q TPID (0x8100) as the Ethertype then stopped parsing the
+packet.  The flow key for any packet with an 802.1Q header would look
+essentially like this, ignoring metadata:
+
+    eth(...), eth_type(0x8100)
+
+Naively, to add VLAN support, it makes sense to add a new "vlan" flow
+key attribute to contain the VLAN tag, then continue to decode the
+encapsulated headers beyond the VLAN tag using the existing field
+definitions.  With this change, an TCP packet in VLAN 10 would have a
+flow key much like this:
+
+    eth(...), vlan(vid=10, pcp=0), eth_type(0x0800), ip(proto=6, ...), tcp(...)
+
+But this change would negatively affect a userspace application that
+has not been updated to understand the new "vlan" flow key attribute.
+The application could, following the flow compatibility rules above,
+ignore the "vlan" attribute that it does not understand and therefore
+assume that the flow contained IP packets.  This is a bad assumption
+(the flow only contains IP packets if one parses and skips over the
+802.1Q header) and it could cause the application's behavior to change
+across kernel versions even though it follows the compatibility rules.
+
+The solution is to use a set of nested attributes.  This is, for
+example, why 802.1Q support uses nested attributes.  A TCP packet in
+VLAN 10 is actually expressed as:
+
+    eth(...), eth_type(0x8100), vlan(vid=10, pcp=0), encap(eth_type(0x0800),
+    ip(proto=6, ...), tcp(...)))
+
+Notice how the "eth_type", "ip", and "tcp" flow key attributes are
+nested inside the "encap" attribute.  Thus, an application that does
+not understand the "vlan" key will not see either of those attributes
+and therefore will not misinterpret them.  (Also, the outer eth_type
+is still 0x8100, not changed to 0x0800.)
+
+Handling malformed packets
+--------------------------
+
+Don't drop packets in the kernel for malformed protocol headers, bad
+checksums, etc.  This would prevent userspace from implementing a
+simple Ethernet switch that forwards every packet.
+
+Instead, in such a case, include an attribute with "empty" content.
+It doesn't matter if the empty content could be valid protocol values,
+as long as those values are rarely seen in practice, because userspace
+can always forward all packets with those values to userspace and
+handle them individually.
+
+For example, consider a packet that contains an IP header that
+indicates protocol 6 for TCP, but which is truncated just after the IP
+header, so that the TCP header is missing.  The flow key for this
+packet would include a tcp attribute with all-zero src and dst, like
+this:
+
+    eth(...), eth_type(0x0800), ip(proto=6, ...), tcp(src=0, dst=0)
+
+As another example, consider a packet with an Ethernet type of 0x8100,
+indicating that a VLAN TCI should follow, but which is truncated just
+after the Ethernet type.  The flow key for this packet would include
+an all-zero-bits vlan and an empty encap attribute, like this:
+
+    eth(...), eth_type(0x8100), vlan(0), encap()
+
+Unlike a TCP packet with source and destination ports 0, an
+all-zero-bits VLAN TCI is not that rare, so the CFI bit (aka
+VLAN_TAG_PRESENT inside the kernel) is ordinarily set in a vlan
+attribute expressly to allow this situation to be distinguished.
+Thus, the flow key in this second example unambiguously indicates a
+missing or malformed VLAN TCI.
+
+Other rules
+-----------
+
+The other rules for flow keys are much less subtle:
+
+    - Duplicate attributes are not allowed at a given nesting level.
+
+    - Ordering of attributes is not significant.
+
+    - When the kernel sends a given flow key to userspace, it always
+      composes it the same way.  This allows userspace to hash and
+      compare entire flow keys that it may not be able to fully
+      interpret.
diff --git a/Documentation/networking/team.txt b/Documentation/networking/team.txt
new file mode 100644
index 0000000..5a01368
--- /dev/null
+++ b/Documentation/networking/team.txt
@@ -0,0 +1,2 @@
+Team devices are driven from userspace via libteam library which is here:
+	https://github.com/jpirko/libteam
diff --git a/Documentation/power/devices.txt b/Documentation/power/devices.txt
index 646a89e..3139fb5 100644
--- a/Documentation/power/devices.txt
+++ b/Documentation/power/devices.txt
@@ -123,9 +123,10 @@ please refer directly to the source code for more information about it.
 Subsystem-Level Methods
 -----------------------
 The core methods to suspend and resume devices reside in struct dev_pm_ops
-pointed to by the pm member of struct bus_type, struct device_type and
-struct class.  They are mostly of interest to the people writing infrastructure
-for buses, like PCI or USB, or device type and device class drivers.
+pointed to by the ops member of struct dev_pm_domain, or by the pm member of
+struct bus_type, struct device_type and struct class.  They are mostly of
+interest to the people writing infrastructure for platforms and buses, like PCI
+or USB, or device type and device class drivers.
 
 Bus drivers implement these methods as appropriate for the hardware and the
 drivers using it; PCI works differently from USB, and so on.  Not many people
@@ -139,41 +140,57 @@ sequencing in the driver model tree.
 
 /sys/devices/.../power/wakeup files
 -----------------------------------
-All devices in the driver model have two flags to control handling of wakeup
-events (hardware signals that can force the device and/or system out of a low
-power state).  These flags are initialized by bus or device driver code using
+All device objects in the driver model contain fields that control the handling
+of system wakeup events (hardware signals that can force the system out of a
+sleep state).  These fields are initialized by bus or device driver code using
 device_set_wakeup_capable() and device_set_wakeup_enable(), defined in
 include/linux/pm_wakeup.h.
 
-The "can_wakeup" flag just records whether the device (and its driver) can
+The "power.can_wakeup" flag just records whether the device (and its driver) can
 physically support wakeup events.  The device_set_wakeup_capable() routine
-affects this flag.  The "should_wakeup" flag controls whether the device should
-try to use its wakeup mechanism.  device_set_wakeup_enable() affects this flag;
-for the most part drivers should not change its value.  The initial value of
-should_wakeup is supposed to be false for the majority of devices; the major
-exceptions are power buttons, keyboards, and Ethernet adapters whose WoL
-(wake-on-LAN) feature has been set up with ethtool.  It should also default
-to true for devices that don't generate wakeup requests on their own but merely
-forward wakeup requests from one bus to another (like PCI bridges).
+affects this flag.  The "power.wakeup" field is a pointer to an object of type
+struct wakeup_source used for controlling whether or not the device should use
+its system wakeup mechanism and for notifying the PM core of system wakeup
+events signaled by the device.  This object is only present for wakeup-capable
+devices (i.e. devices whose "can_wakeup" flags are set) and is created (or
+removed) by device_set_wakeup_capable().
 
 Whether or not a device is capable of issuing wakeup events is a hardware
 matter, and the kernel is responsible for keeping track of it.  By contrast,
 whether or not a wakeup-capable device should issue wakeup events is a policy
 decision, and it is managed by user space through a sysfs attribute: the
-power/wakeup file.  User space can write the strings "enabled" or "disabled" to
-set or clear the "should_wakeup" flag, respectively.  This file is only present
-for wakeup-capable devices (i.e. devices whose "can_wakeup" flags are set)
-and is created (or removed) by device_set_wakeup_capable().  Reads from the
-file will return the corresponding string.
-
-The device_may_wakeup() routine returns true only if both flags are set.
+"power/wakeup" file.  User space can write the strings "enabled" or "disabled"
+to it to indicate whether or not, respectively, the device is supposed to signal
+system wakeup.  This file is only present if the "power.wakeup" object exists
+for the given device and is created (or removed) along with that object, by
+device_set_wakeup_capable().  Reads from the file will return the corresponding
+string.
+
+The "power/wakeup" file is supposed to contain the "disabled" string initially
+for the majority of devices; the major exceptions are power buttons, keyboards,
+and Ethernet adapters whose WoL (wake-on-LAN) feature has been set up with
+ethtool.  It should also default to "enabled" for devices that don't generate
+wakeup requests on their own but merely forward wakeup requests from one bus to
+another (like PCI Express ports).
+
+The device_may_wakeup() routine returns true only if the "power.wakeup" object
+exists and the corresponding "power/wakeup" file contains the string "enabled".
 This information is used by subsystems, like the PCI bus type code, to see
 whether or not to enable the devices' wakeup mechanisms.  If device wakeup
 mechanisms are enabled or disabled directly by drivers, they also should use
 device_may_wakeup() to decide what to do during a system sleep transition.
-However for runtime power management, wakeup events should be enabled whenever
-the device and driver both support them, regardless of the should_wakeup flag.
-
+Device drivers, however, are not supposed to call device_set_wakeup_enable()
+directly in any case.
+
+It ought to be noted that system wakeup is conceptually different from "remote
+wakeup" used by runtime power management, although it may be supported by the
+same physical mechanism.  Remote wakeup is a feature allowing devices in
+low-power states to trigger specific interrupts to signal conditions in which
+they should be put into the full-power state.  Those interrupts may or may not
+be used to signal system wakeup events, depending on the hardware design.  On
+some systems it is impossible to trigger them from system sleep states.  In any
+case, remote wakeup should always be enabled for runtime power management for
+all devices and drivers that support it.
 
 /sys/devices/.../power/control files
 ------------------------------------
@@ -249,20 +266,31 @@ for every device before the next phase begins.  Not all busses or classes
 support all these callbacks and not all drivers use all the callbacks.  The
 various phases always run after tasks have been frozen and before they are
 unfrozen.  Furthermore, the *_noirq phases run at a time when IRQ handlers have
-been disabled (except for those marked with the IRQ_WAKEUP flag).
-
-All phases use bus, type, or class callbacks (that is, methods defined in
-dev->bus->pm, dev->type->pm, or dev->class->pm).  These callbacks are mutually
-exclusive, so if the device type provides a struct dev_pm_ops object pointed to
-by its pm field (i.e. both dev->type and dev->type->pm are defined), the
-callbacks included in that object (i.e. dev->type->pm) will be used.  Otherwise,
-if the class provides a struct dev_pm_ops object pointed to by its pm field
-(i.e. both dev->class and dev->class->pm are defined), the PM core will use the
-callbacks from that object (i.e. dev->class->pm).  Finally, if the pm fields of
-both the device type and class objects are NULL (or those objects do not exist),
-the callbacks provided by the bus (that is, the callbacks from dev->bus->pm)
-will be used (this allows device types to override callbacks provided by bus
-types or classes if necessary).
+been disabled (except for those marked with the IRQF_NO_SUSPEND flag).
+
+All phases use PM domain, bus, type, or class callbacks (that is, methods
+defined in dev->pm_domain->ops, dev->bus->pm, dev->type->pm, or dev->class->pm).
+These callbacks are regarded by the PM core as mutually exclusive.  Moreover,
+PM domain callbacks always take precedence over bus, type and class callbacks,
+while type callbacks take precedence over bus and class callbacks, and class
+callbacks take precedence over bus callbacks.  To be precise, the following
+rules are used to determine which callback to execute in the given phase:
+
+    1.	If dev->pm_domain is present, the PM core will attempt to execute the
+	callback included in dev->pm_domain->ops.  If that callback is not
+	present, no action will be carried out for the given device.
+
+    2.	Otherwise, if both dev->type and dev->type->pm are present, the callback
+	included in dev->type->pm will be executed.
+
+    3.	Otherwise, if both dev->class and dev->class->pm are present, the
+	callback included in dev->class->pm will be executed.
+
+    4.	Otherwise, if both dev->bus and dev->bus->pm are present, the callback
+	included in dev->bus->pm will be executed.
+
+This allows PM domains and device types to override callbacks provided by bus
+types or device classes if necessary.
 
 These callbacks may in turn invoke device- or driver-specific methods stored in
 dev->driver->pm, but they don't have to.
@@ -283,9 +311,8 @@ When the system goes into the standby or memory sleep state, the phases are:
 
 	After the prepare callback method returns, no new children may be
 	registered below the device.  The method may also prepare the device or
-	driver in some way for the upcoming system power transition (for
-	example, by allocating additional memory required for this purpose), but
-	it should not put the device into a low-power state.
+	driver in some way for the upcoming system power transition, but it
+	should not put the device into a low-power state.
 
     2.	The suspend methods should quiesce the device to stop it from performing
 	I/O.  They also may save the device registers and put it into the
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 5336149..c2ae8bf 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -44,25 +44,33 @@ struct dev_pm_ops {
 };
 
 The ->runtime_suspend(), ->runtime_resume() and ->runtime_idle() callbacks
-are executed by the PM core for either the power domain, or the device type
-(if the device power domain's struct dev_pm_ops does not exist), or the class
-(if the device power domain's and type's struct dev_pm_ops object does not
-exist), or the bus type (if the device power domain's, type's and class'
-struct dev_pm_ops objects do not exist) of the given device, so the priority
-order of callbacks from high to low is that power domain callbacks, device
-type callbacks, class callbacks and bus type callbacks, and the high priority
-one will take precedence over low priority one. The bus type, device type and
-class callbacks are referred to as subsystem-level callbacks in what follows,
-and generally speaking, the power domain callbacks are used for representing
-power domains within a SoC.
+are executed by the PM core for the device's subsystem that may be either of
+the following:
+
+  1. PM domain of the device, if the device's PM domain object, dev->pm_domain,
+     is present.
+
+  2. Device type of the device, if both dev->type and dev->type->pm are present.
+
+  3. Device class of the device, if both dev->class and dev->class->pm are
+     present.
+
+  4. Bus type of the device, if both dev->bus and dev->bus->pm are present.
+
+The PM core always checks which callback to use in the order given above, so the
+priority order of callbacks from high to low is: PM domain, device type, class
+and bus type.  Moreover, the high-priority one will always take precedence over
+a low-priority one.  The PM domain, bus type, device type and class callbacks
+are referred to as subsystem-level callbacks in what follows.
 
 By default, the callbacks are always invoked in process context with interrupts
 enabled.  However, subsystems can use the pm_runtime_irq_safe() helper function
-to tell the PM core that a device's ->runtime_suspend() and ->runtime_resume()
-callbacks should be invoked in atomic context with interrupts disabled.
-This implies that these callback routines must not block or sleep, but it also
-means that the synchronous helper functions listed at the end of Section 4 can
-be used within an interrupt handler or in an atomic context.
+to tell the PM core that their ->runtime_suspend(), ->runtime_resume() and
+->runtime_idle() callbacks may be invoked in atomic context with interrupts
+disabled for a given device.  This implies that the callback routines in
+question must not block or sleep, but it also means that the synchronous helper
+functions listed at the end of Section 4 may be used for that device within an
+interrupt handler or generally in an atomic context.
 
 The subsystem-level suspend callback is _entirely_ _responsible_ for handling
 the suspend of the device as appropriate, which may, but need not include
diff --git a/Documentation/serial/serial-rs485.txt b/Documentation/serial/serial-rs485.txt
index 079cb3d..41c8378 100644
--- a/Documentation/serial/serial-rs485.txt
+++ b/Documentation/serial/serial-rs485.txt
@@ -97,15 +97,23 @@
 
 	struct serial_rs485 rs485conf;
 
-	/* Set RS485 mode: */
+	/* Enable RS485 mode: */
 	rs485conf.flags |= SER_RS485_ENABLED;
 
+	/* Set logical level for RTS pin equal to 1 when sending: */
+	rs485conf.flags |= SER_RS485_RTS_ON_SEND;
+	/* or, set logical level for RTS pin equal to 0 when sending: */
+	rs485conf.flags &= ~(SER_RS485_RTS_ON_SEND);
+
+	/* Set logical level for RTS pin equal to 1 after sending: */
+	rs485conf.flags |= SER_RS485_RTS_AFTER_SEND;
+	/* or, set logical level for RTS pin equal to 0 after sending: */
+	rs485conf.flags &= ~(SER_RS485_RTS_AFTER_SEND);
+
 	/* Set rts delay before send, if needed: */
-	rs485conf.flags |= SER_RS485_RTS_BEFORE_SEND;
 	rs485conf.delay_rts_before_send = ...;
 
 	/* Set rts delay after send, if needed: */
-	rs485conf.flags |= SER_RS485_RTS_AFTER_SEND;
 	rs485conf.delay_rts_after_send = ...;
 
 	/* Set this flag if you want to receive data even whilst sending data */
diff --git a/Documentation/sound/alsa/HD-Audio.txt b/Documentation/sound/alsa/HD-Audio.txt
index 03e2771..91fee3b 100644
--- a/Documentation/sound/alsa/HD-Audio.txt
+++ b/Documentation/sound/alsa/HD-Audio.txt
@@ -579,7 +579,7 @@ Development Tree
 ~~~~~~~~~~~~~~~~
 The latest development codes for HD-audio are found on sound git tree:
 
-- git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound-2.6.git
+- git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git
 
 The master branch or for-next branches can be used as the main
 development branches in general while the HD-audio specific patches
@@ -594,7 +594,7 @@ is, installed via the usual spells: configure, make and make
 install(-modules).  See INSTALL in the package.  The snapshot tarballs
 are found at:
 
-- ftp://ftp.kernel.org/pub/linux/kernel/people/tiwai/snapshot/
+- ftp://ftp.suse.com/pub/people/tiwai/snapshot/
 
 
 Sending a Bug Report
@@ -696,7 +696,7 @@ via hda-verb won't change the mixer value.
 
 The hda-verb program is found in the ftp directory:
 
-- ftp://ftp.kernel.org/pub/linux/kernel/people/tiwai/misc/
+- ftp://ftp.suse.com/pub/people/tiwai/misc/
 
 Also a git repository is available:
 
@@ -764,7 +764,7 @@ operation, the jack plugging simulation, etc.
 
 The package is found in:
 
-- ftp://ftp.kernel.org/pub/linux/kernel/people/tiwai/misc/
+- ftp://ftp.suse.com/pub/people/tiwai/misc/
 
 A git repository is available:
 
diff --git a/Documentation/usb/linux-cdc-acm.inf b/Documentation/usb/linux-cdc-acm.inf
index 37a02ce..f0ffc27 100644
--- a/Documentation/usb/linux-cdc-acm.inf
+++ b/Documentation/usb/linux-cdc-acm.inf
@@ -90,10 +90,10 @@ ServiceBinary=%12%\USBSER.sys
 [SourceDisksFiles]
 [SourceDisksNames]
 [DeviceList]
-%DESCRIPTION%=DriverInstall, USB\VID_0525&PID_A4A7, USB\VID_1D6B&PID_0104&MI_02
+%DESCRIPTION%=DriverInstall, USB\VID_0525&PID_A4A7, USB\VID_1D6B&PID_0104&MI_02, USB\VID_1D6B&PID_0106&MI_00
 
 [DeviceList.NTamd64]
-%DESCRIPTION%=DriverInstall, USB\VID_0525&PID_A4A7, USB\VID_1D6B&PID_0104&MI_02
+%DESCRIPTION%=DriverInstall, USB\VID_0525&PID_A4A7, USB\VID_1D6B&PID_0104&MI_02, USB\VID_1D6B&PID_0106&MI_00
 
 
 ;------------------------------------------------------------------------------
diff --git a/MAINTAINERS b/MAINTAINERS
index 071a996..860a4ce 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -789,6 +789,7 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 T:	git git://git.pengutronix.de/git/imx/linux-2.6.git
 F:	arch/arm/mach-mx*/
+F:	arch/arm/mach-imx/
 F:	arch/arm/plat-mxc/
 
 ARM/FREESCALE IMX51
@@ -804,6 +805,13 @@ S:	Maintained
 T:	git git://git.linaro.org/people/shawnguo/linux-2.6.git
 F:	arch/arm/mach-imx/*imx6*
 
+ARM/FREESCALE MXS ARM ARCHITECTURE
+M:	Shawn Guo <shawn.guo@linaro.org>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+T:	git git://git.linaro.org/people/shawnguo/linux-2.6.git
+F:	arch/arm/mach-mxs/
+
 ARM/GLOMATION GESBC9312SX MACHINE SUPPORT
 M:	Lennert Buytenhek <kernel@wantstofly.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -1789,6 +1797,14 @@ F:	include/net/cfg80211.h
 F:	net/wireless/*
 X:	net/wireless/wext*
 
+CHAR and MISC DRIVERS
+M:	Arnd Bergmann <arnd@arndb.de>
+M:	Greg Kroah-Hartman <greg@kroah.com>
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc.git
+S:	Maintained
+F:	drivers/char/*
+F:	drivers/misc/*
+
 CHECKPATCH
 M:	Andy Whitcroft <apw@canonical.com>
 S:	Supported
@@ -1927,9 +1943,11 @@ S:	Maintained
 F:	drivers/connector/
 
 CONTROL GROUPS (CGROUPS)
-M:	Paul Menage <paul@paulmenage.org>
+M:	Tejun Heo <tj@kernel.org>
 M:	Li Zefan <lizf@cn.fujitsu.com>
 L:	containers@lists.linux-foundation.org
+L:	cgroups@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup.git
 S:	Maintained
 F:	include/linux/cgroup*
 F:	kernel/cgroup*
@@ -2584,7 +2602,7 @@ S:	Maintained
 F:	drivers/net/ethernet/i825xx/eexpress.*
 
 ETHERNET BRIDGE
-M:	Stephen Hemminger <shemminger@linux-foundation.org>
+M:	Stephen Hemminger <shemminger@vyatta.com>
 L:	bridge@lists.linux-foundation.org
 L:	netdev@vger.kernel.org
 W:	http://www.linuxfoundation.org/en/Net:Bridge
@@ -3718,7 +3736,7 @@ F:	fs/jbd2/
 F:	include/linux/jbd2.h
 
 JSM Neo PCI based serial card
-M:	Breno Leitao <leitao@linux.vnet.ibm.com>
+M:	Lucas Tavares <lucaskt@linux.vnet.ibm.com>
 L:	linux-serial@vger.kernel.org
 S:	Maintained
 F:	drivers/tty/serial/jsm/
@@ -4304,6 +4322,7 @@ MEMORY RESOURCE CONTROLLER
 M:	Balbir Singh <bsingharora@gmail.com>
 M:	Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
 M:	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
+L:	cgroups@vger.kernel.org
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	mm/memcontrol.c
@@ -4337,7 +4356,7 @@ MIPS
 M:	Ralf Baechle <ralf@linux-mips.org>
 L:	linux-mips@linux-mips.org
 W:	http://www.linux-mips.org/
-T:	git git://git.linux-mips.org/pub/scm/linux.git
+T:	git git://git.linux-mips.org/pub/scm/ralf/linux.git
 Q:	http://patchwork.linux-mips.org/project/linux-mips/list/
 S:	Supported
 F:	Documentation/mips/
@@ -4470,7 +4489,7 @@ S:	Supported
 F:	drivers/infiniband/hw/nes/
 
 NETEM NETWORK EMULATOR
-M:	Stephen Hemminger <shemminger@linux-foundation.org>
+M:	Stephen Hemminger <shemminger@vyatta.com>
 L:	netem@lists.linux-foundation.org
 S:	Maintained
 F:	net/sched/sch_netem.c
@@ -4849,6 +4868,14 @@ S:	Maintained
 T:	git git://openrisc.net/~jonas/linux
 F:	arch/openrisc
 
+OPENVSWITCH
+M:	Jesse Gross <jesse@nicira.com>
+L:	dev@openvswitch.org
+W:	http://openvswitch.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jesse/openvswitch.git
+S:	Maintained
+F:	net/openvswitch/
+
 OPL4 DRIVER
 M:	Clemens Ladisch <clemens@ladisch.de>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
@@ -4947,7 +4974,7 @@ F:	drivers/char/ppdev.c
 F:	include/linux/ppdev.h
 
 PARAVIRT_OPS INTERFACE
-M:	Jeremy Fitzhardinge <jeremy@xensource.com>
+M:	Jeremy Fitzhardinge <jeremy@goop.org>
 M:	Chris Wright <chrisw@sous-sol.org>
 M:	Alok Kataria <akataria@vmware.com>
 M:	Rusty Russell <rusty@rustcorp.com.au>
@@ -5656,7 +5683,6 @@ F:	drivers/media/video/*7146*
 F:	include/media/*7146*
 
 SAMSUNG AUDIO (ASoC) DRIVERS
-M:	Jassi Brar <jassisinghbrar@gmail.com>
 M:	Sangbeom Kim <sbkim73@samsung.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 S:	Supported
@@ -5884,7 +5910,6 @@ F:	drivers/net/ethernet/emulex/benet/
 
 SFC NETWORK DRIVER
 M:	Solarflare linux maintainers <linux-net-drivers@solarflare.com>
-M:	Steve Hodgson <shodgson@solarflare.com>
 M:	Ben Hutchings <bhutchings@solarflare.com>
 L:	netdev@vger.kernel.org
 S:	Supported
@@ -5985,7 +6010,7 @@ S:	Maintained
 F:	drivers/usb/misc/sisusbvga/
 
 SKGE, SKY2 10/100/1000 GIGABIT ETHERNET DRIVERS
-M:	Stephen Hemminger <shemminger@linux-foundation.org>
+M:	Stephen Hemminger <shemminger@vyatta.com>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/marvell/sk*
@@ -6492,6 +6517,13 @@ W:	http://tcp-lp-mod.sourceforge.net/
 S:	Maintained
 F:	net/ipv4/tcp_lp.c
 
+TEAM DRIVER
+M:	Jiri Pirko <jpirko@redhat.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	drivers/net/team/
+F:	include/linux/if_team.h
+
 TEGRA SUPPORT
 M:	Colin Cross <ccross@android.com>
 M:	Olof Johansson <olof@lixom.net>
@@ -7399,8 +7431,8 @@ S:	Maintained
 F:	arch/x86/kernel/cpu/mcheck/*
 
 XEN HYPERVISOR INTERFACE
-M:	Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
+M:	Jeremy Fitzhardinge <jeremy@goop.org>
 L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
 L:	virtualization@lists.linux-foundation.org
 S:	Supported
@@ -7433,7 +7465,8 @@ F:	drivers/xen/*swiotlb*
 
 XFS FILESYSTEM
 P:	Silicon Graphics Inc
-M:	Alex Elder <aelder@sgi.com>
+M:	Ben Myers <bpm@sgi.com>
+M:	Alex Elder <elder@kernel.org>
 M:	xfs-masters@oss.sgi.com
 L:	xfs@oss.sgi.com
 W:	http://oss.sgi.com/projects/xfs
diff --git a/Makefile b/Makefile
index dab8610..12aafc2 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 2
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc4
 NAME = Saber-toothed Squirrel
 
 # *DOCUMENTATION*
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 44789ef..e084b7e 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1231,7 +1231,7 @@ config ARM_ERRATA_742231
 	  capabilities of the processor.
 
 config PL310_ERRATA_588369
-	bool "Clean & Invalidate maintenance operations do not invalidate clean lines"
+	bool "PL310 errata: Clean & Invalidate maintenance operations do not invalidate clean lines"
 	depends on CACHE_L2X0
 	help
 	   The PL310 L2 cache controller implements three types of Clean &
@@ -1256,7 +1256,7 @@ config ARM_ERRATA_720789
 	  entries regardless of the ASID.
 
 config PL310_ERRATA_727915
-	bool "Background Clean & Invalidate by Way operation can cause data corruption"
+	bool "PL310 errata: Background Clean & Invalidate by Way operation can cause data corruption"
 	depends on CACHE_L2X0
 	help
 	  PL310 implements the Clean & Invalidate by Way L2 cache maintenance
@@ -1289,8 +1289,8 @@ config ARM_ERRATA_751472
 	  operation is received by a CPU before the ICIALLUIS has completed,
 	  potentially leading to corrupted entries in the cache or TLB.
 
-config ARM_ERRATA_753970
-	bool "ARM errata: cache sync operation may be faulty"
+config PL310_ERRATA_753970
+	bool "PL310 errata: cache sync operation may be faulty"
 	depends on CACHE_PL310
 	help
 	  This option enables the workaround for the 753970 PL310 (r3p0) erratum.
@@ -1352,6 +1352,18 @@ config ARM_ERRATA_764369
 	  relevant cache maintenance functions and sets a specific bit
 	  in the diagnostic control register of the SCU.
 
+config PL310_ERRATA_769419
+	bool "PL310 errata: no automatic Store Buffer drain"
+	depends on CACHE_L2X0
+	help
+	  On revisions of the PL310 prior to r3p2, the Store Buffer does
+	  not automatically drain. This can cause normal, non-cacheable
+	  writes to be retained when the memory system is idle, leading
+	  to suboptimal I/O performance for drivers using coherent DMA.
+	  This option adds a write barrier to the cpu_idle loop so that,
+	  on systems with an outer cache, the store buffer is drained
+	  explicitly.
+
 endmenu
 
 source "arch/arm/common/Kconfig"
diff --git a/arch/arm/boot/Makefile b/arch/arm/boot/Makefile
index 176062a..5df26a9 100644
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@@ -65,6 +65,8 @@ $(obj)/%.dtb: $(src)/dts/%.dts
 
 $(obj)/dtbs: $(addprefix $(obj)/, $(dtb-y))
 
+clean-files := *.dtb
+
 quiet_cmd_uimage = UIMAGE  $@
       cmd_uimage = $(CONFIG_SHELL) $(MKIMAGE) -A arm -O linux -T kernel \
 		   -C none -a $(LOADADDR) -e $(STARTADDR) \
diff --git a/arch/arm/common/gic.c b/arch/arm/common/gic.c
index 0e6ae47..410a546 100644
--- a/arch/arm/common/gic.c
+++ b/arch/arm/common/gic.c
@@ -526,7 +526,8 @@ static void __init gic_pm_init(struct gic_chip_data *gic)
 		sizeof(u32));
 	BUG_ON(!gic->saved_ppi_conf);
 
-	cpu_pm_register_notifier(&gic_notifier_block);
+	if (gic == &gic_data[0])
+		cpu_pm_register_notifier(&gic_notifier_block);
 }
 #else
 static void __init gic_pm_init(struct gic_chip_data *gic)
@@ -581,13 +582,16 @@ void __init gic_init(unsigned int gic_nr, int irq_start,
 	 * For primary GICs, skip over SGIs.
 	 * For secondary GICs, skip over PPIs, too.
 	 */
+	domain->hwirq_base = 32;
 	if (gic_nr == 0) {
 		gic_cpu_base_addr = cpu_base;
-		domain->hwirq_base = 16;
-		if (irq_start > 0)
-			irq_start = (irq_start & ~31) + 16;
-	} else
-		domain->hwirq_base = 32;
+
+		if ((irq_start & 31) > 0) {
+			domain->hwirq_base = 16;
+			if (irq_start != -1)
+				irq_start = (irq_start & ~31) + 16;
+		}
+	}
 
 	/*
 	 * Find out how many interrupts are supported.
diff --git a/arch/arm/common/pl330.c b/arch/arm/common/pl330.c
index 7129cfb..f407a6b 100644
--- a/arch/arm/common/pl330.c
+++ b/arch/arm/common/pl330.c
@@ -1211,8 +1211,8 @@ static inline u32 _prepare_ccr(const struct pl330_reqcfg *rqc)
 	ccr |= (rqc->brst_size << CC_SRCBRSTSIZE_SHFT);
 	ccr |= (rqc->brst_size << CC_DSTBRSTSIZE_SHFT);
 
-	ccr |= (rqc->dcctl << CC_SRCCCTRL_SHFT);
-	ccr |= (rqc->scctl << CC_DSTCCTRL_SHFT);
+	ccr |= (rqc->scctl << CC_SRCCCTRL_SHFT);
+	ccr |= (rqc->dcctl << CC_DSTCCTRL_SHFT);
 
 	ccr |= (rqc->swap << CC_SWAP_SHFT);
 
@@ -1623,6 +1623,11 @@ static inline int _alloc_event(struct pl330_thread *thrd)
 	return -1;
 }
 
+static bool _chan_ns(const struct pl330_info *pi, int i)
+{
+	return pi->pcfg.irq_ns & (1 << i);
+}
+
 /* Upon success, returns IdentityToken for the
  * allocated channel, NULL otherwise.
  */
@@ -1647,7 +1652,8 @@ void *pl330_request_channel(const struct pl330_info *pi)
 
 	for (i = 0; i < chans; i++) {
 		thrd = &pl330->channels[i];
-		if (thrd->free) {
+		if ((thrd->free) && (!_manager_ns(thrd) ||
+					_chan_ns(pi, i))) {
 			thrd->ev = _alloc_event(thrd);
 			if (thrd->ev >= 0) {
 				thrd->free = false;
diff --git a/arch/arm/configs/at91cap9adk_defconfig b/arch/arm/configs/at91cap9_defconfig
index ffb1edd..8826eb2 100644
--- a/arch/arm/configs/at91cap9adk_defconfig
+++ b/arch/arm/configs/at91cap9_defconfig
@@ -38,7 +38,6 @@ CONFIG_IP_PNP_RARP=y
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
-CONFIG_MTD_PARTITIONS=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
@@ -52,16 +51,12 @@ CONFIG_MTD_NAND_ATMEL=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
-CONFIG_ATMEL_SSC=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_SCSI_MULTI_LUN=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
 CONFIG_MACB=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_EVDEV=y
 # CONFIG_INPUT_KEYBOARD is not set
@@ -81,7 +76,6 @@ CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_FB=y
 CONFIG_FB_ATMEL=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_CLUT224 is not set
@@ -99,7 +93,6 @@ CONFIG_MMC_AT91=m
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_AT91SAM9=y
 CONFIG_EXT2_FS=y
-CONFIG_INOTIFY=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_JFFS2_FS=y
diff --git a/arch/arm/configs/at91rm9200_defconfig b/arch/arm/configs/at91rm9200_defconfig
index 38cb7c9..bbe4e1a 100644
--- a/arch/arm/configs/at91rm9200_defconfig
+++ b/arch/arm/configs/at91rm9200_defconfig
@@ -5,7 +5,6 @@ CONFIG_SYSVIPC=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=14
-CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_MODULES=y
 CONFIG_MODULE_FORCE_LOAD=y
@@ -56,7 +55,6 @@ CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_NET_IPIP=m
-CONFIG_NET_IPGRE=m
 CONFIG_INET_AH=m
 CONFIG_INET_ESP=m
 CONFIG_INET_IPCOMP=m
@@ -75,18 +73,8 @@ CONFIG_IPV6_TUNNEL=m
 CONFIG_BRIDGE=m
 CONFIG_VLAN_8021Q=m
 CONFIG_BT=m
-CONFIG_BT_L2CAP=m
-CONFIG_BT_SCO=m
-CONFIG_BT_RFCOMM=m
-CONFIG_BT_RFCOMM_TTY=y
-CONFIG_BT_BNEP=m
-CONFIG_BT_BNEP_MC_FILTER=y
-CONFIG_BT_BNEP_PROTO_FILTER=y
-CONFIG_BT_HIDP=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
-CONFIG_MTD_CONCAT=y
-CONFIG_MTD_PARTITIONS=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_AFS_PARTS=y
 CONFIG_MTD_CHAR=y
@@ -108,8 +96,6 @@ CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_NBD=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
-CONFIG_ATMEL_TCLIB=y
-CONFIG_EEPROM_LEGACY=m
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_BLK_DEV_SR=m
@@ -119,14 +105,23 @@ CONFIG_SCSI_MULTI_LUN=y
 # CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_NETDEVICES=y
 CONFIG_TUN=m
+CONFIG_ARM_AT91_ETHER=y
 CONFIG_PHYLIB=y
 CONFIG_DAVICOM_PHY=y
 CONFIG_SMSC_PHY=y
 CONFIG_MICREL_PHY=y
-CONFIG_NET_ETHERNET=y
-CONFIG_ARM_AT91_ETHER=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
+CONFIG_PPP=y
+CONFIG_PPP_BSDCOMP=y
+CONFIG_PPP_DEFLATE=y
+CONFIG_PPP_FILTER=y
+CONFIG_PPP_MPPE=m
+CONFIG_PPP_MULTILINK=y
+CONFIG_PPPOE=m
+CONFIG_PPP_ASYNC=y
+CONFIG_SLIP=m
+CONFIG_SLIP_COMPRESSED=y
+CONFIG_SLIP_SMART=y
+CONFIG_SLIP_MODE_SLIP6=y
 CONFIG_USB_CATC=m
 CONFIG_USB_KAWETH=m
 CONFIG_USB_PEGASUS=m
@@ -139,18 +134,6 @@ CONFIG_USB_NET_RNDIS_HOST=m
 CONFIG_USB_ALI_M5632=y
 CONFIG_USB_AN2720=y
 CONFIG_USB_EPSON2888=y
-CONFIG_PPP=y
-CONFIG_PPP_MULTILINK=y
-CONFIG_PPP_FILTER=y
-CONFIG_PPP_ASYNC=y
-CONFIG_PPP_DEFLATE=y
-CONFIG_PPP_BSDCOMP=y
-CONFIG_PPP_MPPE=m
-CONFIG_PPPOE=m
-CONFIG_SLIP=m
-CONFIG_SLIP_COMPRESSED=y
-CONFIG_SLIP_SMART=y
-CONFIG_SLIP_MODE_SLIP6=y
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_MOUSEDEV_SCREEN_X=640
 CONFIG_INPUT_MOUSEDEV_SCREEN_Y=480
@@ -158,9 +141,9 @@ CONFIG_INPUT_EVDEV=y
 CONFIG_KEYBOARD_GPIO=y
 # CONFIG_INPUT_MOUSE is not set
 CONFIG_INPUT_TOUCHSCREEN=y
+CONFIG_LEGACY_PTY_COUNT=32
 CONFIG_SERIAL_ATMEL=y
 CONFIG_SERIAL_ATMEL_CONSOLE=y
-CONFIG_LEGACY_PTY_COUNT=32
 CONFIG_HW_RANDOM=y
 CONFIG_I2C=y
 CONFIG_I2C_CHARDEV=y
@@ -290,7 +273,6 @@ CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
 CONFIG_ROOT_NFS=y
 CONFIG_NFSD=y
-CONFIG_SMB_FS=m
 CONFIG_CIFS=m
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_MAC_PARTITION=y
@@ -335,7 +317,6 @@ CONFIG_NLS_UTF8=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 # CONFIG_FTRACE is not set
 CONFIG_CRYPTO_PCBC=y
 CONFIG_CRYPTO_SHA1=y
diff --git a/arch/arm/configs/at91sam9260ek_defconfig b/arch/arm/configs/at91sam9260_defconfig
index f8a9226..505b376 100644
--- a/arch/arm/configs/at91sam9260ek_defconfig
+++ b/arch/arm/configs/at91sam9260_defconfig
@@ -12,11 +12,23 @@ CONFIG_MODULE_UNLOAD=y
 # CONFIG_IOSCHED_CFQ is not set
 CONFIG_ARCH_AT91=y
 CONFIG_ARCH_AT91SAM9260=y
+CONFIG_ARCH_AT91SAM9260_SAM9XE=y
 CONFIG_MACH_AT91SAM9260EK=y
+CONFIG_MACH_CAM60=y
+CONFIG_MACH_SAM9_L9260=y
+CONFIG_MACH_AFEB9260=y
+CONFIG_MACH_USB_A9260=y
+CONFIG_MACH_QIL_A9260=y
+CONFIG_MACH_CPU9260=y
+CONFIG_MACH_FLEXIBITY=y
+CONFIG_MACH_SNAPPER_9260=y
+CONFIG_MACH_AT91SAM_DT=y
 CONFIG_AT91_PROGRAMMABLE_CLOCKS=y
 # CONFIG_ARM_THUMB is not set
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_ARM_APPENDED_DTB=y
+CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_CMDLINE="mem=64M console=ttyS0,115200 initrd=0x21100000,3145728 root=/dev/ram0 rw"
 CONFIG_FPE_NWFPE=y
 CONFIG_NET=y
@@ -33,12 +45,10 @@ CONFIG_IP_PNP_BOOTP=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
-CONFIG_ATMEL_SSC=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_SCSI_MULTI_LUN=y
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
 CONFIG_MACB=y
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
@@ -55,7 +65,6 @@ CONFIG_I2C_GPIO=y
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_AT91SAM9X_WATCHDOG=y
-# CONFIG_VGA_CONSOLE is not set
 # CONFIG_USB_HID is not set
 CONFIG_USB=y
 CONFIG_USB_DEVICEFS=y
@@ -71,7 +80,6 @@ CONFIG_USB_G_SERIAL=m
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_AT91SAM9=y
 CONFIG_EXT2_FS=y
-CONFIG_INOTIFY=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 CONFIG_CRAMFS=y
diff --git a/arch/arm/configs/at91sam9g20ek_defconfig b/arch/arm/configs/at91sam9g20_defconfig
index 9e90e6d..9123568 100644
--- a/arch/arm/configs/at91sam9g20ek_defconfig
+++ b/arch/arm/configs/at91sam9g20_defconfig
@@ -14,6 +14,15 @@ CONFIG_ARCH_AT91=y
 CONFIG_ARCH_AT91SAM9G20=y
 CONFIG_MACH_AT91SAM9G20EK=y
 CONFIG_MACH_AT91SAM9G20EK_2MMC=y
+CONFIG_MACH_CPU9G20=y
+CONFIG_MACH_ACMENETUSFOXG20=y
+CONFIG_MACH_PORTUXG20=y
+CONFIG_MACH_STAMP9G20=y
+CONFIG_MACH_PCONTROL_G20=y
+CONFIG_MACH_GSIA18S=y
+CONFIG_MACH_USB_A9G20=y
+CONFIG_MACH_SNAPPER_9260=y
+CONFIG_MACH_AT91SAM_DT=y
 CONFIG_AT91_PROGRAMMABLE_CLOCKS=y
 # CONFIG_ARM_THUMB is not set
 CONFIG_AEABI=y
@@ -21,9 +30,10 @@ CONFIG_LEDS=y
 CONFIG_LEDS_CPU=y
 CONFIG_ZBOOT_ROM_TEXT=0x0
 CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_ARM_APPENDED_DTB=y
+CONFIG_ARM_ATAG_DTB_COMPAT=y
 CONFIG_CMDLINE="mem=64M console=ttyS0,115200 initrd=0x21100000,3145728 root=/dev/ram0 rw"
 CONFIG_FPE_NWFPE=y
-CONFIG_PM=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -37,8 +47,6 @@ CONFIG_IP_PNP_BOOTP=y
 # CONFIG_IPV6 is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
-CONFIG_MTD_CONCAT=y
-CONFIG_MTD_PARTITIONS=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
@@ -48,17 +56,13 @@ CONFIG_MTD_NAND_ATMEL=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_SIZE=8192
-CONFIG_ATMEL_SSC=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_SCSI_MULTI_LUN=y
 # CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
 CONFIG_MACB=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_MOUSEDEV_SCREEN_X=320
 CONFIG_INPUT_MOUSEDEV_SCREEN_Y=240
@@ -66,15 +70,14 @@ CONFIG_INPUT_EVDEV=y
 # CONFIG_KEYBOARD_ATKBD is not set
 CONFIG_KEYBOARD_GPIO=y
 # CONFIG_INPUT_MOUSE is not set
+CONFIG_LEGACY_PTY_COUNT=16
 CONFIG_SERIAL_ATMEL=y
 CONFIG_SERIAL_ATMEL_CONSOLE=y
-CONFIG_LEGACY_PTY_COUNT=16
 CONFIG_HW_RANDOM=y
 CONFIG_SPI=y
 CONFIG_SPI_ATMEL=y
 CONFIG_SPI_SPIDEV=y
 # CONFIG_HWMON is not set
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_SOUND=y
 CONFIG_SND=y
 CONFIG_SND_SEQUENCER=y
@@ -82,7 +85,6 @@ CONFIG_SND_MIXER_OSS=y
 CONFIG_SND_PCM_OSS=y
 CONFIG_SND_SEQUENCER_OSS=y
 # CONFIG_SND_VERBOSE_PROCFS is not set
-CONFIG_SND_AT73C213=y
 CONFIG_USB=y
 CONFIG_USB_DEVICEFS=y
 # CONFIG_USB_DEVICE_CLASS is not set
@@ -105,7 +107,6 @@ CONFIG_LEDS_TRIGGER_HEARTBEAT=y
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_AT91SAM9=y
 CONFIG_EXT2_FS=y
-CONFIG_INOTIFY=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
diff --git a/arch/arm/configs/at91sam9g45_defconfig b/arch/arm/configs/at91sam9g45_defconfig
index c5876d2..606d48f 100644
--- a/arch/arm/configs/at91sam9g45_defconfig
+++ b/arch/arm/configs/at91sam9g45_defconfig
@@ -18,6 +18,7 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_ARCH_AT91=y
 CONFIG_ARCH_AT91SAM9G45=y
 CONFIG_MACH_AT91SAM9M10G45EK=y
+CONFIG_MACH_AT91SAM_DT=y
 CONFIG_AT91_PROGRAMMABLE_CLOCKS=y
 CONFIG_AT91_SLOW_CLOCK=y
 CONFIG_AEABI=y
@@ -73,11 +74,8 @@ CONFIG_SCSI_MULTI_LUN=y
 # CONFIG_SCSI_LOWLEVEL is not set
 CONFIG_NETDEVICES=y
 CONFIG_MII=y
-CONFIG_DAVICOM_PHY=y
-CONFIG_NET_ETHERNET=y
 CONFIG_MACB=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
+CONFIG_DAVICOM_PHY=y
 CONFIG_LIBERTAS_THINFIRM=m
 CONFIG_LIBERTAS_THINFIRM_USB=m
 CONFIG_AT76C50X_USB=m
@@ -131,7 +129,6 @@ CONFIG_I2C_GPIO=y
 CONFIG_SPI=y
 CONFIG_SPI_ATMEL=y
 # CONFIG_HWMON is not set
-# CONFIG_MFD_SUPPORT is not set
 CONFIG_FB=y
 CONFIG_FB_ATMEL=y
 CONFIG_FB_UDL=m
diff --git a/arch/arm/configs/at91sam9rlek_defconfig b/arch/arm/configs/at91sam9rl_defconfig
index 75621e4..ad562ee 100644
--- a/arch/arm/configs/at91sam9rlek_defconfig
+++ b/arch/arm/configs/at91sam9rl_defconfig
@@ -23,8 +23,6 @@ CONFIG_NET=y
 CONFIG_UNIX=y
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 CONFIG_MTD=y
-CONFIG_MTD_CONCAT=y
-CONFIG_MTD_PARTITIONS=y
 CONFIG_MTD_CMDLINE_PARTS=y
 CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
@@ -35,7 +33,6 @@ CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_RAM=y
 CONFIG_BLK_DEV_RAM_COUNT=4
 CONFIG_BLK_DEV_RAM_SIZE=24576
-CONFIG_ATMEL_SSC=y
 CONFIG_SCSI=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_SCSI_MULTI_LUN=y
@@ -62,13 +59,11 @@ CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_AT91SAM9X_WATCHDOG=y
 CONFIG_FB=y
 CONFIG_FB_ATMEL=y
-# CONFIG_VGA_CONSOLE is not set
 CONFIG_MMC=y
 CONFIG_MMC_AT91=m
 CONFIG_RTC_CLASS=y
 CONFIG_RTC_DRV_AT91SAM9=y
 CONFIG_EXT2_FS=y
-CONFIG_INOTIFY=y
 CONFIG_MSDOS_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
diff --git a/arch/arm/configs/ezx_defconfig b/arch/arm/configs/ezx_defconfig
index 227a477..d95763d 100644
--- a/arch/arm/configs/ezx_defconfig
+++ b/arch/arm/configs/ezx_defconfig
@@ -287,7 +287,7 @@ CONFIG_USB=y
 # CONFIG_USB_DEVICE_CLASS is not set
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_PXA27X=y
+CONFIG_USB_PXA27X=y
 CONFIG_USB_ETH=m
 # CONFIG_USB_ETH_RNDIS is not set
 CONFIG_MMC=y
diff --git a/arch/arm/configs/imote2_defconfig b/arch/arm/configs/imote2_defconfig
index 176ec22..fd996bb 100644
--- a/arch/arm/configs/imote2_defconfig
+++ b/arch/arm/configs/imote2_defconfig
@@ -263,7 +263,7 @@ CONFIG_USB=y
 # CONFIG_USB_DEVICE_CLASS is not set
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_GADGET=y
-CONFIG_USB_GADGET_PXA27X=y
+CONFIG_USB_PXA27X=y
 CONFIG_USB_ETH=m
 # CONFIG_USB_ETH_RNDIS is not set
 CONFIG_MMC=y
diff --git a/arch/arm/configs/magician_defconfig b/arch/arm/configs/magician_defconfig
index a88e64d..443675d 100644
--- a/arch/arm/configs/magician_defconfig
+++ b/arch/arm/configs/magician_defconfig
@@ -132,7 +132,7 @@ CONFIG_USB_MON=m
 CONFIG_USB_OHCI_HCD=y
 CONFIG_USB_GADGET=y
 CONFIG_USB_GADGET_VBUS_DRAW=500
-CONFIG_USB_GADGET_PXA27X=y
+CONFIG_USB_PXA27X=y
 CONFIG_USB_ETH=m
 # CONFIG_USB_ETH_RNDIS is not set
 CONFIG_USB_GADGETFS=m
diff --git a/arch/arm/configs/omap1_defconfig b/arch/arm/configs/omap1_defconfig
index 7b63462..a7e7775 100644
--- a/arch/arm/configs/omap1_defconfig
+++ b/arch/arm/configs/omap1_defconfig
@@ -48,7 +48,6 @@ CONFIG_MACH_SX1=y
 CONFIG_MACH_NOKIA770=y
 CONFIG_MACH_AMS_DELTA=y
 CONFIG_MACH_OMAP_GENERIC=y
-CONFIG_OMAP_CLOCKS_SET_BY_BOOTLOADER=y
 CONFIG_OMAP_ARM_216MHZ=y
 CONFIG_OMAP_ARM_195MHZ=y
 CONFIG_OMAP_ARM_192MHZ=y
diff --git a/arch/arm/configs/u300_defconfig b/arch/arm/configs/u300_defconfig
index 4a5a126..374000e 100644
--- a/arch/arm/configs/u300_defconfig
+++ b/arch/arm/configs/u300_defconfig
@@ -14,8 +14,6 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_ARCH_U300=y
 CONFIG_MACH_U300=y
 CONFIG_MACH_U300_BS335=y
-CONFIG_MACH_U300_DUAL_RAM=y
-CONFIG_U300_DEBUG=y
 CONFIG_MACH_U300_SPIDUMMY=y
 CONFIG_NO_HZ=y
 CONFIG_HIGH_RES_TIMERS=y
@@ -26,19 +24,21 @@ CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_CMDLINE="root=/dev/ram0 rw rootfstype=rootfs console=ttyAMA0,115200n8 lpj=515072"
 CONFIG_CPU_IDLE=y
 CONFIG_FPE_NWFPE=y
-CONFIG_PM=y
 # CONFIG_SUSPEND is not set
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
 # CONFIG_PREVENT_FIRMWARE_BUILD is not set
-# CONFIG_MISC_DEVICES is not set
+CONFIG_MTD=y
+CONFIG_MTD_CMDLINE_PARTS=y
+CONFIG_MTD_NAND=y
+CONFIG_MTD_NAND_FSMC=y
 # CONFIG_INPUT_MOUSEDEV is not set
 CONFIG_INPUT_EVDEV=y
 # CONFIG_KEYBOARD_ATKBD is not set
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
+CONFIG_LEGACY_PTY_COUNT=16
 CONFIG_SERIAL_AMBA_PL011=y
 CONFIG_SERIAL_AMBA_PL011_CONSOLE=y
-CONFIG_LEGACY_PTY_COUNT=16
 # CONFIG_HW_RANDOM is not set
 CONFIG_I2C=y
 # CONFIG_HWMON is not set
@@ -51,6 +51,7 @@ CONFIG_BACKLIGHT_CLASS_DEVICE=y
 # CONFIG_HID_SUPPORT is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_MMC=y
+CONFIG_MMC_CLKGATE=y
 CONFIG_MMC_ARMMMCI=y
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_HCTOSYS is not set
@@ -65,10 +66,8 @@ CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_FS=y
-CONFIG_DEBUG_KERNEL=y
 # CONFIG_SCHED_DEBUG is not set
 CONFIG_TIMER_STATS=y
 # CONFIG_DEBUG_PREEMPT is not set
 CONFIG_DEBUG_INFO=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 # CONFIG_CRC32 is not set
diff --git a/arch/arm/configs/u8500_defconfig b/arch/arm/configs/u8500_defconfig
index 97d31a4..2d7b6e7 100644
--- a/arch/arm/configs/u8500_defconfig
+++ b/arch/arm/configs/u8500_defconfig
@@ -10,7 +10,7 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_ARCH_U8500=y
 CONFIG_UX500_SOC_DB5500=y
 CONFIG_UX500_SOC_DB8500=y
-CONFIG_MACH_U8500=y
+CONFIG_MACH_HREFV60=y
 CONFIG_MACH_SNOWBALL=y
 CONFIG_MACH_U5500=y
 CONFIG_NO_HZ=y
@@ -24,6 +24,7 @@ CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND=y
 CONFIG_VFP=y
 CONFIG_NEON=y
+CONFIG_PM_RUNTIME=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
@@ -41,11 +42,8 @@ CONFIG_MISC_DEVICES=y
 CONFIG_AB8500_PWM=y
 CONFIG_SENSORS_BH1780=y
 CONFIG_NETDEVICES=y
-CONFIG_SMSC_PHY=y
-CONFIG_NET_ETHERNET=y
 CONFIG_SMSC911X=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
+CONFIG_SMSC_PHY=y
 # CONFIG_WLAN is not set
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_EVDEV=y
@@ -72,15 +70,12 @@ CONFIG_SPI=y
 CONFIG_SPI_PL022=y
 CONFIG_GPIO_STMPE=y
 CONFIG_GPIO_TC3589X=y
-# CONFIG_HWMON is not set
 CONFIG_MFD_STMPE=y
 CONFIG_MFD_TC3589X=y
+CONFIG_AB5500_CORE=y
 CONFIG_AB8500_CORE=y
 CONFIG_REGULATOR_AB8500=y
 # CONFIG_HID_SUPPORT is not set
-CONFIG_USB_MUSB_HDRC=y
-CONFIG_USB_GADGET_MUSB_HDRC=y
-CONFIG_MUSB_PIO_ONLY=y
 CONFIG_USB_GADGET=y
 CONFIG_AB8500_USB=y
 CONFIG_MMC=y
@@ -97,6 +92,7 @@ CONFIG_DMADEVICES=y
 CONFIG_STE_DMA40=y
 CONFIG_STAGING=y
 CONFIG_TOUCHSCREEN_SYNAPTICS_I2C_RMI4=y
+CONFIG_HSEM_U8500=y
 CONFIG_EXT2_FS=y
 CONFIG_EXT2_FS_XATTR=y
 CONFIG_EXT2_FS_POSIX_ACL=y
diff --git a/arch/arm/configs/zeus_defconfig b/arch/arm/configs/zeus_defconfig
index 59577ad..547a3c1 100644
--- a/arch/arm/configs/zeus_defconfig
+++ b/arch/arm/configs/zeus_defconfig
@@ -140,7 +140,7 @@ CONFIG_USB_SERIAL=m
 CONFIG_USB_SERIAL_GENERIC=y
 CONFIG_USB_SERIAL_MCT_U232=m
 CONFIG_USB_GADGET=m
-CONFIG_USB_GADGET_PXA27X=y
+CONFIG_USB_PXA27X=y
 CONFIG_USB_ETH=m
 CONFIG_USB_GADGETFS=m
 CONFIG_USB_FILE_STORAGE=m
diff --git a/arch/arm/include/asm/hardware/cache-l2x0.h b/arch/arm/include/asm/hardware/cache-l2x0.h
index 1db1143..7df239b 100644
--- a/arch/arm/include/asm/hardware/cache-l2x0.h
+++ b/arch/arm/include/asm/hardware/cache-l2x0.h
@@ -20,6 +20,8 @@
 #ifndef __ASM_ARM_HARDWARE_L2X0_H
 #define __ASM_ARM_HARDWARE_L2X0_H
 
+#include <linux/errno.h>
+
 #define L2X0_CACHE_ID			0x000
 #define L2X0_CACHE_TYPE			0x004
 #define L2X0_CTRL			0x100
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 7d19425..2b0efc3 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -13,6 +13,7 @@
 struct tag;
 struct meminfo;
 struct sys_timer;
+struct pt_regs;
 
 struct machine_desc {
 	unsigned int		nr;		/* architecture number	*/
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index 71d99b8..0bda22c 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -55,16 +55,6 @@ reserve_pmu(enum arm_pmu_type type);
 extern void
 release_pmu(enum arm_pmu_type type);
 
-/**
- * init_pmu() - Initialise the PMU.
- *
- * Initialise the system ready for PMU enabling. This should typically set the
- * IRQ affinity and nothing else. The users (oprofile/perf events etc) will do
- * the actual hardware initialisation.
- */
-extern int
-init_pmu(enum arm_pmu_type type);
-
 #else /* CONFIG_CPU_HAS_PMU */
 
 #include <linux/err.h>
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index a7e457e..58b8b84 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -25,7 +25,7 @@ extern struct cputopo_arm cpu_topology[NR_CPUS];
 
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
+const struct cpumask *cpu_coregroup_mask(int cpu);
 
 #else
 
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index c60a294..4a11237 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -402,6 +402,8 @@
 #define __NR_syncfs			(__NR_SYSCALL_BASE+373)
 #define __NR_sendmmsg			(__NR_SYSCALL_BASE+374)
 #define __NR_setns			(__NR_SYSCALL_BASE+375)
+#define __NR_process_vm_readv		(__NR_SYSCALL_BASE+376)
+#define __NR_process_vm_writev		(__NR_SYSCALL_BASE+377)
 
 /*
  * The following SWIs are ARM private.
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index 9943e9e..463ff4a 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -385,6 +385,8 @@
 		CALL(sys_syncfs)
 		CALL(sys_sendmmsg)
 /* 375 */	CALL(sys_setns)
+		CALL(sys_process_vm_readv)
+		CALL(sys_process_vm_writev)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 9ad50c4..b145f16 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -497,7 +497,7 @@ ENDPROC(__und_usr)
 	.popsection
 	.pushsection __ex_table,"a"
 	.long	1b, 4b
-#if __LINUX_ARM_ARCH__ >= 7
+#if CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7
 	.long	2b, 4b
 	.long	3b, 4b
 #endif
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 566c54c..08c82fd 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -360,7 +360,7 @@ __secondary_data:
  *  r13 = *virtual* address to jump to upon completion
  */
 __enable_mmu:
-#ifdef CONFIG_ALIGNMENT_TRAP
+#if defined(CONFIG_ALIGNMENT_TRAP) && __LINUX_ARM_ARCH__ < 6
 	orr	r0, r0, #CR_A
 #else
 	bic	r0, r0, #CR_A
diff --git a/arch/arm/kernel/kprobes-arm.c b/arch/arm/kernel/kprobes-arm.c
index 9fe8910..8a30c89 100644
--- a/arch/arm/kernel/kprobes-arm.c
+++ b/arch/arm/kernel/kprobes-arm.c
@@ -519,10 +519,12 @@ static const union decode_item arm_cccc_0000_____1001_table[] = {
 static const union decode_item arm_cccc_0001_____1001_table[] = {
 	/* Synchronization primitives					*/
 
+#if __LINUX_ARM_ARCH__ < 6
+	/* Deprecated on ARMv6 and may be UNDEFINED on v7		*/
 	/* SMP/SWPB		cccc 0001 0x00 xxxx xxxx xxxx 1001 xxxx */
 	DECODE_EMULATEX	(0x0fb000f0, 0x01000090, emulate_rd12rn16rm0_rwflags_nopc,
 						 REGS(NOPC, NOPC, 0, 0, NOPC)),
-
+#endif
 	/* LDREX/STREX{,D,B,H}	cccc 0001 1xxx xxxx xxxx xxxx 1001 xxxx */
 	/* And unallocated instructions...				*/
 	DECODE_END
diff --git a/arch/arm/kernel/kprobes-test-arm.c b/arch/arm/kernel/kprobes-test-arm.c
index fc82de8..ba32b39 100644
--- a/arch/arm/kernel/kprobes-test-arm.c
+++ b/arch/arm/kernel/kprobes-test-arm.c
@@ -427,18 +427,25 @@ void kprobe_arm_test_cases(void)
 
 	TEST_GROUP("Synchronization primitives")
 
-	/*
-	 * Use hard coded constants for SWP instructions to avoid warnings
-	 * about deprecated instructions.
-	 */
-	TEST_RP( ".word 0xe108e097 @ swp	lr, r",7,VAL2,", [r",8,0,"]")
-	TEST_R(  ".word 0x610d0091 @ swpvs	r0, r",1,VAL1,", [sp]")
-	TEST_RP( ".word 0xe10cd09e @ swp	sp, r",14,VAL2,", [r",12,13*4,"]")
+#if __LINUX_ARM_ARCH__ < 6
+	TEST_RP("swp	lr, r",7,VAL2,", [r",8,0,"]")
+	TEST_R( "swpvs	r0, r",1,VAL1,", [sp]")
+	TEST_RP("swp	sp, r",14,VAL2,", [r",12,13*4,"]")
+#else
+	TEST_UNSUPPORTED(".word 0xe108e097 @ swp	lr, r7, [r8]")
+	TEST_UNSUPPORTED(".word 0x610d0091 @ swpvs	r0, r1, [sp]")
+	TEST_UNSUPPORTED(".word 0xe10cd09e @ swp	sp, r14 [r12]")
+#endif
 	TEST_UNSUPPORTED(".word 0xe102f091 @ swp pc, r1, [r2]")
 	TEST_UNSUPPORTED(".word 0xe102009f @ swp r0, pc, [r2]")
 	TEST_UNSUPPORTED(".word 0xe10f0091 @ swp r0, r1, [pc]")
-	TEST_RP( ".word 0xe148e097 @ swpb	lr, r",7,VAL2,", [r",8,0,"]")
-	TEST_R(  ".word 0x614d0091 @ swpvsb	r0, r",1,VAL1,", [sp]")
+#if __LINUX_ARM_ARCH__ < 6
+	TEST_RP("swpb	lr, r",7,VAL2,", [r",8,0,"]")
+	TEST_R( "swpvsb	r0, r",1,VAL1,", [sp]")
+#else
+	TEST_UNSUPPORTED(".word 0xe148e097 @ swpb	lr, r7, [r8]")
+	TEST_UNSUPPORTED(".word 0x614d0091 @ swpvsb	r0, r1, [sp]")
+#endif
 	TEST_UNSUPPORTED(".word 0xe142f091 @ swpb pc, r1, [r2]")
 
 	TEST_UNSUPPORTED(".word	0xe1100090") /* Unallocated space */
@@ -550,7 +557,7 @@ void kprobe_arm_test_cases(void)
 	TEST_RPR(  "strccd	r",8, VAL2,", [r",13,0, ", r",12,48,"]")
 	TEST_RPR(  "strd	r",4, VAL1,", [r",2, 24,", r",3, 48,"]!")
 	TEST_RPR(  "strcsd	r",12,VAL2,", [r",11,48,", -r",10,24,"]!")
-	TEST_RPR(  "strd	r",2, VAL1,", [r",3, 24,"], r",4,48,"")
+	TEST_RPR(  "strd	r",2, VAL1,", [r",5, 24,"], r",4,48,"")
 	TEST_RPR(  "strd	r",10,VAL2,", [r",9, 48,"], -r",7,24,"")
 	TEST_UNSUPPORTED(".word 0xe1afc0fa	@ strd r12, [pc, r10]!")
 
diff --git a/arch/arm/kernel/kprobes-test-thumb.c b/arch/arm/kernel/kprobes-test-thumb.c
index 5e726c3..5d8b857 100644
--- a/arch/arm/kernel/kprobes-test-thumb.c
+++ b/arch/arm/kernel/kprobes-test-thumb.c
@@ -222,8 +222,8 @@ void kprobe_thumb16_test_cases(void)
 DONT_TEST_IN_ITBLOCK(
 	TEST_BF_R(  "cbnz	r",0,0, ", 2f")
 	TEST_BF_R(  "cbz	r",2,-1,", 2f")
-	TEST_BF_RX( "cbnz	r",4,1, ", 2f",0x20)
-	TEST_BF_RX( "cbz	r",7,0, ", 2f",0x40)
+	TEST_BF_RX( "cbnz	r",4,1, ", 2f", SPACE_0x20)
+	TEST_BF_RX( "cbz	r",7,0, ", 2f", SPACE_0x40)
 )
 	TEST_R("sxth	r0, r",7, HH1,"")
 	TEST_R("sxth	r7, r",0, HH2,"")
@@ -246,7 +246,7 @@ DONT_TEST_IN_ITBLOCK(
 	TESTCASE_START(code)		\
 	TEST_ARG_PTR(13, offset)	\
 	TEST_ARG_END("")		\
-	TEST_BRANCH_F(code,0)		\
+	TEST_BRANCH_F(code)		\
 	TESTCASE_END
 
 	TEST("push	{r0}")
@@ -319,8 +319,8 @@ CONDITION_INSTRUCTIONS(8,
 
 	TEST_BF(  "b	2f")
 	TEST_BB(  "b	2b")
-	TEST_BF_X("b	2f", 0x400)
-	TEST_BB_X("b	2b", 0x400)
+	TEST_BF_X("b	2f", SPACE_0x400)
+	TEST_BB_X("b	2b", SPACE_0x400)
 
 	TEST_GROUP("Testing instructions in IT blocks")
 
@@ -746,7 +746,7 @@ CONDITION_INSTRUCTIONS(22,
 	TEST_BB("bne.w	2b")
 	TEST_BF("bgt.w	2f")
 	TEST_BB("blt.w	2b")
-	TEST_BF_X("bpl.w	2f",0x1000)
+	TEST_BF_X("bpl.w	2f", SPACE_0x1000)
 )
 
 	TEST_UNSUPPORTED("msr	cpsr, r0")
@@ -786,11 +786,11 @@ CONDITION_INSTRUCTIONS(22,
 
 	TEST_BF(  "b.w	2f")
 	TEST_BB(  "b.w	2b")
-	TEST_BF_X("b.w	2f", 0x1000)
+	TEST_BF_X("b.w	2f", SPACE_0x1000)
 
 	TEST_BF(  "bl.w	2f")
 	TEST_BB(  "bl.w	2b")
-	TEST_BB_X("bl.w	2b", 0x1000)
+	TEST_BB_X("bl.w	2b", SPACE_0x1000)
 
 	TEST_X(	"blx	__dummy_arm_subroutine",
 		".arm				\n\t"
diff --git a/arch/arm/kernel/kprobes-test.h b/arch/arm/kernel/kprobes-test.h
index 0dc5d77..e28a869 100644
--- a/arch/arm/kernel/kprobes-test.h
+++ b/arch/arm/kernel/kprobes-test.h
@@ -149,23 +149,31 @@ struct test_arg_end {
 	"1:	"instruction"				\n\t"	\
 	"	nop					\n\t"
 
-#define TEST_BRANCH_F(instruction, xtra_dist)			\
+#define TEST_BRANCH_F(instruction)				\
 	TEST_INSTRUCTION(instruction)				\
-	".if "#xtra_dist"				\n\t"	\
 	"	b	99f				\n\t"	\
-	".space "#xtra_dist"				\n\t"	\
-	".endif						\n\t"	\
+	"2:	nop					\n\t"
+
+#define TEST_BRANCH_B(instruction)				\
+	"	b	50f				\n\t"	\
+	"	b	99f				\n\t"	\
+	"2:	nop					\n\t"	\
+	"	b	99f				\n\t"	\
+	TEST_INSTRUCTION(instruction)
+
+#define TEST_BRANCH_FX(instruction, codex)			\
+	TEST_INSTRUCTION(instruction)				\
+	"	b	99f				\n\t"	\
+	codex"						\n\t"	\
 	"	b	99f				\n\t"	\
 	"2:	nop					\n\t"
 
-#define TEST_BRANCH_B(instruction, xtra_dist)			\
+#define TEST_BRANCH_BX(instruction, codex)			\
 	"	b	50f				\n\t"	\
 	"	b	99f				\n\t"	\
 	"2:	nop					\n\t"	\
 	"	b	99f				\n\t"	\
-	".if "#xtra_dist"				\n\t"	\
-	".space "#xtra_dist"				\n\t"	\
-	".endif						\n\t"	\
+	codex"						\n\t"	\
 	TEST_INSTRUCTION(instruction)
 
 #define TESTCASE_END						\
@@ -301,47 +309,60 @@ struct test_arg_end {
 	TESTCASE_START(code1 #reg1 code2)	\
 	TEST_ARG_PTR(reg1, val1)		\
 	TEST_ARG_END("")			\
-	TEST_BRANCH_F(code1 #reg1 code2, 0)	\
+	TEST_BRANCH_F(code1 #reg1 code2)	\
 	TESTCASE_END
 
-#define TEST_BF_X(code, xtra_dist)		\
+#define TEST_BF(code)				\
 	TESTCASE_START(code)			\
 	TEST_ARG_END("")			\
-	TEST_BRANCH_F(code, xtra_dist)		\
+	TEST_BRANCH_F(code)			\
 	TESTCASE_END
 
-#define TEST_BB_X(code, xtra_dist)		\
+#define TEST_BB(code)				\
 	TESTCASE_START(code)			\
 	TEST_ARG_END("")			\
-	TEST_BRANCH_B(code, xtra_dist)		\
+	TEST_BRANCH_B(code)			\
 	TESTCASE_END
 
-#define TEST_BF_RX(code1, reg, val, code2, xtra_dist)	\
-	TESTCASE_START(code1 #reg code2)		\
-	TEST_ARG_REG(reg, val)				\
-	TEST_ARG_END("")				\
-	TEST_BRANCH_F(code1 #reg code2, xtra_dist)	\
+#define TEST_BF_R(code1, reg, val, code2)	\
+	TESTCASE_START(code1 #reg code2)	\
+	TEST_ARG_REG(reg, val)			\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_F(code1 #reg code2)		\
 	TESTCASE_END
 
-#define TEST_BB_RX(code1, reg, val, code2, xtra_dist)	\
-	TESTCASE_START(code1 #reg code2)		\
-	TEST_ARG_REG(reg, val)				\
-	TEST_ARG_END("")				\
-	TEST_BRANCH_B(code1 #reg code2, xtra_dist)	\
+#define TEST_BB_R(code1, reg, val, code2)	\
+	TESTCASE_START(code1 #reg code2)	\
+	TEST_ARG_REG(reg, val)			\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_B(code1 #reg code2)		\
 	TESTCASE_END
 
-#define TEST_BF(code)	TEST_BF_X(code, 0)
-#define TEST_BB(code)	TEST_BB_X(code, 0)
-
-#define TEST_BF_R(code1, reg, val, code2) TEST_BF_RX(code1, reg, val, code2, 0)
-#define TEST_BB_R(code1, reg, val, code2) TEST_BB_RX(code1, reg, val, code2, 0)
-
 #define TEST_BF_RR(code1, reg1, val1, code2, reg2, val2, code3)	\
 	TESTCASE_START(code1 #reg1 code2 #reg2 code3)		\
 	TEST_ARG_REG(reg1, val1)				\
 	TEST_ARG_REG(reg2, val2)				\
 	TEST_ARG_END("")					\
-	TEST_BRANCH_F(code1 #reg1 code2 #reg2 code3, 0)		\
+	TEST_BRANCH_F(code1 #reg1 code2 #reg2 code3)		\
+	TESTCASE_END
+
+#define TEST_BF_X(code, codex)			\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_FX(code, codex)		\
+	TESTCASE_END
+
+#define TEST_BB_X(code, codex)			\
+	TESTCASE_START(code)			\
+	TEST_ARG_END("")			\
+	TEST_BRANCH_BX(code, codex)		\
+	TESTCASE_END
+
+#define TEST_BF_RX(code1, reg, val, code2, codex)	\
+	TESTCASE_START(code1 #reg code2)		\
+	TEST_ARG_REG(reg, val)				\
+	TEST_ARG_END("")				\
+	TEST_BRANCH_FX(code1 #reg code2, codex)		\
 	TESTCASE_END
 
 #define TEST_X(code, codex)			\
@@ -372,6 +393,25 @@ struct test_arg_end {
 	TESTCASE_END
 
 
+/*
+ * Macros for defining space directives spread over multiple lines.
+ * These are required so the compiler guesses better the length of inline asm
+ * code and will spill the literal pool early enough to avoid generating PC
+ * relative loads with out of range offsets.
+ */
+#define TWICE(x)	x x
+#define SPACE_0x8	TWICE(".space 4\n\t")
+#define SPACE_0x10	TWICE(SPACE_0x8)
+#define SPACE_0x20	TWICE(SPACE_0x10)
+#define SPACE_0x40	TWICE(SPACE_0x20)
+#define SPACE_0x80	TWICE(SPACE_0x40)
+#define SPACE_0x100	TWICE(SPACE_0x80)
+#define SPACE_0x200	TWICE(SPACE_0x100)
+#define SPACE_0x400	TWICE(SPACE_0x200)
+#define SPACE_0x800	TWICE(SPACE_0x400)
+#define SPACE_0x1000	TWICE(SPACE_0x800)
+
+
 /* Various values used in test cases... */
 #define N(val)	(val ^ 0xffffffff)
 #define VAL1	0x12345678
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index c1b4463..e59bbd4 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -32,24 +32,6 @@ static atomic_t waiting_for_crash_ipi;
 
 int machine_kexec_prepare(struct kimage *image)
 {
-	unsigned long page_list;
-	void *reboot_code_buffer;
-	page_list = image->head & PAGE_MASK;
-
-	reboot_code_buffer = page_address(image->control_code_page);
-
-	/* Prepare parameters for reboot_code_buffer*/
-	kexec_start_address = image->start;
-	kexec_indirection_page = page_list;
-	kexec_mach_type = machine_arch_type;
-	kexec_boot_atags = image->start - KEXEC_ARM_ZIMAGE_OFFSET + KEXEC_ARM_ATAGS_OFFSET;
-
-	/* copy our kernel relocation code to the control code page */
-	memcpy(reboot_code_buffer,
-	       relocate_new_kernel, relocate_new_kernel_size);
-
-	flush_icache_range((unsigned long) reboot_code_buffer,
-			   (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE);
 	return 0;
 }
 
@@ -100,14 +82,31 @@ void (*kexec_reinit)(void);
 
 void machine_kexec(struct kimage *image)
 {
+	unsigned long page_list;
 	unsigned long reboot_code_buffer_phys;
 	void *reboot_code_buffer;
 
+
+	page_list = image->head & PAGE_MASK;
+
 	/* we need both effective and real address here */
 	reboot_code_buffer_phys =
 	    page_to_pfn(image->control_code_page) << PAGE_SHIFT;
 	reboot_code_buffer = page_address(image->control_code_page);
 
+	/* Prepare parameters for reboot_code_buffer*/
+	kexec_start_address = image->start;
+	kexec_indirection_page = page_list;
+	kexec_mach_type = machine_arch_type;
+	kexec_boot_atags = image->start - KEXEC_ARM_ZIMAGE_OFFSET + KEXEC_ARM_ATAGS_OFFSET;
+
+	/* copy our kernel relocation code to the control code page */
+	memcpy(reboot_code_buffer,
+	       relocate_new_kernel, relocate_new_kernel_size);
+
+
+	flush_icache_range((unsigned long) reboot_code_buffer,
+			   (unsigned long) reboot_code_buffer + KEXEC_CONTROL_PAGE_SIZE);
 	printk(KERN_INFO "Bye!\n");
 
 	if (kexec_reinit)
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 24e2347..8e9c98e 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -343,19 +343,25 @@ validate_group(struct perf_event *event)
 {
 	struct perf_event *sibling, *leader = event->group_leader;
 	struct pmu_hw_events fake_pmu;
+	DECLARE_BITMAP(fake_used_mask, ARMPMU_MAX_HWEVENTS);
 
-	memset(&fake_pmu, 0, sizeof(fake_pmu));
+	/*
+	 * Initialise the fake PMU. We only need to populate the
+	 * used_mask for the purposes of validation.
+	 */
+	memset(fake_used_mask, 0, sizeof(fake_used_mask));
+	fake_pmu.used_mask = fake_used_mask;
 
 	if (!validate_event(&fake_pmu, leader))
-		return -ENOSPC;
+		return -EINVAL;
 
 	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
 		if (!validate_event(&fake_pmu, sibling))
-			return -ENOSPC;
+			return -EINVAL;
 	}
 
 	if (!validate_event(&fake_pmu, event))
-		return -ENOSPC;
+		return -EINVAL;
 
 	return 0;
 }
@@ -396,6 +402,9 @@ armpmu_reserve_hardware(struct arm_pmu *armpmu)
 	int i, err, irq, irqs;
 	struct platform_device *pmu_device = armpmu->plat_device;
 
+	if (!pmu_device)
+		return -ENODEV;
+
 	err = reserve_pmu(armpmu->type);
 	if (err) {
 		pr_warning("unable to reserve pmu\n");
diff --git a/arch/arm/kernel/pmu.c b/arch/arm/kernel/pmu.c
index 2c3407e..2334bf8 100644
--- a/arch/arm/kernel/pmu.c
+++ b/arch/arm/kernel/pmu.c
@@ -33,3 +33,4 @@ release_pmu(enum arm_pmu_type type)
 {
 	clear_bit_unlock(type, pmu_lock);
 }
+EXPORT_SYMBOL_GPL(release_pmu);
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 75316f0..3d0c6fb 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -192,6 +192,9 @@ void cpu_idle(void)
 #endif
 
 			local_irq_disable();
+#ifdef CONFIG_PL310_ERRATA_769419
+			wmb();
+#endif
 			if (hlt_counter) {
 				local_irq_enable();
 				cpu_relax();
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 7e7977a..3448a3f 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -461,8 +461,10 @@ static void __init setup_processor(void)
 	       cpu_name, read_cpuid_id(), read_cpuid_id() & 15,
 	       proc_arch[cpu_architecture()], cr_alignment);
 
-	sprintf(init_utsname()->machine, "%s%c", list->arch_name, ENDIANNESS);
-	sprintf(elf_platform, "%s%c", list->elf_name, ENDIANNESS);
+	snprintf(init_utsname()->machine, __NEW_UTS_LEN + 1, "%s%c",
+		 list->arch_name, ENDIANNESS);
+	snprintf(elf_platform, ELF_PLATFORM_SIZE, "%s%c",
+		 list->elf_name, ENDIANNESS);
 	elf_hwcap = list->elf_hwcap;
 #ifndef CONFIG_ARM_THUMB
 	elf_hwcap &= ~HWCAP_THUMB;
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 1040c00..8200dea 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -43,7 +43,7 @@
 
 struct cputopo_arm cpu_topology[NR_CPUS];
 
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
+const struct cpumask *cpu_coregroup_mask(int cpu)
 {
 	return &cpu_topology[cpu].core_sibling;
 }
diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h
index 10d868a..d6408d1 100644
--- a/arch/arm/lib/bitops.h
+++ b/arch/arm/lib/bitops.h
@@ -1,5 +1,9 @@
+#include <asm/unwind.h>
+
 #if __LINUX_ARM_ARCH__ >= 6
-	.macro	bitop, instr
+	.macro	bitop, name, instr
+ENTRY(	\name		)
+UNWIND(	.fnstart	)
 	ands	ip, r1, #3
 	strneb	r1, [ip]		@ assert word-aligned
 	mov	r2, #1
@@ -13,9 +17,13 @@
 	cmp	r0, #0
 	bne	1b
 	bx	lr
+UNWIND(	.fnend		)
+ENDPROC(\name		)
 	.endm
 
-	.macro	testop, instr, store
+	.macro	testop, name, instr, store
+ENTRY(	\name		)
+UNWIND(	.fnstart	)
 	ands	ip, r1, #3
 	strneb	r1, [ip]		@ assert word-aligned
 	mov	r2, #1
@@ -34,9 +42,13 @@
 	cmp	r0, #0
 	movne	r0, #1
 2:	bx	lr
+UNWIND(	.fnend		)
+ENDPROC(\name		)
 	.endm
 #else
-	.macro	bitop, instr
+	.macro	bitop, name, instr
+ENTRY(	\name		)
+UNWIND(	.fnstart	)
 	ands	ip, r1, #3
 	strneb	r1, [ip]		@ assert word-aligned
 	and	r2, r0, #31
@@ -49,6 +61,8 @@
 	str	r2, [r1, r0, lsl #2]
 	restore_irqs ip
 	mov	pc, lr
+UNWIND(	.fnend		)
+ENDPROC(\name		)
 	.endm
 
 /**
@@ -59,7 +73,9 @@
  * Note: we can trivially conditionalise the store instruction
  * to avoid dirtying the data cache.
  */
-	.macro	testop, instr, store
+	.macro	testop, name, instr, store
+ENTRY(	\name		)
+UNWIND(	.fnstart	)
 	ands	ip, r1, #3
 	strneb	r1, [ip]		@ assert word-aligned
 	and	r3, r0, #31
@@ -73,5 +89,7 @@
 	moveq	r0, #0
 	restore_irqs ip
 	mov	pc, lr
+UNWIND(	.fnend		)
+ENDPROC(\name		)
 	.endm
 #endif
diff --git a/arch/arm/lib/changebit.S b/arch/arm/lib/changebit.S
index 68ed5b6..f402786 100644
--- a/arch/arm/lib/changebit.S
+++ b/arch/arm/lib/changebit.S
@@ -12,6 +12,4 @@
 #include "bitops.h"
                 .text
 
-ENTRY(_change_bit)
-	bitop	eor
-ENDPROC(_change_bit)
+bitop	_change_bit, eor
diff --git a/arch/arm/lib/clearbit.S b/arch/arm/lib/clearbit.S
index 4c04c3b..f6b75fb 100644
--- a/arch/arm/lib/clearbit.S
+++ b/arch/arm/lib/clearbit.S
@@ -12,6 +12,4 @@
 #include "bitops.h"
                 .text
 
-ENTRY(_clear_bit)
-	bitop	bic
-ENDPROC(_clear_bit)
+bitop	_clear_bit, bic
diff --git a/arch/arm/lib/setbit.S b/arch/arm/lib/setbit.S
index bbee5c6..618feda 100644
--- a/arch/arm/lib/setbit.S
+++ b/arch/arm/lib/setbit.S
@@ -12,6 +12,4 @@
 #include "bitops.h"
 		.text
 
-ENTRY(_set_bit)
-	bitop	orr
-ENDPROC(_set_bit)
+bitop	_set_bit, orr
diff --git a/arch/arm/lib/testchangebit.S b/arch/arm/lib/testchangebit.S
index 15a4d43..4becdc3 100644
--- a/arch/arm/lib/testchangebit.S
+++ b/arch/arm/lib/testchangebit.S
@@ -12,6 +12,4 @@
 #include "bitops.h"
                 .text
 
-ENTRY(_test_and_change_bit)
-	testop	eor, str
-ENDPROC(_test_and_change_bit)
+testop	_test_and_change_bit, eor, str
diff --git a/arch/arm/lib/testclearbit.S b/arch/arm/lib/testclearbit.S
index 521b66b..918841d 100644
--- a/arch/arm/lib/testclearbit.S
+++ b/arch/arm/lib/testclearbit.S
@@ -12,6 +12,4 @@
 #include "bitops.h"
                 .text
 
-ENTRY(_test_and_clear_bit)
-	testop	bicne, strne
-ENDPROC(_test_and_clear_bit)
+testop	_test_and_clear_bit, bicne, strne
diff --git a/arch/arm/lib/testsetbit.S b/arch/arm/lib/testsetbit.S
index 1c98cc2..8d1b2fe 100644
--- a/arch/arm/lib/testsetbit.S
+++ b/arch/arm/lib/testsetbit.S
@@ -12,6 +12,4 @@
 #include "bitops.h"
                 .text
 
-ENTRY(_test_and_set_bit)
-	testop	orreq, streq
-ENDPROC(_test_and_set_bit)
+testop	_test_and_set_bit, orreq, streq
diff --git a/arch/arm/mach-bcmring/core.c b/arch/arm/mach-bcmring/core.c
index 43eadbc..430da12 100644
--- a/arch/arm/mach-bcmring/core.c
+++ b/arch/arm/mach-bcmring/core.c
@@ -235,7 +235,7 @@ void __init bcmring_init_timer(void)
 	 */
 	bcmring_clocksource_init();
 
-	sp804_clockevents_register(TIMER0_VA_BASE, IRQ_TIMER0, "timer0");
+	sp804_clockevents_init(TIMER0_VA_BASE, IRQ_TIMER0, "timer0");
 }
 
 struct sys_timer bcmring_timer = {
diff --git a/arch/arm/mach-bcmring/dma.c b/arch/arm/mach-bcmring/dma.c
index b52b8de..f4d4d6d 100644
--- a/arch/arm/mach-bcmring/dma.c
+++ b/arch/arm/mach-bcmring/dma.c
@@ -36,6 +36,7 @@
 #include <linux/mm.h>
 #include <linux/pfn.h>
 #include <linux/atomic.h>
+#include <linux/sched.h>
 #include <mach/dma.h>
 
 /* I don't quite understand why dc4 fails when this is set to 1 and DMA is enabled */
diff --git a/arch/arm/mach-exynos/cpuidle.c b/arch/arm/mach-exynos/cpuidle.c
index 35f6502..4ebb382 100644
--- a/arch/arm/mach-exynos/cpuidle.c
+++ b/arch/arm/mach-exynos/cpuidle.c
@@ -12,6 +12,8 @@
 #include <linux/init.h>
 #include <linux/cpuidle.h>
 #include <linux/io.h>
+#include <linux/export.h>
+#include <linux/time.h>
 
 #include <asm/proc-fns.h>
 
diff --git a/arch/arm/mach-highbank/highbank.c b/arch/arm/mach-highbank/highbank.c
index b82dcf0..88660d5 100644
--- a/arch/arm/mach-highbank/highbank.c
+++ b/arch/arm/mach-highbank/highbank.c
@@ -22,6 +22,7 @@
 #include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/of_address.h>
+#include <linux/smp.h>
 
 #include <asm/cacheflush.h>
 #include <asm/unified.h>
@@ -72,6 +73,9 @@ static void __init highbank_map_io(void)
 
 void highbank_set_cpu_jump(int cpu, void *jump_addr)
 {
+#ifdef CONFIG_SMP
+	cpu = cpu_logical_map(cpu);
+#endif
 	writel(BSYM(virt_to_phys(jump_addr)), HB_JUMP_TABLE_VIRT(cpu));
 	__cpuc_flush_dcache_area(HB_JUMP_TABLE_VIRT(cpu), 16);
 	outer_clean_range(HB_JUMP_TABLE_PHYS(cpu),
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index 5f7f9c2..c44aa97 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -10,11 +10,6 @@ config HAVE_IMX_MMDC
 config HAVE_IMX_SRC
 	bool
 
-#
-# ARCH_MX31 and ARCH_MX35 are left for compatibility
-# Some usages assume that having one of them implies not having (e.g.) ARCH_MX2.
-# To easily distinguish good and reviewed from unreviewed usages new (and IMHO
-# more sensible) names are used: SOC_IMX31 and SOC_IMX35
 config ARCH_MX1
 	bool
 
@@ -27,12 +22,6 @@ config ARCH_MX25
 config MACH_MX27
 	bool
 
-config ARCH_MX31
-	bool
-
-config ARCH_MX35
-	bool
-
 config SOC_IMX1
 	bool
 	select ARCH_MX1
@@ -72,7 +61,6 @@ config SOC_IMX31
 	select CPU_V6
 	select IMX_HAVE_PLATFORM_MXC_RNGA
 	select ARCH_MXC_AUDMUX_V2
-	select ARCH_MX31
 	select MXC_AVIC
 	select SMP_ON_UP if SMP
 
@@ -82,7 +70,6 @@ config SOC_IMX35
 	select ARCH_MXC_IOMUX_V3
 	select ARCH_MXC_AUDMUX_V2
 	select HAVE_EPIT
-	select ARCH_MX35
 	select MXC_AVIC
 	select SMP_ON_UP if SMP
 
diff --git a/arch/arm/mach-imx/clock-imx6q.c b/arch/arm/mach-imx/clock-imx6q.c
index 613a1b9..039a7ab 100644
--- a/arch/arm/mach-imx/clock-imx6q.c
+++ b/arch/arm/mach-imx/clock-imx6q.c
@@ -1953,14 +1953,17 @@ static struct map_desc imx6q_clock_desc[] = {
 	imx_map_entry(MX6Q, ANATOP, MT_DEVICE),
 };
 
+void __init imx6q_clock_map_io(void)
+{
+	iotable_init(imx6q_clock_desc, ARRAY_SIZE(imx6q_clock_desc));
+}
+
 int __init mx6q_clocks_init(void)
 {
 	struct device_node *np;
 	void __iomem *base;
 	int i, irq;
 
-	iotable_init(imx6q_clock_desc, ARRAY_SIZE(imx6q_clock_desc));
-
 	/* retrieve the freqency of fixed clocks from device tree */
 	for_each_compatible_node(np, NULL, "fixed-clock") {
 		u32 rate;
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index 8bf5fa3..9cd860a 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -34,6 +34,7 @@ static void __init imx6q_map_io(void)
 {
 	imx_lluart_map_io();
 	imx_scu_map_io();
+	imx6q_clock_map_io();
 }
 
 static void __init imx6q_gpio_add_irq_domain(struct device_node *np,
diff --git a/arch/arm/mach-imx/mm-imx3.c b/arch/arm/mach-imx/mm-imx3.c
index 9f0e82e..31807d2 100644
--- a/arch/arm/mach-imx/mm-imx3.c
+++ b/arch/arm/mach-imx/mm-imx3.c
@@ -33,29 +33,32 @@
 static void imx3_idle(void)
 {
 	unsigned long reg = 0;
-	__asm__ __volatile__(
-		/* disable I and D cache */
-		"mrc p15, 0, %0, c1, c0, 0\n"
-		"bic %0, %0, #0x00001000\n"
-		"bic %0, %0, #0x00000004\n"
-		"mcr p15, 0, %0, c1, c0, 0\n"
-		/* invalidate I cache */
-		"mov %0, #0\n"
-		"mcr p15, 0, %0, c7, c5, 0\n"
-		/* clear and invalidate D cache */
-		"mov %0, #0\n"
-		"mcr p15, 0, %0, c7, c14, 0\n"
-		/* WFI */
-		"mov %0, #0\n"
-		"mcr p15, 0, %0, c7, c0, 4\n"
-		"nop\n" "nop\n" "nop\n" "nop\n"
-		"nop\n" "nop\n" "nop\n"
-		/* enable I and D cache */
-		"mrc p15, 0, %0, c1, c0, 0\n"
-		"orr %0, %0, #0x00001000\n"
-		"orr %0, %0, #0x00000004\n"
-		"mcr p15, 0, %0, c1, c0, 0\n"
-		: "=r" (reg));
+
+	if (!need_resched())
+		__asm__ __volatile__(
+			/* disable I and D cache */
+			"mrc p15, 0, %0, c1, c0, 0\n"
+			"bic %0, %0, #0x00001000\n"
+			"bic %0, %0, #0x00000004\n"
+			"mcr p15, 0, %0, c1, c0, 0\n"
+			/* invalidate I cache */
+			"mov %0, #0\n"
+			"mcr p15, 0, %0, c7, c5, 0\n"
+			/* clear and invalidate D cache */
+			"mov %0, #0\n"
+			"mcr p15, 0, %0, c7, c14, 0\n"
+			/* WFI */
+			"mov %0, #0\n"
+			"mcr p15, 0, %0, c7, c0, 4\n"
+			"nop\n" "nop\n" "nop\n" "nop\n"
+			"nop\n" "nop\n" "nop\n"
+			/* enable I and D cache */
+			"mrc p15, 0, %0, c1, c0, 0\n"
+			"orr %0, %0, #0x00001000\n"
+			"orr %0, %0, #0x00000004\n"
+			"mcr p15, 0, %0, c1, c0, 0\n"
+			: "=r" (reg));
+	local_irq_enable();
 }
 
 static void __iomem *imx3_ioremap(unsigned long phys_addr, size_t size,
@@ -108,6 +111,7 @@ void imx3_init_l2x0(void)
 	l2x0_init(l2x0_base, 0x00030024, 0x00000000);
 }
 
+#ifdef CONFIG_SOC_IMX31
 static struct map_desc mx31_io_desc[] __initdata = {
 	imx_map_entry(MX31, X_MEMC, MT_DEVICE),
 	imx_map_entry(MX31, AVIC, MT_DEVICE_NONSHARED),
@@ -126,33 +130,11 @@ void __init mx31_map_io(void)
 	iotable_init(mx31_io_desc, ARRAY_SIZE(mx31_io_desc));
 }
 
-static struct map_desc mx35_io_desc[] __initdata = {
-	imx_map_entry(MX35, X_MEMC, MT_DEVICE),
-	imx_map_entry(MX35, AVIC, MT_DEVICE_NONSHARED),
-	imx_map_entry(MX35, AIPS1, MT_DEVICE_NONSHARED),
-	imx_map_entry(MX35, AIPS2, MT_DEVICE_NONSHARED),
-	imx_map_entry(MX35, SPBA0, MT_DEVICE_NONSHARED),
-};
-
-void __init mx35_map_io(void)
-{
-	iotable_init(mx35_io_desc, ARRAY_SIZE(mx35_io_desc));
-}
-
 void __init imx31_init_early(void)
 {
 	mxc_set_cpu_type(MXC_CPU_MX31);
 	mxc_arch_reset_init(MX31_IO_ADDRESS(MX31_WDOG_BASE_ADDR));
-	imx_idle = imx3_idle;
-	imx_ioremap = imx3_ioremap;
-}
-
-void __init imx35_init_early(void)
-{
-	mxc_set_cpu_type(MXC_CPU_MX35);
-	mxc_iomux_v3_init(MX35_IO_ADDRESS(MX35_IOMUXC_BASE_ADDR));
-	mxc_arch_reset_init(MX35_IO_ADDRESS(MX35_WDOG_BASE_ADDR));
-	imx_idle = imx3_idle;
+	pm_idle = imx3_idle;
 	imx_ioremap = imx3_ioremap;
 }
 
@@ -161,11 +143,6 @@ void __init mx31_init_irq(void)
 	mxc_init_irq(MX31_IO_ADDRESS(MX31_AVIC_BASE_ADDR));
 }
 
-void __init mx35_init_irq(void)
-{
-	mxc_init_irq(MX35_IO_ADDRESS(MX35_AVIC_BASE_ADDR));
-}
-
 static struct sdma_script_start_addrs imx31_to1_sdma_script __initdata = {
 	.per_2_per_addr = 1677,
 };
@@ -199,6 +176,35 @@ void __init imx31_soc_init(void)
 
 	imx_add_imx_sdma("imx31-sdma", MX31_SDMA_BASE_ADDR, MX31_INT_SDMA, &imx31_sdma_pdata);
 }
+#endif /* ifdef CONFIG_SOC_IMX31 */
+
+#ifdef CONFIG_SOC_IMX35
+static struct map_desc mx35_io_desc[] __initdata = {
+	imx_map_entry(MX35, X_MEMC, MT_DEVICE),
+	imx_map_entry(MX35, AVIC, MT_DEVICE_NONSHARED),
+	imx_map_entry(MX35, AIPS1, MT_DEVICE_NONSHARED),
+	imx_map_entry(MX35, AIPS2, MT_DEVICE_NONSHARED),
+	imx_map_entry(MX35, SPBA0, MT_DEVICE_NONSHARED),
+};
+
+void __init mx35_map_io(void)
+{
+	iotable_init(mx35_io_desc, ARRAY_SIZE(mx35_io_desc));
+}
+
+void __init imx35_init_early(void)
+{
+	mxc_set_cpu_type(MXC_CPU_MX35);
+	mxc_iomux_v3_init(MX35_IO_ADDRESS(MX35_IOMUXC_BASE_ADDR));
+	mxc_arch_reset_init(MX35_IO_ADDRESS(MX35_WDOG_BASE_ADDR));
+	pm_idle = imx3_idle;
+	imx_ioremap = imx3_ioremap;
+}
+
+void __init mx35_init_irq(void)
+{
+	mxc_init_irq(MX35_IO_ADDRESS(MX35_AVIC_BASE_ADDR));
+}
 
 static struct sdma_script_start_addrs imx35_to1_sdma_script __initdata = {
 	.ap_2_ap_addr = 642,
@@ -254,3 +260,4 @@ void __init imx35_soc_init(void)
 
 	imx_add_imx_sdma("imx35-sdma", MX35_SDMA_BASE_ADDR, MX35_INT_SDMA, &imx35_sdma_pdata);
 }
+#endif /* ifdef CONFIG_SOC_IMX35 */
diff --git a/arch/arm/mach-imx/src.c b/arch/arm/mach-imx/src.c
index 36cacbd..a8e3368 100644
--- a/arch/arm/mach-imx/src.c
+++ b/arch/arm/mach-imx/src.c
@@ -14,6 +14,7 @@
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
+#include <linux/smp.h>
 #include <asm/unified.h>
 
 #define SRC_SCR				0x000
@@ -23,10 +24,15 @@
 
 static void __iomem *src_base;
 
+#ifndef CONFIG_SMP
+#define cpu_logical_map(cpu)		0
+#endif
+
 void imx_enable_cpu(int cpu, bool enable)
 {
 	u32 mask, val;
 
+	cpu = cpu_logical_map(cpu);
 	mask = 1 << (BP_SRC_SCR_CORE1_ENABLE + cpu - 1);
 	val = readl_relaxed(src_base + SRC_SCR);
 	val = enable ? val | mask : val & ~mask;
@@ -35,6 +41,7 @@ void imx_enable_cpu(int cpu, bool enable)
 
 void imx_set_cpu_jump(int cpu, void *jump_addr)
 {
+	cpu = cpu_logical_map(cpu);
 	writel_relaxed(BSYM(virt_to_phys(jump_addr)),
 		       src_base + SRC_GPR1 + cpu * 8);
 }
diff --git a/arch/arm/mach-mmp/gplugd.c b/arch/arm/mach-mmp/gplugd.c
index 6915656..4665767 100644
--- a/arch/arm/mach-mmp/gplugd.c
+++ b/arch/arm/mach-mmp/gplugd.c
@@ -182,7 +182,7 @@ static void __init gplugd_init(void)
 
 	/* on-chip devices */
 	pxa168_add_uart(3);
-	pxa168_add_ssp(0);
+	pxa168_add_ssp(1);
 	pxa168_add_twsi(0, NULL, ARRAY_AND_SIZE(gplugd_i2c_board_info));
 
 	pxa168_add_eth(&gplugd_eth_platform_data);
diff --git a/arch/arm/mach-mmp/include/mach/gpio-pxa.h b/arch/arm/mach-mmp/include/mach/gpio-pxa.h
index d14eeaf..99b4ce1 100644
--- a/arch/arm/mach-mmp/include/mach/gpio-pxa.h
+++ b/arch/arm/mach-mmp/include/mach/gpio-pxa.h
@@ -7,7 +7,7 @@
 #define GPIO_REGS_VIRT	(APB_VIRT_BASE + 0x19000)
 
 #define BANK_OFF(n)	(((n) < 3) ? (n) << 2 : 0x100 + (((n) - 3) << 2))
-#define GPIO_REG(x)	(GPIO_REGS_VIRT + (x))
+#define GPIO_REG(x)	(*(volatile u32 *)(GPIO_REGS_VIRT + (x)))
 
 #define NR_BUILTIN_GPIO		IRQ_GPIO_NUM
 
diff --git a/arch/arm/mach-mx5/cpu.c b/arch/arm/mach-mx5/cpu.c
index 5c53282..5e2e7a8 100644
--- a/arch/arm/mach-mx5/cpu.c
+++ b/arch/arm/mach-mx5/cpu.c
@@ -16,7 +16,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <mach/hardware.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 static int mx5_cpu_rev = -1;
 
@@ -67,7 +67,8 @@ static int __init mx51_neon_fixup(void)
 	if (!cpu_is_mx51())
 		return 0;
 
-	if (mx51_revision() < IMX_CHIP_REVISION_3_0 && (elf_hwcap & HWCAP_NEON)) {
+	if (mx51_revision() < IMX_CHIP_REVISION_3_0 &&
+			(elf_hwcap & HWCAP_NEON)) {
 		elf_hwcap &= ~HWCAP_NEON;
 		pr_info("Turning off NEON support, detected broken NEON implementation\n");
 	}
diff --git a/arch/arm/mach-mx5/mm.c b/arch/arm/mach-mx5/mm.c
index 26eacc9..df4a508f 100644
--- a/arch/arm/mach-mx5/mm.c
+++ b/arch/arm/mach-mx5/mm.c
@@ -23,7 +23,9 @@
 
 static void imx5_idle(void)
 {
-	mx5_cpu_lp_set(WAIT_UNCLOCKED_POWER_OFF);
+	if (!need_resched())
+		mx5_cpu_lp_set(WAIT_UNCLOCKED_POWER_OFF);
+	local_irq_enable();
 }
 
 /*
@@ -89,7 +91,7 @@ void __init imx51_init_early(void)
 	mxc_set_cpu_type(MXC_CPU_MX51);
 	mxc_iomux_v3_init(MX51_IO_ADDRESS(MX51_IOMUXC_BASE_ADDR));
 	mxc_arch_reset_init(MX51_IO_ADDRESS(MX51_WDOG1_BASE_ADDR));
-	imx_idle = imx5_idle;
+	pm_idle = imx5_idle;
 }
 
 void __init imx53_init_early(void)
diff --git a/arch/arm/mach-mxs/clock-mx28.c b/arch/arm/mach-mxs/clock-mx28.c
index 229ae34..da6e4aa 100644
--- a/arch/arm/mach-mxs/clock-mx28.c
+++ b/arch/arm/mach-mxs/clock-mx28.c
@@ -404,7 +404,7 @@ static int name##_set_rate(struct clk *clk, unsigned long rate)		\
 	reg = __raw_readl(CLKCTRL_BASE_ADDR + HW_CLKCTRL_##dr);		\
 	reg &= ~BM_CLKCTRL_##dr##_DIV;					\
 	reg |= div << BP_CLKCTRL_##dr##_DIV;				\
-	if (reg | (1 << clk->enable_shift)) {				\
+	if (reg & (1 << clk->enable_shift)) {				\
 		pr_err("%s: clock is gated\n", __func__);		\
 		return -EINVAL;						\
 	}								\
diff --git a/arch/arm/mach-omap1/Kconfig b/arch/arm/mach-omap1/Kconfig
index e0a0281..73f287d 100644
--- a/arch/arm/mach-omap1/Kconfig
+++ b/arch/arm/mach-omap1/Kconfig
@@ -171,14 +171,6 @@ config MACH_OMAP_GENERIC
 comment "OMAP CPU Speed"
 	depends on ARCH_OMAP1
 
-config OMAP_CLOCKS_SET_BY_BOOTLOADER
-	bool "OMAP clocks set by bootloader"
-	depends on ARCH_OMAP1
-	help
-	  Enable this option to prevent the kernel from overriding the clock
-	  frequencies programmed by bootloader for MPU, DSP, MMUs, TC,
-	  internal LCD controller and MPU peripherals.
-
 config OMAP_ARM_216MHZ
 	bool "OMAP ARM 216 MHz CPU (1710 only)"
         depends on ARCH_OMAP1 && ARCH_OMAP16XX
diff --git a/arch/arm/mach-omap1/board-ams-delta.c b/arch/arm/mach-omap1/board-ams-delta.c
index 51bae31..b0f15d2 100644
--- a/arch/arm/mach-omap1/board-ams-delta.c
+++ b/arch/arm/mach-omap1/board-ams-delta.c
@@ -302,8 +302,6 @@ static void __init ams_delta_init(void)
 	omap_cfg_reg(J19_1610_CAM_D6);
 	omap_cfg_reg(J18_1610_CAM_D7);
 
-	iotable_init(ams_delta_io_desc, ARRAY_SIZE(ams_delta_io_desc));
-
 	omap_board_config = ams_delta_config;
 	omap_board_config_size = ARRAY_SIZE(ams_delta_config);
 	omap_serial_init();
@@ -373,10 +371,16 @@ static int __init ams_delta_modem_init(void)
 }
 arch_initcall(ams_delta_modem_init);
 
+static void __init ams_delta_map_io(void)
+{
+	omap15xx_map_io();
+	iotable_init(ams_delta_io_desc, ARRAY_SIZE(ams_delta_io_desc));
+}
+
 MACHINE_START(AMS_DELTA, "Amstrad E3 (Delta)")
 	/* Maintainer: Jonathan McDowell <noodles@earth.li> */
 	.atag_offset	= 0x100,
-	.map_io		= omap15xx_map_io,
+	.map_io		= ams_delta_map_io,
 	.init_early	= omap1_init_early,
 	.reserve	= omap_reserve,
 	.init_irq	= omap1_init_irq,
diff --git a/arch/arm/mach-omap1/clock.h b/arch/arm/mach-omap1/clock.h
index eaf09ef..16b1423 100644
--- a/arch/arm/mach-omap1/clock.h
+++ b/arch/arm/mach-omap1/clock.h
@@ -17,7 +17,8 @@
 
 #include <plat/clock.h>
 
-extern int __init omap1_clk_init(void);
+int omap1_clk_init(void);
+void omap1_clk_late_init(void);
 extern int omap1_clk_enable(struct clk *clk);
 extern void omap1_clk_disable(struct clk *clk);
 extern long omap1_clk_round_rate(struct clk *clk, unsigned long rate);
diff --git a/arch/arm/mach-omap1/clock_data.c b/arch/arm/mach-omap1/clock_data.c
index 92400b9..1297bb5 100644
--- a/arch/arm/mach-omap1/clock_data.c
+++ b/arch/arm/mach-omap1/clock_data.c
@@ -767,6 +767,15 @@ static struct clk_functions omap1_clk_functions = {
 	.clk_disable_unused	= omap1_clk_disable_unused,
 };
 
+static void __init omap1_show_rates(void)
+{
+	pr_notice("Clocking rate (xtal/DPLL1/MPU): "
+			"%ld.%01ld/%ld.%01ld/%ld.%01ld MHz\n",
+		ck_ref.rate / 1000000, (ck_ref.rate / 100000) % 10,
+		ck_dpll1.rate / 1000000, (ck_dpll1.rate / 100000) % 10,
+		arm_ck.rate / 1000000, (arm_ck.rate / 100000) % 10);
+}
+
 int __init omap1_clk_init(void)
 {
 	struct omap_clk *c;
@@ -835,9 +844,12 @@ int __init omap1_clk_init(void)
 	/* We want to be in syncronous scalable mode */
 	omap_writew(0x1000, ARM_SYSST);
 
-#ifdef CONFIG_OMAP_CLOCKS_SET_BY_BOOTLOADER
-	/* Use values set by bootloader. Determine PLL rate and recalculate
-	 * dependent clocks as if kernel had changed PLL or divisors.
+
+	/*
+	 * Initially use the values set by bootloader. Determine PLL rate and
+	 * recalculate dependent clocks as if kernel had changed PLL or
+	 * divisors. See also omap1_clk_late_init() that can reprogram dpll1
+	 * after the SRAM is initialized.
 	 */
 	{
 		unsigned pll_ctl_val = omap_readw(DPLL_CTL);
@@ -862,25 +874,10 @@ int __init omap1_clk_init(void)
 			}
 		}
 	}
-#else
-	/* Find the highest supported frequency and enable it */
-	if (omap1_select_table_rate(&virtual_ck_mpu, ~0)) {
-		printk(KERN_ERR "System frequencies not set. Check your config.\n");
-		/* Guess sane values (60MHz) */
-		omap_writew(0x2290, DPLL_CTL);
-		omap_writew(cpu_is_omap7xx() ? 0x3005 : 0x1005, ARM_CKCTL);
-		ck_dpll1.rate = 60000000;
-	}
-#endif
 	propagate_rate(&ck_dpll1);
 	/* Cache rates for clocks connected to ck_ref (not dpll1) */
 	propagate_rate(&ck_ref);
-	printk(KERN_INFO "Clocking rate (xtal/DPLL1/MPU): "
-		"%ld.%01ld/%ld.%01ld/%ld.%01ld MHz\n",
-	       ck_ref.rate / 1000000, (ck_ref.rate / 100000) % 10,
-	       ck_dpll1.rate / 1000000, (ck_dpll1.rate / 100000) % 10,
-	       arm_ck.rate / 1000000, (arm_ck.rate / 100000) % 10);
-
+	omap1_show_rates();
 	if (machine_is_omap_perseus2() || machine_is_omap_fsample()) {
 		/* Select slicer output as OMAP input clock */
 		omap_writew(omap_readw(OMAP7XX_PCC_UPLD_CTRL) & ~0x1,
@@ -925,3 +922,21 @@ int __init omap1_clk_init(void)
 
 	return 0;
 }
+
+#define OMAP1_DPLL1_SANE_VALUE	60000000
+
+void __init omap1_clk_late_init(void)
+{
+	if (ck_dpll1.rate >= OMAP1_DPLL1_SANE_VALUE)
+		return;
+
+	/* Find the highest supported frequency and enable it */
+	if (omap1_select_table_rate(&virtual_ck_mpu, ~0)) {
+		pr_err("System frequencies not set, using default. Check your config.\n");
+		omap_writew(0x2290, DPLL_CTL);
+		omap_writew(cpu_is_omap7xx() ? 0x3005 : 0x1005, ARM_CKCTL);
+		ck_dpll1.rate = OMAP1_DPLL1_SANE_VALUE;
+	}
+	propagate_rate(&ck_dpll1);
+	omap1_show_rates();
+}
diff --git a/arch/arm/mach-omap1/devices.c b/arch/arm/mach-omap1/devices.c
index 48ef988..475cb2f 100644
--- a/arch/arm/mach-omap1/devices.c
+++ b/arch/arm/mach-omap1/devices.c
@@ -30,6 +30,8 @@
 #include <plat/omap7xx.h>
 #include <plat/mcbsp.h>
 
+#include "clock.h"
+
 /*-------------------------------------------------------------------------*/
 
 #if defined(CONFIG_RTC_DRV_OMAP) || defined(CONFIG_RTC_DRV_OMAP_MODULE)
@@ -293,6 +295,7 @@ static int __init omap1_init_devices(void)
 		return -ENODEV;
 
 	omap_sram_init();
+	omap1_clk_late_init();
 
 	/* please keep these calls, and their implementations above,
 	 * in alphabetical order so they're easier to sort through.
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 5034147..e1293aa 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -334,6 +334,7 @@ config MACH_OMAP4_PANDA
 config OMAP3_EMU
 	bool "OMAP3 debugging peripherals"
 	depends on ARCH_OMAP3
+	select ARM_AMBA
 	select OC_ETM
 	help
 	  Say Y here to enable debugging hardware of omap3
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index 69ab1c0..b009f17 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -4,7 +4,7 @@
 
 # Common support
 obj-y := id.o io.o control.o mux.o devices.o serial.o gpmc.o timer.o pm.o \
-	 common.o gpio.o dma.o wd_timer.o
+	 common.o gpio.o dma.o wd_timer.o display.o
 
 omap-2-3-common				= irq.o sdrc.o
 hwmod-common				= omap_hwmod.o \
@@ -264,7 +264,4 @@ smsc911x-$(CONFIG_SMSC911X)		:= gpmc-smsc911x.o
 obj-y					+= $(smsc911x-m) $(smsc911x-y)
 obj-$(CONFIG_ARCH_OMAP4)		+= hwspinlock.o
 
-disp-$(CONFIG_OMAP2_DSS)		:= display.o
-obj-y					+= $(disp-m) $(disp-y)
-
 obj-y					+= common-board-devices.o twl-common.o
diff --git a/arch/arm/mach-omap2/cpuidle34xx.c b/arch/arm/mach-omap2/cpuidle34xx.c
index 1fe35c2..942bb4f 100644
--- a/arch/arm/mach-omap2/cpuidle34xx.c
+++ b/arch/arm/mach-omap2/cpuidle34xx.c
@@ -24,6 +24,7 @@
 
 #include <linux/sched.h>
 #include <linux/cpuidle.h>
+#include <linux/export.h>
 
 #include <plat/prcm.h>
 #include <plat/irqs.h>
diff --git a/arch/arm/mach-omap2/display.c b/arch/arm/mach-omap2/display.c
index adb2756..dce9905 100644
--- a/arch/arm/mach-omap2/display.c
+++ b/arch/arm/mach-omap2/display.c
@@ -27,8 +27,35 @@
 #include <plat/omap_hwmod.h>
 #include <plat/omap_device.h>
 #include <plat/omap-pm.h>
+#include <plat/common.h>
 
 #include "control.h"
+#include "display.h"
+
+#define DISPC_CONTROL		0x0040
+#define DISPC_CONTROL2		0x0238
+#define DISPC_IRQSTATUS		0x0018
+
+#define DSS_SYSCONFIG		0x10
+#define DSS_SYSSTATUS		0x14
+#define DSS_CONTROL		0x40
+#define DSS_SDI_CONTROL		0x44
+#define DSS_PLL_CONTROL		0x48
+
+#define LCD_EN_MASK		(0x1 << 0)
+#define DIGIT_EN_MASK		(0x1 << 1)
+
+#define FRAMEDONE_IRQ_SHIFT	0
+#define EVSYNC_EVEN_IRQ_SHIFT	2
+#define EVSYNC_ODD_IRQ_SHIFT	3
+#define FRAMEDONE2_IRQ_SHIFT	22
+#define FRAMEDONETV_IRQ_SHIFT	24
+
+/*
+ * FRAMEDONE_IRQ_TIMEOUT: how long (in milliseconds) to wait during DISPC
+ *     reset before deciding that something has gone wrong
+ */
+#define FRAMEDONE_IRQ_TIMEOUT		100
 
 static struct platform_device omap_display_device = {
 	.name          = "omapdss",
@@ -172,3 +199,135 @@ int __init omap_display_init(struct omap_dss_board_info *board_data)
 
 	return r;
 }
+
+static void dispc_disable_outputs(void)
+{
+	u32 v, irq_mask = 0;
+	bool lcd_en, digit_en, lcd2_en = false;
+	int i;
+	struct omap_dss_dispc_dev_attr *da;
+	struct omap_hwmod *oh;
+
+	oh = omap_hwmod_lookup("dss_dispc");
+	if (!oh) {
+		WARN(1, "display: could not disable outputs during reset - could not find dss_dispc hwmod\n");
+		return;
+	}
+
+	if (!oh->dev_attr) {
+		pr_err("display: could not disable outputs during reset due to missing dev_attr\n");
+		return;
+	}
+
+	da = (struct omap_dss_dispc_dev_attr *)oh->dev_attr;
+
+	/* store value of LCDENABLE and DIGITENABLE bits */
+	v = omap_hwmod_read(oh, DISPC_CONTROL);
+	lcd_en = v & LCD_EN_MASK;
+	digit_en = v & DIGIT_EN_MASK;
+
+	/* store value of LCDENABLE for LCD2 */
+	if (da->manager_count > 2) {
+		v = omap_hwmod_read(oh, DISPC_CONTROL2);
+		lcd2_en = v & LCD_EN_MASK;
+	}
+
+	if (!(lcd_en | digit_en | lcd2_en))
+		return; /* no managers currently enabled */
+
+	/*
+	 * If any manager was enabled, we need to disable it before
+	 * DSS clocks are disabled or DISPC module is reset
+	 */
+	if (lcd_en)
+		irq_mask |= 1 << FRAMEDONE_IRQ_SHIFT;
+
+	if (digit_en) {
+		if (da->has_framedonetv_irq) {
+			irq_mask |= 1 << FRAMEDONETV_IRQ_SHIFT;
+		} else {
+			irq_mask |= 1 << EVSYNC_EVEN_IRQ_SHIFT |
+				1 << EVSYNC_ODD_IRQ_SHIFT;
+		}
+	}
+
+	if (lcd2_en)
+		irq_mask |= 1 << FRAMEDONE2_IRQ_SHIFT;
+
+	/*
+	 * clear any previous FRAMEDONE, FRAMEDONETV,
+	 * EVSYNC_EVEN/ODD or FRAMEDONE2 interrupts
+	 */
+	omap_hwmod_write(irq_mask, oh, DISPC_IRQSTATUS);
+
+	/* disable LCD and TV managers */
+	v = omap_hwmod_read(oh, DISPC_CONTROL);
+	v &= ~(LCD_EN_MASK | DIGIT_EN_MASK);
+	omap_hwmod_write(v, oh, DISPC_CONTROL);
+
+	/* disable LCD2 manager */
+	if (da->manager_count > 2) {
+		v = omap_hwmod_read(oh, DISPC_CONTROL2);
+		v &= ~LCD_EN_MASK;
+		omap_hwmod_write(v, oh, DISPC_CONTROL2);
+	}
+
+	i = 0;
+	while ((omap_hwmod_read(oh, DISPC_IRQSTATUS) & irq_mask) !=
+	       irq_mask) {
+		i++;
+		if (i > FRAMEDONE_IRQ_TIMEOUT) {
+			pr_err("didn't get FRAMEDONE1/2 or TV interrupt\n");
+			break;
+		}
+		mdelay(1);
+	}
+}
+
+#define MAX_MODULE_SOFTRESET_WAIT	10000
+int omap_dss_reset(struct omap_hwmod *oh)
+{
+	struct omap_hwmod_opt_clk *oc;
+	int c = 0;
+	int i, r;
+
+	if (!(oh->class->sysc->sysc_flags & SYSS_HAS_RESET_STATUS)) {
+		pr_err("dss_core: hwmod data doesn't contain reset data\n");
+		return -EINVAL;
+	}
+
+	for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
+		if (oc->_clk)
+			clk_enable(oc->_clk);
+
+	dispc_disable_outputs();
+
+	/* clear SDI registers */
+	if (cpu_is_omap3430()) {
+		omap_hwmod_write(0x0, oh, DSS_SDI_CONTROL);
+		omap_hwmod_write(0x0, oh, DSS_PLL_CONTROL);
+	}
+
+	/*
+	 * clear DSS_CONTROL register to switch DSS clock sources to
+	 * PRCM clock, if any
+	 */
+	omap_hwmod_write(0x0, oh, DSS_CONTROL);
+
+	omap_test_timeout((omap_hwmod_read(oh, oh->class->sysc->syss_offs)
+				& SYSS_RESETDONE_MASK),
+			MAX_MODULE_SOFTRESET_WAIT, c);
+
+	if (c == MAX_MODULE_SOFTRESET_WAIT)
+		pr_warning("dss_core: waiting for reset to finish failed\n");
+	else
+		pr_debug("dss_core: softreset done\n");
+
+	for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++)
+		if (oc->_clk)
+			clk_disable(oc->_clk);
+
+	r = (c == MAX_MODULE_SOFTRESET_WAIT) ? -ETIMEDOUT : 0;
+
+	return r;
+}
diff --git a/arch/arm/mach-omap2/display.h b/arch/arm/mach-omap2/display.h
new file mode 100644
index 0000000..b871b017
--- /dev/null
+++ b/arch/arm/mach-omap2/display.h
@@ -0,0 +1,29 @@
+/*
+ * display.h - OMAP2+ integration-specific DSS header
+ *
+ * Copyright (C) 2011 Texas Instruments, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARCH_ARM_MACH_OMAP2_DISPLAY_H
+#define __ARCH_ARM_MACH_OMAP2_DISPLAY_H
+
+#include <linux/kernel.h>
+
+struct omap_dss_dispc_dev_attr {
+	u8	manager_count;
+	bool	has_framedonetv_irq;
+};
+
+#endif
diff --git a/arch/arm/mach-omap2/io.h b/arch/arm/mach-omap2/io.h
deleted file mode 100644
index e69de29..0000000
--- a/arch/arm/mach-omap2/io.h
+++ /dev/null
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 6b3088d..207a2ff 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -749,7 +749,7 @@ static int _count_mpu_irqs(struct omap_hwmod *oh)
 		ohii = &oh->mpu_irqs[i++];
 	} while (ohii->irq != -1);
 
-	return i;
+	return i-1;
 }
 
 /**
@@ -772,7 +772,7 @@ static int _count_sdma_reqs(struct omap_hwmod *oh)
 		ohdi = &oh->sdma_reqs[i++];
 	} while (ohdi->dma_req != -1);
 
-	return i;
+	return i-1;
 }
 
 /**
@@ -795,7 +795,7 @@ static int _count_ocp_if_addr_spaces(struct omap_hwmod_ocp_if *os)
 		mem = &os->addr[i++];
 	} while (mem->pa_start != mem->pa_end);
 
-	return i;
+	return i-1;
 }
 
 /**
diff --git a/arch/arm/mach-omap2/omap_hwmod_2420_data.c b/arch/arm/mach-omap2/omap_hwmod_2420_data.c
index 6d72062..a5409ce 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2420_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2420_data.c
@@ -875,6 +875,10 @@ static struct omap_hwmod_ocp_if *omap2420_dss_slaves[] = {
 };
 
 static struct omap_hwmod_opt_clk dss_opt_clks[] = {
+	/*
+	 * The DSS HW needs all DSS clocks enabled during reset. The dss_core
+	 * driver does not use these clocks.
+	 */
 	{ .role = "tv_clk", .clk = "dss_54m_fck" },
 	{ .role = "sys_clk", .clk = "dss2_fck" },
 };
@@ -899,7 +903,7 @@ static struct omap_hwmod omap2420_dss_core_hwmod = {
 	.slaves_cnt	= ARRAY_SIZE(omap2420_dss_slaves),
 	.masters	= omap2420_dss_masters,
 	.masters_cnt	= ARRAY_SIZE(omap2420_dss_masters),
-	.flags		= HWMOD_NO_IDLEST,
+	.flags		= HWMOD_NO_IDLEST | HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 };
 
 /* l4_core -> dss_dispc */
@@ -939,6 +943,7 @@ static struct omap_hwmod omap2420_dss_dispc_hwmod = {
 	.slaves		= omap2420_dss_dispc_slaves,
 	.slaves_cnt	= ARRAY_SIZE(omap2420_dss_dispc_slaves),
 	.flags		= HWMOD_NO_IDLEST,
+	.dev_attr	= &omap2_3_dss_dispc_dev_attr
 };
 
 /* l4_core -> dss_rfbi */
@@ -961,6 +966,10 @@ static struct omap_hwmod_ocp_if *omap2420_dss_rfbi_slaves[] = {
 	&omap2420_l4_core__dss_rfbi,
 };
 
+static struct omap_hwmod_opt_clk dss_rfbi_opt_clks[] = {
+	{ .role = "ick", .clk = "dss_ick" },
+};
+
 static struct omap_hwmod omap2420_dss_rfbi_hwmod = {
 	.name		= "dss_rfbi",
 	.class		= &omap2_rfbi_hwmod_class,
@@ -972,6 +981,8 @@ static struct omap_hwmod omap2420_dss_rfbi_hwmod = {
 			.module_offs = CORE_MOD,
 		},
 	},
+	.opt_clks	= dss_rfbi_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(dss_rfbi_opt_clks),
 	.slaves		= omap2420_dss_rfbi_slaves,
 	.slaves_cnt	= ARRAY_SIZE(omap2420_dss_rfbi_slaves),
 	.flags		= HWMOD_NO_IDLEST,
@@ -981,7 +992,7 @@ static struct omap_hwmod omap2420_dss_rfbi_hwmod = {
 static struct omap_hwmod_ocp_if omap2420_l4_core__dss_venc = {
 	.master		= &omap2420_l4_core_hwmod,
 	.slave		= &omap2420_dss_venc_hwmod,
-	.clk		= "dss_54m_fck",
+	.clk		= "dss_ick",
 	.addr		= omap2_dss_venc_addrs,
 	.fw = {
 		.omap2 = {
@@ -1001,7 +1012,7 @@ static struct omap_hwmod_ocp_if *omap2420_dss_venc_slaves[] = {
 static struct omap_hwmod omap2420_dss_venc_hwmod = {
 	.name		= "dss_venc",
 	.class		= &omap2_venc_hwmod_class,
-	.main_clk	= "dss1_fck",
+	.main_clk	= "dss_54m_fck",
 	.prcm		= {
 		.omap2 = {
 			.prcm_reg_id = 1,
diff --git a/arch/arm/mach-omap2/omap_hwmod_2430_data.c b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
index a2580d0..c4f56cb 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2430_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2430_data.c
@@ -942,6 +942,10 @@ static struct omap_hwmod_ocp_if *omap2430_dss_slaves[] = {
 };
 
 static struct omap_hwmod_opt_clk dss_opt_clks[] = {
+	/*
+	 * The DSS HW needs all DSS clocks enabled during reset. The dss_core
+	 * driver does not use these clocks.
+	 */
 	{ .role = "tv_clk", .clk = "dss_54m_fck" },
 	{ .role = "sys_clk", .clk = "dss2_fck" },
 };
@@ -966,7 +970,7 @@ static struct omap_hwmod omap2430_dss_core_hwmod = {
 	.slaves_cnt	= ARRAY_SIZE(omap2430_dss_slaves),
 	.masters	= omap2430_dss_masters,
 	.masters_cnt	= ARRAY_SIZE(omap2430_dss_masters),
-	.flags		= HWMOD_NO_IDLEST,
+	.flags		= HWMOD_NO_IDLEST | HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 };
 
 /* l4_core -> dss_dispc */
@@ -1000,6 +1004,7 @@ static struct omap_hwmod omap2430_dss_dispc_hwmod = {
 	.slaves		= omap2430_dss_dispc_slaves,
 	.slaves_cnt	= ARRAY_SIZE(omap2430_dss_dispc_slaves),
 	.flags		= HWMOD_NO_IDLEST,
+	.dev_attr	= &omap2_3_dss_dispc_dev_attr
 };
 
 /* l4_core -> dss_rfbi */
@@ -1016,6 +1021,10 @@ static struct omap_hwmod_ocp_if *omap2430_dss_rfbi_slaves[] = {
 	&omap2430_l4_core__dss_rfbi,
 };
 
+static struct omap_hwmod_opt_clk dss_rfbi_opt_clks[] = {
+	{ .role = "ick", .clk = "dss_ick" },
+};
+
 static struct omap_hwmod omap2430_dss_rfbi_hwmod = {
 	.name		= "dss_rfbi",
 	.class		= &omap2_rfbi_hwmod_class,
@@ -1027,6 +1036,8 @@ static struct omap_hwmod omap2430_dss_rfbi_hwmod = {
 			.module_offs = CORE_MOD,
 		},
 	},
+	.opt_clks	= dss_rfbi_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(dss_rfbi_opt_clks),
 	.slaves		= omap2430_dss_rfbi_slaves,
 	.slaves_cnt	= ARRAY_SIZE(omap2430_dss_rfbi_slaves),
 	.flags		= HWMOD_NO_IDLEST,
@@ -1036,7 +1047,7 @@ static struct omap_hwmod omap2430_dss_rfbi_hwmod = {
 static struct omap_hwmod_ocp_if omap2430_l4_core__dss_venc = {
 	.master		= &omap2430_l4_core_hwmod,
 	.slave		= &omap2430_dss_venc_hwmod,
-	.clk		= "dss_54m_fck",
+	.clk		= "dss_ick",
 	.addr		= omap2_dss_venc_addrs,
 	.flags		= OCPIF_SWSUP_IDLE,
 	.user		= OCP_USER_MPU | OCP_USER_SDMA,
@@ -1050,7 +1061,7 @@ static struct omap_hwmod_ocp_if *omap2430_dss_venc_slaves[] = {
 static struct omap_hwmod omap2430_dss_venc_hwmod = {
 	.name		= "dss_venc",
 	.class		= &omap2_venc_hwmod_class,
-	.main_clk	= "dss1_fck",
+	.main_clk	= "dss_54m_fck",
 	.prcm		= {
 		.omap2 = {
 			.prcm_reg_id = 1,
diff --git a/arch/arm/mach-omap2/omap_hwmod_2xxx_3xxx_ipblock_data.c b/arch/arm/mach-omap2/omap_hwmod_2xxx_3xxx_ipblock_data.c
index c451729..c11273d 100644
--- a/arch/arm/mach-omap2/omap_hwmod_2xxx_3xxx_ipblock_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_2xxx_3xxx_ipblock_data.c
@@ -11,6 +11,7 @@
 #include <plat/omap_hwmod.h>
 #include <plat/serial.h>
 #include <plat/dma.h>
+#include <plat/common.h>
 
 #include <mach/irqs.h>
 
@@ -43,13 +44,15 @@ static struct omap_hwmod_class_sysconfig omap2_dss_sysc = {
 	.rev_offs	= 0x0000,
 	.sysc_offs	= 0x0010,
 	.syss_offs	= 0x0014,
-	.sysc_flags	= (SYSC_HAS_SOFTRESET | SYSC_HAS_AUTOIDLE),
+	.sysc_flags	= (SYSC_HAS_SOFTRESET | SYSC_HAS_AUTOIDLE |
+			   SYSS_HAS_RESET_STATUS),
 	.sysc_fields	= &omap_hwmod_sysc_type1,
 };
 
 struct omap_hwmod_class omap2_dss_hwmod_class = {
 	.name	= "dss",
 	.sysc	= &omap2_dss_sysc,
+	.reset	= omap_dss_reset,
 };
 
 /*
diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
index bc9035e..7f8915a 100644
--- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c
@@ -1369,9 +1369,14 @@ static struct omap_hwmod_ocp_if *omap3xxx_dss_slaves[] = {
 };
 
 static struct omap_hwmod_opt_clk dss_opt_clks[] = {
-	{ .role = "tv_clk", .clk = "dss_tv_fck" },
-	{ .role = "video_clk", .clk = "dss_96m_fck" },
+	/*
+	 * The DSS HW needs all DSS clocks enabled during reset. The dss_core
+	 * driver does not use these clocks.
+	 */
 	{ .role = "sys_clk", .clk = "dss2_alwon_fck" },
+	{ .role = "tv_clk", .clk = "dss_tv_fck" },
+	/* required only on OMAP3430 */
+	{ .role = "tv_dac_clk", .clk = "dss_96m_fck" },
 };
 
 static struct omap_hwmod omap3430es1_dss_core_hwmod = {
@@ -1394,11 +1399,12 @@ static struct omap_hwmod omap3430es1_dss_core_hwmod = {
 	.slaves_cnt	= ARRAY_SIZE(omap3430es1_dss_slaves),
 	.masters	= omap3xxx_dss_masters,
 	.masters_cnt	= ARRAY_SIZE(omap3xxx_dss_masters),
-	.flags		= HWMOD_NO_IDLEST,
+	.flags		= HWMOD_NO_IDLEST | HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 };
 
 static struct omap_hwmod omap3xxx_dss_core_hwmod = {
 	.name		= "dss_core",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.class		= &omap2_dss_hwmod_class,
 	.main_clk	= "dss1_alwon_fck", /* instead of dss_fck */
 	.sdma_reqs	= omap3xxx_dss_sdma_chs,
@@ -1456,6 +1462,7 @@ static struct omap_hwmod omap3xxx_dss_dispc_hwmod = {
 	.slaves		= omap3xxx_dss_dispc_slaves,
 	.slaves_cnt	= ARRAY_SIZE(omap3xxx_dss_dispc_slaves),
 	.flags		= HWMOD_NO_IDLEST,
+	.dev_attr	= &omap2_3_dss_dispc_dev_attr
 };
 
 /*
@@ -1486,6 +1493,7 @@ static struct omap_hwmod_addr_space omap3xxx_dss_dsi1_addrs[] = {
 static struct omap_hwmod_ocp_if omap3xxx_l4_core__dss_dsi1 = {
 	.master		= &omap3xxx_l4_core_hwmod,
 	.slave		= &omap3xxx_dss_dsi1_hwmod,
+	.clk		= "dss_ick",
 	.addr		= omap3xxx_dss_dsi1_addrs,
 	.fw = {
 		.omap2 = {
@@ -1502,6 +1510,10 @@ static struct omap_hwmod_ocp_if *omap3xxx_dss_dsi1_slaves[] = {
 	&omap3xxx_l4_core__dss_dsi1,
 };
 
+static struct omap_hwmod_opt_clk dss_dsi1_opt_clks[] = {
+	{ .role = "sys_clk", .clk = "dss2_alwon_fck" },
+};
+
 static struct omap_hwmod omap3xxx_dss_dsi1_hwmod = {
 	.name		= "dss_dsi1",
 	.class		= &omap3xxx_dsi_hwmod_class,
@@ -1514,6 +1526,8 @@ static struct omap_hwmod omap3xxx_dss_dsi1_hwmod = {
 			.module_offs = OMAP3430_DSS_MOD,
 		},
 	},
+	.opt_clks	= dss_dsi1_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(dss_dsi1_opt_clks),
 	.slaves		= omap3xxx_dss_dsi1_slaves,
 	.slaves_cnt	= ARRAY_SIZE(omap3xxx_dss_dsi1_slaves),
 	.flags		= HWMOD_NO_IDLEST,
@@ -1540,6 +1554,10 @@ static struct omap_hwmod_ocp_if *omap3xxx_dss_rfbi_slaves[] = {
 	&omap3xxx_l4_core__dss_rfbi,
 };
 
+static struct omap_hwmod_opt_clk dss_rfbi_opt_clks[] = {
+	{ .role = "ick", .clk = "dss_ick" },
+};
+
 static struct omap_hwmod omap3xxx_dss_rfbi_hwmod = {
 	.name		= "dss_rfbi",
 	.class		= &omap2_rfbi_hwmod_class,
@@ -1551,6 +1569,8 @@ static struct omap_hwmod omap3xxx_dss_rfbi_hwmod = {
 			.module_offs = OMAP3430_DSS_MOD,
 		},
 	},
+	.opt_clks	= dss_rfbi_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(dss_rfbi_opt_clks),
 	.slaves		= omap3xxx_dss_rfbi_slaves,
 	.slaves_cnt	= ARRAY_SIZE(omap3xxx_dss_rfbi_slaves),
 	.flags		= HWMOD_NO_IDLEST,
@@ -1560,7 +1580,7 @@ static struct omap_hwmod omap3xxx_dss_rfbi_hwmod = {
 static struct omap_hwmod_ocp_if omap3xxx_l4_core__dss_venc = {
 	.master		= &omap3xxx_l4_core_hwmod,
 	.slave		= &omap3xxx_dss_venc_hwmod,
-	.clk		= "dss_tv_fck",
+	.clk		= "dss_ick",
 	.addr		= omap2_dss_venc_addrs,
 	.fw = {
 		.omap2 = {
@@ -1578,10 +1598,15 @@ static struct omap_hwmod_ocp_if *omap3xxx_dss_venc_slaves[] = {
 	&omap3xxx_l4_core__dss_venc,
 };
 
+static struct omap_hwmod_opt_clk dss_venc_opt_clks[] = {
+	/* required only on OMAP3430 */
+	{ .role = "tv_dac_clk", .clk = "dss_96m_fck" },
+};
+
 static struct omap_hwmod omap3xxx_dss_venc_hwmod = {
 	.name		= "dss_venc",
 	.class		= &omap2_venc_hwmod_class,
-	.main_clk	= "dss1_alwon_fck",
+	.main_clk	= "dss_tv_fck",
 	.prcm		= {
 		.omap2 = {
 			.prcm_reg_id = 1,
@@ -1589,6 +1614,8 @@ static struct omap_hwmod omap3xxx_dss_venc_hwmod = {
 			.module_offs = OMAP3430_DSS_MOD,
 		},
 	},
+	.opt_clks	= dss_venc_opt_clks,
+	.opt_clks_cnt	= ARRAY_SIZE(dss_venc_opt_clks),
 	.slaves		= omap3xxx_dss_venc_slaves,
 	.slaves_cnt	= ARRAY_SIZE(omap3xxx_dss_venc_slaves),
 	.flags		= HWMOD_NO_IDLEST,
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index 7695e5d..daaf165 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -30,6 +30,7 @@
 #include <plat/mmc.h>
 #include <plat/i2c.h>
 #include <plat/dmtimer.h>
+#include <plat/common.h>
 
 #include "omap_hwmod_common_data.h"
 
@@ -1187,6 +1188,7 @@ static struct omap_hwmod_class_sysconfig omap44xx_dss_sysc = {
 static struct omap_hwmod_class omap44xx_dss_hwmod_class = {
 	.name	= "dss",
 	.sysc	= &omap44xx_dss_sysc,
+	.reset	= omap_dss_reset,
 };
 
 /* dss */
@@ -1240,12 +1242,12 @@ static struct omap_hwmod_ocp_if *omap44xx_dss_slaves[] = {
 static struct omap_hwmod_opt_clk dss_opt_clks[] = {
 	{ .role = "sys_clk", .clk = "dss_sys_clk" },
 	{ .role = "tv_clk", .clk = "dss_tv_clk" },
-	{ .role = "dss_clk", .clk = "dss_dss_clk" },
-	{ .role = "video_clk", .clk = "dss_48mhz_clk" },
+	{ .role = "hdmi_clk", .clk = "dss_48mhz_clk" },
 };
 
 static struct omap_hwmod omap44xx_dss_hwmod = {
 	.name		= "dss_core",
+	.flags		= HWMOD_CONTROL_OPT_CLKS_IN_RESET,
 	.class		= &omap44xx_dss_hwmod_class,
 	.clkdm_name	= "l3_dss_clkdm",
 	.main_clk	= "dss_dss_clk",
@@ -1325,6 +1327,11 @@ static struct omap_hwmod_addr_space omap44xx_dss_dispc_addrs[] = {
 	{ }
 };
 
+static struct omap_dss_dispc_dev_attr omap44xx_dss_dispc_dev_attr = {
+	.manager_count		= 3,
+	.has_framedonetv_irq	= 1
+};
+
 /* l4_per -> dss_dispc */
 static struct omap_hwmod_ocp_if omap44xx_l4_per__dss_dispc = {
 	.master		= &omap44xx_l4_per_hwmod,
@@ -1340,12 +1347,6 @@ static struct omap_hwmod_ocp_if *omap44xx_dss_dispc_slaves[] = {
 	&omap44xx_l4_per__dss_dispc,
 };
 
-static struct omap_hwmod_opt_clk dss_dispc_opt_clks[] = {
-	{ .role = "sys_clk", .clk = "dss_sys_clk" },
-	{ .role = "tv_clk", .clk = "dss_tv_clk" },
-	{ .role = "hdmi_clk", .clk = "dss_48mhz_clk" },
-};
-
 static struct omap_hwmod omap44xx_dss_dispc_hwmod = {
 	.name		= "dss_dispc",
 	.class		= &omap44xx_dispc_hwmod_class,
@@ -1359,10 +1360,9 @@ static struct omap_hwmod omap44xx_dss_dispc_hwmod = {
 			.context_offs = OMAP4_RM_DSS_DSS_CONTEXT_OFFSET,
 		},
 	},
-	.opt_clks	= dss_dispc_opt_clks,
-	.opt_clks_cnt	= ARRAY_SIZE(dss_dispc_opt_clks),
 	.slaves		= omap44xx_dss_dispc_slaves,
 	.slaves_cnt	= ARRAY_SIZE(omap44xx_dss_dispc_slaves),
+	.dev_attr	= &omap44xx_dss_dispc_dev_attr
 };
 
 /*
@@ -1624,7 +1624,7 @@ static struct omap_hwmod omap44xx_dss_hdmi_hwmod = {
 	.clkdm_name	= "l3_dss_clkdm",
 	.mpu_irqs	= omap44xx_dss_hdmi_irqs,
 	.sdma_reqs	= omap44xx_dss_hdmi_sdma_reqs,
-	.main_clk	= "dss_dss_clk",
+	.main_clk	= "dss_48mhz_clk",
 	.prcm = {
 		.omap4 = {
 			.clkctrl_offs = OMAP4_CM_DSS_DSS_CLKCTRL_OFFSET,
@@ -1785,7 +1785,7 @@ static struct omap_hwmod omap44xx_dss_venc_hwmod = {
 	.name		= "dss_venc",
 	.class		= &omap44xx_venc_hwmod_class,
 	.clkdm_name	= "l3_dss_clkdm",
-	.main_clk	= "dss_dss_clk",
+	.main_clk	= "dss_tv_clk",
 	.prcm = {
 		.omap4 = {
 			.clkctrl_offs = OMAP4_CM_DSS_DSS_CLKCTRL_OFFSET,
diff --git a/arch/arm/mach-omap2/omap_hwmod_common_data.c b/arch/arm/mach-omap2/omap_hwmod_common_data.c
index de832eb..51e5418 100644
--- a/arch/arm/mach-omap2/omap_hwmod_common_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_common_data.c
@@ -49,3 +49,7 @@ struct omap_hwmod_sysc_fields omap_hwmod_sysc_type2 = {
 	.srst_shift	= SYSC_TYPE2_SOFTRESET_SHIFT,
 };
 
+struct omap_dss_dispc_dev_attr omap2_3_dss_dispc_dev_attr = {
+	.manager_count		= 2,
+	.has_framedonetv_irq	= 0
+};
diff --git a/arch/arm/mach-omap2/omap_hwmod_common_data.h b/arch/arm/mach-omap2/omap_hwmod_common_data.h
index 39a7c37..ad5d8f0 100644
--- a/arch/arm/mach-omap2/omap_hwmod_common_data.h
+++ b/arch/arm/mach-omap2/omap_hwmod_common_data.h
@@ -16,6 +16,8 @@
 
 #include <plat/omap_hwmod.h>
 
+#include "display.h"
+
 /* Common address space across OMAP2xxx */
 extern struct omap_hwmod_addr_space omap2xxx_uart1_addr_space[];
 extern struct omap_hwmod_addr_space omap2xxx_uart2_addr_space[];
@@ -111,4 +113,6 @@ extern struct omap_hwmod_class omap2xxx_dma_hwmod_class;
 extern struct omap_hwmod_class omap2xxx_mailbox_hwmod_class;
 extern struct omap_hwmod_class omap2xxx_mcspi_class;
 
+extern struct omap_dss_dispc_dev_attr omap2_3_dss_dispc_dev_attr;
+
 #endif
diff --git a/arch/arm/mach-omap2/omap_l3_noc.c b/arch/arm/mach-omap2/omap_l3_noc.c
index 6a66aa5..d15225f 100644
--- a/arch/arm/mach-omap2/omap_l3_noc.c
+++ b/arch/arm/mach-omap2/omap_l3_noc.c
@@ -237,7 +237,7 @@ static int __devexit omap4_l3_remove(struct platform_device *pdev)
 static const struct of_device_id l3_noc_match[] = {
 	{.compatible = "ti,omap4-l3-noc", },
 	{},
-}
+};
 MODULE_DEVICE_TABLE(of, l3_noc_match);
 #else
 #define l3_noc_match NULL
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index 1e79bdf..00bff46 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -24,6 +24,7 @@
 #include "powerdomain.h"
 #include "clockdomain.h"
 #include "pm.h"
+#include "twl-common.h"
 
 static struct omap_device_pm_latency *pm_lats;
 
@@ -226,11 +227,8 @@ postcore_initcall(omap2_common_pm_init);
 
 static int __init omap2_common_pm_late_init(void)
 {
-	/* Init the OMAP TWL parameters */
-	omap3_twl_init();
-	omap4_twl_init();
-
 	/* Init the voltage layer */
+	omap_pmic_late_init();
 	omap_voltage_late_init();
 
 	/* Initialize the voltages */
diff --git a/arch/arm/mach-omap2/smartreflex.c b/arch/arm/mach-omap2/smartreflex.c
index 6a4f683..cf246b3 100644
--- a/arch/arm/mach-omap2/smartreflex.c
+++ b/arch/arm/mach-omap2/smartreflex.c
@@ -139,7 +139,7 @@ static irqreturn_t sr_interrupt(int irq, void *data)
 		sr_write_reg(sr_info, ERRCONFIG_V1, status);
 	} else if (sr_info->ip_type == SR_TYPE_V2) {
 		/* Read the status bits */
-		sr_read_reg(sr_info, IRQSTATUS);
+		status = sr_read_reg(sr_info, IRQSTATUS);
 
 		/* Clear them by writing back */
 		sr_write_reg(sr_info, IRQSTATUS, status);
diff --git a/arch/arm/mach-omap2/twl-common.c b/arch/arm/mach-omap2/twl-common.c
index 52243577..10b20c6 100644
--- a/arch/arm/mach-omap2/twl-common.c
+++ b/arch/arm/mach-omap2/twl-common.c
@@ -30,6 +30,7 @@
 #include <plat/usb.h>
 
 #include "twl-common.h"
+#include "pm.h"
 
 static struct i2c_board_info __initdata pmic_i2c_board_info = {
 	.addr		= 0x48,
@@ -48,6 +49,16 @@ void __init omap_pmic_init(int bus, u32 clkrate,
 	omap_register_i2c_bus(bus, clkrate, &pmic_i2c_board_info, 1);
 }
 
+void __init omap_pmic_late_init(void)
+{
+	/* Init the OMAP TWL parameters (if PMIC has been registerd) */
+	if (!pmic_i2c_board_info.irq)
+		return;
+
+	omap3_twl_init();
+	omap4_twl_init();
+}
+
 #if defined(CONFIG_ARCH_OMAP3)
 static struct twl4030_usb_data omap3_usb_pdata = {
 	.usb_mode	= T2_USB_MODE_ULPI,
diff --git a/arch/arm/mach-omap2/twl-common.h b/arch/arm/mach-omap2/twl-common.h
index 5e83a5b..275dde8 100644
--- a/arch/arm/mach-omap2/twl-common.h
+++ b/arch/arm/mach-omap2/twl-common.h
@@ -1,6 +1,8 @@
 #ifndef __OMAP_PMIC_COMMON__
 #define __OMAP_PMIC_COMMON__
 
+#include <plat/irqs.h>
+
 #define TWL_COMMON_PDATA_USB		(1 << 0)
 #define TWL_COMMON_PDATA_BCI		(1 << 1)
 #define TWL_COMMON_PDATA_MADC		(1 << 2)
@@ -30,6 +32,7 @@ struct twl4030_platform_data;
 
 void omap_pmic_init(int bus, u32 clkrate, const char *pmic_type, int pmic_irq,
 		    struct twl4030_platform_data *pmic_data);
+void omap_pmic_late_init(void);
 
 static inline void omap2_pmic_init(const char *pmic_type,
 				   struct twl4030_platform_data *pmic_data)
diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c
index fc0b854..4b81f59 100644
--- a/arch/arm/mach-pxa/balloon3.c
+++ b/arch/arm/mach-pxa/balloon3.c
@@ -307,7 +307,7 @@ static inline void balloon3_mmc_init(void) {}
 /******************************************************************************
  * USB Gadget
  ******************************************************************************/
-#if defined(CONFIG_USB_GADGET_PXA27X)||defined(CONFIG_USB_GADGET_PXA27X_MODULE)
+#if defined(CONFIG_USB_PXA27X)||defined(CONFIG_USB_PXA27X_MODULE)
 static void balloon3_udc_command(int cmd)
 {
 	if (cmd == PXA2XX_UDC_CMD_CONNECT)
diff --git a/arch/arm/mach-pxa/colibri-pxa320.c b/arch/arm/mach-pxa/colibri-pxa320.c
index 692e1ff..d23b92b 100644
--- a/arch/arm/mach-pxa/colibri-pxa320.c
+++ b/arch/arm/mach-pxa/colibri-pxa320.c
@@ -146,7 +146,7 @@ static void __init colibri_pxa320_init_eth(void)
 static inline void __init colibri_pxa320_init_eth(void) {}
 #endif /* CONFIG_AX88796 */
 
-#if defined(CONFIG_USB_GADGET_PXA27X)||defined(CONFIG_USB_GADGET_PXA27X_MODULE)
+#if defined(CONFIG_USB_PXA27X)||defined(CONFIG_USB_PXA27X_MODULE)
 static struct gpio_vbus_mach_info colibri_pxa320_gpio_vbus_info = {
 	.gpio_vbus		= mfp_to_gpio(MFP_PIN_GPIO96),
 	.gpio_pullup		= -1,
diff --git a/arch/arm/mach-pxa/gumstix.c b/arch/arm/mach-pxa/gumstix.c
index 9c8208c..ffdd70d 100644
--- a/arch/arm/mach-pxa/gumstix.c
+++ b/arch/arm/mach-pxa/gumstix.c
@@ -106,7 +106,7 @@ static void __init gumstix_mmc_init(void)
 }
 #endif
 
-#ifdef CONFIG_USB_GADGET_PXA25X
+#ifdef CONFIG_USB_PXA25X
 static struct gpio_vbus_mach_info gumstix_udc_info = {
 	.gpio_vbus		= GPIO_GUMSTIX_USB_GPIOn,
 	.gpio_pullup		= GPIO_GUMSTIX_USB_GPIOx,
diff --git a/arch/arm/mach-pxa/include/mach/palm27x.h b/arch/arm/mach-pxa/include/mach/palm27x.h
index f80bbe2..d4eac3d 100644
--- a/arch/arm/mach-pxa/include/mach/palm27x.h
+++ b/arch/arm/mach-pxa/include/mach/palm27x.h
@@ -37,8 +37,8 @@ extern void __init palm27x_lcd_init(int power,
 #define palm27x_lcd_init(power, mode)	do {} while (0)
 #endif
 
-#if	defined(CONFIG_USB_GADGET_PXA27X) || \
-	defined(CONFIG_USB_GADGET_PXA27X_MODULE)
+#if	defined(CONFIG_USB_PXA27X) || \
+	defined(CONFIG_USB_PXA27X_MODULE)
 extern void __init palm27x_udc_init(int vbus, int pullup,
 					int vbus_inverted);
 #else
diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c
index 325c245..fbc10d7 100644
--- a/arch/arm/mach-pxa/palm27x.c
+++ b/arch/arm/mach-pxa/palm27x.c
@@ -164,8 +164,8 @@ void __init palm27x_lcd_init(int power, struct pxafb_mode_info *mode)
 /******************************************************************************
  * USB Gadget
  ******************************************************************************/
-#if	defined(CONFIG_USB_GADGET_PXA27X) || \
-	defined(CONFIG_USB_GADGET_PXA27X_MODULE)
+#if	defined(CONFIG_USB_PXA27X) || \
+	defined(CONFIG_USB_PXA27X_MODULE)
 static struct gpio_vbus_mach_info palm27x_udc_info = {
 	.gpio_vbus_inverted	= 1,
 };
diff --git a/arch/arm/mach-pxa/palmtc.c b/arch/arm/mach-pxa/palmtc.c
index 6ec7cae..2c24c67 100644
--- a/arch/arm/mach-pxa/palmtc.c
+++ b/arch/arm/mach-pxa/palmtc.c
@@ -338,7 +338,7 @@ static inline void palmtc_mkp_init(void) {}
 /******************************************************************************
  * UDC
  ******************************************************************************/
-#if defined(CONFIG_USB_GADGET_PXA25X)||defined(CONFIG_USB_GADGET_PXA25X_MODULE)
+#if defined(CONFIG_USB_PXA25X)||defined(CONFIG_USB_PXA25X_MODULE)
 static struct gpio_vbus_mach_info palmtc_udc_info = {
 	.gpio_vbus		= GPIO_NR_PALMTC_USB_DETECT_N,
 	.gpio_vbus_inverted	= 1,
diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c
index a7539a6..ca0c661 100644
--- a/arch/arm/mach-pxa/vpac270.c
+++ b/arch/arm/mach-pxa/vpac270.c
@@ -343,7 +343,7 @@ static inline void vpac270_uhc_init(void) {}
 /******************************************************************************
  * USB Gadget
  ******************************************************************************/
-#if defined(CONFIG_USB_GADGET_PXA27X)||defined(CONFIG_USB_GADGET_PXA27X_MODULE)
+#if defined(CONFIG_USB_PXA27X)||defined(CONFIG_USB_PXA27X_MODULE)
 static struct gpio_vbus_mach_info vpac270_gpio_vbus_info = {
 	.gpio_vbus		= GPIO41_VPAC270_UDC_DETECT,
 	.gpio_pullup		= -1,
diff --git a/arch/arm/mach-s3c64xx/mach-crag6410-module.c b/arch/arm/mach-s3c64xx/mach-crag6410-module.c
index 6666856..f208154 100644
--- a/arch/arm/mach-s3c64xx/mach-crag6410-module.c
+++ b/arch/arm/mach-s3c64xx/mach-crag6410-module.c
@@ -8,7 +8,7 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/interrupt.h>
 #include <linux/i2c.h>
 
diff --git a/arch/arm/mach-shmobile/pm-sh7372.c b/arch/arm/mach-shmobile/pm-sh7372.c
index 0a5b229..34bbcbf 100644
--- a/arch/arm/mach-shmobile/pm-sh7372.c
+++ b/arch/arm/mach-shmobile/pm-sh7372.c
@@ -20,6 +20,7 @@
 #include <linux/delay.h>
 #include <linux/irq.h>
 #include <linux/bitrev.h>
+#include <linux/console.h>
 #include <asm/system.h>
 #include <asm/io.h>
 #include <asm/tlbflush.h>
@@ -106,9 +107,8 @@ static int pd_power_down(struct generic_pm_domain *genpd)
 	return 0;
 }
 
-static int pd_power_up(struct generic_pm_domain *genpd)
+static int __pd_power_up(struct sh7372_pm_domain *sh7372_pd, bool do_resume)
 {
-	struct sh7372_pm_domain *sh7372_pd = to_sh7372_pd(genpd);
 	unsigned int mask = 1 << sh7372_pd->bit_shift;
 	unsigned int retry_count;
 	int ret = 0;
@@ -123,13 +123,13 @@ static int pd_power_up(struct generic_pm_domain *genpd)
 
 	for (retry_count = 2 * PSTR_RETRIES; retry_count; retry_count--) {
 		if (!(__raw_readl(SWUCR) & mask))
-			goto out;
+			break;
 		if (retry_count > PSTR_RETRIES)
 			udelay(PSTR_DELAY_US);
 		else
 			cpu_relax();
 	}
-	if (__raw_readl(SWUCR) & mask)
+	if (!retry_count)
 		ret = -EIO;
 
 	if (!sh7372_pd->no_debug)
@@ -137,12 +137,17 @@ static int pd_power_up(struct generic_pm_domain *genpd)
 			 mask, __raw_readl(PSTR));
 
  out:
-	if (ret == 0 && sh7372_pd->resume)
+	if (ret == 0 && sh7372_pd->resume && do_resume)
 		sh7372_pd->resume();
 
 	return ret;
 }
 
+static int pd_power_up(struct generic_pm_domain *genpd)
+{
+	 return __pd_power_up(to_sh7372_pd(genpd), true);
+}
+
 static void sh7372_a4r_suspend(void)
 {
 	sh7372_intcs_suspend();
@@ -174,7 +179,7 @@ void sh7372_init_pm_domain(struct sh7372_pm_domain *sh7372_pd)
 	genpd->active_wakeup = pd_active_wakeup;
 	genpd->power_off = pd_power_down;
 	genpd->power_on = pd_power_up;
-	genpd->power_on(&sh7372_pd->genpd);
+	__pd_power_up(sh7372_pd, false);
 }
 
 void sh7372_add_device_to_domain(struct sh7372_pm_domain *sh7372_pd,
@@ -227,11 +232,23 @@ struct sh7372_pm_domain sh7372_a3sp = {
 	.no_debug = true,
 };
 
+static void sh7372_a3sp_init(void)
+{
+	/* serial consoles make use of SCIF hardware located in A3SP,
+	 * keep such power domain on if "no_console_suspend" is set.
+	 */
+	sh7372_a3sp.stay_on = !console_suspend_enabled;
+}
+
 struct sh7372_pm_domain sh7372_a3sg = {
 	.bit_shift = 13,
 };
 
-#endif /* CONFIG_PM */
+#else /* !CONFIG_PM */
+
+static inline void sh7372_a3sp_init(void) {}
+
+#endif /* !CONFIG_PM */
 
 #if defined(CONFIG_SUSPEND) || defined(CONFIG_CPU_IDLE)
 static int sh7372_do_idle_core_standby(unsigned long unused)
@@ -465,6 +482,8 @@ void __init sh7372_pm_init(void)
 	/* do not convert A3SM, A3SP, A3SG, A4R power down into A4S */
 	__raw_writel(0, PDNSEL);
 
+	sh7372_a3sp_init();
+
 	sh7372_suspend_init();
 	sh7372_cpuidle_init();
 }
diff --git a/arch/arm/mach-w90x900/dev.c b/arch/arm/mach-w90x900/dev.c
index 7a1fa6a..5b0c38a 100644
--- a/arch/arm/mach-w90x900/dev.c
+++ b/arch/arm/mach-w90x900/dev.c
@@ -422,7 +422,7 @@ struct platform_device nuc900_device_kpi = {
 
 /* LCD controller*/
 
-static struct nuc900fb_display __initdata nuc900_lcd_info[] = {
+static struct nuc900fb_display nuc900_lcd_info[] = {
 	/* Giantplus Technology GPM1040A0 320x240 Color TFT LCD */
 	[0] = {
 		.type		= LCM_DCCS_VA_SRC_RGB565,
@@ -445,7 +445,7 @@ static struct nuc900fb_display __initdata nuc900_lcd_info[] = {
 	},
 };
 
-static struct nuc900fb_mach_info nuc900_fb_info __initdata = {
+static struct nuc900fb_mach_info nuc900_fb_info = {
 #if defined(CONFIG_GPM1040A0_320X240)
 	.displays		= &nuc900_lcd_info[0],
 #else
diff --git a/arch/arm/mach-w90x900/include/mach/mfp.h b/arch/arm/mach-w90x900/include/mach/mfp.h
index 94c0e71..23ef1f5 100644
--- a/arch/arm/mach-w90x900/include/mach/mfp.h
+++ b/arch/arm/mach-w90x900/include/mach/mfp.h
@@ -19,6 +19,7 @@
 extern void mfp_set_groupf(struct device *dev);
 extern void mfp_set_groupc(struct device *dev);
 extern void mfp_set_groupi(struct device *dev);
-extern void mfp_set_groupg(struct device *dev);
+extern void mfp_set_groupg(struct device *dev, const char *subname);
+extern void mfp_set_groupd(struct device *dev, const char *subname);
 
 #endif /* __ASM_ARCH_MFP_H */
diff --git a/arch/arm/mach-w90x900/include/mach/nuc900_spi.h b/arch/arm/mach-w90x900/include/mach/nuc900_spi.h
index bd94819..2c4e0c1 100644
--- a/arch/arm/mach-w90x900/include/mach/nuc900_spi.h
+++ b/arch/arm/mach-w90x900/include/mach/nuc900_spi.h
@@ -14,7 +14,7 @@
 #ifndef __ASM_ARCH_SPI_H
 #define __ASM_ARCH_SPI_H
 
-extern void mfp_set_groupg(struct device *dev);
+extern void mfp_set_groupg(struct device *dev, const char *subname);
 
 struct nuc900_spi_info {
 	unsigned int num_cs;
diff --git a/arch/arm/mach-w90x900/mfp.c b/arch/arm/mach-w90x900/mfp.c
index fb7fb62..9dd7461 100644
--- a/arch/arm/mach-w90x900/mfp.c
+++ b/arch/arm/mach-w90x900/mfp.c
@@ -26,10 +26,8 @@
 #define REG_MFSEL	(W90X900_VA_GCR + 0xC)
 
 #define GPSELF		(0x01 << 1)
-
 #define GPSELC		(0x03 << 2)
-#define ENKPI		(0x02 << 2)
-#define ENNAND		(0x01 << 2)
+#define GPSELD		(0x0f << 4)
 
 #define GPSELEI0	(0x01 << 26)
 #define GPSELEI1	(0x01 << 27)
@@ -37,11 +35,16 @@
 #define GPIOG0TO1	(0x03 << 14)
 #define GPIOG2TO3	(0x03 << 16)
 #define GPIOG22TO23	(0x03 << 22)
+#define GPIOG18TO20	(0x07 << 18)
 
 #define ENSPI		(0x0a << 14)
 #define ENI2C0		(0x01 << 14)
 #define ENI2C1		(0x01 << 16)
 #define ENAC97		(0x02 << 22)
+#define ENSD1		(0x02 << 18)
+#define ENSD0		(0x0a << 4)
+#define ENKPI		(0x02 << 2)
+#define ENNAND		(0x01 << 2)
 
 static DEFINE_MUTEX(mfp_mutex);
 
@@ -127,16 +130,19 @@ void mfp_set_groupi(struct device *dev)
 }
 EXPORT_SYMBOL(mfp_set_groupi);
 
-void mfp_set_groupg(struct device *dev)
+void mfp_set_groupg(struct device *dev, const char *subname)
 {
 	unsigned long mfpen;
 	const char *dev_id;
 
-	BUG_ON(!dev);
+	BUG_ON((!dev) && (!subname));
 
 	mutex_lock(&mfp_mutex);
 
-	dev_id = dev_name(dev);
+	if (subname != NULL)
+		dev_id = subname;
+	else
+		dev_id = dev_name(dev);
 
 	mfpen = __raw_readl(REG_MFSEL);
 
@@ -152,6 +158,9 @@ void mfp_set_groupg(struct device *dev)
 	} else if (strcmp(dev_id, "nuc900-audio") == 0) {
 		mfpen &= ~(GPIOG22TO23);
 		mfpen |= ENAC97;/*enable AC97*/
+	} else if (strcmp(dev_id, "nuc900-mmc-port1") == 0) {
+		mfpen &= ~(GPIOG18TO20);
+		mfpen |= (ENSD1 | 0x01);/*enable sd1*/
 	} else {
 		mfpen &= ~(GPIOG0TO1 | GPIOG2TO3);/*GPIOG[3:0]*/
 	}
@@ -162,3 +171,30 @@ void mfp_set_groupg(struct device *dev)
 }
 EXPORT_SYMBOL(mfp_set_groupg);
 
+void mfp_set_groupd(struct device *dev, const char *subname)
+{
+	unsigned long mfpen;
+	const char *dev_id;
+
+	BUG_ON((!dev) && (!subname));
+
+	mutex_lock(&mfp_mutex);
+
+	if (subname != NULL)
+		dev_id = subname;
+	else
+		dev_id = dev_name(dev);
+
+	mfpen = __raw_readl(REG_MFSEL);
+
+	if (strcmp(dev_id, "nuc900-mmc-port0") == 0) {
+		mfpen &= ~GPSELD;/*enable sd0*/
+		mfpen |= ENSD0;
+	} else
+		mfpen &= (~GPSELD);
+
+	__raw_writel(mfpen, REG_MFSEL);
+
+	mutex_unlock(&mfp_mutex);
+}
+EXPORT_SYMBOL(mfp_set_groupd);
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 8ac9e9f..b1e192b 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -61,7 +61,7 @@ static inline void cache_sync(void)
 {
 	void __iomem *base = l2x0_base;
 
-#ifdef CONFIG_ARM_ERRATA_753970
+#ifdef CONFIG_PL310_ERRATA_753970
 	/* write to an unmmapped register */
 	writel_relaxed(0, base + L2X0_DUMMY_REG);
 #else
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index e4e7f6c..1aa664a 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -168,7 +168,7 @@ static int __init consistent_init(void)
 	pte_t *pte;
 	int i = 0;
 	unsigned long base = consistent_base;
-	unsigned long num_ptes = (CONSISTENT_END - base) >> PGDIR_SHIFT;
+	unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT;
 
 	consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL);
 	if (!consistent_pte) {
@@ -332,6 +332,15 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
 	struct page *page;
 	void *addr;
 
+	/*
+	 * Following is a work-around (a.k.a. hack) to prevent pages
+	 * with __GFP_COMP being passed to split_page() which cannot
+	 * handle them.  The real problem is that this flag probably
+	 * should be 0 on ARM as it is not supported on this
+	 * platform; see CONFIG_HUGETLBFS.
+	 */
+	gfp &= ~(__GFP_COMP);
+
 	*handle = ~0;
 	size = PAGE_ALIGN(size);
 
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 74be05f..44b628e 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -9,8 +9,7 @@
 #include <linux/io.h>
 #include <linux/personality.h>
 #include <linux/random.h>
-#include <asm/cputype.h>
-#include <asm/system.h>
+#include <asm/cachetype.h>
 
 #define COLOUR_ALIGN(addr,pgoff)		\
 	((((addr)+SHMLBA-1)&~(SHMLBA-1)) +	\
@@ -32,25 +31,15 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long start_addr;
-#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
-	unsigned int cache_type;
-	int do_align = 0, aliasing = 0;
+	int do_align = 0;
+	int aliasing = cache_is_vipt_aliasing();
 
 	/*
 	 * We only need to do colour alignment if either the I or D
-	 * caches alias.  This is indicated by bits 9 and 21 of the
-	 * cache type register.
+	 * caches alias.
 	 */
-	cache_type = read_cpuid_cachetype();
-	if (cache_type != read_cpuid_id()) {
-		aliasing = (cache_type | cache_type >> 12) & (1 << 11);
-		if (aliasing)
-			do_align = filp || flags & MAP_SHARED;
-	}
-#else
-#define do_align 0
-#define aliasing 0
-#endif
+	if (aliasing)
+		do_align = filp || (flags & MAP_SHARED);
 
 	/*
 	 * We enforce the MAP_FIXED case.
diff --git a/arch/arm/plat-mxc/include/mach/common.h b/arch/arm/plat-mxc/include/mach/common.h
index 83b745a..c75f254 100644
--- a/arch/arm/plat-mxc/include/mach/common.h
+++ b/arch/arm/plat-mxc/include/mach/common.h
@@ -85,7 +85,6 @@ enum mxc_cpu_pwr_mode {
 };
 
 extern void mx5_cpu_lp_set(enum mxc_cpu_pwr_mode mode);
-extern void (*imx_idle)(void);
 extern void imx_print_silicon_rev(const char *cpu, int srev);
 
 void avic_handle_irq(struct pt_regs *);
@@ -133,4 +132,5 @@ extern void imx53_qsb_common_init(void);
 extern void imx53_smd_common_init(void);
 extern int imx6q_set_lpm(enum mxc_cpu_pwr_mode mode);
 extern void imx6q_pm_init(void);
+extern void imx6q_clock_map_io(void);
 #endif
diff --git a/arch/arm/plat-mxc/include/mach/mxc.h b/arch/arm/plat-mxc/include/mach/mxc.h
index 00a7819..a4d36d6 100644
--- a/arch/arm/plat-mxc/include/mach/mxc.h
+++ b/arch/arm/plat-mxc/include/mach/mxc.h
@@ -50,20 +50,6 @@
 #define IMX_CHIP_REVISION_3_3		0x33
 #define IMX_CHIP_REVISION_UNKNOWN	0xff
 
-#define IMX_CHIP_REVISION_1_0_STRING		"1.0"
-#define IMX_CHIP_REVISION_1_1_STRING		"1.1"
-#define IMX_CHIP_REVISION_1_2_STRING		"1.2"
-#define IMX_CHIP_REVISION_1_3_STRING		"1.3"
-#define IMX_CHIP_REVISION_2_0_STRING		"2.0"
-#define IMX_CHIP_REVISION_2_1_STRING		"2.1"
-#define IMX_CHIP_REVISION_2_2_STRING		"2.2"
-#define IMX_CHIP_REVISION_2_3_STRING		"2.3"
-#define IMX_CHIP_REVISION_3_0_STRING		"3.0"
-#define IMX_CHIP_REVISION_3_1_STRING		"3.1"
-#define IMX_CHIP_REVISION_3_2_STRING		"3.2"
-#define IMX_CHIP_REVISION_3_3_STRING		"3.3"
-#define IMX_CHIP_REVISION_UNKNOWN_STRING	"unknown"
-
 #ifndef __ASSEMBLY__
 extern unsigned int __mxc_cpu_type;
 #endif
diff --git a/arch/arm/plat-mxc/include/mach/system.h b/arch/arm/plat-mxc/include/mach/system.h
index cf88b35..b9895d2 100644
--- a/arch/arm/plat-mxc/include/mach/system.h
+++ b/arch/arm/plat-mxc/include/mach/system.h
@@ -17,14 +17,9 @@
 #ifndef __ASM_ARCH_MXC_SYSTEM_H__
 #define __ASM_ARCH_MXC_SYSTEM_H__
 
-extern void (*imx_idle)(void);
-
 static inline void arch_idle(void)
 {
-	if (imx_idle != NULL)
-		(imx_idle)();
-	else
-		cpu_do_idle();
+	cpu_do_idle();
 }
 
 void arch_reset(char mode, const char *cmd);
diff --git a/arch/arm/plat-mxc/system.c b/arch/arm/plat-mxc/system.c
index 9dad8dc..d65fb31 100644
--- a/arch/arm/plat-mxc/system.c
+++ b/arch/arm/plat-mxc/system.c
@@ -21,6 +21,7 @@
 #include <linux/io.h>
 #include <linux/err.h>
 #include <linux/delay.h>
+#include <linux/module.h>
 
 #include <mach/hardware.h>
 #include <mach/common.h>
@@ -28,8 +29,8 @@
 #include <asm/system.h>
 #include <asm/mach-types.h>
 
-void (*imx_idle)(void) = NULL;
 void __iomem *(*imx_ioremap)(unsigned long, size_t, unsigned int) = NULL;
+EXPORT_SYMBOL_GPL(imx_ioremap);
 
 static void __iomem *wdog_base;
 
diff --git a/arch/arm/plat-omap/include/plat/clock.h b/arch/arm/plat-omap/include/plat/clock.h
index 197ca03..eb73ab4 100644
--- a/arch/arm/plat-omap/include/plat/clock.h
+++ b/arch/arm/plat-omap/include/plat/clock.h
@@ -165,8 +165,8 @@ struct dpll_data {
 	u8			auto_recal_bit;
 	u8			recal_en_bit;
 	u8			recal_st_bit;
-	u8			flags;
 #  endif
+	u8			flags;
 };
 
 #endif
diff --git a/arch/arm/plat-omap/include/plat/common.h b/arch/arm/plat-omap/include/plat/common.h
index c50df48..3ff3e36 100644
--- a/arch/arm/plat-omap/include/plat/common.h
+++ b/arch/arm/plat-omap/include/plat/common.h
@@ -30,6 +30,7 @@
 #include <linux/delay.h>
 
 #include <plat/i2c.h>
+#include <plat/omap_hwmod.h>
 
 struct sys_timer;
 
@@ -55,6 +56,8 @@ void am35xx_init_early(void);
 void ti816x_init_early(void);
 void omap4430_init_early(void);
 
+extern int omap_dss_reset(struct omap_hwmod *);
+
 void omap_sram_init(void);
 
 /*
diff --git a/arch/arm/plat-s3c24xx/cpu-freq-debugfs.c b/arch/arm/plat-s3c24xx/cpu-freq-debugfs.c
index a927666..c7adad0 100644
--- a/arch/arm/plat-s3c24xx/cpu-freq-debugfs.c
+++ b/arch/arm/plat-s3c24xx/cpu-freq-debugfs.c
@@ -12,7 +12,7 @@
 */
 
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
 #include <linux/cpufreq.h>
diff --git a/arch/arm/plat-s5p/sysmmu.c b/arch/arm/plat-s5p/sysmmu.c
index e1cbc72..c8bec9c 100644
--- a/arch/arm/plat-s5p/sysmmu.c
+++ b/arch/arm/plat-s5p/sysmmu.c
@@ -11,6 +11,7 @@
 #include <linux/io.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
+#include <linux/export.h>
 
 #include <asm/pgtable.h>
 
diff --git a/arch/arm/plat-samsung/include/plat/gpio-cfg.h b/arch/arm/plat-samsung/include/plat/gpio-cfg.h
index d48245b..df8155b 100644
--- a/arch/arm/plat-samsung/include/plat/gpio-cfg.h
+++ b/arch/arm/plat-samsung/include/plat/gpio-cfg.h
@@ -24,6 +24,8 @@
 #ifndef __PLAT_GPIO_CFG_H
 #define __PLAT_GPIO_CFG_H __FILE__
 
+#include<linux/types.h>
+
 typedef unsigned int __bitwise__ samsung_gpio_pull_t;
 typedef unsigned int __bitwise__ s5p_gpio_drvstr_t;
 
diff --git a/arch/arm/plat-samsung/pd.c b/arch/arm/plat-samsung/pd.c
index efe1d56..312b510 100644
--- a/arch/arm/plat-samsung/pd.c
+++ b/arch/arm/plat-samsung/pd.c
@@ -11,7 +11,7 @@
 */
 
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/platform_device.h>
 #include <linux/err.h>
 #include <linux/pm_runtime.h>
diff --git a/arch/arm/plat-samsung/pwm.c b/arch/arm/plat-samsung/pwm.c
index dc1185d..c559d84 100644
--- a/arch/arm/plat-samsung/pwm.c
+++ b/arch/arm/plat-samsung/pwm.c
@@ -11,7 +11,7 @@
  * the Free Software Foundation; either version 2 of the License.
 */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
diff --git a/arch/arm/tools/mach-types b/arch/arm/tools/mach-types
index 5bdeef9..ccbe16f 100644
--- a/arch/arm/tools/mach-types
+++ b/arch/arm/tools/mach-types
@@ -1123,5 +1123,6 @@ blissc			MACH_BLISSC		BLISSC			3491
 thales_adc		MACH_THALES_ADC		THALES_ADC		3492
 ubisys_p9d_evp		MACH_UBISYS_P9D_EVP	UBISYS_P9D_EVP		3493
 atdgp318		MACH_ATDGP318		ATDGP318		3494
+m28evk			MACH_M28EVK		M28EVK			3613
 smdk4212		MACH_SMDK4212		SMDK4212		3638
 smdk4412		MACH_SMDK4412		SMDK4412		3765
diff --git a/arch/cris/arch-v10/drivers/Kconfig b/arch/cris/arch-v10/drivers/Kconfig
index 32d9086..5f2cdb3 100644
--- a/arch/cris/arch-v10/drivers/Kconfig
+++ b/arch/cris/arch-v10/drivers/Kconfig
@@ -3,7 +3,7 @@ if ETRAX_ARCH_V10
 config ETRAX_ETHERNET
 	bool "Ethernet support"
 	depends on ETRAX_ARCH_V10
-	select NET_ETHERNET
+	select ETHERNET
 	select NET_CORE
 	select MII
 	help
diff --git a/arch/cris/arch-v32/drivers/Kconfig b/arch/cris/arch-v32/drivers/Kconfig
index e47e9c3..de43aad 100644
--- a/arch/cris/arch-v32/drivers/Kconfig
+++ b/arch/cris/arch-v32/drivers/Kconfig
@@ -3,7 +3,7 @@ if ETRAX_ARCH_V32
 config ETRAX_ETHERNET
 	bool "Ethernet support"
 	depends on ETRAX_ARCH_V32
-	select NET_ETHERNET
+	select ETHERNET
 	select NET_CORE
 	select MII
 	help
diff --git a/arch/microblaze/include/asm/namei.h b/arch/microblaze/include/asm/namei.h
deleted file mode 100644
index 61d60b8..0000000
--- a/arch/microblaze/include/asm/namei.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/*
- * Copyright (C) 2006 Atmark Techno, Inc.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#ifndef _ASM_MICROBLAZE_NAMEI_H
-#define _ASM_MICROBLAZE_NAMEI_H
-
-#ifdef __KERNEL__
-
-/* This dummy routine maybe changed to something useful
- * for /usr/gnemul/ emulation stuff.
- * Look at asm-sparc/namei.h for details.
- */
-#define __emul_prefix() NULL
-
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_MICROBLAZE_NAMEI_H */
diff --git a/arch/mips/cavium-octeon/flash_setup.c b/arch/mips/cavium-octeon/flash_setup.c
index 975c203..0a430e0 100644
--- a/arch/mips/cavium-octeon/flash_setup.c
+++ b/arch/mips/cavium-octeon/flash_setup.c
@@ -17,8 +17,6 @@
 
 static struct map_info flash_map;
 static struct mtd_info *mymtd;
-static int nr_parts;
-static struct mtd_partition *parts;
 static const char *part_probe_types[] = {
 	"cmdlinepart",
 #ifdef CONFIG_MTD_REDBOOT_PARTS
@@ -61,11 +59,8 @@ static int __init flash_init(void)
 		mymtd = do_map_probe("cfi_probe", &flash_map);
 		if (mymtd) {
 			mymtd->owner = THIS_MODULE;
-
-			nr_parts = parse_mtd_partitions(mymtd,
-							part_probe_types,
-							&parts, 0);
-			mtd_device_register(mymtd, parts, nr_parts);
+			mtd_device_parse_register(mymtd, part_probe_types,
+						  0, NULL, 0);
 		} else {
 			pr_err("Failed to register MTD device for flash\n");
 		}
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 8b60642..efcfff4 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -207,8 +207,9 @@ void octeon_prepare_cpus(unsigned int max_cpus)
 	 * the other bits alone.
 	 */
 	cvmx_write_csr(CVMX_CIU_MBOX_CLRX(cvmx_get_core_num()), 0xffff);
-	if (request_irq(OCTEON_IRQ_MBOX0, mailbox_interrupt, IRQF_DISABLED,
-			"SMP-IPI", mailbox_interrupt)) {
+	if (request_irq(OCTEON_IRQ_MBOX0, mailbox_interrupt,
+			IRQF_PERCPU | IRQF_NO_THREAD, "SMP-IPI",
+			mailbox_interrupt)) {
 		panic("Cannot request_irq(OCTEON_IRQ_MBOX0)\n");
 	}
 }
diff --git a/arch/mips/emma/common/prom.c b/arch/mips/emma/common/prom.c
index 708f087..cae4225 100644
--- a/arch/mips/emma/common/prom.c
+++ b/arch/mips/emma/common/prom.c
@@ -50,7 +50,7 @@ void __init prom_init(void)
 
 	/* arg[0] is "g", the rest is boot parameters */
 	for (i = 1; i < argc; i++) {
-		if (strlen(arcs_cmdline) + strlen(arg[i] + 1)
+		if (strlen(arcs_cmdline) + strlen(arg[i]) + 1
 		    >= sizeof(arcs_cmdline))
 			break;
 		strcat(arcs_cmdline, arg[i]);
diff --git a/arch/mips/include/asm/mach-bcm47xx/gpio.h b/arch/mips/include/asm/mach-bcm47xx/gpio.h
index 76961ca..2ef17e8 100644
--- a/arch/mips/include/asm/mach-bcm47xx/gpio.h
+++ b/arch/mips/include/asm/mach-bcm47xx/gpio.h
@@ -36,6 +36,8 @@ static inline int gpio_get_value(unsigned gpio)
 	return -EINVAL;
 }
 
+#define gpio_get_value_cansleep	gpio_get_value
+
 static inline void gpio_set_value(unsigned gpio, int value)
 {
 	switch (bcm47xx_bus_type) {
@@ -54,6 +56,19 @@ static inline void gpio_set_value(unsigned gpio, int value)
 	}
 }
 
+#define gpio_set_value_cansleep gpio_set_value
+
+static inline int gpio_cansleep(unsigned gpio)
+{
+	return 0;
+}
+
+static inline int gpio_is_valid(unsigned gpio)
+{
+	return gpio < (BCM47XX_EXTIF_GPIO_LINES + BCM47XX_CHIPCO_GPIO_LINES);
+}
+
+
 static inline int gpio_direction_input(unsigned gpio)
 {
 	switch (bcm47xx_bus_type) {
@@ -137,7 +152,4 @@ static inline int gpio_polarity(unsigned gpio, int value)
 }
 
 
-/* cansleep wrappers */
-#include <asm-generic/gpio.h>
-
 #endif /* __BCM47XX_GPIO_H */
diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h
index ecea787..d8dad53 100644
--- a/arch/mips/include/asm/unistd.h
+++ b/arch/mips/include/asm/unistd.h
@@ -365,16 +365,18 @@
 #define __NR_syncfs			(__NR_Linux + 342)
 #define __NR_sendmmsg			(__NR_Linux + 343)
 #define __NR_setns			(__NR_Linux + 344)
+#define __NR_process_vm_readv		(__NR_Linux + 345)
+#define __NR_process_vm_writev		(__NR_Linux + 346)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		344
+#define __NR_Linux_syscalls		346
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		344
+#define __NR_O32_Linux_syscalls		346
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -686,16 +688,18 @@
 #define __NR_syncfs			(__NR_Linux + 301)
 #define __NR_sendmmsg			(__NR_Linux + 302)
 #define __NR_setns			(__NR_Linux + 303)
+#define __NR_process_vm_readv		(__NR_Linux + 304)
+#define __NR_process_vm_writev		(__NR_Linux + 305)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		303
+#define __NR_Linux_syscalls		305
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		303
+#define __NR_64_Linux_syscalls		305
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1012,16 +1016,18 @@
 #define __NR_syncfs			(__NR_Linux + 306)
 #define __NR_sendmmsg			(__NR_Linux + 307)
 #define __NR_setns			(__NR_Linux + 308)
+#define __NR_process_vm_readv		(__NR_Linux + 309)
+#define __NR_process_vm_writev		(__NR_Linux + 310)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		308
+#define __NR_Linux_syscalls		310
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		308
+#define __NR_N32_Linux_syscalls		310
 
 #ifdef __KERNEL__
 
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index 98c5a97..e2d8e19 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -103,19 +103,10 @@ static int c0_compare_int_pending(void)
 
 /*
  * Compare interrupt can be routed and latched outside the core,
- * so a single execution hazard barrier may not be enough to give
- * it time to clear as seen in the Cause register.  4 time the
- * pipeline depth seems reasonably conservative, and empirically
- * works better in configurations with high CPU/bus clock ratios.
+ * so wait up to worst case number of cycle counter ticks for timer interrupt
+ * changes to propagate to the cause register.
  */
-
-#define compare_change_hazard() \
-	do { \
-		irq_disable_hazard(); \
-		irq_disable_hazard(); \
-		irq_disable_hazard(); \
-		irq_disable_hazard(); \
-	} while (0)
+#define COMPARE_INT_SEEN_TICKS 50
 
 int c0_compare_int_usable(void)
 {
@@ -126,8 +117,12 @@ int c0_compare_int_usable(void)
 	 * IP7 already pending?  Try to clear it by acking the timer.
 	 */
 	if (c0_compare_int_pending()) {
-		write_c0_compare(read_c0_count());
-		compare_change_hazard();
+		cnt = read_c0_count();
+		write_c0_compare(cnt);
+		back_to_back_c0_hazard();
+		while (read_c0_count() < (cnt  + COMPARE_INT_SEEN_TICKS))
+			if (!c0_compare_int_pending())
+				break;
 		if (c0_compare_int_pending())
 			return 0;
 	}
@@ -136,7 +131,7 @@ int c0_compare_int_usable(void)
 		cnt = read_c0_count();
 		cnt += delta;
 		write_c0_compare(cnt);
-		compare_change_hazard();
+		back_to_back_c0_hazard();
 		if ((int)(read_c0_count() - cnt) < 0)
 		    break;
 		/* increase delta if the timer was already expired */
@@ -145,12 +140,17 @@ int c0_compare_int_usable(void)
 	while ((int)(read_c0_count() - cnt) <= 0)
 		;	/* Wait for expiry  */
 
-	compare_change_hazard();
+	while (read_c0_count() < (cnt + COMPARE_INT_SEEN_TICKS))
+		if (c0_compare_int_pending())
+			break;
 	if (!c0_compare_int_pending())
 		return 0;
-
-	write_c0_compare(read_c0_count());
-	compare_change_hazard();
+	cnt = read_c0_count();
+	write_c0_compare(cnt);
+	back_to_back_c0_hazard();
+	while (read_c0_count() < (cnt + COMPARE_INT_SEEN_TICKS))
+		if (!c0_compare_int_pending())
+			break;
 	if (c0_compare_int_pending())
 		return 0;
 
diff --git a/arch/mips/kernel/cpufreq/loongson2_clock.c b/arch/mips/kernel/cpufreq/loongson2_clock.c
index cefc6e2..5426779 100644
--- a/arch/mips/kernel/cpufreq/loongson2_clock.c
+++ b/arch/mips/kernel/cpufreq/loongson2_clock.c
@@ -7,6 +7,7 @@
  * for more details.
  */
 
+#include <linux/module.h>
 #include <linux/cpufreq.h>
 #include <linux/platform_device.h>
 
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index 4f2971b..315fc0b 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -623,7 +623,7 @@ static int mipspmu_event_init(struct perf_event *event)
 	if (!atomic_inc_not_zero(&active_events)) {
 		if (atomic_read(&active_events) > MIPS_MAX_HWEVENTS) {
 			atomic_dec(&active_events);
-			return -ENOSPC;
+			return -EINVAL;
 		}
 
 		mutex_lock(&pmu_reserve_mutex);
@@ -732,15 +732,15 @@ static int validate_group(struct perf_event *event)
 	memset(&fake_cpuc, 0, sizeof(fake_cpuc));
 
 	if (!validate_event(&fake_cpuc, leader))
-		return -ENOSPC;
+		return -EINVAL;
 
 	list_for_each_entry(sibling, &leader->sibling_list, group_entry) {
 		if (!validate_event(&fake_cpuc, sibling))
-			return -ENOSPC;
+			return -EINVAL;
 	}
 
 	if (!validate_event(&fake_cpuc, event))
-		return -ENOSPC;
+		return -EINVAL;
 
 	return 0;
 }
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 4792065..a632bc1 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -591,6 +591,8 @@ einval:	li	v0, -ENOSYS
 	sys	sys_syncfs		1
 	sys	sys_sendmmsg		4
 	sys	sys_setns		2
+	sys	sys_process_vm_readv	6	/* 4345 */
+	sys	sys_process_vm_writev	6
 	.endm
 
 	/* We pre-compute the number of _instruction_ bytes needed to
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index fb7334b..3b5a5e9 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -430,4 +430,6 @@ sys_call_table:
 	PTR	sys_syncfs
 	PTR	sys_sendmmsg
 	PTR	sys_setns
+	PTR	sys_process_vm_readv
+	PTR	sys_process_vm_writev		/* 5305 */
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 6de1f59..6be6f70 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -430,4 +430,6 @@ EXPORT(sysn32_call_table)
 	PTR	sys_syncfs
 	PTR	compat_sys_sendmmsg
 	PTR	sys_setns
+	PTR	compat_sys_process_vm_readv
+	PTR	compat_sys_process_vm_writev	/* 6310 */
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 1d81316..5422855 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -548,4 +548,6 @@ sys_call_table:
 	PTR	sys_syncfs
 	PTR	compat_sys_sendmmsg
 	PTR	sys_setns
+	PTR	compat_sys_process_vm_readv	/* 4345 */
+	PTR	compat_sys_process_vm_writev
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 261ccbc..5c8a49d 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1596,7 +1596,8 @@ void __cpuinit per_cpu_trap_init(void)
 	}
 #endif /* CONFIG_MIPS_MT_SMTC */
 
-	cpu_data[cpu].asid_cache = ASID_FIRST_VERSION;
+	if (!cpu_data[cpu].asid_cache)
+		cpu_data[cpu].asid_cache = ASID_FIRST_VERSION;
 
 	atomic_inc(&init_mm.mm_count);
 	current->active_mm = &init_mm;
diff --git a/arch/mips/lantiq/clk.c b/arch/mips/lantiq/clk.c
index 7e9c0ff..77ed70f 100644
--- a/arch/mips/lantiq/clk.c
+++ b/arch/mips/lantiq/clk.c
@@ -7,7 +7,7 @@
  * Copyright (C) 2010 John Crispin <blogic@openwrt.org>
  */
 #include <linux/io.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/arch/mips/lantiq/devices.c b/arch/mips/lantiq/devices.c
index 44a3677..de1cb2b 100644
--- a/arch/mips/lantiq/devices.c
+++ b/arch/mips/lantiq/devices.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/kernel.h>
diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c
index 56ba007..e34fcfd 100644
--- a/arch/mips/lantiq/prom.c
+++ b/arch/mips/lantiq/prom.c
@@ -6,7 +6,7 @@
  * Copyright (C) 2010 John Crispin <blogic@openwrt.org>
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/clk.h>
 #include <asm/bootinfo.h>
 #include <asm/time.h>
diff --git a/arch/mips/lantiq/setup.c b/arch/mips/lantiq/setup.c
index 9b8af77..1ff6c9d 100644
--- a/arch/mips/lantiq/setup.c
+++ b/arch/mips/lantiq/setup.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/io.h>
 #include <linux/ioport.h>
 #include <asm/bootinfo.h>
diff --git a/arch/mips/lantiq/xway/clk-ase.c b/arch/mips/lantiq/xway/clk-ase.c
index 22d823a..6522583 100644
--- a/arch/mips/lantiq/xway/clk-ase.c
+++ b/arch/mips/lantiq/xway/clk-ase.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/io.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/clk.h>
 
diff --git a/arch/mips/lantiq/xway/clk-xway.c b/arch/mips/lantiq/xway/clk-xway.c
index ddd3959..696b1a3 100644
--- a/arch/mips/lantiq/xway/clk-xway.c
+++ b/arch/mips/lantiq/xway/clk-xway.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/io.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/init.h>
 #include <linux/clk.h>
 
diff --git a/arch/mips/lantiq/xway/devices.c b/arch/mips/lantiq/xway/devices.c
index d0e32ab..d614aa7 100644
--- a/arch/mips/lantiq/xway/devices.c
+++ b/arch/mips/lantiq/xway/devices.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/mtd/physmap.h>
diff --git a/arch/mips/lantiq/xway/dma.c b/arch/mips/lantiq/xway/dma.c
index 4278a45..cbb6ae5 100644
--- a/arch/mips/lantiq/xway/dma.c
+++ b/arch/mips/lantiq/xway/dma.c
@@ -19,6 +19,7 @@
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/dma-mapping.h>
+#include <linux/export.h>
 
 #include <lantiq_soc.h>
 #include <xway_dma.h>
diff --git a/arch/mips/lantiq/xway/gpio.c b/arch/mips/lantiq/xway/gpio.c
index a321451..d2fa98f 100644
--- a/arch/mips/lantiq/xway/gpio.c
+++ b/arch/mips/lantiq/xway/gpio.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/slab.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
 #include <linux/ioport.h>
diff --git a/arch/mips/lantiq/xway/gpio_ebu.c b/arch/mips/lantiq/xway/gpio_ebu.c
index a479355..b91c7f1 100644
--- a/arch/mips/lantiq/xway/gpio_ebu.c
+++ b/arch/mips/lantiq/xway/gpio_ebu.c
@@ -7,7 +7,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
diff --git a/arch/mips/lantiq/xway/gpio_stp.c b/arch/mips/lantiq/xway/gpio_stp.c
index 67d59d6..ff9991c 100644
--- a/arch/mips/lantiq/xway/gpio_stp.c
+++ b/arch/mips/lantiq/xway/gpio_stp.c
@@ -9,7 +9,7 @@
 
 #include <linux/slab.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/platform_device.h>
 #include <linux/mutex.h>
diff --git a/arch/mips/lantiq/xway/prom-ase.c b/arch/mips/lantiq/xway/prom-ase.c
index abe49f4..ae4959a 100644
--- a/arch/mips/lantiq/xway/prom-ase.c
+++ b/arch/mips/lantiq/xway/prom-ase.c
@@ -6,7 +6,7 @@
  *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/clk.h>
 #include <asm/bootinfo.h>
 #include <asm/time.h>
diff --git a/arch/mips/lantiq/xway/prom-xway.c b/arch/mips/lantiq/xway/prom-xway.c
index 1686692a..2228133 100644
--- a/arch/mips/lantiq/xway/prom-xway.c
+++ b/arch/mips/lantiq/xway/prom-xway.c
@@ -6,7 +6,7 @@
  *  Copyright (C) 2010 John Crispin <blogic@openwrt.org>
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/clk.h>
 #include <asm/bootinfo.h>
 #include <asm/time.h>
diff --git a/arch/mips/lantiq/xway/reset.c b/arch/mips/lantiq/xway/reset.c
index a1be36d..3d41f0b 100644
--- a/arch/mips/lantiq/xway/reset.c
+++ b/arch/mips/lantiq/xway/reset.c
@@ -10,7 +10,7 @@
 #include <linux/io.h>
 #include <linux/ioport.h>
 #include <linux/pm.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <asm/reboot.h>
 
 #include <lantiq_soc.h>
diff --git a/arch/mips/nxp/pnx8550/common/pci.c b/arch/mips/nxp/pnx8550/common/pci.c
deleted file mode 100644
index 98e86dd..0000000
--- a/arch/mips/nxp/pnx8550/common/pci.c
+++ /dev/null
@@ -1,134 +0,0 @@
-/*
- *
- * BRIEF MODULE DESCRIPTION
- *
- * Author: source@mvista.com
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- */
-#include <linux/types.h>
-#include <linux/pci.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-
-#include <pci.h>
-#include <glb.h>
-#include <nand.h>
-
-static struct resource pci_io_resource = {
-	.start	= PNX8550_PCIIO + 0x1000,	/* reserve regacy I/O space */
-	.end	= PNX8550_PCIIO + PNX8550_PCIIO_SIZE,
-	.name	= "pci IO space",
-	.flags	= IORESOURCE_IO
-};
-
-static struct resource pci_mem_resource = {
-	.start	= PNX8550_PCIMEM,
-	.end	= PNX8550_PCIMEM + PNX8550_PCIMEM_SIZE - 1,
-	.name	= "pci memory space",
-	.flags	= IORESOURCE_MEM
-};
-
-extern struct pci_ops pnx8550_pci_ops;
-
-static struct pci_controller pnx8550_controller = {
-	.pci_ops	= &pnx8550_pci_ops,
-	.io_map_base	= PNX8550_PORT_BASE,
-	.io_resource	= &pci_io_resource,
-	.mem_resource	= &pci_mem_resource,
-};
-
-/* Return the total size of DRAM-memory, (RANK0 + RANK1) */
-static inline unsigned long get_system_mem_size(void)
-{
-	/* Read IP2031_RANK0_ADDR_LO */
-	unsigned long dram_r0_lo = inl(PCI_BASE | 0x65010);
-	/* Read IP2031_RANK1_ADDR_HI */
-	unsigned long dram_r1_hi = inl(PCI_BASE | 0x65018);
-
-	return dram_r1_hi - dram_r0_lo + 1;
-}
-
-static int __init pnx8550_pci_setup(void)
-{
-	int pci_mem_code;
-	int mem_size = get_system_mem_size() >> 20;
-
-	/* Clear the Global 2 Register, PCI Inta Output Enable Registers
-	   Bit 1:Enable DAC Powerdown
-	  -> 0:DACs are enabled and are working normally
-	     1:DACs are powerdown
-	   Bit 0:Enable of PCI inta output
-	  -> 0 = Disable PCI inta output
-	     1 = Enable PCI inta output
-	*/
-	PNX8550_GLB2_ENAB_INTA_O = 0;
-
-	/* Calc the PCI mem size code */
-	if (mem_size >= 128)
-		pci_mem_code = SIZE_128M;
-	else if (mem_size >= 64)
-		pci_mem_code = SIZE_64M;
-	else if (mem_size >= 32)
-		pci_mem_code = SIZE_32M;
-	else
-		pci_mem_code = SIZE_16M;
-
-	/* Set PCI_XIO registers */
-	outl(pci_mem_resource.start, PCI_BASE | PCI_BASE1_LO);
-	outl(pci_mem_resource.end + 1, PCI_BASE | PCI_BASE1_HI);
-	outl(pci_io_resource.start, PCI_BASE | PCI_BASE2_LO);
-	outl(pci_io_resource.end, PCI_BASE | PCI_BASE2_HI);
-
-	/* Send memory transaction via PCI_BASE2 */
-	outl(0x00000001, PCI_BASE | PCI_IO);
-
-	/* Unlock the setup register */
-	outl(0xca, PCI_BASE | PCI_UNLOCKREG);
-
-	/*
-	 * BAR0 of PNX8550 (pci base 10) must be zero in order for ide
-	 * to work, and in order for bus_to_baddr to work without any
-	 * hacks.
-	 */
-	outl(0x00000000, PCI_BASE | PCI_BASE10);
-
-	/*
-	 *These two bars are set by default or the boot code.
-	 * However, it's safer to set them here so we're not boot
-	 * code dependent.
-	 */
-	outl(0x1be00000, PCI_BASE | PCI_BASE14);  /* PNX MMIO */
-	outl(PNX8550_NAND_BASE_ADDR, PCI_BASE | PCI_BASE18);  /* XIO      */
-
-	outl(PCI_EN_TA |
-	     PCI_EN_PCI2MMI |
-	     PCI_EN_XIO |
-	     PCI_SETUP_BASE18_SIZE(SIZE_32M) |
-	     PCI_SETUP_BASE18_EN |
-	     PCI_SETUP_BASE14_EN |
-	     PCI_SETUP_BASE10_PREF |
-	     PCI_SETUP_BASE10_SIZE(pci_mem_code) |
-	     PCI_SETUP_CFGMANAGE_EN |
-	     PCI_SETUP_PCIARB_EN,
-	     PCI_BASE |
-	     PCI_SETUP);	/* PCI_SETUP */
-	outl(0x00000000, PCI_BASE | PCI_CTRL);	/* PCI_CONTROL */
-
-	register_pci_controller(&pnx8550_controller);
-
-	return 0;
-}
-
-arch_initcall(pnx8550_pci_setup);
diff --git a/arch/mips/nxp/pnx8550/common/setup.c b/arch/mips/nxp/pnx8550/common/setup.c
deleted file mode 100644
index 71adac3..0000000
--- a/arch/mips/nxp/pnx8550/common/setup.c
+++ /dev/null
@@ -1,143 +0,0 @@
-/*
- *
- * 2.6 port, Embedded Alley Solutions, Inc
- *
- *  Based on Per Hallsmark, per.hallsmark@mvista.com
- *
- *  This program is free software; you can distribute it and/or modify it
- *  under the terms of the GNU General Public License (Version 2) as
- *  published by the Free Software Foundation.
- *
- *  This program is distributed in the hope it will be useful, but WITHOUT
- *  ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- *  FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- *  for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place - Suite 330, Boston MA 02111-1307, USA.
- */
-#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/irq.h>
-#include <linux/mm.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/serial_pnx8xxx.h>
-#include <linux/pm.h>
-
-#include <asm/cpu.h>
-#include <asm/bootinfo.h>
-#include <asm/irq.h>
-#include <asm/mipsregs.h>
-#include <asm/reboot.h>
-#include <asm/pgtable.h>
-#include <asm/time.h>
-
-#include <glb.h>
-#include <int.h>
-#include <pci.h>
-#include <uart.h>
-#include <nand.h>
-
-extern void __init board_setup(void);
-extern void pnx8550_machine_restart(char *);
-extern void pnx8550_machine_halt(void);
-extern void pnx8550_machine_power_off(void);
-extern struct resource ioport_resource;
-extern struct resource iomem_resource;
-extern char *prom_getcmdline(void);
-
-struct resource standard_io_resources[] = {
-	{
-		.start	= 0x00,
-		.end	= 0x1f,
-		.name	= "dma1",
-		.flags	= IORESOURCE_BUSY
-	}, {
-		.start	= 0x40,
-		.end	= 0x5f,
-		.name	= "timer",
-		.flags	= IORESOURCE_BUSY
-	}, {
-		.start	= 0x80,
-		.end	= 0x8f,
-		.name	= "dma page reg",
-		.flags	= IORESOURCE_BUSY
-	}, {
-		.start	= 0xc0,
-		.end	= 0xdf,
-		.name	= "dma2",
-		.flags	= IORESOURCE_BUSY
-	},
-};
-
-#define STANDARD_IO_RESOURCES ARRAY_SIZE(standard_io_resources)
-
-extern struct resource pci_io_resource;
-extern struct resource pci_mem_resource;
-
-/* Return the total size of DRAM-memory, (RANK0 + RANK1) */
-unsigned long get_system_mem_size(void)
-{
-	/* Read IP2031_RANK0_ADDR_LO */
-	unsigned long dram_r0_lo = inl(PCI_BASE | 0x65010);
-	/* Read IP2031_RANK1_ADDR_HI */
-	unsigned long dram_r1_hi = inl(PCI_BASE | 0x65018);
-
-	return dram_r1_hi - dram_r0_lo + 1;
-}
-
-int pnx8550_console_port = -1;
-
-void __init plat_mem_setup(void)
-{
-	int i;
-	char* argptr;
-
-	board_setup();  /* board specific setup */
-
-        _machine_restart = pnx8550_machine_restart;
-        _machine_halt = pnx8550_machine_halt;
-        pm_power_off = pnx8550_machine_power_off;
-
-	/* Clear the Global 2 Register, PCI Inta Output Enable Registers
-	   Bit 1:Enable DAC Powerdown
-	  -> 0:DACs are enabled and are working normally
-	     1:DACs are powerdown
-	   Bit 0:Enable of PCI inta output
-	  -> 0 = Disable PCI inta output
-	     1 = Enable PCI inta output
-	*/
-	PNX8550_GLB2_ENAB_INTA_O = 0;
-
-	/* IO/MEM resources. */
-	set_io_port_base(PNX8550_PORT_BASE);
-	ioport_resource.start = 0;
-	ioport_resource.end = ~0;
-	iomem_resource.start = 0;
-	iomem_resource.end = ~0;
-
-	/* Request I/O space for devices on this board */
-	for (i = 0; i < STANDARD_IO_RESOURCES; i++)
-		request_resource(&ioport_resource, standard_io_resources + i);
-
-	/* Place the Mode Control bit for GPIO pin 16 in primary function */
-	/* Pin 16 is used by UART1, UA1_TX                                */
-	outl((PNX8550_GPIO_MODE_PRIMOP << PNX8550_GPIO_MC_16_BIT) |
-			(PNX8550_GPIO_MODE_PRIMOP << PNX8550_GPIO_MC_17_BIT),
-			PNX8550_GPIO_MC1);
-
-	argptr = prom_getcmdline();
-	if ((argptr = strstr(argptr, "console=ttyS")) != NULL) {
-		argptr += strlen("console=ttyS");
-		pnx8550_console_port = *argptr == '0' ? 0 : 1;
-
-		/* We must initialize the UART (console) before early printk */
-		/* Set LCR to 8-bit and BAUD to 38400 (no 5)                */
-		ip3106_lcr(UART_BASE, pnx8550_console_port) =
-			PNX8XXX_UART_LCR_8BIT;
-		ip3106_baud(UART_BASE, pnx8550_console_port) = 5;
-	}
-}
diff --git a/arch/mips/pci/pci-alchemy.c b/arch/mips/pci/pci-alchemy.c
index 4ee5710..b5ce041 100644
--- a/arch/mips/pci/pci-alchemy.c
+++ b/arch/mips/pci/pci-alchemy.c
@@ -7,6 +7,7 @@
  * Support for all devices (greater than 16) added by David Gathright.
  */
 
+#include <linux/export.h>
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
diff --git a/arch/mips/pci/pci-lantiq.c b/arch/mips/pci/pci-lantiq.c
index 8656388..be1e1af 100644
--- a/arch/mips/pci/pci-lantiq.c
+++ b/arch/mips/pci/pci-lantiq.c
@@ -13,6 +13,7 @@
 #include <linux/delay.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
+#include <linux/export.h>
 #include <linux/platform_device.h>
 
 #include <asm/pci.h>
diff --git a/arch/mips/pmc-sierra/yosemite/prom.c b/arch/mips/pmc-sierra/yosemite/prom.c
index cf4c868..dcc926e 100644
--- a/arch/mips/pmc-sierra/yosemite/prom.c
+++ b/arch/mips/pmc-sierra/yosemite/prom.c
@@ -102,7 +102,7 @@ void __init prom_init(void)
 
 	/* Get the boot parameters */
 	for (i = 1; i < argc; i++) {
-		if (strlen(arcs_cmdline) + strlen(arg[i] + 1) >=
+		if (strlen(arcs_cmdline) + strlen(arg[i]) + 1 >=
 		    sizeof(arcs_cmdline))
 			break;
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index b177caa..951e18f 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -345,7 +345,7 @@ config ARCH_ENABLE_MEMORY_HOTREMOVE
 
 config KEXEC
 	bool "kexec system call (EXPERIMENTAL)"
-	depends on (PPC_BOOK3S || FSL_BOOKE || (44x && !SMP && !47x)) && EXPERIMENTAL
+	depends on (PPC_BOOK3S || FSL_BOOKE || (44x && !SMP && !PPC_47x)) && EXPERIMENTAL
 	help
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 57af16e..70ba0c0 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -255,12 +255,6 @@ checkbin:
 		echo 'disable kernel modules' ; \
 		false ; \
 	fi
-	@if ! /bin/echo dssall | $(AS) -many -o $(TOUT) >/dev/null 2>&1 ; then \
-		echo -n '*** ${VERSION}.${PATCHLEVEL} kernels no longer build ' ; \
-		echo 'correctly with old versions of binutils.' ; \
-		echo '*** Please upgrade your binutils to 2.12.1 or newer' ; \
-		false ; \
-	fi
 
 CLEAN_FILES += $(TOUT)
 
diff --git a/arch/powerpc/boot/dts/p1023rds.dts b/arch/powerpc/boot/dts/p1023rds.dts
index d9b7767..d3b4782 100644
--- a/arch/powerpc/boot/dts/p1023rds.dts
+++ b/arch/powerpc/boot/dts/p1023rds.dts
@@ -449,6 +449,7 @@
 			interrupt-parent = <&mpic>;
 			interrupts = <16 2>;
 			interrupt-map-mask = <0xf800 0 0 7>;
+			/* IRQ[0:3] are pulled up on board, set to active-low */
 			interrupt-map = <
 				/* IDSEL 0x0 */
 				0000 0 0 1 &mpic 0 1
@@ -488,11 +489,15 @@
 			interrupt-parent = <&mpic>;
 			interrupts = <16 2>;
 			interrupt-map-mask = <0xf800 0 0 7>;
+			/*
+			 * IRQ[4:6] only for PCIe, set to active-high,
+			 * IRQ[7] is pulled up on board, set to active-low
+			 */
 			interrupt-map = <
 				/* IDSEL 0x0 */
-				0000 0 0 1 &mpic 4 1
-				0000 0 0 2 &mpic 5 1
-				0000 0 0 3 &mpic 6 1
+				0000 0 0 1 &mpic 4 2
+				0000 0 0 2 &mpic 5 2
+				0000 0 0 3 &mpic 6 2
 				0000 0 0 4 &mpic 7 1
 				>;
 			ranges = <0x2000000 0x0 0xa0000000
@@ -527,12 +532,16 @@
 			interrupt-parent = <&mpic>;
 			interrupts = <16 2>;
 			interrupt-map-mask = <0xf800 0 0 7>;
+			/*
+			 * IRQ[8:10] are pulled up on board, set to active-low
+			 * IRQ[11] only for PCIe, set to active-high,
+			 */
 			interrupt-map = <
 				/* IDSEL 0x0 */
 				0000 0 0 1 &mpic 8 1
 				0000 0 0 2 &mpic 9 1
 				0000 0 0 3 &mpic 10 1
-				0000 0 0 4 &mpic 11 1
+				0000 0 0 4 &mpic 11 2
 				>;
 			ranges = <0x2000000 0x0 0x80000000
 				  0x2000000 0x0 0x80000000
diff --git a/arch/powerpc/boot/dts/tqm8548-bigflash.dts b/arch/powerpc/boot/dts/tqm8548-bigflash.dts
index 9452c3c..d918752 100644
--- a/arch/powerpc/boot/dts/tqm8548-bigflash.dts
+++ b/arch/powerpc/boot/dts/tqm8548-bigflash.dts
@@ -352,7 +352,7 @@
 		ranges = <
 			0 0x0 0xfc000000 0x04000000	// NOR FLASH bank 1
 			1 0x0 0xf8000000 0x08000000	// NOR FLASH bank 0
-			2 0x0 0xa3000000 0x00008000	// CAN (2 x i82527)
+			2 0x0 0xa3000000 0x00008000	// CAN (2 x CC770)
 			3 0x0 0xa3010000 0x00008000	// NAND FLASH
 
 		>;
@@ -393,18 +393,27 @@
 		};
 
 		/* Note: CAN support needs be enabled in U-Boot */
-		can0@2,0 {
-			compatible = "intel,82527"; // Bosch CC770
+		can@2,0 {
+			compatible = "bosch,cc770"; // Bosch CC770
 			reg = <2 0x0 0x100>;
 			interrupts = <4 1>;
 			interrupt-parent = <&mpic>;
+			bosch,external-clock-frequency = <16000000>;
+			bosch,disconnect-rx1-input;
+			bosch,disconnect-tx1-output;
+			bosch,iso-low-speed-mux;
+			bosch,clock-out-frequency = <16000000>;
 		};
 
-		can1@2,100 {
-			compatible = "intel,82527"; // Bosch CC770
+		can@2,100 {
+			compatible = "bosch,cc770"; // Bosch CC770
 			reg = <2 0x100 0x100>;
 			interrupts = <4 1>;
 			interrupt-parent = <&mpic>;
+			bosch,external-clock-frequency = <16000000>;
+			bosch,disconnect-rx1-input;
+			bosch,disconnect-tx1-output;
+			bosch,iso-low-speed-mux;
 		};
 
 		/* Note: NAND support needs to be enabled in U-Boot */
diff --git a/arch/powerpc/boot/dts/tqm8548.dts b/arch/powerpc/boot/dts/tqm8548.dts
index 619776f..988d887 100644
--- a/arch/powerpc/boot/dts/tqm8548.dts
+++ b/arch/powerpc/boot/dts/tqm8548.dts
@@ -352,7 +352,7 @@
 		ranges = <
 			0 0x0 0xfc000000 0x04000000	// NOR FLASH bank 1
 			1 0x0 0xf8000000 0x08000000	// NOR FLASH bank 0
-			2 0x0 0xe3000000 0x00008000	// CAN (2 x i82527)
+			2 0x0 0xe3000000 0x00008000	// CAN (2 x CC770)
 			3 0x0 0xe3010000 0x00008000	// NAND FLASH
 
 		>;
@@ -393,18 +393,27 @@
 		};
 
 		/* Note: CAN support needs be enabled in U-Boot */
-		can0@2,0 {
-			compatible = "intel,82527"; // Bosch CC770
+		can@2,0 {
+			compatible = "bosch,cc770"; // Bosch CC770
 			reg = <2 0x0 0x100>;
 			interrupts = <4 1>;
 			interrupt-parent = <&mpic>;
+			bosch,external-clock-frequency = <16000000>;
+			bosch,disconnect-rx1-input;
+			bosch,disconnect-tx1-output;
+			bosch,iso-low-speed-mux;
+			bosch,clock-out-frequency = <16000000>;
 		};
 
-		can1@2,100 {
-			compatible = "intel,82527"; // Bosch CC770
+		can@2,100 {
+			compatible = "bosch,cc770"; // Bosch CC770
 			reg = <2 0x100 0x100>;
 			interrupts = <4 1>;
 			interrupt-parent = <&mpic>;
+			bosch,external-clock-frequency = <16000000>;
+			bosch,disconnect-rx1-input;
+			bosch,disconnect-tx1-output;
+			bosch,iso-low-speed-mux;
 		};
 
 		/* Note: NAND support needs to be enabled in U-Boot */
diff --git a/arch/powerpc/boot/dts/tqm8xx.dts b/arch/powerpc/boot/dts/tqm8xx.dts
index f6da7ec..c3dba25 100644
--- a/arch/powerpc/boot/dts/tqm8xx.dts
+++ b/arch/powerpc/boot/dts/tqm8xx.dts
@@ -57,6 +57,7 @@
 
 		ranges = <
 			0x0 0x0 0x40000000 0x800000
+			0x3 0x0 0xc0000000 0x200
 		>;
 
 		flash@0,0 {
@@ -67,6 +68,30 @@
 			bank-width = <4>;
 			device-width = <2>;
 		};
+
+		/* Note: CAN support needs be enabled in U-Boot */
+		can@3,0 {
+			compatible = "intc,82527";
+			reg = <3 0x0 0x80>;
+			interrupts = <8 1>;
+			interrupt-parent = <&PIC>;
+			bosch,external-clock-frequency = <16000000>;
+			bosch,disconnect-rx1-input;
+			bosch,disconnect-tx1-output;
+			bosch,iso-low-speed-mux;
+			bosch,clock-out-frequency = <16000000>;
+		};
+
+		can@3,100 {
+			compatible = "intc,82527";
+			reg = <3 0x100 0x80>;
+			interrupts = <8 1>;
+			interrupt-parent = <&PIC>;
+			bosch,external-clock-frequency = <16000000>;
+			bosch,disconnect-rx1-input;
+			bosch,disconnect-tx1-output;
+			bosch,iso-low-speed-mux;
+		};
 	};
 
 	soc@fff00000 {
diff --git a/arch/powerpc/configs/ppc44x_defconfig b/arch/powerpc/configs/ppc44x_defconfig
index 6cdf1c0..3b98d73 100644
--- a/arch/powerpc/configs/ppc44x_defconfig
+++ b/arch/powerpc/configs/ppc44x_defconfig
@@ -52,6 +52,8 @@ CONFIG_MTD_CFI=y
 CONFIG_MTD_JEDECPROBE=y
 CONFIG_MTD_CFI_AMDSTD=y
 CONFIG_MTD_PHYSMAP_OF=y
+CONFIG_MTD_NAND=m
+CONFIG_MTD_NAND_NDFC=m
 CONFIG_MTD_UBI=m
 CONFIG_MTD_UBI_GLUEBI=m
 CONFIG_PROC_DEVICETREE=y
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index e2a4c26..02e41b5 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -49,13 +49,13 @@ static __inline__ int atomic_add_return(int a, atomic_t *v)
 	int t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%2		# atomic_add_return\n\
 	add	%0,%1,%0\n"
 	PPC405_ERR77(0,%2)
 "	stwcx.	%0,0,%2 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (a), "r" (&v->counter)
 	: "cc", "memory");
@@ -85,13 +85,13 @@ static __inline__ int atomic_sub_return(int a, atomic_t *v)
 	int t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%2		# atomic_sub_return\n\
 	subf	%0,%1,%0\n"
 	PPC405_ERR77(0,%2)
 "	stwcx.	%0,0,%2 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (a), "r" (&v->counter)
 	: "cc", "memory");
@@ -119,13 +119,13 @@ static __inline__ int atomic_inc_return(atomic_t *v)
 	int t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%1		# atomic_inc_return\n\
 	addic	%0,%0,1\n"
 	PPC405_ERR77(0,%1)
 "	stwcx.	%0,0,%1 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (&v->counter)
 	: "cc", "xer", "memory");
@@ -163,13 +163,13 @@ static __inline__ int atomic_dec_return(atomic_t *v)
 	int t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%1		# atomic_dec_return\n\
 	addic	%0,%0,-1\n"
 	PPC405_ERR77(0,%1)
 "	stwcx.	%0,0,%1\n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (&v->counter)
 	: "cc", "xer", "memory");
@@ -194,7 +194,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	int t;
 
 	__asm__ __volatile__ (
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%1		# __atomic_add_unless\n\
 	cmpw	0,%0,%3 \n\
 	beq-	2f \n\
@@ -202,7 +202,7 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	PPC405_ERR77(0,%2)
 "	stwcx.	%0,0,%1 \n\
 	bne-	1b \n"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 "	subf	%0,%2,%0 \n\
 2:"
 	: "=&r" (t)
@@ -226,7 +226,7 @@ static __inline__ int atomic_dec_if_positive(atomic_t *v)
 	int t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	lwarx	%0,0,%1		# atomic_dec_if_positive\n\
 	cmpwi	%0,1\n\
 	addi	%0,%0,-1\n\
@@ -234,7 +234,7 @@ static __inline__ int atomic_dec_if_positive(atomic_t *v)
 	PPC405_ERR77(0,%1)
 "	stwcx.	%0,0,%1\n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	"\n\
 2:"	: "=&b" (t)
 	: "r" (&v->counter)
@@ -285,12 +285,12 @@ static __inline__ long atomic64_add_return(long a, atomic64_t *v)
 	long t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%2		# atomic64_add_return\n\
 	add	%0,%1,%0\n\
 	stdcx.	%0,0,%2 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (a), "r" (&v->counter)
 	: "cc", "memory");
@@ -319,12 +319,12 @@ static __inline__ long atomic64_sub_return(long a, atomic64_t *v)
 	long t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%2		# atomic64_sub_return\n\
 	subf	%0,%1,%0\n\
 	stdcx.	%0,0,%2 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (a), "r" (&v->counter)
 	: "cc", "memory");
@@ -351,12 +351,12 @@ static __inline__ long atomic64_inc_return(atomic64_t *v)
 	long t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%1		# atomic64_inc_return\n\
 	addic	%0,%0,1\n\
 	stdcx.	%0,0,%1 \n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (&v->counter)
 	: "cc", "xer", "memory");
@@ -393,12 +393,12 @@ static __inline__ long atomic64_dec_return(atomic64_t *v)
 	long t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%1		# atomic64_dec_return\n\
 	addic	%0,%0,-1\n\
 	stdcx.	%0,0,%1\n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	: "=&r" (t)
 	: "r" (&v->counter)
 	: "cc", "xer", "memory");
@@ -418,13 +418,13 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 	long t;
 
 	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%1		# atomic64_dec_if_positive\n\
 	addic.	%0,%0,-1\n\
 	blt-	2f\n\
 	stdcx.	%0,0,%1\n\
 	bne-	1b"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 	"\n\
 2:"	: "=&r" (t)
 	: "r" (&v->counter)
@@ -450,14 +450,14 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
 	long t;
 
 	__asm__ __volatile__ (
-	PPC_RELEASE_BARRIER
+	PPC_ATOMIC_ENTRY_BARRIER
 "1:	ldarx	%0,0,%1		# __atomic_add_unless\n\
 	cmpd	0,%0,%3 \n\
 	beq-	2f \n\
 	add	%0,%2,%0 \n"
 "	stdcx.	%0,0,%1 \n\
 	bne-	1b \n"
-	PPC_ACQUIRE_BARRIER
+	PPC_ATOMIC_EXIT_BARRIER
 "	subf	%0,%2,%0 \n\
 2:"
 	: "=&r" (t)
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index e137afc..efdc926 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -124,14 +124,14 @@ static __inline__ unsigned long fn(			\
 	return (old & mask);				\
 }
 
-DEFINE_TESTOP(test_and_set_bits, or, PPC_RELEASE_BARRIER,
-	      PPC_ACQUIRE_BARRIER, 0)
+DEFINE_TESTOP(test_and_set_bits, or, PPC_ATOMIC_ENTRY_BARRIER,
+	      PPC_ATOMIC_EXIT_BARRIER, 0)
 DEFINE_TESTOP(test_and_set_bits_lock, or, "",
 	      PPC_ACQUIRE_BARRIER, 1)
-DEFINE_TESTOP(test_and_clear_bits, andc, PPC_RELEASE_BARRIER,
-	      PPC_ACQUIRE_BARRIER, 0)
-DEFINE_TESTOP(test_and_change_bits, xor, PPC_RELEASE_BARRIER,
-	      PPC_ACQUIRE_BARRIER, 0)
+DEFINE_TESTOP(test_and_clear_bits, andc, PPC_ATOMIC_ENTRY_BARRIER,
+	      PPC_ATOMIC_EXIT_BARRIER, 0)
+DEFINE_TESTOP(test_and_change_bits, xor, PPC_ATOMIC_ENTRY_BARRIER,
+	      PPC_ATOMIC_EXIT_BARRIER, 0)
 
 static __inline__ int test_and_set_bit(unsigned long nr,
 				       volatile unsigned long *addr)
diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h
index c94e4a3..2a9cf84 100644
--- a/arch/powerpc/include/asm/futex.h
+++ b/arch/powerpc/include/asm/futex.h
@@ -11,12 +11,13 @@
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \
   __asm__ __volatile ( \
-	PPC_RELEASE_BARRIER \
+	PPC_ATOMIC_ENTRY_BARRIER \
 "1:	lwarx	%0,0,%2\n" \
 	insn \
 	PPC405_ERR77(0, %2) \
 "2:	stwcx.	%1,0,%2\n" \
 	"bne-	1b\n" \
+	PPC_ATOMIC_EXIT_BARRIER \
 	"li	%1,0\n" \
 "3:	.section .fixup,\"ax\"\n" \
 "4:	li	%1,%3\n" \
@@ -92,14 +93,14 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
         __asm__ __volatile__ (
-        PPC_RELEASE_BARRIER
+        PPC_ATOMIC_ENTRY_BARRIER
 "1:     lwarx   %1,0,%3         # futex_atomic_cmpxchg_inatomic\n\
         cmpw    0,%1,%4\n\
         bne-    3f\n"
         PPC405_ERR77(0,%3)
 "2:     stwcx.  %5,0,%3\n\
         bne-    1b\n"
-        PPC_ACQUIRE_BARRIER
+        PPC_ATOMIC_EXIT_BARRIER
 "3:	.section .fixup,\"ax\"\n\
 4:	li	%0,%6\n\
 	b	3b\n\
diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index 08fe69e..0ad432b 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -149,12 +149,6 @@ struct kvm_regs {
 #define KVM_SREGS_E_UPDATE_DBSR		(1 << 3)
 
 /*
- * Book3S special bits to indicate contents in the struct by maintaining
- * backwards compatibility with older structs. If adding a new field,
- * please make sure to add a flag for that new field */
-#define KVM_SREGS_S_HIOR		(1 << 0)
-
-/*
  * In KVM_SET_SREGS, reserved/pad fields must be left untouched from a
  * previous KVM_GET_REGS.
  *
@@ -179,8 +173,6 @@ struct kvm_sregs {
 				__u64 ibat[8]; 
 				__u64 dbat[8]; 
 			} ppc32;
-			__u64 flags; /* KVM_SREGS_S_ */
-			__u64 hior;
 		} s;
 		struct {
 			union {
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index a384ffd..d4df013 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -90,8 +90,6 @@ struct kvmppc_vcpu_book3s {
 #endif
 	int context_id[SID_CONTEXTS];
 
-	bool hior_sregs;		/* HIOR is set by SREGS, not PVR */
-
 	struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE];
 	struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG];
 	struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE];
diff --git a/arch/powerpc/include/asm/reg_booke.h b/arch/powerpc/include/asm/reg_booke.h
index 28cdbd9..03c48e8 100644
--- a/arch/powerpc/include/asm/reg_booke.h
+++ b/arch/powerpc/include/asm/reg_booke.h
@@ -31,7 +31,7 @@
 
 #define MSR_		MSR_ME | MSR_CE
 #define MSR_KERNEL	MSR_ | MSR_64BIT
-#define MSR_USER32	MSR_ | MSR_PR | MSR_EE | MSR_DE
+#define MSR_USER32	MSR_ | MSR_PR | MSR_EE
 #define MSR_USER64	MSR_USER32 | MSR_64BIT
 #elif defined (CONFIG_40x)
 #define MSR_KERNEL	(MSR_ME|MSR_RI|MSR_IR|MSR_DR|MSR_CE)
diff --git a/arch/powerpc/include/asm/sections.h b/arch/powerpc/include/asm/sections.h
index 6fbce72..a0f358d 100644
--- a/arch/powerpc/include/asm/sections.h
+++ b/arch/powerpc/include/asm/sections.h
@@ -8,7 +8,7 @@
 
 #ifdef __powerpc64__
 
-extern char _end[];
+extern char __end_interrupts[];
 
 static inline int in_kernel_text(unsigned long addr)
 {
diff --git a/arch/powerpc/include/asm/synch.h b/arch/powerpc/include/asm/synch.h
index d7cab44..e682a71 100644
--- a/arch/powerpc/include/asm/synch.h
+++ b/arch/powerpc/include/asm/synch.h
@@ -13,6 +13,7 @@
 extern unsigned int __start___lwsync_fixup, __stop___lwsync_fixup;
 extern void do_lwsync_fixups(unsigned long value, void *fixup_start,
 			     void *fixup_end);
+extern void do_final_fixups(void);
 
 static inline void eieio(void)
 {
@@ -41,11 +42,15 @@ static inline void isync(void)
 	START_LWSYNC_SECTION(97);			\
 	isync;						\
 	MAKE_LWSYNC_SECTION_ENTRY(97, __lwsync_fixup);
-#define PPC_ACQUIRE_BARRIER	"\n" stringify_in_c(__PPC_ACQUIRE_BARRIER)
-#define PPC_RELEASE_BARRIER	stringify_in_c(LWSYNC) "\n"
+#define PPC_ACQUIRE_BARRIER	 "\n" stringify_in_c(__PPC_ACQUIRE_BARRIER)
+#define PPC_RELEASE_BARRIER	 stringify_in_c(LWSYNC) "\n"
+#define PPC_ATOMIC_ENTRY_BARRIER "\n" stringify_in_c(LWSYNC) "\n"
+#define PPC_ATOMIC_EXIT_BARRIER	 "\n" stringify_in_c(sync) "\n"
 #else
 #define PPC_ACQUIRE_BARRIER
 #define PPC_RELEASE_BARRIER
+#define PPC_ATOMIC_ENTRY_BARRIER
+#define PPC_ATOMIC_EXIT_BARRIER
 #endif
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 56212bc..4f80cf1 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -215,7 +215,22 @@ reenable_mmu:				/* re-enable mmu so we can */
 	stw	r9,8(r1)
 	stw	r11,12(r1)
 	stw	r3,ORIG_GPR3(r1)
+	/*
+	 * The trace_hardirqs_off will use CALLER_ADDR0 and CALLER_ADDR1.
+	 * If from user mode there is only one stack frame on the stack, and
+	 * accessing CALLER_ADDR1 will cause oops. So we need create a dummy
+	 * stack frame to make trace_hardirqs_off happy.
+	 */
+	andi.	r12,r12,MSR_PR
+	beq	11f
+	stwu	r1,-16(r1)
+	bl	trace_hardirqs_off
+	addi	r1,r1,16
+	b	12f
+
+11:
 	bl	trace_hardirqs_off
+12:
 	lwz	r0,GPR0(r1)
 	lwz	r3,ORIG_GPR3(r1)
 	lwz	r4,GPR4(r1)
diff --git a/arch/powerpc/kernel/jump_label.c b/arch/powerpc/kernel/jump_label.c
index 368d158..a1ed8a8 100644
--- a/arch/powerpc/kernel/jump_label.c
+++ b/arch/powerpc/kernel/jump_label.c
@@ -11,6 +11,7 @@
 #include <linux/jump_label.h>
 #include <asm/code-patching.h>
 
+#ifdef HAVE_JUMP_LABEL
 void arch_jump_label_transform(struct jump_entry *entry,
 			       enum jump_label_type type)
 {
@@ -21,3 +22,4 @@ void arch_jump_label_transform(struct jump_entry *entry,
 	else
 		patch_instruction(addr, PPC_INST_NOP);
 }
+#endif
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 35f2764..2985338 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -132,7 +132,6 @@ static void kvm_patch_ins_b(u32 *inst, int addr)
 	/* On relocatable kernels interrupts handlers and our code
 	   can be in different regions, so we don't patch them */
 
-	extern u32 __end_interrupts;
 	if ((ulong)inst < (ulong)&__end_interrupts)
 		return;
 #endif
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index f7d760a..7cd07b4 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -738,7 +738,7 @@ relocate_new_kernel:
 	mr      r5, r31
 
 	li	r0, 0
-#elif defined(CONFIG_44x)  && !defined(CONFIG_47x)
+#elif defined(CONFIG_44x)  && !defined(CONFIG_PPC_47x)
 
 /*
  * Code for setting up 1:1 mapping for PPC440x for KEXEC
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 9054ca9..6457574 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -486,28 +486,6 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	new_thread = &new->thread;
 	old_thread = &current->thread;
 
-#if defined(CONFIG_PPC_BOOK3E_64)
-	/* XXX Current Book3E code doesn't deal with kernel side DBCR0,
-	 * we always hold the user values, so we set it now.
-	 *
-	 * However, we ensure the kernel MSR:DE is appropriately cleared too
-	 * to avoid spurrious single step exceptions in the kernel.
-	 *
-	 * This will have to change to merge with the ppc32 code at some point,
-	 * but I don't like much what ppc32 is doing today so there's some
-	 * thinking needed there
-	 */
-	if ((new_thread->dbcr0 | old_thread->dbcr0) & DBCR0_IDM) {
-		u32 dbcr0;
-
-		mtmsr(mfmsr() & ~MSR_DE);
-		isync();
-		dbcr0 = mfspr(SPRN_DBCR0);
-		dbcr0 = (dbcr0 & DBCR0_EDM) | new_thread->dbcr0;
-		mtspr(SPRN_DBCR0, dbcr0);
-	}
-#endif /* CONFIG_PPC64_BOOK3E */
-
 #ifdef CONFIG_PPC64
 	/*
 	 * Collect processor utilization data per process
@@ -657,7 +635,7 @@ void show_regs(struct pt_regs * regs)
 	if ((regs->trap != 0xc00) && cpu_has_feature(CPU_FTR_CFAR))
 		printk("CFAR: "REG"\n", regs->orig_gpr3);
 	if (trap == 0x300 || trap == 0x600)
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
 		printk("DEAR: "REG", ESR: "REG"\n", regs->dar, regs->dsisr);
 #else
 		printk("DAR: "REG", DSISR: %08lx\n", regs->dar, regs->dsisr);
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index b4fa661..cc58486 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1579,10 +1579,8 @@ static void __init prom_instantiate_rtas(void)
 		return;
 
 	base = alloc_down(size, PAGE_SIZE, 0);
-	if (base == 0) {
-		prom_printf("RTAS allocation failed !\n");
-		return;
-	}
+	if (base == 0)
+		prom_panic("Could not allocate memory for RTAS\n");
 
 	rtas_inst = call_prom("open", 1, 1, ADDR("/rtas"));
 	if (!IHANDLE_VALID(rtas_inst)) {
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index c1ce863..ac76108 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -107,6 +107,8 @@ notrace unsigned long __init early_init(unsigned long dt_ptr)
 			 PTRRELOC(&__start___lwsync_fixup),
 			 PTRRELOC(&__stop___lwsync_fixup));
 
+	do_final_fixups();
+
 	return KERNELBASE + offset;
 }
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 1a9dea8..fb9bb46 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -359,6 +359,7 @@ void __init setup_system(void)
 			  &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
 	do_lwsync_fixups(cur_cpu_spec->cpu_features,
 			 &__start___lwsync_fixup, &__stop___lwsync_fixup);
+	do_final_fixups();
 
 	/*
 	 * Unflatten the device-tree passed by prom_init or kexec
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 78b76dc..836a5a1 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -97,7 +97,7 @@ static inline int put_sigset_t(compat_sigset_t __user *uset, sigset_t *set)
 	compat_sigset_t	cset;
 
 	switch (_NSIG_WORDS) {
-	case 4: cset.sig[5] = set->sig[3] & 0xffffffffull;
+	case 4: cset.sig[6] = set->sig[3] & 0xffffffffull;
 		cset.sig[7] = set->sig[3] >> 32;
 	case 3: cset.sig[4] = set->sig[2] & 0xffffffffull;
 		cset.sig[5] = set->sig[2] >> 32;
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 4e59082..5459d14 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -1298,14 +1298,12 @@ void __kprobes DebugException(struct pt_regs *regs, unsigned long debug_status)
 
 		if (user_mode(regs)) {
 			current->thread.dbcr0 &= ~DBCR0_IC;
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
 			if (DBCR_ACTIVE_EVENTS(current->thread.dbcr0,
 					       current->thread.dbcr1))
 				regs->msr |= MSR_DE;
 			else
 				/* Make sure the IDM bit is off */
 				current->thread.dbcr0 &= ~DBCR0_IDM;
-#endif
 		}
 
 		_exception(SIGTRAP, regs, TRAP_TRACE, regs->nip);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 0cdbc07..0cb137a 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -44,6 +44,7 @@
 #include <asm/processor.h>
 #include <asm/cputhreads.h>
 #include <asm/page.h>
+#include <asm/hvcall.h>
 #include <linux/gfp.h>
 #include <linux/sched.h>
 #include <linux/vmalloc.h>
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index bc4d50d..3c791e1 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -151,16 +151,14 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
 #ifdef CONFIG_PPC_BOOK3S_64
 	if ((pvr >= 0x330000) && (pvr < 0x70330000)) {
 		kvmppc_mmu_book3s_64_init(vcpu);
-		if (!to_book3s(vcpu)->hior_sregs)
-			to_book3s(vcpu)->hior = 0xfff00000;
+		to_book3s(vcpu)->hior = 0xfff00000;
 		to_book3s(vcpu)->msr_mask = 0xffffffffffffffffULL;
 		vcpu->arch.cpu_type = KVM_CPU_3S_64;
 	} else
 #endif
 	{
 		kvmppc_mmu_book3s_32_init(vcpu);
-		if (!to_book3s(vcpu)->hior_sregs)
-			to_book3s(vcpu)->hior = 0;
+		to_book3s(vcpu)->hior = 0;
 		to_book3s(vcpu)->msr_mask = 0xffffffffULL;
 		vcpu->arch.cpu_type = KVM_CPU_3S_32;
 	}
@@ -797,9 +795,6 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 		}
 	}
 
-	if (sregs->u.s.flags & KVM_SREGS_S_HIOR)
-		sregs->u.s.hior = to_book3s(vcpu)->hior;
-
 	return 0;
 }
 
@@ -836,11 +831,6 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	/* Flush the MMU after messing with the segments */
 	kvmppc_mmu_pte_flush(vcpu, 0, 0);
 
-	if (sregs->u.s.flags & KVM_SREGS_S_HIOR) {
-		to_book3s(vcpu)->hior_sregs = true;
-		to_book3s(vcpu)->hior = sregs->u.s.hior;
-	}
-
 	return 0;
 }
 
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index efbf9ad..607fbdf 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -208,7 +208,6 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_PPC_BOOKE_SREGS:
 #else
 	case KVM_CAP_PPC_SEGSTATE:
-	case KVM_CAP_PPC_HIOR:
 	case KVM_CAP_PPC_PAPR:
 #endif
 	case KVM_CAP_PPC_UNSET_IRQ:
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 0d08d01..7a8a748 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -18,6 +18,8 @@
 #include <linux/init.h>
 #include <asm/cputable.h>
 #include <asm/code-patching.h>
+#include <asm/page.h>
+#include <asm/sections.h>
 
 
 struct fixup_entry {
@@ -128,6 +130,27 @@ void do_lwsync_fixups(unsigned long value, void *fixup_start, void *fixup_end)
 	}
 }
 
+void do_final_fixups(void)
+{
+#if defined(CONFIG_PPC64) && defined(CONFIG_RELOCATABLE)
+	int *src, *dest;
+	unsigned long length;
+
+	if (PHYSICAL_START == 0)
+		return;
+
+	src = (int *)(KERNELBASE + PHYSICAL_START);
+	dest = (int *)KERNELBASE;
+	length = (__end_interrupts - _stext) / sizeof(int);
+
+	while (length--) {
+		patch_instruction(dest, *src);
+		src++;
+		dest++;
+	}
+#endif
+}
+
 #ifdef CONFIG_FTR_FIXUP_SELFTEST
 
 #define check(x)	\
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 5964371..8558b57 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -15,6 +15,7 @@
 #include <linux/of_fdt.h>
 #include <linux/memblock.h>
 #include <linux/bootmem.h>
+#include <linux/moduleparam.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
diff --git a/arch/powerpc/platforms/85xx/Kconfig b/arch/powerpc/platforms/85xx/Kconfig
index 45023e2..d7946be2 100644
--- a/arch/powerpc/platforms/85xx/Kconfig
+++ b/arch/powerpc/platforms/85xx/Kconfig
@@ -203,7 +203,7 @@ config P3060_QDS
 	select PPC_E500MC
 	select PHYS_64BIT
 	select SWIOTLB
-	select MPC8xxx_GPIO
+	select GPIO_MPC8XXX
 	select HAS_RAPIDIO
 	select PPC_EPAPR_HV_PIC
 	help
diff --git a/arch/powerpc/platforms/85xx/p3060_qds.c b/arch/powerpc/platforms/85xx/p3060_qds.c
index 01dcf44..081cf4a 100644
--- a/arch/powerpc/platforms/85xx/p3060_qds.c
+++ b/arch/powerpc/platforms/85xx/p3060_qds.c
@@ -70,7 +70,7 @@ define_machine(p3060_qds) {
 	.power_save		= e500_idle,
 };
 
-machine_device_initcall(p3060_qds, declare_of_platform_devices);
+machine_device_initcall(p3060_qds, corenet_ds_publish_devices);
 
 #ifdef CONFIG_SWIOTLB
 machine_arch_initcall(p3060_qds, swiotlb_setup_bus_notifier);
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index e458872..3fe6d92 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -347,7 +347,7 @@ config SIMPLE_GPIO
 
 config MCU_MPC8349EMITX
 	bool "MPC8349E-mITX MCU driver"
-	depends on I2C && PPC_83xx
+	depends on I2C=y && PPC_83xx
 	select GENERIC_GPIO
 	select ARCH_REQUIRE_GPIOLIB
 	help
diff --git a/arch/powerpc/platforms/ps3/interrupt.c b/arch/powerpc/platforms/ps3/interrupt.c
index 404bc52..1d6f4f4 100644
--- a/arch/powerpc/platforms/ps3/interrupt.c
+++ b/arch/powerpc/platforms/ps3/interrupt.c
@@ -88,6 +88,7 @@ struct ps3_private {
 	struct ps3_bmp bmp __attribute__ ((aligned (PS3_BMP_MINALIGN)));
 	u64 ppe_id;
 	u64 thread_id;
+	unsigned long ipi_mask;
 };
 
 static DEFINE_PER_CPU(struct ps3_private, ps3_private);
@@ -144,7 +145,11 @@ static void ps3_chip_unmask(struct irq_data *d)
 static void ps3_chip_eoi(struct irq_data *d)
 {
 	const struct ps3_private *pd = irq_data_get_irq_chip_data(d);
-	lv1_end_of_interrupt_ext(pd->ppe_id, pd->thread_id, d->irq);
+
+	/* non-IPIs are EOIed here. */
+
+	if (!test_bit(63 - d->irq, &pd->ipi_mask))
+		lv1_end_of_interrupt_ext(pd->ppe_id, pd->thread_id, d->irq);
 }
 
 /**
@@ -691,6 +696,16 @@ void __init ps3_register_ipi_debug_brk(unsigned int cpu, unsigned int virq)
 		cpu, virq, pd->bmp.ipi_debug_brk_mask);
 }
 
+void __init ps3_register_ipi_irq(unsigned int cpu, unsigned int virq)
+{
+	struct ps3_private *pd = &per_cpu(ps3_private, cpu);
+
+	set_bit(63 - virq, &pd->ipi_mask);
+
+	DBG("%s:%d: cpu %u, virq %u, ipi_mask %lxh\n", __func__, __LINE__,
+		cpu, virq, pd->ipi_mask);
+}
+
 static unsigned int ps3_get_irq(void)
 {
 	struct ps3_private *pd = &__get_cpu_var(ps3_private);
@@ -720,6 +735,12 @@ static unsigned int ps3_get_irq(void)
 		BUG();
 	}
 #endif
+
+	/* IPIs are EOIed here. */
+
+	if (test_bit(63 - plug, &pd->ipi_mask))
+		lv1_end_of_interrupt_ext(pd->ppe_id, pd->thread_id, plug);
+
 	return plug;
 }
 
diff --git a/arch/powerpc/platforms/ps3/platform.h b/arch/powerpc/platforms/ps3/platform.h
index 9a196a8..1a633ed 100644
--- a/arch/powerpc/platforms/ps3/platform.h
+++ b/arch/powerpc/platforms/ps3/platform.h
@@ -43,6 +43,7 @@ void ps3_mm_shutdown(void);
 void ps3_init_IRQ(void);
 void ps3_shutdown_IRQ(int cpu);
 void __init ps3_register_ipi_debug_brk(unsigned int cpu, unsigned int virq);
+void __init ps3_register_ipi_irq(unsigned int cpu, unsigned int virq);
 
 /* smp */
 
diff --git a/arch/powerpc/platforms/ps3/smp.c b/arch/powerpc/platforms/ps3/smp.c
index 4c44794..efc1cd8 100644
--- a/arch/powerpc/platforms/ps3/smp.c
+++ b/arch/powerpc/platforms/ps3/smp.c
@@ -59,46 +59,49 @@ static void ps3_smp_message_pass(int cpu, int msg)
 
 static int ps3_smp_probe(void)
 {
-	return 2;
-}
+	int cpu;
 
-static void __init ps3_smp_setup_cpu(int cpu)
-{
-	int result;
-	unsigned int *virqs = per_cpu(ps3_ipi_virqs, cpu);
-	int i;
+	for (cpu = 0; cpu < 2; cpu++) {
+		int result;
+		unsigned int *virqs = per_cpu(ps3_ipi_virqs, cpu);
+		int i;
 
-	DBG(" -> %s:%d: (%d)\n", __func__, __LINE__, cpu);
+		DBG(" -> %s:%d: (%d)\n", __func__, __LINE__, cpu);
 
-	/*
-	 * Check assumptions on ps3_ipi_virqs[] indexing. If this
-	 * check fails, then a different mapping of PPC_MSG_
-	 * to index needs to be setup.
-	 */
+		/*
+		* Check assumptions on ps3_ipi_virqs[] indexing. If this
+		* check fails, then a different mapping of PPC_MSG_
+		* to index needs to be setup.
+		*/
 
-	BUILD_BUG_ON(PPC_MSG_CALL_FUNCTION    != 0);
-	BUILD_BUG_ON(PPC_MSG_RESCHEDULE       != 1);
-	BUILD_BUG_ON(PPC_MSG_CALL_FUNC_SINGLE != 2);
-	BUILD_BUG_ON(PPC_MSG_DEBUGGER_BREAK   != 3);
+		BUILD_BUG_ON(PPC_MSG_CALL_FUNCTION    != 0);
+		BUILD_BUG_ON(PPC_MSG_RESCHEDULE       != 1);
+		BUILD_BUG_ON(PPC_MSG_CALL_FUNC_SINGLE != 2);
+		BUILD_BUG_ON(PPC_MSG_DEBUGGER_BREAK   != 3);
 
-	for (i = 0; i < MSG_COUNT; i++) {
-		result = ps3_event_receive_port_setup(cpu, &virqs[i]);
+		for (i = 0; i < MSG_COUNT; i++) {
+			result = ps3_event_receive_port_setup(cpu, &virqs[i]);
 
-		if (result)
-			continue;
+			if (result)
+				continue;
 
-		DBG("%s:%d: (%d, %d) => virq %u\n",
-			__func__, __LINE__, cpu, i, virqs[i]);
+			DBG("%s:%d: (%d, %d) => virq %u\n",
+				__func__, __LINE__, cpu, i, virqs[i]);
 
-		result = smp_request_message_ipi(virqs[i], i);
+			result = smp_request_message_ipi(virqs[i], i);
 
-		if (result)
-			virqs[i] = NO_IRQ;
-	}
+			if (result)
+				virqs[i] = NO_IRQ;
+			else
+				ps3_register_ipi_irq(cpu, virqs[i]);
+		}
 
-	ps3_register_ipi_debug_brk(cpu, virqs[PPC_MSG_DEBUGGER_BREAK]);
+		ps3_register_ipi_debug_brk(cpu, virqs[PPC_MSG_DEBUGGER_BREAK]);
 
-	DBG(" <- %s:%d: (%d)\n", __func__, __LINE__, cpu);
+		DBG(" <- %s:%d: (%d)\n", __func__, __LINE__, cpu);
+	}
+
+	return 2;
 }
 
 void ps3_smp_cleanup_cpu(int cpu)
@@ -121,7 +124,6 @@ static struct smp_ops_t ps3_smp_ops = {
 	.probe		= ps3_smp_probe,
 	.message_pass	= ps3_smp_message_pass,
 	.kick_cpu	= smp_generic_kick_cpu,
-	.setup_cpu	= ps3_smp_setup_cpu,
 };
 
 void smp_init_ps3(void)
diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c
index af1a5df..b6731e4 100644
--- a/arch/powerpc/sysdev/ehv_pic.c
+++ b/arch/powerpc/sysdev/ehv_pic.c
@@ -280,6 +280,7 @@ void __init ehv_pic_init(void)
 
 	if (!ehv_pic->irqhost) {
 		of_node_put(np);
+		kfree(ehv_pic);
 		return;
 	}
 
diff --git a/arch/powerpc/sysdev/fsl_lbc.c b/arch/powerpc/sysdev/fsl_lbc.c
index c4d96fa..d5c3c90 100644
--- a/arch/powerpc/sysdev/fsl_lbc.c
+++ b/arch/powerpc/sysdev/fsl_lbc.c
@@ -328,6 +328,7 @@ static int __devinit fsl_lbc_ctrl_probe(struct platform_device *dev)
 err:
 	iounmap(fsl_lbc_ctrl_dev->regs);
 	kfree(fsl_lbc_ctrl_dev);
+	fsl_lbc_ctrl_dev = NULL;
 	return ret;
 }
 
diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c
index 3363fbc..ceb09cb 100644
--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@@ -216,7 +216,7 @@ int qe_setbrg(enum qe_clock brg, unsigned int rate, unsigned int multiplier)
 	/* Errata QE_General4, which affects some MPC832x and MPC836x SOCs, says
 	   that the BRG divisor must be even if you're not using divide-by-16
 	   mode. */
-	if (!div16 && (divisor & 1))
+	if (!div16 && (divisor & 1) && (divisor > 3))
 		divisor++;
 
 	tempval = ((divisor - 1) << QE_BRGC_DIVISOR_SHIFT) |
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index a9fbd43..373679b 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -572,6 +572,7 @@ config KEXEC
 config CRASH_DUMP
 	bool "kernel crash dumps"
 	depends on 64BIT
+	select KEXEC
 	help
 	  Generate crash dump after being started by kexec.
 	  Crash dump kernels are loaded in the main kernel with kexec-tools
diff --git a/arch/s390/crypto/crypt_s390.h b/arch/s390/crypto/crypt_s390.h
index 4967677..ffd1ac2 100644
--- a/arch/s390/crypto/crypt_s390.h
+++ b/arch/s390/crypto/crypt_s390.h
@@ -368,9 +368,12 @@ static inline int crypt_s390_func_available(int func,
 
 	if (facility_mask & CRYPT_S390_MSA && !test_facility(17))
 		return 0;
-	if (facility_mask & CRYPT_S390_MSA3 && !test_facility(76))
+
+	if (facility_mask & CRYPT_S390_MSA3 &&
+	    (!test_facility(2) || !test_facility(76)))
 		return 0;
-	if (facility_mask & CRYPT_S390_MSA4 && !test_facility(77))
+	if (facility_mask & CRYPT_S390_MSA4 &&
+	    (!test_facility(2) || !test_facility(77)))
 		return 0;
 
 	switch (func & CRYPT_S390_OP_MASK) {
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 24e1847..b0c235c 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -47,7 +47,7 @@ struct sca_block {
 #define KVM_HPAGE_MASK(x)	(~(KVM_HPAGE_SIZE(x) - 1))
 #define KVM_PAGES_PER_HPAGE(x)	(KVM_HPAGE_SIZE(x) / PAGE_SIZE)
 
-#define CPUSTAT_HOST       0x80000000
+#define CPUSTAT_STOPPED    0x80000000
 #define CPUSTAT_WAIT       0x10000000
 #define CPUSTAT_ECALL_PEND 0x08000000
 #define CPUSTAT_STOP_INT   0x04000000
@@ -139,6 +139,7 @@ struct kvm_vcpu_stat {
 	u32 instruction_stfl;
 	u32 instruction_tprot;
 	u32 instruction_sigp_sense;
+	u32 instruction_sigp_sense_running;
 	u32 instruction_sigp_external_call;
 	u32 instruction_sigp_emergency;
 	u32 instruction_sigp_stop;
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 34ede0e..4f289ff 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -593,14 +593,16 @@ static inline pgste_t pgste_update_all(pte_t *ptep, pgste_t pgste)
 	unsigned long address, bits;
 	unsigned char skey;
 
+	if (!pte_present(*ptep))
+		return pgste;
 	address = pte_val(*ptep) & PAGE_MASK;
 	skey = page_get_storage_key(address);
 	bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
 	/* Clear page changed & referenced bit in the storage key */
-	if (bits) {
-		skey ^= bits;
-		page_set_storage_key(address, skey, 1);
-	}
+	if (bits & _PAGE_CHANGED)
+		page_set_storage_key(address, skey ^ bits, 1);
+	else if (bits)
+		page_reset_referenced(address);
 	/* Transfer page changed & referenced bit to guest bits in pgste */
 	pgste_val(pgste) |= bits << 48;		/* RCP_GR_BIT & RCP_GC_BIT */
 	/* Get host changed & referenced bits from pgste */
@@ -625,6 +627,8 @@ static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste)
 #ifdef CONFIG_PGSTE
 	int young;
 
+	if (!pte_present(*ptep))
+		return pgste;
 	young = page_reset_referenced(pte_val(*ptep) & PAGE_MASK);
 	/* Transfer page referenced bit to pte software bit (host view) */
 	if (young || (pgste_val(pgste) & RCP_HR_BIT))
@@ -638,13 +642,15 @@ static inline pgste_t pgste_update_young(pte_t *ptep, pgste_t pgste)
 
 }
 
-static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste)
+static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste, pte_t entry)
 {
 #ifdef CONFIG_PGSTE
 	unsigned long address;
 	unsigned long okey, nkey;
 
-	address = pte_val(*ptep) & PAGE_MASK;
+	if (!pte_present(entry))
+		return;
+	address = pte_val(entry) & PAGE_MASK;
 	okey = nkey = page_get_storage_key(address);
 	nkey &= ~(_PAGE_ACC_BITS | _PAGE_FP_BIT);
 	/* Set page access key and fetch protection bit from pgste */
@@ -712,7 +718,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 
 	if (mm_has_pgste(mm)) {
 		pgste = pgste_get_lock(ptep);
-		pgste_set_pte(ptep, pgste);
+		pgste_set_pte(ptep, pgste, entry);
 		*ptep = entry;
 		pgste_set_unlock(ptep, pgste);
 	} else
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 5a09971..097183c 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -82,6 +82,7 @@ extern unsigned int user_mode;
 #define MACHINE_FLAG_LPAR	(1UL << 12)
 #define MACHINE_FLAG_SPP	(1UL << 13)
 #define MACHINE_FLAG_TOPOLOGY	(1UL << 14)
+#define MACHINE_FLAG_STCKF	(1UL << 15)
 
 #define MACHINE_IS_VM		(S390_lowcore.machine_flags & MACHINE_FLAG_VM)
 #define MACHINE_IS_KVM		(S390_lowcore.machine_flags & MACHINE_FLAG_KVM)
@@ -100,6 +101,7 @@ extern unsigned int user_mode;
 #define MACHINE_HAS_PFMF	(0)
 #define MACHINE_HAS_SPP		(0)
 #define MACHINE_HAS_TOPOLOGY	(0)
+#define MACHINE_HAS_STCKF	(0)
 #else /* __s390x__ */
 #define MACHINE_HAS_IEEE	(1)
 #define MACHINE_HAS_CSP		(1)
@@ -111,6 +113,7 @@ extern unsigned int user_mode;
 #define MACHINE_HAS_PFMF	(S390_lowcore.machine_flags & MACHINE_FLAG_PFMF)
 #define MACHINE_HAS_SPP		(S390_lowcore.machine_flags & MACHINE_FLAG_SPP)
 #define MACHINE_HAS_TOPOLOGY	(S390_lowcore.machine_flags & MACHINE_FLAG_TOPOLOGY)
+#define MACHINE_HAS_STCKF	(S390_lowcore.machine_flags & MACHINE_FLAG_STCKF)
 #endif /* __s390x__ */
 
 #define ZFCPDUMP_HSA_SIZE	(32UL<<20)
diff --git a/arch/s390/include/asm/timex.h b/arch/s390/include/asm/timex.h
index d610bef..c447a27 100644
--- a/arch/s390/include/asm/timex.h
+++ b/arch/s390/include/asm/timex.h
@@ -90,7 +90,7 @@ static inline unsigned long long get_clock_fast(void)
 {
 	unsigned long long clk;
 
-	if (test_facility(25))
+	if (MACHINE_HAS_STCKF)
 		asm volatile(".insn	s,0xb27c0000,%0" : "=Q" (clk) : : "cc");
 	else
 		clk = get_clock();
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 404bdb96..58de4c9 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -277,7 +277,9 @@
 #define __NR_clock_adjtime	337
 #define __NR_syncfs		338
 #define __NR_setns		339
-#define NR_syscalls 340
+#define __NR_process_vm_readv	340
+#define __NR_process_vm_writev	341
+#define NR_syscalls 342
 
 /* 
  * There are some system calls that are not present on 64 bit, some
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
index 5006a1d..18c51df 100644
--- a/arch/s390/kernel/compat_wrapper.S
+++ b/arch/s390/kernel/compat_wrapper.S
@@ -1627,3 +1627,23 @@ ENTRY(sys_setns_wrapper)
 	lgfr	%r2,%r2			# int
 	lgfr	%r3,%r3			# int
 	jg	sys_setns
+
+ENTRY(compat_sys_process_vm_readv_wrapper)
+	lgfr	%r2,%r2			# compat_pid_t
+	llgtr	%r3,%r3			# struct compat_iovec __user *
+	llgfr	%r4,%r4			# unsigned long
+	llgtr	%r5,%r5			# struct compat_iovec __user *
+	llgfr	%r6,%r6			# unsigned long
+	llgf	%r0,164(%r15)		# unsigned long
+	stg	%r0,160(%r15)
+	jg	sys_process_vm_readv
+
+ENTRY(compat_sys_process_vm_writev_wrapper)
+	lgfr	%r2,%r2			# compat_pid_t
+	llgtr	%r3,%r3			# struct compat_iovec __user *
+	llgfr	%r4,%r4			# unsigned long
+	llgtr	%r5,%r5			# struct compat_iovec __user *
+	llgfr	%r6,%r6			# unsigned long
+	llgf	%r0,164(%r15)		# unsigned long
+	stg	%r0,160(%r15)
+	jg	sys_process_vm_writev
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 37394b3..c9ffe00 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -390,6 +390,8 @@ static __init void detect_machine_facilities(void)
 		S390_lowcore.machine_flags |= MACHINE_FLAG_MVCOS;
 	if (test_facility(40))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_SPP;
+	if (test_facility(25))
+		S390_lowcore.machine_flags |= MACHINE_FLAG_STCKF;
 #endif
 }
 
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index 450931a..573bc29 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -296,13 +296,6 @@ static int __poke_user(struct task_struct *child, addr_t addr, addr_t data)
 		     ((data & PSW_MASK_EA) && !(data & PSW_MASK_BA))))
 			/* Invalid psw mask. */
 			return -EINVAL;
-		if (addr == (addr_t) &dummy->regs.psw.addr)
-			/*
-			 * The debugger changed the instruction address,
-			 * reset system call restart, see signal.c:do_signal
-			 */
-			task_thread_info(child)->system_call = 0;
-
 		*(addr_t *)((addr_t) &task_pt_regs(child)->psw + addr) = data;
 
 	} else if (addr < (addr_t) (&dummy->regs.orig_gpr2)) {
@@ -614,11 +607,6 @@ static int __poke_user_compat(struct task_struct *child,
 			/* Transfer 31 bit amode bit to psw mask. */
 			regs->psw.mask = (regs->psw.mask & ~PSW_MASK_BA) |
 				(__u64)(tmp & PSW32_ADDR_AMODE);
-			/*
-			 * The debugger changed the instruction address,
-			 * reset system call restart, see signal.c:do_signal
-			 */
-			task_thread_info(child)->system_call = 0;
 		} else {
 			/* gpr 0-15 */
 			*(__u32*)((addr_t) &regs->psw + addr*2 + 4) = tmp;
@@ -905,6 +893,14 @@ static int s390_last_break_get(struct task_struct *target,
 	return 0;
 }
 
+static int s390_last_break_set(struct task_struct *target,
+			       const struct user_regset *regset,
+			       unsigned int pos, unsigned int count,
+			       const void *kbuf, const void __user *ubuf)
+{
+	return 0;
+}
+
 #endif
 
 static int s390_system_call_get(struct task_struct *target,
@@ -951,6 +947,7 @@ static const struct user_regset s390_regsets[] = {
 		.size = sizeof(long),
 		.align = sizeof(long),
 		.get = s390_last_break_get,
+		.set = s390_last_break_set,
 	},
 #endif
 	[REGSET_SYSTEM_CALL] = {
@@ -1116,6 +1113,14 @@ static int s390_compat_last_break_get(struct task_struct *target,
 	return 0;
 }
 
+static int s390_compat_last_break_set(struct task_struct *target,
+				      const struct user_regset *regset,
+				      unsigned int pos, unsigned int count,
+				      const void *kbuf, const void __user *ubuf)
+{
+	return 0;
+}
+
 static const struct user_regset s390_compat_regsets[] = {
 	[REGSET_GENERAL] = {
 		.core_note_type = NT_PRSTATUS,
@@ -1139,6 +1144,7 @@ static const struct user_regset s390_compat_regsets[] = {
 		.size = sizeof(long),
 		.align = sizeof(long),
 		.get = s390_compat_last_break_get,
+		.set = s390_compat_last_break_set,
 	},
 	[REGSET_SYSTEM_CALL] = {
 		.core_note_type = NT_S390_SYSTEM_CALL,
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 8ac6bfa..e54c4ff 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -211,6 +211,8 @@ static void __init setup_zfcpdump(unsigned int console_devno)
 
 	if (ipl_info.type != IPL_TYPE_FCP_DUMP)
 		return;
+	if (OLDMEM_BASE)
+		return;
 	if (console_devno != -1)
 		sprintf(str, " cio_ignore=all,!0.0.%04x,!0.0.%04x",
 			ipl_info.data.fcp.dev_id.devno, console_devno);
@@ -482,7 +484,7 @@ static void __init setup_memory_end(void)
 
 
 #ifdef CONFIG_ZFCPDUMP
-	if (ipl_info.type == IPL_TYPE_FCP_DUMP) {
+	if (ipl_info.type == IPL_TYPE_FCP_DUMP && !OLDMEM_BASE) {
 		memory_end = ZFCPDUMP_HSA_SIZE;
 		memory_end_set = 1;
 	}
@@ -577,7 +579,7 @@ static unsigned long __init find_crash_base(unsigned long crash_size,
 		*msg = "first memory chunk must be at least crashkernel size";
 		return 0;
 	}
-	if (is_kdump_kernel() && (crash_size == OLDMEM_SIZE))
+	if (OLDMEM_BASE && crash_size == OLDMEM_SIZE)
 		return OLDMEM_BASE;
 
 	for (i = MEMORY_CHUNKS - 1; i >= 0; i--) {
diff --git a/arch/s390/kernel/signal.c b/arch/s390/kernel/signal.c
index 05a85bc..7f6f9f3 100644
--- a/arch/s390/kernel/signal.c
+++ b/arch/s390/kernel/signal.c
@@ -460,9 +460,9 @@ void do_signal(struct pt_regs *regs)
 						     regs->svc_code >> 16);
 				break;
 			}
-			/* No longer in a system call */
-			clear_thread_flag(TIF_SYSCALL);
 		}
+		/* No longer in a system call */
+		clear_thread_flag(TIF_SYSCALL);
 
 		if ((is_compat_task() ?
 		     handle_signal32(signr, &ka, &info, oldset, regs) :
@@ -486,6 +486,7 @@ void do_signal(struct pt_regs *regs)
 	}
 
 	/* No handlers present - check for system call restart */
+	clear_thread_flag(TIF_SYSCALL);
 	if (current_thread_info()->system_call) {
 		regs->svc_code = current_thread_info()->system_call;
 		switch (regs->gprs[2]) {
@@ -500,9 +501,6 @@ void do_signal(struct pt_regs *regs)
 			regs->gprs[2] = regs->orig_gpr2;
 			set_thread_flag(TIF_SYSCALL);
 			break;
-		default:
-			clear_thread_flag(TIF_SYSCALL);
-			break;
 		}
 	}
 
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 73eb08c..bcab2f0 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -348,3 +348,5 @@ SYSCALL(sys_open_by_handle_at,sys_open_by_handle_at,compat_sys_open_by_handle_at
 SYSCALL(sys_clock_adjtime,sys_clock_adjtime,compat_sys_clock_adjtime_wrapper)
 SYSCALL(sys_syncfs,sys_syncfs,sys_syncfs_wrapper)
 SYSCALL(sys_setns,sys_setns,sys_setns_wrapper)
+SYSCALL(sys_process_vm_readv,sys_process_vm_readv,compat_sys_process_vm_readv_wrapper) /* 340 */
+SYSCALL(sys_process_vm_writev,sys_process_vm_writev,compat_sys_process_vm_writev_wrapper)
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 77b8942..fdb5b8c 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -68,8 +68,10 @@ static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
 	return mask;
 }
 
-static void add_cpus_to_mask(struct topology_cpu *tl_cpu,
-			     struct mask_info *book, struct mask_info *core)
+static struct mask_info *add_cpus_to_mask(struct topology_cpu *tl_cpu,
+					  struct mask_info *book,
+					  struct mask_info *core,
+					  int z10)
 {
 	unsigned int cpu;
 
@@ -88,10 +90,16 @@ static void add_cpus_to_mask(struct topology_cpu *tl_cpu,
 			cpu_book_id[lcpu] = book->id;
 #endif
 			cpumask_set_cpu(lcpu, &core->mask);
-			cpu_core_id[lcpu] = core->id;
+			if (z10) {
+				cpu_core_id[lcpu] = rcpu;
+				core = core->next;
+			} else {
+				cpu_core_id[lcpu] = core->id;
+			}
 			smp_cpu_polarization[lcpu] = tl_cpu->pp;
 		}
 	}
+	return core;
 }
 
 static void clear_masks(void)
@@ -123,18 +131,41 @@ static void tl_to_cores(struct sysinfo_15_1_x *info)
 {
 #ifdef CONFIG_SCHED_BOOK
 	struct mask_info *book = &book_info;
+	struct cpuid cpu_id;
 #else
 	struct mask_info *book = NULL;
 #endif
 	struct mask_info *core = &core_info;
 	union topology_entry *tle, *end;
+	int z10 = 0;
 
-
+#ifdef CONFIG_SCHED_BOOK
+	get_cpu_id(&cpu_id);
+	z10 = cpu_id.machine == 0x2097 || cpu_id.machine == 0x2098;
+#endif
 	spin_lock_irq(&topology_lock);
 	clear_masks();
 	tle = info->tle;
 	end = (union topology_entry *)((unsigned long)info + info->length);
 	while (tle < end) {
+#ifdef CONFIG_SCHED_BOOK
+		if (z10) {
+			switch (tle->nl) {
+			case 1:
+				book = book->next;
+				book->id = tle->container.id;
+				break;
+			case 0:
+				core = add_cpus_to_mask(&tle->cpu, book, core, z10);
+				break;
+			default:
+				clear_masks();
+				goto out;
+			}
+			tle = next_tle(tle);
+			continue;
+		}
+#endif
 		switch (tle->nl) {
 #ifdef CONFIG_SCHED_BOOK
 		case 2:
@@ -147,7 +178,7 @@ static void tl_to_cores(struct sysinfo_15_1_x *info)
 			core->id = tle->container.id;
 			break;
 		case 0:
-			add_cpus_to_mask(&tle->cpu, book, core);
+			add_cpus_to_mask(&tle->cpu, book, core, z10);
 			break;
 		default:
 			clear_masks();
@@ -328,8 +359,8 @@ void __init s390_init_cpu_topology(void)
 	for (i = 0; i < TOPOLOGY_NR_MAG; i++)
 		printk(" %d", info->mag[i]);
 	printk(" / %d\n", info->mnest);
-	alloc_masks(info, &core_info, 2);
+	alloc_masks(info, &core_info, 1);
 #ifdef CONFIG_SCHED_BOOK
-	alloc_masks(info, &book_info, 3);
+	alloc_masks(info, &book_info, 2);
 #endif
 }
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 56fe6bc..e4c79eb 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -43,6 +43,8 @@ SECTIONS
 
 	NOTES :text :note
 
+	.dummy : { *(.dummy) } :data
+
 	RODATA
 
 #ifdef CONFIG_SHARED_KERNEL
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 87cedd6..8943e82 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -70,7 +70,7 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
 		return -EOPNOTSUPP;
 	}
 
-	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+	atomic_set_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
 	vcpu->run->s390_reset_flags |= KVM_S390_RESET_SUBSYSTEM;
 	vcpu->run->s390_reset_flags |= KVM_S390_RESET_IPL;
 	vcpu->run->s390_reset_flags |= KVM_S390_RESET_CPU_INIT;
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index c7c5189..0243454 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -132,7 +132,6 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 	int rc = 0;
 
 	vcpu->stat.exit_stop_request++;
-	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	spin_lock_bh(&vcpu->arch.local_int.lock);
 	if (vcpu->arch.local_int.action_bits & ACTION_STORE_ON_STOP) {
 		vcpu->arch.local_int.action_bits &= ~ACTION_STORE_ON_STOP;
@@ -149,6 +148,8 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 	}
 
 	if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) {
+		atomic_set_mask(CPUSTAT_STOPPED,
+				&vcpu->arch.sie_block->cpuflags);
 		vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP;
 		VCPU_EVENT(vcpu, 3, "%s", "cpu stopped");
 		rc = -EOPNOTSUPP;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 87c1670..278ee00 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -252,6 +252,7 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 			offsetof(struct _lowcore, restart_psw), sizeof(psw_t));
 		if (rc == -EFAULT)
 			exception = 1;
+		atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
 		break;
 
 	case KVM_S390_PROGRAM_INT:
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 0bd3bea..d1c44573 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -65,6 +65,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
 	{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
 	{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
+	{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
 	{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
 	{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
 	{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
@@ -127,6 +128,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	switch (ext) {
 	case KVM_CAP_S390_PSW:
 	case KVM_CAP_S390_GMAP:
+	case KVM_CAP_SYNC_MMU:
 		r = 1;
 		break;
 	default:
@@ -270,10 +272,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	restore_fp_regs(&vcpu->arch.guest_fpregs);
 	restore_access_regs(vcpu->arch.guest_acrs);
 	gmap_enable(vcpu->arch.gmap);
+	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
 	gmap_disable(vcpu->arch.gmap);
 	save_fp_regs(&vcpu->arch.guest_fpregs);
 	save_access_regs(vcpu->arch.guest_acrs);
@@ -301,7 +305,9 @@ static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
-	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH | CPUSTAT_SM);
+	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
+						    CPUSTAT_SM |
+						    CPUSTAT_STOPPED);
 	vcpu->arch.sie_block->ecb   = 6;
 	vcpu->arch.sie_block->eca   = 0xC1002001U;
 	vcpu->arch.sie_block->fac   = (int) (long) facilities;
@@ -428,7 +434,7 @@ static int kvm_arch_vcpu_ioctl_set_initial_psw(struct kvm_vcpu *vcpu, psw_t psw)
 {
 	int rc = 0;
 
-	if (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_RUNNING)
+	if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_STOPPED))
 		rc = -EBUSY;
 	else {
 		vcpu->run->psw_mask = psw.mask;
@@ -501,7 +507,7 @@ rerun_vcpu:
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
 
-	atomic_set_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);
+	atomic_clear_mask(CPUSTAT_STOPPED, &vcpu->arch.sie_block->cpuflags);
 
 	BUG_ON(vcpu->kvm->arch.float_int.local_int[vcpu->vcpu_id] == NULL);
 
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 3916263..d026389 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -336,6 +336,7 @@ static int handle_tprot(struct kvm_vcpu *vcpu)
 	u64 address1 = disp1 + base1 ? vcpu->arch.guest_gprs[base1] : 0;
 	u64 address2 = disp2 + base2 ? vcpu->arch.guest_gprs[base2] : 0;
 	struct vm_area_struct *vma;
+	unsigned long user_address;
 
 	vcpu->stat.instruction_tprot++;
 
@@ -349,9 +350,14 @@ static int handle_tprot(struct kvm_vcpu *vcpu)
 		return -EOPNOTSUPP;
 
 
+	/* we must resolve the address without holding the mmap semaphore.
+	 * This is ok since the userspace hypervisor is not supposed to change
+	 * the mapping while the guest queries the memory. Otherwise the guest
+	 * might crash or get wrong info anyway. */
+	user_address = (unsigned long) __guestaddr_to_user(vcpu, address1);
+
 	down_read(&current->mm->mmap_sem);
-	vma = find_vma(current->mm,
-			(unsigned long) __guestaddr_to_user(vcpu, address1));
+	vma = find_vma(current->mm, user_address);
 	if (!vma) {
 		up_read(&current->mm->mmap_sem);
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index f815118..0a7941d 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -31,9 +31,11 @@
 #define SIGP_SET_PREFIX        0x0d
 #define SIGP_STORE_STATUS_ADDR 0x0e
 #define SIGP_SET_ARCH          0x12
+#define SIGP_SENSE_RUNNING     0x15
 
 /* cpu status bits */
 #define SIGP_STAT_EQUIPMENT_CHECK   0x80000000UL
+#define SIGP_STAT_NOT_RUNNING	    0x00000400UL
 #define SIGP_STAT_INCORRECT_STATE   0x00000200UL
 #define SIGP_STAT_INVALID_PARAMETER 0x00000100UL
 #define SIGP_STAT_EXT_CALL_PENDING  0x00000080UL
@@ -57,8 +59,8 @@ static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
 	spin_lock(&fi->lock);
 	if (fi->local_int[cpu_addr] == NULL)
 		rc = 3; /* not operational */
-	else if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
-		 & CPUSTAT_RUNNING) {
+	else if (!(atomic_read(fi->local_int[cpu_addr]->cpuflags)
+		  & CPUSTAT_STOPPED)) {
 		*reg &= 0xffffffff00000000UL;
 		rc = 1; /* status stored */
 	} else {
@@ -251,7 +253,7 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 
 	spin_lock_bh(&li->lock);
 	/* cpu must be in stopped state */
-	if (atomic_read(li->cpuflags) & CPUSTAT_RUNNING) {
+	if (!(atomic_read(li->cpuflags) & CPUSTAT_STOPPED)) {
 		rc = 1; /* incorrect state */
 		*reg &= SIGP_STAT_INCORRECT_STATE;
 		kfree(inti);
@@ -275,6 +277,38 @@ out_fi:
 	return rc;
 }
 
+static int __sigp_sense_running(struct kvm_vcpu *vcpu, u16 cpu_addr,
+				unsigned long *reg)
+{
+	int rc;
+	struct kvm_s390_float_interrupt *fi = &vcpu->kvm->arch.float_int;
+
+	if (cpu_addr >= KVM_MAX_VCPUS)
+		return 3; /* not operational */
+
+	spin_lock(&fi->lock);
+	if (fi->local_int[cpu_addr] == NULL)
+		rc = 3; /* not operational */
+	else {
+		if (atomic_read(fi->local_int[cpu_addr]->cpuflags)
+		    & CPUSTAT_RUNNING) {
+			/* running */
+			rc = 1;
+		} else {
+			/* not running */
+			*reg &= 0xffffffff00000000UL;
+			*reg |= SIGP_STAT_NOT_RUNNING;
+			rc = 0;
+		}
+	}
+	spin_unlock(&fi->lock);
+
+	VCPU_EVENT(vcpu, 4, "sensed running status of cpu %x rc %x", cpu_addr,
+		   rc);
+
+	return rc;
+}
+
 int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 {
 	int r1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
@@ -331,6 +365,11 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 		rc = __sigp_set_prefix(vcpu, cpu_addr, parameter,
 				       &vcpu->arch.guest_gprs[r1]);
 		break;
+	case SIGP_SENSE_RUNNING:
+		vcpu->stat.instruction_sigp_sense_running++;
+		rc = __sigp_sense_running(vcpu, cpu_addr,
+					  &vcpu->arch.guest_gprs[r1]);
+		break;
 	case SIGP_RESTART:
 		vcpu->stat.instruction_sigp_restart++;
 		/* user space must know about restart */
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 1766def..a9a3018 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -587,8 +587,13 @@ static void pfault_interrupt(unsigned int ext_int_code,
 		} else {
 			/* Completion interrupt was faster than initial
 			 * interrupt. Set pfault_wait to -1 so the initial
-			 * interrupt doesn't put the task to sleep. */
-			tsk->thread.pfault_wait = -1;
+			 * interrupt doesn't put the task to sleep.
+			 * If the task is not running, ignore the completion
+			 * interrupt since it must be a leftover of a PFAULT
+			 * CANCEL operation which didn't remove all pending
+			 * completion interrupts. */
+			if (tsk->state == TASK_RUNNING)
+				tsk->thread.pfault_wait = -1;
 		}
 		put_task_struct(tsk);
 	} else {
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index 5b31a8e..a790cc6 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -431,10 +431,6 @@ extern unsigned long *sparc_valid_addr_bitmap;
 #define kern_addr_valid(addr) \
 	(test_bit(__pa((unsigned long)(addr))>>20, sparc_valid_addr_bitmap))
 
-extern int io_remap_pfn_range(struct vm_area_struct *vma,
-			      unsigned long from, unsigned long pfn,
-			      unsigned long size, pgprot_t prot);
-
 /*
  * For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in
  * its high 4 bits.  These macros/functions put it there or get it from there.
@@ -443,6 +439,22 @@ extern int io_remap_pfn_range(struct vm_area_struct *vma,
 #define GET_IOSPACE(pfn)		(pfn >> (BITS_PER_LONG - 4))
 #define GET_PFN(pfn)			(pfn & 0x0fffffffUL)
 
+extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
+			   unsigned long, pgprot_t);
+
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+				     unsigned long from, unsigned long pfn,
+				     unsigned long size, pgprot_t prot)
+{
+	unsigned long long offset, space, phys_base;
+
+	offset = ((unsigned long long) GET_PFN(pfn)) << PAGE_SHIFT;
+	space = GET_IOSPACE(pfn);
+	phys_base = offset | (space << 32ULL);
+
+	return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
+}
+
 #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 #define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
 ({									  \
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index adf8932..38ebb2c 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -757,10 +757,6 @@ static inline bool kern_addr_valid(unsigned long addr)
 
 extern int page_in_phys_avail(unsigned long paddr);
 
-extern int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
-			       unsigned long pfn,
-			       unsigned long size, pgprot_t prot);
-
 /*
  * For sparc32&64, the pfn in io_remap_pfn_range() carries <iospace> in
  * its high 4 bits.  These macros/functions put it there or get it from there.
@@ -769,6 +765,22 @@ extern int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
 #define GET_IOSPACE(pfn)		(pfn >> (BITS_PER_LONG - 4))
 #define GET_PFN(pfn)			(pfn & 0x0fffffffffffffffUL)
 
+extern int remap_pfn_range(struct vm_area_struct *, unsigned long, unsigned long,
+			   unsigned long, pgprot_t);
+
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+				     unsigned long from, unsigned long pfn,
+				     unsigned long size, pgprot_t prot)
+{
+	unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
+	int space = GET_IOSPACE(pfn);
+	unsigned long phys_base;
+
+	phys_base = offset | (((unsigned long) space) << 32UL);
+
+	return remap_pfn_range(vma, from, phys_base >> PAGE_SHIFT, size, prot);
+}
+
 #include <asm-generic/pgtable.h>
 
 /* We provide our own get_unmapped_area to cope with VA holes and
diff --git a/arch/sparc/kernel/entry.h b/arch/sparc/kernel/entry.h
index e27f8ea..0c218e4 100644
--- a/arch/sparc/kernel/entry.h
+++ b/arch/sparc/kernel/entry.h
@@ -42,6 +42,9 @@ extern void fpsave(unsigned long *fpregs, unsigned long *fsr,
 extern void fpload(unsigned long *fpregs, unsigned long *fsr);
 
 #else /* CONFIG_SPARC32 */
+
+#include <asm/trap_block.h>
+
 struct popc_3insn_patch_entry {
 	unsigned int	addr;
 	unsigned int	insns[3];
@@ -57,6 +60,10 @@ extern struct popc_6insn_patch_entry __popc_6insn_patch,
 	__popc_6insn_patch_end;
 
 extern void __init per_cpu_patch(void);
+extern void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *,
+				    struct sun4v_1insn_patch_entry *);
+extern void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *,
+				    struct sun4v_2insn_patch_entry *);
 extern void __init sun4v_patch(void);
 extern void __init boot_cpu_id_too_large(int cpu);
 extern unsigned int dcache_parity_tl1_occurred;
diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c
index da0c6c7..e551987 100644
--- a/arch/sparc/kernel/module.c
+++ b/arch/sparc/kernel/module.c
@@ -17,6 +17,8 @@
 #include <asm/processor.h>
 #include <asm/spitfire.h>
 
+#include "entry.h"
+
 #ifdef CONFIG_SPARC64
 
 #include <linux/jump_label.h>
@@ -203,6 +205,29 @@ int apply_relocate_add(Elf_Shdr *sechdrs,
 }
 
 #ifdef CONFIG_SPARC64
+static void do_patch_sections(const Elf_Ehdr *hdr,
+			      const Elf_Shdr *sechdrs)
+{
+	const Elf_Shdr *s, *sun4v_1insn = NULL, *sun4v_2insn = NULL;
+	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+
+	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
+		if (!strcmp(".sun4v_1insn_patch", secstrings + s->sh_name))
+			sun4v_1insn = s;
+		if (!strcmp(".sun4v_2insn_patch", secstrings + s->sh_name))
+			sun4v_2insn = s;
+	}
+
+	if (sun4v_1insn && tlb_type == hypervisor) {
+		void *p = (void *) sun4v_1insn->sh_addr;
+		sun4v_patch_1insn_range(p, p + sun4v_1insn->sh_size);
+	}
+	if (sun4v_2insn && tlb_type == hypervisor) {
+		void *p = (void *) sun4v_2insn->sh_addr;
+		sun4v_patch_2insn_range(p, p + sun4v_2insn->sh_size);
+	}
+}
+
 int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
@@ -210,6 +235,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 	/* make jump label nops */
 	jump_label_apply_nops(me);
 
+	do_patch_sections(hdr, sechdrs);
+
 	/* Cheetah's I-cache is fully coherent.  */
 	if (tlb_type == spitfire) {
 		unsigned long va;
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index c965595a..a854a1c 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -234,40 +234,50 @@ void __init per_cpu_patch(void)
 	}
 }
 
-void __init sun4v_patch(void)
+void sun4v_patch_1insn_range(struct sun4v_1insn_patch_entry *start,
+			     struct sun4v_1insn_patch_entry *end)
 {
-	extern void sun4v_hvapi_init(void);
-	struct sun4v_1insn_patch_entry *p1;
-	struct sun4v_2insn_patch_entry *p2;
-
-	if (tlb_type != hypervisor)
-		return;
+	while (start < end) {
+		unsigned long addr = start->addr;
 
-	p1 = &__sun4v_1insn_patch;
-	while (p1 < &__sun4v_1insn_patch_end) {
-		unsigned long addr = p1->addr;
-
-		*(unsigned int *) (addr +  0) = p1->insn;
+		*(unsigned int *) (addr +  0) = start->insn;
 		wmb();
 		__asm__ __volatile__("flush	%0" : : "r" (addr +  0));
 
-		p1++;
+		start++;
 	}
+}
 
-	p2 = &__sun4v_2insn_patch;
-	while (p2 < &__sun4v_2insn_patch_end) {
-		unsigned long addr = p2->addr;
+void sun4v_patch_2insn_range(struct sun4v_2insn_patch_entry *start,
+			     struct sun4v_2insn_patch_entry *end)
+{
+	while (start < end) {
+		unsigned long addr = start->addr;
 
-		*(unsigned int *) (addr +  0) = p2->insns[0];
+		*(unsigned int *) (addr +  0) = start->insns[0];
 		wmb();
 		__asm__ __volatile__("flush	%0" : : "r" (addr +  0));
 
-		*(unsigned int *) (addr +  4) = p2->insns[1];
+		*(unsigned int *) (addr +  4) = start->insns[1];
 		wmb();
 		__asm__ __volatile__("flush	%0" : : "r" (addr +  4));
 
-		p2++;
+		start++;
 	}
+}
+
+void __init sun4v_patch(void)
+{
+	extern void sun4v_hvapi_init(void);
+
+	if (tlb_type != hypervisor)
+		return;
+
+	sun4v_patch_1insn_range(&__sun4v_1insn_patch,
+				&__sun4v_1insn_patch_end);
+
+	sun4v_patch_2insn_range(&__sun4v_2insn_patch,
+				&__sun4v_2insn_patch_end);
 
 	sun4v_hvapi_init();
 }
diff --git a/arch/sparc/kernel/signal32.c b/arch/sparc/kernel/signal32.c
index 2caa556..023b886 100644
--- a/arch/sparc/kernel/signal32.c
+++ b/arch/sparc/kernel/signal32.c
@@ -822,21 +822,23 @@ static inline void syscall_restart32(unsigned long orig_i0, struct pt_regs *regs
  * want to handle. Thus you cannot kill init even with a SIGKILL even by
  * mistake.
  */
-void do_signal32(sigset_t *oldset, struct pt_regs * regs,
-		 int restart_syscall, unsigned long orig_i0)
+void do_signal32(sigset_t *oldset, struct pt_regs * regs)
 {
 	struct k_sigaction ka;
+	unsigned long orig_i0;
+	int restart_syscall;
 	siginfo_t info;
 	int signr;
 	
 	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
 
-	/* If the debugger messes with the program counter, it clears
-	 * the "in syscall" bit, directing us to not perform a syscall
-	 * restart.
-	 */
-	if (restart_syscall && !pt_regs_is_syscall(regs))
-		restart_syscall = 0;
+	restart_syscall = 0;
+	orig_i0 = 0;
+	if (pt_regs_is_syscall(regs) &&
+	    (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) {
+		restart_syscall = 1;
+		orig_i0 = regs->u_regs[UREG_G6];
+	}
 
 	if (signr > 0) {
 		if (restart_syscall)
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 8ce247a..d54c6e5 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -519,10 +519,26 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 	siginfo_t info;
 	int signr;
 
+	/* It's a lot of work and synchronization to add a new ptrace
+	 * register for GDB to save and restore in order to get
+	 * orig_i0 correct for syscall restarts when debugging.
+	 *
+	 * Although it should be the case that most of the global
+	 * registers are volatile across a system call, glibc already
+	 * depends upon that fact that we preserve them.  So we can't
+	 * just use any global register to save away the orig_i0 value.
+	 *
+	 * In particular %g2, %g3, %g4, and %g5 are all assumed to be
+	 * preserved across a system call trap by various pieces of
+	 * code in glibc.
+	 *
+	 * %g7 is used as the "thread register".   %g6 is not used in
+	 * any fixed manner.  %g6 is used as a scratch register and
+	 * a compiler temporary, but it's value is never used across
+	 * a system call.  Therefore %g6 is usable for orig_i0 storage.
+	 */
 	if (pt_regs_is_syscall(regs) && (regs->psr & PSR_C))
-		restart_syscall = 1;
-	else
-		restart_syscall = 0;
+		regs->u_regs[UREG_G6] = orig_i0;
 
 	if (test_thread_flag(TIF_RESTORE_SIGMASK))
 		oldset = &current->saved_sigmask;
@@ -535,8 +551,12 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 	 * the software "in syscall" bit, directing us to not perform
 	 * a syscall restart.
 	 */
-	if (restart_syscall && !pt_regs_is_syscall(regs))
-		restart_syscall = 0;
+	restart_syscall = 0;
+	if (pt_regs_is_syscall(regs) && (regs->psr & PSR_C)) {
+		restart_syscall = 1;
+		orig_i0 = regs->u_regs[UREG_G6];
+	}
+
 
 	if (signr > 0) {
 		if (restart_syscall)
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index a2b8159..f0836cd 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -529,11 +529,27 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 	siginfo_t info;
 	int signr;
 	
+	/* It's a lot of work and synchronization to add a new ptrace
+	 * register for GDB to save and restore in order to get
+	 * orig_i0 correct for syscall restarts when debugging.
+	 *
+	 * Although it should be the case that most of the global
+	 * registers are volatile across a system call, glibc already
+	 * depends upon that fact that we preserve them.  So we can't
+	 * just use any global register to save away the orig_i0 value.
+	 *
+	 * In particular %g2, %g3, %g4, and %g5 are all assumed to be
+	 * preserved across a system call trap by various pieces of
+	 * code in glibc.
+	 *
+	 * %g7 is used as the "thread register".   %g6 is not used in
+	 * any fixed manner.  %g6 is used as a scratch register and
+	 * a compiler temporary, but it's value is never used across
+	 * a system call.  Therefore %g6 is usable for orig_i0 storage.
+	 */
 	if (pt_regs_is_syscall(regs) &&
-	    (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) {
-		restart_syscall = 1;
-	} else
-		restart_syscall = 0;
+	    (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY)))
+		regs->u_regs[UREG_G6] = orig_i0;
 
 	if (current_thread_info()->status & TS_RESTORE_SIGMASK)
 		oldset = &current->saved_sigmask;
@@ -542,22 +558,20 @@ static void do_signal(struct pt_regs *regs, unsigned long orig_i0)
 
 #ifdef CONFIG_COMPAT
 	if (test_thread_flag(TIF_32BIT)) {
-		extern void do_signal32(sigset_t *, struct pt_regs *,
-					int restart_syscall,
-					unsigned long orig_i0);
-		do_signal32(oldset, regs, restart_syscall, orig_i0);
+		extern void do_signal32(sigset_t *, struct pt_regs *);
+		do_signal32(oldset, regs);
 		return;
 	}
 #endif	
 
 	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
 
-	/* If the debugger messes with the program counter, it clears
-	 * the software "in syscall" bit, directing us to not perform
-	 * a syscall restart.
-	 */
-	if (restart_syscall && !pt_regs_is_syscall(regs))
-		restart_syscall = 0;
+	restart_syscall = 0;
+	if (pt_regs_is_syscall(regs) &&
+	    (regs->tstate & (TSTATE_XCARRY | TSTATE_ICARRY))) {
+		restart_syscall = 1;
+		orig_i0 = regs->u_regs[UREG_G6];
+	}
 
 	if (signr > 0) {
 		if (restart_syscall)
diff --git a/arch/sparc/kernel/sigutil_64.c b/arch/sparc/kernel/sigutil_64.c
index e7dc508..b19570d 100644
--- a/arch/sparc/kernel/sigutil_64.c
+++ b/arch/sparc/kernel/sigutil_64.c
@@ -2,6 +2,7 @@
 #include <linux/types.h>
 #include <linux/thread_info.h>
 #include <linux/uaccess.h>
+#include <linux/errno.h>
 
 #include <asm/sigcontext.h>
 #include <asm/fpumacro.h>
diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile
index e3cda21..301421c 100644
--- a/arch/sparc/mm/Makefile
+++ b/arch/sparc/mm/Makefile
@@ -8,7 +8,6 @@ obj-$(CONFIG_SPARC64)   += ultra.o tlb.o tsb.o gup.o
 obj-y                   += fault_$(BITS).o
 obj-y                   += init_$(BITS).o
 obj-$(CONFIG_SPARC32)   += loadmmu.o
-obj-y                   += generic_$(BITS).o
 obj-$(CONFIG_SPARC32)   += extable.o btfixup.o srmmu.o iommu.o io-unit.o
 obj-$(CONFIG_SPARC32)   += hypersparc.o viking.o tsunami.o swift.o
 obj-$(CONFIG_SPARC_LEON)+= leon_mm.o
diff --git a/arch/sparc/mm/generic_32.c b/arch/sparc/mm/generic_32.c
deleted file mode 100644
index 6ca39a6..0000000
--- a/arch/sparc/mm/generic_32.c
+++ /dev/null
@@ -1,99 +0,0 @@
-/*
- * generic.c: Generic Sparc mm routines that are not dependent upon
- *            MMU type but are Sparc specific.
- *
- * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
- */
-
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/pagemap.h>
-#include <linux/export.h>
-
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-
-/* Remap IO memory, the same way as remap_pfn_range(), but use
- * the obio memory space.
- *
- * They use a pgprot that sets PAGE_IO and does not check the
- * mem_map table as this is independent of normal memory.
- */
-static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte, unsigned long address, unsigned long size,
-	unsigned long offset, pgprot_t prot, int space)
-{
-	unsigned long end;
-
-	address &= ~PMD_MASK;
-	end = address + size;
-	if (end > PMD_SIZE)
-		end = PMD_SIZE;
-	do {
-		set_pte_at(mm, address, pte, mk_pte_io(offset, prot, space));
-		address += PAGE_SIZE;
-		offset += PAGE_SIZE;
-		pte++;
-	} while (address < end);
-}
-
-static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
-	unsigned long offset, pgprot_t prot, int space)
-{
-	unsigned long end;
-
-	address &= ~PGDIR_MASK;
-	end = address + size;
-	if (end > PGDIR_SIZE)
-		end = PGDIR_SIZE;
-	offset -= address;
-	do {
-		pte_t *pte = pte_alloc_map(mm, NULL, pmd, address);
-		if (!pte)
-			return -ENOMEM;
-		io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space);
-		address = (address + PMD_SIZE) & PMD_MASK;
-		pmd++;
-	} while (address < end);
-	return 0;
-}
-
-int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
-		       unsigned long pfn, unsigned long size, pgprot_t prot)
-{
-	int error = 0;
-	pgd_t * dir;
-	unsigned long beg = from;
-	unsigned long end = from + size;
-	struct mm_struct *mm = vma->vm_mm;
-	int space = GET_IOSPACE(pfn);
-	unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
-
-	/* See comment in mm/memory.c remap_pfn_range */
-	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
-	vma->vm_pgoff = (offset >> PAGE_SHIFT) |
-		((unsigned long)space << 28UL);
-
-	offset -= from;
-	dir = pgd_offset(mm, from);
-	flush_cache_range(vma, beg, end);
-
-	while (from < end) {
-		pmd_t *pmd = pmd_alloc(mm, dir, from);
-		error = -ENOMEM;
-		if (!pmd)
-			break;
-		error = io_remap_pmd_range(mm, pmd, from, end - from, offset + from, prot, space);
-		if (error)
-			break;
-		from = (from + PGDIR_SIZE) & PGDIR_MASK;
-		dir++;
-	}
-
-	flush_tlb_range(vma, beg, end);
-	return error;
-}
-EXPORT_SYMBOL(io_remap_pfn_range);
diff --git a/arch/sparc/mm/generic_64.c b/arch/sparc/mm/generic_64.c
deleted file mode 100644
index 9b357dd..0000000
--- a/arch/sparc/mm/generic_64.c
+++ /dev/null
@@ -1,165 +0,0 @@
-/*
- * generic.c: Generic Sparc mm routines that are not dependent upon
- *            MMU type but are Sparc specific.
- *
- * Copyright (C) 1996 David S. Miller (davem@caip.rutgers.edu)
- */
-
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/swap.h>
-#include <linux/export.h>
-#include <linux/pagemap.h>
-
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
-#include <asm/tlbflush.h>
-
-/* Remap IO memory, the same way as remap_pfn_range(), but use
- * the obio memory space.
- *
- * They use a pgprot that sets PAGE_IO and does not check the
- * mem_map table as this is independent of normal memory.
- */
-static inline void io_remap_pte_range(struct mm_struct *mm, pte_t * pte,
-				      unsigned long address,
-				      unsigned long size,
-				      unsigned long offset, pgprot_t prot,
-				      int space)
-{
-	unsigned long end;
-
-	/* clear hack bit that was used as a write_combine side-effect flag */
-	offset &= ~0x1UL;
-	address &= ~PMD_MASK;
-	end = address + size;
-	if (end > PMD_SIZE)
-		end = PMD_SIZE;
-	do {
-		pte_t entry;
-		unsigned long curend = address + PAGE_SIZE;
-		
-		entry = mk_pte_io(offset, prot, space, PAGE_SIZE);
-		if (!(address & 0xffff)) {
-			if (PAGE_SIZE < (4 * 1024 * 1024) &&
-			    !(address & 0x3fffff) &&
-			    !(offset & 0x3ffffe) &&
-			    end >= address + 0x400000) {
-				entry = mk_pte_io(offset, prot, space,
-						  4 * 1024 * 1024);
-				curend = address + 0x400000;
-				offset += 0x400000;
-			} else if (PAGE_SIZE < (512 * 1024) &&
-				   !(address & 0x7ffff) &&
-				   !(offset & 0x7fffe) &&
-				   end >= address + 0x80000) {
-				entry = mk_pte_io(offset, prot, space,
-						  512 * 1024 * 1024);
-				curend = address + 0x80000;
-				offset += 0x80000;
-			} else if (PAGE_SIZE < (64 * 1024) &&
-				   !(offset & 0xfffe) &&
-				   end >= address + 0x10000) {
-				entry = mk_pte_io(offset, prot, space,
-						  64 * 1024);
-				curend = address + 0x10000;
-				offset += 0x10000;
-			} else
-				offset += PAGE_SIZE;
-		} else
-			offset += PAGE_SIZE;
-
-		if (pte_write(entry))
-			entry = pte_mkdirty(entry);
-		do {
-			BUG_ON(!pte_none(*pte));
-			set_pte_at(mm, address, pte, entry);
-			address += PAGE_SIZE;
-			pte_val(entry) += PAGE_SIZE;
-			pte++;
-		} while (address < curend);
-	} while (address < end);
-}
-
-static inline int io_remap_pmd_range(struct mm_struct *mm, pmd_t * pmd, unsigned long address, unsigned long size,
-	unsigned long offset, pgprot_t prot, int space)
-{
-	unsigned long end;
-
-	address &= ~PGDIR_MASK;
-	end = address + size;
-	if (end > PGDIR_SIZE)
-		end = PGDIR_SIZE;
-	offset -= address;
-	do {
-		pte_t *pte = pte_alloc_map(mm, NULL, pmd, address);
-		if (!pte)
-			return -ENOMEM;
-		io_remap_pte_range(mm, pte, address, end - address, address + offset, prot, space);
-		pte_unmap(pte);
-		address = (address + PMD_SIZE) & PMD_MASK;
-		pmd++;
-	} while (address < end);
-	return 0;
-}
-
-static inline int io_remap_pud_range(struct mm_struct *mm, pud_t * pud, unsigned long address, unsigned long size,
-	unsigned long offset, pgprot_t prot, int space)
-{
-	unsigned long end;
-
-	address &= ~PUD_MASK;
-	end = address + size;
-	if (end > PUD_SIZE)
-		end = PUD_SIZE;
-	offset -= address;
-	do {
-		pmd_t *pmd = pmd_alloc(mm, pud, address);
-		if (!pud)
-			return -ENOMEM;
-		io_remap_pmd_range(mm, pmd, address, end - address, address + offset, prot, space);
-		address = (address + PUD_SIZE) & PUD_MASK;
-		pud++;
-	} while (address < end);
-	return 0;
-}
-
-int io_remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
-		unsigned long pfn, unsigned long size, pgprot_t prot)
-{
-	int error = 0;
-	pgd_t * dir;
-	unsigned long beg = from;
-	unsigned long end = from + size;
-	struct mm_struct *mm = vma->vm_mm;
-	int space = GET_IOSPACE(pfn);
-	unsigned long offset = GET_PFN(pfn) << PAGE_SHIFT;
-	unsigned long phys_base;
-
-	phys_base = offset | (((unsigned long) space) << 32UL);
-
-	/* See comment in mm/memory.c remap_pfn_range */
-	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
-	vma->vm_pgoff = phys_base >> PAGE_SHIFT;
-
-	offset -= from;
-	dir = pgd_offset(mm, from);
-	flush_cache_range(vma, beg, end);
-
-	while (from < end) {
-		pud_t *pud = pud_alloc(mm, dir, from);
-		error = -ENOMEM;
-		if (!pud)
-			break;
-		error = io_remap_pud_range(mm, pud, from, end - from, offset + from, prot, space);
-		if (error)
-			break;
-		from = (from + PGDIR_SIZE) & PGDIR_MASK;
-		dir++;
-	}
-
-	flush_tlb_range(vma, beg, end);
-	return error;
-}
-EXPORT_SYMBOL(io_remap_pfn_range);
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index e57dcce..942ed61 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -237,13 +237,13 @@ menu "PKUnity NetBook-0916 Features"
 
 config I2C_BATTERY_BQ27200
 	tristate "I2C Battery BQ27200 Support"
-	select PUV3_I2C
+	select I2C_PUV3
 	select POWER_SUPPLY
 	select BATTERY_BQ27x00
 
 config I2C_EEPROM_AT24
 	tristate "I2C EEPROMs AT24 support"
-	select PUV3_I2C
+	select I2C_PUV3
 	select MISC_DEVICES
 	select EEPROM_AT24
 
diff --git a/arch/unicore32/Kconfig.debug b/arch/unicore32/Kconfig.debug
index ae2ec33..1a36262 100644
--- a/arch/unicore32/Kconfig.debug
+++ b/arch/unicore32/Kconfig.debug
@@ -44,18 +44,4 @@ config DEBUG_OCD
 	  Say Y here if you want the debug print routines to direct their
 	  output to the UniCore On-Chip-Debugger channel using CP #1.
 
-config DEBUG_OCD_BREAKPOINT
-	bool "Breakpoint support via On-Chip-Debugger"
-	depends on DEBUG_OCD
-
-config DEBUG_UART
-	int "Kernel low-level debugging messages via serial port"
-	depends on DEBUG_LL
-	range 0 1
-	default "0"
-	help
-	  Choice for UART for kernel low-level using PKUnity UARTS,
-	  should be between zero and one. The port must have been
-	  initialised by the boot-loader before use.
-
 endmenu
diff --git a/arch/unicore32/boot/compressed/Makefile b/arch/unicore32/boot/compressed/Makefile
index b0954a2..950a9af 100644
--- a/arch/unicore32/boot/compressed/Makefile
+++ b/arch/unicore32/boot/compressed/Makefile
@@ -10,8 +10,8 @@
 # Copyright (C) 2001~2010 GUAN Xue-tao
 #
 
-EXTRA_CFLAGS	:= -fpic -fno-builtin
-EXTRA_AFLAGS	:= -Wa,-march=all
+ccflags-y	:= -fpic -fno-builtin
+asflags-y	:= -Wa,-march=all
 
 OBJS		:= misc.o
 
diff --git a/arch/unicore32/include/asm/bitops.h b/arch/unicore32/include/asm/bitops.h
index 1628a63..401f597 100644
--- a/arch/unicore32/include/asm/bitops.h
+++ b/arch/unicore32/include/asm/bitops.h
@@ -13,12 +13,6 @@
 #ifndef __UNICORE_BITOPS_H__
 #define __UNICORE_BITOPS_H__
 
-#define find_next_bit		__uc32_find_next_bit
-#define find_next_zero_bit	__uc32_find_next_zero_bit
-
-#define find_first_bit		__uc32_find_first_bit
-#define find_first_zero_bit	__uc32_find_first_zero_bit
-
 #define _ASM_GENERIC_BITOPS_FLS_H_
 #define _ASM_GENERIC_BITOPS___FLS_H_
 #define _ASM_GENERIC_BITOPS_FFS_H_
@@ -44,4 +38,10 @@ static inline int fls(int x)
 
 #include <asm-generic/bitops.h>
 
+/* following definitions: to avoid using codes in lib/find_*.c */
+#define find_next_bit		find_next_bit
+#define find_next_zero_bit	find_next_zero_bit
+#define find_first_bit		find_first_bit
+#define find_first_zero_bit	find_first_zero_bit
+
 #endif /* __UNICORE_BITOPS_H__ */
diff --git a/arch/unicore32/include/asm/processor.h b/arch/unicore32/include/asm/processor.h
index e11cb07..f0d780a 100644
--- a/arch/unicore32/include/asm/processor.h
+++ b/arch/unicore32/include/asm/processor.h
@@ -53,7 +53,6 @@ struct thread_struct {
 #define start_thread(regs, pc, sp)					\
 ({									\
 	unsigned long *stack = (unsigned long *)sp;			\
-	set_fs(USER_DS);						\
 	memset(regs->uregs, 0, sizeof(regs->uregs));			\
 	regs->UCreg_asr = USER_MODE;					\
 	regs->UCreg_pc = pc & ~1;	/* pc */                        \
diff --git a/arch/unicore32/kernel/ksyms.c b/arch/unicore32/kernel/ksyms.c
index a897080..d98bd81 100644
--- a/arch/unicore32/kernel/ksyms.c
+++ b/arch/unicore32/kernel/ksyms.c
@@ -24,8 +24,8 @@
 
 #include "ksyms.h"
 
-EXPORT_SYMBOL(__uc32_find_next_zero_bit);
-EXPORT_SYMBOL(__uc32_find_next_bit);
+EXPORT_SYMBOL(find_next_zero_bit);
+EXPORT_SYMBOL(find_next_bit);
 
 EXPORT_SYMBOL(__backtrace);
 
diff --git a/arch/unicore32/lib/findbit.S b/arch/unicore32/lib/findbit.S
index c360ce9..c777462 100644
--- a/arch/unicore32/lib/findbit.S
+++ b/arch/unicore32/lib/findbit.S
@@ -17,7 +17,7 @@
  * Purpose  : Find a 'zero' bit
  * Prototype: int find_first_zero_bit(void *addr, unsigned int maxbit);
  */
-__uc32_find_first_zero_bit:
+ENTRY(find_first_zero_bit)
 		cxor.a	r1, #0
 		beq	3f
 		mov	r2, #0
@@ -29,13 +29,14 @@ __uc32_find_first_zero_bit:
 		bub	1b
 3:		mov	r0, r1			@ no free bits
 		mov	pc, lr
+ENDPROC(find_first_zero_bit)
 
 /*
  * Purpose  : Find next 'zero' bit
  * Prototype: int find_next_zero_bit
  *		(void *addr, unsigned int maxbit, int offset)
  */
-ENTRY(__uc32_find_next_zero_bit)
+ENTRY(find_next_zero_bit)
 		cxor.a	r1, #0
 		beq	3b
 		and.a	ip, r2, #7
@@ -47,14 +48,14 @@ ENTRY(__uc32_find_next_zero_bit)
 		or	r2, r2, #7		@ if zero, then no bits here
 		add	r2, r2, #1		@ align bit pointer
 		b	2b			@ loop for next bit
-ENDPROC(__uc32_find_next_zero_bit)
+ENDPROC(find_next_zero_bit)
 
 /*
  * Purpose  : Find a 'one' bit
  * Prototype: int find_first_bit
  *		(const unsigned long *addr, unsigned int maxbit);
  */
-__uc32_find_first_bit:
+ENTRY(find_first_bit)
 		cxor.a	r1, #0
 		beq	3f
 		mov	r2, #0
@@ -66,13 +67,14 @@ __uc32_find_first_bit:
 		bub	1b
 3:		mov	r0, r1			@ no free bits
 		mov	pc, lr
+ENDPROC(find_first_bit)
 
 /*
  * Purpose  : Find next 'one' bit
  * Prototype: int find_next_zero_bit
  *		(void *addr, unsigned int maxbit, int offset)
  */
-ENTRY(__uc32_find_next_bit)
+ENTRY(find_next_bit)
 		cxor.a	r1, #0
 		beq	3b
 		and.a	ip, r2, #7
@@ -83,7 +85,7 @@ ENTRY(__uc32_find_next_bit)
 		or	r2, r2, #7		@ if zero, then no bits here
 		add	r2, r2, #1		@ align bit pointer
 		b	2b			@ loop for next bit
-ENDPROC(__uc32_find_next_bit)
+ENDPROC(find_next_bit)
 
 /*
  * One or more bits in the LSB of r3 are assumed to be set.
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 9b7273c..1a6c09a 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -49,6 +49,7 @@ extern unsigned int apic_verbosity;
 extern int local_apic_timer_c2_ok;
 
 extern int disable_apic;
+extern unsigned int lapic_timer_frequency;
 
 #ifdef CONFIG_SMP
 extern void __inquire_remote_apic(int apicid);
diff --git a/arch/x86/include/asm/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h
index 4420993..925b605 100644
--- a/arch/x86/include/asm/intel_scu_ipc.h
+++ b/arch/x86/include/asm/intel_scu_ipc.h
@@ -3,11 +3,15 @@
 
 #include <linux/notifier.h>
 
-#define IPCMSG_VRTC	0xFA	 /* Set vRTC device */
-
-/* Command id associated with message IPCMSG_VRTC */
-#define IPC_CMD_VRTC_SETTIME      1 /* Set time */
-#define IPC_CMD_VRTC_SETALARM     2 /* Set alarm */
+#define IPCMSG_WARM_RESET	0xF0
+#define IPCMSG_COLD_RESET	0xF1
+#define IPCMSG_SOFT_RESET	0xF2
+#define IPCMSG_COLD_BOOT	0xF3
+
+#define IPCMSG_VRTC		0xFA	 /* Set vRTC device */
+	/* Command id associated with message IPCMSG_VRTC */
+	#define IPC_CMD_VRTC_SETTIME      1 /* Set time */
+	#define IPC_CMD_VRTC_SETALARM     2 /* Set alarm */
 
 /* Read single register */
 int intel_scu_ipc_ioread8(u16 addr, u8 *data);
diff --git a/arch/x86/include/asm/mach_traps.h b/arch/x86/include/asm/mach_traps.h
index 72a8b52..a01e7ec7 100644
--- a/arch/x86/include/asm/mach_traps.h
+++ b/arch/x86/include/asm/mach_traps.h
@@ -17,7 +17,7 @@
 #define NMI_REASON_CLEAR_IOCHK	0x08
 #define NMI_REASON_CLEAR_MASK	0x0f
 
-static inline unsigned char get_nmi_reason(void)
+static inline unsigned char default_get_nmi_reason(void)
 {
 	return inb(NMI_REASON_PORT);
 }
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index c9321f3..0e8ae57 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -201,7 +201,10 @@ int mce_notify_irq(void);
 void mce_notify_process(void);
 
 DECLARE_PER_CPU(struct mce, injectm);
-extern struct file_operations mce_chrdev_ops;
+
+extern void register_mce_write_callback(ssize_t (*)(struct file *filp,
+				    const char __user *ubuf,
+				    size_t usize, loff_t *off));
 
 /*
  * Exception handler
diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h
index 719f00b..93f7909 100644
--- a/arch/x86/include/asm/mrst.h
+++ b/arch/x86/include/asm/mrst.h
@@ -31,11 +31,20 @@ enum mrst_cpu_type {
 };
 
 extern enum mrst_cpu_type __mrst_cpu_chip;
+
+#ifdef CONFIG_X86_INTEL_MID
+
 static inline enum mrst_cpu_type mrst_identify_cpu(void)
 {
 	return __mrst_cpu_chip;
 }
 
+#else /* !CONFIG_X86_INTEL_MID */
+
+#define mrst_identify_cpu()    (0)
+
+#endif /* !CONFIG_X86_INTEL_MID */
+
 enum mrst_timer_options {
 	MRST_TIMER_DEFAULT,
 	MRST_TIMER_APBT_ONLY,
@@ -44,6 +53,13 @@ enum mrst_timer_options {
 
 extern enum mrst_timer_options mrst_timer_options;
 
+/*
+ * Penwell uses spread spectrum clock, so the freq number is not exactly
+ * the same as reported by MSR based on SDM.
+ */
+#define PENWELL_FSB_FREQ_83SKU         83200
+#define PENWELL_FSB_FREQ_100SKU        99840
+
 #define SFI_MTMR_MAX_NUM 8
 #define SFI_MRTC_MAX	8
 
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 084ef95..95203d4 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -169,7 +169,14 @@ static inline int wrmsr_safe(unsigned msr, unsigned low, unsigned high)
 	return native_write_msr_safe(msr, low, high);
 }
 
-/* rdmsr with exception handling */
+/*
+ * rdmsr with exception handling.
+ *
+ * Please note that the exception handling works only after we've
+ * switched to the "smart" #GP handler in trap_init() which knows about
+ * exception tables - using this macro earlier than that causes machine
+ * hangs on boxes which do not implement the @msr in the first argument.
+ */
 #define rdmsr_safe(msr, p1, p2)					\
 ({								\
 	int __err;						\
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index c2ff2a1..2d2f01c 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -401,6 +401,7 @@ extern unsigned long arch_align_stack(unsigned long sp);
 extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
 
 void default_idle(void);
+bool set_pm_idle_to_default(void);
 
 void stop_this_cpu(void *dummy);
 
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index fa7b917..431793e 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -32,6 +32,22 @@ extern int no_timer_check;
  *  (mathieu.desnoyers@polymtl.ca)
  *
  *			-johnstul@us.ibm.com "math is hard, lets go shopping!"
+ *
+ * In:
+ *
+ * ns = cycles * cyc2ns_scale / SC
+ *
+ * Although we may still have enough bits to store the value of ns,
+ * in some cases, we may not have enough bits to store cycles * cyc2ns_scale,
+ * leading to an incorrect result.
+ *
+ * To avoid this, we can decompose 'cycles' into quotient and remainder
+ * of division by SC.  Then,
+ *
+ * ns = (quot * SC + rem) * cyc2ns_scale / SC
+ *    = quot * cyc2ns_scale + (rem * cyc2ns_scale) / SC
+ *
+ *			- sqazi@google.com
  */
 
 DECLARE_PER_CPU(unsigned long, cyc2ns);
@@ -41,9 +57,14 @@ DECLARE_PER_CPU(unsigned long long, cyc2ns_offset);
 
 static inline unsigned long long __cycles_2_ns(unsigned long long cyc)
 {
+	unsigned long long quot;
+	unsigned long long rem;
 	int cpu = smp_processor_id();
 	unsigned long long ns = per_cpu(cyc2ns_offset, cpu);
-	ns += cyc * per_cpu(cyc2ns, cpu) >> CYC2NS_SCALE_FACTOR;
+	quot = (cyc >> CYC2NS_SCALE_FACTOR);
+	rem = cyc & ((1ULL << CYC2NS_SCALE_FACTOR) - 1);
+	ns += quot * per_cpu(cyc2ns, cpu) +
+		((rem * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR);
 	return ns;
 }
 
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index 10474fb..cf1d736 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -57,6 +57,7 @@
 
 #define UV1_HUB_PART_NUMBER	0x88a5
 #define UV2_HUB_PART_NUMBER	0x8eb8
+#define UV2_HUB_PART_NUMBER_X	0x1111
 
 /* Compat: if this #define is present, UV headers support UV2 */
 #define UV2_HUB_IS_SUPPORTED	1
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index d3d8590..1971e65 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -152,6 +152,7 @@ struct x86_cpuinit_ops {
 /**
  * struct x86_platform_ops - platform specific runtime functions
  * @calibrate_tsc:		calibrate TSC
+ * @wallclock_init:		init the wallclock device
  * @get_wallclock:		get time from HW clock like RTC etc.
  * @set_wallclock:		set time back to HW clock
  * @is_untracked_pat_range	exclude from PAT logic
@@ -160,11 +161,13 @@ struct x86_cpuinit_ops {
  */
 struct x86_platform_ops {
 	unsigned long (*calibrate_tsc)(void);
+	void (*wallclock_init)(void);
 	unsigned long (*get_wallclock)(void);
 	int (*set_wallclock)(unsigned long nowtime);
 	void (*iommu_shutdown)(void);
 	bool (*is_untracked_pat_range)(u64 start, u64 end);
 	void (*nmi_init)(void);
+	unsigned char (*get_nmi_reason)(void);
 	int (*i8042_detect)(void);
 };
 
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c638228..1f84794 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -738,5 +738,5 @@ void __kprobes text_poke_smp_batch(struct text_poke_param *params, int n)
 
 	atomic_set(&stop_machine_first, 1);
 	wrote_text = 0;
-	__stop_machine(stop_machine_text_poke, (void *)&tpp, NULL);
+	__stop_machine(stop_machine_text_poke, (void *)&tpp, cpu_online_mask);
 }
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index a2fd72e..f98d84c 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -186,7 +186,7 @@ static struct resource lapic_resource = {
 	.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
 };
 
-static unsigned int calibration_result;
+unsigned int lapic_timer_frequency = 0;
 
 static void apic_pm_activate(void);
 
@@ -454,7 +454,7 @@ static void lapic_timer_setup(enum clock_event_mode mode,
 	switch (mode) {
 	case CLOCK_EVT_MODE_PERIODIC:
 	case CLOCK_EVT_MODE_ONESHOT:
-		__setup_APIC_LVTT(calibration_result,
+		__setup_APIC_LVTT(lapic_timer_frequency,
 				  mode != CLOCK_EVT_MODE_PERIODIC, 1);
 		break;
 	case CLOCK_EVT_MODE_UNUSED:
@@ -638,6 +638,25 @@ static int __init calibrate_APIC_clock(void)
 	long delta, deltatsc;
 	int pm_referenced = 0;
 
+	/**
+	 * check if lapic timer has already been calibrated by platform
+	 * specific routine, such as tsc calibration code. if so, we just fill
+	 * in the clockevent structure and return.
+	 */
+
+	if (lapic_timer_frequency) {
+		apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n",
+				lapic_timer_frequency);
+		lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
+					TICK_NSEC, lapic_clockevent.shift);
+		lapic_clockevent.max_delta_ns =
+			clockevent_delta2ns(0x7FFFFF, &lapic_clockevent);
+		lapic_clockevent.min_delta_ns =
+			clockevent_delta2ns(0xF, &lapic_clockevent);
+		lapic_clockevent.features &= ~CLOCK_EVT_FEAT_DUMMY;
+		return 0;
+	}
+
 	local_irq_disable();
 
 	/* Replace the global interrupt handler */
@@ -679,12 +698,12 @@ static int __init calibrate_APIC_clock(void)
 	lapic_clockevent.min_delta_ns =
 		clockevent_delta2ns(0xF, &lapic_clockevent);
 
-	calibration_result = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
+	lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
 
 	apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta);
 	apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult);
 	apic_printk(APIC_VERBOSE, "..... calibration result: %u\n",
-		    calibration_result);
+		    lapic_timer_frequency);
 
 	if (cpu_has_tsc) {
 		apic_printk(APIC_VERBOSE, "..... CPU clock speed is "
@@ -695,13 +714,13 @@ static int __init calibrate_APIC_clock(void)
 
 	apic_printk(APIC_VERBOSE, "..... host bus clock speed is "
 		    "%u.%04u MHz.\n",
-		    calibration_result / (1000000 / HZ),
-		    calibration_result % (1000000 / HZ));
+		    lapic_timer_frequency / (1000000 / HZ),
+		    lapic_timer_frequency % (1000000 / HZ));
 
 	/*
 	 * Do a sanity check on the APIC calibration result
 	 */
-	if (calibration_result < (1000000 / HZ)) {
+	if (lapic_timer_frequency < (1000000 / HZ)) {
 		local_irq_enable();
 		pr_warning("APIC frequency too slow, disabling apic timer\n");
 		return -1;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 3c31fa9..6d939d7 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -193,10 +193,8 @@ int __init arch_early_irq_init(void)
 	struct irq_cfg *cfg;
 	int count, node, i;
 
-	if (!legacy_pic->nr_legacy_irqs) {
-		nr_irqs_gsi = 0;
+	if (!legacy_pic->nr_legacy_irqs)
 		io_apic_irqs = ~0UL;
-	}
 
 	for (i = 0; i < nr_ioapics; i++) {
 		ioapics[i].saved_registers =
@@ -1696,6 +1694,7 @@ __apicdebuginit(void) print_IO_APICs(void)
 	int ioapic_idx;
 	struct irq_cfg *cfg;
 	unsigned int irq;
+	struct irq_chip *chip;
 
 	printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
 	for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++)
@@ -1716,6 +1715,10 @@ __apicdebuginit(void) print_IO_APICs(void)
 	for_each_active_irq(irq) {
 		struct irq_pin_list *entry;
 
+		chip = irq_get_chip(irq);
+		if (chip != &ioapic_chip)
+			continue;
+
 		cfg = irq_get_chip_data(irq);
 		if (!cfg)
 			continue;
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 62ae300..9d59bba 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -93,6 +93,8 @@ static int __init early_get_pnodeid(void)
 
 	if (node_id.s.part_number == UV2_HUB_PART_NUMBER)
 		uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1;
+	if (node_id.s.part_number == UV2_HUB_PART_NUMBER_X)
+		uv_min_hub_revision_id += UV2_HUB_REVISION_BASE - 1;
 
 	uv_hub_info->hub_revision = uv_min_hub_revision_id;
 	pnode = (node_id.s.node_id >> 1) & ((1 << m_n_config.s.n_skt) - 1);
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index c7e46cb..0bab2b1 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -442,8 +442,6 @@ static void __cpuinit bsp_init_amd(struct cpuinfo_x86 *c)
 
 static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
 {
-	u32 dummy;
-
 	early_init_amd_mc(c);
 
 	/*
@@ -473,12 +471,12 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
 			set_cpu_cap(c, X86_FEATURE_EXTD_APICID);
 	}
 #endif
-
-	rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
 }
 
 static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 {
+	u32 dummy;
+
 #ifdef CONFIG_SMP
 	unsigned long long value;
 
@@ -657,6 +655,8 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 			checking_wrmsrl(MSR_AMD64_MCx_MASK(4), mask);
 		}
 	}
+
+	rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 6199232..319882e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -208,7 +208,7 @@ static int inject_init(void)
 	if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL))
 		return -ENOMEM;
 	printk(KERN_INFO "Machine check injector initialized\n");
-	mce_chrdev_ops.write = mce_write;
+	register_mce_write_callback(mce_write);
 	register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0,
 				"mce_notify");
 	return 0;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 362056a..2af127d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1634,16 +1634,35 @@ static long mce_chrdev_ioctl(struct file *f, unsigned int cmd,
 	}
 }
 
-/* Modified in mce-inject.c, so not static or const */
-struct file_operations mce_chrdev_ops = {
+static ssize_t (*mce_write)(struct file *filp, const char __user *ubuf,
+			    size_t usize, loff_t *off);
+
+void register_mce_write_callback(ssize_t (*fn)(struct file *filp,
+			     const char __user *ubuf,
+			     size_t usize, loff_t *off))
+{
+	mce_write = fn;
+}
+EXPORT_SYMBOL_GPL(register_mce_write_callback);
+
+ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf,
+			 size_t usize, loff_t *off)
+{
+	if (mce_write)
+		return mce_write(filp, ubuf, usize, off);
+	else
+		return -EINVAL;
+}
+
+static const struct file_operations mce_chrdev_ops = {
 	.open			= mce_chrdev_open,
 	.release		= mce_chrdev_release,
 	.read			= mce_chrdev_read,
+	.write			= mce_chrdev_write,
 	.poll			= mce_chrdev_poll,
 	.unlocked_ioctl		= mce_chrdev_ioctl,
 	.llseek			= no_llseek,
 };
-EXPORT_SYMBOL_GPL(mce_chrdev_ops);
 
 static struct miscdevice mce_chrdev_device = {
 	MISC_MCELOG_MINOR,
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index a71efcdb..97b2635 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -547,6 +547,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
 
 		if (tmp != mask_lo) {
 			printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n");
+			add_taint(TAINT_FIRMWARE_WORKAROUND);
 			mask_lo = tmp;
 		}
 	}
@@ -693,6 +694,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 
 	/* Disable MTRRs, and set the default type to uncached */
 	mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi);
+	wbinvd();
 }
 
 static void post_set(void) __releases(set_atomicity_lock)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 6408910..2bda212 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -312,12 +312,8 @@ int x86_setup_perfctr(struct perf_event *event)
 			return -EOPNOTSUPP;
 	}
 
-	/*
-	 * Do not allow config1 (extended registers) to propagate,
-	 * there's no sane user-space generalization yet:
-	 */
 	if (attr->type == PERF_TYPE_RAW)
-		return 0;
+		return x86_pmu_extra_regs(event->attr.config, event);
 
 	if (attr->type == PERF_TYPE_HW_CACHE)
 		return set_ext_hw_attr(hwc, event);
@@ -588,7 +584,7 @@ done:
 				x86_pmu.put_event_constraints(cpuc, cpuc->event_list[i]);
 		}
 	}
-	return num ? -ENOSPC : 0;
+	return num ? -EINVAL : 0;
 }
 
 /*
@@ -607,7 +603,7 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
 
 	if (is_x86_event(leader)) {
 		if (n >= max_count)
-			return -ENOSPC;
+			return -EINVAL;
 		cpuc->event_list[n] = leader;
 		n++;
 	}
@@ -620,7 +616,7 @@ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader,
 			continue;
 
 		if (n >= max_count)
-			return -ENOSPC;
+			return -EINVAL;
 
 		cpuc->event_list[n] = event;
 		n++;
@@ -1316,7 +1312,7 @@ static int validate_event(struct perf_event *event)
 	c = x86_pmu.get_event_constraints(fake_cpuc, event);
 
 	if (!c || !c->weight)
-		ret = -ENOSPC;
+		ret = -EINVAL;
 
 	if (x86_pmu.put_event_constraints)
 		x86_pmu.put_event_constraints(fake_cpuc, event);
@@ -1341,7 +1337,7 @@ static int validate_group(struct perf_event *event)
 {
 	struct perf_event *leader = event->group_leader;
 	struct cpu_hw_events *fake_cpuc;
-	int ret = -ENOSPC, n;
+	int ret = -EINVAL, n;
 
 	fake_cpuc = allocate_fake_cpuc();
 	if (IS_ERR(fake_cpuc))
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index ab6343d..3b8a2d3 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -199,8 +199,7 @@ static int force_ibs_eilvt_setup(void)
 		goto out;
 	}
 
-	pr_err(FW_BUG "using offset %d for IBS interrupts\n", offset);
-	pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
+	pr_info("IBS: LVT offset %d assigned\n", offset);
 
 	return 0;
 out:
@@ -265,19 +264,23 @@ perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *h
 static __init int amd_ibs_init(void)
 {
 	u32 caps;
-	int ret;
+	int ret = -EINVAL;
 
 	caps = __get_ibs_caps();
 	if (!caps)
 		return -ENODEV;	/* ibs not supported by the cpu */
 
-	if (!ibs_eilvt_valid()) {
-		ret = force_ibs_eilvt_setup();
-		if (ret) {
-			pr_err("Failed to setup IBS, %d\n", ret);
-			return ret;
-		}
-	}
+	/*
+	 * Force LVT offset assignment for family 10h: The offsets are
+	 * not assigned by the BIOS for this family, so the OS is
+	 * responsible for doing it. If the OS assignment fails, fall
+	 * back to BIOS settings and try to setup this.
+	 */
+	if (boot_cpu_data.x86 == 0x10)
+		force_ibs_eilvt_setup();
+
+	if (!ibs_eilvt_valid())
+		goto out;
 
 	get_online_cpus();
 	ibs_caps = caps;
@@ -287,7 +290,11 @@ static __init int amd_ibs_init(void)
 	smp_call_function(setup_APIC_ibs, NULL, 1);
 	put_online_cpus();
 
-	return perf_event_ibs_init();
+	ret = perf_event_ibs_init();
+out:
+	if (ret)
+		pr_err("Failed to setup IBS, %d\n", ret);
+	return ret;
 }
 
 /* Since we need the pci subsystem to init ibs we can't do this earlier: */
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 2be5ebe..8d601b1 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -1545,6 +1545,13 @@ static void intel_clovertown_quirks(void)
 	x86_pmu.pebs_constraints = NULL;
 }
 
+static void intel_sandybridge_quirks(void)
+{
+	printk(KERN_WARNING "PEBS disabled due to CPU errata.\n");
+	x86_pmu.pebs = 0;
+	x86_pmu.pebs_constraints = NULL;
+}
+
 __init int intel_pmu_init(void)
 {
 	union cpuid10_edx edx;
@@ -1694,6 +1701,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 42: /* SandyBridge */
+		x86_pmu.quirks = intel_sandybridge_quirks;
 	case 45: /* SandyBridge, "Romely-EP" */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index c0d238f..73da6b6 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -493,6 +493,7 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 	unsigned long from = cpuc->lbr_entries[0].from;
 	unsigned long old_to, to = cpuc->lbr_entries[0].to;
 	unsigned long ip = regs->ip;
+	int is_64bit = 0;
 
 	/*
 	 * We don't need to fixup if the PEBS assist is fault like
@@ -544,7 +545,10 @@ static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs)
 		} else
 			kaddr = (void *)to;
 
-		kernel_insn_init(&insn, kaddr);
+#ifdef CONFIG_X86_64
+		is_64bit = kernel_ip(to) || !test_thread_flag(TIF_IA32);
+#endif
+		insn_init(&insn, kaddr, is_64bit);
 		insn_get_length(&insn);
 		to += insn.length;
 	} while (to < ip);
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 492bf13..ef484d9 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1268,7 +1268,7 @@ reserve:
 	}
 
 done:
-	return num ? -ENOSPC : 0;
+	return num ? -EINVAL : 0;
 }
 
 static __initconst const struct x86_pmu p4_pmu = {
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index acf8fbf..69bca46 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -38,6 +38,9 @@ static inline void stack_overflow_check(struct pt_regs *regs)
 #ifdef CONFIG_DEBUG_STACKOVERFLOW
 	u64 curbase = (u64)task_stack_page(current);
 
+	if (user_mode_vm(regs))
+		return;
+
 	WARN_ONCE(regs->sp >= curbase &&
 		  regs->sp <= curbase + THREAD_SIZE &&
 		  regs->sp <  curbase + sizeof(struct thread_info) +
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index c1a0188..44842d7 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -74,9 +74,10 @@ static cycle_t kvm_clock_read(void)
 	struct pvclock_vcpu_time_info *src;
 	cycle_t ret;
 
-	src = &get_cpu_var(hv_clock);
+	preempt_disable_notrace();
+	src = &__get_cpu_var(hv_clock);
 	ret = pvclock_clocksource_read(src);
-	put_cpu_var(hv_clock);
+	preempt_enable_notrace();
 	return ret;
 }
 
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index f2d2a66..9d46f5e 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -256,7 +256,7 @@ static int __init microcode_dev_init(void)
 	return 0;
 }
 
-static void microcode_dev_exit(void)
+static void __exit microcode_dev_exit(void)
 {
 	misc_deregister(&microcode_dev);
 }
@@ -519,10 +519,8 @@ static int __init microcode_init(void)
 
 	microcode_pdev = platform_device_register_simple("microcode", -1,
 							 NULL, 0);
-	if (IS_ERR(microcode_pdev)) {
-		microcode_dev_exit();
+	if (IS_ERR(microcode_pdev))
 		return PTR_ERR(microcode_pdev);
-	}
 
 	get_online_cpus();
 	mutex_lock(&microcode_mutex);
@@ -532,14 +530,12 @@ static int __init microcode_init(void)
 	mutex_unlock(&microcode_mutex);
 	put_online_cpus();
 
-	if (error) {
-		platform_device_unregister(microcode_pdev);
-		return error;
-	}
+	if (error)
+		goto out_pdev;
 
 	error = microcode_dev_init();
 	if (error)
-		return error;
+		goto out_sysdev_driver;
 
 	register_syscore_ops(&mc_syscore_ops);
 	register_hotcpu_notifier(&mc_cpu_notifier);
@@ -548,6 +544,20 @@ static int __init microcode_init(void)
 		" <tigran@aivazian.fsnet.co.uk>, Peter Oruba\n");
 
 	return 0;
+
+out_sysdev_driver:
+	get_online_cpus();
+	mutex_lock(&microcode_mutex);
+
+	sysdev_driver_unregister(&cpu_sysdev_class, &mc_sysdev_driver);
+
+	mutex_unlock(&microcode_mutex);
+	put_online_cpus();
+
+out_pdev:
+	platform_device_unregister(microcode_pdev);
+	return error;
+
 }
 module_init(microcode_init);
 
diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c
index 9103b89..0741b062 100644
--- a/arch/x86/kernel/mpparse.c
+++ b/arch/x86/kernel/mpparse.c
@@ -95,8 +95,8 @@ static void __init MP_bus_info(struct mpc_bus *m)
 	}
 #endif
 
+	set_bit(m->busid, mp_bus_not_pci);
 	if (strncmp(str, BUSTYPE_ISA, sizeof(BUSTYPE_ISA) - 1) == 0) {
-		set_bit(m->busid, mp_bus_not_pci);
 #if defined(CONFIG_EISA) || defined(CONFIG_MCA)
 		mp_bus_id_to_type[m->busid] = MP_BUS_ISA;
 #endif
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index b9c8628..e88f37b 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -29,6 +29,7 @@
 #include <asm/traps.h>
 #include <asm/mach_traps.h>
 #include <asm/nmi.h>
+#include <asm/x86_init.h>
 
 #define NMI_MAX_NAMELEN	16
 struct nmiaction {
@@ -348,7 +349,7 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
 
 	/* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
 	raw_spin_lock(&nmi_reason_lock);
-	reason = get_nmi_reason();
+	reason = x86_platform.get_nmi_reason();
 
 	if (reason & NMI_REASON_MASK) {
 		if (reason & NMI_REASON_SERR)
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index b9b3b1a..ee5d4fb 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -403,6 +403,14 @@ void default_idle(void)
 EXPORT_SYMBOL(default_idle);
 #endif
 
+bool set_pm_idle_to_default(void)
+{
+	bool ret = !!pm_idle;
+
+	pm_idle = default_idle;
+
+	return ret;
+}
 void stop_this_cpu(void *dummy)
 {
 	local_irq_disable();
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index b78643d..03920a1 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -553,4 +553,17 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC,
 			quirk_amd_nb_node);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_LINK,
 			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F0,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F1,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F2,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4,
+			quirk_amd_nb_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F5,
+			quirk_amd_nb_node);
+
 #endif
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index e334be1..37a458b 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -124,7 +124,7 @@ __setup("reboot=", reboot_setup);
  */
 
 /*
- * Some machines require the "reboot=b"  commandline option,
+ * Some machines require the "reboot=b" or "reboot=k"  commandline options,
  * this quirk makes that automatic.
  */
 static int __init set_bios_reboot(const struct dmi_system_id *d)
@@ -136,6 +136,15 @@ static int __init set_bios_reboot(const struct dmi_system_id *d)
 	return 0;
 }
 
+static int __init set_kbd_reboot(const struct dmi_system_id *d)
+{
+	if (reboot_type != BOOT_KBD) {
+		reboot_type = BOOT_KBD;
+		printk(KERN_INFO "%s series board detected. Selecting KBD-method for reboot.\n", d->ident);
+	}
+	return 0;
+}
+
 static struct dmi_system_id __initdata reboot_dmi_table[] = {
 	{	/* Handle problems with rebooting on Dell E520's */
 		.callback = set_bios_reboot,
@@ -295,7 +304,7 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 		},
 	},
 	{ /* Handle reboot issue on Acer Aspire one */
-		.callback = set_bios_reboot,
+		.callback = set_kbd_reboot,
 		.ident = "Acer Aspire One A110",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
@@ -443,6 +452,14 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6420"),
 		},
 	},
+	{	/* Handle problems with rebooting on the OptiPlex 990. */
+		.callback = set_pci_reboot,
+		.ident = "Dell OptiPlex 990",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"),
+		},
+	},
 	{ }
 };
 
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 348ce01..af6db6e 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -12,6 +12,7 @@
 #include <asm/vsyscall.h>
 #include <asm/x86_init.h>
 #include <asm/time.h>
+#include <asm/mrst.h>
 
 #ifdef CONFIG_X86_32
 /*
@@ -242,6 +243,10 @@ static __init int add_rtc_cmos(void)
 	if (of_have_populated_dt())
 		return 0;
 
+	/* Intel MID platforms don't have ioport rtc */
+	if (mrst_identify_cpu())
+		return -ENODEV;
+
 	platform_device_register(&rtc_device);
 	dev_info(&rtc_device.dev,
 		 "registered platform RTC device (no PNP device found)\n");
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index afaf384..cf0ef98 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1045,6 +1045,8 @@ void __init setup_arch(char **cmdline_p)
 
 	x86_init.timers.wallclock_init();
 
+	x86_platform.wallclock_init();
+
 	mcheck_init();
 
 	arch_init_ideal_nops();
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 6f164bd..c1d6cd5 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -21,12 +21,14 @@
 #include <asm/pat.h>
 #include <asm/tsc.h>
 #include <asm/iommu.h>
+#include <asm/mach_traps.h>
 
 void __cpuinit x86_init_noop(void) { }
 void __init x86_init_uint_noop(unsigned int unused) { }
 void __init x86_init_pgd_noop(pgd_t *unused) { }
 int __init iommu_init_noop(void) { return 0; }
 void iommu_shutdown_noop(void) { }
+void wallclock_init_noop(void) { }
 
 /*
  * The platform setup functions are preset with the default functions
@@ -97,11 +99,13 @@ static int default_i8042_detect(void) { return 1; };
 
 struct x86_platform_ops x86_platform = {
 	.calibrate_tsc			= native_calibrate_tsc,
+	.wallclock_init			= wallclock_init_noop,
 	.get_wallclock			= mach_get_cmos_time,
 	.set_wallclock			= mach_set_rtc_mmss,
 	.iommu_shutdown			= iommu_shutdown_noop,
 	.is_untracked_pat_range		= is_ISA_range,
 	.nmi_init			= default_nmi_init,
+	.get_nmi_reason			= default_get_nmi_reason,
 	.i8042_detect			= default_i8042_detect
 };
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a0d6bd9..579a0b5 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -39,6 +39,7 @@
 #include <asm/mce.h>
 #include <asm/i387.h>
 #include <asm/xcr.h>
+#include <asm/perf_event.h>
 
 #include "trace.h"
 
@@ -118,7 +119,7 @@ module_param(ple_gap, int, S_IRUGO);
 static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
 module_param(ple_window, int, S_IRUGO);
 
-#define NR_AUTOLOAD_MSRS 1
+#define NR_AUTOLOAD_MSRS 8
 #define VMCS02_POOL_SIZE 1
 
 struct vmcs {
@@ -622,6 +623,7 @@ static unsigned long *vmx_msr_bitmap_legacy;
 static unsigned long *vmx_msr_bitmap_longmode;
 
 static bool cpu_has_load_ia32_efer;
+static bool cpu_has_load_perf_global_ctrl;
 
 static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
 static DEFINE_SPINLOCK(vmx_vpid_lock);
@@ -1191,15 +1193,34 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 	vmcs_write32(EXCEPTION_BITMAP, eb);
 }
 
+static void clear_atomic_switch_msr_special(unsigned long entry,
+		unsigned long exit)
+{
+	vmcs_clear_bits(VM_ENTRY_CONTROLS, entry);
+	vmcs_clear_bits(VM_EXIT_CONTROLS, exit);
+}
+
 static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 {
 	unsigned i;
 	struct msr_autoload *m = &vmx->msr_autoload;
 
-	if (msr == MSR_EFER && cpu_has_load_ia32_efer) {
-		vmcs_clear_bits(VM_ENTRY_CONTROLS, VM_ENTRY_LOAD_IA32_EFER);
-		vmcs_clear_bits(VM_EXIT_CONTROLS, VM_EXIT_LOAD_IA32_EFER);
-		return;
+	switch (msr) {
+	case MSR_EFER:
+		if (cpu_has_load_ia32_efer) {
+			clear_atomic_switch_msr_special(VM_ENTRY_LOAD_IA32_EFER,
+					VM_EXIT_LOAD_IA32_EFER);
+			return;
+		}
+		break;
+	case MSR_CORE_PERF_GLOBAL_CTRL:
+		if (cpu_has_load_perf_global_ctrl) {
+			clear_atomic_switch_msr_special(
+					VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL,
+					VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL);
+			return;
+		}
+		break;
 	}
 
 	for (i = 0; i < m->nr; ++i)
@@ -1215,25 +1236,55 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
 }
 
+static void add_atomic_switch_msr_special(unsigned long entry,
+		unsigned long exit, unsigned long guest_val_vmcs,
+		unsigned long host_val_vmcs, u64 guest_val, u64 host_val)
+{
+	vmcs_write64(guest_val_vmcs, guest_val);
+	vmcs_write64(host_val_vmcs, host_val);
+	vmcs_set_bits(VM_ENTRY_CONTROLS, entry);
+	vmcs_set_bits(VM_EXIT_CONTROLS, exit);
+}
+
 static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 				  u64 guest_val, u64 host_val)
 {
 	unsigned i;
 	struct msr_autoload *m = &vmx->msr_autoload;
 
-	if (msr == MSR_EFER && cpu_has_load_ia32_efer) {
-		vmcs_write64(GUEST_IA32_EFER, guest_val);
-		vmcs_write64(HOST_IA32_EFER, host_val);
-		vmcs_set_bits(VM_ENTRY_CONTROLS, VM_ENTRY_LOAD_IA32_EFER);
-		vmcs_set_bits(VM_EXIT_CONTROLS, VM_EXIT_LOAD_IA32_EFER);
-		return;
+	switch (msr) {
+	case MSR_EFER:
+		if (cpu_has_load_ia32_efer) {
+			add_atomic_switch_msr_special(VM_ENTRY_LOAD_IA32_EFER,
+					VM_EXIT_LOAD_IA32_EFER,
+					GUEST_IA32_EFER,
+					HOST_IA32_EFER,
+					guest_val, host_val);
+			return;
+		}
+		break;
+	case MSR_CORE_PERF_GLOBAL_CTRL:
+		if (cpu_has_load_perf_global_ctrl) {
+			add_atomic_switch_msr_special(
+					VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL,
+					VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL,
+					GUEST_IA32_PERF_GLOBAL_CTRL,
+					HOST_IA32_PERF_GLOBAL_CTRL,
+					guest_val, host_val);
+			return;
+		}
+		break;
 	}
 
 	for (i = 0; i < m->nr; ++i)
 		if (m->guest[i].index == msr)
 			break;
 
-	if (i == m->nr) {
+	if (i == NR_AUTOLOAD_MSRS) {
+		printk_once(KERN_WARNING"Not enough mst switch entries. "
+				"Can't add msr %x\n", msr);
+		return;
+	} else if (i == m->nr) {
 		++m->nr;
 		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
 		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
@@ -2455,6 +2506,42 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 		&& allow_1_setting(MSR_IA32_VMX_EXIT_CTLS,
 				   VM_EXIT_LOAD_IA32_EFER);
 
+	cpu_has_load_perf_global_ctrl =
+		allow_1_setting(MSR_IA32_VMX_ENTRY_CTLS,
+				VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL)
+		&& allow_1_setting(MSR_IA32_VMX_EXIT_CTLS,
+				   VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL);
+
+	/*
+	 * Some cpus support VM_ENTRY_(LOAD|SAVE)_IA32_PERF_GLOBAL_CTRL
+	 * but due to arrata below it can't be used. Workaround is to use
+	 * msr load mechanism to switch IA32_PERF_GLOBAL_CTRL.
+	 *
+	 * VM Exit May Incorrectly Clear IA32_PERF_GLOBAL_CTRL [34:32]
+	 *
+	 * AAK155             (model 26)
+	 * AAP115             (model 30)
+	 * AAT100             (model 37)
+	 * BC86,AAY89,BD102   (model 44)
+	 * BA97               (model 46)
+	 *
+	 */
+	if (cpu_has_load_perf_global_ctrl && boot_cpu_data.x86 == 0x6) {
+		switch (boot_cpu_data.x86_model) {
+		case 26:
+		case 30:
+		case 37:
+		case 44:
+		case 46:
+			cpu_has_load_perf_global_ctrl = false;
+			printk_once(KERN_WARNING"kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL "
+					"does not work properly. Using workaround\n");
+			break;
+		default:
+			break;
+		}
+	}
+
 	return 0;
 }
 
@@ -5968,6 +6055,24 @@ static void vmx_cancel_injection(struct kvm_vcpu *vcpu)
 	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
 }
 
+static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
+{
+	int i, nr_msrs;
+	struct perf_guest_switch_msr *msrs;
+
+	msrs = perf_guest_get_msrs(&nr_msrs);
+
+	if (!msrs)
+		return;
+
+	for (i = 0; i < nr_msrs; i++)
+		if (msrs[i].host == msrs[i].guest)
+			clear_atomic_switch_msr(vmx, msrs[i].msr);
+		else
+			add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest,
+					msrs[i].host);
+}
+
 #ifdef CONFIG_X86_64
 #define R "r"
 #define Q "q"
@@ -6017,6 +6122,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
 		vmx_set_interrupt_shadow(vcpu, 0);
 
+	atomic_switch_perf_msrs(vmx);
+
 	vmx->__launched = vmx->loaded_vmcs->launched;
 	asm(
 		/* Store host registers */
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index b499626..f4f29b1 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -45,6 +45,7 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 	BUG_ON(!pte_none(*(kmap_pte-idx)));
 	set_pte(kmap_pte-idx, mk_pte(page, prot));
+	arch_flush_lazy_mmu_mode();
 
 	return (void *)vaddr;
 }
@@ -88,6 +89,7 @@ void __kunmap_atomic(void *kvaddr)
 		 */
 		kpte_clear_flush(kmap_pte-idx, vaddr);
 		kmap_atomic_idx_pop();
+		arch_flush_lazy_mmu_mode();
 	}
 #ifdef CONFIG_DEBUG_HIGHMEM
 	else {
diff --git a/arch/x86/oprofile/init.c b/arch/x86/oprofile/init.c
index cdfe4c5..f148cf6 100644
--- a/arch/x86/oprofile/init.c
+++ b/arch/x86/oprofile/init.c
@@ -21,6 +21,7 @@ extern int op_nmi_timer_init(struct oprofile_operations *ops);
 extern void op_nmi_exit(void);
 extern void x86_backtrace(struct pt_regs * const regs, unsigned int depth);
 
+static int nmi_timer;
 
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
@@ -31,8 +32,9 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 #ifdef CONFIG_X86_LOCAL_APIC
 	ret = op_nmi_init(ops);
 #endif
+	nmi_timer = (ret != 0);
 #ifdef CONFIG_X86_IO_APIC
-	if (ret < 0)
+	if (nmi_timer)
 		ret = op_nmi_timer_init(ops);
 #endif
 	ops->backtrace = x86_backtrace;
@@ -44,6 +46,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 void oprofile_arch_exit(void)
 {
 #ifdef CONFIG_X86_LOCAL_APIC
-	op_nmi_exit();
+	if (!nmi_timer)
+		op_nmi_exit();
 #endif
 }
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index 541020d..ad4ec1c 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -76,6 +76,20 @@ struct sfi_rtc_table_entry sfi_mrtc_array[SFI_MRTC_MAX];
 EXPORT_SYMBOL_GPL(sfi_mrtc_array);
 int sfi_mrtc_num;
 
+static void mrst_power_off(void)
+{
+	if (__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT)
+		intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 1);
+}
+
+static void mrst_reboot(void)
+{
+	if (__mrst_cpu_chip == MRST_CPU_CHIP_LINCROFT)
+		intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0);
+	else
+		intel_scu_ipc_simple_command(IPCMSG_COLD_BOOT, 0);
+}
+
 /* parse all the mtimer info to a static mtimer array */
 static int __init sfi_parse_mtmr(struct sfi_table_header *table)
 {
@@ -187,11 +201,34 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table)
 static unsigned long __init mrst_calibrate_tsc(void)
 {
 	unsigned long flags, fast_calibrate;
-
-	local_irq_save(flags);
-	fast_calibrate = apbt_quick_calibrate();
-	local_irq_restore(flags);
-
+	if (__mrst_cpu_chip == MRST_CPU_CHIP_PENWELL) {
+		u32 lo, hi, ratio, fsb;
+
+		rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+		pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi);
+		ratio = (hi >> 8) & 0x1f;
+		pr_debug("ratio is %d\n", ratio);
+		if (!ratio) {
+			pr_err("read a zero ratio, should be incorrect!\n");
+			pr_err("force tsc ratio to 16 ...\n");
+			ratio = 16;
+		}
+		rdmsr(MSR_FSB_FREQ, lo, hi);
+		if ((lo & 0x7) == 0x7)
+			fsb = PENWELL_FSB_FREQ_83SKU;
+		else
+			fsb = PENWELL_FSB_FREQ_100SKU;
+		fast_calibrate = ratio * fsb;
+		pr_debug("read penwell tsc %lu khz\n", fast_calibrate);
+		lapic_timer_frequency = fsb * 1000 / HZ;
+		/* mark tsc clocksource as reliable */
+		set_cpu_cap(&boot_cpu_data, X86_FEATURE_TSC_RELIABLE);
+	} else {
+		local_irq_save(flags);
+		fast_calibrate = apbt_quick_calibrate();
+		local_irq_restore(flags);
+	}
+	
 	if (fast_calibrate)
 		return fast_calibrate;
 
@@ -242,15 +279,15 @@ static int mrst_i8042_detect(void)
 	return 0;
 }
 
-/* Reboot and power off are handled by the SCU on a MID device */
-static void mrst_power_off(void)
-{
-	intel_scu_ipc_simple_command(0xf1, 1);
-}
-
-static void mrst_reboot(void)
+/*
+ * Moorestown does not have external NMI source nor port 0x61 to report
+ * NMI status. The possible NMI sources are from pmu as a result of NMI
+ * watchdog or lock debug. Reading io port 0x61 results in 0xff which
+ * misled NMI handler.
+ */
+static unsigned char mrst_get_nmi_reason(void)
 {
-	intel_scu_ipc_simple_command(0xf1, 0);
+	return 0;
 }
 
 /*
@@ -274,6 +311,8 @@ void __init x86_mrst_early_setup(void)
 	x86_platform.calibrate_tsc = mrst_calibrate_tsc;
 	x86_platform.i8042_detect = mrst_i8042_detect;
 	x86_init.timers.wallclock_init = mrst_rtc_init;
+	x86_platform.get_nmi_reason = mrst_get_nmi_reason;
+
 	x86_init.pci.init = pci_mrst_init;
 	x86_init.pci.fixup_irqs = x86_init_noop;
 
@@ -448,6 +487,46 @@ static void __init *max7315_platform_data(void *info)
 	return max7315;
 }
 
+static void *tca6416_platform_data(void *info)
+{
+	static struct pca953x_platform_data tca6416;
+	struct i2c_board_info *i2c_info = info;
+	int gpio_base, intr;
+	char base_pin_name[SFI_NAME_LEN + 1];
+	char intr_pin_name[SFI_NAME_LEN + 1];
+
+	strcpy(i2c_info->type, "tca6416");
+	strcpy(base_pin_name, "tca6416_base");
+	strcpy(intr_pin_name, "tca6416_int");
+
+	gpio_base = get_gpio_by_name(base_pin_name);
+	intr = get_gpio_by_name(intr_pin_name);
+
+	if (gpio_base == -1)
+		return NULL;
+	tca6416.gpio_base = gpio_base;
+	if (intr != -1) {
+		i2c_info->irq = intr + MRST_IRQ_OFFSET;
+		tca6416.irq_base = gpio_base + MRST_IRQ_OFFSET;
+	} else {
+		i2c_info->irq = -1;
+		tca6416.irq_base = -1;
+	}
+	return &tca6416;
+}
+
+static void *mpu3050_platform_data(void *info)
+{
+	struct i2c_board_info *i2c_info = info;
+	int intr = get_gpio_by_name("mpu3050_int");
+
+	if (intr == -1)
+		return NULL;
+
+	i2c_info->irq = intr + MRST_IRQ_OFFSET;
+	return NULL;
+}
+
 static void __init *emc1403_platform_data(void *info)
 {
 	static short intr2nd_pdata;
@@ -610,12 +689,15 @@ static void *msic_ocd_platform_data(void *info)
 static const struct devs_id __initconst device_ids[] = {
 	{"bma023", SFI_DEV_TYPE_I2C, 1, &no_platform_data},
 	{"pmic_gpio", SFI_DEV_TYPE_SPI, 1, &pmic_gpio_platform_data},
+	{"pmic_gpio", SFI_DEV_TYPE_IPC, 1, &pmic_gpio_platform_data},
 	{"spi_max3111", SFI_DEV_TYPE_SPI, 0, &max3111_platform_data},
 	{"i2c_max7315", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data},
 	{"i2c_max7315_2", SFI_DEV_TYPE_I2C, 1, &max7315_platform_data},
+	{"tca6416", SFI_DEV_TYPE_I2C, 1, &tca6416_platform_data},
 	{"emc1403", SFI_DEV_TYPE_I2C, 1, &emc1403_platform_data},
 	{"i2c_accel", SFI_DEV_TYPE_I2C, 0, &lis331dl_platform_data},
 	{"pmic_audio", SFI_DEV_TYPE_IPC, 1, &no_platform_data},
+	{"mpu3050", SFI_DEV_TYPE_I2C, 1, &mpu3050_platform_data},
 
 	/* MSIC subdevices */
 	{"msic_battery", SFI_DEV_TYPE_IPC, 1, &msic_battery_platform_data},
diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h
index 118c143..2c32df6 100644
--- a/arch/x86/um/asm/processor.h
+++ b/arch/x86/um/asm/processor.h
@@ -11,7 +11,7 @@
 #endif
 
 #define KSTK_EIP(tsk) KSTK_REG(tsk, HOST_IP)
-#define KSTK_ESP(tsk) KSTK_REG(tsk, HOST_IP)
+#define KSTK_ESP(tsk) KSTK_REG(tsk, HOST_SP)
 #define KSTK_EBP(tsk) KSTK_REG(tsk, HOST_BP)
 
 #define ARCH_IS_STACKGROW(address) \
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index da8afd5..1f92865 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1356,7 +1356,7 @@ static int __cpuinit xen_hvm_cpu_notify(struct notifier_block *self,
 	int cpu = (long)hcpu;
 	switch (action) {
 	case CPU_UP_PREPARE:
-		per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
+		xen_vcpu_setup(cpu);
 		if (xen_have_vector_callback)
 			xen_init_lock_cpu(cpu);
 		break;
@@ -1386,7 +1386,6 @@ static void __init xen_hvm_guest_init(void)
 	xen_hvm_smp_init();
 	register_cpu_notifier(&xen_hvm_cpu_notifier);
 	xen_unplug_emulated_devices();
-	have_vcpu_info_placement = 0;
 	x86_init.irqs.intr_init = xen_init_IRQ;
 	xen_hvm_init_time_ops();
 	xen_hvm_init_mmu_ops();
diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index 6bbfd7a..5a40d24 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -71,7 +71,7 @@ int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
 
 	if (shared == NULL) {
 		struct vm_struct *area =
-			alloc_vm_area(PAGE_SIZE * max_nr_gframes);
+			alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL);
 		BUG_ON(area == NULL);
 		shared = area->addr;
 		*__shared = shared;
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 38d0af4..1093f80 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -410,6 +410,6 @@ void __init xen_arch_setup(void)
 #endif
 	disable_cpuidle();
 	boot_option_idle_override = IDLE_HALT;
-
+	WARN_ON(set_pm_idle_to_default());
 	fiddle_vdso();
 }
diff --git a/block/blk-core.c b/block/blk-core.c
index f43c8a5..ea70e6c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1379,15 +1379,19 @@ get_rq:
 		 */
 		if (list_empty(&plug->list))
 			trace_block_plug(q);
-		else if (!plug->should_sort) {
-			struct request *__rq;
+		else {
+			if (!plug->should_sort) {
+				struct request *__rq;
 
-			__rq = list_entry_rq(plug->list.prev);
-			if (__rq->q != q)
-				plug->should_sort = 1;
+				__rq = list_entry_rq(plug->list.prev);
+				if (__rq->q != q)
+					plug->should_sort = 1;
+			}
+			if (request_count >= BLK_MAX_REQUEST_COUNT) {
+				blk_flush_plug_list(plug, false);
+				trace_block_plug(q);
+			}
 		}
-		if (request_count >= BLK_MAX_REQUEST_COUNT)
-			blk_flush_plug_list(plug, false);
 		list_add_tail(&req->queuelist, &plug->list);
 		drive_stat_acct(req, 1);
 	} else {
diff --git a/block/blk-map.c b/block/blk-map.c
index e663ac2..164cd00 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -204,10 +204,11 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 		if (!iov[i].iov_len)
 			return -EINVAL;
 
-		if (uaddr & queue_dma_alignment(q)) {
+		/*
+		 * Keep going so we check length of all segments
+		 */
+		if (uaddr & queue_dma_alignment(q))
 			unaligned = 1;
-			break;
-		}
 	}
 
 	if (unaligned || (q->dma_pad_mask & len) || map_data)
diff --git a/block/genhd.c b/block/genhd.c
index 9253839..02e9fca 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -19,7 +19,6 @@
 #include <linux/mutex.h>
 #include <linux/idr.h>
 #include <linux/log2.h>
-#include <linux/ctype.h>
 
 #include "blk.h"
 
@@ -916,74 +915,6 @@ static int __init genhd_device_init(void)
 
 subsys_initcall(genhd_device_init);
 
-static ssize_t alias_show(struct device *dev,
-			       struct device_attribute *attr, char *buf)
-{
-	struct gendisk *disk = dev_to_disk(dev);
-	ssize_t ret = 0;
-
-	if (disk->alias)
-		ret = snprintf(buf, ALIAS_LEN, "%s\n", disk->alias);
-	return ret;
-}
-
-static ssize_t alias_store(struct device *dev, struct device_attribute *attr,
-			   const char *buf, size_t count)
-{
-	struct gendisk *disk = dev_to_disk(dev);
-	char *alias;
-	char *envp[] = { NULL, NULL };
-	unsigned char c;
-	int i;
-	ssize_t ret = count;
-
-	if (!count)
-		return -EINVAL;
-
-	if (count >= ALIAS_LEN) {
-		printk(KERN_ERR "alias: alias is too long\n");
-		return -EINVAL;
-	}
-
-	/* Validation check */
-	for (i = 0; i < count; i++) {
-		c = buf[i];
-		if (i == count - 1 && c == '\n')
-			break;
-		if (!isalnum(c) && c != '_' && c != '-') {
-			printk(KERN_ERR "alias: invalid alias\n");
-			return -EINVAL;
-		}
-	}
-
-	if (disk->alias) {
-		printk(KERN_INFO "alias: %s is already assigned (%s)\n",
-		       disk->disk_name, disk->alias);
-		return -EINVAL;
-	}
-
-	alias = kasprintf(GFP_KERNEL, "%s", buf);
-	if (!alias)
-		return -ENOMEM;
-
-	if (alias[count - 1] == '\n')
-		alias[count - 1] = '\0';
-
-	envp[0] = kasprintf(GFP_KERNEL, "ALIAS=%s", alias);
-	if (!envp[0]) {
-		kfree(alias);
-		return -ENOMEM;
-	}
-
-	disk->alias = alias;
-	printk(KERN_INFO "alias: assigned %s to %s\n", alias, disk->disk_name);
-
-	kobject_uevent_env(&dev->kobj, KOBJ_ADD, envp);
-
-	kfree(envp[0]);
-	return ret;
-}
-
 static ssize_t disk_range_show(struct device *dev,
 			       struct device_attribute *attr, char *buf)
 {
@@ -1043,7 +974,6 @@ static ssize_t disk_discard_alignment_show(struct device *dev,
 	return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue));
 }
 
-static DEVICE_ATTR(alias, S_IRUGO|S_IWUSR, alias_show, alias_store);
 static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);
 static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL);
 static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL);
@@ -1066,7 +996,6 @@ static struct device_attribute dev_attr_fail_timeout =
 #endif
 
 static struct attribute *disk_attrs[] = {
-	&dev_attr_alias.attr,
 	&dev_attr_range.attr,
 	&dev_attr_ext_range.attr,
 	&dev_attr_removable.attr,
diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c
index 1274080..631b947 100644
--- a/drivers/acpi/apei/erst.c
+++ b/drivers/acpi/apei/erst.c
@@ -932,7 +932,8 @@ static int erst_check_table(struct acpi_table_erst *erst_tab)
 static int erst_open_pstore(struct pstore_info *psi);
 static int erst_close_pstore(struct pstore_info *psi);
 static ssize_t erst_reader(u64 *id, enum pstore_type_id *type,
-			   struct timespec *time, struct pstore_info *psi);
+			   struct timespec *time, char **buf,
+			   struct pstore_info *psi);
 static int erst_writer(enum pstore_type_id type, u64 *id, unsigned int part,
 		       size_t size, struct pstore_info *psi);
 static int erst_clearer(enum pstore_type_id type, u64 id,
@@ -986,17 +987,23 @@ static int erst_close_pstore(struct pstore_info *psi)
 }
 
 static ssize_t erst_reader(u64 *id, enum pstore_type_id *type,
-			   struct timespec *time, struct pstore_info *psi)
+			   struct timespec *time, char **buf,
+			   struct pstore_info *psi)
 {
 	int rc;
 	ssize_t len = 0;
 	u64 record_id;
-	struct cper_pstore_record *rcd = (struct cper_pstore_record *)
-					(erst_info.buf - sizeof(*rcd));
+	struct cper_pstore_record *rcd;
+	size_t rcd_len = sizeof(*rcd) + erst_info.bufsize;
 
 	if (erst_disable)
 		return -ENODEV;
 
+	rcd = kmalloc(rcd_len, GFP_KERNEL);
+	if (!rcd) {
+		rc = -ENOMEM;
+		goto out;
+	}
 skip:
 	rc = erst_get_record_id_next(&reader_pos, &record_id);
 	if (rc)
@@ -1004,22 +1011,27 @@ skip:
 
 	/* no more record */
 	if (record_id == APEI_ERST_INVALID_RECORD_ID) {
-		rc = -1;
+		rc = -EINVAL;
 		goto out;
 	}
 
-	len = erst_read(record_id, &rcd->hdr, sizeof(*rcd) +
-			erst_info.bufsize);
+	len = erst_read(record_id, &rcd->hdr, rcd_len);
 	/* The record may be cleared by others, try read next record */
 	if (len == -ENOENT)
 		goto skip;
-	else if (len < 0) {
-		rc = -1;
+	else if (len < sizeof(*rcd)) {
+		rc = -EIO;
 		goto out;
 	}
 	if (uuid_le_cmp(rcd->hdr.creator_id, CPER_CREATOR_PSTORE) != 0)
 		goto skip;
 
+	*buf = kmalloc(len, GFP_KERNEL);
+	if (*buf == NULL) {
+		rc = -ENOMEM;
+		goto out;
+	}
+	memcpy(*buf, rcd->data, len - sizeof(*rcd));
 	*id = record_id;
 	if (uuid_le_cmp(rcd->sec_hdr.section_type,
 			CPER_SECTION_TYPE_DMESG) == 0)
@@ -1037,6 +1049,7 @@ skip:
 	time->tv_nsec = 0;
 
 out:
+	kfree(rcd);
 	return (rc < 0) ? rc : (len - sizeof(*rcd));
 }
 
diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c
index ec55595..43b8758 100644
--- a/drivers/ata/ahci_platform.c
+++ b/drivers/ata/ahci_platform.c
@@ -67,7 +67,7 @@ static int __init ahci_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct ahci_platform_data *pdata = dev_get_platdata(dev);
 	const struct platform_device_id *id = platform_get_device_id(pdev);
-	struct ata_port_info pi = ahci_port_info[id->driver_data];
+	struct ata_port_info pi = ahci_port_info[id ? id->driver_data : 0];
 	const struct ata_port_info *ppi[] = { &pi, NULL };
 	struct ahci_host_priv *hpriv;
 	struct ata_host *host;
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index 63d5327..4cadfa2 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -2533,10 +2533,12 @@ static int ata_pci_init_one(struct pci_dev *pdev,
 	if (rc)
 		goto out;
 
+#ifdef CONFIG_ATA_BMDMA
 	if (bmdma)
 		/* prepare and activate BMDMA host */
 		rc = ata_pci_bmdma_prepare_host(pdev, ppi, &host);
 	else
+#endif
 		/* prepare and activate SFF host */
 		rc = ata_pci_sff_prepare_host(pdev, ppi, &host);
 	if (rc)
@@ -2544,10 +2546,12 @@ static int ata_pci_init_one(struct pci_dev *pdev,
 	host->private_data = host_priv;
 	host->flags |= hflags;
 
+#ifdef CONFIG_ATA_BMDMA
 	if (bmdma) {
 		pci_set_master(pdev);
 		rc = ata_pci_sff_activate_host(host, ata_bmdma_interrupt, sht);
 	} else
+#endif
 		rc = ata_pci_sff_activate_host(host, ata_sff_interrupt, sht);
 out:
 	if (rc == 0)
diff --git a/drivers/atm/iphase.c b/drivers/atm/iphase.c
index 3d0c2b0..9e373ba 100644
--- a/drivers/atm/iphase.c
+++ b/drivers/atm/iphase.c
@@ -1320,8 +1320,8 @@ static void rx_dle_intr(struct atm_dev *dev)
           if (ia_vcc == NULL)
           {
              atomic_inc(&vcc->stats->rx_err);
+             atm_return(vcc, skb->truesize);
              dev_kfree_skb_any(skb);
-             atm_return(vcc, atm_guess_pdu2truesize(len));
              goto INCR_DLE;
            }
           // get real pkt length  pwang_test
@@ -1334,8 +1334,8 @@ static void rx_dle_intr(struct atm_dev *dev)
              atomic_inc(&vcc->stats->rx_err);
              IF_ERR(printk("rx_dle_intr: Bad  AAL5 trailer %d (skb len %d)", 
                                                             length, skb->len);)
+             atm_return(vcc, skb->truesize);
              dev_kfree_skb_any(skb);
-             atm_return(vcc, atm_guess_pdu2truesize(len));
              goto INCR_DLE;
           }
           skb_trim(skb, length);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 82c8654..d8b3d89 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -22,6 +22,7 @@
 #include <linux/kallsyms.h>
 #include <linux/mutex.h>
 #include <linux/async.h>
+#include <linux/pm_runtime.h>
 
 #include "base.h"
 #include "power/power.h"
@@ -1742,6 +1743,8 @@ void device_shutdown(void)
 		 */
 		list_del_init(&dev->kobj.entry);
 		spin_unlock(&devices_kset->list_lock);
+		/* Disable all device's runtime power management */
+		pm_runtime_disable(dev);
 
 		if (dev->bus && dev->bus->shutdown) {
 			dev_dbg(dev, "shutdown\n");
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 793f796..5693ece 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -127,12 +127,13 @@ static ssize_t node_read_meminfo(struct sys_device * dev,
 		       nid, K(node_page_state(nid, NR_WRITEBACK)),
 		       nid, K(node_page_state(nid, NR_FILE_PAGES)),
 		       nid, K(node_page_state(nid, NR_FILE_MAPPED)),
-		       nid, K(node_page_state(nid, NR_ANON_PAGES)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		       nid, K(node_page_state(nid, NR_ANON_PAGES)
 			+ node_page_state(nid, NR_ANON_TRANSPARENT_HUGEPAGES) *
-			HPAGE_PMD_NR
+			HPAGE_PMD_NR),
+#else
+		       nid, K(node_page_state(nid, NR_ANON_PAGES)),
 #endif
-		       ),
 		       nid, K(node_page_state(nid, NR_SHMEM)),
 		       nid, node_page_state(nid, NR_KERNEL_STACK) *
 				THREAD_SIZE / 1024,
@@ -143,13 +144,14 @@ static ssize_t node_read_meminfo(struct sys_device * dev,
 		       nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE) +
 				node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
 		       nid, K(node_page_state(nid, NR_SLAB_RECLAIMABLE)),
-		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE))
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE))
 			, nid,
 			K(node_page_state(nid, NR_ANON_TRANSPARENT_HUGEPAGES) *
-			HPAGE_PMD_NR)
+			HPAGE_PMD_NR));
+#else
+		       nid, K(node_page_state(nid, NR_SLAB_UNRECLAIMABLE)));
 #endif
-		       );
 	n += hugetlb_report_node_meminfo(nid, buf + n);
 	return n;
 }
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index 5f0f85d..428e55e 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -229,7 +229,8 @@ int pm_clk_suspend(struct device *dev)
 
 	list_for_each_entry_reverse(ce, &psd->clock_list, node) {
 		if (ce->status < PCE_STATUS_ERROR) {
-			clk_disable(ce->clk);
+			if (ce->status == PCE_STATUS_ENABLED)
+				clk_disable(ce->clk);
 			ce->status = PCE_STATUS_ACQUIRED;
 		}
 	}
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 7fa0984..c3d2dfc 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -920,7 +920,8 @@ static int __device_suspend(struct device *dev, pm_message_t state, bool async)
  End:
 	if (!error) {
 		dev->power.is_suspended = true;
-		if (dev->power.wakeup_path && dev->parent)
+		if (dev->power.wakeup_path
+		    && dev->parent && !dev->parent->power.ignore_children)
 			dev->parent->power.wakeup_path = true;
 	}
 
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 30a94ea..86de6c5 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -212,11 +212,9 @@ int dev_pm_qos_add_request(struct device *dev, struct dev_pm_qos_request *req,
 	if (!dev || !req) /*guard against callers passing in null */
 		return -EINVAL;
 
-	if (dev_pm_qos_request_active(req)) {
-		WARN(1, KERN_ERR "dev_pm_qos_add_request() called for already "
-			"added request\n");
+	if (WARN(dev_pm_qos_request_active(req),
+		 "%s() called for already added request\n", __func__))
 		return -EINVAL;
-	}
 
 	req->dev = dev;
 
@@ -271,11 +269,9 @@ int dev_pm_qos_update_request(struct dev_pm_qos_request *req,
 	if (!req) /*guard against callers passing in null */
 		return -EINVAL;
 
-	if (!dev_pm_qos_request_active(req)) {
-		WARN(1, KERN_ERR "dev_pm_qos_update_request() called for "
-			"unknown object\n");
+	if (WARN(!dev_pm_qos_request_active(req),
+		 "%s() called for unknown object\n", __func__))
 		return -EINVAL;
-	}
 
 	mutex_lock(&dev_pm_qos_mtx);
 
@@ -312,11 +308,9 @@ int dev_pm_qos_remove_request(struct dev_pm_qos_request *req)
 	if (!req) /*guard against callers passing in null */
 		return -EINVAL;
 
-	if (!dev_pm_qos_request_active(req)) {
-		WARN(1, KERN_ERR "dev_pm_qos_remove_request() called for "
-			"unknown object\n");
+	if (WARN(!dev_pm_qos_request_active(req),
+		 "%s() called for unknown object\n", __func__))
 		return -EINVAL;
-	}
 
 	mutex_lock(&dev_pm_qos_mtx);
 
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 486f94e..8004ac3 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -24,6 +24,7 @@
 #include <linux/interrupt.h>
 #include <linux/types.h>
 #include <linux/pci.h>
+#include <linux/pci-aspm.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
@@ -4319,6 +4320,10 @@ static int __devinit cciss_pci_init(ctlr_info_t *h)
 		dev_warn(&h->pdev->dev, "controller appears to be disabled\n");
 		return -ENODEV;
 	}
+
+	pci_disable_link_state(h->pdev, PCIE_LINK_STATE_L0S |
+				PCIE_LINK_STATE_L1 | PCIE_LINK_STATE_CLKPM);
+
 	err = pci_enable_device(h->pdev);
 	if (err) {
 		dev_warn(&h->pdev->dev, "Unable to Enable PCI device\n");
@@ -5158,6 +5163,7 @@ reinit_after_soft_reset:
 	h->cciss_max_sectors = 8192;
 
 	rebuild_lun_table(h, 1, 0);
+	cciss_engage_scsi(h);
 	h->busy_initializing = 0;
 	return 1;
 
diff --git a/drivers/block/cciss_scsi.c b/drivers/block/cciss_scsi.c
index 951a4e3..e820b68 100644
--- a/drivers/block/cciss_scsi.c
+++ b/drivers/block/cciss_scsi.c
@@ -1720,5 +1720,6 @@ static int  cciss_eh_abort_handler(struct scsi_cmnd *scsicmd)
 /* If no tape support, then these become defined out of existence */
 
 #define cciss_scsi_setup(cntl_num)
+#define cciss_engage_scsi(h)
 
 #endif /* CONFIG_CISS_SCSI_TAPE */
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 3d80682..68b205a 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -161,17 +161,19 @@ static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = {
 	&xor_funcs
 };
 
-static loff_t get_loop_size(struct loop_device *lo, struct file *file)
+static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file)
 {
-	loff_t size, offset, loopsize;
+	loff_t size, loopsize;
 
 	/* Compute loopsize in bytes */
 	size = i_size_read(file->f_mapping->host);
-	offset = lo->lo_offset;
 	loopsize = size - offset;
-	if (lo->lo_sizelimit > 0 && lo->lo_sizelimit < loopsize)
-		loopsize = lo->lo_sizelimit;
+	/* offset is beyond i_size, wierd but possible */
+	if (loopsize < 0)
+		return 0;
 
+	if (sizelimit > 0 && sizelimit < loopsize)
+		loopsize = sizelimit;
 	/*
 	 * Unfortunately, if we want to do I/O on the device,
 	 * the number of 512-byte sectors has to fit into a sector_t.
@@ -179,17 +181,25 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file)
 	return loopsize >> 9;
 }
 
+static loff_t get_loop_size(struct loop_device *lo, struct file *file)
+{
+	return get_size(lo->lo_offset, lo->lo_sizelimit, file);
+}
+
 static int
-figure_loop_size(struct loop_device *lo)
+figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
 {
-	loff_t size = get_loop_size(lo, lo->lo_backing_file);
+	loff_t size = get_size(offset, sizelimit, lo->lo_backing_file);
 	sector_t x = (sector_t)size;
 
 	if (unlikely((loff_t)x != size))
 		return -EFBIG;
-
+	if (lo->lo_offset != offset)
+		lo->lo_offset = offset;
+	if (lo->lo_sizelimit != sizelimit)
+		lo->lo_sizelimit = sizelimit;
 	set_capacity(lo->lo_disk, x);
-	return 0;					
+	return 0;
 }
 
 static inline int
@@ -372,7 +382,8 @@ do_lo_receive(struct loop_device *lo,
 
 	if (retval < 0)
 		return retval;
-
+	if (retval != bvec->bv_len)
+		return -EIO;
 	return 0;
 }
 
@@ -1058,9 +1069,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
 
 	if (lo->lo_offset != info->lo_offset ||
 	    lo->lo_sizelimit != info->lo_sizelimit) {
-		lo->lo_offset = info->lo_offset;
-		lo->lo_sizelimit = info->lo_sizelimit;
-		if (figure_loop_size(lo))
+		if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit))
 			return -EFBIG;
 	}
 	loop_config_discard(lo);
@@ -1246,7 +1255,7 @@ static int loop_set_capacity(struct loop_device *lo, struct block_device *bdev)
 	err = -ENXIO;
 	if (unlikely(lo->lo_state != Lo_bound))
 		goto out;
-	err = figure_loop_size(lo);
+	err = figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit);
 	if (unlikely(err))
 		goto out;
 	sec = get_capacity(lo->lo_disk);
@@ -1284,13 +1293,19 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
 			goto out_unlocked;
 		break;
 	case LOOP_SET_STATUS:
-		err = loop_set_status_old(lo, (struct loop_info __user *) arg);
+		err = -EPERM;
+		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
+			err = loop_set_status_old(lo,
+					(struct loop_info __user *)arg);
 		break;
 	case LOOP_GET_STATUS:
 		err = loop_get_status_old(lo, (struct loop_info __user *) arg);
 		break;
 	case LOOP_SET_STATUS64:
-		err = loop_set_status64(lo, (struct loop_info64 __user *) arg);
+		err = -EPERM;
+		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
+			err = loop_set_status64(lo,
+					(struct loop_info64 __user *) arg);
 		break;
 	case LOOP_GET_STATUS64:
 		err = loop_get_status64(lo, (struct loop_info64 __user *) arg);
diff --git a/drivers/block/paride/pg.c b/drivers/block/paride/pg.c
index 6b9a200..a79fb4f 100644
--- a/drivers/block/paride/pg.c
+++ b/drivers/block/paride/pg.c
@@ -630,6 +630,7 @@ static ssize_t pg_read(struct file *filp, char __user *buf, size_t count, loff_t
 		if (dev->status & 0x10)
 			return -ETIME;
 
+	memset(&hdr, 0, sizeof(hdr));
 	hdr.magic = PG_MAGIC;
 	hdr.dlen = dev->dlen;
 	copy = 0;
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 63e19ba..6035ab8 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -941,7 +941,7 @@ void get_random_bytes(void *buf, int nbytes)
 		if (!arch_get_random_long(&v))
 			break;
 		
-		memcpy(buf, &v, chunk);
+		memcpy(p, &v, chunk);
 		p += chunk;
 		nbytes -= chunk;
 	}
diff --git a/drivers/crypto/mv_cesa.c b/drivers/crypto/mv_cesa.c
index 5c6f56f..dcd8bab 100644
--- a/drivers/crypto/mv_cesa.c
+++ b/drivers/crypto/mv_cesa.c
@@ -343,11 +343,13 @@ static void mv_process_hash_current(int first_block)
 		else
 			op.config |= CFG_MID_FRAG;
 
-		writel(req_ctx->state[0], cpg->reg + DIGEST_INITIAL_VAL_A);
-		writel(req_ctx->state[1], cpg->reg + DIGEST_INITIAL_VAL_B);
-		writel(req_ctx->state[2], cpg->reg + DIGEST_INITIAL_VAL_C);
-		writel(req_ctx->state[3], cpg->reg + DIGEST_INITIAL_VAL_D);
-		writel(req_ctx->state[4], cpg->reg + DIGEST_INITIAL_VAL_E);
+		if (first_block) {
+			writel(req_ctx->state[0], cpg->reg + DIGEST_INITIAL_VAL_A);
+			writel(req_ctx->state[1], cpg->reg + DIGEST_INITIAL_VAL_B);
+			writel(req_ctx->state[2], cpg->reg + DIGEST_INITIAL_VAL_C);
+			writel(req_ctx->state[3], cpg->reg + DIGEST_INITIAL_VAL_D);
+			writel(req_ctx->state[4], cpg->reg + DIGEST_INITIAL_VAL_E);
+		}
 	}
 
 	memcpy(cpg->sram + SRAM_CONFIG, &op, sizeof(struct sec_accel_config));
diff --git a/drivers/devfreq/Kconfig b/drivers/devfreq/Kconfig
index 643b055..8f04910 100644
--- a/drivers/devfreq/Kconfig
+++ b/drivers/devfreq/Kconfig
@@ -1,36 +1,29 @@
-config ARCH_HAS_DEVFREQ
-	bool
-	depends on ARCH_HAS_OPP
-	help
-	  Denotes that the architecture supports DEVFREQ. If the architecture
-	  supports multiple OPP entries per device and the frequency of the
-	  devices with OPPs may be altered dynamically, the architecture
-	  supports DEVFREQ.
-
 menuconfig PM_DEVFREQ
 	bool "Generic Dynamic Voltage and Frequency Scaling (DVFS) support"
-	depends on PM_OPP && ARCH_HAS_DEVFREQ
 	help
-	  With OPP support, a device may have a list of frequencies and
-	  voltages available. DEVFREQ, a generic DVFS framework can be
-	  registered for a device with OPP support in order to let the
-	  governor provided to DEVFREQ choose an operating frequency
-	  based on the OPP's list and the policy given with DEVFREQ.
+	  A device may have a list of frequencies and voltages available.
+	  devfreq, a generic DVFS framework can be registered for a device
+	  in order to let the governor provided to devfreq choose an
+	  operating frequency based on the device driver's policy.
 
-	  Each device may have its own governor and policy. DEVFREQ can
+	  Each device may have its own governor and policy. Devfreq can
 	  reevaluate the device state periodically and/or based on the
-	  OPP list changes (each frequency/voltage pair in OPP may be
-	  disabled or enabled).
+	  notification to "nb", a notifier block, of devfreq.
 
-	  Like some CPUs with CPUFREQ, a device may have multiple clocks.
+	  Like some CPUs with CPUfreq, a device may have multiple clocks.
 	  However, because the clock frequencies of a single device are
-	  determined by the single device's state, an instance of DEVFREQ
+	  determined by the single device's state, an instance of devfreq
 	  is attached to a single device and returns a "representative"
-	  clock frequency from the OPP of the device, which is also attached
-	  to a device by 1-to-1. The device registering DEVFREQ takes the
-	  responsiblity to "interpret" the frequency listed in OPP and
+	  clock frequency of the device, which is also attached
+	  to a device by 1-to-1. The device registering devfreq takes the
+	  responsiblity to "interpret" the representative frequency and
 	  to set its every clock accordingly with the "target" callback
-	  given to DEVFREQ.
+	  given to devfreq.
+
+	  When OPP is used with the devfreq device, it is recommended to
+	  register devfreq's nb to the OPP's notifier head.  If OPP is
+	  used with the devfreq device, you may use OPP helper
+	  functions defined in devfreq.h.
 
 if PM_DEVFREQ
 
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 5d15b81..59d24e9 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -15,7 +15,9 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/init.h>
+#include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/stat.h>
 #include <linux/opp.h>
 #include <linux/devfreq.h>
 #include <linux/workqueue.h>
@@ -416,10 +418,14 @@ out:
  */
 int devfreq_remove_device(struct devfreq *devfreq)
 {
+	bool central_polling;
+
 	if (!devfreq)
 		return -EINVAL;
 
-	if (!devfreq->governor->no_central_polling) {
+	central_polling = !devfreq->governor->no_central_polling;
+
+	if (central_polling) {
 		mutex_lock(&devfreq_list_lock);
 		while (wait_remove_device == devfreq) {
 			mutex_unlock(&devfreq_list_lock);
@@ -431,7 +437,7 @@ int devfreq_remove_device(struct devfreq *devfreq)
 	mutex_lock(&devfreq->lock);
 	_remove_devfreq(devfreq, false); /* it unlocks devfreq->lock */
 
-	if (!devfreq->governor->no_central_polling)
+	if (central_polling)
 		mutex_unlock(&devfreq_list_lock);
 
 	return 0;
diff --git a/drivers/edac/mpc85xx_edac.c b/drivers/edac/mpc85xx_edac.c
index 8af8e86..73464a6 100644
--- a/drivers/edac/mpc85xx_edac.c
+++ b/drivers/edac/mpc85xx_edac.c
@@ -1128,7 +1128,7 @@ static struct of_device_id mpc85xx_mc_err_of_match[] = {
 	{ .compatible = "fsl,p1020-memory-controller", },
 	{ .compatible = "fsl,p1021-memory-controller", },
 	{ .compatible = "fsl,p2020-memory-controller", },
-	{ .compatible = "fsl,p4080-memory-controller", },
+	{ .compatible = "fsl,qoriq-memory-controller", },
 	{},
 };
 MODULE_DEVICE_TABLE(of, mpc85xx_mc_err_of_match);
diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c
index bcb1126..153980b 100644
--- a/drivers/firmware/dmi_scan.c
+++ b/drivers/firmware/dmi_scan.c
@@ -585,14 +585,12 @@ int dmi_name_in_serial(const char *str)
 }
 
 /**
- *	dmi_name_in_vendors - Check if string is anywhere in the DMI vendor information.
+ *	dmi_name_in_vendors - Check if string is in the DMI system or board vendor name
  *	@str: 	Case sensitive Name
  */
 int dmi_name_in_vendors(const char *str)
 {
-	static int fields[] = { DMI_BIOS_VENDOR, DMI_BIOS_VERSION, DMI_SYS_VENDOR,
-				DMI_PRODUCT_NAME, DMI_PRODUCT_VERSION, DMI_BOARD_VENDOR,
-				DMI_BOARD_NAME, DMI_BOARD_VERSION, DMI_NONE };
+	static int fields[] = { DMI_SYS_VENDOR, DMI_BOARD_VENDOR, DMI_NONE };
 	int i;
 	for (i = 0; fields[i] != DMI_NONE; i++) {
 		int f = fields[i];
diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c
index 8370f72..b0a8117 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -457,7 +457,8 @@ static int efi_pstore_close(struct pstore_info *psi)
 }
 
 static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
-			       struct timespec *timespec, struct pstore_info *psi)
+			       struct timespec *timespec,
+			       char **buf, struct pstore_info *psi)
 {
 	efi_guid_t vendor = LINUX_EFI_CRASH_GUID;
 	struct efivars *efivars = psi->data;
@@ -478,7 +479,11 @@ static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
 				timespec->tv_nsec = 0;
 				get_var_data_locked(efivars, &efivars->walk_entry->var);
 				size = efivars->walk_entry->var.DataSize;
-				memcpy(psi->buf, efivars->walk_entry->var.Data, size);
+				*buf = kmalloc(size, GFP_KERNEL);
+				if (*buf == NULL)
+					return -ENOMEM;
+				memcpy(*buf, efivars->walk_entry->var.Data,
+				       size);
 				efivars->walk_entry = list_entry(efivars->walk_entry->list.next,
 					           struct efivar_entry, list);
 				return size;
@@ -576,7 +581,8 @@ static int efi_pstore_close(struct pstore_info *psi)
 }
 
 static ssize_t efi_pstore_read(u64 *id, enum pstore_type_id *type,
-			       struct timespec *time, struct pstore_info *psi)
+			       struct timespec *timespec,
+			       char **buf, struct pstore_info *psi)
 {
 	return -1;
 }
diff --git a/drivers/firmware/sigma.c b/drivers/firmware/sigma.c
index f10fc52..1eedb6f 100644
--- a/drivers/firmware/sigma.c
+++ b/drivers/firmware/sigma.c
@@ -14,13 +14,34 @@
 #include <linux/module.h>
 #include <linux/sigma.h>
 
-/* Return: 0==OK, <0==error, =1 ==no more actions */
+static size_t sigma_action_size(struct sigma_action *sa)
+{
+	size_t payload = 0;
+
+	switch (sa->instr) {
+	case SIGMA_ACTION_WRITEXBYTES:
+	case SIGMA_ACTION_WRITESINGLE:
+	case SIGMA_ACTION_WRITESAFELOAD:
+		payload = sigma_action_len(sa);
+		break;
+	default:
+		break;
+	}
+
+	payload = ALIGN(payload, 2);
+
+	return payload + sizeof(struct sigma_action);
+}
+
+/*
+ * Returns a negative error value in case of an error, 0 if processing of
+ * the firmware should be stopped after this action, 1 otherwise.
+ */
 static int
-process_sigma_action(struct i2c_client *client, struct sigma_firmware *ssfw)
+process_sigma_action(struct i2c_client *client, struct sigma_action *sa)
 {
-	struct sigma_action *sa = (void *)(ssfw->fw->data + ssfw->pos);
 	size_t len = sigma_action_len(sa);
-	int ret = 0;
+	int ret;
 
 	pr_debug("%s: instr:%i addr:%#x len:%zu\n", __func__,
 		sa->instr, sa->addr, len);
@@ -29,44 +50,50 @@ process_sigma_action(struct i2c_client *client, struct sigma_firmware *ssfw)
 	case SIGMA_ACTION_WRITEXBYTES:
 	case SIGMA_ACTION_WRITESINGLE:
 	case SIGMA_ACTION_WRITESAFELOAD:
-		if (ssfw->fw->size < ssfw->pos + len)
-			return -EINVAL;
 		ret = i2c_master_send(client, (void *)&sa->addr, len);
 		if (ret < 0)
 			return -EINVAL;
 		break;
-
 	case SIGMA_ACTION_DELAY:
-		ret = 0;
 		udelay(len);
 		len = 0;
 		break;
-
 	case SIGMA_ACTION_END:
-		return 1;
-
+		return 0;
 	default:
 		return -EINVAL;
 	}
 
-	/* when arrive here ret=0 or sent data */
-	ssfw->pos += sigma_action_size(sa, len);
-	return ssfw->pos == ssfw->fw->size;
+	return 1;
 }
 
 static int
 process_sigma_actions(struct i2c_client *client, struct sigma_firmware *ssfw)
 {
-	pr_debug("%s: processing %p\n", __func__, ssfw);
+	struct sigma_action *sa;
+	size_t size;
+	int ret;
+
+	while (ssfw->pos + sizeof(*sa) <= ssfw->fw->size) {
+		sa = (struct sigma_action *)(ssfw->fw->data + ssfw->pos);
+
+		size = sigma_action_size(sa);
+		ssfw->pos += size;
+		if (ssfw->pos > ssfw->fw->size || size == 0)
+			break;
+
+		ret = process_sigma_action(client, sa);
 
-	while (1) {
-		int ret = process_sigma_action(client, ssfw);
 		pr_debug("%s: action returned %i\n", __func__, ret);
-		if (ret == 1)
-			return 0;
-		else if (ret)
+
+		if (ret <= 0)
 			return ret;
 	}
+
+	if (ssfw->pos != ssfw->fw->size)
+		return -EINVAL;
+
+	return 0;
 }
 
 int process_sigma_firmware(struct i2c_client *client, const char *name)
@@ -89,16 +116,24 @@ int process_sigma_firmware(struct i2c_client *client, const char *name)
 
 	/* then verify the header */
 	ret = -EINVAL;
-	if (fw->size < sizeof(*ssfw_head))
+
+	/*
+	 * Reject too small or unreasonable large files. The upper limit has been
+	 * chosen a bit arbitrarily, but it should be enough for all practical
+	 * purposes and having the limit makes it easier to avoid integer
+	 * overflows later in the loading process.
+	 */
+	if (fw->size < sizeof(*ssfw_head) || fw->size >= 0x4000000)
 		goto done;
 
 	ssfw_head = (void *)fw->data;
 	if (memcmp(ssfw_head->magic, SIGMA_MAGIC, ARRAY_SIZE(ssfw_head->magic)))
 		goto done;
 
-	crc = crc32(0, fw->data, fw->size);
+	crc = crc32(0, fw->data + sizeof(*ssfw_head),
+			fw->size - sizeof(*ssfw_head));
 	pr_debug("%s: crc=%x\n", __func__, crc);
-	if (crc != ssfw_head->crc)
+	if (crc != le32_to_cpu(ssfw_head->crc))
 		goto done;
 
 	ssfw.pos = sizeof(*ssfw_head);
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index dbcb0bc..4e018d6 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -18,7 +18,7 @@ obj-$(CONFIG_ARCH_DAVINCI)	+= gpio-davinci.o
 obj-$(CONFIG_GPIO_EP93XX)	+= gpio-ep93xx.o
 obj-$(CONFIG_GPIO_IT8761E)	+= gpio-it8761e.o
 obj-$(CONFIG_GPIO_JANZ_TTL)	+= gpio-janz-ttl.o
-obj-$(CONFIG_MACH_KS8695)	+= gpio-ks8695.o
+obj-$(CONFIG_ARCH_KS8695)	+= gpio-ks8695.o
 obj-$(CONFIG_GPIO_LANGWELL)	+= gpio-langwell.o
 obj-$(CONFIG_ARCH_LPC32XX)	+= gpio-lpc32xx.o
 obj-$(CONFIG_GPIO_MAX730X)	+= gpio-max730x.o
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 147df8a..d3f3e8f 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -546,7 +546,7 @@ static void pca953x_irq_teardown(struct pca953x_chip *chip)
  * Translate OpenFirmware node properties into platform_data
  * WARNING: This is DEPRECATED and will be removed eventually!
  */
-void
+static void
 pca953x_get_alt_pdata(struct i2c_client *client, int *gpio_base, int *invert)
 {
 	struct device_node *node;
@@ -574,7 +574,7 @@ pca953x_get_alt_pdata(struct i2c_client *client, int *gpio_base, int *invert)
 		*invert = *val;
 }
 #else
-void
+static void
 pca953x_get_alt_pdata(struct i2c_client *client, int *gpio_base, int *invert)
 {
 	*gpio_base = -1;
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 405c63b..8323fc3 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -1873,6 +1873,10 @@ int drm_mode_dirtyfb_ioctl(struct drm_device *dev,
 	}
 
 	if (num_clips && clips_ptr) {
+		if (num_clips < 0 || num_clips > DRM_MODE_FB_DIRTY_MAX_CLIPS) {
+			ret = -EINVAL;
+			goto out_err1;
+		}
 		clips = kzalloc(num_clips * sizeof(*clips), GFP_KERNEL);
 		if (!clips) {
 			ret = -ENOMEM;
diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index 3969f75..d2619d7 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -456,6 +456,30 @@ done:
 EXPORT_SYMBOL(drm_crtc_helper_set_mode);
 
 
+static int
+drm_crtc_helper_disable(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct drm_connector *connector;
+	struct drm_encoder *encoder;
+
+	/* Decouple all encoders and their attached connectors from this crtc */
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		if (encoder->crtc != crtc)
+			continue;
+
+		list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
+			if (connector->encoder != encoder)
+				continue;
+
+			connector->encoder = NULL;
+		}
+	}
+
+	drm_helper_disable_unused_functions(dev);
+	return 0;
+}
+
 /**
  * drm_crtc_helper_set_config - set a new config from userspace
  * @crtc: CRTC to setup
@@ -510,8 +534,7 @@ int drm_crtc_helper_set_config(struct drm_mode_set *set)
 				(int)set->num_connectors, set->x, set->y);
 	} else {
 		DRM_DEBUG_KMS("[CRTC:%d] [NOFB]\n", set->crtc->base.id);
-		set->mode = NULL;
-		set->num_connectors = 0;
+		return drm_crtc_helper_disable(set->crtc);
 	}
 
 	dev = set->crtc->dev;
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 68b7562..44a5d0a 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -110,10 +110,7 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	/* Prevent vblank irq processing while disabling vblank irqs,
 	 * so no updates of timestamps or count can happen after we've
 	 * disabled. Needed to prevent races in case of delayed irq's.
-	 * Disable preemption, so vblank_time_lock is held as short as
-	 * possible, even under a kernel with PREEMPT_RT patches.
 	 */
-	preempt_disable();
 	spin_lock_irqsave(&dev->vblank_time_lock, irqflags);
 
 	dev->driver->disable_vblank(dev, crtc);
@@ -164,7 +161,6 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	clear_vblank_timestamps(dev, crtc);
 
 	spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags);
-	preempt_enable();
 }
 
 static void vblank_disable_fn(unsigned long arg)
@@ -889,10 +885,6 @@ int drm_vblank_get(struct drm_device *dev, int crtc)
 	spin_lock_irqsave(&dev->vbl_lock, irqflags);
 	/* Going from 0->1 means we have to enable interrupts again */
 	if (atomic_add_return(1, &dev->vblank_refcount[crtc]) == 1) {
-		/* Disable preemption while holding vblank_time_lock. Do
-		 * it explicitely to guard against PREEMPT_RT kernel.
-		 */
-		preempt_disable();
 		spin_lock_irqsave(&dev->vblank_time_lock, irqflags2);
 		if (!dev->vblank_enabled[crtc]) {
 			/* Enable vblank irqs under vblank_time_lock protection.
@@ -912,7 +904,6 @@ int drm_vblank_get(struct drm_device *dev, int crtc)
 			}
 		}
 		spin_unlock_irqrestore(&dev->vblank_time_lock, irqflags2);
-		preempt_enable();
 	} else {
 		if (!dev->vblank_enabled[crtc]) {
 			atomic_dec(&dev->vblank_refcount[crtc]);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_buf.c b/drivers/gpu/drm/exynos/exynos_drm_buf.c
index 6f8afea..2bb07bc 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_buf.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_buf.c
@@ -27,82 +27,84 @@
 #include "drm.h"
 
 #include "exynos_drm_drv.h"
+#include "exynos_drm_gem.h"
 #include "exynos_drm_buf.h"
 
-static DEFINE_MUTEX(exynos_drm_buf_lock);
-
 static int lowlevel_buffer_allocate(struct drm_device *dev,
-		struct exynos_drm_buf_entry *entry)
+		struct exynos_drm_gem_buf *buffer)
 {
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
-	entry->vaddr = dma_alloc_writecombine(dev->dev, entry->size,
-			(dma_addr_t *)&entry->paddr, GFP_KERNEL);
-	if (!entry->paddr) {
+	buffer->kvaddr = dma_alloc_writecombine(dev->dev, buffer->size,
+			&buffer->dma_addr, GFP_KERNEL);
+	if (!buffer->kvaddr) {
 		DRM_ERROR("failed to allocate buffer.\n");
 		return -ENOMEM;
 	}
 
-	DRM_DEBUG_KMS("allocated : vaddr(0x%x), paddr(0x%x), size(0x%x)\n",
-			(unsigned int)entry->vaddr, entry->paddr, entry->size);
+	DRM_DEBUG_KMS("vaddr(0x%lx), dma_addr(0x%lx), size(0x%lx)\n",
+			(unsigned long)buffer->kvaddr,
+			(unsigned long)buffer->dma_addr,
+			buffer->size);
 
 	return 0;
 }
 
 static void lowlevel_buffer_deallocate(struct drm_device *dev,
-		struct exynos_drm_buf_entry *entry)
+		struct exynos_drm_gem_buf *buffer)
 {
 	DRM_DEBUG_KMS("%s.\n", __FILE__);
 
-	if (entry->paddr && entry->vaddr && entry->size)
-		dma_free_writecombine(dev->dev, entry->size, entry->vaddr,
-				entry->paddr);
+	if (buffer->dma_addr && buffer->size)
+		dma_free_writecombine(dev->dev, buffer->size, buffer->kvaddr,
+				(dma_addr_t)buffer->dma_addr);
 	else
-		DRM_DEBUG_KMS("entry data is null.\n");
+		DRM_DEBUG_KMS("buffer data are invalid.\n");
 }
 
-struct exynos_drm_buf_entry *exynos_drm_buf_create(struct drm_device *dev,
+struct exynos_drm_gem_buf *exynos_drm_buf_create(struct drm_device *dev,
 		unsigned int size)
 {
-	struct exynos_drm_buf_entry *entry;
+	struct exynos_drm_gem_buf *buffer;
 
 	DRM_DEBUG_KMS("%s.\n", __FILE__);
+	DRM_DEBUG_KMS("desired size = 0x%x\n", size);
 
-	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
-	if (!entry) {
-		DRM_ERROR("failed to allocate exynos_drm_buf_entry.\n");
+	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
+	if (!buffer) {
+		DRM_ERROR("failed to allocate exynos_drm_gem_buf.\n");
 		return ERR_PTR(-ENOMEM);
 	}
 
-	entry->size = size;
+	buffer->size = size;
 
 	/*
 	 * allocate memory region with size and set the memory information
-	 * to vaddr and paddr of a entry object.
+	 * to vaddr and dma_addr of a buffer object.
 	 */
-	if (lowlevel_buffer_allocate(dev, entry) < 0) {
-		kfree(entry);
-		entry = NULL;
+	if (lowlevel_buffer_allocate(dev, buffer) < 0) {
+		kfree(buffer);
+		buffer = NULL;
 		return ERR_PTR(-ENOMEM);
 	}
 
-	return entry;
+	return buffer;
 }
 
 void exynos_drm_buf_destroy(struct drm_device *dev,
-		struct exynos_drm_buf_entry *entry)
+		struct exynos_drm_gem_buf *buffer)
 {
 	DRM_DEBUG_KMS("%s.\n", __FILE__);
 
-	if (!entry) {
-		DRM_DEBUG_KMS("entry is null.\n");
+	if (!buffer) {
+		DRM_DEBUG_KMS("buffer is null.\n");
 		return;
 	}
 
-	lowlevel_buffer_deallocate(dev, entry);
+	lowlevel_buffer_deallocate(dev, buffer);
 
-	kfree(entry);
-	entry = NULL;
+	kfree(buffer);
+	buffer = NULL;
 }
 
 MODULE_AUTHOR("Inki Dae <inki.dae@samsung.com>");
diff --git a/drivers/gpu/drm/exynos/exynos_drm_buf.h b/drivers/gpu/drm/exynos/exynos_drm_buf.h
index 045d59e..6e91f9c 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_buf.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_buf.h
@@ -26,28 +26,15 @@
 #ifndef _EXYNOS_DRM_BUF_H_
 #define _EXYNOS_DRM_BUF_H_
 
-/*
- * exynos drm buffer entry structure.
- *
- * @paddr: physical address of allocated memory.
- * @vaddr: kernel virtual address of allocated memory.
- * @size: size of allocated memory.
- */
-struct exynos_drm_buf_entry {
-	dma_addr_t paddr;
-	void __iomem *vaddr;
-	unsigned int size;
-};
-
 /* allocate physical memory. */
-struct exynos_drm_buf_entry *exynos_drm_buf_create(struct drm_device *dev,
+struct exynos_drm_gem_buf *exynos_drm_buf_create(struct drm_device *dev,
 		unsigned int size);
 
-/* get physical memory information of a drm framebuffer. */
-struct exynos_drm_buf_entry *exynos_drm_fb_get_buf(struct drm_framebuffer *fb);
+/* get memory information of a drm framebuffer. */
+struct exynos_drm_gem_buf *exynos_drm_fb_get_buf(struct drm_framebuffer *fb);
 
 /* remove allocated physical memory. */
 void exynos_drm_buf_destroy(struct drm_device *dev,
-		struct exynos_drm_buf_entry *entry);
+		struct exynos_drm_gem_buf *buffer);
 
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_connector.c b/drivers/gpu/drm/exynos/exynos_drm_connector.c
index 985d9e7..d620b07 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_connector.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_connector.c
@@ -37,6 +37,8 @@
 
 struct exynos_drm_connector {
 	struct drm_connector	drm_connector;
+	uint32_t		encoder_id;
+	struct exynos_drm_manager *manager;
 };
 
 /* convert exynos_video_timings to drm_display_mode */
@@ -47,6 +49,7 @@ convert_to_display_mode(struct drm_display_mode *mode,
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
 	mode->clock = timing->pixclock / 1000;
+	mode->vrefresh = timing->refresh;
 
 	mode->hdisplay = timing->xres;
 	mode->hsync_start = mode->hdisplay + timing->left_margin;
@@ -57,6 +60,12 @@ convert_to_display_mode(struct drm_display_mode *mode,
 	mode->vsync_start = mode->vdisplay + timing->upper_margin;
 	mode->vsync_end = mode->vsync_start + timing->vsync_len;
 	mode->vtotal = mode->vsync_end + timing->lower_margin;
+
+	if (timing->vmode & FB_VMODE_INTERLACED)
+		mode->flags |= DRM_MODE_FLAG_INTERLACE;
+
+	if (timing->vmode & FB_VMODE_DOUBLE)
+		mode->flags |= DRM_MODE_FLAG_DBLSCAN;
 }
 
 /* convert drm_display_mode to exynos_video_timings */
@@ -69,7 +78,7 @@ convert_to_video_timing(struct fb_videomode *timing,
 	memset(timing, 0, sizeof(*timing));
 
 	timing->pixclock = mode->clock * 1000;
-	timing->refresh = mode->vrefresh;
+	timing->refresh = drm_mode_vrefresh(mode);
 
 	timing->xres = mode->hdisplay;
 	timing->left_margin = mode->hsync_start - mode->hdisplay;
@@ -92,15 +101,16 @@ convert_to_video_timing(struct fb_videomode *timing,
 
 static int exynos_drm_connector_get_modes(struct drm_connector *connector)
 {
-	struct exynos_drm_manager *manager =
-				exynos_drm_get_manager(connector->encoder);
-	struct exynos_drm_display *display = manager->display;
+	struct exynos_drm_connector *exynos_connector =
+					to_exynos_connector(connector);
+	struct exynos_drm_manager *manager = exynos_connector->manager;
+	struct exynos_drm_display_ops *display_ops = manager->display_ops;
 	unsigned int count;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
-	if (!display) {
-		DRM_DEBUG_KMS("display is null.\n");
+	if (!display_ops) {
+		DRM_DEBUG_KMS("display_ops is null.\n");
 		return 0;
 	}
 
@@ -112,7 +122,7 @@ static int exynos_drm_connector_get_modes(struct drm_connector *connector)
 	 * P.S. in case of lcd panel, count is always 1 if success
 	 * because lcd panel has only one mode.
 	 */
-	if (display->get_edid) {
+	if (display_ops->get_edid) {
 		int ret;
 		void *edid;
 
@@ -122,7 +132,7 @@ static int exynos_drm_connector_get_modes(struct drm_connector *connector)
 			return 0;
 		}
 
-		ret = display->get_edid(manager->dev, connector,
+		ret = display_ops->get_edid(manager->dev, connector,
 						edid, MAX_EDID);
 		if (ret < 0) {
 			DRM_ERROR("failed to get edid data.\n");
@@ -140,8 +150,8 @@ static int exynos_drm_connector_get_modes(struct drm_connector *connector)
 		struct drm_display_mode *mode = drm_mode_create(connector->dev);
 		struct fb_videomode *timing;
 
-		if (display->get_timing)
-			timing = display->get_timing(manager->dev);
+		if (display_ops->get_timing)
+			timing = display_ops->get_timing(manager->dev);
 		else {
 			drm_mode_destroy(connector->dev, mode);
 			return 0;
@@ -162,9 +172,10 @@ static int exynos_drm_connector_get_modes(struct drm_connector *connector)
 static int exynos_drm_connector_mode_valid(struct drm_connector *connector,
 					    struct drm_display_mode *mode)
 {
-	struct exynos_drm_manager *manager =
-				exynos_drm_get_manager(connector->encoder);
-	struct exynos_drm_display *display = manager->display;
+	struct exynos_drm_connector *exynos_connector =
+					to_exynos_connector(connector);
+	struct exynos_drm_manager *manager = exynos_connector->manager;
+	struct exynos_drm_display_ops *display_ops = manager->display_ops;
 	struct fb_videomode timing;
 	int ret = MODE_BAD;
 
@@ -172,8 +183,8 @@ static int exynos_drm_connector_mode_valid(struct drm_connector *connector,
 
 	convert_to_video_timing(&timing, mode);
 
-	if (display && display->check_timing)
-		if (!display->check_timing(manager->dev, (void *)&timing))
+	if (display_ops && display_ops->check_timing)
+		if (!display_ops->check_timing(manager->dev, (void *)&timing))
 			ret = MODE_OK;
 
 	return ret;
@@ -181,9 +192,25 @@ static int exynos_drm_connector_mode_valid(struct drm_connector *connector,
 
 struct drm_encoder *exynos_drm_best_encoder(struct drm_connector *connector)
 {
+	struct drm_device *dev = connector->dev;
+	struct exynos_drm_connector *exynos_connector =
+					to_exynos_connector(connector);
+	struct drm_mode_object *obj;
+	struct drm_encoder *encoder;
+
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
-	return connector->encoder;
+	obj = drm_mode_object_find(dev, exynos_connector->encoder_id,
+				   DRM_MODE_OBJECT_ENCODER);
+	if (!obj) {
+		DRM_DEBUG_KMS("Unknown ENCODER ID %d\n",
+				exynos_connector->encoder_id);
+		return NULL;
+	}
+
+	encoder = obj_to_encoder(obj);
+
+	return encoder;
 }
 
 static struct drm_connector_helper_funcs exynos_connector_helper_funcs = {
@@ -196,15 +223,17 @@ static struct drm_connector_helper_funcs exynos_connector_helper_funcs = {
 static enum drm_connector_status
 exynos_drm_connector_detect(struct drm_connector *connector, bool force)
 {
-	struct exynos_drm_manager *manager =
-				exynos_drm_get_manager(connector->encoder);
-	struct exynos_drm_display *display = manager->display;
+	struct exynos_drm_connector *exynos_connector =
+					to_exynos_connector(connector);
+	struct exynos_drm_manager *manager = exynos_connector->manager;
+	struct exynos_drm_display_ops *display_ops =
+					manager->display_ops;
 	enum drm_connector_status status = connector_status_disconnected;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
-	if (display && display->is_connected) {
-		if (display->is_connected(manager->dev))
+	if (display_ops && display_ops->is_connected) {
+		if (display_ops->is_connected(manager->dev))
 			status = connector_status_connected;
 		else
 			status = connector_status_disconnected;
@@ -251,9 +280,11 @@ struct drm_connector *exynos_drm_connector_create(struct drm_device *dev,
 
 	connector = &exynos_connector->drm_connector;
 
-	switch (manager->display->type) {
+	switch (manager->display_ops->type) {
 	case EXYNOS_DISPLAY_TYPE_HDMI:
 		type = DRM_MODE_CONNECTOR_HDMIA;
+		connector->interlace_allowed = true;
+		connector->polled = DRM_CONNECTOR_POLL_HPD;
 		break;
 	default:
 		type = DRM_MODE_CONNECTOR_Unknown;
@@ -267,7 +298,10 @@ struct drm_connector *exynos_drm_connector_create(struct drm_device *dev,
 	if (err)
 		goto err_connector;
 
+	exynos_connector->encoder_id = encoder->base.id;
+	exynos_connector->manager = manager;
 	connector->encoder = encoder;
+
 	err = drm_mode_connector_attach_encoder(connector, encoder);
 	if (err) {
 		DRM_ERROR("failed to attach a connector to a encoder\n");
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index 9337e5e..ee43cc2 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -29,36 +29,17 @@
 #include "drmP.h"
 #include "drm_crtc_helper.h"
 
+#include "exynos_drm_crtc.h"
 #include "exynos_drm_drv.h"
 #include "exynos_drm_fb.h"
 #include "exynos_drm_encoder.h"
+#include "exynos_drm_gem.h"
 #include "exynos_drm_buf.h"
 
 #define to_exynos_crtc(x)	container_of(x, struct exynos_drm_crtc,\
 				drm_crtc)
 
 /*
- * Exynos specific crtc postion structure.
- *
- * @fb_x: offset x on a framebuffer to be displyed
- *	- the unit is screen coordinates.
- * @fb_y: offset y on a framebuffer to be displayed
- *	- the unit is screen coordinates.
- * @crtc_x: offset x on hardware screen.
- * @crtc_y: offset y on hardware screen.
- * @crtc_w: width of hardware screen.
- * @crtc_h: height of hardware screen.
- */
-struct exynos_drm_crtc_pos {
-	unsigned int fb_x;
-	unsigned int fb_y;
-	unsigned int crtc_x;
-	unsigned int crtc_y;
-	unsigned int crtc_w;
-	unsigned int crtc_h;
-};
-
-/*
  * Exynos specific crtc structure.
  *
  * @drm_crtc: crtc object.
@@ -85,30 +66,31 @@ static void exynos_drm_crtc_apply(struct drm_crtc *crtc)
 
 	exynos_drm_fn_encoder(crtc, overlay,
 			exynos_drm_encoder_crtc_mode_set);
-	exynos_drm_fn_encoder(crtc, NULL, exynos_drm_encoder_crtc_commit);
+	exynos_drm_fn_encoder(crtc, &exynos_crtc->pipe,
+			exynos_drm_encoder_crtc_commit);
 }
 
-static int exynos_drm_overlay_update(struct exynos_drm_overlay *overlay,
-				       struct drm_framebuffer *fb,
-				       struct drm_display_mode *mode,
-				       struct exynos_drm_crtc_pos *pos)
+int exynos_drm_overlay_update(struct exynos_drm_overlay *overlay,
+			      struct drm_framebuffer *fb,
+			      struct drm_display_mode *mode,
+			      struct exynos_drm_crtc_pos *pos)
 {
-	struct exynos_drm_buf_entry *entry;
+	struct exynos_drm_gem_buf *buffer;
 	unsigned int actual_w;
 	unsigned int actual_h;
 
-	entry = exynos_drm_fb_get_buf(fb);
-	if (!entry) {
-		DRM_LOG_KMS("entry is null.\n");
+	buffer = exynos_drm_fb_get_buf(fb);
+	if (!buffer) {
+		DRM_LOG_KMS("buffer is null.\n");
 		return -EFAULT;
 	}
 
-	overlay->paddr = entry->paddr;
-	overlay->vaddr = entry->vaddr;
+	overlay->dma_addr = buffer->dma_addr;
+	overlay->vaddr = buffer->kvaddr;
 
-	DRM_DEBUG_KMS("vaddr = 0x%lx, paddr = 0x%lx\n",
+	DRM_DEBUG_KMS("vaddr = 0x%lx, dma_addr = 0x%lx\n",
 			(unsigned long)overlay->vaddr,
-			(unsigned long)overlay->paddr);
+			(unsigned long)overlay->dma_addr);
 
 	actual_w = min((mode->hdisplay - pos->crtc_x), pos->crtc_w);
 	actual_h = min((mode->vdisplay - pos->crtc_y), pos->crtc_h);
@@ -171,9 +153,26 @@ static int exynos_drm_crtc_update(struct drm_crtc *crtc)
 
 static void exynos_drm_crtc_dpms(struct drm_crtc *crtc, int mode)
 {
-	DRM_DEBUG_KMS("%s\n", __FILE__);
+	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
 
-	/* TODO */
+	DRM_DEBUG_KMS("crtc[%d] mode[%d]\n", crtc->base.id, mode);
+
+	switch (mode) {
+	case DRM_MODE_DPMS_ON:
+		exynos_drm_fn_encoder(crtc, &exynos_crtc->pipe,
+				exynos_drm_encoder_crtc_commit);
+		break;
+	case DRM_MODE_DPMS_STANDBY:
+	case DRM_MODE_DPMS_SUSPEND:
+	case DRM_MODE_DPMS_OFF:
+		/* TODO */
+		exynos_drm_fn_encoder(crtc, NULL,
+				exynos_drm_encoder_crtc_disable);
+		break;
+	default:
+		DRM_DEBUG_KMS("unspecified mode %d\n", mode);
+		break;
+	}
 }
 
 static void exynos_drm_crtc_prepare(struct drm_crtc *crtc)
@@ -185,9 +184,12 @@ static void exynos_drm_crtc_prepare(struct drm_crtc *crtc)
 
 static void exynos_drm_crtc_commit(struct drm_crtc *crtc)
 {
+	struct exynos_drm_crtc *exynos_crtc = to_exynos_crtc(crtc);
+
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
-	/* drm framework doesn't check NULL. */
+	exynos_drm_fn_encoder(crtc, &exynos_crtc->pipe,
+			exynos_drm_encoder_crtc_commit);
 }
 
 static bool
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.h b/drivers/gpu/drm/exynos/exynos_drm_crtc.h
index c584042..25f72a6 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.h
@@ -35,4 +35,29 @@ int exynos_drm_crtc_create(struct drm_device *dev, unsigned int nr);
 int exynos_drm_crtc_enable_vblank(struct drm_device *dev, int crtc);
 void exynos_drm_crtc_disable_vblank(struct drm_device *dev, int crtc);
 
+/*
+ * Exynos specific crtc postion structure.
+ *
+ * @fb_x: offset x on a framebuffer to be displyed
+ *	- the unit is screen coordinates.
+ * @fb_y: offset y on a framebuffer to be displayed
+ *	- the unit is screen coordinates.
+ * @crtc_x: offset x on hardware screen.
+ * @crtc_y: offset y on hardware screen.
+ * @crtc_w: width of hardware screen.
+ * @crtc_h: height of hardware screen.
+ */
+struct exynos_drm_crtc_pos {
+	unsigned int fb_x;
+	unsigned int fb_y;
+	unsigned int crtc_x;
+	unsigned int crtc_y;
+	unsigned int crtc_w;
+	unsigned int crtc_h;
+};
+
+int exynos_drm_overlay_update(struct exynos_drm_overlay *overlay,
+			      struct drm_framebuffer *fb,
+			      struct drm_display_mode *mode,
+			      struct exynos_drm_crtc_pos *pos);
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 83810cb..53e2216 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -27,6 +27,7 @@
 
 #include "drmP.h"
 #include "drm.h"
+#include "drm_crtc_helper.h"
 
 #include <drm/exynos_drm.h>
 
@@ -61,6 +62,9 @@ static int exynos_drm_load(struct drm_device *dev, unsigned long flags)
 
 	drm_mode_config_init(dev);
 
+	/* init kms poll for handling hpd */
+	drm_kms_helper_poll_init(dev);
+
 	exynos_drm_mode_config_init(dev);
 
 	/*
@@ -116,6 +120,7 @@ static int exynos_drm_unload(struct drm_device *dev)
 	exynos_drm_fbdev_fini(dev);
 	exynos_drm_device_unregister(dev);
 	drm_vblank_cleanup(dev);
+	drm_kms_helper_poll_fini(dev);
 	drm_mode_config_cleanup(dev);
 	kfree(dev->dev_private);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index c03683f..5e02e6e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -29,6 +29,7 @@
 #ifndef _EXYNOS_DRM_DRV_H_
 #define _EXYNOS_DRM_DRV_H_
 
+#include <linux/module.h>
 #include "drm.h"
 
 #define MAX_CRTC	2
@@ -79,8 +80,8 @@ struct exynos_drm_overlay_ops {
  * @scan_flag: interlace or progressive way.
  *	(it could be DRM_MODE_FLAG_*)
  * @bpp: pixel size.(in bit)
- * @paddr: bus(accessed by dma) physical memory address to this overlay
- *		and this is physically continuous.
+ * @dma_addr: bus(accessed by dma) address to the memory region allocated
+ *	for a overlay.
  * @vaddr: virtual memory addresss to this overlay.
  * @default_win: a window to be enabled.
  * @color_key: color key on or off.
@@ -108,7 +109,7 @@ struct exynos_drm_overlay {
 	unsigned int scan_flag;
 	unsigned int bpp;
 	unsigned int pitch;
-	dma_addr_t paddr;
+	dma_addr_t dma_addr;
 	void __iomem *vaddr;
 
 	bool default_win;
@@ -130,7 +131,7 @@ struct exynos_drm_overlay {
  * @check_timing: check if timing is valid or not.
  * @power_on: display device on or off.
  */
-struct exynos_drm_display {
+struct exynos_drm_display_ops {
 	enum exynos_drm_output_type type;
 	bool (*is_connected)(struct device *dev);
 	int (*get_edid)(struct device *dev, struct drm_connector *connector,
@@ -146,12 +147,14 @@ struct exynos_drm_display {
  * @mode_set: convert drm_display_mode to hw specific display mode and
  *	      would be called by encoder->mode_set().
  * @commit: set current hw specific display mode to hw.
+ * @disable: disable hardware specific display mode.
  * @enable_vblank: specific driver callback for enabling vblank interrupt.
  * @disable_vblank: specific driver callback for disabling vblank interrupt.
  */
 struct exynos_drm_manager_ops {
 	void (*mode_set)(struct device *subdrv_dev, void *mode);
 	void (*commit)(struct device *subdrv_dev);
+	void (*disable)(struct device *subdrv_dev);
 	int (*enable_vblank)(struct device *subdrv_dev);
 	void (*disable_vblank)(struct device *subdrv_dev);
 };
@@ -178,7 +181,7 @@ struct exynos_drm_manager {
 	int pipe;
 	struct exynos_drm_manager_ops *ops;
 	struct exynos_drm_overlay_ops *overlay_ops;
-	struct exynos_drm_display *display;
+	struct exynos_drm_display_ops *display_ops;
 };
 
 /*
diff --git a/drivers/gpu/drm/exynos/exynos_drm_encoder.c b/drivers/gpu/drm/exynos/exynos_drm_encoder.c
index 7cf6fa8..1530614 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_encoder.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_encoder.c
@@ -53,15 +53,36 @@ static void exynos_drm_encoder_dpms(struct drm_encoder *encoder, int mode)
 	struct drm_device *dev = encoder->dev;
 	struct drm_connector *connector;
 	struct exynos_drm_manager *manager = exynos_drm_get_manager(encoder);
+	struct exynos_drm_manager_ops *manager_ops = manager->ops;
 
 	DRM_DEBUG_KMS("%s, encoder dpms: %d\n", __FILE__, mode);
 
+	switch (mode) {
+	case DRM_MODE_DPMS_ON:
+		if (manager_ops && manager_ops->commit)
+			manager_ops->commit(manager->dev);
+		break;
+	case DRM_MODE_DPMS_STANDBY:
+	case DRM_MODE_DPMS_SUSPEND:
+	case DRM_MODE_DPMS_OFF:
+		/* TODO */
+		if (manager_ops && manager_ops->disable)
+			manager_ops->disable(manager->dev);
+		break;
+	default:
+		DRM_ERROR("unspecified mode %d\n", mode);
+		break;
+	}
+
 	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
 		if (connector->encoder == encoder) {
-			struct exynos_drm_display *display = manager->display;
+			struct exynos_drm_display_ops *display_ops =
+							manager->display_ops;
 
-			if (display && display->power_on)
-				display->power_on(manager->dev, mode);
+			DRM_DEBUG_KMS("connector[%d] dpms[%d]\n",
+					connector->base.id, mode);
+			if (display_ops && display_ops->power_on)
+				display_ops->power_on(manager->dev, mode);
 		}
 	}
 }
@@ -116,15 +137,11 @@ static void exynos_drm_encoder_commit(struct drm_encoder *encoder)
 {
 	struct exynos_drm_manager *manager = exynos_drm_get_manager(encoder);
 	struct exynos_drm_manager_ops *manager_ops = manager->ops;
-	struct exynos_drm_overlay_ops *overlay_ops = manager->overlay_ops;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
 	if (manager_ops && manager_ops->commit)
 		manager_ops->commit(manager->dev);
-
-	if (overlay_ops && overlay_ops->commit)
-		overlay_ops->commit(manager->dev);
 }
 
 static struct drm_crtc *
@@ -208,10 +225,23 @@ void exynos_drm_fn_encoder(struct drm_crtc *crtc, void *data,
 {
 	struct drm_device *dev = crtc->dev;
 	struct drm_encoder *encoder;
+	struct exynos_drm_private *private = dev->dev_private;
+	struct exynos_drm_manager *manager;
 
 	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
-		if (encoder->crtc != crtc)
-			continue;
+		/*
+		 * if crtc is detached from encoder, check pipe,
+		 * otherwise check crtc attached to encoder
+		 */
+		if (!encoder->crtc) {
+			manager = to_exynos_encoder(encoder)->manager;
+			if (manager->pipe < 0 ||
+					private->crtc[manager->pipe] != crtc)
+				continue;
+		} else {
+			if (encoder->crtc != crtc)
+				continue;
+		}
 
 		fn(encoder, data);
 	}
@@ -250,8 +280,18 @@ void exynos_drm_encoder_crtc_commit(struct drm_encoder *encoder, void *data)
 	struct exynos_drm_manager *manager =
 		to_exynos_encoder(encoder)->manager;
 	struct exynos_drm_overlay_ops *overlay_ops = manager->overlay_ops;
+	int crtc = *(int *)data;
+
+	DRM_DEBUG_KMS("%s\n", __FILE__);
+
+	/*
+	 * when crtc is detached from encoder, this pipe is used
+	 * to select manager operation
+	 */
+	manager->pipe = crtc;
 
-	overlay_ops->commit(manager->dev);
+	if (overlay_ops && overlay_ops->commit)
+		overlay_ops->commit(manager->dev);
 }
 
 void exynos_drm_encoder_crtc_mode_set(struct drm_encoder *encoder, void *data)
@@ -261,7 +301,28 @@ void exynos_drm_encoder_crtc_mode_set(struct drm_encoder *encoder, void *data)
 	struct exynos_drm_overlay_ops *overlay_ops = manager->overlay_ops;
 	struct exynos_drm_overlay *overlay = data;
 
-	overlay_ops->mode_set(manager->dev, overlay);
+	if (overlay_ops && overlay_ops->mode_set)
+		overlay_ops->mode_set(manager->dev, overlay);
+}
+
+void exynos_drm_encoder_crtc_disable(struct drm_encoder *encoder, void *data)
+{
+	struct exynos_drm_manager *manager =
+		to_exynos_encoder(encoder)->manager;
+	struct exynos_drm_overlay_ops *overlay_ops = manager->overlay_ops;
+
+	DRM_DEBUG_KMS("\n");
+
+	if (overlay_ops && overlay_ops->disable)
+		overlay_ops->disable(manager->dev);
+
+	/*
+	 * crtc is already detached from encoder and last
+	 * function for detaching is properly done, so
+	 * clear pipe from manager to prevent repeated call
+	 */
+	if (!encoder->crtc)
+		manager->pipe = -1;
 }
 
 MODULE_AUTHOR("Inki Dae <inki.dae@samsung.com>");
diff --git a/drivers/gpu/drm/exynos/exynos_drm_encoder.h b/drivers/gpu/drm/exynos/exynos_drm_encoder.h
index 5ecd645..a22acfb 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_encoder.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_encoder.h
@@ -41,5 +41,6 @@ void exynos_drm_enable_vblank(struct drm_encoder *encoder, void *data);
 void exynos_drm_disable_vblank(struct drm_encoder *encoder, void *data);
 void exynos_drm_encoder_crtc_commit(struct drm_encoder *encoder, void *data);
 void exynos_drm_encoder_crtc_mode_set(struct drm_encoder *encoder, void *data);
+void exynos_drm_encoder_crtc_disable(struct drm_encoder *encoder, void *data);
 
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index 48d29cf..5bf4a1a 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -29,7 +29,9 @@
 #include "drmP.h"
 #include "drm_crtc.h"
 #include "drm_crtc_helper.h"
+#include "drm_fb_helper.h"
 
+#include "exynos_drm_drv.h"
 #include "exynos_drm_fb.h"
 #include "exynos_drm_buf.h"
 #include "exynos_drm_gem.h"
@@ -41,14 +43,14 @@
  *
  * @fb: drm framebuffer obejct.
  * @exynos_gem_obj: exynos specific gem object containing a gem object.
- * @entry: pointer to exynos drm buffer entry object.
- *	- containing only the information to physically continuous memory
- *	region allocated at default framebuffer creation.
+ * @buffer: pointer to exynos_drm_gem_buffer object.
+ *	- contain the memory information to memory region allocated
+ *	at default framebuffer creation.
  */
 struct exynos_drm_fb {
 	struct drm_framebuffer		fb;
 	struct exynos_drm_gem_obj	*exynos_gem_obj;
-	struct exynos_drm_buf_entry	*entry;
+	struct exynos_drm_gem_buf	*buffer;
 };
 
 static void exynos_drm_fb_destroy(struct drm_framebuffer *fb)
@@ -63,8 +65,8 @@ static void exynos_drm_fb_destroy(struct drm_framebuffer *fb)
 	 * default framebuffer has no gem object so
 	 * a buffer of the default framebuffer should be released at here.
 	 */
-	if (!exynos_fb->exynos_gem_obj && exynos_fb->entry)
-		exynos_drm_buf_destroy(fb->dev, exynos_fb->entry);
+	if (!exynos_fb->exynos_gem_obj && exynos_fb->buffer)
+		exynos_drm_buf_destroy(fb->dev, exynos_fb->buffer);
 
 	kfree(exynos_fb);
 	exynos_fb = NULL;
@@ -143,29 +145,29 @@ exynos_drm_fb_init(struct drm_file *file_priv, struct drm_device *dev,
 	 */
 	if (!mode_cmd->handle) {
 		if (!file_priv) {
-			struct exynos_drm_buf_entry *entry;
+			struct exynos_drm_gem_buf *buffer;
 
 			/*
 			 * in case that file_priv is NULL, it allocates
 			 * only buffer and this buffer would be used
 			 * for default framebuffer.
 			 */
-			entry = exynos_drm_buf_create(dev, size);
-			if (IS_ERR(entry)) {
-				ret = PTR_ERR(entry);
+			buffer = exynos_drm_buf_create(dev, size);
+			if (IS_ERR(buffer)) {
+				ret = PTR_ERR(buffer);
 				goto err_buffer;
 			}
 
-			exynos_fb->entry = entry;
+			exynos_fb->buffer = buffer;
 
-			DRM_LOG_KMS("default fb: paddr = 0x%lx, size = 0x%x\n",
-					(unsigned long)entry->paddr, size);
+			DRM_LOG_KMS("default: dma_addr = 0x%lx, size = 0x%x\n",
+					(unsigned long)buffer->dma_addr, size);
 
 			goto out;
 		} else {
-			exynos_gem_obj = exynos_drm_gem_create(file_priv, dev,
-							size,
-							&mode_cmd->handle);
+			exynos_gem_obj = exynos_drm_gem_create(dev, file_priv,
+							&mode_cmd->handle,
+							size);
 			if (IS_ERR(exynos_gem_obj)) {
 				ret = PTR_ERR(exynos_gem_obj);
 				goto err_buffer;
@@ -189,10 +191,10 @@ exynos_drm_fb_init(struct drm_file *file_priv, struct drm_device *dev,
 	 * so that default framebuffer has no its own gem object,
 	 * only its own buffer object.
 	 */
-	exynos_fb->entry = exynos_gem_obj->entry;
+	exynos_fb->buffer = exynos_gem_obj->buffer;
 
-	DRM_LOG_KMS("paddr = 0x%lx, size = 0x%x, gem object = 0x%x\n",
-			(unsigned long)exynos_fb->entry->paddr, size,
+	DRM_LOG_KMS("dma_addr = 0x%lx, size = 0x%x, gem object = 0x%x\n",
+			(unsigned long)exynos_fb->buffer->dma_addr, size,
 			(unsigned int)&exynos_gem_obj->base);
 
 out:
@@ -220,26 +222,36 @@ struct drm_framebuffer *exynos_drm_fb_create(struct drm_device *dev,
 	return exynos_drm_fb_init(file_priv, dev, mode_cmd);
 }
 
-struct exynos_drm_buf_entry *exynos_drm_fb_get_buf(struct drm_framebuffer *fb)
+struct exynos_drm_gem_buf *exynos_drm_fb_get_buf(struct drm_framebuffer *fb)
 {
 	struct exynos_drm_fb *exynos_fb = to_exynos_fb(fb);
-	struct exynos_drm_buf_entry *entry;
+	struct exynos_drm_gem_buf *buffer;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
 
-	entry = exynos_fb->entry;
-	if (!entry)
+	buffer = exynos_fb->buffer;
+	if (!buffer)
 		return NULL;
 
-	DRM_DEBUG_KMS("vaddr = 0x%lx, paddr = 0x%lx\n",
-			(unsigned long)entry->vaddr,
-			(unsigned long)entry->paddr);
+	DRM_DEBUG_KMS("vaddr = 0x%lx, dma_addr = 0x%lx\n",
+			(unsigned long)buffer->kvaddr,
+			(unsigned long)buffer->dma_addr);
 
-	return entry;
+	return buffer;
+}
+
+static void exynos_drm_output_poll_changed(struct drm_device *dev)
+{
+	struct exynos_drm_private *private = dev->dev_private;
+	struct drm_fb_helper *fb_helper = private->fb_helper;
+
+	if (fb_helper)
+		drm_fb_helper_hotplug_event(fb_helper);
 }
 
 static struct drm_mode_config_funcs exynos_drm_mode_config_funcs = {
 	.fb_create = exynos_drm_fb_create,
+	.output_poll_changed = exynos_drm_output_poll_changed,
 };
 
 void exynos_drm_mode_config_init(struct drm_device *dev)
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
index 1f4b3d1..836f4100 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c
@@ -33,6 +33,7 @@
 
 #include "exynos_drm_drv.h"
 #include "exynos_drm_fb.h"
+#include "exynos_drm_gem.h"
 #include "exynos_drm_buf.h"
 
 #define MAX_CONNECTOR		4
@@ -85,15 +86,13 @@ static struct fb_ops exynos_drm_fb_ops = {
 };
 
 static int exynos_drm_fbdev_update(struct drm_fb_helper *helper,
-				     struct drm_framebuffer *fb,
-				     unsigned int fb_width,
-				     unsigned int fb_height)
+				     struct drm_framebuffer *fb)
 {
 	struct fb_info *fbi = helper->fbdev;
 	struct drm_device *dev = helper->dev;
 	struct exynos_drm_fbdev *exynos_fb = to_exynos_fbdev(helper);
-	struct exynos_drm_buf_entry *entry;
-	unsigned int size = fb_width * fb_height * (fb->bits_per_pixel >> 3);
+	struct exynos_drm_gem_buf *buffer;
+	unsigned int size = fb->width * fb->height * (fb->bits_per_pixel >> 3);
 	unsigned long offset;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
@@ -101,20 +100,20 @@ static int exynos_drm_fbdev_update(struct drm_fb_helper *helper,
 	exynos_fb->fb = fb;
 
 	drm_fb_helper_fill_fix(fbi, fb->pitch, fb->depth);
-	drm_fb_helper_fill_var(fbi, helper, fb_width, fb_height);
+	drm_fb_helper_fill_var(fbi, helper, fb->width, fb->height);
 
-	entry = exynos_drm_fb_get_buf(fb);
-	if (!entry) {
-		DRM_LOG_KMS("entry is null.\n");
+	buffer = exynos_drm_fb_get_buf(fb);
+	if (!buffer) {
+		DRM_LOG_KMS("buffer is null.\n");
 		return -EFAULT;
 	}
 
 	offset = fbi->var.xoffset * (fb->bits_per_pixel >> 3);
 	offset += fbi->var.yoffset * fb->pitch;
 
-	dev->mode_config.fb_base = entry->paddr;
-	fbi->screen_base = entry->vaddr + offset;
-	fbi->fix.smem_start = entry->paddr + offset;
+	dev->mode_config.fb_base = (resource_size_t)buffer->dma_addr;
+	fbi->screen_base = buffer->kvaddr + offset;
+	fbi->fix.smem_start = (unsigned long)(buffer->dma_addr + offset);
 	fbi->screen_size = size;
 	fbi->fix.smem_len = size;
 
@@ -171,8 +170,7 @@ static int exynos_drm_fbdev_create(struct drm_fb_helper *helper,
 		goto out;
 	}
 
-	ret = exynos_drm_fbdev_update(helper, helper->fb, sizes->fb_width,
-			sizes->fb_height);
+	ret = exynos_drm_fbdev_update(helper, helper->fb);
 	if (ret < 0)
 		fb_dealloc_cmap(&fbi->cmap);
 
@@ -235,8 +233,7 @@ static int exynos_drm_fbdev_recreate(struct drm_fb_helper *helper,
 	}
 
 	helper->fb = exynos_fbdev->fb;
-	return exynos_drm_fbdev_update(helper, helper->fb, sizes->fb_width,
-			sizes->fb_height);
+	return exynos_drm_fbdev_update(helper, helper->fb);
 }
 
 static int exynos_drm_fbdev_probe(struct drm_fb_helper *helper,
@@ -405,6 +402,18 @@ int exynos_drm_fbdev_reinit(struct drm_device *dev)
 	fb_helper = private->fb_helper;
 
 	if (fb_helper) {
+		struct list_head temp_list;
+
+		INIT_LIST_HEAD(&temp_list);
+
+		/*
+		 * fb_helper is reintialized but kernel fb is reused
+		 * so kernel_fb_list need to be backuped and restored
+		 */
+		if (!list_empty(&fb_helper->kernel_fb_list))
+			list_replace_init(&fb_helper->kernel_fb_list,
+					&temp_list);
+
 		drm_fb_helper_fini(fb_helper);
 
 		ret = drm_fb_helper_init(dev, fb_helper,
@@ -414,6 +423,9 @@ int exynos_drm_fbdev_reinit(struct drm_device *dev)
 			return ret;
 		}
 
+		if (!list_empty(&temp_list))
+			list_replace(&temp_list, &fb_helper->kernel_fb_list);
+
 		ret = drm_fb_helper_single_add_all_connectors(fb_helper);
 		if (ret < 0) {
 			DRM_ERROR("failed to add fb helper to connectors\n");
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 4659c88..db3b3d9 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -64,7 +64,7 @@ struct fimd_win_data {
 	unsigned int		fb_width;
 	unsigned int		fb_height;
 	unsigned int		bpp;
-	dma_addr_t		paddr;
+	dma_addr_t		dma_addr;
 	void __iomem		*vaddr;
 	unsigned int		buf_offsize;
 	unsigned int		line_size;	/* bytes */
@@ -124,7 +124,7 @@ static int fimd_display_power_on(struct device *dev, int mode)
 	return 0;
 }
 
-static struct exynos_drm_display fimd_display = {
+static struct exynos_drm_display_ops fimd_display_ops = {
 	.type = EXYNOS_DISPLAY_TYPE_LCD,
 	.is_connected = fimd_display_is_connected,
 	.get_timing = fimd_get_timing,
@@ -177,6 +177,40 @@ static void fimd_commit(struct device *dev)
 	writel(val, ctx->regs + VIDCON0);
 }
 
+static void fimd_disable(struct device *dev)
+{
+	struct fimd_context *ctx = get_fimd_context(dev);
+	struct exynos_drm_subdrv *subdrv = &ctx->subdrv;
+	struct drm_device *drm_dev = subdrv->drm_dev;
+	struct exynos_drm_manager *manager = &subdrv->manager;
+	u32 val;
+
+	DRM_DEBUG_KMS("%s\n", __FILE__);
+
+	/* fimd dma off */
+	val = readl(ctx->regs + VIDCON0);
+	val &= ~(VIDCON0_ENVID | VIDCON0_ENVID_F);
+	writel(val, ctx->regs + VIDCON0);
+
+	/*
+	 * if vblank is enabled status with dma off then
+	 * it disables vsync interrupt.
+	 */
+	if (drm_dev->vblank_enabled[manager->pipe] &&
+		atomic_read(&drm_dev->vblank_refcount[manager->pipe])) {
+		drm_vblank_put(drm_dev, manager->pipe);
+
+		/*
+		 * if vblank_disable_allowed is 0 then disable
+		 * vsync interrupt right now else the vsync interrupt
+		 * would be disabled by drm timer once a current process
+		 * gives up ownershop of vblank event.
+		 */
+		if (!drm_dev->vblank_disable_allowed)
+			drm_vblank_off(drm_dev, manager->pipe);
+	}
+}
+
 static int fimd_enable_vblank(struct device *dev)
 {
 	struct fimd_context *ctx = get_fimd_context(dev);
@@ -220,6 +254,7 @@ static void fimd_disable_vblank(struct device *dev)
 
 static struct exynos_drm_manager_ops fimd_manager_ops = {
 	.commit = fimd_commit,
+	.disable = fimd_disable,
 	.enable_vblank = fimd_enable_vblank,
 	.disable_vblank = fimd_disable_vblank,
 };
@@ -251,7 +286,7 @@ static void fimd_win_mode_set(struct device *dev,
 	win_data->ovl_height = overlay->crtc_height;
 	win_data->fb_width = overlay->fb_width;
 	win_data->fb_height = overlay->fb_height;
-	win_data->paddr = overlay->paddr + offset;
+	win_data->dma_addr = overlay->dma_addr + offset;
 	win_data->vaddr = overlay->vaddr + offset;
 	win_data->bpp = overlay->bpp;
 	win_data->buf_offsize = (overlay->fb_width - overlay->crtc_width) *
@@ -263,7 +298,7 @@ static void fimd_win_mode_set(struct device *dev,
 	DRM_DEBUG_KMS("ovl_width = %d, ovl_height = %d\n",
 			win_data->ovl_width, win_data->ovl_height);
 	DRM_DEBUG_KMS("paddr = 0x%lx, vaddr = 0x%lx\n",
-			(unsigned long)win_data->paddr,
+			(unsigned long)win_data->dma_addr,
 			(unsigned long)win_data->vaddr);
 	DRM_DEBUG_KMS("fb_width = %d, crtc_width = %d\n",
 			overlay->fb_width, overlay->crtc_width);
@@ -376,16 +411,16 @@ static void fimd_win_commit(struct device *dev)
 	writel(val, ctx->regs + SHADOWCON);
 
 	/* buffer start address */
-	val = win_data->paddr;
+	val = (unsigned long)win_data->dma_addr;
 	writel(val, ctx->regs + VIDWx_BUF_START(win, 0));
 
 	/* buffer end address */
 	size = win_data->fb_width * win_data->ovl_height * (win_data->bpp >> 3);
-	val = win_data->paddr + size;
+	val = (unsigned long)(win_data->dma_addr + size);
 	writel(val, ctx->regs + VIDWx_BUF_END(win, 0));
 
 	DRM_DEBUG_KMS("start addr = 0x%lx, end addr = 0x%lx, size = 0x%lx\n",
-			(unsigned long)win_data->paddr, val, size);
+			(unsigned long)win_data->dma_addr, val, size);
 	DRM_DEBUG_KMS("ovl_width = %d, ovl_height = %d\n",
 			win_data->ovl_width, win_data->ovl_height);
 
@@ -447,7 +482,6 @@ static void fimd_win_commit(struct device *dev)
 static void fimd_win_disable(struct device *dev)
 {
 	struct fimd_context *ctx = get_fimd_context(dev);
-	struct fimd_win_data *win_data;
 	int win = ctx->default_win;
 	u32 val;
 
@@ -456,8 +490,6 @@ static void fimd_win_disable(struct device *dev)
 	if (win < 0 || win > WINDOWS_NR)
 		return;
 
-	win_data = &ctx->win_data[win];
-
 	/* protect windows */
 	val = readl(ctx->regs + SHADOWCON);
 	val |= SHADOWCON_WINx_PROTECT(win);
@@ -528,6 +560,16 @@ static irqreturn_t fimd_irq_handler(int irq, void *dev_id)
 		/* VSYNC interrupt */
 		writel(VIDINTCON1_INT_FRAME, ctx->regs + VIDINTCON1);
 
+	/*
+	 * in case that vblank_disable_allowed is 1, it could induce
+	 * the problem that manager->pipe could be -1 because with
+	 * disable callback, vsync interrupt isn't disabled and at this moment,
+	 * vsync interrupt could occur. the vsync interrupt would be disabled
+	 * by timer handler later.
+	 */
+	if (manager->pipe == -1)
+		return IRQ_HANDLED;
+
 	drm_handle_vblank(drm_dev, manager->pipe);
 	fimd_finish_pageflip(drm_dev, manager->pipe);
 
@@ -548,13 +590,6 @@ static int fimd_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
 	 */
 	drm_dev->irq_enabled = 1;
 
-	/*
-	 * with vblank_disable_allowed = 1, vblank interrupt will be disabled
-	 * by drm timer once a current process gives up ownership of
-	 * vblank event.(drm_vblank_put function was called)
-	 */
-	drm_dev->vblank_disable_allowed = 1;
-
 	return 0;
 }
 
@@ -731,7 +766,7 @@ static int __devinit fimd_probe(struct platform_device *pdev)
 	subdrv->manager.pipe = -1;
 	subdrv->manager.ops = &fimd_manager_ops;
 	subdrv->manager.overlay_ops = &fimd_overlay_ops;
-	subdrv->manager.display = &fimd_display;
+	subdrv->manager.display_ops = &fimd_display_ops;
 	subdrv->manager.dev = dev;
 
 	platform_set_drvdata(pdev, ctx);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index a8e7a88..aba0fe4 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -62,40 +62,28 @@ static unsigned int get_gem_mmap_offset(struct drm_gem_object *obj)
 	return (unsigned int)obj->map_list.hash.key << PAGE_SHIFT;
 }
 
-struct exynos_drm_gem_obj *exynos_drm_gem_create(struct drm_file *file_priv,
-		struct drm_device *dev, unsigned int size,
-		unsigned int *handle)
+static struct exynos_drm_gem_obj
+		*exynos_drm_gem_init(struct drm_device *drm_dev,
+			struct drm_file *file_priv, unsigned int *handle,
+			unsigned int size)
 {
 	struct exynos_drm_gem_obj *exynos_gem_obj;
-	struct exynos_drm_buf_entry *entry;
 	struct drm_gem_object *obj;
 	int ret;
 
-	DRM_DEBUG_KMS("%s\n", __FILE__);
-
-	size = roundup(size, PAGE_SIZE);
-
 	exynos_gem_obj = kzalloc(sizeof(*exynos_gem_obj), GFP_KERNEL);
 	if (!exynos_gem_obj) {
 		DRM_ERROR("failed to allocate exynos gem object.\n");
 		return ERR_PTR(-ENOMEM);
 	}
 
-	/* allocate the new buffer object and memory region. */
-	entry = exynos_drm_buf_create(dev, size);
-	if (!entry) {
-		kfree(exynos_gem_obj);
-		return ERR_PTR(-ENOMEM);
-	}
-
-	exynos_gem_obj->entry = entry;
-
 	obj = &exynos_gem_obj->base;
 
-	ret = drm_gem_object_init(dev, obj, size);
+	ret = drm_gem_object_init(drm_dev, obj, size);
 	if (ret < 0) {
-		DRM_ERROR("failed to initailize gem object.\n");
-		goto err_obj_init;
+		DRM_ERROR("failed to initialize gem object.\n");
+		ret = -EINVAL;
+		goto err_object_init;
 	}
 
 	DRM_DEBUG_KMS("created file object = 0x%x\n", (unsigned int)obj->filp);
@@ -127,24 +115,50 @@ err_handle_create:
 err_create_mmap_offset:
 	drm_gem_object_release(obj);
 
-err_obj_init:
-	exynos_drm_buf_destroy(dev, exynos_gem_obj->entry);
-
+err_object_init:
 	kfree(exynos_gem_obj);
 
 	return ERR_PTR(ret);
 }
 
+struct exynos_drm_gem_obj *exynos_drm_gem_create(struct drm_device *dev,
+				struct drm_file *file_priv,
+				unsigned int *handle, unsigned long size)
+{
+
+	struct exynos_drm_gem_obj *exynos_gem_obj = NULL;
+	struct exynos_drm_gem_buf *buffer;
+
+	size = roundup(size, PAGE_SIZE);
+
+	DRM_DEBUG_KMS("%s: size = 0x%lx\n", __FILE__, size);
+
+	buffer = exynos_drm_buf_create(dev, size);
+	if (IS_ERR(buffer)) {
+		return ERR_CAST(buffer);
+	}
+
+	exynos_gem_obj = exynos_drm_gem_init(dev, file_priv, handle, size);
+	if (IS_ERR(exynos_gem_obj)) {
+		exynos_drm_buf_destroy(dev, buffer);
+		return exynos_gem_obj;
+	}
+
+	exynos_gem_obj->buffer = buffer;
+
+	return exynos_gem_obj;
+}
+
 int exynos_drm_gem_create_ioctl(struct drm_device *dev, void *data,
-		struct drm_file *file_priv)
+					struct drm_file *file_priv)
 {
 	struct drm_exynos_gem_create *args = data;
-	struct exynos_drm_gem_obj *exynos_gem_obj;
+	struct exynos_drm_gem_obj *exynos_gem_obj = NULL;
 
-	DRM_DEBUG_KMS("%s : size = 0x%x\n", __FILE__, args->size);
+	DRM_DEBUG_KMS("%s\n", __FILE__);
 
-	exynos_gem_obj = exynos_drm_gem_create(file_priv, dev, args->size,
-			&args->handle);
+	exynos_gem_obj = exynos_drm_gem_create(dev, file_priv,
+						&args->handle, args->size);
 	if (IS_ERR(exynos_gem_obj))
 		return PTR_ERR(exynos_gem_obj);
 
@@ -175,7 +189,7 @@ static int exynos_drm_gem_mmap_buffer(struct file *filp,
 {
 	struct drm_gem_object *obj = filp->private_data;
 	struct exynos_drm_gem_obj *exynos_gem_obj = to_exynos_gem_obj(obj);
-	struct exynos_drm_buf_entry *entry;
+	struct exynos_drm_gem_buf *buffer;
 	unsigned long pfn, vm_size;
 
 	DRM_DEBUG_KMS("%s\n", __FILE__);
@@ -187,20 +201,20 @@ static int exynos_drm_gem_mmap_buffer(struct file *filp,
 
 	vm_size = vma->vm_end - vma->vm_start;
 	/*
-	 * a entry contains information to physically continuous memory
+	 * a buffer contains information to physically continuous memory
 	 * allocated by user request or at framebuffer creation.
 	 */
-	entry = exynos_gem_obj->entry;
+	buffer = exynos_gem_obj->buffer;
 
 	/* check if user-requested size is valid. */
-	if (vm_size > entry->size)
+	if (vm_size > buffer->size)
 		return -EINVAL;
 
 	/*
 	 * get page frame number to physical memory to be mapped
 	 * to user space.
 	 */
-	pfn = exynos_gem_obj->entry->paddr >> PAGE_SHIFT;
+	pfn = ((unsigned long)exynos_gem_obj->buffer->dma_addr) >> PAGE_SHIFT;
 
 	DRM_DEBUG_KMS("pfn = 0x%lx\n", pfn);
 
@@ -281,7 +295,7 @@ void exynos_drm_gem_free_object(struct drm_gem_object *gem_obj)
 
 	exynos_gem_obj = to_exynos_gem_obj(gem_obj);
 
-	exynos_drm_buf_destroy(gem_obj->dev, exynos_gem_obj->entry);
+	exynos_drm_buf_destroy(gem_obj->dev, exynos_gem_obj->buffer);
 
 	kfree(exynos_gem_obj);
 }
@@ -302,8 +316,8 @@ int exynos_drm_gem_dumb_create(struct drm_file *file_priv,
 	args->pitch = args->width * args->bpp >> 3;
 	args->size = args->pitch * args->height;
 
-	exynos_gem_obj = exynos_drm_gem_create(file_priv, dev, args->size,
-							&args->handle);
+	exynos_gem_obj = exynos_drm_gem_create(dev, file_priv, &args->handle,
+							args->size);
 	if (IS_ERR(exynos_gem_obj))
 		return PTR_ERR(exynos_gem_obj);
 
@@ -360,7 +374,8 @@ int exynos_drm_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	mutex_lock(&dev->struct_mutex);
 
-	pfn = (exynos_gem_obj->entry->paddr >> PAGE_SHIFT) + page_offset;
+	pfn = (((unsigned long)exynos_gem_obj->buffer->dma_addr) >>
+			PAGE_SHIFT) + page_offset;
 
 	ret = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, pfn);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index e5fc014..ef87973 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -30,13 +30,29 @@
 			struct exynos_drm_gem_obj, base)
 
 /*
+ * exynos drm gem buffer structure.
+ *
+ * @kvaddr: kernel virtual address to allocated memory region.
+ * @dma_addr: bus address(accessed by dma) to allocated memory region.
+ *	- this address could be physical address without IOMMU and
+ *	device address with IOMMU.
+ * @size: size of allocated memory region.
+ */
+struct exynos_drm_gem_buf {
+	void __iomem		*kvaddr;
+	dma_addr_t		dma_addr;
+	unsigned long		size;
+};
+
+/*
  * exynos drm buffer structure.
  *
  * @base: a gem object.
  *	- a new handle to this gem object would be created
  *	by drm_gem_handle_create().
- * @entry: pointer to exynos drm buffer entry object.
- *	- containing the information to physically
+ * @buffer: a pointer to exynos_drm_gem_buffer object.
+ *	- contain the information to memory region allocated
+ *	by user request or at framebuffer creation.
  *	continuous memory region allocated by user request
  *	or at framebuffer creation.
  *
@@ -45,13 +61,13 @@
  */
 struct exynos_drm_gem_obj {
 	struct drm_gem_object base;
-	struct exynos_drm_buf_entry *entry;
+	struct exynos_drm_gem_buf *buffer;
 };
 
 /* create a new buffer and get a new gem handle. */
-struct exynos_drm_gem_obj *exynos_drm_gem_create(struct drm_file *file_priv,
-		struct drm_device *dev, unsigned int size,
-		unsigned int *handle);
+struct exynos_drm_gem_obj *exynos_drm_gem_create(struct drm_device *dev,
+		struct drm_file *file_priv,
+		unsigned int *handle, unsigned long size);
 
 /*
  * request gem object creation and buffer allocation as the size
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 4f40f1c..d09a6e0 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -636,11 +636,16 @@ static int i915_ringbuffer_info(struct seq_file *m, void *data)
 	struct drm_device *dev = node->minor->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct intel_ring_buffer *ring;
+	int ret;
 
 	ring = &dev_priv->ring[(uintptr_t)node->info_ent->data];
 	if (ring->size == 0)
 		return 0;
 
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
 	seq_printf(m, "Ring %s:\n", ring->name);
 	seq_printf(m, "  Head :    %08x\n", I915_READ_HEAD(ring) & HEAD_ADDR);
 	seq_printf(m, "  Tail :    %08x\n", I915_READ_TAIL(ring) & TAIL_ADDR);
@@ -654,6 +659,8 @@ static int i915_ringbuffer_info(struct seq_file *m, void *data)
 	seq_printf(m, "  Control : %08x\n", I915_READ_CTL(ring));
 	seq_printf(m, "  Start :   %08x\n", I915_READ_START(ring));
 
+	mutex_unlock(&dev->struct_mutex);
+
 	return 0;
 }
 
@@ -842,7 +849,16 @@ static int i915_rstdby_delays(struct seq_file *m, void *unused)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	u16 crstanddelay = I915_READ16(CRSTANDVID);
+	u16 crstanddelay;
+	int ret;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	crstanddelay = I915_READ16(CRSTANDVID);
+
+	mutex_unlock(&dev->struct_mutex);
 
 	seq_printf(m, "w/ctx: %d, w/o ctx: %d\n", (crstanddelay >> 8) & 0x3f, (crstanddelay & 0x3f));
 
@@ -940,7 +956,11 @@ static int i915_delayfreq_table(struct seq_file *m, void *unused)
 	struct drm_device *dev = node->minor->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	u32 delayfreq;
-	int i;
+	int ret, i;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
 
 	for (i = 0; i < 16; i++) {
 		delayfreq = I915_READ(PXVFREQ_BASE + i * 4);
@@ -948,6 +968,8 @@ static int i915_delayfreq_table(struct seq_file *m, void *unused)
 			   (delayfreq & PXVFREQ_PX_MASK) >> PXVFREQ_PX_SHIFT);
 	}
 
+	mutex_unlock(&dev->struct_mutex);
+
 	return 0;
 }
 
@@ -962,13 +984,19 @@ static int i915_inttoext_table(struct seq_file *m, void *unused)
 	struct drm_device *dev = node->minor->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	u32 inttoext;
-	int i;
+	int ret, i;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
 
 	for (i = 1; i <= 32; i++) {
 		inttoext = I915_READ(INTTOEXT_BASE_ILK + i * 4);
 		seq_printf(m, "INTTOEXT%02d: 0x%08x\n", i, inttoext);
 	}
 
+	mutex_unlock(&dev->struct_mutex);
+
 	return 0;
 }
 
@@ -977,9 +1005,19 @@ static int i915_drpc_info(struct seq_file *m, void *unused)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	u32 rgvmodectl = I915_READ(MEMMODECTL);
-	u32 rstdbyctl = I915_READ(RSTDBYCTL);
-	u16 crstandvid = I915_READ16(CRSTANDVID);
+	u32 rgvmodectl, rstdbyctl;
+	u16 crstandvid;
+	int ret;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	rgvmodectl = I915_READ(MEMMODECTL);
+	rstdbyctl = I915_READ(RSTDBYCTL);
+	crstandvid = I915_READ16(CRSTANDVID);
+
+	mutex_unlock(&dev->struct_mutex);
 
 	seq_printf(m, "HD boost: %s\n", (rgvmodectl & MEMMODE_BOOST_EN) ?
 		   "yes" : "no");
@@ -1167,9 +1205,16 @@ static int i915_gfxec(struct seq_file *m, void *unused)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
+	int ret;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
 
 	seq_printf(m, "GFXEC: %ld\n", (unsigned long)I915_READ(0x112f4));
 
+	mutex_unlock(&dev->struct_mutex);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index e9c2cfe..15bfa91 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -68,7 +68,7 @@ module_param_named(i915_enable_rc6, i915_enable_rc6, int, 0600);
 MODULE_PARM_DESC(i915_enable_rc6,
 		"Enable power-saving render C-state 6 (default: true)");
 
-unsigned int i915_enable_fbc __read_mostly = -1;
+int i915_enable_fbc __read_mostly = -1;
 module_param_named(i915_enable_fbc, i915_enable_fbc, int, 0600);
 MODULE_PARM_DESC(i915_enable_fbc,
 		"Enable frame buffer compression for power savings "
@@ -80,7 +80,7 @@ MODULE_PARM_DESC(lvds_downclock,
 		"Use panel (LVDS/eDP) downclocking for power savings "
 		"(default: false)");
 
-unsigned int i915_panel_use_ssc __read_mostly = -1;
+int i915_panel_use_ssc __read_mostly = -1;
 module_param_named(lvds_use_ssc, i915_panel_use_ssc, int, 0600);
 MODULE_PARM_DESC(lvds_use_ssc,
 		"Use Spread Spectrum Clock with panels [LVDS/eDP] "
@@ -107,7 +107,7 @@ static struct drm_driver driver;
 extern int intel_agp_enabled;
 
 #define INTEL_VGA_DEVICE(id, info) {		\
-	.class = PCI_CLASS_DISPLAY_VGA << 8,	\
+	.class = PCI_BASE_CLASS_DISPLAY << 16,	\
 	.class_mask = 0xff0000,			\
 	.vendor = 0x8086,			\
 	.device = id,				\
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 06a37f4..4a9c1b9 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -126,6 +126,9 @@ struct drm_i915_master_private {
 	struct _drm_i915_sarea *sarea_priv;
 };
 #define I915_FENCE_REG_NONE -1
+#define I915_MAX_NUM_FENCES 16
+/* 16 fences + sign bit for FENCE_REG_NONE */
+#define I915_MAX_NUM_FENCE_BITS 5
 
 struct drm_i915_fence_reg {
 	struct list_head lru_list;
@@ -168,7 +171,7 @@ struct drm_i915_error_state {
 	u32 instdone1;
 	u32 seqno;
 	u64 bbaddr;
-	u64 fence[16];
+	u64 fence[I915_MAX_NUM_FENCES];
 	struct timeval time;
 	struct drm_i915_error_object {
 		int page_count;
@@ -182,7 +185,7 @@ struct drm_i915_error_state {
 		u32 gtt_offset;
 		u32 read_domains;
 		u32 write_domain;
-		s32 fence_reg:5;
+		s32 fence_reg:I915_MAX_NUM_FENCE_BITS;
 		s32 pinned:2;
 		u32 tiling:2;
 		u32 dirty:1;
@@ -375,7 +378,7 @@ typedef struct drm_i915_private {
 	struct notifier_block lid_notifier;
 
 	int crt_ddc_pin;
-	struct drm_i915_fence_reg fence_regs[16]; /* assume 965 */
+	struct drm_i915_fence_reg fence_regs[I915_MAX_NUM_FENCES]; /* assume 965 */
 	int fence_reg_start; /* 4 if userland hasn't ioctl'd us yet */
 	int num_fence_regs; /* 8 on pre-965, 16 otherwise */
 
@@ -506,7 +509,7 @@ typedef struct drm_i915_private {
 	u8 saveAR[21];
 	u8 saveDACMASK;
 	u8 saveCR[37];
-	uint64_t saveFENCE[16];
+	uint64_t saveFENCE[I915_MAX_NUM_FENCES];
 	u32 saveCURACNTR;
 	u32 saveCURAPOS;
 	u32 saveCURABASE;
@@ -777,10 +780,8 @@ struct drm_i915_gem_object {
 	 * Fence register bits (if any) for this object.  Will be set
 	 * as needed when mapped into the GTT.
 	 * Protected by dev->struct_mutex.
-	 *
-	 * Size: 4 bits for 16 fences + sign (for FENCE_REG_NONE)
 	 */
-	signed int fence_reg:5;
+	signed int fence_reg:I915_MAX_NUM_FENCE_BITS;
 
 	/**
 	 * Advice: are the backing pages purgeable?
@@ -999,10 +1000,10 @@ extern int i915_panel_ignore_lid __read_mostly;
 extern unsigned int i915_powersave __read_mostly;
 extern unsigned int i915_semaphores __read_mostly;
 extern unsigned int i915_lvds_downclock __read_mostly;
-extern unsigned int i915_panel_use_ssc __read_mostly;
+extern int i915_panel_use_ssc __read_mostly;
 extern int i915_vbt_sdvo_panel_type __read_mostly;
 extern unsigned int i915_enable_rc6 __read_mostly;
-extern unsigned int i915_enable_fbc __read_mostly;
+extern int i915_enable_fbc __read_mostly;
 extern bool i915_enable_hangcheck __read_mostly;
 
 extern int i915_suspend(struct drm_device *dev, pm_message_t state);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index d18b07a..8359dc7 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1745,7 +1745,7 @@ static void i915_gem_reset_fences(struct drm_device *dev)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int i;
 
-	for (i = 0; i < 16; i++) {
+	for (i = 0; i < dev_priv->num_fence_regs; i++) {
 		struct drm_i915_fence_reg *reg = &dev_priv->fence_regs[i];
 		struct drm_i915_gem_object *obj = reg->obj;
 
@@ -3512,9 +3512,11 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data,
 			 * so emit a request to do so.
 			 */
 			request = kzalloc(sizeof(*request), GFP_KERNEL);
-			if (request)
+			if (request) {
 				ret = i915_add_request(obj->ring, NULL, request);
-			else
+				if (ret)
+					kfree(request);
+			} else
 				ret = -ENOMEM;
 		}
 
@@ -3613,7 +3615,7 @@ struct drm_i915_gem_object *i915_gem_alloc_object(struct drm_device *dev,
 	obj->base.write_domain = I915_GEM_DOMAIN_CPU;
 	obj->base.read_domains = I915_GEM_DOMAIN_CPU;
 
-	if (IS_GEN6(dev)) {
+	if (IS_GEN6(dev) || IS_GEN7(dev)) {
 		/* On Gen6, we can have the GPU use the LLC (the CPU
 		 * cache) for about a 10% performance improvement
 		 * compared to uncached.  Graphics requests other than
@@ -3877,7 +3879,7 @@ i915_gem_load(struct drm_device *dev)
 	INIT_LIST_HEAD(&dev_priv->mm.gtt_list);
 	for (i = 0; i < I915_NUM_RINGS; i++)
 		init_ring_lists(&dev_priv->ring[i]);
-	for (i = 0; i < 16; i++)
+	for (i = 0; i < I915_MAX_NUM_FENCES; i++)
 		INIT_LIST_HEAD(&dev_priv->fence_regs[i].lru_list);
 	INIT_DELAYED_WORK(&dev_priv->mm.retire_work,
 			  i915_gem_retire_work_handler);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 9ee2729..b40004b 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -824,6 +824,7 @@ static void i915_gem_record_fences(struct drm_device *dev,
 
 	/* Fences */
 	switch (INTEL_INFO(dev)->gen) {
+	case 7:
 	case 6:
 		for (i = 0; i < 16; i++)
 			error->fence[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8));
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 5a09416..b080cc8 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1553,12 +1553,21 @@
  */
 #define   PP_READY		(1 << 30)
 #define   PP_SEQUENCE_NONE	(0 << 28)
-#define   PP_SEQUENCE_ON	(1 << 28)
-#define   PP_SEQUENCE_OFF	(2 << 28)
-#define   PP_SEQUENCE_MASK	0x30000000
+#define   PP_SEQUENCE_POWER_UP	(1 << 28)
+#define   PP_SEQUENCE_POWER_DOWN (2 << 28)
+#define   PP_SEQUENCE_MASK	(3 << 28)
+#define   PP_SEQUENCE_SHIFT	28
 #define   PP_CYCLE_DELAY_ACTIVE	(1 << 27)
-#define   PP_SEQUENCE_STATE_ON_IDLE (1 << 3)
 #define   PP_SEQUENCE_STATE_MASK 0x0000000f
+#define   PP_SEQUENCE_STATE_OFF_IDLE	(0x0 << 0)
+#define   PP_SEQUENCE_STATE_OFF_S0_1	(0x1 << 0)
+#define   PP_SEQUENCE_STATE_OFF_S0_2	(0x2 << 0)
+#define   PP_SEQUENCE_STATE_OFF_S0_3	(0x3 << 0)
+#define   PP_SEQUENCE_STATE_ON_IDLE	(0x8 << 0)
+#define   PP_SEQUENCE_STATE_ON_S1_0	(0x9 << 0)
+#define   PP_SEQUENCE_STATE_ON_S1_2	(0xa << 0)
+#define   PP_SEQUENCE_STATE_ON_S1_3	(0xb << 0)
+#define   PP_SEQUENCE_STATE_RESET	(0xf << 0)
 #define PP_CONTROL	0x61204
 #define   POWER_TARGET_ON	(1 << 0)
 #define PP_ON_DELAYS	0x61208
@@ -3444,6 +3453,10 @@
 #define  GT_FIFO_FREE_ENTRIES			0x120008
 #define    GT_FIFO_NUM_RESERVED_ENTRIES		20
 
+#define GEN6_UCGCTL2				0x9404
+# define GEN6_RCPBUNIT_CLOCK_GATE_DISABLE		(1 << 12)
+# define GEN6_RCCUNIT_CLOCK_GATE_DISABLE		(1 << 11)
+
 #define GEN6_RPNSWREQ				0xA008
 #define   GEN6_TURBO_DISABLE			(1<<31)
 #define   GEN6_FREQUENCY(x)			((x)<<25)
diff --git a/drivers/gpu/drm/i915/i915_suspend.c b/drivers/gpu/drm/i915/i915_suspend.c
index f8f602d..7886e4f 100644
--- a/drivers/gpu/drm/i915/i915_suspend.c
+++ b/drivers/gpu/drm/i915/i915_suspend.c
@@ -370,6 +370,7 @@ static void i915_save_modeset_reg(struct drm_device *dev)
 
 	/* Fences */
 	switch (INTEL_INFO(dev)->gen) {
+	case 7:
 	case 6:
 		for (i = 0; i < 16; i++)
 			dev_priv->saveFENCE[i] = I915_READ64(FENCE_REG_SANDYBRIDGE_0 + (i * 8));
@@ -404,6 +405,7 @@ static void i915_restore_modeset_reg(struct drm_device *dev)
 
 	/* Fences */
 	switch (INTEL_INFO(dev)->gen) {
+	case 7:
 	case 6:
 		for (i = 0; i < 16; i++)
 			I915_WRITE64(FENCE_REG_SANDYBRIDGE_0 + (i * 8), dev_priv->saveFENCE[i]);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 981b1f1..e77a863 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2933,7 +2933,8 @@ static void ironlake_pch_enable(struct drm_crtc *crtc)
 
 	/* For PCH DP, enable TRANS_DP_CTL */
 	if (HAS_PCH_CPT(dev) &&
-	    intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT)) {
+	    (intel_pipe_has_type(crtc, INTEL_OUTPUT_DISPLAYPORT) ||
+	     intel_pipe_has_type(crtc, INTEL_OUTPUT_EDP))) {
 		u32 bpc = (I915_READ(PIPECONF(pipe)) & PIPE_BPC_MASK) >> 5;
 		reg = TRANS_DP_CTL(pipe);
 		temp = I915_READ(reg);
@@ -4711,7 +4712,7 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
 				lvds_bpc = 6;
 
 			if (lvds_bpc < display_bpc) {
-				DRM_DEBUG_DRIVER("clamping display bpc (was %d) to LVDS (%d)\n", display_bpc, lvds_bpc);
+				DRM_DEBUG_KMS("clamping display bpc (was %d) to LVDS (%d)\n", display_bpc, lvds_bpc);
 				display_bpc = lvds_bpc;
 			}
 			continue;
@@ -4722,7 +4723,7 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
 			unsigned int edp_bpc = dev_priv->edp.bpp / 3;
 
 			if (edp_bpc < display_bpc) {
-				DRM_DEBUG_DRIVER("clamping display bpc (was %d) to eDP (%d)\n", display_bpc, edp_bpc);
+				DRM_DEBUG_KMS("clamping display bpc (was %d) to eDP (%d)\n", display_bpc, edp_bpc);
 				display_bpc = edp_bpc;
 			}
 			continue;
@@ -4737,7 +4738,7 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
 			/* Don't use an invalid EDID bpc value */
 			if (connector->display_info.bpc &&
 			    connector->display_info.bpc < display_bpc) {
-				DRM_DEBUG_DRIVER("clamping display bpc (was %d) to EDID reported max of %d\n", display_bpc, connector->display_info.bpc);
+				DRM_DEBUG_KMS("clamping display bpc (was %d) to EDID reported max of %d\n", display_bpc, connector->display_info.bpc);
 				display_bpc = connector->display_info.bpc;
 			}
 		}
@@ -4748,10 +4749,10 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
 		 */
 		if (intel_encoder->type == INTEL_OUTPUT_HDMI) {
 			if (display_bpc > 8 && display_bpc < 12) {
-				DRM_DEBUG_DRIVER("forcing bpc to 12 for HDMI\n");
+				DRM_DEBUG_KMS("forcing bpc to 12 for HDMI\n");
 				display_bpc = 12;
 			} else {
-				DRM_DEBUG_DRIVER("forcing bpc to 8 for HDMI\n");
+				DRM_DEBUG_KMS("forcing bpc to 8 for HDMI\n");
 				display_bpc = 8;
 			}
 		}
@@ -4789,8 +4790,8 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
 
 	display_bpc = min(display_bpc, bpc);
 
-	DRM_DEBUG_DRIVER("setting pipe bpc to %d (max display bpc %d)\n",
-			 bpc, display_bpc);
+	DRM_DEBUG_KMS("setting pipe bpc to %d (max display bpc %d)\n",
+		      bpc, display_bpc);
 
 	*pipe_bpp = display_bpc * 3;
 
@@ -5671,7 +5672,7 @@ static int ironlake_crtc_mode_set(struct drm_crtc *crtc,
 	pipeconf &= ~PIPECONF_DITHER_TYPE_MASK;
 	if ((is_lvds && dev_priv->lvds_dither) || dither) {
 		pipeconf |= PIPECONF_DITHER_EN;
-		pipeconf |= PIPECONF_DITHER_TYPE_ST1;
+		pipeconf |= PIPECONF_DITHER_TYPE_SP;
 	}
 	if (is_dp || intel_encoder_is_pch_edp(&has_edp_encoder->base)) {
 		intel_dp_set_m_n(crtc, mode, adjusted_mode);
@@ -8148,6 +8149,20 @@ static void gen6_init_clock_gating(struct drm_device *dev)
 	I915_WRITE(WM2_LP_ILK, 0);
 	I915_WRITE(WM1_LP_ILK, 0);
 
+	/* According to the BSpec vol1g, bit 12 (RCPBUNIT) clock
+	 * gating disable must be set.  Failure to set it results in
+	 * flickering pixels due to Z write ordering failures after
+	 * some amount of runtime in the Mesa "fire" demo, and Unigine
+	 * Sanctuary and Tropics, and apparently anything else with
+	 * alpha test or pixel discard.
+	 *
+	 * According to the spec, bit 11 (RCCUNIT) must also be set,
+	 * but we didn't debug actual testcases to find it out.
+	 */
+	I915_WRITE(GEN6_UCGCTL2,
+		   GEN6_RCPBUNIT_CLOCK_GATE_DISABLE |
+		   GEN6_RCCUNIT_CLOCK_GATE_DISABLE);
+
 	/*
 	 * According to the spec the following bits should be
 	 * set in order to enable memory self-refresh and fbc:
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 09b318b..4d0358f 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -59,7 +59,6 @@ struct intel_dp {
 	struct i2c_algo_dp_aux_data algo;
 	bool is_pch_edp;
 	uint8_t	train_set[4];
-	uint8_t link_status[DP_LINK_STATUS_SIZE];
 	int panel_power_up_delay;
 	int panel_power_down_delay;
 	int panel_power_cycle_delay;
@@ -68,7 +67,6 @@ struct intel_dp {
 	struct drm_display_mode *panel_fixed_mode;  /* for eDP */
 	struct delayed_work panel_vdd_work;
 	bool want_panel_vdd;
-	unsigned long panel_off_jiffies;
 };
 
 /**
@@ -157,16 +155,12 @@ intel_edp_link_config(struct intel_encoder *intel_encoder,
 static int
 intel_dp_max_lane_count(struct intel_dp *intel_dp)
 {
-	int max_lane_count = 4;
-
-	if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11) {
-		max_lane_count = intel_dp->dpcd[DP_MAX_LANE_COUNT] & 0x1f;
-		switch (max_lane_count) {
-		case 1: case 2: case 4:
-			break;
-		default:
-			max_lane_count = 4;
-		}
+	int max_lane_count = intel_dp->dpcd[DP_MAX_LANE_COUNT] & 0x1f;
+	switch (max_lane_count) {
+	case 1: case 2: case 4:
+		break;
+	default:
+		max_lane_count = 4;
 	}
 	return max_lane_count;
 }
@@ -768,12 +762,11 @@ intel_dp_set_m_n(struct drm_crtc *crtc, struct drm_display_mode *mode,
 			continue;
 
 		intel_dp = enc_to_intel_dp(encoder);
-		if (intel_dp->base.type == INTEL_OUTPUT_DISPLAYPORT) {
+		if (intel_dp->base.type == INTEL_OUTPUT_DISPLAYPORT ||
+		    intel_dp->base.type == INTEL_OUTPUT_EDP)
+		{
 			lane_count = intel_dp->lane_count;
 			break;
-		} else if (is_edp(intel_dp)) {
-			lane_count = dev_priv->edp.lanes;
-			break;
 		}
 	}
 
@@ -810,6 +803,7 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 		  struct drm_display_mode *adjusted_mode)
 {
 	struct drm_device *dev = encoder->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 	struct drm_crtc *crtc = intel_dp->base.base.crtc;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
@@ -822,18 +816,31 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 			ironlake_edp_pll_off(encoder);
 	}
 
-	intel_dp->DP = DP_VOLTAGE_0_4 | DP_PRE_EMPHASIS_0;
-	intel_dp->DP |= intel_dp->color_range;
+	/*
+	 * There are three kinds of DP registers:
+	 *
+	 * 	IBX PCH
+	 * 	CPU
+	 * 	CPT PCH
+	 *
+	 * IBX PCH and CPU are the same for almost everything,
+	 * except that the CPU DP PLL is configured in this
+	 * register
+	 *
+	 * CPT PCH is quite different, having many bits moved
+	 * to the TRANS_DP_CTL register instead. That
+	 * configuration happens (oddly) in ironlake_pch_enable
+	 */
 
-	if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
-		intel_dp->DP |= DP_SYNC_HS_HIGH;
-	if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
-		intel_dp->DP |= DP_SYNC_VS_HIGH;
+	/* Preserve the BIOS-computed detected bit. This is
+	 * supposed to be read-only.
+	 */
+	intel_dp->DP = I915_READ(intel_dp->output_reg) & DP_DETECTED;
+	intel_dp->DP |=  DP_VOLTAGE_0_4 | DP_PRE_EMPHASIS_0;
 
-	if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
-		intel_dp->DP |= DP_LINK_TRAIN_OFF_CPT;
-	else
-		intel_dp->DP |= DP_LINK_TRAIN_OFF;
+	/* Handle DP bits in common between all three register formats */
+
+	intel_dp->DP |= DP_VOLTAGE_0_4 | DP_PRE_EMPHASIS_0;
 
 	switch (intel_dp->lane_count) {
 	case 1:
@@ -852,59 +859,106 @@ intel_dp_mode_set(struct drm_encoder *encoder, struct drm_display_mode *mode,
 		intel_dp->DP |= DP_AUDIO_OUTPUT_ENABLE;
 		intel_write_eld(encoder, adjusted_mode);
 	}
-
 	memset(intel_dp->link_configuration, 0, DP_LINK_CONFIGURATION_SIZE);
 	intel_dp->link_configuration[0] = intel_dp->link_bw;
 	intel_dp->link_configuration[1] = intel_dp->lane_count;
 	intel_dp->link_configuration[8] = DP_SET_ANSI_8B10B;
-
 	/*
 	 * Check for DPCD version > 1.1 and enhanced framing support
 	 */
 	if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11 &&
 	    (intel_dp->dpcd[DP_MAX_LANE_COUNT] & DP_ENHANCED_FRAME_CAP)) {
 		intel_dp->link_configuration[1] |= DP_LANE_COUNT_ENHANCED_FRAME_EN;
-		intel_dp->DP |= DP_ENHANCED_FRAMING;
 	}
 
-	/* CPT DP's pipe select is decided in TRANS_DP_CTL */
-	if (intel_crtc->pipe == 1 && !HAS_PCH_CPT(dev))
-		intel_dp->DP |= DP_PIPEB_SELECT;
+	/* Split out the IBX/CPU vs CPT settings */
 
-	if (is_cpu_edp(intel_dp)) {
-		/* don't miss out required setting for eDP */
-		intel_dp->DP |= DP_PLL_ENABLE;
-		if (adjusted_mode->clock < 200000)
-			intel_dp->DP |= DP_PLL_FREQ_160MHZ;
-		else
-			intel_dp->DP |= DP_PLL_FREQ_270MHZ;
+	if (!HAS_PCH_CPT(dev) || is_cpu_edp(intel_dp)) {
+		intel_dp->DP |= intel_dp->color_range;
+
+		if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
+			intel_dp->DP |= DP_SYNC_HS_HIGH;
+		if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
+			intel_dp->DP |= DP_SYNC_VS_HIGH;
+		intel_dp->DP |= DP_LINK_TRAIN_OFF;
+
+		if (intel_dp->link_configuration[1] & DP_LANE_COUNT_ENHANCED_FRAME_EN)
+			intel_dp->DP |= DP_ENHANCED_FRAMING;
+
+		if (intel_crtc->pipe == 1)
+			intel_dp->DP |= DP_PIPEB_SELECT;
+
+		if (is_cpu_edp(intel_dp)) {
+			/* don't miss out required setting for eDP */
+			intel_dp->DP |= DP_PLL_ENABLE;
+			if (adjusted_mode->clock < 200000)
+				intel_dp->DP |= DP_PLL_FREQ_160MHZ;
+			else
+				intel_dp->DP |= DP_PLL_FREQ_270MHZ;
+		}
+	} else {
+		intel_dp->DP |= DP_LINK_TRAIN_OFF_CPT;
 	}
 }
 
-static void ironlake_wait_panel_off(struct intel_dp *intel_dp)
+#define IDLE_ON_MASK		(PP_ON | 0 	  | PP_SEQUENCE_MASK | 0                     | PP_SEQUENCE_STATE_MASK)
+#define IDLE_ON_VALUE   	(PP_ON | 0 	  | PP_SEQUENCE_NONE | 0                     | PP_SEQUENCE_STATE_ON_IDLE)
+
+#define IDLE_OFF_MASK		(PP_ON | 0        | PP_SEQUENCE_MASK | 0                     | PP_SEQUENCE_STATE_MASK)
+#define IDLE_OFF_VALUE		(0     | 0        | PP_SEQUENCE_NONE | 0                     | PP_SEQUENCE_STATE_OFF_IDLE)
+
+#define IDLE_CYCLE_MASK		(PP_ON | 0        | PP_SEQUENCE_MASK | PP_CYCLE_DELAY_ACTIVE | PP_SEQUENCE_STATE_MASK)
+#define IDLE_CYCLE_VALUE	(0     | 0        | PP_SEQUENCE_NONE | 0                     | PP_SEQUENCE_STATE_OFF_IDLE)
+
+static void ironlake_wait_panel_status(struct intel_dp *intel_dp,
+				       u32 mask,
+				       u32 value)
 {
-	unsigned long	off_time;
-	unsigned long	delay;
+	struct drm_device *dev = intel_dp->base.base.dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	DRM_DEBUG_KMS("Wait for panel power off time\n");
+	DRM_DEBUG_KMS("mask %08x value %08x status %08x control %08x\n",
+		      mask, value,
+		      I915_READ(PCH_PP_STATUS),
+		      I915_READ(PCH_PP_CONTROL));
 
-	if (ironlake_edp_have_panel_power(intel_dp) ||
-	    ironlake_edp_have_panel_vdd(intel_dp))
-	{
-		DRM_DEBUG_KMS("Panel still on, no delay needed\n");
-		return;
+	if (_wait_for((I915_READ(PCH_PP_STATUS) & mask) == value, 5000, 10)) {
+		DRM_ERROR("Panel status timeout: status %08x control %08x\n",
+			  I915_READ(PCH_PP_STATUS),
+			  I915_READ(PCH_PP_CONTROL));
 	}
+}
 
-	off_time = intel_dp->panel_off_jiffies + msecs_to_jiffies(intel_dp->panel_power_down_delay);
-	if (time_after(jiffies, off_time)) {
-		DRM_DEBUG_KMS("Time already passed");
-		return;
-	}
-	delay = jiffies_to_msecs(off_time - jiffies);
-	if (delay > intel_dp->panel_power_down_delay)
-		delay = intel_dp->panel_power_down_delay;
-	DRM_DEBUG_KMS("Waiting an additional %ld ms\n", delay);
-	msleep(delay);
+static void ironlake_wait_panel_on(struct intel_dp *intel_dp)
+{
+	DRM_DEBUG_KMS("Wait for panel power on\n");
+	ironlake_wait_panel_status(intel_dp, IDLE_ON_MASK, IDLE_ON_VALUE);
+}
+
+static void ironlake_wait_panel_off(struct intel_dp *intel_dp)
+{
+	DRM_DEBUG_KMS("Wait for panel power off time\n");
+	ironlake_wait_panel_status(intel_dp, IDLE_OFF_MASK, IDLE_OFF_VALUE);
+}
+
+static void ironlake_wait_panel_power_cycle(struct intel_dp *intel_dp)
+{
+	DRM_DEBUG_KMS("Wait for panel power cycle\n");
+	ironlake_wait_panel_status(intel_dp, IDLE_CYCLE_MASK, IDLE_CYCLE_VALUE);
+}
+
+
+/* Read the current pp_control value, unlocking the register if it
+ * is locked
+ */
+
+static  u32 ironlake_get_pp_control(struct drm_i915_private *dev_priv)
+{
+	u32	control = I915_READ(PCH_PP_CONTROL);
+
+	control &= ~PANEL_UNLOCK_MASK;
+	control |= PANEL_UNLOCK_REGS;
+	return control;
 }
 
 static void ironlake_edp_panel_vdd_on(struct intel_dp *intel_dp)
@@ -921,15 +975,16 @@ static void ironlake_edp_panel_vdd_on(struct intel_dp *intel_dp)
 	     "eDP VDD already requested on\n");
 
 	intel_dp->want_panel_vdd = true;
+
 	if (ironlake_edp_have_panel_vdd(intel_dp)) {
 		DRM_DEBUG_KMS("eDP VDD already on\n");
 		return;
 	}
 
-	ironlake_wait_panel_off(intel_dp);
-	pp = I915_READ(PCH_PP_CONTROL);
-	pp &= ~PANEL_UNLOCK_MASK;
-	pp |= PANEL_UNLOCK_REGS;
+	if (!ironlake_edp_have_panel_power(intel_dp))
+		ironlake_wait_panel_power_cycle(intel_dp);
+
+	pp = ironlake_get_pp_control(dev_priv);
 	pp |= EDP_FORCE_VDD;
 	I915_WRITE(PCH_PP_CONTROL, pp);
 	POSTING_READ(PCH_PP_CONTROL);
@@ -952,9 +1007,7 @@ static void ironlake_panel_vdd_off_sync(struct intel_dp *intel_dp)
 	u32 pp;
 
 	if (!intel_dp->want_panel_vdd && ironlake_edp_have_panel_vdd(intel_dp)) {
-		pp = I915_READ(PCH_PP_CONTROL);
-		pp &= ~PANEL_UNLOCK_MASK;
-		pp |= PANEL_UNLOCK_REGS;
+		pp = ironlake_get_pp_control(dev_priv);
 		pp &= ~EDP_FORCE_VDD;
 		I915_WRITE(PCH_PP_CONTROL, pp);
 		POSTING_READ(PCH_PP_CONTROL);
@@ -962,7 +1015,8 @@ static void ironlake_panel_vdd_off_sync(struct intel_dp *intel_dp)
 		/* Make sure sequencer is idle before allowing subsequent activity */
 		DRM_DEBUG_KMS("PCH_PP_STATUS: 0x%08x PCH_PP_CONTROL: 0x%08x\n",
 			      I915_READ(PCH_PP_STATUS), I915_READ(PCH_PP_CONTROL));
-		intel_dp->panel_off_jiffies = jiffies;
+
+		msleep(intel_dp->panel_power_down_delay);
 	}
 }
 
@@ -972,9 +1026,9 @@ static void ironlake_panel_vdd_work(struct work_struct *__work)
 						 struct intel_dp, panel_vdd_work);
 	struct drm_device *dev = intel_dp->base.base.dev;
 
-	mutex_lock(&dev->struct_mutex);
+	mutex_lock(&dev->mode_config.mutex);
 	ironlake_panel_vdd_off_sync(intel_dp);
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&dev->mode_config.mutex);
 }
 
 static void ironlake_edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync)
@@ -984,7 +1038,7 @@ static void ironlake_edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync)
 
 	DRM_DEBUG_KMS("Turn eDP VDD off %d\n", intel_dp->want_panel_vdd);
 	WARN(!intel_dp->want_panel_vdd, "eDP VDD not forced on");
-	
+
 	intel_dp->want_panel_vdd = false;
 
 	if (sync) {
@@ -1000,23 +1054,25 @@ static void ironlake_edp_panel_vdd_off(struct intel_dp *intel_dp, bool sync)
 	}
 }
 
-/* Returns true if the panel was already on when called */
 static void ironlake_edp_panel_on(struct intel_dp *intel_dp)
 {
 	struct drm_device *dev = intel_dp->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 pp, idle_on_mask = PP_ON | PP_SEQUENCE_STATE_ON_IDLE;
+	u32 pp;
 
 	if (!is_edp(intel_dp))
 		return;
-	if (ironlake_edp_have_panel_power(intel_dp))
+
+	DRM_DEBUG_KMS("Turn eDP power on\n");
+
+	if (ironlake_edp_have_panel_power(intel_dp)) {
+		DRM_DEBUG_KMS("eDP power already on\n");
 		return;
+	}
 
-	ironlake_wait_panel_off(intel_dp);
-	pp = I915_READ(PCH_PP_CONTROL);
-	pp &= ~PANEL_UNLOCK_MASK;
-	pp |= PANEL_UNLOCK_REGS;
+	ironlake_wait_panel_power_cycle(intel_dp);
 
+	pp = ironlake_get_pp_control(dev_priv);
 	if (IS_GEN5(dev)) {
 		/* ILK workaround: disable reset around power sequence */
 		pp &= ~PANEL_POWER_RESET;
@@ -1025,13 +1081,13 @@ static void ironlake_edp_panel_on(struct intel_dp *intel_dp)
 	}
 
 	pp |= POWER_TARGET_ON;
+	if (!IS_GEN5(dev))
+		pp |= PANEL_POWER_RESET;
+
 	I915_WRITE(PCH_PP_CONTROL, pp);
 	POSTING_READ(PCH_PP_CONTROL);
 
-	if (wait_for((I915_READ(PCH_PP_STATUS) & idle_on_mask) == idle_on_mask,
-		     5000))
-		DRM_ERROR("panel on wait timed out: 0x%08x\n",
-			  I915_READ(PCH_PP_STATUS));
+	ironlake_wait_panel_on(intel_dp);
 
 	if (IS_GEN5(dev)) {
 		pp |= PANEL_POWER_RESET; /* restore panel reset bit */
@@ -1040,46 +1096,25 @@ static void ironlake_edp_panel_on(struct intel_dp *intel_dp)
 	}
 }
 
-static void ironlake_edp_panel_off(struct drm_encoder *encoder)
+static void ironlake_edp_panel_off(struct intel_dp *intel_dp)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
-	struct drm_device *dev = encoder->dev;
+	struct drm_device *dev = intel_dp->base.base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	u32 pp, idle_off_mask = PP_ON | PP_SEQUENCE_MASK |
-		PP_CYCLE_DELAY_ACTIVE | PP_SEQUENCE_STATE_MASK;
+	u32 pp;
 
 	if (!is_edp(intel_dp))
 		return;
-	pp = I915_READ(PCH_PP_CONTROL);
-	pp &= ~PANEL_UNLOCK_MASK;
-	pp |= PANEL_UNLOCK_REGS;
 
-	if (IS_GEN5(dev)) {
-		/* ILK workaround: disable reset around power sequence */
-		pp &= ~PANEL_POWER_RESET;
-		I915_WRITE(PCH_PP_CONTROL, pp);
-		POSTING_READ(PCH_PP_CONTROL);
-	}
+	DRM_DEBUG_KMS("Turn eDP power off\n");
 
-	intel_dp->panel_off_jiffies = jiffies;
+	WARN(intel_dp->want_panel_vdd, "Cannot turn power off while VDD is on\n");
 
-	if (IS_GEN5(dev)) {
-		pp &= ~POWER_TARGET_ON;
-		I915_WRITE(PCH_PP_CONTROL, pp);
-		POSTING_READ(PCH_PP_CONTROL);
-		pp &= ~POWER_TARGET_ON;
-		I915_WRITE(PCH_PP_CONTROL, pp);
-		POSTING_READ(PCH_PP_CONTROL);
-		msleep(intel_dp->panel_power_cycle_delay);
-
-		if (wait_for((I915_READ(PCH_PP_STATUS) & idle_off_mask) == 0, 5000))
-			DRM_ERROR("panel off wait timed out: 0x%08x\n",
-				  I915_READ(PCH_PP_STATUS));
+	pp = ironlake_get_pp_control(dev_priv);
+	pp &= ~(POWER_TARGET_ON | EDP_FORCE_VDD | PANEL_POWER_RESET | EDP_BLC_ENABLE);
+	I915_WRITE(PCH_PP_CONTROL, pp);
+	POSTING_READ(PCH_PP_CONTROL);
 
-		pp |= PANEL_POWER_RESET; /* restore panel reset bit */
-		I915_WRITE(PCH_PP_CONTROL, pp);
-		POSTING_READ(PCH_PP_CONTROL);
-	}
+	ironlake_wait_panel_off(intel_dp);
 }
 
 static void ironlake_edp_backlight_on(struct intel_dp *intel_dp)
@@ -1099,9 +1134,7 @@ static void ironlake_edp_backlight_on(struct intel_dp *intel_dp)
 	 * allowing it to appear.
 	 */
 	msleep(intel_dp->backlight_on_delay);
-	pp = I915_READ(PCH_PP_CONTROL);
-	pp &= ~PANEL_UNLOCK_MASK;
-	pp |= PANEL_UNLOCK_REGS;
+	pp = ironlake_get_pp_control(dev_priv);
 	pp |= EDP_BLC_ENABLE;
 	I915_WRITE(PCH_PP_CONTROL, pp);
 	POSTING_READ(PCH_PP_CONTROL);
@@ -1117,9 +1150,7 @@ static void ironlake_edp_backlight_off(struct intel_dp *intel_dp)
 		return;
 
 	DRM_DEBUG_KMS("\n");
-	pp = I915_READ(PCH_PP_CONTROL);
-	pp &= ~PANEL_UNLOCK_MASK;
-	pp |= PANEL_UNLOCK_REGS;
+	pp = ironlake_get_pp_control(dev_priv);
 	pp &= ~EDP_BLC_ENABLE;
 	I915_WRITE(PCH_PP_CONTROL, pp);
 	POSTING_READ(PCH_PP_CONTROL);
@@ -1187,17 +1218,18 @@ static void intel_dp_prepare(struct drm_encoder *encoder)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 
+	ironlake_edp_backlight_off(intel_dp);
+	ironlake_edp_panel_off(intel_dp);
+
 	/* Wake up the sink first */
 	ironlake_edp_panel_vdd_on(intel_dp);
 	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_ON);
+	intel_dp_link_down(intel_dp);
 	ironlake_edp_panel_vdd_off(intel_dp, false);
 
 	/* Make sure the panel is off before trying to
 	 * change the mode
 	 */
-	ironlake_edp_backlight_off(intel_dp);
-	intel_dp_link_down(intel_dp);
-	ironlake_edp_panel_off(encoder);
 }
 
 static void intel_dp_commit(struct drm_encoder *encoder)
@@ -1211,7 +1243,6 @@ static void intel_dp_commit(struct drm_encoder *encoder)
 	intel_dp_start_link_train(intel_dp);
 	ironlake_edp_panel_on(intel_dp);
 	ironlake_edp_panel_vdd_off(intel_dp, true);
-
 	intel_dp_complete_link_train(intel_dp);
 	ironlake_edp_backlight_on(intel_dp);
 
@@ -1230,16 +1261,20 @@ intel_dp_dpms(struct drm_encoder *encoder, int mode)
 	uint32_t dp_reg = I915_READ(intel_dp->output_reg);
 
 	if (mode != DRM_MODE_DPMS_ON) {
+		ironlake_edp_backlight_off(intel_dp);
+		ironlake_edp_panel_off(intel_dp);
+
 		ironlake_edp_panel_vdd_on(intel_dp);
-		if (is_edp(intel_dp))
-			ironlake_edp_backlight_off(intel_dp);
 		intel_dp_sink_dpms(intel_dp, mode);
 		intel_dp_link_down(intel_dp);
-		ironlake_edp_panel_off(encoder);
-		if (is_edp(intel_dp) && !is_pch_edp(intel_dp))
-			ironlake_edp_pll_off(encoder);
 		ironlake_edp_panel_vdd_off(intel_dp, false);
+
+		if (is_cpu_edp(intel_dp))
+			ironlake_edp_pll_off(encoder);
 	} else {
+		if (is_cpu_edp(intel_dp))
+			ironlake_edp_pll_on(encoder);
+
 		ironlake_edp_panel_vdd_on(intel_dp);
 		intel_dp_sink_dpms(intel_dp, mode);
 		if (!(dp_reg & DP_PORT_EN)) {
@@ -1247,7 +1282,6 @@ intel_dp_dpms(struct drm_encoder *encoder, int mode)
 			ironlake_edp_panel_on(intel_dp);
 			ironlake_edp_panel_vdd_off(intel_dp, true);
 			intel_dp_complete_link_train(intel_dp);
-			ironlake_edp_backlight_on(intel_dp);
 		} else
 			ironlake_edp_panel_vdd_off(intel_dp, false);
 		ironlake_edp_backlight_on(intel_dp);
@@ -1285,11 +1319,11 @@ intel_dp_aux_native_read_retry(struct intel_dp *intel_dp, uint16_t address,
  * link status information
  */
 static bool
-intel_dp_get_link_status(struct intel_dp *intel_dp)
+intel_dp_get_link_status(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_STATUS_SIZE])
 {
 	return intel_dp_aux_native_read_retry(intel_dp,
 					      DP_LANE0_1_STATUS,
-					      intel_dp->link_status,
+					      link_status,
 					      DP_LINK_STATUS_SIZE);
 }
 
@@ -1301,27 +1335,25 @@ intel_dp_link_status(uint8_t link_status[DP_LINK_STATUS_SIZE],
 }
 
 static uint8_t
-intel_get_adjust_request_voltage(uint8_t link_status[DP_LINK_STATUS_SIZE],
+intel_get_adjust_request_voltage(uint8_t adjust_request[2],
 				 int lane)
 {
-	int	    i = DP_ADJUST_REQUEST_LANE0_1 + (lane >> 1);
 	int	    s = ((lane & 1) ?
 			 DP_ADJUST_VOLTAGE_SWING_LANE1_SHIFT :
 			 DP_ADJUST_VOLTAGE_SWING_LANE0_SHIFT);
-	uint8_t l = intel_dp_link_status(link_status, i);
+	uint8_t l = adjust_request[lane>>1];
 
 	return ((l >> s) & 3) << DP_TRAIN_VOLTAGE_SWING_SHIFT;
 }
 
 static uint8_t
-intel_get_adjust_request_pre_emphasis(uint8_t link_status[DP_LINK_STATUS_SIZE],
+intel_get_adjust_request_pre_emphasis(uint8_t adjust_request[2],
 				      int lane)
 {
-	int	    i = DP_ADJUST_REQUEST_LANE0_1 + (lane >> 1);
 	int	    s = ((lane & 1) ?
 			 DP_ADJUST_PRE_EMPHASIS_LANE1_SHIFT :
 			 DP_ADJUST_PRE_EMPHASIS_LANE0_SHIFT);
-	uint8_t l = intel_dp_link_status(link_status, i);
+	uint8_t l = adjust_request[lane>>1];
 
 	return ((l >> s) & 3) << DP_TRAIN_PRE_EMPHASIS_SHIFT;
 }
@@ -1344,6 +1376,7 @@ static char	*link_train_names[] = {
  * a maximum voltage of 800mV and a maximum pre-emphasis of 6dB
  */
 #define I830_DP_VOLTAGE_MAX	    DP_TRAIN_VOLTAGE_SWING_800
+#define I830_DP_VOLTAGE_MAX_CPT	    DP_TRAIN_VOLTAGE_SWING_1200
 
 static uint8_t
 intel_dp_pre_emphasis_max(uint8_t voltage_swing)
@@ -1362,15 +1395,18 @@ intel_dp_pre_emphasis_max(uint8_t voltage_swing)
 }
 
 static void
-intel_get_adjust_train(struct intel_dp *intel_dp)
+intel_get_adjust_train(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_STATUS_SIZE])
 {
+	struct drm_device *dev = intel_dp->base.base.dev;
 	uint8_t v = 0;
 	uint8_t p = 0;
 	int lane;
+	uint8_t	*adjust_request = link_status + (DP_ADJUST_REQUEST_LANE0_1 - DP_LANE0_1_STATUS);
+	int voltage_max;
 
 	for (lane = 0; lane < intel_dp->lane_count; lane++) {
-		uint8_t this_v = intel_get_adjust_request_voltage(intel_dp->link_status, lane);
-		uint8_t this_p = intel_get_adjust_request_pre_emphasis(intel_dp->link_status, lane);
+		uint8_t this_v = intel_get_adjust_request_voltage(adjust_request, lane);
+		uint8_t this_p = intel_get_adjust_request_pre_emphasis(adjust_request, lane);
 
 		if (this_v > v)
 			v = this_v;
@@ -1378,8 +1414,12 @@ intel_get_adjust_train(struct intel_dp *intel_dp)
 			p = this_p;
 	}
 
-	if (v >= I830_DP_VOLTAGE_MAX)
-		v = I830_DP_VOLTAGE_MAX | DP_TRAIN_MAX_SWING_REACHED;
+	if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+		voltage_max = I830_DP_VOLTAGE_MAX_CPT;
+	else
+		voltage_max = I830_DP_VOLTAGE_MAX;
+	if (v >= voltage_max)
+		v = voltage_max | DP_TRAIN_MAX_SWING_REACHED;
 
 	if (p >= intel_dp_pre_emphasis_max(v))
 		p = intel_dp_pre_emphasis_max(v) | DP_TRAIN_MAX_PRE_EMPHASIS_REACHED;
@@ -1389,7 +1429,7 @@ intel_get_adjust_train(struct intel_dp *intel_dp)
 }
 
 static uint32_t
-intel_dp_signal_levels(uint8_t train_set, int lane_count)
+intel_dp_signal_levels(uint8_t train_set)
 {
 	uint32_t	signal_levels = 0;
 
@@ -1458,9 +1498,8 @@ static uint8_t
 intel_get_lane_status(uint8_t link_status[DP_LINK_STATUS_SIZE],
 		      int lane)
 {
-	int i = DP_LANE0_1_STATUS + (lane >> 1);
 	int s = (lane & 1) * 4;
-	uint8_t l = intel_dp_link_status(link_status, i);
+	uint8_t l = link_status[lane>>1];
 
 	return (l >> s) & 0xf;
 }
@@ -1485,18 +1524,18 @@ intel_clock_recovery_ok(uint8_t link_status[DP_LINK_STATUS_SIZE], int lane_count
 			 DP_LANE_CHANNEL_EQ_DONE|\
 			 DP_LANE_SYMBOL_LOCKED)
 static bool
-intel_channel_eq_ok(struct intel_dp *intel_dp)
+intel_channel_eq_ok(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_STATUS_SIZE])
 {
 	uint8_t lane_align;
 	uint8_t lane_status;
 	int lane;
 
-	lane_align = intel_dp_link_status(intel_dp->link_status,
+	lane_align = intel_dp_link_status(link_status,
 					  DP_LANE_ALIGN_STATUS_UPDATED);
 	if ((lane_align & DP_INTERLANE_ALIGN_DONE) == 0)
 		return false;
 	for (lane = 0; lane < intel_dp->lane_count; lane++) {
-		lane_status = intel_get_lane_status(intel_dp->link_status, lane);
+		lane_status = intel_get_lane_status(link_status, lane);
 		if ((lane_status & CHANNEL_EQ_BITS) != CHANNEL_EQ_BITS)
 			return false;
 	}
@@ -1521,8 +1560,9 @@ intel_dp_set_link_train(struct intel_dp *intel_dp,
 
 	ret = intel_dp_aux_native_write(intel_dp,
 					DP_TRAINING_LANE0_SET,
-					intel_dp->train_set, 4);
-	if (ret != 4)
+					intel_dp->train_set,
+					intel_dp->lane_count);
+	if (ret != intel_dp->lane_count)
 		return false;
 
 	return true;
@@ -1538,7 +1578,7 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 	int i;
 	uint8_t voltage;
 	bool clock_recovery = false;
-	int tries;
+	int voltage_tries, loop_tries;
 	u32 reg;
 	uint32_t DP = intel_dp->DP;
 
@@ -1565,16 +1605,20 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 		DP &= ~DP_LINK_TRAIN_MASK;
 	memset(intel_dp->train_set, 0, 4);
 	voltage = 0xff;
-	tries = 0;
+	voltage_tries = 0;
+	loop_tries = 0;
 	clock_recovery = false;
 	for (;;) {
 		/* Use intel_dp->train_set[0] to set the voltage and pre emphasis values */
+		uint8_t	    link_status[DP_LINK_STATUS_SIZE];
 		uint32_t    signal_levels;
-		if (IS_GEN6(dev) && is_edp(intel_dp)) {
+
+		if (IS_GEN6(dev) && is_cpu_edp(intel_dp)) {
 			signal_levels = intel_gen6_edp_signal_levels(intel_dp->train_set[0]);
 			DP = (DP & ~EDP_LINK_TRAIN_VOL_EMP_MASK_SNB) | signal_levels;
 		} else {
-			signal_levels = intel_dp_signal_levels(intel_dp->train_set[0], intel_dp->lane_count);
+			signal_levels = intel_dp_signal_levels(intel_dp->train_set[0]);
+			DRM_DEBUG_KMS("training pattern 1 signal levels %08x\n", signal_levels);
 			DP = (DP & ~(DP_VOLTAGE_MASK|DP_PRE_EMPHASIS_MASK)) | signal_levels;
 		}
 
@@ -1590,10 +1634,13 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 		/* Set training pattern 1 */
 
 		udelay(100);
-		if (!intel_dp_get_link_status(intel_dp))
+		if (!intel_dp_get_link_status(intel_dp, link_status)) {
+			DRM_ERROR("failed to get link status\n");
 			break;
+		}
 
-		if (intel_clock_recovery_ok(intel_dp->link_status, intel_dp->lane_count)) {
+		if (intel_clock_recovery_ok(link_status, intel_dp->lane_count)) {
+			DRM_DEBUG_KMS("clock recovery OK\n");
 			clock_recovery = true;
 			break;
 		}
@@ -1602,20 +1649,30 @@ intel_dp_start_link_train(struct intel_dp *intel_dp)
 		for (i = 0; i < intel_dp->lane_count; i++)
 			if ((intel_dp->train_set[i] & DP_TRAIN_MAX_SWING_REACHED) == 0)
 				break;
-		if (i == intel_dp->lane_count)
-			break;
+		if (i == intel_dp->lane_count) {
+			++loop_tries;
+			if (loop_tries == 5) {
+				DRM_DEBUG_KMS("too many full retries, give up\n");
+				break;
+			}
+			memset(intel_dp->train_set, 0, 4);
+			voltage_tries = 0;
+			continue;
+		}
 
 		/* Check to see if we've tried the same voltage 5 times */
 		if ((intel_dp->train_set[0] & DP_TRAIN_VOLTAGE_SWING_MASK) == voltage) {
-			++tries;
-			if (tries == 5)
+			++voltage_tries;
+			if (voltage_tries == 5) {
+				DRM_DEBUG_KMS("too many voltage retries, give up\n");
 				break;
+			}
 		} else
-			tries = 0;
+			voltage_tries = 0;
 		voltage = intel_dp->train_set[0] & DP_TRAIN_VOLTAGE_SWING_MASK;
 
 		/* Compute new intel_dp->train_set as requested by target */
-		intel_get_adjust_train(intel_dp);
+		intel_get_adjust_train(intel_dp, link_status);
 	}
 
 	intel_dp->DP = DP;
@@ -1638,6 +1695,7 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 	for (;;) {
 		/* Use intel_dp->train_set[0] to set the voltage and pre emphasis values */
 		uint32_t    signal_levels;
+		uint8_t	    link_status[DP_LINK_STATUS_SIZE];
 
 		if (cr_tries > 5) {
 			DRM_ERROR("failed to train DP, aborting\n");
@@ -1645,11 +1703,11 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 			break;
 		}
 
-		if (IS_GEN6(dev) && is_edp(intel_dp)) {
+		if (IS_GEN6(dev) && is_cpu_edp(intel_dp)) {
 			signal_levels = intel_gen6_edp_signal_levels(intel_dp->train_set[0]);
 			DP = (DP & ~EDP_LINK_TRAIN_VOL_EMP_MASK_SNB) | signal_levels;
 		} else {
-			signal_levels = intel_dp_signal_levels(intel_dp->train_set[0], intel_dp->lane_count);
+			signal_levels = intel_dp_signal_levels(intel_dp->train_set[0]);
 			DP = (DP & ~(DP_VOLTAGE_MASK|DP_PRE_EMPHASIS_MASK)) | signal_levels;
 		}
 
@@ -1665,17 +1723,17 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 			break;
 
 		udelay(400);
-		if (!intel_dp_get_link_status(intel_dp))
+		if (!intel_dp_get_link_status(intel_dp, link_status))
 			break;
 
 		/* Make sure clock is still ok */
-		if (!intel_clock_recovery_ok(intel_dp->link_status, intel_dp->lane_count)) {
+		if (!intel_clock_recovery_ok(link_status, intel_dp->lane_count)) {
 			intel_dp_start_link_train(intel_dp);
 			cr_tries++;
 			continue;
 		}
 
-		if (intel_channel_eq_ok(intel_dp)) {
+		if (intel_channel_eq_ok(intel_dp, link_status)) {
 			channel_eq = true;
 			break;
 		}
@@ -1690,7 +1748,7 @@ intel_dp_complete_link_train(struct intel_dp *intel_dp)
 		}
 
 		/* Compute new intel_dp->train_set as requested by target */
-		intel_get_adjust_train(intel_dp);
+		intel_get_adjust_train(intel_dp, link_status);
 		++tries;
 	}
 
@@ -1735,8 +1793,12 @@ intel_dp_link_down(struct intel_dp *intel_dp)
 
 	msleep(17);
 
-	if (is_edp(intel_dp))
-		DP |= DP_LINK_TRAIN_OFF;
+	if (is_edp(intel_dp)) {
+		if (HAS_PCH_CPT(dev) && !is_cpu_edp(intel_dp))
+			DP |= DP_LINK_TRAIN_OFF_CPT;
+		else
+			DP |= DP_LINK_TRAIN_OFF;
+	}
 
 	if (!HAS_PCH_CPT(dev) &&
 	    I915_READ(intel_dp->output_reg) & DP_PIPEB_SELECT) {
@@ -1822,6 +1884,7 @@ static void
 intel_dp_check_link_status(struct intel_dp *intel_dp)
 {
 	u8 sink_irq_vector;
+	u8 link_status[DP_LINK_STATUS_SIZE];
 
 	if (intel_dp->dpms_mode != DRM_MODE_DPMS_ON)
 		return;
@@ -1830,7 +1893,7 @@ intel_dp_check_link_status(struct intel_dp *intel_dp)
 		return;
 
 	/* Try to read receiver status if the link appears to be up */
-	if (!intel_dp_get_link_status(intel_dp)) {
+	if (!intel_dp_get_link_status(intel_dp, link_status)) {
 		intel_dp_link_down(intel_dp);
 		return;
 	}
@@ -1855,7 +1918,7 @@ intel_dp_check_link_status(struct intel_dp *intel_dp)
 			DRM_DEBUG_DRIVER("CP or sink specific irq unhandled\n");
 	}
 
-	if (!intel_channel_eq_ok(intel_dp)) {
+	if (!intel_channel_eq_ok(intel_dp, link_status)) {
 		DRM_DEBUG_KMS("%s: channel EQ not ok, retraining\n",
 			      drm_get_encoder_name(&intel_dp->base.base));
 		intel_dp_start_link_train(intel_dp);
@@ -2179,7 +2242,8 @@ intel_trans_dp_port_sel(struct drm_crtc *crtc)
 			continue;
 
 		intel_dp = enc_to_intel_dp(encoder);
-		if (intel_dp->base.type == INTEL_OUTPUT_DISPLAYPORT)
+		if (intel_dp->base.type == INTEL_OUTPUT_DISPLAYPORT ||
+		    intel_dp->base.type == INTEL_OUTPUT_EDP)
 			return intel_dp->output_reg;
 	}
 
@@ -2321,7 +2385,7 @@ intel_dp_init(struct drm_device *dev, int output_reg)
 
 		cur.t8 = (pp_on & PANEL_LIGHT_ON_DELAY_MASK) >>
 			PANEL_LIGHT_ON_DELAY_SHIFT;
-		
+
 		cur.t9 = (pp_off & PANEL_LIGHT_OFF_DELAY_MASK) >>
 			PANEL_LIGHT_OFF_DELAY_SHIFT;
 
@@ -2354,11 +2418,10 @@ intel_dp_init(struct drm_device *dev, int output_reg)
 		DRM_DEBUG_KMS("backlight on delay %d, off delay %d\n",
 			      intel_dp->backlight_on_delay, intel_dp->backlight_off_delay);
 
-		intel_dp->panel_off_jiffies = jiffies - intel_dp->panel_power_down_delay;
-
 		ironlake_edp_panel_vdd_on(intel_dp);
 		ret = intel_dp_get_dpcd(intel_dp);
 		ironlake_edp_panel_vdd_off(intel_dp, false);
+
 		if (ret) {
 			if (intel_dp->dpcd[DP_DPCD_REV] >= 0x11)
 				dev_priv->no_aux_handshake =
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 499d4c0..21f60b7 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -326,7 +326,8 @@ static int intel_panel_update_status(struct backlight_device *bd)
 static int intel_panel_get_brightness(struct backlight_device *bd)
 {
 	struct drm_device *dev = bl_get_data(bd);
-	return intel_panel_get_backlight(dev);
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	return dev_priv->backlight_level;
 }
 
 static const struct backlight_ops intel_panel_bl_ops = {
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index ddbabef..b12fd2c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -369,3 +369,48 @@ nouveau_finish_page_flip(struct nouveau_channel *chan,
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 	return 0;
 }
+
+int
+nouveau_display_dumb_create(struct drm_file *file_priv, struct drm_device *dev,
+			    struct drm_mode_create_dumb *args)
+{
+	struct nouveau_bo *bo;
+	int ret;
+
+	args->pitch = roundup(args->width * (args->bpp / 8), 256);
+	args->size = args->pitch * args->height;
+	args->size = roundup(args->size, PAGE_SIZE);
+
+	ret = nouveau_gem_new(dev, args->size, 0, TTM_PL_FLAG_VRAM, 0, 0, &bo);
+	if (ret)
+		return ret;
+
+	ret = drm_gem_handle_create(file_priv, bo->gem, &args->handle);
+	drm_gem_object_unreference_unlocked(bo->gem);
+	return ret;
+}
+
+int
+nouveau_display_dumb_destroy(struct drm_file *file_priv, struct drm_device *dev,
+			     uint32_t handle)
+{
+	return drm_gem_handle_delete(file_priv, handle);
+}
+
+int
+nouveau_display_dumb_map_offset(struct drm_file *file_priv,
+				struct drm_device *dev,
+				uint32_t handle, uint64_t *poffset)
+{
+	struct drm_gem_object *gem;
+
+	gem = drm_gem_object_lookup(dev, file_priv, handle);
+	if (gem) {
+		struct nouveau_bo *bo = gem->driver_private;
+		*poffset = bo->bo.addr_space_offset;
+		drm_gem_object_unreference_unlocked(gem);
+		return 0;
+	}
+
+	return -ENOENT;
+}
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.c b/drivers/gpu/drm/nouveau/nouveau_drv.c
index 9f7bb12..9791d13 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.c
@@ -433,6 +433,10 @@ static struct drm_driver driver = {
 	.gem_open_object = nouveau_gem_object_open,
 	.gem_close_object = nouveau_gem_object_close,
 
+	.dumb_create = nouveau_display_dumb_create,
+	.dumb_map_offset = nouveau_display_dumb_map_offset,
+	.dumb_destroy = nouveau_display_dumb_destroy,
+
 	.name = DRIVER_NAME,
 	.desc = DRIVER_DESC,
 #ifdef GIT_REVISION
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index 29837da..4c0be3a 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -1418,6 +1418,12 @@ int nouveau_crtc_page_flip(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 			   struct drm_pending_vblank_event *event);
 int nouveau_finish_page_flip(struct nouveau_channel *,
 			     struct nouveau_page_flip_state *);
+int nouveau_display_dumb_create(struct drm_file *, struct drm_device *,
+				struct drm_mode_create_dumb *args);
+int nouveau_display_dumb_map_offset(struct drm_file *, struct drm_device *,
+				    uint32_t handle, uint64_t *offset);
+int nouveau_display_dumb_destroy(struct drm_file *, struct drm_device *,
+				 uint32_t handle);
 
 /* nv10_gpio.c */
 int nv10_gpio_get(struct drm_device *dev, enum dcb_gpio_tag tag);
diff --git a/drivers/gpu/drm/nouveau/nouveau_object.c b/drivers/gpu/drm/nouveau/nouveau_object.c
index 02222c5..960c0ae 100644
--- a/drivers/gpu/drm/nouveau/nouveau_object.c
+++ b/drivers/gpu/drm/nouveau/nouveau_object.c
@@ -680,7 +680,7 @@ nouveau_gpuobj_channel_init_pramin(struct nouveau_channel *chan)
 		return ret;
 	}
 
-	ret = drm_mm_init(&chan->ramin_heap, base, size);
+	ret = drm_mm_init(&chan->ramin_heap, base, size - base);
 	if (ret) {
 		NV_ERROR(dev, "Error creating PRAMIN heap: %d\n", ret);
 		nouveau_gpuobj_ref(NULL, &chan->ramin);
diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
index b75258a..c8a463b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
@@ -67,7 +67,10 @@ nouveau_sgdma_clear(struct ttm_backend *be)
 			pci_unmap_page(dev->pdev, nvbe->pages[nvbe->nr_pages],
 				       PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
 		}
+		nvbe->unmap_pages = false;
 	}
+
+	nvbe->pages = NULL;
 }
 
 static void
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index d23ca00..06de250 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -616,7 +616,7 @@ nv50_display_unk10_handler(struct drm_device *dev)
 	struct drm_nouveau_private *dev_priv = dev->dev_private;
 	struct nv50_display *disp = nv50_display(dev);
 	u32 unk30 = nv_rd32(dev, 0x610030), mc;
-	int i, crtc, or, type = OUTPUT_ANY;
+	int i, crtc, or = 0, type = OUTPUT_ANY;
 
 	NV_DEBUG_KMS(dev, "0x610030: 0x%08x\n", unk30);
 	disp->irq.dcb = NULL;
@@ -708,7 +708,7 @@ nv50_display_unk20_handler(struct drm_device *dev)
 	struct nv50_display *disp = nv50_display(dev);
 	u32 unk30 = nv_rd32(dev, 0x610030), tmp, pclk, script, mc = 0;
 	struct dcb_entry *dcb;
-	int i, crtc, or, type = OUTPUT_ANY;
+	int i, crtc, or = 0, type = OUTPUT_ANY;
 
 	NV_DEBUG_KMS(dev, "0x610030: 0x%08x\n", unk30);
 	dcb = disp->irq.dcb;
diff --git a/drivers/gpu/drm/nouveau/nvc0_graph.c b/drivers/gpu/drm/nouveau/nvc0_graph.c
index a74e501..ecfafd7 100644
--- a/drivers/gpu/drm/nouveau/nvc0_graph.c
+++ b/drivers/gpu/drm/nouveau/nvc0_graph.c
@@ -381,6 +381,8 @@ nvc0_graph_init_gpc_0(struct drm_device *dev)
 	u8  tpnr[GPC_MAX];
 	int i, gpc, tpc;
 
+	nv_wr32(dev, TP_UNIT(0, 0, 0x5c), 1); /* affects TFB offset queries */
+
 	/*
 	 *      TP      ROP UNKVAL(magic_not_rop_nr)
 	 * 450: 4/0/0/0 2        3
diff --git a/drivers/gpu/drm/nouveau/nvd0_display.c b/drivers/gpu/drm/nouveau/nvd0_display.c
index 23d63b4..cb006a7 100644
--- a/drivers/gpu/drm/nouveau/nvd0_display.c
+++ b/drivers/gpu/drm/nouveau/nvd0_display.c
@@ -780,7 +780,7 @@ nvd0_sor_dpms(struct drm_encoder *encoder, int mode)
 			continue;
 
 		if (nv_partner != nv_encoder &&
-		    nv_partner->dcb->or == nv_encoder->or) {
+		    nv_partner->dcb->or == nv_encoder->dcb->or) {
 			if (nv_partner->last_dpms == DRM_MODE_DPMS_ON)
 				return;
 			break;
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index 87631fe..2b97262 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1107,9 +1107,40 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 		return -EINVAL;
 	}
 
-	if (tiling_flags & RADEON_TILING_MACRO)
+	if (tiling_flags & RADEON_TILING_MACRO) {
+		if (rdev->family >= CHIP_CAYMAN)
+			tmp = rdev->config.cayman.tile_config;
+		else
+			tmp = rdev->config.evergreen.tile_config;
+
+		switch ((tmp & 0xf0) >> 4) {
+		case 0: /* 4 banks */
+			fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_4_BANK);
+			break;
+		case 1: /* 8 banks */
+		default:
+			fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_8_BANK);
+			break;
+		case 2: /* 16 banks */
+			fb_format |= EVERGREEN_GRPH_NUM_BANKS(EVERGREEN_ADDR_SURF_16_BANK);
+			break;
+		}
+
+		switch ((tmp & 0xf000) >> 12) {
+		case 0: /* 1KB rows */
+		default:
+			fb_format |= EVERGREEN_GRPH_TILE_SPLIT(EVERGREEN_ADDR_SURF_TILE_SPLIT_1KB);
+			break;
+		case 1: /* 2KB rows */
+			fb_format |= EVERGREEN_GRPH_TILE_SPLIT(EVERGREEN_ADDR_SURF_TILE_SPLIT_2KB);
+			break;
+		case 2: /* 4KB rows */
+			fb_format |= EVERGREEN_GRPH_TILE_SPLIT(EVERGREEN_ADDR_SURF_TILE_SPLIT_4KB);
+			break;
+		}
+
 		fb_format |= EVERGREEN_GRPH_ARRAY_MODE(EVERGREEN_GRPH_ARRAY_2D_TILED_THIN1);
-	else if (tiling_flags & RADEON_TILING_MICRO)
+	} else if (tiling_flags & RADEON_TILING_MICRO)
 		fb_format |= EVERGREEN_GRPH_ARRAY_MODE(EVERGREEN_GRPH_ARRAY_1D_TILED_THIN1);
 
 	switch (radeon_crtc->crtc_id) {
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 1d603a3..5e00d16 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -82,6 +82,7 @@ u32 evergreen_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
 	u32 tmp = RREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset);
+	int i;
 
 	/* Lock the graphics update lock */
 	tmp |= EVERGREEN_GRPH_UPDATE_LOCK;
@@ -99,7 +100,11 @@ u32 evergreen_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 	       (u32)crtc_base);
 
 	/* Wait for update_pending to go high. */
-	while (!(RREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset) & EVERGREEN_GRPH_SURFACE_UPDATE_PENDING));
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if (RREG32(EVERGREEN_GRPH_UPDATE + radeon_crtc->crtc_offset) & EVERGREEN_GRPH_SURFACE_UPDATE_PENDING)
+			break;
+		udelay(1);
+	}
 	DRM_DEBUG("Update pending now high. Unlocking vupdate_lock.\n");
 
 	/* Unlock the lock, so double-buffering can take place inside vblank */
diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
index 7fdfa8e..cd4590a 100644
--- a/drivers/gpu/drm/radeon/evergreen_cs.c
+++ b/drivers/gpu/drm/radeon/evergreen_cs.c
@@ -38,6 +38,7 @@ struct evergreen_cs_track {
 	u32			group_size;
 	u32			nbanks;
 	u32			npipes;
+	u32			row_size;
 	/* value we track */
 	u32			nsamples;
 	u32			cb_color_base_last[12];
@@ -77,6 +78,44 @@ struct evergreen_cs_track {
 	struct radeon_bo	*db_s_write_bo;
 };
 
+static u32 evergreen_cs_get_aray_mode(u32 tiling_flags)
+{
+	if (tiling_flags & RADEON_TILING_MACRO)
+		return ARRAY_2D_TILED_THIN1;
+	else if (tiling_flags & RADEON_TILING_MICRO)
+		return ARRAY_1D_TILED_THIN1;
+	else
+		return ARRAY_LINEAR_GENERAL;
+}
+
+static u32 evergreen_cs_get_num_banks(u32 nbanks)
+{
+	switch (nbanks) {
+	case 2:
+		return ADDR_SURF_2_BANK;
+	case 4:
+		return ADDR_SURF_4_BANK;
+	case 8:
+	default:
+		return ADDR_SURF_8_BANK;
+	case 16:
+		return ADDR_SURF_16_BANK;
+	}
+}
+
+static u32 evergreen_cs_get_tile_split(u32 row_size)
+{
+	switch (row_size) {
+	case 1:
+	default:
+		return ADDR_SURF_TILE_SPLIT_1KB;
+	case 2:
+		return ADDR_SURF_TILE_SPLIT_2KB;
+	case 4:
+		return ADDR_SURF_TILE_SPLIT_4KB;
+	}
+}
+
 static void evergreen_cs_track_init(struct evergreen_cs_track *track)
 {
 	int i;
@@ -480,21 +519,22 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		}
 		break;
 	case DB_Z_INFO:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
-		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
-			return -EINVAL;
-		}
 		track->db_z_info = radeon_get_ib_value(p, idx);
-		ib[idx] &= ~Z_ARRAY_MODE(0xf);
-		track->db_z_info &= ~Z_ARRAY_MODE(0xf);
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
-			ib[idx] |= Z_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-			track->db_z_info |= Z_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-		} else {
-			ib[idx] |= Z_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
-			track->db_z_info |= Z_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+		if (!p->keep_tiling_flags) {
+			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			if (r) {
+				dev_warn(p->dev, "bad SET_CONTEXT_REG "
+						"0x%04X\n", reg);
+				return -EINVAL;
+			}
+			ib[idx] &= ~Z_ARRAY_MODE(0xf);
+			track->db_z_info &= ~Z_ARRAY_MODE(0xf);
+			ib[idx] |= Z_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+			track->db_z_info |= Z_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+				ib[idx] |= DB_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
+				ib[idx] |= DB_TILE_SPLIT(evergreen_cs_get_tile_split(track->row_size));
+			}
 		}
 		break;
 	case DB_STENCIL_INFO:
@@ -607,40 +647,34 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR5_INFO:
 	case CB_COLOR6_INFO:
 	case CB_COLOR7_INFO:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
-		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
-			return -EINVAL;
-		}
 		tmp = (reg - CB_COLOR0_INFO) / 0x3c;
 		track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
-			ib[idx] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-			track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-		} else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
-			ib[idx] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
-			track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+		if (!p->keep_tiling_flags) {
+			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			if (r) {
+				dev_warn(p->dev, "bad SET_CONTEXT_REG "
+						"0x%04X\n", reg);
+				return -EINVAL;
+			}
+			ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+			track->cb_color_info[tmp] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
 		}
 		break;
 	case CB_COLOR8_INFO:
 	case CB_COLOR9_INFO:
 	case CB_COLOR10_INFO:
 	case CB_COLOR11_INFO:
-		r = evergreen_cs_packet_next_reloc(p, &reloc);
-		if (r) {
-			dev_warn(p->dev, "bad SET_CONTEXT_REG "
-					"0x%04X\n", reg);
-			return -EINVAL;
-		}
 		tmp = ((reg - CB_COLOR8_INFO) / 0x1c) + 8;
 		track->cb_color_info[tmp] = radeon_get_ib_value(p, idx);
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
-			ib[idx] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-			track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-		} else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO) {
-			ib[idx] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
-			track->cb_color_info[tmp] |= CB_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+		if (!p->keep_tiling_flags) {
+			r = evergreen_cs_packet_next_reloc(p, &reloc);
+			if (r) {
+				dev_warn(p->dev, "bad SET_CONTEXT_REG "
+						"0x%04X\n", reg);
+				return -EINVAL;
+			}
+			ib[idx] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+			track->cb_color_info[tmp] |= CB_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
 		}
 		break;
 	case CB_COLOR0_PITCH:
@@ -695,6 +729,16 @@ static int evergreen_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case CB_COLOR9_ATTRIB:
 	case CB_COLOR10_ATTRIB:
 	case CB_COLOR11_ATTRIB:
+		r = evergreen_cs_packet_next_reloc(p, &reloc);
+		if (r) {
+			dev_warn(p->dev, "bad SET_CONTEXT_REG "
+					"0x%04X\n", reg);
+			return -EINVAL;
+		}
+		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+			ib[idx] |= CB_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
+			ib[idx] |= CB_TILE_SPLIT(evergreen_cs_get_tile_split(track->row_size));
+		}
 		break;
 	case CB_COLOR0_DIM:
 	case CB_COLOR1_DIM:
@@ -1311,10 +1355,16 @@ static int evergreen_packet3_check(struct radeon_cs_parser *p,
 					return -EINVAL;
 				}
 				ib[idx+1+(i*8)+2] += (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
-				if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
-					ib[idx+1+(i*8)+1] |= TEX_ARRAY_MODE(ARRAY_2D_TILED_THIN1);
-				else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
-					ib[idx+1+(i*8)+1] |= TEX_ARRAY_MODE(ARRAY_1D_TILED_THIN1);
+				if (!p->keep_tiling_flags) {
+					ib[idx+1+(i*8)+1] |=
+						TEX_ARRAY_MODE(evergreen_cs_get_aray_mode(reloc->lobj.tiling_flags));
+					if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO) {
+						ib[idx+1+(i*8)+6] |=
+							TEX_TILE_SPLIT(evergreen_cs_get_tile_split(track->row_size));
+						ib[idx+1+(i*8)+7] |=
+							TEX_NUM_BANKS(evergreen_cs_get_num_banks(track->nbanks));
+					}
+				}
 				texture = reloc->robj;
 				/* tex mip base */
 				r = evergreen_cs_packet_next_reloc(p, &reloc);
@@ -1414,6 +1464,7 @@ int evergreen_cs_parse(struct radeon_cs_parser *p)
 {
 	struct radeon_cs_packet pkt;
 	struct evergreen_cs_track *track;
+	u32 tmp;
 	int r;
 
 	if (p->track == NULL) {
@@ -1422,9 +1473,63 @@ int evergreen_cs_parse(struct radeon_cs_parser *p)
 		if (track == NULL)
 			return -ENOMEM;
 		evergreen_cs_track_init(track);
-		track->npipes = p->rdev->config.evergreen.tiling_npipes;
-		track->nbanks = p->rdev->config.evergreen.tiling_nbanks;
-		track->group_size = p->rdev->config.evergreen.tiling_group_size;
+		if (p->rdev->family >= CHIP_CAYMAN)
+			tmp = p->rdev->config.cayman.tile_config;
+		else
+			tmp = p->rdev->config.evergreen.tile_config;
+
+		switch (tmp & 0xf) {
+		case 0:
+			track->npipes = 1;
+			break;
+		case 1:
+		default:
+			track->npipes = 2;
+			break;
+		case 2:
+			track->npipes = 4;
+			break;
+		case 3:
+			track->npipes = 8;
+			break;
+		}
+
+		switch ((tmp & 0xf0) >> 4) {
+		case 0:
+			track->nbanks = 4;
+			break;
+		case 1:
+		default:
+			track->nbanks = 8;
+			break;
+		case 2:
+			track->nbanks = 16;
+			break;
+		}
+
+		switch ((tmp & 0xf00) >> 8) {
+		case 0:
+			track->group_size = 256;
+			break;
+		case 1:
+		default:
+			track->group_size = 512;
+			break;
+		}
+
+		switch ((tmp & 0xf000) >> 12) {
+		case 0:
+			track->row_size = 1;
+			break;
+		case 1:
+		default:
+			track->row_size = 2;
+			break;
+		case 2:
+			track->row_size = 4;
+			break;
+		}
+
 		p->track = track;
 	}
 	do {
diff --git a/drivers/gpu/drm/radeon/evergreen_reg.h b/drivers/gpu/drm/radeon/evergreen_reg.h
index c781c92..7d7f215 100644
--- a/drivers/gpu/drm/radeon/evergreen_reg.h
+++ b/drivers/gpu/drm/radeon/evergreen_reg.h
@@ -42,6 +42,17 @@
 #       define EVERGREEN_GRPH_DEPTH_8BPP                0
 #       define EVERGREEN_GRPH_DEPTH_16BPP               1
 #       define EVERGREEN_GRPH_DEPTH_32BPP               2
+#       define EVERGREEN_GRPH_NUM_BANKS(x)              (((x) & 0x3) << 2)
+#       define EVERGREEN_ADDR_SURF_2_BANK               0
+#       define EVERGREEN_ADDR_SURF_4_BANK               1
+#       define EVERGREEN_ADDR_SURF_8_BANK               2
+#       define EVERGREEN_ADDR_SURF_16_BANK              3
+#       define EVERGREEN_GRPH_Z(x)                      (((x) & 0x3) << 4)
+#       define EVERGREEN_GRPH_BANK_WIDTH(x)             (((x) & 0x3) << 6)
+#       define EVERGREEN_ADDR_SURF_BANK_WIDTH_1         0
+#       define EVERGREEN_ADDR_SURF_BANK_WIDTH_2         1
+#       define EVERGREEN_ADDR_SURF_BANK_WIDTH_4         2
+#       define EVERGREEN_ADDR_SURF_BANK_WIDTH_8         3
 #       define EVERGREEN_GRPH_FORMAT(x)                 (((x) & 0x7) << 8)
 /* 8 BPP */
 #       define EVERGREEN_GRPH_FORMAT_INDEXED            0
@@ -61,6 +72,24 @@
 #       define EVERGREEN_GRPH_FORMAT_8B_BGRA1010102     5
 #       define EVERGREEN_GRPH_FORMAT_RGB111110          6
 #       define EVERGREEN_GRPH_FORMAT_BGR101111          7
+#       define EVERGREEN_GRPH_BANK_HEIGHT(x)            (((x) & 0x3) << 11)
+#       define EVERGREEN_ADDR_SURF_BANK_HEIGHT_1        0
+#       define EVERGREEN_ADDR_SURF_BANK_HEIGHT_2        1
+#       define EVERGREEN_ADDR_SURF_BANK_HEIGHT_4        2
+#       define EVERGREEN_ADDR_SURF_BANK_HEIGHT_8        3
+#       define EVERGREEN_GRPH_TILE_SPLIT(x)             (((x) & 0x7) << 13)
+#       define EVERGREEN_ADDR_SURF_TILE_SPLIT_64B       0
+#       define EVERGREEN_ADDR_SURF_TILE_SPLIT_128B      1
+#       define EVERGREEN_ADDR_SURF_TILE_SPLIT_256B      2
+#       define EVERGREEN_ADDR_SURF_TILE_SPLIT_512B      3
+#       define EVERGREEN_ADDR_SURF_TILE_SPLIT_1KB       4
+#       define EVERGREEN_ADDR_SURF_TILE_SPLIT_2KB       5
+#       define EVERGREEN_ADDR_SURF_TILE_SPLIT_4KB       6
+#       define EVERGREEN_GRPH_MACRO_TILE_ASPECT(x)      (((x) & 0x3) << 18)
+#       define EVERGREEN_ADDR_SURF_MACRO_TILE_ASPECT_1  0
+#       define EVERGREEN_ADDR_SURF_MACRO_TILE_ASPECT_2  1
+#       define EVERGREEN_ADDR_SURF_MACRO_TILE_ASPECT_4  2
+#       define EVERGREEN_ADDR_SURF_MACRO_TILE_ASPECT_8  3
 #       define EVERGREEN_GRPH_ARRAY_MODE(x)             (((x) & 0x7) << 20)
 #       define EVERGREEN_GRPH_ARRAY_LINEAR_GENERAL      0
 #       define EVERGREEN_GRPH_ARRAY_LINEAR_ALIGNED      1
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index b937c49..e00039e 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -899,6 +899,10 @@
 #define DB_HTILE_DATA_BASE				0x28014
 #define DB_Z_INFO					0x28040
 #       define Z_ARRAY_MODE(x)                          ((x) << 4)
+#       define DB_TILE_SPLIT(x)                         (((x) & 0x7) << 8)
+#       define DB_NUM_BANKS(x)                          (((x) & 0x3) << 12)
+#       define DB_BANK_WIDTH(x)                         (((x) & 0x3) << 16)
+#       define DB_BANK_HEIGHT(x)                        (((x) & 0x3) << 20)
 #define DB_STENCIL_INFO					0x28044
 #define DB_Z_READ_BASE					0x28048
 #define DB_STENCIL_READ_BASE				0x2804c
@@ -951,6 +955,29 @@
 #	define CB_SF_EXPORT_FULL			0
 #	define CB_SF_EXPORT_NORM			1
 #define	CB_COLOR0_ATTRIB				0x28c74
+#       define CB_TILE_SPLIT(x)                         (((x) & 0x7) << 5)
+#       define ADDR_SURF_TILE_SPLIT_64B                 0
+#       define ADDR_SURF_TILE_SPLIT_128B                1
+#       define ADDR_SURF_TILE_SPLIT_256B                2
+#       define ADDR_SURF_TILE_SPLIT_512B                3
+#       define ADDR_SURF_TILE_SPLIT_1KB                 4
+#       define ADDR_SURF_TILE_SPLIT_2KB                 5
+#       define ADDR_SURF_TILE_SPLIT_4KB                 6
+#       define CB_NUM_BANKS(x)                          (((x) & 0x3) << 10)
+#       define ADDR_SURF_2_BANK                         0
+#       define ADDR_SURF_4_BANK                         1
+#       define ADDR_SURF_8_BANK                         2
+#       define ADDR_SURF_16_BANK                        3
+#       define CB_BANK_WIDTH(x)                         (((x) & 0x3) << 13)
+#       define ADDR_SURF_BANK_WIDTH_1                   0
+#       define ADDR_SURF_BANK_WIDTH_2                   1
+#       define ADDR_SURF_BANK_WIDTH_4                   2
+#       define ADDR_SURF_BANK_WIDTH_8                   3
+#       define CB_BANK_HEIGHT(x)                        (((x) & 0x3) << 16)
+#       define ADDR_SURF_BANK_HEIGHT_1                  0
+#       define ADDR_SURF_BANK_HEIGHT_2                  1
+#       define ADDR_SURF_BANK_HEIGHT_4                  2
+#       define ADDR_SURF_BANK_HEIGHT_8                  3
 #define	CB_COLOR0_DIM					0x28c78
 /* only CB0-7 blocks have these regs */
 #define	CB_COLOR0_CMASK					0x28c7c
@@ -1137,7 +1164,11 @@
 #	define SQ_SEL_1					5
 #define SQ_TEX_RESOURCE_WORD5_0                         0x30014
 #define SQ_TEX_RESOURCE_WORD6_0                         0x30018
+#       define TEX_TILE_SPLIT(x)                        (((x) & 0x7) << 29)
 #define SQ_TEX_RESOURCE_WORD7_0                         0x3001c
+#       define TEX_BANK_WIDTH(x)                        (((x) & 0x3) << 8)
+#       define TEX_BANK_HEIGHT(x)                       (((x) & 0x3) << 10)
+#       define TEX_NUM_BANKS(x)                         (((x) & 0x3) << 16)
 
 #define SQ_VTX_CONSTANT_WORD0_0				0x30000
 #define SQ_VTX_CONSTANT_WORD1_0				0x30004
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index ad158ea..bfc08f6 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -187,13 +187,18 @@ u32 r100_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
 	u32 tmp = ((u32)crtc_base) | RADEON_CRTC_OFFSET__OFFSET_LOCK;
+	int i;
 
 	/* Lock the graphics update lock */
 	/* update the scanout addresses */
 	WREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset, tmp);
 
 	/* Wait for update_pending to go high. */
-	while (!(RREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset) & RADEON_CRTC_OFFSET__GUI_TRIG_OFFSET));
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if (RREG32(RADEON_CRTC_OFFSET + radeon_crtc->crtc_offset) & RADEON_CRTC_OFFSET__GUI_TRIG_OFFSET)
+			break;
+		udelay(1);
+	}
 	DRM_DEBUG("Update pending now high. Unlocking vupdate_lock.\n");
 
 	/* Unlock the lock, so double-buffering can take place inside vblank */
diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 400b26d..c93bc64 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -701,16 +701,21 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 			return r;
 		}
 
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
-			tile_flags |= R300_TXO_MACRO_TILE;
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
-			tile_flags |= R300_TXO_MICRO_TILE;
-		else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
-			tile_flags |= R300_TXO_MICRO_TILE_SQUARE;
-
-		tmp = idx_value + ((u32)reloc->lobj.gpu_offset);
-		tmp |= tile_flags;
-		ib[idx] = tmp;
+		if (p->keep_tiling_flags) {
+			ib[idx] = (idx_value & 31) | /* keep the 1st 5 bits */
+				  ((idx_value & ~31) + (u32)reloc->lobj.gpu_offset);
+		} else {
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+				tile_flags |= R300_TXO_MACRO_TILE;
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+				tile_flags |= R300_TXO_MICRO_TILE;
+			else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
+				tile_flags |= R300_TXO_MICRO_TILE_SQUARE;
+
+			tmp = idx_value + ((u32)reloc->lobj.gpu_offset);
+			tmp |= tile_flags;
+			ib[idx] = tmp;
+		}
 		track->textures[i].robj = reloc->robj;
 		track->tex_dirty = true;
 		break;
@@ -760,24 +765,26 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		/* RB3D_COLORPITCH1 */
 		/* RB3D_COLORPITCH2 */
 		/* RB3D_COLORPITCH3 */
-		r = r100_cs_packet_next_reloc(p, &reloc);
-		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
-			return r;
-		}
+		if (!p->keep_tiling_flags) {
+			r = r100_cs_packet_next_reloc(p, &reloc);
+			if (r) {
+				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
+					  idx, reg);
+				r100_cs_dump_packet(p, pkt);
+				return r;
+			}
 
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
-			tile_flags |= R300_COLOR_TILE_ENABLE;
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
-			tile_flags |= R300_COLOR_MICROTILE_ENABLE;
-		else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
-			tile_flags |= R300_COLOR_MICROTILE_SQUARE_ENABLE;
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+				tile_flags |= R300_COLOR_TILE_ENABLE;
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+				tile_flags |= R300_COLOR_MICROTILE_ENABLE;
+			else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
+				tile_flags |= R300_COLOR_MICROTILE_SQUARE_ENABLE;
 
-		tmp = idx_value & ~(0x7 << 16);
-		tmp |= tile_flags;
-		ib[idx] = tmp;
+			tmp = idx_value & ~(0x7 << 16);
+			tmp |= tile_flags;
+			ib[idx] = tmp;
+		}
 		i = (reg - 0x4E38) >> 2;
 		track->cb[i].pitch = idx_value & 0x3FFE;
 		switch (((idx_value >> 21) & 0xF)) {
@@ -843,25 +850,26 @@ static int r300_packet0_check(struct radeon_cs_parser *p,
 		break;
 	case 0x4F24:
 		/* ZB_DEPTHPITCH */
-		r = r100_cs_packet_next_reloc(p, &reloc);
-		if (r) {
-			DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
-				  idx, reg);
-			r100_cs_dump_packet(p, pkt);
-			return r;
-		}
-
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
-			tile_flags |= R300_DEPTHMACROTILE_ENABLE;
-		if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
-			tile_flags |= R300_DEPTHMICROTILE_TILED;
-		else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
-			tile_flags |= R300_DEPTHMICROTILE_TILED_SQUARE;
+		if (!p->keep_tiling_flags) {
+			r = r100_cs_packet_next_reloc(p, &reloc);
+			if (r) {
+				DRM_ERROR("No reloc for ib[%d]=0x%04X\n",
+					  idx, reg);
+				r100_cs_dump_packet(p, pkt);
+				return r;
+			}
 
-		tmp = idx_value & ~(0x7 << 16);
-		tmp |= tile_flags;
-		ib[idx] = tmp;
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+				tile_flags |= R300_DEPTHMACROTILE_ENABLE;
+			if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+				tile_flags |= R300_DEPTHMICROTILE_TILED;
+			else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO_SQUARE)
+				tile_flags |= R300_DEPTHMICROTILE_TILED_SQUARE;
 
+			tmp = idx_value & ~(0x7 << 16);
+			tmp |= tile_flags;
+			ib[idx] = tmp;
+		}
 		track->zb.pitch = idx_value & 0x3FFC;
 		track->zb_dirty = true;
 		break;
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index 0a2e023..cb1acff 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -941,7 +941,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 		track->db_depth_control = radeon_get_ib_value(p, idx);
 		break;
 	case R_028010_DB_DEPTH_INFO:
-		if (r600_cs_packet_next_is_pkt3_nop(p)) {
+		if (!p->keep_tiling_flags &&
+		    r600_cs_packet_next_is_pkt3_nop(p)) {
 			r = r600_cs_packet_next_reloc(p, &reloc);
 			if (r) {
 				dev_warn(p->dev, "bad SET_CONTEXT_REG "
@@ -992,7 +993,8 @@ static int r600_cs_check_reg(struct radeon_cs_parser *p, u32 reg, u32 idx)
 	case R_0280B4_CB_COLOR5_INFO:
 	case R_0280B8_CB_COLOR6_INFO:
 	case R_0280BC_CB_COLOR7_INFO:
-		if (r600_cs_packet_next_is_pkt3_nop(p)) {
+		if (!p->keep_tiling_flags &&
+		     r600_cs_packet_next_is_pkt3_nop(p)) {
 			r = r600_cs_packet_next_reloc(p, &reloc);
 			if (r) {
 				dev_err(p->dev, "bad SET_CONTEXT_REG 0x%04X\n", reg);
@@ -1291,10 +1293,12 @@ static int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 idx,
 	mip_offset <<= 8;
 
 	word0 = radeon_get_ib_value(p, idx + 0);
-	if (tiling_flags & RADEON_TILING_MACRO)
-		word0 |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
-	else if (tiling_flags & RADEON_TILING_MICRO)
-		word0 |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
+	if (!p->keep_tiling_flags) {
+		if (tiling_flags & RADEON_TILING_MACRO)
+			word0 |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
+		else if (tiling_flags & RADEON_TILING_MICRO)
+			word0 |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
+	}
 	word1 = radeon_get_ib_value(p, idx + 1);
 	w0 = G_038000_TEX_WIDTH(word0) + 1;
 	h0 = G_038004_TEX_HEIGHT(word1) + 1;
@@ -1621,10 +1625,12 @@ static int r600_packet3_check(struct radeon_cs_parser *p,
 					return -EINVAL;
 				}
 				base_offset = (u32)((reloc->lobj.gpu_offset >> 8) & 0xffffffff);
-				if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
-					ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
-				else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
-					ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
+				if (!p->keep_tiling_flags) {
+					if (reloc->lobj.tiling_flags & RADEON_TILING_MACRO)
+						ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_2D_TILED_THIN1);
+					else if (reloc->lobj.tiling_flags & RADEON_TILING_MICRO)
+						ib[idx+1+(i*7)+0] |= S_038000_TILE_MODE(V_038000_ARRAY_1D_TILED_THIN1);
+				}
 				texture = reloc->robj;
 				/* tex mip base */
 				r = r600_cs_packet_next_reloc(p, &reloc);
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index fc5a1d6..8227e76 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -611,7 +611,8 @@ struct radeon_cs_parser {
 	struct radeon_ib	*ib;
 	void			*track;
 	unsigned		family;
-	int parser_error;
+	int			parser_error;
+	bool			keep_tiling_flags;
 };
 
 extern int radeon_cs_update_pages(struct radeon_cs_parser *p, int pg_idx);
diff --git a/drivers/gpu/drm/radeon/radeon_acpi.c b/drivers/gpu/drm/radeon/radeon_acpi.c
index 3f6636b..3516a60 100644
--- a/drivers/gpu/drm/radeon/radeon_acpi.c
+++ b/drivers/gpu/drm/radeon/radeon_acpi.c
@@ -35,7 +35,8 @@ static int radeon_atif_call(acpi_handle handle)
 
 	/* Fail only if calling the method fails and ATIF is supported */
 	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
-		printk(KERN_DEBUG "failed to evaluate ATIF got %s\n", acpi_format_exception(status));
+		DRM_DEBUG_DRIVER("failed to evaluate ATIF got %s\n",
+				 acpi_format_exception(status));
 		kfree(buffer.pointer);
 		return 1;
 	}
@@ -50,13 +51,13 @@ int radeon_acpi_init(struct radeon_device *rdev)
 	acpi_handle handle;
 	int ret;
 
-	/* No need to proceed if we're sure that ATIF is not supported */
-	if (!ASIC_IS_AVIVO(rdev) || !rdev->bios)
-		return 0;
-
 	/* Get the device handle */
 	handle = DEVICE_ACPI_HANDLE(&rdev->pdev->dev);
 
+	/* No need to proceed if we're sure that ATIF is not supported */
+	if (!ASIC_IS_AVIVO(rdev) || !rdev->bios || !handle)
+		return 0;
+
 	/* Call the ATIF method */
 	ret = radeon_atif_call(handle);
 	if (ret)
diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
index d2d1792..d24baf3 100644
--- a/drivers/gpu/drm/radeon/radeon_atombios.c
+++ b/drivers/gpu/drm/radeon/radeon_atombios.c
@@ -62,6 +62,87 @@ union atom_supported_devices {
 	struct _ATOM_SUPPORTED_DEVICES_INFO_2d1 info_2d1;
 };
 
+static void radeon_lookup_i2c_gpio_quirks(struct radeon_device *rdev,
+					  ATOM_GPIO_I2C_ASSIGMENT *gpio,
+					  u8 index)
+{
+	/* r4xx mask is technically not used by the hw, so patch in the legacy mask bits */
+	if ((rdev->family == CHIP_R420) ||
+	    (rdev->family == CHIP_R423) ||
+	    (rdev->family == CHIP_RV410)) {
+		if ((le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x0018) ||
+		    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x0019) ||
+		    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x001a)) {
+			gpio->ucClkMaskShift = 0x19;
+			gpio->ucDataMaskShift = 0x18;
+		}
+	}
+
+	/* some evergreen boards have bad data for this entry */
+	if (ASIC_IS_DCE4(rdev)) {
+		if ((index == 7) &&
+		    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1936) &&
+		    (gpio->sucI2cId.ucAccess == 0)) {
+			gpio->sucI2cId.ucAccess = 0x97;
+			gpio->ucDataMaskShift = 8;
+			gpio->ucDataEnShift = 8;
+			gpio->ucDataY_Shift = 8;
+			gpio->ucDataA_Shift = 8;
+		}
+	}
+
+	/* some DCE3 boards have bad data for this entry */
+	if (ASIC_IS_DCE3(rdev)) {
+		if ((index == 4) &&
+		    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1fda) &&
+		    (gpio->sucI2cId.ucAccess == 0x94))
+			gpio->sucI2cId.ucAccess = 0x14;
+	}
+}
+
+static struct radeon_i2c_bus_rec radeon_get_bus_rec_for_i2c_gpio(ATOM_GPIO_I2C_ASSIGMENT *gpio)
+{
+	struct radeon_i2c_bus_rec i2c;
+
+	memset(&i2c, 0, sizeof(struct radeon_i2c_bus_rec));
+
+	i2c.mask_clk_reg = le16_to_cpu(gpio->usClkMaskRegisterIndex) * 4;
+	i2c.mask_data_reg = le16_to_cpu(gpio->usDataMaskRegisterIndex) * 4;
+	i2c.en_clk_reg = le16_to_cpu(gpio->usClkEnRegisterIndex) * 4;
+	i2c.en_data_reg = le16_to_cpu(gpio->usDataEnRegisterIndex) * 4;
+	i2c.y_clk_reg = le16_to_cpu(gpio->usClkY_RegisterIndex) * 4;
+	i2c.y_data_reg = le16_to_cpu(gpio->usDataY_RegisterIndex) * 4;
+	i2c.a_clk_reg = le16_to_cpu(gpio->usClkA_RegisterIndex) * 4;
+	i2c.a_data_reg = le16_to_cpu(gpio->usDataA_RegisterIndex) * 4;
+	i2c.mask_clk_mask = (1 << gpio->ucClkMaskShift);
+	i2c.mask_data_mask = (1 << gpio->ucDataMaskShift);
+	i2c.en_clk_mask = (1 << gpio->ucClkEnShift);
+	i2c.en_data_mask = (1 << gpio->ucDataEnShift);
+	i2c.y_clk_mask = (1 << gpio->ucClkY_Shift);
+	i2c.y_data_mask = (1 << gpio->ucDataY_Shift);
+	i2c.a_clk_mask = (1 << gpio->ucClkA_Shift);
+	i2c.a_data_mask = (1 << gpio->ucDataA_Shift);
+
+	if (gpio->sucI2cId.sbfAccess.bfHW_Capable)
+		i2c.hw_capable = true;
+	else
+		i2c.hw_capable = false;
+
+	if (gpio->sucI2cId.ucAccess == 0xa0)
+		i2c.mm_i2c = true;
+	else
+		i2c.mm_i2c = false;
+
+	i2c.i2c_id = gpio->sucI2cId.ucAccess;
+
+	if (i2c.mask_clk_reg)
+		i2c.valid = true;
+	else
+		i2c.valid = false;
+
+	return i2c;
+}
+
 static struct radeon_i2c_bus_rec radeon_lookup_i2c_gpio(struct radeon_device *rdev,
 							       uint8_t id)
 {
@@ -85,59 +166,10 @@ static struct radeon_i2c_bus_rec radeon_lookup_i2c_gpio(struct radeon_device *rd
 		for (i = 0; i < num_indices; i++) {
 			gpio = &i2c_info->asGPIO_Info[i];
 
-			/* some evergreen boards have bad data for this entry */
-			if (ASIC_IS_DCE4(rdev)) {
-				if ((i == 7) &&
-				    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1936) &&
-				    (gpio->sucI2cId.ucAccess == 0)) {
-					gpio->sucI2cId.ucAccess = 0x97;
-					gpio->ucDataMaskShift = 8;
-					gpio->ucDataEnShift = 8;
-					gpio->ucDataY_Shift = 8;
-					gpio->ucDataA_Shift = 8;
-				}
-			}
-
-			/* some DCE3 boards have bad data for this entry */
-			if (ASIC_IS_DCE3(rdev)) {
-				if ((i == 4) &&
-				    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1fda) &&
-				    (gpio->sucI2cId.ucAccess == 0x94))
-					gpio->sucI2cId.ucAccess = 0x14;
-			}
+			radeon_lookup_i2c_gpio_quirks(rdev, gpio, i);
 
 			if (gpio->sucI2cId.ucAccess == id) {
-				i2c.mask_clk_reg = le16_to_cpu(gpio->usClkMaskRegisterIndex) * 4;
-				i2c.mask_data_reg = le16_to_cpu(gpio->usDataMaskRegisterIndex) * 4;
-				i2c.en_clk_reg = le16_to_cpu(gpio->usClkEnRegisterIndex) * 4;
-				i2c.en_data_reg = le16_to_cpu(gpio->usDataEnRegisterIndex) * 4;
-				i2c.y_clk_reg = le16_to_cpu(gpio->usClkY_RegisterIndex) * 4;
-				i2c.y_data_reg = le16_to_cpu(gpio->usDataY_RegisterIndex) * 4;
-				i2c.a_clk_reg = le16_to_cpu(gpio->usClkA_RegisterIndex) * 4;
-				i2c.a_data_reg = le16_to_cpu(gpio->usDataA_RegisterIndex) * 4;
-				i2c.mask_clk_mask = (1 << gpio->ucClkMaskShift);
-				i2c.mask_data_mask = (1 << gpio->ucDataMaskShift);
-				i2c.en_clk_mask = (1 << gpio->ucClkEnShift);
-				i2c.en_data_mask = (1 << gpio->ucDataEnShift);
-				i2c.y_clk_mask = (1 << gpio->ucClkY_Shift);
-				i2c.y_data_mask = (1 << gpio->ucDataY_Shift);
-				i2c.a_clk_mask = (1 << gpio->ucClkA_Shift);
-				i2c.a_data_mask = (1 << gpio->ucDataA_Shift);
-
-				if (gpio->sucI2cId.sbfAccess.bfHW_Capable)
-					i2c.hw_capable = true;
-				else
-					i2c.hw_capable = false;
-
-				if (gpio->sucI2cId.ucAccess == 0xa0)
-					i2c.mm_i2c = true;
-				else
-					i2c.mm_i2c = false;
-
-				i2c.i2c_id = gpio->sucI2cId.ucAccess;
-
-				if (i2c.mask_clk_reg)
-					i2c.valid = true;
+				i2c = radeon_get_bus_rec_for_i2c_gpio(gpio);
 				break;
 			}
 		}
@@ -157,8 +189,6 @@ void radeon_atombios_i2c_init(struct radeon_device *rdev)
 	int i, num_indices;
 	char stmp[32];
 
-	memset(&i2c, 0, sizeof(struct radeon_i2c_bus_rec));
-
 	if (atom_parse_data_header(ctx, index, &size, NULL, NULL, &data_offset)) {
 		i2c_info = (struct _ATOM_GPIO_I2C_INFO *)(ctx->bios + data_offset);
 
@@ -167,60 +197,12 @@ void radeon_atombios_i2c_init(struct radeon_device *rdev)
 
 		for (i = 0; i < num_indices; i++) {
 			gpio = &i2c_info->asGPIO_Info[i];
-			i2c.valid = false;
-
-			/* some evergreen boards have bad data for this entry */
-			if (ASIC_IS_DCE4(rdev)) {
-				if ((i == 7) &&
-				    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1936) &&
-				    (gpio->sucI2cId.ucAccess == 0)) {
-					gpio->sucI2cId.ucAccess = 0x97;
-					gpio->ucDataMaskShift = 8;
-					gpio->ucDataEnShift = 8;
-					gpio->ucDataY_Shift = 8;
-					gpio->ucDataA_Shift = 8;
-				}
-			}
-
-			/* some DCE3 boards have bad data for this entry */
-			if (ASIC_IS_DCE3(rdev)) {
-				if ((i == 4) &&
-				    (le16_to_cpu(gpio->usClkMaskRegisterIndex) == 0x1fda) &&
-				    (gpio->sucI2cId.ucAccess == 0x94))
-					gpio->sucI2cId.ucAccess = 0x14;
-			}
 
-			i2c.mask_clk_reg = le16_to_cpu(gpio->usClkMaskRegisterIndex) * 4;
-			i2c.mask_data_reg = le16_to_cpu(gpio->usDataMaskRegisterIndex) * 4;
-			i2c.en_clk_reg = le16_to_cpu(gpio->usClkEnRegisterIndex) * 4;
-			i2c.en_data_reg = le16_to_cpu(gpio->usDataEnRegisterIndex) * 4;
-			i2c.y_clk_reg = le16_to_cpu(gpio->usClkY_RegisterIndex) * 4;
-			i2c.y_data_reg = le16_to_cpu(gpio->usDataY_RegisterIndex) * 4;
-			i2c.a_clk_reg = le16_to_cpu(gpio->usClkA_RegisterIndex) * 4;
-			i2c.a_data_reg = le16_to_cpu(gpio->usDataA_RegisterIndex) * 4;
-			i2c.mask_clk_mask = (1 << gpio->ucClkMaskShift);
-			i2c.mask_data_mask = (1 << gpio->ucDataMaskShift);
-			i2c.en_clk_mask = (1 << gpio->ucClkEnShift);
-			i2c.en_data_mask = (1 << gpio->ucDataEnShift);
-			i2c.y_clk_mask = (1 << gpio->ucClkY_Shift);
-			i2c.y_data_mask = (1 << gpio->ucDataY_Shift);
-			i2c.a_clk_mask = (1 << gpio->ucClkA_Shift);
-			i2c.a_data_mask = (1 << gpio->ucDataA_Shift);
-
-			if (gpio->sucI2cId.sbfAccess.bfHW_Capable)
-				i2c.hw_capable = true;
-			else
-				i2c.hw_capable = false;
+			radeon_lookup_i2c_gpio_quirks(rdev, gpio, i);
 
-			if (gpio->sucI2cId.ucAccess == 0xa0)
-				i2c.mm_i2c = true;
-			else
-				i2c.mm_i2c = false;
+			i2c = radeon_get_bus_rec_for_i2c_gpio(gpio);
 
-			i2c.i2c_id = gpio->sucI2cId.ucAccess;
-
-			if (i2c.mask_clk_reg) {
-				i2c.valid = true;
+			if (i2c.valid) {
 				sprintf(stmp, "0x%x", i2c.i2c_id);
 				rdev->i2c_bus[i] = radeon_i2c_create(rdev->ddev, &i2c, stmp);
 			}
@@ -1996,14 +1978,14 @@ static int radeon_atombios_parse_power_table_1_3(struct radeon_device *rdev)
 		return state_index;
 	/* last mode is usually default, array is low to high */
 	for (i = 0; i < num_modes; i++) {
+		rdev->pm.power_state[state_index].clock_info =
+			kzalloc(sizeof(struct radeon_pm_clock_info) * 1, GFP_KERNEL);
+		if (!rdev->pm.power_state[state_index].clock_info)
+			return state_index;
+		rdev->pm.power_state[state_index].num_clock_modes = 1;
 		rdev->pm.power_state[state_index].clock_info[0].voltage.type = VOLTAGE_NONE;
 		switch (frev) {
 		case 1:
-			rdev->pm.power_state[state_index].clock_info =
-				kzalloc(sizeof(struct radeon_pm_clock_info) * 1, GFP_KERNEL);
-			if (!rdev->pm.power_state[state_index].clock_info)
-				return state_index;
-			rdev->pm.power_state[state_index].num_clock_modes = 1;
 			rdev->pm.power_state[state_index].clock_info[0].mclk =
 				le16_to_cpu(power_info->info.asPowerPlayInfo[i].usMemoryClock);
 			rdev->pm.power_state[state_index].clock_info[0].sclk =
@@ -2039,11 +2021,6 @@ static int radeon_atombios_parse_power_table_1_3(struct radeon_device *rdev)
 			state_index++;
 			break;
 		case 2:
-			rdev->pm.power_state[state_index].clock_info =
-				kzalloc(sizeof(struct radeon_pm_clock_info) * 1, GFP_KERNEL);
-			if (!rdev->pm.power_state[state_index].clock_info)
-				return state_index;
-			rdev->pm.power_state[state_index].num_clock_modes = 1;
 			rdev->pm.power_state[state_index].clock_info[0].mclk =
 				le32_to_cpu(power_info->info_2.asPowerPlayInfo[i].ulMemoryClock);
 			rdev->pm.power_state[state_index].clock_info[0].sclk =
@@ -2080,11 +2057,6 @@ static int radeon_atombios_parse_power_table_1_3(struct radeon_device *rdev)
 			state_index++;
 			break;
 		case 3:
-			rdev->pm.power_state[state_index].clock_info =
-				kzalloc(sizeof(struct radeon_pm_clock_info) * 1, GFP_KERNEL);
-			if (!rdev->pm.power_state[state_index].clock_info)
-				return state_index;
-			rdev->pm.power_state[state_index].num_clock_modes = 1;
 			rdev->pm.power_state[state_index].clock_info[0].mclk =
 				le32_to_cpu(power_info->info_3.asPowerPlayInfo[i].ulMemoryClock);
 			rdev->pm.power_state[state_index].clock_info[0].sclk =
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index ccaa243..29afd71 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -93,7 +93,7 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 {
 	struct drm_radeon_cs *cs = data;
 	uint64_t *chunk_array_ptr;
-	unsigned size, i;
+	unsigned size, i, flags = 0;
 
 	if (!cs->num_chunks) {
 		return 0;
@@ -140,6 +140,10 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 			if (p->chunks[i].length_dw == 0)
 				return -EINVAL;
 		}
+		if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_FLAGS &&
+		    !p->chunks[i].length_dw) {
+			return -EINVAL;
+		}
 
 		p->chunks[i].length_dw = user_chunk.length_dw;
 		p->chunks[i].user_ptr = (void __user *)(unsigned long)user_chunk.chunk_data;
@@ -155,6 +159,9 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 					       p->chunks[i].user_ptr, size)) {
 				return -EFAULT;
 			}
+			if (p->chunks[i].chunk_id == RADEON_CHUNK_ID_FLAGS) {
+				flags = p->chunks[i].kdata[0];
+			}
 		} else {
 			p->chunks[i].kpage[0] = kmalloc(PAGE_SIZE, GFP_KERNEL);
 			p->chunks[i].kpage[1] = kmalloc(PAGE_SIZE, GFP_KERNEL);
@@ -174,6 +181,8 @@ int radeon_cs_parser_init(struct radeon_cs_parser *p, void *data)
 			  p->chunks[p->chunk_ib_idx].length_dw);
 		return -EINVAL;
 	}
+
+	p->keep_tiling_flags = (flags & RADEON_CS_KEEP_TILING_FLAGS) != 0;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index a0b35e9..71499fc 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -53,9 +53,10 @@
  *   2.9.0 - r600 tiling (s3tc,rgtc) working, SET_PREDICATION packet 3 on r600 + eg, backend query
  *   2.10.0 - fusion 2D tiling
  *   2.11.0 - backend map, initial compute support for the CS checker
+ *   2.12.0 - RADEON_CS_KEEP_TILING_FLAGS
  */
 #define KMS_DRIVER_MAJOR	2
-#define KMS_DRIVER_MINOR	11
+#define KMS_DRIVER_MINOR	12
 #define KMS_DRIVER_PATCHLEVEL	0
 int radeon_driver_load_kms(struct drm_device *dev, unsigned long flags);
 int radeon_driver_unload_kms(struct drm_device *dev);
diff --git a/drivers/gpu/drm/radeon/rs600.c b/drivers/gpu/drm/radeon/rs600.c
index 481b99e..b1053d6 100644
--- a/drivers/gpu/drm/radeon/rs600.c
+++ b/drivers/gpu/drm/radeon/rs600.c
@@ -62,6 +62,7 @@ u32 rs600_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
 	u32 tmp = RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset);
+	int i;
 
 	/* Lock the graphics update lock */
 	tmp |= AVIVO_D1GRPH_UPDATE_LOCK;
@@ -74,7 +75,11 @@ u32 rs600_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 	       (u32)crtc_base);
 
 	/* Wait for update_pending to go high. */
-	while (!(RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING));
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if (RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING)
+			break;
+		udelay(1);
+	}
 	DRM_DEBUG("Update pending now high. Unlocking vupdate_lock.\n");
 
 	/* Unlock the lock, so double-buffering can take place inside vblank */
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index a983f41..23ae1c6 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -47,6 +47,7 @@ u32 rv770_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 {
 	struct radeon_crtc *radeon_crtc = rdev->mode_info.crtcs[crtc_id];
 	u32 tmp = RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset);
+	int i;
 
 	/* Lock the graphics update lock */
 	tmp |= AVIVO_D1GRPH_UPDATE_LOCK;
@@ -66,7 +67,11 @@ u32 rv770_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 	       (u32)crtc_base);
 
 	/* Wait for update_pending to go high. */
-	while (!(RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING));
+	for (i = 0; i < rdev->usec_timeout; i++) {
+		if (RREG32(AVIVO_D1GRPH_UPDATE + radeon_crtc->crtc_offset) & AVIVO_D1GRPH_SURFACE_UPDATE_PENDING)
+			break;
+		udelay(1);
+	}
 	DRM_DEBUG("Update pending now high. Unlocking vupdate_lock.\n");
 
 	/* Unlock the lock, so double-buffering can take place inside vblank */
diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 617b646..0bb0f5f 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -574,10 +574,16 @@ retry:
 		return ret;
 
 	spin_lock(&glob->lru_lock);
+
+	if (unlikely(list_empty(&bo->ddestroy))) {
+		spin_unlock(&glob->lru_lock);
+		return 0;
+	}
+
 	ret = ttm_bo_reserve_locked(bo, interruptible,
 				    no_wait_reserve, false, 0);
 
-	if (unlikely(ret != 0) || list_empty(&bo->ddestroy)) {
+	if (unlikely(ret != 0)) {
 		spin_unlock(&glob->lru_lock);
 		return ret;
 	}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 880e285..37d4054 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1809,7 +1809,8 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 	}
 
 	rects_size = arg->num_outputs * sizeof(struct drm_vmw_rect);
-	rects = kzalloc(rects_size, GFP_KERNEL);
+	rects = kcalloc(arg->num_outputs, sizeof(struct drm_vmw_rect),
+			GFP_KERNEL);
 	if (unlikely(!rects)) {
 		ret = -ENOMEM;
 		goto out_unlock;
@@ -1824,10 +1825,10 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 	}
 
 	for (i = 0; i < arg->num_outputs; ++i) {
-		if (rects->x < 0 ||
-		    rects->y < 0 ||
-		    rects->x + rects->w > mode_config->max_width ||
-		    rects->y + rects->h > mode_config->max_height) {
+		if (rects[i].x < 0 ||
+		    rects[i].y < 0 ||
+		    rects[i].x + rects[i].w > mode_config->max_width ||
+		    rects[i].y + rects[i].h > mode_config->max_height) {
 			DRM_ERROR("Invalid GUI layout.\n");
 			ret = -EINVAL;
 			goto out_free;
diff --git a/drivers/gpu/vga/vgaarb.c b/drivers/gpu/vga/vgaarb.c
index c72f1c0..111d956 100644
--- a/drivers/gpu/vga/vgaarb.c
+++ b/drivers/gpu/vga/vgaarb.c
@@ -465,31 +465,29 @@ static void vga_arbiter_check_bridge_sharing(struct vga_device *vgadev)
 	while (new_bus) {
 		new_bridge = new_bus->self;
 
-		if (new_bridge) {
-			/* go through list of devices already registered */
-			list_for_each_entry(same_bridge_vgadev, &vga_list, list) {
-				bus = same_bridge_vgadev->pdev->bus;
-				bridge = bus->self;
-
-				/* see if the share a bridge with this device */
-				if (new_bridge == bridge) {
-					/* if their direct parent bridge is the same
-					   as any bridge of this device then it can't be used
-					   for that device */
-					same_bridge_vgadev->bridge_has_one_vga = false;
-				}
+		/* go through list of devices already registered */
+		list_for_each_entry(same_bridge_vgadev, &vga_list, list) {
+			bus = same_bridge_vgadev->pdev->bus;
+			bridge = bus->self;
+
+			/* see if the share a bridge with this device */
+			if (new_bridge == bridge) {
+				/* if their direct parent bridge is the same
+				   as any bridge of this device then it can't be used
+				   for that device */
+				same_bridge_vgadev->bridge_has_one_vga = false;
+			}
 
-				/* now iterate the previous devices bridge hierarchy */
-				/* if the new devices parent bridge is in the other devices
-				   hierarchy then we can't use it to control this device */
-				while (bus) {
-					bridge = bus->self;
-					if (bridge) {
-						if (bridge == vgadev->pdev->bus->self)
-							vgadev->bridge_has_one_vga = false;
-					}
-					bus = bus->parent;
+			/* now iterate the previous devices bridge hierarchy */
+			/* if the new devices parent bridge is in the other devices
+			   hierarchy then we can't use it to control this device */
+			while (bus) {
+				bridge = bus->self;
+				if (bridge) {
+					if (bridge == vgadev->pdev->bus->self)
+						vgadev->bridge_has_one_vga = false;
 				}
+				bus = bus->parent;
 			}
 		}
 		new_bus = new_bus->parent;
@@ -993,14 +991,20 @@ static ssize_t vga_arb_write(struct file *file, const char __user * buf,
 				uc = &priv->cards[i];
 		}
 
-		if (!uc)
-			return -EINVAL;
+		if (!uc) {
+			ret_val = -EINVAL;
+			goto done;
+		}
 
-		if (io_state & VGA_RSRC_LEGACY_IO && uc->io_cnt == 0)
-			return -EINVAL;
+		if (io_state & VGA_RSRC_LEGACY_IO && uc->io_cnt == 0) {
+			ret_val = -EINVAL;
+			goto done;
+		}
 
-		if (io_state & VGA_RSRC_LEGACY_MEM && uc->mem_cnt == 0)
-			return -EINVAL;
+		if (io_state & VGA_RSRC_LEGACY_MEM && uc->mem_cnt == 0) {
+			ret_val = -EINVAL;
+			goto done;
+		}
 
 		vga_put(pdev, io_state);
 
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 848a56c..af35384 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1771,8 +1771,8 @@ static const struct hid_device_id hid_ignore_list[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ESSENTIAL_REALITY, USB_DEVICE_ID_ESSENTIAL_REALITY_P5) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ETT, USB_DEVICE_ID_TC5UH) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_ETT, USB_DEVICE_ID_TC4UM) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0001) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0002) },
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0003) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GENERAL_TOUCH, 0x0004) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_4_PHIDGETSERVO_30) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GLAB, USB_DEVICE_ID_1_PHIDGETSERVO_30) },
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 06ce996..4a441a6 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -266,7 +266,7 @@
 #define USB_DEVICE_ID_GAMERON_DUAL_PCS_ADAPTOR	0x0002
 
 #define USB_VENDOR_ID_GENERAL_TOUCH	0x0dfc
-#define USB_DEVICE_ID_GENERAL_TOUCH_WIN7_TWOFINGERS 0x0001
+#define USB_DEVICE_ID_GENERAL_TOUCH_WIN7_TWOFINGERS 0x0003
 
 #define USB_VENDOR_ID_GLAB		0x06c2
 #define USB_DEVICE_ID_4_PHIDGETSERVO_30	0x0038
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 9ec854a..91be41f 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -315,7 +315,7 @@ config SENSORS_DS1621
 
 config SENSORS_EXYNOS4_TMU
 	tristate "Temperature sensor on Samsung EXYNOS4"
-	depends on EXYNOS4_DEV_TMU
+	depends on ARCH_EXYNOS4
 	help
 	  If you say yes here you get support for TMU (Thermal Managment
 	  Unit) on SAMSUNG EXYNOS4 series of SoC.
diff --git a/drivers/hwmon/ad7314.c b/drivers/hwmon/ad7314.c
index 318e38e..5d760f3 100644
--- a/drivers/hwmon/ad7314.c
+++ b/drivers/hwmon/ad7314.c
@@ -160,7 +160,6 @@ MODULE_DEVICE_TABLE(spi, ad7314_id);
 static struct spi_driver ad7314_driver = {
 	.driver = {
 		.name = "ad7314",
-		.bus = &spi_bus_type,
 		.owner = THIS_MODULE,
 	},
 	.probe = ad7314_probe,
diff --git a/drivers/hwmon/ads7871.c b/drivers/hwmon/ads7871.c
index 5231934..04450f8 100644
--- a/drivers/hwmon/ads7871.c
+++ b/drivers/hwmon/ads7871.c
@@ -227,7 +227,6 @@ static int __devexit ads7871_remove(struct spi_device *spi)
 static struct spi_driver ads7871_driver = {
 	.driver = {
 		.name = DEVICE_NAME,
-		.bus = &spi_bus_type,
 		.owner = THIS_MODULE,
 	},
 
diff --git a/drivers/hwmon/exynos4_tmu.c b/drivers/hwmon/exynos4_tmu.c
index faa0884..f2359a0 100644
--- a/drivers/hwmon/exynos4_tmu.c
+++ b/drivers/hwmon/exynos4_tmu.c
@@ -506,17 +506,7 @@ static struct platform_driver exynos4_tmu_driver = {
 	.resume = exynos4_tmu_resume,
 };
 
-static int __init exynos4_tmu_driver_init(void)
-{
-	return platform_driver_register(&exynos4_tmu_driver);
-}
-module_init(exynos4_tmu_driver_init);
-
-static void __exit exynos4_tmu_driver_exit(void)
-{
-	platform_driver_unregister(&exynos4_tmu_driver);
-}
-module_exit(exynos4_tmu_driver_exit);
+module_platform_driver(exynos4_tmu_driver);
 
 MODULE_DESCRIPTION("EXYNOS4 TMU Driver");
 MODULE_AUTHOR("Donggeun Kim <dg77.kim@samsung.com>");
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index 89aa9fb..9ba38f3 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -539,18 +539,7 @@ static struct platform_driver gpio_fan_driver = {
 	},
 };
 
-static int __init gpio_fan_init(void)
-{
-	return platform_driver_register(&gpio_fan_driver);
-}
-
-static void __exit gpio_fan_exit(void)
-{
-	platform_driver_unregister(&gpio_fan_driver);
-}
-
-module_init(gpio_fan_init);
-module_exit(gpio_fan_exit);
+module_platform_driver(gpio_fan_driver);
 
 MODULE_AUTHOR("Simon Guinot <sguinot@lacie.com>");
 MODULE_DESCRIPTION("GPIO FAN driver");
diff --git a/drivers/hwmon/jz4740-hwmon.c b/drivers/hwmon/jz4740-hwmon.c
index fea292d..7a48b1e 100644
--- a/drivers/hwmon/jz4740-hwmon.c
+++ b/drivers/hwmon/jz4740-hwmon.c
@@ -212,17 +212,7 @@ struct platform_driver jz4740_hwmon_driver = {
 	},
 };
 
-static int __init jz4740_hwmon_init(void)
-{
-	return platform_driver_register(&jz4740_hwmon_driver);
-}
-module_init(jz4740_hwmon_init);
-
-static void __exit jz4740_hwmon_exit(void)
-{
-	platform_driver_unregister(&jz4740_hwmon_driver);
-}
-module_exit(jz4740_hwmon_exit);
+module_platform_driver(jz4740_hwmon_driver);
 
 MODULE_DESCRIPTION("JZ4740 SoC HWMON driver");
 MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index eab1161..9b382ec 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -432,19 +432,7 @@ static struct platform_driver ntc_thermistor_driver = {
 	.id_table = ntc_thermistor_id,
 };
 
-static int __init ntc_thermistor_init(void)
-{
-	return platform_driver_register(&ntc_thermistor_driver);
-}
-
-module_init(ntc_thermistor_init);
-
-static void __exit ntc_thermistor_cleanup(void)
-{
-	platform_driver_unregister(&ntc_thermistor_driver);
-}
-
-module_exit(ntc_thermistor_cleanup);
+module_platform_driver(ntc_thermistor_driver);
 
 MODULE_DESCRIPTION("NTC Thermistor Driver");
 MODULE_AUTHOR("MyungJoo Ham <myungjoo.ham@samsung.com>");
diff --git a/drivers/hwmon/s3c-hwmon.c b/drivers/hwmon/s3c-hwmon.c
index b39f52e..f6c26d1 100644
--- a/drivers/hwmon/s3c-hwmon.c
+++ b/drivers/hwmon/s3c-hwmon.c
@@ -393,18 +393,7 @@ static struct platform_driver s3c_hwmon_driver = {
 	.remove		= __devexit_p(s3c_hwmon_remove),
 };
 
-static int __init s3c_hwmon_init(void)
-{
-	return platform_driver_register(&s3c_hwmon_driver);
-}
-
-static void __exit s3c_hwmon_exit(void)
-{
-	platform_driver_unregister(&s3c_hwmon_driver);
-}
-
-module_init(s3c_hwmon_init);
-module_exit(s3c_hwmon_exit);
+module_platform_driver(s3c_hwmon_driver);
 
 MODULE_AUTHOR("Ben Dooks <ben@simtec.co.uk>");
 MODULE_DESCRIPTION("S3C ADC HWMon driver");
diff --git a/drivers/hwmon/sch5627.c b/drivers/hwmon/sch5627.c
index e3b5c60..79b6dab 100644
--- a/drivers/hwmon/sch5627.c
+++ b/drivers/hwmon/sch5627.c
@@ -590,19 +590,8 @@ static struct platform_driver sch5627_driver = {
 	.remove		= sch5627_remove,
 };
 
-static int __init sch5627_init(void)
-{
-	return platform_driver_register(&sch5627_driver);
-}
-
-static void __exit sch5627_exit(void)
-{
-	platform_driver_unregister(&sch5627_driver);
-}
+module_platform_driver(sch5627_driver);
 
 MODULE_DESCRIPTION("SMSC SCH5627 Hardware Monitoring Driver");
 MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
 MODULE_LICENSE("GPL");
-
-module_init(sch5627_init);
-module_exit(sch5627_exit);
diff --git a/drivers/hwmon/sch5636.c b/drivers/hwmon/sch5636.c
index 244407a..9d5236f 100644
--- a/drivers/hwmon/sch5636.c
+++ b/drivers/hwmon/sch5636.c
@@ -521,19 +521,8 @@ static struct platform_driver sch5636_driver = {
 	.remove		= sch5636_remove,
 };
 
-static int __init sch5636_init(void)
-{
-	return platform_driver_register(&sch5636_driver);
-}
-
-static void __exit sch5636_exit(void)
-{
-	platform_driver_unregister(&sch5636_driver);
-}
+module_platform_driver(sch5636_driver);
 
 MODULE_DESCRIPTION("SMSC SCH5636 Hardware Monitoring Driver");
 MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
 MODULE_LICENSE("GPL");
-
-module_init(sch5636_init);
-module_exit(sch5636_exit);
diff --git a/drivers/hwmon/twl4030-madc-hwmon.c b/drivers/hwmon/twl4030-madc-hwmon.c
index 5724074..0018c7d 100644
--- a/drivers/hwmon/twl4030-madc-hwmon.c
+++ b/drivers/hwmon/twl4030-madc-hwmon.c
@@ -136,19 +136,7 @@ static struct platform_driver twl4030_madc_hwmon_driver = {
 		   },
 };
 
-static int __init twl4030_madc_hwmon_init(void)
-{
-	return platform_driver_register(&twl4030_madc_hwmon_driver);
-}
-
-module_init(twl4030_madc_hwmon_init);
-
-static void __exit twl4030_madc_hwmon_exit(void)
-{
-	platform_driver_unregister(&twl4030_madc_hwmon_driver);
-}
-
-module_exit(twl4030_madc_hwmon_exit);
+module_platform_driver(twl4030_madc_hwmon_driver);
 
 MODULE_DESCRIPTION("TWL4030 ADC Hwmon driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/hwmon/ultra45_env.c b/drivers/hwmon/ultra45_env.c
index 3cd07bf..b9a87e8 100644
--- a/drivers/hwmon/ultra45_env.c
+++ b/drivers/hwmon/ultra45_env.c
@@ -309,15 +309,4 @@ static struct platform_driver env_driver = {
 	.remove		= __devexit_p(env_remove),
 };
 
-static int __init env_init(void)
-{
-	return platform_driver_register(&env_driver);
-}
-
-static void __exit env_exit(void)
-{
-	platform_driver_unregister(&env_driver);
-}
-
-module_init(env_init);
-module_exit(env_exit);
+module_platform_driver(env_driver);
diff --git a/drivers/hwmon/wm831x-hwmon.c b/drivers/hwmon/wm831x-hwmon.c
index 97b1f83..9b598ed 100644
--- a/drivers/hwmon/wm831x-hwmon.c
+++ b/drivers/hwmon/wm831x-hwmon.c
@@ -209,17 +209,7 @@ static struct platform_driver wm831x_hwmon_driver = {
 	},
 };
 
-static int __init wm831x_hwmon_init(void)
-{
-	return platform_driver_register(&wm831x_hwmon_driver);
-}
-module_init(wm831x_hwmon_init);
-
-static void __exit wm831x_hwmon_exit(void)
-{
-	platform_driver_unregister(&wm831x_hwmon_driver);
-}
-module_exit(wm831x_hwmon_exit);
+module_platform_driver(wm831x_hwmon_driver);
 
 MODULE_AUTHOR("Mark Brown <broonie@opensource.wolfsonmicro.com>");
 MODULE_DESCRIPTION("WM831x Hardware Monitoring");
diff --git a/drivers/hwmon/wm8350-hwmon.c b/drivers/hwmon/wm8350-hwmon.c
index 1329059..3ff67ed 100644
--- a/drivers/hwmon/wm8350-hwmon.c
+++ b/drivers/hwmon/wm8350-hwmon.c
@@ -133,17 +133,7 @@ static struct platform_driver wm8350_hwmon_driver = {
 	},
 };
 
-static int __init wm8350_hwmon_init(void)
-{
-	return platform_driver_register(&wm8350_hwmon_driver);
-}
-module_init(wm8350_hwmon_init);
-
-static void __exit wm8350_hwmon_exit(void)
-{
-	platform_driver_unregister(&wm8350_hwmon_driver);
-}
-module_exit(wm8350_hwmon_exit);
+module_platform_driver(wm8350_hwmon_driver);
 
 MODULE_AUTHOR("Mark Brown <broonie@opensource.wolfsonmicro.com>");
 MODULE_DESCRIPTION("WM8350 Hardware Monitoring");
diff --git a/drivers/i2c/algos/i2c-algo-bit.c b/drivers/i2c/algos/i2c-algo-bit.c
index 85584a5..525c734 100644
--- a/drivers/i2c/algos/i2c-algo-bit.c
+++ b/drivers/i2c/algos/i2c-algo-bit.c
@@ -488,7 +488,7 @@ static int bit_doAddress(struct i2c_adapter *i2c_adap, struct i2c_msg *msg)
 
 	if (flags & I2C_M_TEN) {
 		/* a ten bit address */
-		addr = 0xf0 | ((msg->addr >> 7) & 0x03);
+		addr = 0xf0 | ((msg->addr >> 7) & 0x06);
 		bit_dbg(2, &i2c_adap->dev, "addr0: %d\n", addr);
 		/* try extended address code...*/
 		ret = try_address(i2c_adap, addr, retries);
@@ -498,7 +498,7 @@ static int bit_doAddress(struct i2c_adapter *i2c_adap, struct i2c_msg *msg)
 			return -ENXIO;
 		}
 		/* the remaining 8 bit address */
-		ret = i2c_outb(i2c_adap, msg->addr & 0x7f);
+		ret = i2c_outb(i2c_adap, msg->addr & 0xff);
 		if ((ret != 1) && !nak_ok) {
 			/* the chip did not ack / xmission error occurred */
 			dev_err(&i2c_adap->dev, "died at 2nd address code\n");
diff --git a/drivers/i2c/busses/i2c-nuc900.c b/drivers/i2c/busses/i2c-nuc900.c
index 835e47b..03b6157 100644
--- a/drivers/i2c/busses/i2c-nuc900.c
+++ b/drivers/i2c/busses/i2c-nuc900.c
@@ -593,7 +593,7 @@ static int __devinit nuc900_i2c_probe(struct platform_device *pdev)
 	i2c->adap.algo_data = i2c;
 	i2c->adap.dev.parent = &pdev->dev;
 
-	mfp_set_groupg(&pdev->dev);
+	mfp_set_groupg(&pdev->dev, NULL);
 
 	clk_get_rate(i2c->clk);
 
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 131079a..1e56061 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -539,8 +539,10 @@ i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info)
 	client->dev.type = &i2c_client_type;
 	client->dev.of_node = info->of_node;
 
+	/* For 10-bit clients, add an arbitrary offset to avoid collisions */
 	dev_set_name(&client->dev, "%d-%04x", i2c_adapter_id(adap),
-		     client->addr);
+		     client->addr | ((client->flags & I2C_CLIENT_TEN)
+				     ? 0xa000 : 0));
 	status = device_register(&client->dev);
 	if (status)
 		goto out_err;
diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c
index c90ce50..57a45ce8 100644
--- a/drivers/i2c/i2c-dev.c
+++ b/drivers/i2c/i2c-dev.c
@@ -579,7 +579,7 @@ static int i2cdev_detach_adapter(struct device *dev, void *dummy)
 	return 0;
 }
 
-int i2cdev_notifier_call(struct notifier_block *nb, unsigned long action,
+static int i2cdev_notifier_call(struct notifier_block *nb, unsigned long action,
 			 void *data)
 {
 	struct device *dev = data;
diff --git a/drivers/ide/cy82c693.c b/drivers/ide/cy82c693.c
index 67cbcfa..847553f 100644
--- a/drivers/ide/cy82c693.c
+++ b/drivers/ide/cy82c693.c
@@ -1,7 +1,7 @@
 /*
  *  Copyright (C) 1998-2000 Andreas S. Krebs (akrebs@altavista.net), Maintainer
  *  Copyright (C) 1998-2002 Andre Hedrick <andre@linux-ide.org>, Integrator
- *  Copyright (C) 2007-2010 Bartlomiej Zolnierkiewicz
+ *  Copyright (C) 2007-2011 Bartlomiej Zolnierkiewicz
  *
  * CYPRESS CY82C693 chipset IDE controller
  *
@@ -90,7 +90,7 @@ static void cy82c693_set_pio_mode(ide_hwif_t *hwif, ide_drive_t *drive)
 	u8 time_16, time_8;
 
 	/* select primary or secondary channel */
-	if (hwif->index > 0) {  /* drive is on the secondary channel */
+	if (drive->dn > 1) {  /* drive is on the secondary channel */
 		dev = pci_get_slot(dev->bus, dev->devfn+1);
 		if (!dev) {
 			printk(KERN_ERR "%s: tune_drive: "
@@ -141,7 +141,7 @@ static void cy82c693_set_pio_mode(ide_hwif_t *hwif, ide_drive_t *drive)
 		pci_write_config_byte(dev, CY82_IDE_SLAVE_IOW, time_16);
 		pci_write_config_byte(dev, CY82_IDE_SLAVE_8BIT, time_8);
 	}
-	if (hwif->index > 0)
+	if (drive->dn > 1)
 		pci_dev_put(dev);
 }
 
diff --git a/drivers/ide/icside.c b/drivers/ide/icside.c
index 4a697a2..8716066 100644
--- a/drivers/ide/icside.c
+++ b/drivers/ide/icside.c
@@ -521,8 +521,8 @@ icside_register_v6(struct icside_state *state, struct expansion_card *ec)
 	if (ec->dma != NO_DMA && !request_dma(ec->dma, DRV_NAME)) {
 		d.init_dma = icside_dma_init;
 		d.port_ops = &icside_v6_port_ops;
+	} else
 		d.dma_ops = NULL;
-	}
 
 	ret = ide_host_register(host, &d, hws);
 	if (ret)
diff --git a/drivers/ide/piix.c b/drivers/ide/piix.c
index b59d04c..1892e81 100644
--- a/drivers/ide/piix.c
+++ b/drivers/ide/piix.c
@@ -331,7 +331,7 @@ static const struct ide_port_ops ich_port_ops = {
 		.udma_mask	= udma,			\
 	}
 
-#define DECLARE_ICH_DEV(udma) \
+#define DECLARE_ICH_DEV(mwdma, udma) \
 	{ \
 		.name		= DRV_NAME, \
 		.init_chipset	= init_chipset_ich, \
@@ -340,7 +340,7 @@ static const struct ide_port_ops ich_port_ops = {
 		.port_ops	= &ich_port_ops, \
 		.pio_mask	= ATA_PIO4, \
 		.swdma_mask	= ATA_SWDMA2_ONLY, \
-		.mwdma_mask	= ATA_MWDMA12_ONLY, \
+		.mwdma_mask	= mwdma, \
 		.udma_mask	= udma, \
 	}
 
@@ -362,13 +362,15 @@ static const struct ide_port_info piix_pci_info[] __devinitdata = {
 	/* 2: PIIX4 */
 	DECLARE_PIIX_DEV(ATA_UDMA2),
 	/* 3: ICH0 */
-	DECLARE_ICH_DEV(ATA_UDMA2),
+	DECLARE_ICH_DEV(ATA_MWDMA12_ONLY, ATA_UDMA2),
 	/* 4: ICH */
-	DECLARE_ICH_DEV(ATA_UDMA4),
+	DECLARE_ICH_DEV(ATA_MWDMA12_ONLY, ATA_UDMA4),
 	/* 5: PIIX4 */
 	DECLARE_PIIX_DEV(ATA_UDMA4),
-	/* 6: ICH[2-7]/ICH[2-3]M/C-ICH/ICH5-SATA/ESB2/ICH8M */
-	DECLARE_ICH_DEV(ATA_UDMA5),
+	/* 6: ICH[2-6]/ICH[2-3]M/C-ICH/ICH5-SATA/ESB2/ICH8M */
+	DECLARE_ICH_DEV(ATA_MWDMA12_ONLY, ATA_UDMA5),
+	/* 7: ICH7/7-R, no MWDMA1 */
+	DECLARE_ICH_DEV(ATA_MWDMA2_ONLY, ATA_UDMA5),
 };
 
 /**
@@ -438,9 +440,9 @@ static const struct pci_device_id piix_pci_tbl[] = {
 #endif
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ESB_2),      6 },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICH6_19),    6 },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICH7_21),    6 },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICH7_21),    7 },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_82801DB_1),  6 },
-	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ESB2_18),    6 },
+	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ESB2_18),    7 },
 	{ PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_ICH8_6),     6 },
 	{ 0, },
 };
diff --git a/drivers/ide/triflex.c b/drivers/ide/triflex.c
index e53a1b7..281c914 100644
--- a/drivers/ide/triflex.c
+++ b/drivers/ide/triflex.c
@@ -113,12 +113,26 @@ static const struct pci_device_id triflex_pci_tbl[] = {
 };
 MODULE_DEVICE_TABLE(pci, triflex_pci_tbl);
 
+#ifdef CONFIG_PM
+static int triflex_ide_pci_suspend(struct pci_dev *dev, pm_message_t state)
+{
+	/*
+	 * We must not disable or powerdown the device.
+	 * APM bios refuses to suspend if IDE is not accessible.
+	 */
+	pci_save_state(dev);
+	return 0;
+}
+#else
+#define triflex_ide_pci_suspend NULL
+#endif
+
 static struct pci_driver triflex_pci_driver = {
 	.name		= "TRIFLEX_IDE",
 	.id_table	= triflex_pci_tbl,
 	.probe		= triflex_init_one,
 	.remove		= ide_pci_remove,
-	.suspend	= ide_pci_suspend,
+	.suspend	= triflex_ide_pci_suspend,
 	.resume		= ide_pci_resume,
 };
 
diff --git a/drivers/ieee802154/fakehard.c b/drivers/ieee802154/fakehard.c
index eb0e2cc..73d4531 100644
--- a/drivers/ieee802154/fakehard.c
+++ b/drivers/ieee802154/fakehard.c
@@ -343,7 +343,7 @@ static void ieee802154_fake_setup(struct net_device *dev)
 {
 	dev->addr_len		= IEEE802154_ADDR_LEN;
 	memset(dev->broadcast, 0xff, IEEE802154_ADDR_LEN);
-	dev->features		= NETIF_F_NO_CSUM;
+	dev->features		= NETIF_F_HW_CSUM;
 	dev->needed_tailroom	= 2; /* FCS */
 	dev->mtu		= 127;
 	dev->tx_queue_len	= 10;
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 691276b..1612cfd 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -178,6 +178,25 @@ static void queue_req(struct addr_req *req)
 	mutex_unlock(&lock);
 }
 
+static int dst_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *addr)
+{
+	struct neighbour *n;
+	int ret;
+
+	rcu_read_lock();
+	n = dst_get_neighbour_noref(dst);
+	if (!n || !(n->nud_state & NUD_VALID)) {
+		if (n)
+			neigh_event_send(n, NULL);
+		ret = -ENODATA;
+	} else {
+		ret = rdma_copy_addr(addr, dst->dev, n->ha);
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 static int addr4_resolve(struct sockaddr_in *src_in,
 			 struct sockaddr_in *dst_in,
 			 struct rdma_dev_addr *addr)
@@ -185,7 +204,6 @@ static int addr4_resolve(struct sockaddr_in *src_in,
 	__be32 src_ip = src_in->sin_addr.s_addr;
 	__be32 dst_ip = dst_in->sin_addr.s_addr;
 	struct rtable *rt;
-	struct neighbour *neigh;
 	struct flowi4 fl4;
 	int ret;
 
@@ -214,18 +232,7 @@ static int addr4_resolve(struct sockaddr_in *src_in,
 		goto put;
 	}
 
-	neigh = neigh_lookup(&arp_tbl, &rt->rt_gateway, rt->dst.dev);
-	if (!neigh || !(neigh->nud_state & NUD_VALID)) {
-		neigh_event_send(dst_get_neighbour(&rt->dst), NULL);
-		ret = -ENODATA;
-		if (neigh)
-			goto release;
-		goto put;
-	}
-
-	ret = rdma_copy_addr(addr, neigh->dev, neigh->ha);
-release:
-	neigh_release(neigh);
+	ret = dst_fetch_ha(&rt->dst, addr);
 put:
 	ip_rt_put(rt);
 out:
@@ -238,13 +245,12 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 			 struct rdma_dev_addr *addr)
 {
 	struct flowi6 fl6;
-	struct neighbour *neigh;
 	struct dst_entry *dst;
 	int ret;
 
 	memset(&fl6, 0, sizeof fl6);
-	ipv6_addr_copy(&fl6.daddr, &dst_in->sin6_addr);
-	ipv6_addr_copy(&fl6.saddr, &src_in->sin6_addr);
+	fl6.daddr = dst_in->sin6_addr;
+	fl6.saddr = src_in->sin6_addr;
 	fl6.flowi6_oif = addr->bound_dev_if;
 
 	dst = ip6_route_output(&init_net, NULL, &fl6);
@@ -258,7 +264,7 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 			goto put;
 
 		src_in->sin6_family = AF_INET6;
-		ipv6_addr_copy(&src_in->sin6_addr, &fl6.saddr);
+		src_in->sin6_addr = fl6.saddr;
 	}
 
 	if (dst->dev->flags & IFF_LOOPBACK) {
@@ -274,15 +280,7 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 		goto put;
 	}
 
-	neigh = dst_get_neighbour(dst);
-	if (!neigh || !(neigh->nud_state & NUD_VALID)) {
-		if (neigh)
-			neigh_event_send(neigh, NULL);
-		ret = -ENODATA;
-		goto put;
-	}
-
-	ret = rdma_copy_addr(addr, dst->dev, neigh->ha);
+	ret = dst_fetch_ha(dst, addr);
 put:
 	dst_release(dst);
 	return ret;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 75ff821..09e66cc 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -2005,11 +2005,11 @@ static int cma_resolve_loopback(struct rdma_id_private *id_priv)
 	if (cma_zero_addr(src)) {
 		dst = (struct sockaddr *) &id_priv->id.route.addr.dst_addr;
 		if ((src->sa_family = dst->sa_family) == AF_INET) {
-			((struct sockaddr_in *) src)->sin_addr.s_addr =
-				((struct sockaddr_in *) dst)->sin_addr.s_addr;
+			((struct sockaddr_in *)src)->sin_addr =
+				((struct sockaddr_in *)dst)->sin_addr;
 		} else {
-			ipv6_addr_copy(&((struct sockaddr_in6 *) src)->sin6_addr,
-				       &((struct sockaddr_in6 *) dst)->sin6_addr);
+			((struct sockaddr_in6 *)src)->sin6_addr =
+				((struct sockaddr_in6 *)dst)->sin6_addr;
 		}
 	}
 
diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c
index de6d077..740dcc0 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cm.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c
@@ -1338,7 +1338,6 @@ static int pass_accept_req(struct t3cdev *tdev, struct sk_buff *skb, void *ctx)
 	struct iwch_ep *child_ep, *parent_ep = ctx;
 	struct cpl_pass_accept_req *req = cplhdr(skb);
 	unsigned int hwtid = GET_TID(req);
-	struct neighbour *neigh;
 	struct dst_entry *dst;
 	struct l2t_entry *l2t;
 	struct rtable *rt;
@@ -1375,8 +1374,7 @@ static int pass_accept_req(struct t3cdev *tdev, struct sk_buff *skb, void *ctx)
 		goto reject;
 	}
 	dst = &rt->dst;
-	neigh = dst_get_neighbour(dst);
-	l2t = t3_l2t_get(tdev, neigh, neigh->dev);
+	l2t = t3_l2t_get(tdev, dst, NULL);
 	if (!l2t) {
 		printk(KERN_ERR MOD "%s - failed to allocate l2t entry!\n",
 		       __func__);
@@ -1887,7 +1885,6 @@ static int is_loopback_dst(struct iw_cm_id *cm_id)
 int iwch_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 {
 	struct iwch_dev *h = to_iwch_dev(cm_id->device);
-	struct neighbour *neigh;
 	struct iwch_ep *ep;
 	struct rtable *rt;
 	int err = 0;
@@ -1945,11 +1942,7 @@ int iwch_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		goto fail3;
 	}
 	ep->dst = &rt->dst;
-
-	neigh = dst_get_neighbour(ep->dst);
-
-	/* get a l2t entry */
-	ep->l2t = t3_l2t_get(ep->com.tdev, neigh, neigh->dev);
+	ep->l2t = t3_l2t_get(ep->com.tdev, ep->dst, NULL);
 	if (!ep->l2t) {
 		printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
 		err = -ENOMEM;
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index b36cdac..0668bb3 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -542,8 +542,10 @@ static void send_mpa_req(struct c4iw_ep *ep, struct sk_buff *skb,
 		     (mpa_rev_to_use == 2 ? MPA_ENHANCED_RDMA_CONN : 0);
 	mpa->private_data_size = htons(ep->plen);
 	mpa->revision = mpa_rev_to_use;
-	if (mpa_rev_to_use == 1)
+	if (mpa_rev_to_use == 1) {
 		ep->tried_with_mpa_v1 = 1;
+		ep->retry_with_mpa_v1 = 0;
+	}
 
 	if (mpa_rev_to_use == 2) {
 		mpa->private_data_size +=
@@ -1554,6 +1556,67 @@ static void get_4tuple(struct cpl_pass_accept_req *req,
 	return;
 }
 
+static int import_ep(struct c4iw_ep *ep, __be32 peer_ip, struct dst_entry *dst,
+		     struct c4iw_dev *cdev, bool clear_mpa_v1)
+{
+	struct neighbour *n;
+	int err, step;
+
+	rcu_read_lock();
+	n = dst_get_neighbour_noref(dst);
+	err = -ENODEV;
+	if (!n)
+		goto out;
+	err = -ENOMEM;
+	if (n->dev->flags & IFF_LOOPBACK) {
+		struct net_device *pdev;
+
+		pdev = ip_dev_find(&init_net, peer_ip);
+		ep->l2t = cxgb4_l2t_get(cdev->rdev.lldi.l2t,
+					n, pdev, 0);
+		if (!ep->l2t)
+			goto out;
+		ep->mtu = pdev->mtu;
+		ep->tx_chan = cxgb4_port_chan(pdev);
+		ep->smac_idx = (cxgb4_port_viid(pdev) & 0x7F) << 1;
+		step = cdev->rdev.lldi.ntxq /
+			cdev->rdev.lldi.nchan;
+		ep->txq_idx = cxgb4_port_idx(pdev) * step;
+		step = cdev->rdev.lldi.nrxq /
+			cdev->rdev.lldi.nchan;
+		ep->ctrlq_idx = cxgb4_port_idx(pdev);
+		ep->rss_qid = cdev->rdev.lldi.rxq_ids[
+			cxgb4_port_idx(pdev) * step];
+		dev_put(pdev);
+	} else {
+		ep->l2t = cxgb4_l2t_get(cdev->rdev.lldi.l2t,
+					n, n->dev, 0);
+		if (!ep->l2t)
+			goto out;
+		ep->mtu = dst_mtu(ep->dst);
+		ep->tx_chan = cxgb4_port_chan(n->dev);
+		ep->smac_idx = (cxgb4_port_viid(n->dev) & 0x7F) << 1;
+		step = cdev->rdev.lldi.ntxq /
+			cdev->rdev.lldi.nchan;
+		ep->txq_idx = cxgb4_port_idx(n->dev) * step;
+		ep->ctrlq_idx = cxgb4_port_idx(n->dev);
+		step = cdev->rdev.lldi.nrxq /
+			cdev->rdev.lldi.nchan;
+		ep->rss_qid = cdev->rdev.lldi.rxq_ids[
+			cxgb4_port_idx(n->dev) * step];
+
+		if (clear_mpa_v1) {
+			ep->retry_with_mpa_v1 = 0;
+			ep->tried_with_mpa_v1 = 0;
+		}
+	}
+	err = 0;
+out:
+	rcu_read_unlock();
+
+	return err;
+}
+
 static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
 {
 	struct c4iw_ep *child_ep, *parent_ep;
@@ -1561,18 +1624,11 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
 	unsigned int stid = GET_POPEN_TID(ntohl(req->tos_stid));
 	struct tid_info *t = dev->rdev.lldi.tids;
 	unsigned int hwtid = GET_TID(req);
-	struct neighbour *neigh;
 	struct dst_entry *dst;
-	struct l2t_entry *l2t;
 	struct rtable *rt;
 	__be32 local_ip, peer_ip;
 	__be16 local_port, peer_port;
-	struct net_device *pdev;
-	u32 tx_chan, smac_idx;
-	u16 rss_qid;
-	u32 mtu;
-	int step;
-	int txq_idx, ctrlq_idx;
+	int err;
 
 	parent_ep = lookup_stid(t, stid);
 	PDBG("%s parent ep %p tid %u\n", __func__, parent_ep, hwtid);
@@ -1594,47 +1650,24 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
 		goto reject;
 	}
 	dst = &rt->dst;
-	neigh = dst_get_neighbour(dst);
-	if (neigh->dev->flags & IFF_LOOPBACK) {
-		pdev = ip_dev_find(&init_net, peer_ip);
-		BUG_ON(!pdev);
-		l2t = cxgb4_l2t_get(dev->rdev.lldi.l2t, neigh, pdev, 0);
-		mtu = pdev->mtu;
-		tx_chan = cxgb4_port_chan(pdev);
-		smac_idx = (cxgb4_port_viid(pdev) & 0x7F) << 1;
-		step = dev->rdev.lldi.ntxq / dev->rdev.lldi.nchan;
-		txq_idx = cxgb4_port_idx(pdev) * step;
-		ctrlq_idx = cxgb4_port_idx(pdev);
-		step = dev->rdev.lldi.nrxq / dev->rdev.lldi.nchan;
-		rss_qid = dev->rdev.lldi.rxq_ids[cxgb4_port_idx(pdev) * step];
-		dev_put(pdev);
-	} else {
-		l2t = cxgb4_l2t_get(dev->rdev.lldi.l2t, neigh, neigh->dev, 0);
-		mtu = dst_mtu(dst);
-		tx_chan = cxgb4_port_chan(neigh->dev);
-		smac_idx = (cxgb4_port_viid(neigh->dev) & 0x7F) << 1;
-		step = dev->rdev.lldi.ntxq / dev->rdev.lldi.nchan;
-		txq_idx = cxgb4_port_idx(neigh->dev) * step;
-		ctrlq_idx = cxgb4_port_idx(neigh->dev);
-		step = dev->rdev.lldi.nrxq / dev->rdev.lldi.nchan;
-		rss_qid = dev->rdev.lldi.rxq_ids[
-			  cxgb4_port_idx(neigh->dev) * step];
-	}
-	if (!l2t) {
-		printk(KERN_ERR MOD "%s - failed to allocate l2t entry!\n",
+
+	child_ep = alloc_ep(sizeof(*child_ep), GFP_KERNEL);
+	if (!child_ep) {
+		printk(KERN_ERR MOD "%s - failed to allocate ep entry!\n",
 		       __func__);
 		dst_release(dst);
 		goto reject;
 	}
 
-	child_ep = alloc_ep(sizeof(*child_ep), GFP_KERNEL);
-	if (!child_ep) {
-		printk(KERN_ERR MOD "%s - failed to allocate ep entry!\n",
+	err = import_ep(child_ep, peer_ip, dst, dev, false);
+	if (err) {
+		printk(KERN_ERR MOD "%s - failed to allocate l2t entry!\n",
 		       __func__);
-		cxgb4_l2t_release(l2t);
 		dst_release(dst);
+		kfree(child_ep);
 		goto reject;
 	}
+
 	state_set(&child_ep->com, CONNECTING);
 	child_ep->com.dev = dev;
 	child_ep->com.cm_id = NULL;
@@ -1647,18 +1680,11 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
 	c4iw_get_ep(&parent_ep->com);
 	child_ep->parent_ep = parent_ep;
 	child_ep->tos = GET_POPEN_TOS(ntohl(req->tos_stid));
-	child_ep->l2t = l2t;
 	child_ep->dst = dst;
 	child_ep->hwtid = hwtid;
-	child_ep->tx_chan = tx_chan;
-	child_ep->smac_idx = smac_idx;
-	child_ep->rss_qid = rss_qid;
-	child_ep->mtu = mtu;
-	child_ep->txq_idx = txq_idx;
-	child_ep->ctrlq_idx = ctrlq_idx;
 
 	PDBG("%s tx_chan %u smac_idx %u rss_qid %u\n", __func__,
-	     tx_chan, smac_idx, rss_qid);
+	     child_ep->tx_chan, child_ep->smac_idx, child_ep->rss_qid);
 
 	init_timer(&child_ep->timer);
 	cxgb4_insert_tid(t, child_ep, hwtid);
@@ -1788,11 +1814,8 @@ static int is_neg_adv_abort(unsigned int status)
 
 static int c4iw_reconnect(struct c4iw_ep *ep)
 {
-	int err = 0;
 	struct rtable *rt;
-	struct net_device *pdev;
-	struct neighbour *neigh;
-	int step;
+	int err = 0;
 
 	PDBG("%s qp %p cm_id %p\n", __func__, ep->com.qp, ep->com.cm_id);
 	init_timer(&ep->timer);
@@ -1820,45 +1843,10 @@ static int c4iw_reconnect(struct c4iw_ep *ep)
 	}
 	ep->dst = &rt->dst;
 
-	neigh = dst_get_neighbour(ep->dst);
-
-	/* get a l2t entry */
-	if (neigh->dev->flags & IFF_LOOPBACK) {
-		PDBG("%s LOOPBACK\n", __func__);
-		pdev = ip_dev_find(&init_net,
-				   ep->com.cm_id->remote_addr.sin_addr.s_addr);
-		ep->l2t = cxgb4_l2t_get(ep->com.dev->rdev.lldi.l2t,
-					neigh, pdev, 0);
-		ep->mtu = pdev->mtu;
-		ep->tx_chan = cxgb4_port_chan(pdev);
-		ep->smac_idx = (cxgb4_port_viid(pdev) & 0x7F) << 1;
-		step = ep->com.dev->rdev.lldi.ntxq /
-			ep->com.dev->rdev.lldi.nchan;
-		ep->txq_idx = cxgb4_port_idx(pdev) * step;
-		step = ep->com.dev->rdev.lldi.nrxq /
-			ep->com.dev->rdev.lldi.nchan;
-		ep->ctrlq_idx = cxgb4_port_idx(pdev);
-		ep->rss_qid = ep->com.dev->rdev.lldi.rxq_ids[
-			cxgb4_port_idx(pdev) * step];
-		dev_put(pdev);
-	} else {
-		ep->l2t = cxgb4_l2t_get(ep->com.dev->rdev.lldi.l2t,
-					neigh, neigh->dev, 0);
-		ep->mtu = dst_mtu(ep->dst);
-		ep->tx_chan = cxgb4_port_chan(neigh->dev);
-		ep->smac_idx = (cxgb4_port_viid(neigh->dev) & 0x7F) << 1;
-		step = ep->com.dev->rdev.lldi.ntxq /
-			ep->com.dev->rdev.lldi.nchan;
-		ep->txq_idx = cxgb4_port_idx(neigh->dev) * step;
-		ep->ctrlq_idx = cxgb4_port_idx(neigh->dev);
-		step = ep->com.dev->rdev.lldi.nrxq /
-			ep->com.dev->rdev.lldi.nchan;
-		ep->rss_qid = ep->com.dev->rdev.lldi.rxq_ids[
-			cxgb4_port_idx(neigh->dev) * step];
-	}
-	if (!ep->l2t) {
+	err = import_ep(ep, ep->com.cm_id->remote_addr.sin_addr.s_addr,
+			ep->dst, ep->com.dev, false);
+	if (err) {
 		printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
-		err = -ENOMEM;
 		goto fail4;
 	}
 
@@ -2234,13 +2222,10 @@ err:
 
 int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 {
-	int err = 0;
 	struct c4iw_dev *dev = to_c4iw_dev(cm_id->device);
 	struct c4iw_ep *ep;
 	struct rtable *rt;
-	struct net_device *pdev;
-	struct neighbour *neigh;
-	int step;
+	int err = 0;
 
 	if ((conn_param->ord > c4iw_max_read_depth) ||
 	    (conn_param->ird > c4iw_max_read_depth)) {
@@ -2301,47 +2286,10 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	}
 	ep->dst = &rt->dst;
 
-	neigh = dst_get_neighbour(ep->dst);
-
-	/* get a l2t entry */
-	if (neigh->dev->flags & IFF_LOOPBACK) {
-		PDBG("%s LOOPBACK\n", __func__);
-		pdev = ip_dev_find(&init_net,
-				   cm_id->remote_addr.sin_addr.s_addr);
-		ep->l2t = cxgb4_l2t_get(ep->com.dev->rdev.lldi.l2t,
-					neigh, pdev, 0);
-		ep->mtu = pdev->mtu;
-		ep->tx_chan = cxgb4_port_chan(pdev);
-		ep->smac_idx = (cxgb4_port_viid(pdev) & 0x7F) << 1;
-		step = ep->com.dev->rdev.lldi.ntxq /
-		       ep->com.dev->rdev.lldi.nchan;
-		ep->txq_idx = cxgb4_port_idx(pdev) * step;
-		step = ep->com.dev->rdev.lldi.nrxq /
-		       ep->com.dev->rdev.lldi.nchan;
-		ep->ctrlq_idx = cxgb4_port_idx(pdev);
-		ep->rss_qid = ep->com.dev->rdev.lldi.rxq_ids[
-			      cxgb4_port_idx(pdev) * step];
-		dev_put(pdev);
-	} else {
-		ep->l2t = cxgb4_l2t_get(ep->com.dev->rdev.lldi.l2t,
-					neigh, neigh->dev, 0);
-		ep->mtu = dst_mtu(ep->dst);
-		ep->tx_chan = cxgb4_port_chan(neigh->dev);
-		ep->smac_idx = (cxgb4_port_viid(neigh->dev) & 0x7F) << 1;
-		step = ep->com.dev->rdev.lldi.ntxq /
-		       ep->com.dev->rdev.lldi.nchan;
-		ep->txq_idx = cxgb4_port_idx(neigh->dev) * step;
-		ep->ctrlq_idx = cxgb4_port_idx(neigh->dev);
-		step = ep->com.dev->rdev.lldi.nrxq /
-		       ep->com.dev->rdev.lldi.nchan;
-		ep->rss_qid = ep->com.dev->rdev.lldi.rxq_ids[
-			      cxgb4_port_idx(neigh->dev) * step];
-		ep->retry_with_mpa_v1 = 0;
-		ep->tried_with_mpa_v1 = 0;
-	}
-	if (!ep->l2t) {
+	err = import_ep(ep, cm_id->remote_addr.sin_addr.s_addr,
+			ep->dst, ep->com.dev, true);
+	if (err) {
 		printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
-		err = -ENOMEM;
 		goto fail4;
 	}
 
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index f35a935..0f1607c 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -311,7 +311,7 @@ void c4iw_count_rcqes(struct t4_cq *cq, struct t4_wq *wq, int *count)
 	while (ptr != cq->sw_pidx) {
 		cqe = &cq->sw_queue[ptr];
 		if (RQ_TYPE(cqe) && (CQE_OPCODE(cqe) != FW_RI_READ_RESP) &&
-		    (CQE_QPID(cqe) == wq->rq.qid) && cqe_completes_wr(cqe, wq))
+		    (CQE_QPID(cqe) == wq->sq.qid) && cqe_completes_wr(cqe, wq))
 			(*count)++;
 		if (++ptr == cq->size)
 			ptr = 0;
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index f36da99..95c94d8 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -109,7 +109,8 @@ int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int ignore_mkey, int ignore_bkey,
 
 	err = mlx4_cmd_box(dev->dev, inmailbox->dma, outmailbox->dma,
 			   in_modifier, op_modifier,
-			   MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C);
+			   MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C,
+			   MLX4_CMD_NATIVE);
 
 	if (!err)
 		memcpy(response_mad, outmailbox->buf, 256);
@@ -330,7 +331,8 @@ static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		return IB_MAD_RESULT_FAILURE;
 
 	err = mlx4_cmd_box(dev->dev, 0, mailbox->dma, inmod, 0,
-			   MLX4_CMD_QUERY_IF_STAT, MLX4_CMD_TIME_CLASS_C);
+			   MLX4_CMD_QUERY_IF_STAT, MLX4_CMD_TIME_CLASS_C,
+			   MLX4_CMD_WRAPPED);
 	if (err)
 		err = IB_MAD_RESULT_FAILURE;
 	else {
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 77f3dbc..b8279de 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -177,7 +177,7 @@ mlx4_ib_port_link_layer(struct ib_device *device, u8 port_num)
 {
 	struct mlx4_dev *dev = to_mdev(device)->dev;
 
-	return dev->caps.port_mask & (1 << (port_num - 1)) ?
+	return dev->caps.port_mask[port_num] == MLX4_PORT_TYPE_IB ?
 		IB_LINK_LAYER_INFINIBAND : IB_LINK_LAYER_ETHERNET;
 }
 
@@ -434,7 +434,7 @@ static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask,
 	memset(mailbox->buf, 0, 256);
 	memcpy(mailbox->buf, props->node_desc, 64);
 	mlx4_cmd(to_mdev(ibdev)->dev, mailbox->dma, 1, 0,
-		 MLX4_CMD_SET_NODE, MLX4_CMD_TIME_CLASS_A);
+		 MLX4_CMD_SET_NODE, MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 
 	mlx4_free_cmd_mailbox(to_mdev(ibdev)->dev, mailbox);
 
@@ -463,7 +463,7 @@ static int mlx4_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols,
 	}
 
 	err = mlx4_cmd(dev->dev, mailbox->dma, port, is_eth, MLX4_CMD_SET_PORT,
-		       MLX4_CMD_TIME_CLASS_B);
+		       MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
 
 	mlx4_free_cmd_mailbox(dev->dev, mailbox);
 	return err;
@@ -899,7 +899,8 @@ static void update_gids_task(struct work_struct *work)
 	memcpy(gids, gw->gids, sizeof gw->gids);
 
 	err = mlx4_cmd(dev, mailbox->dma, MLX4_SET_PORT_GID_TABLE << 8 | gw->port,
-		       1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B);
+		       1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
+		       MLX4_CMD_NATIVE);
 	if (err)
 		printk(KERN_WARNING "set port command failed\n");
 	else {
@@ -1074,6 +1075,11 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 
 	printk_once(KERN_INFO "%s", mlx4_ib_version);
 
+	if (mlx4_is_mfunc(dev)) {
+		printk(KERN_WARNING "IB not yet supported in SRIOV\n");
+		return NULL;
+	}
+
 	mlx4_foreach_ib_transport_port(i, dev)
 		num_ports++;
 
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index dfce9ea..b1e6cae 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -1348,7 +1348,8 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi
 	else
 		netdev = nesvnic->netdev;
 
-	neigh = neigh_lookup(&arp_tbl, &rt->rt_gateway, netdev);
+	rcu_read_lock();
+	neigh = dst_get_neighbour_noref(&rt->dst);
 	if (neigh) {
 		if (neigh->nud_state & NUD_VALID) {
 			nes_debug(NES_DBG_CM, "Neighbor MAC address for 0x%08X"
@@ -1359,7 +1360,6 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi
 				if (!memcmp(nesadapter->arp_table[arpindex].mac_addr,
 					    neigh->ha, ETH_ALEN)) {
 					/* Mac address same as in nes_arp_table */
-					neigh_release(neigh);
 					ip_rt_put(rt);
 					return rc;
 				}
@@ -1373,13 +1373,11 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi
 					     dst_ip, NES_ARP_ADD);
 			rc = nes_arp_table(nesvnic->nesdev, dst_ip, NULL,
 					   NES_ARP_RESOLVE);
+		} else {
+			neigh_event_send(neigh, NULL);
 		}
-		neigh_release(neigh);
 	}
-
-	if ((neigh == NULL) || (!(neigh->nud_state & NUD_VALID)))
-		neigh_event_send(dst_get_neighbour(&rt->dst), NULL);
-
+	rcu_read_unlock();
 	ip_rt_put(rt);
 	return rc;
 }
diff --git a/drivers/infiniband/hw/nes/nes_nic.c b/drivers/infiniband/hw/nes/nes_nic.c
index c00d2f3..4b3fa71 100644
--- a/drivers/infiniband/hw/nes/nes_nic.c
+++ b/drivers/infiniband/hw/nes/nes_nic.c
@@ -1589,7 +1589,7 @@ static const struct ethtool_ops nes_ethtool_ops = {
 	.set_pauseparam = nes_netdev_set_pauseparam,
 };
 
-static void nes_vlan_mode(struct net_device *netdev, struct nes_device *nesdev, u32 features)
+static void nes_vlan_mode(struct net_device *netdev, struct nes_device *nesdev, netdev_features_t features)
 {
 	struct nes_adapter *nesadapter = nesdev->nesadapter;
 	u32 u32temp;
@@ -1610,7 +1610,7 @@ static void nes_vlan_mode(struct net_device *netdev, struct nes_device *nesdev,
 	spin_unlock_irqrestore(&nesadapter->phy_lock, flags);
 }
 
-static u32 nes_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t nes_fix_features(struct net_device *netdev, netdev_features_t features)
 {
 	/*
 	 * Since there is no support for separate rx/tx vlan accel
@@ -1624,7 +1624,7 @@ static u32 nes_fix_features(struct net_device *netdev, u32 features)
 	return features;
 }
 
-static int nes_set_features(struct net_device *netdev, u32 features)
+static int nes_set_features(struct net_device *netdev, netdev_features_t features)
 {
 	struct nes_vnic *nesvnic = netdev_priv(netdev);
 	struct nes_device *nesdev = nesvnic->nesdev;
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index 5bd2162..1d58959 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -2307,19 +2307,11 @@ static int qib_7322_bringup_serdes(struct qib_pportdata *ppd)
 		SYM_LSB(IBCCtrlA_0, MaxPktLen);
 	ppd->cpspec->ibcctrl_a = ibc; /* without linkcmd or linkinitcmd! */
 
-	/* initially come up waiting for TS1, without sending anything. */
-	val = ppd->cpspec->ibcctrl_a | (QLOGIC_IB_IBCC_LINKINITCMD_DISABLE <<
-		QLOGIC_IB_IBCC_LINKINITCMD_SHIFT);
-
-	ppd->cpspec->ibcctrl_a = val;
 	/*
 	 * Reset the PCS interface to the serdes (and also ibc, which is still
 	 * in reset from above).  Writes new value of ibcctrl_a as last step.
 	 */
 	qib_7322_mini_pcs_reset(ppd);
-	qib_write_kreg(dd, kr_scratch, 0ULL);
-	/* clear the linkinit cmds */
-	ppd->cpspec->ibcctrl_a &= ~SYM_MASK(IBCCtrlA_0, LinkInitCmd);
 
 	if (!ppd->cpspec->ibcctrl_b) {
 		unsigned lse = ppd->link_speed_enabled;
@@ -2385,6 +2377,14 @@ static int qib_7322_bringup_serdes(struct qib_pportdata *ppd)
 	ppd->cpspec->ibcctrl_a |= SYM_MASK(IBCCtrlA_0, IBLinkEn);
 	set_vls(ppd);
 
+	/* initially come up DISABLED, without sending anything. */
+	val = ppd->cpspec->ibcctrl_a | (QLOGIC_IB_IBCC_LINKINITCMD_DISABLE <<
+					QLOGIC_IB_IBCC_LINKINITCMD_SHIFT);
+	qib_write_kreg_port(ppd, krp_ibcctrl_a, val);
+	qib_write_kreg(dd, kr_scratch, 0ULL);
+	/* clear the linkinit cmds */
+	ppd->cpspec->ibcctrl_a = val & ~SYM_MASK(IBCCtrlA_0, LinkInitCmd);
+
 	/* be paranoid against later code motion, etc. */
 	spin_lock_irqsave(&dd->cspec->rcvmod_lock, flags);
 	ppd->p_rcvctrl |= SYM_MASK(RcvCtrl_0, RcvIBPortEnable);
@@ -5241,7 +5241,7 @@ static int qib_7322_ib_updown(struct qib_pportdata *ppd, int ibup, u64 ibcs)
 			   off */
 			if (ppd->dd->flags & QIB_HAS_QSFP) {
 				qd->t_insert = get_jiffies_64();
-				schedule_work(&qd->work);
+				queue_work(ib_wq, &qd->work);
 			}
 			spin_lock_irqsave(&ppd->sdma_lock, flags);
 			if (__qib_sdma_running(ppd))
diff --git a/drivers/infiniband/hw/qib/qib_qsfp.c b/drivers/infiniband/hw/qib/qib_qsfp.c
index e06c4ed..fa71b1e 100644
--- a/drivers/infiniband/hw/qib/qib_qsfp.c
+++ b/drivers/infiniband/hw/qib/qib_qsfp.c
@@ -480,18 +480,6 @@ void qib_qsfp_init(struct qib_qsfp_data *qd,
 	udelay(20); /* Generous RST dwell */
 
 	dd->f_gpio_mod(dd, mask, mask, mask);
-	/* Spec says module can take up to two seconds! */
-	mask = QSFP_GPIO_MOD_PRS_N;
-	if (qd->ppd->hw_pidx)
-		mask <<= QSFP_GPIO_PORT2_SHIFT;
-
-	/* Do not try to wait here. Better to let event handle it */
-	if (!qib_qsfp_mod_present(qd->ppd))
-		goto bail;
-	/* We see a module, but it may be unwise to look yet. Just schedule */
-	qd->t_insert = get_jiffies_64();
-	queue_work(ib_wq, &qd->work);
-bail:
 	return;
 }
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 0ef9af9..4115be5 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -57,21 +57,24 @@ struct ipoib_ah *ipoib_create_ah(struct net_device *dev,
 				 struct ib_pd *pd, struct ib_ah_attr *attr)
 {
 	struct ipoib_ah *ah;
+	struct ib_ah *vah;
 
 	ah = kmalloc(sizeof *ah, GFP_KERNEL);
 	if (!ah)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	ah->dev       = dev;
 	ah->last_send = 0;
 	kref_init(&ah->ref);
 
-	ah->ah = ib_create_ah(pd, attr);
-	if (IS_ERR(ah->ah)) {
+	vah = ib_create_ah(pd, attr);
+	if (IS_ERR(vah)) {
 		kfree(ah);
-		ah = NULL;
-	} else
+		ah = (struct ipoib_ah *)vah;
+	} else {
+		ah->ah = vah;
 		ipoib_dbg(netdev_priv(dev), "Created ah %p\n", ah->ah);
+	}
 
 	return ah;
 }
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 7567b60..3514ca0 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -171,7 +171,7 @@ static int ipoib_stop(struct net_device *dev)
 	return 0;
 }
 
-static u32 ipoib_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t ipoib_fix_features(struct net_device *dev, netdev_features_t features)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
@@ -432,7 +432,7 @@ static void path_rec_completion(int status,
 
 	spin_lock_irqsave(&priv->lock, flags);
 
-	if (ah) {
+	if (!IS_ERR_OR_NULL(ah)) {
 		path->pathrec = *pathrec;
 
 		old_ah   = path->ah;
@@ -555,15 +555,14 @@ static int path_rec_start(struct net_device *dev,
 	return 0;
 }
 
-static void neigh_add_path(struct sk_buff *skb, struct net_device *dev)
+/* called with rcu_read_lock */
+static void neigh_add_path(struct sk_buff *skb, struct neighbour *n, struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ipoib_path *path;
 	struct ipoib_neigh *neigh;
-	struct neighbour *n;
 	unsigned long flags;
 
-	n = dst_get_neighbour(skb_dst(skb));
 	neigh = ipoib_neigh_alloc(n, skb->dev);
 	if (!neigh) {
 		++dev->stats.tx_dropped;
@@ -636,16 +635,14 @@ err_drop:
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
-static void ipoib_path_lookup(struct sk_buff *skb, struct net_device *dev)
+/* called with rcu_read_lock */
+static void ipoib_path_lookup(struct sk_buff *skb, struct neighbour *n, struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(skb->dev);
-	struct dst_entry *dst = skb_dst(skb);
-	struct neighbour *n;
 
 	/* Look up path record for unicasts */
-	n = dst_get_neighbour(dst);
 	if (n->ha[4] != 0xff) {
-		neigh_add_path(skb, dev);
+		neigh_add_path(skb, n, dev);
 		return;
 	}
 
@@ -720,13 +717,19 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct neighbour *n = NULL;
 	unsigned long flags;
 
-	if (likely(skb_dst(skb)))
-		n = dst_get_neighbour(skb_dst(skb));
-
+	rcu_read_lock();
+	if (likely(skb_dst(skb))) {
+		n = dst_get_neighbour_noref(skb_dst(skb));
+		if (!n) {
+			++dev->stats.tx_dropped;
+			dev_kfree_skb_any(skb);
+			goto unlock;
+		}
+	}
 	if (likely(n)) {
 		if (unlikely(!*to_ipoib_neigh(n))) {
-			ipoib_path_lookup(skb, dev);
-			return NETDEV_TX_OK;
+			ipoib_path_lookup(skb, n, dev);
+			goto unlock;
 		}
 
 		neigh = *to_ipoib_neigh(n);
@@ -748,18 +751,18 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			list_del(&neigh->list);
 			ipoib_neigh_free(dev, neigh);
 			spin_unlock_irqrestore(&priv->lock, flags);
-			ipoib_path_lookup(skb, dev);
-			return NETDEV_TX_OK;
+			ipoib_path_lookup(skb, n, dev);
+			goto unlock;
 		}
 
 		if (ipoib_cm_get(neigh)) {
 			if (ipoib_cm_up(neigh)) {
 				ipoib_cm_send(dev, skb, ipoib_cm_get(neigh));
-				return NETDEV_TX_OK;
+				goto unlock;
 			}
 		} else if (neigh->ah) {
 			ipoib_send(dev, skb, neigh->ah, IPOIB_QPN(n->ha));
-			return NETDEV_TX_OK;
+			goto unlock;
 		}
 
 		if (skb_queue_len(&neigh->queue) < IPOIB_MAX_PATH_REC_QUEUE) {
@@ -793,13 +796,14 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev)
 					   phdr->hwaddr + 4);
 				dev_kfree_skb_any(skb);
 				++dev->stats.tx_dropped;
-				return NETDEV_TX_OK;
+				goto unlock;
 			}
 
 			unicast_arp_send(skb, dev, phdr);
 		}
 	}
-
+unlock:
+	rcu_read_unlock();
 	return NETDEV_TX_OK;
 }
 
@@ -837,7 +841,7 @@ static int ipoib_hard_header(struct sk_buff *skb,
 	dst = skb_dst(skb);
 	n = NULL;
 	if (dst)
-		n = dst_get_neighbour(dst);
+		n = dst_get_neighbour_noref_raw(dst);
 	if ((!dst || !n) && daddr) {
 		struct ipoib_pseudoheader *phdr =
 			(struct ipoib_pseudoheader *) skb_push(skb, sizeof *phdr);
@@ -1218,6 +1222,8 @@ static struct net_device *ipoib_add_port(const char *format,
 	priv->dev->mtu  = IPOIB_UD_MTU(priv->max_ib_mtu);
 	priv->mcast_mtu  = priv->admin_mtu = priv->dev->mtu;
 
+	priv->dev->neigh_priv_len = sizeof(struct ipoib_neigh);
+
 	result = ib_query_pkey(hca, port, 0, &priv->pkey);
 	if (result) {
 		printk(KERN_WARNING "%s: ib_query_pkey port %d failed (ret = %d)\n",
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 1b7a976..f7ff9dd 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -240,8 +240,11 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
 		av.grh.dgid = mcast->mcmember.mgid;
 
 		ah = ipoib_create_ah(dev, priv->pd, &av);
-		if (!ah) {
-			ipoib_warn(priv, "ib_address_create failed\n");
+		if (IS_ERR(ah)) {
+			ipoib_warn(priv, "ib_address_create failed %ld\n",
+				-PTR_ERR(ah));
+			/* use original error */
+			return PTR_ERR(ah);
 		} else {
 			spin_lock_irq(&priv->lock);
 			mcast->ah = ah;
@@ -266,7 +269,7 @@ static int ipoib_mcast_join_finish(struct ipoib_mcast *mcast,
 
 		skb->dev = dev;
 		if (dst)
-			n = dst_get_neighbour(dst);
+			n = dst_get_neighbour_noref_raw(dst);
 		if (!dst || !n) {
 			/* put pseudoheader back on for next time */
 			skb_push(skb, sizeof (struct ipoib_pseudoheader));
@@ -722,8 +725,10 @@ out:
 	if (mcast && mcast->ah) {
 		struct dst_entry *dst = skb_dst(skb);
 		struct neighbour *n = NULL;
+
+		rcu_read_lock();
 		if (dst)
-			n = dst_get_neighbour(dst);
+			n = dst_get_neighbour_noref(dst);
 		if (n && !*to_ipoib_neigh(n)) {
 			struct ipoib_neigh *neigh = ipoib_neigh_alloc(n,
 								      skb->dev);
@@ -734,7 +739,7 @@ out:
 				list_add_tail(&neigh->list, &mcast->neigh_list);
 			}
 		}
-
+		rcu_read_unlock();
 		spin_unlock_irqrestore(&priv->lock, flags);
 		ipoib_send(dev, skb, mcast->ah, IB_MULTICAST_QPN);
 		return;
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index 09b93b1..e2a9867 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1210,18 +1210,28 @@ static int elantech_reconnect(struct psmouse *psmouse)
  */
 static int elantech_set_properties(struct elantech_data *etd)
 {
+	/* This represents the version of IC body. */
 	int ver = (etd->fw_version & 0x0f0000) >> 16;
 
+	/* Early version of Elan touchpads doesn't obey the rule. */
 	if (etd->fw_version < 0x020030 || etd->fw_version == 0x020600)
 		etd->hw_version = 1;
-	else if (etd->fw_version < 0x150600)
-		etd->hw_version = 2;
-	else if (ver == 5)
-		etd->hw_version = 3;
-	else if (ver == 6)
-		etd->hw_version = 4;
-	else
-		return -1;
+	else {
+		switch (ver) {
+		case 2:
+		case 4:
+			etd->hw_version = 2;
+			break;
+		case 5:
+			etd->hw_version = 3;
+			break;
+		case 6:
+			etd->hw_version = 4;
+			break;
+		default:
+			return -1;
+		}
+	}
 
 	/*
 	 * Turn on packet checking by default.
diff --git a/drivers/input/serio/ams_delta_serio.c b/drivers/input/serio/ams_delta_serio.c
index 4b2a42f..d4d08bd 100644
--- a/drivers/input/serio/ams_delta_serio.c
+++ b/drivers/input/serio/ams_delta_serio.c
@@ -24,6 +24,7 @@
 #include <linux/irq.h>
 #include <linux/serio.h>
 #include <linux/slab.h>
+#include <linux/module.h>
 
 #include <asm/mach-types.h>
 #include <plat/board-ams-delta.h>
diff --git a/drivers/input/serio/i8042-x86ia64io.h b/drivers/input/serio/i8042-x86ia64io.h
index bb9f5d3..b4cfc6c 100644
--- a/drivers/input/serio/i8042-x86ia64io.h
+++ b/drivers/input/serio/i8042-x86ia64io.h
@@ -431,6 +431,13 @@ static const struct dmi_system_id __initconst i8042_dmi_nomux_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V13"),
 		},
 	},
+	{
+		/* Newer HP Pavilion dv4 models */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"),
+		},
+	},
 	{ }
 };
 
@@ -560,6 +567,13 @@ static const struct dmi_system_id __initconst i8042_dmi_notimeout_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Vostro V13"),
 		},
 	},
+	{
+		/* Newer HP Pavilion dv4 models */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion dv4 Notebook PC"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index c0c7820..a004c39 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3524,7 +3524,7 @@ found:
 	return 0;
 }
 
-int dmar_parse_rmrr_atsr_dev(void)
+int __init dmar_parse_rmrr_atsr_dev(void)
 {
 	struct dmar_rmrr_unit *rmrr, *rmrr_n;
 	struct dmar_atsr_unit *atsr, *atsr_n;
diff --git a/drivers/iommu/intr_remapping.c b/drivers/iommu/intr_remapping.c
index 07c9f18..6777ca0 100644
--- a/drivers/iommu/intr_remapping.c
+++ b/drivers/iommu/intr_remapping.c
@@ -773,7 +773,7 @@ int __init parse_ioapics_under_ir(void)
 	return ir_supported;
 }
 
-int ir_dev_scope_init(void)
+int __init ir_dev_scope_init(void)
 {
 	if (!intr_remapping_enabled)
 		return 0;
diff --git a/drivers/isdn/divert/divert_procfs.c b/drivers/isdn/divert/divert_procfs.c
index 33ec9e4..9021182 100644
--- a/drivers/isdn/divert/divert_procfs.c
+++ b/drivers/isdn/divert/divert_procfs.c
@@ -242,6 +242,12 @@ static int isdn_divert_ioctl_unlocked(struct file *file, uint cmd, ulong arg)
 		case IIOCDOCFINT:
 			if (!divert_if.drv_to_name(dioctl.cf_ctrl.drvid))
 				return (-EINVAL);	/* invalid driver */
+			if (strnlen(dioctl.cf_ctrl.msn, sizeof(dioctl.cf_ctrl.msn)) ==
+					sizeof(dioctl.cf_ctrl.msn))
+				return -EINVAL;
+			if (strnlen(dioctl.cf_ctrl.fwd_nr, sizeof(dioctl.cf_ctrl.fwd_nr)) ==
+					sizeof(dioctl.cf_ctrl.fwd_nr))
+				return -EINVAL;
 			if ((i = cf_command(dioctl.cf_ctrl.drvid,
 					    (cmd == IIOCDOCFACT) ? 1 : (cmd == IIOCDOCFDIS) ? 0 : 2,
 					    dioctl.cf_ctrl.cfproc,
diff --git a/drivers/isdn/gigaset/i4l.c b/drivers/isdn/gigaset/i4l.c
index 04231cb..1793ba1 100644
--- a/drivers/isdn/gigaset/i4l.c
+++ b/drivers/isdn/gigaset/i4l.c
@@ -624,8 +624,6 @@ int gigaset_isdn_regdev(struct cardstate *cs, const char *isdnid)
 {
 	isdn_if *iif;
 
-	pr_info("ISDN4Linux interface\n");
-
 	iif = kmalloc(sizeof *iif, GFP_KERNEL);
 	if (!iif) {
 		pr_err("out of memory\n");
@@ -684,6 +682,7 @@ void gigaset_isdn_unregdev(struct cardstate *cs)
  */
 void gigaset_isdn_regdrv(void)
 {
+	pr_info("ISDN4Linux interface\n");
 	/* nothing to do */
 }
 
diff --git a/drivers/isdn/i4l/isdn_net.c b/drivers/isdn/i4l/isdn_net.c
index 1f73d7f..2339d73 100644
--- a/drivers/isdn/i4l/isdn_net.c
+++ b/drivers/isdn/i4l/isdn_net.c
@@ -2756,6 +2756,9 @@ isdn_net_setcfg(isdn_net_ioctl_cfg * cfg)
 			char *c,
 			*e;
 
+			if (strnlen(cfg->drvid, sizeof(cfg->drvid)) ==
+					sizeof(cfg->drvid))
+				return -EINVAL;
 			drvidx = -1;
 			chidx = -1;
 			strcpy(drvid, cfg->drvid);
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index 661b692..6d5628b 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -270,11 +270,8 @@ void led_blink_set(struct led_classdev *led_cdev,
 	del_timer_sync(&led_cdev->blink_timer);
 
 	if (led_cdev->blink_set &&
-	    !led_cdev->blink_set(led_cdev, delay_on, delay_off)) {
-		led_cdev->blink_delay_on = *delay_on;
-		led_cdev->blink_delay_off = *delay_off;
+	    !led_cdev->blink_set(led_cdev, delay_on, delay_off))
 		return;
-	}
 
 	/* blink with 1 Hz as default if nothing specified */
 	if (!*delay_on && !*delay_off)
diff --git a/drivers/lguest/lguest_device.c b/drivers/lguest/lguest_device.c
index 0dc30ff..595d731 100644
--- a/drivers/lguest/lguest_device.c
+++ b/drivers/lguest/lguest_device.c
@@ -381,6 +381,11 @@ error:
 	return PTR_ERR(vqs[i]);
 }
 
+static const char *lg_bus_name(struct virtio_device *vdev)
+{
+	return "";
+}
+
 /* The ops structure which hooks everything together. */
 static struct virtio_config_ops lguest_config_ops = {
 	.get_features = lg_get_features,
@@ -392,6 +397,7 @@ static struct virtio_config_ops lguest_config_ops = {
 	.reset = lg_reset,
 	.find_vqs = lg_find_vqs,
 	.del_vqs = lg_del_vqs,
+	.bus_name = lg_bus_name,
 };
 
 /*
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index d593878..5664696 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -472,7 +472,7 @@ config BMP085
 	  module will be called bmp085.
 
 config PCH_PHUB
-	tristate "Intel EG20T PCH / OKI SEMICONDUCTOR IOH(ML7213/ML7223) PHUB"
+	tristate "Intel EG20T PCH/LAPIS Semicon IOH(ML7213/ML7223/ML7831) PHUB"
 	depends on PCI
 	help
 	  This driver is for PCH(Platform controller Hub) PHUB(Packet Hub) of
@@ -480,12 +480,13 @@ config PCH_PHUB
 	  processor. The Topcliff has MAC address and Option ROM data in SROM.
 	  This driver can access MAC address and Option ROM data in SROM.
 
-	  This driver also can be used for OKI SEMICONDUCTOR IOH(Input/
-	  Output Hub), ML7213 and ML7223.
-	  ML7213 IOH is for IVI(In-Vehicle Infotainment) use and ML7223 IOH is
-	  for MP(Media Phone) use.
-	  ML7213/ML7223 is companion chip for Intel Atom E6xx series.
-	  ML7213/ML7223 is completely compatible for Intel EG20T PCH.
+	  This driver also can be used for LAPIS Semiconductor's IOH,
+	  ML7213/ML7223/ML7831.
+	  ML7213 which is for IVI(In-Vehicle Infotainment) use.
+	  ML7223 IOH is for MP(Media Phone) use.
+	  ML7831 IOH is for general purpose use.
+	  ML7213/ML7223/ML7831 is companion chip for Intel Atom E6xx series.
+	  ML7213/ML7223/ML7831 is completely compatible for Intel EG20T PCH.
 
 	  To compile this driver as a module, choose M here: the module will
 	  be called pch_phub.
diff --git a/drivers/misc/ad525x_dpot.h b/drivers/misc/ad525x_dpot.h
index a662f59..82b2cb7 100644
--- a/drivers/misc/ad525x_dpot.h
+++ b/drivers/misc/ad525x_dpot.h
@@ -100,7 +100,7 @@ enum dpot_devid {
 	AD5293_ID = DPOT_CONF(F_RDACS_RW | F_SPI_16BIT, BRDAC0, 10, 27),
 	AD7376_ID = DPOT_CONF(F_RDACS_WONLY | F_AD_APPDATA | F_SPI_8BIT,
 			BRDAC0, 7, 28),
-	AD8400_ID = DPOT_CONF(F_RDACS_WONLY | F_AD_APPDATA | F_SPI_8BIT,
+	AD8400_ID = DPOT_CONF(F_RDACS_WONLY | F_AD_APPDATA | F_SPI_16BIT,
 			BRDAC0, 8, 29),
 	AD8402_ID = DPOT_CONF(F_RDACS_WONLY | F_AD_APPDATA | F_SPI_16BIT,
 			BRDAC0 | BRDAC1, 8, 30),
diff --git a/drivers/misc/carma/carma-fpga-program.c b/drivers/misc/carma/carma-fpga-program.c
index 7ce6065..eb5cd28 100644
--- a/drivers/misc/carma/carma-fpga-program.c
+++ b/drivers/misc/carma/carma-fpga-program.c
@@ -945,8 +945,7 @@ static int fpga_of_remove(struct platform_device *op)
 /* CTL-CPLD Version Register */
 #define CTL_CPLD_VERSION	0x2000
 
-static int fpga_of_probe(struct platform_device *op,
-			 const struct of_device_id *match)
+static int fpga_of_probe(struct platform_device *op)
 {
 	struct device_node *of_node = op->dev.of_node;
 	struct device *this_device;
@@ -1107,7 +1106,7 @@ static struct of_device_id fpga_of_match[] = {
 	{},
 };
 
-static struct of_platform_driver fpga_of_driver = {
+static struct platform_driver fpga_of_driver = {
 	.probe		= fpga_of_probe,
 	.remove		= fpga_of_remove,
 	.driver		= {
@@ -1124,12 +1123,12 @@ static struct of_platform_driver fpga_of_driver = {
 static int __init fpga_init(void)
 {
 	led_trigger_register_simple("fpga", &ledtrig_fpga);
-	return of_register_platform_driver(&fpga_of_driver);
+	return platform_driver_register(&fpga_of_driver);
 }
 
 static void __exit fpga_exit(void)
 {
-	of_unregister_platform_driver(&fpga_of_driver);
+	platform_driver_unregister(&fpga_of_driver);
 	led_trigger_unregister_simple(ledtrig_fpga);
 }
 
diff --git a/drivers/misc/carma/carma-fpga.c b/drivers/misc/carma/carma-fpga.c
index 3965821..14e974b2 100644
--- a/drivers/misc/carma/carma-fpga.c
+++ b/drivers/misc/carma/carma-fpga.c
@@ -1249,8 +1249,7 @@ static bool dma_filter(struct dma_chan *chan, void *data)
 	return true;
 }
 
-static int data_of_probe(struct platform_device *op,
-			 const struct of_device_id *match)
+static int data_of_probe(struct platform_device *op)
 {
 	struct device_node *of_node = op->dev.of_node;
 	struct device *this_device;
@@ -1401,7 +1400,7 @@ static struct of_device_id data_of_match[] = {
 	{},
 };
 
-static struct of_platform_driver data_of_driver = {
+static struct platform_driver data_of_driver = {
 	.probe		= data_of_probe,
 	.remove		= data_of_remove,
 	.driver		= {
@@ -1417,12 +1416,12 @@ static struct of_platform_driver data_of_driver = {
 
 static int __init data_init(void)
 {
-	return of_register_platform_driver(&data_of_driver);
+	return platform_driver_register(&data_of_driver);
 }
 
 static void __exit data_exit(void)
 {
-	of_unregister_platform_driver(&data_of_driver);
+	platform_driver_unregister(&data_of_driver);
 }
 
 MODULE_AUTHOR("Ira W. Snyder <iws@ovro.caltech.edu>");
diff --git a/drivers/misc/eeprom/Kconfig b/drivers/misc/eeprom/Kconfig
index 26cf12c..701edf6 100644
--- a/drivers/misc/eeprom/Kconfig
+++ b/drivers/misc/eeprom/Kconfig
@@ -85,7 +85,7 @@ config EEPROM_93XX46
 
 config EEPROM_DIGSY_MTC_CFG
 	bool "DigsyMTC display configuration EEPROMs device"
-	depends on PPC_MPC5200_GPIO && GPIOLIB && SPI_GPIO
+	depends on GPIO_MPC5200 && SPI_GPIO
 	help
 	  This option enables access to display configuration EEPROMs
 	  on digsy_mtc board. You have to additionally select Microwire
diff --git a/drivers/misc/eeprom/eeprom_93cx6.c b/drivers/misc/eeprom/eeprom_93cx6.c
index 7b33de9..0ff4b02 100644
--- a/drivers/misc/eeprom/eeprom_93cx6.c
+++ b/drivers/misc/eeprom/eeprom_93cx6.c
@@ -63,6 +63,7 @@ static void eeprom_93cx6_startup(struct eeprom_93cx6 *eeprom)
 	eeprom->reg_data_out = 0;
 	eeprom->reg_data_clock = 0;
 	eeprom->reg_chip_select = 1;
+	eeprom->drive_data = 1;
 	eeprom->register_write(eeprom);
 
 	/*
@@ -101,6 +102,7 @@ static void eeprom_93cx6_write_bits(struct eeprom_93cx6 *eeprom,
 	 */
 	eeprom->reg_data_in = 0;
 	eeprom->reg_data_out = 0;
+	eeprom->drive_data = 1;
 
 	/*
 	 * Start writing all bits.
@@ -140,6 +142,7 @@ static void eeprom_93cx6_read_bits(struct eeprom_93cx6 *eeprom,
 	 */
 	eeprom->reg_data_in = 0;
 	eeprom->reg_data_out = 0;
+	eeprom->drive_data = 0;
 
 	/*
 	 * Start reading all bits.
@@ -231,3 +234,88 @@ void eeprom_93cx6_multiread(struct eeprom_93cx6 *eeprom, const u8 word,
 }
 EXPORT_SYMBOL_GPL(eeprom_93cx6_multiread);
 
+/**
+ * eeprom_93cx6_wren - set the write enable state
+ * @eeprom: Pointer to eeprom structure
+ * @enable: true to enable writes, otherwise disable writes
+ *
+ * Set the EEPROM write enable state to either allow or deny
+ * writes depending on the @enable value.
+ */
+void eeprom_93cx6_wren(struct eeprom_93cx6 *eeprom, bool enable)
+{
+	u16 command;
+
+	/* start the command */
+	eeprom_93cx6_startup(eeprom);
+
+	/* create command to enable/disable */
+
+	command = enable ? PCI_EEPROM_EWEN_OPCODE : PCI_EEPROM_EWDS_OPCODE;
+	command <<= (eeprom->width - 2);
+
+	eeprom_93cx6_write_bits(eeprom, command,
+				PCI_EEPROM_WIDTH_OPCODE + eeprom->width);
+
+	eeprom_93cx6_cleanup(eeprom);
+}
+EXPORT_SYMBOL_GPL(eeprom_93cx6_wren);
+
+/**
+ * eeprom_93cx6_write - write data to the EEPROM
+ * @eeprom: Pointer to eeprom structure
+ * @addr: Address to write data to.
+ * @data: The data to write to address @addr.
+ *
+ * Write the @data to the specified @addr in the EEPROM and
+ * waiting for the device to finish writing.
+ *
+ * Note, since we do not expect large number of write operations
+ * we delay in between parts of the operation to avoid using excessive
+ * amounts of CPU time busy waiting.
+ */
+void eeprom_93cx6_write(struct eeprom_93cx6 *eeprom, u8 addr, u16 data)
+{
+	int timeout = 100;
+	u16 command;
+
+	/* start the command */
+	eeprom_93cx6_startup(eeprom);
+
+	command = PCI_EEPROM_WRITE_OPCODE << eeprom->width;
+	command |= addr;
+
+	/* send write command */
+	eeprom_93cx6_write_bits(eeprom, command,
+				PCI_EEPROM_WIDTH_OPCODE + eeprom->width);
+
+	/* send data */
+	eeprom_93cx6_write_bits(eeprom, data, 16);
+
+	/* get ready to check for busy */
+	eeprom->drive_data = 0;
+	eeprom->reg_chip_select = 1;
+	eeprom->register_write(eeprom);
+
+	/* wait at-least 250ns to get DO to be the busy signal */
+	usleep_range(1000, 2000);
+
+	/* wait for DO to go high to signify finish */
+
+	while (true) {
+		eeprom->register_read(eeprom);
+
+		if (eeprom->reg_data_out)
+			break;
+
+		usleep_range(1000, 2000);
+
+		if (--timeout <= 0) {
+			printk(KERN_ERR "%s: timeout\n", __func__);
+			break;
+		}
+	}
+
+	eeprom_93cx6_cleanup(eeprom);
+}
+EXPORT_SYMBOL_GPL(eeprom_93cx6_write);
diff --git a/drivers/misc/pch_phub.c b/drivers/misc/pch_phub.c
index dee33ad..10fc478 100644
--- a/drivers/misc/pch_phub.c
+++ b/drivers/misc/pch_phub.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2010 OKI SEMICONDUCTOR CO., LTD.
+ * Copyright (C) 2011 LAPIS Semiconductor Co., Ltd.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -41,10 +41,10 @@
 #define PCH_PHUB_ROM_START_ADDR_EG20T 0x80 /* ROM data area start address offset
 					      (Intel EG20T PCH)*/
 #define PCH_PHUB_ROM_START_ADDR_ML7213 0x400 /* ROM data area start address
-						offset(OKI SEMICONDUCTOR ML7213)
+						offset(LAPIS Semicon ML7213)
 					      */
 #define PCH_PHUB_ROM_START_ADDR_ML7223 0x400 /* ROM data area start address
-						offset(OKI SEMICONDUCTOR ML7223)
+						offset(LAPIS Semicon ML7223)
 					      */
 
 /* MAX number of INT_REDUCE_CONTROL registers */
@@ -73,6 +73,9 @@
 #define PCI_DEVICE_ID_ROHM_ML7223_mPHUB	0x8012 /* for Bus-m */
 #define PCI_DEVICE_ID_ROHM_ML7223_nPHUB	0x8002 /* for Bus-n */
 
+/* Macros for ML7831 */
+#define PCI_DEVICE_ID_ROHM_ML7831_PHUB 0x8801
+
 /* SROM ACCESS Macro */
 #define PCH_WORD_ADDR_MASK (~((1 << 2) - 1))
 
@@ -115,6 +118,7 @@
  * @pch_mac_start_address:		MAC address area start address
  * @pch_opt_rom_start_address:		Option ROM start address
  * @ioh_type:				Save IOH type
+ * @pdev:				pointer to pci device struct
  */
 struct pch_phub_reg {
 	u32 phub_id_reg;
@@ -136,6 +140,7 @@ struct pch_phub_reg {
 	u32 pch_mac_start_address;
 	u32 pch_opt_rom_start_address;
 	int ioh_type;
+	struct pci_dev *pdev;
 };
 
 /* SROM SPEC for MAC address assignment offset */
@@ -471,7 +476,7 @@ static int pch_phub_write_gbe_mac_addr(struct pch_phub_reg *chip, u8 *data)
 	int retval;
 	int i;
 
-	if (chip->ioh_type == 1) /* EG20T */
+	if ((chip->ioh_type == 1) || (chip->ioh_type == 5)) /* EG20T or ML7831*/
 		retval = pch_phub_gbe_serial_rom_conf(chip);
 	else	/* ML7223 */
 		retval = pch_phub_gbe_serial_rom_conf_mp(chip);
@@ -498,6 +503,7 @@ static ssize_t pch_phub_bin_read(struct file *filp, struct kobject *kobj,
 	unsigned int orom_size;
 	int ret;
 	int err;
+	ssize_t rom_size;
 
 	struct pch_phub_reg *chip =
 		dev_get_drvdata(container_of(kobj, struct device, kobj));
@@ -509,6 +515,10 @@ static ssize_t pch_phub_bin_read(struct file *filp, struct kobject *kobj,
 	}
 
 	/* Get Rom signature */
+	chip->pch_phub_extrom_base_address = pci_map_rom(chip->pdev, &rom_size);
+	if (!chip->pch_phub_extrom_base_address)
+		goto exrom_map_err;
+
 	pch_phub_read_serial_rom(chip, chip->pch_opt_rom_start_address,
 				(unsigned char *)&rom_signature);
 	rom_signature &= 0xff;
@@ -539,10 +549,13 @@ static ssize_t pch_phub_bin_read(struct file *filp, struct kobject *kobj,
 		goto return_err;
 	}
 return_ok:
+	pci_unmap_rom(chip->pdev, chip->pch_phub_extrom_base_address);
 	mutex_unlock(&pch_phub_mutex);
 	return addr_offset;
 
 return_err:
+	pci_unmap_rom(chip->pdev, chip->pch_phub_extrom_base_address);
+exrom_map_err:
 	mutex_unlock(&pch_phub_mutex);
 return_err_nomutex:
 	return err;
@@ -555,6 +568,7 @@ static ssize_t pch_phub_bin_write(struct file *filp, struct kobject *kobj,
 	int err;
 	unsigned int addr_offset;
 	int ret;
+	ssize_t rom_size;
 	struct pch_phub_reg *chip =
 		dev_get_drvdata(container_of(kobj, struct device, kobj));
 
@@ -571,6 +585,12 @@ static ssize_t pch_phub_bin_write(struct file *filp, struct kobject *kobj,
 		goto return_ok;
 	}
 
+	chip->pch_phub_extrom_base_address = pci_map_rom(chip->pdev, &rom_size);
+	if (!chip->pch_phub_extrom_base_address) {
+		err = -ENOMEM;
+		goto exrom_map_err;
+	}
+
 	for (addr_offset = 0; addr_offset < count; addr_offset++) {
 		if (PCH_PHUB_OROM_SIZE < off + addr_offset)
 			goto return_ok;
@@ -585,10 +605,14 @@ static ssize_t pch_phub_bin_write(struct file *filp, struct kobject *kobj,
 	}
 
 return_ok:
+	pci_unmap_rom(chip->pdev, chip->pch_phub_extrom_base_address);
 	mutex_unlock(&pch_phub_mutex);
 	return addr_offset;
 
 return_err:
+	pci_unmap_rom(chip->pdev, chip->pch_phub_extrom_base_address);
+
+exrom_map_err:
 	mutex_unlock(&pch_phub_mutex);
 	return err;
 }
@@ -598,8 +622,14 @@ static ssize_t show_pch_mac(struct device *dev, struct device_attribute *attr,
 {
 	u8 mac[8];
 	struct pch_phub_reg *chip = dev_get_drvdata(dev);
+	ssize_t rom_size;
+
+	chip->pch_phub_extrom_base_address = pci_map_rom(chip->pdev, &rom_size);
+	if (!chip->pch_phub_extrom_base_address)
+		return -ENOMEM;
 
 	pch_phub_read_gbe_mac_addr(chip, mac);
+	pci_unmap_rom(chip->pdev, chip->pch_phub_extrom_base_address);
 
 	return sprintf(buf, "%pM\n", mac);
 }
@@ -608,6 +638,7 @@ static ssize_t store_pch_mac(struct device *dev, struct device_attribute *attr,
 			     const char *buf, size_t count)
 {
 	u8 mac[6];
+	ssize_t rom_size;
 	struct pch_phub_reg *chip = dev_get_drvdata(dev);
 
 	if (count != 18)
@@ -617,7 +648,12 @@ static ssize_t store_pch_mac(struct device *dev, struct device_attribute *attr,
 		(u32 *)&mac[0], (u32 *)&mac[1], (u32 *)&mac[2], (u32 *)&mac[3],
 		(u32 *)&mac[4], (u32 *)&mac[5]);
 
+	chip->pch_phub_extrom_base_address = pci_map_rom(chip->pdev, &rom_size);
+	if (!chip->pch_phub_extrom_base_address)
+		return -ENOMEM;
+
 	pch_phub_write_gbe_mac_addr(chip, mac);
+	pci_unmap_rom(chip->pdev, chip->pch_phub_extrom_base_address);
 
 	return count;
 }
@@ -640,7 +676,6 @@ static int __devinit pch_phub_probe(struct pci_dev *pdev,
 	int retval;
 
 	int ret;
-	ssize_t rom_size;
 	struct pch_phub_reg *chip;
 
 	chip = kzalloc(sizeof(struct pch_phub_reg), GFP_KERNEL);
@@ -677,19 +712,7 @@ static int __devinit pch_phub_probe(struct pci_dev *pdev,
 		"in pch_phub_base_address variable is %p\n", __func__,
 		chip->pch_phub_base_address);
 
-	if (id->driver_data != 3) {
-		chip->pch_phub_extrom_base_address =\
-						   pci_map_rom(pdev, &rom_size);
-		if (chip->pch_phub_extrom_base_address == 0) {
-			dev_err(&pdev->dev, "%s: pci_map_rom FAILED", __func__);
-			ret = -ENOMEM;
-			goto err_pci_map;
-		}
-		dev_dbg(&pdev->dev, "%s : "
-			"pci_map_rom SUCCESS and value in "
-			"pch_phub_extrom_base_address variable is %p\n",
-			__func__, chip->pch_phub_extrom_base_address);
-	}
+	chip->pdev = pdev; /* Save pci device struct */
 
 	if (id->driver_data == 1) { /* EG20T PCH */
 		const char *board_name;
@@ -763,6 +786,22 @@ static int __devinit pch_phub_probe(struct pci_dev *pdev,
 		chip->pch_opt_rom_start_address =\
 						 PCH_PHUB_ROM_START_ADDR_ML7223;
 		chip->pch_mac_start_address = PCH_PHUB_MAC_START_ADDR_ML7223;
+	} else if (id->driver_data == 5) { /* ML7831 */
+		retval = sysfs_create_file(&pdev->dev.kobj,
+					   &dev_attr_pch_mac.attr);
+		if (retval)
+			goto err_sysfs_create;
+
+		retval = sysfs_create_bin_file(&pdev->dev.kobj, &pch_bin_attr);
+		if (retval)
+			goto exit_bin_attr;
+
+		/* set the prefech value */
+		iowrite32(0x000affaa, chip->pch_phub_base_address + 0x14);
+		/* set the interrupt delay value */
+		iowrite32(0x25, chip->pch_phub_base_address + 0x44);
+		chip->pch_opt_rom_start_address = PCH_PHUB_ROM_START_ADDR_EG20T;
+		chip->pch_mac_start_address = PCH_PHUB_MAC_START_ADDR_EG20T;
 	}
 
 	chip->ioh_type = id->driver_data;
@@ -773,8 +812,6 @@ exit_bin_attr:
 	sysfs_remove_file(&pdev->dev.kobj, &dev_attr_pch_mac.attr);
 
 err_sysfs_create:
-	pci_unmap_rom(pdev, chip->pch_phub_extrom_base_address);
-err_pci_map:
 	pci_iounmap(pdev, chip->pch_phub_base_address);
 err_pci_iomap:
 	pci_release_regions(pdev);
@@ -792,7 +829,6 @@ static void __devexit pch_phub_remove(struct pci_dev *pdev)
 
 	sysfs_remove_file(&pdev->dev.kobj, &dev_attr_pch_mac.attr);
 	sysfs_remove_bin_file(&pdev->dev.kobj, &pch_bin_attr);
-	pci_unmap_rom(pdev, chip->pch_phub_extrom_base_address);
 	pci_iounmap(pdev, chip->pch_phub_base_address);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
@@ -847,6 +883,7 @@ static struct pci_device_id pch_phub_pcidev_id[] = {
 	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ROHM_ML7213_PHUB), 2,  },
 	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ROHM_ML7223_mPHUB), 3,  },
 	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ROHM_ML7223_nPHUB), 4,  },
+	{ PCI_VDEVICE(ROHM, PCI_DEVICE_ID_ROHM_ML7831_PHUB), 5,  },
 	{ }
 };
 MODULE_DEVICE_TABLE(pci, pch_phub_pcidev_id);
@@ -873,5 +910,5 @@ static void __exit pch_phub_pci_exit(void)
 module_init(pch_phub_pci_init);
 module_exit(pch_phub_pci_exit);
 
-MODULE_DESCRIPTION("Intel EG20T PCH/OKI SEMICONDUCTOR IOH(ML7213/ML7223) PHUB");
+MODULE_DESCRIPTION("Intel EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7223) PHUB");
 MODULE_LICENSE("GPL");
diff --git a/drivers/misc/sgi-xp/xpnet.c b/drivers/misc/sgi-xp/xpnet.c
index 42f0673..3fac67a 100644
--- a/drivers/misc/sgi-xp/xpnet.c
+++ b/drivers/misc/sgi-xp/xpnet.c
@@ -576,7 +576,7 @@ xpnet_init(void)
 	 * report an error if the data is not retrievable and the
 	 * packet will be dropped.
 	 */
-	xpnet_device->features = NETIF_F_NO_CSUM;
+	xpnet_device->features = NETIF_F_HW_CSUM;
 
 	result = register_netdev(xpnet_device);
 	if (result != 0) {
diff --git a/drivers/misc/spear13xx_pcie_gadget.c b/drivers/misc/spear13xx_pcie_gadget.c
index cfbddbe..43d073b 100644
--- a/drivers/misc/spear13xx_pcie_gadget.c
+++ b/drivers/misc/spear13xx_pcie_gadget.c
@@ -903,6 +903,6 @@ static void __exit spear_pcie_gadget_exit(void)
 }
 module_exit(spear_pcie_gadget_exit);
 
-MODULE_ALIAS("pcie-gadget-spear");
+MODULE_ALIAS("platform:pcie-gadget-spear");
 MODULE_AUTHOR("Pratyush Anand");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 583f66c..9845afb 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -125,6 +125,8 @@ config IFB
 	  'ifb1' etc.
 	  Look at the iproute2 documentation directory for usage etc
 
+source "drivers/net/team/Kconfig"
+
 config MACVLAN
 	tristate "MAC-VLAN support (EXPERIMENTAL)"
 	depends on EXPERIMENTAL
@@ -241,10 +243,14 @@ source "drivers/atm/Kconfig"
 
 source "drivers/net/caif/Kconfig"
 
+source "drivers/net/dsa/Kconfig"
+
 source "drivers/net/ethernet/Kconfig"
 
 source "drivers/net/fddi/Kconfig"
 
+source "drivers/net/hippi/Kconfig"
+
 config NET_SB1000
 	tristate "General Instruments Surfboard 1000"
 	depends on PNP
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index fa877cd..1988881 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_NET) += Space.o loopback.o
 obj-$(CONFIG_NETCONSOLE) += netconsole.o
 obj-$(CONFIG_PHYLIB) += phy/
 obj-$(CONFIG_RIONET) += rionet.o
+obj-$(CONFIG_NET_TEAM) += team/
 obj-$(CONFIG_TUN) += tun.o
 obj-$(CONFIG_VETH) += veth.o
 obj-$(CONFIG_VIRTIO_NET) += virtio_net.o
@@ -29,6 +30,7 @@ obj-$(CONFIG_DEV_APPLETALK) += appletalk/
 obj-$(CONFIG_CAIF) += caif/
 obj-$(CONFIG_CAN) += can/
 obj-$(CONFIG_ETRAX_ETHERNET) += cris/
+obj-$(CONFIG_NET_DSA) += dsa/
 obj-$(CONFIG_ETHERNET) += ethernet/
 obj-$(CONFIG_FDDI) += fddi/
 obj-$(CONFIG_HIPPI) += hippi/
diff --git a/drivers/net/arcnet/Kconfig b/drivers/net/arcnet/Kconfig
index a73d9dc..84fb634 100644
--- a/drivers/net/arcnet/Kconfig
+++ b/drivers/net/arcnet/Kconfig
@@ -4,7 +4,7 @@
 
 menuconfig ARCNET
 	depends on NETDEVICES && (ISA || PCI || PCMCIA)
-	bool "ARCnet support"
+	tristate "ARCnet support"
 	---help---
 	  If you have a network card of this type, say Y and check out the
 	  (arguably) beautiful poetry in
diff --git a/drivers/net/bonding/bond_ipv6.c b/drivers/net/bonding/bond_ipv6.c
deleted file mode 100644
index 027a0ee..0000000
--- a/drivers/net/bonding/bond_ipv6.c
+++ /dev/null
@@ -1,225 +0,0 @@
-/*
- * Copyright(c) 2008 Hewlett-Packard Development Company, L.P.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
- * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
- * for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
- *
- * The full GNU General Public License is included in this distribution in the
- * file called LICENSE.
- *
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/types.h>
-#include <linux/if_vlan.h>
-#include <net/ipv6.h>
-#include <net/ndisc.h>
-#include <net/addrconf.h>
-#include <net/netns/generic.h>
-#include "bonding.h"
-
-/*
- * Assign bond->master_ipv6 to the next IPv6 address in the list, or
- * zero it out if there are none.
- */
-static void bond_glean_dev_ipv6(struct net_device *dev, struct in6_addr *addr)
-{
-	struct inet6_dev *idev;
-
-	if (!dev)
-		return;
-
-	idev = in6_dev_get(dev);
-	if (!idev)
-		return;
-
-	read_lock_bh(&idev->lock);
-	if (!list_empty(&idev->addr_list)) {
-		struct inet6_ifaddr *ifa
-			= list_first_entry(&idev->addr_list,
-					   struct inet6_ifaddr, if_list);
-		ipv6_addr_copy(addr, &ifa->addr);
-	} else
-		ipv6_addr_set(addr, 0, 0, 0, 0);
-
-	read_unlock_bh(&idev->lock);
-
-	in6_dev_put(idev);
-}
-
-static void bond_na_send(struct net_device *slave_dev,
-			 struct in6_addr *daddr,
-			 int router,
-			 unsigned short vlan_id)
-{
-	struct in6_addr mcaddr;
-	struct icmp6hdr icmp6h = {
-		.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT,
-	};
-	struct sk_buff *skb;
-
-	icmp6h.icmp6_router = router;
-	icmp6h.icmp6_solicited = 0;
-	icmp6h.icmp6_override = 1;
-
-	addrconf_addr_solict_mult(daddr, &mcaddr);
-
-	pr_debug("ipv6 na on slave %s: dest %pI6, src %pI6\n",
-		 slave_dev->name, &mcaddr, daddr);
-
-	skb = ndisc_build_skb(slave_dev, &mcaddr, daddr, &icmp6h, daddr,
-			      ND_OPT_TARGET_LL_ADDR);
-
-	if (!skb) {
-		pr_err("NA packet allocation failed\n");
-		return;
-	}
-
-	if (vlan_id) {
-		/* The Ethernet header is not present yet, so it is
-		 * too early to insert a VLAN tag.  Force use of an
-		 * out-of-line tag here and let dev_hard_start_xmit()
-		 * insert it if the slave hardware can't.
-		 */
-		skb = __vlan_hwaccel_put_tag(skb, vlan_id);
-		if (!skb) {
-			pr_err("failed to insert VLAN tag\n");
-			return;
-		}
-	}
-
-	ndisc_send_skb(skb, slave_dev, NULL, &mcaddr, daddr, &icmp6h);
-}
-
-/*
- * Kick out an unsolicited Neighbor Advertisement for an IPv6 address on
- * the bonding master.  This will help the switch learn our address
- * if in active-backup mode.
- *
- * Caller must hold curr_slave_lock for read or better
- */
-void bond_send_unsolicited_na(struct bonding *bond)
-{
-	struct slave *slave = bond->curr_active_slave;
-	struct vlan_entry *vlan;
-	struct inet6_dev *idev;
-	int is_router;
-
-	pr_debug("%s: bond %s slave %s\n", bond->dev->name,
-		 __func__, slave ? slave->dev->name : "NULL");
-
-	if (!slave || !bond->send_unsol_na ||
-	    test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
-		return;
-
-	bond->send_unsol_na--;
-
-	idev = in6_dev_get(bond->dev);
-	if (!idev)
-		return;
-
-	is_router = !!idev->cnf.forwarding;
-
-	in6_dev_put(idev);
-
-	if (!ipv6_addr_any(&bond->master_ipv6))
-		bond_na_send(slave->dev, &bond->master_ipv6, is_router, 0);
-
-	list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
-		if (!ipv6_addr_any(&vlan->vlan_ipv6)) {
-			bond_na_send(slave->dev, &vlan->vlan_ipv6, is_router,
-				     vlan->vlan_id);
-		}
-	}
-}
-
-/*
- * bond_inet6addr_event: handle inet6addr notifier chain events.
- *
- * We keep track of device IPv6 addresses primarily to use as source
- * addresses in NS probes.
- *
- * We track one IPv6 for the main device (if it has one).
- */
-static int bond_inet6addr_event(struct notifier_block *this,
-				unsigned long event,
-				void *ptr)
-{
-	struct inet6_ifaddr *ifa = ptr;
-	struct net_device *vlan_dev, *event_dev = ifa->idev->dev;
-	struct bonding *bond;
-	struct vlan_entry *vlan;
-	struct bond_net *bn = net_generic(dev_net(event_dev), bond_net_id);
-
-	list_for_each_entry(bond, &bn->dev_list, bond_list) {
-		if (bond->dev == event_dev) {
-			switch (event) {
-			case NETDEV_UP:
-				if (ipv6_addr_any(&bond->master_ipv6))
-					ipv6_addr_copy(&bond->master_ipv6,
-						       &ifa->addr);
-				return NOTIFY_OK;
-			case NETDEV_DOWN:
-				if (ipv6_addr_equal(&bond->master_ipv6,
-						    &ifa->addr))
-					bond_glean_dev_ipv6(bond->dev,
-							    &bond->master_ipv6);
-				return NOTIFY_OK;
-			default:
-				return NOTIFY_DONE;
-			}
-		}
-
-		list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
-			rcu_read_lock();
-			vlan_dev = __vlan_find_dev_deep(bond->dev,
-							vlan->vlan_id);
-			rcu_read_unlock();
-			if (vlan_dev == event_dev) {
-				switch (event) {
-				case NETDEV_UP:
-					if (ipv6_addr_any(&vlan->vlan_ipv6))
-						ipv6_addr_copy(&vlan->vlan_ipv6,
-							       &ifa->addr);
-					return NOTIFY_OK;
-				case NETDEV_DOWN:
-					if (ipv6_addr_equal(&vlan->vlan_ipv6,
-							    &ifa->addr))
-						bond_glean_dev_ipv6(vlan_dev,
-								    &vlan->vlan_ipv6);
-					return NOTIFY_OK;
-				default:
-					return NOTIFY_DONE;
-				}
-			}
-		}
-	}
-	return NOTIFY_DONE;
-}
-
-static struct notifier_block bond_inet6addr_notifier = {
-	.notifier_call = bond_inet6addr_event,
-};
-
-void bond_register_ipv6_notifier(void)
-{
-	register_inet6addr_notifier(&bond_inet6addr_notifier);
-}
-
-void bond_unregister_ipv6_notifier(void)
-{
-	unregister_inet6addr_notifier(&bond_inet6addr_notifier);
-}
-
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b0c5772..0c0dacb 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -428,27 +428,34 @@ int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb,
  * @bond_dev: bonding net device that got called
  * @vid: vlan id being added
  */
-static void bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid)
+static int bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
-	struct slave *slave;
+	struct slave *slave, *stop_at;
 	int i, res;
 
 	bond_for_each_slave(bond, slave, i) {
-		struct net_device *slave_dev = slave->dev;
-		const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
-
-		if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) &&
-		    slave_ops->ndo_vlan_rx_add_vid) {
-			slave_ops->ndo_vlan_rx_add_vid(slave_dev, vid);
-		}
+		res = vlan_vid_add(slave->dev, vid);
+		if (res)
+			goto unwind;
 	}
 
 	res = bond_add_vlan(bond, vid);
 	if (res) {
 		pr_err("%s: Error: Failed to add vlan id %d\n",
 		       bond_dev->name, vid);
+		return res;
 	}
+
+	return 0;
+
+unwind:
+	/* unwind from head to the slave that failed */
+	stop_at = slave;
+	bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at)
+		vlan_vid_del(slave->dev, vid);
+
+	return res;
 }
 
 /**
@@ -456,56 +463,48 @@ static void bond_vlan_rx_add_vid(struct net_device *bond_dev, uint16_t vid)
  * @bond_dev: bonding net device that got called
  * @vid: vlan id being removed
  */
-static void bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid)
+static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, uint16_t vid)
 {
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave;
 	int i, res;
 
-	bond_for_each_slave(bond, slave, i) {
-		struct net_device *slave_dev = slave->dev;
-		const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
-
-		if ((slave_dev->features & NETIF_F_HW_VLAN_FILTER) &&
-		    slave_ops->ndo_vlan_rx_kill_vid) {
-			slave_ops->ndo_vlan_rx_kill_vid(slave_dev, vid);
-		}
-	}
+	bond_for_each_slave(bond, slave, i)
+		vlan_vid_del(slave->dev, vid);
 
 	res = bond_del_vlan(bond, vid);
 	if (res) {
 		pr_err("%s: Error: Failed to remove vlan id %d\n",
 		       bond_dev->name, vid);
+		return res;
 	}
+
+	return 0;
 }
 
 static void bond_add_vlans_on_slave(struct bonding *bond, struct net_device *slave_dev)
 {
 	struct vlan_entry *vlan;
-	const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
-
-	if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) ||
-	    !(slave_ops->ndo_vlan_rx_add_vid))
-		return;
+	int res;
 
-	list_for_each_entry(vlan, &bond->vlan_list, vlan_list)
-		slave_ops->ndo_vlan_rx_add_vid(slave_dev, vlan->vlan_id);
+	list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
+		res = vlan_vid_add(slave_dev, vlan->vlan_id);
+		if (res)
+			pr_warning("%s: Failed to add vlan id %d to device %s\n",
+				   bond->dev->name, vlan->vlan_id,
+				   slave_dev->name);
+	}
 }
 
 static void bond_del_vlans_from_slave(struct bonding *bond,
 				      struct net_device *slave_dev)
 {
-	const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
 	struct vlan_entry *vlan;
 
-	if (!(slave_dev->features & NETIF_F_HW_VLAN_FILTER) ||
-	    !(slave_ops->ndo_vlan_rx_kill_vid))
-		return;
-
 	list_for_each_entry(vlan, &bond->vlan_list, vlan_list) {
 		if (!vlan->vlan_id)
 			continue;
-		slave_ops->ndo_vlan_rx_kill_vid(slave_dev, vlan->vlan_id);
+		vlan_vid_del(slave_dev, vlan->vlan_id);
 	}
 }
 
@@ -1325,11 +1324,12 @@ static int bond_sethwaddr(struct net_device *bond_dev,
 	return 0;
 }
 
-static u32 bond_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t bond_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct slave *slave;
 	struct bonding *bond = netdev_priv(dev);
-	u32 mask;
+	netdev_features_t mask;
 	int i;
 
 	read_lock(&bond->lock);
@@ -1363,7 +1363,7 @@ static void bond_compute_features(struct bonding *bond)
 {
 	struct slave *slave;
 	struct net_device *bond_dev = bond->dev;
-	u32 vlan_features = BOND_VLAN_FEATURES;
+	netdev_features_t vlan_features = BOND_VLAN_FEATURES;
 	unsigned short max_hard_header_len = ETH_HLEN;
 	int i;
 
@@ -1897,7 +1897,7 @@ int bond_release(struct net_device *bond_dev, struct net_device *slave_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave, *oldcurrent;
 	struct sockaddr addr;
-	u32 old_features = bond_dev->features;
+	netdev_features_t old_features = bond_dev->features;
 
 	/* slave is not a slave or master is not master of this slave */
 	if (!(slave_dev->flags & IFF_SLAVE) ||
@@ -2553,30 +2553,6 @@ re_arm:
 	}
 }
 
-static __be32 bond_glean_dev_ip(struct net_device *dev)
-{
-	struct in_device *idev;
-	struct in_ifaddr *ifa;
-	__be32 addr = 0;
-
-	if (!dev)
-		return 0;
-
-	rcu_read_lock();
-	idev = __in_dev_get_rcu(dev);
-	if (!idev)
-		goto out;
-
-	ifa = idev->ifa_list;
-	if (!ifa)
-		goto out;
-
-	addr = ifa->ifa_local;
-out:
-	rcu_read_unlock();
-	return addr;
-}
-
 static int bond_has_this_ip(struct bonding *bond, __be32 ip)
 {
 	struct vlan_entry *vlan;
@@ -3322,6 +3298,10 @@ static int bond_inetaddr_event(struct notifier_block *this, unsigned long event,
 	struct bonding *bond;
 	struct vlan_entry *vlan;
 
+	/* we only care about primary address */
+	if(ifa->ifa_flags & IFA_F_SECONDARY)
+		return NOTIFY_DONE;
+
 	list_for_each_entry(bond, &bn->dev_list, bond_list) {
 		if (bond->dev == event_dev) {
 			switch (event) {
@@ -3329,7 +3309,7 @@ static int bond_inetaddr_event(struct notifier_block *this, unsigned long event,
 				bond->master_ip = ifa->ifa_local;
 				return NOTIFY_OK;
 			case NETDEV_DOWN:
-				bond->master_ip = bond_glean_dev_ip(bond->dev);
+				bond->master_ip = 0;
 				return NOTIFY_OK;
 			default:
 				return NOTIFY_DONE;
@@ -3345,8 +3325,7 @@ static int bond_inetaddr_event(struct notifier_block *this, unsigned long event,
 					vlan->vlan_ip = ifa->ifa_local;
 					return NOTIFY_OK;
 				case NETDEV_DOWN:
-					vlan->vlan_ip =
-						bond_glean_dev_ip(vlan_dev);
+					vlan->vlan_ip = 0;
 					return NOTIFY_OK;
 				default:
 					return NOTIFY_DONE;
@@ -4360,7 +4339,7 @@ static void bond_setup(struct net_device *bond_dev)
 				NETIF_F_HW_VLAN_RX |
 				NETIF_F_HW_VLAN_FILTER;
 
-	bond_dev->hw_features &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_NO_CSUM);
+	bond_dev->hw_features &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_HW_CSUM);
 	bond_dev->features |= bond_dev->hw_features;
 }
 
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 5a20804..4ef7e2f 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -319,6 +319,13 @@ static ssize_t bonding_store_mode(struct device *d,
 		goto out;
 	}
 
+	if (bond->slave_cnt > 0) {
+		pr_err("unable to update mode of %s because it has slaves.\n",
+			bond->dev->name);
+		ret = -EPERM;
+		goto out;
+	}
+
 	new_value = bond_parse_parm(buf, bond_mode_tbl);
 	if (new_value < 0)  {
 		pr_err("%s: Ignoring invalid mode value %.*s.\n",
diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c
index 0733525..0a4fc62 100644
--- a/drivers/net/caif/caif_hsi.c
+++ b/drivers/net/caif/caif_hsi.c
@@ -117,15 +117,6 @@ static int cfhsi_flush_fifo(struct cfhsi *cfhsi)
 	dev_dbg(&cfhsi->ndev->dev, "%s.\n",
 		__func__);
 
-
-	ret = cfhsi->dev->cfhsi_wake_up(cfhsi->dev);
-	if (ret) {
-		dev_warn(&cfhsi->ndev->dev,
-			"%s: can't wake up HSI interface: %d.\n",
-			__func__, ret);
-		return ret;
-	}
-
 	do {
 		ret = cfhsi->dev->cfhsi_fifo_occupancy(cfhsi->dev,
 				&fifo_occupancy);
@@ -168,8 +159,6 @@ static int cfhsi_flush_fifo(struct cfhsi *cfhsi)
 		}
 	} while (1);
 
-	cfhsi->dev->cfhsi_wake_down(cfhsi->dev);
-
 	return ret;
 }
 
@@ -944,7 +933,7 @@ static int cfhsi_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		/* Create HSI frame. */
 		len = cfhsi_tx_frm(desc, cfhsi);
-		BUG_ON(!len);
+		WARN_ON(!len);
 
 		/* Set up new transfer. */
 		res = cfhsi->dev->cfhsi_tx(cfhsi->tx_buf, len, cfhsi->dev);
diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c
index 23406e6..9341a2d 100644
--- a/drivers/net/caif/caif_serial.c
+++ b/drivers/net/caif/caif_serial.c
@@ -261,7 +261,7 @@ static int handle_tx(struct ser_device *ser)
 		skb_pull(skb, tty_wr);
 		if (skb->len == 0) {
 			struct sk_buff *tmp = skb_dequeue(&ser->head);
-			BUG_ON(tmp != skb);
+			WARN_ON(tmp != skb);
 			if (in_interrupt())
 				dev_kfree_skb_irq(skb);
 			else
@@ -305,7 +305,7 @@ static void ldisc_tx_wakeup(struct tty_struct *tty)
 
 	ser = tty->disc_data;
 	BUG_ON(ser == NULL);
-	BUG_ON(ser->tty != tty);
+	WARN_ON(ser->tty != tty);
 	handle_tx(ser);
 }
 
diff --git a/drivers/net/caif/caif_shmcore.c b/drivers/net/caif/caif_shmcore.c
index d4b26fb..5b20413 100644
--- a/drivers/net/caif/caif_shmcore.c
+++ b/drivers/net/caif/caif_shmcore.c
@@ -238,11 +238,11 @@ int caif_shmdrv_rx_cb(u32 mbx_msg, void *priv)
 		if ((avail_emptybuff > HIGH_WATERMARK) &&
 					(!pshm_drv->tx_empty_available)) {
 			pshm_drv->tx_empty_available = 1;
+			spin_unlock_irqrestore(&pshm_drv->lock, flags);
 			pshm_drv->cfdev.flowctrl
 					(pshm_drv->pshm_dev->pshm_netdev,
 								CAIF_FLOW_ON);
 
-			spin_unlock_irqrestore(&pshm_drv->lock, flags);
 
 			/* Schedule the work queue. if required */
 			if (!work_pending(&pshm_drv->shm_tx_work))
@@ -285,6 +285,7 @@ static void shm_rx_work_func(struct work_struct *rx_work)
 			list_entry(pshm_drv->rx_full_list.next, struct buf_list,
 					list);
 		list_del_init(&pbuf->list);
+		spin_unlock_irqrestore(&pshm_drv->lock, flags);
 
 		/* Retrieve pointer to start of the packet descriptor area. */
 		pck_desc = (struct shm_pck_desc *) pbuf->desc_vptr;
@@ -336,7 +337,11 @@ static void shm_rx_work_func(struct work_struct *rx_work)
 			/* Get a suitable CAIF packet and copy in data. */
 			skb = netdev_alloc_skb(pshm_drv->pshm_dev->pshm_netdev,
 							frm_pck_len + 1);
-			BUG_ON(skb == NULL);
+
+			if (skb == NULL) {
+				pr_info("OOM: Try next frame in descriptor\n");
+				break;
+			}
 
 			p = skb_put(skb, frm_pck_len);
 			memcpy(p, pbuf->desc_vptr + frm_pck_ofs, frm_pck_len);
@@ -360,6 +365,7 @@ static void shm_rx_work_func(struct work_struct *rx_work)
 			pck_desc++;
 		}
 
+		spin_lock_irqsave(&pshm_drv->lock, flags);
 		list_add_tail(&pbuf->list, &pshm_drv->rx_pend_list);
 
 		spin_unlock_irqrestore(&pshm_drv->lock, flags);
@@ -412,7 +418,6 @@ static void shm_tx_work_func(struct work_struct *tx_work)
 
 		if (skb == NULL)
 			goto send_msg;
-
 		/* Check the available no. of buffers in the empty list */
 		list_for_each(pos, &pshm_drv->tx_empty_list)
 			avail_emptybuff++;
@@ -421,9 +426,11 @@ static void shm_tx_work_func(struct work_struct *tx_work)
 					pshm_drv->tx_empty_available) {
 			/* Update blocking condition. */
 			pshm_drv->tx_empty_available = 0;
+			spin_unlock_irqrestore(&pshm_drv->lock, flags);
 			pshm_drv->cfdev.flowctrl
 					(pshm_drv->pshm_dev->pshm_netdev,
 					CAIF_FLOW_OFF);
+			spin_lock_irqsave(&pshm_drv->lock, flags);
 		}
 		/*
 		 * We simply return back to the caller if we do not have space
@@ -469,6 +476,8 @@ static void shm_tx_work_func(struct work_struct *tx_work)
 			}
 
 			skb = skb_dequeue(&pshm_drv->sk_qhead);
+			if (skb == NULL)
+				break;
 			/* Copy in CAIF frame. */
 			skb_copy_bits(skb, 0, pbuf->desc_vptr +
 					pbuf->frm_ofs + SHM_HDR_LEN +
@@ -477,7 +486,7 @@ static void shm_tx_work_func(struct work_struct *tx_work)
 			pshm_drv->pshm_dev->pshm_netdev->stats.tx_packets++;
 			pshm_drv->pshm_dev->pshm_netdev->stats.tx_bytes +=
 									frmlen;
-			dev_kfree_skb(skb);
+			dev_kfree_skb_irq(skb);
 
 			/* Fill in the shared memory packet descriptor area. */
 			pck_desc = (struct shm_pck_desc *) (pbuf->desc_vptr);
@@ -512,16 +521,11 @@ send_msg:
 static int shm_netdev_tx(struct sk_buff *skb, struct net_device *shm_netdev)
 {
 	struct shmdrv_layer *pshm_drv;
-	unsigned long flags = 0;
 
 	pshm_drv = netdev_priv(shm_netdev);
 
-	spin_lock_irqsave(&pshm_drv->lock, flags);
-
 	skb_queue_tail(&pshm_drv->sk_qhead, skb);
 
-	spin_unlock_irqrestore(&pshm_drv->lock, flags);
-
 	/* Schedule Tx work queue. for deferred processing of skbs*/
 	if (!work_pending(&pshm_drv->shm_tx_work))
 		queue_work(pshm_drv->pshm_tx_workqueue, &pshm_drv->shm_tx_work);
@@ -606,6 +610,7 @@ int caif_shmcore_probe(struct shmdev_layer *pshm_dev)
 		pshm_drv->shm_rx_addr = pshm_dev->shm_base_addr +
 						(NR_TX_BUF * TX_BUF_SZ);
 
+	spin_lock_init(&pshm_drv->lock);
 	INIT_LIST_HEAD(&pshm_drv->tx_empty_list);
 	INIT_LIST_HEAD(&pshm_drv->tx_pend_list);
 	INIT_LIST_HEAD(&pshm_drv->tx_full_list);
@@ -640,7 +645,7 @@ int caif_shmcore_probe(struct shmdev_layer *pshm_dev)
 		tx_buf->frm_ofs = SHM_CAIF_FRM_OFS;
 
 		if (pshm_dev->shm_loopback)
-			tx_buf->desc_vptr = (char *)tx_buf->phy_addr;
+			tx_buf->desc_vptr = (unsigned char *)tx_buf->phy_addr;
 		else
 			tx_buf->desc_vptr =
 					ioremap(tx_buf->phy_addr, TX_BUF_SZ);
@@ -664,7 +669,7 @@ int caif_shmcore_probe(struct shmdev_layer *pshm_dev)
 		rx_buf->len = RX_BUF_SZ;
 
 		if (pshm_dev->shm_loopback)
-			rx_buf->desc_vptr = (char *)rx_buf->phy_addr;
+			rx_buf->desc_vptr = (unsigned char *)rx_buf->phy_addr;
 		else
 			rx_buf->desc_vptr =
 					ioremap(rx_buf->phy_addr, RX_BUF_SZ);
diff --git a/drivers/net/caif/caif_spi.c b/drivers/net/caif/caif_spi.c
index 05e791f..761057b 100644
--- a/drivers/net/caif/caif_spi.c
+++ b/drivers/net/caif/caif_spi.c
@@ -226,7 +226,7 @@ static ssize_t dbgfs_frame(struct file *file, char __user *user_buf,
 			"Tx data (Len: %d):\n", cfspi->tx_cpck_len);
 
 	len += print_frame((buf + len), (DEBUGFS_BUF_SIZE - len),
-			   cfspi->xfer.va_tx,
+			   cfspi->xfer.va_tx[0],
 			   (cfspi->tx_cpck_len + SPI_CMD_SZ), 100);
 
 	len += snprintf((buf + len), (DEBUGFS_BUF_SIZE - len),
@@ -599,48 +599,11 @@ static int cfspi_close(struct net_device *dev)
 	netif_stop_queue(dev);
 	return 0;
 }
-static const struct net_device_ops cfspi_ops = {
-	.ndo_open = cfspi_open,
-	.ndo_stop = cfspi_close,
-	.ndo_start_xmit = cfspi_xmit
-};
 
-static void cfspi_setup(struct net_device *dev)
+static int cfspi_init(struct net_device *dev)
 {
+	int res = 0;
 	struct cfspi *cfspi = netdev_priv(dev);
-	dev->features = 0;
-	dev->netdev_ops = &cfspi_ops;
-	dev->type = ARPHRD_CAIF;
-	dev->flags = IFF_NOARP | IFF_POINTOPOINT;
-	dev->tx_queue_len = 0;
-	dev->mtu = SPI_MAX_PAYLOAD_SIZE;
-	dev->destructor = free_netdev;
-	skb_queue_head_init(&cfspi->qhead);
-	skb_queue_head_init(&cfspi->chead);
-	cfspi->cfdev.link_select = CAIF_LINK_HIGH_BANDW;
-	cfspi->cfdev.use_frag = false;
-	cfspi->cfdev.use_stx = false;
-	cfspi->cfdev.use_fcs = false;
-	cfspi->ndev = dev;
-}
-
-int cfspi_spi_probe(struct platform_device *pdev)
-{
-	struct cfspi *cfspi = NULL;
-	struct net_device *ndev;
-	struct cfspi_dev *dev;
-	int res;
-	dev = (struct cfspi_dev *)pdev->dev.platform_data;
-
-	ndev = alloc_netdev(sizeof(struct cfspi),
-			"cfspi%d", cfspi_setup);
-	if (!ndev)
-		return -ENOMEM;
-
-	cfspi = netdev_priv(ndev);
-	netif_stop_queue(ndev);
-	cfspi->ndev = ndev;
-	cfspi->pdev = pdev;
 
 	/* Set flow info. */
 	cfspi->flow_off_sent = 0;
@@ -656,16 +619,11 @@ int cfspi_spi_probe(struct platform_device *pdev)
 		cfspi->slave_talked = false;
 	}
 
-	/* Assign the SPI device. */
-	cfspi->dev = dev;
-	/* Assign the device ifc to this SPI interface. */
-	dev->ifc = &cfspi->ifc;
-
 	/* Allocate DMA buffers. */
-	cfspi->xfer.va_tx = dma_alloc(&cfspi->xfer.pa_tx);
-	if (!cfspi->xfer.va_tx) {
+	cfspi->xfer.va_tx[0] = dma_alloc(&cfspi->xfer.pa_tx[0]);
+	if (!cfspi->xfer.va_tx[0]) {
 		res = -ENODEV;
-		goto err_dma_alloc_tx;
+		goto err_dma_alloc_tx_0;
 	}
 
 	cfspi->xfer.va_rx = dma_alloc(&cfspi->xfer.pa_rx);
@@ -714,6 +672,87 @@ int cfspi_spi_probe(struct platform_device *pdev)
 	/* Schedule the work queue. */
 	queue_work(cfspi->wq, &cfspi->work);
 
+	return 0;
+
+ err_create_wq:
+	dma_free(cfspi->xfer.va_rx, cfspi->xfer.pa_rx);
+ err_dma_alloc_rx:
+	dma_free(cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]);
+ err_dma_alloc_tx_0:
+	return res;
+}
+
+static void cfspi_uninit(struct net_device *dev)
+{
+	struct cfspi *cfspi = netdev_priv(dev);
+
+	/* Remove from list. */
+	spin_lock(&cfspi_list_lock);
+	list_del(&cfspi->list);
+	spin_unlock(&cfspi_list_lock);
+
+	cfspi->ndev = NULL;
+	/* Free DMA buffers. */
+	dma_free(cfspi->xfer.va_rx, cfspi->xfer.pa_rx);
+	dma_free(cfspi->xfer.va_tx[0], cfspi->xfer.pa_tx[0]);
+	set_bit(SPI_TERMINATE, &cfspi->state);
+	wake_up_interruptible(&cfspi->wait);
+	destroy_workqueue(cfspi->wq);
+	/* Destroy debugfs directory and files. */
+	dev_debugfs_rem(cfspi);
+	return;
+}
+
+static const struct net_device_ops cfspi_ops = {
+	.ndo_open = cfspi_open,
+	.ndo_stop = cfspi_close,
+	.ndo_init = cfspi_init,
+	.ndo_uninit = cfspi_uninit,
+	.ndo_start_xmit = cfspi_xmit
+};
+
+static void cfspi_setup(struct net_device *dev)
+{
+	struct cfspi *cfspi = netdev_priv(dev);
+	dev->features = 0;
+	dev->netdev_ops = &cfspi_ops;
+	dev->type = ARPHRD_CAIF;
+	dev->flags = IFF_NOARP | IFF_POINTOPOINT;
+	dev->tx_queue_len = 0;
+	dev->mtu = SPI_MAX_PAYLOAD_SIZE;
+	dev->destructor = free_netdev;
+	skb_queue_head_init(&cfspi->qhead);
+	skb_queue_head_init(&cfspi->chead);
+	cfspi->cfdev.link_select = CAIF_LINK_HIGH_BANDW;
+	cfspi->cfdev.use_frag = false;
+	cfspi->cfdev.use_stx = false;
+	cfspi->cfdev.use_fcs = false;
+	cfspi->ndev = dev;
+}
+
+int cfspi_spi_probe(struct platform_device *pdev)
+{
+	struct cfspi *cfspi = NULL;
+	struct net_device *ndev;
+	struct cfspi_dev *dev;
+	int res;
+	dev = (struct cfspi_dev *)pdev->dev.platform_data;
+
+	ndev = alloc_netdev(sizeof(struct cfspi),
+			"cfspi%d", cfspi_setup);
+	if (!dev)
+		return -ENODEV;
+
+	cfspi = netdev_priv(ndev);
+	netif_stop_queue(ndev);
+	cfspi->ndev = ndev;
+	cfspi->pdev = pdev;
+
+	/* Assign the SPI device. */
+	cfspi->dev = dev;
+	/* Assign the device ifc to this SPI interface. */
+	dev->ifc = &cfspi->ifc;
+
 	/* Register network device. */
 	res = register_netdev(ndev);
 	if (res) {
@@ -723,15 +762,6 @@ int cfspi_spi_probe(struct platform_device *pdev)
 	return res;
 
  err_net_reg:
-	dev_debugfs_rem(cfspi);
-	set_bit(SPI_TERMINATE, &cfspi->state);
-	wake_up_interruptible(&cfspi->wait);
-	destroy_workqueue(cfspi->wq);
- err_create_wq:
-	dma_free(cfspi->xfer.va_rx, cfspi->xfer.pa_rx);
- err_dma_alloc_rx:
-	dma_free(cfspi->xfer.va_tx, cfspi->xfer.pa_tx);
- err_dma_alloc_tx:
 	free_netdev(ndev);
 
 	return res;
@@ -739,34 +769,8 @@ int cfspi_spi_probe(struct platform_device *pdev)
 
 int cfspi_spi_remove(struct platform_device *pdev)
 {
-	struct list_head *list_node;
-	struct list_head *n;
-	struct cfspi *cfspi = NULL;
-	struct cfspi_dev *dev;
-
-	dev = (struct cfspi_dev *)pdev->dev.platform_data;
-	spin_lock(&cfspi_list_lock);
-	list_for_each_safe(list_node, n, &cfspi_list) {
-		cfspi = list_entry(list_node, struct cfspi, list);
-		/* Find the corresponding device. */
-		if (cfspi->dev == dev) {
-			/* Remove from list. */
-			list_del(list_node);
-			/* Free DMA buffers. */
-			dma_free(cfspi->xfer.va_rx, cfspi->xfer.pa_rx);
-			dma_free(cfspi->xfer.va_tx, cfspi->xfer.pa_tx);
-			set_bit(SPI_TERMINATE, &cfspi->state);
-			wake_up_interruptible(&cfspi->wait);
-			destroy_workqueue(cfspi->wq);
-			/* Destroy debugfs directory and files. */
-			dev_debugfs_rem(cfspi);
-			unregister_netdev(cfspi->ndev);
-			spin_unlock(&cfspi_list_lock);
-			return 0;
-		}
-	}
-	spin_unlock(&cfspi_list_lock);
-	return -ENODEV;
+	/* Everything is done in cfspi_uninit(). */
+	return 0;
 }
 
 static void __exit cfspi_exit_module(void)
@@ -777,7 +781,7 @@ static void __exit cfspi_exit_module(void)
 
 	list_for_each_safe(list_node, n, &cfspi_list) {
 		cfspi = list_entry(list_node, struct cfspi, list);
-		platform_device_unregister(cfspi->pdev);
+		unregister_netdev(cfspi->ndev);
 	}
 
 	/* Destroy sysfs files. */
diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index f6c98fb..ab45758 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -116,6 +116,8 @@ source "drivers/net/can/sja1000/Kconfig"
 
 source "drivers/net/can/c_can/Kconfig"
 
+source "drivers/net/can/cc770/Kconfig"
+
 source "drivers/net/can/usb/Kconfig"
 
 source "drivers/net/can/softing/Kconfig"
diff --git a/drivers/net/can/Makefile b/drivers/net/can/Makefile
index 24ebfe8..938be37 100644
--- a/drivers/net/can/Makefile
+++ b/drivers/net/can/Makefile
@@ -14,6 +14,7 @@ obj-y				+= softing/
 obj-$(CONFIG_CAN_SJA1000)	+= sja1000/
 obj-$(CONFIG_CAN_MSCAN)		+= mscan/
 obj-$(CONFIG_CAN_C_CAN)		+= c_can/
+obj-$(CONFIG_CAN_CC770)		+= cc770/
 obj-$(CONFIG_CAN_AT91)		+= at91_can.o
 obj-$(CONFIG_CAN_TI_HECC)	+= ti_hecc.o
 obj-$(CONFIG_CAN_MCP251X)	+= mcp251x.o
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index 044ea06..6ea905c 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -1383,18 +1383,7 @@ static struct platform_driver at91_can_driver = {
 	.id_table = at91_can_id_table,
 };
 
-static int __init at91_can_module_init(void)
-{
-	return platform_driver_register(&at91_can_driver);
-}
-
-static void __exit at91_can_module_exit(void)
-{
-	platform_driver_unregister(&at91_can_driver);
-}
-
-module_init(at91_can_module_init);
-module_exit(at91_can_module_exit);
+module_platform_driver(at91_can_driver);
 
 MODULE_AUTHOR("Marc Kleine-Budde <mkl@pengutronix.de>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/bfin_can.c b/drivers/net/can/bfin_can.c
index a1c5abc..349e0fa 100644
--- a/drivers/net/can/bfin_can.c
+++ b/drivers/net/can/bfin_can.c
@@ -676,17 +676,7 @@ static struct platform_driver bfin_can_driver = {
 	},
 };
 
-static int __init bfin_can_init(void)
-{
-	return platform_driver_register(&bfin_can_driver);
-}
-module_init(bfin_can_init);
-
-static void __exit bfin_can_exit(void)
-{
-	platform_driver_unregister(&bfin_can_driver);
-}
-module_exit(bfin_can_exit);
+module_platform_driver(bfin_can_driver);
 
 MODULE_AUTHOR("Barry Song <21cnbao@gmail.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c
index 0b5c6f8..5e1a5ff 100644
--- a/drivers/net/can/c_can/c_can_platform.c
+++ b/drivers/net/can/c_can/c_can_platform.c
@@ -197,17 +197,7 @@ static struct platform_driver c_can_plat_driver = {
 	.remove = __devexit_p(c_can_plat_remove),
 };
 
-static int __init c_can_plat_init(void)
-{
-	return platform_driver_register(&c_can_plat_driver);
-}
-module_init(c_can_plat_init);
-
-static void __exit c_can_plat_exit(void)
-{
-	platform_driver_unregister(&c_can_plat_driver);
-}
-module_exit(c_can_plat_exit);
+module_platform_driver(c_can_plat_driver);
 
 MODULE_AUTHOR("Bhupesh Sharma <bhupesh.sharma@st.com>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/cc770/Kconfig b/drivers/net/can/cc770/Kconfig
new file mode 100644
index 0000000..22c07a8
--- /dev/null
+++ b/drivers/net/can/cc770/Kconfig
@@ -0,0 +1,21 @@
+menuconfig CAN_CC770
+	tristate "Bosch CC770 and Intel AN82527 devices"
+	depends on CAN_DEV && HAS_IOMEM
+
+if CAN_CC770
+
+config CAN_CC770_ISA
+	tristate "ISA Bus based legacy CC770 driver"
+	---help---
+	  This driver adds legacy support for CC770 and AN82527 chips
+	  connected to the ISA bus using I/O port, memory mapped or
+	  indirect access.
+
+config CAN_CC770_PLATFORM
+	tristate "Generic Platform Bus based CC770 driver"
+	---help---
+	  This driver adds support for the CC770 and AN82527 chips
+	  connected to the "platform bus" (Linux abstraction for directly
+	  to the processor attached devices).
+
+endif
diff --git a/drivers/net/can/cc770/Makefile b/drivers/net/can/cc770/Makefile
new file mode 100644
index 0000000..9fb8321
--- /dev/null
+++ b/drivers/net/can/cc770/Makefile
@@ -0,0 +1,9 @@
+#
+#  Makefile for the Bosch CC770 CAN controller drivers.
+#
+
+obj-$(CONFIG_CAN_CC770) += cc770.o
+obj-$(CONFIG_CAN_CC770_ISA) += cc770_isa.o
+obj-$(CONFIG_CAN_CC770_PLATFORM) += cc770_platform.o
+
+ccflags-$(CONFIG_CAN_DEBUG_DEVICES) := -DDEBUG
diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c
new file mode 100644
index 0000000..7668967
--- /dev/null
+++ b/drivers/net/can/cc770/cc770.c
@@ -0,0 +1,881 @@
+/*
+ * Core driver for the CC770 and AN82527 CAN controllers
+ *
+ * Copyright (C) 2009, 2011 Wolfgang Grandegger <wg@grandegger.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/fcntl.h>
+#include <linux/interrupt.h>
+#include <linux/ptrace.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <linux/if_arp.h>
+#include <linux/if_ether.h>
+#include <linux/skbuff.h>
+#include <linux/delay.h>
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/error.h>
+#include <linux/can/dev.h>
+#include <linux/can/platform/cc770.h>
+
+#include "cc770.h"
+
+MODULE_AUTHOR("Wolfgang Grandegger <wg@grandegger.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION(KBUILD_MODNAME "CAN netdevice driver");
+
+/*
+ * The CC770 is a CAN controller from Bosch, which is 100% compatible
+ * with the AN82527 from Intel, but with "bugs" being fixed and some
+ * additional functionality, mainly:
+ *
+ * 1. RX and TX error counters are readable.
+ * 2. Support of silent (listen-only) mode.
+ * 3. Message object 15 can receive all types of frames, also RTR and EFF.
+ *
+ * Details are available from Bosch's "CC770_Product_Info_2007-01.pdf",
+ * which explains in detail the compatibility between the CC770 and the
+ * 82527. This driver use the additional functionality 3. on real CC770
+ * devices. Unfortunately, the CC770 does still not store the message
+ * identifier of received remote transmission request frames and
+ * therefore it's set to 0.
+ *
+ * The message objects 1..14 can be used for TX and RX while the message
+ * objects 15 is optimized for RX. It has a shadow register for reliable
+ * data receiption under heavy bus load. Therefore it makes sense to use
+ * this message object for the needed use case. The frame type (EFF/SFF)
+ * for the message object 15 can be defined via kernel module parameter
+ * "msgobj15_eff". If not equal 0, it will receive 29-bit EFF frames,
+ * otherwise 11 bit SFF messages.
+ */
+static int msgobj15_eff;
+module_param(msgobj15_eff, int, S_IRUGO);
+MODULE_PARM_DESC(msgobj15_eff, "Extended 29-bit frames for message object 15 "
+		 "(default: 11-bit standard frames)");
+
+static int i82527_compat;
+module_param(i82527_compat, int, S_IRUGO);
+MODULE_PARM_DESC(i82527_compat, "Strict Intel 82527 comptibility mode "
+		 "without using additional functions");
+
+/*
+ * This driver uses the last 5 message objects 11..15. The definitions
+ * and structure below allows to configure and assign them to the real
+ * message object.
+ */
+static unsigned char cc770_obj_flags[CC770_OBJ_MAX] = {
+	[CC770_OBJ_RX0] = CC770_OBJ_FLAG_RX,
+	[CC770_OBJ_RX1] = CC770_OBJ_FLAG_RX | CC770_OBJ_FLAG_EFF,
+	[CC770_OBJ_RX_RTR0] = CC770_OBJ_FLAG_RX | CC770_OBJ_FLAG_RTR,
+	[CC770_OBJ_RX_RTR1] = CC770_OBJ_FLAG_RX | CC770_OBJ_FLAG_RTR |
+			      CC770_OBJ_FLAG_EFF,
+	[CC770_OBJ_TX] = 0,
+};
+
+static struct can_bittiming_const cc770_bittiming_const = {
+	.name = KBUILD_MODNAME,
+	.tseg1_min = 1,
+	.tseg1_max = 16,
+	.tseg2_min = 1,
+	.tseg2_max = 8,
+	.sjw_max = 4,
+	.brp_min = 1,
+	.brp_max = 64,
+	.brp_inc = 1,
+};
+
+static inline int intid2obj(unsigned int intid)
+{
+	if (intid == 2)
+		return 0;
+	else
+		return MSGOBJ_LAST + 2 - intid;
+}
+
+static void enable_all_objs(const struct net_device *dev)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+	u8 msgcfg;
+	unsigned char obj_flags;
+	unsigned int o, mo;
+
+	for (o = 0; o < ARRAY_SIZE(priv->obj_flags); o++) {
+		obj_flags = priv->obj_flags[o];
+		mo = obj2msgobj(o);
+
+		if (obj_flags & CC770_OBJ_FLAG_RX) {
+			/*
+			 * We don't need extra objects for RTR and EFF if
+			 * the additional CC770 functions are enabled.
+			 */
+			if (priv->control_normal_mode & CTRL_EAF) {
+				if (o > 0)
+					continue;
+				netdev_dbg(dev, "Message object %d for "
+					   "RX data, RTR, SFF and EFF\n", mo);
+			} else {
+				netdev_dbg(dev,
+					   "Message object %d for RX %s %s\n",
+					   mo, obj_flags & CC770_OBJ_FLAG_RTR ?
+					   "RTR" : "data",
+					   obj_flags & CC770_OBJ_FLAG_EFF ?
+					   "EFF" : "SFF");
+			}
+
+			if (obj_flags & CC770_OBJ_FLAG_EFF)
+				msgcfg = MSGCFG_XTD;
+			else
+				msgcfg = 0;
+			if (obj_flags & CC770_OBJ_FLAG_RTR)
+				msgcfg |= MSGCFG_DIR;
+
+			cc770_write_reg(priv, msgobj[mo].config, msgcfg);
+			cc770_write_reg(priv, msgobj[mo].ctrl0,
+					MSGVAL_SET | TXIE_RES |
+					RXIE_SET | INTPND_RES);
+
+			if (obj_flags & CC770_OBJ_FLAG_RTR)
+				cc770_write_reg(priv, msgobj[mo].ctrl1,
+						NEWDAT_RES | CPUUPD_SET |
+						TXRQST_RES | RMTPND_RES);
+			else
+				cc770_write_reg(priv, msgobj[mo].ctrl1,
+						NEWDAT_RES | MSGLST_RES |
+						TXRQST_RES | RMTPND_RES);
+		} else {
+			netdev_dbg(dev, "Message object %d for "
+				   "TX data, RTR, SFF and EFF\n", mo);
+
+			cc770_write_reg(priv, msgobj[mo].ctrl1,
+					RMTPND_RES | TXRQST_RES |
+					CPUUPD_RES | NEWDAT_RES);
+			cc770_write_reg(priv, msgobj[mo].ctrl0,
+					MSGVAL_RES | TXIE_RES |
+					RXIE_RES | INTPND_RES);
+		}
+	}
+}
+
+static void disable_all_objs(const struct cc770_priv *priv)
+{
+	int o, mo;
+
+	for (o = 0; o <  ARRAY_SIZE(priv->obj_flags); o++) {
+		mo = obj2msgobj(o);
+
+		if (priv->obj_flags[o] & CC770_OBJ_FLAG_RX) {
+			if (o > 0 && priv->control_normal_mode & CTRL_EAF)
+				continue;
+
+			cc770_write_reg(priv, msgobj[mo].ctrl1,
+					NEWDAT_RES | MSGLST_RES |
+					TXRQST_RES | RMTPND_RES);
+			cc770_write_reg(priv, msgobj[mo].ctrl0,
+					MSGVAL_RES | TXIE_RES |
+					RXIE_RES | INTPND_RES);
+		} else {
+			/* Clear message object for send */
+			cc770_write_reg(priv, msgobj[mo].ctrl1,
+					RMTPND_RES | TXRQST_RES |
+					CPUUPD_RES | NEWDAT_RES);
+			cc770_write_reg(priv, msgobj[mo].ctrl0,
+					MSGVAL_RES | TXIE_RES |
+					RXIE_RES | INTPND_RES);
+		}
+	}
+}
+
+static void set_reset_mode(struct net_device *dev)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+
+	/* Enable configuration and puts chip in bus-off, disable interrupts */
+	cc770_write_reg(priv, control, CTRL_CCE | CTRL_INI);
+
+	priv->can.state = CAN_STATE_STOPPED;
+
+	/* Clear interrupts */
+	cc770_read_reg(priv, interrupt);
+
+	/* Clear status register */
+	cc770_write_reg(priv, status, 0);
+
+	/* Disable all used message objects */
+	disable_all_objs(priv);
+}
+
+static void set_normal_mode(struct net_device *dev)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+
+	/* Clear interrupts */
+	cc770_read_reg(priv, interrupt);
+
+	/* Clear status register and pre-set last error code */
+	cc770_write_reg(priv, status, STAT_LEC_MASK);
+
+	/* Enable all used message objects*/
+	enable_all_objs(dev);
+
+	/*
+	 * Clear bus-off, interrupts only for errors,
+	 * not for status change
+	 */
+	cc770_write_reg(priv, control, priv->control_normal_mode);
+
+	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+}
+
+static void chipset_init(struct cc770_priv *priv)
+{
+	int mo, id, data;
+
+	/* Enable configuration and put chip in bus-off, disable interrupts */
+	cc770_write_reg(priv, control, (CTRL_CCE | CTRL_INI));
+
+	/* Set CLKOUT divider and slew rates */
+	cc770_write_reg(priv, clkout, priv->clkout);
+
+	/* Configure CPU interface / CLKOUT enable */
+	cc770_write_reg(priv, cpu_interface, priv->cpu_interface);
+
+	/* Set bus configuration  */
+	cc770_write_reg(priv, bus_config, priv->bus_config);
+
+	/* Clear interrupts */
+	cc770_read_reg(priv, interrupt);
+
+	/* Clear status register */
+	cc770_write_reg(priv, status, 0);
+
+	/* Clear and invalidate message objects */
+	for (mo = MSGOBJ_FIRST; mo <= MSGOBJ_LAST; mo++) {
+		cc770_write_reg(priv, msgobj[mo].ctrl0,
+				INTPND_UNC | RXIE_RES |
+				TXIE_RES | MSGVAL_RES);
+		cc770_write_reg(priv, msgobj[mo].ctrl0,
+				INTPND_RES | RXIE_RES |
+				TXIE_RES | MSGVAL_RES);
+		cc770_write_reg(priv, msgobj[mo].ctrl1,
+				NEWDAT_RES | MSGLST_RES |
+				TXRQST_RES | RMTPND_RES);
+		for (data = 0; data < 8; data++)
+			cc770_write_reg(priv, msgobj[mo].data[data], 0);
+		for (id = 0; id < 4; id++)
+			cc770_write_reg(priv, msgobj[mo].id[id], 0);
+		cc770_write_reg(priv, msgobj[mo].config, 0);
+	}
+
+	/* Set all global ID masks to "don't care" */
+	cc770_write_reg(priv, global_mask_std[0], 0);
+	cc770_write_reg(priv, global_mask_std[1], 0);
+	cc770_write_reg(priv, global_mask_ext[0], 0);
+	cc770_write_reg(priv, global_mask_ext[1], 0);
+	cc770_write_reg(priv, global_mask_ext[2], 0);
+	cc770_write_reg(priv, global_mask_ext[3], 0);
+
+}
+
+static int cc770_probe_chip(struct net_device *dev)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+
+	/* Enable configuration, put chip in bus-off, disable ints */
+	cc770_write_reg(priv, control, CTRL_CCE | CTRL_EAF | CTRL_INI);
+	/* Configure cpu interface / CLKOUT disable */
+	cc770_write_reg(priv, cpu_interface, priv->cpu_interface);
+
+	/*
+	 * Check if hardware reset is still inactive or maybe there
+	 * is no chip in this address space
+	 */
+	if (cc770_read_reg(priv, cpu_interface) & CPUIF_RST) {
+		netdev_info(dev, "probing @0x%p failed (reset)\n",
+			    priv->reg_base);
+		return -ENODEV;
+	}
+
+	/* Write and read back test pattern (some arbitrary values) */
+	cc770_write_reg(priv, msgobj[1].data[1], 0x25);
+	cc770_write_reg(priv, msgobj[2].data[3], 0x52);
+	cc770_write_reg(priv, msgobj[10].data[6], 0xc3);
+	if ((cc770_read_reg(priv, msgobj[1].data[1]) != 0x25) ||
+	    (cc770_read_reg(priv, msgobj[2].data[3]) != 0x52) ||
+	    (cc770_read_reg(priv, msgobj[10].data[6]) != 0xc3)) {
+		netdev_info(dev, "probing @0x%p failed (pattern)\n",
+			    priv->reg_base);
+		return -ENODEV;
+	}
+
+	/* Check if this chip is a CC770 supporting additional functions */
+	if (cc770_read_reg(priv, control) & CTRL_EAF)
+		priv->control_normal_mode |= CTRL_EAF;
+
+	return 0;
+}
+
+static void cc770_start(struct net_device *dev)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+
+	/* leave reset mode */
+	if (priv->can.state != CAN_STATE_STOPPED)
+		set_reset_mode(dev);
+
+	/* leave reset mode */
+	set_normal_mode(dev);
+}
+
+static int cc770_set_mode(struct net_device *dev, enum can_mode mode)
+{
+	switch (mode) {
+	case CAN_MODE_START:
+		cc770_start(dev);
+		netif_wake_queue(dev);
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int cc770_set_bittiming(struct net_device *dev)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+	struct can_bittiming *bt = &priv->can.bittiming;
+	u8 btr0, btr1;
+
+	btr0 = ((bt->brp - 1) & 0x3f) | (((bt->sjw - 1) & 0x3) << 6);
+	btr1 = ((bt->prop_seg + bt->phase_seg1 - 1) & 0xf) |
+		(((bt->phase_seg2 - 1) & 0x7) << 4);
+	if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES)
+		btr1 |= 0x80;
+
+	netdev_info(dev, "setting BTR0=0x%02x BTR1=0x%02x\n", btr0, btr1);
+
+	cc770_write_reg(priv, bit_timing_0, btr0);
+	cc770_write_reg(priv, bit_timing_1, btr1);
+
+	return 0;
+}
+
+static int cc770_get_berr_counter(const struct net_device *dev,
+				  struct can_berr_counter *bec)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+
+	bec->txerr = cc770_read_reg(priv, tx_error_counter);
+	bec->rxerr = cc770_read_reg(priv, rx_error_counter);
+
+	return 0;
+}
+
+static netdev_tx_t cc770_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+	struct net_device_stats *stats = &dev->stats;
+	struct can_frame *cf = (struct can_frame *)skb->data;
+	unsigned int mo = obj2msgobj(CC770_OBJ_TX);
+	u8 dlc, rtr;
+	u32 id;
+	int i;
+
+	if (can_dropped_invalid_skb(dev, skb))
+		return NETDEV_TX_OK;
+
+	if ((cc770_read_reg(priv,
+			    msgobj[mo].ctrl1) & TXRQST_UNC) == TXRQST_SET) {
+		netdev_err(dev, "TX register is still occupied!\n");
+		return NETDEV_TX_BUSY;
+	}
+
+	netif_stop_queue(dev);
+
+	dlc = cf->can_dlc;
+	id = cf->can_id;
+	if (cf->can_id & CAN_RTR_FLAG)
+		rtr = 0;
+	else
+		rtr = MSGCFG_DIR;
+	cc770_write_reg(priv, msgobj[mo].ctrl1,
+			RMTPND_RES | TXRQST_RES | CPUUPD_SET | NEWDAT_RES);
+	cc770_write_reg(priv, msgobj[mo].ctrl0,
+			MSGVAL_SET | TXIE_SET | RXIE_RES | INTPND_RES);
+	if (id & CAN_EFF_FLAG) {
+		id &= CAN_EFF_MASK;
+		cc770_write_reg(priv, msgobj[mo].config,
+				(dlc << 4) | rtr | MSGCFG_XTD);
+		cc770_write_reg(priv, msgobj[mo].id[3], id << 3);
+		cc770_write_reg(priv, msgobj[mo].id[2], id >> 5);
+		cc770_write_reg(priv, msgobj[mo].id[1], id >> 13);
+		cc770_write_reg(priv, msgobj[mo].id[0], id >> 21);
+	} else {
+		id &= CAN_SFF_MASK;
+		cc770_write_reg(priv, msgobj[mo].config, (dlc << 4) | rtr);
+		cc770_write_reg(priv, msgobj[mo].id[0], id >> 3);
+		cc770_write_reg(priv, msgobj[mo].id[1], id << 5);
+	}
+
+	for (i = 0; i < dlc; i++)
+		cc770_write_reg(priv, msgobj[mo].data[i], cf->data[i]);
+
+	cc770_write_reg(priv, msgobj[mo].ctrl1,
+			RMTPND_RES | TXRQST_SET | CPUUPD_RES | NEWDAT_UNC);
+
+	stats->tx_bytes += dlc;
+
+	can_put_echo_skb(skb, dev, 0);
+
+	/*
+	 * HM: We had some cases of repeated IRQs so make sure the
+	 * INT is acknowledged I know it's already further up, but
+	 * doing again fixed the issue
+	 */
+	cc770_write_reg(priv, msgobj[mo].ctrl0,
+			MSGVAL_UNC | TXIE_UNC | RXIE_UNC | INTPND_RES);
+
+	return NETDEV_TX_OK;
+}
+
+static void cc770_rx(struct net_device *dev, unsigned int mo, u8 ctrl1)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+	struct net_device_stats *stats = &dev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	u8 config;
+	u32 id;
+	int i;
+
+	skb = alloc_can_skb(dev, &cf);
+	if (!skb)
+		return;
+
+	config = cc770_read_reg(priv, msgobj[mo].config);
+
+	if (ctrl1 & RMTPND_SET) {
+		/*
+		 * Unfortunately, the chip does not store the real message
+		 * identifier of the received remote transmission request
+		 * frame. Therefore we set it to 0.
+		 */
+		cf->can_id = CAN_RTR_FLAG;
+		if (config & MSGCFG_XTD)
+			cf->can_id |= CAN_EFF_FLAG;
+		cf->can_dlc = 0;
+	} else {
+		if (config & MSGCFG_XTD) {
+			id = cc770_read_reg(priv, msgobj[mo].id[3]);
+			id |= cc770_read_reg(priv, msgobj[mo].id[2]) << 8;
+			id |= cc770_read_reg(priv, msgobj[mo].id[1]) << 16;
+			id |= cc770_read_reg(priv, msgobj[mo].id[0]) << 24;
+			id >>= 3;
+			id |= CAN_EFF_FLAG;
+		} else {
+			id = cc770_read_reg(priv, msgobj[mo].id[1]);
+			id |= cc770_read_reg(priv, msgobj[mo].id[0]) << 8;
+			id >>= 5;
+		}
+
+		cf->can_id = id;
+		cf->can_dlc = get_can_dlc((config & 0xf0) >> 4);
+		for (i = 0; i < cf->can_dlc; i++)
+			cf->data[i] = cc770_read_reg(priv, msgobj[mo].data[i]);
+	}
+	netif_rx(skb);
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+}
+
+static int cc770_err(struct net_device *dev, u8 status)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+	struct net_device_stats *stats = &dev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	u8 lec;
+
+	netdev_dbg(dev, "status interrupt (%#x)\n", status);
+
+	skb = alloc_can_err_skb(dev, &cf);
+	if (!skb)
+		return -ENOMEM;
+
+	/* Use extended functions of the CC770 */
+	if (priv->control_normal_mode & CTRL_EAF) {
+		cf->data[6] = cc770_read_reg(priv, tx_error_counter);
+		cf->data[7] = cc770_read_reg(priv, rx_error_counter);
+	}
+
+	if (status & STAT_BOFF) {
+		/* Disable interrupts */
+		cc770_write_reg(priv, control, CTRL_INI);
+		cf->can_id |= CAN_ERR_BUSOFF;
+		priv->can.state = CAN_STATE_BUS_OFF;
+		can_bus_off(dev);
+	} else if (status & STAT_WARN) {
+		cf->can_id |= CAN_ERR_CRTL;
+		/* Only the CC770 does show error passive */
+		if (cf->data[7] > 127) {
+			cf->data[1] = CAN_ERR_CRTL_RX_PASSIVE |
+				CAN_ERR_CRTL_TX_PASSIVE;
+			priv->can.state = CAN_STATE_ERROR_PASSIVE;
+			priv->can.can_stats.error_passive++;
+		} else {
+			cf->data[1] = CAN_ERR_CRTL_RX_WARNING |
+				CAN_ERR_CRTL_TX_WARNING;
+			priv->can.state = CAN_STATE_ERROR_WARNING;
+			priv->can.can_stats.error_warning++;
+		}
+	} else {
+		/* Back to error avtive */
+		cf->can_id |= CAN_ERR_PROT;
+		cf->data[2] = CAN_ERR_PROT_ACTIVE;
+		priv->can.state = CAN_STATE_ERROR_ACTIVE;
+	}
+
+	lec = status & STAT_LEC_MASK;
+	if (lec < 7 && lec > 0) {
+		if (lec == STAT_LEC_ACK) {
+			cf->can_id |= CAN_ERR_ACK;
+		} else {
+			cf->can_id |= CAN_ERR_PROT;
+			switch (lec) {
+			case STAT_LEC_STUFF:
+				cf->data[2] |= CAN_ERR_PROT_STUFF;
+				break;
+			case STAT_LEC_FORM:
+				cf->data[2] |= CAN_ERR_PROT_FORM;
+				break;
+			case STAT_LEC_BIT1:
+				cf->data[2] |= CAN_ERR_PROT_BIT1;
+				break;
+			case STAT_LEC_BIT0:
+				cf->data[2] |= CAN_ERR_PROT_BIT0;
+				break;
+			case STAT_LEC_CRC:
+				cf->data[3] |= CAN_ERR_PROT_LOC_CRC_SEQ;
+				break;
+			}
+		}
+	}
+
+	netif_rx(skb);
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+
+	return 0;
+}
+
+static int cc770_status_interrupt(struct net_device *dev)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+	u8 status;
+
+	status = cc770_read_reg(priv, status);
+	/* Reset the status register including RXOK and TXOK */
+	cc770_write_reg(priv, status, STAT_LEC_MASK);
+
+	if (status & (STAT_WARN | STAT_BOFF) ||
+	    (status & STAT_LEC_MASK) != STAT_LEC_MASK) {
+		cc770_err(dev, status);
+		return status & STAT_BOFF;
+	}
+
+	return 0;
+}
+
+static void cc770_rx_interrupt(struct net_device *dev, unsigned int o)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+	struct net_device_stats *stats = &dev->stats;
+	unsigned int mo = obj2msgobj(o);
+	u8 ctrl1;
+	int n = CC770_MAX_MSG;
+
+	while (n--) {
+		ctrl1 = cc770_read_reg(priv, msgobj[mo].ctrl1);
+
+		if (!(ctrl1 & NEWDAT_SET))  {
+			/* Check for RTR if additional functions are enabled */
+			if (priv->control_normal_mode & CTRL_EAF) {
+				if (!(cc770_read_reg(priv, msgobj[mo].ctrl0) &
+				      INTPND_SET))
+					break;
+			} else {
+				break;
+			}
+		}
+
+		if (ctrl1 & MSGLST_SET) {
+			stats->rx_over_errors++;
+			stats->rx_errors++;
+		}
+		if (mo < MSGOBJ_LAST)
+			cc770_write_reg(priv, msgobj[mo].ctrl1,
+					NEWDAT_RES | MSGLST_RES |
+					TXRQST_UNC | RMTPND_UNC);
+		cc770_rx(dev, mo, ctrl1);
+
+		cc770_write_reg(priv, msgobj[mo].ctrl0,
+				MSGVAL_SET | TXIE_RES |
+				RXIE_SET | INTPND_RES);
+		cc770_write_reg(priv, msgobj[mo].ctrl1,
+				NEWDAT_RES | MSGLST_RES |
+				TXRQST_RES | RMTPND_RES);
+	}
+}
+
+static void cc770_rtr_interrupt(struct net_device *dev, unsigned int o)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+	unsigned int mo = obj2msgobj(o);
+	u8 ctrl0, ctrl1;
+	int n = CC770_MAX_MSG;
+
+	while (n--) {
+		ctrl0 = cc770_read_reg(priv, msgobj[mo].ctrl0);
+		if (!(ctrl0 & INTPND_SET))
+			break;
+
+		ctrl1 = cc770_read_reg(priv, msgobj[mo].ctrl1);
+		cc770_rx(dev, mo, ctrl1);
+
+		cc770_write_reg(priv, msgobj[mo].ctrl0,
+				MSGVAL_SET | TXIE_RES |
+				RXIE_SET | INTPND_RES);
+		cc770_write_reg(priv, msgobj[mo].ctrl1,
+				NEWDAT_RES | CPUUPD_SET |
+				TXRQST_RES | RMTPND_RES);
+	}
+}
+
+static void cc770_tx_interrupt(struct net_device *dev, unsigned int o)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+	struct net_device_stats *stats = &dev->stats;
+	unsigned int mo = obj2msgobj(o);
+
+	/* Nothing more to send, switch off interrupts */
+	cc770_write_reg(priv, msgobj[mo].ctrl0,
+			MSGVAL_RES | TXIE_RES | RXIE_RES | INTPND_RES);
+	/*
+	 * We had some cases of repeated IRQ so make sure the
+	 * INT is acknowledged
+	 */
+	cc770_write_reg(priv, msgobj[mo].ctrl0,
+			MSGVAL_UNC | TXIE_UNC | RXIE_UNC | INTPND_RES);
+
+	stats->tx_packets++;
+	can_get_echo_skb(dev, 0);
+	netif_wake_queue(dev);
+}
+
+irqreturn_t cc770_interrupt(int irq, void *dev_id)
+{
+	struct net_device *dev = (struct net_device *)dev_id;
+	struct cc770_priv *priv = netdev_priv(dev);
+	u8 intid;
+	int o, n = 0;
+
+	/* Shared interrupts and IRQ off? */
+	if (priv->can.state == CAN_STATE_STOPPED)
+		return IRQ_NONE;
+
+	if (priv->pre_irq)
+		priv->pre_irq(priv);
+
+	while (n < CC770_MAX_IRQ) {
+		/* Read the highest pending interrupt request */
+		intid = cc770_read_reg(priv, interrupt);
+		if (!intid)
+			break;
+		n++;
+
+		if (intid == 1) {
+			/* Exit in case of bus-off */
+			if (cc770_status_interrupt(dev))
+				break;
+		} else {
+			o = intid2obj(intid);
+
+			if (o >= CC770_OBJ_MAX) {
+				netdev_err(dev, "Unexpected interrupt id %d\n",
+					   intid);
+				continue;
+			}
+
+			if (priv->obj_flags[o] & CC770_OBJ_FLAG_RTR)
+				cc770_rtr_interrupt(dev, o);
+			else if (priv->obj_flags[o] & CC770_OBJ_FLAG_RX)
+				cc770_rx_interrupt(dev, o);
+			else
+				cc770_tx_interrupt(dev, o);
+		}
+	}
+
+	if (priv->post_irq)
+		priv->post_irq(priv);
+
+	if (n >= CC770_MAX_IRQ)
+		netdev_dbg(dev, "%d messages handled in ISR", n);
+
+	return (n) ? IRQ_HANDLED : IRQ_NONE;
+}
+
+static int cc770_open(struct net_device *dev)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+	int err;
+
+	/* set chip into reset mode */
+	set_reset_mode(dev);
+
+	/* common open */
+	err = open_candev(dev);
+	if (err)
+		return err;
+
+	err = request_irq(dev->irq, &cc770_interrupt, priv->irq_flags,
+			  dev->name, dev);
+	if (err) {
+		close_candev(dev);
+		return -EAGAIN;
+	}
+
+	/* init and start chip */
+	cc770_start(dev);
+
+	netif_start_queue(dev);
+
+	return 0;
+}
+
+static int cc770_close(struct net_device *dev)
+{
+	netif_stop_queue(dev);
+	set_reset_mode(dev);
+
+	free_irq(dev->irq, dev);
+	close_candev(dev);
+
+	return 0;
+}
+
+struct net_device *alloc_cc770dev(int sizeof_priv)
+{
+	struct net_device *dev;
+	struct cc770_priv *priv;
+
+	dev = alloc_candev(sizeof(struct cc770_priv) + sizeof_priv,
+			   CC770_ECHO_SKB_MAX);
+	if (!dev)
+		return NULL;
+
+	priv = netdev_priv(dev);
+
+	priv->dev = dev;
+	priv->can.bittiming_const = &cc770_bittiming_const;
+	priv->can.do_set_bittiming = cc770_set_bittiming;
+	priv->can.do_set_mode = cc770_set_mode;
+	priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES;
+
+	memcpy(priv->obj_flags, cc770_obj_flags, sizeof(cc770_obj_flags));
+
+	if (sizeof_priv)
+		priv->priv = (void *)priv + sizeof(struct cc770_priv);
+
+	return dev;
+}
+EXPORT_SYMBOL_GPL(alloc_cc770dev);
+
+void free_cc770dev(struct net_device *dev)
+{
+	free_candev(dev);
+}
+EXPORT_SYMBOL_GPL(free_cc770dev);
+
+static const struct net_device_ops cc770_netdev_ops = {
+	.ndo_open = cc770_open,
+	.ndo_stop = cc770_close,
+	.ndo_start_xmit = cc770_start_xmit,
+};
+
+int register_cc770dev(struct net_device *dev)
+{
+	struct cc770_priv *priv = netdev_priv(dev);
+	int err;
+
+	err = cc770_probe_chip(dev);
+	if (err)
+		return err;
+
+	dev->netdev_ops = &cc770_netdev_ops;
+
+	dev->flags |= IFF_ECHO;	/* we support local echo */
+
+	/* Should we use additional functions? */
+	if (!i82527_compat && priv->control_normal_mode & CTRL_EAF) {
+		priv->can.do_get_berr_counter = cc770_get_berr_counter;
+		priv->control_normal_mode = CTRL_IE | CTRL_EAF | CTRL_EIE;
+		netdev_dbg(dev, "i82527 mode with additional functions\n");
+	} else {
+		priv->control_normal_mode = CTRL_IE | CTRL_EIE;
+		netdev_dbg(dev, "strict i82527 compatibility mode\n");
+	}
+
+	chipset_init(priv);
+	set_reset_mode(dev);
+
+	return register_candev(dev);
+}
+EXPORT_SYMBOL_GPL(register_cc770dev);
+
+void unregister_cc770dev(struct net_device *dev)
+{
+	set_reset_mode(dev);
+	unregister_candev(dev);
+}
+EXPORT_SYMBOL_GPL(unregister_cc770dev);
+
+static __init int cc770_init(void)
+{
+	if (msgobj15_eff) {
+		cc770_obj_flags[CC770_OBJ_RX0] |= CC770_OBJ_FLAG_EFF;
+		cc770_obj_flags[CC770_OBJ_RX1] &= ~CC770_OBJ_FLAG_EFF;
+	}
+
+	pr_info("CAN netdevice driver\n");
+
+	return 0;
+}
+module_init(cc770_init);
+
+static __exit void cc770_exit(void)
+{
+	pr_info("driver removed\n");
+}
+module_exit(cc770_exit);
diff --git a/drivers/net/can/cc770/cc770.h b/drivers/net/can/cc770/cc770.h
new file mode 100644
index 0000000..a1739db
--- /dev/null
+++ b/drivers/net/can/cc770/cc770.h
@@ -0,0 +1,203 @@
+/*
+ * Core driver for the CC770 and AN82527 CAN controllers
+ *
+ * Copyright (C) 2009, 2011 Wolfgang Grandegger <wg@grandegger.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef CC770_DEV_H
+#define CC770_DEV_H
+
+#include <linux/can/dev.h>
+
+struct cc770_msgobj {
+	u8 ctrl0;
+	u8 ctrl1;
+	u8 id[4];
+	u8 config;
+	u8 data[8];
+	u8 dontuse;		/* padding */
+} __packed;
+
+struct cc770_regs {
+	union {
+		struct cc770_msgobj msgobj[16]; /* Message object 1..15 */
+		struct {
+			u8 control;		/* Control Register */
+			u8 status;		/* Status Register */
+			u8 cpu_interface;	/* CPU Interface Register */
+			u8 dontuse1;
+			u8 high_speed_read[2];	/* High Speed Read */
+			u8 global_mask_std[2];	/* Standard Global Mask */
+			u8 global_mask_ext[4];	/* Extended Global Mask */
+			u8 msg15_mask[4];	/* Message 15 Mask */
+			u8 dontuse2[15];
+			u8 clkout;		/* Clock Out Register */
+			u8 dontuse3[15];
+			u8 bus_config;		/* Bus Configuration Register */
+			u8 dontuse4[15];
+			u8 bit_timing_0;	/* Bit Timing Register byte 0 */
+			u8 dontuse5[15];
+			u8 bit_timing_1;	/* Bit Timing Register byte 1 */
+			u8 dontuse6[15];
+			u8 interrupt;		/* Interrupt Register */
+			u8 dontuse7[15];
+			u8 rx_error_counter;	/* Receive Error Counter */
+			u8 dontuse8[15];
+			u8 tx_error_counter;	/* Transmit Error Counter */
+			u8 dontuse9[31];
+			u8 p1_conf;
+			u8 dontuse10[15];
+			u8 p2_conf;
+			u8 dontuse11[15];
+			u8 p1_in;
+			u8 dontuse12[15];
+			u8 p2_in;
+			u8 dontuse13[15];
+			u8 p1_out;
+			u8 dontuse14[15];
+			u8 p2_out;
+			u8 dontuse15[15];
+			u8 serial_reset_addr;
+		};
+	};
+} __packed;
+
+/* Control Register (0x00) */
+#define CTRL_INI	0x01	/* Initialization */
+#define CTRL_IE		0x02	/* Interrupt Enable */
+#define CTRL_SIE	0x04	/* Status Interrupt Enable */
+#define CTRL_EIE	0x08	/* Error Interrupt Enable */
+#define CTRL_EAF	0x20	/* Enable additional functions */
+#define CTRL_CCE	0x40	/* Change Configuration Enable */
+
+/* Status Register (0x01) */
+#define STAT_LEC_STUFF	0x01	/* Stuff error */
+#define STAT_LEC_FORM	0x02	/* Form error */
+#define STAT_LEC_ACK	0x03	/* Acknowledgement error */
+#define STAT_LEC_BIT1	0x04	/* Bit1 error */
+#define STAT_LEC_BIT0	0x05	/* Bit0 error */
+#define STAT_LEC_CRC	0x06	/* CRC error */
+#define STAT_LEC_MASK	0x07	/* Last Error Code mask */
+#define STAT_TXOK	0x08	/* Transmit Message Successfully */
+#define STAT_RXOK	0x10	/* Receive Message Successfully */
+#define STAT_WAKE	0x20	/* Wake Up Status */
+#define STAT_WARN	0x40	/* Warning Status */
+#define STAT_BOFF	0x80	/* Bus Off Status */
+
+/*
+ * CPU Interface Register (0x02)
+ * Clock Out Register (0x1f)
+ * Bus Configuration Register (0x2f)
+ *
+ * see include/linux/can/platform/cc770.h
+ */
+
+/* Message Control Register 0 (Base Address + 0x0) */
+#define INTPND_RES	0x01	/* No Interrupt pending */
+#define INTPND_SET	0x02	/* Interrupt pending */
+#define INTPND_UNC	0x03
+#define RXIE_RES	0x04	/* Receive Interrupt Disable */
+#define RXIE_SET	0x08	/* Receive Interrupt Enable */
+#define RXIE_UNC	0x0c
+#define TXIE_RES	0x10	/* Transmit Interrupt Disable */
+#define TXIE_SET	0x20	/* Transmit Interrupt Enable */
+#define TXIE_UNC	0x30
+#define MSGVAL_RES	0x40	/* Message Invalid */
+#define MSGVAL_SET	0x80	/* Message Valid */
+#define MSGVAL_UNC	0xc0
+
+/* Message Control Register 1 (Base Address + 0x01) */
+#define NEWDAT_RES	0x01	/* No New Data */
+#define NEWDAT_SET	0x02	/* New Data */
+#define NEWDAT_UNC	0x03
+#define MSGLST_RES	0x04	/* No Message Lost */
+#define MSGLST_SET	0x08	/* Message Lost */
+#define MSGLST_UNC	0x0c
+#define CPUUPD_RES	0x04	/* No CPU Updating */
+#define CPUUPD_SET	0x08	/* CPU Updating */
+#define CPUUPD_UNC	0x0c
+#define TXRQST_RES	0x10	/* No Transmission Request */
+#define TXRQST_SET	0x20	/* Transmission Request */
+#define TXRQST_UNC	0x30
+#define RMTPND_RES	0x40	/* No Remote Request Pending */
+#define RMTPND_SET	0x80	/* Remote Request Pending */
+#define RMTPND_UNC	0xc0
+
+/* Message Configuration Register (Base Address + 0x06) */
+#define MSGCFG_XTD	0x04	/* Extended Identifier */
+#define MSGCFG_DIR	0x08	/* Direction is Transmit */
+
+#define MSGOBJ_FIRST	1
+#define MSGOBJ_LAST	15
+
+#define CC770_IO_SIZE	0x100
+#define CC770_MAX_IRQ	20	/* max. number of interrupts handled in ISR */
+#define CC770_MAX_MSG	4	/* max. number of messages handled in ISR */
+
+#define CC770_ECHO_SKB_MAX	1
+
+#define cc770_read_reg(priv, member)					\
+	priv->read_reg(priv, offsetof(struct cc770_regs, member))
+
+#define cc770_write_reg(priv, member, value)				\
+	priv->write_reg(priv, offsetof(struct cc770_regs, member), value)
+
+/*
+ * Message objects and flags used by this driver
+ */
+#define CC770_OBJ_FLAG_RX	0x01
+#define CC770_OBJ_FLAG_RTR	0x02
+#define CC770_OBJ_FLAG_EFF	0x04
+
+enum {
+	CC770_OBJ_RX0 = 0,	/* for receiving normal messages */
+	CC770_OBJ_RX1,		/* for receiving normal messages */
+	CC770_OBJ_RX_RTR0,	/* for receiving remote transmission requests */
+	CC770_OBJ_RX_RTR1,	/* for receiving remote transmission requests */
+	CC770_OBJ_TX,		/* for sending messages */
+	CC770_OBJ_MAX
+};
+
+#define obj2msgobj(o)	(MSGOBJ_LAST - (o)) /* message object 11..15 */
+
+/*
+ * CC770 private data structure
+ */
+struct cc770_priv {
+	struct can_priv can;	/* must be the first member */
+	struct sk_buff *echo_skb;
+
+	/* the lower-layer is responsible for appropriate locking */
+	u8 (*read_reg)(const struct cc770_priv *priv, int reg);
+	void (*write_reg)(const struct cc770_priv *priv, int reg, u8 val);
+	void (*pre_irq)(const struct cc770_priv *priv);
+	void (*post_irq)(const struct cc770_priv *priv);
+
+	void *priv;		/* for board-specific data */
+	struct net_device *dev;
+
+	void __iomem *reg_base;	 /* ioremap'ed address to registers */
+	unsigned long irq_flags; /* for request_irq() */
+
+	unsigned char obj_flags[CC770_OBJ_MAX];
+	u8 control_normal_mode;	/* Control register for normal mode */
+	u8 cpu_interface;	/* CPU interface register */
+	u8 clkout;		/* Clock out register */
+	u8 bus_config;		/* Bus conffiguration register */
+};
+
+struct net_device *alloc_cc770dev(int sizeof_priv);
+void free_cc770dev(struct net_device *dev);
+int register_cc770dev(struct net_device *dev);
+void unregister_cc770dev(struct net_device *dev);
+
+#endif /* CC770_DEV_H */
diff --git a/drivers/net/can/cc770/cc770_isa.c b/drivers/net/can/cc770/cc770_isa.c
new file mode 100644
index 0000000..4be5fe2
--- /dev/null
+++ b/drivers/net/can/cc770/cc770_isa.c
@@ -0,0 +1,367 @@
+/*
+ * Driver for CC770 and AN82527 CAN controllers on the legacy ISA bus
+ *
+ * Copyright (C) 2009, 2011 Wolfgang Grandegger <wg@grandegger.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * Bosch CC770 and Intel AN82527 CAN controllers on the ISA or PC-104 bus.
+ * The I/O port or memory address and the IRQ number must be specified via
+ * module parameters:
+ *
+ *   insmod cc770_isa.ko port=0x310,0x380 irq=7,11
+ *
+ * for ISA devices using I/O ports or:
+ *
+ *   insmod cc770_isa.ko mem=0xd1000,0xd1000 irq=7,11
+ *
+ * for memory mapped ISA devices.
+ *
+ * Indirect access via address and data port is supported as well:
+ *
+ *   insmod cc770_isa.ko port=0x310,0x380 indirect=1 irq=7,11
+ *
+ * Furthermore, the following mode parameter can be defined:
+ *
+ *   clk: External oscillator clock frequency (default=16000000 [16 MHz])
+ *   cir: CPU interface register (default=0x40 [DSC])
+ *   bcr: Bus configuration register (default=0x40 [CBY])
+ *   cor: Clockout register (default=0x00)
+ *
+ * Note: for clk, cir, bcr and cor, the first argument re-defines the
+ * default for all other devices, e.g.:
+ *
+ *   insmod cc770_isa.ko mem=0xd1000,0xd1000 irq=7,11 clk=24000000
+ *
+ * is equivalent to
+ *
+ *   insmod cc770_isa.ko mem=0xd1000,0xd1000 irq=7,11 clk=24000000,24000000
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/netdevice.h>
+#include <linux/delay.h>
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/platform/cc770.h>
+
+#include "cc770.h"
+
+#define MAXDEV 8
+
+MODULE_AUTHOR("Wolfgang Grandegger <wg@grandegger.com>");
+MODULE_DESCRIPTION("Socket-CAN driver for CC770 on the ISA bus");
+MODULE_LICENSE("GPL v2");
+
+#define CLK_DEFAULT	16000000	/* 16 MHz */
+#define COR_DEFAULT	0x00
+#define BCR_DEFAULT	BUSCFG_CBY
+
+static unsigned long port[MAXDEV];
+static unsigned long mem[MAXDEV];
+static int __devinitdata irq[MAXDEV];
+static int __devinitdata clk[MAXDEV];
+static u8 __devinitdata cir[MAXDEV] = {[0 ... (MAXDEV - 1)] = 0xff};
+static u8 __devinitdata cor[MAXDEV] = {[0 ... (MAXDEV - 1)] = 0xff};
+static u8 __devinitdata bcr[MAXDEV] = {[0 ... (MAXDEV - 1)] = 0xff};
+static int __devinitdata indirect[MAXDEV] = {[0 ... (MAXDEV - 1)] = -1};
+
+module_param_array(port, ulong, NULL, S_IRUGO);
+MODULE_PARM_DESC(port, "I/O port number");
+
+module_param_array(mem, ulong, NULL, S_IRUGO);
+MODULE_PARM_DESC(mem, "I/O memory address");
+
+module_param_array(indirect, int, NULL, S_IRUGO);
+MODULE_PARM_DESC(indirect, "Indirect access via address and data port");
+
+module_param_array(irq, int, NULL, S_IRUGO);
+MODULE_PARM_DESC(irq, "IRQ number");
+
+module_param_array(clk, int, NULL, S_IRUGO);
+MODULE_PARM_DESC(clk, "External oscillator clock frequency "
+		 "(default=16000000 [16 MHz])");
+
+module_param_array(cir, byte, NULL, S_IRUGO);
+MODULE_PARM_DESC(cir, "CPU interface register (default=0x40 [DSC])");
+
+module_param_array(cor, byte, NULL, S_IRUGO);
+MODULE_PARM_DESC(cor, "Clockout register (default=0x00)");
+
+module_param_array(bcr, byte, NULL, S_IRUGO);
+MODULE_PARM_DESC(bcr, "Bus configuration register (default=0x40 [CBY])");
+
+#define CC770_IOSIZE          0x20
+#define CC770_IOSIZE_INDIRECT 0x02
+
+static struct platform_device *cc770_isa_devs[MAXDEV];
+
+static u8 cc770_isa_mem_read_reg(const struct cc770_priv *priv, int reg)
+{
+	return readb(priv->reg_base + reg);
+}
+
+static void cc770_isa_mem_write_reg(const struct cc770_priv *priv,
+				      int reg, u8 val)
+{
+	writeb(val, priv->reg_base + reg);
+}
+
+static u8 cc770_isa_port_read_reg(const struct cc770_priv *priv, int reg)
+{
+	return inb((unsigned long)priv->reg_base + reg);
+}
+
+static void cc770_isa_port_write_reg(const struct cc770_priv *priv,
+				       int reg, u8 val)
+{
+	outb(val, (unsigned long)priv->reg_base + reg);
+}
+
+static u8 cc770_isa_port_read_reg_indirect(const struct cc770_priv *priv,
+					     int reg)
+{
+	unsigned long base = (unsigned long)priv->reg_base;
+
+	outb(reg, base);
+	return inb(base + 1);
+}
+
+static void cc770_isa_port_write_reg_indirect(const struct cc770_priv *priv,
+						int reg, u8 val)
+{
+	unsigned long base = (unsigned long)priv->reg_base;
+
+	outb(reg, base);
+	outb(val, base + 1);
+}
+
+static int __devinit cc770_isa_probe(struct platform_device *pdev)
+{
+	struct net_device *dev;
+	struct cc770_priv *priv;
+	void __iomem *base = NULL;
+	int iosize = CC770_IOSIZE;
+	int idx = pdev->id;
+	int err;
+	u32 clktmp;
+
+	dev_dbg(&pdev->dev, "probing idx=%d: port=%#lx, mem=%#lx, irq=%d\n",
+		idx, port[idx], mem[idx], irq[idx]);
+	if (mem[idx]) {
+		if (!request_mem_region(mem[idx], iosize, KBUILD_MODNAME)) {
+			err = -EBUSY;
+			goto exit;
+		}
+		base = ioremap_nocache(mem[idx], iosize);
+		if (!base) {
+			err = -ENOMEM;
+			goto exit_release;
+		}
+	} else {
+		if (indirect[idx] > 0 ||
+		    (indirect[idx] == -1 && indirect[0] > 0))
+			iosize = CC770_IOSIZE_INDIRECT;
+		if (!request_region(port[idx], iosize, KBUILD_MODNAME)) {
+			err = -EBUSY;
+			goto exit;
+		}
+	}
+
+	dev = alloc_cc770dev(0);
+	if (!dev) {
+		err = -ENOMEM;
+		goto exit_unmap;
+	}
+	priv = netdev_priv(dev);
+
+	dev->irq = irq[idx];
+	priv->irq_flags = IRQF_SHARED;
+	if (mem[idx]) {
+		priv->reg_base = base;
+		dev->base_addr = mem[idx];
+		priv->read_reg = cc770_isa_mem_read_reg;
+		priv->write_reg = cc770_isa_mem_write_reg;
+	} else {
+		priv->reg_base = (void __iomem *)port[idx];
+		dev->base_addr = port[idx];
+
+		if (iosize == CC770_IOSIZE_INDIRECT) {
+			priv->read_reg = cc770_isa_port_read_reg_indirect;
+			priv->write_reg = cc770_isa_port_write_reg_indirect;
+		} else {
+			priv->read_reg = cc770_isa_port_read_reg;
+			priv->write_reg = cc770_isa_port_write_reg;
+		}
+	}
+
+	if (clk[idx])
+		clktmp = clk[idx];
+	else if (clk[0])
+		clktmp = clk[0];
+	else
+		clktmp = CLK_DEFAULT;
+	priv->can.clock.freq = clktmp;
+
+	if (cir[idx] != 0xff) {
+		priv->cpu_interface = cir[idx];
+	} else if (cir[0] != 0xff) {
+		priv->cpu_interface = cir[0];
+	} else {
+		/* The system clock may not exceed 10 MHz */
+		if (clktmp > 10000000) {
+			priv->cpu_interface |= CPUIF_DSC;
+			clktmp /= 2;
+		}
+		/* The memory clock may not exceed 8 MHz */
+		if (clktmp > 8000000)
+			priv->cpu_interface |= CPUIF_DMC;
+	}
+
+	if (priv->cpu_interface & CPUIF_DSC)
+		priv->can.clock.freq /= 2;
+
+	if (bcr[idx] != 0xff)
+		priv->bus_config = bcr[idx];
+	else if (bcr[0] != 0xff)
+		priv->bus_config = bcr[0];
+	else
+		priv->bus_config = BCR_DEFAULT;
+
+	if (cor[idx] != 0xff)
+		priv->clkout = cor[idx];
+	else if (cor[0] != 0xff)
+		priv->clkout = cor[0];
+	else
+		priv->clkout = COR_DEFAULT;
+
+	dev_set_drvdata(&pdev->dev, dev);
+	SET_NETDEV_DEV(dev, &pdev->dev);
+
+	err = register_cc770dev(dev);
+	if (err) {
+		dev_err(&pdev->dev,
+			"couldn't register device (err=%d)\n", err);
+		goto exit_unmap;
+	}
+
+	dev_info(&pdev->dev, "device registered (reg_base=0x%p, irq=%d)\n",
+		 priv->reg_base, dev->irq);
+	return 0;
+
+ exit_unmap:
+	if (mem[idx])
+		iounmap(base);
+ exit_release:
+	if (mem[idx])
+		release_mem_region(mem[idx], iosize);
+	else
+		release_region(port[idx], iosize);
+ exit:
+	return err;
+}
+
+static int __devexit cc770_isa_remove(struct platform_device *pdev)
+{
+	struct net_device *dev = dev_get_drvdata(&pdev->dev);
+	struct cc770_priv *priv = netdev_priv(dev);
+	int idx = pdev->id;
+
+	unregister_cc770dev(dev);
+	dev_set_drvdata(&pdev->dev, NULL);
+
+	if (mem[idx]) {
+		iounmap(priv->reg_base);
+		release_mem_region(mem[idx], CC770_IOSIZE);
+	} else {
+		if (priv->read_reg == cc770_isa_port_read_reg_indirect)
+			release_region(port[idx], CC770_IOSIZE_INDIRECT);
+		else
+			release_region(port[idx], CC770_IOSIZE);
+	}
+	free_cc770dev(dev);
+
+	return 0;
+}
+
+static struct platform_driver cc770_isa_driver = {
+	.probe = cc770_isa_probe,
+	.remove = __devexit_p(cc770_isa_remove),
+	.driver = {
+		.name = KBUILD_MODNAME,
+		.owner = THIS_MODULE,
+	},
+};
+
+static int __init cc770_isa_init(void)
+{
+	int idx, err;
+
+	for (idx = 0; idx < ARRAY_SIZE(cc770_isa_devs); idx++) {
+		if ((port[idx] || mem[idx]) && irq[idx]) {
+			cc770_isa_devs[idx] =
+				platform_device_alloc(KBUILD_MODNAME, idx);
+			if (!cc770_isa_devs[idx]) {
+				err = -ENOMEM;
+				goto exit_free_devices;
+			}
+			err = platform_device_add(cc770_isa_devs[idx]);
+			if (err) {
+				platform_device_put(cc770_isa_devs[idx]);
+				goto exit_free_devices;
+			}
+			pr_debug("platform device %d: port=%#lx, mem=%#lx, "
+				 "irq=%d\n",
+				 idx, port[idx], mem[idx], irq[idx]);
+		} else if (idx == 0 || port[idx] || mem[idx]) {
+			pr_err("insufficient parameters supplied\n");
+			err = -EINVAL;
+			goto exit_free_devices;
+		}
+	}
+
+	err = platform_driver_register(&cc770_isa_driver);
+	if (err)
+		goto exit_free_devices;
+
+	pr_info("driver for max. %d devices registered\n", MAXDEV);
+
+	return 0;
+
+exit_free_devices:
+	while (--idx >= 0) {
+		if (cc770_isa_devs[idx])
+			platform_device_unregister(cc770_isa_devs[idx]);
+	}
+
+	return err;
+}
+module_init(cc770_isa_init);
+
+static void __exit cc770_isa_exit(void)
+{
+	int idx;
+
+	platform_driver_unregister(&cc770_isa_driver);
+	for (idx = 0; idx < ARRAY_SIZE(cc770_isa_devs); idx++) {
+		if (cc770_isa_devs[idx])
+			platform_device_unregister(cc770_isa_devs[idx]);
+	}
+}
+module_exit(cc770_isa_exit);
diff --git a/drivers/net/can/cc770/cc770_platform.c b/drivers/net/can/cc770/cc770_platform.c
new file mode 100644
index 0000000..53115ee
--- /dev/null
+++ b/drivers/net/can/cc770/cc770_platform.c
@@ -0,0 +1,272 @@
+/*
+ * Driver for CC770 and AN82527 CAN controllers on the platform bus
+ *
+ * Copyright (C) 2009, 2011 Wolfgang Grandegger <wg@grandegger.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the version 2 of the GNU General Public License
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+/*
+ * If platform data are used you should have similar definitions
+ * in your board-specific code:
+ *
+ *   static struct cc770_platform_data myboard_cc770_pdata = {
+ *           .osc_freq = 16000000,
+ *           .cir = 0x41,
+ *           .cor = 0x20,
+ *           .bcr = 0x40,
+ *   };
+ *
+ * Please see include/linux/can/platform/cc770.h for description of
+ * above fields.
+ *
+ * If the device tree is used, you need a CAN node definition in your
+ * DTS file similar to:
+ *
+ *   can@3,100 {
+ *           compatible = "bosch,cc770";
+ *           reg = <3 0x100 0x80>;
+ *           interrupts = <2 0>;
+ *           interrupt-parent = <&mpic>;
+ *           bosch,external-clock-frequency = <16000000>;
+ *   };
+ *
+ * See "Documentation/devicetree/bindings/net/can/cc770.txt" for further
+ * information.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/netdevice.h>
+#include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/platform/cc770.h>
+
+#include "cc770.h"
+
+#define DRV_NAME "cc770_platform"
+
+MODULE_AUTHOR("Wolfgang Grandegger <wg@grandegger.com>");
+MODULE_DESCRIPTION("Socket-CAN driver for CC770 on the platform bus");
+MODULE_LICENSE("GPL v2");
+
+#define CC770_PLATFORM_CAN_CLOCK  16000000
+
+static u8 cc770_platform_read_reg(const struct cc770_priv *priv, int reg)
+{
+	return ioread8(priv->reg_base + reg);
+}
+
+static void cc770_platform_write_reg(const struct cc770_priv *priv, int reg,
+				     u8 val)
+{
+	iowrite8(val, priv->reg_base + reg);
+}
+
+static int __devinit cc770_get_of_node_data(struct platform_device *pdev,
+					    struct cc770_priv *priv)
+{
+	struct device_node *np = pdev->dev.of_node;
+	const u32 *prop;
+	int prop_size;
+	u32 clkext;
+
+	prop = of_get_property(np, "bosch,external-clock-frequency",
+			       &prop_size);
+	if (prop && (prop_size ==  sizeof(u32)))
+		clkext = *prop;
+	else
+		clkext = CC770_PLATFORM_CAN_CLOCK; /* default */
+	priv->can.clock.freq = clkext;
+
+	/* The system clock may not exceed 10 MHz */
+	if (priv->can.clock.freq > 10000000) {
+		priv->cpu_interface |= CPUIF_DSC;
+		priv->can.clock.freq /= 2;
+	}
+
+	/* The memory clock may not exceed 8 MHz */
+	if (priv->can.clock.freq > 8000000)
+		priv->cpu_interface |= CPUIF_DMC;
+
+	if (of_get_property(np, "bosch,divide-memory-clock", NULL))
+		priv->cpu_interface |= CPUIF_DMC;
+	if (of_get_property(np, "bosch,iso-low-speed-mux", NULL))
+		priv->cpu_interface |= CPUIF_MUX;
+
+	if (!of_get_property(np, "bosch,no-comperator-bypass", NULL))
+		priv->bus_config |= BUSCFG_CBY;
+	if (of_get_property(np, "bosch,disconnect-rx0-input", NULL))
+		priv->bus_config |= BUSCFG_DR0;
+	if (of_get_property(np, "bosch,disconnect-rx1-input", NULL))
+		priv->bus_config |= BUSCFG_DR1;
+	if (of_get_property(np, "bosch,disconnect-tx1-output", NULL))
+		priv->bus_config |= BUSCFG_DT1;
+	if (of_get_property(np, "bosch,polarity-dominant", NULL))
+		priv->bus_config |= BUSCFG_POL;
+
+	prop = of_get_property(np, "bosch,clock-out-frequency", &prop_size);
+	if (prop && (prop_size == sizeof(u32)) && *prop > 0) {
+		u32 cdv = clkext / *prop;
+		int slew;
+
+		if (cdv > 0 && cdv < 16) {
+			priv->cpu_interface |= CPUIF_CEN;
+			priv->clkout |= (cdv - 1) & CLKOUT_CD_MASK;
+
+			prop = of_get_property(np, "bosch,slew-rate",
+					       &prop_size);
+			if (prop && (prop_size == sizeof(u32))) {
+				slew = *prop;
+			} else {
+				/* Determine default slew rate */
+				slew = (CLKOUT_SL_MASK >>
+					CLKOUT_SL_SHIFT) -
+					((cdv * clkext - 1) / 8000000);
+				if (slew < 0)
+					slew = 0;
+			}
+			priv->clkout |= (slew << CLKOUT_SL_SHIFT) &
+				CLKOUT_SL_MASK;
+		} else {
+			dev_dbg(&pdev->dev, "invalid clock-out-frequency\n");
+		}
+	}
+
+	return 0;
+}
+
+static int __devinit cc770_get_platform_data(struct platform_device *pdev,
+					     struct cc770_priv *priv)
+{
+
+	struct cc770_platform_data *pdata = pdev->dev.platform_data;
+
+	priv->can.clock.freq = pdata->osc_freq;
+	if (priv->cpu_interface | CPUIF_DSC)
+		priv->can.clock.freq /= 2;
+	priv->clkout = pdata->cor;
+	priv->bus_config = pdata->bcr;
+	priv->cpu_interface = pdata->cir;
+
+	return 0;
+}
+
+static int __devinit cc770_platform_probe(struct platform_device *pdev)
+{
+	struct net_device *dev;
+	struct cc770_priv *priv;
+	struct resource *mem;
+	resource_size_t mem_size;
+	void __iomem *base;
+	int err, irq;
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	irq = platform_get_irq(pdev, 0);
+	if (!mem || irq <= 0)
+		return -ENODEV;
+
+	mem_size = resource_size(mem);
+	if (!request_mem_region(mem->start, mem_size, pdev->name))
+		return -EBUSY;
+
+	base = ioremap(mem->start, mem_size);
+	if (!base) {
+		err = -ENOMEM;
+		goto exit_release_mem;
+	}
+
+	dev = alloc_cc770dev(0);
+	if (!dev) {
+		err = -ENOMEM;
+		goto exit_unmap_mem;
+	}
+
+	dev->irq = irq;
+	priv = netdev_priv(dev);
+	priv->read_reg = cc770_platform_read_reg;
+	priv->write_reg = cc770_platform_write_reg;
+	priv->irq_flags = IRQF_SHARED;
+	priv->reg_base = base;
+
+	if (pdev->dev.of_node)
+		err = cc770_get_of_node_data(pdev, priv);
+	else if (pdev->dev.platform_data)
+		err = cc770_get_platform_data(pdev, priv);
+	else
+		err = -ENODEV;
+	if (err)
+		goto exit_free_cc770;
+
+	dev_dbg(&pdev->dev,
+		 "reg_base=0x%p irq=%d clock=%d cpu_interface=0x%02x "
+		 "bus_config=0x%02x clkout=0x%02x\n",
+		 priv->reg_base, dev->irq, priv->can.clock.freq,
+		 priv->cpu_interface, priv->bus_config, priv->clkout);
+
+	dev_set_drvdata(&pdev->dev, dev);
+	SET_NETDEV_DEV(dev, &pdev->dev);
+
+	err = register_cc770dev(dev);
+	if (err) {
+		dev_err(&pdev->dev,
+			"couldn't register CC700 device (err=%d)\n", err);
+		goto exit_free_cc770;
+	}
+
+	return 0;
+
+exit_free_cc770:
+	free_cc770dev(dev);
+exit_unmap_mem:
+	iounmap(base);
+exit_release_mem:
+	release_mem_region(mem->start, mem_size);
+
+	return err;
+}
+
+static int __devexit cc770_platform_remove(struct platform_device *pdev)
+{
+	struct net_device *dev = dev_get_drvdata(&pdev->dev);
+	struct cc770_priv *priv = netdev_priv(dev);
+	struct resource *mem;
+
+	unregister_cc770dev(dev);
+	iounmap(priv->reg_base);
+	free_cc770dev(dev);
+
+	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	release_mem_region(mem->start, resource_size(mem));
+
+	return 0;
+}
+
+static struct of_device_id __devinitdata cc770_platform_table[] = {
+	{.compatible = "bosch,cc770"}, /* CC770 from Bosch */
+	{.compatible = "intc,82527"},  /* AN82527 from Intel CP */
+	{},
+};
+
+static struct platform_driver cc770_platform_driver = {
+	.driver = {
+		.name = DRV_NAME,
+		.owner = THIS_MODULE,
+		.of_match_table = cc770_platform_table,
+	},
+	.probe = cc770_platform_probe,
+	.remove = __devexit_p(cc770_platform_remove),
+};
+
+module_platform_driver(cc770_platform_driver);
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 25695bd..120f1ab 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -454,7 +454,7 @@ static void can_setup(struct net_device *dev)
 
 	/* New-style flags. */
 	dev->flags = IFF_NOARP;
-	dev->features = NETIF_F_NO_CSUM;
+	dev->features = NETIF_F_HW_CSUM;
 }
 
 struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf)
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index e023379..165a4c7 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -1060,20 +1060,7 @@ static struct platform_driver flexcan_driver = {
 	.remove = __devexit_p(flexcan_remove),
 };
 
-static int __init flexcan_init(void)
-{
-	pr_info("%s netdevice driver\n", DRV_NAME);
-	return platform_driver_register(&flexcan_driver);
-}
-
-static void __exit flexcan_exit(void)
-{
-	platform_driver_unregister(&flexcan_driver);
-	pr_info("%s: driver removed\n", DRV_NAME);
-}
-
-module_init(flexcan_init);
-module_exit(flexcan_exit);
+module_platform_driver(flexcan_driver);
 
 MODULE_AUTHOR("Sascha Hauer <kernel@pengutronix.de>, "
 	      "Marc Kleine-Budde <kernel@pengutronix.de>");
diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c
index 32778d5..08c893c 100644
--- a/drivers/net/can/janz-ican3.c
+++ b/drivers/net/can/janz-ican3.c
@@ -1803,20 +1803,9 @@ static struct platform_driver ican3_driver = {
 	.remove		= __devexit_p(ican3_remove),
 };
 
-static int __init ican3_init(void)
-{
-	return platform_driver_register(&ican3_driver);
-}
-
-static void __exit ican3_exit(void)
-{
-	platform_driver_unregister(&ican3_driver);
-}
+module_platform_driver(ican3_driver);
 
 MODULE_AUTHOR("Ira W. Snyder <iws@ovro.caltech.edu>");
 MODULE_DESCRIPTION("Janz MODULbus VMOD-ICAN3 Driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:janz-ican3");
-
-module_init(ican3_init);
-module_exit(ican3_exit);
diff --git a/drivers/net/can/mscan/mpc5xxx_can.c b/drivers/net/can/mscan/mpc5xxx_can.c
index 5fedc33..5caa572 100644
--- a/drivers/net/can/mscan/mpc5xxx_can.c
+++ b/drivers/net/can/mscan/mpc5xxx_can.c
@@ -411,17 +411,7 @@ static struct platform_driver mpc5xxx_can_driver = {
 #endif
 };
 
-static int __init mpc5xxx_can_init(void)
-{
-	return platform_driver_register(&mpc5xxx_can_driver);
-}
-module_init(mpc5xxx_can_init);
-
-static void __exit mpc5xxx_can_exit(void)
-{
-	platform_driver_unregister(&mpc5xxx_can_driver);
-};
-module_exit(mpc5xxx_can_exit);
+module_platform_driver(mpc5xxx_can_driver);
 
 MODULE_AUTHOR("Wolfgang Grandegger <wg@grandegger.com>");
 MODULE_DESCRIPTION("Freescale MPC5xxx CAN driver");
diff --git a/drivers/net/can/mscan/mscan.c b/drivers/net/can/mscan/mscan.c
index ec4a311..1c82dd8 100644
--- a/drivers/net/can/mscan/mscan.c
+++ b/drivers/net/can/mscan/mscan.c
@@ -581,7 +581,10 @@ static int mscan_open(struct net_device *dev)
 
 	priv->open_time = jiffies;
 
-	clrbits8(&regs->canctl1, MSCAN_LISTEN);
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+		setbits8(&regs->canctl1, MSCAN_LISTEN);
+	else
+		clrbits8(&regs->canctl1, MSCAN_LISTEN);
 
 	ret = mscan_start(dev);
 	if (ret)
@@ -690,7 +693,8 @@ struct net_device *alloc_mscandev(void)
 	priv->can.bittiming_const = &mscan_bittiming_const;
 	priv->can.do_set_bittiming = mscan_do_set_bittiming;
 	priv->can.do_set_mode = mscan_do_set_mode;
-	priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES;
+	priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES |
+		CAN_CTRLMODE_LISTENONLY;
 
 	for (i = 0; i < TX_QUEUE_SIZE; i++) {
 		priv->tx_queue[i].id = i;
diff --git a/drivers/net/can/sja1000/Kconfig b/drivers/net/can/sja1000/Kconfig
index fe9e64d..36e9d59 100644
--- a/drivers/net/can/sja1000/Kconfig
+++ b/drivers/net/can/sja1000/Kconfig
@@ -6,7 +6,6 @@ if CAN_SJA1000
 
 config CAN_SJA1000_ISA
 	tristate "ISA Bus based legacy SJA1000 driver"
-	depends on ISA
 	---help---
 	  This driver adds legacy support for SJA1000 chips connected to
 	  the ISA bus using I/O port, memory mapped or indirect access.
diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c
index 905bce0..2c7f503 100644
--- a/drivers/net/can/sja1000/peak_pci.c
+++ b/drivers/net/can/sja1000/peak_pci.c
@@ -20,7 +20,6 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/version.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/netdevice.h>
diff --git a/drivers/net/can/sja1000/sja1000_isa.c b/drivers/net/can/sja1000/sja1000_isa.c
index 496223e..90c5c2d 100644
--- a/drivers/net/can/sja1000/sja1000_isa.c
+++ b/drivers/net/can/sja1000/sja1000_isa.c
@@ -17,7 +17,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/isa.h>
+#include <linux/platform_device.h>
 #include <linux/interrupt.h>
 #include <linux/netdevice.h>
 #include <linux/delay.h>
@@ -44,9 +44,9 @@ static unsigned long port[MAXDEV];
 static unsigned long mem[MAXDEV];
 static int __devinitdata irq[MAXDEV];
 static int __devinitdata clk[MAXDEV];
-static char __devinitdata cdr[MAXDEV] = {[0 ... (MAXDEV - 1)] = -1};
-static char __devinitdata ocr[MAXDEV] = {[0 ... (MAXDEV - 1)] = -1};
-static char __devinitdata indirect[MAXDEV] = {[0 ... (MAXDEV - 1)] = -1};
+static unsigned char __devinitdata cdr[MAXDEV] = {[0 ... (MAXDEV - 1)] = 0xff};
+static unsigned char __devinitdata ocr[MAXDEV] = {[0 ... (MAXDEV - 1)] = 0xff};
+static int __devinitdata indirect[MAXDEV] = {[0 ... (MAXDEV - 1)] = -1};
 
 module_param_array(port, ulong, NULL, S_IRUGO);
 MODULE_PARM_DESC(port, "I/O port number");
@@ -54,7 +54,7 @@ MODULE_PARM_DESC(port, "I/O port number");
 module_param_array(mem, ulong, NULL, S_IRUGO);
 MODULE_PARM_DESC(mem, "I/O memory address");
 
-module_param_array(indirect, byte, NULL, S_IRUGO);
+module_param_array(indirect, int, NULL, S_IRUGO);
 MODULE_PARM_DESC(indirect, "Indirect access via address and data port");
 
 module_param_array(irq, int, NULL, S_IRUGO);
@@ -75,6 +75,8 @@ MODULE_PARM_DESC(ocr, "Output control register "
 #define SJA1000_IOSIZE          0x20
 #define SJA1000_IOSIZE_INDIRECT 0x02
 
+static struct platform_device *sja1000_isa_devs[MAXDEV];
+
 static u8 sja1000_isa_mem_read_reg(const struct sja1000_priv *priv, int reg)
 {
 	return readb(priv->reg_base + reg);
@@ -115,26 +117,18 @@ static void sja1000_isa_port_write_reg_indirect(const struct sja1000_priv *priv,
 	outb(val, base + 1);
 }
 
-static int __devinit sja1000_isa_match(struct device *pdev, unsigned int idx)
-{
-	if (port[idx] || mem[idx]) {
-		if (irq[idx])
-			return 1;
-	} else if (idx)
-		return 0;
-
-	dev_err(pdev, "insufficient parameters supplied\n");
-	return 0;
-}
-
-static int __devinit sja1000_isa_probe(struct device *pdev, unsigned int idx)
+static int __devinit sja1000_isa_probe(struct platform_device *pdev)
 {
 	struct net_device *dev;
 	struct sja1000_priv *priv;
 	void __iomem *base = NULL;
 	int iosize = SJA1000_IOSIZE;
+	int idx = pdev->id;
 	int err;
 
+	dev_dbg(&pdev->dev, "probing idx=%d: port=%#lx, mem=%#lx, irq=%d\n",
+		idx, port[idx], mem[idx], irq[idx]);
+
 	if (mem[idx]) {
 		if (!request_mem_region(mem[idx], iosize, DRV_NAME)) {
 			err = -EBUSY;
@@ -189,31 +183,31 @@ static int __devinit sja1000_isa_probe(struct device *pdev, unsigned int idx)
 	else
 		priv->can.clock.freq = CLK_DEFAULT / 2;
 
-	if (ocr[idx] != -1)
-		priv->ocr = ocr[idx] & 0xff;
-	else if (ocr[0] != -1)
-		priv->ocr = ocr[0] & 0xff;
+	if (ocr[idx] != 0xff)
+		priv->ocr = ocr[idx];
+	else if (ocr[0] != 0xff)
+		priv->ocr = ocr[0];
 	else
 		priv->ocr = OCR_DEFAULT;
 
-	if (cdr[idx] != -1)
-		priv->cdr = cdr[idx] & 0xff;
-	else if (cdr[0] != -1)
-		priv->cdr = cdr[0] & 0xff;
+	if (cdr[idx] != 0xff)
+		priv->cdr = cdr[idx];
+	else if (cdr[0] != 0xff)
+		priv->cdr = cdr[0];
 	else
 		priv->cdr = CDR_DEFAULT;
 
-	dev_set_drvdata(pdev, dev);
-	SET_NETDEV_DEV(dev, pdev);
+	dev_set_drvdata(&pdev->dev, dev);
+	SET_NETDEV_DEV(dev, &pdev->dev);
 
 	err = register_sja1000dev(dev);
 	if (err) {
-		dev_err(pdev, "registering %s failed (err=%d)\n",
+		dev_err(&pdev->dev, "registering %s failed (err=%d)\n",
 			DRV_NAME, err);
 		goto exit_unmap;
 	}
 
-	dev_info(pdev, "%s device registered (reg_base=0x%p, irq=%d)\n",
+	dev_info(&pdev->dev, "%s device registered (reg_base=0x%p, irq=%d)\n",
 		 DRV_NAME, priv->reg_base, dev->irq);
 	return 0;
 
@@ -229,13 +223,14 @@ static int __devinit sja1000_isa_probe(struct device *pdev, unsigned int idx)
 	return err;
 }
 
-static int __devexit sja1000_isa_remove(struct device *pdev, unsigned int idx)
+static int __devexit sja1000_isa_remove(struct platform_device *pdev)
 {
-	struct net_device *dev = dev_get_drvdata(pdev);
+	struct net_device *dev = dev_get_drvdata(&pdev->dev);
 	struct sja1000_priv *priv = netdev_priv(dev);
+	int idx = pdev->id;
 
 	unregister_sja1000dev(dev);
-	dev_set_drvdata(pdev, NULL);
+	dev_set_drvdata(&pdev->dev, NULL);
 
 	if (mem[idx]) {
 		iounmap(priv->reg_base);
@@ -251,29 +246,70 @@ static int __devexit sja1000_isa_remove(struct device *pdev, unsigned int idx)
 	return 0;
 }
 
-static struct isa_driver sja1000_isa_driver = {
-	.match = sja1000_isa_match,
+static struct platform_driver sja1000_isa_driver = {
 	.probe = sja1000_isa_probe,
 	.remove = __devexit_p(sja1000_isa_remove),
 	.driver = {
 		.name = DRV_NAME,
+		.owner = THIS_MODULE,
 	},
 };
 
 static int __init sja1000_isa_init(void)
 {
-	int err = isa_register_driver(&sja1000_isa_driver, MAXDEV);
+	int idx, err;
+
+	for (idx = 0; idx < MAXDEV; idx++) {
+		if ((port[idx] || mem[idx]) && irq[idx]) {
+			sja1000_isa_devs[idx] =
+				platform_device_alloc(DRV_NAME, idx);
+			if (!sja1000_isa_devs[idx]) {
+				err = -ENOMEM;
+				goto exit_free_devices;
+			}
+			err = platform_device_add(sja1000_isa_devs[idx]);
+			if (err) {
+				platform_device_put(sja1000_isa_devs[idx]);
+				goto exit_free_devices;
+			}
+			pr_debug("%s: platform device %d: port=%#lx, mem=%#lx, "
+				 "irq=%d\n",
+				 DRV_NAME, idx, port[idx], mem[idx], irq[idx]);
+		} else if (idx == 0 || port[idx] || mem[idx]) {
+				pr_err("%s: insufficient parameters supplied\n",
+				       DRV_NAME);
+				err = -EINVAL;
+				goto exit_free_devices;
+		}
+	}
+
+	err = platform_driver_register(&sja1000_isa_driver);
+	if (err)
+		goto exit_free_devices;
+
+	pr_info("Legacy %s driver for max. %d devices registered\n",
+		DRV_NAME, MAXDEV);
+
+	return 0;
+
+exit_free_devices:
+	while (--idx >= 0) {
+		if (sja1000_isa_devs[idx])
+			platform_device_unregister(sja1000_isa_devs[idx]);
+	}
 
-	if (!err)
-		printk(KERN_INFO
-		       "Legacy %s driver for max. %d devices registered\n",
-		       DRV_NAME, MAXDEV);
 	return err;
 }
 
 static void __exit sja1000_isa_exit(void)
 {
-	isa_unregister_driver(&sja1000_isa_driver);
+	int idx;
+
+	platform_driver_unregister(&sja1000_isa_driver);
+	for (idx = 0; idx < MAXDEV; idx++) {
+		if (sja1000_isa_devs[idx])
+			platform_device_unregister(sja1000_isa_devs[idx]);
+	}
 }
 
 module_init(sja1000_isa_init);
diff --git a/drivers/net/can/sja1000/sja1000_of_platform.c b/drivers/net/can/sja1000/sja1000_of_platform.c
index c3dd9d0..f2683eb 100644
--- a/drivers/net/can/sja1000/sja1000_of_platform.c
+++ b/drivers/net/can/sja1000/sja1000_of_platform.c
@@ -220,14 +220,4 @@ static struct platform_driver sja1000_ofp_driver = {
 	.remove = __devexit_p(sja1000_ofp_remove),
 };
 
-static int __init sja1000_ofp_init(void)
-{
-	return platform_driver_register(&sja1000_ofp_driver);
-}
-module_init(sja1000_ofp_init);
-
-static void __exit sja1000_ofp_exit(void)
-{
-	return platform_driver_unregister(&sja1000_ofp_driver);
-};
-module_exit(sja1000_ofp_exit);
+module_platform_driver(sja1000_ofp_driver);
diff --git a/drivers/net/can/sja1000/sja1000_platform.c b/drivers/net/can/sja1000/sja1000_platform.c
index d9fadc4..4f50145 100644
--- a/drivers/net/can/sja1000/sja1000_platform.c
+++ b/drivers/net/can/sja1000/sja1000_platform.c
@@ -185,15 +185,4 @@ static struct platform_driver sp_driver = {
 	},
 };
 
-static int __init sp_init(void)
-{
-	return platform_driver_register(&sp_driver);
-}
-
-static void __exit sp_exit(void)
-{
-	platform_driver_unregister(&sp_driver);
-}
-
-module_init(sp_init);
-module_exit(sp_exit);
+module_platform_driver(sp_driver);
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index a979b00..3f1ebcc 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -387,7 +387,7 @@ static void slc_setup(struct net_device *dev)
 
 	/* New-style flags. */
 	dev->flags		= IFF_NOARP;
-	dev->features           = NETIF_F_NO_CSUM;
+	dev->features           = NETIF_F_HW_CSUM;
 }
 
 /******************************************
diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c
index 09a8b86..a7c77c74 100644
--- a/drivers/net/can/softing/softing_main.c
+++ b/drivers/net/can/softing/softing_main.c
@@ -874,21 +874,9 @@ static struct platform_driver softing_driver = {
 	.remove = __devexit_p(softing_pdev_remove),
 };
 
-MODULE_ALIAS("platform:softing");
-
-static int __init softing_start(void)
-{
-	return platform_driver_register(&softing_driver);
-}
-
-static void __exit softing_stop(void)
-{
-	platform_driver_unregister(&softing_driver);
-}
-
-module_init(softing_start);
-module_exit(softing_stop);
+module_platform_driver(softing_driver);
 
+MODULE_ALIAS("platform:softing");
 MODULE_DESCRIPTION("Softing DPRAM CAN driver");
 MODULE_AUTHOR("Kurt Van Dijck <kurt.van.dijck@eia.be>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index 2adc294..df809e3 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -1037,20 +1037,7 @@ static struct platform_driver ti_hecc_driver = {
 	.resume = ti_hecc_resume,
 };
 
-static int __init ti_hecc_init_driver(void)
-{
-	printk(KERN_INFO DRV_DESC "\n");
-	return platform_driver_register(&ti_hecc_driver);
-}
-
-static void __exit ti_hecc_exit_driver(void)
-{
-	printk(KERN_INFO DRV_DESC " unloaded\n");
-	platform_driver_unregister(&ti_hecc_driver);
-}
-
-module_exit(ti_hecc_exit_driver);
-module_init(ti_hecc_init_driver);
+module_platform_driver(ti_hecc_driver);
 
 MODULE_AUTHOR("Anant Gole <anantgole@ti.com>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
new file mode 100644
index 0000000..dd151d5
--- /dev/null
+++ b/drivers/net/dsa/Kconfig
@@ -0,0 +1,36 @@
+menu "Distributed Switch Architecture drivers"
+	depends on NET_DSA
+
+config NET_DSA_MV88E6XXX
+	tristate
+	default n
+
+config NET_DSA_MV88E6060
+	tristate "Marvell 88E6060 ethernet switch chip support"
+	select NET_DSA_TAG_TRAILER
+	---help---
+	  This enables support for the Marvell 88E6060 ethernet switch
+	  chip.
+
+config NET_DSA_MV88E6XXX_NEED_PPU
+	bool
+	default n
+
+config NET_DSA_MV88E6131
+	tristate "Marvell 88E6085/6095/6095F/6131 ethernet switch chip support"
+	select NET_DSA_MV88E6XXX
+	select NET_DSA_MV88E6XXX_NEED_PPU
+	select NET_DSA_TAG_DSA
+	---help---
+	  This enables support for the Marvell 88E6085/6095/6095F/6131
+	  ethernet switch chips.
+
+config NET_DSA_MV88E6123_61_65
+	tristate "Marvell 88E6123/6161/6165 ethernet switch chip support"
+	select NET_DSA_MV88E6XXX
+	select NET_DSA_TAG_EDSA
+	---help---
+	  This enables support for the Marvell 88E6123/6161/6165
+	  ethernet switch chips.
+
+endmenu
diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile
new file mode 100644
index 0000000..f3bda05
--- /dev/null
+++ b/drivers/net/dsa/Makefile
@@ -0,0 +1,9 @@
+obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o
+obj-$(CONFIG_NET_DSA_MV88E6XXX) += mv88e6xxx_drv.o
+mv88e6xxx_drv-y += mv88e6xxx.o
+ifdef CONFIG_NET_DSA_MV88E6123_61_65
+mv88e6xxx_drv-y += mv88e6123_61_65.o
+endif
+ifdef CONFIG_NET_DSA_MV88E6131
+mv88e6xxx_drv-y += mv88e6131.o
+endif
diff --git a/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c
index 8f4ff5a..7fc4e81 100644
--- a/net/dsa/mv88e6060.c
+++ b/drivers/net/dsa/mv88e6060.c
@@ -11,7 +11,7 @@
 #include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/phy.h>
-#include "dsa_priv.h"
+#include <net/dsa.h>
 
 #define REG_PORT(p)		(8 + (p))
 #define REG_GLOBAL		0x0f
@@ -286,3 +286,8 @@ static void __exit mv88e6060_cleanup(void)
 	unregister_switch_driver(&mv88e6060_switch_driver);
 }
 module_exit(mv88e6060_cleanup);
+
+MODULE_AUTHOR("Lennert Buytenhek <buytenh@wantstofly.org>");
+MODULE_DESCRIPTION("Driver for Marvell 88E6060 ethernet switch chip");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mv88e6060");
diff --git a/net/dsa/mv88e6123_61_65.c b/drivers/net/dsa/mv88e6123_61_65.c
index 52faaa2..c0a458f 100644
--- a/net/dsa/mv88e6123_61_65.c
+++ b/drivers/net/dsa/mv88e6123_61_65.c
@@ -11,7 +11,7 @@
 #include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/phy.h>
-#include "dsa_priv.h"
+#include <net/dsa.h>
 #include "mv88e6xxx.h"
 
 static char *mv88e6123_61_65_probe(struct mii_bus *bus, int sw_addr)
@@ -419,7 +419,7 @@ static int mv88e6123_61_65_get_sset_count(struct dsa_switch *ds)
 	return ARRAY_SIZE(mv88e6123_61_65_hw_stats);
 }
 
-static struct dsa_switch_driver mv88e6123_61_65_switch_driver = {
+struct dsa_switch_driver mv88e6123_61_65_switch_driver = {
 	.tag_protocol		= cpu_to_be16(ETH_P_EDSA),
 	.priv_size		= sizeof(struct mv88e6xxx_priv_state),
 	.probe			= mv88e6123_61_65_probe,
@@ -433,15 +433,6 @@ static struct dsa_switch_driver mv88e6123_61_65_switch_driver = {
 	.get_sset_count		= mv88e6123_61_65_get_sset_count,
 };
 
-static int __init mv88e6123_61_65_init(void)
-{
-	register_switch_driver(&mv88e6123_61_65_switch_driver);
-	return 0;
-}
-module_init(mv88e6123_61_65_init);
-
-static void __exit mv88e6123_61_65_cleanup(void)
-{
-	unregister_switch_driver(&mv88e6123_61_65_switch_driver);
-}
-module_exit(mv88e6123_61_65_cleanup);
+MODULE_ALIAS("platform:mv88e6123");
+MODULE_ALIAS("platform:mv88e6161");
+MODULE_ALIAS("platform:mv88e6165");
diff --git a/net/dsa/mv88e6131.c b/drivers/net/dsa/mv88e6131.c
index 9bd1061..e0eb6824 100644
--- a/net/dsa/mv88e6131.c
+++ b/drivers/net/dsa/mv88e6131.c
@@ -11,7 +11,7 @@
 #include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/phy.h>
-#include "dsa_priv.h"
+#include <net/dsa.h>
 #include "mv88e6xxx.h"
 
 /*
@@ -415,7 +415,7 @@ static int mv88e6131_get_sset_count(struct dsa_switch *ds)
 	return ARRAY_SIZE(mv88e6131_hw_stats);
 }
 
-static struct dsa_switch_driver mv88e6131_switch_driver = {
+struct dsa_switch_driver mv88e6131_switch_driver = {
 	.tag_protocol		= cpu_to_be16(ETH_P_DSA),
 	.priv_size		= sizeof(struct mv88e6xxx_priv_state),
 	.probe			= mv88e6131_probe,
@@ -429,15 +429,7 @@ static struct dsa_switch_driver mv88e6131_switch_driver = {
 	.get_sset_count		= mv88e6131_get_sset_count,
 };
 
-static int __init mv88e6131_init(void)
-{
-	register_switch_driver(&mv88e6131_switch_driver);
-	return 0;
-}
-module_init(mv88e6131_init);
-
-static void __exit mv88e6131_cleanup(void)
-{
-	unregister_switch_driver(&mv88e6131_switch_driver);
-}
-module_exit(mv88e6131_cleanup);
+MODULE_ALIAS("platform:mv88e6085");
+MODULE_ALIAS("platform:mv88e6095");
+MODULE_ALIAS("platform:mv88e6095f");
+MODULE_ALIAS("platform:mv88e6131");
diff --git a/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index efe661a..5467c04 100644
--- a/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -11,7 +11,7 @@
 #include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/phy.h>
-#include "dsa_priv.h"
+#include <net/dsa.h>
 #include "mv88e6xxx.h"
 
 /*
@@ -520,3 +520,30 @@ void mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds,
 
 	mutex_unlock(&ps->stats_mutex);
 }
+
+static int __init mv88e6xxx_init(void)
+{
+#if IS_ENABLED(CONFIG_NET_DSA_MV88E6131)
+	register_switch_driver(&mv88e6131_switch_driver);
+#endif
+#if IS_ENABLED(CONFIG_NET_DSA_MV88E6123_61_65)
+	register_switch_driver(&mv88e6123_61_65_switch_driver);
+#endif
+	return 0;
+}
+module_init(mv88e6xxx_init);
+
+static void __exit mv88e6xxx_cleanup(void)
+{
+#if IS_ENABLED(CONFIG_NET_DSA_MV88E6123_61_65)
+	unregister_switch_driver(&mv88e6123_61_65_switch_driver);
+#endif
+#if IS_ENABLED(CONFIG_NET_DSA_MV88E6131)
+	unregister_switch_driver(&mv88e6131_switch_driver);
+#endif
+}
+module_exit(mv88e6xxx_cleanup);
+
+MODULE_AUTHOR("Lennert Buytenhek <buytenh@wantstofly.org>");
+MODULE_DESCRIPTION("Driver for Marvell 88E6XXX ethernet switch chips");
+MODULE_LICENSE("GPL");
diff --git a/net/dsa/mv88e6xxx.h b/drivers/net/dsa/mv88e6xxx.h
index 61156ca2..fc2cd7b 100644
--- a/net/dsa/mv88e6xxx.h
+++ b/drivers/net/dsa/mv88e6xxx.h
@@ -71,6 +71,9 @@ void mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds,
 				 int nr_stats, struct mv88e6xxx_hw_stat *stats,
 				 int port, uint64_t *data);
 
+extern struct dsa_switch_driver mv88e6131_switch_driver;
+extern struct dsa_switch_driver mv88e6123_61_65_switch_driver;
+
 #define REG_READ(addr, reg)						\
 	({								\
 		int __ret;						\
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index a7c5e88..087648e 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -134,7 +134,7 @@ static void dummy_setup(struct net_device *dev)
 	dev->flags |= IFF_NOARP;
 	dev->flags &= ~IFF_MULTICAST;
 	dev->features	|= NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_TSO;
-	dev->features	|= NETIF_F_NO_CSUM | NETIF_F_HIGHDMA | NETIF_F_LLTX;
+	dev->features	|= NETIF_F_HW_CSUM | NETIF_F_HIGHDMA | NETIF_F_LLTX;
 	random_ether_addr(dev->dev_addr);
 }
 
diff --git a/drivers/net/ethernet/3com/3c589_cs.c b/drivers/net/ethernet/3com/3c589_cs.c
index 972f80e..da410f0 100644
--- a/drivers/net/ethernet/3com/3c589_cs.c
+++ b/drivers/net/ethernet/3com/3c589_cs.c
@@ -468,9 +468,10 @@ static void tc589_reset(struct net_device *dev)
 static void netdev_get_drvinfo(struct net_device *dev,
 			       struct ethtool_drvinfo *info)
 {
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	sprintf(info->bus_info, "PCMCIA 0x%lx", dev->base_addr);
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	snprintf(info->bus_info, sizeof(info->bus_info),
+		"PCMCIA 0x%lx", dev->base_addr);
 }
 
 static const struct ethtool_ops netdev_ethtool_ops = {
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index b42c06b..8153a3e 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -2929,15 +2929,17 @@ static void vortex_get_drvinfo(struct net_device *dev,
 {
 	struct vortex_private *vp = netdev_priv(dev);
 
-	strcpy(info->driver, DRV_NAME);
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
 	if (VORTEX_PCI(vp)) {
-		strcpy(info->bus_info, pci_name(VORTEX_PCI(vp)));
+		strlcpy(info->bus_info, pci_name(VORTEX_PCI(vp)),
+			sizeof(info->bus_info));
 	} else {
 		if (VORTEX_EISA(vp))
-			strcpy(info->bus_info, dev_name(vp->gendev));
+			strlcpy(info->bus_info, dev_name(vp->gendev),
+				sizeof(info->bus_info));
 		else
-			sprintf(info->bus_info, "EISA 0x%lx %d",
-					dev->base_addr, dev->irq);
+			snprintf(info->bus_info, sizeof(info->bus_info),
+				"EISA 0x%lx %d", dev->base_addr, dev->irq);
 	}
 }
 
diff --git a/drivers/net/ethernet/3com/typhoon.c b/drivers/net/ethernet/3com/typhoon.c
index 20ea075..6d6bc75 100644
--- a/drivers/net/ethernet/3com/typhoon.c
+++ b/drivers/net/ethernet/3com/typhoon.c
@@ -988,21 +988,23 @@ typhoon_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 
 	smp_rmb();
 	if(tp->card_state == Sleeping) {
-		strcpy(info->fw_version, "Sleep image");
+		strlcpy(info->fw_version, "Sleep image",
+			sizeof(info->fw_version));
 	} else {
 		INIT_COMMAND_WITH_RESPONSE(&xp_cmd, TYPHOON_CMD_READ_VERSIONS);
 		if(typhoon_issue_command(tp, 1, &xp_cmd, 3, xp_resp) < 0) {
-			strcpy(info->fw_version, "Unknown runtime");
+			strlcpy(info->fw_version, "Unknown runtime",
+				sizeof(info->fw_version));
 		} else {
 			u32 sleep_ver = le32_to_cpu(xp_resp[0].parm2);
-			snprintf(info->fw_version, 32, "%02x.%03x.%03x",
-				 sleep_ver >> 24, (sleep_ver >> 12) & 0xfff,
-				 sleep_ver & 0xfff);
+			snprintf(info->fw_version, sizeof(info->fw_version),
+				"%02x.%03x.%03x", sleep_ver >> 24,
+				(sleep_ver >> 12) & 0xfff, sleep_ver & 0xfff);
 		}
 	}
 
-	strcpy(info->driver, KBUILD_MODNAME);
-	strcpy(info->bus_info, pci_name(pci_dev));
+	strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
+	strlcpy(info->bus_info, pci_name(pci_dev), sizeof(info->bus_info));
 }
 
 static int
diff --git a/drivers/net/ethernet/8390/8390.h b/drivers/net/ethernet/8390/8390.h
index 58a12e4..ef325ff 100644
--- a/drivers/net/ethernet/8390/8390.h
+++ b/drivers/net/ethernet/8390/8390.h
@@ -14,8 +14,6 @@
 
 #define TX_PAGES 12	/* Two Tx slots */
 
-#define ETHER_ADDR_LEN 6
-
 /* The 8390 specific per-packet-header format. */
 struct e8390_pkt_hdr {
   unsigned char status; /* status */
diff --git a/drivers/net/ethernet/8390/apne.c b/drivers/net/ethernet/8390/apne.c
index 5477373..3ad5d2f 100644
--- a/drivers/net/ethernet/8390/apne.c
+++ b/drivers/net/ethernet/8390/apne.c
@@ -318,7 +318,7 @@ static int __init apne_probe1(struct net_device *dev, int ioaddr)
     i = request_irq(dev->irq, apne_interrupt, IRQF_SHARED, DRV_NAME, dev);
     if (i) return i;
 
-    for(i = 0; i < ETHER_ADDR_LEN; i++)
+    for (i = 0; i < ETH_ALEN; i++)
 	dev->dev_addr[i] = SA_prom[i];
 
     printk(" %pM\n", dev->dev_addr);
diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c
index e9f8432..9e8ba4f 100644
--- a/drivers/net/ethernet/8390/ax88796.c
+++ b/drivers/net/ethernet/8390/ax88796.c
@@ -735,15 +735,14 @@ static int ax_init_dev(struct net_device *dev)
 	if (ax->plat->flags & AXFLG_MAC_FROMDEV) {
 		ei_outb(E8390_NODMA + E8390_PAGE1 + E8390_STOP,
 			ei_local->mem + E8390_CMD); /* 0x61 */
-		for (i = 0; i < ETHER_ADDR_LEN; i++)
+		for (i = 0; i < ETH_ALEN; i++)
 			dev->dev_addr[i] =
 				ei_inb(ioaddr + EN1_PHYS_SHIFT(i));
 	}
 
 	if ((ax->plat->flags & AXFLG_MAC_FROMPLATFORM) &&
 	    ax->plat->mac_addr)
-		memcpy(dev->dev_addr, ax->plat->mac_addr,
-		       ETHER_ADDR_LEN);
+		memcpy(dev->dev_addr, ax->plat->mac_addr, ETH_ALEN);
 
 	ax_reset_8390(dev);
 
@@ -991,18 +990,7 @@ static struct platform_driver axdrv = {
 	.resume		= ax_resume,
 };
 
-static int __init axdrv_init(void)
-{
-	return platform_driver_register(&axdrv);
-}
-
-static void __exit axdrv_exit(void)
-{
-	platform_driver_unregister(&axdrv);
-}
-
-module_init(axdrv_init);
-module_exit(axdrv_exit);
+module_platform_driver(axdrv);
 
 MODULE_DESCRIPTION("AX88796 10/100 Ethernet platform driver");
 MODULE_AUTHOR("Ben Dooks, <ben@simtec.co.uk>");
diff --git a/drivers/net/ethernet/8390/es3210.c b/drivers/net/ethernet/8390/es3210.c
index 7a09575..6428f9e 100644
--- a/drivers/net/ethernet/8390/es3210.c
+++ b/drivers/net/ethernet/8390/es3210.c
@@ -195,7 +195,7 @@ static int __init es_probe1(struct net_device *dev, int ioaddr)
 		goto out;
 	}
 
-	for (i = 0; i < ETHER_ADDR_LEN ; i++)
+	for (i = 0; i < ETH_ALEN ; i++)
 		dev->dev_addr[i] = inb(ioaddr + ES_SA_PROM + i);
 
 /*	Check the Racal vendor ID as well. */
diff --git a/drivers/net/ethernet/8390/hp-plus.c b/drivers/net/ethernet/8390/hp-plus.c
index eeac843..d42938b 100644
--- a/drivers/net/ethernet/8390/hp-plus.c
+++ b/drivers/net/ethernet/8390/hp-plus.c
@@ -202,7 +202,7 @@ static int __init hpp_probe1(struct net_device *dev, int ioaddr)
 	/* Retrieve and checksum the station address. */
 	outw(MAC_Page, ioaddr + HP_PAGING);
 
-	for(i = 0; i < ETHER_ADDR_LEN; i++) {
+	for(i = 0; i < ETH_ALEN; i++) {
 		unsigned char inval = inb(ioaddr + 8 + i);
 		dev->dev_addr[i] = inval;
 		checksum += inval;
diff --git a/drivers/net/ethernet/8390/hp.c b/drivers/net/ethernet/8390/hp.c
index 18564d4..113f1e0 100644
--- a/drivers/net/ethernet/8390/hp.c
+++ b/drivers/net/ethernet/8390/hp.c
@@ -156,7 +156,7 @@ static int __init hp_probe1(struct net_device *dev, int ioaddr)
 
 	printk("%s: %s (ID %02x) at %#3x,", dev->name, name, board_id, ioaddr);
 
-	for(i = 0; i < ETHER_ADDR_LEN; i++)
+	for(i = 0; i < ETH_ALEN; i++)
 		dev->dev_addr[i] = inb(ioaddr + i);
 
 	printk(" %pM", dev->dev_addr);
diff --git a/drivers/net/ethernet/8390/hydra.c b/drivers/net/ethernet/8390/hydra.c
index 3dac937..5370c88 100644
--- a/drivers/net/ethernet/8390/hydra.c
+++ b/drivers/net/ethernet/8390/hydra.c
@@ -129,7 +129,7 @@ static int __devinit hydra_init(struct zorro_dev *z)
     if (!dev)
 	return -ENOMEM;
 
-    for(j = 0; j < ETHER_ADDR_LEN; j++)
+    for (j = 0; j < ETH_ALEN; j++)
 	dev->dev_addr[j] = *((u8 *)(board + HYDRA_ADDRPROM + 2*j));
 
     /* We must set the 8390 for word mode. */
diff --git a/drivers/net/ethernet/8390/lne390.c b/drivers/net/ethernet/8390/lne390.c
index f9888d2..69490ae 100644
--- a/drivers/net/ethernet/8390/lne390.c
+++ b/drivers/net/ethernet/8390/lne390.c
@@ -191,14 +191,14 @@ static int __init lne390_probe1(struct net_device *dev, int ioaddr)
 		|| inb(ioaddr + LNE390_SA_PROM + 1) != LNE390_ADDR1
 		|| inb(ioaddr + LNE390_SA_PROM + 2) != LNE390_ADDR2 ) {
 		printk("lne390.c: card not found");
-		for(i = 0; i < ETHER_ADDR_LEN; i++)
+		for (i = 0; i < ETH_ALEN; i++)
 			printk(" %02x", inb(ioaddr + LNE390_SA_PROM + i));
 		printk(" (invalid prefix).\n");
 		return -ENODEV;
 	}
 #endif
 
-	for(i = 0; i < ETHER_ADDR_LEN; i++)
+	for (i = 0; i < ETH_ALEN; i++)
 		dev->dev_addr[i] = inb(ioaddr + LNE390_SA_PROM + i);
 	printk("lne390.c: LNE390%X in EISA slot %d, address %pM.\n",
 	       0xa+revision, ioaddr/0x1000, dev->dev_addr);
diff --git a/drivers/net/ethernet/8390/ne-h8300.c b/drivers/net/ethernet/8390/ne-h8300.c
index cd36a6a..9b9c77d 100644
--- a/drivers/net/ethernet/8390/ne-h8300.c
+++ b/drivers/net/ethernet/8390/ne-h8300.c
@@ -312,7 +312,7 @@ static int __init ne_probe1(struct net_device *dev, int ioaddr)
 
 	dev->base_addr = ioaddr;
 
-	for(i = 0; i < ETHER_ADDR_LEN; i++)
+	for (i = 0; i < ETH_ALEN; i++)
 		dev->dev_addr[i] = SA_prom[i];
 	printk(" %pM\n", dev->dev_addr);
 
diff --git a/drivers/net/ethernet/8390/ne.c b/drivers/net/ethernet/8390/ne.c
index 1063093..f92ea2a 100644
--- a/drivers/net/ethernet/8390/ne.c
+++ b/drivers/net/ethernet/8390/ne.c
@@ -503,12 +503,12 @@ static int __init ne_probe1(struct net_device *dev, unsigned long ioaddr)
 #ifdef CONFIG_PLAT_MAPPI
 	outb_p(E8390_NODMA + E8390_PAGE1 + E8390_STOP,
 		ioaddr + E8390_CMD); /* 0x61 */
-	for (i = 0 ; i < ETHER_ADDR_LEN ; i++) {
+	for (i = 0; i < ETH_ALEN; i++) {
 		dev->dev_addr[i] = SA_prom[i]
 			= inb_p(ioaddr + EN1_PHYS_SHIFT(i));
 	}
 #else
-	for(i = 0; i < ETHER_ADDR_LEN; i++) {
+	for (i = 0; i < ETH_ALEN; i++) {
 		dev->dev_addr[i] = SA_prom[i];
 	}
 #endif
diff --git a/drivers/net/ethernet/8390/ne2.c b/drivers/net/ethernet/8390/ne2.c
index 70cdc69..922b320 100644
--- a/drivers/net/ethernet/8390/ne2.c
+++ b/drivers/net/ethernet/8390/ne2.c
@@ -460,7 +460,7 @@ static int __init ne2_probe1(struct net_device *dev, int slot)
 
 	dev->base_addr = base_addr;
 
-	for(i = 0; i < ETHER_ADDR_LEN; i++)
+	for (i = 0; i < ETH_ALEN; i++)
 		dev->dev_addr[i] = SA_prom[i];
 
 	printk(" %pM\n", dev->dev_addr);
diff --git a/drivers/net/ethernet/8390/ne2k-pci.c b/drivers/net/ethernet/8390/ne2k-pci.c
index 3992342..3fab04a 100644
--- a/drivers/net/ethernet/8390/ne2k-pci.c
+++ b/drivers/net/ethernet/8390/ne2k-pci.c
@@ -639,9 +639,9 @@ static void ne2k_pci_get_drvinfo(struct net_device *dev,
 	struct ei_device *ei = netdev_priv(dev);
 	struct pci_dev *pci_dev = (struct pci_dev *) ei->priv;
 
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->bus_info, pci_name(pci_dev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(pci_dev), sizeof(info->bus_info));
 }
 
 static const struct ethtool_ops ne2k_pci_ethtool_ops = {
diff --git a/drivers/net/ethernet/8390/ne3210.c b/drivers/net/ethernet/8390/ne3210.c
index 243ed2a..2a3e805 100644
--- a/drivers/net/ethernet/8390/ne3210.c
+++ b/drivers/net/ethernet/8390/ne3210.c
@@ -125,7 +125,7 @@ static int __init ne3210_eisa_probe (struct device *device)
 #endif
 
 	port_index = inb(ioaddr + NE3210_CFG2) >> 6;
-	for(i = 0; i < ETHER_ADDR_LEN; i++)
+	for (i = 0; i < ETH_ALEN; i++)
 		dev->dev_addr[i] = inb(ioaddr + NE3210_SA_PROM + i);
 	printk("ne3210.c: NE3210 in EISA slot %d, media: %s, addr: %pM.\n",
 		edev->slot, ifmap[port_index], dev->dev_addr);
diff --git a/drivers/net/ethernet/8390/stnic.c b/drivers/net/ethernet/8390/stnic.c
index d85f0a8..3b90375 100644
--- a/drivers/net/ethernet/8390/stnic.c
+++ b/drivers/net/ethernet/8390/stnic.c
@@ -114,7 +114,7 @@ static int __init stnic_probe(void)
 #ifdef CONFIG_SH_STANDARD_BIOS
   sh_bios_get_node_addr (stnic_eadr);
 #endif
-  for (i = 0; i < ETHER_ADDR_LEN; i++)
+  for (i = 0; i < ETH_ALEN; i++)
     dev->dev_addr[i] = stnic_eadr[i];
 
   /* Set the base address to point to the NIC, not the "real" base! */
diff --git a/drivers/net/ethernet/8390/zorro8390.c b/drivers/net/ethernet/8390/zorro8390.c
index 3aa9fe9..bcd2732 100644
--- a/drivers/net/ethernet/8390/zorro8390.c
+++ b/drivers/net/ethernet/8390/zorro8390.c
@@ -365,7 +365,7 @@ static int __devinit zorro8390_init(struct net_device *dev,
 	if (i)
 		return i;
 
-	for (i = 0; i < ETHER_ADDR_LEN; i++)
+	for (i = 0; i < ETH_ALEN; i++)
 		dev->dev_addr[i] = SA_prom[i];
 
 	pr_debug("Found ethernet address: %pM\n", dev->dev_addr);
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 597f4d4..3474a61 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -28,6 +28,7 @@ source "drivers/net/ethernet/cadence/Kconfig"
 source "drivers/net/ethernet/adi/Kconfig"
 source "drivers/net/ethernet/broadcom/Kconfig"
 source "drivers/net/ethernet/brocade/Kconfig"
+source "drivers/net/ethernet/calxeda/Kconfig"
 source "drivers/net/ethernet/chelsio/Kconfig"
 source "drivers/net/ethernet/cirrus/Kconfig"
 source "drivers/net/ethernet/cisco/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index be5dde0..cd6d69a 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_NET_ATMEL) += cadence/
 obj-$(CONFIG_NET_BFIN) += adi/
 obj-$(CONFIG_NET_VENDOR_BROADCOM) += broadcom/
 obj-$(CONFIG_NET_VENDOR_BROCADE) += brocade/
+obj-$(CONFIG_NET_CALXEDA_XGMAC) += calxeda/
 obj-$(CONFIG_NET_VENDOR_CHELSIO) += chelsio/
 obj-$(CONFIG_NET_VENDOR_CIRRUS) += cirrus/
 obj-$(CONFIG_NET_VENDOR_CISCO) += cisco/
diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c
index 6d9f691..cb4f38a 100644
--- a/drivers/net/ethernet/adaptec/starfire.c
+++ b/drivers/net/ethernet/adaptec/starfire.c
@@ -607,7 +607,7 @@ static const struct ethtool_ops ethtool_ops;
 
 
 #ifdef VLAN_SUPPORT
-static void netdev_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+static int netdev_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 {
 	struct netdev_private *np = netdev_priv(dev);
 
@@ -617,9 +617,11 @@ static void netdev_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 	set_bit(vid, np->active_vlans);
 	set_rx_mode(dev);
 	spin_unlock(&np->lock);
+
+	return 0;
 }
 
-static void netdev_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+static int netdev_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 {
 	struct netdev_private *np = netdev_priv(dev);
 
@@ -629,6 +631,8 @@ static void netdev_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 	clear_bit(vid, np->active_vlans);
 	set_rx_mode(dev);
 	spin_unlock(&np->lock);
+
+	return 0;
 }
 #endif /* VLAN_SUPPORT */
 
@@ -1842,9 +1846,9 @@ static int check_if_running(struct net_device *dev)
 static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
 	struct netdev_private *np = netdev_priv(dev);
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->bus_info, pci_name(np->pci_dev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
 }
 
 static int get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c
index 442fefa..c885aa9 100644
--- a/drivers/net/ethernet/aeroflex/greth.c
+++ b/drivers/net/ethernet/aeroflex/greth.c
@@ -1623,18 +1623,7 @@ static struct platform_driver greth_of_driver = {
 	.remove = __devexit_p(greth_of_remove),
 };
 
-static int __init greth_init(void)
-{
-	return platform_driver_register(&greth_of_driver);
-}
-
-static void __exit greth_cleanup(void)
-{
-	platform_driver_unregister(&greth_of_driver);
-}
-
-module_init(greth_init);
-module_exit(greth_cleanup);
+module_platform_driver(greth_of_driver);
 
 MODULE_AUTHOR("Aeroflex Gaisler AB.");
 MODULE_DESCRIPTION("Aeroflex Gaisler Ethernet MAC driver");
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c
index a9745f4..33e0a8c 100644
--- a/drivers/net/ethernet/amd/amd8111e.c
+++ b/drivers/net/ethernet/amd/amd8111e.c
@@ -499,7 +499,7 @@ static int amd8111e_restart(struct net_device *dev)
 	writel( VAL0 | APAD_XMT | REX_RTRY, mmio + CMD2 );
 
 	/* Setting the MAC address to the device */
-	for(i = 0; i < ETH_ADDR_LEN; i++)
+	for (i = 0; i < ETH_ALEN; i++)
 		writeb( dev->dev_addr[i], mmio + PADR + i );
 
 	/* Enable interrupt coalesce */
@@ -1412,10 +1412,11 @@ static void amd8111e_get_drvinfo(struct net_device* dev, struct ethtool_drvinfo
 {
 	struct amd8111e_priv *lp = netdev_priv(dev);
 	struct pci_dev *pci_dev = lp->pci_dev;
-	strcpy (info->driver, MODULE_NAME);
-	strcpy (info->version, MODULE_VERS);
-	sprintf(info->fw_version,"%u",chip_version);
-	strcpy (info->bus_info, pci_name(pci_dev));
+	strlcpy(info->driver, MODULE_NAME, sizeof(info->driver));
+	strlcpy(info->version, MODULE_VERS, sizeof(info->version));
+	snprintf(info->fw_version, sizeof(info->fw_version),
+		"%u", chip_version);
+	strlcpy(info->bus_info, pci_name(pci_dev), sizeof(info->bus_info));
 }
 
 static int amd8111e_get_regs_len(struct net_device *dev)
@@ -1549,7 +1550,7 @@ static int amd8111e_set_mac_address(struct net_device *dev, void *p)
 	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
 	spin_lock_irq(&lp->lock);
 	/* Setting the MAC address to the device */
-	for(i = 0; i < ETH_ADDR_LEN; i++)
+	for (i = 0; i < ETH_ALEN; i++)
 		writeb( dev->dev_addr[i], lp->mmio + PADR + i );
 
 	spin_unlock_irq(&lp->lock);
@@ -1885,7 +1886,7 @@ static int __devinit amd8111e_probe_one(struct pci_dev *pdev,
 	}
 
 	/* Initializing MAC address */
-	for(i = 0; i < ETH_ADDR_LEN; i++)
+	for (i = 0; i < ETH_ALEN; i++)
 		dev->dev_addr[i] = readb(lp->mmio + PADR + i);
 
 	/* Setting user defined parametrs */
diff --git a/drivers/net/ethernet/amd/amd8111e.h b/drivers/net/ethernet/amd/amd8111e.h
index 2ff2e7a..5bbb53a 100644
--- a/drivers/net/ethernet/amd/amd8111e.h
+++ b/drivers/net/ethernet/amd/amd8111e.h
@@ -586,7 +586,6 @@ typedef enum {
 
 #define PKT_BUFF_SZ			1536
 #define MIN_PKT_LEN			60
-#define ETH_ADDR_LEN			6
 
 #define  AMD8111E_TX_TIMEOUT		(3 * HZ)/* 3 sec */
 #define SOFT_TIMER_FREQ 		0xBEBC  /* 0.5 sec */
diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c
index 4865ff1..cc9262b 100644
--- a/drivers/net/ethernet/amd/au1000_eth.c
+++ b/drivers/net/ethernet/amd/au1000_eth.c
@@ -1339,18 +1339,7 @@ static struct platform_driver au1000_eth_driver = {
 		.owner  = THIS_MODULE,
 	},
 };
-MODULE_ALIAS("platform:au1000-eth");
-
-
-static int __init au1000_init_module(void)
-{
-	return platform_driver_register(&au1000_eth_driver);
-}
 
-static void __exit au1000_exit_module(void)
-{
-	platform_driver_unregister(&au1000_eth_driver);
-}
+module_platform_driver(au1000_eth_driver);
 
-module_init(au1000_init_module);
-module_exit(au1000_exit_module);
+MODULE_ALIAS("platform:au1000-eth");
diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c
index 3accd5d..6be0dd6 100644
--- a/drivers/net/ethernet/amd/nmclan_cs.c
+++ b/drivers/net/ethernet/amd/nmclan_cs.c
@@ -160,8 +160,6 @@ Include Files
 Defines
 ---------------------------------------------------------------------------- */
 
-#define ETHER_ADDR_LEN			ETH_ALEN
-					/* 6 bytes in an Ethernet Address */
 #define MACE_LADRF_LEN			8
 					/* 8 bytes in Logical Address Filter */
 
@@ -600,7 +598,7 @@ static int mace_init(mace_private *lp, unsigned int ioaddr, char *enet_addr)
   	}
   }
   /* Set PADR register */
-  for (i = 0; i < ETHER_ADDR_LEN; i++)
+  for (i = 0; i < ETH_ALEN; i++)
     mace_write(lp, ioaddr, MACE_PADR, enet_addr[i]);
 
   /* MAC Configuration Control Register should be written last */
@@ -639,11 +637,11 @@ static int nmclan_config(struct pcmcia_device *link)
 
   /* Read the ethernet address from the CIS. */
   len = pcmcia_get_tuple(link, 0x80, &buf);
-  if (!buf || len < ETHER_ADDR_LEN) {
+  if (!buf || len < ETH_ALEN) {
 	  kfree(buf);
 	  goto failed;
   }
-  memcpy(dev->dev_addr, buf, ETHER_ADDR_LEN);
+  memcpy(dev->dev_addr, buf, ETH_ALEN);
   kfree(buf);
 
   /* Verify configuration by reading the MACE ID. */
@@ -822,9 +820,10 @@ static int mace_close(struct net_device *dev)
 static void netdev_get_drvinfo(struct net_device *dev,
 			       struct ethtool_drvinfo *info)
 {
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	sprintf(info->bus_info, "PCMCIA 0x%lx", dev->base_addr);
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	snprintf(info->bus_info, sizeof(info->bus_info),
+		"PCMCIA 0x%lx", dev->base_addr);
 }
 
 static const struct ethtool_ops netdev_ethtool_ops = {
@@ -1420,7 +1419,7 @@ Output
 static void set_multicast_list(struct net_device *dev)
 {
   mace_private *lp = netdev_priv(dev);
-  int adr[ETHER_ADDR_LEN] = {0}; /* Ethernet address */
+  int adr[ETH_ALEN] = {0}; /* Ethernet address */
   struct netdev_hw_addr *ha;
 
 #ifdef PCMCIA_DEBUG
@@ -1442,7 +1441,7 @@ static void set_multicast_list(struct net_device *dev)
     /* Calculate multicast logical address filter */
     memset(lp->multicast_ladrf, 0, MACE_LADRF_LEN);
     netdev_for_each_mc_addr(ha, dev) {
-      memcpy(adr, ha->addr, ETHER_ADDR_LEN);
+      memcpy(adr, ha->addr, ETH_ALEN);
       BuildLAF(lp->multicast_ladrf, adr);
     }
   }
diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index f92bc6e..20e6dab 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -711,12 +711,14 @@ static void pcnet32_get_drvinfo(struct net_device *dev,
 {
 	struct pcnet32_private *lp = netdev_priv(dev);
 
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
 	if (lp->pci_dev)
-		strcpy(info->bus_info, pci_name(lp->pci_dev));
+		strlcpy(info->bus_info, pci_name(lp->pci_dev),
+			sizeof(info->bus_info));
 	else
-		sprintf(info->bus_info, "VLB 0x%lx", dev->base_addr);
+		snprintf(info->bus_info, sizeof(info->bus_info),
+			"VLB 0x%lx", dev->base_addr);
 }
 
 static u32 pcnet32_get_link(struct net_device *dev)
diff --git a/drivers/net/ethernet/amd/sunlance.c b/drivers/net/ethernet/amd/sunlance.c
index 8fda457..7ea16d3 100644
--- a/drivers/net/ethernet/amd/sunlance.c
+++ b/drivers/net/ethernet/amd/sunlance.c
@@ -1540,17 +1540,4 @@ static struct platform_driver sunlance_sbus_driver = {
 	.remove		= __devexit_p(sunlance_sbus_remove),
 };
 
-
-/* Find all the lance cards on the system and initialize them */
-static int __init sparc_lance_init(void)
-{
-	return platform_driver_register(&sunlance_sbus_driver);
-}
-
-static void __exit sparc_lance_exit(void)
-{
-	platform_driver_unregister(&sunlance_sbus_driver);
-}
-
-module_init(sparc_lance_init);
-module_exit(sparc_lance_exit);
+module_platform_driver(sunlance_sbus_driver);
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c
index 7be884d..0a9326a 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_ethtool.c
@@ -232,7 +232,6 @@ static void atl1c_get_drvinfo(struct net_device *netdev,
 	strlcpy(drvinfo->driver,  atl1c_driver_name, sizeof(drvinfo->driver));
 	strlcpy(drvinfo->version, atl1c_driver_version,
 		sizeof(drvinfo->version));
-	strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version));
 	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
 		sizeof(drvinfo->bus_info));
 	drvinfo->n_stats = 0;
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 02c7ed8..b859124 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -411,7 +411,7 @@ static void atl1c_set_multi(struct net_device *netdev)
 	}
 }
 
-static void __atl1c_vlan_mode(u32 features, u32 *mac_ctrl_data)
+static void __atl1c_vlan_mode(netdev_features_t features, u32 *mac_ctrl_data)
 {
 	if (features & NETIF_F_HW_VLAN_RX) {
 		/* enable VLAN tag insert/strip */
@@ -422,7 +422,8 @@ static void __atl1c_vlan_mode(u32 features, u32 *mac_ctrl_data)
 	}
 }
 
-static void atl1c_vlan_mode(struct net_device *netdev, u32 features)
+static void atl1c_vlan_mode(struct net_device *netdev,
+	netdev_features_t features)
 {
 	struct atl1c_adapter *adapter = netdev_priv(netdev);
 	struct pci_dev *pdev = adapter->pdev;
@@ -482,7 +483,8 @@ static void atl1c_set_rxbufsize(struct atl1c_adapter *adapter,
 		roundup(mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN, 8) : AT_RX_BUF_SIZE;
 }
 
-static u32 atl1c_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t atl1c_fix_features(struct net_device *netdev,
+	netdev_features_t features)
 {
 	/*
 	 * Since there is no support for separate rx/tx vlan accel
@@ -499,9 +501,10 @@ static u32 atl1c_fix_features(struct net_device *netdev, u32 features)
 	return features;
 }
 
-static int atl1c_set_features(struct net_device *netdev, u32 features)
+static int atl1c_set_features(struct net_device *netdev,
+	netdev_features_t features)
 {
-	u32 changed = netdev->features ^ features;
+	netdev_features_t changed = netdev->features ^ features;
 
 	if (changed & NETIF_F_HW_VLAN_RX)
 		atl1c_vlan_mode(netdev, features);
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c b/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c
index 6269438..6e61f9f 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_ethtool.c
@@ -310,10 +310,12 @@ static void atl1e_get_drvinfo(struct net_device *netdev,
 {
 	struct atl1e_adapter *adapter = netdev_priv(netdev);
 
-	strncpy(drvinfo->driver,  atl1e_driver_name, 32);
-	strncpy(drvinfo->version, atl1e_driver_version, 32);
-	strncpy(drvinfo->fw_version, "L1e", 32);
-	strncpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+	strlcpy(drvinfo->driver,  atl1e_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, atl1e_driver_version,
+		sizeof(drvinfo->version));
+	strlcpy(drvinfo->fw_version, "L1e", sizeof(drvinfo->fw_version));
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
 	drvinfo->n_stats = 0;
 	drvinfo->testinfo_len = 0;
 	drvinfo->regdump_len = atl1e_get_regs_len(netdev);
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index 95483bc..c915c08 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -313,7 +313,7 @@ static void atl1e_set_multi(struct net_device *netdev)
 	}
 }
 
-static void __atl1e_vlan_mode(u32 features, u32 *mac_ctrl_data)
+static void __atl1e_vlan_mode(netdev_features_t features, u32 *mac_ctrl_data)
 {
 	if (features & NETIF_F_HW_VLAN_RX) {
 		/* enable VLAN tag insert/strip */
@@ -324,7 +324,8 @@ static void __atl1e_vlan_mode(u32 features, u32 *mac_ctrl_data)
 	}
 }
 
-static void atl1e_vlan_mode(struct net_device *netdev, u32 features)
+static void atl1e_vlan_mode(struct net_device *netdev,
+	netdev_features_t features)
 {
 	struct atl1e_adapter *adapter = netdev_priv(netdev);
 	u32 mac_ctrl_data = 0;
@@ -370,7 +371,8 @@ static int atl1e_set_mac_addr(struct net_device *netdev, void *p)
 	return 0;
 }
 
-static u32 atl1e_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t atl1e_fix_features(struct net_device *netdev,
+	netdev_features_t features)
 {
 	/*
 	 * Since there is no support for separate rx/tx vlan accel
@@ -384,9 +386,10 @@ static u32 atl1e_fix_features(struct net_device *netdev, u32 features)
 	return features;
 }
 
-static int atl1e_set_features(struct net_device *netdev, u32 features)
+static int atl1e_set_features(struct net_device *netdev,
+	netdev_features_t features)
 {
-	u32 changed = netdev->features ^ features;
+	netdev_features_t changed = netdev->features ^ features;
 
 	if (changed & NETIF_F_HW_VLAN_RX)
 		atl1e_vlan_mode(netdev, features);
diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c
index 33a4e35..9bd2049 100644
--- a/drivers/net/ethernet/atheros/atlx/atl1.c
+++ b/drivers/net/ethernet/atheros/atlx/atl1.c
@@ -3365,7 +3365,6 @@ static void atl1_get_drvinfo(struct net_device *netdev,
 	strlcpy(drvinfo->driver, ATLX_DRIVER_NAME, sizeof(drvinfo->driver));
 	strlcpy(drvinfo->version, ATLX_DRIVER_VERSION,
 		sizeof(drvinfo->version));
-	strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version));
 	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
 		sizeof(drvinfo->bus_info));
 	drvinfo->eedump_len = ATL1_EEDUMP_LEN;
diff --git a/drivers/net/ethernet/atheros/atlx/atl2.c b/drivers/net/ethernet/atheros/atlx/atl2.c
index 1feae59..071f4c8 100644
--- a/drivers/net/ethernet/atheros/atlx/atl2.c
+++ b/drivers/net/ethernet/atheros/atlx/atl2.c
@@ -361,7 +361,7 @@ static inline void atl2_irq_disable(struct atl2_adapter *adapter)
     synchronize_irq(adapter->pdev->irq);
 }
 
-static void __atl2_vlan_mode(u32 features, u32 *ctrl)
+static void __atl2_vlan_mode(netdev_features_t features, u32 *ctrl)
 {
 	if (features & NETIF_F_HW_VLAN_RX) {
 		/* enable VLAN tag insert/strip */
@@ -372,7 +372,8 @@ static void __atl2_vlan_mode(u32 features, u32 *ctrl)
 	}
 }
 
-static void atl2_vlan_mode(struct net_device *netdev, u32 features)
+static void atl2_vlan_mode(struct net_device *netdev,
+	netdev_features_t features)
 {
 	struct atl2_adapter *adapter = netdev_priv(netdev);
 	u32 ctrl;
@@ -391,7 +392,8 @@ static void atl2_restore_vlan(struct atl2_adapter *adapter)
 	atl2_vlan_mode(adapter->netdev, adapter->netdev->features);
 }
 
-static u32 atl2_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t atl2_fix_features(struct net_device *netdev,
+	netdev_features_t features)
 {
 	/*
 	 * Since there is no support for separate rx/tx vlan accel
@@ -405,9 +407,10 @@ static u32 atl2_fix_features(struct net_device *netdev, u32 features)
 	return features;
 }
 
-static int atl2_set_features(struct net_device *netdev, u32 features)
+static int atl2_set_features(struct net_device *netdev,
+	netdev_features_t features)
 {
-	u32 changed = netdev->features ^ features;
+	netdev_features_t changed = netdev->features ^ features;
 
 	if (changed & NETIF_F_HW_VLAN_RX)
 		atl2_vlan_mode(netdev, features);
@@ -2049,10 +2052,12 @@ static void atl2_get_drvinfo(struct net_device *netdev,
 {
 	struct atl2_adapter *adapter = netdev_priv(netdev);
 
-	strncpy(drvinfo->driver,  atl2_driver_name, 32);
-	strncpy(drvinfo->version, atl2_driver_version, 32);
-	strncpy(drvinfo->fw_version, "L2", 32);
-	strncpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+	strlcpy(drvinfo->driver,  atl2_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, atl2_driver_version,
+		sizeof(drvinfo->version));
+	strlcpy(drvinfo->fw_version, "L2", sizeof(drvinfo->fw_version));
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
 	drvinfo->n_stats = 0;
 	drvinfo->testinfo_len = 0;
 	drvinfo->regdump_len = atl2_get_regs_len(netdev);
diff --git a/drivers/net/ethernet/atheros/atlx/atlx.c b/drivers/net/ethernet/atheros/atlx/atlx.c
index aabcf4b..8ff7411 100644
--- a/drivers/net/ethernet/atheros/atlx/atlx.c
+++ b/drivers/net/ethernet/atheros/atlx/atlx.c
@@ -211,7 +211,7 @@ static void atlx_link_chg_task(struct work_struct *work)
 	spin_unlock_irqrestore(&adapter->lock, flags);
 }
 
-static void __atlx_vlan_mode(u32 features, u32 *ctrl)
+static void __atlx_vlan_mode(netdev_features_t features, u32 *ctrl)
 {
 	if (features & NETIF_F_HW_VLAN_RX) {
 		/* enable VLAN tag insert/strip */
@@ -222,7 +222,8 @@ static void __atlx_vlan_mode(u32 features, u32 *ctrl)
 	}
 }
 
-static void atlx_vlan_mode(struct net_device *netdev, u32 features)
+static void atlx_vlan_mode(struct net_device *netdev,
+	netdev_features_t features)
 {
 	struct atlx_adapter *adapter = netdev_priv(netdev);
 	unsigned long flags;
@@ -242,7 +243,8 @@ static void atlx_restore_vlan(struct atlx_adapter *adapter)
 	atlx_vlan_mode(adapter->netdev, adapter->netdev->features);
 }
 
-static u32 atlx_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t atlx_fix_features(struct net_device *netdev,
+	netdev_features_t features)
 {
 	/*
 	 * Since there is no support for separate rx/tx vlan accel
@@ -256,9 +258,10 @@ static u32 atlx_fix_features(struct net_device *netdev, u32 features)
 	return features;
 }
 
-static int atlx_set_features(struct net_device *netdev, u32 features)
+static int atlx_set_features(struct net_device *netdev,
+	netdev_features_t features)
 {
-	u32 changed = netdev->features ^ features;
+	netdev_features_t changed = netdev->features ^ features;
 
 	if (changed & NETIF_F_HW_VLAN_RX)
 		atlx_vlan_mode(netdev, features);
diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c
index 4cf835d..3fb66d0 100644
--- a/drivers/net/ethernet/broadcom/b44.c
+++ b/drivers/net/ethernet/broadcom/b44.c
@@ -608,7 +608,7 @@ static void b44_tx(struct b44 *bp)
 				 skb->len,
 				 DMA_TO_DEVICE);
 		rp->skb = NULL;
-		dev_kfree_skb(skb);
+		dev_kfree_skb_irq(skb);
 	}
 
 	bp->tx_cons = cons;
diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c
index 965c723..787e175 100644
--- a/drivers/net/ethernet/broadcom/bnx2.c
+++ b/drivers/net/ethernet/broadcom/bnx2.c
@@ -409,7 +409,7 @@ static int bnx2_unregister_cnic(struct net_device *dev)
 	mutex_lock(&bp->cnic_lock);
 	cp->drv_state = 0;
 	bnapi->cnic_present = 0;
-	rcu_assign_pointer(bp->cnic_ops, NULL);
+	RCU_INIT_POINTER(bp->cnic_ops, NULL);
 	mutex_unlock(&bp->cnic_lock);
 	synchronize_rcu();
 	return 0;
@@ -2054,8 +2054,8 @@ __acquires(&bp->phy_lock)
 
 	if (bp->autoneg & AUTONEG_SPEED) {
 		u32 adv_reg, adv1000_reg;
-		u32 new_adv_reg = 0;
-		u32 new_adv1000_reg = 0;
+		u32 new_adv = 0;
+		u32 new_adv1000 = 0;
 
 		bnx2_read_phy(bp, bp->mii_adv, &adv_reg);
 		adv_reg &= (PHY_ALL_10_100_SPEED | ADVERTISE_PAUSE_CAP |
@@ -2064,27 +2064,18 @@ __acquires(&bp->phy_lock)
 		bnx2_read_phy(bp, MII_CTRL1000, &adv1000_reg);
 		adv1000_reg &= PHY_ALL_1000_SPEED;
 
-		if (bp->advertising & ADVERTISED_10baseT_Half)
-			new_adv_reg |= ADVERTISE_10HALF;
-		if (bp->advertising & ADVERTISED_10baseT_Full)
-			new_adv_reg |= ADVERTISE_10FULL;
-		if (bp->advertising & ADVERTISED_100baseT_Half)
-			new_adv_reg |= ADVERTISE_100HALF;
-		if (bp->advertising & ADVERTISED_100baseT_Full)
-			new_adv_reg |= ADVERTISE_100FULL;
-		if (bp->advertising & ADVERTISED_1000baseT_Full)
-			new_adv1000_reg |= ADVERTISE_1000FULL;
+		new_adv = ethtool_adv_to_mii_adv_t(bp->advertising);
+		new_adv |= ADVERTISE_CSMA;
+		new_adv |= bnx2_phy_get_pause_adv(bp);
 
-		new_adv_reg |= ADVERTISE_CSMA;
+		new_adv1000 |= ethtool_adv_to_mii_ctrl1000_t(bp->advertising);
 
-		new_adv_reg |= bnx2_phy_get_pause_adv(bp);
-
-		if ((adv1000_reg != new_adv1000_reg) ||
-			(adv_reg != new_adv_reg) ||
+		if ((adv1000_reg != new_adv1000) ||
+			(adv_reg != new_adv) ||
 			((bmcr & BMCR_ANENABLE) == 0)) {
 
-			bnx2_write_phy(bp, bp->mii_adv, new_adv_reg);
-			bnx2_write_phy(bp, MII_CTRL1000, new_adv1000_reg);
+			bnx2_write_phy(bp, bp->mii_adv, new_adv);
+			bnx2_write_phy(bp, MII_CTRL1000, new_adv1000);
 			bnx2_write_phy(bp, bp->mii_bmcr, BMCR_ANRESTART |
 				BMCR_ANENABLE);
 		}
@@ -2734,31 +2725,27 @@ bnx2_free_rx_page(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, u16 index)
 }
 
 static inline int
-bnx2_alloc_rx_skb(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, u16 index, gfp_t gfp)
+bnx2_alloc_rx_data(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, u16 index, gfp_t gfp)
 {
-	struct sk_buff *skb;
+	u8 *data;
 	struct sw_bd *rx_buf = &rxr->rx_buf_ring[index];
 	dma_addr_t mapping;
 	struct rx_bd *rxbd = &rxr->rx_desc_ring[RX_RING(index)][RX_IDX(index)];
-	unsigned long align;
 
-	skb = __netdev_alloc_skb(bp->dev, bp->rx_buf_size, gfp);
-	if (skb == NULL) {
+	data = kmalloc(bp->rx_buf_size, gfp);
+	if (!data)
 		return -ENOMEM;
-	}
 
-	if (unlikely((align = (unsigned long) skb->data & (BNX2_RX_ALIGN - 1))))
-		skb_reserve(skb, BNX2_RX_ALIGN - align);
-
-	mapping = dma_map_single(&bp->pdev->dev, skb->data, bp->rx_buf_use_size,
+	mapping = dma_map_single(&bp->pdev->dev,
+				 get_l2_fhdr(data),
+				 bp->rx_buf_use_size,
 				 PCI_DMA_FROMDEVICE);
 	if (dma_mapping_error(&bp->pdev->dev, mapping)) {
-		dev_kfree_skb(skb);
+		kfree(data);
 		return -EIO;
 	}
 
-	rx_buf->skb = skb;
-	rx_buf->desc = (struct l2_fhdr *) skb->data;
+	rx_buf->data = data;
 	dma_unmap_addr_set(rx_buf, mapping, mapping);
 
 	rxbd->rx_bd_haddr_hi = (u64) mapping >> 32;
@@ -2823,6 +2810,7 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
 	struct bnx2_tx_ring_info *txr = &bnapi->tx_ring;
 	u16 hw_cons, sw_cons, sw_ring_cons;
 	int tx_pkt = 0, index;
+	unsigned int tx_bytes = 0;
 	struct netdev_queue *txq;
 
 	index = (bnapi - bp->bnx2_napi);
@@ -2877,6 +2865,7 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
 
 		sw_cons = NEXT_TX_BD(sw_cons);
 
+		tx_bytes += skb->len;
 		dev_kfree_skb(skb);
 		tx_pkt++;
 		if (tx_pkt == budget)
@@ -2886,6 +2875,7 @@ bnx2_tx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
 			hw_cons = bnx2_get_hw_tx_cons(bnapi);
 	}
 
+	netdev_tx_completed_queue(txq, tx_pkt, tx_bytes);
 	txr->hw_tx_cons = hw_cons;
 	txr->tx_cons = sw_cons;
 
@@ -2965,8 +2955,8 @@ bnx2_reuse_rx_skb_pages(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr,
 }
 
 static inline void
-bnx2_reuse_rx_skb(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr,
-		  struct sk_buff *skb, u16 cons, u16 prod)
+bnx2_reuse_rx_data(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr,
+		   u8 *data, u16 cons, u16 prod)
 {
 	struct sw_bd *cons_rx_buf, *prod_rx_buf;
 	struct rx_bd *cons_bd, *prod_bd;
@@ -2980,8 +2970,7 @@ bnx2_reuse_rx_skb(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr,
 
 	rxr->rx_prod_bseq += bp->rx_buf_use_size;
 
-	prod_rx_buf->skb = skb;
-	prod_rx_buf->desc = (struct l2_fhdr *) skb->data;
+	prod_rx_buf->data = data;
 
 	if (cons == prod)
 		return;
@@ -2995,33 +2984,39 @@ bnx2_reuse_rx_skb(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr,
 	prod_bd->rx_bd_haddr_lo = cons_bd->rx_bd_haddr_lo;
 }
 
-static int
-bnx2_rx_skb(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, struct sk_buff *skb,
+static struct sk_buff *
+bnx2_rx_skb(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, u8 *data,
 	    unsigned int len, unsigned int hdr_len, dma_addr_t dma_addr,
 	    u32 ring_idx)
 {
 	int err;
 	u16 prod = ring_idx & 0xffff;
+	struct sk_buff *skb;
 
-	err = bnx2_alloc_rx_skb(bp, rxr, prod, GFP_ATOMIC);
+	err = bnx2_alloc_rx_data(bp, rxr, prod, GFP_ATOMIC);
 	if (unlikely(err)) {
-		bnx2_reuse_rx_skb(bp, rxr, skb, (u16) (ring_idx >> 16), prod);
+		bnx2_reuse_rx_data(bp, rxr, data, (u16) (ring_idx >> 16), prod);
+error:
 		if (hdr_len) {
 			unsigned int raw_len = len + 4;
 			int pages = PAGE_ALIGN(raw_len - hdr_len) >> PAGE_SHIFT;
 
 			bnx2_reuse_rx_skb_pages(bp, rxr, NULL, pages);
 		}
-		return err;
+		return NULL;
 	}
 
-	skb_reserve(skb, BNX2_RX_OFFSET);
 	dma_unmap_single(&bp->pdev->dev, dma_addr, bp->rx_buf_use_size,
 			 PCI_DMA_FROMDEVICE);
-
+	skb = build_skb(data);
+	if (!skb) {
+		kfree(data);
+		goto error;
+	}
+	skb_reserve(skb, ((u8 *)get_l2_fhdr(data) - data) + BNX2_RX_OFFSET);
 	if (hdr_len == 0) {
 		skb_put(skb, len);
-		return 0;
+		return skb;
 	} else {
 		unsigned int i, frag_len, frag_size, pages;
 		struct sw_pg *rx_pg;
@@ -3052,7 +3047,7 @@ bnx2_rx_skb(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, struct sk_buff *skb,
 					skb_frag_size_sub(frag, tail);
 					skb->data_len -= tail;
 				}
-				return 0;
+				return skb;
 			}
 			rx_pg = &rxr->rx_pg_ring[pg_cons];
 
@@ -3074,7 +3069,7 @@ bnx2_rx_skb(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, struct sk_buff *skb,
 				rxr->rx_pg_prod = pg_prod;
 				bnx2_reuse_rx_skb_pages(bp, rxr, skb,
 							pages - i);
-				return err;
+				return NULL;
 			}
 
 			dma_unmap_page(&bp->pdev->dev, mapping_old,
@@ -3091,7 +3086,7 @@ bnx2_rx_skb(struct bnx2 *bp, struct bnx2_rx_ring_info *rxr, struct sk_buff *skb,
 		rxr->rx_pg_prod = pg_prod;
 		rxr->rx_pg_cons = pg_cons;
 	}
-	return 0;
+	return skb;
 }
 
 static inline u16
@@ -3130,19 +3125,17 @@ bnx2_rx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
 		struct sw_bd *rx_buf, *next_rx_buf;
 		struct sk_buff *skb;
 		dma_addr_t dma_addr;
+		u8 *data;
 
 		sw_ring_cons = RX_RING_IDX(sw_cons);
 		sw_ring_prod = RX_RING_IDX(sw_prod);
 
 		rx_buf = &rxr->rx_buf_ring[sw_ring_cons];
-		skb = rx_buf->skb;
-		prefetchw(skb);
-
-		next_rx_buf =
-			&rxr->rx_buf_ring[RX_RING_IDX(NEXT_RX_BD(sw_cons))];
-		prefetch(next_rx_buf->desc);
+		data = rx_buf->data;
+		rx_buf->data = NULL;
 
-		rx_buf->skb = NULL;
+		rx_hdr = get_l2_fhdr(data);
+		prefetch(rx_hdr);
 
 		dma_addr = dma_unmap_addr(rx_buf, mapping);
 
@@ -3150,7 +3143,10 @@ bnx2_rx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
 			BNX2_RX_OFFSET + BNX2_RX_COPY_THRESH,
 			PCI_DMA_FROMDEVICE);
 
-		rx_hdr = rx_buf->desc;
+		next_rx_buf =
+			&rxr->rx_buf_ring[RX_RING_IDX(NEXT_RX_BD(sw_cons))];
+		prefetch(get_l2_fhdr(next_rx_buf->data));
+
 		len = rx_hdr->l2_fhdr_pkt_len;
 		status = rx_hdr->l2_fhdr_status;
 
@@ -3169,7 +3165,7 @@ bnx2_rx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
 				       L2_FHDR_ERRORS_TOO_SHORT |
 				       L2_FHDR_ERRORS_GIANT_FRAME))) {
 
-			bnx2_reuse_rx_skb(bp, rxr, skb, sw_ring_cons,
+			bnx2_reuse_rx_data(bp, rxr, data, sw_ring_cons,
 					  sw_ring_prod);
 			if (pg_ring_used) {
 				int pages;
@@ -3184,30 +3180,29 @@ bnx2_rx_int(struct bnx2 *bp, struct bnx2_napi *bnapi, int budget)
 		len -= 4;
 
 		if (len <= bp->rx_copy_thresh) {
-			struct sk_buff *new_skb;
-
-			new_skb = netdev_alloc_skb(bp->dev, len + 6);
-			if (new_skb == NULL) {
-				bnx2_reuse_rx_skb(bp, rxr, skb, sw_ring_cons,
+			skb = netdev_alloc_skb(bp->dev, len + 6);
+			if (skb == NULL) {
+				bnx2_reuse_rx_data(bp, rxr, data, sw_ring_cons,
 						  sw_ring_prod);
 				goto next_rx;
 			}
 
 			/* aligned copy */
-			skb_copy_from_linear_data_offset(skb,
-							 BNX2_RX_OFFSET - 6,
-				      new_skb->data, len + 6);
-			skb_reserve(new_skb, 6);
-			skb_put(new_skb, len);
+			memcpy(skb->data,
+			       (u8 *)rx_hdr + BNX2_RX_OFFSET - 6,
+			       len + 6);
+			skb_reserve(skb, 6);
+			skb_put(skb, len);
 
-			bnx2_reuse_rx_skb(bp, rxr, skb,
+			bnx2_reuse_rx_data(bp, rxr, data,
 				sw_ring_cons, sw_ring_prod);
 
-			skb = new_skb;
-		} else if (unlikely(bnx2_rx_skb(bp, rxr, skb, len, hdr_len,
-			   dma_addr, (sw_ring_cons << 16) | sw_ring_prod)))
-			goto next_rx;
-
+		} else {
+			skb = bnx2_rx_skb(bp, rxr, data, len, hdr_len, dma_addr,
+					  (sw_ring_cons << 16) | sw_ring_prod);
+			if (!skb)
+				goto next_rx;
+		}
 		if ((status & L2_FHDR_STATUS_L2_VLAN_TAG) &&
 		    !(bp->rx_mode & BNX2_EMAC_RX_MODE_KEEP_VLAN_TAG))
 			__vlan_hwaccel_put_tag(skb, rx_hdr->l2_fhdr_vlan_tag);
@@ -5234,7 +5229,7 @@ bnx2_init_rx_ring(struct bnx2 *bp, int ring_num)
 
 	ring_prod = prod = rxr->rx_prod;
 	for (i = 0; i < bp->rx_ring_size; i++) {
-		if (bnx2_alloc_rx_skb(bp, rxr, ring_prod, GFP_KERNEL) < 0) {
+		if (bnx2_alloc_rx_data(bp, rxr, ring_prod, GFP_KERNEL) < 0) {
 			netdev_warn(bp->dev, "init'ed rx ring %d with %d/%d skbs only\n",
 				    ring_num, i, bp->rx_ring_size);
 			break;
@@ -5329,7 +5324,7 @@ bnx2_set_rx_ring_size(struct bnx2 *bp, u32 size)
 	rx_size = bp->dev->mtu + ETH_HLEN + BNX2_RX_OFFSET + 8;
 
 	rx_space = SKB_DATA_ALIGN(rx_size + BNX2_RX_ALIGN) + NET_SKB_PAD +
-		sizeof(struct skb_shared_info);
+		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	bp->rx_copy_thresh = BNX2_RX_COPY_THRESH;
 	bp->rx_pg_ring_size = 0;
@@ -5351,8 +5346,9 @@ bnx2_set_rx_ring_size(struct bnx2 *bp, u32 size)
 	}
 
 	bp->rx_buf_use_size = rx_size;
-	/* hw alignment */
-	bp->rx_buf_size = bp->rx_buf_use_size + BNX2_RX_ALIGN;
+	/* hw alignment + build_skb() overhead*/
+	bp->rx_buf_size = SKB_DATA_ALIGN(bp->rx_buf_use_size + BNX2_RX_ALIGN) +
+		NET_SKB_PAD + SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	bp->rx_jumbo_thresh = rx_size - BNX2_RX_OFFSET;
 	bp->rx_ring_size = size;
 	bp->rx_max_ring = bnx2_find_max_ring(size, MAX_RX_RINGS);
@@ -5400,6 +5396,7 @@ bnx2_free_tx_skbs(struct bnx2 *bp)
 			}
 			dev_kfree_skb(skb);
 		}
+		netdev_tx_reset_queue(netdev_get_tx_queue(bp->dev, i));
 	}
 }
 
@@ -5418,9 +5415,9 @@ bnx2_free_rx_skbs(struct bnx2 *bp)
 
 		for (j = 0; j < bp->rx_max_ring_idx; j++) {
 			struct sw_bd *rx_buf = &rxr->rx_buf_ring[j];
-			struct sk_buff *skb = rx_buf->skb;
+			u8 *data = rx_buf->data;
 
-			if (skb == NULL)
+			if (data == NULL)
 				continue;
 
 			dma_unmap_single(&bp->pdev->dev,
@@ -5428,9 +5425,9 @@ bnx2_free_rx_skbs(struct bnx2 *bp)
 					 bp->rx_buf_use_size,
 					 PCI_DMA_FROMDEVICE);
 
-			rx_buf->skb = NULL;
+			rx_buf->data = NULL;
 
-			dev_kfree_skb(skb);
+			kfree(data);
 		}
 		for (j = 0; j < bp->rx_max_pg_ring_idx; j++)
 			bnx2_free_rx_page(bp, rxr, j);
@@ -5736,7 +5733,8 @@ static int
 bnx2_run_loopback(struct bnx2 *bp, int loopback_mode)
 {
 	unsigned int pkt_size, num_pkts, i;
-	struct sk_buff *skb, *rx_skb;
+	struct sk_buff *skb;
+	u8 *data;
 	unsigned char *packet;
 	u16 rx_start_idx, rx_idx;
 	dma_addr_t map;
@@ -5828,14 +5826,14 @@ bnx2_run_loopback(struct bnx2 *bp, int loopback_mode)
 	}
 
 	rx_buf = &rxr->rx_buf_ring[rx_start_idx];
-	rx_skb = rx_buf->skb;
+	data = rx_buf->data;
 
-	rx_hdr = rx_buf->desc;
-	skb_reserve(rx_skb, BNX2_RX_OFFSET);
+	rx_hdr = get_l2_fhdr(data);
+	data = (u8 *)rx_hdr + BNX2_RX_OFFSET;
 
 	dma_sync_single_for_cpu(&bp->pdev->dev,
 		dma_unmap_addr(rx_buf, mapping),
-		bp->rx_buf_size, PCI_DMA_FROMDEVICE);
+		bp->rx_buf_use_size, PCI_DMA_FROMDEVICE);
 
 	if (rx_hdr->l2_fhdr_status &
 		(L2_FHDR_ERRORS_BAD_CRC |
@@ -5852,7 +5850,7 @@ bnx2_run_loopback(struct bnx2 *bp, int loopback_mode)
 	}
 
 	for (i = 14; i < pkt_size; i++) {
-		if (*(rx_skb->data + i) != (unsigned char) (i & 0xff)) {
+		if (*(data + i) != (unsigned char) (i & 0xff)) {
 			goto loopback_test_done;
 		}
 	}
@@ -6552,6 +6550,8 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 	txbd->tx_bd_vlan_tag_flags |= TX_BD_FLAGS_END;
 
+	netdev_tx_sent_queue(txq, skb->len);
+
 	prod = NEXT_TX_BD(prod);
 	txr->tx_prod_bseq += skb->len;
 
@@ -6873,10 +6873,10 @@ bnx2_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
 	struct bnx2 *bp = netdev_priv(dev);
 
-	strcpy(info->driver, DRV_MODULE_NAME);
-	strcpy(info->version, DRV_MODULE_VERSION);
-	strcpy(info->bus_info, pci_name(bp->pdev));
-	strcpy(info->fw_version, bp->fw_version);
+	strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
+	strlcpy(info->fw_version, bp->fw_version, sizeof(info->fw_version));
 }
 
 #define BNX2_REGDUMP_LEN		(32 * 1024)
@@ -7571,8 +7571,8 @@ bnx2_set_phys_id(struct net_device *dev, enum ethtool_phys_id_state state)
 	return 0;
 }
 
-static u32
-bnx2_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t
+bnx2_fix_features(struct net_device *dev, netdev_features_t features)
 {
 	struct bnx2 *bp = netdev_priv(dev);
 
@@ -7583,7 +7583,7 @@ bnx2_fix_features(struct net_device *dev, u32 features)
 }
 
 static int
-bnx2_set_features(struct net_device *dev, u32 features)
+bnx2_set_features(struct net_device *dev, netdev_features_t features)
 {
 	struct bnx2 *bp = netdev_priv(dev);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2.h b/drivers/net/ethernet/broadcom/bnx2.h
index 99d31a7..1db2d51 100644
--- a/drivers/net/ethernet/broadcom/bnx2.h
+++ b/drivers/net/ethernet/broadcom/bnx2.h
@@ -6563,12 +6563,25 @@ struct l2_fhdr {
 #define MB_TX_CID_ADDR	MB_GET_CID_ADDR(TX_CID)
 #define MB_RX_CID_ADDR	MB_GET_CID_ADDR(RX_CID)
 
+/*
+ * This driver uses new build_skb() API :
+ * RX ring buffer contains pointer to kmalloc() data only,
+ * skb are built only after Hardware filled the frame.
+ */
 struct sw_bd {
-	struct sk_buff		*skb;
-	struct l2_fhdr		*desc;
+	u8			*data;
 	DEFINE_DMA_UNMAP_ADDR(mapping);
 };
 
+/* Its faster to compute this from data than storing it in sw_bd
+ * (less cache misses)
+ */
+static inline struct l2_fhdr *get_l2_fhdr(u8 *data)
+{
+	return (struct l2_fhdr *)(PTR_ALIGN(data, BNX2_RX_ALIGN) + NET_SKB_PAD);
+}
+
+
 struct sw_pg {
 	struct page		*page;
 	DEFINE_DMA_UNMAP_ADDR(mapping);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
index aec7212..8c73d34 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -23,8 +23,8 @@
  * (you will need to reboot afterwards) */
 /* #define BNX2X_STOP_ON_ERROR */
 
-#define DRV_MODULE_VERSION      "1.70.30-0"
-#define DRV_MODULE_RELDATE      "2011/10/25"
+#define DRV_MODULE_VERSION      "1.70.35-0"
+#define DRV_MODULE_RELDATE      "2011/11/10"
 #define BNX2X_BC_VER            0x040200
 
 #if defined(CONFIG_DCB)
@@ -293,8 +293,13 @@ enum {
 #define FCOE_TXQ_IDX(bp)	(MAX_ETH_TXQ_IDX(bp))
 
 /* fast path */
+/*
+ * This driver uses new build_skb() API :
+ * RX ring buffer contains pointer to kmalloc() data only,
+ * skb are built only after Hardware filled the frame.
+ */
 struct sw_rx_bd {
-	struct sk_buff	*skb;
+	u8		*data;
 	DEFINE_DMA_UNMAP_ADDR(mapping);
 };
 
@@ -411,8 +416,7 @@ union db_prod {
 
 
 /* Number of u64 elements in SGE mask array */
-#define RX_SGE_MASK_LEN			((NUM_RX_SGE_PAGES * RX_SGE_CNT) / \
-					 BIT_VEC64_ELEM_SZ)
+#define RX_SGE_MASK_LEN			(NUM_RX_SGE / BIT_VEC64_ELEM_SZ)
 #define RX_SGE_MASK_LEN_MASK		(RX_SGE_MASK_LEN - 1)
 #define NEXT_SGE_MASK_ELEM(el)		(((el) + 1) & RX_SGE_MASK_LEN_MASK)
 
@@ -425,8 +429,8 @@ union host_hc_status_block {
 
 struct bnx2x_agg_info {
 	/*
-	 * First aggregation buffer is an skb, the following - are pages.
-	 * We will preallocate the skbs for each aggregation when
+	 * First aggregation buffer is a data buffer, the following - are pages.
+	 * We will preallocate the data buffer for each aggregation when
 	 * we open the interface and will replace the BD at the consumer
 	 * with this one when we receive the TPA_START CQE in order to
 	 * keep the Rx BD ring consistent.
@@ -440,6 +444,7 @@ struct bnx2x_agg_info {
 	u16			parsing_flags;
 	u16			vlan_tag;
 	u16			len_on_bd;
+	u32			rxhash;
 };
 
 #define Q_STATS_OFFSET32(stat_name) \
@@ -507,6 +512,7 @@ struct bnx2x_fastpath {
 	__le16			fp_hc_idx;
 
 	u8			index;		/* number in fp array */
+	u8			rx_queue;	/* index for skb_record */
 	u8			cl_id;		/* eth client id */
 	u8			cl_qzone_id;
 	u8			fw_sb_id;	/* status block number in FW */
@@ -881,6 +887,8 @@ struct bnx2x_common {
 #define CHIP_PORT_MODE_NONE			0x2
 #define CHIP_MODE(bp)			(bp->common.chip_port_mode)
 #define CHIP_MODE_IS_4_PORT(bp) (CHIP_MODE(bp) == CHIP_4_PORT_MODE)
+
+	u32			boot_mode;
 };
 
 /* IGU MSIX STATISTICS on 57712: 64 for VFs; 4 for PFs; 4 for Attentions */
@@ -1042,6 +1050,8 @@ struct bnx2x_slowpath {
 
 	u32				wb_comp;
 	u32				wb_data[4];
+
+	union drv_info_to_mcp		drv_info_to_mcp;
 };
 
 #define bnx2x_sp(bp, var)		(&bp->slowpath->var)
@@ -1122,18 +1132,21 @@ enum {
 enum {
 	BNX2X_PORT_QUERY_IDX,
 	BNX2X_PF_QUERY_IDX,
+	BNX2X_FCOE_QUERY_IDX,
 	BNX2X_FIRST_QUEUE_QUERY_IDX,
 };
 
 struct bnx2x_fw_stats_req {
 	struct stats_query_header hdr;
-	struct stats_query_entry query[STATS_QUERY_CMD_COUNT];
+	struct stats_query_entry query[FP_SB_MAX_E1x+
+		BNX2X_FIRST_QUEUE_QUERY_IDX];
 };
 
 struct bnx2x_fw_stats_data {
 	struct stats_counter	storm_counters;
 	struct per_port_stats	port;
 	struct per_pf_stats	pf;
+	struct fcoe_statistics_params	fcoe;
 	struct per_queue_stats  queue_stats[1];
 };
 
@@ -1141,6 +1154,7 @@ struct bnx2x_fw_stats_data {
 enum {
 	BNX2X_SP_RTNL_SETUP_TC,
 	BNX2X_SP_RTNL_TX_TIMEOUT,
+	BNX2X_SP_RTNL_FAN_FAILURE,
 };
 
 
@@ -1186,10 +1200,20 @@ struct bnx2x {
 #define ETH_MAX_JUMBO_PACKET_SIZE	9600
 
 	/* Max supported alignment is 256 (8 shift) */
-#define BNX2X_RX_ALIGN_SHIFT		((L1_CACHE_SHIFT < 8) ? \
-					 L1_CACHE_SHIFT : 8)
-	/* FW use 2 Cache lines Alignment for start packet and size  */
-#define BNX2X_FW_RX_ALIGN		(2 << BNX2X_RX_ALIGN_SHIFT)
+#define BNX2X_RX_ALIGN_SHIFT		min(8, L1_CACHE_SHIFT)
+
+	/* FW uses 2 Cache lines Alignment for start packet and size
+	 *
+	 * We assume skb_build() uses sizeof(struct skb_shared_info) bytes
+	 * at the end of skb->data, to avoid wasting a full cache line.
+	 * This reduces memory use (skb->truesize).
+	 */
+#define BNX2X_FW_RX_ALIGN_START	(1UL << BNX2X_RX_ALIGN_SHIFT)
+
+#define BNX2X_FW_RX_ALIGN_END					\
+	max(1UL << BNX2X_RX_ALIGN_SHIFT, 			\
+	    SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+
 #define BNX2X_PXP_DRAM_ALIGN		(BNX2X_RX_ALIGN_SHIFT - 5)
 
 	struct host_sp_status_block *def_status_blk;
@@ -1249,6 +1273,7 @@ struct bnx2x {
 #define NO_ISCSI_OOO_FLAG		(1 << 13)
 #define NO_ISCSI_FLAG			(1 << 14)
 #define NO_FCOE_FLAG			(1 << 15)
+#define BC_SUPPORTS_PFC_STATS		(1 << 17)
 
 #define NO_ISCSI(bp)		((bp)->flags & NO_ISCSI_FLAG)
 #define NO_ISCSI_OOO(bp)	((bp)->flags & NO_ISCSI_OOO_FLAG)
@@ -1984,13 +2009,6 @@ static inline u32 reg_poll(struct bnx2x *bp, u32 reg, u32 expected, int ms,
 #define HW_PRTY_ASSERT_SET_4 (AEU_INPUTS_ATTN_BITS_PGLUE_PARITY_ERROR | \
 			      AEU_INPUTS_ATTN_BITS_ATC_PARITY_ERROR)
 
-#define RSS_FLAGS(bp) \
-		(TSTORM_ETH_FUNCTION_COMMON_CONFIG_RSS_IPV4_CAPABILITY | \
-		 TSTORM_ETH_FUNCTION_COMMON_CONFIG_RSS_IPV4_TCP_CAPABILITY | \
-		 TSTORM_ETH_FUNCTION_COMMON_CONFIG_RSS_IPV6_CAPABILITY | \
-		 TSTORM_ETH_FUNCTION_COMMON_CONFIG_RSS_IPV6_TCP_CAPABILITY | \
-		 (bp->multi_mode << \
-		  TSTORM_ETH_FUNCTION_COMMON_CONFIG_RSS_MODE_SHIFT))
 #define MULTI_MASK			0x7f
 
 
@@ -2055,6 +2073,8 @@ static inline u32 reg_poll(struct bnx2x *bp, u32 reg, u32 expected, int ms,
 #define BNX2X_VPD_LEN			128
 #define VENDOR_ID_LEN			4
 
+int bnx2x_close(struct net_device *dev);
+
 /* Congestion management fairness mode */
 #define CMNG_FNS_NONE		0
 #define CMNG_FNS_MINMAX		1
@@ -2072,4 +2092,16 @@ static const u32 dmae_reg_go_c[] = {
 
 void bnx2x_set_ethtool_ops(struct net_device *netdev);
 void bnx2x_notify_link_changed(struct bnx2x *bp);
+
+
+#define BNX2X_MF_PROTOCOL(bp) \
+	((bp)->mf_config[BP_VN(bp)] & FUNC_MF_CFG_PROTOCOL_MASK)
+
+#ifdef BCM_CNIC
+#define BNX2X_IS_MF_PROTOCOL_ISCSI(bp) \
+	(BNX2X_MF_PROTOCOL(bp) == FUNC_MF_CFG_PROTOCOL_ISCSI)
+
+#define IS_MF_ISCSI_SD(bp) (IS_MF_SD(bp) && BNX2X_IS_MF_PROTOCOL_ISCSI(bp))
+#endif
+
 #endif /* bnx2x.h */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index 580b44e..2b731b2 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -79,19 +79,21 @@ static inline void bnx2x_bz_fp(struct bnx2x *bp, int index)
  * @to:		destination FP index
  *
  * Makes sure the contents of the bp->fp[to].napi is kept
- * intact.
+ * intact. This is done by first copying the napi struct from
+ * the target to the source, and then mem copying the entire
+ * source onto the target
  */
 static inline void bnx2x_move_fp(struct bnx2x *bp, int from, int to)
 {
 	struct bnx2x_fastpath *from_fp = &bp->fp[from];
 	struct bnx2x_fastpath *to_fp = &bp->fp[to];
-	struct napi_struct orig_napi = to_fp->napi;
+
+	/* Copy the NAPI object as it has been already initialized */
+	from_fp->napi = to_fp->napi;
+
 	/* Move bnx2x_fastpath contents */
 	memcpy(to_fp, from_fp, sizeof(*to_fp));
 	to_fp->index = to;
-
-	/* Restore the NAPI object as it has been already initialized */
-	to_fp->napi = orig_napi;
 }
 
 int load_count[2][3] = { {0} }; /* per-path: 0-common, 1-port0, 2-port1 */
@@ -100,7 +102,8 @@ int load_count[2][3] = { {0} }; /* per-path: 0-common, 1-port0, 2-port1 */
  * return idx of last bd freed
  */
 static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata,
-			     u16 idx)
+			     u16 idx, unsigned int *pkts_compl,
+			     unsigned int *bytes_compl)
 {
 	struct sw_tx_bd *tx_buf = &txdata->tx_buf_ring[idx];
 	struct eth_tx_start_bd *tx_start_bd;
@@ -157,6 +160,10 @@ static u16 bnx2x_free_tx_pkt(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata,
 
 	/* release skb */
 	WARN_ON(!skb);
+	if (skb) {
+		(*pkts_compl)++;
+		(*bytes_compl) += skb->len;
+	}
 	dev_kfree_skb_any(skb);
 	tx_buf->first_bd = 0;
 	tx_buf->skb = NULL;
@@ -168,6 +175,7 @@ int bnx2x_tx_int(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata)
 {
 	struct netdev_queue *txq;
 	u16 hw_cons, sw_cons, bd_cons = txdata->tx_bd_cons;
+	unsigned int pkts_compl = 0, bytes_compl = 0;
 
 #ifdef BNX2X_STOP_ON_ERROR
 	if (unlikely(bp->panic))
@@ -187,10 +195,14 @@ int bnx2x_tx_int(struct bnx2x *bp, struct bnx2x_fp_txdata *txdata)
 				      " pkt_cons %u\n",
 		   txdata->txq_index, hw_cons, sw_cons, pkt_cons);
 
-		bd_cons = bnx2x_free_tx_pkt(bp, txdata, pkt_cons);
+		bd_cons = bnx2x_free_tx_pkt(bp, txdata, pkt_cons,
+		    &pkts_compl, &bytes_compl);
+
 		sw_cons++;
 	}
 
+	netdev_tx_completed_queue(txq, pkts_compl, bytes_compl);
+
 	txdata->tx_pkt_cons = sw_cons;
 	txdata->tx_bd_cons = bd_cons;
 
@@ -292,8 +304,21 @@ static void bnx2x_update_sge_prod(struct bnx2x_fastpath *fp,
 	   fp->last_max_sge, fp->rx_sge_prod);
 }
 
+/* Set Toeplitz hash value in the skb using the value from the
+ * CQE (calculated by HW).
+ */
+static u32 bnx2x_get_rxhash(const struct bnx2x *bp,
+			    const struct eth_fast_path_rx_cqe *cqe)
+{
+	/* Set Toeplitz hash from CQE */
+	if ((bp->dev->features & NETIF_F_RXHASH) &&
+	    (cqe->status_flags & ETH_FAST_PATH_RX_CQE_RSS_HASH_FLG))
+		return le32_to_cpu(cqe->rss_hash_result);
+	return 0;
+}
+
 static void bnx2x_tpa_start(struct bnx2x_fastpath *fp, u16 queue,
-			    struct sk_buff *skb, u16 cons, u16 prod,
+			    u16 cons, u16 prod,
 			    struct eth_fast_path_rx_cqe *cqe)
 {
 	struct bnx2x *bp = fp->bp;
@@ -308,9 +333,9 @@ static void bnx2x_tpa_start(struct bnx2x_fastpath *fp, u16 queue,
 	if (tpa_info->tpa_state != BNX2X_TPA_STOP)
 		BNX2X_ERR("start of bin not in stop [%d]\n", queue);
 
-	/* Try to map an empty skb from the aggregation info  */
+	/* Try to map an empty data buffer from the aggregation info  */
 	mapping = dma_map_single(&bp->pdev->dev,
-				 first_buf->skb->data,
+				 first_buf->data + NET_SKB_PAD,
 				 fp->rx_buf_size, DMA_FROM_DEVICE);
 	/*
 	 *  ...if it fails - move the skb from the consumer to the producer
@@ -320,15 +345,15 @@ static void bnx2x_tpa_start(struct bnx2x_fastpath *fp, u16 queue,
 
 	if (unlikely(dma_mapping_error(&bp->pdev->dev, mapping))) {
 		/* Move the BD from the consumer to the producer */
-		bnx2x_reuse_rx_skb(fp, cons, prod);
+		bnx2x_reuse_rx_data(fp, cons, prod);
 		tpa_info->tpa_state = BNX2X_TPA_ERROR;
 		return;
 	}
 
-	/* move empty skb from pool to prod */
-	prod_rx_buf->skb = first_buf->skb;
+	/* move empty data from pool to prod */
+	prod_rx_buf->data = first_buf->data;
 	dma_unmap_addr_set(prod_rx_buf, mapping, mapping);
-	/* point prod_bd to new skb */
+	/* point prod_bd to new data */
 	prod_bd->addr_hi = cpu_to_le32(U64_HI(mapping));
 	prod_bd->addr_lo = cpu_to_le32(U64_LO(mapping));
 
@@ -342,6 +367,7 @@ static void bnx2x_tpa_start(struct bnx2x_fastpath *fp, u16 queue,
 	tpa_info->tpa_state = BNX2X_TPA_START;
 	tpa_info->len_on_bd = le16_to_cpu(cqe->len_on_bd);
 	tpa_info->placement_offset = cqe->placement_offset;
+	tpa_info->rxhash = bnx2x_get_rxhash(bp, cqe);
 
 #ifdef BNX2X_STOP_ON_ERROR
 	fp->tpa_queue_used |= (1 << queue);
@@ -469,11 +495,12 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 {
 	struct bnx2x_agg_info *tpa_info = &fp->tpa_info[queue];
 	struct sw_rx_bd *rx_buf = &tpa_info->first_buf;
-	u8 pad = tpa_info->placement_offset;
+	u32 pad = tpa_info->placement_offset;
 	u16 len = tpa_info->len_on_bd;
-	struct sk_buff *skb = rx_buf->skb;
+	struct sk_buff *skb = NULL;
+	u8 *data = rx_buf->data;
 	/* alloc new skb */
-	struct sk_buff *new_skb;
+	u8 *new_data;
 	u8 old_tpa_state = tpa_info->tpa_state;
 
 	tpa_info->tpa_state = BNX2X_TPA_STOP;
@@ -484,18 +511,18 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 	if (old_tpa_state == BNX2X_TPA_ERROR)
 		goto drop;
 
-	/* Try to allocate the new skb */
-	new_skb = netdev_alloc_skb(bp->dev, fp->rx_buf_size);
+	/* Try to allocate the new data */
+	new_data = kmalloc(fp->rx_buf_size + NET_SKB_PAD, GFP_ATOMIC);
 
 	/* Unmap skb in the pool anyway, as we are going to change
 	   pool entry status to BNX2X_TPA_STOP even if new skb allocation
 	   fails. */
 	dma_unmap_single(&bp->pdev->dev, dma_unmap_addr(rx_buf, mapping),
 			 fp->rx_buf_size, DMA_FROM_DEVICE);
+	if (likely(new_data))
+		skb = build_skb(data);
 
-	if (likely(new_skb)) {
-		prefetch(skb);
-		prefetch(((char *)(skb)) + L1_CACHE_BYTES);
+	if (likely(skb)) {
 
 #ifdef BNX2X_STOP_ON_ERROR
 		if (pad + len > fp->rx_buf_size) {
@@ -507,8 +534,9 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 		}
 #endif
 
-		skb_reserve(skb, pad);
+		skb_reserve(skb, pad + NET_SKB_PAD);
 		skb_put(skb, len);
+		skb->rxhash = tpa_info->rxhash;
 
 		skb->protocol = eth_type_trans(skb, bp->dev);
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -524,8 +552,8 @@ static void bnx2x_tpa_stop(struct bnx2x *bp, struct bnx2x_fastpath *fp,
 		}
 
 
-		/* put new skb in bin */
-		rx_buf->skb = new_skb;
+		/* put new data in bin */
+		rx_buf->data = new_data;
 
 		return;
 	}
@@ -537,19 +565,6 @@ drop:
 	fp->eth_q_stats.rx_skb_alloc_failed++;
 }
 
-/* Set Toeplitz hash value in the skb using the value from the
- * CQE (calculated by HW).
- */
-static inline void bnx2x_set_skb_rxhash(struct bnx2x *bp, union eth_rx_cqe *cqe,
-					struct sk_buff *skb)
-{
-	/* Set Toeplitz hash from CQE */
-	if ((bp->dev->features & NETIF_F_RXHASH) &&
-	    (cqe->fast_path_cqe.status_flags &
-	     ETH_FAST_PATH_RX_CQE_RSS_HASH_FLG))
-		skb->rxhash =
-		le32_to_cpu(cqe->fast_path_cqe.rss_hash_result);
-}
 
 int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget)
 {
@@ -592,6 +607,7 @@ int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget)
 		u8 cqe_fp_flags;
 		enum eth_rx_cqe_type cqe_fp_type;
 		u16 len, pad;
+		u8 *data;
 
 #ifdef BNX2X_STOP_ON_ERROR
 		if (unlikely(bp->panic))
@@ -602,13 +618,6 @@ int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget)
 		bd_prod = RX_BD(bd_prod);
 		bd_cons = RX_BD(bd_cons);
 
-		/* Prefetch the page containing the BD descriptor
-		   at producer's index. It will be needed when new skb is
-		   allocated */
-		prefetch((void *)(PAGE_ALIGN((unsigned long)
-					     (&fp->rx_desc_ring[bd_prod])) -
-				  PAGE_SIZE + 1));
-
 		cqe = &fp->rx_comp_ring[comp_ring_cons];
 		cqe_fp = &cqe->fast_path_cqe;
 		cqe_fp_flags = cqe_fp->type_error_flags;
@@ -624,138 +633,123 @@ int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget)
 		if (unlikely(CQE_TYPE_SLOW(cqe_fp_type))) {
 			bnx2x_sp_event(fp, cqe);
 			goto next_cqe;
+		}
+		rx_buf = &fp->rx_buf_ring[bd_cons];
+		data = rx_buf->data;
 
-		/* this is an rx packet */
-		} else {
-			rx_buf = &fp->rx_buf_ring[bd_cons];
-			skb = rx_buf->skb;
-			prefetch(skb);
-
-			if (!CQE_TYPE_FAST(cqe_fp_type)) {
+		if (!CQE_TYPE_FAST(cqe_fp_type)) {
 #ifdef BNX2X_STOP_ON_ERROR
-				/* sanity check */
-				if (fp->disable_tpa &&
-				    (CQE_TYPE_START(cqe_fp_type) ||
-				     CQE_TYPE_STOP(cqe_fp_type)))
-					BNX2X_ERR("START/STOP packet while "
-						  "disable_tpa type %x\n",
-						  CQE_TYPE(cqe_fp_type));
+			/* sanity check */
+			if (fp->disable_tpa &&
+			    (CQE_TYPE_START(cqe_fp_type) ||
+			     CQE_TYPE_STOP(cqe_fp_type)))
+				BNX2X_ERR("START/STOP packet while "
+					  "disable_tpa type %x\n",
+					  CQE_TYPE(cqe_fp_type));
 #endif
 
-				if (CQE_TYPE_START(cqe_fp_type)) {
-					u16 queue = cqe_fp->queue_index;
-					DP(NETIF_MSG_RX_STATUS,
-					   "calling tpa_start on queue %d\n",
-					   queue);
+			if (CQE_TYPE_START(cqe_fp_type)) {
+				u16 queue = cqe_fp->queue_index;
+				DP(NETIF_MSG_RX_STATUS,
+				   "calling tpa_start on queue %d\n",
+				   queue);
 
-					bnx2x_tpa_start(fp, queue, skb,
-							bd_cons, bd_prod,
-							cqe_fp);
-
-					/* Set Toeplitz hash for LRO skb */
-					bnx2x_set_skb_rxhash(bp, cqe, skb);
-
-					goto next_rx;
-
-				} else {
-					u16 queue =
-						cqe->end_agg_cqe.queue_index;
-					DP(NETIF_MSG_RX_STATUS,
-					   "calling tpa_stop on queue %d\n",
-					   queue);
-
-					bnx2x_tpa_stop(bp, fp, queue,
-						       &cqe->end_agg_cqe,
-						       comp_ring_cons);
+				bnx2x_tpa_start(fp, queue,
+						bd_cons, bd_prod,
+						cqe_fp);
+				goto next_rx;
+			} else {
+				u16 queue =
+					cqe->end_agg_cqe.queue_index;
+				DP(NETIF_MSG_RX_STATUS,
+				   "calling tpa_stop on queue %d\n",
+				   queue);
+
+				bnx2x_tpa_stop(bp, fp, queue,
+					       &cqe->end_agg_cqe,
+					       comp_ring_cons);
 #ifdef BNX2X_STOP_ON_ERROR
-					if (bp->panic)
-						return 0;
+				if (bp->panic)
+					return 0;
 #endif
 
-					bnx2x_update_sge_prod(fp, cqe_fp);
-					goto next_cqe;
-				}
+				bnx2x_update_sge_prod(fp, cqe_fp);
+				goto next_cqe;
 			}
-			/* non TPA */
-			len = le16_to_cpu(cqe_fp->pkt_len);
-			pad = cqe_fp->placement_offset;
-			dma_sync_single_for_cpu(&bp->pdev->dev,
+		}
+		/* non TPA */
+		len = le16_to_cpu(cqe_fp->pkt_len);
+		pad = cqe_fp->placement_offset;
+		dma_sync_single_for_cpu(&bp->pdev->dev,
 					dma_unmap_addr(rx_buf, mapping),
-						       pad + RX_COPY_THRESH,
-						       DMA_FROM_DEVICE);
-			prefetch(((char *)(skb)) + L1_CACHE_BYTES);
+					pad + RX_COPY_THRESH,
+					DMA_FROM_DEVICE);
+		pad += NET_SKB_PAD;
+		prefetch(data + pad); /* speedup eth_type_trans() */
+		/* is this an error packet? */
+		if (unlikely(cqe_fp_flags & ETH_RX_ERROR_FALGS)) {
+			DP(NETIF_MSG_RX_ERR,
+			   "ERROR  flags %x  rx packet %u\n",
+			   cqe_fp_flags, sw_comp_cons);
+			fp->eth_q_stats.rx_err_discard_pkt++;
+			goto reuse_rx;
+		}
 
-			/* is this an error packet? */
-			if (unlikely(cqe_fp_flags & ETH_RX_ERROR_FALGS)) {
+		/* Since we don't have a jumbo ring
+		 * copy small packets if mtu > 1500
+		 */
+		if ((bp->dev->mtu > ETH_MAX_PACKET_SIZE) &&
+		    (len <= RX_COPY_THRESH)) {
+			skb = netdev_alloc_skb_ip_align(bp->dev, len);
+			if (skb == NULL) {
 				DP(NETIF_MSG_RX_ERR,
-				   "ERROR  flags %x  rx packet %u\n",
-				   cqe_fp_flags, sw_comp_cons);
-				fp->eth_q_stats.rx_err_discard_pkt++;
+				   "ERROR  packet dropped because of alloc failure\n");
+				fp->eth_q_stats.rx_skb_alloc_failed++;
 				goto reuse_rx;
 			}
-
-			/* Since we don't have a jumbo ring
-			 * copy small packets if mtu > 1500
-			 */
-			if ((bp->dev->mtu > ETH_MAX_PACKET_SIZE) &&
-			    (len <= RX_COPY_THRESH)) {
-				struct sk_buff *new_skb;
-
-				new_skb = netdev_alloc_skb(bp->dev, len + pad);
-				if (new_skb == NULL) {
-					DP(NETIF_MSG_RX_ERR,
-					   "ERROR  packet dropped "
-					   "because of alloc failure\n");
-					fp->eth_q_stats.rx_skb_alloc_failed++;
-					goto reuse_rx;
-				}
-
-				/* aligned copy */
-				skb_copy_from_linear_data_offset(skb, pad,
-						    new_skb->data + pad, len);
-				skb_reserve(new_skb, pad);
-				skb_put(new_skb, len);
-
-				bnx2x_reuse_rx_skb(fp, bd_cons, bd_prod);
-
-				skb = new_skb;
-
-			} else
-			if (likely(bnx2x_alloc_rx_skb(bp, fp, bd_prod) == 0)) {
+			memcpy(skb->data, data + pad, len);
+			bnx2x_reuse_rx_data(fp, bd_cons, bd_prod);
+		} else {
+			if (likely(bnx2x_alloc_rx_data(bp, fp, bd_prod) == 0)) {
 				dma_unmap_single(&bp->pdev->dev,
-					dma_unmap_addr(rx_buf, mapping),
+						 dma_unmap_addr(rx_buf, mapping),
 						 fp->rx_buf_size,
 						 DMA_FROM_DEVICE);
+				skb = build_skb(data);
+				if (unlikely(!skb)) {
+					kfree(data);
+					fp->eth_q_stats.rx_skb_alloc_failed++;
+					goto next_rx;
+				}
 				skb_reserve(skb, pad);
-				skb_put(skb, len);
-
 			} else {
 				DP(NETIF_MSG_RX_ERR,
 				   "ERROR  packet dropped because "
 				   "of alloc failure\n");
 				fp->eth_q_stats.rx_skb_alloc_failed++;
 reuse_rx:
-				bnx2x_reuse_rx_skb(fp, bd_cons, bd_prod);
+				bnx2x_reuse_rx_data(fp, bd_cons, bd_prod);
 				goto next_rx;
 			}
+		}
 
-			skb->protocol = eth_type_trans(skb, bp->dev);
+		skb_put(skb, len);
+		skb->protocol = eth_type_trans(skb, bp->dev);
 
-			/* Set Toeplitz hash for a none-LRO skb */
-			bnx2x_set_skb_rxhash(bp, cqe, skb);
+		/* Set Toeplitz hash for a none-LRO skb */
+		skb->rxhash = bnx2x_get_rxhash(bp, cqe_fp);
 
-			skb_checksum_none_assert(skb);
+		skb_checksum_none_assert(skb);
 
-			if (bp->dev->features & NETIF_F_RXCSUM) {
+		if (bp->dev->features & NETIF_F_RXCSUM) {
 
-				if (likely(BNX2X_RX_CSUM_OK(cqe)))
-					skb->ip_summed = CHECKSUM_UNNECESSARY;
-				else
-					fp->eth_q_stats.hw_csum_err++;
-			}
+			if (likely(BNX2X_RX_CSUM_OK(cqe)))
+				skb->ip_summed = CHECKSUM_UNNECESSARY;
+			else
+				fp->eth_q_stats.hw_csum_err++;
 		}
 
-		skb_record_rx_queue(skb, fp->index);
+		skb_record_rx_queue(skb, fp->rx_queue);
 
 		if (le16_to_cpu(cqe_fp->pars_flags.flags) &
 		    PARSING_FLAGS_VLAN)
@@ -765,7 +759,7 @@ reuse_rx:
 
 
 next_rx:
-		rx_buf->skb = NULL;
+		rx_buf->data = NULL;
 
 		bd_cons = NEXT_RX_IDX(bd_cons);
 		bd_prod = NEXT_RX_IDX(bd_prod);
@@ -1011,9 +1005,9 @@ void bnx2x_init_rx_rings(struct bnx2x *bp)
 				struct sw_rx_bd *first_buf =
 					&tpa_info->first_buf;
 
-				first_buf->skb = netdev_alloc_skb(bp->dev,
-						       fp->rx_buf_size);
-				if (!first_buf->skb) {
+				first_buf->data = kmalloc(fp->rx_buf_size + NET_SKB_PAD,
+							  GFP_ATOMIC);
+				if (!first_buf->data) {
 					BNX2X_ERR("Failed to allocate TPA "
 						  "skb pool for queue[%d] - "
 						  "disabling TPA on this "
@@ -1093,16 +1087,18 @@ static void bnx2x_free_tx_skbs(struct bnx2x *bp)
 		struct bnx2x_fastpath *fp = &bp->fp[i];
 		for_each_cos_in_tx_queue(fp, cos) {
 			struct bnx2x_fp_txdata *txdata = &fp->txdata[cos];
+			unsigned pkts_compl = 0, bytes_compl = 0;
 
-			u16 bd_cons = txdata->tx_bd_cons;
 			u16 sw_prod = txdata->tx_pkt_prod;
 			u16 sw_cons = txdata->tx_pkt_cons;
 
 			while (sw_cons != sw_prod) {
-				bd_cons = bnx2x_free_tx_pkt(bp, txdata,
-							    TX_BD(sw_cons));
+				bnx2x_free_tx_pkt(bp, txdata, TX_BD(sw_cons),
+				    &pkts_compl, &bytes_compl);
 				sw_cons++;
 			}
+			netdev_tx_reset_queue(
+			    netdev_get_tx_queue(bp->dev, txdata->txq_index));
 		}
 	}
 }
@@ -1118,16 +1114,16 @@ static void bnx2x_free_rx_bds(struct bnx2x_fastpath *fp)
 
 	for (i = 0; i < NUM_RX_BD; i++) {
 		struct sw_rx_bd *rx_buf = &fp->rx_buf_ring[i];
-		struct sk_buff *skb = rx_buf->skb;
+		u8 *data = rx_buf->data;
 
-		if (skb == NULL)
+		if (data == NULL)
 			continue;
 		dma_unmap_single(&bp->pdev->dev,
 				 dma_unmap_addr(rx_buf, mapping),
 				 fp->rx_buf_size, DMA_FROM_DEVICE);
 
-		rx_buf->skb = NULL;
-		dev_kfree_skb(skb);
+		rx_buf->data = NULL;
+		kfree(data);
 	}
 }
 
@@ -1445,6 +1441,11 @@ void bnx2x_set_num_queues(struct bnx2x *bp)
 		break;
 	}
 
+#ifdef BCM_CNIC
+	/* override in ISCSI SD mod */
+	if (IS_MF_ISCSI_SD(bp))
+		bp->num_queues = 1;
+#endif
 	/* Add special queues */
 	bp->num_queues += NON_ETH_CONTEXT_USE;
 }
@@ -1509,6 +1510,7 @@ static inline void bnx2x_set_rx_buf_size(struct bnx2x *bp)
 
 	for_each_queue(bp, i) {
 		struct bnx2x_fastpath *fp = &bp->fp[i];
+		u32 mtu;
 
 		/* Always use a mini-jumbo MTU for the FCoE L2 ring */
 		if (IS_FCOE_IDX(i))
@@ -1518,13 +1520,15 @@ static inline void bnx2x_set_rx_buf_size(struct bnx2x *bp)
 			 * IP_HEADER_ALIGNMENT_PADDING to prevent a buffer
 			 * overrun attack.
 			 */
-			fp->rx_buf_size =
-				BNX2X_FCOE_MINI_JUMBO_MTU + ETH_OVREHEAD +
-				BNX2X_FW_RX_ALIGN + IP_HEADER_ALIGNMENT_PADDING;
+			mtu = BNX2X_FCOE_MINI_JUMBO_MTU;
 		else
-			fp->rx_buf_size =
-				bp->dev->mtu + ETH_OVREHEAD +
-				BNX2X_FW_RX_ALIGN + IP_HEADER_ALIGNMENT_PADDING;
+			mtu = bp->dev->mtu;
+		fp->rx_buf_size = BNX2X_FW_RX_ALIGN_START +
+				  IP_HEADER_ALIGNMENT_PADDING +
+				  ETH_OVREHEAD +
+				  mtu +
+				  BNX2X_FW_RX_ALIGN_END;
+		/* Note : rx_buf_size doesnt take into account NET_SKB_PAD */
 	}
 }
 
@@ -1541,7 +1545,8 @@ static inline int bnx2x_init_rss_pf(struct bnx2x *bp)
 	if (bp->multi_mode != ETH_RSS_MODE_DISABLED) {
 		for (i = 0; i < sizeof(ind_table); i++)
 			ind_table[i] =
-				bp->fp->cl_id +	(i % num_eth_queues);
+				bp->fp->cl_id +
+				ethtool_rxfh_indir_default(i, num_eth_queues);
 	}
 
 	/*
@@ -1929,13 +1934,17 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
 		break;
 	}
 
-	if (!bp->port.pmf)
+	if (bp->port.pmf)
+		bnx2x_update_drv_flags(bp, DRV_FLAGS_DCB_CONFIGURED, 0);
+	else
 		bnx2x__link_status_update(bp);
 
 	/* start the timer */
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
 
 #ifdef BCM_CNIC
+	/* re-read iscsi info */
+	bnx2x_get_iscsi_info(bp);
 	bnx2x_setup_cnic_irq_info(bp);
 	if (bp->state == BNX2X_STATE_OPEN)
 		bnx2x_cnic_notify(bp, CNIC_CTL_START_CMD);
@@ -2799,6 +2808,7 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		mapping = skb_frag_dma_map(&bp->pdev->dev, frag, 0,
 					   skb_frag_size(frag), DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(&bp->pdev->dev, mapping))) {
+			unsigned int pkts_compl = 0, bytes_compl = 0;
 
 			DP(NETIF_MSG_TX_QUEUED, "Unable to map page - "
 						"dropping packet...\n");
@@ -2810,7 +2820,8 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 			 */
 			first_bd->nbd = cpu_to_le16(nbd);
 			bnx2x_free_tx_pkt(bp, txdata,
-					  TX_BD(txdata->tx_pkt_prod));
+					  TX_BD(txdata->tx_pkt_prod),
+					  &pkts_compl, &bytes_compl);
 			return NETDEV_TX_OK;
 		}
 
@@ -2871,6 +2882,8 @@ netdev_tx_t bnx2x_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		   pbd_e2->parsing_data);
 	DP(NETIF_MSG_TX_QUEUED, "doorbell: nbd %d  bd %u\n", nbd, bd_prod);
 
+	netdev_tx_sent_queue(txq, skb->len);
+
 	txdata->tx_pkt_prod++;
 	/*
 	 * Make sure that the BD data is updated before updating the producer
@@ -2981,9 +2994,14 @@ int bnx2x_change_mac_addr(struct net_device *dev, void *p)
 	struct bnx2x *bp = netdev_priv(dev);
 	int rc = 0;
 
-	if (!is_valid_ether_addr((u8 *)(addr->sa_data)))
+	if (!bnx2x_is_valid_ether_addr(bp, addr->sa_data))
 		return -EINVAL;
 
+#ifdef BCM_CNIC
+	if (IS_MF_ISCSI_SD(bp) && !is_zero_ether_addr(addr->sa_data))
+		return -EINVAL;
+#endif
+
 	if (netif_running(dev))  {
 		rc = bnx2x_set_eth_mac(bp, false);
 		if (rc)
@@ -3098,7 +3116,12 @@ static int bnx2x_alloc_fp_mem_at(struct bnx2x *bp, int index)
 	u8 cos;
 	int rx_ring_size = 0;
 
-	/* if rx_ring_size specified - use it */
+#ifdef BCM_CNIC
+	if (IS_MF_ISCSI_SD(bp)) {
+		rx_ring_size = MIN_RX_SIZE_NONTPA;
+		bp->rx_ring_size = rx_ring_size;
+	} else
+#endif
 	if (!bp->rx_ring_size) {
 
 		rx_ring_size = MAX_RX_AVAIL/BNX2X_NUM_RX_QUEUES(bp);
@@ -3108,7 +3131,7 @@ static int bnx2x_alloc_fp_mem_at(struct bnx2x *bp, int index)
 				     MIN_RX_SIZE_TPA, rx_ring_size);
 
 		bp->rx_ring_size = rx_ring_size;
-	} else
+	} else /* if rx_ring_size specified - use it */
 		rx_ring_size = bp->rx_ring_size;
 
 	/* Common */
@@ -3278,14 +3301,14 @@ int __devinit bnx2x_alloc_mem_bp(struct bnx2x *bp)
 	msix_table_size = bp->igu_sb_cnt + 1;
 
 	/* fp array: RSS plus CNIC related L2 queues */
-	fp = kzalloc((BNX2X_MAX_RSS_COUNT(bp) + NON_ETH_CONTEXT_USE) *
+	fp = kcalloc(BNX2X_MAX_RSS_COUNT(bp) + NON_ETH_CONTEXT_USE,
 		     sizeof(*fp), GFP_KERNEL);
 	if (!fp)
 		goto alloc_err;
 	bp->fp = fp;
 
 	/* msix table */
-	tbl = kzalloc(msix_table_size * sizeof(*tbl), GFP_KERNEL);
+	tbl = kcalloc(msix_table_size, sizeof(*tbl), GFP_KERNEL);
 	if (!tbl)
 		goto alloc_err;
 	bp->msix_table = tbl;
@@ -3409,7 +3432,8 @@ int bnx2x_change_mtu(struct net_device *dev, int new_mtu)
 	return bnx2x_reload_if_running(dev);
 }
 
-u32 bnx2x_fix_features(struct net_device *dev, u32 features)
+netdev_features_t bnx2x_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
@@ -3420,7 +3444,7 @@ u32 bnx2x_fix_features(struct net_device *dev, u32 features)
 	return features;
 }
 
-int bnx2x_set_features(struct net_device *dev, u32 features)
+int bnx2x_set_features(struct net_device *dev, netdev_features_t features)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	u32 flags = bp->flags;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index 283d663..bf27c54 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -20,6 +20,7 @@
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <linux/netdevice.h>
+#include <linux/etherdevice.h>
 
 
 #include "bnx2x.h"
@@ -533,8 +534,9 @@ int bnx2x_change_mtu(struct net_device *dev, int new_mtu);
  */
 int bnx2x_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type);
 #endif
-u32 bnx2x_fix_features(struct net_device *dev, u32 features);
-int bnx2x_set_features(struct net_device *dev, u32 features);
+netdev_features_t bnx2x_fix_features(struct net_device *dev,
+	netdev_features_t features);
+int bnx2x_set_features(struct net_device *dev, netdev_features_t features);
 
 /**
  * bnx2x_tx_timeout - tx timeout netdev callback
@@ -874,8 +876,7 @@ static inline void bnx2x_clear_sge_mask_next_elems(struct bnx2x_fastpath *fp)
 static inline void bnx2x_init_sge_ring_bit_mask(struct bnx2x_fastpath *fp)
 {
 	/* Set the mask to all 1-s: it's faster to compare to 0 than to 0xf-s */
-	memset(fp->sge_mask, 0xff,
-	       (NUM_RX_SGE >> BIT_VEC64_ELEM_SHIFT)*sizeof(u64));
+	memset(fp->sge_mask, 0xff, sizeof(fp->sge_mask));
 
 	/* Clear the two last indices in the page to 1:
 	   these are the indices that correspond to the "next" element,
@@ -911,26 +912,27 @@ static inline int bnx2x_alloc_rx_sge(struct bnx2x *bp,
 	return 0;
 }
 
-static inline int bnx2x_alloc_rx_skb(struct bnx2x *bp,
-				     struct bnx2x_fastpath *fp, u16 index)
+static inline int bnx2x_alloc_rx_data(struct bnx2x *bp,
+				      struct bnx2x_fastpath *fp, u16 index)
 {
-	struct sk_buff *skb;
+	u8 *data;
 	struct sw_rx_bd *rx_buf = &fp->rx_buf_ring[index];
 	struct eth_rx_bd *rx_bd = &fp->rx_desc_ring[index];
 	dma_addr_t mapping;
 
-	skb = netdev_alloc_skb(bp->dev, fp->rx_buf_size);
-	if (unlikely(skb == NULL))
+	data = kmalloc(fp->rx_buf_size + NET_SKB_PAD, GFP_ATOMIC);
+	if (unlikely(data == NULL))
 		return -ENOMEM;
 
-	mapping = dma_map_single(&bp->pdev->dev, skb->data, fp->rx_buf_size,
+	mapping = dma_map_single(&bp->pdev->dev, data + NET_SKB_PAD,
+				 fp->rx_buf_size,
 				 DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(&bp->pdev->dev, mapping))) {
-		dev_kfree_skb_any(skb);
+		kfree(data);
 		return -ENOMEM;
 	}
 
-	rx_buf->skb = skb;
+	rx_buf->data = data;
 	dma_unmap_addr_set(rx_buf, mapping, mapping);
 
 	rx_bd->addr_hi = cpu_to_le32(U64_HI(mapping));
@@ -939,12 +941,12 @@ static inline int bnx2x_alloc_rx_skb(struct bnx2x *bp,
 	return 0;
 }
 
-/* note that we are not allocating a new skb,
+/* note that we are not allocating a new buffer,
  * we are just moving one from cons to prod
  * we are not creating a new mapping,
  * so there is no need to check for dma_mapping_error().
  */
-static inline void bnx2x_reuse_rx_skb(struct bnx2x_fastpath *fp,
+static inline void bnx2x_reuse_rx_data(struct bnx2x_fastpath *fp,
 				      u16 cons, u16 prod)
 {
 	struct sw_rx_bd *cons_rx_buf = &fp->rx_buf_ring[cons];
@@ -954,7 +956,7 @@ static inline void bnx2x_reuse_rx_skb(struct bnx2x_fastpath *fp,
 
 	dma_unmap_addr_set(prod_rx_buf, mapping,
 			   dma_unmap_addr(cons_rx_buf, mapping));
-	prod_rx_buf->skb = cons_rx_buf->skb;
+	prod_rx_buf->data = cons_rx_buf->data;
 	*prod_bd = *cons_bd;
 }
 
@@ -1030,9 +1032,9 @@ static inline void bnx2x_free_tpa_pool(struct bnx2x *bp,
 	for (i = 0; i < last; i++) {
 		struct bnx2x_agg_info *tpa_info = &fp->tpa_info[i];
 		struct sw_rx_bd *first_buf = &tpa_info->first_buf;
-		struct sk_buff *skb = first_buf->skb;
+		u8 *data = first_buf->data;
 
-		if (skb == NULL) {
+		if (data == NULL) {
 			DP(NETIF_MSG_IFDOWN, "tpa bin %d empty on free\n", i);
 			continue;
 		}
@@ -1040,8 +1042,8 @@ static inline void bnx2x_free_tpa_pool(struct bnx2x *bp,
 			dma_unmap_single(&bp->pdev->dev,
 					 dma_unmap_addr(first_buf, mapping),
 					 fp->rx_buf_size, DMA_FROM_DEVICE);
-		dev_kfree_skb(skb);
-		first_buf->skb = NULL;
+		kfree(data);
+		first_buf->data = NULL;
 	}
 }
 
@@ -1149,7 +1151,7 @@ static inline int bnx2x_alloc_rx_bds(struct bnx2x_fastpath *fp,
 	 * fp->eth_q_stats.rx_skb_alloc_failed = 0
 	 */
 	for (i = 0; i < rx_ring_size; i++) {
-		if (bnx2x_alloc_rx_skb(bp, fp, ring_prod) < 0) {
+		if (bnx2x_alloc_rx_data(bp, fp, ring_prod) < 0) {
 			fp->eth_q_stats.rx_skb_alloc_failed++;
 			continue;
 		}
@@ -1318,6 +1320,7 @@ static inline void bnx2x_init_fcoe_fp(struct bnx2x *bp)
 	struct bnx2x_fastpath *fp = bnx2x_fcoe_fp(bp);
 	unsigned long q_type = 0;
 
+	bnx2x_fcoe(bp, rx_queue) = BNX2X_NUM_ETH_QUEUES(bp);
 	bnx2x_fcoe(bp, cl_id) = bnx2x_cnic_eth_cl_id(bp,
 						     BNX2X_FCOE_ETH_CL_ID_IDX);
 	/** Current BNX2X_FCOE_ETH_CID deffinition implies not more than
@@ -1488,4 +1491,77 @@ static inline u16 bnx2x_extract_max_cfg(struct bnx2x *bp, u32 mf_cfg)
 	return max_cfg;
 }
 
+/**
+ * bnx2x_get_iscsi_info - update iSCSI params according to licensing info.
+ *
+ * @bp:		driver handle
+ *
+ */
+void bnx2x_get_iscsi_info(struct bnx2x *bp);
+
+/* returns func by VN for current port */
+static inline int func_by_vn(struct bnx2x *bp, int vn)
+{
+	return 2 * vn + BP_PORT(bp);
+}
+
+/**
+ * bnx2x_link_sync_notify - send notification to other functions.
+ *
+ * @bp:		driver handle
+ *
+ */
+static inline void bnx2x_link_sync_notify(struct bnx2x *bp)
+{
+	int func;
+	int vn;
+
+	/* Set the attention towards other drivers on the same port */
+	for (vn = VN_0; vn < BP_MAX_VN_NUM(bp); vn++) {
+		if (vn == BP_VN(bp))
+			continue;
+
+		func = func_by_vn(bp, vn);
+		REG_WR(bp, MISC_REG_AEU_GENERAL_ATTN_0 +
+		       (LINK_SYNC_ATTENTION_BIT_FUNC_0 + func)*4, 1);
+	}
+}
+
+/**
+ * bnx2x_update_drv_flags - update flags in shmem
+ *
+ * @bp:		driver handle
+ * @flags:	flags to update
+ * @set:	set or clear
+ *
+ */
+static inline void bnx2x_update_drv_flags(struct bnx2x *bp, u32 flags, u32 set)
+{
+	if (SHMEM2_HAS(bp, drv_flags)) {
+		u32 drv_flags;
+		bnx2x_acquire_hw_lock(bp, HW_LOCK_DRV_FLAGS);
+		drv_flags = SHMEM2_RD(bp, drv_flags);
+
+		if (set)
+			SET_FLAGS(drv_flags, flags);
+		else
+			RESET_FLAGS(drv_flags, flags);
+
+		SHMEM2_WR(bp, drv_flags, drv_flags);
+		DP(NETIF_MSG_HW, "drv_flags 0x%08x\n", drv_flags);
+		bnx2x_release_hw_lock(bp, HW_LOCK_DRV_FLAGS);
+	}
+}
+
+static inline bool bnx2x_is_valid_ether_addr(struct bnx2x *bp, u8 *addr)
+{
+	if (is_valid_ether_addr(addr))
+		return true;
+#ifdef BCM_CNIC
+	if (is_zero_ether_addr(addr) && IS_MF_ISCSI_SD(bp))
+		return true;
+#endif
+	return false;
+}
+
 #endif /* BNX2X_CMN_H */
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
index 51bd748..5051cf3 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.c
@@ -685,24 +685,6 @@ int bnx2x_dcbnl_update_applist(struct bnx2x *bp, bool delall)
 }
 #endif
 
-static inline void bnx2x_update_drv_flags(struct bnx2x *bp, u32 flags, u32 set)
-{
-	if (SHMEM2_HAS(bp, drv_flags)) {
-		u32 drv_flags;
-		bnx2x_acquire_hw_lock(bp, HW_LOCK_DRV_FLAGS);
-		drv_flags = SHMEM2_RD(bp, drv_flags);
-
-		if (set)
-			SET_FLAGS(drv_flags, flags);
-		else
-			RESET_FLAGS(drv_flags, flags);
-
-		SHMEM2_WR(bp, drv_flags, drv_flags);
-		DP(NETIF_MSG_HW, "drv_flags 0x%08x\n", drv_flags);
-		bnx2x_release_hw_lock(bp, HW_LOCK_DRV_FLAGS);
-	}
-}
-
 static inline void bnx2x_dcbx_update_tc_mapping(struct bnx2x *bp)
 {
 	u8 prio, cos;
@@ -755,18 +737,26 @@ void bnx2x_dcbx_set_params(struct bnx2x *bp, u32 state)
 			/* mark DCBX result for PMF migration */
 			bnx2x_update_drv_flags(bp, DRV_FLAGS_DCB_CONFIGURED, 1);
 #ifdef BCM_DCBNL
-			/**
+			/*
 			 * Add new app tlvs to dcbnl
 			 */
 			bnx2x_dcbnl_update_applist(bp, false);
 #endif
-			bnx2x_dcbx_stop_hw_tx(bp);
-
-			/* reconfigure the netdevice with the results of the new
+			/*
+			 * reconfigure the netdevice with the results of the new
 			 * dcbx negotiation.
 			 */
 			bnx2x_dcbx_update_tc_mapping(bp);
 
+			/*
+			 * allow other funtions to update their netdevices
+			 * accordingly
+			 */
+			if (IS_MF(bp))
+				bnx2x_link_sync_notify(bp);
+
+			bnx2x_dcbx_stop_hw_tx(bp);
+
 			return;
 		}
 	case BNX2X_DCBX_STATE_TX_PAUSED:
@@ -775,6 +765,7 @@ void bnx2x_dcbx_set_params(struct bnx2x *bp, u32 state)
 
 		bnx2x_dcbx_update_ets_params(bp);
 		bnx2x_dcbx_resume_hw_tx(bp);
+
 		return;
 	case BNX2X_DCBX_STATE_TX_RELEASED:
 		DP(NETIF_MSG_LINK, "BNX2X_DCBX_STATE_TX_RELEASED\n");
@@ -883,7 +874,7 @@ static void bnx2x_dcbx_admin_mib_updated_params(struct bnx2x *bp,
 		/*For IEEE admin_recommendation_bw_precentage
 		 *For IEEE admin_recommendation_ets_pg */
 		af->pfc.pri_en_bitmap = (u8)dp->admin_pfc_bitmap;
-		for (i = 0; i < 4; i++) {
+		for (i = 0; i < DCBX_CONFIG_MAX_APP_PROTOCOL; i++) {
 			if (dp->admin_priority_app_table[i].valid) {
 				struct bnx2x_admin_priority_app_table *table =
 					dp->admin_priority_app_table;
@@ -923,7 +914,7 @@ static void bnx2x_dcbx_admin_mib_updated_params(struct bnx2x *bp,
 
 void bnx2x_dcbx_set_state(struct bnx2x *bp, bool dcb_on, u32 dcbx_enabled)
 {
-	if (!CHIP_IS_E1x(bp) && !CHIP_IS_E3(bp)) {
+	if (!CHIP_IS_E1x(bp)) {
 		bp->dcb_state = dcb_on;
 		bp->dcbx_enabled = dcbx_enabled;
 	} else {
@@ -1863,7 +1854,7 @@ static void bnx2x_dcbx_fw_struct(struct bnx2x *bp,
 void bnx2x_dcbx_pmf_update(struct bnx2x *bp)
 {
 	/* if we need to syncronize DCBX result from prev PMF
-	 * read it from shmem and update bp accordingly
+	 * read it from shmem and update bp and netdev accordingly
 	 */
 	if (SHMEM2_HAS(bp, drv_flags) &&
 	   GET_FLAGS(SHMEM2_RD(bp, drv_flags), DRV_FLAGS_DCB_CONFIGURED)) {
@@ -1875,6 +1866,22 @@ void bnx2x_dcbx_pmf_update(struct bnx2x *bp)
 					  bp->dcbx_error);
 		bnx2x_get_dcbx_drv_param(bp, &bp->dcbx_local_feat,
 					 bp->dcbx_error);
+#ifdef BCM_DCBNL
+		/*
+		 * Add new app tlvs to dcbnl
+		 */
+		bnx2x_dcbnl_update_applist(bp, false);
+		/*
+		 * Send a notification for the new negotiated parameters
+		 */
+		dcbnl_cee_notify(bp->dev, RTM_GETDCB, DCB_CMD_CEE_GET, 0, 0);
+#endif
+		/*
+		 * reconfigure the netdevice with the results of the new
+		 * dcbx negotiation.
+		 */
+		bnx2x_dcbx_update_tc_mapping(bp);
+
 	}
 }
 
@@ -2242,7 +2249,7 @@ static int bnx2x_set_admin_app_up(struct bnx2x *bp, u8 idtype, u16 idval, u8 up)
 	int i, ff;
 
 	/* iterate over the app entries looking for idtype and idval */
-	for (i = 0, ff = -1; i < 4; i++) {
+	for (i = 0, ff = -1; i < DCBX_CONFIG_MAX_APP_PROTOCOL; i++) {
 		struct bnx2x_admin_priority_app_table *app_ent =
 			&bp->dcbx_config_params.admin_priority_app_table[i];
 		if (bnx2x_admin_app_is_equal(app_ent, idtype, idval))
@@ -2251,7 +2258,7 @@ static int bnx2x_set_admin_app_up(struct bnx2x *bp, u8 idtype, u16 idval, u8 up)
 		if (ff < 0 && !app_ent->valid)
 			ff = i;
 	}
-	if (i < 4)
+	if (i < DCBX_CONFIG_MAX_APP_PROTOCOL)
 		/* if found overwrite up */
 		bp->dcbx_config_params.
 			admin_priority_app_table[i].priority = up;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h
index 2c6a3bc..2ab9254 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_dcb.h
@@ -90,6 +90,7 @@ struct bnx2x_admin_priority_app_table {
 		u32 app_id;
 };
 
+#define DCBX_CONFIG_MAX_APP_PROTOCOL 4
 struct bnx2x_config_dcbx_params {
 	u32 overwrite_settings;
 	u32 admin_dcbx_version;
@@ -109,7 +110,8 @@ struct bnx2x_config_dcbx_params {
 	u32 admin_recommendation_bw_precentage[8];
 	u32 admin_recommendation_ets_pg[8];
 	u32 admin_pfc_bitmap;
-	struct bnx2x_admin_priority_app_table admin_priority_app_table[4];
+	struct bnx2x_admin_priority_app_table
+		admin_priority_app_table[DCBX_CONFIG_MAX_APP_PROTOCOL];
 	u32 admin_default_priority;
 };
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index f0ca8b2..a688b9d 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -107,6 +107,10 @@ static const struct {
 				4, STATS_FLAGS_PORT, "rx_filtered_packets" },
 	{ STATS_OFFSET32(mf_tag_discard),
 				4, STATS_FLAGS_PORT, "rx_mf_tag_discard" },
+	{ STATS_OFFSET32(pfc_frames_received_hi),
+				8, STATS_FLAGS_PORT, "pfc_frames_received" },
+	{ STATS_OFFSET32(pfc_frames_sent_hi),
+				8, STATS_FLAGS_PORT, "pfc_frames_sent" },
 	{ STATS_OFFSET32(brb_drop_hi),
 				8, STATS_FLAGS_PORT, "rx_brb_discard" },
 	{ STATS_OFFSET32(brb_truncate_hi),
@@ -352,7 +356,7 @@ static int bnx2x_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 		DP(NETIF_MSG_LINK, "Unsupported port type\n");
 		return -EINVAL;
 	}
-	/* Save new config in case command complete successuly */
+	/* Save new config in case command complete successully */
 	new_multi_phy_config = bp->link_params.multi_phy_config;
 	/* Get the new cfg_idx */
 	cfg_idx = bnx2x_get_link_cfg_idx(bp);
@@ -761,8 +765,8 @@ static void bnx2x_get_drvinfo(struct net_device *dev,
 	struct bnx2x *bp = netdev_priv(dev);
 	u8 phy_fw_ver[PHY_FW_VER_LEN];
 
-	strcpy(info->driver, DRV_MODULE_NAME);
-	strcpy(info->version, DRV_MODULE_VERSION);
+	strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
 
 	phy_fw_ver[0] = '\0';
 	if (bp->port.pmf) {
@@ -773,14 +777,14 @@ static void bnx2x_get_drvinfo(struct net_device *dev,
 		bnx2x_release_phy_lock(bp);
 	}
 
-	strncpy(info->fw_version, bp->fw_ver, 32);
+	strlcpy(info->fw_version, bp->fw_ver, sizeof(info->fw_version));
 	snprintf(info->fw_version + strlen(bp->fw_ver), 32 - strlen(bp->fw_ver),
 		 "bc %d.%d.%d%s%s",
 		 (bp->common.bc_ver & 0xff0000) >> 16,
 		 (bp->common.bc_ver & 0xff00) >> 8,
 		 (bp->common.bc_ver & 0xff),
 		 ((phy_fw_ver[0] != '\0') ? " phy " : ""), phy_fw_ver);
-	strcpy(info->bus_info, pci_name(bp->pdev));
+	strlcpy(info->bus_info, pci_name(bp->pdev), sizeof(info->bus_info));
 	info->n_stats = BNX2X_NUM_STATS;
 	info->testinfo_len = BNX2X_NUM_TESTS;
 	info->eedump_len = bp->common.flash_size;
@@ -1740,6 +1744,8 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode)
 	struct sw_rx_bd *rx_buf;
 	u16 len;
 	int rc = -ENODEV;
+	u8 *data;
+	struct netdev_queue *txq = netdev_get_tx_queue(bp->dev, txdata->txq_index);
 
 	/* check the loopback mode */
 	switch (loopback_mode) {
@@ -1748,8 +1754,18 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode)
 			return -EINVAL;
 		break;
 	case BNX2X_MAC_LOOPBACK:
-		bp->link_params.loopback_mode = CHIP_IS_E3(bp) ?
-						LOOPBACK_XMAC : LOOPBACK_BMAC;
+		if (CHIP_IS_E3(bp)) {
+			int cfg_idx = bnx2x_get_link_cfg_idx(bp);
+			if (bp->port.supported[cfg_idx] &
+			    (SUPPORTED_10000baseT_Full |
+			     SUPPORTED_20000baseMLD2_Full |
+			     SUPPORTED_20000baseKR2_Full))
+				bp->link_params.loopback_mode = LOOPBACK_XMAC;
+			else
+				bp->link_params.loopback_mode = LOOPBACK_UMAC;
+		} else
+			bp->link_params.loopback_mode = LOOPBACK_BMAC;
+
 		bnx2x_phy_init(&bp->link_params, &bp->link_vars);
 		break;
 	default:
@@ -1784,6 +1800,8 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode)
 	tx_start_idx = le16_to_cpu(*txdata->tx_cons_sb);
 	rx_start_idx = le16_to_cpu(*fp_rx->rx_cons_sb);
 
+	netdev_tx_sent_queue(txq, skb->len);
+
 	pkt_prod = txdata->tx_pkt_prod++;
 	tx_buf = &txdata->tx_buf_ring[TX_BD(pkt_prod)];
 	tx_buf->first_bd = txdata->tx_bd_prod;
@@ -1865,10 +1883,9 @@ static int bnx2x_run_loopback(struct bnx2x *bp, int loopback_mode)
 	dma_sync_single_for_cpu(&bp->pdev->dev,
 				   dma_unmap_addr(rx_buf, mapping),
 				   fp_rx->rx_buf_size, DMA_FROM_DEVICE);
-	skb = rx_buf->skb;
-	skb_reserve(skb, cqe->fast_path_cqe.placement_offset);
+	data = rx_buf->data + NET_SKB_PAD + cqe->fast_path_cqe.placement_offset;
 	for (i = ETH_HLEN; i < pkt_size; i++)
-		if (*(skb->data + i) != (unsigned char) (i & 0xff))
+		if (*(data + i) != (unsigned char) (i & 0xff))
 			goto test_loopback_rx_exit;
 
 	rc = 0;
@@ -2285,18 +2302,20 @@ static int bnx2x_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info,
 	}
 }
 
-static int bnx2x_get_rxfh_indir(struct net_device *dev,
-				struct ethtool_rxfh_indir *indir)
+static u32 bnx2x_get_rxfh_indir_size(struct net_device *dev)
+{
+	struct bnx2x *bp = netdev_priv(dev);
+
+	return (bp->multi_mode == ETH_RSS_MODE_DISABLED ?
+		0 : T_ETH_INDIRECTION_TABLE_SIZE);
+}
+
+static int bnx2x_get_rxfh_indir(struct net_device *dev, u32 *indir)
 {
 	struct bnx2x *bp = netdev_priv(dev);
-	size_t copy_size =
-		min_t(size_t, indir->size, T_ETH_INDIRECTION_TABLE_SIZE);
 	u8 ind_table[T_ETH_INDIRECTION_TABLE_SIZE] = {0};
 	size_t i;
 
-	if (bp->multi_mode == ETH_RSS_MODE_DISABLED)
-		return -EOPNOTSUPP;
-
 	/* Get the current configuration of the RSS indirection table */
 	bnx2x_get_rss_ind_table(&bp->rss_conf_obj, ind_table);
 
@@ -2309,33 +2328,19 @@ static int bnx2x_get_rxfh_indir(struct net_device *dev,
 	 * align the returned table to the Client ID of the leading RSS
 	 * queue.
 	 */
-	for (i = 0; i < copy_size; i++)
-		indir->ring_index[i] = ind_table[i] - bp->fp->cl_id;
-
-	indir->size = T_ETH_INDIRECTION_TABLE_SIZE;
+	for (i = 0; i < T_ETH_INDIRECTION_TABLE_SIZE; i++)
+		indir[i] = ind_table[i] - bp->fp->cl_id;
 
 	return 0;
 }
 
-static int bnx2x_set_rxfh_indir(struct net_device *dev,
-				const struct ethtool_rxfh_indir *indir)
+static int bnx2x_set_rxfh_indir(struct net_device *dev, const u32 *indir)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 	size_t i;
 	u8 ind_table[T_ETH_INDIRECTION_TABLE_SIZE] = {0};
-	u32 num_eth_queues = BNX2X_NUM_ETH_QUEUES(bp);
-
-	if (bp->multi_mode == ETH_RSS_MODE_DISABLED)
-		return -EOPNOTSUPP;
-
-	/* validate the size */
-	if (indir->size != T_ETH_INDIRECTION_TABLE_SIZE)
-		return -EINVAL;
 
 	for (i = 0; i < T_ETH_INDIRECTION_TABLE_SIZE; i++) {
-		/* validate the indices */
-		if (indir->ring_index[i] >= num_eth_queues)
-			return -EINVAL;
 		/*
 		 * The same as in bnx2x_get_rxfh_indir: we can't use a memcpy()
 		 * as an internal storage of an indirection table is a u8 array
@@ -2345,7 +2350,7 @@ static int bnx2x_set_rxfh_indir(struct net_device *dev,
 		 * align the received table to the Client ID of the leading RSS
 		 * queue
 		 */
-		ind_table[i] = indir->ring_index[i] + bp->fp->cl_id;
+		ind_table[i] = indir[i] + bp->fp->cl_id;
 	}
 
 	return bnx2x_config_rss_pf(bp, ind_table, false);
@@ -2378,6 +2383,7 @@ static const struct ethtool_ops bnx2x_ethtool_ops = {
 	.set_phys_id		= bnx2x_set_phys_id,
 	.get_ethtool_stats	= bnx2x_get_ethtool_stats,
 	.get_rxnfc		= bnx2x_get_rxnfc,
+	.get_rxfh_indir_size	= bnx2x_get_rxfh_indir_size,
 	.get_rxfh_indir		= bnx2x_get_rxfh_indir,
 	.set_rxfh_indir		= bnx2x_set_rxfh_indir,
 };
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
index fc754cb..3e30c86 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_hsi.h
@@ -1247,11 +1247,14 @@ struct drv_func_mb {
 	#define DRV_MSG_CODE_VRFY_SPECIFIC_PHY_OPT_MDL  0xa1000000
 	#define REQ_BC_VER_4_VRFY_SPECIFIC_PHY_OPT_MDL  0x00050234
 	#define REQ_BC_VER_4_SFP_TX_DISABLE_SUPPORTED   0x00070014
+	#define REQ_BC_VER_4_PFC_STATS_SUPPORTED        0x00070201
 
 	#define DRV_MSG_CODE_DCBX_ADMIN_PMF_MSG         0xb0000000
 	#define DRV_MSG_CODE_DCBX_PMF_DRV_OK            0xb2000000
 
 	#define DRV_MSG_CODE_VF_DISABLED_DONE           0xc0000000
+	#define DRV_MSG_CODE_DRV_INFO_ACK               0xd8000000
+	#define DRV_MSG_CODE_DRV_INFO_NACK              0xd9000000
 
 	#define DRV_MSG_CODE_SET_MF_BW                  0xe0000000
 	#define REQ_BC_VER_4_SET_MF_BW                  0x00060202
@@ -1304,6 +1307,8 @@ struct drv_func_mb {
 	#define FW_MSG_CODE_VRFY_OPT_MDL_INVLD_IMG      0xa0200000
 	#define FW_MSG_CODE_VRFY_OPT_MDL_UNAPPROVED     0xa0300000
 	#define FW_MSG_CODE_VF_DISABLED_DONE            0xb0000000
+	#define FW_MSG_CODE_DRV_INFO_ACK                0xd8100000
+	#define FW_MSG_CODE_DRV_INFO_NACK               0xd9100000
 
 	#define FW_MSG_CODE_SET_MF_BW_SENT              0xe0000000
 	#define FW_MSG_CODE_SET_MF_BW_DONE              0xe1000000
@@ -1360,6 +1365,7 @@ struct drv_func_mb {
 
 	#define DRV_STATUS_DCBX_EVENT_MASK              0x000f0000
 	#define DRV_STATUS_DCBX_NEGOTIATION_RESULTS     0x00010000
+	#define DRV_STATUS_DRV_INFO_REQ                 0x04000000
 
 	u32 virt_mac_upper;
 	#define VIRT_MAC_SIGN_MASK                      0xffff0000
@@ -1964,9 +1970,38 @@ struct shmem2_region {
 	u32 extended_dev_info_shared_addr;
 	u32 ncsi_oem_data_addr;
 
-	u32 ocsd_host_addr;
-	u32 ocbb_host_addr;
-	u32 ocsd_req_update_interval;
+	u32 ocsd_host_addr; /* initialized by option ROM */
+	u32 ocbb_host_addr; /* initialized by option ROM */
+	u32 ocsd_req_update_interval; /* initialized by option ROM */
+	u32 temperature_in_half_celsius;
+	u32 glob_struct_in_host;
+
+	u32 dcbx_neg_res_ext_offset;
+#define SHMEM_DCBX_NEG_RES_EXT_NONE			0x00000000
+
+	u32 drv_capabilities_flag[E2_FUNC_MAX];
+#define DRV_FLAGS_CAPABILITIES_LOADED_SUPPORTED 0x00000001
+#define DRV_FLAGS_CAPABILITIES_LOADED_L2        0x00000002
+#define DRV_FLAGS_CAPABILITIES_LOADED_FCOE      0x00000004
+#define DRV_FLAGS_CAPABILITIES_LOADED_ISCSI     0x00000008
+
+	u32 extended_dev_info_shared_cfg_size;
+
+	u32 dcbx_en[PORT_MAX];
+
+	/* The offset points to the multi threaded meta structure */
+	u32 multi_thread_data_offset;
+
+	/* address of DMAable host address holding values from the drivers */
+	u32 drv_info_host_addr_lo;
+	u32 drv_info_host_addr_hi;
+
+	/* general values written by the MFW (such as current version) */
+	u32 drv_info_control;
+#define DRV_INFO_CONTROL_VER_MASK          0x000000ff
+#define DRV_INFO_CONTROL_VER_SHIFT         0
+#define DRV_INFO_CONTROL_OP_CODE_MASK      0x0000ff00
+#define DRV_INFO_CONTROL_OP_CODE_SHIFT     8
 };
 
 
@@ -2501,14 +2536,18 @@ struct mac_stx {
 #define MAC_STX_IDX_MAX                     2
 
 struct host_port_stats {
-	u32            host_port_stats_start;
+	u32            host_port_stats_counter;
 
 	struct mac_stx mac_stx[MAC_STX_IDX_MAX];
 
 	u32            brb_drop_hi;
 	u32            brb_drop_lo;
 
-	u32            host_port_stats_end;
+	u32            not_used; /* obsolete */
+	u32            pfc_frames_tx_hi;
+	u32            pfc_frames_tx_lo;
+	u32            pfc_frames_rx_hi;
+	u32            pfc_frames_rx_lo;
 };
 
 
@@ -2548,6 +2587,118 @@ struct host_func_stats {
 /* VIC definitions */
 #define VICSTATST_UIF_INDEX 2
 
+/* current drv_info version */
+#define DRV_INFO_CUR_VER 1
+
+/* drv_info op codes supported */
+enum drv_info_opcode {
+	ETH_STATS_OPCODE,
+	FCOE_STATS_OPCODE,
+	ISCSI_STATS_OPCODE
+};
+
+#define ETH_STAT_INFO_VERSION_LEN	12
+/*  Per PCI Function Ethernet Statistics required from the driver */
+struct eth_stats_info {
+	/* Function's Driver Version. padded to 12 */
+	u8 version[ETH_STAT_INFO_VERSION_LEN];
+	/* Locally Admin Addr. BigEndian EIU48. Actual size is 6 bytes */
+	u8 mac_local[8];
+	u8 mac_add1[8];		/* Additional Programmed MAC Addr 1. */
+	u8 mac_add2[8];		/* Additional Programmed MAC Addr 2. */
+	u32 mtu_size;		/* MTU Size. Note   : Negotiated MTU */
+	u32 feature_flags;	/* Feature_Flags. */
+#define FEATURE_ETH_CHKSUM_OFFLOAD_MASK		0x01
+#define FEATURE_ETH_LSO_MASK			0x02
+#define FEATURE_ETH_BOOTMODE_MASK		0x1C
+#define FEATURE_ETH_BOOTMODE_SHIFT		2
+#define FEATURE_ETH_BOOTMODE_NONE		(0x0 << 2)
+#define FEATURE_ETH_BOOTMODE_PXE		(0x1 << 2)
+#define FEATURE_ETH_BOOTMODE_ISCSI		(0x2 << 2)
+#define FEATURE_ETH_BOOTMODE_FCOE		(0x3 << 2)
+#define FEATURE_ETH_TOE_MASK			0x20
+	u32 lso_max_size;	/* LSO MaxOffloadSize. */
+	u32 lso_min_seg_cnt;	/* LSO MinSegmentCount. */
+	/* Num Offloaded Connections TCP_IPv4. */
+	u32 ipv4_ofld_cnt;
+	/* Num Offloaded Connections TCP_IPv6. */
+	u32 ipv6_ofld_cnt;
+	u32 promiscuous_mode;	/* Promiscuous Mode. non-zero true */
+	u32 txq_size;		/* TX Descriptors Queue Size */
+	u32 rxq_size;		/* RX Descriptors Queue Size */
+	/* TX Descriptor Queue Avg Depth. % Avg Queue Depth since last poll */
+	u32 txq_avg_depth;
+	/* RX Descriptors Queue Avg Depth. % Avg Queue Depth since last poll */
+	u32 rxq_avg_depth;
+	/* IOV_Offload. 0=none; 1=MultiQueue, 2=VEB 3= VEPA*/
+	u32 iov_offload;
+	/* Number of NetQueue/VMQ Config'd. */
+	u32 netq_cnt;
+	u32 vf_cnt;		/* Num VF assigned to this PF. */
+};
+
+/*  Per PCI Function FCOE Statistics required from the driver */
+struct fcoe_stats_info {
+	u8 version[12];		/* Function's Driver Version. */
+	u8 mac_local[8];	/* Locally Admin Addr. */
+	u8 mac_add1[8];		/* Additional Programmed MAC Addr 1. */
+	u8 mac_add2[8];		/* Additional Programmed MAC Addr 2. */
+	/* QoS Priority (per 802.1p). 0-7255 */
+	u32 qos_priority;
+	u32 txq_size;		/* FCoE TX Descriptors Queue Size. */
+	u32 rxq_size;		/* FCoE RX Descriptors Queue Size. */
+	/* FCoE TX Descriptor Queue Avg Depth. */
+	u32 txq_avg_depth;
+	/* FCoE RX Descriptors Queue Avg Depth. */
+	u32 rxq_avg_depth;
+	u32 rx_frames_lo;	/* FCoE RX Frames received. */
+	u32 rx_frames_hi;	/* FCoE RX Frames received. */
+	u32 rx_bytes_lo;	/* FCoE RX Bytes received. */
+	u32 rx_bytes_hi;	/* FCoE RX Bytes received. */
+	u32 tx_frames_lo;	/* FCoE TX Frames sent. */
+	u32 tx_frames_hi;	/* FCoE TX Frames sent. */
+	u32 tx_bytes_lo;	/* FCoE TX Bytes sent. */
+	u32 tx_bytes_hi;	/* FCoE TX Bytes sent. */
+};
+
+/* Per PCI  Function iSCSI Statistics required from the driver*/
+struct iscsi_stats_info {
+	u8 version[12];		/* Function's Driver Version. */
+	u8 mac_local[8];	/* Locally Admin iSCSI MAC Addr. */
+	u8 mac_add1[8];		/* Additional Programmed MAC Addr 1. */
+	/* QoS Priority (per 802.1p). 0-7255 */
+	u32 qos_priority;
+	u8 initiator_name[64];	/* iSCSI Boot Initiator Node name. */
+	u8 ww_port_name[64];	/* iSCSI World wide port name */
+	u8 boot_target_name[64];/* iSCSI Boot Target Name. */
+	u8 boot_target_ip[16];	/* iSCSI Boot Target IP. */
+	u32 boot_target_portal;	/* iSCSI Boot Target Portal. */
+	u8 boot_init_ip[16];	/* iSCSI Boot Initiator IP Address. */
+	u32 max_frame_size;	/* Max Frame Size. bytes */
+	u32 txq_size;		/* PDU TX Descriptors Queue Size. */
+	u32 rxq_size;		/* PDU RX Descriptors Queue Size. */
+	u32 txq_avg_depth;	/* PDU TX Descriptor Queue Avg Depth. */
+	u32 rxq_avg_depth;	/* PDU RX Descriptors Queue Avg Depth. */
+	u32 rx_pdus_lo;		/* iSCSI PDUs received. */
+	u32 rx_pdus_hi;		/* iSCSI PDUs received. */
+	u32 rx_bytes_lo;	/* iSCSI RX Bytes received. */
+	u32 rx_bytes_hi;	/* iSCSI RX Bytes received. */
+	u32 tx_pdus_lo;		/* iSCSI PDUs sent. */
+	u32 tx_pdus_hi;		/* iSCSI PDUs sent. */
+	u32 tx_bytes_lo;	/* iSCSI PDU TX Bytes sent. */
+	u32 tx_bytes_hi;	/* iSCSI PDU TX Bytes sent. */
+	u32 pcp_prior_map_tbl;	/* C-PCP to S-PCP Priority MapTable.
+				 * 9 nibbles, the position of each nibble
+				 * represents the C-PCP value, the value
+				 * of the nibble = S-PCP value.
+				 */
+};
+
+union drv_info_to_mcp {
+	struct eth_stats_info	ether_stat;
+	struct fcoe_stats_info	fcoe_stat;
+	struct iscsi_stats_info	iscsi_stat;
+};
 #define BCM_5710_FW_MAJOR_VERSION			7
 #define BCM_5710_FW_MINOR_VERSION			0
 #define BCM_5710_FW_REVISION_VERSION		29
@@ -4161,8 +4312,62 @@ struct ustorm_eth_rx_producers {
 
 
 /*
- * cfc delete event data
+ * FCoE RX statistics parameters section#0
  */
+struct fcoe_rx_stat_params_section0 {
+	__le32 fcoe_rx_pkt_cnt;
+	__le32 fcoe_rx_byte_cnt;
+};
+
+
+/*
+ * FCoE RX statistics parameters section#1
+ */
+struct fcoe_rx_stat_params_section1 {
+	__le32 fcoe_ver_cnt;
+	__le32 fcoe_rx_drop_pkt_cnt;
+};
+
+
+/*
+ * FCoE RX statistics parameters section#2
+ */
+struct fcoe_rx_stat_params_section2 {
+	__le32 fc_crc_cnt;
+	__le32 eofa_del_cnt;
+	__le32 miss_frame_cnt;
+	__le32 seq_timeout_cnt;
+	__le32 drop_seq_cnt;
+	__le32 fcoe_rx_drop_pkt_cnt;
+	__le32 fcp_rx_pkt_cnt;
+	__le32 reserved0;
+};
+
+
+/*
+ * FCoE TX statistics parameters
+ */
+struct fcoe_tx_stat_params {
+	__le32 fcoe_tx_pkt_cnt;
+	__le32 fcoe_tx_byte_cnt;
+	__le32 fcp_tx_pkt_cnt;
+	__le32 reserved0;
+};
+
+/*
+ * FCoE statistics parameters
+ */
+struct fcoe_statistics_params {
+	struct fcoe_tx_stat_params tx_stat;
+	struct fcoe_rx_stat_params_section0 rx_stat0;
+	struct fcoe_rx_stat_params_section1 rx_stat1;
+	struct fcoe_rx_stat_params_section2 rx_stat2;
+};
+
+
+/*
+ * cfc delete event data
+*/
 struct cfc_del_event_data {
 	u32 cid;
 	u32 reserved0;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index bce203f..4df9505 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -27,7 +27,6 @@
 #include "bnx2x.h"
 #include "bnx2x_cmn.h"
 
-
 /********************************************************/
 #define ETH_HLEN			14
 /* L2 header size + 2*VLANs (8 bytes) + LLC SNAP (8 bytes) */
@@ -163,6 +162,11 @@
 #define EDC_MODE_LIMITING				0x0044
 #define EDC_MODE_PASSIVE_DAC			0x0055
 
+/* BRB default for class 0 E2 */
+#define DEFAULT0_E2_BRB_MAC_PAUSE_XOFF_THR	170
+#define DEFAULT0_E2_BRB_MAC_PAUSE_XON_THR		250
+#define DEFAULT0_E2_BRB_MAC_FULL_XOFF_THR		10
+#define DEFAULT0_E2_BRB_MAC_FULL_XON_THR		50
 
 /* BRB thresholds for E2*/
 #define PFC_E2_BRB_MAC_PAUSE_XOFF_THR_PAUSE		170
@@ -177,6 +181,12 @@
 #define PFC_E2_BRB_MAC_FULL_XON_THR_PAUSE			50
 #define PFC_E2_BRB_MAC_FULL_XON_THR_NON_PAUSE		250
 
+/* BRB default for class 0 E3A0 */
+#define DEFAULT0_E3A0_BRB_MAC_PAUSE_XOFF_THR	290
+#define DEFAULT0_E3A0_BRB_MAC_PAUSE_XON_THR	410
+#define DEFAULT0_E3A0_BRB_MAC_FULL_XOFF_THR	10
+#define DEFAULT0_E3A0_BRB_MAC_FULL_XON_THR	50
+
 /* BRB thresholds for E3A0 */
 #define PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_PAUSE		290
 #define PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE		0
@@ -190,6 +200,11 @@
 #define PFC_E3A0_BRB_MAC_FULL_XON_THR_PAUSE		50
 #define PFC_E3A0_BRB_MAC_FULL_XON_THR_NON_PAUSE		410
 
+/* BRB default for E3B0 */
+#define DEFAULT0_E3B0_BRB_MAC_PAUSE_XOFF_THR	330
+#define DEFAULT0_E3B0_BRB_MAC_PAUSE_XON_THR	490
+#define DEFAULT0_E3B0_BRB_MAC_FULL_XOFF_THR	15
+#define DEFAULT0_E3B0_BRB_MAC_FULL_XON_THR	55
 
 /* BRB thresholds for E3B0 2 port mode*/
 #define PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_PAUSE		1025
@@ -239,18 +254,29 @@
 #define PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_PAUSE		50
 #define PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_NON_PAUSE	384
 
-
 /* only for E3B0*/
 #define PFC_E3B0_4P_BRB_FULL_LB_XOFF_THR			304
 #define PFC_E3B0_4P_BRB_FULL_LB_XON_THR			384
-#define PFC_E3B0_4P_LB_GUART				120
+#define PFC_E3B0_4P_LB_GUART		120
 
 #define PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART		120
-#define PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART_HYST		80
+#define PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART_HYST	80
 
 #define PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART		80
-#define PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART_HYST		120
+#define PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART_HYST	120
+
+/* Pause defines*/
+#define DEFAULT_E3B0_BRB_FULL_LB_XOFF_THR			330
+#define DEFAULT_E3B0_BRB_FULL_LB_XON_THR			490
+#define DEFAULT_E3B0_LB_GUART		40
+
+#define DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART		40
+#define DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART_HYST	0
+
+#define DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART		40
+#define DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART_HYST	0
 
+/* ETS defines*/
 #define DCBX_INVALID_COS					(0xFF)
 
 #define ETS_BW_LIMIT_CREDIT_UPPER_BOUND		(0x5000)
@@ -440,7 +466,7 @@ static u32 bnx2x_ets_get_min_w_val_nig(const struct link_vars *vars)
 	u32 min_w_val = 0;
 	/* Calculate min_w_val.*/
 	if (vars->link_up) {
-		if (SPEED_20000 == vars->line_speed)
+		if (vars->line_speed == SPEED_20000)
 			min_w_val = ETS_E3B0_NIG_MIN_W_VAL_20GBPS;
 		else
 			min_w_val = ETS_E3B0_NIG_MIN_W_VAL_UP_TO_10GBPS;
@@ -490,7 +516,7 @@ static void bnx2x_ets_e3b0_set_credit_upper_bound_nig(
 	REG_WR(bp, (port) ? NIG_REG_P1_TX_ARB_CREDIT_UPPER_BOUND_5 :
 		   NIG_REG_P0_TX_ARB_CREDIT_UPPER_BOUND_5, credit_upper_bound);
 
-	if (0 == port) {
+	if (!port) {
 		REG_WR(bp, NIG_REG_P0_TX_ARB_CREDIT_UPPER_BOUND_6,
 			credit_upper_bound);
 		REG_WR(bp, NIG_REG_P0_TX_ARB_CREDIT_UPPER_BOUND_7,
@@ -584,7 +610,7 @@ static void bnx2x_ets_e3b0_nig_disabled(const struct link_params *params,
 		   NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_4, 0x0);
 	REG_WR(bp, (port) ? NIG_REG_P1_TX_ARB_CREDIT_WEIGHT_5 :
 		   NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_5, 0x0);
-	if (0 == port) {
+	if (!port) {
 		REG_WR(bp, NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_6, 0x0);
 		REG_WR(bp, NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_7, 0x0);
 		REG_WR(bp, NIG_REG_P0_TX_ARB_CREDIT_WEIGHT_8, 0x0);
@@ -612,7 +638,7 @@ static void bnx2x_ets_e3b0_set_credit_upper_bound_pbf(
 	* In 2 port mode port0 has COS0-5 that can be used for WFQ.In 4
 	* port mode port1 has COS0-2 that can be used for WFQ.
 	*/
-	if (0 == port) {
+	if (!port) {
 		base_upper_bound = PBF_REG_COS0_UPPER_BOUND_P0;
 		max_cos = DCBX_E3B0_MAX_NUM_COS_PORT0;
 	} else {
@@ -674,7 +700,7 @@ static void bnx2x_ets_e3b0_pbf_disabled(const struct link_params *params)
 	* In 2 port mode port0 has COS0-5 that can be used for WFQ.
 	* In 4 port mode port1 has COS0-2 that can be used for WFQ.
 	*/
-	if (0 == port) {
+	if (!port) {
 		base_weight = PBF_REG_COS0_WEIGHT_P0;
 		max_cos = DCBX_E3B0_MAX_NUM_COS_PORT0;
 	} else {
@@ -846,34 +872,47 @@ static int bnx2x_ets_e3b0_set_cos_bw(struct bnx2x *bp,
 ******************************************************************************/
 static int bnx2x_ets_e3b0_get_total_bw(
 	const struct link_params *params,
-	const struct bnx2x_ets_params *ets_params,
+	struct bnx2x_ets_params *ets_params,
 	u16 *total_bw)
 {
 	struct bnx2x *bp = params->bp;
 	u8 cos_idx = 0;
+	u8 is_bw_cos_exist = 0;
 
 	*total_bw = 0 ;
+
 	/* Calculate total BW requested */
 	for (cos_idx = 0; cos_idx < ets_params->num_of_cos; cos_idx++) {
-		if (bnx2x_cos_state_bw == ets_params->cos[cos_idx].state) {
+		if (ets_params->cos[cos_idx].state == bnx2x_cos_state_bw) {
+			is_bw_cos_exist = 1;
+			if (!ets_params->cos[cos_idx].params.bw_params.bw) {
+				DP(NETIF_MSG_LINK, "bnx2x_ets_E3B0_config BW"
+						   "was set to 0\n");
+				/*
+				 * This is to prevent a state when ramrods
+				 * can't be sent
+				*/
+				ets_params->cos[cos_idx].params.bw_params.bw
+					 = 1;
+			}
 			*total_bw +=
 				ets_params->cos[cos_idx].params.bw_params.bw;
 		}
 	}
 
 	/* Check total BW is valid */
-	if ((100 != *total_bw) || (0 == *total_bw)) {
-		if (0 == *total_bw) {
+	if ((is_bw_cos_exist == 1) && (*total_bw != 100)) {
+		if (*total_bw == 0) {
 			DP(NETIF_MSG_LINK,
-			   "bnx2x_ets_E3B0_config toatl BW shouldn't be 0\n");
+			   "bnx2x_ets_E3B0_config total BW shouldn't be 0\n");
 			return -EINVAL;
 		}
 		DP(NETIF_MSG_LINK,
-		   "bnx2x_ets_E3B0_config toatl BW should be 100\n");
-		/**
-		*   We can handle a case whre the BW isn't 100 this can happen
-		*   if the TC are joined.
-		*/
+		   "bnx2x_ets_E3B0_config total BW should be 100\n");
+		/*
+		 * We can handle a case whre the BW isn't 100 this can happen
+		 * if the TC are joined.
+		 */
 	}
 	return 0;
 }
@@ -904,7 +943,7 @@ static int bnx2x_ets_e3b0_sp_pri_to_cos_set(const struct link_params *params,
 	const u8 max_num_of_cos = (port) ? DCBX_E3B0_MAX_NUM_COS_PORT1 :
 		DCBX_E3B0_MAX_NUM_COS_PORT0;
 
-	if (DCBX_INVALID_COS != sp_pri_to_cos[pri]) {
+	if (sp_pri_to_cos[pri] != DCBX_INVALID_COS) {
 		DP(NETIF_MSG_LINK, "bnx2x_ets_e3b0_sp_pri_to_cos_set invalid "
 				   "parameter There can't be two COS's with "
 				   "the same strict pri\n");
@@ -913,7 +952,7 @@ static int bnx2x_ets_e3b0_sp_pri_to_cos_set(const struct link_params *params,
 
 	if (pri > max_num_of_cos) {
 		DP(NETIF_MSG_LINK, "bnx2x_ets_e3b0_sp_pri_to_cos_set invalid "
-			       "parameter Illegal strict priority\n");
+		   "parameter Illegal strict priority\n");
 	    return -EINVAL;
 	}
 
@@ -995,8 +1034,8 @@ static int bnx2x_ets_e3b0_sp_set_pri_cli_reg(const struct link_params *params,
 
 	/* Set all the strict priority first */
 	for (i = 0; i < max_num_of_cos; i++) {
-		if (DCBX_INVALID_COS != sp_pri_to_cos[i]) {
-			if (DCBX_MAX_NUM_COS <= sp_pri_to_cos[i]) {
+		if (sp_pri_to_cos[i] != DCBX_INVALID_COS) {
+			if (sp_pri_to_cos[i] >= DCBX_MAX_NUM_COS) {
 				DP(NETIF_MSG_LINK,
 					   "bnx2x_ets_e3b0_sp_set_pri_cli_reg "
 					   "invalid cos entry\n");
@@ -1010,7 +1049,7 @@ static int bnx2x_ets_e3b0_sp_set_pri_cli_reg(const struct link_params *params,
 			    sp_pri_to_cos[i], pri_set);
 			pri_bitmask = 1 << sp_pri_to_cos[i];
 			/* COS is used remove it from bitmap.*/
-			if (0 == (pri_bitmask & cos_bit_to_set)) {
+			if (!(pri_bitmask & cos_bit_to_set)) {
 				DP(NETIF_MSG_LINK,
 					"bnx2x_ets_e3b0_sp_set_pri_cli_reg "
 					"invalid There can't be two COS's with"
@@ -1072,7 +1111,7 @@ static int bnx2x_ets_e3b0_sp_set_pri_cli_reg(const struct link_params *params,
 ******************************************************************************/
 int bnx2x_ets_e3b0_config(const struct link_params *params,
 			 const struct link_vars *vars,
-			 const struct bnx2x_ets_params *ets_params)
+			 struct bnx2x_ets_params *ets_params)
 {
 	struct bnx2x *bp = params->bp;
 	int bnx2x_status = 0;
@@ -1105,15 +1144,15 @@ int bnx2x_ets_e3b0_config(const struct link_params *params,
 	/* Prepare BW parameters*/
 	bnx2x_status = bnx2x_ets_e3b0_get_total_bw(params, ets_params,
 						   &total_bw);
-	if (0 != bnx2x_status) {
+	if (bnx2x_status) {
 		DP(NETIF_MSG_LINK,
 		   "bnx2x_ets_E3B0_config get_total_bw failed\n");
 		return -EINVAL;
 	}
 
-	/**
-	 *  Upper bound is set according to current link speed (min_w_val
-	 *  should be the same for upper bound and COS credit val).
+	/*
+	 * Upper bound is set according to current link speed (min_w_val
+	 * should be the same for upper bound and COS credit val).
 	 */
 	bnx2x_ets_e3b0_set_credit_upper_bound_nig(params, min_w_val_nig);
 	bnx2x_ets_e3b0_set_credit_upper_bound_pbf(params, min_w_val_pbf);
@@ -1122,7 +1161,7 @@ int bnx2x_ets_e3b0_config(const struct link_params *params,
 	for (cos_entry = 0; cos_entry < ets_params->num_of_cos; cos_entry++) {
 		if (bnx2x_cos_state_bw == ets_params->cos[cos_entry].state) {
 			cos_bw_bitmap |= (1 << cos_entry);
-			/**
+			/*
 			 * The function also sets the BW in HW(not the mappin
 			 * yet)
 			 */
@@ -1146,7 +1185,7 @@ int bnx2x_ets_e3b0_config(const struct link_params *params,
 			   "bnx2x_ets_e3b0_config cos state not valid\n");
 			return -EINVAL;
 		}
-		if (0 != bnx2x_status) {
+		if (bnx2x_status) {
 			DP(NETIF_MSG_LINK,
 			   "bnx2x_ets_e3b0_config set cos bw failed\n");
 			return bnx2x_status;
@@ -1157,7 +1196,7 @@ int bnx2x_ets_e3b0_config(const struct link_params *params,
 	bnx2x_status = bnx2x_ets_e3b0_sp_set_pri_cli_reg(params,
 							 sp_pri_to_cos);
 
-	if (0 != bnx2x_status) {
+	if (bnx2x_status) {
 		DP(NETIF_MSG_LINK,
 		   "bnx2x_ets_E3B0_config set_pri_cli_reg failed\n");
 		return bnx2x_status;
@@ -1168,7 +1207,7 @@ int bnx2x_ets_e3b0_config(const struct link_params *params,
 					      cos_sp_bitmap,
 					      cos_bw_bitmap);
 
-	if (0 != bnx2x_status) {
+	if (bnx2x_status) {
 		DP(NETIF_MSG_LINK, "bnx2x_ets_E3B0_config SP failed\n");
 		return bnx2x_status;
 	}
@@ -1232,9 +1271,9 @@ void bnx2x_ets_bw_limit(const struct link_params *params, const u32 cos0_bw,
 
 	DP(NETIF_MSG_LINK, "ETS enabled BW limit configuration\n");
 
-	if ((0 == total_bw) ||
-	    (0 == cos0_bw) ||
-	    (0 == cos1_bw)) {
+	if ((!total_bw) ||
+	    (!cos0_bw) ||
+	    (!cos1_bw)) {
 		DP(NETIF_MSG_LINK, "Total BW can't be zero\n");
 		return;
 	}
@@ -1290,7 +1329,7 @@ int bnx2x_ets_strict(const struct link_params *params, const u8 strict_cos)
 	 * dbg0-010     dbg1-001     cos1-100     cos0-011     MCP-000
 	 * dbg0-010     dbg1-001     cos0-011     cos1-100     MCP-000
 	 */
-	val = (0 == strict_cos) ? 0x2318 : 0x22E0;
+	val = (!strict_cos) ? 0x2318 : 0x22E0;
 	REG_WR(bp, NIG_REG_P0_TX_ARB_PRIORITY_CLIENT, val);
 
 	return 0;
@@ -1298,7 +1337,6 @@ int bnx2x_ets_strict(const struct link_params *params, const u8 strict_cos)
 /******************************************************************/
 /*			PFC section				  */
 /******************************************************************/
-
 static void bnx2x_update_pfc_xmac(struct link_params *params,
 				  struct link_vars *vars,
 				  u8 is_lb)
@@ -1401,7 +1439,7 @@ void bnx2x_pfc_statistic(struct link_params *params, struct link_vars *vars,
 	if (!vars->link_up)
 		return;
 
-	if (MAC_TYPE_EMAC == vars->mac_type) {
+	if (vars->mac_type == MAC_TYPE_EMAC) {
 		DP(NETIF_MSG_LINK, "About to read PFC stats from EMAC\n");
 		bnx2x_emac_get_pfc_stat(params, pfc_frames_sent,
 					pfc_frames_received);
@@ -1435,6 +1473,18 @@ static void bnx2x_set_mdio_clk(struct bnx2x *bp, u32 chip_id, u8 port)
 
 	udelay(40);
 }
+static u8 bnx2x_is_4_port_mode(struct bnx2x *bp)
+{
+	u32 port4mode_ovwr_val;
+	/* Check 4-port override enabled */
+	port4mode_ovwr_val = REG_RD(bp, MISC_REG_PORT4MODE_EN_OVWR);
+	if (port4mode_ovwr_val & (1<<0)) {
+		/* Return 4-port mode override value */
+		return ((port4mode_ovwr_val & (1<<1)) == (1<<1));
+	}
+	/* Return 4-port mode from input pin */
+	return (u8)REG_RD(bp, MISC_REG_PORT4MODE_EN);
+}
 
 static void bnx2x_emac_init(struct link_params *params,
 			    struct link_vars *vars)
@@ -1601,31 +1651,18 @@ static void bnx2x_umac_enable(struct link_params *params,
 
 }
 
-static u8 bnx2x_is_4_port_mode(struct bnx2x *bp)
-{
-	u32 port4mode_ovwr_val;
-	/* Check 4-port override enabled */
-	port4mode_ovwr_val = REG_RD(bp, MISC_REG_PORT4MODE_EN_OVWR);
-	if (port4mode_ovwr_val & (1<<0)) {
-		/* Return 4-port mode override value */
-		return ((port4mode_ovwr_val & (1<<1)) == (1<<1));
-	}
-	/* Return 4-port mode from input pin */
-	return (u8)REG_RD(bp, MISC_REG_PORT4MODE_EN);
-}
-
 /* Define the XMAC mode */
 static void bnx2x_xmac_init(struct link_params *params, u32 max_speed)
 {
 	struct bnx2x *bp = params->bp;
 	u32 is_port4mode = bnx2x_is_4_port_mode(bp);
 
-	/**
-	* In 4-port mode, need to set the mode only once, so if XMAC is
-	* already out of reset, it means the mode has already been set,
-	* and it must not* reset the XMAC again, since it controls both
-	* ports of the path
-	**/
+	/*
+	 * In 4-port mode, need to set the mode only once, so if XMAC is
+	 * already out of reset, it means the mode has already been set,
+	 * and it must not* reset the XMAC again, since it controls both
+	 * ports of the path
+	 */
 
 	if ((CHIP_NUM(bp) == CHIP_NUM_57840) &&
 	    (REG_RD(bp, MISC_REG_RESET_REG_2) &
@@ -1743,6 +1780,7 @@ static int bnx2x_xmac_enable(struct link_params *params,
 
 	return 0;
 }
+
 static int bnx2x_emac_enable(struct link_params *params,
 			     struct link_vars *vars, u8 lb)
 {
@@ -1999,7 +2037,6 @@ static void bnx2x_update_pfc_bmac2(struct link_params *params,
 	REG_WR_DMAE(bp, bmac_addr + BIGMAC2_REGISTER_BMAC_CONTROL, wb_data, 2);
 }
 
-
 /* PFC BRB internal port configuration params */
 struct bnx2x_pfc_brb_threshold_val {
 	u32 pause_xoff;
@@ -2009,6 +2046,8 @@ struct bnx2x_pfc_brb_threshold_val {
 };
 
 struct bnx2x_pfc_brb_e3b0_val {
+	u32 per_class_guaranty_mode;
+	u32 lb_guarantied_hyst;
 	u32 full_lb_xoff_th;
 	u32 full_lb_xon_threshold;
 	u32 lb_guarantied;
@@ -2021,6 +2060,9 @@ struct bnx2x_pfc_brb_e3b0_val {
 struct bnx2x_pfc_brb_th_val {
 	struct bnx2x_pfc_brb_threshold_val pauseable_th;
 	struct bnx2x_pfc_brb_threshold_val non_pauseable_th;
+	struct bnx2x_pfc_brb_threshold_val default_class0;
+	struct bnx2x_pfc_brb_threshold_val default_class1;
+
 };
 static int bnx2x_pfc_brb_get_config_params(
 				struct link_params *params,
@@ -2028,140 +2070,200 @@ static int bnx2x_pfc_brb_get_config_params(
 {
 	struct bnx2x *bp = params->bp;
 	DP(NETIF_MSG_LINK, "Setting PFC BRB configuration\n");
+
+	config_val->default_class1.pause_xoff = 0;
+	config_val->default_class1.pause_xon = 0;
+	config_val->default_class1.full_xoff = 0;
+	config_val->default_class1.full_xon = 0;
+
 	if (CHIP_IS_E2(bp)) {
+		/*  class0 defaults */
+		config_val->default_class0.pause_xoff =
+			DEFAULT0_E2_BRB_MAC_PAUSE_XOFF_THR;
+		config_val->default_class0.pause_xon =
+			DEFAULT0_E2_BRB_MAC_PAUSE_XON_THR;
+		config_val->default_class0.full_xoff =
+			DEFAULT0_E2_BRB_MAC_FULL_XOFF_THR;
+		config_val->default_class0.full_xon =
+			DEFAULT0_E2_BRB_MAC_FULL_XON_THR;
+		/*  pause able*/
 		config_val->pauseable_th.pause_xoff =
-		    PFC_E2_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
+			PFC_E2_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
 		config_val->pauseable_th.pause_xon =
-		    PFC_E2_BRB_MAC_PAUSE_XON_THR_PAUSE;
+			PFC_E2_BRB_MAC_PAUSE_XON_THR_PAUSE;
 		config_val->pauseable_th.full_xoff =
-		    PFC_E2_BRB_MAC_FULL_XOFF_THR_PAUSE;
+			PFC_E2_BRB_MAC_FULL_XOFF_THR_PAUSE;
 		config_val->pauseable_th.full_xon =
-		    PFC_E2_BRB_MAC_FULL_XON_THR_PAUSE;
+			PFC_E2_BRB_MAC_FULL_XON_THR_PAUSE;
 		/* non pause able*/
 		config_val->non_pauseable_th.pause_xoff =
-		    PFC_E2_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
+			PFC_E2_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
 		config_val->non_pauseable_th.pause_xon =
-		    PFC_E2_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
+			PFC_E2_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
 		config_val->non_pauseable_th.full_xoff =
-		    PFC_E2_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
+			PFC_E2_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
 		config_val->non_pauseable_th.full_xon =
-		    PFC_E2_BRB_MAC_FULL_XON_THR_NON_PAUSE;
+			PFC_E2_BRB_MAC_FULL_XON_THR_NON_PAUSE;
 	} else if (CHIP_IS_E3A0(bp)) {
+		/*  class0 defaults */
+		config_val->default_class0.pause_xoff =
+			DEFAULT0_E3A0_BRB_MAC_PAUSE_XOFF_THR;
+		config_val->default_class0.pause_xon =
+			DEFAULT0_E3A0_BRB_MAC_PAUSE_XON_THR;
+		config_val->default_class0.full_xoff =
+			DEFAULT0_E3A0_BRB_MAC_FULL_XOFF_THR;
+		config_val->default_class0.full_xon =
+			DEFAULT0_E3A0_BRB_MAC_FULL_XON_THR;
+		/*  pause able */
 		config_val->pauseable_th.pause_xoff =
-		    PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
+			PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
 		config_val->pauseable_th.pause_xon =
-		    PFC_E3A0_BRB_MAC_PAUSE_XON_THR_PAUSE;
+			PFC_E3A0_BRB_MAC_PAUSE_XON_THR_PAUSE;
 		config_val->pauseable_th.full_xoff =
-		    PFC_E3A0_BRB_MAC_FULL_XOFF_THR_PAUSE;
+			PFC_E3A0_BRB_MAC_FULL_XOFF_THR_PAUSE;
 		config_val->pauseable_th.full_xon =
-		    PFC_E3A0_BRB_MAC_FULL_XON_THR_PAUSE;
+			PFC_E3A0_BRB_MAC_FULL_XON_THR_PAUSE;
 		/* non pause able*/
 		config_val->non_pauseable_th.pause_xoff =
-		    PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
+			PFC_E3A0_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
 		config_val->non_pauseable_th.pause_xon =
-		    PFC_E3A0_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
+			PFC_E3A0_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
 		config_val->non_pauseable_th.full_xoff =
-		    PFC_E3A0_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
+			PFC_E3A0_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
 		config_val->non_pauseable_th.full_xon =
-		    PFC_E3A0_BRB_MAC_FULL_XON_THR_NON_PAUSE;
+			PFC_E3A0_BRB_MAC_FULL_XON_THR_NON_PAUSE;
 	} else if (CHIP_IS_E3B0(bp)) {
+		/*  class0 defaults */
+		config_val->default_class0.pause_xoff =
+			DEFAULT0_E3B0_BRB_MAC_PAUSE_XOFF_THR;
+		config_val->default_class0.pause_xon =
+		    DEFAULT0_E3B0_BRB_MAC_PAUSE_XON_THR;
+		config_val->default_class0.full_xoff =
+		    DEFAULT0_E3B0_BRB_MAC_FULL_XOFF_THR;
+		config_val->default_class0.full_xon =
+		    DEFAULT0_E3B0_BRB_MAC_FULL_XON_THR;
+
 		if (params->phy[INT_PHY].flags &
 		    FLAGS_4_PORT_MODE) {
 			config_val->pauseable_th.pause_xoff =
-			    PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
+				PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
 			config_val->pauseable_th.pause_xon =
-			    PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_PAUSE;
+				PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_PAUSE;
 			config_val->pauseable_th.full_xoff =
-			    PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_PAUSE;
+				PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_PAUSE;
 			config_val->pauseable_th.full_xon =
-			    PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_PAUSE;
+				PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_PAUSE;
 			/* non pause able*/
 			config_val->non_pauseable_th.pause_xoff =
-			    PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
+			PFC_E3B0_4P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
 			config_val->non_pauseable_th.pause_xon =
-			    PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
+			PFC_E3B0_4P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
 			config_val->non_pauseable_th.full_xoff =
-			    PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
+			PFC_E3B0_4P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
 			config_val->non_pauseable_th.full_xon =
-			    PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_NON_PAUSE;
-	    } else {
-		config_val->pauseable_th.pause_xoff =
-		    PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
-		config_val->pauseable_th.pause_xon =
-		    PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_PAUSE;
-		config_val->pauseable_th.full_xoff =
-		    PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_PAUSE;
-		config_val->pauseable_th.full_xon =
-			PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_PAUSE;
-		/* non pause able*/
-		config_val->non_pauseable_th.pause_xoff =
-		    PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
-		config_val->non_pauseable_th.pause_xon =
-		    PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
-		config_val->non_pauseable_th.full_xoff =
-		    PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
-		config_val->non_pauseable_th.full_xon =
-		    PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_NON_PAUSE;
-	    }
+			PFC_E3B0_4P_BRB_MAC_FULL_XON_THR_NON_PAUSE;
+		} else {
+			config_val->pauseable_th.pause_xoff =
+				PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_PAUSE;
+			config_val->pauseable_th.pause_xon =
+				PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_PAUSE;
+			config_val->pauseable_th.full_xoff =
+				PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_PAUSE;
+			config_val->pauseable_th.full_xon =
+				PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_PAUSE;
+			/* non pause able*/
+			config_val->non_pauseable_th.pause_xoff =
+				PFC_E3B0_2P_BRB_MAC_PAUSE_XOFF_THR_NON_PAUSE;
+			config_val->non_pauseable_th.pause_xon =
+				PFC_E3B0_2P_BRB_MAC_PAUSE_XON_THR_NON_PAUSE;
+			config_val->non_pauseable_th.full_xoff =
+				PFC_E3B0_2P_BRB_MAC_FULL_XOFF_THR_NON_PAUSE;
+			config_val->non_pauseable_th.full_xon =
+				PFC_E3B0_2P_BRB_MAC_FULL_XON_THR_NON_PAUSE;
+		}
 	} else
 	    return -EINVAL;
 
 	return 0;
 }
 
-
-static void bnx2x_pfc_brb_get_e3b0_config_params(struct link_params *params,
-						 struct bnx2x_pfc_brb_e3b0_val
-						 *e3b0_val,
-						 u32 cos0_pauseable,
-						 u32 cos1_pauseable)
+static void bnx2x_pfc_brb_get_e3b0_config_params(
+		struct link_params *params,
+		struct bnx2x_pfc_brb_e3b0_val
+		*e3b0_val,
+		struct bnx2x_nig_brb_pfc_port_params *pfc_params,
+		const u8 pfc_enabled)
 {
-	if (params->phy[INT_PHY].flags & FLAGS_4_PORT_MODE) {
+	if (pfc_enabled && pfc_params) {
+		e3b0_val->per_class_guaranty_mode = 1;
+		e3b0_val->lb_guarantied_hyst = 80;
+
+		if (params->phy[INT_PHY].flags &
+		    FLAGS_4_PORT_MODE) {
+			e3b0_val->full_lb_xoff_th =
+				PFC_E3B0_4P_BRB_FULL_LB_XOFF_THR;
+			e3b0_val->full_lb_xon_threshold =
+				PFC_E3B0_4P_BRB_FULL_LB_XON_THR;
+			e3b0_val->lb_guarantied =
+				PFC_E3B0_4P_LB_GUART;
+			e3b0_val->mac_0_class_t_guarantied =
+				PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART;
+			e3b0_val->mac_0_class_t_guarantied_hyst =
+				PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART_HYST;
+			e3b0_val->mac_1_class_t_guarantied =
+				PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART;
+			e3b0_val->mac_1_class_t_guarantied_hyst =
+				PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART_HYST;
+		} else {
+			e3b0_val->full_lb_xoff_th =
+				PFC_E3B0_2P_BRB_FULL_LB_XOFF_THR;
+			e3b0_val->full_lb_xon_threshold =
+				PFC_E3B0_2P_BRB_FULL_LB_XON_THR;
+			e3b0_val->mac_0_class_t_guarantied_hyst =
+				PFC_E3B0_2P_BRB_MAC_0_CLASS_T_GUART_HYST;
+			e3b0_val->mac_1_class_t_guarantied =
+				PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART;
+			e3b0_val->mac_1_class_t_guarantied_hyst =
+				PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART_HYST;
+
+			if (pfc_params->cos0_pauseable !=
+				pfc_params->cos1_pauseable) {
+				/* nonpauseable= Lossy + pauseable = Lossless*/
+				e3b0_val->lb_guarantied =
+					PFC_E3B0_2P_MIX_PAUSE_LB_GUART;
+				e3b0_val->mac_0_class_t_guarantied =
+			       PFC_E3B0_2P_MIX_PAUSE_MAC_0_CLASS_T_GUART;
+			} else if (pfc_params->cos0_pauseable) {
+				/* Lossless +Lossless*/
+				e3b0_val->lb_guarantied =
+					PFC_E3B0_2P_PAUSE_LB_GUART;
+				e3b0_val->mac_0_class_t_guarantied =
+				   PFC_E3B0_2P_PAUSE_MAC_0_CLASS_T_GUART;
+			} else {
+				/* Lossy +Lossy*/
+				e3b0_val->lb_guarantied =
+					PFC_E3B0_2P_NON_PAUSE_LB_GUART;
+				e3b0_val->mac_0_class_t_guarantied =
+			       PFC_E3B0_2P_NON_PAUSE_MAC_0_CLASS_T_GUART;
+			}
+		}
+	} else {
+		e3b0_val->per_class_guaranty_mode = 0;
+		e3b0_val->lb_guarantied_hyst = 0;
 		e3b0_val->full_lb_xoff_th =
-		    PFC_E3B0_4P_BRB_FULL_LB_XOFF_THR;
+			DEFAULT_E3B0_BRB_FULL_LB_XOFF_THR;
 		e3b0_val->full_lb_xon_threshold =
-		    PFC_E3B0_4P_BRB_FULL_LB_XON_THR;
+			DEFAULT_E3B0_BRB_FULL_LB_XON_THR;
 		e3b0_val->lb_guarantied =
-		    PFC_E3B0_4P_LB_GUART;
+			DEFAULT_E3B0_LB_GUART;
 		e3b0_val->mac_0_class_t_guarantied =
-		    PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART;
+			DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART;
 		e3b0_val->mac_0_class_t_guarantied_hyst =
-		    PFC_E3B0_4P_BRB_MAC_0_CLASS_T_GUART_HYST;
+			DEFAULT_E3B0_BRB_MAC_0_CLASS_T_GUART_HYST;
 		e3b0_val->mac_1_class_t_guarantied =
-		    PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART;
+			DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART;
 		e3b0_val->mac_1_class_t_guarantied_hyst =
-		    PFC_E3B0_4P_BRB_MAC_1_CLASS_T_GUART_HYST;
-	} else {
-		e3b0_val->full_lb_xoff_th =
-		    PFC_E3B0_2P_BRB_FULL_LB_XOFF_THR;
-		e3b0_val->full_lb_xon_threshold =
-		    PFC_E3B0_2P_BRB_FULL_LB_XON_THR;
-		e3b0_val->mac_0_class_t_guarantied_hyst =
-		    PFC_E3B0_2P_BRB_MAC_0_CLASS_T_GUART_HYST;
-		e3b0_val->mac_1_class_t_guarantied =
-		    PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART;
-		e3b0_val->mac_1_class_t_guarantied_hyst =
-		    PFC_E3B0_2P_BRB_MAC_1_CLASS_T_GUART_HYST;
-
-		if (cos0_pauseable != cos1_pauseable) {
-			/* nonpauseable= Lossy + pauseable = Lossless*/
-			e3b0_val->lb_guarantied =
-			    PFC_E3B0_2P_MIX_PAUSE_LB_GUART;
-			e3b0_val->mac_0_class_t_guarantied =
-			    PFC_E3B0_2P_MIX_PAUSE_MAC_0_CLASS_T_GUART;
-		} else if (cos0_pauseable) {
-			/* Lossless +Lossless*/
-			e3b0_val->lb_guarantied =
-			    PFC_E3B0_2P_PAUSE_LB_GUART;
-			e3b0_val->mac_0_class_t_guarantied =
-			    PFC_E3B0_2P_PAUSE_MAC_0_CLASS_T_GUART;
-		} else {
-			/* Lossy +Lossy*/
-			e3b0_val->lb_guarantied =
-			    PFC_E3B0_2P_NON_PAUSE_LB_GUART;
-			e3b0_val->mac_0_class_t_guarantied =
-			    PFC_E3B0_2P_NON_PAUSE_MAC_0_CLASS_T_GUART;
-		}
+			DEFAULT_E3B0_BRB_MAC_1_CLASS_T_GUART_HYST;
 	}
 }
 static int bnx2x_update_pfc_brb(struct link_params *params,
@@ -2172,23 +2274,28 @@ static int bnx2x_update_pfc_brb(struct link_params *params,
 	struct bnx2x *bp = params->bp;
 	struct bnx2x_pfc_brb_th_val config_val = { {0} };
 	struct bnx2x_pfc_brb_threshold_val *reg_th_config =
-	    &config_val.pauseable_th;
+		&config_val.pauseable_th;
 	struct bnx2x_pfc_brb_e3b0_val e3b0_val = {0};
-	int set_pfc = params->feature_config_flags &
+	const int set_pfc = params->feature_config_flags &
 		FEATURE_CONFIG_PFC_ENABLED;
+	const u8 pfc_enabled = (set_pfc && pfc_params);
 	int bnx2x_status = 0;
 	u8 port = params->port;
 
 	/* default - pause configuration */
 	reg_th_config = &config_val.pauseable_th;
 	bnx2x_status = bnx2x_pfc_brb_get_config_params(params, &config_val);
-	if (0 != bnx2x_status)
+	if (bnx2x_status)
 		return bnx2x_status;
 
-	if (set_pfc && pfc_params)
+	if (pfc_enabled) {
 		/* First COS */
-		if (!pfc_params->cos0_pauseable)
+		if (pfc_params->cos0_pauseable)
+			reg_th_config = &config_val.pauseable_th;
+		else
 			reg_th_config = &config_val.non_pauseable_th;
+	} else
+		reg_th_config = &config_val.default_class0;
 	/*
 	 * The number of free blocks below which the pause signal to class 0
 	 * of MAC #n is asserted. n=0,1
@@ -2215,122 +2322,119 @@ static int bnx2x_update_pfc_brb(struct link_params *params,
 	REG_WR(bp, (port) ? BRB1_REG_FULL_0_XON_THRESHOLD_1 :
 	       BRB1_REG_FULL_0_XON_THRESHOLD_0 , reg_th_config->full_xon);
 
-	if (set_pfc && pfc_params) {
+	if (pfc_enabled) {
 		/* Second COS */
 		if (pfc_params->cos1_pauseable)
 			reg_th_config = &config_val.pauseable_th;
 		else
 			reg_th_config = &config_val.non_pauseable_th;
+	} else
+		reg_th_config = &config_val.default_class1;
+	/*
+	 * The number of free blocks below which the pause signal to
+	 * class 1 of MAC #n is asserted. n=0,1
+	 */
+	REG_WR(bp, (port) ? BRB1_REG_PAUSE_1_XOFF_THRESHOLD_1 :
+	       BRB1_REG_PAUSE_1_XOFF_THRESHOLD_0,
+	       reg_th_config->pause_xoff);
+
+	/*
+	 * The number of free blocks above which the pause signal to
+	 * class 1 of MAC #n is de-asserted. n=0,1
+	 */
+	REG_WR(bp, (port) ? BRB1_REG_PAUSE_1_XON_THRESHOLD_1 :
+	       BRB1_REG_PAUSE_1_XON_THRESHOLD_0,
+	       reg_th_config->pause_xon);
+	/*
+	 * The number of free blocks below which the full signal to
+	 * class 1 of MAC #n is asserted. n=0,1
+	 */
+	REG_WR(bp, (port) ? BRB1_REG_FULL_1_XOFF_THRESHOLD_1 :
+	       BRB1_REG_FULL_1_XOFF_THRESHOLD_0,
+	       reg_th_config->full_xoff);
+	/*
+	 * The number of free blocks above which the full signal to
+	 * class 1 of MAC #n is de-asserted. n=0,1
+	 */
+	REG_WR(bp, (port) ? BRB1_REG_FULL_1_XON_THRESHOLD_1 :
+	       BRB1_REG_FULL_1_XON_THRESHOLD_0,
+	       reg_th_config->full_xon);
+
+	if (CHIP_IS_E3B0(bp)) {
+		bnx2x_pfc_brb_get_e3b0_config_params(
+			params,
+			&e3b0_val,
+			pfc_params,
+			pfc_enabled);
+
+		REG_WR(bp, BRB1_REG_PER_CLASS_GUARANTY_MODE,
+			   e3b0_val.per_class_guaranty_mode);
+
 		/*
-		 * The number of free blocks below which the pause signal to
-		 * class 1 of MAC #n is asserted. n=0,1
-		**/
-		REG_WR(bp, (port) ? BRB1_REG_PAUSE_1_XOFF_THRESHOLD_1 :
-		       BRB1_REG_PAUSE_1_XOFF_THRESHOLD_0,
-		       reg_th_config->pause_xoff);
+		 * The hysteresis on the guarantied buffer space for the Lb
+		 * port before signaling XON.
+		 */
+		REG_WR(bp, BRB1_REG_LB_GUARANTIED_HYST,
+			   e3b0_val.lb_guarantied_hyst);
+
 		/*
-		 * The number of free blocks above which the pause signal to
-		 * class 1 of MAC #n is de-asserted. n=0,1
+		 * The number of free blocks below which the full signal to the
+		 * LB port is asserted.
 		 */
-		REG_WR(bp, (port) ? BRB1_REG_PAUSE_1_XON_THRESHOLD_1 :
-		       BRB1_REG_PAUSE_1_XON_THRESHOLD_0,
-		       reg_th_config->pause_xon);
+		REG_WR(bp, BRB1_REG_FULL_LB_XOFF_THRESHOLD,
+		       e3b0_val.full_lb_xoff_th);
 		/*
-		 * The number of free blocks below which the full signal to
-		 * class 1 of MAC #n is asserted. n=0,1
+		 * The number of free blocks above which the full signal to the
+		 * LB port is de-asserted.
 		 */
-		REG_WR(bp, (port) ? BRB1_REG_FULL_1_XOFF_THRESHOLD_1 :
-		       BRB1_REG_FULL_1_XOFF_THRESHOLD_0,
-		       reg_th_config->full_xoff);
+		REG_WR(bp, BRB1_REG_FULL_LB_XON_THRESHOLD,
+		       e3b0_val.full_lb_xon_threshold);
 		/*
-		 * The number of free blocks above which the full signal to
-		 * class 1 of MAC #n is de-asserted. n=0,1
+		 * The number of blocks guarantied for the MAC #n port. n=0,1
 		 */
-		REG_WR(bp, (port) ? BRB1_REG_FULL_1_XON_THRESHOLD_1 :
-		       BRB1_REG_FULL_1_XON_THRESHOLD_0,
-		       reg_th_config->full_xon);
 
+		/* The number of blocks guarantied for the LB port.*/
+		REG_WR(bp, BRB1_REG_LB_GUARANTIED,
+		       e3b0_val.lb_guarantied);
 
-		if (CHIP_IS_E3B0(bp)) {
-			/*Should be done by init tool */
-			/*
-			* BRB_empty_for_dup = BRB1_REG_BRB_EMPTY_THRESHOLD
-			* reset value
-			* 944
-			*/
-
-			/**
-			 * The hysteresis on the guarantied buffer space for the Lb port
-			 * before signaling XON.
-			 **/
-			REG_WR(bp, BRB1_REG_LB_GUARANTIED_HYST, 80);
-
-			bnx2x_pfc_brb_get_e3b0_config_params(
-			    params,
-			    &e3b0_val,
-			    pfc_params->cos0_pauseable,
-			    pfc_params->cos1_pauseable);
-			/**
-			 * The number of free blocks below which the full signal to the
-			 * LB port is asserted.
-			*/
-			REG_WR(bp, BRB1_REG_FULL_LB_XOFF_THRESHOLD,
-				   e3b0_val.full_lb_xoff_th);
-			/**
-			 * The number of free blocks above which the full signal to the
-			 * LB port is de-asserted.
-			*/
-			REG_WR(bp, BRB1_REG_FULL_LB_XON_THRESHOLD,
-				   e3b0_val.full_lb_xon_threshold);
-			/**
-			* The number of blocks guarantied for the MAC #n port. n=0,1
-			*/
-
-			/*The number of blocks guarantied for the LB port.*/
-			REG_WR(bp, BRB1_REG_LB_GUARANTIED,
-			       e3b0_val.lb_guarantied);
-
-			/**
-			 * The number of blocks guarantied for the MAC #n port.
-			*/
-			REG_WR(bp, BRB1_REG_MAC_GUARANTIED_0,
-				   2 * e3b0_val.mac_0_class_t_guarantied);
-			REG_WR(bp, BRB1_REG_MAC_GUARANTIED_1,
-				   2 * e3b0_val.mac_1_class_t_guarantied);
-			/**
-			 * The number of blocks guarantied for class #t in MAC0. t=0,1
-			*/
-			REG_WR(bp, BRB1_REG_MAC_0_CLASS_0_GUARANTIED,
-			       e3b0_val.mac_0_class_t_guarantied);
-			REG_WR(bp, BRB1_REG_MAC_0_CLASS_1_GUARANTIED,
-			       e3b0_val.mac_0_class_t_guarantied);
-			/**
-			 * The hysteresis on the guarantied buffer space for class in
-			 * MAC0.  t=0,1
-			*/
-			REG_WR(bp, BRB1_REG_MAC_0_CLASS_0_GUARANTIED_HYST,
-			       e3b0_val.mac_0_class_t_guarantied_hyst);
-			REG_WR(bp, BRB1_REG_MAC_0_CLASS_1_GUARANTIED_HYST,
-			       e3b0_val.mac_0_class_t_guarantied_hyst);
-
-			/**
-			 * The number of blocks guarantied for class #t in MAC1.t=0,1
-			*/
-			REG_WR(bp, BRB1_REG_MAC_1_CLASS_0_GUARANTIED,
-			       e3b0_val.mac_1_class_t_guarantied);
-			REG_WR(bp, BRB1_REG_MAC_1_CLASS_1_GUARANTIED,
-			       e3b0_val.mac_1_class_t_guarantied);
-			/**
-			 * The hysteresis on the guarantied buffer space for class #t
-			* in MAC1.  t=0,1
-			*/
-			REG_WR(bp, BRB1_REG_MAC_1_CLASS_0_GUARANTIED_HYST,
-			       e3b0_val.mac_1_class_t_guarantied_hyst);
-			REG_WR(bp, BRB1_REG_MAC_1_CLASS_1_GUARANTIED_HYST,
-			       e3b0_val.mac_1_class_t_guarantied_hyst);
-
-	    }
+		/*
+		 * The number of blocks guarantied for the MAC #n port.
+		 */
+		REG_WR(bp, BRB1_REG_MAC_GUARANTIED_0,
+		       2 * e3b0_val.mac_0_class_t_guarantied);
+		REG_WR(bp, BRB1_REG_MAC_GUARANTIED_1,
+		       2 * e3b0_val.mac_1_class_t_guarantied);
+		/*
+		 * The number of blocks guarantied for class #t in MAC0. t=0,1
+		 */
+		REG_WR(bp, BRB1_REG_MAC_0_CLASS_0_GUARANTIED,
+		       e3b0_val.mac_0_class_t_guarantied);
+		REG_WR(bp, BRB1_REG_MAC_0_CLASS_1_GUARANTIED,
+		       e3b0_val.mac_0_class_t_guarantied);
+		/*
+		 * The hysteresis on the guarantied buffer space for class in
+		 * MAC0.  t=0,1
+		 */
+		REG_WR(bp, BRB1_REG_MAC_0_CLASS_0_GUARANTIED_HYST,
+		       e3b0_val.mac_0_class_t_guarantied_hyst);
+		REG_WR(bp, BRB1_REG_MAC_0_CLASS_1_GUARANTIED_HYST,
+		       e3b0_val.mac_0_class_t_guarantied_hyst);
 
+		/*
+		 * The number of blocks guarantied for class #t in MAC1.t=0,1
+		 */
+		REG_WR(bp, BRB1_REG_MAC_1_CLASS_0_GUARANTIED,
+		       e3b0_val.mac_1_class_t_guarantied);
+		REG_WR(bp, BRB1_REG_MAC_1_CLASS_1_GUARANTIED,
+		       e3b0_val.mac_1_class_t_guarantied);
+		/*
+		 * The hysteresis on the guarantied buffer space for class #t
+		 * in MAC1.  t=0,1
+		 */
+		REG_WR(bp, BRB1_REG_MAC_1_CLASS_0_GUARANTIED_HYST,
+		       e3b0_val.mac_1_class_t_guarantied_hyst);
+		REG_WR(bp, BRB1_REG_MAC_1_CLASS_1_GUARANTIED_HYST,
+		       e3b0_val.mac_1_class_t_guarantied_hyst);
 	}
 
 	return bnx2x_status;
@@ -2515,7 +2619,7 @@ int bnx2x_update_pfc(struct link_params *params,
 
 	/* update BRB params */
 	bnx2x_status = bnx2x_update_pfc_brb(params, vars, pfc_params);
-	if (0 != bnx2x_status)
+	if (bnx2x_status)
 		return bnx2x_status;
 
 	if (!vars->link_up)
@@ -2533,7 +2637,6 @@ int bnx2x_update_pfc(struct link_params *params,
 			bnx2x_emac_enable(params, vars, 0);
 			return bnx2x_status;
 		}
-
 		if (CHIP_IS_E2(bp))
 			bnx2x_update_pfc_bmac2(params, vars, bmac_loopback);
 		else
@@ -3053,7 +3156,6 @@ static int bnx2x_cl45_write(struct bnx2x *bp, struct bnx2x_phy *phy,
 		DP(NETIF_MSG_LINK, "write phy register failed\n");
 		netdev_err(bp->dev,  "MDC/MDIO access timeout\n");
 		rc = -EFAULT;
-
 	} else {
 		/* data */
 		tmp = ((phy->addr << 21) | (devad << 16) | val |
@@ -3090,8 +3192,6 @@ static int bnx2x_cl45_write(struct bnx2x *bp, struct bnx2x_phy *phy,
 			       EMAC_MDIO_STATUS_10MB);
 	return rc;
 }
-
-
 /******************************************************************/
 /*			BSC access functions from E3	          */
 /******************************************************************/
@@ -3339,7 +3439,7 @@ static void bnx2x_set_aer_mmd(struct link_params *params,
 		aer_val = 0x3800 + offset - 1;
 	else
 		aer_val = 0x3800 + offset;
-	DP(NETIF_MSG_LINK, "Set AER to 0x%x\n", aer_val);
+
 	CL22_WR_OVER_CL45(bp, phy, MDIO_REG_BANK_AER_BLOCK,
 			  MDIO_AER_BLOCK_AER_REG, aer_val);
 
@@ -3942,13 +4042,11 @@ static void bnx2x_warpcore_set_20G_DXGXS(struct bnx2x *bp,
 
 static void bnx2x_warpcore_set_sgmii_speed(struct bnx2x_phy *phy,
 					   struct link_params *params,
-					   u8 fiber_mode)
+					   u8 fiber_mode,
+					   u8 always_autoneg)
 {
 	struct bnx2x *bp = params->bp;
 	u16 val16, digctrl_kx1, digctrl_kx2;
-	u8 lane;
-
-	lane = bnx2x_get_warpcore_lane(phy, params);
 
 	/* Clear XFI clock comp in non-10G single lane mode. */
 	bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
@@ -3956,7 +4054,7 @@ static void bnx2x_warpcore_set_sgmii_speed(struct bnx2x_phy *phy,
 	bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
 			 MDIO_WC_REG_RX66_CONTROL, val16 & ~(3<<13));
 
-	if (phy->req_line_speed == SPEED_AUTO_NEG) {
+	if (always_autoneg || phy->req_line_speed == SPEED_AUTO_NEG) {
 		/* SGMII Autoneg */
 		bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
 				MDIO_WC_REG_COMBO_IEEE0_MIICTRL, &val16);
@@ -3967,7 +4065,7 @@ static void bnx2x_warpcore_set_sgmii_speed(struct bnx2x_phy *phy,
 	} else {
 		bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
 				MDIO_WC_REG_COMBO_IEEE0_MIICTRL, &val16);
-		val16 &= 0xcfbf;
+		val16 &= 0xcebf;
 		switch (phy->req_line_speed) {
 		case SPEED_10:
 			break;
@@ -4043,9 +4141,7 @@ static void bnx2x_warpcore_reset_lane(struct bnx2x *bp,
 	bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
 			 MDIO_WC_REG_DIGITAL5_MISC6, &val);
 }
-
-
-	/* Clear SFI/XFI link settings registers */
+/* Clear SFI/XFI link settings registers */
 static void bnx2x_warpcore_clear_regs(struct bnx2x_phy *phy,
 				      struct link_params *params,
 				      u16 lane)
@@ -4250,7 +4346,7 @@ static void bnx2x_warpcore_config_init(struct bnx2x_phy *phy,
 		vars->phy_flags |= PHY_SGMII_FLAG;
 		DP(NETIF_MSG_LINK, "Setting SGMII mode\n");
 		bnx2x_warpcore_clear_regs(phy, params, lane);
-		bnx2x_warpcore_set_sgmii_speed(phy, params, 0);
+		bnx2x_warpcore_set_sgmii_speed(phy, params, 0, 1);
 	} else {
 		switch (serdes_net_if) {
 		case PORT_HW_CFG_NET_SERDES_IF_KR:
@@ -4278,7 +4374,8 @@ static void bnx2x_warpcore_config_init(struct bnx2x_phy *phy,
 				}
 				bnx2x_warpcore_set_sgmii_speed(phy,
 								params,
-								fiber_mode);
+								fiber_mode,
+								0);
 			}
 
 			break;
@@ -4291,7 +4388,8 @@ static void bnx2x_warpcore_config_init(struct bnx2x_phy *phy,
 				bnx2x_warpcore_set_10G_XFI(phy, params, 0);
 			} else if (vars->line_speed == SPEED_1000) {
 				DP(NETIF_MSG_LINK, "Setting 1G Fiber\n");
-				bnx2x_warpcore_set_sgmii_speed(phy, params, 1);
+				bnx2x_warpcore_set_sgmii_speed(
+						phy, params, 1, 0);
 			}
 			/* Issue Module detection */
 			if (bnx2x_is_sfp_module_plugged(phy, params))
@@ -4428,12 +4526,6 @@ static void bnx2x_set_warpcore_loopback(struct bnx2x_phy *phy,
 
 		/* Switch back to 4-copy registers */
 		bnx2x_set_aer_mmd(params, phy);
-		/* Global loopback, not recommended. */
-		bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
-				MDIO_WC_REG_COMBO_IEEE0_MIICTRL, &val16);
-		bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
-				MDIO_WC_REG_COMBO_IEEE0_MIICTRL, val16 |
-				0x4000);
 	} else {
 		/* 10G & 20G */
 		bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
@@ -4450,25 +4542,14 @@ static void bnx2x_set_warpcore_loopback(struct bnx2x_phy *phy,
 }
 
 
-void bnx2x_link_status_update(struct link_params *params,
-			      struct link_vars *vars)
+void bnx2x_sync_link(struct link_params *params,
+			   struct link_vars *vars)
 {
 	struct bnx2x *bp = params->bp;
 	u8 link_10g_plus;
-	u8 port = params->port;
-	u32 sync_offset, media_types;
-	/* Update PHY configuration */
-	set_phy_vars(params, vars);
-
-	vars->link_status = REG_RD(bp, params->shmem_base +
-				   offsetof(struct shmem_region,
-					    port_mb[port].link_status));
-
-	vars->link_up = (vars->link_status & LINK_STATUS_LINK_UP);
-	vars->phy_flags = PHY_XGXS_FLAG;
 	if (vars->link_status & LINK_STATUS_PHYSICAL_LINK_FLAG)
 		vars->phy_flags |= PHY_PHYSICAL_LINK_FLAG;
-
+	vars->link_up = (vars->link_status & LINK_STATUS_LINK_UP);
 	if (vars->link_up) {
 		DP(NETIF_MSG_LINK, "phy link up\n");
 
@@ -4563,7 +4644,23 @@ void bnx2x_link_status_update(struct link_params *params,
 		if (vars->link_status & LINK_STATUS_PHYSICAL_LINK_FLAG)
 			vars->phy_flags |= PHY_HALF_OPEN_CONN_FLAG;
 	}
+}
+
+void bnx2x_link_status_update(struct link_params *params,
+			      struct link_vars *vars)
+{
+	struct bnx2x *bp = params->bp;
+	u8 port = params->port;
+	u32 sync_offset, media_types;
+	/* Update PHY configuration */
+	set_phy_vars(params, vars);
 
+	vars->link_status = REG_RD(bp, params->shmem_base +
+				   offsetof(struct shmem_region,
+					    port_mb[port].link_status));
+
+	vars->phy_flags = PHY_XGXS_FLAG;
+	bnx2x_sync_link(params, vars);
 	/* Sync media type */
 	sync_offset = params->shmem_base +
 			offsetof(struct shmem_region,
@@ -4602,7 +4699,6 @@ void bnx2x_link_status_update(struct link_params *params,
 		 vars->line_speed, vars->duplex, vars->flow_ctrl);
 }
 
-
 static void bnx2x_set_master_ln(struct link_params *params,
 				struct bnx2x_phy *phy)
 {
@@ -4676,11 +4772,8 @@ static void bnx2x_set_swap_lanes(struct link_params *params,
 	 *  Each two bits represents a lane number:
 	 *  No swap is 0123 => 0x1b no need to enable the swap
 	 */
-	u16 ser_lane, rx_lane_swap, tx_lane_swap;
+	u16 rx_lane_swap, tx_lane_swap;
 
-	ser_lane = ((params->lane_config &
-		     PORT_HW_CFG_LANE_SWAP_CFG_MASTER_MASK) >>
-		    PORT_HW_CFG_LANE_SWAP_CFG_MASTER_SHIFT);
 	rx_lane_swap = ((params->lane_config &
 			 PORT_HW_CFG_LANE_SWAP_CFG_RX_MASK) >>
 			PORT_HW_CFG_LANE_SWAP_CFG_RX_SHIFT);
@@ -5356,7 +5449,6 @@ static int bnx2x_link_settings_status(struct bnx2x_phy *phy,
 				      struct link_params *params,
 				      struct link_vars *vars)
 {
-
 	struct bnx2x *bp = params->bp;
 
 	u16 gp_status, duplex = DUPLEX_HALF, link_up = 0, speed_mask;
@@ -5403,9 +5495,7 @@ static int bnx2x_warpcore_read_status(struct bnx2x_phy *phy,
 				     struct link_params *params,
 				     struct link_vars *vars)
 {
-
 	struct bnx2x *bp = params->bp;
-
 	u8 lane;
 	u16 gp_status1, gp_speed, link_up, duplex = DUPLEX_FULL;
 	int rc = 0;
@@ -6678,7 +6768,6 @@ int bnx2x_link_update(struct link_params *params, struct link_vars *vars)
 	return rc;
 }
 
-
 /*****************************************************************************/
 /*			    External Phy section			     */
 /*****************************************************************************/
@@ -8103,7 +8192,15 @@ static void bnx2x_warpcore_power_module(struct link_params *params,
 static void bnx2x_warpcore_hw_reset(struct bnx2x_phy *phy,
 				    struct link_params *params)
 {
+	struct bnx2x *bp = params->bp;
 	bnx2x_warpcore_power_module(params, phy, 0);
+	/* Put Warpcore in low power mode */
+	REG_WR(bp, MISC_REG_WC0_RESET, 0x0c0e);
+
+	/* Put LCPLL in low power mode */
+	REG_WR(bp, MISC_REG_LCPLL_E40_PWRDWN, 1);
+	REG_WR(bp, MISC_REG_LCPLL_E40_RESETB_ANA, 0);
+	REG_WR(bp, MISC_REG_LCPLL_E40_RESETB_DIG, 0);
 }
 
 static void bnx2x_power_sfp_module(struct link_params *params,
@@ -9040,13 +9137,13 @@ static u8 bnx2x_8727_read_status(struct bnx2x_phy *phy,
 			DP(NETIF_MSG_LINK,
 			   "8727 Power fault has been detected on port %d\n",
 			   oc_port);
-			netdev_err(bp->dev, "Error:  Power fault on Port %d has"
-					    " been detected and the power to "
-					    "that SFP+ module has been removed"
-					    " to prevent failure of the card."
-					    " Please remove the SFP+ module and"
-					    " restart the system to clear this"
-					    " error.\n",
+			netdev_err(bp->dev, "Error: Power fault on Port %d has "
+					    "been detected and the power to "
+					    "that SFP+ module has been removed "
+					    "to prevent failure of the card. "
+					    "Please remove the SFP+ module and "
+					    "restart the system to clear this "
+					    "error.\n",
 			 oc_port);
 			/* Disable all RX_ALARMs except for mod_abs */
 			bnx2x_cl45_write(bp, phy,
@@ -9228,7 +9325,7 @@ static void bnx2x_save_848xx_spirom_version(struct bnx2x_phy *phy,
 static void bnx2x_848xx_set_led(struct bnx2x *bp,
 				struct bnx2x_phy *phy)
 {
-	u16 val;
+	u16 val, offset;
 
 	/* PHYC_CTL_LED_CTL */
 	bnx2x_cl45_read(bp, phy,
@@ -9263,14 +9360,22 @@ static void bnx2x_848xx_set_led(struct bnx2x *bp,
 			MDIO_PMA_REG_8481_LED3_BLINK,
 			0);
 
-	bnx2x_cl45_read(bp, phy,
+	/* Configure the blink rate to ~15.9 Hz */
+	bnx2x_cl45_write(bp, phy,
 			MDIO_PMA_DEVAD,
-			MDIO_PMA_REG_84823_CTL_LED_CTL_1, &val);
-	val |= MDIO_PMA_REG_84823_LED3_STRETCH_EN; /* stretch_en for LED3*/
+			MDIO_PMA_REG_84823_CTL_SLOW_CLK_CNT_HIGH,
+			MDIO_PMA_REG_84823_BLINK_RATE_VAL_15P9HZ);
+
+	if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833)
+		offset = MDIO_PMA_REG_84833_CTL_LED_CTL_1;
+	else
+		offset = MDIO_PMA_REG_84823_CTL_LED_CTL_1;
 
+	bnx2x_cl45_read(bp, phy,
+			MDIO_PMA_DEVAD, offset, &val);
+	val |= MDIO_PMA_REG_84823_LED3_STRETCH_EN; /* stretch_en for LED3*/
 	bnx2x_cl45_write(bp, phy,
-			 MDIO_PMA_DEVAD,
-			 MDIO_PMA_REG_84823_CTL_LED_CTL_1, val);
+			 MDIO_PMA_DEVAD, offset, val);
 
 	/* 'Interrupt Mask' */
 	bnx2x_cl45_write(bp, phy,
@@ -9283,7 +9388,7 @@ static int bnx2x_848xx_cmn_config_init(struct bnx2x_phy *phy,
 				       struct link_vars *vars)
 {
 	struct bnx2x *bp = params->bp;
-	u16 autoneg_val, an_1000_val, an_10_100_val;
+	u16 autoneg_val, an_1000_val, an_10_100_val, an_10g_val;
 	u16 tmp_req_line_speed;
 
 	tmp_req_line_speed = phy->req_line_speed;
@@ -9378,6 +9483,8 @@ static int bnx2x_848xx_cmn_config_init(struct bnx2x_phy *phy,
 		bnx2x_cl45_write(bp, phy,
 				 MDIO_AN_DEVAD, MDIO_AN_REG_8481_AUX_CTRL,
 				 (1<<15 | 1<<9 | 7<<0));
+		/* The PHY needs this set even for forced link. */
+		an_10_100_val |= (1<<8) | (1<<7);
 		DP(NETIF_MSG_LINK, "Setting 100M force\n");
 	}
 	if ((phy->req_line_speed == SPEED_10) &&
@@ -9415,9 +9522,17 @@ static int bnx2x_848xx_cmn_config_init(struct bnx2x_phy *phy,
 			DP(NETIF_MSG_LINK, "Advertising 10G\n");
 			/* Restart autoneg for 10G*/
 
+			bnx2x_cl45_read(bp, phy,
+					MDIO_AN_DEVAD,
+					MDIO_AN_REG_8481_10GBASE_T_AN_CTRL,
+					&an_10g_val);
+			bnx2x_cl45_write(bp, phy,
+					 MDIO_AN_DEVAD,
+					 MDIO_AN_REG_8481_10GBASE_T_AN_CTRL,
+					 an_10g_val | 0x1000);
 			bnx2x_cl45_write(bp, phy,
-				 MDIO_AN_DEVAD, MDIO_AN_REG_CTRL,
-				 0x3200);
+					 MDIO_AN_DEVAD, MDIO_AN_REG_CTRL,
+					 0x3200);
 	} else
 		bnx2x_cl45_write(bp, phy,
 				 MDIO_AN_DEVAD,
@@ -9449,74 +9564,95 @@ static int bnx2x_8481_config_init(struct bnx2x_phy *phy,
 	return bnx2x_848xx_cmn_config_init(phy, params, vars);
 }
 
-
-#define PHY84833_HDSHK_WAIT 300
-static int bnx2x_84833_pair_swap_cfg(struct bnx2x_phy *phy,
+#define PHY84833_CMDHDLR_WAIT 300
+#define PHY84833_CMDHDLR_MAX_ARGS 5
+static int bnx2x_84833_cmd_hdlr(struct bnx2x_phy *phy,
 				   struct link_params *params,
-				   struct link_vars *vars)
+		   u16 fw_cmd,
+		   u16 cmd_args[])
 {
 	u32 idx;
-	u32 pair_swap;
 	u16 val;
-	u16 data;
 	struct bnx2x *bp = params->bp;
-	/* Do pair swap */
-
-	/* Check for configuration. */
-	pair_swap = REG_RD(bp, params->shmem_base +
-			   offsetof(struct shmem_region,
-			dev_info.port_hw_config[params->port].xgbt_phy_cfg)) &
-		PORT_HW_CFG_RJ45_PAIR_SWAP_MASK;
-
-	if (pair_swap == 0)
-		return 0;
-
-	data = (u16)pair_swap;
-
 	/* Write CMD_OPEN_OVERRIDE to STATUS reg */
 	bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-			MDIO_84833_TOP_CFG_SCRATCH_REG2,
-			PHY84833_CMD_OPEN_OVERRIDE);
-	for (idx = 0; idx < PHY84833_HDSHK_WAIT; idx++) {
+			MDIO_84833_CMD_HDLR_STATUS,
+			PHY84833_STATUS_CMD_OPEN_OVERRIDE);
+	for (idx = 0; idx < PHY84833_CMDHDLR_WAIT; idx++) {
 		bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
-				MDIO_84833_TOP_CFG_SCRATCH_REG2, &val);
-		if (val == PHY84833_CMD_OPEN_FOR_CMDS)
+				MDIO_84833_CMD_HDLR_STATUS, &val);
+		if (val == PHY84833_STATUS_CMD_OPEN_FOR_CMDS)
 			break;
 		msleep(1);
 	}
-	if (idx >= PHY84833_HDSHK_WAIT) {
-		DP(NETIF_MSG_LINK, "Pairswap: FW not ready.\n");
+	if (idx >= PHY84833_CMDHDLR_WAIT) {
+		DP(NETIF_MSG_LINK, "FW cmd: FW not ready.\n");
 		return -EINVAL;
 	}
 
+	/* Prepare argument(s) and issue command */
+	for (idx = 0; idx < PHY84833_CMDHDLR_MAX_ARGS; idx++) {
+		bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
+				MDIO_84833_CMD_HDLR_DATA1 + idx,
+				cmd_args[idx]);
+	}
 	bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-			MDIO_84833_TOP_CFG_SCRATCH_REG4,
-			data);
-	/* Issue pair swap command */
-	bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-			MDIO_84833_TOP_CFG_SCRATCH_REG0,
-			PHY84833_DIAG_CMD_PAIR_SWAP_CHANGE);
-	for (idx = 0; idx < PHY84833_HDSHK_WAIT; idx++) {
+			MDIO_84833_CMD_HDLR_COMMAND, fw_cmd);
+	for (idx = 0; idx < PHY84833_CMDHDLR_WAIT; idx++) {
 		bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
-				MDIO_84833_TOP_CFG_SCRATCH_REG2, &val);
-		if ((val == PHY84833_CMD_COMPLETE_PASS) ||
-			(val == PHY84833_CMD_COMPLETE_ERROR))
+				MDIO_84833_CMD_HDLR_STATUS, &val);
+		if ((val == PHY84833_STATUS_CMD_COMPLETE_PASS) ||
+			(val == PHY84833_STATUS_CMD_COMPLETE_ERROR))
 			break;
 		msleep(1);
 	}
-	if ((idx >= PHY84833_HDSHK_WAIT) ||
-		(val == PHY84833_CMD_COMPLETE_ERROR)) {
-		DP(NETIF_MSG_LINK, "Pairswap: override failed.\n");
+	if ((idx >= PHY84833_CMDHDLR_WAIT) ||
+		(val == PHY84833_STATUS_CMD_COMPLETE_ERROR)) {
+		DP(NETIF_MSG_LINK, "FW cmd failed.\n");
 		return -EINVAL;
 	}
+	/* Gather returning data */
+	for (idx = 0; idx < PHY84833_CMDHDLR_MAX_ARGS; idx++) {
+		bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
+				MDIO_84833_CMD_HDLR_DATA1 + idx,
+				&cmd_args[idx]);
+	}
 	bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-			MDIO_84833_TOP_CFG_SCRATCH_REG2,
-			PHY84833_CMD_CLEAR_COMPLETE);
-	DP(NETIF_MSG_LINK, "Pairswap OK, val=0x%x\n", data);
+			MDIO_84833_CMD_HDLR_STATUS,
+			PHY84833_STATUS_CMD_CLEAR_COMPLETE);
 	return 0;
 }
 
 
+static int bnx2x_84833_pair_swap_cfg(struct bnx2x_phy *phy,
+				   struct link_params *params,
+				   struct link_vars *vars)
+{
+	u32 pair_swap;
+	u16 data[PHY84833_CMDHDLR_MAX_ARGS];
+	int status;
+	struct bnx2x *bp = params->bp;
+
+	/* Check for configuration. */
+	pair_swap = REG_RD(bp, params->shmem_base +
+			   offsetof(struct shmem_region,
+			dev_info.port_hw_config[params->port].xgbt_phy_cfg)) &
+		PORT_HW_CFG_RJ45_PAIR_SWAP_MASK;
+
+	if (pair_swap == 0)
+		return 0;
+
+	/* Only the second argument is used for this command */
+	data[1] = (u16)pair_swap;
+
+	status = bnx2x_84833_cmd_hdlr(phy, params,
+		PHY84833_CMD_SET_PAIR_SWAP, data);
+	if (status == 0)
+		DP(NETIF_MSG_LINK, "Pairswap OK, val=0x%x\n", data[1]);
+
+	return status;
+}
+
 static u8 bnx2x_84833_get_reset_gpios(struct bnx2x *bp,
 				      u32 shmem_base_path[],
 				      u32 chip_id)
@@ -9579,24 +9715,6 @@ static int bnx2x_84833_hw_reset_phy(struct bnx2x_phy *phy,
 	return 0;
 }
 
-static int bnx2x_84833_common_init_phy(struct bnx2x *bp,
-						u32 shmem_base_path[],
-						u32 chip_id)
-{
-	u8 reset_gpios;
-
-	reset_gpios = bnx2x_84833_get_reset_gpios(bp, shmem_base_path, chip_id);
-
-	bnx2x_set_mult_gpio(bp, reset_gpios, MISC_REGISTERS_GPIO_OUTPUT_LOW);
-	udelay(10);
-	bnx2x_set_mult_gpio(bp, reset_gpios, MISC_REGISTERS_GPIO_OUTPUT_HIGH);
-	msleep(800);
-	DP(NETIF_MSG_LINK, "84833 reset pulse on pin values 0x%x\n",
-		reset_gpios);
-
-	return 0;
-}
-
 #define PHY84833_CONSTANT_LATENCY 1193
 static int bnx2x_848x3_config_init(struct bnx2x_phy *phy,
 				   struct link_params *params,
@@ -9605,8 +9723,8 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy,
 	struct bnx2x *bp = params->bp;
 	u8 port, initialize = 1;
 	u16 val;
-	u16 temp;
-	u32 actual_phy_selection, cms_enable, idx;
+	u32 actual_phy_selection, cms_enable;
+	u16 cmd_args[PHY84833_CMDHDLR_MAX_ARGS];
 	int rc = 0;
 
 	msleep(1);
@@ -9625,6 +9743,13 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy,
 		bnx2x_cl45_write(bp, phy,
 				MDIO_PMA_DEVAD,
 				MDIO_PMA_REG_CTRL, 0x8000);
+	}
+
+	bnx2x_wait_reset_complete(bp, phy, params);
+
+	/* Wait for GPHY to come out of reset */
+	msleep(50);
+	if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833) {
 		/* Bring PHY out of super isolate mode */
 		bnx2x_cl45_read(bp, phy,
 				MDIO_CTL_DEVAD,
@@ -9633,26 +9758,19 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy,
 		bnx2x_cl45_write(bp, phy,
 				MDIO_CTL_DEVAD,
 				MDIO_84833_TOP_CFG_XGPHY_STRAP1, val);
-	}
-
-	bnx2x_wait_reset_complete(bp, phy, params);
-
-	/* Wait for GPHY to come out of reset */
-	msleep(50);
-
-	if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM84833)
 		bnx2x_84833_pair_swap_cfg(phy, params, vars);
-
-	/*
-	 * BCM84823 requires that XGXS links up first @ 10G for normal behavior
-	 */
-	temp = vars->line_speed;
-	vars->line_speed = SPEED_10000;
-	bnx2x_set_autoneg(&params->phy[INT_PHY], params, vars, 0);
-	bnx2x_program_serdes(&params->phy[INT_PHY], params, vars);
-	vars->line_speed = temp;
-
-	/* Set dual-media configuration according to configuration */
+	} else {
+		/*
+		 * BCM84823 requires that XGXS links up first @ 10G for normal
+		 * behavior.
+		 */
+		u16 temp;
+		temp = vars->line_speed;
+		vars->line_speed = SPEED_10000;
+		bnx2x_set_autoneg(&params->phy[INT_PHY], params, vars, 0);
+		bnx2x_program_serdes(&params->phy[INT_PHY], params, vars);
+		vars->line_speed = temp;
+	}
 
 	bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
 			MDIO_CTL_REG_84823_MEDIA, &val);
@@ -9700,64 +9818,18 @@ static int bnx2x_848x3_config_init(struct bnx2x_phy *phy,
 
 	/* AutogrEEEn */
 	if (params->feature_config_flags &
-		FEATURE_CONFIG_AUTOGREEEN_ENABLED) {
-		/* Ensure that f/w is ready */
-		for (idx = 0; idx < PHY84833_HDSHK_WAIT; idx++) {
-			bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
-					MDIO_84833_TOP_CFG_SCRATCH_REG2, &val);
-			if (val == PHY84833_CMD_OPEN_FOR_CMDS)
-				break;
-			usleep_range(1000, 1000);
-		}
-		if (idx >= PHY84833_HDSHK_WAIT) {
-			DP(NETIF_MSG_LINK, "AutogrEEEn: FW not ready.\n");
-			return -EINVAL;
-		}
-
-		/* Select EEE mode */
-		bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-				MDIO_84833_TOP_CFG_SCRATCH_REG3,
-				0x2);
-
-		/* Set Idle and Latency */
-		bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-				MDIO_84833_TOP_CFG_SCRATCH_REG4,
-				PHY84833_CONSTANT_LATENCY + 1);
-
-		bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-				MDIO_84833_TOP_CFG_DATA3_REG,
-				PHY84833_CONSTANT_LATENCY + 1);
-
-		bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-				MDIO_84833_TOP_CFG_DATA4_REG,
-				PHY84833_CONSTANT_LATENCY);
-
-		/* Send EEE instruction to command register */
-		bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-				MDIO_84833_TOP_CFG_SCRATCH_REG0,
-				PHY84833_DIAG_CMD_SET_EEE_MODE);
-
-		/* Ensure that the command has completed */
-		for (idx = 0; idx < PHY84833_HDSHK_WAIT; idx++) {
-			bnx2x_cl45_read(bp, phy, MDIO_CTL_DEVAD,
-					MDIO_84833_TOP_CFG_SCRATCH_REG2, &val);
-			if ((val == PHY84833_CMD_COMPLETE_PASS) ||
-				(val == PHY84833_CMD_COMPLETE_ERROR))
-				break;
-			usleep_range(1000, 1000);
-		}
-		if ((idx >= PHY84833_HDSHK_WAIT) ||
-			(val == PHY84833_CMD_COMPLETE_ERROR)) {
-			DP(NETIF_MSG_LINK, "AutogrEEEn: command failed.\n");
-			return -EINVAL;
-		}
-
-		/* Reset command handler */
-		bnx2x_cl45_write(bp, phy, MDIO_CTL_DEVAD,
-			    MDIO_84833_TOP_CFG_SCRATCH_REG2,
-			    PHY84833_CMD_CLEAR_COMPLETE);
-	}
+		FEATURE_CONFIG_AUTOGREEEN_ENABLED)
+		cmd_args[0] = 0x2;
+	else
+		cmd_args[0] = 0x0;
 
+	cmd_args[1] = 0x0;
+	cmd_args[2] = PHY84833_CONSTANT_LATENCY + 1;
+	cmd_args[3] = PHY84833_CONSTANT_LATENCY;
+	rc = bnx2x_84833_cmd_hdlr(phy, params,
+		PHY84833_CMD_SET_EEE_MODE, cmd_args);
+	if (rc != 0)
+		DP(NETIF_MSG_LINK, "Cfg AutogrEEEn failed.\n");
 	if (initialize)
 		rc = bnx2x_848xx_cmn_config_init(phy, params, vars);
 	else
@@ -10144,8 +10216,10 @@ static int bnx2x_54618se_config_init(struct bnx2x_phy *phy,
 	DP(NETIF_MSG_LINK, "54618SE cfg init\n");
 	usleep_range(1000, 1000);
 
-	/* This works with E3 only, no need to check the chip
-	   before determining the port. */
+	/*
+	 * This works with E3 only, no need to check the chip
+	 * before determining the port.
+	 */
 	port = params->port;
 
 	cfg_pin = (REG_RD(bp, params->shmem_base +
@@ -10327,6 +10401,43 @@ static int bnx2x_54618se_config_init(struct bnx2x_phy *phy,
 	return 0;
 }
 
+
+static void bnx2x_5461x_set_link_led(struct bnx2x_phy *phy,
+				       struct link_params *params, u8 mode)
+{
+	struct bnx2x *bp = params->bp;
+	u16 temp;
+
+	bnx2x_cl22_write(bp, phy,
+		MDIO_REG_GPHY_SHADOW,
+		MDIO_REG_GPHY_SHADOW_LED_SEL1);
+	bnx2x_cl22_read(bp, phy,
+		MDIO_REG_GPHY_SHADOW,
+		&temp);
+	temp &= 0xff00;
+
+	DP(NETIF_MSG_LINK, "54618x set link led (mode=%x)\n", mode);
+	switch (mode) {
+	case LED_MODE_FRONT_PANEL_OFF:
+	case LED_MODE_OFF:
+		temp |= 0x00ee;
+		break;
+	case LED_MODE_OPER:
+		temp |= 0x0001;
+		break;
+	case LED_MODE_ON:
+		temp |= 0x00ff;
+		break;
+	default:
+		break;
+	}
+	bnx2x_cl22_write(bp, phy,
+		MDIO_REG_GPHY_SHADOW,
+		MDIO_REG_GPHY_SHADOW_WR_ENA | temp);
+	return;
+}
+
+
 static void bnx2x_54618se_link_reset(struct bnx2x_phy *phy,
 				     struct link_params *params)
 {
@@ -11103,7 +11214,7 @@ static struct bnx2x_phy phy_54618se = {
 	.config_loopback = (config_loopback_t)bnx2x_54618se_config_loopback,
 	.format_fw_ver	= (format_fw_ver_t)NULL,
 	.hw_reset	= (hw_reset_t)NULL,
-	.set_link_led	= (set_link_led_t)NULL,
+	.set_link_led	= (set_link_led_t)bnx2x_5461x_set_link_led,
 	.phy_specific_func = (phy_specific_func_t)NULL
 };
 /*****************************************************************/
@@ -11181,7 +11292,9 @@ static int bnx2x_populate_int_phy(struct bnx2x *bp, u32 shmem_base, u8 port,
 				       offsetof(struct shmem_region,
 			dev_info.port_feature_config[port].link_config)) &
 			  PORT_FEATURE_CONNECTED_SWITCH_MASK);
-	chip_id = REG_RD(bp, MISC_REG_CHIP_NUM) << 16;
+	chip_id = (REG_RD(bp, MISC_REG_CHIP_NUM) << 16) |
+		((REG_RD(bp, MISC_REG_CHIP_REV) & 0xf) << 12);
+
 	DP(NETIF_MSG_LINK, ":chip_id = 0x%x\n", chip_id);
 	if (USES_WARPCORE(bp)) {
 		u32 serdes_net_if;
@@ -11360,6 +11473,10 @@ static int bnx2x_populate_ext_phy(struct bnx2x *bp,
 		return -EINVAL;
 	default:
 		*phy = phy_null;
+		/* In case external PHY wasn't found */
+		if ((phy_type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_DIRECT) &&
+		    (phy_type != PORT_HW_CFG_XGXS_EXT_PHY_TYPE_NOT_CONN))
+			return -EINVAL;
 		return 0;
 	}
 
@@ -11533,7 +11650,7 @@ u32 bnx2x_phy_selection(struct link_params *params)
 
 int bnx2x_phy_probe(struct link_params *params)
 {
-	u8 phy_index, actual_phy_idx, link_cfg_idx;
+	u8 phy_index, actual_phy_idx;
 	u32 phy_config_swapped, sync_offset, media_types;
 	struct bnx2x *bp = params->bp;
 	struct bnx2x_phy *phy;
@@ -11544,7 +11661,6 @@ int bnx2x_phy_probe(struct link_params *params)
 
 	for (phy_index = INT_PHY; phy_index < MAX_PHYS;
 	      phy_index++) {
-		link_cfg_idx = LINK_CONFIG_IDX(phy_index);
 		actual_phy_idx = phy_index;
 		if (phy_config_swapped) {
 			if (phy_index == EXT_PHY1)
@@ -12210,6 +12326,63 @@ static int bnx2x_8727_common_init_phy(struct bnx2x *bp,
 	return 0;
 }
 
+static int bnx2x_84833_common_init_phy(struct bnx2x *bp,
+						u32 shmem_base_path[],
+						u32 shmem2_base_path[],
+						u8 phy_index,
+						u32 chip_id)
+{
+	u8 reset_gpios;
+	struct bnx2x_phy phy;
+	u32 shmem_base, shmem2_base, cnt;
+	s8 port = 0;
+	u16 val;
+
+	reset_gpios = bnx2x_84833_get_reset_gpios(bp, shmem_base_path, chip_id);
+	bnx2x_set_mult_gpio(bp, reset_gpios, MISC_REGISTERS_GPIO_OUTPUT_LOW);
+	udelay(10);
+	bnx2x_set_mult_gpio(bp, reset_gpios, MISC_REGISTERS_GPIO_OUTPUT_HIGH);
+	DP(NETIF_MSG_LINK, "84833 reset pulse on pin values 0x%x\n",
+		reset_gpios);
+	for (port = PORT_MAX - 1; port >= PORT_0; port--) {
+		/* This PHY is for E2 and E3. */
+		shmem_base = shmem_base_path[port];
+		shmem2_base = shmem2_base_path[port];
+		/* Extract the ext phy address for the port */
+		if (bnx2x_populate_phy(bp, phy_index, shmem_base, shmem2_base,
+				       0, &phy) !=
+		    0) {
+			DP(NETIF_MSG_LINK, "populate_phy failed\n");
+			return -EINVAL;
+		}
+
+		/* Wait for FW completing its initialization. */
+		for (cnt = 0; cnt < 1000; cnt++) {
+			bnx2x_cl45_read(bp, &phy,
+				MDIO_PMA_DEVAD,
+				MDIO_PMA_REG_CTRL, &val);
+			if (!(val & (1<<15)))
+				break;
+			msleep(1);
+		}
+		if (cnt >= 1000)
+			DP(NETIF_MSG_LINK,
+				"84833 Cmn reset timeout (%d)\n", port);
+
+		/* Put the port in super isolate mode. */
+		bnx2x_cl45_read(bp, &phy,
+				MDIO_CTL_DEVAD,
+				MDIO_84833_TOP_CFG_XGPHY_STRAP1, &val);
+		val |= MDIO_84833_SUPER_ISOLATE;
+		bnx2x_cl45_write(bp, &phy,
+				MDIO_CTL_DEVAD,
+				MDIO_84833_TOP_CFG_XGPHY_STRAP1, val);
+	}
+
+	return 0;
+}
+
+
 static int bnx2x_ext_phy_common_init(struct bnx2x *bp, u32 shmem_base_path[],
 				     u32 shmem2_base_path[], u8 phy_index,
 				     u32 ext_phy_type, u32 chip_id)
@@ -12244,7 +12417,9 @@ static int bnx2x_ext_phy_common_init(struct bnx2x *bp, u32 shmem_base_path[],
 		 * GPIO3's are linked, and so both need to be toggled
 		 * to obtain required 2us pulse.
 		 */
-		rc = bnx2x_84833_common_init_phy(bp, shmem_base_path, chip_id);
+		rc = bnx2x_84833_common_init_phy(bp, shmem_base_path,
+						shmem2_base_path,
+						phy_index, chip_id);
 		break;
 	case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_FAILURE:
 		rc = -EINVAL;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h
index 2a46e63..e02a68a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.h
@@ -479,7 +479,7 @@ int bnx2x_ets_strict(const struct link_params *params, const u8 strict_cos);
 /*  Configure the COS to ETS according to BW and SP settings.*/
 int bnx2x_ets_e3b0_config(const struct link_params *params,
 			 const struct link_vars *vars,
-			 const struct bnx2x_ets_params *ets_params);
+			 struct bnx2x_ets_params *ets_params);
 /* Read pfc statistic*/
 void bnx2x_pfc_statistic(struct link_params *params, struct link_vars *vars,
 						 u32 pfc_frames_sent[2],
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 6486ab8..ffeaaa9 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -2318,12 +2318,6 @@ static void bnx2x_calc_vn_weight_sum(struct bnx2x *bp)
 					CMNG_FLAGS_PER_PORT_FAIRNESS_VN;
 }
 
-/* returns func by VN for current port */
-static inline int func_by_vn(struct bnx2x *bp, int vn)
-{
-	return 2 * vn + BP_PORT(bp);
-}
-
 static void bnx2x_init_vn_minmax(struct bnx2x *bp, int vn)
 {
 	struct rate_shaping_vars_per_vn m_rs_vn;
@@ -2475,22 +2469,6 @@ static void bnx2x_cmng_fns_init(struct bnx2x *bp, u8 read_cfg, u8 cmng_type)
 	   "rate shaping and fairness are disabled\n");
 }
 
-static inline void bnx2x_link_sync_notify(struct bnx2x *bp)
-{
-	int func;
-	int vn;
-
-	/* Set the attention towards other drivers on the same port */
-	for (vn = VN_0; vn < BP_MAX_VN_NUM(bp); vn++) {
-		if (vn == BP_VN(bp))
-			continue;
-
-		func = func_by_vn(bp, vn);
-		REG_WR(bp, MISC_REG_AEU_GENERAL_ATTN_0 +
-		       (LINK_SYNC_ATTENTION_BIT_FUNC_0 + func)*4, 1);
-	}
-}
-
 /* This function is called upon link interrupt */
 static void bnx2x_link_attn(struct bnx2x *bp)
 {
@@ -2549,6 +2527,9 @@ void bnx2x__link_status_update(struct bnx2x *bp)
 	if (bp->state != BNX2X_STATE_OPEN)
 		return;
 
+	/* read updated dcb configuration */
+	bnx2x_dcbx_pmf_update(bp);
+
 	bnx2x_link_status_update(&bp->link_params, &bp->link_vars);
 
 	if (bp->link_vars.link_up)
@@ -2643,15 +2624,6 @@ u32 bnx2x_fw_command(struct bnx2x *bp, u32 command, u32 param)
 	return rc;
 }
 
-static u8 stat_counter_valid(struct bnx2x *bp, struct bnx2x_fastpath *fp)
-{
-#ifdef BCM_CNIC
-	/* Statistics are not supported for CNIC Clients at the moment */
-	if (IS_FCOE_FP(fp))
-		return false;
-#endif
-	return true;
-}
 
 void bnx2x_func_init(struct bnx2x *bp, struct bnx2x_func_init_params *p)
 {
@@ -2695,11 +2667,11 @@ static inline unsigned long bnx2x_get_common_flags(struct bnx2x *bp,
 	 *  parent connection). The statistics are zeroed when the parent
 	 *  connection is initialized.
 	 */
-	if (stat_counter_valid(bp, fp)) {
-		__set_bit(BNX2X_Q_FLG_STATS, &flags);
-		if (zero_stats)
-			__set_bit(BNX2X_Q_FLG_ZERO_STATS, &flags);
-	}
+
+	__set_bit(BNX2X_Q_FLG_STATS, &flags);
+	if (zero_stats)
+		__set_bit(BNX2X_Q_FLG_ZERO_STATS, &flags);
+
 
 	return flags;
 }
@@ -2808,8 +2780,8 @@ static void bnx2x_pf_rx_q_prep(struct bnx2x *bp,
 	/* This should be a maximum number of data bytes that may be
 	 * placed on the BD (not including paddings).
 	 */
-	rxq_init->buf_sz = fp->rx_buf_size - BNX2X_FW_RX_ALIGN -
-		IP_HEADER_ALIGNMENT_PADDING;
+	rxq_init->buf_sz = fp->rx_buf_size - BNX2X_FW_RX_ALIGN_START -
+		BNX2X_FW_RX_ALIGN_END -	IP_HEADER_ALIGNMENT_PADDING;
 
 	rxq_init->cl_qzone_id = fp->cl_qzone_id;
 	rxq_init->tpa_agg_sz = tpa_agg_size;
@@ -2940,6 +2912,143 @@ static void bnx2x_e1h_enable(struct bnx2x *bp)
 	 */
 }
 
+#define DRV_INFO_ETH_STAT_NUM_MACS_REQUIRED 3
+
+static void bnx2x_drv_info_ether_stat(struct bnx2x *bp)
+{
+	struct eth_stats_info *ether_stat =
+		&bp->slowpath->drv_info_to_mcp.ether_stat;
+
+	/* leave last char as NULL */
+	memcpy(ether_stat->version, DRV_MODULE_VERSION,
+	       ETH_STAT_INFO_VERSION_LEN - 1);
+
+	bp->fp[0].mac_obj.get_n_elements(bp, &bp->fp[0].mac_obj,
+					 DRV_INFO_ETH_STAT_NUM_MACS_REQUIRED,
+					 ether_stat->mac_local);
+
+	ether_stat->mtu_size = bp->dev->mtu;
+
+	if (bp->dev->features & NETIF_F_RXCSUM)
+		ether_stat->feature_flags |= FEATURE_ETH_CHKSUM_OFFLOAD_MASK;
+	if (bp->dev->features & NETIF_F_TSO)
+		ether_stat->feature_flags |= FEATURE_ETH_LSO_MASK;
+	ether_stat->feature_flags |= bp->common.boot_mode;
+
+	ether_stat->promiscuous_mode = (bp->dev->flags & IFF_PROMISC) ? 1 : 0;
+
+	ether_stat->txq_size = bp->tx_ring_size;
+	ether_stat->rxq_size = bp->rx_ring_size;
+}
+
+static void bnx2x_drv_info_fcoe_stat(struct bnx2x *bp)
+{
+#ifdef BCM_CNIC
+	struct bnx2x_dcbx_app_params *app = &bp->dcbx_port_params.app;
+	struct fcoe_stats_info *fcoe_stat =
+		&bp->slowpath->drv_info_to_mcp.fcoe_stat;
+
+	memcpy(fcoe_stat->mac_local, bp->fip_mac, ETH_ALEN);
+
+	fcoe_stat->qos_priority =
+		app->traffic_type_priority[LLFC_TRAFFIC_TYPE_FCOE];
+
+	/* insert FCoE stats from ramrod response */
+	if (!NO_FCOE(bp)) {
+		struct tstorm_per_queue_stats *fcoe_q_tstorm_stats =
+			&bp->fw_stats_data->queue_stats[FCOE_IDX].
+			tstorm_queue_statistics;
+
+		struct xstorm_per_queue_stats *fcoe_q_xstorm_stats =
+			&bp->fw_stats_data->queue_stats[FCOE_IDX].
+			xstorm_queue_statistics;
+
+		struct fcoe_statistics_params *fw_fcoe_stat =
+			&bp->fw_stats_data->fcoe;
+
+		ADD_64(fcoe_stat->rx_bytes_hi, 0, fcoe_stat->rx_bytes_lo,
+		       fw_fcoe_stat->rx_stat0.fcoe_rx_byte_cnt);
+
+		ADD_64(fcoe_stat->rx_bytes_hi,
+		       fcoe_q_tstorm_stats->rcv_ucast_bytes.hi,
+		       fcoe_stat->rx_bytes_lo,
+		       fcoe_q_tstorm_stats->rcv_ucast_bytes.lo);
+
+		ADD_64(fcoe_stat->rx_bytes_hi,
+		       fcoe_q_tstorm_stats->rcv_bcast_bytes.hi,
+		       fcoe_stat->rx_bytes_lo,
+		       fcoe_q_tstorm_stats->rcv_bcast_bytes.lo);
+
+		ADD_64(fcoe_stat->rx_bytes_hi,
+		       fcoe_q_tstorm_stats->rcv_mcast_bytes.hi,
+		       fcoe_stat->rx_bytes_lo,
+		       fcoe_q_tstorm_stats->rcv_mcast_bytes.lo);
+
+		ADD_64(fcoe_stat->rx_frames_hi, 0, fcoe_stat->rx_frames_lo,
+		       fw_fcoe_stat->rx_stat0.fcoe_rx_pkt_cnt);
+
+		ADD_64(fcoe_stat->rx_frames_hi, 0, fcoe_stat->rx_frames_lo,
+		       fcoe_q_tstorm_stats->rcv_ucast_pkts);
+
+		ADD_64(fcoe_stat->rx_frames_hi, 0, fcoe_stat->rx_frames_lo,
+		       fcoe_q_tstorm_stats->rcv_bcast_pkts);
+
+		ADD_64(fcoe_stat->rx_frames_hi, 0, fcoe_stat->rx_frames_lo,
+		       fcoe_q_tstorm_stats->rcv_mcast_pkts);
+
+		ADD_64(fcoe_stat->tx_bytes_hi, 0, fcoe_stat->tx_bytes_lo,
+		       fw_fcoe_stat->tx_stat.fcoe_tx_byte_cnt);
+
+		ADD_64(fcoe_stat->tx_bytes_hi,
+		       fcoe_q_xstorm_stats->ucast_bytes_sent.hi,
+		       fcoe_stat->tx_bytes_lo,
+		       fcoe_q_xstorm_stats->ucast_bytes_sent.lo);
+
+		ADD_64(fcoe_stat->tx_bytes_hi,
+		       fcoe_q_xstorm_stats->bcast_bytes_sent.hi,
+		       fcoe_stat->tx_bytes_lo,
+		       fcoe_q_xstorm_stats->bcast_bytes_sent.lo);
+
+		ADD_64(fcoe_stat->tx_bytes_hi,
+		       fcoe_q_xstorm_stats->mcast_bytes_sent.hi,
+		       fcoe_stat->tx_bytes_lo,
+		       fcoe_q_xstorm_stats->mcast_bytes_sent.lo);
+
+		ADD_64(fcoe_stat->tx_frames_hi, 0, fcoe_stat->tx_frames_lo,
+		       fw_fcoe_stat->tx_stat.fcoe_tx_pkt_cnt);
+
+		ADD_64(fcoe_stat->tx_frames_hi, 0, fcoe_stat->tx_frames_lo,
+		       fcoe_q_xstorm_stats->ucast_pkts_sent);
+
+		ADD_64(fcoe_stat->tx_frames_hi, 0, fcoe_stat->tx_frames_lo,
+		       fcoe_q_xstorm_stats->bcast_pkts_sent);
+
+		ADD_64(fcoe_stat->tx_frames_hi, 0, fcoe_stat->tx_frames_lo,
+		       fcoe_q_xstorm_stats->mcast_pkts_sent);
+	}
+
+	/* ask L5 driver to add data to the struct */
+	bnx2x_cnic_notify(bp, CNIC_CTL_FCOE_STATS_GET_CMD);
+#endif
+}
+
+static void bnx2x_drv_info_iscsi_stat(struct bnx2x *bp)
+{
+#ifdef BCM_CNIC
+	struct bnx2x_dcbx_app_params *app = &bp->dcbx_port_params.app;
+	struct iscsi_stats_info *iscsi_stat =
+		&bp->slowpath->drv_info_to_mcp.iscsi_stat;
+
+	memcpy(iscsi_stat->mac_local, bp->cnic_eth_dev.iscsi_mac, ETH_ALEN);
+
+	iscsi_stat->qos_priority =
+		app->traffic_type_priority[LLFC_TRAFFIC_TYPE_ISCSI];
+
+	/* ask L5 driver to add data to the struct */
+	bnx2x_cnic_notify(bp, CNIC_CTL_ISCSI_STATS_GET_CMD);
+#endif
+}
+
 /* called due to MCP event (on pmf):
  *	reread new bandwidth configuration
  *	configure FW
@@ -2960,6 +3069,50 @@ static inline void bnx2x_set_mf_bw(struct bnx2x *bp)
 	bnx2x_fw_command(bp, DRV_MSG_CODE_SET_MF_BW_ACK, 0);
 }
 
+static void bnx2x_handle_drv_info_req(struct bnx2x *bp)
+{
+	enum drv_info_opcode op_code;
+	u32 drv_info_ctl = SHMEM2_RD(bp, drv_info_control);
+
+	/* if drv_info version supported by MFW doesn't match - send NACK */
+	if ((drv_info_ctl & DRV_INFO_CONTROL_VER_MASK) != DRV_INFO_CUR_VER) {
+		bnx2x_fw_command(bp, DRV_MSG_CODE_DRV_INFO_NACK, 0);
+		return;
+	}
+
+	op_code = (drv_info_ctl & DRV_INFO_CONTROL_OP_CODE_MASK) >>
+		  DRV_INFO_CONTROL_OP_CODE_SHIFT;
+
+	memset(&bp->slowpath->drv_info_to_mcp, 0,
+	       sizeof(union drv_info_to_mcp));
+
+	switch (op_code) {
+	case ETH_STATS_OPCODE:
+		bnx2x_drv_info_ether_stat(bp);
+		break;
+	case FCOE_STATS_OPCODE:
+		bnx2x_drv_info_fcoe_stat(bp);
+		break;
+	case ISCSI_STATS_OPCODE:
+		bnx2x_drv_info_iscsi_stat(bp);
+		break;
+	default:
+		/* if op code isn't supported - send NACK */
+		bnx2x_fw_command(bp, DRV_MSG_CODE_DRV_INFO_NACK, 0);
+		return;
+	}
+
+	/* if we got drv_info attn from MFW then these fields are defined in
+	 * shmem2 for sure
+	 */
+	SHMEM2_WR(bp, drv_info_host_addr_lo,
+		U64_LO(bnx2x_sp_mapping(bp, drv_info_to_mcp)));
+	SHMEM2_WR(bp, drv_info_host_addr_hi,
+		U64_HI(bnx2x_sp_mapping(bp, drv_info_to_mcp)));
+
+	bnx2x_fw_command(bp, DRV_MSG_CODE_DRV_INFO_ACK, 0);
+}
+
 static void bnx2x_dcc_event(struct bnx2x *bp, u32 dcc_event)
 {
 	DP(BNX2X_MSG_MCP, "dcc_event 0x%x\n", dcc_event);
@@ -3318,6 +3471,17 @@ static inline void bnx2x_fan_failure(struct bnx2x *bp)
 	netdev_err(bp->dev, "Fan Failure on Network Controller has caused"
 	       " the driver to shutdown the card to prevent permanent"
 	       " damage.  Please contact OEM Support for assistance\n");
+
+	/*
+	 * Scheudle device reset (unload)
+	 * This is due to some boards consuming sufficient power when driver is
+	 * up to overheat if fan fails.
+	 */
+	smp_mb__before_clear_bit();
+	set_bit(BNX2X_SP_RTNL_FAN_FAILURE, &bp->sp_rtnl_state);
+	smp_mb__after_clear_bit();
+	schedule_delayed_work(&bp->sp_rtnl_task, 0);
+
 }
 
 static inline void bnx2x_attn_int_deasserted0(struct bnx2x *bp, u32 attn)
@@ -3456,6 +3620,8 @@ static inline void bnx2x_attn_int_deasserted3(struct bnx2x *bp, u32 attn)
 			if (val & DRV_STATUS_SET_MF_BW)
 				bnx2x_set_mf_bw(bp);
 
+			if (val & DRV_STATUS_DRV_INFO_REQ)
+				bnx2x_handle_drv_info_req(bp);
 			if ((bp->port.pmf == 0) && (val & DRV_STATUS_PMF))
 				bnx2x_pmf_update(bp);
 
@@ -5247,7 +5413,7 @@ static void bnx2x_init_eth_fp(struct bnx2x *bp, int fp_idx)
 	u8 cos;
 	unsigned long q_type = 0;
 	u32 cids[BNX2X_MULTI_TX_COS] = { 0 };
-
+	fp->rx_queue = fp_idx;
 	fp->cid = fp_idx;
 	fp->cl_id = bnx2x_fp_cl_id(fp);
 	fp->fw_sb_id = bnx2x_fp_fw_sb_id(fp);
@@ -6856,13 +7022,16 @@ void bnx2x_free_mem(struct bnx2x *bp)
 static inline int bnx2x_alloc_fw_stats_mem(struct bnx2x *bp)
 {
 	int num_groups;
+	int is_fcoe_stats = NO_FCOE(bp) ? 0 : 1;
 
-	/* number of eth_queues */
-	u8 num_queue_stats = BNX2X_NUM_ETH_QUEUES(bp);
+	/* number of queues for statistics is number of eth queues + FCoE */
+	u8 num_queue_stats = BNX2X_NUM_ETH_QUEUES(bp) + is_fcoe_stats;
 
 	/* Total number of FW statistics requests =
-	 * 1 for port stats + 1 for PF stats + num_eth_queues */
-	bp->fw_stats_num = 2 + num_queue_stats;
+	 * 1 for port stats + 1 for PF stats + potential 1 for FCoE stats +
+	 * num of queues
+	 */
+	bp->fw_stats_num = 2 + is_fcoe_stats + num_queue_stats;
 
 
 	/* Request is built from stats_query_header and an array of
@@ -6870,8 +7039,8 @@ static inline int bnx2x_alloc_fw_stats_mem(struct bnx2x *bp)
 	 * STATS_QUERY_CMD_COUNT rules. The real number or requests is
 	 * configured in the stats_query_header.
 	 */
-	num_groups = (2 + num_queue_stats) / STATS_QUERY_CMD_COUNT +
-		(((2 + num_queue_stats) % STATS_QUERY_CMD_COUNT) ? 1 : 0);
+	num_groups = ((bp->fw_stats_num) / STATS_QUERY_CMD_COUNT) +
+		     (((bp->fw_stats_num) % STATS_QUERY_CMD_COUNT) ? 1 : 0);
 
 	bp->fw_stats_req_sz = sizeof(struct stats_query_header) +
 			num_groups * sizeof(struct stats_query_cmd_group);
@@ -6880,9 +7049,13 @@ static inline int bnx2x_alloc_fw_stats_mem(struct bnx2x *bp)
 	 *
 	 * stats_counter holds per-STORM counters that are incremented
 	 * when STORM has finished with the current request.
+	 *
+	 * memory for FCoE offloaded statistics are counted anyway,
+	 * even if they will not be sent.
 	 */
 	bp->fw_stats_data_sz = sizeof(struct per_port_stats) +
 		sizeof(struct per_pf_stats) +
+		sizeof(struct fcoe_statistics_params) +
 		sizeof(struct per_queue_stats) * num_queue_stats +
 		sizeof(struct stats_counter);
 
@@ -7025,6 +7198,13 @@ int bnx2x_set_eth_mac(struct bnx2x *bp, bool set)
 {
 	unsigned long ramrod_flags = 0;
 
+#ifdef BCM_CNIC
+	if (is_zero_ether_addr(bp->dev->dev_addr) && IS_MF_ISCSI_SD(bp)) {
+		DP(NETIF_MSG_IFUP, "Ignoring Zero MAC for iSCSI SD mode\n");
+		return 0;
+	}
+#endif
+
 	DP(NETIF_MSG_IFUP, "Adding Eth MAC\n");
 
 	__set_bit(RAMROD_COMP_WAIT, &ramrod_flags);
@@ -8522,6 +8702,17 @@ sp_rtnl_not_reset:
 	if (test_and_clear_bit(BNX2X_SP_RTNL_SETUP_TC, &bp->sp_rtnl_state))
 		bnx2x_setup_tc(bp->dev, bp->dcbx_port_params.ets.num_of_cos);
 
+	/*
+	 * in case of fan failure we need to reset id if the "stop on error"
+	 * debug flag is set, since we trying to prevent permanent overheating
+	 * damage
+	 */
+	if (test_and_clear_bit(BNX2X_SP_RTNL_FAN_FAILURE, &bp->sp_rtnl_state)) {
+		DP(BNX2X_MSG_SP, "fan failure detected. Unloading driver\n");
+		netif_device_detach(bp->dev);
+		bnx2x_close(bp->dev);
+	}
+
 sp_rtnl_exit:
 	rtnl_unlock();
 }
@@ -8708,7 +8899,7 @@ static void __devinit bnx2x_undi_unload(struct bnx2x *bp)
 
 static void __devinit bnx2x_get_common_hwinfo(struct bnx2x *bp)
 {
-	u32 val, val2, val3, val4, id;
+	u32 val, val2, val3, val4, id, boot_mode;
 	u16 pmc;
 
 	/* Get the chip revision id and number. */
@@ -8817,6 +9008,26 @@ static void __devinit bnx2x_get_common_hwinfo(struct bnx2x *bp)
 	bp->link_params.feature_config_flags |=
 		(val >= REQ_BC_VER_4_SFP_TX_DISABLE_SUPPORTED) ?
 		FEATURE_CONFIG_BC_SUPPORTS_SFP_TX_DISABLED : 0;
+	bp->flags |= (val >= REQ_BC_VER_4_PFC_STATS_SUPPORTED) ?
+			BC_SUPPORTS_PFC_STATS : 0;
+
+	boot_mode = SHMEM_RD(bp,
+			dev_info.port_feature_config[BP_PORT(bp)].mba_config) &
+			PORT_FEATURE_MBA_BOOT_AGENT_TYPE_MASK;
+	switch (boot_mode) {
+	case PORT_FEATURE_MBA_BOOT_AGENT_TYPE_PXE:
+		bp->common.boot_mode = FEATURE_ETH_BOOTMODE_PXE;
+		break;
+	case PORT_FEATURE_MBA_BOOT_AGENT_TYPE_ISCSIB:
+		bp->common.boot_mode = FEATURE_ETH_BOOTMODE_ISCSI;
+		break;
+	case PORT_FEATURE_MBA_BOOT_AGENT_TYPE_FCOE_BOOT:
+		bp->common.boot_mode = FEATURE_ETH_BOOTMODE_FCOE;
+		break;
+	case PORT_FEATURE_MBA_BOOT_AGENT_TYPE_NONE:
+		bp->common.boot_mode = FEATURE_ETH_BOOTMODE_NONE;
+		break;
+	}
 
 	pci_read_config_word(bp->pdev, bp->pm_cap + PCI_PM_PMC, &pmc);
 	bp->flags |= (pmc & PCI_PM_CAP_PME_D3cold) ? 0 : NO_WOL_FLAG;
@@ -9267,22 +9478,43 @@ static void __devinit bnx2x_get_port_hwinfo(struct bnx2x *bp)
 							bp->common.shmem2_base);
 }
 
-#ifdef BCM_CNIC
-static void __devinit bnx2x_get_cnic_info(struct bnx2x *bp)
+void bnx2x_get_iscsi_info(struct bnx2x *bp)
 {
+#ifdef BCM_CNIC
 	int port = BP_PORT(bp);
-	int func = BP_ABS_FUNC(bp);
 
 	u32 max_iscsi_conn = FW_ENCODE_32BIT_PATTERN ^ SHMEM_RD(bp,
 				drv_lic_key[port].max_iscsi_conn);
-	u32 max_fcoe_conn = FW_ENCODE_32BIT_PATTERN ^ SHMEM_RD(bp,
-				drv_lic_key[port].max_fcoe_conn);
 
-	/* Get the number of maximum allowed iSCSI and FCoE connections */
+	/* Get the number of maximum allowed iSCSI connections */
 	bp->cnic_eth_dev.max_iscsi_conn =
 		(max_iscsi_conn & BNX2X_MAX_ISCSI_INIT_CONN_MASK) >>
 		BNX2X_MAX_ISCSI_INIT_CONN_SHIFT;
 
+	BNX2X_DEV_INFO("max_iscsi_conn 0x%x\n",
+		       bp->cnic_eth_dev.max_iscsi_conn);
+
+	/*
+	 * If maximum allowed number of connections is zero -
+	 * disable the feature.
+	 */
+	if (!bp->cnic_eth_dev.max_iscsi_conn)
+		bp->flags |= NO_ISCSI_FLAG;
+#else
+	bp->flags |= NO_ISCSI_FLAG;
+#endif
+}
+
+static void __devinit bnx2x_get_fcoe_info(struct bnx2x *bp)
+{
+#ifdef BCM_CNIC
+	int port = BP_PORT(bp);
+	int func = BP_ABS_FUNC(bp);
+
+	u32 max_fcoe_conn = FW_ENCODE_32BIT_PATTERN ^ SHMEM_RD(bp,
+				drv_lic_key[port].max_fcoe_conn);
+
+	/* Get the number of maximum allowed FCoE connections */
 	bp->cnic_eth_dev.max_fcoe_conn =
 		(max_fcoe_conn & BNX2X_MAX_FCOE_INIT_CONN_MASK) >>
 		BNX2X_MAX_FCOE_INIT_CONN_SHIFT;
@@ -9334,21 +9566,29 @@ static void __devinit bnx2x_get_cnic_info(struct bnx2x *bp)
 		}
 	}
 
-	BNX2X_DEV_INFO("max_iscsi_conn 0x%x max_fcoe_conn 0x%x\n",
-		       bp->cnic_eth_dev.max_iscsi_conn,
-		       bp->cnic_eth_dev.max_fcoe_conn);
+	BNX2X_DEV_INFO("max_fcoe_conn 0x%x\n", bp->cnic_eth_dev.max_fcoe_conn);
 
 	/*
 	 * If maximum allowed number of connections is zero -
 	 * disable the feature.
 	 */
-	if (!bp->cnic_eth_dev.max_iscsi_conn)
-		bp->flags |= NO_ISCSI_OOO_FLAG | NO_ISCSI_FLAG;
-
 	if (!bp->cnic_eth_dev.max_fcoe_conn)
 		bp->flags |= NO_FCOE_FLAG;
-}
+#else
+	bp->flags |= NO_FCOE_FLAG;
 #endif
+}
+
+static void __devinit bnx2x_get_cnic_info(struct bnx2x *bp)
+{
+	/*
+	 * iSCSI may be dynamically disabled but reading
+	 * info here we will decrease memory usage by driver
+	 * if the feature is disabled for good
+	 */
+	bnx2x_get_iscsi_info(bp);
+	bnx2x_get_fcoe_info(bp);
+}
 
 static void __devinit bnx2x_get_mac_hwinfo(struct bnx2x *bp)
 {
@@ -9374,7 +9614,8 @@ static void __devinit bnx2x_get_mac_hwinfo(struct bnx2x *bp)
 			bnx2x_set_mac_buf(bp->dev->dev_addr, val, val2);
 
 #ifdef BCM_CNIC
-		/* iSCSI and FCoE NPAR MACs: if there is no either iSCSI or
+		/*
+		 * iSCSI and FCoE NPAR MACs: if there is no either iSCSI or
 		 * FCoE MAC then the appropriate feature should be disabled.
 		 */
 		if (IS_MF_SI(bp)) {
@@ -9396,11 +9637,22 @@ static void __devinit bnx2x_get_mac_hwinfo(struct bnx2x *bp)
 				val = MF_CFG_RD(bp, func_ext_config[func].
 						    fcoe_mac_addr_lower);
 				bnx2x_set_mac_buf(fip_mac, val, val2);
-				BNX2X_DEV_INFO("Read FCoE L2 MAC to %pM\n",
+				BNX2X_DEV_INFO("Read FCoE L2 MAC: %pM\n",
 					       fip_mac);
 
 			} else
 				bp->flags |= NO_FCOE_FLAG;
+		} else { /* SD mode */
+			if (BNX2X_IS_MF_PROTOCOL_ISCSI(bp)) {
+				/* use primary mac as iscsi mac */
+				memcpy(iscsi_mac, bp->dev->dev_addr, ETH_ALEN);
+				/* Zero primary MAC configuration */
+				memset(bp->dev->dev_addr, 0, ETH_ALEN);
+
+				BNX2X_DEV_INFO("SD ISCSI MODE\n");
+				BNX2X_DEV_INFO("Read iSCSI MAC: %pM\n",
+					       iscsi_mac);
+			}
 		}
 #endif
 	} else {
@@ -9449,7 +9701,7 @@ static void __devinit bnx2x_get_mac_hwinfo(struct bnx2x *bp)
 	}
 #endif
 
-	if (!is_valid_ether_addr(bp->dev->dev_addr))
+	if (!bnx2x_is_valid_ether_addr(bp, bp->dev->dev_addr))
 		dev_err(&bp->pdev->dev,
 			"bad Ethernet MAC address configuration: "
 			"%pM, change it manually before bringing up "
@@ -9661,9 +9913,7 @@ static int __devinit bnx2x_get_hwinfo(struct bnx2x *bp)
 	/* Get MAC addresses */
 	bnx2x_get_mac_hwinfo(bp);
 
-#ifdef BCM_CNIC
 	bnx2x_get_cnic_info(bp);
-#endif
 
 	/* Get current FW pulse sequence */
 	if (!BP_NOMCP(bp)) {
@@ -9681,30 +9931,49 @@ static int __devinit bnx2x_get_hwinfo(struct bnx2x *bp)
 static void __devinit bnx2x_read_fwinfo(struct bnx2x *bp)
 {
 	int cnt, i, block_end, rodi;
-	char vpd_data[BNX2X_VPD_LEN+1];
+	char vpd_start[BNX2X_VPD_LEN+1];
 	char str_id_reg[VENDOR_ID_LEN+1];
 	char str_id_cap[VENDOR_ID_LEN+1];
+	char *vpd_data;
+	char *vpd_extended_data = NULL;
 	u8 len;
 
-	cnt = pci_read_vpd(bp->pdev, 0, BNX2X_VPD_LEN, vpd_data);
+	cnt = pci_read_vpd(bp->pdev, 0, BNX2X_VPD_LEN, vpd_start);
 	memset(bp->fw_ver, 0, sizeof(bp->fw_ver));
 
 	if (cnt < BNX2X_VPD_LEN)
 		goto out_not_found;
 
-	i = pci_vpd_find_tag(vpd_data, 0, BNX2X_VPD_LEN,
+	/* VPD RO tag should be first tag after identifier string, hence
+	 * we should be able to find it in first BNX2X_VPD_LEN chars
+	 */
+	i = pci_vpd_find_tag(vpd_start, 0, BNX2X_VPD_LEN,
 			     PCI_VPD_LRDT_RO_DATA);
 	if (i < 0)
 		goto out_not_found;
 
-
 	block_end = i + PCI_VPD_LRDT_TAG_SIZE +
-		    pci_vpd_lrdt_size(&vpd_data[i]);
+		    pci_vpd_lrdt_size(&vpd_start[i]);
 
 	i += PCI_VPD_LRDT_TAG_SIZE;
 
-	if (block_end > BNX2X_VPD_LEN)
-		goto out_not_found;
+	if (block_end > BNX2X_VPD_LEN) {
+		vpd_extended_data = kmalloc(block_end, GFP_KERNEL);
+		if (vpd_extended_data  == NULL)
+			goto out_not_found;
+
+		/* read rest of vpd image into vpd_extended_data */
+		memcpy(vpd_extended_data, vpd_start, BNX2X_VPD_LEN);
+		cnt = pci_read_vpd(bp->pdev, BNX2X_VPD_LEN,
+				   block_end - BNX2X_VPD_LEN,
+				   vpd_extended_data + BNX2X_VPD_LEN);
+		if (cnt < (block_end - BNX2X_VPD_LEN))
+			goto out_not_found;
+		vpd_data = vpd_extended_data;
+	} else
+		vpd_data = vpd_start;
+
+	/* now vpd_data holds full vpd content in both cases */
 
 	rodi = pci_vpd_find_info_keyword(vpd_data, i, block_end,
 				   PCI_VPD_RO_KEYWORD_MFR_ID);
@@ -9736,9 +10005,11 @@ static void __devinit bnx2x_read_fwinfo(struct bnx2x *bp)
 				bp->fw_ver[len] = ' ';
 			}
 		}
+		kfree(vpd_extended_data);
 		return;
 	}
 out_not_found:
+	kfree(vpd_extended_data);
 	return;
 }
 
@@ -9840,15 +10111,20 @@ static int __devinit bnx2x_init_bp(struct bnx2x *bp)
 
 	bp->multi_mode = multi_mode;
 
+	bp->disable_tpa = disable_tpa;
+
+#ifdef BCM_CNIC
+	bp->disable_tpa |= IS_MF_ISCSI_SD(bp);
+#endif
+
 	/* Set TPA flags */
-	if (disable_tpa) {
+	if (bp->disable_tpa) {
 		bp->flags &= ~TPA_ENABLE_FLAG;
 		bp->dev->features &= ~NETIF_F_LRO;
 	} else {
 		bp->flags |= TPA_ENABLE_FLAG;
 		bp->dev->features |= NETIF_F_LRO;
 	}
-	bp->disable_tpa = disable_tpa;
 
 	if (CHIP_IS_E1(bp))
 		bp->dropless_fc = 0;
@@ -9965,7 +10241,7 @@ static int bnx2x_open(struct net_device *dev)
 }
 
 /* called with rtnl_lock */
-static int bnx2x_close(struct net_device *dev)
+int bnx2x_close(struct net_device *dev)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
@@ -10119,6 +10395,11 @@ void bnx2x_set_rx_mode(struct net_device *dev)
 	}
 
 	bp->rx_mode = rx_mode;
+#ifdef BCM_CNIC
+	/* handle ISCSI SD mode */
+	if (IS_MF_ISCSI_SD(bp))
+		bp->rx_mode = BNX2X_RX_MODE_NONE;
+#endif
 
 	/* Schedule the rx_mode command */
 	if (test_bit(BNX2X_FILTER_RX_MODE_PENDING, &bp->sp_state)) {
@@ -10198,6 +10479,15 @@ static void poll_bnx2x(struct net_device *dev)
 }
 #endif
 
+static int bnx2x_validate_addr(struct net_device *dev)
+{
+	struct bnx2x *bp = netdev_priv(dev);
+
+	if (!bnx2x_is_valid_ether_addr(bp, dev->dev_addr))
+		return -EADDRNOTAVAIL;
+	return 0;
+}
+
 static const struct net_device_ops bnx2x_netdev_ops = {
 	.ndo_open		= bnx2x_open,
 	.ndo_stop		= bnx2x_close,
@@ -10205,7 +10495,7 @@ static const struct net_device_ops bnx2x_netdev_ops = {
 	.ndo_select_queue	= bnx2x_select_queue,
 	.ndo_set_rx_mode	= bnx2x_set_rx_mode,
 	.ndo_set_mac_address	= bnx2x_change_mac_addr,
-	.ndo_validate_addr	= eth_validate_addr,
+	.ndo_validate_addr	= bnx2x_validate_addr,
 	.ndo_do_ioctl		= bnx2x_ioctl,
 	.ndo_change_mtu		= bnx2x_change_mtu,
 	.ndo_fix_features	= bnx2x_fix_features,
@@ -10548,33 +10838,38 @@ do {									\
 
 int bnx2x_init_firmware(struct bnx2x *bp)
 {
-	const char *fw_file_name;
 	struct bnx2x_fw_file_hdr *fw_hdr;
 	int rc;
 
-	if (CHIP_IS_E1(bp))
-		fw_file_name = FW_FILE_NAME_E1;
-	else if (CHIP_IS_E1H(bp))
-		fw_file_name = FW_FILE_NAME_E1H;
-	else if (!CHIP_IS_E1x(bp))
-		fw_file_name = FW_FILE_NAME_E2;
-	else {
-		BNX2X_ERR("Unsupported chip revision\n");
-		return -EINVAL;
-	}
 
-	BNX2X_DEV_INFO("Loading %s\n", fw_file_name);
+	if (!bp->firmware) {
+		const char *fw_file_name;
 
-	rc = request_firmware(&bp->firmware, fw_file_name, &bp->pdev->dev);
-	if (rc) {
-		BNX2X_ERR("Can't load firmware file %s\n", fw_file_name);
-		goto request_firmware_exit;
-	}
+		if (CHIP_IS_E1(bp))
+			fw_file_name = FW_FILE_NAME_E1;
+		else if (CHIP_IS_E1H(bp))
+			fw_file_name = FW_FILE_NAME_E1H;
+		else if (!CHIP_IS_E1x(bp))
+			fw_file_name = FW_FILE_NAME_E2;
+		else {
+			BNX2X_ERR("Unsupported chip revision\n");
+			return -EINVAL;
+		}
+		BNX2X_DEV_INFO("Loading %s\n", fw_file_name);
 
-	rc = bnx2x_check_firmware(bp);
-	if (rc) {
-		BNX2X_ERR("Corrupt firmware file %s\n", fw_file_name);
-		goto request_firmware_exit;
+		rc = request_firmware(&bp->firmware, fw_file_name,
+				      &bp->pdev->dev);
+		if (rc) {
+			BNX2X_ERR("Can't load firmware file %s\n",
+				  fw_file_name);
+			goto request_firmware_exit;
+		}
+
+		rc = bnx2x_check_firmware(bp);
+		if (rc) {
+			BNX2X_ERR("Corrupt firmware file %s\n", fw_file_name);
+			goto request_firmware_exit;
+		}
 	}
 
 	fw_hdr = (struct bnx2x_fw_file_hdr *)bp->firmware->data;
@@ -10630,6 +10925,7 @@ static void bnx2x_release_firmware(struct bnx2x *bp)
 	kfree(bp->init_ops);
 	kfree(bp->init_data);
 	release_firmware(bp->firmware);
+	bp->firmware = NULL;
 }
 
 
@@ -10817,8 +11113,8 @@ static int __devinit bnx2x_init_one(struct pci_dev *pdev,
 	bp->qm_cid_count = bnx2x_set_qm_cid_count(bp);
 
 #ifdef BCM_CNIC
-	/* disable FCOE L2 queue for E1x and E3*/
-	if (CHIP_IS_E1x(bp) || CHIP_IS_E3(bp))
+	/* disable FCOE L2 queue for E1x */
+	if (CHIP_IS_E1x(bp))
 		bp->flags |= NO_FCOE_FLAG;
 
 #endif
@@ -10925,6 +11221,8 @@ static void __devexit bnx2x_remove_one(struct pci_dev *pdev)
 	if (bp->doorbells)
 		iounmap(bp->doorbells);
 
+	bnx2x_release_firmware(bp);
+
 	bnx2x_free_mem_bp(bp);
 
 	free_netdev(dev);
@@ -11478,6 +11776,38 @@ static int bnx2x_drv_ctl(struct net_device *dev, struct drv_ctl_info *ctl)
 		smp_mb__after_atomic_inc();
 		break;
 	}
+	case DRV_CTL_ULP_REGISTER_CMD: {
+		int ulp_type = ctl->data.ulp_type;
+
+		if (CHIP_IS_E3(bp)) {
+			int idx = BP_FW_MB_IDX(bp);
+			u32 cap;
+
+			cap = SHMEM2_RD(bp, drv_capabilities_flag[idx]);
+			if (ulp_type == CNIC_ULP_ISCSI)
+				cap |= DRV_FLAGS_CAPABILITIES_LOADED_ISCSI;
+			else if (ulp_type == CNIC_ULP_FCOE)
+				cap |= DRV_FLAGS_CAPABILITIES_LOADED_FCOE;
+			SHMEM2_WR(bp, drv_capabilities_flag[idx], cap);
+		}
+		break;
+	}
+	case DRV_CTL_ULP_UNREGISTER_CMD: {
+		int ulp_type = ctl->data.ulp_type;
+
+		if (CHIP_IS_E3(bp)) {
+			int idx = BP_FW_MB_IDX(bp);
+			u32 cap;
+
+			cap = SHMEM2_RD(bp, drv_capabilities_flag[idx]);
+			if (ulp_type == CNIC_ULP_ISCSI)
+				cap &= ~DRV_FLAGS_CAPABILITIES_LOADED_ISCSI;
+			else if (ulp_type == CNIC_ULP_FCOE)
+				cap &= ~DRV_FLAGS_CAPABILITIES_LOADED_FCOE;
+			SHMEM2_WR(bp, drv_capabilities_flag[idx], cap);
+		}
+		break;
+	}
 
 	default:
 		BNX2X_ERR("unknown command %x\n", ctl->cmd);
@@ -11553,7 +11883,7 @@ static int bnx2x_unregister_cnic(struct net_device *dev)
 
 	mutex_lock(&bp->cnic_mutex);
 	cp->drv_state = 0;
-	rcu_assign_pointer(bp->cnic_ops, NULL);
+	RCU_INIT_POINTER(bp->cnic_ops, NULL);
 	mutex_unlock(&bp->cnic_mutex);
 	synchronize_rcu();
 	kfree(bp->cnic_kwq);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
index fc7bd0f..44609de 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
@@ -160,8 +160,11 @@
 #define BRB1_REG_PAUSE_HIGH_THRESHOLD_1 			 0x6007c
 /* [RW 10] Write client 0: Assert pause threshold. */
 #define BRB1_REG_PAUSE_LOW_THRESHOLD_0				 0x60068
-#define BRB1_REG_PAUSE_LOW_THRESHOLD_1				 0x6006c
-/* [R 24] The number of full blocks occupied by port. */
+/* [RW 1] Indicates if to use per-class guaranty mode (new mode) or per-MAC
+ * guaranty mode (backwards-compatible mode). 0=per-MAC guaranty mode (BC
+ * mode). 1=per-class guaranty mode (new mode). */
+#define BRB1_REG_PER_CLASS_GUARANTY_MODE			 0x60268
+/* [R 24] The number of full blocks occpied by port. */
 #define BRB1_REG_PORT_NUM_OCC_BLOCKS_0				 0x60094
 /* [RW 1] Reset the design by software. */
 #define BRB1_REG_SOFT_RESET					 0x600dc
@@ -1619,6 +1622,14 @@
    register bits. */
 #define MISC_REG_LCPLL_CTRL_1					 0xa2a4
 #define MISC_REG_LCPLL_CTRL_REG_2				 0xa2a8
+/* [RW 1] LCPLL power down. Global register. Active High. Reset on POR
+ * reset. */
+#define MISC_REG_LCPLL_E40_PWRDWN				 0xaa74
+/* [RW 1] LCPLL VCO reset. Global register. Active Low Reset on POR reset. */
+#define MISC_REG_LCPLL_E40_RESETB_ANA				 0xaa78
+/* [RW 1] LCPLL post-divider reset. Global register. Active Low Reset on POR
+ * reset. */
+#define MISC_REG_LCPLL_E40_RESETB_DIG				 0xaa7c
 /* [RW 4] Interrupt mask register #0 read/write */
 #define MISC_REG_MISC_INT_MASK					 0xa388
 /* [RW 1] Parity mask register #0 read/write */
@@ -1754,6 +1765,7 @@
  * is compared to the value on ctrl_md_devad. Drives output
  * misc_xgxs0_phy_addr. Global register. */
 #define MISC_REG_WC0_CTRL_PHY_ADDR				 0xa9cc
+#define MISC_REG_WC0_RESET					 0xac30
 /* [RW 2] XMAC Core port mode. Indicates the number of ports on the system
    side. This should be less than or equal to phy_port_mode; if some of the
    ports are not used. This enables reduction of frequency on the core side.
@@ -6823,11 +6835,13 @@ Theotherbitsarereservedandshouldbezero*/
 #define MDIO_CTL_REG_84823_MEDIA_PRIORITY_COPPER	0x0000
 #define MDIO_CTL_REG_84823_MEDIA_PRIORITY_FIBER		0x0100
 #define MDIO_CTL_REG_84823_MEDIA_FIBER_1G			0x1000
-#define MDIO_CTL_REG_84823_USER_CTRL_REG		0x4005
-#define MDIO_CTL_REG_84823_USER_CTRL_CMS		0x0080
-
-#define MDIO_PMA_REG_84823_CTL_LED_CTL_1		0xa8e3
-#define MDIO_PMA_REG_84823_LED3_STRETCH_EN		0x0080
+#define MDIO_CTL_REG_84823_USER_CTRL_REG			0x4005
+#define MDIO_CTL_REG_84823_USER_CTRL_CMS			0x0080
+#define MDIO_PMA_REG_84823_CTL_SLOW_CLK_CNT_HIGH		0xa82b
+#define MDIO_PMA_REG_84823_BLINK_RATE_VAL_15P9HZ	0x2f
+#define MDIO_PMA_REG_84823_CTL_LED_CTL_1			0xa8e3
+#define MDIO_PMA_REG_84833_CTL_LED_CTL_1			0xa8ec
+#define MDIO_PMA_REG_84823_LED3_STRETCH_EN			0x0080
 
 /* BCM84833 only */
 #define MDIO_84833_TOP_CFG_XGPHY_STRAP1			0x401a
@@ -6838,26 +6852,35 @@ Theotherbitsarereservedandshouldbezero*/
 #define MDIO_84833_TOP_CFG_SCRATCH_REG2			0x4007
 #define MDIO_84833_TOP_CFG_SCRATCH_REG3			0x4008
 #define MDIO_84833_TOP_CFG_SCRATCH_REG4			0x4009
-#define MDIO_84833_TOP_CFG_DATA3_REG			0x4011
-#define MDIO_84833_TOP_CFG_DATA4_REG			0x4012
+#define MDIO_84833_TOP_CFG_SCRATCH_REG26		0x4037
+#define MDIO_84833_TOP_CFG_SCRATCH_REG27		0x4038
+#define MDIO_84833_TOP_CFG_SCRATCH_REG28		0x4039
+#define MDIO_84833_TOP_CFG_SCRATCH_REG29		0x403a
+#define MDIO_84833_TOP_CFG_SCRATCH_REG30		0x403b
+#define MDIO_84833_TOP_CFG_SCRATCH_REG31		0x403c
+#define MDIO_84833_CMD_HDLR_COMMAND	MDIO_84833_TOP_CFG_SCRATCH_REG0
+#define MDIO_84833_CMD_HDLR_STATUS	MDIO_84833_TOP_CFG_SCRATCH_REG26
+#define MDIO_84833_CMD_HDLR_DATA1	MDIO_84833_TOP_CFG_SCRATCH_REG27
+#define MDIO_84833_CMD_HDLR_DATA2	MDIO_84833_TOP_CFG_SCRATCH_REG28
+#define MDIO_84833_CMD_HDLR_DATA3	MDIO_84833_TOP_CFG_SCRATCH_REG29
+#define MDIO_84833_CMD_HDLR_DATA4	MDIO_84833_TOP_CFG_SCRATCH_REG30
+#define MDIO_84833_CMD_HDLR_DATA5	MDIO_84833_TOP_CFG_SCRATCH_REG31
 
 /* Mailbox command set used by 84833. */
-#define PHY84833_DIAG_CMD_PAIR_SWAP_CHANGE		0x2
+#define PHY84833_CMD_SET_PAIR_SWAP			0x8001
+#define PHY84833_CMD_GET_EEE_MODE			0x8008
+#define PHY84833_CMD_SET_EEE_MODE			0x8009
 /* Mailbox status set used by 84833. */
-#define PHY84833_CMD_RECEIVED				0x0001
-#define PHY84833_CMD_IN_PROGRESS			0x0002
-#define PHY84833_CMD_COMPLETE_PASS			0x0004
-#define PHY84833_CMD_COMPLETE_ERROR			0x0008
-#define PHY84833_CMD_OPEN_FOR_CMDS			0x0010
-#define PHY84833_CMD_SYSTEM_BOOT			0x0020
-#define PHY84833_CMD_NOT_OPEN_FOR_CMDS			0x0040
-#define PHY84833_CMD_CLEAR_COMPLETE			0x0080
-#define PHY84833_CMD_OPEN_OVERRIDE			0xa5a5
-
+#define PHY84833_STATUS_CMD_RECEIVED			0x0001
+#define PHY84833_STATUS_CMD_IN_PROGRESS			0x0002
+#define PHY84833_STATUS_CMD_COMPLETE_PASS		0x0004
+#define PHY84833_STATUS_CMD_COMPLETE_ERROR		0x0008
+#define PHY84833_STATUS_CMD_OPEN_FOR_CMDS		0x0010
+#define PHY84833_STATUS_CMD_SYSTEM_BOOT			0x0020
+#define PHY84833_STATUS_CMD_NOT_OPEN_FOR_CMDS		0x0040
+#define PHY84833_STATUS_CMD_CLEAR_COMPLETE		0x0080
+#define PHY84833_STATUS_CMD_OPEN_OVERRIDE		0xa5a5
 
-/* 84833 F/W Feature Commands */
-#define PHY84833_DIAG_CMD_GET_EEE_MODE			0x27
-#define PHY84833_DIAG_CMD_SET_EEE_MODE			0x28
 
 /* Warpcore clause 45 addressing */
 #define MDIO_WC_DEVAD					0x3
@@ -6990,6 +7013,7 @@ Theotherbitsarereservedandshouldbezero*/
 #define MDIO_REG_INTR_MASK				0x1b
 #define MDIO_REG_INTR_MASK_LINK_STATUS			(0x1 << 1)
 #define MDIO_REG_GPHY_SHADOW				0x1c
+#define MDIO_REG_GPHY_SHADOW_LED_SEL1			(0x0d << 10)
 #define MDIO_REG_GPHY_SHADOW_LED_SEL2			(0x0e << 10)
 #define MDIO_REG_GPHY_SHADOW_WR_ENA			(0x1 << 15)
 #define MDIO_REG_GPHY_SHADOW_AUTO_DET_MED		(0x1e << 10)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 0440425..5ac6160 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -30,6 +30,8 @@
 
 #define BNX2X_MAX_EMUL_MULTI		16
 
+#define MAC_LEADING_ZERO_CNT (ALIGN(ETH_ALEN, sizeof(u32)) - ETH_ALEN)
+
 /**** Exe Queue interfaces ****/
 
 /**
@@ -441,6 +443,36 @@ static bool bnx2x_put_credit_vlan_mac(struct bnx2x_vlan_mac_obj *o)
 	return true;
 }
 
+static int bnx2x_get_n_elements(struct bnx2x *bp, struct bnx2x_vlan_mac_obj *o,
+				int n, u8 *buf)
+{
+	struct bnx2x_vlan_mac_registry_elem *pos;
+	u8 *next = buf;
+	int counter = 0;
+
+	/* traverse list */
+	list_for_each_entry(pos, &o->head, link) {
+		if (counter < n) {
+			/* place leading zeroes in buffer */
+			memset(next, 0, MAC_LEADING_ZERO_CNT);
+
+			/* place mac after leading zeroes*/
+			memcpy(next + MAC_LEADING_ZERO_CNT, pos->u.mac.mac,
+			       ETH_ALEN);
+
+			/* calculate address of next element and
+			 * advance counter
+			 */
+			counter++;
+			next = buf + counter * ALIGN(ETH_ALEN, sizeof(u32));
+
+			DP(BNX2X_MSG_SP, "copied element number %d to address %p element was %pM\n",
+			   counter, next, pos->u.mac.mac);
+		}
+	}
+	return counter * ETH_ALEN;
+}
+
 /* check_add() callbacks */
 static int bnx2x_check_mac_add(struct bnx2x_vlan_mac_obj *o,
 			       union bnx2x_classification_ramrod_data *data)
@@ -1886,6 +1918,7 @@ void bnx2x_init_mac_obj(struct bnx2x *bp,
 		mac_obj->check_move        = bnx2x_check_move;
 		mac_obj->ramrod_cmd        =
 			RAMROD_CMD_ID_ETH_CLASSIFICATION_RULES;
+		mac_obj->get_n_elements    = bnx2x_get_n_elements;
 
 		/* Exe Queue */
 		bnx2x_exe_queue_init(bp,
@@ -3342,7 +3375,7 @@ static inline int bnx2x_mcast_refresh_registry_e1(struct bnx2x *bp,
 		if (!list_empty(&o->registry.exact_match.macs))
 			return 0;
 
-		elem = kzalloc(sizeof(*elem)*len, GFP_ATOMIC);
+		elem = kcalloc(len, sizeof(*elem), GFP_ATOMIC);
 		if (!elem) {
 			BNX2X_ERR("Failed to allocate registry memory\n");
 			return -ENOMEM;
@@ -5380,7 +5413,7 @@ static int bnx2x_func_hw_init(struct bnx2x *bp,
 	rc = drv->init_fw(bp);
 	if (rc) {
 		BNX2X_ERR("Error loading firmware\n");
-		goto fw_init_err;
+		goto init_err;
 	}
 
 	/* Handle the beginning of COMMON_XXX pases separatelly... */
@@ -5388,25 +5421,25 @@ static int bnx2x_func_hw_init(struct bnx2x *bp,
 	case FW_MSG_CODE_DRV_LOAD_COMMON_CHIP:
 		rc = bnx2x_func_init_cmn_chip(bp, drv);
 		if (rc)
-			goto init_hw_err;
+			goto init_err;
 
 		break;
 	case FW_MSG_CODE_DRV_LOAD_COMMON:
 		rc = bnx2x_func_init_cmn(bp, drv);
 		if (rc)
-			goto init_hw_err;
+			goto init_err;
 
 		break;
 	case FW_MSG_CODE_DRV_LOAD_PORT:
 		rc = bnx2x_func_init_port(bp, drv);
 		if (rc)
-			goto init_hw_err;
+			goto init_err;
 
 		break;
 	case FW_MSG_CODE_DRV_LOAD_FUNCTION:
 		rc = bnx2x_func_init_func(bp, drv);
 		if (rc)
-			goto init_hw_err;
+			goto init_err;
 
 		break;
 	default:
@@ -5414,10 +5447,7 @@ static int bnx2x_func_hw_init(struct bnx2x *bp,
 		rc = -EINVAL;
 	}
 
-init_hw_err:
-	drv->release_fw(bp);
-
-fw_init_err:
+init_err:
 	drv->gunzip_end(bp);
 
 	/* In case of success, complete the comand immediatelly: no ramrods
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
index 9a517c2..992308f 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h
@@ -285,6 +285,19 @@ struct bnx2x_vlan_mac_obj {
 	/* RAMROD command to be used */
 	int				ramrod_cmd;
 
+	/* copy first n elements onto preallocated buffer
+	 *
+	 * @param n number of elements to get
+	 * @param buf buffer preallocated by caller into which elements
+	 *            will be copied. Note elements are 4-byte aligned
+	 *            so buffer size must be able to accomodate the
+	 *            aligned elements.
+	 *
+	 * @return number of copied bytes
+	 */
+	int (*get_n_elements)(struct bnx2x *bp, struct bnx2x_vlan_mac_obj *o,
+			      int n, u8 *buf);
+
 	/**
 	 * Checks if ADD-ramrod with the given params may be performed.
 	 *
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
index 02ac6a7..bc0121a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.c
@@ -39,6 +39,17 @@ static inline long bnx2x_hilo(u32 *hiref)
 #endif
 }
 
+static u16 bnx2x_get_port_stats_dma_len(struct bnx2x *bp)
+{
+	u16 res = sizeof(struct host_port_stats) >> 2;
+
+	/* if PFC stats are not supported by the MFW, don't DMA them */
+	if (!(bp->flags &  BC_SUPPORTS_PFC_STATS))
+		res -= (sizeof(u32)*4) >> 2;
+
+	return res;
+}
+
 /*
  * Init service functions
  */
@@ -178,7 +189,8 @@ static void bnx2x_stats_pmf_update(struct bnx2x *bp)
 				   DMAE_LEN32_RD_MAX * 4);
 	dmae->dst_addr_hi = U64_HI(bnx2x_sp_mapping(bp, port_stats) +
 				   DMAE_LEN32_RD_MAX * 4);
-	dmae->len = (sizeof(struct host_port_stats) >> 2) - DMAE_LEN32_RD_MAX;
+	dmae->len = bnx2x_get_port_stats_dma_len(bp) - DMAE_LEN32_RD_MAX;
+
 	dmae->comp_addr_lo = U64_LO(bnx2x_sp_mapping(bp, stats_comp));
 	dmae->comp_addr_hi = U64_HI(bnx2x_sp_mapping(bp, stats_comp));
 	dmae->comp_val = DMAE_COMP_VAL;
@@ -217,7 +229,7 @@ static void bnx2x_port_stats_init(struct bnx2x *bp)
 		dmae->src_addr_hi = U64_HI(bnx2x_sp_mapping(bp, port_stats));
 		dmae->dst_addr_lo = bp->port.port_stx >> 2;
 		dmae->dst_addr_hi = 0;
-		dmae->len = sizeof(struct host_port_stats) >> 2;
+		dmae->len = bnx2x_get_port_stats_dma_len(bp);
 		dmae->comp_addr_lo = dmae_reg_go_c[loader_idx] >> 2;
 		dmae->comp_addr_hi = 0;
 		dmae->comp_val = 1;
@@ -540,6 +552,25 @@ static void bnx2x_bmac_stats_update(struct bnx2x *bp)
 		UPDATE_STAT64(tx_stat_gterr,
 				tx_stat_dot3statsinternalmactransmiterrors);
 		UPDATE_STAT64(tx_stat_gtufl, tx_stat_mac_ufl);
+
+		/* collect PFC stats */
+		DIFF_64(diff.hi, new->tx_stat_gtpp_hi,
+			pstats->pfc_frames_tx_hi,
+			diff.lo, new->tx_stat_gtpp_lo,
+			pstats->pfc_frames_tx_lo);
+		pstats->pfc_frames_tx_hi = new->tx_stat_gtpp_hi;
+		pstats->pfc_frames_tx_lo = new->tx_stat_gtpp_lo;
+		ADD_64(pstats->pfc_frames_tx_hi, diff.hi,
+			pstats->pfc_frames_tx_lo, diff.lo);
+
+		DIFF_64(diff.hi, new->rx_stat_grpp_hi,
+			pstats->pfc_frames_rx_hi,
+			diff.lo, new->rx_stat_grpp_lo,
+			pstats->pfc_frames_rx_lo);
+		pstats->pfc_frames_rx_hi = new->rx_stat_grpp_hi;
+		pstats->pfc_frames_rx_lo = new->rx_stat_grpp_lo;
+		ADD_64(pstats->pfc_frames_rx_hi, diff.hi,
+			pstats->pfc_frames_rx_lo, diff.lo);
 	}
 
 	estats->pause_frames_received_hi =
@@ -551,6 +582,15 @@ static void bnx2x_bmac_stats_update(struct bnx2x *bp)
 				pstats->mac_stx[1].tx_stat_outxoffsent_hi;
 	estats->pause_frames_sent_lo =
 				pstats->mac_stx[1].tx_stat_outxoffsent_lo;
+
+	estats->pfc_frames_received_hi =
+				pstats->pfc_frames_rx_hi;
+	estats->pfc_frames_received_lo =
+				pstats->pfc_frames_rx_lo;
+	estats->pfc_frames_sent_hi =
+				pstats->pfc_frames_tx_hi;
+	estats->pfc_frames_sent_lo =
+				pstats->pfc_frames_tx_lo;
 }
 
 static void bnx2x_mstat_stats_update(struct bnx2x *bp)
@@ -571,6 +611,11 @@ static void bnx2x_mstat_stats_update(struct bnx2x *bp)
 	ADD_STAT64(stats_tx.tx_gtxpf, tx_stat_outxoffsent);
 	ADD_STAT64(stats_tx.tx_gtxpf, tx_stat_flowcontroldone);
 
+	/* collect pfc stats */
+	ADD_64(pstats->pfc_frames_tx_hi, new->stats_tx.tx_gtxpp_hi,
+		pstats->pfc_frames_tx_lo, new->stats_tx.tx_gtxpp_lo);
+	ADD_64(pstats->pfc_frames_rx_hi, new->stats_rx.rx_grxpp_hi,
+		pstats->pfc_frames_rx_lo, new->stats_rx.rx_grxpp_lo);
 
 	ADD_STAT64(stats_tx.tx_gt64, tx_stat_etherstatspkts64octets);
 	ADD_STAT64(stats_tx.tx_gt127,
@@ -628,6 +673,15 @@ static void bnx2x_mstat_stats_update(struct bnx2x *bp)
 				pstats->mac_stx[1].tx_stat_outxoffsent_hi;
 	estats->pause_frames_sent_lo =
 				pstats->mac_stx[1].tx_stat_outxoffsent_lo;
+
+	estats->pfc_frames_received_hi =
+				pstats->pfc_frames_rx_hi;
+	estats->pfc_frames_received_lo =
+				pstats->pfc_frames_rx_lo;
+	estats->pfc_frames_sent_hi =
+				pstats->pfc_frames_tx_hi;
+	estats->pfc_frames_sent_lo =
+				pstats->pfc_frames_tx_lo;
 }
 
 static void bnx2x_emac_stats_update(struct bnx2x *bp)
@@ -740,7 +794,7 @@ static int bnx2x_hw_stats_update(struct bnx2x *bp)
 	estats->brb_drop_hi = pstats->brb_drop_hi;
 	estats->brb_drop_lo = pstats->brb_drop_lo;
 
-	pstats->host_port_stats_start = ++pstats->host_port_stats_end;
+	pstats->host_port_stats_counter++;
 
 	if (!BP_NOMCP(bp)) {
 		u32 nig_timer_max =
@@ -1265,7 +1319,7 @@ static void bnx2x_port_stats_stop(struct bnx2x *bp)
 		dmae->src_addr_hi = U64_HI(bnx2x_sp_mapping(bp, port_stats));
 		dmae->dst_addr_lo = bp->port.port_stx >> 2;
 		dmae->dst_addr_hi = 0;
-		dmae->len = sizeof(struct host_port_stats) >> 2;
+		dmae->len = bnx2x_get_port_stats_dma_len(bp);
 		if (bp->func_stx) {
 			dmae->comp_addr_lo = dmae_reg_go_c[loader_idx] >> 2;
 			dmae->comp_addr_hi = 0;
@@ -1349,12 +1403,14 @@ void bnx2x_stats_handle(struct bnx2x *bp, enum bnx2x_stats_event event)
 	enum bnx2x_stats_state state;
 	if (unlikely(bp->panic))
 		return;
-	bnx2x_stats_stm[bp->stats_state][event].action(bp);
+
 	spin_lock_bh(&bp->stats_lock);
 	state = bp->stats_state;
 	bp->stats_state = bnx2x_stats_stm[state][event].next_state;
 	spin_unlock_bh(&bp->stats_lock);
 
+	bnx2x_stats_stm[state][event].action(bp);
+
 	if ((event != STATS_EVENT_UPDATE) || netif_msg_timer(bp))
 		DP(BNX2X_MSG_STATS, "state %d -> event %d -> state %d\n",
 		   state, event, bp->stats_state);
@@ -1380,7 +1436,7 @@ static void bnx2x_port_stats_base_init(struct bnx2x *bp)
 	dmae->src_addr_hi = U64_HI(bnx2x_sp_mapping(bp, port_stats));
 	dmae->dst_addr_lo = bp->port.port_stx >> 2;
 	dmae->dst_addr_hi = 0;
-	dmae->len = sizeof(struct host_port_stats) >> 2;
+	dmae->len = bnx2x_get_port_stats_dma_len(bp);
 	dmae->comp_addr_lo = U64_LO(bnx2x_sp_mapping(bp, stats_comp));
 	dmae->comp_addr_hi = U64_HI(bnx2x_sp_mapping(bp, stats_comp));
 	dmae->comp_val = DMAE_COMP_VAL;
@@ -1457,6 +1513,7 @@ static void bnx2x_func_stats_base_update(struct bnx2x *bp)
 static inline void bnx2x_prep_fw_stats_req(struct bnx2x *bp)
 {
 	int i;
+	int first_queue_query_index;
 	struct stats_query_header *stats_hdr = &bp->fw_stats_req->hdr;
 
 	dma_addr_t cur_data_offset;
@@ -1512,14 +1569,40 @@ static inline void bnx2x_prep_fw_stats_req(struct bnx2x *bp)
 	cur_query_entry->address.hi = cpu_to_le32(U64_HI(cur_data_offset));
 	cur_query_entry->address.lo = cpu_to_le32(U64_LO(cur_data_offset));
 
+	/**** FCoE FW statistics data ****/
+	if (!NO_FCOE(bp)) {
+		cur_data_offset = bp->fw_stats_data_mapping +
+			offsetof(struct bnx2x_fw_stats_data, fcoe);
+
+		cur_query_entry =
+			&bp->fw_stats_req->query[BNX2X_FCOE_QUERY_IDX];
+
+		cur_query_entry->kind = STATS_TYPE_FCOE;
+		/* For FCoE query index is a DONT CARE */
+		cur_query_entry->index = BP_PORT(bp);
+		cur_query_entry->funcID = cpu_to_le16(BP_FUNC(bp));
+		cur_query_entry->address.hi =
+			cpu_to_le32(U64_HI(cur_data_offset));
+		cur_query_entry->address.lo =
+			cpu_to_le32(U64_LO(cur_data_offset));
+	}
+
 	/**** Clients' queries ****/
 	cur_data_offset = bp->fw_stats_data_mapping +
 		offsetof(struct bnx2x_fw_stats_data, queue_stats);
 
+	/* first queue query index depends whether FCoE offloaded request will
+	 * be included in the ramrod
+	 */
+	if (!NO_FCOE(bp))
+		first_queue_query_index = BNX2X_FIRST_QUEUE_QUERY_IDX;
+	else
+		first_queue_query_index = BNX2X_FIRST_QUEUE_QUERY_IDX - 1;
+
 	for_each_eth_queue(bp, i) {
 		cur_query_entry =
 			&bp->fw_stats_req->
-					query[BNX2X_FIRST_QUEUE_QUERY_IDX + i];
+					query[first_queue_query_index + i];
 
 		cur_query_entry->kind = STATS_TYPE_QUEUE;
 		cur_query_entry->index = bnx2x_stats_id(&bp->fp[i]);
@@ -1531,6 +1614,21 @@ static inline void bnx2x_prep_fw_stats_req(struct bnx2x *bp)
 
 		cur_data_offset += sizeof(struct per_queue_stats);
 	}
+
+	/* add FCoE queue query if needed */
+	if (!NO_FCOE(bp)) {
+		cur_query_entry =
+			&bp->fw_stats_req->
+					query[first_queue_query_index + i];
+
+		cur_query_entry->kind = STATS_TYPE_QUEUE;
+		cur_query_entry->index = bnx2x_stats_id(&bp->fp[FCOE_IDX]);
+		cur_query_entry->funcID = cpu_to_le16(BP_FUNC(bp));
+		cur_query_entry->address.hi =
+			cpu_to_le32(U64_HI(cur_data_offset));
+		cur_query_entry->address.lo =
+			cpu_to_le32(U64_LO(cur_data_offset));
+	}
 }
 
 void bnx2x_stats_init(struct bnx2x *bp)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
index 5d8ce2f..683deb0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
@@ -193,6 +193,12 @@ struct bnx2x_eth_stats {
 	u32 total_tpa_aggregated_frames_lo;
 	u32 total_tpa_bytes_hi;
 	u32 total_tpa_bytes_lo;
+
+	/* PFC */
+	u32 pfc_frames_received_hi;
+	u32 pfc_frames_received_lo;
+	u32 pfc_frames_sent_hi;
+	u32 pfc_frames_sent_lo;
 };
 
 
diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index 6f10c69..4bcb67e 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -250,6 +250,21 @@ static u32 cnic_reg_rd_ind(struct cnic_dev *dev, u32 off)
 	return io->data;
 }
 
+static void cnic_ulp_ctl(struct cnic_dev *dev, int ulp_type, bool reg)
+{
+	struct cnic_local *cp = dev->cnic_priv;
+	struct cnic_eth_dev *ethdev = cp->ethdev;
+	struct drv_ctl_info info;
+
+	if (reg)
+		info.cmd = DRV_CTL_ULP_REGISTER_CMD;
+	else
+		info.cmd = DRV_CTL_ULP_UNREGISTER_CMD;
+
+	info.data.ulp_type = ulp_type;
+	ethdev->drv_ctl(dev->netdev, &info);
+}
+
 static int cnic_in_use(struct cnic_sock *csk)
 {
 	return test_bit(SK_F_INUSE, &csk->flags);
@@ -506,7 +521,7 @@ int cnic_unregister_driver(int ulp_type)
 	}
 	read_unlock(&cnic_dev_lock);
 
-	rcu_assign_pointer(cnic_ulp_tbl[ulp_type], NULL);
+	RCU_INIT_POINTER(cnic_ulp_tbl[ulp_type], NULL);
 
 	mutex_unlock(&cnic_lock);
 	synchronize_rcu();
@@ -563,6 +578,8 @@ static int cnic_register_device(struct cnic_dev *dev, int ulp_type,
 
 	mutex_unlock(&cnic_lock);
 
+	cnic_ulp_ctl(dev, ulp_type, true);
+
 	return 0;
 
 }
@@ -579,7 +596,7 @@ static int cnic_unregister_device(struct cnic_dev *dev, int ulp_type)
 	}
 	mutex_lock(&cnic_lock);
 	if (rcu_dereference(cp->ulp_ops[ulp_type])) {
-		rcu_assign_pointer(cp->ulp_ops[ulp_type], NULL);
+		RCU_INIT_POINTER(cp->ulp_ops[ulp_type], NULL);
 		cnic_put(dev);
 	} else {
 		pr_err("%s: device not registered to this ulp type %d\n",
@@ -602,6 +619,8 @@ static int cnic_unregister_device(struct cnic_dev *dev, int ulp_type)
 	if (test_bit(ULP_F_CALL_PENDING, &cp->ulp_flags[ulp_type]))
 		netdev_warn(dev->netdev, "Failed waiting for ULP up call to complete\n");
 
+	cnic_ulp_ctl(dev, ulp_type, false);
+
 	return 0;
 }
 EXPORT_SYMBOL(cnic_unregister_driver);
@@ -3052,9 +3071,26 @@ static void cnic_ulp_start(struct cnic_dev *dev)
 	}
 }
 
+static int cnic_copy_ulp_stats(struct cnic_dev *dev, int ulp_type)
+{
+	struct cnic_local *cp = dev->cnic_priv;
+	struct cnic_ulp_ops *ulp_ops;
+	int rc;
+
+	mutex_lock(&cnic_lock);
+	ulp_ops = cnic_ulp_tbl_prot(ulp_type);
+	if (ulp_ops && ulp_ops->cnic_get_stats)
+		rc = ulp_ops->cnic_get_stats(cp->ulp_handle[ulp_type]);
+	else
+		rc = -ENODEV;
+	mutex_unlock(&cnic_lock);
+	return rc;
+}
+
 static int cnic_ctl(void *data, struct cnic_ctl_info *info)
 {
 	struct cnic_dev *dev = data;
+	int ulp_type = CNIC_ULP_ISCSI;
 
 	switch (info->cmd) {
 	case CNIC_CTL_STOP_CMD:
@@ -3100,6 +3136,15 @@ static int cnic_ctl(void *data, struct cnic_ctl_info *info)
 		}
 		break;
 	}
+	case CNIC_CTL_FCOE_STATS_GET_CMD:
+		ulp_type = CNIC_ULP_FCOE;
+		/* fall through */
+	case CNIC_CTL_ISCSI_STATS_GET_CMD:
+		cnic_hold(dev);
+		cnic_copy_ulp_stats(dev, ulp_type);
+		cnic_put(dev);
+		break;
+
 	default:
 		return -EINVAL;
 	}
@@ -3475,7 +3520,7 @@ static int cnic_get_v6_route(struct sockaddr_in6 *dst_addr,
 	struct flowi6 fl6;
 
 	memset(&fl6, 0, sizeof(fl6));
-	ipv6_addr_copy(&fl6.daddr, &dst_addr->sin6_addr);
+	fl6.daddr = dst_addr->sin6_addr;
 	if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL)
 		fl6.flowi6_oif = dst_addr->sin6_scope_id;
 
@@ -5134,7 +5179,7 @@ static void cnic_stop_hw(struct cnic_dev *dev)
 		}
 		cnic_shutdown_rings(dev);
 		clear_bit(CNIC_F_CNIC_UP, &dev->flags);
-		rcu_assign_pointer(cp->ulp_ops[CNIC_ULP_L4], NULL);
+		RCU_INIT_POINTER(cp->ulp_ops[CNIC_ULP_L4], NULL);
 		synchronize_rcu();
 		cnic_cm_shutdown(dev);
 		cp->stop_hw(dev);
@@ -5288,6 +5333,8 @@ static struct cnic_dev *init_bnx2x_cnic(struct net_device *dev)
 	cdev->pcidev = pdev;
 	cp->chip_id = ethdev->chip_id;
 
+	cdev->stats_addr = ethdev->addr_drv_info_to_mcp;
+
 	if (!(ethdev->drv_state & CNIC_DRV_STATE_NO_ISCSI))
 		cdev->max_iscsi_conn = ethdev->max_iscsi_conn;
 	if (BNX2X_CHIP_IS_E2_PLUS(cp->chip_id) &&
diff --git a/drivers/net/ethernet/broadcom/cnic_if.h b/drivers/net/ethernet/broadcom/cnic_if.h
index 79443e0..d1f6456 100644
--- a/drivers/net/ethernet/broadcom/cnic_if.h
+++ b/drivers/net/ethernet/broadcom/cnic_if.h
@@ -86,6 +86,8 @@ struct kcqe {
 #define CNIC_CTL_START_CMD		2
 #define CNIC_CTL_COMPLETION_CMD		3
 #define CNIC_CTL_STOP_ISCSI_CMD		4
+#define CNIC_CTL_FCOE_STATS_GET_CMD	5
+#define CNIC_CTL_ISCSI_STATS_GET_CMD	6
 
 #define DRV_CTL_IO_WR_CMD		0x101
 #define DRV_CTL_IO_RD_CMD		0x102
@@ -96,6 +98,8 @@ struct kcqe {
 #define DRV_CTL_STOP_L2_CMD		0x107
 #define DRV_CTL_RET_L2_SPQ_CREDIT_CMD	0x10c
 #define DRV_CTL_ISCSI_STOPPED_CMD	0x10d
+#define DRV_CTL_ULP_REGISTER_CMD	0x10e
+#define DRV_CTL_ULP_UNREGISTER_CMD	0x10f
 
 struct cnic_ctl_completion {
 	u32	cid;
@@ -133,6 +137,7 @@ struct drv_ctl_info {
 		struct drv_ctl_spq_credit credit;
 		struct drv_ctl_io io;
 		struct drv_ctl_l2_ring ring;
+		int ulp_type;
 		char bytes[MAX_DRV_CTL_DATA];
 	} data;
 };
@@ -201,6 +206,7 @@ struct cnic_eth_dev {
 					       struct kwqe_16 *[], u32);
 	int		(*drv_ctl)(struct net_device *, struct drv_ctl_info *);
 	unsigned long	reserved1[2];
+	union drv_info_to_mcp	*addr_drv_info_to_mcp;
 };
 
 struct cnic_sockaddr {
@@ -297,6 +303,8 @@ struct cnic_dev {
 	int		max_fcoe_conn;
 	int		max_rdma_conn;
 
+	union drv_info_to_mcp	*stats_addr;
+
 	void		*cnic_priv;
 };
 
@@ -326,6 +334,7 @@ struct cnic_ulp_ops {
 	void (*cm_remote_abort)(struct cnic_sock *);
 	int (*iscsi_nl_send_msg)(void *ulp_ctx, u32 msg_type,
 				  char *data, u16 data_size);
+	int (*cnic_get_stats)(void *ulp_ctx);
 	struct module *owner;
 	atomic_t ref_count;
 };
diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c
index 0a1d7f2..8fa7abc 100644
--- a/drivers/net/ethernet/broadcom/sb1250-mac.c
+++ b/drivers/net/ethernet/broadcom/sb1250-mac.c
@@ -163,7 +163,6 @@ enum sbmac_state {
 #define SBMAC_MAX_TXDESCR	256
 #define SBMAC_MAX_RXDESCR	256
 
-#define ETHER_ADDR_LEN		6
 #define ENET_PACKET_SIZE	1518
 /*#define ENET_PACKET_SIZE	9216 */
 
@@ -266,7 +265,7 @@ struct sbmac_softc {
 	int			sbm_pause;	/* current pause setting */
 	int			sbm_link;	/* current link state */
 
-	unsigned char		sbm_hwaddr[ETHER_ADDR_LEN];
+	unsigned char		sbm_hwaddr[ETH_ALEN];
 
 	struct sbmacdma		sbm_txdma;	/* only channel 0 for now */
 	struct sbmacdma		sbm_rxdma;
@@ -2676,15 +2675,4 @@ static struct platform_driver sbmac_driver = {
 	},
 };
 
-static int __init sbmac_init_module(void)
-{
-	return platform_driver_register(&sbmac_driver);
-}
-
-static void __exit sbmac_cleanup_module(void)
-{
-	platform_driver_unregister(&sbmac_driver);
-}
-
-module_init(sbmac_init_module);
-module_exit(sbmac_cleanup_module);
+module_platform_driver(sbmac_driver);
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index bf40741..8bf11ca 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -89,10 +89,10 @@ static inline void _tg3_flag_clear(enum TG3_FLAGS flag, unsigned long *bits)
 
 #define DRV_MODULE_NAME		"tg3"
 #define TG3_MAJ_NUM			3
-#define TG3_MIN_NUM			121
+#define TG3_MIN_NUM			122
 #define DRV_MODULE_VERSION	\
 	__stringify(TG3_MAJ_NUM) "." __stringify(TG3_MIN_NUM)
-#define DRV_MODULE_RELDATE	"November 2, 2011"
+#define DRV_MODULE_RELDATE	"December 7, 2011"
 
 #define RESET_KIND_SHUTDOWN	0
 #define RESET_KIND_INIT		1
@@ -135,7 +135,6 @@ static inline void _tg3_flag_clear(enum TG3_FLAGS flag, unsigned long *bits)
 	(tg3_flag(tp, LRG_PROD_RING_CAP) ? \
 	 TG3_RX_JMB_MAX_SIZE_5717 : TG3_RX_JMB_MAX_SIZE_5700)
 #define TG3_DEF_RX_JUMBO_RING_PENDING	100
-#define TG3_RSS_INDIR_TBL_SIZE		128
 
 /* Do not place this n-ring entries value into the tp struct itself,
  * we really want to expose these constants to GCC so that modulo et
@@ -194,12 +193,13 @@ static inline void _tg3_flag_clear(enum TG3_FLAGS flag, unsigned long *bits)
 #if (NET_IP_ALIGN != 0)
 #define TG3_RX_OFFSET(tp)	((tp)->rx_offset)
 #else
-#define TG3_RX_OFFSET(tp)	0
+#define TG3_RX_OFFSET(tp)	(NET_SKB_PAD)
 #endif
 
 /* minimum number of free TX descriptors required to wake up TX process */
 #define TG3_TX_WAKEUP_THRESH(tnapi)		((tnapi)->tx_pending / 4)
-#define TG3_TX_BD_DMA_MAX		4096
+#define TG3_TX_BD_DMA_MAX_2K		2048
+#define TG3_TX_BD_DMA_MAX_4K		4096
 
 #define TG3_RAW_IP_ALIGN 2
 
@@ -1670,22 +1670,6 @@ static void tg3_link_report(struct tg3 *tp)
 	}
 }
 
-static u16 tg3_advert_flowctrl_1000T(u8 flow_ctrl)
-{
-	u16 miireg;
-
-	if ((flow_ctrl & FLOW_CTRL_TX) && (flow_ctrl & FLOW_CTRL_RX))
-		miireg = ADVERTISE_PAUSE_CAP;
-	else if (flow_ctrl & FLOW_CTRL_TX)
-		miireg = ADVERTISE_PAUSE_ASYM;
-	else if (flow_ctrl & FLOW_CTRL_RX)
-		miireg = ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM;
-	else
-		miireg = 0;
-
-	return miireg;
-}
-
 static u16 tg3_advert_flowctrl_1000X(u8 flow_ctrl)
 {
 	u16 miireg;
@@ -1706,18 +1690,12 @@ static u8 tg3_resolve_flowctrl_1000X(u16 lcladv, u16 rmtadv)
 {
 	u8 cap = 0;
 
-	if (lcladv & ADVERTISE_1000XPAUSE) {
-		if (lcladv & ADVERTISE_1000XPSE_ASYM) {
-			if (rmtadv & LPA_1000XPAUSE)
-				cap = FLOW_CTRL_TX | FLOW_CTRL_RX;
-			else if (rmtadv & LPA_1000XPAUSE_ASYM)
-				cap = FLOW_CTRL_RX;
-		} else {
-			if (rmtadv & LPA_1000XPAUSE)
-				cap = FLOW_CTRL_TX | FLOW_CTRL_RX;
-		}
-	} else if (lcladv & ADVERTISE_1000XPSE_ASYM) {
-		if ((rmtadv & LPA_1000XPAUSE) && (rmtadv & LPA_1000XPAUSE_ASYM))
+	if (lcladv & rmtadv & ADVERTISE_1000XPAUSE) {
+		cap = FLOW_CTRL_TX | FLOW_CTRL_RX;
+	} else if (lcladv & rmtadv & ADVERTISE_1000XPSE_ASYM) {
+		if (lcladv & ADVERTISE_1000XPAUSE)
+			cap = FLOW_CTRL_RX;
+		if (rmtadv & ADVERTISE_1000XPAUSE)
 			cap = FLOW_CTRL_TX;
 	}
 
@@ -1792,7 +1770,7 @@ static void tg3_adjust_link(struct net_device *dev)
 		if (phydev->duplex == DUPLEX_HALF)
 			mac_mode |= MAC_MODE_HALF_DUPLEX;
 		else {
-			lcl_adv = tg3_advert_flowctrl_1000T(
+			lcl_adv = mii_advertise_flowctrl(
 				  tp->link_config.flowctrl);
 
 			if (phydev->pause)
@@ -2160,7 +2138,7 @@ static void tg3_phy_eee_enable(struct tg3 *tp)
 	if (tp->link_config.active_speed == SPEED_1000 &&
 	    (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 ||
 	     GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 ||
-	     GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) &&
+	     tg3_flag(tp, 57765_CLASS)) &&
 	    !TG3_PHY_AUXCTL_SMDSP_ENABLE(tp)) {
 		val = MII_TG3_DSP_TAP26_ALNOKO |
 		      MII_TG3_DSP_TAP26_RMRXSTO;
@@ -2679,8 +2657,7 @@ static void tg3_frob_aux_power(struct tg3 *tp, bool include_wol)
 	bool need_vaux = false;
 
 	/* The GPIOs do something completely different on 57765. */
-	if (!tg3_flag(tp, IS_NIC) ||
-	    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+	if (!tg3_flag(tp, IS_NIC) || tg3_flag(tp, 57765_CLASS))
 		return;
 
 	if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 ||
@@ -3594,37 +3571,24 @@ static int tg3_phy_autoneg_cfg(struct tg3 *tp, u32 advertise, u32 flowctrl)
 	u32 val, new_adv;
 
 	new_adv = ADVERTISE_CSMA;
-	if (advertise & ADVERTISED_10baseT_Half)
-		new_adv |= ADVERTISE_10HALF;
-	if (advertise & ADVERTISED_10baseT_Full)
-		new_adv |= ADVERTISE_10FULL;
-	if (advertise & ADVERTISED_100baseT_Half)
-		new_adv |= ADVERTISE_100HALF;
-	if (advertise & ADVERTISED_100baseT_Full)
-		new_adv |= ADVERTISE_100FULL;
-
-	new_adv |= tg3_advert_flowctrl_1000T(flowctrl);
+	new_adv |= ethtool_adv_to_mii_adv_t(advertise) & ADVERTISE_ALL;
+	new_adv |= mii_advertise_flowctrl(flowctrl);
 
 	err = tg3_writephy(tp, MII_ADVERTISE, new_adv);
 	if (err)
 		goto done;
 
-	if (tp->phy_flags & TG3_PHYFLG_10_100_ONLY)
-		goto done;
-
-	new_adv = 0;
-	if (advertise & ADVERTISED_1000baseT_Half)
-		new_adv |= ADVERTISE_1000HALF;
-	if (advertise & ADVERTISED_1000baseT_Full)
-		new_adv |= ADVERTISE_1000FULL;
+	if (!(tp->phy_flags & TG3_PHYFLG_10_100_ONLY)) {
+		new_adv = ethtool_adv_to_mii_ctrl1000_t(advertise);
 
-	if (tp->pci_chip_rev_id == CHIPREV_ID_5701_A0 ||
-	    tp->pci_chip_rev_id == CHIPREV_ID_5701_B0)
-		new_adv |= CTL1000_AS_MASTER | CTL1000_ENABLE_MASTER;
+		if (tp->pci_chip_rev_id == CHIPREV_ID_5701_A0 ||
+		    tp->pci_chip_rev_id == CHIPREV_ID_5701_B0)
+			new_adv |= CTL1000_AS_MASTER | CTL1000_ENABLE_MASTER;
 
-	err = tg3_writephy(tp, MII_CTRL1000, new_adv);
-	if (err)
-		goto done;
+		err = tg3_writephy(tp, MII_CTRL1000, new_adv);
+		if (err)
+			goto done;
+	}
 
 	if (!(tp->phy_flags & TG3_PHYFLG_EEE_CAP))
 		goto done;
@@ -3650,6 +3614,7 @@ static int tg3_phy_autoneg_cfg(struct tg3 *tp, u32 advertise, u32 flowctrl)
 		switch (GET_ASIC_REV(tp->pci_chip_rev_id)) {
 		case ASIC_REV_5717:
 		case ASIC_REV_57765:
+		case ASIC_REV_57766:
 		case ASIC_REV_5719:
 			/* If we advertised any eee advertisements above... */
 			if (val)
@@ -3786,76 +3751,61 @@ static int tg3_init_5401phy_dsp(struct tg3 *tp)
 	return err;
 }
 
-static int tg3_copper_is_advertising_all(struct tg3 *tp, u32 mask)
+static bool tg3_phy_copper_an_config_ok(struct tg3 *tp, u32 *lcladv)
 {
-	u32 adv_reg, all_mask = 0;
+	u32 advmsk, tgtadv, advertising;
 
-	if (mask & ADVERTISED_10baseT_Half)
-		all_mask |= ADVERTISE_10HALF;
-	if (mask & ADVERTISED_10baseT_Full)
-		all_mask |= ADVERTISE_10FULL;
-	if (mask & ADVERTISED_100baseT_Half)
-		all_mask |= ADVERTISE_100HALF;
-	if (mask & ADVERTISED_100baseT_Full)
-		all_mask |= ADVERTISE_100FULL;
+	advertising = tp->link_config.advertising;
+	tgtadv = ethtool_adv_to_mii_adv_t(advertising) & ADVERTISE_ALL;
 
-	if (tg3_readphy(tp, MII_ADVERTISE, &adv_reg))
-		return 0;
+	advmsk = ADVERTISE_ALL;
+	if (tp->link_config.active_duplex == DUPLEX_FULL) {
+		tgtadv |= mii_advertise_flowctrl(tp->link_config.flowctrl);
+		advmsk |= ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM;
+	}
 
-	if ((adv_reg & ADVERTISE_ALL) != all_mask)
-		return 0;
+	if (tg3_readphy(tp, MII_ADVERTISE, lcladv))
+		return false;
+
+	if ((*lcladv & advmsk) != tgtadv)
+		return false;
 
 	if (!(tp->phy_flags & TG3_PHYFLG_10_100_ONLY)) {
 		u32 tg3_ctrl;
 
-		all_mask = 0;
-		if (mask & ADVERTISED_1000baseT_Half)
-			all_mask |= ADVERTISE_1000HALF;
-		if (mask & ADVERTISED_1000baseT_Full)
-			all_mask |= ADVERTISE_1000FULL;
+		tgtadv = ethtool_adv_to_mii_ctrl1000_t(advertising);
 
 		if (tg3_readphy(tp, MII_CTRL1000, &tg3_ctrl))
-			return 0;
+			return false;
 
 		tg3_ctrl &= (ADVERTISE_1000HALF | ADVERTISE_1000FULL);
-		if (tg3_ctrl != all_mask)
-			return 0;
+		if (tg3_ctrl != tgtadv)
+			return false;
 	}
 
-	return 1;
+	return true;
 }
 
-static int tg3_adv_1000T_flowctrl_ok(struct tg3 *tp, u32 *lcladv, u32 *rmtadv)
+static bool tg3_phy_copper_fetch_rmtadv(struct tg3 *tp, u32 *rmtadv)
 {
-	u32 curadv, reqadv;
+	u32 lpeth = 0;
 
-	if (tg3_readphy(tp, MII_ADVERTISE, lcladv))
-		return 1;
-
-	curadv = *lcladv & (ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM);
-	reqadv = tg3_advert_flowctrl_1000T(tp->link_config.flowctrl);
+	if (!(tp->phy_flags & TG3_PHYFLG_10_100_ONLY)) {
+		u32 val;
 
-	if (tp->link_config.active_duplex == DUPLEX_FULL) {
-		if (curadv != reqadv)
-			return 0;
+		if (tg3_readphy(tp, MII_STAT1000, &val))
+			return false;
 
-		if (tg3_flag(tp, PAUSE_AUTONEG))
-			tg3_readphy(tp, MII_LPA, rmtadv);
-	} else {
-		/* Reprogram the advertisement register, even if it
-		 * does not affect the current link.  If the link
-		 * gets renegotiated in the future, we can save an
-		 * additional renegotiation cycle by advertising
-		 * it correctly in the first place.
-		 */
-		if (curadv != reqadv) {
-			*lcladv &= ~(ADVERTISE_PAUSE_CAP |
-				     ADVERTISE_PAUSE_ASYM);
-			tg3_writephy(tp, MII_ADVERTISE, *lcladv | reqadv);
-		}
+		lpeth = mii_stat1000_to_ethtool_lpa_t(val);
 	}
 
-	return 1;
+	if (tg3_readphy(tp, MII_LPA, rmtadv))
+		return false;
+
+	lpeth |= mii_lpa_to_ethtool_lpa_t(*rmtadv);
+	tp->link_config.rmt_adv = lpeth;
+
+	return true;
 }
 
 static int tg3_setup_copper_phy(struct tg3 *tp, int force_reset)
@@ -3961,6 +3911,8 @@ static int tg3_setup_copper_phy(struct tg3 *tp, int force_reset)
 	current_link_up = 0;
 	current_speed = SPEED_INVALID;
 	current_duplex = DUPLEX_INVALID;
+	tp->phy_flags &= ~TG3_PHYFLG_MDIX_STATE;
+	tp->link_config.rmt_adv = 0;
 
 	if (tp->phy_flags & TG3_PHYFLG_CAPACITIVE_COUPLING) {
 		err = tg3_phy_auxctl_read(tp,
@@ -4016,12 +3968,9 @@ static int tg3_setup_copper_phy(struct tg3 *tp, int force_reset)
 
 		if (tp->link_config.autoneg == AUTONEG_ENABLE) {
 			if ((bmcr & BMCR_ANENABLE) &&
-			    tg3_copper_is_advertising_all(tp,
-						tp->link_config.advertising)) {
-				if (tg3_adv_1000T_flowctrl_ok(tp, &lcl_adv,
-								  &rmt_adv))
-					current_link_up = 1;
-			}
+			    tg3_phy_copper_an_config_ok(tp, &lcl_adv) &&
+			    tg3_phy_copper_fetch_rmtadv(tp, &rmt_adv))
+				current_link_up = 1;
 		} else {
 			if (!(bmcr & BMCR_ANENABLE) &&
 			    tp->link_config.speed == current_speed &&
@@ -4033,8 +3982,22 @@ static int tg3_setup_copper_phy(struct tg3 *tp, int force_reset)
 		}
 
 		if (current_link_up == 1 &&
-		    tp->link_config.active_duplex == DUPLEX_FULL)
+		    tp->link_config.active_duplex == DUPLEX_FULL) {
+			u32 reg, bit;
+
+			if (tp->phy_flags & TG3_PHYFLG_IS_FET) {
+				reg = MII_TG3_FET_GEN_STAT;
+				bit = MII_TG3_FET_GEN_STAT_MDIXSTAT;
+			} else {
+				reg = MII_TG3_EXT_STAT;
+				bit = MII_TG3_EXT_STAT_MDIX;
+			}
+
+			if (!tg3_readphy(tp, reg, &val) && (val & bit))
+				tp->phy_flags |= TG3_PHYFLG_MDIX_STATE;
+
 			tg3_setup_flow_control(tp, lcl_adv, rmt_adv);
+		}
 	}
 
 relink:
@@ -4643,6 +4606,9 @@ restart_autoneg:
 			if (sg_dig_status & SG_DIG_PARTNER_ASYM_PAUSE)
 				remote_adv |= LPA_1000XPAUSE_ASYM;
 
+			tp->link_config.rmt_adv =
+					   mii_adv_to_ethtool_adv_x(remote_adv);
+
 			tg3_setup_flow_control(tp, local_adv, remote_adv);
 			current_link_up = 1;
 			tp->serdes_counter = 0;
@@ -4714,6 +4680,9 @@ static int tg3_setup_fiber_by_hand(struct tg3 *tp, u32 mac_status)
 			if (rxflags & MR_LP_ADV_ASYM_PAUSE)
 				remote_adv |= LPA_1000XPAUSE_ASYM;
 
+			tp->link_config.rmt_adv =
+					   mii_adv_to_ethtool_adv_x(remote_adv);
+
 			tg3_setup_flow_control(tp, local_adv, remote_adv);
 
 			current_link_up = 1;
@@ -4796,6 +4765,7 @@ static int tg3_setup_fiber_phy(struct tg3 *tp, int force_reset)
 	udelay(40);
 
 	current_link_up = 0;
+	tp->link_config.rmt_adv = 0;
 	mac_status = tr32(MAC_STATUS);
 
 	if (tg3_flag(tp, HW_AUTONEG))
@@ -4887,6 +4857,7 @@ static int tg3_setup_fiber_mii_phy(struct tg3 *tp, int force_reset)
 	current_link_up = 0;
 	current_speed = SPEED_INVALID;
 	current_duplex = DUPLEX_INVALID;
+	tp->link_config.rmt_adv = 0;
 
 	err |= tg3_readphy(tp, MII_BMSR, &bmsr);
 	err |= tg3_readphy(tp, MII_BMSR, &bmsr);
@@ -4903,23 +4874,19 @@ static int tg3_setup_fiber_mii_phy(struct tg3 *tp, int force_reset)
 	    (tp->phy_flags & TG3_PHYFLG_PARALLEL_DETECT)) {
 		/* do nothing, just check for link up at the end */
 	} else if (tp->link_config.autoneg == AUTONEG_ENABLE) {
-		u32 adv, new_adv;
+		u32 adv, newadv;
 
 		err |= tg3_readphy(tp, MII_ADVERTISE, &adv);
-		new_adv = adv & ~(ADVERTISE_1000XFULL | ADVERTISE_1000XHALF |
-				  ADVERTISE_1000XPAUSE |
-				  ADVERTISE_1000XPSE_ASYM |
-				  ADVERTISE_SLCT);
-
-		new_adv |= tg3_advert_flowctrl_1000X(tp->link_config.flowctrl);
+		newadv = adv & ~(ADVERTISE_1000XFULL | ADVERTISE_1000XHALF |
+				 ADVERTISE_1000XPAUSE |
+				 ADVERTISE_1000XPSE_ASYM |
+				 ADVERTISE_SLCT);
 
-		if (tp->link_config.advertising & ADVERTISED_1000baseT_Half)
-			new_adv |= ADVERTISE_1000XHALF;
-		if (tp->link_config.advertising & ADVERTISED_1000baseT_Full)
-			new_adv |= ADVERTISE_1000XFULL;
+		newadv |= tg3_advert_flowctrl_1000X(tp->link_config.flowctrl);
+		newadv |= ethtool_adv_to_mii_adv_x(tp->link_config.advertising);
 
-		if ((new_adv != adv) || !(bmcr & BMCR_ANENABLE)) {
-			tg3_writephy(tp, MII_ADVERTISE, new_adv);
+		if ((newadv != adv) || !(bmcr & BMCR_ANENABLE)) {
+			tg3_writephy(tp, MII_ADVERTISE, newadv);
 			bmcr |= BMCR_ANENABLE | BMCR_ANRESTART;
 			tg3_writephy(tp, MII_BMCR, bmcr);
 
@@ -4997,6 +4964,9 @@ static int tg3_setup_fiber_mii_phy(struct tg3 *tp, int force_reset)
 					current_duplex = DUPLEX_FULL;
 				else
 					current_duplex = DUPLEX_HALF;
+
+				tp->link_config.rmt_adv =
+					   mii_adv_to_ethtool_adv_x(remote_adv);
 			} else if (!tg3_flag(tp, 5780_CLASS)) {
 				/* Link is up via parallel detect */
 			} else {
@@ -5320,6 +5290,7 @@ static void tg3_tx(struct tg3_napi *tnapi)
 	u32 sw_idx = tnapi->tx_cons;
 	struct netdev_queue *txq;
 	int index = tnapi - tp->napi;
+	unsigned int pkts_compl = 0, bytes_compl = 0;
 
 	if (tg3_flag(tp, ENABLE_TSS))
 		index--;
@@ -5370,6 +5341,9 @@ static void tg3_tx(struct tg3_napi *tnapi)
 			sw_idx = NEXT_TX(sw_idx);
 		}
 
+		pkts_compl++;
+		bytes_compl += skb->len;
+
 		dev_kfree_skb(skb);
 
 		if (unlikely(tx_bug)) {
@@ -5378,6 +5352,8 @@ static void tg3_tx(struct tg3_napi *tnapi)
 		}
 	}
 
+	netdev_completed_queue(tp->dev, pkts_compl, bytes_compl);
+
 	tnapi->tx_cons = sw_idx;
 
 	/* Need to make the tx_cons update visible to tg3_start_xmit()
@@ -5397,15 +5373,15 @@ static void tg3_tx(struct tg3_napi *tnapi)
 	}
 }
 
-static void tg3_rx_skb_free(struct tg3 *tp, struct ring_info *ri, u32 map_sz)
+static void tg3_rx_data_free(struct tg3 *tp, struct ring_info *ri, u32 map_sz)
 {
-	if (!ri->skb)
+	if (!ri->data)
 		return;
 
 	pci_unmap_single(tp->pdev, dma_unmap_addr(ri, mapping),
 			 map_sz, PCI_DMA_FROMDEVICE);
-	dev_kfree_skb_any(ri->skb);
-	ri->skb = NULL;
+	kfree(ri->data);
+	ri->data = NULL;
 }
 
 /* Returns size of skb allocated or < 0 on error.
@@ -5419,28 +5395,28 @@ static void tg3_rx_skb_free(struct tg3 *tp, struct ring_info *ri, u32 map_sz)
  * buffers the cpu only reads the last cacheline of the RX descriptor
  * (to fetch the error flags, vlan tag, checksum, and opaque cookie).
  */
-static int tg3_alloc_rx_skb(struct tg3 *tp, struct tg3_rx_prodring_set *tpr,
+static int tg3_alloc_rx_data(struct tg3 *tp, struct tg3_rx_prodring_set *tpr,
 			    u32 opaque_key, u32 dest_idx_unmasked)
 {
 	struct tg3_rx_buffer_desc *desc;
 	struct ring_info *map;
-	struct sk_buff *skb;
+	u8 *data;
 	dma_addr_t mapping;
-	int skb_size, dest_idx;
+	int skb_size, data_size, dest_idx;
 
 	switch (opaque_key) {
 	case RXD_OPAQUE_RING_STD:
 		dest_idx = dest_idx_unmasked & tp->rx_std_ring_mask;
 		desc = &tpr->rx_std[dest_idx];
 		map = &tpr->rx_std_buffers[dest_idx];
-		skb_size = tp->rx_pkt_map_sz;
+		data_size = tp->rx_pkt_map_sz;
 		break;
 
 	case RXD_OPAQUE_RING_JUMBO:
 		dest_idx = dest_idx_unmasked & tp->rx_jmb_ring_mask;
 		desc = &tpr->rx_jmb[dest_idx].std;
 		map = &tpr->rx_jmb_buffers[dest_idx];
-		skb_size = TG3_RX_JMB_MAP_SZ;
+		data_size = TG3_RX_JMB_MAP_SZ;
 		break;
 
 	default:
@@ -5453,31 +5429,33 @@ static int tg3_alloc_rx_skb(struct tg3 *tp, struct tg3_rx_prodring_set *tpr,
 	 * Callers depend upon this behavior and assume that
 	 * we leave everything unchanged if we fail.
 	 */
-	skb = netdev_alloc_skb(tp->dev, skb_size + TG3_RX_OFFSET(tp));
-	if (skb == NULL)
+	skb_size = SKB_DATA_ALIGN(data_size + TG3_RX_OFFSET(tp)) +
+		   SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	data = kmalloc(skb_size, GFP_ATOMIC);
+	if (!data)
 		return -ENOMEM;
 
-	skb_reserve(skb, TG3_RX_OFFSET(tp));
-
-	mapping = pci_map_single(tp->pdev, skb->data, skb_size,
+	mapping = pci_map_single(tp->pdev,
+				 data + TG3_RX_OFFSET(tp),
+				 data_size,
 				 PCI_DMA_FROMDEVICE);
 	if (pci_dma_mapping_error(tp->pdev, mapping)) {
-		dev_kfree_skb(skb);
+		kfree(data);
 		return -EIO;
 	}
 
-	map->skb = skb;
+	map->data = data;
 	dma_unmap_addr_set(map, mapping, mapping);
 
 	desc->addr_hi = ((u64)mapping >> 32);
 	desc->addr_lo = ((u64)mapping & 0xffffffff);
 
-	return skb_size;
+	return data_size;
 }
 
 /* We only need to move over in the address because the other
  * members of the RX descriptor are invariant.  See notes above
- * tg3_alloc_rx_skb for full details.
+ * tg3_alloc_rx_data for full details.
  */
 static void tg3_recycle_rx(struct tg3_napi *tnapi,
 			   struct tg3_rx_prodring_set *dpr,
@@ -5511,7 +5489,7 @@ static void tg3_recycle_rx(struct tg3_napi *tnapi,
 		return;
 	}
 
-	dest_map->skb = src_map->skb;
+	dest_map->data = src_map->data;
 	dma_unmap_addr_set(dest_map, mapping,
 			   dma_unmap_addr(src_map, mapping));
 	dest_desc->addr_hi = src_desc->addr_hi;
@@ -5522,7 +5500,7 @@ static void tg3_recycle_rx(struct tg3_napi *tnapi,
 	 */
 	smp_wmb();
 
-	src_map->skb = NULL;
+	src_map->data = NULL;
 }
 
 /* The RX ring scheme is composed of multiple rings which post fresh
@@ -5576,19 +5554,20 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 		struct sk_buff *skb;
 		dma_addr_t dma_addr;
 		u32 opaque_key, desc_idx, *post_ptr;
+		u8 *data;
 
 		desc_idx = desc->opaque & RXD_OPAQUE_INDEX_MASK;
 		opaque_key = desc->opaque & RXD_OPAQUE_RING_MASK;
 		if (opaque_key == RXD_OPAQUE_RING_STD) {
 			ri = &tp->napi[0].prodring.rx_std_buffers[desc_idx];
 			dma_addr = dma_unmap_addr(ri, mapping);
-			skb = ri->skb;
+			data = ri->data;
 			post_ptr = &std_prod_idx;
 			rx_std_posted++;
 		} else if (opaque_key == RXD_OPAQUE_RING_JUMBO) {
 			ri = &tp->napi[0].prodring.rx_jmb_buffers[desc_idx];
 			dma_addr = dma_unmap_addr(ri, mapping);
-			skb = ri->skb;
+			data = ri->data;
 			post_ptr = &jmb_prod_idx;
 		} else
 			goto next_pkt_nopost;
@@ -5606,13 +5585,14 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 			goto next_pkt;
 		}
 
+		prefetch(data + TG3_RX_OFFSET(tp));
 		len = ((desc->idx_len & RXD_LEN_MASK) >> RXD_LEN_SHIFT) -
 		      ETH_FCS_LEN;
 
 		if (len > TG3_RX_COPY_THRESH(tp)) {
 			int skb_size;
 
-			skb_size = tg3_alloc_rx_skb(tp, tpr, opaque_key,
+			skb_size = tg3_alloc_rx_data(tp, tpr, opaque_key,
 						    *post_ptr);
 			if (skb_size < 0)
 				goto drop_it;
@@ -5620,35 +5600,37 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 			pci_unmap_single(tp->pdev, dma_addr, skb_size,
 					 PCI_DMA_FROMDEVICE);
 
-			/* Ensure that the update to the skb happens
+			skb = build_skb(data);
+			if (!skb) {
+				kfree(data);
+				goto drop_it_no_recycle;
+			}
+			skb_reserve(skb, TG3_RX_OFFSET(tp));
+			/* Ensure that the update to the data happens
 			 * after the usage of the old DMA mapping.
 			 */
 			smp_wmb();
 
-			ri->skb = NULL;
+			ri->data = NULL;
 
-			skb_put(skb, len);
 		} else {
-			struct sk_buff *copy_skb;
-
 			tg3_recycle_rx(tnapi, tpr, opaque_key,
 				       desc_idx, *post_ptr);
 
-			copy_skb = netdev_alloc_skb(tp->dev, len +
-						    TG3_RAW_IP_ALIGN);
-			if (copy_skb == NULL)
+			skb = netdev_alloc_skb(tp->dev,
+					       len + TG3_RAW_IP_ALIGN);
+			if (skb == NULL)
 				goto drop_it_no_recycle;
 
-			skb_reserve(copy_skb, TG3_RAW_IP_ALIGN);
-			skb_put(copy_skb, len);
+			skb_reserve(skb, TG3_RAW_IP_ALIGN);
 			pci_dma_sync_single_for_cpu(tp->pdev, dma_addr, len, PCI_DMA_FROMDEVICE);
-			skb_copy_from_linear_data(skb, copy_skb->data, len);
+			memcpy(skb->data,
+			       data + TG3_RX_OFFSET(tp),
+			       len);
 			pci_dma_sync_single_for_device(tp->pdev, dma_addr, len, PCI_DMA_FROMDEVICE);
-
-			/* We'll reuse the original ring buffer. */
-			skb = copy_skb;
 		}
 
+		skb_put(skb, len);
 		if ((tp->dev->features & NETIF_F_RXCSUM) &&
 		    (desc->type_flags & RXD_FLAG_TCPUDP_CSUM) &&
 		    (((desc->ip_tcp_csum & RXD_TCPCSUM_MASK)
@@ -5787,7 +5769,7 @@ static int tg3_rx_prodring_xfer(struct tg3 *tp,
 		di = dpr->rx_std_prod_idx;
 
 		for (i = di; i < di + cpycnt; i++) {
-			if (dpr->rx_std_buffers[i].skb) {
+			if (dpr->rx_std_buffers[i].data) {
 				cpycnt = i - di;
 				err = -ENOSPC;
 				break;
@@ -5845,7 +5827,7 @@ static int tg3_rx_prodring_xfer(struct tg3 *tp,
 		di = dpr->rx_jmb_prod_idx;
 
 		for (i = di; i < di + cpycnt; i++) {
-			if (dpr->rx_jmb_buffers[i].skb) {
+			if (dpr->rx_jmb_buffers[i].data) {
 				cpycnt = i - di;
 				err = -ENOSPC;
 				break;
@@ -6451,17 +6433,17 @@ static bool tg3_tx_frag_set(struct tg3_napi *tnapi, u32 *entry, u32 *budget,
 	if (tg3_40bit_overflow_test(tp, map, len))
 		hwbug = 1;
 
-	if (tg3_flag(tp, 4K_FIFO_LIMIT)) {
+	if (tp->dma_limit) {
 		u32 prvidx = *entry;
 		u32 tmp_flag = flags & ~TXD_FLAG_END;
-		while (len > TG3_TX_BD_DMA_MAX && *budget) {
-			u32 frag_len = TG3_TX_BD_DMA_MAX;
-			len -= TG3_TX_BD_DMA_MAX;
+		while (len > tp->dma_limit && *budget) {
+			u32 frag_len = tp->dma_limit;
+			len -= tp->dma_limit;
 
 			/* Avoid the 8byte DMA problem */
 			if (len <= 8) {
-				len += TG3_TX_BD_DMA_MAX / 2;
-				frag_len = TG3_TX_BD_DMA_MAX / 2;
+				len += tp->dma_limit / 2;
+				frag_len = tp->dma_limit / 2;
 			}
 
 			tnapi->tx_buffers[*entry].fragmented = true;
@@ -6816,6 +6798,7 @@ static netdev_tx_t tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	skb_tx_timestamp(skb);
+	netdev_sent_queue(tp->dev, skb->len);
 
 	/* Packets are ready, update Tx producer idx local and on card. */
 	tw32_tx_mbox(tnapi->prodmbox, entry);
@@ -6968,7 +6951,7 @@ static int tg3_phy_lpbk_set(struct tg3 *tp, u32 speed, bool extlpbk)
 	return 0;
 }
 
-static void tg3_set_loopback(struct net_device *dev, u32 features)
+static void tg3_set_loopback(struct net_device *dev, netdev_features_t features)
 {
 	struct tg3 *tp = netdev_priv(dev);
 
@@ -6994,7 +6977,8 @@ static void tg3_set_loopback(struct net_device *dev, u32 features)
 	}
 }
 
-static u32 tg3_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t tg3_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct tg3 *tp = netdev_priv(dev);
 
@@ -7004,9 +6988,9 @@ static u32 tg3_fix_features(struct net_device *dev, u32 features)
 	return features;
 }
 
-static int tg3_set_features(struct net_device *dev, u32 features)
+static int tg3_set_features(struct net_device *dev, netdev_features_t features)
 {
-	u32 changed = dev->features ^ features;
+	netdev_features_t changed = dev->features ^ features;
 
 	if ((changed & NETIF_F_LOOPBACK) && netif_running(dev))
 		tg3_set_loopback(dev, features);
@@ -7082,14 +7066,14 @@ static void tg3_rx_prodring_free(struct tg3 *tp,
 	if (tpr != &tp->napi[0].prodring) {
 		for (i = tpr->rx_std_cons_idx; i != tpr->rx_std_prod_idx;
 		     i = (i + 1) & tp->rx_std_ring_mask)
-			tg3_rx_skb_free(tp, &tpr->rx_std_buffers[i],
+			tg3_rx_data_free(tp, &tpr->rx_std_buffers[i],
 					tp->rx_pkt_map_sz);
 
 		if (tg3_flag(tp, JUMBO_CAPABLE)) {
 			for (i = tpr->rx_jmb_cons_idx;
 			     i != tpr->rx_jmb_prod_idx;
 			     i = (i + 1) & tp->rx_jmb_ring_mask) {
-				tg3_rx_skb_free(tp, &tpr->rx_jmb_buffers[i],
+				tg3_rx_data_free(tp, &tpr->rx_jmb_buffers[i],
 						TG3_RX_JMB_MAP_SZ);
 			}
 		}
@@ -7098,12 +7082,12 @@ static void tg3_rx_prodring_free(struct tg3 *tp,
 	}
 
 	for (i = 0; i <= tp->rx_std_ring_mask; i++)
-		tg3_rx_skb_free(tp, &tpr->rx_std_buffers[i],
+		tg3_rx_data_free(tp, &tpr->rx_std_buffers[i],
 				tp->rx_pkt_map_sz);
 
 	if (tg3_flag(tp, JUMBO_CAPABLE) && !tg3_flag(tp, 5780_CLASS)) {
 		for (i = 0; i <= tp->rx_jmb_ring_mask; i++)
-			tg3_rx_skb_free(tp, &tpr->rx_jmb_buffers[i],
+			tg3_rx_data_free(tp, &tpr->rx_jmb_buffers[i],
 					TG3_RX_JMB_MAP_SZ);
 	}
 }
@@ -7159,7 +7143,7 @@ static int tg3_rx_prodring_alloc(struct tg3 *tp,
 
 	/* Now allocate fresh SKBs for each rx ring. */
 	for (i = 0; i < tp->rx_pending; i++) {
-		if (tg3_alloc_rx_skb(tp, tpr, RXD_OPAQUE_RING_STD, i) < 0) {
+		if (tg3_alloc_rx_data(tp, tpr, RXD_OPAQUE_RING_STD, i) < 0) {
 			netdev_warn(tp->dev,
 				    "Using a smaller RX standard ring. Only "
 				    "%d out of %d buffers were allocated "
@@ -7191,7 +7175,7 @@ static int tg3_rx_prodring_alloc(struct tg3 *tp,
 	}
 
 	for (i = 0; i < tp->rx_jumbo_pending; i++) {
-		if (tg3_alloc_rx_skb(tp, tpr, RXD_OPAQUE_RING_JUMBO, i) < 0) {
+		if (tg3_alloc_rx_data(tp, tpr, RXD_OPAQUE_RING_JUMBO, i) < 0) {
 			netdev_warn(tp->dev,
 				    "Using a smaller RX jumbo ring. Only %d "
 				    "out of %d buffers were allocated "
@@ -7297,6 +7281,7 @@ static void tg3_free_rings(struct tg3 *tp)
 			dev_kfree_skb_any(skb);
 		}
 	}
+	netdev_reset_queue(tp->dev);
 }
 
 /* Initialize tx/rx rings for packet processing.
@@ -7591,8 +7576,6 @@ static int tg3_abort_hw(struct tg3 *tp, int silent)
 		if (tnapi->hw_status)
 			memset(tnapi->hw_status, 0, TG3_HW_STATUS_SIZE);
 	}
-	if (tp->hw_stats)
-		memset(tp->hw_stats, 0, sizeof(struct tg3_hw_stats));
 
 	return err;
 }
@@ -7626,15 +7609,11 @@ static void tg3_restore_pci_state(struct tg3 *tp)
 
 	pci_write_config_word(tp->pdev, PCI_COMMAND, tp->pci_cmd);
 
-	if (GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5785) {
-		if (tg3_flag(tp, PCI_EXPRESS))
-			pcie_set_readrq(tp->pdev, tp->pcie_readrq);
-		else {
-			pci_write_config_byte(tp->pdev, PCI_CACHE_LINE_SIZE,
-					      tp->pci_cacheline_sz);
-			pci_write_config_byte(tp->pdev, PCI_LATENCY_TIMER,
-					      tp->pci_lat_timer);
-		}
+	if (!tg3_flag(tp, PCI_EXPRESS)) {
+		pci_write_config_byte(tp->pdev, PCI_CACHE_LINE_SIZE,
+				      tp->pci_cacheline_sz);
+		pci_write_config_byte(tp->pdev, PCI_LATENCY_TIMER,
+				      tp->pci_lat_timer);
 	}
 
 	/* Make sure PCI-X relaxed ordering bit is clear. */
@@ -7819,8 +7798,6 @@ static int tg3_chip_reset(struct tg3 *tp)
 				      pci_pcie_cap(tp->pdev) + PCI_EXP_DEVCTL,
 				      val16);
 
-		pcie_set_readrq(tp->pdev, tp->pcie_readrq);
-
 		/* Clear error status */
 		pci_write_config_word(tp->pdev,
 				      pci_pcie_cap(tp->pdev) + PCI_EXP_DEVSTA,
@@ -7914,6 +7891,11 @@ static int tg3_chip_reset(struct tg3 *tp)
 	return 0;
 }
 
+static struct rtnl_link_stats64 *tg3_get_stats64(struct net_device *,
+						 struct rtnl_link_stats64 *);
+static struct tg3_ethtool_stats *tg3_get_estats(struct tg3 *,
+						struct tg3_ethtool_stats *);
+
 /* tp->lock is held. */
 static int tg3_halt(struct tg3 *tp, int kind, int silent)
 {
@@ -7931,6 +7913,15 @@ static int tg3_halt(struct tg3 *tp, int kind, int silent)
 	tg3_write_sig_legacy(tp, kind);
 	tg3_write_sig_post_reset(tp, kind);
 
+	if (tp->hw_stats) {
+		/* Save the stats across chip resets... */
+		tg3_get_stats64(tp->dev, &tp->net_stats_prev),
+		tg3_get_estats(tp, &tp->estats_prev);
+
+		/* And make sure the next sample is new data */
+		memset(tp->hw_stats, 0, sizeof(struct tg3_hw_stats));
+	}
+
 	if (err)
 		return err;
 
@@ -8074,7 +8065,7 @@ static void tg3_rings_reset(struct tg3 *tp)
 		limit = NIC_SRAM_SEND_RCB + TG3_BDINFO_SIZE * 16;
 	else if (tg3_flag(tp, 5717_PLUS))
 		limit = NIC_SRAM_SEND_RCB + TG3_BDINFO_SIZE * 4;
-	else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+	else if (tg3_flag(tp, 57765_CLASS))
 		limit = NIC_SRAM_SEND_RCB + TG3_BDINFO_SIZE * 2;
 	else
 		limit = NIC_SRAM_SEND_RCB + TG3_BDINFO_SIZE;
@@ -8091,7 +8082,7 @@ static void tg3_rings_reset(struct tg3 *tp)
 	else if (!tg3_flag(tp, 5705_PLUS))
 		limit = NIC_SRAM_RCV_RET_RCB + TG3_BDINFO_SIZE * 16;
 	else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5755 ||
-		 GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+		 tg3_flag(tp, 57765_CLASS))
 		limit = NIC_SRAM_RCV_RET_RCB + TG3_BDINFO_SIZE * 4;
 	else
 		limit = NIC_SRAM_RCV_RET_RCB + TG3_BDINFO_SIZE;
@@ -8197,7 +8188,8 @@ static void tg3_setup_rxbd_thresholds(struct tg3 *tp)
 	if (!tg3_flag(tp, 5750_PLUS) ||
 	    tg3_flag(tp, 5780_CLASS) ||
 	    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5750 ||
-	    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5752)
+	    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5752 ||
+	    tg3_flag(tp, 57765_PLUS))
 		bdcache_maxcnt = TG3_SRAM_RX_STD_BDCACHE_SIZE_5700;
 	else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5755 ||
 		 GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5787)
@@ -8217,10 +8209,7 @@ static void tg3_setup_rxbd_thresholds(struct tg3 *tp)
 	if (!tg3_flag(tp, JUMBO_CAPABLE) || tg3_flag(tp, 5780_CLASS))
 		return;
 
-	if (!tg3_flag(tp, 5705_PLUS))
-		bdcache_maxcnt = TG3_SRAM_RX_JMB_BDCACHE_SIZE_5700;
-	else
-		bdcache_maxcnt = TG3_SRAM_RX_JMB_BDCACHE_SIZE_5717;
+	bdcache_maxcnt = TG3_SRAM_RX_JMB_BDCACHE_SIZE_5700;
 
 	host_rep_thresh = max_t(u32, tp->rx_jumbo_pending / 8, 1);
 
@@ -8231,6 +8220,37 @@ static void tg3_setup_rxbd_thresholds(struct tg3 *tp)
 		tw32(JMB_REPLENISH_LWM, bdcache_maxcnt);
 }
 
+void tg3_rss_init_indir_tbl(struct tg3 *tp)
+{
+	int i;
+
+	if (!tg3_flag(tp, SUPPORT_MSIX))
+		return;
+
+	if (tp->irq_cnt <= 2)
+		memset(&tp->rss_ind_tbl[0], 0, sizeof(tp->rss_ind_tbl));
+	else
+		for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i++)
+			tp->rss_ind_tbl[i] = i % (tp->irq_cnt - 1);
+}
+
+void tg3_rss_write_indir_tbl(struct tg3 *tp)
+{
+	int i = 0;
+	u32 reg = MAC_RSS_INDIR_TBL_0;
+
+	while (i < TG3_RSS_INDIR_TBL_SIZE) {
+		u32 val = tp->rss_ind_tbl[i];
+		i++;
+		for (; i % 8; i++) {
+			val <<= 4;
+			val |= tp->rss_ind_tbl[i];
+		}
+		tw32(reg, val);
+		reg += 4;
+	}
+}
+
 /* tp->lock is held. */
 static int tg3_reset_hw(struct tg3 *tp, int reset_phy)
 {
@@ -8337,7 +8357,7 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy)
 		tw32(GRC_MODE, grc_mode);
 	}
 
-	if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) {
+	if (tg3_flag(tp, 57765_CLASS)) {
 		if (tp->pci_chip_rev_id == CHIPREV_ID_57765_A0) {
 			u32 grc_mode = tr32(GRC_MODE);
 
@@ -8425,7 +8445,7 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy)
 		      ~DMA_RWCTRL_DIS_CACHE_ALIGNMENT;
 		if (tp->pci_chip_rev_id == CHIPREV_ID_57765_A0)
 			val &= ~DMA_RWCTRL_CRDRDR_RDMA_MRRS_MSK;
-		if (GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_57765 &&
+		if (!tg3_flag(tp, 57765_CLASS) &&
 		    GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5717)
 			val |= DMA_RWCTRL_TAGGED_STAT_WA;
 		tw32(TG3PCI_DMA_RW_CTRL, val | tp->dma_rwctrl);
@@ -8572,7 +8592,7 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy)
 			tw32(RCVDBDI_JUMBO_BD + TG3_BDINFO_MAXLEN_FLAGS,
 			     val | BDINFO_FLAGS_USE_EXT_RECV);
 			if (!tg3_flag(tp, USE_JUMBO_BDFLAG) ||
-			    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+			    tg3_flag(tp, 57765_CLASS))
 				tw32(RCVDBDI_JUMBO_BD + TG3_BDINFO_NIC_ADDR,
 				     NIC_SRAM_RX_JUMBO_BUFFER_DESC);
 		} else {
@@ -8581,10 +8601,7 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy)
 		}
 
 		if (tg3_flag(tp, 57765_PLUS)) {
-			if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
-				val = TG3_RX_STD_MAX_SIZE_5700;
-			else
-				val = TG3_RX_STD_MAX_SIZE_5717;
+			val = TG3_RX_STD_RING_SIZE(tp);
 			val <<= BDINFO_FLAGS_MAXLEN_SHIFT;
 			val |= (TG3_RX_STD_DMA_SZ << 2);
 		} else
@@ -8661,6 +8678,9 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy)
 	if (tg3_flag(tp, PCI_EXPRESS))
 		rdmac_mode |= RDMAC_MODE_FIFO_LONG_BURST;
 
+	if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57766)
+		rdmac_mode |= RDMAC_MODE_JMB_2K_MMRR;
+
 	if (tg3_flag(tp, HW_TSO_1) ||
 	    tg3_flag(tp, HW_TSO_2) ||
 	    tg3_flag(tp, HW_TSO_3))
@@ -8924,28 +8944,7 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy)
 	udelay(100);
 
 	if (tg3_flag(tp, ENABLE_RSS)) {
-		int i = 0;
-		u32 reg = MAC_RSS_INDIR_TBL_0;
-
-		if (tp->irq_cnt == 2) {
-			for (i = 0; i < TG3_RSS_INDIR_TBL_SIZE; i += 8) {
-				tw32(reg, 0x0);
-				reg += 4;
-			}
-		} else {
-			u32 val;
-
-			while (i < TG3_RSS_INDIR_TBL_SIZE) {
-				val = i % (tp->irq_cnt - 1);
-				i++;
-				for (; i % 8; i++) {
-					val <<= 4;
-					val |= (i % (tp->irq_cnt - 1));
-				}
-				tw32(reg, val);
-				reg += 4;
-			}
-		}
+		tg3_rss_write_indir_tbl(tp);
 
 		/* Setup the "secret" hash key. */
 		tw32(MAC_RSS_HASH_KEY_0, 0x5f865437);
@@ -9002,7 +9001,7 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy)
 	/* Prevent chip from dropping frames when flow control
 	 * is enabled.
 	 */
-	if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+	if (tg3_flag(tp, 57765_CLASS))
 		val = 1;
 	else
 		val = 2;
@@ -9217,7 +9216,7 @@ static void tg3_timer(unsigned long __opaque)
 	spin_lock(&tp->lock);
 
 	if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 ||
-	    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+	    tg3_flag(tp, 57765_CLASS))
 		tg3_chk_missed_msi(tp);
 
 	if (!tg3_flag(tp, TAGGED_STATUS)) {
@@ -9669,6 +9668,8 @@ static int tg3_open(struct net_device *dev)
 	 */
 	tg3_ints_init(tp);
 
+	tg3_rss_init_indir_tbl(tp);
+
 	/* The placement of this call is tied
 	 * to the setup and use of Host TX descriptors.
 	 */
@@ -9700,8 +9701,8 @@ static int tg3_open(struct net_device *dev)
 		tg3_free_rings(tp);
 	} else {
 		if (tg3_flag(tp, TAGGED_STATUS) &&
-			GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5717 &&
-			GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_57765)
+		    GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5717 &&
+		    !tg3_flag(tp, 57765_CLASS))
 			tp->timer_offset = HZ;
 		else
 			tp->timer_offset = HZ / 10;
@@ -9782,10 +9783,6 @@ err_out1:
 	return err;
 }
 
-static struct rtnl_link_stats64 *tg3_get_stats64(struct net_device *,
-						 struct rtnl_link_stats64 *);
-static struct tg3_ethtool_stats *tg3_get_estats(struct tg3 *);
-
 static int tg3_close(struct net_device *dev)
 {
 	int i;
@@ -9817,10 +9814,9 @@ static int tg3_close(struct net_device *dev)
 
 	tg3_ints_fini(tp);
 
-	tg3_get_stats64(tp->dev, &tp->net_stats_prev);
-
-	memcpy(&tp->estats_prev, tg3_get_estats(tp),
-	       sizeof(tp->estats_prev));
+	/* Clear stats across close / open calls */
+	memset(&tp->net_stats_prev, 0, sizeof(tp->net_stats_prev));
+	memset(&tp->estats_prev, 0, sizeof(tp->estats_prev));
 
 	tg3_napi_fini(tp);
 
@@ -9868,9 +9864,9 @@ static u64 calc_crc_errors(struct tg3 *tp)
 	estats->member =	old_estats->member + \
 				get_stat64(&hw_stats->member)
 
-static struct tg3_ethtool_stats *tg3_get_estats(struct tg3 *tp)
+static struct tg3_ethtool_stats *tg3_get_estats(struct tg3 *tp,
+					       struct tg3_ethtool_stats *estats)
 {
-	struct tg3_ethtool_stats *estats = &tp->estats;
 	struct tg3_ethtool_stats *old_estats = &tp->estats_prev;
 	struct tg3_hw_stats *hw_stats = tp->hw_stats;
 
@@ -10318,12 +10314,20 @@ static int tg3_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 			cmd->advertising |= ADVERTISED_Asym_Pause;
 		}
 	}
-	if (netif_running(dev)) {
+	if (netif_running(dev) && netif_carrier_ok(dev)) {
 		ethtool_cmd_speed_set(cmd, tp->link_config.active_speed);
 		cmd->duplex = tp->link_config.active_duplex;
+		cmd->lp_advertising = tp->link_config.rmt_adv;
+		if (!(tp->phy_flags & TG3_PHYFLG_ANY_SERDES)) {
+			if (tp->phy_flags & TG3_PHYFLG_MDIX_STATE)
+				cmd->eth_tp_mdix = ETH_TP_MDI_X;
+			else
+				cmd->eth_tp_mdix = ETH_TP_MDI;
+		}
 	} else {
 		ethtool_cmd_speed_set(cmd, SPEED_INVALID);
 		cmd->duplex = DUPLEX_INVALID;
+		cmd->eth_tp_mdix = ETH_TP_MDI_INVALID;
 	}
 	cmd->phy_address = tp->phy_addr;
 	cmd->transceiver = XCVR_INTERNAL;
@@ -10428,10 +10432,10 @@ static void tg3_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info
 {
 	struct tg3 *tp = netdev_priv(dev);
 
-	strcpy(info->driver, DRV_MODULE_NAME);
-	strcpy(info->version, DRV_MODULE_VERSION);
-	strcpy(info->fw_version, tp->fw_ver);
-	strcpy(info->bus_info, pci_name(tp->pdev));
+	strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
+	strlcpy(info->fw_version, tp->fw_ver, sizeof(info->fw_version));
+	strlcpy(info->bus_info, pci_name(tp->pdev), sizeof(info->bus_info));
 }
 
 static void tg3_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
@@ -10590,12 +10594,12 @@ static void tg3_get_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 
 	epause->autoneg = !!tg3_flag(tp, PAUSE_AUTONEG);
 
-	if (tp->link_config.active_flowctrl & FLOW_CTRL_RX)
+	if (tp->link_config.flowctrl & FLOW_CTRL_RX)
 		epause->rx_pause = 1;
 	else
 		epause->rx_pause = 0;
 
-	if (tp->link_config.active_flowctrl & FLOW_CTRL_TX)
+	if (tp->link_config.flowctrl & FLOW_CTRL_TX)
 		epause->tx_pause = 1;
 	else
 		epause->tx_pause = 0;
@@ -10769,7 +10773,8 @@ static void tg3_get_ethtool_stats(struct net_device *dev,
 				   struct ethtool_stats *estats, u64 *tmp_stats)
 {
 	struct tg3 *tp = netdev_priv(dev);
-	memcpy(tmp_stats, tg3_get_estats(tp), sizeof(tp->estats));
+
+	tg3_get_estats(tp, (struct tg3_ethtool_stats *)tmp_stats);
 }
 
 static __be32 *tg3_vpd_readblock(struct tg3 *tp, u32 *vpdlen)
@@ -11352,7 +11357,7 @@ static int tg3_test_memory(struct tg3 *tp)
 
 	if (tg3_flag(tp, 5717_PLUS))
 		mem_tbl = mem_tbl_5717;
-	else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+	else if (tg3_flag(tp, 57765_CLASS))
 		mem_tbl = mem_tbl_57765;
 	else if (tg3_flag(tp, 5755_PLUS))
 		mem_tbl = mem_tbl_5755;
@@ -11400,8 +11405,8 @@ static int tg3_run_loopback(struct tg3 *tp, u32 pktsz, bool tso_loopback)
 	u32 rx_start_idx, rx_idx, tx_idx, opaque_key;
 	u32 base_flags = 0, mss = 0, desc_idx, coal_now, data_off, val;
 	u32 budget;
-	struct sk_buff *skb, *rx_skb;
-	u8 *tx_data;
+	struct sk_buff *skb;
+	u8 *tx_data, *rx_data;
 	dma_addr_t map;
 	int num_pkts, tx_len, rx_len, i, err;
 	struct tg3_rx_buffer_desc *desc;
@@ -11569,11 +11574,11 @@ static int tg3_run_loopback(struct tg3 *tp, u32 pktsz, bool tso_loopback)
 		}
 
 		if (opaque_key == RXD_OPAQUE_RING_STD) {
-			rx_skb = tpr->rx_std_buffers[desc_idx].skb;
+			rx_data = tpr->rx_std_buffers[desc_idx].data;
 			map = dma_unmap_addr(&tpr->rx_std_buffers[desc_idx],
 					     mapping);
 		} else if (opaque_key == RXD_OPAQUE_RING_JUMBO) {
-			rx_skb = tpr->rx_jmb_buffers[desc_idx].skb;
+			rx_data = tpr->rx_jmb_buffers[desc_idx].data;
 			map = dma_unmap_addr(&tpr->rx_jmb_buffers[desc_idx],
 					     mapping);
 		} else
@@ -11582,15 +11587,16 @@ static int tg3_run_loopback(struct tg3 *tp, u32 pktsz, bool tso_loopback)
 		pci_dma_sync_single_for_cpu(tp->pdev, map, rx_len,
 					    PCI_DMA_FROMDEVICE);
 
+		rx_data += TG3_RX_OFFSET(tp);
 		for (i = data_off; i < rx_len; i++, val++) {
-			if (*(rx_skb->data + i) != (u8) (val & 0xff))
+			if (*(rx_data + i) != (u8) (val & 0xff))
 				goto out;
 		}
 	}
 
 	err = 0;
 
-	/* tg3_free_rings will unmap and free the rx_skb */
+	/* tg3_free_rings will unmap and free the rx_data */
 out:
 	return err;
 }
@@ -12612,7 +12618,7 @@ static void __devinit tg3_nvram_init(struct tg3 *tp)
 		else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906)
 			tg3_get_5906_nvram_info(tp);
 		else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57780 ||
-			 GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+			 tg3_flag(tp, 57765_CLASS))
 			tg3_get_57780_nvram_info(tp);
 		else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 ||
 			 GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719)
@@ -13218,8 +13224,7 @@ static u32 __devinit tg3_read_otp_phycfg(struct tg3 *tp)
 
 static void __devinit tg3_phy_init_link_config(struct tg3 *tp)
 {
-	u32 adv = ADVERTISED_Autoneg |
-		  ADVERTISED_Pause;
+	u32 adv = ADVERTISED_Autoneg;
 
 	if (!(tp->phy_flags & TG3_PHYFLG_10_100_ONLY))
 		adv |= ADVERTISED_1000baseT_Half |
@@ -13322,7 +13327,7 @@ static int __devinit tg3_phy_probe(struct tg3 *tp)
 	if (!(tp->phy_flags & TG3_PHYFLG_ANY_SERDES) &&
 	    !tg3_flag(tp, ENABLE_APE) &&
 	    !tg3_flag(tp, ENABLE_ASF)) {
-		u32 bmsr, mask;
+		u32 bmsr, dummy;
 
 		tg3_readphy(tp, MII_BMSR, &bmsr);
 		if (!tg3_readphy(tp, MII_BMSR, &bmsr) &&
@@ -13335,10 +13340,7 @@ static int __devinit tg3_phy_probe(struct tg3 *tp)
 
 		tg3_phy_set_wirespeed(tp);
 
-		mask = (ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full |
-			ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full |
-			ADVERTISED_1000baseT_Half | ADVERTISED_1000baseT_Full);
-		if (!tg3_copper_is_advertising_all(tp, mask)) {
+		if (!tg3_phy_copper_an_config_ok(tp, &dummy)) {
 			tg3_phy_autoneg_cfg(tp, tp->link_config.advertising,
 					    tp->link_config.flowctrl);
 
@@ -13460,6 +13462,17 @@ out_no_vpd:
 			strcpy(tp->board_part_number, "BCM57795");
 		else
 			goto nomatch;
+	} else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57766) {
+		if (tp->pdev->device == TG3PCI_DEVICE_TIGON3_57762)
+			strcpy(tp->board_part_number, "BCM57762");
+		else if (tp->pdev->device == TG3PCI_DEVICE_TIGON3_57766)
+			strcpy(tp->board_part_number, "BCM57766");
+		else if (tp->pdev->device == TG3PCI_DEVICE_TIGON3_57782)
+			strcpy(tp->board_part_number, "BCM57782");
+		else if (tp->pdev->device == TG3PCI_DEVICE_TIGON3_57786)
+			strcpy(tp->board_part_number, "BCM57786");
+		else
+			goto nomatch;
 	} else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906) {
 		strcpy(tp->board_part_number, "BCM95906");
 	} else {
@@ -13798,7 +13811,11 @@ static int __devinit tg3_get_invariants(struct tg3 *tp)
 			 tp->pdev->device == TG3PCI_DEVICE_TIGON3_57761 ||
 			 tp->pdev->device == TG3PCI_DEVICE_TIGON3_57765 ||
 			 tp->pdev->device == TG3PCI_DEVICE_TIGON3_57791 ||
-			 tp->pdev->device == TG3PCI_DEVICE_TIGON3_57795)
+			 tp->pdev->device == TG3PCI_DEVICE_TIGON3_57795 ||
+			 tp->pdev->device == TG3PCI_DEVICE_TIGON3_57762 ||
+			 tp->pdev->device == TG3PCI_DEVICE_TIGON3_57766 ||
+			 tp->pdev->device == TG3PCI_DEVICE_TIGON3_57782 ||
+			 tp->pdev->device == TG3PCI_DEVICE_TIGON3_57786)
 			pci_read_config_dword(tp->pdev,
 					      TG3PCI_GEN15_PRODID_ASICREV,
 					      &prod_id_asic_rev);
@@ -13945,7 +13962,10 @@ static int __devinit tg3_get_invariants(struct tg3 *tp)
 		tg3_flag_set(tp, 5717_PLUS);
 
 	if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765 ||
-	    tg3_flag(tp, 5717_PLUS))
+	    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57766)
+		tg3_flag_set(tp, 57765_CLASS);
+
+	if (tg3_flag(tp, 57765_CLASS) || tg3_flag(tp, 5717_PLUS))
 		tg3_flag_set(tp, 57765_PLUS);
 
 	/* Intentionally exclude ASIC_REV_5906 */
@@ -13997,9 +14017,13 @@ static int __devinit tg3_get_invariants(struct tg3 *tp)
 	if (tg3_flag(tp, HW_TSO_1) ||
 	    tg3_flag(tp, HW_TSO_2) ||
 	    tg3_flag(tp, HW_TSO_3) ||
-	    (tp->fw_needed && !tg3_flag(tp, ENABLE_ASF)))
+	    tp->fw_needed) {
+		/* For firmware TSO, assume ASF is disabled.
+		 * We'll disable TSO later if we discover ASF
+		 * is enabled in tg3_get_eeprom_hw_cfg().
+		 */
 		tg3_flag_set(tp, TSO_CAPABLE);
-	else {
+	} else {
 		tg3_flag_clear(tp, TSO_CAPABLE);
 		tg3_flag_clear(tp, TSO_BUG);
 		tp->fw_needed = NULL;
@@ -14034,9 +14058,13 @@ static int __devinit tg3_get_invariants(struct tg3 *tp)
 		tg3_flag_set(tp, SHORT_DMA_BUG);
 
 	if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719)
-		tg3_flag_set(tp, 4K_FIFO_LIMIT);
+		tp->dma_limit = TG3_TX_BD_DMA_MAX_4K;
+	else if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57766)
+		tp->dma_limit = TG3_TX_BD_DMA_MAX_2K;
 
-	if (tg3_flag(tp, 5717_PLUS))
+	if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 ||
+	    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 ||
+	    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5720)
 		tg3_flag_set(tp, LRG_PROD_RING_CAP);
 
 	if (tg3_flag(tp, 57765_PLUS) &&
@@ -14056,12 +14084,11 @@ static int __devinit tg3_get_invariants(struct tg3 *tp)
 
 		tg3_flag_set(tp, PCI_EXPRESS);
 
-		tp->pcie_readrq = 4096;
-		if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 ||
-		    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5720)
-			tp->pcie_readrq = 2048;
-
-		pcie_set_readrq(tp->pdev, tp->pcie_readrq);
+		if (tp->pci_chip_rev_id == CHIPREV_ID_5719_A0) {
+			int readrq = pcie_get_readrq(tp->pdev);
+			if (readrq > 2048)
+				pcie_set_readrq(tp->pdev, 2048);
+		}
 
 		pci_read_config_word(tp->pdev,
 				     pci_pcie_cap(tp->pdev) + PCI_EXP_LNKCTL,
@@ -14273,6 +14300,12 @@ static int __devinit tg3_get_invariants(struct tg3 *tp)
 	 */
 	tg3_get_eeprom_hw_cfg(tp);
 
+	if (tp->fw_needed && tg3_flag(tp, ENABLE_ASF)) {
+		tg3_flag_clear(tp, TSO_CAPABLE);
+		tg3_flag_clear(tp, TSO_BUG);
+		tp->fw_needed = NULL;
+	}
+
 	if (tg3_flag(tp, ENABLE_APE)) {
 		/* Allow reads and writes to the
 		 * APE register and memory space.
@@ -14311,7 +14344,7 @@ static int __devinit tg3_get_invariants(struct tg3 *tp)
 
 	if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5755 ||
 	    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57780 ||
-	    GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765)
+	    tg3_flag(tp, 57765_CLASS))
 		tp->grc_local_ctrl |= GRC_LCLCTRL_GPIO_UART_SEL;
 
 	if (tp->pdev->device == PCI_DEVICE_ID_TIGON3_5761 ||
@@ -14548,11 +14581,11 @@ static int __devinit tg3_get_invariants(struct tg3 *tp)
 	else
 		tg3_flag_clear(tp, POLL_SERDES);
 
-	tp->rx_offset = NET_IP_ALIGN;
+	tp->rx_offset = NET_SKB_PAD + NET_IP_ALIGN;
 	tp->rx_copy_thresh = TG3_RX_COPY_THRESHOLD;
 	if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5701 &&
 	    tg3_flag(tp, PCIX_MODE)) {
-		tp->rx_offset = 0;
+		tp->rx_offset = NET_SKB_PAD;
 #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 		tp->rx_copy_thresh = ~(u16)0;
 #endif
@@ -15313,7 +15346,7 @@ static int __devinit tg3_init_one(struct pci_dev *pdev,
 	u32 sndmbx, rcvmbx, intmbx;
 	char str[40];
 	u64 dma_mask, persist_dma_mask;
-	u32 features = 0;
+	netdev_features_t features = 0;
 
 	printk_once(KERN_INFO "%s\n", version);
 
diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h
index 94b4bd0..aea8f72 100644
--- a/drivers/net/ethernet/broadcom/tg3.h
+++ b/drivers/net/ethernet/broadcom/tg3.h
@@ -31,6 +31,8 @@
 #define TG3_RX_RET_MAX_SIZE_5705	512
 #define TG3_RX_RET_MAX_SIZE_5717	4096
 
+#define TG3_RSS_INDIR_TBL_SIZE		128
+
 /* First 256 bytes are a mirror of PCI config space. */
 #define TG3PCI_VENDOR			0x00000000
 #define  TG3PCI_VENDOR_BROADCOM		 0x14e4
@@ -57,6 +59,10 @@
 #define  TG3PCI_DEVICE_TIGON3_57795	 0x16b6
 #define  TG3PCI_DEVICE_TIGON3_5719	 0x1657
 #define  TG3PCI_DEVICE_TIGON3_5720	 0x165f
+#define  TG3PCI_DEVICE_TIGON3_57762	 0x1682
+#define  TG3PCI_DEVICE_TIGON3_57766	 0x1686
+#define  TG3PCI_DEVICE_TIGON3_57786	 0x16b3
+#define  TG3PCI_DEVICE_TIGON3_57782	 0x16b7
 /* 0x04 --> 0x2c unused */
 #define TG3PCI_SUBVENDOR_ID_BROADCOM		PCI_VENDOR_ID_BROADCOM
 #define TG3PCI_SUBDEVICE_ID_BROADCOM_95700A6	0x1644
@@ -168,6 +174,7 @@
 #define   ASIC_REV_57765		 0x57785
 #define   ASIC_REV_5719			 0x5719
 #define   ASIC_REV_5720			 0x5720
+#define   ASIC_REV_57766		 0x57766
 #define  GET_CHIP_REV(CHIP_REV_ID)	((CHIP_REV_ID) >> 8)
 #define   CHIPREV_5700_AX		 0x70
 #define   CHIPREV_5700_BX		 0x71
@@ -1340,6 +1347,7 @@
 #define  RDMAC_MODE_MBUF_SBD_CRPT_ENAB	 0x00002000
 #define  RDMAC_MODE_FIFO_SIZE_128	 0x00020000
 #define  RDMAC_MODE_FIFO_LONG_BURST	 0x00030000
+#define  RDMAC_MODE_JMB_2K_MMRR		 0x00800000
 #define  RDMAC_MODE_MULT_DMA_RD_DIS	 0x01000000
 #define  RDMAC_MODE_IPV4_LSO_EN		 0x08000000
 #define  RDMAC_MODE_IPV6_LSO_EN		 0x10000000
@@ -2174,6 +2182,7 @@
 #define  MII_TG3_EXT_CTRL_TBI		0x8000
 
 #define MII_TG3_EXT_STAT		0x11 /* Extended status register */
+#define  MII_TG3_EXT_STAT_MDIX		0x2000
 #define  MII_TG3_EXT_STAT_LPASS		0x0100
 
 #define MII_TG3_RXR_COUNTERS		0x14 /* Local/Remote Receiver Counts */
@@ -2277,6 +2286,9 @@
 #define  MII_TG3_FET_PTEST_FRC_TX_LINK	0x1000
 #define  MII_TG3_FET_PTEST_FRC_TX_LOCK	0x0800
 
+#define MII_TG3_FET_GEN_STAT		0x1c
+#define  MII_TG3_FET_GEN_STAT_MDIXSTAT	0x2000
+
 #define MII_TG3_FET_TEST		0x1f
 #define  MII_TG3_FET_SHADOW_EN		0x0080
 
@@ -2662,9 +2674,13 @@ struct tg3_hw_stats {
 /* 'mapping' is superfluous as the chip does not write into
  * the tx/rx post rings so we could just fetch it from there.
  * But the cache behavior is better how we are doing it now.
+ *
+ * This driver uses new build_skb() API :
+ * RX ring buffer contains pointer to kmalloc() data only,
+ * skb are built only after Hardware filled the frame.
  */
 struct ring_info {
-	struct sk_buff			*skb;
+	u8				*data;
 	DEFINE_DMA_UNMAP_ADDR(mapping);
 };
 
@@ -2690,6 +2706,7 @@ struct tg3_link_config {
 #define DUPLEX_INVALID		0xff
 #define AUTONEG_INVALID		0xff
 	u16				active_speed;
+	u32				rmt_adv;
 
 	/* When we go in and out of low power mode we need
 	 * to swap with this state.
@@ -2865,6 +2882,8 @@ enum TG3_FLAGS {
 	TG3_FLAG_NVRAM_BUFFERED,
 	TG3_FLAG_SUPPORT_MSI,
 	TG3_FLAG_SUPPORT_MSIX,
+	TG3_FLAG_USING_MSI,
+	TG3_FLAG_USING_MSIX,
 	TG3_FLAG_PCIX_MODE,
 	TG3_FLAG_PCI_HIGH_SPEED,
 	TG3_FLAG_PCI_32BIT,
@@ -2880,7 +2899,6 @@ enum TG3_FLAGS {
 	TG3_FLAG_CHIP_RESETTING,
 	TG3_FLAG_INIT_COMPLETE,
 	TG3_FLAG_TSO_BUG,
-	TG3_FLAG_IS_5788,
 	TG3_FLAG_MAX_RXPEND_64,
 	TG3_FLAG_TSO_CAPABLE,
 	TG3_FLAG_PCI_EXPRESS, /* BCM5785 + pci_is_pcie() */
@@ -2889,14 +2907,9 @@ enum TG3_FLAGS {
 	TG3_FLAG_IS_NIC,
 	TG3_FLAG_FLASH,
 	TG3_FLAG_HW_TSO_1,
-	TG3_FLAG_5705_PLUS,
-	TG3_FLAG_5750_PLUS,
+	TG3_FLAG_HW_TSO_2,
 	TG3_FLAG_HW_TSO_3,
-	TG3_FLAG_USING_MSI,
-	TG3_FLAG_USING_MSIX,
 	TG3_FLAG_ICH_WORKAROUND,
-	TG3_FLAG_5780_CLASS,
-	TG3_FLAG_HW_TSO_2,
 	TG3_FLAG_1SHOT_MSI,
 	TG3_FLAG_NO_FWARE_REPORTED,
 	TG3_FLAG_NO_NVRAM_ADDR_TRANS,
@@ -2910,18 +2923,23 @@ enum TG3_FLAGS {
 	TG3_FLAG_RGMII_EXT_IBND_RX_EN,
 	TG3_FLAG_RGMII_EXT_IBND_TX_EN,
 	TG3_FLAG_CLKREQ_BUG,
-	TG3_FLAG_5755_PLUS,
 	TG3_FLAG_NO_NVRAM,
 	TG3_FLAG_ENABLE_RSS,
 	TG3_FLAG_ENABLE_TSS,
 	TG3_FLAG_SHORT_DMA_BUG,
 	TG3_FLAG_USE_JUMBO_BDFLAG,
 	TG3_FLAG_L1PLLPD_EN,
-	TG3_FLAG_57765_PLUS,
 	TG3_FLAG_APE_HAS_NCSI,
-	TG3_FLAG_5717_PLUS,
 	TG3_FLAG_4K_FIFO_LIMIT,
 	TG3_FLAG_RESET_TASK_PENDING,
+	TG3_FLAG_5705_PLUS,
+	TG3_FLAG_IS_5788,
+	TG3_FLAG_5750_PLUS,
+	TG3_FLAG_5780_CLASS,
+	TG3_FLAG_5755_PLUS,
+	TG3_FLAG_57765_PLUS,
+	TG3_FLAG_57765_CLASS,
+	TG3_FLAG_5717_PLUS,
 
 	/* Add new flags before this comment and TG3_FLAG_NUMBER_OF_FLAGS */
 	TG3_FLAG_NUMBER_OF_FLAGS,	/* Last entry in enum TG3_FLAGS */
@@ -2985,6 +3003,7 @@ struct tg3 {
 	/* begin "tx thread" cacheline section */
 	void				(*write32_tx_mbox) (struct tg3 *, u32,
 							    u32);
+	u32				dma_limit;
 
 	/* begin "rx thread" cacheline section */
 	struct tg3_napi			napi[TG3_IRQ_MAX_VECS];
@@ -3005,7 +3024,6 @@ struct tg3 {
 	unsigned long			rx_dropped;
 	unsigned long			tx_dropped;
 	struct rtnl_link_stats64	net_stats_prev;
-	struct tg3_ethtool_stats	estats;
 	struct tg3_ethtool_stats	estats_prev;
 
 	DECLARE_BITMAP(tg3_flags, TG3_FLAG_NUMBER_OF_FLAGS);
@@ -3131,10 +3149,12 @@ struct tg3 {
 #define TG3_PHYFLG_SERDES_PREEMPHASIS	0x00010000
 #define TG3_PHYFLG_PARALLEL_DETECT	0x00020000
 #define TG3_PHYFLG_EEE_CAP		0x00040000
+#define TG3_PHYFLG_MDIX_STATE		0x00200000
 
 	u32				led_ctrl;
 	u32				phy_otp;
 	u32				setlpicnt;
+	u8				rss_ind_tbl[TG3_RSS_INDIR_TBL_SIZE];
 
 #define TG3_BPN_SIZE			24
 	char				board_part_number[TG3_BPN_SIZE];
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 7f3091e..aac3a3b 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -2968,7 +2968,7 @@ bnad_change_mtu(struct net_device *netdev, int new_mtu)
 	return err;
 }
 
-static void
+static int
 bnad_vlan_rx_add_vid(struct net_device *netdev,
 				 unsigned short vid)
 {
@@ -2976,7 +2976,7 @@ bnad_vlan_rx_add_vid(struct net_device *netdev,
 	unsigned long flags;
 
 	if (!bnad->rx_info[0].rx)
-		return;
+		return 0;
 
 	mutex_lock(&bnad->conf_mutex);
 
@@ -2986,9 +2986,11 @@ bnad_vlan_rx_add_vid(struct net_device *netdev,
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 
 	mutex_unlock(&bnad->conf_mutex);
+
+	return 0;
 }
 
-static void
+static int
 bnad_vlan_rx_kill_vid(struct net_device *netdev,
 				  unsigned short vid)
 {
@@ -2996,7 +2998,7 @@ bnad_vlan_rx_kill_vid(struct net_device *netdev,
 	unsigned long flags;
 
 	if (!bnad->rx_info[0].rx)
-		return;
+		return 0;
 
 	mutex_lock(&bnad->conf_mutex);
 
@@ -3006,6 +3008,8 @@ bnad_vlan_rx_kill_vid(struct net_device *netdev,
 	spin_unlock_irqrestore(&bnad->bna_lock, flags);
 
 	mutex_unlock(&bnad->conf_mutex);
+
+	return 0;
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
index fd3dcc1..38d5c66 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
@@ -296,8 +296,8 @@ bnad_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 	struct bfa_ioc_attr *ioc_attr;
 	unsigned long flags;
 
-	strcpy(drvinfo->driver, BNAD_NAME);
-	strcpy(drvinfo->version, BNAD_VERSION);
+	strlcpy(drvinfo->driver, BNAD_NAME, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, BNAD_VERSION, sizeof(drvinfo->version));
 
 	ioc_attr = kzalloc(sizeof(*ioc_attr), GFP_KERNEL);
 	if (ioc_attr) {
@@ -305,12 +305,13 @@ bnad_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 		bfa_nw_ioc_get_attr(&bnad->bna.ioceth.ioc, ioc_attr);
 		spin_unlock_irqrestore(&bnad->bna_lock, flags);
 
-		strncpy(drvinfo->fw_version, ioc_attr->adapter_attr.fw_ver,
-			sizeof(drvinfo->fw_version) - 1);
+		strlcpy(drvinfo->fw_version, ioc_attr->adapter_attr.fw_ver,
+			sizeof(drvinfo->fw_version));
 		kfree(ioc_attr);
 	}
 
-	strncpy(drvinfo->bus_info, pci_name(bnad->pcidev), ETHTOOL_BUSINFO_LEN);
+	strlcpy(drvinfo->bus_info, pci_name(bnad->pcidev),
+		sizeof(drvinfo->bus_info));
 }
 
 static void
diff --git a/drivers/net/ethernet/brocade/bna/cna.h b/drivers/net/ethernet/brocade/bna/cna.h
index 1b3e90d..32e8f17 100644
--- a/drivers/net/ethernet/brocade/bna/cna.h
+++ b/drivers/net/ethernet/brocade/bna/cna.h
@@ -43,8 +43,7 @@ extern char bfa_version[];
 
 #pragma pack(1)
 
-#define MAC_ADDRLEN	(6)
-typedef struct mac { u8 mac[MAC_ADDRLEN]; } mac_t;
+typedef struct mac { u8 mac[ETH_ALEN]; } mac_t;
 
 #pragma pack()
 
diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig
index 98849a1..b48378a 100644
--- a/drivers/net/ethernet/cadence/Kconfig
+++ b/drivers/net/ethernet/cadence/Kconfig
@@ -7,6 +7,7 @@ config HAVE_NET_MACB
 
 config NET_ATMEL
 	bool "Atmel devices"
+	default y
 	depends on HAVE_NET_MACB || (ARM && ARCH_AT91RM9200)
 	---help---
 	  If you have a network (Ethernet) card belonging to this class, say Y.
diff --git a/drivers/net/ethernet/calxeda/Kconfig b/drivers/net/ethernet/calxeda/Kconfig
new file mode 100644
index 0000000..a52e725
--- /dev/null
+++ b/drivers/net/ethernet/calxeda/Kconfig
@@ -0,0 +1,7 @@
+config NET_CALXEDA_XGMAC
+	tristate "Calxeda 1G/10G XGMAC Ethernet driver"
+
+	select CRC32
+	help
+	  This is the driver for the XGMAC Ethernet IP block found on Calxeda
+	  Highbank platforms.
diff --git a/drivers/net/ethernet/calxeda/Makefile b/drivers/net/ethernet/calxeda/Makefile
new file mode 100644
index 0000000..f0ef080
--- /dev/null
+++ b/drivers/net/ethernet/calxeda/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_NET_CALXEDA_XGMAC) += xgmac.o
diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c
new file mode 100644
index 0000000..107c1b0
--- /dev/null
+++ b/drivers/net/ethernet/calxeda/xgmac.c
@@ -0,0 +1,1928 @@
+/*
+ * Copyright 2010-2011 Calxeda, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/circ_buf.h>
+#include <linux/interrupt.h>
+#include <linux/etherdevice.h>
+#include <linux/platform_device.h>
+#include <linux/skbuff.h>
+#include <linux/ethtool.h>
+#include <linux/if.h>
+#include <linux/crc32.h>
+#include <linux/dma-mapping.h>
+#include <linux/slab.h>
+
+/* XGMAC Register definitions */
+#define XGMAC_CONTROL		0x00000000	/* MAC Configuration */
+#define XGMAC_FRAME_FILTER	0x00000004	/* MAC Frame Filter */
+#define XGMAC_FLOW_CTRL		0x00000018	/* MAC Flow Control */
+#define XGMAC_VLAN_TAG		0x0000001C	/* VLAN Tags */
+#define XGMAC_VERSION		0x00000020	/* Version */
+#define XGMAC_VLAN_INCL		0x00000024	/* VLAN tag for tx frames */
+#define XGMAC_LPI_CTRL		0x00000028	/* LPI Control and Status */
+#define XGMAC_LPI_TIMER		0x0000002C	/* LPI Timers Control */
+#define XGMAC_TX_PACE		0x00000030	/* Transmit Pace and Stretch */
+#define XGMAC_VLAN_HASH		0x00000034	/* VLAN Hash Table */
+#define XGMAC_DEBUG		0x00000038	/* Debug */
+#define XGMAC_INT_STAT		0x0000003C	/* Interrupt and Control */
+#define XGMAC_ADDR_HIGH(reg)	(0x00000040 + ((reg) * 8))
+#define XGMAC_ADDR_LOW(reg)	(0x00000044 + ((reg) * 8))
+#define XGMAC_HASH(n)		(0x00000300 + (n) * 4) /* HASH table regs */
+#define XGMAC_NUM_HASH		16
+#define XGMAC_OMR		0x00000400
+#define XGMAC_REMOTE_WAKE	0x00000700	/* Remote Wake-Up Frm Filter */
+#define XGMAC_PMT		0x00000704	/* PMT Control and Status */
+#define XGMAC_MMC_CTRL		0x00000800	/* XGMAC MMC Control */
+#define XGMAC_MMC_INTR_RX	0x00000804	/* Recieve Interrupt */
+#define XGMAC_MMC_INTR_TX	0x00000808	/* Transmit Interrupt */
+#define XGMAC_MMC_INTR_MASK_RX	0x0000080c	/* Recieve Interrupt Mask */
+#define XGMAC_MMC_INTR_MASK_TX	0x00000810	/* Transmit Interrupt Mask */
+
+/* Hardware TX Statistics Counters */
+#define XGMAC_MMC_TXOCTET_GB_LO	0x00000814
+#define XGMAC_MMC_TXOCTET_GB_HI	0x00000818
+#define XGMAC_MMC_TXFRAME_GB_LO	0x0000081C
+#define XGMAC_MMC_TXFRAME_GB_HI	0x00000820
+#define XGMAC_MMC_TXBCFRAME_G	0x00000824
+#define XGMAC_MMC_TXMCFRAME_G	0x0000082C
+#define XGMAC_MMC_TXUCFRAME_GB	0x00000864
+#define XGMAC_MMC_TXMCFRAME_GB	0x0000086C
+#define XGMAC_MMC_TXBCFRAME_GB	0x00000874
+#define XGMAC_MMC_TXUNDERFLOW	0x0000087C
+#define XGMAC_MMC_TXOCTET_G_LO	0x00000884
+#define XGMAC_MMC_TXOCTET_G_HI	0x00000888
+#define XGMAC_MMC_TXFRAME_G_LO	0x0000088C
+#define XGMAC_MMC_TXFRAME_G_HI	0x00000890
+#define XGMAC_MMC_TXPAUSEFRAME	0x00000894
+#define XGMAC_MMC_TXVLANFRAME	0x0000089C
+
+/* Hardware RX Statistics Counters */
+#define XGMAC_MMC_RXFRAME_GB_LO	0x00000900
+#define XGMAC_MMC_RXFRAME_GB_HI	0x00000904
+#define XGMAC_MMC_RXOCTET_GB_LO	0x00000908
+#define XGMAC_MMC_RXOCTET_GB_HI	0x0000090C
+#define XGMAC_MMC_RXOCTET_G_LO	0x00000910
+#define XGMAC_MMC_RXOCTET_G_HI	0x00000914
+#define XGMAC_MMC_RXBCFRAME_G	0x00000918
+#define XGMAC_MMC_RXMCFRAME_G	0x00000920
+#define XGMAC_MMC_RXCRCERR	0x00000928
+#define XGMAC_MMC_RXRUNT	0x00000930
+#define XGMAC_MMC_RXJABBER	0x00000934
+#define XGMAC_MMC_RXUCFRAME_G	0x00000970
+#define XGMAC_MMC_RXLENGTHERR	0x00000978
+#define XGMAC_MMC_RXPAUSEFRAME	0x00000988
+#define XGMAC_MMC_RXOVERFLOW	0x00000990
+#define XGMAC_MMC_RXVLANFRAME	0x00000998
+#define XGMAC_MMC_RXWATCHDOG	0x000009a0
+
+/* DMA Control and Status Registers */
+#define XGMAC_DMA_BUS_MODE	0x00000f00	/* Bus Mode */
+#define XGMAC_DMA_TX_POLL	0x00000f04	/* Transmit Poll Demand */
+#define XGMAC_DMA_RX_POLL	0x00000f08	/* Received Poll Demand */
+#define XGMAC_DMA_RX_BASE_ADDR	0x00000f0c	/* Receive List Base */
+#define XGMAC_DMA_TX_BASE_ADDR	0x00000f10	/* Transmit List Base */
+#define XGMAC_DMA_STATUS	0x00000f14	/* Status Register */
+#define XGMAC_DMA_CONTROL	0x00000f18	/* Ctrl (Operational Mode) */
+#define XGMAC_DMA_INTR_ENA	0x00000f1c	/* Interrupt Enable */
+#define XGMAC_DMA_MISS_FRAME_CTR 0x00000f20	/* Missed Frame Counter */
+#define XGMAC_DMA_RI_WDOG_TIMER	0x00000f24	/* RX Intr Watchdog Timer */
+#define XGMAC_DMA_AXI_BUS	0x00000f28	/* AXI Bus Mode */
+#define XGMAC_DMA_AXI_STATUS	0x00000f2C	/* AXI Status */
+#define XGMAC_DMA_HW_FEATURE	0x00000f58	/* Enabled Hardware Features */
+
+#define XGMAC_ADDR_AE		0x80000000
+#define XGMAC_MAX_FILTER_ADDR	31
+
+/* PMT Control and Status */
+#define XGMAC_PMT_POINTER_RESET	0x80000000
+#define XGMAC_PMT_GLBL_UNICAST	0x00000200
+#define XGMAC_PMT_WAKEUP_RX_FRM	0x00000040
+#define XGMAC_PMT_MAGIC_PKT	0x00000020
+#define XGMAC_PMT_WAKEUP_FRM_EN	0x00000004
+#define XGMAC_PMT_MAGIC_PKT_EN	0x00000002
+#define XGMAC_PMT_POWERDOWN	0x00000001
+
+#define XGMAC_CONTROL_SPD	0x40000000	/* Speed control */
+#define XGMAC_CONTROL_SPD_MASK	0x60000000
+#define XGMAC_CONTROL_SPD_1G	0x60000000
+#define XGMAC_CONTROL_SPD_2_5G	0x40000000
+#define XGMAC_CONTROL_SPD_10G	0x00000000
+#define XGMAC_CONTROL_SARC	0x10000000	/* Source Addr Insert/Replace */
+#define XGMAC_CONTROL_SARK_MASK	0x18000000
+#define XGMAC_CONTROL_CAR	0x04000000	/* CRC Addition/Replacement */
+#define XGMAC_CONTROL_CAR_MASK	0x06000000
+#define XGMAC_CONTROL_DP	0x01000000	/* Disable Padding */
+#define XGMAC_CONTROL_WD	0x00800000	/* Disable Watchdog on rx */
+#define XGMAC_CONTROL_JD	0x00400000	/* Jabber disable */
+#define XGMAC_CONTROL_JE	0x00100000	/* Jumbo frame */
+#define XGMAC_CONTROL_LM	0x00001000	/* Loop-back mode */
+#define XGMAC_CONTROL_IPC	0x00000400	/* Checksum Offload */
+#define XGMAC_CONTROL_ACS	0x00000080	/* Automatic Pad/FCS Strip */
+#define XGMAC_CONTROL_DDIC	0x00000010	/* Disable Deficit Idle Count */
+#define XGMAC_CONTROL_TE	0x00000008	/* Transmitter Enable */
+#define XGMAC_CONTROL_RE	0x00000004	/* Receiver Enable */
+
+/* XGMAC Frame Filter defines */
+#define XGMAC_FRAME_FILTER_PR	0x00000001	/* Promiscuous Mode */
+#define XGMAC_FRAME_FILTER_HUC	0x00000002	/* Hash Unicast */
+#define XGMAC_FRAME_FILTER_HMC	0x00000004	/* Hash Multicast */
+#define XGMAC_FRAME_FILTER_DAIF	0x00000008	/* DA Inverse Filtering */
+#define XGMAC_FRAME_FILTER_PM	0x00000010	/* Pass all multicast */
+#define XGMAC_FRAME_FILTER_DBF	0x00000020	/* Disable Broadcast frames */
+#define XGMAC_FRAME_FILTER_SAIF	0x00000100	/* Inverse Filtering */
+#define XGMAC_FRAME_FILTER_SAF	0x00000200	/* Source Address Filter */
+#define XGMAC_FRAME_FILTER_HPF	0x00000400	/* Hash or perfect Filter */
+#define XGMAC_FRAME_FILTER_VHF	0x00000800	/* VLAN Hash Filter */
+#define XGMAC_FRAME_FILTER_VPF	0x00001000	/* VLAN Perfect Filter */
+#define XGMAC_FRAME_FILTER_RA	0x80000000	/* Receive all mode */
+
+/* XGMAC FLOW CTRL defines */
+#define XGMAC_FLOW_CTRL_PT_MASK	0xffff0000	/* Pause Time Mask */
+#define XGMAC_FLOW_CTRL_PT_SHIFT	16
+#define XGMAC_FLOW_CTRL_DZQP	0x00000080	/* Disable Zero-Quanta Phase */
+#define XGMAC_FLOW_CTRL_PLT	0x00000020	/* Pause Low Threshhold */
+#define XGMAC_FLOW_CTRL_PLT_MASK 0x00000030	/* PLT MASK */
+#define XGMAC_FLOW_CTRL_UP	0x00000008	/* Unicast Pause Frame Detect */
+#define XGMAC_FLOW_CTRL_RFE	0x00000004	/* Rx Flow Control Enable */
+#define XGMAC_FLOW_CTRL_TFE	0x00000002	/* Tx Flow Control Enable */
+#define XGMAC_FLOW_CTRL_FCB_BPA	0x00000001	/* Flow Control Busy ... */
+
+/* XGMAC_INT_STAT reg */
+#define XGMAC_INT_STAT_PMT	0x0080		/* PMT Interrupt Status */
+#define XGMAC_INT_STAT_LPI	0x0040		/* LPI Interrupt Status */
+
+/* DMA Bus Mode register defines */
+#define DMA_BUS_MODE_SFT_RESET	0x00000001	/* Software Reset */
+#define DMA_BUS_MODE_DSL_MASK	0x0000007c	/* Descriptor Skip Length */
+#define DMA_BUS_MODE_DSL_SHIFT	2		/* (in DWORDS) */
+#define DMA_BUS_MODE_ATDS	0x00000080	/* Alternate Descriptor Size */
+
+/* Programmable burst length */
+#define DMA_BUS_MODE_PBL_MASK	0x00003f00	/* Programmable Burst Len */
+#define DMA_BUS_MODE_PBL_SHIFT	8
+#define DMA_BUS_MODE_FB		0x00010000	/* Fixed burst */
+#define DMA_BUS_MODE_RPBL_MASK	0x003e0000	/* Rx-Programmable Burst Len */
+#define DMA_BUS_MODE_RPBL_SHIFT	17
+#define DMA_BUS_MODE_USP	0x00800000
+#define DMA_BUS_MODE_8PBL	0x01000000
+#define DMA_BUS_MODE_AAL	0x02000000
+
+/* DMA Bus Mode register defines */
+#define DMA_BUS_PR_RATIO_MASK	0x0000c000	/* Rx/Tx priority ratio */
+#define DMA_BUS_PR_RATIO_SHIFT	14
+#define DMA_BUS_FB		0x00010000	/* Fixed Burst */
+
+/* DMA Control register defines */
+#define DMA_CONTROL_ST		0x00002000	/* Start/Stop Transmission */
+#define DMA_CONTROL_SR		0x00000002	/* Start/Stop Receive */
+#define DMA_CONTROL_DFF		0x01000000	/* Disable flush of rx frames */
+
+/* DMA Normal interrupt */
+#define DMA_INTR_ENA_NIE	0x00010000	/* Normal Summary */
+#define DMA_INTR_ENA_AIE	0x00008000	/* Abnormal Summary */
+#define DMA_INTR_ENA_ERE	0x00004000	/* Early Receive */
+#define DMA_INTR_ENA_FBE	0x00002000	/* Fatal Bus Error */
+#define DMA_INTR_ENA_ETE	0x00000400	/* Early Transmit */
+#define DMA_INTR_ENA_RWE	0x00000200	/* Receive Watchdog */
+#define DMA_INTR_ENA_RSE	0x00000100	/* Receive Stopped */
+#define DMA_INTR_ENA_RUE	0x00000080	/* Receive Buffer Unavailable */
+#define DMA_INTR_ENA_RIE	0x00000040	/* Receive Interrupt */
+#define DMA_INTR_ENA_UNE	0x00000020	/* Tx Underflow */
+#define DMA_INTR_ENA_OVE	0x00000010	/* Receive Overflow */
+#define DMA_INTR_ENA_TJE	0x00000008	/* Transmit Jabber */
+#define DMA_INTR_ENA_TUE	0x00000004	/* Transmit Buffer Unavail */
+#define DMA_INTR_ENA_TSE	0x00000002	/* Transmit Stopped */
+#define DMA_INTR_ENA_TIE	0x00000001	/* Transmit Interrupt */
+
+#define DMA_INTR_NORMAL		(DMA_INTR_ENA_NIE | DMA_INTR_ENA_RIE | \
+				 DMA_INTR_ENA_TUE)
+
+#define DMA_INTR_ABNORMAL	(DMA_INTR_ENA_AIE | DMA_INTR_ENA_FBE | \
+				 DMA_INTR_ENA_RWE | DMA_INTR_ENA_RSE | \
+				 DMA_INTR_ENA_RUE | DMA_INTR_ENA_UNE | \
+				 DMA_INTR_ENA_OVE | DMA_INTR_ENA_TJE | \
+				 DMA_INTR_ENA_TSE)
+
+/* DMA default interrupt mask */
+#define DMA_INTR_DEFAULT_MASK	(DMA_INTR_NORMAL | DMA_INTR_ABNORMAL)
+
+/* DMA Status register defines */
+#define DMA_STATUS_GMI		0x08000000	/* MMC interrupt */
+#define DMA_STATUS_GLI		0x04000000	/* GMAC Line interface int */
+#define DMA_STATUS_EB_MASK	0x00380000	/* Error Bits Mask */
+#define DMA_STATUS_EB_TX_ABORT	0x00080000	/* Error Bits - TX Abort */
+#define DMA_STATUS_EB_RX_ABORT	0x00100000	/* Error Bits - RX Abort */
+#define DMA_STATUS_TS_MASK	0x00700000	/* Transmit Process State */
+#define DMA_STATUS_TS_SHIFT	20
+#define DMA_STATUS_RS_MASK	0x000e0000	/* Receive Process State */
+#define DMA_STATUS_RS_SHIFT	17
+#define DMA_STATUS_NIS		0x00010000	/* Normal Interrupt Summary */
+#define DMA_STATUS_AIS		0x00008000	/* Abnormal Interrupt Summary */
+#define DMA_STATUS_ERI		0x00004000	/* Early Receive Interrupt */
+#define DMA_STATUS_FBI		0x00002000	/* Fatal Bus Error Interrupt */
+#define DMA_STATUS_ETI		0x00000400	/* Early Transmit Interrupt */
+#define DMA_STATUS_RWT		0x00000200	/* Receive Watchdog Timeout */
+#define DMA_STATUS_RPS		0x00000100	/* Receive Process Stopped */
+#define DMA_STATUS_RU		0x00000080	/* Receive Buffer Unavailable */
+#define DMA_STATUS_RI		0x00000040	/* Receive Interrupt */
+#define DMA_STATUS_UNF		0x00000020	/* Transmit Underflow */
+#define DMA_STATUS_OVF		0x00000010	/* Receive Overflow */
+#define DMA_STATUS_TJT		0x00000008	/* Transmit Jabber Timeout */
+#define DMA_STATUS_TU		0x00000004	/* Transmit Buffer Unavail */
+#define DMA_STATUS_TPS		0x00000002	/* Transmit Process Stopped */
+#define DMA_STATUS_TI		0x00000001	/* Transmit Interrupt */
+
+/* Common MAC defines */
+#define MAC_ENABLE_TX		0x00000008	/* Transmitter Enable */
+#define MAC_ENABLE_RX		0x00000004	/* Receiver Enable */
+
+/* XGMAC Operation Mode Register */
+#define XGMAC_OMR_TSF		0x00200000	/* TX FIFO Store and Forward */
+#define XGMAC_OMR_FTF		0x00100000	/* Flush Transmit FIFO */
+#define XGMAC_OMR_TTC		0x00020000	/* Transmit Threshhold Ctrl */
+#define XGMAC_OMR_TTC_MASK	0x00030000
+#define XGMAC_OMR_RFD		0x00006000	/* FC Deactivation Threshhold */
+#define XGMAC_OMR_RFD_MASK	0x00007000	/* FC Deact Threshhold MASK */
+#define XGMAC_OMR_RFA		0x00000600	/* FC Activation Threshhold */
+#define XGMAC_OMR_RFA_MASK	0x00000E00	/* FC Act Threshhold MASK */
+#define XGMAC_OMR_EFC		0x00000100	/* Enable Hardware FC */
+#define XGMAC_OMR_FEF		0x00000080	/* Forward Error Frames */
+#define XGMAC_OMR_DT		0x00000040	/* Drop TCP/IP csum Errors */
+#define XGMAC_OMR_RSF		0x00000020	/* RX FIFO Store and Forward */
+#define XGMAC_OMR_RTC		0x00000010	/* RX Threshhold Ctrl */
+#define XGMAC_OMR_RTC_MASK	0x00000018	/* RX Threshhold Ctrl MASK */
+
+/* XGMAC HW Features Register */
+#define DMA_HW_FEAT_TXCOESEL	0x00010000	/* TX Checksum offload */
+
+#define XGMAC_MMC_CTRL_CNT_FRZ	0x00000008
+
+/* XGMAC Descriptor Defines */
+#define MAX_DESC_BUF_SZ		(0x2000 - 8)
+
+#define RXDESC_EXT_STATUS	0x00000001
+#define RXDESC_CRC_ERR		0x00000002
+#define RXDESC_RX_ERR		0x00000008
+#define RXDESC_RX_WDOG		0x00000010
+#define RXDESC_FRAME_TYPE	0x00000020
+#define RXDESC_GIANT_FRAME	0x00000080
+#define RXDESC_LAST_SEG		0x00000100
+#define RXDESC_FIRST_SEG	0x00000200
+#define RXDESC_VLAN_FRAME	0x00000400
+#define RXDESC_OVERFLOW_ERR	0x00000800
+#define RXDESC_LENGTH_ERR	0x00001000
+#define RXDESC_SA_FILTER_FAIL	0x00002000
+#define RXDESC_DESCRIPTOR_ERR	0x00004000
+#define RXDESC_ERROR_SUMMARY	0x00008000
+#define RXDESC_FRAME_LEN_OFFSET	16
+#define RXDESC_FRAME_LEN_MASK	0x3fff0000
+#define RXDESC_DA_FILTER_FAIL	0x40000000
+
+#define RXDESC1_END_RING	0x00008000
+
+#define RXDESC_IP_PAYLOAD_MASK	0x00000003
+#define RXDESC_IP_PAYLOAD_UDP	0x00000001
+#define RXDESC_IP_PAYLOAD_TCP	0x00000002
+#define RXDESC_IP_PAYLOAD_ICMP	0x00000003
+#define RXDESC_IP_HEADER_ERR	0x00000008
+#define RXDESC_IP_PAYLOAD_ERR	0x00000010
+#define RXDESC_IPV4_PACKET	0x00000040
+#define RXDESC_IPV6_PACKET	0x00000080
+#define TXDESC_UNDERFLOW_ERR	0x00000001
+#define TXDESC_JABBER_TIMEOUT	0x00000002
+#define TXDESC_LOCAL_FAULT	0x00000004
+#define TXDESC_REMOTE_FAULT	0x00000008
+#define TXDESC_VLAN_FRAME	0x00000010
+#define TXDESC_FRAME_FLUSHED	0x00000020
+#define TXDESC_IP_HEADER_ERR	0x00000040
+#define TXDESC_PAYLOAD_CSUM_ERR	0x00000080
+#define TXDESC_ERROR_SUMMARY	0x00008000
+#define TXDESC_SA_CTRL_INSERT	0x00040000
+#define TXDESC_SA_CTRL_REPLACE	0x00080000
+#define TXDESC_2ND_ADDR_CHAINED	0x00100000
+#define TXDESC_END_RING		0x00200000
+#define TXDESC_CSUM_IP		0x00400000
+#define TXDESC_CSUM_IP_PAYLD	0x00800000
+#define TXDESC_CSUM_ALL		0x00C00000
+#define TXDESC_CRC_EN_REPLACE	0x01000000
+#define TXDESC_CRC_EN_APPEND	0x02000000
+#define TXDESC_DISABLE_PAD	0x04000000
+#define TXDESC_FIRST_SEG	0x10000000
+#define TXDESC_LAST_SEG		0x20000000
+#define TXDESC_INTERRUPT	0x40000000
+
+#define DESC_OWN		0x80000000
+#define DESC_BUFFER1_SZ_MASK	0x00001fff
+#define DESC_BUFFER2_SZ_MASK	0x1fff0000
+#define DESC_BUFFER2_SZ_OFFSET	16
+
+struct xgmac_dma_desc {
+	__le32 flags;
+	__le32 buf_size;
+	__le32 buf1_addr;		/* Buffer 1 Address Pointer */
+	__le32 buf2_addr;		/* Buffer 2 Address Pointer */
+	__le32 ext_status;
+	__le32 res[3];
+};
+
+struct xgmac_extra_stats {
+	/* Transmit errors */
+	unsigned long tx_jabber;
+	unsigned long tx_frame_flushed;
+	unsigned long tx_payload_error;
+	unsigned long tx_ip_header_error;
+	unsigned long tx_local_fault;
+	unsigned long tx_remote_fault;
+	/* Receive errors */
+	unsigned long rx_watchdog;
+	unsigned long rx_da_filter_fail;
+	unsigned long rx_sa_filter_fail;
+	unsigned long rx_payload_error;
+	unsigned long rx_ip_header_error;
+	/* Tx/Rx IRQ errors */
+	unsigned long tx_undeflow;
+	unsigned long tx_process_stopped;
+	unsigned long rx_buf_unav;
+	unsigned long rx_process_stopped;
+	unsigned long tx_early;
+	unsigned long fatal_bus_error;
+};
+
+struct xgmac_priv {
+	struct xgmac_dma_desc *dma_rx;
+	struct sk_buff **rx_skbuff;
+	unsigned int rx_tail;
+	unsigned int rx_head;
+
+	struct xgmac_dma_desc *dma_tx;
+	struct sk_buff **tx_skbuff;
+	unsigned int tx_head;
+	unsigned int tx_tail;
+
+	void __iomem *base;
+	struct sk_buff_head rx_recycle;
+	unsigned int dma_buf_sz;
+	dma_addr_t dma_rx_phy;
+	dma_addr_t dma_tx_phy;
+
+	struct net_device *dev;
+	struct device *device;
+	struct napi_struct napi;
+
+	struct xgmac_extra_stats xstats;
+
+	spinlock_t stats_lock;
+	int pmt_irq;
+	char rx_pause;
+	char tx_pause;
+	int wolopts;
+};
+
+/* XGMAC Configuration Settings */
+#define MAX_MTU			9000
+#define PAUSE_TIME		0x400
+
+#define DMA_RX_RING_SZ		256
+#define DMA_TX_RING_SZ		128
+/* minimum number of free TX descriptors required to wake up TX process */
+#define TX_THRESH		(DMA_TX_RING_SZ/4)
+
+/* DMA descriptor ring helpers */
+#define dma_ring_incr(n, s)	(((n) + 1) & ((s) - 1))
+#define dma_ring_space(h, t, s)	CIRC_SPACE(h, t, s)
+#define dma_ring_cnt(h, t, s)	CIRC_CNT(h, t, s)
+
+/* XGMAC Descriptor Access Helpers */
+static inline void desc_set_buf_len(struct xgmac_dma_desc *p, u32 buf_sz)
+{
+	if (buf_sz > MAX_DESC_BUF_SZ)
+		p->buf_size = cpu_to_le32(MAX_DESC_BUF_SZ |
+			(buf_sz - MAX_DESC_BUF_SZ) << DESC_BUFFER2_SZ_OFFSET);
+	else
+		p->buf_size = cpu_to_le32(buf_sz);
+}
+
+static inline int desc_get_buf_len(struct xgmac_dma_desc *p)
+{
+	u32 len = cpu_to_le32(p->flags);
+	return (len & DESC_BUFFER1_SZ_MASK) +
+		((len & DESC_BUFFER2_SZ_MASK) >> DESC_BUFFER2_SZ_OFFSET);
+}
+
+static inline void desc_init_rx_desc(struct xgmac_dma_desc *p, int ring_size,
+				     int buf_sz)
+{
+	struct xgmac_dma_desc *end = p + ring_size - 1;
+
+	memset(p, 0, sizeof(*p) * ring_size);
+
+	for (; p <= end; p++)
+		desc_set_buf_len(p, buf_sz);
+
+	end->buf_size |= cpu_to_le32(RXDESC1_END_RING);
+}
+
+static inline void desc_init_tx_desc(struct xgmac_dma_desc *p, u32 ring_size)
+{
+	memset(p, 0, sizeof(*p) * ring_size);
+	p[ring_size - 1].flags = cpu_to_le32(TXDESC_END_RING);
+}
+
+static inline int desc_get_owner(struct xgmac_dma_desc *p)
+{
+	return le32_to_cpu(p->flags) & DESC_OWN;
+}
+
+static inline void desc_set_rx_owner(struct xgmac_dma_desc *p)
+{
+	/* Clear all fields and set the owner */
+	p->flags = cpu_to_le32(DESC_OWN);
+}
+
+static inline void desc_set_tx_owner(struct xgmac_dma_desc *p, u32 flags)
+{
+	u32 tmpflags = le32_to_cpu(p->flags);
+	tmpflags &= TXDESC_END_RING;
+	tmpflags |= flags | DESC_OWN;
+	p->flags = cpu_to_le32(tmpflags);
+}
+
+static inline int desc_get_tx_ls(struct xgmac_dma_desc *p)
+{
+	return le32_to_cpu(p->flags) & TXDESC_LAST_SEG;
+}
+
+static inline u32 desc_get_buf_addr(struct xgmac_dma_desc *p)
+{
+	return le32_to_cpu(p->buf1_addr);
+}
+
+static inline void desc_set_buf_addr(struct xgmac_dma_desc *p,
+				     u32 paddr, int len)
+{
+	p->buf1_addr = cpu_to_le32(paddr);
+	if (len > MAX_DESC_BUF_SZ)
+		p->buf2_addr = cpu_to_le32(paddr + MAX_DESC_BUF_SZ);
+}
+
+static inline void desc_set_buf_addr_and_size(struct xgmac_dma_desc *p,
+					      u32 paddr, int len)
+{
+	desc_set_buf_len(p, len);
+	desc_set_buf_addr(p, paddr, len);
+}
+
+static inline int desc_get_rx_frame_len(struct xgmac_dma_desc *p)
+{
+	u32 data = le32_to_cpu(p->flags);
+	u32 len = (data & RXDESC_FRAME_LEN_MASK) >> RXDESC_FRAME_LEN_OFFSET;
+	if (data & RXDESC_FRAME_TYPE)
+		len -= ETH_FCS_LEN;
+
+	return len;
+}
+
+static void xgmac_dma_flush_tx_fifo(void __iomem *ioaddr)
+{
+	int timeout = 1000;
+	u32 reg = readl(ioaddr + XGMAC_OMR);
+	writel(reg | XGMAC_OMR_FTF, ioaddr + XGMAC_OMR);
+
+	while ((timeout-- > 0) && readl(ioaddr + XGMAC_OMR) & XGMAC_OMR_FTF)
+		udelay(1);
+}
+
+static int desc_get_tx_status(struct xgmac_priv *priv, struct xgmac_dma_desc *p)
+{
+	struct xgmac_extra_stats *x = &priv->xstats;
+	u32 status = le32_to_cpu(p->flags);
+
+	if (!(status & TXDESC_ERROR_SUMMARY))
+		return 0;
+
+	netdev_dbg(priv->dev, "tx desc error = 0x%08x\n", status);
+	if (status & TXDESC_JABBER_TIMEOUT)
+		x->tx_jabber++;
+	if (status & TXDESC_FRAME_FLUSHED)
+		x->tx_frame_flushed++;
+	if (status & TXDESC_UNDERFLOW_ERR)
+		xgmac_dma_flush_tx_fifo(priv->base);
+	if (status & TXDESC_IP_HEADER_ERR)
+		x->tx_ip_header_error++;
+	if (status & TXDESC_LOCAL_FAULT)
+		x->tx_local_fault++;
+	if (status & TXDESC_REMOTE_FAULT)
+		x->tx_remote_fault++;
+	if (status & TXDESC_PAYLOAD_CSUM_ERR)
+		x->tx_payload_error++;
+
+	return -1;
+}
+
+static int desc_get_rx_status(struct xgmac_priv *priv, struct xgmac_dma_desc *p)
+{
+	struct xgmac_extra_stats *x = &priv->xstats;
+	int ret = CHECKSUM_UNNECESSARY;
+	u32 status = le32_to_cpu(p->flags);
+	u32 ext_status = le32_to_cpu(p->ext_status);
+
+	if (status & RXDESC_DA_FILTER_FAIL) {
+		netdev_dbg(priv->dev, "XGMAC RX : Dest Address filter fail\n");
+		x->rx_da_filter_fail++;
+		return -1;
+	}
+
+	/* Check if packet has checksum already */
+	if ((status & RXDESC_FRAME_TYPE) && (status & RXDESC_EXT_STATUS) &&
+		!(ext_status & RXDESC_IP_PAYLOAD_MASK))
+		ret = CHECKSUM_NONE;
+
+	netdev_dbg(priv->dev, "rx status - frame type=%d, csum = %d, ext stat %08x\n",
+		   (status & RXDESC_FRAME_TYPE) ? 1 : 0, ret, ext_status);
+
+	if (!(status & RXDESC_ERROR_SUMMARY))
+		return ret;
+
+	/* Handle any errors */
+	if (status & (RXDESC_DESCRIPTOR_ERR | RXDESC_OVERFLOW_ERR |
+		RXDESC_GIANT_FRAME | RXDESC_LENGTH_ERR | RXDESC_CRC_ERR))
+		return -1;
+
+	if (status & RXDESC_EXT_STATUS) {
+		if (ext_status & RXDESC_IP_HEADER_ERR)
+			x->rx_ip_header_error++;
+		if (ext_status & RXDESC_IP_PAYLOAD_ERR)
+			x->rx_payload_error++;
+		netdev_dbg(priv->dev, "IP checksum error - stat %08x\n",
+			   ext_status);
+		return CHECKSUM_NONE;
+	}
+
+	return ret;
+}
+
+static inline void xgmac_mac_enable(void __iomem *ioaddr)
+{
+	u32 value = readl(ioaddr + XGMAC_CONTROL);
+	value |= MAC_ENABLE_RX | MAC_ENABLE_TX;
+	writel(value, ioaddr + XGMAC_CONTROL);
+
+	value = readl(ioaddr + XGMAC_DMA_CONTROL);
+	value |= DMA_CONTROL_ST | DMA_CONTROL_SR;
+	writel(value, ioaddr + XGMAC_DMA_CONTROL);
+}
+
+static inline void xgmac_mac_disable(void __iomem *ioaddr)
+{
+	u32 value = readl(ioaddr + XGMAC_DMA_CONTROL);
+	value &= ~(DMA_CONTROL_ST | DMA_CONTROL_SR);
+	writel(value, ioaddr + XGMAC_DMA_CONTROL);
+
+	value = readl(ioaddr + XGMAC_CONTROL);
+	value &= ~(MAC_ENABLE_TX | MAC_ENABLE_RX);
+	writel(value, ioaddr + XGMAC_CONTROL);
+}
+
+static void xgmac_set_mac_addr(void __iomem *ioaddr, unsigned char *addr,
+			       int num)
+{
+	u32 data;
+
+	data = (addr[5] << 8) | addr[4] | (num ? XGMAC_ADDR_AE : 0);
+	writel(data, ioaddr + XGMAC_ADDR_HIGH(num));
+	data = (addr[3] << 24) | (addr[2] << 16) | (addr[1] << 8) | addr[0];
+	writel(data, ioaddr + XGMAC_ADDR_LOW(num));
+}
+
+static void xgmac_get_mac_addr(void __iomem *ioaddr, unsigned char *addr,
+			       int num)
+{
+	u32 hi_addr, lo_addr;
+
+	/* Read the MAC address from the hardware */
+	hi_addr = readl(ioaddr + XGMAC_ADDR_HIGH(num));
+	lo_addr = readl(ioaddr + XGMAC_ADDR_LOW(num));
+
+	/* Extract the MAC address from the high and low words */
+	addr[0] = lo_addr & 0xff;
+	addr[1] = (lo_addr >> 8) & 0xff;
+	addr[2] = (lo_addr >> 16) & 0xff;
+	addr[3] = (lo_addr >> 24) & 0xff;
+	addr[4] = hi_addr & 0xff;
+	addr[5] = (hi_addr >> 8) & 0xff;
+}
+
+static int xgmac_set_flow_ctrl(struct xgmac_priv *priv, int rx, int tx)
+{
+	u32 reg;
+	unsigned int flow = 0;
+
+	priv->rx_pause = rx;
+	priv->tx_pause = tx;
+
+	if (rx || tx) {
+		if (rx)
+			flow |= XGMAC_FLOW_CTRL_RFE;
+		if (tx)
+			flow |= XGMAC_FLOW_CTRL_TFE;
+
+		flow |= XGMAC_FLOW_CTRL_PLT | XGMAC_FLOW_CTRL_UP;
+		flow |= (PAUSE_TIME << XGMAC_FLOW_CTRL_PT_SHIFT);
+
+		writel(flow, priv->base + XGMAC_FLOW_CTRL);
+
+		reg = readl(priv->base + XGMAC_OMR);
+		reg |= XGMAC_OMR_EFC;
+		writel(reg, priv->base + XGMAC_OMR);
+	} else {
+		writel(0, priv->base + XGMAC_FLOW_CTRL);
+
+		reg = readl(priv->base + XGMAC_OMR);
+		reg &= ~XGMAC_OMR_EFC;
+		writel(reg, priv->base + XGMAC_OMR);
+	}
+
+	return 0;
+}
+
+static void xgmac_rx_refill(struct xgmac_priv *priv)
+{
+	struct xgmac_dma_desc *p;
+	dma_addr_t paddr;
+
+	while (dma_ring_space(priv->rx_head, priv->rx_tail, DMA_RX_RING_SZ) > 1) {
+		int entry = priv->rx_head;
+		struct sk_buff *skb;
+
+		p = priv->dma_rx + entry;
+
+		if (priv->rx_skbuff[entry] != NULL)
+			continue;
+
+		skb = __skb_dequeue(&priv->rx_recycle);
+		if (skb == NULL)
+			skb = netdev_alloc_skb(priv->dev, priv->dma_buf_sz);
+		if (unlikely(skb == NULL))
+			break;
+
+		priv->rx_skbuff[entry] = skb;
+		paddr = dma_map_single(priv->device, skb->data,
+					 priv->dma_buf_sz, DMA_FROM_DEVICE);
+		desc_set_buf_addr(p, paddr, priv->dma_buf_sz);
+
+		netdev_dbg(priv->dev, "rx ring: head %d, tail %d\n",
+			priv->rx_head, priv->rx_tail);
+
+		priv->rx_head = dma_ring_incr(priv->rx_head, DMA_RX_RING_SZ);
+		/* Ensure descriptor is in memory before handing to h/w */
+		wmb();
+		desc_set_rx_owner(p);
+	}
+}
+
+/**
+ * init_xgmac_dma_desc_rings - init the RX/TX descriptor rings
+ * @dev: net device structure
+ * Description:  this function initializes the DMA RX/TX descriptors
+ * and allocates the socket buffers.
+ */
+static int xgmac_dma_desc_rings_init(struct net_device *dev)
+{
+	struct xgmac_priv *priv = netdev_priv(dev);
+	unsigned int bfsize;
+
+	/* Set the Buffer size according to the MTU;
+	 * indeed, in case of jumbo we need to bump-up the buffer sizes.
+	 */
+	bfsize = ALIGN(dev->mtu + ETH_HLEN + ETH_FCS_LEN + NET_IP_ALIGN + 64,
+		       64);
+
+	netdev_dbg(priv->dev, "mtu [%d] bfsize [%d]\n", dev->mtu, bfsize);
+
+	priv->rx_skbuff = kzalloc(sizeof(struct sk_buff *) * DMA_RX_RING_SZ,
+				  GFP_KERNEL);
+	if (!priv->rx_skbuff)
+		return -ENOMEM;
+
+	priv->dma_rx = dma_alloc_coherent(priv->device,
+					  DMA_RX_RING_SZ *
+					  sizeof(struct xgmac_dma_desc),
+					  &priv->dma_rx_phy,
+					  GFP_KERNEL);
+	if (!priv->dma_rx)
+		goto err_dma_rx;
+
+	priv->tx_skbuff = kzalloc(sizeof(struct sk_buff *) * DMA_TX_RING_SZ,
+				  GFP_KERNEL);
+	if (!priv->tx_skbuff)
+		goto err_tx_skb;
+
+	priv->dma_tx = dma_alloc_coherent(priv->device,
+					  DMA_TX_RING_SZ *
+					  sizeof(struct xgmac_dma_desc),
+					  &priv->dma_tx_phy,
+					  GFP_KERNEL);
+	if (!priv->dma_tx)
+		goto err_dma_tx;
+
+	netdev_dbg(priv->dev, "DMA desc rings: virt addr (Rx %p, "
+	    "Tx %p)\n\tDMA phy addr (Rx 0x%08x, Tx 0x%08x)\n",
+	    priv->dma_rx, priv->dma_tx,
+	    (unsigned int)priv->dma_rx_phy, (unsigned int)priv->dma_tx_phy);
+
+	priv->rx_tail = 0;
+	priv->rx_head = 0;
+	priv->dma_buf_sz = bfsize;
+	desc_init_rx_desc(priv->dma_rx, DMA_RX_RING_SZ, priv->dma_buf_sz);
+	xgmac_rx_refill(priv);
+
+	priv->tx_tail = 0;
+	priv->tx_head = 0;
+	desc_init_tx_desc(priv->dma_tx, DMA_TX_RING_SZ);
+
+	writel(priv->dma_tx_phy, priv->base + XGMAC_DMA_TX_BASE_ADDR);
+	writel(priv->dma_rx_phy, priv->base + XGMAC_DMA_RX_BASE_ADDR);
+
+	return 0;
+
+err_dma_tx:
+	kfree(priv->tx_skbuff);
+err_tx_skb:
+	dma_free_coherent(priv->device,
+			  DMA_RX_RING_SZ * sizeof(struct xgmac_dma_desc),
+			  priv->dma_rx, priv->dma_rx_phy);
+err_dma_rx:
+	kfree(priv->rx_skbuff);
+	return -ENOMEM;
+}
+
+static void xgmac_free_rx_skbufs(struct xgmac_priv *priv)
+{
+	int i;
+	struct xgmac_dma_desc *p;
+
+	if (!priv->rx_skbuff)
+		return;
+
+	for (i = 0; i < DMA_RX_RING_SZ; i++) {
+		if (priv->rx_skbuff[i] == NULL)
+			continue;
+
+		p = priv->dma_rx + i;
+		dma_unmap_single(priv->device, desc_get_buf_addr(p),
+				 priv->dma_buf_sz, DMA_FROM_DEVICE);
+		dev_kfree_skb_any(priv->rx_skbuff[i]);
+		priv->rx_skbuff[i] = NULL;
+	}
+}
+
+static void xgmac_free_tx_skbufs(struct xgmac_priv *priv)
+{
+	int i, f;
+	struct xgmac_dma_desc *p;
+
+	if (!priv->tx_skbuff)
+		return;
+
+	for (i = 0; i < DMA_TX_RING_SZ; i++) {
+		if (priv->tx_skbuff[i] == NULL)
+			continue;
+
+		p = priv->dma_tx + i;
+		dma_unmap_single(priv->device, desc_get_buf_addr(p),
+				 desc_get_buf_len(p), DMA_TO_DEVICE);
+
+		for (f = 0; f < skb_shinfo(priv->tx_skbuff[i])->nr_frags; f++) {
+			p = priv->dma_tx + i++;
+			dma_unmap_page(priv->device, desc_get_buf_addr(p),
+				       desc_get_buf_len(p), DMA_TO_DEVICE);
+		}
+
+		dev_kfree_skb_any(priv->tx_skbuff[i]);
+		priv->tx_skbuff[i] = NULL;
+	}
+}
+
+static void xgmac_free_dma_desc_rings(struct xgmac_priv *priv)
+{
+	/* Release the DMA TX/RX socket buffers */
+	xgmac_free_rx_skbufs(priv);
+	xgmac_free_tx_skbufs(priv);
+
+	/* Free the consistent memory allocated for descriptor rings */
+	if (priv->dma_tx) {
+		dma_free_coherent(priv->device,
+				  DMA_TX_RING_SZ * sizeof(struct xgmac_dma_desc),
+				  priv->dma_tx, priv->dma_tx_phy);
+		priv->dma_tx = NULL;
+	}
+	if (priv->dma_rx) {
+		dma_free_coherent(priv->device,
+				  DMA_RX_RING_SZ * sizeof(struct xgmac_dma_desc),
+				  priv->dma_rx, priv->dma_rx_phy);
+		priv->dma_rx = NULL;
+	}
+	kfree(priv->rx_skbuff);
+	priv->rx_skbuff = NULL;
+	kfree(priv->tx_skbuff);
+	priv->tx_skbuff = NULL;
+}
+
+/**
+ * xgmac_tx:
+ * @priv: private driver structure
+ * Description: it reclaims resources after transmission completes.
+ */
+static void xgmac_tx_complete(struct xgmac_priv *priv)
+{
+	int i;
+	void __iomem *ioaddr = priv->base;
+
+	writel(DMA_STATUS_TU | DMA_STATUS_NIS, ioaddr + XGMAC_DMA_STATUS);
+
+	while (dma_ring_cnt(priv->tx_head, priv->tx_tail, DMA_TX_RING_SZ)) {
+		unsigned int entry = priv->tx_tail;
+		struct sk_buff *skb = priv->tx_skbuff[entry];
+		struct xgmac_dma_desc *p = priv->dma_tx + entry;
+
+		/* Check if the descriptor is owned by the DMA. */
+		if (desc_get_owner(p))
+			break;
+
+		/* Verify tx error by looking at the last segment */
+		if (desc_get_tx_ls(p))
+			desc_get_tx_status(priv, p);
+
+		netdev_dbg(priv->dev, "tx ring: curr %d, dirty %d\n",
+			priv->tx_head, priv->tx_tail);
+
+		dma_unmap_single(priv->device, desc_get_buf_addr(p),
+				 desc_get_buf_len(p), DMA_TO_DEVICE);
+
+		priv->tx_skbuff[entry] = NULL;
+		priv->tx_tail = dma_ring_incr(entry, DMA_TX_RING_SZ);
+
+		if (!skb) {
+			continue;
+		}
+
+		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+			entry = priv->tx_tail = dma_ring_incr(priv->tx_tail,
+							      DMA_TX_RING_SZ);
+			p = priv->dma_tx + priv->tx_tail;
+
+			dma_unmap_page(priv->device, desc_get_buf_addr(p),
+				       desc_get_buf_len(p), DMA_TO_DEVICE);
+		}
+
+		/*
+		 * If there's room in the queue (limit it to size)
+		 * we add this skb back into the pool,
+		 * if it's the right size.
+		 */
+		if ((skb_queue_len(&priv->rx_recycle) <
+			DMA_RX_RING_SZ) &&
+			skb_recycle_check(skb, priv->dma_buf_sz))
+			__skb_queue_head(&priv->rx_recycle, skb);
+		else
+			dev_kfree_skb(skb);
+	}
+
+	if (dma_ring_space(priv->tx_head, priv->tx_tail, DMA_TX_RING_SZ) >
+	    TX_THRESH)
+		netif_wake_queue(priv->dev);
+}
+
+/**
+ * xgmac_tx_err:
+ * @priv: pointer to the private device structure
+ * Description: it cleans the descriptors and restarts the transmission
+ * in case of errors.
+ */
+static void xgmac_tx_err(struct xgmac_priv *priv)
+{
+	u32 reg, value, inten;
+
+	netif_stop_queue(priv->dev);
+
+	inten = readl(priv->base + XGMAC_DMA_INTR_ENA);
+	writel(0, priv->base + XGMAC_DMA_INTR_ENA);
+
+	reg = readl(priv->base + XGMAC_DMA_CONTROL);
+	writel(reg & ~DMA_CONTROL_ST, priv->base + XGMAC_DMA_CONTROL);
+	do {
+		value = readl(priv->base + XGMAC_DMA_STATUS) & 0x700000;
+	} while (value && (value != 0x600000));
+
+	xgmac_free_tx_skbufs(priv);
+	desc_init_tx_desc(priv->dma_tx, DMA_TX_RING_SZ);
+	priv->tx_tail = 0;
+	priv->tx_head = 0;
+	writel(reg | DMA_CONTROL_ST, priv->base + XGMAC_DMA_CONTROL);
+
+	writel(DMA_STATUS_TU | DMA_STATUS_TPS | DMA_STATUS_NIS | DMA_STATUS_AIS,
+		priv->base + XGMAC_DMA_STATUS);
+	writel(inten, priv->base + XGMAC_DMA_INTR_ENA);
+
+	netif_wake_queue(priv->dev);
+}
+
+static int xgmac_hw_init(struct net_device *dev)
+{
+	u32 value, ctrl;
+	int limit;
+	struct xgmac_priv *priv = netdev_priv(dev);
+	void __iomem *ioaddr = priv->base;
+
+	/* Save the ctrl register value */
+	ctrl = readl(ioaddr + XGMAC_CONTROL) & XGMAC_CONTROL_SPD_MASK;
+
+	/* SW reset */
+	value = DMA_BUS_MODE_SFT_RESET;
+	writel(value, ioaddr + XGMAC_DMA_BUS_MODE);
+	limit = 15000;
+	while (limit-- &&
+		(readl(ioaddr + XGMAC_DMA_BUS_MODE) & DMA_BUS_MODE_SFT_RESET))
+		cpu_relax();
+	if (limit < 0)
+		return -EBUSY;
+
+	value = (0x10 << DMA_BUS_MODE_PBL_SHIFT) |
+		(0x10 << DMA_BUS_MODE_RPBL_SHIFT) |
+		DMA_BUS_MODE_FB | DMA_BUS_MODE_ATDS | DMA_BUS_MODE_AAL;
+	writel(value, ioaddr + XGMAC_DMA_BUS_MODE);
+
+	/* Enable interrupts */
+	writel(DMA_INTR_DEFAULT_MASK, ioaddr + XGMAC_DMA_STATUS);
+	writel(DMA_INTR_DEFAULT_MASK, ioaddr + XGMAC_DMA_INTR_ENA);
+
+	/* XGMAC requires AXI bus init. This is a 'magic number' for now */
+	writel(0x000100E, ioaddr + XGMAC_DMA_AXI_BUS);
+
+	ctrl |= XGMAC_CONTROL_DDIC | XGMAC_CONTROL_JE | XGMAC_CONTROL_ACS |
+		XGMAC_CONTROL_CAR;
+	if (dev->features & NETIF_F_RXCSUM)
+		ctrl |= XGMAC_CONTROL_IPC;
+	writel(ctrl, ioaddr + XGMAC_CONTROL);
+
+	value = DMA_CONTROL_DFF;
+	writel(value, ioaddr + XGMAC_DMA_CONTROL);
+
+	/* Set the HW DMA mode and the COE */
+	writel(XGMAC_OMR_TSF | XGMAC_OMR_RSF | XGMAC_OMR_RFD | XGMAC_OMR_RFA,
+		ioaddr + XGMAC_OMR);
+
+	/* Reset the MMC counters */
+	writel(1, ioaddr + XGMAC_MMC_CTRL);
+	return 0;
+}
+
+/**
+ *  xgmac_open - open entry point of the driver
+ *  @dev : pointer to the device structure.
+ *  Description:
+ *  This function is the open entry point of the driver.
+ *  Return value:
+ *  0 on success and an appropriate (-)ve integer as defined in errno.h
+ *  file on failure.
+ */
+static int xgmac_open(struct net_device *dev)
+{
+	int ret;
+	struct xgmac_priv *priv = netdev_priv(dev);
+	void __iomem *ioaddr = priv->base;
+
+	/* Check that the MAC address is valid.  If its not, refuse
+	 * to bring the device up. The user must specify an
+	 * address using the following linux command:
+	 *      ifconfig eth0 hw ether xx:xx:xx:xx:xx:xx  */
+	if (!is_valid_ether_addr(dev->dev_addr)) {
+		random_ether_addr(dev->dev_addr);
+		netdev_dbg(priv->dev, "generated random MAC address %pM\n",
+			dev->dev_addr);
+	}
+
+	skb_queue_head_init(&priv->rx_recycle);
+	memset(&priv->xstats, 0, sizeof(struct xgmac_extra_stats));
+
+	/* Initialize the XGMAC and descriptors */
+	xgmac_hw_init(dev);
+	xgmac_set_mac_addr(ioaddr, dev->dev_addr, 0);
+	xgmac_set_flow_ctrl(priv, priv->rx_pause, priv->tx_pause);
+
+	ret = xgmac_dma_desc_rings_init(dev);
+	if (ret < 0)
+		return ret;
+
+	/* Enable the MAC Rx/Tx */
+	xgmac_mac_enable(ioaddr);
+
+	napi_enable(&priv->napi);
+	netif_start_queue(dev);
+
+	return 0;
+}
+
+/**
+ *  xgmac_release - close entry point of the driver
+ *  @dev : device pointer.
+ *  Description:
+ *  This is the stop entry point of the driver.
+ */
+static int xgmac_stop(struct net_device *dev)
+{
+	struct xgmac_priv *priv = netdev_priv(dev);
+
+	netif_stop_queue(dev);
+
+	if (readl(priv->base + XGMAC_DMA_INTR_ENA))
+		napi_disable(&priv->napi);
+
+	writel(0, priv->base + XGMAC_DMA_INTR_ENA);
+	skb_queue_purge(&priv->rx_recycle);
+
+	/* Disable the MAC core */
+	xgmac_mac_disable(priv->base);
+
+	/* Release and free the Rx/Tx resources */
+	xgmac_free_dma_desc_rings(priv);
+
+	return 0;
+}
+
+/**
+ *  xgmac_xmit:
+ *  @skb : the socket buffer
+ *  @dev : device pointer
+ *  Description : Tx entry point of the driver.
+ */
+static netdev_tx_t xgmac_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct xgmac_priv *priv = netdev_priv(dev);
+	unsigned int entry;
+	int i;
+	int nfrags = skb_shinfo(skb)->nr_frags;
+	struct xgmac_dma_desc *desc, *first;
+	unsigned int desc_flags;
+	unsigned int len;
+	dma_addr_t paddr;
+
+	if (dma_ring_space(priv->tx_head, priv->tx_tail, DMA_TX_RING_SZ) <
+	    (nfrags + 1)) {
+		writel(DMA_INTR_DEFAULT_MASK | DMA_INTR_ENA_TIE,
+			priv->base + XGMAC_DMA_INTR_ENA);
+		netif_stop_queue(dev);
+		return NETDEV_TX_BUSY;
+	}
+
+	desc_flags = (skb->ip_summed == CHECKSUM_PARTIAL) ?
+		TXDESC_CSUM_ALL : 0;
+	entry = priv->tx_head;
+	desc = priv->dma_tx + entry;
+	first = desc;
+
+	len = skb_headlen(skb);
+	paddr = dma_map_single(priv->device, skb->data, len, DMA_TO_DEVICE);
+	if (dma_mapping_error(priv->device, paddr)) {
+		dev_kfree_skb(skb);
+		return -EIO;
+	}
+	priv->tx_skbuff[entry] = skb;
+	desc_set_buf_addr_and_size(desc, paddr, len);
+
+	for (i = 0; i < nfrags; i++) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+		len = frag->size;
+
+		paddr = skb_frag_dma_map(priv->device, frag, 0, len,
+					 DMA_TO_DEVICE);
+		if (dma_mapping_error(priv->device, paddr)) {
+			dev_kfree_skb(skb);
+			return -EIO;
+		}
+
+		entry = dma_ring_incr(entry, DMA_TX_RING_SZ);
+		desc = priv->dma_tx + entry;
+		priv->tx_skbuff[entry] = NULL;
+
+		desc_set_buf_addr_and_size(desc, paddr, len);
+		if (i < (nfrags - 1))
+			desc_set_tx_owner(desc, desc_flags);
+	}
+
+	/* Interrupt on completition only for the latest segment */
+	if (desc != first)
+		desc_set_tx_owner(desc, desc_flags |
+			TXDESC_LAST_SEG | TXDESC_INTERRUPT);
+	else
+		desc_flags |= TXDESC_LAST_SEG | TXDESC_INTERRUPT;
+
+	/* Set owner on first desc last to avoid race condition */
+	wmb();
+	desc_set_tx_owner(first, desc_flags | TXDESC_FIRST_SEG);
+
+	priv->tx_head = dma_ring_incr(entry, DMA_TX_RING_SZ);
+
+	writel(1, priv->base + XGMAC_DMA_TX_POLL);
+
+	return NETDEV_TX_OK;
+}
+
+static int xgmac_rx(struct xgmac_priv *priv, int limit)
+{
+	unsigned int entry;
+	unsigned int count = 0;
+	struct xgmac_dma_desc *p;
+
+	while (count < limit) {
+		int ip_checksum;
+		struct sk_buff *skb;
+		int frame_len;
+
+		writel(DMA_STATUS_RI | DMA_STATUS_NIS,
+		       priv->base + XGMAC_DMA_STATUS);
+
+		entry = priv->rx_tail;
+		p = priv->dma_rx + entry;
+		if (desc_get_owner(p))
+			break;
+
+		count++;
+		priv->rx_tail = dma_ring_incr(priv->rx_tail, DMA_RX_RING_SZ);
+
+		/* read the status of the incoming frame */
+		ip_checksum = desc_get_rx_status(priv, p);
+		if (ip_checksum < 0)
+			continue;
+
+		skb = priv->rx_skbuff[entry];
+		if (unlikely(!skb)) {
+			netdev_err(priv->dev, "Inconsistent Rx descriptor chain\n");
+			break;
+		}
+		priv->rx_skbuff[entry] = NULL;
+
+		frame_len = desc_get_rx_frame_len(p);
+		netdev_dbg(priv->dev, "RX frame size %d, COE status: %d\n",
+			frame_len, ip_checksum);
+
+		skb_put(skb, frame_len);
+		dma_unmap_single(priv->device, desc_get_buf_addr(p),
+				 frame_len, DMA_FROM_DEVICE);
+
+		skb->protocol = eth_type_trans(skb, priv->dev);
+		skb->ip_summed = ip_checksum;
+		if (ip_checksum == CHECKSUM_NONE)
+			netif_receive_skb(skb);
+		else
+			napi_gro_receive(&priv->napi, skb);
+	}
+
+	xgmac_rx_refill(priv);
+
+	writel(1, priv->base + XGMAC_DMA_RX_POLL);
+
+	return count;
+}
+
+/**
+ *  xgmac_poll - xgmac poll method (NAPI)
+ *  @napi : pointer to the napi structure.
+ *  @budget : maximum number of packets that the current CPU can receive from
+ *	      all interfaces.
+ *  Description :
+ *   This function implements the the reception process.
+ *   Also it runs the TX completion thread
+ */
+static int xgmac_poll(struct napi_struct *napi, int budget)
+{
+	struct xgmac_priv *priv = container_of(napi,
+				       struct xgmac_priv, napi);
+	int work_done = 0;
+
+	xgmac_tx_complete(priv);
+	work_done = xgmac_rx(priv, budget);
+
+	if (work_done < budget) {
+		napi_complete(napi);
+		writel(DMA_INTR_DEFAULT_MASK, priv->base + XGMAC_DMA_INTR_ENA);
+	}
+	return work_done;
+}
+
+/**
+ *  xgmac_tx_timeout
+ *  @dev : Pointer to net device structure
+ *  Description: this function is called when a packet transmission fails to
+ *   complete within a reasonable tmrate. The driver will mark the error in the
+ *   netdev structure and arrange for the device to be reset to a sane state
+ *   in order to transmit a new packet.
+ */
+static void xgmac_tx_timeout(struct net_device *dev)
+{
+	struct xgmac_priv *priv = netdev_priv(dev);
+
+	/* Clear Tx resources and restart transmitting again */
+	xgmac_tx_err(priv);
+}
+
+/**
+ *  xgmac_set_rx_mode - entry point for multicast addressing
+ *  @dev : pointer to the device structure
+ *  Description:
+ *  This function is a driver entry point which gets called by the kernel
+ *  whenever multicast addresses must be enabled/disabled.
+ *  Return value:
+ *  void.
+ */
+static void xgmac_set_rx_mode(struct net_device *dev)
+{
+	int i;
+	struct xgmac_priv *priv = netdev_priv(dev);
+	void __iomem *ioaddr = priv->base;
+	unsigned int value = 0;
+	u32 hash_filter[XGMAC_NUM_HASH];
+	int reg = 1;
+	struct netdev_hw_addr *ha;
+	bool use_hash = false;
+
+	netdev_dbg(priv->dev, "# mcasts %d, # unicast %d\n",
+		 netdev_mc_count(dev), netdev_uc_count(dev));
+
+	if (dev->flags & IFF_PROMISC) {
+		writel(XGMAC_FRAME_FILTER_PR, ioaddr + XGMAC_FRAME_FILTER);
+		return;
+	}
+
+	memset(hash_filter, 0, sizeof(hash_filter));
+
+	if (netdev_uc_count(dev) > XGMAC_MAX_FILTER_ADDR) {
+		use_hash = true;
+		value |= XGMAC_FRAME_FILTER_HUC | XGMAC_FRAME_FILTER_HPF;
+	}
+	netdev_for_each_uc_addr(ha, dev) {
+		if (use_hash) {
+			u32 bit_nr = ~ether_crc(ETH_ALEN, ha->addr) >> 23;
+
+			/* The most significant 4 bits determine the register to
+			 * use (H/L) while the other 5 bits determine the bit
+			 * within the register. */
+			hash_filter[bit_nr >> 5] |= 1 << (bit_nr & 31);
+		} else {
+			xgmac_set_mac_addr(ioaddr, ha->addr, reg);
+			reg++;
+		}
+	}
+
+	if (dev->flags & IFF_ALLMULTI) {
+		value |= XGMAC_FRAME_FILTER_PM;
+		goto out;
+	}
+
+	if ((netdev_mc_count(dev) + reg - 1) > XGMAC_MAX_FILTER_ADDR) {
+		use_hash = true;
+		value |= XGMAC_FRAME_FILTER_HMC | XGMAC_FRAME_FILTER_HPF;
+	}
+	netdev_for_each_mc_addr(ha, dev) {
+		if (use_hash) {
+			u32 bit_nr = ~ether_crc(ETH_ALEN, ha->addr) >> 23;
+
+			/* The most significant 4 bits determine the register to
+			 * use (H/L) while the other 5 bits determine the bit
+			 * within the register. */
+			hash_filter[bit_nr >> 5] |= 1 << (bit_nr & 31);
+		} else {
+			xgmac_set_mac_addr(ioaddr, ha->addr, reg);
+			reg++;
+		}
+	}
+
+out:
+	for (i = 0; i < XGMAC_NUM_HASH; i++)
+		writel(hash_filter[i], ioaddr + XGMAC_HASH(i));
+
+	writel(value, ioaddr + XGMAC_FRAME_FILTER);
+}
+
+/**
+ *  xgmac_change_mtu - entry point to change MTU size for the device.
+ *  @dev : device pointer.
+ *  @new_mtu : the new MTU size for the device.
+ *  Description: the Maximum Transfer Unit (MTU) is used by the network layer
+ *  to drive packet transmission. Ethernet has an MTU of 1500 octets
+ *  (ETH_DATA_LEN). This value can be changed with ifconfig.
+ *  Return value:
+ *  0 on success and an appropriate (-)ve integer as defined in errno.h
+ *  file on failure.
+ */
+static int xgmac_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct xgmac_priv *priv = netdev_priv(dev);
+	int old_mtu;
+
+	if ((new_mtu < 46) || (new_mtu > MAX_MTU)) {
+		netdev_err(priv->dev, "invalid MTU, max MTU is: %d\n", MAX_MTU);
+		return -EINVAL;
+	}
+
+	old_mtu = dev->mtu;
+	dev->mtu = new_mtu;
+
+	/* return early if the buffer sizes will not change */
+	if (old_mtu <= ETH_DATA_LEN && new_mtu <= ETH_DATA_LEN)
+		return 0;
+	if (old_mtu == new_mtu)
+		return 0;
+
+	/* Stop everything, get ready to change the MTU */
+	if (!netif_running(dev))
+		return 0;
+
+	/* Bring the interface down and then back up */
+	xgmac_stop(dev);
+	return xgmac_open(dev);
+}
+
+static irqreturn_t xgmac_pmt_interrupt(int irq, void *dev_id)
+{
+	u32 intr_status;
+	struct net_device *dev = (struct net_device *)dev_id;
+	struct xgmac_priv *priv = netdev_priv(dev);
+	void __iomem *ioaddr = priv->base;
+
+	intr_status = readl(ioaddr + XGMAC_INT_STAT);
+	if (intr_status & XGMAC_INT_STAT_PMT) {
+		netdev_dbg(priv->dev, "received Magic frame\n");
+		/* clear the PMT bits 5 and 6 by reading the PMT */
+		readl(ioaddr + XGMAC_PMT);
+	}
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t xgmac_interrupt(int irq, void *dev_id)
+{
+	u32 intr_status;
+	bool tx_err = false;
+	struct net_device *dev = (struct net_device *)dev_id;
+	struct xgmac_priv *priv = netdev_priv(dev);
+	struct xgmac_extra_stats *x = &priv->xstats;
+
+	/* read the status register (CSR5) */
+	intr_status = readl(priv->base + XGMAC_DMA_STATUS);
+	intr_status &= readl(priv->base + XGMAC_DMA_INTR_ENA);
+	writel(intr_status, priv->base + XGMAC_DMA_STATUS);
+
+	/* It displays the DMA process states (CSR5 register) */
+	/* ABNORMAL interrupts */
+	if (unlikely(intr_status & DMA_STATUS_AIS)) {
+		if (intr_status & DMA_STATUS_TJT) {
+			netdev_err(priv->dev, "transmit jabber\n");
+			x->tx_jabber++;
+		}
+		if (intr_status & DMA_STATUS_RU)
+			x->rx_buf_unav++;
+		if (intr_status & DMA_STATUS_RPS) {
+			netdev_err(priv->dev, "receive process stopped\n");
+			x->rx_process_stopped++;
+		}
+		if (intr_status & DMA_STATUS_ETI) {
+			netdev_err(priv->dev, "transmit early interrupt\n");
+			x->tx_early++;
+		}
+		if (intr_status & DMA_STATUS_TPS) {
+			netdev_err(priv->dev, "transmit process stopped\n");
+			x->tx_process_stopped++;
+			tx_err = true;
+		}
+		if (intr_status & DMA_STATUS_FBI) {
+			netdev_err(priv->dev, "fatal bus error\n");
+			x->fatal_bus_error++;
+			tx_err = true;
+		}
+
+		if (tx_err)
+			xgmac_tx_err(priv);
+	}
+
+	/* TX/RX NORMAL interrupts */
+	if (intr_status & (DMA_STATUS_RI | DMA_STATUS_TU)) {
+		writel(DMA_INTR_ABNORMAL, priv->base + XGMAC_DMA_INTR_ENA);
+		napi_schedule(&priv->napi);
+	}
+
+	return IRQ_HANDLED;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+/* Polling receive - used by NETCONSOLE and other diagnostic tools
+ * to allow network I/O with interrupts disabled. */
+static void xgmac_poll_controller(struct net_device *dev)
+{
+	disable_irq(dev->irq);
+	xgmac_interrupt(dev->irq, dev);
+	enable_irq(dev->irq);
+}
+#endif
+
+struct rtnl_link_stats64 *
+xgmac_get_stats64(struct net_device *dev,
+		       struct rtnl_link_stats64 *storage)
+{
+	struct xgmac_priv *priv = netdev_priv(dev);
+	void __iomem *base = priv->base;
+	u32 count;
+
+	spin_lock_bh(&priv->stats_lock);
+	writel(XGMAC_MMC_CTRL_CNT_FRZ, base + XGMAC_MMC_CTRL);
+
+	storage->rx_bytes = readl(base + XGMAC_MMC_RXOCTET_G_LO);
+	storage->rx_bytes |= (u64)(readl(base + XGMAC_MMC_RXOCTET_G_HI)) << 32;
+
+	storage->rx_packets = readl(base + XGMAC_MMC_RXFRAME_GB_LO);
+	storage->multicast = readl(base + XGMAC_MMC_RXMCFRAME_G);
+	storage->rx_crc_errors = readl(base + XGMAC_MMC_RXCRCERR);
+	storage->rx_length_errors = readl(base + XGMAC_MMC_RXLENGTHERR);
+	storage->rx_missed_errors = readl(base + XGMAC_MMC_RXOVERFLOW);
+
+	storage->tx_bytes = readl(base + XGMAC_MMC_TXOCTET_G_LO);
+	storage->tx_bytes |= (u64)(readl(base + XGMAC_MMC_TXOCTET_G_HI)) << 32;
+
+	count = readl(base + XGMAC_MMC_TXFRAME_GB_LO);
+	storage->tx_errors = count - readl(base + XGMAC_MMC_TXFRAME_G_LO);
+	storage->tx_packets = count;
+	storage->tx_fifo_errors = readl(base + XGMAC_MMC_TXUNDERFLOW);
+
+	writel(0, base + XGMAC_MMC_CTRL);
+	spin_unlock_bh(&priv->stats_lock);
+	return storage;
+}
+
+static int xgmac_set_mac_address(struct net_device *dev, void *p)
+{
+	struct xgmac_priv *priv = netdev_priv(dev);
+	void __iomem *ioaddr = priv->base;
+	struct sockaddr *addr = p;
+
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
+
+	xgmac_set_mac_addr(ioaddr, dev->dev_addr, 0);
+
+	return 0;
+}
+
+static int xgmac_set_features(struct net_device *dev, netdev_features_t features)
+{
+	u32 ctrl;
+	struct xgmac_priv *priv = netdev_priv(dev);
+	void __iomem *ioaddr = priv->base;
+	u32 changed = dev->features ^ features;
+
+	if (!(changed & NETIF_F_RXCSUM))
+		return 0;
+
+	ctrl = readl(ioaddr + XGMAC_CONTROL);
+	if (features & NETIF_F_RXCSUM)
+		ctrl |= XGMAC_CONTROL_IPC;
+	else
+		ctrl &= ~XGMAC_CONTROL_IPC;
+	writel(ctrl, ioaddr + XGMAC_CONTROL);
+
+	return 0;
+}
+
+static const struct net_device_ops xgmac_netdev_ops = {
+	.ndo_open = xgmac_open,
+	.ndo_start_xmit = xgmac_xmit,
+	.ndo_stop = xgmac_stop,
+	.ndo_change_mtu = xgmac_change_mtu,
+	.ndo_set_rx_mode = xgmac_set_rx_mode,
+	.ndo_tx_timeout = xgmac_tx_timeout,
+	.ndo_get_stats64 = xgmac_get_stats64,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller = xgmac_poll_controller,
+#endif
+	.ndo_set_mac_address = xgmac_set_mac_address,
+	.ndo_set_features = xgmac_set_features,
+};
+
+static int xgmac_ethtool_getsettings(struct net_device *dev,
+					  struct ethtool_cmd *cmd)
+{
+	cmd->autoneg = 0;
+	cmd->duplex = DUPLEX_FULL;
+	ethtool_cmd_speed_set(cmd, 10000);
+	cmd->supported = 0;
+	cmd->advertising = 0;
+	cmd->transceiver = XCVR_INTERNAL;
+	return 0;
+}
+
+static void xgmac_get_pauseparam(struct net_device *netdev,
+				      struct ethtool_pauseparam *pause)
+{
+	struct xgmac_priv *priv = netdev_priv(netdev);
+
+	pause->rx_pause = priv->rx_pause;
+	pause->tx_pause = priv->tx_pause;
+}
+
+static int xgmac_set_pauseparam(struct net_device *netdev,
+				     struct ethtool_pauseparam *pause)
+{
+	struct xgmac_priv *priv = netdev_priv(netdev);
+
+	if (pause->autoneg)
+		return -EINVAL;
+
+	return xgmac_set_flow_ctrl(priv, pause->rx_pause, pause->tx_pause);
+}
+
+struct xgmac_stats {
+	char stat_string[ETH_GSTRING_LEN];
+	int stat_offset;
+	bool is_reg;
+};
+
+#define XGMAC_STAT(m)	\
+	{ #m, offsetof(struct xgmac_priv, xstats.m), false }
+#define XGMAC_HW_STAT(m, reg_offset)	\
+	{ #m, reg_offset, true }
+
+static const struct xgmac_stats xgmac_gstrings_stats[] = {
+	XGMAC_STAT(tx_frame_flushed),
+	XGMAC_STAT(tx_payload_error),
+	XGMAC_STAT(tx_ip_header_error),
+	XGMAC_STAT(tx_local_fault),
+	XGMAC_STAT(tx_remote_fault),
+	XGMAC_STAT(tx_early),
+	XGMAC_STAT(tx_process_stopped),
+	XGMAC_STAT(tx_jabber),
+	XGMAC_STAT(rx_buf_unav),
+	XGMAC_STAT(rx_process_stopped),
+	XGMAC_STAT(rx_payload_error),
+	XGMAC_STAT(rx_ip_header_error),
+	XGMAC_STAT(rx_da_filter_fail),
+	XGMAC_STAT(rx_sa_filter_fail),
+	XGMAC_STAT(fatal_bus_error),
+	XGMAC_HW_STAT(rx_watchdog, XGMAC_MMC_RXWATCHDOG),
+	XGMAC_HW_STAT(tx_vlan, XGMAC_MMC_TXVLANFRAME),
+	XGMAC_HW_STAT(rx_vlan, XGMAC_MMC_RXVLANFRAME),
+	XGMAC_HW_STAT(tx_pause, XGMAC_MMC_TXPAUSEFRAME),
+	XGMAC_HW_STAT(rx_pause, XGMAC_MMC_RXPAUSEFRAME),
+};
+#define XGMAC_STATS_LEN ARRAY_SIZE(xgmac_gstrings_stats)
+
+static void xgmac_get_ethtool_stats(struct net_device *dev,
+					 struct ethtool_stats *dummy,
+					 u64 *data)
+{
+	struct xgmac_priv *priv = netdev_priv(dev);
+	void *p = priv;
+	int i;
+
+	for (i = 0; i < XGMAC_STATS_LEN; i++) {
+		if (xgmac_gstrings_stats[i].is_reg)
+			*data++ = readl(priv->base +
+				xgmac_gstrings_stats[i].stat_offset);
+		else
+			*data++ = *(u32 *)(p +
+				xgmac_gstrings_stats[i].stat_offset);
+	}
+}
+
+static int xgmac_get_sset_count(struct net_device *netdev, int sset)
+{
+	switch (sset) {
+	case ETH_SS_STATS:
+		return XGMAC_STATS_LEN;
+	default:
+		return -EINVAL;
+	}
+}
+
+static void xgmac_get_strings(struct net_device *dev, u32 stringset,
+				   u8 *data)
+{
+	int i;
+	u8 *p = data;
+
+	switch (stringset) {
+	case ETH_SS_STATS:
+		for (i = 0; i < XGMAC_STATS_LEN; i++) {
+			memcpy(p, xgmac_gstrings_stats[i].stat_string,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+}
+
+static void xgmac_get_wol(struct net_device *dev,
+			       struct ethtool_wolinfo *wol)
+{
+	struct xgmac_priv *priv = netdev_priv(dev);
+
+	if (device_can_wakeup(priv->device)) {
+		wol->supported = WAKE_MAGIC | WAKE_UCAST;
+		wol->wolopts = priv->wolopts;
+	}
+}
+
+static int xgmac_set_wol(struct net_device *dev,
+			      struct ethtool_wolinfo *wol)
+{
+	struct xgmac_priv *priv = netdev_priv(dev);
+	u32 support = WAKE_MAGIC | WAKE_UCAST;
+
+	if (!device_can_wakeup(priv->device))
+		return -ENOTSUPP;
+
+	if (wol->wolopts & ~support)
+		return -EINVAL;
+
+	priv->wolopts = wol->wolopts;
+
+	if (wol->wolopts) {
+		device_set_wakeup_enable(priv->device, 1);
+		enable_irq_wake(dev->irq);
+	} else {
+		device_set_wakeup_enable(priv->device, 0);
+		disable_irq_wake(dev->irq);
+	}
+
+	return 0;
+}
+
+static struct ethtool_ops xgmac_ethtool_ops = {
+	.get_settings = xgmac_ethtool_getsettings,
+	.get_link = ethtool_op_get_link,
+	.get_pauseparam = xgmac_get_pauseparam,
+	.set_pauseparam = xgmac_set_pauseparam,
+	.get_ethtool_stats = xgmac_get_ethtool_stats,
+	.get_strings = xgmac_get_strings,
+	.get_wol = xgmac_get_wol,
+	.set_wol = xgmac_set_wol,
+	.get_sset_count = xgmac_get_sset_count,
+};
+
+/**
+ * xgmac_probe
+ * @pdev: platform device pointer
+ * Description: the driver is initialized through platform_device.
+ */
+static int xgmac_probe(struct platform_device *pdev)
+{
+	int ret = 0;
+	struct resource *res;
+	struct net_device *ndev = NULL;
+	struct xgmac_priv *priv = NULL;
+	u32 uid;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -ENODEV;
+
+	if (!request_mem_region(res->start, resource_size(res), pdev->name))
+		return -EBUSY;
+
+	ndev = alloc_etherdev(sizeof(struct xgmac_priv));
+	if (!ndev) {
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
+
+	SET_NETDEV_DEV(ndev, &pdev->dev);
+	priv = netdev_priv(ndev);
+	platform_set_drvdata(pdev, ndev);
+	ether_setup(ndev);
+	ndev->netdev_ops = &xgmac_netdev_ops;
+	SET_ETHTOOL_OPS(ndev, &xgmac_ethtool_ops);
+	spin_lock_init(&priv->stats_lock);
+
+	priv->device = &pdev->dev;
+	priv->dev = ndev;
+	priv->rx_pause = 1;
+	priv->tx_pause = 1;
+
+	priv->base = ioremap(res->start, resource_size(res));
+	if (!priv->base) {
+		netdev_err(ndev, "ioremap failed\n");
+		ret = -ENOMEM;
+		goto err_io;
+	}
+
+	uid = readl(priv->base + XGMAC_VERSION);
+	netdev_info(ndev, "h/w version is 0x%x\n", uid);
+
+	writel(0, priv->base + XGMAC_DMA_INTR_ENA);
+	ndev->irq = platform_get_irq(pdev, 0);
+	if (ndev->irq == -ENXIO) {
+		netdev_err(ndev, "No irq resource\n");
+		ret = ndev->irq;
+		goto err_irq;
+	}
+
+	ret = request_irq(ndev->irq, xgmac_interrupt, 0,
+			  dev_name(&pdev->dev), ndev);
+	if (ret < 0) {
+		netdev_err(ndev, "Could not request irq %d - ret %d)\n",
+			ndev->irq, ret);
+		goto err_irq;
+	}
+
+	priv->pmt_irq = platform_get_irq(pdev, 1);
+	if (priv->pmt_irq == -ENXIO) {
+		netdev_err(ndev, "No pmt irq resource\n");
+		ret = priv->pmt_irq;
+		goto err_pmt_irq;
+	}
+
+	ret = request_irq(priv->pmt_irq, xgmac_pmt_interrupt, 0,
+			  dev_name(&pdev->dev), ndev);
+	if (ret < 0) {
+		netdev_err(ndev, "Could not request irq %d - ret %d)\n",
+			priv->pmt_irq, ret);
+		goto err_pmt_irq;
+	}
+
+	device_set_wakeup_capable(&pdev->dev, 1);
+	if (device_can_wakeup(priv->device))
+		priv->wolopts = WAKE_MAGIC;	/* Magic Frame as default */
+
+	ndev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA;
+	if (readl(priv->base + XGMAC_DMA_HW_FEATURE) & DMA_HW_FEAT_TXCOESEL)
+		ndev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+				     NETIF_F_RXCSUM;
+	ndev->features |= ndev->hw_features;
+	ndev->priv_flags |= IFF_UNICAST_FLT;
+
+	/* Get the MAC address */
+	xgmac_get_mac_addr(priv->base, ndev->dev_addr, 0);
+	if (!is_valid_ether_addr(ndev->dev_addr))
+		netdev_warn(ndev, "MAC address %pM not valid",
+			 ndev->dev_addr);
+
+	netif_napi_add(ndev, &priv->napi, xgmac_poll, 64);
+	ret = register_netdev(ndev);
+	if (ret)
+		goto err_reg;
+
+	return 0;
+
+err_reg:
+	netif_napi_del(&priv->napi);
+	free_irq(priv->pmt_irq, ndev);
+err_pmt_irq:
+	free_irq(ndev->irq, ndev);
+err_irq:
+	iounmap(priv->base);
+err_io:
+	free_netdev(ndev);
+err_alloc:
+	release_mem_region(res->start, resource_size(res));
+	platform_set_drvdata(pdev, NULL);
+	return ret;
+}
+
+/**
+ * xgmac_dvr_remove
+ * @pdev: platform device pointer
+ * Description: this function resets the TX/RX processes, disables the MAC RX/TX
+ * changes the link status, releases the DMA descriptor rings,
+ * unregisters the MDIO bus and unmaps the allocated memory.
+ */
+static int xgmac_remove(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct xgmac_priv *priv = netdev_priv(ndev);
+	struct resource *res;
+
+	xgmac_mac_disable(priv->base);
+
+	/* Free the IRQ lines */
+	free_irq(ndev->irq, ndev);
+	free_irq(priv->pmt_irq, ndev);
+
+	platform_set_drvdata(pdev, NULL);
+	unregister_netdev(ndev);
+	netif_napi_del(&priv->napi);
+
+	iounmap(priv->base);
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	release_mem_region(res->start, resource_size(res));
+
+	free_netdev(ndev);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static void xgmac_pmt(void __iomem *ioaddr, unsigned long mode)
+{
+	unsigned int pmt = 0;
+
+	if (mode & WAKE_MAGIC)
+		pmt |= XGMAC_PMT_POWERDOWN | XGMAC_PMT_MAGIC_PKT;
+	if (mode & WAKE_UCAST)
+		pmt |= XGMAC_PMT_POWERDOWN | XGMAC_PMT_GLBL_UNICAST;
+
+	writel(pmt, ioaddr + XGMAC_PMT);
+}
+
+static int xgmac_suspend(struct device *dev)
+{
+	struct net_device *ndev = platform_get_drvdata(to_platform_device(dev));
+	struct xgmac_priv *priv = netdev_priv(ndev);
+	u32 value;
+
+	if (!ndev || !netif_running(ndev))
+		return 0;
+
+	netif_device_detach(ndev);
+	napi_disable(&priv->napi);
+	writel(0, priv->base + XGMAC_DMA_INTR_ENA);
+
+	if (device_may_wakeup(priv->device)) {
+		/* Stop TX/RX DMA Only */
+		value = readl(priv->base + XGMAC_DMA_CONTROL);
+		value &= ~(DMA_CONTROL_ST | DMA_CONTROL_SR);
+		writel(value, priv->base + XGMAC_DMA_CONTROL);
+
+		xgmac_pmt(priv->base, priv->wolopts);
+	} else
+		xgmac_mac_disable(priv->base);
+
+	return 0;
+}
+
+static int xgmac_resume(struct device *dev)
+{
+	struct net_device *ndev = platform_get_drvdata(to_platform_device(dev));
+	struct xgmac_priv *priv = netdev_priv(ndev);
+	void __iomem *ioaddr = priv->base;
+
+	if (!netif_running(ndev))
+		return 0;
+
+	xgmac_pmt(ioaddr, 0);
+
+	/* Enable the MAC and DMA */
+	xgmac_mac_enable(ioaddr);
+	writel(DMA_INTR_DEFAULT_MASK, ioaddr + XGMAC_DMA_STATUS);
+	writel(DMA_INTR_DEFAULT_MASK, ioaddr + XGMAC_DMA_INTR_ENA);
+
+	netif_device_attach(ndev);
+	napi_enable(&priv->napi);
+
+	return 0;
+}
+
+static SIMPLE_DEV_PM_OPS(xgmac_pm_ops, xgmac_suspend, xgmac_resume);
+#define XGMAC_PM_OPS (&xgmac_pm_ops)
+#else
+#define XGMAC_PM_OPS NULL
+#endif /* CONFIG_PM_SLEEP */
+
+static const struct of_device_id xgmac_of_match[] = {
+	{ .compatible = "calxeda,hb-xgmac", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, xgmac_of_match);
+
+static struct platform_driver xgmac_driver = {
+	.driver = {
+		.name = "calxedaxgmac",
+		.of_match_table = xgmac_of_match,
+	},
+	.probe = xgmac_probe,
+	.remove = xgmac_remove,
+	.driver.pm = XGMAC_PM_OPS,
+};
+
+module_platform_driver(xgmac_driver);
+
+MODULE_AUTHOR("Calxeda, Inc.");
+MODULE_DESCRIPTION("Calxeda 10G XGMAC driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
index ca26d97..1d17c92 100644
--- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
+++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
@@ -434,10 +434,10 @@ static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
 	struct adapter *adapter = dev->ml_priv;
 
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->fw_version, "N/A");
-	strcpy(info->bus_info, pci_name(adapter->pdev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(adapter->pdev),
+		sizeof(info->bus_info));
 }
 
 static int get_sset_count(struct net_device *dev, int sset)
@@ -849,7 +849,8 @@ static int t1_set_mac_addr(struct net_device *dev, void *p)
 	return 0;
 }
 
-static u32 t1_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t t1_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	/*
 	 * Since there is no support for separate rx/tx vlan accel
@@ -863,9 +864,9 @@ static u32 t1_fix_features(struct net_device *dev, u32 features)
 	return features;
 }
 
-static int t1_set_features(struct net_device *dev, u32 features)
+static int t1_set_features(struct net_device *dev, netdev_features_t features)
 {
-	u32 changed = dev->features ^ features;
+	netdev_features_t changed = dev->features ^ features;
 	struct adapter *adapter = dev->ml_priv;
 
 	if (changed & NETIF_F_HW_VLAN_RX)
diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c
index f9b6023..47a8435 100644
--- a/drivers/net/ethernet/chelsio/cxgb/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb/sge.c
@@ -742,7 +742,7 @@ static inline void setup_ring_params(struct adapter *adapter, u64 addr,
 /*
  * Enable/disable VLAN acceleration.
  */
-void t1_vlan_mode(struct adapter *adapter, u32 features)
+void t1_vlan_mode(struct adapter *adapter, netdev_features_t features)
 {
 	struct sge *sge = adapter->sge;
 
diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.h b/drivers/net/ethernet/chelsio/cxgb/sge.h
index e03980b..b9bf16b 100644
--- a/drivers/net/ethernet/chelsio/cxgb/sge.h
+++ b/drivers/net/ethernet/chelsio/cxgb/sge.h
@@ -79,7 +79,7 @@ irqreturn_t t1_interrupt(int irq, void *cookie);
 int t1_poll(struct napi_struct *, int);
 
 netdev_tx_t t1_start_xmit(struct sk_buff *skb, struct net_device *dev);
-void t1_vlan_mode(struct adapter *adapter, u32 features);
+void t1_vlan_mode(struct adapter *adapter, netdev_features_t features);
 void t1_sge_start(struct sge *);
 void t1_sge_stop(struct sge *);
 int t1_sge_intr_error_handler(struct sge *);
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
index 4d15c8f..857cc25 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_main.c
@@ -1576,12 +1576,11 @@ static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 	t3_get_tp_version(adapter, &tp_vers);
 	spin_unlock(&adapter->stats_lock);
 
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->bus_info, pci_name(adapter->pdev));
-	if (!fw_vers)
-		strcpy(info->fw_version, "N/A");
-	else {
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(adapter->pdev),
+		sizeof(info->bus_info));
+	if (fw_vers)
 		snprintf(info->fw_version, sizeof(info->fw_version),
 			 "%s %u.%u.%u TP %u.%u.%u",
 			 G_FW_VERSION_TYPE(fw_vers) ? "T" : "N",
@@ -1591,7 +1590,6 @@ static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 			 G_TP_VERSION_MAJOR(tp_vers),
 			 G_TP_VERSION_MINOR(tp_vers),
 			 G_TP_VERSION_MICRO(tp_vers));
-	}
 }
 
 static void get_strings(struct net_device *dev, u32 stringset, u8 * data)
@@ -2531,7 +2529,7 @@ static void t3_synchronize_rx(struct adapter *adap, const struct port_info *p)
 	}
 }
 
-static void cxgb_vlan_mode(struct net_device *dev, u32 features)
+static void cxgb_vlan_mode(struct net_device *dev, netdev_features_t features)
 {
 	struct port_info *pi = netdev_priv(dev);
 	struct adapter *adapter = pi->adapter;
@@ -2552,7 +2550,8 @@ static void cxgb_vlan_mode(struct net_device *dev, u32 features)
 	t3_synchronize_rx(adapter, pi);
 }
 
-static u32 cxgb_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t cxgb_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	/*
 	 * Since there is no support for separate rx/tx vlan accel
@@ -2566,9 +2565,9 @@ static u32 cxgb_fix_features(struct net_device *dev, u32 features)
 	return features;
 }
 
-static int cxgb_set_features(struct net_device *dev, u32 features)
+static int cxgb_set_features(struct net_device *dev, netdev_features_t features)
 {
-	u32 changed = dev->features ^ features;
+	netdev_features_t changed = dev->features ^ features;
 
 	if (changed & NETIF_F_HW_VLAN_RX)
 		cxgb_vlan_mode(dev, features);
diff --git a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c
index 90ff131..65e4b28 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c
@@ -969,7 +969,7 @@ static int nb_callback(struct notifier_block *self, unsigned long event,
 	case (NETEVENT_REDIRECT):{
 		struct netevent_redirect *nr = ctx;
 		cxgb_redirect(nr->old, nr->new);
-		cxgb_neigh_update(dst_get_neighbour(nr->new));
+		cxgb_neigh_update(dst_get_neighbour_noref(nr->new));
 		break;
 	}
 	default:
@@ -1072,8 +1072,11 @@ static int is_offloading(struct net_device *dev)
 
 static void cxgb_neigh_update(struct neighbour *neigh)
 {
-	struct net_device *dev = neigh->dev;
+	struct net_device *dev;
 
+	if (!neigh)
+		return;
+	dev = neigh->dev;
 	if (dev && (is_offloading(dev))) {
 		struct t3cdev *tdev = dev2t3cdev(dev);
 
@@ -1107,6 +1110,7 @@ static void set_l2t_ix(struct t3cdev *tdev, u32 tid, struct l2t_entry *e)
 static void cxgb_redirect(struct dst_entry *old, struct dst_entry *new)
 {
 	struct net_device *olddev, *newdev;
+	struct neighbour *n;
 	struct tid_info *ti;
 	struct t3cdev *tdev;
 	u32 tid;
@@ -1114,8 +1118,16 @@ static void cxgb_redirect(struct dst_entry *old, struct dst_entry *new)
 	struct l2t_entry *e;
 	struct t3c_tid_entry *te;
 
-	olddev = dst_get_neighbour(old)->dev;
-	newdev = dst_get_neighbour(new)->dev;
+	n = dst_get_neighbour_noref(old);
+	if (!n)
+		return;
+	olddev = n->dev;
+
+	n = dst_get_neighbour_noref(new);
+	if (!n)
+		return;
+	newdev = n->dev;
+
 	if (!is_offloading(olddev))
 		return;
 	if (!is_offloading(newdev)) {
@@ -1132,7 +1144,7 @@ static void cxgb_redirect(struct dst_entry *old, struct dst_entry *new)
 	}
 
 	/* Add new L2T entry */
-	e = t3_l2t_get(tdev, dst_get_neighbour(new), newdev);
+	e = t3_l2t_get(tdev, new, newdev);
 	if (!e) {
 		printk(KERN_ERR "%s: couldn't allocate new l2t entry!\n",
 		       __func__);
@@ -1301,7 +1313,7 @@ int cxgb3_offload_activate(struct adapter *adapter)
 
 out_free_l2t:
 	t3_free_l2t(L2DATA(dev));
-	rcu_assign_pointer(dev->l2opt, NULL);
+	RCU_INIT_POINTER(dev->l2opt, NULL);
 out_free:
 	kfree(t);
 	return err;
@@ -1329,7 +1341,7 @@ void cxgb3_offload_deactivate(struct adapter *adapter)
 	rcu_read_lock();
 	d = L2DATA(tdev);
 	rcu_read_unlock();
-	rcu_assign_pointer(tdev->l2opt, NULL);
+	RCU_INIT_POINTER(tdev->l2opt, NULL);
 	call_rcu(&d->rcu_head, clean_l2_data);
 	if (t->nofail_skb)
 		kfree_skb(t->nofail_skb);
diff --git a/drivers/net/ethernet/chelsio/cxgb3/l2t.c b/drivers/net/ethernet/chelsio/cxgb3/l2t.c
index 70fec8b..3fa3c88 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/l2t.c
@@ -298,18 +298,31 @@ static inline void reuse_entry(struct l2t_entry *e, struct neighbour *neigh)
 	spin_unlock(&e->lock);
 }
 
-struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct neighbour *neigh,
+struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct dst_entry *dst,
 			     struct net_device *dev)
 {
 	struct l2t_entry *e = NULL;
+	struct neighbour *neigh;
+	struct port_info *p;
 	struct l2t_data *d;
 	int hash;
-	u32 addr = *(u32 *) neigh->primary_key;
-	int ifidx = neigh->dev->ifindex;
-	struct port_info *p = netdev_priv(dev);
-	int smt_idx = p->port_id;
+	u32 addr;
+	int ifidx;
+	int smt_idx;
 
 	rcu_read_lock();
+	neigh = dst_get_neighbour_noref(dst);
+	if (!neigh)
+		goto done_rcu;
+
+	addr = *(u32 *) neigh->primary_key;
+	ifidx = neigh->dev->ifindex;
+
+	if (!dev)
+		dev = neigh->dev;
+	p = netdev_priv(dev);
+	smt_idx = p->port_id;
+
 	d = L2DATA(cdev);
 	if (!d)
 		goto done_rcu;
@@ -323,7 +336,7 @@ struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct neighbour *neigh,
 			l2t_hold(d, e);
 			if (atomic_read(&e->refcnt) == 1)
 				reuse_entry(e, neigh);
-			goto done;
+			goto done_unlock;
 		}
 
 	/* Need to allocate a new entry */
@@ -344,7 +357,7 @@ struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct neighbour *neigh,
 			e->vlan = VLAN_NONE;
 		spin_unlock(&e->lock);
 	}
-done:
+done_unlock:
 	write_unlock_bh(&d->lock);
 done_rcu:
 	rcu_read_unlock();
diff --git a/drivers/net/ethernet/chelsio/cxgb3/l2t.h b/drivers/net/ethernet/chelsio/cxgb3/l2t.h
index c5f5479..c4e8643 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/l2t.h
+++ b/drivers/net/ethernet/chelsio/cxgb3/l2t.h
@@ -109,7 +109,7 @@ static inline void set_arp_failure_handler(struct sk_buff *skb,
 
 void t3_l2e_free(struct l2t_data *d, struct l2t_entry *e);
 void t3_l2t_update(struct t3cdev *dev, struct neighbour *neigh);
-struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct neighbour *neigh,
+struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct dst_entry *dst,
 			     struct net_device *dev);
 int t3_l2t_send_slow(struct t3cdev *dev, struct sk_buff *skb,
 		     struct l2t_entry *e);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 4c8f42a..fccbe49 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -1002,13 +1002,12 @@ static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
 	struct adapter *adapter = netdev2adap(dev);
 
-	strcpy(info->driver, KBUILD_MODNAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->bus_info, pci_name(adapter->pdev));
+	strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(adapter->pdev),
+		sizeof(info->bus_info));
 
-	if (!adapter->params.fw_vers)
-		strcpy(info->fw_version, "N/A");
-	else
+	if (adapter->params.fw_vers)
 		snprintf(info->fw_version, sizeof(info->fw_version),
 			"%u.%u.%u.%u, TP %u.%u.%u.%u",
 			FW_HDR_FW_VER_MAJOR_GET(adapter->params.fw_vers),
@@ -1855,10 +1854,10 @@ static int set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	return err;
 }
 
-static int cxgb_set_features(struct net_device *dev, u32 features)
+static int cxgb_set_features(struct net_device *dev, netdev_features_t features)
 {
 	const struct port_info *pi = netdev_priv(dev);
-	u32 changed = dev->features ^ features;
+	netdev_features_t changed = dev->features ^ features;
 	int err;
 
 	if (!(changed & NETIF_F_HW_VLAN_RX))
@@ -1872,30 +1871,30 @@ static int cxgb_set_features(struct net_device *dev, u32 features)
 	return err;
 }
 
-static int get_rss_table(struct net_device *dev, struct ethtool_rxfh_indir *p)
+static u32 get_rss_table_size(struct net_device *dev)
+{
+	const struct port_info *pi = netdev_priv(dev);
+
+	return pi->rss_size;
+}
+
+static int get_rss_table(struct net_device *dev, u32 *p)
 {
 	const struct port_info *pi = netdev_priv(dev);
-	unsigned int n = min_t(unsigned int, p->size, pi->rss_size);
+	unsigned int n = pi->rss_size;
 
-	p->size = pi->rss_size;
 	while (n--)
-		p->ring_index[n] = pi->rss[n];
+		p[n] = pi->rss[n];
 	return 0;
 }
 
-static int set_rss_table(struct net_device *dev,
-			 const struct ethtool_rxfh_indir *p)
+static int set_rss_table(struct net_device *dev, const u32 *p)
 {
 	unsigned int i;
 	struct port_info *pi = netdev_priv(dev);
 
-	if (p->size != pi->rss_size)
-		return -EINVAL;
-	for (i = 0; i < p->size; i++)
-		if (p->ring_index[i] >= pi->nqsets)
-			return -EINVAL;
-	for (i = 0; i < p->size; i++)
-		pi->rss[i] = p->ring_index[i];
+	for (i = 0; i < pi->rss_size; i++)
+		pi->rss[i] = p[i];
 	if (pi->adapter->flags & FULL_INIT_DONE)
 		return write_rss(pi, pi->rss);
 	return 0;
@@ -1990,6 +1989,7 @@ static struct ethtool_ops cxgb_ethtool_ops = {
 	.get_wol           = get_wol,
 	.set_wol           = set_wol,
 	.get_rxnfc         = get_rxnfc,
+	.get_rxfh_indir_size = get_rss_table_size,
 	.get_rxfh_indir    = get_rss_table,
 	.set_rxfh_indir    = set_rss_table,
 	.flash_device      = set_flash,
@@ -3449,7 +3449,7 @@ static int __devinit init_rss(struct adapter *adap)
 		if (!pi->rss)
 			return -ENOMEM;
 		for (j = 0; j < pi->rss_size; j++)
-			pi->rss[j] = j % pi->nqsets;
+			pi->rss[j] = ethtool_rxfh_indir_default(j, pi->nqsets);
 	}
 	return 0;
 }
@@ -3537,7 +3537,7 @@ static int __devinit init_one(struct pci_dev *pdev,
 {
 	int func, i, err;
 	struct port_info *pi;
-	unsigned int highdma = 0;
+	bool highdma = false;
 	struct adapter *adapter = NULL;
 
 	printk_once(KERN_INFO "%s - version %s\n", DRV_DESC, DRV_VERSION);
@@ -3563,7 +3563,7 @@ static int __devinit init_one(struct pci_dev *pdev,
 	}
 
 	if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) {
-		highdma = NETIF_F_HIGHDMA;
+		highdma = true;
 		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
 		if (err) {
 			dev_err(&pdev->dev, "unable to obtain 64-bit DMA for "
@@ -3637,7 +3637,9 @@ static int __devinit init_one(struct pci_dev *pdev,
 			NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
 			NETIF_F_RXCSUM | NETIF_F_RXHASH |
 			NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX;
-		netdev->features |= netdev->hw_features | highdma;
+		if (highdma)
+			netdev->hw_features |= NETIF_F_HIGHDMA;
+		netdev->features |= netdev->hw_features;
 		netdev->vlan_features = netdev->features & VLAN_FEAT;
 
 		netdev->priv_flags |= IFF_UNICAST_FLT;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 140254c..2dae795 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -491,7 +491,7 @@ static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n,
 	__be64 *d = &q->desc[q->pidx];
 	struct rx_sw_desc *sd = &q->sdesc[q->pidx];
 
-	gfp |= __GFP_NOWARN;         /* failures are expected */
+	gfp |= __GFP_NOWARN | __GFP_COLD;
 
 #if FL_PG_ORDER > 0
 	/*
@@ -528,7 +528,7 @@ static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n,
 #endif
 
 	while (n--) {
-		pg = __netdev_alloc_page(adap->port[0], gfp);
+		pg = alloc_page(gfp);
 		if (unlikely(!pg)) {
 			q->alloc_failed++;
 			break;
@@ -537,7 +537,7 @@ static unsigned int refill_fl(struct adapter *adap, struct sge_fl *q, int n,
 		mapping = dma_map_page(adap->pdev_dev, pg, 0, PAGE_SIZE,
 				       PCI_DMA_FROMDEVICE);
 		if (unlikely(dma_mapping_error(adap->pdev_dev, mapping))) {
-			netdev_free_page(adap->port[0], pg);
+			put_page(pg);
 			goto out;
 		}
 		*d++ = cpu_to_be64(mapping);
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index da9072b..8155cfe 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -1092,7 +1092,8 @@ static int cxgb4vf_change_mtu(struct net_device *dev, int new_mtu)
 	return ret;
 }
 
-static u32 cxgb4vf_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t cxgb4vf_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	/*
 	 * Since there is no support for separate rx/tx vlan accel
@@ -1106,10 +1107,11 @@ static u32 cxgb4vf_fix_features(struct net_device *dev, u32 features)
 	return features;
 }
 
-static int cxgb4vf_set_features(struct net_device *dev, u32 features)
+static int cxgb4vf_set_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct port_info *pi = netdev_priv(dev);
-	u32 changed = dev->features ^ features;
+	netdev_features_t changed = dev->features ^ features;
 
 	if (changed & NETIF_F_HW_VLAN_RX)
 		t4vf_set_rxmode(pi->adapter, pi->viid, -1, -1, -1, -1,
@@ -1203,9 +1205,10 @@ static void cxgb4vf_get_drvinfo(struct net_device *dev,
 {
 	struct adapter *adapter = netdev2adap(dev);
 
-	strcpy(drvinfo->driver, KBUILD_MODNAME);
-	strcpy(drvinfo->version, DRV_VERSION);
-	strcpy(drvinfo->bus_info, pci_name(to_pci_dev(dev->dev.parent)));
+	strlcpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version));
+	strlcpy(drvinfo->bus_info, pci_name(to_pci_dev(dev->dev.parent)),
+		sizeof(drvinfo->bus_info));
 	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
 		 "%u.%u.%u.%u, TP %u.%u.%u.%u",
 		 FW_HDR_FW_VER_MAJOR_GET(adapter->params.dev.fwrev),
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
index 8d5d55a..c381db2 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -653,8 +653,7 @@ static unsigned int refill_fl(struct adapter *adapter, struct sge_fl *fl,
 
 alloc_small_pages:
 	while (n--) {
-		page = __netdev_alloc_page(adapter->port[0],
-					   gfp | __GFP_NOWARN);
+		page = alloc_page(gfp | __GFP_NOWARN | __GFP_COLD);
 		if (unlikely(!page)) {
 			fl->alloc_failed++;
 			break;
@@ -664,7 +663,7 @@ alloc_small_pages:
 		dma_addr = dma_map_page(adapter->pdev_dev, page, 0, PAGE_SIZE,
 				       PCI_DMA_FROMDEVICE);
 		if (unlikely(dma_mapping_error(adapter->pdev_dev, dma_addr))) {
-			netdev_free_page(adapter->port[0], page);
+			put_page(page);
 			break;
 		}
 		*d++ = cpu_to_be64(dma_addr);
diff --git a/drivers/net/ethernet/cisco/enic/enic_dev.c b/drivers/net/ethernet/cisco/enic/enic_dev.c
index fd6247b..bf0fc56 100644
--- a/drivers/net/ethernet/cisco/enic/enic_dev.c
+++ b/drivers/net/ethernet/cisco/enic/enic_dev.c
@@ -212,23 +212,29 @@ int enic_dev_deinit_done(struct enic *enic, int *status)
 }
 
 /* rtnl lock is held */
-void enic_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
+int enic_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 {
 	struct enic *enic = netdev_priv(netdev);
+	int err;
 
 	spin_lock(&enic->devcmd_lock);
-	enic_add_vlan(enic, vid);
+	err = enic_add_vlan(enic, vid);
 	spin_unlock(&enic->devcmd_lock);
+
+	return err;
 }
 
 /* rtnl lock is held */
-void enic_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
+int enic_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 {
 	struct enic *enic = netdev_priv(netdev);
+	int err;
 
 	spin_lock(&enic->devcmd_lock);
-	enic_del_vlan(enic, vid);
+	err = enic_del_vlan(enic, vid);
 	spin_unlock(&enic->devcmd_lock);
+
+	return err;
 }
 
 int enic_dev_enable2(struct enic *enic, int active)
diff --git a/drivers/net/ethernet/cisco/enic/enic_dev.h b/drivers/net/ethernet/cisco/enic/enic_dev.h
index 1f83a47..da1cba3 100644
--- a/drivers/net/ethernet/cisco/enic/enic_dev.h
+++ b/drivers/net/ethernet/cisco/enic/enic_dev.h
@@ -46,8 +46,8 @@ int enic_dev_packet_filter(struct enic *enic, int directed, int multicast,
 	int broadcast, int promisc, int allmulti);
 int enic_dev_add_addr(struct enic *enic, u8 *addr);
 int enic_dev_del_addr(struct enic *enic, u8 *addr);
-void enic_vlan_rx_add_vid(struct net_device *netdev, u16 vid);
-void enic_vlan_rx_kill_vid(struct net_device *netdev, u16 vid);
+int enic_vlan_rx_add_vid(struct net_device *netdev, u16 vid);
+int enic_vlan_rx_kill_vid(struct net_device *netdev, u16 vid);
 int enic_dev_notify_unset(struct enic *enic);
 int enic_dev_hang_notify(struct enic *enic);
 int enic_dev_set_ig_vlan_rewrite_mode(struct enic *enic);
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index c3786fd..2fd9db4 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -217,11 +217,11 @@ static void enic_get_drvinfo(struct net_device *netdev,
 
 	enic_dev_fw_info(enic, &fw_info);
 
-	strncpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
-	strncpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version));
-	strncpy(drvinfo->fw_version, fw_info->fw_version,
+	strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version));
+	strlcpy(drvinfo->fw_version, fw_info->fw_version,
 		sizeof(drvinfo->fw_version));
-	strncpy(drvinfo->bus_info, pci_name(enic->pdev),
+	strlcpy(drvinfo->bus_info, pci_name(enic->pdev),
 		sizeof(drvinfo->bus_info));
 }
 
@@ -2379,7 +2379,7 @@ static int __devinit enic_probe(struct pci_dev *pdev,
 
 #endif
 	/* Allocate structure for port profiles */
-	enic->pp = kzalloc(num_pps * sizeof(*enic->pp), GFP_KERNEL);
+	enic->pp = kcalloc(num_pps, sizeof(*enic->pp), GFP_KERNEL);
 	if (!enic->pp) {
 		pr_err("port profile alloc failed, aborting\n");
 		err = -ENOMEM;
diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c
index 438f458..f801754 100644
--- a/drivers/net/ethernet/davicom/dm9000.c
+++ b/drivers/net/ethernet/davicom/dm9000.c
@@ -474,10 +474,11 @@ static int dm9000_nway_reset(struct net_device *dev)
 	return mii_nway_restart(&dm->mii);
 }
 
-static int dm9000_set_features(struct net_device *dev, u32 features)
+static int dm9000_set_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	board_info_t *dm = to_dm9000_board(dev);
-	u32 changed = dev->features ^ features;
+	netdev_features_t changed = dev->features ^ features;
 	unsigned long flags;
 
 	if (!(changed & NETIF_F_RXCSUM))
@@ -613,7 +614,7 @@ static int dm9000_set_wol(struct net_device *dev, struct ethtool_wolinfo *w)
 
 		if (!dm->wake_state)
 			irq_set_irq_wake(dm->irq_wake, 1);
-		else if (dm->wake_state & !opts)
+		else if (dm->wake_state && !opts)
 			irq_set_irq_wake(dm->irq_wake, 0);
 	}
 
diff --git a/drivers/net/ethernet/dec/tulip/de2104x.c b/drivers/net/ethernet/dec/tulip/de2104x.c
index 1427739..1eb46a0 100644
--- a/drivers/net/ethernet/dec/tulip/de2104x.c
+++ b/drivers/net/ethernet/dec/tulip/de2104x.c
@@ -1598,9 +1598,9 @@ static void de_get_drvinfo (struct net_device *dev,struct ethtool_drvinfo *info)
 {
 	struct de_private *de = netdev_priv(dev);
 
-	strcpy (info->driver, DRV_NAME);
-	strcpy (info->version, DRV_VERSION);
-	strcpy (info->bus_info, pci_name(de->pdev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(de->pdev), sizeof(info->bus_info));
 	info->eedump_len = DE_EEPROM_SIZE;
 }
 
diff --git a/drivers/net/ethernet/dec/tulip/dmfe.c b/drivers/net/ethernet/dec/tulip/dmfe.c
index 17b11ee..51f7542 100644
--- a/drivers/net/ethernet/dec/tulip/dmfe.c
+++ b/drivers/net/ethernet/dec/tulip/dmfe.c
@@ -1085,10 +1085,11 @@ static void dmfe_ethtool_get_drvinfo(struct net_device *dev,
 {
 	struct dmfe_board_info *np = netdev_priv(dev);
 
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
 	if (np->pdev)
-		strcpy(info->bus_info, pci_name(np->pdev));
+		strlcpy(info->bus_info, pci_name(np->pdev),
+			sizeof(info->bus_info));
 	else
 		sprintf(info->bus_info, "EISA 0x%lx %d",
 			dev->base_addr, dev->irq);
diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index 9656dd0..4eb0d76 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -871,9 +871,9 @@ static struct net_device_stats *tulip_get_stats(struct net_device *dev)
 static void tulip_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
 	struct tulip_private *np = netdev_priv(dev);
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->bus_info, pci_name(np->pdev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(np->pdev), sizeof(info->bus_info));
 }
 
 
diff --git a/drivers/net/ethernet/dec/tulip/uli526x.c b/drivers/net/ethernet/dec/tulip/uli526x.c
index 7a44a7a..48b0b65 100644
--- a/drivers/net/ethernet/dec/tulip/uli526x.c
+++ b/drivers/net/ethernet/dec/tulip/uli526x.c
@@ -960,10 +960,11 @@ static void netdev_get_drvinfo(struct net_device *dev,
 {
 	struct uli526x_board_info *np = netdev_priv(dev);
 
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
 	if (np->pdev)
-		strcpy(info->bus_info, pci_name(np->pdev));
+		strlcpy(info->bus_info, pci_name(np->pdev),
+			sizeof(info->bus_info));
 	else
 		sprintf(info->bus_info, "EISA 0x%lx %d",
 			dev->base_addr, dev->irq);
diff --git a/drivers/net/ethernet/dec/tulip/winbond-840.c b/drivers/net/ethernet/dec/tulip/winbond-840.c
index 4d01219..52da7b2 100644
--- a/drivers/net/ethernet/dec/tulip/winbond-840.c
+++ b/drivers/net/ethernet/dec/tulip/winbond-840.c
@@ -1390,9 +1390,9 @@ static void netdev_get_drvinfo (struct net_device *dev, struct ethtool_drvinfo *
 {
 	struct netdev_private *np = netdev_priv(dev);
 
-	strcpy (info->driver, DRV_NAME);
-	strcpy (info->version, DRV_VERSION);
-	strcpy (info->bus_info, pci_name(np->pci_dev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
 }
 
 static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
diff --git a/drivers/net/ethernet/dlink/sundance.c b/drivers/net/ethernet/dlink/sundance.c
index dcd7f7a..28a3a9b 100644
--- a/drivers/net/ethernet/dlink/sundance.c
+++ b/drivers/net/ethernet/dlink/sundance.c
@@ -1634,9 +1634,9 @@ static int check_if_running(struct net_device *dev)
 static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
 	struct netdev_private *np = netdev_priv(dev);
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->bus_info, pci_name(np->pci_dev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
 }
 
 static int get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
diff --git a/drivers/net/ethernet/dnet.c b/drivers/net/ethernet/dnet.c
index c1063d1..ce88c0f 100644
--- a/drivers/net/ethernet/dnet.c
+++ b/drivers/net/ethernet/dnet.c
@@ -804,9 +804,9 @@ static int dnet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 static void dnet_get_drvinfo(struct net_device *dev,
 			     struct ethtool_drvinfo *info)
 {
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->bus_info, "0");
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, "0", sizeof(info->bus_info));
 }
 
 static const struct ethtool_ops dnet_ethtool_ops = {
@@ -977,18 +977,7 @@ static struct platform_driver dnet_driver = {
 	},
 };
 
-static int __init dnet_init(void)
-{
-	return platform_driver_register(&dnet_driver);
-}
-
-static void __exit dnet_exit(void)
-{
-	platform_driver_unregister(&dnet_driver);
-}
-
-module_init(dnet_init);
-module_exit(dnet_exit);
+module_platform_driver(dnet_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Dave DNET Ethernet driver");
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 644e8fe..995198d 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -40,6 +40,7 @@
 #define OC_NAME			"Emulex OneConnect 10Gbps NIC"
 #define OC_NAME_BE		OC_NAME	"(be3)"
 #define OC_NAME_LANCER		OC_NAME "(Lancer)"
+#define OC_NAME_SH		OC_NAME "(Skyhawk)"
 #define DRV_DESC		"ServerEngines BladeEngine 10Gbps NIC Driver"
 
 #define BE_VENDOR_ID 		0x19a2
@@ -50,6 +51,7 @@
 #define OC_DEVICE_ID2		0x710	/* Device Id for BE3 cards */
 #define OC_DEVICE_ID3		0xe220	/* Device id for Lancer cards */
 #define OC_DEVICE_ID4           0xe228   /* Device id for VF in Lancer */
+#define OC_DEVICE_ID5		0x720	/* Device Id for Skyhawk cards */
 
 static inline char *nic_name(struct pci_dev *pdev)
 {
@@ -63,6 +65,8 @@ static inline char *nic_name(struct pci_dev *pdev)
 		return OC_NAME_LANCER;
 	case BE_DEVICE_ID2:
 		return BE3_NAME;
+	case OC_DEVICE_ID5:
+		return OC_NAME_SH;
 	default:
 		return BE_NAME;
 	}
@@ -288,15 +292,13 @@ struct be_drv_stats {
 };
 
 struct be_vf_cfg {
-	unsigned char vf_mac_addr[ETH_ALEN];
-	u32 vf_if_handle;
-	u32 vf_pmac_id;
-	u16 vf_vlan_tag;
-	u32 vf_tx_rate;
+	unsigned char mac_addr[ETH_ALEN];
+	int if_handle;
+	int pmac_id;
+	u16 vlan_tag;
+	u32 tx_rate;
 };
 
-#define BE_INVALID_PMAC_ID		0xffffffff
-
 struct be_adapter {
 	struct pci_dev *pdev;
 	struct net_device *netdev;
@@ -347,11 +349,13 @@ struct be_adapter {
 
 	/* Ethtool knobs and info */
 	char fw_ver[FW_VER_LEN];
-	u32 if_handle;		/* Used to configure filtering */
+	int if_handle;		/* Used to configure filtering */
 	u32 pmac_id;		/* MAC addr handle used by BE card */
 	u32 beacon_state;	/* for set_phys_id */
 
 	bool eeh_err;
+	bool ue_detected;
+	bool fw_timeout;
 	u32 port_num;
 	bool promiscuous;
 	bool wol;
@@ -359,7 +363,6 @@ struct be_adapter {
 	u32 function_caps;
 	u32 rx_fc;		/* Rx flow control */
 	u32 tx_fc;		/* Tx flow control */
-	bool ue_detected;
 	bool stats_cmd_sent;
 	int link_speed;
 	u8 port_type;
@@ -369,16 +372,20 @@ struct be_adapter {
 	u32 flash_status;
 	struct completion flash_compl;
 
-	bool be3_native;
-	bool sriov_enabled;
-	struct be_vf_cfg *vf_cfg;
+	u32 num_vfs;
 	u8 is_virtfn;
+	struct be_vf_cfg *vf_cfg;
+	bool be3_native;
 	u32 sli_family;
 	u8 hba_port_num;
 	u16 pvid;
 };
 
 #define be_physfn(adapter) (!adapter->is_virtfn)
+#define	sriov_enabled(adapter)		(adapter->num_vfs > 0)
+#define for_all_vfs(adapter, vf_cfg, i)					\
+	for (i = 0, vf_cfg = &adapter->vf_cfg[i]; i < adapter->num_vfs;	\
+		i++, vf_cfg++)
 
 /* BladeEngine Generation numbers */
 #define BE_GEN2 2
@@ -524,6 +531,11 @@ static inline bool be_multi_rxq(const struct be_adapter *adapter)
 	return adapter->num_rx_qs > 1;
 }
 
+static inline bool be_error(struct be_adapter *adapter)
+{
+	return adapter->eeh_err || adapter->ue_detected || adapter->fw_timeout;
+}
+
 extern void be_cq_notify(struct be_adapter *adapter, u16 qid, bool arm,
 		u16 num_popped);
 extern void be_link_status_update(struct be_adapter *adapter, u32 link_status);
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 2c7b366..62868ea 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -31,11 +31,8 @@ static void be_mcc_notify(struct be_adapter *adapter)
 	struct be_queue_info *mccq = &adapter->mcc_obj.q;
 	u32 val = 0;
 
-	if (adapter->eeh_err) {
-		dev_info(&adapter->pdev->dev,
-			"Error in Card Detected! Cannot issue commands\n");
+	if (be_error(adapter))
 		return;
-	}
 
 	val |= mccq->id & DB_MCCQ_RING_ID_MASK;
 	val |= 1 << DB_MCCQ_NUM_POSTED_SHIFT;
@@ -266,10 +263,10 @@ static int be_mcc_wait_compl(struct be_adapter *adapter)
 	int i, num, status = 0;
 	struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
 
-	if (adapter->eeh_err)
-		return -EIO;
-
 	for (i = 0; i < mcc_timeout; i++) {
+		if (be_error(adapter))
+			return -EIO;
+
 		num = be_process_mcc(adapter, &status);
 		if (num)
 			be_cq_notify(adapter, mcc_obj->cq.id,
@@ -280,7 +277,8 @@ static int be_mcc_wait_compl(struct be_adapter *adapter)
 		udelay(100);
 	}
 	if (i == mcc_timeout) {
-		dev_err(&adapter->pdev->dev, "mccq poll timed out\n");
+		dev_err(&adapter->pdev->dev, "FW not responding\n");
+		adapter->fw_timeout = true;
 		return -1;
 	}
 	return status;
@@ -298,26 +296,21 @@ static int be_mbox_db_ready_wait(struct be_adapter *adapter, void __iomem *db)
 	int msecs = 0;
 	u32 ready;
 
-	if (adapter->eeh_err) {
-		dev_err(&adapter->pdev->dev,
-			"Error detected in card.Cannot issue commands\n");
-		return -EIO;
-	}
-
 	do {
+		if (be_error(adapter))
+			return -EIO;
+
 		ready = ioread32(db);
-		if (ready == 0xffffffff) {
-			dev_err(&adapter->pdev->dev,
-				"pci slot disconnected\n");
+		if (ready == 0xffffffff)
 			return -1;
-		}
 
 		ready &= MPU_MAILBOX_DB_RDY_MASK;
 		if (ready)
 			break;
 
 		if (msecs > 4000) {
-			dev_err(&adapter->pdev->dev, "mbox poll timed out\n");
+			dev_err(&adapter->pdev->dev, "FW not responding\n");
+			adapter->fw_timeout = true;
 			be_detect_dump_ue(adapter);
 			return -1;
 		}
@@ -555,9 +548,6 @@ int be_cmd_fw_clean(struct be_adapter *adapter)
 	u8 *wrb;
 	int status;
 
-	if (adapter->eeh_err)
-		return -EIO;
-
 	if (mutex_lock_interruptible(&adapter->mbox_lock))
 		return -1;
 
@@ -619,7 +609,7 @@ int be_cmd_eq_create(struct be_adapter *adapter,
 
 /* Use MCC */
 int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
-			u8 type, bool permanent, u32 if_handle)
+			u8 type, bool permanent, u32 if_handle, u32 pmac_id)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_mac_query *req;
@@ -641,6 +631,7 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
 		req->permanent = 1;
 	} else {
 		req->if_id = cpu_to_le16((u16) if_handle);
+		req->pmac_id = cpu_to_le32(pmac_id);
 		req->permanent = 0;
 	}
 
@@ -695,12 +686,15 @@ err:
 }
 
 /* Uses synchronous MCCQ */
-int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, u32 pmac_id, u32 dom)
+int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, int pmac_id, u32 dom)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_pmac_del *req;
 	int status;
 
+	if (pmac_id == -1)
+		return 0;
+
 	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
@@ -923,10 +917,14 @@ int be_cmd_txq_create(struct be_adapter *adapter,
 	void *ctxt;
 	int status;
 
-	if (mutex_lock_interruptible(&adapter->mbox_lock))
-		return -1;
+	spin_lock_bh(&adapter->mcc_lock);
+
+	wrb = wrb_from_mccq(adapter);
+	if (!wrb) {
+		status = -EBUSY;
+		goto err;
+	}
 
-	wrb = wrb_from_mbox(adapter);
 	req = embedded_payload(wrb);
 	ctxt = &req->context;
 
@@ -952,14 +950,15 @@ int be_cmd_txq_create(struct be_adapter *adapter,
 
 	be_cmd_page_addrs_prepare(req->pages, ARRAY_SIZE(req->pages), q_mem);
 
-	status = be_mbox_notify_wait(adapter);
+	status = be_mcc_notify_wait(adapter);
 	if (!status) {
 		struct be_cmd_resp_eth_tx_create *resp = embedded_payload(wrb);
 		txq->id = le16_to_cpu(resp->cid);
 		txq->created = true;
 	}
 
-	mutex_unlock(&adapter->mbox_lock);
+err:
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	return status;
 }
@@ -1018,9 +1017,6 @@ int be_cmd_q_destroy(struct be_adapter *adapter, struct be_queue_info *q,
 	u8 subsys = 0, opcode = 0;
 	int status;
 
-	if (adapter->eeh_err)
-		return -EIO;
-
 	if (mutex_lock_interruptible(&adapter->mbox_lock))
 		return -1;
 
@@ -1136,16 +1132,13 @@ err:
 }
 
 /* Uses MCCQ */
-int be_cmd_if_destroy(struct be_adapter *adapter, u32 interface_id, u32 domain)
+int be_cmd_if_destroy(struct be_adapter *adapter, int interface_id, u32 domain)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_if_destroy *req;
 	int status;
 
-	if (adapter->eeh_err)
-		return -EIO;
-
-	if (!interface_id)
+	if (interface_id == -1)
 		return 0;
 
 	spin_lock_bh(&adapter->mcc_lock);
@@ -1254,6 +1247,9 @@ int be_cmd_link_status_query(struct be_adapter *adapter, u8 *mac_speed,
 	}
 	req = embedded_payload(wrb);
 
+	if (lancer_chip(adapter))
+		req->hdr.version = 1;
+
 	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
 		OPCODE_COMMON_NTWK_LINK_STATUS_QUERY, sizeof(*req), wrb, NULL);
 
@@ -1673,8 +1669,9 @@ int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable, u16 table_size)
 {
 	struct be_mcc_wrb *wrb;
 	struct be_cmd_req_rss_config *req;
-	u32 myhash[10] = {0x0123, 0x4567, 0x89AB, 0xCDEF, 0x01EF,
-			0x0123, 0x4567, 0x89AB, 0xCDEF, 0x01EF};
+	u32 myhash[10] = {0x15d43fa5, 0x2534685a, 0x5f87693a, 0x5668494e,
+			0x33cf6a53, 0x383334c6, 0x76ac4257, 0x59b242b2,
+			0x3ea83c02, 0x4a110304};
 	int status;
 
 	if (mutex_lock_interruptible(&adapter->mbox_lock))
@@ -1836,6 +1833,53 @@ err_unlock:
 	return status;
 }
 
+int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
+		u32 data_size, u32 data_offset, const char *obj_name,
+		u32 *data_read, u32 *eof, u8 *addn_status)
+{
+	struct be_mcc_wrb *wrb;
+	struct lancer_cmd_req_read_object *req;
+	struct lancer_cmd_resp_read_object *resp;
+	int status;
+
+	spin_lock_bh(&adapter->mcc_lock);
+
+	wrb = wrb_from_mccq(adapter);
+	if (!wrb) {
+		status = -EBUSY;
+		goto err_unlock;
+	}
+
+	req = embedded_payload(wrb);
+
+	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+			OPCODE_COMMON_READ_OBJECT,
+			sizeof(struct lancer_cmd_req_read_object), wrb,
+			NULL);
+
+	req->desired_read_len = cpu_to_le32(data_size);
+	req->read_offset = cpu_to_le32(data_offset);
+	strcpy(req->object_name, obj_name);
+	req->descriptor_count = cpu_to_le32(1);
+	req->buf_len = cpu_to_le32(data_size);
+	req->addr_low = cpu_to_le32((cmd->dma & 0xFFFFFFFF));
+	req->addr_high = cpu_to_le32(upper_32_bits(cmd->dma));
+
+	status = be_mcc_notify_wait(adapter);
+
+	resp = embedded_payload(wrb);
+	if (!status) {
+		*data_read = le32_to_cpu(resp->actual_read_len);
+		*eof = le32_to_cpu(resp->eof);
+	} else {
+		*addn_status = resp->additional_status;
+	}
+
+err_unlock:
+	spin_unlock_bh(&adapter->mcc_lock);
+	return status;
+}
+
 int be_cmd_write_flashrom(struct be_adapter *adapter, struct be_dma_mem *cmd,
 			u32 flash_type, u32 flash_opcode, u32 buf_size)
 {
@@ -2238,3 +2282,99 @@ err:
 	mutex_unlock(&adapter->mbox_lock);
 	return status;
 }
+
+/* Uses synchronous MCCQ */
+int be_cmd_get_mac_from_list(struct be_adapter *adapter, u32 domain,
+							u32 *pmac_id)
+{
+	struct be_mcc_wrb *wrb;
+	struct be_cmd_req_get_mac_list *req;
+	int status;
+	int mac_count;
+
+	spin_lock_bh(&adapter->mcc_lock);
+
+	wrb = wrb_from_mccq(adapter);
+	if (!wrb) {
+		status = -EBUSY;
+		goto err;
+	}
+	req = embedded_payload(wrb);
+
+	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+				OPCODE_COMMON_GET_MAC_LIST, sizeof(*req),
+				wrb, NULL);
+
+	req->hdr.domain = domain;
+
+	status = be_mcc_notify_wait(adapter);
+	if (!status) {
+		struct be_cmd_resp_get_mac_list *resp =
+						embedded_payload(wrb);
+		int i;
+		u8 *ctxt = &resp->context[0][0];
+		status = -EIO;
+		mac_count = resp->mac_count;
+		be_dws_le_to_cpu(&resp->context, sizeof(resp->context));
+		for (i = 0; i < mac_count; i++) {
+			if (!AMAP_GET_BITS(struct amap_get_mac_list_context,
+					   act, ctxt)) {
+				*pmac_id = AMAP_GET_BITS
+					(struct amap_get_mac_list_context,
+					 macid, ctxt);
+				status = 0;
+				break;
+			}
+			ctxt += sizeof(struct amap_get_mac_list_context) / 8;
+		}
+	}
+
+err:
+	spin_unlock_bh(&adapter->mcc_lock);
+	return status;
+}
+
+/* Uses synchronous MCCQ */
+int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
+			u8 mac_count, u32 domain)
+{
+	struct be_mcc_wrb *wrb;
+	struct be_cmd_req_set_mac_list *req;
+	int status;
+	struct be_dma_mem cmd;
+
+	memset(&cmd, 0, sizeof(struct be_dma_mem));
+	cmd.size = sizeof(struct be_cmd_req_set_mac_list);
+	cmd.va = dma_alloc_coherent(&adapter->pdev->dev, cmd.size,
+			&cmd.dma, GFP_KERNEL);
+	if (!cmd.va) {
+		dev_err(&adapter->pdev->dev, "Memory alloc failure\n");
+		return -ENOMEM;
+	}
+
+	spin_lock_bh(&adapter->mcc_lock);
+
+	wrb = wrb_from_mccq(adapter);
+	if (!wrb) {
+		status = -EBUSY;
+		goto err;
+	}
+
+	req = cmd.va;
+	be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+				OPCODE_COMMON_SET_MAC_LIST, sizeof(*req),
+				wrb, &cmd);
+
+	req->hdr.domain = domain;
+	req->mac_count = mac_count;
+	if (mac_count)
+		memcpy(req->mac, mac_array, ETH_ALEN*mac_count);
+
+	status = be_mcc_notify_wait(adapter);
+
+err:
+	dma_free_coherent(&adapter->pdev->dev, cmd.size,
+				cmd.va, cmd.dma);
+	spin_unlock_bh(&adapter->mcc_lock);
+	return status;
+}
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index a35cd03..0b694c6 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -189,6 +189,9 @@ struct be_mcc_mailbox {
 #define OPCODE_COMMON_GET_PHY_DETAILS			102
 #define OPCODE_COMMON_SET_DRIVER_FUNCTION_CAP		103
 #define OPCODE_COMMON_GET_CNTL_ADDITIONAL_ATTRIBUTES	121
+#define OPCODE_COMMON_GET_MAC_LIST			147
+#define OPCODE_COMMON_SET_MAC_LIST			148
+#define OPCODE_COMMON_READ_OBJECT			171
 #define OPCODE_COMMON_WRITE_OBJECT			172
 
 #define OPCODE_ETH_RSS_CONFIG				1
@@ -294,6 +297,7 @@ struct be_cmd_req_mac_query {
 	u8 type;
 	u8 permanent;
 	u16 if_id;
+	u32 pmac_id;
 } __packed;
 
 struct be_cmd_resp_mac_query {
@@ -1161,6 +1165,38 @@ struct lancer_cmd_resp_write_object {
 	u32 actual_write_len;
 };
 
+/************************ Lancer Read FW info **************/
+#define LANCER_READ_FILE_CHUNK			(32*1024)
+#define LANCER_READ_FILE_EOF_MASK		0x80000000
+
+#define LANCER_FW_DUMP_FILE			"/dbg/dump.bin"
+#define LANCER_VPD_PF_FILE			"/vpd/ntr_pf.vpd"
+#define LANCER_VPD_VF_FILE			"/vpd/ntr_vf.vpd"
+
+struct lancer_cmd_req_read_object {
+	struct be_cmd_req_hdr hdr;
+	u32 desired_read_len;
+	u32 read_offset;
+	u8 object_name[104];
+	u32 descriptor_count;
+	u32 buf_len;
+	u32 addr_low;
+	u32 addr_high;
+};
+
+struct lancer_cmd_resp_read_object {
+	u8 opcode;
+	u8 subsystem;
+	u8 rsvd1[2];
+	u8 status;
+	u8 additional_status;
+	u8 rsvd2[2];
+	u32 resp_len;
+	u32 actual_resp_len;
+	u32 actual_read_len;
+	u32 eof;
+};
+
 /************************ WOL *******************************/
 struct be_cmd_req_acpi_wol_magic_config{
 	struct be_cmd_req_hdr hdr;
@@ -1307,6 +1343,34 @@ struct be_cmd_resp_set_func_cap {
 	u8 rsvd[212];
 };
 
+/******************** GET/SET_MACLIST  **************************/
+#define BE_MAX_MAC			64
+struct amap_get_mac_list_context {
+	u8 macid[31];
+	u8 act;
+} __packed;
+
+struct be_cmd_req_get_mac_list {
+	struct be_cmd_req_hdr hdr;
+	u32 rsvd;
+} __packed;
+
+struct be_cmd_resp_get_mac_list {
+	struct be_cmd_resp_hdr hdr;
+	u8 mac_count;
+	u8 rsvd1;
+	u16 rsvd2;
+	u8 context[sizeof(struct amap_get_mac_list_context) / 8][BE_MAX_MAC];
+} __packed;
+
+struct be_cmd_req_set_mac_list {
+	struct be_cmd_req_hdr hdr;
+	u8 mac_count;
+	u8 rsvd1;
+	u16 rsvd2;
+	struct macaddr mac[BE_MAX_MAC];
+} __packed;
+
 /*************** HW Stats Get v1 **********************************/
 #define BE_TXP_SW_SZ			48
 struct be_port_rxf_stats_v1 {
@@ -1413,15 +1477,15 @@ static inline void *be_erx_stats_from_cmd(struct be_adapter *adapter)
 extern int be_pci_fnum_get(struct be_adapter *adapter);
 extern int be_cmd_POST(struct be_adapter *adapter);
 extern int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
-			u8 type, bool permanent, u32 if_handle);
+			u8 type, bool permanent, u32 if_handle, u32 pmac_id);
 extern int be_cmd_pmac_add(struct be_adapter *adapter, u8 *mac_addr,
 			u32 if_id, u32 *pmac_id, u32 domain);
 extern int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id,
-			u32 pmac_id, u32 domain);
+			int pmac_id, u32 domain);
 extern int be_cmd_if_create(struct be_adapter *adapter, u32 cap_flags,
 			u32 en_flags, u8 *mac, u32 *if_handle, u32 *pmac_id,
 			u32 domain);
-extern int be_cmd_if_destroy(struct be_adapter *adapter, u32 if_handle,
+extern int be_cmd_if_destroy(struct be_adapter *adapter, int if_handle,
 			u32 domain);
 extern int be_cmd_eq_create(struct be_adapter *adapter,
 			struct be_queue_info *eq, int eq_delay);
@@ -1480,6 +1544,9 @@ extern int lancer_cmd_write_object(struct be_adapter *adapter,
 				u32 data_size, u32 data_offset,
 				const char *obj_name,
 				u32 *data_written, u8 *addn_status);
+int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
+		u32 data_size, u32 data_offset, const char *obj_name,
+		u32 *data_read, u32 *eof, u8 *addn_status);
 int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc,
 				int offset);
 extern int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac,
@@ -1506,4 +1573,8 @@ extern int be_cmd_get_cntl_attributes(struct be_adapter *adapter);
 extern int be_cmd_req_native_mode(struct be_adapter *adapter);
 extern int be_cmd_get_reg_len(struct be_adapter *adapter, u32 *log_size);
 extern void be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf);
+extern int be_cmd_get_mac_from_list(struct be_adapter *adapter, u32 domain,
+							u32 *pmac_id);
+extern int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
+						u8 mac_count, u32 domain);
 
diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index bf8153e..6ba2dc6 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -127,8 +127,8 @@ static void be_get_drvinfo(struct net_device *netdev,
 	memset(fw_on_flash, 0 , sizeof(fw_on_flash));
 	be_cmd_get_fw_ver(adapter, adapter->fw_ver, fw_on_flash);
 
-	strcpy(drvinfo->driver, DRV_NAME);
-	strcpy(drvinfo->version, DRV_VER);
+	strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, DRV_VER, sizeof(drvinfo->version));
 	strncpy(drvinfo->fw_version, adapter->fw_ver, FW_VER_LEN);
 	if (memcmp(adapter->fw_ver, fw_on_flash, FW_VER_LEN) != 0) {
 		strcat(drvinfo->fw_version, " [");
@@ -136,21 +136,84 @@ static void be_get_drvinfo(struct net_device *netdev,
 		strcat(drvinfo->fw_version, "]");
 	}
 
-	strcpy(drvinfo->bus_info, pci_name(adapter->pdev));
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
 	drvinfo->testinfo_len = 0;
 	drvinfo->regdump_len = 0;
 	drvinfo->eedump_len = 0;
 }
 
+static u32
+lancer_cmd_get_file_len(struct be_adapter *adapter, u8 *file_name)
+{
+	u32 data_read = 0, eof;
+	u8 addn_status;
+	struct be_dma_mem data_len_cmd;
+	int status;
+
+	memset(&data_len_cmd, 0, sizeof(data_len_cmd));
+	/* data_offset and data_size should be 0 to get reg len */
+	status = lancer_cmd_read_object(adapter, &data_len_cmd, 0, 0,
+				file_name, &data_read, &eof, &addn_status);
+
+	return data_read;
+}
+
+static int
+lancer_cmd_read_file(struct be_adapter *adapter, u8 *file_name,
+		u32 buf_len, void *buf)
+{
+	struct be_dma_mem read_cmd;
+	u32 read_len = 0, total_read_len = 0, chunk_size;
+	u32 eof = 0;
+	u8 addn_status;
+	int status = 0;
+
+	read_cmd.size = LANCER_READ_FILE_CHUNK;
+	read_cmd.va = pci_alloc_consistent(adapter->pdev, read_cmd.size,
+			&read_cmd.dma);
+
+	if (!read_cmd.va) {
+		dev_err(&adapter->pdev->dev,
+				"Memory allocation failure while reading dump\n");
+		return -ENOMEM;
+	}
+
+	while ((total_read_len < buf_len) && !eof) {
+		chunk_size = min_t(u32, (buf_len - total_read_len),
+				LANCER_READ_FILE_CHUNK);
+		chunk_size = ALIGN(chunk_size, 4);
+		status = lancer_cmd_read_object(adapter, &read_cmd, chunk_size,
+				total_read_len, file_name, &read_len,
+				&eof, &addn_status);
+		if (!status) {
+			memcpy(buf + total_read_len, read_cmd.va, read_len);
+			total_read_len += read_len;
+			eof &= LANCER_READ_FILE_EOF_MASK;
+		} else {
+			status = -EIO;
+			break;
+		}
+	}
+	pci_free_consistent(adapter->pdev, read_cmd.size, read_cmd.va,
+			read_cmd.dma);
+
+	return status;
+}
+
 static int
 be_get_reg_len(struct net_device *netdev)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 	u32 log_size = 0;
 
-	if (be_physfn(adapter))
-		be_cmd_get_reg_len(adapter, &log_size);
-
+	if (be_physfn(adapter)) {
+		if (lancer_chip(adapter))
+			log_size = lancer_cmd_get_file_len(adapter,
+					LANCER_FW_DUMP_FILE);
+		else
+			be_cmd_get_reg_len(adapter, &log_size);
+	}
 	return log_size;
 }
 
@@ -161,7 +224,11 @@ be_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *buf)
 
 	if (be_physfn(adapter)) {
 		memset(buf, 0, regs->len);
-		be_cmd_get_regs(adapter, regs->len, buf);
+		if (lancer_chip(adapter))
+			lancer_cmd_read_file(adapter, LANCER_FW_DUMP_FILE,
+					regs->len, buf);
+		else
+			be_cmd_get_regs(adapter, regs->len, buf);
 	}
 }
 
@@ -453,16 +520,13 @@ static int be_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
 	return 0;
 }
 
-static void
-be_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring)
+static void be_get_ringparam(struct net_device *netdev,
+			     struct ethtool_ringparam *ring)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 
-	ring->rx_max_pending = adapter->rx_obj[0].q.len;
-	ring->tx_max_pending = adapter->tx_obj[0].q.len;
-
-	ring->rx_pending = atomic_read(&adapter->rx_obj[0].q.used);
-	ring->tx_pending = atomic_read(&adapter->tx_obj[0].q.used);
+	ring->rx_max_pending = ring->rx_pending = adapter->rx_obj[0].q.len;
+	ring->tx_max_pending = ring->tx_pending = adapter->tx_obj[0].q.len;
 }
 
 static void
@@ -660,7 +724,17 @@ be_do_flash(struct net_device *netdev, struct ethtool_flash *efl)
 static int
 be_get_eeprom_len(struct net_device *netdev)
 {
-	return BE_READ_SEEPROM_LEN;
+	struct be_adapter *adapter = netdev_priv(netdev);
+	if (lancer_chip(adapter)) {
+		if (be_physfn(adapter))
+			return lancer_cmd_get_file_len(adapter,
+					LANCER_VPD_PF_FILE);
+		else
+			return lancer_cmd_get_file_len(adapter,
+					LANCER_VPD_VF_FILE);
+	} else {
+		return BE_READ_SEEPROM_LEN;
+	}
 }
 
 static int
@@ -675,6 +749,15 @@ be_read_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom,
 	if (!eeprom->len)
 		return -EINVAL;
 
+	if (lancer_chip(adapter)) {
+		if (be_physfn(adapter))
+			return lancer_cmd_read_file(adapter, LANCER_VPD_PF_FILE,
+					eeprom->len, data);
+		else
+			return lancer_cmd_read_file(adapter, LANCER_VPD_VF_FILE,
+					eeprom->len, data);
+	}
+
 	eeprom->magic = BE_VENDOR_ID | (adapter->pdev->device<<16);
 
 	memset(&eeprom_cmd, 0, sizeof(struct be_dma_mem));
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index bf266a0..b145a49 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -27,13 +27,14 @@ MODULE_DESCRIPTION(DRV_DESC " " DRV_VER);
 MODULE_AUTHOR("ServerEngines Corporation");
 MODULE_LICENSE("GPL");
 
-static ushort rx_frag_size = 2048;
 static unsigned int num_vfs;
-module_param(rx_frag_size, ushort, S_IRUGO);
 module_param(num_vfs, uint, S_IRUGO);
-MODULE_PARM_DESC(rx_frag_size, "Size of a fragment that holds rcvd data.");
 MODULE_PARM_DESC(num_vfs, "Number of PCI VFs to initialize");
 
+static ushort rx_frag_size = 2048;
+module_param(rx_frag_size, ushort, S_IRUGO);
+MODULE_PARM_DESC(rx_frag_size, "Size of a fragment that holds rcvd data.");
+
 static DEFINE_PCI_DEVICE_TABLE(be_dev_ids) = {
 	{ PCI_DEVICE(BE_VENDOR_ID, BE_DEVICE_ID1) },
 	{ PCI_DEVICE(BE_VENDOR_ID, BE_DEVICE_ID2) },
@@ -41,6 +42,7 @@ static DEFINE_PCI_DEVICE_TABLE(be_dev_ids) = {
 	{ PCI_DEVICE(BE_VENDOR_ID, OC_DEVICE_ID2) },
 	{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID3)},
 	{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID4)},
+	{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID5)},
 	{ 0 }
 };
 MODULE_DEVICE_TABLE(pci, be_dev_ids);
@@ -237,7 +239,8 @@ static int be_mac_addr_set(struct net_device *netdev, void *p)
 		return -EADDRNOTAVAIL;
 
 	status = be_cmd_mac_addr_query(adapter, current_mac,
-			MAC_ADDRESS_TYPE_NETWORK, false, adapter->if_handle);
+				MAC_ADDRESS_TYPE_NETWORK, false,
+				adapter->if_handle, 0);
 	if (status)
 		goto err;
 
@@ -315,6 +318,8 @@ static void populate_be3_stats(struct be_adapter *adapter)
 	struct be_drv_stats *drvs = &adapter->drv_stats;
 
 	be_dws_le_to_cpu(hw_stats, sizeof(*hw_stats));
+	drvs->pmem_fifo_overflow_drop = port_stats->pmem_fifo_overflow_drop;
+	drvs->rx_priority_pause_frames = port_stats->rx_priority_pause_frames;
 	drvs->rx_pause_frames = port_stats->rx_pause_frames;
 	drvs->rx_crc_errors = port_stats->rx_crc_errors;
 	drvs->rx_control_frames = port_stats->rx_control_frames;
@@ -549,11 +554,26 @@ static inline void wrb_fill(struct be_eth_wrb *wrb, u64 addr, int len)
 	wrb->frag_len = len & ETH_WRB_FRAG_LEN_MASK;
 }
 
+static inline u16 be_get_tx_vlan_tag(struct be_adapter *adapter,
+					struct sk_buff *skb)
+{
+	u8 vlan_prio;
+	u16 vlan_tag;
+
+	vlan_tag = vlan_tx_tag_get(skb);
+	vlan_prio = (vlan_tag & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+	/* If vlan priority provided by OS is NOT in available bmap */
+	if (!(adapter->vlan_prio_bmap & (1 << vlan_prio)))
+		vlan_tag = (vlan_tag & ~VLAN_PRIO_MASK) |
+				adapter->recommended_prio;
+
+	return vlan_tag;
+}
+
 static void wrb_fill_hdr(struct be_adapter *adapter, struct be_eth_hdr_wrb *hdr,
 		struct sk_buff *skb, u32 wrb_cnt, u32 len)
 {
-	u8 vlan_prio = 0;
-	u16 vlan_tag = 0;
+	u16 vlan_tag;
 
 	memset(hdr, 0, sizeof(*hdr));
 
@@ -584,12 +604,7 @@ static void wrb_fill_hdr(struct be_adapter *adapter, struct be_eth_hdr_wrb *hdr,
 
 	if (vlan_tx_tag_present(skb)) {
 		AMAP_SET_BITS(struct amap_eth_hdr_wrb, vlan, hdr, 1);
-		vlan_tag = vlan_tx_tag_get(skb);
-		vlan_prio = (vlan_tag & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
-		/* If vlan priority provided by OS is NOT in available bmap */
-		if (!(adapter->vlan_prio_bmap & (1 << vlan_prio)))
-			vlan_tag = (vlan_tag & ~VLAN_PRIO_MASK) |
-					adapter->recommended_prio;
+		vlan_tag = be_get_tx_vlan_tag(adapter, skb);
 		AMAP_SET_BITS(struct amap_eth_hdr_wrb, vlan_tag, hdr, vlan_tag);
 	}
 
@@ -692,6 +707,25 @@ static netdev_tx_t be_xmit(struct sk_buff *skb,
 	u32 start = txq->head;
 	bool dummy_wrb, stopped = false;
 
+	/* For vlan tagged pkts, BE
+	 * 1) calculates checksum even when CSO is not requested
+	 * 2) calculates checksum wrongly for padded pkt less than
+	 * 60 bytes long.
+	 * As a workaround disable TX vlan offloading in such cases.
+	 */
+	if (unlikely(vlan_tx_tag_present(skb) &&
+		     (skb->ip_summed != CHECKSUM_PARTIAL || skb->len <= 60))) {
+		skb = skb_share_check(skb, GFP_ATOMIC);
+		if (unlikely(!skb))
+			goto tx_drop;
+
+		skb = __vlan_put_tag(skb, be_get_tx_vlan_tag(adapter, skb));
+		if (unlikely(!skb))
+			goto tx_drop;
+
+		skb->vlan_tci = 0;
+	}
+
 	wrb_cnt = wrb_cnt_for_skb(adapter, skb, &dummy_wrb);
 
 	copied = make_tx_wrbs(adapter, txq, skb, wrb_cnt, dummy_wrb);
@@ -719,6 +753,7 @@ static netdev_tx_t be_xmit(struct sk_buff *skb,
 		txq->head = start;
 		dev_kfree_skb_any(skb);
 	}
+tx_drop:
 	return NETDEV_TX_OK;
 }
 
@@ -746,15 +781,15 @@ static int be_change_mtu(struct net_device *netdev, int new_mtu)
  */
 static int be_vid_config(struct be_adapter *adapter, bool vf, u32 vf_num)
 {
+	struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf_num];
 	u16 vtag[BE_NUM_VLANS_SUPPORTED];
 	u16 ntags = 0, i;
 	int status = 0;
-	u32 if_handle;
 
 	if (vf) {
-		if_handle = adapter->vf_cfg[vf_num].vf_if_handle;
-		vtag[0] = cpu_to_le16(adapter->vf_cfg[vf_num].vf_vlan_tag);
-		status = be_cmd_vlan_config(adapter, if_handle, vtag, 1, 1, 0);
+		vtag[0] = cpu_to_le16(vf_cfg->vlan_tag);
+		status = be_cmd_vlan_config(adapter, vf_cfg->if_handle, vtag,
+					    1, 1, 0);
 	}
 
 	/* No need to further configure vids if in promiscuous mode */
@@ -779,31 +814,35 @@ static int be_vid_config(struct be_adapter *adapter, bool vf, u32 vf_num)
 	return status;
 }
 
-static void be_vlan_add_vid(struct net_device *netdev, u16 vid)
+static int be_vlan_add_vid(struct net_device *netdev, u16 vid)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 
 	adapter->vlans_added++;
 	if (!be_physfn(adapter))
-		return;
+		return 0;
 
 	adapter->vlan_tag[vid] = 1;
 	if (adapter->vlans_added <= (adapter->max_vlans + 1))
 		be_vid_config(adapter, false, 0);
+
+	return 0;
 }
 
-static void be_vlan_rem_vid(struct net_device *netdev, u16 vid)
+static int be_vlan_rem_vid(struct net_device *netdev, u16 vid)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 
 	adapter->vlans_added--;
 
 	if (!be_physfn(adapter))
-		return;
+		return 0;
 
 	adapter->vlan_tag[vid] = 0;
 	if (adapter->vlans_added <= adapter->max_vlans)
 		be_vid_config(adapter, false, 0);
+
+	return 0;
 }
 
 static void be_set_rx_mode(struct net_device *netdev)
@@ -840,28 +879,30 @@ done:
 static int be_set_vf_mac(struct net_device *netdev, int vf, u8 *mac)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
+	struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf];
 	int status;
 
-	if (!adapter->sriov_enabled)
+	if (!sriov_enabled(adapter))
 		return -EPERM;
 
-	if (!is_valid_ether_addr(mac) || (vf >= num_vfs))
+	if (!is_valid_ether_addr(mac) || vf >= adapter->num_vfs)
 		return -EINVAL;
 
-	if (adapter->vf_cfg[vf].vf_pmac_id != BE_INVALID_PMAC_ID)
-		status = be_cmd_pmac_del(adapter,
-					adapter->vf_cfg[vf].vf_if_handle,
-					adapter->vf_cfg[vf].vf_pmac_id, vf + 1);
+	if (lancer_chip(adapter)) {
+		status = be_cmd_set_mac_list(adapter,  mac, 1, vf + 1);
+	} else {
+		status = be_cmd_pmac_del(adapter, vf_cfg->if_handle,
+					 vf_cfg->pmac_id, vf + 1);
 
-	status = be_cmd_pmac_add(adapter, mac,
-				adapter->vf_cfg[vf].vf_if_handle,
-				&adapter->vf_cfg[vf].vf_pmac_id, vf + 1);
+		status = be_cmd_pmac_add(adapter, mac, vf_cfg->if_handle,
+					 &vf_cfg->pmac_id, vf + 1);
+	}
 
 	if (status)
 		dev_err(&adapter->pdev->dev, "MAC %pM set on VF %d Failed\n",
 				mac, vf);
 	else
-		memcpy(adapter->vf_cfg[vf].vf_mac_addr, mac, ETH_ALEN);
+		memcpy(vf_cfg->mac_addr, mac, ETH_ALEN);
 
 	return status;
 }
@@ -870,18 +911,19 @@ static int be_get_vf_config(struct net_device *netdev, int vf,
 			struct ifla_vf_info *vi)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
+	struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf];
 
-	if (!adapter->sriov_enabled)
+	if (!sriov_enabled(adapter))
 		return -EPERM;
 
-	if (vf >= num_vfs)
+	if (vf >= adapter->num_vfs)
 		return -EINVAL;
 
 	vi->vf = vf;
-	vi->tx_rate = adapter->vf_cfg[vf].vf_tx_rate;
-	vi->vlan = adapter->vf_cfg[vf].vf_vlan_tag;
+	vi->tx_rate = vf_cfg->tx_rate;
+	vi->vlan = vf_cfg->vlan_tag;
 	vi->qos = 0;
-	memcpy(&vi->mac, adapter->vf_cfg[vf].vf_mac_addr, ETH_ALEN);
+	memcpy(&vi->mac, vf_cfg->mac_addr, ETH_ALEN);
 
 	return 0;
 }
@@ -892,17 +934,17 @@ static int be_set_vf_vlan(struct net_device *netdev,
 	struct be_adapter *adapter = netdev_priv(netdev);
 	int status = 0;
 
-	if (!adapter->sriov_enabled)
+	if (!sriov_enabled(adapter))
 		return -EPERM;
 
-	if ((vf >= num_vfs) || (vlan > 4095))
+	if (vf >= adapter->num_vfs || vlan > 4095)
 		return -EINVAL;
 
 	if (vlan) {
-		adapter->vf_cfg[vf].vf_vlan_tag = vlan;
+		adapter->vf_cfg[vf].vlan_tag = vlan;
 		adapter->vlans_added++;
 	} else {
-		adapter->vf_cfg[vf].vf_vlan_tag = 0;
+		adapter->vf_cfg[vf].vlan_tag = 0;
 		adapter->vlans_added--;
 	}
 
@@ -920,16 +962,16 @@ static int be_set_vf_tx_rate(struct net_device *netdev,
 	struct be_adapter *adapter = netdev_priv(netdev);
 	int status = 0;
 
-	if (!adapter->sriov_enabled)
+	if (!sriov_enabled(adapter))
 		return -EPERM;
 
-	if ((vf >= num_vfs) || (rate < 0))
+	if (vf >= adapter->num_vfs || rate < 0)
 		return -EINVAL;
 
 	if (rate > 10000)
 		rate = 10000;
 
-	adapter->vf_cfg[vf].vf_tx_rate = rate;
+	adapter->vf_cfg[vf].tx_rate = rate;
 	status = be_cmd_set_qos(adapter, rate / 10, vf + 1);
 
 	if (status)
@@ -1645,8 +1687,7 @@ static void be_tx_queues_destroy(struct be_adapter *adapter)
 
 static int be_num_txqs_want(struct be_adapter *adapter)
 {
-	if ((num_vfs && adapter->sriov_enabled) ||
-		be_is_mc(adapter) ||
+	if (sriov_enabled(adapter) || be_is_mc(adapter) ||
 		lancer_chip(adapter) || !be_physfn(adapter) ||
 		adapter->generation == BE_GEN2)
 		return 1;
@@ -1662,9 +1703,12 @@ static int be_tx_queues_create(struct be_adapter *adapter)
 	u8 i;
 
 	adapter->num_tx_qs = be_num_txqs_want(adapter);
-	if (adapter->num_tx_qs != MAX_TX_QS)
+	if (adapter->num_tx_qs != MAX_TX_QS) {
+		rtnl_lock();
 		netif_set_real_num_tx_queues(adapter->netdev,
 			adapter->num_tx_qs);
+		rtnl_unlock();
+	}
 
 	adapter->tx_eq.max_eqd = 0;
 	adapter->tx_eq.min_eqd = 0;
@@ -1693,9 +1737,6 @@ static int be_tx_queues_create(struct be_adapter *adapter)
 		if (be_queue_alloc(adapter, q, TX_Q_LEN,
 			sizeof(struct be_eth_wrb)))
 			goto err;
-
-		if (be_cmd_txq_create(adapter, q, cq))
-			goto err;
 	}
 	return 0;
 
@@ -1728,8 +1769,8 @@ static void be_rx_queues_destroy(struct be_adapter *adapter)
 static u32 be_num_rxqs_want(struct be_adapter *adapter)
 {
 	if ((adapter->function_caps & BE_FUNCTION_CAPS_RSS) &&
-		!adapter->sriov_enabled && be_physfn(adapter) &&
-		!be_is_mc(adapter)) {
+	     !sriov_enabled(adapter) && be_physfn(adapter) &&
+	     !be_is_mc(adapter)) {
 		return 1 + MAX_RSS_QS; /* one default non-RSS queue */
 	} else {
 		dev_warn(&adapter->pdev->dev,
@@ -1982,6 +2023,9 @@ void be_detect_dump_ue(struct be_adapter *adapter)
 	u32 sliport_status = 0, sliport_err1 = 0, sliport_err2 = 0;
 	u32 i;
 
+	if (adapter->eeh_err || adapter->ue_detected)
+		return;
+
 	if (lancer_chip(adapter)) {
 		sliport_status = ioread32(adapter->db + SLIPORT_STATUS_OFFSET);
 		if (sliport_status & SLIPORT_STATUS_ERR_MASK) {
@@ -2008,7 +2052,8 @@ void be_detect_dump_ue(struct be_adapter *adapter)
 		sliport_status & SLIPORT_STATUS_ERR_MASK) {
 		adapter->ue_detected = true;
 		adapter->eeh_err = true;
-		dev_err(&adapter->pdev->dev, "UE Detected!!\n");
+		dev_err(&adapter->pdev->dev,
+			"Unrecoverable error in the card\n");
 	}
 
 	if (ue_lo) {
@@ -2036,53 +2081,6 @@ void be_detect_dump_ue(struct be_adapter *adapter)
 	}
 }
 
-static void be_worker(struct work_struct *work)
-{
-	struct be_adapter *adapter =
-		container_of(work, struct be_adapter, work.work);
-	struct be_rx_obj *rxo;
-	int i;
-
-	if (!adapter->ue_detected)
-		be_detect_dump_ue(adapter);
-
-	/* when interrupts are not yet enabled, just reap any pending
-	* mcc completions */
-	if (!netif_running(adapter->netdev)) {
-		int mcc_compl, status = 0;
-
-		mcc_compl = be_process_mcc(adapter, &status);
-
-		if (mcc_compl) {
-			struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
-			be_cq_notify(adapter, mcc_obj->cq.id, false, mcc_compl);
-		}
-
-		goto reschedule;
-	}
-
-	if (!adapter->stats_cmd_sent) {
-		if (lancer_chip(adapter))
-			lancer_cmd_get_pport_stats(adapter,
-						&adapter->stats_cmd);
-		else
-			be_cmd_get_stats(adapter, &adapter->stats_cmd);
-	}
-
-	for_all_rx_queues(adapter, rxo, i) {
-		be_rx_eqd_update(adapter, rxo);
-
-		if (rxo->rx_post_starved) {
-			rxo->rx_post_starved = false;
-			be_post_rx_frags(rxo, GFP_KERNEL);
-		}
-	}
-
-reschedule:
-	adapter->work_counter++;
-	schedule_delayed_work(&adapter->work, msecs_to_jiffies(1000));
-}
-
 static void be_msix_disable(struct be_adapter *adapter)
 {
 	if (msix_enabled(adapter)) {
@@ -2119,27 +2117,28 @@ done:
 static int be_sriov_enable(struct be_adapter *adapter)
 {
 	be_check_sriov_fn_type(adapter);
+
 #ifdef CONFIG_PCI_IOV
 	if (be_physfn(adapter) && num_vfs) {
 		int status, pos;
-		u16 nvfs;
+		u16 dev_vfs;
 
 		pos = pci_find_ext_capability(adapter->pdev,
 						PCI_EXT_CAP_ID_SRIOV);
 		pci_read_config_word(adapter->pdev,
-					pos + PCI_SRIOV_TOTAL_VF, &nvfs);
+				     pos + PCI_SRIOV_TOTAL_VF, &dev_vfs);
 
-		if (num_vfs > nvfs) {
+		adapter->num_vfs = min_t(u16, num_vfs, dev_vfs);
+		if (adapter->num_vfs != num_vfs)
 			dev_info(&adapter->pdev->dev,
-					"Device supports %d VFs and not %d\n",
-					nvfs, num_vfs);
-			num_vfs = nvfs;
-		}
+				 "Device supports %d VFs and not %d\n",
+				 adapter->num_vfs, num_vfs);
 
-		status = pci_enable_sriov(adapter->pdev, num_vfs);
-		adapter->sriov_enabled = status ? false : true;
+		status = pci_enable_sriov(adapter->pdev, adapter->num_vfs);
+		if (status)
+			adapter->num_vfs = 0;
 
-		if (adapter->sriov_enabled) {
+		if (adapter->num_vfs) {
 			adapter->vf_cfg = kcalloc(num_vfs,
 						sizeof(struct be_vf_cfg),
 						GFP_KERNEL);
@@ -2154,10 +2153,10 @@ static int be_sriov_enable(struct be_adapter *adapter)
 static void be_sriov_disable(struct be_adapter *adapter)
 {
 #ifdef CONFIG_PCI_IOV
-	if (adapter->sriov_enabled) {
+	if (sriov_enabled(adapter)) {
 		pci_disable_sriov(adapter->pdev);
 		kfree(adapter->vf_cfg);
-		adapter->sriov_enabled = false;
+		adapter->num_vfs = 0;
 	}
 #endif
 }
@@ -2351,8 +2350,8 @@ static int be_close(struct net_device *netdev)
 static int be_rx_queues_setup(struct be_adapter *adapter)
 {
 	struct be_rx_obj *rxo;
-	int rc, i;
-	u8 rsstable[MAX_RSS_QS];
+	int rc, i, j;
+	u8 rsstable[128];
 
 	for_all_rx_queues(adapter, rxo, i) {
 		rc = be_cmd_rxq_create(adapter, &rxo->q, rxo->cq.id,
@@ -2364,11 +2363,15 @@ static int be_rx_queues_setup(struct be_adapter *adapter)
 	}
 
 	if (be_multi_rxq(adapter)) {
-		for_all_rss_queues(adapter, rxo, i)
-			rsstable[i] = rxo->rss_id;
+		for (j = 0; j < 128; j += adapter->num_rx_qs - 1) {
+			for_all_rss_queues(adapter, rxo, i) {
+				if ((j + i) >= 128)
+					break;
+				rsstable[j + i] = rxo->rss_id;
+			}
+		}
+		rc = be_cmd_rss_config(adapter, rsstable, 128);
 
-		rc = be_cmd_rss_config(adapter, rsstable,
-			adapter->num_rx_qs - 1);
 		if (rc)
 			return rc;
 	}
@@ -2465,19 +2468,24 @@ static inline int be_vf_eth_addr_config(struct be_adapter *adapter)
 	u32 vf;
 	int status = 0;
 	u8 mac[ETH_ALEN];
+	struct be_vf_cfg *vf_cfg;
 
 	be_vf_eth_addr_generate(adapter, mac);
 
-	for (vf = 0; vf < num_vfs; vf++) {
-		status = be_cmd_pmac_add(adapter, mac,
-					adapter->vf_cfg[vf].vf_if_handle,
-					&adapter->vf_cfg[vf].vf_pmac_id,
-					vf + 1);
+	for_all_vfs(adapter, vf_cfg, vf) {
+		if (lancer_chip(adapter)) {
+			status = be_cmd_set_mac_list(adapter,  mac, 1, vf + 1);
+		} else {
+			status = be_cmd_pmac_add(adapter, mac,
+						 vf_cfg->if_handle,
+						 &vf_cfg->pmac_id, vf + 1);
+		}
+
 		if (status)
 			dev_err(&adapter->pdev->dev,
-				"Mac address add failed for VF %d\n", vf);
+			"Mac address assignment failed for VF %d\n", vf);
 		else
-			memcpy(adapter->vf_cfg[vf].vf_mac_addr, mac, ETH_ALEN);
+			memcpy(vf_cfg->mac_addr, mac, ETH_ALEN);
 
 		mac[5] += 1;
 	}
@@ -2486,24 +2494,23 @@ static inline int be_vf_eth_addr_config(struct be_adapter *adapter)
 
 static void be_vf_clear(struct be_adapter *adapter)
 {
+	struct be_vf_cfg *vf_cfg;
 	u32 vf;
 
-	for (vf = 0; vf < num_vfs; vf++) {
-		if (adapter->vf_cfg[vf].vf_pmac_id != BE_INVALID_PMAC_ID)
-			be_cmd_pmac_del(adapter,
-					adapter->vf_cfg[vf].vf_if_handle,
-					adapter->vf_cfg[vf].vf_pmac_id, vf + 1);
-	}
+	for_all_vfs(adapter, vf_cfg, vf) {
+		if (lancer_chip(adapter))
+			be_cmd_set_mac_list(adapter, NULL, 0, vf + 1);
+		else
+			be_cmd_pmac_del(adapter, vf_cfg->if_handle,
+					vf_cfg->pmac_id, vf + 1);
 
-	for (vf = 0; vf < num_vfs; vf++)
-		if (adapter->vf_cfg[vf].vf_if_handle)
-			be_cmd_if_destroy(adapter,
-				adapter->vf_cfg[vf].vf_if_handle, vf + 1);
+		be_cmd_if_destroy(adapter, vf_cfg->if_handle, vf + 1);
+	}
 }
 
 static int be_clear(struct be_adapter *adapter)
 {
-	if (be_physfn(adapter) && adapter->sriov_enabled)
+	if (sriov_enabled(adapter))
 		be_vf_clear(adapter);
 
 	be_cmd_if_destroy(adapter, adapter->if_handle,  0);
@@ -2511,61 +2518,94 @@ static int be_clear(struct be_adapter *adapter)
 	be_mcc_queues_destroy(adapter);
 	be_rx_queues_destroy(adapter);
 	be_tx_queues_destroy(adapter);
-	adapter->eq_next_idx = 0;
-
-	adapter->be3_native = false;
-	adapter->promiscuous = false;
 
 	/* tell fw we're done with firing cmds */
 	be_cmd_fw_clean(adapter);
 	return 0;
 }
 
+static void be_vf_setup_init(struct be_adapter *adapter)
+{
+	struct be_vf_cfg *vf_cfg;
+	int vf;
+
+	for_all_vfs(adapter, vf_cfg, vf) {
+		vf_cfg->if_handle = -1;
+		vf_cfg->pmac_id = -1;
+	}
+}
+
 static int be_vf_setup(struct be_adapter *adapter)
 {
+	struct be_vf_cfg *vf_cfg;
 	u32 cap_flags, en_flags, vf;
 	u16 lnk_speed;
 	int status;
 
-	cap_flags = en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST;
-	for (vf = 0; vf < num_vfs; vf++) {
+	be_vf_setup_init(adapter);
+
+	cap_flags = en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
+				BE_IF_FLAGS_MULTICAST;
+	for_all_vfs(adapter, vf_cfg, vf) {
 		status = be_cmd_if_create(adapter, cap_flags, en_flags, NULL,
-					&adapter->vf_cfg[vf].vf_if_handle,
-					NULL, vf+1);
+					  &vf_cfg->if_handle, NULL, vf + 1);
 		if (status)
 			goto err;
-		adapter->vf_cfg[vf].vf_pmac_id = BE_INVALID_PMAC_ID;
 	}
 
-	if (!lancer_chip(adapter)) {
-		status = be_vf_eth_addr_config(adapter);
-		if (status)
-			goto err;
-	}
+	status = be_vf_eth_addr_config(adapter);
+	if (status)
+		goto err;
 
-	for (vf = 0; vf < num_vfs; vf++) {
+	for_all_vfs(adapter, vf_cfg, vf) {
 		status = be_cmd_link_status_query(adapter, NULL, &lnk_speed,
-				vf + 1);
+						  vf + 1);
 		if (status)
 			goto err;
-		adapter->vf_cfg[vf].vf_tx_rate = lnk_speed * 10;
+		vf_cfg->tx_rate = lnk_speed * 10;
 	}
 	return 0;
 err:
 	return status;
 }
 
+static void be_setup_init(struct be_adapter *adapter)
+{
+	adapter->vlan_prio_bmap = 0xff;
+	adapter->link_speed = -1;
+	adapter->if_handle = -1;
+	adapter->be3_native = false;
+	adapter->promiscuous = false;
+	adapter->eq_next_idx = 0;
+}
+
+static int be_configure_mac_from_list(struct be_adapter *adapter, u8 *mac)
+{
+	u32 pmac_id;
+	int status = be_cmd_get_mac_from_list(adapter, 0, &pmac_id);
+	if (status != 0)
+		goto do_none;
+	status = be_cmd_mac_addr_query(adapter, mac,
+			MAC_ADDRESS_TYPE_NETWORK,
+			false, adapter->if_handle, pmac_id);
+	if (status != 0)
+		goto do_none;
+	status = be_cmd_pmac_add(adapter, mac, adapter->if_handle,
+			&adapter->pmac_id, 0);
+do_none:
+	return status;
+}
+
 static int be_setup(struct be_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
 	u32 cap_flags, en_flags;
 	u32 tx_fc, rx_fc;
-	int status;
+	int status, i;
 	u8 mac[ETH_ALEN];
+	struct be_tx_obj *txo;
 
-	/* Allow all priorities by default. A GRP5 evt may modify this */
-	adapter->vlan_prio_bmap = 0xff;
-	adapter->link_speed = -1;
+	be_setup_init(adapter);
 
 	be_cmd_req_native_mode(adapter);
 
@@ -2583,7 +2623,7 @@ static int be_setup(struct be_adapter *adapter)
 
 	memset(mac, 0, ETH_ALEN);
 	status = be_cmd_mac_addr_query(adapter, mac, MAC_ADDRESS_TYPE_NETWORK,
-			true /*permanent */, 0);
+			true /*permanent */, 0, 0);
 	if (status)
 		return status;
 	memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN);
@@ -2592,7 +2632,8 @@ static int be_setup(struct be_adapter *adapter)
 	en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
 			BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS;
 	cap_flags = en_flags | BE_IF_FLAGS_MCAST_PROMISCUOUS |
-			BE_IF_FLAGS_PROMISCUOUS;
+			BE_IF_FLAGS_VLAN_PROMISCUOUS | BE_IF_FLAGS_PROMISCUOUS;
+
 	if (adapter->function_caps & BE_FUNCTION_CAPS_RSS) {
 		cap_flags |= BE_IF_FLAGS_RSS;
 		en_flags |= BE_IF_FLAGS_RSS;
@@ -2603,12 +2644,23 @@ static int be_setup(struct be_adapter *adapter)
 	if (status != 0)
 		goto err;
 
-	/* For BEx, the VF's permanent mac queried from card is incorrect.
-	 * Query the mac configued by the PF using if_handle
-	 */
-	if (!be_physfn(adapter) && !lancer_chip(adapter)) {
-		status = be_cmd_mac_addr_query(adapter, mac,
-			MAC_ADDRESS_TYPE_NETWORK, false, adapter->if_handle);
+	 for_all_tx_queues(adapter, txo, i) {
+		status = be_cmd_txq_create(adapter, &txo->q, &txo->cq);
+		if (status)
+			goto err;
+	}
+
+	 /* The VF's permanent mac queried from card is incorrect.
+	  * For BEx: Query the mac configued by the PF using if_handle
+	  * For Lancer: Get and use mac_list to obtain mac address.
+	  */
+	if (!be_physfn(adapter)) {
+		if (lancer_chip(adapter))
+			status = be_configure_mac_from_list(adapter, mac);
+		else
+			status = be_cmd_mac_addr_query(adapter, mac,
+					MAC_ADDRESS_TYPE_NETWORK, false,
+					adapter->if_handle, 0);
 		if (!status) {
 			memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN);
 			memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN);
@@ -2624,18 +2676,21 @@ static int be_setup(struct be_adapter *adapter)
 	be_set_rx_mode(adapter->netdev);
 
 	status = be_cmd_get_flow_control(adapter, &tx_fc, &rx_fc);
-	if (status)
+	/* For Lancer: It is legal for this cmd to fail on VF */
+	if (status && (be_physfn(adapter) || !lancer_chip(adapter)))
 		goto err;
+
 	if (rx_fc != adapter->rx_fc || tx_fc != adapter->tx_fc) {
 		status = be_cmd_set_flow_control(adapter, adapter->tx_fc,
 					adapter->rx_fc);
-		if (status)
+		/* For Lancer: It is legal for this cmd to fail on VF */
+		if (status && (be_physfn(adapter) || !lancer_chip(adapter)))
 			goto err;
 	}
 
 	pcie_set_readrq(adapter->pdev, 4096);
 
-	if (be_physfn(adapter) && adapter->sriov_enabled) {
+	if (sriov_enabled(adapter)) {
 		status = be_vf_setup(adapter);
 		if (status)
 			goto err;
@@ -2647,6 +2702,19 @@ err:
 	return status;
 }
 
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void be_netpoll(struct net_device *netdev)
+{
+	struct be_adapter *adapter = netdev_priv(netdev);
+	struct be_rx_obj *rxo;
+	int i;
+
+	event_handle(adapter, &adapter->tx_eq, false);
+	for_all_rx_queues(adapter, rxo, i)
+		event_handle(adapter, &rxo->rx_eq, true);
+}
+#endif
+
 #define FW_FILE_HDR_SIGN 	"ServerEngines Corp. "
 static bool be_flash_redboot(struct be_adapter *adapter,
 			const u8 *p, u32 img_start, int image_size,
@@ -2995,7 +3063,10 @@ static struct net_device_ops be_netdev_ops = {
 	.ndo_set_vf_mac		= be_set_vf_mac,
 	.ndo_set_vf_vlan	= be_set_vf_vlan,
 	.ndo_set_vf_tx_rate	= be_set_vf_tx_rate,
-	.ndo_get_vf_config	= be_get_vf_config
+	.ndo_get_vf_config	= be_get_vf_config,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= be_netpoll,
+#endif
 };
 
 static void be_netdev_init(struct net_device *netdev)
@@ -3242,6 +3313,7 @@ static int be_dev_family_check(struct be_adapter *adapter)
 		break;
 	case BE_DEVICE_ID2:
 	case OC_DEVICE_ID2:
+	case OC_DEVICE_ID5:
 		adapter->generation = BE_GEN3;
 		break;
 	case OC_DEVICE_ID3:
@@ -3267,7 +3339,7 @@ static int be_dev_family_check(struct be_adapter *adapter)
 
 static int lancer_wait_ready(struct be_adapter *adapter)
 {
-#define SLIPORT_READY_TIMEOUT 500
+#define SLIPORT_READY_TIMEOUT 30
 	u32 sliport_status;
 	int status = 0, i;
 
@@ -3276,7 +3348,7 @@ static int lancer_wait_ready(struct be_adapter *adapter)
 		if (sliport_status & SLIPORT_STATUS_RDY_MASK)
 			break;
 
-		msleep(20);
+		msleep(1000);
 	}
 
 	if (i == SLIPORT_READY_TIMEOUT)
@@ -3313,6 +3385,104 @@ static int lancer_test_and_set_rdy_state(struct be_adapter *adapter)
 	return status;
 }
 
+static void lancer_test_and_recover_fn_err(struct be_adapter *adapter)
+{
+	int status;
+	u32 sliport_status;
+
+	if (adapter->eeh_err || adapter->ue_detected)
+		return;
+
+	sliport_status = ioread32(adapter->db + SLIPORT_STATUS_OFFSET);
+
+	if (sliport_status & SLIPORT_STATUS_ERR_MASK) {
+		dev_err(&adapter->pdev->dev,
+				"Adapter in error state."
+				"Trying to recover.\n");
+
+		status = lancer_test_and_set_rdy_state(adapter);
+		if (status)
+			goto err;
+
+		netif_device_detach(adapter->netdev);
+
+		if (netif_running(adapter->netdev))
+			be_close(adapter->netdev);
+
+		be_clear(adapter);
+
+		adapter->fw_timeout = false;
+
+		status = be_setup(adapter);
+		if (status)
+			goto err;
+
+		if (netif_running(adapter->netdev)) {
+			status = be_open(adapter->netdev);
+			if (status)
+				goto err;
+		}
+
+		netif_device_attach(adapter->netdev);
+
+		dev_err(&adapter->pdev->dev,
+				"Adapter error recovery succeeded\n");
+	}
+	return;
+err:
+	dev_err(&adapter->pdev->dev,
+			"Adapter error recovery failed\n");
+}
+
+static void be_worker(struct work_struct *work)
+{
+	struct be_adapter *adapter =
+		container_of(work, struct be_adapter, work.work);
+	struct be_rx_obj *rxo;
+	int i;
+
+	if (lancer_chip(adapter))
+		lancer_test_and_recover_fn_err(adapter);
+
+	be_detect_dump_ue(adapter);
+
+	/* when interrupts are not yet enabled, just reap any pending
+	* mcc completions */
+	if (!netif_running(adapter->netdev)) {
+		int mcc_compl, status = 0;
+
+		mcc_compl = be_process_mcc(adapter, &status);
+
+		if (mcc_compl) {
+			struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
+			be_cq_notify(adapter, mcc_obj->cq.id, false, mcc_compl);
+		}
+
+		goto reschedule;
+	}
+
+	if (!adapter->stats_cmd_sent) {
+		if (lancer_chip(adapter))
+			lancer_cmd_get_pport_stats(adapter,
+						&adapter->stats_cmd);
+		else
+			be_cmd_get_stats(adapter, &adapter->stats_cmd);
+	}
+
+	for_all_rx_queues(adapter, rxo, i) {
+		be_rx_eqd_update(adapter, rxo);
+
+		if (rxo->rx_post_starved) {
+			rxo->rx_post_starved = false;
+			be_post_rx_frags(rxo, GFP_KERNEL);
+		}
+	}
+
+reschedule:
+	adapter->work_counter++;
+	schedule_delayed_work(&adapter->work, msecs_to_jiffies(1000));
+}
+
 static int __devinit be_probe(struct pci_dev *pdev,
 			const struct pci_device_id *pdev_id)
 {
@@ -3365,7 +3535,12 @@ static int __devinit be_probe(struct pci_dev *pdev,
 		goto disable_sriov;
 
 	if (lancer_chip(adapter)) {
-		status = lancer_test_and_set_rdy_state(adapter);
+		status = lancer_wait_ready(adapter);
+		if (!status) {
+			iowrite32(SLI_PORT_CONTROL_IP_MASK,
+					adapter->db + SLIPORT_CONTROL_OFFSET);
+			status = lancer_test_and_set_rdy_state(adapter);
+		}
 		if (status) {
 			dev_err(&pdev->dev, "Adapter in non recoverable error\n");
 			goto ctrl_clean;
@@ -3559,6 +3734,8 @@ static pci_ers_result_t be_eeh_reset(struct pci_dev *pdev)
 
 	dev_info(&adapter->pdev->dev, "EEH reset\n");
 	adapter->eeh_err = false;
+	adapter->ue_detected = false;
+	adapter->fw_timeout = false;
 
 	status = pci_enable_device(pdev);
 	if (status)
diff --git a/drivers/net/ethernet/ethoc.c b/drivers/net/ethernet/ethoc.c
index 251b635..60f0e78 100644
--- a/drivers/net/ethernet/ethoc.c
+++ b/drivers/net/ethernet/ethoc.c
@@ -1185,18 +1185,7 @@ static struct platform_driver ethoc_driver = {
 	},
 };
 
-static int __init ethoc_init(void)
-{
-	return platform_driver_register(&ethoc_driver);
-}
-
-static void __exit ethoc_exit(void)
-{
-	platform_driver_unregister(&ethoc_driver);
-}
-
-module_init(ethoc_init);
-module_exit(ethoc_exit);
+module_platform_driver(ethoc_driver);
 
 MODULE_AUTHOR("Thierry Reding <thierry.reding@avionic-design.de>");
 MODULE_DESCRIPTION("OpenCores Ethernet MAC driver");
diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c
index 61d2bdd..c82d444 100644
--- a/drivers/net/ethernet/fealnx.c
+++ b/drivers/net/ethernet/fealnx.c
@@ -1818,9 +1818,9 @@ static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *i
 {
 	struct netdev_private *np = netdev_priv(dev);
 
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->bus_info, pci_name(np->pci_dev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
 }
 
 static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig
index c520cfd..820de8b 100644
--- a/drivers/net/ethernet/freescale/Kconfig
+++ b/drivers/net/ethernet/freescale/Kconfig
@@ -21,9 +21,10 @@ config NET_VENDOR_FREESCALE
 if NET_VENDOR_FREESCALE
 
 config FEC
-	bool "FEC ethernet controller (of ColdFire and some i.MX CPUs)"
+	tristate "FEC ethernet controller (of ColdFire and some i.MX CPUs)"
 	depends on (M523x || M527x || M5272 || M528x || M520x || M532x || \
 		   ARCH_MXC || ARCH_MXS)
+	default ARCH_MXC || ARCH_MXS if ARM
 	select PHYLIB
 	---help---
 	  Say Y here if you want to use the built-in 10/100 Fast ethernet
diff --git a/drivers/net/ethernet/freescale/fec.c b/drivers/net/ethernet/freescale/fec.c
index 1124ce0..4ea2bdc 100644
--- a/drivers/net/ethernet/freescale/fec.c
+++ b/drivers/net/ethernet/freescale/fec.c
@@ -99,7 +99,7 @@ static struct platform_device_id fec_devtype[] = {
 MODULE_DEVICE_TABLE(platform, fec_devtype);
 
 enum imx_fec_type {
-	IMX25_FEC = 1, 	/* runs on i.mx25/50/53 */
+	IMX25_FEC = 1,	/* runs on i.mx25/50/53 */
 	IMX27_FEC,	/* runs on i.mx27/35/51 */
 	IMX28_FEC,
 	IMX6Q_FEC,
@@ -132,7 +132,7 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
 #elif defined (CONFIG_M5272C3)
 #define	FEC_FLASHMAC	(0xffe04000 + 4)
 #elif defined(CONFIG_MOD5272)
-#define FEC_FLASHMAC 	0xffc0406b
+#define FEC_FLASHMAC	0xffc0406b
 #else
 #define	FEC_FLASHMAC	0
 #endif
@@ -232,6 +232,7 @@ struct fec_enet_private {
 	struct	platform_device *pdev;
 
 	int	opened;
+	int	dev_id;
 
 	/* Phylib and MDIO interface */
 	struct	mii_bus *mii_bus;
@@ -259,6 +260,8 @@ struct fec_enet_private {
 /* Transmitter timeout */
 #define TX_TIMEOUT (2 * HZ)
 
+static int mii_cnt;
+
 static void *swap_buffer(void *bufaddr, int len)
 {
 	int i;
@@ -515,6 +518,7 @@ fec_stop(struct net_device *ndev)
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	const struct platform_device_id *id_entry =
 				platform_get_device_id(fep->pdev);
+	u32 rmii_mode = readl(fep->hwp + FEC_R_CNTRL) & (1 << 8);
 
 	/* We cannot expect a graceful transmit stop without link !!! */
 	if (fep->link) {
@@ -531,8 +535,10 @@ fec_stop(struct net_device *ndev)
 	writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
 
 	/* We have to keep ENET enabled to have MII interrupt stay working */
-	if (id_entry->driver_data & FEC_QUIRK_ENET_MAC)
+	if (id_entry->driver_data & FEC_QUIRK_ENET_MAC) {
 		writel(2, fep->hwp + FEC_ECNTRL);
+		writel(rmii_mode, fep->hwp + FEC_R_CNTRL);
+	}
 }
 
 
@@ -818,7 +824,7 @@ static void __inline__ fec_get_mac(struct net_device *ndev)
 			iap = (unsigned char *)FEC_FLASHMAC;
 #else
 		if (pdata)
-			memcpy(iap, pdata->mac, ETH_ALEN);
+			iap = (unsigned char *)&pdata->mac;
 #endif
 	}
 
@@ -837,7 +843,7 @@ static void __inline__ fec_get_mac(struct net_device *ndev)
 
 	/* Adjust MAC if using macaddr */
 	if (iap == macaddr)
-		 ndev->dev_addr[ETH_ALEN-1] = macaddr[ETH_ALEN-1] + fep->pdev->id;
+		 ndev->dev_addr[ETH_ALEN-1] = macaddr[ETH_ALEN-1] + fep->dev_id;
 }
 
 /* ------------------------------------------------------------------------- */
@@ -865,6 +871,8 @@ static void fec_enet_adjust_link(struct net_device *ndev)
 	if (phy_dev->link) {
 		if (fep->full_duplex != phy_dev->duplex) {
 			fec_restart(ndev, phy_dev->duplex);
+			/* prevent unnecessary second fec_restart() below */
+			fep->link = phy_dev->link;
 			status_change = 1;
 		}
 	}
@@ -953,7 +961,7 @@ static int fec_enet_mii_probe(struct net_device *ndev)
 	char mdio_bus_id[MII_BUS_ID_SIZE];
 	char phy_name[MII_BUS_ID_SIZE + 3];
 	int phy_id;
-	int dev_id = fep->pdev->id;
+	int dev_id = fep->dev_id;
 
 	fep->phy_dev = NULL;
 
@@ -972,8 +980,9 @@ static int fec_enet_mii_probe(struct net_device *ndev)
 	}
 
 	if (phy_id >= PHY_MAX_ADDR) {
-		printk(KERN_INFO "%s: no PHY, assuming direct connection "
-			"to switch\n", ndev->name);
+		printk(KERN_INFO
+			"%s: no PHY, assuming direct connection to switch\n",
+			ndev->name);
 		strncpy(mdio_bus_id, "0", MII_BUS_ID_SIZE);
 		phy_id = 0;
 	}
@@ -998,8 +1007,9 @@ static int fec_enet_mii_probe(struct net_device *ndev)
 	fep->link = 0;
 	fep->full_duplex = 0;
 
-	printk(KERN_INFO "%s: Freescale FEC PHY driver [%s] "
-		"(mii_bus:phy_addr=%s, irq=%d)\n", ndev->name,
+	printk(KERN_INFO
+		"%s: Freescale FEC PHY driver [%s] (mii_bus:phy_addr=%s, irq=%d)\n",
+		ndev->name,
 		fep->phy_dev->drv->name, dev_name(&fep->phy_dev->dev),
 		fep->phy_dev->irq);
 
@@ -1031,10 +1041,14 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	 * mdio interface in board design, and need to be configured by
 	 * fec0 mii_bus.
 	 */
-	if ((id_entry->driver_data & FEC_QUIRK_ENET_MAC) && pdev->id > 0) {
+	if ((id_entry->driver_data & FEC_QUIRK_ENET_MAC) && fep->dev_id > 0) {
 		/* fec1 uses fec0 mii_bus */
-		fep->mii_bus = fec0_mii_bus;
-		return 0;
+		if (mii_cnt && fec0_mii_bus) {
+			fep->mii_bus = fec0_mii_bus;
+			mii_cnt++;
+			return 0;
+		}
+		return -ENOENT;
 	}
 
 	fep->mii_timeout = 0;
@@ -1063,7 +1077,7 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	fep->mii_bus->read = fec_enet_mdio_read;
 	fep->mii_bus->write = fec_enet_mdio_write;
 	fep->mii_bus->reset = fec_enet_mdio_reset;
-	snprintf(fep->mii_bus->id, MII_BUS_ID_SIZE, "%x", pdev->id + 1);
+	snprintf(fep->mii_bus->id, MII_BUS_ID_SIZE, "%x", fep->dev_id + 1);
 	fep->mii_bus->priv = fep;
 	fep->mii_bus->parent = &pdev->dev;
 
@@ -1079,6 +1093,8 @@ static int fec_enet_mii_init(struct platform_device *pdev)
 	if (mdiobus_register(fep->mii_bus))
 		goto err_out_free_mdio_irq;
 
+	mii_cnt++;
+
 	/* save fec0 mii_bus */
 	if (id_entry->driver_data & FEC_QUIRK_ENET_MAC)
 		fec0_mii_bus = fep->mii_bus;
@@ -1095,11 +1111,11 @@ err_out:
 
 static void fec_enet_mii_remove(struct fec_enet_private *fep)
 {
-	if (fep->phy_dev)
-		phy_disconnect(fep->phy_dev);
-	mdiobus_unregister(fep->mii_bus);
-	kfree(fep->mii_bus->irq);
-	mdiobus_free(fep->mii_bus);
+	if (--mii_cnt == 0) {
+		mdiobus_unregister(fep->mii_bus);
+		kfree(fep->mii_bus->irq);
+		mdiobus_free(fep->mii_bus);
+	}
 }
 
 static int fec_enet_get_settings(struct net_device *ndev,
@@ -1521,6 +1537,7 @@ fec_probe(struct platform_device *pdev)
 	int i, irq, ret = 0;
 	struct resource *r;
 	const struct of_device_id *of_id;
+	static int dev_id;
 
 	of_id = of_match_device(fec_dt_ids, &pdev->dev);
 	if (of_id)
@@ -1548,6 +1565,7 @@ fec_probe(struct platform_device *pdev)
 
 	fep->hwp = ioremap(r->start, resource_size(r));
 	fep->pdev = pdev;
+	fep->dev_id = dev_id++;
 
 	if (!fep->hwp) {
 		ret = -ENOMEM;
@@ -1571,8 +1589,12 @@ fec_probe(struct platform_device *pdev)
 
 	for (i = 0; i < FEC_IRQ_NUM; i++) {
 		irq = platform_get_irq(pdev, i);
-		if (i && irq < 0)
-			break;
+		if (irq < 0) {
+			if (i)
+				break;
+			ret = irq;
+			goto failed_irq;
+		}
 		ret = request_irq(irq, fec_enet_interrupt, IRQF_DISABLED, pdev->name, ndev);
 		if (ret) {
 			while (--i >= 0) {
@@ -1583,7 +1605,7 @@ fec_probe(struct platform_device *pdev)
 		}
 	}
 
-	fep->clk = clk_get(&pdev->dev, "fec_clk");
+	fep->clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(fep->clk)) {
 		ret = PTR_ERR(fep->clk);
 		goto failed_clk;
@@ -1635,13 +1657,18 @@ fec_drv_remove(struct platform_device *pdev)
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	struct resource *r;
+	int i;
 
-	fec_stop(ndev);
+	unregister_netdev(ndev);
 	fec_enet_mii_remove(fep);
+	for (i = 0; i < FEC_IRQ_NUM; i++) {
+		int irq = platform_get_irq(pdev, i);
+		if (irq > 0)
+			free_irq(irq, ndev);
+	}
 	clk_disable(fep->clk);
 	clk_put(fep->clk);
 	iounmap(fep->hwp);
-	unregister_netdev(ndev);
 	free_netdev(ndev);
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index 5bf5471..910a8e1 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -1171,16 +1171,6 @@ static struct platform_driver fs_enet_driver = {
 	.remove = fs_enet_remove,
 };
 
-static int __init fs_init(void)
-{
-	return platform_driver_register(&fs_enet_driver);
-}
-
-static void __exit fs_cleanup(void)
-{
-	platform_driver_unregister(&fs_enet_driver);
-}
-
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static void fs_enet_netpoll(struct net_device *dev)
 {
@@ -1190,7 +1180,4 @@ static void fs_enet_netpoll(struct net_device *dev)
 }
 #endif
 
-/**************************************************************************************/
-
-module_init(fs_init);
-module_exit(fs_cleanup);
+module_platform_driver(fs_enet_driver);
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
index b09270b..0f2d1a7 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-bitbang.c
@@ -232,15 +232,4 @@ static struct platform_driver fs_enet_bb_mdio_driver = {
 	.remove = fs_enet_mdio_remove,
 };
 
-static int fs_enet_mdio_bb_init(void)
-{
-	return platform_driver_register(&fs_enet_bb_mdio_driver);
-}
-
-static void fs_enet_mdio_bb_exit(void)
-{
-	platform_driver_unregister(&fs_enet_bb_mdio_driver);
-}
-
-module_init(fs_enet_mdio_bb_init);
-module_exit(fs_enet_mdio_bb_exit);
+module_platform_driver(fs_enet_bb_mdio_driver);
diff --git a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
index e0e9d6c..55bb867 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mii-fec.c
@@ -237,15 +237,4 @@ static struct platform_driver fs_enet_fec_mdio_driver = {
 	.remove = fs_enet_mdio_remove,
 };
 
-static int fs_enet_mdio_fec_init(void)
-{
-	return platform_driver_register(&fs_enet_fec_mdio_driver);
-}
-
-static void fs_enet_mdio_fec_exit(void)
-{
-	platform_driver_unregister(&fs_enet_fec_mdio_driver);
-}
-
-module_init(fs_enet_mdio_fec_init);
-module_exit(fs_enet_mdio_fec_exit);
+module_platform_driver(fs_enet_fec_mdio_driver);
diff --git a/drivers/net/ethernet/freescale/fsl_pq_mdio.c b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
index 52f4e8a..9eb8159 100644
--- a/drivers/net/ethernet/freescale/fsl_pq_mdio.c
+++ b/drivers/net/ethernet/freescale/fsl_pq_mdio.c
@@ -183,28 +183,10 @@ void fsl_pq_mdio_bus_name(char *name, struct device_node *np)
 }
 EXPORT_SYMBOL_GPL(fsl_pq_mdio_bus_name);
 
-/* Scan the bus in reverse, looking for an empty spot */
-static int fsl_pq_mdio_find_free(struct mii_bus *new_bus)
-{
-	int i;
-
-	for (i = PHY_MAX_ADDR; i > 0; i--) {
-		u32 phy_id;
-
-		if (get_phy_id(new_bus, i, &phy_id))
-			return -1;
-
-		if (phy_id == 0xffffffff)
-			break;
-	}
 
-	return i;
-}
-
-
-#if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE)
 static u32 __iomem *get_gfar_tbipa(struct fsl_pq_mdio __iomem *regs, struct device_node *np)
 {
+#if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE)
 	struct gfar __iomem *enet_regs;
 
 	/*
@@ -220,15 +202,15 @@ static u32 __iomem *get_gfar_tbipa(struct fsl_pq_mdio __iomem *regs, struct devi
 	} else if (of_device_is_compatible(np, "fsl,etsec2-mdio") ||
 			of_device_is_compatible(np, "fsl,etsec2-tbi")) {
 		return of_iomap(np, 1);
-	} else
-		return NULL;
-}
+	}
 #endif
+	return NULL;
+}
 
 
-#if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE)
 static int get_ucc_id_for_range(u64 start, u64 end, u32 *ucc_id)
 {
+#if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE)
 	struct device_node *np = NULL;
 	int err = 0;
 
@@ -261,9 +243,10 @@ static int get_ucc_id_for_range(u64 start, u64 end, u32 *ucc_id)
 		return err;
 	else
 		return -EINVAL;
-}
+#else
+	return -ENODEV;
 #endif
-
+}
 
 static int fsl_pq_mdio_probe(struct platform_device *ofdev)
 {
@@ -339,19 +322,13 @@ static int fsl_pq_mdio_probe(struct platform_device *ofdev)
 			of_device_is_compatible(np, "fsl,etsec2-mdio") ||
 			of_device_is_compatible(np, "fsl,etsec2-tbi") ||
 			of_device_is_compatible(np, "gianfar")) {
-#if defined(CONFIG_GIANFAR) || defined(CONFIG_GIANFAR_MODULE)
 		tbipa = get_gfar_tbipa(regs, np);
 		if (!tbipa) {
 			err = -EINVAL;
 			goto err_free_irqs;
 		}
-#else
-		err = -ENODEV;
-		goto err_free_irqs;
-#endif
 	} else if (of_device_is_compatible(np, "fsl,ucc-mdio") ||
 			of_device_is_compatible(np, "ucc_geth_phy")) {
-#if defined(CONFIG_UCC_GETH) || defined(CONFIG_UCC_GETH_MODULE)
 		u32 id;
 		static u32 mii_mng_master;
 
@@ -364,10 +341,6 @@ static int fsl_pq_mdio_probe(struct platform_device *ofdev)
 			mii_mng_master = id;
 			ucc_set_qe_mux_mii_mng(id - 1);
 		}
-#else
-		err = -ENODEV;
-		goto err_free_irqs;
-#endif
 	} else {
 		err = -ENODEV;
 		goto err_free_irqs;
@@ -386,23 +359,12 @@ static int fsl_pq_mdio_probe(struct platform_device *ofdev)
 	}
 
 	if (tbiaddr == -1) {
-		out_be32(tbipa, 0);
-
-		tbiaddr = fsl_pq_mdio_find_free(new_bus);
-	}
-
-	/*
-	 * We define TBIPA at 0 to be illegal, opting to fail for boards that
-	 * have PHYs at 1-31, rather than change tbipa and rescan.
-	 */
-	if (tbiaddr == 0) {
 		err = -EBUSY;
-
 		goto err_free_irqs;
+	} else {
+		out_be32(tbipa, tbiaddr);
 	}
 
-	out_be32(tbipa, tbiaddr);
-
 	err = of_mdiobus_register(new_bus, np);
 	if (err) {
 		printk (KERN_ERR "%s: Cannot register as MDIO bus\n",
@@ -480,15 +442,6 @@ static struct platform_driver fsl_pq_mdio_driver = {
 	.remove = fsl_pq_mdio_remove,
 };
 
-int __init fsl_pq_mdio_init(void)
-{
-	return platform_driver_register(&fsl_pq_mdio_driver);
-}
-module_init(fsl_pq_mdio_init);
+module_platform_driver(fsl_pq_mdio_driver);
 
-void fsl_pq_mdio_exit(void)
-{
-	platform_driver_unregister(&fsl_pq_mdio_driver);
-}
-module_exit(fsl_pq_mdio_exit);
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 83199fd..e01cdaa 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -734,7 +734,7 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev)
 
 	mac_addr = of_get_mac_address(np);
 	if (mac_addr)
-		memcpy(dev->dev_addr, mac_addr, MAC_ADDR_LEN);
+		memcpy(dev->dev_addr, mac_addr, ETH_ALEN);
 
 	if (model && !strcasecmp(model, "TSEC"))
 		priv->device_flags =
@@ -2306,7 +2306,7 @@ void gfar_check_rx_parser_mode(struct gfar_private *priv)
 }
 
 /* Enables and disables VLAN insertion/extraction */
-void gfar_vlan_mode(struct net_device *dev, u32 features)
+void gfar_vlan_mode(struct net_device *dev, netdev_features_t features)
 {
 	struct gfar_private *priv = netdev_priv(dev);
 	struct gfar __iomem *regs = NULL;
@@ -3114,7 +3114,7 @@ static void gfar_set_multi(struct net_device *dev)
 static void gfar_clear_exact_match(struct net_device *dev)
 {
 	int idx;
-	static const u8 zero_arr[MAC_ADDR_LEN] = {0, 0, 0, 0, 0, 0};
+	static const u8 zero_arr[ETH_ALEN] = {0, 0, 0, 0, 0, 0};
 
 	for(idx = 1;idx < GFAR_EM_NUM + 1;idx++)
 		gfar_set_mac_for_addr(dev, idx, zero_arr);
@@ -3137,7 +3137,7 @@ static void gfar_set_hash_for_addr(struct net_device *dev, u8 *addr)
 {
 	u32 tempval;
 	struct gfar_private *priv = netdev_priv(dev);
-	u32 result = ether_crc(MAC_ADDR_LEN, addr);
+	u32 result = ether_crc(ETH_ALEN, addr);
 	int width = priv->hash_width;
 	u8 whichbit = (result >> (32 - width)) & 0x1f;
 	u8 whichreg = result >> (32 - width + 5);
@@ -3158,7 +3158,7 @@ static void gfar_set_mac_for_addr(struct net_device *dev, int num,
 	struct gfar_private *priv = netdev_priv(dev);
 	struct gfar __iomem *regs = priv->gfargrp[0].regs;
 	int idx;
-	char tmpbuf[MAC_ADDR_LEN];
+	char tmpbuf[ETH_ALEN];
 	u32 tempval;
 	u32 __iomem *macptr = &regs->macstnaddr1;
 
@@ -3166,8 +3166,8 @@ static void gfar_set_mac_for_addr(struct net_device *dev, int num,
 
 	/* Now copy it into the mac registers backwards, cuz */
 	/* little endian is silly */
-	for (idx = 0; idx < MAC_ADDR_LEN; idx++)
-		tmpbuf[MAC_ADDR_LEN - 1 - idx] = addr[idx];
+	for (idx = 0; idx < ETH_ALEN; idx++)
+		tmpbuf[ETH_ALEN - 1 - idx] = addr[idx];
 
 	gfar_write(macptr, *((u32 *) (tmpbuf)));
 
@@ -3281,16 +3281,4 @@ static struct platform_driver gfar_driver = {
 	.remove = gfar_remove,
 };
 
-static int __init gfar_init(void)
-{
-	return platform_driver_register(&gfar_driver);
-}
-
-static void __exit gfar_exit(void)
-{
-	platform_driver_unregister(&gfar_driver);
-}
-
-module_init(gfar_init);
-module_exit(gfar_exit);
-
+module_platform_driver(gfar_driver);
diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h
index 9aa4377..fe7ac3a 100644
--- a/drivers/net/ethernet/freescale/gianfar.h
+++ b/drivers/net/ethernet/freescale/gianfar.h
@@ -74,9 +74,6 @@ struct ethtool_rx_list {
  * will be the next highest multiple of 512 bytes. */
 #define INCREMENTAL_BUFFER_SIZE 512
 
-
-#define MAC_ADDR_LEN 6
-
 #define PHY_INIT_TIMEOUT 100000
 #define GFAR_PHY_CHANGE_TIME 2
 
@@ -1179,9 +1176,9 @@ extern void gfar_phy_test(struct mii_bus *bus, struct phy_device *phydev,
 extern void gfar_configure_coalescing(struct gfar_private *priv,
 		unsigned long tx_mask, unsigned long rx_mask);
 void gfar_init_sysfs(struct net_device *dev);
-int gfar_set_features(struct net_device *dev, u32 features);
+int gfar_set_features(struct net_device *dev, netdev_features_t features);
 extern void gfar_check_rx_parser_mode(struct gfar_private *priv);
-extern void gfar_vlan_mode(struct net_device *dev, u32 features);
+extern void gfar_vlan_mode(struct net_device *dev, netdev_features_t features);
 
 extern const struct ethtool_ops gfar_ethtool_ops;
 
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index 212736b..5890f4b 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -519,12 +519,12 @@ static int gfar_sringparam(struct net_device *dev, struct ethtool_ringparam *rva
 	return err;
 }
 
-int gfar_set_features(struct net_device *dev, u32 features)
+int gfar_set_features(struct net_device *dev, netdev_features_t features)
 {
 	struct gfar_private *priv = netdev_priv(dev);
 	unsigned long flags;
 	int err = 0, i = 0;
-	u32 changed = dev->features ^ features;
+	netdev_features_t changed = dev->features ^ features;
 
 	if (changed & (NETIF_F_HW_VLAN_TX|NETIF_F_HW_VLAN_RX))
 		gfar_vlan_mode(dev, features);
@@ -1410,10 +1410,9 @@ static int gfar_optimize_filer_masks(struct filer_table *tab)
 
 	/* We need a copy of the filer table because
 	 * we want to change its order */
-	temp_table = kmalloc(sizeof(*temp_table), GFP_KERNEL);
+	temp_table = kmemdup(tab, sizeof(*temp_table), GFP_KERNEL);
 	if (temp_table == NULL)
 		return -ENOMEM;
-	memcpy(temp_table, tab, sizeof(*temp_table));
 
 	mask_table = kcalloc(MAX_FILER_CACHE_IDX / 2 + 1,
 			sizeof(struct gfar_mask_entry), GFP_KERNEL);
diff --git a/drivers/net/ethernet/freescale/gianfar_ptp.c b/drivers/net/ethernet/freescale/gianfar_ptp.c
index f67b8ae..83e0ed75 100644
--- a/drivers/net/ethernet/freescale/gianfar_ptp.c
+++ b/drivers/net/ethernet/freescale/gianfar_ptp.c
@@ -562,21 +562,7 @@ static struct platform_driver gianfar_ptp_driver = {
 	.remove      = gianfar_ptp_remove,
 };
 
-/* module operations */
-
-static int __init ptp_gianfar_init(void)
-{
-	return platform_driver_register(&gianfar_ptp_driver);
-}
-
-module_init(ptp_gianfar_init);
-
-static void __exit ptp_gianfar_exit(void)
-{
-	platform_driver_unregister(&gianfar_ptp_driver);
-}
-
-module_exit(ptp_gianfar_exit);
+module_platform_driver(gianfar_ptp_driver);
 
 MODULE_AUTHOR("Richard Cochran <richard.cochran@omicron.at>");
 MODULE_DESCRIPTION("PTP clock using the eTSEC");
diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index b5dc027..ba2dc08 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -443,7 +443,7 @@ static void hw_add_addr_in_hash(struct ucc_geth_private *ugeth,
 
 static inline int compare_addr(u8 **addr1, u8 **addr2)
 {
-	return memcmp(addr1, addr2, ENET_NUM_OCTETS_PER_ADDRESS);
+	return memcmp(addr1, addr2, ETH_ALEN);
 }
 
 #ifdef DEBUG
diff --git a/drivers/net/ethernet/freescale/ucc_geth.h b/drivers/net/ethernet/freescale/ucc_geth.h
index d12fcad..2e395a2 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.h
+++ b/drivers/net/ethernet/freescale/ucc_geth.h
@@ -20,6 +20,7 @@
 
 #include <linux/kernel.h>
 #include <linux/list.h>
+#include <linux/if_ether.h>
 
 #include <asm/immap_qe.h>
 #include <asm/qe.h>
@@ -881,7 +882,6 @@ struct ucc_geth_hardware_statistics {
 #define TX_RING_MOD_MASK(size)                  (size-1)
 #define RX_RING_MOD_MASK(size)                  (size-1)
 
-#define ENET_NUM_OCTETS_PER_ADDRESS             6
 #define ENET_GROUP_ADDR                         0x01	/* Group address mask
 							   for ethernet
 							   addresses */
@@ -1051,7 +1051,7 @@ enum ucc_geth_num_of_station_addresses {
 
 /* UCC GETH 82xx Ethernet Address Container */
 struct enet_addr_container {
-	u8 address[ENET_NUM_OCTETS_PER_ADDRESS];	/* ethernet address */
+	u8 address[ETH_ALEN];	/* ethernet address */
 	enum ucc_geth_enet_address_recognition_location location;	/* location in
 								   82xx address
 								   recognition
@@ -1194,7 +1194,7 @@ struct ucc_geth_private {
 	u16 cpucount[NUM_TX_QUEUES];
 	u16 __iomem *p_cpucount[NUM_TX_QUEUES];
 	int indAddrRegUsed[NUM_OF_PADDRS];
-	u8 paddr[NUM_OF_PADDRS][ENET_NUM_OCTETS_PER_ADDRESS];	/* ethernet address */
+	u8 paddr[NUM_OF_PADDRS][ETH_ALEN];	/* ethernet address */
 	u8 numGroupAddrInHash;
 	u8 numIndAddrInHash;
 	u8 numIndAddrInReg;
diff --git a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
index 1541675..ee84b47 100644
--- a/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
+++ b/drivers/net/ethernet/fujitsu/fmvj18x_cs.c
@@ -1058,9 +1058,10 @@ static void fjn_rx(struct net_device *dev)
 static void netdev_get_drvinfo(struct net_device *dev,
 			       struct ethtool_drvinfo *info)
 {
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	sprintf(info->bus_info, "PCMCIA 0x%lx", dev->base_addr);
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	snprintf(info->bus_info, sizeof(info->bus_info),
+		"PCMCIA 0x%lx", dev->base_addr);
 }
 
 static const struct ethtool_ops netdev_ethtool_ops = {
diff --git a/drivers/net/ethernet/i825xx/eepro.c b/drivers/net/ethernet/i825xx/eepro.c
index 067c460..114cda77 100644
--- a/drivers/net/ethernet/i825xx/eepro.c
+++ b/drivers/net/ethernet/i825xx/eepro.c
@@ -1726,9 +1726,10 @@ static int eepro_ethtool_get_settings(struct net_device *dev,
 static void eepro_ethtool_get_drvinfo(struct net_device *dev,
 					struct ethtool_drvinfo *drvinfo)
 {
-	strcpy(drvinfo->driver, DRV_NAME);
-	strcpy(drvinfo->version, DRV_VERSION);
-	sprintf(drvinfo->bus_info, "ISA 0x%lx", dev->base_addr);
+	strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version));
+	snprintf(drvinfo->bus_info, sizeof(drvinfo->bus_info),
+		"ISA 0x%lx", dev->base_addr);
 }
 
 static const struct ethtool_ops eepro_ethtool_ops = {
diff --git a/drivers/net/ethernet/ibm/ehea/ehea.h b/drivers/net/ethernet/ibm/ehea/ehea.h
index 410d6a1..6650068 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea.h
+++ b/drivers/net/ethernet/ibm/ehea/ehea.h
@@ -61,9 +61,9 @@
 #ifdef EHEA_SMALL_QUEUES
 #define EHEA_MAX_CQE_COUNT      1023
 #define EHEA_DEF_ENTRIES_SQ     1023
-#define EHEA_DEF_ENTRIES_RQ1    4095
+#define EHEA_DEF_ENTRIES_RQ1    1023
 #define EHEA_DEF_ENTRIES_RQ2    1023
-#define EHEA_DEF_ENTRIES_RQ3    1023
+#define EHEA_DEF_ENTRIES_RQ3    511
 #else
 #define EHEA_MAX_CQE_COUNT      4080
 #define EHEA_DEF_ENTRIES_SQ     4080
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index 37b70f7..3554414 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -371,7 +371,8 @@ static void ehea_update_stats(struct work_struct *work)
 out_herr:
 	free_page((unsigned long)cb2);
 resched:
-	schedule_delayed_work(&port->stats_work, msecs_to_jiffies(1000));
+	schedule_delayed_work(&port->stats_work,
+			      round_jiffies_relative(msecs_to_jiffies(1000)));
 }
 
 static void ehea_refill_rq1(struct ehea_port_res *pr, int index, int nr_of_wqes)
@@ -2113,17 +2114,19 @@ static int ehea_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }
 
-static void ehea_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+static int ehea_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 {
 	struct ehea_port *port = netdev_priv(dev);
 	struct ehea_adapter *adapter = port->adapter;
 	struct hcp_ehea_port_cb1 *cb1;
 	int index;
 	u64 hret;
+	int err = 0;
 
 	cb1 = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!cb1) {
 		pr_err("no mem for cb1\n");
+		err = -ENOMEM;
 		goto out;
 	}
 
@@ -2131,6 +2134,7 @@ static void ehea_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 				      H_PORT_CB1, H_PORT_CB1_ALL, cb1);
 	if (hret != H_SUCCESS) {
 		pr_err("query_ehea_port failed\n");
+		err = -EINVAL;
 		goto out;
 	}
 
@@ -2139,24 +2143,28 @@ static void ehea_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 
 	hret = ehea_h_modify_ehea_port(adapter->handle, port->logical_port_id,
 				       H_PORT_CB1, H_PORT_CB1_ALL, cb1);
-	if (hret != H_SUCCESS)
+	if (hret != H_SUCCESS) {
 		pr_err("modify_ehea_port failed\n");
+		err = -EINVAL;
+	}
 out:
 	free_page((unsigned long)cb1);
-	return;
+	return err;
 }
 
-static void ehea_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+static int ehea_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 {
 	struct ehea_port *port = netdev_priv(dev);
 	struct ehea_adapter *adapter = port->adapter;
 	struct hcp_ehea_port_cb1 *cb1;
 	int index;
 	u64 hret;
+	int err = 0;
 
 	cb1 = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!cb1) {
 		pr_err("no mem for cb1\n");
+		err = -ENOMEM;
 		goto out;
 	}
 
@@ -2164,6 +2172,7 @@ static void ehea_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 				      H_PORT_CB1, H_PORT_CB1_ALL, cb1);
 	if (hret != H_SUCCESS) {
 		pr_err("query_ehea_port failed\n");
+		err = -EINVAL;
 		goto out;
 	}
 
@@ -2172,10 +2181,13 @@ static void ehea_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 
 	hret = ehea_h_modify_ehea_port(adapter->handle, port->logical_port_id,
 				       H_PORT_CB1, H_PORT_CB1_ALL, cb1);
-	if (hret != H_SUCCESS)
+	if (hret != H_SUCCESS) {
 		pr_err("modify_ehea_port failed\n");
+		err = -EINVAL;
+	}
 out:
 	free_page((unsigned long)cb1);
+	return err;
 }
 
 int ehea_activate_qp(struct ehea_adapter *adapter, struct ehea_qp *qp)
@@ -2434,7 +2446,8 @@ static int ehea_open(struct net_device *dev)
 	}
 
 	mutex_unlock(&port->port_lock);
-	schedule_delayed_work(&port->stats_work, msecs_to_jiffies(1000));
+	schedule_delayed_work(&port->stats_work,
+			      round_jiffies_relative(msecs_to_jiffies(1000)));
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index ed79b2d..2abce96 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -2924,6 +2924,9 @@ static int __devexit emac_remove(struct platform_device *ofdev)
 	if (emac_has_feature(dev, EMAC_FTR_HAS_ZMII))
 		zmii_detach(dev->zmii_dev, dev->zmii_port);
 
+	busy_phy_map &= ~(1 << dev->phy.address);
+	DBG(dev, "busy_phy_map now %#x" NL, busy_phy_map);
+
 	mal_unregister_commac(dev->mal, &dev->commac);
 	emac_put_deps(dev);
 
diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c
index b1cd41b..e877371 100644
--- a/drivers/net/ethernet/ibm/ibmveth.c
+++ b/drivers/net/ethernet/ibm/ibmveth.c
@@ -735,7 +735,8 @@ static void netdev_get_drvinfo(struct net_device *dev,
 		sizeof(info->version) - 1);
 }
 
-static u32 ibmveth_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t ibmveth_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	/*
 	 * Since the ibmveth firmware interface does not have the
@@ -838,7 +839,8 @@ static int ibmveth_set_csum_offload(struct net_device *dev, u32 data)
 	return rc1 ? rc1 : rc2;
 }
 
-static int ibmveth_set_features(struct net_device *dev, u32 features)
+static int ibmveth_set_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct ibmveth_adapter *adapter = netdev_priv(dev);
 	int rx_csum = !!(features & NETIF_F_RXCSUM);
diff --git a/drivers/net/ethernet/ibm/iseries_veth.c b/drivers/net/ethernet/ibm/iseries_veth.c
index 4326681..acc31af 100644
--- a/drivers/net/ethernet/ibm/iseries_veth.c
+++ b/drivers/net/ethernet/ibm/iseries_veth.c
@@ -1421,7 +1421,7 @@ static void veth_receive(struct veth_lpar_connection *cnx,
 
 		/* FIXME: do we need this? */
 		memset(local_list, 0, sizeof(local_list));
-		memset(remote_list, 0, sizeof(VETH_MAX_FRAMES_PER_MSG));
+		memset(remote_list, 0, sizeof(remote_list));
 
 		/* a 0 address marks the end of the valid entries */
 		if (senddata->addr[startchunk] == 0)
diff --git a/drivers/net/ethernet/icplus/ipg.c b/drivers/net/ethernet/icplus/ipg.c
index 8fd80a0..075451d 100644
--- a/drivers/net/ethernet/icplus/ipg.c
+++ b/drivers/net/ethernet/icplus/ipg.c
@@ -371,16 +371,9 @@ static void mdio_write(struct net_device *dev, int phy_id, int phy_reg, int val)
 	}
 
 	/* The last cycle is a tri-state, so read from the PHY. */
-	for (j = 7; j < 8; j++) {
-		for (i = 0; i < p[j].len; i++) {
-			ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_LO | polarity);
-
-			p[j].field |= ((ipg_r8(PHY_CTRL) &
-				IPG_PC_MGMTDATA) >> 1) << (p[j].len - 1 - i);
-
-			ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_HI | polarity);
-		}
-	}
+	ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_LO | polarity);
+	ipg_r8(PHY_CTRL);
+	ipg_write_phy_ctl(ioaddr, IPG_PC_MGMTCLK_HI | polarity);
 }
 
 static void ipg_set_led_mode(struct net_device *dev)
diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c
index 5a2fdf7..9436397 100644
--- a/drivers/net/ethernet/intel/e100.c
+++ b/drivers/net/ethernet/intel/e100.c
@@ -2376,10 +2376,10 @@ static void e100_get_drvinfo(struct net_device *netdev,
 	struct ethtool_drvinfo *info)
 {
 	struct nic *nic = netdev_priv(netdev);
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->fw_version, "N/A");
-	strcpy(info->bus_info, pci_name(nic->pdev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(nic->pdev),
+		sizeof(info->bus_info));
 }
 
 #define E100_PHY_REGS 0x1C
diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index 2b223ac..3103f0b 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -515,14 +515,14 @@ static void e1000_get_drvinfo(struct net_device *netdev,
 			      struct ethtool_drvinfo *drvinfo)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
-	char firmware_version[32];
 
-	strncpy(drvinfo->driver,  e1000_driver_name, 32);
-	strncpy(drvinfo->version, e1000_driver_version, 32);
+	strlcpy(drvinfo->driver,  e1000_driver_name,
+		sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, e1000_driver_version,
+		sizeof(drvinfo->version));
 
-	sprintf(firmware_version, "N/A");
-	strncpy(drvinfo->fw_version, firmware_version, 32);
-	strncpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
 	drvinfo->regdump_len = e1000_get_regs_len(netdev);
 	drvinfo->eedump_len = e1000_get_eeprom_len(netdev);
 }
diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.h b/drivers/net/ethernet/intel/e1000/e1000_hw.h
index 5c9a840..cf7e3c0 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_hw.h
+++ b/drivers/net/ethernet/intel/e1000/e1000_hw.h
@@ -448,7 +448,6 @@ void e1000_io_write(struct e1000_hw *hw, unsigned long port, u32 value);
 #define E1000_DEV_ID_INTEL_CE4100_GBE    0x2E6E
 
 #define NODE_ADDRESS_SIZE 6
-#define ETH_LENGTH_OF_ADDRESS 6
 
 /* MAC decode size is 128K - This is the size of BAR0 */
 #define MAC_DECODE_SIZE (128 * 1024)
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index cf480b5..053f012 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -167,9 +167,10 @@ static int e1000_82547_fifo_workaround(struct e1000_adapter *adapter,
                                        struct sk_buff *skb);
 
 static bool e1000_vlan_used(struct e1000_adapter *adapter);
-static void e1000_vlan_mode(struct net_device *netdev, u32 features);
-static void e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid);
-static void e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid);
+static void e1000_vlan_mode(struct net_device *netdev,
+			    netdev_features_t features);
+static int e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid);
+static int e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid);
 static void e1000_restore_vlan(struct e1000_adapter *adapter);
 
 #ifdef CONFIG_PM
@@ -806,7 +807,8 @@ static int e1000_is_need_ioport(struct pci_dev *pdev)
 	}
 }
 
-static u32 e1000_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t e1000_fix_features(struct net_device *netdev,
+	netdev_features_t features)
 {
 	/*
 	 * Since there is no support for separate rx/tx vlan accel
@@ -820,10 +822,11 @@ static u32 e1000_fix_features(struct net_device *netdev, u32 features)
 	return features;
 }
 
-static int e1000_set_features(struct net_device *netdev, u32 features)
+static int e1000_set_features(struct net_device *netdev,
+	netdev_features_t features)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
-	u32 changed = features ^ netdev->features;
+	netdev_features_t changed = features ^ netdev->features;
 
 	if (changed & NETIF_F_HW_VLAN_RX)
 		e1000_vlan_mode(netdev, features);
@@ -4577,7 +4580,8 @@ static void e1000_vlan_filter_on_off(struct e1000_adapter *adapter,
 		e1000_irq_enable(adapter);
 }
 
-static void e1000_vlan_mode(struct net_device *netdev, u32 features)
+static void e1000_vlan_mode(struct net_device *netdev,
+	netdev_features_t features)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -4600,7 +4604,7 @@ static void e1000_vlan_mode(struct net_device *netdev, u32 features)
 		e1000_irq_enable(adapter);
 }
 
-static void e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
+static int e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -4609,7 +4613,7 @@ static void e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 	if ((hw->mng_cookie.status &
 	     E1000_MNG_DHCP_COOKIE_STATUS_VLAN_SUPPORT) &&
 	    (vid == adapter->mng_vlan_id))
-		return;
+		return 0;
 
 	if (!e1000_vlan_used(adapter))
 		e1000_vlan_filter_on_off(adapter, true);
@@ -4621,9 +4625,11 @@ static void e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 	e1000_write_vfta(hw, index, vfta);
 
 	set_bit(vid, adapter->active_vlans);
+
+	return 0;
 }
 
-static void e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
+static int e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -4644,6 +4650,8 @@ static void e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 
 	if (!e1000_vlan_used(adapter))
 		e1000_vlan_filter_on_off(adapter, false);
+
+	return 0;
 }
 
 static void e1000_restore_vlan(struct e1000_adapter *adapter)
diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index 9fe18d1..f478a22 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -309,6 +309,7 @@ struct e1000_adapter {
 	u32 txd_cmd;
 
 	bool detect_tx_hung;
+	bool tx_hang_recheck;
 	u8 tx_timeout_factor;
 
 	u32 tx_int_delay;
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index 69c9d21..fb2c28e 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -579,26 +579,24 @@ static void e1000_get_drvinfo(struct net_device *netdev,
 			      struct ethtool_drvinfo *drvinfo)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
-	char firmware_version[32];
 
-	strncpy(drvinfo->driver,  e1000e_driver_name,
-		sizeof(drvinfo->driver) - 1);
-	strncpy(drvinfo->version, e1000e_driver_version,
-		sizeof(drvinfo->version) - 1);
+	strlcpy(drvinfo->driver,  e1000e_driver_name,
+		sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, e1000e_driver_version,
+		sizeof(drvinfo->version));
 
 	/*
 	 * EEPROM image version # is reported as firmware version # for
 	 * PCI-E controllers
 	 */
-	snprintf(firmware_version, sizeof(firmware_version), "%d.%d-%d",
+	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+		"%d.%d-%d",
 		(adapter->eeprom_vers & 0xF000) >> 12,
 		(adapter->eeprom_vers & 0x0FF0) >> 4,
 		(adapter->eeprom_vers & 0x000F));
 
-	strncpy(drvinfo->fw_version, firmware_version,
-		sizeof(drvinfo->fw_version) - 1);
-	strncpy(drvinfo->bus_info, pci_name(adapter->pdev),
-		sizeof(drvinfo->bus_info) - 1);
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
 	drvinfo->regdump_len = e1000_get_regs_len(netdev);
 	drvinfo->eedump_len = e1000_get_eeprom_len(netdev);
 }
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index a855db1..90953b4 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -163,16 +163,13 @@ static void e1000_regdump(struct e1000_hw *hw, struct e1000_reg_info *reginfo)
 			regs[n] = __er32(hw, E1000_TARC(n));
 		break;
 	default:
-		printk(KERN_INFO "%-15s %08x\n",
-		       reginfo->name, __er32(hw, reginfo->ofs));
+		pr_info("%-15s %08x\n",
+			reginfo->name, __er32(hw, reginfo->ofs));
 		return;
 	}
 
 	snprintf(rname, 16, "%s%s", reginfo->name, "[0-1]");
-	printk(KERN_INFO "%-15s ", rname);
-	for (n = 0; n < 2; n++)
-		printk(KERN_CONT "%08x ", regs[n]);
-	printk(KERN_CONT "\n");
+	pr_info("%-15s %08x %08x\n", rname, regs[0], regs[1]);
 }
 
 /*
@@ -208,16 +205,15 @@ static void e1000e_dump(struct e1000_adapter *adapter)
 	/* Print netdevice Info */
 	if (netdev) {
 		dev_info(&adapter->pdev->dev, "Net device Info\n");
-		printk(KERN_INFO "Device Name     state            "
-		       "trans_start      last_rx\n");
-		printk(KERN_INFO "%-15s %016lX %016lX %016lX\n",
-		       netdev->name, netdev->state, netdev->trans_start,
-		       netdev->last_rx);
+		pr_info("Device Name     state            trans_start      last_rx\n");
+		pr_info("%-15s %016lX %016lX %016lX\n",
+			netdev->name, netdev->state, netdev->trans_start,
+			netdev->last_rx);
 	}
 
 	/* Print Registers */
 	dev_info(&adapter->pdev->dev, "Register Dump\n");
-	printk(KERN_INFO " Register Name   Value\n");
+	pr_info(" Register Name   Value\n");
 	for (reginfo = (struct e1000_reg_info *)e1000_reg_info_tbl;
 	     reginfo->name; reginfo++) {
 		e1000_regdump(hw, reginfo);
@@ -228,15 +224,14 @@ static void e1000e_dump(struct e1000_adapter *adapter)
 		goto exit;
 
 	dev_info(&adapter->pdev->dev, "Tx Ring Summary\n");
-	printk(KERN_INFO "Queue [NTU] [NTC] [bi(ntc)->dma  ]"
-	       " leng ntw timestamp\n");
+	pr_info("Queue [NTU] [NTC] [bi(ntc)->dma  ] leng ntw timestamp\n");
 	buffer_info = &tx_ring->buffer_info[tx_ring->next_to_clean];
-	printk(KERN_INFO " %5d %5X %5X %016llX %04X %3X %016llX\n",
-	       0, tx_ring->next_to_use, tx_ring->next_to_clean,
-	       (unsigned long long)buffer_info->dma,
-	       buffer_info->length,
-	       buffer_info->next_to_watch,
-	       (unsigned long long)buffer_info->time_stamp);
+	pr_info(" %5d %5X %5X %016llX %04X %3X %016llX\n",
+		0, tx_ring->next_to_use, tx_ring->next_to_clean,
+		(unsigned long long)buffer_info->dma,
+		buffer_info->length,
+		buffer_info->next_to_watch,
+		(unsigned long long)buffer_info->time_stamp);
 
 	/* Print Tx Ring */
 	if (!netif_msg_tx_done(adapter))
@@ -271,37 +266,32 @@ static void e1000e_dump(struct e1000_adapter *adapter)
 	 *   +----------------------------------------------------------------+
 	 *   63       48 47     40 39  36 35    32 31     24 23  20 19        0
 	 */
-	printk(KERN_INFO "Tl[desc]     [address 63:0  ] [SpeCssSCmCsLen]"
-	       " [bi->dma       ] leng  ntw timestamp        bi->skb "
-	       "<-- Legacy format\n");
-	printk(KERN_INFO "Tc[desc]     [Ce CoCsIpceCoS] [MssHlRSCm0Plen]"
-	       " [bi->dma       ] leng  ntw timestamp        bi->skb "
-	       "<-- Ext Context format\n");
-	printk(KERN_INFO "Td[desc]     [address 63:0  ] [VlaPoRSCm1Dlen]"
-	       " [bi->dma       ] leng  ntw timestamp        bi->skb "
-	       "<-- Ext Data format\n");
+	pr_info("Tl[desc]     [address 63:0  ] [SpeCssSCmCsLen] [bi->dma       ] leng  ntw timestamp        bi->skb <-- Legacy format\n");
+	pr_info("Tc[desc]     [Ce CoCsIpceCoS] [MssHlRSCm0Plen] [bi->dma       ] leng  ntw timestamp        bi->skb <-- Ext Context format\n");
+	pr_info("Td[desc]     [address 63:0  ] [VlaPoRSCm1Dlen] [bi->dma       ] leng  ntw timestamp        bi->skb <-- Ext Data format\n");
 	for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
+		const char *next_desc;
 		tx_desc = E1000_TX_DESC(*tx_ring, i);
 		buffer_info = &tx_ring->buffer_info[i];
 		u0 = (struct my_u0 *)tx_desc;
-		printk(KERN_INFO "T%c[0x%03X]    %016llX %016llX %016llX "
-		       "%04X  %3X %016llX %p",
-		       (!(le64_to_cpu(u0->b) & (1 << 29)) ? 'l' :
-			((le64_to_cpu(u0->b) & (1 << 20)) ? 'd' : 'c')), i,
-		       (unsigned long long)le64_to_cpu(u0->a),
-		       (unsigned long long)le64_to_cpu(u0->b),
-		       (unsigned long long)buffer_info->dma,
-		       buffer_info->length, buffer_info->next_to_watch,
-		       (unsigned long long)buffer_info->time_stamp,
-		       buffer_info->skb);
 		if (i == tx_ring->next_to_use && i == tx_ring->next_to_clean)
-			printk(KERN_CONT " NTC/U\n");
+			next_desc = " NTC/U";
 		else if (i == tx_ring->next_to_use)
-			printk(KERN_CONT " NTU\n");
+			next_desc = " NTU";
 		else if (i == tx_ring->next_to_clean)
-			printk(KERN_CONT " NTC\n");
+			next_desc = " NTC";
 		else
-			printk(KERN_CONT "\n");
+			next_desc = "";
+		pr_info("T%c[0x%03X]    %016llX %016llX %016llX %04X  %3X %016llX %p%s\n",
+			(!(le64_to_cpu(u0->b) & (1 << 29)) ? 'l' :
+			 ((le64_to_cpu(u0->b) & (1 << 20)) ? 'd' : 'c')),
+			i,
+			(unsigned long long)le64_to_cpu(u0->a),
+			(unsigned long long)le64_to_cpu(u0->b),
+			(unsigned long long)buffer_info->dma,
+			buffer_info->length, buffer_info->next_to_watch,
+			(unsigned long long)buffer_info->time_stamp,
+			buffer_info->skb, next_desc);
 
 		if (netif_msg_pktdata(adapter) && buffer_info->dma != 0)
 			print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS,
@@ -312,9 +302,9 @@ static void e1000e_dump(struct e1000_adapter *adapter)
 	/* Print Rx Ring Summary */
 rx_ring_summary:
 	dev_info(&adapter->pdev->dev, "Rx Ring Summary\n");
-	printk(KERN_INFO "Queue [NTU] [NTC]\n");
-	printk(KERN_INFO " %5d %5X %5X\n", 0,
-	       rx_ring->next_to_use, rx_ring->next_to_clean);
+	pr_info("Queue [NTU] [NTC]\n");
+	pr_info(" %5d %5X %5X\n",
+		0, rx_ring->next_to_use, rx_ring->next_to_clean);
 
 	/* Print Rx Ring */
 	if (!netif_msg_rx_status(adapter))
@@ -337,10 +327,7 @@ rx_ring_summary:
 		 * 24 |                Buffer Address 3 [63:0]              |
 		 *    +-----------------------------------------------------+
 		 */
-		printk(KERN_INFO "R  [desc]      [buffer 0 63:0 ] "
-		       "[buffer 1 63:0 ] "
-		       "[buffer 2 63:0 ] [buffer 3 63:0 ] [bi->dma       ] "
-		       "[bi->skb] <-- Ext Pkt Split format\n");
+		pr_info("R  [desc]      [buffer 0 63:0 ] [buffer 1 63:0 ] [buffer 2 63:0 ] [buffer 3 63:0 ] [bi->dma       ] [bi->skb] <-- Ext Pkt Split format\n");
 		/* [Extended] Receive Descriptor (Write-Back) Format
 		 *
 		 *   63       48 47    32 31     13 12    8 7    4 3        0
@@ -352,35 +339,40 @@ rx_ring_summary:
 		 *   +------------------------------------------------------+
 		 *   63       48 47    32 31            20 19               0
 		 */
-		printk(KERN_INFO "RWB[desc]      [ck ipid mrqhsh] "
-		       "[vl   l0 ee  es] "
-		       "[ l3  l2  l1 hs] [reserved      ] ---------------- "
-		       "[bi->skb] <-- Ext Rx Write-Back format\n");
+		pr_info("RWB[desc]      [ck ipid mrqhsh] [vl   l0 ee  es] [ l3  l2  l1 hs] [reserved      ] ---------------- [bi->skb] <-- Ext Rx Write-Back format\n");
 		for (i = 0; i < rx_ring->count; i++) {
+			const char *next_desc;
 			buffer_info = &rx_ring->buffer_info[i];
 			rx_desc_ps = E1000_RX_DESC_PS(*rx_ring, i);
 			u1 = (struct my_u1 *)rx_desc_ps;
 			staterr =
 			    le32_to_cpu(rx_desc_ps->wb.middle.status_error);
+
+			if (i == rx_ring->next_to_use)
+				next_desc = " NTU";
+			else if (i == rx_ring->next_to_clean)
+				next_desc = " NTC";
+			else
+				next_desc = "";
+
 			if (staterr & E1000_RXD_STAT_DD) {
 				/* Descriptor Done */
-				printk(KERN_INFO "RWB[0x%03X]     %016llX "
-				       "%016llX %016llX %016llX "
-				       "---------------- %p", i,
-				       (unsigned long long)le64_to_cpu(u1->a),
-				       (unsigned long long)le64_to_cpu(u1->b),
-				       (unsigned long long)le64_to_cpu(u1->c),
-				       (unsigned long long)le64_to_cpu(u1->d),
-				       buffer_info->skb);
+				pr_info("%s[0x%03X]     %016llX %016llX %016llX %016llX ---------------- %p%s\n",
+					"RWB", i,
+					(unsigned long long)le64_to_cpu(u1->a),
+					(unsigned long long)le64_to_cpu(u1->b),
+					(unsigned long long)le64_to_cpu(u1->c),
+					(unsigned long long)le64_to_cpu(u1->d),
+					buffer_info->skb, next_desc);
 			} else {
-				printk(KERN_INFO "R  [0x%03X]     %016llX "
-				       "%016llX %016llX %016llX %016llX %p", i,
-				       (unsigned long long)le64_to_cpu(u1->a),
-				       (unsigned long long)le64_to_cpu(u1->b),
-				       (unsigned long long)le64_to_cpu(u1->c),
-				       (unsigned long long)le64_to_cpu(u1->d),
-				       (unsigned long long)buffer_info->dma,
-				       buffer_info->skb);
+				pr_info("%s[0x%03X]     %016llX %016llX %016llX %016llX %016llX %p%s\n",
+					"R  ", i,
+					(unsigned long long)le64_to_cpu(u1->a),
+					(unsigned long long)le64_to_cpu(u1->b),
+					(unsigned long long)le64_to_cpu(u1->c),
+					(unsigned long long)le64_to_cpu(u1->d),
+					(unsigned long long)buffer_info->dma,
+					buffer_info->skb, next_desc);
 
 				if (netif_msg_pktdata(adapter))
 					print_hex_dump(KERN_INFO, "",
@@ -388,13 +380,6 @@ rx_ring_summary:
 						phys_to_virt(buffer_info->dma),
 						adapter->rx_ps_bsize0, true);
 			}
-
-			if (i == rx_ring->next_to_use)
-				printk(KERN_CONT " NTU\n");
-			else if (i == rx_ring->next_to_clean)
-				printk(KERN_CONT " NTC\n");
-			else
-				printk(KERN_CONT "\n");
 		}
 		break;
 	default:
@@ -407,9 +392,7 @@ rx_ring_summary:
 		 * 8 |                      Reserved                       |
 		 *   +-----------------------------------------------------+
 		 */
-		printk(KERN_INFO "R  [desc]      [buf addr 63:0 ] "
-		       "[reserved 63:0 ] [bi->dma       ] "
-		       "[bi->skb] <-- Ext (Read) format\n");
+		pr_info("R  [desc]      [buf addr 63:0 ] [reserved 63:0 ] [bi->dma       ] [bi->skb] <-- Ext (Read) format\n");
 		/* Extended Receive Descriptor (Write-Back) Format
 		 *
 		 *   63       48 47    32 31    24 23            4 3        0
@@ -423,29 +406,37 @@ rx_ring_summary:
 		 *   +------------------------------------------------------+
 		 *   63       48 47    32 31            20 19               0
 		 */
-		printk(KERN_INFO "RWB[desc]      [cs ipid    mrq] "
-		       "[vt   ln xe  xs] "
-		       "[bi->skb] <-- Ext (Write-Back) format\n");
+		pr_info("RWB[desc]      [cs ipid    mrq] [vt   ln xe  xs] [bi->skb] <-- Ext (Write-Back) format\n");
 
 		for (i = 0; i < rx_ring->count; i++) {
+			const char *next_desc;
+
 			buffer_info = &rx_ring->buffer_info[i];
 			rx_desc = E1000_RX_DESC_EXT(*rx_ring, i);
 			u1 = (struct my_u1 *)rx_desc;
 			staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
+
+			if (i == rx_ring->next_to_use)
+				next_desc = " NTU";
+			else if (i == rx_ring->next_to_clean)
+				next_desc = " NTC";
+			else
+				next_desc = "";
+
 			if (staterr & E1000_RXD_STAT_DD) {
 				/* Descriptor Done */
-				printk(KERN_INFO "RWB[0x%03X]     %016llX "
-				       "%016llX ---------------- %p", i,
-				       (unsigned long long)le64_to_cpu(u1->a),
-				       (unsigned long long)le64_to_cpu(u1->b),
-				       buffer_info->skb);
+				pr_info("%s[0x%03X]     %016llX %016llX ---------------- %p%s\n",
+					"RWB", i,
+					(unsigned long long)le64_to_cpu(u1->a),
+					(unsigned long long)le64_to_cpu(u1->b),
+					buffer_info->skb, next_desc);
 			} else {
-				printk(KERN_INFO "R  [0x%03X]     %016llX "
-				       "%016llX %016llX %p", i,
-				       (unsigned long long)le64_to_cpu(u1->a),
-				       (unsigned long long)le64_to_cpu(u1->b),
-				       (unsigned long long)buffer_info->dma,
-				       buffer_info->skb);
+				pr_info("%s[0x%03X]     %016llX %016llX %016llX %p%s\n",
+					"R  ", i,
+					(unsigned long long)le64_to_cpu(u1->a),
+					(unsigned long long)le64_to_cpu(u1->b),
+					(unsigned long long)buffer_info->dma,
+					buffer_info->skb, next_desc);
 
 				if (netif_msg_pktdata(adapter))
 					print_hex_dump(KERN_INFO, "",
@@ -456,13 +447,6 @@ rx_ring_summary:
 						       adapter->rx_buffer_len,
 						       true);
 			}
-
-			if (i == rx_ring->next_to_use)
-				printk(KERN_CONT " NTU\n");
-			else if (i == rx_ring->next_to_clean)
-				printk(KERN_CONT " NTC\n");
-			else
-				printk(KERN_CONT "\n");
 		}
 	}
 
@@ -1030,6 +1014,7 @@ static void e1000_print_hw_hang(struct work_struct *work)
 	struct e1000_adapter *adapter = container_of(work,
 	                                             struct e1000_adapter,
 	                                             print_hang_task);
+	struct net_device *netdev = adapter->netdev;
 	struct e1000_ring *tx_ring = adapter->tx_ring;
 	unsigned int i = tx_ring->next_to_clean;
 	unsigned int eop = tx_ring->buffer_info[i].next_to_watch;
@@ -1041,6 +1026,21 @@ static void e1000_print_hw_hang(struct work_struct *work)
 	if (test_bit(__E1000_DOWN, &adapter->state))
 		return;
 
+	if (!adapter->tx_hang_recheck &&
+	    (adapter->flags2 & FLAG2_DMA_BURST)) {
+		/* May be block on write-back, flush and detect again
+		 * flush pending descriptor writebacks to memory
+		 */
+		ew32(TIDV, adapter->tx_int_delay | E1000_TIDV_FPD);
+		/* execute the writes immediately */
+		e1e_flush();
+		adapter->tx_hang_recheck = true;
+		return;
+	}
+	/* Real hang detected */
+	adapter->tx_hang_recheck = false;
+	netif_stop_queue(netdev);
+
 	e1e_rphy(hw, PHY_STATUS, &phy_status);
 	e1e_rphy(hw, PHY_1000T_STATUS, &phy_1000t_status);
 	e1e_rphy(hw, PHY_EXT_STATUS, &phy_ext_status);
@@ -1095,6 +1095,7 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter)
 	unsigned int i, eop;
 	unsigned int count = 0;
 	unsigned int total_tx_bytes = 0, total_tx_packets = 0;
+	unsigned int bytes_compl = 0, pkts_compl = 0;
 
 	i = tx_ring->next_to_clean;
 	eop = tx_ring->buffer_info[i].next_to_watch;
@@ -1112,6 +1113,10 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter)
 			if (cleaned) {
 				total_tx_packets += buffer_info->segs;
 				total_tx_bytes += buffer_info->bytecount;
+				if (buffer_info->skb) {
+					bytes_compl += buffer_info->skb->len;
+					pkts_compl++;
+				}
 			}
 
 			e1000_put_txbuf(adapter, buffer_info);
@@ -1130,6 +1135,8 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter)
 
 	tx_ring->next_to_clean = i;
 
+	netdev_completed_queue(netdev, pkts_compl, bytes_compl);
+
 #define TX_WAKE_THRESHOLD 32
 	if (count && netif_carrier_ok(netdev) &&
 	    e1000_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD) {
@@ -1154,10 +1161,10 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter)
 		if (tx_ring->buffer_info[i].time_stamp &&
 		    time_after(jiffies, tx_ring->buffer_info[i].time_stamp
 			       + (adapter->tx_timeout_factor * HZ)) &&
-		    !(er32(STATUS) & E1000_STATUS_TXOFF)) {
+		    !(er32(STATUS) & E1000_STATUS_TXOFF))
 			schedule_work(&adapter->print_hang_task);
-			netif_stop_queue(netdev);
-		}
+		else
+			adapter->tx_hang_recheck = false;
 	}
 	adapter->total_tx_bytes += total_tx_bytes;
 	adapter->total_tx_packets += total_tx_packets;
@@ -1222,8 +1229,7 @@ static bool e1000_clean_rx_irq_ps(struct e1000_adapter *adapter,
 			adapter->flags2 |= FLAG2_IS_DISCARDING;
 
 		if (adapter->flags2 & FLAG2_IS_DISCARDING) {
-			e_dbg("Packet Split buffers didn't pick up the full "
-			      "packet\n");
+			e_dbg("Packet Split buffers didn't pick up the full packet\n");
 			dev_kfree_skb_irq(skb);
 			if (staterr & E1000_RXD_STAT_EOP)
 				adapter->flags2 &= ~FLAG2_IS_DISCARDING;
@@ -1238,8 +1244,7 @@ static bool e1000_clean_rx_irq_ps(struct e1000_adapter *adapter,
 		length = le16_to_cpu(rx_desc->wb.middle.length0);
 
 		if (!length) {
-			e_dbg("Last part of the packet spanning multiple "
-			      "descriptors\n");
+			e_dbg("Last part of the packet spanning multiple descriptors\n");
 			dev_kfree_skb_irq(skb);
 			goto next_desc;
 		}
@@ -1917,8 +1922,7 @@ void e1000e_set_interrupt_capability(struct e1000_adapter *adapter)
 					return;
 			}
 			/* MSI-X failed, so fall through and try MSI */
-			e_err("Failed to initialize MSI-X interrupts.  "
-			      "Falling back to MSI interrupts.\n");
+			e_err("Failed to initialize MSI-X interrupts.  Falling back to MSI interrupts.\n");
 			e1000e_reset_interrupt_capability(adapter);
 		}
 		adapter->int_mode = E1000E_INT_MODE_MSI;
@@ -1928,8 +1932,7 @@ void e1000e_set_interrupt_capability(struct e1000_adapter *adapter)
 			adapter->flags |= FLAG_MSI_ENABLED;
 		} else {
 			adapter->int_mode = E1000E_INT_MODE_LEGACY;
-			e_err("Failed to initialize MSI interrupts.  Falling "
-			      "back to legacy interrupts.\n");
+			e_err("Failed to initialize MSI interrupts.  Falling back to legacy interrupts.\n");
 		}
 		/* Fall through */
 	case E1000E_INT_MODE_LEGACY:
@@ -2260,6 +2263,7 @@ static void e1000_clean_tx_ring(struct e1000_adapter *adapter)
 		e1000_put_txbuf(adapter, buffer_info);
 	}
 
+	netdev_reset_queue(adapter->netdev);
 	size = sizeof(struct e1000_buffer) * tx_ring->count;
 	memset(tx_ring->buffer_info, 0, size);
 
@@ -2518,7 +2522,7 @@ clean_rx:
 	return work_done;
 }
 
-static void e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
+static int e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -2528,7 +2532,7 @@ static void e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 	if ((adapter->hw.mng_cookie.status &
 	     E1000_MNG_DHCP_COOKIE_STATUS_VLAN) &&
 	    (vid == adapter->mng_vlan_id))
-		return;
+		return 0;
 
 	/* add VID to filter table */
 	if (adapter->flags & FLAG_HAS_HW_VLAN_FILTER) {
@@ -2539,9 +2543,11 @@ static void e1000_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 	}
 
 	set_bit(vid, adapter->active_vlans);
+
+	return 0;
 }
 
-static void e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
+static int e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -2552,7 +2558,7 @@ static void e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 	    (vid == adapter->mng_vlan_id)) {
 		/* release control to f/w */
 		e1000e_release_hw_control(adapter);
-		return;
+		return 0;
 	}
 
 	/* remove VID from filter table */
@@ -2564,6 +2570,8 @@ static void e1000_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 	}
 
 	clear_bit(vid, adapter->active_vlans);
+
+	return 0;
 }
 
 /**
@@ -3113,79 +3121,147 @@ static void e1000_configure_rx(struct e1000_adapter *adapter)
 }
 
 /**
- *  e1000_update_mc_addr_list - Update Multicast addresses
- *  @hw: pointer to the HW structure
- *  @mc_addr_list: array of multicast addresses to program
- *  @mc_addr_count: number of multicast addresses to program
+ * e1000e_write_mc_addr_list - write multicast addresses to MTA
+ * @netdev: network interface device structure
+ *
+ * Writes multicast address list to the MTA hash table.
+ * Returns: -ENOMEM on failure
+ *                0 on no addresses written
+ *                X on writing X addresses to MTA
+ */
+static int e1000e_write_mc_addr_list(struct net_device *netdev)
+{
+	struct e1000_adapter *adapter = netdev_priv(netdev);
+	struct e1000_hw *hw = &adapter->hw;
+	struct netdev_hw_addr *ha;
+	u8 *mta_list;
+	int i;
+
+	if (netdev_mc_empty(netdev)) {
+		/* nothing to program, so clear mc list */
+		hw->mac.ops.update_mc_addr_list(hw, NULL, 0);
+		return 0;
+	}
+
+	mta_list = kzalloc(netdev_mc_count(netdev) * ETH_ALEN, GFP_ATOMIC);
+	if (!mta_list)
+		return -ENOMEM;
+
+	/* update_mc_addr_list expects a packed array of only addresses. */
+	i = 0;
+	netdev_for_each_mc_addr(ha, netdev)
+		memcpy(mta_list + (i++ * ETH_ALEN), ha->addr, ETH_ALEN);
+
+	hw->mac.ops.update_mc_addr_list(hw, mta_list, i);
+	kfree(mta_list);
+
+	return netdev_mc_count(netdev);
+}
+
+/**
+ * e1000e_write_uc_addr_list - write unicast addresses to RAR table
+ * @netdev: network interface device structure
  *
- *  Updates the Multicast Table Array.
- *  The caller must have a packed mc_addr_list of multicast addresses.
+ * Writes unicast address list to the RAR table.
+ * Returns: -ENOMEM on failure/insufficient address space
+ *                0 on no addresses written
+ *                X on writing X addresses to the RAR table
  **/
-static void e1000_update_mc_addr_list(struct e1000_hw *hw, u8 *mc_addr_list,
-				      u32 mc_addr_count)
+static int e1000e_write_uc_addr_list(struct net_device *netdev)
 {
-	hw->mac.ops.update_mc_addr_list(hw, mc_addr_list, mc_addr_count);
+	struct e1000_adapter *adapter = netdev_priv(netdev);
+	struct e1000_hw *hw = &adapter->hw;
+	unsigned int rar_entries = hw->mac.rar_entry_count;
+	int count = 0;
+
+	/* save a rar entry for our hardware address */
+	rar_entries--;
+
+	/* save a rar entry for the LAA workaround */
+	if (adapter->flags & FLAG_RESET_OVERWRITES_LAA)
+		rar_entries--;
+
+	/* return ENOMEM indicating insufficient memory for addresses */
+	if (netdev_uc_count(netdev) > rar_entries)
+		return -ENOMEM;
+
+	if (!netdev_uc_empty(netdev) && rar_entries) {
+		struct netdev_hw_addr *ha;
+
+		/*
+		 * write the addresses in reverse order to avoid write
+		 * combining
+		 */
+		netdev_for_each_uc_addr(ha, netdev) {
+			if (!rar_entries)
+				break;
+			e1000e_rar_set(hw, ha->addr, rar_entries--);
+			count++;
+		}
+	}
+
+	/* zero out the remaining RAR entries not used above */
+	for (; rar_entries > 0; rar_entries--) {
+		ew32(RAH(rar_entries), 0);
+		ew32(RAL(rar_entries), 0);
+	}
+	e1e_flush();
+
+	return count;
 }
 
 /**
- * e1000_set_multi - Multicast and Promiscuous mode set
+ * e1000e_set_rx_mode - secondary unicast, Multicast and Promiscuous mode set
  * @netdev: network interface device structure
  *
- * The set_multi entry point is called whenever the multicast address
- * list or the network interface flags are updated.  This routine is
- * responsible for configuring the hardware for proper multicast,
+ * The ndo_set_rx_mode entry point is called whenever the unicast or multicast
+ * address list or the network interface flags are updated.  This routine is
+ * responsible for configuring the hardware for proper unicast, multicast,
  * promiscuous mode, and all-multi behavior.
  **/
-static void e1000_set_multi(struct net_device *netdev)
+static void e1000e_set_rx_mode(struct net_device *netdev)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
-	struct netdev_hw_addr *ha;
-	u8  *mta_list;
 	u32 rctl;
 
 	/* Check for Promiscuous and All Multicast modes */
-
 	rctl = er32(RCTL);
 
+	/* clear the affected bits */
+	rctl &= ~(E1000_RCTL_UPE | E1000_RCTL_MPE);
+
 	if (netdev->flags & IFF_PROMISC) {
 		rctl |= (E1000_RCTL_UPE | E1000_RCTL_MPE);
-		rctl &= ~E1000_RCTL_VFE;
 		/* Do not hardware filter VLANs in promisc mode */
 		e1000e_vlan_filter_disable(adapter);
 	} else {
+		int count;
 		if (netdev->flags & IFF_ALLMULTI) {
 			rctl |= E1000_RCTL_MPE;
-			rctl &= ~E1000_RCTL_UPE;
 		} else {
-			rctl &= ~(E1000_RCTL_UPE | E1000_RCTL_MPE);
+			/*
+			 * Write addresses to the MTA, if the attempt fails
+			 * then we should just turn on promiscuous mode so
+			 * that we can at least receive multicast traffic
+			 */
+			count = e1000e_write_mc_addr_list(netdev);
+			if (count < 0)
+				rctl |= E1000_RCTL_MPE;
 		}
 		e1000e_vlan_filter_enable(adapter);
-	}
-
-	ew32(RCTL, rctl);
-
-	if (!netdev_mc_empty(netdev)) {
-		int i = 0;
-
-		mta_list = kmalloc(netdev_mc_count(netdev) * 6, GFP_ATOMIC);
-		if (!mta_list)
-			return;
-
-		/* prepare a packed array of only addresses. */
-		netdev_for_each_mc_addr(ha, netdev)
-			memcpy(mta_list + (i++ * ETH_ALEN), ha->addr, ETH_ALEN);
-
-		e1000_update_mc_addr_list(hw, mta_list, i);
-		kfree(mta_list);
-	} else {
 		/*
-		 * if we're called from probe, we might not have
-		 * anything to do here, so clear out the list
+		 * Write addresses to available RAR registers, if there is not
+		 * sufficient space to store all the addresses then enable
+		 * unicast promiscuous mode
 		 */
-		e1000_update_mc_addr_list(hw, NULL, 0);
+		count = e1000e_write_uc_addr_list(netdev);
+		if (count < 0)
+			rctl |= E1000_RCTL_UPE;
 	}
 
+	ew32(RCTL, rctl);
+
 	if (netdev->features & NETIF_F_HW_VLAN_RX)
 		e1000e_vlan_strip_enable(adapter);
 	else
@@ -3198,7 +3274,7 @@ static void e1000_set_multi(struct net_device *netdev)
  **/
 static void e1000_configure(struct e1000_adapter *adapter)
 {
-	e1000_set_multi(adapter->netdev);
+	e1000e_set_rx_mode(adapter->netdev);
 
 	e1000_restore_vlan(adapter);
 	e1000_init_manageability_pt(adapter);
@@ -3444,7 +3520,6 @@ int e1000e_up(struct e1000_adapter *adapter)
 
 	clear_bit(__E1000_DOWN, &adapter->state);
 
-	napi_enable(&adapter->napi);
 	if (adapter->msix_entries)
 		e1000_configure_msix(adapter);
 	e1000_irq_enable(adapter);
@@ -3506,7 +3581,6 @@ void e1000e_down(struct e1000_adapter *adapter)
 	e1e_flush();
 	usleep_range(10000, 20000);
 
-	napi_disable(&adapter->napi);
 	e1000_irq_disable(adapter);
 
 	del_timer_sync(&adapter->watchdog_timer);
@@ -3782,6 +3856,7 @@ static int e1000_open(struct net_device *netdev)
 
 	e1000_irq_enable(adapter);
 
+	adapter->tx_hang_recheck = false;
 	netif_start_queue(netdev);
 
 	adapter->idle_check = true;
@@ -3828,6 +3903,8 @@ static int e1000_close(struct net_device *netdev)
 
 	pm_runtime_get_sync(&pdev->dev);
 
+	napi_disable(&adapter->napi);
+
 	if (!test_bit(__E1000_DOWN, &adapter->state)) {
 		e1000e_down(adapter);
 		e1000_free_irq(adapter);
@@ -4168,16 +4245,13 @@ static void e1000_print_link_info(struct e1000_adapter *adapter)
 	u32 ctrl = er32(CTRL);
 
 	/* Link status message must follow this format for user tools */
-	printk(KERN_INFO "e1000e: %s NIC Link is Up %d Mbps %s, "
-	       "Flow Control: %s\n",
-	       adapter->netdev->name,
-	       adapter->link_speed,
-	       (adapter->link_duplex == FULL_DUPLEX) ?
-	       "Full Duplex" : "Half Duplex",
-	       ((ctrl & E1000_CTRL_TFCE) && (ctrl & E1000_CTRL_RFCE)) ?
-	       "Rx/Tx" :
-	       ((ctrl & E1000_CTRL_RFCE) ? "Rx" :
-		((ctrl & E1000_CTRL_TFCE) ? "Tx" : "None")));
+	printk(KERN_INFO "e1000e: %s NIC Link is Up %d Mbps %s Duplex, Flow Control: %s\n",
+		adapter->netdev->name,
+		adapter->link_speed,
+		adapter->link_duplex == FULL_DUPLEX ? "Full" : "Half",
+		(ctrl & E1000_CTRL_TFCE) && (ctrl & E1000_CTRL_RFCE) ? "Rx/Tx" :
+		(ctrl & E1000_CTRL_RFCE) ? "Rx" :
+		(ctrl & E1000_CTRL_TFCE) ? "Tx" : "None");
 }
 
 static bool e1000e_has_link(struct e1000_adapter *adapter)
@@ -4323,10 +4397,7 @@ static void e1000_watchdog_task(struct work_struct *work)
 				e1e_rphy(hw, PHY_AUTONEG_EXP, &autoneg_exp);
 
 				if (!(autoneg_exp & NWAY_ER_LP_NWAY_CAPS))
-					e_info("Autonegotiated half duplex but"
-					       " link partner cannot autoneg. "
-					       " Try forcing full duplex if "
-					       "link gets many collisions.\n");
+					e_info("Autonegotiated half duplex but link partner cannot autoneg.  Try forcing full duplex if link gets many collisions.\n");
 			}
 
 			/* adjust timeout factor according to speed/duplex */
@@ -4985,6 +5056,7 @@ static netdev_tx_t e1000_xmit_frame(struct sk_buff *skb,
 	/* if count is 0 then mapping error has occurred */
 	count = e1000_tx_map(adapter, skb, first, max_per_txd, nr_frags, mss);
 	if (count) {
+		netdev_sent_queue(netdev, skb->len);
 		e1000_tx_queue(adapter, tx_flags, count);
 		/* Make sure there is space in the ring for the next send. */
 		e1000_maybe_stop_tx(netdev, MAX_SKB_FRAGS + 2);
@@ -5110,8 +5182,7 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
 	if ((adapter->hw.mac.type == e1000_pch2lan) &&
 	    !(adapter->flags2 & FLAG2_CRC_STRIPPING) &&
 	    (new_mtu > ETH_DATA_LEN)) {
-		e_err("Jumbo Frames not supported on 82579 when CRC "
-		      "stripping is disabled.\n");
+		e_err("Jumbo Frames not supported on 82579 when CRC stripping is disabled.\n");
 		return -EINVAL;
 	}
 
@@ -5331,7 +5402,7 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool *enable_wake,
 
 	if (wufc) {
 		e1000_setup_rctl(adapter);
-		e1000_set_multi(netdev);
+		e1000e_set_rx_mode(netdev);
 
 		/* turn on all-multi mode if wake on multicast is enabled */
 		if (wufc & E1000_WUFC_MC) {
@@ -5527,8 +5598,8 @@ static int __e1000_resume(struct pci_dev *pdev)
 				phy_data & E1000_WUS_MC ? "Multicast Packet" :
 				phy_data & E1000_WUS_BC ? "Broadcast Packet" :
 				phy_data & E1000_WUS_MAG ? "Magic Packet" :
-				phy_data & E1000_WUS_LNKC ? "Link Status "
-				" Change" : "other");
+				phy_data & E1000_WUS_LNKC ?
+				"Link Status Change" : "other");
 		}
 		e1e_wphy(&adapter->hw, BM_WUS, ~0);
 	} else {
@@ -5859,10 +5930,11 @@ static void e1000_eeprom_checks(struct e1000_adapter *adapter)
 	}
 }
 
-static int e1000_set_features(struct net_device *netdev, u32 features)
+static int e1000_set_features(struct net_device *netdev,
+	netdev_features_t features)
 {
 	struct e1000_adapter *adapter = netdev_priv(netdev);
-	u32 changed = features ^ netdev->features;
+	netdev_features_t changed = features ^ netdev->features;
 
 	if (changed & (NETIF_F_TSO | NETIF_F_TSO6))
 		adapter->flags |= FLAG_TSO_FORCE;
@@ -5884,7 +5956,7 @@ static const struct net_device_ops e1000e_netdev_ops = {
 	.ndo_stop		= e1000_close,
 	.ndo_start_xmit		= e1000_xmit_frame,
 	.ndo_get_stats64	= e1000e_get_stats64,
-	.ndo_set_rx_mode	= e1000_set_multi,
+	.ndo_set_rx_mode	= e1000e_set_rx_mode,
 	.ndo_set_mac_address	= e1000_set_mac,
 	.ndo_change_mtu		= e1000_change_mtu,
 	.ndo_do_ioctl		= e1000_ioctl,
@@ -5949,8 +6021,7 @@ static int __devinit e1000_probe(struct pci_dev *pdev,
 			err = dma_set_coherent_mask(&pdev->dev,
 						    DMA_BIT_MASK(32));
 			if (err) {
-				dev_err(&pdev->dev, "No usable DMA "
-					"configuration, aborting\n");
+				dev_err(&pdev->dev, "No usable DMA configuration, aborting\n");
 				goto err_dma;
 			}
 		}
@@ -6076,6 +6147,8 @@ static int __devinit e1000_probe(struct pci_dev *pdev,
 				  NETIF_F_TSO6 |
 				  NETIF_F_HW_CSUM);
 
+	netdev->priv_flags |= IFF_UNICAST_FLT;
+
 	if (pci_using_dac) {
 		netdev->features |= NETIF_F_HIGHDMA;
 		netdev->vlan_features |= NETIF_F_HIGHDMA;
diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index 7881fb9..b8e20f0 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -29,6 +29,8 @@
  * e1000_82576
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/types.h>
 #include <linux/if_ether.h>
 
@@ -244,8 +246,7 @@ static s32 igb_get_invariants_82575(struct e1000_hw *hw)
 	 * Check for invalid size
 	 */
 	if ((hw->mac.type == e1000_82576) && (size > 15)) {
-		printk("igb: The NVM size is not valid, "
-			"defaulting to 32K.\n");
+		pr_notice("The NVM size is not valid, defaulting to 32K\n");
 		size = 15;
 	}
 	nvm->word_size = 1 << size;
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index 43873eb..e9335ef 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -673,25 +673,22 @@ static void igb_get_drvinfo(struct net_device *netdev,
 			    struct ethtool_drvinfo *drvinfo)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
-	char firmware_version[32];
 	u16 eeprom_data;
 
-	strncpy(drvinfo->driver,  igb_driver_name, sizeof(drvinfo->driver) - 1);
-	strncpy(drvinfo->version, igb_driver_version,
-		sizeof(drvinfo->version) - 1);
+	strlcpy(drvinfo->driver,  igb_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, igb_driver_version, sizeof(drvinfo->version));
 
 	/* EEPROM image version # is reported as firmware version # for
 	 * 82575 controllers */
 	adapter->hw.nvm.ops.read(&adapter->hw, 5, 1, &eeprom_data);
-	sprintf(firmware_version, "%d.%d-%d",
+	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+		"%d.%d-%d",
 		(eeprom_data & 0xF000) >> 12,
 		(eeprom_data & 0x0FF0) >> 4,
 		eeprom_data & 0x000F);
 
-	strncpy(drvinfo->fw_version, firmware_version,
-		sizeof(drvinfo->fw_version) - 1);
-	strncpy(drvinfo->bus_info, pci_name(adapter->pdev),
-		sizeof(drvinfo->bus_info) - 1);
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
 	drvinfo->n_stats = IGB_STATS_LEN;
 	drvinfo->testinfo_len = IGB_TEST_LEN;
 	drvinfo->regdump_len = igb_get_regs_len(netdev);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index ced5444..89d576ce 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -25,6 +25,8 @@
 
 *******************************************************************************/
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/init.h>
@@ -145,9 +147,9 @@ static bool igb_clean_rx_irq(struct igb_q_vector *, int);
 static int igb_ioctl(struct net_device *, struct ifreq *, int cmd);
 static void igb_tx_timeout(struct net_device *);
 static void igb_reset_task(struct work_struct *);
-static void igb_vlan_mode(struct net_device *netdev, u32 features);
-static void igb_vlan_rx_add_vid(struct net_device *, u16);
-static void igb_vlan_rx_kill_vid(struct net_device *, u16);
+static void igb_vlan_mode(struct net_device *netdev, netdev_features_t features);
+static int igb_vlan_rx_add_vid(struct net_device *, u16);
+static int igb_vlan_rx_kill_vid(struct net_device *, u16);
 static void igb_restore_vlan(struct igb_adapter *);
 static void igb_rar_set_qsel(struct igb_adapter *, u8 *, u32 , u8);
 static void igb_ping_all_vfs(struct igb_adapter *);
@@ -325,16 +327,13 @@ static void igb_regdump(struct e1000_hw *hw, struct igb_reg_info *reginfo)
 			regs[n] = rd32(E1000_TXDCTL(n));
 		break;
 	default:
-		printk(KERN_INFO "%-15s %08x\n",
-			reginfo->name, rd32(reginfo->ofs));
+		pr_info("%-15s %08x\n", reginfo->name, rd32(reginfo->ofs));
 		return;
 	}
 
 	snprintf(rname, 16, "%s%s", reginfo->name, "[0-3]");
-	printk(KERN_INFO "%-15s ", rname);
-	for (n = 0; n < 4; n++)
-		printk(KERN_CONT "%08x ", regs[n]);
-	printk(KERN_CONT "\n");
+	pr_info("%-15s %08x %08x %08x %08x\n", rname, regs[0], regs[1],
+		regs[2], regs[3]);
 }
 
 /*
@@ -359,18 +358,15 @@ static void igb_dump(struct igb_adapter *adapter)
 	/* Print netdevice Info */
 	if (netdev) {
 		dev_info(&adapter->pdev->dev, "Net device Info\n");
-		printk(KERN_INFO "Device Name     state            "
-			"trans_start      last_rx\n");
-		printk(KERN_INFO "%-15s %016lX %016lX %016lX\n",
-		netdev->name,
-		netdev->state,
-		netdev->trans_start,
-		netdev->last_rx);
+		pr_info("Device Name     state            trans_start      "
+			"last_rx\n");
+		pr_info("%-15s %016lX %016lX %016lX\n", netdev->name,
+			netdev->state, netdev->trans_start, netdev->last_rx);
 	}
 
 	/* Print Registers */
 	dev_info(&adapter->pdev->dev, "Register Dump\n");
-	printk(KERN_INFO " Register Name   Value\n");
+	pr_info(" Register Name   Value\n");
 	for (reginfo = (struct igb_reg_info *)igb_reg_info_tbl;
 	     reginfo->name; reginfo++) {
 		igb_regdump(hw, reginfo);
@@ -381,18 +377,17 @@ static void igb_dump(struct igb_adapter *adapter)
 		goto exit;
 
 	dev_info(&adapter->pdev->dev, "TX Rings Summary\n");
-	printk(KERN_INFO "Queue [NTU] [NTC] [bi(ntc)->dma  ]"
-		" leng ntw timestamp\n");
+	pr_info("Queue [NTU] [NTC] [bi(ntc)->dma  ] leng ntw timestamp\n");
 	for (n = 0; n < adapter->num_tx_queues; n++) {
 		struct igb_tx_buffer *buffer_info;
 		tx_ring = adapter->tx_ring[n];
 		buffer_info = &tx_ring->tx_buffer_info[tx_ring->next_to_clean];
-		printk(KERN_INFO " %5d %5X %5X %016llX %04X %p %016llX\n",
-			   n, tx_ring->next_to_use, tx_ring->next_to_clean,
-			   (u64)buffer_info->dma,
-			   buffer_info->length,
-			   buffer_info->next_to_watch,
-			   (u64)buffer_info->time_stamp);
+		pr_info(" %5d %5X %5X %016llX %04X %p %016llX\n",
+			n, tx_ring->next_to_use, tx_ring->next_to_clean,
+			(u64)buffer_info->dma,
+			buffer_info->length,
+			buffer_info->next_to_watch,
+			(u64)buffer_info->time_stamp);
 	}
 
 	/* Print TX Rings */
@@ -414,36 +409,38 @@ static void igb_dump(struct igb_adapter *adapter)
 
 	for (n = 0; n < adapter->num_tx_queues; n++) {
 		tx_ring = adapter->tx_ring[n];
-		printk(KERN_INFO "------------------------------------\n");
-		printk(KERN_INFO "TX QUEUE INDEX = %d\n", tx_ring->queue_index);
-		printk(KERN_INFO "------------------------------------\n");
-		printk(KERN_INFO "T [desc]     [address 63:0  ] "
-			"[PlPOCIStDDM Ln] [bi->dma       ] "
-			"leng  ntw timestamp        bi->skb\n");
+		pr_info("------------------------------------\n");
+		pr_info("TX QUEUE INDEX = %d\n", tx_ring->queue_index);
+		pr_info("------------------------------------\n");
+		pr_info("T [desc]     [address 63:0  ] [PlPOCIStDDM Ln] "
+			"[bi->dma       ] leng  ntw timestamp        "
+			"bi->skb\n");
 
 		for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) {
+			const char *next_desc;
 			struct igb_tx_buffer *buffer_info;
 			tx_desc = IGB_TX_DESC(tx_ring, i);
 			buffer_info = &tx_ring->tx_buffer_info[i];
 			u0 = (struct my_u0 *)tx_desc;
-			printk(KERN_INFO "T [0x%03X]    %016llX %016llX %016llX"
-				" %04X  %p %016llX %p", i,
+			if (i == tx_ring->next_to_use &&
+			    i == tx_ring->next_to_clean)
+				next_desc = " NTC/U";
+			else if (i == tx_ring->next_to_use)
+				next_desc = " NTU";
+			else if (i == tx_ring->next_to_clean)
+				next_desc = " NTC";
+			else
+				next_desc = "";
+
+			pr_info("T [0x%03X]    %016llX %016llX %016llX"
+				" %04X  %p %016llX %p%s\n", i,
 				le64_to_cpu(u0->a),
 				le64_to_cpu(u0->b),
 				(u64)buffer_info->dma,
 				buffer_info->length,
 				buffer_info->next_to_watch,
 				(u64)buffer_info->time_stamp,
-				buffer_info->skb);
-			if (i == tx_ring->next_to_use &&
-				i == tx_ring->next_to_clean)
-				printk(KERN_CONT " NTC/U\n");
-			else if (i == tx_ring->next_to_use)
-				printk(KERN_CONT " NTU\n");
-			else if (i == tx_ring->next_to_clean)
-				printk(KERN_CONT " NTC\n");
-			else
-				printk(KERN_CONT "\n");
+				buffer_info->skb, next_desc);
 
 			if (netif_msg_pktdata(adapter) && buffer_info->dma != 0)
 				print_hex_dump(KERN_INFO, "",
@@ -456,11 +453,11 @@ static void igb_dump(struct igb_adapter *adapter)
 	/* Print RX Rings Summary */
 rx_ring_summary:
 	dev_info(&adapter->pdev->dev, "RX Rings Summary\n");
-	printk(KERN_INFO "Queue [NTU] [NTC]\n");
+	pr_info("Queue [NTU] [NTC]\n");
 	for (n = 0; n < adapter->num_rx_queues; n++) {
 		rx_ring = adapter->rx_ring[n];
-		printk(KERN_INFO " %5d %5X %5X\n", n,
-			   rx_ring->next_to_use, rx_ring->next_to_clean);
+		pr_info(" %5d %5X %5X\n",
+			n, rx_ring->next_to_use, rx_ring->next_to_clean);
 	}
 
 	/* Print RX Rings */
@@ -492,36 +489,43 @@ rx_ring_summary:
 
 	for (n = 0; n < adapter->num_rx_queues; n++) {
 		rx_ring = adapter->rx_ring[n];
-		printk(KERN_INFO "------------------------------------\n");
-		printk(KERN_INFO "RX QUEUE INDEX = %d\n", rx_ring->queue_index);
-		printk(KERN_INFO "------------------------------------\n");
-		printk(KERN_INFO "R  [desc]      [ PktBuf     A0] "
-			"[  HeadBuf   DD] [bi->dma       ] [bi->skb] "
-			"<-- Adv Rx Read format\n");
-		printk(KERN_INFO "RWB[desc]      [PcsmIpSHl PtRs] "
-			"[vl er S cks ln] ---------------- [bi->skb] "
-			"<-- Adv Rx Write-Back format\n");
+		pr_info("------------------------------------\n");
+		pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index);
+		pr_info("------------------------------------\n");
+		pr_info("R  [desc]      [ PktBuf     A0] [  HeadBuf   DD] "
+			"[bi->dma       ] [bi->skb] <-- Adv Rx Read format\n");
+		pr_info("RWB[desc]      [PcsmIpSHl PtRs] [vl er S cks ln] -----"
+			"----------- [bi->skb] <-- Adv Rx Write-Back format\n");
 
 		for (i = 0; i < rx_ring->count; i++) {
+			const char *next_desc;
 			struct igb_rx_buffer *buffer_info;
 			buffer_info = &rx_ring->rx_buffer_info[i];
 			rx_desc = IGB_RX_DESC(rx_ring, i);
 			u0 = (struct my_u0 *)rx_desc;
 			staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
+
+			if (i == rx_ring->next_to_use)
+				next_desc = " NTU";
+			else if (i == rx_ring->next_to_clean)
+				next_desc = " NTC";
+			else
+				next_desc = "";
+
 			if (staterr & E1000_RXD_STAT_DD) {
 				/* Descriptor Done */
-				printk(KERN_INFO "RWB[0x%03X]     %016llX "
-					"%016llX ---------------- %p", i,
+				pr_info("%s[0x%03X]     %016llX %016llX -------"
+					"--------- %p%s\n", "RWB", i,
 					le64_to_cpu(u0->a),
 					le64_to_cpu(u0->b),
-					buffer_info->skb);
+					buffer_info->skb, next_desc);
 			} else {
-				printk(KERN_INFO "R  [0x%03X]     %016llX "
-					"%016llX %016llX %p", i,
+				pr_info("%s[0x%03X]     %016llX %016llX %016llX"
+					" %p%s\n", "R  ", i,
 					le64_to_cpu(u0->a),
 					le64_to_cpu(u0->b),
 					(u64)buffer_info->dma,
-					buffer_info->skb);
+					buffer_info->skb, next_desc);
 
 				if (netif_msg_pktdata(adapter)) {
 					print_hex_dump(KERN_INFO, "",
@@ -538,14 +542,6 @@ rx_ring_summary:
 					  PAGE_SIZE/2, true);
 				}
 			}
-
-			if (i == rx_ring->next_to_use)
-				printk(KERN_CONT " NTU\n");
-			else if (i == rx_ring->next_to_clean)
-				printk(KERN_CONT " NTC\n");
-			else
-				printk(KERN_CONT "\n");
-
 		}
 	}
 
@@ -599,10 +595,10 @@ struct net_device *igb_get_hw_dev(struct e1000_hw *hw)
 static int __init igb_init_module(void)
 {
 	int ret;
-	printk(KERN_INFO "%s - version %s\n",
+	pr_info("%s - version %s\n",
 	       igb_driver_string, igb_driver_version);
 
-	printk(KERN_INFO "%s\n", igb_copyright);
+	pr_info("%s\n", igb_copyright);
 
 #ifdef CONFIG_IGB_DCA
 	dca_register_notify(&dca_notifier);
@@ -1742,7 +1738,8 @@ void igb_reset(struct igb_adapter *adapter)
 	igb_get_phy_info(hw);
 }
 
-static u32 igb_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t igb_fix_features(struct net_device *netdev,
+	netdev_features_t features)
 {
 	/*
 	 * Since there is no support for separate rx/tx vlan accel
@@ -1756,9 +1753,10 @@ static u32 igb_fix_features(struct net_device *netdev, u32 features)
 	return features;
 }
 
-static int igb_set_features(struct net_device *netdev, u32 features)
+static int igb_set_features(struct net_device *netdev,
+	netdev_features_t features)
 {
-	u32 changed = netdev->features ^ features;
+	netdev_features_t changed = netdev->features ^ features;
 
 	if (changed & NETIF_F_HW_VLAN_RX)
 		igb_vlan_mode(netdev, features);
@@ -3640,23 +3638,23 @@ static void igb_watchdog_task(struct work_struct *work)
 
 			ctrl = rd32(E1000_CTRL);
 			/* Links status message must follow this format */
-			printk(KERN_INFO "igb: %s NIC Link is Up %d Mbps %s, "
-				 "Flow Control: %s\n",
+			printk(KERN_INFO "igb: %s NIC Link is Up %d Mbps %s "
+			       "Duplex, Flow Control: %s\n",
 			       netdev->name,
 			       adapter->link_speed,
 			       adapter->link_duplex == FULL_DUPLEX ?
-				 "Full Duplex" : "Half Duplex",
-			       ((ctrl & E1000_CTRL_TFCE) &&
-			        (ctrl & E1000_CTRL_RFCE)) ? "RX/TX" :
-			       ((ctrl & E1000_CTRL_RFCE) ?  "RX" :
-			       ((ctrl & E1000_CTRL_TFCE) ?  "TX" : "None")));
+			       "Full" : "Half",
+			       (ctrl & E1000_CTRL_TFCE) &&
+			       (ctrl & E1000_CTRL_RFCE) ? "RX/TX" :
+			       (ctrl & E1000_CTRL_RFCE) ?  "RX" :
+			       (ctrl & E1000_CTRL_TFCE) ?  "TX" : "None");
 
 			/* check for thermal sensor event */
-			if (igb_thermal_sensor_event(hw, E1000_THSTAT_LINK_THROTTLE)) {
-				printk(KERN_INFO "igb: %s The network adapter "
-						 "link speed was downshifted "
-						 "because it overheated.\n",
-						 netdev->name);
+			if (igb_thermal_sensor_event(hw,
+			    E1000_THSTAT_LINK_THROTTLE)) {
+				netdev_info(netdev, "The network adapter link "
+					    "speed was downshifted because it "
+					    "overheated\n");
 			}
 
 			/* adjust timeout factor according to speed/duplex */
@@ -3686,11 +3684,10 @@ static void igb_watchdog_task(struct work_struct *work)
 			adapter->link_duplex = 0;
 
 			/* check for thermal sensor event */
-			if (igb_thermal_sensor_event(hw, E1000_THSTAT_PWR_DOWN)) {
-				printk(KERN_ERR "igb: %s The network adapter "
-						"was stopped because it "
-						"overheated.\n",
-						netdev->name);
+			if (igb_thermal_sensor_event(hw,
+			    E1000_THSTAT_PWR_DOWN)) {
+				netdev_err(netdev, "The network adapter was "
+					   "stopped because it overheated\n");
 			}
 
 			/* Links status message must follow this format */
@@ -6138,7 +6135,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 		return true;
 
 	if (!page) {
-		page = netdev_alloc_page(rx_ring->netdev);
+		page = alloc_page(GFP_ATOMIC | __GFP_COLD);
 		bi->page = page;
 		if (unlikely(!page)) {
 			rx_ring->rx_stats.alloc_failed++;
@@ -6467,7 +6464,7 @@ s32 igb_write_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value)
 	return 0;
 }
 
-static void igb_vlan_mode(struct net_device *netdev, u32 features)
+static void igb_vlan_mode(struct net_device *netdev, netdev_features_t features)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -6494,7 +6491,7 @@ static void igb_vlan_mode(struct net_device *netdev, u32 features)
 	igb_rlpml_set(adapter);
 }
 
-static void igb_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
+static int igb_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -6507,9 +6504,11 @@ static void igb_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 	igb_vfta_set(hw, vid, true);
 
 	set_bit(vid, adapter->active_vlans);
+
+	return 0;
 }
 
-static void igb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
+static int igb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 {
 	struct igb_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -6524,6 +6523,8 @@ static void igb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 		igb_vfta_set(hw, vid, false);
 
 	clear_bit(vid, adapter->active_vlans);
+
+	return 0;
 }
 
 static void igb_restore_vlan(struct igb_adapter *adapter)
@@ -7064,15 +7065,28 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba)
 			wr32(E1000_DMCTXTH, 0);
 
 			/*
-			 * DMA Coalescing high water mark needs to be higher
-			 * than the RX threshold. set hwm to PBA -  2 * max
-			 * frame size
+			 * DMA Coalescing high water mark needs to be greater
+			 * than the Rx threshold. Set hwm to PBA - max frame
+			 * size in 16B units, capping it at PBA - 6KB.
 			 */
-			hwm = pba - (2 * adapter->max_frame_size);
+			hwm = 64 * pba - adapter->max_frame_size / 16;
+			if (hwm < 64 * (pba - 6))
+				hwm = 64 * (pba - 6);
+			reg = rd32(E1000_FCRTC);
+			reg &= ~E1000_FCRTC_RTH_COAL_MASK;
+			reg |= ((hwm << E1000_FCRTC_RTH_COAL_SHIFT)
+				& E1000_FCRTC_RTH_COAL_MASK);
+			wr32(E1000_FCRTC, reg);
+
+			/*
+			 * Set the DMA Coalescing Rx threshold to PBA - 2 * max
+			 * frame size, capping it at PBA - 10KB.
+			 */
+			dmac_thr = pba - adapter->max_frame_size / 512;
+			if (dmac_thr < pba - 10)
+				dmac_thr = pba - 10;
 			reg = rd32(E1000_DMACR);
 			reg &= ~E1000_DMACR_DMACTHR_MASK;
-			dmac_thr = pba - 4;
-
 			reg |= ((dmac_thr << E1000_DMACR_DMACTHR_SHIFT)
 				& E1000_DMACR_DMACTHR_MASK);
 
@@ -7088,7 +7102,6 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba)
 			 * coalescing(smart fifb)-UTRESH=0
 			 */
 			wr32(E1000_DMCRTRH, 0);
-			wr32(E1000_FCRTC, hwm);
 
 			reg = (IGB_DMCTLX_DCFLUSH_DIS | 0x4);
 
diff --git a/drivers/net/ethernet/intel/igbvf/ethtool.c b/drivers/net/ethernet/intel/igbvf/ethtool.c
index 2c25858..7b600a1 100644
--- a/drivers/net/ethernet/intel/igbvf/ethtool.c
+++ b/drivers/net/ethernet/intel/igbvf/ethtool.c
@@ -191,12 +191,12 @@ static void igbvf_get_drvinfo(struct net_device *netdev,
                               struct ethtool_drvinfo *drvinfo)
 {
 	struct igbvf_adapter *adapter = netdev_priv(netdev);
-	char firmware_version[32] = "N/A";
 
-	strncpy(drvinfo->driver,  igbvf_driver_name, 32);
-	strncpy(drvinfo->version, igbvf_driver_version, 32);
-	strncpy(drvinfo->fw_version, firmware_version, 32);
-	strncpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+	strlcpy(drvinfo->driver,  igbvf_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, igbvf_driver_version,
+		sizeof(drvinfo->version));
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
 	drvinfo->regdump_len = igbvf_get_regs_len(netdev);
 	drvinfo->eedump_len = igbvf_get_eeprom_len(netdev);
 }
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index cca7812..fd3da30 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -25,6 +25,8 @@
 
 *******************************************************************************/
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/init.h>
@@ -1174,18 +1176,20 @@ static void igbvf_set_rlpml(struct igbvf_adapter *adapter)
 	e1000_rlpml_set_vf(hw, max_frame_size);
 }
 
-static void igbvf_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
+static int igbvf_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 {
 	struct igbvf_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
 
-	if (hw->mac.ops.set_vfta(hw, vid, true))
+	if (hw->mac.ops.set_vfta(hw, vid, true)) {
 		dev_err(&adapter->pdev->dev, "Failed to add vlan id %d\n", vid);
-	else
-		set_bit(vid, adapter->active_vlans);
+		return -EINVAL;
+	}
+	set_bit(vid, adapter->active_vlans);
+	return 0;
 }
 
-static void igbvf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
+static int igbvf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 {
 	struct igbvf_adapter *adapter = netdev_priv(netdev);
 	struct e1000_hw *hw = &adapter->hw;
@@ -1195,11 +1199,13 @@ static void igbvf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 	if (!test_bit(__IGBVF_DOWN, &adapter->state))
 		igbvf_irq_enable(adapter);
 
-	if (hw->mac.ops.set_vfta(hw, vid, false))
+	if (hw->mac.ops.set_vfta(hw, vid, false)) {
 		dev_err(&adapter->pdev->dev,
 		        "Failed to remove vlan id %d\n", vid);
-	else
-		clear_bit(vid, adapter->active_vlans);
+		return -EINVAL;
+	}
+	clear_bit(vid, adapter->active_vlans);
+	return 0;
 }
 
 static void igbvf_restore_vlan(struct igbvf_adapter *adapter)
@@ -1746,10 +1752,9 @@ void igbvf_update_stats(struct igbvf_adapter *adapter)
 
 static void igbvf_print_link_info(struct igbvf_adapter *adapter)
 {
-	dev_info(&adapter->pdev->dev, "Link is Up %d Mbps %s\n",
-	         adapter->link_speed,
-	         ((adapter->link_duplex == FULL_DUPLEX) ?
-	          "Full Duplex" : "Half Duplex"));
+	dev_info(&adapter->pdev->dev, "Link is Up %d Mbps %s Duplex\n",
+		 adapter->link_speed,
+		 adapter->link_duplex == FULL_DUPLEX ? "Full" : "Half");
 }
 
 static bool igbvf_has_link(struct igbvf_adapter *adapter)
@@ -2532,7 +2537,8 @@ static void igbvf_print_device_info(struct igbvf_adapter *adapter)
 	dev_info(&pdev->dev, "Address: %pM\n", netdev->dev_addr);
 }
 
-static int igbvf_set_features(struct net_device *netdev, u32 features)
+static int igbvf_set_features(struct net_device *netdev,
+	netdev_features_t features)
 {
 	struct igbvf_adapter *adapter = netdev_priv(netdev);
 
@@ -2842,9 +2848,8 @@ static struct pci_driver igbvf_driver = {
 static int __init igbvf_init_module(void)
 {
 	int ret;
-	printk(KERN_INFO "%s - version %s\n",
-	       igbvf_driver_string, igbvf_driver_version);
-	printk(KERN_INFO "%s\n", igbvf_copyright);
+	pr_info("%s - version %s\n", igbvf_driver_string, igbvf_driver_version);
+	pr_info("%s\n", igbvf_copyright);
 
 	ret = pci_register_driver(&igbvf_driver);
 
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
index 9dfce7d..dbb7dd2 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c
@@ -473,10 +473,12 @@ ixgb_get_drvinfo(struct net_device *netdev,
 {
 	struct ixgb_adapter *adapter = netdev_priv(netdev);
 
-	strncpy(drvinfo->driver,  ixgb_driver_name, 32);
-	strncpy(drvinfo->version, ixgb_driver_version, 32);
-	strncpy(drvinfo->fw_version, "N/A", 32);
-	strncpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+	strlcpy(drvinfo->driver,  ixgb_driver_name,
+		sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, ixgb_driver_version,
+		sizeof(drvinfo->version));
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
 	drvinfo->n_stats = IXGB_STATS_LEN;
 	drvinfo->regdump_len = ixgb_get_regs_len(netdev);
 	drvinfo->eedump_len = ixgb_get_eeprom_len(netdev);
diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
index e21148f..c573655f 100644
--- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c
+++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c
@@ -101,8 +101,8 @@ static void ixgb_tx_timeout_task(struct work_struct *work);
 
 static void ixgb_vlan_strip_enable(struct ixgb_adapter *adapter);
 static void ixgb_vlan_strip_disable(struct ixgb_adapter *adapter);
-static void ixgb_vlan_rx_add_vid(struct net_device *netdev, u16 vid);
-static void ixgb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid);
+static int ixgb_vlan_rx_add_vid(struct net_device *netdev, u16 vid);
+static int ixgb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid);
 static void ixgb_restore_vlan(struct ixgb_adapter *adapter);
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -325,8 +325,8 @@ ixgb_reset(struct ixgb_adapter *adapter)
 	}
 }
 
-static u32
-ixgb_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t
+ixgb_fix_features(struct net_device *netdev, netdev_features_t features)
 {
 	/*
 	 * Tx VLAN insertion does not work per HW design when Rx stripping is
@@ -339,10 +339,10 @@ ixgb_fix_features(struct net_device *netdev, u32 features)
 }
 
 static int
-ixgb_set_features(struct net_device *netdev, u32 features)
+ixgb_set_features(struct net_device *netdev, netdev_features_t features)
 {
 	struct ixgb_adapter *adapter = netdev_priv(netdev);
-	u32 changed = features ^ netdev->features;
+	netdev_features_t changed = features ^ netdev->features;
 
 	if (!(changed & (NETIF_F_RXCSUM|NETIF_F_HW_VLAN_RX)))
 		return 0;
@@ -2217,7 +2217,7 @@ ixgb_vlan_strip_disable(struct ixgb_adapter *adapter)
 	IXGB_WRITE_REG(&adapter->hw, CTRL0, ctrl);
 }
 
-static void
+static int
 ixgb_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 {
 	struct ixgb_adapter *adapter = netdev_priv(netdev);
@@ -2230,9 +2230,11 @@ ixgb_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 	vfta |= (1 << (vid & 0x1F));
 	ixgb_write_vfta(&adapter->hw, index, vfta);
 	set_bit(vid, adapter->active_vlans);
+
+	return 0;
 }
 
-static void
+static int
 ixgb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 {
 	struct ixgb_adapter *adapter = netdev_priv(netdev);
@@ -2245,6 +2247,8 @@ ixgb_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 	vfta &= ~(1 << (vid & 0x1F));
 	ixgb_write_vfta(&adapter->hw, index, vfta);
 	clear_bit(vid, adapter->active_vlans);
+
+	return 0;
 }
 
 static void
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
index 33b93ff..da31735 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c
@@ -158,10 +158,6 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
-	/* Abort a bad configuration */
-	if (ffs(up_map) > adapter->dcb_cfg.num_tcs.pg_tcs)
-		return;
-
 	if (prio != DCB_ATTR_VALUE_UNDEFINED)
 		adapter->temp_dcb_cfg.tc_config[tc].path[0].prio_type = prio;
 	if (bwg_id != DCB_ATTR_VALUE_UNDEFINED)
@@ -185,7 +181,7 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc,
 
 	if (adapter->temp_dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap !=
 	     adapter->dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap)
-		adapter->dcb_set_bitmap |= BIT_PFC;
+		adapter->dcb_set_bitmap |= BIT_PFC | BIT_APP_UPCHG;
 }
 
 static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id,
@@ -206,10 +202,6 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc,
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
-	/* Abort bad configurations */
-	if (ffs(up_map) > adapter->dcb_cfg.num_tcs.pg_tcs)
-		return;
-
 	if (prio != DCB_ATTR_VALUE_UNDEFINED)
 		adapter->temp_dcb_cfg.tc_config[tc].path[1].prio_type = prio;
 	if (bwg_id != DCB_ATTR_VALUE_UNDEFINED)
@@ -309,6 +301,27 @@ static void ixgbe_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority,
 	*setting = adapter->dcb_cfg.tc_config[priority].dcb_pfc;
 }
 
+#ifdef IXGBE_FCOE
+static void ixgbe_dcbnl_devreset(struct net_device *dev)
+{
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+
+	while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state))
+		usleep_range(1000, 2000);
+
+	if (netif_running(dev))
+		dev->netdev_ops->ndo_stop(dev);
+
+	ixgbe_clear_interrupt_scheme(adapter);
+	ixgbe_init_interrupt_scheme(adapter);
+
+	if (netif_running(dev))
+		dev->netdev_ops->ndo_open(dev);
+
+	clear_bit(__IXGBE_RESETTING, &adapter->state);
+}
+#endif
+
 static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
@@ -338,27 +351,6 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 	if (ret)
 		return DCB_NO_HW_CHG;
 
-#ifdef IXGBE_FCOE
-	if (up && !(up & (1 << adapter->fcoe.up)))
-		adapter->dcb_set_bitmap |= BIT_APP_UPCHG;
-
-	/*
-	 * Only take down the adapter if an app change occurred. FCoE
-	 * may shuffle tx rings in this case and this can not be done
-	 * without a reset currently.
-	 */
-	if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) {
-		while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state))
-			usleep_range(1000, 2000);
-
-		adapter->fcoe.up = ffs(up) - 1;
-
-		if (netif_running(netdev))
-			netdev->netdev_ops->ndo_stop(netdev);
-		ixgbe_clear_interrupt_scheme(adapter);
-	}
-#endif
-
 	if (adapter->dcb_cfg.pfc_mode_enable) {
 		switch (adapter->hw.mac.type) {
 		case ixgbe_mac_82599EB:
@@ -385,15 +377,6 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 		}
 	}
 
-#ifdef IXGBE_FCOE
-	if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) {
-		ixgbe_init_interrupt_scheme(adapter);
-		if (netif_running(netdev))
-			netdev->netdev_ops->ndo_open(netdev);
-		ret = DCB_HW_CHG_RST;
-	}
-#endif
-
 	if (adapter->dcb_set_bitmap & (BIT_PG_TX|BIT_PG_RX)) {
 		u16 refill[MAX_TRAFFIC_CLASS], max[MAX_TRAFFIC_CLASS];
 		u8 bwg_id[MAX_TRAFFIC_CLASS], prio_type[MAX_TRAFFIC_CLASS];
@@ -442,8 +425,19 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev)
 	if (adapter->dcb_cfg.pfc_mode_enable)
 		adapter->hw.fc.current_mode = ixgbe_fc_pfc;
 
-	if (adapter->dcb_set_bitmap & BIT_APP_UPCHG)
-		clear_bit(__IXGBE_RESETTING, &adapter->state);
+#ifdef IXGBE_FCOE
+	/* Reprogam FCoE hardware offloads when the traffic class
+	 * FCoE is using changes. This happens if the APP info
+	 * changes or the up2tc mapping is updated.
+	 */
+	if ((up && !(up & (1 << adapter->fcoe.up))) ||
+	    (adapter->dcb_set_bitmap & BIT_APP_UPCHG)) {
+		adapter->fcoe.up = ffs(up) - 1;
+		ixgbe_dcbnl_devreset(netdev);
+		ret = DCB_HW_CHG_RST;
+	}
+#endif
+
 	adapter->dcb_set_bitmap = 0x00;
 	return ret;
 }
@@ -661,22 +655,6 @@ static int ixgbe_dcbnl_ieee_setpfc(struct net_device *dev,
 	return ixgbe_dcb_hw_pfc_config(&adapter->hw, pfc->pfc_en, prio_tc);
 }
 
-#ifdef IXGBE_FCOE
-static void ixgbe_dcbnl_devreset(struct net_device *dev)
-{
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
-
-	if (netif_running(dev))
-		dev->netdev_ops->ndo_stop(dev);
-
-	ixgbe_clear_interrupt_scheme(adapter);
-	ixgbe_init_interrupt_scheme(adapter);
-
-	if (netif_running(dev))
-		dev->netdev_ops->ndo_open(dev);
-}
-#endif
-
 static int ixgbe_dcbnl_ieee_setapp(struct net_device *dev,
 				   struct dcb_app *app)
 {
@@ -761,7 +739,9 @@ static u8 ixgbe_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 		ixgbe_dcbnl_ieee_setets(dev, &ets);
 		ixgbe_dcbnl_ieee_setpfc(dev, &pfc);
 	} else if (mode & DCB_CAP_DCBX_VER_CEE) {
-		adapter->dcb_set_bitmap |= (BIT_PFC & BIT_PG_TX & BIT_PG_RX);
+		u8 mask = BIT_PFC | BIT_PG_TX | BIT_PG_RX | BIT_APP_UPCHG;
+
+		adapter->dcb_set_bitmap |= mask;
 		ixgbe_dcbnl_set_all(dev);
 	} else {
 		/* Drop into single TC mode strict priority as this
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 70d58c3..91f871b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -888,23 +888,19 @@ static void ixgbe_get_drvinfo(struct net_device *netdev,
                               struct ethtool_drvinfo *drvinfo)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
-	char firmware_version[32];
 	u32 nvm_track_id;
 
-	strncpy(drvinfo->driver, ixgbe_driver_name,
-	        sizeof(drvinfo->driver) - 1);
-	strncpy(drvinfo->version, ixgbe_driver_version,
-	        sizeof(drvinfo->version) - 1);
+	strlcpy(drvinfo->driver, ixgbe_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, ixgbe_driver_version,
+		sizeof(drvinfo->version));
 
 	nvm_track_id = (adapter->eeprom_verh << 16) |
 			adapter->eeprom_verl;
-	snprintf(firmware_version, sizeof(firmware_version), "0x%08x",
+	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "0x%08x",
 		 nvm_track_id);
 
-	strncpy(drvinfo->fw_version, firmware_version,
-		sizeof(drvinfo->fw_version) - 1);
-	strncpy(drvinfo->bus_info, pci_name(adapter->pdev),
-		sizeof(drvinfo->bus_info) - 1);
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
 	drvinfo->n_stats = IXGBE_STATS_LEN;
 	drvinfo->testinfo_len = IXGBE_TEST_LEN;
 	drvinfo->regdump_len = ixgbe_get_regs_len(netdev);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 8ef92d1..5d94ce1 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1140,7 +1140,7 @@ void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count)
 
 		if (ring_is_ps_enabled(rx_ring)) {
 			if (!bi->page) {
-				bi->page = netdev_alloc_page(rx_ring->netdev);
+				bi->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
 				if (!bi->page) {
 					rx_ring->rx_stats.alloc_rx_page_failed++;
 					goto no_buffers;
@@ -3044,7 +3044,7 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter)
 	hw->mac.ops.enable_rx_dma(hw, rxctrl);
 }
 
-static void ixgbe_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
+static int ixgbe_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -3053,9 +3053,11 @@ static void ixgbe_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 	/* add VID to filter table */
 	hw->mac.ops.set_vfta(&adapter->hw, vid, pool_ndx, true);
 	set_bit(vid, adapter->active_vlans);
+
+	return 0;
 }
 
-static void ixgbe_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
+static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -3064,6 +3066,8 @@ static void ixgbe_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 	/* remove VID from filter table */
 	hw->mac.ops.set_vfta(&adapter->hw, vid, pool_ndx, false);
 	clear_bit(vid, adapter->active_vlans);
+
+	return 0;
 }
 
 /**
@@ -7174,7 +7178,8 @@ void ixgbe_do_reset(struct net_device *netdev)
 		ixgbe_reset(adapter);
 }
 
-static u32 ixgbe_fix_features(struct net_device *netdev, u32 data)
+static netdev_features_t ixgbe_fix_features(struct net_device *netdev,
+	netdev_features_t data)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
@@ -7204,7 +7209,8 @@ static u32 ixgbe_fix_features(struct net_device *netdev, u32 data)
 	return data;
 }
 
-static int ixgbe_set_features(struct net_device *netdev, u32 data)
+static int ixgbe_set_features(struct net_device *netdev,
+	netdev_features_t data)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	bool need_reset = false;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
index 00fcd39..cf6812d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c
@@ -572,7 +572,7 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf)
 
 		/* reply to reset with ack and vf mac address */
 		msgbuf[0] = IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_ACK;
-		memcpy(new_mac, vf_mac, IXGBE_ETH_LENGTH_OF_ADDRESS);
+		memcpy(new_mac, vf_mac, ETH_ALEN);
 		/*
 		 * Piggyback the multicast filter type so VF can compute the
 		 * correct vectors
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
index df04f1a..e8badab 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h
@@ -33,7 +33,6 @@ void ixgbe_msg_task(struct ixgbe_adapter *adapter);
 int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask);
 void ixgbe_disable_tx_rx(struct ixgbe_adapter *adapter);
 void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter);
-void ixgbe_dump_registers(struct ixgbe_adapter *adapter);
 int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int queue, u8 *mac);
 int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int queue, u16 vlan,
 			   u8 qos);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
index 6c5cca8..242643a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h
@@ -1710,8 +1710,6 @@ enum {
 #define IXGBE_NVM_POLL_WRITE       1  /* Flag for polling for write complete */
 #define IXGBE_NVM_POLL_READ        0  /* Flag for polling for read complete */
 
-#define IXGBE_ETH_LENGTH_OF_ADDRESS   6
-
 #define IXGBE_EEPROM_PAGE_SIZE_MAX       128
 #define IXGBE_EEPROM_RD_BUFFER_MAX_COUNT 512 /* EEPROM words # read in burst */
 #define IXGBE_EEPROM_WR_BUFFER_MAX_COUNT 256 /* EEPROM words # wr in burst */
@@ -2802,9 +2800,9 @@ struct ixgbe_eeprom_info {
 struct ixgbe_mac_info {
 	struct ixgbe_mac_operations     ops;
 	enum ixgbe_mac_type             type;
-	u8                              addr[IXGBE_ETH_LENGTH_OF_ADDRESS];
-	u8                              perm_addr[IXGBE_ETH_LENGTH_OF_ADDRESS];
-	u8                              san_addr[IXGBE_ETH_LENGTH_OF_ADDRESS];
+	u8                              addr[ETH_ALEN];
+	u8                              perm_addr[ETH_ALEN];
+	u8                              san_addr[ETH_ALEN];
 	/* prefix for World Wide Node Name (WWNN) */
 	u16                             wwnn_prefix;
 	/* prefix for World Wide Port Name (WWPN) */
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
index e5101e9..8cc5ecc 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c
@@ -751,16 +751,20 @@ static s32 ixgbe_blink_led_start_X540(struct ixgbe_hw *hw, u32 index)
 {
 	u32 macc_reg;
 	u32 ledctl_reg;
+	ixgbe_link_speed speed;
+	bool link_up;
 
 	/*
-	 * In order for the blink bit in the LED control register
-	 * to work, link and speed must be forced in the MAC. We
-	 * will reverse this when we stop the blinking.
+	 * Link should be up in order for the blink bit in the LED control
+	 * register to work. Force link and speed in the MAC if link is down.
+	 * This will be reversed when we stop the blinking.
 	 */
-	macc_reg = IXGBE_READ_REG(hw, IXGBE_MACC);
-	macc_reg |= IXGBE_MACC_FLU | IXGBE_MACC_FSV_10G | IXGBE_MACC_FS;
-	IXGBE_WRITE_REG(hw, IXGBE_MACC, macc_reg);
-
+	hw->mac.ops.check_link(hw, &speed, &link_up, false);
+	if (link_up == false) {
+		macc_reg = IXGBE_READ_REG(hw, IXGBE_MACC);
+		macc_reg |= IXGBE_MACC_FLU | IXGBE_MACC_FSV_10G | IXGBE_MACC_FS;
+		IXGBE_WRITE_REG(hw, IXGBE_MACC, macc_reg);
+	}
 	/* Set the LED to LINK_UP + BLINK. */
 	ledctl_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL);
 	ledctl_reg &= ~IXGBE_LED_MODE_MASK(index);
diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h
index 78abb6f..2eb89cb 100644
--- a/drivers/net/ethernet/intel/ixgbevf/defines.h
+++ b/drivers/net/ethernet/intel/ixgbevf/defines.h
@@ -35,7 +35,6 @@
 #define IXGBE_VF_IRQ_CLEAR_MASK         7
 #define IXGBE_VF_MAX_TX_QUEUES          1
 #define IXGBE_VF_MAX_RX_QUEUES          1
-#define IXGBE_ETH_LENGTH_OF_ADDRESS     6
 
 /* Link speed */
 typedef u32 ixgbe_link_speed;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
index e29ba45..dc8e651 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c
@@ -27,6 +27,8 @@
 
 /* ethtool support for ixgbevf */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/types.h>
 #include <linux/module.h>
 #include <linux/slab.h>
@@ -265,11 +267,11 @@ static void ixgbevf_get_drvinfo(struct net_device *netdev,
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
 
-	strlcpy(drvinfo->driver, ixgbevf_driver_name, 32);
-	strlcpy(drvinfo->version, ixgbevf_driver_version, 32);
-
-	strlcpy(drvinfo->fw_version, "N/A", 4);
-	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+	strlcpy(drvinfo->driver, ixgbevf_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, ixgbevf_driver_version,
+		sizeof(drvinfo->version));
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
 }
 
 static void ixgbevf_get_ringparam(struct net_device *netdev,
@@ -549,8 +551,8 @@ static const u32 register_test_patterns[] = {
 	writel((W & M), (adapter->hw.hw_addr + R));                           \
 	val = readl(adapter->hw.hw_addr + R);                                 \
 	if ((W & M) != (val & M)) {                                           \
-		printk(KERN_ERR "set/check reg %04X test failed: got 0x%08X " \
-				 "expected 0x%08X\n", R, (val & M), (W & M)); \
+		pr_err("set/check reg %04X test failed: got 0x%08X expected " \
+		       "0x%08X\n", R, (val & M), (W & M));                    \
 		*data = R;                                                    \
 		writel(before, (adapter->hw.hw_addr + R));                    \
 		return 1;                                                     \
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 4c8e199..891162d 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -29,6 +29,9 @@
 /******************************************************************************
  Copyright (c)2006 - 2007 Myricom, Inc. for some LRO specific code
 ******************************************************************************/
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/module.h>
@@ -363,7 +366,7 @@ static void ixgbevf_alloc_rx_buffers(struct ixgbevf_adapter *adapter,
 		if (!bi->page_dma &&
 		    (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED)) {
 			if (!bi->page) {
-				bi->page = netdev_alloc_page(adapter->netdev);
+				bi->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
 				if (!bi->page) {
 					adapter->alloc_rx_page_failed++;
 					goto no_buffers;
@@ -1400,7 +1403,7 @@ static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter)
 	}
 }
 
-static void ixgbevf_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
+static int ixgbevf_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -1409,9 +1412,11 @@ static void ixgbevf_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 	if (hw->mac.ops.set_vfta)
 		hw->mac.ops.set_vfta(hw, vid, 0, true);
 	set_bit(vid, adapter->active_vlans);
+
+	return 0;
 }
 
-static void ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
+static int ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -1420,6 +1425,8 @@ static void ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 	if (hw->mac.ops.set_vfta)
 		hw->mac.ops.set_vfta(hw, vid, 0, false);
 	clear_bit(vid, adapter->active_vlans);
+
+	return 0;
 }
 
 static void ixgbevf_restore_vlan(struct ixgbevf_adapter *adapter)
@@ -1437,7 +1444,7 @@ static int ixgbevf_write_uc_addr_list(struct net_device *netdev)
 	int count = 0;
 
 	if ((netdev_uc_count(netdev)) > 10) {
-		printk(KERN_ERR "Too many unicast filters - No Space\n");
+		pr_err("Too many unicast filters - No Space\n");
 		return -ENOSPC;
 	}
 
@@ -2135,7 +2142,7 @@ static int ixgbevf_init_interrupt_scheme(struct ixgbevf_adapter *adapter)
 
 	err = ixgbevf_alloc_queues(adapter);
 	if (err) {
-		printk(KERN_ERR "Unable to allocate memory for queues\n");
+		pr_err("Unable to allocate memory for queues\n");
 		goto err_alloc_queues;
 	}
 
@@ -2189,7 +2196,7 @@ static int __devinit ixgbevf_sw_init(struct ixgbevf_adapter *adapter)
 	} else {
 		err = hw->mac.ops.init_hw(hw);
 		if (err) {
-			printk(KERN_ERR "init_shared_code failed: %d\n", err);
+			pr_err("init_shared_code failed: %d\n", err);
 			goto out;
 		}
 	}
@@ -2630,8 +2637,8 @@ static int ixgbevf_open(struct net_device *netdev)
 		 * the vf can't start. */
 		if (hw->adapter_stopped) {
 			err = IXGBE_ERR_MBX;
-			printk(KERN_ERR "Unable to start - perhaps the PF"
-			       " Driver isn't up yet\n");
+			pr_err("Unable to start - perhaps the PF Driver isn't "
+			       "up yet\n");
 			goto err_setup_reset;
 		}
 	}
@@ -2842,10 +2849,8 @@ static bool ixgbevf_tx_csum(struct ixgbevf_adapter *adapter,
 				break;
 			default:
 				if (unlikely(net_ratelimit())) {
-					printk(KERN_WARNING
-					       "partial checksum but "
-					       "proto=%x!\n",
-					       skb->protocol);
+					pr_warn("partial checksum but "
+						"proto=%x!\n", skb->protocol);
 				}
 				break;
 			}
@@ -3249,7 +3254,8 @@ static struct rtnl_link_stats64 *ixgbevf_get_stats(struct net_device *netdev,
 	return stats;
 }
 
-static int ixgbevf_set_features(struct net_device *netdev, u32 features)
+static int ixgbevf_set_features(struct net_device *netdev,
+	netdev_features_t features)
 {
 	struct ixgbevf_adapter *adapter = netdev_priv(netdev);
 
@@ -3414,7 +3420,7 @@ static int __devinit ixgbevf_probe(struct pci_dev *pdev,
 	memcpy(netdev->perm_addr, adapter->hw.mac.addr, netdev->addr_len);
 
 	if (!is_valid_ether_addr(netdev->dev_addr)) {
-		printk(KERN_ERR "invalid MAC address\n");
+		pr_err("invalid MAC address\n");
 		err = -EIO;
 		goto err_sw_init;
 	}
@@ -3535,10 +3541,10 @@ static struct pci_driver ixgbevf_driver = {
 static int __init ixgbevf_init_module(void)
 {
 	int ret;
-	printk(KERN_INFO "ixgbevf: %s - version %s\n", ixgbevf_driver_string,
-	       ixgbevf_driver_version);
+	pr_info("%s - version %s\n", ixgbevf_driver_string,
+		ixgbevf_driver_version);
 
-	printk(KERN_INFO "%s\n", ixgbevf_copyright);
+	pr_info("%s\n", ixgbevf_copyright);
 
 	ret = pci_register_driver(&ixgbevf_driver);
 	return ret;
diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c
index aa3682e..21533e3 100644
--- a/drivers/net/ethernet/intel/ixgbevf/vf.c
+++ b/drivers/net/ethernet/intel/ixgbevf/vf.c
@@ -108,7 +108,7 @@ static s32 ixgbevf_reset_hw_vf(struct ixgbe_hw *hw)
 	if (msgbuf[0] != (IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_ACK))
 		return IXGBE_ERR_INVALID_MAC_ADDR;
 
-	memcpy(hw->mac.perm_addr, addr, IXGBE_ETH_LENGTH_OF_ADDRESS);
+	memcpy(hw->mac.perm_addr, addr, ETH_ALEN);
 	hw->mac.mc_filter_type = msgbuf[IXGBE_VF_MC_TYPE_WORD];
 
 	return 0;
@@ -211,7 +211,7 @@ static s32 ixgbevf_mta_vector(struct ixgbe_hw *hw, u8 *mc_addr)
  **/
 static s32 ixgbevf_get_mac_addr_vf(struct ixgbe_hw *hw, u8 *mac_addr)
 {
-	memcpy(mac_addr, hw->mac.perm_addr, IXGBE_ETH_LENGTH_OF_ADDRESS);
+	memcpy(mac_addr, hw->mac.perm_addr, ETH_ALEN);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index 7becff1..27d651a 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -1745,6 +1745,112 @@ jme_phy_off(struct jme_adapter *jme)
 }
 
 static int
+jme_phy_specreg_read(struct jme_adapter *jme, u32 specreg)
+{
+	u32 phy_addr;
+
+	phy_addr = JM_PHY_SPEC_REG_READ | specreg;
+	jme_mdio_write(jme->dev, jme->mii_if.phy_id, JM_PHY_SPEC_ADDR_REG,
+			phy_addr);
+	return jme_mdio_read(jme->dev, jme->mii_if.phy_id,
+			JM_PHY_SPEC_DATA_REG);
+}
+
+static void
+jme_phy_specreg_write(struct jme_adapter *jme, u32 ext_reg, u32 phy_data)
+{
+	u32 phy_addr;
+
+	phy_addr = JM_PHY_SPEC_REG_WRITE | ext_reg;
+	jme_mdio_write(jme->dev, jme->mii_if.phy_id, JM_PHY_SPEC_DATA_REG,
+			phy_data);
+	jme_mdio_write(jme->dev, jme->mii_if.phy_id, JM_PHY_SPEC_ADDR_REG,
+			phy_addr);
+}
+
+static int
+jme_phy_calibration(struct jme_adapter *jme)
+{
+	u32 ctrl1000, phy_data;
+
+	jme_phy_off(jme);
+	jme_phy_on(jme);
+	/*  Enabel PHY test mode 1 */
+	ctrl1000 = jme_mdio_read(jme->dev, jme->mii_if.phy_id, MII_CTRL1000);
+	ctrl1000 &= ~PHY_GAD_TEST_MODE_MSK;
+	ctrl1000 |= PHY_GAD_TEST_MODE_1;
+	jme_mdio_write(jme->dev, jme->mii_if.phy_id, MII_CTRL1000, ctrl1000);
+
+	phy_data = jme_phy_specreg_read(jme, JM_PHY_EXT_COMM_2_REG);
+	phy_data &= ~JM_PHY_EXT_COMM_2_CALI_MODE_0;
+	phy_data |= JM_PHY_EXT_COMM_2_CALI_LATCH |
+			JM_PHY_EXT_COMM_2_CALI_ENABLE;
+	jme_phy_specreg_write(jme, JM_PHY_EXT_COMM_2_REG, phy_data);
+	msleep(20);
+	phy_data = jme_phy_specreg_read(jme, JM_PHY_EXT_COMM_2_REG);
+	phy_data &= ~(JM_PHY_EXT_COMM_2_CALI_ENABLE |
+			JM_PHY_EXT_COMM_2_CALI_MODE_0 |
+			JM_PHY_EXT_COMM_2_CALI_LATCH);
+	jme_phy_specreg_write(jme, JM_PHY_EXT_COMM_2_REG, phy_data);
+
+	/*  Disable PHY test mode */
+	ctrl1000 = jme_mdio_read(jme->dev, jme->mii_if.phy_id, MII_CTRL1000);
+	ctrl1000 &= ~PHY_GAD_TEST_MODE_MSK;
+	jme_mdio_write(jme->dev, jme->mii_if.phy_id, MII_CTRL1000, ctrl1000);
+	return 0;
+}
+
+static int
+jme_phy_setEA(struct jme_adapter *jme)
+{
+	u32 phy_comm0 = 0, phy_comm1 = 0;
+	u8 nic_ctrl;
+
+	pci_read_config_byte(jme->pdev, PCI_PRIV_SHARE_NICCTRL, &nic_ctrl);
+	if ((nic_ctrl & 0x3) == JME_FLAG_PHYEA_ENABLE)
+		return 0;
+
+	switch (jme->pdev->device) {
+	case PCI_DEVICE_ID_JMICRON_JMC250:
+		if (((jme->chip_main_rev == 5) &&
+			((jme->chip_sub_rev == 0) || (jme->chip_sub_rev == 1) ||
+			(jme->chip_sub_rev == 3))) ||
+			(jme->chip_main_rev >= 6)) {
+			phy_comm0 = 0x008A;
+			phy_comm1 = 0x4109;
+		}
+		if ((jme->chip_main_rev == 3) &&
+			((jme->chip_sub_rev == 1) || (jme->chip_sub_rev == 2)))
+			phy_comm0 = 0xE088;
+		break;
+	case PCI_DEVICE_ID_JMICRON_JMC260:
+		if (((jme->chip_main_rev == 5) &&
+			((jme->chip_sub_rev == 0) || (jme->chip_sub_rev == 1) ||
+			(jme->chip_sub_rev == 3))) ||
+			(jme->chip_main_rev >= 6)) {
+			phy_comm0 = 0x008A;
+			phy_comm1 = 0x4109;
+		}
+		if ((jme->chip_main_rev == 3) &&
+			((jme->chip_sub_rev == 1) || (jme->chip_sub_rev == 2)))
+			phy_comm0 = 0xE088;
+		if ((jme->chip_main_rev == 2) && (jme->chip_sub_rev == 0))
+			phy_comm0 = 0x608A;
+		if ((jme->chip_main_rev == 2) && (jme->chip_sub_rev == 2))
+			phy_comm0 = 0x408A;
+		break;
+	default:
+		return -ENODEV;
+	}
+	if (phy_comm0)
+		jme_phy_specreg_write(jme, JM_PHY_EXT_COMM_0_REG, phy_comm0);
+	if (phy_comm1)
+		jme_phy_specreg_write(jme, JM_PHY_EXT_COMM_1_REG, phy_comm1);
+
+	return 0;
+}
+
+static int
 jme_open(struct net_device *netdev)
 {
 	struct jme_adapter *jme = netdev_priv(netdev);
@@ -1769,7 +1875,8 @@ jme_open(struct net_device *netdev)
 		jme_set_settings(netdev, &jme->old_ecmd);
 	else
 		jme_reset_phy_processor(jme);
-
+	jme_phy_calibration(jme);
+	jme_phy_setEA(jme);
 	jme_reset_link(jme);
 
 	return 0;
@@ -1883,7 +1990,7 @@ jme_fill_tx_map(struct pci_dev *pdev,
 		struct page *page,
 		u32 page_offset,
 		u32 len,
-		u8 hidma)
+		bool hidma)
 {
 	dma_addr_t dmaaddr;
 
@@ -1917,7 +2024,7 @@ jme_map_tx_skb(struct jme_adapter *jme, struct sk_buff *skb, int idx)
 	struct jme_ring *txring = &(jme->txring[0]);
 	struct txdesc *txdesc = txring->desc, *ctxdesc;
 	struct jme_buffer_info *txbi = txring->bufinf, *ctxbi;
-	u8 hidma = jme->dev->features & NETIF_F_HIGHDMA;
+	bool hidma = jme->dev->features & NETIF_F_HIGHDMA;
 	int i, nr_frags = skb_shinfo(skb)->nr_frags;
 	int mask = jme->tx_ring_mask;
 	const struct skb_frag_struct *frag;
@@ -2292,9 +2399,9 @@ jme_get_drvinfo(struct net_device *netdev,
 {
 	struct jme_adapter *jme = netdev_priv(netdev);
 
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->bus_info, pci_name(jme->pdev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(jme->pdev), sizeof(info->bus_info));
 }
 
 static int
@@ -2620,8 +2727,8 @@ jme_set_msglevel(struct net_device *netdev, u32 value)
 	jme->msg_enable = value;
 }
 
-static u32
-jme_fix_features(struct net_device *netdev, u32 features)
+static netdev_features_t
+jme_fix_features(struct net_device *netdev, netdev_features_t features)
 {
 	if (netdev->mtu > 1900)
 		features &= ~(NETIF_F_ALL_TSO | NETIF_F_ALL_CSUM);
@@ -2629,7 +2736,7 @@ jme_fix_features(struct net_device *netdev, u32 features)
 }
 
 static int
-jme_set_features(struct net_device *netdev, u32 features)
+jme_set_features(struct net_device *netdev, netdev_features_t features)
 {
 	struct jme_adapter *jme = netdev_priv(netdev);
 
@@ -3184,7 +3291,8 @@ jme_resume(struct device *dev)
 		jme_set_settings(netdev, &jme->old_ecmd);
 	else
 		jme_reset_phy_processor(jme);
-
+	jme_phy_calibration(jme);
+	jme_phy_setEA(jme);
 	jme_start_irq(jme);
 	netif_device_attach(netdev);
 
@@ -3239,4 +3347,3 @@ MODULE_DESCRIPTION("JMicron JMC2x0 PCI Express Ethernet driver");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_VERSION);
 MODULE_DEVICE_TABLE(pci, jme_pci_tbl);
-
diff --git a/drivers/net/ethernet/jme.h b/drivers/net/ethernet/jme.h
index 02ea27c..4304072 100644
--- a/drivers/net/ethernet/jme.h
+++ b/drivers/net/ethernet/jme.h
@@ -760,6 +760,25 @@ enum jme_rxmcs_bits {
 				  RXMCS_CHECKSUM,
 };
 
+/*	Extern PHY common register 2	*/
+
+#define PHY_GAD_TEST_MODE_1			0x00002000
+#define PHY_GAD_TEST_MODE_MSK			0x0000E000
+#define JM_PHY_SPEC_REG_READ			0x00004000
+#define JM_PHY_SPEC_REG_WRITE			0x00008000
+#define PHY_CALIBRATION_DELAY			20
+#define JM_PHY_SPEC_ADDR_REG			0x1E
+#define JM_PHY_SPEC_DATA_REG			0x1F
+
+#define JM_PHY_EXT_COMM_0_REG			0x30
+#define JM_PHY_EXT_COMM_1_REG			0x31
+#define JM_PHY_EXT_COMM_2_REG			0x32
+#define JM_PHY_EXT_COMM_2_CALI_ENABLE		0x01
+#define JM_PHY_EXT_COMM_2_CALI_MODE_0		0x02
+#define JM_PHY_EXT_COMM_2_CALI_LATCH		0x10
+#define PCI_PRIV_SHARE_NICCTRL			0xF5
+#define JME_FLAG_PHYEA_ENABLE			0x2
+
 /*
  * Wakeup Frame setup interface registers
  */
diff --git a/drivers/net/ethernet/korina.c b/drivers/net/ethernet/korina.c
index d8430f4..6ad094f 100644
--- a/drivers/net/ethernet/korina.c
+++ b/drivers/net/ethernet/korina.c
@@ -1230,18 +1230,7 @@ static struct platform_driver korina_driver = {
 	.remove = korina_remove,
 };
 
-static int __init korina_init_module(void)
-{
-	return platform_driver_register(&korina_driver);
-}
-
-static void korina_cleanup_module(void)
-{
-	return platform_driver_unregister(&korina_driver);
-}
-
-module_init(korina_init_module);
-module_exit(korina_cleanup_module);
+module_platform_driver(korina_driver);
 
 MODULE_AUTHOR("Philip Rischel <rischelp@idt.com>");
 MODULE_AUTHOR("Felix Fietkau <nbd@openwrt.org>");
diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index 6bb2b95..0b3567a 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -34,6 +34,8 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/io.h>
+#include <linux/dma-mapping.h>
+#include <linux/module.h>
 
 #include <asm/checksum.h>
 
diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c
index 194a031..e87847e 100644
--- a/drivers/net/ethernet/marvell/mv643xx_eth.c
+++ b/drivers/net/ethernet/marvell/mv643xx_eth.c
@@ -1502,10 +1502,12 @@ mv643xx_eth_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 static void mv643xx_eth_get_drvinfo(struct net_device *dev,
 				    struct ethtool_drvinfo *drvinfo)
 {
-	strncpy(drvinfo->driver,  mv643xx_eth_driver_name, 32);
-	strncpy(drvinfo->version, mv643xx_eth_driver_version, 32);
-	strncpy(drvinfo->fw_version, "N/A", 32);
-	strncpy(drvinfo->bus_info, "platform", 32);
+	strlcpy(drvinfo->driver, mv643xx_eth_driver_name,
+		sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, mv643xx_eth_driver_version,
+		sizeof(drvinfo->version));
+	strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version));
+	strlcpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info));
 	drvinfo->n_stats = ARRAY_SIZE(mv643xx_eth_stats);
 }
 
@@ -1578,10 +1580,10 @@ mv643xx_eth_set_ringparam(struct net_device *dev, struct ethtool_ringparam *er)
 
 
 static int
-mv643xx_eth_set_features(struct net_device *dev, u32 features)
+mv643xx_eth_set_features(struct net_device *dev, netdev_features_t features)
 {
 	struct mv643xx_eth_private *mp = netdev_priv(dev);
-	u32 rx_csum = features & NETIF_F_RXCSUM;
+	bool rx_csum = features & NETIF_F_RXCSUM;
 
 	wrlp(mp, PORT_CONFIG, rx_csum ? 0x02000000 : 0x00000000);
 
diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
index d17d062..5ec409e 100644
--- a/drivers/net/ethernet/marvell/pxa168_eth.c
+++ b/drivers/net/ethernet/marvell/pxa168_eth.c
@@ -1645,18 +1645,7 @@ static struct platform_driver pxa168_eth_driver = {
 		   },
 };
 
-static int __init pxa168_init_module(void)
-{
-	return platform_driver_register(&pxa168_eth_driver);
-}
-
-static void __exit pxa168_cleanup_module(void)
-{
-	platform_driver_unregister(&pxa168_eth_driver);
-}
-
-module_init(pxa168_init_module);
-module_exit(pxa168_cleanup_module);
+module_platform_driver(pxa168_eth_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Ethernet driver for Marvell PXA168");
diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c
index c7b6083..d957b2c 100644
--- a/drivers/net/ethernet/marvell/skge.c
+++ b/drivers/net/ethernet/marvell/skge.c
@@ -394,10 +394,10 @@ static void skge_get_drvinfo(struct net_device *dev,
 {
 	struct skge_port *skge = netdev_priv(dev);
 
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->fw_version, "N/A");
-	strcpy(info->bus_info, pci_name(skge->hw->pdev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(skge->hw->pdev),
+		sizeof(info->bus_info));
 }
 
 static const struct skge_stat {
diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c
index fdc6c39..760c2b1 100644
--- a/drivers/net/ethernet/marvell/sky2.c
+++ b/drivers/net/ethernet/marvell/sky2.c
@@ -50,7 +50,7 @@
 #include "sky2.h"
 
 #define DRV_NAME		"sky2"
-#define DRV_VERSION		"1.29"
+#define DRV_VERSION		"1.30"
 
 /*
  * The Yukon II chipset takes 64 bit command blocks (called list elements)
@@ -68,7 +68,7 @@
 #define MAX_SKB_TX_LE	(2 + (sizeof(dma_addr_t)/sizeof(u32))*(MAX_SKB_FRAGS+1))
 #define TX_MIN_PENDING		(MAX_SKB_TX_LE+1)
 #define TX_MAX_PENDING		1024
-#define TX_DEF_PENDING		127
+#define TX_DEF_PENDING		63
 
 #define TX_WATCHDOG		(5 * HZ)
 #define NAPI_WEIGHT		64
@@ -869,6 +869,7 @@ static void sky2_wol_init(struct sky2_port *sky2)
 
 	/* block receiver */
 	sky2_write8(hw, SK_REG(port, RX_GMF_CTRL_T), GMF_RST_SET);
+	sky2_read32(hw, B0_CTST);
 }
 
 static void sky2_set_tx_stfwd(struct sky2_hw *hw, unsigned port)
@@ -1109,6 +1110,7 @@ static void tx_init(struct sky2_port *sky2)
 	sky2->tx_prod = sky2->tx_cons = 0;
 	sky2->tx_tcpsum = 0;
 	sky2->tx_last_mss = 0;
+	netdev_reset_queue(sky2->netdev);
 
 	le = get_tx_le(sky2, &sky2->tx_prod);
 	le->addr = 0;
@@ -1274,8 +1276,16 @@ static void rx_set_checksum(struct sky2_port *sky2)
 		     ? BMU_ENA_RX_CHKSUM : BMU_DIS_RX_CHKSUM);
 }
 
+/*
+ * Fixed initial key as seed to RSS.
+ */
+static const uint32_t rss_init_key[10] = {
+	0x7c3351da, 0x51c5cf4e,	0x44adbdd1, 0xe8d38d18,	0x48897c43,
+	0xb1d60e7e, 0x6a3dd760, 0x01a2e453, 0x16f46f13, 0x1a0e7b30
+};
+
 /* Enable/disable receive hash calculation (RSS) */
-static void rx_set_rss(struct net_device *dev, u32 features)
+static void rx_set_rss(struct net_device *dev, netdev_features_t features)
 {
 	struct sky2_port *sky2 = netdev_priv(dev);
 	struct sky2_hw *hw = sky2->hw;
@@ -1289,12 +1299,9 @@ static void rx_set_rss(struct net_device *dev, u32 features)
 
 	/* Program RSS initial values */
 	if (features & NETIF_F_RXHASH) {
-		u32 key[nkeys];
-
-		get_random_bytes(key, nkeys * sizeof(u32));
 		for (i = 0; i < nkeys; i++)
 			sky2_write32(hw, SK_REG(sky2->port, RSS_KEY + i * 4),
-				     key[i]);
+				     rss_init_key[i]);
 
 		/* Need to turn on (undocumented) flag to make hashing work  */
 		sky2_write32(hw, SK_REG(sky2->port, RX_GMF_CTRL_T),
@@ -1396,7 +1403,7 @@ static int sky2_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 
 #define SKY2_VLAN_OFFLOADS (NETIF_F_IP_CSUM | NETIF_F_SG | NETIF_F_TSO)
 
-static void sky2_vlan_mode(struct net_device *dev, u32 features)
+static void sky2_vlan_mode(struct net_device *dev, netdev_features_t features)
 {
 	struct sky2_port *sky2 = netdev_priv(dev);
 	struct sky2_hw *hw = sky2->hw;
@@ -1717,6 +1724,8 @@ static int sky2_setup_irq(struct sky2_hw *hw, const char *name)
 	if (err)
 		dev_err(&pdev->dev, "cannot assign irq %d\n", pdev->irq);
 	else {
+		hw->flags |= SKY2_HW_IRQ_SETUP;
+
 		napi_enable(&hw->napi);
 		sky2_write32(hw, B0_IMSK, Y2_IS_BASE);
 		sky2_read32(hw, B0_IMSK);
@@ -1727,7 +1736,7 @@ static int sky2_setup_irq(struct sky2_hw *hw, const char *name)
 
 
 /* Bring up network interface. */
-static int sky2_up(struct net_device *dev)
+static int sky2_open(struct net_device *dev)
 {
 	struct sky2_port *sky2 = netdev_priv(dev);
 	struct sky2_hw *hw = sky2->hw;
@@ -1747,6 +1756,11 @@ static int sky2_up(struct net_device *dev)
 
 	sky2_hw_up(sky2);
 
+	if (hw->chip_id == CHIP_ID_YUKON_OPT ||
+	    hw->chip_id == CHIP_ID_YUKON_PRM ||
+	    hw->chip_id == CHIP_ID_YUKON_OP_2)
+		imask |= Y2_IS_PHY_QLNK;	/* enable PHY Quick Link */
+
 	/* Enable interrupts from phy/mac for port */
 	imask = sky2_read32(hw, B0_IMSK);
 	imask |= portirq_msk[port];
@@ -1958,6 +1972,7 @@ static netdev_tx_t sky2_xmit_frame(struct sk_buff *skb,
 	if (tx_avail(sky2) <= MAX_SKB_TX_LE)
 		netif_stop_queue(dev);
 
+	netdev_sent_queue(dev, skb->len);
 	sky2_put_idx(hw, txqaddr[sky2->port], sky2->tx_prod);
 
 	return NETDEV_TX_OK;
@@ -1989,7 +2004,8 @@ mapping_error:
 static void sky2_tx_complete(struct sky2_port *sky2, u16 done)
 {
 	struct net_device *dev = sky2->netdev;
-	unsigned idx;
+	u16 idx;
+	unsigned int bytes_compl = 0, pkts_compl = 0;
 
 	BUG_ON(done >= sky2->tx_ring_size);
 
@@ -2004,10 +2020,8 @@ static void sky2_tx_complete(struct sky2_port *sky2, u16 done)
 			netif_printk(sky2, tx_done, KERN_DEBUG, dev,
 				     "tx done %u\n", idx);
 
-			u64_stats_update_begin(&sky2->tx_stats.syncp);
-			++sky2->tx_stats.packets;
-			sky2->tx_stats.bytes += skb->len;
-			u64_stats_update_end(&sky2->tx_stats.syncp);
+			pkts_compl++;
+			bytes_compl += skb->len;
 
 			re->skb = NULL;
 			dev_kfree_skb_any(skb);
@@ -2018,6 +2032,13 @@ static void sky2_tx_complete(struct sky2_port *sky2, u16 done)
 
 	sky2->tx_cons = idx;
 	smp_mb();
+
+	netdev_completed_queue(dev, pkts_compl, bytes_compl);
+
+	u64_stats_update_begin(&sky2->tx_stats.syncp);
+	sky2->tx_stats.packets += pkts_compl;
+	sky2->tx_stats.bytes += bytes_compl;
+	u64_stats_update_end(&sky2->tx_stats.syncp);
 }
 
 static void sky2_tx_reset(struct sky2_hw *hw, unsigned port)
@@ -2040,6 +2061,8 @@ static void sky2_tx_reset(struct sky2_hw *hw, unsigned port)
 
 	sky2_write32(hw, RB_ADDR(txqaddr[port], RB_CTRL), RB_RST_SET);
 	sky2_write8(hw, SK_REG(port, TX_GMF_CTRL_T), GMF_RST_SET);
+
+	sky2_read32(hw, B0_CTST);
 }
 
 static void sky2_hw_down(struct sky2_port *sky2)
@@ -2090,7 +2113,7 @@ static void sky2_hw_down(struct sky2_port *sky2)
 }
 
 /* Network shutdown */
-static int sky2_down(struct net_device *dev)
+static int sky2_close(struct net_device *dev)
 {
 	struct sky2_port *sky2 = netdev_priv(dev);
 	struct sky2_hw *hw = sky2->hw;
@@ -2101,15 +2124,22 @@ static int sky2_down(struct net_device *dev)
 
 	netif_info(sky2, ifdown, dev, "disabling interface\n");
 
-	/* Disable port IRQ */
-	sky2_write32(hw, B0_IMSK,
-		     sky2_read32(hw, B0_IMSK) & ~portirq_msk[sky2->port]);
-	sky2_read32(hw, B0_IMSK);
-
 	if (hw->ports == 1) {
+		sky2_write32(hw, B0_IMSK, 0);
+		sky2_read32(hw, B0_IMSK);
+
 		napi_disable(&hw->napi);
 		free_irq(hw->pdev->irq, hw);
+		hw->flags &= ~SKY2_HW_IRQ_SETUP;
 	} else {
+		u32 imask;
+
+		/* Disable port IRQ */
+		imask  = sky2_read32(hw, B0_IMSK);
+		imask &= ~portirq_msk[sky2->port];
+		sky2_write32(hw, B0_IMSK, imask);
+		sky2_read32(hw, B0_IMSK);
+
 		synchronize_irq(hw->pdev->irq);
 		napi_synchronize(&hw->napi);
 	}
@@ -2587,7 +2617,7 @@ static inline void sky2_tx_done(struct net_device *dev, u16 last)
 	if (netif_running(dev)) {
 		sky2_tx_complete(sky2, last);
 
-		/* Wake unless it's detached, and called e.g. from sky2_down() */
+		/* Wake unless it's detached, and called e.g. from sky2_close() */
 		if (tx_avail(sky2) > MAX_SKB_TX_LE + 4)
 			netif_wake_queue(dev);
 	}
@@ -3258,7 +3288,6 @@ static void sky2_reset(struct sky2_hw *hw)
 	    hw->chip_id == CHIP_ID_YUKON_PRM ||
 	    hw->chip_id == CHIP_ID_YUKON_OP_2) {
 		u16 reg;
-		u32 msk;
 
 		if (hw->chip_id == CHIP_ID_YUKON_OPT && hw->chip_rev == 0) {
 			/* disable PCI-E PHY power down (set PHY reg 0x80, bit 7 */
@@ -3281,11 +3310,6 @@ static void sky2_reset(struct sky2_hw *hw)
 		sky2_write8(hw, B2_TST_CTRL1, TST_CFG_WRITE_ON);
 		sky2_pci_write16(hw, PSM_CONFIG_REG4, reg);
 
-		/* enable PHY Quick Link */
-		msk = sky2_read32(hw, B0_IMSK);
-		msk |= Y2_IS_PHY_QLNK;
-		sky2_write32(hw, B0_IMSK, msk);
-
 		/* check if PSMv2 was running before */
 		reg = sky2_pci_read16(hw, PSM_CONFIG_REG3);
 		if (reg & PCI_EXP_LNKCTL_ASPMC)
@@ -3383,7 +3407,7 @@ static void sky2_detach(struct net_device *dev)
 		netif_tx_lock(dev);
 		netif_device_detach(dev);	/* stop txq */
 		netif_tx_unlock(dev);
-		sky2_down(dev);
+		sky2_close(dev);
 	}
 }
 
@@ -3393,7 +3417,7 @@ static int sky2_reattach(struct net_device *dev)
 	int err = 0;
 
 	if (netif_running(dev)) {
-		err = sky2_up(dev);
+		err = sky2_open(dev);
 		if (err) {
 			netdev_info(dev, "could not restart %d\n", err);
 			dev_close(dev);
@@ -3410,10 +3434,13 @@ static void sky2_all_down(struct sky2_hw *hw)
 {
 	int i;
 
-	sky2_read32(hw, B0_IMSK);
-	sky2_write32(hw, B0_IMSK, 0);
-	synchronize_irq(hw->pdev->irq);
-	napi_disable(&hw->napi);
+	if (hw->flags & SKY2_HW_IRQ_SETUP) {
+		sky2_read32(hw, B0_IMSK);
+		sky2_write32(hw, B0_IMSK, 0);
+
+		synchronize_irq(hw->pdev->irq);
+		napi_disable(&hw->napi);
+	}
 
 	for (i = 0; i < hw->ports; i++) {
 		struct net_device *dev = hw->dev[i];
@@ -3446,11 +3473,12 @@ static void sky2_all_up(struct sky2_hw *hw)
 		netif_wake_queue(dev);
 	}
 
-	sky2_write32(hw, B0_IMSK, imask);
-	sky2_read32(hw, B0_IMSK);
-
-	sky2_read32(hw, B0_Y2_SP_LISR);
-	napi_enable(&hw->napi);
+	if (hw->flags & SKY2_HW_IRQ_SETUP) {
+		sky2_write32(hw, B0_IMSK, imask);
+		sky2_read32(hw, B0_IMSK);
+		sky2_read32(hw, B0_Y2_SP_LISR);
+		napi_enable(&hw->napi);
+	}
 }
 
 static void sky2_restart(struct work_struct *work)
@@ -3623,10 +3651,10 @@ static void sky2_get_drvinfo(struct net_device *dev,
 {
 	struct sky2_port *sky2 = netdev_priv(dev);
 
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->fw_version, "N/A");
-	strcpy(info->bus_info, pci_name(sky2->hw->pdev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(sky2->hw->pdev),
+		sizeof(info->bus_info));
 }
 
 static const struct sky2_stat {
@@ -4071,6 +4099,16 @@ static int sky2_set_coalesce(struct net_device *dev,
 	return 0;
 }
 
+/*
+ * Hardware is limited to min of 128 and max of 2048 for ring size
+ * and  rounded up to next power of two
+ * to avoid division in modulus calclation
+ */
+static unsigned long roundup_ring_size(unsigned long pending)
+{
+	return max(128ul, roundup_pow_of_two(pending+1));
+}
+
 static void sky2_get_ringparam(struct net_device *dev,
 			       struct ethtool_ringparam *ering)
 {
@@ -4098,7 +4136,7 @@ static int sky2_set_ringparam(struct net_device *dev,
 
 	sky2->rx_pending = ering->rx_pending;
 	sky2->tx_pending = ering->tx_pending;
-	sky2->tx_ring_size = roundup_pow_of_two(sky2->tx_pending+1);
+	sky2->tx_ring_size = roundup_ring_size(sky2->tx_pending);
 
 	return sky2_reattach(dev);
 }
@@ -4281,7 +4319,8 @@ static int sky2_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom
 	return sky2_vpd_write(sky2->hw, cap, data, eeprom->offset, eeprom->len);
 }
 
-static u32 sky2_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t sky2_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	const struct sky2_port *sky2 = netdev_priv(dev);
 	const struct sky2_hw *hw = sky2->hw;
@@ -4305,13 +4344,13 @@ static u32 sky2_fix_features(struct net_device *dev, u32 features)
 	return features;
 }
 
-static int sky2_set_features(struct net_device *dev, u32 features)
+static int sky2_set_features(struct net_device *dev, netdev_features_t features)
 {
 	struct sky2_port *sky2 = netdev_priv(dev);
-	u32 changed = dev->features ^ features;
+	netdev_features_t changed = dev->features ^ features;
 
 	if (changed & NETIF_F_RXCSUM) {
-		u32 on = features & NETIF_F_RXCSUM;
+		bool on = features & NETIF_F_RXCSUM;
 		sky2_write32(sky2->hw, Q_ADDR(rxqaddr[sky2->port], Q_CSR),
 			     on ? BMU_ENA_RX_CHKSUM : BMU_DIS_RX_CHKSUM);
 	}
@@ -4556,7 +4595,7 @@ static int sky2_device_event(struct notifier_block *unused,
 	struct net_device *dev = ptr;
 	struct sky2_port *sky2 = netdev_priv(dev);
 
-	if (dev->netdev_ops->ndo_open != sky2_up || !sky2_debug)
+	if (dev->netdev_ops->ndo_open != sky2_open || !sky2_debug)
 		return NOTIFY_DONE;
 
 	switch (event) {
@@ -4621,8 +4660,8 @@ static __exit void sky2_debug_cleanup(void)
    not allowing netpoll on second port */
 static const struct net_device_ops sky2_netdev_ops[2] = {
   {
-	.ndo_open		= sky2_up,
-	.ndo_stop		= sky2_down,
+	.ndo_open		= sky2_open,
+	.ndo_stop		= sky2_close,
 	.ndo_start_xmit		= sky2_xmit_frame,
 	.ndo_do_ioctl		= sky2_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
@@ -4638,8 +4677,8 @@ static const struct net_device_ops sky2_netdev_ops[2] = {
 #endif
   },
   {
-	.ndo_open		= sky2_up,
-	.ndo_stop		= sky2_down,
+	.ndo_open		= sky2_open,
+	.ndo_stop		= sky2_close,
 	.ndo_start_xmit		= sky2_xmit_frame,
 	.ndo_do_ioctl		= sky2_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
@@ -4692,7 +4731,7 @@ static __devinit struct net_device *sky2_init_netdev(struct sky2_hw *hw,
 	spin_lock_init(&sky2->phy_lock);
 
 	sky2->tx_pending = TX_DEF_PENDING;
-	sky2->tx_ring_size = roundup_pow_of_two(TX_DEF_PENDING+1);
+	sky2->tx_ring_size = roundup_ring_size(TX_DEF_PENDING);
 	sky2->rx_pending = RX_DEF_PENDING;
 
 	hw->dev[port] = dev;
diff --git a/drivers/net/ethernet/marvell/sky2.h b/drivers/net/ethernet/marvell/sky2.h
index 0af31b8..ff6f58b 100644
--- a/drivers/net/ethernet/marvell/sky2.h
+++ b/drivers/net/ethernet/marvell/sky2.h
@@ -2287,6 +2287,7 @@ struct sky2_hw {
 #define SKY2_HW_RSS_BROKEN	0x00000100
 #define SKY2_HW_VLAN_BROKEN     0x00000200
 #define SKY2_HW_RSS_CHKSUM	0x00000400	/* RSS requires chksum */
+#define SKY2_HW_IRQ_SETUP	0x00000800
 
 	u8	     	     chip_id;
 	u8		     chip_rev;
diff --git a/drivers/net/ethernet/mellanox/mlx4/Makefile b/drivers/net/ethernet/mellanox/mlx4/Makefile
index d1aa45a..4a40ab9 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx4/Makefile
@@ -1,7 +1,7 @@
 obj-$(CONFIG_MLX4_CORE)		+= mlx4_core.o
 
 mlx4_core-y :=	alloc.o catas.o cmd.o cq.o eq.o fw.o icm.o intf.o main.o mcg.o \
-		mr.o pd.o port.o profile.o qp.o reset.o sense.o srq.o
+		mr.o pd.o port.o profile.o qp.o reset.o sense.o srq.o resource_tracker.o
 
 obj-$(CONFIG_MLX4_EN)               += mlx4_en.o
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 45aea9c..915e947 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -48,7 +48,8 @@ static struct work_struct catas_work;
 static int internal_err_reset = 1;
 module_param(internal_err_reset, int, 0644);
 MODULE_PARM_DESC(internal_err_reset,
-		 "Reset device on internal errors if non-zero (default 1)");
+		 "Reset device on internal errors if non-zero"
+		 " (default 1, in SRIOV mode default is 0)");
 
 static void dump_err_buf(struct mlx4_dev *dev)
 {
@@ -116,6 +117,10 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	phys_addr_t addr;
 
+	/*If we are in SRIOV the default of the module param must be 0*/
+	if (mlx4_is_mfunc(dev))
+		internal_err_reset = 0;
+
 	INIT_LIST_HEAD(&priv->catas_err.list);
 	init_timer(&priv->catas_err.timer);
 	priv->catas_err.map = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 78f5a1a..c4fef83 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -39,12 +39,18 @@
 #include <linux/errno.h>
 
 #include <linux/mlx4/cmd.h>
+#include <linux/semaphore.h>
 
 #include <asm/io.h>
 
 #include "mlx4.h"
+#include "fw.h"
 
 #define CMD_POLL_TOKEN 0xffff
+#define INBOX_MASK	0xffffffffffffff00ULL
+
+#define CMD_CHAN_VER 1
+#define CMD_CHAN_IF_REV 1
 
 enum {
 	/* command completed successfully: */
@@ -110,8 +116,12 @@ struct mlx4_cmd_context {
 	int			next;
 	u64			out_param;
 	u16			token;
+	u8			fw_status;
 };
 
+static int mlx4_master_process_vhcr(struct mlx4_dev *dev, int slave,
+				    struct mlx4_vhcr_cmd *in_vhcr);
+
 static int mlx4_status_to_errno(u8 status)
 {
 	static const int trans_table[] = {
@@ -142,6 +152,119 @@ static int mlx4_status_to_errno(u8 status)
 	return trans_table[status];
 }
 
+static int comm_pending(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	u32 status = readl(&priv->mfunc.comm->slave_read);
+
+	return (swab32(status) >> 31) != priv->cmd.comm_toggle;
+}
+
+static void mlx4_comm_cmd_post(struct mlx4_dev *dev, u8 cmd, u16 param)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	u32 val;
+
+	priv->cmd.comm_toggle ^= 1;
+	val = param | (cmd << 16) | (priv->cmd.comm_toggle << 31);
+	__raw_writel((__force u32) cpu_to_be32(val),
+		     &priv->mfunc.comm->slave_write);
+	mmiowb();
+}
+
+static int mlx4_comm_cmd_poll(struct mlx4_dev *dev, u8 cmd, u16 param,
+		       unsigned long timeout)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	unsigned long end;
+	int err = 0;
+	int ret_from_pending = 0;
+
+	/* First, verify that the master reports correct status */
+	if (comm_pending(dev)) {
+		mlx4_warn(dev, "Communication channel is not idle."
+			  "my toggle is %d (cmd:0x%x)\n",
+			  priv->cmd.comm_toggle, cmd);
+		return -EAGAIN;
+	}
+
+	/* Write command */
+	down(&priv->cmd.poll_sem);
+	mlx4_comm_cmd_post(dev, cmd, param);
+
+	end = msecs_to_jiffies(timeout) + jiffies;
+	while (comm_pending(dev) && time_before(jiffies, end))
+		cond_resched();
+	ret_from_pending = comm_pending(dev);
+	if (ret_from_pending) {
+		/* check if the slave is trying to boot in the middle of
+		 * FLR process. The only non-zero result in the RESET command
+		 * is MLX4_DELAY_RESET_SLAVE*/
+		if ((MLX4_COMM_CMD_RESET == cmd)) {
+			mlx4_warn(dev, "Got slave FLRed from Communication"
+				  " channel (ret:0x%x)\n", ret_from_pending);
+			err = MLX4_DELAY_RESET_SLAVE;
+		} else {
+			mlx4_warn(dev, "Communication channel timed out\n");
+			err = -ETIMEDOUT;
+		}
+	}
+
+	up(&priv->cmd.poll_sem);
+	return err;
+}
+
+static int mlx4_comm_cmd_wait(struct mlx4_dev *dev, u8 op,
+			      u16 param, unsigned long timeout)
+{
+	struct mlx4_cmd *cmd = &mlx4_priv(dev)->cmd;
+	struct mlx4_cmd_context *context;
+	int err = 0;
+
+	down(&cmd->event_sem);
+
+	spin_lock(&cmd->context_lock);
+	BUG_ON(cmd->free_head < 0);
+	context = &cmd->context[cmd->free_head];
+	context->token += cmd->token_mask + 1;
+	cmd->free_head = context->next;
+	spin_unlock(&cmd->context_lock);
+
+	init_completion(&context->done);
+
+	mlx4_comm_cmd_post(dev, op, param);
+
+	if (!wait_for_completion_timeout(&context->done,
+					 msecs_to_jiffies(timeout))) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	err = context->result;
+	if (err && context->fw_status != CMD_STAT_MULTI_FUNC_REQ) {
+		mlx4_err(dev, "command 0x%x failed: fw status = 0x%x\n",
+			 op, context->fw_status);
+		goto out;
+	}
+
+out:
+	spin_lock(&cmd->context_lock);
+	context->next = cmd->free_head;
+	cmd->free_head = context - cmd->context;
+	spin_unlock(&cmd->context_lock);
+
+	up(&cmd->event_sem);
+	return err;
+}
+
+int mlx4_comm_cmd(struct mlx4_dev *dev, u8 cmd, u16 param,
+		  unsigned long timeout)
+{
+	if (mlx4_priv(dev)->cmd.use_events)
+		return mlx4_comm_cmd_wait(dev, cmd, param, timeout);
+	return mlx4_comm_cmd_poll(dev, cmd, param, timeout);
+}
+
 static int cmd_pending(struct mlx4_dev *dev)
 {
 	u32 status = readl(mlx4_priv(dev)->cmd.hcr + HCR_STATUS_OFFSET);
@@ -167,8 +290,10 @@ static int mlx4_cmd_post(struct mlx4_dev *dev, u64 in_param, u64 out_param,
 		end += msecs_to_jiffies(GO_BIT_TIMEOUT_MSECS);
 
 	while (cmd_pending(dev)) {
-		if (time_after_eq(jiffies, end))
+		if (time_after_eq(jiffies, end)) {
+			mlx4_err(dev, "%s:cmd_pending failed\n", __func__);
 			goto out;
+		}
 		cond_resched();
 	}
 
@@ -192,7 +317,7 @@ static int mlx4_cmd_post(struct mlx4_dev *dev, u64 in_param, u64 out_param,
 					       (cmd->toggle << HCR_T_BIT)	|
 					       (event ? (1 << HCR_E_BIT) : 0)	|
 					       (op_modifier << HCR_OPMOD_SHIFT) |
-					       op),			  hcr + 6);
+					       op), hcr + 6);
 
 	/*
 	 * Make sure that our HCR writes don't get mixed in with
@@ -209,6 +334,62 @@ out:
 	return ret;
 }
 
+static int mlx4_slave_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
+			  int out_is_imm, u32 in_modifier, u8 op_modifier,
+			  u16 op, unsigned long timeout)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_vhcr_cmd *vhcr = priv->mfunc.vhcr;
+	int ret;
+
+	down(&priv->cmd.slave_sem);
+	vhcr->in_param = cpu_to_be64(in_param);
+	vhcr->out_param = out_param ? cpu_to_be64(*out_param) : 0;
+	vhcr->in_modifier = cpu_to_be32(in_modifier);
+	vhcr->opcode = cpu_to_be16((((u16) op_modifier) << 12) | (op & 0xfff));
+	vhcr->token = cpu_to_be16(CMD_POLL_TOKEN);
+	vhcr->status = 0;
+	vhcr->flags = !!(priv->cmd.use_events) << 6;
+	if (mlx4_is_master(dev)) {
+		ret = mlx4_master_process_vhcr(dev, dev->caps.function, vhcr);
+		if (!ret) {
+			if (out_is_imm) {
+				if (out_param)
+					*out_param =
+						be64_to_cpu(vhcr->out_param);
+				else {
+					mlx4_err(dev, "response expected while"
+						 "output mailbox is NULL for "
+						 "command 0x%x\n", op);
+					vhcr->status = -EINVAL;
+				}
+			}
+			ret = vhcr->status;
+		}
+	} else {
+		ret = mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR_POST, 0,
+				    MLX4_COMM_TIME + timeout);
+		if (!ret) {
+			if (out_is_imm) {
+				if (out_param)
+					*out_param =
+						be64_to_cpu(vhcr->out_param);
+				else {
+					mlx4_err(dev, "response expected while"
+						 "output mailbox is NULL for "
+						 "command 0x%x\n", op);
+					vhcr->status = -EINVAL;
+				}
+			}
+			ret = vhcr->status;
+		} else
+			mlx4_err(dev, "failed execution of VHCR_POST command"
+				 "opcode 0x%x\n", op);
+	}
+	up(&priv->cmd.slave_sem);
+	return ret;
+}
+
 static int mlx4_cmd_poll(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 			 int out_is_imm, u32 in_modifier, u8 op_modifier,
 			 u16 op, unsigned long timeout)
@@ -217,6 +398,7 @@ static int mlx4_cmd_poll(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 	void __iomem *hcr = priv->cmd.hcr;
 	int err = 0;
 	unsigned long end;
+	u32 stat;
 
 	down(&priv->cmd.poll_sem);
 
@@ -240,9 +422,12 @@ static int mlx4_cmd_poll(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 					  __raw_readl(hcr + HCR_OUT_PARAM_OFFSET)) << 32 |
 			(u64) be32_to_cpu((__force __be32)
 					  __raw_readl(hcr + HCR_OUT_PARAM_OFFSET + 4));
-
-	err = mlx4_status_to_errno(be32_to_cpu((__force __be32)
-					       __raw_readl(hcr + HCR_STATUS_OFFSET)) >> 24);
+	stat = be32_to_cpu((__force __be32)
+			   __raw_readl(hcr + HCR_STATUS_OFFSET)) >> 24;
+	err = mlx4_status_to_errno(stat);
+	if (err)
+		mlx4_err(dev, "command 0x%x failed: fw status = 0x%x\n",
+			 op, stat);
 
 out:
 	up(&priv->cmd.poll_sem);
@@ -259,6 +444,7 @@ void mlx4_cmd_event(struct mlx4_dev *dev, u16 token, u8 status, u64 out_param)
 	if (token != context->token)
 		return;
 
+	context->fw_status = status;
 	context->result    = mlx4_status_to_errno(status);
 	context->out_param = out_param;
 
@@ -287,14 +473,18 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 	mlx4_cmd_post(dev, in_param, out_param ? *out_param : 0,
 		      in_modifier, op_modifier, op, context->token, 1);
 
-	if (!wait_for_completion_timeout(&context->done, msecs_to_jiffies(timeout))) {
+	if (!wait_for_completion_timeout(&context->done,
+					 msecs_to_jiffies(timeout))) {
 		err = -EBUSY;
 		goto out;
 	}
 
 	err = context->result;
-	if (err)
+	if (err) {
+		mlx4_err(dev, "command 0x%x failed: fw status = 0x%x\n",
+			 op, context->fw_status);
 		goto out;
+	}
 
 	if (out_is_imm)
 		*out_param = context->out_param;
@@ -311,17 +501,1042 @@ out:
 
 int __mlx4_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 	       int out_is_imm, u32 in_modifier, u8 op_modifier,
-	       u16 op, unsigned long timeout)
+	       u16 op, unsigned long timeout, int native)
 {
-	if (mlx4_priv(dev)->cmd.use_events)
-		return mlx4_cmd_wait(dev, in_param, out_param, out_is_imm,
-				     in_modifier, op_modifier, op, timeout);
-	else
-		return mlx4_cmd_poll(dev, in_param, out_param, out_is_imm,
-				     in_modifier, op_modifier, op, timeout);
+	if (!mlx4_is_mfunc(dev) || (native && mlx4_is_master(dev))) {
+		if (mlx4_priv(dev)->cmd.use_events)
+			return mlx4_cmd_wait(dev, in_param, out_param,
+					     out_is_imm, in_modifier,
+					     op_modifier, op, timeout);
+		else
+			return mlx4_cmd_poll(dev, in_param, out_param,
+					     out_is_imm, in_modifier,
+					     op_modifier, op, timeout);
+	}
+	return mlx4_slave_cmd(dev, in_param, out_param, out_is_imm,
+			      in_modifier, op_modifier, op, timeout);
 }
 EXPORT_SYMBOL_GPL(__mlx4_cmd);
 
+
+static int mlx4_ARM_COMM_CHANNEL(struct mlx4_dev *dev)
+{
+	return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_ARM_COMM_CHANNEL,
+			MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+}
+
+static int mlx4_ACCESS_MEM(struct mlx4_dev *dev, u64 master_addr,
+			   int slave, u64 slave_addr,
+			   int size, int is_read)
+{
+	u64 in_param;
+	u64 out_param;
+
+	if ((slave_addr & 0xfff) | (master_addr & 0xfff) |
+	    (slave & ~0x7f) | (size & 0xff)) {
+		mlx4_err(dev, "Bad access mem params - slave_addr:0x%llx "
+			      "master_addr:0x%llx slave_id:%d size:%d\n",
+			      slave_addr, master_addr, slave, size);
+		return -EINVAL;
+	}
+
+	if (is_read) {
+		in_param = (u64) slave | slave_addr;
+		out_param = (u64) dev->caps.function | master_addr;
+	} else {
+		in_param = (u64) dev->caps.function | master_addr;
+		out_param = (u64) slave | slave_addr;
+	}
+
+	return mlx4_cmd_imm(dev, in_param, &out_param, size, 0,
+			    MLX4_CMD_ACCESS_MEM,
+			    MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
+}
+
+int mlx4_DMA_wrapper(struct mlx4_dev *dev, int slave,
+		     struct mlx4_vhcr *vhcr,
+		     struct mlx4_cmd_mailbox *inbox,
+		     struct mlx4_cmd_mailbox *outbox,
+		     struct mlx4_cmd_info *cmd)
+{
+	u64 in_param;
+	u64 out_param;
+	int err;
+
+	in_param = cmd->has_inbox ? (u64) inbox->dma : vhcr->in_param;
+	out_param = cmd->has_outbox ? (u64) outbox->dma : vhcr->out_param;
+	if (cmd->encode_slave_id) {
+		in_param &= 0xffffffffffffff00ll;
+		in_param |= slave;
+	}
+
+	err = __mlx4_cmd(dev, in_param, &out_param, cmd->out_is_imm,
+			 vhcr->in_modifier, vhcr->op_modifier, vhcr->op,
+			 MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
+
+	if (cmd->out_is_imm)
+		vhcr->out_param = out_param;
+
+	return err;
+}
+
+static struct mlx4_cmd_info cmd_info[] = {
+	{
+		.opcode = MLX4_CMD_QUERY_FW,
+		.has_inbox = false,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = NULL
+	},
+	{
+		.opcode = MLX4_CMD_QUERY_HCA,
+		.has_inbox = false,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = NULL
+	},
+	{
+		.opcode = MLX4_CMD_QUERY_DEV_CAP,
+		.has_inbox = false,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = NULL
+	},
+	{
+		.opcode = MLX4_CMD_QUERY_FUNC_CAP,
+		.has_inbox = false,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_QUERY_FUNC_CAP_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_QUERY_ADAPTER,
+		.has_inbox = false,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = NULL
+	},
+	{
+		.opcode = MLX4_CMD_INIT_PORT,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_INIT_PORT_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_CLOSE_PORT,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm  = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_CLOSE_PORT_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_QUERY_PORT,
+		.has_inbox = false,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_QUERY_PORT_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_SET_PORT,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_SET_PORT_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_MAP_EQ,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_MAP_EQ_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_SW2HW_EQ,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = true,
+		.verify = NULL,
+		.wrapper = mlx4_SW2HW_EQ_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_HW_HEALTH_CHECK,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = NULL
+	},
+	{
+		.opcode = MLX4_CMD_NOP,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = NULL
+	},
+	{
+		.opcode = MLX4_CMD_ALLOC_RES,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = true,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_ALLOC_RES_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_FREE_RES,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_FREE_RES_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_SW2HW_MPT,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = true,
+		.verify = NULL,
+		.wrapper = mlx4_SW2HW_MPT_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_QUERY_MPT,
+		.has_inbox = false,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_QUERY_MPT_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_HW2SW_MPT,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_HW2SW_MPT_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_READ_MTT,
+		.has_inbox = false,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = NULL
+	},
+	{
+		.opcode = MLX4_CMD_WRITE_MTT,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_WRITE_MTT_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_SYNC_TPT,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = NULL
+	},
+	{
+		.opcode = MLX4_CMD_HW2SW_EQ,
+		.has_inbox = false,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = true,
+		.verify = NULL,
+		.wrapper = mlx4_HW2SW_EQ_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_QUERY_EQ,
+		.has_inbox = false,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = true,
+		.verify = NULL,
+		.wrapper = mlx4_QUERY_EQ_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_SW2HW_CQ,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = true,
+		.verify = NULL,
+		.wrapper = mlx4_SW2HW_CQ_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_HW2SW_CQ,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_HW2SW_CQ_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_QUERY_CQ,
+		.has_inbox = false,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_QUERY_CQ_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_MODIFY_CQ,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = true,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_MODIFY_CQ_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_SW2HW_SRQ,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = true,
+		.verify = NULL,
+		.wrapper = mlx4_SW2HW_SRQ_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_HW2SW_SRQ,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_HW2SW_SRQ_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_QUERY_SRQ,
+		.has_inbox = false,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_QUERY_SRQ_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_ARM_SRQ,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_ARM_SRQ_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_RST2INIT_QP,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = true,
+		.verify = NULL,
+		.wrapper = mlx4_RST2INIT_QP_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_INIT2INIT_QP,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_GEN_QP_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_INIT2RTR_QP,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_INIT2RTR_QP_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_RTR2RTS_QP,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_GEN_QP_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_RTS2RTS_QP,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_GEN_QP_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_SQERR2RTS_QP,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_GEN_QP_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_2ERR_QP,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_GEN_QP_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_RTS2SQD_QP,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_GEN_QP_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_SQD2SQD_QP,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_GEN_QP_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_SQD2RTS_QP,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_GEN_QP_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_2RST_QP,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_2RST_QP_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_QUERY_QP,
+		.has_inbox = false,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_GEN_QP_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_SUSPEND_QP,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_GEN_QP_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_UNSUSPEND_QP,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_GEN_QP_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_QUERY_IF_STAT,
+		.has_inbox = false,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_QUERY_IF_STAT_wrapper
+	},
+	/* Native multicast commands are not available for guests */
+	{
+		.opcode = MLX4_CMD_QP_ATTACH,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_QP_ATTACH_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_PROMISC,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_PROMISC_wrapper
+	},
+	/* Ethernet specific commands */
+	{
+		.opcode = MLX4_CMD_SET_VLAN_FLTR,
+		.has_inbox = true,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_SET_VLAN_FLTR_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_SET_MCAST_FLTR,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_SET_MCAST_FLTR_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_DUMP_ETH_STATS,
+		.has_inbox = false,
+		.has_outbox = true,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_DUMP_ETH_STATS_wrapper
+	},
+	{
+		.opcode = MLX4_CMD_INFORM_FLR_DONE,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = NULL
+	},
+};
+
+static int mlx4_master_process_vhcr(struct mlx4_dev *dev, int slave,
+				    struct mlx4_vhcr_cmd *in_vhcr)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_cmd_info *cmd = NULL;
+	struct mlx4_vhcr_cmd *vhcr_cmd = in_vhcr ? in_vhcr : priv->mfunc.vhcr;
+	struct mlx4_vhcr *vhcr;
+	struct mlx4_cmd_mailbox *inbox = NULL;
+	struct mlx4_cmd_mailbox *outbox = NULL;
+	u64 in_param;
+	u64 out_param;
+	int ret = 0;
+	int i;
+
+	/* Create sw representation of Virtual HCR */
+	vhcr = kzalloc(sizeof(struct mlx4_vhcr), GFP_KERNEL);
+	if (!vhcr)
+		return -ENOMEM;
+
+	/* DMA in the vHCR */
+	if (!in_vhcr) {
+		ret = mlx4_ACCESS_MEM(dev, priv->mfunc.vhcr_dma, slave,
+				      priv->mfunc.master.slave_state[slave].vhcr_dma,
+				      ALIGN(sizeof(struct mlx4_vhcr_cmd),
+					    MLX4_ACCESS_MEM_ALIGN), 1);
+		if (ret) {
+			mlx4_err(dev, "%s:Failed reading vhcr"
+				 "ret: 0x%x\n", __func__, ret);
+			kfree(vhcr);
+			return ret;
+		}
+	}
+
+	/* Fill SW VHCR fields */
+	vhcr->in_param = be64_to_cpu(vhcr_cmd->in_param);
+	vhcr->out_param = be64_to_cpu(vhcr_cmd->out_param);
+	vhcr->in_modifier = be32_to_cpu(vhcr_cmd->in_modifier);
+	vhcr->token = be16_to_cpu(vhcr_cmd->token);
+	vhcr->op = be16_to_cpu(vhcr_cmd->opcode) & 0xfff;
+	vhcr->op_modifier = (u8) (be16_to_cpu(vhcr_cmd->opcode) >> 12);
+	vhcr->e_bit = vhcr_cmd->flags & (1 << 6);
+
+	/* Lookup command */
+	for (i = 0; i < ARRAY_SIZE(cmd_info); ++i) {
+		if (vhcr->op == cmd_info[i].opcode) {
+			cmd = &cmd_info[i];
+			break;
+		}
+	}
+	if (!cmd) {
+		mlx4_err(dev, "Unknown command:0x%x accepted from slave:%d\n",
+			 vhcr->op, slave);
+		vhcr_cmd->status = -EINVAL;
+		goto out_status;
+	}
+
+	/* Read inbox */
+	if (cmd->has_inbox) {
+		vhcr->in_param &= INBOX_MASK;
+		inbox = mlx4_alloc_cmd_mailbox(dev);
+		if (IS_ERR(inbox)) {
+			ret = PTR_ERR(inbox);
+			inbox = NULL;
+			goto out;
+		}
+
+		ret = mlx4_ACCESS_MEM(dev, inbox->dma, slave,
+				      vhcr->in_param,
+				      MLX4_MAILBOX_SIZE, 1);
+		if (ret) {
+			mlx4_err(dev, "%s: Failed reading inbox (cmd:0x%x)\n",
+				 __func__, cmd->opcode);
+			goto out;
+		}
+	}
+
+	/* Apply permission and bound checks if applicable */
+	if (cmd->verify && cmd->verify(dev, slave, vhcr, inbox)) {
+		mlx4_warn(dev, "Command:0x%x from slave: %d failed protection "
+			  "checks for resource_id:%d\n", vhcr->op, slave,
+			  vhcr->in_modifier);
+		vhcr_cmd->status = -EPERM;
+		goto out_status;
+	}
+
+	/* Allocate outbox */
+	if (cmd->has_outbox) {
+		outbox = mlx4_alloc_cmd_mailbox(dev);
+		if (IS_ERR(outbox)) {
+			ret = PTR_ERR(outbox);
+			outbox = NULL;
+			goto out;
+		}
+	}
+
+	/* Execute the command! */
+	if (cmd->wrapper) {
+		vhcr_cmd->status = cmd->wrapper(dev, slave, vhcr, inbox, outbox,
+					   cmd);
+		if (cmd->out_is_imm)
+			vhcr_cmd->out_param = cpu_to_be64(vhcr->out_param);
+	} else {
+		in_param = cmd->has_inbox ? (u64) inbox->dma :
+			vhcr->in_param;
+		out_param = cmd->has_outbox ? (u64) outbox->dma :
+			vhcr->out_param;
+		vhcr_cmd->status = __mlx4_cmd(dev, in_param, &out_param,
+					 cmd->out_is_imm, vhcr->in_modifier,
+					 vhcr->op_modifier, vhcr->op,
+					 MLX4_CMD_TIME_CLASS_A,
+					 MLX4_CMD_NATIVE);
+
+		if (vhcr_cmd->status) {
+			mlx4_warn(dev, "vhcr command:0x%x slave:%d failed with"
+				  " error:%d, status %d\n",
+				  vhcr->op, slave, vhcr->errno,
+				  vhcr_cmd->status);
+			ret = vhcr_cmd->status;
+			goto out;
+		}
+
+		if (cmd->out_is_imm) {
+			vhcr->out_param = out_param;
+			vhcr_cmd->out_param = cpu_to_be64(vhcr->out_param);
+		}
+	}
+
+	/* Write outbox if command completed successfully */
+	if (cmd->has_outbox && !vhcr->errno) {
+		ret = mlx4_ACCESS_MEM(dev, outbox->dma, slave,
+				      vhcr->out_param,
+				      MLX4_MAILBOX_SIZE, MLX4_CMD_WRAPPED);
+		if (ret) {
+			mlx4_err(dev, "%s:Failed writing outbox\n", __func__);
+			goto out;
+		}
+	}
+
+out_status:
+	/* DMA back vhcr result */
+	if (!in_vhcr) {
+		ret = mlx4_ACCESS_MEM(dev, priv->mfunc.vhcr_dma, slave,
+				      priv->mfunc.master.slave_state[slave].vhcr_dma,
+				      ALIGN(sizeof(struct mlx4_vhcr),
+					    MLX4_ACCESS_MEM_ALIGN),
+				      MLX4_CMD_WRAPPED);
+		if (ret)
+			mlx4_err(dev, "%s:Failed writing vhcr result\n",
+				 __func__);
+		else if (vhcr->e_bit &&
+			 mlx4_GEN_EQE(dev, slave, &priv->mfunc.master.cmd_eqe))
+				mlx4_warn(dev, "Failed to generate command completion "
+					  "eqe for slave %d\n", slave);
+	}
+
+out:
+	kfree(vhcr);
+	mlx4_free_cmd_mailbox(dev, inbox);
+	mlx4_free_cmd_mailbox(dev, outbox);
+	return ret;
+}
+
+static void mlx4_master_do_cmd(struct mlx4_dev *dev, int slave, u8 cmd,
+			       u16 param, u8 toggle)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_slave_state *slave_state = priv->mfunc.master.slave_state;
+	u32 reply;
+	u32 slave_status = 0;
+	u8 is_going_down = 0;
+
+	slave_state[slave].comm_toggle ^= 1;
+	reply = (u32) slave_state[slave].comm_toggle << 31;
+	if (toggle != slave_state[slave].comm_toggle) {
+		mlx4_warn(dev, "Incorrect toggle %d from slave %d. *** MASTER"
+			  "STATE COMPROMISIED ***\n", toggle, slave);
+		goto reset_slave;
+	}
+	if (cmd == MLX4_COMM_CMD_RESET) {
+		mlx4_warn(dev, "Received reset from slave:%d\n", slave);
+		slave_state[slave].active = false;
+		/*check if we are in the middle of FLR process,
+		if so return "retry" status to the slave*/
+		if (MLX4_COMM_CMD_FLR == slave_state[slave].last_cmd) {
+			slave_status = MLX4_DELAY_RESET_SLAVE;
+			goto inform_slave_state;
+		}
+
+		/* write the version in the event field */
+		reply |= mlx4_comm_get_version();
+
+		goto reset_slave;
+	}
+	/*command from slave in the middle of FLR*/
+	if (cmd != MLX4_COMM_CMD_RESET &&
+	    MLX4_COMM_CMD_FLR == slave_state[slave].last_cmd) {
+		mlx4_warn(dev, "slave:%d is Trying to run cmd(0x%x) "
+			  "in the middle of FLR\n", slave, cmd);
+		return;
+	}
+
+	switch (cmd) {
+	case MLX4_COMM_CMD_VHCR0:
+		if (slave_state[slave].last_cmd != MLX4_COMM_CMD_RESET)
+			goto reset_slave;
+		slave_state[slave].vhcr_dma = ((u64) param) << 48;
+		priv->mfunc.master.slave_state[slave].cookie = 0;
+		mutex_init(&priv->mfunc.master.gen_eqe_mutex[slave]);
+		break;
+	case MLX4_COMM_CMD_VHCR1:
+		if (slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR0)
+			goto reset_slave;
+		slave_state[slave].vhcr_dma |= ((u64) param) << 32;
+		break;
+	case MLX4_COMM_CMD_VHCR2:
+		if (slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR1)
+			goto reset_slave;
+		slave_state[slave].vhcr_dma |= ((u64) param) << 16;
+		break;
+	case MLX4_COMM_CMD_VHCR_EN:
+		if (slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR2)
+			goto reset_slave;
+		slave_state[slave].vhcr_dma |= param;
+		slave_state[slave].active = true;
+		break;
+	case MLX4_COMM_CMD_VHCR_POST:
+		if ((slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR_EN) &&
+		    (slave_state[slave].last_cmd != MLX4_COMM_CMD_VHCR_POST))
+			goto reset_slave;
+		down(&priv->cmd.slave_sem);
+		if (mlx4_master_process_vhcr(dev, slave, NULL)) {
+			mlx4_err(dev, "Failed processing vhcr for slave:%d,"
+				 " reseting slave.\n", slave);
+			up(&priv->cmd.slave_sem);
+			goto reset_slave;
+		}
+		up(&priv->cmd.slave_sem);
+		break;
+	default:
+		mlx4_warn(dev, "Bad comm cmd:%d from slave:%d\n", cmd, slave);
+		goto reset_slave;
+	}
+	spin_lock(&priv->mfunc.master.slave_state_lock);
+	if (!slave_state[slave].is_slave_going_down)
+		slave_state[slave].last_cmd = cmd;
+	else
+		is_going_down = 1;
+	spin_unlock(&priv->mfunc.master.slave_state_lock);
+	if (is_going_down) {
+		mlx4_warn(dev, "Slave is going down aborting command(%d)"
+			  " executing from slave:%d\n",
+			  cmd, slave);
+		return;
+	}
+	__raw_writel((__force u32) cpu_to_be32(reply),
+		     &priv->mfunc.comm[slave].slave_read);
+	mmiowb();
+
+	return;
+
+reset_slave:
+	/* cleanup any slave resources */
+	mlx4_delete_all_resources_for_slave(dev, slave);
+	spin_lock(&priv->mfunc.master.slave_state_lock);
+	if (!slave_state[slave].is_slave_going_down)
+		slave_state[slave].last_cmd = MLX4_COMM_CMD_RESET;
+	spin_unlock(&priv->mfunc.master.slave_state_lock);
+	/*with slave in the middle of flr, no need to clean resources again.*/
+inform_slave_state:
+	memset(&slave_state[slave].event_eq, 0,
+	       sizeof(struct mlx4_slave_event_eq_info));
+	__raw_writel((__force u32) cpu_to_be32(reply),
+		     &priv->mfunc.comm[slave].slave_read);
+	wmb();
+}
+
+/* master command processing */
+void mlx4_master_comm_channel(struct work_struct *work)
+{
+	struct mlx4_mfunc_master_ctx *master =
+		container_of(work,
+			     struct mlx4_mfunc_master_ctx,
+			     comm_work);
+	struct mlx4_mfunc *mfunc =
+		container_of(master, struct mlx4_mfunc, master);
+	struct mlx4_priv *priv =
+		container_of(mfunc, struct mlx4_priv, mfunc);
+	struct mlx4_dev *dev = &priv->dev;
+	__be32 *bit_vec;
+	u32 comm_cmd;
+	u32 vec;
+	int i, j, slave;
+	int toggle;
+	int served = 0;
+	int reported = 0;
+	u32 slt;
+
+	bit_vec = master->comm_arm_bit_vector;
+	for (i = 0; i < COMM_CHANNEL_BIT_ARRAY_SIZE; i++) {
+		vec = be32_to_cpu(bit_vec[i]);
+		for (j = 0; j < 32; j++) {
+			if (!(vec & (1 << j)))
+				continue;
+			++reported;
+			slave = (i * 32) + j;
+			comm_cmd = swab32(readl(
+					  &mfunc->comm[slave].slave_write));
+			slt = swab32(readl(&mfunc->comm[slave].slave_read))
+				     >> 31;
+			toggle = comm_cmd >> 31;
+			if (toggle != slt) {
+				if (master->slave_state[slave].comm_toggle
+				    != slt) {
+					printk(KERN_INFO "slave %d out of sync."
+					       " read toggle %d, state toggle %d. "
+					       "Resynching.\n", slave, slt,
+					       master->slave_state[slave].comm_toggle);
+					master->slave_state[slave].comm_toggle =
+						slt;
+				}
+				mlx4_master_do_cmd(dev, slave,
+						   comm_cmd >> 16 & 0xff,
+						   comm_cmd & 0xffff, toggle);
+				++served;
+			}
+		}
+	}
+
+	if (reported && reported != served)
+		mlx4_warn(dev, "Got command event with bitmask from %d slaves"
+			  " but %d were served\n",
+			  reported, served);
+
+	if (mlx4_ARM_COMM_CHANNEL(dev))
+		mlx4_warn(dev, "Failed to arm comm channel events\n");
+}
+
+static int sync_toggles(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int wr_toggle;
+	int rd_toggle;
+	unsigned long end;
+
+	wr_toggle = swab32(readl(&priv->mfunc.comm->slave_write)) >> 31;
+	end = jiffies + msecs_to_jiffies(5000);
+
+	while (time_before(jiffies, end)) {
+		rd_toggle = swab32(readl(&priv->mfunc.comm->slave_read)) >> 31;
+		if (rd_toggle == wr_toggle) {
+			priv->cmd.comm_toggle = rd_toggle;
+			return 0;
+		}
+
+		cond_resched();
+	}
+
+	/*
+	 * we could reach here if for example the previous VM using this
+	 * function misbehaved and left the channel with unsynced state. We
+	 * should fix this here and give this VM a chance to use a properly
+	 * synced channel
+	 */
+	mlx4_warn(dev, "recovering from previously mis-behaved VM\n");
+	__raw_writel((__force u32) 0, &priv->mfunc.comm->slave_read);
+	__raw_writel((__force u32) 0, &priv->mfunc.comm->slave_write);
+	priv->cmd.comm_toggle = 0;
+
+	return 0;
+}
+
+int mlx4_multi_func_init(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_slave_state *s_state;
+	int i, err, port;
+
+	priv->mfunc.vhcr = dma_alloc_coherent(&(dev->pdev->dev), PAGE_SIZE,
+					    &priv->mfunc.vhcr_dma,
+					    GFP_KERNEL);
+	if (!priv->mfunc.vhcr) {
+		mlx4_err(dev, "Couldn't allocate vhcr.\n");
+		return -ENOMEM;
+	}
+
+	if (mlx4_is_master(dev))
+		priv->mfunc.comm =
+		ioremap(pci_resource_start(dev->pdev, priv->fw.comm_bar) +
+			priv->fw.comm_base, MLX4_COMM_PAGESIZE);
+	else
+		priv->mfunc.comm =
+		ioremap(pci_resource_start(dev->pdev, 2) +
+			MLX4_SLAVE_COMM_BASE, MLX4_COMM_PAGESIZE);
+	if (!priv->mfunc.comm) {
+		mlx4_err(dev, "Couldn't map communication vector.\n");
+		goto err_vhcr;
+	}
+
+	if (mlx4_is_master(dev)) {
+		priv->mfunc.master.slave_state =
+			kzalloc(dev->num_slaves *
+				sizeof(struct mlx4_slave_state), GFP_KERNEL);
+		if (!priv->mfunc.master.slave_state)
+			goto err_comm;
+
+		for (i = 0; i < dev->num_slaves; ++i) {
+			s_state = &priv->mfunc.master.slave_state[i];
+			s_state->last_cmd = MLX4_COMM_CMD_RESET;
+			__raw_writel((__force u32) 0,
+				     &priv->mfunc.comm[i].slave_write);
+			__raw_writel((__force u32) 0,
+				     &priv->mfunc.comm[i].slave_read);
+			mmiowb();
+			for (port = 1; port <= MLX4_MAX_PORTS; port++) {
+				s_state->vlan_filter[port] =
+					kzalloc(sizeof(struct mlx4_vlan_fltr),
+						GFP_KERNEL);
+				if (!s_state->vlan_filter[port]) {
+					if (--port)
+						kfree(s_state->vlan_filter[port]);
+					goto err_slaves;
+				}
+				INIT_LIST_HEAD(&s_state->mcast_filters[port]);
+			}
+			spin_lock_init(&s_state->lock);
+		}
+
+		memset(&priv->mfunc.master.cmd_eqe, 0, sizeof(struct mlx4_eqe));
+		priv->mfunc.master.cmd_eqe.type = MLX4_EVENT_TYPE_CMD;
+		INIT_WORK(&priv->mfunc.master.comm_work,
+			  mlx4_master_comm_channel);
+		INIT_WORK(&priv->mfunc.master.slave_event_work,
+			  mlx4_gen_slave_eqe);
+		INIT_WORK(&priv->mfunc.master.slave_flr_event_work,
+			  mlx4_master_handle_slave_flr);
+		spin_lock_init(&priv->mfunc.master.slave_state_lock);
+		priv->mfunc.master.comm_wq =
+			create_singlethread_workqueue("mlx4_comm");
+		if (!priv->mfunc.master.comm_wq)
+			goto err_slaves;
+
+		if (mlx4_init_resource_tracker(dev))
+			goto err_thread;
+
+		sema_init(&priv->cmd.slave_sem, 1);
+		err = mlx4_ARM_COMM_CHANNEL(dev);
+		if (err) {
+			mlx4_err(dev, " Failed to arm comm channel eq: %x\n",
+				 err);
+			goto err_resource;
+		}
+
+	} else {
+		err = sync_toggles(dev);
+		if (err) {
+			mlx4_err(dev, "Couldn't sync toggles\n");
+			goto err_comm;
+		}
+
+		sema_init(&priv->cmd.slave_sem, 1);
+	}
+	return 0;
+
+err_resource:
+	mlx4_free_resource_tracker(dev);
+err_thread:
+	flush_workqueue(priv->mfunc.master.comm_wq);
+	destroy_workqueue(priv->mfunc.master.comm_wq);
+err_slaves:
+	while (--i) {
+		for (port = 1; port <= MLX4_MAX_PORTS; port++)
+			kfree(priv->mfunc.master.slave_state[i].vlan_filter[port]);
+	}
+	kfree(priv->mfunc.master.slave_state);
+err_comm:
+	iounmap(priv->mfunc.comm);
+err_vhcr:
+	dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE,
+					     priv->mfunc.vhcr,
+					     priv->mfunc.vhcr_dma);
+	priv->mfunc.vhcr = NULL;
+	return -ENOMEM;
+}
+
 int mlx4_cmd_init(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -331,22 +1546,51 @@ int mlx4_cmd_init(struct mlx4_dev *dev)
 	priv->cmd.use_events = 0;
 	priv->cmd.toggle     = 1;
 
-	priv->cmd.hcr = ioremap(pci_resource_start(dev->pdev, 0) + MLX4_HCR_BASE,
-				MLX4_HCR_SIZE);
-	if (!priv->cmd.hcr) {
-		mlx4_err(dev, "Couldn't map command register.");
-		return -ENOMEM;
+	priv->cmd.hcr = NULL;
+	priv->mfunc.vhcr = NULL;
+
+	if (!mlx4_is_slave(dev)) {
+		priv->cmd.hcr = ioremap(pci_resource_start(dev->pdev, 0) +
+					MLX4_HCR_BASE, MLX4_HCR_SIZE);
+		if (!priv->cmd.hcr) {
+			mlx4_err(dev, "Couldn't map command register.\n");
+			return -ENOMEM;
+		}
 	}
 
 	priv->cmd.pool = pci_pool_create("mlx4_cmd", dev->pdev,
 					 MLX4_MAILBOX_SIZE,
 					 MLX4_MAILBOX_SIZE, 0);
-	if (!priv->cmd.pool) {
-		iounmap(priv->cmd.hcr);
-		return -ENOMEM;
-	}
+	if (!priv->cmd.pool)
+		goto err_hcr;
 
 	return 0;
+
+err_hcr:
+	if (!mlx4_is_slave(dev))
+		iounmap(priv->cmd.hcr);
+	return -ENOMEM;
+}
+
+void mlx4_multi_func_cleanup(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int i, port;
+
+	if (mlx4_is_master(dev)) {
+		flush_workqueue(priv->mfunc.master.comm_wq);
+		destroy_workqueue(priv->mfunc.master.comm_wq);
+		for (i = 0; i < dev->num_slaves; i++) {
+			for (port = 1; port <= MLX4_MAX_PORTS; port++)
+				kfree(priv->mfunc.master.slave_state[i].vlan_filter[port]);
+		}
+		kfree(priv->mfunc.master.slave_state);
+		iounmap(priv->mfunc.comm);
+		dma_free_coherent(&(dev->pdev->dev), PAGE_SIZE,
+						     priv->mfunc.vhcr,
+						     priv->mfunc.vhcr_dma);
+		priv->mfunc.vhcr = NULL;
+	}
 }
 
 void mlx4_cmd_cleanup(struct mlx4_dev *dev)
@@ -354,7 +1598,9 @@ void mlx4_cmd_cleanup(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
 	pci_pool_destroy(priv->cmd.pool);
-	iounmap(priv->cmd.hcr);
+
+	if (!mlx4_is_slave(dev))
+		iounmap(priv->cmd.hcr);
 }
 
 /*
@@ -365,6 +1611,7 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int i;
+	int err = 0;
 
 	priv->cmd.context = kmalloc(priv->cmd.max_cmds *
 				   sizeof (struct mlx4_cmd_context),
@@ -389,11 +1636,10 @@ int mlx4_cmd_use_events(struct mlx4_dev *dev)
 		; /* nothing */
 	--priv->cmd.token_mask;
 
-	priv->cmd.use_events = 1;
-
 	down(&priv->cmd.poll_sem);
+	priv->cmd.use_events = 1;
 
-	return 0;
+	return err;
 }
 
 /*
@@ -433,7 +1679,8 @@ struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mlx4_alloc_cmd_mailbox);
 
-void mlx4_free_cmd_mailbox(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox)
+void mlx4_free_cmd_mailbox(struct mlx4_dev *dev,
+			   struct mlx4_cmd_mailbox *mailbox)
 {
 	if (!mailbox)
 		return;
@@ -442,3 +1689,8 @@ void mlx4_free_cmd_mailbox(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbo
 	kfree(mailbox);
 }
 EXPORT_SYMBOL_GPL(mlx4_free_cmd_mailbox);
+
+u32 mlx4_comm_get_version(void)
+{
+	 return ((u32) CMD_CHAN_IF_REV << 8) | (u32) CMD_CHAN_VER;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
index 499a516..475f9d6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -34,9 +34,9 @@
  * SOFTWARE.
  */
 
+#include <linux/init.h>
 #include <linux/hardirq.h>
 #include <linux/export.h>
-#include <linux/gfp.h>
 
 #include <linux/mlx4/cmd.h>
 #include <linux/mlx4/cq.h>
@@ -44,27 +44,6 @@
 #include "mlx4.h"
 #include "icm.h"
 
-struct mlx4_cq_context {
-	__be32			flags;
-	u16			reserved1[3];
-	__be16			page_offset;
-	__be32			logsize_usrpage;
-	__be16			cq_period;
-	__be16			cq_max_count;
-	u8			reserved2[3];
-	u8			comp_eqn;
-	u8			log_page_size;
-	u8			reserved3[2];
-	u8			mtt_base_addr_h;
-	__be32			mtt_base_addr_l;
-	__be32			last_notified_index;
-	__be32			solicit_producer_index;
-	__be32			consumer_index;
-	__be32			producer_index;
-	u32			reserved4[2];
-	__be64			db_rec_addr;
-};
-
 #define MLX4_CQ_STATUS_OK		( 0 << 28)
 #define MLX4_CQ_STATUS_OVERFLOW		( 9 << 28)
 #define MLX4_CQ_STATUS_WRITE_FAIL	(10 << 28)
@@ -81,7 +60,7 @@ void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn)
 	cq = radix_tree_lookup(&mlx4_priv(dev)->cq_table.tree,
 			       cqn & (dev->caps.num_cqs - 1));
 	if (!cq) {
-		mlx4_warn(dev, "Completion event for bogus CQ %08x\n", cqn);
+		mlx4_dbg(dev, "Completion event for bogus CQ %08x\n", cqn);
 		return;
 	}
 
@@ -117,23 +96,24 @@ void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type)
 static int mlx4_SW2HW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
 			 int cq_num)
 {
-	return mlx4_cmd(dev, mailbox->dma, cq_num, 0, MLX4_CMD_SW2HW_CQ,
-			MLX4_CMD_TIME_CLASS_A);
+	return mlx4_cmd(dev, mailbox->dma | dev->caps.function, cq_num, 0,
+			MLX4_CMD_SW2HW_CQ, MLX4_CMD_TIME_CLASS_A,
+			MLX4_CMD_WRAPPED);
 }
 
 static int mlx4_MODIFY_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
 			 int cq_num, u32 opmod)
 {
 	return mlx4_cmd(dev, mailbox->dma, cq_num, opmod, MLX4_CMD_MODIFY_CQ,
-			MLX4_CMD_TIME_CLASS_A);
+			MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 }
 
 static int mlx4_HW2SW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
 			 int cq_num)
 {
-	return mlx4_cmd_box(dev, 0, mailbox ? mailbox->dma : 0, cq_num,
-			    mailbox ? 0 : 1, MLX4_CMD_HW2SW_CQ,
-			    MLX4_CMD_TIME_CLASS_A);
+	return mlx4_cmd_box(dev, dev->caps.function, mailbox ? mailbox->dma : 0,
+			    cq_num, mailbox ? 0 : 1, MLX4_CMD_HW2SW_CQ,
+			    MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 }
 
 int mlx4_cq_modify(struct mlx4_dev *dev, struct mlx4_cq *cq,
@@ -188,6 +168,78 @@ int mlx4_cq_resize(struct mlx4_dev *dev, struct mlx4_cq *cq,
 }
 EXPORT_SYMBOL_GPL(mlx4_cq_resize);
 
+int __mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_cq_table *cq_table = &priv->cq_table;
+	int err;
+
+	*cqn = mlx4_bitmap_alloc(&cq_table->bitmap);
+	if (*cqn == -1)
+		return -ENOMEM;
+
+	err = mlx4_table_get(dev, &cq_table->table, *cqn);
+	if (err)
+		goto err_out;
+
+	err = mlx4_table_get(dev, &cq_table->cmpt_table, *cqn);
+	if (err)
+		goto err_put;
+	return 0;
+
+err_put:
+	mlx4_table_put(dev, &cq_table->table, *cqn);
+
+err_out:
+	mlx4_bitmap_free(&cq_table->bitmap, *cqn);
+	return err;
+}
+
+static int mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn)
+{
+	u64 out_param;
+	int err;
+
+	if (mlx4_is_mfunc(dev)) {
+		err = mlx4_cmd_imm(dev, 0, &out_param, RES_CQ,
+				   RES_OP_RESERVE_AND_MAP, MLX4_CMD_ALLOC_RES,
+				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		if (err)
+			return err;
+		else {
+			*cqn = get_param_l(&out_param);
+			return 0;
+		}
+	}
+	return __mlx4_cq_alloc_icm(dev, cqn);
+}
+
+void __mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_cq_table *cq_table = &priv->cq_table;
+
+	mlx4_table_put(dev, &cq_table->cmpt_table, cqn);
+	mlx4_table_put(dev, &cq_table->table, cqn);
+	mlx4_bitmap_free(&cq_table->bitmap, cqn);
+}
+
+static void mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn)
+{
+	u64 in_param;
+	int err;
+
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&in_param, cqn);
+		err = mlx4_cmd(dev, in_param, RES_CQ, RES_OP_RESERVE_AND_MAP,
+			       MLX4_CMD_FREE_RES,
+			       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		if (err)
+			mlx4_warn(dev, "Failed freeing cq:%d\n", cqn);
+	} else
+		__mlx4_cq_free_icm(dev, cqn);
+}
+
 int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
 		  struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq,
 		  unsigned vector, int collapsed)
@@ -204,23 +256,15 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
 
 	cq->vector = vector;
 
-	cq->cqn = mlx4_bitmap_alloc(&cq_table->bitmap);
-	if (cq->cqn == -1)
-		return -ENOMEM;
-
-	err = mlx4_table_get(dev, &cq_table->table, cq->cqn);
-	if (err)
-		goto err_out;
-
-	err = mlx4_table_get(dev, &cq_table->cmpt_table, cq->cqn);
+	err = mlx4_cq_alloc_icm(dev, &cq->cqn);
 	if (err)
-		goto err_put;
+		return err;
 
 	spin_lock_irq(&cq_table->lock);
 	err = radix_tree_insert(&cq_table->tree, cq->cqn, cq);
 	spin_unlock_irq(&cq_table->lock);
 	if (err)
-		goto err_cmpt_put;
+		goto err_icm;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox)) {
@@ -259,14 +303,8 @@ err_radix:
 	radix_tree_delete(&cq_table->tree, cq->cqn);
 	spin_unlock_irq(&cq_table->lock);
 
-err_cmpt_put:
-	mlx4_table_put(dev, &cq_table->cmpt_table, cq->cqn);
-
-err_put:
-	mlx4_table_put(dev, &cq_table->table, cq->cqn);
-
-err_out:
-	mlx4_bitmap_free(&cq_table->bitmap, cq->cqn);
+err_icm:
+	mlx4_cq_free_icm(dev, cq->cqn);
 
 	return err;
 }
@@ -292,8 +330,7 @@ void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq)
 		complete(&cq->free);
 	wait_for_completion(&cq->free);
 
-	mlx4_table_put(dev, &cq_table->table, cq->cqn);
-	mlx4_bitmap_free(&cq_table->bitmap, cq->cqn);
+	mlx4_cq_free_icm(dev, cq->cqn);
 }
 EXPORT_SYMBOL_GPL(mlx4_cq_free);
 
@@ -304,6 +341,8 @@ int mlx4_init_cq_table(struct mlx4_dev *dev)
 
 	spin_lock_init(&cq_table->lock);
 	INIT_RADIX_TREE(&cq_table->tree, GFP_ATOMIC);
+	if (mlx4_is_slave(dev))
+		return 0;
 
 	err = mlx4_bitmap_init(&cq_table->bitmap, dev->caps.num_cqs,
 			       dev->caps.num_cqs - 1, dev->caps.reserved_cqs, 0);
@@ -315,6 +354,8 @@ int mlx4_init_cq_table(struct mlx4_dev *dev)
 
 void mlx4_cleanup_cq_table(struct mlx4_dev *dev)
 {
+	if (mlx4_is_slave(dev))
+		return;
 	/* Nothing to do to clean up radix_tree */
 	mlx4_bitmap_cleanup(&mlx4_priv(dev)->cq_table.bitmap);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
index 227997d..2d1a342 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c
@@ -51,10 +51,7 @@ int mlx4_en_create_cq(struct mlx4_en_priv *priv,
 	int err;
 
 	cq->size = entries;
-	if (mode == RX)
-		cq->buf_size = cq->size * sizeof(struct mlx4_cqe);
-	else
-		cq->buf_size = sizeof(struct mlx4_cqe);
+	cq->buf_size = cq->size * sizeof(struct mlx4_cqe);
 
 	cq->ring = ring;
 	cq->is_tx = mode;
@@ -120,7 +117,7 @@ int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
 		cq->size = priv->rx_ring[cq->ring].actual_size;
 
 	err = mlx4_cq_alloc(mdev->dev, cq->size, &cq->wqres.mtt, &mdev->priv_uar,
-			    cq->wqres.db.dma, &cq->mcq, cq->vector, cq->is_tx);
+			    cq->wqres.db.dma, &cq->mcq, cq->vector, 0);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
index 74e2a2a..7dbc6a2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c
@@ -45,13 +45,16 @@ mlx4_en_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo)
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
 
-	strncpy(drvinfo->driver, DRV_NAME, 32);
-	strncpy(drvinfo->version, DRV_VERSION " (" DRV_RELDATE ")", 32);
-	sprintf(drvinfo->fw_version, "%d.%d.%d",
+	strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, DRV_VERSION " (" DRV_RELDATE ")",
+		sizeof(drvinfo->version));
+	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+		"%d.%d.%d",
 		(u16) (mdev->dev->caps.fw_ver >> 32),
 		(u16) ((mdev->dev->caps.fw_ver >> 16) & 0xffff),
 		(u16) (mdev->dev->caps.fw_ver & 0xffff));
-	strncpy(drvinfo->bus_info, pci_name(mdev->dev->pdev), 32);
+	strlcpy(drvinfo->bus_info, pci_name(mdev->dev->pdev),
+		sizeof(drvinfo->bus_info));
 	drvinfo->n_stats = 0;
 	drvinfo->regdump_len = 0;
 	drvinfo->eedump_len = 0;
@@ -103,8 +106,17 @@ static void mlx4_en_get_wol(struct net_device *netdev,
 	struct mlx4_en_priv *priv = netdev_priv(netdev);
 	int err = 0;
 	u64 config = 0;
+	u64 mask;
 
-	if (!(priv->mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_WOL)) {
+	if ((priv->port < 1) || (priv->port > 2)) {
+		en_err(priv, "Failed to get WoL information\n");
+		return;
+	}
+
+	mask = (priv->port == 1) ? MLX4_DEV_CAP_FLAG_WOL_PORT1 :
+		MLX4_DEV_CAP_FLAG_WOL_PORT2;
+
+	if (!(priv->mdev->dev->caps.flags & mask)) {
 		wol->supported = 0;
 		wol->wolopts = 0;
 		return;
@@ -133,8 +145,15 @@ static int mlx4_en_set_wol(struct net_device *netdev,
 	struct mlx4_en_priv *priv = netdev_priv(netdev);
 	u64 config = 0;
 	int err = 0;
+	u64 mask;
+
+	if ((priv->port < 1) || (priv->port > 2))
+		return -EOPNOTSUPP;
+
+	mask = (priv->port == 1) ? MLX4_DEV_CAP_FLAG_WOL_PORT1 :
+		MLX4_DEV_CAP_FLAG_WOL_PORT2;
 
-	if (!(priv->mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_WOL))
+	if (!(priv->mdev->dev->caps.flags & mask))
 		return -EOPNOTSUPP;
 
 	if (wol->supported & ~WAKE_MAGIC)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 78d776b..1db6fea 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -45,7 +45,7 @@
 #include "mlx4_en.h"
 #include "en_port.h"
 
-static void mlx4_en_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+static int mlx4_en_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
@@ -67,9 +67,10 @@ static void mlx4_en_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 		en_err(priv, "failed adding vlan %d\n", vid);
 	mutex_unlock(&mdev->state_lock);
 
+	return 0;
 }
 
-static void mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+static int mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
@@ -93,6 +94,8 @@ static void mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 			en_err(priv, "Failed configuring VLAN filter\n");
 	}
 	mutex_unlock(&mdev->state_lock);
+
+	return 0;
 }
 
 u64 mlx4_en_mac_to_u64(u8 *addr)
@@ -133,7 +136,7 @@ static void mlx4_en_do_set_mac(struct work_struct *work)
 	if (priv->port_up) {
 		/* Remove old MAC and insert the new one */
 		err = mlx4_replace_mac(mdev->dev, priv->port,
-				       priv->base_qpn, priv->mac, 0);
+				       priv->base_qpn, priv->mac);
 		if (err)
 			en_err(priv, "Failed changing HW MAC address\n");
 	} else
@@ -204,6 +207,16 @@ static void mlx4_en_do_set_multicast(struct work_struct *work)
 		goto out;
 	}
 
+	if (!netif_carrier_ok(dev)) {
+		if (!mlx4_en_QUERY_PORT(mdev, priv->port)) {
+			if (priv->port_state.link_state) {
+				priv->last_link_state = MLX4_DEV_EVENT_PORT_UP;
+				netif_carrier_on(dev);
+				en_dbg(LINK, priv, "Link Up\n");
+			}
+		}
+	}
+
 	/*
 	 * Promsicuous mode: disable all filters
 	 */
@@ -599,12 +612,12 @@ int mlx4_en_start_port(struct net_device *dev)
 		++rx_index;
 	}
 
-	/* Set port mac number */
-	en_dbg(DRV, priv, "Setting mac for port %d\n", priv->port);
-	err = mlx4_register_mac(mdev->dev, priv->port,
-				priv->mac, &priv->base_qpn, 0);
+	/* Set qp number */
+	en_dbg(DRV, priv, "Getting qp number for port %d\n", priv->port);
+	err = mlx4_get_eth_qp(mdev->dev, priv->port,
+				priv->mac, &priv->base_qpn);
 	if (err) {
-		en_err(priv, "Failed setting port mac\n");
+		en_err(priv, "Failed getting eth qp\n");
 		goto cq_err;
 	}
 	mdev->mac_removed[priv->port] = 0;
@@ -699,7 +712,7 @@ tx_err:
 
 	mlx4_en_release_rss_steer(priv);
 mac_err:
-	mlx4_unregister_mac(mdev->dev, priv->port, priv->base_qpn);
+	mlx4_put_eth_qp(mdev->dev, priv->port, priv->mac, priv->base_qpn);
 cq_err:
 	while (rx_index--)
 		mlx4_en_deactivate_cq(priv, &priv->rx_cq[rx_index]);
@@ -745,10 +758,6 @@ void mlx4_en_stop_port(struct net_device *dev)
 	/* Flush multicast filter */
 	mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0, 1, MLX4_MCAST_CONFIG);
 
-	/* Unregister Mac address for the port */
-	mlx4_unregister_mac(mdev->dev, priv->port, priv->base_qpn);
-	mdev->mac_removed[priv->port] = 1;
-
 	/* Free TX Rings */
 	for (i = 0; i < priv->tx_ring_num; i++) {
 		mlx4_en_deactivate_tx_ring(priv, &priv->tx_ring[i]);
@@ -762,6 +771,10 @@ void mlx4_en_stop_port(struct net_device *dev)
 	/* Free RSS qps */
 	mlx4_en_release_rss_steer(priv);
 
+	/* Unregister Mac address for the port */
+	mlx4_put_eth_qp(mdev->dev, priv->port, priv->mac, priv->base_qpn);
+	mdev->mac_removed[priv->port] = 1;
+
 	/* Free RX Rings */
 	for (i = 0; i < priv->rx_ring_num; i++) {
 		mlx4_en_deactivate_rx_ring(priv, &priv->rx_ring[i]);
@@ -974,6 +987,21 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
+static int mlx4_en_set_features(struct net_device *netdev,
+		netdev_features_t features)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+
+	if (features & NETIF_F_LOOPBACK)
+		priv->ctrl_flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK);
+	else
+		priv->ctrl_flags &=
+			cpu_to_be32(~MLX4_WQE_CTRL_FORCE_LOOPBACK);
+
+	return 0;
+
+}
+
 static const struct net_device_ops mlx4_netdev_ops = {
 	.ndo_open		= mlx4_en_open,
 	.ndo_stop		= mlx4_en_close,
@@ -990,6 +1018,7 @@ static const struct net_device_ops mlx4_netdev_ops = {
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= mlx4_en_netpoll,
 #endif
+	.ndo_set_features	= mlx4_en_set_features,
 };
 
 int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
@@ -1022,6 +1051,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	priv->port = port;
 	priv->port_up = false;
 	priv->flags = prof->flags;
+	priv->ctrl_flags = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE |
+			MLX4_WQE_CTRL_SOLICITED);
 	priv->tx_ring_num = prof->tx_ring_num;
 	priv->rx_ring_num = prof->rx_ring_num;
 	priv->mac_index = -1;
@@ -1088,6 +1119,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	dev->features = dev->hw_features | NETIF_F_HIGHDMA |
 			NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX |
 			NETIF_F_HW_VLAN_FILTER;
+	dev->hw_features |= NETIF_F_LOOPBACK;
 
 	mdev->pndev[port] = dev;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.c b/drivers/net/ethernet/mellanox/mlx4/en_port.c
index 03c84cd..3317914 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.c
@@ -41,13 +41,6 @@
 #include "mlx4_en.h"
 
 
-int mlx4_SET_MCAST_FLTR(struct mlx4_dev *dev, u8 port,
-			u64 mac, u64 clear, u8 mode)
-{
-	return mlx4_cmd(dev, (mac | (clear << 63)), port, mode,
-			MLX4_CMD_SET_MCAST_FLTR, MLX4_CMD_TIME_CLASS_B);
-}
-
 int mlx4_SET_VLAN_FLTR(struct mlx4_dev *dev, struct mlx4_en_priv *priv)
 {
 	struct mlx4_cmd_mailbox *mailbox;
@@ -72,76 +65,7 @@ int mlx4_SET_VLAN_FLTR(struct mlx4_dev *dev, struct mlx4_en_priv *priv)
 		filter->entry[i] = cpu_to_be32(entry);
 	}
 	err = mlx4_cmd(dev, mailbox->dma, priv->port, 0, MLX4_CMD_SET_VLAN_FLTR,
-		       MLX4_CMD_TIME_CLASS_B);
-	mlx4_free_cmd_mailbox(dev, mailbox);
-	return err;
-}
-
-
-int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu,
-			  u8 pptx, u8 pfctx, u8 pprx, u8 pfcrx)
-{
-	struct mlx4_cmd_mailbox *mailbox;
-	struct mlx4_set_port_general_context *context;
-	int err;
-	u32 in_mod;
-
-	mailbox = mlx4_alloc_cmd_mailbox(dev);
-	if (IS_ERR(mailbox))
-		return PTR_ERR(mailbox);
-	context = mailbox->buf;
-	memset(context, 0, sizeof *context);
-
-	context->flags = SET_PORT_GEN_ALL_VALID;
-	context->mtu = cpu_to_be16(mtu);
-	context->pptx = (pptx * (!pfctx)) << 7;
-	context->pfctx = pfctx;
-	context->pprx = (pprx * (!pfcrx)) << 7;
-	context->pfcrx = pfcrx;
-
-	in_mod = MLX4_SET_PORT_GENERAL << 8 | port;
-	err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
-		       MLX4_CMD_TIME_CLASS_B);
-
-	mlx4_free_cmd_mailbox(dev, mailbox);
-	return err;
-}
-
-int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
-			   u8 promisc)
-{
-	struct mlx4_cmd_mailbox *mailbox;
-	struct mlx4_set_port_rqp_calc_context *context;
-	int err;
-	u32 in_mod;
-	u32 m_promisc = (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) ?
-						MCAST_DIRECT : MCAST_DEFAULT;
-
-	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER  &&
-			dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER)
-		return 0;
-
-	mailbox = mlx4_alloc_cmd_mailbox(dev);
-	if (IS_ERR(mailbox))
-		return PTR_ERR(mailbox);
-	context = mailbox->buf;
-	memset(context, 0, sizeof *context);
-
-	context->base_qpn = cpu_to_be32(base_qpn);
-	context->n_mac = dev->caps.log_num_macs;
-	context->promisc = cpu_to_be32(promisc << SET_PORT_PROMISC_SHIFT |
-				       base_qpn);
-	context->mcast = cpu_to_be32(m_promisc << SET_PORT_MC_PROMISC_SHIFT |
-				     base_qpn);
-	context->intra_no_vlan = 0;
-	context->no_vlan = MLX4_NO_VLAN_IDX;
-	context->intra_vlan_miss = 0;
-	context->vlan_miss = MLX4_VLAN_MISS_IDX;
-
-	in_mod = MLX4_SET_PORT_RQP_CALC << 8 | port;
-	err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
-		       MLX4_CMD_TIME_CLASS_B);
-
+		       MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	return err;
 }
@@ -159,7 +83,8 @@ int mlx4_en_QUERY_PORT(struct mlx4_en_dev *mdev, u8 port)
 		return PTR_ERR(mailbox);
 	memset(mailbox->buf, 0, sizeof(*qport_context));
 	err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, port, 0,
-			   MLX4_CMD_QUERY_PORT, MLX4_CMD_TIME_CLASS_B);
+			   MLX4_CMD_QUERY_PORT, MLX4_CMD_TIME_CLASS_B,
+			   MLX4_CMD_WRAPPED);
 	if (err)
 		goto out;
 	qport_context = mailbox->buf;
@@ -204,7 +129,8 @@ int mlx4_en_DUMP_ETH_STATS(struct mlx4_en_dev *mdev, u8 port, u8 reset)
 		return PTR_ERR(mailbox);
 	memset(mailbox->buf, 0, sizeof(*mlx4_en_stats));
 	err = mlx4_cmd_box(mdev->dev, 0, mailbox->dma, in_mod, 0,
-			   MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B);
+			   MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B,
+			   MLX4_CMD_WRAPPED);
 	if (err)
 		goto out;
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_port.h b/drivers/net/ethernet/mellanox/mlx4/en_port.h
index 19eb244..6934fd7 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_port.h
+++ b/drivers/net/ethernet/mellanox/mlx4/en_port.h
@@ -39,49 +39,6 @@
 #define SET_PORT_PROMISC_SHIFT	31
 #define SET_PORT_MC_PROMISC_SHIFT	30
 
-enum {
-	MLX4_CMD_SET_VLAN_FLTR  = 0x47,
-	MLX4_CMD_SET_MCAST_FLTR = 0x48,
-	MLX4_CMD_DUMP_ETH_STATS = 0x49,
-};
-
-enum {
-	MCAST_DIRECT_ONLY       = 0,
-	MCAST_DIRECT            = 1,
-	MCAST_DEFAULT           = 2
-};
-
-struct mlx4_set_port_general_context {
-	u8 reserved[3];
-	u8 flags;
-	u16 reserved2;
-	__be16 mtu;
-	u8 pptx;
-	u8 pfctx;
-	u16 reserved3;
-	u8 pprx;
-	u8 pfcrx;
-	u16 reserved4;
-};
-
-struct mlx4_set_port_rqp_calc_context {
-	__be32 base_qpn;
-	u8 rererved;
-	u8 n_mac;
-	u8 n_vlan;
-	u8 n_prio;
-	u8 reserved2[3];
-	u8 mac_miss;
-	u8 intra_no_vlan;
-	u8 no_vlan;
-	u8 intra_vlan_miss;
-	u8 vlan_miss;
-	u8 reserved3[3];
-	u8 no_vlan_prio;
-	__be32 promisc;
-	__be32 mcast;
-};
-
 #define VLAN_FLTR_SIZE	128
 struct mlx4_set_vlan_fltr_mbox {
 	__be32 entry[VLAN_FLTR_SIZE];
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_resources.c b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
index 0dfb4ec..bcbc54c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_resources.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_resources.c
@@ -44,7 +44,7 @@ void mlx4_en_fill_qp_context(struct mlx4_en_priv *priv, int size, int stride,
 	struct mlx4_en_dev *mdev = priv->mdev;
 
 	memset(context, 0, sizeof *context);
-	context->flags = cpu_to_be32(7 << 16 | rss << 13);
+	context->flags = cpu_to_be32(7 << 16 | rss << MLX4_RSS_QPC_FLAG_OFFSET);
 	context->pd = cpu_to_be32(mdev->priv_pdn);
 	context->mtu_msgmax = 0xff;
 	if (!is_tx && !rss)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index b89c36d..630a7c1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -541,6 +541,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 	unsigned int length;
 	int polled = 0;
 	int ip_summed;
+	struct ethhdr *ethh;
+	u64 s_mac;
 
 	if (!priv->port_up)
 		return 0;
@@ -577,10 +579,24 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			goto next;
 		}
 
+		/* Get pointer to first fragment since we haven't skb yet and
+		 * cast it to ethhdr struct */
+		ethh = (struct ethhdr *)(page_address(skb_frags[0].page) +
+					 skb_frags[0].offset);
+		s_mac = mlx4_en_mac_to_u64(ethh->h_source);
+
+		/* If source MAC is equal to our own MAC and not performing
+		 * the selftest or flb disabled - drop the packet */
+		if (s_mac == priv->mac &&
+			(!(dev->features & NETIF_F_LOOPBACK) ||
+			 !priv->validate_loopback))
+			goto next;
+
 		/*
 		 * Packet is OK - process it.
 		 */
 		length = be32_to_cpu(cqe->byte_cnt);
+		length -= ring->fcs_del;
 		ring->bytes += length;
 		ring->packets++;
 
@@ -813,8 +829,11 @@ static int mlx4_en_config_rss_qp(struct mlx4_en_priv *priv, int qpn,
 	context->db_rec_addr = cpu_to_be64(ring->wqres.db.dma);
 
 	/* Cancel FCS removal if FW allows */
-	if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_FCS_KEEP)
+	if (mdev->dev->caps.flags & MLX4_DEV_CAP_FLAG_FCS_KEEP) {
 		context->param3 |= cpu_to_be32(1 << 29);
+		ring->fcs_del = ETH_FCS_LEN;
+	} else
+		ring->fcs_del = 0;
 
 	err = mlx4_qp_to_ready(mdev->dev, &ring->wqres.mtt, context, qp, state);
 	if (err) {
@@ -833,9 +852,10 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 	struct mlx4_en_dev *mdev = priv->mdev;
 	struct mlx4_en_rss_map *rss_map = &priv->rss_map;
 	struct mlx4_qp_context context;
-	struct mlx4_en_rss_context *rss_context;
+	struct mlx4_rss_context *rss_context;
 	void *ptr;
-	u8 rss_mask = 0x3f;
+	u8 rss_mask = (MLX4_RSS_IPV4 | MLX4_RSS_TCP_IPV4 | MLX4_RSS_IPV6 |
+			MLX4_RSS_TCP_IPV6);
 	int i, qpn;
 	int err = 0;
 	int good_qps = 0;
@@ -873,18 +893,21 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 	mlx4_en_fill_qp_context(priv, 0, 0, 0, 1, priv->base_qpn,
 				priv->rx_ring[0].cqn, &context);
 
-	ptr = ((void *) &context) + 0x3c;
+	ptr = ((void *) &context) + offsetof(struct mlx4_qp_context, pri_path)
+					+ MLX4_RSS_OFFSET_IN_QPC_PRI_PATH;
 	rss_context = ptr;
 	rss_context->base_qpn = cpu_to_be32(ilog2(priv->rx_ring_num) << 24 |
 					    (rss_map->base_qpn));
+	if (priv->mdev->profile.udp_rss) {
+		rss_mask |=  MLX4_RSS_UDP_IPV4 | MLX4_RSS_UDP_IPV6;
+		rss_context->base_qpn_udp = rss_context->default_qpn;
+	}
 	rss_context->default_qpn = cpu_to_be32(rss_map->base_qpn);
 	rss_context->flags = rss_mask;
-	rss_context->hash_fn = 1;
+	rss_context->hash_fn = MLX4_RSS_HASH_TOP;
 	for (i = 0; i < 10; i++)
 		rss_context->rss_key[i] = rsskey[i];
 
-	if (priv->mdev->profile.udp_rss)
-		rss_context->base_qpn_udp = rss_context->default_qpn;
 	err = mlx4_qp_to_ready(mdev->dev, &priv->res.mtt, &context,
 			       &rss_map->indir_qp, &rss_map->indir_state);
 	if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
index 9fdbcec..bf2e5d3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_selftest.c
@@ -43,7 +43,7 @@
 static int mlx4_en_test_registers(struct mlx4_en_priv *priv)
 {
 	return mlx4_cmd(priv->mdev->dev, 0, 0, 0, MLX4_CMD_HW_HEALTH_CHECK,
-			MLX4_CMD_TIME_CLASS_A);
+			MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 }
 
 static int mlx4_en_test_loopback_xmit(struct mlx4_en_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index d901b42..9ef9038 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -307,59 +307,60 @@ int mlx4_en_free_tx_buf(struct net_device *dev, struct mlx4_en_tx_ring *ring)
 	return cnt;
 }
 
-
 static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_cq *mcq = &cq->mcq;
 	struct mlx4_en_tx_ring *ring = &priv->tx_ring[cq->ring];
-	struct mlx4_cqe *cqe = cq->buf;
+	struct mlx4_cqe *cqe;
 	u16 index;
-	u16 new_index;
+	u16 new_index, ring_index;
 	u32 txbbs_skipped = 0;
-	u32 cq_last_sav;
-
-	/* index always points to the first TXBB of the last polled descriptor */
-	index = ring->cons & ring->size_mask;
-	new_index = be16_to_cpu(cqe->wqe_index) & ring->size_mask;
-	if (index == new_index)
-		return;
+	u32 cons_index = mcq->cons_index;
+	int size = cq->size;
+	u32 size_mask = ring->size_mask;
+	struct mlx4_cqe *buf = cq->buf;
 
 	if (!priv->port_up)
 		return;
 
-	/*
-	 * We use a two-stage loop:
-	 * - the first samples the HW-updated CQE
-	 * - the second frees TXBBs until the last sample
-	 * This lets us amortize CQE cache misses, while still polling the CQ
-	 * until is quiescent.
-	 */
-	cq_last_sav = mcq->cons_index;
-	do {
+	index = cons_index & size_mask;
+	cqe = &buf[index];
+	ring_index = ring->cons & size_mask;
+
+	/* Process all completed CQEs */
+	while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK,
+			cons_index & size)) {
+		/*
+		 * make sure we read the CQE after we read the
+		 * ownership bit
+		 */
+		rmb();
+
+		/* Skip over last polled CQE */
+		new_index = be16_to_cpu(cqe->wqe_index) & size_mask;
+
 		do {
-			/* Skip over last polled CQE */
-			index = (index + ring->last_nr_txbb) & ring->size_mask;
 			txbbs_skipped += ring->last_nr_txbb;
-
-			/* Poll next CQE */
+			ring_index = (ring_index + ring->last_nr_txbb) & size_mask;
+			/* free next descriptor */
 			ring->last_nr_txbb = mlx4_en_free_tx_desc(
-						priv, ring, index,
-						!!((ring->cons + txbbs_skipped) &
-						   ring->size));
-			++mcq->cons_index;
-
-		} while (index != new_index);
+					priv, ring, ring_index,
+					!!((ring->cons + txbbs_skipped) &
+							ring->size));
+		} while (ring_index != new_index);
+
+		++cons_index;
+		index = cons_index & size_mask;
+		cqe = &buf[index];
+	}
 
-		new_index = be16_to_cpu(cqe->wqe_index) & ring->size_mask;
-	} while (index != new_index);
-	AVG_PERF_COUNTER(priv->pstats.tx_coal_avg,
-			 (u32) (mcq->cons_index - cq_last_sav));
 
 	/*
 	 * To prevent CQ overflow we first update CQ consumer and only then
 	 * the ring consumer.
 	 */
+	mcq->cons_index = cons_index;
 	mlx4_cq_set_ci(mcq);
 	wmb();
 	ring->cons += txbbs_skipped;
@@ -565,7 +566,8 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, struct sk_buff *sk
 		inl->byte_count = cpu_to_be32(1 << 31 | (skb->len - spc));
 	}
 	tx_desc->ctrl.vlan_tag = cpu_to_be16(*vlan_tag);
-	tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_VLAN * !!(*vlan_tag);
+	tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_VLAN *
+		(!!vlan_tx_tag_present(skb));
 	tx_desc->ctrl.fence_size = (real_size / 16) & 0x3f;
 }
 
@@ -676,27 +678,25 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Prepare ctrl segement apart opcode+ownership, which depends on
 	 * whether LSO is used */
 	tx_desc->ctrl.vlan_tag = cpu_to_be16(vlan_tag);
-	tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_VLAN * !!vlan_tag;
+	tx_desc->ctrl.ins_vlan = MLX4_WQE_CTRL_INS_VLAN *
+		!!vlan_tx_tag_present(skb);
 	tx_desc->ctrl.fence_size = (real_size / 16) & 0x3f;
-	tx_desc->ctrl.srcrb_flags = cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE |
-						MLX4_WQE_CTRL_SOLICITED);
+	tx_desc->ctrl.srcrb_flags = priv->ctrl_flags;
 	if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
 		tx_desc->ctrl.srcrb_flags |= cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM |
 							 MLX4_WQE_CTRL_TCP_UDP_CSUM);
 		ring->tx_csum++;
 	}
 
-	if (unlikely(priv->validate_loopback)) {
-		/* Copy dst mac address to wqe */
-		skb_reset_mac_header(skb);
-		ethh = eth_hdr(skb);
-		if (ethh && ethh->h_dest) {
-			mac = mlx4_en_mac_to_u64(ethh->h_dest);
-			mac_h = (u32) ((mac & 0xffff00000000ULL) >> 16);
-			mac_l = (u32) (mac & 0xffffffff);
-			tx_desc->ctrl.srcrb_flags |= cpu_to_be32(mac_h);
-			tx_desc->ctrl.imm = cpu_to_be32(mac_l);
-		}
+	/* Copy dst mac address to wqe */
+	skb_reset_mac_header(skb);
+	ethh = eth_hdr(skb);
+	if (ethh && ethh->h_dest) {
+		mac = mlx4_en_mac_to_u64(ethh->h_dest);
+		mac_h = (u32) ((mac & 0xffff00000000ULL) >> 16);
+		mac_l = (u32) (mac & 0xffffffff);
+		tx_desc->ctrl.srcrb_flags |= cpu_to_be32(mac_h);
+		tx_desc->ctrl.imm = cpu_to_be32(mac_l);
 	}
 
 	/* Handle LSO (TSO) packets */
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index 24ee967..1e9b55e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -31,6 +31,7 @@
  * SOFTWARE.
  */
 
+#include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
 #include <linux/export.h>
@@ -52,30 +53,6 @@ enum {
 	MLX4_EQ_ENTRY_SIZE	= 0x20
 };
 
-/*
- * Must be packed because start is 64 bits but only aligned to 32 bits.
- */
-struct mlx4_eq_context {
-	__be32			flags;
-	u16			reserved1[3];
-	__be16			page_offset;
-	u8			log_eq_size;
-	u8			reserved2[4];
-	u8			eq_period;
-	u8			reserved3;
-	u8			eq_max_count;
-	u8			reserved4[3];
-	u8			intr;
-	u8			log_page_size;
-	u8			reserved5[2];
-	u8			mtt_base_addr_h;
-	__be32			mtt_base_addr_l;
-	u32			reserved6[2];
-	__be32			consumer_index;
-	__be32			producer_index;
-	u32			reserved7[4];
-};
-
 #define MLX4_EQ_STATUS_OK	   ( 0 << 28)
 #define MLX4_EQ_STATUS_WRITE_FAIL  (10 << 28)
 #define MLX4_EQ_OWNER_SW	   ( 0 << 24)
@@ -100,46 +77,9 @@ struct mlx4_eq_context {
 			       (1ull << MLX4_EVENT_TYPE_SRQ_CATAS_ERROR)    | \
 			       (1ull << MLX4_EVENT_TYPE_SRQ_QP_LAST_WQE)    | \
 			       (1ull << MLX4_EVENT_TYPE_SRQ_LIMIT)	    | \
-			       (1ull << MLX4_EVENT_TYPE_CMD))
-
-struct mlx4_eqe {
-	u8			reserved1;
-	u8			type;
-	u8			reserved2;
-	u8			subtype;
-	union {
-		u32		raw[6];
-		struct {
-			__be32	cqn;
-		} __packed comp;
-		struct {
-			u16	reserved1;
-			__be16	token;
-			u32	reserved2;
-			u8	reserved3[3];
-			u8	status;
-			__be64	out_param;
-		} __packed cmd;
-		struct {
-			__be32	qpn;
-		} __packed qp;
-		struct {
-			__be32	srqn;
-		} __packed srq;
-		struct {
-			__be32	cqn;
-			u32	reserved1;
-			u8	reserved2[3];
-			u8	syndrome;
-		} __packed cq_err;
-		struct {
-			u32	reserved1[2];
-			__be32	port;
-		} __packed port_change;
-	}			event;
-	u8			reserved3[3];
-	u8			owner;
-} __packed;
+			       (1ull << MLX4_EVENT_TYPE_CMD)		    | \
+			       (1ull << MLX4_EVENT_TYPE_COMM_CHANNEL)       | \
+			       (1ull << MLX4_EVENT_TYPE_FLR_EVENT))
 
 static void eq_set_ci(struct mlx4_eq *eq, int req_not)
 {
@@ -162,13 +102,144 @@ static struct mlx4_eqe *next_eqe_sw(struct mlx4_eq *eq)
 	return !!(eqe->owner & 0x80) ^ !!(eq->cons_index & eq->nent) ? NULL : eqe;
 }
 
+static struct mlx4_eqe *next_slave_event_eqe(struct mlx4_slave_event_eq *slave_eq)
+{
+	struct mlx4_eqe *eqe =
+		&slave_eq->event_eqe[slave_eq->cons & (SLAVE_EVENT_EQ_SIZE - 1)];
+	return (!!(eqe->owner & 0x80) ^
+		!!(slave_eq->cons & SLAVE_EVENT_EQ_SIZE)) ?
+		eqe : NULL;
+}
+
+void mlx4_gen_slave_eqe(struct work_struct *work)
+{
+	struct mlx4_mfunc_master_ctx *master =
+		container_of(work, struct mlx4_mfunc_master_ctx,
+			     slave_event_work);
+	struct mlx4_mfunc *mfunc =
+		container_of(master, struct mlx4_mfunc, master);
+	struct mlx4_priv *priv = container_of(mfunc, struct mlx4_priv, mfunc);
+	struct mlx4_dev *dev = &priv->dev;
+	struct mlx4_slave_event_eq *slave_eq = &mfunc->master.slave_eq;
+	struct mlx4_eqe *eqe;
+	u8 slave;
+	int i;
+
+	for (eqe = next_slave_event_eqe(slave_eq); eqe;
+	      eqe = next_slave_event_eqe(slave_eq)) {
+		slave = eqe->slave_id;
+
+		/* All active slaves need to receive the event */
+		if (slave == ALL_SLAVES) {
+			for (i = 0; i < dev->num_slaves; i++) {
+				if (i != dev->caps.function &&
+				    master->slave_state[i].active)
+					if (mlx4_GEN_EQE(dev, i, eqe))
+						mlx4_warn(dev, "Failed to "
+							  " generate event "
+							  "for slave %d\n", i);
+			}
+		} else {
+			if (mlx4_GEN_EQE(dev, slave, eqe))
+				mlx4_warn(dev, "Failed to generate event "
+					       "for slave %d\n", slave);
+		}
+		++slave_eq->cons;
+	}
+}
+
+
+static void slave_event(struct mlx4_dev *dev, u8 slave, struct mlx4_eqe *eqe)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_slave_event_eq *slave_eq = &priv->mfunc.master.slave_eq;
+	struct mlx4_eqe *s_eqe =
+		&slave_eq->event_eqe[slave_eq->prod & (SLAVE_EVENT_EQ_SIZE - 1)];
+
+	if ((!!(s_eqe->owner & 0x80)) ^
+	    (!!(slave_eq->prod & SLAVE_EVENT_EQ_SIZE))) {
+		mlx4_warn(dev, "Master failed to generate an EQE for slave: %d. "
+			  "No free EQE on slave events queue\n", slave);
+		return;
+	}
+
+	memcpy(s_eqe, eqe, sizeof(struct mlx4_eqe) - 1);
+	s_eqe->slave_id = slave;
+	/* ensure all information is written before setting the ownersip bit */
+	wmb();
+	s_eqe->owner = !!(slave_eq->prod & SLAVE_EVENT_EQ_SIZE) ? 0x0 : 0x80;
+	++slave_eq->prod;
+
+	queue_work(priv->mfunc.master.comm_wq,
+		   &priv->mfunc.master.slave_event_work);
+}
+
+static void mlx4_slave_event(struct mlx4_dev *dev, int slave,
+			     struct mlx4_eqe *eqe)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_slave_state *s_slave =
+		&priv->mfunc.master.slave_state[slave];
+
+	if (!s_slave->active) {
+		/*mlx4_warn(dev, "Trying to pass event to inactive slave\n");*/
+		return;
+	}
+
+	slave_event(dev, slave, eqe);
+}
+
+void mlx4_master_handle_slave_flr(struct work_struct *work)
+{
+	struct mlx4_mfunc_master_ctx *master =
+		container_of(work, struct mlx4_mfunc_master_ctx,
+			     slave_flr_event_work);
+	struct mlx4_mfunc *mfunc =
+		container_of(master, struct mlx4_mfunc, master);
+	struct mlx4_priv *priv =
+		container_of(mfunc, struct mlx4_priv, mfunc);
+	struct mlx4_dev *dev = &priv->dev;
+	struct mlx4_slave_state *slave_state = priv->mfunc.master.slave_state;
+	int i;
+	int err;
+
+	mlx4_dbg(dev, "mlx4_handle_slave_flr\n");
+
+	for (i = 0 ; i < dev->num_slaves; i++) {
+
+		if (MLX4_COMM_CMD_FLR == slave_state[i].last_cmd) {
+			mlx4_dbg(dev, "mlx4_handle_slave_flr: "
+				 "clean slave: %d\n", i);
+
+			mlx4_delete_all_resources_for_slave(dev, i);
+			/*return the slave to running mode*/
+			spin_lock(&priv->mfunc.master.slave_state_lock);
+			slave_state[i].last_cmd = MLX4_COMM_CMD_RESET;
+			slave_state[i].is_slave_going_down = 0;
+			spin_unlock(&priv->mfunc.master.slave_state_lock);
+			/*notify the FW:*/
+			err = mlx4_cmd(dev, 0, i, 0, MLX4_CMD_INFORM_FLR_DONE,
+				       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+			if (err)
+				mlx4_warn(dev, "Failed to notify FW on "
+					  "FLR done (slave:%d)\n", i);
+		}
+	}
+}
+
 static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 {
+	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_eqe *eqe;
 	int cqn;
 	int eqes_found = 0;
 	int set_ci = 0;
 	int port;
+	int slave = 0;
+	int ret;
+	u32 flr_slave;
+	u8 update_slave_state;
+	int i;
 
 	while ((eqe = next_eqe_sw(eq))) {
 		/*
@@ -191,14 +262,68 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 		case MLX4_EVENT_TYPE_PATH_MIG_FAILED:
 		case MLX4_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
 		case MLX4_EVENT_TYPE_WQ_ACCESS_ERROR:
-			mlx4_qp_event(dev, be32_to_cpu(eqe->event.qp.qpn) & 0xffffff,
-				      eqe->type);
+			mlx4_dbg(dev, "event %d arrived\n", eqe->type);
+			if (mlx4_is_master(dev)) {
+				/* forward only to slave owning the QP */
+				ret = mlx4_get_slave_from_resource_id(dev,
+						RES_QP,
+						be32_to_cpu(eqe->event.qp.qpn)
+						& 0xffffff, &slave);
+				if (ret && ret != -ENOENT) {
+					mlx4_dbg(dev, "QP event %02x(%02x) on "
+						 "EQ %d at index %u: could "
+						 "not get slave id (%d)\n",
+						 eqe->type, eqe->subtype,
+						 eq->eqn, eq->cons_index, ret);
+					break;
+				}
+
+				if (!ret && slave != dev->caps.function) {
+					mlx4_slave_event(dev, slave, eqe);
+					break;
+				}
+
+			}
+			mlx4_qp_event(dev, be32_to_cpu(eqe->event.qp.qpn) &
+				      0xffffff, eqe->type);
 			break;
 
 		case MLX4_EVENT_TYPE_SRQ_LIMIT:
+			mlx4_warn(dev, "%s: MLX4_EVENT_TYPE_SRQ_LIMIT\n",
+				  __func__);
 		case MLX4_EVENT_TYPE_SRQ_CATAS_ERROR:
-			mlx4_srq_event(dev, be32_to_cpu(eqe->event.srq.srqn) & 0xffffff,
-				      eqe->type);
+			if (mlx4_is_master(dev)) {
+				/* forward only to slave owning the SRQ */
+				ret = mlx4_get_slave_from_resource_id(dev,
+						RES_SRQ,
+						be32_to_cpu(eqe->event.srq.srqn)
+						& 0xffffff,
+						&slave);
+				if (ret && ret != -ENOENT) {
+					mlx4_warn(dev, "SRQ event %02x(%02x) "
+						  "on EQ %d at index %u: could"
+						  " not get slave id (%d)\n",
+						  eqe->type, eqe->subtype,
+						  eq->eqn, eq->cons_index, ret);
+					break;
+				}
+				mlx4_warn(dev, "%s: slave:%d, srq_no:0x%x,"
+					  " event: %02x(%02x)\n", __func__,
+					  slave,
+					  be32_to_cpu(eqe->event.srq.srqn),
+					  eqe->type, eqe->subtype);
+
+				if (!ret && slave != dev->caps.function) {
+					mlx4_warn(dev, "%s: sending event "
+						  "%02x(%02x) to slave:%d\n",
+						   __func__, eqe->type,
+						  eqe->subtype, slave);
+					mlx4_slave_event(dev, slave, eqe);
+					break;
+				}
+			}
+			mlx4_srq_event(dev, be32_to_cpu(eqe->event.srq.srqn) &
+				       0xffffff, eqe->type);
 			break;
 
 		case MLX4_EVENT_TYPE_CMD:
@@ -211,13 +336,35 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 		case MLX4_EVENT_TYPE_PORT_CHANGE:
 			port = be32_to_cpu(eqe->event.port_change.port) >> 28;
 			if (eqe->subtype == MLX4_PORT_CHANGE_SUBTYPE_DOWN) {
-				mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_DOWN,
+				mlx4_dispatch_event(dev,
+						    MLX4_DEV_EVENT_PORT_DOWN,
 						    port);
 				mlx4_priv(dev)->sense.do_sense_port[port] = 1;
+				if (mlx4_is_master(dev))
+					/*change the state of all slave's port
+					* to down:*/
+					for (i = 0; i < dev->num_slaves; i++) {
+						mlx4_dbg(dev, "%s: Sending "
+							 "MLX4_PORT_CHANGE_SUBTYPE_DOWN"
+							 " to slave: %d, port:%d\n",
+							 __func__, i, port);
+						if (i == dev->caps.function)
+							continue;
+						mlx4_slave_event(dev, i, eqe);
+					}
 			} else {
-				mlx4_dispatch_event(dev, MLX4_DEV_EVENT_PORT_UP,
+				mlx4_dispatch_event(dev,
+						    MLX4_DEV_EVENT_PORT_UP,
 						    port);
 				mlx4_priv(dev)->sense.do_sense_port[port] = 0;
+
+				if (mlx4_is_master(dev)) {
+					for (i = 0; i < dev->num_slaves; i++) {
+						if (i == dev->caps.function)
+							continue;
+						mlx4_slave_event(dev, i, eqe);
+					}
+				}
 			}
 			break;
 
@@ -226,7 +373,28 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 				  eqe->event.cq_err.syndrome == 1 ?
 				  "overrun" : "access violation",
 				  be32_to_cpu(eqe->event.cq_err.cqn) & 0xffffff);
-			mlx4_cq_event(dev, be32_to_cpu(eqe->event.cq_err.cqn),
+			if (mlx4_is_master(dev)) {
+				ret = mlx4_get_slave_from_resource_id(dev,
+					RES_CQ,
+					be32_to_cpu(eqe->event.cq_err.cqn)
+					& 0xffffff, &slave);
+				if (ret && ret != -ENOENT) {
+					mlx4_dbg(dev, "CQ event %02x(%02x) on "
+						 "EQ %d at index %u: could "
+						  "not get slave id (%d)\n",
+						  eqe->type, eqe->subtype,
+						  eq->eqn, eq->cons_index, ret);
+					break;
+				}
+
+				if (!ret && slave != dev->caps.function) {
+					mlx4_slave_event(dev, slave, eqe);
+					break;
+				}
+			}
+			mlx4_cq_event(dev,
+				      be32_to_cpu(eqe->event.cq_err.cqn)
+				      & 0xffffff,
 				      eqe->type);
 			break;
 
@@ -234,13 +402,60 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 			mlx4_warn(dev, "EQ overrun on EQN %d\n", eq->eqn);
 			break;
 
+		case MLX4_EVENT_TYPE_COMM_CHANNEL:
+			if (!mlx4_is_master(dev)) {
+				mlx4_warn(dev, "Received comm channel event "
+					       "for non master device\n");
+				break;
+			}
+			memcpy(&priv->mfunc.master.comm_arm_bit_vector,
+			       eqe->event.comm_channel_arm.bit_vec,
+			       sizeof eqe->event.comm_channel_arm.bit_vec);
+			queue_work(priv->mfunc.master.comm_wq,
+				   &priv->mfunc.master.comm_work);
+			break;
+
+		case MLX4_EVENT_TYPE_FLR_EVENT:
+			flr_slave = be32_to_cpu(eqe->event.flr_event.slave_id);
+			if (!mlx4_is_master(dev)) {
+				mlx4_warn(dev, "Non-master function received"
+					       "FLR event\n");
+				break;
+			}
+
+			mlx4_dbg(dev, "FLR event for slave: %d\n", flr_slave);
+
+			if (flr_slave > dev->num_slaves) {
+				mlx4_warn(dev,
+					  "Got FLR for unknown function: %d\n",
+					  flr_slave);
+				update_slave_state = 0;
+			} else
+				update_slave_state = 1;
+
+			spin_lock(&priv->mfunc.master.slave_state_lock);
+			if (update_slave_state) {
+				priv->mfunc.master.slave_state[flr_slave].active = false;
+				priv->mfunc.master.slave_state[flr_slave].last_cmd = MLX4_COMM_CMD_FLR;
+				priv->mfunc.master.slave_state[flr_slave].is_slave_going_down = 1;
+			}
+			spin_unlock(&priv->mfunc.master.slave_state_lock);
+			queue_work(priv->mfunc.master.comm_wq,
+				   &priv->mfunc.master.slave_flr_event_work);
+			break;
 		case MLX4_EVENT_TYPE_EEC_CATAS_ERROR:
 		case MLX4_EVENT_TYPE_ECC_DETECT:
 		default:
-			mlx4_warn(dev, "Unhandled event %02x(%02x) on EQ %d at index %u\n",
-				  eqe->type, eqe->subtype, eq->eqn, eq->cons_index);
+			mlx4_warn(dev, "Unhandled event %02x(%02x) on EQ %d at "
+				  "index %u. owner=%x, nent=0x%x, slave=%x, "
+				  "ownership=%s\n",
+				  eqe->type, eqe->subtype, eq->eqn,
+				  eq->cons_index, eqe->owner, eq->nent,
+				  eqe->slave_id,
+				  !!(eqe->owner & 0x80) ^
+				  !!(eq->cons_index & eq->nent) ? "HW" : "SW");
 			break;
-		}
+		};
 
 		++eq->cons_index;
 		eqes_found = 1;
@@ -290,25 +505,58 @@ static irqreturn_t mlx4_msi_x_interrupt(int irq, void *eq_ptr)
 	return IRQ_HANDLED;
 }
 
+int mlx4_MAP_EQ_wrapper(struct mlx4_dev *dev, int slave,
+			struct mlx4_vhcr *vhcr,
+			struct mlx4_cmd_mailbox *inbox,
+			struct mlx4_cmd_mailbox *outbox,
+			struct mlx4_cmd_info *cmd)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_slave_event_eq_info *event_eq =
+		&priv->mfunc.master.slave_state[slave].event_eq;
+	u32 in_modifier = vhcr->in_modifier;
+	u32 eqn = in_modifier & 0x1FF;
+	u64 in_param =  vhcr->in_param;
+	int err = 0;
+
+	if (slave == dev->caps.function)
+		err = mlx4_cmd(dev, in_param, (in_modifier & 0x80000000) | eqn,
+			       0, MLX4_CMD_MAP_EQ, MLX4_CMD_TIME_CLASS_B,
+			       MLX4_CMD_NATIVE);
+	if (!err) {
+		if (in_modifier >> 31) {
+			/* unmap */
+			event_eq->event_type &= ~in_param;
+		} else {
+			event_eq->eqn = eqn;
+			event_eq->event_type = in_param;
+		}
+	}
+	return err;
+}
+
 static int mlx4_MAP_EQ(struct mlx4_dev *dev, u64 event_mask, int unmap,
 			int eq_num)
 {
 	return mlx4_cmd(dev, event_mask, (unmap << 31) | eq_num,
-			0, MLX4_CMD_MAP_EQ, MLX4_CMD_TIME_CLASS_B);
+			0, MLX4_CMD_MAP_EQ, MLX4_CMD_TIME_CLASS_B,
+			MLX4_CMD_WRAPPED);
 }
 
 static int mlx4_SW2HW_EQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
 			 int eq_num)
 {
-	return mlx4_cmd(dev, mailbox->dma, eq_num, 0, MLX4_CMD_SW2HW_EQ,
-			MLX4_CMD_TIME_CLASS_A);
+	return mlx4_cmd(dev, mailbox->dma | dev->caps.function, eq_num, 0,
+			MLX4_CMD_SW2HW_EQ, MLX4_CMD_TIME_CLASS_A,
+			MLX4_CMD_WRAPPED);
 }
 
 static int mlx4_HW2SW_EQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
 			 int eq_num)
 {
-	return mlx4_cmd_box(dev, 0, mailbox->dma, eq_num, 0, MLX4_CMD_HW2SW_EQ,
-			    MLX4_CMD_TIME_CLASS_A);
+	return mlx4_cmd_box(dev, dev->caps.function, mailbox->dma, eq_num,
+			    0, MLX4_CMD_HW2SW_EQ, MLX4_CMD_TIME_CLASS_A,
+			    MLX4_CMD_WRAPPED);
 }
 
 static int mlx4_num_eq_uar(struct mlx4_dev *dev)
@@ -585,14 +833,16 @@ int mlx4_init_eq_table(struct mlx4_dev *dev)
 	for (i = 0; i < mlx4_num_eq_uar(dev); ++i)
 		priv->eq_table.uar_map[i] = NULL;
 
-	err = mlx4_map_clr_int(dev);
-	if (err)
-		goto err_out_bitmap;
+	if (!mlx4_is_slave(dev)) {
+		err = mlx4_map_clr_int(dev);
+		if (err)
+			goto err_out_bitmap;
 
-	priv->eq_table.clr_mask =
-		swab32(1 << (priv->eq_table.inta_pin & 31));
-	priv->eq_table.clr_int  = priv->clr_base +
-		(priv->eq_table.inta_pin < 32 ? 4 : 0);
+		priv->eq_table.clr_mask =
+			swab32(1 << (priv->eq_table.inta_pin & 31));
+		priv->eq_table.clr_int  = priv->clr_base +
+			(priv->eq_table.inta_pin < 32 ? 4 : 0);
+	}
 
 	priv->eq_table.irq_names =
 		kmalloc(MLX4_IRQNAME_SIZE * (dev->caps.num_comp_vectors + 1 +
@@ -700,7 +950,8 @@ err_out_unmap:
 		mlx4_free_eq(dev, &priv->eq_table.eq[i]);
 		--i;
 	}
-	mlx4_unmap_clr_int(dev);
+	if (!mlx4_is_slave(dev))
+		mlx4_unmap_clr_int(dev);
 	mlx4_free_irqs(dev);
 
 err_out_bitmap:
@@ -725,7 +976,8 @@ void mlx4_cleanup_eq_table(struct mlx4_dev *dev)
 	for (i = 0; i < dev->caps.num_comp_vectors + dev->caps.comp_pool + 1; ++i)
 		mlx4_free_eq(dev, &priv->eq_table.eq[i]);
 
-	mlx4_unmap_clr_int(dev);
+	if (!mlx4_is_slave(dev))
+		mlx4_unmap_clr_int(dev);
 
 	for (i = 0; i < mlx4_num_eq_uar(dev); ++i)
 		if (priv->eq_table.uar_map[i])
@@ -748,7 +1000,7 @@ int mlx4_test_interrupts(struct mlx4_dev *dev)
 
 	err = mlx4_NOP(dev);
 	/* When not in MSI_X, there is only one irq to check */
-	if (!(dev->flags & MLX4_FLAG_MSI_X))
+	if (!(dev->flags & MLX4_FLAG_MSI_X) || mlx4_is_slave(dev))
 		return err;
 
 	/* A loop over all completion vectors, for each vector we will check
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 435ca6e..f03b54e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -32,6 +32,7 @@
  * SOFTWARE.
  */
 
+#include <linux/etherdevice.h>
 #include <linux/mlx4/cmd.h>
 #include <linux/module.h>
 #include <linux/cache.h>
@@ -139,12 +140,185 @@ int mlx4_MOD_STAT_CFG(struct mlx4_dev *dev, struct mlx4_mod_stat_cfg *cfg)
 	MLX4_PUT(inbox, cfg->log_pg_sz_m, MOD_STAT_CFG_PG_SZ_M_OFFSET);
 
 	err = mlx4_cmd(dev, mailbox->dma, 0, 0, MLX4_CMD_MOD_STAT_CFG,
-			MLX4_CMD_TIME_CLASS_A);
+			MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	return err;
 }
 
+int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
+				struct mlx4_vhcr *vhcr,
+				struct mlx4_cmd_mailbox *inbox,
+				struct mlx4_cmd_mailbox *outbox,
+				struct mlx4_cmd_info *cmd)
+{
+	u8	field;
+	u32	size;
+	int	err = 0;
+
+#define QUERY_FUNC_CAP_FLAGS_OFFSET		0x0
+#define QUERY_FUNC_CAP_NUM_PORTS_OFFSET		0x1
+#define QUERY_FUNC_CAP_FUNCTION_OFFSET		0x3
+#define QUERY_FUNC_CAP_PF_BHVR_OFFSET		0x4
+#define QUERY_FUNC_CAP_QP_QUOTA_OFFSET		0x10
+#define QUERY_FUNC_CAP_CQ_QUOTA_OFFSET		0x14
+#define QUERY_FUNC_CAP_SRQ_QUOTA_OFFSET		0x18
+#define QUERY_FUNC_CAP_MPT_QUOTA_OFFSET		0x20
+#define QUERY_FUNC_CAP_MTT_QUOTA_OFFSET		0x24
+#define QUERY_FUNC_CAP_MCG_QUOTA_OFFSET		0x28
+#define QUERY_FUNC_CAP_MAX_EQ_OFFSET		0x2c
+#define QUERY_FUNC_CAP_RESERVED_EQ_OFFSET	0X30
+
+#define QUERY_FUNC_CAP_PHYS_PORT_OFFSET		0x3
+#define QUERY_FUNC_CAP_ETH_PROPS_OFFSET		0xc
+
+	if (vhcr->op_modifier == 1) {
+		field = vhcr->in_modifier;
+		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_PHYS_PORT_OFFSET);
+
+		field = 0; /* ensure fvl bit is not set */
+		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_ETH_PROPS_OFFSET);
+	} else if (vhcr->op_modifier == 0) {
+		field = 1 << 7; /* enable only ethernet interface */
+		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FLAGS_OFFSET);
+
+		field = slave;
+		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FUNCTION_OFFSET);
+
+		field = dev->caps.num_ports;
+		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_NUM_PORTS_OFFSET);
+
+		size = 0; /* no PF behavious is set for now */
+		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_PF_BHVR_OFFSET);
+
+		size = dev->caps.num_qps;
+		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_QP_QUOTA_OFFSET);
+
+		size = dev->caps.num_srqs;
+		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_SRQ_QUOTA_OFFSET);
+
+		size = dev->caps.num_cqs;
+		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_CQ_QUOTA_OFFSET);
+
+		size = dev->caps.num_eqs;
+		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MAX_EQ_OFFSET);
+
+		size = dev->caps.reserved_eqs;
+		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_RESERVED_EQ_OFFSET);
+
+		size = dev->caps.num_mpts;
+		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MPT_QUOTA_OFFSET);
+
+		size = dev->caps.num_mtts;
+		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MTT_QUOTA_OFFSET);
+
+		size = dev->caps.num_mgms + dev->caps.num_amgms;
+		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET);
+
+	} else
+		err = -EINVAL;
+
+	return err;
+}
+
+int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, struct mlx4_func_cap *func_cap)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	u32			*outbox;
+	u8			field;
+	u32			size;
+	int			i;
+	int			err = 0;
+
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+
+	err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0, MLX4_CMD_QUERY_FUNC_CAP,
+			   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+	if (err)
+		goto out;
+
+	outbox = mailbox->buf;
+
+	MLX4_GET(field, outbox, QUERY_FUNC_CAP_FLAGS_OFFSET);
+	if (!(field & (1 << 7))) {
+		mlx4_err(dev, "The host doesn't support eth interface\n");
+		err = -EPROTONOSUPPORT;
+		goto out;
+	}
+
+	MLX4_GET(field, outbox, QUERY_FUNC_CAP_FUNCTION_OFFSET);
+	func_cap->function = field;
+
+	MLX4_GET(field, outbox, QUERY_FUNC_CAP_NUM_PORTS_OFFSET);
+	func_cap->num_ports = field;
+
+	MLX4_GET(size, outbox, QUERY_FUNC_CAP_PF_BHVR_OFFSET);
+	func_cap->pf_context_behaviour = size;
+
+	MLX4_GET(size, outbox, QUERY_FUNC_CAP_QP_QUOTA_OFFSET);
+	func_cap->qp_quota = size & 0xFFFFFF;
+
+	MLX4_GET(size, outbox, QUERY_FUNC_CAP_SRQ_QUOTA_OFFSET);
+	func_cap->srq_quota = size & 0xFFFFFF;
+
+	MLX4_GET(size, outbox, QUERY_FUNC_CAP_CQ_QUOTA_OFFSET);
+	func_cap->cq_quota = size & 0xFFFFFF;
+
+	MLX4_GET(size, outbox, QUERY_FUNC_CAP_MAX_EQ_OFFSET);
+	func_cap->max_eq = size & 0xFFFFFF;
+
+	MLX4_GET(size, outbox, QUERY_FUNC_CAP_RESERVED_EQ_OFFSET);
+	func_cap->reserved_eq = size & 0xFFFFFF;
+
+	MLX4_GET(size, outbox, QUERY_FUNC_CAP_MPT_QUOTA_OFFSET);
+	func_cap->mpt_quota = size & 0xFFFFFF;
+
+	MLX4_GET(size, outbox, QUERY_FUNC_CAP_MTT_QUOTA_OFFSET);
+	func_cap->mtt_quota = size & 0xFFFFFF;
+
+	MLX4_GET(size, outbox, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET);
+	func_cap->mcg_quota = size & 0xFFFFFF;
+
+	for (i = 1; i <= func_cap->num_ports; ++i) {
+		err = mlx4_cmd_box(dev, 0, mailbox->dma, i, 1,
+				   MLX4_CMD_QUERY_FUNC_CAP,
+				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		if (err)
+			goto out;
+
+		MLX4_GET(field, outbox, QUERY_FUNC_CAP_ETH_PROPS_OFFSET);
+		if (field & (1 << 7)) {
+			mlx4_err(dev, "VLAN is enforced on this port\n");
+			err = -EPROTONOSUPPORT;
+			goto out;
+		}
+
+		if (field & (1 << 6)) {
+			mlx4_err(dev, "Force mac is enabled on this port\n");
+			err = -EPROTONOSUPPORT;
+			goto out;
+		}
+
+		MLX4_GET(field, outbox, QUERY_FUNC_CAP_PHYS_PORT_OFFSET);
+		func_cap->physical_port[i] = field;
+	}
+
+	/* All other resources are allocated by the master, but we still report
+	 * 'num' and 'reserved' capabilities as follows:
+	 * - num remains the maximum resource index
+	 * - 'num - reserved' is the total available objects of a resource, but
+	 *   resource indices may be less than 'reserved'
+	 * TODO: set per-resource quotas */
+
+out:
+	mlx4_free_cmd_mailbox(dev, mailbox);
+
+	return err;
+}
+
 int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 {
 	struct mlx4_cmd_mailbox *mailbox;
@@ -229,7 +403,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	outbox = mailbox->buf;
 
 	err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0, MLX4_CMD_QUERY_DEV_CAP,
-			   MLX4_CMD_TIME_CLASS_A);
+			   MLX4_CMD_TIME_CLASS_A, !mlx4_is_slave(dev));
 	if (err)
 		goto out;
 
@@ -396,7 +570,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 
 		for (i = 1; i <= dev_cap->num_ports; ++i) {
 			err = mlx4_cmd_box(dev, 0, mailbox->dma, i, 0, MLX4_CMD_QUERY_PORT,
-					   MLX4_CMD_TIME_CLASS_B);
+					   MLX4_CMD_TIME_CLASS_B,
+					   !mlx4_is_slave(dev));
 			if (err)
 				goto out;
 
@@ -470,6 +645,54 @@ out:
 	return err;
 }
 
+int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave,
+			    struct mlx4_vhcr *vhcr,
+			    struct mlx4_cmd_mailbox *inbox,
+			    struct mlx4_cmd_mailbox *outbox,
+			    struct mlx4_cmd_info *cmd)
+{
+	u64 def_mac;
+	u8 port_type;
+	int err;
+
+	err = mlx4_cmd_box(dev, 0, outbox->dma, vhcr->in_modifier, 0,
+			   MLX4_CMD_QUERY_PORT, MLX4_CMD_TIME_CLASS_B,
+			   MLX4_CMD_NATIVE);
+
+	if (!err && dev->caps.function != slave) {
+		/* set slave default_mac address */
+		MLX4_GET(def_mac, outbox->buf, QUERY_PORT_MAC_OFFSET);
+		def_mac += slave << 8;
+		MLX4_PUT(outbox->buf, def_mac, QUERY_PORT_MAC_OFFSET);
+
+		/* get port type - currently only eth is enabled */
+		MLX4_GET(port_type, outbox->buf,
+			 QUERY_PORT_SUPPORTED_TYPE_OFFSET);
+
+		/* disable ib */
+		port_type &= 0xFE;
+
+		/* check eth is enabled for this port */
+		if (!(port_type & 2))
+			mlx4_dbg(dev, "QUERY PORT: eth not supported by host");
+
+		MLX4_PUT(outbox->buf, port_type,
+			 QUERY_PORT_SUPPORTED_TYPE_OFFSET);
+	}
+
+	return err;
+}
+
+static int mlx4_QUERY_PORT(struct mlx4_dev *dev, void *ptr, u8 port)
+{
+	struct mlx4_cmd_mailbox *outbox = ptr;
+
+	return mlx4_cmd_box(dev, 0, outbox->dma, port, 0,
+			    MLX4_CMD_QUERY_PORT, MLX4_CMD_TIME_CLASS_B,
+			    MLX4_CMD_WRAPPED);
+}
+EXPORT_SYMBOL_GPL(mlx4_QUERY_PORT);
+
 int mlx4_map_cmd(struct mlx4_dev *dev, u16 op, struct mlx4_icm *icm, u64 virt)
 {
 	struct mlx4_cmd_mailbox *mailbox;
@@ -519,7 +742,8 @@ int mlx4_map_cmd(struct mlx4_dev *dev, u16 op, struct mlx4_icm *icm, u64 virt)
 
 			if (++nent == MLX4_MAILBOX_SIZE / 16) {
 				err = mlx4_cmd(dev, mailbox->dma, nent, 0, op,
-						MLX4_CMD_TIME_CLASS_B);
+						MLX4_CMD_TIME_CLASS_B,
+						MLX4_CMD_NATIVE);
 				if (err)
 					goto out;
 				nent = 0;
@@ -528,7 +752,8 @@ int mlx4_map_cmd(struct mlx4_dev *dev, u16 op, struct mlx4_icm *icm, u64 virt)
 	}
 
 	if (nent)
-		err = mlx4_cmd(dev, mailbox->dma, nent, 0, op, MLX4_CMD_TIME_CLASS_B);
+		err = mlx4_cmd(dev, mailbox->dma, nent, 0, op,
+			       MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
 	if (err)
 		goto out;
 
@@ -557,13 +782,15 @@ int mlx4_MAP_FA(struct mlx4_dev *dev, struct mlx4_icm *icm)
 
 int mlx4_UNMAP_FA(struct mlx4_dev *dev)
 {
-	return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_UNMAP_FA, MLX4_CMD_TIME_CLASS_B);
+	return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_UNMAP_FA,
+			MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
 }
 
 
 int mlx4_RUN_FW(struct mlx4_dev *dev)
 {
-	return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_RUN_FW, MLX4_CMD_TIME_CLASS_A);
+	return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_RUN_FW,
+			MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
 }
 
 int mlx4_QUERY_FW(struct mlx4_dev *dev)
@@ -579,6 +806,7 @@ int mlx4_QUERY_FW(struct mlx4_dev *dev)
 
 #define QUERY_FW_OUT_SIZE             0x100
 #define QUERY_FW_VER_OFFSET            0x00
+#define QUERY_FW_PPF_ID		       0x09
 #define QUERY_FW_CMD_IF_REV_OFFSET     0x0a
 #define QUERY_FW_MAX_CMD_OFFSET        0x0f
 #define QUERY_FW_ERR_START_OFFSET      0x30
@@ -589,13 +817,16 @@ int mlx4_QUERY_FW(struct mlx4_dev *dev)
 #define QUERY_FW_CLR_INT_BASE_OFFSET   0x20
 #define QUERY_FW_CLR_INT_BAR_OFFSET    0x28
 
+#define QUERY_FW_COMM_BASE_OFFSET      0x40
+#define QUERY_FW_COMM_BAR_OFFSET       0x48
+
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
 		return PTR_ERR(mailbox);
 	outbox = mailbox->buf;
 
 	err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0, MLX4_CMD_QUERY_FW,
-			    MLX4_CMD_TIME_CLASS_A);
+			    MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
 	if (err)
 		goto out;
 
@@ -608,6 +839,9 @@ int mlx4_QUERY_FW(struct mlx4_dev *dev)
 		((fw_ver & 0xffff0000ull) >> 16) |
 		((fw_ver & 0x0000ffffull) << 16);
 
+	MLX4_GET(lg, outbox, QUERY_FW_PPF_ID);
+	dev->caps.function = lg;
+
 	MLX4_GET(cmd_if_rev, outbox, QUERY_FW_CMD_IF_REV_OFFSET);
 	if (cmd_if_rev < MLX4_COMMAND_INTERFACE_MIN_REV ||
 	    cmd_if_rev > MLX4_COMMAND_INTERFACE_MAX_REV) {
@@ -649,6 +883,11 @@ int mlx4_QUERY_FW(struct mlx4_dev *dev)
 	MLX4_GET(fw->clr_int_bar,  outbox, QUERY_FW_CLR_INT_BAR_OFFSET);
 	fw->clr_int_bar = (fw->clr_int_bar >> 6) * 2;
 
+	MLX4_GET(fw->comm_base, outbox, QUERY_FW_COMM_BASE_OFFSET);
+	MLX4_GET(fw->comm_bar,  outbox, QUERY_FW_COMM_BAR_OFFSET);
+	fw->comm_bar = (fw->comm_bar >> 6) * 2;
+	mlx4_dbg(dev, "Communication vector bar:%d offset:0x%llx\n",
+		 fw->comm_bar, fw->comm_base);
 	mlx4_dbg(dev, "FW size %d KB\n", fw->fw_pages >> 2);
 
 	/*
@@ -711,7 +950,7 @@ int mlx4_QUERY_ADAPTER(struct mlx4_dev *dev, struct mlx4_adapter *adapter)
 	outbox = mailbox->buf;
 
 	err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0, MLX4_CMD_QUERY_ADAPTER,
-			   MLX4_CMD_TIME_CLASS_A);
+			   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
 	if (err)
 		goto out;
 
@@ -743,6 +982,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 #define	 INIT_HCA_LOG_SRQ_OFFSET	 (INIT_HCA_QPC_OFFSET + 0x2f)
 #define	 INIT_HCA_CQC_BASE_OFFSET	 (INIT_HCA_QPC_OFFSET + 0x30)
 #define	 INIT_HCA_LOG_CQ_OFFSET		 (INIT_HCA_QPC_OFFSET + 0x37)
+#define	 INIT_HCA_EQE_CQE_OFFSETS	 (INIT_HCA_QPC_OFFSET + 0x38)
 #define	 INIT_HCA_ALTC_BASE_OFFSET	 (INIT_HCA_QPC_OFFSET + 0x40)
 #define	 INIT_HCA_AUXC_BASE_OFFSET	 (INIT_HCA_QPC_OFFSET + 0x50)
 #define	 INIT_HCA_EQC_BASE_OFFSET	 (INIT_HCA_QPC_OFFSET + 0x60)
@@ -831,10 +1071,11 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 
 	/* UAR attributes */
 
-	MLX4_PUT(inbox, (u8) (PAGE_SHIFT - 12), INIT_HCA_UAR_PAGE_SZ_OFFSET);
+	MLX4_PUT(inbox, param->uar_page_sz,	INIT_HCA_UAR_PAGE_SZ_OFFSET);
 	MLX4_PUT(inbox, param->log_uar_sz,      INIT_HCA_LOG_UAR_SZ_OFFSET);
 
-	err = mlx4_cmd(dev, mailbox->dma, 0, 0, MLX4_CMD_INIT_HCA, 10000);
+	err = mlx4_cmd(dev, mailbox->dma, 0, 0, MLX4_CMD_INIT_HCA, 10000,
+		       MLX4_CMD_NATIVE);
 
 	if (err)
 		mlx4_err(dev, "INIT_HCA returns %d\n", err);
@@ -843,6 +1084,101 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 	return err;
 }
 
+int mlx4_QUERY_HCA(struct mlx4_dev *dev,
+		   struct mlx4_init_hca_param *param)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	__be32 *outbox;
+	int err;
+
+#define QUERY_HCA_GLOBAL_CAPS_OFFSET	0x04
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+	outbox = mailbox->buf;
+
+	err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0,
+			   MLX4_CMD_QUERY_HCA,
+			   MLX4_CMD_TIME_CLASS_B,
+			   !mlx4_is_slave(dev));
+	if (err)
+		goto out;
+
+	MLX4_GET(param->global_caps, outbox, QUERY_HCA_GLOBAL_CAPS_OFFSET);
+
+	/* QPC/EEC/CQC/EQC/RDMARC attributes */
+
+	MLX4_GET(param->qpc_base,      outbox, INIT_HCA_QPC_BASE_OFFSET);
+	MLX4_GET(param->log_num_qps,   outbox, INIT_HCA_LOG_QP_OFFSET);
+	MLX4_GET(param->srqc_base,     outbox, INIT_HCA_SRQC_BASE_OFFSET);
+	MLX4_GET(param->log_num_srqs,  outbox, INIT_HCA_LOG_SRQ_OFFSET);
+	MLX4_GET(param->cqc_base,      outbox, INIT_HCA_CQC_BASE_OFFSET);
+	MLX4_GET(param->log_num_cqs,   outbox, INIT_HCA_LOG_CQ_OFFSET);
+	MLX4_GET(param->altc_base,     outbox, INIT_HCA_ALTC_BASE_OFFSET);
+	MLX4_GET(param->auxc_base,     outbox, INIT_HCA_AUXC_BASE_OFFSET);
+	MLX4_GET(param->eqc_base,      outbox, INIT_HCA_EQC_BASE_OFFSET);
+	MLX4_GET(param->log_num_eqs,   outbox, INIT_HCA_LOG_EQ_OFFSET);
+	MLX4_GET(param->rdmarc_base,   outbox, INIT_HCA_RDMARC_BASE_OFFSET);
+	MLX4_GET(param->log_rd_per_qp, outbox, INIT_HCA_LOG_RD_OFFSET);
+
+	/* multicast attributes */
+
+	MLX4_GET(param->mc_base,         outbox, INIT_HCA_MC_BASE_OFFSET);
+	MLX4_GET(param->log_mc_entry_sz, outbox,
+		 INIT_HCA_LOG_MC_ENTRY_SZ_OFFSET);
+	MLX4_GET(param->log_mc_hash_sz,  outbox,
+		 INIT_HCA_LOG_MC_HASH_SZ_OFFSET);
+	MLX4_GET(param->log_mc_table_sz, outbox,
+		 INIT_HCA_LOG_MC_TABLE_SZ_OFFSET);
+
+	/* TPT attributes */
+
+	MLX4_GET(param->dmpt_base,  outbox, INIT_HCA_DMPT_BASE_OFFSET);
+	MLX4_GET(param->log_mpt_sz, outbox, INIT_HCA_LOG_MPT_SZ_OFFSET);
+	MLX4_GET(param->mtt_base,   outbox, INIT_HCA_MTT_BASE_OFFSET);
+	MLX4_GET(param->cmpt_base,  outbox, INIT_HCA_CMPT_BASE_OFFSET);
+
+	/* UAR attributes */
+
+	MLX4_GET(param->uar_page_sz, outbox, INIT_HCA_UAR_PAGE_SZ_OFFSET);
+	MLX4_GET(param->log_uar_sz, outbox, INIT_HCA_LOG_UAR_SZ_OFFSET);
+
+out:
+	mlx4_free_cmd_mailbox(dev, mailbox);
+
+	return err;
+}
+
+int mlx4_INIT_PORT_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int port = vhcr->in_modifier;
+	int err;
+
+	if (priv->mfunc.master.slave_state[slave].init_port_mask & (1 << port))
+		return 0;
+
+	if (dev->caps.port_mask[port] == MLX4_PORT_TYPE_IB)
+		return -ENODEV;
+
+	/* Enable port only if it was previously disabled */
+	if (!priv->mfunc.master.init_port_ref[port]) {
+		err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_INIT_PORT,
+			       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
+		if (err)
+			return err;
+		priv->mfunc.master.slave_state[slave].init_port_mask |=
+			(1 << port);
+	}
+	++priv->mfunc.master.init_port_ref[port];
+	return 0;
+}
+
 int mlx4_INIT_PORT(struct mlx4_dev *dev, int port)
 {
 	struct mlx4_cmd_mailbox *mailbox;
@@ -886,33 +1222,62 @@ int mlx4_INIT_PORT(struct mlx4_dev *dev, int port)
 		MLX4_PUT(inbox, field, INIT_PORT_MAX_PKEY_OFFSET);
 
 		err = mlx4_cmd(dev, mailbox->dma, port, 0, MLX4_CMD_INIT_PORT,
-			       MLX4_CMD_TIME_CLASS_A);
+			       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
 
 		mlx4_free_cmd_mailbox(dev, mailbox);
 	} else
 		err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_INIT_PORT,
-			       MLX4_CMD_TIME_CLASS_A);
+			       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 
 	return err;
 }
 EXPORT_SYMBOL_GPL(mlx4_INIT_PORT);
 
+int mlx4_CLOSE_PORT_wrapper(struct mlx4_dev *dev, int slave,
+			    struct mlx4_vhcr *vhcr,
+			    struct mlx4_cmd_mailbox *inbox,
+			    struct mlx4_cmd_mailbox *outbox,
+			    struct mlx4_cmd_info *cmd)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int port = vhcr->in_modifier;
+	int err;
+
+	if (!(priv->mfunc.master.slave_state[slave].init_port_mask &
+	    (1 << port)))
+		return 0;
+
+	if (dev->caps.port_mask[port] == MLX4_PORT_TYPE_IB)
+		return -ENODEV;
+	if (priv->mfunc.master.init_port_ref[port] == 1) {
+		err = mlx4_cmd(dev, 0, port, 0, MLX4_CMD_CLOSE_PORT, 1000,
+			       MLX4_CMD_NATIVE);
+		if (err)
+			return err;
+	}
+	priv->mfunc.master.slave_state[slave].init_port_mask &= ~(1 << port);
+	--priv->mfunc.master.init_port_ref[port];
+	return 0;
+}
+
 int mlx4_CLOSE_PORT(struct mlx4_dev *dev, int port)
 {
-	return mlx4_cmd(dev, 0, port, 0, MLX4_CMD_CLOSE_PORT, 1000);
+	return mlx4_cmd(dev, 0, port, 0, MLX4_CMD_CLOSE_PORT, 1000,
+			MLX4_CMD_WRAPPED);
 }
 EXPORT_SYMBOL_GPL(mlx4_CLOSE_PORT);
 
 int mlx4_CLOSE_HCA(struct mlx4_dev *dev, int panic)
 {
-	return mlx4_cmd(dev, 0, 0, panic, MLX4_CMD_CLOSE_HCA, 1000);
+	return mlx4_cmd(dev, 0, 0, panic, MLX4_CMD_CLOSE_HCA, 1000,
+			MLX4_CMD_NATIVE);
 }
 
 int mlx4_SET_ICM_SIZE(struct mlx4_dev *dev, u64 icm_size, u64 *aux_pages)
 {
 	int ret = mlx4_cmd_imm(dev, icm_size, aux_pages, 0, 0,
 			       MLX4_CMD_SET_ICM_SIZE,
-			       MLX4_CMD_TIME_CLASS_A);
+			       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
 	if (ret)
 		return ret;
 
@@ -929,7 +1294,7 @@ int mlx4_SET_ICM_SIZE(struct mlx4_dev *dev, u64 icm_size, u64 *aux_pages)
 int mlx4_NOP(struct mlx4_dev *dev)
 {
 	/* Input modifier of 0x1f means "finish as soon as possible." */
-	return mlx4_cmd(dev, 0, 0x1f, 0, MLX4_CMD_NOP, 100);
+	return mlx4_cmd(dev, 0, 0x1f, 0, MLX4_CMD_NOP, 100, MLX4_CMD_NATIVE);
 }
 
 #define MLX4_WOL_SETUP_MODE (5 << 28)
@@ -938,7 +1303,8 @@ int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port)
 	u32 in_mod = MLX4_WOL_SETUP_MODE | port << 8;
 
 	return mlx4_cmd_imm(dev, 0, config, in_mod, 0x3,
-			    MLX4_CMD_MOD_STAT_CFG, MLX4_CMD_TIME_CLASS_A);
+			    MLX4_CMD_MOD_STAT_CFG, MLX4_CMD_TIME_CLASS_A,
+			    MLX4_CMD_NATIVE);
 }
 EXPORT_SYMBOL_GPL(mlx4_wol_read);
 
@@ -947,6 +1313,6 @@ int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port)
 	u32 in_mod = MLX4_WOL_SETUP_MODE | port << 8;
 
 	return mlx4_cmd(dev, config, in_mod, 0x1, MLX4_CMD_MOD_STAT_CFG,
-					MLX4_CMD_TIME_CLASS_A);
+			MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
 }
 EXPORT_SYMBOL_GPL(mlx4_wol_write);
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index bf5ec22..3368363 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -116,6 +116,23 @@ struct mlx4_dev_cap {
 	u32 max_counters;
 };
 
+struct mlx4_func_cap {
+	u8	function;
+	u8	num_ports;
+	u8	flags;
+	u32	pf_context_behaviour;
+	int	qp_quota;
+	int	cq_quota;
+	int	srq_quota;
+	int	mpt_quota;
+	int	mtt_quota;
+	int	max_eq;
+	int	reserved_eq;
+	int	mcg_quota;
+	u8	physical_port[MLX4_MAX_PORTS + 1];
+	u8	port_flags[MLX4_MAX_PORTS + 1];
+};
+
 struct mlx4_adapter {
 	char board_id[MLX4_BOARD_ID_LEN];
 	u8   inta_pin;
@@ -133,6 +150,7 @@ struct mlx4_init_hca_param {
 	u64 dmpt_base;
 	u64 cmpt_base;
 	u64 mtt_base;
+	u64 global_caps;
 	u16 log_mc_entry_sz;
 	u16 log_mc_hash_sz;
 	u8  log_num_qps;
@@ -143,6 +161,7 @@ struct mlx4_init_hca_param {
 	u8  log_mc_table_sz;
 	u8  log_mpt_sz;
 	u8  log_uar_sz;
+	u8  uar_page_sz; /* log pg sz in 4k chunks */
 };
 
 struct mlx4_init_ib_param {
@@ -167,12 +186,19 @@ struct mlx4_set_ib_param {
 };
 
 int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap);
+int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, struct mlx4_func_cap *func_cap);
+int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
+				struct mlx4_vhcr *vhcr,
+				struct mlx4_cmd_mailbox *inbox,
+				struct mlx4_cmd_mailbox *outbox,
+				struct mlx4_cmd_info *cmd);
 int mlx4_MAP_FA(struct mlx4_dev *dev, struct mlx4_icm *icm);
 int mlx4_UNMAP_FA(struct mlx4_dev *dev);
 int mlx4_RUN_FW(struct mlx4_dev *dev);
 int mlx4_QUERY_FW(struct mlx4_dev *dev);
 int mlx4_QUERY_ADAPTER(struct mlx4_dev *dev, struct mlx4_adapter *adapter);
 int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param);
+int mlx4_QUERY_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param);
 int mlx4_CLOSE_HCA(struct mlx4_dev *dev, int panic);
 int mlx4_map_cmd(struct mlx4_dev *dev, u16 op, struct mlx4_icm *icm, u64 virt);
 int mlx4_SET_ICM_SIZE(struct mlx4_dev *dev, u64 icm_size, u64 *aux_pages);
diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
index 02393fd..a9ade1c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/icm.c
+++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
@@ -213,7 +213,7 @@ static int mlx4_MAP_ICM(struct mlx4_dev *dev, struct mlx4_icm *icm, u64 virt)
 static int mlx4_UNMAP_ICM(struct mlx4_dev *dev, u64 virt, u32 page_count)
 {
 	return mlx4_cmd(dev, virt, page_count, 0, MLX4_CMD_UNMAP_ICM,
-			MLX4_CMD_TIME_CLASS_B);
+			MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
 }
 
 int mlx4_MAP_ICM_AUX(struct mlx4_dev *dev, struct mlx4_icm *icm)
@@ -223,7 +223,8 @@ int mlx4_MAP_ICM_AUX(struct mlx4_dev *dev, struct mlx4_icm *icm)
 
 int mlx4_UNMAP_ICM_AUX(struct mlx4_dev *dev)
 {
-	return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_UNMAP_ICM_AUX, MLX4_CMD_TIME_CLASS_B);
+	return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_UNMAP_ICM_AUX,
+			MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
 }
 
 int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, int obj)
diff --git a/drivers/net/ethernet/mellanox/mlx4/intf.c b/drivers/net/ethernet/mellanox/mlx4/intf.c
index ca6feb5..b4e9f6f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/intf.c
+++ b/drivers/net/ethernet/mellanox/mlx4/intf.c
@@ -142,7 +142,8 @@ int mlx4_register_device(struct mlx4_dev *dev)
 		mlx4_add_device(intf, priv);
 
 	mutex_unlock(&intf_mutex);
-	mlx4_start_catas_poll(dev);
+	if (!mlx4_is_slave(dev))
+		mlx4_start_catas_poll(dev);
 
 	return 0;
 }
@@ -152,7 +153,8 @@ void mlx4_unregister_device(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_interface *intf;
 
-	mlx4_stop_catas_poll(dev);
+	if (!mlx4_is_slave(dev))
+		mlx4_stop_catas_poll(dev);
 	mutex_lock(&intf_mutex);
 
 	list_for_each_entry(intf, &intf_list, list)
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 94bbc85..b969bfb 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -40,6 +40,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
 #include <linux/io-mapping.h>
+#include <linux/delay.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/doorbell.h>
@@ -75,21 +76,42 @@ MODULE_PARM_DESC(msi_x, "attempt to use MSI-X if nonzero");
 
 #endif /* CONFIG_PCI_MSI */
 
+static int num_vfs;
+module_param(num_vfs, int, 0444);
+MODULE_PARM_DESC(num_vfs, "enable #num_vfs functions if num_vfs > 0");
+
+static int probe_vf;
+module_param(probe_vf, int, 0644);
+MODULE_PARM_DESC(probe_vf, "number of vfs to probe by pf driver (num_vfs > 0)");
+
+int mlx4_log_num_mgm_entry_size = 10;
+module_param_named(log_num_mgm_entry_size,
+			mlx4_log_num_mgm_entry_size, int, 0444);
+MODULE_PARM_DESC(log_num_mgm_entry_size, "log mgm size, that defines the num"
+					 " of qp per mcg, for example:"
+					 " 10 gives 248.range: 9<="
+					 " log_num_mgm_entry_size <= 12");
+
+#define MLX4_VF                                        (1 << 0)
+
+#define HCA_GLOBAL_CAP_MASK            0
+#define PF_CONTEXT_BEHAVIOUR_MASK      0
+
 static char mlx4_version[] __devinitdata =
 	DRV_NAME ": Mellanox ConnectX core driver v"
 	DRV_VERSION " (" DRV_RELDATE ")\n";
 
 static struct mlx4_profile default_profile = {
-	.num_qp		= 1 << 17,
+	.num_qp		= 1 << 18,
 	.num_srq	= 1 << 16,
 	.rdmarc_per_qp	= 1 << 4,
 	.num_cq		= 1 << 16,
 	.num_mcg	= 1 << 13,
-	.num_mpt	= 1 << 17,
+	.num_mpt	= 1 << 19,
 	.num_mtt	= 1 << 20,
 };
 
-static int log_num_mac = 2;
+static int log_num_mac = 7;
 module_param_named(log_num_mac, log_num_mac, int, 0444);
 MODULE_PARM_DESC(log_num_mac, "Log2 max number of MACs per ETH port (1-7)");
 
@@ -104,10 +126,27 @@ module_param_named(use_prio, use_prio, bool, 0444);
 MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports "
 		  "(0/1, default 0)");
 
-static int log_mtts_per_seg = ilog2(MLX4_MTT_ENTRY_PER_SEG);
+int log_mtts_per_seg = ilog2(MLX4_MTT_ENTRY_PER_SEG);
 module_param_named(log_mtts_per_seg, log_mtts_per_seg, int, 0444);
 MODULE_PARM_DESC(log_mtts_per_seg, "Log2 number of MTT entries per segment (1-7)");
 
+static int port_type_array[2] = {1, 1};
+static int arr_argc = 2;
+module_param_array(port_type_array, int, &arr_argc, 0444);
+MODULE_PARM_DESC(port_type_array, "Array of port types: IB by default");
+
+struct mlx4_port_config {
+	struct list_head list;
+	enum mlx4_port_type port_type[MLX4_MAX_PORTS + 1];
+	struct pci_dev *pdev;
+};
+
+static inline int mlx4_master_get_num_eqs(struct mlx4_dev *dev)
+{
+	return dev->caps.reserved_eqs +
+		MLX4_MFUNC_EQ_NUM * (dev->num_slaves + 1);
+}
+
 int mlx4_check_port_params(struct mlx4_dev *dev,
 			   enum mlx4_port_type *port_type)
 {
@@ -140,10 +179,8 @@ static void mlx4_set_port_mask(struct mlx4_dev *dev)
 {
 	int i;
 
-	dev->caps.port_mask = 0;
 	for (i = 1; i <= dev->caps.num_ports; ++i)
-		if (dev->caps.port_type[i] == MLX4_PORT_TYPE_IB)
-			dev->caps.port_mask |= 1 << (i - 1);
+		dev->caps.port_mask[i] = dev->caps.port_type[i];
 }
 
 static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
@@ -194,6 +231,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		dev->caps.trans_code[i]     = dev_cap->trans_code[i];
 	}
 
+	dev->caps.uar_page_size	     = PAGE_SIZE;
 	dev->caps.num_uars	     = dev_cap->uar_size / PAGE_SIZE;
 	dev->caps.local_ca_ack_delay = dev_cap->local_ca_ack_delay;
 	dev->caps.bf_reg_size	     = dev_cap->bf_reg_size;
@@ -207,7 +245,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.reserved_srqs	     = dev_cap->reserved_srqs;
 	dev->caps.max_sq_desc_sz     = dev_cap->max_sq_desc_sz;
 	dev->caps.max_rq_desc_sz     = dev_cap->max_rq_desc_sz;
-	dev->caps.num_qp_per_mgm     = MLX4_QP_PER_MGM;
+	dev->caps.num_qp_per_mgm     = mlx4_get_qp_per_mgm(dev);
 	/*
 	 * Subtract 1 from the limit because we need to allocate a
 	 * spare CQE so the HCA HW can tell the difference between an
@@ -216,17 +254,18 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_cqes	     = dev_cap->max_cq_sz - 1;
 	dev->caps.reserved_cqs	     = dev_cap->reserved_cqs;
 	dev->caps.reserved_eqs	     = dev_cap->reserved_eqs;
-	dev->caps.mtts_per_seg	     = 1 << log_mtts_per_seg;
-	dev->caps.reserved_mtts	     = DIV_ROUND_UP(dev_cap->reserved_mtts,
-						    dev->caps.mtts_per_seg);
+	dev->caps.reserved_mtts      = dev_cap->reserved_mtts;
 	dev->caps.reserved_mrws	     = dev_cap->reserved_mrws;
-	dev->caps.reserved_uars	     = dev_cap->reserved_uars;
+
+	/* The first 128 UARs are used for EQ doorbells */
+	dev->caps.reserved_uars	     = max_t(int, 128, dev_cap->reserved_uars);
 	dev->caps.reserved_pds	     = dev_cap->reserved_pds;
 	dev->caps.reserved_xrcds     = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ?
 					dev_cap->reserved_xrcds : 0;
 	dev->caps.max_xrcds          = (dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC) ?
 					dev_cap->max_xrcds : 0;
-	dev->caps.mtt_entry_sz	     = dev->caps.mtts_per_seg * dev_cap->mtt_entry_sz;
+	dev->caps.mtt_entry_sz       = dev_cap->mtt_entry_sz;
+
 	dev->caps.max_msg_sz         = dev_cap->max_msg_sz;
 	dev->caps.page_size_cap	     = ~(u32) (dev_cap->min_page_sz - 1);
 	dev->caps.flags		     = dev_cap->flags;
@@ -240,10 +279,36 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.log_num_prios = use_prio ? 3 : 0;
 
 	for (i = 1; i <= dev->caps.num_ports; ++i) {
-		if (dev->caps.supported_type[i] != MLX4_PORT_TYPE_ETH)
-			dev->caps.port_type[i] = MLX4_PORT_TYPE_IB;
-		else
-			dev->caps.port_type[i] = MLX4_PORT_TYPE_ETH;
+		dev->caps.port_type[i] = MLX4_PORT_TYPE_NONE;
+		if (dev->caps.supported_type[i]) {
+			/* if only ETH is supported - assign ETH */
+			if (dev->caps.supported_type[i] == MLX4_PORT_TYPE_ETH)
+				dev->caps.port_type[i] = MLX4_PORT_TYPE_ETH;
+			/* if only IB is supported,
+			 * assign IB only if SRIOV is off*/
+			else if (dev->caps.supported_type[i] ==
+				 MLX4_PORT_TYPE_IB) {
+				if (dev->flags & MLX4_FLAG_SRIOV)
+					dev->caps.port_type[i] =
+						MLX4_PORT_TYPE_NONE;
+				else
+					dev->caps.port_type[i] =
+						MLX4_PORT_TYPE_IB;
+			/* if IB and ETH are supported,
+			 * first of all check if SRIOV is on */
+			} else if (dev->flags & MLX4_FLAG_SRIOV)
+				dev->caps.port_type[i] = MLX4_PORT_TYPE_ETH;
+			/* if IB and ETH are supported and SRIOV is off
+			 * use module parameters */
+			else {
+				if (port_type_array[i-1])
+					dev->caps.port_type[i] =
+						MLX4_PORT_TYPE_IB;
+				else
+					dev->caps.port_type[i] =
+						MLX4_PORT_TYPE_ETH;
+			}
+		}
 		dev->caps.possible_type[i] = dev->caps.port_type[i];
 		mlx4_priv(dev)->sense.sense_allowed[i] =
 			dev->caps.supported_type[i] == MLX4_PORT_TYPE_AUTO;
@@ -262,8 +327,6 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		}
 	}
 
-	mlx4_set_port_mask(dev);
-
 	dev->caps.max_counters = 1 << ilog2(dev_cap->max_counters);
 
 	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] = dev_cap->reserved_qps;
@@ -282,6 +345,149 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 
 	return 0;
 }
+/*The function checks if there are live vf, return the num of them*/
+static int mlx4_how_many_lives_vf(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_slave_state *s_state;
+	int i;
+	int ret = 0;
+
+	for (i = 1/*the ppf is 0*/; i < dev->num_slaves; ++i) {
+		s_state = &priv->mfunc.master.slave_state[i];
+		if (s_state->active && s_state->last_cmd !=
+		    MLX4_COMM_CMD_RESET) {
+			mlx4_warn(dev, "%s: slave: %d is still active\n",
+				  __func__, i);
+			ret++;
+		}
+	}
+	return ret;
+}
+
+static int mlx4_is_slave_active(struct mlx4_dev *dev, int slave)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_slave_state *s_slave;
+
+	if (!mlx4_is_master(dev))
+		return 0;
+
+	s_slave = &priv->mfunc.master.slave_state[slave];
+	return !!s_slave->active;
+}
+EXPORT_SYMBOL(mlx4_is_slave_active);
+
+static int mlx4_slave_cap(struct mlx4_dev *dev)
+{
+	int			   err;
+	u32			   page_size;
+	struct mlx4_dev_cap	   dev_cap;
+	struct mlx4_func_cap	   func_cap;
+	struct mlx4_init_hca_param hca_param;
+	int			   i;
+
+	memset(&hca_param, 0, sizeof(hca_param));
+	err = mlx4_QUERY_HCA(dev, &hca_param);
+	if (err) {
+		mlx4_err(dev, "QUERY_HCA command failed, aborting.\n");
+		return err;
+	}
+
+	/*fail if the hca has an unknown capability */
+	if ((hca_param.global_caps | HCA_GLOBAL_CAP_MASK) !=
+	    HCA_GLOBAL_CAP_MASK) {
+		mlx4_err(dev, "Unknown hca global capabilities\n");
+		return -ENOSYS;
+	}
+
+	mlx4_log_num_mgm_entry_size = hca_param.log_mc_entry_sz;
+
+	memset(&dev_cap, 0, sizeof(dev_cap));
+	err = mlx4_dev_cap(dev, &dev_cap);
+	if (err) {
+		mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
+		return err;
+	}
+
+	page_size = ~dev->caps.page_size_cap + 1;
+	mlx4_warn(dev, "HCA minimum page size:%d\n", page_size);
+	if (page_size > PAGE_SIZE) {
+		mlx4_err(dev, "HCA minimum page size of %d bigger than "
+			 "kernel PAGE_SIZE of %ld, aborting.\n",
+			 page_size, PAGE_SIZE);
+		return -ENODEV;
+	}
+
+	/* slave gets uar page size from QUERY_HCA fw command */
+	dev->caps.uar_page_size = 1 << (hca_param.uar_page_sz + 12);
+
+	/* TODO: relax this assumption */
+	if (dev->caps.uar_page_size != PAGE_SIZE) {
+		mlx4_err(dev, "UAR size:%d != kernel PAGE_SIZE of %ld\n",
+			 dev->caps.uar_page_size, PAGE_SIZE);
+		return -ENODEV;
+	}
+
+	memset(&func_cap, 0, sizeof(func_cap));
+	err = mlx4_QUERY_FUNC_CAP(dev, &func_cap);
+	if (err) {
+		mlx4_err(dev, "QUERY_FUNC_CAP command failed, aborting.\n");
+		return err;
+	}
+
+	if ((func_cap.pf_context_behaviour | PF_CONTEXT_BEHAVIOUR_MASK) !=
+	    PF_CONTEXT_BEHAVIOUR_MASK) {
+		mlx4_err(dev, "Unknown pf context behaviour\n");
+		return -ENOSYS;
+	}
+
+	dev->caps.function		= func_cap.function;
+	dev->caps.num_ports		= func_cap.num_ports;
+	dev->caps.num_qps		= func_cap.qp_quota;
+	dev->caps.num_srqs		= func_cap.srq_quota;
+	dev->caps.num_cqs		= func_cap.cq_quota;
+	dev->caps.num_eqs               = func_cap.max_eq;
+	dev->caps.reserved_eqs          = func_cap.reserved_eq;
+	dev->caps.num_mpts		= func_cap.mpt_quota;
+	dev->caps.num_mtts		= func_cap.mtt_quota;
+	dev->caps.num_pds               = MLX4_NUM_PDS;
+	dev->caps.num_mgms              = 0;
+	dev->caps.num_amgms             = 0;
+
+	for (i = 1; i <= dev->caps.num_ports; ++i)
+		dev->caps.port_mask[i] = dev->caps.port_type[i];
+
+	if (dev->caps.num_ports > MLX4_MAX_PORTS) {
+		mlx4_err(dev, "HCA has %d ports, but we only support %d, "
+			 "aborting.\n", dev->caps.num_ports, MLX4_MAX_PORTS);
+		return -ENODEV;
+	}
+
+	if (dev->caps.uar_page_size * (dev->caps.num_uars -
+				       dev->caps.reserved_uars) >
+				       pci_resource_len(dev->pdev, 2)) {
+		mlx4_err(dev, "HCA reported UAR region size of 0x%x bigger than "
+			 "PCI resource 2 size of 0x%llx, aborting.\n",
+			 dev->caps.uar_page_size * dev->caps.num_uars,
+			 (unsigned long long) pci_resource_len(dev->pdev, 2));
+		return -ENODEV;
+	}
+
+#if 0
+	mlx4_warn(dev, "sqp_demux:%d\n", dev->caps.sqp_demux);
+	mlx4_warn(dev, "num_uars:%d reserved_uars:%d uar region:0x%x bar2:0x%llx\n",
+		  dev->caps.num_uars, dev->caps.reserved_uars,
+		  dev->caps.uar_page_size * dev->caps.num_uars,
+		  pci_resource_len(dev->pdev, 2));
+	mlx4_warn(dev, "num_eqs:%d reserved_eqs:%d\n", dev->caps.num_eqs,
+		  dev->caps.reserved_eqs);
+	mlx4_warn(dev, "num_pds:%d reserved_pds:%d slave_pd_shift:%d pd_base:%d\n",
+		  dev->caps.num_pds, dev->caps.reserved_pds,
+		  dev->caps.slave_pd_shift, dev->caps.pd_base);
+#endif
+	return 0;
+}
 
 /*
  * Change the port configuration of the device.
@@ -451,6 +657,7 @@ static int mlx4_init_cmpt_table(struct mlx4_dev *dev, u64 cmpt_base,
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int err;
+	int num_eqs;
 
 	err = mlx4_init_icm_table(dev, &priv->qp_table.cmpt_table,
 				  cmpt_base +
@@ -480,12 +687,14 @@ static int mlx4_init_cmpt_table(struct mlx4_dev *dev, u64 cmpt_base,
 	if (err)
 		goto err_srq;
 
+	num_eqs = (mlx4_is_master(dev)) ?
+		roundup_pow_of_two(mlx4_master_get_num_eqs(dev)) :
+		dev->caps.num_eqs;
 	err = mlx4_init_icm_table(dev, &priv->eq_table.cmpt_table,
 				  cmpt_base +
 				  ((u64) (MLX4_CMPT_TYPE_EQ *
 					  cmpt_entry_sz) << MLX4_CMPT_SHIFT),
-				  cmpt_entry_sz,
-				  dev->caps.num_eqs, dev->caps.num_eqs, 0, 0);
+				  cmpt_entry_sz, num_eqs, num_eqs, 0, 0);
 	if (err)
 		goto err_cq;
 
@@ -509,6 +718,7 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	u64 aux_pages;
+	int num_eqs;
 	int err;
 
 	err = mlx4_SET_ICM_SIZE(dev, icm_size, &aux_pages);
@@ -540,10 +750,13 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 		goto err_unmap_aux;
 	}
 
+
+	num_eqs = (mlx4_is_master(dev)) ?
+		roundup_pow_of_two(mlx4_master_get_num_eqs(dev)) :
+		dev->caps.num_eqs;
 	err = mlx4_init_icm_table(dev, &priv->eq_table.table,
 				  init_hca->eqc_base, dev_cap->eqc_entry_sz,
-				  dev->caps.num_eqs, dev->caps.num_eqs,
-				  0, 0);
+				  num_eqs, num_eqs, 0, 0);
 	if (err) {
 		mlx4_err(dev, "Failed to map EQ context memory, aborting.\n");
 		goto err_unmap_cmpt;
@@ -563,7 +776,7 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 	err = mlx4_init_icm_table(dev, &priv->mr_table.mtt_table,
 				  init_hca->mtt_base,
 				  dev->caps.mtt_entry_sz,
-				  dev->caps.num_mtt_segs,
+				  dev->caps.num_mtts,
 				  dev->caps.reserved_mtts, 1, 0);
 	if (err) {
 		mlx4_err(dev, "Failed to map MTT context memory, aborting.\n");
@@ -650,7 +863,8 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 	 * and it's a lot easier than trying to track ref counts.
 	 */
 	err = mlx4_init_icm_table(dev, &priv->mcg_table.table,
-				  init_hca->mc_base, MLX4_MGM_ENTRY_SIZE,
+				  init_hca->mc_base,
+				  mlx4_get_mgm_entry_size(dev),
 				  dev->caps.num_mgms + dev->caps.num_amgms,
 				  dev->caps.num_mgms + dev->caps.num_amgms,
 				  0, 0);
@@ -726,6 +940,16 @@ static void mlx4_free_icms(struct mlx4_dev *dev)
 	mlx4_free_icm(dev, priv->fw.aux_icm, 0);
 }
 
+static void mlx4_slave_exit(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	down(&priv->cmd.slave_sem);
+	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0, MLX4_COMM_TIME))
+		mlx4_warn(dev, "Failed to close slave function.\n");
+	up(&priv->cmd.slave_sem);
+}
+
 static int map_bf_area(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -733,8 +957,10 @@ static int map_bf_area(struct mlx4_dev *dev)
 	resource_size_t bf_len;
 	int err = 0;
 
-	bf_start = pci_resource_start(dev->pdev, 2) + (dev->caps.num_uars << PAGE_SHIFT);
-	bf_len = pci_resource_len(dev->pdev, 2) - (dev->caps.num_uars << PAGE_SHIFT);
+	bf_start = pci_resource_start(dev->pdev, 2) +
+			(dev->caps.num_uars << PAGE_SHIFT);
+	bf_len = pci_resource_len(dev->pdev, 2) -
+			(dev->caps.num_uars << PAGE_SHIFT);
 	priv->bf_mapping = io_mapping_create_wc(bf_start, bf_len);
 	if (!priv->bf_mapping)
 		err = -ENOMEM;
@@ -751,10 +977,81 @@ static void unmap_bf_area(struct mlx4_dev *dev)
 static void mlx4_close_hca(struct mlx4_dev *dev)
 {
 	unmap_bf_area(dev);
-	mlx4_CLOSE_HCA(dev, 0);
-	mlx4_free_icms(dev);
-	mlx4_UNMAP_FA(dev);
-	mlx4_free_icm(dev, mlx4_priv(dev)->fw.fw_icm, 0);
+	if (mlx4_is_slave(dev))
+		mlx4_slave_exit(dev);
+	else {
+		mlx4_CLOSE_HCA(dev, 0);
+		mlx4_free_icms(dev);
+		mlx4_UNMAP_FA(dev);
+		mlx4_free_icm(dev, mlx4_priv(dev)->fw.fw_icm, 0);
+	}
+}
+
+static int mlx4_init_slave(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	u64 dma = (u64) priv->mfunc.vhcr_dma;
+	int num_of_reset_retries = NUM_OF_RESET_RETRIES;
+	int ret_from_reset = 0;
+	u32 slave_read;
+	u32 cmd_channel_ver;
+
+	down(&priv->cmd.slave_sem);
+	priv->cmd.max_cmds = 1;
+	mlx4_warn(dev, "Sending reset\n");
+	ret_from_reset = mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0,
+				       MLX4_COMM_TIME);
+	/* if we are in the middle of flr the slave will try
+	 * NUM_OF_RESET_RETRIES times before leaving.*/
+	if (ret_from_reset) {
+		if (MLX4_DELAY_RESET_SLAVE == ret_from_reset) {
+			msleep(SLEEP_TIME_IN_RESET);
+			while (ret_from_reset && num_of_reset_retries) {
+				mlx4_warn(dev, "slave is currently in the"
+					  "middle of FLR. retrying..."
+					  "(try num:%d)\n",
+					  (NUM_OF_RESET_RETRIES -
+					   num_of_reset_retries  + 1));
+				ret_from_reset =
+					mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET,
+						      0, MLX4_COMM_TIME);
+				num_of_reset_retries = num_of_reset_retries - 1;
+			}
+		} else
+			goto err;
+	}
+
+	/* check the driver version - the slave I/F revision
+	 * must match the master's */
+	slave_read = swab32(readl(&priv->mfunc.comm->slave_read));
+	cmd_channel_ver = mlx4_comm_get_version();
+
+	if (MLX4_COMM_GET_IF_REV(cmd_channel_ver) !=
+		MLX4_COMM_GET_IF_REV(slave_read)) {
+		mlx4_err(dev, "slave driver version is not supported"
+			 " by the master\n");
+		goto err;
+	}
+
+	mlx4_warn(dev, "Sending vhcr0\n");
+	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR0, dma >> 48,
+						    MLX4_COMM_TIME))
+		goto err;
+	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR1, dma >> 32,
+						    MLX4_COMM_TIME))
+		goto err;
+	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR2, dma >> 16,
+						    MLX4_COMM_TIME))
+		goto err;
+	if (mlx4_comm_cmd(dev, MLX4_COMM_CMD_VHCR_EN, dma, MLX4_COMM_TIME))
+		goto err;
+	up(&priv->cmd.slave_sem);
+	return 0;
+
+err:
+	mlx4_comm_cmd(dev, MLX4_COMM_CMD_RESET, 0, 0);
+	up(&priv->cmd.slave_sem);
+	return -EIO;
 }
 
 static int mlx4_init_hca(struct mlx4_dev *dev)
@@ -768,56 +1065,76 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 	u64 icm_size;
 	int err;
 
-	err = mlx4_QUERY_FW(dev);
-	if (err) {
-		if (err == -EACCES)
-			mlx4_info(dev, "non-primary physical function, skipping.\n");
-		else
-			mlx4_err(dev, "QUERY_FW command failed, aborting.\n");
-		return err;
-	}
+	if (!mlx4_is_slave(dev)) {
+		err = mlx4_QUERY_FW(dev);
+		if (err) {
+			if (err == -EACCES)
+				mlx4_info(dev, "non-primary physical function, skipping.\n");
+			else
+				mlx4_err(dev, "QUERY_FW command failed, aborting.\n");
+			goto unmap_bf;
+		}
 
-	err = mlx4_load_fw(dev);
-	if (err) {
-		mlx4_err(dev, "Failed to start FW, aborting.\n");
-		return err;
-	}
+		err = mlx4_load_fw(dev);
+		if (err) {
+			mlx4_err(dev, "Failed to start FW, aborting.\n");
+			goto unmap_bf;
+		}
 
-	mlx4_cfg.log_pg_sz_m = 1;
-	mlx4_cfg.log_pg_sz = 0;
-	err = mlx4_MOD_STAT_CFG(dev, &mlx4_cfg);
-	if (err)
-		mlx4_warn(dev, "Failed to override log_pg_sz parameter\n");
+		mlx4_cfg.log_pg_sz_m = 1;
+		mlx4_cfg.log_pg_sz = 0;
+		err = mlx4_MOD_STAT_CFG(dev, &mlx4_cfg);
+		if (err)
+			mlx4_warn(dev, "Failed to override log_pg_sz parameter\n");
 
-	err = mlx4_dev_cap(dev, &dev_cap);
-	if (err) {
-		mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
-		goto err_stop_fw;
-	}
+		err = mlx4_dev_cap(dev, &dev_cap);
+		if (err) {
+			mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting.\n");
+			goto err_stop_fw;
+		}
 
-	profile = default_profile;
+		profile = default_profile;
 
-	icm_size = mlx4_make_profile(dev, &profile, &dev_cap, &init_hca);
-	if ((long long) icm_size < 0) {
-		err = icm_size;
-		goto err_stop_fw;
-	}
+		icm_size = mlx4_make_profile(dev, &profile, &dev_cap,
+					     &init_hca);
+		if ((long long) icm_size < 0) {
+			err = icm_size;
+			goto err_stop_fw;
+		}
 
-	if (map_bf_area(dev))
-		mlx4_dbg(dev, "Failed to map blue flame area\n");
+		init_hca.log_uar_sz = ilog2(dev->caps.num_uars);
+		init_hca.uar_page_sz = PAGE_SHIFT - 12;
 
-	init_hca.log_uar_sz = ilog2(dev->caps.num_uars);
+		err = mlx4_init_icm(dev, &dev_cap, &init_hca, icm_size);
+		if (err)
+			goto err_stop_fw;
 
-	err = mlx4_init_icm(dev, &dev_cap, &init_hca, icm_size);
-	if (err)
-		goto err_stop_fw;
+		err = mlx4_INIT_HCA(dev, &init_hca);
+		if (err) {
+			mlx4_err(dev, "INIT_HCA command failed, aborting.\n");
+			goto err_free_icm;
+		}
+	} else {
+		err = mlx4_init_slave(dev);
+		if (err) {
+			mlx4_err(dev, "Failed to initialize slave\n");
+			goto unmap_bf;
+		}
 
-	err = mlx4_INIT_HCA(dev, &init_hca);
-	if (err) {
-		mlx4_err(dev, "INIT_HCA command failed, aborting.\n");
-		goto err_free_icm;
+		err = mlx4_slave_cap(dev);
+		if (err) {
+			mlx4_err(dev, "Failed to obtain slave caps\n");
+			goto err_close;
+		}
 	}
 
+	if (map_bf_area(dev))
+		mlx4_dbg(dev, "Failed to map blue flame area\n");
+
+	/*Only the master set the ports, all the rest got it from it.*/
+	if (!mlx4_is_slave(dev))
+		mlx4_set_port_mask(dev);
+
 	err = mlx4_QUERY_ADAPTER(dev, &adapter);
 	if (err) {
 		mlx4_err(dev, "QUERY_ADAPTER command failed, aborting.\n");
@@ -830,16 +1147,19 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 	return 0;
 
 err_close:
-	mlx4_CLOSE_HCA(dev, 0);
+	mlx4_close_hca(dev);
 
 err_free_icm:
-	mlx4_free_icms(dev);
+	if (!mlx4_is_slave(dev))
+		mlx4_free_icms(dev);
 
 err_stop_fw:
+	if (!mlx4_is_slave(dev)) {
+		mlx4_UNMAP_FA(dev);
+		mlx4_free_icm(dev, priv->fw.fw_icm, 0);
+	}
+unmap_bf:
 	unmap_bf_area(dev);
-	mlx4_UNMAP_FA(dev);
-	mlx4_free_icm(dev, priv->fw.fw_icm, 0);
-
 	return err;
 }
 
@@ -986,55 +1306,62 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 		goto err_srq_table_free;
 	}
 
-	err = mlx4_init_mcg_table(dev);
-	if (err) {
-		mlx4_err(dev, "Failed to initialize "
-			 "multicast group table, aborting.\n");
-		goto err_qp_table_free;
+	if (!mlx4_is_slave(dev)) {
+		err = mlx4_init_mcg_table(dev);
+		if (err) {
+			mlx4_err(dev, "Failed to initialize "
+				 "multicast group table, aborting.\n");
+			goto err_qp_table_free;
+		}
 	}
 
 	err = mlx4_init_counters_table(dev);
 	if (err && err != -ENOENT) {
 		mlx4_err(dev, "Failed to initialize counters table, aborting.\n");
-		goto err_counters_table_free;
+		goto err_mcg_table_free;
 	}
 
-	for (port = 1; port <= dev->caps.num_ports; port++) {
-		enum mlx4_port_type port_type = 0;
-		mlx4_SENSE_PORT(dev, port, &port_type);
-		if (port_type)
-			dev->caps.port_type[port] = port_type;
-		ib_port_default_caps = 0;
-		err = mlx4_get_port_ib_caps(dev, port, &ib_port_default_caps);
-		if (err)
-			mlx4_warn(dev, "failed to get port %d default "
-				  "ib capabilities (%d). Continuing with "
-				  "caps = 0\n", port, err);
-		dev->caps.ib_port_def_cap[port] = ib_port_default_caps;
-
-		err = mlx4_check_ext_port_caps(dev, port);
-		if (err)
-			mlx4_warn(dev, "failed to get port %d extended "
-				  "port capabilities support info (%d)."
-				  " Assuming not supported\n", port, err);
+	if (!mlx4_is_slave(dev)) {
+		for (port = 1; port <= dev->caps.num_ports; port++) {
+			if (!mlx4_is_mfunc(dev)) {
+				enum mlx4_port_type port_type = 0;
+				mlx4_SENSE_PORT(dev, port, &port_type);
+				if (port_type)
+					dev->caps.port_type[port] = port_type;
+			}
+			ib_port_default_caps = 0;
+			err = mlx4_get_port_ib_caps(dev, port,
+						    &ib_port_default_caps);
+			if (err)
+				mlx4_warn(dev, "failed to get port %d default "
+					  "ib capabilities (%d). Continuing "
+					  "with caps = 0\n", port, err);
+			dev->caps.ib_port_def_cap[port] = ib_port_default_caps;
+
+			err = mlx4_check_ext_port_caps(dev, port);
+			if (err)
+				mlx4_warn(dev, "failed to get port %d extended "
+					  "port capabilities support info (%d)."
+					  " Assuming not supported\n",
+					  port, err);
 
-		err = mlx4_SET_PORT(dev, port);
-		if (err) {
-			mlx4_err(dev, "Failed to set port %d, aborting\n",
-				port);
-			goto err_mcg_table_free;
+			err = mlx4_SET_PORT(dev, port);
+			if (err) {
+				mlx4_err(dev, "Failed to set port %d, aborting\n",
+					port);
+				goto err_counters_table_free;
+			}
 		}
 	}
-	mlx4_set_port_mask(dev);
 
 	return 0;
 
-err_mcg_table_free:
-	mlx4_cleanup_mcg_table(dev);
-
 err_counters_table_free:
 	mlx4_cleanup_counters_table(dev);
 
+err_mcg_table_free:
+	mlx4_cleanup_mcg_table(dev);
+
 err_qp_table_free:
 	mlx4_cleanup_qp_table(dev);
 
@@ -1081,8 +1408,16 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 	int i;
 
 	if (msi_x) {
-		nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
-			     nreq);
+		/* In multifunction mode each function gets 2 msi-X vectors
+		 * one for data path completions anf the other for asynch events
+		 * or command completions */
+		if (mlx4_is_mfunc(dev)) {
+			nreq = 2;
+		} else {
+			nreq = min_t(int, dev->caps.num_eqs -
+				     dev->caps.reserved_eqs, nreq);
+		}
+
 		entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
 		if (!entries)
 			goto no_msi;
@@ -1138,16 +1473,24 @@ static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
 
 	info->dev = dev;
 	info->port = port;
-	mlx4_init_mac_table(dev, &info->mac_table);
-	mlx4_init_vlan_table(dev, &info->vlan_table);
-	info->base_qpn = dev->caps.reserved_qps_base[MLX4_QP_REGION_ETH_ADDR] +
+	if (!mlx4_is_slave(dev)) {
+		INIT_RADIX_TREE(&info->mac_tree, GFP_KERNEL);
+		mlx4_init_mac_table(dev, &info->mac_table);
+		mlx4_init_vlan_table(dev, &info->vlan_table);
+		info->base_qpn =
+			dev->caps.reserved_qps_base[MLX4_QP_REGION_ETH_ADDR] +
 			(port - 1) * (1 << log_num_mac);
+	}
 
 	sprintf(info->dev_name, "mlx4_port%d", port);
 	info->port_attr.attr.name = info->dev_name;
-	info->port_attr.attr.mode = S_IRUGO | S_IWUSR;
+	if (mlx4_is_mfunc(dev))
+		info->port_attr.attr.mode = S_IRUGO;
+	else {
+		info->port_attr.attr.mode = S_IRUGO | S_IWUSR;
+		info->port_attr.store     = set_port_type;
+	}
 	info->port_attr.show      = show_port_type;
-	info->port_attr.store     = set_port_type;
 	sysfs_attr_init(&info->port_attr.attr);
 
 	err = device_create_file(&dev->pdev->dev, &info->port_attr);
@@ -1220,6 +1563,46 @@ static void mlx4_clear_steering(struct mlx4_dev *dev)
 	kfree(priv->steer);
 }
 
+static int extended_func_num(struct pci_dev *pdev)
+{
+	return PCI_SLOT(pdev->devfn) * 8 + PCI_FUNC(pdev->devfn);
+}
+
+#define MLX4_OWNER_BASE	0x8069c
+#define MLX4_OWNER_SIZE	4
+
+static int mlx4_get_ownership(struct mlx4_dev *dev)
+{
+	void __iomem *owner;
+	u32 ret;
+
+	owner = ioremap(pci_resource_start(dev->pdev, 0) + MLX4_OWNER_BASE,
+			MLX4_OWNER_SIZE);
+	if (!owner) {
+		mlx4_err(dev, "Failed to obtain ownership bit\n");
+		return -ENOMEM;
+	}
+
+	ret = readl(owner);
+	iounmap(owner);
+	return (int) !!ret;
+}
+
+static void mlx4_free_ownership(struct mlx4_dev *dev)
+{
+	void __iomem *owner;
+
+	owner = ioremap(pci_resource_start(dev->pdev, 0) + MLX4_OWNER_BASE,
+			MLX4_OWNER_SIZE);
+	if (!owner) {
+		mlx4_err(dev, "Failed to obtain ownership bit\n");
+		return;
+	}
+	writel(0, owner);
+	msleep(1000);
+	iounmap(owner);
+}
+
 static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct mlx4_priv *priv;
@@ -1235,13 +1618,20 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 			"aborting.\n");
 		return err;
 	}
-
+	if (num_vfs > MLX4_MAX_NUM_VF) {
+		printk(KERN_ERR "There are more VF's (%d) than allowed(%d)\n",
+		       num_vfs, MLX4_MAX_NUM_VF);
+		return -EINVAL;
+	}
 	/*
-	 * Check for BARs.  We expect 0: 1MB
+	 * Check for BARs.
 	 */
-	if (!(pci_resource_flags(pdev, 0) & IORESOURCE_MEM) ||
-	    pci_resource_len(pdev, 0) != 1 << 20) {
-		dev_err(&pdev->dev, "Missing DCS, aborting.\n");
+	if (((id == NULL) || !(id->driver_data & MLX4_VF)) &&
+	    !(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) {
+		dev_err(&pdev->dev, "Missing DCS, aborting."
+			"(id == 0X%p, id->driver_data: 0x%lx,"
+			" pci_resource_flags(pdev, 0):0x%lx)\n", id,
+			id ? id->driver_data : 0, pci_resource_flags(pdev, 0));
 		err = -ENODEV;
 		goto err_disable_pdev;
 	}
@@ -1305,42 +1695,132 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	mutex_init(&priv->bf_mutex);
 
 	dev->rev_id = pdev->revision;
+	/* Detect if this device is a virtual function */
+	if (id && id->driver_data & MLX4_VF) {
+		/* When acting as pf, we normally skip vfs unless explicitly
+		 * requested to probe them. */
+		if (num_vfs && extended_func_num(pdev) > probe_vf) {
+			mlx4_warn(dev, "Skipping virtual function:%d\n",
+						extended_func_num(pdev));
+			err = -ENODEV;
+			goto err_free_dev;
+		}
+		mlx4_warn(dev, "Detected virtual function - running in slave mode\n");
+		dev->flags |= MLX4_FLAG_SLAVE;
+	} else {
+		/* We reset the device and enable SRIOV only for physical
+		 * devices.  Try to claim ownership on the device;
+		 * if already taken, skip -- do not allow multiple PFs */
+		err = mlx4_get_ownership(dev);
+		if (err) {
+			if (err < 0)
+				goto err_free_dev;
+			else {
+				mlx4_warn(dev, "Multiple PFs not yet supported."
+					  " Skipping PF.\n");
+				err = -EINVAL;
+				goto err_free_dev;
+			}
+		}
 
-	/*
-	 * Now reset the HCA before we touch the PCI capabilities or
-	 * attempt a firmware command, since a boot ROM may have left
-	 * the HCA in an undefined state.
-	 */
-	err = mlx4_reset(dev);
-	if (err) {
-		mlx4_err(dev, "Failed to reset HCA, aborting.\n");
-		goto err_free_dev;
+		if (num_vfs) {
+			mlx4_warn(dev, "Enabling sriov with:%d vfs\n", num_vfs);
+			err = pci_enable_sriov(pdev, num_vfs);
+			if (err) {
+				mlx4_err(dev, "Failed to enable sriov,"
+					 "continuing without sriov enabled"
+					 " (err = %d).\n", err);
+				num_vfs = 0;
+				err = 0;
+			} else {
+				mlx4_warn(dev, "Running in master mode\n");
+				dev->flags |= MLX4_FLAG_SRIOV |
+					      MLX4_FLAG_MASTER;
+				dev->num_vfs = num_vfs;
+			}
+		}
+
+		/*
+		 * Now reset the HCA before we touch the PCI capabilities or
+		 * attempt a firmware command, since a boot ROM may have left
+		 * the HCA in an undefined state.
+		 */
+		err = mlx4_reset(dev);
+		if (err) {
+			mlx4_err(dev, "Failed to reset HCA, aborting.\n");
+			goto err_rel_own;
+		}
 	}
 
+slave_start:
 	if (mlx4_cmd_init(dev)) {
 		mlx4_err(dev, "Failed to init command interface, aborting.\n");
-		goto err_free_dev;
+		goto err_sriov;
+	}
+
+	/* In slave functions, the communication channel must be initialized
+	 * before posting commands. Also, init num_slaves before calling
+	 * mlx4_init_hca */
+	if (mlx4_is_mfunc(dev)) {
+		if (mlx4_is_master(dev))
+			dev->num_slaves = MLX4_MAX_NUM_SLAVES;
+		else {
+			dev->num_slaves = 0;
+			if (mlx4_multi_func_init(dev)) {
+				mlx4_err(dev, "Failed to init slave mfunc"
+					 " interface, aborting.\n");
+				goto err_cmd;
+			}
+		}
 	}
 
 	err = mlx4_init_hca(dev);
-	if (err)
-		goto err_cmd;
+	if (err) {
+		if (err == -EACCES) {
+			/* Not primary Physical function
+			 * Running in slave mode */
+			mlx4_cmd_cleanup(dev);
+			dev->flags |= MLX4_FLAG_SLAVE;
+			dev->flags &= ~MLX4_FLAG_MASTER;
+			goto slave_start;
+		} else
+			goto err_mfunc;
+	}
+
+	/* In master functions, the communication channel must be initialized
+	 * after obtaining its address from fw */
+	if (mlx4_is_master(dev)) {
+		if (mlx4_multi_func_init(dev)) {
+			mlx4_err(dev, "Failed to init master mfunc"
+				 "interface, aborting.\n");
+			goto err_close;
+		}
+	}
 
 	err = mlx4_alloc_eq_table(dev);
 	if (err)
-		goto err_close;
+		goto err_master_mfunc;
 
 	priv->msix_ctl.pool_bm = 0;
 	spin_lock_init(&priv->msix_ctl.pool_lock);
 
 	mlx4_enable_msi_x(dev);
-
-	err = mlx4_init_steering(dev);
-	if (err)
+	if ((mlx4_is_mfunc(dev)) &&
+	    !(dev->flags & MLX4_FLAG_MSI_X)) {
+		mlx4_err(dev, "INTx is not supported in multi-function mode."
+			 " aborting.\n");
 		goto err_free_eq;
+	}
+
+	if (!mlx4_is_slave(dev)) {
+		err = mlx4_init_steering(dev);
+		if (err)
+			goto err_free_eq;
+	}
 
 	err = mlx4_setup_hca(dev);
-	if (err == -EBUSY && (dev->flags & MLX4_FLAG_MSI_X)) {
+	if (err == -EBUSY && (dev->flags & MLX4_FLAG_MSI_X) &&
+	    !mlx4_is_mfunc(dev)) {
 		dev->flags &= ~MLX4_FLAG_MSI_X;
 		pci_disable_msix(pdev);
 		err = mlx4_setup_hca(dev);
@@ -1383,20 +1863,37 @@ err_port:
 	mlx4_cleanup_uar_table(dev);
 
 err_steer:
-	mlx4_clear_steering(dev);
+	if (!mlx4_is_slave(dev))
+		mlx4_clear_steering(dev);
 
 err_free_eq:
 	mlx4_free_eq_table(dev);
 
+err_master_mfunc:
+	if (mlx4_is_master(dev))
+		mlx4_multi_func_cleanup(dev);
+
 err_close:
 	if (dev->flags & MLX4_FLAG_MSI_X)
 		pci_disable_msix(pdev);
 
 	mlx4_close_hca(dev);
 
+err_mfunc:
+	if (mlx4_is_slave(dev))
+		mlx4_multi_func_cleanup(dev);
+
 err_cmd:
 	mlx4_cmd_cleanup(dev);
 
+err_sriov:
+	if (num_vfs && (dev->flags & MLX4_FLAG_SRIOV))
+		pci_disable_sriov(pdev);
+
+err_rel_own:
+	if (!mlx4_is_slave(dev))
+		mlx4_free_ownership(dev);
+
 err_free_dev:
 	kfree(priv);
 
@@ -1424,6 +1921,12 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	int p;
 
 	if (dev) {
+		/* in SRIOV it is not allowed to unload the pf's
+		 * driver while there are alive vf's */
+		if (mlx4_is_master(dev)) {
+			if (mlx4_how_many_lives_vf(dev))
+				printk(KERN_ERR "Removing PF when there are assigned VF's !!!\n");
+		}
 		mlx4_stop_sense(dev);
 		mlx4_unregister_device(dev);
 
@@ -1443,17 +1946,31 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 		mlx4_cleanup_xrcd_table(dev);
 		mlx4_cleanup_pd_table(dev);
 
+		if (mlx4_is_master(dev))
+			mlx4_free_resource_tracker(dev);
+
 		iounmap(priv->kar);
 		mlx4_uar_free(dev, &priv->driver_uar);
 		mlx4_cleanup_uar_table(dev);
-		mlx4_clear_steering(dev);
+		if (!mlx4_is_slave(dev))
+			mlx4_clear_steering(dev);
 		mlx4_free_eq_table(dev);
+		if (mlx4_is_master(dev))
+			mlx4_multi_func_cleanup(dev);
 		mlx4_close_hca(dev);
+		if (mlx4_is_slave(dev))
+			mlx4_multi_func_cleanup(dev);
 		mlx4_cmd_cleanup(dev);
 
 		if (dev->flags & MLX4_FLAG_MSI_X)
 			pci_disable_msix(pdev);
+		if (num_vfs && (dev->flags & MLX4_FLAG_SRIOV)) {
+			mlx4_warn(dev, "Disabling sriov\n");
+			pci_disable_sriov(pdev);
+		}
 
+		if (!mlx4_is_slave(dev))
+			mlx4_free_ownership(dev);
 		kfree(priv);
 		pci_release_regions(pdev);
 		pci_disable_device(pdev);
@@ -1468,33 +1985,48 @@ int mlx4_restart_one(struct pci_dev *pdev)
 }
 
 static DEFINE_PCI_DEVICE_TABLE(mlx4_pci_table) = {
-	{ PCI_VDEVICE(MELLANOX, 0x6340) }, /* MT25408 "Hermon" SDR */
-	{ PCI_VDEVICE(MELLANOX, 0x634a) }, /* MT25408 "Hermon" DDR */
-	{ PCI_VDEVICE(MELLANOX, 0x6354) }, /* MT25408 "Hermon" QDR */
-	{ PCI_VDEVICE(MELLANOX, 0x6732) }, /* MT25408 "Hermon" DDR PCIe gen2 */
-	{ PCI_VDEVICE(MELLANOX, 0x673c) }, /* MT25408 "Hermon" QDR PCIe gen2 */
-	{ PCI_VDEVICE(MELLANOX, 0x6368) }, /* MT25408 "Hermon" EN 10GigE */
-	{ PCI_VDEVICE(MELLANOX, 0x6750) }, /* MT25408 "Hermon" EN 10GigE PCIe gen2 */
-	{ PCI_VDEVICE(MELLANOX, 0x6372) }, /* MT25458 ConnectX EN 10GBASE-T 10GigE */
-	{ PCI_VDEVICE(MELLANOX, 0x675a) }, /* MT25458 ConnectX EN 10GBASE-T+Gen2 10GigE */
-	{ PCI_VDEVICE(MELLANOX, 0x6764) }, /* MT26468 ConnectX EN 10GigE PCIe gen2*/
-	{ PCI_VDEVICE(MELLANOX, 0x6746) }, /* MT26438 ConnectX EN 40GigE PCIe gen2 5GT/s */
-	{ PCI_VDEVICE(MELLANOX, 0x676e) }, /* MT26478 ConnectX2 40GigE PCIe gen2 */
-	{ PCI_VDEVICE(MELLANOX, 0x1002) }, /* MT25400 Family [ConnectX-2 Virtual Function] */
-	{ PCI_VDEVICE(MELLANOX, 0x1003) }, /* MT27500 Family [ConnectX-3] */
-	{ PCI_VDEVICE(MELLANOX, 0x1004) }, /* MT27500 Family [ConnectX-3 Virtual Function] */
-	{ PCI_VDEVICE(MELLANOX, 0x1005) }, /* MT27510 Family */
-	{ PCI_VDEVICE(MELLANOX, 0x1006) }, /* MT27511 Family */
-	{ PCI_VDEVICE(MELLANOX, 0x1007) }, /* MT27520 Family */
-	{ PCI_VDEVICE(MELLANOX, 0x1008) }, /* MT27521 Family */
-	{ PCI_VDEVICE(MELLANOX, 0x1009) }, /* MT27530 Family */
-	{ PCI_VDEVICE(MELLANOX, 0x100a) }, /* MT27531 Family */
-	{ PCI_VDEVICE(MELLANOX, 0x100b) }, /* MT27540 Family */
-	{ PCI_VDEVICE(MELLANOX, 0x100c) }, /* MT27541 Family */
-	{ PCI_VDEVICE(MELLANOX, 0x100d) }, /* MT27550 Family */
-	{ PCI_VDEVICE(MELLANOX, 0x100e) }, /* MT27551 Family */
-	{ PCI_VDEVICE(MELLANOX, 0x100f) }, /* MT27560 Family */
-	{ PCI_VDEVICE(MELLANOX, 0x1010) }, /* MT27561 Family */
+	/* MT25408 "Hermon" SDR */
+	{ PCI_VDEVICE(MELLANOX, 0x6340), 0 },
+	/* MT25408 "Hermon" DDR */
+	{ PCI_VDEVICE(MELLANOX, 0x634a), 0 },
+	/* MT25408 "Hermon" QDR */
+	{ PCI_VDEVICE(MELLANOX, 0x6354), 0 },
+	/* MT25408 "Hermon" DDR PCIe gen2 */
+	{ PCI_VDEVICE(MELLANOX, 0x6732), 0 },
+	/* MT25408 "Hermon" QDR PCIe gen2 */
+	{ PCI_VDEVICE(MELLANOX, 0x673c), 0 },
+	/* MT25408 "Hermon" EN 10GigE */
+	{ PCI_VDEVICE(MELLANOX, 0x6368), 0 },
+	/* MT25408 "Hermon" EN 10GigE PCIe gen2 */
+	{ PCI_VDEVICE(MELLANOX, 0x6750), 0 },
+	/* MT25458 ConnectX EN 10GBASE-T 10GigE */
+	{ PCI_VDEVICE(MELLANOX, 0x6372), 0 },
+	/* MT25458 ConnectX EN 10GBASE-T+Gen2 10GigE */
+	{ PCI_VDEVICE(MELLANOX, 0x675a), 0 },
+	/* MT26468 ConnectX EN 10GigE PCIe gen2*/
+	{ PCI_VDEVICE(MELLANOX, 0x6764), 0 },
+	/* MT26438 ConnectX EN 40GigE PCIe gen2 5GT/s */
+	{ PCI_VDEVICE(MELLANOX, 0x6746), 0 },
+	/* MT26478 ConnectX2 40GigE PCIe gen2 */
+	{ PCI_VDEVICE(MELLANOX, 0x676e), 0 },
+	/* MT25400 Family [ConnectX-2 Virtual Function] */
+	{ PCI_VDEVICE(MELLANOX, 0x1002), MLX4_VF },
+	/* MT27500 Family [ConnectX-3] */
+	{ PCI_VDEVICE(MELLANOX, 0x1003), 0 },
+	/* MT27500 Family [ConnectX-3 Virtual Function] */
+	{ PCI_VDEVICE(MELLANOX, 0x1004), MLX4_VF },
+	{ PCI_VDEVICE(MELLANOX, 0x1005), 0 }, /* MT27510 Family */
+	{ PCI_VDEVICE(MELLANOX, 0x1006), 0 }, /* MT27511 Family */
+	{ PCI_VDEVICE(MELLANOX, 0x1007), 0 }, /* MT27520 Family */
+	{ PCI_VDEVICE(MELLANOX, 0x1008), 0 }, /* MT27521 Family */
+	{ PCI_VDEVICE(MELLANOX, 0x1009), 0 }, /* MT27530 Family */
+	{ PCI_VDEVICE(MELLANOX, 0x100a), 0 }, /* MT27531 Family */
+	{ PCI_VDEVICE(MELLANOX, 0x100b), 0 }, /* MT27540 Family */
+	{ PCI_VDEVICE(MELLANOX, 0x100c), 0 }, /* MT27541 Family */
+	{ PCI_VDEVICE(MELLANOX, 0x100d), 0 }, /* MT27550 Family */
+	{ PCI_VDEVICE(MELLANOX, 0x100e), 0 }, /* MT27551 Family */
+	{ PCI_VDEVICE(MELLANOX, 0x100f), 0 }, /* MT27560 Family */
+	{ PCI_VDEVICE(MELLANOX, 0x1010), 0 }, /* MT27561 Family */
 	{ 0, }
 };
 
@@ -1523,6 +2055,12 @@ static int __init mlx4_verify_params(void)
 		return -1;
 	}
 
+	/* Check if module param for ports type has legal combination */
+	if (port_type_array[0] == false && port_type_array[1] == true) {
+		printk(KERN_WARNING "Module parameter configuration ETH/IB is not supported. Switching to default configuration IB/IB\n");
+		port_type_array[0] = true;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index 978688c..0785d9b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -44,28 +44,47 @@
 
 static const u8 zero_gid[16];	/* automatically initialized to 0 */
 
+struct mlx4_mgm {
+	__be32			next_gid_index;
+	__be32			members_count;
+	u32			reserved[2];
+	u8			gid[16];
+	__be32			qp[MLX4_MAX_QP_PER_MGM];
+};
+
+int mlx4_get_mgm_entry_size(struct mlx4_dev *dev)
+{
+	return min((1 << mlx4_log_num_mgm_entry_size), MLX4_MAX_MGM_ENTRY_SIZE);
+}
+
+int mlx4_get_qp_per_mgm(struct mlx4_dev *dev)
+{
+	return 4 * (mlx4_get_mgm_entry_size(dev) / 16 - 2);
+}
+
 static int mlx4_READ_ENTRY(struct mlx4_dev *dev, int index,
 			   struct mlx4_cmd_mailbox *mailbox)
 {
 	return mlx4_cmd_box(dev, 0, mailbox->dma, index, 0, MLX4_CMD_READ_MCG,
-			    MLX4_CMD_TIME_CLASS_A);
+			    MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
 }
 
 static int mlx4_WRITE_ENTRY(struct mlx4_dev *dev, int index,
 			    struct mlx4_cmd_mailbox *mailbox)
 {
 	return mlx4_cmd(dev, mailbox->dma, index, 0, MLX4_CMD_WRITE_MCG,
-			MLX4_CMD_TIME_CLASS_A);
+			MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
 }
 
-static int mlx4_WRITE_PROMISC(struct mlx4_dev *dev, u8 vep_num, u8 port, u8 steer,
+static int mlx4_WRITE_PROMISC(struct mlx4_dev *dev, u8 port, u8 steer,
 			      struct mlx4_cmd_mailbox *mailbox)
 {
 	u32 in_mod;
 
-	in_mod = (u32) vep_num << 24 | (u32) port << 16 | steer << 1;
+	in_mod = (u32) port << 16 | steer << 1;
 	return mlx4_cmd(dev, mailbox->dma, in_mod, 0x1,
-			MLX4_CMD_WRITE_MCG, MLX4_CMD_TIME_CLASS_A);
+			MLX4_CMD_WRITE_MCG, MLX4_CMD_TIME_CLASS_A,
+			MLX4_CMD_NATIVE);
 }
 
 static int mlx4_GID_HASH(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
@@ -75,7 +94,8 @@ static int mlx4_GID_HASH(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
 	int err;
 
 	err = mlx4_cmd_imm(dev, mailbox->dma, &imm, 0, op_mod,
-			   MLX4_CMD_MGID_HASH, MLX4_CMD_TIME_CLASS_A);
+			   MLX4_CMD_MGID_HASH, MLX4_CMD_TIME_CLASS_A,
+			   MLX4_CMD_NATIVE);
 
 	if (!err)
 		*hash = imm;
@@ -102,7 +122,7 @@ static struct mlx4_promisc_qp *get_promisc_qp(struct mlx4_dev *dev, u8 pf_num,
  * Add new entry to steering data structure.
  * All promisc QPs should be added as well
  */
-static int new_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
+static int new_steering_entry(struct mlx4_dev *dev, u8 port,
 			      enum mlx4_steer_type steer,
 			      unsigned int index, u32 qpn)
 {
@@ -115,10 +135,8 @@ static int new_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
 	struct mlx4_promisc_qp *dqp = NULL;
 	u32 prot;
 	int err;
-	u8 pf_num;
 
-	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
-	s_steer = &mlx4_priv(dev)->steer[pf_num];
+	s_steer = &mlx4_priv(dev)->steer[0];
 	new_entry = kzalloc(sizeof *new_entry, GFP_KERNEL);
 	if (!new_entry)
 		return -ENOMEM;
@@ -130,7 +148,7 @@ static int new_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
 	/* If the given qpn is also a promisc qp,
 	 * it should be inserted to duplicates list
 	 */
-	pqp = get_promisc_qp(dev, pf_num, steer, qpn);
+	pqp = get_promisc_qp(dev, 0, steer, qpn);
 	if (pqp) {
 		dqp = kmalloc(sizeof *dqp, GFP_KERNEL);
 		if (!dqp) {
@@ -165,7 +183,7 @@ static int new_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
 		/* don't add already existing qpn */
 		if (pqp->qpn == qpn)
 			continue;
-		if (members_count == MLX4_QP_PER_MGM) {
+		if (members_count == dev->caps.num_qp_per_mgm) {
 			/* out of space */
 			err = -ENOMEM;
 			goto out_mailbox;
@@ -193,7 +211,7 @@ out_alloc:
 }
 
 /* update the data structures with existing steering entry */
-static int existing_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
+static int existing_steering_entry(struct mlx4_dev *dev, u8 port,
 				   enum mlx4_steer_type steer,
 				   unsigned int index, u32 qpn)
 {
@@ -201,12 +219,10 @@ static int existing_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
 	struct mlx4_steer_index *tmp_entry, *entry = NULL;
 	struct mlx4_promisc_qp *pqp;
 	struct mlx4_promisc_qp *dqp;
-	u8 pf_num;
 
-	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
-	s_steer = &mlx4_priv(dev)->steer[pf_num];
+	s_steer = &mlx4_priv(dev)->steer[0];
 
-	pqp = get_promisc_qp(dev, pf_num, steer, qpn);
+	pqp = get_promisc_qp(dev, 0, steer, qpn);
 	if (!pqp)
 		return 0; /* nothing to do */
 
@@ -225,7 +241,7 @@ static int existing_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
 	 * we need to add it as a duplicate to this entry
 	 * for future references */
 	list_for_each_entry(dqp, &entry->duplicates, list) {
-		if (qpn == dqp->qpn)
+		if (qpn == pqp->qpn)
 			return 0; /* qp is already duplicated */
 	}
 
@@ -241,20 +257,18 @@ static int existing_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
 
 /* Check whether a qpn is a duplicate on steering entry
  * If so, it should not be removed from mgm */
-static bool check_duplicate_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
+static bool check_duplicate_entry(struct mlx4_dev *dev, u8 port,
 				  enum mlx4_steer_type steer,
 				  unsigned int index, u32 qpn)
 {
 	struct mlx4_steer *s_steer;
 	struct mlx4_steer_index *tmp_entry, *entry = NULL;
 	struct mlx4_promisc_qp *dqp, *tmp_dqp;
-	u8 pf_num;
 
-	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
-	s_steer = &mlx4_priv(dev)->steer[pf_num];
+	s_steer = &mlx4_priv(dev)->steer[0];
 
 	/* if qp is not promisc, it cannot be duplicated */
-	if (!get_promisc_qp(dev, pf_num, steer, qpn))
+	if (!get_promisc_qp(dev, 0, steer, qpn))
 		return false;
 
 	/* The qp is promisc qp so it is a duplicate on this index
@@ -279,7 +293,7 @@ static bool check_duplicate_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
 }
 
 /* I a steering entry contains only promisc QPs, it can be removed. */
-static bool can_remove_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
+static bool can_remove_steering_entry(struct mlx4_dev *dev, u8 port,
 				      enum mlx4_steer_type steer,
 				      unsigned int index, u32 tqpn)
 {
@@ -291,10 +305,8 @@ static bool can_remove_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
 	u32 members_count;
 	bool ret = false;
 	int i;
-	u8 pf_num;
 
-	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
-	s_steer = &mlx4_priv(dev)->steer[pf_num];
+	s_steer = &mlx4_priv(dev)->steer[0];
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
@@ -306,7 +318,7 @@ static bool can_remove_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
 	members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
 	for (i = 0;  i < members_count; i++) {
 		qpn = be32_to_cpu(mgm->qp[i]) & MGM_QPN_MASK;
-		if (!get_promisc_qp(dev, pf_num, steer, qpn) && qpn != tqpn) {
+		if (!get_promisc_qp(dev, 0, steer, qpn) && qpn != tqpn) {
 			/* the qp is not promisc, the entry can't be removed */
 			goto out;
 		}
@@ -332,7 +344,7 @@ out:
 	return ret;
 }
 
-static int add_promisc_qp(struct mlx4_dev *dev, u8 vep_num, u8 port,
+static int add_promisc_qp(struct mlx4_dev *dev, u8 port,
 			  enum mlx4_steer_type steer, u32 qpn)
 {
 	struct mlx4_steer *s_steer;
@@ -347,14 +359,13 @@ static int add_promisc_qp(struct mlx4_dev *dev, u8 vep_num, u8 port,
 	bool found;
 	int last_index;
 	int err;
-	u8 pf_num;
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
-	s_steer = &mlx4_priv(dev)->steer[pf_num];
+
+	s_steer = &mlx4_priv(dev)->steer[0];
 
 	mutex_lock(&priv->mcg_table.mutex);
 
-	if (get_promisc_qp(dev, pf_num, steer, qpn)) {
+	if (get_promisc_qp(dev, 0, steer, qpn)) {
 		err = 0;  /* Noting to do, already exists */
 		goto out_mutex;
 	}
@@ -397,7 +408,7 @@ static int add_promisc_qp(struct mlx4_dev *dev, u8 vep_num, u8 port,
 		}
 		if (!found) {
 			/* Need to add the qpn to mgm */
-			if (members_count == MLX4_QP_PER_MGM) {
+			if (members_count == dev->caps.num_qp_per_mgm) {
 				/* entry is full */
 				err = -ENOMEM;
 				goto out_mailbox;
@@ -420,7 +431,7 @@ static int add_promisc_qp(struct mlx4_dev *dev, u8 vep_num, u8 port,
 		mgm->qp[members_count++] = cpu_to_be32(dqp->qpn & MGM_QPN_MASK);
 	mgm->members_count = cpu_to_be32(members_count | MLX4_PROT_ETH << 30);
 
-	err = mlx4_WRITE_PROMISC(dev, vep_num, port, steer, mailbox);
+	err = mlx4_WRITE_PROMISC(dev, port, steer, mailbox);
 	if (err)
 		goto out_list;
 
@@ -439,7 +450,7 @@ out_mutex:
 	return err;
 }
 
-static int remove_promisc_qp(struct mlx4_dev *dev, u8 vep_num, u8 port,
+static int remove_promisc_qp(struct mlx4_dev *dev, u8 port,
 			     enum mlx4_steer_type steer, u32 qpn)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -454,13 +465,11 @@ static int remove_promisc_qp(struct mlx4_dev *dev, u8 vep_num, u8 port,
 	bool back_to_list = false;
 	int loc, i;
 	int err;
-	u8 pf_num;
 
-	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
-	s_steer = &mlx4_priv(dev)->steer[pf_num];
+	s_steer = &mlx4_priv(dev)->steer[0];
 	mutex_lock(&priv->mcg_table.mutex);
 
-	pqp = get_promisc_qp(dev, pf_num, steer, qpn);
+	pqp = get_promisc_qp(dev, 0, steer, qpn);
 	if (unlikely(!pqp)) {
 		mlx4_warn(dev, "QP %x is not promiscuous QP\n", qpn);
 		/* nothing to do */
@@ -479,12 +488,13 @@ static int remove_promisc_qp(struct mlx4_dev *dev, u8 vep_num, u8 port,
 		goto out_list;
 	}
 	mgm = mailbox->buf;
+	memset(mgm, 0, sizeof *mgm);
 	members_count = 0;
 	list_for_each_entry(dqp, &s_steer->promisc_qps[steer], list)
 		mgm->qp[members_count++] = cpu_to_be32(dqp->qpn & MGM_QPN_MASK);
 	mgm->members_count = cpu_to_be32(members_count | MLX4_PROT_ETH << 30);
 
-	err = mlx4_WRITE_PROMISC(dev, vep_num, port, steer, mailbox);
+	err = mlx4_WRITE_PROMISC(dev, port, steer, mailbox);
 	if (err)
 		goto out_mailbox;
 
@@ -649,12 +659,13 @@ int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 		}
 		index += dev->caps.num_mgms;
 
+		new_entry = 1;
 		memset(mgm, 0, sizeof *mgm);
 		memcpy(mgm->gid, gid, 16);
 	}
 
 	members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
-	if (members_count == MLX4_QP_PER_MGM) {
+	if (members_count == dev->caps.num_qp_per_mgm) {
 		mlx4_err(dev, "MGM at index %x is full.\n", index);
 		err = -ENOMEM;
 		goto out;
@@ -696,9 +707,9 @@ out:
 	if (prot == MLX4_PROT_ETH) {
 		/* manage the steering entry for promisc mode */
 		if (new_entry)
-			new_steering_entry(dev, 0, port, steer, index, qp->qpn);
+			new_steering_entry(dev, port, steer, index, qp->qpn);
 		else
-			existing_steering_entry(dev, 0, port, steer,
+			existing_steering_entry(dev, port, steer,
 						index, qp->qpn);
 	}
 	if (err && link && index != -1) {
@@ -749,7 +760,7 @@ int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 
 	/* if this pq is also a promisc qp, it shouldn't be removed */
 	if (prot == MLX4_PROT_ETH &&
-	    check_duplicate_entry(dev, 0, port, steer, index, qp->qpn))
+	    check_duplicate_entry(dev, port, steer, index, qp->qpn))
 		goto out;
 
 	members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
@@ -769,7 +780,8 @@ int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	mgm->qp[i - 1]     = 0;
 
 	if (prot == MLX4_PROT_ETH)
-		removed_entry = can_remove_steering_entry(dev, 0, port, steer, index, qp->qpn);
+		removed_entry = can_remove_steering_entry(dev, port, steer,
+								index, qp->qpn);
 	if (i != 1 && (prot != MLX4_PROT_ETH || !removed_entry)) {
 		err = mlx4_WRITE_ENTRY(dev, index, mailbox);
 		goto out;
@@ -828,6 +840,34 @@ out:
 	return err;
 }
 
+static int mlx4_QP_ATTACH(struct mlx4_dev *dev, struct mlx4_qp *qp,
+			  u8 gid[16], u8 attach, u8 block_loopback,
+			  enum mlx4_protocol prot)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	int err = 0;
+	int qpn;
+
+	if (!mlx4_is_mfunc(dev))
+		return -EBADF;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+
+	memcpy(mailbox->buf, gid, 16);
+	qpn = qp->qpn;
+	qpn |= (prot << 28);
+	if (attach && block_loopback)
+		qpn |= (1 << 31);
+
+	err = mlx4_cmd(dev, mailbox->dma, qpn, attach,
+		       MLX4_CMD_QP_ATTACH, MLX4_CMD_TIME_CLASS_A,
+		       MLX4_CMD_WRAPPED);
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
 
 int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 			  int block_mcast_loopback, enum mlx4_protocol prot)
@@ -843,9 +883,12 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	if (prot == MLX4_PROT_ETH)
 		gid[7] |= (steer << 1);
 
-	return mlx4_qp_attach_common(dev, qp, gid,
-				     block_mcast_loopback, prot,
-				     steer);
+	if (mlx4_is_mfunc(dev))
+		return mlx4_QP_ATTACH(dev, qp, gid, 1,
+					block_mcast_loopback, prot);
+
+	return mlx4_qp_attach_common(dev, qp, gid, block_mcast_loopback,
+					prot, steer);
 }
 EXPORT_SYMBOL_GPL(mlx4_multicast_attach);
 
@@ -860,22 +903,90 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 			!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER))
 		return 0;
 
-	if (prot == MLX4_PROT_ETH) {
+	if (prot == MLX4_PROT_ETH)
 		gid[7] |= (steer << 1);
-	}
+
+	if (mlx4_is_mfunc(dev))
+		return mlx4_QP_ATTACH(dev, qp, gid, 0, 0, prot);
 
 	return mlx4_qp_detach_common(dev, qp, gid, prot, steer);
 }
 EXPORT_SYMBOL_GPL(mlx4_multicast_detach);
 
+int mlx4_unicast_attach(struct mlx4_dev *dev,
+			struct mlx4_qp *qp, u8 gid[16],
+			int block_mcast_loopback, enum mlx4_protocol prot)
+{
+	if (prot == MLX4_PROT_ETH &&
+			!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER))
+		return 0;
+
+	if (prot == MLX4_PROT_ETH)
+		gid[7] |= (MLX4_UC_STEER << 1);
+
+	if (mlx4_is_mfunc(dev))
+		return mlx4_QP_ATTACH(dev, qp, gid, 1,
+					block_mcast_loopback, prot);
+
+	return mlx4_qp_attach_common(dev, qp, gid, block_mcast_loopback,
+					prot, MLX4_UC_STEER);
+}
+EXPORT_SYMBOL_GPL(mlx4_unicast_attach);
+
+int mlx4_unicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp,
+			       u8 gid[16], enum mlx4_protocol prot)
+{
+	if (prot == MLX4_PROT_ETH &&
+			!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER))
+		return 0;
+
+	if (prot == MLX4_PROT_ETH)
+		gid[7] |= (MLX4_UC_STEER << 1);
+
+	if (mlx4_is_mfunc(dev))
+		return mlx4_QP_ATTACH(dev, qp, gid, 0, 0, prot);
+
+	return mlx4_qp_detach_common(dev, qp, gid, prot, MLX4_UC_STEER);
+}
+EXPORT_SYMBOL_GPL(mlx4_unicast_detach);
+
+int mlx4_PROMISC_wrapper(struct mlx4_dev *dev, int slave,
+			 struct mlx4_vhcr *vhcr,
+			 struct mlx4_cmd_mailbox *inbox,
+			 struct mlx4_cmd_mailbox *outbox,
+			 struct mlx4_cmd_info *cmd)
+{
+	u32 qpn = (u32) vhcr->in_param & 0xffffffff;
+	u8 port = vhcr->in_param >> 62;
+	enum mlx4_steer_type steer = vhcr->in_modifier;
+
+	/* Promiscuous unicast is not allowed in mfunc */
+	if (mlx4_is_mfunc(dev) && steer == MLX4_UC_STEER)
+		return 0;
+
+	if (vhcr->op_modifier)
+		return add_promisc_qp(dev, port, steer, qpn);
+	else
+		return remove_promisc_qp(dev, port, steer, qpn);
+}
+
+static int mlx4_PROMISC(struct mlx4_dev *dev, u32 qpn,
+			enum mlx4_steer_type steer, u8 add, u8 port)
+{
+	return mlx4_cmd(dev, (u64) qpn | (u64) port << 62, (u32) steer, add,
+			MLX4_CMD_PROMISC, MLX4_CMD_TIME_CLASS_A,
+			MLX4_CMD_WRAPPED);
+}
 
 int mlx4_multicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port)
 {
 	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER))
 		return 0;
 
+	if (mlx4_is_mfunc(dev))
+		return mlx4_PROMISC(dev, qpn, MLX4_MC_STEER, 1, port);
 
-	return add_promisc_qp(dev, 0, port, MLX4_MC_STEER, qpn);
+	return add_promisc_qp(dev, port, MLX4_MC_STEER, qpn);
 }
 EXPORT_SYMBOL_GPL(mlx4_multicast_promisc_add);
 
@@ -884,8 +995,10 @@ int mlx4_multicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port)
 	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER))
 		return 0;
 
+	if (mlx4_is_mfunc(dev))
+		return mlx4_PROMISC(dev, qpn, MLX4_MC_STEER, 0, port);
 
-	return remove_promisc_qp(dev, 0, port, MLX4_MC_STEER, qpn);
+	return remove_promisc_qp(dev, port, MLX4_MC_STEER, qpn);
 }
 EXPORT_SYMBOL_GPL(mlx4_multicast_promisc_remove);
 
@@ -894,8 +1007,10 @@ int mlx4_unicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port)
 	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER))
 		return 0;
 
+	if (mlx4_is_mfunc(dev))
+		return mlx4_PROMISC(dev, qpn, MLX4_UC_STEER, 1, port);
 
-	return add_promisc_qp(dev, 0, port, MLX4_UC_STEER, qpn);
+	return add_promisc_qp(dev, port, MLX4_UC_STEER, qpn);
 }
 EXPORT_SYMBOL_GPL(mlx4_unicast_promisc_add);
 
@@ -904,7 +1019,10 @@ int mlx4_unicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port)
 	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER))
 		return 0;
 
-	return remove_promisc_qp(dev, 0, port, MLX4_UC_STEER, qpn);
+	if (mlx4_is_mfunc(dev))
+		return mlx4_PROMISC(dev, qpn, MLX4_UC_STEER, 0, port);
+
+	return remove_promisc_qp(dev, port, MLX4_UC_STEER, qpn);
 }
 EXPORT_SYMBOL_GPL(mlx4_unicast_promisc_remove);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 5dfa68f..a80121a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -46,21 +46,25 @@
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/driver.h>
 #include <linux/mlx4/doorbell.h>
+#include <linux/mlx4/cmd.h>
 
 #define DRV_NAME	"mlx4_core"
-#define DRV_VERSION	"1.0"
-#define DRV_RELDATE	"July 14, 2011"
+#define PFX		DRV_NAME ": "
+#define DRV_VERSION	"1.1"
+#define DRV_RELDATE	"Dec, 2011"
 
 enum {
 	MLX4_HCR_BASE		= 0x80680,
 	MLX4_HCR_SIZE		= 0x0001c,
-	MLX4_CLR_INT_SIZE	= 0x00008
+	MLX4_CLR_INT_SIZE	= 0x00008,
+	MLX4_SLAVE_COMM_BASE	= 0x0,
+	MLX4_COMM_PAGESIZE	= 0x1000
 };
 
 enum {
-	MLX4_MGM_ENTRY_SIZE	=  0x100,
-	MLX4_QP_PER_MGM		= 4 * (MLX4_MGM_ENTRY_SIZE / 16 - 2),
-	MLX4_MTT_ENTRY_PER_SEG	= 8
+	MLX4_MAX_MGM_ENTRY_SIZE = 0x1000,
+	MLX4_MAX_QP_PER_MGM	= 4 * (MLX4_MAX_MGM_ENTRY_SIZE / 16 - 2),
+	MLX4_MTT_ENTRY_PER_SEG	= 8,
 };
 
 enum {
@@ -80,6 +84,94 @@ enum {
 	MLX4_NUM_CMPTS		= MLX4_CMPT_NUM_TYPE << MLX4_CMPT_SHIFT
 };
 
+enum mlx4_mr_state {
+	MLX4_MR_DISABLED = 0,
+	MLX4_MR_EN_HW,
+	MLX4_MR_EN_SW
+};
+
+#define MLX4_COMM_TIME		10000
+enum {
+	MLX4_COMM_CMD_RESET,
+	MLX4_COMM_CMD_VHCR0,
+	MLX4_COMM_CMD_VHCR1,
+	MLX4_COMM_CMD_VHCR2,
+	MLX4_COMM_CMD_VHCR_EN,
+	MLX4_COMM_CMD_VHCR_POST,
+	MLX4_COMM_CMD_FLR = 254
+};
+
+/*The flag indicates that the slave should delay the RESET cmd*/
+#define MLX4_DELAY_RESET_SLAVE 0xbbbbbbb
+/*indicates how many retries will be done if we are in the middle of FLR*/
+#define NUM_OF_RESET_RETRIES	10
+#define SLEEP_TIME_IN_RESET	(2 * 1000)
+enum mlx4_resource {
+	RES_QP,
+	RES_CQ,
+	RES_SRQ,
+	RES_XRCD,
+	RES_MPT,
+	RES_MTT,
+	RES_MAC,
+	RES_VLAN,
+	RES_EQ,
+	RES_COUNTER,
+	MLX4_NUM_OF_RESOURCE_TYPE
+};
+
+enum mlx4_alloc_mode {
+	RES_OP_RESERVE,
+	RES_OP_RESERVE_AND_MAP,
+	RES_OP_MAP_ICM,
+};
+
+
+/*
+ *Virtual HCR structures.
+ * mlx4_vhcr is the sw representation, in machine endianess
+ *
+ * mlx4_vhcr_cmd is the formalized structure, the one that is passed
+ * to FW to go through communication channel.
+ * It is big endian, and has the same structure as the physical HCR
+ * used by command interface
+ */
+struct mlx4_vhcr {
+	u64	in_param;
+	u64	out_param;
+	u32	in_modifier;
+	u32	errno;
+	u16	op;
+	u16	token;
+	u8	op_modifier;
+	u8	e_bit;
+};
+
+struct mlx4_vhcr_cmd {
+	__be64 in_param;
+	__be32 in_modifier;
+	__be64 out_param;
+	__be16 token;
+	u16 reserved;
+	u8 status;
+	u8 flags;
+	__be16 opcode;
+};
+
+struct mlx4_cmd_info {
+	u16 opcode;
+	bool has_inbox;
+	bool has_outbox;
+	bool out_is_imm;
+	bool encode_slave_id;
+	int (*verify)(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr,
+		      struct mlx4_cmd_mailbox *inbox);
+	int (*wrapper)(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr,
+		       struct mlx4_cmd_mailbox *inbox,
+		       struct mlx4_cmd_mailbox *outbox,
+		       struct mlx4_cmd_info *cmd);
+};
+
 #ifdef CONFIG_MLX4_DEBUG
 extern int mlx4_debug_level;
 #else /* CONFIG_MLX4_DEBUG */
@@ -99,6 +191,12 @@ do {									\
 #define mlx4_warn(mdev, format, arg...) \
 	dev_warn(&mdev->pdev->dev, format, ##arg)
 
+extern int mlx4_log_num_mgm_entry_size;
+extern int log_mtts_per_seg;
+
+#define MLX4_MAX_NUM_SLAVES	(MLX4_MAX_NUM_PF + MLX4_MAX_NUM_VF)
+#define ALL_SLAVES 0xff
+
 struct mlx4_bitmap {
 	u32			last;
 	u32			top;
@@ -130,6 +228,147 @@ struct mlx4_icm_table {
 	struct mlx4_icm	      **icm;
 };
 
+/*
+ * Must be packed because mtt_seg is 64 bits but only aligned to 32 bits.
+ */
+struct mlx4_mpt_entry {
+	__be32 flags;
+	__be32 qpn;
+	__be32 key;
+	__be32 pd_flags;
+	__be64 start;
+	__be64 length;
+	__be32 lkey;
+	__be32 win_cnt;
+	u8	reserved1[3];
+	u8	mtt_rep;
+	__be64 mtt_addr;
+	__be32 mtt_sz;
+	__be32 entity_size;
+	__be32 first_byte_offset;
+} __packed;
+
+/*
+ * Must be packed because start is 64 bits but only aligned to 32 bits.
+ */
+struct mlx4_eq_context {
+	__be32			flags;
+	u16			reserved1[3];
+	__be16			page_offset;
+	u8			log_eq_size;
+	u8			reserved2[4];
+	u8			eq_period;
+	u8			reserved3;
+	u8			eq_max_count;
+	u8			reserved4[3];
+	u8			intr;
+	u8			log_page_size;
+	u8			reserved5[2];
+	u8			mtt_base_addr_h;
+	__be32			mtt_base_addr_l;
+	u32			reserved6[2];
+	__be32			consumer_index;
+	__be32			producer_index;
+	u32			reserved7[4];
+};
+
+struct mlx4_cq_context {
+	__be32			flags;
+	u16			reserved1[3];
+	__be16			page_offset;
+	__be32			logsize_usrpage;
+	__be16			cq_period;
+	__be16			cq_max_count;
+	u8			reserved2[3];
+	u8			comp_eqn;
+	u8			log_page_size;
+	u8			reserved3[2];
+	u8			mtt_base_addr_h;
+	__be32			mtt_base_addr_l;
+	__be32			last_notified_index;
+	__be32			solicit_producer_index;
+	__be32			consumer_index;
+	__be32			producer_index;
+	u32			reserved4[2];
+	__be64			db_rec_addr;
+};
+
+struct mlx4_srq_context {
+	__be32			state_logsize_srqn;
+	u8			logstride;
+	u8			reserved1;
+	__be16			xrcd;
+	__be32			pg_offset_cqn;
+	u32			reserved2;
+	u8			log_page_size;
+	u8			reserved3[2];
+	u8			mtt_base_addr_h;
+	__be32			mtt_base_addr_l;
+	__be32			pd;
+	__be16			limit_watermark;
+	__be16			wqe_cnt;
+	u16			reserved4;
+	__be16			wqe_counter;
+	u32			reserved5;
+	__be64			db_rec_addr;
+};
+
+struct mlx4_eqe {
+	u8			reserved1;
+	u8			type;
+	u8			reserved2;
+	u8			subtype;
+	union {
+		u32		raw[6];
+		struct {
+			__be32	cqn;
+		} __packed comp;
+		struct {
+			u16	reserved1;
+			__be16	token;
+			u32	reserved2;
+			u8	reserved3[3];
+			u8	status;
+			__be64	out_param;
+		} __packed cmd;
+		struct {
+			__be32	qpn;
+		} __packed qp;
+		struct {
+			__be32	srqn;
+		} __packed srq;
+		struct {
+			__be32	cqn;
+			u32	reserved1;
+			u8	reserved2[3];
+			u8	syndrome;
+		} __packed cq_err;
+		struct {
+			u32	reserved1[2];
+			__be32	port;
+		} __packed port_change;
+		struct {
+			#define COMM_CHANNEL_BIT_ARRAY_SIZE	4
+			u32 reserved;
+			u32 bit_vec[COMM_CHANNEL_BIT_ARRAY_SIZE];
+		} __packed comm_channel_arm;
+		struct {
+			u8	port;
+			u8	reserved[3];
+			__be64	mac;
+		} __packed mac_update;
+		struct {
+			u8	port;
+		} __packed sw_event;
+		struct {
+			__be32	slave_id;
+		} __packed flr_event;
+	}			event;
+	u8			slave_id;
+	u8			reserved3[2];
+	u8			owner;
+} __packed;
+
 struct mlx4_eq {
 	struct mlx4_dev	       *dev;
 	void __iomem	       *doorbell;
@@ -142,6 +381,18 @@ struct mlx4_eq {
 	struct mlx4_mtt		mtt;
 };
 
+struct mlx4_slave_eqe {
+	u8 type;
+	u8 port;
+	u32 param;
+};
+
+struct mlx4_slave_event_eq_info {
+	u32 eqn;
+	u16 token;
+	u64 event_type;
+};
+
 struct mlx4_profile {
 	int			num_qp;
 	int			rdmarc_per_qp;
@@ -155,16 +406,37 @@ struct mlx4_profile {
 struct mlx4_fw {
 	u64			clr_int_base;
 	u64			catas_offset;
+	u64			comm_base;
 	struct mlx4_icm	       *fw_icm;
 	struct mlx4_icm	       *aux_icm;
 	u32			catas_size;
 	u16			fw_pages;
 	u8			clr_int_bar;
 	u8			catas_bar;
+	u8			comm_bar;
 };
 
-#define MGM_QPN_MASK       0x00FFFFFF
-#define MGM_BLCK_LB_BIT    30
+struct mlx4_comm {
+	u32			slave_write;
+	u32			slave_read;
+};
+
+enum {
+	MLX4_MCAST_CONFIG       = 0,
+	MLX4_MCAST_DISABLE      = 1,
+	MLX4_MCAST_ENABLE       = 2,
+};
+
+#define VLAN_FLTR_SIZE	128
+
+struct mlx4_vlan_fltr {
+	__be32 entry[VLAN_FLTR_SIZE];
+};
+
+struct mlx4_mcast_entry {
+	struct list_head list;
+	u64 addr;
+};
 
 struct mlx4_promisc_qp {
 	struct list_head list;
@@ -177,19 +449,87 @@ struct mlx4_steer_index {
 	struct list_head duplicates;
 };
 
-struct mlx4_mgm {
-	__be32			next_gid_index;
-	__be32			members_count;
-	u32			reserved[2];
-	u8			gid[16];
-	__be32			qp[MLX4_QP_PER_MGM];
+struct mlx4_slave_state {
+	u8 comm_toggle;
+	u8 last_cmd;
+	u8 init_port_mask;
+	bool active;
+	u8 function;
+	dma_addr_t vhcr_dma;
+	u16 mtu[MLX4_MAX_PORTS + 1];
+	__be32 ib_cap_mask[MLX4_MAX_PORTS + 1];
+	struct mlx4_slave_eqe eq[MLX4_MFUNC_MAX_EQES];
+	struct list_head mcast_filters[MLX4_MAX_PORTS + 1];
+	struct mlx4_vlan_fltr *vlan_filter[MLX4_MAX_PORTS + 1];
+	struct mlx4_slave_event_eq_info event_eq;
+	u16 eq_pi;
+	u16 eq_ci;
+	spinlock_t lock;
+	/*initialized via the kzalloc*/
+	u8 is_slave_going_down;
+	u32 cookie;
+};
+
+struct slave_list {
+	struct mutex mutex;
+	struct list_head res_list[MLX4_NUM_OF_RESOURCE_TYPE];
+};
+
+struct mlx4_resource_tracker {
+	spinlock_t lock;
+	/* tree for each resources */
+	struct radix_tree_root res_tree[MLX4_NUM_OF_RESOURCE_TYPE];
+	/* num_of_slave's lists, one per slave */
+	struct slave_list *slave_list;
+};
+
+#define SLAVE_EVENT_EQ_SIZE	128
+struct mlx4_slave_event_eq {
+	u32 eqn;
+	u32 cons;
+	u32 prod;
+	struct mlx4_eqe event_eqe[SLAVE_EVENT_EQ_SIZE];
+};
+
+struct mlx4_master_qp0_state {
+	int proxy_qp0_active;
+	int qp0_active;
+	int port_active;
+};
+
+struct mlx4_mfunc_master_ctx {
+	struct mlx4_slave_state *slave_state;
+	struct mlx4_master_qp0_state qp0_state[MLX4_MAX_PORTS + 1];
+	int			init_port_ref[MLX4_MAX_PORTS + 1];
+	u16			max_mtu[MLX4_MAX_PORTS + 1];
+	int			disable_mcast_ref[MLX4_MAX_PORTS + 1];
+	struct mlx4_resource_tracker res_tracker;
+	struct workqueue_struct *comm_wq;
+	struct work_struct	comm_work;
+	struct work_struct	slave_event_work;
+	struct work_struct	slave_flr_event_work;
+	spinlock_t		slave_state_lock;
+	__be32			comm_arm_bit_vector[4];
+	struct mlx4_eqe		cmd_eqe;
+	struct mlx4_slave_event_eq slave_eq;
+	struct mutex		gen_eqe_mutex[MLX4_MFUNC_MAX];
+};
+
+struct mlx4_mfunc {
+	struct mlx4_comm __iomem       *comm;
+	struct mlx4_vhcr_cmd	       *vhcr;
+	dma_addr_t			vhcr_dma;
+
+	struct mlx4_mfunc_master_ctx	master;
 };
+
 struct mlx4_cmd {
 	struct pci_pool	       *pool;
 	void __iomem	       *hcr;
 	struct mutex		hcr_mutex;
 	struct semaphore	poll_sem;
 	struct semaphore	event_sem;
+	struct semaphore	slave_sem;
 	int			max_cmds;
 	spinlock_t		context_lock;
 	int			free_head;
@@ -197,6 +537,7 @@ struct mlx4_cmd {
 	u16			token_mask;
 	u8			use_events;
 	u8			toggle;
+	u8			comm_toggle;
 };
 
 struct mlx4_uar_table {
@@ -287,6 +628,48 @@ struct mlx4_vlan_table {
 	int			max;
 };
 
+#define SET_PORT_GEN_ALL_VALID		0x7
+#define SET_PORT_PROMISC_SHIFT		31
+#define SET_PORT_MC_PROMISC_SHIFT	30
+
+enum {
+	MCAST_DIRECT_ONLY	= 0,
+	MCAST_DIRECT		= 1,
+	MCAST_DEFAULT		= 2
+};
+
+
+struct mlx4_set_port_general_context {
+	u8 reserved[3];
+	u8 flags;
+	u16 reserved2;
+	__be16 mtu;
+	u8 pptx;
+	u8 pfctx;
+	u16 reserved3;
+	u8 pprx;
+	u8 pfcrx;
+	u16 reserved4;
+};
+
+struct mlx4_set_port_rqp_calc_context {
+	__be32 base_qpn;
+	u8 rererved;
+	u8 n_mac;
+	u8 n_vlan;
+	u8 n_prio;
+	u8 reserved2[3];
+	u8 mac_miss;
+	u8 intra_no_vlan;
+	u8 no_vlan;
+	u8 intra_vlan_miss;
+	u8 vlan_miss;
+	u8 reserved3[3];
+	u8 no_vlan_prio;
+	__be32 promisc;
+	__be32 mcast;
+};
+
 struct mlx4_mac_entry {
 	u64 mac;
 };
@@ -333,6 +716,7 @@ struct mlx4_priv {
 
 	struct mlx4_fw		fw;
 	struct mlx4_cmd		cmd;
+	struct mlx4_mfunc	mfunc;
 
 	struct mlx4_bitmap	pd_bitmap;
 	struct mlx4_bitmap	xrcd_bitmap;
@@ -359,6 +743,7 @@ struct mlx4_priv {
 	struct list_head	bf_list;
 	struct mutex		bf_mutex;
 	struct io_mapping	*bf_mapping;
+	int			reserved_mtts;
 };
 
 static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev)
@@ -403,6 +788,62 @@ void mlx4_cleanup_cq_table(struct mlx4_dev *dev);
 void mlx4_cleanup_qp_table(struct mlx4_dev *dev);
 void mlx4_cleanup_srq_table(struct mlx4_dev *dev);
 void mlx4_cleanup_mcg_table(struct mlx4_dev *dev);
+int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn);
+void __mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn);
+int __mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn);
+void __mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn);
+int __mlx4_srq_alloc_icm(struct mlx4_dev *dev, int *srqn);
+void __mlx4_srq_free_icm(struct mlx4_dev *dev, int srqn);
+int __mlx4_mr_reserve(struct mlx4_dev *dev);
+void __mlx4_mr_release(struct mlx4_dev *dev, u32 index);
+int __mlx4_mr_alloc_icm(struct mlx4_dev *dev, u32 index);
+void __mlx4_mr_free_icm(struct mlx4_dev *dev, u32 index);
+u32 __mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order);
+void __mlx4_free_mtt_range(struct mlx4_dev *dev, u32 first_seg, int order);
+
+int mlx4_WRITE_MTT_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd);
+int mlx4_SYNC_TPT_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd);
+int mlx4_SW2HW_MPT_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd);
+int mlx4_HW2SW_MPT_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd);
+int mlx4_QUERY_MPT_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd);
+int mlx4_SW2HW_EQ_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd);
+int mlx4_DMA_wrapper(struct mlx4_dev *dev, int slave,
+		     struct mlx4_vhcr *vhcr,
+		     struct mlx4_cmd_mailbox *inbox,
+		     struct mlx4_cmd_mailbox *outbox,
+		     struct mlx4_cmd_info *cmd);
+int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
+			    int *base);
+void __mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt);
+int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac);
+void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac);
+int __mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac);
+int __mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
+		     int start_index, int npages, u64 *page_list);
 
 void mlx4_start_catas_poll(struct mlx4_dev *dev);
 void mlx4_stop_catas_poll(struct mlx4_dev *dev);
@@ -419,13 +860,113 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 		      struct mlx4_profile *request,
 		      struct mlx4_dev_cap *dev_cap,
 		      struct mlx4_init_hca_param *init_hca);
+void mlx4_master_comm_channel(struct work_struct *work);
+void mlx4_gen_slave_eqe(struct work_struct *work);
+void mlx4_master_handle_slave_flr(struct work_struct *work);
+
+int mlx4_ALLOC_RES_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd);
+int mlx4_FREE_RES_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd);
+int mlx4_MAP_EQ_wrapper(struct mlx4_dev *dev, int slave,
+			struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox,
+			struct mlx4_cmd_mailbox *outbox,
+			struct mlx4_cmd_info *cmd);
+int mlx4_COMM_INT_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd);
+int mlx4_HW2SW_EQ_wrapper(struct mlx4_dev *dev, int slave,
+			    struct mlx4_vhcr *vhcr,
+			    struct mlx4_cmd_mailbox *inbox,
+			    struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd);
+int mlx4_QUERY_EQ_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd);
+int mlx4_SW2HW_CQ_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd);
+int mlx4_HW2SW_CQ_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd);
+int mlx4_QUERY_CQ_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd);
+int mlx4_MODIFY_CQ_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd);
+int mlx4_SW2HW_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd);
+int mlx4_HW2SW_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd);
+int mlx4_QUERY_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd);
+int mlx4_ARM_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+			 struct mlx4_vhcr *vhcr,
+			 struct mlx4_cmd_mailbox *inbox,
+			 struct mlx4_cmd_mailbox *outbox,
+			 struct mlx4_cmd_info *cmd);
+int mlx4_GEN_QP_wrapper(struct mlx4_dev *dev, int slave,
+			struct mlx4_vhcr *vhcr,
+			struct mlx4_cmd_mailbox *inbox,
+			struct mlx4_cmd_mailbox *outbox,
+			struct mlx4_cmd_info *cmd);
+int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
+			     struct mlx4_vhcr *vhcr,
+			     struct mlx4_cmd_mailbox *inbox,
+			     struct mlx4_cmd_mailbox *outbox,
+			     struct mlx4_cmd_info *cmd);
+int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave,
+			     struct mlx4_vhcr *vhcr,
+			     struct mlx4_cmd_mailbox *inbox,
+			     struct mlx4_cmd_mailbox *outbox,
+			     struct mlx4_cmd_info *cmd);
+int mlx4_2RST_QP_wrapper(struct mlx4_dev *dev, int slave,
+			 struct mlx4_vhcr *vhcr,
+			 struct mlx4_cmd_mailbox *inbox,
+			 struct mlx4_cmd_mailbox *outbox,
+			 struct mlx4_cmd_info *cmd);
+
+int mlx4_GEN_EQE(struct mlx4_dev *dev, int slave, struct mlx4_eqe *eqe);
 
 int mlx4_cmd_init(struct mlx4_dev *dev);
 void mlx4_cmd_cleanup(struct mlx4_dev *dev);
+int mlx4_multi_func_init(struct mlx4_dev *dev);
+void mlx4_multi_func_cleanup(struct mlx4_dev *dev);
 void mlx4_cmd_event(struct mlx4_dev *dev, u16 token, u8 status, u64 out_param);
 int mlx4_cmd_use_events(struct mlx4_dev *dev);
 void mlx4_cmd_use_polling(struct mlx4_dev *dev);
 
+int mlx4_comm_cmd(struct mlx4_dev *dev, u8 cmd, u16 param,
+		  unsigned long timeout);
+
 void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn);
 void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type);
 
@@ -452,12 +993,113 @@ void mlx4_init_mac_table(struct mlx4_dev *dev, struct mlx4_mac_table *table);
 void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table);
 
 int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port);
+/* resource tracker functions*/
+int mlx4_get_slave_from_resource_id(struct mlx4_dev *dev,
+				    enum mlx4_resource resource_type,
+				    int resource_id, int *slave);
+void mlx4_delete_all_resources_for_slave(struct mlx4_dev *dev, int slave_id);
+int mlx4_init_resource_tracker(struct mlx4_dev *dev);
+
+void mlx4_free_resource_tracker(struct mlx4_dev *dev);
+
+int mlx4_SET_PORT_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd);
+int mlx4_INIT_PORT_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd);
+int mlx4_CLOSE_PORT_wrapper(struct mlx4_dev *dev, int slave,
+			    struct mlx4_vhcr *vhcr,
+			    struct mlx4_cmd_mailbox *inbox,
+			    struct mlx4_cmd_mailbox *outbox,
+			    struct mlx4_cmd_info *cmd);
+int mlx4_QUERY_PORT_wrapper(struct mlx4_dev *dev, int slave,
+			    struct mlx4_vhcr *vhcr,
+			    struct mlx4_cmd_mailbox *inbox,
+			    struct mlx4_cmd_mailbox *outbox,
+			    struct mlx4_cmd_info *cmd);
 int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps);
 int mlx4_check_ext_port_caps(struct mlx4_dev *dev, u8 port);
 
+
+int mlx4_QP_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd);
+
+int mlx4_PROMISC_wrapper(struct mlx4_dev *dev, int slave,
+			 struct mlx4_vhcr *vhcr,
+			 struct mlx4_cmd_mailbox *inbox,
+			 struct mlx4_cmd_mailbox *outbox,
+			 struct mlx4_cmd_info *cmd);
 int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 			  enum mlx4_protocol prot, enum mlx4_steer_type steer);
 int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 			  int block_mcast_loopback, enum mlx4_protocol prot,
 			  enum mlx4_steer_type steer);
+int mlx4_SET_MCAST_FLTR_wrapper(struct mlx4_dev *dev, int slave,
+				struct mlx4_vhcr *vhcr,
+				struct mlx4_cmd_mailbox *inbox,
+				struct mlx4_cmd_mailbox *outbox,
+				struct mlx4_cmd_info *cmd);
+int mlx4_SET_VLAN_FLTR_wrapper(struct mlx4_dev *dev, int slave,
+			       struct mlx4_vhcr *vhcr,
+			       struct mlx4_cmd_mailbox *inbox,
+			       struct mlx4_cmd_mailbox *outbox,
+			       struct mlx4_cmd_info *cmd);
+int mlx4_common_set_vlan_fltr(struct mlx4_dev *dev, int function,
+				     int port, void *buf);
+int mlx4_common_dump_eth_stats(struct mlx4_dev *dev, int slave, u32 in_mod,
+				struct mlx4_cmd_mailbox *outbox);
+int mlx4_DUMP_ETH_STATS_wrapper(struct mlx4_dev *dev, int slave,
+				   struct mlx4_vhcr *vhcr,
+				   struct mlx4_cmd_mailbox *inbox,
+				   struct mlx4_cmd_mailbox *outbox,
+				struct mlx4_cmd_info *cmd);
+int mlx4_PKEY_TABLE_wrapper(struct mlx4_dev *dev, int slave,
+			    struct mlx4_vhcr *vhcr,
+			    struct mlx4_cmd_mailbox *inbox,
+			    struct mlx4_cmd_mailbox *outbox,
+			    struct mlx4_cmd_info *cmd);
+int mlx4_QUERY_IF_STAT_wrapper(struct mlx4_dev *dev, int slave,
+			       struct mlx4_vhcr *vhcr,
+			       struct mlx4_cmd_mailbox *inbox,
+			       struct mlx4_cmd_mailbox *outbox,
+			       struct mlx4_cmd_info *cmd);
+
+int mlx4_get_mgm_entry_size(struct mlx4_dev *dev);
+int mlx4_get_qp_per_mgm(struct mlx4_dev *dev);
+
+static inline void set_param_l(u64 *arg, u32 val)
+{
+	*((u32 *)arg) = val;
+}
+
+static inline void set_param_h(u64 *arg, u32 val)
+{
+	*arg = (*arg & 0xffffffff) | ((u64) val << 32);
+}
+
+static inline u32 get_param_l(u64 *arg)
+{
+	return (u32) (*arg & 0xffffffff);
+}
+
+static inline u32 get_param_h(u64 *arg)
+{
+	return (u32)(*arg >> 32);
+}
+
+static inline spinlock_t *mlx4_tlock(struct mlx4_dev *dev)
+{
+	return &mlx4_priv(dev)->mfunc.master.res_tracker.lock;
+}
+
+#define NOT_MASKED_PD_BITS 17
+
 #endif /* MLX4_H */
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 8fda331c..f2a8e65 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -51,8 +51,8 @@
 #include "en_port.h"
 
 #define DRV_NAME	"mlx4_en"
-#define DRV_VERSION	"1.5.4.2"
-#define DRV_RELDATE	"October 2011"
+#define DRV_VERSION	"2.0"
+#define DRV_RELDATE	"Dec 2011"
 
 #define MLX4_EN_MSG_LEVEL	(NETIF_MSG_LINK | NETIF_MSG_IFDOWN)
 
@@ -272,6 +272,7 @@ struct mlx4_en_rx_ring {
 	u32 prod;
 	u32 cons;
 	u32 buf_size;
+	u8  fcs_del;
 	void *buf;
 	void *rx_info;
 	unsigned long bytes;
@@ -365,16 +366,6 @@ struct mlx4_en_rss_map {
 	enum mlx4_qp_state indir_state;
 };
 
-struct mlx4_en_rss_context {
-	__be32 base_qpn;
-	__be32 default_qpn;
-	u16 reserved;
-	u8 hash_fn;
-	u8 flags;
-	__be32 rss_key[10];
-	__be32 base_qpn_udp;
-};
-
 struct mlx4_en_port_state {
 	int link_state;
 	int link_speed;
@@ -462,6 +453,7 @@ struct mlx4_en_priv {
 	int base_qpn;
 
 	struct mlx4_en_rss_map rss_map;
+	u32 ctrl_flags;
 	u32 flags;
 #define MLX4_EN_FLAG_PROMISC	0x1
 #define MLX4_EN_FLAG_MC_PROMISC	0x2
@@ -494,9 +486,9 @@ struct mlx4_en_priv {
 enum mlx4_en_wol {
 	MLX4_EN_WOL_MAGIC = (1ULL << 61),
 	MLX4_EN_WOL_ENABLED = (1ULL << 62),
-	MLX4_EN_WOL_DO_MODIFY = (1ULL << 63),
 };
 
+#define MLX4_EN_WOL_DO_MODIFY (1ULL << 63)
 
 void mlx4_en_destroy_netdev(struct net_device *dev);
 int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
diff --git a/drivers/net/ethernet/mellanox/mlx4/mr.c b/drivers/net/ethernet/mellanox/mlx4/mr.c
index efa3e77..f7243b2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mr.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mr.c
@@ -32,35 +32,17 @@
  * SOFTWARE.
  */
 
+#include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/export.h>
 #include <linux/slab.h>
+#include <linux/kernel.h>
 
 #include <linux/mlx4/cmd.h>
 
 #include "mlx4.h"
 #include "icm.h"
 
-/*
- * Must be packed because mtt_seg is 64 bits but only aligned to 32 bits.
- */
-struct mlx4_mpt_entry {
-	__be32 flags;
-	__be32 qpn;
-	__be32 key;
-	__be32 pd_flags;
-	__be64 start;
-	__be64 length;
-	__be32 lkey;
-	__be32 win_cnt;
-	u8	reserved1[3];
-	u8	mtt_rep;
-	__be64 mtt_seg;
-	__be32 mtt_sz;
-	__be32 entity_size;
-	__be32 first_byte_offset;
-} __packed;
-
 #define MLX4_MPT_FLAG_SW_OWNS	    (0xfUL << 28)
 #define MLX4_MPT_FLAG_FREE	    (0x3UL << 28)
 #define MLX4_MPT_FLAG_MIO	    (1 << 17)
@@ -180,22 +162,48 @@ static void mlx4_buddy_cleanup(struct mlx4_buddy *buddy)
 	kfree(buddy->num_free);
 }
 
-static u32 mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order)
+u32 __mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order)
 {
 	struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
 	u32 seg;
+	int seg_order;
+	u32 offset;
 
-	seg = mlx4_buddy_alloc(&mr_table->mtt_buddy, order);
+	seg_order = max_t(int, order - log_mtts_per_seg, 0);
+
+	seg = mlx4_buddy_alloc(&mr_table->mtt_buddy, seg_order);
 	if (seg == -1)
 		return -1;
 
-	if (mlx4_table_get_range(dev, &mr_table->mtt_table, seg,
-				 seg + (1 << order) - 1)) {
-		mlx4_buddy_free(&mr_table->mtt_buddy, seg, order);
+	offset = seg * (1 << log_mtts_per_seg);
+
+	if (mlx4_table_get_range(dev, &mr_table->mtt_table, offset,
+				 offset + (1 << order) - 1)) {
+		mlx4_buddy_free(&mr_table->mtt_buddy, seg, seg_order);
 		return -1;
 	}
 
-	return seg;
+	return offset;
+}
+
+static u32 mlx4_alloc_mtt_range(struct mlx4_dev *dev, int order)
+{
+	u64 in_param;
+	u64 out_param;
+	int err;
+
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&in_param, order);
+		err = mlx4_cmd_imm(dev, in_param, &out_param, RES_MTT,
+						       RES_OP_RESERVE_AND_MAP,
+						       MLX4_CMD_ALLOC_RES,
+						       MLX4_CMD_TIME_CLASS_A,
+						       MLX4_CMD_WRAPPED);
+		if (err)
+			return -1;
+		return get_param_l(&out_param);
+	}
+	return __mlx4_alloc_mtt_range(dev, order);
 }
 
 int mlx4_mtt_init(struct mlx4_dev *dev, int npages, int page_shift,
@@ -210,33 +218,63 @@ int mlx4_mtt_init(struct mlx4_dev *dev, int npages, int page_shift,
 	} else
 		mtt->page_shift = page_shift;
 
-	for (mtt->order = 0, i = dev->caps.mtts_per_seg; i < npages; i <<= 1)
+	for (mtt->order = 0, i = 1; i < npages; i <<= 1)
 		++mtt->order;
 
-	mtt->first_seg = mlx4_alloc_mtt_range(dev, mtt->order);
-	if (mtt->first_seg == -1)
+	mtt->offset = mlx4_alloc_mtt_range(dev, mtt->order);
+	if (mtt->offset == -1)
 		return -ENOMEM;
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mlx4_mtt_init);
 
-void mlx4_mtt_cleanup(struct mlx4_dev *dev, struct mlx4_mtt *mtt)
+void __mlx4_free_mtt_range(struct mlx4_dev *dev, u32 offset, int order)
 {
+	u32 first_seg;
+	int seg_order;
 	struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
 
+	seg_order = max_t(int, order - log_mtts_per_seg, 0);
+	first_seg = offset / (1 << log_mtts_per_seg);
+
+	mlx4_buddy_free(&mr_table->mtt_buddy, first_seg, seg_order);
+	mlx4_table_put_range(dev, &mr_table->mtt_table, first_seg,
+			     first_seg + (1 << seg_order) - 1);
+}
+
+static void mlx4_free_mtt_range(struct mlx4_dev *dev, u32 offset, int order)
+{
+	u64 in_param;
+	int err;
+
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&in_param, offset);
+		set_param_h(&in_param, order);
+		err = mlx4_cmd(dev, in_param, RES_MTT, RES_OP_RESERVE_AND_MAP,
+						       MLX4_CMD_FREE_RES,
+						       MLX4_CMD_TIME_CLASS_A,
+						       MLX4_CMD_WRAPPED);
+		if (err)
+			mlx4_warn(dev, "Failed to free mtt range at:"
+				  "%d order:%d\n", offset, order);
+		return;
+	}
+	 __mlx4_free_mtt_range(dev, offset, order);
+}
+
+void mlx4_mtt_cleanup(struct mlx4_dev *dev, struct mlx4_mtt *mtt)
+{
 	if (mtt->order < 0)
 		return;
 
-	mlx4_buddy_free(&mr_table->mtt_buddy, mtt->first_seg, mtt->order);
-	mlx4_table_put_range(dev, &mr_table->mtt_table, mtt->first_seg,
-			     mtt->first_seg + (1 << mtt->order) - 1);
+	mlx4_free_mtt_range(dev, mtt->offset, mtt->order);
 }
 EXPORT_SYMBOL_GPL(mlx4_mtt_cleanup);
 
 u64 mlx4_mtt_addr(struct mlx4_dev *dev, struct mlx4_mtt *mtt)
 {
-	return (u64) mtt->first_seg * dev->caps.mtt_entry_sz;
+	return (u64) mtt->offset * dev->caps.mtt_entry_sz;
 }
 EXPORT_SYMBOL_GPL(mlx4_mtt_addr);
 
@@ -253,69 +291,205 @@ static u32 key_to_hw_index(u32 key)
 static int mlx4_SW2HW_MPT(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
 			  int mpt_index)
 {
-	return mlx4_cmd(dev, mailbox->dma, mpt_index, 0, MLX4_CMD_SW2HW_MPT,
-			MLX4_CMD_TIME_CLASS_B);
+	return mlx4_cmd(dev, mailbox->dma | dev->caps.function , mpt_index,
+			0, MLX4_CMD_SW2HW_MPT, MLX4_CMD_TIME_CLASS_B,
+			MLX4_CMD_WRAPPED);
 }
 
 static int mlx4_HW2SW_MPT(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
 			  int mpt_index)
 {
 	return mlx4_cmd_box(dev, 0, mailbox ? mailbox->dma : 0, mpt_index,
-			    !mailbox, MLX4_CMD_HW2SW_MPT, MLX4_CMD_TIME_CLASS_B);
+			    !mailbox, MLX4_CMD_HW2SW_MPT,
+			    MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
 }
 
-int mlx4_mr_alloc(struct mlx4_dev *dev, u32 pd, u64 iova, u64 size, u32 access,
-		  int npages, int page_shift, struct mlx4_mr *mr)
+static int mlx4_mr_reserve_range(struct mlx4_dev *dev, int cnt, int align,
+			  u32 *base_mridx)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	u32 index;
-	int err;
+	u32 mridx;
 
-	index = mlx4_bitmap_alloc(&priv->mr_table.mpt_bitmap);
-	if (index == -1)
+	mridx = mlx4_bitmap_alloc_range(&priv->mr_table.mpt_bitmap, cnt, align);
+	if (mridx == -1)
 		return -ENOMEM;
 
+	*base_mridx = mridx;
+	return 0;
+
+}
+EXPORT_SYMBOL_GPL(mlx4_mr_reserve_range);
+
+static void mlx4_mr_release_range(struct mlx4_dev *dev, u32 base_mridx, int cnt)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	mlx4_bitmap_free_range(&priv->mr_table.mpt_bitmap, base_mridx, cnt);
+}
+EXPORT_SYMBOL_GPL(mlx4_mr_release_range);
+
+static int mlx4_mr_alloc_reserved(struct mlx4_dev *dev, u32 mridx, u32 pd,
+			   u64 iova, u64 size, u32 access, int npages,
+			   int page_shift, struct mlx4_mr *mr)
+{
 	mr->iova       = iova;
 	mr->size       = size;
 	mr->pd	       = pd;
 	mr->access     = access;
-	mr->enabled    = 0;
-	mr->key	       = hw_index_to_key(index);
+	mr->enabled    = MLX4_MR_DISABLED;
+	mr->key	       = hw_index_to_key(mridx);
+
+	return mlx4_mtt_init(dev, npages, page_shift, &mr->mtt);
+}
+EXPORT_SYMBOL_GPL(mlx4_mr_alloc_reserved);
+
+static int mlx4_WRITE_MTT(struct mlx4_dev *dev,
+			  struct mlx4_cmd_mailbox *mailbox,
+			  int num_entries)
+{
+	return mlx4_cmd(dev, mailbox->dma, num_entries, 0, MLX4_CMD_WRITE_MTT,
+			MLX4_CMD_TIME_CLASS_A,  MLX4_CMD_WRAPPED);
+}
 
-	err = mlx4_mtt_init(dev, npages, page_shift, &mr->mtt);
+int __mlx4_mr_reserve(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	return mlx4_bitmap_alloc(&priv->mr_table.mpt_bitmap);
+}
+
+static int mlx4_mr_reserve(struct mlx4_dev *dev)
+{
+	u64 out_param;
+
+	if (mlx4_is_mfunc(dev)) {
+		if (mlx4_cmd_imm(dev, 0, &out_param, RES_MPT, RES_OP_RESERVE,
+				   MLX4_CMD_ALLOC_RES,
+				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED))
+			return -1;
+		return get_param_l(&out_param);
+	}
+	return  __mlx4_mr_reserve(dev);
+}
+
+void __mlx4_mr_release(struct mlx4_dev *dev, u32 index)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	mlx4_bitmap_free(&priv->mr_table.mpt_bitmap, index);
+}
+
+static void mlx4_mr_release(struct mlx4_dev *dev, u32 index)
+{
+	u64 in_param;
+
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&in_param, index);
+		if (mlx4_cmd(dev, in_param, RES_MPT, RES_OP_RESERVE,
+			       MLX4_CMD_FREE_RES,
+			       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED))
+			mlx4_warn(dev, "Failed to release mr index:%d\n",
+				  index);
+		return;
+	}
+	__mlx4_mr_release(dev, index);
+}
+
+int __mlx4_mr_alloc_icm(struct mlx4_dev *dev, u32 index)
+{
+	struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
+
+	return mlx4_table_get(dev, &mr_table->dmpt_table, index);
+}
+
+static int mlx4_mr_alloc_icm(struct mlx4_dev *dev, u32 index)
+{
+	u64 param;
+
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&param, index);
+		return mlx4_cmd_imm(dev, param, &param, RES_MPT, RES_OP_MAP_ICM,
+							MLX4_CMD_ALLOC_RES,
+							MLX4_CMD_TIME_CLASS_A,
+							MLX4_CMD_WRAPPED);
+	}
+	return __mlx4_mr_alloc_icm(dev, index);
+}
+
+void __mlx4_mr_free_icm(struct mlx4_dev *dev, u32 index)
+{
+	struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
+
+	mlx4_table_put(dev, &mr_table->dmpt_table, index);
+}
+
+static void mlx4_mr_free_icm(struct mlx4_dev *dev, u32 index)
+{
+	u64 in_param;
+
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&in_param, index);
+		if (mlx4_cmd(dev, in_param, RES_MPT, RES_OP_MAP_ICM,
+			     MLX4_CMD_FREE_RES, MLX4_CMD_TIME_CLASS_A,
+			     MLX4_CMD_WRAPPED))
+			mlx4_warn(dev, "Failed to free icm of mr index:%d\n",
+				  index);
+		return;
+	}
+	return __mlx4_mr_free_icm(dev, index);
+}
+
+int mlx4_mr_alloc(struct mlx4_dev *dev, u32 pd, u64 iova, u64 size, u32 access,
+		  int npages, int page_shift, struct mlx4_mr *mr)
+{
+	u32 index;
+	int err;
+
+	index = mlx4_mr_reserve(dev);
+	if (index == -1)
+		return -ENOMEM;
+
+	err = mlx4_mr_alloc_reserved(dev, index, pd, iova, size,
+				     access, npages, page_shift, mr);
 	if (err)
-		mlx4_bitmap_free(&priv->mr_table.mpt_bitmap, index);
+		mlx4_mr_release(dev, index);
 
 	return err;
 }
 EXPORT_SYMBOL_GPL(mlx4_mr_alloc);
 
-void mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr)
+static void mlx4_mr_free_reserved(struct mlx4_dev *dev, struct mlx4_mr *mr)
 {
-	struct mlx4_priv *priv = mlx4_priv(dev);
 	int err;
 
-	if (mr->enabled) {
+	if (mr->enabled == MLX4_MR_EN_HW) {
 		err = mlx4_HW2SW_MPT(dev, NULL,
 				     key_to_hw_index(mr->key) &
 				     (dev->caps.num_mpts - 1));
 		if (err)
-			mlx4_warn(dev, "HW2SW_MPT failed (%d)\n", err);
-	}
+			mlx4_warn(dev, "xxx HW2SW_MPT failed (%d)\n", err);
 
+		mr->enabled = MLX4_MR_EN_SW;
+	}
 	mlx4_mtt_cleanup(dev, &mr->mtt);
-	mlx4_bitmap_free(&priv->mr_table.mpt_bitmap, key_to_hw_index(mr->key));
+}
+EXPORT_SYMBOL_GPL(mlx4_mr_free_reserved);
+
+void mlx4_mr_free(struct mlx4_dev *dev, struct mlx4_mr *mr)
+{
+	mlx4_mr_free_reserved(dev, mr);
+	if (mr->enabled)
+		mlx4_mr_free_icm(dev, key_to_hw_index(mr->key));
+	mlx4_mr_release(dev, key_to_hw_index(mr->key));
 }
 EXPORT_SYMBOL_GPL(mlx4_mr_free);
 
 int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr)
 {
-	struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
 	struct mlx4_cmd_mailbox *mailbox;
 	struct mlx4_mpt_entry *mpt_entry;
 	int err;
 
-	err = mlx4_table_get(dev, &mr_table->dmpt_table, key_to_hw_index(mr->key));
+	err = mlx4_mr_alloc_icm(dev, key_to_hw_index(mr->key));
 	if (err)
 		return err;
 
@@ -340,9 +514,10 @@ int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr)
 
 	if (mr->mtt.order < 0) {
 		mpt_entry->flags |= cpu_to_be32(MLX4_MPT_FLAG_PHYSICAL);
-		mpt_entry->mtt_seg = 0;
+		mpt_entry->mtt_addr = 0;
 	} else {
-		mpt_entry->mtt_seg = cpu_to_be64(mlx4_mtt_addr(dev, &mr->mtt));
+		mpt_entry->mtt_addr = cpu_to_be64(mlx4_mtt_addr(dev,
+						  &mr->mtt));
 	}
 
 	if (mr->mtt.order >= 0 && mr->mtt.page_shift == 0) {
@@ -350,8 +525,7 @@ int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr)
 		mpt_entry->flags    |= cpu_to_be32(MLX4_MPT_FLAG_FREE);
 		mpt_entry->pd_flags |= cpu_to_be32(MLX4_MPT_PD_FLAG_FAST_REG |
 						   MLX4_MPT_PD_FLAG_RAE);
-		mpt_entry->mtt_sz    = cpu_to_be32((1 << mr->mtt.order) *
-						   dev->caps.mtts_per_seg);
+		mpt_entry->mtt_sz    = cpu_to_be32(1 << mr->mtt.order);
 	} else {
 		mpt_entry->flags    |= cpu_to_be32(MLX4_MPT_FLAG_SW_OWNS);
 	}
@@ -362,8 +536,7 @@ int mlx4_mr_enable(struct mlx4_dev *dev, struct mlx4_mr *mr)
 		mlx4_warn(dev, "SW2HW_MPT failed (%d)\n", err);
 		goto err_cmd;
 	}
-
-	mr->enabled = 1;
+	mr->enabled = MLX4_MR_EN_HW;
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
 
@@ -373,7 +546,7 @@ err_cmd:
 	mlx4_free_cmd_mailbox(dev, mailbox);
 
 err_table:
-	mlx4_table_put(dev, &mr_table->dmpt_table, key_to_hw_index(mr->key));
+	mlx4_mr_free_icm(dev, key_to_hw_index(mr->key));
 	return err;
 }
 EXPORT_SYMBOL_GPL(mlx4_mr_enable);
@@ -385,18 +558,10 @@ static int mlx4_write_mtt_chunk(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 	__be64 *mtts;
 	dma_addr_t dma_handle;
 	int i;
-	int s = start_index * sizeof (u64);
 
-	/* All MTTs must fit in the same page */
-	if (start_index / (PAGE_SIZE / sizeof (u64)) !=
-	    (start_index + npages - 1) / (PAGE_SIZE / sizeof (u64)))
-		return -EINVAL;
-
-	if (start_index & (dev->caps.mtts_per_seg - 1))
-		return -EINVAL;
+	mtts = mlx4_table_find(&priv->mr_table.mtt_table, mtt->offset +
+			       start_index, &dma_handle);
 
-	mtts = mlx4_table_find(&priv->mr_table.mtt_table, mtt->first_seg +
-				s / dev->caps.mtt_entry_sz, &dma_handle);
 	if (!mtts)
 		return -ENOMEM;
 
@@ -412,27 +577,75 @@ static int mlx4_write_mtt_chunk(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 	return 0;
 }
 
-int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
-		   int start_index, int npages, u64 *page_list)
+int __mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
+		     int start_index, int npages, u64 *page_list)
 {
+	int err = 0;
 	int chunk;
-	int err;
+	int mtts_per_page;
+	int max_mtts_first_page;
 
-	if (mtt->order < 0)
-		return -EINVAL;
+	/* compute how may mtts fit in the first page */
+	mtts_per_page = PAGE_SIZE / sizeof(u64);
+	max_mtts_first_page = mtts_per_page - (mtt->offset + start_index)
+			      % mtts_per_page;
+
+	chunk = min_t(int, max_mtts_first_page, npages);
 
 	while (npages > 0) {
-		chunk = min_t(int, PAGE_SIZE / sizeof(u64), npages);
 		err = mlx4_write_mtt_chunk(dev, mtt, start_index, chunk, page_list);
 		if (err)
 			return err;
-
 		npages      -= chunk;
 		start_index += chunk;
 		page_list   += chunk;
+
+		chunk = min_t(int, mtts_per_page, npages);
 	}
+	return err;
+}
 
-	return 0;
+int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
+		   int start_index, int npages, u64 *page_list)
+{
+	struct mlx4_cmd_mailbox *mailbox = NULL;
+	__be64 *inbox = NULL;
+	int chunk;
+	int err = 0;
+	int i;
+
+	if (mtt->order < 0)
+		return -EINVAL;
+
+	if (mlx4_is_mfunc(dev)) {
+		mailbox = mlx4_alloc_cmd_mailbox(dev);
+		if (IS_ERR(mailbox))
+			return PTR_ERR(mailbox);
+		inbox = mailbox->buf;
+
+		while (npages > 0) {
+			chunk = min_t(int, MLX4_MAILBOX_SIZE / sizeof(u64) - 2,
+				      npages);
+			inbox[0] = cpu_to_be64(mtt->offset + start_index);
+			inbox[1] = 0;
+			for (i = 0; i < chunk; ++i)
+				inbox[i + 2] = cpu_to_be64(page_list[i] |
+					       MLX4_MTT_FLAG_PRESENT);
+			err = mlx4_WRITE_MTT(dev, mailbox, chunk);
+			if (err) {
+				mlx4_free_cmd_mailbox(dev, mailbox);
+				return err;
+			}
+
+			npages      -= chunk;
+			start_index += chunk;
+			page_list   += chunk;
+		}
+		mlx4_free_cmd_mailbox(dev, mailbox);
+		return err;
+	}
+
+	return __mlx4_write_mtt(dev, mtt, start_index, npages, page_list);
 }
 EXPORT_SYMBOL_GPL(mlx4_write_mtt);
 
@@ -462,21 +675,34 @@ EXPORT_SYMBOL_GPL(mlx4_buf_write_mtt);
 
 int mlx4_init_mr_table(struct mlx4_dev *dev)
 {
-	struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_mr_table *mr_table = &priv->mr_table;
 	int err;
 
+	if (!is_power_of_2(dev->caps.num_mpts))
+		return -EINVAL;
+
+	/* Nothing to do for slaves - all MR handling is forwarded
+	* to the master */
+	if (mlx4_is_slave(dev))
+		return 0;
+
 	err = mlx4_bitmap_init(&mr_table->mpt_bitmap, dev->caps.num_mpts,
 			       ~0, dev->caps.reserved_mrws, 0);
 	if (err)
 		return err;
 
 	err = mlx4_buddy_init(&mr_table->mtt_buddy,
-			      ilog2(dev->caps.num_mtt_segs));
+			      ilog2(dev->caps.num_mtts /
+			      (1 << log_mtts_per_seg)));
 	if (err)
 		goto err_buddy;
 
 	if (dev->caps.reserved_mtts) {
-		if (mlx4_alloc_mtt_range(dev, fls(dev->caps.reserved_mtts - 1)) == -1) {
+		priv->reserved_mtts =
+			mlx4_alloc_mtt_range(dev,
+					     fls(dev->caps.reserved_mtts - 1));
+		if (priv->reserved_mtts < 0) {
 			mlx4_warn(dev, "MTT table of order %d is too small.\n",
 				  mr_table->mtt_buddy.max_order);
 			err = -ENOMEM;
@@ -497,8 +723,14 @@ err_buddy:
 
 void mlx4_cleanup_mr_table(struct mlx4_dev *dev)
 {
-	struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_mr_table *mr_table = &priv->mr_table;
 
+	if (mlx4_is_slave(dev))
+		return;
+	if (priv->reserved_mtts >= 0)
+		mlx4_free_mtt_range(dev, priv->reserved_mtts,
+				    fls(dev->caps.reserved_mtts - 1));
 	mlx4_buddy_cleanup(&mr_table->mtt_buddy);
 	mlx4_bitmap_cleanup(&mr_table->mpt_bitmap);
 }
@@ -581,7 +813,7 @@ int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages,
 		   int max_maps, u8 page_shift, struct mlx4_fmr *fmr)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	u64 mtt_seg;
+	u64 mtt_offset;
 	int err = -ENOMEM;
 
 	if (page_shift < (ffs(dev->caps.page_size_cap) - 1) || page_shift >= 32)
@@ -601,11 +833,12 @@ int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages,
 	if (err)
 		return err;
 
-	mtt_seg = fmr->mr.mtt.first_seg * dev->caps.mtt_entry_sz;
+	mtt_offset = fmr->mr.mtt.offset * dev->caps.mtt_entry_sz;
 
 	fmr->mtts = mlx4_table_find(&priv->mr_table.mtt_table,
-				    fmr->mr.mtt.first_seg,
+				    fmr->mr.mtt.offset,
 				    &fmr->dma_handle);
+
 	if (!fmr->mtts) {
 		err = -ENOMEM;
 		goto err_free;
@@ -619,6 +852,46 @@ err_free:
 }
 EXPORT_SYMBOL_GPL(mlx4_fmr_alloc);
 
+static int mlx4_fmr_alloc_reserved(struct mlx4_dev *dev, u32 mridx,
+			    u32 pd, u32 access, int max_pages,
+			    int max_maps, u8 page_shift, struct mlx4_fmr *fmr)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int err = -ENOMEM;
+
+	if (page_shift < (ffs(dev->caps.page_size_cap) - 1) || page_shift >= 32)
+		return -EINVAL;
+
+	/* All MTTs must fit in the same page */
+	if (max_pages * sizeof *fmr->mtts > PAGE_SIZE)
+		return -EINVAL;
+
+	fmr->page_shift = page_shift;
+	fmr->max_pages  = max_pages;
+	fmr->max_maps   = max_maps;
+	fmr->maps = 0;
+
+	err = mlx4_mr_alloc_reserved(dev, mridx, pd, 0, 0, access, max_pages,
+				     page_shift, &fmr->mr);
+	if (err)
+		return err;
+
+	fmr->mtts = mlx4_table_find(&priv->mr_table.mtt_table,
+				    fmr->mr.mtt.offset,
+				    &fmr->dma_handle);
+	if (!fmr->mtts) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+
+	return 0;
+
+err_free:
+	mlx4_mr_free_reserved(dev, &fmr->mr);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_fmr_alloc_reserved);
+
 int mlx4_fmr_enable(struct mlx4_dev *dev, struct mlx4_fmr *fmr)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -640,12 +913,32 @@ EXPORT_SYMBOL_GPL(mlx4_fmr_enable);
 void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
 		    u32 *lkey, u32 *rkey)
 {
+	struct mlx4_cmd_mailbox *mailbox;
+	int err;
+
 	if (!fmr->maps)
 		return;
 
 	fmr->maps = 0;
 
-	*(u8 *) fmr->mpt = MLX4_MPT_STATUS_SW;
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox)) {
+		err = PTR_ERR(mailbox);
+		printk(KERN_WARNING "mlx4_ib: mlx4_alloc_cmd_mailbox"
+		       " failed (%d)\n", err);
+		return;
+	}
+
+	err = mlx4_HW2SW_MPT(dev, NULL,
+			     key_to_hw_index(fmr->mr.key) &
+			     (dev->caps.num_mpts - 1));
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	if (err) {
+		printk(KERN_WARNING "mlx4_ib: mlx4_HW2SW_MPT failed (%d)\n",
+		       err);
+		return;
+	}
+	fmr->mr.enabled = MLX4_MR_EN_SW;
 }
 EXPORT_SYMBOL_GPL(mlx4_fmr_unmap);
 
@@ -654,15 +947,28 @@ int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr)
 	if (fmr->maps)
 		return -EBUSY;
 
-	fmr->mr.enabled = 0;
 	mlx4_mr_free(dev, &fmr->mr);
+	fmr->mr.enabled = MLX4_MR_DISABLED;
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mlx4_fmr_free);
 
+static int mlx4_fmr_free_reserved(struct mlx4_dev *dev, struct mlx4_fmr *fmr)
+{
+	if (fmr->maps)
+		return -EBUSY;
+
+	mlx4_mr_free_reserved(dev, &fmr->mr);
+	fmr->mr.enabled = MLX4_MR_DISABLED;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx4_fmr_free_reserved);
+
 int mlx4_SYNC_TPT(struct mlx4_dev *dev)
 {
-	return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_SYNC_TPT, 1000);
+	return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_SYNC_TPT, 1000,
+			MLX4_CMD_WRAPPED);
 }
 EXPORT_SYMBOL_GPL(mlx4_SYNC_TPT);
diff --git a/drivers/net/ethernet/mellanox/mlx4/pd.c b/drivers/net/ethernet/mellanox/mlx4/pd.c
index 260ed25..5c9a54d 100644
--- a/drivers/net/ethernet/mellanox/mlx4/pd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/pd.c
@@ -31,6 +31,7 @@
  * SOFTWARE.
  */
 
+#include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/export.h>
 #include <linux/io-mapping.h>
@@ -51,7 +52,8 @@ int mlx4_pd_alloc(struct mlx4_dev *dev, u32 *pdn)
 	*pdn = mlx4_bitmap_alloc(&priv->pd_bitmap);
 	if (*pdn == -1)
 		return -ENOMEM;
-
+	if (mlx4_is_mfunc(dev))
+		*pdn |= (dev->caps.function + 1) << NOT_MASKED_PD_BITS;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mlx4_pd_alloc);
@@ -85,7 +87,8 @@ int mlx4_init_pd_table(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
 	return mlx4_bitmap_init(&priv->pd_bitmap, dev->caps.num_pds,
-				(1 << 24) - 1, dev->caps.reserved_pds, 0);
+				(1 << NOT_MASKED_PD_BITS) - 1,
+				 dev->caps.reserved_pds, 0);
 }
 
 void mlx4_cleanup_pd_table(struct mlx4_dev *dev)
@@ -108,13 +111,19 @@ void mlx4_cleanup_xrcd_table(struct mlx4_dev *dev)
 
 int mlx4_uar_alloc(struct mlx4_dev *dev, struct mlx4_uar *uar)
 {
+	int offset;
+
 	uar->index = mlx4_bitmap_alloc(&mlx4_priv(dev)->uar_table.bitmap);
 	if (uar->index == -1)
 		return -ENOMEM;
 
-	uar->pfn = (pci_resource_start(dev->pdev, 2) >> PAGE_SHIFT) + uar->index;
+	if (mlx4_is_slave(dev))
+		offset = uar->index % ((int) pci_resource_len(dev->pdev, 2) /
+				       dev->caps.uar_page_size);
+	else
+		offset = uar->index;
+	uar->pfn = (pci_resource_start(dev->pdev, 2) >> PAGE_SHIFT) + offset;
 	uar->map = NULL;
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mlx4_uar_alloc);
@@ -232,7 +241,7 @@ int mlx4_init_uar_table(struct mlx4_dev *dev)
 
 	return mlx4_bitmap_init(&mlx4_priv(dev)->uar_table.bitmap,
 				dev->caps.num_uars, dev->caps.num_uars - 1,
-				max(128, dev->caps.reserved_uars), 0);
+				dev->caps.reserved_uars, 0);
 }
 
 void mlx4_cleanup_uar_table(struct mlx4_dev *dev)
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index d942aea..88b52e5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -70,41 +70,12 @@ void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table)
 	table->total = 0;
 }
 
-static int mlx4_set_port_mac_table(struct mlx4_dev *dev, u8 port,
-				   __be64 *entries)
-{
-	struct mlx4_cmd_mailbox *mailbox;
-	u32 in_mod;
-	int err;
-
-	mailbox = mlx4_alloc_cmd_mailbox(dev);
-	if (IS_ERR(mailbox))
-		return PTR_ERR(mailbox);
-
-	memcpy(mailbox->buf, entries, MLX4_MAC_TABLE_SIZE);
-
-	in_mod = MLX4_SET_PORT_MAC_TABLE << 8 | port;
-	err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
-		       MLX4_CMD_TIME_CLASS_B);
-
-	mlx4_free_cmd_mailbox(dev, mailbox);
-	return err;
-}
-
-static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port,
-			     u64 mac, int *qpn, u8 reserve)
+static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn)
 {
 	struct mlx4_qp qp;
 	u8 gid[16] = {0};
 	int err;
 
-	if (reserve) {
-		err = mlx4_qp_reserve_range(dev, 1, 1, qpn);
-		if (err) {
-			mlx4_err(dev, "Failed to reserve qp for mac registration\n");
-			return err;
-		}
-	}
 	qp.qpn = *qpn;
 
 	mac &= 0xffffffffffffULL;
@@ -113,16 +84,15 @@ static int mlx4_uc_steer_add(struct mlx4_dev *dev, u8 port,
 	gid[5] = port;
 	gid[7] = MLX4_UC_STEER << 1;
 
-	err = mlx4_qp_attach_common(dev, &qp, gid, 0,
-				    MLX4_PROT_ETH, MLX4_UC_STEER);
-	if (err && reserve)
-		mlx4_qp_release_range(dev, *qpn, 1);
+	err = mlx4_unicast_attach(dev, &qp, gid, 0, MLX4_PROT_ETH);
+	if (err)
+		mlx4_warn(dev, "Failed Attaching Unicast\n");
 
 	return err;
 }
 
 static void mlx4_uc_steer_release(struct mlx4_dev *dev, u8 port,
-				  u64 mac, int qpn, u8 free)
+				  u64 mac, int qpn)
 {
 	struct mlx4_qp qp;
 	u8 gid[16] = {0};
@@ -134,60 +104,164 @@ static void mlx4_uc_steer_release(struct mlx4_dev *dev, u8 port,
 	gid[5] = port;
 	gid[7] = MLX4_UC_STEER << 1;
 
-	mlx4_qp_detach_common(dev, &qp, gid, MLX4_PROT_ETH, MLX4_UC_STEER);
-	if (free)
-		mlx4_qp_release_range(dev, qpn, 1);
+	mlx4_unicast_detach(dev, &qp, gid, MLX4_PROT_ETH);
+}
+
+static int validate_index(struct mlx4_dev *dev,
+			  struct mlx4_mac_table *table, int index)
+{
+	int err = 0;
+
+	if (index < 0 || index >= table->max || !table->entries[index]) {
+		mlx4_warn(dev, "No valid Mac entry for the given index\n");
+		err = -EINVAL;
+	}
+	return err;
+}
+
+static int find_index(struct mlx4_dev *dev,
+		      struct mlx4_mac_table *table, u64 mac)
+{
+	int i;
+
+	for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
+		if ((mac & MLX4_MAC_MASK) ==
+		    (MLX4_MAC_MASK & be64_to_cpu(table->entries[i])))
+			return i;
+	}
+	/* Mac not found */
+	return -EINVAL;
 }
 
-int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn, u8 wrap)
+int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn)
 {
 	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
-	struct mlx4_mac_table *table = &info->mac_table;
 	struct mlx4_mac_entry *entry;
-	int i, err = 0;
-	int free = -1;
+	int index = 0;
+	int err = 0;
 
-	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER) {
-		err = mlx4_uc_steer_add(dev, port, mac, qpn, 1);
-		if (err)
-			return err;
+	mlx4_dbg(dev, "Registering MAC: 0x%llx for adding\n",
+			(unsigned long long) mac);
+	index = mlx4_register_mac(dev, port, mac);
+	if (index < 0) {
+		err = index;
+		mlx4_err(dev, "Failed adding MAC: 0x%llx\n",
+			 (unsigned long long) mac);
+		return err;
+	}
 
-		entry = kmalloc(sizeof *entry, GFP_KERNEL);
-		if (!entry) {
-			mlx4_uc_steer_release(dev, port, mac, *qpn, 1);
-			return -ENOMEM;
-		}
+	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER)) {
+		*qpn = info->base_qpn + index;
+		return 0;
+	}
+
+	err = mlx4_qp_reserve_range(dev, 1, 1, qpn);
+	mlx4_dbg(dev, "Reserved qp %d\n", *qpn);
+	if (err) {
+		mlx4_err(dev, "Failed to reserve qp for mac registration\n");
+		goto qp_err;
+	}
+
+	err = mlx4_uc_steer_add(dev, port, mac, qpn);
+	if (err)
+		goto steer_err;
 
-		entry->mac = mac;
-		err = radix_tree_insert(&info->mac_tree, *qpn, entry);
-		if (err) {
+	entry = kmalloc(sizeof *entry, GFP_KERNEL);
+	if (!entry) {
+		err = -ENOMEM;
+		goto alloc_err;
+	}
+	entry->mac = mac;
+	err = radix_tree_insert(&info->mac_tree, *qpn, entry);
+	if (err)
+		goto insert_err;
+	return 0;
+
+insert_err:
+	kfree(entry);
+
+alloc_err:
+	mlx4_uc_steer_release(dev, port, mac, *qpn);
+
+steer_err:
+	mlx4_qp_release_range(dev, *qpn, 1);
+
+qp_err:
+	mlx4_unregister_mac(dev, port, mac);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_get_eth_qp);
+
+void mlx4_put_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int qpn)
+{
+	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
+	struct mlx4_mac_entry *entry;
+
+	mlx4_dbg(dev, "Registering MAC: 0x%llx for deleting\n",
+		 (unsigned long long) mac);
+	mlx4_unregister_mac(dev, port, mac);
+
+	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER) {
+		entry = radix_tree_lookup(&info->mac_tree, qpn);
+		if (entry) {
+			mlx4_dbg(dev, "Releasing qp: port %d, mac 0x%llx,"
+				 " qpn %d\n", port,
+				 (unsigned long long) mac, qpn);
+			mlx4_uc_steer_release(dev, port, entry->mac, qpn);
+			mlx4_qp_release_range(dev, qpn, 1);
+			radix_tree_delete(&info->mac_tree, qpn);
 			kfree(entry);
-			mlx4_uc_steer_release(dev, port, mac, *qpn, 1);
-			return err;
 		}
 	}
+}
+EXPORT_SYMBOL_GPL(mlx4_put_eth_qp);
+
+static int mlx4_set_port_mac_table(struct mlx4_dev *dev, u8 port,
+				   __be64 *entries)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	u32 in_mod;
+	int err;
 
-	mlx4_dbg(dev, "Registering MAC: 0x%llx\n", (unsigned long long) mac);
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+
+	memcpy(mailbox->buf, entries, MLX4_MAC_TABLE_SIZE);
+
+	in_mod = MLX4_SET_PORT_MAC_TABLE << 8 | port;
+
+	err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
+		       MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
+
+int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac)
+{
+	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
+	struct mlx4_mac_table *table = &info->mac_table;
+	int i, err = 0;
+	int free = -1;
+
+	mlx4_dbg(dev, "Registering MAC: 0x%llx for port %d\n",
+		 (unsigned long long) mac, port);
 
 	mutex_lock(&table->mutex);
-	for (i = 0; i < MLX4_MAX_MAC_NUM - 1; i++) {
-		if (free < 0 && !table->refs[i]) {
+	for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
+		if (free < 0 && !table->entries[i]) {
 			free = i;
 			continue;
 		}
 
 		if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i]))) {
-			/* MAC already registered, increase references count */
-			++table->refs[i];
+			/* MAC already registered, Must not have duplicates */
+			err = -EEXIST;
 			goto out;
 		}
 	}
 
-	if (free < 0) {
-		err = -ENOMEM;
-		goto out;
-	}
-
 	mlx4_dbg(dev, "Free MAC index is %d\n", free);
 
 	if (table->total == table->max) {
@@ -197,103 +271,103 @@ int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn, u8 wrap)
 	}
 
 	/* Register new MAC */
-	table->refs[free] = 1;
 	table->entries[free] = cpu_to_be64(mac | MLX4_MAC_VALID);
 
 	err = mlx4_set_port_mac_table(dev, port, table->entries);
 	if (unlikely(err)) {
-		mlx4_err(dev, "Failed adding MAC: 0x%llx\n", (unsigned long long) mac);
-		table->refs[free] = 0;
+		mlx4_err(dev, "Failed adding MAC: 0x%llx\n",
+			 (unsigned long long) mac);
 		table->entries[free] = 0;
 		goto out;
 	}
 
-	if (!(dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER))
-		*qpn = info->base_qpn + free;
+	err = free;
 	++table->total;
 out:
 	mutex_unlock(&table->mutex);
 	return err;
 }
-EXPORT_SYMBOL_GPL(mlx4_register_mac);
+EXPORT_SYMBOL_GPL(__mlx4_register_mac);
 
-static int validate_index(struct mlx4_dev *dev,
-			  struct mlx4_mac_table *table, int index)
+int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac)
 {
-	int err = 0;
+	u64 out_param;
+	int err;
 
-	if (index < 0 || index >= table->max || !table->entries[index]) {
-		mlx4_warn(dev, "No valid Mac entry for the given index\n");
-		err = -EINVAL;
-	}
-	return err;
-}
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&out_param, port);
+		err = mlx4_cmd_imm(dev, mac, &out_param, RES_MAC,
+				   RES_OP_RESERVE_AND_MAP, MLX4_CMD_ALLOC_RES,
+				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		if (err)
+			return err;
 
-static int find_index(struct mlx4_dev *dev,
-		      struct mlx4_mac_table *table, u64 mac)
-{
-	int i;
-	for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
-		if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i])))
-			return i;
+		return get_param_l(&out_param);
 	}
-	/* Mac not found */
-	return -EINVAL;
+	return __mlx4_register_mac(dev, port, mac);
 }
+EXPORT_SYMBOL_GPL(mlx4_register_mac);
 
-void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, int qpn)
+
+void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac)
 {
 	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
 	struct mlx4_mac_table *table = &info->mac_table;
-	int index = qpn - info->base_qpn;
-	struct mlx4_mac_entry *entry;
+	int index;
 
-	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER) {
-		entry = radix_tree_lookup(&info->mac_tree, qpn);
-		if (entry) {
-			mlx4_uc_steer_release(dev, port, entry->mac, qpn, 1);
-			radix_tree_delete(&info->mac_tree, qpn);
-			index = find_index(dev, table, entry->mac);
-			kfree(entry);
-		}
-	}
+	index = find_index(dev, table, mac);
 
 	mutex_lock(&table->mutex);
 
 	if (validate_index(dev, table, index))
 		goto out;
 
-	/* Check whether this address has reference count */
-	if (!(--table->refs[index])) {
-		table->entries[index] = 0;
-		mlx4_set_port_mac_table(dev, port, table->entries);
-		--table->total;
-	}
+	table->entries[index] = 0;
+	mlx4_set_port_mac_table(dev, port, table->entries);
+	--table->total;
 out:
 	mutex_unlock(&table->mutex);
 }
+EXPORT_SYMBOL_GPL(__mlx4_unregister_mac);
+
+void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac)
+{
+	u64 out_param;
+	int err;
+
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&out_param, port);
+		err = mlx4_cmd_imm(dev, mac, &out_param, RES_MAC,
+				   RES_OP_RESERVE_AND_MAP, MLX4_CMD_FREE_RES,
+				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		return;
+	}
+	__mlx4_unregister_mac(dev, port, mac);
+	return;
+}
 EXPORT_SYMBOL_GPL(mlx4_unregister_mac);
 
-int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac, u8 wrap)
+int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac)
 {
 	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
 	struct mlx4_mac_table *table = &info->mac_table;
-	int index = qpn - info->base_qpn;
 	struct mlx4_mac_entry *entry;
-	int err;
+	int index = qpn - info->base_qpn;
+	int err = 0;
 
 	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER) {
 		entry = radix_tree_lookup(&info->mac_tree, qpn);
 		if (!entry)
 			return -EINVAL;
-		index = find_index(dev, table, entry->mac);
-		mlx4_uc_steer_release(dev, port, entry->mac, qpn, 0);
+		mlx4_uc_steer_release(dev, port, entry->mac, qpn);
+		mlx4_unregister_mac(dev, port, entry->mac);
 		entry->mac = new_mac;
-		err = mlx4_uc_steer_add(dev, port, entry->mac, &qpn, 0);
-		if (err || index < 0)
-			return err;
+		mlx4_register_mac(dev, port, new_mac);
+		err = mlx4_uc_steer_add(dev, port, entry->mac, &qpn);
+		return err;
 	}
 
+	/* CX1 doesn't support multi-functions */
 	mutex_lock(&table->mutex);
 
 	err = validate_index(dev, table, index);
@@ -304,7 +378,8 @@ int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac, u8 wra
 
 	err = mlx4_set_port_mac_table(dev, port, table->entries);
 	if (unlikely(err)) {
-		mlx4_err(dev, "Failed adding MAC: 0x%llx\n", (unsigned long long) new_mac);
+		mlx4_err(dev, "Failed adding MAC: 0x%llx\n",
+			 (unsigned long long) new_mac);
 		table->entries[index] = 0;
 	}
 out:
@@ -312,6 +387,7 @@ out:
 	return err;
 }
 EXPORT_SYMBOL_GPL(mlx4_replace_mac);
+
 static int mlx4_set_port_vlan_table(struct mlx4_dev *dev, u8 port,
 				    __be32 *entries)
 {
@@ -326,7 +402,7 @@ static int mlx4_set_port_vlan_table(struct mlx4_dev *dev, u8 port,
 	memcpy(mailbox->buf, entries, MLX4_VLAN_TABLE_SIZE);
 	in_mod = MLX4_SET_PORT_VLAN_TABLE << 8 | port;
 	err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
-		       MLX4_CMD_TIME_CLASS_B);
+		       MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
 
@@ -352,7 +428,8 @@ int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx)
 }
 EXPORT_SYMBOL_GPL(mlx4_find_cached_vlan);
 
-int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index)
+static int __mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan,
+				int *index)
 {
 	struct mlx4_vlan_table *table = &mlx4_priv(dev)->port[port].vlan_table;
 	int i, err = 0;
@@ -387,7 +464,7 @@ int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index)
 		goto out;
 	}
 
-	/* Register new MAC */
+	/* Register new VLAN */
 	table->refs[free] = 1;
 	table->entries[free] = cpu_to_be32(vlan | MLX4_VLAN_VALID);
 
@@ -405,9 +482,27 @@ out:
 	mutex_unlock(&table->mutex);
 	return err;
 }
+
+int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index)
+{
+	u64 out_param;
+	int err;
+
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&out_param, port);
+		err = mlx4_cmd_imm(dev, vlan, &out_param, RES_VLAN,
+				   RES_OP_RESERVE_AND_MAP, MLX4_CMD_ALLOC_RES,
+				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		if (!err)
+			*index = get_param_l(&out_param);
+
+		return err;
+	}
+	return __mlx4_register_vlan(dev, port, vlan, index);
+}
 EXPORT_SYMBOL_GPL(mlx4_register_vlan);
 
-void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index)
+static void __mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index)
 {
 	struct mlx4_vlan_table *table = &mlx4_priv(dev)->port[port].vlan_table;
 
@@ -432,6 +527,25 @@ void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index)
 out:
 	mutex_unlock(&table->mutex);
 }
+
+void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index)
+{
+	u64 in_param;
+	int err;
+
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&in_param, port);
+		err = mlx4_cmd(dev, in_param, RES_VLAN, RES_OP_RESERVE_AND_MAP,
+			       MLX4_CMD_FREE_RES, MLX4_CMD_TIME_CLASS_A,
+			       MLX4_CMD_WRAPPED);
+		if (!err)
+			mlx4_warn(dev, "Failed freeing vlan at index:%d\n",
+					index);
+
+		return;
+	}
+	__mlx4_unregister_vlan(dev, port, index);
+}
 EXPORT_SYMBOL_GPL(mlx4_unregister_vlan);
 
 int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps)
@@ -462,7 +576,8 @@ int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps)
 	*(__be32 *) (&inbuf[20]) = cpu_to_be32(port);
 
 	err = mlx4_cmd_box(dev, inmailbox->dma, outmailbox->dma, port, 3,
-			   MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C);
+			   MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C,
+			   MLX4_CMD_NATIVE);
 	if (!err)
 		*caps = *(__be32 *) (outbuf + 84);
 	mlx4_free_cmd_mailbox(dev, inmailbox);
@@ -499,7 +614,8 @@ int mlx4_check_ext_port_caps(struct mlx4_dev *dev, u8 port)
 	*(__be32 *) (&inbuf[20]) = cpu_to_be32(port);
 
 	err = mlx4_cmd_box(dev, inmailbox->dma, outmailbox->dma, port, 3,
-			   MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C);
+			   MLX4_CMD_MAD_IFC, MLX4_CMD_TIME_CLASS_C,
+			   MLX4_CMD_NATIVE);
 
 	packet_error = be16_to_cpu(*(__be16 *) (outbuf + 4));
 
@@ -512,6 +628,139 @@ int mlx4_check_ext_port_caps(struct mlx4_dev *dev, u8 port)
 	return err;
 }
 
+static int mlx4_common_set_port(struct mlx4_dev *dev, int slave, u32 in_mod,
+				u8 op_mod, struct mlx4_cmd_mailbox *inbox)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_port_info *port_info;
+	struct mlx4_mfunc_master_ctx *master = &priv->mfunc.master;
+	struct mlx4_slave_state *slave_st = &master->slave_state[slave];
+	struct mlx4_set_port_rqp_calc_context *qpn_context;
+	struct mlx4_set_port_general_context *gen_context;
+	int reset_qkey_viols;
+	int port;
+	int is_eth;
+	u32 in_modifier;
+	u32 promisc;
+	u16 mtu, prev_mtu;
+	int err;
+	int i;
+	__be32 agg_cap_mask;
+	__be32 slave_cap_mask;
+	__be32 new_cap_mask;
+
+	port = in_mod & 0xff;
+	in_modifier = in_mod >> 8;
+	is_eth = op_mod;
+	port_info = &priv->port[port];
+
+	/* Slaves cannot perform SET_PORT operations except changing MTU */
+	if (is_eth) {
+		if (slave != dev->caps.function &&
+		    in_modifier != MLX4_SET_PORT_GENERAL) {
+			mlx4_warn(dev, "denying SET_PORT for slave:%d\n",
+					slave);
+			return -EINVAL;
+		}
+		switch (in_modifier) {
+		case MLX4_SET_PORT_RQP_CALC:
+			qpn_context = inbox->buf;
+			qpn_context->base_qpn =
+				cpu_to_be32(port_info->base_qpn);
+			qpn_context->n_mac = 0x7;
+			promisc = be32_to_cpu(qpn_context->promisc) >>
+				SET_PORT_PROMISC_SHIFT;
+			qpn_context->promisc = cpu_to_be32(
+				promisc << SET_PORT_PROMISC_SHIFT |
+				port_info->base_qpn);
+			promisc = be32_to_cpu(qpn_context->mcast) >>
+				SET_PORT_MC_PROMISC_SHIFT;
+			qpn_context->mcast = cpu_to_be32(
+				promisc << SET_PORT_MC_PROMISC_SHIFT |
+				port_info->base_qpn);
+			break;
+		case MLX4_SET_PORT_GENERAL:
+			gen_context = inbox->buf;
+			/* Mtu is configured as the max MTU among all the
+			 * the functions on the port. */
+			mtu = be16_to_cpu(gen_context->mtu);
+			mtu = min_t(int, mtu, dev->caps.eth_mtu_cap[port]);
+			prev_mtu = slave_st->mtu[port];
+			slave_st->mtu[port] = mtu;
+			if (mtu > master->max_mtu[port])
+				master->max_mtu[port] = mtu;
+			if (mtu < prev_mtu && prev_mtu ==
+						master->max_mtu[port]) {
+				slave_st->mtu[port] = mtu;
+				master->max_mtu[port] = mtu;
+				for (i = 0; i < dev->num_slaves; i++) {
+					master->max_mtu[port] =
+					max(master->max_mtu[port],
+					    master->slave_state[i].mtu[port]);
+				}
+			}
+
+			gen_context->mtu = cpu_to_be16(master->max_mtu[port]);
+			break;
+		}
+		return mlx4_cmd(dev, inbox->dma, in_mod, op_mod,
+				MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B,
+				MLX4_CMD_NATIVE);
+	}
+
+	/* For IB, we only consider:
+	 * - The capability mask, which is set to the aggregate of all
+	 *   slave function capabilities
+	 * - The QKey violatin counter - reset according to each request.
+	 */
+
+	if (dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
+		reset_qkey_viols = (*(u8 *) inbox->buf) & 0x40;
+		new_cap_mask = ((__be32 *) inbox->buf)[2];
+	} else {
+		reset_qkey_viols = ((u8 *) inbox->buf)[3] & 0x1;
+		new_cap_mask = ((__be32 *) inbox->buf)[1];
+	}
+
+	agg_cap_mask = 0;
+	slave_cap_mask =
+		priv->mfunc.master.slave_state[slave].ib_cap_mask[port];
+	priv->mfunc.master.slave_state[slave].ib_cap_mask[port] = new_cap_mask;
+	for (i = 0; i < dev->num_slaves; i++)
+		agg_cap_mask |=
+			priv->mfunc.master.slave_state[i].ib_cap_mask[port];
+
+	/* only clear mailbox for guests.  Master may be setting
+	* MTU or PKEY table size
+	*/
+	if (slave != dev->caps.function)
+		memset(inbox->buf, 0, 256);
+	if (dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
+		*(u8 *) inbox->buf	   = !!reset_qkey_viols << 6;
+		((__be32 *) inbox->buf)[2] = agg_cap_mask;
+	} else {
+		((u8 *) inbox->buf)[3]     = !!reset_qkey_viols;
+		((__be32 *) inbox->buf)[1] = agg_cap_mask;
+	}
+
+	err = mlx4_cmd(dev, inbox->dma, port, is_eth, MLX4_CMD_SET_PORT,
+		       MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+	if (err)
+		priv->mfunc.master.slave_state[slave].ib_cap_mask[port] =
+			slave_cap_mask;
+	return err;
+}
+
+int mlx4_SET_PORT_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd)
+{
+	return mlx4_common_set_port(dev, slave, vhcr->in_modifier,
+				    vhcr->op_modifier, inbox);
+}
+
 int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port)
 {
 	struct mlx4_cmd_mailbox *mailbox;
@@ -528,8 +777,127 @@ int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port)
 
 	((__be32 *) mailbox->buf)[1] = dev->caps.ib_port_def_cap[port];
 	err = mlx4_cmd(dev, mailbox->dma, port, 0, MLX4_CMD_SET_PORT,
-		       MLX4_CMD_TIME_CLASS_B);
+		       MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	return err;
 }
+
+int mlx4_SET_PORT_general(struct mlx4_dev *dev, u8 port, int mtu,
+			  u8 pptx, u8 pfctx, u8 pprx, u8 pfcrx)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_set_port_general_context *context;
+	int err;
+	u32 in_mod;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+	context = mailbox->buf;
+	memset(context, 0, sizeof *context);
+
+	context->flags = SET_PORT_GEN_ALL_VALID;
+	context->mtu = cpu_to_be16(mtu);
+	context->pptx = (pptx * (!pfctx)) << 7;
+	context->pfctx = pfctx;
+	context->pprx = (pprx * (!pfcrx)) << 7;
+	context->pfcrx = pfcrx;
+
+	in_mod = MLX4_SET_PORT_GENERAL << 8 | port;
+	err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
+		       MLX4_CMD_TIME_CLASS_B,  MLX4_CMD_WRAPPED);
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
+EXPORT_SYMBOL(mlx4_SET_PORT_general);
+
+int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
+			   u8 promisc)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_set_port_rqp_calc_context *context;
+	int err;
+	u32 in_mod;
+	u32 m_promisc = (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER) ?
+		MCAST_DIRECT : MCAST_DEFAULT;
+
+	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER  &&
+	    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER)
+		return 0;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+	context = mailbox->buf;
+	memset(context, 0, sizeof *context);
+
+	context->base_qpn = cpu_to_be32(base_qpn);
+	context->n_mac = dev->caps.log_num_macs;
+	context->promisc = cpu_to_be32(promisc << SET_PORT_PROMISC_SHIFT |
+				       base_qpn);
+	context->mcast = cpu_to_be32(m_promisc << SET_PORT_MC_PROMISC_SHIFT |
+				     base_qpn);
+	context->intra_no_vlan = 0;
+	context->no_vlan = MLX4_NO_VLAN_IDX;
+	context->intra_vlan_miss = 0;
+	context->vlan_miss = MLX4_VLAN_MISS_IDX;
+
+	in_mod = MLX4_SET_PORT_RQP_CALC << 8 | port;
+	err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
+		       MLX4_CMD_TIME_CLASS_B,  MLX4_CMD_WRAPPED);
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
+EXPORT_SYMBOL(mlx4_SET_PORT_qpn_calc);
+
+int mlx4_SET_MCAST_FLTR_wrapper(struct mlx4_dev *dev, int slave,
+				struct mlx4_vhcr *vhcr,
+				struct mlx4_cmd_mailbox *inbox,
+				struct mlx4_cmd_mailbox *outbox,
+				struct mlx4_cmd_info *cmd)
+{
+	int err = 0;
+
+	return err;
+}
+
+int mlx4_SET_MCAST_FLTR(struct mlx4_dev *dev, u8 port,
+			u64 mac, u64 clear, u8 mode)
+{
+	return mlx4_cmd(dev, (mac | (clear << 63)), port, mode,
+			MLX4_CMD_SET_MCAST_FLTR, MLX4_CMD_TIME_CLASS_B,
+			MLX4_CMD_WRAPPED);
+}
+EXPORT_SYMBOL(mlx4_SET_MCAST_FLTR);
+
+int mlx4_SET_VLAN_FLTR_wrapper(struct mlx4_dev *dev, int slave,
+			       struct mlx4_vhcr *vhcr,
+			       struct mlx4_cmd_mailbox *inbox,
+			       struct mlx4_cmd_mailbox *outbox,
+			       struct mlx4_cmd_info *cmd)
+{
+	int err = 0;
+
+	return err;
+}
+
+int mlx4_common_dump_eth_stats(struct mlx4_dev *dev, int slave,
+			       u32 in_mod, struct mlx4_cmd_mailbox *outbox)
+{
+	return mlx4_cmd_box(dev, 0, outbox->dma, in_mod, 0,
+			    MLX4_CMD_DUMP_ETH_STATS, MLX4_CMD_TIME_CLASS_B,
+			    MLX4_CMD_NATIVE);
+}
+
+int mlx4_DUMP_ETH_STATS_wrapper(struct mlx4_dev *dev, int slave,
+				struct mlx4_vhcr *vhcr,
+				struct mlx4_cmd_mailbox *inbox,
+				struct mlx4_cmd_mailbox *outbox,
+				struct mlx4_cmd_info *cmd)
+{
+	return mlx4_common_dump_eth_stats(dev, slave,
+					  vhcr->in_modifier, outbox);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx4/profile.c b/drivers/net/ethernet/mellanox/mlx4/profile.c
index b967647..66f91ca 100644
--- a/drivers/net/ethernet/mellanox/mlx4/profile.c
+++ b/drivers/net/ethernet/mellanox/mlx4/profile.c
@@ -98,8 +98,8 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 	profile[MLX4_RES_EQ].size     = dev_cap->eqc_entry_sz;
 	profile[MLX4_RES_DMPT].size   = dev_cap->dmpt_entry_sz;
 	profile[MLX4_RES_CMPT].size   = dev_cap->cmpt_entry_sz;
-	profile[MLX4_RES_MTT].size    = dev->caps.mtts_per_seg * dev_cap->mtt_entry_sz;
-	profile[MLX4_RES_MCG].size    = MLX4_MGM_ENTRY_SIZE;
+	profile[MLX4_RES_MTT].size    = dev_cap->mtt_entry_sz;
+	profile[MLX4_RES_MCG].size    = mlx4_get_mgm_entry_size(dev);
 
 	profile[MLX4_RES_QP].num      = request->num_qp;
 	profile[MLX4_RES_RDMARC].num  = request->num_qp * request->rdmarc_per_qp;
@@ -210,7 +210,7 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 			init_hca->cmpt_base	 = profile[i].start;
 			break;
 		case MLX4_RES_MTT:
-			dev->caps.num_mtt_segs	 = profile[i].num;
+			dev->caps.num_mtts	 = profile[i].num;
 			priv->mr_table.mtt_base	 = profile[i].start;
 			init_hca->mtt_base	 = profile[i].start;
 			break;
@@ -218,7 +218,8 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 			dev->caps.num_mgms	  = profile[i].num >> 1;
 			dev->caps.num_amgms	  = profile[i].num >> 1;
 			init_hca->mc_base	  = profile[i].start;
-			init_hca->log_mc_entry_sz = ilog2(MLX4_MGM_ENTRY_SIZE);
+			init_hca->log_mc_entry_sz =
+					ilog2(mlx4_get_mgm_entry_size(dev));
 			init_hca->log_mc_table_sz = profile[i].log_num;
 			init_hca->log_mc_hash_sz  = profile[i].log_num - 1;
 			break;
diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c
index 15f870c..6b03ac8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx4/qp.c
@@ -35,6 +35,8 @@
 
 #include <linux/gfp.h>
 #include <linux/export.h>
+#include <linux/init.h>
+
 #include <linux/mlx4/cmd.h>
 #include <linux/mlx4/qp.h>
 
@@ -55,7 +57,7 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type)
 	spin_unlock(&qp_table->lock);
 
 	if (!qp) {
-		mlx4_warn(dev, "Async event for bogus QP %08x\n", qpn);
+		mlx4_dbg(dev, "Async event for none existent QP %08x\n", qpn);
 		return;
 	}
 
@@ -65,10 +67,17 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type)
 		complete(&qp->free);
 }
 
-int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
-		   enum mlx4_qp_state cur_state, enum mlx4_qp_state new_state,
-		   struct mlx4_qp_context *context, enum mlx4_qp_optpar optpar,
-		   int sqd_event, struct mlx4_qp *qp)
+static int is_qp0(struct mlx4_dev *dev, struct mlx4_qp *qp)
+{
+	return qp->qpn >= dev->caps.sqp_start &&
+		qp->qpn <= dev->caps.sqp_start + 1;
+}
+
+static int __mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
+		     enum mlx4_qp_state cur_state, enum mlx4_qp_state new_state,
+		     struct mlx4_qp_context *context,
+		     enum mlx4_qp_optpar optpar,
+		     int sqd_event, struct mlx4_qp *qp, int native)
 {
 	static const u16 op[MLX4_QP_NUM_STATE][MLX4_QP_NUM_STATE] = {
 		[MLX4_QP_STATE_RST] = {
@@ -110,16 +119,26 @@ int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 		}
 	};
 
+	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_cmd_mailbox *mailbox;
 	int ret = 0;
+	u8 port;
 
 	if (cur_state >= MLX4_QP_NUM_STATE || new_state >= MLX4_QP_NUM_STATE ||
 	    !op[cur_state][new_state])
 		return -EINVAL;
 
-	if (op[cur_state][new_state] == MLX4_CMD_2RST_QP)
-		return mlx4_cmd(dev, 0, qp->qpn, 2,
-				MLX4_CMD_2RST_QP, MLX4_CMD_TIME_CLASS_A);
+	if (op[cur_state][new_state] == MLX4_CMD_2RST_QP) {
+		ret = mlx4_cmd(dev, 0, qp->qpn, 2,
+			MLX4_CMD_2RST_QP, MLX4_CMD_TIME_CLASS_A, native);
+		if (mlx4_is_master(dev) && cur_state != MLX4_QP_STATE_ERR &&
+		    cur_state != MLX4_QP_STATE_RST &&
+		    is_qp0(dev, qp)) {
+			port = (qp->qpn & 1) + 1;
+			priv->mfunc.master.qp0_state[port].qp0_active = 0;
+		}
+		return ret;
+	}
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
@@ -132,107 +151,218 @@ int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 		context->log_page_size   = mtt->page_shift - MLX4_ICM_PAGE_SHIFT;
 	}
 
+	port = ((context->pri_path.sched_queue >> 6) & 1) + 1;
+	if (dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH)
+		context->pri_path.sched_queue = (context->pri_path.sched_queue &
+						0xc3);
+
 	*(__be32 *) mailbox->buf = cpu_to_be32(optpar);
 	memcpy(mailbox->buf + 8, context, sizeof *context);
 
 	((struct mlx4_qp_context *) (mailbox->buf + 8))->local_qpn =
 		cpu_to_be32(qp->qpn);
 
-	ret = mlx4_cmd(dev, mailbox->dma, qp->qpn | (!!sqd_event << 31),
+	ret = mlx4_cmd(dev, mailbox->dma | dev->caps.function,
+		       qp->qpn | (!!sqd_event << 31),
 		       new_state == MLX4_QP_STATE_RST ? 2 : 0,
-		       op[cur_state][new_state], MLX4_CMD_TIME_CLASS_C);
+		       op[cur_state][new_state], MLX4_CMD_TIME_CLASS_C, native);
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	return ret;
 }
+
+int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
+		   enum mlx4_qp_state cur_state, enum mlx4_qp_state new_state,
+		   struct mlx4_qp_context *context,
+		   enum mlx4_qp_optpar optpar,
+		   int sqd_event, struct mlx4_qp *qp)
+{
+	return __mlx4_qp_modify(dev, mtt, cur_state, new_state, context,
+				optpar, sqd_event, qp, 0);
+}
 EXPORT_SYMBOL_GPL(mlx4_qp_modify);
 
-int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base)
+int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
+				   int *base)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_qp_table *qp_table = &priv->qp_table;
-	int qpn;
 
-	qpn = mlx4_bitmap_alloc_range(&qp_table->bitmap, cnt, align);
-	if (qpn == -1)
+	*base = mlx4_bitmap_alloc_range(&qp_table->bitmap, cnt, align);
+	if (*base == -1)
 		return -ENOMEM;
 
-	*base = qpn;
 	return 0;
 }
+
+int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base)
+{
+	u64 in_param;
+	u64 out_param;
+	int err;
+
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&in_param, cnt);
+		set_param_h(&in_param, align);
+		err = mlx4_cmd_imm(dev, in_param, &out_param,
+				   RES_QP, RES_OP_RESERVE,
+				   MLX4_CMD_ALLOC_RES,
+				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		if (err)
+			return err;
+
+		*base = get_param_l(&out_param);
+		return 0;
+	}
+	return __mlx4_qp_reserve_range(dev, cnt, align, base);
+}
 EXPORT_SYMBOL_GPL(mlx4_qp_reserve_range);
 
-void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
+void __mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_qp_table *qp_table = &priv->qp_table;
-	if (base_qpn < dev->caps.sqp_start + 8)
-		return;
 
+	if (mlx4_is_qp_reserved(dev, (u32) base_qpn))
+		return;
 	mlx4_bitmap_free_range(&qp_table->bitmap, base_qpn, cnt);
 }
+
+void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
+{
+	u64 in_param;
+	int err;
+
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&in_param, base_qpn);
+		set_param_h(&in_param, cnt);
+		err = mlx4_cmd(dev, in_param, RES_QP, RES_OP_RESERVE,
+			       MLX4_CMD_FREE_RES,
+			       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		if (err) {
+			mlx4_warn(dev, "Failed to release qp range"
+				  " base:%d cnt:%d\n", base_qpn, cnt);
+		}
+	} else
+		 __mlx4_qp_release_range(dev, base_qpn, cnt);
+}
 EXPORT_SYMBOL_GPL(mlx4_qp_release_range);
 
-int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp)
+int __mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_qp_table *qp_table = &priv->qp_table;
 	int err;
 
-	if (!qpn)
-		return -EINVAL;
-
-	qp->qpn = qpn;
-
-	err = mlx4_table_get(dev, &qp_table->qp_table, qp->qpn);
+	err = mlx4_table_get(dev, &qp_table->qp_table, qpn);
 	if (err)
 		goto err_out;
 
-	err = mlx4_table_get(dev, &qp_table->auxc_table, qp->qpn);
+	err = mlx4_table_get(dev, &qp_table->auxc_table, qpn);
 	if (err)
 		goto err_put_qp;
 
-	err = mlx4_table_get(dev, &qp_table->altc_table, qp->qpn);
+	err = mlx4_table_get(dev, &qp_table->altc_table, qpn);
 	if (err)
 		goto err_put_auxc;
 
-	err = mlx4_table_get(dev, &qp_table->rdmarc_table, qp->qpn);
+	err = mlx4_table_get(dev, &qp_table->rdmarc_table, qpn);
 	if (err)
 		goto err_put_altc;
 
-	err = mlx4_table_get(dev, &qp_table->cmpt_table, qp->qpn);
+	err = mlx4_table_get(dev, &qp_table->cmpt_table, qpn);
 	if (err)
 		goto err_put_rdmarc;
 
-	spin_lock_irq(&qp_table->lock);
-	err = radix_tree_insert(&dev->qp_table_tree, qp->qpn & (dev->caps.num_qps - 1), qp);
-	spin_unlock_irq(&qp_table->lock);
-	if (err)
-		goto err_put_cmpt;
-
-	atomic_set(&qp->refcount, 1);
-	init_completion(&qp->free);
-
 	return 0;
 
-err_put_cmpt:
-	mlx4_table_put(dev, &qp_table->cmpt_table, qp->qpn);
-
 err_put_rdmarc:
-	mlx4_table_put(dev, &qp_table->rdmarc_table, qp->qpn);
+	mlx4_table_put(dev, &qp_table->rdmarc_table, qpn);
 
 err_put_altc:
-	mlx4_table_put(dev, &qp_table->altc_table, qp->qpn);
+	mlx4_table_put(dev, &qp_table->altc_table, qpn);
 
 err_put_auxc:
-	mlx4_table_put(dev, &qp_table->auxc_table, qp->qpn);
+	mlx4_table_put(dev, &qp_table->auxc_table, qpn);
 
 err_put_qp:
-	mlx4_table_put(dev, &qp_table->qp_table, qp->qpn);
+	mlx4_table_put(dev, &qp_table->qp_table, qpn);
 
 err_out:
 	return err;
 }
+
+static int mlx4_qp_alloc_icm(struct mlx4_dev *dev, int qpn)
+{
+	u64 param;
+
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&param, qpn);
+		return mlx4_cmd_imm(dev, param, &param, RES_QP, RES_OP_MAP_ICM,
+				    MLX4_CMD_ALLOC_RES, MLX4_CMD_TIME_CLASS_A,
+				    MLX4_CMD_WRAPPED);
+	}
+	return __mlx4_qp_alloc_icm(dev, qpn);
+}
+
+void __mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_qp_table *qp_table = &priv->qp_table;
+
+	mlx4_table_put(dev, &qp_table->cmpt_table, qpn);
+	mlx4_table_put(dev, &qp_table->rdmarc_table, qpn);
+	mlx4_table_put(dev, &qp_table->altc_table, qpn);
+	mlx4_table_put(dev, &qp_table->auxc_table, qpn);
+	mlx4_table_put(dev, &qp_table->qp_table, qpn);
+}
+
+static void mlx4_qp_free_icm(struct mlx4_dev *dev, int qpn)
+{
+	u64 in_param;
+
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&in_param, qpn);
+		if (mlx4_cmd(dev, in_param, RES_QP, RES_OP_MAP_ICM,
+			     MLX4_CMD_FREE_RES, MLX4_CMD_TIME_CLASS_A,
+			     MLX4_CMD_WRAPPED))
+			mlx4_warn(dev, "Failed to free icm of qp:%d\n", qpn);
+	} else
+		__mlx4_qp_free_icm(dev, qpn);
+}
+
+int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_qp_table *qp_table = &priv->qp_table;
+	int err;
+
+	if (!qpn)
+		return -EINVAL;
+
+	qp->qpn = qpn;
+
+	err = mlx4_qp_alloc_icm(dev, qpn);
+	if (err)
+		return err;
+
+	spin_lock_irq(&qp_table->lock);
+	err = radix_tree_insert(&dev->qp_table_tree, qp->qpn &
+				(dev->caps.num_qps - 1), qp);
+	spin_unlock_irq(&qp_table->lock);
+	if (err)
+		goto err_icm;
+
+	atomic_set(&qp->refcount, 1);
+	init_completion(&qp->free);
+
+	return 0;
+
+err_icm:
+	mlx4_qp_free_icm(dev, qpn);
+	return err;
+}
+
 EXPORT_SYMBOL_GPL(mlx4_qp_alloc);
 
 void mlx4_qp_remove(struct mlx4_dev *dev, struct mlx4_qp *qp)
@@ -248,24 +378,18 @@ EXPORT_SYMBOL_GPL(mlx4_qp_remove);
 
 void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp)
 {
-	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
-
 	if (atomic_dec_and_test(&qp->refcount))
 		complete(&qp->free);
 	wait_for_completion(&qp->free);
 
-	mlx4_table_put(dev, &qp_table->cmpt_table, qp->qpn);
-	mlx4_table_put(dev, &qp_table->rdmarc_table, qp->qpn);
-	mlx4_table_put(dev, &qp_table->altc_table, qp->qpn);
-	mlx4_table_put(dev, &qp_table->auxc_table, qp->qpn);
-	mlx4_table_put(dev, &qp_table->qp_table, qp->qpn);
+	mlx4_qp_free_icm(dev, qp->qpn);
 }
 EXPORT_SYMBOL_GPL(mlx4_qp_free);
 
 static int mlx4_CONF_SPECIAL_QP(struct mlx4_dev *dev, u32 base_qpn)
 {
 	return mlx4_cmd(dev, 0, base_qpn, 0, MLX4_CMD_CONF_SPECIAL_QP,
-			MLX4_CMD_TIME_CLASS_B);
+			MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
 }
 
 int mlx4_init_qp_table(struct mlx4_dev *dev)
@@ -276,6 +400,8 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 
 	spin_lock_init(&qp_table->lock);
 	INIT_RADIX_TREE(&dev->qp_table_tree, GFP_ATOMIC);
+	if (mlx4_is_slave(dev))
+		return 0;
 
 	/*
 	 * We reserve 2 extra QPs per port for the special QPs.  The
@@ -327,6 +453,9 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 
 void mlx4_cleanup_qp_table(struct mlx4_dev *dev)
 {
+	if (mlx4_is_slave(dev))
+		return;
+
 	mlx4_CONF_SPECIAL_QP(dev, 0);
 	mlx4_bitmap_cleanup(&mlx4_priv(dev)->qp_table.bitmap);
 }
@@ -342,7 +471,8 @@ int mlx4_qp_query(struct mlx4_dev *dev, struct mlx4_qp *qp,
 		return PTR_ERR(mailbox);
 
 	err = mlx4_cmd_box(dev, 0, mailbox->dma, qp->qpn, 0,
-			   MLX4_CMD_QUERY_QP, MLX4_CMD_TIME_CLASS_A);
+			   MLX4_CMD_QUERY_QP, MLX4_CMD_TIME_CLASS_A,
+			   MLX4_CMD_WRAPPED);
 	if (!err)
 		memcpy(context, mailbox->buf + 8, sizeof *context);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
new file mode 100644
index 0000000..bdd61c3
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -0,0 +1,3103 @@
+/*
+ * Copyright (c) 2004, 2005 Topspin Communications.  All rights reserved.
+ * Copyright (c) 2005, 2006, 2007, 2008 Mellanox Technologies.
+ * All rights reserved.
+ * Copyright (c) 2005, 2006, 2007 Cisco Systems, Inc.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/sched.h>
+#include <linux/pci.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/mlx4/cmd.h>
+#include <linux/mlx4/qp.h>
+
+#include "mlx4.h"
+#include "fw.h"
+
+#define MLX4_MAC_VALID		(1ull << 63)
+#define MLX4_MAC_MASK		0x7fffffffffffffffULL
+#define ETH_ALEN		6
+
+struct mac_res {
+	struct list_head list;
+	u64 mac;
+	u8 port;
+};
+
+struct res_common {
+	struct list_head	list;
+	u32		        res_id;
+	int			owner;
+	int			state;
+	int			from_state;
+	int			to_state;
+	int			removing;
+};
+
+enum {
+	RES_ANY_BUSY = 1
+};
+
+struct res_gid {
+	struct list_head	list;
+	u8			gid[16];
+	enum mlx4_protocol	prot;
+};
+
+enum res_qp_states {
+	RES_QP_BUSY = RES_ANY_BUSY,
+
+	/* QP number was allocated */
+	RES_QP_RESERVED,
+
+	/* ICM memory for QP context was mapped */
+	RES_QP_MAPPED,
+
+	/* QP is in hw ownership */
+	RES_QP_HW
+};
+
+static inline const char *qp_states_str(enum res_qp_states state)
+{
+	switch (state) {
+	case RES_QP_BUSY: return "RES_QP_BUSY";
+	case RES_QP_RESERVED: return "RES_QP_RESERVED";
+	case RES_QP_MAPPED: return "RES_QP_MAPPED";
+	case RES_QP_HW: return "RES_QP_HW";
+	default: return "Unknown";
+	}
+}
+
+struct res_qp {
+	struct res_common	com;
+	struct res_mtt	       *mtt;
+	struct res_cq	       *rcq;
+	struct res_cq	       *scq;
+	struct res_srq	       *srq;
+	struct list_head	mcg_list;
+	spinlock_t		mcg_spl;
+	int			local_qpn;
+};
+
+enum res_mtt_states {
+	RES_MTT_BUSY = RES_ANY_BUSY,
+	RES_MTT_ALLOCATED,
+};
+
+static inline const char *mtt_states_str(enum res_mtt_states state)
+{
+	switch (state) {
+	case RES_MTT_BUSY: return "RES_MTT_BUSY";
+	case RES_MTT_ALLOCATED: return "RES_MTT_ALLOCATED";
+	default: return "Unknown";
+	}
+}
+
+struct res_mtt {
+	struct res_common	com;
+	int			order;
+	atomic_t		ref_count;
+};
+
+enum res_mpt_states {
+	RES_MPT_BUSY = RES_ANY_BUSY,
+	RES_MPT_RESERVED,
+	RES_MPT_MAPPED,
+	RES_MPT_HW,
+};
+
+struct res_mpt {
+	struct res_common	com;
+	struct res_mtt	       *mtt;
+	int			key;
+};
+
+enum res_eq_states {
+	RES_EQ_BUSY = RES_ANY_BUSY,
+	RES_EQ_RESERVED,
+	RES_EQ_HW,
+};
+
+struct res_eq {
+	struct res_common	com;
+	struct res_mtt	       *mtt;
+};
+
+enum res_cq_states {
+	RES_CQ_BUSY = RES_ANY_BUSY,
+	RES_CQ_ALLOCATED,
+	RES_CQ_HW,
+};
+
+struct res_cq {
+	struct res_common	com;
+	struct res_mtt	       *mtt;
+	atomic_t		ref_count;
+};
+
+enum res_srq_states {
+	RES_SRQ_BUSY = RES_ANY_BUSY,
+	RES_SRQ_ALLOCATED,
+	RES_SRQ_HW,
+};
+
+static inline const char *srq_states_str(enum res_srq_states state)
+{
+	switch (state) {
+	case RES_SRQ_BUSY: return "RES_SRQ_BUSY";
+	case RES_SRQ_ALLOCATED: return "RES_SRQ_ALLOCATED";
+	case RES_SRQ_HW: return "RES_SRQ_HW";
+	default: return "Unknown";
+	}
+}
+
+struct res_srq {
+	struct res_common	com;
+	struct res_mtt	       *mtt;
+	struct res_cq	       *cq;
+	atomic_t		ref_count;
+};
+
+enum res_counter_states {
+	RES_COUNTER_BUSY = RES_ANY_BUSY,
+	RES_COUNTER_ALLOCATED,
+};
+
+static inline const char *counter_states_str(enum res_counter_states state)
+{
+	switch (state) {
+	case RES_COUNTER_BUSY: return "RES_COUNTER_BUSY";
+	case RES_COUNTER_ALLOCATED: return "RES_COUNTER_ALLOCATED";
+	default: return "Unknown";
+	}
+}
+
+struct res_counter {
+	struct res_common	com;
+	int			port;
+};
+
+/* For Debug uses */
+static const char *ResourceType(enum mlx4_resource rt)
+{
+	switch (rt) {
+	case RES_QP: return "RES_QP";
+	case RES_CQ: return "RES_CQ";
+	case RES_SRQ: return "RES_SRQ";
+	case RES_MPT: return "RES_MPT";
+	case RES_MTT: return "RES_MTT";
+	case RES_MAC: return  "RES_MAC";
+	case RES_EQ: return "RES_EQ";
+	case RES_COUNTER: return "RES_COUNTER";
+	default: return "Unknown resource type !!!";
+	};
+}
+
+int mlx4_init_resource_tracker(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int i;
+	int t;
+
+	priv->mfunc.master.res_tracker.slave_list =
+		kzalloc(dev->num_slaves * sizeof(struct slave_list),
+			GFP_KERNEL);
+	if (!priv->mfunc.master.res_tracker.slave_list)
+		return -ENOMEM;
+
+	for (i = 0 ; i < dev->num_slaves; i++) {
+		for (t = 0; t < MLX4_NUM_OF_RESOURCE_TYPE; ++t)
+			INIT_LIST_HEAD(&priv->mfunc.master.res_tracker.
+				       slave_list[i].res_list[t]);
+		mutex_init(&priv->mfunc.master.res_tracker.slave_list[i].mutex);
+	}
+
+	mlx4_dbg(dev, "Started init_resource_tracker: %ld slaves\n",
+		 dev->num_slaves);
+	for (i = 0 ; i < MLX4_NUM_OF_RESOURCE_TYPE; i++)
+		INIT_RADIX_TREE(&priv->mfunc.master.res_tracker.res_tree[i],
+				GFP_ATOMIC|__GFP_NOWARN);
+
+	spin_lock_init(&priv->mfunc.master.res_tracker.lock);
+	return 0 ;
+}
+
+void mlx4_free_resource_tracker(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int i;
+
+	if (priv->mfunc.master.res_tracker.slave_list) {
+		for (i = 0 ; i < dev->num_slaves; i++)
+			mlx4_delete_all_resources_for_slave(dev, i);
+
+		kfree(priv->mfunc.master.res_tracker.slave_list);
+	}
+}
+
+static void update_ud_gid(struct mlx4_dev *dev,
+			  struct mlx4_qp_context *qp_ctx, u8 slave)
+{
+	u32 ts = (be32_to_cpu(qp_ctx->flags) >> 16) & 0xff;
+
+	if (MLX4_QP_ST_UD == ts)
+		qp_ctx->pri_path.mgid_index = 0x80 | slave;
+
+	mlx4_dbg(dev, "slave %d, new gid index: 0x%x ",
+		slave, qp_ctx->pri_path.mgid_index);
+}
+
+static int mpt_mask(struct mlx4_dev *dev)
+{
+	return dev->caps.num_mpts - 1;
+}
+
+static void *find_res(struct mlx4_dev *dev, int res_id,
+		      enum mlx4_resource type)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	return radix_tree_lookup(&priv->mfunc.master.res_tracker.res_tree[type],
+				 res_id);
+}
+
+static int get_res(struct mlx4_dev *dev, int slave, int res_id,
+		   enum mlx4_resource type,
+		   void *res)
+{
+	struct res_common *r;
+	int err = 0;
+
+	spin_lock_irq(mlx4_tlock(dev));
+	r = find_res(dev, res_id, type);
+	if (!r) {
+		err = -ENONET;
+		goto exit;
+	}
+
+	if (r->state == RES_ANY_BUSY) {
+		err = -EBUSY;
+		goto exit;
+	}
+
+	if (r->owner != slave) {
+		err = -EPERM;
+		goto exit;
+	}
+
+	r->from_state = r->state;
+	r->state = RES_ANY_BUSY;
+	mlx4_dbg(dev, "res %s id 0x%x to busy\n",
+		 ResourceType(type), r->res_id);
+
+	if (res)
+		*((struct res_common **)res) = r;
+
+exit:
+	spin_unlock_irq(mlx4_tlock(dev));
+	return err;
+}
+
+int mlx4_get_slave_from_resource_id(struct mlx4_dev *dev,
+				    enum mlx4_resource type,
+				    int res_id, int *slave)
+{
+
+	struct res_common *r;
+	int err = -ENOENT;
+	int id = res_id;
+
+	if (type == RES_QP)
+		id &= 0x7fffff;
+	spin_lock_irq(mlx4_tlock(dev));
+
+	r = find_res(dev, id, type);
+	if (r) {
+		*slave = r->owner;
+		err = 0;
+	}
+	spin_unlock_irq(mlx4_tlock(dev));
+
+	return err;
+}
+
+static void put_res(struct mlx4_dev *dev, int slave, int res_id,
+		    enum mlx4_resource type)
+{
+	struct res_common *r;
+
+	spin_lock_irq(mlx4_tlock(dev));
+	r = find_res(dev, res_id, type);
+	if (r)
+		r->state = r->from_state;
+	spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static struct res_common *alloc_qp_tr(int id)
+{
+	struct res_qp *ret;
+
+	ret = kzalloc(sizeof *ret, GFP_KERNEL);
+	if (!ret)
+		return NULL;
+
+	ret->com.res_id = id;
+	ret->com.state = RES_QP_RESERVED;
+	INIT_LIST_HEAD(&ret->mcg_list);
+	spin_lock_init(&ret->mcg_spl);
+
+	return &ret->com;
+}
+
+static struct res_common *alloc_mtt_tr(int id, int order)
+{
+	struct res_mtt *ret;
+
+	ret = kzalloc(sizeof *ret, GFP_KERNEL);
+	if (!ret)
+		return NULL;
+
+	ret->com.res_id = id;
+	ret->order = order;
+	ret->com.state = RES_MTT_ALLOCATED;
+	atomic_set(&ret->ref_count, 0);
+
+	return &ret->com;
+}
+
+static struct res_common *alloc_mpt_tr(int id, int key)
+{
+	struct res_mpt *ret;
+
+	ret = kzalloc(sizeof *ret, GFP_KERNEL);
+	if (!ret)
+		return NULL;
+
+	ret->com.res_id = id;
+	ret->com.state = RES_MPT_RESERVED;
+	ret->key = key;
+
+	return &ret->com;
+}
+
+static struct res_common *alloc_eq_tr(int id)
+{
+	struct res_eq *ret;
+
+	ret = kzalloc(sizeof *ret, GFP_KERNEL);
+	if (!ret)
+		return NULL;
+
+	ret->com.res_id = id;
+	ret->com.state = RES_EQ_RESERVED;
+
+	return &ret->com;
+}
+
+static struct res_common *alloc_cq_tr(int id)
+{
+	struct res_cq *ret;
+
+	ret = kzalloc(sizeof *ret, GFP_KERNEL);
+	if (!ret)
+		return NULL;
+
+	ret->com.res_id = id;
+	ret->com.state = RES_CQ_ALLOCATED;
+	atomic_set(&ret->ref_count, 0);
+
+	return &ret->com;
+}
+
+static struct res_common *alloc_srq_tr(int id)
+{
+	struct res_srq *ret;
+
+	ret = kzalloc(sizeof *ret, GFP_KERNEL);
+	if (!ret)
+		return NULL;
+
+	ret->com.res_id = id;
+	ret->com.state = RES_SRQ_ALLOCATED;
+	atomic_set(&ret->ref_count, 0);
+
+	return &ret->com;
+}
+
+static struct res_common *alloc_counter_tr(int id)
+{
+	struct res_counter *ret;
+
+	ret = kzalloc(sizeof *ret, GFP_KERNEL);
+	if (!ret)
+		return NULL;
+
+	ret->com.res_id = id;
+	ret->com.state = RES_COUNTER_ALLOCATED;
+
+	return &ret->com;
+}
+
+static struct res_common *alloc_tr(int id, enum mlx4_resource type, int slave,
+				   int extra)
+{
+	struct res_common *ret;
+
+	switch (type) {
+	case RES_QP:
+		ret = alloc_qp_tr(id);
+		break;
+	case RES_MPT:
+		ret = alloc_mpt_tr(id, extra);
+		break;
+	case RES_MTT:
+		ret = alloc_mtt_tr(id, extra);
+		break;
+	case RES_EQ:
+		ret = alloc_eq_tr(id);
+		break;
+	case RES_CQ:
+		ret = alloc_cq_tr(id);
+		break;
+	case RES_SRQ:
+		ret = alloc_srq_tr(id);
+		break;
+	case RES_MAC:
+		printk(KERN_ERR "implementation missing\n");
+		return NULL;
+	case RES_COUNTER:
+		ret = alloc_counter_tr(id);
+		break;
+
+	default:
+		return NULL;
+	}
+	if (ret)
+		ret->owner = slave;
+
+	return ret;
+}
+
+static int add_res_range(struct mlx4_dev *dev, int slave, int base, int count,
+			 enum mlx4_resource type, int extra)
+{
+	int i;
+	int err;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct res_common **res_arr;
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct radix_tree_root *root = &tracker->res_tree[type];
+
+	res_arr = kzalloc(count * sizeof *res_arr, GFP_KERNEL);
+	if (!res_arr)
+		return -ENOMEM;
+
+	for (i = 0; i < count; ++i) {
+		res_arr[i] = alloc_tr(base + i, type, slave, extra);
+		if (!res_arr[i]) {
+			for (--i; i >= 0; --i)
+				kfree(res_arr[i]);
+
+			kfree(res_arr);
+			return -ENOMEM;
+		}
+	}
+
+	spin_lock_irq(mlx4_tlock(dev));
+	for (i = 0; i < count; ++i) {
+		if (find_res(dev, base + i, type)) {
+			err = -EEXIST;
+			goto undo;
+		}
+		err = radix_tree_insert(root, base + i, res_arr[i]);
+		if (err)
+			goto undo;
+		list_add_tail(&res_arr[i]->list,
+			      &tracker->slave_list[slave].res_list[type]);
+	}
+	spin_unlock_irq(mlx4_tlock(dev));
+	kfree(res_arr);
+
+	return 0;
+
+undo:
+	for (--i; i >= base; --i)
+		radix_tree_delete(&tracker->res_tree[type], i);
+
+	spin_unlock_irq(mlx4_tlock(dev));
+
+	for (i = 0; i < count; ++i)
+		kfree(res_arr[i]);
+
+	kfree(res_arr);
+
+	return err;
+}
+
+static int remove_qp_ok(struct res_qp *res)
+{
+	if (res->com.state == RES_QP_BUSY)
+		return -EBUSY;
+	else if (res->com.state != RES_QP_RESERVED)
+		return -EPERM;
+
+	return 0;
+}
+
+static int remove_mtt_ok(struct res_mtt *res, int order)
+{
+	if (res->com.state == RES_MTT_BUSY ||
+	    atomic_read(&res->ref_count)) {
+		printk(KERN_DEBUG "%s-%d: state %s, ref_count %d\n",
+		       __func__, __LINE__,
+		       mtt_states_str(res->com.state),
+		       atomic_read(&res->ref_count));
+		return -EBUSY;
+	} else if (res->com.state != RES_MTT_ALLOCATED)
+		return -EPERM;
+	else if (res->order != order)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int remove_mpt_ok(struct res_mpt *res)
+{
+	if (res->com.state == RES_MPT_BUSY)
+		return -EBUSY;
+	else if (res->com.state != RES_MPT_RESERVED)
+		return -EPERM;
+
+	return 0;
+}
+
+static int remove_eq_ok(struct res_eq *res)
+{
+	if (res->com.state == RES_MPT_BUSY)
+		return -EBUSY;
+	else if (res->com.state != RES_MPT_RESERVED)
+		return -EPERM;
+
+	return 0;
+}
+
+static int remove_counter_ok(struct res_counter *res)
+{
+	if (res->com.state == RES_COUNTER_BUSY)
+		return -EBUSY;
+	else if (res->com.state != RES_COUNTER_ALLOCATED)
+		return -EPERM;
+
+	return 0;
+}
+
+static int remove_cq_ok(struct res_cq *res)
+{
+	if (res->com.state == RES_CQ_BUSY)
+		return -EBUSY;
+	else if (res->com.state != RES_CQ_ALLOCATED)
+		return -EPERM;
+
+	return 0;
+}
+
+static int remove_srq_ok(struct res_srq *res)
+{
+	if (res->com.state == RES_SRQ_BUSY)
+		return -EBUSY;
+	else if (res->com.state != RES_SRQ_ALLOCATED)
+		return -EPERM;
+
+	return 0;
+}
+
+static int remove_ok(struct res_common *res, enum mlx4_resource type, int extra)
+{
+	switch (type) {
+	case RES_QP:
+		return remove_qp_ok((struct res_qp *)res);
+	case RES_CQ:
+		return remove_cq_ok((struct res_cq *)res);
+	case RES_SRQ:
+		return remove_srq_ok((struct res_srq *)res);
+	case RES_MPT:
+		return remove_mpt_ok((struct res_mpt *)res);
+	case RES_MTT:
+		return remove_mtt_ok((struct res_mtt *)res, extra);
+	case RES_MAC:
+		return -ENOSYS;
+	case RES_EQ:
+		return remove_eq_ok((struct res_eq *)res);
+	case RES_COUNTER:
+		return remove_counter_ok((struct res_counter *)res);
+	default:
+		return -EINVAL;
+	}
+}
+
+static int rem_res_range(struct mlx4_dev *dev, int slave, int base, int count,
+			 enum mlx4_resource type, int extra)
+{
+	int i;
+	int err;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct res_common *r;
+
+	spin_lock_irq(mlx4_tlock(dev));
+	for (i = base; i < base + count; ++i) {
+		r = radix_tree_lookup(&tracker->res_tree[type], i);
+		if (!r) {
+			err = -ENOENT;
+			goto out;
+		}
+		if (r->owner != slave) {
+			err = -EPERM;
+			goto out;
+		}
+		err = remove_ok(r, type, extra);
+		if (err)
+			goto out;
+	}
+
+	for (i = base; i < base + count; ++i) {
+		r = radix_tree_lookup(&tracker->res_tree[type], i);
+		radix_tree_delete(&tracker->res_tree[type], i);
+		list_del(&r->list);
+		kfree(r);
+	}
+	err = 0;
+
+out:
+	spin_unlock_irq(mlx4_tlock(dev));
+
+	return err;
+}
+
+static int qp_res_start_move_to(struct mlx4_dev *dev, int slave, int qpn,
+				enum res_qp_states state, struct res_qp **qp,
+				int alloc)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct res_qp *r;
+	int err = 0;
+
+	spin_lock_irq(mlx4_tlock(dev));
+	r = radix_tree_lookup(&tracker->res_tree[RES_QP], qpn);
+	if (!r)
+		err = -ENOENT;
+	else if (r->com.owner != slave)
+		err = -EPERM;
+	else {
+		switch (state) {
+		case RES_QP_BUSY:
+			mlx4_dbg(dev, "%s: failed RES_QP, 0x%x\n",
+				 __func__, r->com.res_id);
+			err = -EBUSY;
+			break;
+
+		case RES_QP_RESERVED:
+			if (r->com.state == RES_QP_MAPPED && !alloc)
+				break;
+
+			mlx4_dbg(dev, "failed RES_QP, 0x%x\n", r->com.res_id);
+			err = -EINVAL;
+			break;
+
+		case RES_QP_MAPPED:
+			if ((r->com.state == RES_QP_RESERVED && alloc) ||
+			    r->com.state == RES_QP_HW)
+				break;
+			else {
+				mlx4_dbg(dev, "failed RES_QP, 0x%x\n",
+					  r->com.res_id);
+				err = -EINVAL;
+			}
+
+			break;
+
+		case RES_QP_HW:
+			if (r->com.state != RES_QP_MAPPED)
+				err = -EINVAL;
+			break;
+		default:
+			err = -EINVAL;
+		}
+
+		if (!err) {
+			r->com.from_state = r->com.state;
+			r->com.to_state = state;
+			r->com.state = RES_QP_BUSY;
+			if (qp)
+				*qp = (struct res_qp *)r;
+		}
+	}
+
+	spin_unlock_irq(mlx4_tlock(dev));
+
+	return err;
+}
+
+static int mr_res_start_move_to(struct mlx4_dev *dev, int slave, int index,
+				enum res_mpt_states state, struct res_mpt **mpt)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct res_mpt *r;
+	int err = 0;
+
+	spin_lock_irq(mlx4_tlock(dev));
+	r = radix_tree_lookup(&tracker->res_tree[RES_MPT], index);
+	if (!r)
+		err = -ENOENT;
+	else if (r->com.owner != slave)
+		err = -EPERM;
+	else {
+		switch (state) {
+		case RES_MPT_BUSY:
+			err = -EINVAL;
+			break;
+
+		case RES_MPT_RESERVED:
+			if (r->com.state != RES_MPT_MAPPED)
+				err = -EINVAL;
+			break;
+
+		case RES_MPT_MAPPED:
+			if (r->com.state != RES_MPT_RESERVED &&
+			    r->com.state != RES_MPT_HW)
+				err = -EINVAL;
+			break;
+
+		case RES_MPT_HW:
+			if (r->com.state != RES_MPT_MAPPED)
+				err = -EINVAL;
+			break;
+		default:
+			err = -EINVAL;
+		}
+
+		if (!err) {
+			r->com.from_state = r->com.state;
+			r->com.to_state = state;
+			r->com.state = RES_MPT_BUSY;
+			if (mpt)
+				*mpt = (struct res_mpt *)r;
+		}
+	}
+
+	spin_unlock_irq(mlx4_tlock(dev));
+
+	return err;
+}
+
+static int eq_res_start_move_to(struct mlx4_dev *dev, int slave, int index,
+				enum res_eq_states state, struct res_eq **eq)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct res_eq *r;
+	int err = 0;
+
+	spin_lock_irq(mlx4_tlock(dev));
+	r = radix_tree_lookup(&tracker->res_tree[RES_EQ], index);
+	if (!r)
+		err = -ENOENT;
+	else if (r->com.owner != slave)
+		err = -EPERM;
+	else {
+		switch (state) {
+		case RES_EQ_BUSY:
+			err = -EINVAL;
+			break;
+
+		case RES_EQ_RESERVED:
+			if (r->com.state != RES_EQ_HW)
+				err = -EINVAL;
+			break;
+
+		case RES_EQ_HW:
+			if (r->com.state != RES_EQ_RESERVED)
+				err = -EINVAL;
+			break;
+
+		default:
+			err = -EINVAL;
+		}
+
+		if (!err) {
+			r->com.from_state = r->com.state;
+			r->com.to_state = state;
+			r->com.state = RES_EQ_BUSY;
+			if (eq)
+				*eq = r;
+		}
+	}
+
+	spin_unlock_irq(mlx4_tlock(dev));
+
+	return err;
+}
+
+static int cq_res_start_move_to(struct mlx4_dev *dev, int slave, int cqn,
+				enum res_cq_states state, struct res_cq **cq)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct res_cq *r;
+	int err;
+
+	spin_lock_irq(mlx4_tlock(dev));
+	r = radix_tree_lookup(&tracker->res_tree[RES_CQ], cqn);
+	if (!r)
+		err = -ENOENT;
+	else if (r->com.owner != slave)
+		err = -EPERM;
+	else {
+		switch (state) {
+		case RES_CQ_BUSY:
+			err = -EBUSY;
+			break;
+
+		case RES_CQ_ALLOCATED:
+			if (r->com.state != RES_CQ_HW)
+				err = -EINVAL;
+			else if (atomic_read(&r->ref_count))
+				err = -EBUSY;
+			else
+				err = 0;
+			break;
+
+		case RES_CQ_HW:
+			if (r->com.state != RES_CQ_ALLOCATED)
+				err = -EINVAL;
+			else
+				err = 0;
+			break;
+
+		default:
+			err = -EINVAL;
+		}
+
+		if (!err) {
+			r->com.from_state = r->com.state;
+			r->com.to_state = state;
+			r->com.state = RES_CQ_BUSY;
+			if (cq)
+				*cq = r;
+		}
+	}
+
+	spin_unlock_irq(mlx4_tlock(dev));
+
+	return err;
+}
+
+static int srq_res_start_move_to(struct mlx4_dev *dev, int slave, int index,
+				 enum res_cq_states state, struct res_srq **srq)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct res_srq *r;
+	int err = 0;
+
+	spin_lock_irq(mlx4_tlock(dev));
+	r = radix_tree_lookup(&tracker->res_tree[RES_SRQ], index);
+	if (!r)
+		err = -ENOENT;
+	else if (r->com.owner != slave)
+		err = -EPERM;
+	else {
+		switch (state) {
+		case RES_SRQ_BUSY:
+			err = -EINVAL;
+			break;
+
+		case RES_SRQ_ALLOCATED:
+			if (r->com.state != RES_SRQ_HW)
+				err = -EINVAL;
+			else if (atomic_read(&r->ref_count))
+				err = -EBUSY;
+			break;
+
+		case RES_SRQ_HW:
+			if (r->com.state != RES_SRQ_ALLOCATED)
+				err = -EINVAL;
+			break;
+
+		default:
+			err = -EINVAL;
+		}
+
+		if (!err) {
+			r->com.from_state = r->com.state;
+			r->com.to_state = state;
+			r->com.state = RES_SRQ_BUSY;
+			if (srq)
+				*srq = r;
+		}
+	}
+
+	spin_unlock_irq(mlx4_tlock(dev));
+
+	return err;
+}
+
+static void res_abort_move(struct mlx4_dev *dev, int slave,
+			   enum mlx4_resource type, int id)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct res_common *r;
+
+	spin_lock_irq(mlx4_tlock(dev));
+	r = radix_tree_lookup(&tracker->res_tree[type], id);
+	if (r && (r->owner == slave))
+		r->state = r->from_state;
+	spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static void res_end_move(struct mlx4_dev *dev, int slave,
+			 enum mlx4_resource type, int id)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct res_common *r;
+
+	spin_lock_irq(mlx4_tlock(dev));
+	r = radix_tree_lookup(&tracker->res_tree[type], id);
+	if (r && (r->owner == slave))
+		r->state = r->to_state;
+	spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static int valid_reserved(struct mlx4_dev *dev, int slave, int qpn)
+{
+	return mlx4_is_qp_reserved(dev, qpn);
+}
+
+static int qp_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+			u64 in_param, u64 *out_param)
+{
+	int err;
+	int count;
+	int align;
+	int base;
+	int qpn;
+
+	switch (op) {
+	case RES_OP_RESERVE:
+		count = get_param_l(&in_param);
+		align = get_param_h(&in_param);
+		err = __mlx4_qp_reserve_range(dev, count, align, &base);
+		if (err)
+			return err;
+
+		err = add_res_range(dev, slave, base, count, RES_QP, 0);
+		if (err) {
+			__mlx4_qp_release_range(dev, base, count);
+			return err;
+		}
+		set_param_l(out_param, base);
+		break;
+	case RES_OP_MAP_ICM:
+		qpn = get_param_l(&in_param) & 0x7fffff;
+		if (valid_reserved(dev, slave, qpn)) {
+			err = add_res_range(dev, slave, qpn, 1, RES_QP, 0);
+			if (err)
+				return err;
+		}
+
+		err = qp_res_start_move_to(dev, slave, qpn, RES_QP_MAPPED,
+					   NULL, 1);
+		if (err)
+			return err;
+
+		if (!valid_reserved(dev, slave, qpn)) {
+			err = __mlx4_qp_alloc_icm(dev, qpn);
+			if (err) {
+				res_abort_move(dev, slave, RES_QP, qpn);
+				return err;
+			}
+		}
+
+		res_end_move(dev, slave, RES_QP, qpn);
+		break;
+
+	default:
+		err = -EINVAL;
+		break;
+	}
+	return err;
+}
+
+static int mtt_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+			 u64 in_param, u64 *out_param)
+{
+	int err = -EINVAL;
+	int base;
+	int order;
+
+	if (op != RES_OP_RESERVE_AND_MAP)
+		return err;
+
+	order = get_param_l(&in_param);
+	base = __mlx4_alloc_mtt_range(dev, order);
+	if (base == -1)
+		return -ENOMEM;
+
+	err = add_res_range(dev, slave, base, 1, RES_MTT, order);
+	if (err)
+		__mlx4_free_mtt_range(dev, base, order);
+	else
+		set_param_l(out_param, base);
+
+	return err;
+}
+
+static int mpt_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+			 u64 in_param, u64 *out_param)
+{
+	int err = -EINVAL;
+	int index;
+	int id;
+	struct res_mpt *mpt;
+
+	switch (op) {
+	case RES_OP_RESERVE:
+		index = __mlx4_mr_reserve(dev);
+		if (index == -1)
+			break;
+		id = index & mpt_mask(dev);
+
+		err = add_res_range(dev, slave, id, 1, RES_MPT, index);
+		if (err) {
+			__mlx4_mr_release(dev, index);
+			break;
+		}
+		set_param_l(out_param, index);
+		break;
+	case RES_OP_MAP_ICM:
+		index = get_param_l(&in_param);
+		id = index & mpt_mask(dev);
+		err = mr_res_start_move_to(dev, slave, id,
+					   RES_MPT_MAPPED, &mpt);
+		if (err)
+			return err;
+
+		err = __mlx4_mr_alloc_icm(dev, mpt->key);
+		if (err) {
+			res_abort_move(dev, slave, RES_MPT, id);
+			return err;
+		}
+
+		res_end_move(dev, slave, RES_MPT, id);
+		break;
+	}
+	return err;
+}
+
+static int cq_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+			u64 in_param, u64 *out_param)
+{
+	int cqn;
+	int err;
+
+	switch (op) {
+	case RES_OP_RESERVE_AND_MAP:
+		err = __mlx4_cq_alloc_icm(dev, &cqn);
+		if (err)
+			break;
+
+		err = add_res_range(dev, slave, cqn, 1, RES_CQ, 0);
+		if (err) {
+			__mlx4_cq_free_icm(dev, cqn);
+			break;
+		}
+
+		set_param_l(out_param, cqn);
+		break;
+
+	default:
+		err = -EINVAL;
+	}
+
+	return err;
+}
+
+static int srq_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+			 u64 in_param, u64 *out_param)
+{
+	int srqn;
+	int err;
+
+	switch (op) {
+	case RES_OP_RESERVE_AND_MAP:
+		err = __mlx4_srq_alloc_icm(dev, &srqn);
+		if (err)
+			break;
+
+		err = add_res_range(dev, slave, srqn, 1, RES_SRQ, 0);
+		if (err) {
+			__mlx4_srq_free_icm(dev, srqn);
+			break;
+		}
+
+		set_param_l(out_param, srqn);
+		break;
+
+	default:
+		err = -EINVAL;
+	}
+
+	return err;
+}
+
+static int mac_add_to_slave(struct mlx4_dev *dev, int slave, u64 mac, int port)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct mac_res *res;
+
+	res = kzalloc(sizeof *res, GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
+	res->mac = mac;
+	res->port = (u8) port;
+	list_add_tail(&res->list,
+		      &tracker->slave_list[slave].res_list[RES_MAC]);
+	return 0;
+}
+
+static void mac_del_from_slave(struct mlx4_dev *dev, int slave, u64 mac,
+			       int port)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct list_head *mac_list =
+		&tracker->slave_list[slave].res_list[RES_MAC];
+	struct mac_res *res, *tmp;
+
+	list_for_each_entry_safe(res, tmp, mac_list, list) {
+		if (res->mac == mac && res->port == (u8) port) {
+			list_del(&res->list);
+			kfree(res);
+			break;
+		}
+	}
+}
+
+static void rem_slave_macs(struct mlx4_dev *dev, int slave)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct list_head *mac_list =
+		&tracker->slave_list[slave].res_list[RES_MAC];
+	struct mac_res *res, *tmp;
+
+	list_for_each_entry_safe(res, tmp, mac_list, list) {
+		list_del(&res->list);
+		__mlx4_unregister_mac(dev, res->port, res->mac);
+		kfree(res);
+	}
+}
+
+static int mac_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+			 u64 in_param, u64 *out_param)
+{
+	int err = -EINVAL;
+	int port;
+	u64 mac;
+
+	if (op != RES_OP_RESERVE_AND_MAP)
+		return err;
+
+	port = get_param_l(out_param);
+	mac = in_param;
+
+	err = __mlx4_register_mac(dev, port, mac);
+	if (err >= 0) {
+		set_param_l(out_param, err);
+		err = 0;
+	}
+
+	if (!err) {
+		err = mac_add_to_slave(dev, slave, mac, port);
+		if (err)
+			__mlx4_unregister_mac(dev, port, mac);
+	}
+	return err;
+}
+
+static int vlan_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+			 u64 in_param, u64 *out_param)
+{
+	return 0;
+}
+
+int mlx4_ALLOC_RES_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd)
+{
+	int err;
+	int alop = vhcr->op_modifier;
+
+	switch (vhcr->in_modifier) {
+	case RES_QP:
+		err = qp_alloc_res(dev, slave, vhcr->op_modifier, alop,
+				   vhcr->in_param, &vhcr->out_param);
+		break;
+
+	case RES_MTT:
+		err = mtt_alloc_res(dev, slave, vhcr->op_modifier, alop,
+				    vhcr->in_param, &vhcr->out_param);
+		break;
+
+	case RES_MPT:
+		err = mpt_alloc_res(dev, slave, vhcr->op_modifier, alop,
+				    vhcr->in_param, &vhcr->out_param);
+		break;
+
+	case RES_CQ:
+		err = cq_alloc_res(dev, slave, vhcr->op_modifier, alop,
+				   vhcr->in_param, &vhcr->out_param);
+		break;
+
+	case RES_SRQ:
+		err = srq_alloc_res(dev, slave, vhcr->op_modifier, alop,
+				    vhcr->in_param, &vhcr->out_param);
+		break;
+
+	case RES_MAC:
+		err = mac_alloc_res(dev, slave, vhcr->op_modifier, alop,
+				    vhcr->in_param, &vhcr->out_param);
+		break;
+
+	case RES_VLAN:
+		err = vlan_alloc_res(dev, slave, vhcr->op_modifier, alop,
+				    vhcr->in_param, &vhcr->out_param);
+		break;
+
+	default:
+		err = -EINVAL;
+		break;
+	}
+
+	return err;
+}
+
+static int qp_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+		       u64 in_param)
+{
+	int err;
+	int count;
+	int base;
+	int qpn;
+
+	switch (op) {
+	case RES_OP_RESERVE:
+		base = get_param_l(&in_param) & 0x7fffff;
+		count = get_param_h(&in_param);
+		err = rem_res_range(dev, slave, base, count, RES_QP, 0);
+		if (err)
+			break;
+		__mlx4_qp_release_range(dev, base, count);
+		break;
+	case RES_OP_MAP_ICM:
+		qpn = get_param_l(&in_param) & 0x7fffff;
+		err = qp_res_start_move_to(dev, slave, qpn, RES_QP_RESERVED,
+					   NULL, 0);
+		if (err)
+			return err;
+
+		if (!valid_reserved(dev, slave, qpn))
+			__mlx4_qp_free_icm(dev, qpn);
+
+		res_end_move(dev, slave, RES_QP, qpn);
+
+		if (valid_reserved(dev, slave, qpn))
+			err = rem_res_range(dev, slave, qpn, 1, RES_QP, 0);
+		break;
+	default:
+		err = -EINVAL;
+		break;
+	}
+	return err;
+}
+
+static int mtt_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+			u64 in_param, u64 *out_param)
+{
+	int err = -EINVAL;
+	int base;
+	int order;
+
+	if (op != RES_OP_RESERVE_AND_MAP)
+		return err;
+
+	base = get_param_l(&in_param);
+	order = get_param_h(&in_param);
+	err = rem_res_range(dev, slave, base, 1, RES_MTT, order);
+	if (!err)
+		__mlx4_free_mtt_range(dev, base, order);
+	return err;
+}
+
+static int mpt_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+			u64 in_param)
+{
+	int err = -EINVAL;
+	int index;
+	int id;
+	struct res_mpt *mpt;
+
+	switch (op) {
+	case RES_OP_RESERVE:
+		index = get_param_l(&in_param);
+		id = index & mpt_mask(dev);
+		err = get_res(dev, slave, id, RES_MPT, &mpt);
+		if (err)
+			break;
+		index = mpt->key;
+		put_res(dev, slave, id, RES_MPT);
+
+		err = rem_res_range(dev, slave, id, 1, RES_MPT, 0);
+		if (err)
+			break;
+		__mlx4_mr_release(dev, index);
+		break;
+	case RES_OP_MAP_ICM:
+			index = get_param_l(&in_param);
+			id = index & mpt_mask(dev);
+			err = mr_res_start_move_to(dev, slave, id,
+						   RES_MPT_RESERVED, &mpt);
+			if (err)
+				return err;
+
+			__mlx4_mr_free_icm(dev, mpt->key);
+			res_end_move(dev, slave, RES_MPT, id);
+			return err;
+		break;
+	default:
+		err = -EINVAL;
+		break;
+	}
+	return err;
+}
+
+static int cq_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+		       u64 in_param, u64 *out_param)
+{
+	int cqn;
+	int err;
+
+	switch (op) {
+	case RES_OP_RESERVE_AND_MAP:
+		cqn = get_param_l(&in_param);
+		err = rem_res_range(dev, slave, cqn, 1, RES_CQ, 0);
+		if (err)
+			break;
+
+		__mlx4_cq_free_icm(dev, cqn);
+		break;
+
+	default:
+		err = -EINVAL;
+		break;
+	}
+
+	return err;
+}
+
+static int srq_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+			u64 in_param, u64 *out_param)
+{
+	int srqn;
+	int err;
+
+	switch (op) {
+	case RES_OP_RESERVE_AND_MAP:
+		srqn = get_param_l(&in_param);
+		err = rem_res_range(dev, slave, srqn, 1, RES_SRQ, 0);
+		if (err)
+			break;
+
+		__mlx4_srq_free_icm(dev, srqn);
+		break;
+
+	default:
+		err = -EINVAL;
+		break;
+	}
+
+	return err;
+}
+
+static int mac_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+			    u64 in_param, u64 *out_param)
+{
+	int port;
+	int err = 0;
+
+	switch (op) {
+	case RES_OP_RESERVE_AND_MAP:
+		port = get_param_l(out_param);
+		mac_del_from_slave(dev, slave, in_param, port);
+		__mlx4_unregister_mac(dev, port, in_param);
+		break;
+	default:
+		err = -EINVAL;
+		break;
+	}
+
+	return err;
+
+}
+
+static int vlan_free_res(struct mlx4_dev *dev, int slave, int op, int cmd,
+			    u64 in_param, u64 *out_param)
+{
+	return 0;
+}
+
+int mlx4_FREE_RES_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd)
+{
+	int err = -EINVAL;
+	int alop = vhcr->op_modifier;
+
+	switch (vhcr->in_modifier) {
+	case RES_QP:
+		err = qp_free_res(dev, slave, vhcr->op_modifier, alop,
+				  vhcr->in_param);
+		break;
+
+	case RES_MTT:
+		err = mtt_free_res(dev, slave, vhcr->op_modifier, alop,
+				   vhcr->in_param, &vhcr->out_param);
+		break;
+
+	case RES_MPT:
+		err = mpt_free_res(dev, slave, vhcr->op_modifier, alop,
+				   vhcr->in_param);
+		break;
+
+	case RES_CQ:
+		err = cq_free_res(dev, slave, vhcr->op_modifier, alop,
+				  vhcr->in_param, &vhcr->out_param);
+		break;
+
+	case RES_SRQ:
+		err = srq_free_res(dev, slave, vhcr->op_modifier, alop,
+				   vhcr->in_param, &vhcr->out_param);
+		break;
+
+	case RES_MAC:
+		err = mac_free_res(dev, slave, vhcr->op_modifier, alop,
+				   vhcr->in_param, &vhcr->out_param);
+		break;
+
+	case RES_VLAN:
+		err = vlan_free_res(dev, slave, vhcr->op_modifier, alop,
+				   vhcr->in_param, &vhcr->out_param);
+		break;
+
+	default:
+		break;
+	}
+	return err;
+}
+
+/* ugly but other choices are uglier */
+static int mr_phys_mpt(struct mlx4_mpt_entry *mpt)
+{
+	return (be32_to_cpu(mpt->flags) >> 9) & 1;
+}
+
+static int mr_get_mtt_addr(struct mlx4_mpt_entry *mpt)
+{
+	return (int)be64_to_cpu(mpt->mtt_addr) & 0xfffffff8;
+}
+
+static int mr_get_mtt_size(struct mlx4_mpt_entry *mpt)
+{
+	return be32_to_cpu(mpt->mtt_sz);
+}
+
+static int mr_get_pdn(struct mlx4_mpt_entry *mpt)
+{
+	return be32_to_cpu(mpt->pd_flags) & 0xffffff;
+}
+
+static int qp_get_mtt_addr(struct mlx4_qp_context *qpc)
+{
+	return be32_to_cpu(qpc->mtt_base_addr_l) & 0xfffffff8;
+}
+
+static int srq_get_mtt_addr(struct mlx4_srq_context *srqc)
+{
+	return be32_to_cpu(srqc->mtt_base_addr_l) & 0xfffffff8;
+}
+
+static int qp_get_mtt_size(struct mlx4_qp_context *qpc)
+{
+	int page_shift = (qpc->log_page_size & 0x3f) + 12;
+	int log_sq_size = (qpc->sq_size_stride >> 3) & 0xf;
+	int log_sq_sride = qpc->sq_size_stride & 7;
+	int log_rq_size = (qpc->rq_size_stride >> 3) & 0xf;
+	int log_rq_stride = qpc->rq_size_stride & 7;
+	int srq = (be32_to_cpu(qpc->srqn) >> 24) & 1;
+	int rss = (be32_to_cpu(qpc->flags) >> 13) & 1;
+	int xrc = (be32_to_cpu(qpc->local_qpn) >> 23) & 1;
+	int sq_size;
+	int rq_size;
+	int total_pages;
+	int total_mem;
+	int page_offset = (be32_to_cpu(qpc->params2) >> 6) & 0x3f;
+
+	sq_size = 1 << (log_sq_size + log_sq_sride + 4);
+	rq_size = (srq|rss|xrc) ? 0 : (1 << (log_rq_size + log_rq_stride + 4));
+	total_mem = sq_size + rq_size;
+	total_pages =
+		roundup_pow_of_two((total_mem + (page_offset << 6)) >>
+				   page_shift);
+
+	return total_pages;
+}
+
+static int qp_get_pdn(struct mlx4_qp_context *qpc)
+{
+	return be32_to_cpu(qpc->pd) & 0xffffff;
+}
+
+static int pdn2slave(int pdn)
+{
+	return (pdn >> NOT_MASKED_PD_BITS) - 1;
+}
+
+static int check_mtt_range(struct mlx4_dev *dev, int slave, int start,
+			   int size, struct res_mtt *mtt)
+{
+	int res_start = mtt->com.res_id;
+	int res_size = (1 << mtt->order);
+
+	if (start < res_start || start + size > res_start + res_size)
+		return -EPERM;
+	return 0;
+}
+
+int mlx4_SW2HW_MPT_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd)
+{
+	int err;
+	int index = vhcr->in_modifier;
+	struct res_mtt *mtt;
+	struct res_mpt *mpt;
+	int mtt_base = mr_get_mtt_addr(inbox->buf) / dev->caps.mtt_entry_sz;
+	int phys;
+	int id;
+
+	id = index & mpt_mask(dev);
+	err = mr_res_start_move_to(dev, slave, id, RES_MPT_HW, &mpt);
+	if (err)
+		return err;
+
+	phys = mr_phys_mpt(inbox->buf);
+	if (!phys) {
+		err = get_res(dev, slave, mtt_base, RES_MTT, &mtt);
+		if (err)
+			goto ex_abort;
+
+		err = check_mtt_range(dev, slave, mtt_base,
+				      mr_get_mtt_size(inbox->buf), mtt);
+		if (err)
+			goto ex_put;
+
+		mpt->mtt = mtt;
+	}
+
+	if (pdn2slave(mr_get_pdn(inbox->buf)) != slave) {
+		err = -EPERM;
+		goto ex_put;
+	}
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+	if (err)
+		goto ex_put;
+
+	if (!phys) {
+		atomic_inc(&mtt->ref_count);
+		put_res(dev, slave, mtt->com.res_id, RES_MTT);
+	}
+
+	res_end_move(dev, slave, RES_MPT, id);
+	return 0;
+
+ex_put:
+	if (!phys)
+		put_res(dev, slave, mtt->com.res_id, RES_MTT);
+ex_abort:
+	res_abort_move(dev, slave, RES_MPT, id);
+
+	return err;
+}
+
+int mlx4_HW2SW_MPT_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd)
+{
+	int err;
+	int index = vhcr->in_modifier;
+	struct res_mpt *mpt;
+	int id;
+
+	id = index & mpt_mask(dev);
+	err = mr_res_start_move_to(dev, slave, id, RES_MPT_MAPPED, &mpt);
+	if (err)
+		return err;
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+	if (err)
+		goto ex_abort;
+
+	if (mpt->mtt)
+		atomic_dec(&mpt->mtt->ref_count);
+
+	res_end_move(dev, slave, RES_MPT, id);
+	return 0;
+
+ex_abort:
+	res_abort_move(dev, slave, RES_MPT, id);
+
+	return err;
+}
+
+int mlx4_QUERY_MPT_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd)
+{
+	int err;
+	int index = vhcr->in_modifier;
+	struct res_mpt *mpt;
+	int id;
+
+	id = index & mpt_mask(dev);
+	err = get_res(dev, slave, id, RES_MPT, &mpt);
+	if (err)
+		return err;
+
+	if (mpt->com.from_state != RES_MPT_HW) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+
+out:
+	put_res(dev, slave, id, RES_MPT);
+	return err;
+}
+
+static int qp_get_rcqn(struct mlx4_qp_context *qpc)
+{
+	return be32_to_cpu(qpc->cqn_recv) & 0xffffff;
+}
+
+static int qp_get_scqn(struct mlx4_qp_context *qpc)
+{
+	return be32_to_cpu(qpc->cqn_send) & 0xffffff;
+}
+
+static u32 qp_get_srqn(struct mlx4_qp_context *qpc)
+{
+	return be32_to_cpu(qpc->srqn) & 0x1ffffff;
+}
+
+int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
+			     struct mlx4_vhcr *vhcr,
+			     struct mlx4_cmd_mailbox *inbox,
+			     struct mlx4_cmd_mailbox *outbox,
+			     struct mlx4_cmd_info *cmd)
+{
+	int err;
+	int qpn = vhcr->in_modifier & 0x7fffff;
+	struct res_mtt *mtt;
+	struct res_qp *qp;
+	struct mlx4_qp_context *qpc = inbox->buf + 8;
+	int mtt_base = qp_get_mtt_addr(qpc) / dev->caps.mtt_entry_sz;
+	int mtt_size = qp_get_mtt_size(qpc);
+	struct res_cq *rcq;
+	struct res_cq *scq;
+	int rcqn = qp_get_rcqn(qpc);
+	int scqn = qp_get_scqn(qpc);
+	u32 srqn = qp_get_srqn(qpc) & 0xffffff;
+	int use_srq = (qp_get_srqn(qpc) >> 24) & 1;
+	struct res_srq *srq;
+	int local_qpn = be32_to_cpu(qpc->local_qpn) & 0xffffff;
+
+	err = qp_res_start_move_to(dev, slave, qpn, RES_QP_HW, &qp, 0);
+	if (err)
+		return err;
+	qp->local_qpn = local_qpn;
+
+	err = get_res(dev, slave, mtt_base, RES_MTT, &mtt);
+	if (err)
+		goto ex_abort;
+
+	err = check_mtt_range(dev, slave, mtt_base, mtt_size, mtt);
+	if (err)
+		goto ex_put_mtt;
+
+	if (pdn2slave(qp_get_pdn(qpc)) != slave) {
+		err = -EPERM;
+		goto ex_put_mtt;
+	}
+
+	err = get_res(dev, slave, rcqn, RES_CQ, &rcq);
+	if (err)
+		goto ex_put_mtt;
+
+	if (scqn != rcqn) {
+		err = get_res(dev, slave, scqn, RES_CQ, &scq);
+		if (err)
+			goto ex_put_rcq;
+	} else
+		scq = rcq;
+
+	if (use_srq) {
+		err = get_res(dev, slave, srqn, RES_SRQ, &srq);
+		if (err)
+			goto ex_put_scq;
+	}
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+	if (err)
+		goto ex_put_srq;
+	atomic_inc(&mtt->ref_count);
+	qp->mtt = mtt;
+	atomic_inc(&rcq->ref_count);
+	qp->rcq = rcq;
+	atomic_inc(&scq->ref_count);
+	qp->scq = scq;
+
+	if (scqn != rcqn)
+		put_res(dev, slave, scqn, RES_CQ);
+
+	if (use_srq) {
+		atomic_inc(&srq->ref_count);
+		put_res(dev, slave, srqn, RES_SRQ);
+		qp->srq = srq;
+	}
+	put_res(dev, slave, rcqn, RES_CQ);
+	put_res(dev, slave, mtt_base, RES_MTT);
+	res_end_move(dev, slave, RES_QP, qpn);
+
+	return 0;
+
+ex_put_srq:
+	if (use_srq)
+		put_res(dev, slave, srqn, RES_SRQ);
+ex_put_scq:
+	if (scqn != rcqn)
+		put_res(dev, slave, scqn, RES_CQ);
+ex_put_rcq:
+	put_res(dev, slave, rcqn, RES_CQ);
+ex_put_mtt:
+	put_res(dev, slave, mtt_base, RES_MTT);
+ex_abort:
+	res_abort_move(dev, slave, RES_QP, qpn);
+
+	return err;
+}
+
+static int eq_get_mtt_addr(struct mlx4_eq_context *eqc)
+{
+	return be32_to_cpu(eqc->mtt_base_addr_l) & 0xfffffff8;
+}
+
+static int eq_get_mtt_size(struct mlx4_eq_context *eqc)
+{
+	int log_eq_size = eqc->log_eq_size & 0x1f;
+	int page_shift = (eqc->log_page_size & 0x3f) + 12;
+
+	if (log_eq_size + 5 < page_shift)
+		return 1;
+
+	return 1 << (log_eq_size + 5 - page_shift);
+}
+
+static int cq_get_mtt_addr(struct mlx4_cq_context *cqc)
+{
+	return be32_to_cpu(cqc->mtt_base_addr_l) & 0xfffffff8;
+}
+
+static int cq_get_mtt_size(struct mlx4_cq_context *cqc)
+{
+	int log_cq_size = (be32_to_cpu(cqc->logsize_usrpage) >> 24) & 0x1f;
+	int page_shift = (cqc->log_page_size & 0x3f) + 12;
+
+	if (log_cq_size + 5 < page_shift)
+		return 1;
+
+	return 1 << (log_cq_size + 5 - page_shift);
+}
+
+int mlx4_SW2HW_EQ_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd)
+{
+	int err;
+	int eqn = vhcr->in_modifier;
+	int res_id = (slave << 8) | eqn;
+	struct mlx4_eq_context *eqc = inbox->buf;
+	int mtt_base = eq_get_mtt_addr(eqc) / dev->caps.mtt_entry_sz;
+	int mtt_size = eq_get_mtt_size(eqc);
+	struct res_eq *eq;
+	struct res_mtt *mtt;
+
+	err = add_res_range(dev, slave, res_id, 1, RES_EQ, 0);
+	if (err)
+		return err;
+	err = eq_res_start_move_to(dev, slave, res_id, RES_EQ_HW, &eq);
+	if (err)
+		goto out_add;
+
+	err = get_res(dev, slave, mtt_base, RES_MTT, &mtt);
+	if (err)
+		goto out_move;
+
+	err = check_mtt_range(dev, slave, mtt_base, mtt_size, mtt);
+	if (err)
+		goto out_put;
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+	if (err)
+		goto out_put;
+
+	atomic_inc(&mtt->ref_count);
+	eq->mtt = mtt;
+	put_res(dev, slave, mtt->com.res_id, RES_MTT);
+	res_end_move(dev, slave, RES_EQ, res_id);
+	return 0;
+
+out_put:
+	put_res(dev, slave, mtt->com.res_id, RES_MTT);
+out_move:
+	res_abort_move(dev, slave, RES_EQ, res_id);
+out_add:
+	rem_res_range(dev, slave, res_id, 1, RES_EQ, 0);
+	return err;
+}
+
+static int get_containing_mtt(struct mlx4_dev *dev, int slave, int start,
+			      int len, struct res_mtt **res)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct res_mtt *mtt;
+	int err = -EINVAL;
+
+	spin_lock_irq(mlx4_tlock(dev));
+	list_for_each_entry(mtt, &tracker->slave_list[slave].res_list[RES_MTT],
+			    com.list) {
+		if (!check_mtt_range(dev, slave, start, len, mtt)) {
+			*res = mtt;
+			mtt->com.from_state = mtt->com.state;
+			mtt->com.state = RES_MTT_BUSY;
+			err = 0;
+			break;
+		}
+	}
+	spin_unlock_irq(mlx4_tlock(dev));
+
+	return err;
+}
+
+int mlx4_WRITE_MTT_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd)
+{
+	struct mlx4_mtt mtt;
+	__be64 *page_list = inbox->buf;
+	u64 *pg_list = (u64 *)page_list;
+	int i;
+	struct res_mtt *rmtt = NULL;
+	int start = be64_to_cpu(page_list[0]);
+	int npages = vhcr->in_modifier;
+	int err;
+
+	err = get_containing_mtt(dev, slave, start, npages, &rmtt);
+	if (err)
+		return err;
+
+	/* Call the SW implementation of write_mtt:
+	 * - Prepare a dummy mtt struct
+	 * - Translate inbox contents to simple addresses in host endianess */
+	mtt.offset = 0;  /* TBD this is broken but I don't handle it since
+			    we don't really use it */
+	mtt.order = 0;
+	mtt.page_shift = 0;
+	for (i = 0; i < npages; ++i)
+		pg_list[i + 2] = (be64_to_cpu(page_list[i + 2]) & ~1ULL);
+
+	err = __mlx4_write_mtt(dev, &mtt, be64_to_cpu(page_list[0]), npages,
+			       ((u64 *)page_list + 2));
+
+	if (rmtt)
+		put_res(dev, slave, rmtt->com.res_id, RES_MTT);
+
+	return err;
+}
+
+int mlx4_HW2SW_EQ_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd)
+{
+	int eqn = vhcr->in_modifier;
+	int res_id = eqn | (slave << 8);
+	struct res_eq *eq;
+	int err;
+
+	err = eq_res_start_move_to(dev, slave, res_id, RES_EQ_RESERVED, &eq);
+	if (err)
+		return err;
+
+	err = get_res(dev, slave, eq->mtt->com.res_id, RES_MTT, NULL);
+	if (err)
+		goto ex_abort;
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+	if (err)
+		goto ex_put;
+
+	atomic_dec(&eq->mtt->ref_count);
+	put_res(dev, slave, eq->mtt->com.res_id, RES_MTT);
+	res_end_move(dev, slave, RES_EQ, res_id);
+	rem_res_range(dev, slave, res_id, 1, RES_EQ, 0);
+
+	return 0;
+
+ex_put:
+	put_res(dev, slave, eq->mtt->com.res_id, RES_MTT);
+ex_abort:
+	res_abort_move(dev, slave, RES_EQ, res_id);
+
+	return err;
+}
+
+int mlx4_GEN_EQE(struct mlx4_dev *dev, int slave, struct mlx4_eqe *eqe)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_slave_event_eq_info *event_eq;
+	struct mlx4_cmd_mailbox *mailbox;
+	u32 in_modifier = 0;
+	int err;
+	int res_id;
+	struct res_eq *req;
+
+	if (!priv->mfunc.master.slave_state)
+		return -EINVAL;
+
+	event_eq = &priv->mfunc.master.slave_state[slave].event_eq;
+
+	/* Create the event only if the slave is registered */
+	if ((event_eq->event_type & (1 << eqe->type)) == 0)
+		return 0;
+
+	mutex_lock(&priv->mfunc.master.gen_eqe_mutex[slave]);
+	res_id = (slave << 8) | event_eq->eqn;
+	err = get_res(dev, slave, res_id, RES_EQ, &req);
+	if (err)
+		goto unlock;
+
+	if (req->com.from_state != RES_EQ_HW) {
+		err = -EINVAL;
+		goto put;
+	}
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox)) {
+		err = PTR_ERR(mailbox);
+		goto put;
+	}
+
+	if (eqe->type == MLX4_EVENT_TYPE_CMD) {
+		++event_eq->token;
+		eqe->event.cmd.token = cpu_to_be16(event_eq->token);
+	}
+
+	memcpy(mailbox->buf, (u8 *) eqe, 28);
+
+	in_modifier = (slave & 0xff) | ((event_eq->eqn & 0xff) << 16);
+
+	err = mlx4_cmd(dev, mailbox->dma, in_modifier, 0,
+		       MLX4_CMD_GEN_EQE, MLX4_CMD_TIME_CLASS_B,
+		       MLX4_CMD_NATIVE);
+
+	put_res(dev, slave, res_id, RES_EQ);
+	mutex_unlock(&priv->mfunc.master.gen_eqe_mutex[slave]);
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+
+put:
+	put_res(dev, slave, res_id, RES_EQ);
+
+unlock:
+	mutex_unlock(&priv->mfunc.master.gen_eqe_mutex[slave]);
+	return err;
+}
+
+int mlx4_QUERY_EQ_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd)
+{
+	int eqn = vhcr->in_modifier;
+	int res_id = eqn | (slave << 8);
+	struct res_eq *eq;
+	int err;
+
+	err = get_res(dev, slave, res_id, RES_EQ, &eq);
+	if (err)
+		return err;
+
+	if (eq->com.from_state != RES_EQ_HW) {
+		err = -EINVAL;
+		goto ex_put;
+	}
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+
+ex_put:
+	put_res(dev, slave, res_id, RES_EQ);
+	return err;
+}
+
+int mlx4_SW2HW_CQ_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd)
+{
+	int err;
+	int cqn = vhcr->in_modifier;
+	struct mlx4_cq_context *cqc = inbox->buf;
+	int mtt_base = cq_get_mtt_addr(cqc) / dev->caps.mtt_entry_sz;
+	struct res_cq *cq;
+	struct res_mtt *mtt;
+
+	err = cq_res_start_move_to(dev, slave, cqn, RES_CQ_HW, &cq);
+	if (err)
+		return err;
+	err = get_res(dev, slave, mtt_base, RES_MTT, &mtt);
+	if (err)
+		goto out_move;
+	err = check_mtt_range(dev, slave, mtt_base, cq_get_mtt_size(cqc), mtt);
+	if (err)
+		goto out_put;
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+	if (err)
+		goto out_put;
+	atomic_inc(&mtt->ref_count);
+	cq->mtt = mtt;
+	put_res(dev, slave, mtt->com.res_id, RES_MTT);
+	res_end_move(dev, slave, RES_CQ, cqn);
+	return 0;
+
+out_put:
+	put_res(dev, slave, mtt->com.res_id, RES_MTT);
+out_move:
+	res_abort_move(dev, slave, RES_CQ, cqn);
+	return err;
+}
+
+int mlx4_HW2SW_CQ_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd)
+{
+	int err;
+	int cqn = vhcr->in_modifier;
+	struct res_cq *cq;
+
+	err = cq_res_start_move_to(dev, slave, cqn, RES_CQ_ALLOCATED, &cq);
+	if (err)
+		return err;
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+	if (err)
+		goto out_move;
+	atomic_dec(&cq->mtt->ref_count);
+	res_end_move(dev, slave, RES_CQ, cqn);
+	return 0;
+
+out_move:
+	res_abort_move(dev, slave, RES_CQ, cqn);
+	return err;
+}
+
+int mlx4_QUERY_CQ_wrapper(struct mlx4_dev *dev, int slave,
+			  struct mlx4_vhcr *vhcr,
+			  struct mlx4_cmd_mailbox *inbox,
+			  struct mlx4_cmd_mailbox *outbox,
+			  struct mlx4_cmd_info *cmd)
+{
+	int cqn = vhcr->in_modifier;
+	struct res_cq *cq;
+	int err;
+
+	err = get_res(dev, slave, cqn, RES_CQ, &cq);
+	if (err)
+		return err;
+
+	if (cq->com.from_state != RES_CQ_HW)
+		goto ex_put;
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ex_put:
+	put_res(dev, slave, cqn, RES_CQ);
+
+	return err;
+}
+
+static int handle_resize(struct mlx4_dev *dev, int slave,
+			 struct mlx4_vhcr *vhcr,
+			 struct mlx4_cmd_mailbox *inbox,
+			 struct mlx4_cmd_mailbox *outbox,
+			 struct mlx4_cmd_info *cmd,
+			 struct res_cq *cq)
+{
+	int err;
+	struct res_mtt *orig_mtt;
+	struct res_mtt *mtt;
+	struct mlx4_cq_context *cqc = inbox->buf;
+	int mtt_base = cq_get_mtt_addr(cqc) / dev->caps.mtt_entry_sz;
+
+	err = get_res(dev, slave, cq->mtt->com.res_id, RES_MTT, &orig_mtt);
+	if (err)
+		return err;
+
+	if (orig_mtt != cq->mtt) {
+		err = -EINVAL;
+		goto ex_put;
+	}
+
+	err = get_res(dev, slave, mtt_base, RES_MTT, &mtt);
+	if (err)
+		goto ex_put;
+
+	err = check_mtt_range(dev, slave, mtt_base, cq_get_mtt_size(cqc), mtt);
+	if (err)
+		goto ex_put1;
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+	if (err)
+		goto ex_put1;
+	atomic_dec(&orig_mtt->ref_count);
+	put_res(dev, slave, orig_mtt->com.res_id, RES_MTT);
+	atomic_inc(&mtt->ref_count);
+	cq->mtt = mtt;
+	put_res(dev, slave, mtt->com.res_id, RES_MTT);
+	return 0;
+
+ex_put1:
+	put_res(dev, slave, mtt->com.res_id, RES_MTT);
+ex_put:
+	put_res(dev, slave, orig_mtt->com.res_id, RES_MTT);
+
+	return err;
+
+}
+
+int mlx4_MODIFY_CQ_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd)
+{
+	int cqn = vhcr->in_modifier;
+	struct res_cq *cq;
+	int err;
+
+	err = get_res(dev, slave, cqn, RES_CQ, &cq);
+	if (err)
+		return err;
+
+	if (cq->com.from_state != RES_CQ_HW)
+		goto ex_put;
+
+	if (vhcr->op_modifier == 0) {
+		err = handle_resize(dev, slave, vhcr, inbox, outbox, cmd, cq);
+		if (err)
+			goto ex_put;
+	}
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+ex_put:
+	put_res(dev, slave, cqn, RES_CQ);
+
+	return err;
+}
+
+static int srq_get_pdn(struct mlx4_srq_context *srqc)
+{
+	return be32_to_cpu(srqc->pd) & 0xffffff;
+}
+
+static int srq_get_mtt_size(struct mlx4_srq_context *srqc)
+{
+	int log_srq_size = (be32_to_cpu(srqc->state_logsize_srqn) >> 24) & 0xf;
+	int log_rq_stride = srqc->logstride & 7;
+	int page_shift = (srqc->log_page_size & 0x3f) + 12;
+
+	if (log_srq_size + log_rq_stride + 4 < page_shift)
+		return 1;
+
+	return 1 << (log_srq_size + log_rq_stride + 4 - page_shift);
+}
+
+int mlx4_SW2HW_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd)
+{
+	int err;
+	int srqn = vhcr->in_modifier;
+	struct res_mtt *mtt;
+	struct res_srq *srq;
+	struct mlx4_srq_context *srqc = inbox->buf;
+	int mtt_base = srq_get_mtt_addr(srqc) / dev->caps.mtt_entry_sz;
+
+	if (srqn != (be32_to_cpu(srqc->state_logsize_srqn) & 0xffffff))
+		return -EINVAL;
+
+	err = srq_res_start_move_to(dev, slave, srqn, RES_SRQ_HW, &srq);
+	if (err)
+		return err;
+	err = get_res(dev, slave, mtt_base, RES_MTT, &mtt);
+	if (err)
+		goto ex_abort;
+	err = check_mtt_range(dev, slave, mtt_base, srq_get_mtt_size(srqc),
+			      mtt);
+	if (err)
+		goto ex_put_mtt;
+
+	if (pdn2slave(srq_get_pdn(srqc)) != slave) {
+		err = -EPERM;
+		goto ex_put_mtt;
+	}
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+	if (err)
+		goto ex_put_mtt;
+
+	atomic_inc(&mtt->ref_count);
+	srq->mtt = mtt;
+	put_res(dev, slave, mtt->com.res_id, RES_MTT);
+	res_end_move(dev, slave, RES_SRQ, srqn);
+	return 0;
+
+ex_put_mtt:
+	put_res(dev, slave, mtt->com.res_id, RES_MTT);
+ex_abort:
+	res_abort_move(dev, slave, RES_SRQ, srqn);
+
+	return err;
+}
+
+int mlx4_HW2SW_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd)
+{
+	int err;
+	int srqn = vhcr->in_modifier;
+	struct res_srq *srq;
+
+	err = srq_res_start_move_to(dev, slave, srqn, RES_SRQ_ALLOCATED, &srq);
+	if (err)
+		return err;
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+	if (err)
+		goto ex_abort;
+	atomic_dec(&srq->mtt->ref_count);
+	if (srq->cq)
+		atomic_dec(&srq->cq->ref_count);
+	res_end_move(dev, slave, RES_SRQ, srqn);
+
+	return 0;
+
+ex_abort:
+	res_abort_move(dev, slave, RES_SRQ, srqn);
+
+	return err;
+}
+
+int mlx4_QUERY_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+			   struct mlx4_vhcr *vhcr,
+			   struct mlx4_cmd_mailbox *inbox,
+			   struct mlx4_cmd_mailbox *outbox,
+			   struct mlx4_cmd_info *cmd)
+{
+	int err;
+	int srqn = vhcr->in_modifier;
+	struct res_srq *srq;
+
+	err = get_res(dev, slave, srqn, RES_SRQ, &srq);
+	if (err)
+		return err;
+	if (srq->com.from_state != RES_SRQ_HW) {
+		err = -EBUSY;
+		goto out;
+	}
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+out:
+	put_res(dev, slave, srqn, RES_SRQ);
+	return err;
+}
+
+int mlx4_ARM_SRQ_wrapper(struct mlx4_dev *dev, int slave,
+			 struct mlx4_vhcr *vhcr,
+			 struct mlx4_cmd_mailbox *inbox,
+			 struct mlx4_cmd_mailbox *outbox,
+			 struct mlx4_cmd_info *cmd)
+{
+	int err;
+	int srqn = vhcr->in_modifier;
+	struct res_srq *srq;
+
+	err = get_res(dev, slave, srqn, RES_SRQ, &srq);
+	if (err)
+		return err;
+
+	if (srq->com.from_state != RES_SRQ_HW) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+out:
+	put_res(dev, slave, srqn, RES_SRQ);
+	return err;
+}
+
+int mlx4_GEN_QP_wrapper(struct mlx4_dev *dev, int slave,
+			struct mlx4_vhcr *vhcr,
+			struct mlx4_cmd_mailbox *inbox,
+			struct mlx4_cmd_mailbox *outbox,
+			struct mlx4_cmd_info *cmd)
+{
+	int err;
+	int qpn = vhcr->in_modifier & 0x7fffff;
+	struct res_qp *qp;
+
+	err = get_res(dev, slave, qpn, RES_QP, &qp);
+	if (err)
+		return err;
+	if (qp->com.from_state != RES_QP_HW) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+out:
+	put_res(dev, slave, qpn, RES_QP);
+	return err;
+}
+
+int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave,
+			     struct mlx4_vhcr *vhcr,
+			     struct mlx4_cmd_mailbox *inbox,
+			     struct mlx4_cmd_mailbox *outbox,
+			     struct mlx4_cmd_info *cmd)
+{
+	struct mlx4_qp_context *qpc = inbox->buf + 8;
+
+	update_ud_gid(dev, qpc, (u8)slave);
+
+	return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+}
+
+int mlx4_2RST_QP_wrapper(struct mlx4_dev *dev, int slave,
+			 struct mlx4_vhcr *vhcr,
+			 struct mlx4_cmd_mailbox *inbox,
+			 struct mlx4_cmd_mailbox *outbox,
+			 struct mlx4_cmd_info *cmd)
+{
+	int err;
+	int qpn = vhcr->in_modifier & 0x7fffff;
+	struct res_qp *qp;
+
+	err = qp_res_start_move_to(dev, slave, qpn, RES_QP_MAPPED, &qp, 0);
+	if (err)
+		return err;
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+	if (err)
+		goto ex_abort;
+
+	atomic_dec(&qp->mtt->ref_count);
+	atomic_dec(&qp->rcq->ref_count);
+	atomic_dec(&qp->scq->ref_count);
+	if (qp->srq)
+		atomic_dec(&qp->srq->ref_count);
+	res_end_move(dev, slave, RES_QP, qpn);
+	return 0;
+
+ex_abort:
+	res_abort_move(dev, slave, RES_QP, qpn);
+
+	return err;
+}
+
+static struct res_gid *find_gid(struct mlx4_dev *dev, int slave,
+				struct res_qp *rqp, u8 *gid)
+{
+	struct res_gid *res;
+
+	list_for_each_entry(res, &rqp->mcg_list, list) {
+		if (!memcmp(res->gid, gid, 16))
+			return res;
+	}
+	return NULL;
+}
+
+static int add_mcg_res(struct mlx4_dev *dev, int slave, struct res_qp *rqp,
+		       u8 *gid, enum mlx4_protocol prot)
+{
+	struct res_gid *res;
+	int err;
+
+	res = kzalloc(sizeof *res, GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
+
+	spin_lock_irq(&rqp->mcg_spl);
+	if (find_gid(dev, slave, rqp, gid)) {
+		kfree(res);
+		err = -EEXIST;
+	} else {
+		memcpy(res->gid, gid, 16);
+		res->prot = prot;
+		list_add_tail(&res->list, &rqp->mcg_list);
+		err = 0;
+	}
+	spin_unlock_irq(&rqp->mcg_spl);
+
+	return err;
+}
+
+static int rem_mcg_res(struct mlx4_dev *dev, int slave, struct res_qp *rqp,
+		       u8 *gid, enum mlx4_protocol prot)
+{
+	struct res_gid *res;
+	int err;
+
+	spin_lock_irq(&rqp->mcg_spl);
+	res = find_gid(dev, slave, rqp, gid);
+	if (!res || res->prot != prot)
+		err = -EINVAL;
+	else {
+		list_del(&res->list);
+		kfree(res);
+		err = 0;
+	}
+	spin_unlock_irq(&rqp->mcg_spl);
+
+	return err;
+}
+
+int mlx4_QP_ATTACH_wrapper(struct mlx4_dev *dev, int slave,
+			       struct mlx4_vhcr *vhcr,
+			       struct mlx4_cmd_mailbox *inbox,
+			       struct mlx4_cmd_mailbox *outbox,
+			       struct mlx4_cmd_info *cmd)
+{
+	struct mlx4_qp qp; /* dummy for calling attach/detach */
+	u8 *gid = inbox->buf;
+	enum mlx4_protocol prot = (vhcr->in_modifier >> 28) & 0x7;
+	int err, err1;
+	int qpn;
+	struct res_qp *rqp;
+	int attach = vhcr->op_modifier;
+	int block_loopback = vhcr->in_modifier >> 31;
+	u8 steer_type_mask = 2;
+	enum mlx4_steer_type type = gid[7] & steer_type_mask;
+
+	qpn = vhcr->in_modifier & 0xffffff;
+	err = get_res(dev, slave, qpn, RES_QP, &rqp);
+	if (err)
+		return err;
+
+	qp.qpn = qpn;
+	if (attach) {
+		err = add_mcg_res(dev, slave, rqp, gid, prot);
+		if (err)
+			goto ex_put;
+
+		err = mlx4_qp_attach_common(dev, &qp, gid,
+					    block_loopback, prot, type);
+		if (err)
+			goto ex_rem;
+	} else {
+		err = rem_mcg_res(dev, slave, rqp, gid, prot);
+		if (err)
+			goto ex_put;
+		err = mlx4_qp_detach_common(dev, &qp, gid, prot, type);
+	}
+
+	put_res(dev, slave, qpn, RES_QP);
+	return 0;
+
+ex_rem:
+	/* ignore error return below, already in error */
+	err1 = rem_mcg_res(dev, slave, rqp, gid, prot);
+ex_put:
+	put_res(dev, slave, qpn, RES_QP);
+
+	return err;
+}
+
+enum {
+	BUSY_MAX_RETRIES = 10
+};
+
+int mlx4_QUERY_IF_STAT_wrapper(struct mlx4_dev *dev, int slave,
+			       struct mlx4_vhcr *vhcr,
+			       struct mlx4_cmd_mailbox *inbox,
+			       struct mlx4_cmd_mailbox *outbox,
+			       struct mlx4_cmd_info *cmd)
+{
+	int err;
+	int index = vhcr->in_modifier & 0xffff;
+
+	err = get_res(dev, slave, index, RES_COUNTER, NULL);
+	if (err)
+		return err;
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+	put_res(dev, slave, index, RES_COUNTER);
+	return err;
+}
+
+static void detach_qp(struct mlx4_dev *dev, int slave, struct res_qp *rqp)
+{
+	struct res_gid *rgid;
+	struct res_gid *tmp;
+	int err;
+	struct mlx4_qp qp; /* dummy for calling attach/detach */
+
+	list_for_each_entry_safe(rgid, tmp, &rqp->mcg_list, list) {
+		qp.qpn = rqp->local_qpn;
+		err = mlx4_qp_detach_common(dev, &qp, rgid->gid, rgid->prot,
+					    MLX4_MC_STEER);
+		list_del(&rgid->list);
+		kfree(rgid);
+	}
+}
+
+static int _move_all_busy(struct mlx4_dev *dev, int slave,
+			  enum mlx4_resource type, int print)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker =
+		&priv->mfunc.master.res_tracker;
+	struct list_head *rlist = &tracker->slave_list[slave].res_list[type];
+	struct res_common *r;
+	struct res_common *tmp;
+	int busy;
+
+	busy = 0;
+	spin_lock_irq(mlx4_tlock(dev));
+	list_for_each_entry_safe(r, tmp, rlist, list) {
+		if (r->owner == slave) {
+			if (!r->removing) {
+				if (r->state == RES_ANY_BUSY) {
+					if (print)
+						mlx4_dbg(dev,
+							 "%s id 0x%x is busy\n",
+							  ResourceType(type),
+							  r->res_id);
+					++busy;
+				} else {
+					r->from_state = r->state;
+					r->state = RES_ANY_BUSY;
+					r->removing = 1;
+				}
+			}
+		}
+	}
+	spin_unlock_irq(mlx4_tlock(dev));
+
+	return busy;
+}
+
+static int move_all_busy(struct mlx4_dev *dev, int slave,
+			 enum mlx4_resource type)
+{
+	unsigned long begin;
+	int busy;
+
+	begin = jiffies;
+	do {
+		busy = _move_all_busy(dev, slave, type, 0);
+		if (time_after(jiffies, begin + 5 * HZ))
+			break;
+		if (busy)
+			cond_resched();
+	} while (busy);
+
+	if (busy)
+		busy = _move_all_busy(dev, slave, type, 1);
+
+	return busy;
+}
+static void rem_slave_qps(struct mlx4_dev *dev, int slave)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct list_head *qp_list =
+		&tracker->slave_list[slave].res_list[RES_QP];
+	struct res_qp *qp;
+	struct res_qp *tmp;
+	int state;
+	u64 in_param;
+	int qpn;
+	int err;
+
+	err = move_all_busy(dev, slave, RES_QP);
+	if (err)
+		mlx4_warn(dev, "rem_slave_qps: Could not move all qps to busy"
+			  "for slave %d\n", slave);
+
+	spin_lock_irq(mlx4_tlock(dev));
+	list_for_each_entry_safe(qp, tmp, qp_list, com.list) {
+		spin_unlock_irq(mlx4_tlock(dev));
+		if (qp->com.owner == slave) {
+			qpn = qp->com.res_id;
+			detach_qp(dev, slave, qp);
+			state = qp->com.from_state;
+			while (state != 0) {
+				switch (state) {
+				case RES_QP_RESERVED:
+					spin_lock_irq(mlx4_tlock(dev));
+					radix_tree_delete(&tracker->res_tree[RES_QP],
+							  qp->com.res_id);
+					list_del(&qp->com.list);
+					spin_unlock_irq(mlx4_tlock(dev));
+					kfree(qp);
+					state = 0;
+					break;
+				case RES_QP_MAPPED:
+					if (!valid_reserved(dev, slave, qpn))
+						__mlx4_qp_free_icm(dev, qpn);
+					state = RES_QP_RESERVED;
+					break;
+				case RES_QP_HW:
+					in_param = slave;
+					err = mlx4_cmd(dev, in_param,
+						       qp->local_qpn, 2,
+						       MLX4_CMD_2RST_QP,
+						       MLX4_CMD_TIME_CLASS_A,
+						       MLX4_CMD_NATIVE);
+					if (err)
+						mlx4_dbg(dev, "rem_slave_qps: failed"
+							 " to move slave %d qpn %d to"
+							 " reset\n", slave,
+							 qp->local_qpn);
+					atomic_dec(&qp->rcq->ref_count);
+					atomic_dec(&qp->scq->ref_count);
+					atomic_dec(&qp->mtt->ref_count);
+					if (qp->srq)
+						atomic_dec(&qp->srq->ref_count);
+					state = RES_QP_MAPPED;
+					break;
+				default:
+					state = 0;
+				}
+			}
+		}
+		spin_lock_irq(mlx4_tlock(dev));
+	}
+	spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static void rem_slave_srqs(struct mlx4_dev *dev, int slave)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct list_head *srq_list =
+		&tracker->slave_list[slave].res_list[RES_SRQ];
+	struct res_srq *srq;
+	struct res_srq *tmp;
+	int state;
+	u64 in_param;
+	LIST_HEAD(tlist);
+	int srqn;
+	int err;
+
+	err = move_all_busy(dev, slave, RES_SRQ);
+	if (err)
+		mlx4_warn(dev, "rem_slave_srqs: Could not move all srqs to "
+			  "busy for slave %d\n", slave);
+
+	spin_lock_irq(mlx4_tlock(dev));
+	list_for_each_entry_safe(srq, tmp, srq_list, com.list) {
+		spin_unlock_irq(mlx4_tlock(dev));
+		if (srq->com.owner == slave) {
+			srqn = srq->com.res_id;
+			state = srq->com.from_state;
+			while (state != 0) {
+				switch (state) {
+				case RES_SRQ_ALLOCATED:
+					__mlx4_srq_free_icm(dev, srqn);
+					spin_lock_irq(mlx4_tlock(dev));
+					radix_tree_delete(&tracker->res_tree[RES_SRQ],
+							  srqn);
+					list_del(&srq->com.list);
+					spin_unlock_irq(mlx4_tlock(dev));
+					kfree(srq);
+					state = 0;
+					break;
+
+				case RES_SRQ_HW:
+					in_param = slave;
+					err = mlx4_cmd(dev, in_param, srqn, 1,
+						       MLX4_CMD_HW2SW_SRQ,
+						       MLX4_CMD_TIME_CLASS_A,
+						       MLX4_CMD_NATIVE);
+					if (err)
+						mlx4_dbg(dev, "rem_slave_srqs: failed"
+							 " to move slave %d srq %d to"
+							 " SW ownership\n",
+							 slave, srqn);
+
+					atomic_dec(&srq->mtt->ref_count);
+					if (srq->cq)
+						atomic_dec(&srq->cq->ref_count);
+					state = RES_SRQ_ALLOCATED;
+					break;
+
+				default:
+					state = 0;
+				}
+			}
+		}
+		spin_lock_irq(mlx4_tlock(dev));
+	}
+	spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static void rem_slave_cqs(struct mlx4_dev *dev, int slave)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct list_head *cq_list =
+		&tracker->slave_list[slave].res_list[RES_CQ];
+	struct res_cq *cq;
+	struct res_cq *tmp;
+	int state;
+	u64 in_param;
+	LIST_HEAD(tlist);
+	int cqn;
+	int err;
+
+	err = move_all_busy(dev, slave, RES_CQ);
+	if (err)
+		mlx4_warn(dev, "rem_slave_cqs: Could not move all cqs to "
+			  "busy for slave %d\n", slave);
+
+	spin_lock_irq(mlx4_tlock(dev));
+	list_for_each_entry_safe(cq, tmp, cq_list, com.list) {
+		spin_unlock_irq(mlx4_tlock(dev));
+		if (cq->com.owner == slave && !atomic_read(&cq->ref_count)) {
+			cqn = cq->com.res_id;
+			state = cq->com.from_state;
+			while (state != 0) {
+				switch (state) {
+				case RES_CQ_ALLOCATED:
+					__mlx4_cq_free_icm(dev, cqn);
+					spin_lock_irq(mlx4_tlock(dev));
+					radix_tree_delete(&tracker->res_tree[RES_CQ],
+							  cqn);
+					list_del(&cq->com.list);
+					spin_unlock_irq(mlx4_tlock(dev));
+					kfree(cq);
+					state = 0;
+					break;
+
+				case RES_CQ_HW:
+					in_param = slave;
+					err = mlx4_cmd(dev, in_param, cqn, 1,
+						       MLX4_CMD_HW2SW_CQ,
+						       MLX4_CMD_TIME_CLASS_A,
+						       MLX4_CMD_NATIVE);
+					if (err)
+						mlx4_dbg(dev, "rem_slave_cqs: failed"
+							 " to move slave %d cq %d to"
+							 " SW ownership\n",
+							 slave, cqn);
+					atomic_dec(&cq->mtt->ref_count);
+					state = RES_CQ_ALLOCATED;
+					break;
+
+				default:
+					state = 0;
+				}
+			}
+		}
+		spin_lock_irq(mlx4_tlock(dev));
+	}
+	spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static void rem_slave_mrs(struct mlx4_dev *dev, int slave)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct list_head *mpt_list =
+		&tracker->slave_list[slave].res_list[RES_MPT];
+	struct res_mpt *mpt;
+	struct res_mpt *tmp;
+	int state;
+	u64 in_param;
+	LIST_HEAD(tlist);
+	int mptn;
+	int err;
+
+	err = move_all_busy(dev, slave, RES_MPT);
+	if (err)
+		mlx4_warn(dev, "rem_slave_mrs: Could not move all mpts to "
+			  "busy for slave %d\n", slave);
+
+	spin_lock_irq(mlx4_tlock(dev));
+	list_for_each_entry_safe(mpt, tmp, mpt_list, com.list) {
+		spin_unlock_irq(mlx4_tlock(dev));
+		if (mpt->com.owner == slave) {
+			mptn = mpt->com.res_id;
+			state = mpt->com.from_state;
+			while (state != 0) {
+				switch (state) {
+				case RES_MPT_RESERVED:
+					__mlx4_mr_release(dev, mpt->key);
+					spin_lock_irq(mlx4_tlock(dev));
+					radix_tree_delete(&tracker->res_tree[RES_MPT],
+							  mptn);
+					list_del(&mpt->com.list);
+					spin_unlock_irq(mlx4_tlock(dev));
+					kfree(mpt);
+					state = 0;
+					break;
+
+				case RES_MPT_MAPPED:
+					__mlx4_mr_free_icm(dev, mpt->key);
+					state = RES_MPT_RESERVED;
+					break;
+
+				case RES_MPT_HW:
+					in_param = slave;
+					err = mlx4_cmd(dev, in_param, mptn, 0,
+						     MLX4_CMD_HW2SW_MPT,
+						     MLX4_CMD_TIME_CLASS_A,
+						     MLX4_CMD_NATIVE);
+					if (err)
+						mlx4_dbg(dev, "rem_slave_mrs: failed"
+							 " to move slave %d mpt %d to"
+							 " SW ownership\n",
+							 slave, mptn);
+					if (mpt->mtt)
+						atomic_dec(&mpt->mtt->ref_count);
+					state = RES_MPT_MAPPED;
+					break;
+				default:
+					state = 0;
+				}
+			}
+		}
+		spin_lock_irq(mlx4_tlock(dev));
+	}
+	spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static void rem_slave_mtts(struct mlx4_dev *dev, int slave)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker =
+		&priv->mfunc.master.res_tracker;
+	struct list_head *mtt_list =
+		&tracker->slave_list[slave].res_list[RES_MTT];
+	struct res_mtt *mtt;
+	struct res_mtt *tmp;
+	int state;
+	LIST_HEAD(tlist);
+	int base;
+	int err;
+
+	err = move_all_busy(dev, slave, RES_MTT);
+	if (err)
+		mlx4_warn(dev, "rem_slave_mtts: Could not move all mtts to "
+			  "busy for slave %d\n", slave);
+
+	spin_lock_irq(mlx4_tlock(dev));
+	list_for_each_entry_safe(mtt, tmp, mtt_list, com.list) {
+		spin_unlock_irq(mlx4_tlock(dev));
+		if (mtt->com.owner == slave) {
+			base = mtt->com.res_id;
+			state = mtt->com.from_state;
+			while (state != 0) {
+				switch (state) {
+				case RES_MTT_ALLOCATED:
+					__mlx4_free_mtt_range(dev, base,
+							      mtt->order);
+					spin_lock_irq(mlx4_tlock(dev));
+					radix_tree_delete(&tracker->res_tree[RES_MTT],
+							  base);
+					list_del(&mtt->com.list);
+					spin_unlock_irq(mlx4_tlock(dev));
+					kfree(mtt);
+					state = 0;
+					break;
+
+				default:
+					state = 0;
+				}
+			}
+		}
+		spin_lock_irq(mlx4_tlock(dev));
+	}
+	spin_unlock_irq(mlx4_tlock(dev));
+}
+
+static void rem_slave_eqs(struct mlx4_dev *dev, int slave)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_resource_tracker *tracker = &priv->mfunc.master.res_tracker;
+	struct list_head *eq_list =
+		&tracker->slave_list[slave].res_list[RES_EQ];
+	struct res_eq *eq;
+	struct res_eq *tmp;
+	int err;
+	int state;
+	LIST_HEAD(tlist);
+	int eqn;
+	struct mlx4_cmd_mailbox *mailbox;
+
+	err = move_all_busy(dev, slave, RES_EQ);
+	if (err)
+		mlx4_warn(dev, "rem_slave_eqs: Could not move all eqs to "
+			  "busy for slave %d\n", slave);
+
+	spin_lock_irq(mlx4_tlock(dev));
+	list_for_each_entry_safe(eq, tmp, eq_list, com.list) {
+		spin_unlock_irq(mlx4_tlock(dev));
+		if (eq->com.owner == slave) {
+			eqn = eq->com.res_id;
+			state = eq->com.from_state;
+			while (state != 0) {
+				switch (state) {
+				case RES_EQ_RESERVED:
+					spin_lock_irq(mlx4_tlock(dev));
+					radix_tree_delete(&tracker->res_tree[RES_EQ],
+							  eqn);
+					list_del(&eq->com.list);
+					spin_unlock_irq(mlx4_tlock(dev));
+					kfree(eq);
+					state = 0;
+					break;
+
+				case RES_EQ_HW:
+					mailbox = mlx4_alloc_cmd_mailbox(dev);
+					if (IS_ERR(mailbox)) {
+						cond_resched();
+						continue;
+					}
+					err = mlx4_cmd_box(dev, slave, 0,
+							   eqn & 0xff, 0,
+							   MLX4_CMD_HW2SW_EQ,
+							   MLX4_CMD_TIME_CLASS_A,
+							   MLX4_CMD_NATIVE);
+					mlx4_dbg(dev, "rem_slave_eqs: failed"
+						 " to move slave %d eqs %d to"
+						 " SW ownership\n", slave, eqn);
+					mlx4_free_cmd_mailbox(dev, mailbox);
+					if (!err) {
+						atomic_dec(&eq->mtt->ref_count);
+						state = RES_EQ_RESERVED;
+					}
+					break;
+
+				default:
+					state = 0;
+				}
+			}
+		}
+		spin_lock_irq(mlx4_tlock(dev));
+	}
+	spin_unlock_irq(mlx4_tlock(dev));
+}
+
+void mlx4_delete_all_resources_for_slave(struct mlx4_dev *dev, int slave)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	mutex_lock(&priv->mfunc.master.res_tracker.slave_list[slave].mutex);
+	/*VLAN*/
+	rem_slave_macs(dev, slave);
+	rem_slave_qps(dev, slave);
+	rem_slave_srqs(dev, slave);
+	rem_slave_cqs(dev, slave);
+	rem_slave_mrs(dev, slave);
+	rem_slave_eqs(dev, slave);
+	rem_slave_mtts(dev, slave);
+	mutex_unlock(&priv->mfunc.master.res_tracker.slave_list[slave].mutex);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx4/sense.c b/drivers/net/ethernet/mellanox/mlx4/sense.c
index e2337a7..8024982 100644
--- a/drivers/net/ethernet/mellanox/mlx4/sense.c
+++ b/drivers/net/ethernet/mellanox/mlx4/sense.c
@@ -45,7 +45,8 @@ int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port,
 	int err = 0;
 
 	err = mlx4_cmd_imm(dev, 0, &out_param, port, 0,
-			   MLX4_CMD_SENSE_PORT, MLX4_CMD_TIME_CLASS_B);
+			   MLX4_CMD_SENSE_PORT, MLX4_CMD_TIME_CLASS_B,
+			   MLX4_CMD_WRAPPED);
 	if (err) {
 		mlx4_err(dev, "Sense command failed for port: %d\n", port);
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlx4/srq.c b/drivers/net/ethernet/mellanox/mlx4/srq.c
index 9cbf3fc..2823fff 100644
--- a/drivers/net/ethernet/mellanox/mlx4/srq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/srq.c
@@ -31,6 +31,8 @@
  * SOFTWARE.
  */
 
+#include <linux/init.h>
+
 #include <linux/mlx4/cmd.h>
 #include <linux/export.h>
 #include <linux/gfp.h>
@@ -38,26 +40,6 @@
 #include "mlx4.h"
 #include "icm.h"
 
-struct mlx4_srq_context {
-	__be32			state_logsize_srqn;
-	u8			logstride;
-	u8			reserved1;
-	__be16			xrcd;
-	__be32			pg_offset_cqn;
-	u32			reserved2;
-	u8			log_page_size;
-	u8			reserved3[2];
-	u8			mtt_base_addr_h;
-	__be32			mtt_base_addr_l;
-	__be32			pd;
-	__be16			limit_watermark;
-	__be16			wqe_cnt;
-	u16			reserved4;
-	__be16			wqe_counter;
-	u32			reserved5;
-	__be64			db_rec_addr;
-};
-
 void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type)
 {
 	struct mlx4_srq_table *srq_table = &mlx4_priv(dev)->srq_table;
@@ -85,8 +67,9 @@ void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type)
 static int mlx4_SW2HW_SRQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
 			  int srq_num)
 {
-	return mlx4_cmd(dev, mailbox->dma, srq_num, 0, MLX4_CMD_SW2HW_SRQ,
-			MLX4_CMD_TIME_CLASS_A);
+	return mlx4_cmd(dev, mailbox->dma | dev->caps.function, srq_num, 0,
+			MLX4_CMD_SW2HW_SRQ, MLX4_CMD_TIME_CLASS_A,
+			MLX4_CMD_WRAPPED);
 }
 
 static int mlx4_HW2SW_SRQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
@@ -94,48 +77,109 @@ static int mlx4_HW2SW_SRQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox
 {
 	return mlx4_cmd_box(dev, 0, mailbox ? mailbox->dma : 0, srq_num,
 			    mailbox ? 0 : 1, MLX4_CMD_HW2SW_SRQ,
-			    MLX4_CMD_TIME_CLASS_A);
+			    MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 }
 
 static int mlx4_ARM_SRQ(struct mlx4_dev *dev, int srq_num, int limit_watermark)
 {
 	return mlx4_cmd(dev, limit_watermark, srq_num, 0, MLX4_CMD_ARM_SRQ,
-			MLX4_CMD_TIME_CLASS_B);
+			MLX4_CMD_TIME_CLASS_B, MLX4_CMD_WRAPPED);
 }
 
 static int mlx4_QUERY_SRQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
 			  int srq_num)
 {
 	return mlx4_cmd_box(dev, 0, mailbox->dma, srq_num, 0, MLX4_CMD_QUERY_SRQ,
-			    MLX4_CMD_TIME_CLASS_A);
+			    MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
 }
 
-int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, u32 cqn, u16 xrcd,
-		   struct mlx4_mtt *mtt, u64 db_rec, struct mlx4_srq *srq)
+int __mlx4_srq_alloc_icm(struct mlx4_dev *dev, int *srqn)
 {
 	struct mlx4_srq_table *srq_table = &mlx4_priv(dev)->srq_table;
-	struct mlx4_cmd_mailbox *mailbox;
-	struct mlx4_srq_context *srq_context;
-	u64 mtt_addr;
 	int err;
 
-	srq->srqn = mlx4_bitmap_alloc(&srq_table->bitmap);
-	if (srq->srqn == -1)
+
+	*srqn = mlx4_bitmap_alloc(&srq_table->bitmap);
+	if (*srqn == -1)
 		return -ENOMEM;
 
-	err = mlx4_table_get(dev, &srq_table->table, srq->srqn);
+	err = mlx4_table_get(dev, &srq_table->table, *srqn);
 	if (err)
 		goto err_out;
 
-	err = mlx4_table_get(dev, &srq_table->cmpt_table, srq->srqn);
+	err = mlx4_table_get(dev, &srq_table->cmpt_table, *srqn);
 	if (err)
 		goto err_put;
+	return 0;
+
+err_put:
+	mlx4_table_put(dev, &srq_table->table, *srqn);
+
+err_out:
+	mlx4_bitmap_free(&srq_table->bitmap, *srqn);
+	return err;
+}
+
+static int mlx4_srq_alloc_icm(struct mlx4_dev *dev, int *srqn)
+{
+	u64 out_param;
+	int err;
+
+	if (mlx4_is_mfunc(dev)) {
+		err = mlx4_cmd_imm(dev, 0, &out_param, RES_SRQ,
+				   RES_OP_RESERVE_AND_MAP,
+				   MLX4_CMD_ALLOC_RES,
+				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		if (!err)
+			*srqn = get_param_l(&out_param);
+
+		return err;
+	}
+	return __mlx4_srq_alloc_icm(dev, srqn);
+}
+
+void __mlx4_srq_free_icm(struct mlx4_dev *dev, int srqn)
+{
+	struct mlx4_srq_table *srq_table = &mlx4_priv(dev)->srq_table;
+
+	mlx4_table_put(dev, &srq_table->cmpt_table, srqn);
+	mlx4_table_put(dev, &srq_table->table, srqn);
+	mlx4_bitmap_free(&srq_table->bitmap, srqn);
+}
+
+static void mlx4_srq_free_icm(struct mlx4_dev *dev, int srqn)
+{
+	u64 in_param;
+
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&in_param, srqn);
+		if (mlx4_cmd(dev, in_param, RES_SRQ, RES_OP_RESERVE_AND_MAP,
+			     MLX4_CMD_FREE_RES,
+			     MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED))
+			mlx4_warn(dev, "Failed freeing cq:%d\n", srqn);
+		return;
+	}
+	__mlx4_srq_free_icm(dev, srqn);
+}
+
+int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, u32 cqn, u16 xrcd,
+		   struct mlx4_mtt *mtt, u64 db_rec, struct mlx4_srq *srq)
+{
+	struct mlx4_srq_table *srq_table = &mlx4_priv(dev)->srq_table;
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_srq_context *srq_context;
+	u64 mtt_addr;
+	int err;
+
+	err = mlx4_srq_alloc_icm(dev, &srq->srqn);
+	if (err)
+		return err;
 
 	spin_lock_irq(&srq_table->lock);
 	err = radix_tree_insert(&srq_table->tree, srq->srqn, srq);
 	spin_unlock_irq(&srq_table->lock);
 	if (err)
-		goto err_cmpt_put;
+		goto err_icm;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox)) {
@@ -174,15 +218,8 @@ err_radix:
 	radix_tree_delete(&srq_table->tree, srq->srqn);
 	spin_unlock_irq(&srq_table->lock);
 
-err_cmpt_put:
-	mlx4_table_put(dev, &srq_table->cmpt_table, srq->srqn);
-
-err_put:
-	mlx4_table_put(dev, &srq_table->table, srq->srqn);
-
-err_out:
-	mlx4_bitmap_free(&srq_table->bitmap, srq->srqn);
-
+err_icm:
+	mlx4_srq_free_icm(dev, srq->srqn);
 	return err;
 }
 EXPORT_SYMBOL_GPL(mlx4_srq_alloc);
@@ -204,8 +241,7 @@ void mlx4_srq_free(struct mlx4_dev *dev, struct mlx4_srq *srq)
 		complete(&srq->free);
 	wait_for_completion(&srq->free);
 
-	mlx4_table_put(dev, &srq_table->table, srq->srqn);
-	mlx4_bitmap_free(&srq_table->bitmap, srq->srqn);
+	mlx4_srq_free_icm(dev, srq->srqn);
 }
 EXPORT_SYMBOL_GPL(mlx4_srq_free);
 
@@ -245,6 +281,8 @@ int mlx4_init_srq_table(struct mlx4_dev *dev)
 
 	spin_lock_init(&srq_table->lock);
 	INIT_RADIX_TREE(&srq_table->tree, GFP_ATOMIC);
+	if (mlx4_is_slave(dev))
+		return 0;
 
 	err = mlx4_bitmap_init(&srq_table->bitmap, dev->caps.num_srqs,
 			       dev->caps.num_srqs - 1, dev->caps.reserved_srqs, 0);
@@ -256,5 +294,7 @@ int mlx4_init_srq_table(struct mlx4_dev *dev)
 
 void mlx4_cleanup_srq_table(struct mlx4_dev *dev)
 {
+	if (mlx4_is_slave(dev))
+		return;
 	mlx4_bitmap_cleanup(&mlx4_priv(dev)->srq_table.bitmap);
 }
diff --git a/drivers/net/ethernet/micrel/Kconfig b/drivers/net/ethernet/micrel/Kconfig
index d10c2e1..1ea811c 100644
--- a/drivers/net/ethernet/micrel/Kconfig
+++ b/drivers/net/ethernet/micrel/Kconfig
@@ -42,6 +42,8 @@ config KS8851
 	select NET_CORE
 	select MII
 	select CRC32
+	select MISC_DEVICES
+	select EEPROM_93CX6
 	---help---
 	  SPI driver for Micrel KS8851 SPI attached network chip.
 
diff --git a/drivers/net/ethernet/micrel/ks8842.c b/drivers/net/ethernet/micrel/ks8842.c
index 4a6ae05..75ec87a 100644
--- a/drivers/net/ethernet/micrel/ks8842.c
+++ b/drivers/net/ethernet/micrel/ks8842.c
@@ -1264,18 +1264,7 @@ static struct platform_driver ks8842_platform_driver = {
 	.remove		= ks8842_remove,
 };
 
-static int __init ks8842_init(void)
-{
-	return platform_driver_register(&ks8842_platform_driver);
-}
-
-static void __exit ks8842_exit(void)
-{
-	platform_driver_unregister(&ks8842_platform_driver);
-}
-
-module_init(ks8842_init);
-module_exit(ks8842_exit);
+module_platform_driver(ks8842_platform_driver);
 
 MODULE_DESCRIPTION("Timberdale KS8842 ethernet driver");
 MODULE_AUTHOR("Mocean Laboratories <info@mocean-labs.com>");
diff --git a/drivers/net/ethernet/micrel/ks8851.c b/drivers/net/ethernet/micrel/ks8851.c
index f56743a..6b35e7d 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -22,6 +22,7 @@
 #include <linux/cache.h>
 #include <linux/crc32.h>
 #include <linux/mii.h>
+#include <linux/eeprom_93cx6.h>
 
 #include <linux/spi/spi.h>
 
@@ -82,6 +83,7 @@ union ks8851_tx_hdr {
  * @rc_ccr: Cached copy of KS_CCR.
  * @rc_rxqcr: Cached copy of KS_RXQCR.
  * @eeprom_size: Companion eeprom size in Bytes, 0 if no eeprom
+ * @eeprom: 93CX6 EEPROM state for accessing on-board EEPROM.
  *
  * The @lock ensures that the chip is protected when certain operations are
  * in progress. When the read or write packet transfer is in progress, most
@@ -128,6 +130,8 @@ struct ks8851_net {
 	struct spi_message	spi_msg2;
 	struct spi_transfer	spi_xfer1;
 	struct spi_transfer	spi_xfer2[2];
+
+	struct eeprom_93cx6	eeprom;
 };
 
 static int msg_enable;
@@ -343,6 +347,26 @@ static void ks8851_soft_reset(struct ks8851_net *ks, unsigned op)
 }
 
 /**
+ * ks8851_set_powermode - set power mode of the device
+ * @ks: The device state
+ * @pwrmode: The power mode value to write to KS_PMECR.
+ *
+ * Change the power mode of the chip.
+ */
+static void ks8851_set_powermode(struct ks8851_net *ks, unsigned pwrmode)
+{
+	unsigned pmecr;
+
+	netif_dbg(ks, hw, ks->netdev, "setting power mode %d\n", pwrmode);
+
+	pmecr = ks8851_rdreg16(ks, KS_PMECR);
+	pmecr &= ~PMECR_PM_MASK;
+	pmecr |= pwrmode;
+
+	ks8851_wrreg16(ks, KS_PMECR, pmecr);
+}
+
+/**
  * ks8851_write_mac_addr - write mac address to device registers
  * @dev: The network device
  *
@@ -358,8 +382,15 @@ static int ks8851_write_mac_addr(struct net_device *dev)
 
 	mutex_lock(&ks->lock);
 
+	/*
+	 * Wake up chip in case it was powered off when stopped; otherwise,
+	 * the first write to the MAC address does not take effect.
+	 */
+	ks8851_set_powermode(ks, PMECR_PM_NORMAL);
 	for (i = 0; i < ETH_ALEN; i++)
 		ks8851_wrreg8(ks, KS_MAR(i), dev->dev_addr[i]);
+	if (!netif_running(dev))
+		ks8851_set_powermode(ks, PMECR_PM_SOFTDOWN);
 
 	mutex_unlock(&ks->lock);
 
@@ -367,21 +398,47 @@ static int ks8851_write_mac_addr(struct net_device *dev)
 }
 
 /**
+ * ks8851_read_mac_addr - read mac address from device registers
+ * @dev: The network device
+ *
+ * Update our copy of the KS8851 MAC address from the registers of @dev.
+*/
+static void ks8851_read_mac_addr(struct net_device *dev)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	int i;
+
+	mutex_lock(&ks->lock);
+
+	for (i = 0; i < ETH_ALEN; i++)
+		dev->dev_addr[i] = ks8851_rdreg8(ks, KS_MAR(i));
+
+	mutex_unlock(&ks->lock);
+}
+
+/**
  * ks8851_init_mac - initialise the mac address
  * @ks: The device structure
  *
  * Get or create the initial mac address for the device and then set that
- * into the station address register. Currently we assume that the device
- * does not have a valid mac address in it, and so we use random_ether_addr()
+ * into the station address register. If there is an EEPROM present, then
+ * we try that. If no valid mac address is found we use random_ether_addr()
  * to create a new one.
- *
- * In future, the driver should check to see if the device has an EEPROM
- * attached and whether that has a valid ethernet address in it.
  */
 static void ks8851_init_mac(struct ks8851_net *ks)
 {
 	struct net_device *dev = ks->netdev;
 
+	/* first, try reading what we've got already */
+	if (ks->rc_ccr & CCR_EEPROM) {
+		ks8851_read_mac_addr(dev);
+		if (is_valid_ether_addr(dev->dev_addr))
+			return;
+
+		netdev_err(ks->netdev, "invalid mac address read %pM\n",
+				dev->dev_addr);
+	}
+
 	random_ether_addr(dev->dev_addr);
 	ks8851_write_mac_addr(dev);
 }
@@ -739,26 +796,6 @@ static void ks8851_tx_work(struct work_struct *work)
 }
 
 /**
- * ks8851_set_powermode - set power mode of the device
- * @ks: The device state
- * @pwrmode: The power mode value to write to KS_PMECR.
- *
- * Change the power mode of the chip.
- */
-static void ks8851_set_powermode(struct ks8851_net *ks, unsigned pwrmode)
-{
-	unsigned pmecr;
-
-	netif_dbg(ks, hw, ks->netdev, "setting power mode %d\n", pwrmode);
-
-	pmecr = ks8851_rdreg16(ks, KS_PMECR);
-	pmecr &= ~PMECR_PM_MASK;
-	pmecr |= pwrmode;
-
-	ks8851_wrreg16(ks, KS_PMECR, pmecr);
-}
-
-/**
  * ks8851_net_open - open network device
  * @dev: The network device being opened.
  *
@@ -1038,234 +1075,6 @@ static const struct net_device_ops ks8851_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 };
 
-/* Companion eeprom access */
-
-enum {	/* EEPROM programming states */
-	EEPROM_CONTROL,
-	EEPROM_ADDRESS,
-	EEPROM_DATA,
-	EEPROM_COMPLETE
-};
-
-/**
- * ks8851_eeprom_read - read a 16bits word in ks8851 companion EEPROM
- * @dev: The network device the PHY is on.
- * @addr: EEPROM address to read
- *
- * eeprom_size: used to define the data coding length. Can be changed
- * through debug-fs.
- *
- * Programs a read on the EEPROM using ks8851 EEPROM SW access feature.
- * Warning: The READ feature is not supported on ks8851 revision 0.
- *
- * Rough programming model:
- *  - on period start: set clock high and read value on bus
- *  - on period / 2: set clock low and program value on bus
- *  - start on period / 2
- */
-unsigned int ks8851_eeprom_read(struct net_device *dev, unsigned int addr)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	int eepcr;
-	int ctrl = EEPROM_OP_READ;
-	int state = EEPROM_CONTROL;
-	int bit_count = EEPROM_OP_LEN - 1;
-	unsigned int data = 0;
-	int dummy;
-	unsigned int addr_len;
-
-	addr_len = (ks->eeprom_size == 128) ? 6 : 8;
-
-	/* start transaction: chip select high, authorize write */
-	mutex_lock(&ks->lock);
-	eepcr = EEPCR_EESA | EEPCR_EESRWA;
-	ks8851_wrreg16(ks, KS_EEPCR, eepcr);
-	eepcr |= EEPCR_EECS;
-	ks8851_wrreg16(ks, KS_EEPCR, eepcr);
-	mutex_unlock(&ks->lock);
-
-	while (state != EEPROM_COMPLETE) {
-		/* falling clock period starts... */
-		/* set EED_IO pin for control and address */
-		eepcr &= ~EEPCR_EEDO;
-		switch (state) {
-		case EEPROM_CONTROL:
-			eepcr |= ((ctrl >> bit_count) & 1) << 2;
-			if (bit_count-- <= 0) {
-				bit_count = addr_len - 1;
-				state = EEPROM_ADDRESS;
-			}
-			break;
-		case EEPROM_ADDRESS:
-			eepcr |= ((addr >> bit_count) & 1) << 2;
-			bit_count--;
-			break;
-		case EEPROM_DATA:
-			/* Change to receive mode */
-			eepcr &= ~EEPCR_EESRWA;
-			break;
-		}
-
-		/* lower clock  */
-		eepcr &= ~EEPCR_EESCK;
-
-		mutex_lock(&ks->lock);
-		ks8851_wrreg16(ks, KS_EEPCR, eepcr);
-		mutex_unlock(&ks->lock);
-
-		/* waitread period / 2 */
-		udelay(EEPROM_SK_PERIOD / 2);
-
-		/* rising clock period starts... */
-
-		/* raise clock */
-		mutex_lock(&ks->lock);
-		eepcr |= EEPCR_EESCK;
-		ks8851_wrreg16(ks, KS_EEPCR, eepcr);
-		mutex_unlock(&ks->lock);
-
-		/* Manage read */
-		switch (state) {
-		case EEPROM_ADDRESS:
-			if (bit_count < 0) {
-				bit_count = EEPROM_DATA_LEN - 1;
-				state = EEPROM_DATA;
-			}
-			break;
-		case EEPROM_DATA:
-			mutex_lock(&ks->lock);
-			dummy = ks8851_rdreg16(ks, KS_EEPCR);
-			mutex_unlock(&ks->lock);
-			data |= ((dummy >> EEPCR_EESB_OFFSET) & 1) << bit_count;
-			if (bit_count-- <= 0)
-				state = EEPROM_COMPLETE;
-			break;
-		}
-
-		/* wait period / 2 */
-		udelay(EEPROM_SK_PERIOD / 2);
-	}
-
-	/* close transaction */
-	mutex_lock(&ks->lock);
-	eepcr &= ~EEPCR_EECS;
-	ks8851_wrreg16(ks, KS_EEPCR, eepcr);
-	eepcr = 0;
-	ks8851_wrreg16(ks, KS_EEPCR, eepcr);
-	mutex_unlock(&ks->lock);
-
-	return data;
-}
-
-/**
- * ks8851_eeprom_write - write a 16bits word in ks8851 companion EEPROM
- * @dev: The network device the PHY is on.
- * @op: operand (can be WRITE, EWEN, EWDS)
- * @addr: EEPROM address to write
- * @data: data to write
- *
- * eeprom_size: used to define the data coding length. Can be changed
- * through debug-fs.
- *
- * Programs a write on the EEPROM using ks8851 EEPROM SW access feature.
- *
- * Note that a write enable is required before writing data.
- *
- * Rough programming model:
- *  - on period start: set clock high
- *  - on period / 2: set clock low and program value on bus
- *  - start on period / 2
- */
-void ks8851_eeprom_write(struct net_device *dev, unsigned int op,
-					unsigned int addr, unsigned int data)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	int eepcr;
-	int state = EEPROM_CONTROL;
-	int bit_count = EEPROM_OP_LEN - 1;
-	unsigned int addr_len;
-
-	addr_len = (ks->eeprom_size == 128) ? 6 : 8;
-
-	switch (op) {
-	case EEPROM_OP_EWEN:
-		addr = 0x30;
-	break;
-	case EEPROM_OP_EWDS:
-		addr = 0;
-		break;
-	}
-
-	/* start transaction: chip select high, authorize write */
-	mutex_lock(&ks->lock);
-	eepcr = EEPCR_EESA | EEPCR_EESRWA;
-	ks8851_wrreg16(ks, KS_EEPCR, eepcr);
-	eepcr |= EEPCR_EECS;
-	ks8851_wrreg16(ks, KS_EEPCR, eepcr);
-	mutex_unlock(&ks->lock);
-
-	while (state != EEPROM_COMPLETE) {
-		/* falling clock period starts... */
-		/* set EED_IO pin for control and address */
-		eepcr &= ~EEPCR_EEDO;
-		switch (state) {
-		case EEPROM_CONTROL:
-			eepcr |= ((op >> bit_count) & 1) << 2;
-			if (bit_count-- <= 0) {
-				bit_count = addr_len - 1;
-				state = EEPROM_ADDRESS;
-			}
-			break;
-		case EEPROM_ADDRESS:
-			eepcr |= ((addr >> bit_count) & 1) << 2;
-			if (bit_count-- <= 0) {
-				if (op == EEPROM_OP_WRITE) {
-					bit_count = EEPROM_DATA_LEN - 1;
-					state = EEPROM_DATA;
-				} else {
-					state = EEPROM_COMPLETE;
-				}
-			}
-			break;
-		case EEPROM_DATA:
-			eepcr |= ((data >> bit_count) & 1) << 2;
-			if (bit_count-- <= 0)
-				state = EEPROM_COMPLETE;
-			break;
-		}
-
-		/* lower clock  */
-		eepcr &= ~EEPCR_EESCK;
-
-		mutex_lock(&ks->lock);
-		ks8851_wrreg16(ks, KS_EEPCR, eepcr);
-		mutex_unlock(&ks->lock);
-
-		/* wait period / 2 */
-		udelay(EEPROM_SK_PERIOD / 2);
-
-		/* rising clock period starts... */
-
-		/* raise clock */
-		eepcr |= EEPCR_EESCK;
-		mutex_lock(&ks->lock);
-		ks8851_wrreg16(ks, KS_EEPCR, eepcr);
-		mutex_unlock(&ks->lock);
-
-		/* wait period / 2 */
-		udelay(EEPROM_SK_PERIOD / 2);
-	}
-
-	/* close transaction */
-	mutex_lock(&ks->lock);
-	eepcr &= ~EEPCR_EECS;
-	ks8851_wrreg16(ks, KS_EEPCR, eepcr);
-	eepcr = 0;
-	ks8851_wrreg16(ks, KS_EEPCR, eepcr);
-	mutex_unlock(&ks->lock);
-
-}
-
 /* ethtool support */
 
 static void ks8851_get_drvinfo(struct net_device *dev,
@@ -1312,115 +1121,141 @@ static int ks8851_nway_reset(struct net_device *dev)
 	return mii_nway_restart(&ks->mii);
 }
 
-static int ks8851_get_eeprom_len(struct net_device *dev)
-{
-	struct ks8851_net *ks = netdev_priv(dev);
-	return ks->eeprom_size;
-}
+/* EEPROM support */
 
-static int ks8851_get_eeprom(struct net_device *dev,
-			    struct ethtool_eeprom *eeprom, u8 *bytes)
+static void ks8851_eeprom_regread(struct eeprom_93cx6 *ee)
 {
-	struct ks8851_net *ks = netdev_priv(dev);
-	u16 *eeprom_buff;
-	int first_word;
-	int last_word;
-	int ret_val = 0;
-	u16 i;
-
-	if (eeprom->len == 0)
-		return -EINVAL;
+	struct ks8851_net *ks = ee->data;
+	unsigned val;
 
-	if (eeprom->len > ks->eeprom_size)
-		return -EINVAL;
+	val = ks8851_rdreg16(ks, KS_EEPCR);
 
-	eeprom->magic = ks8851_rdreg16(ks, KS_CIDER);
+	ee->reg_data_out = (val & EEPCR_EESB) ? 1 : 0;
+	ee->reg_data_clock = (val & EEPCR_EESCK) ? 1 : 0;
+	ee->reg_chip_select = (val & EEPCR_EECS) ? 1 : 0;
+}
 
-	first_word = eeprom->offset >> 1;
-	last_word = (eeprom->offset + eeprom->len - 1) >> 1;
+static void ks8851_eeprom_regwrite(struct eeprom_93cx6 *ee)
+{
+	struct ks8851_net *ks = ee->data;
+	unsigned val = EEPCR_EESA;	/* default - eeprom access on */
+
+	if (ee->drive_data)
+		val |= EEPCR_EESRWA;
+	if (ee->reg_data_in)
+		val |= EEPCR_EEDO;
+	if (ee->reg_data_clock)
+		val |= EEPCR_EESCK;
+	if (ee->reg_chip_select)
+		val |= EEPCR_EECS;
+
+	ks8851_wrreg16(ks, KS_EEPCR, val);
+}
 
-	eeprom_buff = kmalloc(sizeof(u16) *
-			(last_word - first_word + 1), GFP_KERNEL);
-	if (!eeprom_buff)
-		return -ENOMEM;
+/**
+ * ks8851_eeprom_claim - claim device EEPROM and activate the interface
+ * @ks: The network device state.
+ *
+ * Check for the presence of an EEPROM, and then activate software access
+ * to the device.
+ */
+static int ks8851_eeprom_claim(struct ks8851_net *ks)
+{
+	if (!(ks->rc_ccr & CCR_EEPROM))
+		return -ENOENT;
 
-	for (i = 0; i < last_word - first_word + 1; i++)
-		eeprom_buff[i] = ks8851_eeprom_read(dev, first_word + 1);
+	mutex_lock(&ks->lock);
 
-	/* Device's eeprom is little-endian, word addressable */
-	for (i = 0; i < last_word - first_word + 1; i++)
-		le16_to_cpus(&eeprom_buff[i]);
+	/* start with clock low, cs high */
+	ks8851_wrreg16(ks, KS_EEPCR, EEPCR_EESA | EEPCR_EECS);
+	return 0;
+}
 
-	memcpy(bytes, (u8 *)eeprom_buff + (eeprom->offset & 1), eeprom->len);
-	kfree(eeprom_buff);
+/**
+ * ks8851_eeprom_release - release the EEPROM interface
+ * @ks: The device state
+ *
+ * Release the software access to the device EEPROM
+ */
+static void ks8851_eeprom_release(struct ks8851_net *ks)
+{
+	unsigned val = ks8851_rdreg16(ks, KS_EEPCR);
 
-	return ret_val;
+	ks8851_wrreg16(ks, KS_EEPCR, val & ~EEPCR_EESA);
+	mutex_unlock(&ks->lock);
 }
 
+#define KS_EEPROM_MAGIC (0x00008851)
+
 static int ks8851_set_eeprom(struct net_device *dev,
-			    struct ethtool_eeprom *eeprom, u8 *bytes)
+			     struct ethtool_eeprom *ee, u8 *data)
 {
 	struct ks8851_net *ks = netdev_priv(dev);
-	u16 *eeprom_buff;
-	void *ptr;
-	int max_len;
-	int first_word;
-	int last_word;
-	int ret_val = 0;
-	u16 i;
-
-	if (eeprom->len == 0)
-		return -EOPNOTSUPP;
-
-	if (eeprom->len > ks->eeprom_size)
+	int offset = ee->offset;
+	int len = ee->len;
+	u16 tmp;
+
+	/* currently only support byte writing */
+	if (len != 1)
 		return -EINVAL;
 
-	if (eeprom->magic != ks8851_rdreg16(ks, KS_CIDER))
-		return -EFAULT;
+	if (ee->magic != KS_EEPROM_MAGIC)
+		return -EINVAL;
 
-	first_word = eeprom->offset >> 1;
-	last_word = (eeprom->offset + eeprom->len - 1) >> 1;
-	max_len = (last_word - first_word + 1) * 2;
-	eeprom_buff = kmalloc(max_len, GFP_KERNEL);
-	if (!eeprom_buff)
-		return -ENOMEM;
+	if (ks8851_eeprom_claim(ks))
+		return -ENOENT;
 
-	ptr = (void *)eeprom_buff;
+	eeprom_93cx6_wren(&ks->eeprom, true);
 
-	if (eeprom->offset & 1) {
-		/* need read/modify/write of first changed EEPROM word */
-		/* only the second byte of the word is being modified */
-		eeprom_buff[0] = ks8851_eeprom_read(dev, first_word);
-		ptr++;
+	/* ethtool currently only supports writing bytes, which means
+	 * we have to read/modify/write our 16bit EEPROMs */
+
+	eeprom_93cx6_read(&ks->eeprom, offset/2, &tmp);
+
+	if (offset & 1) {
+		tmp &= 0xff;
+		tmp |= *data << 8;
+	} else {
+		tmp &= 0xff00;
+		tmp |= *data;
 	}
-	if ((eeprom->offset + eeprom->len) & 1)
-		/* need read/modify/write of last changed EEPROM word */
-		/* only the first byte of the word is being modified */
-		eeprom_buff[last_word - first_word] =
-					ks8851_eeprom_read(dev, last_word);
 
+	eeprom_93cx6_write(&ks->eeprom, offset/2, tmp);
+	eeprom_93cx6_wren(&ks->eeprom, false);
 
-	/* Device's eeprom is little-endian, word addressable */
-	le16_to_cpus(&eeprom_buff[0]);
-	le16_to_cpus(&eeprom_buff[last_word - first_word]);
+	ks8851_eeprom_release(ks);
 
-	memcpy(ptr, bytes, eeprom->len);
+	return 0;
+}
 
-	for (i = 0; i < last_word - first_word + 1; i++)
-		eeprom_buff[i] = cpu_to_le16(eeprom_buff[i]);
+static int ks8851_get_eeprom(struct net_device *dev,
+			     struct ethtool_eeprom *ee, u8 *data)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+	int offset = ee->offset;
+	int len = ee->len;
 
-	ks8851_eeprom_write(dev, EEPROM_OP_EWEN, 0, 0);
+	/* must be 2 byte aligned */
+	if (len & 1 || offset & 1)
+		return -EINVAL;
 
-	for (i = 0; i < last_word - first_word + 1; i++) {
-		ks8851_eeprom_write(dev, EEPROM_OP_WRITE, first_word + i,
-							eeprom_buff[i]);
-		mdelay(EEPROM_WRITE_TIME);
-	}
+	if (ks8851_eeprom_claim(ks))
+		return -ENOENT;
+
+	ee->magic = KS_EEPROM_MAGIC;
 
-	ks8851_eeprom_write(dev, EEPROM_OP_EWDS, 0, 0);
+	eeprom_93cx6_multiread(&ks->eeprom, offset/2, (__le16 *)data, len/2);
+	ks8851_eeprom_release(ks);
 
-	kfree(eeprom_buff);
-	return ret_val;
+	return 0;
+}
+
+static int ks8851_get_eeprom_len(struct net_device *dev)
+{
+	struct ks8851_net *ks = netdev_priv(dev);
+
+	/* currently, we assume it is an 93C46 attached, so return 128 */
+	return ks->rc_ccr & CCR_EEPROM ? 128 : 0;
 }
 
 static const struct ethtool_ops ks8851_ethtool_ops = {
@@ -1613,6 +1448,13 @@ static int __devinit ks8851_probe(struct spi_device *spi)
 	spi_message_add_tail(&ks->spi_xfer2[0], &ks->spi_msg2);
 	spi_message_add_tail(&ks->spi_xfer2[1], &ks->spi_msg2);
 
+	/* setup EEPROM state */
+
+	ks->eeprom.data = ks;
+	ks->eeprom.width = PCI_EEPROM_WIDTH_93C46;
+	ks->eeprom.register_read = ks8851_eeprom_regread;
+	ks->eeprom.register_write = ks8851_eeprom_regwrite;
+
 	/* setup mii state */
 	ks->mii.dev		= ndev;
 	ks->mii.phy_id		= 1,
@@ -1674,9 +1516,10 @@ static int __devinit ks8851_probe(struct spi_device *spi)
 		goto err_netdev;
 	}
 
-	netdev_info(ndev, "revision %d, MAC %pM, IRQ %d\n",
+	netdev_info(ndev, "revision %d, MAC %pM, IRQ %d, %s EEPROM\n",
 		    CIDER_REV_GET(ks8851_rdreg16(ks, KS_CIDER)),
-		    ndev->dev_addr, ndev->irq);
+		    ndev->dev_addr, ndev->irq,
+		    ks->rc_ccr & CCR_EEPROM ? "has" : "no");
 
 	return 0;
 
diff --git a/drivers/net/ethernet/micrel/ks8851.h b/drivers/net/ethernet/micrel/ks8851.h
index 537fb06e..b0fae86 100644
--- a/drivers/net/ethernet/micrel/ks8851.h
+++ b/drivers/net/ethernet/micrel/ks8851.h
@@ -16,7 +16,7 @@
 #define CCR_32PIN				(1 << 0)
 
 /* MAC address registers */
-#define KS_MAR(_m)				0x15 - (_m)
+#define KS_MAR(_m)				(0x15 - (_m))
 #define KS_MARL					0x10
 #define KS_MARM					0x12
 #define KS_MARH					0x14
@@ -27,22 +27,11 @@
 #define KS_EEPCR				0x22
 #define EEPCR_EESRWA				(1 << 5)
 #define EEPCR_EESA				(1 << 4)
-#define EEPCR_EESB_OFFSET			3
-#define EEPCR_EESB				(1 << EEPCR_EESB_OFFSET)
+#define EEPCR_EESB				(1 << 3)
 #define EEPCR_EEDO				(1 << 2)
 #define EEPCR_EESCK				(1 << 1)
 #define EEPCR_EECS				(1 << 0)
 
-#define EEPROM_OP_LEN				3	/* bits:*/
-#define EEPROM_OP_READ				0x06
-#define EEPROM_OP_EWEN				0x04
-#define EEPROM_OP_WRITE				0x05
-#define EEPROM_OP_EWDS				0x14
-
-#define EEPROM_DATA_LEN				16	/* 16 bits EEPROM */
-#define EEPROM_WRITE_TIME			4	/* wrt ack time in ms */
-#define EEPROM_SK_PERIOD			400	/* in us */
-
 #define KS_MBIR					0x24
 #define MBIR_TXMBF				(1 << 12)
 #define MBIR_TXMBFA				(1 << 11)
diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c
index d19c849..e58e78e 100644
--- a/drivers/net/ethernet/micrel/ks8851_mll.c
+++ b/drivers/net/ethernet/micrel/ks8851_mll.c
@@ -1500,8 +1500,7 @@ static int ks_hw_init(struct ks_net *ks)
 	ks->all_mcast = 0;
 	ks->mcast_lst_size = 0;
 
-	ks->frame_head_info = (struct type_frame_head *) \
-		kmalloc(MHEADER_SIZE, GFP_KERNEL);
+	ks->frame_head_info = kmalloc(MHEADER_SIZE, GFP_KERNEL);
 	if (!ks->frame_head_info) {
 		pr_err("Error: Fail to allocate frame memory\n");
 		return false;
@@ -1659,18 +1658,7 @@ static struct platform_driver ks8851_platform_driver = {
 	.remove = __devexit_p(ks8851_remove),
 };
 
-static int __init ks8851_init(void)
-{
-	return platform_driver_register(&ks8851_platform_driver);
-}
-
-static void __exit ks8851_exit(void)
-{
-	platform_driver_unregister(&ks8851_platform_driver);
-}
-
-module_init(ks8851_init);
-module_exit(ks8851_exit);
+module_platform_driver(ks8851_platform_driver);
 
 MODULE_DESCRIPTION("KS8851 MLL Network driver");
 MODULE_AUTHOR("David Choi <david.choi@micrel.com>");
diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index 7ece990..a718865 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -743,8 +743,7 @@
 /* Change default LED mode. */
 #define SET_DEFAULT_LED			LED_SPEED_DUPLEX_ACT
 
-#define MAC_ADDR_LEN			6
-#define MAC_ADDR_ORDER(i)		(MAC_ADDR_LEN - 1 - (i))
+#define MAC_ADDR_ORDER(i)		(ETH_ALEN - 1 - (i))
 
 #define MAX_ETHERNET_BODY_SIZE		1500
 #define ETHERNET_HEADER_SIZE		14
@@ -1043,7 +1042,7 @@ enum {
  * @valid:	Valid setting indicating the entry is being used.
  */
 struct ksz_mac_table {
-	u8 mac_addr[MAC_ADDR_LEN];
+	u8 mac_addr[ETH_ALEN];
 	u16 vid;
 	u8 fid;
 	u8 ports;
@@ -1187,8 +1186,8 @@ struct ksz_switch {
 	u8 diffserv[DIFFSERV_ENTRIES];
 	u8 p_802_1p[PRIO_802_1P_ENTRIES];
 
-	u8 br_addr[MAC_ADDR_LEN];
-	u8 other_addr[MAC_ADDR_LEN];
+	u8 br_addr[ETH_ALEN];
+	u8 other_addr[ETH_ALEN];
 
 	u8 broad_per;
 	u8 member;
@@ -1292,14 +1291,14 @@ struct ksz_hw {
 	int tx_int_mask;
 	int tx_size;
 
-	u8 perm_addr[MAC_ADDR_LEN];
-	u8 override_addr[MAC_ADDR_LEN];
-	u8 address[ADDITIONAL_ENTRIES][MAC_ADDR_LEN];
+	u8 perm_addr[ETH_ALEN];
+	u8 override_addr[ETH_ALEN];
+	u8 address[ADDITIONAL_ENTRIES][ETH_ALEN];
 	u8 addr_list_size;
 	u8 mac_override;
 	u8 promiscuous;
 	u8 all_multi;
-	u8 multi_list[MAX_MULTICAST_LIST][MAC_ADDR_LEN];
+	u8 multi_list[MAX_MULTICAST_LIST][ETH_ALEN];
 	u8 multi_bits[HW_MULTICAST_SIZE];
 	u8 multi_list_size;
 
@@ -3654,7 +3653,7 @@ static void hw_add_wol_bcast(struct ksz_hw *hw)
 	static const u8 mask[] = { 0x3F };
 	static const u8 pattern[] = { 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF };
 
-	hw_set_wol_frame(hw, 2, 1, mask, MAC_ADDR_LEN, pattern);
+	hw_set_wol_frame(hw, 2, 1, mask, ETH_ALEN, pattern);
 }
 
 /**
@@ -3689,7 +3688,7 @@ static void hw_add_wol_ucast(struct ksz_hw *hw)
 {
 	static const u8 mask[] = { 0x3F };
 
-	hw_set_wol_frame(hw, 0, 1, mask, MAC_ADDR_LEN, hw->override_addr);
+	hw_set_wol_frame(hw, 0, 1, mask, ETH_ALEN, hw->override_addr);
 }
 
 /**
@@ -4055,7 +4054,7 @@ static void hw_set_addr(struct ksz_hw *hw)
 {
 	int i;
 
-	for (i = 0; i < MAC_ADDR_LEN; i++)
+	for (i = 0; i < ETH_ALEN; i++)
 		writeb(hw->override_addr[MAC_ADDR_ORDER(i)],
 			hw->io + KS884X_ADDR_0_OFFSET + i);
 
@@ -4072,17 +4071,16 @@ static void hw_read_addr(struct ksz_hw *hw)
 {
 	int i;
 
-	for (i = 0; i < MAC_ADDR_LEN; i++)
+	for (i = 0; i < ETH_ALEN; i++)
 		hw->perm_addr[MAC_ADDR_ORDER(i)] = readb(hw->io +
 			KS884X_ADDR_0_OFFSET + i);
 
 	if (!hw->mac_override) {
-		memcpy(hw->override_addr, hw->perm_addr, MAC_ADDR_LEN);
+		memcpy(hw->override_addr, hw->perm_addr, ETH_ALEN);
 		if (empty_addr(hw->override_addr)) {
-			memcpy(hw->perm_addr, DEFAULT_MAC_ADDRESS,
-				MAC_ADDR_LEN);
+			memcpy(hw->perm_addr, DEFAULT_MAC_ADDRESS, ETH_ALEN);
 			memcpy(hw->override_addr, DEFAULT_MAC_ADDRESS,
-				MAC_ADDR_LEN);
+			       ETH_ALEN);
 			hw->override_addr[5] += hw->id;
 			hw_set_addr(hw);
 		}
@@ -4130,16 +4128,16 @@ static int hw_add_addr(struct ksz_hw *hw, u8 *mac_addr)
 	int i;
 	int j = ADDITIONAL_ENTRIES;
 
-	if (!memcmp(hw->override_addr, mac_addr, MAC_ADDR_LEN))
+	if (!memcmp(hw->override_addr, mac_addr, ETH_ALEN))
 		return 0;
 	for (i = 0; i < hw->addr_list_size; i++) {
-		if (!memcmp(hw->address[i], mac_addr, MAC_ADDR_LEN))
+		if (!memcmp(hw->address[i], mac_addr, ETH_ALEN))
 			return 0;
 		if (ADDITIONAL_ENTRIES == j && empty_addr(hw->address[i]))
 			j = i;
 	}
 	if (j < ADDITIONAL_ENTRIES) {
-		memcpy(hw->address[j], mac_addr, MAC_ADDR_LEN);
+		memcpy(hw->address[j], mac_addr, ETH_ALEN);
 		hw_ena_add_addr(hw, j, hw->address[j]);
 		return 0;
 	}
@@ -4151,8 +4149,8 @@ static int hw_del_addr(struct ksz_hw *hw, u8 *mac_addr)
 	int i;
 
 	for (i = 0; i < hw->addr_list_size; i++) {
-		if (!memcmp(hw->address[i], mac_addr, MAC_ADDR_LEN)) {
-			memset(hw->address[i], 0, MAC_ADDR_LEN);
+		if (!memcmp(hw->address[i], mac_addr, ETH_ALEN)) {
+			memset(hw->address[i], 0, ETH_ALEN);
 			writel(0, hw->io + ADD_ADDR_INCR * i +
 				KS_ADD_ADDR_0_HI);
 			return 0;
@@ -4382,12 +4380,10 @@ static void ksz_update_timer(struct ksz_timer_info *info)
  */
 static int ksz_alloc_soft_desc(struct ksz_desc_info *desc_info, int transmit)
 {
-	desc_info->ring = kmalloc(sizeof(struct ksz_desc) * desc_info->alloc,
-		GFP_KERNEL);
+	desc_info->ring = kzalloc(sizeof(struct ksz_desc) * desc_info->alloc,
+				  GFP_KERNEL);
 	if (!desc_info->ring)
 		return 1;
-	memset((void *) desc_info->ring, 0,
-		sizeof(struct ksz_desc) * desc_info->alloc);
 	hw_init_desc(desc_info, transmit);
 	return 0;
 }
@@ -5676,7 +5672,7 @@ static int netdev_set_mac_address(struct net_device *dev, void *addr)
 		hw_del_addr(hw, dev->dev_addr);
 	else {
 		hw->mac_override = 1;
-		memcpy(hw->override_addr, mac->sa_data, MAC_ADDR_LEN);
+		memcpy(hw->override_addr, mac->sa_data, ETH_ALEN);
 	}
 
 	memcpy(dev->dev_addr, mac->sa_data, MAX_ADDR_LEN);
@@ -5786,7 +5782,7 @@ static void netdev_set_rx_mode(struct net_device *dev)
 		netdev_for_each_mc_addr(ha, dev) {
 			if (i >= MAX_MULTICAST_LIST)
 				break;
-			memcpy(hw->multi_list[i++], ha->addr, MAC_ADDR_LEN);
+			memcpy(hw->multi_list[i++], ha->addr, ETH_ALEN);
 		}
 		hw->multi_list_size = (u8) i;
 		hw_set_grp_addr(hw);
@@ -6093,9 +6089,10 @@ static void netdev_get_drvinfo(struct net_device *dev,
 	struct dev_priv *priv = netdev_priv(dev);
 	struct dev_info *hw_priv = priv->adapter;
 
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->bus_info, pci_name(hw_priv->pdev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(hw_priv->pdev),
+		sizeof(info->bus_info));
 }
 
 /**
@@ -6587,7 +6584,8 @@ static void netdev_get_ethtool_stats(struct net_device *dev,
  *
  * Return 0 if successful; otherwise an error code.
  */
-static int netdev_set_features(struct net_device *dev, u32 features)
+static int netdev_set_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct dev_priv *priv = netdev_priv(dev);
 	struct dev_info *hw_priv = priv->adapter;
@@ -6860,7 +6858,7 @@ static void get_mac_addr(struct dev_info *hw_priv, u8 *macaddr, int port)
 	int num;
 
 	i = j = num = got_num = 0;
-	while (j < MAC_ADDR_LEN) {
+	while (j < ETH_ALEN) {
 		if (macaddr[i]) {
 			int digit;
 
@@ -6891,7 +6889,7 @@ static void get_mac_addr(struct dev_info *hw_priv, u8 *macaddr, int port)
 		}
 		i++;
 	}
-	if (MAC_ADDR_LEN == j) {
+	if (ETH_ALEN == j) {
 		if (MAIN_PORT == port)
 			hw_priv->hw.mac_override = 1;
 	}
@@ -7058,7 +7056,7 @@ static int __devinit pcidev_init(struct pci_dev *pdev,
 
 	/* Multiple device interfaces mode requires a second MAC address. */
 	if (hw->dev_count > 1) {
-		memcpy(sw->other_addr, hw->override_addr, MAC_ADDR_LEN);
+		memcpy(sw->other_addr, hw->override_addr, ETH_ALEN);
 		read_other_addr(hw);
 		if (mac1addr[0] != ':')
 			get_mac_addr(hw_priv, mac1addr, OTHER_PORT);
@@ -7108,12 +7106,11 @@ static int __devinit pcidev_init(struct pci_dev *pdev,
 		dev->irq = pdev->irq;
 		if (MAIN_PORT == i)
 			memcpy(dev->dev_addr, hw_priv->hw.override_addr,
-				MAC_ADDR_LEN);
+			       ETH_ALEN);
 		else {
-			memcpy(dev->dev_addr, sw->other_addr,
-				MAC_ADDR_LEN);
+			memcpy(dev->dev_addr, sw->other_addr, ETH_ALEN);
 			if (!memcmp(sw->other_addr, hw->override_addr,
-					MAC_ADDR_LEN))
+				    ETH_ALEN))
 				dev->dev_addr[5] += port->first_port;
 		}
 
diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
index 0778edc..20b72ec 100644
--- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
+++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c
@@ -1491,7 +1491,7 @@ myri10ge_clean_rx_done(struct myri10ge_slice_state *ss, int budget)
 	 * access to avoid theoretical race condition with functions that
 	 * change NETIF_F_LRO flag at runtime.
 	 */
-	bool lro_enabled = ACCESS_ONCE(mgp->dev->features) & NETIF_F_LRO;
+	bool lro_enabled = !!(ACCESS_ONCE(mgp->dev->features) & NETIF_F_LRO);
 
 	while (rx_done->entry[idx].length != 0 && work_done < budget) {
 		length = ntohs(rx_done->entry[idx].length);
@@ -3149,7 +3149,8 @@ static int myri10ge_set_mac_address(struct net_device *dev, void *addr)
 	return 0;
 }
 
-static u32 myri10ge_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t myri10ge_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	if (!(features & NETIF_F_RXCSUM))
 		features &= ~NETIF_F_LRO;
diff --git a/drivers/net/ethernet/natsemi/jazzsonic.c b/drivers/net/ethernet/natsemi/jazzsonic.c
index fc7c6a9..5b89fd3 100644
--- a/drivers/net/ethernet/natsemi/jazzsonic.c
+++ b/drivers/net/ethernet/natsemi/jazzsonic.c
@@ -294,15 +294,4 @@ static struct platform_driver jazz_sonic_driver = {
 	},
 };
 
-static int __init jazz_sonic_init_module(void)
-{
-	return platform_driver_register(&jazz_sonic_driver);
-}
-
-static void __exit jazz_sonic_cleanup_module(void)
-{
-	platform_driver_unregister(&jazz_sonic_driver);
-}
-
-module_init(jazz_sonic_init_module);
-module_exit(jazz_sonic_cleanup_module);
+module_platform_driver(jazz_sonic_driver);
diff --git a/drivers/net/ethernet/natsemi/macsonic.c b/drivers/net/ethernet/natsemi/macsonic.c
index a2eacbf..70367d7 100644
--- a/drivers/net/ethernet/natsemi/macsonic.c
+++ b/drivers/net/ethernet/natsemi/macsonic.c
@@ -643,15 +643,4 @@ static struct platform_driver mac_sonic_driver = {
 	},
 };
 
-static int __init mac_sonic_init_module(void)
-{
-	return platform_driver_register(&mac_sonic_driver);
-}
-
-static void __exit mac_sonic_cleanup_module(void)
-{
-	platform_driver_unregister(&mac_sonic_driver);
-}
-
-module_init(mac_sonic_init_module);
-module_exit(mac_sonic_cleanup_module);
+module_platform_driver(mac_sonic_driver);
diff --git a/drivers/net/ethernet/natsemi/natsemi.c b/drivers/net/ethernet/natsemi/natsemi.c
index 6ca047a..ac7b16b 100644
--- a/drivers/net/ethernet/natsemi/natsemi.c
+++ b/drivers/net/ethernet/natsemi/natsemi.c
@@ -2555,9 +2555,9 @@ static void set_rx_mode(struct net_device *dev)
 static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
 	struct netdev_private *np = netdev_priv(dev);
-	strncpy(info->driver, DRV_NAME, ETHTOOL_BUSINFO_LEN);
-	strncpy(info->version, DRV_VERSION, ETHTOOL_BUSINFO_LEN);
-	strncpy(info->bus_info, pci_name(np->pci_dev), ETHTOOL_BUSINFO_LEN);
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
 }
 
 static int get_regs_len(struct net_device *dev)
diff --git a/drivers/net/ethernet/natsemi/ns83820.c b/drivers/net/ethernet/natsemi/ns83820.c
index 2b8f64d..c24b46c 100644
--- a/drivers/net/ethernet/natsemi/ns83820.c
+++ b/drivers/net/ethernet/natsemi/ns83820.c
@@ -1364,9 +1364,9 @@ static int ns83820_set_settings(struct net_device *ndev,
 static void ns83820_get_drvinfo(struct net_device *ndev, struct ethtool_drvinfo *info)
 {
 	struct ns83820 *dev = PRIV(ndev);
-	strcpy(info->driver, "ns83820");
-	strcpy(info->version, VERSION);
-	strcpy(info->bus_info, pci_name(dev->pci_dev));
+	strlcpy(info->driver, "ns83820", sizeof(info->driver));
+	strlcpy(info->version, VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(dev->pci_dev), sizeof(info->bus_info));
 }
 
 static u32 ns83820_get_link(struct net_device *ndev)
diff --git a/drivers/net/ethernet/natsemi/xtsonic.c b/drivers/net/ethernet/natsemi/xtsonic.c
index ccf61b9..e01c0a0 100644
--- a/drivers/net/ethernet/natsemi/xtsonic.c
+++ b/drivers/net/ethernet/natsemi/xtsonic.c
@@ -319,15 +319,4 @@ static struct platform_driver xtsonic_driver = {
 	},
 };
 
-static int __init xtsonic_init(void)
-{
-	return platform_driver_register(&xtsonic_driver);
-}
-
-static void __exit xtsonic_cleanup(void)
-{
-	platform_driver_unregister(&xtsonic_driver);
-}
-
-module_init(xtsonic_init);
-module_exit(xtsonic_cleanup);
+module_platform_driver(xtsonic_driver);
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index c27fb3d..97f63e1 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -5391,10 +5391,9 @@ static void s2io_ethtool_gdrvinfo(struct net_device *dev,
 {
 	struct s2io_nic *sp = netdev_priv(dev);
 
-	strncpy(info->driver, s2io_driver_name, sizeof(info->driver));
-	strncpy(info->version, s2io_driver_version, sizeof(info->version));
-	strncpy(info->fw_version, "", sizeof(info->fw_version));
-	strncpy(info->bus_info, pci_name(sp->pdev), sizeof(info->bus_info));
+	strlcpy(info->driver, s2io_driver_name, sizeof(info->driver));
+	strlcpy(info->version, s2io_driver_version, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(sp->pdev), sizeof(info->bus_info));
 	info->regdump_len = XENA_REG_SPACE;
 	info->eedump_len = XENA_EEPROM_SPACE;
 }
@@ -6616,10 +6615,10 @@ static void s2io_ethtool_get_strings(struct net_device *dev,
 	}
 }
 
-static int s2io_set_features(struct net_device *dev, u32 features)
+static int s2io_set_features(struct net_device *dev, netdev_features_t features)
 {
 	struct s2io_nic *sp = netdev_priv(dev);
-	u32 changed = (features ^ dev->features) & NETIF_F_LRO;
+	netdev_features_t changed = (features ^ dev->features) & NETIF_F_LRO;
 
 	if (changed && netif_running(dev)) {
 		int rc;
diff --git a/drivers/net/ethernet/neterion/vxge/vxge-main.c b/drivers/net/ethernet/neterion/vxge/vxge-main.c
index a83197d..ef76725 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-main.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-main.c
@@ -2662,9 +2662,10 @@ static void vxge_poll_vp_lockup(unsigned long data)
 	mod_timer(&vdev->vp_lockup_timer, jiffies + HZ / 1000);
 }
 
-static u32 vxge_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t vxge_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
-	u32 changed = dev->features ^ features;
+	netdev_features_t changed = dev->features ^ features;
 
 	/* Enabling RTH requires some of the logic in vxge_device_register and a
 	 * vpath reset.  Due to these restrictions, only allow modification
@@ -2676,10 +2677,10 @@ static u32 vxge_fix_features(struct net_device *dev, u32 features)
 	return features;
 }
 
-static int vxge_set_features(struct net_device *dev, u32 features)
+static int vxge_set_features(struct net_device *dev, netdev_features_t features)
 {
 	struct vxgedev *vdev = netdev_priv(dev);
-	u32 changed = dev->features ^ features;
+	netdev_features_t changed = dev->features ^ features;
 
 	if (!(changed & NETIF_F_RXHASH))
 		return 0;
@@ -3304,7 +3305,7 @@ static void vxge_tx_watchdog(struct net_device *dev)
  *
  * Add the vlan id to the devices vlan id table
  */
-static void
+static int
 vxge_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 {
 	struct vxgedev *vdev = netdev_priv(dev);
@@ -3319,6 +3320,7 @@ vxge_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 		vxge_hw_vpath_vid_add(vpath->handle, vid);
 	}
 	set_bit(vid, vdev->active_vlans);
+	return 0;
 }
 
 /**
@@ -3328,7 +3330,7 @@ vxge_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
  *
  * Remove the vlan id from the device's vlan id table
  */
-static void
+static int
 vxge_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 {
 	struct vxgedev *vdev = netdev_priv(dev);
@@ -3347,6 +3349,7 @@ vxge_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 	vxge_debug_entryexit(VXGE_TRACE,
 		"%s:%d  Exiting...", __func__, __LINE__);
 	clear_bit(vid, vdev->active_vlans);
+	return 0;
 }
 
 static const struct net_device_ops vxge_netdev_ops = {
diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c
index f1bfb8f..b75a049 100644
--- a/drivers/net/ethernet/nuvoton/w90p910_ether.c
+++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c
@@ -1103,18 +1103,7 @@ static struct platform_driver w90p910_ether_driver = {
 	},
 };
 
-static int __init w90p910_ether_init(void)
-{
-	return platform_driver_register(&w90p910_ether_driver);
-}
-
-static void __exit w90p910_ether_exit(void)
-{
-	platform_driver_unregister(&w90p910_ether_driver);
-}
-
-module_init(w90p910_ether_init);
-module_exit(w90p910_ether_exit);
+module_platform_driver(w90p910_ether_driver);
 
 MODULE_AUTHOR("Wan ZongShun <mcuos.com@gmail.com>");
 MODULE_DESCRIPTION("w90p910 MAC driver!");
diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index 1dca570..4c4e7f4 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -65,7 +65,8 @@
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 #include <linux/prefetch.h>
-#include  <linux/io.h>
+#include <linux/u64_stats_sync.h>
+#include <linux/io.h>
 
 #include <asm/irq.h>
 #include <asm/system.h>
@@ -609,7 +610,7 @@ struct nv_ethtool_str {
 };
 
 static const struct nv_ethtool_str nv_estats_str[] = {
-	{ "tx_bytes" },
+	{ "tx_bytes" }, /* includes Ethernet FCS CRC */
 	{ "tx_zero_rexmt" },
 	{ "tx_one_rexmt" },
 	{ "tx_many_rexmt" },
@@ -637,7 +638,7 @@ static const struct nv_ethtool_str nv_estats_str[] = {
 	/* version 2 stats */
 	{ "tx_deferral" },
 	{ "tx_packets" },
-	{ "rx_bytes" },
+	{ "rx_bytes" }, /* includes Ethernet FCS CRC */
 	{ "tx_pause" },
 	{ "rx_pause" },
 	{ "rx_drop_frame" },
@@ -649,7 +650,7 @@ static const struct nv_ethtool_str nv_estats_str[] = {
 };
 
 struct nv_ethtool_stats {
-	u64 tx_bytes;
+	u64 tx_bytes; /* should be ifconfig->tx_bytes + 4*tx_packets */
 	u64 tx_zero_rexmt;
 	u64 tx_one_rexmt;
 	u64 tx_many_rexmt;
@@ -670,14 +671,14 @@ struct nv_ethtool_stats {
 	u64 rx_unicast;
 	u64 rx_multicast;
 	u64 rx_broadcast;
-	u64 rx_packets;
+	u64 rx_packets; /* should be ifconfig->rx_packets */
 	u64 rx_errors_total;
 	u64 tx_errors_total;
 
 	/* version 2 stats */
 	u64 tx_deferral;
-	u64 tx_packets;
-	u64 rx_bytes;
+	u64 tx_packets; /* should be ifconfig->tx_packets */
+	u64 rx_bytes;   /* should be ifconfig->rx_bytes + 4*rx_packets */
 	u64 tx_pause;
 	u64 rx_pause;
 	u64 rx_drop_frame;
@@ -736,6 +737,16 @@ struct nv_skb_map {
  * - tx setup is lockless: it relies on netif_tx_lock. Actual submission
  *	needs netdev_priv(dev)->lock :-(
  * - set_multicast_list: preparation lockless, relies on netif_tx_lock.
+ *
+ * Hardware stats updates are protected by hwstats_lock:
+ * - updated by nv_do_stats_poll (timer). This is meant to avoid
+ *   integer wraparound in the NIC stats registers, at low frequency
+ *   (0.1 Hz)
+ * - updated by nv_get_ethtool_stats + nv_get_stats64
+ *
+ * Software stats are accessed only through 64b synchronization points
+ * and are not subject to other synchronization techniques (single
+ * update thread on the TX or RX paths).
  */
 
 /* in dev: base, irq */
@@ -745,9 +756,10 @@ struct fe_priv {
 	struct net_device *dev;
 	struct napi_struct napi;
 
-	/* General data:
-	 * Locking: spin_lock(&np->lock); */
+	/* hardware stats are updated in syscall and timer */
+	spinlock_t hwstats_lock;
 	struct nv_ethtool_stats estats;
+
 	int in_shutdown;
 	u32 linkspeed;
 	int duplex;
@@ -798,6 +810,13 @@ struct fe_priv {
 	u32 nic_poll_irq;
 	int rx_ring_size;
 
+	/* RX software stats */
+	struct u64_stats_sync swstats_rx_syncp;
+	u64 stat_rx_packets;
+	u64 stat_rx_bytes; /* not always available in HW */
+	u64 stat_rx_missed_errors;
+	u64 stat_rx_dropped;
+
 	/* media detection workaround.
 	 * Locking: Within irq hander or disable_irq+spin_lock(&np->lock);
 	 */
@@ -820,6 +839,12 @@ struct fe_priv {
 	struct nv_skb_map *tx_end_flip;
 	int tx_stop;
 
+	/* TX software stats */
+	struct u64_stats_sync swstats_tx_syncp;
+	u64 stat_tx_packets; /* not always available in HW */
+	u64 stat_tx_bytes;
+	u64 stat_tx_dropped;
+
 	/* msi/msi-x fields */
 	u32 msi_flags;
 	struct msix_entry msi_x_entry[NV_MSI_X_MAX_VECTORS];
@@ -892,6 +917,11 @@ enum {
 static int dma_64bit = NV_DMA_64BIT_ENABLED;
 
 /*
+ * Debug output control for tx_timeout
+ */
+static bool debug_tx_timeout = false;
+
+/*
  * Crossover Detection
  * Realtek 8201 phy + some OEM boards do not work properly.
  */
@@ -1630,11 +1660,19 @@ static void nv_mac_reset(struct net_device *dev)
 	pci_push(base);
 }
 
-static void nv_get_hw_stats(struct net_device *dev)
+/* Caller must appropriately lock netdev_priv(dev)->hwstats_lock */
+static void nv_update_stats(struct net_device *dev)
 {
 	struct fe_priv *np = netdev_priv(dev);
 	u8 __iomem *base = get_hwbase(dev);
 
+	/* If it happens that this is run in top-half context, then
+	 * replace the spin_lock of hwstats_lock with
+	 * spin_lock_irqsave() in calling functions. */
+	WARN_ONCE(in_irq(), "forcedeth: estats spin_lock(_bh) from top-half");
+	assert_spin_locked(&np->hwstats_lock);
+
+	/* query hardware */
 	np->estats.tx_bytes += readl(base + NvRegTxCnt);
 	np->estats.tx_zero_rexmt += readl(base + NvRegTxZeroReXmt);
 	np->estats.tx_one_rexmt += readl(base + NvRegTxOneReXmt);
@@ -1693,33 +1731,73 @@ static void nv_get_hw_stats(struct net_device *dev)
 }
 
 /*
- * nv_get_stats: dev->get_stats function
+ * nv_get_stats64: dev->ndo_get_stats64 function
  * Get latest stats value from the nic.
  * Called with read_lock(&dev_base_lock) held for read -
  * only synchronized against unregister_netdevice.
  */
-static struct net_device_stats *nv_get_stats(struct net_device *dev)
+static struct rtnl_link_stats64*
+nv_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *storage)
+	__acquires(&netdev_priv(dev)->hwstats_lock)
+	__releases(&netdev_priv(dev)->hwstats_lock)
 {
 	struct fe_priv *np = netdev_priv(dev);
+	unsigned int syncp_start;
+
+	/*
+	 * Note: because HW stats are not always available and for
+	 * consistency reasons, the following ifconfig stats are
+	 * managed by software: rx_bytes, tx_bytes, rx_packets and
+	 * tx_packets. The related hardware stats reported by ethtool
+	 * should be equivalent to these ifconfig stats, with 4
+	 * additional bytes per packet (Ethernet FCS CRC), except for
+	 * tx_packets when TSO kicks in.
+	 */
+
+	/* software stats */
+	do {
+		syncp_start = u64_stats_fetch_begin_bh(&np->swstats_rx_syncp);
+		storage->rx_packets       = np->stat_rx_packets;
+		storage->rx_bytes         = np->stat_rx_bytes;
+		storage->rx_dropped       = np->stat_rx_dropped;
+		storage->rx_missed_errors = np->stat_rx_missed_errors;
+	} while (u64_stats_fetch_retry_bh(&np->swstats_rx_syncp, syncp_start));
+
+	do {
+		syncp_start = u64_stats_fetch_begin_bh(&np->swstats_tx_syncp);
+		storage->tx_packets = np->stat_tx_packets;
+		storage->tx_bytes   = np->stat_tx_bytes;
+		storage->tx_dropped = np->stat_tx_dropped;
+	} while (u64_stats_fetch_retry_bh(&np->swstats_tx_syncp, syncp_start));
 
 	/* If the nic supports hw counters then retrieve latest values */
-	if (np->driver_data & (DEV_HAS_STATISTICS_V1|DEV_HAS_STATISTICS_V2|DEV_HAS_STATISTICS_V3)) {
-		nv_get_hw_stats(dev);
-
-		/* copy to net_device stats */
-		dev->stats.tx_packets = np->estats.tx_packets;
-		dev->stats.rx_bytes = np->estats.rx_bytes;
-		dev->stats.tx_bytes = np->estats.tx_bytes;
-		dev->stats.tx_fifo_errors = np->estats.tx_fifo_errors;
-		dev->stats.tx_carrier_errors = np->estats.tx_carrier_errors;
-		dev->stats.rx_crc_errors = np->estats.rx_crc_errors;
-		dev->stats.rx_over_errors = np->estats.rx_over_errors;
-		dev->stats.rx_fifo_errors = np->estats.rx_drop_frame;
-		dev->stats.rx_errors = np->estats.rx_errors_total;
-		dev->stats.tx_errors = np->estats.tx_errors_total;
-	}
-
-	return &dev->stats;
+	if (np->driver_data & DEV_HAS_STATISTICS_V123) {
+		spin_lock_bh(&np->hwstats_lock);
+
+		nv_update_stats(dev);
+
+		/* generic stats */
+		storage->rx_errors = np->estats.rx_errors_total;
+		storage->tx_errors = np->estats.tx_errors_total;
+
+		/* meaningful only when NIC supports stats v3 */
+		storage->multicast = np->estats.rx_multicast;
+
+		/* detailed rx_errors */
+		storage->rx_length_errors = np->estats.rx_length_error;
+		storage->rx_over_errors   = np->estats.rx_over_errors;
+		storage->rx_crc_errors    = np->estats.rx_crc_errors;
+		storage->rx_frame_errors  = np->estats.rx_frame_align_error;
+		storage->rx_fifo_errors   = np->estats.rx_drop_frame;
+
+		/* detailed tx_errors */
+		storage->tx_carrier_errors = np->estats.tx_carrier_errors;
+		storage->tx_fifo_errors    = np->estats.tx_fifo_errors;
+
+		spin_unlock_bh(&np->hwstats_lock);
+	}
+
+	return storage;
 }
 
 /*
@@ -1752,8 +1830,12 @@ static int nv_alloc_rx(struct net_device *dev)
 				np->put_rx.orig = np->first_rx.orig;
 			if (unlikely(np->put_rx_ctx++ == np->last_rx_ctx))
 				np->put_rx_ctx = np->first_rx_ctx;
-		} else
+		} else {
+			u64_stats_update_begin(&np->swstats_rx_syncp);
+			np->stat_rx_dropped++;
+			u64_stats_update_end(&np->swstats_rx_syncp);
 			return 1;
+		}
 	}
 	return 0;
 }
@@ -1784,8 +1866,12 @@ static int nv_alloc_rx_optimized(struct net_device *dev)
 				np->put_rx.ex = np->first_rx.ex;
 			if (unlikely(np->put_rx_ctx++ == np->last_rx_ctx))
 				np->put_rx_ctx = np->first_rx_ctx;
-		} else
+		} else {
+			u64_stats_update_begin(&np->swstats_rx_syncp);
+			np->stat_rx_dropped++;
+			u64_stats_update_end(&np->swstats_rx_syncp);
 			return 1;
+		}
 	}
 	return 0;
 }
@@ -1842,6 +1928,7 @@ static void nv_init_tx(struct net_device *dev)
 		np->last_tx.ex = &np->tx_ring.ex[np->tx_ring_size-1];
 	np->get_tx_ctx = np->put_tx_ctx = np->first_tx_ctx = np->tx_skb;
 	np->last_tx_ctx = &np->tx_skb[np->tx_ring_size-1];
+	netdev_reset_queue(np->dev);
 	np->tx_pkts_in_progress = 0;
 	np->tx_change_owner = NULL;
 	np->tx_end_flip = NULL;
@@ -1920,8 +2007,11 @@ static void nv_drain_tx(struct net_device *dev)
 			np->tx_ring.ex[i].bufhigh = 0;
 			np->tx_ring.ex[i].buflow = 0;
 		}
-		if (nv_release_txskb(np, &np->tx_skb[i]))
-			dev->stats.tx_dropped++;
+		if (nv_release_txskb(np, &np->tx_skb[i])) {
+			u64_stats_update_begin(&np->swstats_tx_syncp);
+			np->stat_tx_dropped++;
+			u64_stats_update_end(&np->swstats_tx_syncp);
+		}
 		np->tx_skb[i].dma = 0;
 		np->tx_skb[i].dma_len = 0;
 		np->tx_skb[i].dma_single = 0;
@@ -2187,6 +2277,9 @@ static netdev_tx_t nv_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* set tx flags */
 	start_tx->flaglen |= cpu_to_le32(tx_flags | tx_flags_extra);
+
+	netdev_sent_queue(np->dev, skb->len);
+
 	np->put_tx.orig = put_tx;
 
 	spin_unlock_irqrestore(&np->lock, flags);
@@ -2331,6 +2424,9 @@ static netdev_tx_t nv_start_xmit_optimized(struct sk_buff *skb,
 
 	/* set tx flags */
 	start_tx->flaglen |= cpu_to_le32(tx_flags | tx_flags_extra);
+
+	netdev_sent_queue(np->dev, skb->len);
+
 	np->put_tx.ex = put_tx;
 
 	spin_unlock_irqrestore(&np->lock, flags);
@@ -2368,6 +2464,7 @@ static int nv_tx_done(struct net_device *dev, int limit)
 	u32 flags;
 	int tx_work = 0;
 	struct ring_desc *orig_get_tx = np->get_tx.orig;
+	unsigned int bytes_compl = 0;
 
 	while ((np->get_tx.orig != np->put_tx.orig) &&
 	       !((flags = le32_to_cpu(np->get_tx.orig->flaglen)) & NV_TX_VALID) &&
@@ -2378,9 +2475,16 @@ static int nv_tx_done(struct net_device *dev, int limit)
 		if (np->desc_ver == DESC_VER_1) {
 			if (flags & NV_TX_LASTPACKET) {
 				if (flags & NV_TX_ERROR) {
-					if ((flags & NV_TX_RETRYERROR) && !(flags & NV_TX_RETRYCOUNT_MASK))
+					if ((flags & NV_TX_RETRYERROR)
+					    && !(flags & NV_TX_RETRYCOUNT_MASK))
 						nv_legacybackoff_reseed(dev);
+				} else {
+					u64_stats_update_begin(&np->swstats_tx_syncp);
+					np->stat_tx_packets++;
+					np->stat_tx_bytes += np->get_tx_ctx->skb->len;
+					u64_stats_update_end(&np->swstats_tx_syncp);
 				}
+				bytes_compl += np->get_tx_ctx->skb->len;
 				dev_kfree_skb_any(np->get_tx_ctx->skb);
 				np->get_tx_ctx->skb = NULL;
 				tx_work++;
@@ -2388,9 +2492,16 @@ static int nv_tx_done(struct net_device *dev, int limit)
 		} else {
 			if (flags & NV_TX2_LASTPACKET) {
 				if (flags & NV_TX2_ERROR) {
-					if ((flags & NV_TX2_RETRYERROR) && !(flags & NV_TX2_RETRYCOUNT_MASK))
+					if ((flags & NV_TX2_RETRYERROR)
+					    && !(flags & NV_TX2_RETRYCOUNT_MASK))
 						nv_legacybackoff_reseed(dev);
+				} else {
+					u64_stats_update_begin(&np->swstats_tx_syncp);
+					np->stat_tx_packets++;
+					np->stat_tx_bytes += np->get_tx_ctx->skb->len;
+					u64_stats_update_end(&np->swstats_tx_syncp);
 				}
+				bytes_compl += np->get_tx_ctx->skb->len;
 				dev_kfree_skb_any(np->get_tx_ctx->skb);
 				np->get_tx_ctx->skb = NULL;
 				tx_work++;
@@ -2401,6 +2512,9 @@ static int nv_tx_done(struct net_device *dev, int limit)
 		if (unlikely(np->get_tx_ctx++ == np->last_tx_ctx))
 			np->get_tx_ctx = np->first_tx_ctx;
 	}
+
+	netdev_completed_queue(np->dev, tx_work, bytes_compl);
+
 	if (unlikely((np->tx_stop == 1) && (np->get_tx.orig != orig_get_tx))) {
 		np->tx_stop = 0;
 		netif_wake_queue(dev);
@@ -2414,6 +2528,7 @@ static int nv_tx_done_optimized(struct net_device *dev, int limit)
 	u32 flags;
 	int tx_work = 0;
 	struct ring_desc_ex *orig_get_tx = np->get_tx.ex;
+	unsigned long bytes_cleaned = 0;
 
 	while ((np->get_tx.ex != np->put_tx.ex) &&
 	       !((flags = le32_to_cpu(np->get_tx.ex->flaglen)) & NV_TX2_VALID) &&
@@ -2423,14 +2538,21 @@ static int nv_tx_done_optimized(struct net_device *dev, int limit)
 
 		if (flags & NV_TX2_LASTPACKET) {
 			if (flags & NV_TX2_ERROR) {
-				if ((flags & NV_TX2_RETRYERROR) && !(flags & NV_TX2_RETRYCOUNT_MASK)) {
+				if ((flags & NV_TX2_RETRYERROR)
+				    && !(flags & NV_TX2_RETRYCOUNT_MASK)) {
 					if (np->driver_data & DEV_HAS_GEAR_MODE)
 						nv_gear_backoff_reseed(dev);
 					else
 						nv_legacybackoff_reseed(dev);
 				}
+			} else {
+				u64_stats_update_begin(&np->swstats_tx_syncp);
+				np->stat_tx_packets++;
+				np->stat_tx_bytes += np->get_tx_ctx->skb->len;
+				u64_stats_update_end(&np->swstats_tx_syncp);
 			}
 
+			bytes_cleaned += np->get_tx_ctx->skb->len;
 			dev_kfree_skb_any(np->get_tx_ctx->skb);
 			np->get_tx_ctx->skb = NULL;
 			tx_work++;
@@ -2438,11 +2560,15 @@ static int nv_tx_done_optimized(struct net_device *dev, int limit)
 			if (np->tx_limit)
 				nv_tx_flip_ownership(dev);
 		}
+
 		if (unlikely(np->get_tx.ex++ == np->last_tx.ex))
 			np->get_tx.ex = np->first_tx.ex;
 		if (unlikely(np->get_tx_ctx++ == np->last_tx_ctx))
 			np->get_tx_ctx = np->first_tx_ctx;
 	}
+
+	netdev_completed_queue(np->dev, tx_work, bytes_cleaned);
+
 	if (unlikely((np->tx_stop == 1) && (np->get_tx.ex != orig_get_tx))) {
 		np->tx_stop = 0;
 		netif_wake_queue(dev);
@@ -2461,56 +2587,64 @@ static void nv_tx_timeout(struct net_device *dev)
 	u32 status;
 	union ring_type put_tx;
 	int saved_tx_limit;
-	int i;
 
 	if (np->msi_flags & NV_MSI_X_ENABLED)
 		status = readl(base + NvRegMSIXIrqStatus) & NVREG_IRQSTAT_MASK;
 	else
 		status = readl(base + NvRegIrqStatus) & NVREG_IRQSTAT_MASK;
 
-	netdev_info(dev, "Got tx_timeout. irq: %08x\n", status);
+	netdev_warn(dev, "Got tx_timeout. irq status: %08x\n", status);
 
-	netdev_info(dev, "Ring at %lx\n", (unsigned long)np->ring_addr);
-	netdev_info(dev, "Dumping tx registers\n");
-	for (i = 0; i <= np->register_size; i += 32) {
-		netdev_info(dev,
-			    "%3x: %08x %08x %08x %08x %08x %08x %08x %08x\n",
-			    i,
-			    readl(base + i + 0), readl(base + i + 4),
-			    readl(base + i + 8), readl(base + i + 12),
-			    readl(base + i + 16), readl(base + i + 20),
-			    readl(base + i + 24), readl(base + i + 28));
-	}
-	netdev_info(dev, "Dumping tx ring\n");
-	for (i = 0; i < np->tx_ring_size; i += 4) {
-		if (!nv_optimized(np)) {
-			netdev_info(dev,
-				    "%03x: %08x %08x // %08x %08x // %08x %08x // %08x %08x\n",
-				    i,
-				    le32_to_cpu(np->tx_ring.orig[i].buf),
-				    le32_to_cpu(np->tx_ring.orig[i].flaglen),
-				    le32_to_cpu(np->tx_ring.orig[i+1].buf),
-				    le32_to_cpu(np->tx_ring.orig[i+1].flaglen),
-				    le32_to_cpu(np->tx_ring.orig[i+2].buf),
-				    le32_to_cpu(np->tx_ring.orig[i+2].flaglen),
-				    le32_to_cpu(np->tx_ring.orig[i+3].buf),
-				    le32_to_cpu(np->tx_ring.orig[i+3].flaglen));
-		} else {
+	if (unlikely(debug_tx_timeout)) {
+		int i;
+
+		netdev_info(dev, "Ring at %lx\n", (unsigned long)np->ring_addr);
+		netdev_info(dev, "Dumping tx registers\n");
+		for (i = 0; i <= np->register_size; i += 32) {
 			netdev_info(dev,
-				    "%03x: %08x %08x %08x // %08x %08x %08x // %08x %08x %08x // %08x %08x %08x\n",
+				    "%3x: %08x %08x %08x %08x "
+				    "%08x %08x %08x %08x\n",
 				    i,
-				    le32_to_cpu(np->tx_ring.ex[i].bufhigh),
-				    le32_to_cpu(np->tx_ring.ex[i].buflow),
-				    le32_to_cpu(np->tx_ring.ex[i].flaglen),
-				    le32_to_cpu(np->tx_ring.ex[i+1].bufhigh),
-				    le32_to_cpu(np->tx_ring.ex[i+1].buflow),
-				    le32_to_cpu(np->tx_ring.ex[i+1].flaglen),
-				    le32_to_cpu(np->tx_ring.ex[i+2].bufhigh),
-				    le32_to_cpu(np->tx_ring.ex[i+2].buflow),
-				    le32_to_cpu(np->tx_ring.ex[i+2].flaglen),
-				    le32_to_cpu(np->tx_ring.ex[i+3].bufhigh),
-				    le32_to_cpu(np->tx_ring.ex[i+3].buflow),
-				    le32_to_cpu(np->tx_ring.ex[i+3].flaglen));
+				    readl(base + i + 0), readl(base + i + 4),
+				    readl(base + i + 8), readl(base + i + 12),
+				    readl(base + i + 16), readl(base + i + 20),
+				    readl(base + i + 24), readl(base + i + 28));
+		}
+		netdev_info(dev, "Dumping tx ring\n");
+		for (i = 0; i < np->tx_ring_size; i += 4) {
+			if (!nv_optimized(np)) {
+				netdev_info(dev,
+					    "%03x: %08x %08x // %08x %08x "
+					    "// %08x %08x // %08x %08x\n",
+					    i,
+					    le32_to_cpu(np->tx_ring.orig[i].buf),
+					    le32_to_cpu(np->tx_ring.orig[i].flaglen),
+					    le32_to_cpu(np->tx_ring.orig[i+1].buf),
+					    le32_to_cpu(np->tx_ring.orig[i+1].flaglen),
+					    le32_to_cpu(np->tx_ring.orig[i+2].buf),
+					    le32_to_cpu(np->tx_ring.orig[i+2].flaglen),
+					    le32_to_cpu(np->tx_ring.orig[i+3].buf),
+					    le32_to_cpu(np->tx_ring.orig[i+3].flaglen));
+			} else {
+				netdev_info(dev,
+					    "%03x: %08x %08x %08x "
+					    "// %08x %08x %08x "
+					    "// %08x %08x %08x "
+					    "// %08x %08x %08x\n",
+					    i,
+					    le32_to_cpu(np->tx_ring.ex[i].bufhigh),
+					    le32_to_cpu(np->tx_ring.ex[i].buflow),
+					    le32_to_cpu(np->tx_ring.ex[i].flaglen),
+					    le32_to_cpu(np->tx_ring.ex[i+1].bufhigh),
+					    le32_to_cpu(np->tx_ring.ex[i+1].buflow),
+					    le32_to_cpu(np->tx_ring.ex[i+1].flaglen),
+					    le32_to_cpu(np->tx_ring.ex[i+2].bufhigh),
+					    le32_to_cpu(np->tx_ring.ex[i+2].buflow),
+					    le32_to_cpu(np->tx_ring.ex[i+2].flaglen),
+					    le32_to_cpu(np->tx_ring.ex[i+3].bufhigh),
+					    le32_to_cpu(np->tx_ring.ex[i+3].buflow),
+					    le32_to_cpu(np->tx_ring.ex[i+3].flaglen));
+			}
 		}
 	}
 
@@ -2633,8 +2767,11 @@ static int nv_rx_process(struct net_device *dev, int limit)
 					}
 					/* the rest are hard errors */
 					else {
-						if (flags & NV_RX_MISSEDFRAME)
-							dev->stats.rx_missed_errors++;
+						if (flags & NV_RX_MISSEDFRAME) {
+							u64_stats_update_begin(&np->swstats_rx_syncp);
+							np->stat_rx_missed_errors++;
+							u64_stats_update_end(&np->swstats_rx_syncp);
+						}
 						dev_kfree_skb(skb);
 						goto next_pkt;
 					}
@@ -2677,7 +2814,10 @@ static int nv_rx_process(struct net_device *dev, int limit)
 		skb_put(skb, len);
 		skb->protocol = eth_type_trans(skb, dev);
 		napi_gro_receive(&np->napi, skb);
-		dev->stats.rx_packets++;
+		u64_stats_update_begin(&np->swstats_rx_syncp);
+		np->stat_rx_packets++;
+		np->stat_rx_bytes += len;
+		u64_stats_update_end(&np->swstats_rx_syncp);
 next_pkt:
 		if (unlikely(np->get_rx.orig++ == np->last_rx.orig))
 			np->get_rx.orig = np->first_rx.orig;
@@ -2760,7 +2900,10 @@ static int nv_rx_process_optimized(struct net_device *dev, int limit)
 				__vlan_hwaccel_put_tag(skb, vid);
 			}
 			napi_gro_receive(&np->napi, skb);
-			dev->stats.rx_packets++;
+			u64_stats_update_begin(&np->swstats_rx_syncp);
+			np->stat_rx_packets++;
+			np->stat_rx_bytes += len;
+			u64_stats_update_end(&np->swstats_rx_syncp);
 		} else {
 			dev_kfree_skb(skb);
 		}
@@ -3003,6 +3146,73 @@ static void nv_update_pause(struct net_device *dev, u32 pause_flags)
 	}
 }
 
+static void nv_force_linkspeed(struct net_device *dev, int speed, int duplex)
+{
+	struct fe_priv *np = netdev_priv(dev);
+	u8 __iomem *base = get_hwbase(dev);
+	u32 phyreg, txreg;
+	int mii_status;
+
+	np->linkspeed = NVREG_LINKSPEED_FORCE|speed;
+	np->duplex = duplex;
+
+	/* see if gigabit phy */
+	mii_status = mii_rw(dev, np->phyaddr, MII_BMSR, MII_READ);
+	if (mii_status & PHY_GIGABIT) {
+		np->gigabit = PHY_GIGABIT;
+		phyreg = readl(base + NvRegSlotTime);
+		phyreg &= ~(0x3FF00);
+		if ((np->linkspeed & 0xFFF) == NVREG_LINKSPEED_10)
+			phyreg |= NVREG_SLOTTIME_10_100_FULL;
+		else if ((np->linkspeed & 0xFFF) == NVREG_LINKSPEED_100)
+			phyreg |= NVREG_SLOTTIME_10_100_FULL;
+		else if ((np->linkspeed & 0xFFF) == NVREG_LINKSPEED_1000)
+			phyreg |= NVREG_SLOTTIME_1000_FULL;
+		writel(phyreg, base + NvRegSlotTime);
+	}
+
+	phyreg = readl(base + NvRegPhyInterface);
+	phyreg &= ~(PHY_HALF|PHY_100|PHY_1000);
+	if (np->duplex == 0)
+		phyreg |= PHY_HALF;
+	if ((np->linkspeed & NVREG_LINKSPEED_MASK) == NVREG_LINKSPEED_100)
+		phyreg |= PHY_100;
+	else if ((np->linkspeed & NVREG_LINKSPEED_MASK) ==
+							NVREG_LINKSPEED_1000)
+		phyreg |= PHY_1000;
+	writel(phyreg, base + NvRegPhyInterface);
+
+	if (phyreg & PHY_RGMII) {
+		if ((np->linkspeed & NVREG_LINKSPEED_MASK) ==
+							NVREG_LINKSPEED_1000)
+			txreg = NVREG_TX_DEFERRAL_RGMII_1000;
+		else
+			txreg = NVREG_TX_DEFERRAL_RGMII_10_100;
+	} else {
+		txreg = NVREG_TX_DEFERRAL_DEFAULT;
+	}
+	writel(txreg, base + NvRegTxDeferral);
+
+	if (np->desc_ver == DESC_VER_1) {
+		txreg = NVREG_TX_WM_DESC1_DEFAULT;
+	} else {
+		if ((np->linkspeed & NVREG_LINKSPEED_MASK) ==
+					 NVREG_LINKSPEED_1000)
+			txreg = NVREG_TX_WM_DESC2_3_1000;
+		else
+			txreg = NVREG_TX_WM_DESC2_3_DEFAULT;
+	}
+	writel(txreg, base + NvRegTxWatermark);
+
+	writel(NVREG_MISC1_FORCE | (np->duplex ? 0 : NVREG_MISC1_HD),
+			base + NvRegMisc1);
+	pci_push(base);
+	writel(np->linkspeed, base + NvRegLinkSpeed);
+	pci_push(base);
+
+	return;
+}
+
 /**
  * nv_update_linkspeed: Setup the MAC according to the link partner
  * @dev: Network device to be configured
@@ -3024,11 +3234,25 @@ static int nv_update_linkspeed(struct net_device *dev)
 	int newls = np->linkspeed;
 	int newdup = np->duplex;
 	int mii_status;
+	u32 bmcr;
 	int retval = 0;
 	u32 control_1000, status_1000, phyreg, pause_flags, txreg;
 	u32 txrxFlags = 0;
 	u32 phy_exp;
 
+	/* If device loopback is enabled, set carrier on and enable max link
+	 * speed.
+	 */
+	bmcr = mii_rw(dev, np->phyaddr, MII_BMCR, MII_READ);
+	if (bmcr & BMCR_LOOPBACK) {
+		if (netif_running(dev)) {
+			nv_force_linkspeed(dev, NVREG_LINKSPEED_1000, 1);
+			if (!netif_carrier_ok(dev))
+				netif_carrier_on(dev);
+		}
+		return 1;
+	}
+
 	/* BMSR_LSTATUS is latched, read it twice:
 	 * we want the current value.
 	 */
@@ -3711,6 +3935,7 @@ static int nv_request_irq(struct net_device *dev, int intr_test)
 				writel(0, base + NvRegMSIXMap0);
 				writel(0, base + NvRegMSIXMap1);
 			}
+			netdev_info(dev, "MSI-X enabled\n");
 		}
 	}
 	if (ret != 0 && np->msi_flags & NV_MSI_CAPABLE) {
@@ -3732,6 +3957,7 @@ static int nv_request_irq(struct net_device *dev, int intr_test)
 			writel(0, base + NvRegMSIMap1);
 			/* enable msi vector 0 */
 			writel(NVREG_MSI_VECTOR_0_ENABLED, base + NvRegMSIIrqMask);
+			netdev_info(dev, "MSI enabled\n");
 		}
 	}
 	if (ret != 0) {
@@ -3886,11 +4112,18 @@ static void nv_poll_controller(struct net_device *dev)
 #endif
 
 static void nv_do_stats_poll(unsigned long data)
+	__acquires(&netdev_priv(dev)->hwstats_lock)
+	__releases(&netdev_priv(dev)->hwstats_lock)
 {
 	struct net_device *dev = (struct net_device *) data;
 	struct fe_priv *np = netdev_priv(dev);
 
-	nv_get_hw_stats(dev);
+	/* If lock is currently taken, the stats are being refreshed
+	 * and hence fresh enough */
+	if (spin_trylock(&np->hwstats_lock)) {
+		nv_update_stats(dev);
+		spin_unlock(&np->hwstats_lock);
+	}
 
 	if (!np->in_shutdown)
 		mod_timer(&np->stats_poll,
@@ -3900,9 +4133,9 @@ static void nv_do_stats_poll(unsigned long data)
 static void nv_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
 	struct fe_priv *np = netdev_priv(dev);
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, FORCEDETH_VERSION);
-	strcpy(info->bus_info, pci_name(np->pci_dev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, FORCEDETH_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
 }
 
 static void nv_get_wol(struct net_device *dev, struct ethtool_wolinfo *wolinfo)
@@ -4455,7 +4688,63 @@ static int nv_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam*
 	return 0;
 }
 
-static u32 nv_fix_features(struct net_device *dev, u32 features)
+static int nv_set_loopback(struct net_device *dev, netdev_features_t features)
+{
+	struct fe_priv *np = netdev_priv(dev);
+	unsigned long flags;
+	u32 miicontrol;
+	int err, retval = 0;
+
+	spin_lock_irqsave(&np->lock, flags);
+	miicontrol = mii_rw(dev, np->phyaddr, MII_BMCR, MII_READ);
+	if (features & NETIF_F_LOOPBACK) {
+		if (miicontrol & BMCR_LOOPBACK) {
+			spin_unlock_irqrestore(&np->lock, flags);
+			netdev_info(dev, "Loopback already enabled\n");
+			return 0;
+		}
+		nv_disable_irq(dev);
+		/* Turn on loopback mode */
+		miicontrol |= BMCR_LOOPBACK | BMCR_FULLDPLX | BMCR_SPEED1000;
+		err = mii_rw(dev, np->phyaddr, MII_BMCR, miicontrol);
+		if (err) {
+			retval = PHY_ERROR;
+			spin_unlock_irqrestore(&np->lock, flags);
+			phy_init(dev);
+		} else {
+			if (netif_running(dev)) {
+				/* Force 1000 Mbps full-duplex */
+				nv_force_linkspeed(dev, NVREG_LINKSPEED_1000,
+									 1);
+				/* Force link up */
+				netif_carrier_on(dev);
+			}
+			spin_unlock_irqrestore(&np->lock, flags);
+			netdev_info(dev,
+				"Internal PHY loopback mode enabled.\n");
+		}
+	} else {
+		if (!(miicontrol & BMCR_LOOPBACK)) {
+			spin_unlock_irqrestore(&np->lock, flags);
+			netdev_info(dev, "Loopback already disabled\n");
+			return 0;
+		}
+		nv_disable_irq(dev);
+		/* Turn off loopback */
+		spin_unlock_irqrestore(&np->lock, flags);
+		netdev_info(dev, "Internal PHY loopback mode disabled.\n");
+		phy_init(dev);
+	}
+	msleep(500);
+	spin_lock_irqsave(&np->lock, flags);
+	nv_enable_irq(dev);
+	spin_unlock_irqrestore(&np->lock, flags);
+
+	return retval;
+}
+
+static netdev_features_t nv_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	/* vlan is dependent on rx checksum offload */
 	if (features & (NETIF_F_HW_VLAN_TX|NETIF_F_HW_VLAN_RX))
@@ -4464,7 +4753,7 @@ static u32 nv_fix_features(struct net_device *dev, u32 features)
 	return features;
 }
 
-static void nv_vlan_mode(struct net_device *dev, u32 features)
+static void nv_vlan_mode(struct net_device *dev, netdev_features_t features)
 {
 	struct fe_priv *np = get_nvpriv(dev);
 
@@ -4485,11 +4774,18 @@ static void nv_vlan_mode(struct net_device *dev, u32 features)
 	spin_unlock_irq(&np->lock);
 }
 
-static int nv_set_features(struct net_device *dev, u32 features)
+static int nv_set_features(struct net_device *dev, netdev_features_t features)
 {
 	struct fe_priv *np = netdev_priv(dev);
 	u8 __iomem *base = get_hwbase(dev);
-	u32 changed = dev->features ^ features;
+	netdev_features_t changed = dev->features ^ features;
+	int retval;
+
+	if ((changed & NETIF_F_LOOPBACK) && netif_running(dev)) {
+		retval = nv_set_loopback(dev, features);
+		if (retval != 0)
+			return retval;
+	}
 
 	if (changed & NETIF_F_RXCSUM) {
 		spin_lock_irq(&np->lock);
@@ -4535,14 +4831,18 @@ static int nv_get_sset_count(struct net_device *dev, int sset)
 	}
 }
 
-static void nv_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *estats, u64 *buffer)
+static void nv_get_ethtool_stats(struct net_device *dev,
+				 struct ethtool_stats *estats, u64 *buffer)
+	__acquires(&netdev_priv(dev)->hwstats_lock)
+	__releases(&netdev_priv(dev)->hwstats_lock)
 {
 	struct fe_priv *np = netdev_priv(dev);
 
-	/* update stats */
-	nv_get_hw_stats(dev);
-
-	memcpy(buffer, &np->estats, nv_get_sset_count(dev, ETH_SS_STATS)*sizeof(u64));
+	spin_lock_bh(&np->hwstats_lock);
+	nv_update_stats(dev);
+	memcpy(buffer, &np->estats,
+	       nv_get_sset_count(dev, ETH_SS_STATS)*sizeof(u64));
+	spin_unlock_bh(&np->hwstats_lock);
 }
 
 static int nv_link_test(struct net_device *dev)
@@ -5124,6 +5424,12 @@ static int nv_open(struct net_device *dev)
 
 	spin_unlock_irq(&np->lock);
 
+	/* If the loopback feature was set while the device was down, make sure
+	 * that it's set correctly now.
+	 */
+	if (dev->features & NETIF_F_LOOPBACK)
+		nv_set_loopback(dev, dev->features);
+
 	return 0;
 out_drain:
 	nv_drain_rxtx(dev);
@@ -5180,7 +5486,7 @@ static int nv_close(struct net_device *dev)
 static const struct net_device_ops nv_netdev_ops = {
 	.ndo_open		= nv_open,
 	.ndo_stop		= nv_close,
-	.ndo_get_stats		= nv_get_stats,
+	.ndo_get_stats64	= nv_get_stats64,
 	.ndo_start_xmit		= nv_start_xmit,
 	.ndo_tx_timeout		= nv_tx_timeout,
 	.ndo_change_mtu		= nv_change_mtu,
@@ -5197,7 +5503,7 @@ static const struct net_device_ops nv_netdev_ops = {
 static const struct net_device_ops nv_netdev_ops_optimized = {
 	.ndo_open		= nv_open,
 	.ndo_stop		= nv_close,
-	.ndo_get_stats		= nv_get_stats,
+	.ndo_get_stats64	= nv_get_stats64,
 	.ndo_start_xmit		= nv_start_xmit_optimized,
 	.ndo_tx_timeout		= nv_tx_timeout,
 	.ndo_change_mtu		= nv_change_mtu,
@@ -5236,6 +5542,7 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_i
 	np->dev = dev;
 	np->pci_dev = pci_dev;
 	spin_lock_init(&np->lock);
+	spin_lock_init(&np->hwstats_lock);
 	SET_NETDEV_DEV(dev, &pci_dev->dev);
 
 	init_timer(&np->oom_kick);
@@ -5244,7 +5551,7 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_i
 	init_timer(&np->nic_poll);
 	np->nic_poll.data = (unsigned long) dev;
 	np->nic_poll.function = nv_do_nic_poll;	/* timer handler */
-	init_timer(&np->stats_poll);
+	init_timer_deferrable(&np->stats_poll);
 	np->stats_poll.data = (unsigned long) dev;
 	np->stats_poll.function = nv_do_stats_poll;	/* timer handler */
 
@@ -5328,6 +5635,9 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_i
 
 	dev->features |= dev->hw_features;
 
+	/* Add loopback capability to the device. */
+	dev->hw_features |= NETIF_F_LOOPBACK;
+
 	np->pause_flags = NV_PAUSEFRAME_RX_CAPABLE | NV_PAUSEFRAME_RX_REQ | NV_PAUSEFRAME_AUTONEG;
 	if ((id->driver_data & DEV_HAS_PAUSEFRAME_TX_V1) ||
 	    (id->driver_data & DEV_HAS_PAUSEFRAME_TX_V2) ||
@@ -5603,12 +5913,14 @@ static int __devinit nv_probe(struct pci_dev *pci_dev, const struct pci_device_i
 	dev_info(&pci_dev->dev, "ifname %s, PHY OUI 0x%x @ %d, addr %pM\n",
 		 dev->name, np->phy_oui, np->phyaddr, dev->dev_addr);
 
-	dev_info(&pci_dev->dev, "%s%s%s%s%s%s%s%s%s%sdesc-v%u\n",
+	dev_info(&pci_dev->dev, "%s%s%s%s%s%s%s%s%s%s%sdesc-v%u\n",
 		 dev->features & NETIF_F_HIGHDMA ? "highdma " : "",
 		 dev->features & (NETIF_F_IP_CSUM | NETIF_F_SG) ?
 			"csum " : "",
 		 dev->features & (NETIF_F_HW_VLAN_RX | NETIF_F_HW_VLAN_TX) ?
 			"vlan " : "",
+		 dev->features & (NETIF_F_LOOPBACK) ?
+			"loopback " : "",
 		 id->driver_data & DEV_HAS_POWER_CNTRL ? "pwrctl " : "",
 		 id->driver_data & DEV_HAS_MGMT_UNIT ? "mgmt " : "",
 		 id->driver_data & DEV_NEED_TIMERIRQ ? "timirq " : "",
@@ -5982,6 +6294,9 @@ module_param(phy_cross, int, 0);
 MODULE_PARM_DESC(phy_cross, "Phy crossover detection for Realtek 8201 phy is enabled by setting to 1 and disabled by setting to 0.");
 module_param(phy_power_down, int, 0);
 MODULE_PARM_DESC(phy_power_down, "Power down phy and disable link when interface is down (1), or leave phy powered up (0).");
+module_param(debug_tx_timeout, bool, 0);
+MODULE_PARM_DESC(debug_tx_timeout,
+		 "Dump tx related registers and ring when tx_timeout happens");
 
 MODULE_AUTHOR("Manfred Spraul <manfred@colorfullife.com>");
 MODULE_DESCRIPTION("Reverse Engineered nForce ethernet driver");
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
index 8c80271..ac4e72d 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
@@ -161,10 +161,10 @@ static void pch_gbe_get_drvinfo(struct net_device *netdev,
 {
 	struct pch_gbe_adapter *adapter = netdev_priv(netdev);
 
-	strcpy(drvinfo->driver, KBUILD_MODNAME);
-	strcpy(drvinfo->version, pch_driver_version);
-	strcpy(drvinfo->fw_version, "N/A");
-	strcpy(drvinfo->bus_info, pci_name(adapter->pdev));
+	strlcpy(drvinfo->driver, KBUILD_MODNAME, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, pch_driver_version, sizeof(drvinfo->version));
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
 	drvinfo->regdump_len = pch_gbe_get_regs_len(netdev);
 }
 
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 48406ca..964e9c0 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -2109,10 +2109,11 @@ static int pch_gbe_change_mtu(struct net_device *netdev, int new_mtu)
  * Returns
  *	0:		HW state updated successfully
  */
-static int pch_gbe_set_features(struct net_device *netdev, u32 features)
+static int pch_gbe_set_features(struct net_device *netdev,
+	netdev_features_t features)
 {
 	struct pch_gbe_adapter *adapter = netdev_priv(netdev);
-	u32 changed = features ^ netdev->features;
+	netdev_features_t changed = features ^ netdev->features;
 
 	if (!(changed & NETIF_F_RXCSUM))
 		return 0;
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c
index 9c075ea..9cb5f91 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_param.c
@@ -18,8 +18,8 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307, USA.
  */
 
-#include <linux/module.h>	/* for __MODULE_STRING */
 #include "pch_gbe.h"
+#include <linux/module.h>	/* for __MODULE_STRING */
 
 #define OPTION_UNSET   -1
 #define OPTION_DISABLED 0
diff --git a/drivers/net/ethernet/pasemi/Makefile b/drivers/net/ethernet/pasemi/Makefile
index 05db543..90497ff 100644
--- a/drivers/net/ethernet/pasemi/Makefile
+++ b/drivers/net/ethernet/pasemi/Makefile
@@ -2,4 +2,5 @@
 # Makefile for the A Semi network device drivers.
 #
 
-obj-$(CONFIG_PASEMI_MAC) += pasemi_mac.o pasemi_mac_ethtool.o
+obj-$(CONFIG_PASEMI_MAC) += pasemi_mac_driver.o
+pasemi_mac_driver-objs := pasemi_mac.o pasemi_mac_ethtool.o
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
index e09ea83..8a37198 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
@@ -83,14 +83,18 @@ netxen_nic_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo)
 	u32 fw_minor = 0;
 	u32 fw_build = 0;
 
-	strncpy(drvinfo->driver, netxen_nic_driver_name, 32);
-	strncpy(drvinfo->version, NETXEN_NIC_LINUX_VERSIONID, 32);
+	strlcpy(drvinfo->driver, netxen_nic_driver_name,
+		sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, NETXEN_NIC_LINUX_VERSIONID,
+		sizeof(drvinfo->version));
 	fw_major = NXRD32(adapter, NETXEN_FW_VERSION_MAJOR);
 	fw_minor = NXRD32(adapter, NETXEN_FW_VERSION_MINOR);
 	fw_build = NXRD32(adapter, NETXEN_FW_VERSION_SUB);
-	sprintf(drvinfo->fw_version, "%d.%d.%d", fw_major, fw_minor, fw_build);
+	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+		"%d.%d.%d", fw_major, fw_minor, fw_build);
 
-	strncpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
 	drvinfo->regdump_len = NETXEN_NIC_REGS_LEN;
 	drvinfo->eedump_len = netxen_nic_get_eeprom_len(dev);
 }
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index 8cf3173..7dd9a4b 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -544,7 +544,8 @@ static void netxen_set_multicast_list(struct net_device *dev)
 	adapter->set_multi(dev);
 }
 
-static u32 netxen_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t netxen_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	if (!(features & NETIF_F_RXCSUM)) {
 		netdev_info(dev, "disabling LRO as RXCSUM is off\n");
@@ -555,7 +556,8 @@ static u32 netxen_fix_features(struct net_device *dev, u32 features)
 	return features;
 }
 
-static int netxen_set_features(struct net_device *dev, u32 features)
+static int netxen_set_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct netxen_adapter *adapter = netdev_priv(dev);
 	int hw_lro;
diff --git a/drivers/net/ethernet/qlogic/qla3xxx.c b/drivers/net/ethernet/qlogic/qla3xxx.c
index a4bdff4..7931531 100644
--- a/drivers/net/ethernet/qlogic/qla3xxx.c
+++ b/drivers/net/ethernet/qlogic/qla3xxx.c
@@ -1735,10 +1735,11 @@ static void ql_get_drvinfo(struct net_device *ndev,
 			   struct ethtool_drvinfo *drvinfo)
 {
 	struct ql3_adapter *qdev = netdev_priv(ndev);
-	strncpy(drvinfo->driver, ql3xxx_driver_name, 32);
-	strncpy(drvinfo->version, ql3xxx_driver_version, 32);
-	strncpy(drvinfo->fw_version, "N/A", 32);
-	strncpy(drvinfo->bus_info, pci_name(qdev->pdev), 32);
+	strlcpy(drvinfo->driver, ql3xxx_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, ql3xxx_driver_version,
+		sizeof(drvinfo->version));
+	strlcpy(drvinfo->bus_info, pci_name(qdev->pdev),
+		sizeof(drvinfo->bus_info));
 	drvinfo->regdump_len = 0;
 	drvinfo->eedump_len = 0;
 }
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
index 7ed53db..60976fc 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -1466,8 +1466,9 @@ void qlcnic_advert_link_change(struct qlcnic_adapter *adapter, int linkup);
 
 int qlcnic_fw_cmd_set_mtu(struct qlcnic_adapter *adapter, int mtu);
 int qlcnic_change_mtu(struct net_device *netdev, int new_mtu);
-u32 qlcnic_fix_features(struct net_device *netdev, u32 features);
-int qlcnic_set_features(struct net_device *netdev, u32 features);
+netdev_features_t qlcnic_fix_features(struct net_device *netdev,
+	netdev_features_t features);
+int qlcnic_set_features(struct net_device *netdev, netdev_features_t features);
 int qlcnic_config_hw_lro(struct qlcnic_adapter *adapter, int enable);
 int qlcnic_config_bridged_mode(struct qlcnic_adapter *adapter, u32 enable);
 int qlcnic_send_lro_cleanup(struct qlcnic_adapter *adapter);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 8aa1c6e..cc228cf 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -140,11 +140,14 @@ qlcnic_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo)
 	fw_major = QLCRD32(adapter, QLCNIC_FW_VERSION_MAJOR);
 	fw_minor = QLCRD32(adapter, QLCNIC_FW_VERSION_MINOR);
 	fw_build = QLCRD32(adapter, QLCNIC_FW_VERSION_SUB);
-	sprintf(drvinfo->fw_version, "%d.%d.%d", fw_major, fw_minor, fw_build);
-
-	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), 32);
-	strlcpy(drvinfo->driver, qlcnic_driver_name, 32);
-	strlcpy(drvinfo->version, QLCNIC_LINUX_VERSIONID, 32);
+	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+		"%d.%d.%d", fw_major, fw_minor, fw_build);
+
+	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
+		sizeof(drvinfo->bus_info));
+	strlcpy(drvinfo->driver, qlcnic_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, QLCNIC_LINUX_VERSIONID,
+		sizeof(drvinfo->version));
 }
 
 static int
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
index bcb81e4..b528e52 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
@@ -817,12 +817,13 @@ int qlcnic_change_mtu(struct net_device *netdev, int mtu)
 }
 
 
-u32 qlcnic_fix_features(struct net_device *netdev, u32 features)
+netdev_features_t qlcnic_fix_features(struct net_device *netdev,
+	netdev_features_t features)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 
 	if ((adapter->flags & QLCNIC_ESWITCH_ENABLED)) {
-		u32 changed = features ^ netdev->features;
+		netdev_features_t changed = features ^ netdev->features;
 		features ^= changed & (NETIF_F_ALL_CSUM | NETIF_F_RXCSUM);
 	}
 
@@ -833,10 +834,10 @@ u32 qlcnic_fix_features(struct net_device *netdev, u32 features)
 }
 
 
-int qlcnic_set_features(struct net_device *netdev, u32 features)
+int qlcnic_set_features(struct net_device *netdev, netdev_features_t features)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
-	u32 changed = netdev->features ^ features;
+	netdev_features_t changed = netdev->features ^ features;
 	int hw_lro = (features & NETIF_F_LRO) ? QLCNIC_LRO_ENABLED : 0;
 
 	if (!(changed & NETIF_F_LRO))
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
index 0bd1638..69b8e4e 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -97,8 +97,8 @@ static int qlcnicvf_config_bridged_mode(struct qlcnic_adapter *, u32);
 static int qlcnicvf_start_firmware(struct qlcnic_adapter *);
 static void qlcnic_set_netdev_features(struct qlcnic_adapter *,
 				struct qlcnic_esw_func_cfg *);
-static void qlcnic_vlan_rx_add(struct net_device *, u16);
-static void qlcnic_vlan_rx_del(struct net_device *, u16);
+static int qlcnic_vlan_rx_add(struct net_device *, u16);
+static int qlcnic_vlan_rx_del(struct net_device *, u16);
 
 /*  PCI Device ID Table  */
 #define ENTRY(device) \
@@ -735,20 +735,22 @@ qlcnic_set_vlan_config(struct qlcnic_adapter *adapter,
 		adapter->pvid = 0;
 }
 
-static void
+static int
 qlcnic_vlan_rx_add(struct net_device *netdev, u16 vid)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 	set_bit(vid, adapter->vlans);
+	return 0;
 }
 
-static void
+static int
 qlcnic_vlan_rx_del(struct net_device *netdev, u16 vid)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
 
 	qlcnic_restore_indev_addr(netdev, NETDEV_DOWN);
 	clear_bit(vid, adapter->vlans);
+	return 0;
 }
 
 static void
@@ -792,7 +794,7 @@ qlcnic_set_netdev_features(struct qlcnic_adapter *adapter,
 		struct qlcnic_esw_func_cfg *esw_cfg)
 {
 	struct net_device *netdev = adapter->netdev;
-	unsigned long features, vlan_features;
+	netdev_features_t features, vlan_features;
 
 	features = (NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_RXCSUM |
 			NETIF_F_IPV6_CSUM | NETIF_F_GRO);
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h
index 8731f79..b8478aa 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge.h
+++ b/drivers/net/ethernet/qlogic/qlge/qlge.h
@@ -58,10 +58,8 @@
 
 
 #define TX_DESC_PER_IOCB 8
-/* The maximum number of frags we handle is based
- * on PAGE_SIZE...
- */
-#if (PAGE_SHIFT == 12) || (PAGE_SHIFT == 13)	/* 4k & 8k pages */
+
+#if ((MAX_SKB_FRAGS - TX_DESC_PER_IOCB) + 2) > 0
 #define TX_DESC_PER_OAL ((MAX_SKB_FRAGS - TX_DESC_PER_IOCB) + 2)
 #else /* all other page sizes */
 #define TX_DESC_PER_OAL 0
@@ -1353,7 +1351,7 @@ struct tx_ring_desc {
 	struct ob_mac_iocb_req *queue_entry;
 	u32 index;
 	struct oal oal;
-	struct map_list map[MAX_SKB_FRAGS + 1];
+	struct map_list map[MAX_SKB_FRAGS + 2];
 	int map_cnt;
 	struct tx_ring_desc *next;
 };
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c
index 9b67bfe..8e2c2a7 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c
@@ -366,13 +366,16 @@ static void ql_get_drvinfo(struct net_device *ndev,
 			   struct ethtool_drvinfo *drvinfo)
 {
 	struct ql_adapter *qdev = netdev_priv(ndev);
-	strncpy(drvinfo->driver, qlge_driver_name, 32);
-	strncpy(drvinfo->version, qlge_driver_version, 32);
-	snprintf(drvinfo->fw_version, 32, "v%d.%d.%d",
+	strlcpy(drvinfo->driver, qlge_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->version, qlge_driver_version,
+		sizeof(drvinfo->version));
+	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
+		 "v%d.%d.%d",
 		 (qdev->fw_rev_id & 0x00ff0000) >> 16,
 		 (qdev->fw_rev_id & 0x0000ff00) >> 8,
 		 (qdev->fw_rev_id & 0x000000ff));
-	strncpy(drvinfo->bus_info, pci_name(qdev->pdev), 32);
+	strlcpy(drvinfo->bus_info, pci_name(qdev->pdev),
+		sizeof(drvinfo->bus_info));
 	drvinfo->n_stats = 0;
 	drvinfo->testinfo_len = 0;
 	if (!test_bit(QL_FRC_COREDUMP, &qdev->flags))
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index c92afcd..b548987 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -2307,7 +2307,7 @@ static int ql_napi_poll_msix(struct napi_struct *napi, int budget)
 	return work_done;
 }
 
-static void qlge_vlan_mode(struct net_device *ndev, u32 features)
+static void qlge_vlan_mode(struct net_device *ndev, netdev_features_t features)
 {
 	struct ql_adapter *qdev = netdev_priv(ndev);
 
@@ -2323,7 +2323,8 @@ static void qlge_vlan_mode(struct net_device *ndev, u32 features)
 	}
 }
 
-static u32 qlge_fix_features(struct net_device *ndev, u32 features)
+static netdev_features_t qlge_fix_features(struct net_device *ndev,
+	netdev_features_t features)
 {
 	/*
 	 * Since there is no support for separate rx/tx vlan accel
@@ -2337,9 +2338,10 @@ static u32 qlge_fix_features(struct net_device *ndev, u32 features)
 	return features;
 }
 
-static int qlge_set_features(struct net_device *ndev, u32 features)
+static int qlge_set_features(struct net_device *ndev,
+	netdev_features_t features)
 {
-	u32 changed = ndev->features ^ features;
+	netdev_features_t changed = ndev->features ^ features;
 
 	if (changed & NETIF_F_HW_VLAN_RX)
 		qlge_vlan_mode(ndev, features);
@@ -2347,56 +2349,66 @@ static int qlge_set_features(struct net_device *ndev, u32 features)
 	return 0;
 }
 
-static void __qlge_vlan_rx_add_vid(struct ql_adapter *qdev, u16 vid)
+static int __qlge_vlan_rx_add_vid(struct ql_adapter *qdev, u16 vid)
 {
 	u32 enable_bit = MAC_ADDR_E;
+	int err;
 
-	if (ql_set_mac_addr_reg
-	    (qdev, (u8 *) &enable_bit, MAC_ADDR_TYPE_VLAN, vid)) {
+	err = ql_set_mac_addr_reg(qdev, (u8 *) &enable_bit,
+				  MAC_ADDR_TYPE_VLAN, vid);
+	if (err)
 		netif_err(qdev, ifup, qdev->ndev,
 			  "Failed to init vlan address.\n");
-	}
+	return err;
 }
 
-static void qlge_vlan_rx_add_vid(struct net_device *ndev, u16 vid)
+static int qlge_vlan_rx_add_vid(struct net_device *ndev, u16 vid)
 {
 	struct ql_adapter *qdev = netdev_priv(ndev);
 	int status;
+	int err;
 
 	status = ql_sem_spinlock(qdev, SEM_MAC_ADDR_MASK);
 	if (status)
-		return;
+		return status;
 
-	__qlge_vlan_rx_add_vid(qdev, vid);
+	err = __qlge_vlan_rx_add_vid(qdev, vid);
 	set_bit(vid, qdev->active_vlans);
 
 	ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK);
+
+	return err;
 }
 
-static void __qlge_vlan_rx_kill_vid(struct ql_adapter *qdev, u16 vid)
+static int __qlge_vlan_rx_kill_vid(struct ql_adapter *qdev, u16 vid)
 {
 	u32 enable_bit = 0;
+	int err;
 
-	if (ql_set_mac_addr_reg
-	    (qdev, (u8 *) &enable_bit, MAC_ADDR_TYPE_VLAN, vid)) {
+	err = ql_set_mac_addr_reg(qdev, (u8 *) &enable_bit,
+				  MAC_ADDR_TYPE_VLAN, vid);
+	if (err)
 		netif_err(qdev, ifup, qdev->ndev,
 			  "Failed to clear vlan address.\n");
-	}
+	return err;
 }
 
-static void qlge_vlan_rx_kill_vid(struct net_device *ndev, u16 vid)
+static int qlge_vlan_rx_kill_vid(struct net_device *ndev, u16 vid)
 {
 	struct ql_adapter *qdev = netdev_priv(ndev);
 	int status;
+	int err;
 
 	status = ql_sem_spinlock(qdev, SEM_MAC_ADDR_MASK);
 	if (status)
-		return;
+		return status;
 
-	__qlge_vlan_rx_kill_vid(qdev, vid);
+	err = __qlge_vlan_rx_kill_vid(qdev, vid);
 	clear_bit(vid, qdev->active_vlans);
 
 	ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK);
+
+	return err;
 }
 
 static void qlge_restore_vlan(struct ql_adapter *qdev)
diff --git a/drivers/net/ethernet/rdc/r6040.c b/drivers/net/ethernet/rdc/r6040.c
index 1fc01ca..4bf68cf 100644
--- a/drivers/net/ethernet/rdc/r6040.c
+++ b/drivers/net/ethernet/rdc/r6040.c
@@ -940,7 +940,7 @@ static void r6040_multicast_list(struct net_device *dev)
 	iowrite16(lp->mcr0, ioaddr + MCR0);
 
 	/* Fill the MAC hash tables with their values */
-	if (lp->mcr0 && MCR0_HASH_EN) {
+	if (lp->mcr0 & MCR0_HASH_EN) {
 		iowrite16(hash_table[0], ioaddr + MAR0);
 		iowrite16(hash_table[1], ioaddr + MAR1);
 		iowrite16(hash_table[2], ioaddr + MAR2);
diff --git a/drivers/net/ethernet/realtek/8139cp.c b/drivers/net/ethernet/realtek/8139cp.c
index ee5da92..87cff10 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -1319,9 +1319,9 @@ static void cp_get_drvinfo (struct net_device *dev, struct ethtool_drvinfo *info
 {
 	struct cp_private *cp = netdev_priv(dev);
 
-	strcpy (info->driver, DRV_NAME);
-	strcpy (info->version, DRV_VERSION);
-	strcpy (info->bus_info, pci_name(cp->pdev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(cp->pdev), sizeof(info->bus_info));
 }
 
 static void cp_get_ringparam(struct net_device *dev,
@@ -1392,7 +1392,7 @@ static void cp_set_msglevel(struct net_device *dev, u32 value)
 	cp->msg_enable = value;
 }
 
-static int cp_set_features(struct net_device *dev, u32 features)
+static int cp_set_features(struct net_device *dev, netdev_features_t features)
 {
 	struct cp_private *cp = netdev_priv(dev);
 	unsigned long flags;
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index 4d6b254..d9c7227 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2330,9 +2330,9 @@ static int rtl8139_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 static void rtl8139_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
 	struct rtl8139_private *tp = netdev_priv(dev);
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->bus_info, pci_name(tp->pci_dev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info));
 	info->regdump_len = tp->regs_len;
 }
 
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 92b45f0..36b2a4b 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -69,9 +69,6 @@
    The RTL chips use a 64 element hash table based on the Ethernet CRC. */
 static const int multicast_filter_limit = 32;
 
-/* MAC address length */
-#define MAC_ADDR_LEN	6
-
 #define MAX_READ_REQUEST_SHIFT	12
 #define TX_DMA_BURST	6	/* Maximum PCI burst, '6' is 1024 */
 #define SafeMtu		0x1c20	/* ... actually life sucks beyond ~7k */
@@ -1183,11 +1180,13 @@ static u8 rtl8168d_efuse_read(void __iomem *ioaddr, int reg_addr)
 	return value;
 }
 
-static void rtl8169_irq_mask_and_ack(void __iomem *ioaddr)
+static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp)
 {
-	RTL_W16(IntrMask, 0x0000);
+	void __iomem *ioaddr = tp->mmio_addr;
 
-	RTL_W16(IntrStatus, 0xffff);
+	RTL_W16(IntrMask, 0x0000);
+	RTL_W16(IntrStatus, tp->intr_event);
+	RTL_R8(ChipCmd);
 }
 
 static unsigned int rtl8169_tbi_reset_pending(struct rtl8169_private *tp)
@@ -1292,7 +1291,7 @@ static void __rtl8169_check_link_status(struct net_device *dev,
 		netif_carrier_off(dev);
 		netif_info(tp, ifdown, dev, "link down\n");
 		if (pm)
-			pm_schedule_suspend(&tp->pci_dev->dev, 100);
+			pm_schedule_suspend(&tp->pci_dev->dev, 5000);
 	}
 	spin_unlock_irqrestore(&tp->lock, flags);
 }
@@ -1404,12 +1403,13 @@ static void rtl8169_get_drvinfo(struct net_device *dev,
 	struct rtl8169_private *tp = netdev_priv(dev);
 	struct rtl_fw *rtl_fw = tp->rtl_fw;
 
-	strcpy(info->driver, MODULENAME);
-	strcpy(info->version, RTL8169_VERSION);
-	strcpy(info->bus_info, pci_name(tp->pci_dev));
+	strlcpy(info->driver, MODULENAME, sizeof(info->driver));
+	strlcpy(info->version, RTL8169_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info));
 	BUILD_BUG_ON(sizeof(info->fw_version) < sizeof(rtl_fw->version));
-	strcpy(info->fw_version, IS_ERR_OR_NULL(rtl_fw) ? "N/A" :
-	       rtl_fw->version);
+	if (!IS_ERR_OR_NULL(rtl_fw))
+		strlcpy(info->fw_version, rtl_fw->version,
+			sizeof(info->fw_version));
 }
 
 static int rtl8169_get_regs_len(struct net_device *dev)
@@ -1553,7 +1553,8 @@ static int rtl8169_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 	return ret;
 }
 
-static u32 rtl8169_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t rtl8169_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 
@@ -1567,7 +1568,8 @@ static u32 rtl8169_fix_features(struct net_device *dev, u32 features)
 	return features;
 }
 
-static int rtl8169_set_features(struct net_device *dev, u32 features)
+static int rtl8169_set_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 	void __iomem *ioaddr = tp->mmio_addr;
@@ -3933,8 +3935,6 @@ static void rtl_hw_reset(struct rtl8169_private *tp)
 			break;
 		udelay(100);
 	}
-
-	rtl8169_init_ring_indexes(tp);
 }
 
 static int __devinit
@@ -4099,7 +4099,7 @@ rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	spin_lock_init(&tp->lock);
 
 	/* Get MAC address */
-	for (i = 0; i < MAC_ADDR_LEN; i++)
+	for (i = 0; i < ETH_ALEN; i++)
 		dev->dev_addr[i] = RTL_R8(MAC0 + i);
 	memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len);
 
@@ -4339,7 +4339,7 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp)
 	void __iomem *ioaddr = tp->mmio_addr;
 
 	/* Disable interrupts */
-	rtl8169_irq_mask_and_ack(ioaddr);
+	rtl8169_irq_mask_and_ack(tp);
 
 	rtl_rx_close(tp);
 
@@ -4885,8 +4885,7 @@ static void rtl_hw_start_8168(struct net_device *dev)
 	RTL_W16(IntrMitigate, 0x5151);
 
 	/* Work around for RxFIFO overflow. */
-	if (tp->mac_version == RTL_GIGA_MAC_VER_11 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_22) {
+	if (tp->mac_version == RTL_GIGA_MAC_VER_11) {
 		tp->intr_event |= RxFIFOOver | PCSTimeout;
 		tp->intr_event &= ~RxOverflow;
 	}
@@ -5076,6 +5075,11 @@ static void rtl_hw_start_8101(struct net_device *dev)
 	void __iomem *ioaddr = tp->mmio_addr;
 	struct pci_dev *pdev = tp->pci_dev;
 
+	if (tp->mac_version >= RTL_GIGA_MAC_VER_30) {
+		tp->intr_event &= ~RxFIFOOver;
+		tp->napi_event &= ~RxFIFOOver;
+	}
+
 	if (tp->mac_version == RTL_GIGA_MAC_VER_13 ||
 	    tp->mac_version == RTL_GIGA_MAC_VER_16) {
 		int cap = pci_pcie_cap(pdev);
@@ -5342,7 +5346,7 @@ static void rtl8169_wait_for_quiescence(struct net_device *dev)
 	/* Wait for any pending NAPI task to complete */
 	napi_disable(&tp->napi);
 
-	rtl8169_irq_mask_and_ack(ioaddr);
+	rtl8169_irq_mask_and_ack(tp);
 
 	tp->intr_mask = 0xffff;
 	RTL_W16(IntrMask, tp->intr_event);
@@ -5389,14 +5393,16 @@ static void rtl8169_reset_task(struct work_struct *work)
 	if (!netif_running(dev))
 		goto out_unlock;
 
+	rtl8169_hw_reset(tp);
+
 	rtl8169_wait_for_quiescence(dev);
 
 	for (i = 0; i < NUM_RX_DESC; i++)
 		rtl8169_mark_to_asic(tp->RxDescArray + i, rx_buf_sz);
 
 	rtl8169_tx_clear(tp);
+	rtl8169_init_ring_indexes(tp);
 
-	rtl8169_hw_reset(tp);
 	rtl_hw_start(dev);
 	netif_wake_queue(dev);
 	rtl8169_check_link_status(dev, tp, tp->mmio_addr);
@@ -5407,11 +5413,6 @@ out_unlock:
 
 static void rtl8169_tx_timeout(struct net_device *dev)
 {
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	rtl8169_hw_reset(tp);
-
-	/* Let's wait a bit while any (async) irq lands on */
 	rtl8169_schedule_work(dev, rtl8169_reset_task);
 }
 
@@ -5804,6 +5805,10 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 	 */
 	status = RTL_R16(IntrStatus);
 	while (status && status != 0xffff) {
+		status &= tp->intr_event;
+		if (!status)
+			break;
+
 		handled = 1;
 
 		/* Handle all of the error cases first. These will reset
@@ -5818,27 +5823,9 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 			switch (tp->mac_version) {
 			/* Work around for rx fifo overflow */
 			case RTL_GIGA_MAC_VER_11:
-			case RTL_GIGA_MAC_VER_22:
-			case RTL_GIGA_MAC_VER_26:
 				netif_stop_queue(dev);
 				rtl8169_tx_timeout(dev);
 				goto done;
-			/* Testers needed. */
-			case RTL_GIGA_MAC_VER_17:
-			case RTL_GIGA_MAC_VER_19:
-			case RTL_GIGA_MAC_VER_20:
-			case RTL_GIGA_MAC_VER_21:
-			case RTL_GIGA_MAC_VER_23:
-			case RTL_GIGA_MAC_VER_24:
-			case RTL_GIGA_MAC_VER_27:
-			case RTL_GIGA_MAC_VER_28:
-			case RTL_GIGA_MAC_VER_31:
-			/* Experimental science. Pktgen proof. */
-			case RTL_GIGA_MAC_VER_12:
-			case RTL_GIGA_MAC_VER_25:
-				if (status == RxFIFOOver)
-					goto done;
-				break;
 			default:
 				break;
 			}
diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 9b23074..ebfb682 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1957,18 +1957,7 @@ static struct platform_driver sh_eth_driver = {
 	},
 };
 
-static int __init sh_eth_init(void)
-{
-	return platform_driver_register(&sh_eth_driver);
-}
-
-static void __exit sh_eth_cleanup(void)
-{
-	platform_driver_unregister(&sh_eth_driver);
-}
-
-module_init(sh_eth_init);
-module_exit(sh_eth_cleanup);
+module_platform_driver(sh_eth_driver);
 
 MODULE_AUTHOR("Nobuhiro Iwamatsu, Yoshihiro Shimoda");
 MODULE_DESCRIPTION("Renesas SuperH Ethernet driver");
diff --git a/drivers/net/ethernet/seeq/sgiseeq.c b/drivers/net/ethernet/seeq/sgiseeq.c
index c3673f1..f955a19 100644
--- a/drivers/net/ethernet/seeq/sgiseeq.c
+++ b/drivers/net/ethernet/seeq/sgiseeq.c
@@ -834,23 +834,7 @@ static struct platform_driver sgiseeq_driver = {
 	}
 };
 
-static int __init sgiseeq_module_init(void)
-{
-	if (platform_driver_register(&sgiseeq_driver)) {
-		printk(KERN_ERR "Driver registration failed\n");
-		return -ENODEV;
-	}
-
-	return 0;
-}
-
-static void __exit sgiseeq_module_exit(void)
-{
-	platform_driver_unregister(&sgiseeq_driver);
-}
-
-module_init(sgiseeq_module_init);
-module_exit(sgiseeq_module_exit);
+module_platform_driver(sgiseeq_driver);
 
 MODULE_DESCRIPTION("SGI Seeq 8003 driver");
 MODULE_AUTHOR("Linux/MIPS Mailing List <linux-mips@linux-mips.org>");
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index d5731f1..e43702f 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1336,7 +1336,8 @@ static int efx_probe_nic(struct efx_nic *efx)
 	if (efx->n_channels > 1)
 		get_random_bytes(&efx->rx_hash_key, sizeof(efx->rx_hash_key));
 	for (i = 0; i < ARRAY_SIZE(efx->rx_indir_table); i++)
-		efx->rx_indir_table[i] = i % efx->n_rx_channels;
+		efx->rx_indir_table[i] =
+			ethtool_rxfh_indir_default(i, efx->n_rx_channels);
 
 	efx_set_channels(efx);
 	netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels);
@@ -1900,7 +1901,7 @@ static void efx_set_multicast_list(struct net_device *net_dev)
 	/* Otherwise efx_start_port() will do this */
 }
 
-static int efx_set_features(struct net_device *net_dev, u32 data)
+static int efx_set_features(struct net_device *net_dev, netdev_features_t data)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
 
@@ -2235,9 +2236,9 @@ static DEFINE_PCI_DEVICE_TABLE(efx_pci_table) = {
 	{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE,
 		    PCI_DEVICE_ID_SOLARFLARE_SFC4000B),
 	 .driver_data = (unsigned long) &falcon_b0_nic_type},
-	{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, BETHPAGE_A_P_DEVID),
+	{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x0803),	/* SFC9020 */
 	 .driver_data = (unsigned long) &siena_a0_nic_type},
-	{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, SIENA_A_P_DEVID),
+	{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x0813),	/* SFL9021 */
 	 .driver_data = (unsigned long) &siena_a0_nic_type},
 	{0}			/* end of list */
 };
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index 4764793..8a5336d 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -14,10 +14,6 @@
 #include "net_driver.h"
 #include "filter.h"
 
-/* PCI IDs */
-#define BETHPAGE_A_P_DEVID      0x0803
-#define SIENA_A_P_DEVID         0x0813
-
 /* Solarstorm controllers use BAR 0 for I/O space and BAR 2(&3) for memory */
 #define EFX_MEM_BAR 2
 
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index f3cd96d..1be51b2 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -956,40 +956,28 @@ static int efx_ethtool_set_rx_ntuple(struct net_device *net_dev,
 	return rc < 0 ? rc : 0;
 }
 
-static int efx_ethtool_get_rxfh_indir(struct net_device *net_dev,
-				      struct ethtool_rxfh_indir *indir)
+static u32 efx_ethtool_get_rxfh_indir_size(struct net_device *net_dev)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
-	size_t copy_size =
-		min_t(size_t, indir->size, ARRAY_SIZE(efx->rx_indir_table));
 
-	if (efx_nic_rev(efx) < EFX_REV_FALCON_B0)
-		return -EOPNOTSUPP;
+	return (efx_nic_rev(efx) < EFX_REV_FALCON_B0 ?
+		0 : ARRAY_SIZE(efx->rx_indir_table));
+}
+
+static int efx_ethtool_get_rxfh_indir(struct net_device *net_dev, u32 *indir)
+{
+	struct efx_nic *efx = netdev_priv(net_dev);
 
-	indir->size = ARRAY_SIZE(efx->rx_indir_table);
-	memcpy(indir->ring_index, efx->rx_indir_table,
-	       copy_size * sizeof(indir->ring_index[0]));
+	memcpy(indir, efx->rx_indir_table, sizeof(efx->rx_indir_table));
 	return 0;
 }
 
 static int efx_ethtool_set_rxfh_indir(struct net_device *net_dev,
-				      const struct ethtool_rxfh_indir *indir)
+				      const u32 *indir)
 {
 	struct efx_nic *efx = netdev_priv(net_dev);
-	size_t i;
-
-	if (efx_nic_rev(efx) < EFX_REV_FALCON_B0)
-		return -EOPNOTSUPP;
-
-	/* Validate size and indices */
-	if (indir->size != ARRAY_SIZE(efx->rx_indir_table))
-		return -EINVAL;
-	for (i = 0; i < ARRAY_SIZE(efx->rx_indir_table); i++)
-		if (indir->ring_index[i] >= efx->n_rx_channels)
-			return -EINVAL;
 
-	memcpy(efx->rx_indir_table, indir->ring_index,
-	       sizeof(efx->rx_indir_table));
+	memcpy(efx->rx_indir_table, indir, sizeof(efx->rx_indir_table));
 	efx_nic_push_rx_indir_table(efx);
 	return 0;
 }
@@ -1020,6 +1008,7 @@ const struct ethtool_ops efx_ethtool_ops = {
 	.reset			= efx_ethtool_reset,
 	.get_rxnfc		= efx_ethtool_get_rxnfc,
 	.set_rx_ntuple		= efx_ethtool_set_rx_ntuple,
+	.get_rxfh_indir_size	= efx_ethtool_get_rxfh_indir_size,
 	.get_rxfh_indir		= efx_ethtool_get_rxfh_indir,
 	.set_rxfh_indir		= efx_ethtool_set_rxfh_indir,
 };
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index b8e251a..c49502b 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -908,7 +908,7 @@ struct efx_nic_type {
 	unsigned int phys_addr_channels;
 	unsigned int tx_dc_base;
 	unsigned int rx_dc_base;
-	u32 offload_features;
+	netdev_features_t offload_features;
 };
 
 /**************************************************************************
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index 752d521..aca3498 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -479,11 +479,8 @@ static void efx_rx_packet_gro(struct efx_channel *channel,
 		if (efx->net_dev->features & NETIF_F_RXHASH)
 			skb->rxhash = efx_rx_buf_hash(eh);
 
-		skb_frag_set_page(skb, 0, page);
-		skb_shinfo(skb)->frags[0].page_offset =
-			efx_rx_buf_offset(efx, rx_buf);
-		skb_frag_size_set(&skb_shinfo(skb)->frags[0], rx_buf->len);
-		skb_shinfo(skb)->nr_frags = 1;
+		skb_fill_page_desc(skb, 0, page,
+				   efx_rx_buf_offset(efx, rx_buf), rx_buf->len);
 
 		skb->len = rx_buf->len;
 		skb->data_len = rx_buf->len;
@@ -669,7 +666,7 @@ int efx_probe_rx_queue(struct efx_rx_queue *rx_queue)
 		  rx_queue->ptr_mask);
 
 	/* Allocate RX buffers */
-	rx_queue->buffer = kzalloc(entries * sizeof(*rx_queue->buffer),
+	rx_queue->buffer = kcalloc(entries, sizeof(*rx_queue->buffer),
 				   GFP_KERNEL);
 	if (!rx_queue->buffer)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c
index 822f6c2..52edd24 100644
--- a/drivers/net/ethernet/sfc/selftest.c
+++ b/drivers/net/ethernet/sfc/selftest.c
@@ -503,8 +503,8 @@ efx_test_loopback(struct efx_tx_queue *tx_queue,
 		/* Determine how many packets to send */
 		state->packet_count = efx->txq_entries / 3;
 		state->packet_count = min(1 << (i << 2), state->packet_count);
-		state->skbs = kzalloc(sizeof(state->skbs[0]) *
-				      state->packet_count, GFP_KERNEL);
+		state->skbs = kcalloc(state->packet_count,
+				      sizeof(state->skbs[0]), GFP_KERNEL);
 		if (!state->skbs)
 			return -ENOMEM;
 		state->flush = false;
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index df88c543..72f0fbc 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -31,7 +31,9 @@
 #define EFX_TXQ_THRESHOLD(_efx) ((_efx)->txq_entries / 2u)
 
 static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
-			       struct efx_tx_buffer *buffer)
+			       struct efx_tx_buffer *buffer,
+			       unsigned int *pkts_compl,
+			       unsigned int *bytes_compl)
 {
 	if (buffer->unmap_len) {
 		struct pci_dev *pci_dev = tx_queue->efx->pci_dev;
@@ -48,6 +50,8 @@ static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
 	}
 
 	if (buffer->skb) {
+		(*pkts_compl)++;
+		(*bytes_compl) += buffer->skb->len;
 		dev_kfree_skb_any((struct sk_buff *) buffer->skb);
 		buffer->skb = NULL;
 		netif_vdbg(tx_queue->efx, tx_done, tx_queue->efx->net_dev,
@@ -250,6 +254,8 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
 	buffer->skb = skb;
 	buffer->continuation = false;
 
+	netdev_tx_sent_queue(tx_queue->core_txq, skb->len);
+
 	/* Pass off to hardware */
 	efx_nic_push_buffers(tx_queue);
 
@@ -267,10 +273,11 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
  unwind:
 	/* Work backwards until we hit the original insert pointer value */
 	while (tx_queue->insert_count != tx_queue->write_count) {
+		unsigned int pkts_compl = 0, bytes_compl = 0;
 		--tx_queue->insert_count;
 		insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask;
 		buffer = &tx_queue->buffer[insert_ptr];
-		efx_dequeue_buffer(tx_queue, buffer);
+		efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
 		buffer->len = 0;
 	}
 
@@ -293,7 +300,9 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
  * specified index.
  */
 static void efx_dequeue_buffers(struct efx_tx_queue *tx_queue,
-				unsigned int index)
+				unsigned int index,
+				unsigned int *pkts_compl,
+				unsigned int *bytes_compl)
 {
 	struct efx_nic *efx = tx_queue->efx;
 	unsigned int stop_index, read_ptr;
@@ -311,7 +320,7 @@ static void efx_dequeue_buffers(struct efx_tx_queue *tx_queue,
 			return;
 		}
 
-		efx_dequeue_buffer(tx_queue, buffer);
+		efx_dequeue_buffer(tx_queue, buffer, pkts_compl, bytes_compl);
 		buffer->continuation = true;
 		buffer->len = 0;
 
@@ -422,10 +431,12 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index)
 {
 	unsigned fill_level;
 	struct efx_nic *efx = tx_queue->efx;
+	unsigned int pkts_compl = 0, bytes_compl = 0;
 
 	EFX_BUG_ON_PARANOID(index > tx_queue->ptr_mask);
 
-	efx_dequeue_buffers(tx_queue, index);
+	efx_dequeue_buffers(tx_queue, index, &pkts_compl, &bytes_compl);
+	netdev_tx_completed_queue(tx_queue->core_txq, pkts_compl, bytes_compl);
 
 	/* See if we need to restart the netif queue.  This barrier
 	 * separates the update of read_count from the test of the
@@ -468,7 +479,7 @@ int efx_probe_tx_queue(struct efx_tx_queue *tx_queue)
 		  tx_queue->queue, efx->txq_entries, tx_queue->ptr_mask);
 
 	/* Allocate software ring */
-	tx_queue->buffer = kzalloc(entries * sizeof(*tx_queue->buffer),
+	tx_queue->buffer = kcalloc(entries, sizeof(*tx_queue->buffer),
 				   GFP_KERNEL);
 	if (!tx_queue->buffer)
 		return -ENOMEM;
@@ -515,13 +526,15 @@ void efx_release_tx_buffers(struct efx_tx_queue *tx_queue)
 
 	/* Free any buffers left in the ring */
 	while (tx_queue->read_count != tx_queue->write_count) {
+		unsigned int pkts_compl = 0, bytes_compl = 0;
 		buffer = &tx_queue->buffer[tx_queue->read_count & tx_queue->ptr_mask];
-		efx_dequeue_buffer(tx_queue, buffer);
+		efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
 		buffer->continuation = true;
 		buffer->len = 0;
 
 		++tx_queue->read_count;
 	}
+	netdev_tx_reset_queue(tx_queue->core_txq);
 }
 
 void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
@@ -1160,6 +1173,8 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
 			goto mem_err;
 	}
 
+	netdev_tx_sent_queue(tx_queue->core_txq, skb->len);
+
 	/* Pass off to hardware */
 	efx_nic_push_buffers(tx_queue);
 
diff --git a/drivers/net/ethernet/sgi/meth.c b/drivers/net/ethernet/sgi/meth.c
index 60135aa..f98c6c6 100644
--- a/drivers/net/ethernet/sgi/meth.c
+++ b/drivers/net/ethernet/sgi/meth.c
@@ -830,24 +830,7 @@ static struct platform_driver meth_driver = {
 	}
 };
 
-static int __init meth_init_module(void)
-{
-	int err;
-
-	err = platform_driver_register(&meth_driver);
-	if (err)
-		printk(KERN_ERR "Driver registration failed\n");
-
-	return err;
-}
-
-static void __exit meth_exit_module(void)
-{
-	platform_driver_unregister(&meth_driver);
-}
-
-module_init(meth_init_module);
-module_exit(meth_exit_module);
+module_platform_driver(meth_driver);
 
 MODULE_AUTHOR("Ilya Volynets <ilya@theIlya.com>");
 MODULE_DESCRIPTION("SGI O2 Builtin Fast Ethernet driver");
diff --git a/drivers/net/ethernet/sis/sis190.c b/drivers/net/ethernet/sis/sis190.c
index 1b4658c..5b118cd 100644
--- a/drivers/net/ethernet/sis/sis190.c
+++ b/drivers/net/ethernet/sis/sis190.c
@@ -47,8 +47,6 @@
 #define sis190_rx_skb			netif_rx
 #define sis190_rx_quota(count, quota)	count
 
-#define MAC_ADDR_LEN		6
-
 #define NUM_TX_DESC		64	/* [8..1024] */
 #define NUM_RX_DESC		64	/* [8..8192] */
 #define TX_RING_BYTES		(NUM_TX_DESC * sizeof(struct TxDesc))
@@ -1601,7 +1599,7 @@ static int __devinit sis190_get_mac_addr_from_eeprom(struct pci_dev *pdev,
 	}
 
 	/* Get MAC address from EEPROM */
-	for (i = 0; i < MAC_ADDR_LEN / 2; i++) {
+	for (i = 0; i < ETH_ALEN / 2; i++) {
 		u16 w = sis190_read_eeprom(ioaddr, EEPROMMACAddr + i);
 
 		((__le16 *)dev->dev_addr)[i] = cpu_to_le16(w);
@@ -1653,7 +1651,7 @@ static int __devinit sis190_get_mac_addr_from_apc(struct pci_dev *pdev,
 	udelay(50);
 	pci_read_config_byte(isa_bridge, 0x48, &reg);
 
-        for (i = 0; i < MAC_ADDR_LEN; i++) {
+        for (i = 0; i < ETH_ALEN; i++) {
                 outb(0x9 + i, 0x78);
                 dev->dev_addr[i] = inb(0x79);
         }
@@ -1692,7 +1690,7 @@ static inline void sis190_init_rxfilter(struct net_device *dev)
 	 */
 	SIS_W16(RxMacControl, ctl & ~0x0f00);
 
-	for (i = 0; i < MAC_ADDR_LEN; i++)
+	for (i = 0; i < ETH_ALEN; i++)
 		SIS_W8(RxMacAddr + i, dev->dev_addr[i]);
 
 	SIS_W16(RxMacControl, ctl);
@@ -1760,9 +1758,10 @@ static void sis190_get_drvinfo(struct net_device *dev,
 {
 	struct sis190_private *tp = netdev_priv(dev);
 
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->bus_info, pci_name(tp->pci_dev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(tp->pci_dev),
+		sizeof(info->bus_info));
 }
 
 static int sis190_get_regs_len(struct net_device *dev)
diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c
index a184abc..c8efc70 100644
--- a/drivers/net/ethernet/sis/sis900.c
+++ b/drivers/net/ethernet/sis/sis900.c
@@ -1991,9 +1991,10 @@ static void sis900_get_drvinfo(struct net_device *net_dev,
 {
 	struct sis900_private *sis_priv = netdev_priv(net_dev);
 
-	strcpy (info->driver, SIS900_MODULE_NAME);
-	strcpy (info->version, SIS900_DRV_VERSION);
-	strcpy (info->bus_info, pci_name(sis_priv->pci_dev));
+	strlcpy(info->driver, SIS900_MODULE_NAME, sizeof(info->driver));
+	strlcpy(info->version, SIS900_DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(sis_priv->pci_dev),
+		sizeof(info->bus_info));
 }
 
 static u32 sis900_get_msglevel(struct net_device *net_dev)
diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c
index 0a5dfb8..2c077ce 100644
--- a/drivers/net/ethernet/smsc/epic100.c
+++ b/drivers/net/ethernet/smsc/epic100.c
@@ -1414,9 +1414,9 @@ static void netdev_get_drvinfo (struct net_device *dev, struct ethtool_drvinfo *
 {
 	struct epic_private *np = netdev_priv(dev);
 
-	strcpy (info->driver, DRV_NAME);
-	strcpy (info->version, DRV_VERSION);
-	strcpy (info->bus_info, pci_name(np->pci_dev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(np->pci_dev), sizeof(info->bus_info));
 }
 
 static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
diff --git a/drivers/net/ethernet/smsc/smc911x.c b/drivers/net/ethernet/smsc/smc911x.c
index 8f61fe9..313ba3b 100644
--- a/drivers/net/ethernet/smsc/smc911x.c
+++ b/drivers/net/ethernet/smsc/smc911x.c
@@ -2196,15 +2196,4 @@ static struct platform_driver smc911x_driver = {
 	},
 };
 
-static int __init smc911x_init(void)
-{
-	return platform_driver_register(&smc911x_driver);
-}
-
-static void __exit smc911x_cleanup(void)
-{
-	platform_driver_unregister(&smc911x_driver);
-}
-
-module_init(smc911x_init);
-module_exit(smc911x_cleanup);
+module_platform_driver(smc911x_driver);
diff --git a/drivers/net/ethernet/smsc/smc91c92_cs.c b/drivers/net/ethernet/smsc/smc91c92_cs.c
index cbfa981..ada927a 100644
--- a/drivers/net/ethernet/smsc/smc91c92_cs.c
+++ b/drivers/net/ethernet/smsc/smc91c92_cs.c
@@ -1909,8 +1909,8 @@ static int check_if_running(struct net_device *dev)
 
 static void smc_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
 }
 
 static int smc_get_settings(struct net_device *dev, struct ethtool_cmd *ecmd)
diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c
index f47f81e..64ad3ed 100644
--- a/drivers/net/ethernet/smsc/smc91x.c
+++ b/drivers/net/ethernet/smsc/smc91x.c
@@ -2417,15 +2417,4 @@ static struct platform_driver smc_driver = {
 	},
 };
 
-static int __init smc_init(void)
-{
-	return platform_driver_register(&smc_driver);
-}
-
-static void __exit smc_cleanup(void)
-{
-	platform_driver_unregister(&smc_driver);
-}
-
-module_init(smc_init);
-module_exit(smc_cleanup);
+module_platform_driver(smc_driver);
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index d2be42a..06d0df6 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -44,6 +44,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
 #include <linux/sched.h>
 #include <linux/timer.h>
 #include <linux/bug.h>
@@ -88,6 +89,8 @@ struct smsc911x_ops {
 				unsigned int *buf, unsigned int wordcount);
 };
 
+#define SMSC911X_NUM_SUPPLIES 2
+
 struct smsc911x_data {
 	void __iomem *ioaddr;
 
@@ -138,6 +141,9 @@ struct smsc911x_data {
 
 	/* register access functions */
 	const struct smsc911x_ops *ops;
+
+	/* regulators */
+	struct regulator_bulk_data supplies[SMSC911X_NUM_SUPPLIES];
 };
 
 /* Easy access to information */
@@ -362,6 +368,76 @@ out:
 	spin_unlock_irqrestore(&pdata->dev_lock, flags);
 }
 
+/*
+ * enable resources, currently just regulators.
+ */
+static int smsc911x_enable_resources(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct smsc911x_data *pdata = netdev_priv(ndev);
+	int ret = 0;
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(pdata->supplies),
+			pdata->supplies);
+	if (ret)
+		netdev_err(ndev, "failed to enable regulators %d\n",
+				ret);
+	return ret;
+}
+
+/*
+ * disable resources, currently just regulators.
+ */
+static int smsc911x_disable_resources(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct smsc911x_data *pdata = netdev_priv(ndev);
+	int ret = 0;
+
+	ret = regulator_bulk_disable(ARRAY_SIZE(pdata->supplies),
+			pdata->supplies);
+	return ret;
+}
+
+/*
+ * Request resources, currently just regulators.
+ *
+ * The SMSC911x has two power pins: vddvario and vdd33a, in designs where
+ * these are not always-on we need to request regulators to be turned on
+ * before we can try to access the device registers.
+ */
+static int smsc911x_request_resources(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct smsc911x_data *pdata = netdev_priv(ndev);
+	int ret = 0;
+
+	/* Request regulators */
+	pdata->supplies[0].supply = "vdd33a";
+	pdata->supplies[1].supply = "vddvario";
+	ret = regulator_bulk_get(&pdev->dev,
+			ARRAY_SIZE(pdata->supplies),
+			pdata->supplies);
+	if (ret)
+		netdev_err(ndev, "couldn't get regulators %d\n",
+				ret);
+	return ret;
+}
+
+/*
+ * Free resources, currently just regulators.
+ *
+ */
+static void smsc911x_free_resources(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct smsc911x_data *pdata = netdev_priv(ndev);
+
+	/* Free regulators */
+	regulator_bulk_free(ARRAY_SIZE(pdata->supplies),
+			pdata->supplies);
+}
+
 /* waits for MAC not busy, with timeout.  Only called by smsc911x_mac_read
  * and smsc911x_mac_write, so assumes mac_lock is held */
 static int smsc911x_mac_complete(struct smsc911x_data *pdata)
@@ -1937,6 +2013,7 @@ static int __devinit smsc911x_init(struct net_device *dev)
 {
 	struct smsc911x_data *pdata = netdev_priv(dev);
 	unsigned int byte_test;
+	unsigned int to = 100;
 
 	SMSC_TRACE(pdata, probe, "Driver Parameters:");
 	SMSC_TRACE(pdata, probe, "LAN base: 0x%08lX",
@@ -1952,6 +2029,17 @@ static int __devinit smsc911x_init(struct net_device *dev)
 		return -ENODEV;
 	}
 
+	/*
+	 * poll the READY bit in PMT_CTRL. Any other access to the device is
+	 * forbidden while this bit isn't set. Try for 100ms
+	 */
+	while (!(smsc911x_reg_read(pdata, PMT_CTRL) & PMT_CTRL_READY_) && --to)
+		udelay(1000);
+	if (to == 0) {
+		pr_err("Device not READY in 100ms aborting\n");
+		return -ENODEV;
+	}
+
 	/* Check byte ordering */
 	byte_test = smsc911x_reg_read(pdata, BYTE_TEST);
 	SMSC_TRACE(pdata, probe, "BYTE_TEST: 0x%08X", byte_test);
@@ -2080,6 +2168,9 @@ static int __devexit smsc911x_drv_remove(struct platform_device *pdev)
 
 	iounmap(pdata->ioaddr);
 
+	(void)smsc911x_disable_resources(pdev);
+	smsc911x_free_resources(pdev);
+
 	free_netdev(dev);
 
 	return 0;
@@ -2206,10 +2297,20 @@ static int __devinit smsc911x_drv_probe(struct platform_device *pdev)
 	pdata->dev = dev;
 	pdata->msg_enable = ((1 << debug) - 1);
 
+	platform_set_drvdata(pdev, dev);
+
+	retval = smsc911x_request_resources(pdev);
+	if (retval)
+		goto out_return_resources;
+
+	retval = smsc911x_enable_resources(pdev);
+	if (retval)
+		goto out_disable_resources;
+
 	if (pdata->ioaddr == NULL) {
 		SMSC_WARN(pdata, probe, "Error smsc911x base address invalid");
 		retval = -ENOMEM;
-		goto out_free_netdev_2;
+		goto out_disable_resources;
 	}
 
 	retval = smsc911x_probe_config_dt(&pdata->config, np);
@@ -2221,7 +2322,7 @@ static int __devinit smsc911x_drv_probe(struct platform_device *pdev)
 
 	if (retval) {
 		SMSC_WARN(pdata, probe, "Error smsc911x config not found");
-		goto out_unmap_io_3;
+		goto out_disable_resources;
 	}
 
 	/* assume standard, non-shifted, access to HW registers */
@@ -2232,7 +2333,7 @@ static int __devinit smsc911x_drv_probe(struct platform_device *pdev)
 
 	retval = smsc911x_init(dev);
 	if (retval < 0)
-		goto out_unmap_io_3;
+		goto out_disable_resources;
 
 	/* configure irq polarity and type before connecting isr */
 	if (pdata->config.irq_polarity == SMSC911X_IRQ_POLARITY_ACTIVE_HIGH)
@@ -2252,15 +2353,13 @@ static int __devinit smsc911x_drv_probe(struct platform_device *pdev)
 	if (retval) {
 		SMSC_WARN(pdata, probe,
 			  "Unable to claim requested irq: %d", dev->irq);
-		goto out_unmap_io_3;
+		goto out_free_irq;
 	}
 
-	platform_set_drvdata(pdev, dev);
-
 	retval = register_netdev(dev);
 	if (retval) {
 		SMSC_WARN(pdata, probe, "Error %i registering device", retval);
-		goto out_unset_drvdata_4;
+		goto out_free_irq;
 	} else {
 		SMSC_TRACE(pdata, probe,
 			   "Network interface: \"%s\"", dev->name);
@@ -2309,12 +2408,14 @@ static int __devinit smsc911x_drv_probe(struct platform_device *pdev)
 
 out_unregister_netdev_5:
 	unregister_netdev(dev);
-out_unset_drvdata_4:
-	platform_set_drvdata(pdev, NULL);
+out_free_irq:
 	free_irq(dev->irq, dev);
-out_unmap_io_3:
+out_disable_resources:
+	(void)smsc911x_disable_resources(pdev);
+out_return_resources:
+	smsc911x_free_resources(pdev);
+	platform_set_drvdata(pdev, NULL);
 	iounmap(pdata->ioaddr);
-out_free_netdev_2:
 	free_netdev(dev);
 out_release_io_1:
 	release_mem_region(res->start, resource_size(res));
diff --git a/drivers/net/ethernet/smsc/smsc9420.c b/drivers/net/ethernet/smsc/smsc9420.c
index edb24b0..a9efbdf 100644
--- a/drivers/net/ethernet/smsc/smsc9420.c
+++ b/drivers/net/ethernet/smsc/smsc9420.c
@@ -279,9 +279,10 @@ static void smsc9420_ethtool_get_drvinfo(struct net_device *netdev,
 {
 	struct smsc9420_pdata *pd = netdev_priv(netdev);
 
-	strcpy(drvinfo->driver, DRV_NAME);
-	strcpy(drvinfo->bus_info, pci_name(pd->pdev));
-	strcpy(drvinfo->version, DRV_VERSION);
+	strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->bus_info, pci_name(pd->pdev),
+		sizeof(drvinfo->bus_info));
+	strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version));
 }
 
 static u32 smsc9420_ethtool_get_msglevel(struct net_device *netdev)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
index da66ac5..4d5402a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -39,10 +39,11 @@ static int dwmac1000_dma_init(void __iomem *ioaddr, int pbl, u32 dma_tx,
 	/* DMA SW reset */
 	value |= DMA_BUS_MODE_SFT_RESET;
 	writel(value, ioaddr + DMA_BUS_MODE);
-	limit = 15000;
+	limit = 10;
 	while (limit--) {
 		if (!(readl(ioaddr + DMA_BUS_MODE) & DMA_BUS_MODE_SFT_RESET))
 			break;
+		mdelay(10);
 	}
 	if (limit < 0)
 		return -EBUSY;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
index 627f656..bc17fd0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_dma.c
@@ -41,10 +41,11 @@ static int dwmac100_dma_init(void __iomem *ioaddr, int pbl, u32 dma_tx,
 	/* DMA SW reset */
 	value |= DMA_BUS_MODE_SFT_RESET;
 	writel(value, ioaddr + DMA_BUS_MODE);
-	limit = 15000;
+	limit = 10;
 	while (limit--) {
 		if (!(readl(ioaddr + DMA_BUS_MODE) & DMA_BUS_MODE_SFT_RESET))
 			break;
+		mdelay(10);
 	}
 	if (limit < 0)
 		return -EBUSY;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 9bafa6c..a140a8f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -72,7 +72,6 @@ struct stmmac_priv {
 	spinlock_t lock;
 	spinlock_t tx_lock;
 	int wolopts;
-	int wolenabled;
 	int wol_irq;
 #ifdef CONFIG_STMMAC_TIMER
 	struct stmmac_timer *tm;
@@ -80,6 +79,7 @@ struct stmmac_priv {
 	struct plat_stmmacenet_data *plat;
 	struct stmmac_counters mmc;
 	struct dma_features dma_cap;
+	int hw_cap_support;
 };
 
 extern int stmmac_mdio_unregister(struct net_device *ndev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index e8eff09..ed83c4c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -185,9 +185,10 @@ static void stmmac_ethtool_getdrvinfo(struct net_device *dev,
 	struct stmmac_priv *priv = netdev_priv(dev);
 
 	if (priv->plat->has_gmac)
-		strcpy(info->driver, GMAC_ETHTOOL_NAME);
+		strlcpy(info->driver, GMAC_ETHTOOL_NAME, sizeof(info->driver));
 	else
-		strcpy(info->driver, MAC100_ETHTOOL_NAME);
+		strlcpy(info->driver, MAC100_ETHTOOL_NAME,
+			sizeof(info->driver));
 
 	strcpy(info->version, DRV_MODULE_VERSION);
 	info->fw_version[0] = '\0';
@@ -430,6 +431,12 @@ static int stmmac_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	struct stmmac_priv *priv = netdev_priv(dev);
 	u32 support = WAKE_MAGIC | WAKE_UCAST;
 
+	/* By default almost all GMAC devices support the WoL via
+	 * magic frame but we can disable it if the HW capability
+	 * register shows no support for pmt_magic_frame. */
+	if ((priv->hw_cap_support) && (!priv->dma_cap.pmt_magic_frame))
+		wol->wolopts &= ~WAKE_MAGIC;
+
 	if (!device_can_wakeup(priv->device))
 		return -EINVAL;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 20546bb..24c2bf6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -321,12 +321,10 @@ static int stmmac_init_phy(struct net_device *dev)
 	}
 
 	/* Stop Advertising 1000BASE Capability if interface is not GMII */
-	if ((interface) && ((interface == PHY_INTERFACE_MODE_MII) ||
-	    (interface == PHY_INTERFACE_MODE_RMII))) {
-		phydev->supported &= (PHY_BASIC_FEATURES | SUPPORTED_Pause |
-				      SUPPORTED_Asym_Pause);
-		phydev->advertising = phydev->supported;
-	}
+	if ((interface == PHY_INTERFACE_MODE_MII) ||
+	    (interface == PHY_INTERFACE_MODE_RMII))
+		phydev->advertising &= ~(SUPPORTED_1000baseT_Half |
+					 SUPPORTED_1000baseT_Full);
 
 	/*
 	 * Broken HW is sometimes missing the pull-up resistor on the
@@ -783,10 +781,15 @@ static void stmmac_mmc_setup(struct stmmac_priv *priv)
 	unsigned int mode = MMC_CNTRL_RESET_ON_READ | MMC_CNTRL_COUNTER_RESET |
 			    MMC_CNTRL_PRESET | MMC_CNTRL_FULL_HALF_PRESET;
 
-	/* Do not manage MMC IRQ (FIXME) */
+	/* Mask MMC irq, counters are managed in SW and registers
+	 * are cleared on each READ eventually. */
 	dwmac_mmc_intr_all_mask(priv->ioaddr);
-	dwmac_mmc_ctrl(priv->ioaddr, mode);
-	memset(&priv->mmc, 0, sizeof(struct stmmac_counters));
+
+	if (priv->dma_cap.rmon) {
+		dwmac_mmc_ctrl(priv->ioaddr, mode);
+		memset(&priv->mmc, 0, sizeof(struct stmmac_counters));
+	} else
+		pr_info(" No MAC Management Counters available");
 }
 
 static u32 stmmac_get_synopsys_id(struct stmmac_priv *priv)
@@ -807,8 +810,29 @@ static u32 stmmac_get_synopsys_id(struct stmmac_priv *priv)
 	return 0;
 }
 
-/* New GMAC chips support a new register to indicate the
- * presence of the optional feature/functions.
+/**
+ * stmmac_selec_desc_mode
+ * @dev : device pointer
+ * Description: select the Enhanced/Alternate or Normal descriptors */
+static void stmmac_selec_desc_mode(struct stmmac_priv *priv)
+{
+	if (priv->plat->enh_desc) {
+		pr_info(" Enhanced/Alternate descriptors\n");
+		priv->hw->desc = &enh_desc_ops;
+	} else {
+		pr_info(" Normal descriptors\n");
+		priv->hw->desc = &ndesc_ops;
+	}
+}
+
+/**
+ * stmmac_get_hw_features
+ * @priv : private device pointer
+ * Description:
+ *  new GMAC chip generations have a new register to indicate the
+ *  presence of the optional feature/functions.
+ *  This can be also used to override the value passed through the
+ *  platform and necessary for old MAC10/100 and GMAC chips.
  */
 static int stmmac_get_hw_features(struct stmmac_priv *priv)
 {
@@ -829,7 +853,7 @@ static int stmmac_get_hw_features(struct stmmac_priv *priv)
 			(hw_cap & DMA_HW_FEAT_RWKSEL) >> 9;
 		priv->dma_cap.pmt_magic_frame =
 			(hw_cap & DMA_HW_FEAT_MGKSEL) >> 10;
-		/*MMC*/
+		/* MMC */
 		priv->dma_cap.rmon = (hw_cap & DMA_HW_FEAT_MMCSEL) >> 11;
 		/* IEEE 1588-2002*/
 		priv->dma_cap.time_stamp =
@@ -857,8 +881,7 @@ static int stmmac_get_hw_features(struct stmmac_priv *priv)
 		priv->dma_cap.enh_desc =
 			(hw_cap & DMA_HW_FEAT_ENHDESSEL) >> 24;
 
-	} else
-		pr_debug("\tNo HW DMA feature register supported");
+	}
 
 	return hw_cap;
 }
@@ -913,6 +936,44 @@ static int stmmac_open(struct net_device *dev)
 		goto open_error;
 	}
 
+	stmmac_get_synopsys_id(priv);
+
+	priv->hw_cap_support = stmmac_get_hw_features(priv);
+
+	if (priv->hw_cap_support) {
+		pr_info(" Support DMA HW capability register");
+
+		/* We can override some gmac/dma configuration fields: e.g.
+		 * enh_desc, tx_coe (e.g. that are passed through the
+		 * platform) with the values from the HW capability
+		 * register (if supported).
+		 */
+		priv->plat->enh_desc = priv->dma_cap.enh_desc;
+		priv->plat->tx_coe = priv->dma_cap.tx_coe;
+		priv->plat->pmt = priv->dma_cap.pmt_remote_wake_up;
+
+		/* By default disable wol on magic frame if not supported */
+		if (!priv->dma_cap.pmt_magic_frame)
+			priv->wolopts &= ~WAKE_MAGIC;
+
+	} else
+		pr_info(" No HW DMA feature register supported");
+
+	/* Select the enhnaced/normal descriptor structures */
+	stmmac_selec_desc_mode(priv);
+
+	/* PMT module is not integrated in all the MAC devices. */
+	if (priv->plat->pmt) {
+		pr_info(" Remote wake-up capable\n");
+		device_set_wakeup_capable(priv->device, 1);
+	}
+
+	priv->rx_coe = priv->hw->mac->rx_coe(priv->ioaddr);
+	if (priv->rx_coe)
+		pr_info(" Checksum Offload Engine supported\n");
+	if (priv->plat->tx_coe)
+		pr_info(" Checksum insertion supported\n");
+
 	/* Create and initialize the TX/RX descriptors chains. */
 	priv->dma_tx_size = STMMAC_ALIGN(dma_txsize);
 	priv->dma_rx_size = STMMAC_ALIGN(dma_rxsize);
@@ -935,15 +996,6 @@ static int stmmac_open(struct net_device *dev)
 	/* Initialize the MAC Core */
 	priv->hw->mac->core_init(priv->ioaddr);
 
-	stmmac_get_synopsys_id(priv);
-
-	stmmac_get_hw_features(priv);
-
-	priv->rx_coe = priv->hw->mac->rx_coe(priv->ioaddr);
-	if (priv->rx_coe)
-		pr_info("stmmac: Rx Checksum Offload Engine supported\n");
-	if (priv->plat->tx_coe)
-		pr_info("\tTX Checksum insertion supported\n");
 	netdev_update_features(dev);
 
 	/* Request the IRQ lines */
@@ -965,8 +1017,7 @@ static int stmmac_open(struct net_device *dev)
 	memset(&priv->xstats, 0, sizeof(struct stmmac_extra_stats));
 	priv->xstats.threshold = tc;
 
-	if (priv->dma_cap.rmon)
-		stmmac_mmc_setup(priv);
+	stmmac_mmc_setup(priv);
 
 	/* Start the ball rolling... */
 	DBG(probe, DEBUG, "%s: DMA RX/TX processes started...\n", dev->name);
@@ -1419,7 +1470,8 @@ static int stmmac_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
-static u32 stmmac_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t stmmac_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 
@@ -1489,9 +1541,7 @@ static int stmmac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	if (!priv->phydev)
 		return -EINVAL;
 
-	spin_lock(&priv->lock);
 	ret = phy_mii_ioctl(priv->phydev, rq, cmd);
-	spin_unlock(&priv->lock);
 
 	return ret;
 }
@@ -1558,7 +1608,7 @@ static int stmmac_sysfs_dma_cap_read(struct seq_file *seq, void *v)
 	struct net_device *dev = seq->private;
 	struct stmmac_priv *priv = netdev_priv(dev);
 
-	if (!stmmac_get_hw_features(priv)) {
+	if (!priv->hw_cap_support) {
 		seq_printf(seq, "DMA HW features not supported\n");
 		return 0;
 	}
@@ -1766,12 +1816,6 @@ static int stmmac_mac_device_setup(struct net_device *dev)
 	if (!device)
 		return -ENOMEM;
 
-	if (priv->plat->enh_desc) {
-		device->desc = &enh_desc_ops;
-		pr_info("\tEnhanced descriptor structure\n");
-	} else
-		device->desc = &ndesc_ops;
-
 	priv->hw = device;
 	priv->hw->ring = &ring_mode_ops;
 
@@ -1845,11 +1889,6 @@ static int stmmac_dvr_probe(struct platform_device *pdev)
 
 	priv->ioaddr = addr;
 
-	/* PMT module is not integrated in all the MAC devices. */
-	if (plat_dat->pmt) {
-		pr_info("\tPMT module supported\n");
-		device_set_wakeup_capable(&pdev->dev, 1);
-	}
 	/*
 	 * On some platforms e.g. SPEAr the wake up irq differs from the mac irq
 	 * The external wake up irq can be passed through the platform code
@@ -1862,7 +1901,6 @@ static int stmmac_dvr_probe(struct platform_device *pdev)
 	if (priv->wol_irq == -ENXIO)
 		priv->wol_irq = ndev->irq;
 
-
 	platform_set_drvdata(pdev, ndev);
 
 	/* Set the I/O base addr */
@@ -1875,7 +1913,7 @@ static int stmmac_dvr_probe(struct platform_device *pdev)
 			goto out_free_ndev;
 	}
 
-	/* MAC HW revice detection */
+	/* MAC HW device detection */
 	ret = stmmac_mac_device_setup(ndev);
 	if (ret < 0)
 		goto out_plat_exit;
@@ -1978,12 +2016,13 @@ static int stmmac_suspend(struct device *dev)
 	if (!ndev || !netif_running(ndev))
 		return 0;
 
+	if (priv->phydev)
+		phy_stop(priv->phydev);
+
 	spin_lock(&priv->lock);
 
 	netif_device_detach(ndev);
 	netif_stop_queue(ndev);
-	if (priv->phydev)
-		phy_stop(priv->phydev);
 
 #ifdef CONFIG_STMMAC_TIMER
 	priv->tm->timer_stop();
@@ -2041,12 +2080,13 @@ static int stmmac_resume(struct device *dev)
 #endif
 	napi_enable(&priv->napi);
 
-	if (priv->phydev)
-		phy_start(priv->phydev);
-
 	netif_start_queue(ndev);
 
 	spin_unlock(&priv->lock);
+
+	if (priv->phydev)
+		phy_start(priv->phydev);
+
 	return 0;
 }
 
@@ -2091,27 +2131,6 @@ static struct platform_driver stmmac_driver = {
 	},
 };
 
-/**
- * stmmac_init_module - Entry point for the driver
- * Description: This function is the entry point for the driver.
- */
-static int __init stmmac_init_module(void)
-{
-	int ret;
-
-	ret = platform_driver_register(&stmmac_driver);
-	return ret;
-}
-
-/**
- * stmmac_cleanup_module - Cleanup routine for the driver
- * Description: This function is the cleanup routine for the driver.
- */
-static void __exit stmmac_cleanup_module(void)
-{
-	platform_driver_unregister(&stmmac_driver);
-}
-
 #ifndef MODULE
 static int __init stmmac_cmdline_opt(char *str)
 {
@@ -2171,8 +2190,7 @@ err:
 __setup("stmmaceth=", stmmac_cmdline_opt);
 #endif
 
-module_init(stmmac_init_module);
-module_exit(stmmac_cleanup_module);
+module_platform_driver(stmmac_driver);
 
 MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet driver");
 MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c
index fd40988..f10665f 100644
--- a/drivers/net/ethernet/sun/cassini.c
+++ b/drivers/net/ethernet/sun/cassini.c
@@ -4532,10 +4532,9 @@ static void cas_set_multicast(struct net_device *dev)
 static void cas_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
 	struct cas *cp = netdev_priv(dev);
-	strncpy(info->driver, DRV_MODULE_NAME, ETHTOOL_BUSINFO_LEN);
-	strncpy(info->version, DRV_MODULE_VERSION, ETHTOOL_BUSINFO_LEN);
-	info->fw_version[0] = '\0';
-	strncpy(info->bus_info, pci_name(cp->pdev), ETHTOOL_BUSINFO_LEN);
+	strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(cp->pdev), sizeof(info->bus_info));
 	info->regdump_len = cp->casreg_len < CAS_MAX_REGS ?
 		cp->casreg_len : CAS_MAX_REGS;
 	info->n_stats = CAS_NUM_STAT_KEYS;
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 73c7081..cf43393 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -1151,19 +1151,8 @@ static int link_status_mii(struct niu *np, int *link_up_p)
 		supported |= SUPPORTED_1000baseT_Full;
 	lp->supported = supported;
 
-	advertising = 0;
-	if (advert & ADVERTISE_10HALF)
-		advertising |= ADVERTISED_10baseT_Half;
-	if (advert & ADVERTISE_10FULL)
-		advertising |= ADVERTISED_10baseT_Full;
-	if (advert & ADVERTISE_100HALF)
-		advertising |= ADVERTISED_100baseT_Half;
-	if (advert & ADVERTISE_100FULL)
-		advertising |= ADVERTISED_100baseT_Full;
-	if (ctrl1000 & ADVERTISE_1000HALF)
-		advertising |= ADVERTISED_1000baseT_Half;
-	if (ctrl1000 & ADVERTISE_1000FULL)
-		advertising |= ADVERTISED_1000baseT_Full;
+	advertising = mii_adv_to_ethtool_adv_t(advert);
+	advertising |= mii_ctrl1000_to_ethtool_adv_t(ctrl1000);
 
 	if (bmcr & BMCR_ANENABLE) {
 		int neg, neg1000;
@@ -3609,6 +3598,7 @@ static int release_tx_packet(struct niu *np, struct tx_ring_info *rp, int idx)
 static void niu_tx_work(struct niu *np, struct tx_ring_info *rp)
 {
 	struct netdev_queue *txq;
+	unsigned int tx_bytes;
 	u16 pkt_cnt, tmp;
 	int cons, index;
 	u64 cs;
@@ -3631,12 +3621,18 @@ static void niu_tx_work(struct niu *np, struct tx_ring_info *rp)
 	netif_printk(np, tx_done, KERN_DEBUG, np->dev,
 		     "%s() pkt_cnt[%u] cons[%d]\n", __func__, pkt_cnt, cons);
 
-	while (pkt_cnt--)
+	tx_bytes = 0;
+	tmp = pkt_cnt;
+	while (tmp--) {
+		tx_bytes += rp->tx_buffs[cons].skb->len;
 		cons = release_tx_packet(np, rp, cons);
+	}
 
 	rp->cons = cons;
 	smp_mb();
 
+	netdev_tx_completed_queue(txq, pkt_cnt, tx_bytes);
+
 out:
 	if (unlikely(netif_tx_queue_stopped(txq) &&
 		     (niu_tx_avail(rp) > NIU_TX_WAKEUP_THRESH(rp)))) {
@@ -4337,6 +4333,7 @@ static void niu_free_channels(struct niu *np)
 			struct tx_ring_info *rp = &np->tx_rings[i];
 
 			niu_free_tx_ring_info(np, rp);
+			netdev_tx_reset_queue(netdev_get_tx_queue(np->dev, i));
 		}
 		kfree(np->tx_rings);
 		np->tx_rings = NULL;
@@ -6742,6 +6739,8 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb,
 		prod = NEXT_TX(rp, prod);
 	}
 
+	netdev_tx_sent_queue(txq, skb->len);
+
 	if (prod < rp->prod)
 		rp->wrap_bit ^= TX_RING_KICK_WRAP;
 	rp->prod = prod;
@@ -6823,12 +6822,13 @@ static void niu_get_drvinfo(struct net_device *dev,
 	struct niu *np = netdev_priv(dev);
 	struct niu_vpd *vpd = &np->vpd;
 
-	strcpy(info->driver, DRV_MODULE_NAME);
-	strcpy(info->version, DRV_MODULE_VERSION);
-	sprintf(info->fw_version, "%d.%d",
+	strlcpy(info->driver, DRV_MODULE_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_MODULE_VERSION, sizeof(info->version));
+	snprintf(info->fw_version, sizeof(info->fw_version), "%d.%d",
 		vpd->fcode_major, vpd->fcode_minor);
 	if (np->parent->plat_type != PLAT_TYPE_NIU)
-		strcpy(info->bus_info, pci_name(np->pdev));
+		strlcpy(info->bus_info, pci_name(np->pdev),
+			sizeof(info->bus_info));
 }
 
 static int niu_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
@@ -8589,9 +8589,11 @@ static int __devinit phy_record(struct niu_parent *parent,
 	if (dev_id_1 < 0 || dev_id_2 < 0)
 		return 0;
 	if (type == PHY_TYPE_PMA_PMD || type == PHY_TYPE_PCS) {
+		/* Because of the NIU_PHY_ID_MASK being applied, the 8704
+		 * test covers the 8706 as well.
+		 */
 		if (((id & NIU_PHY_ID_MASK) != NIU_PHY_ID_BCM8704) &&
-		    ((id & NIU_PHY_ID_MASK) != NIU_PHY_ID_MRVL88X2011) &&
-		    ((id & NIU_PHY_ID_MASK) != NIU_PHY_ID_BCM8706))
+		    ((id & NIU_PHY_ID_MASK) != NIU_PHY_ID_MRVL88X2011))
 			return 0;
 	} else {
 		if ((id & NIU_PHY_ID_MASK) != NIU_PHY_ID_BCM5464R)
diff --git a/drivers/net/ethernet/sun/sunbmac.c b/drivers/net/ethernet/sun/sunbmac.c
index 0d8cfd9..220f724 100644
--- a/drivers/net/ethernet/sun/sunbmac.c
+++ b/drivers/net/ethernet/sun/sunbmac.c
@@ -1293,15 +1293,4 @@ static struct platform_driver bigmac_sbus_driver = {
 	.remove		= __devexit_p(bigmac_sbus_remove),
 };
 
-static int __init bigmac_init(void)
-{
-	return platform_driver_register(&bigmac_sbus_driver);
-}
-
-static void __exit bigmac_exit(void)
-{
-	platform_driver_unregister(&bigmac_sbus_driver);
-}
-
-module_init(bigmac_init);
-module_exit(bigmac_exit);
+module_platform_driver(bigmac_sbus_driver);
diff --git a/drivers/net/ethernet/sun/sungem.c b/drivers/net/ethernet/sun/sungem.c
index ceab215..31441a8 100644
--- a/drivers/net/ethernet/sun/sungem.c
+++ b/drivers/net/ethernet/sun/sungem.c
@@ -2517,9 +2517,9 @@ static void gem_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info
 {
 	struct gem *gp = netdev_priv(dev);
 
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->bus_info, pci_name(gp->pdev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(gp->pdev), sizeof(info->bus_info));
 }
 
 static int gem_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index c517dac..eebd52f 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -2457,11 +2457,11 @@ static void hme_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info
 {
 	struct happy_meal *hp = netdev_priv(dev);
 
-	strcpy(info->driver, "sunhme");
-	strcpy(info->version, "2.02");
+	strlcpy(info->driver, "sunhme", sizeof(info->driver));
+	strlcpy(info->version, "2.02", sizeof(info->version));
 	if (hp->happy_flags & HFLAG_PCI) {
 		struct pci_dev *pdev = hp->happy_dev;
-		strcpy(info->bus_info, pci_name(pdev));
+		strlcpy(info->bus_info, pci_name(pdev), sizeof(info->bus_info));
 	}
 #ifdef CONFIG_SBUS
 	else {
@@ -2469,7 +2469,8 @@ static void hme_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info
 		struct platform_device *op = hp->happy_dev;
 		regs = of_get_property(op->dev.of_node, "regs", NULL);
 		if (regs)
-			sprintf(info->bus_info, "SBUS:%d",
+			snprintf(info->bus_info, sizeof(info->bus_info),
+				"SBUS:%d",
 				regs->which_io);
 	}
 #endif
@@ -2637,7 +2638,7 @@ static int __devinit happy_meal_sbus_probe_one(struct platform_device *op, int i
 	sbus_dp = op->dev.parent->of_node;
 
 	/* We can match PCI devices too, do not accept those here. */
-	if (strcmp(sbus_dp->name, "sbus"))
+	if (strcmp(sbus_dp->name, "sbus") && strcmp(sbus_dp->name, "sbi"))
 		return err;
 
 	if (is_qfe) {
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index 3a90af6..4b19e9b 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -727,9 +727,10 @@ static void __bdx_vlan_rx_vid(struct net_device *ndev, uint16_t vid, int enable)
  * @ndev network device
  * @vid  VLAN vid to add
  */
-static void bdx_vlan_rx_add_vid(struct net_device *ndev, uint16_t vid)
+static int bdx_vlan_rx_add_vid(struct net_device *ndev, uint16_t vid)
 {
 	__bdx_vlan_rx_vid(ndev, vid, 1);
+	return 0;
 }
 
 /*
@@ -737,9 +738,10 @@ static void bdx_vlan_rx_add_vid(struct net_device *ndev, uint16_t vid)
  * @ndev network device
  * @vid  VLAN vid to kill
  */
-static void bdx_vlan_rx_kill_vid(struct net_device *ndev, unsigned short vid)
+static int bdx_vlan_rx_kill_vid(struct net_device *ndev, unsigned short vid)
 {
 	__bdx_vlan_rx_vid(ndev, vid, 0);
+	return 0;
 }
 
 /**
diff --git a/drivers/net/ethernet/tundra/tsi108_eth.c b/drivers/net/ethernet/tundra/tsi108_eth.c
index a8df7ec..a9ce01ba 100644
--- a/drivers/net/ethernet/tundra/tsi108_eth.c
+++ b/drivers/net/ethernet/tundra/tsi108_eth.c
@@ -1688,18 +1688,6 @@ static void tsi108_timed_checker(unsigned long dev_ptr)
 	mod_timer(&data->timer, jiffies + CHECK_PHY_INTERVAL);
 }
 
-static int tsi108_ether_init(void)
-{
-	int ret;
-	ret = platform_driver_register (&tsi_eth_driver);
-	if (ret < 0){
-		printk("tsi108_ether_init: error initializing ethernet "
-		       "device\n");
-		return ret;
-	}
-	return 0;
-}
-
 static int tsi108_ether_remove(struct platform_device *pdev)
 {
 	struct net_device *dev = platform_get_drvdata(pdev);
@@ -1714,13 +1702,7 @@ static int tsi108_ether_remove(struct platform_device *pdev)
 
 	return 0;
 }
-static void tsi108_ether_exit(void)
-{
-	platform_driver_unregister(&tsi_eth_driver);
-}
-
-module_init(tsi108_ether_init);
-module_exit(tsi108_ether_exit);
+module_platform_driver(tsi_eth_driver);
 
 MODULE_AUTHOR("Tundra Semiconductor Corporation");
 MODULE_DESCRIPTION("Tsi108 Gigabit Ethernet driver");
diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c
index f34dd99..bcdbdc7 100644
--- a/drivers/net/ethernet/via/via-rhine.c
+++ b/drivers/net/ethernet/via/via-rhine.c
@@ -488,8 +488,8 @@ static int netdev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
 static const struct ethtool_ops netdev_ethtool_ops;
 static int  rhine_close(struct net_device *dev);
 static void rhine_shutdown (struct pci_dev *pdev);
-static void rhine_vlan_rx_add_vid(struct net_device *dev, unsigned short vid);
-static void rhine_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid);
+static int rhine_vlan_rx_add_vid(struct net_device *dev, unsigned short vid);
+static int rhine_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid);
 static void rhine_set_cam(void __iomem *ioaddr, int idx, u8 *addr);
 static void rhine_set_vlan_cam(void __iomem *ioaddr, int idx, u8 *addr);
 static void rhine_set_cam_mask(void __iomem *ioaddr, u32 mask);
@@ -1261,7 +1261,7 @@ static void rhine_update_vcam(struct net_device *dev)
 	rhine_set_vlan_cam_mask(ioaddr, vCAMmask);
 }
 
-static void rhine_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+static int rhine_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 {
 	struct rhine_private *rp = netdev_priv(dev);
 
@@ -1269,9 +1269,10 @@ static void rhine_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 	set_bit(vid, rp->active_vlans);
 	rhine_update_vcam(dev);
 	spin_unlock_irq(&rp->lock);
+	return 0;
 }
 
-static void rhine_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+static int rhine_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 {
 	struct rhine_private *rp = netdev_priv(dev);
 
@@ -1279,6 +1280,7 @@ static void rhine_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 	clear_bit(vid, rp->active_vlans);
 	rhine_update_vcam(dev);
 	spin_unlock_irq(&rp->lock);
+	return 0;
 }
 
 static void init_registers(struct net_device *dev)
@@ -2009,9 +2011,9 @@ static void netdev_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *i
 {
 	struct rhine_private *rp = netdev_priv(dev);
 
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->bus_info, pci_name(rp->pdev));
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(rp->pdev), sizeof(info->bus_info));
 }
 
 static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c
index 4535d7c..4128d6b 100644
--- a/drivers/net/ethernet/via/via-velocity.c
+++ b/drivers/net/ethernet/via/via-velocity.c
@@ -522,7 +522,7 @@ static void velocity_init_cam_filter(struct velocity_info *vptr)
 	mac_set_vlan_cam_mask(regs, vptr->vCAMmask);
 }
 
-static void velocity_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+static int velocity_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 {
 	struct velocity_info *vptr = netdev_priv(dev);
 
@@ -530,9 +530,10 @@ static void velocity_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 	set_bit(vid, vptr->active_vlans);
 	velocity_init_cam_filter(vptr);
 	spin_unlock_irq(&vptr->lock);
+	return 0;
 }
 
-static void velocity_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+static int velocity_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 {
 	struct velocity_info *vptr = netdev_priv(dev);
 
@@ -540,6 +541,7 @@ static void velocity_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid
 	clear_bit(vid, vptr->active_vlans);
 	velocity_init_cam_filter(vptr);
 	spin_unlock_irq(&vptr->lock);
+	return 0;
 }
 
 static void velocity_init_rx_ring_indexes(struct velocity_info *vptr)
@@ -3270,9 +3272,9 @@ static int velocity_set_settings(struct net_device *dev,
 static void velocity_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
 	struct velocity_info *vptr = netdev_priv(dev);
-	strcpy(info->driver, VELOCITY_NAME);
-	strcpy(info->version, VELOCITY_VERSION);
-	strcpy(info->bus_info, pci_name(vptr->pdev));
+	strlcpy(info->driver, VELOCITY_NAME, sizeof(info->driver));
+	strlcpy(info->version, VELOCITY_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, pci_name(vptr->pdev), sizeof(info->bus_info));
 }
 
 static void velocity_ethtool_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
diff --git a/drivers/net/ethernet/xilinx/ll_temac_main.c b/drivers/net/ethernet/xilinx/ll_temac_main.c
index caf3659..903a77b 100644
--- a/drivers/net/ethernet/xilinx/ll_temac_main.c
+++ b/drivers/net/ethernet/xilinx/ll_temac_main.c
@@ -114,6 +114,7 @@ void temac_indirect_out32(struct temac_local *lp, int reg, u32 value)
 		return;
 	temac_iow(lp, XTE_LSW0_OFFSET, value);
 	temac_iow(lp, XTE_CTL0_OFFSET, CNTLREG_WRITE_ENABLE_MASK | reg);
+	temac_indirect_busywait(lp);
 }
 
 /**
@@ -203,6 +204,9 @@ static void temac_dma_bd_release(struct net_device *ndev)
 	struct temac_local *lp = netdev_priv(ndev);
 	int i;
 
+	/* Reset Local Link (DMA) */
+	lp->dma_out(lp, DMA_CONTROL_REG, DMA_CONTROL_RST);
+
 	for (i = 0; i < RX_BD_NUM; i++) {
 		if (!lp->rx_skb[i])
 			break;
@@ -233,7 +237,7 @@ static int temac_dma_bd_init(struct net_device *ndev)
 	struct sk_buff *skb;
 	int i;
 
-	lp->rx_skb = kzalloc(sizeof(*lp->rx_skb) * RX_BD_NUM, GFP_KERNEL);
+	lp->rx_skb = kcalloc(RX_BD_NUM, sizeof(*lp->rx_skb), GFP_KERNEL);
 	if (!lp->rx_skb) {
 		dev_err(&ndev->dev,
 				"can't allocate memory for DMA RX buffer\n");
@@ -860,6 +864,8 @@ static int temac_open(struct net_device *ndev)
 		phy_start(lp->phy_dev);
 	}
 
+	temac_device_reset(ndev);
+
 	rc = request_irq(lp->tx_irq, ll_temac_tx_irq, 0, ndev->name, ndev);
 	if (rc)
 		goto err_tx_irq;
@@ -867,7 +873,6 @@ static int temac_open(struct net_device *ndev)
 	if (rc)
 		goto err_rx_irq;
 
-	temac_device_reset(ndev);
 	return 0;
 
  err_rx_irq:
@@ -915,12 +920,26 @@ temac_poll_controller(struct net_device *ndev)
 }
 #endif
 
+static int temac_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
+{
+	struct temac_local *lp = netdev_priv(ndev);
+
+	if (!netif_running(ndev))
+		return -EINVAL;
+
+	if (!lp->phy_dev)
+		return -EINVAL;
+
+	return phy_mii_ioctl(lp->phy_dev, rq, cmd);
+}
+
 static const struct net_device_ops temac_netdev_ops = {
 	.ndo_open = temac_open,
 	.ndo_stop = temac_stop,
 	.ndo_start_xmit = temac_start_xmit,
 	.ndo_set_mac_address = netdev_set_mac_address,
 	.ndo_validate_addr = eth_validate_addr,
+	.ndo_do_ioctl = temac_ioctl,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = temac_poll_controller,
 #endif
@@ -1162,17 +1181,7 @@ static struct platform_driver temac_of_driver = {
 	},
 };
 
-static int __init temac_init(void)
-{
-	return platform_driver_register(&temac_of_driver);
-}
-module_init(temac_init);
-
-static void __exit temac_exit(void)
-{
-	platform_driver_unregister(&temac_of_driver);
-}
-module_exit(temac_exit);
+module_platform_driver(temac_of_driver);
 
 MODULE_DESCRIPTION("Xilinx LL_TEMAC Ethernet driver");
 MODULE_AUTHOR("Yoshio Kashiwagi");
diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 8018d7d..dca6541 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -1303,27 +1303,7 @@ static struct platform_driver xemaclite_of_driver = {
 	.remove		= __devexit_p(xemaclite_of_remove),
 };
 
-/**
- * xgpiopss_init - Initial driver registration call
- *
- * Return:	0 upon success, or a negative error upon failure.
- */
-static int __init xemaclite_init(void)
-{
-	/* No kernel boot options used, we just need to register the driver */
-	return platform_driver_register(&xemaclite_of_driver);
-}
-
-/**
- * xemaclite_cleanup - Driver un-registration call
- */
-static void __exit xemaclite_cleanup(void)
-{
-	platform_driver_unregister(&xemaclite_of_driver);
-}
-
-module_init(xemaclite_init);
-module_exit(xemaclite_cleanup);
+module_platform_driver(xemaclite_of_driver);
 
 MODULE_AUTHOR("Xilinx, Inc.");
 MODULE_DESCRIPTION("Xilinx Ethernet MAC Lite driver");
diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c
index bbe8b7d..33979c3 100644
--- a/drivers/net/ethernet/xircom/xirc2ps_cs.c
+++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c
@@ -1411,7 +1411,7 @@ do_open(struct net_device *dev)
 static void netdev_get_drvinfo(struct net_device *dev,
 			       struct ethtool_drvinfo *info)
 {
-	strcpy(info->driver, "xirc2ps_cs");
+	strlcpy(info->driver, "xirc2ps_cs", sizeof(info->driver));
 	sprintf(info->bus_info, "PCMCIA 0x%lx", dev->base_addr);
 }
 
diff --git a/drivers/net/hippi/Kconfig b/drivers/net/hippi/Kconfig
index 7393eb7..95eb34f 100644
--- a/drivers/net/hippi/Kconfig
+++ b/drivers/net/hippi/Kconfig
@@ -36,4 +36,4 @@ config ROADRUNNER_LARGE_RINGS
 	  kernel code or by user space programs. Say Y here only if you have
 	  the memory.
 
-endif /* HIPPI */
+endif # HIPPI
diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c
index 46b5f5f..e05b645 100644
--- a/drivers/net/ifb.c
+++ b/drivers/net/ifb.c
@@ -164,7 +164,7 @@ static const struct net_device_ops ifb_netdev_ops = {
 	.ndo_validate_addr = eth_validate_addr,
 };
 
-#define IFB_FEATURES (NETIF_F_NO_CSUM | NETIF_F_SG  | NETIF_F_FRAGLIST	| \
+#define IFB_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG  | NETIF_F_FRAGLIST	| \
 		      NETIF_F_TSO_ECN | NETIF_F_TSO | NETIF_F_TSO6	| \
 		      NETIF_F_HIGHDMA | NETIF_F_HW_VLAN_TX)
 
diff --git a/drivers/net/irda/bfin_sir.c b/drivers/net/irda/bfin_sir.c
index 9d4ce1a..a561ae4 100644
--- a/drivers/net/irda/bfin_sir.c
+++ b/drivers/net/irda/bfin_sir.c
@@ -806,18 +806,7 @@ static struct platform_driver bfin_ir_driver = {
 	},
 };
 
-static int __init bfin_sir_init(void)
-{
-	return platform_driver_register(&bfin_ir_driver);
-}
-
-static void __exit bfin_sir_exit(void)
-{
-	platform_driver_unregister(&bfin_ir_driver);
-}
-
-module_init(bfin_sir_init);
-module_exit(bfin_sir_exit);
+module_platform_driver(bfin_ir_driver);
 
 module_param(max_rate, int, 0);
 MODULE_PARM_DESC(max_rate, "Maximum baud rate (115200, 57600, 38400, 19200, 9600)");
diff --git a/drivers/net/irda/pxaficp_ir.c b/drivers/net/irda/pxaficp_ir.c
index d0851df..81d5275 100644
--- a/drivers/net/irda/pxaficp_ir.c
+++ b/drivers/net/irda/pxaficp_ir.c
@@ -966,18 +966,7 @@ static struct platform_driver pxa_ir_driver = {
 	.resume		= pxa_irda_resume,
 };
 
-static int __init pxa_irda_init(void)
-{
-	return platform_driver_register(&pxa_ir_driver);
-}
-
-static void __exit pxa_irda_exit(void)
-{
-	platform_driver_unregister(&pxa_ir_driver);
-}
-
-module_init(pxa_irda_init);
-module_exit(pxa_irda_exit);
+module_platform_driver(pxa_ir_driver);
 
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:pxa2xx-ir");
diff --git a/drivers/net/irda/sh_irda.c b/drivers/net/irda/sh_irda.c
index d275e27..725d6b3 100644
--- a/drivers/net/irda/sh_irda.c
+++ b/drivers/net/irda/sh_irda.c
@@ -873,18 +873,7 @@ static struct platform_driver sh_irda_driver = {
 	},
 };
 
-static int __init sh_irda_init(void)
-{
-	return platform_driver_register(&sh_irda_driver);
-}
-
-static void __exit sh_irda_exit(void)
-{
-	platform_driver_unregister(&sh_irda_driver);
-}
-
-module_init(sh_irda_init);
-module_exit(sh_irda_exit);
+module_platform_driver(sh_irda_driver);
 
 MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>");
 MODULE_DESCRIPTION("SuperH IrDA driver");
diff --git a/drivers/net/irda/sh_sir.c b/drivers/net/irda/sh_sir.c
index ed7d7d6..e6661b5 100644
--- a/drivers/net/irda/sh_sir.c
+++ b/drivers/net/irda/sh_sir.c
@@ -808,18 +808,7 @@ static struct platform_driver sh_sir_driver = {
 	},
 };
 
-static int __init sh_sir_init(void)
-{
-	return platform_driver_register(&sh_sir_driver);
-}
-
-static void __exit sh_sir_exit(void)
-{
-	platform_driver_unregister(&sh_sir_driver);
-}
-
-module_init(sh_sir_init);
-module_exit(sh_sir_exit);
+module_platform_driver(sh_sir_driver);
 
 MODULE_AUTHOR("Kuninori Morimoto <morimoto.kuninori@renesas.com>");
 MODULE_DESCRIPTION("SuperH IrDA driver");
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index 4ce9e5f..b71998d 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -169,7 +169,7 @@ static void loopback_setup(struct net_device *dev)
 	dev->features 		= NETIF_F_SG | NETIF_F_FRAGLIST
 		| NETIF_F_ALL_TSO
 		| NETIF_F_UFO
-		| NETIF_F_NO_CSUM
+		| NETIF_F_HW_CSUM
 		| NETIF_F_RXCSUM
 		| NETIF_F_HIGHDMA
 		| NETIF_F_LLTX
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 7413497..f2f820c 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -26,6 +26,7 @@
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
 #include <linux/if_arp.h>
+#include <linux/if_vlan.h>
 #include <linux/if_link.h>
 #include <linux/if_macvlan.h>
 #include <net/rtnetlink.h>
@@ -520,26 +521,23 @@ static struct rtnl_link_stats64 *macvlan_dev_get_stats64(struct net_device *dev,
 	return stats;
 }
 
-static void macvlan_vlan_rx_add_vid(struct net_device *dev,
+static int macvlan_vlan_rx_add_vid(struct net_device *dev,
 				    unsigned short vid)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	struct net_device *lowerdev = vlan->lowerdev;
-	const struct net_device_ops *ops = lowerdev->netdev_ops;
 
-	if (ops->ndo_vlan_rx_add_vid)
-		ops->ndo_vlan_rx_add_vid(lowerdev, vid);
+	return vlan_vid_add(lowerdev, vid);
 }
 
-static void macvlan_vlan_rx_kill_vid(struct net_device *dev,
+static int macvlan_vlan_rx_kill_vid(struct net_device *dev,
 				     unsigned short vid)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	struct net_device *lowerdev = vlan->lowerdev;
-	const struct net_device_ops *ops = lowerdev->netdev_ops;
 
-	if (ops->ndo_vlan_rx_kill_vid)
-		ops->ndo_vlan_rx_kill_vid(lowerdev, vid);
+	vlan_vid_del(lowerdev, vid);
+	return 0;
 }
 
 static void macvlan_ethtool_get_drvinfo(struct net_device *dev,
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 1b7082d..7c88d13 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -145,8 +145,8 @@ static void macvtap_put_queue(struct macvtap_queue *q)
 	if (vlan) {
 		int index = get_slot(vlan, q);
 
-		rcu_assign_pointer(vlan->taps[index], NULL);
-		rcu_assign_pointer(q->vlan, NULL);
+		RCU_INIT_POINTER(vlan->taps[index], NULL);
+		RCU_INIT_POINTER(q->vlan, NULL);
 		sock_put(&q->sk);
 		--vlan->numvtaps;
 	}
@@ -223,8 +223,8 @@ static void macvtap_del_queues(struct net_device *dev)
 					      lockdep_is_held(&macvtap_lock));
 		if (q) {
 			qlist[j++] = q;
-			rcu_assign_pointer(vlan->taps[i], NULL);
-			rcu_assign_pointer(q->vlan, NULL);
+			RCU_INIT_POINTER(vlan->taps[i], NULL);
+			RCU_INIT_POINTER(q->vlan, NULL);
 			vlan->numvtaps--;
 		}
 	}
diff --git a/drivers/net/mii.c b/drivers/net/mii.c
index c62e781..c70c233 100644
--- a/drivers/net/mii.c
+++ b/drivers/net/mii.c
@@ -35,26 +35,11 @@
 
 static u32 mii_get_an(struct mii_if_info *mii, u16 addr)
 {
-	u32 result = 0;
 	int advert;
 
 	advert = mii->mdio_read(mii->dev, mii->phy_id, addr);
-	if (advert & LPA_LPACK)
-		result |= ADVERTISED_Autoneg;
-	if (advert & ADVERTISE_10HALF)
-		result |= ADVERTISED_10baseT_Half;
-	if (advert & ADVERTISE_10FULL)
-		result |= ADVERTISED_10baseT_Full;
-	if (advert & ADVERTISE_100HALF)
-		result |= ADVERTISED_100baseT_Half;
-	if (advert & ADVERTISE_100FULL)
-		result |= ADVERTISED_100baseT_Full;
-	if (advert & ADVERTISE_PAUSE_CAP)
-		result |= ADVERTISED_Pause;
-	if (advert & ADVERTISE_PAUSE_ASYM)
-		result |= ADVERTISED_Asym_Pause;
-
-	return result;
+
+	return mii_lpa_to_ethtool_lpa_t(advert);
 }
 
 /**
@@ -104,19 +89,14 @@ int mii_ethtool_gset(struct mii_if_info *mii, struct ethtool_cmd *ecmd)
 		ecmd->autoneg = AUTONEG_ENABLE;
 
 		ecmd->advertising |= mii_get_an(mii, MII_ADVERTISE);
-		if (ctrl1000 & ADVERTISE_1000HALF)
-			ecmd->advertising |= ADVERTISED_1000baseT_Half;
-		if (ctrl1000 & ADVERTISE_1000FULL)
-			ecmd->advertising |= ADVERTISED_1000baseT_Full;
+		if (mii->supports_gmii)
+			ecmd->advertising |=
+					mii_ctrl1000_to_ethtool_adv_t(ctrl1000);
 
 		if (bmsr & BMSR_ANEGCOMPLETE) {
 			ecmd->lp_advertising = mii_get_an(mii, MII_LPA);
-			if (stat1000 & LPA_1000HALF)
-				ecmd->lp_advertising |=
-					ADVERTISED_1000baseT_Half;
-			if (stat1000 & LPA_1000FULL)
-				ecmd->lp_advertising |=
-					ADVERTISED_1000baseT_Full;
+			ecmd->lp_advertising |=
+					mii_stat1000_to_ethtool_lpa_t(stat1000);
 		} else {
 			ecmd->lp_advertising = 0;
 		}
@@ -204,20 +184,11 @@ int mii_ethtool_sset(struct mii_if_info *mii, struct ethtool_cmd *ecmd)
 			advert2 = mii->mdio_read(dev, mii->phy_id, MII_CTRL1000);
 			tmp2 = advert2 & ~(ADVERTISE_1000HALF | ADVERTISE_1000FULL);
 		}
-		if (ecmd->advertising & ADVERTISED_10baseT_Half)
-			tmp |= ADVERTISE_10HALF;
-		if (ecmd->advertising & ADVERTISED_10baseT_Full)
-			tmp |= ADVERTISE_10FULL;
-		if (ecmd->advertising & ADVERTISED_100baseT_Half)
-			tmp |= ADVERTISE_100HALF;
-		if (ecmd->advertising & ADVERTISED_100baseT_Full)
-			tmp |= ADVERTISE_100FULL;
-		if (mii->supports_gmii) {
-			if (ecmd->advertising & ADVERTISED_1000baseT_Half)
-				tmp2 |= ADVERTISE_1000HALF;
-			if (ecmd->advertising & ADVERTISED_1000baseT_Full)
-				tmp2 |= ADVERTISE_1000FULL;
-		}
+		tmp |= ethtool_adv_to_mii_adv_t(ecmd->advertising);
+
+		if (mii->supports_gmii)
+			tmp2 |=
+			      ethtool_adv_to_mii_ctrl1000_t(ecmd->advertising);
 		if (advert != tmp) {
 			mii->mdio_write(dev, mii->phy_id, MII_ADVERTISE, tmp);
 			mii->advertising = tmp;
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index bb88e12..a702443 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -3,7 +3,7 @@
 #
 
 menuconfig PHYLIB
-	bool "PHY Device support and infrastructure"
+	tristate "PHY Device support and infrastructure"
 	depends on !S390
 	depends on NETDEVICES
 	help
diff --git a/drivers/net/phy/mdio-bitbang.c b/drivers/net/phy/mdio-bitbang.c
index 6539189..daec9b0 100644
--- a/drivers/net/phy/mdio-bitbang.c
+++ b/drivers/net/phy/mdio-bitbang.c
@@ -202,6 +202,14 @@ static int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val)
 	return 0;
 }
 
+static int mdiobb_reset(struct mii_bus *bus)
+{
+	struct mdiobb_ctrl *ctrl = bus->priv;
+	if (ctrl->reset)
+		ctrl->reset(bus);
+	return 0;
+}
+
 struct mii_bus *alloc_mdio_bitbang(struct mdiobb_ctrl *ctrl)
 {
 	struct mii_bus *bus;
@@ -214,6 +222,7 @@ struct mii_bus *alloc_mdio_bitbang(struct mdiobb_ctrl *ctrl)
 
 	bus->read = mdiobb_read;
 	bus->write = mdiobb_write;
+	bus->reset = mdiobb_reset;
 	bus->priv = ctrl;
 
 	return bus;
diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c
index 2843c90..89c5a3e 100644
--- a/drivers/net/phy/mdio-gpio.c
+++ b/drivers/net/phy/mdio-gpio.c
@@ -95,6 +95,7 @@ static struct mii_bus * __devinit mdio_gpio_bus_init(struct device *dev,
 		goto out;
 
 	bitbang->ctrl.ops = &mdio_gpio_ops;
+	bitbang->ctrl.reset = pdata->reset;
 	bitbang->mdc = pdata->mdc;
 	bitbang->mdio = pdata->mdio;
 
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 83a5a5a..f320f46 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -563,20 +563,9 @@ static int genphy_config_advert(struct phy_device *phydev)
 	if (adv < 0)
 		return adv;
 
-	adv &= ~(ADVERTISE_ALL | ADVERTISE_100BASE4 | ADVERTISE_PAUSE_CAP | 
+	adv &= ~(ADVERTISE_ALL | ADVERTISE_100BASE4 | ADVERTISE_PAUSE_CAP |
 		 ADVERTISE_PAUSE_ASYM);
-	if (advertise & ADVERTISED_10baseT_Half)
-		adv |= ADVERTISE_10HALF;
-	if (advertise & ADVERTISED_10baseT_Full)
-		adv |= ADVERTISE_10FULL;
-	if (advertise & ADVERTISED_100baseT_Half)
-		adv |= ADVERTISE_100HALF;
-	if (advertise & ADVERTISED_100baseT_Full)
-		adv |= ADVERTISE_100FULL;
-	if (advertise & ADVERTISED_Pause)
-		adv |= ADVERTISE_PAUSE_CAP;
-	if (advertise & ADVERTISED_Asym_Pause)
-		adv |= ADVERTISE_PAUSE_ASYM;
+	adv |= ethtool_adv_to_mii_adv_t(advertise);
 
 	if (adv != oldadv) {
 		err = phy_write(phydev, MII_ADVERTISE, adv);
@@ -595,10 +584,7 @@ static int genphy_config_advert(struct phy_device *phydev)
 			return adv;
 
 		adv &= ~(ADVERTISE_1000FULL | ADVERTISE_1000HALF);
-		if (advertise & SUPPORTED_1000baseT_Half)
-			adv |= ADVERTISE_1000HALF;
-		if (advertise & SUPPORTED_1000baseT_Full)
-			adv |= ADVERTISE_1000FULL;
+		adv |= ethtool_adv_to_mii_ctrl1000_t(advertise);
 
 		if (adv != oldadv) {
 			err = phy_write(phydev, MII_CTRL1000, adv);
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 89f829f..c1c9293 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -162,7 +162,7 @@ static void del_chan(struct pppox_sock *sock)
 {
 	spin_lock(&chan_lock);
 	clear_bit(sock->proto.pptp.src_addr.call_id, callid_bitmap);
-	rcu_assign_pointer(callid_sock[sock->proto.pptp.src_addr.call_id], NULL);
+	RCU_INIT_POINTER(callid_sock[sock->proto.pptp.src_addr.call_id], NULL);
 	spin_unlock(&chan_lock);
 	synchronize_rcu();
 }
@@ -423,10 +423,8 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr,
 	lock_sock(sk);
 
 	opt->src_addr = sp->sa_addr.pptp;
-	if (add_chan(po)) {
-		release_sock(sk);
+	if (add_chan(po))
 		error = -EBUSY;
-	}
 
 	release_sock(sk);
 	return error;
diff --git a/drivers/net/team/Kconfig b/drivers/net/team/Kconfig
new file mode 100644
index 0000000..248a144
--- /dev/null
+++ b/drivers/net/team/Kconfig
@@ -0,0 +1,43 @@
+menuconfig NET_TEAM
+	tristate "Ethernet team driver support (EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	---help---
+	  This allows one to create virtual interfaces that teams together
+	  multiple ethernet devices.
+
+	  Team devices can be added using the "ip" command from the
+	  iproute2 package:
+
+	  "ip link add link [ address MAC ] [ NAME ] type team"
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called team.
+
+if NET_TEAM
+
+config NET_TEAM_MODE_ROUNDROBIN
+	tristate "Round-robin mode support"
+	depends on NET_TEAM
+	---help---
+	  Basic mode where port used for transmitting packets is selected in
+	  round-robin fashion using packet counter.
+
+	  All added ports are setup to have bond's mac address.
+
+	  To compile this team mode as a module, choose M here: the module
+	  will be called team_mode_roundrobin.
+
+config NET_TEAM_MODE_ACTIVEBACKUP
+	tristate "Active-backup mode support"
+	depends on NET_TEAM
+	---help---
+	  Only one port is active at a time and the rest of ports are used
+	  for backup.
+
+	  Mac addresses of ports are not modified. Userspace is responsible
+	  to do so.
+
+	  To compile this team mode as a module, choose M here: the module
+	  will be called team_mode_activebackup.
+
+endif # NET_TEAM
diff --git a/drivers/net/team/Makefile b/drivers/net/team/Makefile
new file mode 100644
index 0000000..85f2028
--- /dev/null
+++ b/drivers/net/team/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for the network team driver
+#
+
+obj-$(CONFIG_NET_TEAM) += team.o
+obj-$(CONFIG_NET_TEAM_MODE_ROUNDROBIN) += team_mode_roundrobin.o
+obj-$(CONFIG_NET_TEAM_MODE_ACTIVEBACKUP) += team_mode_activebackup.o
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
new file mode 100644
index 0000000..ed2a862
--- /dev/null
+++ b/drivers/net/team/team.c
@@ -0,0 +1,1684 @@
+/*
+ * net/drivers/team/team.c - Network team device driver
+ * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/rcupdate.h>
+#include <linux/errno.h>
+#include <linux/ctype.h>
+#include <linux/notifier.h>
+#include <linux/netdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/if_arp.h>
+#include <linux/socket.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <net/rtnetlink.h>
+#include <net/genetlink.h>
+#include <net/netlink.h>
+#include <linux/if_team.h>
+
+#define DRV_NAME "team"
+
+
+/**********
+ * Helpers
+ **********/
+
+#define team_port_exists(dev) (dev->priv_flags & IFF_TEAM_PORT)
+
+static struct team_port *team_port_get_rcu(const struct net_device *dev)
+{
+	struct team_port *port = rcu_dereference(dev->rx_handler_data);
+
+	return team_port_exists(dev) ? port : NULL;
+}
+
+static struct team_port *team_port_get_rtnl(const struct net_device *dev)
+{
+	struct team_port *port = rtnl_dereference(dev->rx_handler_data);
+
+	return team_port_exists(dev) ? port : NULL;
+}
+
+/*
+ * Since the ability to change mac address for open port device is tested in
+ * team_port_add, this function can be called without control of return value
+ */
+static int __set_port_mac(struct net_device *port_dev,
+			  const unsigned char *dev_addr)
+{
+	struct sockaddr addr;
+
+	memcpy(addr.sa_data, dev_addr, ETH_ALEN);
+	addr.sa_family = ARPHRD_ETHER;
+	return dev_set_mac_address(port_dev, &addr);
+}
+
+int team_port_set_orig_mac(struct team_port *port)
+{
+	return __set_port_mac(port->dev, port->orig.dev_addr);
+}
+
+int team_port_set_team_mac(struct team_port *port)
+{
+	return __set_port_mac(port->dev, port->team->dev->dev_addr);
+}
+EXPORT_SYMBOL(team_port_set_team_mac);
+
+
+/*******************
+ * Options handling
+ *******************/
+
+struct team_option *__team_find_option(struct team *team, const char *opt_name)
+{
+	struct team_option *option;
+
+	list_for_each_entry(option, &team->option_list, list) {
+		if (strcmp(option->name, opt_name) == 0)
+			return option;
+	}
+	return NULL;
+}
+
+int team_options_register(struct team *team,
+			  const struct team_option *option,
+			  size_t option_count)
+{
+	int i;
+	struct team_option **dst_opts;
+	int err;
+
+	dst_opts = kzalloc(sizeof(struct team_option *) * option_count,
+			   GFP_KERNEL);
+	if (!dst_opts)
+		return -ENOMEM;
+	for (i = 0; i < option_count; i++, option++) {
+		if (__team_find_option(team, option->name)) {
+			err = -EEXIST;
+			goto rollback;
+		}
+		dst_opts[i] = kmemdup(option, sizeof(*option), GFP_KERNEL);
+		if (!dst_opts[i]) {
+			err = -ENOMEM;
+			goto rollback;
+		}
+	}
+
+	for (i = 0; i < option_count; i++)
+		list_add_tail(&dst_opts[i]->list, &team->option_list);
+
+	kfree(dst_opts);
+	return 0;
+
+rollback:
+	for (i = 0; i < option_count; i++)
+		kfree(dst_opts[i]);
+
+	kfree(dst_opts);
+	return err;
+}
+
+EXPORT_SYMBOL(team_options_register);
+
+static void __team_options_change_check(struct team *team,
+					struct team_option *changed_option);
+
+static void __team_options_unregister(struct team *team,
+				      const struct team_option *option,
+				      size_t option_count)
+{
+	int i;
+
+	for (i = 0; i < option_count; i++, option++) {
+		struct team_option *del_opt;
+
+		del_opt = __team_find_option(team, option->name);
+		if (del_opt) {
+			list_del(&del_opt->list);
+			kfree(del_opt);
+		}
+	}
+}
+
+void team_options_unregister(struct team *team,
+			     const struct team_option *option,
+			     size_t option_count)
+{
+	__team_options_unregister(team, option, option_count);
+	__team_options_change_check(team, NULL);
+}
+EXPORT_SYMBOL(team_options_unregister);
+
+static int team_option_get(struct team *team, struct team_option *option,
+			   void *arg)
+{
+	return option->getter(team, arg);
+}
+
+static int team_option_set(struct team *team, struct team_option *option,
+			   void *arg)
+{
+	int err;
+
+	err = option->setter(team, arg);
+	if (err)
+		return err;
+
+	__team_options_change_check(team, option);
+	return err;
+}
+
+/****************
+ * Mode handling
+ ****************/
+
+static LIST_HEAD(mode_list);
+static DEFINE_SPINLOCK(mode_list_lock);
+
+static struct team_mode *__find_mode(const char *kind)
+{
+	struct team_mode *mode;
+
+	list_for_each_entry(mode, &mode_list, list) {
+		if (strcmp(mode->kind, kind) == 0)
+			return mode;
+	}
+	return NULL;
+}
+
+static bool is_good_mode_name(const char *name)
+{
+	while (*name != '\0') {
+		if (!isalpha(*name) && !isdigit(*name) && *name != '_')
+			return false;
+		name++;
+	}
+	return true;
+}
+
+int team_mode_register(struct team_mode *mode)
+{
+	int err = 0;
+
+	if (!is_good_mode_name(mode->kind) ||
+	    mode->priv_size > TEAM_MODE_PRIV_SIZE)
+		return -EINVAL;
+	spin_lock(&mode_list_lock);
+	if (__find_mode(mode->kind)) {
+		err = -EEXIST;
+		goto unlock;
+	}
+	list_add_tail(&mode->list, &mode_list);
+unlock:
+	spin_unlock(&mode_list_lock);
+	return err;
+}
+EXPORT_SYMBOL(team_mode_register);
+
+int team_mode_unregister(struct team_mode *mode)
+{
+	spin_lock(&mode_list_lock);
+	list_del_init(&mode->list);
+	spin_unlock(&mode_list_lock);
+	return 0;
+}
+EXPORT_SYMBOL(team_mode_unregister);
+
+static struct team_mode *team_mode_get(const char *kind)
+{
+	struct team_mode *mode;
+
+	spin_lock(&mode_list_lock);
+	mode = __find_mode(kind);
+	if (!mode) {
+		spin_unlock(&mode_list_lock);
+		request_module("team-mode-%s", kind);
+		spin_lock(&mode_list_lock);
+		mode = __find_mode(kind);
+	}
+	if (mode)
+		if (!try_module_get(mode->owner))
+			mode = NULL;
+
+	spin_unlock(&mode_list_lock);
+	return mode;
+}
+
+static void team_mode_put(const struct team_mode *mode)
+{
+	module_put(mode->owner);
+}
+
+static bool team_dummy_transmit(struct team *team, struct sk_buff *skb)
+{
+	dev_kfree_skb_any(skb);
+	return false;
+}
+
+rx_handler_result_t team_dummy_receive(struct team *team,
+				       struct team_port *port,
+				       struct sk_buff *skb)
+{
+	return RX_HANDLER_ANOTHER;
+}
+
+static void team_adjust_ops(struct team *team)
+{
+	/*
+	 * To avoid checks in rx/tx skb paths, ensure here that non-null and
+	 * correct ops are always set.
+	 */
+
+	if (list_empty(&team->port_list) ||
+	    !team->mode || !team->mode->ops->transmit)
+		team->ops.transmit = team_dummy_transmit;
+	else
+		team->ops.transmit = team->mode->ops->transmit;
+
+	if (list_empty(&team->port_list) ||
+	    !team->mode || !team->mode->ops->receive)
+		team->ops.receive = team_dummy_receive;
+	else
+		team->ops.receive = team->mode->ops->receive;
+}
+
+/*
+ * We can benefit from the fact that it's ensured no port is present
+ * at the time of mode change. Therefore no packets are in fly so there's no
+ * need to set mode operations in any special way.
+ */
+static int __team_change_mode(struct team *team,
+			      const struct team_mode *new_mode)
+{
+	/* Check if mode was previously set and do cleanup if so */
+	if (team->mode) {
+		void (*exit_op)(struct team *team) = team->ops.exit;
+
+		/* Clear ops area so no callback is called any longer */
+		memset(&team->ops, 0, sizeof(struct team_mode_ops));
+		team_adjust_ops(team);
+
+		if (exit_op)
+			exit_op(team);
+		team_mode_put(team->mode);
+		team->mode = NULL;
+		/* zero private data area */
+		memset(&team->mode_priv, 0,
+		       sizeof(struct team) - offsetof(struct team, mode_priv));
+	}
+
+	if (!new_mode)
+		return 0;
+
+	if (new_mode->ops->init) {
+		int err;
+
+		err = new_mode->ops->init(team);
+		if (err)
+			return err;
+	}
+
+	team->mode = new_mode;
+	memcpy(&team->ops, new_mode->ops, sizeof(struct team_mode_ops));
+	team_adjust_ops(team);
+
+	return 0;
+}
+
+static int team_change_mode(struct team *team, const char *kind)
+{
+	struct team_mode *new_mode;
+	struct net_device *dev = team->dev;
+	int err;
+
+	if (!list_empty(&team->port_list)) {
+		netdev_err(dev, "No ports can be present during mode change\n");
+		return -EBUSY;
+	}
+
+	if (team->mode && strcmp(team->mode->kind, kind) == 0) {
+		netdev_err(dev, "Unable to change to the same mode the team is in\n");
+		return -EINVAL;
+	}
+
+	new_mode = team_mode_get(kind);
+	if (!new_mode) {
+		netdev_err(dev, "Mode \"%s\" not found\n", kind);
+		return -EINVAL;
+	}
+
+	err = __team_change_mode(team, new_mode);
+	if (err) {
+		netdev_err(dev, "Failed to change to mode \"%s\"\n", kind);
+		team_mode_put(new_mode);
+		return err;
+	}
+
+	netdev_info(dev, "Mode changed to \"%s\"\n", kind);
+	return 0;
+}
+
+
+/************************
+ * Rx path frame handler
+ ************************/
+
+/* note: already called with rcu_read_lock */
+static rx_handler_result_t team_handle_frame(struct sk_buff **pskb)
+{
+	struct sk_buff *skb = *pskb;
+	struct team_port *port;
+	struct team *team;
+	rx_handler_result_t res;
+
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		return RX_HANDLER_CONSUMED;
+
+	*pskb = skb;
+
+	port = team_port_get_rcu(skb->dev);
+	team = port->team;
+
+	res = team->ops.receive(team, port, skb);
+	if (res == RX_HANDLER_ANOTHER) {
+		struct team_pcpu_stats *pcpu_stats;
+
+		pcpu_stats = this_cpu_ptr(team->pcpu_stats);
+		u64_stats_update_begin(&pcpu_stats->syncp);
+		pcpu_stats->rx_packets++;
+		pcpu_stats->rx_bytes += skb->len;
+		if (skb->pkt_type == PACKET_MULTICAST)
+			pcpu_stats->rx_multicast++;
+		u64_stats_update_end(&pcpu_stats->syncp);
+
+		skb->dev = team->dev;
+	} else {
+		this_cpu_inc(team->pcpu_stats->rx_dropped);
+	}
+
+	return res;
+}
+
+
+/****************
+ * Port handling
+ ****************/
+
+static bool team_port_find(const struct team *team,
+			   const struct team_port *port)
+{
+	struct team_port *cur;
+
+	list_for_each_entry(cur, &team->port_list, list)
+		if (cur == port)
+			return true;
+	return false;
+}
+
+/*
+ * Add/delete port to the team port list. Write guarded by rtnl_lock.
+ * Takes care of correct port->index setup (might be racy).
+ */
+static void team_port_list_add_port(struct team *team,
+				    struct team_port *port)
+{
+	port->index = team->port_count++;
+	hlist_add_head_rcu(&port->hlist,
+			   team_port_index_hash(team, port->index));
+	list_add_tail_rcu(&port->list, &team->port_list);
+}
+
+static void __reconstruct_port_hlist(struct team *team, int rm_index)
+{
+	int i;
+	struct team_port *port;
+
+	for (i = rm_index + 1; i < team->port_count; i++) {
+		port = team_get_port_by_index(team, i);
+		hlist_del_rcu(&port->hlist);
+		port->index--;
+		hlist_add_head_rcu(&port->hlist,
+				   team_port_index_hash(team, port->index));
+	}
+}
+
+static void team_port_list_del_port(struct team *team,
+				   struct team_port *port)
+{
+	int rm_index = port->index;
+
+	hlist_del_rcu(&port->hlist);
+	list_del_rcu(&port->list);
+	__reconstruct_port_hlist(team, rm_index);
+	team->port_count--;
+}
+
+#define TEAM_VLAN_FEATURES (NETIF_F_ALL_CSUM | NETIF_F_SG | \
+			    NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | \
+			    NETIF_F_HIGHDMA | NETIF_F_LRO)
+
+static void __team_compute_features(struct team *team)
+{
+	struct team_port *port;
+	u32 vlan_features = TEAM_VLAN_FEATURES;
+	unsigned short max_hard_header_len = ETH_HLEN;
+
+	list_for_each_entry(port, &team->port_list, list) {
+		vlan_features = netdev_increment_features(vlan_features,
+					port->dev->vlan_features,
+					TEAM_VLAN_FEATURES);
+
+		if (port->dev->hard_header_len > max_hard_header_len)
+			max_hard_header_len = port->dev->hard_header_len;
+	}
+
+	team->dev->vlan_features = vlan_features;
+	team->dev->hard_header_len = max_hard_header_len;
+
+	netdev_change_features(team->dev);
+}
+
+static void team_compute_features(struct team *team)
+{
+	mutex_lock(&team->lock);
+	__team_compute_features(team);
+	mutex_unlock(&team->lock);
+}
+
+static int team_port_enter(struct team *team, struct team_port *port)
+{
+	int err = 0;
+
+	dev_hold(team->dev);
+	port->dev->priv_flags |= IFF_TEAM_PORT;
+	if (team->ops.port_enter) {
+		err = team->ops.port_enter(team, port);
+		if (err) {
+			netdev_err(team->dev, "Device %s failed to enter team mode\n",
+				   port->dev->name);
+			goto err_port_enter;
+		}
+	}
+
+	return 0;
+
+err_port_enter:
+	port->dev->priv_flags &= ~IFF_TEAM_PORT;
+	dev_put(team->dev);
+
+	return err;
+}
+
+static void team_port_leave(struct team *team, struct team_port *port)
+{
+	if (team->ops.port_leave)
+		team->ops.port_leave(team, port);
+	port->dev->priv_flags &= ~IFF_TEAM_PORT;
+	dev_put(team->dev);
+}
+
+static void __team_port_change_check(struct team_port *port, bool linkup);
+
+static int team_port_add(struct team *team, struct net_device *port_dev)
+{
+	struct net_device *dev = team->dev;
+	struct team_port *port;
+	char *portname = port_dev->name;
+	int err;
+
+	if (port_dev->flags & IFF_LOOPBACK ||
+	    port_dev->type != ARPHRD_ETHER) {
+		netdev_err(dev, "Device %s is of an unsupported type\n",
+			   portname);
+		return -EINVAL;
+	}
+
+	if (team_port_exists(port_dev)) {
+		netdev_err(dev, "Device %s is already a port "
+				"of a team device\n", portname);
+		return -EBUSY;
+	}
+
+	if (port_dev->flags & IFF_UP) {
+		netdev_err(dev, "Device %s is up. Set it down before adding it as a team port\n",
+			   portname);
+		return -EBUSY;
+	}
+
+	port = kzalloc(sizeof(struct team_port), GFP_KERNEL);
+	if (!port)
+		return -ENOMEM;
+
+	port->dev = port_dev;
+	port->team = team;
+
+	port->orig.mtu = port_dev->mtu;
+	err = dev_set_mtu(port_dev, dev->mtu);
+	if (err) {
+		netdev_dbg(dev, "Error %d calling dev_set_mtu\n", err);
+		goto err_set_mtu;
+	}
+
+	memcpy(port->orig.dev_addr, port_dev->dev_addr, ETH_ALEN);
+
+	err = team_port_enter(team, port);
+	if (err) {
+		netdev_err(dev, "Device %s failed to enter team mode\n",
+			   portname);
+		goto err_port_enter;
+	}
+
+	err = dev_open(port_dev);
+	if (err) {
+		netdev_dbg(dev, "Device %s opening failed\n",
+			   portname);
+		goto err_dev_open;
+	}
+
+	err = vlan_vids_add_by_dev(port_dev, dev);
+	if (err) {
+		netdev_err(dev, "Failed to add vlan ids to device %s\n",
+				portname);
+		goto err_vids_add;
+	}
+
+	err = netdev_set_master(port_dev, dev);
+	if (err) {
+		netdev_err(dev, "Device %s failed to set master\n", portname);
+		goto err_set_master;
+	}
+
+	err = netdev_rx_handler_register(port_dev, team_handle_frame,
+					 port);
+	if (err) {
+		netdev_err(dev, "Device %s failed to register rx_handler\n",
+			   portname);
+		goto err_handler_register;
+	}
+
+	team_port_list_add_port(team, port);
+	team_adjust_ops(team);
+	__team_compute_features(team);
+	__team_port_change_check(port, !!netif_carrier_ok(port_dev));
+
+	netdev_info(dev, "Port device %s added\n", portname);
+
+	return 0;
+
+err_handler_register:
+	netdev_set_master(port_dev, NULL);
+
+err_set_master:
+	vlan_vids_del_by_dev(port_dev, dev);
+
+err_vids_add:
+	dev_close(port_dev);
+
+err_dev_open:
+	team_port_leave(team, port);
+	team_port_set_orig_mac(port);
+
+err_port_enter:
+	dev_set_mtu(port_dev, port->orig.mtu);
+
+err_set_mtu:
+	kfree(port);
+
+	return err;
+}
+
+static int team_port_del(struct team *team, struct net_device *port_dev)
+{
+	struct net_device *dev = team->dev;
+	struct team_port *port;
+	char *portname = port_dev->name;
+
+	port = team_port_get_rtnl(port_dev);
+	if (!port || !team_port_find(team, port)) {
+		netdev_err(dev, "Device %s does not act as a port of this team\n",
+			   portname);
+		return -ENOENT;
+	}
+
+	__team_port_change_check(port, false);
+	team_port_list_del_port(team, port);
+	team_adjust_ops(team);
+	netdev_rx_handler_unregister(port_dev);
+	netdev_set_master(port_dev, NULL);
+	vlan_vids_del_by_dev(port_dev, dev);
+	dev_close(port_dev);
+	team_port_leave(team, port);
+	team_port_set_orig_mac(port);
+	dev_set_mtu(port_dev, port->orig.mtu);
+	synchronize_rcu();
+	kfree(port);
+	netdev_info(dev, "Port device %s removed\n", portname);
+	__team_compute_features(team);
+
+	return 0;
+}
+
+
+/*****************
+ * Net device ops
+ *****************/
+
+static const char team_no_mode_kind[] = "*NOMODE*";
+
+static int team_mode_option_get(struct team *team, void *arg)
+{
+	const char **str = arg;
+
+	*str = team->mode ? team->mode->kind : team_no_mode_kind;
+	return 0;
+}
+
+static int team_mode_option_set(struct team *team, void *arg)
+{
+	const char **str = arg;
+
+	return team_change_mode(team, *str);
+}
+
+static const struct team_option team_options[] = {
+	{
+		.name = "mode",
+		.type = TEAM_OPTION_TYPE_STRING,
+		.getter = team_mode_option_get,
+		.setter = team_mode_option_set,
+	},
+};
+
+static int team_init(struct net_device *dev)
+{
+	struct team *team = netdev_priv(dev);
+	int i;
+	int err;
+
+	team->dev = dev;
+	mutex_init(&team->lock);
+
+	team->pcpu_stats = alloc_percpu(struct team_pcpu_stats);
+	if (!team->pcpu_stats)
+		return -ENOMEM;
+
+	for (i = 0; i < TEAM_PORT_HASHENTRIES; i++)
+		INIT_HLIST_HEAD(&team->port_hlist[i]);
+	INIT_LIST_HEAD(&team->port_list);
+
+	team_adjust_ops(team);
+
+	INIT_LIST_HEAD(&team->option_list);
+	err = team_options_register(team, team_options, ARRAY_SIZE(team_options));
+	if (err)
+		goto err_options_register;
+	netif_carrier_off(dev);
+
+	return 0;
+
+err_options_register:
+	free_percpu(team->pcpu_stats);
+
+	return err;
+}
+
+static void team_uninit(struct net_device *dev)
+{
+	struct team *team = netdev_priv(dev);
+	struct team_port *port;
+	struct team_port *tmp;
+
+	mutex_lock(&team->lock);
+	list_for_each_entry_safe(port, tmp, &team->port_list, list)
+		team_port_del(team, port->dev);
+
+	__team_change_mode(team, NULL); /* cleanup */
+	__team_options_unregister(team, team_options, ARRAY_SIZE(team_options));
+	mutex_unlock(&team->lock);
+}
+
+static void team_destructor(struct net_device *dev)
+{
+	struct team *team = netdev_priv(dev);
+
+	free_percpu(team->pcpu_stats);
+	free_netdev(dev);
+}
+
+static int team_open(struct net_device *dev)
+{
+	netif_carrier_on(dev);
+	return 0;
+}
+
+static int team_close(struct net_device *dev)
+{
+	netif_carrier_off(dev);
+	return 0;
+}
+
+/*
+ * note: already called with rcu_read_lock
+ */
+static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct team *team = netdev_priv(dev);
+	bool tx_success = false;
+	unsigned int len = skb->len;
+
+	tx_success = team->ops.transmit(team, skb);
+	if (tx_success) {
+		struct team_pcpu_stats *pcpu_stats;
+
+		pcpu_stats = this_cpu_ptr(team->pcpu_stats);
+		u64_stats_update_begin(&pcpu_stats->syncp);
+		pcpu_stats->tx_packets++;
+		pcpu_stats->tx_bytes += len;
+		u64_stats_update_end(&pcpu_stats->syncp);
+	} else {
+		this_cpu_inc(team->pcpu_stats->tx_dropped);
+	}
+
+	return NETDEV_TX_OK;
+}
+
+static void team_change_rx_flags(struct net_device *dev, int change)
+{
+	struct team *team = netdev_priv(dev);
+	struct team_port *port;
+	int inc;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(port, &team->port_list, list) {
+		if (change & IFF_PROMISC) {
+			inc = dev->flags & IFF_PROMISC ? 1 : -1;
+			dev_set_promiscuity(port->dev, inc);
+		}
+		if (change & IFF_ALLMULTI) {
+			inc = dev->flags & IFF_ALLMULTI ? 1 : -1;
+			dev_set_allmulti(port->dev, inc);
+		}
+	}
+	rcu_read_unlock();
+}
+
+static void team_set_rx_mode(struct net_device *dev)
+{
+	struct team *team = netdev_priv(dev);
+	struct team_port *port;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(port, &team->port_list, list) {
+		dev_uc_sync(port->dev, dev);
+		dev_mc_sync(port->dev, dev);
+	}
+	rcu_read_unlock();
+}
+
+static int team_set_mac_address(struct net_device *dev, void *p)
+{
+	struct team *team = netdev_priv(dev);
+	struct team_port *port;
+	struct sockaddr *addr = p;
+
+	memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
+	rcu_read_lock();
+	list_for_each_entry_rcu(port, &team->port_list, list)
+		if (team->ops.port_change_mac)
+			team->ops.port_change_mac(team, port);
+	rcu_read_unlock();
+	return 0;
+}
+
+static int team_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct team *team = netdev_priv(dev);
+	struct team_port *port;
+	int err;
+
+	/*
+	 * Alhough this is reader, it's guarded by team lock. It's not possible
+	 * to traverse list in reverse under rcu_read_lock
+	 */
+	mutex_lock(&team->lock);
+	list_for_each_entry(port, &team->port_list, list) {
+		err = dev_set_mtu(port->dev, new_mtu);
+		if (err) {
+			netdev_err(dev, "Device %s failed to change mtu",
+				   port->dev->name);
+			goto unwind;
+		}
+	}
+	mutex_unlock(&team->lock);
+
+	dev->mtu = new_mtu;
+
+	return 0;
+
+unwind:
+	list_for_each_entry_continue_reverse(port, &team->port_list, list)
+		dev_set_mtu(port->dev, dev->mtu);
+	mutex_unlock(&team->lock);
+
+	return err;
+}
+
+static struct rtnl_link_stats64 *
+team_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
+{
+	struct team *team = netdev_priv(dev);
+	struct team_pcpu_stats *p;
+	u64 rx_packets, rx_bytes, rx_multicast, tx_packets, tx_bytes;
+	u32 rx_dropped = 0, tx_dropped = 0;
+	unsigned int start;
+	int i;
+
+	for_each_possible_cpu(i) {
+		p = per_cpu_ptr(team->pcpu_stats, i);
+		do {
+			start = u64_stats_fetch_begin_bh(&p->syncp);
+			rx_packets	= p->rx_packets;
+			rx_bytes	= p->rx_bytes;
+			rx_multicast	= p->rx_multicast;
+			tx_packets	= p->tx_packets;
+			tx_bytes	= p->tx_bytes;
+		} while (u64_stats_fetch_retry_bh(&p->syncp, start));
+
+		stats->rx_packets	+= rx_packets;
+		stats->rx_bytes		+= rx_bytes;
+		stats->multicast	+= rx_multicast;
+		stats->tx_packets	+= tx_packets;
+		stats->tx_bytes		+= tx_bytes;
+		/*
+		 * rx_dropped & tx_dropped are u32, updated
+		 * without syncp protection.
+		 */
+		rx_dropped	+= p->rx_dropped;
+		tx_dropped	+= p->tx_dropped;
+	}
+	stats->rx_dropped	= rx_dropped;
+	stats->tx_dropped	= tx_dropped;
+	return stats;
+}
+
+static int team_vlan_rx_add_vid(struct net_device *dev, uint16_t vid)
+{
+	struct team *team = netdev_priv(dev);
+	struct team_port *port;
+	int err;
+
+	/*
+	 * Alhough this is reader, it's guarded by team lock. It's not possible
+	 * to traverse list in reverse under rcu_read_lock
+	 */
+	mutex_lock(&team->lock);
+	list_for_each_entry(port, &team->port_list, list) {
+		err = vlan_vid_add(port->dev, vid);
+		if (err)
+			goto unwind;
+	}
+	mutex_unlock(&team->lock);
+
+	return 0;
+
+unwind:
+	list_for_each_entry_continue_reverse(port, &team->port_list, list)
+		vlan_vid_del(port->dev, vid);
+	mutex_unlock(&team->lock);
+
+	return err;
+}
+
+static int team_vlan_rx_kill_vid(struct net_device *dev, uint16_t vid)
+{
+	struct team *team = netdev_priv(dev);
+	struct team_port *port;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(port, &team->port_list, list)
+		vlan_vid_del(port->dev, vid);
+	rcu_read_unlock();
+
+	return 0;
+}
+
+static int team_add_slave(struct net_device *dev, struct net_device *port_dev)
+{
+	struct team *team = netdev_priv(dev);
+	int err;
+
+	mutex_lock(&team->lock);
+	err = team_port_add(team, port_dev);
+	mutex_unlock(&team->lock);
+	return err;
+}
+
+static int team_del_slave(struct net_device *dev, struct net_device *port_dev)
+{
+	struct team *team = netdev_priv(dev);
+	int err;
+
+	mutex_lock(&team->lock);
+	err = team_port_del(team, port_dev);
+	mutex_unlock(&team->lock);
+	return err;
+}
+
+static netdev_features_t team_fix_features(struct net_device *dev,
+					   netdev_features_t features)
+{
+	struct team_port *port;
+	struct team *team = netdev_priv(dev);
+	netdev_features_t mask;
+
+	mask = features;
+	features &= ~NETIF_F_ONE_FOR_ALL;
+	features |= NETIF_F_ALL_FOR_ALL;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(port, &team->port_list, list) {
+		features = netdev_increment_features(features,
+						     port->dev->features,
+						     mask);
+	}
+	rcu_read_unlock();
+	return features;
+}
+
+static const struct net_device_ops team_netdev_ops = {
+	.ndo_init		= team_init,
+	.ndo_uninit		= team_uninit,
+	.ndo_open		= team_open,
+	.ndo_stop		= team_close,
+	.ndo_start_xmit		= team_xmit,
+	.ndo_change_rx_flags	= team_change_rx_flags,
+	.ndo_set_rx_mode	= team_set_rx_mode,
+	.ndo_set_mac_address	= team_set_mac_address,
+	.ndo_change_mtu		= team_change_mtu,
+	.ndo_get_stats64	= team_get_stats64,
+	.ndo_vlan_rx_add_vid	= team_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid	= team_vlan_rx_kill_vid,
+	.ndo_add_slave		= team_add_slave,
+	.ndo_del_slave		= team_del_slave,
+	.ndo_fix_features	= team_fix_features,
+};
+
+
+/***********************
+ * rt netlink interface
+ ***********************/
+
+static void team_setup(struct net_device *dev)
+{
+	ether_setup(dev);
+
+	dev->netdev_ops = &team_netdev_ops;
+	dev->destructor	= team_destructor;
+	dev->tx_queue_len = 0;
+	dev->flags |= IFF_MULTICAST;
+	dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_TX_SKB_SHARING);
+
+	/*
+	 * Indicate we support unicast address filtering. That way core won't
+	 * bring us to promisc mode in case a unicast addr is added.
+	 * Let this up to underlay drivers.
+	 */
+	dev->priv_flags |= IFF_UNICAST_FLT;
+
+	dev->features |= NETIF_F_LLTX;
+	dev->features |= NETIF_F_GRO;
+	dev->hw_features = NETIF_F_HW_VLAN_TX |
+			   NETIF_F_HW_VLAN_RX |
+			   NETIF_F_HW_VLAN_FILTER;
+
+	dev->features |= dev->hw_features;
+}
+
+static int team_newlink(struct net *src_net, struct net_device *dev,
+			struct nlattr *tb[], struct nlattr *data[])
+{
+	int err;
+
+	if (tb[IFLA_ADDRESS] == NULL)
+		random_ether_addr(dev->dev_addr);
+
+	err = register_netdevice(dev);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int team_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+	if (tb[IFLA_ADDRESS]) {
+		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
+			return -EINVAL;
+		if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
+			return -EADDRNOTAVAIL;
+	}
+	return 0;
+}
+
+static struct rtnl_link_ops team_link_ops __read_mostly = {
+	.kind		= DRV_NAME,
+	.priv_size	= sizeof(struct team),
+	.setup		= team_setup,
+	.newlink	= team_newlink,
+	.validate	= team_validate,
+};
+
+
+/***********************************
+ * Generic netlink custom interface
+ ***********************************/
+
+static struct genl_family team_nl_family = {
+	.id		= GENL_ID_GENERATE,
+	.name		= TEAM_GENL_NAME,
+	.version	= TEAM_GENL_VERSION,
+	.maxattr	= TEAM_ATTR_MAX,
+	.netnsok	= true,
+};
+
+static const struct nla_policy team_nl_policy[TEAM_ATTR_MAX + 1] = {
+	[TEAM_ATTR_UNSPEC]			= { .type = NLA_UNSPEC, },
+	[TEAM_ATTR_TEAM_IFINDEX]		= { .type = NLA_U32 },
+	[TEAM_ATTR_LIST_OPTION]			= { .type = NLA_NESTED },
+	[TEAM_ATTR_LIST_PORT]			= { .type = NLA_NESTED },
+};
+
+static const struct nla_policy
+team_nl_option_policy[TEAM_ATTR_OPTION_MAX + 1] = {
+	[TEAM_ATTR_OPTION_UNSPEC]		= { .type = NLA_UNSPEC, },
+	[TEAM_ATTR_OPTION_NAME] = {
+		.type = NLA_STRING,
+		.len = TEAM_STRING_MAX_LEN,
+	},
+	[TEAM_ATTR_OPTION_CHANGED]		= { .type = NLA_FLAG },
+	[TEAM_ATTR_OPTION_TYPE]			= { .type = NLA_U8 },
+	[TEAM_ATTR_OPTION_DATA] = {
+		.type = NLA_BINARY,
+		.len = TEAM_STRING_MAX_LEN,
+	},
+};
+
+static int team_nl_cmd_noop(struct sk_buff *skb, struct genl_info *info)
+{
+	struct sk_buff *msg;
+	void *hdr;
+	int err;
+
+	msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_put(msg, info->snd_pid, info->snd_seq,
+			  &team_nl_family, 0, TEAM_CMD_NOOP);
+	if (IS_ERR(hdr)) {
+		err = PTR_ERR(hdr);
+		goto err_msg_put;
+	}
+
+	genlmsg_end(msg, hdr);
+
+	return genlmsg_unicast(genl_info_net(info), msg, info->snd_pid);
+
+err_msg_put:
+	nlmsg_free(msg);
+
+	return err;
+}
+
+/*
+ * Netlink cmd functions should be locked by following two functions.
+ * Since dev gets held here, that ensures dev won't disappear in between.
+ */
+static struct team *team_nl_team_get(struct genl_info *info)
+{
+	struct net *net = genl_info_net(info);
+	int ifindex;
+	struct net_device *dev;
+	struct team *team;
+
+	if (!info->attrs[TEAM_ATTR_TEAM_IFINDEX])
+		return NULL;
+
+	ifindex = nla_get_u32(info->attrs[TEAM_ATTR_TEAM_IFINDEX]);
+	dev = dev_get_by_index(net, ifindex);
+	if (!dev || dev->netdev_ops != &team_netdev_ops) {
+		if (dev)
+			dev_put(dev);
+		return NULL;
+	}
+
+	team = netdev_priv(dev);
+	mutex_lock(&team->lock);
+	return team;
+}
+
+static void team_nl_team_put(struct team *team)
+{
+	mutex_unlock(&team->lock);
+	dev_put(team->dev);
+}
+
+static int team_nl_send_generic(struct genl_info *info, struct team *team,
+				int (*fill_func)(struct sk_buff *skb,
+						 struct genl_info *info,
+						 int flags, struct team *team))
+{
+	struct sk_buff *skb;
+	int err;
+
+	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	err = fill_func(skb, info, NLM_F_ACK, team);
+	if (err < 0)
+		goto err_fill;
+
+	err = genlmsg_unicast(genl_info_net(info), skb, info->snd_pid);
+	return err;
+
+err_fill:
+	nlmsg_free(skb);
+	return err;
+}
+
+static int team_nl_fill_options_get_changed(struct sk_buff *skb,
+					    u32 pid, u32 seq, int flags,
+					    struct team *team,
+					    struct team_option *changed_option)
+{
+	struct nlattr *option_list;
+	void *hdr;
+	struct team_option *option;
+
+	hdr = genlmsg_put(skb, pid, seq, &team_nl_family, flags,
+			  TEAM_CMD_OPTIONS_GET);
+	if (IS_ERR(hdr))
+		return PTR_ERR(hdr);
+
+	NLA_PUT_U32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex);
+	option_list = nla_nest_start(skb, TEAM_ATTR_LIST_OPTION);
+	if (!option_list)
+		return -EMSGSIZE;
+
+	list_for_each_entry(option, &team->option_list, list) {
+		struct nlattr *option_item;
+		long arg;
+
+		option_item = nla_nest_start(skb, TEAM_ATTR_ITEM_OPTION);
+		if (!option_item)
+			goto nla_put_failure;
+		NLA_PUT_STRING(skb, TEAM_ATTR_OPTION_NAME, option->name);
+		if (option == changed_option)
+			NLA_PUT_FLAG(skb, TEAM_ATTR_OPTION_CHANGED);
+		switch (option->type) {
+		case TEAM_OPTION_TYPE_U32:
+			NLA_PUT_U8(skb, TEAM_ATTR_OPTION_TYPE, NLA_U32);
+			team_option_get(team, option, &arg);
+			NLA_PUT_U32(skb, TEAM_ATTR_OPTION_DATA, arg);
+			break;
+		case TEAM_OPTION_TYPE_STRING:
+			NLA_PUT_U8(skb, TEAM_ATTR_OPTION_TYPE, NLA_STRING);
+			team_option_get(team, option, &arg);
+			NLA_PUT_STRING(skb, TEAM_ATTR_OPTION_DATA,
+				       (char *) arg);
+			break;
+		default:
+			BUG();
+		}
+		nla_nest_end(skb, option_item);
+	}
+
+	nla_nest_end(skb, option_list);
+	return genlmsg_end(skb, hdr);
+
+nla_put_failure:
+	genlmsg_cancel(skb, hdr);
+	return -EMSGSIZE;
+}
+
+static int team_nl_fill_options_get(struct sk_buff *skb,
+				    struct genl_info *info, int flags,
+				    struct team *team)
+{
+	return team_nl_fill_options_get_changed(skb, info->snd_pid,
+						info->snd_seq, NLM_F_ACK,
+						team, NULL);
+}
+
+static int team_nl_cmd_options_get(struct sk_buff *skb, struct genl_info *info)
+{
+	struct team *team;
+	int err;
+
+	team = team_nl_team_get(info);
+	if (!team)
+		return -EINVAL;
+
+	err = team_nl_send_generic(info, team, team_nl_fill_options_get);
+
+	team_nl_team_put(team);
+
+	return err;
+}
+
+static int team_nl_cmd_options_set(struct sk_buff *skb, struct genl_info *info)
+{
+	struct team *team;
+	int err = 0;
+	int i;
+	struct nlattr *nl_option;
+
+	team = team_nl_team_get(info);
+	if (!team)
+		return -EINVAL;
+
+	err = -EINVAL;
+	if (!info->attrs[TEAM_ATTR_LIST_OPTION]) {
+		err = -EINVAL;
+		goto team_put;
+	}
+
+	nla_for_each_nested(nl_option, info->attrs[TEAM_ATTR_LIST_OPTION], i) {
+		struct nlattr *mode_attrs[TEAM_ATTR_OPTION_MAX + 1];
+		enum team_option_type opt_type;
+		struct team_option *option;
+		char *opt_name;
+		bool opt_found = false;
+
+		if (nla_type(nl_option) != TEAM_ATTR_ITEM_OPTION) {
+			err = -EINVAL;
+			goto team_put;
+		}
+		err = nla_parse_nested(mode_attrs, TEAM_ATTR_OPTION_MAX,
+				       nl_option, team_nl_option_policy);
+		if (err)
+			goto team_put;
+		if (!mode_attrs[TEAM_ATTR_OPTION_NAME] ||
+		    !mode_attrs[TEAM_ATTR_OPTION_TYPE] ||
+		    !mode_attrs[TEAM_ATTR_OPTION_DATA]) {
+			err = -EINVAL;
+			goto team_put;
+		}
+		switch (nla_get_u8(mode_attrs[TEAM_ATTR_OPTION_TYPE])) {
+		case NLA_U32:
+			opt_type = TEAM_OPTION_TYPE_U32;
+			break;
+		case NLA_STRING:
+			opt_type = TEAM_OPTION_TYPE_STRING;
+			break;
+		default:
+			goto team_put;
+		}
+
+		opt_name = nla_data(mode_attrs[TEAM_ATTR_OPTION_NAME]);
+		list_for_each_entry(option, &team->option_list, list) {
+			long arg;
+			struct nlattr *opt_data_attr;
+
+			if (option->type != opt_type ||
+			    strcmp(option->name, opt_name))
+				continue;
+			opt_found = true;
+			opt_data_attr = mode_attrs[TEAM_ATTR_OPTION_DATA];
+			switch (opt_type) {
+			case TEAM_OPTION_TYPE_U32:
+				arg = nla_get_u32(opt_data_attr);
+				break;
+			case TEAM_OPTION_TYPE_STRING:
+				arg = (long) nla_data(opt_data_attr);
+				break;
+			default:
+				BUG();
+			}
+			err = team_option_set(team, option, &arg);
+			if (err)
+				goto team_put;
+		}
+		if (!opt_found) {
+			err = -ENOENT;
+			goto team_put;
+		}
+	}
+
+team_put:
+	team_nl_team_put(team);
+
+	return err;
+}
+
+static int team_nl_fill_port_list_get_changed(struct sk_buff *skb,
+					      u32 pid, u32 seq, int flags,
+					      struct team *team,
+					      struct team_port *changed_port)
+{
+	struct nlattr *port_list;
+	void *hdr;
+	struct team_port *port;
+
+	hdr = genlmsg_put(skb, pid, seq, &team_nl_family, flags,
+			  TEAM_CMD_PORT_LIST_GET);
+	if (IS_ERR(hdr))
+		return PTR_ERR(hdr);
+
+	NLA_PUT_U32(skb, TEAM_ATTR_TEAM_IFINDEX, team->dev->ifindex);
+	port_list = nla_nest_start(skb, TEAM_ATTR_LIST_PORT);
+	if (!port_list)
+		return -EMSGSIZE;
+
+	list_for_each_entry(port, &team->port_list, list) {
+		struct nlattr *port_item;
+
+		port_item = nla_nest_start(skb, TEAM_ATTR_ITEM_PORT);
+		if (!port_item)
+			goto nla_put_failure;
+		NLA_PUT_U32(skb, TEAM_ATTR_PORT_IFINDEX, port->dev->ifindex);
+		if (port == changed_port)
+			NLA_PUT_FLAG(skb, TEAM_ATTR_PORT_CHANGED);
+		if (port->linkup)
+			NLA_PUT_FLAG(skb, TEAM_ATTR_PORT_LINKUP);
+		NLA_PUT_U32(skb, TEAM_ATTR_PORT_SPEED, port->speed);
+		NLA_PUT_U8(skb, TEAM_ATTR_PORT_DUPLEX, port->duplex);
+		nla_nest_end(skb, port_item);
+	}
+
+	nla_nest_end(skb, port_list);
+	return genlmsg_end(skb, hdr);
+
+nla_put_failure:
+	genlmsg_cancel(skb, hdr);
+	return -EMSGSIZE;
+}
+
+static int team_nl_fill_port_list_get(struct sk_buff *skb,
+				      struct genl_info *info, int flags,
+				      struct team *team)
+{
+	return team_nl_fill_port_list_get_changed(skb, info->snd_pid,
+						  info->snd_seq, NLM_F_ACK,
+						  team, NULL);
+}
+
+static int team_nl_cmd_port_list_get(struct sk_buff *skb,
+				     struct genl_info *info)
+{
+	struct team *team;
+	int err;
+
+	team = team_nl_team_get(info);
+	if (!team)
+		return -EINVAL;
+
+	err = team_nl_send_generic(info, team, team_nl_fill_port_list_get);
+
+	team_nl_team_put(team);
+
+	return err;
+}
+
+static struct genl_ops team_nl_ops[] = {
+	{
+		.cmd = TEAM_CMD_NOOP,
+		.doit = team_nl_cmd_noop,
+		.policy = team_nl_policy,
+	},
+	{
+		.cmd = TEAM_CMD_OPTIONS_SET,
+		.doit = team_nl_cmd_options_set,
+		.policy = team_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = TEAM_CMD_OPTIONS_GET,
+		.doit = team_nl_cmd_options_get,
+		.policy = team_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = TEAM_CMD_PORT_LIST_GET,
+		.doit = team_nl_cmd_port_list_get,
+		.policy = team_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+	},
+};
+
+static struct genl_multicast_group team_change_event_mcgrp = {
+	.name = TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME,
+};
+
+static int team_nl_send_event_options_get(struct team *team,
+					  struct team_option *changed_option)
+{
+	struct sk_buff *skb;
+	int err;
+	struct net *net = dev_net(team->dev);
+
+	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	err = team_nl_fill_options_get_changed(skb, 0, 0, 0, team,
+					       changed_option);
+	if (err < 0)
+		goto err_fill;
+
+	err = genlmsg_multicast_netns(net, skb, 0, team_change_event_mcgrp.id,
+				      GFP_KERNEL);
+	return err;
+
+err_fill:
+	nlmsg_free(skb);
+	return err;
+}
+
+static int team_nl_send_event_port_list_get(struct team_port *port)
+{
+	struct sk_buff *skb;
+	int err;
+	struct net *net = dev_net(port->team->dev);
+
+	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	err = team_nl_fill_port_list_get_changed(skb, 0, 0, 0,
+						 port->team, port);
+	if (err < 0)
+		goto err_fill;
+
+	err = genlmsg_multicast_netns(net, skb, 0, team_change_event_mcgrp.id,
+				      GFP_KERNEL);
+	return err;
+
+err_fill:
+	nlmsg_free(skb);
+	return err;
+}
+
+static int team_nl_init(void)
+{
+	int err;
+
+	err = genl_register_family_with_ops(&team_nl_family, team_nl_ops,
+					    ARRAY_SIZE(team_nl_ops));
+	if (err)
+		return err;
+
+	err = genl_register_mc_group(&team_nl_family, &team_change_event_mcgrp);
+	if (err)
+		goto err_change_event_grp_reg;
+
+	return 0;
+
+err_change_event_grp_reg:
+	genl_unregister_family(&team_nl_family);
+
+	return err;
+}
+
+static void team_nl_fini(void)
+{
+	genl_unregister_family(&team_nl_family);
+}
+
+
+/******************
+ * Change checkers
+ ******************/
+
+static void __team_options_change_check(struct team *team,
+					struct team_option *changed_option)
+{
+	int err;
+
+	err = team_nl_send_event_options_get(team, changed_option);
+	if (err)
+		netdev_warn(team->dev, "Failed to send options change via netlink\n");
+}
+
+/* rtnl lock is held */
+static void __team_port_change_check(struct team_port *port, bool linkup)
+{
+	int err;
+
+	if (port->linkup == linkup)
+		return;
+
+	port->linkup = linkup;
+	if (linkup) {
+		struct ethtool_cmd ecmd;
+
+		err = __ethtool_get_settings(port->dev, &ecmd);
+		if (!err) {
+			port->speed = ethtool_cmd_speed(&ecmd);
+			port->duplex = ecmd.duplex;
+			goto send_event;
+		}
+	}
+	port->speed = 0;
+	port->duplex = 0;
+
+send_event:
+	err = team_nl_send_event_port_list_get(port);
+	if (err)
+		netdev_warn(port->team->dev, "Failed to send port change of device %s via netlink\n",
+			    port->dev->name);
+
+}
+
+static void team_port_change_check(struct team_port *port, bool linkup)
+{
+	struct team *team = port->team;
+
+	mutex_lock(&team->lock);
+	__team_port_change_check(port, linkup);
+	mutex_unlock(&team->lock);
+}
+
+/************************************
+ * Net device notifier event handler
+ ************************************/
+
+static int team_device_event(struct notifier_block *unused,
+			     unsigned long event, void *ptr)
+{
+	struct net_device *dev = (struct net_device *) ptr;
+	struct team_port *port;
+
+	port = team_port_get_rtnl(dev);
+	if (!port)
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case NETDEV_UP:
+		if (netif_carrier_ok(dev))
+			team_port_change_check(port, true);
+	case NETDEV_DOWN:
+		team_port_change_check(port, false);
+	case NETDEV_CHANGE:
+		if (netif_running(port->dev))
+			team_port_change_check(port,
+					       !!netif_carrier_ok(port->dev));
+		break;
+	case NETDEV_UNREGISTER:
+		team_del_slave(port->team->dev, dev);
+		break;
+	case NETDEV_FEAT_CHANGE:
+		team_compute_features(port->team);
+		break;
+	case NETDEV_CHANGEMTU:
+		/* Forbid to change mtu of underlaying device */
+		return NOTIFY_BAD;
+	case NETDEV_PRE_TYPE_CHANGE:
+		/* Forbid to change type of underlaying device */
+		return NOTIFY_BAD;
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block team_notifier_block __read_mostly = {
+	.notifier_call = team_device_event,
+};
+
+
+/***********************
+ * Module init and exit
+ ***********************/
+
+static int __init team_module_init(void)
+{
+	int err;
+
+	register_netdevice_notifier(&team_notifier_block);
+
+	err = rtnl_link_register(&team_link_ops);
+	if (err)
+		goto err_rtnl_reg;
+
+	err = team_nl_init();
+	if (err)
+		goto err_nl_init;
+
+	return 0;
+
+err_nl_init:
+	rtnl_link_unregister(&team_link_ops);
+
+err_rtnl_reg:
+	unregister_netdevice_notifier(&team_notifier_block);
+
+	return err;
+}
+
+static void __exit team_module_exit(void)
+{
+	team_nl_fini();
+	rtnl_link_unregister(&team_link_ops);
+	unregister_netdevice_notifier(&team_notifier_block);
+}
+
+module_init(team_module_init);
+module_exit(team_module_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Jiri Pirko <jpirko@redhat.com>");
+MODULE_DESCRIPTION("Ethernet team device driver");
+MODULE_ALIAS_RTNL_LINK(DRV_NAME);
diff --git a/drivers/net/team/team_mode_activebackup.c b/drivers/net/team/team_mode_activebackup.c
new file mode 100644
index 0000000..f4d960e
--- /dev/null
+++ b/drivers/net/team/team_mode_activebackup.c
@@ -0,0 +1,136 @@
+/*
+ * net/drivers/team/team_mode_activebackup.c - Active-backup mode for team
+ * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <net/rtnetlink.h>
+#include <linux/if_team.h>
+
+struct ab_priv {
+	struct team_port __rcu *active_port;
+};
+
+static struct ab_priv *ab_priv(struct team *team)
+{
+	return (struct ab_priv *) &team->mode_priv;
+}
+
+static rx_handler_result_t ab_receive(struct team *team, struct team_port *port,
+				      struct sk_buff *skb) {
+	struct team_port *active_port;
+
+	active_port = rcu_dereference(ab_priv(team)->active_port);
+	if (active_port != port)
+		return RX_HANDLER_EXACT;
+	return RX_HANDLER_ANOTHER;
+}
+
+static bool ab_transmit(struct team *team, struct sk_buff *skb)
+{
+	struct team_port *active_port;
+
+	active_port = rcu_dereference(ab_priv(team)->active_port);
+	if (unlikely(!active_port))
+		goto drop;
+	skb->dev = active_port->dev;
+	if (dev_queue_xmit(skb))
+		return false;
+	return true;
+
+drop:
+	dev_kfree_skb_any(skb);
+	return false;
+}
+
+static void ab_port_leave(struct team *team, struct team_port *port)
+{
+	if (ab_priv(team)->active_port == port)
+		RCU_INIT_POINTER(ab_priv(team)->active_port, NULL);
+}
+
+static int ab_active_port_get(struct team *team, void *arg)
+{
+	u32 *ifindex = arg;
+
+	*ifindex = 0;
+	if (ab_priv(team)->active_port)
+		*ifindex = ab_priv(team)->active_port->dev->ifindex;
+	return 0;
+}
+
+static int ab_active_port_set(struct team *team, void *arg)
+{
+	u32 *ifindex = arg;
+	struct team_port *port;
+
+	list_for_each_entry_rcu(port, &team->port_list, list) {
+		if (port->dev->ifindex == *ifindex) {
+			rcu_assign_pointer(ab_priv(team)->active_port, port);
+			return 0;
+		}
+	}
+	return -ENOENT;
+}
+
+static const struct team_option ab_options[] = {
+	{
+		.name = "activeport",
+		.type = TEAM_OPTION_TYPE_U32,
+		.getter = ab_active_port_get,
+		.setter = ab_active_port_set,
+	},
+};
+
+int ab_init(struct team *team)
+{
+	return team_options_register(team, ab_options, ARRAY_SIZE(ab_options));
+}
+
+void ab_exit(struct team *team)
+{
+	team_options_unregister(team, ab_options, ARRAY_SIZE(ab_options));
+}
+
+static const struct team_mode_ops ab_mode_ops = {
+	.init			= ab_init,
+	.exit			= ab_exit,
+	.receive		= ab_receive,
+	.transmit		= ab_transmit,
+	.port_leave		= ab_port_leave,
+};
+
+static struct team_mode ab_mode = {
+	.kind		= "activebackup",
+	.owner		= THIS_MODULE,
+	.priv_size	= sizeof(struct ab_priv),
+	.ops		= &ab_mode_ops,
+};
+
+static int __init ab_init_module(void)
+{
+	return team_mode_register(&ab_mode);
+}
+
+static void __exit ab_cleanup_module(void)
+{
+	team_mode_unregister(&ab_mode);
+}
+
+module_init(ab_init_module);
+module_exit(ab_cleanup_module);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Jiri Pirko <jpirko@redhat.com>");
+MODULE_DESCRIPTION("Active-backup mode for team");
+MODULE_ALIAS("team-mode-activebackup");
diff --git a/drivers/net/team/team_mode_roundrobin.c b/drivers/net/team/team_mode_roundrobin.c
new file mode 100644
index 0000000..a0e8f80
--- /dev/null
+++ b/drivers/net/team/team_mode_roundrobin.c
@@ -0,0 +1,107 @@
+/*
+ * net/drivers/team/team_mode_roundrobin.c - Round-robin mode for team
+ * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <linux/if_team.h>
+
+struct rr_priv {
+	unsigned int sent_packets;
+};
+
+static struct rr_priv *rr_priv(struct team *team)
+{
+	return (struct rr_priv *) &team->mode_priv;
+}
+
+static struct team_port *__get_first_port_up(struct team *team,
+					     struct team_port *port)
+{
+	struct team_port *cur;
+
+	if (port->linkup)
+		return port;
+	cur = port;
+	list_for_each_entry_continue_rcu(cur, &team->port_list, list)
+		if (cur->linkup)
+			return cur;
+	list_for_each_entry_rcu(cur, &team->port_list, list) {
+		if (cur == port)
+			break;
+		if (cur->linkup)
+			return cur;
+	}
+	return NULL;
+}
+
+static bool rr_transmit(struct team *team, struct sk_buff *skb)
+{
+	struct team_port *port;
+	int port_index;
+
+	port_index = rr_priv(team)->sent_packets++ % team->port_count;
+	port = team_get_port_by_index_rcu(team, port_index);
+	port = __get_first_port_up(team, port);
+	if (unlikely(!port))
+		goto drop;
+	skb->dev = port->dev;
+	if (dev_queue_xmit(skb))
+		return false;
+	return true;
+
+drop:
+	dev_kfree_skb_any(skb);
+	return false;
+}
+
+static int rr_port_enter(struct team *team, struct team_port *port)
+{
+	return team_port_set_team_mac(port);
+}
+
+static void rr_port_change_mac(struct team *team, struct team_port *port)
+{
+	team_port_set_team_mac(port);
+}
+
+static const struct team_mode_ops rr_mode_ops = {
+	.transmit		= rr_transmit,
+	.port_enter		= rr_port_enter,
+	.port_change_mac	= rr_port_change_mac,
+};
+
+static struct team_mode rr_mode = {
+	.kind		= "roundrobin",
+	.owner		= THIS_MODULE,
+	.priv_size	= sizeof(struct rr_priv),
+	.ops		= &rr_mode_ops,
+};
+
+static int __init rr_init_module(void)
+{
+	return team_mode_register(&rr_mode);
+}
+
+static void __exit rr_cleanup_module(void)
+{
+	team_mode_unregister(&rr_mode);
+}
+
+module_init(rr_init_module);
+module_exit(rr_cleanup_module);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Jiri Pirko <jpirko@redhat.com>");
+MODULE_DESCRIPTION("Round-robin mode for team");
+MODULE_ALIAS("team-mode-roundrobin");
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 7bea9c6..93c5d72 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -123,7 +123,7 @@ struct tun_struct {
 	gid_t			group;
 
 	struct net_device	*dev;
-	u32			set_features;
+	netdev_features_t	set_features;
 #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \
 			  NETIF_F_TSO6|NETIF_F_UFO)
 	struct fasync_struct	*fasync;
@@ -454,7 +454,8 @@ tun_net_change_mtu(struct net_device *dev, int new_mtu)
 	return 0;
 }
 
-static u32 tun_net_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t tun_net_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct tun_struct *tun = netdev_priv(dev);
 
@@ -1196,7 +1197,7 @@ static int tun_get_iff(struct net *net, struct tun_struct *tun,
  * privs required. */
 static int set_offload(struct tun_struct *tun, unsigned long arg)
 {
-	u32 features = 0;
+	netdev_features_t features = 0;
 
 	if (arg & TUN_F_CSUM) {
 		features |= NETIF_F_HW_CSUM;
@@ -1589,16 +1590,15 @@ static void tun_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info
 {
 	struct tun_struct *tun = netdev_priv(dev);
 
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->fw_version, "N/A");
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
 
 	switch (tun->flags & TUN_TYPE_MASK) {
 	case TUN_TUN_DEV:
-		strcpy(info->bus_info, "tun");
+		strlcpy(info->bus_info, "tun", sizeof(info->bus_info));
 		break;
 	case TUN_TAP_DEV:
-		strcpy(info->bus_info, "tap");
+		strlcpy(info->bus_info, "tap", sizeof(info->bus_info));
 		break;
 	}
 }
diff --git a/drivers/net/usb/asix.c b/drivers/net/usb/asix.c
index e81e22e..e6fed4d 100644
--- a/drivers/net/usb/asix.c
+++ b/drivers/net/usb/asix.c
@@ -36,7 +36,7 @@
 #include <linux/usb/usbnet.h>
 #include <linux/slab.h>
 
-#define DRIVER_VERSION "26-Sep-2011"
+#define DRIVER_VERSION "08-Nov-2011"
 #define DRIVER_NAME "asix"
 
 /* ASIX AX8817X based USB 2.0 Ethernet Devices */
@@ -163,7 +163,7 @@
 #define MARVELL_CTRL_TXDELAY	0x0002
 #define MARVELL_CTRL_RXDELAY	0x0080
 
-#define	PHY_MODE_RTL8211CL	0x0004
+#define	PHY_MODE_RTL8211CL	0x000C
 
 /* This structure cannot exceed sizeof(unsigned long [5]) AKA 20 bytes */
 struct asix_data {
@@ -652,9 +652,17 @@ static u32 asix_get_phyid(struct usbnet *dev)
 {
 	int phy_reg;
 	u32 phy_id;
+	int i;
 
-	phy_reg = asix_mdio_read(dev->net, dev->mii.phy_id, MII_PHYSID1);
-	if (phy_reg < 0)
+	/* Poll for the rare case the FW or phy isn't ready yet.  */
+	for (i = 0; i < 100; i++) {
+		phy_reg = asix_mdio_read(dev->net, dev->mii.phy_id, MII_PHYSID1);
+		if (phy_reg != 0 && phy_reg != 0xFFFF)
+			break;
+		mdelay(1);
+	}
+
+	if (phy_reg <= 0 || phy_reg == 0xFFFF)
 		return 0;
 
 	phy_id = (phy_reg & 0xffff) << 16;
@@ -1075,7 +1083,7 @@ static const struct net_device_ops ax88772_netdev_ops = {
 
 static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf)
 {
-	int ret;
+	int ret, embd_phy;
 	struct asix_data *data = (struct asix_data *)&dev->data;
 	u8 buf[ETH_ALEN];
 	u32 phyid;
@@ -1100,16 +1108,36 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->mii.reg_num_mask = 0x1f;
 	dev->mii.phy_id = asix_get_phy_addr(dev);
 
-	phyid = asix_get_phyid(dev);
-	dbg("PHYID=0x%08x", phyid);
-
 	dev->net->netdev_ops = &ax88772_netdev_ops;
 	dev->net->ethtool_ops = &ax88772_ethtool_ops;
 
-	ret = ax88772_reset(dev);
+	embd_phy = ((dev->mii.phy_id & 0x1f) == 0x10 ? 1 : 0);
+
+	/* Reset the PHY to normal operation mode */
+	ret = asix_write_cmd(dev, AX_CMD_SW_PHY_SELECT, embd_phy, 0, 0, NULL);
+	if (ret < 0) {
+		dbg("Select PHY #1 failed: %d", ret);
+		return ret;
+	}
+
+	ret = asix_sw_reset(dev, AX_SWRESET_IPPD | AX_SWRESET_PRL);
+	if (ret < 0)
+		return ret;
+
+	msleep(150);
+
+	ret = asix_sw_reset(dev, AX_SWRESET_CLEAR);
 	if (ret < 0)
 		return ret;
 
+	msleep(150);
+
+	ret = asix_sw_reset(dev, embd_phy ? AX_SWRESET_IPRL : AX_SWRESET_PRTE);
+
+	/* Read PHYID register *AFTER* the PHY was reset properly */
+	phyid = asix_get_phyid(dev);
+	dbg("PHYID=0x%08x", phyid);
+
 	/* Asix framing packs multiple eth frames into a 2K usb bulk transfer */
 	if (dev->driver_info->flags & FLAG_FRAMING_AX) {
 		/* hard_mtu  is still the default - the device does not support
@@ -1220,6 +1248,7 @@ static int ax88178_reset(struct usbnet *dev)
 	__le16 eeprom;
 	u8 status;
 	int gpio0 = 0;
+	u32 phyid;
 
 	asix_read_cmd(dev, AX_CMD_READ_GPIOS, 0, 0, 1, &status);
 	dbg("GPIO Status: 0x%04x", status);
@@ -1235,12 +1264,13 @@ static int ax88178_reset(struct usbnet *dev)
 		data->ledmode = 0;
 		gpio0 = 1;
 	} else {
-		data->phymode = le16_to_cpu(eeprom) & 7;
+		data->phymode = le16_to_cpu(eeprom) & 0x7F;
 		data->ledmode = le16_to_cpu(eeprom) >> 8;
 		gpio0 = (le16_to_cpu(eeprom) & 0x80) ? 0 : 1;
 	}
 	dbg("GPIO0: %d, PhyMode: %d", gpio0, data->phymode);
 
+	/* Power up external GigaPHY through AX88178 GPIO pin */
 	asix_write_gpio(dev, AX_GPIO_RSE | AX_GPIO_GPO_1 | AX_GPIO_GPO1EN, 40);
 	if ((le16_to_cpu(eeprom) >> 8) != 1) {
 		asix_write_gpio(dev, 0x003c, 30);
@@ -1252,6 +1282,13 @@ static int ax88178_reset(struct usbnet *dev)
 		asix_write_gpio(dev, AX_GPIO_GPO1EN | AX_GPIO_GPO_1, 30);
 	}
 
+	/* Read PHYID register *AFTER* powering up PHY */
+	phyid = asix_get_phyid(dev);
+	dbg("PHYID=0x%08x", phyid);
+
+	/* Set AX88178 to enable MII/GMII/RGMII interface for external PHY */
+	asix_write_cmd(dev, AX_CMD_SW_PHY_SELECT, 0, 0, 0, NULL);
+
 	asix_sw_reset(dev, 0);
 	msleep(150);
 
@@ -1396,7 +1433,6 @@ static int ax88178_bind(struct usbnet *dev, struct usb_interface *intf)
 {
 	int ret;
 	u8 buf[ETH_ALEN];
-	u32 phyid;
 	struct asix_data *data = (struct asix_data *)&dev->data;
 
 	data->eeprom_len = AX88772_EEPROM_LEN;
@@ -1423,12 +1459,12 @@ static int ax88178_bind(struct usbnet *dev, struct usb_interface *intf)
 	dev->net->netdev_ops = &ax88178_netdev_ops;
 	dev->net->ethtool_ops = &ax88178_ethtool_ops;
 
-	phyid = asix_get_phyid(dev);
-	dbg("PHYID=0x%08x", phyid);
+	/* Blink LEDS so users know driver saw dongle */
+	asix_sw_reset(dev, 0);
+	msleep(150);
 
-	ret = ax88178_reset(dev);
-	if (ret < 0)
-		return ret;
+	asix_sw_reset(dev, AX_SWRESET_PRL | AX_SWRESET_IPPD);
+	msleep(150);
 
 	/* Asix framing packs multiple eth frames into a 2K usb bulk transfer */
 	if (dev->driver_info->flags & FLAG_FRAMING_AX) {
diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c
index a60d006..331e440 100644
--- a/drivers/net/usb/cdc-phonet.c
+++ b/drivers/net/usb/cdc-phonet.c
@@ -130,7 +130,7 @@ static int rx_submit(struct usbpn_dev *pnd, struct urb *req, gfp_t gfp_flags)
 	struct page *page;
 	int err;
 
-	page = __netdev_alloc_page(dev, gfp_flags);
+	page = alloc_page(gfp_flags);
 	if (!page)
 		return -ENOMEM;
 
@@ -140,7 +140,7 @@ static int rx_submit(struct usbpn_dev *pnd, struct urb *req, gfp_t gfp_flags)
 	err = usb_submit_urb(req, gfp_flags);
 	if (unlikely(err)) {
 		dev_dbg(&dev->dev, "RX submit error (%d)\n", err);
-		netdev_free_page(dev, page);
+		put_page(page);
 	}
 	return err;
 }
@@ -208,9 +208,9 @@ static void rx_complete(struct urb *req)
 	dev->stats.rx_errors++;
 resubmit:
 	if (page)
-		netdev_free_page(dev, page);
+		put_page(page);
 	if (req)
-		rx_submit(pnd, req, GFP_ATOMIC);
+		rx_submit(pnd, req, GFP_ATOMIC | __GFP_COLD);
 }
 
 static int usbpn_close(struct net_device *dev);
@@ -229,7 +229,7 @@ static int usbpn_open(struct net_device *dev)
 	for (i = 0; i < rxq_size; i++) {
 		struct urb *req = usb_alloc_urb(0, GFP_KERNEL);
 
-		if (!req || rx_submit(pnd, req, GFP_KERNEL)) {
+		if (!req || rx_submit(pnd, req, GFP_KERNEL | __GFP_COLD)) {
 			usbpn_close(dev);
 			return -ENOMEM;
 		}
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index c924ea2..99ed6eb 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -567,7 +567,7 @@ static const struct usb_device_id	products [] = {
 {
 	USB_DEVICE_AND_INTERFACE_INFO(0x1004, 0x61aa, USB_CLASS_COMM,
 			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
-	.driver_info = (unsigned long)&wwan_info,
+	.driver_info = 0,
 },
 
 /*
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index f06fb78..009dd0f 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -465,12 +465,10 @@ static int cdc_ncm_bind(struct usbnet *dev, struct usb_interface *intf)
 	int temp;
 	u8 iface_no;
 
-	ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (ctx == NULL)
 		return -ENODEV;
 
-	memset(ctx, 0, sizeof(*ctx));
-
 	init_timer(&ctx->tx_timer);
 	spin_lock_init(&ctx->mtx);
 	ctx->netdev = dev->net;
diff --git a/drivers/net/usb/lg-vl600.c b/drivers/net/usb/lg-vl600.c
index d43db32..9c26c63 100644
--- a/drivers/net/usb/lg-vl600.c
+++ b/drivers/net/usb/lg-vl600.c
@@ -144,10 +144,11 @@ static int vl600_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 	}
 
 	frame = (struct vl600_frame_hdr *) buf->data;
-	/* NOTE: Should check that frame->magic == 0x53544448?
-	 * Otherwise if we receive garbage at the beginning of the frame
-	 * we may end up allocating a huge buffer and saving all the
-	 * future incoming data into it.  */
+	/* Yes, check that frame->magic == 0x53544448 (or 0x44544d48),
+	 * otherwise we may run out of memory w/a bad packet */
+	if (ntohl(frame->magic) != 0x53544448 &&
+			ntohl(frame->magic) != 0x44544d48)
+		goto error;
 
 	if (buf->len < sizeof(*frame) ||
 			buf->len != le32_to_cpup(&frame->len)) {
@@ -296,6 +297,11 @@ encapsulate:
 	 * overwrite the remaining fields.
 	 */
 	packet = (struct vl600_pkt_hdr *) skb->data;
+	/* The VL600 wants IPv6 packets to have an IPv4 ethertype
+	 * Since this modem only supports IPv4 and IPv6, just set all
+	 * frames to 0x0800 (ETH_P_IP)
+	 */
+	packet->h_proto = htons(ETH_P_IP);
 	memset(&packet->dummy, 0, sizeof(packet->dummy));
 	packet->len = cpu_to_le32(orig_len);
 
@@ -308,21 +314,12 @@ encapsulate:
 	if (skb->len < full_len) /* Pad */
 		skb_put(skb, full_len - skb->len);
 
-	/* The VL600 wants IPv6 packets to have an IPv4 ethertype
-	 * Check if this is an IPv6 packet, and set the ethertype
-	 * to 0x800
-	 */
-	if ((skb->data[sizeof(struct vl600_pkt_hdr *) + 0x22] & 0xf0) == 0x60) {
-		skb->data[sizeof(struct vl600_pkt_hdr *) + 0x20] = 0x08;
-		skb->data[sizeof(struct vl600_pkt_hdr *) + 0x21] = 0;
-	}
-
 	return skb;
 }
 
 static const struct driver_info	vl600_info = {
 	.description	= "LG VL600 modem",
-	.flags		= FLAG_ETHER | FLAG_RX_ASSEMBLE,
+	.flags		= FLAG_RX_ASSEMBLE | FLAG_WWAN,
 	.bind		= vl600_bind,
 	.unbind		= vl600_unbind,
 	.status		= usbnet_cdc_status,
diff --git a/drivers/net/usb/smsc75xx.c b/drivers/net/usb/smsc75xx.c
index 22a7cf9..7d62c39 100644
--- a/drivers/net/usb/smsc75xx.c
+++ b/drivers/net/usb/smsc75xx.c
@@ -51,6 +51,7 @@
 #define USB_VENDOR_ID_SMSC		(0x0424)
 #define USB_PRODUCT_ID_LAN7500		(0x7500)
 #define USB_PRODUCT_ID_LAN7505		(0x7505)
+#define RXW_PADDING			2
 
 #define check_warn(ret, fmt, args...) \
 	({ if (ret < 0) netdev_warn(dev->net, fmt, ##args); })
@@ -727,7 +728,8 @@ static int smsc75xx_change_mtu(struct net_device *netdev, int new_mtu)
 }
 
 /* Enable or disable Rx checksum offload engine */
-static int smsc75xx_set_features(struct net_device *netdev, u32 features)
+static int smsc75xx_set_features(struct net_device *netdev,
+	netdev_features_t features)
 {
 	struct usbnet *dev = netdev_priv(netdev);
 	struct smsc75xx_priv *pdata = (struct smsc75xx_priv *)(dev->data[0]);
@@ -1088,13 +1090,13 @@ static int smsc75xx_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 
 		memcpy(&rx_cmd_b, skb->data, sizeof(rx_cmd_b));
 		le32_to_cpus(&rx_cmd_b);
-		skb_pull(skb, 4 + NET_IP_ALIGN);
+		skb_pull(skb, 4 + RXW_PADDING);
 
 		packet = skb->data;
 
 		/* get the packet length */
-		size = (rx_cmd_a & RX_CMD_A_LEN) - NET_IP_ALIGN;
-		align_count = (4 - ((size + NET_IP_ALIGN) % 4)) % 4;
+		size = (rx_cmd_a & RX_CMD_A_LEN) - RXW_PADDING;
+		align_count = (4 - ((size + RXW_PADDING) % 4)) % 4;
 
 		if (unlikely(rx_cmd_a & RX_CMD_A_RED)) {
 			netif_dbg(dev, rx_err, dev->net,
diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c
index eff6767..56f3894 100644
--- a/drivers/net/usb/smsc95xx.c
+++ b/drivers/net/usb/smsc95xx.c
@@ -516,7 +516,8 @@ static void smsc95xx_status(struct usbnet *dev, struct urb *urb)
 }
 
 /* Enable or disable Tx & Rx checksum offload engines */
-static int smsc95xx_set_features(struct net_device *netdev, u32 features)
+static int smsc95xx_set_features(struct net_device *netdev,
+	netdev_features_t features)
 {
 	struct usbnet *dev = netdev_priv(netdev);
 	u32 read_buf;
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index ef883e9..49f4667 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -27,8 +27,8 @@
 
 struct veth_net_stats {
 	u64			rx_packets;
-	u64			tx_packets;
 	u64			rx_bytes;
+	u64			tx_packets;
 	u64			tx_bytes;
 	u64			rx_dropped;
 	struct u64_stats_sync	syncp;
@@ -66,9 +66,8 @@ static int veth_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 
 static void veth_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 {
-	strcpy(info->driver, DRV_NAME);
-	strcpy(info->version, DRV_VERSION);
-	strcpy(info->fw_version, "N/A");
+	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
+	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
 }
 
 static void veth_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
@@ -271,7 +270,7 @@ static void veth_setup(struct net_device *dev)
 	dev->features |= NETIF_F_LLTX;
 	dev->destructor = veth_dev_free;
 
-	dev->hw_features = NETIF_F_NO_CSUM | NETIF_F_SG | NETIF_F_RXCSUM;
+	dev->hw_features = NETIF_F_HW_CSUM | NETIF_F_SG | NETIF_F_RXCSUM;
 }
 
 /*
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 6ee8410..609c51f 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -39,6 +39,7 @@ module_param(gso, bool, 0444);
 #define GOOD_COPY_LEN	128
 
 #define VIRTNET_SEND_COMMAND_SG_MAX    2
+#define VIRTNET_DRIVER_VERSION "1.0.0"
 
 struct virtnet_stats {
 	struct u64_stats_sync syncp;
@@ -699,6 +700,7 @@ static struct rtnl_link_stats64 *virtnet_stats(struct net_device *dev,
 	}
 
 	tot->tx_dropped = dev->stats.tx_dropped;
+	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
 	tot->rx_dropped = dev->stats.rx_dropped;
 	tot->rx_length_errors = dev->stats.rx_length_errors;
 	tot->rx_frame_errors = dev->stats.rx_frame_errors;
@@ -853,7 +855,7 @@ static void virtnet_set_rx_mode(struct net_device *dev)
 	kfree(buf);
 }
 
-static void virtnet_vlan_rx_add_vid(struct net_device *dev, u16 vid)
+static int virtnet_vlan_rx_add_vid(struct net_device *dev, u16 vid)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct scatterlist sg;
@@ -863,9 +865,10 @@ static void virtnet_vlan_rx_add_vid(struct net_device *dev, u16 vid)
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
 				  VIRTIO_NET_CTRL_VLAN_ADD, &sg, 1, 0))
 		dev_warn(&dev->dev, "Failed to add VLAN ID %d.\n", vid);
+	return 0;
 }
 
-static void virtnet_vlan_rx_kill_vid(struct net_device *dev, u16 vid)
+static int virtnet_vlan_rx_kill_vid(struct net_device *dev, u16 vid)
 {
 	struct virtnet_info *vi = netdev_priv(dev);
 	struct scatterlist sg;
@@ -875,6 +878,7 @@ static void virtnet_vlan_rx_kill_vid(struct net_device *dev, u16 vid)
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_VLAN,
 				  VIRTIO_NET_CTRL_VLAN_DEL, &sg, 1, 0))
 		dev_warn(&dev->dev, "Failed to kill VLAN ID %d.\n", vid);
+	return 0;
 }
 
 static void virtnet_get_ringparam(struct net_device *dev,
@@ -889,7 +893,21 @@ static void virtnet_get_ringparam(struct net_device *dev,
 
 }
 
+
+static void virtnet_get_drvinfo(struct net_device *dev,
+				struct ethtool_drvinfo *info)
+{
+	struct virtnet_info *vi = netdev_priv(dev);
+	struct virtio_device *vdev = vi->vdev;
+
+	strlcpy(info->driver, KBUILD_MODNAME, sizeof(info->driver));
+	strlcpy(info->version, VIRTNET_DRIVER_VERSION, sizeof(info->version));
+	strlcpy(info->bus_info, virtio_bus_name(vdev), sizeof(info->bus_info));
+
+}
+
 static const struct ethtool_ops virtnet_ethtool_ops = {
+	.get_drvinfo = virtnet_get_drvinfo,
 	.get_link = ethtool_op_get_link,
 	.get_ringparam = virtnet_get_ringparam,
 };
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index d96bfb1..de7fc34 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1926,7 +1926,7 @@ vmxnet3_restore_vlan(struct vmxnet3_adapter *adapter)
 }
 
 
-static void
+static int
 vmxnet3_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
@@ -1943,10 +1943,12 @@ vmxnet3_vlan_rx_add_vid(struct net_device *netdev, u16 vid)
 	}
 
 	set_bit(vid, adapter->active_vlans);
+
+	return 0;
 }
 
 
-static void
+static int
 vmxnet3_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
@@ -1963,6 +1965,8 @@ vmxnet3_vlan_rx_kill_vid(struct net_device *netdev, u16 vid)
 	}
 
 	clear_bit(vid, adapter->active_vlans);
+
+	return 0;
 }
 
 
@@ -2163,7 +2167,8 @@ vmxnet3_setup_driver_shared(struct vmxnet3_adapter *adapter)
 		rssConf->indTableSize = VMXNET3_RSS_IND_TABLE_SIZE;
 		get_random_bytes(&rssConf->hashKey[0], rssConf->hashKeySize);
 		for (i = 0; i < rssConf->indTableSize; i++)
-			rssConf->indTable[i] = i % adapter->num_rx_queues;
+			rssConf->indTable[i] = ethtool_rxfh_indir_default(
+				i, adapter->num_rx_queues);
 
 		devRead->rssConfDesc.confVer = 1;
 		devRead->rssConfDesc.confLen = sizeof(*rssConf);
diff --git a/drivers/net/vmxnet3/vmxnet3_ethtool.c b/drivers/net/vmxnet3/vmxnet3_ethtool.c
index e662cbc..a3eb75a 100644
--- a/drivers/net/vmxnet3/vmxnet3_ethtool.c
+++ b/drivers/net/vmxnet3/vmxnet3_ethtool.c
@@ -202,14 +202,9 @@ vmxnet3_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 
 	strlcpy(drvinfo->driver, vmxnet3_driver_name, sizeof(drvinfo->driver));
-	drvinfo->driver[sizeof(drvinfo->driver) - 1] = '\0';
 
 	strlcpy(drvinfo->version, VMXNET3_DRIVER_VERSION_REPORT,
 		sizeof(drvinfo->version));
-	drvinfo->driver[sizeof(drvinfo->version) - 1] = '\0';
-
-	strlcpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version));
-	drvinfo->fw_version[sizeof(drvinfo->fw_version) - 1] = '\0';
 
 	strlcpy(drvinfo->bus_info, pci_name(adapter->pdev),
 		ETHTOOL_BUSINFO_LEN);
@@ -262,11 +257,11 @@ vmxnet3_get_strings(struct net_device *netdev, u32 stringset, u8 *buf)
 	}
 }
 
-int vmxnet3_set_features(struct net_device *netdev, u32 features)
+int vmxnet3_set_features(struct net_device *netdev, netdev_features_t features)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	unsigned long flags;
-	u32 changed = features ^ netdev->features;
+	netdev_features_t changed = features ^ netdev->features;
 
 	if (changed & (NETIF_F_RXCSUM | NETIF_F_LRO | NETIF_F_HW_VLAN_RX)) {
 		if (features & NETIF_F_RXCSUM)
@@ -570,44 +565,38 @@ vmxnet3_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *info,
 }
 
 #ifdef VMXNET3_RSS
+static u32
+vmxnet3_get_rss_indir_size(struct net_device *netdev)
+{
+	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
+	struct UPT1_RSSConf *rssConf = adapter->rss_conf;
+
+	return rssConf->indTableSize;
+}
+
 static int
-vmxnet3_get_rss_indir(struct net_device *netdev,
-		      struct ethtool_rxfh_indir *p)
+vmxnet3_get_rss_indir(struct net_device *netdev, u32 *p)
 {
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	struct UPT1_RSSConf *rssConf = adapter->rss_conf;
-	unsigned int n = min_t(unsigned int, p->size, rssConf->indTableSize);
+	unsigned int n = rssConf->indTableSize;
 
-	p->size = rssConf->indTableSize;
 	while (n--)
-		p->ring_index[n] = rssConf->indTable[n];
+		p[n] = rssConf->indTable[n];
 	return 0;
 
 }
 
 static int
-vmxnet3_set_rss_indir(struct net_device *netdev,
-		      const struct ethtool_rxfh_indir *p)
+vmxnet3_set_rss_indir(struct net_device *netdev, const u32 *p)
 {
 	unsigned int i;
 	unsigned long flags;
 	struct vmxnet3_adapter *adapter = netdev_priv(netdev);
 	struct UPT1_RSSConf *rssConf = adapter->rss_conf;
 
-	if (p->size != rssConf->indTableSize)
-		return -EINVAL;
-	for (i = 0; i < rssConf->indTableSize; i++) {
-		/*
-		 * Return with error code if any of the queue indices
-		 * is out of range
-		 */
-		if (p->ring_index[i] < 0 ||
-		    p->ring_index[i] >= adapter->num_rx_queues)
-			return -EINVAL;
-	}
-
 	for (i = 0; i < rssConf->indTableSize; i++)
-		rssConf->indTable[i] = p->ring_index[i];
+		rssConf->indTable[i] = p[i];
 
 	spin_lock_irqsave(&adapter->cmd_lock, flags);
 	VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD,
@@ -634,6 +623,7 @@ static struct ethtool_ops vmxnet3_ethtool_ops = {
 	.set_ringparam     = vmxnet3_set_ringparam,
 	.get_rxnfc         = vmxnet3_get_rxnfc,
 #ifdef VMXNET3_RSS
+	.get_rxfh_indir_size = vmxnet3_get_rss_indir_size,
 	.get_rxfh_indir    = vmxnet3_get_rss_indir,
 	.set_rxfh_indir    = vmxnet3_set_rss_indir,
 #endif
diff --git a/drivers/net/vmxnet3/vmxnet3_int.h b/drivers/net/vmxnet3/vmxnet3_int.h
index b18eac1..ed54797 100644
--- a/drivers/net/vmxnet3/vmxnet3_int.h
+++ b/drivers/net/vmxnet3/vmxnet3_int.h
@@ -401,7 +401,7 @@ void
 vmxnet3_rq_destroy_all(struct vmxnet3_adapter *adapter);
 
 int
-vmxnet3_set_features(struct net_device *netdev, u32 features);
+vmxnet3_set_features(struct net_device *netdev, netdev_features_t features);
 
 int
 vmxnet3_create_queues(struct vmxnet3_adapter *adapter,
diff --git a/drivers/net/wimax/i2400m/usb-tx.c b/drivers/net/wimax/i2400m/usb-tx.c
index ac357ac..99ef81b 100644
--- a/drivers/net/wimax/i2400m/usb-tx.c
+++ b/drivers/net/wimax/i2400m/usb-tx.c
@@ -177,7 +177,6 @@ retry:
 static
 int i2400mu_txd(void *_i2400mu)
 {
-	int result = 0;
 	struct i2400mu *i2400mu = _i2400mu;
 	struct i2400m *i2400m = &i2400mu->i2400m;
 	struct device *dev = &i2400mu->usb_iface->dev;
@@ -208,16 +207,14 @@ int i2400mu_txd(void *_i2400mu)
 		/* Yeah, we ignore errors ... not much we can do */
 		i2400mu_tx(i2400mu, tx_msg, tx_msg_size);
 		i2400m_tx_msg_sent(i2400m);	/* ack it, advance the FIFO */
-		if (result < 0)
-			break;
 	}
 
 	spin_lock_irqsave(&i2400m->tx_lock, flags);
 	i2400mu->tx_kthread = NULL;
 	spin_unlock_irqrestore(&i2400m->tx_lock, flags);
 
-	d_fnend(4, dev, "(i2400mu %p) = %d\n", i2400mu, result);
-	return result;
+	d_fnend(4, dev, "(i2400mu %p)\n", i2400mu);
+	return 0;
 }
 
 
diff --git a/drivers/net/wireless/airo.c b/drivers/net/wireless/airo.c
index ac1176a..1c008c6 100644
--- a/drivers/net/wireless/airo.c
+++ b/drivers/net/wireless/airo.c
@@ -1418,7 +1418,7 @@ static int encapsulate(struct airo_info *ai ,etherHead *frame, MICBuffer *mic, i
 	emmh32_update(&context->seed,frame->da,ETH_ALEN * 2); // DA,SA
 	emmh32_update(&context->seed,(u8*)&mic->typelen,10); // Type/Length and Snap
 	emmh32_update(&context->seed,(u8*)&mic->seq,sizeof(mic->seq)); //SEQ
-	emmh32_update(&context->seed,frame->da + ETH_ALEN * 2,payLen); //payload
+	emmh32_update(&context->seed,(u8*)(frame + 1),payLen); //payload
 	emmh32_final(&context->seed, (u8*)&mic->mic);
 
 	/*    New Type/length ?????????? */
@@ -1506,7 +1506,7 @@ static int decapsulate(struct airo_info *ai, MICBuffer *mic, etherHead *eth, u16
 		emmh32_update(&context->seed, eth->da, ETH_ALEN*2); 
 		emmh32_update(&context->seed, (u8 *)&mic->typelen, sizeof(mic->typelen)+sizeof(mic->u.snap)); 
 		emmh32_update(&context->seed, (u8 *)&mic->seq,sizeof(mic->seq));	
-		emmh32_update(&context->seed, eth->da + ETH_ALEN*2,payLen);	
+		emmh32_update(&context->seed, (u8 *)(eth + 1),payLen);	
 		//Calculate MIC
 		emmh32_final(&context->seed, digest);
 	
diff --git a/drivers/net/wireless/ath/carl9170/main.c b/drivers/net/wireless/ath/carl9170/main.c
index f06e069..5518592 100644
--- a/drivers/net/wireless/ath/carl9170/main.c
+++ b/drivers/net/wireless/ath/carl9170/main.c
@@ -446,7 +446,7 @@ static void carl9170_op_stop(struct ieee80211_hw *hw)
 
 	mutex_lock(&ar->mutex);
 	if (IS_ACCEPTING_CMD(ar)) {
-		rcu_assign_pointer(ar->beacon_iter, NULL);
+		RCU_INIT_POINTER(ar->beacon_iter, NULL);
 
 		carl9170_led_set_state(ar, 0);
 
@@ -678,7 +678,7 @@ unlock:
 		vif_priv->active = false;
 		bitmap_release_region(&ar->vif_bitmap, vif_id, 0);
 		ar->vifs--;
-		rcu_assign_pointer(ar->vif_priv[vif_id].vif, NULL);
+		RCU_INIT_POINTER(ar->vif_priv[vif_id].vif, NULL);
 		list_del_rcu(&vif_priv->list);
 		mutex_unlock(&ar->mutex);
 		synchronize_rcu();
@@ -716,7 +716,7 @@ static void carl9170_op_remove_interface(struct ieee80211_hw *hw,
 	WARN_ON(vif_priv->enable_beacon);
 	vif_priv->enable_beacon = false;
 	list_del_rcu(&vif_priv->list);
-	rcu_assign_pointer(ar->vif_priv[id].vif, NULL);
+	RCU_INIT_POINTER(ar->vif_priv[id].vif, NULL);
 
 	if (vif == main_vif) {
 		rcu_read_unlock();
@@ -1258,7 +1258,7 @@ static int carl9170_op_sta_add(struct ieee80211_hw *hw,
 		}
 
 		for (i = 0; i < CARL9170_NUM_TID; i++)
-			rcu_assign_pointer(sta_info->agg[i], NULL);
+			RCU_INIT_POINTER(sta_info->agg[i], NULL);
 
 		sta_info->ampdu_max_len = 1 << (3 + sta->ht_cap.ampdu_factor);
 		sta_info->ht_sta = true;
@@ -1285,7 +1285,7 @@ static int carl9170_op_sta_remove(struct ieee80211_hw *hw,
 			struct carl9170_sta_tid *tid_info;
 
 			tid_info = rcu_dereference(sta_info->agg[i]);
-			rcu_assign_pointer(sta_info->agg[i], NULL);
+			RCU_INIT_POINTER(sta_info->agg[i], NULL);
 
 			if (!tid_info)
 				continue;
@@ -1398,7 +1398,7 @@ static int carl9170_op_ampdu_action(struct ieee80211_hw *hw,
 			spin_unlock_bh(&ar->tx_ampdu_list_lock);
 		}
 
-		rcu_assign_pointer(sta_info->agg[tid], NULL);
+		RCU_INIT_POINTER(sta_info->agg[tid], NULL);
 		rcu_read_unlock();
 
 		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c
index 0021e49..04fec1f 100644
--- a/drivers/net/wireless/ray_cs.c
+++ b/drivers/net/wireless/ray_cs.c
@@ -2426,7 +2426,7 @@ static void rx_authenticate(ray_dev_t *local, struct rcs __iomem *prcs,
 			    unsigned int pkt_addr, int rx_len)
 {
 	UCHAR buff[256];
-	struct rx_msg *msg = (struct rx_msg *)buff;
+	struct ray_rx_msg *msg = (struct ray_rx_msg *) buff;
 
 	del_timer(&local->timer);
 
@@ -2513,7 +2513,7 @@ static void rx_deauthenticate(ray_dev_t *local, struct rcs __iomem *prcs,
 			      unsigned int pkt_addr, int rx_len)
 {
 /*  UCHAR buff[256];
-    struct rx_msg *msg = (struct rx_msg *)buff;
+    struct ray_rx_msg *msg = (struct ray_rx_msg *) buff;
 */
 	pr_debug("Deauthentication frame received\n");
 	local->authentication_state = UNAUTHENTICATED;
diff --git a/drivers/net/wireless/rayctl.h b/drivers/net/wireless/rayctl.h
index d7646f2..3c3b98b 100644
--- a/drivers/net/wireless/rayctl.h
+++ b/drivers/net/wireless/rayctl.h
@@ -566,9 +566,9 @@ struct phy_header {
     UCHAR hdr_3;
     UCHAR hdr_4;
 };
-struct rx_msg {
+struct ray_rx_msg {
     struct mac_header mac;
-    UCHAR  var[1];
+    UCHAR  var[0];
 };
 
 struct tx_msg {
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 1825629..0b5c18f 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -165,7 +165,8 @@ static int xenvif_change_mtu(struct net_device *dev, int mtu)
 	return 0;
 }
 
-static u32 xenvif_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t xenvif_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct xenvif *vif = netdev_priv(dev);
 
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 0cb594c..639cf8a 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -395,7 +395,7 @@ static void netbk_gop_frag_copy(struct xenvif *vif, struct sk_buff *skb,
 	struct gnttab_copy *copy_gop;
 	struct netbk_rx_meta *meta;
 	/*
-	 * These variables a used iff get_page_ext returns true,
+	 * These variables are used iff get_page_ext returns true,
 	 * in which case they are guaranteed to be initialized.
 	 */
 	unsigned int uninitialized_var(group), uninitialized_var(idx);
@@ -940,8 +940,6 @@ static struct gnttab_copy *xen_netbk_get_requests(struct xen_netbk *netbk,
 		if (!page)
 			return NULL;
 
-		netbk->mmap_pages[pending_idx] = page;
-
 		gop->source.u.ref = txp->gref;
 		gop->source.domid = vif->domid;
 		gop->source.offset = txp->offset;
@@ -1021,7 +1019,7 @@ static int xen_netbk_tx_check_gop(struct xen_netbk *netbk,
 		pending_idx = *((u16 *)skb->data);
 		xen_netbk_idx_release(netbk, pending_idx);
 		for (j = start; j < i; j++) {
-			pending_idx = frag_get_pending_idx(&shinfo->frags[i]);
+			pending_idx = frag_get_pending_idx(&shinfo->frags[j]);
 			xen_netbk_idx_release(netbk, pending_idx);
 		}
 
@@ -1336,8 +1334,6 @@ static unsigned xen_netbk_tx_build_gops(struct xen_netbk *netbk)
 			continue;
 		}
 
-		netbk->mmap_pages[pending_idx] = page;
-
 		gop->source.u.ref = txreq.gref;
 		gop->source.domid = vif->domid;
 		gop->source.offset = txreq.offset;
@@ -1668,7 +1664,7 @@ static int __init netback_init(void)
 					     "netback/%u", group);
 
 		if (IS_ERR(netbk->task)) {
-			printk(KERN_ALERT "kthread_run() fails at netback\n");
+			printk(KERN_ALERT "kthread_create() fails at netback\n");
 			del_timer(&netbk->net_timer);
 			rc = PTR_ERR(netbk->task);
 			goto failed_init;
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 226faab..0a59c57 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -201,7 +201,7 @@ static void xennet_sysfs_delif(struct net_device *netdev);
 #define xennet_sysfs_delif(dev) do { } while (0)
 #endif
 
-static int xennet_can_sg(struct net_device *dev)
+static bool xennet_can_sg(struct net_device *dev)
 {
 	return dev->features & NETIF_F_SG;
 }
@@ -1190,7 +1190,8 @@ static void xennet_uninit(struct net_device *dev)
 	gnttab_free_grant_references(np->gref_rx_head);
 }
 
-static u32 xennet_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t xennet_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct netfront_info *np = netdev_priv(dev);
 	int val;
@@ -1216,7 +1217,8 @@ static u32 xennet_fix_features(struct net_device *dev, u32 features)
 	return features;
 }
 
-static int xennet_set_features(struct net_device *dev, u32 features)
+static int xennet_set_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	if (!(features & NETIF_F_SG) && dev->mtu > ETH_DATA_LEN) {
 		netdev_info(dev, "Reducing MTU because no SG offload");
@@ -1707,7 +1709,6 @@ static void netback_changed(struct xenbus_device *dev,
 	case XenbusStateInitialised:
 	case XenbusStateReconfiguring:
 	case XenbusStateReconfigured:
-	case XenbusStateConnected:
 	case XenbusStateUnknown:
 	case XenbusStateClosed:
 		break;
@@ -1718,6 +1719,9 @@ static void netback_changed(struct xenbus_device *dev,
 		if (xennet_connect(netdev) != 0)
 			break;
 		xenbus_switch_state(dev, XenbusStateConnected);
+		break;
+
+	case XenbusStateConnected:
 		netif_notify_peers(netdev);
 		break;
 
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 6d3dd39..19c0115 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -60,27 +60,27 @@ EXPORT_SYMBOL_GPL(irq_of_parse_and_map);
  */
 struct device_node *of_irq_find_parent(struct device_node *child)
 {
-	struct device_node *p, *c = child;
+	struct device_node *p;
 	const __be32 *parp;
 
-	if (!of_node_get(c))
+	if (!of_node_get(child))
 		return NULL;
 
 	do {
-		parp = of_get_property(c, "interrupt-parent", NULL);
+		parp = of_get_property(child, "interrupt-parent", NULL);
 		if (parp == NULL)
-			p = of_get_parent(c);
+			p = of_get_parent(child);
 		else {
 			if (of_irq_workarounds & OF_IMAP_NO_PHANDLE)
 				p = of_node_get(of_irq_dflt_pic);
 			else
 				p = of_find_node_by_phandle(be32_to_cpup(parp));
 		}
-		of_node_put(c);
-		c = p;
+		of_node_put(child);
+		child = p;
 	} while (p && of_get_property(p, "#interrupt-cells", NULL) == NULL);
 
-	return (p == child) ? NULL : p;
+	return p;
 }
 
 /**
@@ -424,6 +424,8 @@ void __init of_irq_init(const struct of_device_id *matches)
 
 		desc->dev = np;
 		desc->interrupt_parent = of_irq_find_parent(np);
+		if (desc->interrupt_parent == np)
+			desc->interrupt_parent = NULL;
 		list_add_tail(&desc->list, &intc_desc_list);
 	}
 
diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c
index dccd863..f8c752e 100644
--- a/drivers/oprofile/oprof.c
+++ b/drivers/oprofile/oprof.c
@@ -239,26 +239,45 @@ int oprofile_set_ulong(unsigned long *addr, unsigned long val)
 	return err;
 }
 
+static int timer_mode;
+
 static int __init oprofile_init(void)
 {
 	int err;
 
+	/* always init architecture to setup backtrace support */
 	err = oprofile_arch_init(&oprofile_ops);
-	if (err < 0 || timer) {
-		printk(KERN_INFO "oprofile: using timer interrupt.\n");
+
+	timer_mode = err || timer;	/* fall back to timer mode on errors */
+	if (timer_mode) {
+		if (!err)
+			oprofile_arch_exit();
 		err = oprofile_timer_init(&oprofile_ops);
 		if (err)
 			return err;
 	}
-	return oprofilefs_register();
+
+	err = oprofilefs_register();
+	if (!err)
+		return 0;
+
+	/* failed */
+	if (timer_mode)
+		oprofile_timer_exit();
+	else
+		oprofile_arch_exit();
+
+	return err;
 }
 
 
 static void __exit oprofile_exit(void)
 {
-	oprofile_timer_exit();
 	oprofilefs_unregister();
-	oprofile_arch_exit();
+	if (timer_mode)
+		oprofile_timer_exit();
+	else
+		oprofile_arch_exit();
 }
 
 
diff --git a/drivers/oprofile/timer_int.c b/drivers/oprofile/timer_int.c
index 3ef4462..878fba1 100644
--- a/drivers/oprofile/timer_int.c
+++ b/drivers/oprofile/timer_int.c
@@ -110,6 +110,7 @@ int oprofile_timer_init(struct oprofile_operations *ops)
 	ops->start = oprofile_hrtimer_start;
 	ops->stop = oprofile_hrtimer_stop;
 	ops->cpu_type = "timer";
+	printk(KERN_INFO "oprofile: using timer interrupt.\n");
 	return 0;
 }
 
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index b6f9749..f02b523 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -76,6 +76,7 @@ config PCI_IOV
 
 config PCI_PRI
 	bool "PCI PRI support"
+	depends on PCI
 	select PCI_ATS
 	help
 	  PRI is the PCI Page Request Interface. It allows PCI devices that are
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index 596172b..fce1c54 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -459,8 +459,17 @@ static int add_bridge(acpi_handle handle)
 {
 	acpi_status status;
 	unsigned long long tmp;
+	struct acpi_pci_root *root;
 	acpi_handle dummy_handle;
 
+	/*
+	 * We shouldn't use this bridge if PCIe native hotplug control has been
+	 * granted by the BIOS for it.
+	 */
+	root = acpi_pci_find_root(handle);
+	if (root && (root->osc_control_set & OSC_PCI_EXPRESS_NATIVE_HP_CONTROL))
+		return -ENODEV;
+
 	/* if the bridge doesn't have _STA, we assume it is always there */
 	status = acpi_get_handle(handle, "_STA", &dummy_handle);
 	if (ACPI_SUCCESS(status)) {
@@ -1376,13 +1385,23 @@ static void handle_hotplug_event_func(acpi_handle handle, u32 type,
 static acpi_status
 find_root_bridges(acpi_handle handle, u32 lvl, void *context, void **rv)
 {
+	struct acpi_pci_root *root;
 	int *count = (int *)context;
 
-	if (acpi_is_root_bridge(handle)) {
-		acpi_install_notify_handler(handle, ACPI_SYSTEM_NOTIFY,
-				handle_hotplug_event_bridge, NULL);
-			(*count)++;
-	}
+	if (!acpi_is_root_bridge(handle))
+		return AE_OK;
+
+	root = acpi_pci_find_root(handle);
+	if (!root)
+		return AE_OK;
+
+	if (root->osc_control_set & OSC_PCI_EXPRESS_NATIVE_HP_CONTROL)
+		return AE_OK;
+
+	(*count)++;
+	acpi_install_notify_handler(handle, ACPI_SYSTEM_NOTIFY,
+				    handle_hotplug_event_bridge, NULL);
+
 	return AE_OK ;
 }
 
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 1e9c9aa..085dbb5 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -213,9 +213,6 @@ static int board_added(struct slot *p_slot)
 		goto err_exit;
 	}
 
-	/* Wait for 1 second after checking link training status */
-	msleep(1000);
-
 	/* Check for a power fault */
 	if (ctrl->power_fault_detected || pciehp_query_power_fault(p_slot)) {
 		ctrl_err(ctrl, "Power fault on slot %s\n", slot_name(p_slot));
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 96dc473..7b14148 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -280,6 +280,14 @@ int pciehp_check_link_status(struct controller *ctrl)
         else
                 msleep(1000);
 
+	/*
+	 * Need to wait for 1000 ms after Data Link Layer Link Active
+	 * (DLLLA) bit reads 1b before sending configuration request.
+	 * We need it before checking Link Training (LT) bit becuase
+	 * LT is still set even after DLLLA bit is set on some platform.
+	 */
+	msleep(1000);
+
 	retval = pciehp_readw(ctrl, PCI_EXP_LNKSTA, &lnk_status);
 	if (retval) {
 		ctrl_err(ctrl, "Cannot read LNKSTATUS register\n");
@@ -294,6 +302,16 @@ int pciehp_check_link_status(struct controller *ctrl)
 		return retval;
 	}
 
+	/*
+	 * If the port supports Link speeds greater than 5.0 GT/s, we
+	 * must wait for 100 ms after Link training completes before
+	 * sending configuration request.
+	 */
+	if (ctrl->pcie->port->subordinate->max_bus_speed > PCIE_SPEED_5_0GT)
+		msleep(100);
+
+	pcie_update_link_speed(ctrl->pcie->port->subordinate, lnk_status);
+
 	return retval;
 }
 
@@ -484,7 +502,6 @@ int pciehp_power_on_slot(struct slot * slot)
 	u16 slot_cmd;
 	u16 cmd_mask;
 	u16 slot_status;
-	u16 lnk_status;
 	int retval = 0;
 
 	/* Clear sticky power-fault bit from previous power failures */
@@ -516,14 +533,6 @@ int pciehp_power_on_slot(struct slot * slot)
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_cmd);
 
-	retval = pciehp_readw(ctrl, PCI_EXP_LNKSTA, &lnk_status);
-	if (retval) {
-		ctrl_err(ctrl, "%s: Cannot read LNKSTA register\n",
-				__func__);
-		return retval;
-	}
-	pcie_update_link_speed(ctrl->pcie->port->subordinate, lnk_status);
-
 	return retval;
 }
 
diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c
index aca972b..dd7e0c5 100644
--- a/drivers/pci/hotplug/shpchp_core.c
+++ b/drivers/pci/hotplug/shpchp_core.c
@@ -278,8 +278,8 @@ static int get_adapter_status (struct hotplug_slot *hotplug_slot, u8 *value)
 
 static int is_shpc_capable(struct pci_dev *dev)
 {
-	if ((dev->vendor == PCI_VENDOR_ID_AMD) || (dev->device ==
-						PCI_DEVICE_ID_AMD_GOLAM_7450))
+	if (dev->vendor == PCI_VENDOR_ID_AMD &&
+	    dev->device == PCI_DEVICE_ID_AMD_GOLAM_7450)
 		return 1;
 	if (!pci_find_capability(dev, PCI_CAP_ID_SHPC))
 		return 0;
diff --git a/drivers/pci/hotplug/shpchp_hpc.c b/drivers/pci/hotplug/shpchp_hpc.c
index 36547f0..75ba231 100644
--- a/drivers/pci/hotplug/shpchp_hpc.c
+++ b/drivers/pci/hotplug/shpchp_hpc.c
@@ -944,8 +944,8 @@ int shpc_init(struct controller *ctrl, struct pci_dev *pdev)
 	ctrl->pci_dev = pdev;  /* pci_dev of the P2P bridge */
 	ctrl_dbg(ctrl, "Hotplug Controller:\n");
 
-	if ((pdev->vendor == PCI_VENDOR_ID_AMD) || (pdev->device ==
-				PCI_DEVICE_ID_AMD_GOLAM_7450)) {
+	if (pdev->vendor == PCI_VENDOR_ID_AMD &&
+	    pdev->device == PCI_DEVICE_ID_AMD_GOLAM_7450) {
 		/* amd shpc driver doesn't use Base Offset; assume 0 */
 		ctrl->mmio_base = pci_resource_start(pdev, 0);
 		ctrl->mmio_size = pci_resource_len(pdev, 0);
diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c
index a43cfd9..d93e962 100644
--- a/drivers/platform/x86/dell-laptop.c
+++ b/drivers/platform/x86/dell-laptop.c
@@ -589,14 +589,14 @@ static const struct backlight_ops dell_ops = {
 	.update_status  = dell_send_intensity,
 };
 
-static void touchpad_led_on()
+static void touchpad_led_on(void)
 {
 	int command = 0x97;
 	char data = 1;
 	i8042_command(&data, command | 1 << 12);
 }
 
-static void touchpad_led_off()
+static void touchpad_led_off(void)
 {
 	int command = 0x97;
 	char data = 2;
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index 13ef8c3..dcdc1f4 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -121,6 +121,7 @@ struct toshiba_acpi_dev {
 	int illumination_supported:1;
 	int video_supported:1;
 	int fan_supported:1;
+	int system_event_supported:1;
 
 	struct mutex mutex;
 };
@@ -724,7 +725,7 @@ static int keys_proc_show(struct seq_file *m, void *v)
 	u32 hci_result;
 	u32 value;
 
-	if (!dev->key_event_valid) {
+	if (!dev->key_event_valid && dev->system_event_supported) {
 		hci_read1(dev, HCI_SYSTEM_EVENT, &value, &hci_result);
 		if (hci_result == HCI_SUCCESS) {
 			dev->key_event_valid = 1;
@@ -964,6 +965,8 @@ static int __devinit toshiba_acpi_add(struct acpi_device *acpi_dev)
 
 	/* enable event fifo */
 	hci_write1(dev, HCI_SYSTEM_EVENT, 1, &hci_result);
+	if (hci_result == HCI_SUCCESS)
+		dev->system_event_supported = 1;
 
 	props.type = BACKLIGHT_PLATFORM;
 	props.max_brightness = HCI_LCD_BRIGHTNESS_LEVELS - 1;
@@ -1032,12 +1035,15 @@ static void toshiba_acpi_notify(struct acpi_device *acpi_dev, u32 event)
 {
 	struct toshiba_acpi_dev *dev = acpi_driver_data(acpi_dev);
 	u32 hci_result, value;
+	int retries = 3;
 
-	if (event != 0x80)
+	if (!dev->system_event_supported || event != 0x80)
 		return;
+
 	do {
 		hci_read1(dev, HCI_SYSTEM_EVENT, &value, &hci_result);
-		if (hci_result == HCI_SUCCESS) {
+		switch (hci_result) {
+		case HCI_SUCCESS:
 			if (value == 0x100)
 				continue;
 			/* act on key press; ignore key release */
@@ -1049,14 +1055,19 @@ static void toshiba_acpi_notify(struct acpi_device *acpi_dev, u32 event)
 				pr_info("Unknown key %x\n",
 				       value);
 			}
-		} else if (hci_result == HCI_NOT_SUPPORTED) {
+			break;
+		case HCI_NOT_SUPPORTED:
 			/* This is a workaround for an unresolved issue on
 			 * some machines where system events sporadically
 			 * become disabled. */
 			hci_write1(dev, HCI_SYSTEM_EVENT, 1, &hci_result);
 			pr_notice("Re-enabled hotkeys\n");
+			/* fall through */
+		default:
+			retries--;
+			break;
 		}
-	} while (hci_result != HCI_EMPTY);
+	} while (retries && hci_result != HCI_EMPTY);
 }
 
 
diff --git a/drivers/power/intel_mid_battery.c b/drivers/power/intel_mid_battery.c
index cffcb7c..01fa671 100644
--- a/drivers/power/intel_mid_battery.c
+++ b/drivers/power/intel_mid_battery.c
@@ -61,7 +61,8 @@ MODULE_PARM_DESC(debug, "Flag to enable PMIC Battery debug messages.");
 #define PMIC_BATT_CHR_SBATDET_MASK	(1 << 5)
 #define PMIC_BATT_CHR_SDCLMT_MASK	(1 << 6)
 #define PMIC_BATT_CHR_SUSBOVP_MASK	(1 << 7)
-#define PMIC_BATT_CHR_EXCPT_MASK	0xC6
+#define PMIC_BATT_CHR_EXCPT_MASK	0x86
+
 #define PMIC_BATT_ADC_ACCCHRG_MASK	(1 << 31)
 #define PMIC_BATT_ADC_ACCCHRGVAL_MASK	0x7FFFFFFF
 
@@ -304,11 +305,6 @@ static void pmic_battery_read_status(struct pmic_power_module_info *pbi)
 			pbi->batt_status = POWER_SUPPLY_STATUS_NOT_CHARGING;
 			pmic_battery_log_event(BATT_EVENT_BATOVP_EXCPT);
 			batt_exception = 1;
-		} else if (r8 & PMIC_BATT_CHR_SDCLMT_MASK) {
-			pbi->batt_health = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
-			pbi->batt_status = POWER_SUPPLY_STATUS_NOT_CHARGING;
-			pmic_battery_log_event(BATT_EVENT_DCLMT_EXCPT);
-			batt_exception = 1;
 		} else if (r8 & PMIC_BATT_CHR_STEMP_MASK) {
 			pbi->batt_health = POWER_SUPPLY_HEALTH_OVERHEAT;
 			pbi->batt_status = POWER_SUPPLY_STATUS_NOT_CHARGING;
@@ -316,6 +312,10 @@ static void pmic_battery_read_status(struct pmic_power_module_info *pbi)
 			batt_exception = 1;
 		} else {
 			pbi->batt_health = POWER_SUPPLY_HEALTH_GOOD;
+			if (r8 & PMIC_BATT_CHR_SDCLMT_MASK) {
+				/* PMIC will change charging current automatically */
+				pmic_battery_log_event(BATT_EVENT_DCLMT_EXCPT);
+			}
 		}
 	}
 
diff --git a/drivers/regulator/aat2870-regulator.c b/drivers/regulator/aat2870-regulator.c
index 5abeb3a..298c6c6 100644
--- a/drivers/regulator/aat2870-regulator.c
+++ b/drivers/regulator/aat2870-regulator.c
@@ -160,7 +160,7 @@ static struct aat2870_regulator *aat2870_get_regulator(int id)
 			break;
 	}
 
-	if (!ri)
+	if (i == ARRAY_SIZE(aat2870_regulators))
 		return NULL;
 
 	ri->enable_addr = AAT2870_LDO_EN;
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 669d021..938398f 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -2799,8 +2799,8 @@ void regulator_unregister(struct regulator_dev *rdev)
 	list_del(&rdev->list);
 	if (rdev->supply)
 		regulator_put(rdev->supply);
-	device_unregister(&rdev->dev);
 	kfree(rdev->constraints);
+	device_unregister(&rdev->dev);
 	mutex_unlock(&regulator_list_mutex);
 }
 EXPORT_SYMBOL_GPL(regulator_unregister);
diff --git a/drivers/regulator/tps65910-regulator.c b/drivers/regulator/tps65910-regulator.c
index 66d2d60..b552aae 100644
--- a/drivers/regulator/tps65910-regulator.c
+++ b/drivers/regulator/tps65910-regulator.c
@@ -664,10 +664,10 @@ static int tps65910_set_voltage_dcdc(struct regulator_dev *dev,
 
 	switch (id) {
 	case TPS65910_REG_VDD1:
-		dcdc_mult = (selector / VDD1_2_NUM_VOLTS) + 1;
+		dcdc_mult = (selector / VDD1_2_NUM_VOLT_FINE) + 1;
 		if (dcdc_mult == 1)
 			dcdc_mult--;
-		vsel = (selector % VDD1_2_NUM_VOLTS) + 3;
+		vsel = (selector % VDD1_2_NUM_VOLT_FINE) + 3;
 
 		tps65910_modify_bits(pmic, TPS65910_VDD1,
 				(dcdc_mult << VDD1_VGAIN_SEL_SHIFT),
@@ -675,10 +675,10 @@ static int tps65910_set_voltage_dcdc(struct regulator_dev *dev,
 		tps65910_reg_write(pmic, TPS65910_VDD1_OP, vsel);
 		break;
 	case TPS65910_REG_VDD2:
-		dcdc_mult = (selector / VDD1_2_NUM_VOLTS) + 1;
+		dcdc_mult = (selector / VDD1_2_NUM_VOLT_FINE) + 1;
 		if (dcdc_mult == 1)
 			dcdc_mult--;
-		vsel = (selector % VDD1_2_NUM_VOLTS) + 3;
+		vsel = (selector % VDD1_2_NUM_VOLT_FINE) + 3;
 
 		tps65910_modify_bits(pmic, TPS65910_VDD2,
 				(dcdc_mult << VDD2_VGAIN_SEL_SHIFT),
@@ -756,9 +756,9 @@ static int tps65910_list_voltage_dcdc(struct regulator_dev *dev,
 	switch (id) {
 	case TPS65910_REG_VDD1:
 	case TPS65910_REG_VDD2:
-		mult = (selector / VDD1_2_NUM_VOLTS) + 1;
+		mult = (selector / VDD1_2_NUM_VOLT_FINE) + 1;
 		volt = VDD1_2_MIN_VOLT +
-				(selector % VDD1_2_NUM_VOLTS) * VDD1_2_OFFSET;
+				(selector % VDD1_2_NUM_VOLT_FINE) * VDD1_2_OFFSET;
 		break;
 	case TPS65911_REG_VDDCTRL:
 		volt = VDDCTRL_MIN_VOLT + (selector * VDDCTRL_OFFSET);
@@ -947,6 +947,8 @@ static __devinit int tps65910_probe(struct platform_device *pdev)
 
 		if (i == TPS65910_REG_VDD1 || i == TPS65910_REG_VDD2) {
 			pmic->desc[i].ops = &tps65910_ops_dcdc;
+			pmic->desc[i].n_voltages = VDD1_2_NUM_VOLT_FINE *
+							VDD1_2_NUM_VOLT_COARSE;
 		} else if (i == TPS65910_REG_VDD3) {
 			if (tps65910_chip_id(tps65910) == TPS65910)
 				pmic->desc[i].ops = &tps65910_ops_vdd3;
diff --git a/drivers/regulator/twl-regulator.c b/drivers/regulator/twl-regulator.c
index ee8747f..11cc308 100644
--- a/drivers/regulator/twl-regulator.c
+++ b/drivers/regulator/twl-regulator.c
@@ -71,6 +71,7 @@ struct twlreg_info {
 #define VREG_TYPE		1
 #define VREG_REMAP		2
 #define VREG_DEDICATED		3	/* LDO control */
+#define VREG_VOLTAGE_SMPS_4030	9
 /* TWL6030 register offsets */
 #define VREG_TRANS		1
 #define VREG_STATE		2
@@ -514,6 +515,32 @@ static struct regulator_ops twl4030ldo_ops = {
 	.get_status	= twl4030reg_get_status,
 };
 
+static int
+twl4030smps_set_voltage(struct regulator_dev *rdev, int min_uV, int max_uV,
+			unsigned *selector)
+{
+	struct twlreg_info *info = rdev_get_drvdata(rdev);
+	int vsel = DIV_ROUND_UP(min_uV - 600000, 12500);
+
+	twlreg_write(info, TWL_MODULE_PM_RECEIVER, VREG_VOLTAGE_SMPS_4030,
+		vsel);
+	return 0;
+}
+
+static int twl4030smps_get_voltage(struct regulator_dev *rdev)
+{
+	struct twlreg_info *info = rdev_get_drvdata(rdev);
+	int vsel = twlreg_read(info, TWL_MODULE_PM_RECEIVER,
+		VREG_VOLTAGE_SMPS_4030);
+
+	return vsel * 12500 + 600000;
+}
+
+static struct regulator_ops twl4030smps_ops = {
+	.set_voltage	= twl4030smps_set_voltage,
+	.get_voltage	= twl4030smps_get_voltage,
+};
+
 static int twl6030ldo_list_voltage(struct regulator_dev *rdev, unsigned index)
 {
 	struct twlreg_info	*info = rdev_get_drvdata(rdev);
@@ -856,6 +883,21 @@ static struct regulator_ops twlsmps_ops = {
 		}, \
 	}
 
+#define TWL4030_ADJUSTABLE_SMPS(label, offset, num, turnon_delay, remap_conf) \
+	{ \
+	.base = offset, \
+	.id = num, \
+	.delay = turnon_delay, \
+	.remap = remap_conf, \
+	.desc = { \
+		.name = #label, \
+		.id = TWL4030_REG_##label, \
+		.ops = &twl4030smps_ops, \
+		.type = REGULATOR_VOLTAGE, \
+		.owner = THIS_MODULE, \
+		}, \
+	}
+
 #define TWL6030_ADJUSTABLE_LDO(label, offset, min_mVolts, max_mVolts) { \
 	.base = offset, \
 	.min_mV = min_mVolts, \
@@ -947,8 +989,8 @@ static struct twlreg_info twl_regs[] = {
 	TWL4030_ADJUSTABLE_LDO(VINTANA2, 0x43, 12, 100, 0x08),
 	TWL4030_FIXED_LDO(VINTDIG, 0x47, 1500, 13, 100, 0x08),
 	TWL4030_ADJUSTABLE_LDO(VIO, 0x4b, 14, 1000, 0x08),
-	TWL4030_ADJUSTABLE_LDO(VDD1, 0x55, 15, 1000, 0x08),
-	TWL4030_ADJUSTABLE_LDO(VDD2, 0x63, 16, 1000, 0x08),
+	TWL4030_ADJUSTABLE_SMPS(VDD1, 0x55, 15, 1000, 0x08),
+	TWL4030_ADJUSTABLE_SMPS(VDD2, 0x63, 16, 1000, 0x08),
 	TWL4030_FIXED_LDO(VUSB1V5, 0x71, 1500, 17, 100, 0x08),
 	TWL4030_FIXED_LDO(VUSB1V8, 0x74, 1800, 18, 100, 0x08),
 	TWL4030_FIXED_LDO(VUSB3V1, 0x77, 3100, 19, 150, 0x08),
diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c
index e8326f2..dc4c274 100644
--- a/drivers/rtc/class.c
+++ b/drivers/rtc/class.c
@@ -63,7 +63,7 @@ static int rtc_suspend(struct device *dev, pm_message_t mesg)
 	 */
 	delta = timespec_sub(old_system, old_rtc);
 	delta_delta = timespec_sub(delta, old_delta);
-	if (abs(delta_delta.tv_sec)  >= 2) {
+	if (delta_delta.tv_sec < -2 || delta_delta.tv_sec >= 2) {
 		/*
 		 * if delta_delta is too large, assume time correction
 		 * has occured and set old_delta to the current delta.
@@ -97,9 +97,8 @@ static int rtc_resume(struct device *dev)
 	rtc_tm_to_time(&tm, &new_rtc.tv_sec);
 	new_rtc.tv_nsec = 0;
 
-	if (new_rtc.tv_sec <= old_rtc.tv_sec) {
-		if (new_rtc.tv_sec < old_rtc.tv_sec)
-			pr_debug("%s:  time travel!\n", dev_name(&rtc->dev));
+	if (new_rtc.tv_sec < old_rtc.tv_sec) {
+		pr_debug("%s:  time travel!\n", dev_name(&rtc->dev));
 		return 0;
 	}
 
@@ -116,7 +115,8 @@ static int rtc_resume(struct device *dev)
 	sleep_time = timespec_sub(sleep_time,
 			timespec_sub(new_system, old_system));
 
-	timekeeping_inject_sleeptime(&sleep_time);
+	if (sleep_time.tv_sec >= 0)
+		timekeeping_inject_sleeptime(&sleep_time);
 	return 0;
 }
 
diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
index 8e28625..fa4d9f3 100644
--- a/drivers/rtc/interface.c
+++ b/drivers/rtc/interface.c
@@ -319,6 +319,20 @@ int rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 }
 EXPORT_SYMBOL_GPL(rtc_read_alarm);
 
+static int ___rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
+{
+	int err;
+
+	if (!rtc->ops)
+		err = -ENODEV;
+	else if (!rtc->ops->set_alarm)
+		err = -EINVAL;
+	else
+		err = rtc->ops->set_alarm(rtc->dev.parent, alarm);
+
+	return err;
+}
+
 static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 {
 	struct rtc_time tm;
@@ -342,14 +356,7 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
 	 * over right here, before we set the alarm.
 	 */
 
-	if (!rtc->ops)
-		err = -ENODEV;
-	else if (!rtc->ops->set_alarm)
-		err = -EINVAL;
-	else
-		err = rtc->ops->set_alarm(rtc->dev.parent, alarm);
-
-	return err;
+	return ___rtc_set_alarm(rtc, alarm);
 }
 
 int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
@@ -763,6 +770,20 @@ static int rtc_timer_enqueue(struct rtc_device *rtc, struct rtc_timer *timer)
 	return 0;
 }
 
+static void rtc_alarm_disable(struct rtc_device *rtc)
+{
+	struct rtc_wkalrm alarm;
+	struct rtc_time tm;
+
+	__rtc_read_time(rtc, &tm);
+
+	alarm.time = rtc_ktime_to_tm(ktime_add(rtc_tm_to_ktime(tm),
+				     ktime_set(300, 0)));
+	alarm.enabled = 0;
+
+	___rtc_set_alarm(rtc, &alarm);
+}
+
 /**
  * rtc_timer_remove - Removes a rtc_timer from the rtc_device timerqueue
  * @rtc rtc device
@@ -784,8 +805,10 @@ static void rtc_timer_remove(struct rtc_device *rtc, struct rtc_timer *timer)
 		struct rtc_wkalrm alarm;
 		int err;
 		next = timerqueue_getnext(&rtc->timerqueue);
-		if (!next)
+		if (!next) {
+			rtc_alarm_disable(rtc);
 			return;
+		}
 		alarm.time = rtc_ktime_to_tm(next->expires);
 		alarm.enabled = 1;
 		err = __rtc_set_alarm(rtc, &alarm);
@@ -847,7 +870,8 @@ again:
 		err = __rtc_set_alarm(rtc, &alarm);
 		if (err == -ETIME)
 			goto again;
-	}
+	} else
+		rtc_alarm_disable(rtc);
 
 	mutex_unlock(&rtc->ops_lock);
 }
diff --git a/drivers/rtc/rtc-puv3.c b/drivers/rtc/rtc-puv3.c
index b3eba3c..e4b6880 100644
--- a/drivers/rtc/rtc-puv3.c
+++ b/drivers/rtc/rtc-puv3.c
@@ -220,7 +220,7 @@ static void puv3_rtc_enable(struct platform_device *pdev, int en)
 	}
 }
 
-static int puv3_rtc_remove(struct platform_device *dev)
+static int __devexit puv3_rtc_remove(struct platform_device *dev)
 {
 	struct rtc_device *rtc = platform_get_drvdata(dev);
 
@@ -236,7 +236,7 @@ static int puv3_rtc_remove(struct platform_device *dev)
 	return 0;
 }
 
-static int puv3_rtc_probe(struct platform_device *pdev)
+static int __devinit puv3_rtc_probe(struct platform_device *pdev)
 {
 	struct rtc_device *rtc;
 	struct resource *res;
diff --git a/drivers/s390/char/zcore.c b/drivers/s390/char/zcore.c
index 43068fb..1b6d924 100644
--- a/drivers/s390/char/zcore.c
+++ b/drivers/s390/char/zcore.c
@@ -641,6 +641,8 @@ static int __init zcore_init(void)
 
 	if (ipl_info.type != IPL_TYPE_FCP_DUMP)
 		return -ENODATA;
+	if (OLDMEM_BASE)
+		return -ENODATA;
 
 	zcore_dbf = debug_register("zcore", 4, 1, 4 * sizeof(long));
 	debug_register_view(zcore_dbf, &debug_sprintf_view);
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 75c3f1f..a84631a 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -529,10 +529,7 @@ __s390_vary_chpid_on(struct subchannel_id schid, void *data)
 int chsc_chp_vary(struct chp_id chpid, int on)
 {
 	struct channel_path *chp = chpid_to_chp(chpid);
-	struct chp_link link;
 
-	memset(&link, 0, sizeof(struct chp_link));
-	link.chpid = chpid;
 	/* Wait until previous actions have settled. */
 	css_wait_for_slow_path();
 	/*
@@ -542,10 +539,10 @@ int chsc_chp_vary(struct chp_id chpid, int on)
 		/* Try to update the channel path descritor. */
 		chsc_determine_base_channel_path_desc(chpid, &chp->desc);
 		for_each_subchannel_staged(s390_subchannel_vary_chpid_on,
-					   __s390_vary_chpid_on, &link);
+					   __s390_vary_chpid_on, &chpid);
 	} else
 		for_each_subchannel_staged(s390_subchannel_vary_chpid_off,
-					   NULL, &link);
+					   NULL, &chpid);
 
 	return 0;
 }
diff --git a/drivers/s390/cio/cio.h b/drivers/s390/cio/cio.h
index 155a82b..4a1ff5c 100644
--- a/drivers/s390/cio/cio.h
+++ b/drivers/s390/cio/cio.h
@@ -68,8 +68,13 @@ struct schib {
 	__u8 mda[4];		 /* model dependent area */
 } __attribute__ ((packed,aligned(4)));
 
+/*
+ * When rescheduled, todo's with higher values will overwrite those
+ * with lower values.
+ */
 enum sch_todo {
 	SCH_TODO_NOTHING,
+	SCH_TODO_EVAL,
 	SCH_TODO_UNREG,
 };
 
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 92d7324..21908e6 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -195,51 +195,6 @@ void css_sch_device_unregister(struct subchannel *sch)
 }
 EXPORT_SYMBOL_GPL(css_sch_device_unregister);
 
-static void css_sch_todo(struct work_struct *work)
-{
-	struct subchannel *sch;
-	enum sch_todo todo;
-
-	sch = container_of(work, struct subchannel, todo_work);
-	/* Find out todo. */
-	spin_lock_irq(sch->lock);
-	todo = sch->todo;
-	CIO_MSG_EVENT(4, "sch_todo: sch=0.%x.%04x, todo=%d\n", sch->schid.ssid,
-		      sch->schid.sch_no, todo);
-	sch->todo = SCH_TODO_NOTHING;
-	spin_unlock_irq(sch->lock);
-	/* Perform todo. */
-	if (todo == SCH_TODO_UNREG)
-		css_sch_device_unregister(sch);
-	/* Release workqueue ref. */
-	put_device(&sch->dev);
-}
-
-/**
- * css_sched_sch_todo - schedule a subchannel operation
- * @sch: subchannel
- * @todo: todo
- *
- * Schedule the operation identified by @todo to be performed on the slow path
- * workqueue. Do nothing if another operation with higher priority is already
- * scheduled. Needs to be called with subchannel lock held.
- */
-void css_sched_sch_todo(struct subchannel *sch, enum sch_todo todo)
-{
-	CIO_MSG_EVENT(4, "sch_todo: sched sch=0.%x.%04x todo=%d\n",
-		      sch->schid.ssid, sch->schid.sch_no, todo);
-	if (sch->todo >= todo)
-		return;
-	/* Get workqueue ref. */
-	if (!get_device(&sch->dev))
-		return;
-	sch->todo = todo;
-	if (!queue_work(cio_work_q, &sch->todo_work)) {
-		/* Already queued, release workqueue ref. */
-		put_device(&sch->dev);
-	}
-}
-
 static void ssd_from_pmcw(struct chsc_ssd_info *ssd, struct pmcw *pmcw)
 {
 	int i;
@@ -466,6 +421,65 @@ static void css_evaluate_subchannel(struct subchannel_id schid, int slow)
 		css_schedule_eval(schid);
 }
 
+/**
+ * css_sched_sch_todo - schedule a subchannel operation
+ * @sch: subchannel
+ * @todo: todo
+ *
+ * Schedule the operation identified by @todo to be performed on the slow path
+ * workqueue. Do nothing if another operation with higher priority is already
+ * scheduled. Needs to be called with subchannel lock held.
+ */
+void css_sched_sch_todo(struct subchannel *sch, enum sch_todo todo)
+{
+	CIO_MSG_EVENT(4, "sch_todo: sched sch=0.%x.%04x todo=%d\n",
+		      sch->schid.ssid, sch->schid.sch_no, todo);
+	if (sch->todo >= todo)
+		return;
+	/* Get workqueue ref. */
+	if (!get_device(&sch->dev))
+		return;
+	sch->todo = todo;
+	if (!queue_work(cio_work_q, &sch->todo_work)) {
+		/* Already queued, release workqueue ref. */
+		put_device(&sch->dev);
+	}
+}
+
+static void css_sch_todo(struct work_struct *work)
+{
+	struct subchannel *sch;
+	enum sch_todo todo;
+	int ret;
+
+	sch = container_of(work, struct subchannel, todo_work);
+	/* Find out todo. */
+	spin_lock_irq(sch->lock);
+	todo = sch->todo;
+	CIO_MSG_EVENT(4, "sch_todo: sch=0.%x.%04x, todo=%d\n", sch->schid.ssid,
+		      sch->schid.sch_no, todo);
+	sch->todo = SCH_TODO_NOTHING;
+	spin_unlock_irq(sch->lock);
+	/* Perform todo. */
+	switch (todo) {
+	case SCH_TODO_NOTHING:
+		break;
+	case SCH_TODO_EVAL:
+		ret = css_evaluate_known_subchannel(sch, 1);
+		if (ret == -EAGAIN) {
+			spin_lock_irq(sch->lock);
+			css_sched_sch_todo(sch, todo);
+			spin_unlock_irq(sch->lock);
+		}
+		break;
+	case SCH_TODO_UNREG:
+		css_sch_device_unregister(sch);
+		break;
+	}
+	/* Release workqueue ref. */
+	put_device(&sch->dev);
+}
+
 static struct idset *slow_subchannel_set;
 static spinlock_t slow_subchannel_lock;
 static wait_queue_head_t css_eval_wq;
diff --git a/drivers/s390/cio/device.c b/drivers/s390/cio/device.c
index d734f4a..4726985 100644
--- a/drivers/s390/cio/device.c
+++ b/drivers/s390/cio/device.c
@@ -1868,9 +1868,9 @@ static void __ccw_device_pm_restore(struct ccw_device *cdev)
 	 */
 	cdev->private->flags.resuming = 1;
 	cdev->private->path_new_mask = LPM_ANYPATH;
-	css_schedule_eval(sch->schid);
+	css_sched_sch_todo(sch, SCH_TODO_EVAL);
 	spin_unlock_irq(sch->lock);
-	css_complete_work();
+	css_wait_for_slow_path();
 
 	/* cdev may have been moved to a different subchannel. */
 	sch = to_subchannel(cdev->dev.parent);
diff --git a/drivers/s390/cio/device_fsm.c b/drivers/s390/cio/device_fsm.c
index 52c233f..1b85351 100644
--- a/drivers/s390/cio/device_fsm.c
+++ b/drivers/s390/cio/device_fsm.c
@@ -496,8 +496,26 @@ static void ccw_device_reset_path_events(struct ccw_device *cdev)
 	cdev->private->pgid_reset_mask = 0;
 }
 
-void
-ccw_device_verify_done(struct ccw_device *cdev, int err)
+static void create_fake_irb(struct irb *irb, int type)
+{
+	memset(irb, 0, sizeof(*irb));
+	if (type == FAKE_CMD_IRB) {
+		struct cmd_scsw *scsw = &irb->scsw.cmd;
+		scsw->cc = 1;
+		scsw->fctl = SCSW_FCTL_START_FUNC;
+		scsw->actl = SCSW_ACTL_START_PEND;
+		scsw->stctl = SCSW_STCTL_STATUS_PEND;
+	} else if (type == FAKE_TM_IRB) {
+		struct tm_scsw *scsw = &irb->scsw.tm;
+		scsw->x = 1;
+		scsw->cc = 1;
+		scsw->fctl = SCSW_FCTL_START_FUNC;
+		scsw->actl = SCSW_ACTL_START_PEND;
+		scsw->stctl = SCSW_STCTL_STATUS_PEND;
+	}
+}
+
+void ccw_device_verify_done(struct ccw_device *cdev, int err)
 {
 	struct subchannel *sch;
 
@@ -520,12 +538,8 @@ callback:
 		ccw_device_done(cdev, DEV_STATE_ONLINE);
 		/* Deliver fake irb to device driver, if needed. */
 		if (cdev->private->flags.fake_irb) {
-			memset(&cdev->private->irb, 0, sizeof(struct irb));
-			cdev->private->irb.scsw.cmd.cc = 1;
-			cdev->private->irb.scsw.cmd.fctl = SCSW_FCTL_START_FUNC;
-			cdev->private->irb.scsw.cmd.actl = SCSW_ACTL_START_PEND;
-			cdev->private->irb.scsw.cmd.stctl =
-				SCSW_STCTL_STATUS_PEND;
+			create_fake_irb(&cdev->private->irb,
+					cdev->private->flags.fake_irb);
 			cdev->private->flags.fake_irb = 0;
 			if (cdev->handler)
 				cdev->handler(cdev, cdev->private->intparm,
diff --git a/drivers/s390/cio/device_ops.c b/drivers/s390/cio/device_ops.c
index f98698d..ec7fb6d 100644
--- a/drivers/s390/cio/device_ops.c
+++ b/drivers/s390/cio/device_ops.c
@@ -198,7 +198,7 @@ int ccw_device_start_key(struct ccw_device *cdev, struct ccw1 *cpa,
 	if (cdev->private->state == DEV_STATE_VERIFY) {
 		/* Remember to fake irb when finished. */
 		if (!cdev->private->flags.fake_irb) {
-			cdev->private->flags.fake_irb = 1;
+			cdev->private->flags.fake_irb = FAKE_CMD_IRB;
 			cdev->private->intparm = intparm;
 			return 0;
 		} else
@@ -213,9 +213,9 @@ int ccw_device_start_key(struct ccw_device *cdev, struct ccw1 *cpa,
 	ret = cio_set_options (sch, flags);
 	if (ret)
 		return ret;
-	/* Adjust requested path mask to excluded varied off paths. */
+	/* Adjust requested path mask to exclude unusable paths. */
 	if (lpm) {
-		lpm &= sch->opm;
+		lpm &= sch->lpm;
 		if (lpm == 0)
 			return -EACCES;
 	}
@@ -605,11 +605,21 @@ int ccw_device_tm_start_key(struct ccw_device *cdev, struct tcw *tcw,
 	sch = to_subchannel(cdev->dev.parent);
 	if (!sch->schib.pmcw.ena)
 		return -EINVAL;
+	if (cdev->private->state == DEV_STATE_VERIFY) {
+		/* Remember to fake irb when finished. */
+		if (!cdev->private->flags.fake_irb) {
+			cdev->private->flags.fake_irb = FAKE_TM_IRB;
+			cdev->private->intparm = intparm;
+			return 0;
+		} else
+			/* There's already a fake I/O around. */
+			return -EBUSY;
+	}
 	if (cdev->private->state != DEV_STATE_ONLINE)
 		return -EIO;
-	/* Adjust requested path mask to excluded varied off paths. */
+	/* Adjust requested path mask to exclude unusable paths. */
 	if (lpm) {
-		lpm &= sch->opm;
+		lpm &= sch->lpm;
 		if (lpm == 0)
 			return -EACCES;
 	}
diff --git a/drivers/s390/cio/io_sch.h b/drivers/s390/cio/io_sch.h
index 2ebb492..76253df 100644
--- a/drivers/s390/cio/io_sch.h
+++ b/drivers/s390/cio/io_sch.h
@@ -111,6 +111,9 @@ enum cdev_todo {
 	CDEV_TODO_UNREG_EVAL,
 };
 
+#define FAKE_CMD_IRB	1
+#define FAKE_TM_IRB	2
+
 struct ccw_device_private {
 	struct ccw_device *cdev;
 	struct subchannel *sch;
@@ -138,7 +141,7 @@ struct ccw_device_private {
 		unsigned int doverify:1;    /* delayed path verification */
 		unsigned int donotify:1;    /* call notify function */
 		unsigned int recog_done:1;  /* dev. recog. complete */
-		unsigned int fake_irb:1;    /* deliver faked irb */
+		unsigned int fake_irb:2;    /* deliver faked irb */
 		unsigned int resuming:1;    /* recognition while resume */
 		unsigned int pgroup:1;	    /* pathgroup is set up */
 		unsigned int mpath:1;	    /* multipathing is set up */
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index b77ae51..96bbe9d 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -1271,18 +1271,16 @@ ap_config_timeout(unsigned long ptr)
 }
 
 /**
- * ap_schedule_poll_timer(): Schedule poll timer.
+ * __ap_schedule_poll_timer(): Schedule poll timer.
  *
  * Set up the timer to run the poll tasklet
  */
-static inline void ap_schedule_poll_timer(void)
+static inline void __ap_schedule_poll_timer(void)
 {
 	ktime_t hr_time;
 
 	spin_lock_bh(&ap_poll_timer_lock);
-	if (ap_using_interrupts() || ap_suspend_flag)
-		goto out;
-	if (hrtimer_is_queued(&ap_poll_timer))
+	if (hrtimer_is_queued(&ap_poll_timer) || ap_suspend_flag)
 		goto out;
 	if (ktime_to_ns(hrtimer_expires_remaining(&ap_poll_timer)) <= 0) {
 		hr_time = ktime_set(0, poll_timeout);
@@ -1294,6 +1292,18 @@ out:
 }
 
 /**
+ * ap_schedule_poll_timer(): Schedule poll timer.
+ *
+ * Set up the timer to run the poll tasklet
+ */
+static inline void ap_schedule_poll_timer(void)
+{
+	if (ap_using_interrupts())
+		return;
+	__ap_schedule_poll_timer();
+}
+
+/**
  * ap_poll_read(): Receive pending reply messages from an AP device.
  * @ap_dev: pointer to the AP device
  * @flags: pointer to control flags, bit 2^0 is set if another poll is
@@ -1374,8 +1384,9 @@ static int ap_poll_write(struct ap_device *ap_dev, unsigned long *flags)
 			*flags |= 1;
 		*flags |= 2;
 		break;
-	case AP_RESPONSE_Q_FULL:
 	case AP_RESPONSE_RESET_IN_PROGRESS:
+		__ap_schedule_poll_timer();
+	case AP_RESPONSE_Q_FULL:
 		*flags |= 2;
 		break;
 	case AP_RESPONSE_MESSAGE_TOO_BIG:
@@ -1541,6 +1552,8 @@ static void ap_reset(struct ap_device *ap_dev)
 	rc = ap_init_queue(ap_dev->qid);
 	if (rc == -ENODEV)
 		ap_dev->unregistered = 1;
+	else
+		__ap_schedule_poll_timer();
 }
 
 static int __ap_poll_device(struct ap_device *ap_dev, unsigned long *flags)
diff --git a/drivers/s390/kvm/kvm_virtio.c b/drivers/s390/kvm/kvm_virtio.c
index 94f49ff..8af868b 100644
--- a/drivers/s390/kvm/kvm_virtio.c
+++ b/drivers/s390/kvm/kvm_virtio.c
@@ -263,6 +263,11 @@ error:
 	return PTR_ERR(vqs[i]);
 }
 
+static const char *kvm_bus_name(struct virtio_device *vdev)
+{
+	return "";
+}
+
 /*
  * The config ops structure as defined by virtio config
  */
@@ -276,6 +281,7 @@ static struct virtio_config_ops kvm_vq_configspace_ops = {
 	.reset = kvm_reset,
 	.find_vqs = kvm_find_vqs,
 	.del_vqs = kvm_del_vqs,
+	.bus_name = kvm_bus_name,
 };
 
 /*
diff --git a/drivers/s390/net/Kconfig b/drivers/s390/net/Kconfig
index fa80ba1..9b66d2d 100644
--- a/drivers/s390/net/Kconfig
+++ b/drivers/s390/net/Kconfig
@@ -4,7 +4,7 @@ menu "S/390 network device drivers"
 config LCS
 	def_tristate m
 	prompt "Lan Channel Station Interface"
-	depends on CCW && NETDEVICES && (NET_ETHERNET || TR || FDDI)
+	depends on CCW && NETDEVICES && (ETHERNET || TR || FDDI)
 	help
 	   Select this option if you want to use LCS networking on IBM System z.
 	   This device driver supports Token Ring (IEEE 802.5),
diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c
index c28713d..863fc21 100644
--- a/drivers/s390/net/lcs.c
+++ b/drivers/s390/net/lcs.c
@@ -50,7 +50,7 @@
 #include "lcs.h"
 
 
-#if !defined(CONFIG_NET_ETHERNET) && \
+#if !defined(CONFIG_ETHERNET) && \
     !defined(CONFIG_TR) && !defined(CONFIG_FDDI)
 #error Cannot compile lcs.c without some net devices switched on.
 #endif
@@ -1634,7 +1634,7 @@ lcs_startlan_auto(struct lcs_card *card)
 	int rc;
 
 	LCS_DBF_TEXT(2, trace, "strtauto");
-#ifdef CONFIG_NET_ETHERNET
+#ifdef CONFIG_ETHERNET
 	card->lan_type = LCS_FRAME_TYPE_ENET;
 	rc = lcs_send_startlan(card, LCS_INITIATOR_TCPIP);
 	if (rc == 0)
@@ -2166,7 +2166,7 @@ lcs_new_device(struct ccwgroup_device *ccwgdev)
 		goto netdev_out;
 	}
 	switch (card->lan_type) {
-#ifdef CONFIG_NET_ETHERNET
+#ifdef CONFIG_ETHERNET
 	case LCS_FRAME_TYPE_ENET:
 		card->lan_type_trans = eth_type_trans;
 		dev = alloc_etherdev(0);
diff --git a/drivers/s390/net/netiucv.c b/drivers/s390/net/netiucv.c
index 3251333..b6a6356 100644
--- a/drivers/s390/net/netiucv.c
+++ b/drivers/s390/net/netiucv.c
@@ -1994,6 +1994,8 @@ static struct net_device *netiucv_init_netdevice(char *username)
 			   netiucv_setup_netdevice);
 	if (!dev)
 		return NULL;
+	if (dev_alloc_name(dev, dev->name) < 0)
+		goto out_netdev;
 
 	privptr = netdev_priv(dev);
 	privptr->fsm = init_fsm("netiucvdev", dev_state_names,
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index b77c65e..4abc79d 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -236,8 +236,7 @@ static inline int qeth_is_ipa_enabled(struct qeth_ipa_info *ipa,
 #define QETH_IN_BUF_COUNT_MAX 128
 #define QETH_MAX_BUFFER_ELEMENTS(card) ((card)->qdio.in_buf_size >> 12)
 #define QETH_IN_BUF_REQUEUE_THRESHOLD(card) \
-		((card)->ssqd.qdioac1 & AC1_SIGA_INPUT_NEEDED ? 1 : \
-		 ((card)->qdio.in_buf_pool.buf_count / 2))
+		 ((card)->qdio.in_buf_pool.buf_count / 2)
 
 /* buffers we have to be behind before we get a PCI */
 #define QETH_PCI_THRESHOLD_A(card) ((card)->qdio.in_buf_pool.buf_count+1)
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 8153443..fff57de 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -881,7 +881,6 @@ EXPORT_SYMBOL_GPL(qeth_do_run_thread);
 void qeth_schedule_recovery(struct qeth_card *card)
 {
 	QETH_CARD_TEXT(card, 2, "startrec");
-	WARN_ON(1);
 	if (qeth_set_thread_start_bit(card, QETH_RECOVER_THREAD) == 0)
 		schedule_work(&card->kernel_thread_starter);
 }
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index a21ae3d..c4e2004 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -301,21 +301,21 @@ static void qeth_l2_process_vlans(struct qeth_card *card)
 	spin_unlock_bh(&card->vlanlock);
 }
 
-static void qeth_l2_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+static int qeth_l2_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 {
 	struct qeth_card *card = dev->ml_priv;
 	struct qeth_vlan_vid *id;
 
 	QETH_CARD_TEXT_(card, 4, "aid:%d", vid);
 	if (!vid)
-		return;
+		return 0;
 	if (card->info.type == QETH_CARD_TYPE_OSM) {
 		QETH_CARD_TEXT(card, 3, "aidOSM");
-		return;
+		return 0;
 	}
 	if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) {
 		QETH_CARD_TEXT(card, 3, "aidREC");
-		return;
+		return 0;
 	}
 	id = kmalloc(sizeof(struct qeth_vlan_vid), GFP_ATOMIC);
 	if (id) {
@@ -324,10 +324,13 @@ static void qeth_l2_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 		spin_lock_bh(&card->vlanlock);
 		list_add_tail(&id->list, &card->vid_list);
 		spin_unlock_bh(&card->vlanlock);
+	} else {
+		return -ENOMEM;
 	}
+	return 0;
 }
 
-static void qeth_l2_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 {
 	struct qeth_vlan_vid *id, *tmpid = NULL;
 	struct qeth_card *card = dev->ml_priv;
@@ -335,11 +338,11 @@ static void qeth_l2_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 	QETH_CARD_TEXT_(card, 4, "kid:%d", vid);
 	if (card->info.type == QETH_CARD_TYPE_OSM) {
 		QETH_CARD_TEXT(card, 3, "kidOSM");
-		return;
+		return 0;
 	}
 	if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) {
 		QETH_CARD_TEXT(card, 3, "kidREC");
-		return;
+		return 0;
 	}
 	spin_lock_bh(&card->vlanlock);
 	list_for_each_entry(id, &card->vid_list, list) {
@@ -355,6 +358,7 @@ static void qeth_l2_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 		kfree(tmpid);
 	}
 	qeth_l2_set_multicast_list(card->dev);
+	return 0;
 }
 
 static int qeth_l2_stop_card(struct qeth_card *card, int recovery_mode)
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index e4c1176..b3b045c 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1869,15 +1869,15 @@ static void qeth_l3_free_vlan_addresses(struct qeth_card *card,
 	qeth_l3_free_vlan_addresses6(card, vid);
 }
 
-static void qeth_l3_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+static int qeth_l3_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 {
 	struct qeth_card *card = dev->ml_priv;
 
 	set_bit(vid, card->active_vlans);
-	return;
+	return 0;
 }
 
-static void qeth_l3_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+static int qeth_l3_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 {
 	struct qeth_card *card = dev->ml_priv;
 	unsigned long flags;
@@ -1885,7 +1885,7 @@ static void qeth_l3_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 	QETH_CARD_TEXT_(card, 4, "kid:%d", vid);
 	if (qeth_wait_for_threads(card, QETH_RECOVER_THREAD)) {
 		QETH_CARD_TEXT(card, 3, "kidREC");
-		return;
+		return 0;
 	}
 	spin_lock_irqsave(&card->vlanlock, flags);
 	/* unregister IP addresses of vlan device */
@@ -1893,6 +1893,7 @@ static void qeth_l3_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 	clear_bit(vid, card->active_vlans);
 	spin_unlock_irqrestore(&card->vlanlock, flags);
 	qeth_l3_set_multicast_list(card->dev);
+	return 0;
 }
 
 static inline int qeth_l3_rebuild_skb(struct qeth_card *card,
@@ -2756,11 +2757,13 @@ int inline qeth_l3_get_cast_type(struct qeth_card *card, struct sk_buff *skb)
 	struct neighbour *n = NULL;
 	struct dst_entry *dst;
 
+	rcu_read_lock();
 	dst = skb_dst(skb);
 	if (dst)
-		n = dst_get_neighbour(dst);
+		n = dst_get_neighbour_noref(dst);
 	if (n) {
 		cast_type = n->type;
+		rcu_read_unlock();
 		if ((cast_type == RTN_BROADCAST) ||
 		    (cast_type == RTN_MULTICAST) ||
 		    (cast_type == RTN_ANYCAST))
@@ -2768,6 +2771,8 @@ int inline qeth_l3_get_cast_type(struct qeth_card *card, struct sk_buff *skb)
 		else
 			return RTN_UNSPEC;
 	}
+	rcu_read_unlock();
+
 	/* try something else */
 	if (skb->protocol == ETH_P_IPV6)
 		return (skb_network_header(skb)[24] == 0xff) ?
@@ -2847,9 +2852,11 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr,
 	}
 
 	hdr->hdr.l3.length = skb->len - sizeof(struct qeth_hdr);
+
+	rcu_read_lock();
 	dst = skb_dst(skb);
 	if (dst)
-		n = dst_get_neighbour(dst);
+		n = dst_get_neighbour_noref(dst);
 	if (ipv == 4) {
 		/* IPv4 */
 		hdr->hdr.l3.flags = qeth_l3_get_qeth_hdr_flags4(cast_type);
@@ -2893,6 +2900,7 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr,
 				QETH_CAST_UNICAST | QETH_HDR_PASSTHRU;
 		}
 	}
+	rcu_read_unlock();
 }
 
 static inline void qeth_l3_hdr_csum(struct qeth_card *card,
@@ -3202,7 +3210,8 @@ static int qeth_l3_stop(struct net_device *dev)
 	return 0;
 }
 
-static u32 qeth_l3_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t qeth_l3_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct qeth_card *card = dev->ml_priv;
 
@@ -3216,7 +3225,8 @@ static u32 qeth_l3_fix_features(struct net_device *dev, u32 features)
 	return features;
 }
 
-static int qeth_l3_set_features(struct net_device *dev, u32 features)
+static int qeth_l3_set_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct qeth_card *card = dev->ml_priv;
 	u32 changed = dev->features ^ features;
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index 0ea2fbf..d979bb2 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -335,10 +335,10 @@ static ssize_t qeth_l3_dev_sniffer_store(struct device *dev,
 					QETH_IN_BUF_COUNT_MAX)
 				qeth_realloc_buffer_pool(card,
 					QETH_IN_BUF_COUNT_MAX);
-			break;
 		} else
 			rc = -EPERM;
-	default:   /* fall through */
+		break;
+	default:
 		rc = -EINVAL;
 	}
 out:
diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c
index 4aa76d6..705e13e 100644
--- a/drivers/scsi/aacraid/linit.c
+++ b/drivers/scsi/aacraid/linit.c
@@ -38,6 +38,7 @@
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/pci.h>
+#include <linux/pci-aspm.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
@@ -1109,6 +1110,9 @@ static int __devinit aac_probe_one(struct pci_dev *pdev,
 		unique_id++;
 	}
 
+	pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 |
+			       PCIE_LINK_STATE_CLKPM);
+
 	error = pci_enable_device(pdev);
 	if (error)
 		goto out;
diff --git a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
index 000294a..36739da 100644
--- a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
+++ b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
@@ -966,7 +966,7 @@ static int init_act_open(struct cxgbi_sock *csk)
 		csk->saddr.sin_addr.s_addr = chba->ipv4addr;
 
 	csk->rss_qid = 0;
-	csk->l2t = t3_l2t_get(t3dev, dst_get_neighbour(dst), ndev);
+	csk->l2t = t3_l2t_get(t3dev, dst, ndev);
 	if (!csk->l2t) {
 		pr_err("NO l2t available.\n");
 		return -EINVAL;
diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
index ac7a9b1..5a4a3bf 100644
--- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
+++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
@@ -1127,6 +1127,7 @@ static int init_act_open(struct cxgbi_sock *csk)
 	struct net_device *ndev = cdev->ports[csk->port_id];
 	struct port_info *pi = netdev_priv(ndev);
 	struct sk_buff *skb = NULL;
+	struct neighbour *n;
 	unsigned int step;
 
 	log_debug(1 << CXGBI_DBG_TOE | 1 << CXGBI_DBG_SOCK,
@@ -1141,7 +1142,12 @@ static int init_act_open(struct cxgbi_sock *csk)
 	cxgbi_sock_set_flag(csk, CTPF_HAS_ATID);
 	cxgbi_sock_get(csk);
 
-	csk->l2t = cxgb4_l2t_get(lldi->l2t, dst_get_neighbour(csk->dst), ndev, 0);
+	n = dst_get_neighbour_noref(csk->dst);
+	if (!n) {
+		pr_err("%s, can't get neighbour of csk->dst.\n", ndev->name);
+		goto rel_resource;
+	}
+	csk->l2t = cxgb4_l2t_get(lldi->l2t, n, ndev, 0);
 	if (!csk->l2t) {
 		pr_err("%s, cannot alloc l2t.\n", ndev->name);
 		goto rel_resource;
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index c10f74a..1d25a87 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -472,6 +472,7 @@ static struct cxgbi_sock *cxgbi_check_route(struct sockaddr *dst_addr)
 	struct net_device *ndev;
 	struct cxgbi_device *cdev;
 	struct rtable *rt = NULL;
+	struct neighbour *n;
 	struct flowi4 fl4;
 	struct cxgbi_sock *csk = NULL;
 	unsigned int mtu = 0;
@@ -493,7 +494,12 @@ static struct cxgbi_sock *cxgbi_check_route(struct sockaddr *dst_addr)
 		goto err_out;
 	}
 	dst = &rt->dst;
-	ndev = dst_get_neighbour(dst)->dev;
+	n = dst_get_neighbour_noref(dst);
+	if (!n) {
+		err = -ENODEV;
+		goto rel_rt;
+	}
+	ndev = n->dev;
 
 	if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
 		pr_info("multi-cast route %pI4, port %u, dev %s.\n",
@@ -507,7 +513,7 @@ static struct cxgbi_sock *cxgbi_check_route(struct sockaddr *dst_addr)
 		ndev = ip_dev_find(&init_net, daddr->sin_addr.s_addr);
 		mtu = ndev->mtu;
 		pr_info("rt dev %s, loopback -> %s, mtu %u.\n",
-			dst_get_neighbour(dst)->dev->name, ndev->name, mtu);
+			n->dev->name, ndev->name, mtu);
 	}
 
 	cdev = cxgbi_device_find_by_netdev(ndev, &port);
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index e76107b..865d452 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/types.h>
 #include <linux/pci.h>
+#include <linux/pci-aspm.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/delay.h>
@@ -3922,6 +3923,10 @@ static int __devinit hpsa_pci_init(struct ctlr_info *h)
 		dev_warn(&h->pdev->dev, "controller appears to be disabled\n");
 		return -ENODEV;
 	}
+
+	pci_disable_link_state(h->pdev, PCIE_LINK_STATE_L0S |
+			       PCIE_LINK_STATE_L1 | PCIE_LINK_STATE_CLKPM);
+
 	err = pci_enable_device(h->pdev);
 	if (err) {
 		dev_warn(&h->pdev->dev, "unable to enable PCI device\n");
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index 8889b1b..4e041f6 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -2802,6 +2802,11 @@ _scsih_error_recovery_delete_devices(struct MPT2SAS_ADAPTER *ioc)
 
 	if (ioc->is_driver_loading)
 		return;
+
+	fw_event = kzalloc(sizeof(struct fw_event_work), GFP_ATOMIC);
+	if (!fw_event)
+		return;
+
 	fw_event->event = MPT2SAS_REMOVE_UNRESPONDING_DEVICES;
 	fw_event->ioc = ioc;
 	_scsih_fw_event_add(ioc, fw_event);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 06bc265..f85cfa6 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1409,6 +1409,8 @@ static void scsi_kill_request(struct request *req, struct request_queue *q)
 
 	blk_start_request(req);
 
+	scmd_printk(KERN_INFO, cmd, "killing request\n");
+
 	sdev = cmd->device;
 	starget = scsi_target(sdev);
 	shost = sdev->host;
@@ -1490,7 +1492,6 @@ static void scsi_request_fn(struct request_queue *q)
 	struct request *req;
 
 	if (!sdev) {
-		printk("scsi: killing requests for dead queue\n");
 		while ((req = blk_peek_request(q)) != NULL)
 			scsi_kill_request(req, q);
 		return;
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 72273a0..b3c6d95 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -319,11 +319,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
 	return sdev;
 
 out_device_destroy:
-	scsi_device_set_state(sdev, SDEV_DEL);
-	transport_destroy_device(&sdev->sdev_gendev);
-	put_device(&sdev->sdev_dev);
-	scsi_free_queue(sdev->request_queue);
-	put_device(&sdev->sdev_gendev);
+	__scsi_remove_device(sdev);
 out:
 	if (display_failure_msg)
 		printk(ALLOC_FAILURE_MSG, __func__);
diff --git a/drivers/spi/spi-nuc900.c b/drivers/spi/spi-nuc900.c
index e763254..21c70b2 100644
--- a/drivers/spi/spi-nuc900.c
+++ b/drivers/spi/spi-nuc900.c
@@ -426,7 +426,7 @@ static int __devinit nuc900_spi_probe(struct platform_device *pdev)
 		goto err_clk;
 	}
 
-	mfp_set_groupg(&pdev->dev);
+	mfp_set_groupg(&pdev->dev, NULL);
 	nuc900_init_spi(hw);
 
 	err = spi_bitbang_start(&hw->bitbang);
diff --git a/drivers/spi/spi-pl022.c b/drivers/spi/spi-pl022.c
index f103e47..5559b22 100644
--- a/drivers/spi/spi-pl022.c
+++ b/drivers/spi/spi-pl022.c
@@ -2184,6 +2184,12 @@ pl022_probe(struct amba_device *adev, const struct amba_id *id)
 		goto  err_clk_prep;
 	}
 
+	status = clk_enable(pl022->clk);
+	if (status) {
+		dev_err(&adev->dev, "could not enable SSP/SPI bus clock\n");
+		goto err_no_clk_en;
+	}
+
 	/* Disable SSP */
 	writew((readw(SSP_CR1(pl022->virtbase)) & (~SSP_CR1_MASK_SSE)),
 	       SSP_CR1(pl022->virtbase));
@@ -2237,6 +2243,8 @@ pl022_probe(struct amba_device *adev, const struct amba_id *id)
 
 	free_irq(adev->irq[0], pl022);
  err_no_irq:
+	clk_disable(pl022->clk);
+ err_no_clk_en:
 	clk_unprepare(pl022->clk);
  err_clk_prep:
 	clk_put(pl022->clk);
diff --git a/drivers/staging/comedi/comedi_fops.c b/drivers/staging/comedi/comedi_fops.c
index 21d8c1c..5e78c77 100644
--- a/drivers/staging/comedi/comedi_fops.c
+++ b/drivers/staging/comedi/comedi_fops.c
@@ -671,7 +671,7 @@ static int do_insnlist_ioctl(struct comedi_device *dev,
 	}
 
 	insns =
-	    kmalloc(sizeof(struct comedi_insn) * insnlist.n_insns, GFP_KERNEL);
+	    kcalloc(insnlist.n_insns, sizeof(struct comedi_insn), GFP_KERNEL);
 	if (!insns) {
 		DPRINTK("kmalloc failed\n");
 		ret = -ENOMEM;
@@ -1432,7 +1432,21 @@ static int do_cancel(struct comedi_device *dev, struct comedi_subdevice *s)
 	return ret;
 }
 
-static void comedi_unmap(struct vm_area_struct *area)
+
+static void comedi_vm_open(struct vm_area_struct *area)
+{
+	struct comedi_async *async;
+	struct comedi_device *dev;
+
+	async = area->vm_private_data;
+	dev = async->subdevice->device;
+
+	mutex_lock(&dev->mutex);
+	async->mmap_count++;
+	mutex_unlock(&dev->mutex);
+}
+
+static void comedi_vm_close(struct vm_area_struct *area)
 {
 	struct comedi_async *async;
 	struct comedi_device *dev;
@@ -1446,15 +1460,13 @@ static void comedi_unmap(struct vm_area_struct *area)
 }
 
 static struct vm_operations_struct comedi_vm_ops = {
-	.close = comedi_unmap,
+	.open = comedi_vm_open,
+	.close = comedi_vm_close,
 };
 
 static int comedi_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	const unsigned minor = iminor(file->f_dentry->d_inode);
-	struct comedi_device_file_info *dev_file_info =
-	    comedi_get_device_file_info(minor);
-	struct comedi_device *dev = dev_file_info->device;
 	struct comedi_async *async = NULL;
 	unsigned long start = vma->vm_start;
 	unsigned long size;
@@ -1462,6 +1474,15 @@ static int comedi_mmap(struct file *file, struct vm_area_struct *vma)
 	int i;
 	int retval;
 	struct comedi_subdevice *s;
+	struct comedi_device_file_info *dev_file_info;
+	struct comedi_device *dev;
+
+	dev_file_info = comedi_get_device_file_info(minor);
+	if (dev_file_info == NULL)
+	        return -ENODEV;
+	dev = dev_file_info->device;
+	if (dev == NULL)
+	        return -ENODEV;
 
 	mutex_lock(&dev->mutex);
 	if (!dev->attached) {
@@ -1528,11 +1549,17 @@ static unsigned int comedi_poll(struct file *file, poll_table * wait)
 {
 	unsigned int mask = 0;
 	const unsigned minor = iminor(file->f_dentry->d_inode);
-	struct comedi_device_file_info *dev_file_info =
-	    comedi_get_device_file_info(minor);
-	struct comedi_device *dev = dev_file_info->device;
 	struct comedi_subdevice *read_subdev;
 	struct comedi_subdevice *write_subdev;
+	struct comedi_device_file_info *dev_file_info;
+	struct comedi_device *dev;
+	dev_file_info = comedi_get_device_file_info(minor);
+
+	if (dev_file_info == NULL)
+	        return -ENODEV;
+	dev = dev_file_info->device;
+	if (dev == NULL)
+	        return -ENODEV;
 
 	mutex_lock(&dev->mutex);
 	if (!dev->attached) {
@@ -1578,9 +1605,15 @@ static ssize_t comedi_write(struct file *file, const char __user *buf,
 	int n, m, count = 0, retval = 0;
 	DECLARE_WAITQUEUE(wait, current);
 	const unsigned minor = iminor(file->f_dentry->d_inode);
-	struct comedi_device_file_info *dev_file_info =
-	    comedi_get_device_file_info(minor);
-	struct comedi_device *dev = dev_file_info->device;
+	struct comedi_device_file_info *dev_file_info;
+	struct comedi_device *dev;
+	dev_file_info = comedi_get_device_file_info(minor);
+
+	if (dev_file_info == NULL)
+	        return -ENODEV;
+	dev = dev_file_info->device;
+	if (dev == NULL)
+	        return -ENODEV;
 
 	if (!dev->attached) {
 		DPRINTK("no driver configured on comedi%i\n", dev->minor);
@@ -1640,11 +1673,11 @@ static ssize_t comedi_write(struct file *file, const char __user *buf,
 				retval = -EAGAIN;
 				break;
 			}
+			schedule();
 			if (signal_pending(current)) {
 				retval = -ERESTARTSYS;
 				break;
 			}
-			schedule();
 			if (!s->busy)
 				break;
 			if (s->busy != file) {
@@ -1683,9 +1716,15 @@ static ssize_t comedi_read(struct file *file, char __user *buf, size_t nbytes,
 	int n, m, count = 0, retval = 0;
 	DECLARE_WAITQUEUE(wait, current);
 	const unsigned minor = iminor(file->f_dentry->d_inode);
-	struct comedi_device_file_info *dev_file_info =
-	    comedi_get_device_file_info(minor);
-	struct comedi_device *dev = dev_file_info->device;
+	struct comedi_device_file_info *dev_file_info;
+	struct comedi_device *dev;
+	dev_file_info = comedi_get_device_file_info(minor);
+
+	if (dev_file_info == NULL)
+	        return -ENODEV;
+	dev = dev_file_info->device;
+	if (dev == NULL)
+	        return -ENODEV;
 
 	if (!dev->attached) {
 		DPRINTK("no driver configured on comedi%i\n", dev->minor);
@@ -1741,11 +1780,11 @@ static ssize_t comedi_read(struct file *file, char __user *buf, size_t nbytes,
 				retval = -EAGAIN;
 				break;
 			}
+			schedule();
 			if (signal_pending(current)) {
 				retval = -ERESTARTSYS;
 				break;
 			}
-			schedule();
 			if (!s->busy) {
 				retval = 0;
 				break;
@@ -1885,11 +1924,17 @@ ok:
 static int comedi_close(struct inode *inode, struct file *file)
 {
 	const unsigned minor = iminor(inode);
-	struct comedi_device_file_info *dev_file_info =
-	    comedi_get_device_file_info(minor);
-	struct comedi_device *dev = dev_file_info->device;
 	struct comedi_subdevice *s = NULL;
 	int i;
+	struct comedi_device_file_info *dev_file_info;
+	struct comedi_device *dev;
+	dev_file_info = comedi_get_device_file_info(minor);
+
+	if (dev_file_info == NULL)
+	        return -ENODEV;
+	dev = dev_file_info->device;
+	if (dev == NULL)
+	        return -ENODEV;
 
 	mutex_lock(&dev->mutex);
 
@@ -1923,10 +1968,15 @@ static int comedi_close(struct inode *inode, struct file *file)
 static int comedi_fasync(int fd, struct file *file, int on)
 {
 	const unsigned minor = iminor(file->f_dentry->d_inode);
-	struct comedi_device_file_info *dev_file_info =
-	    comedi_get_device_file_info(minor);
+	struct comedi_device_file_info *dev_file_info;
+	struct comedi_device *dev;
+	dev_file_info = comedi_get_device_file_info(minor);
 
-	struct comedi_device *dev = dev_file_info->device;
+	if (dev_file_info == NULL)
+	        return -ENODEV;
+	dev = dev_file_info->device;
+	if (dev == NULL)
+	        return -ENODEV;
 
 	return fasync_helper(fd, file, on, &dev->async_queue);
 }
diff --git a/drivers/staging/comedi/drivers/usbduxsigma.c b/drivers/staging/comedi/drivers/usbduxsigma.c
index a8fea9a..6144afb 100644
--- a/drivers/staging/comedi/drivers/usbduxsigma.c
+++ b/drivers/staging/comedi/drivers/usbduxsigma.c
@@ -1,4 +1,4 @@
-#define DRIVER_VERSION "v0.5"
+#define DRIVER_VERSION "v0.6"
 #define DRIVER_AUTHOR "Bernd Porr, BerndPorr@f2s.com"
 #define DRIVER_DESC "Stirling/ITL USB-DUX SIGMA -- Bernd.Porr@f2s.com"
 /*
@@ -25,7 +25,7 @@ Driver: usbduxsigma
 Description: University of Stirling USB DAQ & INCITE Technology Limited
 Devices: [ITL] USB-DUX (usbduxsigma.o)
 Author: Bernd Porr <BerndPorr@f2s.com>
-Updated: 21 Jul 2011
+Updated: 8 Nov 2011
 Status: testing
 */
 /*
@@ -44,6 +44,7 @@ Status: testing
  *   0.3: proper vendor ID and driver name
  *   0.4: fixed D/A voltage range
  *   0.5: various bug fixes, health check at startup
+ *   0.6: corrected wrong input range
  */
 
 /* generates loads of debug info */
@@ -175,7 +176,7 @@ Status: testing
 /* comedi constants */
 static const struct comedi_lrange range_usbdux_ai_range = { 1, {
 								BIP_RANGE
-								(2.65)
+								(2.65/2.0)
 								}
 };
 
diff --git a/drivers/staging/et131x/Kconfig b/drivers/staging/et131x/Kconfig
index 9e1864c..8190f2a 100644
--- a/drivers/staging/et131x/Kconfig
+++ b/drivers/staging/et131x/Kconfig
@@ -1,6 +1,7 @@
 config ET131X
 	tristate "Agere ET-1310 Gigabit Ethernet support"
-	depends on PCI
+	depends on PCI && NET && NETDEVICES
+	select PHYLIB
 	default n
 	---help---
 	  This driver supports Agere ET-1310 ethernet adapters.
diff --git a/drivers/staging/et131x/et131x.c b/drivers/staging/et131x/et131x.c
index f5f44a0..0c1c6ca 100644
--- a/drivers/staging/et131x/et131x.c
+++ b/drivers/staging/et131x/et131x.c
@@ -4469,6 +4469,12 @@ static int et131x_resume(struct device *dev)
 	return 0;
 }
 
+static SIMPLE_DEV_PM_OPS(et131x_pm_ops, et131x_suspend, et131x_resume);
+#define ET131X_PM_OPS (&et131x_pm_ops)
+#else
+#define ET131X_PM_OPS NULL
+#endif
+
 /* ISR functions */
 
 /**
@@ -5470,12 +5476,6 @@ err_out:
 	return result;
 }
 
-static SIMPLE_DEV_PM_OPS(et131x_pm_ops, et131x_suspend, et131x_resume);
-#define ET131X_PM_OPS (&et131x_pm_ops)
-#else
-#define ET131X_PM_OPS NULL
-#endif
-
 static DEFINE_PCI_DEVICE_TABLE(et131x_pci_table) = {
 	{ PCI_VDEVICE(ATT, ET131X_PCI_DEVICE_ID_GIG), 0UL},
 	{ PCI_VDEVICE(ATT, ET131X_PCI_DEVICE_ID_FAST), 0UL},
diff --git a/drivers/staging/iio/industrialio-core.c b/drivers/staging/iio/industrialio-core.c
index 326e967..aec9311 100644
--- a/drivers/staging/iio/industrialio-core.c
+++ b/drivers/staging/iio/industrialio-core.c
@@ -242,19 +242,26 @@ static const struct file_operations iio_event_chrdev_fileops = {
 
 static int iio_event_getfd(struct iio_dev *indio_dev)
 {
-	if (indio_dev->event_interface == NULL)
+	struct iio_event_interface *ev_int = indio_dev->event_interface;
+	int fd;
+
+	if (ev_int == NULL)
 		return -ENODEV;
 
-	mutex_lock(&indio_dev->event_interface->event_list_lock);
-	if (test_and_set_bit(IIO_BUSY_BIT_POS,
-			     &indio_dev->event_interface->flags)) {
-		mutex_unlock(&indio_dev->event_interface->event_list_lock);
+	mutex_lock(&ev_int->event_list_lock);
+	if (test_and_set_bit(IIO_BUSY_BIT_POS, &ev_int->flags)) {
+		mutex_unlock(&ev_int->event_list_lock);
 		return -EBUSY;
 	}
-	mutex_unlock(&indio_dev->event_interface->event_list_lock);
-	return anon_inode_getfd("iio:event",
-				&iio_event_chrdev_fileops,
-				indio_dev->event_interface, O_RDONLY);
+	mutex_unlock(&ev_int->event_list_lock);
+	fd = anon_inode_getfd("iio:event",
+				&iio_event_chrdev_fileops, ev_int, O_RDONLY);
+	if (fd < 0) {
+		mutex_lock(&ev_int->event_list_lock);
+		clear_bit(IIO_BUSY_BIT_POS, &ev_int->flags);
+		mutex_unlock(&ev_int->event_list_lock);
+	}
+	return fd;
 }
 
 static int __init iio_init(void)
diff --git a/drivers/staging/media/as102/as102_drv.c b/drivers/staging/media/as102/as102_drv.c
index d335c7d..828526d 100644
--- a/drivers/staging/media/as102/as102_drv.c
+++ b/drivers/staging/media/as102/as102_drv.c
@@ -32,8 +32,8 @@
 #include "as102_fw.h"
 #include "dvbdev.h"
 
-int debug;
-module_param_named(debug, debug, int, 0644);
+int as102_debug;
+module_param_named(debug, as102_debug, int, 0644);
 MODULE_PARM_DESC(debug, "Turn on/off debugging (default: off)");
 
 int dual_tuner;
diff --git a/drivers/staging/media/as102/as102_drv.h b/drivers/staging/media/as102/as102_drv.h
index bcda635..fd33f5a 100644
--- a/drivers/staging/media/as102/as102_drv.h
+++ b/drivers/staging/media/as102/as102_drv.h
@@ -37,7 +37,8 @@ extern struct spi_driver as102_spi_driver;
 #define DRIVER_FULL_NAME "Abilis Systems as10x usb driver"
 #define DRIVER_NAME "as10x_usb"
 
-extern int debug;
+extern int as102_debug;
+#define debug	as102_debug
 
 #define dprintk(debug, args...) \
 	do { if (debug) {	\
diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c
index b445cd6..2542c37 100644
--- a/drivers/staging/octeon/ethernet-tx.c
+++ b/drivers/staging/octeon/ethernet-tx.c
@@ -275,7 +275,7 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
 		CVM_OCT_SKB_CB(skb)[0] = hw_buffer.u64;
 		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 			struct skb_frag_struct *fs = skb_shinfo(skb)->frags + i;
-			hw_buffer.s.addr = XKPHYS_TO_PHYS((u64)(page_address(fs->page) + fs->page_offset));
+			hw_buffer.s.addr = XKPHYS_TO_PHYS((u64)(page_address(fs->page.p) + fs->page_offset));
 			hw_buffer.s.size = fs->size;
 			CVM_OCT_SKB_CB(skb)[i + 1] = hw_buffer.u64;
 		}
diff --git a/drivers/staging/rts_pstor/rtsx.c b/drivers/staging/rts_pstor/rtsx.c
index 480b0ed..115635f 100644
--- a/drivers/staging/rts_pstor/rtsx.c
+++ b/drivers/staging/rts_pstor/rtsx.c
@@ -1021,6 +1021,7 @@ static int __devinit rtsx_probe(struct pci_dev *pci,
 	th = kthread_create(rtsx_scan_thread, dev, "rtsx-scan");
 	if (IS_ERR(th)) {
 		printk(KERN_ERR "Unable to start the device-scanning thread\n");
+		complete(&dev->scanning_done);
 		quiesce_and_remove_host(dev);
 		err = PTR_ERR(th);
 		goto errout;
diff --git a/drivers/staging/slicoss/Kconfig b/drivers/staging/slicoss/Kconfig
index 5cde96b..5c2a15b 100644
--- a/drivers/staging/slicoss/Kconfig
+++ b/drivers/staging/slicoss/Kconfig
@@ -1,6 +1,6 @@
 config SLICOSS
 	tristate "Alacritech Gigabit IS-NIC support"
-	depends on PCI && X86
+	depends on PCI && X86 && NET
 	default n
 	help
 	  This driver supports Alacritech's IS-NIC gigabit ethernet cards.
diff --git a/drivers/staging/usbip/vhci_rx.c b/drivers/staging/usbip/vhci_rx.c
index 09c44ab..3872b8c 100644
--- a/drivers/staging/usbip/vhci_rx.c
+++ b/drivers/staging/usbip/vhci_rx.c
@@ -68,6 +68,7 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev,
 {
 	struct usbip_device *ud = &vdev->ud;
 	struct urb *urb;
+	unsigned long flags;
 
 	spin_lock(&vdev->priv_lock);
 	urb = pickup_urb_and_free_priv(vdev, pdu->base.seqnum);
@@ -101,9 +102,9 @@ static void vhci_recv_ret_submit(struct vhci_device *vdev,
 
 	usbip_dbg_vhci_rx("now giveback urb %p\n", urb);
 
-	spin_lock(&the_controller->lock);
+	spin_lock_irqsave(&the_controller->lock, flags);
 	usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb);
-	spin_unlock(&the_controller->lock);
+	spin_unlock_irqrestore(&the_controller->lock, flags);
 
 	usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb, urb->status);
 
@@ -141,6 +142,7 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev,
 {
 	struct vhci_unlink *unlink;
 	struct urb *urb;
+	unsigned long flags;
 
 	usbip_dump_header(pdu);
 
@@ -170,9 +172,9 @@ static void vhci_recv_ret_unlink(struct vhci_device *vdev,
 		urb->status = pdu->u.ret_unlink.status;
 		pr_info("urb->status %d\n", urb->status);
 
-		spin_lock(&the_controller->lock);
+		spin_lock_irqsave(&the_controller->lock, flags);
 		usb_hcd_unlink_urb_from_ep(vhci_to_hcd(the_controller), urb);
-		spin_unlock(&the_controller->lock);
+		spin_unlock_irqrestore(&the_controller->lock, flags);
 
 		usb_hcd_giveback_urb(vhci_to_hcd(the_controller), urb,
 				     urb->status);
diff --git a/drivers/tty/hvc/hvc_dcc.c b/drivers/tty/hvc/hvc_dcc.c
index 435f6fa..44fbeba 100644
--- a/drivers/tty/hvc/hvc_dcc.c
+++ b/drivers/tty/hvc/hvc_dcc.c
@@ -46,6 +46,7 @@ static inline char __dcc_getchar(void)
 
 	asm volatile("mrc p14, 0, %0, c0, c5, 0	@ read comms data reg"
 		: "=r" (__c));
+	isb();
 
 	return __c;
 }
@@ -55,6 +56,7 @@ static inline void __dcc_putchar(char c)
 	asm volatile("mcr p14, 0, %0, c0, c5, 0	@ write a char"
 		: /* no output register */
 		: "r" (c));
+	isb();
 }
 
 static int hvc_dcc_put_chars(uint32_t vt, const char *buf, int count)
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 5f479da..925a1e5 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -1560,7 +1560,7 @@ config SERIAL_IFX6X60
 	  Support for the IFX6x60 modem devices on Intel MID platforms.
 
 config SERIAL_PCH_UART
-	tristate "Intel EG20T PCH / OKI SEMICONDUCTOR IOH(ML7213/ML7223) UART"
+	tristate "Intel EG20T PCH/LAPIS Semicon IOH(ML7213/ML7223/ML7831) UART"
 	depends on PCI
 	select SERIAL_CORE
 	help
@@ -1568,12 +1568,12 @@ config SERIAL_PCH_UART
 	  which is an IOH(Input/Output Hub) for x86 embedded processor.
 	  Enabling PCH_DMA, this PCH UART works as DMA mode.
 
-	  This driver also can be used for OKI SEMICONDUCTOR IOH(Input/
-	  Output Hub), ML7213 and ML7223.
-	  ML7213 IOH is for IVI(In-Vehicle Infotainment) use and ML7223 IOH is
-	  for MP(Media Phone) use.
-	  ML7213/ML7223 is companion chip for Intel Atom E6xx series.
-	  ML7213/ML7223 is completely compatible for Intel EG20T PCH.
+	  This driver also can be used for LAPIS Semiconductor IOH(Input/
+	  Output Hub), ML7213, ML7223 and ML7831.
+	  ML7213 IOH is for IVI(In-Vehicle Infotainment) use, ML7223 IOH is
+	  for MP(Media Phone) use and ML7831 IOH is for general purpose use.
+	  ML7213/ML7223/ML7831 is companion chip for Intel Atom E6xx series.
+	  ML7213/ML7223/ML7831 is completely compatible for Intel EG20T PCH.
 
 config SERIAL_MSM_SMD
 	bool "Enable tty device interface for some SMD ports"
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 4a0f86f..4c823f3 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -228,7 +228,7 @@ void atmel_config_rs485(struct uart_port *port, struct serial_rs485 *rs485conf)
 	if (rs485conf->flags & SER_RS485_ENABLED) {
 		dev_dbg(port->dev, "Setting UART to RS485\n");
 		atmel_port->tx_done_mask = ATMEL_US_TXEMPTY;
-		if (rs485conf->flags & SER_RS485_RTS_AFTER_SEND)
+		if ((rs485conf->delay_rts_after_send) > 0)
 			UART_PUT_TTGR(port, rs485conf->delay_rts_after_send);
 		mode |= ATMEL_US_USMODE_RS485;
 	} else {
@@ -304,7 +304,7 @@ static void atmel_set_mctrl(struct uart_port *port, u_int mctrl)
 
 	if (atmel_port->rs485.flags & SER_RS485_ENABLED) {
 		dev_dbg(port->dev, "Setting UART to RS485\n");
-		if (atmel_port->rs485.flags & SER_RS485_RTS_AFTER_SEND)
+		if ((atmel_port->rs485.delay_rts_after_send) > 0)
 			UART_PUT_TTGR(port,
 					atmel_port->rs485.delay_rts_after_send);
 		mode |= ATMEL_US_USMODE_RS485;
@@ -1228,7 +1228,7 @@ static void atmel_set_termios(struct uart_port *port, struct ktermios *termios,
 
 	if (atmel_port->rs485.flags & SER_RS485_ENABLED) {
 		dev_dbg(port->dev, "Setting UART to RS485\n");
-		if (atmel_port->rs485.flags & SER_RS485_RTS_AFTER_SEND)
+		if ((atmel_port->rs485.delay_rts_after_send) > 0)
 			UART_PUT_TTGR(port,
 					atmel_port->rs485.delay_rts_after_send);
 		mode |= ATMEL_US_USMODE_RS485;
@@ -1447,16 +1447,6 @@ static void __devinit atmel_of_init_port(struct atmel_uart_port *atmel_port,
 		rs485conf->delay_rts_after_send = rs485_delay[1];
 		rs485conf->flags = 0;
 
-		if (rs485conf->delay_rts_before_send == 0 &&
-		    rs485conf->delay_rts_after_send == 0) {
-			rs485conf->flags |= SER_RS485_RTS_ON_SEND;
-		} else {
-			if (rs485conf->delay_rts_before_send)
-				rs485conf->flags |= SER_RS485_RTS_BEFORE_SEND;
-			if (rs485conf->delay_rts_after_send)
-				rs485conf->flags |= SER_RS485_RTS_AFTER_SEND;
-		}
-
 		if (of_get_property(np, "rs485-rx-during-tx", NULL))
 			rs485conf->flags |= SER_RS485_RX_DURING_TX;
 
diff --git a/drivers/tty/serial/crisv10.c b/drivers/tty/serial/crisv10.c
index b743504..1dfba7b 100644
--- a/drivers/tty/serial/crisv10.c
+++ b/drivers/tty/serial/crisv10.c
@@ -3234,9 +3234,8 @@ rs_write(struct tty_struct *tty,
 		e100_disable_rx(info);
 		e100_enable_rx_irq(info);
 #endif
-		if ((info->rs485.flags & SER_RS485_RTS_BEFORE_SEND) &&
-			(info->rs485.delay_rts_before_send > 0))
-				msleep(info->rs485.delay_rts_before_send);
+		if (info->rs485.delay_rts_before_send > 0)
+			msleep(info->rs485.delay_rts_before_send);
 	}
 #endif /* CONFIG_ETRAX_RS485 */
 
@@ -3693,10 +3692,6 @@ rs_ioctl(struct tty_struct *tty,
 
 		rs485data.delay_rts_before_send = rs485ctrl.delay_rts_before_send;
 		rs485data.flags = 0;
-		if (rs485data.delay_rts_before_send != 0)
-			rs485data.flags |= SER_RS485_RTS_BEFORE_SEND;
-		else
-			rs485data.flags &= ~(SER_RS485_RTS_BEFORE_SEND);
 
 		if (rs485ctrl.enabled)
 			rs485data.flags |= SER_RS485_ENABLED;
@@ -4531,7 +4526,6 @@ static int __init rs_init(void)
 		/* Set sane defaults */
 		info->rs485.flags &= ~(SER_RS485_RTS_ON_SEND);
 		info->rs485.flags |= SER_RS485_RTS_AFTER_SEND;
-		info->rs485.flags &= ~(SER_RS485_RTS_BEFORE_SEND);
 		info->rs485.delay_rts_before_send = 0;
 		info->rs485.flags &= ~(SER_RS485_ENABLED);
 #endif
diff --git a/drivers/tty/serial/mfd.c b/drivers/tty/serial/mfd.c
index 286c386..e272d39 100644
--- a/drivers/tty/serial/mfd.c
+++ b/drivers/tty/serial/mfd.c
@@ -884,7 +884,6 @@ serial_hsu_set_termios(struct uart_port *port, struct ktermios *termios,
 {
 	struct uart_hsu_port *up =
 			container_of(port, struct uart_hsu_port, port);
-	struct tty_struct *tty = port->state->port.tty;
 	unsigned char cval, fcr = 0;
 	unsigned long flags;
 	unsigned int baud, quot;
@@ -907,8 +906,7 @@ serial_hsu_set_termios(struct uart_port *port, struct ktermios *termios,
 	}
 
 	/* CMSPAR isn't supported by this driver */
-	if (tty)
-		tty->termios->c_cflag &= ~CMSPAR;
+	termios->c_cflag &= ~CMSPAR;
 
 	if (termios->c_cflag & CSTOPB)
 		cval |= UART_LCR_STOP;
diff --git a/drivers/tty/serial/pch_uart.c b/drivers/tty/serial/pch_uart.c
index 21febef..d6aba8c 100644
--- a/drivers/tty/serial/pch_uart.c
+++ b/drivers/tty/serial/pch_uart.c
@@ -1,5 +1,5 @@
 /*
- *Copyright (C) 2010 OKI SEMICONDUCTOR CO., LTD.
+ *Copyright (C) 2011 LAPIS Semiconductor Co., Ltd.
  *
  *This program is free software; you can redistribute it and/or modify
  *it under the terms of the GNU General Public License as published by
@@ -46,8 +46,8 @@ enum {
 
 /* Set the max number of UART port
  * Intel EG20T PCH: 4 port
- * OKI SEMICONDUCTOR ML7213 IOH: 3 port
- * OKI SEMICONDUCTOR ML7223 IOH: 2 port
+ * LAPIS Semiconductor ML7213 IOH: 3 port
+ * LAPIS Semiconductor ML7223 IOH: 2 port
 */
 #define PCH_UART_NR	4
 
@@ -258,6 +258,8 @@ enum pch_uart_num_t {
 	pch_ml7213_uart2,
 	pch_ml7223_uart0,
 	pch_ml7223_uart1,
+	pch_ml7831_uart0,
+	pch_ml7831_uart1,
 };
 
 static struct pch_uart_driver_data drv_dat[] = {
@@ -270,6 +272,8 @@ static struct pch_uart_driver_data drv_dat[] = {
 	[pch_ml7213_uart2] = {PCH_UART_2LINE, 2},
 	[pch_ml7223_uart0] = {PCH_UART_8LINE, 0},
 	[pch_ml7223_uart1] = {PCH_UART_2LINE, 1},
+	[pch_ml7831_uart0] = {PCH_UART_8LINE, 0},
+	[pch_ml7831_uart1] = {PCH_UART_2LINE, 1},
 };
 
 static unsigned int default_baud = 9600;
@@ -628,6 +632,7 @@ static void pch_request_dma(struct uart_port *port)
 		dev_err(priv->port.dev, "%s:dma_request_channel FAILS(Rx)\n",
 			__func__);
 		dma_release_channel(priv->chan_tx);
+		priv->chan_tx = NULL;
 		return;
 	}
 
@@ -1215,8 +1220,7 @@ static void pch_uart_shutdown(struct uart_port *port)
 		dev_err(priv->port.dev,
 			"pch_uart_hal_set_fifo Failed(ret=%d)\n", ret);
 
-	if (priv->use_dma_flag)
-		pch_free_dma(port);
+	pch_free_dma(port);
 
 	free_irq(priv->port.irq, priv);
 }
@@ -1280,6 +1284,7 @@ static void pch_uart_set_termios(struct uart_port *port,
 	if (rtn)
 		goto out;
 
+	pch_uart_set_mctrl(&priv->port, priv->port.mctrl);
 	/* Don't rewrite B0 */
 	if (tty_termios_baud_rate(termios))
 		tty_termios_encode_baud_rate(termios, baud, baud);
@@ -1552,6 +1557,10 @@ static DEFINE_PCI_DEVICE_TABLE(pch_uart_pci_id) = {
 	 .driver_data = pch_ml7223_uart0},
 	{PCI_DEVICE(PCI_VENDOR_ID_ROHM, 0x800D),
 	 .driver_data = pch_ml7223_uart1},
+	{PCI_DEVICE(PCI_VENDOR_ID_ROHM, 0x8811),
+	 .driver_data = pch_ml7831_uart0},
+	{PCI_DEVICE(PCI_VENDOR_ID_ROHM, 0x8812),
+	 .driver_data = pch_ml7831_uart1},
 	{0,},
 };
 
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index 512c49f..8e0924f 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -36,6 +36,7 @@
 
 #include <linux/kmod.h>
 #include <linux/nsproxy.h>
+#include <linux/ratelimit.h>
 
 /*
  *	This guards the refcounted line discipline lists. The lock
@@ -547,15 +548,16 @@ static void tty_ldisc_flush_works(struct tty_struct *tty)
 /**
  *	tty_ldisc_wait_idle	-	wait for the ldisc to become idle
  *	@tty: tty to wait for
+ *	@timeout: for how long to wait at most
  *
  *	Wait for the line discipline to become idle. The discipline must
  *	have been halted for this to guarantee it remains idle.
  */
-static int tty_ldisc_wait_idle(struct tty_struct *tty)
+static int tty_ldisc_wait_idle(struct tty_struct *tty, long timeout)
 {
-	int ret;
+	long ret;
 	ret = wait_event_timeout(tty_ldisc_idle,
-			atomic_read(&tty->ldisc->users) == 1, 5 * HZ);
+			atomic_read(&tty->ldisc->users) == 1, timeout);
 	if (ret < 0)
 		return ret;
 	return ret > 0 ? 0 : -EBUSY;
@@ -665,7 +667,7 @@ int tty_set_ldisc(struct tty_struct *tty, int ldisc)
 
 	tty_ldisc_flush_works(tty);
 
-	retval = tty_ldisc_wait_idle(tty);
+	retval = tty_ldisc_wait_idle(tty, 5 * HZ);
 
 	tty_lock();
 	mutex_lock(&tty->ldisc_mutex);
@@ -762,8 +764,6 @@ static int tty_ldisc_reinit(struct tty_struct *tty, int ldisc)
 	if (IS_ERR(ld))
 		return -1;
 
-	WARN_ON_ONCE(tty_ldisc_wait_idle(tty));
-
 	tty_ldisc_close(tty, tty->ldisc);
 	tty_ldisc_put(tty->ldisc);
 	tty->ldisc = NULL;
@@ -838,7 +838,7 @@ void tty_ldisc_hangup(struct tty_struct *tty)
 	tty_unlock();
 	cancel_work_sync(&tty->buf.work);
 	mutex_unlock(&tty->ldisc_mutex);
-
+retry:
 	tty_lock();
 	mutex_lock(&tty->ldisc_mutex);
 
@@ -847,6 +847,22 @@ void tty_ldisc_hangup(struct tty_struct *tty)
 	   it means auditing a lot of other paths so this is
 	   a FIXME */
 	if (tty->ldisc) {	/* Not yet closed */
+		if (atomic_read(&tty->ldisc->users) != 1) {
+			char cur_n[TASK_COMM_LEN], tty_n[64];
+			long timeout = 3 * HZ;
+			tty_unlock();
+
+			while (tty_ldisc_wait_idle(tty, timeout) == -EBUSY) {
+				timeout = MAX_SCHEDULE_TIMEOUT;
+				printk_ratelimited(KERN_WARNING
+					"%s: waiting (%s) for %s took too long, but we keep waiting...\n",
+					__func__, get_task_comm(cur_n, current),
+					tty_name(tty, tty_n));
+			}
+			mutex_unlock(&tty->ldisc_mutex);
+			goto retry;
+		}
+
 		if (reset == 0) {
 
 			if (!tty_ldisc_reinit(tty, tty->termios->c_line))
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 6960715..e8c564a 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -539,7 +539,6 @@ static void acm_port_down(struct acm *acm)
 {
 	int i;
 
-	mutex_lock(&open_mutex);
 	if (acm->dev) {
 		usb_autopm_get_interface(acm->control);
 		acm_set_control(acm, acm->ctrlout = 0);
@@ -551,14 +550,15 @@ static void acm_port_down(struct acm *acm)
 		acm->control->needs_remote_wakeup = 0;
 		usb_autopm_put_interface(acm->control);
 	}
-	mutex_unlock(&open_mutex);
 }
 
 static void acm_tty_hangup(struct tty_struct *tty)
 {
 	struct acm *acm = tty->driver_data;
 	tty_port_hangup(&acm->port);
+	mutex_lock(&open_mutex);
 	acm_port_down(acm);
+	mutex_unlock(&open_mutex);
 }
 
 static void acm_tty_close(struct tty_struct *tty, struct file *filp)
@@ -569,8 +569,9 @@ static void acm_tty_close(struct tty_struct *tty, struct file *filp)
 	   shutdown */
 	if (!acm)
 		return;
+
+	mutex_lock(&open_mutex);
 	if (tty_port_close_start(&acm->port, tty, filp) == 0) {
-		mutex_lock(&open_mutex);
 		if (!acm->dev) {
 			tty_port_tty_set(&acm->port, NULL);
 			acm_tty_unregister(acm);
@@ -582,6 +583,7 @@ static void acm_tty_close(struct tty_struct *tty, struct file *filp)
 	acm_port_down(acm);
 	tty_port_close_end(&acm->port, tty);
 	tty_port_tty_set(&acm->port, NULL);
+	mutex_unlock(&open_mutex);
 }
 
 static int acm_tty_write(struct tty_struct *tty,
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 96f05b2..7978146 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -813,6 +813,12 @@ static void hub_activate(struct usb_hub *hub, enum hub_activation_type type)
 					USB_PORT_FEAT_C_PORT_LINK_STATE);
 		}
 
+		if ((portchange & USB_PORT_STAT_C_BH_RESET) &&
+				hub_is_superspeed(hub->hdev)) {
+			need_debounce_delay = true;
+			clear_port_feature(hub->hdev, port1,
+					USB_PORT_FEAT_C_BH_PORT_RESET);
+		}
 		/* We can forget about a "removed" device when there's a
 		 * physical disconnect or the connect status changes.
 		 */
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index d6a8d82..ecf12e1 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -50,15 +50,42 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Logitech Webcam B/C500 */
 	{ USB_DEVICE(0x046d, 0x0807), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* Logitech Webcam C600 */
+	{ USB_DEVICE(0x046d, 0x0808), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	/* Logitech Webcam Pro 9000 */
 	{ USB_DEVICE(0x046d, 0x0809), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* Logitech Webcam C905 */
+	{ USB_DEVICE(0x046d, 0x080a), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Webcam C210 */
+	{ USB_DEVICE(0x046d, 0x0819), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Webcam C260 */
+	{ USB_DEVICE(0x046d, 0x081a), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	/* Logitech Webcam C310 */
 	{ USB_DEVICE(0x046d, 0x081b), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* Logitech Webcam C910 */
+	{ USB_DEVICE(0x046d, 0x0821), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Webcam C160 */
+	{ USB_DEVICE(0x046d, 0x0824), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	/* Logitech Webcam C270 */
 	{ USB_DEVICE(0x046d, 0x0825), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* Logitech Quickcam Pro 9000 */
+	{ USB_DEVICE(0x046d, 0x0990), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Quickcam E3500 */
+	{ USB_DEVICE(0x046d, 0x09a4), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Logitech Quickcam Vision Pro */
+	{ USB_DEVICE(0x046d, 0x09a6), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	/* Logitech Harmony 700-series */
 	{ USB_DEVICE(0x046d, 0xc122), .driver_info = USB_QUIRK_DELAY_INIT },
 
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index fa824cf..25dbd86 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -1284,6 +1284,7 @@ static int __devinit dwc3_gadget_init_endpoints(struct dwc3 *dwc)
 			int		ret;
 
 			dep->endpoint.maxpacket = 1024;
+			dep->endpoint.max_streams = 15;
 			dep->endpoint.ops = &dwc3_gadget_ep_ops;
 			list_add_tail(&dep->endpoint.ep_list,
 					&dwc->gadget.ep_list);
diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index b21cd37..23a4473 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -469,7 +469,7 @@ config USB_LANGWELL
 	   gadget drivers to also be dynamically linked.
 
 config USB_EG20T
-	tristate "Intel EG20T PCH/OKI SEMICONDUCTOR ML7213 IOH UDC"
+	tristate "Intel EG20T PCH/LAPIS Semiconductor IOH(ML7213/ML7831) UDC"
 	depends on PCI
 	select USB_GADGET_DUALSPEED
 	help
@@ -485,10 +485,11 @@ config USB_EG20T
 	  This driver dose not support interrupt transfer or isochronous
 	  transfer modes.
 
-	  This driver also can be used for OKI SEMICONDUCTOR's ML7213 which is
+	  This driver also can be used for LAPIS Semiconductor's ML7213 which is
 	  for IVI(In-Vehicle Infotainment) use.
-	  ML7213 is companion chip for Intel Atom E6xx series.
-	  ML7213 is completely compatible for Intel EG20T PCH.
+	  ML7831 is for general purpose use.
+	  ML7213/ML7831 is companion chip for Intel Atom E6xx series.
+	  ML7213/ML7831 is completely compatible for Intel EG20T PCH.
 
 config USB_CI13XXX_MSM
 	tristate "MIPS USB CI13xxx for MSM"
diff --git a/drivers/usb/gadget/amd5536udc.c b/drivers/usb/gadget/amd5536udc.c
index 4730016..45f422a 100644
--- a/drivers/usb/gadget/amd5536udc.c
+++ b/drivers/usb/gadget/amd5536udc.c
@@ -1959,7 +1959,7 @@ static int amd5536_start(struct usb_gadget_driver *driver,
 	u32 tmp;
 
 	if (!driver || !bind || !driver->setup
-			|| driver->speed != USB_SPEED_HIGH)
+			|| driver->speed < USB_SPEED_HIGH)
 		return -EINVAL;
 	if (!dev)
 		return -ENODEV;
diff --git a/drivers/usb/gadget/ci13xxx_msm.c b/drivers/usb/gadget/ci13xxx_msm.c
index 4eedfe5..1fc6129 100644
--- a/drivers/usb/gadget/ci13xxx_msm.c
+++ b/drivers/usb/gadget/ci13xxx_msm.c
@@ -122,3 +122,5 @@ static int __init ci13xxx_msm_init(void)
 	return platform_driver_register(&ci13xxx_msm_driver);
 }
 module_init(ci13xxx_msm_init);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/usb/gadget/ci13xxx_udc.c b/drivers/usb/gadget/ci13xxx_udc.c
index 83428f5..9a0c397 100644
--- a/drivers/usb/gadget/ci13xxx_udc.c
+++ b/drivers/usb/gadget/ci13xxx_udc.c
@@ -71,6 +71,9 @@
 /******************************************************************************
  * DEFINE
  *****************************************************************************/
+
+#define DMA_ADDR_INVALID	(~(dma_addr_t)0)
+
 /* ctrl register bank access */
 static DEFINE_SPINLOCK(udc_lock);
 
@@ -1434,7 +1437,7 @@ static int _hardware_enqueue(struct ci13xxx_ep *mEp, struct ci13xxx_req *mReq)
 		return -EALREADY;
 
 	mReq->req.status = -EALREADY;
-	if (length && !mReq->req.dma) {
+	if (length && mReq->req.dma == DMA_ADDR_INVALID) {
 		mReq->req.dma = \
 			dma_map_single(mEp->device, mReq->req.buf,
 				       length, mEp->dir ? DMA_TO_DEVICE :
@@ -1453,7 +1456,7 @@ static int _hardware_enqueue(struct ci13xxx_ep *mEp, struct ci13xxx_req *mReq)
 				dma_unmap_single(mEp->device, mReq->req.dma,
 					length, mEp->dir ? DMA_TO_DEVICE :
 					DMA_FROM_DEVICE);
-				mReq->req.dma = 0;
+				mReq->req.dma = DMA_ADDR_INVALID;
 				mReq->map     = 0;
 			}
 			return -ENOMEM;
@@ -1549,7 +1552,7 @@ static int _hardware_dequeue(struct ci13xxx_ep *mEp, struct ci13xxx_req *mReq)
 	if (mReq->map) {
 		dma_unmap_single(mEp->device, mReq->req.dma, mReq->req.length,
 				 mEp->dir ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
-		mReq->req.dma = 0;
+		mReq->req.dma = DMA_ADDR_INVALID;
 		mReq->map     = 0;
 	}
 
@@ -1610,7 +1613,6 @@ __acquires(mEp->lock)
  * @gadget: gadget
  *
  * This function returns an error code
- * Caller must hold lock
  */
 static int _gadget_stop_activity(struct usb_gadget *gadget)
 {
@@ -2189,6 +2191,7 @@ static struct usb_request *ep_alloc_request(struct usb_ep *ep, gfp_t gfp_flags)
 	mReq = kzalloc(sizeof(struct ci13xxx_req), gfp_flags);
 	if (mReq != NULL) {
 		INIT_LIST_HEAD(&mReq->queue);
+		mReq->req.dma = DMA_ADDR_INVALID;
 
 		mReq->ptr = dma_pool_alloc(mEp->td_pool, gfp_flags,
 					   &mReq->dma);
@@ -2328,7 +2331,7 @@ static int ep_dequeue(struct usb_ep *ep, struct usb_request *req)
 	if (mReq->map) {
 		dma_unmap_single(mEp->device, mReq->req.dma, mReq->req.length,
 				 mEp->dir ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
-		mReq->req.dma = 0;
+		mReq->req.dma = DMA_ADDR_INVALID;
 		mReq->map     = 0;
 	}
 	req->status = -ECONNRESET;
@@ -2500,12 +2503,12 @@ static int ci13xxx_wakeup(struct usb_gadget *_gadget)
 	spin_lock_irqsave(udc->lock, flags);
 	if (!udc->remote_wakeup) {
 		ret = -EOPNOTSUPP;
-		dbg_trace("remote wakeup feature is not enabled\n");
+		trace("remote wakeup feature is not enabled\n");
 		goto out;
 	}
 	if (!hw_cread(CAP_PORTSC, PORTSC_SUSP)) {
 		ret = -EINVAL;
-		dbg_trace("port is not suspended\n");
+		trace("port is not suspended\n");
 		goto out;
 	}
 	hw_cwrite(CAP_PORTSC, PORTSC_FPR, PORTSC_FPR);
@@ -2703,7 +2706,9 @@ static int ci13xxx_stop(struct usb_gadget_driver *driver)
 		if (udc->udc_driver->notify_event)
 			udc->udc_driver->notify_event(udc,
 			CI13XXX_CONTROLLER_STOPPED_EVENT);
+		spin_unlock_irqrestore(udc->lock, flags);
 		_gadget_stop_activity(&udc->gadget);
+		spin_lock_irqsave(udc->lock, flags);
 		pm_runtime_put(&udc->gadget.dev);
 	}
 
@@ -2850,7 +2855,7 @@ static int udc_probe(struct ci13xxx_udc_driver *driver, struct device *dev,
 	struct ci13xxx *udc;
 	int retval = 0;
 
-	trace("%p, %p, %p", dev, regs, name);
+	trace("%p, %p, %p", dev, regs, driver->name);
 
 	if (dev == NULL || regs == NULL || driver == NULL ||
 			driver->name == NULL)
diff --git a/drivers/usb/gadget/f_mass_storage.c b/drivers/usb/gadget/f_mass_storage.c
index 52583a2..c39d588 100644
--- a/drivers/usb/gadget/f_mass_storage.c
+++ b/drivers/usb/gadget/f_mass_storage.c
@@ -624,7 +624,8 @@ static int fsg_setup(struct usb_function *f,
 		if (ctrl->bRequestType !=
 		    (USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE))
 			break;
-		if (w_index != fsg->interface_number || w_value != 0)
+		if (w_index != fsg->interface_number || w_value != 0 ||
+				w_length != 0)
 			return -EDOM;
 
 		/*
@@ -639,7 +640,8 @@ static int fsg_setup(struct usb_function *f,
 		if (ctrl->bRequestType !=
 		    (USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE))
 			break;
-		if (w_index != fsg->interface_number || w_value != 0)
+		if (w_index != fsg->interface_number || w_value != 0 ||
+				w_length != 1)
 			return -EDOM;
 		VDBG(fsg, "get max LUN\n");
 		*(u8 *)req->buf = fsg->common->nluns - 1;
diff --git a/drivers/usb/gadget/f_midi.c b/drivers/usb/gadget/f_midi.c
index 67b2229..3797b3d 100644
--- a/drivers/usb/gadget/f_midi.c
+++ b/drivers/usb/gadget/f_midi.c
@@ -95,7 +95,6 @@ static void f_midi_transmit(struct f_midi *midi, struct usb_request *req);
 
 DECLARE_UAC_AC_HEADER_DESCRIPTOR(1);
 DECLARE_USB_MIDI_OUT_JACK_DESCRIPTOR(1);
-DECLARE_USB_MIDI_OUT_JACK_DESCRIPTOR(16);
 DECLARE_USB_MS_ENDPOINT_DESCRIPTOR(16);
 
 /* B.3.1  Standard AC Interface Descriptor */
@@ -140,26 +139,6 @@ static struct usb_ms_header_descriptor ms_header_desc __initdata = {
 	/* .wTotalLength =	DYNAMIC */
 };
 
-/* B.4.3  Embedded MIDI IN Jack Descriptor */
-static struct usb_midi_in_jack_descriptor jack_in_emb_desc = {
-	.bLength =	      USB_DT_MIDI_IN_SIZE,
-	.bDescriptorType =      USB_DT_CS_INTERFACE,
-	.bDescriptorSubtype =   USB_MS_MIDI_IN_JACK,
-	.bJackType =	    USB_MS_EMBEDDED,
-	/* .bJackID =		DYNAMIC */
-};
-
-/* B.4.4  Embedded MIDI OUT Jack Descriptor */
-static struct usb_midi_out_jack_descriptor_16 jack_out_emb_desc = {
-	/* .bLength =		DYNAMIC */
-	.bDescriptorType =	USB_DT_CS_INTERFACE,
-	.bDescriptorSubtype =	USB_MS_MIDI_OUT_JACK,
-	.bJackType =		USB_MS_EMBEDDED,
-	/* .bJackID =		DYNAMIC */
-	/* .bNrInputPins =	DYNAMIC */
-	/* .pins =		DYNAMIC */
-};
-
 /* B.5.1  Standard Bulk OUT Endpoint Descriptor */
 static struct usb_endpoint_descriptor bulk_out_desc = {
 	.bLength =		USB_DT_ENDPOINT_AUDIO_SIZE,
@@ -758,9 +737,11 @@ fail:
 static int __init
 f_midi_bind(struct usb_configuration *c, struct usb_function *f)
 {
-	struct usb_descriptor_header *midi_function[(MAX_PORTS * 2) + 12];
+	struct usb_descriptor_header **midi_function;
 	struct usb_midi_in_jack_descriptor jack_in_ext_desc[MAX_PORTS];
+	struct usb_midi_in_jack_descriptor jack_in_emb_desc[MAX_PORTS];
 	struct usb_midi_out_jack_descriptor_1 jack_out_ext_desc[MAX_PORTS];
+	struct usb_midi_out_jack_descriptor_1 jack_out_emb_desc[MAX_PORTS];
 	struct usb_composite_dev *cdev = c->cdev;
 	struct f_midi *midi = func_to_midi(f);
 	int status, n, jack = 1, i = 0;
@@ -798,6 +779,14 @@ f_midi_bind(struct usb_configuration *c, struct usb_function *f)
 		goto fail;
 	midi->out_ep->driver_data = cdev;	/* claim */
 
+	/* allocate temporary function list */
+	midi_function = kcalloc((MAX_PORTS * 4) + 9, sizeof(midi_function),
+				GFP_KERNEL);
+	if (!midi_function) {
+		status = -ENOMEM;
+		goto fail;
+	}
+
 	/*
 	 * construct the function's descriptor set. As the number of
 	 * input and output MIDI ports is configurable, we have to do
@@ -811,73 +800,74 @@ f_midi_bind(struct usb_configuration *c, struct usb_function *f)
 
 	/* calculate the header's wTotalLength */
 	n = USB_DT_MS_HEADER_SIZE
-		+ (1 + midi->in_ports) * USB_DT_MIDI_IN_SIZE
-		+ (1 + midi->out_ports) * USB_DT_MIDI_OUT_SIZE(1);
+		+ (midi->in_ports + midi->out_ports) *
+			(USB_DT_MIDI_IN_SIZE + USB_DT_MIDI_OUT_SIZE(1));
 	ms_header_desc.wTotalLength = cpu_to_le16(n);
 
 	midi_function[i++] = (struct usb_descriptor_header *) &ms_header_desc;
 
-	/* we have one embedded IN jack */
-	jack_in_emb_desc.bJackID = jack++;
-	midi_function[i++] = (struct usb_descriptor_header *) &jack_in_emb_desc;
-
-	/* and a dynamic amount of external IN jacks */
-	for (n = 0; n < midi->in_ports; n++) {
-		struct usb_midi_in_jack_descriptor *ext = &jack_in_ext_desc[n];
-
-		ext->bLength =			USB_DT_MIDI_IN_SIZE;
-		ext->bDescriptorType =		USB_DT_CS_INTERFACE;
-		ext->bDescriptorSubtype =	USB_MS_MIDI_IN_JACK;
-		ext->bJackType =		USB_MS_EXTERNAL;
-		ext->bJackID =			jack++;
-		ext->iJack =			0;
-
-		midi_function[i++] = (struct usb_descriptor_header *) ext;
-	}
-
-	/* one embedded OUT jack ... */
-	jack_out_emb_desc.bLength = USB_DT_MIDI_OUT_SIZE(midi->in_ports);
-	jack_out_emb_desc.bJackID = jack++;
-	jack_out_emb_desc.bNrInputPins = midi->in_ports;
-	/* ... which referencess all external IN jacks */
+	/* configure the external IN jacks, each linked to an embedded OUT jack */
 	for (n = 0; n < midi->in_ports; n++) {
-		jack_out_emb_desc.pins[n].baSourceID = jack_in_ext_desc[n].bJackID;
-		jack_out_emb_desc.pins[n].baSourcePin =	1;
+		struct usb_midi_in_jack_descriptor *in_ext = &jack_in_ext_desc[n];
+		struct usb_midi_out_jack_descriptor_1 *out_emb = &jack_out_emb_desc[n];
+
+		in_ext->bLength			= USB_DT_MIDI_IN_SIZE;
+		in_ext->bDescriptorType		= USB_DT_CS_INTERFACE;
+		in_ext->bDescriptorSubtype	= USB_MS_MIDI_IN_JACK;
+		in_ext->bJackType		= USB_MS_EXTERNAL;
+		in_ext->bJackID			= jack++;
+		in_ext->iJack			= 0;
+		midi_function[i++] = (struct usb_descriptor_header *) in_ext;
+
+		out_emb->bLength		= USB_DT_MIDI_OUT_SIZE(1);
+		out_emb->bDescriptorType	= USB_DT_CS_INTERFACE;
+		out_emb->bDescriptorSubtype	= USB_MS_MIDI_OUT_JACK;
+		out_emb->bJackType		= USB_MS_EMBEDDED;
+		out_emb->bJackID		= jack++;
+		out_emb->bNrInputPins		= 1;
+		out_emb->pins[0].baSourcePin	= 1;
+		out_emb->pins[0].baSourceID	= in_ext->bJackID;
+		out_emb->iJack			= 0;
+		midi_function[i++] = (struct usb_descriptor_header *) out_emb;
+
+		/* link it to the endpoint */
+		ms_in_desc.baAssocJackID[n] = out_emb->bJackID;
 	}
 
-	midi_function[i++] = (struct usb_descriptor_header *) &jack_out_emb_desc;
-
-	/* and multiple external OUT jacks ... */
+	/* configure the external OUT jacks, each linked to an embedded IN jack */
 	for (n = 0; n < midi->out_ports; n++) {
-		struct usb_midi_out_jack_descriptor_1 *ext = &jack_out_ext_desc[n];
-		int m;
-
-		ext->bLength =			USB_DT_MIDI_OUT_SIZE(1);
-		ext->bDescriptorType =		USB_DT_CS_INTERFACE;
-		ext->bDescriptorSubtype =	USB_MS_MIDI_OUT_JACK;
-		ext->bJackType =		USB_MS_EXTERNAL;
-		ext->bJackID =			jack++;
-		ext->bNrInputPins =		1;
-		ext->iJack =			0;
-		/* ... which all reference the same embedded IN jack */
-		for (m = 0; m < midi->out_ports; m++) {
-			ext->pins[m].baSourceID =	jack_in_emb_desc.bJackID;
-			ext->pins[m].baSourcePin =	1;
-		}
-
-		midi_function[i++] = (struct usb_descriptor_header *) ext;
+		struct usb_midi_in_jack_descriptor *in_emb = &jack_in_emb_desc[n];
+		struct usb_midi_out_jack_descriptor_1 *out_ext = &jack_out_ext_desc[n];
+
+		in_emb->bLength			= USB_DT_MIDI_IN_SIZE;
+		in_emb->bDescriptorType		= USB_DT_CS_INTERFACE;
+		in_emb->bDescriptorSubtype	= USB_MS_MIDI_IN_JACK;
+		in_emb->bJackType		= USB_MS_EMBEDDED;
+		in_emb->bJackID			= jack++;
+		in_emb->iJack			= 0;
+		midi_function[i++] = (struct usb_descriptor_header *) in_emb;
+
+		out_ext->bLength =		USB_DT_MIDI_OUT_SIZE(1);
+		out_ext->bDescriptorType =	USB_DT_CS_INTERFACE;
+		out_ext->bDescriptorSubtype =	USB_MS_MIDI_OUT_JACK;
+		out_ext->bJackType =		USB_MS_EXTERNAL;
+		out_ext->bJackID =		jack++;
+		out_ext->bNrInputPins =		1;
+		out_ext->iJack =		0;
+		out_ext->pins[0].baSourceID =	in_emb->bJackID;
+		out_ext->pins[0].baSourcePin =	1;
+		midi_function[i++] = (struct usb_descriptor_header *) out_ext;
+
+		/* link it to the endpoint */
+		ms_out_desc.baAssocJackID[n] = in_emb->bJackID;
 	}
 
 	/* configure the endpoint descriptors ... */
 	ms_out_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->in_ports);
 	ms_out_desc.bNumEmbMIDIJack = midi->in_ports;
-	for (n = 0; n < midi->in_ports; n++)
-		ms_out_desc.baAssocJackID[n] = jack_in_emb_desc.bJackID;
 
 	ms_in_desc.bLength = USB_DT_MS_ENDPOINT_SIZE(midi->out_ports);
 	ms_in_desc.bNumEmbMIDIJack = midi->out_ports;
-	for (n = 0; n < midi->out_ports; n++)
-		ms_in_desc.baAssocJackID[n] = jack_out_emb_desc.bJackID;
 
 	/* ... and add them to the list */
 	midi_function[i++] = (struct usb_descriptor_header *) &bulk_out_desc;
@@ -901,6 +891,8 @@ f_midi_bind(struct usb_configuration *c, struct usb_function *f)
 		f->descriptors = usb_copy_descriptors(midi_function);
 	}
 
+	kfree(midi_function);
+
 	return 0;
 
 fail:
diff --git a/drivers/usb/gadget/f_phonet.c b/drivers/usb/gadget/f_phonet.c
index 3490770..7cdcb63 100644
--- a/drivers/usb/gadget/f_phonet.c
+++ b/drivers/usb/gadget/f_phonet.c
@@ -298,11 +298,10 @@ static void pn_net_setup(struct net_device *dev)
 static int
 pn_rx_submit(struct f_phonet *fp, struct usb_request *req, gfp_t gfp_flags)
 {
-	struct net_device *dev = fp->dev;
 	struct page *page;
 	int err;
 
-	page = __netdev_alloc_page(dev, gfp_flags);
+	page = alloc_page(gfp_flags);
 	if (!page)
 		return -ENOMEM;
 
@@ -312,7 +311,7 @@ pn_rx_submit(struct f_phonet *fp, struct usb_request *req, gfp_t gfp_flags)
 
 	err = usb_ep_queue(fp->out_ep, req, gfp_flags);
 	if (unlikely(err))
-		netdev_free_page(dev, page);
+		put_page(page);
 	return err;
 }
 
@@ -346,7 +345,7 @@ static void pn_rx_complete(struct usb_ep *ep, struct usb_request *req)
 		}
 
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
-				skb->len == 0, req->actual);
+				skb->len <= 1, req->actual);
 		page = NULL;
 
 		if (req->actual < req->length) { /* Last fragment */
@@ -374,9 +373,9 @@ static void pn_rx_complete(struct usb_ep *ep, struct usb_request *req)
 	}
 
 	if (page)
-		netdev_free_page(dev, page);
+		put_page(page);
 	if (req)
-		pn_rx_submit(fp, req, GFP_ATOMIC);
+		pn_rx_submit(fp, req, GFP_ATOMIC | __GFP_COLD);
 }
 
 /*-------------------------------------------------------------------------*/
@@ -436,7 +435,7 @@ static int pn_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 
 			netif_carrier_on(dev);
 			for (i = 0; i < phonet_rxq_size; i++)
-				pn_rx_submit(fp, fp->out_reqv[i], GFP_ATOMIC);
+				pn_rx_submit(fp, fp->out_reqv[i], GFP_ATOMIC | __GFP_COLD);
 		}
 		spin_unlock(&port->lock);
 		return 0;
diff --git a/drivers/usb/gadget/f_serial.c b/drivers/usb/gadget/f_serial.c
index 91fdf79..cf33a8d 100644
--- a/drivers/usb/gadget/f_serial.c
+++ b/drivers/usb/gadget/f_serial.c
@@ -131,8 +131,8 @@ static int gser_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
 	}
 	if (!gser->port.in->desc || !gser->port.out->desc) {
 		DBG(cdev, "activate generic ttyGS%d\n", gser->port_num);
-		if (!config_ep_by_speed(cdev->gadget, f, gser->port.in) ||
-		    !config_ep_by_speed(cdev->gadget, f, gser->port.out)) {
+		if (config_ep_by_speed(cdev->gadget, f, gser->port.in) ||
+		    config_ep_by_speed(cdev->gadget, f, gser->port.out)) {
 			gser->port.in->desc = NULL;
 			gser->port.out->desc = NULL;
 			return -EINVAL;
diff --git a/drivers/usb/gadget/file_storage.c b/drivers/usb/gadget/file_storage.c
index f7e39b0..11b5196 100644
--- a/drivers/usb/gadget/file_storage.c
+++ b/drivers/usb/gadget/file_storage.c
@@ -859,7 +859,7 @@ static int class_setup_req(struct fsg_dev *fsg,
 			if (ctrl->bRequestType != (USB_DIR_OUT |
 					USB_TYPE_CLASS | USB_RECIP_INTERFACE))
 				break;
-			if (w_index != 0 || w_value != 0) {
+			if (w_index != 0 || w_value != 0 || w_length != 0) {
 				value = -EDOM;
 				break;
 			}
@@ -875,7 +875,7 @@ static int class_setup_req(struct fsg_dev *fsg,
 			if (ctrl->bRequestType != (USB_DIR_IN |
 					USB_TYPE_CLASS | USB_RECIP_INTERFACE))
 				break;
-			if (w_index != 0 || w_value != 0) {
+			if (w_index != 0 || w_value != 0 || w_length != 1) {
 				value = -EDOM;
 				break;
 			}
diff --git a/drivers/usb/gadget/fsl_mxc_udc.c b/drivers/usb/gadget/fsl_mxc_udc.c
index 43a49ec..dcbc0a2 100644
--- a/drivers/usb/gadget/fsl_mxc_udc.c
+++ b/drivers/usb/gadget/fsl_mxc_udc.c
@@ -16,6 +16,7 @@
 #include <linux/err.h>
 #include <linux/fsl_devices.h>
 #include <linux/platform_device.h>
+#include <linux/io.h>
 
 #include <mach/hardware.h>
 
@@ -88,7 +89,6 @@ eenahb:
 void fsl_udc_clk_finalize(struct platform_device *pdev)
 {
 	struct fsl_usb2_platform_data *pdata = pdev->dev.platform_data;
-#if defined(CONFIG_SOC_IMX35)
 	if (cpu_is_mx35()) {
 		unsigned int v;
 
@@ -101,7 +101,6 @@ void fsl_udc_clk_finalize(struct platform_device *pdev)
 					USBPHYCTRL_OTGBASE_OFFSET));
 		}
 	}
-#endif
 
 	/* ULPI transceivers don't need usbpll */
 	if (pdata->phy_mode == FSL_USB2_PHY_ULPI) {
diff --git a/drivers/usb/gadget/fsl_qe_udc.c b/drivers/usb/gadget/fsl_qe_udc.c
index 2a03e4d..e00cf92 100644
--- a/drivers/usb/gadget/fsl_qe_udc.c
+++ b/drivers/usb/gadget/fsl_qe_udc.c
@@ -2336,8 +2336,7 @@ static int fsl_qe_start(struct usb_gadget_driver *driver,
 	if (!udc_controller)
 		return -ENODEV;
 
-	if (!driver || (driver->speed != USB_SPEED_FULL
-			&& driver->speed != USB_SPEED_HIGH)
+	if (!driver || driver->speed < USB_SPEED_FULL
 			|| !bind || !driver->disconnect || !driver->setup)
 		return -EINVAL;
 
diff --git a/drivers/usb/gadget/fsl_udc_core.c b/drivers/usb/gadget/fsl_udc_core.c
index b2c44e1..dd28ef3 100644
--- a/drivers/usb/gadget/fsl_udc_core.c
+++ b/drivers/usb/gadget/fsl_udc_core.c
@@ -696,12 +696,31 @@ static void fsl_free_request(struct usb_ep *_ep, struct usb_request *_req)
 		kfree(req);
 }
 
-/*-------------------------------------------------------------------------*/
+/* Actually add a dTD chain to an empty dQH and let go */
+static void fsl_prime_ep(struct fsl_ep *ep, struct ep_td_struct *td)
+{
+	struct ep_queue_head *qh = get_qh_by_ep(ep);
+
+	/* Write dQH next pointer and terminate bit to 0 */
+	qh->next_dtd_ptr = cpu_to_hc32(td->td_dma
+			& EP_QUEUE_HEAD_NEXT_POINTER_MASK);
+
+	/* Clear active and halt bit */
+	qh->size_ioc_int_sts &= cpu_to_hc32(~(EP_QUEUE_HEAD_STATUS_ACTIVE
+					| EP_QUEUE_HEAD_STATUS_HALT));
+
+	/* Ensure that updates to the QH will occur before priming. */
+	wmb();
+
+	/* Prime endpoint by writing correct bit to ENDPTPRIME */
+	fsl_writel(ep_is_in(ep) ? (1 << (ep_index(ep) + 16))
+			: (1 << (ep_index(ep))), &dr_regs->endpointprime);
+}
+
+/* Add dTD chain to the dQH of an EP */
 static void fsl_queue_td(struct fsl_ep *ep, struct fsl_req *req)
 {
-	int i = ep_index(ep) * 2 + ep_is_in(ep);
 	u32 temp, bitmask, tmp_stat;
-	struct ep_queue_head *dQH = &ep->udc->ep_qh[i];
 
 	/* VDBG("QH addr Register 0x%8x", dr_regs->endpointlistaddr);
 	VDBG("ep_qh[%d] addr is 0x%8x", i, (u32)&(ep->udc->ep_qh[i])); */
@@ -719,7 +738,7 @@ static void fsl_queue_td(struct fsl_ep *ep, struct fsl_req *req)
 			cpu_to_hc32(req->head->td_dma & DTD_ADDR_MASK);
 		/* Read prime bit, if 1 goto done */
 		if (fsl_readl(&dr_regs->endpointprime) & bitmask)
-			goto out;
+			return;
 
 		do {
 			/* Set ATDTW bit in USBCMD */
@@ -736,28 +755,10 @@ static void fsl_queue_td(struct fsl_ep *ep, struct fsl_req *req)
 		fsl_writel(temp & ~USB_CMD_ATDTW, &dr_regs->usbcmd);
 
 		if (tmp_stat)
-			goto out;
+			return;
 	}
 
-	/* Write dQH next pointer and terminate bit to 0 */
-	temp = req->head->td_dma & EP_QUEUE_HEAD_NEXT_POINTER_MASK;
-	dQH->next_dtd_ptr = cpu_to_hc32(temp);
-
-	/* Clear active and halt bit */
-	temp = cpu_to_hc32(~(EP_QUEUE_HEAD_STATUS_ACTIVE
-			| EP_QUEUE_HEAD_STATUS_HALT));
-	dQH->size_ioc_int_sts &= temp;
-
-	/* Ensure that updates to the QH will occur before priming. */
-	wmb();
-
-	/* Prime endpoint by writing 1 to ENDPTPRIME */
-	temp = ep_is_in(ep)
-		? (1 << (ep_index(ep) + 16))
-		: (1 << (ep_index(ep)));
-	fsl_writel(temp, &dr_regs->endpointprime);
-out:
-	return;
+	fsl_prime_ep(ep, req->head);
 }
 
 /* Fill in the dTD structure
@@ -877,7 +878,7 @@ fsl_ep_queue(struct usb_ep *_ep, struct usb_request *_req, gfp_t gfp_flags)
 		VDBG("%s, bad ep", __func__);
 		return -EINVAL;
 	}
-	if (ep->desc->bmAttributes == USB_ENDPOINT_XFER_ISOC) {
+	if (usb_endpoint_xfer_isoc(ep->desc)) {
 		if (req->req.length > ep->ep.maxpacket)
 			return -EMSGSIZE;
 	}
@@ -973,25 +974,20 @@ static int fsl_ep_dequeue(struct usb_ep *_ep, struct usb_request *_req)
 
 		/* The request isn't the last request in this ep queue */
 		if (req->queue.next != &ep->queue) {
-			struct ep_queue_head *qh;
 			struct fsl_req *next_req;
 
-			qh = ep->qh;
 			next_req = list_entry(req->queue.next, struct fsl_req,
 					queue);
 
-			/* Point the QH to the first TD of next request */
-			fsl_writel((u32) next_req->head, &qh->curr_dtd_ptr);
+			/* prime with dTD of next request */
+			fsl_prime_ep(ep, next_req->head);
 		}
-
-		/* The request hasn't been processed, patch up the TD chain */
+	/* The request hasn't been processed, patch up the TD chain */
 	} else {
 		struct fsl_req *prev_req;
 
 		prev_req = list_entry(req->queue.prev, struct fsl_req, queue);
-		fsl_writel(fsl_readl(&req->tail->next_td_ptr),
-				&prev_req->tail->next_td_ptr);
-
+		prev_req->tail->next_td_ptr = req->tail->next_td_ptr;
 	}
 
 	done(ep, req, -ECONNRESET);
@@ -1032,7 +1028,7 @@ static int fsl_ep_set_halt(struct usb_ep *_ep, int value)
 		goto out;
 	}
 
-	if (ep->desc->bmAttributes == USB_ENDPOINT_XFER_ISOC) {
+	if (usb_endpoint_xfer_isoc(ep->desc)) {
 		status = -EOPNOTSUPP;
 		goto out;
 	}
@@ -1068,7 +1064,7 @@ static int fsl_ep_fifo_status(struct usb_ep *_ep)
 	struct fsl_udc *udc;
 	int size = 0;
 	u32 bitmask;
-	struct ep_queue_head *d_qh;
+	struct ep_queue_head *qh;
 
 	ep = container_of(_ep, struct fsl_ep, ep);
 	if (!_ep || (!ep->desc && ep_index(ep) != 0))
@@ -1079,13 +1075,13 @@ static int fsl_ep_fifo_status(struct usb_ep *_ep)
 	if (!udc->driver || udc->gadget.speed == USB_SPEED_UNKNOWN)
 		return -ESHUTDOWN;
 
-	d_qh = &ep->udc->ep_qh[ep_index(ep) * 2 + ep_is_in(ep)];
+	qh = get_qh_by_ep(ep);
 
 	bitmask = (ep_is_in(ep)) ? (1 << (ep_index(ep) + 16)) :
 	    (1 << (ep_index(ep)));
 
 	if (fsl_readl(&dr_regs->endptstatus) & bitmask)
-		size = (d_qh->size_ioc_int_sts & DTD_PACKET_SIZE)
+		size = (qh->size_ioc_int_sts & DTD_PACKET_SIZE)
 		    >> DTD_LENGTH_BIT_POS;
 
 	pr_debug("%s %u\n", __func__, size);
@@ -1717,7 +1713,7 @@ static void dtd_complete_irq(struct fsl_udc *udc)
 
 static inline enum usb_device_speed portscx_device_speed(u32 reg)
 {
-	switch (speed & PORTSCX_PORT_SPEED_MASK) {
+	switch (reg & PORTSCX_PORT_SPEED_MASK) {
 	case PORTSCX_PORT_SPEED_HIGH:
 		return USB_SPEED_HIGH;
 	case PORTSCX_PORT_SPEED_FULL:
@@ -1938,8 +1934,7 @@ static int fsl_start(struct usb_gadget_driver *driver,
 	if (!udc_controller)
 		return -ENODEV;
 
-	if (!driver || (driver->speed != USB_SPEED_FULL
-				&& driver->speed != USB_SPEED_HIGH)
+	if (!driver || driver->speed < USB_SPEED_FULL
 			|| !bind || !driver->disconnect || !driver->setup)
 		return -EINVAL;
 
@@ -2480,8 +2475,7 @@ static int __init fsl_udc_probe(struct platform_device *pdev)
 
 #ifndef CONFIG_ARCH_MXC
 	if (pdata->have_sysif_regs)
-		usb_sys_regs = (struct usb_sys_interface *)
-				((u32)dr_regs + USB_DR_SYS_OFFSET);
+		usb_sys_regs = (void *)dr_regs + USB_DR_SYS_OFFSET;
 #endif
 
 	/* Initialize USB clocks */
diff --git a/drivers/usb/gadget/fsl_usb2_udc.h b/drivers/usb/gadget/fsl_usb2_udc.h
index 1d51be8..f781f5d 100644
--- a/drivers/usb/gadget/fsl_usb2_udc.h
+++ b/drivers/usb/gadget/fsl_usb2_udc.h
@@ -569,6 +569,16 @@ static void dump_msg(const char *label, const u8 * buf, unsigned int length)
 					* 2 + ((windex & USB_DIR_IN) ? 1 : 0))
 #define get_pipe_by_ep(EP)	(ep_index(EP) * 2 + ep_is_in(EP))
 
+static inline struct ep_queue_head *get_qh_by_ep(struct fsl_ep *ep)
+{
+	/* we only have one ep0 structure but two queue heads */
+	if (ep_index(ep) != 0)
+		return ep->qh;
+	else
+		return &ep->udc->ep_qh[(ep->udc->ep0_dir ==
+				USB_DIR_IN) ? 1 : 0];
+}
+
 struct platform_device;
 #ifdef CONFIG_ARCH_MXC
 int fsl_udc_clk_init(struct platform_device *pdev);
diff --git a/drivers/usb/gadget/inode.c b/drivers/usb/gadget/inode.c
index a392ec0..6ccae27 100644
--- a/drivers/usb/gadget/inode.c
+++ b/drivers/usb/gadget/inode.c
@@ -1730,8 +1730,9 @@ static void
 gadgetfs_disconnect (struct usb_gadget *gadget)
 {
 	struct dev_data		*dev = get_gadget_data (gadget);
+	unsigned long		flags;
 
-	spin_lock (&dev->lock);
+	spin_lock_irqsave (&dev->lock, flags);
 	if (dev->state == STATE_DEV_UNCONNECTED)
 		goto exit;
 	dev->state = STATE_DEV_UNCONNECTED;
@@ -1740,7 +1741,7 @@ gadgetfs_disconnect (struct usb_gadget *gadget)
 	next_event (dev, GADGETFS_DISCONNECT);
 	ep0_readable (dev);
 exit:
-	spin_unlock (&dev->lock);
+	spin_unlock_irqrestore (&dev->lock, flags);
 }
 
 static void
diff --git a/drivers/usb/gadget/m66592-udc.c b/drivers/usb/gadget/m66592-udc.c
index 91d0af2..9aa1cbb 100644
--- a/drivers/usb/gadget/m66592-udc.c
+++ b/drivers/usb/gadget/m66592-udc.c
@@ -1472,7 +1472,7 @@ static int m66592_start(struct usb_gadget_driver *driver,
 	int retval;
 
 	if (!driver
-			|| driver->speed != USB_SPEED_HIGH
+			|| driver->speed < USB_SPEED_HIGH
 			|| !bind
 			|| !driver->setup)
 		return -EINVAL;
diff --git a/drivers/usb/gadget/net2280.c b/drivers/usb/gadget/net2280.c
index 7f1bc9a..da2b9d0 100644
--- a/drivers/usb/gadget/net2280.c
+++ b/drivers/usb/gadget/net2280.c
@@ -1881,7 +1881,7 @@ static int net2280_start(struct usb_gadget *_gadget,
 	 * (dev->usb->xcvrdiag & FORCE_FULL_SPEED_MODE)
 	 * "must not be used in normal operation"
 	 */
-	if (!driver || driver->speed != USB_SPEED_HIGH
+	if (!driver || driver->speed < USB_SPEED_HIGH
 			|| !driver->setup)
 		return -EINVAL;
 
diff --git a/drivers/usb/gadget/pch_udc.c b/drivers/usb/gadget/pch_udc.c
index 550d6dc..5048a0c 100644
--- a/drivers/usb/gadget/pch_udc.c
+++ b/drivers/usb/gadget/pch_udc.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2010 OKI SEMICONDUCTOR CO., LTD.
+ * Copyright (C) 2011 LAPIS Semiconductor Co., Ltd.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -354,6 +354,7 @@ struct pch_udc_dev {
 #define PCI_DEVICE_ID_INTEL_EG20T_UDC	0x8808
 #define PCI_VENDOR_ID_ROHM		0x10DB
 #define PCI_DEVICE_ID_ML7213_IOH_UDC	0x801D
+#define PCI_DEVICE_ID_ML7831_IOH_UDC	0x8808
 
 static const char	ep0_string[] = "ep0in";
 static DEFINE_SPINLOCK(udc_stall_spinlock);	/* stall spin lock */
@@ -2970,6 +2971,11 @@ static DEFINE_PCI_DEVICE_TABLE(pch_udc_pcidev_id) = {
 		.class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe,
 		.class_mask = 0xffffffff,
 	},
+	{
+		PCI_DEVICE(PCI_VENDOR_ID_ROHM, PCI_DEVICE_ID_ML7831_IOH_UDC),
+		.class = (PCI_CLASS_SERIAL_USB << 8) | 0xfe,
+		.class_mask = 0xffffffff,
+	},
 	{ 0 },
 };
 
@@ -2999,5 +3005,5 @@ static void __exit pch_udc_pci_exit(void)
 module_exit(pch_udc_pci_exit);
 
 MODULE_DESCRIPTION("Intel EG20T USB Device Controller");
-MODULE_AUTHOR("OKI SEMICONDUCTOR, <toshiharu-linux@dsn.okisemi.com>");
+MODULE_AUTHOR("LAPIS Semiconductor, <tomoya-linux@dsn.lapis-semi.com>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/usb/gadget/r8a66597-udc.c b/drivers/usb/gadget/r8a66597-udc.c
index 68a826a..fc719a3 100644
--- a/drivers/usb/gadget/r8a66597-udc.c
+++ b/drivers/usb/gadget/r8a66597-udc.c
@@ -1718,6 +1718,8 @@ static void r8a66597_fifo_flush(struct usb_ep *_ep)
 	if (list_empty(&ep->queue) && !ep->busy) {
 		pipe_stop(ep->r8a66597, ep->pipenum);
 		r8a66597_bclr(ep->r8a66597, BCLR, ep->fifoctr);
+		r8a66597_write(ep->r8a66597, ACLRM, ep->pipectr);
+		r8a66597_write(ep->r8a66597, 0, ep->pipectr);
 	}
 	spin_unlock_irqrestore(&ep->r8a66597->lock, flags);
 }
@@ -1742,26 +1744,16 @@ static int r8a66597_start(struct usb_gadget *gadget,
 		struct usb_gadget_driver *driver)
 {
 	struct r8a66597 *r8a66597 = gadget_to_r8a66597(gadget);
-	int retval;
 
 	if (!driver
-			|| driver->speed != USB_SPEED_HIGH
+			|| driver->speed < USB_SPEED_HIGH
 			|| !driver->setup)
 		return -EINVAL;
 	if (!r8a66597)
 		return -ENODEV;
 
 	/* hook up the driver */
-	driver->driver.bus = NULL;
 	r8a66597->driver = driver;
-	r8a66597->gadget.dev.driver = &driver->driver;
-
-	retval = device_add(&r8a66597->gadget.dev);
-	if (retval) {
-		dev_err(r8a66597_to_dev(r8a66597), "device_add error (%d)\n",
-			retval);
-		goto error;
-	}
 
 	init_controller(r8a66597);
 	r8a66597_bset(r8a66597, VBSE, INTENB0);
@@ -1775,12 +1767,6 @@ static int r8a66597_start(struct usb_gadget *gadget,
 	}
 
 	return 0;
-
-error:
-	r8a66597->driver = NULL;
-	r8a66597->gadget.dev.driver = NULL;
-
-	return retval;
 }
 
 static int r8a66597_stop(struct usb_gadget *gadget,
@@ -1794,7 +1780,6 @@ static int r8a66597_stop(struct usb_gadget *gadget,
 	disable_controller(r8a66597);
 	spin_unlock_irqrestore(&r8a66597->lock, flags);
 
-	device_del(&r8a66597->gadget.dev);
 	r8a66597->driver = NULL;
 	return 0;
 }
@@ -1845,6 +1830,7 @@ static int __exit r8a66597_remove(struct platform_device *pdev)
 		clk_put(r8a66597->clk);
 	}
 #endif
+	device_unregister(&r8a66597->gadget.dev);
 	kfree(r8a66597);
 	return 0;
 }
@@ -1924,13 +1910,17 @@ static int __init r8a66597_probe(struct platform_device *pdev)
 	r8a66597->irq_sense_low = irq_trigger == IRQF_TRIGGER_LOW;
 
 	r8a66597->gadget.ops = &r8a66597_gadget_ops;
-	device_initialize(&r8a66597->gadget.dev);
 	dev_set_name(&r8a66597->gadget.dev, "gadget");
 	r8a66597->gadget.is_dualspeed = 1;
 	r8a66597->gadget.dev.parent = &pdev->dev;
 	r8a66597->gadget.dev.dma_mask = pdev->dev.dma_mask;
 	r8a66597->gadget.dev.release = pdev->dev.release;
 	r8a66597->gadget.name = udc_name;
+	ret = device_register(&r8a66597->gadget.dev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "device_register failed\n");
+		goto clean_up;
+	}
 
 	init_timer(&r8a66597->timer);
 	r8a66597->timer.function = r8a66597_timer;
@@ -1945,7 +1935,7 @@ static int __init r8a66597_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev, "cannot get clock \"%s\"\n",
 				clk_name);
 			ret = PTR_ERR(r8a66597->clk);
-			goto clean_up;
+			goto clean_up_dev;
 		}
 		clk_enable(r8a66597->clk);
 	}
@@ -2014,7 +2004,9 @@ clean_up2:
 		clk_disable(r8a66597->clk);
 		clk_put(r8a66597->clk);
 	}
+clean_up_dev:
 #endif
+	device_unregister(&r8a66597->gadget.dev);
 clean_up:
 	if (r8a66597) {
 		if (r8a66597->sudmac_reg)
diff --git a/drivers/usb/gadget/s3c-hsotg.c b/drivers/usb/gadget/s3c-hsotg.c
index a552453..b314482 100644
--- a/drivers/usb/gadget/s3c-hsotg.c
+++ b/drivers/usb/gadget/s3c-hsotg.c
@@ -2586,10 +2586,8 @@ static int s3c_hsotg_start(struct usb_gadget_driver *driver,
 		return -EINVAL;
 	}
 
-	if (driver->speed != USB_SPEED_HIGH &&
-	    driver->speed != USB_SPEED_FULL) {
+	if (driver->speed < USB_SPEED_FULL)
 		dev_err(hsotg->dev, "%s: bad speed\n", __func__);
-	}
 
 	if (!bind || !driver->setup) {
 		dev_err(hsotg->dev, "%s: missing entry points\n", __func__);
diff --git a/drivers/usb/gadget/s3c-hsudc.c b/drivers/usb/gadget/s3c-hsudc.c
index 8d54f89..20a553b 100644
--- a/drivers/usb/gadget/s3c-hsudc.c
+++ b/drivers/usb/gadget/s3c-hsudc.c
@@ -1142,8 +1142,7 @@ static int s3c_hsudc_start(struct usb_gadget_driver *driver,
 	int ret;
 
 	if (!driver
-		|| (driver->speed != USB_SPEED_FULL &&
-			driver->speed != USB_SPEED_HIGH)
+		|| driver->speed < USB_SPEED_FULL
 		|| !bind
 		|| !driver->unbind || !driver->disconnect || !driver->setup)
 		return -EINVAL;
diff --git a/drivers/usb/gadget/udc-core.c b/drivers/usb/gadget/udc-core.c
index 022baec..6939e17 100644
--- a/drivers/usb/gadget/udc-core.c
+++ b/drivers/usb/gadget/udc-core.c
@@ -210,10 +210,10 @@ static void usb_gadget_remove_driver(struct usb_udc *udc)
 	kobject_uevent(&udc->dev.kobj, KOBJ_CHANGE);
 
 	if (udc_is_newstyle(udc)) {
-		usb_gadget_disconnect(udc->gadget);
+		udc->driver->disconnect(udc->gadget);
 		udc->driver->unbind(udc->gadget);
 		usb_gadget_udc_stop(udc->gadget, udc->driver);
-
+		usb_gadget_disconnect(udc->gadget);
 	} else {
 		usb_gadget_stop(udc->gadget, udc->driver);
 	}
@@ -344,7 +344,7 @@ EXPORT_SYMBOL_GPL(usb_gadget_unregister_driver);
 static ssize_t usb_udc_srp_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t n)
 {
-	struct usb_udc		*udc = dev_get_drvdata(dev);
+	struct usb_udc		*udc = container_of(dev, struct usb_udc, dev);
 
 	if (sysfs_streq(buf, "1"))
 		usb_gadget_wakeup(udc->gadget);
@@ -378,7 +378,7 @@ static ssize_t usb_udc_speed_show(struct device *dev,
 	return snprintf(buf, PAGE_SIZE, "%s\n",
 			usb_speed_string(udc->gadget->speed));
 }
-static DEVICE_ATTR(speed, S_IRUSR, usb_udc_speed_show, NULL);
+static DEVICE_ATTR(speed, S_IRUGO, usb_udc_speed_show, NULL);
 
 #define USB_UDC_ATTR(name)					\
 ssize_t usb_udc_##name##_show(struct device *dev,		\
@@ -389,7 +389,7 @@ ssize_t usb_udc_##name##_show(struct device *dev,		\
 								\
 	return snprintf(buf, PAGE_SIZE, "%d\n", gadget->name);	\
 }								\
-static DEVICE_ATTR(name, S_IRUSR, usb_udc_##name##_show, NULL)
+static DEVICE_ATTR(name, S_IRUGO, usb_udc_##name##_show, NULL)
 
 static USB_UDC_ATTR(is_dualspeed);
 static USB_UDC_ATTR(is_otg);
diff --git a/drivers/usb/host/ehci-sched.c b/drivers/usb/host/ehci-sched.c
index 2e829fa..a60679c 100644
--- a/drivers/usb/host/ehci-sched.c
+++ b/drivers/usb/host/ehci-sched.c
@@ -1475,30 +1475,36 @@ iso_stream_schedule (
 	 * jump until after the queue is primed.
 	 */
 	else {
+		int done = 0;
 		start = SCHEDULE_SLOP + (now & ~0x07);
 
 		/* NOTE:  assumes URB_ISO_ASAP, to limit complexity/bugs */
 
-		/* find a uframe slot with enough bandwidth */
-		next = start + period;
-		for (; start < next; start++) {
-
+		/* find a uframe slot with enough bandwidth.
+		 * Early uframes are more precious because full-speed
+		 * iso IN transfers can't use late uframes,
+		 * and therefore they should be allocated last.
+		 */
+		next = start;
+		start += period;
+		do {
+			start--;
 			/* check schedule: enough space? */
 			if (stream->highspeed) {
 				if (itd_slot_ok(ehci, mod, start,
 						stream->usecs, period))
-					break;
+					done = 1;
 			} else {
 				if ((start % 8) >= 6)
 					continue;
 				if (sitd_slot_ok(ehci, mod, stream,
 						start, sched, period))
-					break;
+					done = 1;
 			}
-		}
+		} while (start > next && !done);
 
 		/* no room in the schedule */
-		if (start == next) {
+		if (!done) {
 			ehci_dbg(ehci, "iso resched full %p (now %d max %d)\n",
 				urb, now, now + mod);
 			status = -ENOSPC;
diff --git a/drivers/usb/host/ehci-xls.c b/drivers/usb/host/ehci-xls.c
index fe74bd6..b4fb511 100644
--- a/drivers/usb/host/ehci-xls.c
+++ b/drivers/usb/host/ehci-xls.c
@@ -19,7 +19,7 @@ static int ehci_xls_setup(struct usb_hcd *hcd)
 
 	ehci->caps = hcd->regs;
 	ehci->regs = hcd->regs +
-		HC_LENGTH(ehci_readl(ehci, &ehci->caps->hc_capbase));
+		HC_LENGTH(ehci, ehci_readl(ehci, &ehci->caps->hc_capbase));
 	dbg_hcs_params(ehci, "reset");
 	dbg_hcc_params(ehci, "reset");
 
diff --git a/drivers/usb/host/ohci-at91.c b/drivers/usb/host/ohci-at91.c
index ba3a46b..95a9fec 100644
--- a/drivers/usb/host/ohci-at91.c
+++ b/drivers/usb/host/ohci-at91.c
@@ -223,6 +223,9 @@ static void ohci_at91_usb_set_power(struct at91_usbh_data *pdata, int port, int
 	if (port < 0 || port >= 2)
 		return;
 
+	if (pdata->vbus_pin[port] <= 0)
+		return;
+
 	gpio_set_value(pdata->vbus_pin[port], !pdata->vbus_pin_inverted ^ enable);
 }
 
@@ -231,6 +234,9 @@ static int ohci_at91_usb_get_power(struct at91_usbh_data *pdata, int port)
 	if (port < 0 || port >= 2)
 		return -EINVAL;
 
+	if (pdata->vbus_pin[port] <= 0)
+		return -EINVAL;
+
 	return gpio_get_value(pdata->vbus_pin[port]) ^ !pdata->vbus_pin_inverted;
 }
 
diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index 34efd47..b263919 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -389,17 +389,14 @@ ohci_shutdown (struct usb_hcd *hcd)
 	struct ohci_hcd *ohci;
 
 	ohci = hcd_to_ohci (hcd);
-	ohci_writel (ohci, OHCI_INTR_MIE, &ohci->regs->intrdisable);
-	ohci->hc_control = ohci_readl(ohci, &ohci->regs->control);
+	ohci_writel(ohci, (u32) ~0, &ohci->regs->intrdisable);
 
-	/* If the SHUTDOWN quirk is set, don't put the controller in RESET */
-	ohci->hc_control &= (ohci->flags & OHCI_QUIRK_SHUTDOWN ?
-			OHCI_CTRL_RWC | OHCI_CTRL_HCFS :
-			OHCI_CTRL_RWC);
-	ohci_writel(ohci, ohci->hc_control, &ohci->regs->control);
+	/* Software reset, after which the controller goes into SUSPEND */
+	ohci_writel(ohci, OHCI_HCR, &ohci->regs->cmdstatus);
+	ohci_readl(ohci, &ohci->regs->cmdstatus);	/* flush the writes */
+	udelay(10);
 
-	/* flush the writes */
-	(void) ohci_readl (ohci, &ohci->regs->control);
+	ohci_writel(ohci, ohci->fminterval, &ohci->regs->fminterval);
 }
 
 static int check_ed(struct ohci_hcd *ohci, struct ed *ed)
diff --git a/drivers/usb/host/ohci-pci.c b/drivers/usb/host/ohci-pci.c
index ad8166c..bc01b06 100644
--- a/drivers/usb/host/ohci-pci.c
+++ b/drivers/usb/host/ohci-pci.c
@@ -175,28 +175,6 @@ static int ohci_quirk_amd700(struct usb_hcd *hcd)
 	return 0;
 }
 
-/* nVidia controllers continue to drive Reset signalling on the bus
- * even after system shutdown, wasting power.  This flag tells the
- * shutdown routine to leave the controller OPERATIONAL instead of RESET.
- */
-static int ohci_quirk_nvidia_shutdown(struct usb_hcd *hcd)
-{
-	struct pci_dev *pdev = to_pci_dev(hcd->self.controller);
-	struct ohci_hcd	*ohci = hcd_to_ohci(hcd);
-
-	/* Evidently nVidia fixed their later hardware; this is a guess at
-	 * the changeover point.
-	 */
-#define PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_USB		0x026d
-
-	if (pdev->device < PCI_DEVICE_ID_NVIDIA_NFORCE_MCP51_USB) {
-		ohci->flags |= OHCI_QUIRK_SHUTDOWN;
-		ohci_dbg(ohci, "enabled nVidia shutdown quirk\n");
-	}
-
-	return 0;
-}
-
 static void sb800_prefetch(struct ohci_hcd *ohci, int on)
 {
 	struct pci_dev *pdev;
@@ -260,10 +238,6 @@ static const struct pci_device_id ohci_pci_quirks[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_ATI, 0x4399),
 		.driver_data = (unsigned long)ohci_quirk_amd700,
 	},
-	{
-		PCI_DEVICE(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID),
-		.driver_data = (unsigned long) ohci_quirk_nvidia_shutdown,
-	},
 
 	/* FIXME for some of the early AMD 760 southbridges, OHCI
 	 * won't work at all.  blacklist them.
diff --git a/drivers/usb/host/ohci.h b/drivers/usb/host/ohci.h
index 35e5fd6..0795b93 100644
--- a/drivers/usb/host/ohci.h
+++ b/drivers/usb/host/ohci.h
@@ -403,7 +403,6 @@ struct ohci_hcd {
 #define	OHCI_QUIRK_HUB_POWER	0x100			/* distrust firmware power/oc setup */
 #define	OHCI_QUIRK_AMD_PLL	0x200			/* AMD PLL quirk*/
 #define	OHCI_QUIRK_AMD_PREFETCH	0x400			/* pre-fetch for ISO transfer */
-#define	OHCI_QUIRK_SHUTDOWN	0x800			/* nVidia power bug */
 	// there are also chip quirks/bugs in init logic
 
 	struct work_struct	nec_work;	/* Worker for NEC quirk */
diff --git a/drivers/usb/host/pci-quirks.c b/drivers/usb/host/pci-quirks.c
index 27a3dec..caf8742 100644
--- a/drivers/usb/host/pci-quirks.c
+++ b/drivers/usb/host/pci-quirks.c
@@ -37,6 +37,7 @@
 #define OHCI_INTRENABLE		0x10
 #define OHCI_INTRDISABLE	0x14
 #define OHCI_FMINTERVAL		0x34
+#define OHCI_HCFS		(3 << 6)	/* hc functional state */
 #define OHCI_HCR		(1 << 0)	/* host controller reset */
 #define OHCI_OCR		(1 << 3)	/* ownership change request */
 #define OHCI_CTRL_RWC		(1 << 9)	/* remote wakeup connected */
@@ -466,6 +467,8 @@ static void __devinit quirk_usb_handoff_ohci(struct pci_dev *pdev)
 {
 	void __iomem *base;
 	u32 control;
+	u32 fminterval;
+	int cnt;
 
 	if (!mmio_resource_enabled(pdev, 0))
 		return;
@@ -498,41 +501,32 @@ static void __devinit quirk_usb_handoff_ohci(struct pci_dev *pdev)
 	}
 #endif
 
-	/* reset controller, preserving RWC (and possibly IR) */
-	writel(control & OHCI_CTRL_MASK, base + OHCI_CONTROL);
-	readl(base + OHCI_CONTROL);
+	/* disable interrupts */
+	writel((u32) ~0, base + OHCI_INTRDISABLE);
 
-	/* Some NVIDIA controllers stop working if kept in RESET for too long */
-	if (pdev->vendor == PCI_VENDOR_ID_NVIDIA) {
-		u32 fminterval;
-		int cnt;
+	/* Reset the USB bus, if the controller isn't already in RESET */
+	if (control & OHCI_HCFS) {
+		/* Go into RESET, preserving RWC (and possibly IR) */
+		writel(control & OHCI_CTRL_MASK, base + OHCI_CONTROL);
+		readl(base + OHCI_CONTROL);
 
-		/* drive reset for at least 50 ms (7.1.7.5) */
+		/* drive bus reset for at least 50 ms (7.1.7.5) */
 		msleep(50);
+	}
 
-		/* software reset of the controller, preserving HcFmInterval */
-		fminterval = readl(base + OHCI_FMINTERVAL);
-		writel(OHCI_HCR, base + OHCI_CMDSTATUS);
+	/* software reset of the controller, preserving HcFmInterval */
+	fminterval = readl(base + OHCI_FMINTERVAL);
+	writel(OHCI_HCR, base + OHCI_CMDSTATUS);
 
-		/* reset requires max 10 us delay */
-		for (cnt = 30; cnt > 0; --cnt) {	/* ... allow extra time */
-			if ((readl(base + OHCI_CMDSTATUS) & OHCI_HCR) == 0)
-				break;
-			udelay(1);
-		}
-		writel(fminterval, base + OHCI_FMINTERVAL);
-
-		/* Now we're in the SUSPEND state with all devices reset
-		 * and wakeups and interrupts disabled
-		 */
+	/* reset requires max 10 us delay */
+	for (cnt = 30; cnt > 0; --cnt) {	/* ... allow extra time */
+		if ((readl(base + OHCI_CMDSTATUS) & OHCI_HCR) == 0)
+			break;
+		udelay(1);
 	}
+	writel(fminterval, base + OHCI_FMINTERVAL);
 
-	/*
-	 * disable interrupts
-	 */
-	writel(~(u32)0, base + OHCI_INTRDISABLE);
-	writel(~(u32)0, base + OHCI_INTRSTATUS);
-
+	/* Now the controller is safely in SUSPEND and nothing can wake it up */
 	iounmap(base);
 }
 
@@ -627,7 +621,7 @@ static void __devinit quirk_usb_disable_ehci(struct pci_dev *pdev)
 	void __iomem *base, *op_reg_base;
 	u32	hcc_params, cap, val;
 	u8	offset, cap_length;
-	int	wait_time, delta, count = 256/4;
+	int	wait_time, count = 256/4;
 
 	if (!mmio_resource_enabled(pdev, 0))
 		return;
@@ -673,11 +667,10 @@ static void __devinit quirk_usb_disable_ehci(struct pci_dev *pdev)
 		writel(val, op_reg_base + EHCI_USBCMD);
 
 		wait_time = 2000;
-		delta = 100;
 		do {
 			writel(0x3f, op_reg_base + EHCI_USBSTS);
-			udelay(delta);
-			wait_time -= delta;
+			udelay(100);
+			wait_time -= 100;
 			val = readl(op_reg_base + EHCI_USBSTS);
 			if ((val == ~(u32)0) || (val & EHCI_USBSTS_HALTED)) {
 				break;
diff --git a/drivers/usb/host/whci/qset.c b/drivers/usb/host/whci/qset.c
index d6e1754..a403b53 100644
--- a/drivers/usb/host/whci/qset.c
+++ b/drivers/usb/host/whci/qset.c
@@ -124,7 +124,7 @@ void qset_clear(struct whc *whc, struct whc_qset *qset)
 {
 	qset->td_start = qset->td_end = qset->ntds = 0;
 
-	qset->qh.link = cpu_to_le32(QH_LINK_NTDS(8) | QH_LINK_T);
+	qset->qh.link = cpu_to_le64(QH_LINK_NTDS(8) | QH_LINK_T);
 	qset->qh.status = qset->qh.status & QH_STATUS_SEQ_MASK;
 	qset->qh.err_count = 0;
 	qset->qh.scratch[0] = 0;
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 42a22b8..0e4b25f 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -982,7 +982,6 @@ int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *ud
 	struct xhci_virt_device *dev;
 	struct xhci_ep_ctx	*ep0_ctx;
 	struct xhci_slot_ctx    *slot_ctx;
-	struct xhci_input_control_ctx *ctrl_ctx;
 	u32			port_num;
 	struct usb_device *top_dev;
 
@@ -994,12 +993,8 @@ int xhci_setup_addressable_virt_dev(struct xhci_hcd *xhci, struct usb_device *ud
 		return -EINVAL;
 	}
 	ep0_ctx = xhci_get_ep_ctx(xhci, dev->in_ctx, 0);
-	ctrl_ctx = xhci_get_input_control_ctx(xhci, dev->in_ctx);
 	slot_ctx = xhci_get_slot_ctx(xhci, dev->in_ctx);
 
-	/* 2) New slot context and endpoint 0 context are valid*/
-	ctrl_ctx->add_flags = cpu_to_le32(SLOT_FLAG | EP0_FLAG);
-
 	/* 3) Only the control endpoint is valid - one endpoint context */
 	slot_ctx->dev_info |= cpu_to_le32(LAST_CTX(1) | udev->route);
 	switch (udev->speed) {
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 940321b..9f1d4b1 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -816,23 +816,24 @@ void xhci_stop_endpoint_command_watchdog(unsigned long arg)
 	struct xhci_ring *ring;
 	struct xhci_td *cur_td;
 	int ret, i, j;
+	unsigned long flags;
 
 	ep = (struct xhci_virt_ep *) arg;
 	xhci = ep->xhci;
 
-	spin_lock(&xhci->lock);
+	spin_lock_irqsave(&xhci->lock, flags);
 
 	ep->stop_cmds_pending--;
 	if (xhci->xhc_state & XHCI_STATE_DYING) {
 		xhci_dbg(xhci, "Stop EP timer ran, but another timer marked "
 				"xHCI as DYING, exiting.\n");
-		spin_unlock(&xhci->lock);
+		spin_unlock_irqrestore(&xhci->lock, flags);
 		return;
 	}
 	if (!(ep->stop_cmds_pending == 0 && (ep->ep_state & EP_HALT_PENDING))) {
 		xhci_dbg(xhci, "Stop EP timer ran, but no command pending, "
 				"exiting.\n");
-		spin_unlock(&xhci->lock);
+		spin_unlock_irqrestore(&xhci->lock, flags);
 		return;
 	}
 
@@ -844,11 +845,11 @@ void xhci_stop_endpoint_command_watchdog(unsigned long arg)
 	xhci->xhc_state |= XHCI_STATE_DYING;
 	/* Disable interrupts from the host controller and start halting it */
 	xhci_quiesce(xhci);
-	spin_unlock(&xhci->lock);
+	spin_unlock_irqrestore(&xhci->lock, flags);
 
 	ret = xhci_halt(xhci);
 
-	spin_lock(&xhci->lock);
+	spin_lock_irqsave(&xhci->lock, flags);
 	if (ret < 0) {
 		/* This is bad; the host is not responding to commands and it's
 		 * not allowing itself to be halted.  At least interrupts are
@@ -896,7 +897,7 @@ void xhci_stop_endpoint_command_watchdog(unsigned long arg)
 			}
 		}
 	}
-	spin_unlock(&xhci->lock);
+	spin_unlock_irqrestore(&xhci->lock, flags);
 	xhci_dbg(xhci, "Calling usb_hc_died()\n");
 	usb_hc_died(xhci_to_hcd(xhci)->primary_hcd);
 	xhci_dbg(xhci, "xHCI host controller is dead.\n");
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 1ff95a0..a1afb7c 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -711,7 +711,10 @@ static void xhci_clear_command_ring(struct xhci_hcd *xhci)
 	ring = xhci->cmd_ring;
 	seg = ring->deq_seg;
 	do {
-		memset(seg->trbs, 0, SEGMENT_SIZE);
+		memset(seg->trbs, 0,
+			sizeof(union xhci_trb) * (TRBS_PER_SEGMENT - 1));
+		seg->trbs[TRBS_PER_SEGMENT - 1].link.control &=
+			cpu_to_le32(~TRB_CYCLE);
 		seg = seg->next;
 	} while (seg != ring->deq_seg);
 
@@ -799,7 +802,7 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 	u32			command, temp = 0;
 	struct usb_hcd		*hcd = xhci_to_hcd(xhci);
 	struct usb_hcd		*secondary_hcd;
-	int			retval;
+	int			retval = 0;
 
 	/* Wait a bit if either of the roothubs need to settle from the
 	 * transition into bus suspend.
@@ -809,6 +812,9 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 				xhci->bus_state[1].next_statechange))
 		msleep(100);
 
+	set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
+	set_bit(HCD_FLAG_HW_ACCESSIBLE, &xhci->shared_hcd->flags);
+
 	spin_lock_irq(&xhci->lock);
 	if (xhci->quirks & XHCI_RESET_ON_RESUME)
 		hibernated = true;
@@ -878,20 +884,13 @@ int xhci_resume(struct xhci_hcd *xhci, bool hibernated)
 			return retval;
 		xhci_dbg(xhci, "Start the primary HCD\n");
 		retval = xhci_run(hcd->primary_hcd);
-		if (retval)
-			goto failed_restart;
-
-		xhci_dbg(xhci, "Start the secondary HCD\n");
-		retval = xhci_run(secondary_hcd);
 		if (!retval) {
-			set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
-			set_bit(HCD_FLAG_HW_ACCESSIBLE,
-					&xhci->shared_hcd->flags);
+			xhci_dbg(xhci, "Start the secondary HCD\n");
+			retval = xhci_run(secondary_hcd);
 		}
-failed_restart:
 		hcd->state = HC_STATE_SUSPENDED;
 		xhci->shared_hcd->state = HC_STATE_SUSPENDED;
-		return retval;
+		goto done;
 	}
 
 	/* step 4: set Run/Stop bit */
@@ -910,11 +909,14 @@ failed_restart:
 	 * Running endpoints by ringing their doorbells
 	 */
 
-	set_bit(HCD_FLAG_HW_ACCESSIBLE, &hcd->flags);
-	set_bit(HCD_FLAG_HW_ACCESSIBLE, &xhci->shared_hcd->flags);
-
 	spin_unlock_irq(&xhci->lock);
-	return 0;
+
+ done:
+	if (retval == 0) {
+		usb_hcd_resume_root_hub(hcd);
+		usb_hcd_resume_root_hub(xhci->shared_hcd);
+	}
+	return retval;
 }
 #endif	/* CONFIG_PM */
 
@@ -3504,6 +3506,10 @@ int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev)
 	/* Otherwise, update the control endpoint ring enqueue pointer. */
 	else
 		xhci_copy_ep0_dequeue_into_input_ctx(xhci, udev);
+	ctrl_ctx = xhci_get_input_control_ctx(xhci, virt_dev->in_ctx);
+	ctrl_ctx->add_flags = cpu_to_le32(SLOT_FLAG | EP0_FLAG);
+	ctrl_ctx->drop_flags = 0;
+
 	xhci_dbg(xhci, "Slot ID %d Input Context:\n", udev->slot_id);
 	xhci_dbg_ctx(xhci, virt_dev->in_ctx, 2);
 
@@ -3585,7 +3591,6 @@ int xhci_address_device(struct usb_hcd *hcd, struct usb_device *udev)
 	virt_dev->address = (le32_to_cpu(slot_ctx->dev_state) & DEV_ADDR_MASK)
 		+ 1;
 	/* Zero the input context control for later use */
-	ctrl_ctx = xhci_get_input_control_ctx(xhci, virt_dev->in_ctx);
 	ctrl_ctx->add_flags = 0;
 	ctrl_ctx->drop_flags = 0;
 
diff --git a/drivers/usb/musb/Kconfig b/drivers/usb/musb/Kconfig
index fc34b8b..07a0346 100644
--- a/drivers/usb/musb/Kconfig
+++ b/drivers/usb/musb/Kconfig
@@ -11,6 +11,7 @@ config USB_MUSB_HDRC
 	select TWL4030_USB if MACH_OMAP_3430SDP
 	select TWL6030_USB if MACH_OMAP_4430SDP || MACH_OMAP4_PANDA
 	select USB_OTG_UTILS
+	select USB_GADGET_DUALSPEED
 	tristate 'Inventra Highspeed Dual Role Controller (TI, ADI, ...)'
 	help
 	  Say Y here if your system has a dual role high speed USB
@@ -60,7 +61,7 @@ config USB_MUSB_BLACKFIN
 
 config USB_MUSB_UX500
 	tristate "U8500 and U5500"
-	depends on (ARCH_U8500 && AB8500_USB) || (ARCH_U5500)
+	depends on (ARCH_U8500 && AB8500_USB)
 
 endchoice
 
diff --git a/drivers/usb/musb/am35x.c b/drivers/usb/musb/am35x.c
index 08f1d0b6..e233d2b 100644
--- a/drivers/usb/musb/am35x.c
+++ b/drivers/usb/musb/am35x.c
@@ -27,6 +27,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/module.h>
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
diff --git a/drivers/usb/musb/da8xx.c b/drivers/usb/musb/da8xx.c
index 4da7492..2613bfd 100644
--- a/drivers/usb/musb/da8xx.c
+++ b/drivers/usb/musb/da8xx.c
@@ -27,6 +27,7 @@
  */
 
 #include <linux/init.h>
+#include <linux/module.h>
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 20a2873..b63ab15 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -1477,8 +1477,7 @@ static int __init musb_core_init(u16 musb_type, struct musb *musb)
 /*-------------------------------------------------------------------------*/
 
 #if defined(CONFIG_SOC_OMAP2430) || defined(CONFIG_SOC_OMAP3430) || \
-	defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_ARCH_U8500) || \
-	defined(CONFIG_ARCH_U5500)
+	defined(CONFIG_ARCH_OMAP4) || defined(CONFIG_ARCH_U8500)
 
 static irqreturn_t generic_interrupt(int irq, void *__hci)
 {
@@ -2302,18 +2301,12 @@ static int musb_suspend(struct device *dev)
 		 */
 	}
 
-	musb_save_context(musb);
-
 	spin_unlock_irqrestore(&musb->lock, flags);
 	return 0;
 }
 
 static int musb_resume_noirq(struct device *dev)
 {
-	struct musb	*musb = dev_to_musb(dev);
-
-	musb_restore_context(musb);
-
 	/* for static cmos like DaVinci, register values were preserved
 	 * unless for some reason the whole soc powered down or the USB
 	 * module got reset through the PSC (vs just being disabled).
diff --git a/drivers/usb/musb/musb_gadget.c b/drivers/usb/musb/musb_gadget.c
index ae4a20a..922148f 100644
--- a/drivers/usb/musb/musb_gadget.c
+++ b/drivers/usb/musb/musb_gadget.c
@@ -1903,7 +1903,7 @@ static int musb_gadget_start(struct usb_gadget *g,
 	unsigned long		flags;
 	int			retval = -EINVAL;
 
-	if (driver->speed != USB_SPEED_HIGH)
+	if (driver->speed < USB_SPEED_HIGH)
 		goto err0;
 
 	pm_runtime_get_sync(musb->controller);
@@ -1999,10 +1999,6 @@ static void stop_activity(struct musb *musb, struct usb_gadget_driver *driver)
 					nuke(&hw_ep->ep_out, -ESHUTDOWN);
 			}
 		}
-
-		spin_unlock(&musb->lock);
-		driver->disconnect(&musb->g);
-		spin_lock(&musb->lock);
 	}
 }
 
diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c
index d2e2efa..08c679c 100644
--- a/drivers/usb/renesas_usbhs/common.c
+++ b/drivers/usb/renesas_usbhs/common.c
@@ -405,7 +405,7 @@ int usbhsc_drvcllbck_notify_hotplug(struct platform_device *pdev)
 /*
  *		platform functions
  */
-static int __devinit usbhs_probe(struct platform_device *pdev)
+static int usbhs_probe(struct platform_device *pdev)
 {
 	struct renesas_usbhs_platform_info *info = pdev->dev.platform_data;
 	struct renesas_usbhs_driver_callback *dfunc;
diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c
index 8da685e..ffdf5d1 100644
--- a/drivers/usb/renesas_usbhs/fifo.c
+++ b/drivers/usb/renesas_usbhs/fifo.c
@@ -820,7 +820,7 @@ static int usbhsf_dma_prepare_push(struct usbhs_pkt *pkt, int *is_done)
 	if (len % 4) /* 32bit alignment */
 		goto usbhsf_pio_prepare_push;
 
-	if ((*(u32 *) pkt->buf + pkt->actual) & 0x7) /* 8byte alignment */
+	if ((uintptr_t)(pkt->buf + pkt->actual) & 0x7) /* 8byte alignment */
 		goto usbhsf_pio_prepare_push;
 
 	/* get enable DMA fifo */
@@ -897,7 +897,7 @@ static int usbhsf_dma_try_pop(struct usbhs_pkt *pkt, int *is_done)
 	if (!fifo)
 		goto usbhsf_pio_prepare_pop;
 
-	if ((*(u32 *) pkt->buf + pkt->actual) & 0x7) /* 8byte alignment */
+	if ((uintptr_t)(pkt->buf + pkt->actual) & 0x7) /* 8byte alignment */
 		goto usbhsf_pio_prepare_pop;
 
 	ret = usbhsf_fifo_select(pipe, fifo, 0);
diff --git a/drivers/usb/renesas_usbhs/mod.h b/drivers/usb/renesas_usbhs/mod.h
index 8ae3733..6c68755 100644
--- a/drivers/usb/renesas_usbhs/mod.h
+++ b/drivers/usb/renesas_usbhs/mod.h
@@ -143,8 +143,8 @@ void usbhs_irq_callback_update(struct usbhs_priv *priv, struct usbhs_mod *mod);
  */
 #if	defined(CONFIG_USB_RENESAS_USBHS_HCD) || \
 	defined(CONFIG_USB_RENESAS_USBHS_HCD_MODULE)
-extern int __devinit usbhs_mod_host_probe(struct usbhs_priv *priv);
-extern int __devexit usbhs_mod_host_remove(struct usbhs_priv *priv);
+extern int usbhs_mod_host_probe(struct usbhs_priv *priv);
+extern int usbhs_mod_host_remove(struct usbhs_priv *priv);
 #else
 static inline int usbhs_mod_host_probe(struct usbhs_priv *priv)
 {
@@ -157,8 +157,8 @@ static inline void usbhs_mod_host_remove(struct usbhs_priv *priv)
 
 #if	defined(CONFIG_USB_RENESAS_USBHS_UDC) || \
 	defined(CONFIG_USB_RENESAS_USBHS_UDC_MODULE)
-extern int __devinit usbhs_mod_gadget_probe(struct usbhs_priv *priv);
-extern void __devexit usbhs_mod_gadget_remove(struct usbhs_priv *priv);
+extern int usbhs_mod_gadget_probe(struct usbhs_priv *priv);
+extern void usbhs_mod_gadget_remove(struct usbhs_priv *priv);
 #else
 static inline int usbhs_mod_gadget_probe(struct usbhs_priv *priv)
 {
diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c
index 4cc7ee0..7f4e803 100644
--- a/drivers/usb/renesas_usbhs/mod_gadget.c
+++ b/drivers/usb/renesas_usbhs/mod_gadget.c
@@ -751,53 +751,32 @@ static int usbhsg_gadget_start(struct usb_gadget *gadget,
 		struct usb_gadget_driver *driver)
 {
 	struct usbhsg_gpriv *gpriv = usbhsg_gadget_to_gpriv(gadget);
-	struct usbhs_priv *priv;
-	struct device *dev;
-	int ret;
+	struct usbhs_priv *priv = usbhsg_gpriv_to_priv(gpriv);
 
 	if (!driver		||
 	    !driver->setup	||
-	    driver->speed != USB_SPEED_HIGH)
+	    driver->speed < USB_SPEED_FULL)
 		return -EINVAL;
 
-	dev  = usbhsg_gpriv_to_dev(gpriv);
-	priv = usbhsg_gpriv_to_priv(gpriv);
-
 	/* first hook up the driver ... */
 	gpriv->driver = driver;
 	gpriv->gadget.dev.driver = &driver->driver;
 
-	ret = device_add(&gpriv->gadget.dev);
-	if (ret) {
-		dev_err(dev, "device_add error %d\n", ret);
-		goto add_fail;
-	}
-
 	return usbhsg_try_start(priv, USBHSG_STATUS_REGISTERD);
-
-add_fail:
-	gpriv->driver = NULL;
-	gpriv->gadget.dev.driver = NULL;
-
-	return ret;
 }
 
 static int usbhsg_gadget_stop(struct usb_gadget *gadget,
 		struct usb_gadget_driver *driver)
 {
 	struct usbhsg_gpriv *gpriv = usbhsg_gadget_to_gpriv(gadget);
-	struct usbhs_priv *priv;
-	struct device *dev;
+	struct usbhs_priv *priv = usbhsg_gpriv_to_priv(gpriv);
 
 	if (!driver		||
 	    !driver->unbind)
 		return -EINVAL;
 
-	dev  = usbhsg_gpriv_to_dev(gpriv);
-	priv = usbhsg_gpriv_to_priv(gpriv);
-
 	usbhsg_try_stop(priv, USBHSG_STATUS_REGISTERD);
-	device_del(&gpriv->gadget.dev);
+	gpriv->gadget.dev.driver = NULL;
 	gpriv->driver = NULL;
 
 	return 0;
@@ -827,10 +806,17 @@ static int usbhsg_start(struct usbhs_priv *priv)
 
 static int usbhsg_stop(struct usbhs_priv *priv)
 {
+	struct usbhsg_gpriv *gpriv = usbhsg_priv_to_gpriv(priv);
+
+	/* cable disconnect */
+	if (gpriv->driver &&
+	    gpriv->driver->disconnect)
+		gpriv->driver->disconnect(&gpriv->gadget);
+
 	return usbhsg_try_stop(priv, USBHSG_STATUS_STARTED);
 }
 
-int __devinit usbhs_mod_gadget_probe(struct usbhs_priv *priv)
+int usbhs_mod_gadget_probe(struct usbhs_priv *priv)
 {
 	struct usbhsg_gpriv *gpriv;
 	struct usbhsg_uep *uep;
@@ -876,12 +862,14 @@ int __devinit usbhs_mod_gadget_probe(struct usbhs_priv *priv)
 	/*
 	 * init gadget
 	 */
-	device_initialize(&gpriv->gadget.dev);
 	dev_set_name(&gpriv->gadget.dev, "gadget");
 	gpriv->gadget.dev.parent	= dev;
 	gpriv->gadget.name		= "renesas_usbhs_udc";
 	gpriv->gadget.ops		= &usbhsg_gadget_ops;
 	gpriv->gadget.is_dualspeed	= 1;
+	ret = device_register(&gpriv->gadget.dev);
+	if (ret < 0)
+		goto err_add_udc;
 
 	INIT_LIST_HEAD(&gpriv->gadget.ep_list);
 
@@ -912,12 +900,15 @@ int __devinit usbhs_mod_gadget_probe(struct usbhs_priv *priv)
 
 	ret = usb_add_gadget_udc(dev, &gpriv->gadget);
 	if (ret)
-		goto err_add_udc;
+		goto err_register;
 
 
 	dev_info(dev, "gadget probed\n");
 
 	return 0;
+
+err_register:
+	device_unregister(&gpriv->gadget.dev);
 err_add_udc:
 	kfree(gpriv->uep);
 
@@ -927,12 +918,14 @@ usbhs_mod_gadget_probe_err_gpriv:
 	return ret;
 }
 
-void __devexit usbhs_mod_gadget_remove(struct usbhs_priv *priv)
+void usbhs_mod_gadget_remove(struct usbhs_priv *priv)
 {
 	struct usbhsg_gpriv *gpriv = usbhsg_priv_to_gpriv(priv);
 
 	usb_del_gadget_udc(&gpriv->gadget);
 
+	device_unregister(&gpriv->gadget.dev);
+
 	usbhsg_controller_unregister(gpriv);
 
 	kfree(gpriv->uep);
diff --git a/drivers/usb/renesas_usbhs/mod_host.c b/drivers/usb/renesas_usbhs/mod_host.c
index 1a7208a..bade761 100644
--- a/drivers/usb/renesas_usbhs/mod_host.c
+++ b/drivers/usb/renesas_usbhs/mod_host.c
@@ -103,7 +103,7 @@ struct usbhsh_hpriv {
 
 	u32	port_stat;	/* USB_PORT_STAT_xxx */
 
-	struct completion	*done;
+	struct completion	setup_ack_done;
 
 	/* see usbhsh_req_alloc/free */
 	struct list_head	ureq_link_active;
@@ -355,6 +355,7 @@ static void usbhsh_device_free(struct usbhsh_hpriv *hpriv,
 struct usbhsh_ep *usbhsh_endpoint_alloc(struct usbhsh_hpriv *hpriv,
 					struct usbhsh_device *udev,
 					struct usb_host_endpoint *ep,
+					int dir_in_req,
 					gfp_t mem_flags)
 {
 	struct usbhs_priv *priv = usbhsh_hpriv_to_priv(hpriv);
@@ -364,27 +365,38 @@ struct usbhsh_ep *usbhsh_endpoint_alloc(struct usbhsh_hpriv *hpriv,
 	struct usbhs_pipe *pipe, *best_pipe;
 	struct device *dev = usbhsh_hcd_to_dev(hcd);
 	struct usb_endpoint_descriptor *desc = &ep->desc;
-	int type, i;
+	int type, i, dir_in;
 	unsigned int min_usr;
 
+	dir_in_req = !!dir_in_req;
+
 	uep = kzalloc(sizeof(struct usbhsh_ep), mem_flags);
 	if (!uep) {
 		dev_err(dev, "usbhsh_ep alloc fail\n");
 		return NULL;
 	}
-	type = usb_endpoint_type(desc);
+
+	if (usb_endpoint_xfer_control(desc)) {
+		best_pipe = usbhsh_hpriv_to_dcp(hpriv);
+		goto usbhsh_endpoint_alloc_find_pipe;
+	}
 
 	/*
 	 * find best pipe for endpoint
 	 * see
 	 *	HARDWARE LIMITATION
 	 */
+	type = usb_endpoint_type(desc);
 	min_usr = ~0;
 	best_pipe = NULL;
-	usbhs_for_each_pipe_with_dcp(pipe, priv, i) {
+	usbhs_for_each_pipe(pipe, priv, i) {
 		if (!usbhs_pipe_type_is(pipe, type))
 			continue;
 
+		dir_in = !!usbhs_pipe_is_dir_in(pipe);
+		if (0 != (dir_in - dir_in_req))
+			continue;
+
 		info = usbhsh_pipe_info(pipe);
 
 		if (min_usr > info->usr_cnt) {
@@ -398,7 +410,7 @@ struct usbhsh_ep *usbhsh_endpoint_alloc(struct usbhsh_hpriv *hpriv,
 		kfree(uep);
 		return NULL;
 	}
-
+usbhsh_endpoint_alloc_find_pipe:
 	/*
 	 * init uep
 	 */
@@ -423,6 +435,7 @@ struct usbhsh_ep *usbhsh_endpoint_alloc(struct usbhsh_hpriv *hpriv,
 	 * see
 	 *  DCPMAXP/PIPEMAXP
 	 */
+	usbhs_pipe_sequence_data0(uep->pipe);
 	usbhs_pipe_config_update(uep->pipe,
 				 usbhsh_device_number(hpriv, udev),
 				 usb_endpoint_num(desc),
@@ -430,7 +443,7 @@ struct usbhsh_ep *usbhsh_endpoint_alloc(struct usbhsh_hpriv *hpriv,
 
 	dev_dbg(dev, "%s [%d-%s](%p)\n", __func__,
 		usbhsh_device_number(hpriv, udev),
-		usbhs_pipe_name(pipe), uep);
+		usbhs_pipe_name(uep->pipe), uep);
 
 	return uep;
 }
@@ -549,8 +562,7 @@ static void usbhsh_setup_stage_packet_push(struct usbhsh_hpriv *hpriv,
 	 *	usbhsh_irq_setup_ack()
 	 *	usbhsh_irq_setup_err()
 	 */
-	DECLARE_COMPLETION(done);
-	hpriv->done = &done;
+	init_completion(&hpriv->setup_ack_done);
 
 	/* copy original request */
 	memcpy(&req, urb->setup_packet, sizeof(struct usb_ctrlrequest));
@@ -572,8 +584,7 @@ static void usbhsh_setup_stage_packet_push(struct usbhsh_hpriv *hpriv,
 	/*
 	 * wait setup packet ACK
 	 */
-	wait_for_completion(&done);
-	hpriv->done = NULL;
+	wait_for_completion(&hpriv->setup_ack_done);
 
 	dev_dbg(dev, "%s done\n", __func__);
 }
@@ -724,11 +735,11 @@ static int usbhsh_urb_enqueue(struct usb_hcd *hcd,
 	struct usbhsh_device *udev, *new_udev = NULL;
 	struct usbhs_pipe *pipe;
 	struct usbhsh_ep *uep;
+	int is_dir_in = usb_pipein(urb->pipe);
 
 	int ret;
 
-	dev_dbg(dev, "%s (%s)\n",
-		__func__, usb_pipein(urb->pipe) ? "in" : "out");
+	dev_dbg(dev, "%s (%s)\n", __func__, is_dir_in ? "in" : "out");
 
 	ret = usb_hcd_link_urb_to_ep(hcd, urb);
 	if (ret)
@@ -751,7 +762,8 @@ static int usbhsh_urb_enqueue(struct usb_hcd *hcd,
 	 */
 	uep = usbhsh_ep_to_uep(ep);
 	if (!uep) {
-		uep = usbhsh_endpoint_alloc(hpriv, udev, ep, mem_flags);
+		uep = usbhsh_endpoint_alloc(hpriv, udev, ep,
+					    is_dir_in, mem_flags);
 		if (!uep)
 			goto usbhsh_urb_enqueue_error_free_device;
 	}
@@ -1095,10 +1107,7 @@ static int usbhsh_irq_setup_ack(struct usbhs_priv *priv,
 
 	dev_dbg(dev, "setup packet OK\n");
 
-	if (unlikely(!hpriv->done))
-		dev_err(dev, "setup ack happen without necessary data\n");
-	else
-		complete(hpriv->done); /* see usbhsh_urb_enqueue() */
+	complete(&hpriv->setup_ack_done); /* see usbhsh_urb_enqueue() */
 
 	return 0;
 }
@@ -1111,10 +1120,7 @@ static int usbhsh_irq_setup_err(struct usbhs_priv *priv,
 
 	dev_dbg(dev, "setup packet Err\n");
 
-	if (unlikely(!hpriv->done))
-		dev_err(dev, "setup err happen without necessary data\n");
-	else
-		complete(hpriv->done); /* see usbhsh_urb_enqueue() */
+	complete(&hpriv->setup_ack_done); /* see usbhsh_urb_enqueue() */
 
 	return 0;
 }
@@ -1221,8 +1227,18 @@ static int usbhsh_stop(struct usbhs_priv *priv)
 {
 	struct usbhsh_hpriv *hpriv = usbhsh_priv_to_hpriv(priv);
 	struct usb_hcd *hcd = usbhsh_hpriv_to_hcd(hpriv);
+	struct usbhs_mod *mod = usbhs_mod_get_current(priv);
 	struct device *dev = usbhs_priv_to_dev(priv);
 
+	/*
+	 * disable irq callback
+	 */
+	mod->irq_attch	= NULL;
+	mod->irq_dtch	= NULL;
+	mod->irq_sack	= NULL;
+	mod->irq_sign	= NULL;
+	usbhs_irq_callback_update(priv, mod);
+
 	usb_remove_hcd(hcd);
 
 	/* disable sys */
@@ -1235,7 +1251,7 @@ static int usbhsh_stop(struct usbhs_priv *priv)
 	return 0;
 }
 
-int __devinit usbhs_mod_host_probe(struct usbhs_priv *priv)
+int usbhs_mod_host_probe(struct usbhs_priv *priv)
 {
 	struct usbhsh_hpriv *hpriv;
 	struct usb_hcd *hcd;
@@ -1279,7 +1295,6 @@ int __devinit usbhs_mod_host_probe(struct usbhs_priv *priv)
 	hpriv->mod.stop		= usbhsh_stop;
 	hpriv->pipe_info	= pipe_info;
 	hpriv->pipe_size	= pipe_size;
-	hpriv->done		= NULL;
 	usbhsh_req_list_init(hpriv);
 	usbhsh_port_stat_init(hpriv);
 
@@ -1299,7 +1314,7 @@ usbhs_mod_host_probe_err:
 	return -ENOMEM;
 }
 
-int __devexit usbhs_mod_host_remove(struct usbhs_priv *priv)
+int usbhs_mod_host_remove(struct usbhs_priv *priv)
 {
 	struct usbhsh_hpriv *hpriv = usbhsh_priv_to_hpriv(priv);
 	struct usb_hcd *hcd = usbhsh_hpriv_to_hcd(hpriv);
diff --git a/drivers/usb/serial/ark3116.c b/drivers/usb/serial/ark3116.c
index 5cdb9d9..18e875b 100644
--- a/drivers/usb/serial/ark3116.c
+++ b/drivers/usb/serial/ark3116.c
@@ -42,7 +42,7 @@ static int debug;
  * Version information
  */
 
-#define DRIVER_VERSION "v0.6"
+#define DRIVER_VERSION "v0.7"
 #define DRIVER_AUTHOR "Bart Hartgers <bart.hartgers+ark3116@gmail.com>"
 #define DRIVER_DESC "USB ARK3116 serial/IrDA driver"
 #define DRIVER_DEV_DESC "ARK3116 RS232/IrDA"
@@ -380,10 +380,6 @@ static int ark3116_open(struct tty_struct *tty, struct usb_serial_port *port)
 		goto err_out;
 	}
 
-	/* setup termios */
-	if (tty)
-		ark3116_set_termios(tty, port, NULL);
-
 	/* remove any data still left: also clears error state */
 	ark3116_read_reg(serial, UART_RX, buf);
 
@@ -406,6 +402,10 @@ static int ark3116_open(struct tty_struct *tty, struct usb_serial_port *port)
 	/* enable DMA */
 	ark3116_write_reg(port->serial, UART_FCR, UART_FCR_DMA_SELECT);
 
+	/* setup termios */
+	if (tty)
+		ark3116_set_termios(tty, port, NULL);
+
 err_out:
 	kfree(buf);
 	return result;
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 8fe034d..ff3db5d 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -736,6 +736,7 @@ static struct usb_device_id id_table_combined [] = {
 	{ USB_DEVICE(TML_VID, TML_USB_SERIAL_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_ELSTER_UNICOM_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_PROPOX_JTAGCABLEII_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_PROPOX_ISPCABLEIII_PID) },
 	{ USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	{ USB_DEVICE(OLIMEX_VID, OLIMEX_ARM_USB_OCD_H_PID),
@@ -2104,13 +2105,19 @@ static void ftdi_set_termios(struct tty_struct *tty,
 
 	cflag = termios->c_cflag;
 
-	/* FIXME -For this cut I don't care if the line is really changing or
-	   not  - so just do the change regardless  - should be able to
-	   compare old_termios and tty->termios */
+	if (old_termios->c_cflag == termios->c_cflag
+	    && old_termios->c_ispeed == termios->c_ispeed
+	    && old_termios->c_ospeed == termios->c_ospeed)
+		goto no_c_cflag_changes;
+
 	/* NOTE These routines can get interrupted by
 	   ftdi_sio_read_bulk_callback  - need to examine what this means -
 	   don't see any problems yet */
 
+	if ((old_termios->c_cflag & (CSIZE|PARODD|PARENB|CMSPAR|CSTOPB)) ==
+	    (termios->c_cflag & (CSIZE|PARODD|PARENB|CMSPAR|CSTOPB)))
+		goto no_data_parity_stop_changes;
+
 	/* Set number of data bits, parity, stop bits */
 
 	urb_value = 0;
@@ -2151,6 +2158,7 @@ static void ftdi_set_termios(struct tty_struct *tty,
 	}
 
 	/* Now do the baudrate */
+no_data_parity_stop_changes:
 	if ((cflag & CBAUD) == B0) {
 		/* Disable flow control */
 		if (usb_control_msg(dev, usb_sndctrlpipe(dev, 0),
@@ -2178,6 +2186,7 @@ static void ftdi_set_termios(struct tty_struct *tty,
 
 	/* Set flow control */
 	/* Note device also supports DTR/CD (ugh) and Xon/Xoff in hardware */
+no_c_cflag_changes:
 	if (cflag & CRTSCTS) {
 		dbg("%s Setting to CRTSCTS flow control", __func__);
 		if (usb_control_msg(dev,
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 571fa96..055b64e 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -112,6 +112,7 @@
 
 /* Propox devices */
 #define FTDI_PROPOX_JTAGCABLEII_PID	0xD738
+#define FTDI_PROPOX_ISPCABLEIII_PID	0xD739
 
 /* Lenz LI-USB Computer Interface. */
 #define FTDI_LENZ_LIUSB_PID	0xD780
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 89ae1f6..e342660 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -156,6 +156,7 @@ static void option_instat_callback(struct urb *urb);
 #define HUAWEI_PRODUCT_K4511			0x14CC
 #define HUAWEI_PRODUCT_ETS1220			0x1803
 #define HUAWEI_PRODUCT_E353			0x1506
+#define HUAWEI_PRODUCT_E173S			0x1C05
 
 #define QUANTA_VENDOR_ID			0x0408
 #define QUANTA_PRODUCT_Q101			0xEA02
@@ -316,6 +317,9 @@ static void option_instat_callback(struct urb *urb);
 #define ZTE_PRODUCT_AC8710			0xfff1
 #define ZTE_PRODUCT_AC2726			0xfff5
 #define ZTE_PRODUCT_AC8710T			0xffff
+#define ZTE_PRODUCT_MC2718			0xffe8
+#define ZTE_PRODUCT_AD3812			0xffeb
+#define ZTE_PRODUCT_MC2716			0xffed
 
 #define BENQ_VENDOR_ID				0x04a5
 #define BENQ_PRODUCT_H10			0x4068
@@ -468,6 +472,10 @@ static void option_instat_callback(struct urb *urb);
 #define YUGA_PRODUCT_CLU528			0x260D
 #define YUGA_PRODUCT_CLU526			0x260F
 
+/* Viettel products */
+#define VIETTEL_VENDOR_ID			0x2262
+#define VIETTEL_PRODUCT_VT1000			0x0002
+
 /* some devices interfaces need special handling due to a number of reasons */
 enum option_blacklist_reason {
 		OPTION_BLACKLIST_NONE = 0,
@@ -500,6 +508,18 @@ static const struct option_blacklist_info zte_k3765_z_blacklist = {
 	.reserved = BIT(4),
 };
 
+static const struct option_blacklist_info zte_ad3812_z_blacklist = {
+	.sendsetup = BIT(0) | BIT(1) | BIT(2),
+};
+
+static const struct option_blacklist_info zte_mc2718_z_blacklist = {
+	.sendsetup = BIT(1) | BIT(2) | BIT(3) | BIT(4),
+};
+
+static const struct option_blacklist_info zte_mc2716_z_blacklist = {
+	.sendsetup = BIT(1) | BIT(2) | BIT(3),
+};
+
 static const struct option_blacklist_info huawei_cdc12_blacklist = {
 	.reserved = BIT(1) | BIT(2),
 };
@@ -622,6 +642,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E143D, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E143E, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E143F, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E173S, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4505, 0xff, 0xff, 0xff),
 		.driver_info = (kernel_ulong_t) &huawei_cdc12_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K3765, 0xff, 0xff, 0xff),
@@ -640,6 +661,9 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4511, 0xff, 0x01, 0x31) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_K4511, 0xff, 0x01, 0x32) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x01) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x02) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x03) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(HUAWEI_VENDOR_ID, HUAWEI_PRODUCT_E353, 0xff, 0x01, 0x08) },
 	{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V640) },
 	{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V620) },
 	{ USB_DEVICE(NOVATELWIRELESS_VENDOR_ID, NOVATELWIRELESS_PRODUCT_V740) },
@@ -726,6 +750,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(KYOCERA_VENDOR_ID, KYOCERA_PRODUCT_KPC680) },
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6000)}, /* ZTE AC8700 */
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x6613)}, /* Onda H600/ZTE MF330 */
+	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6280) }, /* BP3-USB & BP3-EXT HSDPA */
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6008) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_UC864E) },
@@ -1043,6 +1068,12 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC2726, 0xff, 0xff, 0xff) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AC8710T, 0xff, 0xff, 0xff) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2718, 0xff, 0xff, 0xff),
+	 .driver_info = (kernel_ulong_t)&zte_mc2718_z_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_AD3812, 0xff, 0xff, 0xff),
+	 .driver_info = (kernel_ulong_t)&zte_ad3812_z_blacklist },
+	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2716, 0xff, 0xff, 0xff),
+	 .driver_info = (kernel_ulong_t)&zte_mc2716_z_blacklist },
 	{ USB_DEVICE(BENQ_VENDOR_ID, BENQ_PRODUCT_H10) },
 	{ USB_DEVICE(DLINK_VENDOR_ID, DLINK_PRODUCT_DWM_652) },
 	{ USB_DEVICE(ALINK_VENDOR_ID, DLINK_PRODUCT_DWM_652_U5) }, /* Yes, ALINK_VENDOR_ID */
@@ -1141,6 +1172,7 @@ static const struct usb_device_id option_ids[] = {
 	{ USB_DEVICE(YUGA_VENDOR_ID, YUGA_PRODUCT_CLU516) },
 	{ USB_DEVICE(YUGA_VENDOR_ID, YUGA_PRODUCT_CLU528) },
 	{ USB_DEVICE(YUGA_VENDOR_ID, YUGA_PRODUCT_CLU526) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(VIETTEL_VENDOR_ID, VIETTEL_PRODUCT_VT1000, 0xff, 0xff, 0xff) },
 	{ } /* Terminating entry */
 };
 MODULE_DEVICE_TABLE(usb, option_ids);
diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
index 9083d1e..fc2d66f 100644
--- a/drivers/usb/serial/pl2303.c
+++ b/drivers/usb/serial/pl2303.c
@@ -91,7 +91,6 @@ static const struct usb_device_id id_table[] = {
 	{ USB_DEVICE(SONY_VENDOR_ID, SONY_QN3USB_PRODUCT_ID) },
 	{ USB_DEVICE(SANWA_VENDOR_ID, SANWA_PRODUCT_ID) },
 	{ USB_DEVICE(ADLINK_VENDOR_ID, ADLINK_ND6530_PRODUCT_ID) },
-	{ USB_DEVICE(WINCHIPHEAD_VENDOR_ID, WINCHIPHEAD_USBSER_PRODUCT_ID) },
 	{ USB_DEVICE(SMART_VENDOR_ID, SMART_PRODUCT_ID) },
 	{ }					/* Terminating entry */
 };
diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h
index 3d10d7f..c38b8c0 100644
--- a/drivers/usb/serial/pl2303.h
+++ b/drivers/usb/serial/pl2303.h
@@ -145,10 +145,6 @@
 #define ADLINK_VENDOR_ID		0x0b63
 #define ADLINK_ND6530_PRODUCT_ID	0x6530
 
-/* WinChipHead USB->RS 232 adapter */
-#define WINCHIPHEAD_VENDOR_ID		0x4348
-#define WINCHIPHEAD_USBSER_PRODUCT_ID	0x5523
-
 /* SMART USB Serial Adapter */
 #define SMART_VENDOR_ID	0x0b8c
 #define SMART_PRODUCT_ID	0x2303
diff --git a/drivers/usb/storage/ene_ub6250.c b/drivers/usb/storage/ene_ub6250.c
index 4dca3ef..9fbe742 100644
--- a/drivers/usb/storage/ene_ub6250.c
+++ b/drivers/usb/storage/ene_ub6250.c
@@ -1762,10 +1762,9 @@ static int ms_scsi_write(struct us_data *us, struct scsi_cmnd *srb)
 		result = ene_send_scsi_cmd(us, FDIR_WRITE, scsi_sglist(srb), 1);
 	} else {
 		void *buf;
-		int offset;
+		int offset = 0;
 		u16 PhyBlockAddr;
 		u8 PageNum;
-		u32 result;
 		u16 len, oldphy, newphy;
 
 		buf = kmalloc(blenByte, GFP_KERNEL);
diff --git a/drivers/usb/storage/protocol.c b/drivers/usb/storage/protocol.c
index 93c1a4d..82dd834 100644
--- a/drivers/usb/storage/protocol.c
+++ b/drivers/usb/storage/protocol.c
@@ -59,7 +59,9 @@
 
 void usb_stor_pad12_command(struct scsi_cmnd *srb, struct us_data *us)
 {
-	/* Pad the SCSI command with zeros out to 12 bytes
+	/*
+	 * Pad the SCSI command with zeros out to 12 bytes.  If the
+	 * command already is 12 bytes or longer, leave it alone.
 	 *
 	 * NOTE: This only works because a scsi_cmnd struct field contains
 	 * a unsigned char cmnd[16], so we know we have storage available
@@ -67,9 +69,6 @@ void usb_stor_pad12_command(struct scsi_cmnd *srb, struct us_data *us)
 	for (; srb->cmd_len<12; srb->cmd_len++)
 		srb->cmnd[srb->cmd_len] = 0;
 
-	/* set command length to 12 bytes */
-	srb->cmd_len = 12;
-
 	/* send the command to the transport layer */
 	usb_stor_invoke_transport(srb, us);
 }
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 3041a97..24caba7 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -1854,6 +1854,13 @@ UNUSUAL_DEV(  0x1370, 0x6828, 0x0110, 0x0110,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_IGNORE_RESIDUE ),
 
+/* Reported by Qinglin Ye <yestyle@gmail.com> */
+UNUSUAL_DEV(  0x13fe, 0x3600, 0x0100, 0x0100,
+		"Kingston",
+		"DT 101 G2",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_BULK_IGNORE_TAG ),
+
 /* Reported by Francesco Foresti <frafore@tiscali.it> */
 UNUSUAL_DEV(  0x14cd, 0x6600, 0x0201, 0x0201,
 		"Super Top",
diff --git a/drivers/video/da8xx-fb.c b/drivers/video/da8xx-fb.c
index 55f91d9..29577bf 100644
--- a/drivers/video/da8xx-fb.c
+++ b/drivers/video/da8xx-fb.c
@@ -116,6 +116,7 @@
 /* Clock registers available only on Version 2 */
 #define  LCD_CLK_ENABLE_REG			0x6c
 #define  LCD_CLK_RESET_REG			0x70
+#define  LCD_CLK_MAIN_RESET			BIT(3)
 
 #define LCD_NUM_BUFFERS	2
 
@@ -244,6 +245,10 @@ static inline void lcd_enable_raster(void)
 {
 	u32 reg;
 
+	/* Bring LCDC out of reset */
+	if (lcd_revision == LCD_VERSION_2)
+		lcdc_write(0, LCD_CLK_RESET_REG);
+
 	reg = lcdc_read(LCD_RASTER_CTRL_REG);
 	if (!(reg & LCD_RASTER_ENABLE))
 		lcdc_write(reg | LCD_RASTER_ENABLE, LCD_RASTER_CTRL_REG);
@@ -257,6 +262,10 @@ static inline void lcd_disable_raster(void)
 	reg = lcdc_read(LCD_RASTER_CTRL_REG);
 	if (reg & LCD_RASTER_ENABLE)
 		lcdc_write(reg & ~LCD_RASTER_ENABLE, LCD_RASTER_CTRL_REG);
+
+	if (lcd_revision == LCD_VERSION_2)
+		/* Write 1 to reset LCDC */
+		lcdc_write(LCD_CLK_MAIN_RESET, LCD_CLK_RESET_REG);
 }
 
 static void lcd_blit(int load_mode, struct da8xx_fb_par *par)
@@ -584,8 +593,12 @@ static void lcd_reset(struct da8xx_fb_par *par)
 	lcdc_write(0, LCD_DMA_CTRL_REG);
 	lcdc_write(0, LCD_RASTER_CTRL_REG);
 
-	if (lcd_revision == LCD_VERSION_2)
+	if (lcd_revision == LCD_VERSION_2) {
 		lcdc_write(0, LCD_INT_ENABLE_SET_REG);
+		/* Write 1 to reset */
+		lcdc_write(LCD_CLK_MAIN_RESET, LCD_CLK_RESET_REG);
+		lcdc_write(0, LCD_CLK_RESET_REG);
+	}
 }
 
 static void lcd_calc_clk_divider(struct da8xx_fb_par *par)
diff --git a/drivers/video/omap/dispc.c b/drivers/video/omap/dispc.c
index 0ccd7ad..6f61e78 100644
--- a/drivers/video/omap/dispc.c
+++ b/drivers/video/omap/dispc.c
@@ -19,6 +19,7 @@
  * 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
  */
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/dma-mapping.h>
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
diff --git a/drivers/video/omap2/dss/dispc.c b/drivers/video/omap2/dss/dispc.c
index 3532782..5c81533 100644
--- a/drivers/video/omap2/dss/dispc.c
+++ b/drivers/video/omap2/dss/dispc.c
@@ -1720,12 +1720,11 @@ static int dispc_ovl_calc_scaling(enum omap_plane plane,
 	const int maxdownscale = dss_feat_get_param_max(FEAT_PARAM_DOWNSCALE);
 	unsigned long fclk = 0;
 
-	if ((ovl->caps & OMAP_DSS_OVL_CAP_SCALE) == 0) {
-		if (width != out_width || height != out_height)
-			return -EINVAL;
-		else
-			return 0;
-	}
+	if (width == out_width && height == out_height)
+		return 0;
+
+	if ((ovl->caps & OMAP_DSS_OVL_CAP_SCALE) == 0)
+		return -EINVAL;
 
 	if (out_width < width / maxdownscale ||
 			out_width > width * 8)
diff --git a/drivers/video/omap2/dss/hdmi.c b/drivers/video/omap2/dss/hdmi.c
index 3262f0f..c56378c 100644
--- a/drivers/video/omap2/dss/hdmi.c
+++ b/drivers/video/omap2/dss/hdmi.c
@@ -269,7 +269,7 @@ static void update_hdmi_timings(struct hdmi_config *cfg,
 unsigned long hdmi_get_pixel_clock(void)
 {
 	/* HDMI Pixel Clock in Mhz */
-	return hdmi.ip_data.cfg.timings.timings.pixel_clock * 10000;
+	return hdmi.ip_data.cfg.timings.timings.pixel_clock * 1000;
 }
 
 static void hdmi_compute_pll(struct omap_dss_device *dssdev, int phy,
diff --git a/drivers/video/via/share.h b/drivers/video/via/share.h
index 69d882c..c01c1c1 100644
--- a/drivers/video/via/share.h
+++ b/drivers/video/via/share.h
@@ -559,8 +559,8 @@
 #define M1200X720_R60_VSP       POSITIVE
 
 /* 1200x900@60 Sync Polarity (DCON) */
-#define M1200X900_R60_HSP       NEGATIVE
-#define M1200X900_R60_VSP       NEGATIVE
+#define M1200X900_R60_HSP       POSITIVE
+#define M1200X900_R60_VSP       POSITIVE
 
 /* 1280x600@60 Sync Polarity (GTF Mode) */
 #define M1280x600_R60_HSP       NEGATIVE
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 816ed08..1a61939 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -37,7 +37,7 @@ config VIRTIO_BALLOON
 
  config VIRTIO_MMIO
  	tristate "Platform bus driver for memory mapped virtio devices (EXPERIMENTAL)"
- 	depends on EXPERIMENTAL
+ 	depends on HAS_IOMEM && EXPERIMENTAL
  	select VIRTIO
  	select VIRTIO_RING
  	---help---
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index acc5e43..0269717 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -118,7 +118,7 @@ static void vm_finalize_features(struct virtio_device *vdev)
 	vring_transport_features(vdev);
 
 	for (i = 0; i < ARRAY_SIZE(vdev->features); i++) {
-		writel(i, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES_SET);
+		writel(i, vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES_SEL);
 		writel(vdev->features[i],
 				vm_dev->base + VIRTIO_MMIO_GUEST_FEATURES);
 	}
@@ -361,7 +361,12 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 	return 0;
 }
 
+static const char *vm_bus_name(struct virtio_device *vdev)
+{
+	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
 
+	return vm_dev->pdev->name;
+}
 
 static struct virtio_config_ops virtio_mmio_config_ops = {
 	.get		= vm_get,
@@ -373,6 +378,7 @@ static struct virtio_config_ops virtio_mmio_config_ops = {
 	.del_vqs	= vm_del_vqs,
 	.get_features	= vm_get_features,
 	.finalize_features = vm_finalize_features,
+	.bus_name	= vm_bus_name,
 };
 
 
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index 3d1bf41..baabb79 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -169,11 +169,29 @@ static void vp_set_status(struct virtio_device *vdev, u8 status)
 	iowrite8(status, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
 }
 
+/* wait for pending irq handlers */
+static void vp_synchronize_vectors(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	int i;
+
+	if (vp_dev->intx_enabled)
+		synchronize_irq(vp_dev->pci_dev->irq);
+
+	for (i = 0; i < vp_dev->msix_vectors; ++i)
+		synchronize_irq(vp_dev->msix_entries[i].vector);
+}
+
 static void vp_reset(struct virtio_device *vdev)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 	/* 0 status means a reset. */
 	iowrite8(0, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+	/* Flush out the status write, and flush in device writes,
+	 * including MSi-X interrupts, if any. */
+	ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+	/* Flush pending VQ/configuration callbacks. */
+	vp_synchronize_vectors(vdev);
 }
 
 /* the notify function used when creating a virt queue */
@@ -580,6 +598,13 @@ static int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 				  false, false);
 }
 
+static const char *vp_bus_name(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	return pci_name(vp_dev->pci_dev);
+}
+
 static struct virtio_config_ops virtio_pci_config_ops = {
 	.get		= vp_get,
 	.set		= vp_set,
@@ -590,6 +615,7 @@ static struct virtio_config_ops virtio_pci_config_ops = {
 	.del_vqs	= vp_del_vqs,
 	.get_features	= vp_get_features,
 	.finalize_features = vp_finalize_features,
+	.bus_name	= vp_bus_name,
 };
 
 static void virtio_pci_release_dev(struct device *_d)
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 6285867..79fd606 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -314,13 +314,6 @@ config NUC900_WATCHDOG
 	  To compile this driver as a module, choose M here: the
 	  module will be called nuc900_wdt.
 
-config ADX_WATCHDOG
-	tristate "Avionic Design Xanthos watchdog"
-	depends on ARCH_PXA_ADX
-	help
-	  Say Y here if you want support for the watchdog timer on Avionic
-	  Design Xanthos boards.
-
 config TS72XX_WATCHDOG
 	tristate "TS-72XX SBC Watchdog"
 	depends on MACH_TS72XX
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index 55bd574..fe893e9 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -51,7 +51,6 @@ obj-$(CONFIG_ORION_WATCHDOG) += orion_wdt.o
 obj-$(CONFIG_COH901327_WATCHDOG) += coh901327_wdt.o
 obj-$(CONFIG_STMP3XXX_WATCHDOG) += stmp3xxx_wdt.o
 obj-$(CONFIG_NUC900_WATCHDOG) += nuc900_wdt.o
-obj-$(CONFIG_ADX_WATCHDOG) += adx_wdt.o
 obj-$(CONFIG_TS72XX_WATCHDOG) += ts72xx_wdt.o
 obj-$(CONFIG_IMX2_WDT) += imx2_wdt.o
 
diff --git a/drivers/watchdog/adx_wdt.c b/drivers/watchdog/adx_wdt.c
deleted file mode 100644
index af6e6b1..0000000
--- a/drivers/watchdog/adx_wdt.c
+++ /dev/null
@@ -1,355 +0,0 @@
-/*
- * Copyright (C) 2008-2009 Avionic Design GmbH
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/fs.h>
-#include <linux/gfp.h>
-#include <linux/io.h>
-#include <linux/miscdevice.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/types.h>
-#include <linux/uaccess.h>
-#include <linux/watchdog.h>
-
-#define WATCHDOG_NAME "adx-wdt"
-
-/* register offsets */
-#define	ADX_WDT_CONTROL		0x00
-#define	ADX_WDT_CONTROL_ENABLE	(1 << 0)
-#define	ADX_WDT_CONTROL_nRESET	(1 << 1)
-#define	ADX_WDT_TIMEOUT		0x08
-
-static struct platform_device *adx_wdt_dev;
-static unsigned long driver_open;
-
-#define	WDT_STATE_STOP	0
-#define	WDT_STATE_START	1
-
-struct adx_wdt {
-	void __iomem *base;
-	unsigned long timeout;
-	unsigned int state;
-	unsigned int wake;
-	spinlock_t lock;
-};
-
-static const struct watchdog_info adx_wdt_info = {
-	.identity = "Avionic Design Xanthos Watchdog",
-	.options = WDIOF_SETTIMEOUT | WDIOF_KEEPALIVEPING,
-};
-
-static void adx_wdt_start_locked(struct adx_wdt *wdt)
-{
-	u32 ctrl;
-
-	ctrl = readl(wdt->base + ADX_WDT_CONTROL);
-	ctrl |= ADX_WDT_CONTROL_ENABLE;
-	writel(ctrl, wdt->base + ADX_WDT_CONTROL);
-	wdt->state = WDT_STATE_START;
-}
-
-static void adx_wdt_start(struct adx_wdt *wdt)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&wdt->lock, flags);
-	adx_wdt_start_locked(wdt);
-	spin_unlock_irqrestore(&wdt->lock, flags);
-}
-
-static void adx_wdt_stop_locked(struct adx_wdt *wdt)
-{
-	u32 ctrl;
-
-	ctrl = readl(wdt->base + ADX_WDT_CONTROL);
-	ctrl &= ~ADX_WDT_CONTROL_ENABLE;
-	writel(ctrl, wdt->base + ADX_WDT_CONTROL);
-	wdt->state = WDT_STATE_STOP;
-}
-
-static void adx_wdt_stop(struct adx_wdt *wdt)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&wdt->lock, flags);
-	adx_wdt_stop_locked(wdt);
-	spin_unlock_irqrestore(&wdt->lock, flags);
-}
-
-static void adx_wdt_set_timeout(struct adx_wdt *wdt, unsigned long seconds)
-{
-	unsigned long timeout = seconds * 1000;
-	unsigned long flags;
-	unsigned int state;
-
-	spin_lock_irqsave(&wdt->lock, flags);
-	state = wdt->state;
-	adx_wdt_stop_locked(wdt);
-	writel(timeout, wdt->base + ADX_WDT_TIMEOUT);
-
-	if (state == WDT_STATE_START)
-		adx_wdt_start_locked(wdt);
-
-	wdt->timeout = timeout;
-	spin_unlock_irqrestore(&wdt->lock, flags);
-}
-
-static void adx_wdt_get_timeout(struct adx_wdt *wdt, unsigned long *seconds)
-{
-	*seconds = wdt->timeout / 1000;
-}
-
-static void adx_wdt_keepalive(struct adx_wdt *wdt)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&wdt->lock, flags);
-	writel(wdt->timeout, wdt->base + ADX_WDT_TIMEOUT);
-	spin_unlock_irqrestore(&wdt->lock, flags);
-}
-
-static int adx_wdt_open(struct inode *inode, struct file *file)
-{
-	struct adx_wdt *wdt = platform_get_drvdata(adx_wdt_dev);
-
-	if (test_and_set_bit(0, &driver_open))
-		return -EBUSY;
-
-	file->private_data = wdt;
-	adx_wdt_set_timeout(wdt, 30);
-	adx_wdt_start(wdt);
-
-	return nonseekable_open(inode, file);
-}
-
-static int adx_wdt_release(struct inode *inode, struct file *file)
-{
-	struct adx_wdt *wdt = file->private_data;
-
-	adx_wdt_stop(wdt);
-	clear_bit(0, &driver_open);
-
-	return 0;
-}
-
-static long adx_wdt_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-	struct adx_wdt *wdt = file->private_data;
-	void __user *argp = (void __user *)arg;
-	unsigned long __user *p = argp;
-	unsigned long seconds = 0;
-	unsigned int options;
-	long ret = -EINVAL;
-
-	switch (cmd) {
-	case WDIOC_GETSUPPORT:
-		if (copy_to_user(argp, &adx_wdt_info, sizeof(adx_wdt_info)))
-			return -EFAULT;
-		else
-			return 0;
-
-	case WDIOC_GETSTATUS:
-	case WDIOC_GETBOOTSTATUS:
-		return put_user(0, p);
-
-	case WDIOC_KEEPALIVE:
-		adx_wdt_keepalive(wdt);
-		return 0;
-
-	case WDIOC_SETTIMEOUT:
-		if (get_user(seconds, p))
-			return -EFAULT;
-
-		adx_wdt_set_timeout(wdt, seconds);
-
-		/* fallthrough */
-	case WDIOC_GETTIMEOUT:
-		adx_wdt_get_timeout(wdt, &seconds);
-		return put_user(seconds, p);
-
-	case WDIOC_SETOPTIONS:
-		if (copy_from_user(&options, argp, sizeof(options)))
-			return -EFAULT;
-
-		if (options & WDIOS_DISABLECARD) {
-			adx_wdt_stop(wdt);
-			ret = 0;
-		}
-
-		if (options & WDIOS_ENABLECARD) {
-			adx_wdt_start(wdt);
-			ret = 0;
-		}
-
-		return ret;
-
-	default:
-		break;
-	}
-
-	return -ENOTTY;
-}
-
-static ssize_t adx_wdt_write(struct file *file, const char __user *data,
-		size_t len, loff_t *ppos)
-{
-	struct adx_wdt *wdt = file->private_data;
-
-	if (len)
-		adx_wdt_keepalive(wdt);
-
-	return len;
-}
-
-static const struct file_operations adx_wdt_fops = {
-	.owner = THIS_MODULE,
-	.llseek = no_llseek,
-	.open = adx_wdt_open,
-	.release = adx_wdt_release,
-	.unlocked_ioctl = adx_wdt_ioctl,
-	.write = adx_wdt_write,
-};
-
-static struct miscdevice adx_wdt_miscdev = {
-	.minor = WATCHDOG_MINOR,
-	.name = "watchdog",
-	.fops = &adx_wdt_fops,
-};
-
-static int __devinit adx_wdt_probe(struct platform_device *pdev)
-{
-	struct resource *res;
-	struct adx_wdt *wdt;
-	int ret = 0;
-	u32 ctrl;
-
-	wdt = devm_kzalloc(&pdev->dev, sizeof(*wdt), GFP_KERNEL);
-	if (!wdt) {
-		dev_err(&pdev->dev, "cannot allocate WDT structure\n");
-		return -ENOMEM;
-	}
-
-	spin_lock_init(&wdt->lock);
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(&pdev->dev, "cannot obtain I/O memory region\n");
-		return -ENXIO;
-	}
-
-	res = devm_request_mem_region(&pdev->dev, res->start,
-			resource_size(res), res->name);
-	if (!res) {
-		dev_err(&pdev->dev, "cannot request I/O memory region\n");
-		return -ENXIO;
-	}
-
-	wdt->base = devm_ioremap_nocache(&pdev->dev, res->start,
-			resource_size(res));
-	if (!wdt->base) {
-		dev_err(&pdev->dev, "cannot remap I/O memory region\n");
-		return -ENXIO;
-	}
-
-	/* disable watchdog and reboot on timeout */
-	ctrl = readl(wdt->base + ADX_WDT_CONTROL);
-	ctrl &= ~ADX_WDT_CONTROL_ENABLE;
-	ctrl &= ~ADX_WDT_CONTROL_nRESET;
-	writel(ctrl, wdt->base + ADX_WDT_CONTROL);
-
-	platform_set_drvdata(pdev, wdt);
-	adx_wdt_dev = pdev;
-
-	ret = misc_register(&adx_wdt_miscdev);
-	if (ret) {
-		dev_err(&pdev->dev, "cannot register miscdev on minor %d "
-				"(err=%d)\n", WATCHDOG_MINOR, ret);
-		return ret;
-	}
-
-	return 0;
-}
-
-static int __devexit adx_wdt_remove(struct platform_device *pdev)
-{
-	struct adx_wdt *wdt = platform_get_drvdata(pdev);
-
-	misc_deregister(&adx_wdt_miscdev);
-	adx_wdt_stop(wdt);
-	platform_set_drvdata(pdev, NULL);
-
-	return 0;
-}
-
-static void adx_wdt_shutdown(struct platform_device *pdev)
-{
-	struct adx_wdt *wdt = platform_get_drvdata(pdev);
-	adx_wdt_stop(wdt);
-}
-
-#ifdef CONFIG_PM
-static int adx_wdt_suspend(struct device *dev)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	struct adx_wdt *wdt = platform_get_drvdata(pdev);
-
-	wdt->wake = (wdt->state == WDT_STATE_START) ? 1 : 0;
-	adx_wdt_stop(wdt);
-
-	return 0;
-}
-
-static int adx_wdt_resume(struct device *dev)
-{
-	struct platform_device *pdev = to_platform_device(dev);
-	struct adx_wdt *wdt = platform_get_drvdata(pdev);
-
-	if (wdt->wake)
-		adx_wdt_start(wdt);
-
-	return 0;
-}
-
-static const struct dev_pm_ops adx_wdt_pm_ops = {
-	.suspend = adx_wdt_suspend,
-	.resume = adx_wdt_resume,
-};
-
-#  define ADX_WDT_PM_OPS	(&adx_wdt_pm_ops)
-#else
-#  define ADX_WDT_PM_OPS	NULL
-#endif
-
-static struct platform_driver adx_wdt_driver = {
-	.probe = adx_wdt_probe,
-	.remove = __devexit_p(adx_wdt_remove),
-	.shutdown = adx_wdt_shutdown,
-	.driver = {
-		.name = WATCHDOG_NAME,
-		.owner = THIS_MODULE,
-		.pm = ADX_WDT_PM_OPS,
-	},
-};
-
-static int __init adx_wdt_init(void)
-{
-	return platform_driver_register(&adx_wdt_driver);
-}
-
-static void __exit adx_wdt_exit(void)
-{
-	platform_driver_unregister(&adx_wdt_driver);
-}
-
-module_init(adx_wdt_init);
-module_exit(adx_wdt_exit);
-
-MODULE_DESCRIPTION("Avionic Design Xanthos Watchdog Driver");
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Thierry Reding <thierry.reding@avionic-design.de>");
-MODULE_ALIAS_MISCDEV(WATCHDOG_MINOR);
diff --git a/drivers/watchdog/s3c2410_wdt.c b/drivers/watchdog/s3c2410_wdt.c
index 5de7e4f..a79e384 100644
--- a/drivers/watchdog/s3c2410_wdt.c
+++ b/drivers/watchdog/s3c2410_wdt.c
@@ -401,8 +401,8 @@ static int __devinit s3c2410wdt_probe(struct platform_device *pdev)
 
 	dev_info(dev, "watchdog %sactive, reset %sabled, irq %sabled\n",
 		 (wtcon & S3C2410_WTCON_ENABLE) ?  "" : "in",
-		 (wtcon & S3C2410_WTCON_RSTEN) ? "" : "dis",
-		 (wtcon & S3C2410_WTCON_INTEN) ? "" : "en");
+		 (wtcon & S3C2410_WTCON_RSTEN) ? "en" : "dis",
+		 (wtcon & S3C2410_WTCON_INTEN) ? "en" : "dis");
 
 	return 0;
 
diff --git a/drivers/watchdog/wm831x_wdt.c b/drivers/watchdog/wm831x_wdt.c
index 7be3855..e789a47 100644
--- a/drivers/watchdog/wm831x_wdt.c
+++ b/drivers/watchdog/wm831x_wdt.c
@@ -150,7 +150,7 @@ static int wm831x_wdt_set_timeout(struct watchdog_device *wdt_dev,
 		if (wm831x_wdt_cfgs[i].time == timeout)
 			break;
 	if (i == ARRAY_SIZE(wm831x_wdt_cfgs))
-		ret = -EINVAL;
+		return -EINVAL;
 
 	ret = wm831x_reg_unlock(wm831x);
 	if (ret == 0) {
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index a767884..31ab82f 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -501,7 +501,7 @@ EXPORT_SYMBOL_GPL(balloon_set_new_target);
  * alloc_xenballooned_pages - get pages that have been ballooned out
  * @nr_pages: Number of pages to get
  * @pages: pages returned
- * @highmem: highmem or lowmem pages
+ * @highmem: allow highmem pages
  * @return 0 on success, error otherwise
  */
 int alloc_xenballooned_pages(int nr_pages, struct page **pages, bool highmem)
@@ -511,7 +511,7 @@ int alloc_xenballooned_pages(int nr_pages, struct page **pages, bool highmem)
 	mutex_lock(&balloon_mutex);
 	while (pgno < nr_pages) {
 		page = balloon_retrieve(highmem);
-		if (page && PageHighMem(page) == highmem) {
+		if (page && (highmem || !PageHighMem(page))) {
 			pages[pgno++] = page;
 		} else {
 			enum bp_state st;
diff --git a/drivers/xen/gntalloc.c b/drivers/xen/gntalloc.c
index f6832f4..e1c4c6e 100644
--- a/drivers/xen/gntalloc.c
+++ b/drivers/xen/gntalloc.c
@@ -135,7 +135,7 @@ static int add_grefs(struct ioctl_gntalloc_alloc_gref *op,
 		/* Grant foreign access to the page. */
 		gref->gref_id = gnttab_grant_foreign_access(op->domid,
 			pfn_to_mfn(page_to_pfn(gref->page)), readonly);
-		if (gref->gref_id < 0) {
+		if ((int)gref->gref_id < 0) {
 			rc = gref->gref_id;
 			goto undo;
 		}
@@ -280,7 +280,7 @@ static long gntalloc_ioctl_alloc(struct gntalloc_file_private_data *priv,
 		goto out;
 	}
 
-	gref_ids = kzalloc(sizeof(gref_ids[0]) * op.count, GFP_TEMPORARY);
+	gref_ids = kcalloc(op.count, sizeof(gref_ids[0]), GFP_TEMPORARY);
 	if (!gref_ids) {
 		rc = -ENOMEM;
 		goto out;
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 3987132..afca14d 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -114,11 +114,11 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
 	if (NULL == add)
 		return NULL;
 
-	add->grants    = kzalloc(sizeof(add->grants[0])    * count, GFP_KERNEL);
-	add->map_ops   = kzalloc(sizeof(add->map_ops[0])   * count, GFP_KERNEL);
-	add->unmap_ops = kzalloc(sizeof(add->unmap_ops[0]) * count, GFP_KERNEL);
-	add->kmap_ops  = kzalloc(sizeof(add->kmap_ops[0])  * count, GFP_KERNEL);
-	add->pages     = kzalloc(sizeof(add->pages[0])     * count, GFP_KERNEL);
+	add->grants    = kcalloc(count, sizeof(add->grants[0]), GFP_KERNEL);
+	add->map_ops   = kcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL);
+	add->unmap_ops = kcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL);
+	add->kmap_ops  = kcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL);
+	add->pages     = kcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
 	if (NULL == add->grants    ||
 	    NULL == add->map_ops   ||
 	    NULL == add->unmap_ops ||
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 81c3ce6..1906125 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -35,6 +35,7 @@
 #include <linux/vmalloc.h>
 #include <linux/export.h>
 #include <asm/xen/hypervisor.h>
+#include <asm/xen/page.h>
 #include <xen/interface/xen.h>
 #include <xen/interface/event_channel.h>
 #include <xen/events.h>
@@ -436,19 +437,20 @@ EXPORT_SYMBOL_GPL(xenbus_free_evtchn);
 int xenbus_map_ring_valloc(struct xenbus_device *dev, int gnt_ref, void **vaddr)
 {
 	struct gnttab_map_grant_ref op = {
-		.flags = GNTMAP_host_map,
+		.flags = GNTMAP_host_map | GNTMAP_contains_pte,
 		.ref   = gnt_ref,
 		.dom   = dev->otherend_id,
 	};
 	struct vm_struct *area;
+	pte_t *pte;
 
 	*vaddr = NULL;
 
-	area = alloc_vm_area(PAGE_SIZE);
+	area = alloc_vm_area(PAGE_SIZE, &pte);
 	if (!area)
 		return -ENOMEM;
 
-	op.host_addr = (unsigned long)area->addr;
+	op.host_addr = arbitrary_virt_to_machine(pte).maddr;
 
 	if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, &op, 1))
 		BUG();
@@ -527,6 +529,7 @@ int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr)
 	struct gnttab_unmap_grant_ref op = {
 		.host_addr = (unsigned long)vaddr,
 	};
+	unsigned int level;
 
 	/* It'd be nice if linux/vmalloc.h provided a find_vm_area(void *addr)
 	 * method so that we don't have to muck with vmalloc internals here.
@@ -548,6 +551,8 @@ int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr)
 	}
 
 	op.handle = (grant_handle_t)area->phys_addr;
+	op.host_addr = arbitrary_virt_to_machine(
+		lookup_address((unsigned long)vaddr, &level)).maddr;
 
 	if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, &op, 1))
 		BUG();
diff --git a/fs/bio.c b/fs/bio.c
index 41c93c7..b1fe82c 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -337,7 +337,7 @@ static void bio_fs_destructor(struct bio *bio)
  *	RETURNS:
  *	Pointer to new bio on success, NULL on failure.
  */
-struct bio *bio_alloc(gfp_t gfp_mask, int nr_iovecs)
+struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 {
 	struct bio *bio = bio_alloc_bioset(gfp_mask, nr_iovecs, fs_bio_set);
 
@@ -365,7 +365,7 @@ static void bio_kmalloc_destructor(struct bio *bio)
  *   %__GFP_WAIT, the allocation is guaranteed to succeed.
  *
  **/
-struct bio *bio_kmalloc(gfp_t gfp_mask, int nr_iovecs)
+struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 {
 	struct bio *bio;
 
@@ -696,7 +696,8 @@ static void bio_free_map_data(struct bio_map_data *bmd)
 	kfree(bmd);
 }
 
-static struct bio_map_data *bio_alloc_map_data(int nr_segs, int iov_count,
+static struct bio_map_data *bio_alloc_map_data(int nr_segs,
+					       unsigned int iov_count,
 					       gfp_t gfp_mask)
 {
 	struct bio_map_data *bmd;
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 8855aad..22c64ff 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -683,7 +683,7 @@ static int inode_to_path(u64 inum, struct btrfs_inode_ref *iref,
 		return PTR_ERR(fspath);
 
 	if (fspath > fspath_min) {
-		ipath->fspath->val[i] = (u64)fspath;
+		ipath->fspath->val[i] = (u64)(unsigned long)fspath;
 		++ipath->fspath->elem_cnt;
 		ipath->fspath->bytes_left = fspath - fspath_min;
 	} else {
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 0fe615e..dede441 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -514,10 +514,25 @@ static inline int should_cow_block(struct btrfs_trans_handle *trans,
 				   struct btrfs_root *root,
 				   struct extent_buffer *buf)
 {
+	/* ensure we can see the force_cow */
+	smp_rmb();
+
+	/*
+	 * We do not need to cow a block if
+	 * 1) this block is not created or changed in this transaction;
+	 * 2) this block does not belong to TREE_RELOC tree;
+	 * 3) the root is not forced COW.
+	 *
+	 * What is forced COW:
+	 *    when we create snapshot during commiting the transaction,
+	 *    after we've finished coping src root, we must COW the shared
+	 *    block to ensure the metadata consistency.
+	 */
 	if (btrfs_header_generation(buf) == trans->transid &&
 	    !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN) &&
 	    !(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID &&
-	      btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
+	      btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)) &&
+	    !root->force_cow)
 		return 0;
 	return 1;
 }
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index b9ba59f..50634abe 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -848,7 +848,8 @@ struct btrfs_free_cluster {
 enum btrfs_caching_type {
 	BTRFS_CACHE_NO		= 0,
 	BTRFS_CACHE_STARTED	= 1,
-	BTRFS_CACHE_FINISHED	= 2,
+	BTRFS_CACHE_FAST	= 2,
+	BTRFS_CACHE_FINISHED	= 3,
 };
 
 enum btrfs_disk_cache_state {
@@ -1271,6 +1272,8 @@ struct btrfs_root {
 	 * for stat.  It may be used for more later
 	 */
 	dev_t anon_dev;
+
+	int force_cow;
 };
 
 struct btrfs_ioctl_defrag_range_args {
@@ -2366,6 +2369,9 @@ int btrfs_block_rsv_check(struct btrfs_root *root,
 int btrfs_block_rsv_refill(struct btrfs_root *root,
 			  struct btrfs_block_rsv *block_rsv,
 			  u64 min_reserved);
+int btrfs_block_rsv_refill_noflush(struct btrfs_root *root,
+				   struct btrfs_block_rsv *block_rsv,
+				   u64 min_reserved);
 int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
 			    struct btrfs_block_rsv *dst_rsv,
 			    u64 num_bytes);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 62afe5c..632f8f3 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -620,7 +620,7 @@ out:
 
 static int btree_io_failed_hook(struct bio *failed_bio,
 			 struct page *page, u64 start, u64 end,
-			 u64 mirror_num, struct extent_state *state)
+			 int mirror_num, struct extent_state *state)
 {
 	struct extent_io_tree *tree;
 	unsigned long len;
@@ -2573,22 +2573,10 @@ static int write_dev_supers(struct btrfs_device *device,
 	int errors = 0;
 	u32 crc;
 	u64 bytenr;
-	int last_barrier = 0;
 
 	if (max_mirrors == 0)
 		max_mirrors = BTRFS_SUPER_MIRROR_MAX;
 
-	/* make sure only the last submit_bh does a barrier */
-	if (do_barriers) {
-		for (i = 0; i < max_mirrors; i++) {
-			bytenr = btrfs_sb_offset(i);
-			if (bytenr + BTRFS_SUPER_INFO_SIZE >=
-			    device->total_bytes)
-				break;
-			last_barrier = i;
-		}
-	}
-
 	for (i = 0; i < max_mirrors; i++) {
 		bytenr = btrfs_sb_offset(i);
 		if (bytenr + BTRFS_SUPER_INFO_SIZE >= device->total_bytes)
@@ -2634,17 +2622,136 @@ static int write_dev_supers(struct btrfs_device *device,
 			bh->b_end_io = btrfs_end_buffer_write_sync;
 		}
 
-		if (i == last_barrier && do_barriers)
-			ret = submit_bh(WRITE_FLUSH_FUA, bh);
-		else
-			ret = submit_bh(WRITE_SYNC, bh);
-
+		/*
+		 * we fua the first super.  The others we allow
+		 * to go down lazy.
+		 */
+		ret = submit_bh(WRITE_FUA, bh);
 		if (ret)
 			errors++;
 	}
 	return errors < i ? 0 : -1;
 }
 
+/*
+ * endio for the write_dev_flush, this will wake anyone waiting
+ * for the barrier when it is done
+ */
+static void btrfs_end_empty_barrier(struct bio *bio, int err)
+{
+	if (err) {
+		if (err == -EOPNOTSUPP)
+			set_bit(BIO_EOPNOTSUPP, &bio->bi_flags);
+		clear_bit(BIO_UPTODATE, &bio->bi_flags);
+	}
+	if (bio->bi_private)
+		complete(bio->bi_private);
+	bio_put(bio);
+}
+
+/*
+ * trigger flushes for one the devices.  If you pass wait == 0, the flushes are
+ * sent down.  With wait == 1, it waits for the previous flush.
+ *
+ * any device where the flush fails with eopnotsupp are flagged as not-barrier
+ * capable
+ */
+static int write_dev_flush(struct btrfs_device *device, int wait)
+{
+	struct bio *bio;
+	int ret = 0;
+
+	if (device->nobarriers)
+		return 0;
+
+	if (wait) {
+		bio = device->flush_bio;
+		if (!bio)
+			return 0;
+
+		wait_for_completion(&device->flush_wait);
+
+		if (bio_flagged(bio, BIO_EOPNOTSUPP)) {
+			printk("btrfs: disabling barriers on dev %s\n",
+			       device->name);
+			device->nobarriers = 1;
+		}
+		if (!bio_flagged(bio, BIO_UPTODATE)) {
+			ret = -EIO;
+		}
+
+		/* drop the reference from the wait == 0 run */
+		bio_put(bio);
+		device->flush_bio = NULL;
+
+		return ret;
+	}
+
+	/*
+	 * one reference for us, and we leave it for the
+	 * caller
+	 */
+	device->flush_bio = NULL;;
+	bio = bio_alloc(GFP_NOFS, 0);
+	if (!bio)
+		return -ENOMEM;
+
+	bio->bi_end_io = btrfs_end_empty_barrier;
+	bio->bi_bdev = device->bdev;
+	init_completion(&device->flush_wait);
+	bio->bi_private = &device->flush_wait;
+	device->flush_bio = bio;
+
+	bio_get(bio);
+	submit_bio(WRITE_FLUSH, bio);
+
+	return 0;
+}
+
+/*
+ * send an empty flush down to each device in parallel,
+ * then wait for them
+ */
+static int barrier_all_devices(struct btrfs_fs_info *info)
+{
+	struct list_head *head;
+	struct btrfs_device *dev;
+	int errors = 0;
+	int ret;
+
+	/* send down all the barriers */
+	head = &info->fs_devices->devices;
+	list_for_each_entry_rcu(dev, head, dev_list) {
+		if (!dev->bdev) {
+			errors++;
+			continue;
+		}
+		if (!dev->in_fs_metadata || !dev->writeable)
+			continue;
+
+		ret = write_dev_flush(dev, 0);
+		if (ret)
+			errors++;
+	}
+
+	/* wait for all the barriers */
+	list_for_each_entry_rcu(dev, head, dev_list) {
+		if (!dev->bdev) {
+			errors++;
+			continue;
+		}
+		if (!dev->in_fs_metadata || !dev->writeable)
+			continue;
+
+		ret = write_dev_flush(dev, 1);
+		if (ret)
+			errors++;
+	}
+	if (errors)
+		return -EIO;
+	return 0;
+}
+
 int write_all_supers(struct btrfs_root *root, int max_mirrors)
 {
 	struct list_head *head;
@@ -2666,6 +2773,10 @@ int write_all_supers(struct btrfs_root *root, int max_mirrors)
 
 	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
 	head = &root->fs_info->fs_devices->devices;
+
+	if (do_barriers)
+		barrier_all_devices(root->fs_info);
+
 	list_for_each_entry_rcu(dev, head, dev_list) {
 		if (!dev->bdev) {
 			total_errors++;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index b232150..f0d5718 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -467,13 +467,59 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 			     struct btrfs_root *root,
 			     int load_cache_only)
 {
+	DEFINE_WAIT(wait);
 	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_caching_control *caching_ctl;
 	int ret = 0;
 
-	smp_mb();
-	if (cache->cached != BTRFS_CACHE_NO)
+	caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS);
+	BUG_ON(!caching_ctl);
+
+	INIT_LIST_HEAD(&caching_ctl->list);
+	mutex_init(&caching_ctl->mutex);
+	init_waitqueue_head(&caching_ctl->wait);
+	caching_ctl->block_group = cache;
+	caching_ctl->progress = cache->key.objectid;
+	atomic_set(&caching_ctl->count, 1);
+	caching_ctl->work.func = caching_thread;
+
+	spin_lock(&cache->lock);
+	/*
+	 * This should be a rare occasion, but this could happen I think in the
+	 * case where one thread starts to load the space cache info, and then
+	 * some other thread starts a transaction commit which tries to do an
+	 * allocation while the other thread is still loading the space cache
+	 * info.  The previous loop should have kept us from choosing this block
+	 * group, but if we've moved to the state where we will wait on caching
+	 * block groups we need to first check if we're doing a fast load here,
+	 * so we can wait for it to finish, otherwise we could end up allocating
+	 * from a block group who's cache gets evicted for one reason or
+	 * another.
+	 */
+	while (cache->cached == BTRFS_CACHE_FAST) {
+		struct btrfs_caching_control *ctl;
+
+		ctl = cache->caching_ctl;
+		atomic_inc(&ctl->count);
+		prepare_to_wait(&ctl->wait, &wait, TASK_UNINTERRUPTIBLE);
+		spin_unlock(&cache->lock);
+
+		schedule();
+
+		finish_wait(&ctl->wait, &wait);
+		put_caching_control(ctl);
+		spin_lock(&cache->lock);
+	}
+
+	if (cache->cached != BTRFS_CACHE_NO) {
+		spin_unlock(&cache->lock);
+		kfree(caching_ctl);
 		return 0;
+	}
+	WARN_ON(cache->caching_ctl);
+	cache->caching_ctl = caching_ctl;
+	cache->cached = BTRFS_CACHE_FAST;
+	spin_unlock(&cache->lock);
 
 	/*
 	 * We can't do the read from on-disk cache during a commit since we need
@@ -484,56 +530,51 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 	if (trans && (!trans->transaction->in_commit) &&
 	    (root && root != root->fs_info->tree_root) &&
 	    btrfs_test_opt(root, SPACE_CACHE)) {
-		spin_lock(&cache->lock);
-		if (cache->cached != BTRFS_CACHE_NO) {
-			spin_unlock(&cache->lock);
-			return 0;
-		}
-		cache->cached = BTRFS_CACHE_STARTED;
-		spin_unlock(&cache->lock);
-
 		ret = load_free_space_cache(fs_info, cache);
 
 		spin_lock(&cache->lock);
 		if (ret == 1) {
+			cache->caching_ctl = NULL;
 			cache->cached = BTRFS_CACHE_FINISHED;
 			cache->last_byte_to_unpin = (u64)-1;
 		} else {
-			cache->cached = BTRFS_CACHE_NO;
+			if (load_cache_only) {
+				cache->caching_ctl = NULL;
+				cache->cached = BTRFS_CACHE_NO;
+			} else {
+				cache->cached = BTRFS_CACHE_STARTED;
+			}
 		}
 		spin_unlock(&cache->lock);
+		wake_up(&caching_ctl->wait);
 		if (ret == 1) {
+			put_caching_control(caching_ctl);
 			free_excluded_extents(fs_info->extent_root, cache);
 			return 0;
 		}
+	} else {
+		/*
+		 * We are not going to do the fast caching, set cached to the
+		 * appropriate value and wakeup any waiters.
+		 */
+		spin_lock(&cache->lock);
+		if (load_cache_only) {
+			cache->caching_ctl = NULL;
+			cache->cached = BTRFS_CACHE_NO;
+		} else {
+			cache->cached = BTRFS_CACHE_STARTED;
+		}
+		spin_unlock(&cache->lock);
+		wake_up(&caching_ctl->wait);
 	}
 
-	if (load_cache_only)
-		return 0;
-
-	caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS);
-	BUG_ON(!caching_ctl);
-
-	INIT_LIST_HEAD(&caching_ctl->list);
-	mutex_init(&caching_ctl->mutex);
-	init_waitqueue_head(&caching_ctl->wait);
-	caching_ctl->block_group = cache;
-	caching_ctl->progress = cache->key.objectid;
-	/* one for caching kthread, one for caching block group list */
-	atomic_set(&caching_ctl->count, 2);
-	caching_ctl->work.func = caching_thread;
-
-	spin_lock(&cache->lock);
-	if (cache->cached != BTRFS_CACHE_NO) {
-		spin_unlock(&cache->lock);
-		kfree(caching_ctl);
+	if (load_cache_only) {
+		put_caching_control(caching_ctl);
 		return 0;
 	}
-	cache->caching_ctl = caching_ctl;
-	cache->cached = BTRFS_CACHE_STARTED;
-	spin_unlock(&cache->lock);
 
 	down_write(&fs_info->extent_commit_sem);
+	atomic_inc(&caching_ctl->count);
 	list_add_tail(&caching_ctl->list, &fs_info->caching_block_groups);
 	up_write(&fs_info->extent_commit_sem);
 
@@ -3847,9 +3888,9 @@ int btrfs_block_rsv_check(struct btrfs_root *root,
 	return ret;
 }
 
-int btrfs_block_rsv_refill(struct btrfs_root *root,
-			  struct btrfs_block_rsv *block_rsv,
-			  u64 min_reserved)
+static inline int __btrfs_block_rsv_refill(struct btrfs_root *root,
+					   struct btrfs_block_rsv *block_rsv,
+					   u64 min_reserved, int flush)
 {
 	u64 num_bytes = 0;
 	int ret = -ENOSPC;
@@ -3868,7 +3909,7 @@ int btrfs_block_rsv_refill(struct btrfs_root *root,
 	if (!ret)
 		return 0;
 
-	ret = reserve_metadata_bytes(root, block_rsv, num_bytes, 1);
+	ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
 	if (!ret) {
 		block_rsv_add_bytes(block_rsv, num_bytes, 0);
 		return 0;
@@ -3877,6 +3918,20 @@ int btrfs_block_rsv_refill(struct btrfs_root *root,
 	return ret;
 }
 
+int btrfs_block_rsv_refill(struct btrfs_root *root,
+			   struct btrfs_block_rsv *block_rsv,
+			   u64 min_reserved)
+{
+	return __btrfs_block_rsv_refill(root, block_rsv, min_reserved, 1);
+}
+
+int btrfs_block_rsv_refill_noflush(struct btrfs_root *root,
+				   struct btrfs_block_rsv *block_rsv,
+				   u64 min_reserved)
+{
+	return __btrfs_block_rsv_refill(root, block_rsv, min_reserved, 0);
+}
+
 int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
 			    struct btrfs_block_rsv *dst_rsv,
 			    u64 num_bytes)
@@ -5178,13 +5233,15 @@ search:
 		}
 
 have_block_group:
-		if (unlikely(block_group->cached == BTRFS_CACHE_NO)) {
+		cached = block_group_cache_done(block_group);
+		if (unlikely(!cached)) {
 			u64 free_percent;
 
+			found_uncached_bg = true;
 			ret = cache_block_group(block_group, trans,
 						orig_root, 1);
 			if (block_group->cached == BTRFS_CACHE_FINISHED)
-				goto have_block_group;
+				goto alloc;
 
 			free_percent = btrfs_block_group_used(&block_group->item);
 			free_percent *= 100;
@@ -5206,7 +5263,6 @@ have_block_group:
 							orig_root, 0);
 				BUG_ON(ret);
 			}
-			found_uncached_bg = true;
 
 			/*
 			 * If loop is set for cached only, try the next block
@@ -5216,17 +5272,14 @@ have_block_group:
 				goto loop;
 		}
 
-		cached = block_group_cache_done(block_group);
-		if (unlikely(!cached))
-			found_uncached_bg = true;
-
+alloc:
 		if (unlikely(block_group->ro))
 			goto loop;
 
 		spin_lock(&block_group->free_space_ctl->tree_lock);
 		if (cached &&
 		    block_group->free_space_ctl->free_space <
-		    num_bytes + empty_size) {
+		    num_bytes + empty_cluster + empty_size) {
 			spin_unlock(&block_group->free_space_ctl->tree_lock);
 			goto loop;
 		}
@@ -5247,12 +5300,10 @@ have_block_group:
 			 * people trying to start a new cluster
 			 */
 			spin_lock(&last_ptr->refill_lock);
-			if (last_ptr->block_group &&
-			    (last_ptr->block_group->ro ||
-			    !block_group_bits(last_ptr->block_group, data))) {
-				offset = 0;
+			if (!last_ptr->block_group ||
+			    last_ptr->block_group->ro ||
+			    !block_group_bits(last_ptr->block_group, data))
 				goto refill_cluster;
-			}
 
 			offset = btrfs_alloc_from_cluster(block_group, last_ptr,
 						 num_bytes, search_start);
@@ -5303,7 +5354,7 @@ refill_cluster:
 			/* allocate a cluster in this block group */
 			ret = btrfs_find_space_cluster(trans, root,
 					       block_group, last_ptr,
-					       offset, num_bytes,
+					       search_start, num_bytes,
 					       empty_cluster + empty_size);
 			if (ret == 0) {
 				/*
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 1f87c4d..be1bf62 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2285,16 +2285,22 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 				clean_io_failure(start, page);
 		}
 		if (!uptodate) {
-			u64 failed_mirror;
-			failed_mirror = (u64)bio->bi_bdev;
-			if (tree->ops && tree->ops->readpage_io_failed_hook)
-				ret = tree->ops->readpage_io_failed_hook(
-						bio, page, start, end,
-						failed_mirror, state);
-			else
-				ret = bio_readpage_error(bio, page, start, end,
-							 failed_mirror, NULL);
+			int failed_mirror;
+			failed_mirror = (int)(unsigned long)bio->bi_bdev;
+			/*
+			 * The generic bio_readpage_error handles errors the
+			 * following way: If possible, new read requests are
+			 * created and submitted and will end up in
+			 * end_bio_extent_readpage as well (if we're lucky, not
+			 * in the !uptodate case). In that case it returns 0 and
+			 * we just go on with the next page in our bio. If it
+			 * can't handle the error it will return -EIO and we
+			 * remain responsible for that page.
+			 */
+			ret = bio_readpage_error(bio, page, start, end,
+							failed_mirror, NULL);
 			if (ret == 0) {
+error_handled:
 				uptodate =
 					test_bit(BIO_UPTODATE, &bio->bi_flags);
 				if (err)
@@ -2302,6 +2308,13 @@ static void end_bio_extent_readpage(struct bio *bio, int err)
 				uncache_state(&cached);
 				continue;
 			}
+			if (tree->ops && tree->ops->readpage_io_failed_hook) {
+				ret = tree->ops->readpage_io_failed_hook(
+							bio, page, start, end,
+							failed_mirror, state);
+				if (ret == 0)
+					goto error_handled;
+			}
 		}
 
 		if (uptodate) {
@@ -3366,6 +3379,9 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		return -ENOMEM;
 	path->leave_spinning = 1;
 
+	start = ALIGN(start, BTRFS_I(inode)->root->sectorsize);
+	len = ALIGN(len, BTRFS_I(inode)->root->sectorsize);
+
 	/*
 	 * lookup the last file extent.  We're not using i_size here
 	 * because there might be preallocation past i_size
@@ -3413,7 +3429,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, start, start + len, 0,
 			 &cached_state, GFP_NOFS);
 
-	em = get_extent_skip_holes(inode, off, last_for_get_extent,
+	em = get_extent_skip_holes(inode, start, last_for_get_extent,
 				   get_extent);
 	if (!em)
 		goto out;
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index feb9be0..7604c30 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -70,7 +70,7 @@ struct extent_io_ops {
 			      unsigned long bio_flags);
 	int (*readpage_io_hook)(struct page *page, u64 start, u64 end);
 	int (*readpage_io_failed_hook)(struct bio *bio, struct page *page,
-				       u64 start, u64 end, u64 failed_mirror,
+				       u64 start, u64 end, int failed_mirror,
 				       struct extent_state *state);
 	int (*writepage_io_failed_hook)(struct bio *bio, struct page *page,
 					u64 start, u64 end,
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 181760f..ec23d43 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -351,6 +351,11 @@ static int io_ctl_prepare_pages(struct io_ctl *io_ctl, struct inode *inode,
 		}
 	}
 
+	for (i = 0; i < io_ctl->num_pages; i++) {
+		clear_page_dirty_for_io(io_ctl->pages[i]);
+		set_page_extent_mapped(io_ctl->pages[i]);
+	}
+
 	return 0;
 }
 
@@ -1465,6 +1470,7 @@ static void add_new_bitmap(struct btrfs_free_space_ctl *ctl,
 {
 	info->offset = offset_to_bitmap(ctl, offset);
 	info->bytes = 0;
+	INIT_LIST_HEAD(&info->list);
 	link_free_space(ctl, info);
 	ctl->total_bitmaps++;
 
@@ -1844,7 +1850,13 @@ again:
 		info = tree_search_offset(ctl, offset_to_bitmap(ctl, offset),
 					  1, 0);
 		if (!info) {
-			WARN_ON(1);
+			/* the tree logging code might be calling us before we
+			 * have fully loaded the free space rbtree for this
+			 * block group.  So it is possible the entry won't
+			 * be in the rbtree yet at all.  The caching code
+			 * will make sure not to put it in the rbtree if
+			 * the logging code has pinned it.
+			 */
 			goto out_lock;
 		}
 	}
@@ -2308,6 +2320,7 @@ again:
 
 	if (!found) {
 		start = i;
+		cluster->max_size = 0;
 		found = true;
 	}
 
@@ -2451,16 +2464,23 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct btrfs_free_space *entry;
-	struct rb_node *node;
 	int ret = -ENOSPC;
+	u64 bitmap_offset = offset_to_bitmap(ctl, offset);
 
 	if (ctl->total_bitmaps == 0)
 		return -ENOSPC;
 
 	/*
-	 * First check our cached list of bitmaps and see if there is an entry
-	 * here that will work.
+	 * The bitmap that covers offset won't be in the list unless offset
+	 * is just its start offset.
 	 */
+	entry = list_first_entry(bitmaps, struct btrfs_free_space, list);
+	if (entry->offset != bitmap_offset) {
+		entry = tree_search_offset(ctl, bitmap_offset, 1, 0);
+		if (entry && list_empty(&entry->list))
+			list_add(&entry->list, bitmaps);
+	}
+
 	list_for_each_entry(entry, bitmaps, list) {
 		if (entry->bytes < min_bytes)
 			continue;
@@ -2471,38 +2491,10 @@ setup_cluster_bitmap(struct btrfs_block_group_cache *block_group,
 	}
 
 	/*
-	 * If we do have entries on our list and we are here then we didn't find
-	 * anything, so go ahead and get the next entry after the last entry in
-	 * this list and start the search from there.
+	 * The bitmaps list has all the bitmaps that record free space
+	 * starting after offset, so no more search is required.
 	 */
-	if (!list_empty(bitmaps)) {
-		entry = list_entry(bitmaps->prev, struct btrfs_free_space,
-				   list);
-		node = rb_next(&entry->offset_index);
-		if (!node)
-			return -ENOSPC;
-		entry = rb_entry(node, struct btrfs_free_space, offset_index);
-		goto search;
-	}
-
-	entry = tree_search_offset(ctl, offset_to_bitmap(ctl, offset), 0, 1);
-	if (!entry)
-		return -ENOSPC;
-
-search:
-	node = &entry->offset_index;
-	do {
-		entry = rb_entry(node, struct btrfs_free_space, offset_index);
-		node = rb_next(&entry->offset_index);
-		if (!entry->bitmap)
-			continue;
-		if (entry->bytes < min_bytes)
-			continue;
-		ret = btrfs_bitmap_cluster(block_group, entry, cluster, offset,
-					   bytes, min_bytes);
-	} while (ret && node);
-
-	return ret;
+	return -ENOSPC;
 }
 
 /*
@@ -2520,8 +2512,8 @@ int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
 			     u64 offset, u64 bytes, u64 empty_size)
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
-	struct list_head bitmaps;
 	struct btrfs_free_space *entry, *tmp;
+	LIST_HEAD(bitmaps);
 	u64 min_bytes;
 	int ret;
 
@@ -2560,7 +2552,6 @@ int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	INIT_LIST_HEAD(&bitmaps);
 	ret = setup_cluster_no_bitmap(block_group, cluster, &bitmaps, offset,
 				      bytes, min_bytes);
 	if (ret)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 116ab67..2c984f7 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3490,7 +3490,7 @@ void btrfs_evict_inode(struct inode *inode)
 	 * doing the truncate.
 	 */
 	while (1) {
-		ret = btrfs_block_rsv_refill(root, rsv, min_size);
+		ret = btrfs_block_rsv_refill_noflush(root, rsv, min_size);
 
 		/*
 		 * Try and steal from the global reserve since we will
@@ -6794,11 +6794,13 @@ static int btrfs_getattr(struct vfsmount *mnt,
 			 struct dentry *dentry, struct kstat *stat)
 {
 	struct inode *inode = dentry->d_inode;
+	u32 blocksize = inode->i_sb->s_blocksize;
+
 	generic_fillattr(inode, stat);
 	stat->dev = BTRFS_I(inode)->root->anon_dev;
 	stat->blksize = PAGE_CACHE_SIZE;
-	stat->blocks = (inode_get_bytes(inode) +
-			BTRFS_I(inode)->delalloc_bytes) >> 9;
+	stat->blocks = (ALIGN(inode_get_bytes(inode), blocksize) +
+		ALIGN(BTRFS_I(inode)->delalloc_bytes, blocksize)) >> 9;
 	return 0;
 }
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 4a34c47..72d4616 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1216,12 +1216,12 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
 		*devstr = '\0';
 		devstr = vol_args->name;
 		devid = simple_strtoull(devstr, &end, 10);
-		printk(KERN_INFO "resizing devid %llu\n",
+		printk(KERN_INFO "btrfs: resizing devid %llu\n",
 		       (unsigned long long)devid);
 	}
 	device = btrfs_find_device(root, devid, NULL, NULL);
 	if (!device) {
-		printk(KERN_INFO "resizer unable to find device %llu\n",
+		printk(KERN_INFO "btrfs: resizer unable to find device %llu\n",
 		       (unsigned long long)devid);
 		ret = -EINVAL;
 		goto out_unlock;
@@ -1267,7 +1267,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
 	do_div(new_size, root->sectorsize);
 	new_size *= root->sectorsize;
 
-	printk(KERN_INFO "new size for %s is %llu\n",
+	printk(KERN_INFO "btrfs: new size for %s is %llu\n",
 		device->name, (unsigned long long)new_size);
 
 	if (new_size > old_size) {
@@ -1278,7 +1278,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root,
 		}
 		ret = btrfs_grow_device(trans, device, new_size);
 		btrfs_commit_transaction(trans, root);
-	} else {
+	} else if (new_size < old_size) {
 		ret = btrfs_shrink_device(device, new_size);
 	}
 
@@ -2930,11 +2930,13 @@ static long btrfs_ioctl_ino_to_path(struct btrfs_root *root, void __user *arg)
 		goto out;
 
 	for (i = 0; i < ipath->fspath->elem_cnt; ++i) {
-		rel_ptr = ipath->fspath->val[i] - (u64)ipath->fspath->val;
+		rel_ptr = ipath->fspath->val[i] -
+			  (u64)(unsigned long)ipath->fspath->val;
 		ipath->fspath->val[i] = rel_ptr;
 	}
 
-	ret = copy_to_user((void *)ipa->fspath, (void *)ipath->fspath, size);
+	ret = copy_to_user((void *)(unsigned long)ipa->fspath,
+			   (void *)(unsigned long)ipath->fspath, size);
 	if (ret) {
 		ret = -EFAULT;
 		goto out;
@@ -3017,7 +3019,8 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root,
 	if (ret < 0)
 		goto out;
 
-	ret = copy_to_user((void *)loi->inodes, (void *)inodes, size);
+	ret = copy_to_user((void *)(unsigned long)loi->inodes,
+			   (void *)(unsigned long)inodes, size);
 	if (ret)
 		ret = -EFAULT;
 
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index f4190f2..c27bcb6 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -256,6 +256,11 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, void *ctx)
 	btrfs_release_path(swarn->path);
 
 	ipath = init_ipath(4096, local_root, swarn->path);
+	if (IS_ERR(ipath)) {
+		ret = PTR_ERR(ipath);
+		ipath = NULL;
+		goto err;
+	}
 	ret = paths_from_inode(inum, ipath);
 
 	if (ret < 0)
@@ -272,7 +277,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root, void *ctx)
 			swarn->logical, swarn->dev->name,
 			(unsigned long long)swarn->sector, root, inum, offset,
 			min(isize - offset, (u64)PAGE_SIZE), nlink,
-			(char *)ipath->fspath->val[i]);
+			(char *)(unsigned long)ipath->fspath->val[i]);
 
 	free_ipath(ipath);
 	return 0;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 8bd9d6d..e28ad4b 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -825,13 +825,9 @@ static char *setup_root_args(char *args)
 static struct dentry *mount_subvol(const char *subvol_name, int flags,
 				   const char *device_name, char *data)
 {
-	struct super_block *s;
 	struct dentry *root;
 	struct vfsmount *mnt;
-	struct mnt_namespace *ns_private;
 	char *newargs;
-	struct path path;
-	int error;
 
 	newargs = setup_root_args(data);
 	if (!newargs)
@@ -842,39 +838,17 @@ static struct dentry *mount_subvol(const char *subvol_name, int flags,
 	if (IS_ERR(mnt))
 		return ERR_CAST(mnt);
 
-	ns_private = create_mnt_ns(mnt);
-	if (IS_ERR(ns_private)) {
-		mntput(mnt);
-		return ERR_CAST(ns_private);
-	}
+	root = mount_subtree(mnt, subvol_name);
 
-	/*
-	 * This will trigger the automount of the subvol so we can just
-	 * drop the mnt we have here and return the dentry that we
-	 * found.
-	 */
-	error = vfs_path_lookup(mnt->mnt_root, mnt, subvol_name,
-				LOOKUP_FOLLOW, &path);
-	put_mnt_ns(ns_private);
-	if (error)
-		return ERR_PTR(error);
-
-	if (!is_subvolume_inode(path.dentry->d_inode)) {
-		path_put(&path);
-		mntput(mnt);
-		error = -EINVAL;
+	if (!IS_ERR(root) && !is_subvolume_inode(root->d_inode)) {
+		struct super_block *s = root->d_sb;
+		dput(root);
+		root = ERR_PTR(-EINVAL);
+		deactivate_locked_super(s);
 		printk(KERN_ERR "btrfs: '%s' is not a valid subvolume\n",
 				subvol_name);
-		return ERR_PTR(-EINVAL);
 	}
 
-	/* Get a ref to the sb and the dentry we found and return it */
-	s = path.mnt->mnt_sb;
-	atomic_inc(&s->s_active);
-	root = dget(path.dentry);
-	path_put(&path);
-	down_write(&s->s_umount);
-
 	return root;
 }
 
@@ -1083,7 +1057,7 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 	int i = 0, nr_devices;
 	int ret;
 
-	nr_devices = fs_info->fs_devices->rw_devices;
+	nr_devices = fs_info->fs_devices->open_devices;
 	BUG_ON(!nr_devices);
 
 	devices_info = kmalloc(sizeof(*devices_info) * nr_devices,
@@ -1105,8 +1079,8 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
 	else
 		min_stripe_size = BTRFS_STRIPE_LEN;
 
-	list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
-		if (!device->in_fs_metadata)
+	list_for_each_entry(device, &fs_devices->devices, dev_list) {
+		if (!device->in_fs_metadata || !device->bdev)
 			continue;
 
 		avail_space = device->total_bytes - device->bytes_used;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 6a0574e..81376d9 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -785,6 +785,10 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans,
 
 			btrfs_save_ino_cache(root, trans);
 
+			/* see comments in should_cow_block() */
+			root->force_cow = 0;
+			smp_wmb();
+
 			if (root->commit_root != root->node) {
 				mutex_lock(&root->fs_commit_mutex);
 				switch_commit_root(root);
@@ -947,6 +951,10 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	btrfs_tree_unlock(old);
 	free_extent_buffer(old);
 
+	/* see comments in should_cow_block() */
+	root->force_cow = 1;
+	smp_wmb();
+
 	btrfs_set_root_node(new_root_item, tmp);
 	/* record when the snapshot was created in key.offset */
 	key.offset = trans->transid;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index ab5b1c4..78f2d4d 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -100,6 +100,12 @@ struct btrfs_device {
 	struct reada_zone *reada_curr_zone;
 	struct radix_tree_root reada_zones;
 	struct radix_tree_root reada_extents;
+
+	/* for sending down flush barriers */
+	struct bio *flush_bio;
+	struct completion flush_wait;
+	int nobarriers;
+
 };
 
 struct btrfs_fs_devices {
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 2abd0df..bca3948 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -1143,7 +1143,7 @@ static void ceph_d_prune(struct dentry *dentry)
 {
 	struct ceph_dentry_info *di;
 
-	dout("d_release %p\n", dentry);
+	dout("ceph_d_prune %p\n", dentry);
 
 	/* do we have a valid parent? */
 	if (!dentry->d_parent || IS_ROOT(dentry))
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index e392bfc..116f365 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -1328,12 +1328,13 @@ int ceph_inode_set_size(struct inode *inode, loff_t size)
  */
 void ceph_queue_writeback(struct inode *inode)
 {
+	ihold(inode);
 	if (queue_work(ceph_inode_to_client(inode)->wb_wq,
 		       &ceph_inode(inode)->i_wb_work)) {
 		dout("ceph_queue_writeback %p\n", inode);
-		ihold(inode);
 	} else {
 		dout("ceph_queue_writeback %p failed\n", inode);
+		iput(inode);
 	}
 }
 
@@ -1353,12 +1354,13 @@ static void ceph_writeback_work(struct work_struct *work)
  */
 void ceph_queue_invalidate(struct inode *inode)
 {
+	ihold(inode);
 	if (queue_work(ceph_inode_to_client(inode)->pg_inv_wq,
 		       &ceph_inode(inode)->i_pg_inv_work)) {
 		dout("ceph_queue_invalidate %p\n", inode);
-		ihold(inode);
 	} else {
 		dout("ceph_queue_invalidate %p failed\n", inode);
+		iput(inode);
 	}
 }
 
@@ -1434,13 +1436,14 @@ void ceph_queue_vmtruncate(struct inode *inode)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
 
+	ihold(inode);
 	if (queue_work(ceph_sb_to_client(inode->i_sb)->trunc_wq,
 		       &ci->i_vmtruncate_work)) {
 		dout("ceph_queue_vmtruncate %p\n", inode);
-		ihold(inode);
 	} else {
 		dout("ceph_queue_vmtruncate %p failed, pending=%d\n",
 		     inode, ci->i_truncate_pending);
+		iput(inode);
 	}
 }
 
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index a90846f..8dc73a5 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -638,10 +638,12 @@ static struct dentry *open_root_dentry(struct ceph_fs_client *fsc,
 	if (err == 0) {
 		dout("open_root_inode success\n");
 		if (ceph_ino(req->r_target_inode) == CEPH_INO_ROOT &&
-		    fsc->sb->s_root == NULL)
+		    fsc->sb->s_root == NULL) {
 			root = d_alloc_root(req->r_target_inode);
-		else
+			ceph_init_dentry(root);
+		} else {
 			root = d_obtain_alias(req->r_target_inode);
+		}
 		req->r_target_inode = NULL;
 		dout("open_root_inode success, root dentry is %p\n", root);
 	} else {
diff --git a/fs/dcache.c b/fs/dcache.c
index a901c69..10ba92d 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -36,6 +36,7 @@
 #include <linux/bit_spinlock.h>
 #include <linux/rculist_bl.h>
 #include <linux/prefetch.h>
+#include <linux/ratelimit.h>
 #include "internal.h"
 
 /*
@@ -2383,8 +2384,16 @@ struct dentry *d_materialise_unique(struct dentry *dentry, struct inode *inode)
 				actual = __d_unalias(inode, dentry, alias);
 			}
 			write_sequnlock(&rename_lock);
-			if (IS_ERR(actual))
+			if (IS_ERR(actual)) {
+				if (PTR_ERR(actual) == -ELOOP)
+					pr_warn_ratelimited(
+						"VFS: Lookup of '%s' in %s %s"
+						" would have caused loop\n",
+						dentry->d_name.name,
+						inode->i_sb->s_type->name,
+						inode->i_sb->s_id);
 				dput(alias);
+			}
 			goto out_nolock;
 		}
 	}
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 990626e..0b3109e 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -281,7 +281,7 @@ static int nodeid_to_addr(int nodeid, struct sockaddr *retaddr)
 	} else {
 		struct sockaddr_in6 *in6  = (struct sockaddr_in6 *) &addr;
 		struct sockaddr_in6 *ret6 = (struct sockaddr_in6 *) retaddr;
-		ipv6_addr_copy(&ret6->sin6_addr, &in6->sin6_addr);
+		ret6->sin6_addr = in6->sin6_addr;
 	}
 
 	return 0;
diff --git a/fs/ecryptfs/crypto.c b/fs/ecryptfs/crypto.c
index 58609bd..2a83425 100644
--- a/fs/ecryptfs/crypto.c
+++ b/fs/ecryptfs/crypto.c
@@ -967,7 +967,7 @@ static void ecryptfs_set_default_crypt_stat_vals(
 
 /**
  * ecryptfs_new_file_context
- * @ecryptfs_dentry: The eCryptfs dentry
+ * @ecryptfs_inode: The eCryptfs inode
  *
  * If the crypto context for the file has not yet been established,
  * this is where we do that.  Establishing a new crypto context
@@ -984,13 +984,13 @@ static void ecryptfs_set_default_crypt_stat_vals(
  *
  * Returns zero on success; non-zero otherwise
  */
-int ecryptfs_new_file_context(struct dentry *ecryptfs_dentry)
+int ecryptfs_new_file_context(struct inode *ecryptfs_inode)
 {
 	struct ecryptfs_crypt_stat *crypt_stat =
-	    &ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat;
+	    &ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat =
 	    &ecryptfs_superblock_to_private(
-		    ecryptfs_dentry->d_sb)->mount_crypt_stat;
+		    ecryptfs_inode->i_sb)->mount_crypt_stat;
 	int cipher_name_len;
 	int rc = 0;
 
@@ -1299,12 +1299,12 @@ static int ecryptfs_write_headers_virt(char *page_virt, size_t max,
 }
 
 static int
-ecryptfs_write_metadata_to_contents(struct dentry *ecryptfs_dentry,
+ecryptfs_write_metadata_to_contents(struct inode *ecryptfs_inode,
 				    char *virt, size_t virt_len)
 {
 	int rc;
 
-	rc = ecryptfs_write_lower(ecryptfs_dentry->d_inode, virt,
+	rc = ecryptfs_write_lower(ecryptfs_inode, virt,
 				  0, virt_len);
 	if (rc < 0)
 		printk(KERN_ERR "%s: Error attempting to write header "
@@ -1338,7 +1338,8 @@ static unsigned long ecryptfs_get_zeroed_pages(gfp_t gfp_mask,
 
 /**
  * ecryptfs_write_metadata
- * @ecryptfs_dentry: The eCryptfs dentry
+ * @ecryptfs_dentry: The eCryptfs dentry, which should be negative
+ * @ecryptfs_inode: The newly created eCryptfs inode
  *
  * Write the file headers out.  This will likely involve a userspace
  * callout, in which the session key is encrypted with one or more
@@ -1348,10 +1349,11 @@ static unsigned long ecryptfs_get_zeroed_pages(gfp_t gfp_mask,
  *
  * Returns zero on success; non-zero on error
  */
-int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry)
+int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry,
+			    struct inode *ecryptfs_inode)
 {
 	struct ecryptfs_crypt_stat *crypt_stat =
-		&ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat;
+		&ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat;
 	unsigned int order;
 	char *virt;
 	size_t virt_len;
@@ -1391,7 +1393,7 @@ int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry)
 		rc = ecryptfs_write_metadata_to_xattr(ecryptfs_dentry, virt,
 						      size);
 	else
-		rc = ecryptfs_write_metadata_to_contents(ecryptfs_dentry, virt,
+		rc = ecryptfs_write_metadata_to_contents(ecryptfs_inode, virt,
 							 virt_len);
 	if (rc) {
 		printk(KERN_ERR "%s: Error writing metadata out to lower file; "
@@ -1943,7 +1945,7 @@ static unsigned char *portable_filename_chars = ("-.0123456789ABCD"
 
 /* We could either offset on every reverse map or just pad some 0x00's
  * at the front here */
-static const unsigned char filename_rev_map[] = {
+static const unsigned char filename_rev_map[256] = {
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 7 */
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 15 */
 	0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 23 */
@@ -1959,7 +1961,7 @@ static const unsigned char filename_rev_map[] = {
 	0x00, 0x26, 0x27, 0x28, 0x29, 0x2A, 0x2B, 0x2C, /* 103 */
 	0x2D, 0x2E, 0x2F, 0x30, 0x31, 0x32, 0x33, 0x34, /* 111 */
 	0x35, 0x36, 0x37, 0x38, 0x39, 0x3A, 0x3B, 0x3C, /* 119 */
-	0x3D, 0x3E, 0x3F
+	0x3D, 0x3E, 0x3F /* 123 - 255 initialized to 0x00 */
 };
 
 /**
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 54481a3..a9f29b1 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -584,9 +584,10 @@ int ecryptfs_init_crypt_ctx(struct ecryptfs_crypt_stat *crypt_stat);
 int ecryptfs_write_inode_size_to_metadata(struct inode *ecryptfs_inode);
 int ecryptfs_encrypt_page(struct page *page);
 int ecryptfs_decrypt_page(struct page *page);
-int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry);
+int ecryptfs_write_metadata(struct dentry *ecryptfs_dentry,
+			    struct inode *ecryptfs_inode);
 int ecryptfs_read_metadata(struct dentry *ecryptfs_dentry);
-int ecryptfs_new_file_context(struct dentry *ecryptfs_dentry);
+int ecryptfs_new_file_context(struct inode *ecryptfs_inode);
 void ecryptfs_write_crypt_stat_flags(char *page_virt,
 				     struct ecryptfs_crypt_stat *crypt_stat,
 				     size_t *written);
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index c6ac98c..d3f95f9 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -139,6 +139,27 @@ out:
 	return rc;
 }
 
+static void ecryptfs_vma_close(struct vm_area_struct *vma)
+{
+	filemap_write_and_wait(vma->vm_file->f_mapping);
+}
+
+static const struct vm_operations_struct ecryptfs_file_vm_ops = {
+	.close		= ecryptfs_vma_close,
+	.fault		= filemap_fault,
+};
+
+static int ecryptfs_file_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	int rc;
+
+	rc = generic_file_mmap(file, vma);
+	if (!rc)
+		vma->vm_ops = &ecryptfs_file_vm_ops;
+
+	return rc;
+}
+
 struct kmem_cache *ecryptfs_file_info_cache;
 
 /**
@@ -349,7 +370,7 @@ const struct file_operations ecryptfs_main_fops = {
 #ifdef CONFIG_COMPAT
 	.compat_ioctl = ecryptfs_compat_ioctl,
 #endif
-	.mmap = generic_file_mmap,
+	.mmap = ecryptfs_file_mmap,
 	.open = ecryptfs_open,
 	.flush = ecryptfs_flush,
 	.release = ecryptfs_release,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index a36d327..32f90a3 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -172,22 +172,23 @@ ecryptfs_create_underlying_file(struct inode *lower_dir_inode,
  * it. It will also update the eCryptfs directory inode to mimic the
  * stat of the lower directory inode.
  *
- * Returns zero on success; non-zero on error condition
+ * Returns the new eCryptfs inode on success; an ERR_PTR on error condition
  */
-static int
+static struct inode *
 ecryptfs_do_create(struct inode *directory_inode,
 		   struct dentry *ecryptfs_dentry, int mode)
 {
 	int rc;
 	struct dentry *lower_dentry;
 	struct dentry *lower_dir_dentry;
+	struct inode *inode;
 
 	lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry);
 	lower_dir_dentry = lock_parent(lower_dentry);
 	if (IS_ERR(lower_dir_dentry)) {
 		ecryptfs_printk(KERN_ERR, "Error locking directory of "
 				"dentry\n");
-		rc = PTR_ERR(lower_dir_dentry);
+		inode = ERR_CAST(lower_dir_dentry);
 		goto out;
 	}
 	rc = ecryptfs_create_underlying_file(lower_dir_dentry->d_inode,
@@ -195,20 +196,19 @@ ecryptfs_do_create(struct inode *directory_inode,
 	if (rc) {
 		printk(KERN_ERR "%s: Failure to create dentry in lower fs; "
 		       "rc = [%d]\n", __func__, rc);
+		inode = ERR_PTR(rc);
 		goto out_lock;
 	}
-	rc = ecryptfs_interpose(lower_dentry, ecryptfs_dentry,
-				directory_inode->i_sb);
-	if (rc) {
-		ecryptfs_printk(KERN_ERR, "Failure in ecryptfs_interpose\n");
+	inode = __ecryptfs_get_inode(lower_dentry->d_inode,
+				     directory_inode->i_sb);
+	if (IS_ERR(inode))
 		goto out_lock;
-	}
 	fsstack_copy_attr_times(directory_inode, lower_dir_dentry->d_inode);
 	fsstack_copy_inode_size(directory_inode, lower_dir_dentry->d_inode);
 out_lock:
 	unlock_dir(lower_dir_dentry);
 out:
-	return rc;
+	return inode;
 }
 
 /**
@@ -219,26 +219,26 @@ out:
  *
  * Returns zero on success
  */
-static int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry)
+static int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry,
+				    struct inode *ecryptfs_inode)
 {
 	struct ecryptfs_crypt_stat *crypt_stat =
-		&ecryptfs_inode_to_private(ecryptfs_dentry->d_inode)->crypt_stat;
+		&ecryptfs_inode_to_private(ecryptfs_inode)->crypt_stat;
 	int rc = 0;
 
-	if (S_ISDIR(ecryptfs_dentry->d_inode->i_mode)) {
+	if (S_ISDIR(ecryptfs_inode->i_mode)) {
 		ecryptfs_printk(KERN_DEBUG, "This is a directory\n");
 		crypt_stat->flags &= ~(ECRYPTFS_ENCRYPTED);
 		goto out;
 	}
 	ecryptfs_printk(KERN_DEBUG, "Initializing crypto context\n");
-	rc = ecryptfs_new_file_context(ecryptfs_dentry);
+	rc = ecryptfs_new_file_context(ecryptfs_inode);
 	if (rc) {
 		ecryptfs_printk(KERN_ERR, "Error creating new file "
 				"context; rc = [%d]\n", rc);
 		goto out;
 	}
-	rc = ecryptfs_get_lower_file(ecryptfs_dentry,
-				     ecryptfs_dentry->d_inode);
+	rc = ecryptfs_get_lower_file(ecryptfs_dentry, ecryptfs_inode);
 	if (rc) {
 		printk(KERN_ERR "%s: Error attempting to initialize "
 			"the lower file for the dentry with name "
@@ -246,10 +246,10 @@ static int ecryptfs_initialize_file(struct dentry *ecryptfs_dentry)
 			ecryptfs_dentry->d_name.name, rc);
 		goto out;
 	}
-	rc = ecryptfs_write_metadata(ecryptfs_dentry);
+	rc = ecryptfs_write_metadata(ecryptfs_dentry, ecryptfs_inode);
 	if (rc)
 		printk(KERN_ERR "Error writing headers; rc = [%d]\n", rc);
-	ecryptfs_put_lower_file(ecryptfs_dentry->d_inode);
+	ecryptfs_put_lower_file(ecryptfs_inode);
 out:
 	return rc;
 }
@@ -269,18 +269,28 @@ static int
 ecryptfs_create(struct inode *directory_inode, struct dentry *ecryptfs_dentry,
 		int mode, struct nameidata *nd)
 {
+	struct inode *ecryptfs_inode;
 	int rc;
 
-	/* ecryptfs_do_create() calls ecryptfs_interpose() */
-	rc = ecryptfs_do_create(directory_inode, ecryptfs_dentry, mode);
-	if (unlikely(rc)) {
+	ecryptfs_inode = ecryptfs_do_create(directory_inode, ecryptfs_dentry,
+					    mode);
+	if (unlikely(IS_ERR(ecryptfs_inode))) {
 		ecryptfs_printk(KERN_WARNING, "Failed to create file in"
 				"lower filesystem\n");
+		rc = PTR_ERR(ecryptfs_inode);
 		goto out;
 	}
 	/* At this point, a file exists on "disk"; we need to make sure
 	 * that this on disk file is prepared to be an ecryptfs file */
-	rc = ecryptfs_initialize_file(ecryptfs_dentry);
+	rc = ecryptfs_initialize_file(ecryptfs_dentry, ecryptfs_inode);
+	if (rc) {
+		drop_nlink(ecryptfs_inode);
+		unlock_new_inode(ecryptfs_inode);
+		iput(ecryptfs_inode);
+		goto out;
+	}
+	d_instantiate(ecryptfs_dentry, ecryptfs_inode);
+	unlock_new_inode(ecryptfs_inode);
 out:
 	return rc;
 }
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index f6dba45..12ccacd 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -565,7 +565,7 @@ ext4_fsblk_t ext4_count_free_clusters(struct super_block *sb)
 	brelse(bitmap_bh);
 	printk(KERN_DEBUG "ext4_count_free_clusters: stored = %llu"
 	       ", computed = %llu, %llu\n",
-	       EXT4_B2C(sbi, ext4_free_blocks_count(es)),
+	       EXT4_B2C(EXT4_SB(sb), ext4_free_blocks_count(es)),
 	       desc_count, bitmap_count);
 	return bitmap_count;
 #else
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 240f6e2..848f436 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2270,6 +2270,7 @@ retry:
 			ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: "
 			       "%ld pages, ino %lu; err %d", __func__,
 				wbc->nr_to_write, inode->i_ino, ret);
+			blk_finish_plug(&plug);
 			goto out_writepages;
 		}
 
@@ -2806,8 +2807,8 @@ out:
 	spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
 
 	/* queue the work to convert unwritten extents to written */
-	queue_work(wq, &io_end->work);
 	iocb->private = NULL;
+	queue_work(wq, &io_end->work);
 
 	/* XXX: probably should move into the real I/O completion handler */
 	inode_dio_done(inode);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 9953d80..3858767 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1683,7 +1683,9 @@ static int parse_options(char *options, struct super_block *sb,
 			data_opt = EXT4_MOUNT_WRITEBACK_DATA;
 		datacheck:
 			if (is_remount) {
-				if (test_opt(sb, DATA_FLAGS) != data_opt) {
+				if (!sbi->s_journal)
+					ext4_msg(sb, KERN_WARNING, "Remounting file system with no journal so ignoring journalled data option");
+				else if (test_opt(sb, DATA_FLAGS) != data_opt) {
 					ext4_msg(sb, KERN_ERR,
 						"Cannot change data mode on remount");
 					return 0;
@@ -3099,8 +3101,6 @@ static void ext4_destroy_lazyinit_thread(void)
 }
 
 static int ext4_fill_super(struct super_block *sb, void *data, int silent)
-				__releases(kernel_lock)
-				__acquires(kernel_lock)
 {
 	char *orig_data = kstrdup(data, GFP_KERNEL);
 	struct buffer_head *bh;
diff --git a/fs/minix/bitmap.c b/fs/minix/bitmap.c
index 3f32bcb..ef175cb 100644
--- a/fs/minix/bitmap.c
+++ b/fs/minix/bitmap.c
@@ -16,38 +16,26 @@
 #include <linux/bitops.h>
 #include <linux/sched.h>
 
-static const int nibblemap[] = { 4,3,3,2,3,2,2,1,3,2,2,1,2,1,1,0 };
-
 static DEFINE_SPINLOCK(bitmap_lock);
 
-static unsigned long count_free(struct buffer_head *map[], unsigned numblocks, __u32 numbits)
+/*
+ * bitmap consists of blocks filled with 16bit words
+ * bit set == busy, bit clear == free
+ * endianness is a mess, but for counting zero bits it really doesn't matter...
+ */
+static __u32 count_free(struct buffer_head *map[], unsigned blocksize, __u32 numbits)
 {
-	unsigned i, j, sum = 0;
-	struct buffer_head *bh;
-  
-	for (i=0; i<numblocks-1; i++) {
-		if (!(bh=map[i])) 
-			return(0);
-		for (j=0; j<bh->b_size; j++)
-			sum += nibblemap[bh->b_data[j] & 0xf]
-				+ nibblemap[(bh->b_data[j]>>4) & 0xf];
-	}
+	__u32 sum = 0;
+	unsigned blocks = DIV_ROUND_UP(numbits, blocksize * 8);
 
-	if (numblocks==0 || !(bh=map[numblocks-1]))
-		return(0);
-	i = ((numbits - (numblocks-1) * bh->b_size * 8) / 16) * 2;
-	for (j=0; j<i; j++) {
-		sum += nibblemap[bh->b_data[j] & 0xf]
-			+ nibblemap[(bh->b_data[j]>>4) & 0xf];
+	while (blocks--) {
+		unsigned words = blocksize / 2;
+		__u16 *p = (__u16 *)(*map++)->b_data;
+		while (words--)
+			sum += 16 - hweight16(*p++);
 	}
 
-	i = numbits%16;
-	if (i!=0) {
-		i = *(__u16 *)(&bh->b_data[j]) | ~((1<<i) - 1);
-		sum += nibblemap[i & 0xf] + nibblemap[(i>>4) & 0xf];
-		sum += nibblemap[(i>>8) & 0xf] + nibblemap[(i>>12) & 0xf];
-	}
-	return(sum);
+	return sum;
 }
 
 void minix_free_block(struct inode *inode, unsigned long block)
@@ -105,10 +93,12 @@ int minix_new_block(struct inode * inode)
 	return 0;
 }
 
-unsigned long minix_count_free_blocks(struct minix_sb_info *sbi)
+unsigned long minix_count_free_blocks(struct super_block *sb)
 {
-	return (count_free(sbi->s_zmap, sbi->s_zmap_blocks,
-		sbi->s_nzones - sbi->s_firstdatazone + 1)
+	struct minix_sb_info *sbi = minix_sb(sb);
+	u32 bits = sbi->s_nzones - (sbi->s_firstdatazone + 1);
+
+	return (count_free(sbi->s_zmap, sb->s_blocksize, bits)
 		<< sbi->s_log_zone_size);
 }
 
@@ -273,7 +263,10 @@ struct inode *minix_new_inode(const struct inode *dir, int mode, int *error)
 	return inode;
 }
 
-unsigned long minix_count_free_inodes(struct minix_sb_info *sbi)
+unsigned long minix_count_free_inodes(struct super_block *sb)
 {
-	return count_free(sbi->s_imap, sbi->s_imap_blocks, sbi->s_ninodes + 1);
+	struct minix_sb_info *sbi = minix_sb(sb);
+	u32 bits = sbi->s_ninodes + 1;
+
+	return count_free(sbi->s_imap, sb->s_blocksize, bits);
 }
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 64cdcd6..1d9e339 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -279,6 +279,27 @@ static int minix_fill_super(struct super_block *s, void *data, int silent)
  	else if (sbi->s_mount_state & MINIX_ERROR_FS)
 		printk("MINIX-fs: mounting file system with errors, "
 			"running fsck is recommended\n");
+
+	/* Apparently minix can create filesystems that allocate more blocks for
+	 * the bitmaps than needed.  We simply ignore that, but verify it didn't
+	 * create one with not enough blocks and bail out if so.
+	 */
+	block = minix_blocks_needed(sbi->s_ninodes, s->s_blocksize);
+	if (sbi->s_imap_blocks < block) {
+		printk("MINIX-fs: file system does not have enough "
+				"imap blocks allocated.  Refusing to mount\n");
+		goto out_iput;
+	}
+
+	block = minix_blocks_needed(
+			(sbi->s_nzones - (sbi->s_firstdatazone + 1)),
+			s->s_blocksize);
+	if (sbi->s_zmap_blocks < block) {
+		printk("MINIX-fs: file system does not have enough "
+				"zmap blocks allocated.  Refusing to mount.\n");
+		goto out_iput;
+	}
+
 	return 0;
 
 out_iput:
@@ -339,10 +360,10 @@ static int minix_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_type = sb->s_magic;
 	buf->f_bsize = sb->s_blocksize;
 	buf->f_blocks = (sbi->s_nzones - sbi->s_firstdatazone) << sbi->s_log_zone_size;
-	buf->f_bfree = minix_count_free_blocks(sbi);
+	buf->f_bfree = minix_count_free_blocks(sb);
 	buf->f_bavail = buf->f_bfree;
 	buf->f_files = sbi->s_ninodes;
-	buf->f_ffree = minix_count_free_inodes(sbi);
+	buf->f_ffree = minix_count_free_inodes(sb);
 	buf->f_namelen = sbi->s_namelen;
 	buf->f_fsid.val[0] = (u32)id;
 	buf->f_fsid.val[1] = (u32)(id >> 32);
diff --git a/fs/minix/minix.h b/fs/minix/minix.h
index 341e212..26bbd55 100644
--- a/fs/minix/minix.h
+++ b/fs/minix/minix.h
@@ -48,10 +48,10 @@ extern struct minix_inode * minix_V1_raw_inode(struct super_block *, ino_t, stru
 extern struct minix2_inode * minix_V2_raw_inode(struct super_block *, ino_t, struct buffer_head **);
 extern struct inode * minix_new_inode(const struct inode *, int, int *);
 extern void minix_free_inode(struct inode * inode);
-extern unsigned long minix_count_free_inodes(struct minix_sb_info *sbi);
+extern unsigned long minix_count_free_inodes(struct super_block *sb);
 extern int minix_new_block(struct inode * inode);
 extern void minix_free_block(struct inode *inode, unsigned long block);
-extern unsigned long minix_count_free_blocks(struct minix_sb_info *sbi);
+extern unsigned long minix_count_free_blocks(struct super_block *sb);
 extern int minix_getattr(struct vfsmount *, struct dentry *, struct kstat *);
 extern int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len);
 
@@ -88,6 +88,11 @@ static inline struct minix_inode_info *minix_i(struct inode *inode)
 	return list_entry(inode, struct minix_inode_info, vfs_inode);
 }
 
+static inline unsigned minix_blocks_needed(unsigned bits, unsigned blocksize)
+{
+	return DIV_ROUND_UP(bits, blocksize * 8);
+}
+
 #if defined(CONFIG_MINIX_FS_NATIVE_ENDIAN) && \
 	defined(CONFIG_MINIX_FS_BIG_ENDIAN_16BIT_INDEXED)
 
@@ -125,7 +130,7 @@ static inline int minix_find_first_zero_bit(const void *vaddr, unsigned size)
 	if (!size)
 		return 0;
 
-	size = (size >> 4) + ((size & 15) > 0);
+	size >>= 4;
 	while (*p++ == 0xffff) {
 		if (--size == 0)
 			return (p - addr) << 4;
diff --git a/fs/namespace.c b/fs/namespace.c
index e5e1c7d..6d3a196 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2483,11 +2483,43 @@ struct mnt_namespace *create_mnt_ns(struct vfsmount *mnt)
 		__mnt_make_longterm(mnt);
 		new_ns->root = mnt;
 		list_add(&new_ns->list, &new_ns->root->mnt_list);
+	} else {
+		mntput(mnt);
 	}
 	return new_ns;
 }
 EXPORT_SYMBOL(create_mnt_ns);
 
+struct dentry *mount_subtree(struct vfsmount *mnt, const char *name)
+{
+	struct mnt_namespace *ns;
+	struct super_block *s;
+	struct path path;
+	int err;
+
+	ns = create_mnt_ns(mnt);
+	if (IS_ERR(ns))
+		return ERR_CAST(ns);
+
+	err = vfs_path_lookup(mnt->mnt_root, mnt,
+			name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
+
+	put_mnt_ns(ns);
+
+	if (err)
+		return ERR_PTR(err);
+
+	/* trade a vfsmount reference for active sb one */
+	s = path.mnt->mnt_sb;
+	atomic_inc(&s->s_active);
+	mntput(path.mnt);
+	/* lock the sucker */
+	down_write(&s->s_umount);
+	/* ... and return the root of (sub)tree on it */
+	return path.dentry;
+}
+EXPORT_SYMBOL(mount_subtree);
+
 SYSCALL_DEFINE5(mount, char __user *, dev_name, char __user *, dir_name,
 		char __user *, type, unsigned long, flags, void __user *, data)
 {
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index b238d95..ac28990 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1468,12 +1468,12 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
 				res = NULL;
 				goto out;
 			/* This turned out not to be a regular file */
+			case -EISDIR:
 			case -ENOTDIR:
 				goto no_open;
 			case -ELOOP:
 				if (!(nd->intent.open.flags & O_NOFOLLOW))
 					goto no_open;
-			/* case -EISDIR: */
 			/* case -EINVAL: */
 			default:
 				res = ERR_CAST(inode);
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 0a1f831..eca56d4 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -40,48 +40,8 @@
 
 #define NFSDBG_FACILITY		NFSDBG_FILE
 
-static int nfs_file_open(struct inode *, struct file *);
-static int nfs_file_release(struct inode *, struct file *);
-static loff_t nfs_file_llseek(struct file *file, loff_t offset, int origin);
-static int  nfs_file_mmap(struct file *, struct vm_area_struct *);
-static ssize_t nfs_file_splice_read(struct file *filp, loff_t *ppos,
-					struct pipe_inode_info *pipe,
-					size_t count, unsigned int flags);
-static ssize_t nfs_file_read(struct kiocb *, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos);
-static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe,
-					struct file *filp, loff_t *ppos,
-					size_t count, unsigned int flags);
-static ssize_t nfs_file_write(struct kiocb *, const struct iovec *iov,
-				unsigned long nr_segs, loff_t pos);
-static int  nfs_file_flush(struct file *, fl_owner_t id);
-static int  nfs_file_fsync(struct file *, loff_t, loff_t, int datasync);
-static int nfs_check_flags(int flags);
-static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl);
-static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl);
-static int nfs_setlease(struct file *file, long arg, struct file_lock **fl);
-
 static const struct vm_operations_struct nfs_file_vm_ops;
 
-const struct file_operations nfs_file_operations = {
-	.llseek		= nfs_file_llseek,
-	.read		= do_sync_read,
-	.write		= do_sync_write,
-	.aio_read	= nfs_file_read,
-	.aio_write	= nfs_file_write,
-	.mmap		= nfs_file_mmap,
-	.open		= nfs_file_open,
-	.flush		= nfs_file_flush,
-	.release	= nfs_file_release,
-	.fsync		= nfs_file_fsync,
-	.lock		= nfs_lock,
-	.flock		= nfs_flock,
-	.splice_read	= nfs_file_splice_read,
-	.splice_write	= nfs_file_splice_write,
-	.check_flags	= nfs_check_flags,
-	.setlease	= nfs_setlease,
-};
-
 const struct inode_operations nfs_file_inode_operations = {
 	.permission	= nfs_permission,
 	.getattr	= nfs_getattr,
@@ -886,3 +846,54 @@ static int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
 			file->f_path.dentry->d_name.name, arg);
 	return -EINVAL;
 }
+
+const struct file_operations nfs_file_operations = {
+	.llseek		= nfs_file_llseek,
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read	= nfs_file_read,
+	.aio_write	= nfs_file_write,
+	.mmap		= nfs_file_mmap,
+	.open		= nfs_file_open,
+	.flush		= nfs_file_flush,
+	.release	= nfs_file_release,
+	.fsync		= nfs_file_fsync,
+	.lock		= nfs_lock,
+	.flock		= nfs_flock,
+	.splice_read	= nfs_file_splice_read,
+	.splice_write	= nfs_file_splice_write,
+	.check_flags	= nfs_check_flags,
+	.setlease	= nfs_setlease,
+};
+
+#ifdef CONFIG_NFS_V4
+static int
+nfs4_file_open(struct inode *inode, struct file *filp)
+{
+	/*
+	 * NFSv4 opens are handled in d_lookup and d_revalidate. If we get to
+	 * this point, then something is very wrong
+	 */
+	dprintk("NFS: %s called! inode=%p filp=%p\n", __func__, inode, filp);
+	return -ENOTDIR;
+}
+
+const struct file_operations nfs4_file_operations = {
+	.llseek		= nfs_file_llseek,
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read	= nfs_file_read,
+	.aio_write	= nfs_file_write,
+	.mmap		= nfs_file_mmap,
+	.open		= nfs4_file_open,
+	.flush		= nfs_file_flush,
+	.release	= nfs_file_release,
+	.fsync		= nfs_file_fsync,
+	.lock		= nfs_lock,
+	.flock		= nfs_flock,
+	.splice_read	= nfs_file_splice_read,
+	.splice_write	= nfs_file_splice_write,
+	.check_flags	= nfs_check_flags,
+	.setlease	= nfs_setlease,
+};
+#endif /* CONFIG_NFS_V4 */
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index c07a55a..50a15fa 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -291,7 +291,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		 */
 		inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->file_inode_ops;
 		if (S_ISREG(inode->i_mode)) {
-			inode->i_fop = &nfs_file_operations;
+			inode->i_fop = NFS_SB(sb)->nfs_client->rpc_ops->file_ops;
 			inode->i_data.a_ops = &nfs_file_aops;
 			inode->i_data.backing_dev_info = &NFS_SB(sb)->backing_dev_info;
 		} else if (S_ISDIR(inode->i_mode)) {
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index c1a1bd8..3f4d957 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -299,6 +299,8 @@ extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
 extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc,
 		struct list_head *head);
 
+extern void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
+		struct inode *inode);
 extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
 extern void nfs_readdata_release(struct nfs_read_data *rdata);
 
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index 85f1690..d4bc9ed9 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -853,6 +853,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.dentry_ops	= &nfs_dentry_operations,
 	.dir_inode_ops	= &nfs3_dir_inode_operations,
 	.file_inode_ops	= &nfs3_file_inode_operations,
+	.file_ops	= &nfs_file_operations,
 	.getroot	= nfs3_proc_get_root,
 	.getattr	= nfs3_proc_getattr,
 	.setattr	= nfs3_proc_setattr,
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index b60fddf..be2bbac 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2464,8 +2464,7 @@ static int nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qst
 		case -NFS4ERR_BADNAME:
 			return -ENOENT;
 		case -NFS4ERR_MOVED:
-			err = nfs4_get_referral(dir, name, fattr, fhandle);
-			break;
+			return nfs4_get_referral(dir, name, fattr, fhandle);
 		case -NFS4ERR_WRONGSEC:
 			nfs_fixup_secinfo_attributes(fattr, fhandle);
 		}
@@ -6253,6 +6252,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.dentry_ops	= &nfs4_dentry_operations,
 	.dir_inode_ops	= &nfs4_dir_inode_operations,
 	.file_inode_ops	= &nfs4_file_inode_operations,
+	.file_ops	= &nfs4_file_operations,
 	.getroot	= nfs4_proc_get_root,
 	.getattr	= nfs4_proc_getattr,
 	.setattr	= nfs4_proc_setattr,
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index baf7353..8e672a2 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1260,6 +1260,25 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages);
 
+static void pnfs_ld_handle_read_error(struct nfs_read_data *data)
+{
+	struct nfs_pageio_descriptor pgio;
+
+	put_lseg(data->lseg);
+	data->lseg = NULL;
+	dprintk("pnfs write error = %d\n", data->pnfs_error);
+
+	nfs_pageio_init_read_mds(&pgio, data->inode);
+
+	while (!list_empty(&data->pages)) {
+		struct nfs_page *req = nfs_list_entry(data->pages.next);
+
+		nfs_list_remove_request(req);
+		nfs_pageio_add_request(&pgio, req);
+	}
+	nfs_pageio_complete(&pgio);
+}
+
 /*
  * Called by non rpc-based layout drivers
  */
@@ -1268,11 +1287,8 @@ void pnfs_ld_read_done(struct nfs_read_data *data)
 	if (likely(!data->pnfs_error)) {
 		__nfs4_read_done_cb(data);
 		data->mds_ops->rpc_call_done(&data->task, data);
-	} else {
-		put_lseg(data->lseg);
-		data->lseg = NULL;
-		dprintk("pnfs write error = %d\n", data->pnfs_error);
-	}
+	} else
+		pnfs_ld_handle_read_error(data);
 	data->mds_ops->rpc_release(data);
 }
 EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index ac40b85..f48125d 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -710,6 +710,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.dentry_ops	= &nfs_dentry_operations,
 	.dir_inode_ops	= &nfs_dir_inode_operations,
 	.file_inode_ops	= &nfs_file_inode_operations,
+	.file_ops	= &nfs_file_operations,
 	.getroot	= nfs_proc_get_root,
 	.getattr	= nfs_proc_getattr,
 	.setattr	= nfs_proc_setattr,
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 8b48ec6..cfa175c 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -109,7 +109,7 @@ static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data)
 	}
 }
 
-static void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
+void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio,
 		struct inode *inode)
 {
 	nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops,
@@ -534,23 +534,13 @@ static void nfs_readpage_result_full(struct rpc_task *task, void *calldata)
 static void nfs_readpage_release_full(void *calldata)
 {
 	struct nfs_read_data *data = calldata;
-	struct nfs_pageio_descriptor pgio;
 
-	if (data->pnfs_error) {
-		nfs_pageio_init_read_mds(&pgio, data->inode);
-		pgio.pg_recoalesce = 1;
-	}
 	while (!list_empty(&data->pages)) {
 		struct nfs_page *req = nfs_list_entry(data->pages.next);
 
 		nfs_list_remove_request(req);
-		if (!data->pnfs_error)
-			nfs_readpage_release(req);
-		else
-			nfs_pageio_add_request(&pgio, req);
+		nfs_readpage_release(req);
 	}
-	if (data->pnfs_error)
-		nfs_pageio_complete(&pgio);
 	nfs_readdata_release(calldata);
 }
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 480b3b6..1347774 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2787,43 +2787,18 @@ static void nfs_referral_loop_unprotect(void)
 static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt,
 		const char *export_path)
 {
-	struct mnt_namespace *ns_private;
-	struct super_block *s;
 	struct dentry *dentry;
-	struct path path;
-	int ret;
-
-	ns_private = create_mnt_ns(root_mnt);
-	ret = PTR_ERR(ns_private);
-	if (IS_ERR(ns_private))
-		goto out_mntput;
-
-	ret = nfs_referral_loop_protect();
-	if (ret != 0)
-		goto out_put_mnt_ns;
+	int ret = nfs_referral_loop_protect();
 
-	ret = vfs_path_lookup(root_mnt->mnt_root, root_mnt,
-			export_path, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
+	if (ret) {
+		mntput(root_mnt);
+		return ERR_PTR(ret);
+	}
 
+	dentry = mount_subtree(root_mnt, export_path);
 	nfs_referral_loop_unprotect();
-	put_mnt_ns(ns_private);
-
-	if (ret != 0)
-		goto out_err;
-
-	s = path.mnt->mnt_sb;
-	atomic_inc(&s->s_active);
-	dentry = dget(path.dentry);
 
-	path_put(&path);
-	down_write(&s->s_umount);
 	return dentry;
-out_put_mnt_ns:
-	put_mnt_ns(ns_private);
-out_mntput:
-	mntput(root_mnt);
-out_err:
-	return ERR_PTR(ret);
 }
 
 static struct dentry *nfs4_try_mount(int flags, const char *dev_name,
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index ed553c6..3165aeb 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -5699,7 +5699,7 @@ int ocfs2_remove_btree_range(struct inode *inode,
 					   OCFS2_JOURNAL_ACCESS_WRITE);
 	if (ret) {
 		mlog_errno(ret);
-		goto out;
+		goto out_commit;
 	}
 
 	dquot_free_space_nodirty(inode,
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index c1efe93..78b68af 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -290,7 +290,15 @@ static int ocfs2_readpage(struct file *file, struct page *page)
 	}
 
 	if (down_read_trylock(&oi->ip_alloc_sem) == 0) {
+		/*
+		 * Unlock the page and cycle ip_alloc_sem so that we don't
+		 * busyloop waiting for ip_alloc_sem to unlock
+		 */
 		ret = AOP_TRUNCATED_PAGE;
+		unlock_page(page);
+		unlock = 0;
+		down_read(&oi->ip_alloc_sem);
+		up_read(&oi->ip_alloc_sem);
 		goto out_inode_unlock;
 	}
 
@@ -563,6 +571,7 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
 {
 	struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
 	int level;
+	wait_queue_head_t *wq = ocfs2_ioend_wq(inode);
 
 	/* this io's submitter should not have unlocked this before we could */
 	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
@@ -570,6 +579,15 @@ static void ocfs2_dio_end_io(struct kiocb *iocb,
 	if (ocfs2_iocb_is_sem_locked(iocb))
 		ocfs2_iocb_clear_sem_locked(iocb);
 
+	if (ocfs2_iocb_is_unaligned_aio(iocb)) {
+		ocfs2_iocb_clear_unaligned_aio(iocb);
+
+		if (atomic_dec_and_test(&OCFS2_I(inode)->ip_unaligned_aio) &&
+		    waitqueue_active(wq)) {
+			wake_up_all(wq);
+		}
+	}
+
 	ocfs2_iocb_clear_rw_locked(iocb);
 
 	level = ocfs2_iocb_rw_locked_level(iocb);
@@ -863,6 +881,12 @@ struct ocfs2_write_ctxt {
 	struct page			*w_target_page;
 
 	/*
+	 * w_target_locked is used for page_mkwrite path indicating no unlocking
+	 * against w_target_page in ocfs2_write_end_nolock.
+	 */
+	unsigned int			w_target_locked:1;
+
+	/*
 	 * ocfs2_write_end() uses this to know what the real range to
 	 * write in the target should be.
 	 */
@@ -895,6 +919,24 @@ void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
 
 static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
 {
+	int i;
+
+	/*
+	 * w_target_locked is only set to true in the page_mkwrite() case.
+	 * The intent is to allow us to lock the target page from write_begin()
+	 * to write_end(). The caller must hold a ref on w_target_page.
+	 */
+	if (wc->w_target_locked) {
+		BUG_ON(!wc->w_target_page);
+		for (i = 0; i < wc->w_num_pages; i++) {
+			if (wc->w_target_page == wc->w_pages[i]) {
+				wc->w_pages[i] = NULL;
+				break;
+			}
+		}
+		mark_page_accessed(wc->w_target_page);
+		page_cache_release(wc->w_target_page);
+	}
 	ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
 
 	brelse(wc->w_di_bh);
@@ -1132,20 +1174,17 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 			 */
 			lock_page(mmap_page);
 
+			/* Exit and let the caller retry */
 			if (mmap_page->mapping != mapping) {
+				WARN_ON(mmap_page->mapping);
 				unlock_page(mmap_page);
-				/*
-				 * Sanity check - the locking in
-				 * ocfs2_pagemkwrite() should ensure
-				 * that this code doesn't trigger.
-				 */
-				ret = -EINVAL;
-				mlog_errno(ret);
+				ret = -EAGAIN;
 				goto out;
 			}
 
 			page_cache_get(mmap_page);
 			wc->w_pages[i] = mmap_page;
+			wc->w_target_locked = true;
 		} else {
 			wc->w_pages[i] = find_or_create_page(mapping, index,
 							     GFP_NOFS);
@@ -1160,6 +1199,8 @@ static int ocfs2_grab_pages_for_write(struct address_space *mapping,
 			wc->w_target_page = wc->w_pages[i];
 	}
 out:
+	if (ret)
+		wc->w_target_locked = false;
 	return ret;
 }
 
@@ -1817,11 +1858,23 @@ try_again:
 	 */
 	ret = ocfs2_grab_pages_for_write(mapping, wc, wc->w_cpos, pos, len,
 					 cluster_of_pages, mmap_page);
-	if (ret) {
+	if (ret && ret != -EAGAIN) {
 		mlog_errno(ret);
 		goto out_quota;
 	}
 
+	/*
+	 * ocfs2_grab_pages_for_write() returns -EAGAIN if it could not lock
+	 * the target page. In this case, we exit with no error and no target
+	 * page. This will trigger the caller, page_mkwrite(), to re-try
+	 * the operation.
+	 */
+	if (ret == -EAGAIN) {
+		BUG_ON(wc->w_target_page);
+		ret = 0;
+		goto out_quota;
+	}
+
 	ret = ocfs2_write_cluster_by_desc(mapping, data_ac, meta_ac, wc, pos,
 					  len);
 	if (ret) {
diff --git a/fs/ocfs2/aops.h b/fs/ocfs2/aops.h
index 75cf3ad..ffb2da3 100644
--- a/fs/ocfs2/aops.h
+++ b/fs/ocfs2/aops.h
@@ -78,6 +78,7 @@ enum ocfs2_iocb_lock_bits {
 	OCFS2_IOCB_RW_LOCK = 0,
 	OCFS2_IOCB_RW_LOCK_LEVEL,
 	OCFS2_IOCB_SEM,
+	OCFS2_IOCB_UNALIGNED_IO,
 	OCFS2_IOCB_NUM_LOCKS
 };
 
@@ -91,4 +92,17 @@ enum ocfs2_iocb_lock_bits {
 	clear_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
 #define ocfs2_iocb_is_sem_locked(iocb) \
 	test_bit(OCFS2_IOCB_SEM, (unsigned long *)&iocb->private)
+
+#define ocfs2_iocb_set_unaligned_aio(iocb) \
+	set_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
+#define ocfs2_iocb_clear_unaligned_aio(iocb) \
+	clear_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
+#define ocfs2_iocb_is_unaligned_aio(iocb) \
+	test_bit(OCFS2_IOCB_UNALIGNED_IO, (unsigned long *)&iocb->private)
+
+#define OCFS2_IOEND_WQ_HASH_SZ	37
+#define ocfs2_ioend_wq(v)   (&ocfs2__ioend_wq[((unsigned long)(v)) %\
+					    OCFS2_IOEND_WQ_HASH_SZ])
+extern wait_queue_head_t ocfs2__ioend_wq[OCFS2_IOEND_WQ_HASH_SZ];
+
 #endif /* OCFS2_FILE_H */
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 9a3e6bb..a4e855e 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -216,6 +216,7 @@ struct o2hb_region {
 
 	struct list_head	hr_all_item;
 	unsigned		hr_unclean_stop:1,
+				hr_aborted_start:1,
 				hr_item_pinned:1,
 				hr_item_dropped:1;
 
@@ -254,6 +255,10 @@ struct o2hb_region {
 	 * a more complete api that doesn't lead to this sort of fragility. */
 	atomic_t		hr_steady_iterations;
 
+	/* terminate o2hb thread if it does not reach steady state
+	 * (hr_steady_iterations == 0) within hr_unsteady_iterations */
+	atomic_t		hr_unsteady_iterations;
+
 	char			hr_dev_name[BDEVNAME_SIZE];
 
 	unsigned int		hr_timeout_ms;
@@ -324,6 +329,10 @@ static void o2hb_write_timeout(struct work_struct *work)
 
 static void o2hb_arm_write_timeout(struct o2hb_region *reg)
 {
+	/* Arm writeout only after thread reaches steady state */
+	if (atomic_read(&reg->hr_steady_iterations) != 0)
+		return;
+
 	mlog(ML_HEARTBEAT, "Queue write timeout for %u ms\n",
 	     O2HB_MAX_WRITE_TIMEOUT_MS);
 
@@ -537,9 +546,14 @@ static int o2hb_verify_crc(struct o2hb_region *reg,
 	return read == computed;
 }
 
-/* We want to make sure that nobody is heartbeating on top of us --
- * this will help detect an invalid configuration. */
-static void o2hb_check_last_timestamp(struct o2hb_region *reg)
+/*
+ * Compare the slot data with what we wrote in the last iteration.
+ * If the match fails, print an appropriate error message. This is to
+ * detect errors like... another node hearting on the same slot,
+ * flaky device that is losing writes, etc.
+ * Returns 1 if check succeeds, 0 otherwise.
+ */
+static int o2hb_check_own_slot(struct o2hb_region *reg)
 {
 	struct o2hb_disk_slot *slot;
 	struct o2hb_disk_heartbeat_block *hb_block;
@@ -548,13 +562,13 @@ static void o2hb_check_last_timestamp(struct o2hb_region *reg)
 	slot = &reg->hr_slots[o2nm_this_node()];
 	/* Don't check on our 1st timestamp */
 	if (!slot->ds_last_time)
-		return;
+		return 0;
 
 	hb_block = slot->ds_raw_block;
 	if (le64_to_cpu(hb_block->hb_seq) == slot->ds_last_time &&
 	    le64_to_cpu(hb_block->hb_generation) == slot->ds_last_generation &&
 	    hb_block->hb_node == slot->ds_node_num)
-		return;
+		return 1;
 
 #define ERRSTR1		"Another node is heartbeating on device"
 #define ERRSTR2		"Heartbeat generation mismatch on device"
@@ -574,6 +588,8 @@ static void o2hb_check_last_timestamp(struct o2hb_region *reg)
 	     (unsigned long long)slot->ds_last_time, hb_block->hb_node,
 	     (unsigned long long)le64_to_cpu(hb_block->hb_generation),
 	     (unsigned long long)le64_to_cpu(hb_block->hb_seq));
+
+	return 0;
 }
 
 static inline void o2hb_prepare_block(struct o2hb_region *reg,
@@ -719,17 +735,24 @@ static void o2hb_shutdown_slot(struct o2hb_disk_slot *slot)
 	o2nm_node_put(node);
 }
 
-static void o2hb_set_quorum_device(struct o2hb_region *reg,
-				   struct o2hb_disk_slot *slot)
+static void o2hb_set_quorum_device(struct o2hb_region *reg)
 {
-	assert_spin_locked(&o2hb_live_lock);
-
 	if (!o2hb_global_heartbeat_active())
 		return;
 
-	if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap))
+	/* Prevent race with o2hb_heartbeat_group_drop_item() */
+	if (kthread_should_stop())
+		return;
+
+	/* Tag region as quorum only after thread reaches steady state */
+	if (atomic_read(&reg->hr_steady_iterations) != 0)
 		return;
 
+	spin_lock(&o2hb_live_lock);
+
+	if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap))
+		goto unlock;
+
 	/*
 	 * A region can be added to the quorum only when it sees all
 	 * live nodes heartbeat on it. In other words, the region has been
@@ -737,13 +760,10 @@ static void o2hb_set_quorum_device(struct o2hb_region *reg,
 	 */
 	if (memcmp(reg->hr_live_node_bitmap, o2hb_live_node_bitmap,
 		   sizeof(o2hb_live_node_bitmap)))
-		return;
-
-	if (slot->ds_changed_samples < O2HB_LIVE_THRESHOLD)
-		return;
+		goto unlock;
 
-	printk(KERN_NOTICE "o2hb: Region %s is now a quorum device\n",
-	       config_item_name(&reg->hr_item));
+	printk(KERN_NOTICE "o2hb: Region %s (%s) is now a quorum device\n",
+	       config_item_name(&reg->hr_item), reg->hr_dev_name);
 
 	set_bit(reg->hr_region_num, o2hb_quorum_region_bitmap);
 
@@ -754,6 +774,8 @@ static void o2hb_set_quorum_device(struct o2hb_region *reg,
 	if (o2hb_pop_count(&o2hb_quorum_region_bitmap,
 			   O2NM_MAX_REGIONS) > O2HB_PIN_CUT_OFF)
 		o2hb_region_unpin(NULL);
+unlock:
+	spin_unlock(&o2hb_live_lock);
 }
 
 static int o2hb_check_slot(struct o2hb_region *reg,
@@ -925,8 +947,6 @@ fire_callbacks:
 		slot->ds_equal_samples = 0;
 	}
 out:
-	o2hb_set_quorum_device(reg, slot);
-
 	spin_unlock(&o2hb_live_lock);
 
 	o2hb_run_event_list(&event);
@@ -957,7 +977,8 @@ static int o2hb_highest_node(unsigned long *nodes,
 
 static int o2hb_do_disk_heartbeat(struct o2hb_region *reg)
 {
-	int i, ret, highest_node, change = 0;
+	int i, ret, highest_node;
+	int membership_change = 0, own_slot_ok = 0;
 	unsigned long configured_nodes[BITS_TO_LONGS(O2NM_MAX_NODES)];
 	unsigned long live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
 	struct o2hb_bio_wait_ctxt write_wc;
@@ -966,7 +987,7 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg)
 				       sizeof(configured_nodes));
 	if (ret) {
 		mlog_errno(ret);
-		return ret;
+		goto bail;
 	}
 
 	/*
@@ -982,8 +1003,9 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg)
 
 	highest_node = o2hb_highest_node(configured_nodes, O2NM_MAX_NODES);
 	if (highest_node >= O2NM_MAX_NODES) {
-		mlog(ML_NOTICE, "ocfs2_heartbeat: no configured nodes found!\n");
-		return -EINVAL;
+		mlog(ML_NOTICE, "o2hb: No configured nodes found!\n");
+		ret = -EINVAL;
+		goto bail;
 	}
 
 	/* No sense in reading the slots of nodes that don't exist
@@ -993,29 +1015,27 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg)
 	ret = o2hb_read_slots(reg, highest_node + 1);
 	if (ret < 0) {
 		mlog_errno(ret);
-		return ret;
+		goto bail;
 	}
 
 	/* With an up to date view of the slots, we can check that no
 	 * other node has been improperly configured to heartbeat in
 	 * our slot. */
-	o2hb_check_last_timestamp(reg);
+	own_slot_ok = o2hb_check_own_slot(reg);
 
 	/* fill in the proper info for our next heartbeat */
 	o2hb_prepare_block(reg, reg->hr_generation);
 
-	/* And fire off the write. Note that we don't wait on this I/O
-	 * until later. */
 	ret = o2hb_issue_node_write(reg, &write_wc);
 	if (ret < 0) {
 		mlog_errno(ret);
-		return ret;
+		goto bail;
 	}
 
 	i = -1;
 	while((i = find_next_bit(configured_nodes,
 				 O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES) {
-		change |= o2hb_check_slot(reg, &reg->hr_slots[i]);
+		membership_change |= o2hb_check_slot(reg, &reg->hr_slots[i]);
 	}
 
 	/*
@@ -1030,18 +1050,39 @@ static int o2hb_do_disk_heartbeat(struct o2hb_region *reg)
 		 * disk */
 		mlog(ML_ERROR, "Write error %d on device \"%s\"\n",
 		     write_wc.wc_error, reg->hr_dev_name);
-		return write_wc.wc_error;
+		ret = write_wc.wc_error;
+		goto bail;
 	}
 
-	o2hb_arm_write_timeout(reg);
+	/* Skip disarming the timeout if own slot has stale/bad data */
+	if (own_slot_ok) {
+		o2hb_set_quorum_device(reg);
+		o2hb_arm_write_timeout(reg);
+	}
 
+bail:
 	/* let the person who launched us know when things are steady */
-	if (!change && (atomic_read(&reg->hr_steady_iterations) != 0)) {
-		if (atomic_dec_and_test(&reg->hr_steady_iterations))
+	if (atomic_read(&reg->hr_steady_iterations) != 0) {
+		if (!ret && own_slot_ok && !membership_change) {
+			if (atomic_dec_and_test(&reg->hr_steady_iterations))
+				wake_up(&o2hb_steady_queue);
+		}
+	}
+
+	if (atomic_read(&reg->hr_steady_iterations) != 0) {
+		if (atomic_dec_and_test(&reg->hr_unsteady_iterations)) {
+			printk(KERN_NOTICE "o2hb: Unable to stabilize "
+			       "heartbeart on region %s (%s)\n",
+			       config_item_name(&reg->hr_item),
+			       reg->hr_dev_name);
+			atomic_set(&reg->hr_steady_iterations, 0);
+			reg->hr_aborted_start = 1;
 			wake_up(&o2hb_steady_queue);
+			ret = -EIO;
+		}
 	}
 
-	return 0;
+	return ret;
 }
 
 /* Subtract b from a, storing the result in a. a *must* have a larger
@@ -1095,7 +1136,8 @@ static int o2hb_thread(void *data)
 	/* Pin node */
 	o2nm_depend_this_node();
 
-	while (!kthread_should_stop() && !reg->hr_unclean_stop) {
+	while (!kthread_should_stop() &&
+	       !reg->hr_unclean_stop && !reg->hr_aborted_start) {
 		/* We track the time spent inside
 		 * o2hb_do_disk_heartbeat so that we avoid more than
 		 * hr_timeout_ms between disk writes. On busy systems
@@ -1103,10 +1145,7 @@ static int o2hb_thread(void *data)
 		 * likely to time itself out. */
 		do_gettimeofday(&before_hb);
 
-		i = 0;
-		do {
-			ret = o2hb_do_disk_heartbeat(reg);
-		} while (ret && ++i < 2);
+		ret = o2hb_do_disk_heartbeat(reg);
 
 		do_gettimeofday(&after_hb);
 		elapsed_msec = o2hb_elapsed_msecs(&before_hb, &after_hb);
@@ -1117,7 +1156,8 @@ static int o2hb_thread(void *data)
 		     after_hb.tv_sec, (unsigned long) after_hb.tv_usec,
 		     elapsed_msec);
 
-		if (elapsed_msec < reg->hr_timeout_ms) {
+		if (!kthread_should_stop() &&
+		    elapsed_msec < reg->hr_timeout_ms) {
 			/* the kthread api has blocked signals for us so no
 			 * need to record the return value. */
 			msleep_interruptible(reg->hr_timeout_ms - elapsed_msec);
@@ -1134,20 +1174,20 @@ static int o2hb_thread(void *data)
 	 * to timeout on this region when we could just as easily
 	 * write a clear generation - thus indicating to them that
 	 * this node has left this region.
-	 *
-	 * XXX: Should we skip this on unclean_stop? */
-	o2hb_prepare_block(reg, 0);
-	ret = o2hb_issue_node_write(reg, &write_wc);
-	if (ret == 0) {
-		o2hb_wait_on_io(reg, &write_wc);
-	} else {
-		mlog_errno(ret);
+	 */
+	if (!reg->hr_unclean_stop && !reg->hr_aborted_start) {
+		o2hb_prepare_block(reg, 0);
+		ret = o2hb_issue_node_write(reg, &write_wc);
+		if (ret == 0)
+			o2hb_wait_on_io(reg, &write_wc);
+		else
+			mlog_errno(ret);
 	}
 
 	/* Unpin node */
 	o2nm_undepend_this_node();
 
-	mlog(ML_HEARTBEAT|ML_KTHREAD, "hb thread exiting\n");
+	mlog(ML_HEARTBEAT|ML_KTHREAD, "o2hb thread exiting\n");
 
 	return 0;
 }
@@ -1158,6 +1198,7 @@ static int o2hb_debug_open(struct inode *inode, struct file *file)
 	struct o2hb_debug_buf *db = inode->i_private;
 	struct o2hb_region *reg;
 	unsigned long map[BITS_TO_LONGS(O2NM_MAX_NODES)];
+	unsigned long lts;
 	char *buf = NULL;
 	int i = -1;
 	int out = 0;
@@ -1194,9 +1235,11 @@ static int o2hb_debug_open(struct inode *inode, struct file *file)
 
 	case O2HB_DB_TYPE_REGION_ELAPSED_TIME:
 		reg = (struct o2hb_region *)db->db_data;
-		out += snprintf(buf + out, PAGE_SIZE - out, "%u\n",
-				jiffies_to_msecs(jiffies -
-						 reg->hr_last_timeout_start));
+		lts = reg->hr_last_timeout_start;
+		/* If 0, it has never been set before */
+		if (lts)
+			lts = jiffies_to_msecs(jiffies - lts);
+		out += snprintf(buf + out, PAGE_SIZE - out, "%lu\n", lts);
 		goto done;
 
 	case O2HB_DB_TYPE_REGION_PINNED:
@@ -1426,6 +1469,8 @@ static void o2hb_region_release(struct config_item *item)
 	struct page *page;
 	struct o2hb_region *reg = to_o2hb_region(item);
 
+	mlog(ML_HEARTBEAT, "hb region release (%s)\n", reg->hr_dev_name);
+
 	if (reg->hr_tmp_block)
 		kfree(reg->hr_tmp_block);
 
@@ -1792,7 +1837,10 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 			live_threshold <<= 1;
 		spin_unlock(&o2hb_live_lock);
 	}
-	atomic_set(&reg->hr_steady_iterations, live_threshold + 1);
+	++live_threshold;
+	atomic_set(&reg->hr_steady_iterations, live_threshold);
+	/* unsteady_iterations is double the steady_iterations */
+	atomic_set(&reg->hr_unsteady_iterations, (live_threshold << 1));
 
 	hb_task = kthread_run(o2hb_thread, reg, "o2hb-%s",
 			      reg->hr_item.ci_name);
@@ -1809,14 +1857,12 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 	ret = wait_event_interruptible(o2hb_steady_queue,
 				atomic_read(&reg->hr_steady_iterations) == 0);
 	if (ret) {
-		/* We got interrupted (hello ptrace!).  Clean up */
-		spin_lock(&o2hb_live_lock);
-		hb_task = reg->hr_task;
-		reg->hr_task = NULL;
-		spin_unlock(&o2hb_live_lock);
+		atomic_set(&reg->hr_steady_iterations, 0);
+		reg->hr_aborted_start = 1;
+	}
 
-		if (hb_task)
-			kthread_stop(hb_task);
+	if (reg->hr_aborted_start) {
+		ret = -EIO;
 		goto out;
 	}
 
@@ -1833,8 +1879,8 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 		ret = -EIO;
 
 	if (hb_task && o2hb_global_heartbeat_active())
-		printk(KERN_NOTICE "o2hb: Heartbeat started on region %s\n",
-		       config_item_name(&reg->hr_item));
+		printk(KERN_NOTICE "o2hb: Heartbeat started on region %s (%s)\n",
+		       config_item_name(&reg->hr_item), reg->hr_dev_name);
 
 out:
 	if (filp)
@@ -2092,13 +2138,6 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group,
 
 	/* stop the thread when the user removes the region dir */
 	spin_lock(&o2hb_live_lock);
-	if (o2hb_global_heartbeat_active()) {
-		clear_bit(reg->hr_region_num, o2hb_region_bitmap);
-		clear_bit(reg->hr_region_num, o2hb_live_region_bitmap);
-		if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap))
-			quorum_region = 1;
-		clear_bit(reg->hr_region_num, o2hb_quorum_region_bitmap);
-	}
 	hb_task = reg->hr_task;
 	reg->hr_task = NULL;
 	reg->hr_item_dropped = 1;
@@ -2107,19 +2146,30 @@ static void o2hb_heartbeat_group_drop_item(struct config_group *group,
 	if (hb_task)
 		kthread_stop(hb_task);
 
+	if (o2hb_global_heartbeat_active()) {
+		spin_lock(&o2hb_live_lock);
+		clear_bit(reg->hr_region_num, o2hb_region_bitmap);
+		clear_bit(reg->hr_region_num, o2hb_live_region_bitmap);
+		if (test_bit(reg->hr_region_num, o2hb_quorum_region_bitmap))
+			quorum_region = 1;
+		clear_bit(reg->hr_region_num, o2hb_quorum_region_bitmap);
+		spin_unlock(&o2hb_live_lock);
+		printk(KERN_NOTICE "o2hb: Heartbeat %s on region %s (%s)\n",
+		       ((atomic_read(&reg->hr_steady_iterations) == 0) ?
+			"stopped" : "start aborted"), config_item_name(item),
+		       reg->hr_dev_name);
+	}
+
 	/*
 	 * If we're racing a dev_write(), we need to wake them.  They will
 	 * check reg->hr_task
 	 */
 	if (atomic_read(&reg->hr_steady_iterations) != 0) {
+		reg->hr_aborted_start = 1;
 		atomic_set(&reg->hr_steady_iterations, 0);
 		wake_up(&o2hb_steady_queue);
 	}
 
-	if (o2hb_global_heartbeat_active())
-		printk(KERN_NOTICE "o2hb: Heartbeat stopped on region %s\n",
-		       config_item_name(&reg->hr_item));
-
 	config_item_put(item);
 
 	if (!o2hb_global_heartbeat_active() || !quorum_region)
diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c
index 3a583590..dc45deb 100644
--- a/fs/ocfs2/cluster/netdebug.c
+++ b/fs/ocfs2/cluster/netdebug.c
@@ -47,6 +47,7 @@
 #define SC_DEBUG_NAME		"sock_containers"
 #define NST_DEBUG_NAME		"send_tracking"
 #define STATS_DEBUG_NAME	"stats"
+#define NODES_DEBUG_NAME	"connected_nodes"
 
 #define SHOW_SOCK_CONTAINERS	0
 #define SHOW_SOCK_STATS		1
@@ -55,6 +56,7 @@ static struct dentry *o2net_dentry;
 static struct dentry *sc_dentry;
 static struct dentry *nst_dentry;
 static struct dentry *stats_dentry;
+static struct dentry *nodes_dentry;
 
 static DEFINE_SPINLOCK(o2net_debug_lock);
 
@@ -491,53 +493,87 @@ static const struct file_operations sc_seq_fops = {
 	.release = sc_fop_release,
 };
 
-int o2net_debugfs_init(void)
+static int o2net_fill_bitmap(char *buf, int len)
 {
-	o2net_dentry = debugfs_create_dir(O2NET_DEBUG_DIR, NULL);
-	if (!o2net_dentry) {
-		mlog_errno(-ENOMEM);
-		goto bail;
-	}
+	unsigned long map[BITS_TO_LONGS(O2NM_MAX_NODES)];
+	int i = -1, out = 0;
 
-	nst_dentry = debugfs_create_file(NST_DEBUG_NAME, S_IFREG|S_IRUSR,
-					 o2net_dentry, NULL,
-					 &nst_seq_fops);
-	if (!nst_dentry) {
-		mlog_errno(-ENOMEM);
-		goto bail;
-	}
+	o2net_fill_node_map(map, sizeof(map));
 
-	sc_dentry = debugfs_create_file(SC_DEBUG_NAME, S_IFREG|S_IRUSR,
-					o2net_dentry, NULL,
-					&sc_seq_fops);
-	if (!sc_dentry) {
-		mlog_errno(-ENOMEM);
-		goto bail;
-	}
+	while ((i = find_next_bit(map, O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES)
+		out += snprintf(buf + out, PAGE_SIZE - out, "%d ", i);
+	out += snprintf(buf + out, PAGE_SIZE - out, "\n");
 
-	stats_dentry = debugfs_create_file(STATS_DEBUG_NAME, S_IFREG|S_IRUSR,
-					   o2net_dentry, NULL,
-					   &stats_seq_fops);
-	if (!stats_dentry) {
-		mlog_errno(-ENOMEM);
-		goto bail;
-	}
+	return out;
+}
+
+static int nodes_fop_open(struct inode *inode, struct file *file)
+{
+	char *buf;
+
+	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	i_size_write(inode, o2net_fill_bitmap(buf, PAGE_SIZE));
+
+	file->private_data = buf;
 
 	return 0;
-bail:
-	debugfs_remove(stats_dentry);
-	debugfs_remove(sc_dentry);
-	debugfs_remove(nst_dentry);
-	debugfs_remove(o2net_dentry);
-	return -ENOMEM;
 }
 
+static int o2net_debug_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
+static ssize_t o2net_debug_read(struct file *file, char __user *buf,
+				size_t nbytes, loff_t *ppos)
+{
+	return simple_read_from_buffer(buf, nbytes, ppos, file->private_data,
+				       i_size_read(file->f_mapping->host));
+}
+
+static const struct file_operations nodes_fops = {
+	.open		= nodes_fop_open,
+	.release	= o2net_debug_release,
+	.read		= o2net_debug_read,
+	.llseek		= generic_file_llseek,
+};
+
 void o2net_debugfs_exit(void)
 {
+	debugfs_remove(nodes_dentry);
 	debugfs_remove(stats_dentry);
 	debugfs_remove(sc_dentry);
 	debugfs_remove(nst_dentry);
 	debugfs_remove(o2net_dentry);
 }
 
+int o2net_debugfs_init(void)
+{
+	mode_t mode = S_IFREG|S_IRUSR;
+
+	o2net_dentry = debugfs_create_dir(O2NET_DEBUG_DIR, NULL);
+	if (o2net_dentry)
+		nst_dentry = debugfs_create_file(NST_DEBUG_NAME, mode,
+					o2net_dentry, NULL, &nst_seq_fops);
+	if (nst_dentry)
+		sc_dentry = debugfs_create_file(SC_DEBUG_NAME, mode,
+					o2net_dentry, NULL, &sc_seq_fops);
+	if (sc_dentry)
+		stats_dentry = debugfs_create_file(STATS_DEBUG_NAME, mode,
+					o2net_dentry, NULL, &stats_seq_fops);
+	if (stats_dentry)
+		nodes_dentry = debugfs_create_file(NODES_DEBUG_NAME, mode,
+					o2net_dentry, NULL, &nodes_fops);
+	if (nodes_dentry)
+		return 0;
+
+	o2net_debugfs_exit();
+	mlog_errno(-ENOMEM);
+	return -ENOMEM;
+}
+
 #endif	/* CONFIG_DEBUG_FS */
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index ad7d0c1..044e7b5 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -546,7 +546,7 @@ static void o2net_set_nn_state(struct o2net_node *nn,
 	}
 
 	if (was_valid && !valid) {
-		printk(KERN_NOTICE "o2net: no longer connected to "
+		printk(KERN_NOTICE "o2net: No longer connected to "
 		       SC_NODEF_FMT "\n", SC_NODEF_ARGS(old_sc));
 		o2net_complete_nodes_nsw(nn);
 	}
@@ -556,7 +556,7 @@ static void o2net_set_nn_state(struct o2net_node *nn,
 		cancel_delayed_work(&nn->nn_connect_expired);
 		printk(KERN_NOTICE "o2net: %s " SC_NODEF_FMT "\n",
 		       o2nm_this_node() > sc->sc_node->nd_num ?
-		       		"connected to" : "accepted connection from",
+		       "Connected to" : "Accepted connection from",
 		       SC_NODEF_ARGS(sc));
 	}
 
@@ -644,7 +644,7 @@ static void o2net_state_change(struct sock *sk)
 			o2net_sc_queue_work(sc, &sc->sc_connect_work);
 			break;
 		default:
-			printk(KERN_INFO "o2net: connection to " SC_NODEF_FMT
+			printk(KERN_INFO "o2net: Connection to " SC_NODEF_FMT
 			      " shutdown, state %d\n",
 			      SC_NODEF_ARGS(sc), sk->sk_state);
 			o2net_sc_queue_work(sc, &sc->sc_shutdown_work);
@@ -1035,6 +1035,25 @@ static int o2net_tx_can_proceed(struct o2net_node *nn,
 	return ret;
 }
 
+/* Get a map of all nodes to which this node is currently connected to */
+void o2net_fill_node_map(unsigned long *map, unsigned bytes)
+{
+	struct o2net_sock_container *sc;
+	int node, ret;
+
+	BUG_ON(bytes < (BITS_TO_LONGS(O2NM_MAX_NODES) * sizeof(unsigned long)));
+
+	memset(map, 0, bytes);
+	for (node = 0; node < O2NM_MAX_NODES; ++node) {
+		o2net_tx_can_proceed(o2net_nn_from_num(node), &sc, &ret);
+		if (!ret) {
+			set_bit(node, map);
+			sc_put(sc);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(o2net_fill_node_map);
+
 int o2net_send_message_vec(u32 msg_type, u32 key, struct kvec *caller_vec,
 			   size_t caller_veclen, u8 target_node, int *status)
 {
@@ -1285,11 +1304,11 @@ static int o2net_check_handshake(struct o2net_sock_container *sc)
 	struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num);
 
 	if (hand->protocol_version != cpu_to_be64(O2NET_PROTOCOL_VERSION)) {
-		mlog(ML_NOTICE, SC_NODEF_FMT " advertised net protocol "
-		     "version %llu but %llu is required, disconnecting\n",
-		     SC_NODEF_ARGS(sc),
-		     (unsigned long long)be64_to_cpu(hand->protocol_version),
-		     O2NET_PROTOCOL_VERSION);
+		printk(KERN_NOTICE "o2net: " SC_NODEF_FMT " Advertised net "
+		       "protocol version %llu but %llu is required. "
+		       "Disconnecting.\n", SC_NODEF_ARGS(sc),
+		       (unsigned long long)be64_to_cpu(hand->protocol_version),
+		       O2NET_PROTOCOL_VERSION);
 
 		/* don't bother reconnecting if its the wrong version. */
 		o2net_ensure_shutdown(nn, sc, -ENOTCONN);
@@ -1303,33 +1322,33 @@ static int o2net_check_handshake(struct o2net_sock_container *sc)
 	 */
 	if (be32_to_cpu(hand->o2net_idle_timeout_ms) !=
 				o2net_idle_timeout()) {
-		mlog(ML_NOTICE, SC_NODEF_FMT " uses a network idle timeout of "
-		     "%u ms, but we use %u ms locally.  disconnecting\n",
-		     SC_NODEF_ARGS(sc),
-		     be32_to_cpu(hand->o2net_idle_timeout_ms),
-		     o2net_idle_timeout());
+		printk(KERN_NOTICE "o2net: " SC_NODEF_FMT " uses a network "
+		       "idle timeout of %u ms, but we use %u ms locally. "
+		       "Disconnecting.\n", SC_NODEF_ARGS(sc),
+		       be32_to_cpu(hand->o2net_idle_timeout_ms),
+		       o2net_idle_timeout());
 		o2net_ensure_shutdown(nn, sc, -ENOTCONN);
 		return -1;
 	}
 
 	if (be32_to_cpu(hand->o2net_keepalive_delay_ms) !=
 			o2net_keepalive_delay()) {
-		mlog(ML_NOTICE, SC_NODEF_FMT " uses a keepalive delay of "
-		     "%u ms, but we use %u ms locally.  disconnecting\n",
-		     SC_NODEF_ARGS(sc),
-		     be32_to_cpu(hand->o2net_keepalive_delay_ms),
-		     o2net_keepalive_delay());
+		printk(KERN_NOTICE "o2net: " SC_NODEF_FMT " uses a keepalive "
+		       "delay of %u ms, but we use %u ms locally. "
+		       "Disconnecting.\n", SC_NODEF_ARGS(sc),
+		       be32_to_cpu(hand->o2net_keepalive_delay_ms),
+		       o2net_keepalive_delay());
 		o2net_ensure_shutdown(nn, sc, -ENOTCONN);
 		return -1;
 	}
 
 	if (be32_to_cpu(hand->o2hb_heartbeat_timeout_ms) !=
 			O2HB_MAX_WRITE_TIMEOUT_MS) {
-		mlog(ML_NOTICE, SC_NODEF_FMT " uses a heartbeat timeout of "
-		     "%u ms, but we use %u ms locally.  disconnecting\n",
-		     SC_NODEF_ARGS(sc),
-		     be32_to_cpu(hand->o2hb_heartbeat_timeout_ms),
-		     O2HB_MAX_WRITE_TIMEOUT_MS);
+		printk(KERN_NOTICE "o2net: " SC_NODEF_FMT " uses a heartbeat "
+		       "timeout of %u ms, but we use %u ms locally. "
+		       "Disconnecting.\n", SC_NODEF_ARGS(sc),
+		       be32_to_cpu(hand->o2hb_heartbeat_timeout_ms),
+		       O2HB_MAX_WRITE_TIMEOUT_MS);
 		o2net_ensure_shutdown(nn, sc, -ENOTCONN);
 		return -1;
 	}
@@ -1540,28 +1559,16 @@ static void o2net_idle_timer(unsigned long data)
 {
 	struct o2net_sock_container *sc = (struct o2net_sock_container *)data;
 	struct o2net_node *nn = o2net_nn_from_num(sc->sc_node->nd_num);
-
 #ifdef CONFIG_DEBUG_FS
-	ktime_t now = ktime_get();
+	unsigned long msecs = ktime_to_ms(ktime_get()) -
+		ktime_to_ms(sc->sc_tv_timer);
+#else
+	unsigned long msecs = o2net_idle_timeout();
 #endif
 
-	printk(KERN_NOTICE "o2net: connection to " SC_NODEF_FMT " has been idle for %u.%u "
-	     "seconds, shutting it down.\n", SC_NODEF_ARGS(sc),
-		     o2net_idle_timeout() / 1000,
-		     o2net_idle_timeout() % 1000);
-
-#ifdef CONFIG_DEBUG_FS
-	mlog(ML_NOTICE, "Here are some times that might help debug the "
-	     "situation: (Timer: %lld, Now %lld, DataReady %lld, Advance %lld-%lld, "
-	     "Key 0x%08x, Func %u, FuncTime %lld-%lld)\n",
-	     (long long)ktime_to_us(sc->sc_tv_timer), (long long)ktime_to_us(now),
-	     (long long)ktime_to_us(sc->sc_tv_data_ready),
-	     (long long)ktime_to_us(sc->sc_tv_advance_start),
-	     (long long)ktime_to_us(sc->sc_tv_advance_stop),
-	     sc->sc_msg_key, sc->sc_msg_type,
-	     (long long)ktime_to_us(sc->sc_tv_func_start),
-	     (long long)ktime_to_us(sc->sc_tv_func_stop));
-#endif
+	printk(KERN_NOTICE "o2net: Connection to " SC_NODEF_FMT " has been "
+	       "idle for %lu.%lu secs, shutting it down.\n", SC_NODEF_ARGS(sc),
+	       msecs / 1000, msecs % 1000);
 
 	/*
 	 * Initialize the nn_timeout so that the next connection attempt
@@ -1694,8 +1701,8 @@ static void o2net_start_connect(struct work_struct *work)
 
 out:
 	if (ret) {
-		mlog(ML_NOTICE, "connect attempt to " SC_NODEF_FMT " failed "
-		     "with errno %d\n", SC_NODEF_ARGS(sc), ret);
+		printk(KERN_NOTICE "o2net: Connect attempt to " SC_NODEF_FMT
+		       " failed with errno %d\n", SC_NODEF_ARGS(sc), ret);
 		/* 0 err so that another will be queued and attempted
 		 * from set_nn_state */
 		if (sc)
@@ -1718,8 +1725,8 @@ static void o2net_connect_expired(struct work_struct *work)
 
 	spin_lock(&nn->nn_lock);
 	if (!nn->nn_sc_valid) {
-		mlog(ML_ERROR, "no connection established with node %u after "
-		     "%u.%u seconds, giving up and returning errors.\n",
+		printk(KERN_NOTICE "o2net: No connection established with "
+		       "node %u after %u.%u seconds, giving up.\n",
 		     o2net_num_from_nn(nn),
 		     o2net_idle_timeout() / 1000,
 		     o2net_idle_timeout() % 1000);
@@ -1862,21 +1869,21 @@ static int o2net_accept_one(struct socket *sock)
 
 	node = o2nm_get_node_by_ip(sin.sin_addr.s_addr);
 	if (node == NULL) {
-		mlog(ML_NOTICE, "attempt to connect from unknown node at %pI4:%d\n",
-		     &sin.sin_addr.s_addr, ntohs(sin.sin_port));
+		printk(KERN_NOTICE "o2net: Attempt to connect from unknown "
+		       "node at %pI4:%d\n", &sin.sin_addr.s_addr,
+		       ntohs(sin.sin_port));
 		ret = -EINVAL;
 		goto out;
 	}
 
 	if (o2nm_this_node() >= node->nd_num) {
 		local_node = o2nm_get_node_by_num(o2nm_this_node());
-		mlog(ML_NOTICE, "unexpected connect attempt seen at node '%s' ("
-		     "%u, %pI4:%d) from node '%s' (%u, %pI4:%d)\n",
-		     local_node->nd_name, local_node->nd_num,
-		     &(local_node->nd_ipv4_address),
-		     ntohs(local_node->nd_ipv4_port),
-		     node->nd_name, node->nd_num, &sin.sin_addr.s_addr,
-		     ntohs(sin.sin_port));
+		printk(KERN_NOTICE "o2net: Unexpected connect attempt seen "
+		       "at node '%s' (%u, %pI4:%d) from node '%s' (%u, "
+		       "%pI4:%d)\n", local_node->nd_name, local_node->nd_num,
+		       &(local_node->nd_ipv4_address),
+		       ntohs(local_node->nd_ipv4_port), node->nd_name,
+		       node->nd_num, &sin.sin_addr.s_addr, ntohs(sin.sin_port));
 		ret = -EINVAL;
 		goto out;
 	}
@@ -1901,10 +1908,10 @@ static int o2net_accept_one(struct socket *sock)
 		ret = 0;
 	spin_unlock(&nn->nn_lock);
 	if (ret) {
-		mlog(ML_NOTICE, "attempt to connect from node '%s' at "
-		     "%pI4:%d but it already has an open connection\n",
-		     node->nd_name, &sin.sin_addr.s_addr,
-		     ntohs(sin.sin_port));
+		printk(KERN_NOTICE "o2net: Attempt to connect from node '%s' "
+		       "at %pI4:%d but it already has an open connection\n",
+		       node->nd_name, &sin.sin_addr.s_addr,
+		       ntohs(sin.sin_port));
 		goto out;
 	}
 
@@ -1984,7 +1991,7 @@ static int o2net_open_listening_sock(__be32 addr, __be16 port)
 
 	ret = sock_create(PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
 	if (ret < 0) {
-		mlog(ML_ERROR, "unable to create socket, ret=%d\n", ret);
+		printk(KERN_ERR "o2net: Error %d while creating socket\n", ret);
 		goto out;
 	}
 
@@ -2001,16 +2008,15 @@ static int o2net_open_listening_sock(__be32 addr, __be16 port)
 	sock->sk->sk_reuse = 1;
 	ret = sock->ops->bind(sock, (struct sockaddr *)&sin, sizeof(sin));
 	if (ret < 0) {
-		mlog(ML_ERROR, "unable to bind socket at %pI4:%u, "
-		     "ret=%d\n", &addr, ntohs(port), ret);
+		printk(KERN_ERR "o2net: Error %d while binding socket at "
+		       "%pI4:%u\n", ret, &addr, ntohs(port)); 
 		goto out;
 	}
 
 	ret = sock->ops->listen(sock, 64);
-	if (ret < 0) {
-		mlog(ML_ERROR, "unable to listen on %pI4:%u, ret=%d\n",
-		     &addr, ntohs(port), ret);
-	}
+	if (ret < 0)
+		printk(KERN_ERR "o2net: Error %d while listening on %pI4:%u\n",
+		       ret, &addr, ntohs(port));
 
 out:
 	if (ret) {
diff --git a/fs/ocfs2/cluster/tcp.h b/fs/ocfs2/cluster/tcp.h
index fd6179e..5bada2a 100644
--- a/fs/ocfs2/cluster/tcp.h
+++ b/fs/ocfs2/cluster/tcp.h
@@ -106,6 +106,8 @@ int o2net_register_handler(u32 msg_type, u32 key, u32 max_len,
 			   struct list_head *unreg_list);
 void o2net_unregister_handler_list(struct list_head *list);
 
+void o2net_fill_node_map(unsigned long *map, unsigned bytes);
+
 struct o2nm_node;
 int o2net_register_hb_callbacks(void);
 void o2net_unregister_hb_callbacks(void);
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index e2878b5..8fe4e28 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -1184,8 +1184,7 @@ static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir,
 			if (pde)
 				le16_add_cpu(&pde->rec_len,
 						le16_to_cpu(de->rec_len));
-			else
-				de->inode = 0;
+			de->inode = 0;
 			dir->i_version++;
 			ocfs2_journal_dirty(handle, bh);
 			goto bail;
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index d602abb..a5952ce 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -859,8 +859,8 @@ void dlm_complete_recovery_thread(struct dlm_ctxt *dlm);
 void dlm_wait_for_recovery(struct dlm_ctxt *dlm);
 void dlm_kick_recovery_thread(struct dlm_ctxt *dlm);
 int dlm_is_node_dead(struct dlm_ctxt *dlm, u8 node);
-int dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout);
-int dlm_wait_for_node_recovery(struct dlm_ctxt *dlm, u8 node, int timeout);
+void dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout);
+void dlm_wait_for_node_recovery(struct dlm_ctxt *dlm, u8 node, int timeout);
 
 void dlm_put(struct dlm_ctxt *dlm);
 struct dlm_ctxt *dlm_grab(struct dlm_ctxt *dlm);
@@ -877,9 +877,8 @@ static inline void dlm_lockres_get(struct dlm_lock_resource *res)
 	kref_get(&res->refs);
 }
 void dlm_lockres_put(struct dlm_lock_resource *res);
-void __dlm_unhash_lockres(struct dlm_lock_resource *res);
-void __dlm_insert_lockres(struct dlm_ctxt *dlm,
-			  struct dlm_lock_resource *res);
+void __dlm_unhash_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res);
+void __dlm_insert_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res);
 struct dlm_lock_resource * __dlm_lookup_lockres_full(struct dlm_ctxt *dlm,
 						     const char *name,
 						     unsigned int len,
@@ -902,46 +901,15 @@ struct dlm_lock_resource *dlm_new_lockres(struct dlm_ctxt *dlm,
 					  const char *name,
 					  unsigned int namelen);
 
-#define dlm_lockres_set_refmap_bit(bit,res)  \
-	__dlm_lockres_set_refmap_bit(bit,res,__FILE__,__LINE__)
-#define dlm_lockres_clear_refmap_bit(bit,res)  \
-	__dlm_lockres_clear_refmap_bit(bit,res,__FILE__,__LINE__)
+void dlm_lockres_set_refmap_bit(struct dlm_ctxt *dlm,
+				struct dlm_lock_resource *res, int bit);
+void dlm_lockres_clear_refmap_bit(struct dlm_ctxt *dlm,
+				  struct dlm_lock_resource *res, int bit);
 
-static inline void __dlm_lockres_set_refmap_bit(int bit,
-						struct dlm_lock_resource *res,
-						const char *file,
-						int line)
-{
-	//printk("%s:%d:%.*s: setting bit %d\n", file, line,
-	//     res->lockname.len, res->lockname.name, bit);
-	set_bit(bit, res->refmap);
-}
-
-static inline void __dlm_lockres_clear_refmap_bit(int bit,
-						  struct dlm_lock_resource *res,
-						  const char *file,
-						  int line)
-{
-	//printk("%s:%d:%.*s: clearing bit %d\n", file, line,
-	//     res->lockname.len, res->lockname.name, bit);
-	clear_bit(bit, res->refmap);
-}
-
-void __dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
-				   struct dlm_lock_resource *res,
-				   const char *file,
-				   int line);
-void __dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
-				   struct dlm_lock_resource *res,
-				   int new_lockres,
-				   const char *file,
-				   int line);
-#define dlm_lockres_drop_inflight_ref(d,r)  \
-	__dlm_lockres_drop_inflight_ref(d,r,__FILE__,__LINE__)
-#define dlm_lockres_grab_inflight_ref(d,r)  \
-	__dlm_lockres_grab_inflight_ref(d,r,0,__FILE__,__LINE__)
-#define dlm_lockres_grab_inflight_ref_new(d,r)  \
-	__dlm_lockres_grab_inflight_ref(d,r,1,__FILE__,__LINE__)
+void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
+				   struct dlm_lock_resource *res);
+void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
+				   struct dlm_lock_resource *res);
 
 void dlm_queue_ast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
 void dlm_queue_bast(struct dlm_ctxt *dlm, struct dlm_lock *lock);
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 6ed6b95..92f2ead 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -157,16 +157,18 @@ static int dlm_protocol_compare(struct dlm_protocol_version *existing,
 
 static void dlm_unregister_domain_handlers(struct dlm_ctxt *dlm);
 
-void __dlm_unhash_lockres(struct dlm_lock_resource *lockres)
+void __dlm_unhash_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
 {
-	if (!hlist_unhashed(&lockres->hash_node)) {
-		hlist_del_init(&lockres->hash_node);
-		dlm_lockres_put(lockres);
-	}
+	if (hlist_unhashed(&res->hash_node))
+		return;
+
+	mlog(0, "%s: Unhash res %.*s\n", dlm->name, res->lockname.len,
+	     res->lockname.name);
+	hlist_del_init(&res->hash_node);
+	dlm_lockres_put(res);
 }
 
-void __dlm_insert_lockres(struct dlm_ctxt *dlm,
-		       struct dlm_lock_resource *res)
+void __dlm_insert_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
 {
 	struct hlist_head *bucket;
 	struct qstr *q;
@@ -180,6 +182,9 @@ void __dlm_insert_lockres(struct dlm_ctxt *dlm,
 	dlm_lockres_get(res);
 
 	hlist_add_head(&res->hash_node, bucket);
+
+	mlog(0, "%s: Hash res %.*s\n", dlm->name, res->lockname.len,
+	     res->lockname.name);
 }
 
 struct dlm_lock_resource * __dlm_lookup_lockres_full(struct dlm_ctxt *dlm,
@@ -539,17 +544,17 @@ again:
 
 static void __dlm_print_nodes(struct dlm_ctxt *dlm)
 {
-	int node = -1;
+	int node = -1, num = 0;
 
 	assert_spin_locked(&dlm->spinlock);
 
-	printk(KERN_NOTICE "o2dlm: Nodes in domain %s: ", dlm->name);
-
+	printk("( ");
 	while ((node = find_next_bit(dlm->domain_map, O2NM_MAX_NODES,
 				     node + 1)) < O2NM_MAX_NODES) {
 		printk("%d ", node);
+		++num;
 	}
-	printk("\n");
+	printk(") %u nodes\n", num);
 }
 
 static int dlm_exit_domain_handler(struct o2net_msg *msg, u32 len, void *data,
@@ -566,11 +571,10 @@ static int dlm_exit_domain_handler(struct o2net_msg *msg, u32 len, void *data,
 
 	node = exit_msg->node_idx;
 
-	printk(KERN_NOTICE "o2dlm: Node %u leaves domain %s\n", node, dlm->name);
-
 	spin_lock(&dlm->spinlock);
 	clear_bit(node, dlm->domain_map);
 	clear_bit(node, dlm->exit_domain_map);
+	printk(KERN_NOTICE "o2dlm: Node %u leaves domain %s ", node, dlm->name);
 	__dlm_print_nodes(dlm);
 
 	/* notify anything attached to the heartbeat events */
@@ -755,6 +759,7 @@ void dlm_unregister_domain(struct dlm_ctxt *dlm)
 
 		dlm_mark_domain_leaving(dlm);
 		dlm_leave_domain(dlm);
+		printk(KERN_NOTICE "o2dlm: Leaving domain %s\n", dlm->name);
 		dlm_force_free_mles(dlm);
 		dlm_complete_dlm_shutdown(dlm);
 	}
@@ -970,7 +975,7 @@ static int dlm_assert_joined_handler(struct o2net_msg *msg, u32 len, void *data,
 		clear_bit(assert->node_idx, dlm->exit_domain_map);
 		__dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN);
 
-		printk(KERN_NOTICE "o2dlm: Node %u joins domain %s\n",
+		printk(KERN_NOTICE "o2dlm: Node %u joins domain %s ",
 		       assert->node_idx, dlm->name);
 		__dlm_print_nodes(dlm);
 
@@ -1701,8 +1706,10 @@ static int dlm_try_to_join_domain(struct dlm_ctxt *dlm)
 bail:
 	spin_lock(&dlm->spinlock);
 	__dlm_set_joining_node(dlm, DLM_LOCK_RES_OWNER_UNKNOWN);
-	if (!status)
+	if (!status) {
+		printk(KERN_NOTICE "o2dlm: Joining domain %s ", dlm->name);
 		__dlm_print_nodes(dlm);
+	}
 	spin_unlock(&dlm->spinlock);
 
 	if (ctxt) {
@@ -2131,13 +2138,6 @@ struct dlm_ctxt * dlm_register_domain(const char *domain,
 		goto leave;
 	}
 
-	if (!o2hb_check_local_node_heartbeating()) {
-		mlog(ML_ERROR, "the local node has not been configured, or is "
-		     "not heartbeating\n");
-		ret = -EPROTO;
-		goto leave;
-	}
-
 	mlog(0, "register called for domain \"%s\"\n", domain);
 
 retry:
diff --git a/fs/ocfs2/dlm/dlmlock.c b/fs/ocfs2/dlm/dlmlock.c
index 8d39e0fd6..975810b 100644
--- a/fs/ocfs2/dlm/dlmlock.c
+++ b/fs/ocfs2/dlm/dlmlock.c
@@ -183,10 +183,6 @@ static enum dlm_status dlmlock_master(struct dlm_ctxt *dlm,
 			kick_thread = 1;
 		}
 	}
-	/* reduce the inflight count, this may result in the lockres
-	 * being purged below during calc_usage */
-	if (lock->ml.node == dlm->node_num)
-		dlm_lockres_drop_inflight_ref(dlm, res);
 
 	spin_unlock(&res->spinlock);
 	wake_up(&res->wq);
@@ -231,10 +227,16 @@ static enum dlm_status dlmlock_remote(struct dlm_ctxt *dlm,
 	     lock->ml.type, res->lockname.len,
 	     res->lockname.name, flags);
 
+	/*
+	 * Wait if resource is getting recovered, remastered, etc.
+	 * If the resource was remastered and new owner is self, then exit.
+	 */
 	spin_lock(&res->spinlock);
-
-	/* will exit this call with spinlock held */
 	__dlm_wait_on_lockres(res);
+	if (res->owner == dlm->node_num) {
+		spin_unlock(&res->spinlock);
+		return DLM_RECOVERING;
+	}
 	res->state |= DLM_LOCK_RES_IN_PROGRESS;
 
 	/* add lock to local (secondary) queue */
@@ -319,27 +321,23 @@ static enum dlm_status dlm_send_remote_lock_request(struct dlm_ctxt *dlm,
 	tmpret = o2net_send_message(DLM_CREATE_LOCK_MSG, dlm->key, &create,
 				    sizeof(create), res->owner, &status);
 	if (tmpret >= 0) {
-		// successfully sent and received
-		ret = status;  // this is already a dlm_status
+		ret = status;
 		if (ret == DLM_REJECTED) {
-			mlog(ML_ERROR, "%s:%.*s: BUG.  this is a stale lockres "
-			     "no longer owned by %u.  that node is coming back "
-			     "up currently.\n", dlm->name, create.namelen,
+			mlog(ML_ERROR, "%s: res %.*s, Stale lockres no longer "
+			     "owned by node %u. That node is coming back up "
+			     "currently.\n", dlm->name, create.namelen,
 			     create.name, res->owner);
 			dlm_print_one_lock_resource(res);
 			BUG();
 		}
 	} else {
-		mlog(ML_ERROR, "Error %d when sending message %u (key 0x%x) to "
-		     "node %u\n", tmpret, DLM_CREATE_LOCK_MSG, dlm->key,
-		     res->owner);
-		if (dlm_is_host_down(tmpret)) {
+		mlog(ML_ERROR, "%s: res %.*s, Error %d send CREATE LOCK to "
+		     "node %u\n", dlm->name, create.namelen, create.name,
+		     tmpret, res->owner);
+		if (dlm_is_host_down(tmpret))
 			ret = DLM_RECOVERING;
-			mlog(0, "node %u died so returning DLM_RECOVERING "
-			     "from lock message!\n", res->owner);
-		} else {
+		else
 			ret = dlm_err_to_dlm_status(tmpret);
-		}
 	}
 
 	return ret;
@@ -440,7 +438,7 @@ struct dlm_lock * dlm_new_lock(int type, u8 node, u64 cookie,
 		/* zero memory only if kernel-allocated */
 		lksb = kzalloc(sizeof(*lksb), GFP_NOFS);
 		if (!lksb) {
-			kfree(lock);
+			kmem_cache_free(dlm_lock_cache, lock);
 			return NULL;
 		}
 		kernel_allocated = 1;
@@ -718,18 +716,10 @@ retry_lock:
 
 		if (status == DLM_RECOVERING || status == DLM_MIGRATING ||
 		    status == DLM_FORWARD) {
-			mlog(0, "retrying lock with migration/"
-			     "recovery/in progress\n");
 			msleep(100);
-			/* no waiting for dlm_reco_thread */
 			if (recovery) {
 				if (status != DLM_RECOVERING)
 					goto retry_lock;
-
-				mlog(0, "%s: got RECOVERING "
-				     "for $RECOVERY lock, master "
-				     "was %u\n", dlm->name,
-				     res->owner);
 				/* wait to see the node go down, then
 				 * drop down and allow the lockres to
 				 * get cleaned up.  need to remaster. */
@@ -741,6 +731,14 @@ retry_lock:
 			}
 		}
 
+		/* Inflight taken in dlm_get_lock_resource() is dropped here */
+		spin_lock(&res->spinlock);
+		dlm_lockres_drop_inflight_ref(dlm, res);
+		spin_unlock(&res->spinlock);
+
+		dlm_lockres_calc_usage(dlm, res);
+		dlm_kick_thread(dlm, res);
+
 		if (status != DLM_NORMAL) {
 			lock->lksb->flags &= ~DLM_LKSB_GET_LVB;
 			if (status != DLM_NOTQUEUED)
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 11eefb8..005261c 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -631,39 +631,54 @@ error:
 	return NULL;
 }
 
-void __dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
-				   struct dlm_lock_resource *res,
-				   int new_lockres,
-				   const char *file,
-				   int line)
+void dlm_lockres_set_refmap_bit(struct dlm_ctxt *dlm,
+				struct dlm_lock_resource *res, int bit)
 {
-	if (!new_lockres)
-		assert_spin_locked(&res->spinlock);
+	assert_spin_locked(&res->spinlock);
+
+	mlog(0, "res %.*s, set node %u, %ps()\n", res->lockname.len,
+	     res->lockname.name, bit, __builtin_return_address(0));
+
+	set_bit(bit, res->refmap);
+}
+
+void dlm_lockres_clear_refmap_bit(struct dlm_ctxt *dlm,
+				  struct dlm_lock_resource *res, int bit)
+{
+	assert_spin_locked(&res->spinlock);
+
+	mlog(0, "res %.*s, clr node %u, %ps()\n", res->lockname.len,
+	     res->lockname.name, bit, __builtin_return_address(0));
+
+	clear_bit(bit, res->refmap);
+}
+
+
+void dlm_lockres_grab_inflight_ref(struct dlm_ctxt *dlm,
+				   struct dlm_lock_resource *res)
+{
+	assert_spin_locked(&res->spinlock);
 
-	if (!test_bit(dlm->node_num, res->refmap)) {
-		BUG_ON(res->inflight_locks != 0);
-		dlm_lockres_set_refmap_bit(dlm->node_num, res);
-	}
 	res->inflight_locks++;
-	mlog(0, "%s:%.*s: inflight++: now %u\n",
-	     dlm->name, res->lockname.len, res->lockname.name,
-	     res->inflight_locks);
+
+	mlog(0, "%s: res %.*s, inflight++: now %u, %ps()\n", dlm->name,
+	     res->lockname.len, res->lockname.name, res->inflight_locks,
+	     __builtin_return_address(0));
 }
 
-void __dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
-				   struct dlm_lock_resource *res,
-				   const char *file,
-				   int line)
+void dlm_lockres_drop_inflight_ref(struct dlm_ctxt *dlm,
+				   struct dlm_lock_resource *res)
 {
 	assert_spin_locked(&res->spinlock);
 
 	BUG_ON(res->inflight_locks == 0);
+
 	res->inflight_locks--;
-	mlog(0, "%s:%.*s: inflight--: now %u\n",
-	     dlm->name, res->lockname.len, res->lockname.name,
-	     res->inflight_locks);
-	if (res->inflight_locks == 0)
-		dlm_lockres_clear_refmap_bit(dlm->node_num, res);
+
+	mlog(0, "%s: res %.*s, inflight--: now %u, %ps()\n", dlm->name,
+	     res->lockname.len, res->lockname.name, res->inflight_locks,
+	     __builtin_return_address(0));
+
 	wake_up(&res->wq);
 }
 
@@ -697,7 +712,6 @@ struct dlm_lock_resource * dlm_get_lock_resource(struct dlm_ctxt *dlm,
 	unsigned int hash;
 	int tries = 0;
 	int bit, wait_on_recovery = 0;
-	int drop_inflight_if_nonlocal = 0;
 
 	BUG_ON(!lockid);
 
@@ -709,36 +723,33 @@ lookup:
 	spin_lock(&dlm->spinlock);
 	tmpres = __dlm_lookup_lockres_full(dlm, lockid, namelen, hash);
 	if (tmpres) {
-		int dropping_ref = 0;
-
 		spin_unlock(&dlm->spinlock);
-
 		spin_lock(&tmpres->spinlock);
-		/* We wait for the other thread that is mastering the resource */
+		/* Wait on the thread that is mastering the resource */
 		if (tmpres->owner == DLM_LOCK_RES_OWNER_UNKNOWN) {
 			__dlm_wait_on_lockres(tmpres);
 			BUG_ON(tmpres->owner == DLM_LOCK_RES_OWNER_UNKNOWN);
+			spin_unlock(&tmpres->spinlock);
+			dlm_lockres_put(tmpres);
+			tmpres = NULL;
+			goto lookup;
 		}
 
-		if (tmpres->owner == dlm->node_num) {
-			BUG_ON(tmpres->state & DLM_LOCK_RES_DROPPING_REF);
-			dlm_lockres_grab_inflight_ref(dlm, tmpres);
-		} else if (tmpres->state & DLM_LOCK_RES_DROPPING_REF)
-			dropping_ref = 1;
-		spin_unlock(&tmpres->spinlock);
-
-		/* wait until done messaging the master, drop our ref to allow
-		 * the lockres to be purged, start over. */
-		if (dropping_ref) {
-			spin_lock(&tmpres->spinlock);
-			__dlm_wait_on_lockres_flags(tmpres, DLM_LOCK_RES_DROPPING_REF);
+		/* Wait on the resource purge to complete before continuing */
+		if (tmpres->state & DLM_LOCK_RES_DROPPING_REF) {
+			BUG_ON(tmpres->owner == dlm->node_num);
+			__dlm_wait_on_lockres_flags(tmpres,
+						    DLM_LOCK_RES_DROPPING_REF);
 			spin_unlock(&tmpres->spinlock);
 			dlm_lockres_put(tmpres);
 			tmpres = NULL;
 			goto lookup;
 		}
 
-		mlog(0, "found in hash!\n");
+		/* Grab inflight ref to pin the resource */
+		dlm_lockres_grab_inflight_ref(dlm, tmpres);
+
+		spin_unlock(&tmpres->spinlock);
 		if (res)
 			dlm_lockres_put(res);
 		res = tmpres;
@@ -829,8 +840,8 @@ lookup:
 		 * but they might own this lockres.  wait on them. */
 		bit = find_next_bit(dlm->recovery_map, O2NM_MAX_NODES, 0);
 		if (bit < O2NM_MAX_NODES) {
-			mlog(ML_NOTICE, "%s:%.*s: at least one node (%d) to "
-			     "recover before lock mastery can begin\n",
+			mlog(0, "%s: res %.*s, At least one node (%d) "
+			     "to recover before lock mastery can begin\n",
 			     dlm->name, namelen, (char *)lockid, bit);
 			wait_on_recovery = 1;
 		}
@@ -843,12 +854,11 @@ lookup:
 
 	/* finally add the lockres to its hash bucket */
 	__dlm_insert_lockres(dlm, res);
-	/* since this lockres is new it doesn't not require the spinlock */
-	dlm_lockres_grab_inflight_ref_new(dlm, res);
 
-	/* if this node does not become the master make sure to drop
-	 * this inflight reference below */
-	drop_inflight_if_nonlocal = 1;
+	/* Grab inflight ref to pin the resource */
+	spin_lock(&res->spinlock);
+	dlm_lockres_grab_inflight_ref(dlm, res);
+	spin_unlock(&res->spinlock);
 
 	/* get an extra ref on the mle in case this is a BLOCK
 	 * if so, the creator of the BLOCK may try to put the last
@@ -864,8 +874,8 @@ redo_request:
 		 * dlm spinlock would be detectable be a change on the mle,
 		 * so we only need to clear out the recovery map once. */
 		if (dlm_is_recovery_lock(lockid, namelen)) {
-			mlog(ML_NOTICE, "%s: recovery map is not empty, but "
-			     "must master $RECOVERY lock now\n", dlm->name);
+			mlog(0, "%s: Recovery map is not empty, but must "
+			     "master $RECOVERY lock now\n", dlm->name);
 			if (!dlm_pre_master_reco_lockres(dlm, res))
 				wait_on_recovery = 0;
 			else {
@@ -883,8 +893,8 @@ redo_request:
 		spin_lock(&dlm->spinlock);
 		bit = find_next_bit(dlm->recovery_map, O2NM_MAX_NODES, 0);
 		if (bit < O2NM_MAX_NODES) {
-			mlog(ML_NOTICE, "%s:%.*s: at least one node (%d) to "
-			     "recover before lock mastery can begin\n",
+			mlog(0, "%s: res %.*s, At least one node (%d) "
+			     "to recover before lock mastery can begin\n",
 			     dlm->name, namelen, (char *)lockid, bit);
 			wait_on_recovery = 1;
 		} else
@@ -913,8 +923,8 @@ redo_request:
 			 * yet, keep going until it does.  this is how the
 			 * master will know that asserts are needed back to
 			 * the lower nodes. */
-			mlog(0, "%s:%.*s: requests only up to %u but master "
-			     "is %u, keep going\n", dlm->name, namelen,
+			mlog(0, "%s: res %.*s, Requests only up to %u but "
+			     "master is %u, keep going\n", dlm->name, namelen,
 			     lockid, nodenum, mle->master);
 		}
 	}
@@ -924,13 +934,12 @@ wait:
 	ret = dlm_wait_for_lock_mastery(dlm, res, mle, &blocked);
 	if (ret < 0) {
 		wait_on_recovery = 1;
-		mlog(0, "%s:%.*s: node map changed, redo the "
-		     "master request now, blocked=%d\n",
-		     dlm->name, res->lockname.len,
+		mlog(0, "%s: res %.*s, Node map changed, redo the master "
+		     "request now, blocked=%d\n", dlm->name, res->lockname.len,
 		     res->lockname.name, blocked);
 		if (++tries > 20) {
-			mlog(ML_ERROR, "%s:%.*s: spinning on "
-			     "dlm_wait_for_lock_mastery, blocked=%d\n",
+			mlog(ML_ERROR, "%s: res %.*s, Spinning on "
+			     "dlm_wait_for_lock_mastery, blocked = %d\n",
 			     dlm->name, res->lockname.len,
 			     res->lockname.name, blocked);
 			dlm_print_one_lock_resource(res);
@@ -940,7 +949,8 @@ wait:
 		goto redo_request;
 	}
 
-	mlog(0, "lockres mastered by %u\n", res->owner);
+	mlog(0, "%s: res %.*s, Mastered by %u\n", dlm->name, res->lockname.len,
+	     res->lockname.name, res->owner);
 	/* make sure we never continue without this */
 	BUG_ON(res->owner == O2NM_MAX_NODES);
 
@@ -952,8 +962,6 @@ wait:
 
 wake_waiters:
 	spin_lock(&res->spinlock);
-	if (res->owner != dlm->node_num && drop_inflight_if_nonlocal)
-		dlm_lockres_drop_inflight_ref(dlm, res);
 	res->state &= ~DLM_LOCK_RES_IN_PROGRESS;
 	spin_unlock(&res->spinlock);
 	wake_up(&res->wq);
@@ -1426,9 +1434,7 @@ way_up_top:
 		}
 
 		if (res->owner == dlm->node_num) {
-			mlog(0, "%s:%.*s: setting bit %u in refmap\n",
-			     dlm->name, namelen, name, request->node_idx);
-			dlm_lockres_set_refmap_bit(request->node_idx, res);
+			dlm_lockres_set_refmap_bit(dlm, res, request->node_idx);
 			spin_unlock(&res->spinlock);
 			response = DLM_MASTER_RESP_YES;
 			if (mle)
@@ -1493,10 +1499,8 @@ way_up_top:
 				 * go back and clean the mles on any
 				 * other nodes */
 				dispatch_assert = 1;
-				dlm_lockres_set_refmap_bit(request->node_idx, res);
-				mlog(0, "%s:%.*s: setting bit %u in refmap\n",
-				     dlm->name, namelen, name,
-				     request->node_idx);
+				dlm_lockres_set_refmap_bit(dlm, res,
+							   request->node_idx);
 			} else
 				response = DLM_MASTER_RESP_NO;
 		} else {
@@ -1702,7 +1706,7 @@ again:
 			     "lockres, set the bit in the refmap\n",
 			     namelen, lockname, to);
 			spin_lock(&res->spinlock);
-			dlm_lockres_set_refmap_bit(to, res);
+			dlm_lockres_set_refmap_bit(dlm, res, to);
 			spin_unlock(&res->spinlock);
 		}
 	}
@@ -2187,8 +2191,6 @@ int dlm_drop_lockres_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
 	namelen = res->lockname.len;
 	BUG_ON(namelen > O2NM_MAX_NAME_LEN);
 
-	mlog(0, "%s:%.*s: sending deref to %d\n",
-	     dlm->name, namelen, lockname, res->owner);
 	memset(&deref, 0, sizeof(deref));
 	deref.node_idx = dlm->node_num;
 	deref.namelen = namelen;
@@ -2197,14 +2199,12 @@ int dlm_drop_lockres_ref(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
 	ret = o2net_send_message(DLM_DEREF_LOCKRES_MSG, dlm->key,
 				 &deref, sizeof(deref), res->owner, &r);
 	if (ret < 0)
-		mlog(ML_ERROR, "Error %d when sending message %u (key 0x%x) to "
-		     "node %u\n", ret, DLM_DEREF_LOCKRES_MSG, dlm->key,
-		     res->owner);
+		mlog(ML_ERROR, "%s: res %.*s, error %d send DEREF to node %u\n",
+		     dlm->name, namelen, lockname, ret, res->owner);
 	else if (r < 0) {
 		/* BAD.  other node says I did not have a ref. */
-		mlog(ML_ERROR,"while dropping ref on %s:%.*s "
-		    "(master=%u) got %d.\n", dlm->name, namelen,
-		    lockname, res->owner, r);
+		mlog(ML_ERROR, "%s: res %.*s, DEREF to node %u got %d\n",
+		     dlm->name, namelen, lockname, res->owner, r);
 		dlm_print_one_lock_resource(res);
 		BUG();
 	}
@@ -2260,7 +2260,7 @@ int dlm_deref_lockres_handler(struct o2net_msg *msg, u32 len, void *data,
 	else {
 		BUG_ON(res->state & DLM_LOCK_RES_DROPPING_REF);
 		if (test_bit(node, res->refmap)) {
-			dlm_lockres_clear_refmap_bit(node, res);
+			dlm_lockres_clear_refmap_bit(dlm, res, node);
 			cleared = 1;
 		}
 	}
@@ -2320,7 +2320,7 @@ static void dlm_deref_lockres_worker(struct dlm_work_item *item, void *data)
 	BUG_ON(res->state & DLM_LOCK_RES_DROPPING_REF);
 	if (test_bit(node, res->refmap)) {
 		__dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_SETREF_INPROG);
-		dlm_lockres_clear_refmap_bit(node, res);
+		dlm_lockres_clear_refmap_bit(dlm, res, node);
 		cleared = 1;
 	}
 	spin_unlock(&res->spinlock);
@@ -2802,7 +2802,8 @@ static void dlm_remove_nonlocal_locks(struct dlm_ctxt *dlm,
 				BUG_ON(!list_empty(&lock->bast_list));
 				BUG_ON(lock->ast_pending);
 				BUG_ON(lock->bast_pending);
-				dlm_lockres_clear_refmap_bit(lock->ml.node, res);
+				dlm_lockres_clear_refmap_bit(dlm, res,
+							     lock->ml.node);
 				list_del_init(&lock->list);
 				dlm_lock_put(lock);
 				/* In a normal unlock, we would have added a
@@ -2823,7 +2824,7 @@ static void dlm_remove_nonlocal_locks(struct dlm_ctxt *dlm,
 			mlog(0, "%s:%.*s: node %u had a ref to this "
 			     "migrating lockres, clearing\n", dlm->name,
 			     res->lockname.len, res->lockname.name, bit);
-			dlm_lockres_clear_refmap_bit(bit, res);
+			dlm_lockres_clear_refmap_bit(dlm, res, bit);
 		}
 		bit++;
 	}
@@ -2916,9 +2917,9 @@ static int dlm_do_migrate_request(struct dlm_ctxt *dlm,
 					 &migrate, sizeof(migrate), nodenum,
 					 &status);
 		if (ret < 0) {
-			mlog(ML_ERROR, "Error %d when sending message %u (key "
-			     "0x%x) to node %u\n", ret, DLM_MIGRATE_REQUEST_MSG,
-			     dlm->key, nodenum);
+			mlog(ML_ERROR, "%s: res %.*s, Error %d send "
+			     "MIGRATE_REQUEST to node %u\n", dlm->name,
+			     migrate.namelen, migrate.name, ret, nodenum);
 			if (!dlm_is_host_down(ret)) {
 				mlog(ML_ERROR, "unhandled error=%d!\n", ret);
 				BUG();
@@ -2937,7 +2938,7 @@ static int dlm_do_migrate_request(struct dlm_ctxt *dlm,
 			     dlm->name, res->lockname.len, res->lockname.name,
 			     nodenum);
 			spin_lock(&res->spinlock);
-			dlm_lockres_set_refmap_bit(nodenum, res);
+			dlm_lockres_set_refmap_bit(dlm, res, nodenum);
 			spin_unlock(&res->spinlock);
 		}
 	}
@@ -3271,7 +3272,7 @@ int dlm_finish_migration(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
 	 * mastery reference here since old_master will briefly have
 	 * a reference after the migration completes */
 	spin_lock(&res->spinlock);
-	dlm_lockres_set_refmap_bit(old_master, res);
+	dlm_lockres_set_refmap_bit(dlm, res, old_master);
 	spin_unlock(&res->spinlock);
 
 	mlog(0, "now time to do a migrate request to other nodes\n");
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index 7efab6d..01ebfd0 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -362,40 +362,38 @@ static int dlm_is_node_recovered(struct dlm_ctxt *dlm, u8 node)
 }
 
 
-int dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout)
+void dlm_wait_for_node_death(struct dlm_ctxt *dlm, u8 node, int timeout)
 {
-	if (timeout) {
-		mlog(ML_NOTICE, "%s: waiting %dms for notification of "
-		     "death of node %u\n", dlm->name, timeout, node);
+	if (dlm_is_node_dead(dlm, node))
+		return;
+
+	printk(KERN_NOTICE "o2dlm: Waiting on the death of node %u in "
+	       "domain %s\n", node, dlm->name);
+
+	if (timeout)
 		wait_event_timeout(dlm->dlm_reco_thread_wq,
-			   dlm_is_node_dead(dlm, node),
-			   msecs_to_jiffies(timeout));
-	} else {
-		mlog(ML_NOTICE, "%s: waiting indefinitely for notification "
-		     "of death of node %u\n", dlm->name, node);
+				   dlm_is_node_dead(dlm, node),
+				   msecs_to_jiffies(timeout));
+	else
 		wait_event(dlm->dlm_reco_thread_wq,
 			   dlm_is_node_dead(dlm, node));
-	}
-	/* for now, return 0 */
-	return 0;
 }
 
-int dlm_wait_for_node_recovery(struct dlm_ctxt *dlm, u8 node, int timeout)
+void dlm_wait_for_node_recovery(struct dlm_ctxt *dlm, u8 node, int timeout)
 {
-	if (timeout) {
-		mlog(0, "%s: waiting %dms for notification of "
-		     "recovery of node %u\n", dlm->name, timeout, node);
+	if (dlm_is_node_recovered(dlm, node))
+		return;
+
+	printk(KERN_NOTICE "o2dlm: Waiting on the recovery of node %u in "
+	       "domain %s\n", node, dlm->name);
+
+	if (timeout)
 		wait_event_timeout(dlm->dlm_reco_thread_wq,
-			   dlm_is_node_recovered(dlm, node),
-			   msecs_to_jiffies(timeout));
-	} else {
-		mlog(0, "%s: waiting indefinitely for notification "
-		     "of recovery of node %u\n", dlm->name, node);
+				   dlm_is_node_recovered(dlm, node),
+				   msecs_to_jiffies(timeout));
+	else
 		wait_event(dlm->dlm_reco_thread_wq,
 			   dlm_is_node_recovered(dlm, node));
-	}
-	/* for now, return 0 */
-	return 0;
 }
 
 /* callers of the top-level api calls (dlmlock/dlmunlock) should
@@ -430,6 +428,8 @@ static void dlm_begin_recovery(struct dlm_ctxt *dlm)
 {
 	spin_lock(&dlm->spinlock);
 	BUG_ON(dlm->reco.state & DLM_RECO_STATE_ACTIVE);
+	printk(KERN_NOTICE "o2dlm: Begin recovery on domain %s for node %u\n",
+	       dlm->name, dlm->reco.dead_node);
 	dlm->reco.state |= DLM_RECO_STATE_ACTIVE;
 	spin_unlock(&dlm->spinlock);
 }
@@ -440,9 +440,18 @@ static void dlm_end_recovery(struct dlm_ctxt *dlm)
 	BUG_ON(!(dlm->reco.state & DLM_RECO_STATE_ACTIVE));
 	dlm->reco.state &= ~DLM_RECO_STATE_ACTIVE;
 	spin_unlock(&dlm->spinlock);
+	printk(KERN_NOTICE "o2dlm: End recovery on domain %s\n", dlm->name);
 	wake_up(&dlm->reco.event);
 }
 
+static void dlm_print_recovery_master(struct dlm_ctxt *dlm)
+{
+	printk(KERN_NOTICE "o2dlm: Node %u (%s) is the Recovery Master for the "
+	       "dead node %u in domain %s\n", dlm->reco.new_master,
+	       (dlm->node_num == dlm->reco.new_master ? "me" : "he"),
+	       dlm->reco.dead_node, dlm->name);
+}
+
 static int dlm_do_recovery(struct dlm_ctxt *dlm)
 {
 	int status = 0;
@@ -505,9 +514,8 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm)
 		}
 		mlog(0, "another node will master this recovery session.\n");
 	}
-	mlog(0, "dlm=%s (%d), new_master=%u, this node=%u, dead_node=%u\n",
-	     dlm->name, task_pid_nr(dlm->dlm_reco_thread_task), dlm->reco.new_master,
-	     dlm->node_num, dlm->reco.dead_node);
+
+	dlm_print_recovery_master(dlm);
 
 	/* it is safe to start everything back up here
 	 * because all of the dead node's lock resources
@@ -518,15 +526,13 @@ static int dlm_do_recovery(struct dlm_ctxt *dlm)
 	return 0;
 
 master_here:
-	mlog(ML_NOTICE, "(%d) Node %u is the Recovery Master for the Dead Node "
-	     "%u for Domain %s\n", task_pid_nr(dlm->dlm_reco_thread_task),
-	     dlm->node_num, dlm->reco.dead_node, dlm->name);
+	dlm_print_recovery_master(dlm);
 
 	status = dlm_remaster_locks(dlm, dlm->reco.dead_node);
 	if (status < 0) {
 		/* we should never hit this anymore */
-		mlog(ML_ERROR, "error %d remastering locks for node %u, "
-		     "retrying.\n", status, dlm->reco.dead_node);
+		mlog(ML_ERROR, "%s: Error %d remastering locks for node %u, "
+		     "retrying.\n", dlm->name, status, dlm->reco.dead_node);
 		/* yield a bit to allow any final network messages
 		 * to get handled on remaining nodes */
 		msleep(100);
@@ -567,7 +573,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
 		BUG_ON(ndata->state != DLM_RECO_NODE_DATA_INIT);
 		ndata->state = DLM_RECO_NODE_DATA_REQUESTING;
 
-		mlog(0, "requesting lock info from node %u\n",
+		mlog(0, "%s: Requesting lock info from node %u\n", dlm->name,
 		     ndata->node_num);
 
 		if (ndata->node_num == dlm->node_num) {
@@ -640,7 +646,7 @@ static int dlm_remaster_locks(struct dlm_ctxt *dlm, u8 dead_node)
 		spin_unlock(&dlm_reco_state_lock);
 	}
 
-	mlog(0, "done requesting all lock info\n");
+	mlog(0, "%s: Done requesting all lock info\n", dlm->name);
 
 	/* nodes should be sending reco data now
 	 * just need to wait */
@@ -802,10 +808,9 @@ static int dlm_request_all_locks(struct dlm_ctxt *dlm, u8 request_from,
 
 	/* negative status is handled by caller */
 	if (ret < 0)
-		mlog(ML_ERROR, "Error %d when sending message %u (key "
-		     "0x%x) to node %u\n", ret, DLM_LOCK_REQUEST_MSG,
-		     dlm->key, request_from);
-
+		mlog(ML_ERROR, "%s: Error %d send LOCK_REQUEST to node %u "
+		     "to recover dead node %u\n", dlm->name, ret,
+		     request_from, dead_node);
 	// return from here, then
 	// sleep until all received or error
 	return ret;
@@ -956,9 +961,9 @@ static int dlm_send_all_done_msg(struct dlm_ctxt *dlm, u8 dead_node, u8 send_to)
 	ret = o2net_send_message(DLM_RECO_DATA_DONE_MSG, dlm->key, &done_msg,
 				 sizeof(done_msg), send_to, &tmpret);
 	if (ret < 0) {
-		mlog(ML_ERROR, "Error %d when sending message %u (key "
-		     "0x%x) to node %u\n", ret, DLM_RECO_DATA_DONE_MSG,
-		     dlm->key, send_to);
+		mlog(ML_ERROR, "%s: Error %d send RECO_DATA_DONE to node %u "
+		     "to recover dead node %u\n", dlm->name, ret, send_to,
+		     dead_node);
 		if (!dlm_is_host_down(ret)) {
 			BUG();
 		}
@@ -1127,9 +1132,11 @@ static int dlm_send_mig_lockres_msg(struct dlm_ctxt *dlm,
 	if (ret < 0) {
 		/* XXX: negative status is not handled.
 		 * this will end up killing this node. */
-		mlog(ML_ERROR, "Error %d when sending message %u (key "
-		     "0x%x) to node %u\n", ret, DLM_MIG_LOCKRES_MSG,
-		     dlm->key, send_to);
+		mlog(ML_ERROR, "%s: res %.*s, Error %d send MIG_LOCKRES to "
+		     "node %u (%s)\n", dlm->name, mres->lockname_len,
+		     mres->lockname, ret, send_to,
+		     (orig_flags & DLM_MRES_MIGRATION ?
+		      "migration" : "recovery"));
 	} else {
 		/* might get an -ENOMEM back here */
 		ret = status;
@@ -1767,7 +1774,7 @@ static int dlm_process_recovery_data(struct dlm_ctxt *dlm,
 			     dlm->name, mres->lockname_len, mres->lockname,
 			     from);
 			spin_lock(&res->spinlock);
-			dlm_lockres_set_refmap_bit(from, res);
+			dlm_lockres_set_refmap_bit(dlm, res, from);
 			spin_unlock(&res->spinlock);
 			added++;
 			break;
@@ -1965,7 +1972,7 @@ skip_lvb:
 			mlog(0, "%s:%.*s: added lock for node %u, "
 			     "setting refmap bit\n", dlm->name,
 			     res->lockname.len, res->lockname.name, ml->node);
-			dlm_lockres_set_refmap_bit(ml->node, res);
+			dlm_lockres_set_refmap_bit(dlm, res, ml->node);
 			added++;
 		}
 		spin_unlock(&res->spinlock);
@@ -2084,6 +2091,9 @@ static void dlm_finish_local_lockres_recovery(struct dlm_ctxt *dlm,
 
 	list_for_each_entry_safe(res, next, &dlm->reco.resources, recovering) {
 		if (res->owner == dead_node) {
+			mlog(0, "%s: res %.*s, Changing owner from %u to %u\n",
+			     dlm->name, res->lockname.len, res->lockname.name,
+			     res->owner, new_master);
 			list_del_init(&res->recovering);
 			spin_lock(&res->spinlock);
 			/* new_master has our reference from
@@ -2105,40 +2115,30 @@ static void dlm_finish_local_lockres_recovery(struct dlm_ctxt *dlm,
 	for (i = 0; i < DLM_HASH_BUCKETS; i++) {
 		bucket = dlm_lockres_hash(dlm, i);
 		hlist_for_each_entry(res, hash_iter, bucket, hash_node) {
-			if (res->state & DLM_LOCK_RES_RECOVERING) {
-				if (res->owner == dead_node) {
-					mlog(0, "(this=%u) res %.*s owner=%u "
-					     "was not on recovering list, but "
-					     "clearing state anyway\n",
-					     dlm->node_num, res->lockname.len,
-					     res->lockname.name, new_master);
-				} else if (res->owner == dlm->node_num) {
-					mlog(0, "(this=%u) res %.*s owner=%u "
-					     "was not on recovering list, "
-					     "owner is THIS node, clearing\n",
-					     dlm->node_num, res->lockname.len,
-					     res->lockname.name, new_master);
-				} else
-					continue;
+			if (!(res->state & DLM_LOCK_RES_RECOVERING))
+				continue;
 
-				if (!list_empty(&res->recovering)) {
-					mlog(0, "%s:%.*s: lockres was "
-					     "marked RECOVERING, owner=%u\n",
-					     dlm->name, res->lockname.len,
-					     res->lockname.name, res->owner);
-					list_del_init(&res->recovering);
-					dlm_lockres_put(res);
-				}
-				spin_lock(&res->spinlock);
-				/* new_master has our reference from
-				 * the lock state sent during recovery */
-				dlm_change_lockres_owner(dlm, res, new_master);
-				res->state &= ~DLM_LOCK_RES_RECOVERING;
-				if (__dlm_lockres_has_locks(res))
-					__dlm_dirty_lockres(dlm, res);
-				spin_unlock(&res->spinlock);
-				wake_up(&res->wq);
+			if (res->owner != dead_node &&
+			    res->owner != dlm->node_num)
+				continue;
+
+			if (!list_empty(&res->recovering)) {
+				list_del_init(&res->recovering);
+				dlm_lockres_put(res);
 			}
+
+			/* new_master has our reference from
+			 * the lock state sent during recovery */
+			mlog(0, "%s: res %.*s, Changing owner from %u to %u\n",
+			     dlm->name, res->lockname.len, res->lockname.name,
+			     res->owner, new_master);
+			spin_lock(&res->spinlock);
+			dlm_change_lockres_owner(dlm, res, new_master);
+			res->state &= ~DLM_LOCK_RES_RECOVERING;
+			if (__dlm_lockres_has_locks(res))
+				__dlm_dirty_lockres(dlm, res);
+			spin_unlock(&res->spinlock);
+			wake_up(&res->wq);
 		}
 	}
 }
@@ -2252,12 +2252,12 @@ static void dlm_free_dead_locks(struct dlm_ctxt *dlm,
 			     res->lockname.len, res->lockname.name, freed, dead_node);
 			__dlm_print_one_lock_resource(res);
 		}
-		dlm_lockres_clear_refmap_bit(dead_node, res);
+		dlm_lockres_clear_refmap_bit(dlm, res, dead_node);
 	} else if (test_bit(dead_node, res->refmap)) {
 		mlog(0, "%s:%.*s: dead node %u had a ref, but had "
 		     "no locks and had not purged before dying\n", dlm->name,
 		     res->lockname.len, res->lockname.name, dead_node);
-		dlm_lockres_clear_refmap_bit(dead_node, res);
+		dlm_lockres_clear_refmap_bit(dlm, res, dead_node);
 	}
 
 	/* do not kick thread yet */
@@ -2324,9 +2324,9 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 			dlm_revalidate_lvb(dlm, res, dead_node);
 			if (res->owner == dead_node) {
 				if (res->state & DLM_LOCK_RES_DROPPING_REF) {
-					mlog(ML_NOTICE, "Ignore %.*s for "
+					mlog(ML_NOTICE, "%s: res %.*s, Skip "
 					     "recovery as it is being freed\n",
-					     res->lockname.len,
+					     dlm->name, res->lockname.len,
 					     res->lockname.name);
 				} else
 					dlm_move_lockres_to_recovery_list(dlm,
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 1d6d1d2..e73c833 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -94,24 +94,26 @@ int __dlm_lockres_unused(struct dlm_lock_resource *res)
 {
 	int bit;
 
+	assert_spin_locked(&res->spinlock);
+
 	if (__dlm_lockres_has_locks(res))
 		return 0;
 
+	/* Locks are in the process of being created */
+	if (res->inflight_locks)
+		return 0;
+
 	if (!list_empty(&res->dirty) || res->state & DLM_LOCK_RES_DIRTY)
 		return 0;
 
 	if (res->state & DLM_LOCK_RES_RECOVERING)
 		return 0;
 
+	/* Another node has this resource with this node as the master */
 	bit = find_next_bit(res->refmap, O2NM_MAX_NODES, 0);
 	if (bit < O2NM_MAX_NODES)
 		return 0;
 
-	/*
-	 * since the bit for dlm->node_num is not set, inflight_locks better
-	 * be zero
-	 */
-	BUG_ON(res->inflight_locks != 0);
 	return 1;
 }
 
@@ -185,8 +187,6 @@ static void dlm_purge_lockres(struct dlm_ctxt *dlm,
 		/* clear our bit from the master's refmap, ignore errors */
 		ret = dlm_drop_lockres_ref(dlm, res);
 		if (ret < 0) {
-			mlog(ML_ERROR, "%s: deref %.*s failed %d\n", dlm->name,
-			     res->lockname.len, res->lockname.name, ret);
 			if (!dlm_is_host_down(ret))
 				BUG();
 		}
@@ -209,7 +209,7 @@ static void dlm_purge_lockres(struct dlm_ctxt *dlm,
 		BUG();
 	}
 
-	__dlm_unhash_lockres(res);
+	__dlm_unhash_lockres(dlm, res);
 
 	/* lockres is not in the hash now.  drop the flag and wake up
 	 * any processes waiting in dlm_get_lock_resource. */
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index e1ed5e5..81a4cd2 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -1692,7 +1692,7 @@ int ocfs2_open_lock(struct inode *inode)
 	mlog(0, "inode %llu take PRMODE open lock\n",
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno);
 
-	if (ocfs2_mount_local(osb))
+	if (ocfs2_is_hard_readonly(osb) || ocfs2_mount_local(osb))
 		goto out;
 
 	lockres = &OCFS2_I(inode)->ip_open_lockres;
@@ -1718,6 +1718,12 @@ int ocfs2_try_open_lock(struct inode *inode, int write)
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
 	     write ? "EXMODE" : "PRMODE");
 
+	if (ocfs2_is_hard_readonly(osb)) {
+		if (write)
+			status = -EROFS;
+		goto out;
+	}
+
 	if (ocfs2_mount_local(osb))
 		goto out;
 
@@ -2298,7 +2304,7 @@ int ocfs2_inode_lock_full_nested(struct inode *inode,
 	if (ocfs2_is_hard_readonly(osb)) {
 		if (ex)
 			status = -EROFS;
-		goto bail;
+		goto getbh;
 	}
 
 	if (ocfs2_mount_local(osb))
@@ -2356,7 +2362,7 @@ local:
 			mlog_errno(status);
 		goto bail;
 	}
-
+getbh:
 	if (ret_bh) {
 		status = ocfs2_assign_bh(inode, ret_bh, local_bh);
 		if (status < 0) {
@@ -2628,8 +2634,11 @@ int ocfs2_dentry_lock(struct dentry *dentry, int ex)
 
 	BUG_ON(!dl);
 
-	if (ocfs2_is_hard_readonly(osb))
-		return -EROFS;
+	if (ocfs2_is_hard_readonly(osb)) {
+		if (ex)
+			return -EROFS;
+		return 0;
+	}
 
 	if (ocfs2_mount_local(osb))
 		return 0;
@@ -2647,7 +2656,7 @@ void ocfs2_dentry_unlock(struct dentry *dentry, int ex)
 	struct ocfs2_dentry_lock *dl = dentry->d_fsdata;
 	struct ocfs2_super *osb = OCFS2_SB(dentry->d_sb);
 
-	if (!ocfs2_mount_local(osb))
+	if (!ocfs2_is_hard_readonly(osb) && !ocfs2_mount_local(osb))
 		ocfs2_cluster_unlock(osb, &dl->dl_lockres, level);
 }
 
diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c
index 23457b4..2f5b92e 100644
--- a/fs/ocfs2/extent_map.c
+++ b/fs/ocfs2/extent_map.c
@@ -832,6 +832,102 @@ out:
 	return ret;
 }
 
+int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin)
+{
+	struct inode *inode = file->f_mapping->host;
+	int ret;
+	unsigned int is_last = 0, is_data = 0;
+	u16 cs_bits = OCFS2_SB(inode->i_sb)->s_clustersize_bits;
+	u32 cpos, cend, clen, hole_size;
+	u64 extoff, extlen;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_extent_rec rec;
+
+	BUG_ON(origin != SEEK_DATA && origin != SEEK_HOLE);
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 0);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	down_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+	if (*offset >= inode->i_size) {
+		ret = -ENXIO;
+		goto out_unlock;
+	}
+
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		if (origin == SEEK_HOLE)
+			*offset = inode->i_size;
+		goto out_unlock;
+	}
+
+	clen = 0;
+	cpos = *offset >> cs_bits;
+	cend = ocfs2_clusters_for_bytes(inode->i_sb, inode->i_size);
+
+	while (cpos < cend && !is_last) {
+		ret = ocfs2_get_clusters_nocache(inode, di_bh, cpos, &hole_size,
+						 &rec, &is_last);
+		if (ret) {
+			mlog_errno(ret);
+			goto out_unlock;
+		}
+
+		extoff = cpos;
+		extoff <<= cs_bits;
+
+		if (rec.e_blkno == 0ULL) {
+			clen = hole_size;
+			is_data = 0;
+		} else {
+			clen = le16_to_cpu(rec.e_leaf_clusters) -
+				(cpos - le32_to_cpu(rec.e_cpos));
+			is_data = (rec.e_flags & OCFS2_EXT_UNWRITTEN) ?  0 : 1;
+		}
+
+		if ((!is_data && origin == SEEK_HOLE) ||
+		    (is_data && origin == SEEK_DATA)) {
+			if (extoff > *offset)
+				*offset = extoff;
+			goto out_unlock;
+		}
+
+		if (!is_last)
+			cpos += clen;
+	}
+
+	if (origin == SEEK_HOLE) {
+		extoff = cpos;
+		extoff <<= cs_bits;
+		extlen = clen;
+		extlen <<=  cs_bits;
+
+		if ((extoff + extlen) > inode->i_size)
+			extlen = inode->i_size - extoff;
+		extoff += extlen;
+		if (extoff > *offset)
+			*offset = extoff;
+		goto out_unlock;
+	}
+
+	ret = -ENXIO;
+
+out_unlock:
+
+	brelse(di_bh);
+
+	up_read(&OCFS2_I(inode)->ip_alloc_sem);
+
+	ocfs2_inode_unlock(inode, 0);
+out:
+	if (ret && ret != -ENXIO)
+		ret = -ENXIO;
+	return ret;
+}
+
 int ocfs2_read_virt_blocks(struct inode *inode, u64 v_block, int nr,
 			   struct buffer_head *bhs[], int flags,
 			   int (*validate)(struct super_block *sb,
diff --git a/fs/ocfs2/extent_map.h b/fs/ocfs2/extent_map.h
index e79d41c..67ea57d 100644
--- a/fs/ocfs2/extent_map.h
+++ b/fs/ocfs2/extent_map.h
@@ -53,6 +53,8 @@ int ocfs2_extent_map_get_blocks(struct inode *inode, u64 v_blkno, u64 *p_blkno,
 int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		 u64 map_start, u64 map_len);
 
+int ocfs2_seek_data_hole_offset(struct file *file, loff_t *offset, int origin);
+
 int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster,
 			     u32 *p_cluster, u32 *num_clusters,
 			     struct ocfs2_extent_list *el,
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index de4ea1a..6e39668 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1950,6 +1950,9 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
 	if (ret < 0)
 		mlog_errno(ret);
 
+	if (file->f_flags & O_SYNC)
+		handle->h_sync = 1;
+
 	ocfs2_commit_trans(osb, handle);
 
 out_inode_unlock:
@@ -2052,6 +2055,23 @@ out:
 	return ret;
 }
 
+static void ocfs2_aiodio_wait(struct inode *inode)
+{
+	wait_queue_head_t *wq = ocfs2_ioend_wq(inode);
+
+	wait_event(*wq, (atomic_read(&OCFS2_I(inode)->ip_unaligned_aio) == 0));
+}
+
+static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos)
+{
+	int blockmask = inode->i_sb->s_blocksize - 1;
+	loff_t final_size = pos + count;
+
+	if ((pos & blockmask) || (final_size & blockmask))
+		return 1;
+	return 0;
+}
+
 static int ocfs2_prepare_inode_for_refcount(struct inode *inode,
 					    struct file *file,
 					    loff_t pos, size_t count,
@@ -2230,6 +2250,7 @@ static ssize_t ocfs2_file_aio_write(struct kiocb *iocb,
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	int full_coherency = !(osb->s_mount_opt &
 			       OCFS2_MOUNT_COHERENCY_BUFFERED);
+	int unaligned_dio = 0;
 
 	trace_ocfs2_file_aio_write(inode, file, file->f_path.dentry,
 		(unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -2297,6 +2318,10 @@ relock:
 		goto out;
 	}
 
+	if (direct_io && !is_sync_kiocb(iocb))
+		unaligned_dio = ocfs2_is_io_unaligned(inode, iocb->ki_left,
+						      *ppos);
+
 	/*
 	 * We can't complete the direct I/O as requested, fall back to
 	 * buffered I/O.
@@ -2311,6 +2336,18 @@ relock:
 		goto relock;
 	}
 
+	if (unaligned_dio) {
+		/*
+		 * Wait on previous unaligned aio to complete before
+		 * proceeding.
+		 */
+		ocfs2_aiodio_wait(inode);
+
+		/* Mark the iocb as needing a decrement in ocfs2_dio_end_io */
+		atomic_inc(&OCFS2_I(inode)->ip_unaligned_aio);
+		ocfs2_iocb_set_unaligned_aio(iocb);
+	}
+
 	/*
 	 * To later detect whether a journal commit for sync writes is
 	 * necessary, we sample i_size, and cluster count here.
@@ -2382,8 +2419,12 @@ out_dio:
 	if ((ret == -EIOCBQUEUED) || (!ocfs2_iocb_is_rw_locked(iocb))) {
 		rw_level = -1;
 		have_alloc_sem = 0;
+		unaligned_dio = 0;
 	}
 
+	if (unaligned_dio)
+		atomic_dec(&OCFS2_I(inode)->ip_unaligned_aio);
+
 out:
 	if (rw_level != -1)
 		ocfs2_rw_unlock(inode, rw_level);
@@ -2591,6 +2632,57 @@ bail:
 	return ret;
 }
 
+/* Refer generic_file_llseek_unlocked() */
+static loff_t ocfs2_file_llseek(struct file *file, loff_t offset, int origin)
+{
+	struct inode *inode = file->f_mapping->host;
+	int ret = 0;
+
+	mutex_lock(&inode->i_mutex);
+
+	switch (origin) {
+	case SEEK_SET:
+		break;
+	case SEEK_END:
+		offset += inode->i_size;
+		break;
+	case SEEK_CUR:
+		if (offset == 0) {
+			offset = file->f_pos;
+			goto out;
+		}
+		offset += file->f_pos;
+		break;
+	case SEEK_DATA:
+	case SEEK_HOLE:
+		ret = ocfs2_seek_data_hole_offset(file, &offset, origin);
+		if (ret)
+			goto out;
+		break;
+	default:
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET))
+		ret = -EINVAL;
+	if (!ret && offset > inode->i_sb->s_maxbytes)
+		ret = -EINVAL;
+	if (ret)
+		goto out;
+
+	if (offset != file->f_pos) {
+		file->f_pos = offset;
+		file->f_version = 0;
+	}
+
+out:
+	mutex_unlock(&inode->i_mutex);
+	if (ret)
+		return ret;
+	return offset;
+}
+
 const struct inode_operations ocfs2_file_iops = {
 	.setattr	= ocfs2_setattr,
 	.getattr	= ocfs2_getattr,
@@ -2615,7 +2707,7 @@ const struct inode_operations ocfs2_special_file_iops = {
  * ocfs2_fops_no_plocks and ocfs2_dops_no_plocks!
  */
 const struct file_operations ocfs2_fops = {
-	.llseek		= generic_file_llseek,
+	.llseek		= ocfs2_file_llseek,
 	.read		= do_sync_read,
 	.write		= do_sync_write,
 	.mmap		= ocfs2_mmap,
@@ -2663,7 +2755,7 @@ const struct file_operations ocfs2_dops = {
  * the cluster.
  */
 const struct file_operations ocfs2_fops_no_plocks = {
-	.llseek		= generic_file_llseek,
+	.llseek		= ocfs2_file_llseek,
 	.read		= do_sync_read,
 	.write		= do_sync_write,
 	.mmap		= ocfs2_mmap,
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index a22d2c0..17454a9 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -951,7 +951,7 @@ static void ocfs2_cleanup_delete_inode(struct inode *inode,
 	trace_ocfs2_cleanup_delete_inode(
 		(unsigned long long)OCFS2_I(inode)->ip_blkno, sync_data);
 	if (sync_data)
-		write_inode_now(inode, 1);
+		filemap_write_and_wait(inode->i_mapping);
 	truncate_inode_pages(&inode->i_data, 0);
 }
 
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index 1c508b1..88924a3 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -43,6 +43,9 @@ struct ocfs2_inode_info
 	/* protects extended attribute changes on this inode */
 	struct rw_semaphore		ip_xattr_sem;
 
+	/* Number of outstanding AIO's which are not page aligned */
+	atomic_t			ip_unaligned_aio;
+
 	/* These fields are protected by ip_lock */
 	spinlock_t			ip_lock;
 	u32				ip_open_count;
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index bc91072..726ff26 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -122,7 +122,7 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
 	if ((oldflags & OCFS2_IMMUTABLE_FL) || ((flags ^ oldflags) &
 		(OCFS2_APPEND_FL | OCFS2_IMMUTABLE_FL))) {
 		if (!capable(CAP_LINUX_IMMUTABLE))
-			goto bail_unlock;
+			goto bail_commit;
 	}
 
 	ocfs2_inode->ip_attr = flags;
@@ -132,6 +132,7 @@ static int ocfs2_set_inode_attr(struct inode *inode, unsigned flags,
 	if (status < 0)
 		mlog_errno(status);
 
+bail_commit:
 	ocfs2_commit_trans(osb, handle);
 bail_unlock:
 	ocfs2_inode_unlock(inode, 1);
@@ -381,7 +382,7 @@ int ocfs2_info_handle_freeinode(struct inode *inode,
 	if (!oifi) {
 		status = -ENOMEM;
 		mlog_errno(status);
-		goto bail;
+		goto out_err;
 	}
 
 	if (o2info_from_user(*oifi, req))
@@ -431,7 +432,7 @@ bail:
 		o2info_set_request_error(&oifi->ifi_req, req);
 
 	kfree(oifi);
-
+out_err:
 	return status;
 }
 
@@ -666,7 +667,7 @@ int ocfs2_info_handle_freefrag(struct inode *inode,
 	if (!oiff) {
 		status = -ENOMEM;
 		mlog_errno(status);
-		goto bail;
+		goto out_err;
 	}
 
 	if (o2info_from_user(*oiff, req))
@@ -716,7 +717,7 @@ bail:
 		o2info_set_request_error(&oiff->iff_req, req);
 
 	kfree(oiff);
-
+out_err:
 	return status;
 }
 
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 295d564..0a42ae9 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1544,9 +1544,9 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
 	/* we need to run complete recovery for offline orphan slots */
 	ocfs2_replay_map_set_state(osb, REPLAY_NEEDED);
 
-	mlog(ML_NOTICE, "Recovering node %d from slot %d on device (%u,%u)\n",
-	     node_num, slot_num,
-	     MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev));
+	printk(KERN_NOTICE "ocfs2: Begin replay journal (node %d, slot %d) on "\
+	       "device (%u,%u)\n", node_num, slot_num, MAJOR(osb->sb->s_dev),
+	       MINOR(osb->sb->s_dev));
 
 	OCFS2_I(inode)->ip_clusters = le32_to_cpu(fe->i_clusters);
 
@@ -1601,6 +1601,9 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
 
 	jbd2_journal_destroy(journal);
 
+	printk(KERN_NOTICE "ocfs2: End replay journal (node %d, slot %d) on "\
+	       "device (%u,%u)\n", node_num, slot_num, MAJOR(osb->sb->s_dev),
+	       MINOR(osb->sb->s_dev));
 done:
 	/* drop the lock on this nodes journal */
 	if (got_lock)
@@ -1808,6 +1811,20 @@ static inline unsigned long ocfs2_orphan_scan_timeout(void)
  * every slot, queuing a recovery of the slot on the ocfs2_wq thread. This
  * is done to catch any orphans that are left over in orphan directories.
  *
+ * It scans all slots, even ones that are in use. It does so to handle the
+ * case described below:
+ *
+ *   Node 1 has an inode it was using. The dentry went away due to memory
+ *   pressure.  Node 1 closes the inode, but it's on the free list. The node
+ *   has the open lock.
+ *   Node 2 unlinks the inode. It grabs the dentry lock to notify others,
+ *   but node 1 has no dentry and doesn't get the message. It trylocks the
+ *   open lock, sees that another node has a PR, and does nothing.
+ *   Later node 2 runs its orphan dir. It igets the inode, trylocks the
+ *   open lock, sees the PR still, and does nothing.
+ *   Basically, we have to trigger an orphan iput on node 1. The only way
+ *   for this to happen is if node 1 runs node 2's orphan dir.
+ *
  * ocfs2_queue_orphan_scan gets called every ORPHAN_SCAN_SCHEDULE_TIMEOUT
  * seconds.  It gets an EX lock on os_lockres and checks sequence number
  * stored in LVB. If the sequence number has changed, it means some other
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 68cf2f6..a3385b6 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -441,10 +441,11 @@ static inline int ocfs2_mknod_credits(struct super_block *sb, int is_dir,
 #define OCFS2_SIMPLE_DIR_EXTEND_CREDITS (2)
 
 /* file update (nlink, etc) + directory mtime/ctime + dir entry block + quota
- * update on dir + index leaf + dx root update for free list */
+ * update on dir + index leaf + dx root update for free list +
+ * previous dirblock update in the free list */
 static inline int ocfs2_link_credits(struct super_block *sb)
 {
-	return 2*OCFS2_INODE_UPDATE_CREDITS + 3 +
+	return 2*OCFS2_INODE_UPDATE_CREDITS + 4 +
 	       ocfs2_quota_trans_credits(sb);
 }
 
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 3e9393c..9cd4108 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -61,7 +61,7 @@ static int ocfs2_fault(struct vm_area_struct *area, struct vm_fault *vmf)
 static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh,
 				struct page *page)
 {
-	int ret;
+	int ret = VM_FAULT_NOPAGE;
 	struct inode *inode = file->f_path.dentry->d_inode;
 	struct address_space *mapping = inode->i_mapping;
 	loff_t pos = page_offset(page);
@@ -71,32 +71,25 @@ static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh,
 	void *fsdata;
 	loff_t size = i_size_read(inode);
 
-	/*
-	 * Another node might have truncated while we were waiting on
-	 * cluster locks.
-	 * We don't check size == 0 before the shift. This is borrowed
-	 * from do_generic_file_read.
-	 */
 	last_index = (size - 1) >> PAGE_CACHE_SHIFT;
-	if (unlikely(!size || page->index > last_index)) {
-		ret = -EINVAL;
-		goto out;
-	}
 
 	/*
-	 * The i_size check above doesn't catch the case where nodes
-	 * truncated and then re-extended the file. We'll re-check the
-	 * page mapping after taking the page lock inside of
-	 * ocfs2_write_begin_nolock().
+	 * There are cases that lead to the page no longer bebongs to the
+	 * mapping.
+	 * 1) pagecache truncates locally due to memory pressure.
+	 * 2) pagecache truncates when another is taking EX lock against 
+	 * inode lock. see ocfs2_data_convert_worker.
+	 * 
+	 * The i_size check doesn't catch the case where nodes truncated and
+	 * then re-extended the file. We'll re-check the page mapping after
+	 * taking the page lock inside of ocfs2_write_begin_nolock().
+	 *
+	 * Let VM retry with these cases.
 	 */
-	if (!PageUptodate(page) || page->mapping != inode->i_mapping) {
-		/*
-		 * the page has been umapped in ocfs2_data_downconvert_worker.
-		 * So return 0 here and let VFS retry.
-		 */
-		ret = 0;
+	if ((page->mapping != inode->i_mapping) ||
+	    (!PageUptodate(page)) ||
+	    (page_offset(page) >= size))
 		goto out;
-	}
 
 	/*
 	 * Call ocfs2_write_begin() and ocfs2_write_end() to take
@@ -116,17 +109,21 @@ static int __ocfs2_page_mkwrite(struct file *file, struct buffer_head *di_bh,
 	if (ret) {
 		if (ret != -ENOSPC)
 			mlog_errno(ret);
+		if (ret == -ENOMEM)
+			ret = VM_FAULT_OOM;
+		else
+			ret = VM_FAULT_SIGBUS;
 		goto out;
 	}
 
-	ret = ocfs2_write_end_nolock(mapping, pos, len, len, locked_page,
-				     fsdata);
-	if (ret < 0) {
-		mlog_errno(ret);
+	if (!locked_page) {
+		ret = VM_FAULT_NOPAGE;
 		goto out;
 	}
+	ret = ocfs2_write_end_nolock(mapping, pos, len, len, locked_page,
+				     fsdata);
 	BUG_ON(ret != len);
-	ret = 0;
+	ret = VM_FAULT_LOCKED;
 out:
 	return ret;
 }
@@ -168,8 +165,6 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 out:
 	ocfs2_unblock_signals(&oldset);
-	if (ret)
-		ret = VM_FAULT_SIGBUS;
 	return ret;
 }
 
diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c
index d53cb70..184c76b 100644
--- a/fs/ocfs2/move_extents.c
+++ b/fs/ocfs2/move_extents.c
@@ -745,7 +745,7 @@ static int ocfs2_move_extent(struct ocfs2_move_extents_context *context,
 	 */
 	ocfs2_probe_alloc_group(inode, gd_bh, &goal_bit, len, move_max_hop,
 				new_phys_cpos);
-	if (!new_phys_cpos) {
+	if (!*new_phys_cpos) {
 		ret = -ENOSPC;
 		goto out_commit;
 	}
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 4092858..d355e6e 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -836,18 +836,65 @@ static inline unsigned int ocfs2_clusters_to_megabytes(struct super_block *sb,
 
 static inline void _ocfs2_set_bit(unsigned int bit, unsigned long *bitmap)
 {
-	__test_and_set_bit_le(bit, bitmap);
+	__set_bit_le(bit, bitmap);
 }
 #define ocfs2_set_bit(bit, addr) _ocfs2_set_bit((bit), (unsigned long *)(addr))
 
 static inline void _ocfs2_clear_bit(unsigned int bit, unsigned long *bitmap)
 {
-	__test_and_clear_bit_le(bit, bitmap);
+	__clear_bit_le(bit, bitmap);
 }
 #define ocfs2_clear_bit(bit, addr) _ocfs2_clear_bit((bit), (unsigned long *)(addr))
 
 #define ocfs2_test_bit test_bit_le
 #define ocfs2_find_next_zero_bit find_next_zero_bit_le
 #define ocfs2_find_next_bit find_next_bit_le
+
+static inline void *correct_addr_and_bit_unaligned(int *bit, void *addr)
+{
+#if BITS_PER_LONG == 64
+	*bit += ((unsigned long) addr & 7UL) << 3;
+	addr = (void *) ((unsigned long) addr & ~7UL);
+#elif BITS_PER_LONG == 32
+	*bit += ((unsigned long) addr & 3UL) << 3;
+	addr = (void *) ((unsigned long) addr & ~3UL);
+#else
+#error "how many bits you are?!"
+#endif
+	return addr;
+}
+
+static inline void ocfs2_set_bit_unaligned(int bit, void *bitmap)
+{
+	bitmap = correct_addr_and_bit_unaligned(&bit, bitmap);
+	ocfs2_set_bit(bit, bitmap);
+}
+
+static inline void ocfs2_clear_bit_unaligned(int bit, void *bitmap)
+{
+	bitmap = correct_addr_and_bit_unaligned(&bit, bitmap);
+	ocfs2_clear_bit(bit, bitmap);
+}
+
+static inline int ocfs2_test_bit_unaligned(int bit, void *bitmap)
+{
+	bitmap = correct_addr_and_bit_unaligned(&bit, bitmap);
+	return ocfs2_test_bit(bit, bitmap);
+}
+
+static inline int ocfs2_find_next_zero_bit_unaligned(void *bitmap, int max,
+							int start)
+{
+	int fix = 0, ret, tmpmax;
+	bitmap = correct_addr_and_bit_unaligned(&fix, bitmap);
+	tmpmax = max + fix;
+	start += fix;
+
+	ret = ocfs2_find_next_zero_bit(bitmap, tmpmax, start) - fix;
+	if (ret > max)
+		return max;
+	return ret;
+}
+
 #endif  /* OCFS2_H */
 
diff --git a/fs/ocfs2/quota_local.c b/fs/ocfs2/quota_local.c
index dc8007f..f100bf7 100644
--- a/fs/ocfs2/quota_local.c
+++ b/fs/ocfs2/quota_local.c
@@ -404,7 +404,9 @@ struct ocfs2_quota_recovery *ocfs2_begin_quota_recovery(
 	int status = 0;
 	struct ocfs2_quota_recovery *rec;
 
-	mlog(ML_NOTICE, "Beginning quota recovery in slot %u\n", slot_num);
+	printk(KERN_NOTICE "ocfs2: Beginning quota recovery on device (%s) for "
+	       "slot %u\n", osb->dev_str, slot_num);
+
 	rec = ocfs2_alloc_quota_recovery();
 	if (!rec)
 		return ERR_PTR(-ENOMEM);
@@ -549,8 +551,8 @@ static int ocfs2_recover_local_quota_file(struct inode *lqinode,
 				goto out_commit;
 			}
 			lock_buffer(qbh);
-			WARN_ON(!ocfs2_test_bit(bit, dchunk->dqc_bitmap));
-			ocfs2_clear_bit(bit, dchunk->dqc_bitmap);
+			WARN_ON(!ocfs2_test_bit_unaligned(bit, dchunk->dqc_bitmap));
+			ocfs2_clear_bit_unaligned(bit, dchunk->dqc_bitmap);
 			le32_add_cpu(&dchunk->dqc_free, 1);
 			unlock_buffer(qbh);
 			ocfs2_journal_dirty(handle, qbh);
@@ -596,7 +598,9 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 	struct inode *lqinode;
 	unsigned int flags;
 
-	mlog(ML_NOTICE, "Finishing quota recovery in slot %u\n", slot_num);
+	printk(KERN_NOTICE "ocfs2: Finishing quota recovery on device (%s) for "
+	       "slot %u\n", osb->dev_str, slot_num);
+
 	mutex_lock(&sb_dqopt(sb)->dqonoff_mutex);
 	for (type = 0; type < MAXQUOTAS; type++) {
 		if (list_empty(&(rec->r_list[type])))
@@ -612,8 +616,9 @@ int ocfs2_finish_quota_recovery(struct ocfs2_super *osb,
 		/* Someone else is holding the lock? Then he must be
 		 * doing the recovery. Just skip the file... */
 		if (status == -EAGAIN) {
-			mlog(ML_NOTICE, "skipping quota recovery for slot %d "
-			     "because quota file is locked.\n", slot_num);
+			printk(KERN_NOTICE "ocfs2: Skipping quota recovery on "
+			       "device (%s) for slot %d because quota file is "
+			       "locked.\n", osb->dev_str, slot_num);
 			status = 0;
 			goto out_put;
 		} else if (status < 0) {
@@ -944,7 +949,7 @@ static struct ocfs2_quota_chunk *ocfs2_find_free_entry(struct super_block *sb,
 		      * ol_quota_entries_per_block(sb);
 	}
 
-	found = ocfs2_find_next_zero_bit(dchunk->dqc_bitmap, len, 0);
+	found = ocfs2_find_next_zero_bit_unaligned(dchunk->dqc_bitmap, len, 0);
 	/* We failed? */
 	if (found == len) {
 		mlog(ML_ERROR, "Did not find empty entry in chunk %d with %u"
@@ -1208,7 +1213,7 @@ static void olq_alloc_dquot(struct buffer_head *bh, void *private)
 	struct ocfs2_local_disk_chunk *dchunk;
 
 	dchunk = (struct ocfs2_local_disk_chunk *)bh->b_data;
-	ocfs2_set_bit(*offset, dchunk->dqc_bitmap);
+	ocfs2_set_bit_unaligned(*offset, dchunk->dqc_bitmap);
 	le32_add_cpu(&dchunk->dqc_free, -1);
 }
 
@@ -1289,7 +1294,7 @@ int ocfs2_local_release_dquot(handle_t *handle, struct dquot *dquot)
 			(od->dq_chunk->qc_headerbh->b_data);
 	/* Mark structure as freed */
 	lock_buffer(od->dq_chunk->qc_headerbh);
-	ocfs2_clear_bit(offset, dchunk->dqc_bitmap);
+	ocfs2_clear_bit_unaligned(offset, dchunk->dqc_bitmap);
 	le32_add_cpu(&dchunk->dqc_free, 1);
 	unlock_buffer(od->dq_chunk->qc_headerbh);
 	ocfs2_journal_dirty(handle, od->dq_chunk->qc_headerbh);
diff --git a/fs/ocfs2/slot_map.c b/fs/ocfs2/slot_map.c
index 26fc001..1424c15 100644
--- a/fs/ocfs2/slot_map.c
+++ b/fs/ocfs2/slot_map.c
@@ -493,8 +493,8 @@ int ocfs2_find_slot(struct ocfs2_super *osb)
 			goto bail;
 		}
 	} else
-		mlog(ML_NOTICE, "slot %d is already allocated to this node!\n",
-		     slot);
+		printk(KERN_INFO "ocfs2: Slot %d on device (%s) was already "
+		       "allocated to this node!\n", slot, osb->dev_str);
 
 	ocfs2_set_slot(si, slot, osb->node_num);
 	osb->slot_num = slot;
diff --git a/fs/ocfs2/stack_o2cb.c b/fs/ocfs2/stack_o2cb.c
index 19965b0..9436801 100644
--- a/fs/ocfs2/stack_o2cb.c
+++ b/fs/ocfs2/stack_o2cb.c
@@ -28,6 +28,7 @@
 #include "cluster/masklog.h"
 #include "cluster/nodemanager.h"
 #include "cluster/heartbeat.h"
+#include "cluster/tcp.h"
 
 #include "stackglue.h"
 
@@ -256,6 +257,61 @@ static void o2cb_dump_lksb(struct ocfs2_dlm_lksb *lksb)
 }
 
 /*
+ * Check if this node is heartbeating and is connected to all other
+ * heartbeating nodes.
+ */
+static int o2cb_cluster_check(void)
+{
+	u8 node_num;
+	int i;
+	unsigned long hbmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
+	unsigned long netmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
+
+	node_num = o2nm_this_node();
+	if (node_num == O2NM_MAX_NODES) {
+		printk(KERN_ERR "o2cb: This node has not been configured.\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * o2dlm expects o2net sockets to be created. If not, then
+	 * dlm_join_domain() fails with a stack of errors which are both cryptic
+	 * and incomplete. The idea here is to detect upfront whether we have
+	 * managed to connect to all nodes or not. If not, then list the nodes
+	 * to allow the user to check the configuration (incorrect IP, firewall,
+	 * etc.) Yes, this is racy. But its not the end of the world.
+	 */
+#define	O2CB_MAP_STABILIZE_COUNT	60
+	for (i = 0; i < O2CB_MAP_STABILIZE_COUNT; ++i) {
+		o2hb_fill_node_map(hbmap, sizeof(hbmap));
+		if (!test_bit(node_num, hbmap)) {
+			printk(KERN_ERR "o2cb: %s heartbeat has not been "
+			       "started.\n", (o2hb_global_heartbeat_active() ?
+					      "Global" : "Local"));
+			return -EINVAL;
+		}
+		o2net_fill_node_map(netmap, sizeof(netmap));
+		/* Force set the current node to allow easy compare */
+		set_bit(node_num, netmap);
+		if (!memcmp(hbmap, netmap, sizeof(hbmap)))
+			return 0;
+		if (i < O2CB_MAP_STABILIZE_COUNT)
+			msleep(1000);
+	}
+
+	printk(KERN_ERR "o2cb: This node could not connect to nodes:");
+	i = -1;
+	while ((i = find_next_bit(hbmap, O2NM_MAX_NODES,
+				  i + 1)) < O2NM_MAX_NODES) {
+		if (!test_bit(i, netmap))
+			printk(" %u", i);
+	}
+	printk(".\n");
+
+	return -ENOTCONN;
+}
+
+/*
  * Called from the dlm when it's about to evict a node. This is how the
  * classic stack signals node death.
  */
@@ -263,8 +319,8 @@ static void o2dlm_eviction_cb(int node_num, void *data)
 {
 	struct ocfs2_cluster_connection *conn = data;
 
-	mlog(ML_NOTICE, "o2dlm has evicted node %d from group %.*s\n",
-	     node_num, conn->cc_namelen, conn->cc_name);
+	printk(KERN_NOTICE "o2cb: o2dlm has evicted node %d from domain %.*s\n",
+	       node_num, conn->cc_namelen, conn->cc_name);
 
 	conn->cc_recovery_handler(node_num, conn->cc_recovery_data);
 }
@@ -280,12 +336,11 @@ static int o2cb_cluster_connect(struct ocfs2_cluster_connection *conn)
 	BUG_ON(conn == NULL);
 	BUG_ON(conn->cc_proto == NULL);
 
-	/* for now we only have one cluster/node, make sure we see it
-	 * in the heartbeat universe */
-	if (!o2hb_check_local_node_heartbeating()) {
-		if (o2hb_global_heartbeat_active())
-			mlog(ML_ERROR, "Global heartbeat not started\n");
-		rc = -EINVAL;
+	/* Ensure cluster stack is up and all nodes are connected */
+	rc = o2cb_cluster_check();
+	if (rc) {
+		printk(KERN_ERR "o2cb: Cluster check failed. Fix errors "
+		       "before retrying.\n");
 		goto out;
 	}
 
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 56f6102..4994f8b 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -54,6 +54,7 @@
 #include "ocfs1_fs_compat.h"
 
 #include "alloc.h"
+#include "aops.h"
 #include "blockcheck.h"
 #include "dlmglue.h"
 #include "export.h"
@@ -1107,9 +1108,9 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 
 		ocfs2_set_ro_flag(osb, 1);
 
-		printk(KERN_NOTICE "Readonly device detected. No cluster "
-		       "services will be utilized for this mount. Recovery "
-		       "will be skipped.\n");
+		printk(KERN_NOTICE "ocfs2: Readonly device (%s) detected. "
+		       "Cluster services will not be used for this mount. "
+		       "Recovery will be skipped.\n", osb->dev_str);
 	}
 
 	if (!ocfs2_is_hard_readonly(osb)) {
@@ -1616,12 +1617,17 @@ static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
 	return 0;
 }
 
+wait_queue_head_t ocfs2__ioend_wq[OCFS2_IOEND_WQ_HASH_SZ];
+
 static int __init ocfs2_init(void)
 {
-	int status;
+	int status, i;
 
 	ocfs2_print_version();
 
+	for (i = 0; i < OCFS2_IOEND_WQ_HASH_SZ; i++)
+		init_waitqueue_head(&ocfs2__ioend_wq[i]);
+
 	status = init_ocfs2_uptodate_cache();
 	if (status < 0) {
 		mlog_errno(status);
@@ -1760,7 +1766,7 @@ static void ocfs2_inode_init_once(void *data)
 	ocfs2_extent_map_init(&oi->vfs_inode);
 	INIT_LIST_HEAD(&oi->ip_io_markers);
 	oi->ip_dir_start_lookup = 0;
-
+	atomic_set(&oi->ip_unaligned_aio, 0);
 	init_rwsem(&oi->ip_alloc_sem);
 	init_rwsem(&oi->ip_xattr_sem);
 	mutex_init(&oi->ip_io_mutex);
@@ -1974,7 +1980,8 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 	 * If we failed before we got a uuid_str yet, we can't stop
 	 * heartbeat.  Otherwise, do it.
 	 */
-	if (!mnt_err && !ocfs2_mount_local(osb) && osb->uuid_str)
+	if (!mnt_err && !ocfs2_mount_local(osb) && osb->uuid_str &&
+	    !ocfs2_is_hard_readonly(osb))
 		hangup_needed = 1;
 
 	if (osb->cconn)
@@ -2353,7 +2360,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
 		mlog_errno(status);
 		goto bail;
 	}
-	cleancache_init_shared_fs((char *)&uuid_net_key, sb);
+	cleancache_init_shared_fs((char *)&di->id2.i_super.s_uuid, sb);
 
 bail:
 	return status;
@@ -2462,8 +2469,8 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
 			goto finally;
 		}
 	} else {
-		mlog(ML_NOTICE, "File system was not unmounted cleanly, "
-		     "recovering volume.\n");
+		printk(KERN_NOTICE "ocfs2: File system on device (%s) was not "
+		       "unmounted cleanly, recovering it.\n", osb->dev_str);
 	}
 
 	local = ocfs2_mount_local(osb);
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 194fb22..aa9e877 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -2376,16 +2376,18 @@ static int ocfs2_remove_value_outside(struct inode*inode,
 		}
 
 		ret = ocfs2_xattr_value_truncate(inode, vb, 0, &ctxt);
-		if (ret < 0) {
-			mlog_errno(ret);
-			break;
-		}
 
 		ocfs2_commit_trans(osb, ctxt.handle);
 		if (ctxt.meta_ac) {
 			ocfs2_free_alloc_context(ctxt.meta_ac);
 			ctxt.meta_ac = NULL;
 		}
+
+		if (ret < 0) {
+			mlog_errno(ret);
+			break;
+		}
+
 	}
 
 	if (ctxt.meta_ac)
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 2bd620f..57bbf90 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -167,6 +167,7 @@ int pstore_register(struct pstore_info *psi)
 	}
 
 	psinfo = psi;
+	mutex_init(&psinfo->read_mutex);
 	spin_unlock(&pstore_lock);
 
 	if (owner && !try_module_get(owner)) {
@@ -195,30 +196,32 @@ EXPORT_SYMBOL_GPL(pstore_register);
 void pstore_get_records(int quiet)
 {
 	struct pstore_info *psi = psinfo;
+	char			*buf = NULL;
 	ssize_t			size;
 	u64			id;
 	enum pstore_type_id	type;
 	struct timespec		time;
 	int			failed = 0, rc;
-	unsigned long		flags;
 
 	if (!psi)
 		return;
 
-	spin_lock_irqsave(&psinfo->buf_lock, flags);
+	mutex_lock(&psi->read_mutex);
 	rc = psi->open(psi);
 	if (rc)
 		goto out;
 
-	while ((size = psi->read(&id, &type, &time, psi)) > 0) {
-		rc = pstore_mkfile(type, psi->name, id, psi->buf, (size_t)size,
+	while ((size = psi->read(&id, &type, &time, &buf, psi)) > 0) {
+		rc = pstore_mkfile(type, psi->name, id, buf, (size_t)size,
 				  time, psi);
+		kfree(buf);
+		buf = NULL;
 		if (rc && (rc != -EEXIST || !quiet))
 			failed++;
 	}
 	psi->close(psi);
 out:
-	spin_unlock_irqrestore(&psinfo->buf_lock, flags);
+	mutex_unlock(&psi->read_mutex);
 
 	if (failed)
 		printk(KERN_WARNING "pstore: failed to load %d record(s) from '%s'\n",
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index b6c4b37..76e4266 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -42,6 +42,8 @@ xfs_acl_from_disk(struct xfs_acl *aclp)
 	int count, i;
 
 	count = be32_to_cpu(aclp->acl_cnt);
+	if (count > XFS_ACL_MAX_ENTRIES)
+		return ERR_PTR(-EFSCORRUPTED);
 
 	acl = posix_acl_alloc(count, GFP_KERNEL);
 	if (!acl)
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index d4906e7..c1b55e5 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -110,6 +110,7 @@ xfs_attr_namesp_match(int arg_flags, int ondisk_flags)
 /*
  * Query whether the requested number of additional bytes of extended
  * attribute space will be able to fit inline.
+ *
  * Returns zero if not, else the di_forkoff fork offset to be used in the
  * literal area for attribute data once the new bytes have been added.
  *
@@ -122,7 +123,7 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
 	int offset;
 	int minforkoff;	/* lower limit on valid forkoff locations */
 	int maxforkoff;	/* upper limit on valid forkoff locations */
-	int dsize;	
+	int dsize;
 	xfs_mount_t *mp = dp->i_mount;
 
 	offset = (XFS_LITINO(mp) - bytes) >> 3; /* rounded down */
@@ -136,47 +137,60 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
 		return (offset >= minforkoff) ? minforkoff : 0;
 	}
 
-	if (!(mp->m_flags & XFS_MOUNT_ATTR2)) {
-		if (bytes <= XFS_IFORK_ASIZE(dp))
-			return dp->i_d.di_forkoff;
+	/*
+	 * If the requested numbers of bytes is smaller or equal to the
+	 * current attribute fork size we can always proceed.
+	 *
+	 * Note that if_bytes in the data fork might actually be larger than
+	 * the current data fork size is due to delalloc extents. In that
+	 * case either the extent count will go down when they are converted
+	 * to real extents, or the delalloc conversion will take care of the
+	 * literal area rebalancing.
+	 */
+	if (bytes <= XFS_IFORK_ASIZE(dp))
+		return dp->i_d.di_forkoff;
+
+	/*
+	 * For attr2 we can try to move the forkoff if there is space in the
+	 * literal area, but for the old format we are done if there is no
+	 * space in the fixed attribute fork.
+	 */
+	if (!(mp->m_flags & XFS_MOUNT_ATTR2))
 		return 0;
-	}
 
 	dsize = dp->i_df.if_bytes;
-	
+
 	switch (dp->i_d.di_format) {
 	case XFS_DINODE_FMT_EXTENTS:
-		/* 
+		/*
 		 * If there is no attr fork and the data fork is extents, 
-		 * determine if creating the default attr fork will result 
-		 * in the extents form migrating to btree. If so, the 
-		 * minimum offset only needs to be the space required for 
+		 * determine if creating the default attr fork will result
+		 * in the extents form migrating to btree. If so, the
+		 * minimum offset only needs to be the space required for
 		 * the btree root.
-		 */ 
+		 */
 		if (!dp->i_d.di_forkoff && dp->i_df.if_bytes >
 		    xfs_default_attroffset(dp))
 			dsize = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
 		break;
-		
 	case XFS_DINODE_FMT_BTREE:
 		/*
-		 * If have data btree then keep forkoff if we have one,
-		 * otherwise we are adding a new attr, so then we set 
-		 * minforkoff to where the btree root can finish so we have 
+		 * If we have a data btree then keep forkoff if we have one,
+		 * otherwise we are adding a new attr, so then we set
+		 * minforkoff to where the btree root can finish so we have
 		 * plenty of room for attrs
 		 */
 		if (dp->i_d.di_forkoff) {
-			if (offset < dp->i_d.di_forkoff) 
+			if (offset < dp->i_d.di_forkoff)
 				return 0;
-			else 
-				return dp->i_d.di_forkoff;
-		} else
-			dsize = XFS_BMAP_BROOT_SPACE(dp->i_df.if_broot);
+			return dp->i_d.di_forkoff;
+		}
+		dsize = XFS_BMAP_BROOT_SPACE(dp->i_df.if_broot);
 		break;
 	}
-	
-	/* 
-	 * A data fork btree root must have space for at least 
+
+	/*
+	 * A data fork btree root must have space for at least
 	 * MINDBTPTRS key/ptr pairs if the data fork is small or empty.
 	 */
 	minforkoff = MAX(dsize, XFS_BMDR_SPACE_CALC(MINDBTPTRS));
@@ -186,10 +200,10 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
 	maxforkoff = XFS_LITINO(mp) - XFS_BMDR_SPACE_CALC(MINABTPTRS);
 	maxforkoff = maxforkoff >> 3;	/* rounded down */
 
-	if (offset >= minforkoff && offset < maxforkoff)
-		return offset;
 	if (offset >= maxforkoff)
 		return maxforkoff;
+	if (offset >= minforkoff)
+		return offset;
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index c0237c6..755ee81 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2835,6 +2835,27 @@ corrupt_out:
 	return XFS_ERROR(EFSCORRUPTED);
 }
 
+void
+xfs_promote_inode(
+	struct xfs_inode	*ip)
+{
+	struct xfs_buf		*bp;
+
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
+
+	bp = xfs_incore(ip->i_mount->m_ddev_targp, ip->i_imap.im_blkno,
+			ip->i_imap.im_len, XBF_TRYLOCK);
+	if (!bp)
+		return;
+
+	if (XFS_BUF_ISDELAYWRITE(bp)) {
+		xfs_buf_delwri_promote(bp);
+		wake_up_process(ip->i_mount->m_ddev_targp->bt_task);
+	}
+
+	xfs_buf_relse(bp);
+}
+
 /*
  * Return a pointer to the extent record at file index idx.
  */
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 760140d..b4cd473 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -498,6 +498,7 @@ int		xfs_iunlink(struct xfs_trans *, xfs_inode_t *);
 void		xfs_iext_realloc(xfs_inode_t *, int, int);
 void		xfs_iunpin_wait(xfs_inode_t *);
 int		xfs_iflush(xfs_inode_t *, uint);
+void		xfs_promote_inode(struct xfs_inode *);
 void		xfs_lock_inodes(xfs_inode_t **, int, uint);
 void		xfs_lock_two_inodes(xfs_inode_t *, xfs_inode_t *, uint);
 
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 5cff443..0bbb1a4 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -674,7 +674,8 @@ xfs_qm_dqattach_one(
 	 * disk and we didn't ask it to allocate;
 	 * ESRCH if quotas got turned off suddenly.
 	 */
-	error = xfs_qm_dqget(ip->i_mount, ip, id, type, XFS_QMOPT_DOWARN, &dqp);
+	error = xfs_qm_dqget(ip->i_mount, ip, id, type,
+			     doalloc | XFS_QMOPT_DOWARN, &dqp);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c
index aa3dc1a..be5c51d 100644
--- a/fs/xfs/xfs_sync.c
+++ b/fs/xfs/xfs_sync.c
@@ -770,6 +770,17 @@ restart:
 	if (!xfs_iflock_nowait(ip)) {
 		if (!(sync_mode & SYNC_WAIT))
 			goto out;
+
+		/*
+		 * If we only have a single dirty inode in a cluster there is
+		 * a fair chance that the AIL push may have pushed it into
+		 * the buffer, but xfsbufd won't touch it until 30 seconds
+		 * from now, and thus we will lock up here.
+		 *
+		 * Promote the inode buffer to the front of the delwri list
+		 * and wake up xfsbufd now.
+		 */
+		xfs_promote_inode(ip);
 		xfs_iflock(ip);
 	}
 
diff --git a/include/drm/drm_mode.h b/include/drm/drm_mode.h
index d30bedf..ddd46db 100644
--- a/include/drm/drm_mode.h
+++ b/include/drm/drm_mode.h
@@ -235,6 +235,8 @@ struct drm_mode_fb_cmd {
 #define DRM_MODE_FB_DIRTY_ANNOTATE_FILL 0x02
 #define DRM_MODE_FB_DIRTY_FLAGS         0x03
 
+#define DRM_MODE_FB_DIRTY_MAX_CLIPS     256
+
 /*
  * Mark a region of a framebuffer as dirty.
  *
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 3d53efd..4e4fbb8 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -4,6 +4,7 @@
 */
 #define radeon_PCI_IDS \
 	{0x1002, 0x3150, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY}, \
+	{0x1002, 0x3151, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x3152, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x3154, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x3155, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
@@ -55,6 +56,7 @@
 	{0x1002, 0x4C64, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x4C66, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x4C67, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV250|RADEON_IS_MOBILITY}, \
+	{0x1002, 0x4C6E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x4E44, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
 	{0x1002, 0x4E45, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
 	{0x1002, 0x4E46, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R300}, \
@@ -195,6 +197,14 @@
 	{0x1002, 0x6770, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6778, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6779, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CAICOS|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6840, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6841, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6842, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6843, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6849, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6850, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6858, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6859, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_TURKS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6880, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6888, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6889, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_CYPRESS|RADEON_NEW_MEMMAP}, \
diff --git a/include/drm/exynos_drm.h b/include/drm/exynos_drm.h
index 1d161cb..1205043 100644
--- a/include/drm/exynos_drm.h
+++ b/include/drm/exynos_drm.h
@@ -32,17 +32,16 @@
 /**
  * User-desired buffer creation information structure.
  *
- * @size: requested size for the object.
+ * @size: user-desired memory allocation size.
  *	- this size value would be page-aligned internally.
  * @flags: user request for setting memory type or cache attributes.
- * @handle: returned handle for the object.
- * @pad: just padding to be 64-bit aligned.
+ * @handle: returned a handle to created gem object.
+ *	- this handle will be set by gem module of kernel side.
  */
 struct drm_exynos_gem_create {
-	unsigned int size;
+	uint64_t size;
 	unsigned int flags;
 	unsigned int handle;
-	unsigned int pad;
 };
 
 /**
diff --git a/include/drm/radeon_drm.h b/include/drm/radeon_drm.h
index b65be60..be94be6 100644
--- a/include/drm/radeon_drm.h
+++ b/include/drm/radeon_drm.h
@@ -874,6 +874,10 @@ struct drm_radeon_gem_pwrite {
 
 #define RADEON_CHUNK_ID_RELOCS	0x01
 #define RADEON_CHUNK_ID_IB	0x02
+#define RADEON_CHUNK_ID_FLAGS	0x03
+
+/* The first dword of RADEON_CHUNK_ID_FLAGS is a uint32 of these flags: */
+#define RADEON_CS_KEEP_TILING_FLAGS 0x01
 
 struct drm_radeon_cs_chunk {
 	uint32_t		chunk_id;
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 619b565..0b091b3 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -185,6 +185,7 @@ header-y += if_pppol2tp.h
 header-y += if_pppox.h
 header-y += if_slip.h
 header-y += if_strip.h
+header-y += if_team.h
 header-y += if_tr.h
 header-y += if_tun.h
 header-y += if_tunnel.h
diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 49a83ca..f4ff882 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -445,16 +445,6 @@ void vcc_insert_socket(struct sock *sk);
 
 void atm_dev_release_vccs(struct atm_dev *dev);
 
-/*
- * This is approximately the algorithm used by alloc_skb.
- *
- */
-
-static inline int atm_guess_pdu2truesize(int size)
-{
-	return SKB_DATA_ALIGN(size) + sizeof(struct skb_shared_info);
-}
-
 
 static inline void atm_force_charge(struct atm_vcc *vcc,int truesize)
 {
diff --git a/include/linux/bio.h b/include/linux/bio.h
index a3c071c..847994a 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -211,8 +211,8 @@ extern void bio_pair_release(struct bio_pair *dbio);
 extern struct bio_set *bioset_create(unsigned int, unsigned int);
 extern void bioset_free(struct bio_set *);
 
-extern struct bio *bio_alloc(gfp_t, int);
-extern struct bio *bio_kmalloc(gfp_t, int);
+extern struct bio *bio_alloc(gfp_t, unsigned int);
+extern struct bio *bio_kmalloc(gfp_t, unsigned int);
 extern struct bio *bio_alloc_bioset(gfp_t, int, struct bio_set *);
 extern void bio_put(struct bio *);
 extern void bio_free(struct bio *, struct bio_set *);
@@ -519,7 +519,11 @@ extern void bio_integrity_init(void);
 #define bioset_integrity_create(a, b)	(0)
 #define bio_integrity_prep(a)		(0)
 #define bio_integrity_enabled(a)	(0)
-#define bio_integrity_clone(a, b, c, d)	(0)
+static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
+				      gfp_t gfp_mask, struct bio_set *bs)
+{
+	return 0;
+}
 #define bioset_integrity_free(a)	do { } while (0)
 #define bio_integrity_free(a, b)	do { } while (0)
 #define bio_integrity_endio(a, b)	do { } while (0)
diff --git a/include/linux/can/platform/cc770.h b/include/linux/can/platform/cc770.h
new file mode 100644
index 0000000..7702641
--- /dev/null
+++ b/include/linux/can/platform/cc770.h
@@ -0,0 +1,33 @@
+#ifndef _CAN_PLATFORM_CC770_H_
+#define _CAN_PLATFORM_CC770_H_
+
+/* CPU Interface Register (0x02) */
+#define CPUIF_CEN	0x01	/* Clock Out Enable */
+#define CPUIF_MUX	0x04	/* Multiplex */
+#define CPUIF_SLP	0x08	/* Sleep */
+#define CPUIF_PWD	0x10	/* Power Down Mode */
+#define CPUIF_DMC	0x20	/* Divide Memory Clock */
+#define CPUIF_DSC	0x40	/* Divide System Clock */
+#define CPUIF_RST	0x80	/* Hardware Reset Status */
+
+/* Clock Out Register (0x1f) */
+#define CLKOUT_CD_MASK  0x0f	/* Clock Divider mask */
+#define CLKOUT_SL_MASK	0x30	/* Slew Rate mask */
+#define CLKOUT_SL_SHIFT	4
+
+/* Bus Configuration Register (0x2f) */
+#define BUSCFG_DR0	0x01	/* Disconnect RX0 Input / Select RX input */
+#define BUSCFG_DR1	0x02	/* Disconnect RX1 Input / Silent mode */
+#define BUSCFG_DT1	0x08	/* Disconnect TX1 Output */
+#define BUSCFG_POL	0x20	/* Polarity dominant or recessive */
+#define BUSCFG_CBY	0x40	/* Input Comparator Bypass */
+
+struct cc770_platform_data {
+	u32 osc_freq;	/* CAN bus oscillator frequency in Hz */
+
+	u8 cir;		/* CPU Interface Register */
+	u8 cor;		/* Clock Out Register */
+	u8 bcr;		/* Bus Configuration Register */
+};
+
+#endif	/* !_CAN_PLATFORM_CC770_H_ */
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index f88eacb..7c05ac2 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -10,6 +10,12 @@
 #include "osdmap.h"
 #include "messenger.h"
 
+/* 
+ * Maximum object name size 
+ * (must be at least as big as RBD_MAX_MD_NAME_LEN -- currently 100) 
+ */
+#define MAX_OBJ_NAME_SIZE 100
+
 struct ceph_msg;
 struct ceph_snap_context;
 struct ceph_osd_request;
@@ -75,7 +81,7 @@ struct ceph_osd_request {
 	struct inode *r_inode;         	      /* for use by callbacks */
 	void *r_priv;			      /* ditto */
 
-	char              r_oid[40];          /* object name */
+	char              r_oid[MAX_OBJ_NAME_SIZE];          /* object name */
 	int               r_oid_len;
 	unsigned long     r_stamp;            /* send OR check time */
 
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index ac663c1..0bd390c 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -59,8 +59,16 @@ SUBSYS(net_cls)
 SUBSYS(blkio)
 #endif
 
+/* */
+
 #ifdef CONFIG_CGROUP_PERF
 SUBSYS(perf)
 #endif
 
 /* */
+
+#ifdef CONFIG_NETPRIO_CGROUP
+SUBSYS(net_prio)
+#endif
+
+/* */
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 139c4db..c86c940 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -156,6 +156,7 @@ extern u64 timecounter_cyc2time(struct timecounter *tc,
  * @mult:		cycle to nanosecond multiplier
  * @shift:		cycle to nanosecond divisor (power of two)
  * @max_idle_ns:	max idle time permitted by the clocksource (nsecs)
+ * @maxadj		maximum adjustment value to mult (~11%)
  * @flags:		flags describing special properties
  * @archdata:		arch-specific data
  * @suspend:		suspend function for the clocksource, if necessary
@@ -172,7 +173,7 @@ struct clocksource {
 	u32 mult;
 	u32 shift;
 	u64 max_idle_ns;
-
+	u32 maxadj;
 #ifdef CONFIG_ARCH_CLOCKSOURCE_DATA
 	struct arch_clocksource_data archdata;
 #endif
diff --git a/include/linux/device.h b/include/linux/device.h
index ffbcf95..3136ede 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -69,7 +69,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *);
  * @resume:	Called to bring a device on this bus out of sleep mode.
  * @pm:		Power management operations of this bus, callback the specific
  *		device driver's pm-ops.
- * @iommu_ops   IOMMU specific operations for this bus, used to attach IOMMU
+ * @iommu_ops:  IOMMU specific operations for this bus, used to attach IOMMU
  *              driver implementations to a bus and allow the driver to do
  *              bus-specific setup
  * @p:		The private data of the driver core, only the driver core can
@@ -682,6 +682,11 @@ static inline bool device_async_suspend_enabled(struct device *dev)
 	return !!dev->power.async_suspend;
 }
 
+static inline void pm_suspend_ignore_children(struct device *dev, bool enable)
+{
+	dev->power.ignore_children = enable;
+}
+
 static inline void device_lock(struct device *dev)
 {
 	mutex_lock(&dev->mutex);
diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h
new file mode 100644
index 0000000..5621547
--- /dev/null
+++ b/include/linux/dynamic_queue_limits.h
@@ -0,0 +1,97 @@
+/*
+ * Dynamic queue limits (dql) - Definitions
+ *
+ * Copyright (c) 2011, Tom Herbert <therbert@google.com>
+ *
+ * This header file contains the definitions for dynamic queue limits (dql).
+ * dql would be used in conjunction with a producer/consumer type queue
+ * (possibly a HW queue).  Such a queue would have these general properties:
+ *
+ *   1) Objects are queued up to some limit specified as number of objects.
+ *   2) Periodically a completion process executes which retires consumed
+ *      objects.
+ *   3) Starvation occurs when limit has been reached, all queued data has
+ *      actually been consumed, but completion processing has not yet run
+ *      so queuing new data is blocked.
+ *   4) Minimizing the amount of queued data is desirable.
+ *
+ * The goal of dql is to calculate the limit as the minimum number of objects
+ * needed to prevent starvation.
+ *
+ * The primary functions of dql are:
+ *    dql_queued - called when objects are enqueued to record number of objects
+ *    dql_avail - returns how many objects are available to be queued based
+ *      on the object limit and how many objects are already enqueued
+ *    dql_completed - called at completion time to indicate how many objects
+ *      were retired from the queue
+ *
+ * The dql implementation does not implement any locking for the dql data
+ * structures, the higher layer should provide this.  dql_queued should
+ * be serialized to prevent concurrent execution of the function; this
+ * is also true for  dql_completed.  However, dql_queued and dlq_completed  can
+ * be executed concurrently (i.e. they can be protected by different locks).
+ */
+
+#ifndef _LINUX_DQL_H
+#define _LINUX_DQL_H
+
+#ifdef __KERNEL__
+
+struct dql {
+	/* Fields accessed in enqueue path (dql_queued) */
+	unsigned int	num_queued;		/* Total ever queued */
+	unsigned int	adj_limit;		/* limit + num_completed */
+	unsigned int	last_obj_cnt;		/* Count at last queuing */
+
+	/* Fields accessed only by completion path (dql_completed) */
+
+	unsigned int	limit ____cacheline_aligned_in_smp; /* Current limit */
+	unsigned int	num_completed;		/* Total ever completed */
+
+	unsigned int	prev_ovlimit;		/* Previous over limit */
+	unsigned int	prev_num_queued;	/* Previous queue total */
+	unsigned int	prev_last_obj_cnt;	/* Previous queuing cnt */
+
+	unsigned int	lowest_slack;		/* Lowest slack found */
+	unsigned long	slack_start_time;	/* Time slacks seen */
+
+	/* Configuration */
+	unsigned int	max_limit;		/* Max limit */
+	unsigned int	min_limit;		/* Minimum limit */
+	unsigned int	slack_hold_time;	/* Time to measure slack */
+};
+
+/* Set some static maximums */
+#define DQL_MAX_OBJECT (UINT_MAX / 16)
+#define DQL_MAX_LIMIT ((UINT_MAX / 2) - DQL_MAX_OBJECT)
+
+/*
+ * Record number of objects queued. Assumes that caller has already checked
+ * availability in the queue with dql_avail.
+ */
+static inline void dql_queued(struct dql *dql, unsigned int count)
+{
+	BUG_ON(count > DQL_MAX_OBJECT);
+
+	dql->num_queued += count;
+	dql->last_obj_cnt = count;
+}
+
+/* Returns how many objects can be queued, < 0 indicates over limit. */
+static inline int dql_avail(const struct dql *dql)
+{
+	return dql->adj_limit - dql->num_queued;
+}
+
+/* Record number of completed objects and recalculate the limit. */
+void dql_completed(struct dql *dql, unsigned int count);
+
+/* Reset dql state */
+void dql_reset(struct dql *dql);
+
+/* Initialize dql state */
+int dql_init(struct dql *dql, unsigned hold_time);
+
+#endif /* _KERNEL_ */
+
+#endif /* _LINUX_DQL_H */
diff --git a/include/linux/eeprom_93cx6.h b/include/linux/eeprom_93cx6.h
index c4627cb..e50f98b 100644
--- a/include/linux/eeprom_93cx6.h
+++ b/include/linux/eeprom_93cx6.h
@@ -33,6 +33,7 @@
 #define PCI_EEPROM_WIDTH_93C86	8
 #define PCI_EEPROM_WIDTH_OPCODE	3
 #define PCI_EEPROM_WRITE_OPCODE	0x05
+#define PCI_EEPROM_ERASE_OPCODE 0x07
 #define PCI_EEPROM_READ_OPCODE	0x06
 #define PCI_EEPROM_EWDS_OPCODE	0x10
 #define PCI_EEPROM_EWEN_OPCODE	0x13
@@ -46,6 +47,7 @@
  * @register_write(struct eeprom_93cx6 *eeprom): handler to
  * write to the eeprom register by using all reg_* fields.
  * @width: eeprom width, should be one of the PCI_EEPROM_WIDTH_* defines
+ * @drive_data: Set if we're driving the data line.
  * @reg_data_in: register field to indicate data input
  * @reg_data_out: register field to indicate data output
  * @reg_data_clock: register field to set the data clock
@@ -62,6 +64,7 @@ struct eeprom_93cx6 {
 
 	int width;
 
+	char drive_data;
 	char reg_data_in;
 	char reg_data_out;
 	char reg_data_clock;
@@ -72,3 +75,8 @@ extern void eeprom_93cx6_read(struct eeprom_93cx6 *eeprom,
 	const u8 word, u16 *data);
 extern void eeprom_93cx6_multiread(struct eeprom_93cx6 *eeprom,
 	const u8 word, __le16 *data, const u16 words);
+
+extern void eeprom_93cx6_wren(struct eeprom_93cx6 *eeprom, bool enable);
+
+extern void eeprom_93cx6_write(struct eeprom_93cx6 *eeprom,
+			       u8 addr, u16 data);
diff --git a/include/linux/errqueue.h b/include/linux/errqueue.h
index c9f522b..fd0628b 100644
--- a/include/linux/errqueue.h
+++ b/include/linux/errqueue.h
@@ -25,7 +25,7 @@ struct sock_extended_err {
 #ifdef __KERNEL__
 
 #include <net/ip.h>
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 #include <linux/ipv6.h>
 #endif
 
@@ -34,7 +34,7 @@ struct sock_extended_err {
 struct sock_exterr_skb {
 	union {
 		struct inet_skb_parm	h4;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		struct inet6_skb_parm	h6;
 #endif
 	} header;
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index de33de1..b38bf69 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -543,9 +543,15 @@ struct compat_ethtool_rxnfc {
 /**
  * struct ethtool_rxfh_indir - command to get or set RX flow hash indirection
  * @cmd: Specific command number - %ETHTOOL_GRXFHINDIR or %ETHTOOL_SRXFHINDIR
- * @size: On entry, the array size of the user buffer.  On return from
- *	%ETHTOOL_GRXFHINDIR, the array size of the hardware indirection table.
+ * @size: On entry, the array size of the user buffer, which may be zero.
+ *	On return from %ETHTOOL_GRXFHINDIR, the array size of the hardware
+ *	indirection table.
  * @ring_index: RX ring/queue index for each hash value
+ *
+ * For %ETHTOOL_GRXFHINDIR, a @size of zero means that only the size
+ * should be returned.  For %ETHTOOL_SRXFHINDIR, a @size of zero means
+ * the table should be reset to default values.  This last feature
+ * is not supported by the original implementations.
  */
 struct ethtool_rxfh_indir {
 	__u32	cmd;
@@ -724,9 +730,6 @@ enum ethtool_sfeatures_retval_bits {
 
 #include <linux/rculist.h>
 
-/* needed by dev_disable_lro() */
-extern int __ethtool_set_flags(struct net_device *dev, u32 flags);
-
 extern int __ethtool_get_settings(struct net_device *dev,
 				  struct ethtool_cmd *cmd);
 
@@ -750,19 +753,18 @@ struct net_device;
 
 /* Some generic methods drivers may use in their ethtool_ops */
 u32 ethtool_op_get_link(struct net_device *dev);
-u32 ethtool_op_get_tx_csum(struct net_device *dev);
-int ethtool_op_set_tx_csum(struct net_device *dev, u32 data);
-int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data);
-int ethtool_op_set_tx_ipv6_csum(struct net_device *dev, u32 data);
-u32 ethtool_op_get_sg(struct net_device *dev);
-int ethtool_op_set_sg(struct net_device *dev, u32 data);
-u32 ethtool_op_get_tso(struct net_device *dev);
-int ethtool_op_set_tso(struct net_device *dev, u32 data);
-u32 ethtool_op_get_ufo(struct net_device *dev);
-int ethtool_op_set_ufo(struct net_device *dev, u32 data);
-u32 ethtool_op_get_flags(struct net_device *dev);
-int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported);
-bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported);
+
+/**
+ * ethtool_rxfh_indir_default - get default value for RX flow hash indirection
+ * @index: Index in RX flow hash indirection table
+ * @n_rx_rings: Number of RX rings to use
+ *
+ * This function provides the default policy for RX flow hash indirection.
+ */
+static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings)
+{
+	return index % n_rx_rings;
+}
 
 /**
  * struct ethtool_ops - optional netdev operations
@@ -807,22 +809,6 @@ bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported);
  * @get_pauseparam: Report pause parameters
  * @set_pauseparam: Set pause parameters.  Returns a negative error code
  *	or zero.
- * @get_rx_csum: Deprecated in favour of the netdev feature %NETIF_F_RXCSUM.
- *	Report whether receive checksums are turned on or off.
- * @set_rx_csum: Deprecated in favour of generic netdev features.  Turn
- *	receive checksum on or off.  Returns a negative error code or zero.
- * @get_tx_csum: Deprecated as redundant. Report whether transmit checksums
- *	are turned on or off.
- * @set_tx_csum: Deprecated in favour of generic netdev features.  Turn
- *	transmit checksums on or off.  Returns a negative error code or zero.
- * @get_sg: Deprecated as redundant.  Report whether scatter-gather is
- *	enabled.  
- * @set_sg: Deprecated in favour of generic netdev features.  Turn
- *	scatter-gather on or off. Returns a negative error code or zero.
- * @get_tso: Deprecated as redundant.  Report whether TCP segmentation
- *	offload is enabled.
- * @set_tso: Deprecated in favour of generic netdev features.  Turn TCP
- *	segmentation offload on or off.  Returns a negative error code or zero.
  * @self_test: Run specified self-tests
  * @get_strings: Return a set of strings that describe the requested objects
  * @set_phys_id: Identify the physical devices, e.g. by flashing an LED
@@ -844,15 +830,6 @@ bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported);
  *	negative error code or zero.
  * @complete: Function to be called after any other operation except
  *	@begin.  Will be called even if the other operation failed.
- * @get_ufo: Deprecated as redundant.  Report whether UDP fragmentation
- *	offload is enabled.
- * @set_ufo: Deprecated in favour of generic netdev features.  Turn UDP
- *	fragmentation offload on or off.  Returns a negative error code or zero.
- * @get_flags: Deprecated as redundant.  Report features included in
- *	&enum ethtool_flags that are enabled.  
- * @set_flags: Deprecated in favour of generic netdev features.  Turn
- *	features included in &enum ethtool_flags on or off.  Returns a
- *	negative error code or zero.
  * @get_priv_flags: Report driver-specific feature flags.
  * @set_priv_flags: Set driver-specific feature flags.  Returns a negative
  *	error code or zero.
@@ -868,9 +845,13 @@ bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported);
  *	error code or zero.
  * @set_rx_ntuple: Set an RX n-tuple rule.  Returns a negative error code
  *	or zero.
+ * @get_rxfh_indir_size: Get the size of the RX flow hash indirection table.
+ *	Returns zero if not supported for this specific device.
  * @get_rxfh_indir: Get the contents of the RX flow hash indirection table.
+ *	Will not be called if @get_rxfh_indir_size returns zero.
  *	Returns a negative error code or zero.
  * @set_rxfh_indir: Set the contents of the RX flow hash indirection table.
+ *	Will not be called if @get_rxfh_indir_size returns zero.
  *	Returns a negative error code or zero.
  * @get_channels: Get number of channels.
  * @set_channels: Set number of channels.  Returns a negative error code or
@@ -917,14 +898,6 @@ struct ethtool_ops {
 				  struct ethtool_pauseparam*);
 	int	(*set_pauseparam)(struct net_device *,
 				  struct ethtool_pauseparam*);
-	u32	(*get_rx_csum)(struct net_device *);
-	int	(*set_rx_csum)(struct net_device *, u32);
-	u32	(*get_tx_csum)(struct net_device *);
-	int	(*set_tx_csum)(struct net_device *, u32);
-	u32	(*get_sg)(struct net_device *);
-	int	(*set_sg)(struct net_device *, u32);
-	u32	(*get_tso)(struct net_device *);
-	int	(*set_tso)(struct net_device *, u32);
 	void	(*self_test)(struct net_device *, struct ethtool_test *, u64 *);
 	void	(*get_strings)(struct net_device *, u32 stringset, u8 *);
 	int	(*set_phys_id)(struct net_device *, enum ethtool_phys_id_state);
@@ -932,10 +905,6 @@ struct ethtool_ops {
 				     struct ethtool_stats *, u64 *);
 	int	(*begin)(struct net_device *);
 	void	(*complete)(struct net_device *);
-	u32	(*get_ufo)(struct net_device *);
-	int	(*set_ufo)(struct net_device *, u32);
-	u32	(*get_flags)(struct net_device *);
-	int	(*set_flags)(struct net_device *, u32);
 	u32	(*get_priv_flags)(struct net_device *);
 	int	(*set_priv_flags)(struct net_device *, u32);
 	int	(*get_sset_count)(struct net_device *, int);
@@ -946,10 +915,9 @@ struct ethtool_ops {
 	int	(*reset)(struct net_device *, u32 *);
 	int	(*set_rx_ntuple)(struct net_device *,
 				 struct ethtool_rx_ntuple *);
-	int	(*get_rxfh_indir)(struct net_device *,
-				  struct ethtool_rxfh_indir *);
-	int	(*set_rxfh_indir)(struct net_device *,
-				  const struct ethtool_rxfh_indir *);
+	u32	(*get_rxfh_indir_size)(struct net_device *);
+	int	(*get_rxfh_indir)(struct net_device *, u32 *);
+	int	(*set_rxfh_indir)(struct net_device *, const u32 *);
 	void	(*get_channels)(struct net_device *, struct ethtool_channels *);
 	int	(*set_channels)(struct net_device *, struct ethtool_channels *);
 	int	(*get_dump_flag)(struct net_device *, struct ethtool_dump *);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0c4df26..e313022 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1886,6 +1886,7 @@ extern struct dentry *mount_single(struct file_system_type *fs_type,
 extern struct dentry *mount_nodev(struct file_system_type *fs_type,
 	int flags, void *data,
 	int (*fill_super)(struct super_block *, void *, int));
+extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
 void generic_shutdown_super(struct super_block *sb);
 void kill_block_super(struct super_block *sb);
 void kill_anon_super(struct super_block *sb);
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 96efa67..c3da42d 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -172,6 +172,7 @@ enum {
 	TRACE_EVENT_FL_FILTERED_BIT,
 	TRACE_EVENT_FL_RECORDED_CMD_BIT,
 	TRACE_EVENT_FL_CAP_ANY_BIT,
+	TRACE_EVENT_FL_NO_SET_FILTER_BIT,
 };
 
 enum {
@@ -179,6 +180,7 @@ enum {
 	TRACE_EVENT_FL_FILTERED		= (1 << TRACE_EVENT_FL_FILTERED_BIT),
 	TRACE_EVENT_FL_RECORDED_CMD	= (1 << TRACE_EVENT_FL_RECORDED_CMD_BIT),
 	TRACE_EVENT_FL_CAP_ANY		= (1 << TRACE_EVENT_FL_CAP_ANY_BIT),
+	TRACE_EVENT_FL_NO_SET_FILTER	= (1 << TRACE_EVENT_FL_NO_SET_FILTER_BIT),
 };
 
 struct ftrace_event_call {
diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h
index 61549b2..73c28de 100644
--- a/include/linux/genetlink.h
+++ b/include/linux/genetlink.h
@@ -85,6 +85,30 @@ enum {
 /* All generic netlink requests are serialized by a global lock.  */
 extern void genl_lock(void);
 extern void genl_unlock(void);
+#ifdef CONFIG_PROVE_LOCKING
+extern int lockdep_genl_is_held(void);
+#endif
+
+/**
+ * rcu_dereference_genl - rcu_dereference with debug checking
+ * @p: The pointer to read, prior to dereferencing
+ *
+ * Do an rcu_dereference(p), but check caller either holds rcu_read_lock()
+ * or genl mutex. Note : Please prefer genl_dereference() or rcu_dereference()
+ */
+#define rcu_dereference_genl(p)					\
+	rcu_dereference_check(p, lockdep_genl_is_held())
+
+/**
+ * genl_dereference - fetch RCU pointer when updates are prevented by genl mutex
+ * @p: The pointer to read, prior to dereferencing
+ *
+ * Return the value of the specified RCU-protected pointer, but omit
+ * both the smp_read_barrier_depends() and the ACCESS_ONCE(), because
+ * caller holds genl mutex.
+ */
+#define genl_dereference(p)					\
+	rcu_dereference_protected(p, lockdep_genl_is_held())
 
 #endif /* __KERNEL__ */
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 9de31bc..6d18f35 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -21,8 +21,6 @@
 #define dev_to_part(device)	container_of((device), struct hd_struct, __dev)
 #define disk_to_dev(disk)	(&(disk)->part0.__dev)
 #define part_to_dev(part)	(&((part)->__dev))
-#define alias_name(disk)	((disk)->alias ? (disk)->alias : \
-						 (disk)->disk_name)
 
 extern struct device_type part_type;
 extern struct kobject *block_depr;
@@ -60,7 +58,6 @@ enum {
 
 #define DISK_MAX_PARTS			256
 #define DISK_NAME_LEN			32
-#define ALIAS_LEN			256
 
 #include <linux/major.h>
 #include <linux/device.h>
@@ -166,7 +163,6 @@ struct gendisk {
                                          * disks that can't be partitioned. */
 
 	char disk_name[DISK_NAME_LEN];	/* name of major driver */
-	char *alias;			/* alias name of disk */
 	char *(*devnode)(struct gendisk *gd, mode_t *mode);
 
 	unsigned int events;		/* supported events */
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 19644e0..d9d6c86 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -110,11 +110,6 @@ static inline void copy_huge_page(struct page *dst, struct page *src)
 
 #define hugetlb_change_protection(vma, address, end, newprot)
 
-#ifndef HPAGE_MASK
-#define HPAGE_MASK	PAGE_MASK		/* Keep the compiler happy */
-#define HPAGE_SIZE	PAGE_SIZE
-#endif
-
 #endif /* !CONFIG_HUGETLB_PAGE */
 
 #define HUGETLB_ANON_FILE "anon_hugepage"
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index a81bf6d..07d103a 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -432,9 +432,6 @@ void i2c_unlock_adapter(struct i2c_adapter *);
 /* Internal numbers to terminate lists */
 #define I2C_CLIENT_END		0xfffeU
 
-/* The numbers to use to set I2C bus address */
-#define ANY_I2C_BUS		0xffff
-
 /* Construct an I2C_CLIENT_END-terminated array of i2c addresses */
 #define I2C_ADDRS(addr, addrs...) \
 	((const unsigned short []){ addr, ## addrs, I2C_CLIENT_END })
diff --git a/include/linux/if.h b/include/linux/if.h
index db20bd4..06b6ef6 100644
--- a/include/linux/if.h
+++ b/include/linux/if.h
@@ -79,6 +79,7 @@
 #define IFF_TX_SKB_SHARING	0x10000	/* The interface supports sharing
 					 * skbs on transmit */
 #define IFF_UNICAST_FLT	0x20000		/* Supports unicast filtering	*/
+#define IFF_TEAM_PORT	0x40000		/* device used as team port */
 
 #define IF_GET_IFACE	0x0001		/* for querying only */
 #define IF_GET_PROTO	0x0002
diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h
index e473003..56d907a 100644
--- a/include/linux/if_ether.h
+++ b/include/linux/if_ether.h
@@ -79,6 +79,7 @@
 #define ETH_P_PAE	0x888E		/* Port Access Entity (IEEE 802.1X) */
 #define ETH_P_AOE	0x88A2		/* ATA over Ethernet		*/
 #define ETH_P_8021AD	0x88A8          /* 802.1ad Service VLAN		*/
+#define ETH_P_802_EX1	0x88B5		/* 802.1 Local Experimental 1.  */
 #define ETH_P_TIPC	0x88CA		/* TIPC 			*/
 #define ETH_P_8021AH	0x88E7          /* 802.1ah Backbone Service Tag */
 #define ETH_P_1588	0x88F7		/* IEEE 1588 Timesync */
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
new file mode 100644
index 0000000..828181f
--- /dev/null
+++ b/include/linux/if_team.h
@@ -0,0 +1,242 @@
+/*
+ * include/linux/if_team.h - Network team device driver header
+ * Copyright (c) 2011 Jiri Pirko <jpirko@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _LINUX_IF_TEAM_H_
+#define _LINUX_IF_TEAM_H_
+
+#ifdef __KERNEL__
+
+struct team_pcpu_stats {
+	u64			rx_packets;
+	u64			rx_bytes;
+	u64			rx_multicast;
+	u64			tx_packets;
+	u64			tx_bytes;
+	struct u64_stats_sync	syncp;
+	u32			rx_dropped;
+	u32			tx_dropped;
+};
+
+struct team;
+
+struct team_port {
+	struct net_device *dev;
+	struct hlist_node hlist; /* node in hash list */
+	struct list_head list; /* node in ordinary list */
+	struct team *team;
+	int index;
+
+	/*
+	 * A place for storing original values of the device before it
+	 * become a port.
+	 */
+	struct {
+		unsigned char dev_addr[MAX_ADDR_LEN];
+		unsigned int mtu;
+	} orig;
+
+	bool linkup;
+	u32 speed;
+	u8 duplex;
+
+	struct rcu_head rcu;
+};
+
+struct team_mode_ops {
+	int (*init)(struct team *team);
+	void (*exit)(struct team *team);
+	rx_handler_result_t (*receive)(struct team *team,
+				       struct team_port *port,
+				       struct sk_buff *skb);
+	bool (*transmit)(struct team *team, struct sk_buff *skb);
+	int (*port_enter)(struct team *team, struct team_port *port);
+	void (*port_leave)(struct team *team, struct team_port *port);
+	void (*port_change_mac)(struct team *team, struct team_port *port);
+};
+
+enum team_option_type {
+	TEAM_OPTION_TYPE_U32,
+	TEAM_OPTION_TYPE_STRING,
+};
+
+struct team_option {
+	struct list_head list;
+	const char *name;
+	enum team_option_type type;
+	int (*getter)(struct team *team, void *arg);
+	int (*setter)(struct team *team, void *arg);
+};
+
+struct team_mode {
+	struct list_head list;
+	const char *kind;
+	struct module *owner;
+	size_t priv_size;
+	const struct team_mode_ops *ops;
+};
+
+#define TEAM_PORT_HASHBITS 4
+#define TEAM_PORT_HASHENTRIES (1 << TEAM_PORT_HASHBITS)
+
+#define TEAM_MODE_PRIV_LONGS 4
+#define TEAM_MODE_PRIV_SIZE (sizeof(long) * TEAM_MODE_PRIV_LONGS)
+
+struct team {
+	struct net_device *dev; /* associated netdevice */
+	struct team_pcpu_stats __percpu *pcpu_stats;
+
+	struct mutex lock; /* used for overall locking, e.g. port lists write */
+
+	/*
+	 * port lists with port count
+	 */
+	int port_count;
+	struct hlist_head port_hlist[TEAM_PORT_HASHENTRIES];
+	struct list_head port_list;
+
+	struct list_head option_list;
+
+	const struct team_mode *mode;
+	struct team_mode_ops ops;
+	long mode_priv[TEAM_MODE_PRIV_LONGS];
+};
+
+static inline struct hlist_head *team_port_index_hash(struct team *team,
+						      int port_index)
+{
+	return &team->port_hlist[port_index & (TEAM_PORT_HASHENTRIES - 1)];
+}
+
+static inline struct team_port *team_get_port_by_index(struct team *team,
+						       int port_index)
+{
+	struct hlist_node *p;
+	struct team_port *port;
+	struct hlist_head *head = team_port_index_hash(team, port_index);
+
+	hlist_for_each_entry(port, p, head, hlist)
+		if (port->index == port_index)
+			return port;
+	return NULL;
+}
+static inline struct team_port *team_get_port_by_index_rcu(struct team *team,
+							   int port_index)
+{
+	struct hlist_node *p;
+	struct team_port *port;
+	struct hlist_head *head = team_port_index_hash(team, port_index);
+
+	hlist_for_each_entry_rcu(port, p, head, hlist)
+		if (port->index == port_index)
+			return port;
+	return NULL;
+}
+
+extern int team_port_set_team_mac(struct team_port *port);
+extern int team_options_register(struct team *team,
+				 const struct team_option *option,
+				 size_t option_count);
+extern void team_options_unregister(struct team *team,
+				    const struct team_option *option,
+				    size_t option_count);
+extern int team_mode_register(struct team_mode *mode);
+extern int team_mode_unregister(struct team_mode *mode);
+
+#endif /* __KERNEL__ */
+
+#define TEAM_STRING_MAX_LEN 32
+
+/**********************************
+ * NETLINK_GENERIC netlink family.
+ **********************************/
+
+enum {
+	TEAM_CMD_NOOP,
+	TEAM_CMD_OPTIONS_SET,
+	TEAM_CMD_OPTIONS_GET,
+	TEAM_CMD_PORT_LIST_GET,
+
+	__TEAM_CMD_MAX,
+	TEAM_CMD_MAX = (__TEAM_CMD_MAX - 1),
+};
+
+enum {
+	TEAM_ATTR_UNSPEC,
+	TEAM_ATTR_TEAM_IFINDEX,		/* u32 */
+	TEAM_ATTR_LIST_OPTION,		/* nest */
+	TEAM_ATTR_LIST_PORT,		/* nest */
+
+	__TEAM_ATTR_MAX,
+	TEAM_ATTR_MAX = __TEAM_ATTR_MAX - 1,
+};
+
+/* Nested layout of get/set msg:
+ *
+ *	[TEAM_ATTR_LIST_OPTION]
+ *		[TEAM_ATTR_ITEM_OPTION]
+ *			[TEAM_ATTR_OPTION_*], ...
+ *		[TEAM_ATTR_ITEM_OPTION]
+ *			[TEAM_ATTR_OPTION_*], ...
+ *		...
+ *	[TEAM_ATTR_LIST_PORT]
+ *		[TEAM_ATTR_ITEM_PORT]
+ *			[TEAM_ATTR_PORT_*], ...
+ *		[TEAM_ATTR_ITEM_PORT]
+ *			[TEAM_ATTR_PORT_*], ...
+ *		...
+ */
+
+enum {
+	TEAM_ATTR_ITEM_OPTION_UNSPEC,
+	TEAM_ATTR_ITEM_OPTION,		/* nest */
+
+	__TEAM_ATTR_ITEM_OPTION_MAX,
+	TEAM_ATTR_ITEM_OPTION_MAX = __TEAM_ATTR_ITEM_OPTION_MAX - 1,
+};
+
+enum {
+	TEAM_ATTR_OPTION_UNSPEC,
+	TEAM_ATTR_OPTION_NAME,		/* string */
+	TEAM_ATTR_OPTION_CHANGED,	/* flag */
+	TEAM_ATTR_OPTION_TYPE,		/* u8 */
+	TEAM_ATTR_OPTION_DATA,		/* dynamic */
+
+	__TEAM_ATTR_OPTION_MAX,
+	TEAM_ATTR_OPTION_MAX = __TEAM_ATTR_OPTION_MAX - 1,
+};
+
+enum {
+	TEAM_ATTR_ITEM_PORT_UNSPEC,
+	TEAM_ATTR_ITEM_PORT,		/* nest */
+
+	__TEAM_ATTR_ITEM_PORT_MAX,
+	TEAM_ATTR_ITEM_PORT_MAX = __TEAM_ATTR_ITEM_PORT_MAX - 1,
+};
+
+enum {
+	TEAM_ATTR_PORT_UNSPEC,
+	TEAM_ATTR_PORT_IFINDEX,		/* u32 */
+	TEAM_ATTR_PORT_CHANGED,		/* flag */
+	TEAM_ATTR_PORT_LINKUP,		/* flag */
+	TEAM_ATTR_PORT_SPEED,		/* u32 */
+	TEAM_ATTR_PORT_DUPLEX,		/* u8 */
+
+	__TEAM_ATTR_PORT_MAX,
+	TEAM_ATTR_PORT_MAX = __TEAM_ATTR_PORT_MAX - 1,
+};
+
+/*
+ * NETLINK_GENERIC related info
+ */
+#define TEAM_GENL_NAME "team"
+#define TEAM_GENL_VERSION 0x1
+#define TEAM_GENL_CHANGE_EVENT_MC_GRP_NAME "change_event"
+
+#endif /* _LINUX_IF_TEAM_H_ */
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 12d5543..13aff1e 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -74,22 +74,7 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb)
 /* found in socket.c */
 extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *));
 
-/* if this changes, algorithm will have to be reworked because this
- * depends on completely exhausting the VLAN identifier space.  Thus
- * it gives constant time look-up, but in many cases it wastes memory.
- */
-#define VLAN_GROUP_ARRAY_SPLIT_PARTS  8
-#define VLAN_GROUP_ARRAY_PART_LEN     (VLAN_N_VID/VLAN_GROUP_ARRAY_SPLIT_PARTS)
-
-struct vlan_group {
-	struct net_device	*real_dev; /* The ethernet(like) device
-					    * the vlan is attached to.
-					    */
-	unsigned int		nr_vlans;
-	struct hlist_node	hlist;	/* linked list */
-	struct net_device **vlan_devices_arrays[VLAN_GROUP_ARRAY_SPLIT_PARTS];
-	struct rcu_head		rcu;
-};
+struct vlan_info;
 
 static inline int is_vlan_dev(struct net_device *dev)
 {
@@ -109,6 +94,13 @@ extern u16 vlan_dev_vlan_id(const struct net_device *dev);
 extern bool vlan_do_receive(struct sk_buff **skb, bool last_handler);
 extern struct sk_buff *vlan_untag(struct sk_buff *skb);
 
+extern int vlan_vid_add(struct net_device *dev, unsigned short vid);
+extern void vlan_vid_del(struct net_device *dev, unsigned short vid);
+
+extern int vlan_vids_add_by_dev(struct net_device *dev,
+				const struct net_device *by_dev);
+extern void vlan_vids_del_by_dev(struct net_device *dev,
+				 const struct net_device *by_dev);
 #else
 static inline struct net_device *
 __vlan_find_dev_deep(struct net_device *real_dev, u16 vlan_id)
@@ -139,6 +131,26 @@ static inline struct sk_buff *vlan_untag(struct sk_buff *skb)
 {
 	return skb;
 }
+
+static inline int vlan_vid_add(struct net_device *dev, unsigned short vid)
+{
+	return 0;
+}
+
+static inline void vlan_vid_del(struct net_device *dev, unsigned short vid)
+{
+}
+
+static inline int vlan_vids_add_by_dev(struct net_device *dev,
+				       const struct net_device *by_dev)
+{
+	return 0;
+}
+
+static inline void vlan_vids_del_by_dev(struct net_device *dev,
+					const struct net_device *by_dev)
+{
+}
 #endif
 
 /**
@@ -310,6 +322,40 @@ static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
 
 	return protocol;
 }
+
+static inline void vlan_set_encap_proto(struct sk_buff *skb,
+					struct vlan_hdr *vhdr)
+{
+	__be16 proto;
+	unsigned char *rawp;
+
+	/*
+	 * Was a VLAN packet, grab the encapsulated protocol, which the layer
+	 * three protocols care about.
+	 */
+
+	proto = vhdr->h_vlan_encapsulated_proto;
+	if (ntohs(proto) >= 1536) {
+		skb->protocol = proto;
+		return;
+	}
+
+	rawp = skb->data;
+	if (*(unsigned short *) rawp == 0xFFFF)
+		/*
+		 * This is a magic hack to spot IPX packets. Older Novell
+		 * breaks the protocol design and runs IPX over 802.3 without
+		 * an 802.2 LLC layer. We look for FFFF which isn't a used
+		 * 802.2 SSAP/DSAP. This won't work for fault tolerant netware
+		 * but does for the rest.
+		 */
+		skb->protocol = htons(ETH_P_802_3);
+	else
+		/*
+		 * Real 802.2 LLC
+		 */
+		skb->protocol = htons(ETH_P_802_2);
+}
 #endif /* __KERNEL__ */
 
 /* VLAN IOCTLs are found in sockios.h */
@@ -352,7 +398,7 @@ struct vlan_ioctl_args {
 		unsigned int skb_priority;
 		unsigned int name_type;
 		unsigned int bind_type;
-		unsigned int flag; /* Matches vlan_dev_info flags */
+		unsigned int flag; /* Matches vlan_dev_priv flags */
         } u;
 
 	short vlan_qos;   
diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h
index 80b480c..afa5d5c 100644
--- a/include/linux/inet_diag.h
+++ b/include/linux/inet_diag.h
@@ -22,7 +22,7 @@ struct inet_diag_sockid {
 
 /* Request structure */
 
-struct inet_diag_req {
+struct inet_diag_req_compat {
 	__u8	idiag_family;		/* Family of addresses. */
 	__u8	idiag_src_len;
 	__u8	idiag_dst_len;
@@ -34,6 +34,15 @@ struct inet_diag_req {
 	__u32	idiag_dbs;		/* Tables to dump (NI) */
 };
 
+struct inet_diag_req {
+	__u8	sdiag_family;
+	__u8	sdiag_protocol;
+	__u8	idiag_ext;
+	__u8	pad;
+	__u32	idiag_states;
+	struct inet_diag_sockid id;
+};
+
 enum {
 	INET_DIAG_REQ_NONE,
 	INET_DIAG_REQ_BYTECODE,
@@ -98,9 +107,10 @@ enum {
 	INET_DIAG_VEGASINFO,
 	INET_DIAG_CONG,
 	INET_DIAG_TOS,
+	INET_DIAG_TCLASS,
 };
 
-#define INET_DIAG_MAX INET_DIAG_TOS
+#define INET_DIAG_MAX INET_DIAG_TCLASS
 
 
 /* INET_DIAG_MEM */
@@ -124,16 +134,41 @@ struct tcpvegas_info {
 #ifdef __KERNEL__
 struct sock;
 struct inet_hashinfo;
+struct nlattr;
+struct nlmsghdr;
+struct sk_buff;
+struct netlink_callback;
 
 struct inet_diag_handler {
-	struct inet_hashinfo    *idiag_hashinfo;
+	void			(*dump)(struct sk_buff *skb,
+					struct netlink_callback *cb,
+					struct inet_diag_req *r,
+					struct nlattr *bc);
+
+	int			(*dump_one)(struct sk_buff *in_skb,
+					const struct nlmsghdr *nlh,
+					struct inet_diag_req *req);
+
 	void			(*idiag_get_info)(struct sock *sk,
 						  struct inet_diag_msg *r,
 						  void *info);
-	__u16                   idiag_info_size;
 	__u16                   idiag_type;
 };
 
+struct inet_connection_sock;
+int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
+			      struct sk_buff *skb, struct inet_diag_req *req,
+			      u32 pid, u32 seq, u16 nlmsg_flags,
+			      const struct nlmsghdr *unlh);
+void inet_diag_dump_icsk(struct inet_hashinfo *h, struct sk_buff *skb,
+		struct netlink_callback *cb, struct inet_diag_req *r,
+		struct nlattr *bc);
+int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
+		struct sk_buff *in_skb, const struct nlmsghdr *nlh,
+		struct inet_diag_req *req);
+
+int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk);
+
 extern int  inet_diag_register(const struct inet_diag_handler *handler);
 extern void inet_diag_unregister(const struct inet_diag_handler *handler);
 #endif /* __KERNEL__ */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 08ffab0..32574ee 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -126,6 +126,8 @@ extern struct cred init_cred;
 # define INIT_PERF_EVENTS(tsk)
 #endif
 
+#define INIT_TASK_COMM "swapper"
+
 /*
  *  INIT_TASK is used to set up the first task table, touch at
  * your own risk!. Base=0, limit=0x1fffff (=2MB)
@@ -162,7 +164,7 @@ extern struct cred init_cred;
 	.group_leader	= &tsk,						\
 	RCU_INIT_POINTER(.real_cred, &init_cred),			\
 	RCU_INIT_POINTER(.cred, &init_cred),				\
-	.comm		= "swapper",					\
+	.comm		= INIT_TASK_COMM,				\
 	.thread		= INIT_THREAD,					\
 	.fs		= &init_fs,					\
 	.files		= &init_files,					\
@@ -184,7 +186,6 @@ extern struct cred init_cred;
 		[PIDTYPE_SID]  = INIT_PID_LINK(PIDTYPE_SID),		\
 	},								\
 	.thread_group	= LIST_HEAD_INIT(tsk.thread_group),		\
-	.dirties = INIT_PROP_LOCAL_SINGLE(dirties),			\
 	INIT_IDS							\
 	INIT_PERF_EVENTS(tsk)						\
 	INIT_TRACE_IRQFLAGS						\
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 0c99776..6318268 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -404,7 +404,7 @@ struct tcp6_sock {
 
 extern int inet6_sk_rebuild_header(struct sock *sk);
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static inline struct ipv6_pinfo * inet6_sk(const struct sock *__sk)
 {
 	return inet_sk(__sk)->pinet6;
@@ -515,7 +515,7 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk)
 #define inet6_rcv_saddr(__sk)	NULL
 #define tcp_twsk_ipv6only(__sk)		0
 #define inet_v6_ipv6only(__sk)		0
-#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#endif /* IS_ENABLED(CONFIG_IPV6) */
 
 #define INET6_MATCH(__sk, __net, __hash, __saddr, __daddr, __ports, __dif)\
 	(((__sk)->sk_hash == (__hash)) && sock_net((__sk)) == (__net)	&& \
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index f47fcd3..c3892fc 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -555,7 +555,6 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_PPC_SMT 64
 #define KVM_CAP_PPC_RMA	65
 #define KVM_CAP_MAX_VCPUS 66       /* returns max vcpus per vm */
-#define KVM_CAP_PPC_HIOR 67
 #define KVM_CAP_PPC_PAPR 68
 #define KVM_CAP_S390_GMAP 71
 
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index ff9abff..90b0656 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -301,7 +301,7 @@ static inline int __nlm_privileged_request4(const struct sockaddr *sap)
 	return ipv4_is_loopback(sin->sin_addr.s_addr);
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static inline int __nlm_privileged_request6(const struct sockaddr *sap)
 {
 	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
@@ -314,12 +314,12 @@ static inline int __nlm_privileged_request6(const struct sockaddr *sap)
 
 	return ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LOOPBACK;
 }
-#else	/* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#else	/* IS_ENABLED(CONFIG_IPV6) */
 static inline int __nlm_privileged_request6(const struct sockaddr *sap)
 {
 	return 0;
 }
-#endif	/* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#endif	/* IS_ENABLED(CONFIG_IPV6) */
 
 /*
  * Ensure incoming requests are from local privileged callers.
diff --git a/include/linux/mdio-bitbang.h b/include/linux/mdio-bitbang.h
index 0fe00cd..76f52bb 100644
--- a/include/linux/mdio-bitbang.h
+++ b/include/linux/mdio-bitbang.h
@@ -32,6 +32,8 @@ struct mdiobb_ops {
 
 struct mdiobb_ctrl {
 	const struct mdiobb_ops *ops;
+	/* reset callback */
+	int (*reset)(struct mii_bus *bus);
 };
 
 /* The returned bus is not yet registered with the phy layer. */
diff --git a/include/linux/mdio-gpio.h b/include/linux/mdio-gpio.h
index e9d3fdf..7c9fe3c 100644
--- a/include/linux/mdio-gpio.h
+++ b/include/linux/mdio-gpio.h
@@ -20,6 +20,8 @@ struct mdio_gpio_platform_data {
 
 	unsigned int phy_mask;
 	int irqs[PHY_MAX_ADDR];
+	/* reset callback */
+	int (*reset)(struct mii_bus *bus);
 };
 
 #endif /* __LINUX_MDIO_GPIO_H */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index b87068a..9b296ea 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -85,6 +85,9 @@ extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
 extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
 extern struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm);
 
+extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
+extern struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont);
+
 static inline
 int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup)
 {
@@ -381,5 +384,25 @@ mem_cgroup_print_bad_page(struct page *page)
 }
 #endif
 
+enum {
+	UNDER_LIMIT,
+	SOFT_LIMIT,
+	OVER_LIMIT,
+};
+
+#ifdef CONFIG_INET
+struct sock;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+void sock_update_memcg(struct sock *sk);
+void sock_release_memcg(struct sock *sk);
+#else
+static inline void sock_update_memcg(struct sock *sk)
+{
+}
+static inline void sock_release_memcg(struct sock *sk)
+{
+}
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
+#endif /* CONFIG_INET */
 #endif /* _LINUX_MEMCONTROL_H */
 
diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h
index 82b4c88..8bf2cb9 100644
--- a/include/linux/mfd/tps65910.h
+++ b/include/linux/mfd/tps65910.h
@@ -243,7 +243,8 @@
 
 
 /*Registers VDD1, VDD2 voltage values definitions */
-#define VDD1_2_NUM_VOLTS				73
+#define VDD1_2_NUM_VOLT_FINE				73
+#define VDD1_2_NUM_VOLT_COARSE				3
 #define VDD1_2_MIN_VOLT					6000
 #define VDD1_2_OFFSET					125
 
diff --git a/include/linux/mii.h b/include/linux/mii.h
index 2774823..2783eca 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -9,6 +9,7 @@
 #define __LINUX_MII_H__
 
 #include <linux/types.h>
+#include <linux/ethtool.h>
 
 /* Generic MII registers. */
 #define MII_BMCR		0x00	/* Basic mode control register */
@@ -240,6 +241,205 @@ static inline unsigned int mii_duplex (unsigned int duplex_lock,
 }
 
 /**
+ * ethtool_adv_to_mii_adv_t
+ * @ethadv: the ethtool advertisement settings
+ *
+ * A small helper function that translates ethtool advertisement
+ * settings to phy autonegotiation advertisements for the
+ * MII_ADVERTISE register.
+ */
+static inline u32 ethtool_adv_to_mii_adv_t(u32 ethadv)
+{
+	u32 result = 0;
+
+	if (ethadv & ADVERTISED_10baseT_Half)
+		result |= ADVERTISE_10HALF;
+	if (ethadv & ADVERTISED_10baseT_Full)
+		result |= ADVERTISE_10FULL;
+	if (ethadv & ADVERTISED_100baseT_Half)
+		result |= ADVERTISE_100HALF;
+	if (ethadv & ADVERTISED_100baseT_Full)
+		result |= ADVERTISE_100FULL;
+	if (ethadv & ADVERTISED_Pause)
+		result |= ADVERTISE_PAUSE_CAP;
+	if (ethadv & ADVERTISED_Asym_Pause)
+		result |= ADVERTISE_PAUSE_ASYM;
+
+	return result;
+}
+
+/**
+ * mii_adv_to_ethtool_adv_t
+ * @adv: value of the MII_ADVERTISE register
+ *
+ * A small helper function that translates MII_ADVERTISE bits
+ * to ethtool advertisement settings.
+ */
+static inline u32 mii_adv_to_ethtool_adv_t(u32 adv)
+{
+	u32 result = 0;
+
+	if (adv & ADVERTISE_10HALF)
+		result |= ADVERTISED_10baseT_Half;
+	if (adv & ADVERTISE_10FULL)
+		result |= ADVERTISED_10baseT_Full;
+	if (adv & ADVERTISE_100HALF)
+		result |= ADVERTISED_100baseT_Half;
+	if (adv & ADVERTISE_100FULL)
+		result |= ADVERTISED_100baseT_Full;
+	if (adv & ADVERTISE_PAUSE_CAP)
+		result |= ADVERTISED_Pause;
+	if (adv & ADVERTISE_PAUSE_ASYM)
+		result |= ADVERTISED_Asym_Pause;
+
+	return result;
+}
+
+/**
+ * ethtool_adv_to_mii_ctrl1000_t
+ * @ethadv: the ethtool advertisement settings
+ *
+ * A small helper function that translates ethtool advertisement
+ * settings to phy autonegotiation advertisements for the
+ * MII_CTRL1000 register when in 1000T mode.
+ */
+static inline u32 ethtool_adv_to_mii_ctrl1000_t(u32 ethadv)
+{
+	u32 result = 0;
+
+	if (ethadv & ADVERTISED_1000baseT_Half)
+		result |= ADVERTISE_1000HALF;
+	if (ethadv & ADVERTISED_1000baseT_Full)
+		result |= ADVERTISE_1000FULL;
+
+	return result;
+}
+
+/**
+ * mii_ctrl1000_to_ethtool_adv_t
+ * @adv: value of the MII_CTRL1000 register
+ *
+ * A small helper function that translates MII_CTRL1000
+ * bits, when in 1000Base-T mode, to ethtool
+ * advertisement settings.
+ */
+static inline u32 mii_ctrl1000_to_ethtool_adv_t(u32 adv)
+{
+	u32 result = 0;
+
+	if (adv & ADVERTISE_1000HALF)
+		result |= ADVERTISED_1000baseT_Half;
+	if (adv & ADVERTISE_1000FULL)
+		result |= ADVERTISED_1000baseT_Full;
+
+	return result;
+}
+
+/**
+ * mii_lpa_to_ethtool_lpa_t
+ * @adv: value of the MII_LPA register
+ *
+ * A small helper function that translates MII_LPA
+ * bits, when in 1000Base-T mode, to ethtool
+ * LP advertisement settings.
+ */
+static inline u32 mii_lpa_to_ethtool_lpa_t(u32 lpa)
+{
+	u32 result = 0;
+
+	if (lpa & LPA_LPACK)
+		result |= ADVERTISED_Autoneg;
+
+	return result | mii_adv_to_ethtool_adv_t(lpa);
+}
+
+/**
+ * mii_stat1000_to_ethtool_lpa_t
+ * @adv: value of the MII_STAT1000 register
+ *
+ * A small helper function that translates MII_STAT1000
+ * bits, when in 1000Base-T mode, to ethtool
+ * advertisement settings.
+ */
+static inline u32 mii_stat1000_to_ethtool_lpa_t(u32 lpa)
+{
+	u32 result = 0;
+
+	if (lpa & LPA_1000HALF)
+		result |= ADVERTISED_1000baseT_Half;
+	if (lpa & LPA_1000FULL)
+		result |= ADVERTISED_1000baseT_Full;
+
+	return result;
+}
+
+/**
+ * ethtool_adv_to_mii_adv_x
+ * @ethadv: the ethtool advertisement settings
+ *
+ * A small helper function that translates ethtool advertisement
+ * settings to phy autonegotiation advertisements for the
+ * MII_CTRL1000 register when in 1000Base-X mode.
+ */
+static inline u32 ethtool_adv_to_mii_adv_x(u32 ethadv)
+{
+	u32 result = 0;
+
+	if (ethadv & ADVERTISED_1000baseT_Half)
+		result |= ADVERTISE_1000XHALF;
+	if (ethadv & ADVERTISED_1000baseT_Full)
+		result |= ADVERTISE_1000XFULL;
+	if (ethadv & ADVERTISED_Pause)
+		result |= ADVERTISE_1000XPAUSE;
+	if (ethadv & ADVERTISED_Asym_Pause)
+		result |= ADVERTISE_1000XPSE_ASYM;
+
+	return result;
+}
+
+/**
+ * mii_adv_to_ethtool_adv_x
+ * @adv: value of the MII_CTRL1000 register
+ *
+ * A small helper function that translates MII_CTRL1000
+ * bits, when in 1000Base-X mode, to ethtool
+ * advertisement settings.
+ */
+static inline u32 mii_adv_to_ethtool_adv_x(u32 adv)
+{
+	u32 result = 0;
+
+	if (adv & ADVERTISE_1000XHALF)
+		result |= ADVERTISED_1000baseT_Half;
+	if (adv & ADVERTISE_1000XFULL)
+		result |= ADVERTISED_1000baseT_Full;
+	if (adv & ADVERTISE_1000XPAUSE)
+		result |= ADVERTISED_Pause;
+	if (adv & ADVERTISE_1000XPSE_ASYM)
+		result |= ADVERTISED_Asym_Pause;
+
+	return result;
+}
+
+/**
+ * mii_lpa_to_ethtool_lpa_x
+ * @adv: value of the MII_LPA register
+ *
+ * A small helper function that translates MII_LPA
+ * bits, when in 1000Base-X mode, to ethtool
+ * LP advertisement settings.
+ */
+static inline u32 mii_lpa_to_ethtool_lpa_x(u32 lpa)
+{
+	u32 result = 0;
+
+	if (lpa & LPA_LPACK)
+		result |= ADVERTISED_Autoneg;
+
+	return result | mii_adv_to_ethtool_adv_x(lpa);
+}
+
+/**
  * mii_advertise_flowctrl - get flow control advertisement flags
  * @cap: Flow control capabilities (FLOW_CTRL_RX, FLOW_CTRL_TX or both)
  */
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index b56e458..9958ff2 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -59,12 +59,15 @@ enum {
 	MLX4_CMD_HW_HEALTH_CHECK = 0x50,
 	MLX4_CMD_SET_PORT	 = 0xc,
 	MLX4_CMD_SET_NODE	 = 0x5a,
+	MLX4_CMD_QUERY_FUNC	 = 0x56,
 	MLX4_CMD_ACCESS_DDR	 = 0x2e,
 	MLX4_CMD_MAP_ICM	 = 0xffa,
 	MLX4_CMD_UNMAP_ICM	 = 0xff9,
 	MLX4_CMD_MAP_ICM_AUX	 = 0xffc,
 	MLX4_CMD_UNMAP_ICM_AUX	 = 0xffb,
 	MLX4_CMD_SET_ICM_SIZE	 = 0xffd,
+	/*master notify fw on finish for slave's flr*/
+	MLX4_CMD_INFORM_FLR_DONE = 0x5b,
 
 	/* TPT commands */
 	MLX4_CMD_SW2HW_MPT	 = 0xd,
@@ -119,6 +122,26 @@ enum {
 	/* miscellaneous commands */
 	MLX4_CMD_DIAG_RPRT	 = 0x30,
 	MLX4_CMD_NOP		 = 0x31,
+	MLX4_CMD_ACCESS_MEM	 = 0x2e,
+	MLX4_CMD_SET_VEP	 = 0x52,
+
+	/* Ethernet specific commands */
+	MLX4_CMD_SET_VLAN_FLTR	 = 0x47,
+	MLX4_CMD_SET_MCAST_FLTR	 = 0x48,
+	MLX4_CMD_DUMP_ETH_STATS	 = 0x49,
+
+	/* Communication channel commands */
+	MLX4_CMD_ARM_COMM_CHANNEL = 0x57,
+	MLX4_CMD_GEN_EQE	 = 0x58,
+
+	/* virtual commands */
+	MLX4_CMD_ALLOC_RES	 = 0xf00,
+	MLX4_CMD_FREE_RES	 = 0xf01,
+	MLX4_CMD_MCAST_ATTACH	 = 0xf05,
+	MLX4_CMD_UCAST_ATTACH	 = 0xf06,
+	MLX4_CMD_PROMISC         = 0xf08,
+	MLX4_CMD_QUERY_FUNC_CAP  = 0xf0a,
+	MLX4_CMD_QP_ATTACH	 = 0xf0b,
 
 	/* debug commands */
 	MLX4_CMD_QUERY_DEBUG_MSG = 0x2a,
@@ -126,6 +149,7 @@ enum {
 
 	/* statistics commands */
 	MLX4_CMD_QUERY_IF_STAT	 = 0X54,
+	MLX4_CMD_SET_IF_STAT	 = 0X55,
 };
 
 enum {
@@ -135,7 +159,8 @@ enum {
 };
 
 enum {
-	MLX4_MAILBOX_SIZE	=  4096
+	MLX4_MAILBOX_SIZE	= 4096,
+	MLX4_ACCESS_MEM_ALIGN	= 256,
 };
 
 enum {
@@ -148,6 +173,11 @@ enum {
 	MLX4_SET_PORT_GID_TABLE = 0x5,
 };
 
+enum {
+	MLX4_CMD_WRAPPED,
+	MLX4_CMD_NATIVE
+};
+
 struct mlx4_dev;
 
 struct mlx4_cmd_mailbox {
@@ -157,23 +187,24 @@ struct mlx4_cmd_mailbox {
 
 int __mlx4_cmd(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 	       int out_is_imm, u32 in_modifier, u8 op_modifier,
-	       u16 op, unsigned long timeout);
+	       u16 op, unsigned long timeout, int native);
 
 /* Invoke a command with no output parameter */
 static inline int mlx4_cmd(struct mlx4_dev *dev, u64 in_param, u32 in_modifier,
-			   u8 op_modifier, u16 op, unsigned long timeout)
+			   u8 op_modifier, u16 op, unsigned long timeout,
+			   int native)
 {
 	return __mlx4_cmd(dev, in_param, NULL, 0, in_modifier,
-			  op_modifier, op, timeout);
+			  op_modifier, op, timeout, native);
 }
 
 /* Invoke a command with an output mailbox */
 static inline int mlx4_cmd_box(struct mlx4_dev *dev, u64 in_param, u64 out_param,
 			       u32 in_modifier, u8 op_modifier, u16 op,
-			       unsigned long timeout)
+			       unsigned long timeout, int native)
 {
 	return __mlx4_cmd(dev, in_param, &out_param, 0, in_modifier,
-			  op_modifier, op, timeout);
+			  op_modifier, op, timeout, native);
 }
 
 /*
@@ -183,13 +214,17 @@ static inline int mlx4_cmd_box(struct mlx4_dev *dev, u64 in_param, u64 out_param
  */
 static inline int mlx4_cmd_imm(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
 			       u32 in_modifier, u8 op_modifier, u16 op,
-			       unsigned long timeout)
+			       unsigned long timeout, int native)
 {
 	return __mlx4_cmd(dev, in_param, out_param, 1, in_modifier,
-			  op_modifier, op, timeout);
+			  op_modifier, op, timeout, native);
 }
 
 struct mlx4_cmd_mailbox *mlx4_alloc_cmd_mailbox(struct mlx4_dev *dev);
 void mlx4_free_cmd_mailbox(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox);
 
+u32 mlx4_comm_get_version(void);
+
+#define MLX4_COMM_GET_IF_REV(cmd_chan_ver) (u8)((cmd_chan_ver) >> 8)
+
 #endif /* MLX4_CMD_H */
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 84b0b18..5f784ff 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -47,6 +47,9 @@
 enum {
 	MLX4_FLAG_MSI_X		= 1 << 0,
 	MLX4_FLAG_OLD_PORT_CMDS	= 1 << 1,
+	MLX4_FLAG_MASTER	= 1 << 2,
+	MLX4_FLAG_SLAVE		= 1 << 3,
+	MLX4_FLAG_SRIOV		= 1 << 4,
 };
 
 enum {
@@ -58,6 +61,15 @@ enum {
 };
 
 enum {
+	MLX4_MAX_NUM_PF		= 16,
+	MLX4_MAX_NUM_VF		= 64,
+	MLX4_MFUNC_MAX		= 80,
+	MLX4_MFUNC_EQ_NUM	= 4,
+	MLX4_MFUNC_MAX_EQES     = 8,
+	MLX4_MFUNC_EQE_MASK     = (MLX4_MFUNC_MAX_EQES - 1)
+};
+
+enum {
 	MLX4_DEV_CAP_FLAG_RC		= 1LL <<  0,
 	MLX4_DEV_CAP_FLAG_UC		= 1LL <<  1,
 	MLX4_DEV_CAP_FLAG_UD		= 1LL <<  2,
@@ -77,7 +89,8 @@ enum {
 	MLX4_DEV_CAP_FLAG_IBOE		= 1LL << 30,
 	MLX4_DEV_CAP_FLAG_UC_LOOPBACK	= 1LL << 32,
 	MLX4_DEV_CAP_FLAG_FCS_KEEP	= 1LL << 34,
-	MLX4_DEV_CAP_FLAG_WOL		= 1LL << 38,
+	MLX4_DEV_CAP_FLAG_WOL_PORT1	= 1LL << 37,
+	MLX4_DEV_CAP_FLAG_WOL_PORT2	= 1LL << 38,
 	MLX4_DEV_CAP_FLAG_UDP_RSS	= 1LL << 40,
 	MLX4_DEV_CAP_FLAG_VEP_UC_STEER	= 1LL << 41,
 	MLX4_DEV_CAP_FLAG_VEP_MC_STEER	= 1LL << 42,
@@ -116,7 +129,11 @@ enum mlx4_event {
 	MLX4_EVENT_TYPE_PORT_CHANGE	   = 0x09,
 	MLX4_EVENT_TYPE_EQ_OVERFLOW	   = 0x0f,
 	MLX4_EVENT_TYPE_ECC_DETECT	   = 0x0e,
-	MLX4_EVENT_TYPE_CMD		   = 0x0a
+	MLX4_EVENT_TYPE_CMD		   = 0x0a,
+	MLX4_EVENT_TYPE_VEP_UPDATE	   = 0x19,
+	MLX4_EVENT_TYPE_COMM_CHANNEL	   = 0x18,
+	MLX4_EVENT_TYPE_FLR_EVENT	   = 0x1c,
+	MLX4_EVENT_TYPE_NONE		   = 0xff,
 };
 
 enum {
@@ -183,6 +200,7 @@ enum mlx4_qp_region {
 };
 
 enum mlx4_port_type {
+	MLX4_PORT_TYPE_NONE	= 0,
 	MLX4_PORT_TYPE_IB	= 1,
 	MLX4_PORT_TYPE_ETH	= 2,
 	MLX4_PORT_TYPE_AUTO	= 3
@@ -215,6 +233,7 @@ static inline u64 mlx4_fw_ver(u64 major, u64 minor, u64 subminor)
 
 struct mlx4_caps {
 	u64			fw_ver;
+	u32			function;
 	int			num_ports;
 	int			vl_cap[MLX4_MAX_PORTS + 1];
 	int			ib_mtu_cap[MLX4_MAX_PORTS + 1];
@@ -229,6 +248,7 @@ struct mlx4_caps {
 	u64			trans_code[MLX4_MAX_PORTS + 1];
 	int			local_ca_ack_delay;
 	int			num_uars;
+	u32			uar_page_size;
 	int			bf_reg_size;
 	int			bf_regs_per_page;
 	int			max_sq_sg;
@@ -252,8 +272,7 @@ struct mlx4_caps {
 	int			num_comp_vectors;
 	int			comp_pool;
 	int			num_mpts;
-	int			num_mtt_segs;
-	int			mtts_per_seg;
+	int			num_mtts;
 	int			fmr_reserved_mtts;
 	int			reserved_mtts;
 	int			reserved_mrws;
@@ -283,7 +302,7 @@ struct mlx4_caps {
 	int                     log_num_prios;
 	enum mlx4_port_type	port_type[MLX4_MAX_PORTS + 1];
 	u8			supported_type[MLX4_MAX_PORTS + 1];
-	u32			port_mask;
+	u32			port_mask[MLX4_MAX_PORTS + 1];
 	enum mlx4_port_type	possible_type[MLX4_MAX_PORTS + 1];
 	u32			max_counters;
 	u8			ext_port_cap[MLX4_MAX_PORTS + 1];
@@ -303,7 +322,7 @@ struct mlx4_buf {
 };
 
 struct mlx4_mtt {
-	u32			first_seg;
+	u32			offset;
 	int			order;
 	int			page_shift;
 };
@@ -465,10 +484,12 @@ struct mlx4_counter {
 struct mlx4_dev {
 	struct pci_dev	       *pdev;
 	unsigned long		flags;
+	unsigned long		num_slaves;
 	struct mlx4_caps	caps;
 	struct radix_tree_root	qp_table_tree;
 	u8			rev_id;
 	char			board_id[MLX4_BOARD_ID_LEN];
+	int			num_vfs;
 };
 
 struct mlx4_init_port_param {
@@ -487,14 +508,32 @@ struct mlx4_init_port_param {
 
 #define mlx4_foreach_port(port, dev, type)				\
 	for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++)	\
-		if (((type) == MLX4_PORT_TYPE_IB ? (dev)->caps.port_mask : \
-		     ~(dev)->caps.port_mask) & 1 << ((port) - 1))
+		if ((type) == (dev)->caps.port_mask[(port)])
 
-#define mlx4_foreach_ib_transport_port(port, dev)			\
-	for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++)	\
-		if (((dev)->caps.port_mask & 1 << ((port) - 1)) ||	\
-		    ((dev)->caps.flags & MLX4_DEV_CAP_FLAG_IBOE))
+#define mlx4_foreach_ib_transport_port(port, dev)                         \
+	for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++)	  \
+		if (((dev)->caps.port_mask[port] == MLX4_PORT_TYPE_IB) || \
+			((dev)->caps.flags & MLX4_DEV_CAP_FLAG_IBOE))
 
+static inline int mlx4_is_master(struct mlx4_dev *dev)
+{
+	return dev->flags & MLX4_FLAG_MASTER;
+}
+
+static inline int mlx4_is_qp_reserved(struct mlx4_dev *dev, u32 qpn)
+{
+	return (qpn < dev->caps.sqp_start + 8);
+}
+
+static inline int mlx4_is_mfunc(struct mlx4_dev *dev)
+{
+	return dev->flags & (MLX4_FLAG_SLAVE | MLX4_FLAG_MASTER);
+}
+
+static inline int mlx4_is_slave(struct mlx4_dev *dev)
+{
+	return dev->flags & MLX4_FLAG_SLAVE;
+}
 
 int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
 		   struct mlx4_buf *buf);
@@ -560,6 +599,10 @@ int mlx4_srq_query(struct mlx4_dev *dev, struct mlx4_srq *srq, int *limit_waterm
 int mlx4_INIT_PORT(struct mlx4_dev *dev, int port);
 int mlx4_CLOSE_PORT(struct mlx4_dev *dev, int port);
 
+int mlx4_unicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+			int block_mcast_loopback, enum mlx4_protocol prot);
+int mlx4_unicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+			enum mlx4_protocol prot);
 int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 			  int block_mcast_loopback, enum mlx4_protocol protocol);
 int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
@@ -570,9 +613,11 @@ int mlx4_unicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port);
 int mlx4_unicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port);
 int mlx4_SET_MCAST_FLTR(struct mlx4_dev *dev, u8 port, u64 mac, u64 clear, u8 mode);
 
-int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn, u8 wrap);
-void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, int qpn);
-int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac, u8 wrap);
+int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac);
+void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac);
+int mlx4_replace_mac(struct mlx4_dev *dev, u8 port, int qpn, u64 new_mac);
+int mlx4_get_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int *qpn);
+void mlx4_put_eth_qp(struct mlx4_dev *dev, u8 port, u64 mac, int qpn);
 
 int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
 int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 48cc4cb..bee8fa2 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -97,6 +97,33 @@ enum {
 	MLX4_QP_BIT_RIC				= 1 <<	4,
 };
 
+enum {
+	MLX4_RSS_HASH_XOR			= 0,
+	MLX4_RSS_HASH_TOP			= 1,
+
+	MLX4_RSS_UDP_IPV6			= 1 << 0,
+	MLX4_RSS_UDP_IPV4			= 1 << 1,
+	MLX4_RSS_TCP_IPV6			= 1 << 2,
+	MLX4_RSS_IPV6				= 1 << 3,
+	MLX4_RSS_TCP_IPV4			= 1 << 4,
+	MLX4_RSS_IPV4				= 1 << 5,
+
+	/* offset of mlx4_rss_context within mlx4_qp_context.pri_path */
+	MLX4_RSS_OFFSET_IN_QPC_PRI_PATH		= 0x24,
+	/* offset of being RSS indirection QP within mlx4_qp_context.flags */
+	MLX4_RSS_QPC_FLAG_OFFSET		= 13,
+};
+
+struct mlx4_rss_context {
+	__be32			base_qpn;
+	__be32			default_qpn;
+	u16			reserved;
+	u8			hash_fn;
+	u8			flags;
+	__be32			rss_key[10];
+	__be32			base_qpn_udp;
+};
+
 struct mlx4_qp_path {
 	u8			fl;
 	u8			reserved1[2];
@@ -183,6 +210,7 @@ struct mlx4_wqe_ctrl_seg {
 	 * [4]   IP checksum
 	 * [3:2] C (generate completion queue entry)
 	 * [1]   SE (solicited event)
+	 * [0]   FL (force loopback)
 	 */
 	__be32			srcrb_flags;
 	/*
diff --git a/include/linux/neighbour.h b/include/linux/neighbour.h
index a7003b7..b188f68 100644
--- a/include/linux/neighbour.h
+++ b/include/linux/neighbour.h
@@ -116,6 +116,7 @@ enum {
 	NDTPA_PROXY_DELAY,		/* u64, msecs */
 	NDTPA_PROXY_QLEN,		/* u32 */
 	NDTPA_LOCKTIME,			/* u64, msecs */
+	NDTPA_QUEUE_LENBYTES,		/* u32 */
 	__NDTPA_MAX
 };
 #define NDTPA_MAX (__NDTPA_MAX - 1)
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
new file mode 100644
index 0000000..77f5202
--- /dev/null
+++ b/include/linux/netdev_features.h
@@ -0,0 +1,146 @@
+/*
+ * Network device features.
+ *
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _LINUX_NETDEV_FEATURES_H
+#define _LINUX_NETDEV_FEATURES_H
+
+#include <linux/types.h>
+
+typedef u64 netdev_features_t;
+
+enum {
+	NETIF_F_SG_BIT,			/* Scatter/gather IO. */
+	NETIF_F_IP_CSUM_BIT,		/* Can checksum TCP/UDP over IPv4. */
+	__UNUSED_NETIF_F_1,
+	NETIF_F_HW_CSUM_BIT,		/* Can checksum all the packets. */
+	NETIF_F_IPV6_CSUM_BIT,		/* Can checksum TCP/UDP over IPV6 */
+	NETIF_F_HIGHDMA_BIT,		/* Can DMA to high memory. */
+	NETIF_F_FRAGLIST_BIT,		/* Scatter/gather IO. */
+	NETIF_F_HW_VLAN_TX_BIT,		/* Transmit VLAN hw acceleration */
+	NETIF_F_HW_VLAN_RX_BIT,		/* Receive VLAN hw acceleration */
+	NETIF_F_HW_VLAN_FILTER_BIT,	/* Receive filtering on VLAN */
+	NETIF_F_VLAN_CHALLENGED_BIT,	/* Device cannot handle VLAN packets */
+	NETIF_F_GSO_BIT,		/* Enable software GSO. */
+	NETIF_F_LLTX_BIT,		/* LockLess TX - deprecated. Please */
+					/* do not use LLTX in new drivers */
+	NETIF_F_NETNS_LOCAL_BIT,	/* Does not change network namespaces */
+	NETIF_F_GRO_BIT,		/* Generic receive offload */
+	NETIF_F_LRO_BIT,		/* large receive offload */
+
+	/**/NETIF_F_GSO_SHIFT,		/* keep the order of SKB_GSO_* bits */
+	NETIF_F_TSO_BIT			/* ... TCPv4 segmentation */
+		= NETIF_F_GSO_SHIFT,
+	NETIF_F_UFO_BIT,		/* ... UDPv4 fragmentation */
+	NETIF_F_GSO_ROBUST_BIT,		/* ... ->SKB_GSO_DODGY */
+	NETIF_F_TSO_ECN_BIT,		/* ... TCP ECN support */
+	NETIF_F_TSO6_BIT,		/* ... TCPv6 segmentation */
+	NETIF_F_FSO_BIT,		/* ... FCoE segmentation */
+	NETIF_F_GSO_RESERVED1,		/* ... free (fill GSO_MASK to 8 bits) */
+	/**/NETIF_F_GSO_LAST,		/* [can't be last bit, see GSO_MASK] */
+	NETIF_F_GSO_RESERVED2		/* ... free (fill GSO_MASK to 8 bits) */
+		= NETIF_F_GSO_LAST,
+
+	NETIF_F_FCOE_CRC_BIT,		/* FCoE CRC32 */
+	NETIF_F_SCTP_CSUM_BIT,		/* SCTP checksum offload */
+	NETIF_F_FCOE_MTU_BIT,		/* Supports max FCoE MTU, 2158 bytes*/
+	NETIF_F_NTUPLE_BIT,		/* N-tuple filters supported */
+	NETIF_F_RXHASH_BIT,		/* Receive hashing offload */
+	NETIF_F_RXCSUM_BIT,		/* Receive checksumming offload */
+	NETIF_F_NOCACHE_COPY_BIT,	/* Use no-cache copyfromuser */
+	NETIF_F_LOOPBACK_BIT,		/* Enable loopback */
+
+	/*
+	 * Add your fresh new feature above and remember to update
+	 * netdev_features_strings[] in net/core/ethtool.c and maybe
+	 * some feature mask #defines below. Please also describe it
+	 * in Documentation/networking/netdev-features.txt.
+	 */
+
+	/**/NETDEV_FEATURE_COUNT
+};
+
+/* copy'n'paste compression ;) */
+#define __NETIF_F_BIT(bit)	((netdev_features_t)1 << (bit))
+#define __NETIF_F(name)		__NETIF_F_BIT(NETIF_F_##name##_BIT)
+
+#define NETIF_F_FCOE_CRC	__NETIF_F(FCOE_CRC)
+#define NETIF_F_FCOE_MTU	__NETIF_F(FCOE_MTU)
+#define NETIF_F_FRAGLIST	__NETIF_F(FRAGLIST)
+#define NETIF_F_FSO		__NETIF_F(FSO)
+#define NETIF_F_GRO		__NETIF_F(GRO)
+#define NETIF_F_GSO		__NETIF_F(GSO)
+#define NETIF_F_GSO_ROBUST	__NETIF_F(GSO_ROBUST)
+#define NETIF_F_HIGHDMA		__NETIF_F(HIGHDMA)
+#define NETIF_F_HW_CSUM		__NETIF_F(HW_CSUM)
+#define NETIF_F_HW_VLAN_FILTER	__NETIF_F(HW_VLAN_FILTER)
+#define NETIF_F_HW_VLAN_RX	__NETIF_F(HW_VLAN_RX)
+#define NETIF_F_HW_VLAN_TX	__NETIF_F(HW_VLAN_TX)
+#define NETIF_F_IP_CSUM		__NETIF_F(IP_CSUM)
+#define NETIF_F_IPV6_CSUM	__NETIF_F(IPV6_CSUM)
+#define NETIF_F_LLTX		__NETIF_F(LLTX)
+#define NETIF_F_LOOPBACK	__NETIF_F(LOOPBACK)
+#define NETIF_F_LRO		__NETIF_F(LRO)
+#define NETIF_F_NETNS_LOCAL	__NETIF_F(NETNS_LOCAL)
+#define NETIF_F_NOCACHE_COPY	__NETIF_F(NOCACHE_COPY)
+#define NETIF_F_NTUPLE		__NETIF_F(NTUPLE)
+#define NETIF_F_RXCSUM		__NETIF_F(RXCSUM)
+#define NETIF_F_RXHASH		__NETIF_F(RXHASH)
+#define NETIF_F_SCTP_CSUM	__NETIF_F(SCTP_CSUM)
+#define NETIF_F_SG		__NETIF_F(SG)
+#define NETIF_F_TSO6		__NETIF_F(TSO6)
+#define NETIF_F_TSO_ECN		__NETIF_F(TSO_ECN)
+#define NETIF_F_TSO		__NETIF_F(TSO)
+#define NETIF_F_UFO		__NETIF_F(UFO)
+#define NETIF_F_VLAN_CHALLENGED	__NETIF_F(VLAN_CHALLENGED)
+
+/* Features valid for ethtool to change */
+/* = all defined minus driver/device-class-related */
+#define NETIF_F_NEVER_CHANGE	(NETIF_F_VLAN_CHALLENGED | \
+				 NETIF_F_LLTX | NETIF_F_NETNS_LOCAL)
+
+/* remember that ((t)1 << t_BITS) is undefined in C99 */
+#define NETIF_F_ETHTOOL_BITS	((__NETIF_F_BIT(NETDEV_FEATURE_COUNT - 1) | \
+		(__NETIF_F_BIT(NETDEV_FEATURE_COUNT - 1) - 1)) & \
+		~NETIF_F_NEVER_CHANGE)
+
+/* Segmentation offload feature mask */
+#define NETIF_F_GSO_MASK	(__NETIF_F_BIT(NETIF_F_GSO_LAST + 1) - \
+		__NETIF_F_BIT(NETIF_F_GSO_SHIFT))
+
+/* List of features with software fallbacks. */
+#define NETIF_F_GSO_SOFTWARE	(NETIF_F_TSO | NETIF_F_TSO_ECN | \
+				 NETIF_F_TSO6 | NETIF_F_UFO)
+
+#define NETIF_F_GEN_CSUM	NETIF_F_HW_CSUM
+#define NETIF_F_V4_CSUM		(NETIF_F_GEN_CSUM | NETIF_F_IP_CSUM)
+#define NETIF_F_V6_CSUM		(NETIF_F_GEN_CSUM | NETIF_F_IPV6_CSUM)
+#define NETIF_F_ALL_CSUM	(NETIF_F_V4_CSUM | NETIF_F_V6_CSUM)
+
+#define NETIF_F_ALL_TSO 	(NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN)
+
+#define NETIF_F_ALL_FCOE	(NETIF_F_FCOE_CRC | NETIF_F_FCOE_MTU | \
+				 NETIF_F_FSO)
+
+/*
+ * If one device supports one of these features, then enable them
+ * for all in netdev_increment_features.
+ */
+#define NETIF_F_ONE_FOR_ALL	(NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ROBUST | \
+				 NETIF_F_SG | NETIF_F_HIGHDMA |		\
+				 NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED)
+/*
+ * If one device doesn't support one of these features, then disable it
+ * for all in netdev_increment_features.
+ */
+#define NETIF_F_ALL_FOR_ALL	(NETIF_F_NOCACHE_COPY | NETIF_F_FSO)
+
+/* changeable features with no special hardware requirements */
+#define NETIF_F_SOFT_FEATURES	(NETIF_F_GSO | NETIF_F_GRO)
+
+#endif	/* _LINUX_NETDEV_FEATURES_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index cbeb586..6b9d4ed 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -43,6 +43,7 @@
 #include <linux/rculist.h>
 #include <linux/dmaengine.h>
 #include <linux/workqueue.h>
+#include <linux/dynamic_queue_limits.h>
 
 #include <linux/ethtool.h>
 #include <net/net_namespace.h>
@@ -50,8 +51,10 @@
 #ifdef CONFIG_DCB
 #include <net/dcbnl.h>
 #endif
+#include <net/netprio_cgroup.h>
+
+#include <linux/netdev_features.h>
 
-struct vlan_group;
 struct netpoll_info;
 struct phy_device;
 /* 802.11 specific */
@@ -141,22 +144,20 @@ static inline bool dev_xmit_complete(int rc)
  *	used.
  */
 
-#if defined(CONFIG_WLAN) || defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
+#if defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25)
 # if defined(CONFIG_MAC80211_MESH)
 #  define LL_MAX_HEADER 128
 # else
 #  define LL_MAX_HEADER 96
 # endif
-#elif defined(CONFIG_TR) || defined(CONFIG_TR_MODULE)
+#elif IS_ENABLED(CONFIG_TR)
 # define LL_MAX_HEADER 48
 #else
 # define LL_MAX_HEADER 32
 #endif
 
-#if !defined(CONFIG_NET_IPIP) && !defined(CONFIG_NET_IPIP_MODULE) && \
-    !defined(CONFIG_NET_IPGRE) &&  !defined(CONFIG_NET_IPGRE_MODULE) && \
-    !defined(CONFIG_IPV6_SIT) && !defined(CONFIG_IPV6_SIT_MODULE) && \
-    !defined(CONFIG_IPV6_TUNNEL) && !defined(CONFIG_IPV6_TUNNEL_MODULE)
+#if !IS_ENABLED(CONFIG_NET_IPIP) && !IS_ENABLED(CONFIG_NET_IPGRE) && \
+    !IS_ENABLED(CONFIG_IPV6_SIT) && !IS_ENABLED(CONFIG_IPV6_TUNNEL)
 #define MAX_HEADER LL_MAX_HEADER
 #else
 #define MAX_HEADER (LL_MAX_HEADER + 48)
@@ -212,6 +213,11 @@ enum {
 #include <linux/cache.h>
 #include <linux/skbuff.h>
 
+#ifdef CONFIG_RPS
+#include <linux/jump_label.h>
+extern struct jump_label_key rps_needed;
+#endif
+
 struct neighbour;
 struct neigh_parms;
 struct sk_buff;
@@ -272,16 +278,11 @@ struct hh_cache {
  *
  * We could use other alignment values, but we must maintain the
  * relationship HH alignment <= LL alignment.
- *
- * LL_ALLOCATED_SPACE also takes into account the tailroom the device
- * may need.
  */
 #define LL_RESERVED_SPACE(dev) \
 	((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
 #define LL_RESERVED_SPACE_EXTRA(dev,extra) \
 	((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
-#define LL_ALLOCATED_SPACE(dev) \
-	((((dev)->hard_header_len+(dev)->needed_headroom+(dev)->needed_tailroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
 
 struct header_ops {
 	int	(*create) (struct sk_buff *skb, struct net_device *dev,
@@ -516,11 +517,23 @@ static inline void napi_synchronize(const struct napi_struct *n)
 #endif
 
 enum netdev_queue_state_t {
-	__QUEUE_STATE_XOFF,
+	__QUEUE_STATE_DRV_XOFF,
+	__QUEUE_STATE_STACK_XOFF,
 	__QUEUE_STATE_FROZEN,
-#define QUEUE_STATE_XOFF_OR_FROZEN ((1 << __QUEUE_STATE_XOFF)		| \
-				    (1 << __QUEUE_STATE_FROZEN))
+#define QUEUE_STATE_ANY_XOFF ((1 << __QUEUE_STATE_DRV_XOFF)		| \
+			      (1 << __QUEUE_STATE_STACK_XOFF))
+#define QUEUE_STATE_ANY_XOFF_OR_FROZEN (QUEUE_STATE_ANY_XOFF		| \
+					(1 << __QUEUE_STATE_FROZEN))
 };
+/*
+ * __QUEUE_STATE_DRV_XOFF is used by drivers to stop the transmit queue.  The
+ * netif_tx_* functions below are used to manipulate this flag.  The
+ * __QUEUE_STATE_STACK_XOFF flag is used by the stack to stop the transmit
+ * queue independently.  The netif_xmit_*stopped functions below are called
+ * to check if the queue has been stopped by the driver or stack (either
+ * of the XOFF bits are set in the state).  Drivers should not need to call
+ * netif_xmit*stopped functions, they should only be using netif_tx_*.
+ */
 
 struct netdev_queue {
 /*
@@ -528,9 +541,8 @@ struct netdev_queue {
  */
 	struct net_device	*dev;
 	struct Qdisc		*qdisc;
-	unsigned long		state;
 	struct Qdisc		*qdisc_sleeping;
-#if defined(CONFIG_RPS) || defined(CONFIG_XPS)
+#ifdef CONFIG_SYSFS
 	struct kobject		kobj;
 #endif
 #if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
@@ -545,6 +557,18 @@ struct netdev_queue {
 	 * please use this field instead of dev->trans_start
 	 */
 	unsigned long		trans_start;
+
+	/*
+	 * Number of TX timeouts for this queue
+	 * (/sys/class/net/DEV/Q/trans_timeout)
+	 */
+	unsigned long		trans_timeout;
+
+	unsigned long		state;
+
+#ifdef CONFIG_BQL
+	struct dql		dql;
+#endif
 } ____cacheline_aligned_in_smp;
 
 static inline int netdev_queue_numa_node_read(const struct netdev_queue *q)
@@ -767,11 +791,11 @@ struct netdev_tc_txq {
  *	3. Update dev->stats asynchronously and atomically, and define
  *	   neither operation.
  *
- * void (*ndo_vlan_rx_add_vid)(struct net_device *dev, unsigned short vid);
+ * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, unsigned short vid);
  *	If device support VLAN filtering (dev->features & NETIF_F_HW_VLAN_FILTER)
  *	this function is called when a VLAN id is registered.
  *
- * void (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid);
+ * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, unsigned short vid);
  *	If device support VLAN filtering (dev->features & NETIF_F_HW_VLAN_FILTER)
  *	this function is called when a VLAN id is unregistered.
  *
@@ -845,12 +869,13 @@ struct netdev_tc_txq {
  *	Called to release previously enslaved netdev.
  *
  *      Feature/offload setting functions.
- * u32 (*ndo_fix_features)(struct net_device *dev, u32 features);
+ * netdev_features_t (*ndo_fix_features)(struct net_device *dev,
+ *		netdev_features_t features);
  *	Adjusts the requested feature flags according to device-specific
  *	constraints, and returns the resulting flags. Must not modify
  *	the device state.
  *
- * int (*ndo_set_features)(struct net_device *dev, u32 features);
+ * int (*ndo_set_features)(struct net_device *dev, netdev_features_t features);
  *	Called to update device configuration to new features. Passed
  *	feature set might be less than what was returned by ndo_fix_features()).
  *	Must return >0 or -errno if it changed dev->features itself.
@@ -885,9 +910,9 @@ struct net_device_ops {
 						     struct rtnl_link_stats64 *storage);
 	struct net_device_stats* (*ndo_get_stats)(struct net_device *dev);
 
-	void			(*ndo_vlan_rx_add_vid)(struct net_device *dev,
+	int			(*ndo_vlan_rx_add_vid)(struct net_device *dev,
 						       unsigned short vid);
-	void			(*ndo_vlan_rx_kill_vid)(struct net_device *dev,
+	int			(*ndo_vlan_rx_kill_vid)(struct net_device *dev,
 						        unsigned short vid);
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	void                    (*ndo_poll_controller)(struct net_device *dev);
@@ -912,7 +937,7 @@ struct net_device_ops {
 	int			(*ndo_get_vf_port)(struct net_device *dev,
 						   int vf, struct sk_buff *skb);
 	int			(*ndo_setup_tc)(struct net_device *dev, u8 tc);
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#if IS_ENABLED(CONFIG_FCOE)
 	int			(*ndo_fcoe_enable)(struct net_device *dev);
 	int			(*ndo_fcoe_disable)(struct net_device *dev);
 	int			(*ndo_fcoe_ddp_setup)(struct net_device *dev,
@@ -927,7 +952,7 @@ struct net_device_ops {
 						       unsigned int sgc);
 #endif
 
-#if defined(CONFIG_LIBFCOE) || defined(CONFIG_LIBFCOE_MODULE)
+#if IS_ENABLED(CONFIG_LIBFCOE)
 #define NETDEV_FCOE_WWNN 0
 #define NETDEV_FCOE_WWPN 1
 	int			(*ndo_fcoe_get_wwn)(struct net_device *dev,
@@ -944,10 +969,11 @@ struct net_device_ops {
 						 struct net_device *slave_dev);
 	int			(*ndo_del_slave)(struct net_device *dev,
 						 struct net_device *slave_dev);
-	u32			(*ndo_fix_features)(struct net_device *dev,
-						    u32 features);
+	netdev_features_t	(*ndo_fix_features)(struct net_device *dev,
+						    netdev_features_t features);
 	int			(*ndo_set_features)(struct net_device *dev,
-						    u32 features);
+						    netdev_features_t features);
+	int			(*ndo_neigh_construct)(struct neighbour *n);
 };
 
 /*
@@ -997,91 +1023,13 @@ struct net_device {
 	struct list_head	unreg_list;
 
 	/* currently active device features */
-	u32			features;
+	netdev_features_t	features;
 	/* user-changeable features */
-	u32			hw_features;
+	netdev_features_t	hw_features;
 	/* user-requested features */
-	u32			wanted_features;
+	netdev_features_t	wanted_features;
 	/* mask of features inheritable by VLAN devices */
-	u32			vlan_features;
-
-	/* Net device feature bits; if you change something,
-	 * also update netdev_features_strings[] in ethtool.c */
-
-#define NETIF_F_SG		1	/* Scatter/gather IO. */
-#define NETIF_F_IP_CSUM		2	/* Can checksum TCP/UDP over IPv4. */
-#define NETIF_F_NO_CSUM		4	/* Does not require checksum. F.e. loopack. */
-#define NETIF_F_HW_CSUM		8	/* Can checksum all the packets. */
-#define NETIF_F_IPV6_CSUM	16	/* Can checksum TCP/UDP over IPV6 */
-#define NETIF_F_HIGHDMA		32	/* Can DMA to high memory. */
-#define NETIF_F_FRAGLIST	64	/* Scatter/gather IO. */
-#define NETIF_F_HW_VLAN_TX	128	/* Transmit VLAN hw acceleration */
-#define NETIF_F_HW_VLAN_RX	256	/* Receive VLAN hw acceleration */
-#define NETIF_F_HW_VLAN_FILTER	512	/* Receive filtering on VLAN */
-#define NETIF_F_VLAN_CHALLENGED	1024	/* Device cannot handle VLAN packets */
-#define NETIF_F_GSO		2048	/* Enable software GSO. */
-#define NETIF_F_LLTX		4096	/* LockLess TX - deprecated. Please */
-					/* do not use LLTX in new drivers */
-#define NETIF_F_NETNS_LOCAL	8192	/* Does not change network namespaces */
-#define NETIF_F_GRO		16384	/* Generic receive offload */
-#define NETIF_F_LRO		32768	/* large receive offload */
-
-/* the GSO_MASK reserves bits 16 through 23 */
-#define NETIF_F_FCOE_CRC	(1 << 24) /* FCoE CRC32 */
-#define NETIF_F_SCTP_CSUM	(1 << 25) /* SCTP checksum offload */
-#define NETIF_F_FCOE_MTU	(1 << 26) /* Supports max FCoE MTU, 2158 bytes*/
-#define NETIF_F_NTUPLE		(1 << 27) /* N-tuple filters supported */
-#define NETIF_F_RXHASH		(1 << 28) /* Receive hashing offload */
-#define NETIF_F_RXCSUM		(1 << 29) /* Receive checksumming offload */
-#define NETIF_F_NOCACHE_COPY	(1 << 30) /* Use no-cache copyfromuser */
-#define NETIF_F_LOOPBACK	(1 << 31) /* Enable loopback */
-
-	/* Segmentation offload features */
-#define NETIF_F_GSO_SHIFT	16
-#define NETIF_F_GSO_MASK	0x00ff0000
-#define NETIF_F_TSO		(SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT)
-#define NETIF_F_UFO		(SKB_GSO_UDP << NETIF_F_GSO_SHIFT)
-#define NETIF_F_GSO_ROBUST	(SKB_GSO_DODGY << NETIF_F_GSO_SHIFT)
-#define NETIF_F_TSO_ECN		(SKB_GSO_TCP_ECN << NETIF_F_GSO_SHIFT)
-#define NETIF_F_TSO6		(SKB_GSO_TCPV6 << NETIF_F_GSO_SHIFT)
-#define NETIF_F_FSO		(SKB_GSO_FCOE << NETIF_F_GSO_SHIFT)
-
-	/* Features valid for ethtool to change */
-	/* = all defined minus driver/device-class-related */
-#define NETIF_F_NEVER_CHANGE	(NETIF_F_VLAN_CHALLENGED | \
-				  NETIF_F_LLTX | NETIF_F_NETNS_LOCAL)
-#define NETIF_F_ETHTOOL_BITS	(0xff3fffff & ~NETIF_F_NEVER_CHANGE)
-
-	/* List of features with software fallbacks. */
-#define NETIF_F_GSO_SOFTWARE	(NETIF_F_TSO | NETIF_F_TSO_ECN | \
-				 NETIF_F_TSO6 | NETIF_F_UFO)
-
-
-#define NETIF_F_GEN_CSUM	(NETIF_F_NO_CSUM | NETIF_F_HW_CSUM)
-#define NETIF_F_V4_CSUM		(NETIF_F_GEN_CSUM | NETIF_F_IP_CSUM)
-#define NETIF_F_V6_CSUM		(NETIF_F_GEN_CSUM | NETIF_F_IPV6_CSUM)
-#define NETIF_F_ALL_CSUM	(NETIF_F_V4_CSUM | NETIF_F_V6_CSUM)
-
-#define NETIF_F_ALL_TSO 	(NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_TSO_ECN)
-
-#define NETIF_F_ALL_FCOE	(NETIF_F_FCOE_CRC | NETIF_F_FCOE_MTU | \
-				 NETIF_F_FSO)
-
-	/*
-	 * If one device supports one of these features, then enable them
-	 * for all in netdev_increment_features.
-	 */
-#define NETIF_F_ONE_FOR_ALL	(NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ROBUST | \
-				 NETIF_F_SG | NETIF_F_HIGHDMA |		\
-				 NETIF_F_FRAGLIST | NETIF_F_VLAN_CHALLENGED)
-	/*
-	 * If one device doesn't support one of these features, then disable it
-	 * for all in netdev_increment_features.
-	 */
-#define NETIF_F_ALL_FOR_ALL	(NETIF_F_NOCACHE_COPY | NETIF_F_FSO)
-
-	/* changeable features with no special hardware requirements */
-#define NETIF_F_SOFT_FEATURES	(NETIF_F_GSO | NETIF_F_GRO)
+	netdev_features_t	vlan_features;
 
 	/* Interface index. Unique device identifier	*/
 	int			ifindex;
@@ -1132,6 +1080,7 @@ struct net_device {
 	unsigned char		perm_addr[MAX_ADDR_LEN]; /* permanent hw address */
 	unsigned char		addr_assign_type; /* hw address assignment type */
 	unsigned char		addr_len;	/* hardware address length	*/
+	unsigned char		neigh_priv_len;
 	unsigned short          dev_id;		/* for shared network cards */
 
 	spinlock_t		addr_list_lock;
@@ -1144,11 +1093,11 @@ struct net_device {
 
 	/* Protocol specific pointers */
 
-#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
-	struct vlan_group __rcu	*vlgrp;		/* VLAN group */
+#if IS_ENABLED(CONFIG_VLAN_8021Q)
+	struct vlan_info __rcu	*vlan_info;	/* VLAN info */
 #endif
-#ifdef CONFIG_NET_DSA
-	void			*dsa_ptr;	/* dsa specific data */
+#if IS_ENABLED(CONFIG_NET_DSA)
+	struct dsa_switch_tree	*dsa_ptr;	/* dsa specific data */
 #endif
 	void 			*atalk_ptr;	/* AppleTalk link 	*/
 	struct in_device __rcu	*ip_ptr;	/* IPv4 specific data	*/
@@ -1184,9 +1133,11 @@ struct net_device {
 
 	unsigned char		broadcast[MAX_ADDR_LEN];	/* hw bcast add	*/
 
-#if defined(CONFIG_RPS) || defined(CONFIG_XPS)
+#ifdef CONFIG_SYSFS
 	struct kset		*queues_kset;
+#endif
 
+#ifdef CONFIG_RPS
 	struct netdev_rx_queue	*_rx;
 
 	/* Number of RX queues allocated at register_netdev() time */
@@ -1308,10 +1259,13 @@ struct net_device {
 	struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE];
 	u8 prio_tc_map[TC_BITMASK + 1];
 
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#if IS_ENABLED(CONFIG_FCOE)
 	/* max exchange id for FCoE LRO by ddp */
 	unsigned int		fcoe_ddp_xid;
 #endif
+#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+	struct netprio_map __rcu *priomap;
+#endif
 	/* phy device may attach itself for hardware timestamping */
 	struct phy_device *phydev;
 
@@ -1515,7 +1469,7 @@ struct packet_type {
 					 struct packet_type *,
 					 struct net_device *);
 	struct sk_buff		*(*gso_segment)(struct sk_buff *skb,
-						u32 features);
+						netdev_features_t features);
 	int			(*gso_send_check)(struct sk_buff *skb);
 	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
 					       struct sk_buff *skb);
@@ -1783,7 +1737,7 @@ extern void __netif_schedule(struct Qdisc *q);
 
 static inline void netif_schedule_queue(struct netdev_queue *txq)
 {
-	if (!test_bit(__QUEUE_STATE_XOFF, &txq->state))
+	if (!(txq->state & QUEUE_STATE_ANY_XOFF))
 		__netif_schedule(txq->qdisc);
 }
 
@@ -1797,7 +1751,7 @@ static inline void netif_tx_schedule_all(struct net_device *dev)
 
 static inline void netif_tx_start_queue(struct netdev_queue *dev_queue)
 {
-	clear_bit(__QUEUE_STATE_XOFF, &dev_queue->state);
+	clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
 }
 
 /**
@@ -1829,7 +1783,7 @@ static inline void netif_tx_wake_queue(struct netdev_queue *dev_queue)
 		return;
 	}
 #endif
-	if (test_and_clear_bit(__QUEUE_STATE_XOFF, &dev_queue->state))
+	if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state))
 		__netif_schedule(dev_queue->qdisc);
 }
 
@@ -1861,7 +1815,7 @@ static inline void netif_tx_stop_queue(struct netdev_queue *dev_queue)
 		pr_info("netif_stop_queue() cannot be called before register_netdev()\n");
 		return;
 	}
-	set_bit(__QUEUE_STATE_XOFF, &dev_queue->state);
+	set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
 }
 
 /**
@@ -1888,7 +1842,7 @@ static inline void netif_tx_stop_all_queues(struct net_device *dev)
 
 static inline int netif_tx_queue_stopped(const struct netdev_queue *dev_queue)
 {
-	return test_bit(__QUEUE_STATE_XOFF, &dev_queue->state);
+	return test_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
 }
 
 /**
@@ -1902,9 +1856,68 @@ static inline int netif_queue_stopped(const struct net_device *dev)
 	return netif_tx_queue_stopped(netdev_get_tx_queue(dev, 0));
 }
 
-static inline int netif_tx_queue_frozen_or_stopped(const struct netdev_queue *dev_queue)
+static inline int netif_xmit_stopped(const struct netdev_queue *dev_queue)
 {
-	return dev_queue->state & QUEUE_STATE_XOFF_OR_FROZEN;
+	return dev_queue->state & QUEUE_STATE_ANY_XOFF;
+}
+
+static inline int netif_xmit_frozen_or_stopped(const struct netdev_queue *dev_queue)
+{
+	return dev_queue->state & QUEUE_STATE_ANY_XOFF_OR_FROZEN;
+}
+
+static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
+					unsigned int bytes)
+{
+#ifdef CONFIG_BQL
+	dql_queued(&dev_queue->dql, bytes);
+	if (unlikely(dql_avail(&dev_queue->dql) < 0)) {
+		set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
+		if (unlikely(dql_avail(&dev_queue->dql) >= 0))
+			clear_bit(__QUEUE_STATE_STACK_XOFF,
+			    &dev_queue->state);
+	}
+#endif
+}
+
+static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes)
+{
+	netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes);
+}
+
+static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue,
+					     unsigned pkts, unsigned bytes)
+{
+#ifdef CONFIG_BQL
+	if (likely(bytes)) {
+		dql_completed(&dev_queue->dql, bytes);
+		if (unlikely(test_bit(__QUEUE_STATE_STACK_XOFF,
+		    &dev_queue->state) &&
+		    dql_avail(&dev_queue->dql) >= 0)) {
+			if (test_and_clear_bit(__QUEUE_STATE_STACK_XOFF,
+			     &dev_queue->state))
+				netif_schedule_queue(dev_queue);
+		}
+	}
+#endif
+}
+
+static inline void netdev_completed_queue(struct net_device *dev,
+					  unsigned pkts, unsigned bytes)
+{
+	netdev_tx_completed_queue(netdev_get_tx_queue(dev, 0), pkts, bytes);
+}
+
+static inline void netdev_tx_reset_queue(struct netdev_queue *q)
+{
+#ifdef CONFIG_BQL
+	dql_reset(&q->dql);
+#endif
+}
+
+static inline void netdev_reset_queue(struct net_device *dev_queue)
+{
+	netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0));
 }
 
 /**
@@ -1991,7 +2004,7 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
 	if (netpoll_trap())
 		return;
 #endif
-	if (test_and_clear_bit(__QUEUE_STATE_XOFF, &txq->state))
+	if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &txq->state))
 		__netif_schedule(txq->qdisc);
 }
 
@@ -2520,7 +2533,8 @@ extern int		netdev_set_master(struct net_device *dev, struct net_device *master)
 extern int netdev_set_bond_master(struct net_device *dev,
 				  struct net_device *master);
 extern int skb_checksum_help(struct sk_buff *skb);
-extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features);
+extern struct sk_buff *skb_gso_segment(struct sk_buff *skb,
+	netdev_features_t features);
 #ifdef CONFIG_BUG
 extern void netdev_rx_csum_fault(struct net_device *dev);
 #else
@@ -2536,6 +2550,8 @@ extern void		net_disable_timestamp(void);
 extern void *dev_seq_start(struct seq_file *seq, loff_t *pos);
 extern void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos);
 extern void dev_seq_stop(struct seq_file *seq, void *v);
+extern int dev_seq_open_ops(struct inode *inode, struct file *file,
+			    const struct seq_operations *ops);
 #endif
 
 extern int netdev_class_create_file(struct class_attribute *class_attr);
@@ -2547,11 +2563,13 @@ extern const char *netdev_drivername(const struct net_device *dev);
 
 extern void linkwatch_run_queue(void);
 
-static inline u32 netdev_get_wanted_features(struct net_device *dev)
+static inline netdev_features_t netdev_get_wanted_features(
+	struct net_device *dev)
 {
 	return (dev->features & ~dev->hw_features) | dev->wanted_features;
 }
-u32 netdev_increment_features(u32 all, u32 one, u32 mask);
+netdev_features_t netdev_increment_features(netdev_features_t all,
+	netdev_features_t one, netdev_features_t mask);
 int __netdev_update_features(struct net_device *dev);
 void netdev_update_features(struct net_device *dev);
 void netdev_change_features(struct net_device *dev);
@@ -2559,21 +2577,31 @@ void netdev_change_features(struct net_device *dev);
 void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 					struct net_device *dev);
 
-u32 netif_skb_features(struct sk_buff *skb);
+netdev_features_t netif_skb_features(struct sk_buff *skb);
 
-static inline int net_gso_ok(u32 features, int gso_type)
+static inline int net_gso_ok(netdev_features_t features, int gso_type)
 {
-	int feature = gso_type << NETIF_F_GSO_SHIFT;
+	netdev_features_t feature = gso_type << NETIF_F_GSO_SHIFT;
+
+	/* check flags correspondence */
+	BUILD_BUG_ON(SKB_GSO_TCPV4   != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_UDP     != (NETIF_F_UFO >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_DODGY   != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_TCPV6   != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_FCOE    != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
+
 	return (features & feature) == feature;
 }
 
-static inline int skb_gso_ok(struct sk_buff *skb, u32 features)
+static inline int skb_gso_ok(struct sk_buff *skb, netdev_features_t features)
 {
 	return net_gso_ok(features, skb_shinfo(skb)->gso_type) &&
 	       (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST));
 }
 
-static inline int netif_needs_gso(struct sk_buff *skb, int features)
+static inline int netif_needs_gso(struct sk_buff *skb,
+	netdev_features_t features)
 {
 	return skb_is_gso(skb) && (!skb_gso_ok(skb, features) ||
 		unlikely(skb->ip_summed != CHECKSUM_PARTIAL));
@@ -2592,22 +2620,6 @@ static inline int netif_is_bond_slave(struct net_device *dev)
 
 extern struct pernet_operations __net_initdata loopback_net_ops;
 
-static inline u32 dev_ethtool_get_rx_csum(struct net_device *dev)
-{
-	if (dev->features & NETIF_F_RXCSUM)
-		return 1;
-	if (!dev->ethtool_ops || !dev->ethtool_ops->get_rx_csum)
-		return 0;
-	return dev->ethtool_ops->get_rx_csum(dev);
-}
-
-static inline u32 dev_ethtool_get_flags(struct net_device *dev)
-{
-	if (!dev->ethtool_ops || !dev->ethtool_ops->get_flags)
-		return 0;
-	return dev->ethtool_ops->get_flags(dev);
-}
-
 /* Logging, debugging and troubleshooting/diagnostic helpers. */
 
 /* netdev_printk helpers, similar to dev_printk */
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 857f502..b809265 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -162,6 +162,24 @@ extern struct ctl_path nf_net_ipv4_netfilter_sysctl_path[];
 
 extern struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
 
+#if defined(CONFIG_JUMP_LABEL)
+#include <linux/jump_label.h>
+extern struct jump_label_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
+static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook)
+{
+	if (__builtin_constant_p(pf) &&
+	    __builtin_constant_p(hook))
+		return static_branch(&nf_hooks_needed[pf][hook]);
+
+	return !list_empty(&nf_hooks[pf][hook]);
+}
+#else
+static inline bool nf_hooks_active(u_int8_t pf, unsigned int hook)
+{
+	return !list_empty(&nf_hooks[pf][hook]);
+}
+#endif
+
 int nf_hook_slow(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
 		 struct net_device *indev, struct net_device *outdev,
 		 int (*okfn)(struct sk_buff *), int thresh);
@@ -179,11 +197,9 @@ static inline int nf_hook_thresh(u_int8_t pf, unsigned int hook,
 				 struct net_device *outdev,
 				 int (*okfn)(struct sk_buff *), int thresh)
 {
-#ifndef CONFIG_NETFILTER_DEBUG
-	if (list_empty(&nf_hooks[pf][hook]))
-		return 1;
-#endif
-	return nf_hook_slow(pf, hook, skb, indev, outdev, okfn, thresh);
+	if (nf_hooks_active(pf, hook))
+		return nf_hook_slow(pf, hook, skb, indev, outdev, okfn, thresh);
+	return 1;
 }
 
 static inline int nf_hook(u_int8_t pf, unsigned int hook, struct sk_buff *skb,
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 8374d29..52e4895 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -8,7 +8,7 @@
 #define NETLINK_UNUSED		1	/* Unused number				*/
 #define NETLINK_USERSOCK	2	/* Reserved for user mode socket protocols 	*/
 #define NETLINK_FIREWALL	3	/* Firewalling hook				*/
-#define NETLINK_INET_DIAG	4	/* INET socket monitoring			*/
+#define NETLINK_SOCK_DIAG	4	/* socket monitoring				*/
 #define NETLINK_NFLOG		5	/* netfilter/iptables ULOG */
 #define NETLINK_XFRM		6	/* ipsec */
 #define NETLINK_SELINUX		7	/* SELinux event notifications */
@@ -27,6 +27,8 @@
 #define NETLINK_RDMA		20
 #define NETLINK_CRYPTO		21	/* Crypto layer */
 
+#define NETLINK_INET_DIAG	NETLINK_SOCK_DIAG
+
 #define MAX_LINKS 32		
 
 struct sockaddr_nl {
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index ab2c634..92ecf55 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -410,6 +410,9 @@ extern const struct inode_operations nfs_file_inode_operations;
 extern const struct inode_operations nfs3_file_inode_operations;
 #endif /* CONFIG_NFS_V3 */
 extern const struct file_operations nfs_file_operations;
+#ifdef CONFIG_NFS_V4
+extern const struct file_operations nfs4_file_operations;
+#endif /* CONFIG_NFS_V4 */
 extern const struct address_space_operations nfs_file_aops;
 extern const struct address_space_operations nfs_dir_aops;
 
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index c74595b..2a7c533 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1192,6 +1192,7 @@ struct nfs_rpc_ops {
 	const struct dentry_operations *dentry_ops;
 	const struct inode_operations *dir_inode_ops;
 	const struct inode_operations *file_inode_ops;
+	const struct file_operations *file_ops;
 
 	int	(*getroot) (struct nfs_server *, struct nfs_fh *,
 			    struct nfs_fsinfo *);
diff --git a/include/linux/openvswitch.h b/include/linux/openvswitch.h
new file mode 100644
index 0000000..eb1efa5
--- /dev/null
+++ b/include/linux/openvswitch.h
@@ -0,0 +1,452 @@
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef _LINUX_OPENVSWITCH_H
+#define _LINUX_OPENVSWITCH_H 1
+
+#include <linux/types.h>
+
+/**
+ * struct ovs_header - header for OVS Generic Netlink messages.
+ * @dp_ifindex: ifindex of local port for datapath (0 to make a request not
+ * specific to a datapath).
+ *
+ * Attributes following the header are specific to a particular OVS Generic
+ * Netlink family, but all of the OVS families use this header.
+ */
+
+struct ovs_header {
+	int dp_ifindex;
+};
+
+/* Datapaths. */
+
+#define OVS_DATAPATH_FAMILY  "ovs_datapath"
+#define OVS_DATAPATH_MCGROUP "ovs_datapath"
+#define OVS_DATAPATH_VERSION 0x1
+
+enum ovs_datapath_cmd {
+	OVS_DP_CMD_UNSPEC,
+	OVS_DP_CMD_NEW,
+	OVS_DP_CMD_DEL,
+	OVS_DP_CMD_GET,
+	OVS_DP_CMD_SET
+};
+
+/**
+ * enum ovs_datapath_attr - attributes for %OVS_DP_* commands.
+ * @OVS_DP_ATTR_NAME: Name of the network device that serves as the "local
+ * port".  This is the name of the network device whose dp_ifindex is given in
+ * the &struct ovs_header.  Always present in notifications.  Required in
+ * %OVS_DP_NEW requests.  May be used as an alternative to specifying
+ * dp_ifindex in other requests (with a dp_ifindex of 0).
+ * @OVS_DP_ATTR_UPCALL_PID: The Netlink socket in userspace that is initially
+ * set on the datapath port (for OVS_ACTION_ATTR_MISS).  Only valid on
+ * %OVS_DP_CMD_NEW requests. A value of zero indicates that upcalls should
+ * not be sent.
+ * @OVS_DP_ATTR_STATS: Statistics about packets that have passed through the
+ * datapath.  Always present in notifications.
+ *
+ * These attributes follow the &struct ovs_header within the Generic Netlink
+ * payload for %OVS_DP_* commands.
+ */
+enum ovs_datapath_attr {
+	OVS_DP_ATTR_UNSPEC,
+	OVS_DP_ATTR_NAME,       /* name of dp_ifindex netdev */
+	OVS_DP_ATTR_UPCALL_PID, /* Netlink PID to receive upcalls */
+	OVS_DP_ATTR_STATS,      /* struct ovs_dp_stats */
+	__OVS_DP_ATTR_MAX
+};
+
+#define OVS_DP_ATTR_MAX (__OVS_DP_ATTR_MAX - 1)
+
+struct ovs_dp_stats {
+	__u64 n_hit;             /* Number of flow table matches. */
+	__u64 n_missed;          /* Number of flow table misses. */
+	__u64 n_lost;            /* Number of misses not sent to userspace. */
+	__u64 n_flows;           /* Number of flows present */
+};
+
+struct ovs_vport_stats {
+	__u64   rx_packets;		/* total packets received       */
+	__u64   tx_packets;		/* total packets transmitted    */
+	__u64   rx_bytes;		/* total bytes received         */
+	__u64   tx_bytes;		/* total bytes transmitted      */
+	__u64   rx_errors;		/* bad packets received         */
+	__u64   tx_errors;		/* packet transmit problems     */
+	__u64   rx_dropped;		/* no space in linux buffers    */
+	__u64   tx_dropped;		/* no space available in linux  */
+};
+
+/* Fixed logical ports. */
+#define OVSP_LOCAL      ((__u16)0)
+
+/* Packet transfer. */
+
+#define OVS_PACKET_FAMILY "ovs_packet"
+#define OVS_PACKET_VERSION 0x1
+
+enum ovs_packet_cmd {
+	OVS_PACKET_CMD_UNSPEC,
+
+	/* Kernel-to-user notifications. */
+	OVS_PACKET_CMD_MISS,    /* Flow table miss. */
+	OVS_PACKET_CMD_ACTION,  /* OVS_ACTION_ATTR_USERSPACE action. */
+
+	/* Userspace commands. */
+	OVS_PACKET_CMD_EXECUTE  /* Apply actions to a packet. */
+};
+
+/**
+ * enum ovs_packet_attr - attributes for %OVS_PACKET_* commands.
+ * @OVS_PACKET_ATTR_PACKET: Present for all notifications.  Contains the entire
+ * packet as received, from the start of the Ethernet header onward.  For
+ * %OVS_PACKET_CMD_ACTION, %OVS_PACKET_ATTR_PACKET reflects changes made by
+ * actions preceding %OVS_ACTION_ATTR_USERSPACE, but %OVS_PACKET_ATTR_KEY is
+ * the flow key extracted from the packet as originally received.
+ * @OVS_PACKET_ATTR_KEY: Present for all notifications.  Contains the flow key
+ * extracted from the packet as nested %OVS_KEY_ATTR_* attributes.  This allows
+ * userspace to adapt its flow setup strategy by comparing its notion of the
+ * flow key against the kernel's.
+ * @OVS_PACKET_ATTR_ACTIONS: Contains actions for the packet.  Used
+ * for %OVS_PACKET_CMD_EXECUTE.  It has nested %OVS_ACTION_ATTR_* attributes.
+ * @OVS_PACKET_ATTR_USERDATA: Present for an %OVS_PACKET_CMD_ACTION
+ * notification if the %OVS_ACTION_ATTR_USERSPACE action specified an
+ * %OVS_USERSPACE_ATTR_USERDATA attribute.
+ *
+ * These attributes follow the &struct ovs_header within the Generic Netlink
+ * payload for %OVS_PACKET_* commands.
+ */
+enum ovs_packet_attr {
+	OVS_PACKET_ATTR_UNSPEC,
+	OVS_PACKET_ATTR_PACKET,      /* Packet data. */
+	OVS_PACKET_ATTR_KEY,         /* Nested OVS_KEY_ATTR_* attributes. */
+	OVS_PACKET_ATTR_ACTIONS,     /* Nested OVS_ACTION_ATTR_* attributes. */
+	OVS_PACKET_ATTR_USERDATA,    /* u64 OVS_ACTION_ATTR_USERSPACE arg. */
+	__OVS_PACKET_ATTR_MAX
+};
+
+#define OVS_PACKET_ATTR_MAX (__OVS_PACKET_ATTR_MAX - 1)
+
+/* Virtual ports. */
+
+#define OVS_VPORT_FAMILY  "ovs_vport"
+#define OVS_VPORT_MCGROUP "ovs_vport"
+#define OVS_VPORT_VERSION 0x1
+
+enum ovs_vport_cmd {
+	OVS_VPORT_CMD_UNSPEC,
+	OVS_VPORT_CMD_NEW,
+	OVS_VPORT_CMD_DEL,
+	OVS_VPORT_CMD_GET,
+	OVS_VPORT_CMD_SET
+};
+
+enum ovs_vport_type {
+	OVS_VPORT_TYPE_UNSPEC,
+	OVS_VPORT_TYPE_NETDEV,   /* network device */
+	OVS_VPORT_TYPE_INTERNAL, /* network device implemented by datapath */
+	__OVS_VPORT_TYPE_MAX
+};
+
+#define OVS_VPORT_TYPE_MAX (__OVS_VPORT_TYPE_MAX - 1)
+
+/**
+ * enum ovs_vport_attr - attributes for %OVS_VPORT_* commands.
+ * @OVS_VPORT_ATTR_PORT_NO: 32-bit port number within datapath.
+ * @OVS_VPORT_ATTR_TYPE: 32-bit %OVS_VPORT_TYPE_* constant describing the type
+ * of vport.
+ * @OVS_VPORT_ATTR_NAME: Name of vport.  For a vport based on a network device
+ * this is the name of the network device.  Maximum length %IFNAMSIZ-1 bytes
+ * plus a null terminator.
+ * @OVS_VPORT_ATTR_OPTIONS: Vport-specific configuration information.
+ * @OVS_VPORT_ATTR_UPCALL_PID: The Netlink socket in userspace that
+ * OVS_PACKET_CMD_MISS upcalls will be directed to for packets received on
+ * this port.  A value of zero indicates that upcalls should not be sent.
+ * @OVS_VPORT_ATTR_STATS: A &struct ovs_vport_stats giving statistics for
+ * packets sent or received through the vport.
+ *
+ * These attributes follow the &struct ovs_header within the Generic Netlink
+ * payload for %OVS_VPORT_* commands.
+ *
+ * For %OVS_VPORT_CMD_NEW requests, the %OVS_VPORT_ATTR_TYPE and
+ * %OVS_VPORT_ATTR_NAME attributes are required.  %OVS_VPORT_ATTR_PORT_NO is
+ * optional; if not specified a free port number is automatically selected.
+ * Whether %OVS_VPORT_ATTR_OPTIONS is required or optional depends on the type
+ * of vport.
+ * and other attributes are ignored.
+ *
+ * For other requests, if %OVS_VPORT_ATTR_NAME is specified then it is used to
+ * look up the vport to operate on; otherwise dp_idx from the &struct
+ * ovs_header plus %OVS_VPORT_ATTR_PORT_NO determine the vport.
+ */
+enum ovs_vport_attr {
+	OVS_VPORT_ATTR_UNSPEC,
+	OVS_VPORT_ATTR_PORT_NO,	/* u32 port number within datapath */
+	OVS_VPORT_ATTR_TYPE,	/* u32 OVS_VPORT_TYPE_* constant. */
+	OVS_VPORT_ATTR_NAME,	/* string name, up to IFNAMSIZ bytes long */
+	OVS_VPORT_ATTR_OPTIONS, /* nested attributes, varies by vport type */
+	OVS_VPORT_ATTR_UPCALL_PID, /* u32 Netlink PID to receive upcalls */
+	OVS_VPORT_ATTR_STATS,	/* struct ovs_vport_stats */
+	__OVS_VPORT_ATTR_MAX
+};
+
+#define OVS_VPORT_ATTR_MAX (__OVS_VPORT_ATTR_MAX - 1)
+
+/* Flows. */
+
+#define OVS_FLOW_FAMILY  "ovs_flow"
+#define OVS_FLOW_MCGROUP "ovs_flow"
+#define OVS_FLOW_VERSION 0x1
+
+enum ovs_flow_cmd {
+	OVS_FLOW_CMD_UNSPEC,
+	OVS_FLOW_CMD_NEW,
+	OVS_FLOW_CMD_DEL,
+	OVS_FLOW_CMD_GET,
+	OVS_FLOW_CMD_SET
+};
+
+struct ovs_flow_stats {
+	__u64 n_packets;         /* Number of matched packets. */
+	__u64 n_bytes;           /* Number of matched bytes. */
+};
+
+enum ovs_key_attr {
+	OVS_KEY_ATTR_UNSPEC,
+	OVS_KEY_ATTR_ENCAP,	/* Nested set of encapsulated attributes. */
+	OVS_KEY_ATTR_PRIORITY,  /* u32 skb->priority */
+	OVS_KEY_ATTR_IN_PORT,   /* u32 OVS dp port number */
+	OVS_KEY_ATTR_ETHERNET,  /* struct ovs_key_ethernet */
+	OVS_KEY_ATTR_VLAN,	/* be16 VLAN TCI */
+	OVS_KEY_ATTR_ETHERTYPE,	/* be16 Ethernet type */
+	OVS_KEY_ATTR_IPV4,      /* struct ovs_key_ipv4 */
+	OVS_KEY_ATTR_IPV6,      /* struct ovs_key_ipv6 */
+	OVS_KEY_ATTR_TCP,       /* struct ovs_key_tcp */
+	OVS_KEY_ATTR_UDP,       /* struct ovs_key_udp */
+	OVS_KEY_ATTR_ICMP,      /* struct ovs_key_icmp */
+	OVS_KEY_ATTR_ICMPV6,    /* struct ovs_key_icmpv6 */
+	OVS_KEY_ATTR_ARP,       /* struct ovs_key_arp */
+	OVS_KEY_ATTR_ND,        /* struct ovs_key_nd */
+	__OVS_KEY_ATTR_MAX
+};
+
+#define OVS_KEY_ATTR_MAX (__OVS_KEY_ATTR_MAX - 1)
+
+/**
+ * enum ovs_frag_type - IPv4 and IPv6 fragment type
+ * @OVS_FRAG_TYPE_NONE: Packet is not a fragment.
+ * @OVS_FRAG_TYPE_FIRST: Packet is a fragment with offset 0.
+ * @OVS_FRAG_TYPE_LATER: Packet is a fragment with nonzero offset.
+ *
+ * Used as the @ipv4_frag in &struct ovs_key_ipv4 and as @ipv6_frag &struct
+ * ovs_key_ipv6.
+ */
+enum ovs_frag_type {
+	OVS_FRAG_TYPE_NONE,
+	OVS_FRAG_TYPE_FIRST,
+	OVS_FRAG_TYPE_LATER,
+	__OVS_FRAG_TYPE_MAX
+};
+
+#define OVS_FRAG_TYPE_MAX (__OVS_FRAG_TYPE_MAX - 1)
+
+struct ovs_key_ethernet {
+	__u8	 eth_src[6];
+	__u8	 eth_dst[6];
+};
+
+struct ovs_key_ipv4 {
+	__be32 ipv4_src;
+	__be32 ipv4_dst;
+	__u8   ipv4_proto;
+	__u8   ipv4_tos;
+	__u8   ipv4_ttl;
+	__u8   ipv4_frag;	/* One of OVS_FRAG_TYPE_*. */
+};
+
+struct ovs_key_ipv6 {
+	__be32 ipv6_src[4];
+	__be32 ipv6_dst[4];
+	__be32 ipv6_label;	/* 20-bits in least-significant bits. */
+	__u8   ipv6_proto;
+	__u8   ipv6_tclass;
+	__u8   ipv6_hlimit;
+	__u8   ipv6_frag;	/* One of OVS_FRAG_TYPE_*. */
+};
+
+struct ovs_key_tcp {
+	__be16 tcp_src;
+	__be16 tcp_dst;
+};
+
+struct ovs_key_udp {
+	__be16 udp_src;
+	__be16 udp_dst;
+};
+
+struct ovs_key_icmp {
+	__u8 icmp_type;
+	__u8 icmp_code;
+};
+
+struct ovs_key_icmpv6 {
+	__u8 icmpv6_type;
+	__u8 icmpv6_code;
+};
+
+struct ovs_key_arp {
+	__be32 arp_sip;
+	__be32 arp_tip;
+	__be16 arp_op;
+	__u8   arp_sha[6];
+	__u8   arp_tha[6];
+};
+
+struct ovs_key_nd {
+	__u32 nd_target[4];
+	__u8  nd_sll[6];
+	__u8  nd_tll[6];
+};
+
+/**
+ * enum ovs_flow_attr - attributes for %OVS_FLOW_* commands.
+ * @OVS_FLOW_ATTR_KEY: Nested %OVS_KEY_ATTR_* attributes specifying the flow
+ * key.  Always present in notifications.  Required for all requests (except
+ * dumps).
+ * @OVS_FLOW_ATTR_ACTIONS: Nested %OVS_ACTION_ATTR_* attributes specifying
+ * the actions to take for packets that match the key.  Always present in
+ * notifications.  Required for %OVS_FLOW_CMD_NEW requests, optional for
+ * %OVS_FLOW_CMD_SET requests.
+ * @OVS_FLOW_ATTR_STATS: &struct ovs_flow_stats giving statistics for this
+ * flow.  Present in notifications if the stats would be nonzero.  Ignored in
+ * requests.
+ * @OVS_FLOW_ATTR_TCP_FLAGS: An 8-bit value giving the OR'd value of all of the
+ * TCP flags seen on packets in this flow.  Only present in notifications for
+ * TCP flows, and only if it would be nonzero.  Ignored in requests.
+ * @OVS_FLOW_ATTR_USED: A 64-bit integer giving the time, in milliseconds on
+ * the system monotonic clock, at which a packet was last processed for this
+ * flow.  Only present in notifications if a packet has been processed for this
+ * flow.  Ignored in requests.
+ * @OVS_FLOW_ATTR_CLEAR: If present in a %OVS_FLOW_CMD_SET request, clears the
+ * last-used time, accumulated TCP flags, and statistics for this flow.
+ * Otherwise ignored in requests.  Never present in notifications.
+ *
+ * These attributes follow the &struct ovs_header within the Generic Netlink
+ * payload for %OVS_FLOW_* commands.
+ */
+enum ovs_flow_attr {
+	OVS_FLOW_ATTR_UNSPEC,
+	OVS_FLOW_ATTR_KEY,       /* Sequence of OVS_KEY_ATTR_* attributes. */
+	OVS_FLOW_ATTR_ACTIONS,   /* Nested OVS_ACTION_ATTR_* attributes. */
+	OVS_FLOW_ATTR_STATS,     /* struct ovs_flow_stats. */
+	OVS_FLOW_ATTR_TCP_FLAGS, /* 8-bit OR'd TCP flags. */
+	OVS_FLOW_ATTR_USED,      /* u64 msecs last used in monotonic time. */
+	OVS_FLOW_ATTR_CLEAR,     /* Flag to clear stats, tcp_flags, used. */
+	__OVS_FLOW_ATTR_MAX
+};
+
+#define OVS_FLOW_ATTR_MAX (__OVS_FLOW_ATTR_MAX - 1)
+
+/**
+ * enum ovs_sample_attr - Attributes for %OVS_ACTION_ATTR_SAMPLE action.
+ * @OVS_SAMPLE_ATTR_PROBABILITY: 32-bit fraction of packets to sample with
+ * @OVS_ACTION_ATTR_SAMPLE.  A value of 0 samples no packets, a value of
+ * %UINT32_MAX samples all packets and intermediate values sample intermediate
+ * fractions of packets.
+ * @OVS_SAMPLE_ATTR_ACTIONS: Set of actions to execute in sampling event.
+ * Actions are passed as nested attributes.
+ *
+ * Executes the specified actions with the given probability on a per-packet
+ * basis.
+ */
+enum ovs_sample_attr {
+	OVS_SAMPLE_ATTR_UNSPEC,
+	OVS_SAMPLE_ATTR_PROBABILITY, /* u32 number */
+	OVS_SAMPLE_ATTR_ACTIONS,     /* Nested OVS_ACTION_ATTR_* attributes. */
+	__OVS_SAMPLE_ATTR_MAX,
+};
+
+#define OVS_SAMPLE_ATTR_MAX (__OVS_SAMPLE_ATTR_MAX - 1)
+
+/**
+ * enum ovs_userspace_attr - Attributes for %OVS_ACTION_ATTR_USERSPACE action.
+ * @OVS_USERSPACE_ATTR_PID: u32 Netlink PID to which the %OVS_PACKET_CMD_ACTION
+ * message should be sent.  Required.
+ * @OVS_USERSPACE_ATTR_USERDATA: If present, its u64 argument is copied to the
+ * %OVS_PACKET_CMD_ACTION message as %OVS_PACKET_ATTR_USERDATA,
+ */
+enum ovs_userspace_attr {
+	OVS_USERSPACE_ATTR_UNSPEC,
+	OVS_USERSPACE_ATTR_PID,	      /* u32 Netlink PID to receive upcalls. */
+	OVS_USERSPACE_ATTR_USERDATA,  /* u64 optional user-specified cookie. */
+	__OVS_USERSPACE_ATTR_MAX
+};
+
+#define OVS_USERSPACE_ATTR_MAX (__OVS_USERSPACE_ATTR_MAX - 1)
+
+/**
+ * struct ovs_action_push_vlan - %OVS_ACTION_ATTR_PUSH_VLAN action argument.
+ * @vlan_tpid: Tag protocol identifier (TPID) to push.
+ * @vlan_tci: Tag control identifier (TCI) to push.  The CFI bit must be set
+ * (but it will not be set in the 802.1Q header that is pushed).
+ *
+ * The @vlan_tpid value is typically %ETH_P_8021Q.  The only acceptable TPID
+ * values are those that the kernel module also parses as 802.1Q headers, to
+ * prevent %OVS_ACTION_ATTR_PUSH_VLAN followed by %OVS_ACTION_ATTR_POP_VLAN
+ * from having surprising results.
+ */
+struct ovs_action_push_vlan {
+	__be16 vlan_tpid;	/* 802.1Q TPID. */
+	__be16 vlan_tci;	/* 802.1Q TCI (VLAN ID and priority). */
+};
+
+/**
+ * enum ovs_action_attr - Action types.
+ *
+ * @OVS_ACTION_ATTR_OUTPUT: Output packet to port.
+ * @OVS_ACTION_ATTR_USERSPACE: Send packet to userspace according to nested
+ * %OVS_USERSPACE_ATTR_* attributes.
+ * @OVS_ACTION_ATTR_SET: Replaces the contents of an existing header.  The
+ * single nested %OVS_KEY_ATTR_* attribute specifies a header to modify and its
+ * value.
+ * @OVS_ACTION_ATTR_PUSH_VLAN: Push a new outermost 802.1Q header onto the
+ * packet.
+ * @OVS_ACTION_ATTR_POP_VLAN: Pop the outermost 802.1Q header off the packet.
+ * @OVS_ACTION_ATTR_SAMPLE: Probabilitically executes actions, as specified in
+ * the nested %OVS_SAMPLE_ATTR_* attributes.
+ *
+ * Only a single header can be set with a single %OVS_ACTION_ATTR_SET.  Not all
+ * fields within a header are modifiable, e.g. the IPv4 protocol and fragment
+ * type may not be changed.
+ */
+
+enum ovs_action_attr {
+	OVS_ACTION_ATTR_UNSPEC,
+	OVS_ACTION_ATTR_OUTPUT,	      /* u32 port number. */
+	OVS_ACTION_ATTR_USERSPACE,    /* Nested OVS_USERSPACE_ATTR_*. */
+	OVS_ACTION_ATTR_SET,          /* One nested OVS_KEY_ATTR_*. */
+	OVS_ACTION_ATTR_PUSH_VLAN,    /* struct ovs_action_push_vlan. */
+	OVS_ACTION_ATTR_POP_VLAN,     /* No argument. */
+	OVS_ACTION_ATTR_SAMPLE,       /* Nested OVS_SAMPLE_ATTR_*. */
+	__OVS_ACTION_ATTR_MAX
+};
+
+#define OVS_ACTION_ATTR_MAX (__OVS_ACTION_ATTR_MAX - 1)
+
+#endif /* _LINUX_OPENVSWITCH_H */
diff --git a/include/linux/pci-ats.h b/include/linux/pci-ats.h
index e3d0b38..7ef6872 100644
--- a/include/linux/pci-ats.h
+++ b/include/linux/pci-ats.h
@@ -12,7 +12,7 @@ struct pci_ats {
 	unsigned int is_enabled:1;      /* Enable bit is set */
 };
 
-#ifdef CONFIG_PCI_IOV
+#ifdef CONFIG_PCI_ATS
 
 extern int pci_enable_ats(struct pci_dev *dev, int ps);
 extern void pci_disable_ats(struct pci_dev *dev);
@@ -29,7 +29,7 @@ static inline int pci_ats_enabled(struct pci_dev *dev)
 	return dev->ats && dev->ats->is_enabled;
 }
 
-#else /* CONFIG_PCI_IOV */
+#else /* CONFIG_PCI_ATS */
 
 static inline int pci_enable_ats(struct pci_dev *dev, int ps)
 {
@@ -50,7 +50,7 @@ static inline int pci_ats_enabled(struct pci_dev *dev)
 	return 0;
 }
 
-#endif /* CONFIG_PCI_IOV */
+#endif /* CONFIG_PCI_ATS */
 
 #ifdef CONFIG_PCI_PRI
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 337df0d..7cda65b 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -338,7 +338,7 @@ struct pci_dev {
 	struct list_head msi_list;
 #endif
 	struct pci_vpd *vpd;
-#ifdef CONFIG_PCI_IOV
+#ifdef CONFIG_PCI_ATS
 	union {
 		struct pci_sriov *sriov;	/* SR-IOV capability related */
 		struct pci_dev *physfn;	/* the PF this VF is associated with */
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 172ba70..2aaee0c 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -517,8 +517,12 @@
 #define PCI_DEVICE_ID_AMD_11H_NB_DRAM	0x1302
 #define PCI_DEVICE_ID_AMD_11H_NB_MISC	0x1303
 #define PCI_DEVICE_ID_AMD_11H_NB_LINK	0x1304
+#define PCI_DEVICE_ID_AMD_15H_NB_F0	0x1600
+#define PCI_DEVICE_ID_AMD_15H_NB_F1	0x1601
+#define PCI_DEVICE_ID_AMD_15H_NB_F2	0x1602
 #define PCI_DEVICE_ID_AMD_15H_NB_F3	0x1603
 #define PCI_DEVICE_ID_AMD_15H_NB_F4	0x1604
+#define PCI_DEVICE_ID_AMD_15H_NB_F5	0x1605
 #define PCI_DEVICE_ID_AMD_CNB17H_F3	0x1703
 #define PCI_DEVICE_ID_AMD_LANCE		0x2000
 #define PCI_DEVICE_ID_AMD_LANCE_HOME	0x2001
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 1e9ebe5..b1f8912 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -822,6 +822,7 @@ struct perf_event {
 	int				mmap_locked;
 	struct user_struct		*mmap_user;
 	struct ring_buffer		*rb;
+	struct list_head		rb_entry;
 
 	/* poll related */
 	wait_queue_head_t		waitq;
diff --git a/include/linux/phonet.h b/include/linux/phonet.h
index f53a416..f48bfc8 100644
--- a/include/linux/phonet.h
+++ b/include/linux/phonet.h
@@ -38,6 +38,7 @@
 #define PNPIPE_ENCAP		1
 #define PNPIPE_IFINDEX		2
 #define PNPIPE_HANDLE		3
+#define PNPIPE_INITSTATE	4
 
 #define PNADDR_ANY		0
 #define PNADDR_BROADCAST	0xFC
@@ -49,6 +50,7 @@
 
 /* ioctls */
 #define SIOCPNGETOBJECT		(SIOCPROTOPRIVATE + 0)
+#define SIOCPNENABLEPIPE	(SIOCPROTOPRIVATE + 13)
 #define SIOCPNADDRESOURCE	(SIOCPROTOPRIVATE + 14)
 #define SIOCPNDELRESOURCE	(SIOCPROTOPRIVATE + 15)
 
diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h
index c533670..8daced3 100644
--- a/include/linux/pkt_sched.h
+++ b/include/linux/pkt_sched.h
@@ -30,7 +30,7 @@
  */
 
 struct tc_stats {
-	__u64	bytes;			/* NUmber of enqueues bytes */
+	__u64	bytes;			/* Number of enqueued bytes */
 	__u32	packets;		/* Number of enqueued packets	*/
 	__u32	drops;			/* Packets dropped because of lack of resources */
 	__u32	overlimits;		/* Number of throttle events when this
@@ -181,6 +181,7 @@ enum {
 	TCA_RED_UNSPEC,
 	TCA_RED_PARMS,
 	TCA_RED_STAB,
+	TCA_RED_MAX_P,
 	__TCA_RED_MAX,
 };
 
@@ -194,8 +195,9 @@ struct tc_red_qopt {
 	unsigned char   Plog;		/* log(P_max/(qth_max-qth_min))	*/
 	unsigned char   Scell_log;	/* cell size for idle damping */
 	unsigned char	flags;
-#define TC_RED_ECN	1
-#define TC_RED_HARDDROP	2
+#define TC_RED_ECN		1
+#define TC_RED_HARDDROP		2
+#define TC_RED_ADAPTATIVE	4
 };
 
 struct tc_red_xstats {
@@ -214,6 +216,7 @@ enum {
        TCA_GRED_PARMS,
        TCA_GRED_STAB,
        TCA_GRED_DPS,
+       TCA_GRED_MAX_P,
 	   __TCA_GRED_MAX,
 };
 
@@ -253,6 +256,7 @@ enum {
 	TCA_CHOKE_UNSPEC,
 	TCA_CHOKE_PARMS,
 	TCA_CHOKE_STAB,
+	TCA_CHOKE_MAX_P,
 	__TCA_CHOKE_MAX,
 };
 
@@ -297,7 +301,7 @@ struct tc_htb_glob {
 	__u32 debug;		/* debug flags */
 
 	/* stats */
-	__u32 direct_pkts; /* count of non shapped packets */
+	__u32 direct_pkts; /* count of non shaped packets */
 };
 enum {
 	TCA_HTB_UNSPEC,
@@ -465,6 +469,7 @@ enum {
 	TCA_NETEM_REORDER,
 	TCA_NETEM_CORRUPT,
 	TCA_NETEM_LOSS,
+	TCA_NETEM_RATE,
 	__TCA_NETEM_MAX,
 };
 
@@ -495,6 +500,13 @@ struct tc_netem_corrupt {
 	__u32	correlation;
 };
 
+struct tc_netem_rate {
+	__u32	rate;	/* byte/s */
+	__s32	packet_overhead;
+	__u32	cell_size;
+	__s32	cell_overhead;
+};
+
 enum {
 	NETEM_LOSS_UNSPEC,
 	NETEM_LOSS_GI,		/* General Intuitive - 4 state model */
@@ -503,7 +515,7 @@ enum {
 };
 #define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1)
 
-/* State transition probablities for 4 state model */
+/* State transition probabilities for 4 state model */
 struct tc_netem_gimodel {
 	__u32	p13;
 	__u32	p31;
diff --git a/include/linux/pm.h b/include/linux/pm.h
index f15acb6..3f3ed83 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -54,118 +54,145 @@ typedef struct pm_message {
 /**
  * struct dev_pm_ops - device PM callbacks
  *
- * Several driver power state transitions are externally visible, affecting
+ * Several device power state transitions are externally visible, affecting
  * the state of pending I/O queues and (for drivers that touch hardware)
  * interrupts, wakeups, DMA, and other hardware state.  There may also be
- * internal transitions to various low power modes, which are transparent
+ * internal transitions to various low-power modes which are transparent
  * to the rest of the driver stack (such as a driver that's ON gating off
  * clocks which are not in active use).
  *
- * The externally visible transitions are handled with the help of the following
- * callbacks included in this structure:
- *
- * @prepare: Prepare the device for the upcoming transition, but do NOT change
- *	its hardware state.  Prevent new children of the device from being
- *	registered after @prepare() returns (the driver's subsystem and
- *	generally the rest of the kernel is supposed to prevent new calls to the
- *	probe method from being made too once @prepare() has succeeded).  If
- *	@prepare() detects a situation it cannot handle (e.g. registration of a
- *	child already in progress), it may return -EAGAIN, so that the PM core
- *	can execute it once again (e.g. after the new child has been registered)
- *	to recover from the race condition.  This method is executed for all
- *	kinds of suspend transitions and is followed by one of the suspend
- *	callbacks: @suspend(), @freeze(), or @poweroff().
- *	The PM core executes @prepare() for all devices before starting to
- *	execute suspend callbacks for any of them, so drivers may assume all of
- *	the other devices to be present and functional while @prepare() is being
- *	executed.  In particular, it is safe to make GFP_KERNEL memory
- *	allocations from within @prepare().  However, drivers may NOT assume
- *	anything about the availability of the user space at that time and it
- *	is not correct to request firmware from within @prepare() (it's too
- *	late to do that).  [To work around this limitation, drivers may
- *	register suspend and hibernation notifiers that are executed before the
- *	freezing of tasks.]
+ * The externally visible transitions are handled with the help of callbacks
+ * included in this structure in such a way that two levels of callbacks are
+ * involved.  First, the PM core executes callbacks provided by PM domains,
+ * device types, classes and bus types.  They are the subsystem-level callbacks
+ * supposed to execute callbacks provided by device drivers, although they may
+ * choose not to do that.  If the driver callbacks are executed, they have to
+ * collaborate with the subsystem-level callbacks to achieve the goals
+ * appropriate for the given system transition, given transition phase and the
+ * subsystem the device belongs to.
+ *
+ * @prepare: The principal role of this callback is to prevent new children of
+ *	the device from being registered after it has returned (the driver's
+ *	subsystem and generally the rest of the kernel is supposed to prevent
+ *	new calls to the probe method from being made too once @prepare() has
+ *	succeeded).  If @prepare() detects a situation it cannot handle (e.g.
+ *	registration of a child already in progress), it may return -EAGAIN, so
+ *	that the PM core can execute it once again (e.g. after a new child has
+ *	been registered) to recover from the race condition.
+ *	This method is executed for all kinds of suspend transitions and is
+ *	followed by one of the suspend callbacks: @suspend(), @freeze(), or
+ *	@poweroff().  The PM core executes subsystem-level @prepare() for all
+ *	devices before starting to invoke suspend callbacks for any of them, so
+ *	generally devices may be assumed to be functional or to respond to
+ *	runtime resume requests while @prepare() is being executed.  However,
+ *	device drivers may NOT assume anything about the availability of user
+ *	space at that time and it is NOT valid to request firmware from within
+ *	@prepare() (it's too late to do that).  It also is NOT valid to allocate
+ *	substantial amounts of memory from @prepare() in the GFP_KERNEL mode.
+ *	[To work around these limitations, drivers may register suspend and
+ *	hibernation notifiers to be executed before the freezing of tasks.]
  *
  * @complete: Undo the changes made by @prepare().  This method is executed for
  *	all kinds of resume transitions, following one of the resume callbacks:
  *	@resume(), @thaw(), @restore().  Also called if the state transition
- *	fails before the driver's suspend callback (@suspend(), @freeze(),
- *	@poweroff()) can be executed (e.g. if the suspend callback fails for one
+ *	fails before the driver's suspend callback: @suspend(), @freeze() or
+ *	@poweroff(), can be executed (e.g. if the suspend callback fails for one
  *	of the other devices that the PM core has unsuccessfully attempted to
  *	suspend earlier).
- *	The PM core executes @complete() after it has executed the appropriate
- *	resume callback for all devices.
+ *	The PM core executes subsystem-level @complete() after it has executed
+ *	the appropriate resume callbacks for all devices.
  *
  * @suspend: Executed before putting the system into a sleep state in which the
- *	contents of main memory are preserved.  Quiesce the device, put it into
- *	a low power state appropriate for the upcoming system state (such as
- *	PCI_D3hot), and enable wakeup events as appropriate.
+ *	contents of main memory are preserved.  The exact action to perform
+ *	depends on the device's subsystem (PM domain, device type, class or bus
+ *	type), but generally the device must be quiescent after subsystem-level
+ *	@suspend() has returned, so that it doesn't do any I/O or DMA.
+ *	Subsystem-level @suspend() is executed for all devices after invoking
+ *	subsystem-level @prepare() for all of them.
  *
  * @resume: Executed after waking the system up from a sleep state in which the
- *	contents of main memory were preserved.  Put the device into the
- *	appropriate state, according to the information saved in memory by the
- *	preceding @suspend().  The driver starts working again, responding to
- *	hardware events and software requests.  The hardware may have gone
- *	through a power-off reset, or it may have maintained state from the
- *	previous suspend() which the driver may rely on while resuming.  On most
- *	platforms, there are no restrictions on availability of resources like
- *	clocks during @resume().
+ *	contents of main memory were preserved.  The exact action to perform
+ *	depends on the device's subsystem, but generally the driver is expected
+ *	to start working again, responding to hardware events and software
+ *	requests (the device itself may be left in a low-power state, waiting
+ *	for a runtime resume to occur).  The state of the device at the time its
+ *	driver's @resume() callback is run depends on the platform and subsystem
+ *	the device belongs to.  On most platforms, there are no restrictions on
+ *	availability of resources like clocks during @resume().
+ *	Subsystem-level @resume() is executed for all devices after invoking
+ *	subsystem-level @resume_noirq() for all of them.
  *
  * @freeze: Hibernation-specific, executed before creating a hibernation image.
- *	Quiesce operations so that a consistent image can be created, but do NOT
- *	otherwise put the device into a low power device state and do NOT emit
- *	system wakeup events.  Save in main memory the device settings to be
- *	used by @restore() during the subsequent resume from hibernation or by
- *	the subsequent @thaw(), if the creation of the image or the restoration
- *	of main memory contents from it fails.
+ *	Analogous to @suspend(), but it should not enable the device to signal
+ *	wakeup events or change its power state.  The majority of subsystems
+ *	(with the notable exception of the PCI bus type) expect the driver-level
+ *	@freeze() to save the device settings in memory to be used by @restore()
+ *	during the subsequent resume from hibernation.
+ *	Subsystem-level @freeze() is executed for all devices after invoking
+ *	subsystem-level @prepare() for all of them.
  *
  * @thaw: Hibernation-specific, executed after creating a hibernation image OR
- *	if the creation of the image fails.  Also executed after a failing
+ *	if the creation of an image has failed.  Also executed after a failing
  *	attempt to restore the contents of main memory from such an image.
  *	Undo the changes made by the preceding @freeze(), so the device can be
  *	operated in the same way as immediately before the call to @freeze().
+ *	Subsystem-level @thaw() is executed for all devices after invoking
+ *	subsystem-level @thaw_noirq() for all of them.  It also may be executed
+ *	directly after @freeze() in case of a transition error.
  *
  * @poweroff: Hibernation-specific, executed after saving a hibernation image.
- *	Quiesce the device, put it into a low power state appropriate for the
- *	upcoming system state (such as PCI_D3hot), and enable wakeup events as
- *	appropriate.
+ *	Analogous to @suspend(), but it need not save the device's settings in
+ *	memory.
+ *	Subsystem-level @poweroff() is executed for all devices after invoking
+ *	subsystem-level @prepare() for all of them.
  *
  * @restore: Hibernation-specific, executed after restoring the contents of main
- *	memory from a hibernation image.  Driver starts working again,
- *	responding to hardware events and software requests.  Drivers may NOT
- *	make ANY assumptions about the hardware state right prior to @restore().
- *	On most platforms, there are no restrictions on availability of
- *	resources like clocks during @restore().
- *
- * @suspend_noirq: Complete the operations of ->suspend() by carrying out any
- *	actions required for suspending the device that need interrupts to be
- *	disabled
- *
- * @resume_noirq: Prepare for the execution of ->resume() by carrying out any
- *	actions required for resuming the device that need interrupts to be
- *	disabled
- *
- * @freeze_noirq: Complete the operations of ->freeze() by carrying out any
- *	actions required for freezing the device that need interrupts to be
- *	disabled
- *
- * @thaw_noirq: Prepare for the execution of ->thaw() by carrying out any
- *	actions required for thawing the device that need interrupts to be
- *	disabled
- *
- * @poweroff_noirq: Complete the operations of ->poweroff() by carrying out any
- *	actions required for handling the device that need interrupts to be
- *	disabled
- *
- * @restore_noirq: Prepare for the execution of ->restore() by carrying out any
- *	actions required for restoring the operations of the device that need
- *	interrupts to be disabled
+ *	memory from a hibernation image, analogous to @resume().
+ *
+ * @suspend_noirq: Complete the actions started by @suspend().  Carry out any
+ *	additional operations required for suspending the device that might be
+ *	racing with its driver's interrupt handler, which is guaranteed not to
+ *	run while @suspend_noirq() is being executed.
+ *	It generally is expected that the device will be in a low-power state
+ *	(appropriate for the target system sleep state) after subsystem-level
+ *	@suspend_noirq() has returned successfully.  If the device can generate
+ *	system wakeup signals and is enabled to wake up the system, it should be
+ *	configured to do so at that time.  However, depending on the platform
+ *	and device's subsystem, @suspend() may be allowed to put the device into
+ *	the low-power state and configure it to generate wakeup signals, in
+ *	which case it generally is not necessary to define @suspend_noirq().
+ *
+ * @resume_noirq: Prepare for the execution of @resume() by carrying out any
+ *	operations required for resuming the device that might be racing with
+ *	its driver's interrupt handler, which is guaranteed not to run while
+ *	@resume_noirq() is being executed.
+ *
+ * @freeze_noirq: Complete the actions started by @freeze().  Carry out any
+ *	additional operations required for freezing the device that might be
+ *	racing with its driver's interrupt handler, which is guaranteed not to
+ *	run while @freeze_noirq() is being executed.
+ *	The power state of the device should not be changed by either @freeze()
+ *	or @freeze_noirq() and it should not be configured to signal system
+ *	wakeup by any of these callbacks.
+ *
+ * @thaw_noirq: Prepare for the execution of @thaw() by carrying out any
+ *	operations required for thawing the device that might be racing with its
+ *	driver's interrupt handler, which is guaranteed not to run while
+ *	@thaw_noirq() is being executed.
+ *
+ * @poweroff_noirq: Complete the actions started by @poweroff().  Analogous to
+ *	@suspend_noirq(), but it need not save the device's settings in memory.
+ *
+ * @restore_noirq: Prepare for the execution of @restore() by carrying out any
+ *	operations required for thawing the device that might be racing with its
+ *	driver's interrupt handler, which is guaranteed not to run while
+ *	@restore_noirq() is being executed.  Analogous to @resume_noirq().
  *
  * All of the above callbacks, except for @complete(), return error codes.
  * However, the error codes returned by the resume operations, @resume(),
- * @thaw(), @restore(), @resume_noirq(), @thaw_noirq(), and @restore_noirq() do
+ * @thaw(), @restore(), @resume_noirq(), @thaw_noirq(), and @restore_noirq(), do
  * not cause the PM core to abort the resume transition during which they are
- * returned.  The error codes returned in that cases are only printed by the PM
+ * returned.  The error codes returned in those cases are only printed by the PM
  * core to the system logs for debugging purposes.  Still, it is recommended
  * that drivers only return error codes from their resume methods in case of an
  * unrecoverable failure (i.e. when the device being handled refuses to resume
@@ -174,31 +201,43 @@ typedef struct pm_message {
  * their children.
  *
  * It is allowed to unregister devices while the above callbacks are being
- * executed.  However, it is not allowed to unregister a device from within any
- * of its own callbacks.
+ * executed.  However, a callback routine must NOT try to unregister the device
+ * it was called for, although it may unregister children of that device (for
+ * example, if it detects that a child was unplugged while the system was
+ * asleep).
+ *
+ * Refer to Documentation/power/devices.txt for more information about the role
+ * of the above callbacks in the system suspend process.
  *
- * There also are the following callbacks related to run-time power management
- * of devices:
+ * There also are callbacks related to runtime power management of devices.
+ * Again, these callbacks are executed by the PM core only for subsystems
+ * (PM domains, device types, classes and bus types) and the subsystem-level
+ * callbacks are supposed to invoke the driver callbacks.  Moreover, the exact
+ * actions to be performed by a device driver's callbacks generally depend on
+ * the platform and subsystem the device belongs to.
  *
  * @runtime_suspend: Prepare the device for a condition in which it won't be
  *	able to communicate with the CPU(s) and RAM due to power management.
- *	This need not mean that the device should be put into a low power state.
+ *	This need not mean that the device should be put into a low-power state.
  *	For example, if the device is behind a link which is about to be turned
  *	off, the device may remain at full power.  If the device does go to low
- *	power and is capable of generating run-time wake-up events, remote
- *	wake-up (i.e., a hardware mechanism allowing the device to request a
- *	change of its power state via a wake-up event, such as PCI PME) should
- *	be enabled for it.
+ *	power and is capable of generating runtime wakeup events, remote wakeup
+ *	(i.e., a hardware mechanism allowing the device to request a change of
+ *	its power state via an interrupt) should be enabled for it.
  *
  * @runtime_resume: Put the device into the fully active state in response to a
- *	wake-up event generated by hardware or at the request of software.  If
- *	necessary, put the device into the full power state and restore its
+ *	wakeup event generated by hardware or at the request of software.  If
+ *	necessary, put the device into the full-power state and restore its
  *	registers, so that it is fully operational.
  *
- * @runtime_idle: Device appears to be inactive and it might be put into a low
- *	power state if all of the necessary conditions are satisfied.  Check
+ * @runtime_idle: Device appears to be inactive and it might be put into a
+ *	low-power state if all of the necessary conditions are satisfied.  Check
  *	these conditions and handle the device as appropriate, possibly queueing
  *	a suspend request for it.  The return value is ignored by the PM core.
+ *
+ * Refer to Documentation/power/runtime_pm.txt for more information about the
+ * role of the above callbacks in device runtime power management.
+ *
  */
 
 struct dev_pm_ops {
@@ -447,6 +486,7 @@ struct dev_pm_info {
 	unsigned int		async_suspend:1;
 	bool			is_prepared:1;	/* Owned by the PM core */
 	bool			is_suspended:1;	/* Ditto */
+	bool			ignore_children:1;
 	spinlock_t		lock;
 #ifdef CONFIG_PM_SLEEP
 	struct list_head	entry;
@@ -464,7 +504,6 @@ struct dev_pm_info {
 	atomic_t		usage_count;
 	atomic_t		child_count;
 	unsigned int		disable_depth:3;
-	unsigned int		ignore_children:1;
 	unsigned int		idle_notification:1;
 	unsigned int		request_pending:1;
 	unsigned int		deferred_resume:1;
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index d8d9036..d3085e7 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -52,11 +52,6 @@ static inline bool pm_children_suspended(struct device *dev)
 		|| !atomic_read(&dev->power.child_count);
 }
 
-static inline void pm_suspend_ignore_children(struct device *dev, bool enable)
-{
-	dev->power.ignore_children = enable;
-}
-
 static inline void pm_runtime_get_noresume(struct device *dev)
 {
 	atomic_inc(&dev->power.usage_count);
@@ -130,7 +125,6 @@ static inline void pm_runtime_allow(struct device *dev) {}
 static inline void pm_runtime_forbid(struct device *dev) {}
 
 static inline bool pm_children_suspended(struct device *dev) { return false; }
-static inline void pm_suspend_ignore_children(struct device *dev, bool en) {}
 static inline void pm_runtime_get_noresume(struct device *dev) {}
 static inline void pm_runtime_put_noidle(struct device *dev) {}
 static inline bool device_run_wake(struct device *dev) { return false; }
diff --git a/include/linux/pstore.h b/include/linux/pstore.h
index ea56732..2ca8cde 100644
--- a/include/linux/pstore.h
+++ b/include/linux/pstore.h
@@ -35,10 +35,12 @@ struct pstore_info {
 	spinlock_t	buf_lock;	/* serialize access to 'buf' */
 	char		*buf;
 	size_t		bufsize;
+	struct mutex	read_mutex;	/* serialize open/read/close */
 	int		(*open)(struct pstore_info *psi);
 	int		(*close)(struct pstore_info *psi);
 	ssize_t		(*read)(u64 *id, enum pstore_type_id *type,
-			struct timespec *time, struct pstore_info *psi);
+			struct timespec *time, char **buf,
+			struct pstore_info *psi);
 	int		(*write)(enum pstore_type_id type, u64 *id,
 			unsigned int part, size_t size, struct pstore_info *psi);
 	int		(*erase)(enum pstore_type_id type, u64 id,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 68daf4f..1c4f3e9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1521,7 +1521,6 @@ struct task_struct {
 #ifdef CONFIG_FAULT_INJECTION
 	int make_it_fail;
 #endif
-	struct prop_local_single dirties;
 	/*
 	 * when (nr_dirtied >= nr_dirtied_pause), it's time to call
 	 * balance_dirty_pages() for some dirty throttling pause
diff --git a/include/linux/serial.h b/include/linux/serial.h
index 97ff8e2..3d86517 100644
--- a/include/linux/serial.h
+++ b/include/linux/serial.h
@@ -207,13 +207,15 @@ struct serial_icounter_struct {
 
 struct serial_rs485 {
 	__u32	flags;			/* RS485 feature flags */
-#define SER_RS485_ENABLED		(1 << 0)
-#define SER_RS485_RTS_ON_SEND		(1 << 1)
-#define SER_RS485_RTS_AFTER_SEND	(1 << 2)
-#define SER_RS485_RTS_BEFORE_SEND	(1 << 3)
+#define SER_RS485_ENABLED		(1 << 0)	/* If enabled */
+#define SER_RS485_RTS_ON_SEND		(1 << 1)	/* Logical level for
+							   RTS pin when
+							   sending */
+#define SER_RS485_RTS_AFTER_SEND	(1 << 2)	/* Logical level for
+							   RTS pin after sent*/
 #define SER_RS485_RX_DURING_TX		(1 << 4)
-	__u32	delay_rts_before_send;	/* Milliseconds */
-	__u32	delay_rts_after_send;	/* Milliseconds */
+	__u32	delay_rts_before_send;	/* Delay before send (milliseconds) */
+	__u32	delay_rts_after_send;	/* Delay after send (milliseconds) */
 	__u32	padding[5];		/* Memory is cheap, new structs
 					   are a royal PITA .. */
 };
diff --git a/include/linux/sigma.h b/include/linux/sigma.h
index e2accb3..d0de882 100644
--- a/include/linux/sigma.h
+++ b/include/linux/sigma.h
@@ -24,7 +24,7 @@ struct sigma_firmware {
 struct sigma_firmware_header {
 	unsigned char magic[7];
 	u8 version;
-	u32 crc;
+	__le32 crc;
 };
 
 enum {
@@ -40,19 +40,14 @@ enum {
 struct sigma_action {
 	u8 instr;
 	u8 len_hi;
-	u16 len;
-	u16 addr;
+	__le16 len;
+	__be16 addr;
 	unsigned char payload[];
 };
 
 static inline u32 sigma_action_len(struct sigma_action *sa)
 {
-	return (sa->len_hi << 16) | sa->len;
-}
-
-static inline size_t sigma_action_size(struct sigma_action *sa, u32 payload_len)
-{
-	return sizeof(*sa) + payload_len + (payload_len % 2);
+	return (sa->len_hi << 16) | le16_to_cpu(sa->len);
 }
 
 extern int process_sigma_firmware(struct i2c_client *client, const char *name);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f444264..12e6fed 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -30,6 +30,7 @@
 #include <linux/dmaengine.h>
 #include <linux/hrtimer.h>
 #include <linux/dma-mapping.h>
+#include <linux/netdev_features.h>
 
 /* Don't change this without changing skb_csum_unnecessary! */
 #define CHECKSUM_NONE 0
@@ -87,7 +88,6 @@
  *	at device setup time.
  *	NETIF_F_HW_CSUM	- it is clever device, it is able to checksum
  *			  everything.
- *	NETIF_F_NO_CSUM - loopback or reliable single hop media.
  *	NETIF_F_IP_CSUM - device is dumb. It is able to csum only
  *			  TCP/UDP over IPv4. Sigh. Vendors like this
  *			  way by an unknown reason. Though, see comment above
@@ -546,6 +546,7 @@ extern void consume_skb(struct sk_buff *skb);
 extern void	       __kfree_skb(struct sk_buff *skb);
 extern struct sk_buff *__alloc_skb(unsigned int size,
 				   gfp_t priority, int fclone, int node);
+extern struct sk_buff *build_skb(void *data);
 static inline struct sk_buff *alloc_skb(unsigned int size,
 					gfp_t priority)
 {
@@ -567,8 +568,9 @@ extern struct sk_buff *skb_clone(struct sk_buff *skb,
 				 gfp_t priority);
 extern struct sk_buff *skb_copy(const struct sk_buff *skb,
 				gfp_t priority);
-extern struct sk_buff *pskb_copy(struct sk_buff *skb,
-				 gfp_t gfp_mask);
+extern struct sk_buff *__pskb_copy(struct sk_buff *skb,
+				 int headroom, gfp_t gfp_mask);
+
 extern int	       pskb_expand_head(struct sk_buff *skb,
 					int nhead, int ntail,
 					gfp_t gfp_mask);
@@ -1668,38 +1670,6 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
 }
 
 /**
- *	__netdev_alloc_page - allocate a page for ps-rx on a specific device
- *	@dev: network device to receive on
- *	@gfp_mask: alloc_pages_node mask
- *
- * 	Allocate a new page. dev currently unused.
- *
- * 	%NULL is returned if there is no free memory.
- */
-static inline struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask)
-{
-	return alloc_pages_node(NUMA_NO_NODE, gfp_mask, 0);
-}
-
-/**
- *	netdev_alloc_page - allocate a page for ps-rx on a specific device
- *	@dev: network device to receive on
- *
- * 	Allocate a new page. dev currently unused.
- *
- * 	%NULL is returned if there is no free memory.
- */
-static inline struct page *netdev_alloc_page(struct net_device *dev)
-{
-	return __netdev_alloc_page(dev, GFP_ATOMIC);
-}
-
-static inline void netdev_free_page(struct net_device *dev, struct page *page)
-{
-	__free_page(page);
-}
-
-/**
  * skb_frag_page - retrieve the page refered to by a paged fragment
  * @frag: the paged fragment
  *
@@ -1830,6 +1800,12 @@ static inline dma_addr_t skb_frag_dma_map(struct device *dev,
 			    frag->page_offset + offset, size, dir);
 }
 
+static inline struct sk_buff *pskb_copy(struct sk_buff *skb,
+					gfp_t gfp_mask)
+{
+	return __pskb_copy(skb, skb_headroom(skb), gfp_mask);
+}
+
 /**
  *	skb_clone_writable - is the header of a clone writable
  *	@skb: buffer to check
@@ -2111,7 +2087,8 @@ extern void	       skb_split(struct sk_buff *skb,
 extern int	       skb_shift(struct sk_buff *tgt, struct sk_buff *skb,
 				 int shiftlen);
 
-extern struct sk_buff *skb_segment(struct sk_buff *skb, u32 features);
+extern struct sk_buff *skb_segment(struct sk_buff *skb,
+				   netdev_features_t features);
 
 static inline void *skb_header_pointer(const struct sk_buff *skb, int offset,
 				       int len, void *buffer)
diff --git a/include/linux/sock_diag.h b/include/linux/sock_diag.h
new file mode 100644
index 0000000..379d5dc
--- /dev/null
+++ b/include/linux/sock_diag.h
@@ -0,0 +1,29 @@
+#ifndef __SOCK_DIAG_H__
+#define __SOCK_DIAG_H__
+
+#define SOCK_DIAG_BY_FAMILY 20
+
+struct sk_buff;
+struct nlmsghdr;
+
+struct sock_diag_req {
+	__u8	sdiag_family;
+	__u8	sdiag_protocol;
+};
+
+struct sock_diag_handler {
+	__u8 family;
+	int (*dump)(struct sk_buff *skb, struct nlmsghdr *nlh);
+};
+
+int sock_diag_register(struct sock_diag_handler *h);
+void sock_diag_unregister(struct sock_diag_handler *h);
+
+void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
+void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh));
+
+int sock_diag_check_cookie(void *sk, __u32 *cookie);
+void sock_diag_save_cookie(void *sk, __u32 *cookie);
+
+extern struct sock *sock_diag_nlsk;
+#endif
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 3d8f9c4..2c5993a 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -215,7 +215,7 @@ static inline bool __rpc_copy_addr4(struct sockaddr *dst,
 	return true;
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static inline bool __rpc_cmp_addr6(const struct sockaddr *sap1,
 				   const struct sockaddr *sap2)
 {
@@ -237,10 +237,10 @@ static inline bool __rpc_copy_addr6(struct sockaddr *dst,
 	struct sockaddr_in6 *dsin6 = (struct sockaddr_in6 *) dst;
 
 	dsin6->sin6_family = ssin6->sin6_family;
-	ipv6_addr_copy(&dsin6->sin6_addr, &ssin6->sin6_addr);
+	dsin6->sin6_addr = ssin6->sin6_addr;
 	return true;
 }
-#else	/* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
+#else	/* !(IS_ENABLED(CONFIG_IPV6) */
 static inline bool __rpc_cmp_addr6(const struct sockaddr *sap1,
 				   const struct sockaddr *sap2)
 {
@@ -252,7 +252,7 @@ static inline bool __rpc_copy_addr6(struct sockaddr *dst,
 {
 	return false;
 }
-#endif	/* !(CONFIG_IPV6 || CONFIG_IPV6_MODULE) */
+#endif	/* !(IS_ENABLED(CONFIG_IPV6) */
 
 /**
  * rpc_cmp_addr - compare the address portion of two sockaddrs.
diff --git a/include/linux/unix_diag.h b/include/linux/unix_diag.h
new file mode 100644
index 0000000..3f7afb0
--- /dev/null
+++ b/include/linux/unix_diag.h
@@ -0,0 +1,45 @@
+#ifndef __UNIX_DIAG_H__
+#define __UNIX_DIAG_H__
+
+struct unix_diag_req {
+	__u8	sdiag_family;
+	__u8	sdiag_protocol;
+	__u16	pad;
+	__u32	udiag_states;
+	__u32	udiag_ino;
+	__u32	udiag_show;
+	__u32	udiag_cookie[2];
+};
+
+#define UDIAG_SHOW_NAME		0x00000001	/* show name (not path) */
+#define UDIAG_SHOW_VFS		0x00000002	/* show VFS inode info */
+#define UDIAG_SHOW_PEER		0x00000004	/* show peer socket info */
+#define UDIAG_SHOW_ICONS	0x00000008	/* show pending connections */
+#define UDIAG_SHOW_RQLEN	0x00000010	/* show skb receive queue len */
+
+struct unix_diag_msg {
+	__u8	udiag_family;
+	__u8	udiag_type;
+	__u8	udiag_state;
+	__u8	pad;
+
+	__u32	udiag_ino;
+	__u32	udiag_cookie[2];
+};
+
+enum {
+	UNIX_DIAG_NAME,
+	UNIX_DIAG_VFS,
+	UNIX_DIAG_PEER,
+	UNIX_DIAG_ICONS,
+	UNIX_DIAG_RQLEN,
+
+	UNIX_DIAG_MAX,
+};
+
+struct unix_diag_vfs {
+	__u32	udiag_vfs_ino;
+	__u32	udiag_vfs_dev;
+};
+
+#endif
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index add4790..5206d65 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -85,6 +85,8 @@
  * @reset: reset the device
  *	vdev: the virtio device
  *	After this, status and feature negotiation must be done again
+ *	Device must not be reset from its vq/config callbacks, or in
+ *	parallel with being added/removed.
  * @find_vqs: find virtqueues and instantiate them.
  *	vdev: the virtio_device
  *	nvqs: the number of virtqueues to find
@@ -100,6 +102,10 @@
  *	vdev: the virtio_device
  *	This gives the final feature bits for the device: it can change
  *	the dev->feature bits if it wants.
+ * @bus_name: return the bus name associated with the device
+ *	vdev: the virtio_device
+ *      This returns a pointer to the bus name a la pci_name from which
+ *      the caller can then copy.
  */
 typedef void vq_callback_t(struct virtqueue *);
 struct virtio_config_ops {
@@ -117,6 +123,7 @@ struct virtio_config_ops {
 	void (*del_vqs)(struct virtio_device *);
 	u32 (*get_features)(struct virtio_device *vdev);
 	void (*finalize_features)(struct virtio_device *vdev);
+	const char *(*bus_name)(struct virtio_device *vdev);
 };
 
 /* If driver didn't advertise the feature, it will never appear. */
@@ -182,5 +189,14 @@ struct virtqueue *virtio_find_single_vq(struct virtio_device *vdev,
 		return ERR_PTR(err);
 	return vq;
 }
+
+static inline
+const char *virtio_bus_name(struct virtio_device *vdev)
+{
+	if (!vdev->config->bus_name)
+		return "virtio";
+	return vdev->config->bus_name(vdev);
+}
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_VIRTIO_CONFIG_H */
diff --git a/include/linux/virtio_mmio.h b/include/linux/virtio_mmio.h
index 27c7ede..5c7b6f0 100644
--- a/include/linux/virtio_mmio.h
+++ b/include/linux/virtio_mmio.h
@@ -63,7 +63,7 @@
 #define VIRTIO_MMIO_GUEST_FEATURES	0x020
 
 /* Activated features set selector - Write Only */
-#define VIRTIO_MMIO_GUEST_FEATURES_SET	0x024
+#define VIRTIO_MMIO_GUEST_FEATURES_SEL	0x024
 
 /* Guest's memory page size in bytes - Write Only */
 #define VIRTIO_MMIO_GUEST_PAGE_SIZE	0x028
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 687fb11..4bde182 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -119,7 +119,7 @@ unmap_kernel_range(unsigned long addr, unsigned long size)
 #endif
 
 /* Allocate/destroy a 'vmalloc' VM area. */
-extern struct vm_struct *alloc_vm_area(size_t size);
+extern struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes);
 extern void free_vm_area(struct vm_struct *area);
 
 /* for /dev/kmem */
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 91ab5b0..63b1781 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -11,10 +11,13 @@ extern void unix_notinflight(struct file *fp);
 extern void unix_gc(void);
 extern void wait_for_unix_gc(void);
 extern struct sock *unix_get_socket(struct file *filp);
+extern struct sock *unix_peer_get(struct sock *);
 
 #define UNIX_HASH_SIZE	256
 
 extern unsigned int unix_tot_inflight;
+extern spinlock_t unix_table_lock;
+extern struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
 
 struct unix_address {
 	atomic_t	refcnt;
diff --git a/include/net/atmclip.h b/include/net/atmclip.h
index 497ef64..5865924 100644
--- a/include/net/atmclip.h
+++ b/include/net/atmclip.h
@@ -15,7 +15,6 @@
 
 
 #define CLIP_VCC(vcc) ((struct clip_vcc *) ((vcc)->user_back))
-#define NEIGH2ENTRY(neigh) ((struct atmarp_entry *) (neigh)->primary_key)
 
 struct sk_buff;
 
@@ -36,24 +35,18 @@ struct clip_vcc {
 
 
 struct atmarp_entry {
-	__be32		ip;		/* IP address */
 	struct clip_vcc	*vccs;		/* active VCCs; NULL if resolution is
 					   pending */
 	unsigned long	expires;	/* entry expiration time */
 	struct neighbour *neigh;	/* neighbour back-pointer */
 };
 
-
 #define PRIV(dev) ((struct clip_priv *) netdev_priv(dev))
 
-
 struct clip_priv {
 	int number;			/* for convenience ... */
 	spinlock_t xoff_lock;		/* ensures that pop is atomic (SMP) */
 	struct net_device *next;	/* next CLIP interface */
 };
 
-
-extern struct neigh_table *clip_tbl_hook;
-
 #endif
diff --git a/include/net/caif/caif_dev.h b/include/net/caif/caif_dev.h
index c011281..ef2dd94 100644
--- a/include/net/caif/caif_dev.h
+++ b/include/net/caif/caif_dev.h
@@ -9,6 +9,7 @@
 
 #include <net/caif/caif_layer.h>
 #include <net/caif/cfcnfg.h>
+#include <net/caif/caif_device.h>
 #include <linux/caif/caif_socket.h>
 #include <linux/if.h>
 #include <linux/net.h>
@@ -104,4 +105,24 @@ void caif_client_register_refcnt(struct cflayer *adapt_layer,
  */
 void caif_free_client(struct cflayer *adap_layer);
 
+/**
+ * struct caif_enroll_dev - Enroll a net-device as a CAIF Link layer
+ * @dev:		Network device to enroll.
+ * @caifdev:		Configuration information from CAIF Link Layer
+ * @link_support:	Link layer support layer
+ * @head_room:		Head room needed by link support layer
+ * @layer:		Lowest layer in CAIF stack
+ * @rcv_fun:		Receive function for CAIF stack.
+ *
+ * This function enroll a CAIF link layer into CAIF Stack and
+ * expects the interface to be able to handle CAIF payload.
+ * The link_support layer is used to add any Link Layer specific
+ * framing.
+ */
+void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
+			struct cflayer *link_support, int head_room,
+			struct cflayer **layer, int (**rcv_func)(
+				struct sk_buff *, struct net_device *,
+				struct packet_type *, struct net_device *));
+
 #endif /* CAIF_DEV_H_ */
diff --git a/include/net/caif/caif_layer.h b/include/net/caif/caif_layer.h
index 35bc788..0f3a391 100644
--- a/include/net/caif/caif_layer.h
+++ b/include/net/caif/caif_layer.h
@@ -121,9 +121,7 @@ enum caif_direction {
  * @transmit:	Packet transmit funciton.
  * @ctrlcmd:	Used for control signalling upwards in the stack.
  * @modemcmd:	Used for control signaling downwards in the stack.
- * @prio:	Priority of this layer.
  * @id:		The identity of this layer
- * @type:	The type of this layer
  * @name:	Name of the layer.
  *
  *  This structure defines the layered structure in CAIF.
@@ -230,9 +228,7 @@ struct cflayer {
 	 */
 	int (*modemcmd) (struct cflayer *layr, enum caif_modemcmd ctrl);
 
-	unsigned short prio;
 	unsigned int id;
-	unsigned int type;
 	char name[CAIF_LAYER_NAME_SZ];
 };
 
diff --git a/include/net/caif/caif_spi.h b/include/net/caif/caif_spi.h
index 87c3d11..aa6a485 100644
--- a/include/net/caif/caif_spi.h
+++ b/include/net/caif/caif_spi.h
@@ -55,8 +55,8 @@
 struct cfspi_xfer {
 	u16 tx_dma_len;
 	u16 rx_dma_len;
-	void *va_tx;
-	dma_addr_t pa_tx;
+	void *va_tx[2];
+	dma_addr_t pa_tx[2];
 	void *va_rx;
 	dma_addr_t pa_rx;
 };
diff --git a/include/net/caif/cfcnfg.h b/include/net/caif/cfcnfg.h
index 3e93a4a..90b4ff8 100644
--- a/include/net/caif/cfcnfg.h
+++ b/include/net/caif/cfcnfg.h
@@ -14,18 +14,6 @@
 struct cfcnfg;
 
 /**
- * enum cfcnfg_phy_type -  Types of physical layers defined in CAIF Stack
- *
- * @CFPHYTYPE_FRAG:	Fragmented frames physical interface.
- * @CFPHYTYPE_CAIF:	Generic CAIF physical interface
- */
-enum cfcnfg_phy_type {
-	CFPHYTYPE_FRAG = 1,
-	CFPHYTYPE_CAIF,
-	CFPHYTYPE_MAX
-};
-
-/**
  * enum cfcnfg_phy_preference - Physical preference HW Abstraction
  *
  * @CFPHYPREF_UNSPECIFIED:	Default physical interface
@@ -66,21 +54,20 @@ void cfcnfg_remove(struct cfcnfg *cfg);
  * cfcnfg_add_phy_layer() - Adds a physical layer to the CAIF stack.
  * @cnfg:	Pointer to a CAIF configuration object, created by
  *		cfcnfg_create().
- * @phy_type:	Specifies the type of physical interface, e.g.
- *			CFPHYTYPE_FRAG.
  * @dev:	Pointer to link layer device
  * @phy_layer:	Specify the physical layer. The transmit function
  *		MUST be set in the structure.
  * @pref:	The phy (link layer) preference.
+ * @link_support: Protocol implementation for link layer specific protocol.
  * @fcs:	Specify if checksum is used in CAIF Framing Layer.
- * @stx:	Specify if Start Of Frame eXtention is used.
+ * @head_room:	Head space needed by link specific protocol.
  */
-
 void
-cfcnfg_add_phy_layer(struct cfcnfg *cnfg, enum cfcnfg_phy_type phy_type,
+cfcnfg_add_phy_layer(struct cfcnfg *cnfg,
 		     struct net_device *dev, struct cflayer *phy_layer,
 		     enum cfcnfg_phy_preference pref,
-		     bool fcs, bool stx);
+		     struct cflayer *link_support,
+		     bool fcs, int head_room);
 
 /**
  * cfcnfg_del_phy_layer - Deletes an phy layer from the CAIF stack.
diff --git a/include/net/caif/cfserl.h b/include/net/caif/cfserl.h
index b837432..f121299 100644
--- a/include/net/caif/cfserl.h
+++ b/include/net/caif/cfserl.h
@@ -8,5 +8,5 @@
 #define CFSERL_H_
 #include <net/caif/caif_layer.h>
 
-struct cflayer *cfserl_create(int type, int instance, bool use_stx);
-#endif				/* CFSERL_H_ */
+struct cflayer *cfserl_create(int instance, bool use_stx);
+#endif
diff --git a/include/net/dsa.h b/include/net/dsa.h
index 839f768..7828ebf 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -11,6 +11,11 @@
 #ifndef __LINUX_NET_DSA_H
 #define __LINUX_NET_DSA_H
 
+#include <linux/if_ether.h>
+#include <linux/list.h>
+#include <linux/timer.h>
+#include <linux/workqueue.h>
+
 #define DSA_MAX_SWITCHES	4
 #define DSA_MAX_PORTS		12
 
@@ -54,8 +59,143 @@ struct dsa_platform_data {
 	struct dsa_chip_data	*chip;
 };
 
-extern bool dsa_uses_dsa_tags(void *dsa_ptr);
-extern bool dsa_uses_trailer_tags(void *dsa_ptr);
+struct dsa_switch_tree {
+	/*
+	 * Configuration data for the platform device that owns
+	 * this dsa switch tree instance.
+	 */
+	struct dsa_platform_data	*pd;
+
+	/*
+	 * Reference to network device to use, and which tagging
+	 * protocol to use.
+	 */
+	struct net_device	*master_netdev;
+	__be16			tag_protocol;
+
+	/*
+	 * The switch and port to which the CPU is attached.
+	 */
+	s8			cpu_switch;
+	s8			cpu_port;
+
+	/*
+	 * Link state polling.
+	 */
+	int			link_poll_needed;
+	struct work_struct	link_poll_work;
+	struct timer_list	link_poll_timer;
+
+	/*
+	 * Data for the individual switch chips.
+	 */
+	struct dsa_switch	*ds[DSA_MAX_SWITCHES];
+};
+
+struct dsa_switch {
+	/*
+	 * Parent switch tree, and switch index.
+	 */
+	struct dsa_switch_tree	*dst;
+	int			index;
+
+	/*
+	 * Configuration data for this switch.
+	 */
+	struct dsa_chip_data	*pd;
+
+	/*
+	 * The used switch driver.
+	 */
+	struct dsa_switch_driver	*drv;
+
+	/*
+	 * Reference to mii bus to use.
+	 */
+	struct mii_bus		*master_mii_bus;
+
+	/*
+	 * Slave mii_bus and devices for the individual ports.
+	 */
+	u32			dsa_port_mask;
+	u32			phys_port_mask;
+	struct mii_bus		*slave_mii_bus;
+	struct net_device	*ports[DSA_MAX_PORTS];
+};
+
+static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p)
+{
+	return !!(ds->index == ds->dst->cpu_switch && p == ds->dst->cpu_port);
+}
+
+static inline u8 dsa_upstream_port(struct dsa_switch *ds)
+{
+	struct dsa_switch_tree *dst = ds->dst;
+
+	/*
+	 * If this is the root switch (i.e. the switch that connects
+	 * to the CPU), return the cpu port number on this switch.
+	 * Else return the (DSA) port number that connects to the
+	 * switch that is one hop closer to the cpu.
+	 */
+	if (dst->cpu_switch == ds->index)
+		return dst->cpu_port;
+	else
+		return ds->pd->rtable[dst->cpu_switch];
+}
+
+struct dsa_switch_driver {
+	struct list_head	list;
+
+	__be16			tag_protocol;
+	int			priv_size;
+
+	/*
+	 * Probing and setup.
+	 */
+	char	*(*probe)(struct mii_bus *bus, int sw_addr);
+	int	(*setup)(struct dsa_switch *ds);
+	int	(*set_addr)(struct dsa_switch *ds, u8 *addr);
+
+	/*
+	 * Access to the switch's PHY registers.
+	 */
+	int	(*phy_read)(struct dsa_switch *ds, int port, int regnum);
+	int	(*phy_write)(struct dsa_switch *ds, int port,
+			     int regnum, u16 val);
+
+	/*
+	 * Link state polling and IRQ handling.
+	 */
+	void	(*poll_link)(struct dsa_switch *ds);
+
+	/*
+	 * ethtool hardware statistics.
+	 */
+	void	(*get_strings)(struct dsa_switch *ds, int port, uint8_t *data);
+	void	(*get_ethtool_stats)(struct dsa_switch *ds,
+				     int port, uint64_t *data);
+	int	(*get_sset_count)(struct dsa_switch *ds);
+};
+
+void register_switch_driver(struct dsa_switch_driver *type);
+void unregister_switch_driver(struct dsa_switch_driver *type);
+
+/*
+ * The original DSA tag format and some other tag formats have no
+ * ethertype, which means that we need to add a little hack to the
+ * networking receive path to make sure that received frames get
+ * the right ->protocol assigned to them when one of those tag
+ * formats is in use.
+ */
+static inline bool dsa_uses_dsa_tags(struct dsa_switch_tree *dst)
+{
+	return !!(dst->tag_protocol == htons(ETH_P_DSA));
+}
 
+static inline bool dsa_uses_trailer_tags(struct dsa_switch_tree *dst)
+{
+	return !!(dst->tag_protocol == htons(ETH_P_TRAILER));
+}
 
 #endif
diff --git a/include/net/dst.h b/include/net/dst.h
index 4fb6c43..01343b0 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -86,12 +86,12 @@ struct dst_entry {
 	};
 };
 
-static inline struct neighbour *dst_get_neighbour(struct dst_entry *dst)
+static inline struct neighbour *dst_get_neighbour_noref(struct dst_entry *dst)
 {
 	return rcu_dereference(dst->_neighbour);
 }
 
-static inline struct neighbour *dst_get_neighbour_raw(struct dst_entry *dst)
+static inline struct neighbour *dst_get_neighbour_noref_raw(struct dst_entry *dst)
 {
 	return rcu_dereference_raw(dst->_neighbour);
 }
@@ -205,12 +205,7 @@ dst_feature(const struct dst_entry *dst, u32 feature)
 
 static inline u32 dst_mtu(const struct dst_entry *dst)
 {
-	u32 mtu = dst_metric_raw(dst, RTAX_MTU);
-
-	if (!mtu)
-		mtu = dst->ops->default_mtu(dst);
-
-	return mtu;
+	return dst->ops->mtu(dst);
 }
 
 /* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */
@@ -397,7 +392,7 @@ static inline void dst_confirm(struct dst_entry *dst)
 		struct neighbour *n;
 
 		rcu_read_lock();
-		n = dst_get_neighbour(dst);
+		n = dst_get_neighbour_noref(dst);
 		neigh_confirm(n);
 		rcu_read_unlock();
 	}
diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h
index 9adb998..e1c2ee0 100644
--- a/include/net/dst_ops.h
+++ b/include/net/dst_ops.h
@@ -17,7 +17,7 @@ struct dst_ops {
 	int			(*gc)(struct dst_ops *ops);
 	struct dst_entry *	(*check)(struct dst_entry *, __u32 cookie);
 	unsigned int		(*default_advmss)(const struct dst_entry *);
-	unsigned int		(*default_mtu)(const struct dst_entry *);
+	unsigned int		(*mtu)(const struct dst_entry *);
 	u32 *			(*cow_metrics)(struct dst_entry *, unsigned long);
 	void			(*destroy)(struct dst_entry *);
 	void			(*ifdown)(struct dst_entry *,
diff --git a/include/net/flow.h b/include/net/flow.h
index a094477..9192d69 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -59,8 +59,11 @@ struct flowi4 {
 #define flowi4_proto		__fl_common.flowic_proto
 #define flowi4_flags		__fl_common.flowic_flags
 #define flowi4_secid		__fl_common.flowic_secid
-	__be32			daddr;
+
+	/* (saddr,daddr) must be grouped, same order as in IP header */
 	__be32			saddr;
+	__be32			daddr;
+
 	union flowi_uli		uli;
 #define fl4_sport		uli.ports.sport
 #define fl4_dport		uli.ports.dport
diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h
new file mode 100644
index 0000000..80461c1
--- /dev/null
+++ b/include/net/flow_keys.h
@@ -0,0 +1,16 @@
+#ifndef _NET_FLOW_KEYS_H
+#define _NET_FLOW_KEYS_H
+
+struct flow_keys {
+	/* (src,dst) must be grouped, in the same way than in IP header */
+	__be32 src;
+	__be32 dst;
+	union {
+		__be32 ports;
+		__be16 port16[2];
+	};
+	u8 ip_proto;
+};
+
+extern bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow);
+#endif
diff --git a/include/net/genetlink.h b/include/net/genetlink.h
index 82d8d09..7db3299 100644
--- a/include/net/genetlink.h
+++ b/include/net/genetlink.h
@@ -128,6 +128,8 @@ extern int genl_register_mc_group(struct genl_family *family,
 				  struct genl_multicast_group *grp);
 extern void genl_unregister_mc_group(struct genl_family *family,
 				     struct genl_multicast_group *grp);
+extern void genl_notify(struct sk_buff *skb, struct net *net, u32 pid,
+			u32 group, struct nlmsghdr *nlh, gfp_t flags);
 
 /**
  * genlmsg_put - Add generic netlink header to netlink message
diff --git a/include/net/icmp.h b/include/net/icmp.h
index f0698b9..75d6156 100644
--- a/include/net/icmp.h
+++ b/include/net/icmp.h
@@ -31,8 +31,8 @@ struct icmp_err {
 extern const struct icmp_err icmp_err_convert[];
 #define ICMP_INC_STATS(net, field)	SNMP_INC_STATS((net)->mib.icmp_statistics, field)
 #define ICMP_INC_STATS_BH(net, field)	SNMP_INC_STATS_BH((net)->mib.icmp_statistics, field)
-#define ICMPMSGOUT_INC_STATS(net, field)	SNMP_INC_STATS((net)->mib.icmpmsg_statistics, field+256)
-#define ICMPMSGIN_INC_STATS_BH(net, field)	SNMP_INC_STATS_BH((net)->mib.icmpmsg_statistics, field)
+#define ICMPMSGOUT_INC_STATS(net, field)	SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field+256)
+#define ICMPMSGIN_INC_STATS_BH(net, field)	SNMP_INC_STATS_ATOMIC_LONG((net)->mib.icmpmsg_statistics, field)
 
 struct dst_entry;
 struct net_proto_family;
diff --git a/include/net/ieee802154.h b/include/net/ieee802154.h
index d52685d..ee59f8b 100644
--- a/include/net/ieee802154.h
+++ b/include/net/ieee802154.h
@@ -21,11 +21,14 @@
  * Maxim Gorbachyov <maxim.gorbachev@siemens.com>
  * Maxim Osipov <maxim.osipov@siemens.com>
  * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
+ * Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
  */
 
 #ifndef NET_IEEE802154_H
 #define NET_IEEE802154_H
 
+#define IEEE802154_MTU			127
+
 #define IEEE802154_FC_TYPE_BEACON	0x0	/* Frame is beacon */
 #define	IEEE802154_FC_TYPE_DATA		0x1	/* Frame is data */
 #define IEEE802154_FC_TYPE_ACK		0x2	/* Frame is acknowledgment */
@@ -56,6 +59,9 @@
 	(((x) & IEEE802154_FC_DAMODE_MASK) >> IEEE802154_FC_DAMODE_SHIFT)
 
 
+/* MAC footer size */
+#define IEEE802154_MFR_SIZE	2 /* 2 octets */
+
 /* MAC's Command Frames Identifiers */
 #define IEEE802154_CMD_ASSOCIATION_REQ		0x01
 #define IEEE802154_CMD_ASSOCIATION_RESP		0x02
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index e46674d..00cbb43 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -15,7 +15,7 @@
 #define _INET6_HASHTABLES_H
 
 
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 #include <linux/in6.h>
 #include <linux/ipv6.h>
 #include <linux/types.h>
@@ -110,5 +110,5 @@ extern struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo
 				 const struct in6_addr *saddr, const __be16 sport,
 				 const struct in6_addr *daddr, const __be16 dport,
 				 const int dif);
-#endif /* defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) */
+#endif /* IS_ENABLED(CONFIG_IPV6) */
 #endif /* _INET6_HASHTABLES_H */
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index e6db62e..dbf9aab 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -143,9 +143,9 @@ static inline void *inet_csk_ca(const struct sock *sk)
 	return (void *)inet_csk(sk)->icsk_ca_priv;
 }
 
-extern struct sock *inet_csk_clone(struct sock *sk,
-				   const struct request_sock *req,
-				   const gfp_t priority);
+extern struct sock *inet_csk_clone_lock(const struct sock *sk,
+					const struct request_sock *req,
+					const gfp_t priority);
 
 enum inet_csk_ack_state_t {
 	ICSK_ACK_SCHED	= 1,
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index b897d6e..e3e4051 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -31,6 +31,7 @@
 /** struct ip_options - IP Options
  *
  * @faddr - Saved first hop address
+ * @nexthop - Saved nexthop address in LSRR and SSRR
  * @is_data - Options in __data, rather than skb
  * @is_strictroute - Strict source route
  * @srr_is_hit - Packet destination addr was our one
@@ -41,6 +42,7 @@
  */
 struct ip_options {
 	__be32		faddr;
+	__be32		nexthop;
 	unsigned char	optlen;
 	unsigned char	srr;
 	unsigned char	rr;
@@ -69,7 +71,7 @@ struct ip_options_data {
 
 struct inet_request_sock {
 	struct request_sock	req;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	u16			inet6_rsk_offset;
 #endif
 	__be16			loc_port;
@@ -137,7 +139,7 @@ struct rtable;
 struct inet_sock {
 	/* sk and pinet6 has to be the first two members of inet_sock */
 	struct sock		sk;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct ipv6_pinfo	*pinet6;
 #endif
 	/* Socket demultiplex comparisons on incoming packets. */
@@ -186,7 +188,7 @@ static inline void __inet_sk_copy_descendant(struct sock *sk_to,
 	memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1,
 	       sk_from->sk_prot->obj_size - ancestor_size);
 }
-#if !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE))
+#if !(IS_ENABLED(CONFIG_IPV6))
 static inline void inet_sk_copy_descendant(struct sock *sk_to,
 					   const struct sock *sk_from)
 {
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index e8c25b9..ba52c83 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -218,20 +218,12 @@ extern void inet_twsk_purge(struct inet_hashinfo *hashinfo,
 static inline
 struct net *twsk_net(const struct inet_timewait_sock *twsk)
 {
-#ifdef CONFIG_NET_NS
-	return rcu_dereference_raw(twsk->tw_net); /* protected by locking, */
-						  /* reference counting, */
-						  /* initialization, or RCU. */
-#else
-	return &init_net;
-#endif
+	return read_pnet(&twsk->tw_net);
 }
 
 static inline
 void twsk_net_set(struct inet_timewait_sock *twsk, struct net *net)
 {
-#ifdef CONFIG_NET_NS
-	rcu_assign_pointer(twsk->tw_net, net);
-#endif
+	write_pnet(&twsk->tw_net, net);
 }
 #endif	/* _INET_TIMEWAIT_SOCK_ */
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 78c83e6..06b795d 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -35,6 +35,7 @@ struct inet_peer {
 
 	u32			metrics[RTAX_MAX];
 	u32			rate_tokens;	/* rate limiting for ICMP */
+	int			redirect_genid;
 	unsigned long		rate_last;
 	unsigned long		pmtu_expires;
 	u32			pmtu_orig;
@@ -86,7 +87,7 @@ static inline struct inet_peer *inet_getpeer_v6(const struct in6_addr *v6daddr,
 {
 	struct inetpeer_addr daddr;
 
-	ipv6_addr_copy((struct in6_addr *)daddr.addr.a6, v6daddr);
+	*(struct in6_addr *)daddr.addr.a6 = *v6daddr;
 	daddr.family = AF_INET6;
 	return inet_getpeer(&daddr, create);
 }
diff --git a/include/net/ip.h b/include/net/ip.h
index eca0ef7..775009f 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -353,14 +353,14 @@ static inline void ip_ipgre_mc_map(__be32 naddr, const unsigned char *broadcast,
 		memcpy(buf, &naddr, sizeof(naddr));
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 #include <linux/ipv6.h>
 #endif
 
 static __inline__ void inet_reset_saddr(struct sock *sk)
 {
 	inet_sk(sk)->inet_rcv_saddr = inet_sk(sk)->inet_saddr = 0;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	if (sk->sk_family == PF_INET6) {
 		struct ipv6_pinfo *np = inet6_sk(sk);
 
@@ -379,7 +379,7 @@ static inline int sk_mc_loop(struct sock *sk)
 	switch (sk->sk_family) {
 	case AF_INET:
 		return inet_sk(sk)->mc_loop;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		return inet6_sk(sk)->mc_loop;
 #endif
@@ -450,7 +450,7 @@ extern int ip_options_rcv_srr(struct sk_buff *skb);
  *	Functions provided by ip_sockglue.c
  */
 
-extern int	ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+extern void	ipv4_pktinfo_prepare(struct sk_buff *skb);
 extern void	ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb);
 extern int	ip_cmsg_send(struct net *net,
 			     struct msghdr *msg, struct ipcm_cookie *ipc);
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
index 5e91b72..789d5f4 100644
--- a/include/net/ip6_route.h
+++ b/include/net/ip6_route.h
@@ -95,14 +95,14 @@ extern struct rt6_info		*rt6_lookup(struct net *net,
 
 extern struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 					 struct neighbour *neigh,
-					 const struct in6_addr *addr);
+					 struct flowi6 *fl6);
 extern int icmp6_dst_gc(void);
 
 extern void fib6_force_start_gc(struct net *net);
 
 extern struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 					   const struct in6_addr *addr,
-					   int anycast);
+					   bool anycast);
 
 extern int			ip6_dst_hoplimit(struct dst_entry *dst);
 
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 873d5be..48fd12e 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -21,7 +21,7 @@
 #include <linux/netfilter.h>		/* for union nf_inet_addr */
 #include <linux/ip.h>
 #include <linux/ipv6.h>			/* for struct ipv6hdr */
-#include <net/ipv6.h>			/* for ipv6_addr_copy */
+#include <net/ipv6.h>
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 #include <net/netfilter/nf_conntrack.h>
 #endif
@@ -119,8 +119,8 @@ ip_vs_fill_iphdr(int af, const void *nh, struct ip_vs_iphdr *iphdr)
 		const struct ipv6hdr *iph = nh;
 		iphdr->len = sizeof(struct ipv6hdr);
 		iphdr->protocol = iph->nexthdr;
-		ipv6_addr_copy(&iphdr->saddr.in6, &iph->saddr);
-		ipv6_addr_copy(&iphdr->daddr.in6, &iph->daddr);
+		iphdr->saddr.in6 = iph->saddr;
+		iphdr->daddr.in6 = iph->daddr;
 	} else
 #endif
 	{
@@ -137,7 +137,7 @@ static inline void ip_vs_addr_copy(int af, union nf_inet_addr *dst,
 {
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6)
-		ipv6_addr_copy(&dst->in6, &src->in6);
+		dst->in6 = src->in6;
 	else
 #endif
 	dst->ip = src->ip;
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index a366a8a..e4170a2 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -132,6 +132,15 @@ extern struct ctl_path net_ipv6_ctl_path[];
 	SNMP_INC_STATS##modifier((net)->mib.statname##_statistics, (field));\
 })
 
+/* per device and per net counters are atomic_long_t */
+#define _DEVINC_ATOMIC_ATOMIC(net, statname, idev, field)		\
+({									\
+	struct inet6_dev *_idev = (idev);				\
+	if (likely(_idev != NULL))					\
+		SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \
+	SNMP_INC_STATS_ATOMIC_LONG((net)->mib.statname##_statistics, (field));\
+})
+
 #define _DEVADD(net, statname, modifier, idev, field, val)		\
 ({									\
 	struct inet6_dev *_idev = (idev);				\
@@ -168,11 +177,11 @@ extern struct ctl_path net_ipv6_ctl_path[];
 		_DEVINCATOMIC(net, icmpv6, _BH, idev, field)
 
 #define ICMP6MSGOUT_INC_STATS(net, idev, field)		\
-	_DEVINCATOMIC(net, icmpv6msg, , idev, field +256)
+	_DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field +256)
 #define ICMP6MSGOUT_INC_STATS_BH(net, idev, field)	\
-	_DEVINCATOMIC(net, icmpv6msg, _BH, idev, field +256)
+	_DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field +256)
 #define ICMP6MSGIN_INC_STATS_BH(net, idev, field)	\
-	_DEVINCATOMIC(net, icmpv6msg, _BH, idev, field)
+	_DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field)
 
 struct ip6_ra_chain {
 	struct ip6_ra_chain	*next;
@@ -300,11 +309,6 @@ ipv6_masked_addr_cmp(const struct in6_addr *a1, const struct in6_addr *m,
 		  ((a1->s6_addr32[3] ^ a2->s6_addr32[3]) & m->s6_addr32[3]));
 }
 
-static inline void ipv6_addr_copy(struct in6_addr *a1, const struct in6_addr *a2)
-{
-	memcpy(a1, a2, sizeof(struct in6_addr));
-}
-
 static inline void ipv6_addr_prefix(struct in6_addr *pfx, 
 				    const struct in6_addr *addr,
 				    int plen)
@@ -554,7 +558,7 @@ extern void			ipv6_push_frag_opts(struct sk_buff *skb,
 						    u8 *proto);
 
 extern int			ipv6_skip_exthdr(const struct sk_buff *, int start,
-					         u8 *nexthdrp);
+					         u8 *nexthdrp, __be16 *frag_offp);
 
 extern int 			ipv6_ext_hdr(u8 nexthdr);
 
diff --git a/include/net/ndisc.h b/include/net/ndisc.h
index 62beeb9..c977c37 100644
--- a/include/net/ndisc.h
+++ b/include/net/ndisc.h
@@ -145,13 +145,4 @@ int ndisc_ifinfo_sysctl_strategy(ctl_table *ctl,
 extern void 			inet6_ifinfo_notify(int event,
 						    struct inet6_dev *idev);
 
-static inline struct neighbour * ndisc_get_neigh(struct net_device *dev, const struct in6_addr *addr)
-{
-
-	if (dev)
-		return __neigh_lookup_errno(&nd_tbl, addr, dev);
-
-	return ERR_PTR(-ENODEV);
-}
-
 #endif
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 2720884..6814c4d 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -43,7 +43,6 @@ struct neigh_parms {
 #endif
 	struct net_device *dev;
 	struct neigh_parms *next;
-	int	(*neigh_setup)(struct neighbour *);
 	void	(*neigh_cleanup)(struct neighbour *);
 	struct neigh_table *tbl;
 
@@ -59,7 +58,7 @@ struct neigh_parms {
 	int	reachable_time;
 	int	delay_probe_time;
 
-	int	queue_len;
+	int	queue_len_bytes;
 	int	ucast_probes;
 	int	app_probes;
 	int	mcast_probes;
@@ -99,6 +98,7 @@ struct neighbour {
 	rwlock_t		lock;
 	atomic_t		refcnt;
 	struct sk_buff_head	arp_queue;
+	unsigned int		arp_queue_len_bytes;
 	struct timer_list	timer;
 	unsigned long		used;
 	atomic_t		probes;
@@ -172,12 +172,18 @@ struct neigh_table {
 	atomic_t		entries;
 	rwlock_t		lock;
 	unsigned long		last_rand;
-	struct kmem_cache	*kmem_cachep;
 	struct neigh_statistics	__percpu *stats;
 	struct neigh_hash_table __rcu *nht;
 	struct pneigh_entry	**phash_buckets;
 };
 
+#define NEIGH_PRIV_ALIGN	sizeof(long long)
+
+static inline void *neighbour_priv(const struct neighbour *n)
+{
+	return (char *)n + ALIGN(sizeof(*n) + n->tbl->key_len, NEIGH_PRIV_ALIGN);
+}
+
 /* flags for neigh_update() */
 #define NEIGH_UPDATE_F_OVERRIDE			0x00000001
 #define NEIGH_UPDATE_F_WEAK_OVERRIDE		0x00000002
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 3bb6fa0..ee547c1 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -77,7 +77,7 @@ struct net {
 	struct netns_packet	packet;
 	struct netns_unix	unx;
 	struct netns_ipv4	ipv4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct netns_ipv6	ipv6;
 #endif
 #if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE)
diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h
index 4283508..a88fb69 100644
--- a/include/net/netfilter/nf_conntrack_ecache.h
+++ b/include/net/netfilter/nf_conntrack_ecache.h
@@ -67,18 +67,18 @@ struct nf_ct_event_notifier {
 	int (*fcn)(unsigned int events, struct nf_ct_event *item);
 };
 
-extern struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
-extern int nf_conntrack_register_notifier(struct nf_ct_event_notifier *nb);
-extern void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *nb);
+extern int nf_conntrack_register_notifier(struct net *net, struct nf_ct_event_notifier *nb);
+extern void nf_conntrack_unregister_notifier(struct net *net, struct nf_ct_event_notifier *nb);
 
 extern void nf_ct_deliver_cached_events(struct nf_conn *ct);
 
 static inline void
 nf_conntrack_event_cache(enum ip_conntrack_events event, struct nf_conn *ct)
 {
+	struct net *net = nf_ct_net(ct);
 	struct nf_conntrack_ecache *e;
 
-	if (nf_conntrack_event_cb == NULL)
+	if (net->ct.nf_conntrack_event_cb == NULL)
 		return;
 
 	e = nf_ct_ecache_find(ct);
@@ -95,11 +95,12 @@ nf_conntrack_eventmask_report(unsigned int eventmask,
 			      int report)
 {
 	int ret = 0;
+	struct net *net = nf_ct_net(ct);
 	struct nf_ct_event_notifier *notify;
 	struct nf_conntrack_ecache *e;
 
 	rcu_read_lock();
-	notify = rcu_dereference(nf_conntrack_event_cb);
+	notify = rcu_dereference(net->ct.nf_conntrack_event_cb);
 	if (notify == NULL)
 		goto out_unlock;
 
@@ -164,9 +165,8 @@ struct nf_exp_event_notifier {
 	int (*fcn)(unsigned int events, struct nf_exp_event *item);
 };
 
-extern struct nf_exp_event_notifier __rcu *nf_expect_event_cb;
-extern int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *nb);
-extern void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *nb);
+extern int nf_ct_expect_register_notifier(struct net *net, struct nf_exp_event_notifier *nb);
+extern void nf_ct_expect_unregister_notifier(struct net *net, struct nf_exp_event_notifier *nb);
 
 static inline void
 nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
@@ -174,11 +174,12 @@ nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
 			  u32 pid,
 			  int report)
 {
+	struct net *net = nf_ct_exp_net(exp);
 	struct nf_exp_event_notifier *notify;
 	struct nf_conntrack_ecache *e;
 
 	rcu_read_lock();
-	notify = rcu_dereference(nf_expect_event_cb);
+	notify = rcu_dereference(net->ct.nf_expect_event_cb);
 	if (notify == NULL)
 		goto out_unlock;
 
diff --git a/include/net/netfilter/nf_tproxy_core.h b/include/net/netfilter/nf_tproxy_core.h
index e505358..75ca929 100644
--- a/include/net/netfilter/nf_tproxy_core.h
+++ b/include/net/netfilter/nf_tproxy_core.h
@@ -131,7 +131,7 @@ nf_tproxy_get_sock_v4(struct net *net, const u8 protocol,
 	return sk;
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static inline struct sock *
 nf_tproxy_get_sock_v6(struct net *net, const u8 protocol,
 		      const struct in6_addr *saddr, const struct in6_addr *daddr,
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 0249399..7a911ec 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -18,6 +18,8 @@ struct netns_ct {
 	struct hlist_nulls_head	unconfirmed;
 	struct hlist_nulls_head	dying;
 	struct ip_conntrack_stat __percpu *stat;
+	struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb;
+	struct nf_exp_event_notifier __rcu *nf_expect_event_cb;
 	int			sysctl_events;
 	unsigned int		sysctl_events_retry_timeout;
 	int			sysctl_acct;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index d786b4f..bbd023a 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -55,6 +55,7 @@ struct netns_ipv4 {
 	int current_rt_cache_rebuild_count;
 
 	unsigned int sysctl_ping_group_range[2];
+	long sysctl_tcp_mem[3];
 
 	atomic_t rt_genid;
 	atomic_t dev_addr_genid;
diff --git a/include/net/netns/mib.h b/include/net/netns/mib.h
index 0b44112..d542a4b 100644
--- a/include/net/netns/mib.h
+++ b/include/net/netns/mib.h
@@ -10,15 +10,15 @@ struct netns_mib {
 	DEFINE_SNMP_STAT(struct udp_mib, udp_statistics);
 	DEFINE_SNMP_STAT(struct udp_mib, udplite_statistics);
 	DEFINE_SNMP_STAT(struct icmp_mib, icmp_statistics);
-	DEFINE_SNMP_STAT(struct icmpmsg_mib, icmpmsg_statistics);
+	DEFINE_SNMP_STAT_ATOMIC(struct icmpmsg_mib, icmpmsg_statistics);
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct proc_dir_entry *proc_net_devsnmp6;
 	DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6);
 	DEFINE_SNMP_STAT(struct udp_mib, udplite_stats_in6);
 	DEFINE_SNMP_STAT(struct ipstats_mib, ipv6_statistics);
 	DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics);
-	DEFINE_SNMP_STAT(struct icmpv6msg_mib, icmpv6msg_statistics);
+	DEFINE_SNMP_STAT_ATOMIC(struct icmpv6msg_mib, icmpv6msg_statistics);
 #endif
 #ifdef CONFIG_XFRM_STATISTICS
 	DEFINE_SNMP_STAT(struct linux_xfrm_mib, xfrm_statistics);
diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h
index 748f91f..5299e69 100644
--- a/include/net/netns/xfrm.h
+++ b/include/net/netns/xfrm.h
@@ -56,7 +56,7 @@ struct netns_xfrm {
 #endif
 
 	struct dst_ops		xfrm4_dst_ops;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct dst_ops		xfrm6_dst_ops;
 #endif
 };
diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h
new file mode 100644
index 0000000..e503b87
--- /dev/null
+++ b/include/net/netprio_cgroup.h
@@ -0,0 +1,57 @@
+/*
+ * netprio_cgroup.h			Control Group Priority set
+ *
+ *
+ * Authors:	Neil Horman <nhorman@tuxdriver.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ *
+ */
+
+#ifndef _NETPRIO_CGROUP_H
+#define _NETPRIO_CGROUP_H
+#include <linux/module.h>
+#include <linux/cgroup.h>
+#include <linux/hardirq.h>
+#include <linux/rcupdate.h>
+
+
+struct netprio_map {
+	struct rcu_head rcu;
+	u32 priomap_len;
+	u32 priomap[];
+};
+
+#ifdef CONFIG_CGROUPS
+
+struct cgroup_netprio_state {
+	struct cgroup_subsys_state css;
+	u32 prioidx;
+};
+
+#ifndef CONFIG_NETPRIO_CGROUP
+extern int net_prio_subsys_id;
+#endif
+
+extern void sock_update_netprioidx(struct sock *sk);
+
+static inline struct cgroup_netprio_state
+		*task_netprio_state(struct task_struct *p)
+{
+#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+	return container_of(task_subsys_state(p, net_prio_subsys_id),
+			    struct cgroup_netprio_state, css);
+#else
+	return NULL;
+#endif
+}
+
+#else
+
+#define sock_update_netprioidx(sk)
+#endif
+
+#endif  /* _NET_CLS_CGROUP_H */
diff --git a/include/net/protocol.h b/include/net/protocol.h
index 6f7eb80..875f489 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -25,7 +25,7 @@
 #define _PROTOCOL_H
 
 #include <linux/in6.h>
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 #include <linux/ipv6.h>
 #endif
 
@@ -38,7 +38,7 @@ struct net_protocol {
 	void			(*err_handler)(struct sk_buff *skb, u32 info);
 	int			(*gso_send_check)(struct sk_buff *skb);
 	struct sk_buff	       *(*gso_segment)(struct sk_buff *skb,
-					       u32 features);
+					       netdev_features_t features);
 	struct sk_buff	      **(*gro_receive)(struct sk_buff **head,
 					       struct sk_buff *skb);
 	int			(*gro_complete)(struct sk_buff *skb);
@@ -46,7 +46,7 @@ struct net_protocol {
 				netns_ok:1;
 };
 
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 struct inet6_protocol {
 	int	(*handler)(struct sk_buff *skb);
 
@@ -57,7 +57,7 @@ struct inet6_protocol {
 
 	int	(*gso_send_check)(struct sk_buff *skb);
 	struct sk_buff *(*gso_segment)(struct sk_buff *skb,
-				       u32 features);
+				       netdev_features_t features);
 	struct sk_buff **(*gro_receive)(struct sk_buff **head,
 					struct sk_buff *skb);
 	int	(*gro_complete)(struct sk_buff *skb);
@@ -91,7 +91,7 @@ struct inet_protosw {
 
 extern const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS];
 
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 extern const struct inet6_protocol __rcu *inet6_protos[MAX_INET_PROTOS];
 #endif
 
@@ -100,7 +100,7 @@ extern int	inet_del_protocol(const struct net_protocol *prot, unsigned char num)
 extern void	inet_register_protosw(struct inet_protosw *p);
 extern void	inet_unregister_protosw(struct inet_protosw *p);
 
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 extern int	inet6_add_protocol(const struct inet6_protocol *prot, unsigned char num);
 extern int	inet6_del_protocol(const struct inet6_protocol *prot, unsigned char num);
 extern int	inet6_register_protosw(struct inet_protosw *p);
diff --git a/include/net/red.h b/include/net/red.h
index 3319f16..ef715a1 100644
--- a/include/net/red.h
+++ b/include/net/red.h
@@ -5,6 +5,7 @@
 #include <net/pkt_sched.h>
 #include <net/inet_ecn.h>
 #include <net/dsfield.h>
+#include <linux/reciprocal_div.h>
 
 /*	Random Early Detection (RED) algorithm.
 	=======================================
@@ -87,6 +88,29 @@
 	etc.
  */
 
+/*
+ * Adaptative RED : An Algorithm for Increasing the Robustness of RED's AQM
+ * (Sally FLoyd, Ramakrishna Gummadi, and Scott Shenker) August 2001
+ *
+ * Every 500 ms:
+ *  if (avg > target and max_p <= 0.5)
+ *   increase max_p : max_p += alpha;
+ *  else if (avg < target and max_p >= 0.01)
+ *   decrease max_p : max_p *= beta;
+ *
+ * target :[qth_min + 0.4*(qth_min - qth_max),
+ *          qth_min + 0.6*(qth_min - qth_max)].
+ * alpha : min(0.01, max_p / 4)
+ * beta : 0.9
+ * max_P is a Q0.32 fixed point number (with 32 bits mantissa)
+ * max_P between 0.01 and 0.5 (1% - 50%) [ Its no longer a negative power of two ]
+ */
+#define RED_ONE_PERCENT ((u32)DIV_ROUND_CLOSEST(1ULL<<32, 100))
+
+#define MAX_P_MIN (1 * RED_ONE_PERCENT)
+#define MAX_P_MAX (50 * RED_ONE_PERCENT)
+#define MAX_P_ALPHA(val) min(MAX_P_MIN, val / 4)
+
 #define RED_STAB_SIZE	256
 #define RED_STAB_MASK	(RED_STAB_SIZE - 1)
 
@@ -101,10 +125,14 @@ struct red_stats {
 
 struct red_parms {
 	/* Parameters */
-	u32		qth_min;	/* Min avg length threshold: A scaled */
-	u32		qth_max;	/* Max avg length threshold: A scaled */
+	u32		qth_min;	/* Min avg length threshold: Wlog scaled */
+	u32		qth_max;	/* Max avg length threshold: Wlog scaled */
 	u32		Scell_max;
-	u32		Rmask;		/* Cached random mask, see red_rmask */
+	u32		max_P;		/* probability, [0 .. 1.0] 32 scaled */
+	u32		max_P_reciprocal; /* reciprocal_value(max_P / qth_delta) */
+	u32		qth_delta;	/* max_th - min_th */
+	u32		target_min;	/* min_th + 0.4*(max_th - min_th) */
+	u32		target_max;	/* min_th + 0.6*(max_th - min_th) */
 	u8		Scell_log;
 	u8		Wlog;		/* log(W)		*/
 	u8		Plog;		/* random number bits	*/
@@ -115,19 +143,23 @@ struct red_parms {
 					   number generation */
 	u32		qR;		/* Cached random number */
 
-	unsigned long	qavg;		/* Average queue length: A scaled */
-	psched_time_t	qidlestart;	/* Start of current idle period */
+	unsigned long	qavg;		/* Average queue length: Wlog scaled */
+	ktime_t		qidlestart;	/* Start of current idle period */
 };
 
-static inline u32 red_rmask(u8 Plog)
+static inline u32 red_maxp(u8 Plog)
 {
-	return Plog < 32 ? ((1 << Plog) - 1) : ~0UL;
+	return Plog < 32 ? (~0U >> Plog) : ~0U;
 }
 
+
 static inline void red_set_parms(struct red_parms *p,
 				 u32 qth_min, u32 qth_max, u8 Wlog, u8 Plog,
-				 u8 Scell_log, u8 *stab)
+				 u8 Scell_log, u8 *stab, u32 max_P)
 {
+	int delta = qth_max - qth_min;
+	u32 max_p_delta;
+
 	/* Reset average queue length, the value is strictly bound
 	 * to the parameters below, reseting hurts a bit but leaving
 	 * it might result in an unreasonable qavg for a while. --TGR
@@ -139,26 +171,45 @@ static inline void red_set_parms(struct red_parms *p,
 	p->qth_max	= qth_max << Wlog;
 	p->Wlog		= Wlog;
 	p->Plog		= Plog;
-	p->Rmask	= red_rmask(Plog);
+	if (delta < 0)
+		delta = 1;
+	p->qth_delta	= delta;
+	if (!max_P) {
+		max_P = red_maxp(Plog);
+		max_P *= delta; /* max_P = (qth_max - qth_min)/2^Plog */
+	}
+	p->max_P = max_P;
+	max_p_delta = max_P / delta;
+	max_p_delta = max(max_p_delta, 1U);
+	p->max_P_reciprocal  = reciprocal_value(max_p_delta);
+
+	/* RED Adaptative target :
+	 * [min_th + 0.4*(min_th - max_th),
+	 *  min_th + 0.6*(min_th - max_th)].
+	 */
+	delta /= 5;
+	p->target_min = qth_min + 2*delta;
+	p->target_max = qth_min + 3*delta;
+
 	p->Scell_log	= Scell_log;
 	p->Scell_max	= (255 << Scell_log);
 
 	memcpy(p->Stab, stab, sizeof(p->Stab));
 }
 
-static inline int red_is_idling(struct red_parms *p)
+static inline int red_is_idling(const struct red_parms *p)
 {
-	return p->qidlestart != PSCHED_PASTPERFECT;
+	return p->qidlestart.tv64 != 0;
 }
 
 static inline void red_start_of_idle_period(struct red_parms *p)
 {
-	p->qidlestart = psched_get_time();
+	p->qidlestart = ktime_get();
 }
 
 static inline void red_end_of_idle_period(struct red_parms *p)
 {
-	p->qidlestart = PSCHED_PASTPERFECT;
+	p->qidlestart.tv64 = 0;
 }
 
 static inline void red_restart(struct red_parms *p)
@@ -168,15 +219,12 @@ static inline void red_restart(struct red_parms *p)
 	p->qcount = -1;
 }
 
-static inline unsigned long red_calc_qavg_from_idle_time(struct red_parms *p)
+static inline unsigned long red_calc_qavg_from_idle_time(const struct red_parms *p)
 {
-	psched_time_t now;
-	long us_idle;
+	s64 delta = ktime_us_delta(ktime_get(), p->qidlestart);
+	long us_idle = min_t(s64, delta, p->Scell_max);
 	int  shift;
 
-	now = psched_get_time();
-	us_idle = psched_tdiff_bounded(now, p->qidlestart, p->Scell_max);
-
 	/*
 	 * The problem: ideally, average length queue recalcultion should
 	 * be done over constant clock intervals. This is too expensive, so
@@ -218,7 +266,7 @@ static inline unsigned long red_calc_qavg_from_idle_time(struct red_parms *p)
 	}
 }
 
-static inline unsigned long red_calc_qavg_no_idle_time(struct red_parms *p,
+static inline unsigned long red_calc_qavg_no_idle_time(const struct red_parms *p,
 						       unsigned int backlog)
 {
 	/*
@@ -233,7 +281,7 @@ static inline unsigned long red_calc_qavg_no_idle_time(struct red_parms *p,
 	return p->qavg + (backlog - (p->qavg >> p->Wlog));
 }
 
-static inline unsigned long red_calc_qavg(struct red_parms *p,
+static inline unsigned long red_calc_qavg(const struct red_parms *p,
 					  unsigned int backlog)
 {
 	if (!red_is_idling(p))
@@ -242,23 +290,24 @@ static inline unsigned long red_calc_qavg(struct red_parms *p,
 		return red_calc_qavg_from_idle_time(p);
 }
 
-static inline u32 red_random(struct red_parms *p)
+
+static inline u32 red_random(const struct red_parms *p)
 {
-	return net_random() & p->Rmask;
+	return reciprocal_divide(net_random(), p->max_P_reciprocal);
 }
 
-static inline int red_mark_probability(struct red_parms *p, unsigned long qavg)
+static inline int red_mark_probability(const struct red_parms *p, unsigned long qavg)
 {
 	/* The formula used below causes questions.
 
-	   OK. qR is random number in the interval 0..Rmask
+	   OK. qR is random number in the interval
+		(0..1/max_P)*(qth_max-qth_min)
 	   i.e. 0..(2^Plog). If we used floating point
 	   arithmetics, it would be: (2^Plog)*rnd_num,
 	   where rnd_num is less 1.
 
 	   Taking into account, that qavg have fixed
-	   point at Wlog, and Plog is related to max_P by
-	   max_P = (qth_max-qth_min)/2^Plog; two lines
+	   point at Wlog, two lines
 	   below have the following floating point equivalent:
 
 	   max_P*(qavg - qth_min)/(qth_max-qth_min) < rnd/qcount
@@ -318,4 +367,25 @@ static inline int red_action(struct red_parms *p, unsigned long qavg)
 	return RED_DONT_MARK;
 }
 
+static inline void red_adaptative_algo(struct red_parms *p)
+{
+	unsigned long qavg;
+	u32 max_p_delta;
+
+	qavg = p->qavg;
+	if (red_is_idling(p))
+		qavg = red_calc_qavg_from_idle_time(p);
+
+	/* p->qavg is fixed point number with point at Wlog */
+	qavg >>= p->Wlog;
+
+	if (qavg > p->target_max && p->max_P <= MAX_P_MAX)
+		p->max_P += MAX_P_ALPHA(p->max_P); /* maxp = maxp + alpha */
+	else if (qavg < p->target_min && p->max_P >= MAX_P_MIN)
+		p->max_P = (p->max_P/10)*9; /* maxp = maxp * Beta */
+
+	max_p_delta = DIV_ROUND_CLOSEST(p->max_P, p->qth_delta);
+	max_p_delta = max(max_p_delta, 1U);
+	p->max_P_reciprocal = reciprocal_value(max_p_delta);
+}
 #endif
diff --git a/include/net/route.h b/include/net/route.h
index db7b343..91855d1 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -71,12 +71,12 @@ struct rtable {
 	struct fib_info		*fi; /* for client ref to shared metrics */
 };
 
-static inline bool rt_is_input_route(struct rtable *rt)
+static inline bool rt_is_input_route(const struct rtable *rt)
 {
 	return rt->rt_route_iif != 0;
 }
 
-static inline bool rt_is_output_route(struct rtable *rt)
+static inline bool rt_is_output_route(const struct rtable *rt)
 {
 	return rt->rt_route_iif == 0;
 }
diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h
index 6a72a58..d368561 100644
--- a/include/net/sctp/sctp.h
+++ b/include/net/sctp/sctp.h
@@ -71,7 +71,7 @@
 #include <linux/jiffies.h>
 #include <linux/idr.h>
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
 #endif
@@ -383,7 +383,7 @@ static inline void sctp_sysctl_unregister(void) { return; }
 /* Size of Supported Address Parameter for 'x' address types. */
 #define SCTP_SAT_LEN(x) (sizeof(struct sctp_paramhdr) + (x) * sizeof(__u16))
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 
 void sctp_v6_pf_init(void);
 void sctp_v6_pf_exit(void);
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index e90e7a9..ad0e31b 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -365,7 +365,7 @@ static inline struct sock *sctp_opt2sk(const struct sctp_sock *sp)
        return (struct sock *)sp;
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 struct sctp6_sock {
        struct sctp_sock  sctp;
        struct ipv6_pinfo inet6;
@@ -1085,6 +1085,7 @@ void sctp_transport_burst_reset(struct sctp_transport *);
 unsigned long sctp_transport_timeout(struct sctp_transport *);
 void sctp_transport_reset(struct sctp_transport *);
 void sctp_transport_update_pmtu(struct sctp_transport *, u32);
+void sctp_transport_immediate_rtx(struct sctp_transport *);
 
 
 /* This is the structure we use to queue packets as they come into
diff --git a/include/net/snmp.h b/include/net/snmp.h
index 8f0f9ac..2f65e16 100644
--- a/include/net/snmp.h
+++ b/include/net/snmp.h
@@ -67,7 +67,7 @@ struct icmp_mib {
 
 #define ICMPMSG_MIB_MAX	__ICMPMSG_MIB_MAX
 struct icmpmsg_mib {
-	unsigned long	mibs[ICMPMSG_MIB_MAX];
+	atomic_long_t	mibs[ICMPMSG_MIB_MAX];
 };
 
 /* ICMP6 (IPv6-ICMP) */
@@ -84,7 +84,7 @@ struct icmpv6_mib_device {
 #define ICMP6MSG_MIB_MAX  __ICMP6MSG_MIB_MAX
 /* per network ns counters */
 struct icmpv6msg_mib {
-	unsigned long	mibs[ICMP6MSG_MIB_MAX];
+	atomic_long_t	mibs[ICMP6MSG_MIB_MAX];
 };
 /* per device counters, (shared on all cpus) */
 struct icmpv6msg_mib_device {
diff --git a/include/net/sock.h b/include/net/sock.h
index c0c32a4..3144c79 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -53,6 +53,8 @@
 #include <linux/security.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/memcontrol.h>
+#include <linux/res_counter.h>
 
 #include <linux/filter.h>
 #include <linux/rculist_nulls.h>
@@ -62,6 +64,22 @@
 #include <net/dst.h>
 #include <net/checksum.h>
 
+struct cgroup;
+struct cgroup_subsys;
+#ifdef CONFIG_NET
+int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss);
+void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss);
+#else
+static inline
+int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+	return 0;
+}
+static inline
+void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+}
+#endif
 /*
  * This structure really needs to be cleaned up.
  * Most of it is for TCP, and not used by any of
@@ -167,6 +185,7 @@ struct sock_common {
 	/* public: */
 };
 
+struct cg_proto;
 /**
   *	struct sock - network layer representation of sockets
   *	@__sk_common: shared layout with inet_timewait_sock
@@ -227,6 +246,7 @@ struct sock_common {
   *	@sk_security: used by security modules
   *	@sk_mark: generic packet mark
   *	@sk_classid: this socket's cgroup classid
+  *	@sk_cgrp: this socket's cgroup-specific proto data
   *	@sk_write_pending: a write to stream socket waits to start
   *	@sk_state_change: callback to indicate change in the state of the sock
   *	@sk_data_ready: callback to indicate there is data to be processed
@@ -306,8 +326,8 @@ struct sock {
 	kmemcheck_bitfield_end(flags);
 	int			sk_wmem_queued;
 	gfp_t			sk_allocation;
-	int			sk_route_caps;
-	int			sk_route_nocaps;
+	netdev_features_t	sk_route_caps;
+	netdev_features_t	sk_route_nocaps;
 	int			sk_gso_type;
 	unsigned int		sk_gso_max_size;
 	int			sk_rcvlowat;
@@ -320,6 +340,9 @@ struct sock {
 	unsigned short		sk_ack_backlog;
 	unsigned short		sk_max_ack_backlog;
 	__u32			sk_priority;
+#ifdef CONFIG_CGROUPS
+	__u32			sk_cgrp_prioidx;
+#endif
 	struct pid		*sk_peer_pid;
 	const struct cred	*sk_peer_cred;
 	long			sk_rcvtimeo;
@@ -338,6 +361,7 @@ struct sock {
 #endif
 	__u32			sk_mark;
 	u32			sk_classid;
+	struct cg_proto		*sk_cgrp;
 	void			(*sk_state_change)(struct sock *sk);
 	void			(*sk_data_ready)(struct sock *sk, int bytes);
 	void			(*sk_write_space)(struct sock *sk);
@@ -834,6 +858,37 @@ struct proto {
 #ifdef SOCK_REFCNT_DEBUG
 	atomic_t		socks;
 #endif
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+	/*
+	 * cgroup specific init/deinit functions. Called once for all
+	 * protocols that implement it, from cgroups populate function.
+	 * This function has to setup any files the protocol want to
+	 * appear in the kmem cgroup filesystem.
+	 */
+	int			(*init_cgroup)(struct cgroup *cgrp,
+					       struct cgroup_subsys *ss);
+	void			(*destroy_cgroup)(struct cgroup *cgrp,
+						  struct cgroup_subsys *ss);
+	struct cg_proto		*(*proto_cgroup)(struct mem_cgroup *memcg);
+#endif
+};
+
+struct cg_proto {
+	void			(*enter_memory_pressure)(struct sock *sk);
+	struct res_counter	*memory_allocated;	/* Current allocated memory. */
+	struct percpu_counter	*sockets_allocated;	/* Current number of sockets. */
+	int			*memory_pressure;
+	long			*sysctl_mem;
+	/*
+	 * memcg field is used to find which memcg we belong directly
+	 * Each memcg struct can hold more than one cg_proto, so container_of
+	 * won't really cut.
+	 *
+	 * The elegant solution would be having an inverse function to
+	 * proto_cgroup in struct proto, but that means polluting the structure
+	 * for everybody, instead of just for memcg users.
+	 */
+	struct mem_cgroup	*memcg;
 };
 
 extern int proto_register(struct proto *prot, int alloc_slab);
@@ -852,7 +907,7 @@ static inline void sk_refcnt_debug_dec(struct sock *sk)
 	       sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks));
 }
 
-static inline void sk_refcnt_debug_release(const struct sock *sk)
+inline void sk_refcnt_debug_release(const struct sock *sk)
 {
 	if (atomic_read(&sk->sk_refcnt) != 1)
 		printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n",
@@ -864,6 +919,208 @@ static inline void sk_refcnt_debug_release(const struct sock *sk)
 #define sk_refcnt_debug_release(sk) do { } while (0)
 #endif /* SOCK_REFCNT_DEBUG */
 
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+extern struct jump_label_key memcg_socket_limit_enabled;
+static inline struct cg_proto *parent_cg_proto(struct proto *proto,
+					       struct cg_proto *cg_proto)
+{
+	return proto->proto_cgroup(parent_mem_cgroup(cg_proto->memcg));
+}
+#define mem_cgroup_sockets_enabled static_branch(&memcg_socket_limit_enabled)
+#else
+#define mem_cgroup_sockets_enabled 0
+static inline struct cg_proto *parent_cg_proto(struct proto *proto,
+					       struct cg_proto *cg_proto)
+{
+	return NULL;
+}
+#endif
+
+
+static inline bool sk_has_memory_pressure(const struct sock *sk)
+{
+	return sk->sk_prot->memory_pressure != NULL;
+}
+
+static inline bool sk_under_memory_pressure(const struct sock *sk)
+{
+	if (!sk->sk_prot->memory_pressure)
+		return false;
+
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
+		return !!*sk->sk_cgrp->memory_pressure;
+
+	return !!*sk->sk_prot->memory_pressure;
+}
+
+static inline void sk_leave_memory_pressure(struct sock *sk)
+{
+	int *memory_pressure = sk->sk_prot->memory_pressure;
+
+	if (!memory_pressure)
+		return;
+
+	if (*memory_pressure)
+		*memory_pressure = 0;
+
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
+		struct cg_proto *cg_proto = sk->sk_cgrp;
+		struct proto *prot = sk->sk_prot;
+
+		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
+			if (*cg_proto->memory_pressure)
+				*cg_proto->memory_pressure = 0;
+	}
+
+}
+
+static inline void sk_enter_memory_pressure(struct sock *sk)
+{
+	if (!sk->sk_prot->enter_memory_pressure)
+		return;
+
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
+		struct cg_proto *cg_proto = sk->sk_cgrp;
+		struct proto *prot = sk->sk_prot;
+
+		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
+			cg_proto->enter_memory_pressure(sk);
+	}
+
+	sk->sk_prot->enter_memory_pressure(sk);
+}
+
+static inline long sk_prot_mem_limits(const struct sock *sk, int index)
+{
+	long *prot = sk->sk_prot->sysctl_mem;
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
+		prot = sk->sk_cgrp->sysctl_mem;
+	return prot[index];
+}
+
+static inline void memcg_memory_allocated_add(struct cg_proto *prot,
+					      unsigned long amt,
+					      int *parent_status)
+{
+	struct res_counter *fail;
+	int ret;
+
+	ret = res_counter_charge(prot->memory_allocated,
+				 amt << PAGE_SHIFT, &fail);
+
+	if (ret < 0)
+		*parent_status = OVER_LIMIT;
+}
+
+static inline void memcg_memory_allocated_sub(struct cg_proto *prot,
+					      unsigned long amt)
+{
+	res_counter_uncharge(prot->memory_allocated, amt << PAGE_SHIFT);
+}
+
+static inline u64 memcg_memory_allocated_read(struct cg_proto *prot)
+{
+	u64 ret;
+	ret = res_counter_read_u64(prot->memory_allocated, RES_USAGE);
+	return ret >> PAGE_SHIFT;
+}
+
+static inline long
+sk_memory_allocated(const struct sock *sk)
+{
+	struct proto *prot = sk->sk_prot;
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
+		return memcg_memory_allocated_read(sk->sk_cgrp);
+
+	return atomic_long_read(prot->memory_allocated);
+}
+
+static inline long
+sk_memory_allocated_add(struct sock *sk, int amt, int *parent_status)
+{
+	struct proto *prot = sk->sk_prot;
+
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
+		memcg_memory_allocated_add(sk->sk_cgrp, amt, parent_status);
+		/* update the root cgroup regardless */
+		atomic_long_add_return(amt, prot->memory_allocated);
+		return memcg_memory_allocated_read(sk->sk_cgrp);
+	}
+
+	return atomic_long_add_return(amt, prot->memory_allocated);
+}
+
+static inline void
+sk_memory_allocated_sub(struct sock *sk, int amt, int parent_status)
+{
+	struct proto *prot = sk->sk_prot;
+
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp &&
+	    parent_status != OVER_LIMIT) /* Otherwise was uncharged already */
+		memcg_memory_allocated_sub(sk->sk_cgrp, amt);
+
+	atomic_long_sub(amt, prot->memory_allocated);
+}
+
+static inline void sk_sockets_allocated_dec(struct sock *sk)
+{
+	struct proto *prot = sk->sk_prot;
+
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
+		struct cg_proto *cg_proto = sk->sk_cgrp;
+
+		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
+			percpu_counter_dec(cg_proto->sockets_allocated);
+	}
+
+	percpu_counter_dec(prot->sockets_allocated);
+}
+
+static inline void sk_sockets_allocated_inc(struct sock *sk)
+{
+	struct proto *prot = sk->sk_prot;
+
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp) {
+		struct cg_proto *cg_proto = sk->sk_cgrp;
+
+		for (; cg_proto; cg_proto = parent_cg_proto(prot, cg_proto))
+			percpu_counter_inc(cg_proto->sockets_allocated);
+	}
+
+	percpu_counter_inc(prot->sockets_allocated);
+}
+
+static inline int
+sk_sockets_allocated_read_positive(struct sock *sk)
+{
+	struct proto *prot = sk->sk_prot;
+
+	if (mem_cgroup_sockets_enabled && sk->sk_cgrp)
+		return percpu_counter_sum_positive(sk->sk_cgrp->sockets_allocated);
+
+	return percpu_counter_sum_positive(prot->sockets_allocated);
+}
+
+static inline int
+proto_sockets_allocated_sum_positive(struct proto *prot)
+{
+	return percpu_counter_sum_positive(prot->sockets_allocated);
+}
+
+static inline long
+proto_memory_allocated(struct proto *prot)
+{
+	return atomic_long_read(prot->memory_allocated);
+}
+
+static inline bool
+proto_memory_pressure(struct proto *prot)
+{
+	if (!prot->memory_pressure)
+		return false;
+	return !!*prot->memory_pressure;
+}
+
 
 #ifdef CONFIG_PROC_FS
 /* Called with local bh disabled */
@@ -1090,8 +1347,8 @@ extern struct sock		*sk_alloc(struct net *net, int family,
 					  struct proto *prot);
 extern void			sk_free(struct sock *sk);
 extern void			sk_release_kernel(struct sock *sk);
-extern struct sock		*sk_clone(const struct sock *sk,
-					  const gfp_t priority);
+extern struct sock		*sk_clone_lock(const struct sock *sk,
+					       const gfp_t priority);
 
 extern struct sk_buff		*sock_wmalloc(struct sock *sk,
 					      unsigned long size, int force,
@@ -1394,7 +1651,7 @@ static inline int sk_can_gso(const struct sock *sk)
 
 extern void sk_setup_caps(struct sock *sk, struct dst_entry *dst);
 
-static inline void sk_nocaps_add(struct sock *sk, int flags)
+static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags)
 {
 	sk->sk_route_nocaps |= flags;
 	sk->sk_route_caps &= ~flags;
@@ -1671,7 +1928,7 @@ static inline struct page *sk_stream_alloc_page(struct sock *sk)
 
 	page = alloc_pages(sk->sk_allocation, 0);
 	if (!page) {
-		sk->sk_prot->enter_memory_pressure(sk);
+		sk_enter_memory_pressure(sk);
 		sk_stream_moderate_sndbuf(sk);
 	}
 	return page;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index bb18c4d..a4f52e1 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -44,6 +44,7 @@
 #include <net/dst.h>
 
 #include <linux/seq_file.h>
+#include <linux/memcontrol.h>
 
 extern struct inet_hashinfo tcp_hashinfo;
 
@@ -229,7 +230,6 @@ extern int sysctl_tcp_fack;
 extern int sysctl_tcp_reordering;
 extern int sysctl_tcp_ecn;
 extern int sysctl_tcp_dsack;
-extern long sysctl_tcp_mem[3];
 extern int sysctl_tcp_wmem[3];
 extern int sysctl_tcp_rmem[3];
 extern int sysctl_tcp_app_win;
@@ -285,7 +285,7 @@ static inline bool tcp_too_many_orphans(struct sock *sk, int shift)
 	}
 
 	if (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
-	    atomic_long_read(&tcp_memory_allocated) > sysctl_tcp_mem[2])
+	    sk_memory_allocated(sk) > sk_prot_mem_limits(sk, 2))
 		return true;
 	return false;
 }
@@ -628,7 +628,7 @@ extern u32 __tcp_select_window(struct sock *sk);
 struct tcp_skb_cb {
 	union {
 		struct inet_skb_parm	h4;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		struct inet6_skb_parm	h6;
 #endif
 	} header;	/* For incoming frames		*/
@@ -834,6 +834,14 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk)
 extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh);
 extern __u32 tcp_init_cwnd(const struct tcp_sock *tp, const struct dst_entry *dst);
 
+/* The maximum number of MSS of available cwnd for which TSO defers
+ * sending if not using sysctl_tcp_tso_win_divisor.
+ */
+static inline __u32 tcp_max_tso_deferred_mss(const struct tcp_sock *tp)
+{
+	return 3;
+}
+
 /* Slow start with delack produces 3 packets of burst, so that
  * it is safe "de facto".  This will be the default - same as
  * the default reordering threshold - but if reordering increases,
@@ -1144,7 +1152,7 @@ struct tcp6_md5sig_key {
 /* - sock block */
 struct tcp_md5sig_info {
 	struct tcp4_md5sig_key	*keys4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct tcp6_md5sig_key	*keys6;
 	u32			entries6;
 	u32			alloced6;
@@ -1171,7 +1179,7 @@ struct tcp6_pseudohdr {
 
 union tcp_md5sum_block {
 	struct tcp4_pseudohdr ip4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct tcp6_pseudohdr ip6;
 #endif
 };
@@ -1430,7 +1438,8 @@ extern struct request_sock_ops tcp6_request_sock_ops;
 extern void tcp_v4_destroy_sock(struct sock *sk);
 
 extern int tcp_v4_gso_send_check(struct sk_buff *skb);
-extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features);
+extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
+				       netdev_features_t features);
 extern struct sk_buff **tcp_gro_receive(struct sk_buff **head,
 					struct sk_buff *skb);
 extern struct sk_buff **tcp4_gro_receive(struct sk_buff **head,
diff --git a/include/net/tcp_memcontrol.h b/include/net/tcp_memcontrol.h
new file mode 100644
index 0000000..3512082
--- /dev/null
+++ b/include/net/tcp_memcontrol.h
@@ -0,0 +1,19 @@
+#ifndef _TCP_MEMCG_H
+#define _TCP_MEMCG_H
+
+struct tcp_memcontrol {
+	struct cg_proto cg_proto;
+	/* per-cgroup tcp memory pressure knobs */
+	struct res_counter tcp_memory_allocated;
+	struct percpu_counter tcp_sockets_allocated;
+	/* those two are read-mostly, leave them at the end */
+	long tcp_prot_mem[3];
+	int tcp_memory_pressure;
+};
+
+struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg);
+int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss);
+void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss);
+unsigned long long tcp_max_memory(const struct mem_cgroup *memcg);
+void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx);
+#endif /* _TCP_MEMCG_H */
diff --git a/include/net/udp.h b/include/net/udp.h
index 3b285f4..e39592f 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -41,7 +41,7 @@
 struct udp_skb_cb {
 	union {
 		struct inet_skb_parm	h4;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		struct inet6_skb_parm	h6;
 #endif
 	} header;
@@ -194,9 +194,15 @@ extern int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 extern struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
 				    __be32 daddr, __be16 dport,
 				    int dif);
+extern struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
+				    __be32 daddr, __be16 dport,
+				    int dif, struct udp_table *tbl);
 extern struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport,
 				    const struct in6_addr *daddr, __be16 dport,
 				    int dif);
+extern struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport,
+				    const struct in6_addr *daddr, __be16 dport,
+				    int dif, struct udp_table *tbl);
 
 /*
  * 	SNMP statistics for UDP and UDP-Lite
@@ -217,7 +223,7 @@ extern struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *sadd
 	else	    SNMP_INC_STATS_USER((net)->mib.udp_stats_in6, field);      \
 } while(0)
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 #define UDPX_INC_STATS_BH(sk, field) \
 	do { \
 		if ((sk)->sk_family == AF_INET) \
@@ -258,5 +264,6 @@ extern void udp4_proc_exit(void);
 extern void udp_init(void);
 
 extern int udp4_ufo_send_check(struct sk_buff *skb);
-extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features);
+extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
+	netdev_features_t features);
 #endif	/* _UDP_H */
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index b203e14..89174e29 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -827,6 +827,14 @@ static inline bool addr_match(const void *token1, const void *token2,
 	return true;
 }
 
+static inline bool addr4_match(__be32 a1, __be32 a2, u8 prefixlen)
+{
+	/* C99 6.5.7 (3): u32 << 32 is undefined behaviour */
+	if (prefixlen == 0)
+		return true;
+	return !((a1 ^ a2) & htonl(0xFFFFFFFFu << (32 - prefixlen)));
+}
+
 static __inline__
 __be16 xfrm_flowi_sport(const struct flowi *fl, const union flowi_uli *uli)
 {
@@ -1209,8 +1217,8 @@ void xfrm_flowi_addr_get(const struct flowi *fl,
 		memcpy(&daddr->a4, &fl->u.ip4.daddr, sizeof(daddr->a4));
 		break;
 	case AF_INET6:
-		ipv6_addr_copy((struct in6_addr *)&saddr->a6, &fl->u.ip6.saddr);
-		ipv6_addr_copy((struct in6_addr *)&daddr->a6, &fl->u.ip6.daddr);
+		*(struct in6_addr *)saddr->a6 = fl->u.ip6.saddr;
+		*(struct in6_addr *)daddr->a6 = fl->u.ip6.daddr;
 		break;
 	}
 }
diff --git a/include/video/omapdss.h b/include/video/omapdss.h
index b66ebb2..378c7ed 100644
--- a/include/video/omapdss.h
+++ b/include/video/omapdss.h
@@ -307,15 +307,8 @@ struct omap_dss_board_info {
 	void (*dsi_disable_pads)(int dsi_id, unsigned lane_mask);
 };
 
-#if defined(CONFIG_OMAP2_DSS_MODULE) || defined(CONFIG_OMAP2_DSS)
 /* Init with the board info */
 extern int omap_display_init(struct omap_dss_board_info *board_data);
-#else
-static inline int omap_display_init(struct omap_dss_board_info *board_data)
-{
-	return 0;
-}
-#endif
 
 struct omap_display_platform_data {
 	struct omap_dss_board_info *board_data;
diff --git a/include/xen/platform_pci.h b/include/xen/platform_pci.h
index a785a3b..438c256 100644
--- a/include/xen/platform_pci.h
+++ b/include/xen/platform_pci.h
@@ -29,8 +29,7 @@
 static inline int xen_must_unplug_nics(void) {
 #if (defined(CONFIG_XEN_NETDEV_FRONTEND) || \
 		defined(CONFIG_XEN_NETDEV_FRONTEND_MODULE)) && \
-		(defined(CONFIG_XEN_PLATFORM_PCI) || \
-		 defined(CONFIG_XEN_PLATFORM_PCI_MODULE))
+		defined(CONFIG_XEN_PVHVM)
         return 1;
 #else
         return 0;
@@ -40,8 +39,7 @@ static inline int xen_must_unplug_nics(void) {
 static inline int xen_must_unplug_disks(void) {
 #if (defined(CONFIG_XEN_BLKDEV_FRONTEND) || \
 		defined(CONFIG_XEN_BLKDEV_FRONTEND_MODULE)) && \
-		(defined(CONFIG_XEN_PLATFORM_PCI) || \
-		 defined(CONFIG_XEN_PLATFORM_PCI_MODULE))
+		defined(CONFIG_XEN_PVHVM)
         return 1;
 #else
         return 0;
diff --git a/init/Kconfig b/init/Kconfig
index 43298f9..b8930d5 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -689,6 +689,17 @@ config CGROUP_MEM_RES_CTLR_SWAP_ENABLED
 	  For those who want to have the feature enabled by default should
 	  select this option (if, for some reason, they need to disable it
 	  then swapaccount=0 does the trick).
+config CGROUP_MEM_RES_CTLR_KMEM
+	bool "Memory Resource Controller Kernel Memory accounting (EXPERIMENTAL)"
+	depends on CGROUP_MEM_RES_CTLR && EXPERIMENTAL
+	default n
+	help
+	  The Kernel Memory extension for Memory Resource Controller can limit
+	  the amount of memory used by kernel objects in the system. Those are
+	  fundamentally different from the entities handled by the standard
+	  Memory Controller, which are page-based, and can be swapped. Users of
+	  the kmem extension can use it to guarantee that no group of processes
+	  will ever exhaust kernel resources alone.
 
 config CGROUP_PERF
 	bool "Enable perf_event per-cpu per-container group (cgroup) monitoring"
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index 5e828a2..213c035 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -153,6 +153,13 @@ static void freezer_destroy(struct cgroup_subsys *ss,
 	kfree(cgroup_freezer(cgroup));
 }
 
+/* task is frozen or will freeze immediately when next it gets woken */
+static bool is_task_frozen_enough(struct task_struct *task)
+{
+	return frozen(task) ||
+		(task_is_stopped_or_traced(task) && freezing(task));
+}
+
 /*
  * The call to cgroup_lock() in the freezer.state write method prevents
  * a write to that file racing against an attach, and hence the
@@ -231,7 +238,7 @@ static void update_if_frozen(struct cgroup *cgroup,
 	cgroup_iter_start(cgroup, &it);
 	while ((task = cgroup_iter_next(cgroup, &it))) {
 		ntotal++;
-		if (frozen(task))
+		if (is_task_frozen_enough(task))
 			nfrozen++;
 	}
 
@@ -284,7 +291,7 @@ static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
 	while ((task = cgroup_iter_next(cgroup, &it))) {
 		if (!freeze_task(task, true))
 			continue;
-		if (frozen(task))
+		if (is_task_frozen_enough(task))
 			continue;
 		if (!freezing(task) && !freezer_should_skip(task))
 			num_cant_freeze_now++;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 0e8457d..600c162 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -185,6 +185,9 @@ static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
 static void update_context_time(struct perf_event_context *ctx);
 static u64 perf_event_time(struct perf_event *event);
 
+static void ring_buffer_attach(struct perf_event *event,
+			       struct ring_buffer *rb);
+
 void __weak perf_event_print_debug(void)	{ }
 
 extern __weak const char *perf_pmu_name(void)
@@ -2173,7 +2176,8 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
 
 	perf_event_sched_in(cpuctx, ctx, task);
 
-	cpuctx->task_ctx = ctx;
+	if (ctx->nr_events)
+		cpuctx->task_ctx = ctx;
 
 	perf_pmu_enable(ctx->pmu);
 	perf_ctx_unlock(cpuctx, ctx);
@@ -3190,12 +3194,33 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 	struct ring_buffer *rb;
 	unsigned int events = POLL_HUP;
 
+	/*
+	 * Race between perf_event_set_output() and perf_poll(): perf_poll()
+	 * grabs the rb reference but perf_event_set_output() overrides it.
+	 * Here is the timeline for two threads T1, T2:
+	 * t0: T1, rb = rcu_dereference(event->rb)
+	 * t1: T2, old_rb = event->rb
+	 * t2: T2, event->rb = new rb
+	 * t3: T2, ring_buffer_detach(old_rb)
+	 * t4: T1, ring_buffer_attach(rb1)
+	 * t5: T1, poll_wait(event->waitq)
+	 *
+	 * To avoid this problem, we grab mmap_mutex in perf_poll()
+	 * thereby ensuring that the assignment of the new ring buffer
+	 * and the detachment of the old buffer appear atomic to perf_poll()
+	 */
+	mutex_lock(&event->mmap_mutex);
+
 	rcu_read_lock();
 	rb = rcu_dereference(event->rb);
-	if (rb)
+	if (rb) {
+		ring_buffer_attach(event, rb);
 		events = atomic_xchg(&rb->poll, 0);
+	}
 	rcu_read_unlock();
 
+	mutex_unlock(&event->mmap_mutex);
+
 	poll_wait(file, &event->waitq, wait);
 
 	return events;
@@ -3496,6 +3521,49 @@ unlock:
 	return ret;
 }
 
+static void ring_buffer_attach(struct perf_event *event,
+			       struct ring_buffer *rb)
+{
+	unsigned long flags;
+
+	if (!list_empty(&event->rb_entry))
+		return;
+
+	spin_lock_irqsave(&rb->event_lock, flags);
+	if (!list_empty(&event->rb_entry))
+		goto unlock;
+
+	list_add(&event->rb_entry, &rb->event_list);
+unlock:
+	spin_unlock_irqrestore(&rb->event_lock, flags);
+}
+
+static void ring_buffer_detach(struct perf_event *event,
+			       struct ring_buffer *rb)
+{
+	unsigned long flags;
+
+	if (list_empty(&event->rb_entry))
+		return;
+
+	spin_lock_irqsave(&rb->event_lock, flags);
+	list_del_init(&event->rb_entry);
+	wake_up_all(&event->waitq);
+	spin_unlock_irqrestore(&rb->event_lock, flags);
+}
+
+static void ring_buffer_wakeup(struct perf_event *event)
+{
+	struct ring_buffer *rb;
+
+	rcu_read_lock();
+	rb = rcu_dereference(event->rb);
+	list_for_each_entry_rcu(event, &rb->event_list, rb_entry) {
+		wake_up_all(&event->waitq);
+	}
+	rcu_read_unlock();
+}
+
 static void rb_free_rcu(struct rcu_head *rcu_head)
 {
 	struct ring_buffer *rb;
@@ -3521,9 +3589,19 @@ static struct ring_buffer *ring_buffer_get(struct perf_event *event)
 
 static void ring_buffer_put(struct ring_buffer *rb)
 {
+	struct perf_event *event, *n;
+	unsigned long flags;
+
 	if (!atomic_dec_and_test(&rb->refcount))
 		return;
 
+	spin_lock_irqsave(&rb->event_lock, flags);
+	list_for_each_entry_safe(event, n, &rb->event_list, rb_entry) {
+		list_del_init(&event->rb_entry);
+		wake_up_all(&event->waitq);
+	}
+	spin_unlock_irqrestore(&rb->event_lock, flags);
+
 	call_rcu(&rb->rcu_head, rb_free_rcu);
 }
 
@@ -3546,6 +3624,7 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 		atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
 		vma->vm_mm->pinned_vm -= event->mmap_locked;
 		rcu_assign_pointer(event->rb, NULL);
+		ring_buffer_detach(event, rb);
 		mutex_unlock(&event->mmap_mutex);
 
 		ring_buffer_put(rb);
@@ -3700,7 +3779,7 @@ static const struct file_operations perf_fops = {
 
 void perf_event_wakeup(struct perf_event *event)
 {
-	wake_up_all(&event->waitq);
+	ring_buffer_wakeup(event);
 
 	if (event->pending_kill) {
 		kill_fasync(&event->fasync, SIGIO, event->pending_kill);
@@ -5822,6 +5901,8 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 	INIT_LIST_HEAD(&event->group_entry);
 	INIT_LIST_HEAD(&event->event_entry);
 	INIT_LIST_HEAD(&event->sibling_list);
+	INIT_LIST_HEAD(&event->rb_entry);
+
 	init_waitqueue_head(&event->waitq);
 	init_irq_work(&event->pending, perf_pending_event);
 
@@ -6028,6 +6109,8 @@ set:
 
 	old_rb = event->rb;
 	rcu_assign_pointer(event->rb, rb);
+	if (old_rb)
+		ring_buffer_detach(event, old_rb);
 	ret = 0;
 unlock:
 	mutex_unlock(&event->mmap_mutex);
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 09097dd..64568a6 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -22,6 +22,9 @@ struct ring_buffer {
 	local_t				lost;		/* nr records lost   */
 
 	long				watermark;	/* wakeup watermark  */
+	/* poll crap */
+	spinlock_t			event_lock;
+	struct list_head		event_list;
 
 	struct perf_event_mmap_page	*user_page;
 	void				*data_pages[0];
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index a2a2920..7f3011c 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -209,6 +209,9 @@ ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 		rb->writable = 1;
 
 	atomic_set(&rb->refcount, 1);
+
+	INIT_LIST_HEAD(&rb->event_list);
+	spin_lock_init(&rb->event_lock);
 }
 
 #ifndef CONFIG_PERF_USE_VMALLOC
diff --git a/kernel/fork.c b/kernel/fork.c
index ba0d172..da4a6a1 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -162,7 +162,6 @@ static void account_kernel_stack(struct thread_info *ti, int account)
 
 void free_task(struct task_struct *tsk)
 {
-	prop_local_destroy_single(&tsk->dirties);
 	account_kernel_stack(tsk->stack, -1);
 	free_thread_info(tsk->stack);
 	rt_mutex_debug_task_free(tsk);
@@ -274,10 +273,6 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 
 	tsk->stack = ti;
 
-	err = prop_local_init_single(&tsk->dirties);
-	if (err)
-		goto out;
-
 	setup_thread_stack(tsk, orig);
 	clear_user_return_notifier(tsk);
 	clear_tsk_need_resched(tsk);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 422e567..ae34bf5 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -885,10 +885,13 @@ static void __remove_hrtimer(struct hrtimer *timer,
 			     struct hrtimer_clock_base *base,
 			     unsigned long newstate, int reprogram)
 {
+	struct timerqueue_node *next_timer;
 	if (!(timer->state & HRTIMER_STATE_ENQUEUED))
 		goto out;
 
-	if (&timer->node == timerqueue_getnext(&base->active)) {
+	next_timer = timerqueue_getnext(&base->active);
+	timerqueue_del(&base->active, &timer->node);
+	if (&timer->node == next_timer) {
 #ifdef CONFIG_HIGH_RES_TIMERS
 		/* Reprogram the clock event device. if enabled */
 		if (reprogram && hrtimer_hres_active()) {
@@ -901,7 +904,6 @@ static void __remove_hrtimer(struct hrtimer *timer,
 		}
 #endif
 	}
-	timerqueue_del(&base->active, &timer->node);
 	if (!timerqueue_getnext(&base->active))
 		base->cpu_base->active_bases &= ~(1 << base->index);
 out:
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 67ce837..1da999f 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -623,8 +623,9 @@ static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id)
 
 static int irq_wait_for_interrupt(struct irqaction *action)
 {
+	set_current_state(TASK_INTERRUPTIBLE);
+
 	while (!kthread_should_stop()) {
-		set_current_state(TASK_INTERRUPTIBLE);
 
 		if (test_and_clear_bit(IRQTF_RUNTHREAD,
 				       &action->thread_flags)) {
@@ -632,7 +633,9 @@ static int irq_wait_for_interrupt(struct irqaction *action)
 			return 0;
 		}
 		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
 	}
+	__set_current_state(TASK_RUNNING);
 	return -1;
 }
 
@@ -1596,7 +1599,7 @@ int request_percpu_irq(unsigned int irq, irq_handler_t handler,
 		return -ENOMEM;
 
 	action->handler = handler;
-	action->flags = IRQF_PERCPU;
+	action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND;
 	action->name = devname;
 	action->percpu_dev_id = dev_id;
 
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index aa57d5d..dc813a9 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -84,7 +84,9 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force)
 	 */
 	action = desc->action;
 	if (!action || !(action->flags & IRQF_SHARED) ||
-	    (action->flags & __IRQF_TIMER) || !action->next)
+	    (action->flags & __IRQF_TIMER) ||
+	    (action->handler(irq, action->dev_id) == IRQ_HANDLED) ||
+	    !action->next)
 		goto out;
 
 	/* Already running on another processor */
@@ -115,7 +117,7 @@ static int misrouted_irq(int irq)
 	struct irq_desc *desc;
 	int i, ok = 0;
 
-	if (atomic_inc_return(&irq_poll_active) == 1)
+	if (atomic_inc_return(&irq_poll_active) != 1)
 		goto out;
 
 	irq_poll_cpu = smp_processor_id();
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index bbdfe2a..66ff710 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -66,8 +66,9 @@ void jump_label_inc(struct jump_label_key *key)
 		return;
 
 	jump_label_lock();
-	if (atomic_add_return(1, &key->enabled) == 1)
+	if (atomic_read(&key->enabled) == 0)
 		jump_label_update(key, JUMP_LABEL_ENABLE);
+	atomic_inc(&key->enabled);
 	jump_label_unlock();
 }
 
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index b4511b6..a6b0503 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -55,6 +55,8 @@ enum {
 
 static int hibernation_mode = HIBERNATION_SHUTDOWN;
 
+static bool freezer_test_done;
+
 static const struct platform_hibernation_ops *hibernation_ops;
 
 /**
@@ -345,11 +347,24 @@ int hibernation_snapshot(int platform_mode)
 
 	error = freeze_kernel_threads();
 	if (error)
-		goto Close;
+		goto Cleanup;
+
+	if (hibernation_test(TEST_FREEZER) ||
+		hibernation_testmode(HIBERNATION_TESTPROC)) {
+
+		/*
+		 * Indicate to the caller that we are returning due to a
+		 * successful freezer test.
+		 */
+		freezer_test_done = true;
+		goto Cleanup;
+	}
 
 	error = dpm_prepare(PMSG_FREEZE);
-	if (error)
-		goto Complete_devices;
+	if (error) {
+		dpm_complete(msg);
+		goto Cleanup;
+	}
 
 	suspend_console();
 	pm_restrict_gfp_mask();
@@ -378,8 +393,6 @@ int hibernation_snapshot(int platform_mode)
 		pm_restore_gfp_mask();
 
 	resume_console();
-
- Complete_devices:
 	dpm_complete(msg);
 
  Close:
@@ -389,6 +402,10 @@ int hibernation_snapshot(int platform_mode)
  Recover_platform:
 	platform_recover(platform_mode);
 	goto Resume_devices;
+
+ Cleanup:
+	swsusp_free();
+	goto Close;
 }
 
 /**
@@ -641,15 +658,13 @@ int hibernate(void)
 	if (error)
 		goto Finish;
 
-	if (hibernation_test(TEST_FREEZER))
-		goto Thaw;
-
-	if (hibernation_testmode(HIBERNATION_TESTPROC))
-		goto Thaw;
-
 	error = hibernation_snapshot(hibernation_mode == HIBERNATION_PLATFORM);
 	if (error)
 		goto Thaw;
+	if (freezer_test_done) {
+		freezer_test_done = false;
+		goto Thaw;
+	}
 
 	if (in_suspend) {
 		unsigned int flags = 0;
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 71f49fe..36e0f09 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -290,13 +290,14 @@ static ssize_t state_store(struct kobject *kobj, struct kobj_attribute *attr,
 		if (*s && len == strlen(*s) && !strncmp(buf, *s, len))
 			break;
 	}
-	if (state < PM_SUSPEND_MAX && *s)
+	if (state < PM_SUSPEND_MAX && *s) {
 		error = enter_state(state);
 		if (error) {
 			suspend_stats.fail++;
 			dpm_save_failed_errno(error);
 		} else
 			suspend_stats.success++;
+	}
 #endif
 
  Exit:
diff --git a/kernel/sched.c b/kernel/sched.c
index 0e9344a..d6b149c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -71,6 +71,7 @@
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
 #include <linux/slab.h>
+#include <linux/init_task.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
@@ -4810,6 +4811,9 @@ EXPORT_SYMBOL(wait_for_completion);
  * This waits for either a completion of a specific task to be signaled or for a
  * specified timeout to expire. The timeout is in jiffies. It is not
  * interruptible.
+ *
+ * The return value is 0 if timed out, and positive (at least 1, or number of
+ * jiffies left till timeout) if completed.
  */
 unsigned long __sched
 wait_for_completion_timeout(struct completion *x, unsigned long timeout)
@@ -4824,6 +4828,8 @@ EXPORT_SYMBOL(wait_for_completion_timeout);
  *
  * This waits for completion of a specific task to be signaled. It is
  * interruptible.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if completed.
  */
 int __sched wait_for_completion_interruptible(struct completion *x)
 {
@@ -4841,6 +4847,9 @@ EXPORT_SYMBOL(wait_for_completion_interruptible);
  *
  * This waits for either a completion of a specific task to be signaled or for a
  * specified timeout to expire. It is interruptible. The timeout is in jiffies.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
+ * positive (at least 1, or number of jiffies left till timeout) if completed.
  */
 long __sched
 wait_for_completion_interruptible_timeout(struct completion *x,
@@ -4856,6 +4865,8 @@ EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);
  *
  * This waits to be signaled for completion of a specific task. It can be
  * interrupted by a kill signal.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if completed.
  */
 int __sched wait_for_completion_killable(struct completion *x)
 {
@@ -4874,6 +4885,9 @@ EXPORT_SYMBOL(wait_for_completion_killable);
  * This waits for either a completion of a specific task to be
  * signaled or for a specified timeout to expire. It can be
  * interrupted by a kill signal. The timeout is in jiffies.
+ *
+ * The return value is -ERESTARTSYS if interrupted, 0 if timed out,
+ * positive (at least 1, or number of jiffies left till timeout) if completed.
  */
 long __sched
 wait_for_completion_killable_timeout(struct completion *x,
@@ -6099,6 +6113,9 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	 */
 	idle->sched_class = &idle_sched_class;
 	ftrace_graph_init_idle_task(idle, cpu);
+#if defined(CONFIG_SMP)
+	sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
+#endif
 }
 
 /*
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 5c9e679..a78ed27 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -772,19 +772,32 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 		list_del_leaf_cfs_rq(cfs_rq);
 }
 
+static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
+{
+	long tg_weight;
+
+	/*
+	 * Use this CPU's actual weight instead of the last load_contribution
+	 * to gain a more accurate current total weight. See
+	 * update_cfs_rq_load_contribution().
+	 */
+	tg_weight = atomic_read(&tg->load_weight);
+	tg_weight -= cfs_rq->load_contribution;
+	tg_weight += cfs_rq->load.weight;
+
+	return tg_weight;
+}
+
 static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
 {
-	long load_weight, load, shares;
+	long tg_weight, load, shares;
 
+	tg_weight = calc_tg_weight(tg, cfs_rq);
 	load = cfs_rq->load.weight;
 
-	load_weight = atomic_read(&tg->load_weight);
-	load_weight += load;
-	load_weight -= cfs_rq->load_contribution;
-
 	shares = (tg->shares * load);
-	if (load_weight)
-		shares /= load_weight;
+	if (tg_weight)
+		shares /= tg_weight;
 
 	if (shares < MIN_SHARES)
 		shares = MIN_SHARES;
@@ -1743,7 +1756,7 @@ static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 {
-	if (!cfs_rq->runtime_enabled || !cfs_rq->nr_running)
+	if (!cfs_rq->runtime_enabled || cfs_rq->nr_running)
 		return;
 
 	__return_cfs_rq_runtime(cfs_rq);
@@ -2036,36 +2049,100 @@ static void task_waking_fair(struct task_struct *p)
  * Adding load to a group doesn't make a group heavier, but can cause movement
  * of group shares between cpus. Assuming the shares were perfectly aligned one
  * can calculate the shift in shares.
+ *
+ * Calculate the effective load difference if @wl is added (subtracted) to @tg
+ * on this @cpu and results in a total addition (subtraction) of @wg to the
+ * total group weight.
+ *
+ * Given a runqueue weight distribution (rw_i) we can compute a shares
+ * distribution (s_i) using:
+ *
+ *   s_i = rw_i / \Sum rw_j						(1)
+ *
+ * Suppose we have 4 CPUs and our @tg is a direct child of the root group and
+ * has 7 equal weight tasks, distributed as below (rw_i), with the resulting
+ * shares distribution (s_i):
+ *
+ *   rw_i = {   2,   4,   1,   0 }
+ *   s_i  = { 2/7, 4/7, 1/7,   0 }
+ *
+ * As per wake_affine() we're interested in the load of two CPUs (the CPU the
+ * task used to run on and the CPU the waker is running on), we need to
+ * compute the effect of waking a task on either CPU and, in case of a sync
+ * wakeup, compute the effect of the current task going to sleep.
+ *
+ * So for a change of @wl to the local @cpu with an overall group weight change
+ * of @wl we can compute the new shares distribution (s'_i) using:
+ *
+ *   s'_i = (rw_i + @wl) / (@wg + \Sum rw_j)				(2)
+ *
+ * Suppose we're interested in CPUs 0 and 1, and want to compute the load
+ * differences in waking a task to CPU 0. The additional task changes the
+ * weight and shares distributions like:
+ *
+ *   rw'_i = {   3,   4,   1,   0 }
+ *   s'_i  = { 3/8, 4/8, 1/8,   0 }
+ *
+ * We can then compute the difference in effective weight by using:
+ *
+ *   dw_i = S * (s'_i - s_i)						(3)
+ *
+ * Where 'S' is the group weight as seen by its parent.
+ *
+ * Therefore the effective change in loads on CPU 0 would be 5/56 (3/8 - 2/7)
+ * times the weight of the group. The effect on CPU 1 would be -4/56 (4/8 -
+ * 4/7) times the weight of the group.
  */
 static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
 {
 	struct sched_entity *se = tg->se[cpu];
 
-	if (!tg->parent)
+	if (!tg->parent)	/* the trivial, non-cgroup case */
 		return wl;
 
 	for_each_sched_entity(se) {
-		long lw, w;
+		long w, W;
 
 		tg = se->my_q->tg;
-		w = se->my_q->load.weight;
 
-		/* use this cpu's instantaneous contribution */
-		lw = atomic_read(&tg->load_weight);
-		lw -= se->my_q->load_contribution;
-		lw += w + wg;
+		/*
+		 * W = @wg + \Sum rw_j
+		 */
+		W = wg + calc_tg_weight(tg, se->my_q);
 
-		wl += w;
+		/*
+		 * w = rw_i + @wl
+		 */
+		w = se->my_q->load.weight + wl;
 
-		if (lw > 0 && wl < lw)
-			wl = (wl * tg->shares) / lw;
+		/*
+		 * wl = S * s'_i; see (2)
+		 */
+		if (W > 0 && w < W)
+			wl = (w * tg->shares) / W;
 		else
 			wl = tg->shares;
 
-		/* zero point is MIN_SHARES */
+		/*
+		 * Per the above, wl is the new se->load.weight value; since
+		 * those are clipped to [MIN_SHARES, ...) do so now. See
+		 * calc_cfs_shares().
+		 */
 		if (wl < MIN_SHARES)
 			wl = MIN_SHARES;
+
+		/*
+		 * wl = dw_i = S * (s'_i - s_i); see (3)
+		 */
 		wl -= se->load.weight;
+
+		/*
+		 * Recursively apply this logic to all parent groups to compute
+		 * the final effective load change on the root group. Since
+		 * only the @tg group gets extra weight, all parent groups can
+		 * only redistribute existing shares. @wl is the shift in shares
+		 * resulting from this level per the above.
+		 */
 		wg = 0;
 	}
 
@@ -2249,7 +2326,8 @@ static int select_idle_sibling(struct task_struct *p, int target)
 	int cpu = smp_processor_id();
 	int prev_cpu = task_cpu(p);
 	struct sched_domain *sd;
-	int i;
+	struct sched_group *sg;
+	int i, smt = 0;
 
 	/*
 	 * If the task is going to be woken-up on this cpu and if it is
@@ -2269,25 +2347,38 @@ static int select_idle_sibling(struct task_struct *p, int target)
 	 * Otherwise, iterate the domains and find an elegible idle cpu.
 	 */
 	rcu_read_lock();
+again:
 	for_each_domain(target, sd) {
-		if (!(sd->flags & SD_SHARE_PKG_RESOURCES))
-			break;
+		if (!smt && (sd->flags & SD_SHARE_CPUPOWER))
+			continue;
 
-		for_each_cpu_and(i, sched_domain_span(sd), tsk_cpus_allowed(p)) {
-			if (idle_cpu(i)) {
-				target = i;
-				break;
+		if (!(sd->flags & SD_SHARE_PKG_RESOURCES)) {
+			if (!smt) {
+				smt = 1;
+				goto again;
 			}
+			break;
 		}
 
-		/*
-		 * Lets stop looking for an idle sibling when we reached
-		 * the domain that spans the current cpu and prev_cpu.
-		 */
-		if (cpumask_test_cpu(cpu, sched_domain_span(sd)) &&
-		    cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
-			break;
+		sg = sd->groups;
+		do {
+			if (!cpumask_intersects(sched_group_cpus(sg),
+						tsk_cpus_allowed(p)))
+				goto next;
+
+			for_each_cpu(i, sched_group_cpus(sg)) {
+				if (!idle_cpu(i))
+					goto next;
+			}
+
+			target = cpumask_first_and(sched_group_cpus(sg),
+					tsk_cpus_allowed(p));
+			goto done;
+next:
+			sg = sg->next;
+		} while (sg != sd->groups);
 	}
+done:
 	rcu_read_unlock();
 
 	return target;
@@ -3511,7 +3602,7 @@ static bool update_sd_pick_busiest(struct sched_domain *sd,
 }
 
 /**
- * update_sd_lb_stats - Update sched_group's statistics for load balancing.
+ * update_sd_lb_stats - Update sched_domain's statistics for load balancing.
  * @sd: sched_domain whose statistics are to be updated.
  * @this_cpu: Cpu for which load balance is currently performed.
  * @idle: Idle status of this_cpu
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index efa0a7b..8480224 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -67,3 +67,4 @@ SCHED_FEAT(NONTASK_POWER, 1)
 SCHED_FEAT(TTWU_QUEUE, 1)
 
 SCHED_FEAT(FORCE_SD_OVERLAP, 0)
+SCHED_FEAT(RT_RUNTIME_SHARE, 1)
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 056cbd2..583a136 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -560,6 +560,9 @@ static int balance_runtime(struct rt_rq *rt_rq)
 {
 	int more = 0;
 
+	if (!sched_feat(RT_RUNTIME_SHARE))
+		return more;
+
 	if (rt_rq->rt_time > rt_rq->rt_runtime) {
 		raw_spin_unlock(&rt_rq->rt_runtime_lock);
 		more = do_balance_runtime(rt_rq);
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 1ecd6ba..c4eb71c 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -387,6 +387,7 @@ void clockevents_exchange_device(struct clock_event_device *old,
 	 * released list and do a notify add later.
 	 */
 	if (old) {
+		old->event_handler = clockevents_handle_noop;
 		clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED);
 		list_del(&old->list);
 		list_add(&old->list, &clockevents_released);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index cf52fda..da2f760 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -492,6 +492,22 @@ void clocksource_touch_watchdog(void)
 }
 
 /**
+ * clocksource_max_adjustment- Returns max adjustment amount
+ * @cs:         Pointer to clocksource
+ *
+ */
+static u32 clocksource_max_adjustment(struct clocksource *cs)
+{
+	u64 ret;
+	/*
+	 * We won't try to correct for more then 11% adjustments (110,000 ppm),
+	 */
+	ret = (u64)cs->mult * 11;
+	do_div(ret,100);
+	return (u32)ret;
+}
+
+/**
  * clocksource_max_deferment - Returns max time the clocksource can be deferred
  * @cs:         Pointer to clocksource
  *
@@ -503,25 +519,28 @@ static u64 clocksource_max_deferment(struct clocksource *cs)
 	/*
 	 * Calculate the maximum number of cycles that we can pass to the
 	 * cyc2ns function without overflowing a 64-bit signed result. The
-	 * maximum number of cycles is equal to ULLONG_MAX/cs->mult which
-	 * is equivalent to the below.
-	 * max_cycles < (2^63)/cs->mult
-	 * max_cycles < 2^(log2((2^63)/cs->mult))
-	 * max_cycles < 2^(log2(2^63) - log2(cs->mult))
-	 * max_cycles < 2^(63 - log2(cs->mult))
-	 * max_cycles < 1 << (63 - log2(cs->mult))
+	 * maximum number of cycles is equal to ULLONG_MAX/(cs->mult+cs->maxadj)
+	 * which is equivalent to the below.
+	 * max_cycles < (2^63)/(cs->mult + cs->maxadj)
+	 * max_cycles < 2^(log2((2^63)/(cs->mult + cs->maxadj)))
+	 * max_cycles < 2^(log2(2^63) - log2(cs->mult + cs->maxadj))
+	 * max_cycles < 2^(63 - log2(cs->mult + cs->maxadj))
+	 * max_cycles < 1 << (63 - log2(cs->mult + cs->maxadj))
 	 * Please note that we add 1 to the result of the log2 to account for
 	 * any rounding errors, ensure the above inequality is satisfied and
 	 * no overflow will occur.
 	 */
-	max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1));
+	max_cycles = 1ULL << (63 - (ilog2(cs->mult + cs->maxadj) + 1));
 
 	/*
 	 * The actual maximum number of cycles we can defer the clocksource is
 	 * determined by the minimum of max_cycles and cs->mask.
+	 * Note: Here we subtract the maxadj to make sure we don't sleep for
+	 * too long if there's a large negative adjustment.
 	 */
 	max_cycles = min_t(u64, max_cycles, (u64) cs->mask);
-	max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift);
+	max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult - cs->maxadj,
+					cs->shift);
 
 	/*
 	 * To ensure that the clocksource does not wrap whilst we are idle,
@@ -529,7 +548,7 @@ static u64 clocksource_max_deferment(struct clocksource *cs)
 	 * note a margin of 12.5% is used because this can be computed with
 	 * a shift, versus say 10% which would require division.
 	 */
-	return max_nsecs - (max_nsecs >> 5);
+	return max_nsecs - (max_nsecs >> 3);
 }
 
 #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET
@@ -640,7 +659,6 @@ static void clocksource_enqueue(struct clocksource *cs)
 void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 {
 	u64 sec;
-
 	/*
 	 * Calc the maximum number of seconds which we can run before
 	 * wrapping around. For clocksources which have a mask > 32bit
@@ -651,7 +669,7 @@ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 	 * ~ 0.06ppm granularity for NTP. We apply the same 12.5%
 	 * margin as we do in clocksource_max_deferment()
 	 */
-	sec = (cs->mask - (cs->mask >> 5));
+	sec = (cs->mask - (cs->mask >> 3));
 	do_div(sec, freq);
 	do_div(sec, scale);
 	if (!sec)
@@ -661,6 +679,20 @@ void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq)
 
 	clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
 			       NSEC_PER_SEC / scale, sec * scale);
+
+	/*
+	 * for clocksources that have large mults, to avoid overflow.
+	 * Since mult may be adjusted by ntp, add an safety extra margin
+	 *
+	 */
+	cs->maxadj = clocksource_max_adjustment(cs);
+	while ((cs->mult + cs->maxadj < cs->mult)
+		|| (cs->mult - cs->maxadj > cs->mult)) {
+		cs->mult >>= 1;
+		cs->shift--;
+		cs->maxadj = clocksource_max_adjustment(cs);
+	}
+
 	cs->max_idle_ns = clocksource_max_deferment(cs);
 }
 EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale);
@@ -701,6 +733,12 @@ EXPORT_SYMBOL_GPL(__clocksource_register_scale);
  */
 int clocksource_register(struct clocksource *cs)
 {
+	/* calculate max adjustment for given mult/shift */
+	cs->maxadj = clocksource_max_adjustment(cs);
+	WARN_ONCE(cs->mult + cs->maxadj < cs->mult,
+		"Clocksource %s might overflow on 11%% adjustment\n",
+		cs->name);
+
 	/* calculate max idle time permitted for this clocksource */
 	cs->max_idle_ns = clocksource_max_deferment(cs);
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index f954282..fd4a7b1 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -71,7 +71,7 @@ int tick_check_broadcast_device(struct clock_event_device *dev)
 	     (dev->features & CLOCK_EVT_FEAT_C3STOP))
 		return 0;
 
-	clockevents_exchange_device(NULL, dev);
+	clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
 	tick_broadcast_device.evtdev = dev;
 	if (!cpumask_empty(tick_get_broadcast_mask()))
 		tick_broadcast_start_periodic(dev);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 2b021b0e..2378413 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -249,6 +249,8 @@ ktime_t ktime_get(void)
 		secs = xtime.tv_sec + wall_to_monotonic.tv_sec;
 		nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec;
 		nsecs += timekeeping_get_ns();
+		/* If arch requires, add in gettimeoffset() */
+		nsecs += arch_gettimeoffset();
 
 	} while (read_seqretry(&xtime_lock, seq));
 	/*
@@ -280,6 +282,8 @@ void ktime_get_ts(struct timespec *ts)
 		*ts = xtime;
 		tomono = wall_to_monotonic;
 		nsecs = timekeeping_get_ns();
+		/* If arch requires, add in gettimeoffset() */
+		nsecs += arch_gettimeoffset();
 
 	} while (read_seqretry(&xtime_lock, seq));
 
@@ -802,14 +806,44 @@ static void timekeeping_adjust(s64 offset)
 	s64 error, interval = timekeeper.cycle_interval;
 	int adj;
 
+	/*
+	 * The point of this is to check if the error is greater then half
+	 * an interval.
+	 *
+	 * First we shift it down from NTP_SHIFT to clocksource->shifted nsecs.
+	 *
+	 * Note we subtract one in the shift, so that error is really error*2.
+	 * This "saves" dividing(shifting) intererval twice, but keeps the
+	 * (error > interval) comparision as still measuring if error is
+	 * larger then half an interval.
+	 *
+	 * Note: It does not "save" on aggrivation when reading the code.
+	 */
 	error = timekeeper.ntp_error >> (timekeeper.ntp_error_shift - 1);
 	if (error > interval) {
+		/*
+		 * We now divide error by 4(via shift), which checks if
+		 * the error is greater then twice the interval.
+		 * If it is greater, we need a bigadjust, if its smaller,
+		 * we can adjust by 1.
+		 */
 		error >>= 2;
+		/*
+		 * XXX - In update_wall_time, we round up to the next
+		 * nanosecond, and store the amount rounded up into
+		 * the error. This causes the likely below to be unlikely.
+		 *
+		 * The properfix is to avoid rounding up by using
+		 * the high precision timekeeper.xtime_nsec instead of
+		 * xtime.tv_nsec everywhere. Fixing this will take some
+		 * time.
+		 */
 		if (likely(error <= interval))
 			adj = 1;
 		else
 			adj = timekeeping_bigadjust(error, &interval, &offset);
 	} else if (error < -interval) {
+		/* See comment above, this is just switched for the negative */
 		error >>= 2;
 		if (likely(error >= -interval)) {
 			adj = -1;
@@ -817,9 +851,65 @@ static void timekeeping_adjust(s64 offset)
 			offset = -offset;
 		} else
 			adj = timekeeping_bigadjust(error, &interval, &offset);
-	} else
+	} else /* No adjustment needed */
 		return;
 
+	WARN_ONCE(timekeeper.clock->maxadj &&
+			(timekeeper.mult + adj > timekeeper.clock->mult +
+						timekeeper.clock->maxadj),
+			"Adjusting %s more then 11%% (%ld vs %ld)\n",
+			timekeeper.clock->name, (long)timekeeper.mult + adj,
+			(long)timekeeper.clock->mult +
+				timekeeper.clock->maxadj);
+	/*
+	 * So the following can be confusing.
+	 *
+	 * To keep things simple, lets assume adj == 1 for now.
+	 *
+	 * When adj != 1, remember that the interval and offset values
+	 * have been appropriately scaled so the math is the same.
+	 *
+	 * The basic idea here is that we're increasing the multiplier
+	 * by one, this causes the xtime_interval to be incremented by
+	 * one cycle_interval. This is because:
+	 *	xtime_interval = cycle_interval * mult
+	 * So if mult is being incremented by one:
+	 *	xtime_interval = cycle_interval * (mult + 1)
+	 * Its the same as:
+	 *	xtime_interval = (cycle_interval * mult) + cycle_interval
+	 * Which can be shortened to:
+	 *	xtime_interval += cycle_interval
+	 *
+	 * So offset stores the non-accumulated cycles. Thus the current
+	 * time (in shifted nanoseconds) is:
+	 *	now = (offset * adj) + xtime_nsec
+	 * Now, even though we're adjusting the clock frequency, we have
+	 * to keep time consistent. In other words, we can't jump back
+	 * in time, and we also want to avoid jumping forward in time.
+	 *
+	 * So given the same offset value, we need the time to be the same
+	 * both before and after the freq adjustment.
+	 *	now = (offset * adj_1) + xtime_nsec_1
+	 *	now = (offset * adj_2) + xtime_nsec_2
+	 * So:
+	 *	(offset * adj_1) + xtime_nsec_1 =
+	 *		(offset * adj_2) + xtime_nsec_2
+	 * And we know:
+	 *	adj_2 = adj_1 + 1
+	 * So:
+	 *	(offset * adj_1) + xtime_nsec_1 =
+	 *		(offset * (adj_1+1)) + xtime_nsec_2
+	 *	(offset * adj_1) + xtime_nsec_1 =
+	 *		(offset * adj_1) + offset + xtime_nsec_2
+	 * Canceling the sides:
+	 *	xtime_nsec_1 = offset + xtime_nsec_2
+	 * Which gives us:
+	 *	xtime_nsec_2 = xtime_nsec_1 - offset
+	 * Which simplfies to:
+	 *	xtime_nsec -= offset
+	 *
+	 * XXX - TODO: Doc ntp_error calculation.
+	 */
 	timekeeper.mult += adj;
 	timekeeper.xtime_interval += interval;
 	timekeeper.xtime_nsec -= offset;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 900b409..b1e8943 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -152,7 +152,6 @@ void clear_ftrace_function(void)
 	ftrace_pid_function = ftrace_stub;
 }
 
-#undef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 #ifndef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 /*
  * For those archs that do not test ftrace_trace_stop in their
@@ -1212,7 +1211,9 @@ ftrace_hash_move(struct ftrace_ops *ops, int enable,
 	if (!src->count) {
 		free_ftrace_hash_rcu(*dst);
 		rcu_assign_pointer(*dst, EMPTY_HASH);
-		return 0;
+		/* still need to update the function records */
+		ret = 0;
+		goto out;
 	}
 
 	/*
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 581876f..c212a7f 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1078,7 +1078,6 @@ event_subsystem_dir(const char *name, struct dentry *d_events)
 	/* First see if we did not already create this dir */
 	list_for_each_entry(system, &event_subsystems, list) {
 		if (strcmp(system->name, name) == 0) {
-			__get_system(system);
 			system->nr_events++;
 			return system->entry;
 		}
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 816d3d0..95dc31e 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1649,7 +1649,9 @@ static int replace_system_preds(struct event_subsystem *system,
 		 */
 		err = replace_preds(call, NULL, ps, filter_string, true);
 		if (err)
-			goto fail;
+			call->flags |= TRACE_EVENT_FL_NO_SET_FILTER;
+		else
+			call->flags &= ~TRACE_EVENT_FL_NO_SET_FILTER;
 	}
 
 	list_for_each_entry(call, &ftrace_events, list) {
@@ -1658,6 +1660,9 @@ static int replace_system_preds(struct event_subsystem *system,
 		if (strcmp(call->class->system, system->name) != 0)
 			continue;
 
+		if (call->flags & TRACE_EVENT_FL_NO_SET_FILTER)
+			continue;
+
 		filter_item = kzalloc(sizeof(*filter_item), GFP_KERNEL);
 		if (!filter_item)
 			goto fail_mem;
@@ -1686,7 +1691,7 @@ static int replace_system_preds(struct event_subsystem *system,
 		 * replace the filter for the call.
 		 */
 		filter = call->filter;
-		call->filter = filter_item->filter;
+		rcu_assign_pointer(call->filter, filter_item->filter);
 		filter_item->filter = filter;
 
 		fail = false;
@@ -1741,7 +1746,7 @@ int apply_event_filter(struct ftrace_event_call *call, char *filter_string)
 		filter = call->filter;
 		if (!filter)
 			goto out_unlock;
-		call->filter = NULL;
+		RCU_INIT_POINTER(call->filter, NULL);
 		/* Make sure the filter is not being used */
 		synchronize_sched();
 		__free_filter(filter);
@@ -1782,7 +1787,7 @@ out:
 	 * string
 	 */
 	tmp = call->filter;
-	call->filter = filter;
+	rcu_assign_pointer(call->filter, filter);
 	if (tmp) {
 		/* Make sure the call is done with the filter */
 		synchronize_sched();
diff --git a/lib/Kconfig b/lib/Kconfig
index 32f3e5a..63b5782 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -244,6 +244,9 @@ config CPU_RMAP
 	bool
 	depends on SMP
 
+config DQL
+	bool
+
 #
 # Netlink attribute parsing support is select'ed if needed
 #
diff --git a/lib/Makefile b/lib/Makefile
index a4da283..ff00d4d 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -115,6 +115,8 @@ obj-$(CONFIG_CPU_RMAP) += cpu_rmap.o
 
 obj-$(CONFIG_CORDIC) += cordic.o
 
+obj-$(CONFIG_DQL) += dynamic_queue_limits.o
+
 hostprogs-y	:= gen_crc32table
 clean-files	:= crc32table.h
 
diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c
new file mode 100644
index 0000000..3d1bdcd
--- /dev/null
+++ b/lib/dynamic_queue_limits.c
@@ -0,0 +1,133 @@
+/*
+ * Dynamic byte queue limits.  See include/linux/dynamic_queue_limits.h
+ *
+ * Copyright (c) 2011, Tom Herbert <therbert@google.com>
+ */
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/ctype.h>
+#include <linux/kernel.h>
+#include <linux/dynamic_queue_limits.h>
+
+#define POSDIFF(A, B) ((A) > (B) ? (A) - (B) : 0)
+
+/* Records completed count and recalculates the queue limit */
+void dql_completed(struct dql *dql, unsigned int count)
+{
+	unsigned int inprogress, prev_inprogress, limit;
+	unsigned int ovlimit, all_prev_completed, completed;
+
+	/* Can't complete more than what's in queue */
+	BUG_ON(count > dql->num_queued - dql->num_completed);
+
+	completed = dql->num_completed + count;
+	limit = dql->limit;
+	ovlimit = POSDIFF(dql->num_queued - dql->num_completed, limit);
+	inprogress = dql->num_queued - completed;
+	prev_inprogress = dql->prev_num_queued - dql->num_completed;
+	all_prev_completed = POSDIFF(completed, dql->prev_num_queued);
+
+	if ((ovlimit && !inprogress) ||
+	    (dql->prev_ovlimit && all_prev_completed)) {
+		/*
+		 * Queue considered starved if:
+		 *   - The queue was over-limit in the last interval,
+		 *     and there is no more data in the queue.
+		 *  OR
+		 *   - The queue was over-limit in the previous interval and
+		 *     when enqueuing it was possible that all queued data
+		 *     had been consumed.  This covers the case when queue
+		 *     may have becomes starved between completion processing
+		 *     running and next time enqueue was scheduled.
+		 *
+		 *     When queue is starved increase the limit by the amount
+		 *     of bytes both sent and completed in the last interval,
+		 *     plus any previous over-limit.
+		 */
+		limit += POSDIFF(completed, dql->prev_num_queued) +
+		     dql->prev_ovlimit;
+		dql->slack_start_time = jiffies;
+		dql->lowest_slack = UINT_MAX;
+	} else if (inprogress && prev_inprogress && !all_prev_completed) {
+		/*
+		 * Queue was not starved, check if the limit can be decreased.
+		 * A decrease is only considered if the queue has been busy in
+		 * the whole interval (the check above).
+		 *
+		 * If there is slack, the amount of execess data queued above
+		 * the the amount needed to prevent starvation, the queue limit
+		 * can be decreased.  To avoid hysteresis we consider the
+		 * minimum amount of slack found over several iterations of the
+		 * completion routine.
+		 */
+		unsigned int slack, slack_last_objs;
+
+		/*
+		 * Slack is the maximum of
+		 *   - The queue limit plus previous over-limit minus twice
+		 *     the number of objects completed.  Note that two times
+		 *     number of completed bytes is a basis for an upper bound
+		 *     of the limit.
+		 *   - Portion of objects in the last queuing operation that
+		 *     was not part of non-zero previous over-limit.  That is
+		 *     "round down" by non-overlimit portion of the last
+		 *     queueing operation.
+		 */
+		slack = POSDIFF(limit + dql->prev_ovlimit,
+		    2 * (completed - dql->num_completed));
+		slack_last_objs = dql->prev_ovlimit ?
+		    POSDIFF(dql->prev_last_obj_cnt, dql->prev_ovlimit) : 0;
+
+		slack = max(slack, slack_last_objs);
+
+		if (slack < dql->lowest_slack)
+			dql->lowest_slack = slack;
+
+		if (time_after(jiffies,
+			       dql->slack_start_time + dql->slack_hold_time)) {
+			limit = POSDIFF(limit, dql->lowest_slack);
+			dql->slack_start_time = jiffies;
+			dql->lowest_slack = UINT_MAX;
+		}
+	}
+
+	/* Enforce bounds on limit */
+	limit = clamp(limit, dql->min_limit, dql->max_limit);
+
+	if (limit != dql->limit) {
+		dql->limit = limit;
+		ovlimit = 0;
+	}
+
+	dql->adj_limit = limit + completed;
+	dql->prev_ovlimit = ovlimit;
+	dql->prev_last_obj_cnt = dql->last_obj_cnt;
+	dql->num_completed = completed;
+	dql->prev_num_queued = dql->num_queued;
+}
+EXPORT_SYMBOL(dql_completed);
+
+void dql_reset(struct dql *dql)
+{
+	/* Reset all dynamic values */
+	dql->limit = 0;
+	dql->num_queued = 0;
+	dql->num_completed = 0;
+	dql->last_obj_cnt = 0;
+	dql->prev_num_queued = 0;
+	dql->prev_last_obj_cnt = 0;
+	dql->prev_ovlimit = 0;
+	dql->lowest_slack = UINT_MAX;
+	dql->slack_start_time = jiffies;
+}
+EXPORT_SYMBOL(dql_reset);
+
+int dql_init(struct dql *dql, unsigned hold_time)
+{
+	dql->max_limit = DQL_MAX_LIMIT;
+	dql->min_limit = 0;
+	dql->slack_hold_time = hold_time;
+	dql_reset(dql);
+	return 0;
+}
+EXPORT_SYMBOL(dql_init);
diff --git a/lib/reciprocal_div.c b/lib/reciprocal_div.c
index 6a3bd48..75510e9 100644
--- a/lib/reciprocal_div.c
+++ b/lib/reciprocal_div.c
@@ -1,5 +1,6 @@
 #include <asm/div64.h>
 #include <linux/reciprocal_div.h>
+#include <linux/export.h>
 
 u32 reciprocal_value(u32 k)
 {
@@ -7,3 +8,4 @@ u32 reciprocal_value(u32 k)
 	do_div(val, k);
 	return (u32)val;
 }
+EXPORT_SYMBOL(reciprocal_value);
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 993599e..8e75003 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -777,6 +777,18 @@ char *uuid_string(char *buf, char *end, const u8 *addr,
 	return string(buf, end, uuid, spec);
 }
 
+static
+char *netdev_feature_string(char *buf, char *end, const u8 *addr,
+		      struct printf_spec spec)
+{
+	spec.flags |= SPECIAL | SMALL | ZEROPAD;
+	if (spec.field_width == -1)
+		spec.field_width = 2 + 2 * sizeof(netdev_features_t);
+	spec.base = 16;
+
+	return number(buf, end, *(const netdev_features_t *)addr, spec);
+}
+
 int kptr_restrict __read_mostly;
 
 /*
@@ -824,6 +836,7 @@ int kptr_restrict __read_mostly;
  *       Do not use this feature without some mechanism to verify the
  *       correctness of the format string and va_list arguments.
  * - 'K' For a kernel pointer that should be hidden from unprivileged users
+ * - 'NF' For a netdev_features_t
  *
  * Note: The difference between 'S' and 'F' is that on ia64 and ppc64
  * function pointers are really function descriptors, which contain a
@@ -896,6 +909,12 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		       has_capability_noaudit(current, CAP_SYSLOG))))
 			ptr = NULL;
 		break;
+	case 'N':
+		switch (fmt[1]) {
+		case 'F':
+			return netdev_feature_string(buf, end, ptr, spec);
+		}
+		break;
 	}
 	spec.flags |= SMALL;
 	if (spec.field_width == -1) {
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index a086064..71034f4 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -724,6 +724,14 @@ void bdi_destroy(struct backing_dev_info *bdi)
 
 	bdi_unregister(bdi);
 
+	/*
+	 * If bdi_unregister() had already been called earlier, the
+	 * wakeup_timer could still be armed because bdi_prune_sb()
+	 * can race with the bdi_wakeup_thread_delayed() calls from
+	 * __mark_inode_dirty().
+	 */
+	del_timer_sync(&bdi->wb.wakeup_timer);
+
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
 		percpu_counter_destroy(&bdi->bdi_stat[i]);
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index dae27ba..bb28a5f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2422,6 +2422,8 @@ retry_avoidcopy:
 	 * anon_vma prepared.
 	 */
 	if (unlikely(anon_vma_prepare(vma))) {
+		page_cache_release(new_page);
+		page_cache_release(old_page);
 		/* Caller expects lock to be held */
 		spin_lock(&mm->page_table_lock);
 		return VM_FAULT_OOM;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6aff93c..7266202 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -50,6 +50,8 @@
 #include <linux/cpu.h>
 #include <linux/oom.h>
 #include "internal.h"
+#include <net/sock.h>
+#include <net/tcp_memcontrol.h>
 
 #include <asm/uaccess.h>
 
@@ -227,6 +229,10 @@ struct mem_cgroup {
 	 */
 	struct res_counter memsw;
 	/*
+	 * the counter to account for kmem usage.
+	 */
+	struct res_counter kmem;
+	/*
 	 * Per cgroup active and inactive list, similar to the
 	 * per zone LRU lists.
 	 */
@@ -277,6 +283,11 @@ struct mem_cgroup {
 	 */
 	unsigned long 	move_charge_at_immigrate;
 	/*
+	 * Should kernel memory limits be stabilished independently
+	 * from user memory ?
+	 */
+	int		kmem_independent_accounting;
+	/*
 	 * percpu counter.
 	 */
 	struct mem_cgroup_stat_cpu *stat;
@@ -286,6 +297,10 @@ struct mem_cgroup {
 	 */
 	struct mem_cgroup_stat_cpu nocpu_base;
 	spinlock_t pcp_counter_lock;
+
+#ifdef CONFIG_INET
+	struct tcp_memcontrol tcp_mem;
+#endif
 };
 
 /* Stuffs for move charges at task migration. */
@@ -344,9 +359,14 @@ enum charge_type {
 };
 
 /* for encoding cft->private value on file */
-#define _MEM			(0)
-#define _MEMSWAP		(1)
-#define _OOM_TYPE		(2)
+
+enum mem_type {
+	_MEM = 0,
+	_MEMSWAP,
+	_OOM_TYPE,
+	_KMEM,
+};
+
 #define MEMFILE_PRIVATE(x, val)	(((x) << 16) | (val))
 #define MEMFILE_TYPE(val)	(((val) >> 16) & 0xffff)
 #define MEMFILE_ATTR(val)	((val) & 0xffff)
@@ -365,7 +385,58 @@ enum charge_type {
 
 static void mem_cgroup_get(struct mem_cgroup *memcg);
 static void mem_cgroup_put(struct mem_cgroup *memcg);
-static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
+
+/* Writing them here to avoid exposing memcg's inner layout */
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_INET
+#include <net/sock.h>
+#include <net/ip.h>
+
+static bool mem_cgroup_is_root(struct mem_cgroup *memcg);
+void sock_update_memcg(struct sock *sk)
+{
+	/* A socket spends its whole life in the same cgroup */
+	if (sk->sk_cgrp) {
+		WARN_ON(1);
+		return;
+	}
+	if (static_branch(&memcg_socket_limit_enabled)) {
+		struct mem_cgroup *memcg;
+
+		BUG_ON(!sk->sk_prot->proto_cgroup);
+
+		rcu_read_lock();
+		memcg = mem_cgroup_from_task(current);
+		if (!mem_cgroup_is_root(memcg)) {
+			mem_cgroup_get(memcg);
+			sk->sk_cgrp = sk->sk_prot->proto_cgroup(memcg);
+		}
+		rcu_read_unlock();
+	}
+}
+EXPORT_SYMBOL(sock_update_memcg);
+
+void sock_release_memcg(struct sock *sk)
+{
+	if (static_branch(&memcg_socket_limit_enabled) && sk->sk_cgrp) {
+		struct mem_cgroup *memcg;
+		WARN_ON(!sk->sk_cgrp->memcg);
+		memcg = sk->sk_cgrp->memcg;
+		mem_cgroup_put(memcg);
+	}
+}
+
+struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
+{
+	if (!memcg || mem_cgroup_is_root(memcg))
+		return NULL;
+
+	return &memcg->tcp_mem.cg_proto;
+}
+EXPORT_SYMBOL(tcp_proto_cgroup);
+#endif /* CONFIG_INET */
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
+
 static void drain_all_stock_async(struct mem_cgroup *memcg);
 
 static struct mem_cgroup_per_zone *
@@ -745,7 +816,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
 	preempt_enable();
 }
 
-static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
+struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
 {
 	return container_of(cgroup_subsys_state(cont,
 				mem_cgroup_subsys_id), struct mem_cgroup,
@@ -3848,10 +3919,17 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
 	u64 val;
 
 	if (!mem_cgroup_is_root(memcg)) {
+		val = 0;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+		if (!memcg->kmem_independent_accounting)
+			val = res_counter_read_u64(&memcg->kmem, RES_USAGE);
+#endif
 		if (!swap)
-			return res_counter_read_u64(&memcg->res, RES_USAGE);
+			val += res_counter_read_u64(&memcg->res, RES_USAGE);
 		else
-			return res_counter_read_u64(&memcg->memsw, RES_USAGE);
+			val += res_counter_read_u64(&memcg->memsw, RES_USAGE);
+
+		return val;
 	}
 
 	val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE);
@@ -3884,6 +3962,11 @@ static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
 		else
 			val = res_counter_read_u64(&memcg->memsw, name);
 		break;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+	case _KMEM:
+		val = res_counter_read_u64(&memcg->kmem, name);
+		break;
+#endif
 	default:
 		BUG();
 		break;
@@ -4612,6 +4695,89 @@ static int mem_control_numa_stat_open(struct inode *unused, struct file *file)
 }
 #endif /* CONFIG_NUMA */
 
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+static u64 kmem_limit_independent_read(struct cgroup *cgroup, struct cftype *cft)
+{
+	return mem_cgroup_from_cont(cgroup)->kmem_independent_accounting;
+}
+
+static int kmem_limit_independent_write(struct cgroup *cgroup, struct cftype *cft,
+					u64 val)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup);
+	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+
+	val = !!val;
+
+	/*
+	 * This follows the same hierarchy restrictions than
+	 * mem_cgroup_hierarchy_write()
+	 */
+	if (!parent || !parent->use_hierarchy) {
+		if (list_empty(&cgroup->children))
+			memcg->kmem_independent_accounting = val;
+		else
+			return -EBUSY;
+	}
+	else
+		return -EINVAL;
+
+	return 0;
+}
+static struct cftype kmem_cgroup_files[] = {
+	{
+		.name = "independent_kmem_limit",
+		.read_u64 = kmem_limit_independent_read,
+		.write_u64 = kmem_limit_independent_write,
+	},
+	{
+		.name = "kmem.usage_in_bytes",
+		.private = MEMFILE_PRIVATE(_KMEM, RES_USAGE),
+		.read_u64 = mem_cgroup_read,
+	},
+	{
+		.name = "kmem.limit_in_bytes",
+		.private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
+		.read_u64 = mem_cgroup_read,
+	},
+};
+
+static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+	int ret = 0;
+
+	ret = cgroup_add_files(cont, ss, kmem_cgroup_files,
+			       ARRAY_SIZE(kmem_cgroup_files));
+
+	/*
+	 * Part of this would be better living in a separate allocation
+	 * function, leaving us with just the cgroup tree population work.
+	 * We, however, depend on state such as network's proto_list that
+	 * is only initialized after cgroup creation. I found the less
+	 * cumbersome way to deal with it to defer it all to populate time
+	 */
+	if (!ret)
+		ret = mem_cgroup_sockets_init(cont, ss);
+	return ret;
+};
+
+static void kmem_cgroup_destroy(struct cgroup_subsys *ss,
+				struct cgroup *cont)
+{
+	mem_cgroup_sockets_destroy(cont, ss);
+}
+#else
+static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+	return 0;
+}
+
+static void kmem_cgroup_destroy(struct cgroup_subsys *ss,
+				struct cgroup *cont)
+{
+}
+#endif
+
 static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "usage_in_bytes",
@@ -4843,12 +5009,13 @@ static void mem_cgroup_put(struct mem_cgroup *memcg)
 /*
  * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled.
  */
-static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
+struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 {
 	if (!memcg->res.parent)
 		return NULL;
 	return mem_cgroup_from_res_counter(memcg->res.parent, res);
 }
+EXPORT_SYMBOL(parent_mem_cgroup);
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 static void __init enable_swap_cgroup(void)
@@ -4925,6 +5092,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	if (parent && parent->use_hierarchy) {
 		res_counter_init(&memcg->res, &parent->res);
 		res_counter_init(&memcg->memsw, &parent->memsw);
+		res_counter_init(&memcg->kmem, &parent->kmem);
 		/*
 		 * We increment refcnt of the parent to ensure that we can
 		 * safely access it on res_counter_charge/uncharge.
@@ -4935,6 +5103,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	} else {
 		res_counter_init(&memcg->res, NULL);
 		res_counter_init(&memcg->memsw, NULL);
+		res_counter_init(&memcg->kmem, NULL);
 	}
 	memcg->last_scanned_child = 0;
 	memcg->last_scanned_node = MAX_NUMNODES;
@@ -4965,6 +5134,8 @@ static void mem_cgroup_destroy(struct cgroup_subsys *ss,
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
+	kmem_cgroup_destroy(ss, cont);
+
 	mem_cgroup_put(memcg);
 }
 
@@ -4978,6 +5149,10 @@ static int mem_cgroup_populate(struct cgroup_subsys *ss,
 
 	if (!ret)
 		ret = register_memsw_files(cont, ss);
+
+	if (!ret)
+		ret = register_kmem_files(cont, ss);
+
 	return ret;
 }
 
diff --git a/mm/nommu.c b/mm/nommu.c
index 73419c5..b982290 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -454,7 +454,7 @@ void  __attribute__((weak)) vmalloc_sync_all(void)
  *	between processes, it syncs the pagetable across all
  *	processes.
  */
-struct vm_struct *alloc_vm_area(size_t size)
+struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
 {
 	BUG();
 	return NULL;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 471dedb..76f2c5a 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -185,6 +185,11 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 	if (!p)
 		return 0;
 
+	if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+		task_unlock(p);
+		return 0;
+	}
+
 	/*
 	 * The memory controller may have a limit of 0 bytes, so avoid a divide
 	 * by zero, if necessary.
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index a3278f0..7125248 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -128,7 +128,6 @@ unsigned long global_dirty_limit;
  *
  */
 static struct prop_descriptor vm_completions;
-static struct prop_descriptor vm_dirties;
 
 /*
  * couple the period to the dirty_ratio:
@@ -154,7 +153,6 @@ static void update_completion_period(void)
 {
 	int shift = calc_period_shift();
 	prop_change_shift(&vm_completions, shift);
-	prop_change_shift(&vm_dirties, shift);
 
 	writeback_set_ratelimit();
 }
@@ -235,11 +233,6 @@ void bdi_writeout_inc(struct backing_dev_info *bdi)
 }
 EXPORT_SYMBOL_GPL(bdi_writeout_inc);
 
-void task_dirty_inc(struct task_struct *tsk)
-{
-	prop_inc_single(&vm_dirties, &tsk->dirties);
-}
-
 /*
  * Obtain an accurate fraction of the BDI's portion.
  */
@@ -1133,17 +1126,17 @@ pause:
 					  pages_dirtied,
 					  pause,
 					  start_time);
-		__set_current_state(TASK_UNINTERRUPTIBLE);
+		__set_current_state(TASK_KILLABLE);
 		io_schedule_timeout(pause);
 
-		dirty_thresh = hard_dirty_limit(dirty_thresh);
 		/*
-		 * max-pause area. If dirty exceeded but still within this
-		 * area, no need to sleep for more than 200ms: (a) 8 pages per
-		 * 200ms is typically more than enough to curb heavy dirtiers;
-		 * (b) the pause time limit makes the dirtiers more responsive.
+		 * This is typically equal to (nr_dirty < dirty_thresh) and can
+		 * also keep "1000+ dd on a slow USB stick" under control.
 		 */
-		if (nr_dirty < dirty_thresh)
+		if (task_ratelimit)
+			break;
+
+		if (fatal_signal_pending(current))
 			break;
 	}
 
@@ -1395,7 +1388,6 @@ void __init page_writeback_init(void)
 
 	shift = calc_period_shift();
 	prop_descriptor_init(&vm_completions, shift);
-	prop_descriptor_init(&vm_dirties, shift);
 }
 
 /**
@@ -1724,7 +1716,6 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 		__inc_zone_page_state(page, NR_DIRTIED);
 		__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
 		__inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
-		task_dirty_inc(current);
 		task_io_account_write(PAGE_CACHE_SIZE);
 	}
 }
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index ea53496..12a48a88 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -50,14 +50,13 @@ static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk,
 
 	if (!pages || !bitmap) {
 		if (may_alloc && !pages)
-			pages = pcpu_mem_alloc(pages_size);
+			pages = pcpu_mem_zalloc(pages_size);
 		if (may_alloc && !bitmap)
-			bitmap = pcpu_mem_alloc(bitmap_size);
+			bitmap = pcpu_mem_zalloc(bitmap_size);
 		if (!pages || !bitmap)
 			return NULL;
 	}
 
-	memset(pages, 0, pages_size);
 	bitmap_copy(bitmap, chunk->populated, pcpu_unit_pages);
 
 	*bitmapp = bitmap;
@@ -143,8 +142,8 @@ static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk,
 				 int page_start, int page_end)
 {
 	flush_cache_vunmap(
-		pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
-		pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
+		pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+		pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
 }
 
 static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
@@ -206,8 +205,8 @@ static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk,
 				      int page_start, int page_end)
 {
 	flush_tlb_kernel_range(
-		pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
-		pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
+		pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+		pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
 }
 
 static int __pcpu_map_pages(unsigned long addr, struct page **pages,
@@ -284,8 +283,8 @@ static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
 				int page_start, int page_end)
 {
 	flush_cache_vmap(
-		pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
-		pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
+		pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+		pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
 }
 
 /**
diff --git a/mm/percpu.c b/mm/percpu.c
index bf80e55..3bb810a 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -116,9 +116,9 @@ static int pcpu_atom_size __read_mostly;
 static int pcpu_nr_slots __read_mostly;
 static size_t pcpu_chunk_struct_size __read_mostly;
 
-/* cpus with the lowest and highest unit numbers */
-static unsigned int pcpu_first_unit_cpu __read_mostly;
-static unsigned int pcpu_last_unit_cpu __read_mostly;
+/* cpus with the lowest and highest unit addresses */
+static unsigned int pcpu_low_unit_cpu __read_mostly;
+static unsigned int pcpu_high_unit_cpu __read_mostly;
 
 /* the address of the first chunk which starts with the kernel static area */
 void *pcpu_base_addr __read_mostly;
@@ -273,11 +273,11 @@ static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk,
 	     (rs) = (re) + 1, pcpu_next_pop((chunk), &(rs), &(re), (end)))
 
 /**
- * pcpu_mem_alloc - allocate memory
+ * pcpu_mem_zalloc - allocate memory
  * @size: bytes to allocate
  *
  * Allocate @size bytes.  If @size is smaller than PAGE_SIZE,
- * kzalloc() is used; otherwise, vmalloc() is used.  The returned
+ * kzalloc() is used; otherwise, vzalloc() is used.  The returned
  * memory is always zeroed.
  *
  * CONTEXT:
@@ -286,7 +286,7 @@ static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk,
  * RETURNS:
  * Pointer to the allocated area on success, NULL on failure.
  */
-static void *pcpu_mem_alloc(size_t size)
+static void *pcpu_mem_zalloc(size_t size)
 {
 	if (WARN_ON_ONCE(!slab_is_available()))
 		return NULL;
@@ -302,7 +302,7 @@ static void *pcpu_mem_alloc(size_t size)
  * @ptr: memory to free
  * @size: size of the area
  *
- * Free @ptr.  @ptr should have been allocated using pcpu_mem_alloc().
+ * Free @ptr.  @ptr should have been allocated using pcpu_mem_zalloc().
  */
 static void pcpu_mem_free(void *ptr, size_t size)
 {
@@ -384,7 +384,7 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
 	size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
 	unsigned long flags;
 
-	new = pcpu_mem_alloc(new_size);
+	new = pcpu_mem_zalloc(new_size);
 	if (!new)
 		return -ENOMEM;
 
@@ -604,11 +604,12 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
 {
 	struct pcpu_chunk *chunk;
 
-	chunk = pcpu_mem_alloc(pcpu_chunk_struct_size);
+	chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size);
 	if (!chunk)
 		return NULL;
 
-	chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0]));
+	chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC *
+						sizeof(chunk->map[0]));
 	if (!chunk->map) {
 		kfree(chunk);
 		return NULL;
@@ -977,6 +978,17 @@ bool is_kernel_percpu_address(unsigned long addr)
  * address.  The caller is responsible for ensuring @addr stays valid
  * until this function finishes.
  *
+ * percpu allocator has special setup for the first chunk, which currently
+ * supports either embedding in linear address space or vmalloc mapping,
+ * and, from the second one, the backing allocator (currently either vm or
+ * km) provides translation.
+ *
+ * The addr can be tranlated simply without checking if it falls into the
+ * first chunk. But the current code reflects better how percpu allocator
+ * actually works, and the verification can discover both bugs in percpu
+ * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current
+ * code.
+ *
  * RETURNS:
  * The physical address for @addr.
  */
@@ -984,19 +996,19 @@ phys_addr_t per_cpu_ptr_to_phys(void *addr)
 {
 	void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
 	bool in_first_chunk = false;
-	unsigned long first_start, first_end;
+	unsigned long first_low, first_high;
 	unsigned int cpu;
 
 	/*
-	 * The following test on first_start/end isn't strictly
+	 * The following test on unit_low/high isn't strictly
 	 * necessary but will speed up lookups of addresses which
 	 * aren't in the first chunk.
 	 */
-	first_start = pcpu_chunk_addr(pcpu_first_chunk, pcpu_first_unit_cpu, 0);
-	first_end = pcpu_chunk_addr(pcpu_first_chunk, pcpu_last_unit_cpu,
-				    pcpu_unit_pages);
-	if ((unsigned long)addr >= first_start &&
-	    (unsigned long)addr < first_end) {
+	first_low = pcpu_chunk_addr(pcpu_first_chunk, pcpu_low_unit_cpu, 0);
+	first_high = pcpu_chunk_addr(pcpu_first_chunk, pcpu_high_unit_cpu,
+				     pcpu_unit_pages);
+	if ((unsigned long)addr >= first_low &&
+	    (unsigned long)addr < first_high) {
 		for_each_possible_cpu(cpu) {
 			void *start = per_cpu_ptr(base, cpu);
 
@@ -1233,7 +1245,9 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 
 	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
 		unit_map[cpu] = UINT_MAX;
-	pcpu_first_unit_cpu = NR_CPUS;
+
+	pcpu_low_unit_cpu = NR_CPUS;
+	pcpu_high_unit_cpu = NR_CPUS;
 
 	for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
 		const struct pcpu_group_info *gi = &ai->groups[group];
@@ -1253,9 +1267,13 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 			unit_map[cpu] = unit + i;
 			unit_off[cpu] = gi->base_offset + i * ai->unit_size;
 
-			if (pcpu_first_unit_cpu == NR_CPUS)
-				pcpu_first_unit_cpu = cpu;
-			pcpu_last_unit_cpu = cpu;
+			/* determine low/high unit_cpu */
+			if (pcpu_low_unit_cpu == NR_CPUS ||
+			    unit_off[cpu] < unit_off[pcpu_low_unit_cpu])
+				pcpu_low_unit_cpu = cpu;
+			if (pcpu_high_unit_cpu == NR_CPUS ||
+			    unit_off[cpu] > unit_off[pcpu_high_unit_cpu])
+				pcpu_high_unit_cpu = cpu;
 		}
 	}
 	pcpu_nr_units = unit;
@@ -1889,7 +1907,7 @@ void __init percpu_init_late(void)
 
 		BUILD_BUG_ON(size > PAGE_SIZE);
 
-		map = pcpu_mem_alloc(size);
+		map = pcpu_mem_zalloc(size);
 		BUG_ON(!map);
 
 		spin_lock_irqsave(&pcpu_lock, flags);
diff --git a/mm/slab.c b/mm/slab.c
index 708efe8..83311c9a 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -595,6 +595,7 @@ static enum {
 	PARTIAL_AC,
 	PARTIAL_L3,
 	EARLY,
+	LATE,
 	FULL
 } g_cpucache_up;
 
@@ -671,7 +672,7 @@ static void init_node_lock_keys(int q)
 {
 	struct cache_sizes *s = malloc_sizes;
 
-	if (g_cpucache_up != FULL)
+	if (g_cpucache_up < LATE)
 		return;
 
 	for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) {
@@ -1666,6 +1667,8 @@ void __init kmem_cache_init_late(void)
 {
 	struct kmem_cache *cachep;
 
+	g_cpucache_up = LATE;
+
 	/* Annotate slab for lockdep -- annotate the malloc caches */
 	init_lock_keys();
 
diff --git a/mm/slub.c b/mm/slub.c
index 7d2a996..ed3334d 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1862,7 +1862,7 @@ static void unfreeze_partials(struct kmem_cache *s)
 {
 	struct kmem_cache_node *n = NULL;
 	struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab);
-	struct page *page;
+	struct page *page, *discard_page = NULL;
 
 	while ((page = c->partial)) {
 		enum slab_modes { M_PARTIAL, M_FREE };
@@ -1904,7 +1904,8 @@ static void unfreeze_partials(struct kmem_cache *s)
 				if (l == M_PARTIAL)
 					remove_partial(n, page);
 				else
-					add_partial(n, page, 1);
+					add_partial(n, page,
+						DEACTIVATE_TO_TAIL);
 
 				l = m;
 			}
@@ -1915,14 +1916,22 @@ static void unfreeze_partials(struct kmem_cache *s)
 				"unfreezing slab"));
 
 		if (m == M_FREE) {
-			stat(s, DEACTIVATE_EMPTY);
-			discard_slab(s, page);
-			stat(s, FREE_SLAB);
+			page->next = discard_page;
+			discard_page = page;
 		}
 	}
 
 	if (n)
 		spin_unlock(&n->list_lock);
+
+	while (discard_page) {
+		page = discard_page;
+		discard_page = discard_page->next;
+
+		stat(s, DEACTIVATE_EMPTY);
+		discard_slab(s, page);
+		stat(s, FREE_SLAB);
+	}
 }
 
 /*
@@ -1969,7 +1978,7 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 		page->pobjects = pobjects;
 		page->next = oldpage;
 
-	} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
+	} while (irqsafe_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
 	stat(s, CPU_PARTIAL_FREE);
 	return pobjects;
 }
@@ -4435,30 +4444,31 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 
 		for_each_possible_cpu(cpu) {
 			struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
+			int node = ACCESS_ONCE(c->node);
 			struct page *page;
 
-			if (!c || c->node < 0)
+			if (node < 0)
 				continue;
-
-			if (c->page) {
-					if (flags & SO_TOTAL)
-						x = c->page->objects;
+			page = ACCESS_ONCE(c->page);
+			if (page) {
+				if (flags & SO_TOTAL)
+					x = page->objects;
 				else if (flags & SO_OBJECTS)
-					x = c->page->inuse;
+					x = page->inuse;
 				else
 					x = 1;
 
 				total += x;
-				nodes[c->node] += x;
+				nodes[node] += x;
 			}
 			page = c->partial;
 
 			if (page) {
 				x = page->pobjects;
-                                total += x;
-                                nodes[c->node] += x;
+				total += x;
+				nodes[node] += x;
 			}
-			per_cpu[c->node]++;
+			per_cpu[node]++;
 		}
 	}
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index b669aa6..3231bf3 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2141,23 +2141,30 @@ void  __attribute__((weak)) vmalloc_sync_all(void)
 
 static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data)
 {
-	/* apply_to_page_range() does all the hard work. */
+	pte_t ***p = data;
+
+	if (p) {
+		*(*p) = pte;
+		(*p)++;
+	}
 	return 0;
 }
 
 /**
  *	alloc_vm_area - allocate a range of kernel address space
  *	@size:		size of the area
+ *	@ptes:		returns the PTEs for the address space
  *
  *	Returns:	NULL on failure, vm_struct on success
  *
  *	This function reserves a range of kernel address space, and
  *	allocates pagetables to map that range.  No actual mappings
- *	are created.  If the kernel address space is not shared
- *	between processes, it syncs the pagetable across all
- *	processes.
+ *	are created.
+ *
+ *	If @ptes is non-NULL, pointers to the PTEs (in init_mm)
+ *	allocated for the VM area are returned.
  */
-struct vm_struct *alloc_vm_area(size_t size)
+struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
 {
 	struct vm_struct *area;
 
@@ -2171,19 +2178,11 @@ struct vm_struct *alloc_vm_area(size_t size)
 	 * of kernel virtual address space and mapped into init_mm.
 	 */
 	if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
-				area->size, f, NULL)) {
+				size, f, ptes ? &ptes : NULL)) {
 		free_vm_area(area);
 		return NULL;
 	}
 
-	/*
-	 * If the allocated address space is passed to a hypercall
-	 * before being used then we cannot rely on a page fault to
-	 * trigger an update of the page tables.  So sync all the page
-	 * tables here.
-	 */
-	vmalloc_sync_all();
-
 	return area;
 }
 EXPORT_SYMBOL_GPL(alloc_vm_area);
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 5471628..efea35b 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -51,27 +51,6 @@ const char vlan_version[] = DRV_VERSION;
 
 /* End of global variables definitions. */
 
-static void vlan_group_free(struct vlan_group *grp)
-{
-	int i;
-
-	for (i = 0; i < VLAN_GROUP_ARRAY_SPLIT_PARTS; i++)
-		kfree(grp->vlan_devices_arrays[i]);
-	kfree(grp);
-}
-
-static struct vlan_group *vlan_group_alloc(struct net_device *real_dev)
-{
-	struct vlan_group *grp;
-
-	grp = kzalloc(sizeof(struct vlan_group), GFP_KERNEL);
-	if (!grp)
-		return NULL;
-
-	grp->real_dev = real_dev;
-	return grp;
-}
-
 static int vlan_group_prealloc_vid(struct vlan_group *vg, u16 vlan_id)
 {
 	struct net_device **array;
@@ -92,32 +71,29 @@ static int vlan_group_prealloc_vid(struct vlan_group *vg, u16 vlan_id)
 	return 0;
 }
 
-static void vlan_rcu_free(struct rcu_head *rcu)
-{
-	vlan_group_free(container_of(rcu, struct vlan_group, rcu));
-}
-
 void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
 {
-	struct vlan_dev_info *vlan = vlan_dev_info(dev);
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct net_device *real_dev = vlan->real_dev;
-	const struct net_device_ops *ops = real_dev->netdev_ops;
+	struct vlan_info *vlan_info;
 	struct vlan_group *grp;
 	u16 vlan_id = vlan->vlan_id;
 
 	ASSERT_RTNL();
 
-	grp = rtnl_dereference(real_dev->vlgrp);
-	BUG_ON(!grp);
+	vlan_info = rtnl_dereference(real_dev->vlan_info);
+	BUG_ON(!vlan_info);
+
+	grp = &vlan_info->grp;
 
 	/* Take it out of our own structures, but be sure to interlock with
 	 * HW accelerating devices or SW vlan input packet processing if
 	 * VLAN is not 0 (leave it there for 802.1p).
 	 */
-	if (vlan_id && (real_dev->features & NETIF_F_HW_VLAN_FILTER))
-		ops->ndo_vlan_rx_kill_vid(real_dev, vlan_id);
+	if (vlan_id)
+		vlan_vid_del(real_dev, vlan_id);
 
-	grp->nr_vlans--;
+	grp->nr_vlan_devs--;
 
 	if (vlan->flags & VLAN_FLAG_GVRP)
 		vlan_gvrp_request_leave(dev);
@@ -129,16 +105,9 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
 	 */
 	unregister_netdevice_queue(dev, head);
 
-	/* If the group is now empty, kill off the group. */
-	if (grp->nr_vlans == 0) {
+	if (grp->nr_vlan_devs == 0)
 		vlan_gvrp_uninit_applicant(real_dev);
 
-		RCU_INIT_POINTER(real_dev->vlgrp, NULL);
-
-		/* Free the group, after all cpu's are done. */
-		call_rcu(&grp->rcu, vlan_rcu_free);
-	}
-
 	/* Get rid of the vlan's reference to real_dev */
 	dev_put(real_dev);
 }
@@ -167,21 +136,26 @@ int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id)
 
 int register_vlan_dev(struct net_device *dev)
 {
-	struct vlan_dev_info *vlan = vlan_dev_info(dev);
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct net_device *real_dev = vlan->real_dev;
-	const struct net_device_ops *ops = real_dev->netdev_ops;
 	u16 vlan_id = vlan->vlan_id;
-	struct vlan_group *grp, *ngrp = NULL;
+	struct vlan_info *vlan_info;
+	struct vlan_group *grp;
 	int err;
 
-	grp = rtnl_dereference(real_dev->vlgrp);
-	if (!grp) {
-		ngrp = grp = vlan_group_alloc(real_dev);
-		if (!grp)
-			return -ENOBUFS;
+	err = vlan_vid_add(real_dev, vlan_id);
+	if (err)
+		return err;
+
+	vlan_info = rtnl_dereference(real_dev->vlan_info);
+	/* vlan_info should be there now. vlan_vid_add took care of it */
+	BUG_ON(!vlan_info);
+
+	grp = &vlan_info->grp;
+	if (grp->nr_vlan_devs == 0) {
 		err = vlan_gvrp_init_applicant(real_dev);
 		if (err < 0)
-			goto out_free_group;
+			goto out_vid_del;
 	}
 
 	err = vlan_group_prealloc_vid(grp, vlan_id);
@@ -192,7 +166,7 @@ int register_vlan_dev(struct net_device *dev)
 	if (err < 0)
 		goto out_uninit_applicant;
 
-	/* Account for reference in struct vlan_dev_info */
+	/* Account for reference in struct vlan_dev_priv */
 	dev_hold(real_dev);
 
 	netif_stacked_transfer_operstate(real_dev, dev);
@@ -202,24 +176,15 @@ int register_vlan_dev(struct net_device *dev)
 	 * it into our local structure.
 	 */
 	vlan_group_set_device(grp, vlan_id, dev);
-	grp->nr_vlans++;
-
-	if (ngrp) {
-		rcu_assign_pointer(real_dev->vlgrp, ngrp);
-	}
-	if (real_dev->features & NETIF_F_HW_VLAN_FILTER)
-		ops->ndo_vlan_rx_add_vid(real_dev, vlan_id);
+	grp->nr_vlan_devs++;
 
 	return 0;
 
 out_uninit_applicant:
-	if (ngrp)
+	if (grp->nr_vlan_devs == 0)
 		vlan_gvrp_uninit_applicant(real_dev);
-out_free_group:
-	if (ngrp) {
-		/* Free the group, after all cpu's are done. */
-		call_rcu(&ngrp->rcu, vlan_rcu_free);
-	}
+out_vid_del:
+	vlan_vid_del(real_dev, vlan_id);
 	return err;
 }
 
@@ -267,7 +232,7 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
 		snprintf(name, IFNAMSIZ, "vlan%.4i", vlan_id);
 	}
 
-	new_dev = alloc_netdev(sizeof(struct vlan_dev_info), name, vlan_setup);
+	new_dev = alloc_netdev(sizeof(struct vlan_dev_priv), name, vlan_setup);
 
 	if (new_dev == NULL)
 		return -ENOBUFS;
@@ -278,10 +243,10 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
 	 */
 	new_dev->mtu = real_dev->mtu;
 
-	vlan_dev_info(new_dev)->vlan_id = vlan_id;
-	vlan_dev_info(new_dev)->real_dev = real_dev;
-	vlan_dev_info(new_dev)->dent = NULL;
-	vlan_dev_info(new_dev)->flags = VLAN_FLAG_REORDER_HDR;
+	vlan_dev_priv(new_dev)->vlan_id = vlan_id;
+	vlan_dev_priv(new_dev)->real_dev = real_dev;
+	vlan_dev_priv(new_dev)->dent = NULL;
+	vlan_dev_priv(new_dev)->flags = VLAN_FLAG_REORDER_HDR;
 
 	new_dev->rtnl_link_ops = &vlan_link_ops;
 	err = register_vlan_dev(new_dev);
@@ -298,7 +263,7 @@ out_free_newdev:
 static void vlan_sync_address(struct net_device *dev,
 			      struct net_device *vlandev)
 {
-	struct vlan_dev_info *vlan = vlan_dev_info(vlandev);
+	struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
 
 	/* May be called without an actual change */
 	if (!compare_ether_addr(vlan->real_dev_addr, dev->dev_addr))
@@ -360,25 +325,26 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 {
 	struct net_device *dev = ptr;
 	struct vlan_group *grp;
+	struct vlan_info *vlan_info;
 	int i, flgs;
 	struct net_device *vlandev;
-	struct vlan_dev_info *vlan;
+	struct vlan_dev_priv *vlan;
 	LIST_HEAD(list);
 
 	if (is_vlan_dev(dev))
 		__vlan_device_event(dev, event);
 
 	if ((event == NETDEV_UP) &&
-	    (dev->features & NETIF_F_HW_VLAN_FILTER) &&
-	    dev->netdev_ops->ndo_vlan_rx_add_vid) {
+	    (dev->features & NETIF_F_HW_VLAN_FILTER)) {
 		pr_info("adding VLAN 0 to HW filter on device %s\n",
 			dev->name);
-		dev->netdev_ops->ndo_vlan_rx_add_vid(dev, 0);
+		vlan_vid_add(dev, 0);
 	}
 
-	grp = rtnl_dereference(dev->vlgrp);
-	if (!grp)
+	vlan_info = rtnl_dereference(dev->vlan_info);
+	if (!vlan_info)
 		goto out;
+	grp = &vlan_info->grp;
 
 	/* It is OK that we do not hold the group lock right now,
 	 * as we run under the RTNL lock.
@@ -447,7 +413,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 			if (!(flgs & IFF_UP))
 				continue;
 
-			vlan = vlan_dev_info(vlandev);
+			vlan = vlan_dev_priv(vlandev);
 			if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING))
 				dev_change_flags(vlandev, flgs & ~IFF_UP);
 			netif_stacked_transfer_operstate(dev, vlandev);
@@ -465,7 +431,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 			if (flgs & IFF_UP)
 				continue;
 
-			vlan = vlan_dev_info(vlandev);
+			vlan = vlan_dev_priv(vlandev);
 			if (!(vlan->flags & VLAN_FLAG_LOOSE_BINDING))
 				dev_change_flags(vlandev, flgs | IFF_UP);
 			netif_stacked_transfer_operstate(dev, vlandev);
@@ -482,9 +448,9 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 			if (!vlandev)
 				continue;
 
-			/* unregistration of last vlan destroys group, abort
+			/* removal of last vid destroys vlan_info, abort
 			 * afterwards */
-			if (grp->nr_vlans == 1)
+			if (vlan_info->nr_vids == 1)
 				i = VLAN_N_VID;
 
 			unregister_vlan_dev(vlandev, &list);
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index 9fd45f3..a4886d9 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -3,6 +3,7 @@
 
 #include <linux/if_vlan.h>
 #include <linux/u64_stats_sync.h>
+#include <linux/list.h>
 
 
 /**
@@ -40,8 +41,10 @@ struct vlan_pcpu_stats {
 	u32			tx_dropped;
 };
 
+struct netpoll;
+
 /**
- *	struct vlan_dev_info - VLAN private device data
+ *	struct vlan_dev_priv - VLAN private device data
  *	@nr_ingress_mappings: number of ingress priority mappings
  *	@ingress_priority_map: ingress priority mappings
  *	@nr_egress_mappings: number of egress priority mappings
@@ -53,7 +56,7 @@ struct vlan_pcpu_stats {
  *	@dent: proc dir entry
  *	@vlan_pcpu_stats: ptr to percpu rx stats
  */
-struct vlan_dev_info {
+struct vlan_dev_priv {
 	unsigned int				nr_ingress_mappings;
 	u32					ingress_priority_map[8];
 	unsigned int				nr_egress_mappings;
@@ -67,13 +70,39 @@ struct vlan_dev_info {
 
 	struct proc_dir_entry			*dent;
 	struct vlan_pcpu_stats __percpu		*vlan_pcpu_stats;
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	struct netpoll				*netpoll;
+#endif
 };
 
-static inline struct vlan_dev_info *vlan_dev_info(const struct net_device *dev)
+static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev)
 {
 	return netdev_priv(dev);
 }
 
+/* if this changes, algorithm will have to be reworked because this
+ * depends on completely exhausting the VLAN identifier space.  Thus
+ * it gives constant time look-up, but in many cases it wastes memory.
+ */
+#define VLAN_GROUP_ARRAY_SPLIT_PARTS  8
+#define VLAN_GROUP_ARRAY_PART_LEN     (VLAN_N_VID/VLAN_GROUP_ARRAY_SPLIT_PARTS)
+
+struct vlan_group {
+	unsigned int		nr_vlan_devs;
+	struct hlist_node	hlist;	/* linked list */
+	struct net_device **vlan_devices_arrays[VLAN_GROUP_ARRAY_SPLIT_PARTS];
+};
+
+struct vlan_info {
+	struct net_device	*real_dev; /* The ethernet(like) device
+					    * the vlan is attached to.
+					    */
+	struct vlan_group	grp;
+	struct list_head	vid_list;
+	unsigned int		nr_vids;
+	struct rcu_head		rcu;
+};
+
 static inline struct net_device *vlan_group_get_device(struct vlan_group *vg,
 						       u16 vlan_id)
 {
@@ -97,10 +126,10 @@ static inline void vlan_group_set_device(struct vlan_group *vg,
 static inline struct net_device *vlan_find_dev(struct net_device *real_dev,
 					       u16 vlan_id)
 {
-	struct vlan_group *grp = rcu_dereference_rtnl(real_dev->vlgrp);
+	struct vlan_info *vlan_info = rcu_dereference_rtnl(real_dev->vlan_info);
 
-	if (grp)
-		return vlan_group_get_device(grp, vlan_id);
+	if (vlan_info)
+		return vlan_group_get_device(&vlan_info->grp, vlan_id);
 
 	return NULL;
 }
@@ -121,7 +150,7 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head);
 static inline u32 vlan_get_ingress_priority(struct net_device *dev,
 					    u16 vlan_tci)
 {
-	struct vlan_dev_info *vip = vlan_dev_info(dev);
+	struct vlan_dev_priv *vip = vlan_dev_priv(dev);
 
 	return vip->ingress_priority_map[(vlan_tci >> VLAN_PRIO_SHIFT) & 0x7];
 }
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index f5ffc02..4d39d80 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -36,7 +36,7 @@ bool vlan_do_receive(struct sk_buff **skbp, bool last_handler)
 			skb->pkt_type = PACKET_HOST;
 	}
 
-	if (!(vlan_dev_info(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR)) {
+	if (!(vlan_dev_priv(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR)) {
 		unsigned int offset = skb->data - skb_mac_header(skb);
 
 		/*
@@ -55,7 +55,7 @@ bool vlan_do_receive(struct sk_buff **skbp, bool last_handler)
 	skb->priority = vlan_get_ingress_priority(vlan_dev, skb->vlan_tci);
 	skb->vlan_tci = 0;
 
-	rx_stats = this_cpu_ptr(vlan_dev_info(vlan_dev)->vlan_pcpu_stats);
+	rx_stats = this_cpu_ptr(vlan_dev_priv(vlan_dev)->vlan_pcpu_stats);
 
 	u64_stats_update_begin(&rx_stats->syncp);
 	rx_stats->rx_packets++;
@@ -71,10 +71,10 @@ bool vlan_do_receive(struct sk_buff **skbp, bool last_handler)
 struct net_device *__vlan_find_dev_deep(struct net_device *real_dev,
 					u16 vlan_id)
 {
-	struct vlan_group *grp = rcu_dereference_rtnl(real_dev->vlgrp);
+	struct vlan_info *vlan_info = rcu_dereference_rtnl(real_dev->vlan_info);
 
-	if (grp) {
-		return vlan_group_get_device(grp, vlan_id);
+	if (vlan_info) {
+		return vlan_group_get_device(&vlan_info->grp, vlan_id);
 	} else {
 		/*
 		 * Bonding slaves do not have grp assigned to themselves.
@@ -90,13 +90,13 @@ EXPORT_SYMBOL(__vlan_find_dev_deep);
 
 struct net_device *vlan_dev_real_dev(const struct net_device *dev)
 {
-	return vlan_dev_info(dev)->real_dev;
+	return vlan_dev_priv(dev)->real_dev;
 }
 EXPORT_SYMBOL(vlan_dev_real_dev);
 
 u16 vlan_dev_vlan_id(const struct net_device *dev)
 {
-	return vlan_dev_info(dev)->vlan_id;
+	return vlan_dev_priv(dev)->vlan_id;
 }
 EXPORT_SYMBOL(vlan_dev_vlan_id);
 
@@ -110,39 +110,6 @@ static struct sk_buff *vlan_reorder_header(struct sk_buff *skb)
 	return skb;
 }
 
-static void vlan_set_encap_proto(struct sk_buff *skb, struct vlan_hdr *vhdr)
-{
-	__be16 proto;
-	unsigned char *rawp;
-
-	/*
-	 * Was a VLAN packet, grab the encapsulated protocol, which the layer
-	 * three protocols care about.
-	 */
-
-	proto = vhdr->h_vlan_encapsulated_proto;
-	if (ntohs(proto) >= 1536) {
-		skb->protocol = proto;
-		return;
-	}
-
-	rawp = skb->data;
-	if (*(unsigned short *) rawp == 0xFFFF)
-		/*
-		 * This is a magic hack to spot IPX packets. Older Novell
-		 * breaks the protocol design and runs IPX over 802.3 without
-		 * an 802.2 LLC layer. We look for FFFF which isn't a used
-		 * 802.2 SSAP/DSAP. This won't work for fault tolerant netware
-		 * but does for the rest.
-		 */
-		skb->protocol = htons(ETH_P_802_3);
-	else
-		/*
-		 * Real 802.2 LLC
-		 */
-		skb->protocol = htons(ETH_P_802_2);
-}
-
 struct sk_buff *vlan_untag(struct sk_buff *skb)
 {
 	struct vlan_hdr *vhdr;
@@ -179,3 +146,226 @@ err_free:
 	kfree_skb(skb);
 	return NULL;
 }
+
+
+/*
+ * vlan info and vid list
+ */
+
+static void vlan_group_free(struct vlan_group *grp)
+{
+	int i;
+
+	for (i = 0; i < VLAN_GROUP_ARRAY_SPLIT_PARTS; i++)
+		kfree(grp->vlan_devices_arrays[i]);
+}
+
+static void vlan_info_free(struct vlan_info *vlan_info)
+{
+	vlan_group_free(&vlan_info->grp);
+	kfree(vlan_info);
+}
+
+static void vlan_info_rcu_free(struct rcu_head *rcu)
+{
+	vlan_info_free(container_of(rcu, struct vlan_info, rcu));
+}
+
+static struct vlan_info *vlan_info_alloc(struct net_device *dev)
+{
+	struct vlan_info *vlan_info;
+
+	vlan_info = kzalloc(sizeof(struct vlan_info), GFP_KERNEL);
+	if (!vlan_info)
+		return NULL;
+
+	vlan_info->real_dev = dev;
+	INIT_LIST_HEAD(&vlan_info->vid_list);
+	return vlan_info;
+}
+
+struct vlan_vid_info {
+	struct list_head list;
+	unsigned short vid;
+	int refcount;
+};
+
+static struct vlan_vid_info *vlan_vid_info_get(struct vlan_info *vlan_info,
+					       unsigned short vid)
+{
+	struct vlan_vid_info *vid_info;
+
+	list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+		if (vid_info->vid == vid)
+			return vid_info;
+	}
+	return NULL;
+}
+
+static struct vlan_vid_info *vlan_vid_info_alloc(unsigned short vid)
+{
+	struct vlan_vid_info *vid_info;
+
+	vid_info = kzalloc(sizeof(struct vlan_vid_info), GFP_KERNEL);
+	if (!vid_info)
+		return NULL;
+	vid_info->vid = vid;
+
+	return vid_info;
+}
+
+static int __vlan_vid_add(struct vlan_info *vlan_info, unsigned short vid,
+			  struct vlan_vid_info **pvid_info)
+{
+	struct net_device *dev = vlan_info->real_dev;
+	const struct net_device_ops *ops = dev->netdev_ops;
+	struct vlan_vid_info *vid_info;
+	int err;
+
+	vid_info = vlan_vid_info_alloc(vid);
+	if (!vid_info)
+		return -ENOMEM;
+
+	if ((dev->features & NETIF_F_HW_VLAN_FILTER) &&
+	    ops->ndo_vlan_rx_add_vid) {
+		err =  ops->ndo_vlan_rx_add_vid(dev, vid);
+		if (err) {
+			kfree(vid_info);
+			return err;
+		}
+	}
+	list_add(&vid_info->list, &vlan_info->vid_list);
+	vlan_info->nr_vids++;
+	*pvid_info = vid_info;
+	return 0;
+}
+
+int vlan_vid_add(struct net_device *dev, unsigned short vid)
+{
+	struct vlan_info *vlan_info;
+	struct vlan_vid_info *vid_info;
+	bool vlan_info_created = false;
+	int err;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(dev->vlan_info);
+	if (!vlan_info) {
+		vlan_info = vlan_info_alloc(dev);
+		if (!vlan_info)
+			return -ENOMEM;
+		vlan_info_created = true;
+	}
+	vid_info = vlan_vid_info_get(vlan_info, vid);
+	if (!vid_info) {
+		err = __vlan_vid_add(vlan_info, vid, &vid_info);
+		if (err)
+			goto out_free_vlan_info;
+	}
+	vid_info->refcount++;
+
+	if (vlan_info_created)
+		rcu_assign_pointer(dev->vlan_info, vlan_info);
+
+	return 0;
+
+out_free_vlan_info:
+	if (vlan_info_created)
+		kfree(vlan_info);
+	return err;
+}
+EXPORT_SYMBOL(vlan_vid_add);
+
+static void __vlan_vid_del(struct vlan_info *vlan_info,
+			   struct vlan_vid_info *vid_info)
+{
+	struct net_device *dev = vlan_info->real_dev;
+	const struct net_device_ops *ops = dev->netdev_ops;
+	unsigned short vid = vid_info->vid;
+	int err;
+
+	if ((dev->features & NETIF_F_HW_VLAN_FILTER) &&
+	     ops->ndo_vlan_rx_kill_vid) {
+		err = ops->ndo_vlan_rx_kill_vid(dev, vid);
+		if (err) {
+			pr_warn("failed to kill vid %d for device %s\n",
+				vid, dev->name);
+		}
+	}
+	list_del(&vid_info->list);
+	kfree(vid_info);
+	vlan_info->nr_vids--;
+}
+
+void vlan_vid_del(struct net_device *dev, unsigned short vid)
+{
+	struct vlan_info *vlan_info;
+	struct vlan_vid_info *vid_info;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(dev->vlan_info);
+	if (!vlan_info)
+		return;
+
+	vid_info = vlan_vid_info_get(vlan_info, vid);
+	if (!vid_info)
+		return;
+	vid_info->refcount--;
+	if (vid_info->refcount == 0) {
+		__vlan_vid_del(vlan_info, vid_info);
+		if (vlan_info->nr_vids == 0) {
+			RCU_INIT_POINTER(dev->vlan_info, NULL);
+			call_rcu(&vlan_info->rcu, vlan_info_rcu_free);
+		}
+	}
+}
+EXPORT_SYMBOL(vlan_vid_del);
+
+int vlan_vids_add_by_dev(struct net_device *dev,
+			 const struct net_device *by_dev)
+{
+	struct vlan_vid_info *vid_info;
+	struct vlan_info *vlan_info;
+	int err;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(by_dev->vlan_info);
+	if (!vlan_info)
+		return 0;
+
+	list_for_each_entry(vid_info, &vlan_info->vid_list, list) {
+		err = vlan_vid_add(dev, vid_info->vid);
+		if (err)
+			goto unwind;
+	}
+	return 0;
+
+unwind:
+	list_for_each_entry_continue_reverse(vid_info,
+					     &vlan_info->vid_list,
+					     list) {
+		vlan_vid_del(dev, vid_info->vid);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL(vlan_vids_add_by_dev);
+
+void vlan_vids_del_by_dev(struct net_device *dev,
+			  const struct net_device *by_dev)
+{
+	struct vlan_vid_info *vid_info;
+	struct vlan_info *vlan_info;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(by_dev->vlan_info);
+	if (!vlan_info)
+		return;
+
+	list_for_each_entry(vid_info, &vlan_info->vid_list, list)
+		vlan_vid_del(dev, vid_info->vid);
+}
+EXPORT_SYMBOL(vlan_vids_del_by_dev);
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index bc25286..9988d4a 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -33,6 +33,7 @@
 #include "vlan.h"
 #include "vlanproc.h"
 #include <linux/if_vlan.h>
+#include <linux/netpoll.h>
 
 /*
  *	Rebuild the Ethernet MAC header. This is called after an ARP
@@ -72,7 +73,7 @@ vlan_dev_get_egress_qos_mask(struct net_device *dev, struct sk_buff *skb)
 {
 	struct vlan_priority_tci_mapping *mp;
 
-	mp = vlan_dev_info(dev)->egress_priority_map[(skb->priority & 0xF)];
+	mp = vlan_dev_priv(dev)->egress_priority_map[(skb->priority & 0xF)];
 	while (mp) {
 		if (mp->priority == skb->priority) {
 			return mp->vlan_qos; /* This should already be shifted
@@ -103,10 +104,10 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev,
 	u16 vlan_tci = 0;
 	int rc;
 
-	if (!(vlan_dev_info(dev)->flags & VLAN_FLAG_REORDER_HDR)) {
+	if (!(vlan_dev_priv(dev)->flags & VLAN_FLAG_REORDER_HDR)) {
 		vhdr = (struct vlan_hdr *) skb_push(skb, VLAN_HLEN);
 
-		vlan_tci = vlan_dev_info(dev)->vlan_id;
+		vlan_tci = vlan_dev_priv(dev)->vlan_id;
 		vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb);
 		vhdr->h_vlan_TCI = htons(vlan_tci);
 
@@ -129,7 +130,7 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev,
 		saddr = dev->dev_addr;
 
 	/* Now make the underlying real hard header */
-	dev = vlan_dev_info(dev)->real_dev;
+	dev = vlan_dev_priv(dev)->real_dev;
 	rc = dev_hard_header(skb, dev, type, daddr, saddr, len + vhdrlen);
 	if (rc > 0)
 		rc += vhdrlen;
@@ -149,27 +150,29 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
 	 * OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs...
 	 */
 	if (veth->h_vlan_proto != htons(ETH_P_8021Q) ||
-	    vlan_dev_info(dev)->flags & VLAN_FLAG_REORDER_HDR) {
+	    vlan_dev_priv(dev)->flags & VLAN_FLAG_REORDER_HDR) {
 		u16 vlan_tci;
-		vlan_tci = vlan_dev_info(dev)->vlan_id;
+		vlan_tci = vlan_dev_priv(dev)->vlan_id;
 		vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb);
 		skb = __vlan_hwaccel_put_tag(skb, vlan_tci);
 	}
 
-	skb_set_dev(skb, vlan_dev_info(dev)->real_dev);
+	skb_set_dev(skb, vlan_dev_priv(dev)->real_dev);
 	len = skb->len;
+	if (netpoll_tx_running(dev))
+		return skb->dev->netdev_ops->ndo_start_xmit(skb, skb->dev);
 	ret = dev_queue_xmit(skb);
 
 	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
 		struct vlan_pcpu_stats *stats;
 
-		stats = this_cpu_ptr(vlan_dev_info(dev)->vlan_pcpu_stats);
+		stats = this_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats);
 		u64_stats_update_begin(&stats->syncp);
 		stats->tx_packets++;
 		stats->tx_bytes += len;
 		u64_stats_update_end(&stats->syncp);
 	} else {
-		this_cpu_inc(vlan_dev_info(dev)->vlan_pcpu_stats->tx_dropped);
+		this_cpu_inc(vlan_dev_priv(dev)->vlan_pcpu_stats->tx_dropped);
 	}
 
 	return ret;
@@ -180,7 +183,7 @@ static int vlan_dev_change_mtu(struct net_device *dev, int new_mtu)
 	/* TODO: gotta make sure the underlying layer can handle it,
 	 * maybe an IFF_VLAN_CAPABLE flag for devices?
 	 */
-	if (vlan_dev_info(dev)->real_dev->mtu < new_mtu)
+	if (vlan_dev_priv(dev)->real_dev->mtu < new_mtu)
 		return -ERANGE;
 
 	dev->mtu = new_mtu;
@@ -191,7 +194,7 @@ static int vlan_dev_change_mtu(struct net_device *dev, int new_mtu)
 void vlan_dev_set_ingress_priority(const struct net_device *dev,
 				   u32 skb_prio, u16 vlan_prio)
 {
-	struct vlan_dev_info *vlan = vlan_dev_info(dev);
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 
 	if (vlan->ingress_priority_map[vlan_prio & 0x7] && !skb_prio)
 		vlan->nr_ingress_mappings--;
@@ -204,7 +207,7 @@ void vlan_dev_set_ingress_priority(const struct net_device *dev,
 int vlan_dev_set_egress_priority(const struct net_device *dev,
 				 u32 skb_prio, u16 vlan_prio)
 {
-	struct vlan_dev_info *vlan = vlan_dev_info(dev);
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct vlan_priority_tci_mapping *mp = NULL;
 	struct vlan_priority_tci_mapping *np;
 	u32 vlan_qos = (vlan_prio << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK;
@@ -241,7 +244,7 @@ int vlan_dev_set_egress_priority(const struct net_device *dev,
 /* Flags are defined in the vlan_flags enum in include/linux/if_vlan.h file. */
 int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask)
 {
-	struct vlan_dev_info *vlan = vlan_dev_info(dev);
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	u32 old_flags = vlan->flags;
 
 	if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP |
@@ -261,12 +264,12 @@ int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask)
 
 void vlan_dev_get_realdev_name(const struct net_device *dev, char *result)
 {
-	strncpy(result, vlan_dev_info(dev)->real_dev->name, 23);
+	strncpy(result, vlan_dev_priv(dev)->real_dev->name, 23);
 }
 
 static int vlan_dev_open(struct net_device *dev)
 {
-	struct vlan_dev_info *vlan = vlan_dev_info(dev);
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct net_device *real_dev = vlan->real_dev;
 	int err;
 
@@ -313,7 +316,7 @@ out:
 
 static int vlan_dev_stop(struct net_device *dev)
 {
-	struct vlan_dev_info *vlan = vlan_dev_info(dev);
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct net_device *real_dev = vlan->real_dev;
 
 	dev_mc_unsync(real_dev, dev);
@@ -332,7 +335,7 @@ static int vlan_dev_stop(struct net_device *dev)
 
 static int vlan_dev_set_mac_address(struct net_device *dev, void *p)
 {
-	struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	struct sockaddr *addr = p;
 	int err;
 
@@ -358,7 +361,7 @@ out:
 
 static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
-	struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	const struct net_device_ops *ops = real_dev->netdev_ops;
 	struct ifreq ifrr;
 	int err = -EOPNOTSUPP;
@@ -383,7 +386,7 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 
 static int vlan_dev_neigh_setup(struct net_device *dev, struct neigh_parms *pa)
 {
-	struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	const struct net_device_ops *ops = real_dev->netdev_ops;
 	int err = 0;
 
@@ -397,7 +400,7 @@ static int vlan_dev_neigh_setup(struct net_device *dev, struct neigh_parms *pa)
 static int vlan_dev_fcoe_ddp_setup(struct net_device *dev, u16 xid,
 				   struct scatterlist *sgl, unsigned int sgc)
 {
-	struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	const struct net_device_ops *ops = real_dev->netdev_ops;
 	int rc = 0;
 
@@ -409,7 +412,7 @@ static int vlan_dev_fcoe_ddp_setup(struct net_device *dev, u16 xid,
 
 static int vlan_dev_fcoe_ddp_done(struct net_device *dev, u16 xid)
 {
-	struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	const struct net_device_ops *ops = real_dev->netdev_ops;
 	int len = 0;
 
@@ -421,7 +424,7 @@ static int vlan_dev_fcoe_ddp_done(struct net_device *dev, u16 xid)
 
 static int vlan_dev_fcoe_enable(struct net_device *dev)
 {
-	struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	const struct net_device_ops *ops = real_dev->netdev_ops;
 	int rc = -EINVAL;
 
@@ -432,7 +435,7 @@ static int vlan_dev_fcoe_enable(struct net_device *dev)
 
 static int vlan_dev_fcoe_disable(struct net_device *dev)
 {
-	struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	const struct net_device_ops *ops = real_dev->netdev_ops;
 	int rc = -EINVAL;
 
@@ -443,7 +446,7 @@ static int vlan_dev_fcoe_disable(struct net_device *dev)
 
 static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type)
 {
-	struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	const struct net_device_ops *ops = real_dev->netdev_ops;
 	int rc = -EINVAL;
 
@@ -455,7 +458,7 @@ static int vlan_dev_fcoe_get_wwn(struct net_device *dev, u64 *wwn, int type)
 static int vlan_dev_fcoe_ddp_target(struct net_device *dev, u16 xid,
 				    struct scatterlist *sgl, unsigned int sgc)
 {
-	struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	const struct net_device_ops *ops = real_dev->netdev_ops;
 	int rc = 0;
 
@@ -468,7 +471,7 @@ static int vlan_dev_fcoe_ddp_target(struct net_device *dev, u16 xid,
 
 static void vlan_dev_change_rx_flags(struct net_device *dev, int change)
 {
-	struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 
 	if (dev->flags & IFF_UP) {
 		if (change & IFF_ALLMULTI)
@@ -480,8 +483,8 @@ static void vlan_dev_change_rx_flags(struct net_device *dev, int change)
 
 static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)
 {
-	dev_mc_sync(vlan_dev_info(vlan_dev)->real_dev, vlan_dev);
-	dev_uc_sync(vlan_dev_info(vlan_dev)->real_dev, vlan_dev);
+	dev_mc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
+	dev_uc_sync(vlan_dev_priv(vlan_dev)->real_dev, vlan_dev);
 }
 
 /*
@@ -519,7 +522,7 @@ static const struct net_device_ops vlan_netdev_ops;
 
 static int vlan_dev_init(struct net_device *dev)
 {
-	struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	int subclass = 0;
 
 	netif_carrier_off(dev);
@@ -568,8 +571,8 @@ static int vlan_dev_init(struct net_device *dev)
 
 	vlan_dev_set_lockdep_class(dev, subclass);
 
-	vlan_dev_info(dev)->vlan_pcpu_stats = alloc_percpu(struct vlan_pcpu_stats);
-	if (!vlan_dev_info(dev)->vlan_pcpu_stats)
+	vlan_dev_priv(dev)->vlan_pcpu_stats = alloc_percpu(struct vlan_pcpu_stats);
+	if (!vlan_dev_priv(dev)->vlan_pcpu_stats)
 		return -ENOMEM;
 
 	return 0;
@@ -578,7 +581,7 @@ static int vlan_dev_init(struct net_device *dev)
 static void vlan_dev_uninit(struct net_device *dev)
 {
 	struct vlan_priority_tci_mapping *pm;
-	struct vlan_dev_info *vlan = vlan_dev_info(dev);
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	int i;
 
 	free_percpu(vlan->vlan_pcpu_stats);
@@ -591,18 +594,17 @@ static void vlan_dev_uninit(struct net_device *dev)
 	}
 }
 
-static u32 vlan_dev_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t vlan_dev_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
-	struct net_device *real_dev = vlan_dev_info(dev)->real_dev;
+	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 	u32 old_features = features;
 
-	features &= real_dev->features;
 	features &= real_dev->vlan_features;
+	features |= NETIF_F_RXCSUM;
+	features &= real_dev->features;
 
 	features |= old_features & NETIF_F_SOFT_FEATURES;
-
-	if (dev_ethtool_get_rx_csum(real_dev))
-		features |= NETIF_F_RXCSUM;
 	features |= NETIF_F_LLTX;
 
 	return features;
@@ -611,7 +613,7 @@ static u32 vlan_dev_fix_features(struct net_device *dev, u32 features)
 static int vlan_ethtool_get_settings(struct net_device *dev,
 				     struct ethtool_cmd *cmd)
 {
-	const struct vlan_dev_info *vlan = vlan_dev_info(dev);
+	const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 
 	return __ethtool_get_settings(vlan->real_dev, cmd);
 }
@@ -627,7 +629,7 @@ static void vlan_ethtool_get_drvinfo(struct net_device *dev,
 static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 
-	if (vlan_dev_info(dev)->vlan_pcpu_stats) {
+	if (vlan_dev_priv(dev)->vlan_pcpu_stats) {
 		struct vlan_pcpu_stats *p;
 		u32 rx_errors = 0, tx_dropped = 0;
 		int i;
@@ -636,7 +638,7 @@ static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, st
 			u64 rxpackets, rxbytes, rxmulticast, txpackets, txbytes;
 			unsigned int start;
 
-			p = per_cpu_ptr(vlan_dev_info(dev)->vlan_pcpu_stats, i);
+			p = per_cpu_ptr(vlan_dev_priv(dev)->vlan_pcpu_stats, i);
 			do {
 				start = u64_stats_fetch_begin_bh(&p->syncp);
 				rxpackets	= p->rx_packets;
@@ -661,6 +663,57 @@ static struct rtnl_link_stats64 *vlan_dev_get_stats64(struct net_device *dev, st
 	return stats;
 }
 
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void vlan_dev_poll_controller(struct net_device *dev)
+{
+	return;
+}
+
+static int vlan_dev_netpoll_setup(struct net_device *dev, struct netpoll_info *npinfo)
+{
+	struct vlan_dev_priv *info = vlan_dev_priv(dev);
+	struct net_device *real_dev = info->real_dev;
+	struct netpoll *netpoll;
+	int err = 0;
+
+	netpoll = kzalloc(sizeof(*netpoll), GFP_KERNEL);
+	err = -ENOMEM;
+	if (!netpoll)
+		goto out;
+
+	netpoll->dev = real_dev;
+	strlcpy(netpoll->dev_name, real_dev->name, IFNAMSIZ);
+
+	err = __netpoll_setup(netpoll);
+	if (err) {
+		kfree(netpoll);
+		goto out;
+	}
+
+	info->netpoll = netpoll;
+
+out:
+	return err;
+}
+
+static void vlan_dev_netpoll_cleanup(struct net_device *dev)
+{
+	struct vlan_dev_priv *info = vlan_dev_priv(dev);
+	struct netpoll *netpoll = info->netpoll;
+
+	if (!netpoll)
+		return;
+
+	info->netpoll = NULL;
+
+        /* Wait for transmitting packets to finish before freeing. */
+        synchronize_rcu_bh();
+
+        __netpoll_cleanup(netpoll);
+        kfree(netpoll);
+}
+#endif /* CONFIG_NET_POLL_CONTROLLER */
+
 static const struct ethtool_ops vlan_ethtool_ops = {
 	.get_settings	        = vlan_ethtool_get_settings,
 	.get_drvinfo	        = vlan_ethtool_get_drvinfo,
@@ -689,6 +742,11 @@ static const struct net_device_ops vlan_netdev_ops = {
 	.ndo_fcoe_get_wwn	= vlan_dev_fcoe_get_wwn,
 	.ndo_fcoe_ddp_target	= vlan_dev_fcoe_ddp_target,
 #endif
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= vlan_dev_poll_controller,
+	.ndo_netpoll_setup	= vlan_dev_netpoll_setup,
+	.ndo_netpoll_cleanup	= vlan_dev_netpoll_cleanup,
+#endif
 	.ndo_fix_features	= vlan_dev_fix_features,
 };
 
diff --git a/net/8021q/vlan_gvrp.c b/net/8021q/vlan_gvrp.c
index 061cece..6f97553 100644
--- a/net/8021q/vlan_gvrp.c
+++ b/net/8021q/vlan_gvrp.c
@@ -29,7 +29,7 @@ static struct garp_application vlan_gvrp_app __read_mostly = {
 
 int vlan_gvrp_request_join(const struct net_device *dev)
 {
-	const struct vlan_dev_info *vlan = vlan_dev_info(dev);
+	const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	__be16 vlan_id = htons(vlan->vlan_id);
 
 	return garp_request_join(vlan->real_dev, &vlan_gvrp_app,
@@ -38,7 +38,7 @@ int vlan_gvrp_request_join(const struct net_device *dev)
 
 void vlan_gvrp_request_leave(const struct net_device *dev)
 {
-	const struct vlan_dev_info *vlan = vlan_dev_info(dev);
+	const struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	__be16 vlan_id = htons(vlan->vlan_id);
 
 	garp_request_leave(vlan->real_dev, &vlan_gvrp_app,
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 235c219..5071136 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -105,7 +105,7 @@ static int vlan_changelink(struct net_device *dev,
 static int vlan_newlink(struct net *src_net, struct net_device *dev,
 			struct nlattr *tb[], struct nlattr *data[])
 {
-	struct vlan_dev_info *vlan = vlan_dev_info(dev);
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct net_device *real_dev;
 	int err;
 
@@ -149,7 +149,7 @@ static inline size_t vlan_qos_map_size(unsigned int n)
 
 static size_t vlan_get_size(const struct net_device *dev)
 {
-	struct vlan_dev_info *vlan = vlan_dev_info(dev);
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 
 	return nla_total_size(2) +	/* IFLA_VLAN_ID */
 	       sizeof(struct ifla_vlan_flags) + /* IFLA_VLAN_FLAGS */
@@ -159,14 +159,14 @@ static size_t vlan_get_size(const struct net_device *dev)
 
 static int vlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
-	struct vlan_dev_info *vlan = vlan_dev_info(dev);
+	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct vlan_priority_tci_mapping *pm;
 	struct ifla_vlan_flags f;
 	struct ifla_vlan_qos_mapping m;
 	struct nlattr *nest;
 	unsigned int i;
 
-	NLA_PUT_U16(skb, IFLA_VLAN_ID, vlan_dev_info(dev)->vlan_id);
+	NLA_PUT_U16(skb, IFLA_VLAN_ID, vlan_dev_priv(dev)->vlan_id);
 	if (vlan->flags) {
 		f.flags = vlan->flags;
 		f.mask  = ~0;
@@ -218,7 +218,7 @@ struct rtnl_link_ops vlan_link_ops __read_mostly = {
 	.kind		= "vlan",
 	.maxtype	= IFLA_VLAN_MAX,
 	.policy		= vlan_policy,
-	.priv_size	= sizeof(struct vlan_dev_info),
+	.priv_size	= sizeof(struct vlan_dev_priv),
 	.setup		= vlan_setup,
 	.validate	= vlan_validate,
 	.newlink	= vlan_newlink,
diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c
index d34b6da..c718fd3 100644
--- a/net/8021q/vlanproc.c
+++ b/net/8021q/vlanproc.c
@@ -168,13 +168,13 @@ err:
 
 int vlan_proc_add_dev(struct net_device *vlandev)
 {
-	struct vlan_dev_info *dev_info = vlan_dev_info(vlandev);
+	struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
 	struct vlan_net *vn = net_generic(dev_net(vlandev), vlan_net_id);
 
-	dev_info->dent =
+	vlan->dent =
 		proc_create_data(vlandev->name, S_IFREG|S_IRUSR|S_IWUSR,
 				 vn->proc_vlan_dir, &vlandev_fops, vlandev);
-	if (!dev_info->dent)
+	if (!vlan->dent)
 		return -ENOBUFS;
 	return 0;
 }
@@ -187,10 +187,10 @@ int vlan_proc_rem_dev(struct net_device *vlandev)
 	struct vlan_net *vn = net_generic(dev_net(vlandev), vlan_net_id);
 
 	/** NOTE:  This will consume the memory pointed to by dent, it seems. */
-	if (vlan_dev_info(vlandev)->dent) {
-		remove_proc_entry(vlan_dev_info(vlandev)->dent->name,
+	if (vlan_dev_priv(vlandev)->dent) {
+		remove_proc_entry(vlan_dev_priv(vlandev)->dent->name,
 				  vn->proc_vlan_dir);
-		vlan_dev_info(vlandev)->dent = NULL;
+		vlan_dev_priv(vlandev)->dent = NULL;
 	}
 	return 0;
 }
@@ -268,10 +268,10 @@ static int vlan_seq_show(struct seq_file *seq, void *v)
 			   nmtype ? nmtype :  "UNKNOWN");
 	} else {
 		const struct net_device *vlandev = v;
-		const struct vlan_dev_info *dev_info = vlan_dev_info(vlandev);
+		const struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
 
 		seq_printf(seq, "%-15s| %d  | %s\n",  vlandev->name,
-			   dev_info->vlan_id,    dev_info->real_dev->name);
+			   vlan->vlan_id,    vlan->real_dev->name);
 	}
 	return 0;
 }
@@ -279,7 +279,7 @@ static int vlan_seq_show(struct seq_file *seq, void *v)
 static int vlandev_seq_show(struct seq_file *seq, void *offset)
 {
 	struct net_device *vlandev = (struct net_device *) seq->private;
-	const struct vlan_dev_info *dev_info = vlan_dev_info(vlandev);
+	const struct vlan_dev_priv *vlan = vlan_dev_priv(vlandev);
 	struct rtnl_link_stats64 temp;
 	const struct rtnl_link_stats64 *stats;
 	static const char fmt64[] = "%30s %12llu\n";
@@ -291,8 +291,8 @@ static int vlandev_seq_show(struct seq_file *seq, void *offset)
 	stats = dev_get_stats(vlandev, &temp);
 	seq_printf(seq,
 		   "%s  VID: %d	 REORDER_HDR: %i  dev->priv_flags: %hx\n",
-		   vlandev->name, dev_info->vlan_id,
-		   (int)(dev_info->flags & 1), vlandev->priv_flags);
+		   vlandev->name, vlan->vlan_id,
+		   (int)(vlan->flags & 1), vlandev->priv_flags);
 
 	seq_printf(seq, fmt64, "total frames received", stats->rx_packets);
 	seq_printf(seq, fmt64, "total bytes received", stats->rx_bytes);
@@ -300,23 +300,23 @@ static int vlandev_seq_show(struct seq_file *seq, void *offset)
 	seq_puts(seq, "\n");
 	seq_printf(seq, fmt64, "total frames transmitted", stats->tx_packets);
 	seq_printf(seq, fmt64, "total bytes transmitted", stats->tx_bytes);
-	seq_printf(seq, "Device: %s", dev_info->real_dev->name);
+	seq_printf(seq, "Device: %s", vlan->real_dev->name);
 	/* now show all PRIORITY mappings relating to this VLAN */
 	seq_printf(seq, "\nINGRESS priority mappings: "
 			"0:%u  1:%u  2:%u  3:%u  4:%u  5:%u  6:%u 7:%u\n",
-		   dev_info->ingress_priority_map[0],
-		   dev_info->ingress_priority_map[1],
-		   dev_info->ingress_priority_map[2],
-		   dev_info->ingress_priority_map[3],
-		   dev_info->ingress_priority_map[4],
-		   dev_info->ingress_priority_map[5],
-		   dev_info->ingress_priority_map[6],
-		   dev_info->ingress_priority_map[7]);
+		   vlan->ingress_priority_map[0],
+		   vlan->ingress_priority_map[1],
+		   vlan->ingress_priority_map[2],
+		   vlan->ingress_priority_map[3],
+		   vlan->ingress_priority_map[4],
+		   vlan->ingress_priority_map[5],
+		   vlan->ingress_priority_map[6],
+		   vlan->ingress_priority_map[7]);
 
 	seq_printf(seq, " EGRESS priority mappings: ");
 	for (i = 0; i < 16; i++) {
 		const struct vlan_priority_tci_mapping *mp
-			= dev_info->egress_priority_map[i];
+			= vlan->egress_priority_map[i];
 		while (mp) {
 			seq_printf(seq, "%u:%hu ",
 				   mp->priority, ((mp->vlan_qos >> 13) & 0x7));
diff --git a/net/Kconfig b/net/Kconfig
index a073148..e07272d 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -215,6 +215,7 @@ source "net/sched/Kconfig"
 source "net/dcb/Kconfig"
 source "net/dns_resolver/Kconfig"
 source "net/batman-adv/Kconfig"
+source "net/openvswitch/Kconfig"
 
 config RPS
 	boolean
@@ -232,6 +233,19 @@ config XPS
 	depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS
 	default y
 
+config NETPRIO_CGROUP
+	tristate "Network priority cgroup"
+	depends on CGROUPS
+	---help---
+	  Cgroup subsystem for use in assigning processes to network priorities on
+	  a per-interface basis
+
+config BQL
+	boolean
+	depends on SYSFS
+	select DQL
+	default y
+
 config HAVE_BPF_JIT
 	bool
 
diff --git a/net/Makefile b/net/Makefile
index acdde49..ad432fa 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -69,3 +69,4 @@ obj-$(CONFIG_DNS_RESOLVER)	+= dns_resolver/
 obj-$(CONFIG_CEPH_LIB)		+= ceph/
 obj-$(CONFIG_BATMAN_ADV)	+= batman-adv/
 obj-$(CONFIG_NFC)		+= nfc/
+obj-$(CONFIG_OPENVSWITCH)	+= openvswitch/
diff --git a/net/atm/atm_misc.c b/net/atm/atm_misc.c
index f41f026..876fbe8 100644
--- a/net/atm/atm_misc.c
+++ b/net/atm/atm_misc.c
@@ -26,7 +26,7 @@ struct sk_buff *atm_alloc_charge(struct atm_vcc *vcc, int pdu_size,
 				 gfp_t gfp_flags)
 {
 	struct sock *sk = sk_atm(vcc);
-	int guess = atm_guess_pdu2truesize(pdu_size);
+	int guess = SKB_TRUESIZE(pdu_size);
 
 	atm_force_charge(vcc, guess);
 	if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) {
diff --git a/net/atm/br2684.c b/net/atm/br2684.c
index d07223c..353fccf 100644
--- a/net/atm/br2684.c
+++ b/net/atm/br2684.c
@@ -53,6 +53,7 @@ static const unsigned char ethertype_ipv4[] = { ETHERTYPE_IPV4 };
 static const unsigned char ethertype_ipv6[] = { ETHERTYPE_IPV6 };
 static const unsigned char llc_oui_pid_pad[] =
 			{ LLC, SNAP_BRIDGED, PID_ETHERNET, PAD_BRIDGED };
+static const unsigned char pad[] = { PAD_BRIDGED };
 static const unsigned char llc_oui_ipv4[] = { LLC, SNAP_ROUTED, ETHERTYPE_IPV4 };
 static const unsigned char llc_oui_ipv6[] = { LLC, SNAP_ROUTED, ETHERTYPE_IPV6 };
 
@@ -202,7 +203,10 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct net_device *dev,
 {
 	struct br2684_dev *brdev = BRPRIV(dev);
 	struct atm_vcc *atmvcc;
-	int minheadroom = (brvcc->encaps == e_llc) ? 10 : 2;
+	int minheadroom = (brvcc->encaps == e_llc) ?
+		((brdev->payload == p_bridged) ?
+			sizeof(llc_oui_pid_pad) : sizeof(llc_oui_ipv4)) :
+		((brdev->payload == p_bridged) ? BR2684_PAD_LEN : 0);
 
 	if (skb_headroom(skb) < minheadroom) {
 		struct sk_buff *skb2 = skb_realloc_headroom(skb, minheadroom);
@@ -450,7 +454,7 @@ static void br2684_push(struct atm_vcc *atmvcc, struct sk_buff *skb)
 			skb->pkt_type = PACKET_HOST;
 		} else { /* p_bridged */
 			/* first 2 chars should be 0 */
-			if (*((u16 *) (skb->data)) != 0)
+			if (memcmp(skb->data, pad, BR2684_PAD_LEN) != 0)
 				goto error;
 			skb_pull(skb, BR2684_PAD_LEN);
 			skb->protocol = eth_type_trans(skb, net_dev);
@@ -489,15 +493,11 @@ free_skb:
  */
 static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg)
 {
-	struct sk_buff_head queue;
-	int err;
 	struct br2684_vcc *brvcc;
-	struct sk_buff *skb, *tmp;
-	struct sk_buff_head *rq;
 	struct br2684_dev *brdev;
 	struct net_device *net_dev;
 	struct atm_backend_br2684 be;
-	unsigned long flags;
+	int err;
 
 	if (copy_from_user(&be, arg, sizeof be))
 		return -EFAULT;
@@ -550,23 +550,6 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg)
 	atmvcc->push = br2684_push;
 	atmvcc->pop = br2684_pop;
 
-	__skb_queue_head_init(&queue);
-	rq = &sk_atm(atmvcc)->sk_receive_queue;
-
-	spin_lock_irqsave(&rq->lock, flags);
-	skb_queue_splice_init(rq, &queue);
-	spin_unlock_irqrestore(&rq->lock, flags);
-
-	skb_queue_walk_safe(&queue, skb, tmp) {
-		struct net_device *dev;
-
-		br2684_push(atmvcc, skb);
-		dev = skb->dev;
-
-		dev->stats.rx_bytes -= skb->len;
-		dev->stats.rx_packets--;
-	}
-
 	/* initialize netdev carrier state */
 	if (atmvcc->dev->signal == ATM_PHY_SIG_LOST)
 		netif_carrier_off(net_dev);
@@ -574,6 +557,10 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg)
 		netif_carrier_on(net_dev);
 
 	__module_get(THIS_MODULE);
+
+	/* re-process everything received between connection setup and
+	   backend setup */
+	vcc_process_recv_queue(atmvcc);
 	return 0;
 
 error:
@@ -600,6 +587,7 @@ static void br2684_setup(struct net_device *netdev)
 	struct br2684_dev *brdev = BRPRIV(netdev);
 
 	ether_setup(netdev);
+	netdev->hard_header_len += sizeof(llc_oui_pid_pad); /* worst case */
 	brdev->net_dev = netdev;
 
 	netdev->netdev_ops = &br2684_netdev_ops;
@@ -612,7 +600,7 @@ static void br2684_setup_routed(struct net_device *netdev)
 	struct br2684_dev *brdev = BRPRIV(netdev);
 
 	brdev->net_dev = netdev;
-	netdev->hard_header_len = 0;
+	netdev->hard_header_len = sizeof(llc_oui_ipv4); /* worst case */
 	netdev->netdev_ops = &br2684_netdev_ops_routed;
 	netdev->addr_len = 0;
 	netdev->mtu = 1500;
diff --git a/net/atm/clip.c b/net/atm/clip.c
index 8523940..c12c258 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -33,6 +33,7 @@
 #include <linux/slab.h>
 #include <net/route.h> /* for struct rtable and routing */
 #include <net/icmp.h> /* icmp_send */
+#include <net/arp.h>
 #include <linux/param.h> /* for HZ */
 #include <linux/uaccess.h>
 #include <asm/byteorder.h> /* for htons etc. */
@@ -119,7 +120,7 @@ out:
 /* The neighbour entry n->lock is held. */
 static int neigh_check_cb(struct neighbour *n)
 {
-	struct atmarp_entry *entry = NEIGH2ENTRY(n);
+	struct atmarp_entry *entry = neighbour_priv(n);
 	struct clip_vcc *cv;
 
 	for (cv = entry->vccs; cv; cv = cv->next) {
@@ -189,6 +190,13 @@ static void clip_push(struct atm_vcc *vcc, struct sk_buff *skb)
 	struct clip_vcc *clip_vcc = CLIP_VCC(vcc);
 
 	pr_debug("\n");
+
+	if (!clip_devs) {
+		atm_return(vcc, skb->truesize);
+		kfree_skb(skb);
+		return;
+	}
+
 	if (!skb) {
 		pr_debug("removing VCC %p\n", clip_vcc);
 		if (clip_vcc->entry)
@@ -255,8 +263,10 @@ static void clip_pop(struct atm_vcc *vcc, struct sk_buff *skb)
 
 static void clip_neigh_solicit(struct neighbour *neigh, struct sk_buff *skb)
 {
+	__be32 *ip = (__be32 *) neigh->primary_key;
+
 	pr_debug("(neigh %p, skb %p)\n", neigh, skb);
-	to_atmarpd(act_need, PRIV(neigh->dev)->number, NEIGH2ENTRY(neigh)->ip);
+	to_atmarpd(act_need, PRIV(neigh->dev)->number, *ip);
 }
 
 static void clip_neigh_error(struct neighbour *neigh, struct sk_buff *skb)
@@ -277,72 +287,24 @@ static const struct neigh_ops clip_neigh_ops = {
 
 static int clip_constructor(struct neighbour *neigh)
 {
-	struct atmarp_entry *entry = NEIGH2ENTRY(neigh);
-	struct net_device *dev = neigh->dev;
-	struct in_device *in_dev;
-	struct neigh_parms *parms;
+	struct atmarp_entry *entry = neighbour_priv(neigh);
 
-	pr_debug("(neigh %p, entry %p)\n", neigh, entry);
-	neigh->type = inet_addr_type(&init_net, entry->ip);
-	if (neigh->type != RTN_UNICAST)
+	if (neigh->tbl->family != AF_INET)
 		return -EINVAL;
 
-	rcu_read_lock();
-	in_dev = __in_dev_get_rcu(dev);
-	if (!in_dev) {
-		rcu_read_unlock();
+	if (neigh->type != RTN_UNICAST)
 		return -EINVAL;
-	}
-
-	parms = in_dev->arp_parms;
-	__neigh_parms_put(neigh->parms);
-	neigh->parms = neigh_parms_clone(parms);
-	rcu_read_unlock();
 
+	neigh->nud_state = NUD_NONE;
 	neigh->ops = &clip_neigh_ops;
-	neigh->output = neigh->nud_state & NUD_VALID ?
-	    neigh->ops->connected_output : neigh->ops->output;
+	neigh->output = neigh->ops->output;
 	entry->neigh = neigh;
 	entry->vccs = NULL;
 	entry->expires = jiffies - 1;
+
 	return 0;
 }
 
-static u32 clip_hash(const void *pkey, const struct net_device *dev, __u32 rnd)
-{
-	return jhash_2words(*(u32 *) pkey, dev->ifindex, rnd);
-}
-
-static struct neigh_table clip_tbl = {
-	.family 	= AF_INET,
-	.entry_size 	= sizeof(struct neighbour)+sizeof(struct atmarp_entry),
-	.key_len 	= 4,
-	.hash 		= clip_hash,
-	.constructor 	= clip_constructor,
-	.id 		= "clip_arp_cache",
-
-	/* parameters are copied from ARP ... */
-	.parms = {
-		.tbl 			= &clip_tbl,
-		.base_reachable_time 	= 30 * HZ,
-		.retrans_time 		= 1 * HZ,
-		.gc_staletime 		= 60 * HZ,
-		.reachable_time 	= 30 * HZ,
-		.delay_probe_time 	= 5 * HZ,
-		.queue_len 		= 3,
-		.ucast_probes 		= 3,
-		.mcast_probes 		= 3,
-		.anycast_delay 		= 1 * HZ,
-		.proxy_delay 		= (8 * HZ) / 10,
-		.proxy_qlen 		= 64,
-		.locktime 		= 1 * HZ,
-	},
-	.gc_interval 	= 30 * HZ,
-	.gc_thresh1 	= 128,
-	.gc_thresh2 	= 512,
-	.gc_thresh3 	= 1024,
-};
-
 /* @@@ copy bh locking from arp.c -- need to bh-enable atm code before */
 
 /*
@@ -376,28 +338,19 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb,
 		dev->stats.tx_dropped++;
 		return NETDEV_TX_OK;
 	}
-	n = dst_get_neighbour(dst);
+	n = dst_get_neighbour_noref(dst);
 	if (!n) {
-#if 0
-		n = clip_find_neighbour(skb_dst(skb), 1);
-		if (!n) {
-			dev_kfree_skb(skb);	/* lost that one */
-			dev->stats.tx_dropped++;
-			return 0;
-		}
-		dst_set_neighbour(dst, n);
-#endif
 		pr_err("NO NEIGHBOUR !\n");
 		dev_kfree_skb(skb);
 		dev->stats.tx_dropped++;
 		return NETDEV_TX_OK;
 	}
-	entry = NEIGH2ENTRY(n);
+	entry = neighbour_priv(n);
 	if (!entry->vccs) {
 		if (time_after(jiffies, entry->expires)) {
 			/* should be resolved */
 			entry->expires = jiffies + ATMARP_RETRY_DELAY * HZ;
-			to_atmarpd(act_need, PRIV(dev)->number, entry->ip);
+			to_atmarpd(act_need, PRIV(dev)->number, *((__be32 *)n->primary_key));
 		}
 		if (entry->neigh->arp_queue.qlen < ATMARP_MAX_UNRES_PACKETS)
 			skb_queue_tail(&entry->neigh->arp_queue, skb);
@@ -448,10 +401,7 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb,
 
 static int clip_mkip(struct atm_vcc *vcc, int timeout)
 {
-	struct sk_buff_head *rq, queue;
 	struct clip_vcc *clip_vcc;
-	struct sk_buff *skb, *tmp;
-	unsigned long flags;
 
 	if (!vcc->push)
 		return -EBADFD;
@@ -472,29 +422,9 @@ static int clip_mkip(struct atm_vcc *vcc, int timeout)
 	vcc->push = clip_push;
 	vcc->pop = clip_pop;
 
-	__skb_queue_head_init(&queue);
-	rq = &sk_atm(vcc)->sk_receive_queue;
-
-	spin_lock_irqsave(&rq->lock, flags);
-	skb_queue_splice_init(rq, &queue);
-	spin_unlock_irqrestore(&rq->lock, flags);
-
 	/* re-process everything received between connection setup and MKIP */
-	skb_queue_walk_safe(&queue, skb, tmp) {
-		if (!clip_devs) {
-			atm_return(vcc, skb->truesize);
-			kfree_skb(skb);
-		} else {
-			struct net_device *dev = skb->dev;
-			unsigned int len = skb->len;
-
-			skb_get(skb);
-			clip_push(vcc, skb);
-			dev->stats.rx_packets--;
-			dev->stats.rx_bytes -= len;
-			kfree_skb(skb);
-		}
-	}
+	vcc_process_recv_queue(vcc);
+
 	return 0;
 }
 
@@ -523,11 +453,11 @@ static int clip_setentry(struct atm_vcc *vcc, __be32 ip)
 	rt = ip_route_output(&init_net, ip, 0, 1, 0);
 	if (IS_ERR(rt))
 		return PTR_ERR(rt);
-	neigh = __neigh_lookup(&clip_tbl, &ip, rt->dst.dev, 1);
+	neigh = __neigh_lookup(&arp_tbl, &ip, rt->dst.dev, 1);
 	ip_rt_put(rt);
 	if (!neigh)
 		return -ENOMEM;
-	entry = NEIGH2ENTRY(neigh);
+	entry = neighbour_priv(neigh);
 	if (entry != clip_vcc->entry) {
 		if (!clip_vcc->entry)
 			pr_debug("add\n");
@@ -544,13 +474,15 @@ static int clip_setentry(struct atm_vcc *vcc, __be32 ip)
 }
 
 static const struct net_device_ops clip_netdev_ops = {
-	.ndo_start_xmit = clip_start_xmit,
+	.ndo_start_xmit		= clip_start_xmit,
+	.ndo_neigh_construct	= clip_constructor,
 };
 
 static void clip_setup(struct net_device *dev)
 {
 	dev->netdev_ops = &clip_netdev_ops;
 	dev->type = ARPHRD_ATM;
+	dev->neigh_priv_len = sizeof(struct atmarp_entry);
 	dev->hard_header_len = RFC1483LLC_LEN;
 	dev->mtu = RFC1626_MTU;
 	dev->tx_queue_len = 100;	/* "normal" queue (packets) */
@@ -604,10 +536,8 @@ static int clip_device_event(struct notifier_block *this, unsigned long event,
 	if (!net_eq(dev_net(dev), &init_net))
 		return NOTIFY_DONE;
 
-	if (event == NETDEV_UNREGISTER) {
-		neigh_ifdown(&clip_tbl, dev);
+	if (event == NETDEV_UNREGISTER)
 		return NOTIFY_DONE;
-	}
 
 	/* ignore non-CLIP devices */
 	if (dev->type != ARPHRD_ATM || dev->netdev_ops != &clip_netdev_ops)
@@ -787,9 +717,10 @@ static void svc_addr(struct seq_file *seq, struct sockaddr_atmsvc *addr)
 /* This means the neighbour entry has no attached VCC objects. */
 #define SEQ_NO_VCC_TOKEN	((void *) 2)
 
-static void atmarp_info(struct seq_file *seq, struct net_device *dev,
+static void atmarp_info(struct seq_file *seq, struct neighbour *n,
 			struct atmarp_entry *entry, struct clip_vcc *clip_vcc)
 {
+	struct net_device *dev = n->dev;
 	unsigned long exp;
 	char buf[17];
 	int svc, llc, off;
@@ -809,8 +740,7 @@ static void atmarp_info(struct seq_file *seq, struct net_device *dev,
 	seq_printf(seq, "%-6s%-4s%-4s%5ld ",
 		   dev->name, svc ? "SVC" : "PVC", llc ? "LLC" : "NULL", exp);
 
-	off = scnprintf(buf, sizeof(buf) - 1, "%pI4",
-			&entry->ip);
+	off = scnprintf(buf, sizeof(buf) - 1, "%pI4", n->primary_key);
 	while (off < 16)
 		buf[off++] = ' ';
 	buf[off] = '\0';
@@ -881,14 +811,17 @@ static void *clip_seq_sub_iter(struct neigh_seq_state *_state,
 {
 	struct clip_seq_state *state = (struct clip_seq_state *)_state;
 
-	return clip_seq_vcc_walk(state, NEIGH2ENTRY(n), pos);
+	if (n->dev->type != ARPHRD_ATM)
+		return NULL;
+
+	return clip_seq_vcc_walk(state, neighbour_priv(n), pos);
 }
 
 static void *clip_seq_start(struct seq_file *seq, loff_t * pos)
 {
 	struct clip_seq_state *state = seq->private;
 	state->ns.neigh_sub_iter = clip_seq_sub_iter;
-	return neigh_seq_start(seq, pos, &clip_tbl, NEIGH_SEQ_NEIGH_ONLY);
+	return neigh_seq_start(seq, pos, &arp_tbl, NEIGH_SEQ_NEIGH_ONLY);
 }
 
 static int clip_seq_show(struct seq_file *seq, void *v)
@@ -900,10 +833,10 @@ static int clip_seq_show(struct seq_file *seq, void *v)
 		seq_puts(seq, atm_arp_banner);
 	} else {
 		struct clip_seq_state *state = seq->private;
-		struct neighbour *n = v;
 		struct clip_vcc *vcc = state->vcc;
+		struct neighbour *n = v;
 
-		atmarp_info(seq, n->dev, NEIGH2ENTRY(n), vcc);
+		atmarp_info(seq, n, neighbour_priv(n), vcc);
 	}
 	return 0;
 }
@@ -934,9 +867,6 @@ static void atm_clip_exit_noproc(void);
 
 static int __init atm_clip_init(void)
 {
-	neigh_table_init_no_netlink(&clip_tbl);
-
-	clip_tbl_hook = &clip_tbl;
 	register_atm_ioctl(&clip_ioctl_ops);
 	register_netdevice_notifier(&clip_dev_notifier);
 	register_inetaddr_notifier(&clip_inet_notifier);
@@ -973,12 +903,6 @@ static void atm_clip_exit_noproc(void)
 	 */
 	del_timer_sync(&idle_timer);
 
-	/* Next, purge the table, so that the device
-	 * unregister loop below does not hang due to
-	 * device references remaining in the table.
-	 */
-	neigh_ifdown(&clip_tbl, NULL);
-
 	dev = clip_devs;
 	while (dev) {
 		next = PRIV(dev)->next;
@@ -986,11 +910,6 @@ static void atm_clip_exit_noproc(void)
 		free_netdev(dev);
 		dev = next;
 	}
-
-	/* Now it is safe to fully shutdown whole table. */
-	neigh_table_clear(&clip_tbl);
-
-	clip_tbl_hook = NULL;
 }
 
 static void __exit atm_clip_exit(void)
diff --git a/net/atm/common.c b/net/atm/common.c
index 14ff9fe..b4b44db 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -214,6 +214,26 @@ void vcc_release_async(struct atm_vcc *vcc, int reply)
 }
 EXPORT_SYMBOL(vcc_release_async);
 
+void vcc_process_recv_queue(struct atm_vcc *vcc)
+{
+	struct sk_buff_head queue, *rq;
+	struct sk_buff *skb, *tmp;
+	unsigned long flags;
+
+	__skb_queue_head_init(&queue);
+	rq = &sk_atm(vcc)->sk_receive_queue;
+
+	spin_lock_irqsave(&rq->lock, flags);
+	skb_queue_splice_init(rq, &queue);
+	spin_unlock_irqrestore(&rq->lock, flags);
+
+	skb_queue_walk_safe(&queue, skb, tmp) {
+		__skb_unlink(skb, &queue);
+		vcc->push(vcc, skb);
+	}
+}
+EXPORT_SYMBOL(vcc_process_recv_queue);
+
 void atm_dev_signal_change(struct atm_dev *dev, char signal)
 {
 	pr_debug("%s signal=%d dev=%p number=%d dev->signal=%d\n",
@@ -502,8 +522,11 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 
 	if (sock->state != SS_CONNECTED)
 		return -ENOTCONN;
-	if (flags & ~MSG_DONTWAIT)		/* only handle MSG_DONTWAIT */
+
+	/* only handle MSG_DONTWAIT and MSG_PEEK */
+	if (flags & ~(MSG_DONTWAIT | MSG_PEEK))
 		return -EOPNOTSUPP;
+
 	vcc = ATM_SD(sock);
 	if (test_bit(ATM_VF_RELEASED, &vcc->flags) ||
 	    test_bit(ATM_VF_CLOSE, &vcc->flags) ||
@@ -524,8 +547,13 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 	if (error)
 		return error;
 	sock_recv_ts_and_drops(msg, sk, skb);
-	pr_debug("%d -= %d\n", atomic_read(&sk->sk_rmem_alloc), skb->truesize);
-	atm_return(vcc, skb->truesize);
+
+	if (!(flags & MSG_PEEK)) {
+		pr_debug("%d -= %d\n", atomic_read(&sk->sk_rmem_alloc),
+			 skb->truesize);
+		atm_return(vcc, skb->truesize);
+	}
+
 	skb_free_datagram(sk, skb);
 	return copied;
 }
diff --git a/net/atm/common.h b/net/atm/common.h
index f48a76b..cc3c2da 100644
--- a/net/atm/common.h
+++ b/net/atm/common.h
@@ -24,6 +24,7 @@ int vcc_setsockopt(struct socket *sock, int level, int optname,
 		   char __user *optval, unsigned int optlen);
 int vcc_getsockopt(struct socket *sock, int level, int optname,
 		   char __user *optval, int __user *optlen);
+void vcc_process_recv_queue(struct atm_vcc *vcc);
 
 int atmpvc_init(void);
 void atmpvc_exit(void);
diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c
index db4a11c..df35d9a 100644
--- a/net/atm/pppoatm.c
+++ b/net/atm/pppoatm.c
@@ -303,6 +303,10 @@ static int pppoatm_assign_vcc(struct atm_vcc *atmvcc, void __user *arg)
 	atmvcc->push = pppoatm_push;
 	atmvcc->pop = pppoatm_pop;
 	__module_get(THIS_MODULE);
+
+	/* re-process everything received between connection setup and
+	   backend setup */
+	vcc_process_recv_queue(atmvcc);
 	return 0;
 }
 
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index e7c69f4..b863c18 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -402,14 +402,14 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg)
 		break;
 
 	case AX25_T1:
-		if (ax25_ctl.arg < 1)
+		if (ax25_ctl.arg < 1 || ax25_ctl.arg > ULONG_MAX / HZ)
 			goto einval_put;
 		ax25->rtt = (ax25_ctl.arg * HZ) / 2;
 		ax25->t1  = ax25_ctl.arg * HZ;
 		break;
 
 	case AX25_T2:
-		if (ax25_ctl.arg < 1)
+		if (ax25_ctl.arg < 1 || ax25_ctl.arg > ULONG_MAX / HZ)
 			goto einval_put;
 		ax25->t2 = ax25_ctl.arg * HZ;
 		break;
@@ -422,10 +422,15 @@ static int ax25_ctl_ioctl(const unsigned int cmd, void __user *arg)
 		break;
 
 	case AX25_T3:
+		if (ax25_ctl.arg > ULONG_MAX / HZ)
+			goto einval_put;
 		ax25->t3 = ax25_ctl.arg * HZ;
 		break;
 
 	case AX25_IDLE:
+		if (ax25_ctl.arg > ULONG_MAX / (60 * HZ))
+			goto einval_put;
+
 		ax25->idle = ax25_ctl.arg * 60 * HZ;
 		break;
 
@@ -571,7 +576,7 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case AX25_T1:
-		if (opt < 1) {
+		if (opt < 1 || opt > ULONG_MAX / HZ) {
 			res = -EINVAL;
 			break;
 		}
@@ -580,7 +585,7 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case AX25_T2:
-		if (opt < 1) {
+		if (opt < 1 || opt > ULONG_MAX / HZ) {
 			res = -EINVAL;
 			break;
 		}
@@ -596,7 +601,7 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case AX25_T3:
-		if (opt < 1) {
+		if (opt < 1 || opt > ULONG_MAX / HZ) {
 			res = -EINVAL;
 			break;
 		}
@@ -604,7 +609,7 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case AX25_IDLE:
-		if (opt < 0) {
+		if (opt < 0 || opt > ULONG_MAX / (60 * HZ)) {
 			res = -EINVAL;
 			break;
 		}
diff --git a/net/batman-adv/bat_sysfs.c b/net/batman-adv/bat_sysfs.c
index b8a7414..c25492f 100644
--- a/net/batman-adv/bat_sysfs.c
+++ b/net/batman-adv/bat_sysfs.c
@@ -174,7 +174,7 @@ static int store_uint_attr(const char *buff, size_t count,
 	unsigned long uint_val;
 	int ret;
 
-	ret = strict_strtoul(buff, 10, &uint_val);
+	ret = kstrtoul(buff, 10, &uint_val);
 	if (ret) {
 		bat_info(net_dev,
 			 "%s: Invalid parameter received: %s\n",
@@ -239,7 +239,7 @@ static ssize_t store_vis_mode(struct kobject *kobj, struct attribute *attr,
 	unsigned long val;
 	int ret, vis_mode_tmp = -1;
 
-	ret = strict_strtoul(buff, 10, &val);
+	ret = kstrtoul(buff, 10, &val);
 
 	if (((count == 2) && (!ret) && (val == VIS_TYPE_CLIENT_UPDATE)) ||
 	    (strncmp(buff, "client", 6) == 0) ||
diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c
index 0be9ff3..9bc63b2 100644
--- a/net/batman-adv/bitarray.c
+++ b/net/batman-adv/bitarray.c
@@ -155,7 +155,7 @@ int bit_get_packet(void *priv, unsigned long *seq_bits,
 	/* sequence number is much newer, probably missed a lot of packets */
 
 	if ((seq_num_diff >= TQ_LOCAL_WINDOW_SIZE)
-		|| (seq_num_diff < EXPECTED_SEQNO_RANGE)) {
+		&& (seq_num_diff < EXPECTED_SEQNO_RANGE)) {
 		bat_dbg(DBG_BATMAN, bat_priv,
 			"We missed a lot of packets (%i) !\n",
 			seq_num_diff - 1);
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index 619fb73..24403a7 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -25,6 +25,7 @@
 #include "gateway_common.h"
 #include "hard-interface.h"
 #include "originator.h"
+#include "translation-table.h"
 #include "routing.h"
 #include <linux/ip.h>
 #include <linux/ipv6.h>
@@ -572,108 +573,142 @@ out:
 	return ret;
 }
 
-int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb,
-		 struct orig_node *old_gw)
+bool gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len)
 {
 	struct ethhdr *ethhdr;
 	struct iphdr *iphdr;
 	struct ipv6hdr *ipv6hdr;
 	struct udphdr *udphdr;
-	struct gw_node *curr_gw;
-	struct neigh_node *neigh_curr = NULL, *neigh_old = NULL;
-	unsigned int header_len = 0;
-	int ret = 1;
-
-	if (atomic_read(&bat_priv->gw_mode) == GW_MODE_OFF)
-		return 0;
 
 	/* check for ethernet header */
-	if (!pskb_may_pull(skb, header_len + ETH_HLEN))
-		return 0;
+	if (!pskb_may_pull(skb, *header_len + ETH_HLEN))
+		return false;
 	ethhdr = (struct ethhdr *)skb->data;
-	header_len += ETH_HLEN;
+	*header_len += ETH_HLEN;
 
 	/* check for initial vlan header */
 	if (ntohs(ethhdr->h_proto) == ETH_P_8021Q) {
-		if (!pskb_may_pull(skb, header_len + VLAN_HLEN))
-			return 0;
+		if (!pskb_may_pull(skb, *header_len + VLAN_HLEN))
+			return false;
 		ethhdr = (struct ethhdr *)(skb->data + VLAN_HLEN);
-		header_len += VLAN_HLEN;
+		*header_len += VLAN_HLEN;
 	}
 
 	/* check for ip header */
 	switch (ntohs(ethhdr->h_proto)) {
 	case ETH_P_IP:
-		if (!pskb_may_pull(skb, header_len + sizeof(*iphdr)))
-			return 0;
-		iphdr = (struct iphdr *)(skb->data + header_len);
-		header_len += iphdr->ihl * 4;
+		if (!pskb_may_pull(skb, *header_len + sizeof(*iphdr)))
+			return false;
+		iphdr = (struct iphdr *)(skb->data + *header_len);
+		*header_len += iphdr->ihl * 4;
 
 		/* check for udp header */
 		if (iphdr->protocol != IPPROTO_UDP)
-			return 0;
+			return false;
 
 		break;
 	case ETH_P_IPV6:
-		if (!pskb_may_pull(skb, header_len + sizeof(*ipv6hdr)))
-			return 0;
-		ipv6hdr = (struct ipv6hdr *)(skb->data + header_len);
-		header_len += sizeof(*ipv6hdr);
+		if (!pskb_may_pull(skb, *header_len + sizeof(*ipv6hdr)))
+			return false;
+		ipv6hdr = (struct ipv6hdr *)(skb->data + *header_len);
+		*header_len += sizeof(*ipv6hdr);
 
 		/* check for udp header */
 		if (ipv6hdr->nexthdr != IPPROTO_UDP)
-			return 0;
+			return false;
 
 		break;
 	default:
-		return 0;
+		return false;
 	}
 
-	if (!pskb_may_pull(skb, header_len + sizeof(*udphdr)))
-		return 0;
-	udphdr = (struct udphdr *)(skb->data + header_len);
-	header_len += sizeof(*udphdr);
+	if (!pskb_may_pull(skb, *header_len + sizeof(*udphdr)))
+		return false;
+	udphdr = (struct udphdr *)(skb->data + *header_len);
+	*header_len += sizeof(*udphdr);
 
 	/* check for bootp port */
 	if ((ntohs(ethhdr->h_proto) == ETH_P_IP) &&
 	     (ntohs(udphdr->dest) != 67))
-		return 0;
+		return false;
 
 	if ((ntohs(ethhdr->h_proto) == ETH_P_IPV6) &&
 	    (ntohs(udphdr->dest) != 547))
-		return 0;
+		return false;
 
-	if (atomic_read(&bat_priv->gw_mode) == GW_MODE_SERVER)
-		return -1;
+	return true;
+}
 
-	curr_gw = gw_get_selected_gw_node(bat_priv);
-	if (!curr_gw)
-		return 0;
-
-	/* If old_gw != NULL then this packet is unicast.
-	 * So, at this point we have to check the message type: if it is a
-	 * DHCPREQUEST we have to decide whether to drop it or not */
-	if (old_gw && curr_gw->orig_node != old_gw) {
-		if (is_type_dhcprequest(skb, header_len)) {
-			/* If the dhcp packet has been sent to a different gw,
-			 * we have to evaluate whether the old gw is still
-			 * reliable enough */
-			neigh_curr = find_router(bat_priv, curr_gw->orig_node,
-						 NULL);
-			neigh_old = find_router(bat_priv, old_gw, NULL);
-			if (!neigh_curr || !neigh_old)
-				goto free_neigh;
-			if (neigh_curr->tq_avg - neigh_old->tq_avg <
-								GW_THRESHOLD)
-				ret = -1;
-		}
+bool gw_out_of_range(struct bat_priv *bat_priv,
+		     struct sk_buff *skb, struct ethhdr *ethhdr)
+{
+	struct neigh_node *neigh_curr = NULL, *neigh_old = NULL;
+	struct orig_node *orig_dst_node = NULL;
+	struct gw_node *curr_gw = NULL;
+	bool ret, out_of_range = false;
+	unsigned int header_len = 0;
+	uint8_t curr_tq_avg;
+
+	ret = gw_is_dhcp_target(skb, &header_len);
+	if (!ret)
+		goto out;
+
+	orig_dst_node = transtable_search(bat_priv, ethhdr->h_source,
+					  ethhdr->h_dest);
+	if (!orig_dst_node)
+		goto out;
+
+	if (!orig_dst_node->gw_flags)
+		goto out;
+
+	ret = is_type_dhcprequest(skb, header_len);
+	if (!ret)
+		goto out;
+
+	switch (atomic_read(&bat_priv->gw_mode)) {
+	case GW_MODE_SERVER:
+		/* If we are a GW then we are our best GW. We can artificially
+		 * set the tq towards ourself as the maximum value */
+		curr_tq_avg = TQ_MAX_VALUE;
+		break;
+	case GW_MODE_CLIENT:
+		curr_gw = gw_get_selected_gw_node(bat_priv);
+		if (!curr_gw)
+			goto out;
+
+		/* packet is going to our gateway */
+		if (curr_gw->orig_node == orig_dst_node)
+			goto out;
+
+		/* If the dhcp packet has been sent to a different gw,
+		 * we have to evaluate whether the old gw is still
+		 * reliable enough */
+		neigh_curr = find_router(bat_priv, curr_gw->orig_node, NULL);
+		if (!neigh_curr)
+			goto out;
+
+		curr_tq_avg = neigh_curr->tq_avg;
+		break;
+	case GW_MODE_OFF:
+	default:
+		goto out;
 	}
-free_neigh:
+
+	neigh_old = find_router(bat_priv, orig_dst_node, NULL);
+	if (!neigh_old)
+		goto out;
+
+	if (curr_tq_avg - neigh_old->tq_avg > GW_THRESHOLD)
+		out_of_range = true;
+
+out:
+	if (orig_dst_node)
+		orig_node_free_ref(orig_dst_node);
+	if (curr_gw)
+		gw_node_free_ref(curr_gw);
 	if (neigh_old)
 		neigh_node_free_ref(neigh_old);
 	if (neigh_curr)
 		neigh_node_free_ref(neigh_curr);
-	if (curr_gw)
-		gw_node_free_ref(curr_gw);
-	return ret;
+	return out_of_range;
 }
diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h
index b9b983c..e1edba0 100644
--- a/net/batman-adv/gateway_client.h
+++ b/net/batman-adv/gateway_client.h
@@ -31,7 +31,8 @@ void gw_node_update(struct bat_priv *bat_priv,
 void gw_node_delete(struct bat_priv *bat_priv, struct orig_node *orig_node);
 void gw_node_purge(struct bat_priv *bat_priv);
 int gw_client_seq_print_text(struct seq_file *seq, void *offset);
-int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb,
-		 struct orig_node *old_gw);
+bool gw_is_dhcp_target(struct sk_buff *skb, unsigned int *header_len);
+bool gw_out_of_range(struct bat_priv *bat_priv,
+		     struct sk_buff *skb, struct ethhdr *ethhdr);
 
 #endif /* _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ */
diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c
index 18661af..c4ac7b0 100644
--- a/net/batman-adv/gateway_common.c
+++ b/net/batman-adv/gateway_common.c
@@ -97,7 +97,7 @@ static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff,
 			*tmp_ptr = '\0';
 	}
 
-	ret = strict_strtol(buff, 10, &ldown);
+	ret = kstrtol(buff, 10, &ldown);
 	if (ret) {
 		bat_err(net_dev,
 			"Download speed of gateway mode invalid: %s\n",
@@ -122,7 +122,7 @@ static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff,
 				*tmp_ptr = '\0';
 		}
 
-		ret = strict_strtol(slash_ptr + 1, 10, &lup);
+		ret = kstrtol(slash_ptr + 1, 10, &lup);
 		if (ret) {
 			bat_err(net_dev,
 				"Upload speed of gateway mode invalid: "
diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c
index 2a17250..d1da29d 100644
--- a/net/batman-adv/hash.c
+++ b/net/batman-adv/hash.c
@@ -25,7 +25,7 @@
 /* clears the hash */
 static void hash_init(struct hashtable_t *hash)
 {
-	int i;
+	uint32_t i;
 
 	for (i = 0 ; i < hash->size; i++) {
 		INIT_HLIST_HEAD(&hash->table[i]);
@@ -42,7 +42,7 @@ void hash_destroy(struct hashtable_t *hash)
 }
 
 /* allocates and clears the hash */
-struct hashtable_t *hash_new(int size)
+struct hashtable_t *hash_new(uint32_t size)
 {
 	struct hashtable_t *hash;
 
diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h
index d20aa71..4768717 100644
--- a/net/batman-adv/hash.h
+++ b/net/batman-adv/hash.h
@@ -33,17 +33,17 @@ typedef int (*hashdata_compare_cb)(const struct hlist_node *, const void *);
 /* the hashfunction, should return an index
  * based on the key in the data of the first
  * argument and the size the second */
-typedef int (*hashdata_choose_cb)(const void *, int);
+typedef uint32_t (*hashdata_choose_cb)(const void *, uint32_t);
 typedef void (*hashdata_free_cb)(struct hlist_node *, void *);
 
 struct hashtable_t {
 	struct hlist_head *table;   /* the hashtable itself with the buckets */
 	spinlock_t *list_locks;     /* spinlock for each hash list entry */
-	int size;		    /* size of hashtable */
+	uint32_t size;		    /* size of hashtable */
 };
 
 /* allocates and clears the hash */
-struct hashtable_t *hash_new(int size);
+struct hashtable_t *hash_new(uint32_t size);
 
 /* free only the hashtable and the hash itself. */
 void hash_destroy(struct hashtable_t *hash);
@@ -57,7 +57,7 @@ static inline void hash_delete(struct hashtable_t *hash,
 	struct hlist_head *head;
 	struct hlist_node *node, *node_tmp;
 	spinlock_t *list_lock; /* spinlock to protect write access */
-	int i;
+	uint32_t i;
 
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
@@ -93,7 +93,8 @@ static inline int hash_add(struct hashtable_t *hash,
 			   hashdata_choose_cb choose,
 			   const void *data, struct hlist_node *data_node)
 {
-	int index, ret = -1;
+	uint32_t index;
+	int ret = -1;
 	struct hlist_head *head;
 	struct hlist_node *node;
 	spinlock_t *list_lock; /* spinlock to protect write access */
@@ -137,7 +138,7 @@ static inline void *hash_remove(struct hashtable_t *hash,
 				hashdata_compare_cb compare,
 				hashdata_choose_cb choose, void *data)
 {
-	size_t index;
+	uint32_t index;
 	struct hlist_node *node;
 	struct hlist_head *head;
 	void *data_save = NULL;
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c
index ac3520e..d9c1e7b 100644
--- a/net/batman-adv/icmp_socket.c
+++ b/net/batman-adv/icmp_socket.c
@@ -136,10 +136,9 @@ static ssize_t bat_socket_read(struct file *file, char __user *buf,
 
 	spin_unlock_bh(&socket_client->lock);
 
-	error = __copy_to_user(buf, &socket_packet->icmp_packet,
-			       socket_packet->icmp_len);
+	packet_len = min(count, socket_packet->icmp_len);
+	error = copy_to_user(buf, &socket_packet->icmp_packet, packet_len);
 
-	packet_len = socket_packet->icmp_len;
 	kfree(socket_packet);
 
 	if (error)
@@ -187,12 +186,7 @@ static ssize_t bat_socket_write(struct file *file, const char __user *buff,
 	skb_reserve(skb, sizeof(struct ethhdr));
 	icmp_packet = (struct icmp_packet_rr *)skb_put(skb, packet_len);
 
-	if (!access_ok(VERIFY_READ, buff, packet_len)) {
-		len = -EFAULT;
-		goto free_skb;
-	}
-
-	if (__copy_from_user(icmp_packet, buff, packet_len)) {
+	if (copy_from_user(icmp_packet, buff, packet_len)) {
 		len = -EFAULT;
 		goto free_skb;
 	}
@@ -217,7 +211,7 @@ static ssize_t bat_socket_write(struct file *file, const char __user *buff,
 
 	if (icmp_packet->version != COMPAT_VERSION) {
 		icmp_packet->msg_type = PARAMETER_PROBLEM;
-		icmp_packet->ttl = COMPAT_VERSION;
+		icmp_packet->version = COMPAT_VERSION;
 		bat_socket_add_packet(socket_client, icmp_packet, packet_len);
 		goto free_skb;
 	}
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 964ad4d..86354e0 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -28,7 +28,7 @@
 #define DRIVER_DEVICE "batman-adv"
 
 #ifndef SOURCE_VERSION
-#define SOURCE_VERSION "2011.4.0"
+#define SOURCE_VERSION "2012.0.0"
 #endif
 
 /* B.A.T.M.A.N. parameters */
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 0e5b772..0bc2045 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -164,7 +164,7 @@ void originator_free(struct bat_priv *bat_priv)
 	struct hlist_head *head;
 	spinlock_t *list_lock; /* spinlock to protect write access */
 	struct orig_node *orig_node;
-	int i;
+	uint32_t i;
 
 	if (!hash)
 		return;
@@ -350,7 +350,7 @@ static void _purge_orig(struct bat_priv *bat_priv)
 	struct hlist_head *head;
 	spinlock_t *list_lock; /* spinlock to protect write access */
 	struct orig_node *orig_node;
-	int i;
+	uint32_t i;
 
 	if (!hash)
 		return;
@@ -413,7 +413,8 @@ int orig_seq_print_text(struct seq_file *seq, void *offset)
 	int batman_count = 0;
 	int last_seen_secs;
 	int last_seen_msecs;
-	int i, ret = 0;
+	uint32_t i;
+	int ret = 0;
 
 	primary_if = primary_if_get_selected(bat_priv);
 
@@ -519,7 +520,8 @@ int orig_hash_add_if(struct hard_iface *hard_iface, int max_if_num)
 	struct hlist_node *node;
 	struct hlist_head *head;
 	struct orig_node *orig_node;
-	int i, ret;
+	uint32_t i;
+	int ret;
 
 	/* resize all orig nodes because orig_node->bcast_own(_sum) depend on
 	 * if_num */
@@ -601,7 +603,8 @@ int orig_hash_del_if(struct hard_iface *hard_iface, int max_if_num)
 	struct hlist_head *head;
 	struct hard_iface *hard_iface_tmp;
 	struct orig_node *orig_node;
-	int i, ret;
+	uint32_t i;
+	int ret;
 
 	/* resize all orig nodes because orig_node->bcast_own(_sum) depend on
 	 * if_num */
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index cfc1f60..67765ff 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -42,7 +42,7 @@ int orig_hash_del_if(struct hard_iface *hard_iface, int max_if_num);
 
 /* hashfunction to choose an entry in a hash table of given size */
 /* hash algorithm from http://en.wikipedia.org/wiki/Hash_table */
-static inline int choose_orig(const void *data, int32_t size)
+static inline uint32_t choose_orig(const void *data, uint32_t size)
 {
 	const unsigned char *key = data;
 	uint32_t hash = 0;
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index f961cc5..773e606 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -39,7 +39,7 @@ void slide_own_bcast_window(struct hard_iface *hard_iface)
 	struct hlist_head *head;
 	struct orig_node *orig_node;
 	unsigned long *word;
-	int i;
+	uint32_t i;
 	size_t word_index;
 
 	for (i = 0; i < hash->size; i++) {
@@ -578,6 +578,7 @@ int recv_tt_query(struct sk_buff *skb, struct hard_iface *recv_if)
 {
 	struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface);
 	struct tt_query_packet *tt_query;
+	uint16_t tt_len;
 	struct ethhdr *ethhdr;
 
 	/* drop packet if it has not necessary minimum size */
@@ -616,13 +617,21 @@ int recv_tt_query(struct sk_buff *skb, struct hard_iface *recv_if)
 		}
 		break;
 	case TT_RESPONSE:
-		/* packet needs to be linearized to access the TT changes */
-		if (skb_linearize(skb) < 0)
-			goto out;
+		if (is_my_mac(tt_query->dst)) {
+			/* packet needs to be linearized to access the TT
+			 * changes */
+			if (skb_linearize(skb) < 0)
+				goto out;
+
+			tt_len = tt_query->tt_data * sizeof(struct tt_change);
+
+			/* Ensure we have all the claimed data */
+			if (unlikely(skb_headlen(skb) <
+				     sizeof(struct tt_query_packet) + tt_len))
+				goto out;
 
-		if (is_my_mac(tt_query->dst))
 			handle_tt_response(bat_priv, tt_query);
-		else {
+		} else {
 			bat_dbg(DBG_TT, bat_priv,
 				"Routing TT_RESPONSE to %pM [%c]\n",
 				tt_query->dst,
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index f9cc957..987c75a 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -563,10 +563,10 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface)
 	struct bcast_packet *bcast_packet;
 	struct vlan_ethhdr *vhdr;
 	struct softif_neigh *curr_softif_neigh = NULL;
-	struct orig_node *orig_node = NULL;
+	unsigned int header_len = 0;
 	int data_len = skb->len, ret;
 	short vid = -1;
-	bool do_bcast;
+	bool do_bcast = false;
 
 	if (atomic_read(&bat_priv->mesh_state) != MESH_ACTIVE)
 		goto dropped;
@@ -598,17 +598,28 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface)
 	/* Register the client MAC in the transtable */
 	tt_local_add(soft_iface, ethhdr->h_source, skb->skb_iif);
 
-	orig_node = transtable_search(bat_priv, ethhdr->h_source,
-				      ethhdr->h_dest);
-	do_bcast = is_multicast_ether_addr(ethhdr->h_dest);
-	if (do_bcast || (orig_node && orig_node->gw_flags)) {
-		ret = gw_is_target(bat_priv, skb, orig_node);
+	if (is_multicast_ether_addr(ethhdr->h_dest)) {
+		do_bcast = true;
 
-		if (ret < 0)
-			goto dropped;
-
-		if (ret)
-			do_bcast = false;
+		switch (atomic_read(&bat_priv->gw_mode)) {
+		case GW_MODE_SERVER:
+			/* gateway servers should not send dhcp
+			 * requests into the mesh */
+			ret = gw_is_dhcp_target(skb, &header_len);
+			if (ret)
+				goto dropped;
+			break;
+		case GW_MODE_CLIENT:
+			/* gateway clients should send dhcp requests
+			 * via unicast to their gateway */
+			ret = gw_is_dhcp_target(skb, &header_len);
+			if (ret)
+				do_bcast = false;
+			break;
+		case GW_MODE_OFF:
+		default:
+			break;
+		}
 	}
 
 	/* ethernet packet should be broadcasted */
@@ -644,6 +655,12 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface)
 
 	/* unicast packet */
 	} else {
+		if (atomic_read(&bat_priv->gw_mode) != GW_MODE_OFF) {
+			ret = gw_out_of_range(bat_priv, skb, ethhdr);
+			if (ret)
+				goto dropped;
+		}
+
 		ret = unicast_send_skb(skb, bat_priv);
 		if (ret != 0)
 			goto dropped_freed;
@@ -662,8 +679,6 @@ end:
 		softif_neigh_free_ref(curr_softif_neigh);
 	if (primary_if)
 		hardif_free_ref(primary_if);
-	if (orig_node)
-		orig_node_free_ref(orig_node);
 	return NETDEV_TX_OK;
 }
 
@@ -859,7 +874,7 @@ unreg_debugfs:
 unreg_sysfs:
 	sysfs_del_meshif(soft_iface);
 unreg_soft_iface:
-	unregister_netdev(soft_iface);
+	unregister_netdevice(soft_iface);
 	return NULL;
 
 free_soft_iface:
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index c7aafc7..ab8dea8 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -36,18 +36,9 @@ static void _tt_global_del(struct bat_priv *bat_priv,
 static void tt_purge(struct work_struct *work);
 
 /* returns 1 if they are the same mac addr */
-static int compare_ltt(const struct hlist_node *node, const void *data2)
+static int compare_tt(const struct hlist_node *node, const void *data2)
 {
-	const void *data1 = container_of(node, struct tt_local_entry,
-					 hash_entry);
-
-	return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0);
-}
-
-/* returns 1 if they are the same mac addr */
-static int compare_gtt(const struct hlist_node *node, const void *data2)
-{
-	const void *data1 = container_of(node, struct tt_global_entry,
+	const void *data1 = container_of(node, struct tt_common_entry,
 					 hash_entry);
 
 	return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0);
@@ -60,14 +51,13 @@ static void tt_start_timer(struct bat_priv *bat_priv)
 			   msecs_to_jiffies(5000));
 }
 
-static struct tt_local_entry *tt_local_hash_find(struct bat_priv *bat_priv,
-						 const void *data)
+static struct tt_common_entry *tt_hash_find(struct hashtable_t *hash,
+					    const void *data)
 {
-	struct hashtable_t *hash = bat_priv->tt_local_hash;
 	struct hlist_head *head;
 	struct hlist_node *node;
-	struct tt_local_entry *tt_local_entry, *tt_local_entry_tmp = NULL;
-	int index;
+	struct tt_common_entry *tt_common_entry, *tt_common_entry_tmp = NULL;
+	uint32_t index;
 
 	if (!hash)
 		return NULL;
@@ -76,51 +66,46 @@ static struct tt_local_entry *tt_local_hash_find(struct bat_priv *bat_priv,
 	head = &hash->table[index];
 
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(tt_local_entry, node, head, hash_entry) {
-		if (!compare_eth(tt_local_entry, data))
+	hlist_for_each_entry_rcu(tt_common_entry, node, head, hash_entry) {
+		if (!compare_eth(tt_common_entry, data))
 			continue;
 
-		if (!atomic_inc_not_zero(&tt_local_entry->refcount))
+		if (!atomic_inc_not_zero(&tt_common_entry->refcount))
 			continue;
 
-		tt_local_entry_tmp = tt_local_entry;
+		tt_common_entry_tmp = tt_common_entry;
 		break;
 	}
 	rcu_read_unlock();
 
-	return tt_local_entry_tmp;
+	return tt_common_entry_tmp;
 }
 
-static struct tt_global_entry *tt_global_hash_find(struct bat_priv *bat_priv,
-						   const void *data)
+static struct tt_local_entry *tt_local_hash_find(struct bat_priv *bat_priv,
+						 const void *data)
 {
-	struct hashtable_t *hash = bat_priv->tt_global_hash;
-	struct hlist_head *head;
-	struct hlist_node *node;
-	struct tt_global_entry *tt_global_entry;
-	struct tt_global_entry *tt_global_entry_tmp = NULL;
-	int index;
-
-	if (!hash)
-		return NULL;
-
-	index = choose_orig(data, hash->size);
-	head = &hash->table[index];
+	struct tt_common_entry *tt_common_entry;
+	struct tt_local_entry *tt_local_entry = NULL;
 
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(tt_global_entry, node, head, hash_entry) {
-		if (!compare_eth(tt_global_entry, data))
-			continue;
+	tt_common_entry = tt_hash_find(bat_priv->tt_local_hash, data);
+	if (tt_common_entry)
+		tt_local_entry = container_of(tt_common_entry,
+					      struct tt_local_entry, common);
+	return tt_local_entry;
+}
 
-		if (!atomic_inc_not_zero(&tt_global_entry->refcount))
-			continue;
+static struct tt_global_entry *tt_global_hash_find(struct bat_priv *bat_priv,
+						   const void *data)
+{
+	struct tt_common_entry *tt_common_entry;
+	struct tt_global_entry *tt_global_entry = NULL;
 
-		tt_global_entry_tmp = tt_global_entry;
-		break;
-	}
-	rcu_read_unlock();
+	tt_common_entry = tt_hash_find(bat_priv->tt_global_hash, data);
+	if (tt_common_entry)
+		tt_global_entry = container_of(tt_common_entry,
+					       struct tt_global_entry, common);
+	return tt_global_entry;
 
-	return tt_global_entry_tmp;
 }
 
 static bool is_out_of_time(unsigned long starting_time, unsigned long timeout)
@@ -133,15 +118,18 @@ static bool is_out_of_time(unsigned long starting_time, unsigned long timeout)
 
 static void tt_local_entry_free_ref(struct tt_local_entry *tt_local_entry)
 {
-	if (atomic_dec_and_test(&tt_local_entry->refcount))
-		kfree_rcu(tt_local_entry, rcu);
+	if (atomic_dec_and_test(&tt_local_entry->common.refcount))
+		kfree_rcu(tt_local_entry, common.rcu);
 }
 
 static void tt_global_entry_free_rcu(struct rcu_head *rcu)
 {
+	struct tt_common_entry *tt_common_entry;
 	struct tt_global_entry *tt_global_entry;
 
-	tt_global_entry = container_of(rcu, struct tt_global_entry, rcu);
+	tt_common_entry = container_of(rcu, struct tt_common_entry, rcu);
+	tt_global_entry = container_of(tt_common_entry, struct tt_global_entry,
+				       common);
 
 	if (tt_global_entry->orig_node)
 		orig_node_free_ref(tt_global_entry->orig_node);
@@ -151,8 +139,9 @@ static void tt_global_entry_free_rcu(struct rcu_head *rcu)
 
 static void tt_global_entry_free_ref(struct tt_global_entry *tt_global_entry)
 {
-	if (atomic_dec_and_test(&tt_global_entry->refcount))
-		call_rcu(&tt_global_entry->rcu, tt_global_entry_free_rcu);
+	if (atomic_dec_and_test(&tt_global_entry->common.refcount))
+		call_rcu(&tt_global_entry->common.rcu,
+			 tt_global_entry_free_rcu);
 }
 
 static void tt_local_event(struct bat_priv *bat_priv, const uint8_t *addr,
@@ -201,6 +190,7 @@ void tt_local_add(struct net_device *soft_iface, const uint8_t *addr,
 	struct bat_priv *bat_priv = netdev_priv(soft_iface);
 	struct tt_local_entry *tt_local_entry = NULL;
 	struct tt_global_entry *tt_global_entry = NULL;
+	int hash_added;
 
 	tt_local_entry = tt_local_hash_find(bat_priv, addr);
 
@@ -217,26 +207,33 @@ void tt_local_add(struct net_device *soft_iface, const uint8_t *addr,
 		"Creating new local tt entry: %pM (ttvn: %d)\n", addr,
 		(uint8_t)atomic_read(&bat_priv->ttvn));
 
-	memcpy(tt_local_entry->addr, addr, ETH_ALEN);
-	tt_local_entry->last_seen = jiffies;
-	tt_local_entry->flags = NO_FLAGS;
+	memcpy(tt_local_entry->common.addr, addr, ETH_ALEN);
+	tt_local_entry->common.flags = NO_FLAGS;
 	if (is_wifi_iface(ifindex))
-		tt_local_entry->flags |= TT_CLIENT_WIFI;
-	atomic_set(&tt_local_entry->refcount, 2);
+		tt_local_entry->common.flags |= TT_CLIENT_WIFI;
+	atomic_set(&tt_local_entry->common.refcount, 2);
+	tt_local_entry->last_seen = jiffies;
 
 	/* the batman interface mac address should never be purged */
 	if (compare_eth(addr, soft_iface->dev_addr))
-		tt_local_entry->flags |= TT_CLIENT_NOPURGE;
+		tt_local_entry->common.flags |= TT_CLIENT_NOPURGE;
 
-	tt_local_event(bat_priv, addr, tt_local_entry->flags);
+	hash_added = hash_add(bat_priv->tt_local_hash, compare_tt, choose_orig,
+			 &tt_local_entry->common,
+			 &tt_local_entry->common.hash_entry);
+
+	if (unlikely(hash_added != 0)) {
+		/* remove the reference for the hash */
+		tt_local_entry_free_ref(tt_local_entry);
+		goto out;
+	}
+
+	tt_local_event(bat_priv, addr, tt_local_entry->common.flags);
 
 	/* The local entry has to be marked as NEW to avoid to send it in
 	 * a full table response going out before the next ttvn increment
 	 * (consistency check) */
-	tt_local_entry->flags |= TT_CLIENT_NEW;
-
-	hash_add(bat_priv->tt_local_hash, compare_ltt, choose_orig,
-		 tt_local_entry, &tt_local_entry->hash_entry);
+	tt_local_entry->common.flags |= TT_CLIENT_NEW;
 
 	/* remove address from global hash if present */
 	tt_global_entry = tt_global_hash_find(bat_priv, addr);
@@ -245,10 +242,11 @@ void tt_local_add(struct net_device *soft_iface, const uint8_t *addr,
 	if (tt_global_entry) {
 		/* This node is probably going to update its tt table */
 		tt_global_entry->orig_node->tt_poss_change = true;
-		/* The global entry has to be marked as PENDING and has to be
+		/* The global entry has to be marked as ROAMING and has to be
 		 * kept for consistency purpose */
-		tt_global_entry->flags |= TT_CLIENT_PENDING;
-		send_roam_adv(bat_priv, tt_global_entry->addr,
+		tt_global_entry->common.flags |= TT_CLIENT_ROAM;
+		tt_global_entry->roam_at = jiffies;
+		send_roam_adv(bat_priv, tt_global_entry->common.addr,
 			      tt_global_entry->orig_node);
 	}
 out:
@@ -310,13 +308,12 @@ int tt_local_seq_print_text(struct seq_file *seq, void *offset)
 	struct net_device *net_dev = (struct net_device *)seq->private;
 	struct bat_priv *bat_priv = netdev_priv(net_dev);
 	struct hashtable_t *hash = bat_priv->tt_local_hash;
-	struct tt_local_entry *tt_local_entry;
+	struct tt_common_entry *tt_common_entry;
 	struct hard_iface *primary_if;
 	struct hlist_node *node;
 	struct hlist_head *head;
-	size_t buf_size, pos;
-	char *buff;
-	int i, ret = 0;
+	uint32_t i;
+	int ret = 0;
 
 	primary_if = primary_if_get_selected(bat_priv);
 	if (!primary_if) {
@@ -337,51 +334,27 @@ int tt_local_seq_print_text(struct seq_file *seq, void *offset)
 		   "announced via TT (TTVN: %u):\n",
 		   net_dev->name, (uint8_t)atomic_read(&bat_priv->ttvn));
 
-	buf_size = 1;
-	/* Estimate length for: " * xx:xx:xx:xx:xx:xx\n" */
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
 
 		rcu_read_lock();
-		__hlist_for_each_rcu(node, head)
-			buf_size += 29;
-		rcu_read_unlock();
-	}
-
-	buff = kmalloc(buf_size, GFP_ATOMIC);
-	if (!buff) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	buff[0] = '\0';
-	pos = 0;
-
-	for (i = 0; i < hash->size; i++) {
-		head = &hash->table[i];
-
-		rcu_read_lock();
-		hlist_for_each_entry_rcu(tt_local_entry, node,
+		hlist_for_each_entry_rcu(tt_common_entry, node,
 					 head, hash_entry) {
-			pos += snprintf(buff + pos, 30, " * %pM "
-					"[%c%c%c%c%c]\n",
-					tt_local_entry->addr,
-					(tt_local_entry->flags &
+			seq_printf(seq, " * %pM [%c%c%c%c%c]\n",
+					tt_common_entry->addr,
+					(tt_common_entry->flags &
 					 TT_CLIENT_ROAM ? 'R' : '.'),
-					(tt_local_entry->flags &
+					(tt_common_entry->flags &
 					 TT_CLIENT_NOPURGE ? 'P' : '.'),
-					(tt_local_entry->flags &
+					(tt_common_entry->flags &
 					 TT_CLIENT_NEW ? 'N' : '.'),
-					(tt_local_entry->flags &
+					(tt_common_entry->flags &
 					 TT_CLIENT_PENDING ? 'X' : '.'),
-					(tt_local_entry->flags &
+					(tt_common_entry->flags &
 					 TT_CLIENT_WIFI ? 'W' : '.'));
 		}
 		rcu_read_unlock();
 	}
-
-	seq_printf(seq, "%s", buff);
-	kfree(buff);
 out:
 	if (primary_if)
 		hardif_free_ref(primary_if);
@@ -392,13 +365,13 @@ static void tt_local_set_pending(struct bat_priv *bat_priv,
 				 struct tt_local_entry *tt_local_entry,
 				 uint16_t flags)
 {
-	tt_local_event(bat_priv, tt_local_entry->addr,
-		       tt_local_entry->flags | flags);
+	tt_local_event(bat_priv, tt_local_entry->common.addr,
+		       tt_local_entry->common.flags | flags);
 
 	/* The local client has to be marked as "pending to be removed" but has
 	 * to be kept in the table in order to send it in a full table
 	 * response issued before the net ttvn increment (consistency check) */
-	tt_local_entry->flags |= TT_CLIENT_PENDING;
+	tt_local_entry->common.flags |= TT_CLIENT_PENDING;
 }
 
 void tt_local_remove(struct bat_priv *bat_priv, const uint8_t *addr,
@@ -414,7 +387,7 @@ void tt_local_remove(struct bat_priv *bat_priv, const uint8_t *addr,
 			     (roaming ? TT_CLIENT_ROAM : NO_FLAGS));
 
 	bat_dbg(DBG_TT, bat_priv, "Local tt entry (%pM) pending to be removed: "
-		"%s\n", tt_local_entry->addr, message);
+		"%s\n", tt_local_entry->common.addr, message);
 out:
 	if (tt_local_entry)
 		tt_local_entry_free_ref(tt_local_entry);
@@ -424,23 +397,27 @@ static void tt_local_purge(struct bat_priv *bat_priv)
 {
 	struct hashtable_t *hash = bat_priv->tt_local_hash;
 	struct tt_local_entry *tt_local_entry;
+	struct tt_common_entry *tt_common_entry;
 	struct hlist_node *node, *node_tmp;
 	struct hlist_head *head;
 	spinlock_t *list_lock; /* protects write access to the hash lists */
-	int i;
+	uint32_t i;
 
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
 		list_lock = &hash->list_locks[i];
 
 		spin_lock_bh(list_lock);
-		hlist_for_each_entry_safe(tt_local_entry, node, node_tmp,
+		hlist_for_each_entry_safe(tt_common_entry, node, node_tmp,
 					  head, hash_entry) {
-			if (tt_local_entry->flags & TT_CLIENT_NOPURGE)
+			tt_local_entry = container_of(tt_common_entry,
+						      struct tt_local_entry,
+						      common);
+			if (tt_local_entry->common.flags & TT_CLIENT_NOPURGE)
 				continue;
 
 			/* entry already marked for deletion */
-			if (tt_local_entry->flags & TT_CLIENT_PENDING)
+			if (tt_local_entry->common.flags & TT_CLIENT_PENDING)
 				continue;
 
 			if (!is_out_of_time(tt_local_entry->last_seen,
@@ -451,7 +428,7 @@ static void tt_local_purge(struct bat_priv *bat_priv)
 					     TT_CLIENT_DEL);
 			bat_dbg(DBG_TT, bat_priv, "Local tt entry (%pM) "
 				"pending to be removed: timed out\n",
-				tt_local_entry->addr);
+				tt_local_entry->common.addr);
 		}
 		spin_unlock_bh(list_lock);
 	}
@@ -462,10 +439,11 @@ static void tt_local_table_free(struct bat_priv *bat_priv)
 {
 	struct hashtable_t *hash;
 	spinlock_t *list_lock; /* protects write access to the hash lists */
+	struct tt_common_entry *tt_common_entry;
 	struct tt_local_entry *tt_local_entry;
 	struct hlist_node *node, *node_tmp;
 	struct hlist_head *head;
-	int i;
+	uint32_t i;
 
 	if (!bat_priv->tt_local_hash)
 		return;
@@ -477,9 +455,12 @@ static void tt_local_table_free(struct bat_priv *bat_priv)
 		list_lock = &hash->list_locks[i];
 
 		spin_lock_bh(list_lock);
-		hlist_for_each_entry_safe(tt_local_entry, node, node_tmp,
+		hlist_for_each_entry_safe(tt_common_entry, node, node_tmp,
 					  head, hash_entry) {
 			hlist_del_rcu(node);
+			tt_local_entry = container_of(tt_common_entry,
+						      struct tt_local_entry,
+						      common);
 			tt_local_entry_free_ref(tt_local_entry);
 		}
 		spin_unlock_bh(list_lock);
@@ -527,6 +508,7 @@ int tt_global_add(struct bat_priv *bat_priv, struct orig_node *orig_node,
 	struct tt_global_entry *tt_global_entry;
 	struct orig_node *orig_node_tmp;
 	int ret = 0;
+	int hash_added;
 
 	tt_global_entry = tt_global_hash_find(bat_priv, tt_addr);
 
@@ -537,18 +519,24 @@ int tt_global_add(struct bat_priv *bat_priv, struct orig_node *orig_node,
 		if (!tt_global_entry)
 			goto out;
 
-		memcpy(tt_global_entry->addr, tt_addr, ETH_ALEN);
+		memcpy(tt_global_entry->common.addr, tt_addr, ETH_ALEN);
+		tt_global_entry->common.flags = NO_FLAGS;
+		atomic_set(&tt_global_entry->common.refcount, 2);
 		/* Assign the new orig_node */
 		atomic_inc(&orig_node->refcount);
 		tt_global_entry->orig_node = orig_node;
 		tt_global_entry->ttvn = ttvn;
-		tt_global_entry->flags = NO_FLAGS;
 		tt_global_entry->roam_at = 0;
-		atomic_set(&tt_global_entry->refcount, 2);
 
-		hash_add(bat_priv->tt_global_hash, compare_gtt,
-			 choose_orig, tt_global_entry,
-			 &tt_global_entry->hash_entry);
+		hash_added = hash_add(bat_priv->tt_global_hash, compare_tt,
+				 choose_orig, &tt_global_entry->common,
+				 &tt_global_entry->common.hash_entry);
+
+		if (unlikely(hash_added != 0)) {
+			/* remove the reference for the hash */
+			tt_global_entry_free_ref(tt_global_entry);
+			goto out_remove;
+		}
 		atomic_inc(&orig_node->tt_size);
 	} else {
 		if (tt_global_entry->orig_node != orig_node) {
@@ -559,20 +547,21 @@ int tt_global_add(struct bat_priv *bat_priv, struct orig_node *orig_node,
 			orig_node_free_ref(orig_node_tmp);
 			atomic_inc(&orig_node->tt_size);
 		}
+		tt_global_entry->common.flags = NO_FLAGS;
 		tt_global_entry->ttvn = ttvn;
-		tt_global_entry->flags = NO_FLAGS;
 		tt_global_entry->roam_at = 0;
 	}
 
 	if (wifi)
-		tt_global_entry->flags |= TT_CLIENT_WIFI;
+		tt_global_entry->common.flags |= TT_CLIENT_WIFI;
 
 	bat_dbg(DBG_TT, bat_priv,
 		"Creating new global tt entry: %pM (via %pM)\n",
-		tt_global_entry->addr, orig_node->orig);
+		tt_global_entry->common.addr, orig_node->orig);
 
+out_remove:
 	/* remove address from local hash if present */
-	tt_local_remove(bat_priv, tt_global_entry->addr,
+	tt_local_remove(bat_priv, tt_global_entry->common.addr,
 			"global tt received", roaming);
 	ret = 1;
 out:
@@ -586,13 +575,13 @@ int tt_global_seq_print_text(struct seq_file *seq, void *offset)
 	struct net_device *net_dev = (struct net_device *)seq->private;
 	struct bat_priv *bat_priv = netdev_priv(net_dev);
 	struct hashtable_t *hash = bat_priv->tt_global_hash;
+	struct tt_common_entry *tt_common_entry;
 	struct tt_global_entry *tt_global_entry;
 	struct hard_iface *primary_if;
 	struct hlist_node *node;
 	struct hlist_head *head;
-	size_t buf_size, pos;
-	char *buff;
-	int i, ret = 0;
+	uint32_t i;
+	int ret = 0;
 
 	primary_if = primary_if_get_selected(bat_priv);
 	if (!primary_if) {
@@ -615,53 +604,32 @@ int tt_global_seq_print_text(struct seq_file *seq, void *offset)
 	seq_printf(seq, "       %-13s %s       %-15s %s %s\n",
 		   "Client", "(TTVN)", "Originator", "(Curr TTVN)", "Flags");
 
-	buf_size = 1;
-	/* Estimate length for: " * xx:xx:xx:xx:xx:xx (ttvn) via
-	 * xx:xx:xx:xx:xx:xx (cur_ttvn)\n"*/
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
 
 		rcu_read_lock();
-		__hlist_for_each_rcu(node, head)
-			buf_size += 67;
-		rcu_read_unlock();
-	}
-
-	buff = kmalloc(buf_size, GFP_ATOMIC);
-	if (!buff) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	buff[0] = '\0';
-	pos = 0;
-
-	for (i = 0; i < hash->size; i++) {
-		head = &hash->table[i];
-
-		rcu_read_lock();
-		hlist_for_each_entry_rcu(tt_global_entry, node,
+		hlist_for_each_entry_rcu(tt_common_entry, node,
 					 head, hash_entry) {
-			pos += snprintf(buff + pos, 69,
-					" * %pM  (%3u) via %pM     (%3u)   "
-					"[%c%c%c]\n", tt_global_entry->addr,
+			tt_global_entry = container_of(tt_common_entry,
+						       struct tt_global_entry,
+						       common);
+			seq_printf(seq, " * %pM  (%3u) via %pM     (%3u)   "
+					"[%c%c%c]\n",
+					tt_global_entry->common.addr,
 					tt_global_entry->ttvn,
 					tt_global_entry->orig_node->orig,
 					(uint8_t) atomic_read(
 						&tt_global_entry->orig_node->
 						last_ttvn),
-					(tt_global_entry->flags &
+					(tt_global_entry->common.flags &
 					 TT_CLIENT_ROAM ? 'R' : '.'),
-					(tt_global_entry->flags &
+					(tt_global_entry->common.flags &
 					 TT_CLIENT_PENDING ? 'X' : '.'),
-					(tt_global_entry->flags &
+					(tt_global_entry->common.flags &
 					 TT_CLIENT_WIFI ? 'W' : '.'));
 		}
 		rcu_read_unlock();
 	}
-
-	seq_printf(seq, "%s", buff);
-	kfree(buff);
 out:
 	if (primary_if)
 		hardif_free_ref(primary_if);
@@ -677,13 +645,13 @@ static void _tt_global_del(struct bat_priv *bat_priv,
 
 	bat_dbg(DBG_TT, bat_priv,
 		"Deleting global tt entry %pM (via %pM): %s\n",
-		tt_global_entry->addr, tt_global_entry->orig_node->orig,
+		tt_global_entry->common.addr, tt_global_entry->orig_node->orig,
 		message);
 
 	atomic_dec(&tt_global_entry->orig_node->tt_size);
 
-	hash_remove(bat_priv->tt_global_hash, compare_gtt, choose_orig,
-		    tt_global_entry->addr);
+	hash_remove(bat_priv->tt_global_hash, compare_tt, choose_orig,
+		    tt_global_entry->common.addr);
 out:
 	if (tt_global_entry)
 		tt_global_entry_free_ref(tt_global_entry);
@@ -694,6 +662,7 @@ void tt_global_del(struct bat_priv *bat_priv,
 		   const char *message, bool roaming)
 {
 	struct tt_global_entry *tt_global_entry = NULL;
+	struct tt_local_entry *tt_local_entry = NULL;
 
 	tt_global_entry = tt_global_hash_find(bat_priv, addr);
 	if (!tt_global_entry)
@@ -701,22 +670,37 @@ void tt_global_del(struct bat_priv *bat_priv,
 
 	if (tt_global_entry->orig_node == orig_node) {
 		if (roaming) {
-			tt_global_entry->flags |= TT_CLIENT_ROAM;
-			tt_global_entry->roam_at = jiffies;
-			goto out;
+			/* if we are deleting a global entry due to a roam
+			 * event, there are two possibilities:
+			 * 1) the client roamed from node A to node B => we mark
+			 *    it with TT_CLIENT_ROAM, we start a timer and we
+			 *    wait for node B to claim it. In case of timeout
+			 *    the entry is purged.
+			 * 2) the client roamed to us => we can directly delete
+			 *    the global entry, since it is useless now. */
+			tt_local_entry = tt_local_hash_find(bat_priv,
+							    tt_global_entry->common.addr);
+			if (!tt_local_entry) {
+				tt_global_entry->common.flags |= TT_CLIENT_ROAM;
+				tt_global_entry->roam_at = jiffies;
+				goto out;
+			}
 		}
 		_tt_global_del(bat_priv, tt_global_entry, message);
 	}
 out:
 	if (tt_global_entry)
 		tt_global_entry_free_ref(tt_global_entry);
+	if (tt_local_entry)
+		tt_local_entry_free_ref(tt_local_entry);
 }
 
 void tt_global_del_orig(struct bat_priv *bat_priv,
 			struct orig_node *orig_node, const char *message)
 {
 	struct tt_global_entry *tt_global_entry;
-	int i;
+	struct tt_common_entry *tt_common_entry;
+	uint32_t i;
 	struct hashtable_t *hash = bat_priv->tt_global_hash;
 	struct hlist_node *node, *safe;
 	struct hlist_head *head;
@@ -730,14 +714,18 @@ void tt_global_del_orig(struct bat_priv *bat_priv,
 		list_lock = &hash->list_locks[i];
 
 		spin_lock_bh(list_lock);
-		hlist_for_each_entry_safe(tt_global_entry, node, safe,
+		hlist_for_each_entry_safe(tt_common_entry, node, safe,
 					 head, hash_entry) {
+			tt_global_entry = container_of(tt_common_entry,
+						       struct tt_global_entry,
+						       common);
 			if (tt_global_entry->orig_node == orig_node) {
 				bat_dbg(DBG_TT, bat_priv,
 					"Deleting global tt entry %pM "
-					"(via %pM): originator time out\n",
-					tt_global_entry->addr,
-					tt_global_entry->orig_node->orig);
+					"(via %pM): %s\n",
+					tt_global_entry->common.addr,
+					tt_global_entry->orig_node->orig,
+					message);
 				hlist_del_rcu(node);
 				tt_global_entry_free_ref(tt_global_entry);
 			}
@@ -750,20 +738,24 @@ void tt_global_del_orig(struct bat_priv *bat_priv,
 static void tt_global_roam_purge(struct bat_priv *bat_priv)
 {
 	struct hashtable_t *hash = bat_priv->tt_global_hash;
+	struct tt_common_entry *tt_common_entry;
 	struct tt_global_entry *tt_global_entry;
 	struct hlist_node *node, *node_tmp;
 	struct hlist_head *head;
 	spinlock_t *list_lock; /* protects write access to the hash lists */
-	int i;
+	uint32_t i;
 
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
 		list_lock = &hash->list_locks[i];
 
 		spin_lock_bh(list_lock);
-		hlist_for_each_entry_safe(tt_global_entry, node, node_tmp,
+		hlist_for_each_entry_safe(tt_common_entry, node, node_tmp,
 					  head, hash_entry) {
-			if (!(tt_global_entry->flags & TT_CLIENT_ROAM))
+			tt_global_entry = container_of(tt_common_entry,
+						       struct tt_global_entry,
+						       common);
+			if (!(tt_global_entry->common.flags & TT_CLIENT_ROAM))
 				continue;
 			if (!is_out_of_time(tt_global_entry->roam_at,
 					    TT_CLIENT_ROAM_TIMEOUT * 1000))
@@ -771,7 +763,7 @@ static void tt_global_roam_purge(struct bat_priv *bat_priv)
 
 			bat_dbg(DBG_TT, bat_priv, "Deleting global "
 				"tt entry (%pM): Roaming timeout\n",
-				tt_global_entry->addr);
+				tt_global_entry->common.addr);
 			atomic_dec(&tt_global_entry->orig_node->tt_size);
 			hlist_del_rcu(node);
 			tt_global_entry_free_ref(tt_global_entry);
@@ -785,10 +777,11 @@ static void tt_global_table_free(struct bat_priv *bat_priv)
 {
 	struct hashtable_t *hash;
 	spinlock_t *list_lock; /* protects write access to the hash lists */
+	struct tt_common_entry *tt_common_entry;
 	struct tt_global_entry *tt_global_entry;
 	struct hlist_node *node, *node_tmp;
 	struct hlist_head *head;
-	int i;
+	uint32_t i;
 
 	if (!bat_priv->tt_global_hash)
 		return;
@@ -800,9 +793,12 @@ static void tt_global_table_free(struct bat_priv *bat_priv)
 		list_lock = &hash->list_locks[i];
 
 		spin_lock_bh(list_lock);
-		hlist_for_each_entry_safe(tt_global_entry, node, node_tmp,
+		hlist_for_each_entry_safe(tt_common_entry, node, node_tmp,
 					  head, hash_entry) {
 			hlist_del_rcu(node);
+			tt_global_entry = container_of(tt_common_entry,
+						       struct tt_global_entry,
+						       common);
 			tt_global_entry_free_ref(tt_global_entry);
 		}
 		spin_unlock_bh(list_lock);
@@ -818,8 +814,8 @@ static bool _is_ap_isolated(struct tt_local_entry *tt_local_entry,
 {
 	bool ret = false;
 
-	if (tt_local_entry->flags & TT_CLIENT_WIFI &&
-	    tt_global_entry->flags & TT_CLIENT_WIFI)
+	if (tt_local_entry->common.flags & TT_CLIENT_WIFI &&
+	    tt_global_entry->common.flags & TT_CLIENT_WIFI)
 		ret = true;
 
 	return ret;
@@ -852,7 +848,7 @@ struct orig_node *transtable_search(struct bat_priv *bat_priv,
 
 	/* A global client marked as PENDING has already moved from that
 	 * originator */
-	if (tt_global_entry->flags & TT_CLIENT_PENDING)
+	if (tt_global_entry->common.flags & TT_CLIENT_PENDING)
 		goto out;
 
 	orig_node = tt_global_entry->orig_node;
@@ -871,29 +867,34 @@ uint16_t tt_global_crc(struct bat_priv *bat_priv, struct orig_node *orig_node)
 {
 	uint16_t total = 0, total_one;
 	struct hashtable_t *hash = bat_priv->tt_global_hash;
+	struct tt_common_entry *tt_common_entry;
 	struct tt_global_entry *tt_global_entry;
 	struct hlist_node *node;
 	struct hlist_head *head;
-	int i, j;
+	uint32_t i;
+	int j;
 
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
 
 		rcu_read_lock();
-		hlist_for_each_entry_rcu(tt_global_entry, node,
+		hlist_for_each_entry_rcu(tt_common_entry, node,
 					 head, hash_entry) {
+			tt_global_entry = container_of(tt_common_entry,
+						       struct tt_global_entry,
+						       common);
 			if (compare_eth(tt_global_entry->orig_node,
 					orig_node)) {
 				/* Roaming clients are in the global table for
 				 * consistency only. They don't have to be
 				 * taken into account while computing the
 				 * global crc */
-				if (tt_global_entry->flags & TT_CLIENT_ROAM)
+				if (tt_common_entry->flags & TT_CLIENT_ROAM)
 					continue;
 				total_one = 0;
 				for (j = 0; j < ETH_ALEN; j++)
 					total_one = crc16_byte(total_one,
-						tt_global_entry->addr[j]);
+						tt_common_entry->addr[j]);
 				total ^= total_one;
 			}
 		}
@@ -908,25 +909,26 @@ uint16_t tt_local_crc(struct bat_priv *bat_priv)
 {
 	uint16_t total = 0, total_one;
 	struct hashtable_t *hash = bat_priv->tt_local_hash;
-	struct tt_local_entry *tt_local_entry;
+	struct tt_common_entry *tt_common_entry;
 	struct hlist_node *node;
 	struct hlist_head *head;
-	int i, j;
+	uint32_t i;
+	int j;
 
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
 
 		rcu_read_lock();
-		hlist_for_each_entry_rcu(tt_local_entry, node,
+		hlist_for_each_entry_rcu(tt_common_entry, node,
 					 head, hash_entry) {
 			/* not yet committed clients have not to be taken into
 			 * account while computing the CRC */
-			if (tt_local_entry->flags & TT_CLIENT_NEW)
+			if (tt_common_entry->flags & TT_CLIENT_NEW)
 				continue;
 			total_one = 0;
 			for (j = 0; j < ETH_ALEN; j++)
 				total_one = crc16_byte(total_one,
-						   tt_local_entry->addr[j]);
+						   tt_common_entry->addr[j]);
 			total ^= total_one;
 		}
 		rcu_read_unlock();
@@ -1015,21 +1017,25 @@ unlock:
 /* data_ptr is useless here, but has to be kept to respect the prototype */
 static int tt_local_valid_entry(const void *entry_ptr, const void *data_ptr)
 {
-	const struct tt_local_entry *tt_local_entry = entry_ptr;
+	const struct tt_common_entry *tt_common_entry = entry_ptr;
 
-	if (tt_local_entry->flags & TT_CLIENT_NEW)
+	if (tt_common_entry->flags & TT_CLIENT_NEW)
 		return 0;
 	return 1;
 }
 
 static int tt_global_valid_entry(const void *entry_ptr, const void *data_ptr)
 {
-	const struct tt_global_entry *tt_global_entry = entry_ptr;
+	const struct tt_common_entry *tt_common_entry = entry_ptr;
+	const struct tt_global_entry *tt_global_entry;
 	const struct orig_node *orig_node = data_ptr;
 
-	if (tt_global_entry->flags & TT_CLIENT_ROAM)
+	if (tt_common_entry->flags & TT_CLIENT_ROAM)
 		return 0;
 
+	tt_global_entry = container_of(tt_common_entry, struct tt_global_entry,
+				       common);
+
 	return (tt_global_entry->orig_node == orig_node);
 }
 
@@ -1040,7 +1046,7 @@ static struct sk_buff *tt_response_fill_table(uint16_t tt_len, uint8_t ttvn,
 							      const void *),
 					      void *cb_data)
 {
-	struct tt_local_entry *tt_local_entry;
+	struct tt_common_entry *tt_common_entry;
 	struct tt_query_packet *tt_response;
 	struct tt_change *tt_change;
 	struct hlist_node *node;
@@ -1048,7 +1054,7 @@ static struct sk_buff *tt_response_fill_table(uint16_t tt_len, uint8_t ttvn,
 	struct sk_buff *skb = NULL;
 	uint16_t tt_tot, tt_count;
 	ssize_t tt_query_size = sizeof(struct tt_query_packet);
-	int i;
+	uint32_t i;
 
 	if (tt_query_size + tt_len > primary_if->soft_iface->mtu) {
 		tt_len = primary_if->soft_iface->mtu - tt_query_size;
@@ -1072,15 +1078,16 @@ static struct sk_buff *tt_response_fill_table(uint16_t tt_len, uint8_t ttvn,
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
 
-		hlist_for_each_entry_rcu(tt_local_entry, node,
+		hlist_for_each_entry_rcu(tt_common_entry, node,
 					 head, hash_entry) {
 			if (tt_count == tt_tot)
 				break;
 
-			if ((valid_cb) && (!valid_cb(tt_local_entry, cb_data)))
+			if ((valid_cb) && (!valid_cb(tt_common_entry, cb_data)))
 				continue;
 
-			memcpy(tt_change->addr, tt_local_entry->addr, ETH_ALEN);
+			memcpy(tt_change->addr, tt_common_entry->addr,
+			       ETH_ALEN);
 			tt_change->flags = NO_FLAGS;
 
 			tt_count++;
@@ -1187,11 +1194,11 @@ static bool send_other_tt_response(struct bat_priv *bat_priv,
 		(tt_request->flags & TT_FULL_TABLE ? 'F' : '.'));
 
 	/* Let's get the orig node of the REAL destination */
-	req_dst_orig_node = get_orig_node(bat_priv, tt_request->dst);
+	req_dst_orig_node = orig_hash_find(bat_priv, tt_request->dst);
 	if (!req_dst_orig_node)
 		goto out;
 
-	res_dst_orig_node = get_orig_node(bat_priv, tt_request->src);
+	res_dst_orig_node = orig_hash_find(bat_priv, tt_request->src);
 	if (!res_dst_orig_node)
 		goto out;
 
@@ -1317,7 +1324,7 @@ static bool send_my_tt_response(struct bat_priv *bat_priv,
 	my_ttvn = (uint8_t)atomic_read(&bat_priv->ttvn);
 	req_ttvn = tt_request->ttvn;
 
-	orig_node = get_orig_node(bat_priv, tt_request->src);
+	orig_node = orig_hash_find(bat_priv, tt_request->src);
 	if (!orig_node)
 		goto out;
 
@@ -1497,7 +1504,7 @@ bool is_my_client(struct bat_priv *bat_priv, const uint8_t *addr)
 		goto out;
 	/* Check if the client has been logically deleted (but is kept for
 	 * consistency purpose) */
-	if (tt_local_entry->flags & TT_CLIENT_PENDING)
+	if (tt_local_entry->common.flags & TT_CLIENT_PENDING)
 		goto out;
 	ret = true;
 out:
@@ -1720,45 +1727,53 @@ void tt_free(struct bat_priv *bat_priv)
 	kfree(bat_priv->tt_buff);
 }
 
-/* This function will reset the specified flags from all the entries in
- * the given hash table and will increment num_local_tt for each involved
- * entry */
-static void tt_local_reset_flags(struct bat_priv *bat_priv, uint16_t flags)
+/* This function will enable or disable the specified flags for all the entries
+ * in the given hash table and returns the number of modified entries */
+static uint16_t tt_set_flags(struct hashtable_t *hash, uint16_t flags,
+			     bool enable)
 {
-	int i;
-	struct hashtable_t *hash = bat_priv->tt_local_hash;
+	uint32_t i;
+	uint16_t changed_num = 0;
 	struct hlist_head *head;
 	struct hlist_node *node;
-	struct tt_local_entry *tt_local_entry;
+	struct tt_common_entry *tt_common_entry;
 
 	if (!hash)
-		return;
+		goto out;
 
 	for (i = 0; i < hash->size; i++) {
 		head = &hash->table[i];
 
 		rcu_read_lock();
-		hlist_for_each_entry_rcu(tt_local_entry, node,
+		hlist_for_each_entry_rcu(tt_common_entry, node,
 					 head, hash_entry) {
-			if (!(tt_local_entry->flags & flags))
-				continue;
-			tt_local_entry->flags &= ~flags;
-			atomic_inc(&bat_priv->num_local_tt);
+			if (enable) {
+				if ((tt_common_entry->flags & flags) == flags)
+					continue;
+				tt_common_entry->flags |= flags;
+			} else {
+				if (!(tt_common_entry->flags & flags))
+					continue;
+				tt_common_entry->flags &= ~flags;
+			}
+			changed_num++;
 		}
 		rcu_read_unlock();
 	}
-
+out:
+	return changed_num;
 }
 
 /* Purge out all the tt local entries marked with TT_CLIENT_PENDING */
 static void tt_local_purge_pending_clients(struct bat_priv *bat_priv)
 {
 	struct hashtable_t *hash = bat_priv->tt_local_hash;
+	struct tt_common_entry *tt_common_entry;
 	struct tt_local_entry *tt_local_entry;
 	struct hlist_node *node, *node_tmp;
 	struct hlist_head *head;
 	spinlock_t *list_lock; /* protects write access to the hash lists */
-	int i;
+	uint32_t i;
 
 	if (!hash)
 		return;
@@ -1768,16 +1783,19 @@ static void tt_local_purge_pending_clients(struct bat_priv *bat_priv)
 		list_lock = &hash->list_locks[i];
 
 		spin_lock_bh(list_lock);
-		hlist_for_each_entry_safe(tt_local_entry, node, node_tmp,
+		hlist_for_each_entry_safe(tt_common_entry, node, node_tmp,
 					  head, hash_entry) {
-			if (!(tt_local_entry->flags & TT_CLIENT_PENDING))
+			if (!(tt_common_entry->flags & TT_CLIENT_PENDING))
 				continue;
 
 			bat_dbg(DBG_TT, bat_priv, "Deleting local tt entry "
-				"(%pM): pending\n", tt_local_entry->addr);
+				"(%pM): pending\n", tt_common_entry->addr);
 
 			atomic_dec(&bat_priv->num_local_tt);
 			hlist_del_rcu(node);
+			tt_local_entry = container_of(tt_common_entry,
+						      struct tt_local_entry,
+						      common);
 			tt_local_entry_free_ref(tt_local_entry);
 		}
 		spin_unlock_bh(list_lock);
@@ -1787,7 +1805,11 @@ static void tt_local_purge_pending_clients(struct bat_priv *bat_priv)
 
 void tt_commit_changes(struct bat_priv *bat_priv)
 {
-	tt_local_reset_flags(bat_priv, TT_CLIENT_NEW);
+	uint16_t changed_num = tt_set_flags(bat_priv->tt_local_hash,
+					    TT_CLIENT_NEW, false);
+	/* all the reset entries have now to be effectively counted as local
+	 * entries */
+	atomic_add(changed_num, &bat_priv->num_local_tt);
 	tt_local_purge_pending_clients(bat_priv);
 
 	/* Increment the TTVN only once per OGM interval */
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index ab8d0fe..e9eb043 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -222,24 +222,24 @@ struct socket_packet {
 	struct icmp_packet_rr icmp_packet;
 };
 
-struct tt_local_entry {
+struct tt_common_entry {
 	uint8_t addr[ETH_ALEN];
 	struct hlist_node hash_entry;
-	unsigned long last_seen;
 	uint16_t flags;
 	atomic_t refcount;
 	struct rcu_head rcu;
 };
 
+struct tt_local_entry {
+	struct tt_common_entry common;
+	unsigned long last_seen;
+};
+
 struct tt_global_entry {
-	uint8_t addr[ETH_ALEN];
-	struct hlist_node hash_entry; /* entry in the global table */
+	struct tt_common_entry common;
 	struct orig_node *orig_node;
 	uint8_t ttvn;
-	uint16_t flags; /* only TT_GLOBAL_ROAM is used */
 	unsigned long roam_at; /* time at which TT_GLOBAL_ROAM was set */
-	atomic_t refcount;
-	struct rcu_head rcu;
 };
 
 struct tt_change_node {
diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c
index f81a6b6..cc3b9f2 100644
--- a/net/batman-adv/vis.c
+++ b/net/batman-adv/vis.c
@@ -66,7 +66,7 @@ static int vis_info_cmp(const struct hlist_node *node, const void *data2)
 
 /* hash function to choose an entry in a hash table of given size */
 /* hash algorithm from http://en.wikipedia.org/wiki/Hash_table */
-static int vis_info_choose(const void *data, int size)
+static uint32_t vis_info_choose(const void *data, uint32_t size)
 {
 	const struct vis_info *vis_info = data;
 	const struct vis_packet *packet;
@@ -96,7 +96,7 @@ static struct vis_info *vis_hash_find(struct bat_priv *bat_priv,
 	struct hlist_head *head;
 	struct hlist_node *node;
 	struct vis_info *vis_info, *vis_info_tmp = NULL;
-	int index;
+	uint32_t index;
 
 	if (!hash)
 		return NULL;
@@ -202,7 +202,8 @@ int vis_seq_print_text(struct seq_file *seq, void *offset)
 	HLIST_HEAD(vis_if_list);
 	struct if_list_entry *entry;
 	struct hlist_node *pos, *n;
-	int i, j, ret = 0;
+	uint32_t i;
+	int j, ret = 0;
 	int vis_server = atomic_read(&bat_priv->vis_mode);
 	size_t buff_pos, buf_size;
 	char *buff;
@@ -556,7 +557,8 @@ static int find_best_vis_server(struct bat_priv *bat_priv,
 	struct hlist_head *head;
 	struct orig_node *orig_node;
 	struct vis_packet *packet;
-	int best_tq = -1, i;
+	int best_tq = -1;
+	uint32_t i;
 
 	packet = (struct vis_packet *)info->skb_packet->data;
 
@@ -607,8 +609,9 @@ static int generate_vis_packet(struct bat_priv *bat_priv)
 	struct vis_info *info = bat_priv->my_vis_info;
 	struct vis_packet *packet = (struct vis_packet *)info->skb_packet->data;
 	struct vis_info_entry *entry;
-	struct tt_local_entry *tt_local_entry;
-	int best_tq = -1, i;
+	struct tt_common_entry *tt_common_entry;
+	int best_tq = -1;
+	uint32_t i;
 
 	info->first_seen = jiffies;
 	packet->vis_type = atomic_read(&bat_priv->vis_mode);
@@ -669,13 +672,13 @@ next:
 		head = &hash->table[i];
 
 		rcu_read_lock();
-		hlist_for_each_entry_rcu(tt_local_entry, node, head,
+		hlist_for_each_entry_rcu(tt_common_entry, node, head,
 					 hash_entry) {
 			entry = (struct vis_info_entry *)
 					skb_put(info->skb_packet,
 						sizeof(*entry));
 			memset(entry->src, 0, ETH_ALEN);
-			memcpy(entry->dest, tt_local_entry->addr, ETH_ALEN);
+			memcpy(entry->dest, tt_common_entry->addr, ETH_ALEN);
 			entry->quality = 0; /* 0 means TT */
 			packet->entries++;
 
@@ -696,7 +699,7 @@ unlock:
  * held */
 static void purge_vis_packets(struct bat_priv *bat_priv)
 {
-	int i;
+	uint32_t i;
 	struct hashtable_t *hash = bat_priv->vis_hash;
 	struct hlist_node *node, *node_tmp;
 	struct hlist_head *head;
@@ -733,7 +736,7 @@ static void broadcast_vis_packet(struct bat_priv *bat_priv,
 	struct sk_buff *skb;
 	struct hard_iface *hard_iface;
 	uint8_t dstaddr[ETH_ALEN];
-	int i;
+	uint32_t i;
 
 
 	packet = (struct vis_packet *)info->skb_packet->data;
diff --git a/net/bridge/br.c b/net/bridge/br.c
index f20c4fd..ba780cc 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -62,7 +62,7 @@ static int __init br_init(void)
 
 	brioctl_set(br_ioctl_deviceless_stub);
 
-#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
+#if IS_ENABLED(CONFIG_ATM_LANE)
 	br_fdb_test_addr_hook = br_fdb_test_addr;
 #endif
 
@@ -93,7 +93,7 @@ static void __exit br_deinit(void)
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 
 	br_netfilter_fini();
-#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
+#if IS_ENABLED(CONFIG_ATM_LANE)
 	br_fdb_test_addr_hook = NULL;
 #endif
 
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index feb77ea..71773b0 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -170,8 +170,11 @@ static int br_set_mac_address(struct net_device *dev, void *p)
 		return -EINVAL;
 
 	spin_lock_bh(&br->lock);
-	memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
-	br_stp_change_bridge_id(br, addr->sa_data);
+	if (compare_ether_addr(dev->dev_addr, addr->sa_data)) {
+		memcpy(dev->dev_addr, addr->sa_data, ETH_ALEN);
+		br_fdb_change_mac_address(br, addr->sa_data);
+		br_stp_change_bridge_id(br, addr->sa_data);
+	}
 	br->flags |= BR_SET_MAC_ADDR;
 	spin_unlock_bh(&br->lock);
 
@@ -186,7 +189,8 @@ static void br_getinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 	strcpy(info->bus_info, "N/A");
 }
 
-static u32 br_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t br_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	struct net_bridge *br = netdev_priv(dev);
 
@@ -341,10 +345,10 @@ void br_dev_setup(struct net_device *dev)
 	dev->priv_flags = IFF_EBRIDGE;
 
 	dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
-			NETIF_F_GSO_MASK | NETIF_F_NO_CSUM | NETIF_F_LLTX |
+			NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_LLTX |
 			NETIF_F_NETNS_LOCAL | NETIF_F_HW_VLAN_TX;
 	dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
-			   NETIF_F_GSO_MASK | NETIF_F_NO_CSUM |
+			   NETIF_F_GSO_MASK | NETIF_F_HW_CSUM |
 			   NETIF_F_HW_VLAN_TX;
 
 	br->dev = dev;
diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
index c8e7861..f963f6b 100644
--- a/net/bridge/br_fdb.c
+++ b/net/bridge/br_fdb.c
@@ -28,7 +28,8 @@
 static struct kmem_cache *br_fdb_cache __read_mostly;
 static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
 		      const unsigned char *addr);
-static void fdb_notify(const struct net_bridge_fdb_entry *, int);
+static void fdb_notify(struct net_bridge *br,
+		       const struct net_bridge_fdb_entry *, int);
 
 static u32 fdb_salt __read_mostly;
 
@@ -80,10 +81,10 @@ static void fdb_rcu_free(struct rcu_head *head)
 	kmem_cache_free(br_fdb_cache, ent);
 }
 
-static inline void fdb_delete(struct net_bridge_fdb_entry *f)
+static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f)
 {
-	fdb_notify(f, RTM_DELNEIGH);
 	hlist_del_rcu(&f->hlist);
+	fdb_notify(br, f, RTM_DELNEIGH);
 	call_rcu(&f->rcu, fdb_rcu_free);
 }
 
@@ -114,7 +115,7 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr)
 				}
 
 				/* delete old one */
-				fdb_delete(f);
+				fdb_delete(br, f);
 				goto insert;
 			}
 		}
@@ -126,6 +127,18 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr)
 	spin_unlock_bh(&br->hash_lock);
 }
 
+void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr)
+{
+	struct net_bridge_fdb_entry *f;
+
+	/* If old entry was unassociated with any port, then delete it. */
+	f = __br_fdb_get(br, br->dev->dev_addr);
+	if (f && f->is_local && !f->dst)
+		fdb_delete(br, f);
+
+	fdb_insert(br, NULL, newaddr);
+}
+
 void br_fdb_cleanup(unsigned long _data)
 {
 	struct net_bridge *br = (struct net_bridge *)_data;
@@ -144,7 +157,7 @@ void br_fdb_cleanup(unsigned long _data)
 				continue;
 			this_timer = f->updated + delay;
 			if (time_before_eq(this_timer, jiffies))
-				fdb_delete(f);
+				fdb_delete(br, f);
 			else if (time_before(this_timer, next_timer))
 				next_timer = this_timer;
 		}
@@ -165,7 +178,7 @@ void br_fdb_flush(struct net_bridge *br)
 		struct hlist_node *h, *n;
 		hlist_for_each_entry_safe(f, h, n, &br->hash[i], hlist) {
 			if (!f->is_static)
-				fdb_delete(f);
+				fdb_delete(br, f);
 		}
 	}
 	spin_unlock_bh(&br->hash_lock);
@@ -209,7 +222,7 @@ void br_fdb_delete_by_port(struct net_bridge *br,
 				}
 			}
 
-			fdb_delete(f);
+			fdb_delete(br, f);
 		skip_delete: ;
 		}
 	}
@@ -234,7 +247,7 @@ struct net_bridge_fdb_entry *__br_fdb_get(struct net_bridge *br,
 	return NULL;
 }
 
-#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
+#if IS_ENABLED(CONFIG_ATM_LANE)
 /* Interface used by ATM LANE hook to test
  * if an addr is on some other bridge port */
 int br_fdb_test_addr(struct net_device *dev, unsigned char *addr)
@@ -249,7 +262,7 @@ int br_fdb_test_addr(struct net_device *dev, unsigned char *addr)
 		ret = 0;
 	else {
 		fdb = __br_fdb_get(port->br, addr);
-		ret = fdb && fdb->dst->dev != dev &&
+		ret = fdb && fdb->dst && fdb->dst->dev != dev &&
 			fdb->dst->state == BR_STATE_FORWARDING;
 	}
 	rcu_read_unlock();
@@ -281,6 +294,10 @@ int br_fdb_fillbuf(struct net_bridge *br, void *buf,
 			if (has_expired(br, f))
 				continue;
 
+			/* ignore pseudo entry for local MAC address */
+			if (!f->dst)
+				continue;
+
 			if (skip) {
 				--skip;
 				continue;
@@ -347,7 +364,6 @@ static struct net_bridge_fdb_entry *fdb_create(struct hlist_head *head,
 		fdb->is_static = 0;
 		fdb->updated = fdb->used = jiffies;
 		hlist_add_head_rcu(&fdb->hlist, head);
-		fdb_notify(fdb, RTM_NEWNEIGH);
 	}
 	return fdb;
 }
@@ -371,7 +387,7 @@ static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
 		br_warn(br, "adding interface %s with same address "
 		       "as a received packet\n",
 		       source->dev->name);
-		fdb_delete(fdb);
+		fdb_delete(br, fdb);
 	}
 
 	fdb = fdb_create(head, source, addr);
@@ -379,6 +395,7 @@ static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source,
 		return -ENOMEM;
 
 	fdb->is_local = fdb->is_static = 1;
+	fdb_notify(br, fdb, RTM_NEWNEIGH);
 	return 0;
 }
 
@@ -424,9 +441,11 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source,
 		}
 	} else {
 		spin_lock(&br->hash_lock);
-		if (likely(!fdb_find(head, addr)))
-			fdb_create(head, source, addr);
-
+		if (likely(!fdb_find(head, addr))) {
+			fdb = fdb_create(head, source, addr);
+			if (fdb)
+				fdb_notify(br, fdb, RTM_NEWNEIGH);
+		}
 		/* else  we lose race and someone else inserts
 		 * it first, don't bother updating
 		 */
@@ -446,7 +465,7 @@ static int fdb_to_nud(const struct net_bridge_fdb_entry *fdb)
 		return NUD_REACHABLE;
 }
 
-static int fdb_fill_info(struct sk_buff *skb,
+static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br,
 			 const struct net_bridge_fdb_entry *fdb,
 			 u32 pid, u32 seq, int type, unsigned int flags)
 {
@@ -459,14 +478,13 @@ static int fdb_fill_info(struct sk_buff *skb,
 	if (nlh == NULL)
 		return -EMSGSIZE;
 
-
 	ndm = nlmsg_data(nlh);
 	ndm->ndm_family	 = AF_BRIDGE;
 	ndm->ndm_pad1    = 0;
 	ndm->ndm_pad2    = 0;
 	ndm->ndm_flags	 = 0;
 	ndm->ndm_type	 = 0;
-	ndm->ndm_ifindex = fdb->dst->dev->ifindex;
+	ndm->ndm_ifindex = fdb->dst ? fdb->dst->dev->ifindex : br->dev->ifindex;
 	ndm->ndm_state   = fdb_to_nud(fdb);
 
 	NLA_PUT(skb, NDA_LLADDR, ETH_ALEN, &fdb->addr);
@@ -491,9 +509,10 @@ static inline size_t fdb_nlmsg_size(void)
 		+ nla_total_size(sizeof(struct nda_cacheinfo));
 }
 
-static void fdb_notify(const struct net_bridge_fdb_entry *fdb, int type)
+static void fdb_notify(struct net_bridge *br,
+		       const struct net_bridge_fdb_entry *fdb, int type)
 {
-	struct net *net = dev_net(fdb->dst->dev);
+	struct net *net = dev_net(br->dev);
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
 
@@ -501,7 +520,7 @@ static void fdb_notify(const struct net_bridge_fdb_entry *fdb, int type)
 	if (skb == NULL)
 		goto errout;
 
-	err = fdb_fill_info(skb, fdb, 0, 0, type, 0);
+	err = fdb_fill_info(skb, br, fdb, 0, 0, type, 0);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in fdb_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
@@ -538,7 +557,7 @@ int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb)
 				if (idx < cb->args[0])
 					goto skip;
 
-				if (fdb_fill_info(skb, f,
+				if (fdb_fill_info(skb, br, f,
 						  NETLINK_CB(cb->skb).pid,
 						  cb->nlh->nlmsg_seq,
 						  RTM_NEWNEIGH,
@@ -556,7 +575,7 @@ skip:
 	return skb->len;
 }
 
-/* Create new static fdb entry */
+/* Update (create or replace) forwarding database entry */
 static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr,
 			 __u16 state, __u16 flags)
 {
@@ -572,19 +591,25 @@ static int fdb_add_entry(struct net_bridge_port *source, const __u8 *addr,
 		fdb = fdb_create(head, source, addr);
 		if (!fdb)
 			return -ENOMEM;
+		fdb_notify(br, fdb, RTM_NEWNEIGH);
 	} else {
 		if (flags & NLM_F_EXCL)
 			return -EEXIST;
+	}
+
+	if (fdb_to_nud(fdb) != state) {
+		if (state & NUD_PERMANENT)
+			fdb->is_local = fdb->is_static = 1;
+		else if (state & NUD_NOARP) {
+			fdb->is_local = 0;
+			fdb->is_static = 1;
+		} else
+			fdb->is_local = fdb->is_static = 0;
 
-		if (flags & NLM_F_REPLACE)
-			fdb->updated = fdb->used = jiffies;
-		fdb->is_local = fdb->is_static = 0;
+		fdb->updated = fdb->used = jiffies;
+		fdb_notify(br, fdb, RTM_NEWNEIGH);
 	}
 
-	if (state & NUD_PERMANENT)
-		fdb->is_local = fdb->is_static = 1;
-	else if (state & NUD_NOARP)
-		fdb->is_static = 1;
 	return 0;
 }
 
@@ -627,6 +652,11 @@ int br_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 		return -EINVAL;
 	}
 
+	if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) {
+		pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state);
+		return -EINVAL;
+	}
+
 	p = br_port_get_rtnl(dev);
 	if (p == NULL) {
 		pr_info("bridge: RTM_NEWNEIGH %s not a bridge port\n",
@@ -634,9 +664,15 @@ int br_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 		return -EINVAL;
 	}
 
-	spin_lock_bh(&p->br->hash_lock);
-	err = fdb_add_entry(p, addr, ndm->ndm_state, nlh->nlmsg_flags);
-	spin_unlock_bh(&p->br->hash_lock);
+	if (ndm->ndm_flags & NTF_USE) {
+		rcu_read_lock();
+		br_fdb_update(p->br, p, addr);
+		rcu_read_unlock();
+	} else {
+		spin_lock_bh(&p->br->hash_lock);
+		err = fdb_add_entry(p, addr, ndm->ndm_state, nlh->nlmsg_flags);
+		spin_unlock_bh(&p->br->hash_lock);
+	}
 
 	return err;
 }
@@ -651,7 +687,7 @@ static int fdb_delete_by_addr(struct net_bridge_port *p, const u8 *addr)
 	if (!fdb)
 		return -ENOENT;
 
-	fdb_delete(fdb);
+	fdb_delete(p->br, fdb);
 	return 0;
 }
 
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index ee64287..61f6534 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -98,7 +98,7 @@ static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb)
 /* called with rcu_read_lock */
 void br_deliver(const struct net_bridge_port *to, struct sk_buff *skb)
 {
-	if (should_deliver(to, skb)) {
+	if (to && should_deliver(to, skb)) {
 		__br_deliver(to, skb);
 		return;
 	}
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index f603e5b..0a942fb 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -296,10 +296,11 @@ int br_min_mtu(const struct net_bridge *br)
 /*
  * Recomputes features using slave's features
  */
-u32 br_features_recompute(struct net_bridge *br, u32 features)
+netdev_features_t br_features_recompute(struct net_bridge *br,
+	netdev_features_t features)
 {
 	struct net_bridge_port *p;
-	u32 mask;
+	netdev_features_t mask;
 
 	if (list_empty(&br->port_list))
 		return features;
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 995cbe0..568d5bf 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -24,7 +24,7 @@
 #include <linux/slab.h>
 #include <linux/timer.h>
 #include <net/ip.h>
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
 #include <net/mld.h>
 #include <net/addrconf.h>
@@ -36,7 +36,7 @@
 #define mlock_dereference(X, br) \
 	rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static inline int ipv6_is_transient_multicast(const struct in6_addr *addr)
 {
 	if (ipv6_addr_is_multicast(addr) && IPV6_ADDR_MC_FLAG_TRANSIENT(addr))
@@ -52,7 +52,7 @@ static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b)
 	switch (a->proto) {
 	case htons(ETH_P_IP):
 		return a->u.ip4 == b->u.ip4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
 		return ipv6_addr_equal(&a->u.ip6, &b->u.ip6);
 #endif
@@ -65,7 +65,7 @@ static inline int __br_ip4_hash(struct net_bridge_mdb_htable *mdb, __be32 ip)
 	return jhash_1word(mdb->secret, (__force u32)ip) & (mdb->max - 1);
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static inline int __br_ip6_hash(struct net_bridge_mdb_htable *mdb,
 				const struct in6_addr *ip)
 {
@@ -79,7 +79,7 @@ static inline int br_ip_hash(struct net_bridge_mdb_htable *mdb,
 	switch (ip->proto) {
 	case htons(ETH_P_IP):
 		return __br_ip4_hash(mdb, ip->u.ip4);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
 		return __br_ip6_hash(mdb, &ip->u.ip6);
 #endif
@@ -121,13 +121,13 @@ static struct net_bridge_mdb_entry *br_mdb_ip4_get(
 	return br_mdb_ip_get(mdb, &br_dst);
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static struct net_bridge_mdb_entry *br_mdb_ip6_get(
 	struct net_bridge_mdb_htable *mdb, const struct in6_addr *dst)
 {
 	struct br_ip br_dst;
 
-	ipv6_addr_copy(&br_dst.u.ip6, dst);
+	br_dst.u.ip6 = *dst;
 	br_dst.proto = htons(ETH_P_IPV6);
 
 	return br_mdb_ip_get(mdb, &br_dst);
@@ -152,9 +152,9 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
 	case htons(ETH_P_IP):
 		ip.u.ip4 = ip_hdr(skb)->daddr;
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
-		ipv6_addr_copy(&ip.u.ip6, &ipv6_hdr(skb)->daddr);
+		ip.u.ip6 = ipv6_hdr(skb)->daddr;
 		break;
 #endif
 	default:
@@ -411,7 +411,7 @@ out:
 	return skb;
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 						    const struct in6_addr *group)
 {
@@ -474,7 +474,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 	mldq->mld_cksum = 0;
 	mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval));
 	mldq->mld_reserved = 0;
-	ipv6_addr_copy(&mldq->mld_mca, group);
+	mldq->mld_mca = *group;
 
 	/* checksum */
 	mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
@@ -496,7 +496,7 @@ static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
 	switch (addr->proto) {
 	case htons(ETH_P_IP):
 		return br_ip4_multicast_alloc_query(br, addr->u.ip4);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
 		return br_ip6_multicast_alloc_query(br, &addr->u.ip6);
 #endif
@@ -773,7 +773,7 @@ static int br_ip4_multicast_add_group(struct net_bridge *br,
 	return br_multicast_add_group(br, port, &br_group);
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static int br_ip6_multicast_add_group(struct net_bridge *br,
 				      struct net_bridge_port *port,
 				      const struct in6_addr *group)
@@ -783,7 +783,7 @@ static int br_ip6_multicast_add_group(struct net_bridge *br,
 	if (!ipv6_is_transient_multicast(group))
 		return 0;
 
-	ipv6_addr_copy(&br_group.u.ip6, group);
+	br_group.u.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 
 	return br_multicast_add_group(br, port, &br_group);
@@ -845,7 +845,7 @@ static void br_multicast_send_query(struct net_bridge *br,
 	br_group.proto = htons(ETH_P_IP);
 	__br_multicast_send_query(br, port, &br_group);
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	br_group.proto = htons(ETH_P_IPV6);
 	__br_multicast_send_query(br, port, &br_group);
 #endif
@@ -989,7 +989,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
 	return err;
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 					struct net_bridge_port *port,
 					struct sk_buff *skb)
@@ -1185,7 +1185,7 @@ out:
 	return err;
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static int br_ip6_multicast_query(struct net_bridge *br,
 				  struct net_bridge_port *port,
 				  struct sk_buff *skb)
@@ -1334,7 +1334,7 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br,
 	br_multicast_leave_group(br, port, &br_group);
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static void br_ip6_multicast_leave_group(struct net_bridge *br,
 					 struct net_bridge_port *port,
 					 const struct in6_addr *group)
@@ -1344,7 +1344,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
 	if (!ipv6_is_transient_multicast(group))
 		return;
 
-	ipv6_addr_copy(&br_group.u.ip6, group);
+	br_group.u.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 
 	br_multicast_leave_group(br, port, &br_group);
@@ -1449,7 +1449,7 @@ err_out:
 	return err;
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static int br_multicast_ipv6_rcv(struct net_bridge *br,
 				 struct net_bridge_port *port,
 				 struct sk_buff *skb)
@@ -1458,6 +1458,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
 	const struct ipv6hdr *ip6h;
 	u8 icmp6_type;
 	u8 nexthdr;
+	__be16 frag_off;
 	unsigned len;
 	int offset;
 	int err;
@@ -1483,7 +1484,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
 		return -EINVAL;
 
 	nexthdr = ip6h->nexthdr;
-	offset = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr);
+	offset = ipv6_skip_exthdr(skb, sizeof(*ip6h), &nexthdr, &frag_off);
 
 	if (offset < 0 || nexthdr != IPPROTO_ICMPV6)
 		return 0;
@@ -1501,6 +1502,8 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
 
 	__skb_pull(skb2, offset);
 	skb_reset_transport_header(skb2);
+	skb_postpull_rcsum(skb2, skb_network_header(skb2),
+			   skb_network_header_len(skb2));
 
 	icmp6_type = icmp6_hdr(skb2)->icmp6_type;
 
@@ -1593,7 +1596,7 @@ int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port,
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
 		return br_multicast_ipv4_rcv(br, port, skb);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
 		return br_multicast_ipv6_rcv(br, port, skb);
 #endif
@@ -1770,7 +1773,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val)
 	int err = 0;
 	struct net_bridge_mdb_htable *mdb;
 
-	spin_lock(&br->multicast_lock);
+	spin_lock_bh(&br->multicast_lock);
 	if (br->multicast_disabled == !val)
 		goto unlock;
 
@@ -1806,7 +1809,7 @@ rollback:
 	}
 
 unlock:
-	spin_unlock(&br->multicast_lock);
+	spin_unlock_bh(&br->multicast_lock);
 
 	return err;
 }
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index d6ec372..52e4460 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -356,7 +356,7 @@ static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb)
 	if (!skb->dev)
 		goto free_skb;
 	dst = skb_dst(skb);
-	neigh = dst_get_neighbour(dst);
+	neigh = dst_get_neighbour_noref(dst);
 	if (neigh->hh.hh_len) {
 		neigh_hh_bridge(&neigh->hh, skb);
 		skb->dev = nf_bridge->physindev;
@@ -807,7 +807,7 @@ static unsigned int br_nf_forward_arp(unsigned int hook, struct sk_buff *skb,
 	return NF_STOLEN;
 }
 
-#if defined(CONFIG_NF_CONNTRACK_IPV4) || defined(CONFIG_NF_CONNTRACK_IPV4_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV4)
 static int br_nf_dev_queue_xmit(struct sk_buff *skb)
 {
 	int ret;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index e5f9ece3..a1daf82 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -18,6 +18,7 @@
 #include <net/sock.h>
 
 #include "br_private.h"
+#include "br_private_stp.h"
 
 static inline size_t br_nlmsg_size(void)
 {
@@ -188,6 +189,11 @@ static int br_rtm_setlink(struct sk_buff *skb,  struct nlmsghdr *nlh, void *arg)
 
 	p->state = new_state;
 	br_log_state(p);
+
+	spin_lock_bh(&p->br->lock);
+	br_port_state_selection(p->br);
+	spin_unlock_bh(&p->br->lock);
+
 	br_ifinfo_notify(RTM_NEWLINK, p);
 
 	return 0;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index d7d6fb0..0b67a63 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -56,7 +56,7 @@ struct br_ip
 {
 	union {
 		__be32	ip4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		struct in6_addr ip6;
 #endif
 	} u;
@@ -348,6 +348,7 @@ extern void br_fdb_fini(void);
 extern void br_fdb_flush(struct net_bridge *br);
 extern void br_fdb_changeaddr(struct net_bridge_port *p,
 			      const unsigned char *newaddr);
+extern void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr);
 extern void br_fdb_cleanup(unsigned long arg);
 extern void br_fdb_delete_by_port(struct net_bridge *br,
 				  const struct net_bridge_port *p, int do_all);
@@ -387,7 +388,8 @@ extern int br_add_if(struct net_bridge *br,
 extern int br_del_if(struct net_bridge *br,
 	      struct net_device *dev);
 extern int br_min_mtu(const struct net_bridge *br);
-extern u32 br_features_recompute(struct net_bridge *br, u32 features);
+extern netdev_features_t br_features_recompute(struct net_bridge *br,
+	netdev_features_t features);
 
 /* br_input.c */
 extern int br_handle_frame_finish(struct sk_buff *skb);
@@ -535,7 +537,7 @@ extern void br_stp_port_timer_init(struct net_bridge_port *p);
 extern unsigned long br_timer_value(const struct timer_list *timer);
 
 /* br.c */
-#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
+#if IS_ENABLED(CONFIG_ATM_LANE)
 extern int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr);
 #endif
 
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index ad0a3f7..dd147d7 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -399,25 +399,24 @@ void br_port_state_selection(struct net_bridge *br)
 	struct net_bridge_port *p;
 	unsigned int liveports = 0;
 
-	/* Don't change port states if userspace is handling STP */
-	if (br->stp_enabled == BR_USER_STP)
-		return;
-
 	list_for_each_entry(p, &br->port_list, list) {
 		if (p->state == BR_STATE_DISABLED)
 			continue;
 
-		if (p->port_no == br->root_port) {
-			p->config_pending = 0;
-			p->topology_change_ack = 0;
-			br_make_forwarding(p);
-		} else if (br_is_designated_port(p)) {
-			del_timer(&p->message_age_timer);
-			br_make_forwarding(p);
-		} else {
-			p->config_pending = 0;
-			p->topology_change_ack = 0;
-			br_make_blocking(p);
+		/* Don't change port states if userspace is handling STP */
+		if (br->stp_enabled != BR_USER_STP) {
+			if (p->port_no == br->root_port) {
+				p->config_pending = 0;
+				p->topology_change_ack = 0;
+				br_make_forwarding(p);
+			} else if (br_is_designated_port(p)) {
+				del_timer(&p->message_age_timer);
+				br_make_forwarding(p);
+			} else {
+				p->config_pending = 0;
+				p->topology_change_ack = 0;
+				br_make_blocking(p);
+			}
 		}
 
 		if (p->state == BR_STATE_FORWARDING)
diff --git a/net/bridge/netfilter/ebt_ip6.c b/net/bridge/netfilter/ebt_ip6.c
index 2ed0056..99c8566 100644
--- a/net/bridge/netfilter/ebt_ip6.c
+++ b/net/bridge/netfilter/ebt_ip6.c
@@ -55,9 +55,10 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par)
 		return false;
 	if (info->bitmask & EBT_IP6_PROTO) {
 		uint8_t nexthdr = ih6->nexthdr;
+		__be16 frag_off;
 		int offset_ph;
 
-		offset_ph = ipv6_skip_exthdr(skb, sizeof(_ip6h), &nexthdr);
+		offset_ph = ipv6_skip_exthdr(skb, sizeof(_ip6h), &nexthdr, &frag_off);
 		if (offset_ph == -1)
 			return false;
 		if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO))
diff --git a/net/bridge/netfilter/ebt_log.c b/net/bridge/netfilter/ebt_log.c
index 6e5a8bb..f88ee53 100644
--- a/net/bridge/netfilter/ebt_log.c
+++ b/net/bridge/netfilter/ebt_log.c
@@ -107,12 +107,13 @@ ebt_log_packet(u_int8_t pf, unsigned int hooknum,
 		goto out;
 	}
 
-#if defined(CONFIG_BRIDGE_EBT_IP6) || defined(CONFIG_BRIDGE_EBT_IP6_MODULE)
+#if IS_ENABLED(CONFIG_BRIDGE_EBT_IP6)
 	if ((bitmask & EBT_LOG_IP6) && eth_hdr(skb)->h_proto ==
 	   htons(ETH_P_IPV6)) {
 		const struct ipv6hdr *ih;
 		struct ipv6hdr _iph;
 		uint8_t nexthdr;
+		__be16 frag_off;
 		int offset_ph;
 
 		ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
@@ -123,7 +124,7 @@ ebt_log_packet(u_int8_t pf, unsigned int hooknum,
 		printk(" IPv6 SRC=%pI6 IPv6 DST=%pI6, IPv6 priority=0x%01X, Next Header=%d",
 		       &ih->saddr, &ih->daddr, ih->priority, ih->nexthdr);
 		nexthdr = ih->nexthdr;
-		offset_ph = ipv6_skip_exthdr(skb, sizeof(_iph), &nexthdr);
+		offset_ph = ipv6_skip_exthdr(skb, sizeof(_iph), &nexthdr, &frag_off);
 		if (offset_ph == -1)
 			goto out;
 		print_ports(skb, nexthdr, offset_ph);
diff --git a/net/caif/Kconfig b/net/caif/Kconfig
index 529750d..936361e 100644
--- a/net/caif/Kconfig
+++ b/net/caif/Kconfig
@@ -40,3 +40,14 @@ config CAIF_NETDEV
 	If you select to build it as a built-in then the main CAIF device must
 	also be a built-in.
 	If unsure say Y.
+
+config CAIF_USB
+	tristate "CAIF USB support"
+	depends on CAIF
+	default n
+	---help---
+	Say Y if you are using CAIF over USB CDC NCM.
+	This can be either built-in or a loadable module,
+	If you select to build it as a built-in then the main CAIF device must
+	also be a built-in.
+	If unsure say N.
diff --git a/net/caif/Makefile b/net/caif/Makefile
index ebcd4e7..cc2b511 100644
--- a/net/caif/Makefile
+++ b/net/caif/Makefile
@@ -10,5 +10,6 @@ caif-y := caif_dev.o \
 obj-$(CONFIG_CAIF) += caif.o
 obj-$(CONFIG_CAIF_NETDEV) += chnl_net.o
 obj-$(CONFIG_CAIF) += caif_socket.o
+obj-$(CONFIG_CAIF_USB) += caif_usb.o
 
 export-y := caif.o
diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c
index f1fa1f6..b0ce14f 100644
--- a/net/caif/caif_dev.c
+++ b/net/caif/caif_dev.c
@@ -17,6 +17,7 @@
 #include <linux/netdevice.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
+#include <linux/spinlock.h>
 #include <net/netns/generic.h>
 #include <net/net_namespace.h>
 #include <net/pkt_sched.h>
@@ -24,6 +25,7 @@
 #include <net/caif/caif_layer.h>
 #include <net/caif/cfpkt.h>
 #include <net/caif/cfcnfg.h>
+#include <net/caif/cfserl.h>
 
 MODULE_LICENSE("GPL");
 
@@ -33,6 +35,10 @@ struct caif_device_entry {
 	struct list_head list;
 	struct net_device *netdev;
 	int __percpu *pcpu_refcnt;
+	spinlock_t flow_lock;
+	struct sk_buff *xoff_skb;
+	void (*xoff_skb_dtor)(struct sk_buff *skb);
+	bool xoff;
 };
 
 struct caif_device_entry_list {
@@ -47,13 +53,14 @@ struct caif_net {
 };
 
 static int caif_net_id;
+static int q_high = 50; /* Percent */
 
 struct cfcnfg *get_cfcnfg(struct net *net)
 {
 	struct caif_net *caifn;
-	BUG_ON(!net);
 	caifn = net_generic(net, caif_net_id);
-	BUG_ON(!caifn);
+	if (!caifn)
+		return NULL;
 	return caifn->cfg;
 }
 EXPORT_SYMBOL(get_cfcnfg);
@@ -61,9 +68,9 @@ EXPORT_SYMBOL(get_cfcnfg);
 static struct caif_device_entry_list *caif_device_list(struct net *net)
 {
 	struct caif_net *caifn;
-	BUG_ON(!net);
 	caifn = net_generic(net, caif_net_id);
-	BUG_ON(!caifn);
+	if (!caifn)
+		return NULL;
 	return &caifn->caifdevs;
 }
 
@@ -92,7 +99,8 @@ static struct caif_device_entry *caif_device_alloc(struct net_device *dev)
 	struct caif_device_entry *caifd;
 
 	caifdevs = caif_device_list(dev_net(dev));
-	BUG_ON(!caifdevs);
+	if (!caifdevs)
+		return NULL;
 
 	caifd = kzalloc(sizeof(*caifd), GFP_KERNEL);
 	if (!caifd)
@@ -112,7 +120,9 @@ static struct caif_device_entry *caif_get(struct net_device *dev)
 	struct caif_device_entry_list *caifdevs =
 	    caif_device_list(dev_net(dev));
 	struct caif_device_entry *caifd;
-	BUG_ON(!caifdevs);
+	if (!caifdevs)
+		return NULL;
+
 	list_for_each_entry_rcu(caifd, &caifdevs->list, list) {
 		if (caifd->netdev == dev)
 			return caifd;
@@ -120,15 +130,106 @@ static struct caif_device_entry *caif_get(struct net_device *dev)
 	return NULL;
 }
 
+void caif_flow_cb(struct sk_buff *skb)
+{
+	struct caif_device_entry *caifd;
+	void (*dtor)(struct sk_buff *skb) = NULL;
+	bool send_xoff;
+
+	WARN_ON(skb->dev == NULL);
+
+	rcu_read_lock();
+	caifd = caif_get(skb->dev);
+	caifd_hold(caifd);
+	rcu_read_unlock();
+
+	spin_lock_bh(&caifd->flow_lock);
+	send_xoff = caifd->xoff;
+	caifd->xoff = 0;
+	if (!WARN_ON(caifd->xoff_skb_dtor == NULL)) {
+		WARN_ON(caifd->xoff_skb != skb);
+		dtor = caifd->xoff_skb_dtor;
+		caifd->xoff_skb = NULL;
+		caifd->xoff_skb_dtor = NULL;
+	}
+	spin_unlock_bh(&caifd->flow_lock);
+
+	if (dtor)
+		dtor(skb);
+
+	if (send_xoff)
+		caifd->layer.up->
+			ctrlcmd(caifd->layer.up,
+				_CAIF_CTRLCMD_PHYIF_FLOW_ON_IND,
+				caifd->layer.id);
+	caifd_put(caifd);
+}
+
 static int transmit(struct cflayer *layer, struct cfpkt *pkt)
 {
-	int err;
+	int err, high = 0, qlen = 0;
+	struct caif_dev_common *caifdev;
 	struct caif_device_entry *caifd =
 	    container_of(layer, struct caif_device_entry, layer);
 	struct sk_buff *skb;
+	struct netdev_queue *txq;
+
+	rcu_read_lock_bh();
 
 	skb = cfpkt_tonative(pkt);
 	skb->dev = caifd->netdev;
+	skb_reset_network_header(skb);
+	skb->protocol = htons(ETH_P_CAIF);
+	caifdev = netdev_priv(caifd->netdev);
+
+	/* Check if we need to handle xoff */
+	if (likely(caifd->netdev->tx_queue_len == 0))
+		goto noxoff;
+
+	if (unlikely(caifd->xoff))
+		goto noxoff;
+
+	if (likely(!netif_queue_stopped(caifd->netdev))) {
+		/* If we run with a TX queue, check if the queue is too long*/
+		txq = netdev_get_tx_queue(skb->dev, 0);
+		qlen = qdisc_qlen(rcu_dereference_bh(txq->qdisc));
+
+		if (likely(qlen == 0))
+			goto noxoff;
+
+		high = (caifd->netdev->tx_queue_len * q_high) / 100;
+		if (likely(qlen < high))
+			goto noxoff;
+	}
+
+	/* Hold lock while accessing xoff */
+	spin_lock_bh(&caifd->flow_lock);
+	if (caifd->xoff) {
+		spin_unlock_bh(&caifd->flow_lock);
+		goto noxoff;
+	}
+
+	/*
+	 * Handle flow off, we do this by temporary hi-jacking this
+	 * skb's destructor function, and replace it with our own
+	 * flow-on callback. The callback will set flow-on and call
+	 * the original destructor.
+	 */
+
+	pr_debug("queue has stopped(%d) or is full (%d > %d)\n",
+			netif_queue_stopped(caifd->netdev),
+			qlen, high);
+	caifd->xoff = 1;
+	caifd->xoff_skb = skb;
+	caifd->xoff_skb_dtor = skb->destructor;
+	skb->destructor = caif_flow_cb;
+	spin_unlock_bh(&caifd->flow_lock);
+
+	caifd->layer.up->ctrlcmd(caifd->layer.up,
+					_CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND,
+					caifd->layer.id);
+noxoff:
+	rcu_read_unlock_bh();
 
 	err = dev_queue_xmit(skb);
 	if (err > 0)
@@ -172,7 +273,10 @@ static int receive(struct sk_buff *skb, struct net_device *dev,
 
 	/* Release reference to stack upwards */
 	caifd_put(caifd);
-	return 0;
+
+	if (err != 0)
+		err = NET_RX_DROP;
+	return err;
 }
 
 static struct packet_type caif_packet_type __read_mostly = {
@@ -203,6 +307,57 @@ static void dev_flowctrl(struct net_device *dev, int on)
 	caifd_put(caifd);
 }
 
+void caif_enroll_dev(struct net_device *dev, struct caif_dev_common *caifdev,
+			struct cflayer *link_support, int head_room,
+			struct cflayer **layer, int (**rcv_func)(
+				struct sk_buff *, struct net_device *,
+				struct packet_type *, struct net_device *))
+{
+	struct caif_device_entry *caifd;
+	enum cfcnfg_phy_preference pref;
+	struct cfcnfg *cfg = get_cfcnfg(dev_net(dev));
+	struct caif_device_entry_list *caifdevs;
+
+	caifdevs = caif_device_list(dev_net(dev));
+	if (!cfg || !caifdevs)
+		return;
+	caifd = caif_device_alloc(dev);
+	if (!caifd)
+		return;
+	*layer = &caifd->layer;
+	spin_lock_init(&caifd->flow_lock);
+
+	switch (caifdev->link_select) {
+	case CAIF_LINK_HIGH_BANDW:
+		pref = CFPHYPREF_HIGH_BW;
+		break;
+	case CAIF_LINK_LOW_LATENCY:
+		pref = CFPHYPREF_LOW_LAT;
+		break;
+	default:
+		pref = CFPHYPREF_HIGH_BW;
+		break;
+	}
+	mutex_lock(&caifdevs->lock);
+	list_add_rcu(&caifd->list, &caifdevs->list);
+
+	strncpy(caifd->layer.name, dev->name,
+		sizeof(caifd->layer.name) - 1);
+	caifd->layer.name[sizeof(caifd->layer.name) - 1] = 0;
+	caifd->layer.transmit = transmit;
+	cfcnfg_add_phy_layer(cfg,
+				dev,
+				&caifd->layer,
+				pref,
+				link_support,
+				caifdev->use_fcs,
+				head_room);
+	mutex_unlock(&caifdevs->lock);
+	if (rcv_func)
+		*rcv_func = receive;
+}
+EXPORT_SYMBOL(caif_enroll_dev);
+
 /* notify Caif of device events */
 static int caif_device_notify(struct notifier_block *me, unsigned long what,
 			      void *arg)
@@ -210,62 +365,40 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what,
 	struct net_device *dev = arg;
 	struct caif_device_entry *caifd = NULL;
 	struct caif_dev_common *caifdev;
-	enum cfcnfg_phy_preference pref;
-	enum cfcnfg_phy_type phy_type;
 	struct cfcnfg *cfg;
+	struct cflayer *layer, *link_support;
+	int head_room = 0;
 	struct caif_device_entry_list *caifdevs;
 
-	if (dev->type != ARPHRD_CAIF)
-		return 0;
-
 	cfg = get_cfcnfg(dev_net(dev));
-	if (cfg == NULL)
+	caifdevs = caif_device_list(dev_net(dev));
+	if (!cfg || !caifdevs)
 		return 0;
 
-	caifdevs = caif_device_list(dev_net(dev));
+	caifd = caif_get(dev);
+	if (caifd == NULL && dev->type != ARPHRD_CAIF)
+		return 0;
 
 	switch (what) {
 	case NETDEV_REGISTER:
-		caifd = caif_device_alloc(dev);
-		if (!caifd)
-			return 0;
+		if (caifd != NULL)
+			break;
 
 		caifdev = netdev_priv(dev);
-		caifdev->flowctrl = dev_flowctrl;
 
-		caifd->layer.transmit = transmit;
-
-		if (caifdev->use_frag)
-			phy_type = CFPHYTYPE_FRAG;
-		else
-			phy_type = CFPHYTYPE_CAIF;
-
-		switch (caifdev->link_select) {
-		case CAIF_LINK_HIGH_BANDW:
-			pref = CFPHYPREF_HIGH_BW;
-			break;
-		case CAIF_LINK_LOW_LATENCY:
-			pref = CFPHYPREF_LOW_LAT;
-			break;
-		default:
-			pref = CFPHYPREF_HIGH_BW;
-			break;
+		link_support = NULL;
+		if (caifdev->use_frag) {
+			head_room = 1;
+			link_support = cfserl_create(dev->ifindex,
+							caifdev->use_stx);
+			if (!link_support) {
+				pr_warn("Out of memory\n");
+				break;
+			}
 		}
-		strncpy(caifd->layer.name, dev->name,
-			sizeof(caifd->layer.name) - 1);
-		caifd->layer.name[sizeof(caifd->layer.name) - 1] = 0;
-
-		mutex_lock(&caifdevs->lock);
-		list_add_rcu(&caifd->list, &caifdevs->list);
-
-		cfcnfg_add_phy_layer(cfg,
-				     phy_type,
-				     dev,
-				     &caifd->layer,
-				     pref,
-				     caifdev->use_fcs,
-				     caifdev->use_stx);
-		mutex_unlock(&caifdevs->lock);
+		caif_enroll_dev(dev, caifdev, link_support, head_room,
+				&layer, NULL);
+		caifdev->flowctrl = dev_flowctrl;
 		break;
 
 	case NETDEV_UP:
@@ -277,6 +410,7 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what,
 			break;
 		}
 
+		caifd->xoff = 0;
 		cfcnfg_set_phy_state(cfg, &caifd->layer, true);
 		rcu_read_unlock();
 
@@ -298,6 +432,24 @@ static int caif_device_notify(struct notifier_block *me, unsigned long what,
 		caifd->layer.up->ctrlcmd(caifd->layer.up,
 					 _CAIF_CTRLCMD_PHYIF_DOWN_IND,
 					 caifd->layer.id);
+
+		spin_lock_bh(&caifd->flow_lock);
+
+		/*
+		 * Replace our xoff-destructor with original destructor.
+		 * We trust that skb->destructor *always* is called before
+		 * the skb reference is invalid. The hijacked SKB destructor
+		 * takes the flow_lock so manipulating the skb->destructor here
+		 * should be safe.
+		*/
+		if (caifd->xoff_skb_dtor != NULL && caifd->xoff_skb != NULL)
+			caifd->xoff_skb->destructor = caifd->xoff_skb_dtor;
+
+		caifd->xoff = 0;
+		caifd->xoff_skb_dtor = NULL;
+		caifd->xoff_skb = NULL;
+
+		spin_unlock_bh(&caifd->flow_lock);
 		caifd_put(caifd);
 		break;
 
@@ -353,15 +505,15 @@ static struct notifier_block caif_device_notifier = {
 static int caif_init_net(struct net *net)
 {
 	struct caif_net *caifn = net_generic(net, caif_net_id);
-	BUG_ON(!caifn);
+	if (WARN_ON(!caifn))
+		return -EINVAL;
+
 	INIT_LIST_HEAD(&caifn->caifdevs.list);
 	mutex_init(&caifn->caifdevs.lock);
 
 	caifn->cfg = cfcnfg_create();
-	if (!caifn->cfg) {
-		pr_warn("can't create cfcnfg\n");
+	if (!caifn->cfg)
 		return -ENOMEM;
-	}
 
 	return 0;
 }
@@ -371,17 +523,14 @@ static void caif_exit_net(struct net *net)
 	struct caif_device_entry *caifd, *tmp;
 	struct caif_device_entry_list *caifdevs =
 	    caif_device_list(net);
-	struct cfcnfg *cfg;
+	struct cfcnfg *cfg =  get_cfcnfg(net);
+
+	if (!cfg || !caifdevs)
+		return;
 
 	rtnl_lock();
 	mutex_lock(&caifdevs->lock);
 
-	cfg = get_cfcnfg(net);
-	if (cfg == NULL) {
-		mutex_unlock(&caifdevs->lock);
-		return;
-	}
-
 	list_for_each_entry_safe(caifd, tmp, &caifdevs->list, list) {
 		int i = 0;
 		list_del_rcu(&caifd->list);
diff --git a/net/caif/caif_usb.c b/net/caif/caif_usb.c
new file mode 100644
index 0000000..f5db57c
--- /dev/null
+++ b/net/caif/caif_usb.c
@@ -0,0 +1,208 @@
+/*
+ * CAIF USB handler
+ * Copyright (C) ST-Ericsson AB 2011
+ * Author:	Sjur Brendeland/sjur.brandeland@stericsson.com
+ * License terms: GNU General Public License (GPL) version 2
+ *
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__
+
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/slab.h>
+#include <linux/netdevice.h>
+#include <linux/mii.h>
+#include <linux/usb.h>
+#include <linux/usb/usbnet.h>
+#include <net/netns/generic.h>
+#include <net/caif/caif_dev.h>
+#include <net/caif/caif_layer.h>
+#include <net/caif/cfpkt.h>
+#include <net/caif/cfcnfg.h>
+
+MODULE_LICENSE("GPL");
+
+#define CFUSB_PAD_DESCR_SZ 1	/* Alignment descriptor length */
+#define CFUSB_ALIGNMENT 4	/* Number of bytes to align. */
+#define CFUSB_MAX_HEADLEN (CFUSB_PAD_DESCR_SZ + CFUSB_ALIGNMENT-1)
+#define STE_USB_VID 0x04cc	/* USB Product ID for ST-Ericsson */
+#define STE_USB_PID_CAIF 0x2306	/* Product id for CAIF Modems */
+
+struct cfusbl {
+	struct cflayer layer;
+	u8 tx_eth_hdr[ETH_HLEN];
+};
+
+static bool pack_added;
+
+static int cfusbl_receive(struct cflayer *layr, struct cfpkt *pkt)
+{
+	u8 hpad;
+
+	/* Remove padding. */
+	cfpkt_extr_head(pkt, &hpad, 1);
+	cfpkt_extr_head(pkt, NULL, hpad);
+	return layr->up->receive(layr->up, pkt);
+}
+
+static int cfusbl_transmit(struct cflayer *layr, struct cfpkt *pkt)
+{
+	struct caif_payload_info *info;
+	u8 hpad;
+	u8 zeros[CFUSB_ALIGNMENT];
+	struct sk_buff *skb;
+	struct cfusbl *usbl = container_of(layr, struct cfusbl, layer);
+
+	skb = cfpkt_tonative(pkt);
+
+	skb_reset_network_header(skb);
+	skb->protocol = htons(ETH_P_IP);
+
+	info = cfpkt_info(pkt);
+	hpad = (info->hdr_len + CFUSB_PAD_DESCR_SZ) & (CFUSB_ALIGNMENT - 1);
+
+	if (skb_headroom(skb) < ETH_HLEN + CFUSB_PAD_DESCR_SZ + hpad) {
+		pr_warn("Headroom to small\n");
+		kfree_skb(skb);
+		return -EIO;
+	}
+	memset(zeros, 0, hpad);
+
+	cfpkt_add_head(pkt, zeros, hpad);
+	cfpkt_add_head(pkt, &hpad, 1);
+	cfpkt_add_head(pkt, usbl->tx_eth_hdr, sizeof(usbl->tx_eth_hdr));
+	return layr->dn->transmit(layr->dn, pkt);
+}
+
+static void cfusbl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
+					int phyid)
+{
+	if (layr->up && layr->up->ctrlcmd)
+		layr->up->ctrlcmd(layr->up, ctrl, layr->id);
+}
+
+struct cflayer *cfusbl_create(int phyid, u8 ethaddr[ETH_ALEN],
+					u8 braddr[ETH_ALEN])
+{
+	struct cfusbl *this = kmalloc(sizeof(struct cfusbl), GFP_ATOMIC);
+
+	if (!this) {
+		pr_warn("Out of memory\n");
+		return NULL;
+	}
+	caif_assert(offsetof(struct cfusbl, layer) == 0);
+
+	memset(this, 0, sizeof(struct cflayer));
+	this->layer.receive = cfusbl_receive;
+	this->layer.transmit = cfusbl_transmit;
+	this->layer.ctrlcmd = cfusbl_ctrlcmd;
+	snprintf(this->layer.name, CAIF_LAYER_NAME_SZ, "usb%d", phyid);
+	this->layer.id = phyid;
+
+	/*
+	 * Construct TX ethernet header:
+	 *	0-5	destination address
+	 *	5-11	source address
+	 *	12-13	protocol type
+	 */
+	memcpy(&this->tx_eth_hdr[ETH_ALEN], braddr, ETH_ALEN);
+	memcpy(&this->tx_eth_hdr[ETH_ALEN], ethaddr, ETH_ALEN);
+	this->tx_eth_hdr[12] = cpu_to_be16(ETH_P_802_EX1) & 0xff;
+	this->tx_eth_hdr[13] = (cpu_to_be16(ETH_P_802_EX1) >> 8) & 0xff;
+	pr_debug("caif ethernet TX-header dst:%pM src:%pM type:%02x%02x\n",
+			this->tx_eth_hdr, this->tx_eth_hdr + ETH_ALEN,
+			this->tx_eth_hdr[12], this->tx_eth_hdr[13]);
+
+	return (struct cflayer *) this;
+}
+
+static struct packet_type caif_usb_type __read_mostly = {
+	.type = cpu_to_be16(ETH_P_802_EX1),
+};
+
+static int cfusbl_device_notify(struct notifier_block *me, unsigned long what,
+			      void *arg)
+{
+	struct net_device *dev = arg;
+	struct caif_dev_common common;
+	struct cflayer *layer, *link_support;
+	struct usbnet	*usbnet = netdev_priv(dev);
+	struct usb_device	*usbdev = usbnet->udev;
+	struct ethtool_drvinfo drvinfo;
+
+	/*
+	 * Quirks: High-jack ethtool to find if we have a NCM device,
+	 * and find it's VID/PID.
+	 */
+	if (dev->ethtool_ops == NULL || dev->ethtool_ops->get_drvinfo == NULL)
+		return 0;
+
+	dev->ethtool_ops->get_drvinfo(dev, &drvinfo);
+	if (strncmp(drvinfo.driver, "cdc_ncm", 7) != 0)
+		return 0;
+
+	pr_debug("USB CDC NCM device VID:0x%4x PID:0x%4x\n",
+		le16_to_cpu(usbdev->descriptor.idVendor),
+		le16_to_cpu(usbdev->descriptor.idProduct));
+
+	/* Check for VID/PID that supports CAIF */
+	if (!(le16_to_cpu(usbdev->descriptor.idVendor) == STE_USB_VID &&
+		le16_to_cpu(usbdev->descriptor.idProduct) == STE_USB_PID_CAIF))
+		return 0;
+
+	if (what == NETDEV_UNREGISTER)
+		module_put(THIS_MODULE);
+
+	if (what != NETDEV_REGISTER)
+		return 0;
+
+	__module_get(THIS_MODULE);
+
+	memset(&common, 0, sizeof(common));
+	common.use_frag = false;
+	common.use_fcs = false;
+	common.use_stx = false;
+	common.link_select = CAIF_LINK_HIGH_BANDW;
+	common.flowctrl = NULL;
+
+	link_support = cfusbl_create(dev->ifindex, dev->dev_addr,
+					dev->broadcast);
+
+	if (!link_support)
+		return -ENOMEM;
+
+	if (dev->num_tx_queues > 1)
+		pr_warn("USB device uses more than one tx queue\n");
+
+	caif_enroll_dev(dev, &common, link_support, CFUSB_MAX_HEADLEN,
+			&layer, &caif_usb_type.func);
+	if (!pack_added)
+		dev_add_pack(&caif_usb_type);
+	pack_added = 1;
+
+	strncpy(layer->name, dev->name,
+			sizeof(layer->name) - 1);
+	layer->name[sizeof(layer->name) - 1] = 0;
+
+	return 0;
+}
+
+static struct notifier_block caif_device_notifier = {
+	.notifier_call = cfusbl_device_notify,
+	.priority = 0,
+};
+
+static int __init cfusbl_init(void)
+{
+	return register_netdevice_notifier(&caif_device_notifier);
+}
+
+static void __exit cfusbl_exit(void)
+{
+	unregister_netdevice_notifier(&caif_device_notifier);
+	dev_remove_pack(&caif_usb_type);
+}
+
+module_init(cfusbl_init);
+module_exit(cfusbl_exit);
diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c
index 00523ec..598aafb 100644
--- a/net/caif/cfcnfg.c
+++ b/net/caif/cfcnfg.c
@@ -45,8 +45,8 @@ struct cfcnfg_phyinfo {
 	/* Interface index */
 	int ifindex;
 
-	/* Use Start of frame extension */
-	bool use_stx;
+	/* Protocol head room added for CAIF link layer */
+	int head_room;
 
 	/* Use Start of frame checksum */
 	bool use_fcs;
@@ -187,11 +187,11 @@ int caif_disconnect_client(struct net *net, struct cflayer *adap_layer)
 	if (channel_id != 0) {
 		struct cflayer *servl;
 		servl = cfmuxl_remove_uplayer(cfg->mux, channel_id);
+		cfctrl_linkdown_req(cfg->ctrl, channel_id, adap_layer);
 		if (servl != NULL)
 			layer_set_up(servl, NULL);
 	} else
 		pr_debug("nothing to disconnect\n");
-	cfctrl_linkdown_req(cfg->ctrl, channel_id, adap_layer);
 
 	/* Do RCU sync before initiating cleanup */
 	synchronize_rcu();
@@ -350,9 +350,7 @@ int caif_connect_client(struct net *net, struct caif_connect_request *conn_req,
 
 	*ifindex = phy->ifindex;
 	*proto_tail = 2;
-	*proto_head =
-
-	protohead[param.linktype] + (phy->use_stx ? 1 : 0);
+	*proto_head = protohead[param.linktype] + phy->head_room;
 
 	rcu_read_unlock();
 
@@ -460,13 +458,13 @@ unlock:
 }
 
 void
-cfcnfg_add_phy_layer(struct cfcnfg *cnfg, enum cfcnfg_phy_type phy_type,
+cfcnfg_add_phy_layer(struct cfcnfg *cnfg,
 		     struct net_device *dev, struct cflayer *phy_layer,
 		     enum cfcnfg_phy_preference pref,
-		     bool fcs, bool stx)
+		     struct cflayer *link_support,
+		     bool fcs, int head_room)
 {
 	struct cflayer *frml;
-	struct cflayer *phy_driver = NULL;
 	struct cfcnfg_phyinfo *phyinfo = NULL;
 	int i;
 	u8 phyid;
@@ -482,26 +480,13 @@ cfcnfg_add_phy_layer(struct cfcnfg *cnfg, enum cfcnfg_phy_type phy_type,
 			goto got_phyid;
 	}
 	pr_warn("Too many CAIF Link Layers (max 6)\n");
-	goto out_err;
+	goto out;
 
 got_phyid:
 	phyinfo = kzalloc(sizeof(struct cfcnfg_phyinfo), GFP_ATOMIC);
 	if (!phyinfo)
 		goto out_err;
 
-	switch (phy_type) {
-	case CFPHYTYPE_FRAG:
-		phy_driver =
-		    cfserl_create(CFPHYTYPE_FRAG, phyid, stx);
-		if (!phy_driver)
-			goto out_err;
-		break;
-	case CFPHYTYPE_CAIF:
-		phy_driver = NULL;
-		break;
-	default:
-		goto out_err;
-	}
 	phy_layer->id = phyid;
 	phyinfo->pref = pref;
 	phyinfo->id = phyid;
@@ -509,7 +494,7 @@ got_phyid:
 	phyinfo->dev_info.dev = dev;
 	phyinfo->phy_layer = phy_layer;
 	phyinfo->ifindex = dev->ifindex;
-	phyinfo->use_stx = stx;
+	phyinfo->head_room = head_room;
 	phyinfo->use_fcs = fcs;
 
 	frml = cffrml_create(phyid, fcs);
@@ -519,23 +504,23 @@ got_phyid:
 	phyinfo->frm_layer = frml;
 	layer_set_up(frml, cnfg->mux);
 
-	if (phy_driver != NULL) {
-		phy_driver->id = phyid;
-		layer_set_dn(frml, phy_driver);
-		layer_set_up(phy_driver, frml);
-		layer_set_dn(phy_driver, phy_layer);
-		layer_set_up(phy_layer, phy_driver);
+	if (link_support != NULL) {
+		link_support->id = phyid;
+		layer_set_dn(frml, link_support);
+		layer_set_up(link_support, frml);
+		layer_set_dn(link_support, phy_layer);
+		layer_set_up(phy_layer, link_support);
 	} else {
 		layer_set_dn(frml, phy_layer);
 		layer_set_up(phy_layer, frml);
 	}
 
 	list_add_rcu(&phyinfo->node, &cnfg->phys);
+out:
 	mutex_unlock(&cnfg->lock);
 	return;
 
 out_err:
-	kfree(phy_driver);
 	kfree(phyinfo);
 	mutex_unlock(&cnfg->lock);
 }
diff --git a/net/caif/cffrml.c b/net/caif/cffrml.c
index f399211..d3ca87b 100644
--- a/net/caif/cffrml.c
+++ b/net/caif/cffrml.c
@@ -136,20 +136,21 @@ static int cffrml_receive(struct cflayer *layr, struct cfpkt *pkt)
 
 static int cffrml_transmit(struct cflayer *layr, struct cfpkt *pkt)
 {
-	int tmp;
 	u16 chks;
 	u16 len;
+	__le16 data;
+
 	struct cffrml *this = container_obj(layr);
 	if (this->dofcs) {
 		chks = cfpkt_iterate(pkt, cffrml_checksum, 0xffff);
-		tmp = cpu_to_le16(chks);
-		cfpkt_add_trail(pkt, &tmp, 2);
+		data = cpu_to_le16(chks);
+		cfpkt_add_trail(pkt, &data, 2);
 	} else {
 		cfpkt_pad_trail(pkt, 2);
 	}
 	len = cfpkt_getlen(pkt);
-	tmp = cpu_to_le16(len);
-	cfpkt_add_head(pkt, &tmp, 2);
+	data = cpu_to_le16(len);
+	cfpkt_add_head(pkt, &data, 2);
 	cfpkt_info(pkt)->hdr_len += 2;
 	if (cfpkt_erroneous(pkt)) {
 		pr_err("Packet is erroneous!\n");
diff --git a/net/caif/cfpkt_skbuff.c b/net/caif/cfpkt_skbuff.c
index df08c47..e335ba8 100644
--- a/net/caif/cfpkt_skbuff.c
+++ b/net/caif/cfpkt_skbuff.c
@@ -63,7 +63,6 @@ static inline struct cfpkt *skb_to_pkt(struct sk_buff *skb)
 	return (struct cfpkt *) skb;
 }
 
-
 struct cfpkt *cfpkt_fromnative(enum caif_direction dir, void *nativepkt)
 {
 	struct cfpkt *pkt = skb_to_pkt(nativepkt);
@@ -105,14 +104,12 @@ void cfpkt_destroy(struct cfpkt *pkt)
 	kfree_skb(skb);
 }
 
-
 inline bool cfpkt_more(struct cfpkt *pkt)
 {
 	struct sk_buff *skb = pkt_to_skb(pkt);
 	return skb->len > 0;
 }
 
-
 int cfpkt_peek_head(struct cfpkt *pkt, void *data, u16 len)
 {
 	struct sk_buff *skb = pkt_to_skb(pkt);
@@ -144,9 +141,11 @@ int cfpkt_extr_head(struct cfpkt *pkt, void *data, u16 len)
 	}
 	from = skb_pull(skb, len);
 	from -= len;
-	memcpy(data, from, len);
+	if (data)
+		memcpy(data, from, len);
 	return 0;
 }
+EXPORT_SYMBOL(cfpkt_extr_head);
 
 int cfpkt_extr_trail(struct cfpkt *pkt, void *dta, u16 len)
 {
@@ -170,13 +169,11 @@ int cfpkt_extr_trail(struct cfpkt *pkt, void *dta, u16 len)
 	return 0;
 }
 
-
 int cfpkt_pad_trail(struct cfpkt *pkt, u16 len)
 {
 	return cfpkt_add_body(pkt, NULL, len);
 }
 
-
 int cfpkt_add_body(struct cfpkt *pkt, const void *data, u16 len)
 {
 	struct sk_buff *skb = pkt_to_skb(pkt);
@@ -255,21 +252,19 @@ int cfpkt_add_head(struct cfpkt *pkt, const void *data2, u16 len)
 	memcpy(to, data, len);
 	return 0;
 }
-
+EXPORT_SYMBOL(cfpkt_add_head);
 
 inline int cfpkt_add_trail(struct cfpkt *pkt, const void *data, u16 len)
 {
 	return cfpkt_add_body(pkt, data, len);
 }
 
-
 inline u16 cfpkt_getlen(struct cfpkt *pkt)
 {
 	struct sk_buff *skb = pkt_to_skb(pkt);
 	return skb->len;
 }
 
-
 inline u16 cfpkt_iterate(struct cfpkt *pkt,
 			    u16 (*iter_func)(u16, void *, u16),
 			    u16 data)
@@ -287,7 +282,6 @@ inline u16 cfpkt_iterate(struct cfpkt *pkt,
 	return iter_func(data, pkt->skb.data, cfpkt_getlen(pkt));
 }
 
-
 int cfpkt_setlen(struct cfpkt *pkt, u16 len)
 {
 	struct sk_buff *skb = pkt_to_skb(pkt);
@@ -399,3 +393,4 @@ struct caif_payload_info *cfpkt_info(struct cfpkt *pkt)
 {
 	return (struct caif_payload_info *)&pkt_to_skb(pkt)->cb;
 }
+EXPORT_SYMBOL(cfpkt_info);
diff --git a/net/caif/cfrfml.c b/net/caif/cfrfml.c
index 81660f8..6dc75d4 100644
--- a/net/caif/cfrfml.c
+++ b/net/caif/cfrfml.c
@@ -190,7 +190,7 @@ out:
 
 static int cfrfml_transmit_segment(struct cfrfml *rfml, struct cfpkt *pkt)
 {
-	caif_assert(cfpkt_getlen(pkt) < rfml->fragment_size);
+	caif_assert(cfpkt_getlen(pkt) < rfml->fragment_size + RFM_HEAD_SIZE);
 
 	/* Add info for MUX-layer to route the packet out. */
 	cfpkt_info(pkt)->channel_id = rfml->serv.layer.id;
diff --git a/net/caif/cfserl.c b/net/caif/cfserl.c
index 797c8d1..8e68b97 100644
--- a/net/caif/cfserl.c
+++ b/net/caif/cfserl.c
@@ -31,7 +31,7 @@ static int cfserl_transmit(struct cflayer *layr, struct cfpkt *pkt);
 static void cfserl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl,
 				int phyid);
 
-struct cflayer *cfserl_create(int type, int instance, bool use_stx)
+struct cflayer *cfserl_create(int instance, bool use_stx)
 {
 	struct cfserl *this = kzalloc(sizeof(struct cfserl), GFP_ATOMIC);
 	if (!this)
@@ -40,7 +40,6 @@ struct cflayer *cfserl_create(int type, int instance, bool use_stx)
 	this->layer.receive = cfserl_receive;
 	this->layer.transmit = cfserl_transmit;
 	this->layer.ctrlcmd = cfserl_ctrlcmd;
-	this->layer.type = type;
 	this->usestx = use_stx;
 	spin_lock_init(&this->sync);
 	snprintf(this->layer.name, CAIF_LAYER_NAME_SZ, "ser1");
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 733e4600..f4f3f58 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -244,7 +244,7 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 		ceph_pagelist_init(req->r_trail);
 	}
 	/* create request message; allow space for oid */
-	msg_size += 40;
+	msg_size += MAX_OBJ_NAME_SIZE;
 	if (snapc)
 		msg_size += sizeof(u64) * snapc->num_snaps;
 	if (use_mempool)
diff --git a/net/core/Makefile b/net/core/Makefile
index 0d357b1..674641b 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -3,12 +3,13 @@
 #
 
 obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \
-	 gen_stats.o gen_estimator.o net_namespace.o secure_seq.o
+	 gen_stats.o gen_estimator.o net_namespace.o secure_seq.o flow_dissector.o
 
 obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
 
 obj-y		     += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \
-			neighbour.o rtnetlink.o utils.o link_watch.o filter.o
+			neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
+			sock_diag.o
 
 obj-$(CONFIG_XFRM) += flow.o
 obj-y += net-sysfs.o
@@ -19,3 +20,4 @@ obj-$(CONFIG_FIB_RULES) += fib_rules.o
 obj-$(CONFIG_TRACEPOINTS) += net-traces.o
 obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o
 obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o
+obj-$(CONFIG_NETPRIO_CGROUP) += netprio_cgroup.o
diff --git a/net/core/dev.c b/net/core/dev.c
index 6ba50a1..f494675 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -133,10 +133,9 @@
 #include <linux/pci.h>
 #include <linux/inetdevice.h>
 #include <linux/cpu_rmap.h>
-#include <linux/if_tunnel.h>
-#include <linux/if_pppox.h>
-#include <linux/ppp_defs.h>
 #include <linux/net_tstamp.h>
+#include <linux/jump_label.h>
+#include <net/flow_keys.h>
 
 #include "net-sysfs.h"
 
@@ -1320,8 +1319,6 @@ EXPORT_SYMBOL(dev_close);
  */
 void dev_disable_lro(struct net_device *dev)
 {
-	u32 flags;
-
 	/*
 	 * If we're trying to disable lro on a vlan device
 	 * use the underlying physical device instead
@@ -1329,15 +1326,9 @@ void dev_disable_lro(struct net_device *dev)
 	if (is_vlan_dev(dev))
 		dev = vlan_dev_real_dev(dev);
 
-	if (dev->ethtool_ops && dev->ethtool_ops->get_flags)
-		flags = dev->ethtool_ops->get_flags(dev);
-	else
-		flags = ethtool_op_get_flags(dev);
+	dev->wanted_features &= ~NETIF_F_LRO;
+	netdev_update_features(dev);
 
-	if (!(flags & ETH_FLAG_LRO))
-		return;
-
-	__ethtool_set_flags(dev, flags & ~ETH_FLAG_LRO);
 	if (unlikely(dev->features & NETIF_F_LRO))
 		netdev_WARN(dev, "failed to disable LRO!\n");
 }
@@ -1396,7 +1387,7 @@ rollback:
 	for_each_net(net) {
 		for_each_netdev(net, dev) {
 			if (dev == last)
-				break;
+				goto outroll;
 
 			if (dev->flags & IFF_UP) {
 				nb->notifier_call(nb, NETDEV_GOING_DOWN, dev);
@@ -1407,6 +1398,7 @@ rollback:
 		}
 	}
 
+outroll:
 	raw_notifier_chain_unregister(&netdev_chain, nb);
 	goto unlock;
 }
@@ -1449,34 +1441,55 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev)
 }
 EXPORT_SYMBOL(call_netdevice_notifiers);
 
-/* When > 0 there are consumers of rx skb time stamps */
-static atomic_t netstamp_needed = ATOMIC_INIT(0);
+static struct jump_label_key netstamp_needed __read_mostly;
+#ifdef HAVE_JUMP_LABEL
+/* We are not allowed to call jump_label_dec() from irq context
+ * If net_disable_timestamp() is called from irq context, defer the
+ * jump_label_dec() calls.
+ */
+static atomic_t netstamp_needed_deferred;
+#endif
 
 void net_enable_timestamp(void)
 {
-	atomic_inc(&netstamp_needed);
+#ifdef HAVE_JUMP_LABEL
+	int deferred = atomic_xchg(&netstamp_needed_deferred, 0);
+
+	if (deferred) {
+		while (--deferred)
+			jump_label_dec(&netstamp_needed);
+		return;
+	}
+#endif
+	WARN_ON(in_interrupt());
+	jump_label_inc(&netstamp_needed);
 }
 EXPORT_SYMBOL(net_enable_timestamp);
 
 void net_disable_timestamp(void)
 {
-	atomic_dec(&netstamp_needed);
+#ifdef HAVE_JUMP_LABEL
+	if (in_interrupt()) {
+		atomic_inc(&netstamp_needed_deferred);
+		return;
+	}
+#endif
+	jump_label_dec(&netstamp_needed);
 }
 EXPORT_SYMBOL(net_disable_timestamp);
 
 static inline void net_timestamp_set(struct sk_buff *skb)
 {
-	if (atomic_read(&netstamp_needed))
+	skb->tstamp.tv64 = 0;
+	if (static_branch(&netstamp_needed))
 		__net_timestamp(skb);
-	else
-		skb->tstamp.tv64 = 0;
 }
 
-static inline void net_timestamp_check(struct sk_buff *skb)
-{
-	if (!skb->tstamp.tv64 && atomic_read(&netstamp_needed))
-		__net_timestamp(skb);
-}
+#define net_timestamp_check(COND, SKB)			\
+	if (static_branch(&netstamp_needed)) {		\
+		if ((COND) && !(SKB)->tstamp.tv64)	\
+			__net_timestamp(SKB);		\
+	}						\
 
 static int net_hwtstamp_validate(struct ifreq *ifr)
 {
@@ -1923,7 +1936,8 @@ EXPORT_SYMBOL(skb_checksum_help);
  *	It may return NULL if the skb requires no segmentation.  This is
  *	only possible when GSO is used for verifying header integrity.
  */
-struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features)
+struct sk_buff *skb_gso_segment(struct sk_buff *skb,
+	netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT);
 	struct packet_type *ptype;
@@ -1953,9 +1967,9 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features)
 		if (dev && dev->ethtool_ops && dev->ethtool_ops->get_drvinfo)
 			dev->ethtool_ops->get_drvinfo(dev, &info);
 
-		WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d ip_summed=%d\n",
-		     info.driver, dev ? dev->features : 0L,
-		     skb->sk ? skb->sk->sk_route_caps : 0L,
+		WARN(1, "%s: caps=(%pNF, %pNF) len=%d data_len=%d ip_summed=%d\n",
+		     info.driver, dev ? &dev->features : NULL,
+		     skb->sk ? &skb->sk->sk_route_caps : NULL,
 		     skb->len, skb->data_len, skb->ip_summed);
 
 		if (skb_header_cloned(skb) &&
@@ -2064,7 +2078,7 @@ static void dev_gso_skb_destructor(struct sk_buff *skb)
  *	This function segments the given skb and stores the list of segments
  *	in skb->next.
  */
-static int dev_gso_segment(struct sk_buff *skb, int features)
+static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
 {
 	struct sk_buff *segs;
 
@@ -2103,7 +2117,7 @@ static inline void skb_orphan_try(struct sk_buff *skb)
 	}
 }
 
-static bool can_checksum_protocol(unsigned long features, __be16 protocol)
+static bool can_checksum_protocol(netdev_features_t features, __be16 protocol)
 {
 	return ((features & NETIF_F_GEN_CSUM) ||
 		((features & NETIF_F_V4_CSUM) &&
@@ -2114,7 +2128,8 @@ static bool can_checksum_protocol(unsigned long features, __be16 protocol)
 		 protocol == htons(ETH_P_FCOE)));
 }
 
-static u32 harmonize_features(struct sk_buff *skb, __be16 protocol, u32 features)
+static netdev_features_t harmonize_features(struct sk_buff *skb,
+	__be16 protocol, netdev_features_t features)
 {
 	if (!can_checksum_protocol(features, protocol)) {
 		features &= ~NETIF_F_ALL_CSUM;
@@ -2126,10 +2141,10 @@ static u32 harmonize_features(struct sk_buff *skb, __be16 protocol, u32 features
 	return features;
 }
 
-u32 netif_skb_features(struct sk_buff *skb)
+netdev_features_t netif_skb_features(struct sk_buff *skb)
 {
 	__be16 protocol = skb->protocol;
-	u32 features = skb->dev->features;
+	netdev_features_t features = skb->dev->features;
 
 	if (protocol == htons(ETH_P_8021Q)) {
 		struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
@@ -2175,7 +2190,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 	unsigned int skb_len;
 
 	if (likely(!skb->next)) {
-		u32 features;
+		netdev_features_t features;
 
 		/*
 		 * If device doesn't need skb->dst, release it right now while
@@ -2256,7 +2271,7 @@ gso:
 			return rc;
 		}
 		txq_trans_update(txq);
-		if (unlikely(netif_tx_queue_stopped(txq) && skb->next))
+		if (unlikely(netif_xmit_stopped(txq) && skb->next))
 			return NETDEV_TX_BUSY;
 	} while (skb->next);
 
@@ -2456,6 +2471,18 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
 	return rc;
 }
 
+#if IS_ENABLED(CONFIG_NETPRIO_CGROUP)
+static void skb_update_prio(struct sk_buff *skb)
+{
+	struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap);
+
+	if ((!skb->priority) && (skb->sk) && map)
+		skb->priority = map->priomap[skb->sk->sk_cgrp_prioidx];
+}
+#else
+#define skb_update_prio(skb)
+#endif
+
 static DEFINE_PER_CPU(int, xmit_recursion);
 #define RECURSION_LIMIT 10
 
@@ -2496,6 +2523,8 @@ int dev_queue_xmit(struct sk_buff *skb)
 	 */
 	rcu_read_lock_bh();
 
+	skb_update_prio(skb);
+
 	txq = dev_pick_tx(dev, skb);
 	q = rcu_dereference_bh(txq->qdisc);
 
@@ -2530,7 +2559,7 @@ int dev_queue_xmit(struct sk_buff *skb)
 
 			HARD_TX_LOCK(dev, txq, cpu);
 
-			if (!netif_tx_queue_stopped(txq)) {
+			if (!netif_xmit_stopped(txq)) {
 				__this_cpu_inc(xmit_recursion);
 				rc = dev_hard_start_xmit(skb, dev, txq);
 				__this_cpu_dec(xmit_recursion);
@@ -2591,123 +2620,28 @@ static inline void ____napi_schedule(struct softnet_data *sd,
  */
 void __skb_get_rxhash(struct sk_buff *skb)
 {
-	int nhoff, hash = 0, poff;
-	const struct ipv6hdr *ip6;
-	const struct iphdr *ip;
-	const struct vlan_hdr *vlan;
-	u8 ip_proto;
-	u32 addr1, addr2;
-	u16 proto;
-	union {
-		u32 v32;
-		u16 v16[2];
-	} ports;
-
-	nhoff = skb_network_offset(skb);
-	proto = skb->protocol;
-
-again:
-	switch (proto) {
-	case __constant_htons(ETH_P_IP):
-ip:
-		if (!pskb_may_pull(skb, sizeof(*ip) + nhoff))
-			goto done;
-
-		ip = (const struct iphdr *) (skb->data + nhoff);
-		if (ip_is_fragment(ip))
-			ip_proto = 0;
-		else
-			ip_proto = ip->protocol;
-		addr1 = (__force u32) ip->saddr;
-		addr2 = (__force u32) ip->daddr;
-		nhoff += ip->ihl * 4;
-		break;
-	case __constant_htons(ETH_P_IPV6):
-ipv6:
-		if (!pskb_may_pull(skb, sizeof(*ip6) + nhoff))
-			goto done;
-
-		ip6 = (const struct ipv6hdr *) (skb->data + nhoff);
-		ip_proto = ip6->nexthdr;
-		addr1 = (__force u32) ip6->saddr.s6_addr32[3];
-		addr2 = (__force u32) ip6->daddr.s6_addr32[3];
-		nhoff += 40;
-		break;
-	case __constant_htons(ETH_P_8021Q):
-		if (!pskb_may_pull(skb, sizeof(*vlan) + nhoff))
-			goto done;
-		vlan = (const struct vlan_hdr *) (skb->data + nhoff);
-		proto = vlan->h_vlan_encapsulated_proto;
-		nhoff += sizeof(*vlan);
-		goto again;
-	case __constant_htons(ETH_P_PPP_SES):
-		if (!pskb_may_pull(skb, PPPOE_SES_HLEN + nhoff))
-			goto done;
-		proto = *((__be16 *) (skb->data + nhoff +
-				      sizeof(struct pppoe_hdr)));
-		nhoff += PPPOE_SES_HLEN;
-		switch (proto) {
-		case __constant_htons(PPP_IP):
-			goto ip;
-		case __constant_htons(PPP_IPV6):
-			goto ipv6;
-		default:
-			goto done;
-		}
-	default:
-		goto done;
-	}
-
-	switch (ip_proto) {
-	case IPPROTO_GRE:
-		if (pskb_may_pull(skb, nhoff + 16)) {
-			u8 *h = skb->data + nhoff;
-			__be16 flags = *(__be16 *)h;
+	struct flow_keys keys;
+	u32 hash;
 
-			/*
-			 * Only look inside GRE if version zero and no
-			 * routing
-			 */
-			if (!(flags & (GRE_VERSION|GRE_ROUTING))) {
-				proto = *(__be16 *)(h + 2);
-				nhoff += 4;
-				if (flags & GRE_CSUM)
-					nhoff += 4;
-				if (flags & GRE_KEY)
-					nhoff += 4;
-				if (flags & GRE_SEQ)
-					nhoff += 4;
-				goto again;
-			}
-		}
-		break;
-	case IPPROTO_IPIP:
-		goto again;
-	default:
-		break;
-	}
+	if (!skb_flow_dissect(skb, &keys))
+		return;
 
-	ports.v32 = 0;
-	poff = proto_ports_offset(ip_proto);
-	if (poff >= 0) {
-		nhoff += poff;
-		if (pskb_may_pull(skb, nhoff + 4)) {
-			ports.v32 = * (__force u32 *) (skb->data + nhoff);
-			if (ports.v16[1] < ports.v16[0])
-				swap(ports.v16[0], ports.v16[1]);
-			skb->l4_rxhash = 1;
-		}
+	if (keys.ports) {
+		if ((__force u16)keys.port16[1] < (__force u16)keys.port16[0])
+			swap(keys.port16[0], keys.port16[1]);
+		skb->l4_rxhash = 1;
 	}
 
 	/* get a consistent hash (same value on both flow directions) */
-	if (addr2 < addr1)
-		swap(addr1, addr2);
+	if ((__force u32)keys.dst < (__force u32)keys.src)
+		swap(keys.dst, keys.src);
 
-	hash = jhash_3words(addr1, addr2, ports.v32, hashrnd);
+	hash = jhash_3words((__force u32)keys.dst,
+			    (__force u32)keys.src,
+			    (__force u32)keys.ports, hashrnd);
 	if (!hash)
 		hash = 1;
 
-done:
 	skb->rxhash = hash;
 }
 EXPORT_SYMBOL(__skb_get_rxhash);
@@ -2718,6 +2652,8 @@ EXPORT_SYMBOL(__skb_get_rxhash);
 struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly;
 EXPORT_SYMBOL(rps_sock_flow_table);
 
+struct jump_label_key rps_needed __read_mostly;
+
 static struct rps_dev_flow *
 set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 	    struct rps_dev_flow *rflow, u16 next_cpu)
@@ -2997,12 +2933,11 @@ int netif_rx(struct sk_buff *skb)
 	if (netpoll_rx(skb))
 		return NET_RX_DROP;
 
-	if (netdev_tstamp_prequeue)
-		net_timestamp_check(skb);
+	net_timestamp_check(netdev_tstamp_prequeue, skb);
 
 	trace_netif_rx(skb);
 #ifdef CONFIG_RPS
-	{
+	if (static_branch(&rps_needed))	{
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
 		int cpu;
 
@@ -3017,14 +2952,13 @@ int netif_rx(struct sk_buff *skb)
 
 		rcu_read_unlock();
 		preempt_enable();
-	}
-#else
+	} else
+#endif
 	{
 		unsigned int qtail;
 		ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
 		put_cpu();
 	}
-#endif
 	return ret;
 }
 EXPORT_SYMBOL(netif_rx);
@@ -3230,8 +3164,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	int ret = NET_RX_DROP;
 	__be16 type;
 
-	if (!netdev_tstamp_prequeue)
-		net_timestamp_check(skb);
+	net_timestamp_check(!netdev_tstamp_prequeue, skb);
 
 	trace_netif_receive_skb(skb);
 
@@ -3362,14 +3295,13 @@ out:
  */
 int netif_receive_skb(struct sk_buff *skb)
 {
-	if (netdev_tstamp_prequeue)
-		net_timestamp_check(skb);
+	net_timestamp_check(netdev_tstamp_prequeue, skb);
 
 	if (skb_defer_rx_timestamp(skb))
 		return NET_RX_SUCCESS;
 
 #ifdef CONFIG_RPS
-	{
+	if (static_branch(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
 		int cpu, ret;
 
@@ -3380,16 +3312,12 @@ int netif_receive_skb(struct sk_buff *skb)
 		if (cpu >= 0) {
 			ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
 			rcu_read_unlock();
-		} else {
-			rcu_read_unlock();
-			ret = __netif_receive_skb(skb);
+			return ret;
 		}
-
-		return ret;
+		rcu_read_unlock();
 	}
-#else
-	return __netif_receive_skb(skb);
 #endif
+	return __netif_receive_skb(skb);
 }
 EXPORT_SYMBOL(netif_receive_skb);
 
@@ -4282,6 +4210,12 @@ static int dev_seq_open(struct inode *inode, struct file *file)
 			    sizeof(struct dev_iter_state));
 }
 
+int dev_seq_open_ops(struct inode *inode, struct file *file,
+		     const struct seq_operations *ops)
+{
+	return seq_open_net(inode, file, ops, sizeof(struct dev_iter_state));
+}
+
 static const struct file_operations dev_seq_fops = {
 	.owner	 = THIS_MODULE,
 	.open    = dev_seq_open,
@@ -4532,7 +4466,7 @@ static void dev_change_rx_flags(struct net_device *dev, int flags)
 
 static int __dev_set_promiscuity(struct net_device *dev, int inc)
 {
-	unsigned short old_flags = dev->flags;
+	unsigned int old_flags = dev->flags;
 	uid_t uid;
 	gid_t gid;
 
@@ -4589,7 +4523,7 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc)
  */
 int dev_set_promiscuity(struct net_device *dev, int inc)
 {
-	unsigned short old_flags = dev->flags;
+	unsigned int old_flags = dev->flags;
 	int err;
 
 	err = __dev_set_promiscuity(dev, inc);
@@ -4616,7 +4550,7 @@ EXPORT_SYMBOL(dev_set_promiscuity);
 
 int dev_set_allmulti(struct net_device *dev, int inc)
 {
-	unsigned short old_flags = dev->flags;
+	unsigned int old_flags = dev->flags;
 
 	ASSERT_RTNL();
 
@@ -4719,7 +4653,7 @@ EXPORT_SYMBOL(dev_get_flags);
 
 int __dev_change_flags(struct net_device *dev, unsigned int flags)
 {
-	int old_flags = dev->flags;
+	unsigned int old_flags = dev->flags;
 	int ret;
 
 	ASSERT_RTNL();
@@ -4802,10 +4736,10 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags)
  *	Change settings on device based state flags. The flags are
  *	in the userspace exported format.
  */
-int dev_change_flags(struct net_device *dev, unsigned flags)
+int dev_change_flags(struct net_device *dev, unsigned int flags)
 {
-	int ret, changes;
-	int old_flags = dev->flags;
+	int ret;
+	unsigned int changes, old_flags = dev->flags;
 
 	ret = __dev_change_flags(dev, flags);
 	if (ret < 0)
@@ -5362,7 +5296,8 @@ static void rollback_registered(struct net_device *dev)
 	list_del(&single);
 }
 
-static u32 netdev_fix_features(struct net_device *dev, u32 features)
+static netdev_features_t netdev_fix_features(struct net_device *dev,
+	netdev_features_t features)
 {
 	/* Fix illegal checksum combinations */
 	if ((features & NETIF_F_HW_CSUM) &&
@@ -5371,12 +5306,6 @@ static u32 netdev_fix_features(struct net_device *dev, u32 features)
 		features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM);
 	}
 
-	if ((features & NETIF_F_NO_CSUM) &&
-	    (features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) {
-		netdev_warn(dev, "mixed no checksumming and other settings.\n");
-		features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM);
-	}
-
 	/* Fix illegal SG+CSUM combinations. */
 	if ((features & NETIF_F_SG) &&
 	    !(features & NETIF_F_ALL_CSUM)) {
@@ -5424,7 +5353,7 @@ static u32 netdev_fix_features(struct net_device *dev, u32 features)
 
 int __netdev_update_features(struct net_device *dev)
 {
-	u32 features;
+	netdev_features_t features;
 	int err = 0;
 
 	ASSERT_RTNL();
@@ -5440,16 +5369,16 @@ int __netdev_update_features(struct net_device *dev)
 	if (dev->features == features)
 		return 0;
 
-	netdev_dbg(dev, "Features changed: 0x%08x -> 0x%08x\n",
-		dev->features, features);
+	netdev_dbg(dev, "Features changed: %pNF -> %pNF\n",
+		&dev->features, &features);
 
 	if (dev->netdev_ops->ndo_set_features)
 		err = dev->netdev_ops->ndo_set_features(dev, features);
 
 	if (unlikely(err < 0)) {
 		netdev_err(dev,
-			"set_features() failed (%d); wanted 0x%08x, left 0x%08x\n",
-			err, features, dev->features);
+			"set_features() failed (%d); wanted %pNF, left %pNF\n",
+			err, &features, &dev->features);
 		return -1;
 	}
 
@@ -5548,6 +5477,9 @@ static void netdev_init_one_queue(struct net_device *dev,
 	queue->xmit_lock_owner = -1;
 	netdev_queue_numa_node_write(queue, NUMA_NO_NODE);
 	queue->dev = dev;
+#ifdef CONFIG_BQL
+	dql_init(&queue->dql, HZ);
+#endif
 }
 
 static int netif_alloc_netdev_queues(struct net_device *dev)
@@ -5633,11 +5565,12 @@ int register_netdevice(struct net_device *dev)
 	dev->wanted_features = dev->features & dev->hw_features;
 
 	/* Turn on no cache copy if HW is doing checksum */
-	dev->hw_features |= NETIF_F_NOCACHE_COPY;
-	if ((dev->features & NETIF_F_ALL_CSUM) &&
-	    !(dev->features & NETIF_F_NO_CSUM)) {
-		dev->wanted_features |= NETIF_F_NOCACHE_COPY;
-		dev->features |= NETIF_F_NOCACHE_COPY;
+	if (!(dev->flags & IFF_LOOPBACK)) {
+		dev->hw_features |= NETIF_F_NOCACHE_COPY;
+		if (dev->features & NETIF_F_ALL_CSUM) {
+			dev->wanted_features |= NETIF_F_NOCACHE_COPY;
+			dev->features |= NETIF_F_NOCACHE_COPY;
+		}
 	}
 
 	/* Make NETIF_F_HIGHDMA inheritable to VLAN devices.
@@ -6373,7 +6306,8 @@ static int dev_cpu_callback(struct notifier_block *nfb,
  *	@one to the master device with current feature set @all.  Will not
  *	enable anything that is off in @mask. Returns the new feature set.
  */
-u32 netdev_increment_features(u32 all, u32 one, u32 mask)
+netdev_features_t netdev_increment_features(netdev_features_t all,
+	netdev_features_t one, netdev_features_t mask)
 {
 	if (mask & NETIF_F_GEN_CSUM)
 		mask |= NETIF_F_ALL_CSUM;
@@ -6382,10 +6316,6 @@ u32 netdev_increment_features(u32 all, u32 one, u32 mask)
 	all |= one & (NETIF_F_ONE_FOR_ALL|NETIF_F_ALL_CSUM) & mask;
 	all &= one | ~NETIF_F_ALL_FOR_ALL;
 
-	/* If device needs checksumming, downgrade to it. */
-	if (all & (NETIF_F_ALL_CSUM & ~NETIF_F_NO_CSUM))
-		all &= ~NETIF_F_NO_CSUM;
-
 	/* If one device supports hw checksumming, set for all. */
 	if (all & NETIF_F_GEN_CSUM)
 		all &= ~(NETIF_F_ALL_CSUM & ~NETIF_F_GEN_CSUM);
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 277faef..febba51 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -696,8 +696,7 @@ static const struct seq_operations dev_mc_seq_ops = {
 
 static int dev_mc_seq_open(struct inode *inode, struct file *file)
 {
-	return seq_open_net(inode, file, &dev_mc_seq_ops,
-			    sizeof(struct seq_net_private));
+	return dev_seq_open_ops(inode, file, &dev_mc_seq_ops);
 }
 
 static const struct file_operations dev_mc_seq_fops = {
diff --git a/net/core/dst.c b/net/core/dst.c
index d5e2c4c..43d94ce 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -366,7 +366,7 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 		dev_hold(dst->dev);
 		dev_put(dev);
 		rcu_read_lock();
-		neigh = dst_get_neighbour(dst);
+		neigh = dst_get_neighbour_noref(dst);
 		if (neigh && neigh->dev == dev) {
 			neigh->dev = dst->dev;
 			dev_hold(dst->dev);
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index f444817..597732c 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -36,235 +36,44 @@ u32 ethtool_op_get_link(struct net_device *dev)
 }
 EXPORT_SYMBOL(ethtool_op_get_link);
 
-u32 ethtool_op_get_tx_csum(struct net_device *dev)
-{
-	return (dev->features & NETIF_F_ALL_CSUM) != 0;
-}
-EXPORT_SYMBOL(ethtool_op_get_tx_csum);
-
-int ethtool_op_set_tx_csum(struct net_device *dev, u32 data)
-{
-	if (data)
-		dev->features |= NETIF_F_IP_CSUM;
-	else
-		dev->features &= ~NETIF_F_IP_CSUM;
-
-	return 0;
-}
-EXPORT_SYMBOL(ethtool_op_set_tx_csum);
-
-int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data)
-{
-	if (data)
-		dev->features |= NETIF_F_HW_CSUM;
-	else
-		dev->features &= ~NETIF_F_HW_CSUM;
-
-	return 0;
-}
-EXPORT_SYMBOL(ethtool_op_set_tx_hw_csum);
-
-int ethtool_op_set_tx_ipv6_csum(struct net_device *dev, u32 data)
-{
-	if (data)
-		dev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
-	else
-		dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
-
-	return 0;
-}
-EXPORT_SYMBOL(ethtool_op_set_tx_ipv6_csum);
-
-u32 ethtool_op_get_sg(struct net_device *dev)
-{
-	return (dev->features & NETIF_F_SG) != 0;
-}
-EXPORT_SYMBOL(ethtool_op_get_sg);
-
-int ethtool_op_set_sg(struct net_device *dev, u32 data)
-{
-	if (data)
-		dev->features |= NETIF_F_SG;
-	else
-		dev->features &= ~NETIF_F_SG;
-
-	return 0;
-}
-EXPORT_SYMBOL(ethtool_op_set_sg);
-
-u32 ethtool_op_get_tso(struct net_device *dev)
-{
-	return (dev->features & NETIF_F_TSO) != 0;
-}
-EXPORT_SYMBOL(ethtool_op_get_tso);
-
-int ethtool_op_set_tso(struct net_device *dev, u32 data)
-{
-	if (data)
-		dev->features |= NETIF_F_TSO;
-	else
-		dev->features &= ~NETIF_F_TSO;
-
-	return 0;
-}
-EXPORT_SYMBOL(ethtool_op_set_tso);
-
-u32 ethtool_op_get_ufo(struct net_device *dev)
-{
-	return (dev->features & NETIF_F_UFO) != 0;
-}
-EXPORT_SYMBOL(ethtool_op_get_ufo);
-
-int ethtool_op_set_ufo(struct net_device *dev, u32 data)
-{
-	if (data)
-		dev->features |= NETIF_F_UFO;
-	else
-		dev->features &= ~NETIF_F_UFO;
-	return 0;
-}
-EXPORT_SYMBOL(ethtool_op_set_ufo);
-
-/* the following list of flags are the same as their associated
- * NETIF_F_xxx values in include/linux/netdevice.h
- */
-static const u32 flags_dup_features =
-	(ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | ETH_FLAG_NTUPLE |
-	 ETH_FLAG_RXHASH);
-
-u32 ethtool_op_get_flags(struct net_device *dev)
-{
-	/* in the future, this function will probably contain additional
-	 * handling for flags which are not so easily handled
-	 * by a simple masking operation
-	 */
-
-	return dev->features & flags_dup_features;
-}
-EXPORT_SYMBOL(ethtool_op_get_flags);
-
-/* Check if device can enable (or disable) particular feature coded in "data"
- * argument. Flags "supported" describe features that can be toggled by device.
- * If feature can not be toggled, it state (enabled or disabled) must match
- * hardcoded device features state, otherwise flags are marked as invalid.
- */
-bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported)
-{
-	u32 features = dev->features & flags_dup_features;
-	/* "data" can contain only flags_dup_features bits,
-	 * see __ethtool_set_flags */
-
-	return (features & ~supported) != (data & ~supported);
-}
-EXPORT_SYMBOL(ethtool_invalid_flags);
-
-int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported)
-{
-	if (ethtool_invalid_flags(dev, data, supported))
-		return -EINVAL;
-
-	dev->features = ((dev->features & ~flags_dup_features) |
-			 (data & flags_dup_features));
-	return 0;
-}
-EXPORT_SYMBOL(ethtool_op_set_flags);
-
 /* Handlers for each ethtool command */
 
-#define ETHTOOL_DEV_FEATURE_WORDS	1
-
-static void ethtool_get_features_compat(struct net_device *dev,
-	struct ethtool_get_features_block *features)
-{
-	if (!dev->ethtool_ops)
-		return;
-
-	/* getting RX checksum */
-	if (dev->ethtool_ops->get_rx_csum)
-		if (dev->ethtool_ops->get_rx_csum(dev))
-			features[0].active |= NETIF_F_RXCSUM;
-
-	/* mark legacy-changeable features */
-	if (dev->ethtool_ops->set_sg)
-		features[0].available |= NETIF_F_SG;
-	if (dev->ethtool_ops->set_tx_csum)
-		features[0].available |= NETIF_F_ALL_CSUM;
-	if (dev->ethtool_ops->set_tso)
-		features[0].available |= NETIF_F_ALL_TSO;
-	if (dev->ethtool_ops->set_rx_csum)
-		features[0].available |= NETIF_F_RXCSUM;
-	if (dev->ethtool_ops->set_flags)
-		features[0].available |= flags_dup_features;
-}
-
-static int ethtool_set_feature_compat(struct net_device *dev,
-	int (*legacy_set)(struct net_device *, u32),
-	struct ethtool_set_features_block *features, u32 mask)
-{
-	u32 do_set;
-
-	if (!legacy_set)
-		return 0;
-
-	if (!(features[0].valid & mask))
-		return 0;
-
-	features[0].valid &= ~mask;
-
-	do_set = !!(features[0].requested & mask);
-
-	if (legacy_set(dev, do_set) < 0)
-		netdev_info(dev,
-			"Legacy feature change (%s) failed for 0x%08x\n",
-			do_set ? "set" : "clear", mask);
-
-	return 1;
-}
-
-static int ethtool_set_flags_compat(struct net_device *dev,
-	int (*legacy_set)(struct net_device *, u32),
-	struct ethtool_set_features_block *features, u32 mask)
-{
-	u32 value;
-
-	if (!legacy_set)
-		return 0;
-
-	if (!(features[0].valid & mask))
-		return 0;
-
-	value = dev->features & ~features[0].valid;
-	value |= features[0].requested;
-
-	features[0].valid &= ~mask;
-
-	if (legacy_set(dev, value & mask) < 0)
-		netdev_info(dev, "Legacy flags change failed\n");
-
-	return 1;
-}
-
-static int ethtool_set_features_compat(struct net_device *dev,
-	struct ethtool_set_features_block *features)
-{
-	int compat;
-
-	if (!dev->ethtool_ops)
-		return 0;
-
-	compat  = ethtool_set_feature_compat(dev, dev->ethtool_ops->set_sg,
-		features, NETIF_F_SG);
-	compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_tx_csum,
-		features, NETIF_F_ALL_CSUM);
-	compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_tso,
-		features, NETIF_F_ALL_TSO);
-	compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_rx_csum,
-		features, NETIF_F_RXCSUM);
-	compat |= ethtool_set_flags_compat(dev, dev->ethtool_ops->set_flags,
-		features, flags_dup_features);
-
-	return compat;
-}
+#define ETHTOOL_DEV_FEATURE_WORDS	((NETDEV_FEATURE_COUNT + 31) / 32)
+
+static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = {
+	[NETIF_F_SG_BIT] =               "tx-scatter-gather",
+	[NETIF_F_IP_CSUM_BIT] =          "tx-checksum-ipv4",
+	[NETIF_F_HW_CSUM_BIT] =          "tx-checksum-ip-generic",
+	[NETIF_F_IPV6_CSUM_BIT] =        "tx-checksum-ipv6",
+	[NETIF_F_HIGHDMA_BIT] =          "highdma",
+	[NETIF_F_FRAGLIST_BIT] =         "tx-scatter-gather-fraglist",
+	[NETIF_F_HW_VLAN_TX_BIT] =       "tx-vlan-hw-insert",
+
+	[NETIF_F_HW_VLAN_RX_BIT] =       "rx-vlan-hw-parse",
+	[NETIF_F_HW_VLAN_FILTER_BIT] =   "rx-vlan-filter",
+	[NETIF_F_VLAN_CHALLENGED_BIT] =  "vlan-challenged",
+	[NETIF_F_GSO_BIT] =              "tx-generic-segmentation",
+	[NETIF_F_LLTX_BIT] =             "tx-lockless",
+	[NETIF_F_NETNS_LOCAL_BIT] =      "netns-local",
+	[NETIF_F_GRO_BIT] =              "rx-gro",
+	[NETIF_F_LRO_BIT] =              "rx-lro",
+
+	[NETIF_F_TSO_BIT] =              "tx-tcp-segmentation",
+	[NETIF_F_UFO_BIT] =              "tx-udp-fragmentation",
+	[NETIF_F_GSO_ROBUST_BIT] =       "tx-gso-robust",
+	[NETIF_F_TSO_ECN_BIT] =          "tx-tcp-ecn-segmentation",
+	[NETIF_F_TSO6_BIT] =             "tx-tcp6-segmentation",
+	[NETIF_F_FSO_BIT] =              "tx-fcoe-segmentation",
+
+	[NETIF_F_FCOE_CRC_BIT] =         "tx-checksum-fcoe-crc",
+	[NETIF_F_SCTP_CSUM_BIT] =        "tx-checksum-sctp",
+	[NETIF_F_FCOE_MTU_BIT] =         "fcoe-mtu",
+	[NETIF_F_NTUPLE_BIT] =           "rx-ntuple-filter",
+	[NETIF_F_RXHASH_BIT] =           "rx-hashing",
+	[NETIF_F_RXCSUM_BIT] =           "rx-checksum",
+	[NETIF_F_NOCACHE_COPY_BIT] =     "tx-nocache-copy",
+	[NETIF_F_LOOPBACK_BIT] =         "loopback",
+};
 
 static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
 {
@@ -272,18 +81,21 @@ static int ethtool_get_features(struct net_device *dev, void __user *useraddr)
 		.cmd = ETHTOOL_GFEATURES,
 		.size = ETHTOOL_DEV_FEATURE_WORDS,
 	};
-	struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS] = {
-		{
-			.available = dev->hw_features,
-			.requested = dev->wanted_features,
-			.active = dev->features,
-			.never_changed = NETIF_F_NEVER_CHANGE,
-		},
-	};
+	struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS];
 	u32 __user *sizeaddr;
 	u32 copy_size;
+	int i;
 
-	ethtool_get_features_compat(dev, features);
+	/* in case feature bits run out again */
+	BUILD_BUG_ON(ETHTOOL_DEV_FEATURE_WORDS * sizeof(u32) > sizeof(netdev_features_t));
+
+	for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) {
+		features[i].available = (u32)(dev->hw_features >> (32 * i));
+		features[i].requested = (u32)(dev->wanted_features >> (32 * i));
+		features[i].active = (u32)(dev->features >> (32 * i));
+		features[i].never_changed =
+			(u32)(NETIF_F_NEVER_CHANGE >> (32 * i));
+	}
 
 	sizeaddr = useraddr + offsetof(struct ethtool_gfeatures, size);
 	if (get_user(copy_size, sizeaddr))
@@ -305,7 +117,8 @@ static int ethtool_set_features(struct net_device *dev, void __user *useraddr)
 {
 	struct ethtool_sfeatures cmd;
 	struct ethtool_set_features_block features[ETHTOOL_DEV_FEATURE_WORDS];
-	int ret = 0;
+	netdev_features_t wanted = 0, valid = 0;
+	int i, ret = 0;
 
 	if (copy_from_user(&cmd, useraddr, sizeof(cmd)))
 		return -EFAULT;
@@ -317,65 +130,29 @@ static int ethtool_set_features(struct net_device *dev, void __user *useraddr)
 	if (copy_from_user(features, useraddr, sizeof(features)))
 		return -EFAULT;
 
-	if (features[0].valid & ~NETIF_F_ETHTOOL_BITS)
-		return -EINVAL;
+	for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) {
+		valid |= (netdev_features_t)features[i].valid << (32 * i);
+		wanted |= (netdev_features_t)features[i].requested << (32 * i);
+	}
 
-	if (ethtool_set_features_compat(dev, features))
-		ret |= ETHTOOL_F_COMPAT;
+	if (valid & ~NETIF_F_ETHTOOL_BITS)
+		return -EINVAL;
 
-	if (features[0].valid & ~dev->hw_features) {
-		features[0].valid &= dev->hw_features;
+	if (valid & ~dev->hw_features) {
+		valid &= dev->hw_features;
 		ret |= ETHTOOL_F_UNSUPPORTED;
 	}
 
-	dev->wanted_features &= ~features[0].valid;
-	dev->wanted_features |= features[0].valid & features[0].requested;
+	dev->wanted_features &= ~valid;
+	dev->wanted_features |= wanted & valid;
 	__netdev_update_features(dev);
 
-	if ((dev->wanted_features ^ dev->features) & features[0].valid)
+	if ((dev->wanted_features ^ dev->features) & valid)
 		ret |= ETHTOOL_F_WISH;
 
 	return ret;
 }
 
-static const char netdev_features_strings[ETHTOOL_DEV_FEATURE_WORDS * 32][ETH_GSTRING_LEN] = {
-	/* NETIF_F_SG */              "tx-scatter-gather",
-	/* NETIF_F_IP_CSUM */         "tx-checksum-ipv4",
-	/* NETIF_F_NO_CSUM */         "tx-checksum-unneeded",
-	/* NETIF_F_HW_CSUM */         "tx-checksum-ip-generic",
-	/* NETIF_F_IPV6_CSUM */       "tx-checksum-ipv6",
-	/* NETIF_F_HIGHDMA */         "highdma",
-	/* NETIF_F_FRAGLIST */        "tx-scatter-gather-fraglist",
-	/* NETIF_F_HW_VLAN_TX */      "tx-vlan-hw-insert",
-
-	/* NETIF_F_HW_VLAN_RX */      "rx-vlan-hw-parse",
-	/* NETIF_F_HW_VLAN_FILTER */  "rx-vlan-filter",
-	/* NETIF_F_VLAN_CHALLENGED */ "vlan-challenged",
-	/* NETIF_F_GSO */             "tx-generic-segmentation",
-	/* NETIF_F_LLTX */            "tx-lockless",
-	/* NETIF_F_NETNS_LOCAL */     "netns-local",
-	/* NETIF_F_GRO */             "rx-gro",
-	/* NETIF_F_LRO */             "rx-lro",
-
-	/* NETIF_F_TSO */             "tx-tcp-segmentation",
-	/* NETIF_F_UFO */             "tx-udp-fragmentation",
-	/* NETIF_F_GSO_ROBUST */      "tx-gso-robust",
-	/* NETIF_F_TSO_ECN */         "tx-tcp-ecn-segmentation",
-	/* NETIF_F_TSO6 */            "tx-tcp6-segmentation",
-	/* NETIF_F_FSO */             "tx-fcoe-segmentation",
-	"",
-	"",
-
-	/* NETIF_F_FCOE_CRC */        "tx-checksum-fcoe-crc",
-	/* NETIF_F_SCTP_CSUM */       "tx-checksum-sctp",
-	/* NETIF_F_FCOE_MTU */        "fcoe-mtu",
-	/* NETIF_F_NTUPLE */          "rx-ntuple-filter",
-	/* NETIF_F_RXHASH */          "rx-hashing",
-	/* NETIF_F_RXCSUM */          "rx-checksum",
-	/* NETIF_F_NOCACHE_COPY */    "tx-nocache-copy",
-	/* NETIF_F_LOOPBACK */        "loopback",
-};
-
 static int __ethtool_get_sset_count(struct net_device *dev, int sset)
 {
 	const struct ethtool_ops *ops = dev->ethtool_ops;
@@ -402,7 +179,7 @@ static void __ethtool_get_strings(struct net_device *dev,
 		ops->get_strings(dev, stringset, data);
 }
 
-static u32 ethtool_get_feature_mask(u32 eth_cmd)
+static netdev_features_t ethtool_get_feature_mask(u32 eth_cmd)
 {
 	/* feature masks of legacy discrete ethtool ops */
 
@@ -433,136 +210,82 @@ static u32 ethtool_get_feature_mask(u32 eth_cmd)
 	}
 }
 
-static void *__ethtool_get_one_feature_actor(struct net_device *dev, u32 ethcmd)
-{
-	const struct ethtool_ops *ops = dev->ethtool_ops;
-
-	if (!ops)
-		return NULL;
-
-	switch (ethcmd) {
-	case ETHTOOL_GTXCSUM:
-		return ops->get_tx_csum;
-	case ETHTOOL_GRXCSUM:
-		return ops->get_rx_csum;
-	case ETHTOOL_SSG:
-		return ops->get_sg;
-	case ETHTOOL_STSO:
-		return ops->get_tso;
-	case ETHTOOL_SUFO:
-		return ops->get_ufo;
-	default:
-		return NULL;
-	}
-}
-
-static u32 __ethtool_get_rx_csum_oldbug(struct net_device *dev)
-{
-	return !!(dev->features & NETIF_F_ALL_CSUM);
-}
-
 static int ethtool_get_one_feature(struct net_device *dev,
 	char __user *useraddr, u32 ethcmd)
 {
-	u32 mask = ethtool_get_feature_mask(ethcmd);
+	netdev_features_t mask = ethtool_get_feature_mask(ethcmd);
 	struct ethtool_value edata = {
 		.cmd = ethcmd,
 		.data = !!(dev->features & mask),
 	};
 
-	/* compatibility with discrete get_ ops */
-	if (!(dev->hw_features & mask)) {
-		u32 (*actor)(struct net_device *);
-
-		actor = __ethtool_get_one_feature_actor(dev, ethcmd);
-
-		/* bug compatibility with old get_rx_csum */
-		if (ethcmd == ETHTOOL_GRXCSUM && !actor)
-			actor = __ethtool_get_rx_csum_oldbug;
-
-		if (actor)
-			edata.data = actor(dev);
-	}
-
 	if (copy_to_user(useraddr, &edata, sizeof(edata)))
 		return -EFAULT;
 	return 0;
 }
 
-static int __ethtool_set_tx_csum(struct net_device *dev, u32 data);
-static int __ethtool_set_rx_csum(struct net_device *dev, u32 data);
-static int __ethtool_set_sg(struct net_device *dev, u32 data);
-static int __ethtool_set_tso(struct net_device *dev, u32 data);
-static int __ethtool_set_ufo(struct net_device *dev, u32 data);
-
 static int ethtool_set_one_feature(struct net_device *dev,
 	void __user *useraddr, u32 ethcmd)
 {
 	struct ethtool_value edata;
-	u32 mask;
+	netdev_features_t mask;
 
 	if (copy_from_user(&edata, useraddr, sizeof(edata)))
 		return -EFAULT;
 
 	mask = ethtool_get_feature_mask(ethcmd);
 	mask &= dev->hw_features;
-	if (mask) {
-		if (edata.data)
-			dev->wanted_features |= mask;
-		else
-			dev->wanted_features &= ~mask;
+	if (!mask)
+		return -EOPNOTSUPP;
 
-		__netdev_update_features(dev);
-		return 0;
-	}
+	if (edata.data)
+		dev->wanted_features |= mask;
+	else
+		dev->wanted_features &= ~mask;
 
-	/* Driver is not converted to ndo_fix_features or does not
-	 * support changing this offload. In the latter case it won't
-	 * have corresponding ethtool_ops field set.
-	 *
-	 * Following part is to be removed after all drivers advertise
-	 * their changeable features in netdev->hw_features and stop
-	 * using discrete offload setting ops.
-	 */
+	__netdev_update_features(dev);
 
-	switch (ethcmd) {
-	case ETHTOOL_STXCSUM:
-		return __ethtool_set_tx_csum(dev, edata.data);
-	case ETHTOOL_SRXCSUM:
-		return __ethtool_set_rx_csum(dev, edata.data);
-	case ETHTOOL_SSG:
-		return __ethtool_set_sg(dev, edata.data);
-	case ETHTOOL_STSO:
-		return __ethtool_set_tso(dev, edata.data);
-	case ETHTOOL_SUFO:
-		return __ethtool_set_ufo(dev, edata.data);
-	default:
-		return -EOPNOTSUPP;
-	}
+	return 0;
 }
 
-int __ethtool_set_flags(struct net_device *dev, u32 data)
+#define ETH_ALL_FLAGS    (ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | \
+			  ETH_FLAG_NTUPLE | ETH_FLAG_RXHASH)
+#define ETH_ALL_FEATURES (NETIF_F_LRO | NETIF_F_HW_VLAN_RX | \
+			  NETIF_F_HW_VLAN_TX | NETIF_F_NTUPLE | NETIF_F_RXHASH)
+
+static u32 __ethtool_get_flags(struct net_device *dev)
 {
-	u32 changed;
+	u32 flags = 0;
+
+	if (dev->features & NETIF_F_LRO)	flags |= ETH_FLAG_LRO;
+	if (dev->features & NETIF_F_HW_VLAN_RX)	flags |= ETH_FLAG_RXVLAN;
+	if (dev->features & NETIF_F_HW_VLAN_TX)	flags |= ETH_FLAG_TXVLAN;
+	if (dev->features & NETIF_F_NTUPLE)	flags |= ETH_FLAG_NTUPLE;
+	if (dev->features & NETIF_F_RXHASH)	flags |= ETH_FLAG_RXHASH;
+
+	return flags;
+}
 
-	if (data & ~flags_dup_features)
+static int __ethtool_set_flags(struct net_device *dev, u32 data)
+{
+	netdev_features_t features = 0, changed;
+
+	if (data & ~ETH_ALL_FLAGS)
 		return -EINVAL;
 
-	/* legacy set_flags() op */
-	if (dev->ethtool_ops->set_flags) {
-		if (unlikely(dev->hw_features & flags_dup_features))
-			netdev_warn(dev,
-				"driver BUG: mixed hw_features and set_flags()\n");
-		return dev->ethtool_ops->set_flags(dev, data);
-	}
+	if (data & ETH_FLAG_LRO)	features |= NETIF_F_LRO;
+	if (data & ETH_FLAG_RXVLAN)	features |= NETIF_F_HW_VLAN_RX;
+	if (data & ETH_FLAG_TXVLAN)	features |= NETIF_F_HW_VLAN_TX;
+	if (data & ETH_FLAG_NTUPLE)	features |= NETIF_F_NTUPLE;
+	if (data & ETH_FLAG_RXHASH)	features |= NETIF_F_RXHASH;
 
 	/* allow changing only bits set in hw_features */
-	changed = (data ^ dev->features) & flags_dup_features;
+	changed = (features ^ dev->features) & ETH_ALL_FEATURES;
 	if (changed & ~dev->hw_features)
 		return (changed & dev->hw_features) ? -EINVAL : -EOPNOTSUPP;
 
 	dev->wanted_features =
-		(dev->wanted_features & ~changed) | (data & dev->hw_features);
+		(dev->wanted_features & ~changed) | (features & changed);
 
 	__netdev_update_features(dev);
 
@@ -792,34 +515,44 @@ err_out:
 static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev,
 						     void __user *useraddr)
 {
-	struct ethtool_rxfh_indir *indir;
-	u32 table_size;
-	size_t full_size;
+	u32 user_size, dev_size;
+	u32 *indir;
 	int ret;
 
-	if (!dev->ethtool_ops->get_rxfh_indir)
+	if (!dev->ethtool_ops->get_rxfh_indir_size ||
+	    !dev->ethtool_ops->get_rxfh_indir)
+		return -EOPNOTSUPP;
+	dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev);
+	if (dev_size == 0)
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(&table_size,
+	if (copy_from_user(&user_size,
 			   useraddr + offsetof(struct ethtool_rxfh_indir, size),
-			   sizeof(table_size)))
+			   sizeof(user_size)))
 		return -EFAULT;
 
-	if (table_size >
-	    (KMALLOC_MAX_SIZE - sizeof(*indir)) / sizeof(*indir->ring_index))
-		return -ENOMEM;
-	full_size = sizeof(*indir) + sizeof(*indir->ring_index) * table_size;
-	indir = kzalloc(full_size, GFP_USER);
+	if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh_indir, size),
+			 &dev_size, sizeof(dev_size)))
+		return -EFAULT;
+
+	/* If the user buffer size is 0, this is just a query for the
+	 * device table size.  Otherwise, if it's smaller than the
+	 * device table size it's an error.
+	 */
+	if (user_size < dev_size)
+		return user_size == 0 ? 0 : -EINVAL;
+
+	indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER);
 	if (!indir)
 		return -ENOMEM;
 
-	indir->cmd = ETHTOOL_GRXFHINDIR;
-	indir->size = table_size;
 	ret = dev->ethtool_ops->get_rxfh_indir(dev, indir);
 	if (ret)
 		goto out;
 
-	if (copy_to_user(useraddr, indir, full_size))
+	if (copy_to_user(useraddr +
+			 offsetof(struct ethtool_rxfh_indir, ring_index[0]),
+			 indir, dev_size * sizeof(indir[0])))
 		ret = -EFAULT;
 
 out:
@@ -830,30 +563,56 @@ out:
 static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev,
 						     void __user *useraddr)
 {
-	struct ethtool_rxfh_indir *indir;
-	u32 table_size;
-	size_t full_size;
+	struct ethtool_rxnfc rx_rings;
+	u32 user_size, dev_size, i;
+	u32 *indir;
 	int ret;
 
-	if (!dev->ethtool_ops->set_rxfh_indir)
+	if (!dev->ethtool_ops->get_rxfh_indir_size ||
+	    !dev->ethtool_ops->set_rxfh_indir ||
+	    !dev->ethtool_ops->get_rxnfc)
+		return -EOPNOTSUPP;
+	dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev);
+	if (dev_size == 0)
 		return -EOPNOTSUPP;
 
-	if (copy_from_user(&table_size,
+	if (copy_from_user(&user_size,
 			   useraddr + offsetof(struct ethtool_rxfh_indir, size),
-			   sizeof(table_size)))
+			   sizeof(user_size)))
 		return -EFAULT;
 
-	if (table_size >
-	    (KMALLOC_MAX_SIZE - sizeof(*indir)) / sizeof(*indir->ring_index))
-		return -ENOMEM;
-	full_size = sizeof(*indir) + sizeof(*indir->ring_index) * table_size;
-	indir = kmalloc(full_size, GFP_USER);
+	if (user_size != 0 && user_size != dev_size)
+		return -EINVAL;
+
+	indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER);
 	if (!indir)
 		return -ENOMEM;
 
-	if (copy_from_user(indir, useraddr, full_size)) {
-		ret = -EFAULT;
+	rx_rings.cmd = ETHTOOL_GRXRINGS;
+	ret = dev->ethtool_ops->get_rxnfc(dev, &rx_rings, NULL);
+	if (ret)
 		goto out;
+
+	if (user_size == 0) {
+		for (i = 0; i < dev_size; i++)
+			indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data);
+	} else {
+		if (copy_from_user(indir,
+				  useraddr +
+				  offsetof(struct ethtool_rxfh_indir,
+					   ring_index[0]),
+				  dev_size * sizeof(indir[0]))) {
+			ret = -EFAULT;
+			goto out;
+		}
+
+		/* Validate ring indices */
+		for (i = 0; i < dev_size; i++) {
+			if (indir[i] >= rx_rings.data) {
+				ret = -EINVAL;
+				goto out;
+			}
+		}
 	}
 
 	ret = dev->ethtool_ops->set_rxfh_indir(dev, indir);
@@ -1231,81 +990,6 @@ static int ethtool_set_pauseparam(struct net_device *dev, void __user *useraddr)
 	return dev->ethtool_ops->set_pauseparam(dev, &pauseparam);
 }
 
-static int __ethtool_set_sg(struct net_device *dev, u32 data)
-{
-	int err;
-
-	if (!dev->ethtool_ops->set_sg)
-		return -EOPNOTSUPP;
-
-	if (data && !(dev->features & NETIF_F_ALL_CSUM))
-		return -EINVAL;
-
-	if (!data && dev->ethtool_ops->set_tso) {
-		err = dev->ethtool_ops->set_tso(dev, 0);
-		if (err)
-			return err;
-	}
-
-	if (!data && dev->ethtool_ops->set_ufo) {
-		err = dev->ethtool_ops->set_ufo(dev, 0);
-		if (err)
-			return err;
-	}
-	return dev->ethtool_ops->set_sg(dev, data);
-}
-
-static int __ethtool_set_tx_csum(struct net_device *dev, u32 data)
-{
-	int err;
-
-	if (!dev->ethtool_ops->set_tx_csum)
-		return -EOPNOTSUPP;
-
-	if (!data && dev->ethtool_ops->set_sg) {
-		err = __ethtool_set_sg(dev, 0);
-		if (err)
-			return err;
-	}
-
-	return dev->ethtool_ops->set_tx_csum(dev, data);
-}
-
-static int __ethtool_set_rx_csum(struct net_device *dev, u32 data)
-{
-	if (!dev->ethtool_ops->set_rx_csum)
-		return -EOPNOTSUPP;
-
-	if (!data)
-		dev->features &= ~NETIF_F_GRO;
-
-	return dev->ethtool_ops->set_rx_csum(dev, data);
-}
-
-static int __ethtool_set_tso(struct net_device *dev, u32 data)
-{
-	if (!dev->ethtool_ops->set_tso)
-		return -EOPNOTSUPP;
-
-	if (data && !(dev->features & NETIF_F_SG))
-		return -EINVAL;
-
-	return dev->ethtool_ops->set_tso(dev, data);
-}
-
-static int __ethtool_set_ufo(struct net_device *dev, u32 data)
-{
-	if (!dev->ethtool_ops->set_ufo)
-		return -EOPNOTSUPP;
-	if (data && !(dev->features & NETIF_F_SG))
-		return -EINVAL;
-	if (data && !((dev->features & NETIF_F_GEN_CSUM) ||
-		(dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))
-			== (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)))
-		return -EINVAL;
-	return dev->ethtool_ops->set_ufo(dev, data);
-}
-
 static int ethtool_self_test(struct net_device *dev, char __user *useraddr)
 {
 	struct ethtool_test test;
@@ -1771,9 +1455,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr)
 		break;
 	case ETHTOOL_GFLAGS:
 		rc = ethtool_get_value(dev, useraddr, ethcmd,
-				       (dev->ethtool_ops->get_flags ?
-					dev->ethtool_ops->get_flags :
-					ethtool_op_get_flags));
+					__ethtool_get_flags);
 		break;
 	case ETHTOOL_SFLAGS:
 		rc = ethtool_set_value(dev, useraddr, __ethtool_set_flags);
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
new file mode 100644
index 0000000..0985b9b
--- /dev/null
+++ b/net/core/flow_dissector.c
@@ -0,0 +1,143 @@
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/if_vlan.h>
+#include <net/ip.h>
+#include <linux/if_tunnel.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_defs.h>
+#include <net/flow_keys.h>
+
+/* copy saddr & daddr, possibly using 64bit load/store
+ * Equivalent to :	flow->src = iph->saddr;
+ *			flow->dst = iph->daddr;
+ */
+static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *iph)
+{
+	BUILD_BUG_ON(offsetof(typeof(*flow), dst) !=
+		     offsetof(typeof(*flow), src) + sizeof(flow->src));
+	memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst));
+}
+
+bool skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow)
+{
+	int poff, nhoff = skb_network_offset(skb);
+	u8 ip_proto;
+	__be16 proto = skb->protocol;
+
+	memset(flow, 0, sizeof(*flow));
+
+again:
+	switch (proto) {
+	case __constant_htons(ETH_P_IP): {
+		const struct iphdr *iph;
+		struct iphdr _iph;
+ip:
+		iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
+		if (!iph)
+			return false;
+
+		if (ip_is_fragment(iph))
+			ip_proto = 0;
+		else
+			ip_proto = iph->protocol;
+		iph_to_flow_copy_addrs(flow, iph);
+		nhoff += iph->ihl * 4;
+		break;
+	}
+	case __constant_htons(ETH_P_IPV6): {
+		const struct ipv6hdr *iph;
+		struct ipv6hdr _iph;
+ipv6:
+		iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
+		if (!iph)
+			return false;
+
+		ip_proto = iph->nexthdr;
+		flow->src = iph->saddr.s6_addr32[3];
+		flow->dst = iph->daddr.s6_addr32[3];
+		nhoff += sizeof(struct ipv6hdr);
+		break;
+	}
+	case __constant_htons(ETH_P_8021Q): {
+		const struct vlan_hdr *vlan;
+		struct vlan_hdr _vlan;
+
+		vlan = skb_header_pointer(skb, nhoff, sizeof(_vlan), &_vlan);
+		if (!vlan)
+			return false;
+
+		proto = vlan->h_vlan_encapsulated_proto;
+		nhoff += sizeof(*vlan);
+		goto again;
+	}
+	case __constant_htons(ETH_P_PPP_SES): {
+		struct {
+			struct pppoe_hdr hdr;
+			__be16 proto;
+		} *hdr, _hdr;
+		hdr = skb_header_pointer(skb, nhoff, sizeof(_hdr), &_hdr);
+		if (!hdr)
+			return false;
+		proto = hdr->proto;
+		nhoff += PPPOE_SES_HLEN;
+		switch (proto) {
+		case __constant_htons(PPP_IP):
+			goto ip;
+		case __constant_htons(PPP_IPV6):
+			goto ipv6;
+		default:
+			return false;
+		}
+	}
+	default:
+		return false;
+	}
+
+	switch (ip_proto) {
+	case IPPROTO_GRE: {
+		struct gre_hdr {
+			__be16 flags;
+			__be16 proto;
+		} *hdr, _hdr;
+
+		hdr = skb_header_pointer(skb, nhoff, sizeof(_hdr), &_hdr);
+		if (!hdr)
+			return false;
+		/*
+		 * Only look inside GRE if version zero and no
+		 * routing
+		 */
+		if (!(hdr->flags & (GRE_VERSION|GRE_ROUTING))) {
+			proto = hdr->proto;
+			nhoff += 4;
+			if (hdr->flags & GRE_CSUM)
+				nhoff += 4;
+			if (hdr->flags & GRE_KEY)
+				nhoff += 4;
+			if (hdr->flags & GRE_SEQ)
+				nhoff += 4;
+			goto again;
+		}
+		break;
+	}
+	case IPPROTO_IPIP:
+		goto again;
+	default:
+		break;
+	}
+
+	flow->ip_proto = ip_proto;
+	poff = proto_ports_offset(ip_proto);
+	if (poff >= 0) {
+		__be32 *ports, _ports;
+
+		nhoff += poff;
+		ports = skb_header_pointer(skb, nhoff, sizeof(_ports), &_ports);
+		if (ports)
+			flow->ports = *ports;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL(skb_flow_dissect);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 039d51e..d57a40a 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -238,6 +238,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev)
 				   it to safe state.
 				 */
 				skb_queue_purge(&n->arp_queue);
+				n->arp_queue_len_bytes = 0;
 				n->output = neigh_blackhole;
 				if (n->nud_state & NUD_VALID)
 					n->nud_state = NUD_NOARP;
@@ -272,7 +273,7 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
 }
 EXPORT_SYMBOL(neigh_ifdown);
 
-static struct neighbour *neigh_alloc(struct neigh_table *tbl)
+static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device *dev)
 {
 	struct neighbour *n = NULL;
 	unsigned long now = jiffies;
@@ -287,7 +288,15 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl)
 			goto out_entries;
 	}
 
-	n = kmem_cache_zalloc(tbl->kmem_cachep, GFP_ATOMIC);
+	if (tbl->entry_size)
+		n = kzalloc(tbl->entry_size, GFP_ATOMIC);
+	else {
+		int sz = sizeof(*n) + tbl->key_len;
+
+		sz = ALIGN(sz, NEIGH_PRIV_ALIGN);
+		sz += dev->neigh_priv_len;
+		n = kzalloc(sz, GFP_ATOMIC);
+	}
 	if (!n)
 		goto out_entries;
 
@@ -462,7 +471,7 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey,
 	u32 hash_val;
 	int key_len = tbl->key_len;
 	int error;
-	struct neighbour *n1, *rc, *n = neigh_alloc(tbl);
+	struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev);
 	struct neigh_hash_table *nht;
 
 	if (!n) {
@@ -480,11 +489,12 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey,
 		goto out_neigh_release;
 	}
 
-	/* Device specific setup. */
-	if (n->parms->neigh_setup &&
-	    (error = n->parms->neigh_setup(n)) < 0) {
-		rc = ERR_PTR(error);
-		goto out_neigh_release;
+	if (dev->netdev_ops->ndo_neigh_construct) {
+		error = dev->netdev_ops->ndo_neigh_construct(n);
+		if (error < 0) {
+			rc = ERR_PTR(error);
+			goto out_neigh_release;
+		}
 	}
 
 	n->confirmed = jiffies - (n->parms->base_reachable_time << 1);
@@ -677,18 +687,14 @@ static inline void neigh_parms_put(struct neigh_parms *parms)
 		neigh_parms_destroy(parms);
 }
 
-static void neigh_destroy_rcu(struct rcu_head *head)
-{
-	struct neighbour *neigh = container_of(head, struct neighbour, rcu);
-
-	kmem_cache_free(neigh->tbl->kmem_cachep, neigh);
-}
 /*
  *	neighbour must already be out of the table;
  *
  */
 void neigh_destroy(struct neighbour *neigh)
 {
+	struct net_device *dev = neigh->dev;
+
 	NEIGH_CACHE_STAT_INC(neigh->tbl, destroys);
 
 	if (!neigh->dead) {
@@ -702,14 +708,15 @@ void neigh_destroy(struct neighbour *neigh)
 		printk(KERN_WARNING "Impossible event.\n");
 
 	skb_queue_purge(&neigh->arp_queue);
+	neigh->arp_queue_len_bytes = 0;
 
-	dev_put(neigh->dev);
+	dev_put(dev);
 	neigh_parms_put(neigh->parms);
 
 	NEIGH_PRINTK2("neigh %p is destroyed.\n", neigh);
 
 	atomic_dec(&neigh->tbl->entries);
-	call_rcu(&neigh->rcu, neigh_destroy_rcu);
+	kfree_rcu(neigh, rcu);
 }
 EXPORT_SYMBOL(neigh_destroy);
 
@@ -842,6 +849,7 @@ static void neigh_invalidate(struct neighbour *neigh)
 		write_lock(&neigh->lock);
 	}
 	skb_queue_purge(&neigh->arp_queue);
+	neigh->arp_queue_len_bytes = 0;
 }
 
 static void neigh_probe(struct neighbour *neigh)
@@ -980,15 +988,20 @@ int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb)
 
 	if (neigh->nud_state == NUD_INCOMPLETE) {
 		if (skb) {
-			if (skb_queue_len(&neigh->arp_queue) >=
-			    neigh->parms->queue_len) {
+			while (neigh->arp_queue_len_bytes + skb->truesize >
+			       neigh->parms->queue_len_bytes) {
 				struct sk_buff *buff;
+
 				buff = __skb_dequeue(&neigh->arp_queue);
+				if (!buff)
+					break;
+				neigh->arp_queue_len_bytes -= buff->truesize;
 				kfree_skb(buff);
 				NEIGH_CACHE_STAT_INC(neigh->tbl, unres_discards);
 			}
 			skb_dst_force(skb);
 			__skb_queue_tail(&neigh->arp_queue, skb);
+			neigh->arp_queue_len_bytes += skb->truesize;
 		}
 		rc = 1;
 	}
@@ -1167,7 +1180,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 
 			rcu_read_lock();
 			/* On shaper/eql skb->dst->neighbour != neigh :( */
-			if (dst && (n2 = dst_get_neighbour(dst)) != NULL)
+			if (dst && (n2 = dst_get_neighbour_noref(dst)) != NULL)
 				n1 = n2;
 			n1->output(n1, skb);
 			rcu_read_unlock();
@@ -1175,6 +1188,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 			write_lock_bh(&neigh->lock);
 		}
 		skb_queue_purge(&neigh->arp_queue);
+		neigh->arp_queue_len_bytes = 0;
 	}
 out:
 	if (update_isrouter) {
@@ -1477,11 +1491,6 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl)
 	tbl->parms.reachable_time =
 			  neigh_rand_reach_time(tbl->parms.base_reachable_time);
 
-	if (!tbl->kmem_cachep)
-		tbl->kmem_cachep =
-			kmem_cache_create(tbl->id, tbl->entry_size, 0,
-					  SLAB_HWCACHE_ALIGN|SLAB_PANIC,
-					  NULL);
 	tbl->stats = alloc_percpu(struct neigh_statistics);
 	if (!tbl->stats)
 		panic("cannot create neighbour cache statistics");
@@ -1566,9 +1575,6 @@ int neigh_table_clear(struct neigh_table *tbl)
 	free_percpu(tbl->stats);
 	tbl->stats = NULL;
 
-	kmem_cache_destroy(tbl->kmem_cachep);
-	tbl->kmem_cachep = NULL;
-
 	return 0;
 }
 EXPORT_SYMBOL(neigh_table_clear);
@@ -1747,7 +1753,11 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms)
 		NLA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex);
 
 	NLA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt));
-	NLA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len);
+	NLA_PUT_U32(skb, NDTPA_QUEUE_LENBYTES, parms->queue_len_bytes);
+	/* approximative value for deprecated QUEUE_LEN (in packets) */
+	NLA_PUT_U32(skb, NDTPA_QUEUE_LEN,
+		    DIV_ROUND_UP(parms->queue_len_bytes,
+				 SKB_TRUESIZE(ETH_FRAME_LEN)));
 	NLA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen);
 	NLA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes);
 	NLA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes);
@@ -1974,7 +1984,11 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 
 			switch (i) {
 			case NDTPA_QUEUE_LEN:
-				p->queue_len = nla_get_u32(tbp[i]);
+				p->queue_len_bytes = nla_get_u32(tbp[i]) *
+						     SKB_TRUESIZE(ETH_FRAME_LEN);
+				break;
+			case NDTPA_QUEUE_LENBYTES:
+				p->queue_len_bytes = nla_get_u32(tbp[i]);
 				break;
 			case NDTPA_PROXY_QLEN:
 				p->proxy_qlen = nla_get_u32(tbp[i]);
@@ -2397,7 +2411,10 @@ static struct pneigh_entry *pneigh_get_next(struct seq_file *seq,
 	struct net *net = seq_file_net(seq);
 	struct neigh_table *tbl = state->tbl;
 
-	pn = pn->next;
+	do {
+		pn = pn->next;
+	} while (pn && !net_eq(pneigh_net(pn), net));
+
 	while (!pn) {
 		if (++state->bucket > PNEIGH_HASHMASK)
 			break;
@@ -2635,117 +2652,158 @@ EXPORT_SYMBOL(neigh_app_ns);
 
 #ifdef CONFIG_SYSCTL
 
-#define NEIGH_VARS_MAX 19
+static int proc_unres_qlen(ctl_table *ctl, int write, void __user *buffer,
+			   size_t *lenp, loff_t *ppos)
+{
+	int size, ret;
+	ctl_table tmp = *ctl;
+
+	tmp.data = &size;
+	size = DIV_ROUND_UP(*(int *)ctl->data, SKB_TRUESIZE(ETH_FRAME_LEN));
+	ret = proc_dointvec(&tmp, write, buffer, lenp, ppos);
+	if (write && !ret)
+		*(int *)ctl->data = size * SKB_TRUESIZE(ETH_FRAME_LEN);
+	return ret;
+}
+
+enum {
+	NEIGH_VAR_MCAST_PROBE,
+	NEIGH_VAR_UCAST_PROBE,
+	NEIGH_VAR_APP_PROBE,
+	NEIGH_VAR_RETRANS_TIME,
+	NEIGH_VAR_BASE_REACHABLE_TIME,
+	NEIGH_VAR_DELAY_PROBE_TIME,
+	NEIGH_VAR_GC_STALETIME,
+	NEIGH_VAR_QUEUE_LEN,
+	NEIGH_VAR_QUEUE_LEN_BYTES,
+	NEIGH_VAR_PROXY_QLEN,
+	NEIGH_VAR_ANYCAST_DELAY,
+	NEIGH_VAR_PROXY_DELAY,
+	NEIGH_VAR_LOCKTIME,
+	NEIGH_VAR_RETRANS_TIME_MS,
+	NEIGH_VAR_BASE_REACHABLE_TIME_MS,
+	NEIGH_VAR_GC_INTERVAL,
+	NEIGH_VAR_GC_THRESH1,
+	NEIGH_VAR_GC_THRESH2,
+	NEIGH_VAR_GC_THRESH3,
+	NEIGH_VAR_MAX
+};
 
 static struct neigh_sysctl_table {
 	struct ctl_table_header *sysctl_header;
-	struct ctl_table neigh_vars[NEIGH_VARS_MAX];
+	struct ctl_table neigh_vars[NEIGH_VAR_MAX + 1];
 	char *dev_name;
 } neigh_sysctl_template __read_mostly = {
 	.neigh_vars = {
-		{
+		[NEIGH_VAR_MCAST_PROBE] = {
 			.procname	= "mcast_solicit",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
-		{
+		[NEIGH_VAR_UCAST_PROBE] = {
 			.procname	= "ucast_solicit",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
-		{
+		[NEIGH_VAR_APP_PROBE] = {
 			.procname	= "app_solicit",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
-		{
+		[NEIGH_VAR_RETRANS_TIME] = {
 			.procname	= "retrans_time",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_userhz_jiffies,
 		},
-		{
+		[NEIGH_VAR_BASE_REACHABLE_TIME] = {
 			.procname	= "base_reachable_time",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_jiffies,
 		},
-		{
+		[NEIGH_VAR_DELAY_PROBE_TIME] = {
 			.procname	= "delay_first_probe_time",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_jiffies,
 		},
-		{
+		[NEIGH_VAR_GC_STALETIME] = {
 			.procname	= "gc_stale_time",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_jiffies,
 		},
-		{
+		[NEIGH_VAR_QUEUE_LEN] = {
 			.procname	= "unres_qlen",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
+			.proc_handler	= proc_unres_qlen,
+		},
+		[NEIGH_VAR_QUEUE_LEN_BYTES] = {
+			.procname	= "unres_qlen_bytes",
+			.maxlen		= sizeof(int),
+			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
-		{
+		[NEIGH_VAR_PROXY_QLEN] = {
 			.procname	= "proxy_qlen",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
-		{
+		[NEIGH_VAR_ANYCAST_DELAY] = {
 			.procname	= "anycast_delay",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_userhz_jiffies,
 		},
-		{
+		[NEIGH_VAR_PROXY_DELAY] = {
 			.procname	= "proxy_delay",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_userhz_jiffies,
 		},
-		{
+		[NEIGH_VAR_LOCKTIME] = {
 			.procname	= "locktime",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_userhz_jiffies,
 		},
-		{
+		[NEIGH_VAR_RETRANS_TIME_MS] = {
 			.procname	= "retrans_time_ms",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_ms_jiffies,
 		},
-		{
+		[NEIGH_VAR_BASE_REACHABLE_TIME_MS] = {
 			.procname	= "base_reachable_time_ms",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_ms_jiffies,
 		},
-		{
+		[NEIGH_VAR_GC_INTERVAL] = {
 			.procname	= "gc_interval",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec_jiffies,
 		},
-		{
+		[NEIGH_VAR_GC_THRESH1] = {
 			.procname	= "gc_thresh1",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
-		{
+		[NEIGH_VAR_GC_THRESH2] = {
 			.procname	= "gc_thresh2",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
 			.proc_handler	= proc_dointvec,
 		},
-		{
+		[NEIGH_VAR_GC_THRESH3] = {
 			.procname	= "gc_thresh3",
 			.maxlen		= sizeof(int),
 			.mode		= 0644,
@@ -2778,47 +2836,49 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p,
 	if (!t)
 		goto err;
 
-	t->neigh_vars[0].data  = &p->mcast_probes;
-	t->neigh_vars[1].data  = &p->ucast_probes;
-	t->neigh_vars[2].data  = &p->app_probes;
-	t->neigh_vars[3].data  = &p->retrans_time;
-	t->neigh_vars[4].data  = &p->base_reachable_time;
-	t->neigh_vars[5].data  = &p->delay_probe_time;
-	t->neigh_vars[6].data  = &p->gc_staletime;
-	t->neigh_vars[7].data  = &p->queue_len;
-	t->neigh_vars[8].data  = &p->proxy_qlen;
-	t->neigh_vars[9].data  = &p->anycast_delay;
-	t->neigh_vars[10].data = &p->proxy_delay;
-	t->neigh_vars[11].data = &p->locktime;
-	t->neigh_vars[12].data  = &p->retrans_time;
-	t->neigh_vars[13].data  = &p->base_reachable_time;
+	t->neigh_vars[NEIGH_VAR_MCAST_PROBE].data  = &p->mcast_probes;
+	t->neigh_vars[NEIGH_VAR_UCAST_PROBE].data  = &p->ucast_probes;
+	t->neigh_vars[NEIGH_VAR_APP_PROBE].data  = &p->app_probes;
+	t->neigh_vars[NEIGH_VAR_RETRANS_TIME].data  = &p->retrans_time;
+	t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].data  = &p->base_reachable_time;
+	t->neigh_vars[NEIGH_VAR_DELAY_PROBE_TIME].data  = &p->delay_probe_time;
+	t->neigh_vars[NEIGH_VAR_GC_STALETIME].data  = &p->gc_staletime;
+	t->neigh_vars[NEIGH_VAR_QUEUE_LEN].data  = &p->queue_len_bytes;
+	t->neigh_vars[NEIGH_VAR_QUEUE_LEN_BYTES].data  = &p->queue_len_bytes;
+	t->neigh_vars[NEIGH_VAR_PROXY_QLEN].data  = &p->proxy_qlen;
+	t->neigh_vars[NEIGH_VAR_ANYCAST_DELAY].data  = &p->anycast_delay;
+	t->neigh_vars[NEIGH_VAR_PROXY_DELAY].data = &p->proxy_delay;
+	t->neigh_vars[NEIGH_VAR_LOCKTIME].data = &p->locktime;
+	t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].data  = &p->retrans_time;
+	t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].data  = &p->base_reachable_time;
 
 	if (dev) {
 		dev_name_source = dev->name;
 		/* Terminate the table early */
-		memset(&t->neigh_vars[14], 0, sizeof(t->neigh_vars[14]));
+		memset(&t->neigh_vars[NEIGH_VAR_GC_INTERVAL], 0,
+		       sizeof(t->neigh_vars[NEIGH_VAR_GC_INTERVAL]));
 	} else {
 		dev_name_source = neigh_path[NEIGH_CTL_PATH_DEV].procname;
-		t->neigh_vars[14].data = (int *)(p + 1);
-		t->neigh_vars[15].data = (int *)(p + 1) + 1;
-		t->neigh_vars[16].data = (int *)(p + 1) + 2;
-		t->neigh_vars[17].data = (int *)(p + 1) + 3;
+		t->neigh_vars[NEIGH_VAR_GC_INTERVAL].data = (int *)(p + 1);
+		t->neigh_vars[NEIGH_VAR_GC_THRESH1].data = (int *)(p + 1) + 1;
+		t->neigh_vars[NEIGH_VAR_GC_THRESH2].data = (int *)(p + 1) + 2;
+		t->neigh_vars[NEIGH_VAR_GC_THRESH3].data = (int *)(p + 1) + 3;
 	}
 
 
 	if (handler) {
 		/* RetransTime */
-		t->neigh_vars[3].proc_handler = handler;
-		t->neigh_vars[3].extra1 = dev;
+		t->neigh_vars[NEIGH_VAR_RETRANS_TIME].proc_handler = handler;
+		t->neigh_vars[NEIGH_VAR_RETRANS_TIME].extra1 = dev;
 		/* ReachableTime */
-		t->neigh_vars[4].proc_handler = handler;
-		t->neigh_vars[4].extra1 = dev;
+		t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].proc_handler = handler;
+		t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME].extra1 = dev;
 		/* RetransTime (in milliseconds)*/
-		t->neigh_vars[12].proc_handler = handler;
-		t->neigh_vars[12].extra1 = dev;
+		t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].proc_handler = handler;
+		t->neigh_vars[NEIGH_VAR_RETRANS_TIME_MS].extra1 = dev;
 		/* ReachableTime (in milliseconds) */
-		t->neigh_vars[13].proc_handler = handler;
-		t->neigh_vars[13].extra1 = dev;
+		t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].proc_handler = handler;
+		t->neigh_vars[NEIGH_VAR_BASE_REACHABLE_TIME_MS].extra1 = dev;
 	}
 
 	t->dev_name = kstrdup(dev_name_source, GFP_KERNEL);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index c71c434..9d13463 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -21,6 +21,7 @@
 #include <linux/wireless.h>
 #include <linux/vmalloc.h>
 #include <linux/export.h>
+#include <linux/jiffies.h>
 #include <net/wext.h>
 
 #include "net-sysfs.h"
@@ -606,9 +607,12 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue,
 	rcu_assign_pointer(queue->rps_map, map);
 	spin_unlock(&rps_map_lock);
 
-	if (old_map)
+	if (map)
+		jump_label_inc(&rps_needed);
+	if (old_map) {
 		kfree_rcu(old_map, rcu);
-
+		jump_label_dec(&rps_needed);
+	}
 	free_cpumask_var(mask);
 	return len;
 }
@@ -780,7 +784,7 @@ net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num)
 #endif
 }
 
-#ifdef CONFIG_XPS
+#ifdef CONFIG_SYSFS
 /*
  * netdev_queue sysfs structures and functions.
  */
@@ -826,6 +830,133 @@ static const struct sysfs_ops netdev_queue_sysfs_ops = {
 	.store = netdev_queue_attr_store,
 };
 
+static ssize_t show_trans_timeout(struct netdev_queue *queue,
+				  struct netdev_queue_attribute *attribute,
+				  char *buf)
+{
+	unsigned long trans_timeout;
+
+	spin_lock_irq(&queue->_xmit_lock);
+	trans_timeout = queue->trans_timeout;
+	spin_unlock_irq(&queue->_xmit_lock);
+
+	return sprintf(buf, "%lu", trans_timeout);
+}
+
+static struct netdev_queue_attribute queue_trans_timeout =
+	__ATTR(tx_timeout, S_IRUGO, show_trans_timeout, NULL);
+
+#ifdef CONFIG_BQL
+/*
+ * Byte queue limits sysfs structures and functions.
+ */
+static ssize_t bql_show(char *buf, unsigned int value)
+{
+	return sprintf(buf, "%u\n", value);
+}
+
+static ssize_t bql_set(const char *buf, const size_t count,
+		       unsigned int *pvalue)
+{
+	unsigned int value;
+	int err;
+
+	if (!strcmp(buf, "max") || !strcmp(buf, "max\n"))
+		value = DQL_MAX_LIMIT;
+	else {
+		err = kstrtouint(buf, 10, &value);
+		if (err < 0)
+			return err;
+		if (value > DQL_MAX_LIMIT)
+			return -EINVAL;
+	}
+
+	*pvalue = value;
+
+	return count;
+}
+
+static ssize_t bql_show_hold_time(struct netdev_queue *queue,
+				  struct netdev_queue_attribute *attr,
+				  char *buf)
+{
+	struct dql *dql = &queue->dql;
+
+	return sprintf(buf, "%u\n", jiffies_to_msecs(dql->slack_hold_time));
+}
+
+static ssize_t bql_set_hold_time(struct netdev_queue *queue,
+				 struct netdev_queue_attribute *attribute,
+				 const char *buf, size_t len)
+{
+	struct dql *dql = &queue->dql;
+	unsigned value;
+	int err;
+
+	err = kstrtouint(buf, 10, &value);
+	if (err < 0)
+		return err;
+
+	dql->slack_hold_time = msecs_to_jiffies(value);
+
+	return len;
+}
+
+static struct netdev_queue_attribute bql_hold_time_attribute =
+	__ATTR(hold_time, S_IRUGO | S_IWUSR, bql_show_hold_time,
+	    bql_set_hold_time);
+
+static ssize_t bql_show_inflight(struct netdev_queue *queue,
+				 struct netdev_queue_attribute *attr,
+				 char *buf)
+{
+	struct dql *dql = &queue->dql;
+
+	return sprintf(buf, "%u\n", dql->num_queued - dql->num_completed);
+}
+
+static struct netdev_queue_attribute bql_inflight_attribute =
+	__ATTR(inflight, S_IRUGO | S_IWUSR, bql_show_inflight, NULL);
+
+#define BQL_ATTR(NAME, FIELD)						\
+static ssize_t bql_show_ ## NAME(struct netdev_queue *queue,		\
+				 struct netdev_queue_attribute *attr,	\
+				 char *buf)				\
+{									\
+	return bql_show(buf, queue->dql.FIELD);				\
+}									\
+									\
+static ssize_t bql_set_ ## NAME(struct netdev_queue *queue,		\
+				struct netdev_queue_attribute *attr,	\
+				const char *buf, size_t len)		\
+{									\
+	return bql_set(buf, len, &queue->dql.FIELD);			\
+}									\
+									\
+static struct netdev_queue_attribute bql_ ## NAME ## _attribute =	\
+	__ATTR(NAME, S_IRUGO | S_IWUSR, bql_show_ ## NAME,		\
+	    bql_set_ ## NAME);
+
+BQL_ATTR(limit, limit)
+BQL_ATTR(limit_max, max_limit)
+BQL_ATTR(limit_min, min_limit)
+
+static struct attribute *dql_attrs[] = {
+	&bql_limit_attribute.attr,
+	&bql_limit_max_attribute.attr,
+	&bql_limit_min_attribute.attr,
+	&bql_hold_time_attribute.attr,
+	&bql_inflight_attribute.attr,
+	NULL
+};
+
+static struct attribute_group dql_group = {
+	.name  = "byte_queue_limits",
+	.attrs  = dql_attrs,
+};
+#endif /* CONFIG_BQL */
+
+#ifdef CONFIG_XPS
 static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue)
 {
 	struct net_device *dev = queue->dev;
@@ -890,6 +1021,52 @@ static DEFINE_MUTEX(xps_map_mutex);
 #define xmap_dereference(P)		\
 	rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex))
 
+static void xps_queue_release(struct netdev_queue *queue)
+{
+	struct net_device *dev = queue->dev;
+	struct xps_dev_maps *dev_maps;
+	struct xps_map *map;
+	unsigned long index;
+	int i, pos, nonempty = 0;
+
+	index = get_netdev_queue_index(queue);
+
+	mutex_lock(&xps_map_mutex);
+	dev_maps = xmap_dereference(dev->xps_maps);
+
+	if (dev_maps) {
+		for_each_possible_cpu(i) {
+			map = xmap_dereference(dev_maps->cpu_map[i]);
+			if (!map)
+				continue;
+
+			for (pos = 0; pos < map->len; pos++)
+				if (map->queues[pos] == index)
+					break;
+
+			if (pos < map->len) {
+				if (map->len > 1)
+					map->queues[pos] =
+					    map->queues[--map->len];
+				else {
+					RCU_INIT_POINTER(dev_maps->cpu_map[i],
+					    NULL);
+					kfree_rcu(map, rcu);
+					map = NULL;
+				}
+			}
+			if (map)
+				nonempty = 1;
+		}
+
+		if (!nonempty) {
+			RCU_INIT_POINTER(dev->xps_maps, NULL);
+			kfree_rcu(dev_maps, rcu);
+		}
+	}
+	mutex_unlock(&xps_map_mutex);
+}
+
 static ssize_t store_xps_map(struct netdev_queue *queue,
 		      struct netdev_queue_attribute *attribute,
 		      const char *buf, size_t len)
@@ -901,7 +1078,7 @@ static ssize_t store_xps_map(struct netdev_queue *queue,
 	struct xps_map *map, *new_map;
 	struct xps_dev_maps *dev_maps, *new_dev_maps;
 	int nonempty = 0;
-	int numa_node = -2;
+	int numa_node_id = -2;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
@@ -944,10 +1121,10 @@ static ssize_t store_xps_map(struct netdev_queue *queue,
 		need_set = cpumask_test_cpu(cpu, mask) && cpu_online(cpu);
 #ifdef CONFIG_NUMA
 		if (need_set) {
-			if (numa_node == -2)
-				numa_node = cpu_to_node(cpu);
-			else if (numa_node != cpu_to_node(cpu))
-				numa_node = -1;
+			if (numa_node_id == -2)
+				numa_node_id = cpu_to_node(cpu);
+			else if (numa_node_id != cpu_to_node(cpu))
+				numa_node_id = -1;
 		}
 #endif
 		if (need_set && pos >= map_len) {
@@ -997,7 +1174,7 @@ static ssize_t store_xps_map(struct netdev_queue *queue,
 	if (dev_maps)
 		kfree_rcu(dev_maps, rcu);
 
-	netdev_queue_numa_node_write(queue, (numa_node >= 0) ? numa_node :
+	netdev_queue_numa_node_write(queue, (numa_node_id >= 0) ? numa_node_id :
 					    NUMA_NO_NODE);
 
 	mutex_unlock(&xps_map_mutex);
@@ -1020,58 +1197,23 @@ error:
 
 static struct netdev_queue_attribute xps_cpus_attribute =
     __ATTR(xps_cpus, S_IRUGO | S_IWUSR, show_xps_map, store_xps_map);
+#endif /* CONFIG_XPS */
 
 static struct attribute *netdev_queue_default_attrs[] = {
+	&queue_trans_timeout.attr,
+#ifdef CONFIG_XPS
 	&xps_cpus_attribute.attr,
+#endif
 	NULL
 };
 
 static void netdev_queue_release(struct kobject *kobj)
 {
 	struct netdev_queue *queue = to_netdev_queue(kobj);
-	struct net_device *dev = queue->dev;
-	struct xps_dev_maps *dev_maps;
-	struct xps_map *map;
-	unsigned long index;
-	int i, pos, nonempty = 0;
 
-	index = get_netdev_queue_index(queue);
-
-	mutex_lock(&xps_map_mutex);
-	dev_maps = xmap_dereference(dev->xps_maps);
-
-	if (dev_maps) {
-		for_each_possible_cpu(i) {
-			map = xmap_dereference(dev_maps->cpu_map[i]);
-			if (!map)
-				continue;
-
-			for (pos = 0; pos < map->len; pos++)
-				if (map->queues[pos] == index)
-					break;
-
-			if (pos < map->len) {
-				if (map->len > 1)
-					map->queues[pos] =
-					    map->queues[--map->len];
-				else {
-					RCU_INIT_POINTER(dev_maps->cpu_map[i],
-					    NULL);
-					kfree_rcu(map, rcu);
-					map = NULL;
-				}
-			}
-			if (map)
-				nonempty = 1;
-		}
-
-		if (!nonempty) {
-			RCU_INIT_POINTER(dev->xps_maps, NULL);
-			kfree_rcu(dev_maps, rcu);
-		}
-	}
-
-	mutex_unlock(&xps_map_mutex);
+#ifdef CONFIG_XPS
+	xps_queue_release(queue);
+#endif
 
 	memset(kobj, 0, sizeof(*kobj));
 	dev_put(queue->dev);
@@ -1092,22 +1234,29 @@ static int netdev_queue_add_kobject(struct net_device *net, int index)
 	kobj->kset = net->queues_kset;
 	error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL,
 	    "tx-%u", index);
-	if (error) {
-		kobject_put(kobj);
-		return error;
-	}
+	if (error)
+		goto exit;
+
+#ifdef CONFIG_BQL
+	error = sysfs_create_group(kobj, &dql_group);
+	if (error)
+		goto exit;
+#endif
 
 	kobject_uevent(kobj, KOBJ_ADD);
 	dev_hold(queue->dev);
 
+	return 0;
+exit:
+	kobject_put(kobj);
 	return error;
 }
-#endif /* CONFIG_XPS */
+#endif /* CONFIG_SYSFS */
 
 int
 netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num)
 {
-#ifdef CONFIG_XPS
+#ifdef CONFIG_SYSFS
 	int i;
 	int error = 0;
 
@@ -1119,20 +1268,26 @@ netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num)
 		}
 	}
 
-	while (--i >= new_num)
-		kobject_put(&net->_tx[i].kobj);
+	while (--i >= new_num) {
+		struct netdev_queue *queue = net->_tx + i;
+
+#ifdef CONFIG_BQL
+		sysfs_remove_group(&queue->kobj, &dql_group);
+#endif
+		kobject_put(&queue->kobj);
+	}
 
 	return error;
 #else
 	return 0;
-#endif
+#endif /* CONFIG_SYSFS */
 }
 
 static int register_queue_kobjects(struct net_device *net)
 {
 	int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0;
 
-#if defined(CONFIG_RPS) || defined(CONFIG_XPS)
+#ifdef CONFIG_SYSFS
 	net->queues_kset = kset_create_and_add("queues",
 	    NULL, &net->dev.kobj);
 	if (!net->queues_kset)
@@ -1173,7 +1328,7 @@ static void remove_queue_kobjects(struct net_device *net)
 
 	net_rx_queue_update_kobjects(net, real_rx, 0);
 	netdev_queue_update_kobjects(net, real_tx, 0);
-#if defined(CONFIG_RPS) || defined(CONFIG_XPS)
+#ifdef CONFIG_SYSFS
 	kset_unregister(net->queues_kset);
 #endif
 }
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index cf64c1f..0d38808 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -76,7 +76,7 @@ static void queue_process(struct work_struct *work)
 
 		local_irq_save(flags);
 		__netif_tx_lock(txq, smp_processor_id());
-		if (netif_tx_queue_frozen_or_stopped(txq) ||
+		if (netif_xmit_frozen_or_stopped(txq) ||
 		    ops->ndo_start_xmit(skb, dev) != NETDEV_TX_OK) {
 			skb_queue_head(&npinfo->txq, skb);
 			__netif_tx_unlock(txq);
@@ -317,7 +317,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
 		for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
 		     tries > 0; --tries) {
 			if (__netif_tx_trylock(txq)) {
-				if (!netif_tx_queue_stopped(txq)) {
+				if (!netif_xmit_stopped(txq)) {
 					status = ops->ndo_start_xmit(skb, dev);
 					if (status == NETDEV_TX_OK)
 						txq_trans_update(txq);
@@ -422,6 +422,7 @@ static void arp_reply(struct sk_buff *skb)
 	struct sk_buff *send_skb;
 	struct netpoll *np, *tmp;
 	unsigned long flags;
+	int hlen, tlen;
 	int hits = 0;
 
 	if (list_empty(&npinfo->rx_np))
@@ -479,8 +480,9 @@ static void arp_reply(struct sk_buff *skb)
 		if (tip != np->local_ip)
 			continue;
 
-		send_skb = find_skb(np, size + LL_ALLOCATED_SPACE(np->dev),
-				    LL_RESERVED_SPACE(np->dev));
+		hlen = LL_RESERVED_SPACE(np->dev);
+		tlen = np->dev->needed_tailroom;
+		send_skb = find_skb(np, size + hlen + tlen, hlen);
 		if (!send_skb)
 			continue;
 
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
new file mode 100644
index 0000000..3a9fd48
--- /dev/null
+++ b/net/core/netprio_cgroup.c
@@ -0,0 +1,344 @@
+/*
+ * net/core/netprio_cgroup.c	Priority Control Group
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Neil Horman <nhorman@tuxdriver.com>
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <linux/cgroup.h>
+#include <linux/rcupdate.h>
+#include <linux/atomic.h>
+#include <net/rtnetlink.h>
+#include <net/pkt_cls.h>
+#include <net/sock.h>
+#include <net/netprio_cgroup.h>
+
+static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss,
+					       struct cgroup *cgrp);
+static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp);
+static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp);
+
+struct cgroup_subsys net_prio_subsys = {
+	.name		= "net_prio",
+	.create		= cgrp_create,
+	.destroy	= cgrp_destroy,
+	.populate	= cgrp_populate,
+#ifdef CONFIG_NETPRIO_CGROUP
+	.subsys_id	= net_prio_subsys_id,
+#endif
+	.module		= THIS_MODULE
+};
+
+#define PRIOIDX_SZ 128
+
+static unsigned long prioidx_map[PRIOIDX_SZ];
+static DEFINE_SPINLOCK(prioidx_map_lock);
+static atomic_t max_prioidx = ATOMIC_INIT(0);
+
+static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgrp)
+{
+	return container_of(cgroup_subsys_state(cgrp, net_prio_subsys_id),
+			    struct cgroup_netprio_state, css);
+}
+
+static int get_prioidx(u32 *prio)
+{
+	unsigned long flags;
+	u32 prioidx;
+
+	spin_lock_irqsave(&prioidx_map_lock, flags);
+	prioidx = find_first_zero_bit(prioidx_map, sizeof(unsigned long) * PRIOIDX_SZ);
+	set_bit(prioidx, prioidx_map);
+	spin_unlock_irqrestore(&prioidx_map_lock, flags);
+	if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ)
+		return -ENOSPC;
+
+	atomic_set(&max_prioidx, prioidx);
+	*prio = prioidx;
+	return 0;
+}
+
+static void put_prioidx(u32 idx)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&prioidx_map_lock, flags);
+	clear_bit(idx, prioidx_map);
+	spin_unlock_irqrestore(&prioidx_map_lock, flags);
+}
+
+static void extend_netdev_table(struct net_device *dev, u32 new_len)
+{
+	size_t new_size = sizeof(struct netprio_map) +
+			   ((sizeof(u32) * new_len));
+	struct netprio_map *new_priomap = kzalloc(new_size, GFP_KERNEL);
+	struct netprio_map *old_priomap;
+	int i;
+
+	old_priomap  = rtnl_dereference(dev->priomap);
+
+	if (!new_priomap) {
+		printk(KERN_WARNING "Unable to alloc new priomap!\n");
+		return;
+	}
+
+	for (i = 0;
+	     old_priomap && (i < old_priomap->priomap_len);
+	     i++)
+		new_priomap->priomap[i] = old_priomap->priomap[i];
+
+	new_priomap->priomap_len = new_len;
+
+	rcu_assign_pointer(dev->priomap, new_priomap);
+	if (old_priomap)
+		kfree_rcu(old_priomap, rcu);
+}
+
+static void update_netdev_tables(void)
+{
+	struct net_device *dev;
+	u32 max_len = atomic_read(&max_prioidx);
+	struct netprio_map *map;
+
+	rtnl_lock();
+	for_each_netdev(&init_net, dev) {
+		map = rtnl_dereference(dev->priomap);
+		if ((!map) ||
+		    (map->priomap_len < max_len))
+			extend_netdev_table(dev, max_len);
+	}
+	rtnl_unlock();
+}
+
+static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss,
+						 struct cgroup *cgrp)
+{
+	struct cgroup_netprio_state *cs;
+	int ret;
+
+	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
+	if (!cs)
+		return ERR_PTR(-ENOMEM);
+
+	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx) {
+		kfree(cs);
+		return ERR_PTR(-EINVAL);
+	}
+
+	ret = get_prioidx(&cs->prioidx);
+	if (ret != 0) {
+		printk(KERN_WARNING "No space in priority index array\n");
+		kfree(cs);
+		return ERR_PTR(ret);
+	}
+
+	return &cs->css;
+}
+
+static void cgrp_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+	struct cgroup_netprio_state *cs;
+	struct net_device *dev;
+	struct netprio_map *map;
+
+	cs = cgrp_netprio_state(cgrp);
+	rtnl_lock();
+	for_each_netdev(&init_net, dev) {
+		map = rtnl_dereference(dev->priomap);
+		if (map)
+			map->priomap[cs->prioidx] = 0;
+	}
+	rtnl_unlock();
+	put_prioidx(cs->prioidx);
+	kfree(cs);
+}
+
+static u64 read_prioidx(struct cgroup *cgrp, struct cftype *cft)
+{
+	return (u64)cgrp_netprio_state(cgrp)->prioidx;
+}
+
+static int read_priomap(struct cgroup *cont, struct cftype *cft,
+			struct cgroup_map_cb *cb)
+{
+	struct net_device *dev;
+	u32 prioidx = cgrp_netprio_state(cont)->prioidx;
+	u32 priority;
+	struct netprio_map *map;
+
+	rcu_read_lock();
+	for_each_netdev_rcu(&init_net, dev) {
+		map = rcu_dereference(dev->priomap);
+		priority = map ? map->priomap[prioidx] : 0;
+		cb->fill(cb, dev->name, priority);
+	}
+	rcu_read_unlock();
+	return 0;
+}
+
+static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
+			 const char *buffer)
+{
+	char *devname = kstrdup(buffer, GFP_KERNEL);
+	int ret = -EINVAL;
+	u32 prioidx = cgrp_netprio_state(cgrp)->prioidx;
+	unsigned long priority;
+	char *priostr;
+	struct net_device *dev;
+	struct netprio_map *map;
+
+	if (!devname)
+		return -ENOMEM;
+
+	/*
+	 * Minimally sized valid priomap string
+	 */
+	if (strlen(devname) < 3)
+		goto out_free_devname;
+
+	priostr = strstr(devname, " ");
+	if (!priostr)
+		goto out_free_devname;
+
+	/*
+	 *Separate the devname from the associated priority
+	 *and advance the priostr poitner to the priority value
+	 */
+	*priostr = '\0';
+	priostr++;
+
+	/*
+	 * If the priostr points to NULL, we're at the end of the passed
+	 * in string, and its not a valid write
+	 */
+	if (*priostr == '\0')
+		goto out_free_devname;
+
+	ret = kstrtoul(priostr, 10, &priority);
+	if (ret < 0)
+		goto out_free_devname;
+
+	ret = -ENODEV;
+
+	dev = dev_get_by_name(&init_net, devname);
+	if (!dev)
+		goto out_free_devname;
+
+	update_netdev_tables();
+	ret = 0;
+	rcu_read_lock();
+	map = rcu_dereference(dev->priomap);
+	if (map)
+		map->priomap[prioidx] = priority;
+	rcu_read_unlock();
+	dev_put(dev);
+
+out_free_devname:
+	kfree(devname);
+	return ret;
+}
+
+static struct cftype ss_files[] = {
+	{
+		.name = "prioidx",
+		.read_u64 = read_prioidx,
+	},
+	{
+		.name = "ifpriomap",
+		.read_map = read_priomap,
+		.write_string = write_priomap,
+	},
+};
+
+static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
+{
+	return cgroup_add_files(cgrp, ss, ss_files, ARRAY_SIZE(ss_files));
+}
+
+static int netprio_device_event(struct notifier_block *unused,
+				unsigned long event, void *ptr)
+{
+	struct net_device *dev = ptr;
+	struct netprio_map *old;
+	u32 max_len = atomic_read(&max_prioidx);
+
+	/*
+	 * Note this is called with rtnl_lock held so we have update side
+	 * protection on our rcu assignments
+	 */
+
+	switch (event) {
+
+	case NETDEV_REGISTER:
+		if (max_len)
+			extend_netdev_table(dev, max_len);
+		break;
+	case NETDEV_UNREGISTER:
+		old = rtnl_dereference(dev->priomap);
+		RCU_INIT_POINTER(dev->priomap, NULL);
+		if (old)
+			kfree_rcu(old, rcu);
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block netprio_device_notifier = {
+	.notifier_call = netprio_device_event
+};
+
+static int __init init_cgroup_netprio(void)
+{
+	int ret;
+
+	ret = cgroup_load_subsys(&net_prio_subsys);
+	if (ret)
+		goto out;
+#ifndef CONFIG_NETPRIO_CGROUP
+	smp_wmb();
+	net_prio_subsys_id = net_prio_subsys.subsys_id;
+#endif
+
+	register_netdevice_notifier(&netprio_device_notifier);
+
+out:
+	return ret;
+}
+
+static void __exit exit_cgroup_netprio(void)
+{
+	struct netprio_map *old;
+	struct net_device *dev;
+
+	unregister_netdevice_notifier(&netprio_device_notifier);
+
+	cgroup_unload_subsys(&net_prio_subsys);
+
+#ifndef CONFIG_NETPRIO_CGROUP
+	net_prio_subsys_id = -1;
+	synchronize_rcu();
+#endif
+
+	rtnl_lock();
+	for_each_netdev(&init_net, dev) {
+		old = rtnl_dereference(dev->priomap);
+		RCU_INIT_POINTER(dev->priomap, NULL);
+		if (old)
+			kfree_rcu(old, rcu);
+	}
+	rtnl_unlock();
+}
+
+module_init(init_cgroup_netprio);
+module_exit(exit_cgroup_netprio);
+MODULE_LICENSE("GPL v2");
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 0001c24..449fe0f 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1304,7 +1304,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		scan_ip6(buf, pkt_dev->in6_daddr.s6_addr);
 		snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_daddr);
 
-		ipv6_addr_copy(&pkt_dev->cur_in6_daddr, &pkt_dev->in6_daddr);
+		pkt_dev->cur_in6_daddr = pkt_dev->in6_daddr;
 
 		if (debug)
 			printk(KERN_DEBUG "pktgen: dst6 set to: %s\n", buf);
@@ -1327,8 +1327,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		scan_ip6(buf, pkt_dev->min_in6_daddr.s6_addr);
 		snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->min_in6_daddr);
 
-		ipv6_addr_copy(&pkt_dev->cur_in6_daddr,
-			       &pkt_dev->min_in6_daddr);
+		pkt_dev->cur_in6_daddr = pkt_dev->min_in6_daddr;
 		if (debug)
 			printk(KERN_DEBUG "pktgen: dst6_min set to: %s\n", buf);
 
@@ -1371,7 +1370,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		scan_ip6(buf, pkt_dev->in6_saddr.s6_addr);
 		snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_saddr);
 
-		ipv6_addr_copy(&pkt_dev->cur_in6_saddr, &pkt_dev->in6_saddr);
+		pkt_dev->cur_in6_saddr = pkt_dev->in6_saddr;
 
 		if (debug)
 			printk(KERN_DEBUG "pktgen: src6 set to: %s\n", buf);
@@ -2079,9 +2078,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
 				     ifp = ifp->if_next) {
 					if (ifp->scope == IFA_LINK &&
 					    !(ifp->flags & IFA_F_TENTATIVE)) {
-						ipv6_addr_copy(&pkt_dev->
-							       cur_in6_saddr,
-							       &ifp->addr);
+						pkt_dev->cur_in6_saddr = ifp->addr;
 						err = 0;
 						break;
 					}
@@ -2958,8 +2955,8 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
 	iph->payload_len = htons(sizeof(struct udphdr) + datalen);
 	iph->nexthdr = IPPROTO_UDP;
 
-	ipv6_addr_copy(&iph->daddr, &pkt_dev->cur_in6_daddr);
-	ipv6_addr_copy(&iph->saddr, &pkt_dev->cur_in6_saddr);
+	iph->daddr = pkt_dev->cur_in6_daddr;
+	iph->saddr = pkt_dev->cur_in6_saddr;
 
 	skb->mac_header = (skb->network_header - ETH_HLEN -
 			   pkt_dev->pkt_overhead);
@@ -3345,7 +3342,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev)
 
 	__netif_tx_lock_bh(txq);
 
-	if (unlikely(netif_tx_queue_frozen_or_stopped(txq))) {
+	if (unlikely(netif_xmit_frozen_or_stopped(txq))) {
 		ret = NETDEV_TX_BUSY;
 		pkt_dev->last_ok = 0;
 		goto unlock;
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index 182236b..9b570a6 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -26,10 +26,11 @@
  * but then some measure against one socket starving all other sockets
  * would be needed.
  *
- * It was 128 by default. Experiments with real servers show, that
+ * The minimum value of it is 128. Experiments with real servers show that
  * it is absolutely not enough even at 100conn/sec. 256 cures most
- * of problems. This value is adjusted to 128 for very small machines
- * (<=32Mb of memory) and to 1024 on normal or better ones (>=256Mb).
+ * of problems.
+ * This value is adjusted to 128 for low memory machines,
+ * and it will increase in proportion to the memory of machine.
  * Note : Dont forget somaxconn that may limit backlog too.
  */
 int sysctl_max_syn_backlog = 256;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9083e82..dbf2dda 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -273,6 +273,17 @@ EXPORT_SYMBOL_GPL(rtnl_unregister_all);
 
 static LIST_HEAD(link_ops);
 
+static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind)
+{
+	const struct rtnl_link_ops *ops;
+
+	list_for_each_entry(ops, &link_ops, list) {
+		if (!strcmp(ops->kind, kind))
+			return ops;
+	}
+	return NULL;
+}
+
 /**
  * __rtnl_link_register - Register rtnl_link_ops with rtnetlink.
  * @ops: struct rtnl_link_ops * to register
@@ -285,6 +296,9 @@ static LIST_HEAD(link_ops);
  */
 int __rtnl_link_register(struct rtnl_link_ops *ops)
 {
+	if (rtnl_link_ops_get(ops->kind))
+		return -EEXIST;
+
 	if (!ops->dellink)
 		ops->dellink = unregister_netdevice_queue;
 
@@ -351,17 +365,6 @@ void rtnl_link_unregister(struct rtnl_link_ops *ops)
 }
 EXPORT_SYMBOL_GPL(rtnl_link_unregister);
 
-static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind)
-{
-	const struct rtnl_link_ops *ops;
-
-	list_for_each_entry(ops, &link_ops, list) {
-		if (!strcmp(ops->kind, kind))
-			return ops;
-	}
-	return NULL;
-}
-
 static size_t rtnl_link_get_size(const struct net_device *dev)
 {
 	const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 025233d..6fd4460 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -19,6 +19,7 @@ static int __init net_secret_init(void)
 }
 late_initcall(net_secret_init);
 
+#ifdef CONFIG_INET
 static u32 seq_scale(u32 seq)
 {
 	/*
@@ -33,8 +34,9 @@ static u32 seq_scale(u32 seq)
 	 */
 	return seq + (ktime_to_ns(ktime_get_real()) >> 6);
 }
+#endif
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 __u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
 				   __be16 sport, __be16 dport)
 {
@@ -132,7 +134,7 @@ u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
 EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral);
 #endif
 
-#if defined(CONFIG_IP_DCCP) || defined(CONFIG_IP_DCCP_MODULE)
+#if IS_ENABLED(CONFIG_IP_DCCP)
 u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
 				__be16 sport, __be16 dport)
 {
@@ -154,7 +156,7 @@ u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
 }
 EXPORT_SYMBOL(secure_dccp_sequence_number);
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
 				  __be16 sport, __be16 dport)
 {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 06438f9..da0c97f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -245,6 +245,55 @@ nodata:
 EXPORT_SYMBOL(__alloc_skb);
 
 /**
+ * build_skb - build a network buffer
+ * @data: data buffer provided by caller
+ *
+ * Allocate a new &sk_buff. Caller provides space holding head and
+ * skb_shared_info. @data must have been allocated by kmalloc()
+ * The return is the new skb buffer.
+ * On a failure the return is %NULL, and @data is not freed.
+ * Notes :
+ *  Before IO, driver allocates only data buffer where NIC put incoming frame
+ *  Driver should add room at head (NET_SKB_PAD) and
+ *  MUST add room at tail (SKB_DATA_ALIGN(skb_shared_info))
+ *  After IO, driver calls build_skb(), to allocate sk_buff and populate it
+ *  before giving packet to stack.
+ *  RX rings only contains data buffers, not full skbs.
+ */
+struct sk_buff *build_skb(void *data)
+{
+	struct skb_shared_info *shinfo;
+	struct sk_buff *skb;
+	unsigned int size;
+
+	skb = kmem_cache_alloc(skbuff_head_cache, GFP_ATOMIC);
+	if (!skb)
+		return NULL;
+
+	size = ksize(data) - SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+	memset(skb, 0, offsetof(struct sk_buff, tail));
+	skb->truesize = SKB_TRUESIZE(size);
+	atomic_set(&skb->users, 1);
+	skb->head = data;
+	skb->data = data;
+	skb_reset_tail_pointer(skb);
+	skb->end = skb->tail + size;
+#ifdef NET_SKBUFF_DATA_USES_OFFSET
+	skb->mac_header = ~0U;
+#endif
+
+	/* make sure we initialize shinfo sequentially */
+	shinfo = skb_shinfo(skb);
+	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
+	atomic_set(&shinfo->dataref, 1);
+	kmemcheck_annotate_variable(shinfo->destructor_arg);
+
+	return skb;
+}
+EXPORT_SYMBOL(build_skb);
+
+/**
  *	__netdev_alloc_skb - allocate an skbuff for rx on a specific device
  *	@dev: network device to receive on
  *	@length: length to allocate
@@ -403,7 +452,7 @@ static void skb_release_head_state(struct sk_buff *skb)
 		WARN_ON(in_irq());
 		skb->destructor(skb);
 	}
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	nf_conntrack_put(skb->nfct);
 #endif
 #ifdef NET_SKBUFF_NF_DEFRAG_NEEDED
@@ -553,15 +602,14 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	new->ip_summed		= old->ip_summed;
 	skb_copy_queue_mapping(new, old);
 	new->priority		= old->priority;
-#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
+#if IS_ENABLED(CONFIG_IP_VS)
 	new->ipvs_property	= old->ipvs_property;
 #endif
 	new->protocol		= old->protocol;
 	new->mark		= old->mark;
 	new->skb_iif		= old->skb_iif;
 	__nf_copy(new, old);
-#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
-    defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
 	new->nf_trace		= old->nf_trace;
 #endif
 #ifdef CONFIG_NET_SCHED
@@ -791,8 +839,9 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask)
 EXPORT_SYMBOL(skb_copy);
 
 /**
- *	pskb_copy	-	create copy of an sk_buff with private head.
+ *	__pskb_copy	-	create copy of an sk_buff with private head.
  *	@skb: buffer to copy
+ *	@headroom: headroom of new skb
  *	@gfp_mask: allocation priority
  *
  *	Make a copy of both an &sk_buff and part of its data, located
@@ -803,16 +852,16 @@ EXPORT_SYMBOL(skb_copy);
  *	The returned buffer has a reference count of 1.
  */
 
-struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask)
+struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask)
 {
-	unsigned int size = skb_end_pointer(skb) - skb->head;
+	unsigned int size = skb_headlen(skb) + headroom;
 	struct sk_buff *n = alloc_skb(size, gfp_mask);
 
 	if (!n)
 		goto out;
 
 	/* Set the data pointer */
-	skb_reserve(n, skb_headroom(skb));
+	skb_reserve(n, headroom);
 	/* Set the tail pointer and length */
 	skb_put(n, skb_headlen(skb));
 	/* Copy the bytes */
@@ -848,7 +897,7 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask)
 out:
 	return n;
 }
-EXPORT_SYMBOL(pskb_copy);
+EXPORT_SYMBOL(__pskb_copy);
 
 /**
  *	pskb_expand_head - reallocate header of &sk_buff
@@ -2230,7 +2279,7 @@ static int skb_prepare_for_shift(struct sk_buff *skb)
  * @shiftlen: shift up to this many bytes
  *
  * Attempts to shift up to shiftlen worth of bytes, which may be less than
- * the length of the skb, from tgt to skb. Returns number bytes shifted.
+ * the length of the skb, from skb to tgt. Returns number bytes shifted.
  * It's up to caller to free skb if everything was shifted.
  *
  * If @tgt runs out of frags, the whole operation is aborted.
@@ -2621,7 +2670,7 @@ EXPORT_SYMBOL_GPL(skb_pull_rcsum);
  *	a pointer to the first in a list of new skbs for the segments.
  *	In case of error it returns ERR_PTR(err).
  */
-struct sk_buff *skb_segment(struct sk_buff *skb, u32 features)
+struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features)
 {
 	struct sk_buff *segs = NULL;
 	struct sk_buff *tail = NULL;
diff --git a/net/core/sock.c b/net/core/sock.c
index cbdf51c..0c67fac 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -111,6 +111,7 @@
 #include <linux/init.h>
 #include <linux/highmem.h>
 #include <linux/user_namespace.h>
+#include <linux/jump_label.h>
 
 #include <asm/uaccess.h>
 #include <asm/system.h>
@@ -125,6 +126,7 @@
 #include <net/xfrm.h>
 #include <linux/ipsec.h>
 #include <net/cls_cgroup.h>
+#include <net/netprio_cgroup.h>
 
 #include <linux/filter.h>
 
@@ -134,6 +136,46 @@
 #include <net/tcp.h>
 #endif
 
+static DEFINE_MUTEX(proto_list_mutex);
+static LIST_HEAD(proto_list);
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+int mem_cgroup_sockets_init(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+	struct proto *proto;
+	int ret = 0;
+
+	mutex_lock(&proto_list_mutex);
+	list_for_each_entry(proto, &proto_list, node) {
+		if (proto->init_cgroup) {
+			ret = proto->init_cgroup(cgrp, ss);
+			if (ret)
+				goto out;
+		}
+	}
+
+	mutex_unlock(&proto_list_mutex);
+	return ret;
+out:
+	list_for_each_entry_continue_reverse(proto, &proto_list, node)
+		if (proto->destroy_cgroup)
+			proto->destroy_cgroup(cgrp, ss);
+	mutex_unlock(&proto_list_mutex);
+	return ret;
+}
+
+void mem_cgroup_sockets_destroy(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+	struct proto *proto;
+
+	mutex_lock(&proto_list_mutex);
+	list_for_each_entry_reverse(proto, &proto_list, node)
+		if (proto->destroy_cgroup)
+			proto->destroy_cgroup(cgrp, ss);
+	mutex_unlock(&proto_list_mutex);
+}
+#endif
+
 /*
  * Each address family might have different locking rules, so we have
  * one slock key per address family:
@@ -141,6 +183,9 @@
 static struct lock_class_key af_family_keys[AF_MAX];
 static struct lock_class_key af_family_slock_keys[AF_MAX];
 
+struct jump_label_key memcg_socket_limit_enabled;
+EXPORT_SYMBOL(memcg_socket_limit_enabled);
+
 /*
  * Make lock validator output more readable. (we pre-construct these
  * strings build-time, so that runtime initialization of socket
@@ -221,10 +266,16 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
 int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
 EXPORT_SYMBOL(sysctl_optmem_max);
 
-#if defined(CONFIG_CGROUPS) && !defined(CONFIG_NET_CLS_CGROUP)
+#if defined(CONFIG_CGROUPS)
+#if !defined(CONFIG_NET_CLS_CGROUP)
 int net_cls_subsys_id = -1;
 EXPORT_SYMBOL_GPL(net_cls_subsys_id);
 #endif
+#if !defined(CONFIG_NETPRIO_CGROUP)
+int net_prio_subsys_id = -1;
+EXPORT_SYMBOL_GPL(net_prio_subsys_id);
+#endif
+#endif
 
 static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
 {
@@ -269,14 +320,14 @@ static void sock_warn_obsolete_bsdism(const char *name)
 	}
 }
 
-static void sock_disable_timestamp(struct sock *sk, int flag)
+#define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
+
+static void sock_disable_timestamp(struct sock *sk, unsigned long flags)
 {
-	if (sock_flag(sk, flag)) {
-		sock_reset_flag(sk, flag);
-		if (!sock_flag(sk, SOCK_TIMESTAMP) &&
-		    !sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE)) {
+	if (sk->sk_flags & flags) {
+		sk->sk_flags &= ~flags;
+		if (!(sk->sk_flags & SK_FLAGS_TIMESTAMP))
 			net_disable_timestamp();
-		}
 	}
 }
 
@@ -682,7 +733,7 @@ set_rcvbuf:
 					      SOCK_TIMESTAMPING_RX_SOFTWARE);
 		else
 			sock_disable_timestamp(sk,
-					       SOCK_TIMESTAMPING_RX_SOFTWARE);
+					       (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
 		sock_valbool_flag(sk, SOCK_TIMESTAMPING_SOFTWARE,
 				  val & SOF_TIMESTAMPING_SOFTWARE);
 		sock_valbool_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE,
@@ -1120,6 +1171,18 @@ void sock_update_classid(struct sock *sk)
 		sk->sk_classid = classid;
 }
 EXPORT_SYMBOL(sock_update_classid);
+
+void sock_update_netprioidx(struct sock *sk)
+{
+	struct cgroup_netprio_state *state;
+	if (in_interrupt())
+		return;
+	rcu_read_lock();
+	state = task_netprio_state(current);
+	sk->sk_cgrp_prioidx = state ? state->prioidx : 0;
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(sock_update_netprioidx);
 #endif
 
 /**
@@ -1147,6 +1210,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		atomic_set(&sk->sk_wmem_alloc, 1);
 
 		sock_update_classid(sk);
+		sock_update_netprioidx(sk);
 	}
 
 	return sk;
@@ -1167,8 +1231,7 @@ static void __sk_free(struct sock *sk)
 		RCU_INIT_POINTER(sk->sk_filter, NULL);
 	}
 
-	sock_disable_timestamp(sk, SOCK_TIMESTAMP);
-	sock_disable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE);
+	sock_disable_timestamp(sk, SK_FLAGS_TIMESTAMP);
 
 	if (atomic_read(&sk->sk_omem_alloc))
 		printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n",
@@ -1213,7 +1276,14 @@ void sk_release_kernel(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_release_kernel);
 
-struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
+/**
+ *	sk_clone_lock - clone a socket, and lock its clone
+ *	@sk: the socket to clone
+ *	@priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
+ *
+ *	Caller must unlock socket even in error path (bh_unlock_sock(newsk))
+ */
+struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 {
 	struct sock *newsk;
 
@@ -1297,16 +1367,15 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
 		newsk->sk_wq = NULL;
 
 		if (newsk->sk_prot->sockets_allocated)
-			percpu_counter_inc(newsk->sk_prot->sockets_allocated);
+			sk_sockets_allocated_inc(newsk);
 
-		if (sock_flag(newsk, SOCK_TIMESTAMP) ||
-		    sock_flag(newsk, SOCK_TIMESTAMPING_RX_SOFTWARE))
+		if (newsk->sk_flags & SK_FLAGS_TIMESTAMP)
 			net_enable_timestamp();
 	}
 out:
 	return newsk;
 }
-EXPORT_SYMBOL_GPL(sk_clone);
+EXPORT_SYMBOL_GPL(sk_clone_lock);
 
 void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 {
@@ -1686,30 +1755,34 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
 	struct proto *prot = sk->sk_prot;
 	int amt = sk_mem_pages(size);
 	long allocated;
+	int parent_status = UNDER_LIMIT;
 
 	sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
-	allocated = atomic_long_add_return(amt, prot->memory_allocated);
+
+	allocated = sk_memory_allocated_add(sk, amt, &parent_status);
 
 	/* Under limit. */
-	if (allocated <= prot->sysctl_mem[0]) {
-		if (prot->memory_pressure && *prot->memory_pressure)
-			*prot->memory_pressure = 0;
+	if (parent_status == UNDER_LIMIT &&
+			allocated <= sk_prot_mem_limits(sk, 0)) {
+		sk_leave_memory_pressure(sk);
 		return 1;
 	}
 
-	/* Under pressure. */
-	if (allocated > prot->sysctl_mem[1])
-		if (prot->enter_memory_pressure)
-			prot->enter_memory_pressure(sk);
+	/* Under pressure. (we or our parents) */
+	if ((parent_status > SOFT_LIMIT) ||
+			allocated > sk_prot_mem_limits(sk, 1))
+		sk_enter_memory_pressure(sk);
 
-	/* Over hard limit. */
-	if (allocated > prot->sysctl_mem[2])
+	/* Over hard limit (we or our parents) */
+	if ((parent_status == OVER_LIMIT) ||
+			(allocated > sk_prot_mem_limits(sk, 2)))
 		goto suppress_allocation;
 
 	/* guarantee minimum buffer size under pressure */
 	if (kind == SK_MEM_RECV) {
 		if (atomic_read(&sk->sk_rmem_alloc) < prot->sysctl_rmem[0])
 			return 1;
+
 	} else { /* SK_MEM_SEND */
 		if (sk->sk_type == SOCK_STREAM) {
 			if (sk->sk_wmem_queued < prot->sysctl_wmem[0])
@@ -1719,13 +1792,13 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind)
 				return 1;
 	}
 
-	if (prot->memory_pressure) {
+	if (sk_has_memory_pressure(sk)) {
 		int alloc;
 
-		if (!*prot->memory_pressure)
+		if (!sk_under_memory_pressure(sk))
 			return 1;
-		alloc = percpu_counter_read_positive(prot->sockets_allocated);
-		if (prot->sysctl_mem[2] > alloc *
+		alloc = sk_sockets_allocated_read_positive(sk);
+		if (sk_prot_mem_limits(sk, 2) > alloc *
 		    sk_mem_pages(sk->sk_wmem_queued +
 				 atomic_read(&sk->sk_rmem_alloc) +
 				 sk->sk_forward_alloc))
@@ -1748,7 +1821,9 @@ suppress_allocation:
 
 	/* Alas. Undo changes. */
 	sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM;
-	atomic_long_sub(amt, prot->memory_allocated);
+
+	sk_memory_allocated_sub(sk, amt, parent_status);
+
 	return 0;
 }
 EXPORT_SYMBOL(__sk_mem_schedule);
@@ -1759,15 +1834,13 @@ EXPORT_SYMBOL(__sk_mem_schedule);
  */
 void __sk_mem_reclaim(struct sock *sk)
 {
-	struct proto *prot = sk->sk_prot;
-
-	atomic_long_sub(sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT,
-		   prot->memory_allocated);
+	sk_memory_allocated_sub(sk,
+				sk->sk_forward_alloc >> SK_MEM_QUANTUM_SHIFT, 0);
 	sk->sk_forward_alloc &= SK_MEM_QUANTUM - 1;
 
-	if (prot->memory_pressure && *prot->memory_pressure &&
-	    (atomic_long_read(prot->memory_allocated) < prot->sysctl_mem[0]))
-		*prot->memory_pressure = 0;
+	if (sk_under_memory_pressure(sk) &&
+	    (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)))
+		sk_leave_memory_pressure(sk);
 }
 EXPORT_SYMBOL(__sk_mem_reclaim);
 
@@ -2138,16 +2211,15 @@ EXPORT_SYMBOL(sock_get_timestampns);
 void sock_enable_timestamp(struct sock *sk, int flag)
 {
 	if (!sock_flag(sk, flag)) {
+		unsigned long previous_flags = sk->sk_flags;
+
 		sock_set_flag(sk, flag);
 		/*
 		 * we just set one of the two flags which require net
 		 * time stamping, but time stamping might have been on
 		 * already because of the other one
 		 */
-		if (!sock_flag(sk,
-				flag == SOCK_TIMESTAMP ?
-				SOCK_TIMESTAMPING_RX_SOFTWARE :
-				SOCK_TIMESTAMP))
+		if (!(previous_flags & SK_FLAGS_TIMESTAMP))
 			net_enable_timestamp();
 	}
 }
@@ -2259,9 +2331,6 @@ void sk_common_release(struct sock *sk)
 }
 EXPORT_SYMBOL(sk_common_release);
 
-static DEFINE_RWLOCK(proto_list_lock);
-static LIST_HEAD(proto_list);
-
 #ifdef CONFIG_PROC_FS
 #define PROTO_INUSE_NR	64	/* should be enough for the first time */
 struct prot_inuse {
@@ -2410,10 +2479,10 @@ int proto_register(struct proto *prot, int alloc_slab)
 		}
 	}
 
-	write_lock(&proto_list_lock);
+	mutex_lock(&proto_list_mutex);
 	list_add(&prot->node, &proto_list);
 	assign_proto_idx(prot);
-	write_unlock(&proto_list_lock);
+	mutex_unlock(&proto_list_mutex);
 	return 0;
 
 out_free_timewait_sock_slab_name:
@@ -2436,10 +2505,10 @@ EXPORT_SYMBOL(proto_register);
 
 void proto_unregister(struct proto *prot)
 {
-	write_lock(&proto_list_lock);
+	mutex_lock(&proto_list_mutex);
 	release_proto_idx(prot);
 	list_del(&prot->node);
-	write_unlock(&proto_list_lock);
+	mutex_unlock(&proto_list_mutex);
 
 	if (prot->slab != NULL) {
 		kmem_cache_destroy(prot->slab);
@@ -2462,9 +2531,9 @@ EXPORT_SYMBOL(proto_unregister);
 
 #ifdef CONFIG_PROC_FS
 static void *proto_seq_start(struct seq_file *seq, loff_t *pos)
-	__acquires(proto_list_lock)
+	__acquires(proto_list_mutex)
 {
-	read_lock(&proto_list_lock);
+	mutex_lock(&proto_list_mutex);
 	return seq_list_start_head(&proto_list, *pos);
 }
 
@@ -2474,25 +2543,36 @@ static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 }
 
 static void proto_seq_stop(struct seq_file *seq, void *v)
-	__releases(proto_list_lock)
+	__releases(proto_list_mutex)
 {
-	read_unlock(&proto_list_lock);
+	mutex_unlock(&proto_list_mutex);
 }
 
 static char proto_method_implemented(const void *method)
 {
 	return method == NULL ? 'n' : 'y';
 }
+static long sock_prot_memory_allocated(struct proto *proto)
+{
+	return proto->memory_allocated != NULL ? proto_memory_allocated(proto): -1L;
+}
+
+static char *sock_prot_memory_pressure(struct proto *proto)
+{
+	return proto->memory_pressure != NULL ?
+	proto_memory_pressure(proto) ? "yes" : "no" : "NI";
+}
 
 static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
 {
+
 	seq_printf(seq, "%-9s %4u %6d  %6ld   %-3s %6u   %-3s  %-10s "
 			"%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
 		   proto->name,
 		   proto->obj_size,
 		   sock_prot_inuse_get(seq_file_net(seq), proto),
-		   proto->memory_allocated != NULL ? atomic_long_read(proto->memory_allocated) : -1L,
-		   proto->memory_pressure != NULL ? *proto->memory_pressure ? "yes" : "no" : "NI",
+		   sock_prot_memory_allocated(proto),
+		   sock_prot_memory_pressure(proto),
 		   proto->max_header,
 		   proto->slab == NULL ? "no" : "yes",
 		   module_name(proto->owner),
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
new file mode 100644
index 0000000..711bdef
--- /dev/null
+++ b/net/core/sock_diag.c
@@ -0,0 +1,169 @@
+#include <linux/mutex.h>
+#include <linux/socket.h>
+#include <linux/skbuff.h>
+#include <net/netlink.h>
+#include <net/net_namespace.h>
+#include <linux/module.h>
+
+#include <linux/inet_diag.h>
+#include <linux/sock_diag.h>
+
+static struct sock_diag_handler *sock_diag_handlers[AF_MAX];
+static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
+static DEFINE_MUTEX(sock_diag_table_mutex);
+
+int sock_diag_check_cookie(void *sk, __u32 *cookie)
+{
+	if ((cookie[0] != INET_DIAG_NOCOOKIE ||
+	     cookie[1] != INET_DIAG_NOCOOKIE) &&
+	    ((u32)(unsigned long)sk != cookie[0] ||
+	     (u32)((((unsigned long)sk) >> 31) >> 1) != cookie[1]))
+		return -ESTALE;
+	else
+		return 0;
+}
+EXPORT_SYMBOL_GPL(sock_diag_check_cookie);
+
+void sock_diag_save_cookie(void *sk, __u32 *cookie)
+{
+	cookie[0] = (u32)(unsigned long)sk;
+	cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1);
+}
+EXPORT_SYMBOL_GPL(sock_diag_save_cookie);
+
+void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh))
+{
+	mutex_lock(&sock_diag_table_mutex);
+	inet_rcv_compat = fn;
+	mutex_unlock(&sock_diag_table_mutex);
+}
+EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat);
+
+void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh))
+{
+	mutex_lock(&sock_diag_table_mutex);
+	inet_rcv_compat = NULL;
+	mutex_unlock(&sock_diag_table_mutex);
+}
+EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat);
+
+int sock_diag_register(struct sock_diag_handler *hndl)
+{
+	int err = 0;
+
+	if (hndl->family >= AF_MAX)
+		return -EINVAL;
+
+	mutex_lock(&sock_diag_table_mutex);
+	if (sock_diag_handlers[hndl->family])
+		err = -EBUSY;
+	else
+		sock_diag_handlers[hndl->family] = hndl;
+	mutex_unlock(&sock_diag_table_mutex);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(sock_diag_register);
+
+void sock_diag_unregister(struct sock_diag_handler *hnld)
+{
+	int family = hnld->family;
+
+	if (family >= AF_MAX)
+		return;
+
+	mutex_lock(&sock_diag_table_mutex);
+	BUG_ON(sock_diag_handlers[family] != hnld);
+	sock_diag_handlers[family] = NULL;
+	mutex_unlock(&sock_diag_table_mutex);
+}
+EXPORT_SYMBOL_GPL(sock_diag_unregister);
+
+static inline struct sock_diag_handler *sock_diag_lock_handler(int family)
+{
+	if (sock_diag_handlers[family] == NULL)
+		request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
+				NETLINK_SOCK_DIAG, family);
+
+	mutex_lock(&sock_diag_table_mutex);
+	return sock_diag_handlers[family];
+}
+
+static inline void sock_diag_unlock_handler(struct sock_diag_handler *h)
+{
+	mutex_unlock(&sock_diag_table_mutex);
+}
+
+static int __sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	int err;
+	struct sock_diag_req *req = NLMSG_DATA(nlh);
+	struct sock_diag_handler *hndl;
+
+	if (nlmsg_len(nlh) < sizeof(*req))
+		return -EINVAL;
+
+	hndl = sock_diag_lock_handler(req->sdiag_family);
+	if (hndl == NULL)
+		err = -ENOENT;
+	else
+		err = hndl->dump(skb, nlh);
+	sock_diag_unlock_handler(hndl);
+
+	return err;
+}
+
+static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	int ret;
+
+	switch (nlh->nlmsg_type) {
+	case TCPDIAG_GETSOCK:
+	case DCCPDIAG_GETSOCK:
+		if (inet_rcv_compat == NULL)
+			request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
+					NETLINK_SOCK_DIAG, AF_INET);
+
+		mutex_lock(&sock_diag_table_mutex);
+		if (inet_rcv_compat != NULL)
+			ret = inet_rcv_compat(skb, nlh);
+		else
+			ret = -EOPNOTSUPP;
+		mutex_unlock(&sock_diag_table_mutex);
+
+		return ret;
+	case SOCK_DIAG_BY_FAMILY:
+		return __sock_diag_rcv_msg(skb, nlh);
+	default:
+		return -EINVAL;
+	}
+}
+
+static DEFINE_MUTEX(sock_diag_mutex);
+
+static void sock_diag_rcv(struct sk_buff *skb)
+{
+	mutex_lock(&sock_diag_mutex);
+	netlink_rcv_skb(skb, &sock_diag_rcv_msg);
+	mutex_unlock(&sock_diag_mutex);
+}
+
+struct sock *sock_diag_nlsk;
+EXPORT_SYMBOL_GPL(sock_diag_nlsk);
+
+static int __init sock_diag_init(void)
+{
+	sock_diag_nlsk = netlink_kernel_create(&init_net, NETLINK_SOCK_DIAG, 0,
+					sock_diag_rcv, NULL, THIS_MODULE);
+	return sock_diag_nlsk == NULL ? -ENOMEM : 0;
+}
+
+static void __exit sock_diag_exit(void)
+{
+	netlink_kernel_release(sock_diag_nlsk);
+}
+
+module_init(sock_diag_init);
+module_exit(sock_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_SOCK_DIAG);
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 77a65f0..d05559d 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -68,8 +68,13 @@ static int rps_sock_flow_sysctl(ctl_table *table, int write,
 
 		if (sock_table != orig_sock_table) {
 			rcu_assign_pointer(rps_sock_flow_table, sock_table);
-			synchronize_rcu();
-			vfree(orig_sock_table);
+			if (sock_table)
+				jump_label_inc(&rps_needed);
+			if (orig_sock_table) {
+				jump_label_dec(&rps_needed);
+				synchronize_rcu();
+				vfree(orig_sock_table);
+			}
 		}
 	}
 
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index 583490a..5818032 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -357,7 +357,7 @@ static inline int dccp_bad_service_code(const struct sock *sk,
 struct dccp_skb_cb {
 	union {
 		struct inet_skb_parm	h4;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		struct inet6_skb_parm	h6;
 #endif
 	} header;
diff --git a/net/dccp/diag.c b/net/dccp/diag.c
index b21f261..8f16257 100644
--- a/net/dccp/diag.c
+++ b/net/dccp/diag.c
@@ -48,11 +48,23 @@ static void dccp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 		dccp_get_info(sk, _info);
 }
 
+static void dccp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
+		struct inet_diag_req *r, struct nlattr *bc)
+{
+	inet_diag_dump_icsk(&dccp_hashinfo, skb, cb, r, bc);
+}
+
+static int dccp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
+		struct inet_diag_req *req)
+{
+	return inet_diag_dump_one_icsk(&dccp_hashinfo, in_skb, nlh, req);
+}
+
 static const struct inet_diag_handler dccp_diag_handler = {
-	.idiag_hashinfo	 = &dccp_hashinfo,
+	.dump		 = dccp_diag_dump,
+	.dump_one	 = dccp_diag_dump_one,
 	.idiag_get_info	 = dccp_diag_get_info,
-	.idiag_type	 = DCCPDIAG_GETSOCK,
-	.idiag_info_size = sizeof(struct tcp_info),
+	.idiag_type	 = IPPROTO_DCCP,
 };
 
 static int __init dccp_diag_init(void)
@@ -71,4 +83,4 @@ module_exit(dccp_diag_fini);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>");
 MODULE_DESCRIPTION("DCCP inet_diag handler");
-MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_INET_DIAG, DCCPDIAG_GETSOCK);
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-33 /* AF_INET - IPPROTO_DCCP */);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 90a919a..1c67fe8 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -111,6 +111,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	rt = ip_route_newports(fl4, rt, orig_sport, orig_dport,
 			       inet->inet_sport, inet->inet_dport, sk);
 	if (IS_ERR(rt)) {
+		err = PTR_ERR(rt);
 		rt = NULL;
 		goto failure;
 	}
@@ -473,10 +474,11 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
 					   struct sk_buff *skb)
 {
 	struct rtable *rt;
+	const struct iphdr *iph = ip_hdr(skb);
 	struct flowi4 fl4 = {
 		.flowi4_oif = skb_rtable(skb)->rt_iif,
-		.daddr = ip_hdr(skb)->saddr,
-		.saddr = ip_hdr(skb)->daddr,
+		.daddr = iph->saddr,
+		.saddr = iph->daddr,
 		.flowi4_tos = RT_CONN_FLAGS(sk),
 		.flowi4_proto = sk->sk_protocol,
 		.fl4_sport = dccp_hdr(skb)->dccph_dport,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 17ee85c..ce903f7 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -150,8 +150,8 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			 */
 			memset(&fl6, 0, sizeof(fl6));
 			fl6.flowi6_proto = IPPROTO_DCCP;
-			ipv6_addr_copy(&fl6.daddr, &np->daddr);
-			ipv6_addr_copy(&fl6.saddr, &np->saddr);
+			fl6.daddr = np->daddr;
+			fl6.saddr = np->saddr;
 			fl6.flowi6_oif = sk->sk_bound_dev_if;
 			fl6.fl6_dport = inet->inet_dport;
 			fl6.fl6_sport = inet->inet_sport;
@@ -244,8 +244,8 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
 
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_proto = IPPROTO_DCCP;
-	ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr);
-	ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr);
+	fl6.daddr = ireq6->rmt_addr;
+	fl6.saddr = ireq6->loc_addr;
 	fl6.flowlabel = 0;
 	fl6.flowi6_oif = ireq6->iif;
 	fl6.fl6_dport = inet_rsk(req)->rmt_port;
@@ -270,7 +270,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
 		dh->dccph_checksum = dccp_v6_csum_finish(skb,
 							 &ireq6->loc_addr,
 							 &ireq6->rmt_addr);
-		ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr);
+		fl6.daddr = ireq6->rmt_addr;
 		err = ip6_xmit(sk, skb, &fl6, opt, np->tclass);
 		err = net_xmit_eval(err);
 	}
@@ -313,8 +313,8 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb)
 							    &rxip6h->daddr);
 
 	memset(&fl6, 0, sizeof(fl6));
-	ipv6_addr_copy(&fl6.daddr, &rxip6h->saddr);
-	ipv6_addr_copy(&fl6.saddr, &rxip6h->daddr);
+	fl6.daddr = rxip6h->saddr;
+	fl6.saddr = rxip6h->daddr;
 
 	fl6.flowi6_proto = IPPROTO_DCCP;
 	fl6.flowi6_oif = inet6_iif(rxskb);
@@ -419,8 +419,8 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 		goto drop_and_free;
 
 	ireq6 = inet6_rsk(req);
-	ipv6_addr_copy(&ireq6->rmt_addr, &ipv6_hdr(skb)->saddr);
-	ipv6_addr_copy(&ireq6->loc_addr, &ipv6_hdr(skb)->daddr);
+	ireq6->rmt_addr = ipv6_hdr(skb)->saddr;
+	ireq6->loc_addr = ipv6_hdr(skb)->daddr;
 
 	if (ipv6_opt_accepted(sk, skb) ||
 	    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
@@ -491,7 +491,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 
 		ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr);
 
-		ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr);
+		newnp->rcv_saddr = newnp->saddr;
 
 		inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped;
 		newsk->sk_backlog_rcv = dccp_v4_do_rcv;
@@ -526,9 +526,9 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_proto = IPPROTO_DCCP;
-		ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr);
+		fl6.daddr = ireq6->rmt_addr;
 		final_p = fl6_update_dst(&fl6, opt, &final);
-		ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr);
+		fl6.saddr = ireq6->loc_addr;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 		fl6.fl6_dport = inet_rsk(req)->rmt_port;
 		fl6.fl6_sport = inet_rsk(req)->loc_port;
@@ -559,9 +559,9 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
-	ipv6_addr_copy(&newnp->daddr, &ireq6->rmt_addr);
-	ipv6_addr_copy(&newnp->saddr, &ireq6->loc_addr);
-	ipv6_addr_copy(&newnp->rcv_saddr, &ireq6->loc_addr);
+	newnp->daddr = ireq6->rmt_addr;
+	newnp->saddr = ireq6->loc_addr;
+	newnp->rcv_saddr = ireq6->loc_addr;
 	newsk->sk_bound_dev_if = ireq6->iif;
 
 	/* Now IPv6 options...
@@ -877,7 +877,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 			if (flowlabel == NULL)
 				return -EINVAL;
-			ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
+			usin->sin6_addr = flowlabel->dst;
 			fl6_sock_release(flowlabel);
 		}
 	}
@@ -910,7 +910,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 			return -EINVAL;
 	}
 
-	ipv6_addr_copy(&np->daddr, &usin->sin6_addr);
+	np->daddr = usin->sin6_addr;
 	np->flow_label = fl6.flowlabel;
 
 	/*
@@ -949,8 +949,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		saddr = &np->rcv_saddr;
 
 	fl6.flowi6_proto = IPPROTO_DCCP;
-	ipv6_addr_copy(&fl6.daddr, &np->daddr);
-	ipv6_addr_copy(&fl6.saddr, saddr ? saddr : &np->saddr);
+	fl6.daddr = np->daddr;
+	fl6.saddr = saddr ? *saddr : np->saddr;
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.fl6_dport = usin->sin6_port;
 	fl6.fl6_sport = inet->inet_sport;
@@ -966,11 +966,11 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	if (saddr == NULL) {
 		saddr = &fl6.saddr;
-		ipv6_addr_copy(&np->rcv_saddr, saddr);
+		np->rcv_saddr = *saddr;
 	}
 
 	/* set the source address */
-	ipv6_addr_copy(&np->saddr, saddr);
+	np->saddr = *saddr;
 	inet->inet_rcv_saddr = LOOPBACK4_IPV6;
 
 	__ip6_dst_store(sk, dst, NULL, NULL);
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index d7041a0..5a7f90b 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -53,15 +53,15 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
 	if (tw != NULL) {
 		const struct inet_connection_sock *icsk = inet_csk(sk);
 		const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == PF_INET6) {
 			const struct ipv6_pinfo *np = inet6_sk(sk);
 			struct inet6_timewait_sock *tw6;
 
 			tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot);
 			tw6 = inet6_twsk((struct sock *)tw);
-			ipv6_addr_copy(&tw6->tw_v6_daddr, &np->daddr);
-			ipv6_addr_copy(&tw6->tw_v6_rcv_saddr, &np->rcv_saddr);
+			tw6->tw_v6_daddr = np->daddr;
+			tw6->tw_v6_rcv_saddr = np->rcv_saddr;
 			tw->tw_ipv6only = np->ipv6only;
 		}
 #endif
@@ -100,7 +100,7 @@ struct sock *dccp_create_openreq_child(struct sock *sk,
 	 *   (* Generate a new socket and switch to that socket *)
 	 *   Set S := new socket for this port pair
 	 */
-	struct sock *newsk = inet_csk_clone(sk, req, GFP_ATOMIC);
+	struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC);
 
 	if (newsk != NULL) {
 		struct dccp_request_sock *dreq = dccp_rsk(req);
diff --git a/net/dccp/probe.c b/net/dccp/probe.c
index 33d0e62..0a8d6eb 100644
--- a/net/dccp/probe.c
+++ b/net/dccp/probe.c
@@ -152,6 +152,17 @@ static const struct file_operations dccpprobe_fops = {
 	.llseek  = noop_llseek,
 };
 
+static __init int setup_jprobe(void)
+{
+	int ret = register_jprobe(&dccp_send_probe);
+
+	if (ret) {
+		request_module("dccp");
+		ret = register_jprobe(&dccp_send_probe);
+	}
+	return ret;
+}
+
 static __init int dccpprobe_init(void)
 {
 	int ret = -ENOMEM;
@@ -163,8 +174,7 @@ static __init int dccpprobe_init(void)
 	if (!proc_net_fops_create(&init_net, procname, S_IRUSR, &dccpprobe_fops))
 		goto err0;
 
-	try_then_request_module((ret = register_jprobe(&dccp_send_probe)) == 0,
-				"dccp");
+	ret = setup_jprobe();
 	if (ret)
 		goto err1;
 
diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c
index 7f0eb08..7d2fff2 100644
--- a/net/decnet/dn_neigh.c
+++ b/net/decnet/dn_neigh.c
@@ -107,7 +107,7 @@ struct neigh_table dn_neigh_table = {
 		.gc_staletime =	60 * HZ,
 		.reachable_time =		30 * HZ,
 		.delay_probe_time =	5 * HZ,
-		.queue_len =		3,
+		.queue_len_bytes =	64*1024,
 		.ucast_probes =	0,
 		.app_probes =		0,
 		.mcast_probes =	0,
@@ -202,7 +202,7 @@ static int dn_neigh_output_packet(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct dn_route *rt = (struct dn_route *)dst;
-	struct neighbour *neigh = dst_get_neighbour(dst);
+	struct neighbour *neigh = dst_get_neighbour_noref(dst);
 	struct net_device *dev = neigh->dev;
 	char mac_addr[ETH_ALEN];
 
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index a77d161..f31ce72 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -112,7 +112,7 @@ static unsigned long dn_rt_deadline;
 static int dn_dst_gc(struct dst_ops *ops);
 static struct dst_entry *dn_dst_check(struct dst_entry *, __u32);
 static unsigned int dn_dst_default_advmss(const struct dst_entry *dst);
-static unsigned int dn_dst_default_mtu(const struct dst_entry *dst);
+static unsigned int dn_dst_mtu(const struct dst_entry *dst);
 static void dn_dst_destroy(struct dst_entry *);
 static struct dst_entry *dn_dst_negative_advice(struct dst_entry *);
 static void dn_dst_link_failure(struct sk_buff *);
@@ -135,7 +135,7 @@ static struct dst_ops dn_dst_ops = {
 	.gc =			dn_dst_gc,
 	.check =		dn_dst_check,
 	.default_advmss =	dn_dst_default_advmss,
-	.default_mtu =		dn_dst_default_mtu,
+	.mtu =			dn_dst_mtu,
 	.cow_metrics =		dst_cow_metrics_generic,
 	.destroy =		dn_dst_destroy,
 	.negative_advice =	dn_dst_negative_advice,
@@ -244,7 +244,7 @@ static int dn_dst_gc(struct dst_ops *ops)
  */
 static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu)
 {
-	struct neighbour *n = dst_get_neighbour(dst);
+	struct neighbour *n = dst_get_neighbour_noref(dst);
 	u32 min_mtu = 230;
 	struct dn_dev *dn;
 
@@ -713,7 +713,7 @@ out:
 static int dn_to_neigh_output(struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
-	struct neighbour *n = dst_get_neighbour(dst);
+	struct neighbour *n = dst_get_neighbour_noref(dst);
 
 	return n->output(n, skb);
 }
@@ -728,7 +728,7 @@ static int dn_output(struct sk_buff *skb)
 
 	int err = -EINVAL;
 
-	if ((neigh = dst_get_neighbour(dst)) == NULL)
+	if ((neigh = dst_get_neighbour_noref(dst)) == NULL)
 		goto error;
 
 	skb->dev = dev;
@@ -825,9 +825,11 @@ static unsigned int dn_dst_default_advmss(const struct dst_entry *dst)
 	return dn_mss_from_pmtu(dst->dev, dst_mtu(dst));
 }
 
-static unsigned int dn_dst_default_mtu(const struct dst_entry *dst)
+static unsigned int dn_dst_mtu(const struct dst_entry *dst)
 {
-	return dst->dev->mtu;
+	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+	return mtu ? : dst->dev->mtu;
 }
 
 static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, const void *daddr)
@@ -850,7 +852,7 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res)
 	}
 	rt->rt_type = res->type;
 
-	if (dev != NULL && dst_get_neighbour(&rt->dst) == NULL) {
+	if (dev != NULL && dst_get_neighbour_noref(&rt->dst) == NULL) {
 		n = __neigh_lookup_errno(&dn_neigh_table, &rt->rt_gateway, dev);
 		if (IS_ERR(n))
 			return PTR_ERR(n);
diff --git a/net/decnet/dn_timer.c b/net/decnet/dn_timer.c
index 67f691b..d9c150c 100644
--- a/net/decnet/dn_timer.c
+++ b/net/decnet/dn_timer.c
@@ -36,16 +36,13 @@ static void dn_slow_timer(unsigned long arg);
 
 void dn_start_slow_timer(struct sock *sk)
 {
-	sk->sk_timer.expires	= jiffies + SLOW_INTERVAL;
-	sk->sk_timer.function	= dn_slow_timer;
-	sk->sk_timer.data	= (unsigned long)sk;
-
-	add_timer(&sk->sk_timer);
+	setup_timer(&sk->sk_timer, dn_slow_timer, (unsigned long)sk);
+	sk_reset_timer(sk, &sk->sk_timer, jiffies + SLOW_INTERVAL);
 }
 
 void dn_stop_slow_timer(struct sock *sk)
 {
-	del_timer(&sk->sk_timer);
+	sk_stop_timer(sk, &sk->sk_timer);
 }
 
 static void dn_slow_timer(unsigned long arg)
@@ -53,12 +50,10 @@ static void dn_slow_timer(unsigned long arg)
 	struct sock *sk = (struct sock *)arg;
 	struct dn_scp *scp = DN_SK(sk);
 
-	sock_hold(sk);
 	bh_lock_sock(sk);
 
 	if (sock_owned_by_user(sk)) {
-		sk->sk_timer.expires = jiffies + HZ / 10;
-		add_timer(&sk->sk_timer);
+		sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ / 10);
 		goto out;
 	}
 
@@ -100,9 +95,7 @@ static void dn_slow_timer(unsigned long arg)
 			scp->keepalive_fxn(sk);
 	}
 
-	sk->sk_timer.expires = jiffies + SLOW_INTERVAL;
-
-	add_timer(&sk->sk_timer);
+	sk_reset_timer(sk, &sk->sk_timer, jiffies + SLOW_INTERVAL);
 out:
 	bh_unlock_sock(sk);
 	sock_put(sk);
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index c53ded2..274791c 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -1,5 +1,5 @@
-menuconfig NET_DSA
-	bool "Distributed Switch Architecture support"
+config NET_DSA
+	tristate "Distributed Switch Architecture support"
 	default n
 	depends on EXPERIMENTAL && NETDEVICES && !S390
 	select PHYLIB
@@ -23,38 +23,4 @@ config NET_DSA_TAG_TRAILER
 	bool
 	default n
 
-
-# switch drivers
-config NET_DSA_MV88E6XXX
-	bool
-	default n
-
-config NET_DSA_MV88E6060
-	bool "Marvell 88E6060 ethernet switch chip support"
-	select NET_DSA_TAG_TRAILER
-	---help---
-	  This enables support for the Marvell 88E6060 ethernet switch
-	  chip.
-
-config NET_DSA_MV88E6XXX_NEED_PPU
-	bool
-	default n
-
-config NET_DSA_MV88E6131
-	bool "Marvell 88E6085/6095/6095F/6131 ethernet switch chip support"
-	select NET_DSA_MV88E6XXX
-	select NET_DSA_MV88E6XXX_NEED_PPU
-	select NET_DSA_TAG_DSA
-	---help---
-	  This enables support for the Marvell 88E6085/6095/6095F/6131
-	  ethernet switch chips.
-
-config NET_DSA_MV88E6123_61_65
-	bool "Marvell 88E6123/6161/6165 ethernet switch chip support"
-	select NET_DSA_MV88E6XXX
-	select NET_DSA_TAG_EDSA
-	---help---
-	  This enables support for the Marvell 88E6123/6161/6165
-	  ethernet switch chips.
-
 endif
diff --git a/net/dsa/Makefile b/net/dsa/Makefile
index 2374faf..7b9fcbb 100644
--- a/net/dsa/Makefile
+++ b/net/dsa/Makefile
@@ -1,13 +1,8 @@
-# tagging formats
-obj-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o
-obj-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o
-obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o
-
-# switch drivers
-obj-$(CONFIG_NET_DSA_MV88E6XXX) += mv88e6xxx.o
-obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o
-obj-$(CONFIG_NET_DSA_MV88E6123_61_65) += mv88e6123_61_65.o
-obj-$(CONFIG_NET_DSA_MV88E6131) += mv88e6131.o
-
 # the core
-obj-$(CONFIG_NET_DSA) += dsa.o slave.o
+obj-$(CONFIG_NET_DSA) += dsa_core.o
+dsa_core-y += dsa.o slave.o
+
+# tagging formats
+dsa_core-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o
+dsa_core-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o
+dsa_core-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 0dc1589..88e7c2f 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -29,6 +29,7 @@ void register_switch_driver(struct dsa_switch_driver *drv)
 	list_add_tail(&drv->list, &dsa_switch_drivers);
 	mutex_unlock(&dsa_switch_drivers_mutex);
 }
+EXPORT_SYMBOL_GPL(register_switch_driver);
 
 void unregister_switch_driver(struct dsa_switch_driver *drv)
 {
@@ -36,6 +37,7 @@ void unregister_switch_driver(struct dsa_switch_driver *drv)
 	list_del_init(&drv->list);
 	mutex_unlock(&dsa_switch_drivers_mutex);
 }
+EXPORT_SYMBOL_GPL(unregister_switch_driver);
 
 static struct dsa_switch_driver *
 dsa_switch_probe(struct mii_bus *bus, int sw_addr, char **_name)
@@ -199,29 +201,6 @@ static void dsa_switch_destroy(struct dsa_switch *ds)
 }
 
 
-/* hooks for ethertype-less tagging formats *********************************/
-/*
- * The original DSA tag format and some other tag formats have no
- * ethertype, which means that we need to add a little hack to the
- * networking receive path to make sure that received frames get
- * the right ->protocol assigned to them when one of those tag
- * formats is in use.
- */
-bool dsa_uses_dsa_tags(void *dsa_ptr)
-{
-	struct dsa_switch_tree *dst = dsa_ptr;
-
-	return !!(dst->tag_protocol == htons(ETH_P_DSA));
-}
-
-bool dsa_uses_trailer_tags(void *dsa_ptr)
-{
-	struct dsa_switch_tree *dst = dsa_ptr;
-
-	return !!(dst->tag_protocol == htons(ETH_P_TRAILER));
-}
-
-
 /* link polling *************************************************************/
 static void dsa_link_poll_work(struct work_struct *ugly)
 {
@@ -419,12 +398,36 @@ static struct platform_driver dsa_driver = {
 
 static int __init dsa_init_module(void)
 {
-	return platform_driver_register(&dsa_driver);
+	int rc;
+
+	rc = platform_driver_register(&dsa_driver);
+	if (rc)
+		return rc;
+
+#ifdef CONFIG_NET_DSA_TAG_DSA
+	dev_add_pack(&dsa_packet_type);
+#endif
+#ifdef CONFIG_NET_DSA_TAG_EDSA
+	dev_add_pack(&edsa_packet_type);
+#endif
+#ifdef CONFIG_NET_DSA_TAG_TRAILER
+	dev_add_pack(&trailer_packet_type);
+#endif
+	return 0;
 }
 module_init(dsa_init_module);
 
 static void __exit dsa_cleanup_module(void)
 {
+#ifdef CONFIG_NET_DSA_TAG_TRAILER
+	dev_remove_pack(&trailer_packet_type);
+#endif
+#ifdef CONFIG_NET_DSA_TAG_EDSA
+	dev_remove_pack(&edsa_packet_type);
+#endif
+#ifdef CONFIG_NET_DSA_TAG_DSA
+	dev_remove_pack(&dsa_packet_type);
+#endif
 	platform_driver_unregister(&dsa_driver);
 }
 module_exit(dsa_cleanup_module);
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 4b0ea05..d4cf5cc 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -11,97 +11,9 @@
 #ifndef __DSA_PRIV_H
 #define __DSA_PRIV_H
 
-#include <linux/list.h>
 #include <linux/phy.h>
-#include <linux/timer.h>
-#include <linux/workqueue.h>
 #include <net/dsa.h>
 
-struct dsa_switch {
-	/*
-	 * Parent switch tree, and switch index.
-	 */
-	struct dsa_switch_tree	*dst;
-	int			index;
-
-	/*
-	 * Configuration data for this switch.
-	 */
-	struct dsa_chip_data	*pd;
-
-	/*
-	 * The used switch driver.
-	 */
-	struct dsa_switch_driver	*drv;
-
-	/*
-	 * Reference to mii bus to use.
-	 */
-	struct mii_bus		*master_mii_bus;
-
-	/*
-	 * Slave mii_bus and devices for the individual ports.
-	 */
-	u32			dsa_port_mask;
-	u32			phys_port_mask;
-	struct mii_bus		*slave_mii_bus;
-	struct net_device	*ports[DSA_MAX_PORTS];
-};
-
-struct dsa_switch_tree {
-	/*
-	 * Configuration data for the platform device that owns
-	 * this dsa switch tree instance.
-	 */
-	struct dsa_platform_data	*pd;
-
-	/*
-	 * Reference to network device to use, and which tagging
-	 * protocol to use.
-	 */
-	struct net_device	*master_netdev;
-	__be16			tag_protocol;
-
-	/*
-	 * The switch and port to which the CPU is attached.
-	 */
-	s8			cpu_switch;
-	s8			cpu_port;
-
-	/*
-	 * Link state polling.
-	 */
-	int			link_poll_needed;
-	struct work_struct	link_poll_work;
-	struct timer_list	link_poll_timer;
-
-	/*
-	 * Data for the individual switch chips.
-	 */
-	struct dsa_switch	*ds[DSA_MAX_SWITCHES];
-};
-
-static inline bool dsa_is_cpu_port(struct dsa_switch *ds, int p)
-{
-	return !!(ds->index == ds->dst->cpu_switch && p == ds->dst->cpu_port);
-}
-
-static inline u8 dsa_upstream_port(struct dsa_switch *ds)
-{
-	struct dsa_switch_tree *dst = ds->dst;
-
-	/*
-	 * If this is the root switch (i.e. the switch that connects
-	 * to the CPU), return the cpu port number on this switch.
-	 * Else return the (DSA) port number that connects to the
-	 * switch that is one hop closer to the cpu.
-	 */
-	if (dst->cpu_switch == ds->index)
-		return dst->cpu_port;
-	else
-		return ds->pd->rtable[dst->cpu_switch];
-}
-
 struct dsa_slave_priv {
 	/*
 	 * The linux network interface corresponding to this
@@ -123,44 +35,8 @@ struct dsa_slave_priv {
 	struct phy_device	*phy;
 };
 
-struct dsa_switch_driver {
-	struct list_head	list;
-
-	__be16			tag_protocol;
-	int			priv_size;
-
-	/*
-	 * Probing and setup.
-	 */
-	char	*(*probe)(struct mii_bus *bus, int sw_addr);
-	int	(*setup)(struct dsa_switch *ds);
-	int	(*set_addr)(struct dsa_switch *ds, u8 *addr);
-
-	/*
-	 * Access to the switch's PHY registers.
-	 */
-	int	(*phy_read)(struct dsa_switch *ds, int port, int regnum);
-	int	(*phy_write)(struct dsa_switch *ds, int port,
-			     int regnum, u16 val);
-
-	/*
-	 * Link state polling and IRQ handling.
-	 */
-	void	(*poll_link)(struct dsa_switch *ds);
-
-	/*
-	 * ethtool hardware statistics.
-	 */
-	void	(*get_strings)(struct dsa_switch *ds, int port, uint8_t *data);
-	void	(*get_ethtool_stats)(struct dsa_switch *ds,
-				     int port, uint64_t *data);
-	int	(*get_sset_count)(struct dsa_switch *ds);
-};
-
 /* dsa.c */
 extern char dsa_driver_version[];
-void register_switch_driver(struct dsa_switch_driver *type);
-void unregister_switch_driver(struct dsa_switch_driver *type);
 
 /* slave.c */
 void dsa_slave_mii_bus_init(struct dsa_switch *ds);
@@ -170,12 +46,15 @@ struct net_device *dsa_slave_create(struct dsa_switch *ds,
 
 /* tag_dsa.c */
 netdev_tx_t dsa_xmit(struct sk_buff *skb, struct net_device *dev);
+extern struct packet_type dsa_packet_type;
 
 /* tag_edsa.c */
 netdev_tx_t edsa_xmit(struct sk_buff *skb, struct net_device *dev);
+extern struct packet_type edsa_packet_type;
 
 /* tag_trailer.c */
 netdev_tx_t trailer_xmit(struct sk_buff *skb, struct net_device *dev);
+extern struct packet_type trailer_packet_type;
 
 
 #endif
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index 98dfe80..cacce1e 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -186,20 +186,7 @@ out:
 	return 0;
 }
 
-static struct packet_type dsa_packet_type __read_mostly = {
+struct packet_type dsa_packet_type __read_mostly = {
 	.type	= cpu_to_be16(ETH_P_DSA),
 	.func	= dsa_rcv,
 };
-
-static int __init dsa_init_module(void)
-{
-	dev_add_pack(&dsa_packet_type);
-	return 0;
-}
-module_init(dsa_init_module);
-
-static void __exit dsa_cleanup_module(void)
-{
-	dev_remove_pack(&dsa_packet_type);
-}
-module_exit(dsa_cleanup_module);
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
index 6f38332..e70c43c 100644
--- a/net/dsa/tag_edsa.c
+++ b/net/dsa/tag_edsa.c
@@ -205,20 +205,7 @@ out:
 	return 0;
 }
 
-static struct packet_type edsa_packet_type __read_mostly = {
+struct packet_type edsa_packet_type __read_mostly = {
 	.type	= cpu_to_be16(ETH_P_EDSA),
 	.func	= edsa_rcv,
 };
-
-static int __init edsa_init_module(void)
-{
-	dev_add_pack(&edsa_packet_type);
-	return 0;
-}
-module_init(edsa_init_module);
-
-static void __exit edsa_cleanup_module(void)
-{
-	dev_remove_pack(&edsa_packet_type);
-}
-module_exit(edsa_cleanup_module);
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index d6d7d0a..94bc260 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -114,20 +114,7 @@ out:
 	return 0;
 }
 
-static struct packet_type trailer_packet_type __read_mostly = {
+struct packet_type trailer_packet_type __read_mostly = {
 	.type	= cpu_to_be16(ETH_P_TRAILER),
 	.func	= trailer_rcv,
 };
-
-static int __init trailer_init_module(void)
-{
-	dev_add_pack(&trailer_packet_type);
-	return 0;
-}
-module_init(trailer_init_module);
-
-static void __exit trailer_cleanup_module(void)
-{
-	dev_remove_pack(&trailer_packet_type);
-}
-module_exit(trailer_cleanup_module);
diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c
index 1c1f26c..7e717cb 100644
--- a/net/econet/af_econet.c
+++ b/net/econet/af_econet.c
@@ -322,6 +322,7 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock,
 		/* Real hardware Econet.  We're not worthy etc. */
 #ifdef CONFIG_ECONET_NATIVE
 		unsigned short proto = 0;
+		int hlen, tlen;
 		int res;
 
 		if (len + 15 > dev->mtu) {
@@ -331,12 +332,14 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock,
 
 		dev_hold(dev);
 
-		skb = sock_alloc_send_skb(sk, len + LL_ALLOCATED_SPACE(dev),
+		hlen = LL_RESERVED_SPACE(dev);
+		tlen = dev->needed_tailroom;
+		skb = sock_alloc_send_skb(sk, len + hlen + tlen,
 					  msg->msg_flags & MSG_DONTWAIT, &err);
 		if (skb == NULL)
 			goto out_unlock;
 
-		skb_reserve(skb, LL_RESERVED_SPACE(dev));
+		skb_reserve(skb, hlen);
 		skb_reset_network_header(skb);
 
 		eb = (struct ec_cb *)&skb->cb;
diff --git a/net/ieee802154/6lowpan.c b/net/ieee802154/6lowpan.c
index 19d6aef..e4ecc1e 100644
--- a/net/ieee802154/6lowpan.c
+++ b/net/ieee802154/6lowpan.c
@@ -50,8 +50,6 @@
  * SUCH DAMAGE.
  */
 
-#define DEBUG
-
 #include <linux/bitops.h>
 #include <linux/if_arp.h>
 #include <linux/module.h>
@@ -113,6 +111,20 @@ struct lowpan_dev_record {
 	struct list_head list;
 };
 
+struct lowpan_fragment {
+	struct sk_buff		*skb;		/* skb to be assembled */
+	spinlock_t		lock;		/* concurency lock */
+	u16			length;		/* length to be assemled */
+	u32			bytes_rcv;	/* bytes received */
+	u16			tag;		/* current fragment tag */
+	struct timer_list	timer;		/* assembling timer */
+	struct list_head	list;		/* fragments list */
+};
+
+static unsigned short fragment_tag;
+static LIST_HEAD(lowpan_fragments);
+spinlock_t flist_lock;
+
 static inline struct
 lowpan_dev_info *lowpan_dev_info(const struct net_device *dev)
 {
@@ -234,6 +246,50 @@ lowpan_uncompress_addr(struct sk_buff *skb, struct in6_addr *ipaddr,
 	return 0;
 }
 
+static void
+lowpan_compress_udp_header(u8 **hc06_ptr, struct sk_buff *skb)
+{
+	struct udphdr *uh = udp_hdr(skb);
+
+	pr_debug("(%s): UDP header compression\n", __func__);
+
+	if (((uh->source & LOWPAN_NHC_UDP_4BIT_MASK) ==
+				LOWPAN_NHC_UDP_4BIT_PORT) &&
+	    ((uh->dest & LOWPAN_NHC_UDP_4BIT_MASK) ==
+				LOWPAN_NHC_UDP_4BIT_PORT)) {
+		pr_debug("(%s): both ports compression to 4 bits\n", __func__);
+		**hc06_ptr = LOWPAN_NHC_UDP_CS_P_11;
+		**(hc06_ptr + 1) = /* subtraction is faster */
+		   (u8)((uh->dest - LOWPAN_NHC_UDP_4BIT_PORT) +
+		       ((uh->source & LOWPAN_NHC_UDP_4BIT_PORT) << 4));
+		*hc06_ptr += 2;
+	} else if ((uh->dest & LOWPAN_NHC_UDP_8BIT_MASK) ==
+			LOWPAN_NHC_UDP_8BIT_PORT) {
+		pr_debug("(%s): remove 8 bits of dest\n", __func__);
+		**hc06_ptr = LOWPAN_NHC_UDP_CS_P_01;
+		memcpy(*hc06_ptr + 1, &uh->source, 2);
+		**(hc06_ptr + 3) = (u8)(uh->dest - LOWPAN_NHC_UDP_8BIT_PORT);
+		*hc06_ptr += 4;
+	} else if ((uh->source & LOWPAN_NHC_UDP_8BIT_MASK) ==
+			LOWPAN_NHC_UDP_8BIT_PORT) {
+		pr_debug("(%s): remove 8 bits of source\n", __func__);
+		**hc06_ptr = LOWPAN_NHC_UDP_CS_P_10;
+		memcpy(*hc06_ptr + 1, &uh->dest, 2);
+		**(hc06_ptr + 3) = (u8)(uh->source - LOWPAN_NHC_UDP_8BIT_PORT);
+		*hc06_ptr += 4;
+	} else {
+		pr_debug("(%s): can't compress header\n", __func__);
+		**hc06_ptr = LOWPAN_NHC_UDP_CS_P_00;
+		memcpy(*hc06_ptr + 1, &uh->source, 2);
+		memcpy(*hc06_ptr + 3, &uh->dest, 2);
+		*hc06_ptr += 5;
+	}
+
+	/* checksum is always inline */
+	memcpy(*hc06_ptr, &uh->check, 2);
+	*hc06_ptr += 2;
+}
+
 static u8 lowpan_fetch_skb_u8(struct sk_buff *skb)
 {
 	u8 ret;
@@ -244,6 +300,73 @@ static u8 lowpan_fetch_skb_u8(struct sk_buff *skb)
 	return ret;
 }
 
+static u16 lowpan_fetch_skb_u16(struct sk_buff *skb)
+{
+	u16 ret;
+
+	BUG_ON(!pskb_may_pull(skb, 2));
+
+	ret = skb->data[0] | (skb->data[1] << 8);
+	skb_pull(skb, 2);
+	return ret;
+}
+
+static int
+lowpan_uncompress_udp_header(struct sk_buff *skb)
+{
+	struct udphdr *uh = udp_hdr(skb);
+	u8 tmp;
+
+	tmp = lowpan_fetch_skb_u8(skb);
+
+	if ((tmp & LOWPAN_NHC_UDP_MASK) == LOWPAN_NHC_UDP_ID) {
+		pr_debug("(%s): UDP header uncompression\n", __func__);
+		switch (tmp & LOWPAN_NHC_UDP_CS_P_11) {
+		case LOWPAN_NHC_UDP_CS_P_00:
+			memcpy(&uh->source, &skb->data[0], 2);
+			memcpy(&uh->dest, &skb->data[2], 2);
+			skb_pull(skb, 4);
+			break;
+		case LOWPAN_NHC_UDP_CS_P_01:
+			memcpy(&uh->source, &skb->data[0], 2);
+			uh->dest =
+			   skb->data[2] + LOWPAN_NHC_UDP_8BIT_PORT;
+			skb_pull(skb, 3);
+			break;
+		case LOWPAN_NHC_UDP_CS_P_10:
+			uh->source = skb->data[0] + LOWPAN_NHC_UDP_8BIT_PORT;
+			memcpy(&uh->dest, &skb->data[1], 2);
+			skb_pull(skb, 3);
+			break;
+		case LOWPAN_NHC_UDP_CS_P_11:
+			uh->source =
+			   LOWPAN_NHC_UDP_4BIT_PORT + (skb->data[0] >> 4);
+			uh->dest =
+			   LOWPAN_NHC_UDP_4BIT_PORT + (skb->data[0] & 0x0f);
+			skb_pull(skb, 1);
+			break;
+		default:
+			pr_debug("(%s) ERROR: unknown UDP format\n", __func__);
+			goto err;
+			break;
+		}
+
+		pr_debug("(%s): uncompressed UDP ports: src = %d, dst = %d\n",
+					__func__, uh->source, uh->dest);
+
+		/* copy checksum */
+		memcpy(&uh->check, &skb->data[0], 2);
+		skb_pull(skb, 2);
+	} else {
+		pr_debug("(%s): ERROR: unsupported NH format\n", __func__);
+		goto err;
+	}
+
+	return 0;
+err:
+	return -EINVAL;
+}
+
 static int lowpan_header_create(struct sk_buff *skb,
 			   struct net_device *dev,
 			   unsigned short type, const void *_daddr,
@@ -342,8 +465,6 @@ static int lowpan_header_create(struct sk_buff *skb,
 	if (hdr->nexthdr == UIP_PROTO_UDP)
 		iphc0 |= LOWPAN_IPHC_NH_C;
 
-/* TODO: next header compression */
-
 	if ((iphc0 & LOWPAN_IPHC_NH_C) == 0) {
 		*hc06_ptr = hdr->nexthdr;
 		hc06_ptr += 1;
@@ -431,8 +552,9 @@ static int lowpan_header_create(struct sk_buff *skb,
 		}
 	}
 
-	/* TODO: UDP header compression */
-	/* TODO: Next Header compression */
+	/* UDP header compression */
+	if (hdr->nexthdr == UIP_PROTO_UDP)
+		lowpan_compress_udp_header(&hc06_ptr, skb);
 
 	head[0] = iphc0;
 	head[1] = iphc1;
@@ -467,6 +589,7 @@ static int lowpan_header_create(struct sk_buff *skb,
 		memcpy(&(sa.hwaddr), saddr, 8);
 
 		mac_cb(skb)->flags = IEEE802154_FC_TYPE_DATA;
+
 		return dev_hard_header(skb, lowpan_dev_info(dev)->real_dev,
 				type, (void *)&da, (void *)&sa, skb->len);
 	}
@@ -511,6 +634,21 @@ static int lowpan_skb_deliver(struct sk_buff *skb, struct ipv6hdr *hdr)
 	return stat;
 }
 
+static void lowpan_fragment_timer_expired(unsigned long entry_addr)
+{
+	struct lowpan_fragment *entry = (struct lowpan_fragment *)entry_addr;
+
+	pr_debug("%s: timer expired for frame with tag %d\n", __func__,
+								entry->tag);
+
+	spin_lock(&flist_lock);
+	list_del(&entry->list);
+	spin_unlock(&flist_lock);
+
+	dev_kfree_skb(entry->skb);
+	kfree(entry);
+}
+
 static int
 lowpan_process_data(struct sk_buff *skb)
 {
@@ -525,6 +663,107 @@ lowpan_process_data(struct sk_buff *skb)
 	if (skb->len < 2)
 		goto drop;
 	iphc0 = lowpan_fetch_skb_u8(skb);
+
+	/* fragments assembling */
+	switch (iphc0 & LOWPAN_DISPATCH_MASK) {
+	case LOWPAN_DISPATCH_FRAG1:
+	case LOWPAN_DISPATCH_FRAGN:
+	{
+		struct lowpan_fragment *frame;
+		u8 len, offset;
+		u16 tag;
+		bool found = false;
+
+		len = lowpan_fetch_skb_u8(skb); /* frame length */
+		tag = lowpan_fetch_skb_u16(skb);
+
+		/*
+		 * check if frame assembling with the same tag is
+		 * already in progress
+		 */
+		spin_lock(&flist_lock);
+
+		list_for_each_entry(frame, &lowpan_fragments, list)
+			if (frame->tag == tag) {
+				found = true;
+				break;
+			}
+
+		/* alloc new frame structure */
+		if (!found) {
+			frame = kzalloc(sizeof(struct lowpan_fragment),
+								GFP_ATOMIC);
+			if (!frame)
+				goto unlock_and_drop;
+
+			INIT_LIST_HEAD(&frame->list);
+
+			frame->length = (iphc0 & 7) | (len << 3);
+			frame->tag = tag;
+
+			/* allocate buffer for frame assembling */
+			frame->skb = alloc_skb(frame->length +
+					sizeof(struct ipv6hdr), GFP_ATOMIC);
+
+			if (!frame->skb) {
+				kfree(frame);
+				goto unlock_and_drop;
+			}
+
+			frame->skb->priority = skb->priority;
+			frame->skb->dev = skb->dev;
+
+			/* reserve headroom for uncompressed ipv6 header */
+			skb_reserve(frame->skb, sizeof(struct ipv6hdr));
+			skb_put(frame->skb, frame->length);
+
+			init_timer(&frame->timer);
+			/* time out is the same as for ipv6 - 60 sec */
+			frame->timer.expires = jiffies + LOWPAN_FRAG_TIMEOUT;
+			frame->timer.data = (unsigned long)frame;
+			frame->timer.function = lowpan_fragment_timer_expired;
+
+			add_timer(&frame->timer);
+
+			list_add_tail(&frame->list, &lowpan_fragments);
+		}
+
+		if ((iphc0 & LOWPAN_DISPATCH_MASK) == LOWPAN_DISPATCH_FRAG1)
+			goto unlock_and_drop;
+
+		offset = lowpan_fetch_skb_u8(skb); /* fetch offset */
+
+		/* if payload fits buffer, copy it */
+		if (likely((offset * 8 + skb->len) <= frame->length))
+			skb_copy_to_linear_data_offset(frame->skb, offset * 8,
+							skb->data, skb->len);
+		else
+			goto unlock_and_drop;
+
+		frame->bytes_rcv += skb->len;
+
+		/* frame assembling complete */
+		if ((frame->bytes_rcv == frame->length) &&
+		     frame->timer.expires > jiffies) {
+			/* if timer haven't expired - first of all delete it */
+			del_timer(&frame->timer);
+			list_del(&frame->list);
+			spin_unlock(&flist_lock);
+
+			dev_kfree_skb(skb);
+			skb = frame->skb;
+			kfree(frame);
+			iphc0 = lowpan_fetch_skb_u8(skb);
+			break;
+		}
+		spin_unlock(&flist_lock);
+
+		return kfree_skb(skb), 0;
+	}
+	default:
+		break;
+	}
+
 	iphc1 = lowpan_fetch_skb_u8(skb);
 
 	_saddr = mac_cb(skb)->sa.hwaddr;
@@ -659,7 +898,10 @@ lowpan_process_data(struct sk_buff *skb)
 			goto drop;
 	}
 
-	/* TODO: UDP header parse */
+	/* UDP data uncompression */
+	if (iphc0 & LOWPAN_IPHC_NH_C)
+		if (lowpan_uncompress_udp_header(skb))
+			goto drop;
 
 	/* Not fragmented package */
 	hdr.payload_len = htons(skb->len);
@@ -674,6 +916,9 @@ lowpan_process_data(struct sk_buff *skb)
 	lowpan_raw_dump_table(__func__, "raw header dump", (u8 *)&hdr,
 							sizeof(hdr));
 	return lowpan_skb_deliver(skb, &hdr);
+
+unlock_and_drop:
+	spin_unlock(&flist_lock);
 drop:
 	kfree_skb(skb);
 	return -EINVAL;
@@ -692,18 +937,115 @@ static int lowpan_set_address(struct net_device *dev, void *p)
 	return 0;
 }
 
+static int lowpan_get_mac_header_length(struct sk_buff *skb)
+{
+	/*
+	 * Currently long addressing mode is supported only, so the overall
+	 * header size is 21:
+	 * FC SeqNum DPAN DA  SA  Sec
+	 * 2  +  1  +  2 + 8 + 8 + 0  = 21
+	 */
+	return 21;
+}
+
+static int
+lowpan_fragment_xmit(struct sk_buff *skb, u8 *head,
+			int mlen, int plen, int offset)
+{
+	struct sk_buff *frag;
+	int hlen, ret;
+
+	/* if payload length is zero, therefore it's a first fragment */
+	hlen = (plen == 0 ? LOWPAN_FRAG1_HEAD_SIZE :  LOWPAN_FRAGN_HEAD_SIZE);
+
+	lowpan_raw_dump_inline(__func__, "6lowpan fragment header", head, hlen);
+
+	frag = dev_alloc_skb(hlen + mlen + plen + IEEE802154_MFR_SIZE);
+	if (!frag)
+		return -ENOMEM;
+
+	frag->priority = skb->priority;
+	frag->dev = skb->dev;
+
+	/* copy header, MFR and payload */
+	memcpy(skb_put(frag, mlen), skb->data, mlen);
+	memcpy(skb_put(frag, hlen), head, hlen);
+
+	if (plen)
+		skb_copy_from_linear_data_offset(skb, offset + mlen,
+					skb_put(frag, plen), plen);
+
+	lowpan_raw_dump_table(__func__, " raw fragment dump", frag->data,
+								frag->len);
+
+	ret = dev_queue_xmit(frag);
+
+	return ret;
+}
+
+static int
+lowpan_skb_fragmentation(struct sk_buff *skb)
+{
+	int  err, header_length, payload_length, tag, offset = 0;
+	u8 head[5];
+
+	header_length = lowpan_get_mac_header_length(skb);
+	payload_length = skb->len - header_length;
+	tag = fragment_tag++;
+
+	/* first fragment header */
+	head[0] = LOWPAN_DISPATCH_FRAG1 | (payload_length & 0x7);
+	head[1] = (payload_length >> 3) & 0xff;
+	head[2] = tag & 0xff;
+	head[3] = tag >> 8;
+
+	err = lowpan_fragment_xmit(skb, head, header_length, 0, 0);
+
+	/* next fragment header */
+	head[0] &= ~LOWPAN_DISPATCH_FRAG1;
+	head[0] |= LOWPAN_DISPATCH_FRAGN;
+
+	while ((payload_length - offset > 0) && (err >= 0)) {
+		int len = LOWPAN_FRAG_SIZE;
+
+		head[4] = offset / 8;
+
+		if (payload_length - offset < len)
+			len = payload_length - offset;
+
+		err = lowpan_fragment_xmit(skb, head, header_length,
+							len, offset);
+		offset += len;
+	}
+
+	return err;
+}
+
 static netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	int err = 0;
+	int err = -1;
 
 	pr_debug("(%s): package xmit\n", __func__);
 
 	skb->dev = lowpan_dev_info(dev)->real_dev;
 	if (skb->dev == NULL) {
 		pr_debug("(%s) ERROR: no real wpan device found\n", __func__);
-		dev_kfree_skb(skb);
-	} else
+		goto error;
+	}
+
+	if (skb->len <= IEEE802154_MTU) {
 		err = dev_queue_xmit(skb);
+		goto out;
+	}
+
+	pr_debug("(%s): frame is too big, fragmentation is needed\n",
+								__func__);
+	err = lowpan_skb_fragmentation(skb);
+error:
+	dev_kfree_skb(skb);
+out:
+	if (err < 0)
+		pr_debug("(%s): ERROR: xmit failed\n", __func__);
 
 	return (err < 0 ? NETDEV_TX_BUSY : NETDEV_TX_OK);
 }
@@ -730,13 +1072,12 @@ static void lowpan_setup(struct net_device *dev)
 	dev->addr_len		= IEEE802154_ADDR_LEN;
 	memset(dev->broadcast, 0xff, IEEE802154_ADDR_LEN);
 	dev->type		= ARPHRD_IEEE802154;
-	dev->features		= NETIF_F_NO_CSUM;
 	/* Frame Control + Sequence Number + Address fields + Security Header */
 	dev->hard_header_len	= 2 + 1 + 20 + 14;
 	dev->needed_tailroom	= 2; /* FCS */
 	dev->mtu		= 1281;
 	dev->tx_queue_len	= 0;
-	dev->flags		= IFF_NOARP | IFF_BROADCAST;
+	dev->flags		= IFF_BROADCAST | IFF_MULTICAST;
 	dev->watchdog_timeo	= 0;
 
 	dev->netdev_ops		= &lowpan_netdev_ops;
@@ -765,8 +1106,15 @@ static int lowpan_rcv(struct sk_buff *skb, struct net_device *dev,
 		goto drop;
 
 	/* check that it's our buffer */
-	if ((skb->data[0] & 0xe0) == 0x60)
+	switch (skb->data[0] & 0xe0) {
+	case LOWPAN_DISPATCH_IPHC:	/* ipv6 datagram */
+	case LOWPAN_DISPATCH_FRAG1:	/* first fragment header */
+	case LOWPAN_DISPATCH_FRAGN:	/* next fragments headers */
 		lowpan_process_data(skb);
+		break;
+	default:
+		break;
+	}
 
 	return NET_RX_SUCCESS;
 
diff --git a/net/ieee802154/6lowpan.h b/net/ieee802154/6lowpan.h
index 5d8cf80..aeff3f3 100644
--- a/net/ieee802154/6lowpan.h
+++ b/net/ieee802154/6lowpan.h
@@ -159,6 +159,24 @@
 #define LOWPAN_DISPATCH_FRAG1	0xc0 /* 11000xxx */
 #define LOWPAN_DISPATCH_FRAGN	0xe0 /* 11100xxx */
 
+#define LOWPAN_DISPATCH_MASK	0xf8 /* 11111000 */
+
+#define LOWPAN_FRAG_TIMEOUT	(HZ * 60)	/* time-out 60 sec */
+
+#define LOWPAN_FRAG1_HEAD_SIZE	0x4
+#define LOWPAN_FRAGN_HEAD_SIZE	0x5
+
+/*
+ * According IEEE802.15.4 standard:
+ *   - MTU is 127 octets
+ *   - maximum MHR size is 37 octets
+ *   - MFR size is 2 octets
+ *
+ * so minimal payload size that we may guarantee is:
+ *   MTU - MHR - MFR = 88 octets
+ */
+#define LOWPAN_FRAG_SIZE	88
+
 /*
  * Values of fields within the IPHC encoding first byte
  * (C stands for compressed and I for inline)
@@ -201,6 +219,11 @@
 #define LOWPAN_NHC_UDP_CHECKSUMC	0x04
 #define LOWPAN_NHC_UDP_CHECKSUMI	0x00
 
+#define LOWPAN_NHC_UDP_4BIT_PORT	0xF0B0
+#define LOWPAN_NHC_UDP_4BIT_MASK	0xFFF0
+#define LOWPAN_NHC_UDP_8BIT_PORT	0xF000
+#define LOWPAN_NHC_UDP_8BIT_MASK	0xFF00
+
 /* values for port compression, _with checksum_ ie bit 5 set to 0 */
 #define LOWPAN_NHC_UDP_CS_P_00	0xF0 /* all inline */
 #define LOWPAN_NHC_UDP_CS_P_01	0xF1 /* source 16bit inline,
diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c
index faecf64..1b09eaa 100644
--- a/net/ieee802154/dgram.c
+++ b/net/ieee802154/dgram.c
@@ -209,6 +209,7 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk,
 	unsigned mtu;
 	struct sk_buff *skb;
 	struct dgram_sock *ro = dgram_sk(sk);
+	int hlen, tlen;
 	int err;
 
 	if (msg->msg_flags & MSG_OOB) {
@@ -229,13 +230,15 @@ static int dgram_sendmsg(struct kiocb *iocb, struct sock *sk,
 	mtu = dev->mtu;
 	pr_debug("name = %s, mtu = %u\n", dev->name, mtu);
 
-	skb = sock_alloc_send_skb(sk, LL_ALLOCATED_SPACE(dev) + size,
+	hlen = LL_RESERVED_SPACE(dev);
+	tlen = dev->needed_tailroom;
+	skb = sock_alloc_send_skb(sk, hlen + tlen + size,
 			msg->msg_flags & MSG_DONTWAIT,
 			&err);
 	if (!skb)
 		goto out_dev;
 
-	skb_reserve(skb, LL_RESERVED_SPACE(dev));
+	skb_reserve(skb, hlen);
 
 	skb_reset_network_header(skb);
 
diff --git a/net/ieee802154/raw.c b/net/ieee802154/raw.c
index 10970ca..f96bae8 100644
--- a/net/ieee802154/raw.c
+++ b/net/ieee802154/raw.c
@@ -108,6 +108,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	struct net_device *dev;
 	unsigned mtu;
 	struct sk_buff *skb;
+	int hlen, tlen;
 	int err;
 
 	if (msg->msg_flags & MSG_OOB) {
@@ -137,12 +138,14 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		goto out_dev;
 	}
 
-	skb = sock_alloc_send_skb(sk, LL_ALLOCATED_SPACE(dev) + size,
+	hlen = LL_RESERVED_SPACE(dev);
+	tlen = dev->needed_tailroom;
+	skb = sock_alloc_send_skb(sk, hlen + tlen + size,
 			msg->msg_flags & MSG_DONTWAIT, &err);
 	if (!skb)
 		goto out_dev;
 
-	skb_reserve(skb, LL_RESERVED_SPACE(dev));
+	skb_reserve(skb, hlen);
 
 	skb_reset_mac_header(skb);
 	skb_reset_network_header(skb);
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index cbb505b..1a8f93b 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -409,6 +409,10 @@ config INET_TCP_DIAG
 	depends on INET_DIAG
 	def_tristate INET_DIAG
 
+config INET_UDP_DIAG
+	depends on INET_DIAG
+	def_tristate INET_DIAG && IPV6
+
 menuconfig TCP_CONG_ADVANCED
 	bool "TCP: advanced congestion control"
 	---help---
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index f2dc69c..ff75d3b 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -34,6 +34,7 @@ obj-$(CONFIG_IP_PNP) += ipconfig.o
 obj-$(CONFIG_NETFILTER)	+= netfilter.o netfilter/
 obj-$(CONFIG_INET_DIAG) += inet_diag.o 
 obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o
+obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o
 obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o
 obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o
 obj-$(CONFIG_TCP_CONG_CUBIC) += tcp_cubic.o
@@ -47,6 +48,7 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o
 obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o
 obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o
 obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o
+obj-$(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) += tcp_memcontrol.o
 obj-$(CONFIG_NETLABEL) += cipso_ipv4.o
 
 obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 1b5096a..f7b5670 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1250,7 +1250,8 @@ out:
 	return err;
 }
 
-static struct sk_buff *inet_gso_segment(struct sk_buff *skb, u32 features)
+static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
+	netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct iphdr *iph;
@@ -1572,9 +1573,9 @@ static __net_init int ipv4_mib_init_net(struct net *net)
 			  sizeof(struct icmp_mib),
 			  __alignof__(struct icmp_mib)) < 0)
 		goto err_icmp_mib;
-	if (snmp_mib_init((void __percpu **)net->mib.icmpmsg_statistics,
-			  sizeof(struct icmpmsg_mib),
-			  __alignof__(struct icmpmsg_mib)) < 0)
+	net->mib.icmpmsg_statistics = kzalloc(sizeof(struct icmpmsg_mib),
+					      GFP_KERNEL);
+	if (!net->mib.icmpmsg_statistics)
 		goto err_icmpmsg_mib;
 
 	tcp_mib_init(net);
@@ -1598,7 +1599,7 @@ err_tcp_mib:
 
 static __net_exit void ipv4_mib_exit_net(struct net *net)
 {
-	snmp_mib_free((void __percpu **)net->mib.icmpmsg_statistics);
+	kfree(net->mib.icmpmsg_statistics);
 	snmp_mib_free((void __percpu **)net->mib.icmp_statistics);
 	snmp_mib_free((void __percpu **)net->mib.udplite_statistics);
 	snmp_mib_free((void __percpu **)net->mib.udp_statistics);
@@ -1671,6 +1672,8 @@ static int __init inet_init(void)
 	ip_static_sysctl_init();
 #endif
 
+	tcp_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem;
+
 	/*
 	 *	Add all the base protocols.
 	 */
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index c1f4154..36d1440 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -136,8 +136,6 @@ static void ah_output_done(struct crypto_async_request *base, int err)
 		memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr));
 	}
 
-	err = ah->nexthdr;
-
 	kfree(AH_SKB_CB(skb)->tmp);
 	xfrm_output_resume(skb, err);
 }
@@ -264,12 +262,12 @@ static void ah_input_done(struct crypto_async_request *base, int err)
 	if (err)
 		goto out;
 
+	err = ah->nexthdr;
+
 	skb->network_header += ah_hlen;
 	memcpy(skb_network_header(skb), work_iph, ihl);
 	__skb_pull(skb, ah_hlen + ihl);
 	skb_set_transport_header(skb, -ihl);
-
-	err = ah->nexthdr;
 out:
 	kfree(AH_SKB_CB(skb)->tmp);
 	xfrm_input_resume(skb, err);
@@ -371,8 +369,6 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
 		if (err == -EINPROGRESS)
 			goto out;
 
-		if (err == -EBUSY)
-			err = NET_XMIT_DROP;
 		goto out_free;
 	}
 
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 96a164a..381a087 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -112,11 +112,6 @@
 #include <net/arp.h>
 #include <net/ax25.h>
 #include <net/netrom.h>
-#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE)
-#include <net/atmclip.h>
-struct neigh_table *clip_tbl_hook;
-EXPORT_SYMBOL(clip_tbl_hook);
-#endif
 
 #include <asm/system.h>
 #include <linux/uaccess.h>
@@ -164,7 +159,6 @@ static const struct neigh_ops arp_broken_ops = {
 
 struct neigh_table arp_tbl = {
 	.family		= AF_INET,
-	.entry_size	= sizeof(struct neighbour) + 4,
 	.key_len	= 4,
 	.hash		= arp_hash,
 	.constructor	= arp_constructor,
@@ -177,7 +171,7 @@ struct neigh_table arp_tbl = {
 		.gc_staletime		= 60 * HZ,
 		.reachable_time		= 30 * HZ,
 		.delay_probe_time	= 5 * HZ,
-		.queue_len		= 3,
+		.queue_len_bytes	= 64*1024,
 		.ucast_probes		= 3,
 		.mcast_probes		= 3,
 		.anycast_delay		= 1 * HZ,
@@ -283,9 +277,9 @@ static int arp_constructor(struct neighbour *neigh)
 		default:
 			break;
 		case ARPHRD_ROSE:
-#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
+#if IS_ENABLED(CONFIG_AX25)
 		case ARPHRD_AX25:
-#if defined(CONFIG_NETROM) || defined(CONFIG_NETROM_MODULE)
+#if IS_ENABLED(CONFIG_NETROM)
 		case ARPHRD_NETROM:
 #endif
 			neigh->ops = &arp_broken_ops;
@@ -592,16 +586,18 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
 	struct sk_buff *skb;
 	struct arphdr *arp;
 	unsigned char *arp_ptr;
+	int hlen = LL_RESERVED_SPACE(dev);
+	int tlen = dev->needed_tailroom;
 
 	/*
 	 *	Allocate a buffer
 	 */
 
-	skb = alloc_skb(arp_hdr_len(dev) + LL_ALLOCATED_SPACE(dev), GFP_ATOMIC);
+	skb = alloc_skb(arp_hdr_len(dev) + hlen + tlen, GFP_ATOMIC);
 	if (skb == NULL)
 		return NULL;
 
-	skb_reserve(skb, LL_RESERVED_SPACE(dev));
+	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
 	arp = (struct arphdr *) skb_put(skb, arp_hdr_len(dev));
 	skb->dev = dev;
@@ -633,13 +629,13 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
 		arp->ar_pro = htons(ETH_P_IP);
 		break;
 
-#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
+#if IS_ENABLED(CONFIG_AX25)
 	case ARPHRD_AX25:
 		arp->ar_hrd = htons(ARPHRD_AX25);
 		arp->ar_pro = htons(AX25_P_IP);
 		break;
 
-#if defined(CONFIG_NETROM) || defined(CONFIG_NETROM_MODULE)
+#if IS_ENABLED(CONFIG_NETROM)
 	case ARPHRD_NETROM:
 		arp->ar_hrd = htons(ARPHRD_NETROM);
 		arp->ar_pro = htons(AX25_P_IP);
@@ -647,13 +643,13 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
 #endif
 #endif
 
-#if defined(CONFIG_FDDI) || defined(CONFIG_FDDI_MODULE)
+#if IS_ENABLED(CONFIG_FDDI)
 	case ARPHRD_FDDI:
 		arp->ar_hrd = htons(ARPHRD_ETHER);
 		arp->ar_pro = htons(ETH_P_IP);
 		break;
 #endif
-#if defined(CONFIG_TR) || defined(CONFIG_TR_MODULE)
+#if IS_ENABLED(CONFIG_TR)
 	case ARPHRD_IEEE802_TR:
 		arp->ar_hrd = htons(ARPHRD_IEEE802);
 		arp->ar_pro = htons(ETH_P_IP);
@@ -1040,7 +1036,7 @@ static int arp_req_set(struct net *net, struct arpreq *r,
 			return -EINVAL;
 	}
 	switch (dev->type) {
-#if defined(CONFIG_FDDI) || defined(CONFIG_FDDI_MODULE)
+#if IS_ENABLED(CONFIG_FDDI)
 	case ARPHRD_FDDI:
 		/*
 		 * According to RFC 1390, FDDI devices should accept ARP
@@ -1286,7 +1282,7 @@ void __init arp_init(void)
 }
 
 #ifdef CONFIG_PROC_FS
-#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
+#if IS_ENABLED(CONFIG_AX25)
 
 /* ------------------------------------------------------------------------ */
 /*
@@ -1334,7 +1330,7 @@ static void arp_format_neigh_entry(struct seq_file *seq,
 
 	read_lock(&n->lock);
 	/* Convert hardware address to XX:XX:XX:XX ... form. */
-#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
+#if IS_ENABLED(CONFIG_AX25)
 	if (hatype == ARPHRD_AX25 || hatype == ARPHRD_NETROM)
 		ax2asc2((ax25_address *)n->ha, hbuffer);
 	else {
@@ -1347,7 +1343,7 @@ static void arp_format_neigh_entry(struct seq_file *seq,
 	if (k != 0)
 		--k;
 	hbuffer[k] = 0;
-#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
+#if IS_ENABLED(CONFIG_AX25)
 	}
 #endif
 	sprintf(tbuf, "%pI4", n->primary_key);
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index c6b5092..65f01dc 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1490,7 +1490,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write,
 			     void __user *buffer,
 			     size_t *lenp, loff_t *ppos)
 {
+	int old_value = *(int *)ctl->data;
 	int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+	int new_value = *(int *)ctl->data;
 
 	if (write) {
 		struct ipv4_devconf *cnf = ctl->extra1;
@@ -1501,6 +1503,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write,
 
 		if (cnf == net->ipv4.devconf_dflt)
 			devinet_copy_dflt_conf(net, i);
+		if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1)
+			if ((new_value == 0) && (old_value != 0))
+				rt_cache_flush(net, 0);
 	}
 
 	return ret;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index c7472ef..fa057d1 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -304,9 +304,11 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
 	struct igmpv3_report *pig;
 	struct net *net = dev_net(dev);
 	struct flowi4 fl4;
+	int hlen = LL_RESERVED_SPACE(dev);
+	int tlen = dev->needed_tailroom;
 
 	while (1) {
-		skb = alloc_skb(size + LL_ALLOCATED_SPACE(dev),
+		skb = alloc_skb(size + hlen + tlen,
 				GFP_ATOMIC | __GFP_NOWARN);
 		if (skb)
 			break;
@@ -327,7 +329,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
 	skb_dst_set(skb, &rt->dst);
 	skb->dev = dev;
 
-	skb_reserve(skb, LL_RESERVED_SPACE(dev));
+	skb_reserve(skb, hlen);
 
 	skb_reset_network_header(skb);
 	pip = ip_hdr(skb);
@@ -647,6 +649,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 	__be32	group = pmc ? pmc->multiaddr : 0;
 	struct flowi4 fl4;
 	__be32	dst;
+	int hlen, tlen;
 
 	if (type == IGMPV3_HOST_MEMBERSHIP_REPORT)
 		return igmpv3_send_report(in_dev, pmc);
@@ -661,7 +664,9 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 	if (IS_ERR(rt))
 		return -1;
 
-	skb = alloc_skb(IGMP_SIZE+LL_ALLOCATED_SPACE(dev), GFP_ATOMIC);
+	hlen = LL_RESERVED_SPACE(dev);
+	tlen = dev->needed_tailroom;
+	skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC);
 	if (skb == NULL) {
 		ip_rt_put(rt);
 		return -1;
@@ -669,7 +674,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
 
 	skb_dst_set(skb, &rt->dst);
 
-	skb_reserve(skb, LL_RESERVED_SPACE(dev));
+	skb_reserve(skb, hlen);
 
 	skb_reset_network_header(skb);
 	iph = ip_hdr(skb);
@@ -1574,7 +1579,7 @@ out_unlock:
  * Add multicast single-source filter to the interface list
  */
 static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode,
-	__be32 *psfsrc, int delta)
+	__be32 *psfsrc)
 {
 	struct ip_sf_list *psf, *psf_prev;
 
@@ -1709,14 +1714,15 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
 		pmc->sfcount[sfmode]++;
 	err = 0;
 	for (i=0; i<sfcount; i++) {
-		err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i], delta);
+		err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]);
 		if (err)
 			break;
 	}
 	if (err) {
 		int j;
 
-		pmc->sfcount[sfmode]--;
+		if (!delta)
+			pmc->sfcount[sfmode]--;
 		for (j=0; j<i; j++)
 			(void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]);
 	} else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) {
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index c14d88a..2e4e244 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -418,7 +418,7 @@ static inline u32 inet_synq_hash(const __be32 raddr, const __be16 rport,
 	return jhash_2words((__force u32)raddr, (__force u32)rport, rnd) & (synq_hsize - 1);
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 #define AF_INET_FAMILY(fam) ((fam) == AF_INET)
 #else
 #define AF_INET_FAMILY(fam) 1
@@ -588,10 +588,19 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
 }
 EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_prune);
 
-struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req,
-			    const gfp_t priority)
+/**
+ *	inet_csk_clone_lock - clone an inet socket, and lock its clone
+ *	@sk: the socket to clone
+ *	@req: request_sock
+ *	@priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
+ *
+ *	Caller must unlock socket even in error path (bh_unlock_sock(newsk))
+ */
+struct sock *inet_csk_clone_lock(const struct sock *sk,
+				 const struct request_sock *req,
+				 const gfp_t priority)
 {
-	struct sock *newsk = sk_clone(sk, priority);
+	struct sock *newsk = sk_clone_lock(sk, priority);
 
 	if (newsk != NULL) {
 		struct inet_connection_sock *newicsk = inet_csk(newsk);
@@ -615,7 +624,7 @@ struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req,
 	}
 	return newsk;
 }
-EXPORT_SYMBOL_GPL(inet_csk_clone);
+EXPORT_SYMBOL_GPL(inet_csk_clone_lock);
 
 /*
  * At this point, there should be no process reference to this
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index f5e2bda..fb2e47f 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -33,6 +33,7 @@
 #include <linux/stddef.h>
 
 #include <linux/inet_diag.h>
+#include <linux/sock_diag.h>
 
 static const struct inet_diag_handler **inet_diag_table;
 
@@ -45,24 +46,22 @@ struct inet_diag_entry {
 	u16 userlocks;
 };
 
-static struct sock *idiagnl;
-
 #define INET_DIAG_PUT(skb, attrtype, attrlen) \
 	RTA_DATA(__RTA_PUT(skb, attrtype, attrlen))
 
 static DEFINE_MUTEX(inet_diag_table_mutex);
 
-static const struct inet_diag_handler *inet_diag_lock_handler(int type)
+static const struct inet_diag_handler *inet_diag_lock_handler(int proto)
 {
-	if (!inet_diag_table[type])
-		request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
-			       NETLINK_INET_DIAG, type);
+	if (!inet_diag_table[proto])
+		request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK,
+			       NETLINK_SOCK_DIAG, AF_INET, proto);
 
 	mutex_lock(&inet_diag_table_mutex);
-	if (!inet_diag_table[type])
+	if (!inet_diag_table[proto])
 		return ERR_PTR(-ENOENT);
 
-	return inet_diag_table[type];
+	return inet_diag_table[proto];
 }
 
 static inline void inet_diag_unlock_handler(
@@ -71,21 +70,21 @@ static inline void inet_diag_unlock_handler(
 	mutex_unlock(&inet_diag_table_mutex);
 }
 
-static int inet_csk_diag_fill(struct sock *sk,
-			      struct sk_buff *skb,
-			      int ext, u32 pid, u32 seq, u16 nlmsg_flags,
+int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
+			      struct sk_buff *skb, struct inet_diag_req *req,
+			      u32 pid, u32 seq, u16 nlmsg_flags,
 			      const struct nlmsghdr *unlh)
 {
 	const struct inet_sock *inet = inet_sk(sk);
-	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct inet_diag_msg *r;
 	struct nlmsghdr  *nlh;
 	void *info = NULL;
 	struct inet_diag_meminfo  *minfo = NULL;
 	unsigned char	 *b = skb_tail_pointer(skb);
 	const struct inet_diag_handler *handler;
+	int ext = req->idiag_ext;
 
-	handler = inet_diag_table[unlh->nlmsg_type];
+	handler = inet_diag_table[req->sdiag_protocol];
 	BUG_ON(handler == NULL);
 
 	nlh = NLMSG_PUT(skb, pid, seq, unlh->nlmsg_type, sizeof(*r));
@@ -97,47 +96,51 @@ static int inet_csk_diag_fill(struct sock *sk,
 	if (ext & (1 << (INET_DIAG_MEMINFO - 1)))
 		minfo = INET_DIAG_PUT(skb, INET_DIAG_MEMINFO, sizeof(*minfo));
 
-	if (ext & (1 << (INET_DIAG_INFO - 1)))
-		info = INET_DIAG_PUT(skb, INET_DIAG_INFO,
-				     handler->idiag_info_size);
-
-	if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops) {
-		const size_t len = strlen(icsk->icsk_ca_ops->name);
-
-		strcpy(INET_DIAG_PUT(skb, INET_DIAG_CONG, len + 1),
-		       icsk->icsk_ca_ops->name);
-	}
-
-	if ((ext & (1 << (INET_DIAG_TOS - 1))) && (sk->sk_family != AF_INET6))
-		RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos);
-
 	r->idiag_family = sk->sk_family;
 	r->idiag_state = sk->sk_state;
 	r->idiag_timer = 0;
 	r->idiag_retrans = 0;
 
 	r->id.idiag_if = sk->sk_bound_dev_if;
-	r->id.idiag_cookie[0] = (u32)(unsigned long)sk;
-	r->id.idiag_cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1);
+	sock_diag_save_cookie(sk, r->id.idiag_cookie);
 
 	r->id.idiag_sport = inet->inet_sport;
 	r->id.idiag_dport = inet->inet_dport;
 	r->id.idiag_src[0] = inet->inet_rcv_saddr;
 	r->id.idiag_dst[0] = inet->inet_daddr;
 
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+	/* IPv6 dual-stack sockets use inet->tos for IPv4 connections,
+	 * hence this needs to be included regardless of socket family.
+	 */
+	if (ext & (1 << (INET_DIAG_TOS - 1)))
+		RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos);
+
+#if IS_ENABLED(CONFIG_IPV6)
 	if (r->idiag_family == AF_INET6) {
 		const struct ipv6_pinfo *np = inet6_sk(sk);
 
-		ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
-			       &np->rcv_saddr);
-		ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
-			       &np->daddr);
-		if (ext & (1 << (INET_DIAG_TOS - 1)))
-			RTA_PUT_U8(skb, INET_DIAG_TOS, np->tclass);
+		*(struct in6_addr *)r->id.idiag_src = np->rcv_saddr;
+		*(struct in6_addr *)r->id.idiag_dst = np->daddr;
+		if (ext & (1 << (INET_DIAG_TCLASS - 1)))
+			RTA_PUT_U8(skb, INET_DIAG_TCLASS, np->tclass);
 	}
 #endif
 
+	r->idiag_uid = sock_i_uid(sk);
+	r->idiag_inode = sock_i_ino(sk);
+
+	if (minfo) {
+		minfo->idiag_rmem = sk_rmem_alloc_get(sk);
+		minfo->idiag_wmem = sk->sk_wmem_queued;
+		minfo->idiag_fmem = sk->sk_forward_alloc;
+		minfo->idiag_tmem = sk_wmem_alloc_get(sk);
+	}
+
+	if (icsk == NULL) {
+		r->idiag_rqueue = r->idiag_wqueue = 0;
+		goto out;
+	}
+
 #define EXPIRES_IN_MS(tmo)  DIV_ROUND_UP((tmo - jiffies) * 1000, HZ)
 
 	if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
@@ -158,14 +161,14 @@ static int inet_csk_diag_fill(struct sock *sk,
 	}
 #undef EXPIRES_IN_MS
 
-	r->idiag_uid = sock_i_uid(sk);
-	r->idiag_inode = sock_i_ino(sk);
+	if (ext & (1 << (INET_DIAG_INFO - 1)))
+		info = INET_DIAG_PUT(skb, INET_DIAG_INFO, sizeof(struct tcp_info));
 
-	if (minfo) {
-		minfo->idiag_rmem = sk_rmem_alloc_get(sk);
-		minfo->idiag_wmem = sk->sk_wmem_queued;
-		minfo->idiag_fmem = sk->sk_forward_alloc;
-		minfo->idiag_tmem = sk_wmem_alloc_get(sk);
+	if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops) {
+		const size_t len = strlen(icsk->icsk_ca_ops->name);
+
+		strcpy(INET_DIAG_PUT(skb, INET_DIAG_CONG, len + 1),
+		       icsk->icsk_ca_ops->name);
 	}
 
 	handler->idiag_get_info(sk, r, info);
@@ -174,6 +177,7 @@ static int inet_csk_diag_fill(struct sock *sk,
 	    icsk->icsk_ca_ops && icsk->icsk_ca_ops->get_info)
 		icsk->icsk_ca_ops->get_info(sk, ext, skb);
 
+out:
 	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
 	return skb->len;
 
@@ -182,10 +186,20 @@ nlmsg_failure:
 	nlmsg_trim(skb, b);
 	return -EMSGSIZE;
 }
+EXPORT_SYMBOL_GPL(inet_sk_diag_fill);
+
+static int inet_csk_diag_fill(struct sock *sk,
+			      struct sk_buff *skb, struct inet_diag_req *req,
+			      u32 pid, u32 seq, u16 nlmsg_flags,
+			      const struct nlmsghdr *unlh)
+{
+	return inet_sk_diag_fill(sk, inet_csk(sk),
+			skb, req, pid, seq, nlmsg_flags, unlh);
+}
 
 static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
-			       struct sk_buff *skb, int ext, u32 pid,
-			       u32 seq, u16 nlmsg_flags,
+			       struct sk_buff *skb, struct inet_diag_req *req,
+			       u32 pid, u32 seq, u16 nlmsg_flags,
 			       const struct nlmsghdr *unlh)
 {
 	long tmo;
@@ -206,8 +220,7 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 	r->idiag_family	      = tw->tw_family;
 	r->idiag_retrans      = 0;
 	r->id.idiag_if	      = tw->tw_bound_dev_if;
-	r->id.idiag_cookie[0] = (u32)(unsigned long)tw;
-	r->id.idiag_cookie[1] = (u32)(((unsigned long)tw >> 31) >> 1);
+	sock_diag_save_cookie(tw, r->id.idiag_cookie);
 	r->id.idiag_sport     = tw->tw_sport;
 	r->id.idiag_dport     = tw->tw_dport;
 	r->id.idiag_src[0]    = tw->tw_rcv_saddr;
@@ -219,15 +232,13 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
 	r->idiag_wqueue	      = 0;
 	r->idiag_uid	      = 0;
 	r->idiag_inode	      = 0;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	if (tw->tw_family == AF_INET6) {
 		const struct inet6_timewait_sock *tw6 =
 						inet6_twsk((struct sock *)tw);
 
-		ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
-			       &tw6->tw_v6_rcv_saddr);
-		ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
-			       &tw6->tw_v6_daddr);
+		*(struct in6_addr *)r->id.idiag_src = tw6->tw_v6_rcv_saddr;
+		*(struct in6_addr *)r->id.idiag_dst = tw6->tw_v6_daddr;
 	}
 #endif
 	nlh->nlmsg_len = skb_tail_pointer(skb) - previous_tail;
@@ -238,42 +249,31 @@ nlmsg_failure:
 }
 
 static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
-			int ext, u32 pid, u32 seq, u16 nlmsg_flags,
+			struct inet_diag_req *r, u32 pid, u32 seq, u16 nlmsg_flags,
 			const struct nlmsghdr *unlh)
 {
 	if (sk->sk_state == TCP_TIME_WAIT)
 		return inet_twsk_diag_fill((struct inet_timewait_sock *)sk,
-					   skb, ext, pid, seq, nlmsg_flags,
+					   skb, r, pid, seq, nlmsg_flags,
 					   unlh);
-	return inet_csk_diag_fill(sk, skb, ext, pid, seq, nlmsg_flags, unlh);
+	return inet_csk_diag_fill(sk, skb, r, pid, seq, nlmsg_flags, unlh);
 }
 
-static int inet_diag_get_exact(struct sk_buff *in_skb,
-			       const struct nlmsghdr *nlh)
+int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb,
+		const struct nlmsghdr *nlh, struct inet_diag_req *req)
 {
 	int err;
 	struct sock *sk;
-	struct inet_diag_req *req = NLMSG_DATA(nlh);
 	struct sk_buff *rep;
-	struct inet_hashinfo *hashinfo;
-	const struct inet_diag_handler *handler;
-
-	handler = inet_diag_lock_handler(nlh->nlmsg_type);
-	if (IS_ERR(handler)) {
-		err = PTR_ERR(handler);
-		goto unlock;
-	}
 
-	hashinfo = handler->idiag_hashinfo;
 	err = -EINVAL;
-
-	if (req->idiag_family == AF_INET) {
+	if (req->sdiag_family == AF_INET) {
 		sk = inet_lookup(&init_net, hashinfo, req->id.idiag_dst[0],
 				 req->id.idiag_dport, req->id.idiag_src[0],
 				 req->id.idiag_sport, req->id.idiag_if);
 	}
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
-	else if (req->idiag_family == AF_INET6) {
+#if IS_ENABLED(CONFIG_IPV6)
+	else if (req->sdiag_family == AF_INET6) {
 		sk = inet6_lookup(&init_net, hashinfo,
 				  (struct in6_addr *)req->id.idiag_dst,
 				  req->id.idiag_dport,
@@ -283,29 +283,26 @@ static int inet_diag_get_exact(struct sk_buff *in_skb,
 	}
 #endif
 	else {
-		goto unlock;
+		goto out_nosk;
 	}
 
 	err = -ENOENT;
 	if (sk == NULL)
-		goto unlock;
+		goto out_nosk;
 
-	err = -ESTALE;
-	if ((req->id.idiag_cookie[0] != INET_DIAG_NOCOOKIE ||
-	     req->id.idiag_cookie[1] != INET_DIAG_NOCOOKIE) &&
-	    ((u32)(unsigned long)sk != req->id.idiag_cookie[0] ||
-	     (u32)((((unsigned long)sk) >> 31) >> 1) != req->id.idiag_cookie[1]))
+	err = sock_diag_check_cookie(sk, req->id.idiag_cookie);
+	if (err)
 		goto out;
 
 	err = -ENOMEM;
 	rep = alloc_skb(NLMSG_SPACE((sizeof(struct inet_diag_msg) +
 				     sizeof(struct inet_diag_meminfo) +
-				     handler->idiag_info_size + 64)),
+				     sizeof(struct tcp_info) + 64)),
 			GFP_KERNEL);
 	if (!rep)
 		goto out;
 
-	err = sk_diag_fill(sk, rep, req->idiag_ext,
+	err = sk_diag_fill(sk, rep, req,
 			   NETLINK_CB(in_skb).pid,
 			   nlh->nlmsg_seq, 0, nlh);
 	if (err < 0) {
@@ -313,7 +310,7 @@ static int inet_diag_get_exact(struct sk_buff *in_skb,
 		kfree_skb(rep);
 		goto out;
 	}
-	err = netlink_unicast(idiagnl, rep, NETLINK_CB(in_skb).pid,
+	err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid,
 			      MSG_DONTWAIT);
 	if (err > 0)
 		err = 0;
@@ -325,8 +322,25 @@ out:
 		else
 			sock_put(sk);
 	}
-unlock:
+out_nosk:
+	return err;
+}
+EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk);
+
+static int inet_diag_get_exact(struct sk_buff *in_skb,
+			       const struct nlmsghdr *nlh,
+			       struct inet_diag_req *req)
+{
+	const struct inet_diag_handler *handler;
+	int err;
+
+	handler = inet_diag_lock_handler(req->sdiag_protocol);
+	if (IS_ERR(handler))
+		err = PTR_ERR(handler);
+	else
+		err = handler->dump_one(in_skb, nlh, req);
 	inet_diag_unlock_handler(handler);
+
 	return err;
 }
 
@@ -357,9 +371,12 @@ static int bitstring_match(const __be32 *a1, const __be32 *a2, int bits)
 }
 
 
-static int inet_diag_bc_run(const void *bc, int len,
-			    const struct inet_diag_entry *entry)
+static int inet_diag_bc_run(const struct nlattr *_bc,
+		const struct inet_diag_entry *entry)
 {
+	const void *bc = nla_data(_bc);
+	int len = nla_len(_bc);
+
 	while (len > 0) {
 		int yes = 1;
 		const struct inet_diag_bc_op *op = bc;
@@ -433,6 +450,35 @@ static int inet_diag_bc_run(const void *bc, int len,
 	return len == 0;
 }
 
+int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk)
+{
+	struct inet_diag_entry entry;
+	struct inet_sock *inet = inet_sk(sk);
+
+	if (bc == NULL)
+		return 1;
+
+	entry.family = sk->sk_family;
+#if IS_ENABLED(CONFIG_IPV6)
+	if (entry.family == AF_INET6) {
+		struct ipv6_pinfo *np = inet6_sk(sk);
+
+		entry.saddr = np->rcv_saddr.s6_addr32;
+		entry.daddr = np->daddr.s6_addr32;
+	} else
+#endif
+	{
+		entry.saddr = &inet->inet_rcv_saddr;
+		entry.daddr = &inet->inet_daddr;
+	}
+	entry.sport = inet->inet_num;
+	entry.dport = ntohs(inet->inet_dport);
+	entry.userlocks = sk->sk_userlocks;
+
+	return inet_diag_bc_run(bc, &entry);
+}
+EXPORT_SYMBOL_GPL(inet_diag_bc_sk);
+
 static int valid_cc(const void *bc, int len, int cc)
 {
 	while (len >= 0) {
@@ -489,57 +535,29 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
 
 static int inet_csk_diag_dump(struct sock *sk,
 			      struct sk_buff *skb,
-			      struct netlink_callback *cb)
+			      struct netlink_callback *cb,
+			      struct inet_diag_req *r,
+			      const struct nlattr *bc)
 {
-	struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
-
-	if (nlmsg_attrlen(cb->nlh, sizeof(*r))) {
-		struct inet_diag_entry entry;
-		const struct nlattr *bc = nlmsg_find_attr(cb->nlh,
-							  sizeof(*r),
-							  INET_DIAG_REQ_BYTECODE);
-		struct inet_sock *inet = inet_sk(sk);
-
-		entry.family = sk->sk_family;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
-		if (entry.family == AF_INET6) {
-			struct ipv6_pinfo *np = inet6_sk(sk);
-
-			entry.saddr = np->rcv_saddr.s6_addr32;
-			entry.daddr = np->daddr.s6_addr32;
-		} else
-#endif
-		{
-			entry.saddr = &inet->inet_rcv_saddr;
-			entry.daddr = &inet->inet_daddr;
-		}
-		entry.sport = inet->inet_num;
-		entry.dport = ntohs(inet->inet_dport);
-		entry.userlocks = sk->sk_userlocks;
+	if (!inet_diag_bc_sk(bc, sk))
+		return 0;
 
-		if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry))
-			return 0;
-	}
-
-	return inet_csk_diag_fill(sk, skb, r->idiag_ext,
+	return inet_csk_diag_fill(sk, skb, r,
 				  NETLINK_CB(cb->skb).pid,
 				  cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
 }
 
 static int inet_twsk_diag_dump(struct inet_timewait_sock *tw,
 			       struct sk_buff *skb,
-			       struct netlink_callback *cb)
+			       struct netlink_callback *cb,
+			       struct inet_diag_req *r,
+			       const struct nlattr *bc)
 {
-	struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
-
-	if (nlmsg_attrlen(cb->nlh, sizeof(*r))) {
+	if (bc != NULL) {
 		struct inet_diag_entry entry;
-		const struct nlattr *bc = nlmsg_find_attr(cb->nlh,
-							  sizeof(*r),
-							  INET_DIAG_REQ_BYTECODE);
 
 		entry.family = tw->tw_family;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == AF_INET6) {
 			struct inet6_timewait_sock *tw6 =
 						inet6_twsk((struct sock *)tw);
@@ -555,11 +573,11 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw,
 		entry.dport = ntohs(tw->tw_dport);
 		entry.userlocks = 0;
 
-		if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry))
+		if (!inet_diag_bc_run(bc, &entry))
 			return 0;
 	}
 
-	return inet_twsk_diag_fill(tw, skb, r->idiag_ext,
+	return inet_twsk_diag_fill(tw, skb, r,
 				   NETLINK_CB(cb->skb).pid,
 				   cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
 }
@@ -585,8 +603,7 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
 	r->idiag_retrans = req->retrans;
 
 	r->id.idiag_if = sk->sk_bound_dev_if;
-	r->id.idiag_cookie[0] = (u32)(unsigned long)req;
-	r->id.idiag_cookie[1] = (u32)(((unsigned long)req >> 31) >> 1);
+	sock_diag_save_cookie(req, r->id.idiag_cookie);
 
 	tmo = req->expires - jiffies;
 	if (tmo < 0)
@@ -601,12 +618,10 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
 	r->idiag_wqueue = 0;
 	r->idiag_uid = sock_i_uid(sk);
 	r->idiag_inode = 0;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	if (r->idiag_family == AF_INET6) {
-		ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
-			       &inet6_rsk(req)->loc_addr);
-		ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
-			       &inet6_rsk(req)->rmt_addr);
+		*(struct in6_addr *)r->id.idiag_src = inet6_rsk(req)->loc_addr;
+		*(struct in6_addr *)r->id.idiag_dst = inet6_rsk(req)->rmt_addr;
 	}
 #endif
 	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
@@ -619,13 +634,13 @@ nlmsg_failure:
 }
 
 static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
-			       struct netlink_callback *cb)
+			       struct netlink_callback *cb,
+			       struct inet_diag_req *r,
+			       const struct nlattr *bc)
 {
 	struct inet_diag_entry entry;
-	struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct listen_sock *lopt;
-	const struct nlattr *bc = NULL;
 	struct inet_sock *inet = inet_sk(sk);
 	int j, s_j;
 	int reqnum, s_reqnum;
@@ -645,9 +660,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
 	if (!lopt || !lopt->qlen)
 		goto out;
 
-	if (nlmsg_attrlen(cb->nlh, sizeof(*r))) {
-		bc = nlmsg_find_attr(cb->nlh, sizeof(*r),
-				     INET_DIAG_REQ_BYTECODE);
+	if (bc != NULL) {
 		entry.sport = inet->inet_num;
 		entry.userlocks = sk->sk_userlocks;
 	}
@@ -667,21 +680,20 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
 
 			if (bc) {
 				entry.saddr =
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 					(entry.family == AF_INET6) ?
 					inet6_rsk(req)->loc_addr.s6_addr32 :
 #endif
 					&ireq->loc_addr;
 				entry.daddr =
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 					(entry.family == AF_INET6) ?
 					inet6_rsk(req)->rmt_addr.s6_addr32 :
 #endif
 					&ireq->rmt_addr;
 				entry.dport = ntohs(ireq->rmt_port);
 
-				if (!inet_diag_bc_run(nla_data(bc),
-						      nla_len(bc), &entry))
+				if (!inet_diag_bc_run(bc, &entry))
 					continue;
 			}
 
@@ -704,19 +716,11 @@ out:
 	return err;
 }
 
-static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
+void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb,
+		struct netlink_callback *cb, struct inet_diag_req *r, struct nlattr *bc)
 {
 	int i, num;
 	int s_i, s_num;
-	struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
-	const struct inet_diag_handler *handler;
-	struct inet_hashinfo *hashinfo;
-
-	handler = inet_diag_lock_handler(cb->nlh->nlmsg_type);
-	if (IS_ERR(handler))
-		goto unlock;
-
-	hashinfo = handler->idiag_hashinfo;
 
 	s_i = cb->args[1];
 	s_num = num = cb->args[2];
@@ -741,6 +745,10 @@ static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 					continue;
 				}
 
+				if (r->sdiag_family != AF_UNSPEC &&
+						sk->sk_family != r->sdiag_family)
+					goto next_listen;
+
 				if (r->id.idiag_sport != inet->inet_sport &&
 				    r->id.idiag_sport)
 					goto next_listen;
@@ -750,7 +758,7 @@ static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 				    cb->args[3] > 0)
 					goto syn_recv;
 
-				if (inet_csk_diag_dump(sk, skb, cb) < 0) {
+				if (inet_csk_diag_dump(sk, skb, cb, r, bc) < 0) {
 					spin_unlock_bh(&ilb->lock);
 					goto done;
 				}
@@ -759,7 +767,7 @@ syn_recv:
 				if (!(r->idiag_states & TCPF_SYN_RECV))
 					goto next_listen;
 
-				if (inet_diag_dump_reqs(skb, sk, cb) < 0) {
+				if (inet_diag_dump_reqs(skb, sk, cb, r, bc) < 0) {
 					spin_unlock_bh(&ilb->lock);
 					goto done;
 				}
@@ -781,7 +789,7 @@ skip_listen_ht:
 	}
 
 	if (!(r->idiag_states & ~(TCPF_LISTEN | TCPF_SYN_RECV)))
-		goto unlock;
+		goto out;
 
 	for (i = s_i; i <= hashinfo->ehash_mask; i++) {
 		struct inet_ehash_bucket *head = &hashinfo->ehash[i];
@@ -806,13 +814,16 @@ skip_listen_ht:
 				goto next_normal;
 			if (!(r->idiag_states & (1 << sk->sk_state)))
 				goto next_normal;
+			if (r->sdiag_family != AF_UNSPEC &&
+					sk->sk_family != r->sdiag_family)
+				goto next_normal;
 			if (r->id.idiag_sport != inet->inet_sport &&
 			    r->id.idiag_sport)
 				goto next_normal;
 			if (r->id.idiag_dport != inet->inet_dport &&
 			    r->id.idiag_dport)
 				goto next_normal;
-			if (inet_csk_diag_dump(sk, skb, cb) < 0) {
+			if (inet_csk_diag_dump(sk, skb, cb, r, bc) < 0) {
 				spin_unlock_bh(lock);
 				goto done;
 			}
@@ -828,13 +839,16 @@ next_normal:
 
 				if (num < s_num)
 					goto next_dying;
+				if (r->sdiag_family != AF_UNSPEC &&
+						tw->tw_family != r->sdiag_family)
+					goto next_dying;
 				if (r->id.idiag_sport != tw->tw_sport &&
 				    r->id.idiag_sport)
 					goto next_dying;
 				if (r->id.idiag_dport != tw->tw_dport &&
 				    r->id.idiag_dport)
 					goto next_dying;
-				if (inet_twsk_diag_dump(tw, skb, cb) < 0) {
+				if (inet_twsk_diag_dump(tw, skb, cb, r, bc) < 0) {
 					spin_unlock_bh(lock);
 					goto done;
 				}
@@ -848,15 +862,85 @@ next_dying:
 done:
 	cb->args[1] = i;
 	cb->args[2] = num;
-unlock:
+out:
+	;
+}
+EXPORT_SYMBOL_GPL(inet_diag_dump_icsk);
+
+static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
+		struct inet_diag_req *r, struct nlattr *bc)
+{
+	const struct inet_diag_handler *handler;
+
+	handler = inet_diag_lock_handler(r->sdiag_protocol);
+	if (!IS_ERR(handler))
+		handler->dump(skb, cb, r, bc);
 	inet_diag_unlock_handler(handler);
+
 	return skb->len;
 }
 
-static int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
+	struct nlattr *bc = NULL;
 	int hdrlen = sizeof(struct inet_diag_req);
 
+	if (nlmsg_attrlen(cb->nlh, hdrlen))
+		bc = nlmsg_find_attr(cb->nlh, hdrlen, INET_DIAG_REQ_BYTECODE);
+
+	return __inet_diag_dump(skb, cb, (struct inet_diag_req *)NLMSG_DATA(cb->nlh), bc);
+}
+
+static inline int inet_diag_type2proto(int type)
+{
+	switch (type) {
+	case TCPDIAG_GETSOCK:
+		return IPPROTO_TCP;
+	case DCCPDIAG_GETSOCK:
+		return IPPROTO_DCCP;
+	default:
+		return 0;
+	}
+}
+
+static int inet_diag_dump_compat(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct inet_diag_req_compat *rc = NLMSG_DATA(cb->nlh);
+	struct inet_diag_req req;
+	struct nlattr *bc = NULL;
+	int hdrlen = sizeof(struct inet_diag_req_compat);
+
+	req.sdiag_family = AF_UNSPEC; /* compatibility */
+	req.sdiag_protocol = inet_diag_type2proto(cb->nlh->nlmsg_type);
+	req.idiag_ext = rc->idiag_ext;
+	req.idiag_states = rc->idiag_states;
+	req.id = rc->id;
+
+	if (nlmsg_attrlen(cb->nlh, hdrlen))
+		bc = nlmsg_find_attr(cb->nlh, hdrlen, INET_DIAG_REQ_BYTECODE);
+
+	return __inet_diag_dump(skb, cb, &req, bc);
+}
+
+static int inet_diag_get_exact_compat(struct sk_buff *in_skb,
+			       const struct nlmsghdr *nlh)
+{
+	struct inet_diag_req_compat *rc = NLMSG_DATA(nlh);
+	struct inet_diag_req req;
+
+	req.sdiag_family = rc->idiag_family;
+	req.sdiag_protocol = inet_diag_type2proto(nlh->nlmsg_type);
+	req.idiag_ext = rc->idiag_ext;
+	req.idiag_states = rc->idiag_states;
+	req.id = rc->id;
+
+	return inet_diag_get_exact(in_skb, nlh, &req);
+}
+
+static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	int hdrlen = sizeof(struct inet_diag_req_compat);
+
 	if (nlh->nlmsg_type >= INET_DIAG_GETSOCK_MAX ||
 	    nlmsg_len(nlh) < hdrlen)
 		return -EINVAL;
@@ -873,28 +957,54 @@ static int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 				return -EINVAL;
 		}
 
-		return netlink_dump_start(idiagnl, skb, nlh,
-					  inet_diag_dump, NULL, 0);
+		return netlink_dump_start(sock_diag_nlsk, skb, nlh,
+					  inet_diag_dump_compat, NULL, 0);
 	}
 
-	return inet_diag_get_exact(skb, nlh);
+	return inet_diag_get_exact_compat(skb, nlh);
 }
 
-static DEFINE_MUTEX(inet_diag_mutex);
-
-static void inet_diag_rcv(struct sk_buff *skb)
+static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
 {
-	mutex_lock(&inet_diag_mutex);
-	netlink_rcv_skb(skb, &inet_diag_rcv_msg);
-	mutex_unlock(&inet_diag_mutex);
+	int hdrlen = sizeof(struct inet_diag_req);
+
+	if (nlmsg_len(h) < hdrlen)
+		return -EINVAL;
+
+	if (h->nlmsg_flags & NLM_F_DUMP) {
+		if (nlmsg_attrlen(h, hdrlen)) {
+			struct nlattr *attr;
+			attr = nlmsg_find_attr(h, hdrlen,
+					       INET_DIAG_REQ_BYTECODE);
+			if (attr == NULL ||
+			    nla_len(attr) < sizeof(struct inet_diag_bc_op) ||
+			    inet_diag_bc_audit(nla_data(attr), nla_len(attr)))
+				return -EINVAL;
+		}
+
+		return netlink_dump_start(sock_diag_nlsk, skb, h,
+					  inet_diag_dump, NULL, 0);
+	}
+
+	return inet_diag_get_exact(skb, h, (struct inet_diag_req *)NLMSG_DATA(h));
 }
 
+static struct sock_diag_handler inet_diag_handler = {
+	.family = AF_INET,
+	.dump = inet_diag_handler_dump,
+};
+
+static struct sock_diag_handler inet6_diag_handler = {
+	.family = AF_INET6,
+	.dump = inet_diag_handler_dump,
+};
+
 int inet_diag_register(const struct inet_diag_handler *h)
 {
 	const __u16 type = h->idiag_type;
 	int err = -EINVAL;
 
-	if (type >= INET_DIAG_GETSOCK_MAX)
+	if (type >= IPPROTO_MAX)
 		goto out;
 
 	mutex_lock(&inet_diag_table_mutex);
@@ -913,7 +1023,7 @@ void inet_diag_unregister(const struct inet_diag_handler *h)
 {
 	const __u16 type = h->idiag_type;
 
-	if (type >= INET_DIAG_GETSOCK_MAX)
+	if (type >= IPPROTO_MAX)
 		return;
 
 	mutex_lock(&inet_diag_table_mutex);
@@ -924,7 +1034,7 @@ EXPORT_SYMBOL_GPL(inet_diag_unregister);
 
 static int __init inet_diag_init(void)
 {
-	const int inet_diag_table_size = (INET_DIAG_GETSOCK_MAX *
+	const int inet_diag_table_size = (IPPROTO_MAX *
 					  sizeof(struct inet_diag_handler *));
 	int err = -ENOMEM;
 
@@ -932,25 +1042,35 @@ static int __init inet_diag_init(void)
 	if (!inet_diag_table)
 		goto out;
 
-	idiagnl = netlink_kernel_create(&init_net, NETLINK_INET_DIAG, 0,
-					inet_diag_rcv, NULL, THIS_MODULE);
-	if (idiagnl == NULL)
-		goto out_free_table;
-	err = 0;
+	err = sock_diag_register(&inet_diag_handler);
+	if (err)
+		goto out_free_nl;
+
+	err = sock_diag_register(&inet6_diag_handler);
+	if (err)
+		goto out_free_inet;
+
+	sock_diag_register_inet_compat(inet_diag_rcv_msg_compat);
 out:
 	return err;
-out_free_table:
+
+out_free_inet:
+	sock_diag_unregister(&inet_diag_handler);
+out_free_nl:
 	kfree(inet_diag_table);
 	goto out;
 }
 
 static void __exit inet_diag_exit(void)
 {
-	netlink_kernel_release(idiagnl);
+	sock_diag_unregister(&inet6_diag_handler);
+	sock_diag_unregister(&inet_diag_handler);
+	sock_diag_unregister_inet_compat(inet_diag_rcv_msg_compat);
 	kfree(inet_diag_table);
 }
 
 module_init(inet_diag_init);
 module_exit(inet_diag_exit);
 MODULE_LICENSE("GPL");
-MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_INET_DIAG);
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2 /* AF_INET */);
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10 /* AF_INET6 */);
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 3b34d1c..29a07b6 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -84,7 +84,7 @@ int ip_forward(struct sk_buff *skb)
 
 	rt = skb_rtable(skb);
 
-	if (opt->is_strictroute && ip_hdr(skb)->daddr != rt->rt_gateway)
+	if (opt->is_strictroute && opt->nexthop != rt->rt_gateway)
 		goto sr_failed;
 
 	if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index d55110e..2b53a1f 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -46,7 +46,7 @@
 #include <net/rtnetlink.h>
 #include <net/gre.h>
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 #include <net/ipv6.h>
 #include <net/ip6_fib.h>
 #include <net/ip6_route.h>
@@ -171,7 +171,7 @@ struct pcpu_tstats {
 	unsigned long	rx_bytes;
 	unsigned long	tx_packets;
 	unsigned long	tx_bytes;
-};
+} __attribute__((aligned(4*sizeof(unsigned long))));
 
 static struct net_device_stats *ipgre_get_stats(struct net_device *dev)
 {
@@ -729,9 +729,9 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 			if ((dst = rt->rt_gateway) == 0)
 				goto tx_error_icmp;
 		}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		else if (skb->protocol == htons(ETH_P_IPV6)) {
-			struct neighbour *neigh = dst_get_neighbour(skb_dst(skb));
+			struct neighbour *neigh = dst_get_neighbour_noref(skb_dst(skb));
 			const struct in6_addr *addr6;
 			int addr_type;
 
@@ -799,7 +799,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 			goto tx_error;
 		}
 	}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	else if (skb->protocol == htons(ETH_P_IPV6)) {
 		struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
 
@@ -835,6 +835,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 	if (skb_headroom(skb) < max_headroom || skb_shared(skb)||
 	    (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
 		struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
+		if (max_headroom > dev->needed_headroom)
+			dev->needed_headroom = max_headroom;
 		if (!new_skb) {
 			ip_rt_put(rt);
 			dev->stats.tx_dropped++;
@@ -873,7 +875,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
 	if ((iph->ttl = tiph->ttl) == 0) {
 		if (skb->protocol == htons(ETH_P_IP))
 			iph->ttl = old_iph->ttl;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		else if (skb->protocol == htons(ETH_P_IPV6))
 			iph->ttl = ((const struct ipv6hdr *)old_iph)->hop_limit;
 #endif
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index ec93335..1e60f76 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -568,12 +568,13 @@ void ip_forward_options(struct sk_buff *skb)
 		     ) {
 			if (srrptr + 3 > srrspace)
 				break;
-			if (memcmp(&ip_hdr(skb)->daddr, &optptr[srrptr-1], 4) == 0)
+			if (memcmp(&opt->nexthop, &optptr[srrptr-1], 4) == 0)
 				break;
 		}
 		if (srrptr + 3 <= srrspace) {
 			opt->is_changed = 1;
 			ip_rt_get_source(&optptr[srrptr-1], skb, rt);
+			ip_hdr(skb)->daddr = opt->nexthop;
 			optptr[2] = srrptr+4;
 		} else if (net_ratelimit())
 			printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n");
@@ -640,6 +641,7 @@ int ip_options_rcv_srr(struct sk_buff *skb)
 	}
 	if (srrptr <= srrspace) {
 		opt->srr_is_hit = 1;
+		opt->nexthop = nexthop;
 		opt->is_changed = 1;
 	}
 	return 0;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 0bc95f3..ff302bd 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -206,7 +206,7 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 	}
 
 	rcu_read_lock();
-	neigh = dst_get_neighbour(dst);
+	neigh = dst_get_neighbour_noref(dst);
 	if (neigh) {
 		int res = neigh_output(neigh, skb);
 
@@ -319,6 +319,20 @@ int ip_output(struct sk_buff *skb)
 			    !(IPCB(skb)->flags & IPSKB_REROUTED));
 }
 
+/*
+ * copy saddr and daddr, possibly using 64bit load/stores
+ * Equivalent to :
+ *   iph->saddr = fl4->saddr;
+ *   iph->daddr = fl4->daddr;
+ */
+static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4)
+{
+	BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) !=
+		     offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr));
+	memcpy(&iph->saddr, &fl4->saddr,
+	       sizeof(fl4->saddr) + sizeof(fl4->daddr));
+}
+
 int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl)
 {
 	struct sock *sk = skb->sk;
@@ -381,8 +395,8 @@ packet_routed:
 		iph->frag_off = 0;
 	iph->ttl      = ip_select_ttl(inet, &rt->dst);
 	iph->protocol = sk->sk_protocol;
-	iph->saddr    = fl4->saddr;
-	iph->daddr    = fl4->daddr;
+	ip_copy_addrs(iph, fl4);
+
 	/* Transport layer set skb->h.foo itself. */
 
 	if (inet_opt && inet_opt->opt.optlen) {
@@ -1337,8 +1351,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	ip_select_ident(iph, &rt->dst, sk);
 	iph->ttl = ttl;
 	iph->protocol = sk->sk_protocol;
-	iph->saddr = fl4->saddr;
-	iph->daddr = fl4->daddr;
+	ip_copy_addrs(iph, fl4);
 
 	if (opt) {
 		iph->ihl += opt->optlen>>2;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 09ff51b..8aa87c1 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -37,7 +37,7 @@
 #include <net/route.h>
 #include <net/xfrm.h>
 #include <net/compat.h>
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 #include <net/transp_v6.h>
 #endif
 
@@ -55,20 +55,13 @@
 /*
  *	SOL_IP control messages.
  */
+#define PKTINFO_SKB_CB(__skb) ((struct in_pktinfo *)((__skb)->cb))
 
 static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb)
 {
-	struct in_pktinfo info;
-	struct rtable *rt = skb_rtable(skb);
+	struct in_pktinfo info = *PKTINFO_SKB_CB(skb);
 
 	info.ipi_addr.s_addr = ip_hdr(skb)->daddr;
-	if (rt) {
-		info.ipi_ifindex = rt->rt_iif;
-		info.ipi_spec_dst.s_addr = rt->rt_spec_dst;
-	} else {
-		info.ipi_ifindex = 0;
-		info.ipi_spec_dst.s_addr = 0;
-	}
 
 	put_cmsg(msg, SOL_IP, IP_PKTINFO, sizeof(info), &info);
 }
@@ -515,7 +508,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 						sock_owned_by_user(sk));
 		if (inet->is_icsk) {
 			struct inet_connection_sock *icsk = inet_csk(sk);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 			if (sk->sk_family == PF_INET ||
 			    (!((1 << sk->sk_state) &
 			       (TCPF_LISTEN | TCPF_CLOSE)) &&
@@ -526,7 +519,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
 				if (opt)
 					icsk->icsk_ext_hdr_len += opt->opt.optlen;
 				icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 			}
 #endif
 		}
@@ -992,20 +985,28 @@ e_inval:
 }
 
 /**
- * ip_queue_rcv_skb - Queue an skb into sock receive queue
+ * ipv4_pktinfo_prepare - transfert some info from rtable to skb
  * @sk: socket
  * @skb: buffer
  *
- * Queues an skb into socket receive queue. If IP_CMSG_PKTINFO option
- * is not set, we drop skb dst entry now, while dst cache line is hot.
+ * To support IP_CMSG_PKTINFO option, we store rt_iif and rt_spec_dst
+ * in skb->cb[] before dst drop.
+ * This way, receiver doesnt make cache line misses to read rtable.
  */
-int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+void ipv4_pktinfo_prepare(struct sk_buff *skb)
 {
-	if (!(inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO))
-		skb_dst_drop(skb);
-	return sock_queue_rcv_skb(sk, skb);
+	struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
+	const struct rtable *rt = skb_rtable(skb);
+
+	if (rt) {
+		pktinfo->ipi_ifindex = rt->rt_iif;
+		pktinfo->ipi_spec_dst.s_addr = rt->rt_spec_dst;
+	} else {
+		pktinfo->ipi_ifindex = 0;
+		pktinfo->ipi_spec_dst.s_addr = 0;
+	}
+	skb_dst_drop(skb);
 }
-EXPORT_SYMBOL(ip_queue_rcv_skb);
 
 int ip_setsockopt(struct sock *sk, int level,
 		int optname, char __user *optval, unsigned int optlen)
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 0da2afc..915eb52 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -763,13 +763,15 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d
 	struct sk_buff *skb;
 	struct bootp_pkt *b;
 	struct iphdr *h;
+	int hlen = LL_RESERVED_SPACE(dev);
+	int tlen = dev->needed_tailroom;
 
 	/* Allocate packet */
-	skb = alloc_skb(sizeof(struct bootp_pkt) + LL_ALLOCATED_SPACE(dev) + 15,
+	skb = alloc_skb(sizeof(struct bootp_pkt) + hlen + tlen + 15,
 			GFP_KERNEL);
 	if (!skb)
 		return;
-	skb_reserve(skb, LL_RESERVED_SPACE(dev));
+	skb_reserve(skb, hlen);
 	b = (struct bootp_pkt *) skb_put(skb, sizeof(struct bootp_pkt));
 	memset(b, 0, sizeof(struct bootp_pkt));
 
@@ -822,8 +824,13 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d
 	skb->dev = dev;
 	skb->protocol = htons(ETH_P_IP);
 	if (dev_hard_header(skb, dev, ntohs(skb->protocol),
-			    dev->broadcast, dev->dev_addr, skb->len) < 0 ||
-	    dev_queue_xmit(skb) < 0)
+			    dev->broadcast, dev->dev_addr, skb->len) < 0) {
+		kfree_skb(skb);
+		printk("E");
+		return;
+	}
+
+	if (dev_queue_xmit(skb) < 0)
 		printk("E");
 }
 
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 065effd..413ed1b 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -148,7 +148,7 @@ struct pcpu_tstats {
 	unsigned long	rx_bytes;
 	unsigned long	tx_packets;
 	unsigned long	tx_bytes;
-};
+} __attribute__((aligned(4*sizeof(unsigned long))));
 
 static struct net_device_stats *ipip_get_stats(struct net_device *dev)
 {
@@ -285,6 +285,8 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net,
 	if (register_netdevice(dev) < 0)
 		goto failed_free;
 
+	strcpy(nt->parms.name, dev->name);
+
 	dev_hold(dev);
 	ipip_tunnel_link(ipn, nt);
 	return nt;
@@ -759,7 +761,6 @@ static int ipip_tunnel_init(struct net_device *dev)
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 
 	tunnel->dev = dev;
-	strcpy(tunnel->parms.name, dev->name);
 
 	memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
 	memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
@@ -825,6 +826,7 @@ static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head)
 static int __net_init ipip_init_net(struct net *net)
 {
 	struct ipip_net *ipn = net_generic(net, ipip_net_id);
+	struct ip_tunnel *t;
 	int err;
 
 	ipn->tunnels[0] = ipn->tunnels_wc;
@@ -848,6 +850,9 @@ static int __net_init ipip_init_net(struct net *net)
 	if ((err = register_netdev(ipn->fb_tunnel_dev)))
 		goto err_reg_dev;
 
+	t = netdev_priv(ipn->fb_tunnel_dev);
+
+	strcpy(t->parms.name, ipn->fb_tunnel_dev->name);
 	return 0;
 
 err_reg_dev:
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 76a7f07..8e54490 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1520,7 +1520,6 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v
 	struct mr_table *mrt;
 	struct vif_device *v;
 	int ct;
-	LIST_HEAD(list);
 
 	if (event != NETDEV_UNREGISTER)
 		return NOTIFY_DONE;
@@ -1529,10 +1528,9 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v
 		v = &mrt->vif_table[0];
 		for (ct = 0; ct < mrt->maxvif; ct++, v++) {
 			if (v->dev == dev)
-				vif_delete(mrt, ct, 1, &list);
+				vif_delete(mrt, ct, 1, NULL);
 		}
 	}
-	unregister_netdevice_many(&list);
 	return NOTIFY_DONE;
 }
 
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index 9899619..4f47e06 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -64,7 +64,8 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type)
 	/* Change in oif may mean change in hh_len. */
 	hh_len = skb_dst(skb)->dev->hard_header_len;
 	if (skb_headroom(skb) < hh_len &&
-	    pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC))
+	    pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)),
+				0, GFP_ATOMIC))
 		return -1;
 
 	return 0;
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 1dfc18a..f19f218 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -325,7 +325,6 @@ config IP_NF_TARGET_TTL
 # raw + specific targets
 config IP_NF_RAW
 	tristate  'raw table support (required for NOTRACK/TRACE)'
-	depends on NETFILTER_ADVANCED
 	help
 	  This option adds a `raw' table to iptables. This table is the very
 	  first in the netfilter framework and hooks in at the PREROUTING
diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
index e59aabd..a057fe6 100644
--- a/net/ipv4/netfilter/ip_queue.c
+++ b/net/ipv4/netfilter/ip_queue.c
@@ -404,6 +404,7 @@ __ipq_rcv_skb(struct sk_buff *skb)
 	int status, type, pid, flags;
 	unsigned int nlmsglen, skblen;
 	struct nlmsghdr *nlh;
+	bool enable_timestamp = false;
 
 	skblen = skb->len;
 	if (skblen < sizeof(*nlh))
@@ -441,12 +442,13 @@ __ipq_rcv_skb(struct sk_buff *skb)
 			RCV_SKB_FAIL(-EBUSY);
 		}
 	} else {
-		net_enable_timestamp();
+		enable_timestamp = true;
 		peer_pid = pid;
 	}
 
 	spin_unlock_bh(&queue_lock);
-
+	if (enable_timestamp)
+		net_enable_timestamp();
 	status = ipq_receive_peer(NLMSG_DATA(nlh), type,
 				  nlmsglen - NLMSG_LENGTH(0));
 	if (status < 0)
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index a06f73f..43d4c3b 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -339,7 +339,6 @@ void ping_err(struct sk_buff *skb, u32 info)
 	sk = ping_v4_lookup(net, iph->daddr, iph->saddr,
 			    ntohs(icmph->un.echo.id), skb->dev->ifindex);
 	if (sk == NULL) {
-		ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS);
 		pr_debug("no socket, dropping\n");
 		return;	/* No socket for error */
 	}
@@ -679,7 +678,6 @@ static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n",
 		inet_sk(sk), inet_sk(sk)->inet_num, skb);
 	if (sock_queue_rcv_skb(sk, skb) < 0) {
-		ICMP_INC_STATS_BH(sock_net(sk), ICMP_MIB_INERRORS);
 		kfree_skb(skb);
 		pr_debug("ping_queue_rcv_skb -> failed\n");
 		return -1;
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 466ea8b..3569d8e 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -56,17 +56,17 @@ static int sockstat_seq_show(struct seq_file *seq, void *v)
 
 	local_bh_disable();
 	orphans = percpu_counter_sum_positive(&tcp_orphan_count);
-	sockets = percpu_counter_sum_positive(&tcp_sockets_allocated);
+	sockets = proto_sockets_allocated_sum_positive(&tcp_prot);
 	local_bh_enable();
 
 	socket_seq_show(seq);
 	seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n",
 		   sock_prot_inuse_get(net, &tcp_prot), orphans,
 		   tcp_death_row.tw_count, sockets,
-		   atomic_long_read(&tcp_memory_allocated));
+		   proto_memory_allocated(&tcp_prot));
 	seq_printf(seq, "UDP: inuse %d mem %ld\n",
 		   sock_prot_inuse_get(net, &udp_prot),
-		   atomic_long_read(&udp_memory_allocated));
+		   proto_memory_allocated(&udp_prot));
 	seq_printf(seq, "UDPLITE: inuse %d\n",
 		   sock_prot_inuse_get(net, &udplite_prot));
 	seq_printf(seq, "RAW: inuse %d\n",
@@ -288,7 +288,7 @@ static void icmpmsg_put(struct seq_file *seq)
 
 	count = 0;
 	for (i = 0; i < ICMPMSG_MIB_MAX; i++) {
-		val = snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics, i);
+		val = atomic_long_read(&net->mib.icmpmsg_statistics->mibs[i]);
 		if (val) {
 			type[count] = i;
 			vals[count++] = val;
@@ -307,6 +307,7 @@ static void icmp_put(struct seq_file *seq)
 {
 	int i;
 	struct net *net = seq->private;
+	atomic_long_t *ptr = net->mib.icmpmsg_statistics->mibs;
 
 	seq_puts(seq, "\nIcmp: InMsgs InErrors");
 	for (i=0; icmpmibmap[i].name != NULL; i++)
@@ -319,15 +320,13 @@ static void icmp_put(struct seq_file *seq)
 		snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_INERRORS));
 	for (i=0; icmpmibmap[i].name != NULL; i++)
 		seq_printf(seq, " %lu",
-			snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics,
-				icmpmibmap[i].index));
+			   atomic_long_read(ptr + icmpmibmap[i].index));
 	seq_printf(seq, " %lu %lu",
 		snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTMSGS),
 		snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTERRORS));
 	for (i=0; icmpmibmap[i].name != NULL; i++)
 		seq_printf(seq, " %lu",
-			snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics,
-				icmpmibmap[i].index | 0x100));
+			   atomic_long_read(ptr + (icmpmibmap[i].index | 0x100)));
 }
 
 /*
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 007e2eb..3ccda5a 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -292,7 +292,8 @@ static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb)
 {
 	/* Charge it to the socket. */
 
-	if (ip_queue_rcv_skb(sk, skb) < 0) {
+	ipv4_pktinfo_prepare(skb);
+	if (sock_queue_rcv_skb(sk, skb) < 0) {
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
@@ -327,6 +328,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 	unsigned int iphlen;
 	int err;
 	struct rtable *rt = *rtp;
+	int hlen, tlen;
 
 	if (length > rt->dst.dev->mtu) {
 		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
@@ -336,12 +338,14 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 	if (flags&MSG_PROBE)
 		goto out;
 
+	hlen = LL_RESERVED_SPACE(rt->dst.dev);
+	tlen = rt->dst.dev->needed_tailroom;
 	skb = sock_alloc_send_skb(sk,
-				  length + LL_ALLOCATED_SPACE(rt->dst.dev) + 15,
+				  length + hlen + tlen + 15,
 				  flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto error;
-	skb_reserve(skb, LL_RESERVED_SPACE(rt->dst.dev));
+	skb_reserve(skb, hlen);
 
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 155138d..f30112f 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -108,11 +108,10 @@
 #ifdef CONFIG_SYSCTL
 #include <linux/sysctl.h>
 #endif
-#include <net/atmclip.h>
 #include <net/secure_seq.h>
 
 #define RT_FL_TOS(oldflp4) \
-    ((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)))
+	((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
 
 #define IP_MAX_MTU	0xFFF0
 
@@ -131,6 +130,7 @@ static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
 static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly	= 256;
 static int rt_chain_length_max __read_mostly	= 20;
+static int redirect_genid;
 
 /*
  *	Interface to generic destination cache.
@@ -138,7 +138,7 @@ static int rt_chain_length_max __read_mostly	= 20;
 
 static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
 static unsigned int	 ipv4_default_advmss(const struct dst_entry *dst);
-static unsigned int	 ipv4_default_mtu(const struct dst_entry *dst);
+static unsigned int	 ipv4_mtu(const struct dst_entry *dst);
 static void		 ipv4_dst_destroy(struct dst_entry *dst);
 static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
 static void		 ipv4_link_failure(struct sk_buff *skb);
@@ -193,7 +193,7 @@ static struct dst_ops ipv4_dst_ops = {
 	.gc =			rt_garbage_collect,
 	.check =		ipv4_dst_check,
 	.default_advmss =	ipv4_default_advmss,
-	.default_mtu =		ipv4_default_mtu,
+	.mtu =			ipv4_mtu,
 	.cow_metrics =		ipv4_cow_metrics,
 	.destroy =		ipv4_dst_destroy,
 	.ifdown =		ipv4_dst_ifdown,
@@ -416,9 +416,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
 	else {
 		struct rtable *r = v;
 		struct neighbour *n;
-		int len;
+		int len, HHUptod;
+
+		rcu_read_lock();
+		n = dst_get_neighbour_noref(&r->dst);
+		HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0;
+		rcu_read_unlock();
 
-		n = dst_get_neighbour(&r->dst);
 		seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
 			      "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
 			r->dst.dev ? r->dst.dev->name : "*",
@@ -432,7 +436,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
 			      dst_metric(&r->dst, RTAX_RTTVAR)),
 			r->rt_key_tos,
 			-1,
-			(n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0,
+			HHUptod,
 			r->rt_spec_dst, &len);
 
 		seq_printf(seq, "%*s\n", 127 - len, "");
@@ -837,6 +841,7 @@ static void rt_cache_invalidate(struct net *net)
 
 	get_random_bytes(&shuffle, sizeof(shuffle));
 	atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
+	redirect_genid++;
 }
 
 /*
@@ -1013,23 +1018,18 @@ static int slow_chain_length(const struct rtable *head)
 
 static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr)
 {
-	struct neigh_table *tbl = &arp_tbl;
 	static const __be32 inaddr_any = 0;
 	struct net_device *dev = dst->dev;
 	const __be32 *pkey = daddr;
 	struct neighbour *n;
 
-#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE)
-	if (dev->type == ARPHRD_ATM)
-		tbl = clip_tbl_hook;
-#endif
 	if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
 		pkey = &inaddr_any;
 
-	n = __ipv4_neigh_lookup(tbl, dev, *(__force u32 *)pkey);
+	n = __ipv4_neigh_lookup(&arp_tbl, dev, *(__force u32 *)pkey);
 	if (n)
 		return n;
-	return neigh_create(tbl, pkey, dev);
+	return neigh_create(&arp_tbl, pkey, dev);
 }
 
 static int rt_bind_neighbour(struct rtable *rt)
@@ -1304,16 +1304,40 @@ static void rt_del(unsigned hash, struct rtable *rt)
 	spin_unlock_bh(rt_hash_lock_addr(hash));
 }
 
+static void check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
+{
+	struct rtable *rt = (struct rtable *) dst;
+	__be32 orig_gw = rt->rt_gateway;
+	struct neighbour *n, *old_n;
+
+	dst_confirm(&rt->dst);
+
+	rt->rt_gateway = peer->redirect_learned.a4;
+
+	n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
+	if (IS_ERR(n)) {
+		rt->rt_gateway = orig_gw;
+		return;
+	}
+	old_n = xchg(&rt->dst._neighbour, n);
+	if (old_n)
+		neigh_release(old_n);
+	if (!(n->nud_state & NUD_VALID)) {
+		neigh_event_send(n, NULL);
+	} else {
+		rt->rt_flags |= RTCF_REDIRECTED;
+		call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
+	}
+}
+
 /* called in rcu_read_lock() section */
 void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 		    __be32 saddr, struct net_device *dev)
 {
 	int s, i;
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
-	struct rtable *rt;
 	__be32 skeys[2] = { saddr, 0 };
 	int    ikeys[2] = { dev->ifindex, 0 };
-	struct flowi4 fl4;
 	struct inet_peer *peer;
 	struct net *net;
 
@@ -1336,33 +1360,44 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 			goto reject_redirect;
 	}
 
-	memset(&fl4, 0, sizeof(fl4));
-	fl4.daddr = daddr;
 	for (s = 0; s < 2; s++) {
 		for (i = 0; i < 2; i++) {
-			fl4.flowi4_oif = ikeys[i];
-			fl4.saddr = skeys[s];
-			rt = __ip_route_output_key(net, &fl4);
-			if (IS_ERR(rt))
-				continue;
-
-			if (rt->dst.error || rt->dst.dev != dev ||
-			    rt->rt_gateway != old_gw) {
-				ip_rt_put(rt);
-				continue;
-			}
-
-			if (!rt->peer)
-				rt_bind_peer(rt, rt->rt_dst, 1);
+			unsigned int hash;
+			struct rtable __rcu **rthp;
+			struct rtable *rt;
+
+			hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net));
+
+			rthp = &rt_hash_table[hash].chain;
+
+			while ((rt = rcu_dereference(*rthp)) != NULL) {
+				rthp = &rt->dst.rt_next;
+
+				if (rt->rt_key_dst != daddr ||
+				    rt->rt_key_src != skeys[s] ||
+				    rt->rt_oif != ikeys[i] ||
+				    rt_is_input_route(rt) ||
+				    rt_is_expired(rt) ||
+				    !net_eq(dev_net(rt->dst.dev), net) ||
+				    rt->dst.error ||
+				    rt->dst.dev != dev ||
+				    rt->rt_gateway != old_gw)
+					continue;
 
-			peer = rt->peer;
-			if (peer) {
-				peer->redirect_learned.a4 = new_gw;
-				atomic_inc(&__rt_peer_genid);
+				if (!rt->peer)
+					rt_bind_peer(rt, rt->rt_dst, 1);
+
+				peer = rt->peer;
+				if (peer) {
+					if (peer->redirect_learned.a4 != new_gw ||
+					    peer->redirect_genid != redirect_genid) {
+						peer->redirect_learned.a4 = new_gw;
+						peer->redirect_genid = redirect_genid;
+						atomic_inc(&__rt_peer_genid);
+					}
+					check_peer_redir(&rt->dst, peer);
+				}
 			}
-
-			ip_rt_put(rt);
-			return;
 		}
 	}
 	return;
@@ -1649,40 +1684,9 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 	}
 }
 
-static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
-{
-	struct rtable *rt = (struct rtable *) dst;
-	__be32 orig_gw = rt->rt_gateway;
-	struct neighbour *n, *old_n;
-
-	dst_confirm(&rt->dst);
-
-	rt->rt_gateway = peer->redirect_learned.a4;
 
-	n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
-	if (IS_ERR(n))
-		return PTR_ERR(n);
-	old_n = xchg(&rt->dst._neighbour, n);
-	if (old_n)
-		neigh_release(old_n);
-	if (!n || !(n->nud_state & NUD_VALID)) {
-		if (n)
-			neigh_event_send(n, NULL);
-		rt->rt_gateway = orig_gw;
-		return -EAGAIN;
-	} else {
-		rt->rt_flags |= RTCF_REDIRECTED;
-		call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
-	}
-	return 0;
-}
-
-static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
+static void ipv4_validate_peer(struct rtable *rt)
 {
-	struct rtable *rt = (struct rtable *) dst;
-
-	if (rt_is_expired(rt))
-		return NULL;
 	if (rt->rt_peer_genid != rt_peer_genid()) {
 		struct inet_peer *peer;
 
@@ -1691,17 +1695,26 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 
 		peer = rt->peer;
 		if (peer) {
-			check_peer_pmtu(dst, peer);
+			check_peer_pmtu(&rt->dst, peer);
 
+			if (peer->redirect_genid != redirect_genid)
+				peer->redirect_learned.a4 = 0;
 			if (peer->redirect_learned.a4 &&
-			    peer->redirect_learned.a4 != rt->rt_gateway) {
-				if (check_peer_redir(dst, peer))
-					return NULL;
-			}
+			    peer->redirect_learned.a4 != rt->rt_gateway)
+				check_peer_redir(&rt->dst, peer);
 		}
 
 		rt->rt_peer_genid = rt_peer_genid();
 	}
+}
+
+static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
+{
+	struct rtable *rt = (struct rtable *) dst;
+
+	if (rt_is_expired(rt))
+		return NULL;
+	ipv4_validate_peer(rt);
 	return dst;
 }
 
@@ -1806,12 +1819,17 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
 	return advmss;
 }
 
-static unsigned int ipv4_default_mtu(const struct dst_entry *dst)
+static unsigned int ipv4_mtu(const struct dst_entry *dst)
 {
-	unsigned int mtu = dst->dev->mtu;
+	const struct rtable *rt = (const struct rtable *) dst;
+	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+	if (mtu && rt_is_output_route(rt))
+		return mtu;
+
+	mtu = dst->dev->mtu;
 
 	if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
-		const struct rtable *rt = (const struct rtable *) dst;
 
 		if (rt->rt_gateway != rt->rt_dst && mtu > 576)
 			mtu = 576;
@@ -1844,6 +1862,8 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
 		dst_init_metrics(&rt->dst, peer->metrics, false);
 
 		check_peer_pmtu(&rt->dst, peer);
+		if (peer->redirect_genid != redirect_genid)
+			peer->redirect_learned.a4 = 0;
 		if (peer->redirect_learned.a4 &&
 		    peer->redirect_learned.a4 != rt->rt_gateway) {
 			rt->rt_gateway = peer->redirect_learned.a4;
@@ -2349,6 +2369,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		    rth->rt_mark == skb->mark &&
 		    net_eq(dev_net(rth->dst.dev), net) &&
 		    !rt_is_expired(rth)) {
+			ipv4_validate_peer(rth);
 			if (noref) {
 				dst_use_noref(&rth->dst, jiffies);
 				skb_dst_set_noref(skb, &rth->dst);
@@ -2407,11 +2428,11 @@ EXPORT_SYMBOL(ip_route_input_common);
 static struct rtable *__mkroute_output(const struct fib_result *res,
 				       const struct flowi4 *fl4,
 				       __be32 orig_daddr, __be32 orig_saddr,
-				       int orig_oif, struct net_device *dev_out,
+				       int orig_oif, __u8 orig_rtos,
+				       struct net_device *dev_out,
 				       unsigned int flags)
 {
 	struct fib_info *fi = res->fi;
-	u32 tos = RT_FL_TOS(fl4);
 	struct in_device *in_dev;
 	u16 type = res->type;
 	struct rtable *rth;
@@ -2462,7 +2483,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	rth->rt_genid = rt_genid(dev_net(dev_out));
 	rth->rt_flags	= flags;
 	rth->rt_type	= type;
-	rth->rt_key_tos	= tos;
+	rth->rt_key_tos	= orig_rtos;
 	rth->rt_dst	= fl4->daddr;
 	rth->rt_src	= fl4->saddr;
 	rth->rt_route_iif = 0;
@@ -2512,7 +2533,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
 {
 	struct net_device *dev_out = NULL;
-	u32 tos	= RT_FL_TOS(fl4);
+	__u8 tos = RT_FL_TOS(fl4);
 	unsigned int flags = 0;
 	struct fib_result res;
 	struct rtable *rth;
@@ -2688,7 +2709,7 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
 
 make_route:
 	rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif,
-			       dev_out, flags);
+			       tos, dev_out, flags);
 	if (!IS_ERR(rth)) {
 		unsigned int hash;
 
@@ -2724,6 +2745,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp4)
 			    (IPTOS_RT_MASK | RTO_ONLINK)) &&
 		    net_eq(dev_net(rth->dst.dev), net) &&
 		    !rt_is_expired(rth)) {
+			ipv4_validate_peer(rth);
 			dst_use(&rth->dst, jiffies);
 			RT_CACHE_STAT_INC(out_hit);
 			rcu_read_unlock_bh();
@@ -2747,9 +2769,11 @@ static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 coo
 	return NULL;
 }
 
-static unsigned int ipv4_blackhole_default_mtu(const struct dst_entry *dst)
+static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
 {
-	return 0;
+	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+	return mtu ? : dst->dev->mtu;
 }
 
 static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
@@ -2767,7 +2791,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
 	.protocol		=	cpu_to_be16(ETH_P_IP),
 	.destroy		=	ipv4_dst_destroy,
 	.check			=	ipv4_blackhole_dst_check,
-	.default_mtu		=	ipv4_blackhole_default_mtu,
+	.mtu			=	ipv4_blackhole_mtu,
 	.default_advmss		=	ipv4_default_advmss,
 	.update_pmtu		=	ipv4_rt_blackhole_update_pmtu,
 	.cow_metrics		=	ipv4_rt_blackhole_cow_metrics,
@@ -2845,7 +2869,7 @@ static int rt_fill_info(struct net *net,
 	struct rtable *rt = skb_rtable(skb);
 	struct rtmsg *r;
 	struct nlmsghdr *nlh;
-	long expires = 0;
+	unsigned long expires = 0;
 	const struct inet_peer *peer = rt->peer;
 	u32 id = 0, ts = 0, tsage = 0, error;
 
@@ -2902,8 +2926,12 @@ static int rt_fill_info(struct net *net,
 			tsage = get_seconds() - peer->tcp_ts_stamp;
 		}
 		expires = ACCESS_ONCE(peer->pmtu_expires);
-		if (expires)
-			expires -= jiffies;
+		if (expires) {
+			if (time_before(jiffies, expires))
+				expires -= jiffies;
+			else
+				expires = 0;
+		}
 	}
 
 	if (rt_is_input_route(rt)) {
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 69fd720..4aa7e9d 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/nsproxy.h>
+#include <linux/swap.h>
 #include <net/snmp.h>
 #include <net/icmp.h>
 #include <net/ip.h>
@@ -23,6 +24,7 @@
 #include <net/cipso_ipv4.h>
 #include <net/inet_frag.h>
 #include <net/ping.h>
+#include <net/tcp_memcontrol.h>
 
 static int zero;
 static int tcp_retr1_max = 255;
@@ -73,7 +75,7 @@ static int ipv4_local_port_range(ctl_table *table, int write,
 }
 
 
-void inet_get_ping_group_range_table(struct ctl_table *table, gid_t *low, gid_t *high)
+static void inet_get_ping_group_range_table(struct ctl_table *table, gid_t *low, gid_t *high)
 {
 	gid_t *data = table->data;
 	unsigned seq;
@@ -86,7 +88,7 @@ void inet_get_ping_group_range_table(struct ctl_table *table, gid_t *low, gid_t
 }
 
 /* Update system visible IP port range */
-static void set_ping_group_range(struct ctl_table *table, int range[2])
+static void set_ping_group_range(struct ctl_table *table, gid_t range[2])
 {
 	gid_t *data = table->data;
 	write_seqlock(&sysctl_local_ports.lock);
@@ -174,6 +176,49 @@ static int proc_allowed_congestion_control(ctl_table *ctl,
 	return ret;
 }
 
+static int ipv4_tcp_mem(ctl_table *ctl, int write,
+			   void __user *buffer, size_t *lenp,
+			   loff_t *ppos)
+{
+	int ret;
+	unsigned long vec[3];
+	struct net *net = current->nsproxy->net_ns;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+	struct mem_cgroup *memcg;
+#endif
+
+	ctl_table tmp = {
+		.data = &vec,
+		.maxlen = sizeof(vec),
+		.mode = ctl->mode,
+	};
+
+	if (!write) {
+		ctl->data = &net->ipv4.sysctl_tcp_mem;
+		return proc_doulongvec_minmax(ctl, write, buffer, lenp, ppos);
+	}
+
+	ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+	rcu_read_lock();
+	memcg = mem_cgroup_from_task(current);
+
+	tcp_prot_mem(memcg, vec[0], 0);
+	tcp_prot_mem(memcg, vec[1], 1);
+	tcp_prot_mem(memcg, vec[2], 2);
+	rcu_read_unlock();
+#endif
+
+	net->ipv4.sysctl_tcp_mem[0] = vec[0];
+	net->ipv4.sysctl_tcp_mem[1] = vec[1];
+	net->ipv4.sysctl_tcp_mem[2] = vec[2];
+
+	return 0;
+}
+
 static struct ctl_table ipv4_table[] = {
 	{
 		.procname	= "tcp_timestamps",
@@ -433,13 +478,6 @@ static struct ctl_table ipv4_table[] = {
 		.proc_handler	= proc_dointvec
 	},
 	{
-		.procname	= "tcp_mem",
-		.data		= &sysctl_tcp_mem,
-		.maxlen		= sizeof(sysctl_tcp_mem),
-		.mode		= 0644,
-		.proc_handler	= proc_doulongvec_minmax
-	},
-	{
 		.procname	= "tcp_wmem",
 		.data		= &sysctl_tcp_wmem,
 		.maxlen		= sizeof(sysctl_tcp_wmem),
@@ -721,6 +759,12 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= ipv4_ping_group_range,
 	},
+	{
+		.procname	= "tcp_mem",
+		.maxlen		= sizeof(init_net.ipv4.sysctl_tcp_mem),
+		.mode		= 0644,
+		.proc_handler	= ipv4_tcp_mem,
+	},
 	{ }
 };
 
@@ -734,6 +778,7 @@ EXPORT_SYMBOL_GPL(net_ipv4_ctl_path);
 static __net_init int ipv4_sysctl_init_net(struct net *net)
 {
 	struct ctl_table *table;
+	unsigned long limit;
 
 	table = ipv4_net_table;
 	if (!net_eq(net, &init_net)) {
@@ -769,6 +814,12 @@ static __net_init int ipv4_sysctl_init_net(struct net *net)
 
 	net->ipv4.sysctl_rt_cache_rebuild_count = 4;
 
+	limit = nr_free_buffer_pages() / 8;
+	limit = max(limit, 128UL);
+	net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3;
+	net->ipv4.sysctl_tcp_mem[1] = limit;
+	net->ipv4.sysctl_tcp_mem[2] = net->ipv4.sysctl_tcp_mem[0] * 2;
+
 	net->ipv4.ipv4_hdr = register_net_sysctl_table(net,
 			net_ipv4_ctl_path, table);
 	if (net->ipv4.ipv4_hdr == NULL)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 34f5db1..9bcdec3 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -282,11 +282,9 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
 struct percpu_counter tcp_orphan_count;
 EXPORT_SYMBOL_GPL(tcp_orphan_count);
 
-long sysctl_tcp_mem[3] __read_mostly;
 int sysctl_tcp_wmem[3] __read_mostly;
 int sysctl_tcp_rmem[3] __read_mostly;
 
-EXPORT_SYMBOL(sysctl_tcp_mem);
 EXPORT_SYMBOL(sysctl_tcp_rmem);
 EXPORT_SYMBOL(sysctl_tcp_wmem);
 
@@ -888,18 +886,18 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset,
 }
 EXPORT_SYMBOL(tcp_sendpage);
 
-#define TCP_PAGE(sk)	(sk->sk_sndmsg_page)
-#define TCP_OFF(sk)	(sk->sk_sndmsg_off)
-
-static inline int select_size(const struct sock *sk, int sg)
+static inline int select_size(const struct sock *sk, bool sg)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	int tmp = tp->mss_cache;
 
 	if (sg) {
-		if (sk_can_gso(sk))
-			tmp = 0;
-		else {
+		if (sk_can_gso(sk)) {
+			/* Small frames wont use a full page:
+			 * Payload will immediately follow tcp header.
+			 */
+			tmp = SKB_WITH_OVERHEAD(2048 - MAX_TCP_HEADER);
+		} else {
 			int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER);
 
 			if (tmp >= pgbreak &&
@@ -917,9 +915,9 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	struct iovec *iov;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
-	int iovlen, flags;
+	int iovlen, flags, err, copied;
 	int mss_now, size_goal;
-	int sg, err, copied;
+	bool sg;
 	long timeo;
 
 	lock_sock(sk);
@@ -946,7 +944,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
 		goto out_err;
 
-	sg = sk->sk_route_caps & NETIF_F_SG;
+	sg = !!(sk->sk_route_caps & NETIF_F_SG);
 
 	while (--iovlen >= 0) {
 		size_t seglen = iov->iov_len;
@@ -1005,8 +1003,13 @@ new_segment:
 			} else {
 				int merge = 0;
 				int i = skb_shinfo(skb)->nr_frags;
-				struct page *page = TCP_PAGE(sk);
-				int off = TCP_OFF(sk);
+				struct page *page = sk->sk_sndmsg_page;
+				int off;
+
+				if (page && page_count(page) == 1)
+					sk->sk_sndmsg_off = 0;
+
+				off = sk->sk_sndmsg_off;
 
 				if (skb_can_coalesce(skb, i, page, off) &&
 				    off != PAGE_SIZE) {
@@ -1023,7 +1026,7 @@ new_segment:
 				} else if (page) {
 					if (off == PAGE_SIZE) {
 						put_page(page);
-						TCP_PAGE(sk) = page = NULL;
+						sk->sk_sndmsg_page = page = NULL;
 						off = 0;
 					}
 				} else
@@ -1049,9 +1052,9 @@ new_segment:
 					/* If this page was new, give it to the
 					 * socket so it does not get leaked.
 					 */
-					if (!TCP_PAGE(sk)) {
-						TCP_PAGE(sk) = page;
-						TCP_OFF(sk) = 0;
+					if (!sk->sk_sndmsg_page) {
+						sk->sk_sndmsg_page = page;
+						sk->sk_sndmsg_off = 0;
 					}
 					goto do_error;
 				}
@@ -1061,15 +1064,15 @@ new_segment:
 					skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
 				} else {
 					skb_fill_page_desc(skb, i, page, off, copy);
-					if (TCP_PAGE(sk)) {
+					if (sk->sk_sndmsg_page) {
 						get_page(page);
 					} else if (off + copy < PAGE_SIZE) {
 						get_page(page);
-						TCP_PAGE(sk) = page;
+						sk->sk_sndmsg_page = page;
 					}
 				}
 
-				TCP_OFF(sk) = off + copy;
+				sk->sk_sndmsg_off = off + copy;
 			}
 
 			if (!copied)
@@ -2653,7 +2656,8 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname,
 EXPORT_SYMBOL(compat_tcp_getsockopt);
 #endif
 
-struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features)
+struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
+	netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct tcphdr *th;
@@ -3272,14 +3276,9 @@ void __init tcp_init(void)
 	sysctl_tcp_max_orphans = cnt / 2;
 	sysctl_max_syn_backlog = max(128, cnt / 256);
 
-	limit = nr_free_buffer_pages() / 8;
-	limit = max(limit, 128UL);
-	sysctl_tcp_mem[0] = limit / 4 * 3;
-	sysctl_tcp_mem[1] = limit;
-	sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;
-
 	/* Set per-socket limits to no more than 1/128 the pressure threshold */
-	limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7);
+	limit = ((unsigned long)init_net.ipv4.sysctl_tcp_mem[1])
+		<< (PAGE_SHIFT - 7);
 	max_share = min(4UL*1024*1024, limit);
 
 	sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 850c737..fc6d475 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -292,7 +292,7 @@ int tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight)
 	    left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd &&
 	    left * tp->mss_cache < sk->sk_gso_max_size)
 		return 1;
-	return left <= tcp_max_burst(tp);
+	return left <= tcp_max_tso_deferred_mss(tp);
 }
 EXPORT_SYMBOL_GPL(tcp_is_cwnd_limited);
 
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index 939edb3..8cd357a 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -34,11 +34,23 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 		tcp_get_info(sk, info);
 }
 
+static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
+		struct inet_diag_req *r, struct nlattr *bc)
+{
+	inet_diag_dump_icsk(&tcp_hashinfo, skb, cb, r, bc);
+}
+
+static int tcp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
+		struct inet_diag_req *req)
+{
+	return inet_diag_dump_one_icsk(&tcp_hashinfo, in_skb, nlh, req);
+}
+
 static const struct inet_diag_handler tcp_diag_handler = {
-	.idiag_hashinfo	 = &tcp_hashinfo,
+	.dump		 = tcp_diag_dump,
+	.dump_one	 = tcp_diag_dump_one,
 	.idiag_get_info	 = tcp_diag_get_info,
-	.idiag_type	 = TCPDIAG_GETSOCK,
-	.idiag_info_size = sizeof(struct tcp_info),
+	.idiag_type	 = IPPROTO_TCP,
 };
 
 static int __init tcp_diag_init(void)
@@ -54,4 +66,4 @@ static void __exit tcp_diag_exit(void)
 module_init(tcp_diag_init);
 module_exit(tcp_diag_exit);
 MODULE_LICENSE("GPL");
-MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_INET_DIAG, TCPDIAG_GETSOCK);
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-6 /* AF_INET - IPPROTO_TCP */);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 52b5c2d..f131d92 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -322,7 +322,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
 	/* Check #1 */
 	if (tp->rcv_ssthresh < tp->window_clamp &&
 	    (int)tp->rcv_ssthresh < tcp_space(sk) &&
-	    !tcp_memory_pressure) {
+	    !sk_under_memory_pressure(sk)) {
 		int incr;
 
 		/* Check #2. Increase window, if skb with such overhead
@@ -411,8 +411,8 @@ static void tcp_clamp_window(struct sock *sk)
 
 	if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
-	    !tcp_memory_pressure &&
-	    atomic_long_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) {
+	    !sk_under_memory_pressure(sk) &&
+	    sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
 		sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc),
 				    sysctl_tcp_rmem[2]);
 	}
@@ -2663,7 +2663,7 @@ static void DBGUNDO(struct sock *sk, const char *msg)
 		       tp->snd_ssthresh, tp->prior_ssthresh,
 		       tp->packets_out);
 	}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	else if (sk->sk_family == AF_INET6) {
 		struct ipv6_pinfo *np = inet6_sk(sk);
 		printk(KERN_DEBUG "Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n",
@@ -2858,7 +2858,7 @@ static void tcp_try_keep_open(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	int state = TCP_CA_Open;
 
-	if (tcp_left_out(tp) || tcp_any_retrans_done(sk) || tp->undo_marker)
+	if (tcp_left_out(tp) || tcp_any_retrans_done(sk))
 		state = TCP_CA_Disorder;
 
 	if (inet_csk(sk)->icsk_ca_state != state) {
@@ -2881,7 +2881,8 @@ static void tcp_try_to_open(struct sock *sk, int flag)
 
 	if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) {
 		tcp_try_keep_open(sk);
-		tcp_moderate_cwnd(tp);
+		if (inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
+			tcp_moderate_cwnd(tp);
 	} else {
 		tcp_cwnd_down(sk, flag);
 	}
@@ -3009,11 +3010,11 @@ static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked,
  * tcp_xmit_retransmit_queue().
  */
 static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
-				  int newly_acked_sacked, int flag)
+				  int newly_acked_sacked, bool is_dupack,
+				  int flag)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	int is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
 	int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
 				    (tcp_fackets_out(tp) > tp->reordering));
 	int fast_rexmit = 0, mib_idx;
@@ -3066,17 +3067,6 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
 			}
 			break;
 
-		case TCP_CA_Disorder:
-			tcp_try_undo_dsack(sk);
-			if (!tp->undo_marker ||
-			    /* For SACK case do not Open to allow to undo
-			     * catching for all duplicate ACKs. */
-			    tcp_is_reno(tp) || tp->snd_una != tp->high_seq) {
-				tp->undo_marker = 0;
-				tcp_set_ca_state(sk, TCP_CA_Open);
-			}
-			break;
-
 		case TCP_CA_Recovery:
 			if (tcp_is_reno(tp))
 				tcp_reset_reno_sack(tp);
@@ -3117,7 +3107,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
 				tcp_add_reno_sack(sk);
 		}
 
-		if (icsk->icsk_ca_state == TCP_CA_Disorder)
+		if (icsk->icsk_ca_state <= TCP_CA_Disorder)
 			tcp_try_undo_dsack(sk);
 
 		if (!tcp_time_to_recover(sk)) {
@@ -3681,10 +3671,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	u32 prior_snd_una = tp->snd_una;
 	u32 ack_seq = TCP_SKB_CB(skb)->seq;
 	u32 ack = TCP_SKB_CB(skb)->ack_seq;
+	bool is_dupack = false;
 	u32 prior_in_flight;
 	u32 prior_fackets;
 	int prior_packets;
 	int prior_sacked = tp->sacked_out;
+	int pkts_acked = 0;
 	int newly_acked_sacked = 0;
 	int frto_cwnd = 0;
 
@@ -3757,6 +3749,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	/* See if we can take anything off of the retransmit queue. */
 	flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una);
 
+	pkts_acked = prior_packets - tp->packets_out;
 	newly_acked_sacked = (prior_packets - prior_sacked) -
 			     (tp->packets_out - tp->sacked_out);
 
@@ -3771,8 +3764,9 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		if ((flag & FLAG_DATA_ACKED) && !frto_cwnd &&
 		    tcp_may_raise_cwnd(sk, flag))
 			tcp_cong_avoid(sk, ack, prior_in_flight);
-		tcp_fastretrans_alert(sk, prior_packets - tp->packets_out,
-				      newly_acked_sacked, flag);
+		is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
+		tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked,
+				      is_dupack, flag);
 	} else {
 		if ((flag & FLAG_DATA_ACKED) && !frto_cwnd)
 			tcp_cong_avoid(sk, ack, prior_in_flight);
@@ -3784,6 +3778,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	return 1;
 
 no_queue:
+	/* If data was DSACKed, see if we can undo a cwnd reduction. */
+	if (flag & FLAG_DSACKING_ACK)
+		tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked,
+				      is_dupack, flag);
 	/* If this ack opens up a zero window, clear backoff.  It was
 	 * being used to time the probes, and is probably far higher than
 	 * it needs to be for normal retransmission.
@@ -3797,10 +3795,14 @@ invalid_ack:
 	return -1;
 
 old_ack:
+	/* If data was SACKed, tag it and see if we should send more data.
+	 * If data was DSACKed, see if we can undo a cwnd reduction.
+	 */
 	if (TCP_SKB_CB(skb)->sacked) {
-		tcp_sacktag_write_queue(sk, skb, prior_snd_una);
-		if (icsk->icsk_ca_state == TCP_CA_Open)
-			tcp_try_keep_open(sk);
+		flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una);
+		newly_acked_sacked = tp->sacked_out - prior_sacked;
+		tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked,
+				      is_dupack, flag);
 	}
 
 	SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
@@ -4864,7 +4866,7 @@ static int tcp_prune_queue(struct sock *sk)
 
 	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
 		tcp_clamp_window(sk);
-	else if (tcp_memory_pressure)
+	else if (sk_under_memory_pressure(sk))
 		tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss);
 
 	tcp_collapse_ofo_queue(sk);
@@ -4930,11 +4932,11 @@ static int tcp_should_expand_sndbuf(const struct sock *sk)
 		return 0;
 
 	/* If we are under global TCP memory pressure, do not expand.  */
-	if (tcp_memory_pressure)
+	if (sk_under_memory_pressure(sk))
 		return 0;
 
 	/* If we are under soft global TCP memory pressure, do not expand.  */
-	if (atomic_long_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0])
+	if (sk_memory_allocated(sk) >= sk_prot_mem_limits(sk, 0))
 		return 0;
 
 	/* If we filled the congestion window, do not expand.  */
@@ -5809,6 +5811,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
 			goto discard;
 
 		if (th->syn) {
+			if (th->fin)
+				goto discard;
 			if (icsk->icsk_af_ops->conn_request(sk, skb) < 0)
 				return 1;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a744315..1eb4ad5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -73,6 +73,7 @@
 #include <net/xfrm.h>
 #include <net/netdma.h>
 #include <net/secure_seq.h>
+#include <net/tcp_memcontrol.h>
 
 #include <linux/inet.h>
 #include <linux/ipv6.h>
@@ -1510,6 +1511,8 @@ exit:
 	NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
 	return NULL;
 put_and_exit:
+	tcp_clear_xmit_timers(newsk);
+	tcp_cleanup_congestion_control(newsk);
 	bh_unlock_sock(newsk);
 	sock_put(newsk);
 	goto exit;
@@ -1915,7 +1918,8 @@ static int tcp_v4_init_sock(struct sock *sk)
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
 	local_bh_disable();
-	percpu_counter_inc(&tcp_sockets_allocated);
+	sock_update_memcg(sk);
+	sk_sockets_allocated_inc(sk);
 	local_bh_enable();
 
 	return 0;
@@ -1971,7 +1975,8 @@ void tcp_v4_destroy_sock(struct sock *sk)
 		tp->cookie_values = NULL;
 	}
 
-	percpu_counter_dec(&tcp_sockets_allocated);
+	sk_sockets_allocated_dec(sk);
+	sock_release_memcg(sk);
 }
 EXPORT_SYMBOL(tcp_v4_destroy_sock);
 
@@ -2618,7 +2623,6 @@ struct proto tcp_prot = {
 	.orphan_count		= &tcp_orphan_count,
 	.memory_allocated	= &tcp_memory_allocated,
 	.memory_pressure	= &tcp_memory_pressure,
-	.sysctl_mem		= sysctl_tcp_mem,
 	.sysctl_wmem		= sysctl_tcp_wmem,
 	.sysctl_rmem		= sysctl_tcp_rmem,
 	.max_header		= MAX_TCP_HEADER,
@@ -2632,10 +2636,14 @@ struct proto tcp_prot = {
 	.compat_setsockopt	= compat_tcp_setsockopt,
 	.compat_getsockopt	= compat_tcp_getsockopt,
 #endif
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+	.init_cgroup		= tcp_init_cgroup,
+	.destroy_cgroup		= tcp_destroy_cgroup,
+	.proto_cgroup		= tcp_proto_cgroup,
+#endif
 };
 EXPORT_SYMBOL(tcp_prot);
 
-
 static int __net_init tcp_sk_init(struct net *net)
 {
 	return inet_ctl_sock_create(&net->ipv4.tcp_sock,
diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c
new file mode 100644
index 0000000..7fed04f
--- /dev/null
+++ b/net/ipv4/tcp_memcontrol.c
@@ -0,0 +1,272 @@
+#include <net/tcp.h>
+#include <net/tcp_memcontrol.h>
+#include <net/sock.h>
+#include <net/ip.h>
+#include <linux/nsproxy.h>
+#include <linux/memcontrol.h>
+#include <linux/module.h>
+
+static u64 tcp_cgroup_read(struct cgroup *cont, struct cftype *cft);
+static int tcp_cgroup_write(struct cgroup *cont, struct cftype *cft,
+			    const char *buffer);
+static int tcp_cgroup_reset(struct cgroup *cont, unsigned int event);
+
+static struct cftype tcp_files[] = {
+	{
+		.name = "kmem.tcp.limit_in_bytes",
+		.write_string = tcp_cgroup_write,
+		.read_u64 = tcp_cgroup_read,
+		.private = RES_LIMIT,
+	},
+	{
+		.name = "kmem.tcp.usage_in_bytes",
+		.read_u64 = tcp_cgroup_read,
+		.private = RES_USAGE,
+	},
+	{
+		.name = "kmem.tcp.failcnt",
+		.private = RES_FAILCNT,
+		.trigger = tcp_cgroup_reset,
+		.read_u64 = tcp_cgroup_read,
+	},
+	{
+		.name = "kmem.tcp.max_usage_in_bytes",
+		.private = RES_MAX_USAGE,
+		.trigger = tcp_cgroup_reset,
+		.read_u64 = tcp_cgroup_read,
+	},
+};
+
+static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto)
+{
+	return container_of(cg_proto, struct tcp_memcontrol, cg_proto);
+}
+
+static void memcg_tcp_enter_memory_pressure(struct sock *sk)
+{
+	if (sk->sk_cgrp->memory_pressure)
+		*sk->sk_cgrp->memory_pressure = 1;
+}
+EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure);
+
+int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+	/*
+	 * The root cgroup does not use res_counters, but rather,
+	 * rely on the data already collected by the network
+	 * subsystem
+	 */
+	struct res_counter *res_parent = NULL;
+	struct cg_proto *cg_proto, *parent_cg;
+	struct tcp_memcontrol *tcp;
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+	struct net *net = current->nsproxy->net_ns;
+
+	cg_proto = tcp_prot.proto_cgroup(memcg);
+	if (!cg_proto)
+		goto create_files;
+
+	tcp = tcp_from_cgproto(cg_proto);
+
+	tcp->tcp_prot_mem[0] = net->ipv4.sysctl_tcp_mem[0];
+	tcp->tcp_prot_mem[1] = net->ipv4.sysctl_tcp_mem[1];
+	tcp->tcp_prot_mem[2] = net->ipv4.sysctl_tcp_mem[2];
+	tcp->tcp_memory_pressure = 0;
+
+	parent_cg = tcp_prot.proto_cgroup(parent);
+	if (parent_cg)
+		res_parent = parent_cg->memory_allocated;
+
+	res_counter_init(&tcp->tcp_memory_allocated, res_parent);
+	percpu_counter_init(&tcp->tcp_sockets_allocated, 0);
+
+	cg_proto->enter_memory_pressure = memcg_tcp_enter_memory_pressure;
+	cg_proto->memory_pressure = &tcp->tcp_memory_pressure;
+	cg_proto->sysctl_mem = tcp->tcp_prot_mem;
+	cg_proto->memory_allocated = &tcp->tcp_memory_allocated;
+	cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated;
+	cg_proto->memcg = memcg;
+
+create_files:
+	return cgroup_add_files(cgrp, ss, tcp_files,
+				ARRAY_SIZE(tcp_files));
+}
+EXPORT_SYMBOL(tcp_init_cgroup);
+
+void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+	struct cg_proto *cg_proto;
+	struct tcp_memcontrol *tcp;
+	u64 val;
+
+	cg_proto = tcp_prot.proto_cgroup(memcg);
+	if (!cg_proto)
+		return;
+
+	tcp = tcp_from_cgproto(cg_proto);
+	percpu_counter_destroy(&tcp->tcp_sockets_allocated);
+
+	val = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE);
+
+	if (val != RESOURCE_MAX)
+		jump_label_dec(&memcg_socket_limit_enabled);
+}
+EXPORT_SYMBOL(tcp_destroy_cgroup);
+
+static int tcp_update_limit(struct mem_cgroup *memcg, u64 val)
+{
+	struct net *net = current->nsproxy->net_ns;
+	struct tcp_memcontrol *tcp;
+	struct cg_proto *cg_proto;
+	u64 old_lim;
+	int i;
+	int ret;
+
+	cg_proto = tcp_prot.proto_cgroup(memcg);
+	if (!cg_proto)
+		return -EINVAL;
+
+	if (val > RESOURCE_MAX)
+		val = RESOURCE_MAX;
+
+	tcp = tcp_from_cgproto(cg_proto);
+
+	old_lim = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
+	ret = res_counter_set_limit(&tcp->tcp_memory_allocated, val);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < 3; i++)
+		tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT,
+					     net->ipv4.sysctl_tcp_mem[i]);
+
+	if (val == RESOURCE_MAX && old_lim != RESOURCE_MAX)
+		jump_label_dec(&memcg_socket_limit_enabled);
+	else if (old_lim == RESOURCE_MAX && val != RESOURCE_MAX)
+		jump_label_inc(&memcg_socket_limit_enabled);
+
+	return 0;
+}
+
+static int tcp_cgroup_write(struct cgroup *cont, struct cftype *cft,
+			    const char *buffer)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	unsigned long long val;
+	int ret = 0;
+
+	switch (cft->private) {
+	case RES_LIMIT:
+		/* see memcontrol.c */
+		ret = res_counter_memparse_write_strategy(buffer, &val);
+		if (ret)
+			break;
+		ret = tcp_update_limit(memcg, val);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret;
+}
+
+static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val)
+{
+	struct tcp_memcontrol *tcp;
+	struct cg_proto *cg_proto;
+
+	cg_proto = tcp_prot.proto_cgroup(memcg);
+	if (!cg_proto)
+		return default_val;
+
+	tcp = tcp_from_cgproto(cg_proto);
+	return res_counter_read_u64(&tcp->tcp_memory_allocated, type);
+}
+
+static u64 tcp_read_usage(struct mem_cgroup *memcg)
+{
+	struct tcp_memcontrol *tcp;
+	struct cg_proto *cg_proto;
+
+	cg_proto = tcp_prot.proto_cgroup(memcg);
+	if (!cg_proto)
+		return atomic_long_read(&tcp_memory_allocated) << PAGE_SHIFT;
+
+	tcp = tcp_from_cgproto(cg_proto);
+	return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE);
+}
+
+static u64 tcp_cgroup_read(struct cgroup *cont, struct cftype *cft)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	u64 val;
+
+	switch (cft->private) {
+	case RES_LIMIT:
+		val = tcp_read_stat(memcg, RES_LIMIT, RESOURCE_MAX);
+		break;
+	case RES_USAGE:
+		val = tcp_read_usage(memcg);
+		break;
+	case RES_FAILCNT:
+	case RES_MAX_USAGE:
+		val = tcp_read_stat(memcg, cft->private, 0);
+		break;
+	default:
+		BUG();
+	}
+	return val;
+}
+
+static int tcp_cgroup_reset(struct cgroup *cont, unsigned int event)
+{
+	struct mem_cgroup *memcg;
+	struct tcp_memcontrol *tcp;
+	struct cg_proto *cg_proto;
+
+	memcg = mem_cgroup_from_cont(cont);
+	cg_proto = tcp_prot.proto_cgroup(memcg);
+	if (!cg_proto)
+		return 0;
+	tcp = tcp_from_cgproto(cg_proto);
+
+	switch (event) {
+	case RES_MAX_USAGE:
+		res_counter_reset_max(&tcp->tcp_memory_allocated);
+		break;
+	case RES_FAILCNT:
+		res_counter_reset_failcnt(&tcp->tcp_memory_allocated);
+		break;
+	}
+
+	return 0;
+}
+
+unsigned long long tcp_max_memory(const struct mem_cgroup *memcg)
+{
+	struct tcp_memcontrol *tcp;
+	struct cg_proto *cg_proto;
+
+	cg_proto = tcp_prot.proto_cgroup((struct mem_cgroup *)memcg);
+	if (!cg_proto)
+		return 0;
+
+	tcp = tcp_from_cgproto(cg_proto);
+	return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT);
+}
+
+void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx)
+{
+	struct tcp_memcontrol *tcp;
+	struct cg_proto *cg_proto;
+
+	cg_proto = tcp_prot.proto_cgroup(memcg);
+	if (!cg_proto)
+		return;
+
+	tcp = tcp_from_cgproto(cg_proto);
+
+	tcp->tcp_prot_mem[idx] = val;
+}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 66363b6..550e755 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -336,15 +336,15 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		tcptw->tw_ts_recent	= tp->rx_opt.ts_recent;
 		tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp;
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		if (tw->tw_family == PF_INET6) {
 			struct ipv6_pinfo *np = inet6_sk(sk);
 			struct inet6_timewait_sock *tw6;
 
 			tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot);
 			tw6 = inet6_twsk((struct sock *)tw);
-			ipv6_addr_copy(&tw6->tw_v6_daddr, &np->daddr);
-			ipv6_addr_copy(&tw6->tw_v6_rcv_saddr, &np->rcv_saddr);
+			tw6->tw_v6_daddr = np->daddr;
+			tw6->tw_v6_rcv_saddr = np->rcv_saddr;
 			tw->tw_tclass = np->tclass;
 			tw->tw_ipv6only = np->ipv6only;
 		}
@@ -425,7 +425,7 @@ static inline void TCP_ECN_openreq_child(struct tcp_sock *tp,
  */
 struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct sk_buff *skb)
 {
-	struct sock *newsk = inet_csk_clone(sk, req, GFP_ATOMIC);
+	struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC);
 
 	if (newsk != NULL) {
 		const struct inet_request_sock *ireq = inet_rsk(req);
@@ -495,7 +495,9 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 		newtp->frto_counter = 0;
 		newtp->frto_highmark = 0;
 
-		newicsk->icsk_ca_ops = &tcp_init_congestion_ops;
+		if (newicsk->icsk_ca_ops != &tcp_init_congestion_ops &&
+		    !try_module_get(newicsk->icsk_ca_ops->owner))
+			newicsk->icsk_ca_ops = &tcp_init_congestion_ops;
 
 		tcp_set_ca_state(newsk, TCP_CA_Open);
 		tcp_init_xmit_timers(newsk);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 980b98f..8c8de27 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1093,6 +1093,13 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 {
 	int i, k, eat;
 
+	eat = min_t(int, len, skb_headlen(skb));
+	if (eat) {
+		__skb_pull(skb, eat);
+		len -= eat;
+		if (!len)
+			return;
+	}
 	eat = len;
 	k = 0;
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
@@ -1124,11 +1131,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 	if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
 		return -ENOMEM;
 
-	/* If len == headlen, we avoid __skb_pull to preserve alignment. */
-	if (unlikely(len < skb_headlen(skb)))
-		__skb_pull(skb, len);
-	else
-		__pskb_trim_head(skb, len - skb_headlen(skb));
+	__pskb_trim_head(skb, len);
 
 	TCP_SKB_CB(skb)->seq += len;
 	skb->ip_summed = CHECKSUM_PARTIAL;
@@ -1382,7 +1385,7 @@ static inline int tcp_minshall_check(const struct tcp_sock *tp)
 /* Return 0, if packet can be sent now without violation Nagle's rules:
  * 1. It is full sized.
  * 2. Or it contains FIN. (already checked by caller)
- * 3. Or TCP_NODELAY was set.
+ * 3. Or TCP_CORK is not set, and TCP_NODELAY is set.
  * 4. Or TCP_CORK is not set, and all sent packets are ACKed.
  *    With Minshall's modification: all sent small packets are ACKed.
  */
@@ -1581,7 +1584,7 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
 		 * frame, so if we have space for more than 3 frames
 		 * then send now.
 		 */
-		if (limit > tcp_max_burst(tp) * tp->mss_cache)
+		if (limit > tcp_max_tso_deferred_mss(tp) * tp->mss_cache)
 			goto send_now;
 	}
 
@@ -1919,7 +1922,7 @@ u32 __tcp_select_window(struct sock *sk)
 	if (free_space < (full_space >> 1)) {
 		icsk->icsk_ack.quick = 0;
 
-		if (tcp_memory_pressure)
+		if (sk_under_memory_pressure(sk))
 			tp->rcv_ssthresh = min(tp->rcv_ssthresh,
 					       4U * tp->advmss);
 
@@ -2147,7 +2150,15 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 	 */
 	TCP_SKB_CB(skb)->when = tcp_time_stamp;
 
-	err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
+	/* make sure skb->data is aligned on arches that require it */
+	if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) {
+		struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
+						   GFP_ATOMIC);
+		err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
+			     -ENOBUFS;
+	} else {
+		err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
+	}
 
 	if (err == 0) {
 		/* Update global TCP statistics. */
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 2e0f0af..40a41f0 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -261,7 +261,7 @@ static void tcp_delack_timer(unsigned long data)
 	}
 
 out:
-	if (tcp_memory_pressure)
+	if (sk_under_memory_pressure(sk))
 		sk_mem_reclaim(sk);
 out_unlock:
 	bh_unlock_sock(sk);
@@ -340,7 +340,7 @@ void tcp_retransmit_timer(struct sock *sk)
 			       &inet->inet_daddr, ntohs(inet->inet_dport),
 			       inet->inet_num, tp->snd_una, tp->snd_nxt);
 		}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		else if (sk->sk_family == AF_INET6) {
 			struct ipv6_pinfo *np = inet6_sk(sk);
 			LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c
index ac3b3ee..0177598 100644
--- a/net/ipv4/tunnel4.c
+++ b/net/ipv4/tunnel4.c
@@ -105,7 +105,7 @@ drop:
 	return 0;
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static int tunnel64_rcv(struct sk_buff *skb)
 {
 	struct xfrm_tunnel *handler;
@@ -134,7 +134,7 @@ static void tunnel4_err(struct sk_buff *skb, u32 info)
 			break;
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static void tunnel64_err(struct sk_buff *skb, u32 info)
 {
 	struct xfrm_tunnel *handler;
@@ -152,7 +152,7 @@ static const struct net_protocol tunnel4_protocol = {
 	.netns_ok	=	1,
 };
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static const struct net_protocol tunnel64_protocol = {
 	.handler	=	tunnel64_rcv,
 	.err_handler	=	tunnel64_err,
@@ -167,7 +167,7 @@ static int __init tunnel4_init(void)
 		printk(KERN_ERR "tunnel4 init: can't add protocol\n");
 		return -EAGAIN;
 	}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	if (inet_add_protocol(&tunnel64_protocol, IPPROTO_IPV6)) {
 		printk(KERN_ERR "tunnel64 init: can't add protocol\n");
 		inet_del_protocol(&tunnel4_protocol, IPPROTO_IPIP);
@@ -179,7 +179,7 @@ static int __init tunnel4_init(void)
 
 static void __exit tunnel4_fini(void)
 {
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	if (inet_del_protocol(&tunnel64_protocol, IPPROTO_IPV6))
 		printk(KERN_ERR "tunnel64 close: can't remove protocol\n");
 #endif
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ab0966d..5d075b5 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -445,7 +445,7 @@ exact_match:
 /* UDP is nearly always wildcards out the wazoo, it makes no sense to try
  * harder than this. -DaveM
  */
-static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
+struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 		__be16 sport, __be32 daddr, __be16 dport,
 		int dif, struct udp_table *udptable)
 {
@@ -512,6 +512,7 @@ begin:
 	rcu_read_unlock();
 	return result;
 }
+EXPORT_SYMBOL_GPL(__udp4_lib_lookup);
 
 static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
 						 __be16 sport, __be16 dport,
@@ -1164,7 +1165,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	struct inet_sock *inet = inet_sk(sk);
 	struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
 	struct sk_buff *skb;
-	unsigned int ulen;
+	unsigned int ulen, copied;
 	int peeked;
 	int err;
 	int is_udplite = IS_UDPLITE(sk);
@@ -1186,9 +1187,10 @@ try_again:
 		goto out;
 
 	ulen = skb->len - sizeof(struct udphdr);
-	if (len > ulen)
-		len = ulen;
-	else if (len < ulen)
+	copied = len;
+	if (copied > ulen)
+		copied = ulen;
+	else if (copied < ulen)
 		msg->msg_flags |= MSG_TRUNC;
 
 	/*
@@ -1197,14 +1199,14 @@ try_again:
 	 * coverage checksum (UDP-Lite), do it before the copy.
 	 */
 
-	if (len < ulen || UDP_SKB_CB(skb)->partial_cov) {
+	if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
 		if (udp_lib_checksum_complete(skb))
 			goto csum_copy_err;
 	}
 
 	if (skb_csum_unnecessary(skb))
 		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
-					      msg->msg_iov, len);
+					      msg->msg_iov, copied);
 	else {
 		err = skb_copy_and_csum_datagram_iovec(skb,
 						       sizeof(struct udphdr),
@@ -1233,7 +1235,7 @@ try_again:
 	if (inet->cmsg_flags)
 		ip_cmsg_recv(msg, skb);
 
-	err = len;
+	err = copied;
 	if (flags & MSG_TRUNC)
 		err = ulen;
 
@@ -1357,7 +1359,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	if (inet_sk(sk)->inet_daddr)
 		sock_rps_save_rxhash(sk, skb);
 
-	rc = ip_queue_rcv_skb(sk, skb);
+	rc = sock_queue_rcv_skb(sk, skb);
 	if (rc < 0) {
 		int is_udplite = IS_UDPLITE(sk);
 
@@ -1473,6 +1475,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 	rc = 0;
 
+	ipv4_pktinfo_prepare(skb);
 	bh_lock_sock(sk);
 	if (!sock_owned_by_user(sk))
 		rc = __udp_queue_rcv_skb(sk, skb);
@@ -2246,7 +2249,8 @@ int udp4_ufo_send_check(struct sk_buff *skb)
 	return 0;
 }
 
-struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features)
+struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
+	netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	unsigned int mss;
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
new file mode 100644
index 0000000..69f8a7c
--- /dev/null
+++ b/net/ipv4/udp_diag.c
@@ -0,0 +1,201 @@
+/*
+ * udp_diag.c	Module for monitoring UDP transport protocols sockets.
+ *
+ * Authors:	Pavel Emelyanov, <xemul@parallels.com>
+ *
+ *	This program is free software; you can redistribute it and/or
+ *      modify it under the terms of the GNU General Public License
+ *      as published by the Free Software Foundation; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+
+#include <linux/module.h>
+#include <linux/inet_diag.h>
+#include <linux/udp.h>
+#include <net/udp.h>
+#include <net/udplite.h>
+#include <linux/inet_diag.h>
+#include <linux/sock_diag.h>
+
+static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
+		struct netlink_callback *cb, struct inet_diag_req *req,
+		struct nlattr *bc)
+{
+	if (!inet_diag_bc_sk(bc, sk))
+		return 0;
+
+	return inet_sk_diag_fill(sk, NULL, skb, req, NETLINK_CB(cb->skb).pid,
+			cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
+}
+
+static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
+		const struct nlmsghdr *nlh, struct inet_diag_req *req)
+{
+	int err = -EINVAL;
+	struct sock *sk;
+	struct sk_buff *rep;
+
+	if (req->sdiag_family == AF_INET)
+		sk = __udp4_lib_lookup(&init_net,
+				req->id.idiag_src[0], req->id.idiag_sport,
+				req->id.idiag_dst[0], req->id.idiag_dport,
+				req->id.idiag_if, tbl);
+#if IS_ENABLED(CONFIG_IPV6)
+	else if (req->sdiag_family == AF_INET6)
+		sk = __udp6_lib_lookup(&init_net,
+				(struct in6_addr *)req->id.idiag_src,
+				req->id.idiag_sport,
+				(struct in6_addr *)req->id.idiag_dst,
+				req->id.idiag_dport,
+				req->id.idiag_if, tbl);
+#endif
+	else
+		goto out_nosk;
+
+	err = -ENOENT;
+	if (sk == NULL)
+		goto out_nosk;
+
+	err = sock_diag_check_cookie(sk, req->id.idiag_cookie);
+	if (err)
+		goto out;
+
+	err = -ENOMEM;
+	rep = alloc_skb(NLMSG_SPACE((sizeof(struct inet_diag_msg) +
+				     sizeof(struct inet_diag_meminfo) +
+				     64)), GFP_KERNEL);
+	if (!rep)
+		goto out;
+
+	err = inet_sk_diag_fill(sk, NULL, rep, req,
+			   NETLINK_CB(in_skb).pid,
+			   nlh->nlmsg_seq, 0, nlh);
+	if (err < 0) {
+		WARN_ON(err == -EMSGSIZE);
+		kfree_skb(rep);
+		goto out;
+	}
+	err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid,
+			      MSG_DONTWAIT);
+	if (err > 0)
+		err = 0;
+out:
+	if (sk)
+		sock_put(sk);
+out_nosk:
+	return err;
+}
+
+static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlink_callback *cb,
+		struct inet_diag_req *r, struct nlattr *bc)
+{
+	int num, s_num, slot, s_slot;
+
+	s_slot = cb->args[0];
+	num = s_num = cb->args[1];
+
+	for (slot = s_slot; slot <= table->mask; num = s_num = 0, slot++) {
+		struct sock *sk;
+		struct hlist_nulls_node *node;
+		struct udp_hslot *hslot = &table->hash[slot];
+
+		if (hlist_nulls_empty(&hslot->head))
+			continue;
+
+		spin_lock_bh(&hslot->lock);
+		sk_nulls_for_each(sk, node, &hslot->head) {
+			struct inet_sock *inet = inet_sk(sk);
+
+			if (num < s_num)
+				goto next;
+			if (!(r->idiag_states & (1 << sk->sk_state)))
+				goto next;
+			if (r->sdiag_family != AF_UNSPEC &&
+					sk->sk_family != r->sdiag_family)
+				goto next;
+			if (r->id.idiag_sport != inet->inet_sport &&
+			    r->id.idiag_sport)
+				goto next;
+			if (r->id.idiag_dport != inet->inet_dport &&
+			    r->id.idiag_dport)
+				goto next;
+
+			if (sk_diag_dump(sk, skb, cb, r, bc) < 0) {
+				spin_unlock_bh(&hslot->lock);
+				goto done;
+			}
+next:
+			num++;
+		}
+		spin_unlock_bh(&hslot->lock);
+	}
+done:
+	cb->args[0] = slot;
+	cb->args[1] = num;
+}
+
+static void udp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
+		struct inet_diag_req *r, struct nlattr *bc)
+{
+	udp_dump(&udp_table, skb, cb, r, bc);
+}
+
+static int udp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
+		struct inet_diag_req *req)
+{
+	return udp_dump_one(&udp_table, in_skb, nlh, req);
+}
+
+static const struct inet_diag_handler udp_diag_handler = {
+	.dump		 = udp_diag_dump,
+	.dump_one	 = udp_diag_dump_one,
+	.idiag_type	 = IPPROTO_UDP,
+};
+
+static void udplite_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
+		struct inet_diag_req *r, struct nlattr *bc)
+{
+	udp_dump(&udplite_table, skb, cb, r, bc);
+}
+
+static int udplite_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh,
+		struct inet_diag_req *req)
+{
+	return udp_dump_one(&udplite_table, in_skb, nlh, req);
+}
+
+static const struct inet_diag_handler udplite_diag_handler = {
+	.dump		 = udplite_diag_dump,
+	.dump_one	 = udplite_diag_dump_one,
+	.idiag_type	 = IPPROTO_UDPLITE,
+};
+
+static int __init udp_diag_init(void)
+{
+	int err;
+
+	err = inet_diag_register(&udp_diag_handler);
+	if (err)
+		goto out;
+	err = inet_diag_register(&udplite_diag_handler);
+	if (err)
+		goto out_lite;
+out:
+	return err;
+out_lite:
+	inet_diag_unregister(&udp_diag_handler);
+	goto out;
+}
+
+static void __exit udp_diag_exit(void)
+{
+	inet_diag_unregister(&udplite_diag_handler);
+	inet_diag_unregister(&udp_diag_handler);
+}
+
+module_init(udp_diag_init);
+module_exit(udp_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-17 /* AF_INET - IPPROTO_UDP */);
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-136 /* AF_INET - IPPROTO_UDPLITE */);
diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c
index 8280645..9247d9d 100644
--- a/net/ipv4/xfrm4_tunnel.c
+++ b/net/ipv4/xfrm4_tunnel.c
@@ -64,7 +64,7 @@ static struct xfrm_tunnel xfrm_tunnel_handler __read_mostly = {
 	.priority	=	2,
 };
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static struct xfrm_tunnel xfrm64_tunnel_handler __read_mostly = {
 	.handler	=	xfrm_tunnel_rcv,
 	.err_handler	=	xfrm_tunnel_err,
@@ -84,7 +84,7 @@ static int __init ipip_init(void)
 		xfrm_unregister_type(&ipip_type, AF_INET);
 		return -EAGAIN;
 	}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	if (xfrm4_tunnel_register(&xfrm64_tunnel_handler, AF_INET6)) {
 		printk(KERN_INFO "ipip init: can't add xfrm handler for AF_INET6\n");
 		xfrm4_tunnel_deregister(&xfrm_tunnel_handler, AF_INET);
@@ -97,7 +97,7 @@ static int __init ipip_init(void)
 
 static void __exit ipip_fini(void)
 {
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	if (xfrm4_tunnel_deregister(&xfrm64_tunnel_handler, AF_INET6))
 		printk(KERN_INFO "ipip close: can't remove xfrm handler for AF_INET6\n");
 #endif
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index cf88df8..59a9d0e 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -630,13 +630,13 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
 		goto out;
 	}
 
-	rt = addrconf_dst_alloc(idev, addr, 0);
+	rt = addrconf_dst_alloc(idev, addr, false);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
 		goto out;
 	}
 
-	ipv6_addr_copy(&ifa->addr, addr);
+	ifa->addr = *addr;
 
 	spin_lock_init(&ifa->lock);
 	spin_lock_init(&ifa->state_lock);
@@ -657,7 +657,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen,
 	 * layer address of our nexhop router
 	 */
 
-	if (dst_get_neighbour_raw(&rt->dst) == NULL)
+	if (dst_get_neighbour_noref_raw(&rt->dst) == NULL)
 		ifa->flags &= ~IFA_F_OPTIMISTIC;
 
 	ifa->idev = idev;
@@ -1228,7 +1228,7 @@ try_nextdev:
 	if (!hiscore->ifa)
 		return -EADDRNOTAVAIL;
 
-	ipv6_addr_copy(saddr, &hiscore->ifa->addr);
+	*saddr = hiscore->ifa->addr;
 	in6_ifa_put(hiscore->ifa);
 	return 0;
 }
@@ -1249,7 +1249,7 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
 		list_for_each_entry(ifp, &idev->addr_list, if_list) {
 			if (ifp->scope == IFA_LINK &&
 			    !(ifp->flags & banned_flags)) {
-				ipv6_addr_copy(addr, &ifp->addr);
+				*addr = ifp->addr;
 				err = 0;
 				break;
 			}
@@ -1700,7 +1700,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
 		.fc_protocol = RTPROT_KERNEL,
 	};
 
-	ipv6_addr_copy(&cfg.fc_dst, pfx);
+	cfg.fc_dst = *pfx;
 
 	/* Prevent useless cloning on PtP SIT.
 	   This thing is done here expecting that the whole
@@ -1805,7 +1805,8 @@ static struct inet6_dev *addrconf_add_dev(struct net_device *dev)
 		return ERR_PTR(-EACCES);
 
 	/* Add default multicast route */
-	addrconf_add_mroute(dev);
+	if (!(dev->flags & IFF_LOOPBACK))
+		addrconf_add_mroute(dev);
 
 	/* Add link local route */
 	addrconf_add_lroute(dev);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index d27c797..273f48d 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -347,7 +347,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 			 */
 			v4addr = LOOPBACK4_IPV6;
 			if (!(addr_type & IPV6_ADDR_MULTICAST))	{
-				if (!inet->transparent &&
+				if (!(inet->freebind || inet->transparent) &&
 				    !ipv6_chk_addr(net, &addr->sin6_addr,
 						   dev, 0)) {
 					err = -EADDRNOTAVAIL;
@@ -361,10 +361,10 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	inet->inet_rcv_saddr = v4addr;
 	inet->inet_saddr = v4addr;
 
-	ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr);
+	np->rcv_saddr = addr->sin6_addr;
 
 	if (!(addr_type & IPV6_ADDR_MULTICAST))
-		ipv6_addr_copy(&np->saddr, &addr->sin6_addr);
+		np->saddr = addr->sin6_addr;
 
 	/* Make sure we are allowed to bind here. */
 	if (sk->sk_prot->get_port(sk, snum)) {
@@ -458,14 +458,14 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
 		    peer == 1)
 			return -ENOTCONN;
 		sin->sin6_port = inet->inet_dport;
-		ipv6_addr_copy(&sin->sin6_addr, &np->daddr);
+		sin->sin6_addr = np->daddr;
 		if (np->sndflow)
 			sin->sin6_flowinfo = np->flow_label;
 	} else {
 		if (ipv6_addr_any(&np->rcv_saddr))
-			ipv6_addr_copy(&sin->sin6_addr, &np->saddr);
+			sin->sin6_addr = np->saddr;
 		else
-			ipv6_addr_copy(&sin->sin6_addr, &np->rcv_saddr);
+			sin->sin6_addr = np->rcv_saddr;
 
 		sin->sin6_port = inet->inet_sport;
 	}
@@ -660,8 +660,8 @@ int inet6_sk_rebuild_header(struct sock *sk)
 
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_proto = sk->sk_protocol;
-		ipv6_addr_copy(&fl6.daddr, &np->daddr);
-		ipv6_addr_copy(&fl6.saddr, &np->saddr);
+		fl6.daddr = np->daddr;
+		fl6.saddr = np->saddr;
 		fl6.flowlabel = np->flow_label;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 		fl6.flowi6_mark = sk->sk_mark;
@@ -769,7 +769,8 @@ out:
 	return err;
 }
 
-static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, u32 features)
+static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
+	netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	struct ipv6hdr *ipv6h;
@@ -985,9 +986,9 @@ static int __net_init ipv6_init_mibs(struct net *net)
 			  sizeof(struct icmpv6_mib),
 			  __alignof__(struct icmpv6_mib)) < 0)
 		goto err_icmp_mib;
-	if (snmp_mib_init((void __percpu **)net->mib.icmpv6msg_statistics,
-			  sizeof(struct icmpv6msg_mib),
-			  __alignof__(struct icmpv6msg_mib)) < 0)
+	net->mib.icmpv6msg_statistics = kzalloc(sizeof(struct icmpv6msg_mib),
+						GFP_KERNEL);
+	if (!net->mib.icmpv6msg_statistics)
 		goto err_icmpmsg_mib;
 	return 0;
 
@@ -1008,7 +1009,7 @@ static void ipv6_cleanup_mibs(struct net *net)
 	snmp_mib_free((void __percpu **)net->mib.udplite_stats_in6);
 	snmp_mib_free((void __percpu **)net->mib.ipv6_statistics);
 	snmp_mib_free((void __percpu **)net->mib.icmpv6_statistics);
-	snmp_mib_free((void __percpu **)net->mib.icmpv6msg_statistics);
+	kfree(net->mib.icmpv6msg_statistics);
 }
 
 static int __net_init inet6_net_init(struct net *net)
@@ -1115,6 +1116,8 @@ static int __init inet6_init(void)
 	if (err)
 		goto static_sysctl_fail;
 #endif
+	tcpv6_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem;
+
 	/*
 	 *	ipngwg API draft makes clear that the correct semantics
 	 *	for TCP and UDP is to consider one TCP and UDP instance
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index 2195ae6..2ae79db 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -193,9 +193,9 @@ static void ipv6_rearrange_destopt(struct ipv6hdr *iph, struct ipv6_opt_hdr *des
 						printk(KERN_WARNING "destopt hao: invalid header length: %u\n", hao->length);
 					goto bad;
 				}
-				ipv6_addr_copy(&final_addr, &hao->addr);
-				ipv6_addr_copy(&hao->addr, &iph->saddr);
-				ipv6_addr_copy(&iph->saddr, &final_addr);
+				final_addr = hao->addr;
+				hao->addr = iph->saddr;
+				iph->saddr = final_addr;
 			}
 			break;
 		}
@@ -241,13 +241,13 @@ static void ipv6_rearrange_rthdr(struct ipv6hdr *iph, struct ipv6_rt_hdr *rthdr)
 	segments = rthdr->hdrlen >> 1;
 
 	addrs = ((struct rt0_hdr *)rthdr)->addr;
-	ipv6_addr_copy(&final_addr, addrs + segments - 1);
+	final_addr = addrs[segments - 1];
 
 	addrs += segments - segments_left;
 	memmove(addrs + 1, addrs, (segments_left - 1) * sizeof(*addrs));
 
-	ipv6_addr_copy(addrs, &iph->daddr);
-	ipv6_addr_copy(&iph->daddr, &final_addr);
+	addrs[0] = iph->daddr;
+	iph->daddr = final_addr;
 }
 
 static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir)
@@ -324,8 +324,6 @@ static void ah6_output_done(struct crypto_async_request *base, int err)
 #endif
 	}
 
-	err = ah->nexthdr;
-
 	kfree(AH_SKB_CB(skb)->tmp);
 	xfrm_output_resume(skb, err);
 }
@@ -466,12 +464,12 @@ static void ah6_input_done(struct crypto_async_request *base, int err)
 	if (err)
 		goto out;
 
+	err = ah->nexthdr;
+
 	skb->network_header += ah_hlen;
 	memcpy(skb_network_header(skb), work_iph, hdr_len);
 	__skb_pull(skb, ah_hlen + hdr_len);
 	skb_set_transport_header(skb, -hdr_len);
-
-	err = ah->nexthdr;
 out:
 	kfree(AH_SKB_CB(skb)->tmp);
 	xfrm_input_resume(skb, err);
@@ -583,8 +581,6 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
 		if (err == -EINPROGRESS)
 			goto out;
 
-		if (err == -EBUSY)
-			err = NET_XMIT_DROP;
 		goto out_free;
 	}
 
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 674255f..cc540f9 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -75,7 +75,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	if (pac == NULL)
 		return -ENOMEM;
 	pac->acl_next = NULL;
-	ipv6_addr_copy(&pac->acl_addr, addr);
+	pac->acl_addr = *addr;
 
 	rcu_read_lock();
 	if (ifindex == 0) {
@@ -289,14 +289,14 @@ int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr)
 		goto out;
 	}
 
-	rt = addrconf_dst_alloc(idev, addr, 1);
+	rt = addrconf_dst_alloc(idev, addr, true);
 	if (IS_ERR(rt)) {
 		kfree(aca);
 		err = PTR_ERR(rt);
 		goto out;
 	}
 
-	ipv6_addr_copy(&aca->aca_addr, addr);
+	aca->aca_addr = *addr;
 	aca->aca_idev = idev;
 	aca->aca_rt = rt;
 	aca->aca_users = 1;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index e248069..ae08aee 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -71,7 +71,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 			if (flowlabel == NULL)
 				return -EINVAL;
-			ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
+			usin->sin6_addr = flowlabel->dst;
 		}
 	}
 
@@ -143,7 +143,7 @@ ipv4_connected:
 		}
 	}
 
-	ipv6_addr_copy(&np->daddr, daddr);
+	np->daddr = *daddr;
 	np->flow_label = fl6.flowlabel;
 
 	inet->inet_dport = usin->sin6_port;
@@ -154,8 +154,8 @@ ipv4_connected:
 	 */
 
 	fl6.flowi6_proto = sk->sk_protocol;
-	ipv6_addr_copy(&fl6.daddr, &np->daddr);
-	ipv6_addr_copy(&fl6.saddr, &np->saddr);
+	fl6.daddr = np->daddr;
+	fl6.saddr = np->saddr;
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_dport = inet->inet_dport;
@@ -179,10 +179,10 @@ ipv4_connected:
 	/* source address lookup done in ip6_dst_lookup */
 
 	if (ipv6_addr_any(&np->saddr))
-		ipv6_addr_copy(&np->saddr, &fl6.saddr);
+		np->saddr = fl6.saddr;
 
 	if (ipv6_addr_any(&np->rcv_saddr)) {
-		ipv6_addr_copy(&np->rcv_saddr, &fl6.saddr);
+		np->rcv_saddr = fl6.saddr;
 		inet->inet_rcv_saddr = LOOPBACK4_IPV6;
 		if (sk->sk_prot->rehash)
 			sk->sk_prot->rehash(sk);
@@ -257,7 +257,7 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info)
 	skb_put(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	iph = ipv6_hdr(skb);
-	ipv6_addr_copy(&iph->daddr, &fl6->daddr);
+	iph->daddr = fl6->daddr;
 
 	serr = SKB_EXT_ERR(skb);
 	serr->ee.ee_errno = err;
@@ -294,7 +294,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu)
 	skb_put(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	iph = ipv6_hdr(skb);
-	ipv6_addr_copy(&iph->daddr, &fl6->daddr);
+	iph->daddr = fl6->daddr;
 
 	mtu_info = IP6CBMTU(skb);
 
@@ -303,7 +303,7 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu)
 	mtu_info->ip6m_addr.sin6_port = 0;
 	mtu_info->ip6m_addr.sin6_flowinfo = 0;
 	mtu_info->ip6m_addr.sin6_scope_id = fl6->flowi6_oif;
-	ipv6_addr_copy(&mtu_info->ip6m_addr.sin6_addr, &ipv6_hdr(skb)->daddr);
+	mtu_info->ip6m_addr.sin6_addr = ipv6_hdr(skb)->daddr;
 
 	__skb_pull(skb, skb_tail_pointer(skb) - skb->data);
 	skb_reset_transport_header(skb);
@@ -354,8 +354,8 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
 		sin->sin6_port = serr->port;
 		sin->sin6_scope_id = 0;
 		if (skb->protocol == htons(ETH_P_IPV6)) {
-			ipv6_addr_copy(&sin->sin6_addr,
-				  (struct in6_addr *)(nh + serr->addr_offset));
+			sin->sin6_addr =
+				*(struct in6_addr *)(nh + serr->addr_offset);
 			if (np->sndflow)
 				sin->sin6_flowinfo =
 					(*(__be32 *)(nh + serr->addr_offset - 24) &
@@ -376,7 +376,7 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len)
 		sin->sin6_flowinfo = 0;
 		sin->sin6_scope_id = 0;
 		if (skb->protocol == htons(ETH_P_IPV6)) {
-			ipv6_addr_copy(&sin->sin6_addr, &ipv6_hdr(skb)->saddr);
+			sin->sin6_addr = ipv6_hdr(skb)->saddr;
 			if (np->rxopt.all)
 				datagram_recv_ctl(sk, msg, skb);
 			if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL)
@@ -451,7 +451,7 @@ int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len)
 		sin->sin6_flowinfo = 0;
 		sin->sin6_port = 0;
 		sin->sin6_scope_id = mtu_info.ip6m_addr.sin6_scope_id;
-		ipv6_addr_copy(&sin->sin6_addr, &mtu_info.ip6m_addr.sin6_addr);
+		sin->sin6_addr = mtu_info.ip6m_addr.sin6_addr;
 	}
 
 	put_cmsg(msg, SOL_IPV6, IPV6_PATHMTU, sizeof(mtu_info), &mtu_info);
@@ -475,7 +475,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
 		struct in6_pktinfo src_info;
 
 		src_info.ipi6_ifindex = opt->iif;
-		ipv6_addr_copy(&src_info.ipi6_addr, &ipv6_hdr(skb)->daddr);
+		src_info.ipi6_addr = ipv6_hdr(skb)->daddr;
 		put_cmsg(msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
 	}
 
@@ -550,7 +550,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
 		struct in6_pktinfo src_info;
 
 		src_info.ipi6_ifindex = opt->iif;
-		ipv6_addr_copy(&src_info.ipi6_addr, &ipv6_hdr(skb)->daddr);
+		src_info.ipi6_addr = ipv6_hdr(skb)->daddr;
 		put_cmsg(msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info);
 	}
 	if (np->rxopt.bits.rxohlim) {
@@ -584,7 +584,7 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb)
 			 */
 
 			sin6.sin6_family = AF_INET6;
-			ipv6_addr_copy(&sin6.sin6_addr, &ipv6_hdr(skb)->daddr);
+			sin6.sin6_addr = ipv6_hdr(skb)->daddr;
 			sin6.sin6_port = ports[1];
 			sin6.sin6_flowinfo = 0;
 			sin6.sin6_scope_id = 0;
@@ -654,12 +654,12 @@ int datagram_send_ctl(struct net *net, struct sock *sk,
 
 			if (addr_type != IPV6_ADDR_ANY) {
 				int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL;
-				if (!inet_sk(sk)->transparent &&
+				if (!(inet_sk(sk)->freebind || inet_sk(sk)->transparent) &&
 				    !ipv6_chk_addr(net, &src_info->ipi6_addr,
 						   strict ? dev : NULL, 0))
 					err = -EINVAL;
 				else
-					ipv6_addr_copy(&fl6->saddr, &src_info->ipi6_addr);
+					fl6->saddr = src_info->ipi6_addr;
 			}
 
 			rcu_read_unlock();
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index bf22a22..3d641b6 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -243,9 +243,9 @@ static int ipv6_dest_hao(struct sk_buff *skb, int optoff)
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		skb->ip_summed = CHECKSUM_NONE;
 
-	ipv6_addr_copy(&tmp_addr, &ipv6h->saddr);
-	ipv6_addr_copy(&ipv6h->saddr, &hao->addr);
-	ipv6_addr_copy(&hao->addr, &tmp_addr);
+	tmp_addr = ipv6h->saddr;
+	ipv6h->saddr = hao->addr;
+	hao->addr = tmp_addr;
 
 	if (skb->tstamp.tv64 == 0)
 		__net_timestamp(skb);
@@ -461,9 +461,9 @@ looped_back:
 		return -1;
 	}
 
-	ipv6_addr_copy(&daddr, addr);
-	ipv6_addr_copy(addr, &ipv6_hdr(skb)->daddr);
-	ipv6_addr_copy(&ipv6_hdr(skb)->daddr, &daddr);
+	daddr = *addr;
+	*addr = ipv6_hdr(skb)->daddr;
+	ipv6_hdr(skb)->daddr = daddr;
 
 	skb_dst_drop(skb);
 	ip6_route_input(skb);
@@ -690,7 +690,7 @@ static void ipv6_push_rthdr(struct sk_buff *skb, u8 *proto,
 		memcpy(phdr->addr, ihdr->addr + 1,
 		       (hops - 1) * sizeof(struct in6_addr));
 
-	ipv6_addr_copy(phdr->addr + (hops - 1), *addr_p);
+	phdr->addr[hops - 1] = **addr_p;
 	*addr_p = ihdr->addr;
 
 	phdr->rt_hdr.nexthdr = *proto;
@@ -888,8 +888,8 @@ struct in6_addr *fl6_update_dst(struct flowi6 *fl6,
 	if (!opt || !opt->srcrt)
 		return NULL;
 
-	ipv6_addr_copy(orig, &fl6->daddr);
-	ipv6_addr_copy(&fl6->daddr, ((struct rt0_hdr *)opt->srcrt)->addr);
+	*orig = fl6->daddr;
+	fl6->daddr = *((struct rt0_hdr *)opt->srcrt)->addr;
 	return orig;
 }
 
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index 37f548b..72957f4 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -57,6 +57,9 @@ int ipv6_ext_hdr(u8 nexthdr)
  *	    it returns NULL.
  *	  - First fragment header is skipped, not-first ones
  *	    are considered as unparsable.
+ *	  - Reports the offset field of the final fragment header so it is
+ *	    possible to tell whether this is a first fragment, later fragment,
+ *	    or not fragmented.
  *	  - ESP is unparsable for now and considered like
  *	    normal payload protocol.
  *	  - Note also special handling of AUTH header. Thanks to IPsec wizards.
@@ -64,10 +67,13 @@ int ipv6_ext_hdr(u8 nexthdr)
  * --ANK (980726)
  */
 
-int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp)
+int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp,
+		     __be16 *frag_offp)
 {
 	u8 nexthdr = *nexthdrp;
 
+	*frag_offp = 0;
+
 	while (ipv6_ext_hdr(nexthdr)) {
 		struct ipv6_opt_hdr _hdr, *hp;
 		int hdrlen;
@@ -87,7 +93,8 @@ int ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp)
 			if (fp == NULL)
 				return -1;
 
-			if (ntohs(*fp) & ~0x7)
+			*frag_offp = *fp;
+			if (ntohs(*frag_offp) & ~0x7)
 				break;
 			hdrlen = 8;
 		} else if (nexthdr == NEXTHDR_AUTH)
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 2955715..b6c5731 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -96,7 +96,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 			if (!ipv6_prefix_equal(&saddr, &r->src.addr,
 					       r->src.plen))
 				goto again;
-			ipv6_addr_copy(&flp6->saddr, &saddr);
+			flp6->saddr = saddr;
 		}
 		goto out;
 	}
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 90868fb..01d46bf 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -135,11 +135,12 @@ static int is_ineligible(struct sk_buff *skb)
 	int ptr = (u8 *)(ipv6_hdr(skb) + 1) - skb->data;
 	int len = skb->len - ptr;
 	__u8 nexthdr = ipv6_hdr(skb)->nexthdr;
+	__be16 frag_off;
 
 	if (len < 0)
 		return 1;
 
-	ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr);
+	ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr, &frag_off);
 	if (ptr < 0)
 		return 0;
 	if (nexthdr == IPPROTO_ICMPV6) {
@@ -290,9 +291,9 @@ static void mip6_addr_swap(struct sk_buff *skb)
 		if (likely(off >= 0)) {
 			hao = (struct ipv6_destopt_hao *)
 					(skb_network_header(skb) + off);
-			ipv6_addr_copy(&tmp, &iph->saddr);
-			ipv6_addr_copy(&iph->saddr, &hao->addr);
-			ipv6_addr_copy(&hao->addr, &tmp);
+			tmp = iph->saddr;
+			iph->saddr = hao->addr;
+			hao->addr = tmp;
 		}
 	}
 }
@@ -444,9 +445,9 @@ void icmpv6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info)
 
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_proto = IPPROTO_ICMPV6;
-	ipv6_addr_copy(&fl6.daddr, &hdr->saddr);
+	fl6.daddr = hdr->saddr;
 	if (saddr)
-		ipv6_addr_copy(&fl6.saddr, saddr);
+		fl6.saddr = *saddr;
 	fl6.flowi6_oif = iif;
 	fl6.fl6_icmp_type = type;
 	fl6.fl6_icmp_code = code;
@@ -538,9 +539,9 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_proto = IPPROTO_ICMPV6;
-	ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->saddr);
+	fl6.daddr = ipv6_hdr(skb)->saddr;
 	if (saddr)
-		ipv6_addr_copy(&fl6.saddr, saddr);
+		fl6.saddr = *saddr;
 	fl6.flowi6_oif = skb->dev->ifindex;
 	fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
@@ -596,6 +597,7 @@ static void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info)
 	int inner_offset;
 	int hash;
 	u8 nexthdr;
+	__be16 frag_off;
 
 	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
 		return;
@@ -603,7 +605,8 @@ static void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info)
 	nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr;
 	if (ipv6_ext_hdr(nexthdr)) {
 		/* now skip over extension headers */
-		inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr);
+		inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
+						&nexthdr, &frag_off);
 		if (inner_offset<0)
 			return;
 	} else {
@@ -786,8 +789,8 @@ void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
 		      int oif)
 {
 	memset(fl6, 0, sizeof(*fl6));
-	ipv6_addr_copy(&fl6->saddr, saddr);
-	ipv6_addr_copy(&fl6->daddr, daddr);
+	fl6->saddr = *saddr;
+	fl6->daddr = *daddr;
 	fl6->flowi6_proto 	= IPPROTO_ICMPV6;
 	fl6->fl6_icmp_type	= type;
 	fl6->fl6_icmp_code	= 0;
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index fee46d5..02dd203 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -65,9 +65,9 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
 
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_proto = IPPROTO_TCP;
-	ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr);
+	fl6.daddr = treq->rmt_addr;
 	final_p = fl6_update_dst(&fl6, np->opt, &final);
-	ipv6_addr_copy(&fl6.saddr, &treq->loc_addr);
+	fl6.saddr = treq->loc_addr;
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_dport = inet_rsk(req)->rmt_port;
@@ -85,7 +85,7 @@ struct dst_entry *inet6_csk_route_req(struct sock *sk,
  * request_sock (formerly open request) hash tables.
  */
 static u32 inet6_synq_hash(const struct in6_addr *raddr, const __be16 rport,
-			   const u32 rnd, const u16 synq_hsize)
+			   const u32 rnd, const u32 synq_hsize)
 {
 	u32 c;
 
@@ -157,7 +157,7 @@ void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr)
 	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr;
 
 	sin6->sin6_family = AF_INET6;
-	ipv6_addr_copy(&sin6->sin6_addr, &np->daddr);
+	sin6->sin6_addr = np->daddr;
 	sin6->sin6_port	= inet_sk(sk)->inet_dport;
 	/* We do not store received flowlabel for TCP */
 	sin6->sin6_flowinfo = 0;
@@ -215,8 +215,8 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused)
 
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_proto = sk->sk_protocol;
-	ipv6_addr_copy(&fl6.daddr, &np->daddr);
-	ipv6_addr_copy(&fl6.saddr, &np->saddr);
+	fl6.daddr = np->daddr;
+	fl6.saddr = np->saddr;
 	fl6.flowlabel = np->flow_label;
 	IP6_ECN_flow_xmit(sk, fl6.flowlabel);
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
@@ -246,7 +246,7 @@ int inet6_csk_xmit(struct sk_buff *skb, struct flowi *fl_unused)
 	skb_dst_set_noref(skb, dst);
 
 	/* Restore final destination back after routing done */
-	ipv6_addr_copy(&fl6.daddr, &np->daddr);
+	fl6.daddr = np->daddr;
 
 	res = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass);
 	rcu_read_unlock();
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 93718f3..2783631 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -190,7 +190,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
 	struct fib6_table *table;
 
 	table = kzalloc(sizeof(*table), GFP_ATOMIC);
-	if (table != NULL) {
+	if (table) {
 		table->tb6_id = id;
 		table->tb6_root.leaf = net->ipv6.ip6_null_entry;
 		table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
@@ -210,7 +210,7 @@ struct fib6_table *fib6_new_table(struct net *net, u32 id)
 		return tb;
 
 	tb = fib6_alloc_table(net, id);
-	if (tb != NULL)
+	if (tb)
 		fib6_link_table(net, tb);
 
 	return tb;
@@ -367,7 +367,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	s_e = cb->args[1];
 
 	w = (void *)cb->args[2];
-	if (w == NULL) {
+	if (!w) {
 		/* New dump:
 		 *
 		 * 1. hook callback destructor.
@@ -379,7 +379,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 		 * 2. allocate and initialize walker.
 		 */
 		w = kzalloc(sizeof(*w), GFP_ATOMIC);
-		if (w == NULL)
+		if (!w)
 			return -ENOMEM;
 		w->func = fib6_dump_node;
 		cb->args[2] = (long)w;
@@ -425,7 +425,8 @@ out:
 
 static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr,
 				     int addrlen, int plen,
-				     int offset)
+				     int offset, int allow_create,
+				     int replace_required)
 {
 	struct fib6_node *fn, *in, *ln;
 	struct fib6_node *pn = NULL;
@@ -447,8 +448,18 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr,
 		 *	Prefix match
 		 */
 		if (plen < fn->fn_bit ||
-		    !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit))
+		    !ipv6_prefix_equal(&key->addr, addr, fn->fn_bit)) {
+			if (!allow_create) {
+				if (replace_required) {
+					pr_warn("IPv6: Can't replace route, "
+						"no match found\n");
+					return ERR_PTR(-ENOENT);
+				}
+				pr_warn("IPv6: NLM_F_CREATE should be set "
+					"when creating new route\n");
+			}
 			goto insert_above;
+		}
 
 		/*
 		 *	Exact match ?
@@ -456,7 +467,7 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr,
 
 		if (plen == fn->fn_bit) {
 			/* clean up an intermediate node */
-			if ((fn->fn_flags & RTN_RTINFO) == 0) {
+			if (!(fn->fn_flags & RTN_RTINFO)) {
 				rt6_release(fn->leaf);
 				fn->leaf = NULL;
 			}
@@ -477,6 +488,23 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr,
 		fn = dir ? fn->right: fn->left;
 	} while (fn);
 
+	if (!allow_create) {
+		/* We should not create new node because
+		 * NLM_F_REPLACE was specified without NLM_F_CREATE
+		 * I assume it is safe to require NLM_F_CREATE when
+		 * REPLACE flag is used! Later we may want to remove the
+		 * check for replace_required, because according
+		 * to netlink specification, NLM_F_CREATE
+		 * MUST be specified if new route is created.
+		 * That would keep IPv6 consistent with IPv4
+		 */
+		if (replace_required) {
+			pr_warn("IPv6: Can't replace route, no match found\n");
+			return ERR_PTR(-ENOENT);
+		}
+		pr_warn("IPv6: NLM_F_CREATE should be set "
+			"when creating new route\n");
+	}
 	/*
 	 *	We walked to the bottom of tree.
 	 *	Create new leaf node without children.
@@ -484,7 +512,7 @@ static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr,
 
 	ln = node_alloc();
 
-	if (ln == NULL)
+	if (!ln)
 		return NULL;
 	ln->fn_bit = plen;
 
@@ -527,7 +555,7 @@ insert_above:
 		in = node_alloc();
 		ln = node_alloc();
 
-		if (in == NULL || ln == NULL) {
+		if (!in || !ln) {
 			if (in)
 				node_free(in);
 			if (ln)
@@ -581,7 +609,7 @@ insert_above:
 
 		ln = node_alloc();
 
-		if (ln == NULL)
+		if (!ln)
 			return NULL;
 
 		ln->fn_bit = plen;
@@ -614,10 +642,15 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 {
 	struct rt6_info *iter = NULL;
 	struct rt6_info **ins;
+	int replace = (info->nlh &&
+		       (info->nlh->nlmsg_flags & NLM_F_REPLACE));
+	int add = (!info->nlh ||
+		   (info->nlh->nlmsg_flags & NLM_F_CREATE));
+	int found = 0;
 
 	ins = &fn->leaf;
 
-	for (iter = fn->leaf; iter; iter=iter->dst.rt6_next) {
+	for (iter = fn->leaf; iter; iter = iter->dst.rt6_next) {
 		/*
 		 *	Search for duplicates
 		 */
@@ -626,15 +659,22 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 			/*
 			 *	Same priority level
 			 */
+			if (info->nlh &&
+			    (info->nlh->nlmsg_flags & NLM_F_EXCL))
+				return -EEXIST;
+			if (replace) {
+				found++;
+				break;
+			}
 
 			if (iter->rt6i_dev == rt->rt6i_dev &&
 			    iter->rt6i_idev == rt->rt6i_idev &&
 			    ipv6_addr_equal(&iter->rt6i_gateway,
 					    &rt->rt6i_gateway)) {
-				if (!(iter->rt6i_flags&RTF_EXPIRES))
+				if (!(iter->rt6i_flags & RTF_EXPIRES))
 					return -EEXIST;
 				iter->rt6i_expires = rt->rt6i_expires;
-				if (!(rt->rt6i_flags&RTF_EXPIRES)) {
+				if (!(rt->rt6i_flags & RTF_EXPIRES)) {
 					iter->rt6i_flags &= ~RTF_EXPIRES;
 					iter->rt6i_expires = 0;
 				}
@@ -655,17 +695,40 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 	/*
 	 *	insert node
 	 */
+	if (!replace) {
+		if (!add)
+			pr_warn("IPv6: NLM_F_CREATE should be set when creating new route\n");
+
+add:
+		rt->dst.rt6_next = iter;
+		*ins = rt;
+		rt->rt6i_node = fn;
+		atomic_inc(&rt->rt6i_ref);
+		inet6_rt_notify(RTM_NEWROUTE, rt, info);
+		info->nl_net->ipv6.rt6_stats->fib_rt_entries++;
+
+		if (!(fn->fn_flags & RTN_RTINFO)) {
+			info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
+			fn->fn_flags |= RTN_RTINFO;
+		}
 
-	rt->dst.rt6_next = iter;
-	*ins = rt;
-	rt->rt6i_node = fn;
-	atomic_inc(&rt->rt6i_ref);
-	inet6_rt_notify(RTM_NEWROUTE, rt, info);
-	info->nl_net->ipv6.rt6_stats->fib_rt_entries++;
-
-	if ((fn->fn_flags & RTN_RTINFO) == 0) {
-		info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
-		fn->fn_flags |= RTN_RTINFO;
+	} else {
+		if (!found) {
+			if (add)
+				goto add;
+			pr_warn("IPv6: NLM_F_REPLACE set, but no existing node found!\n");
+			return -ENOENT;
+		}
+		*ins = rt;
+		rt->rt6i_node = fn;
+		rt->dst.rt6_next = iter->dst.rt6_next;
+		atomic_inc(&rt->rt6i_ref);
+		inet6_rt_notify(RTM_NEWROUTE, rt, info);
+		rt6_release(iter);
+		if (!(fn->fn_flags & RTN_RTINFO)) {
+			info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
+			fn->fn_flags |= RTN_RTINFO;
+		}
 	}
 
 	return 0;
@@ -674,7 +737,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
 static __inline__ void fib6_start_gc(struct net *net, struct rt6_info *rt)
 {
 	if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
-	    (rt->rt6i_flags & (RTF_EXPIRES|RTF_CACHE)))
+	    (rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE)))
 		mod_timer(&net->ipv6.ip6_fib_timer,
 			  jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
 }
@@ -696,11 +759,28 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info)
 {
 	struct fib6_node *fn, *pn = NULL;
 	int err = -ENOMEM;
+	int allow_create = 1;
+	int replace_required = 0;
+
+	if (info->nlh) {
+		if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
+			allow_create = 0;
+		if (info->nlh->nlmsg_flags & NLM_F_REPLACE)
+			replace_required = 1;
+	}
+	if (!allow_create && !replace_required)
+		pr_warn("IPv6: RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n");
 
 	fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr),
-			rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst));
+			rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst),
+			allow_create, replace_required);
+
+	if (IS_ERR(fn)) {
+		err = PTR_ERR(fn);
+		fn = NULL;
+	}
 
-	if (fn == NULL)
+	if (!fn)
 		goto out;
 
 	pn = fn;
@@ -709,7 +789,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info)
 	if (rt->rt6i_src.plen) {
 		struct fib6_node *sn;
 
-		if (fn->subtree == NULL) {
+		if (!fn->subtree) {
 			struct fib6_node *sfn;
 
 			/*
@@ -724,7 +804,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info)
 
 			/* Create subtree root node */
 			sfn = node_alloc();
-			if (sfn == NULL)
+			if (!sfn)
 				goto st_failure;
 
 			sfn->leaf = info->nl_net->ipv6.ip6_null_entry;
@@ -736,9 +816,10 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info)
 
 			sn = fib6_add_1(sfn, &rt->rt6i_src.addr,
 					sizeof(struct in6_addr), rt->rt6i_src.plen,
-					offsetof(struct rt6_info, rt6i_src));
+					offsetof(struct rt6_info, rt6i_src),
+					allow_create, replace_required);
 
-			if (sn == NULL) {
+			if (!sn) {
 				/* If it is failed, discard just allocated
 				   root, and then (in st_failure) stale node
 				   in main tree.
@@ -753,13 +834,18 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info)
 		} else {
 			sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr,
 					sizeof(struct in6_addr), rt->rt6i_src.plen,
-					offsetof(struct rt6_info, rt6i_src));
+					offsetof(struct rt6_info, rt6i_src),
+					allow_create, replace_required);
 
-			if (sn == NULL)
+			if (IS_ERR(sn)) {
+				err = PTR_ERR(sn);
+				sn = NULL;
+			}
+			if (!sn)
 				goto st_failure;
 		}
 
-		if (fn->leaf == NULL) {
+		if (!fn->leaf) {
 			fn->leaf = rt;
 			atomic_inc(&rt->rt6i_ref);
 		}
@@ -768,10 +854,9 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info)
 #endif
 
 	err = fib6_add_rt2node(fn, rt, info);
-
-	if (err == 0) {
+	if (!err) {
 		fib6_start_gc(info->nl_net, rt);
-		if (!(rt->rt6i_flags&RTF_CACHE))
+		if (!(rt->rt6i_flags & RTF_CACHE))
 			fib6_prune_clones(info->nl_net, pn, rt);
 	}
 
@@ -819,7 +904,7 @@ st_failure:
  */
 
 struct lookup_args {
-	int		offset;		/* key offset on rt6_info	*/
+	int			offset;		/* key offset on rt6_info	*/
 	const struct in6_addr	*addr;		/* search key			*/
 };
 
@@ -849,11 +934,10 @@ static struct fib6_node * fib6_lookup_1(struct fib6_node *root,
 			fn = next;
 			continue;
 		}
-
 		break;
 	}
 
-	while(fn) {
+	while (fn) {
 		if (FIB6_SUBTREE(fn) || fn->fn_flags & RTN_RTINFO) {
 			struct rt6key *key;
 
@@ -900,8 +984,7 @@ struct fib6_node * fib6_lookup(struct fib6_node *root, const struct in6_addr *da
 	};
 
 	fn = fib6_lookup_1(root, daddr ? args : args + 1);
-
-	if (fn == NULL || fn->fn_flags & RTN_TL_ROOT)
+	if (!fn || fn->fn_flags & RTN_TL_ROOT)
 		fn = root;
 
 	return fn;
@@ -961,7 +1044,7 @@ struct fib6_node * fib6_locate(struct fib6_node *root,
 	}
 #endif
 
-	if (fn && fn->fn_flags&RTN_RTINFO)
+	if (fn && fn->fn_flags & RTN_RTINFO)
 		return fn;
 
 	return NULL;
@@ -975,14 +1058,13 @@ struct fib6_node * fib6_locate(struct fib6_node *root,
 
 static struct rt6_info *fib6_find_prefix(struct net *net, struct fib6_node *fn)
 {
-	if (fn->fn_flags&RTN_ROOT)
+	if (fn->fn_flags & RTN_ROOT)
 		return net->ipv6.ip6_null_entry;
 
-	while(fn) {
-		if(fn->left)
+	while (fn) {
+		if (fn->left)
 			return fn->left->leaf;
-
-		if(fn->right)
+		if (fn->right)
 			return fn->right->leaf;
 
 		fn = FIB6_SUBTREE(fn);
@@ -1020,12 +1102,12 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 		if (children == 3 || FIB6_SUBTREE(fn)
 #ifdef CONFIG_IPV6_SUBTREES
 		    /* Subtree root (i.e. fn) may have one child */
-		    || (children && fn->fn_flags&RTN_ROOT)
+		    || (children && fn->fn_flags & RTN_ROOT)
 #endif
 		    ) {
 			fn->leaf = fib6_find_prefix(net, fn);
 #if RT6_DEBUG >= 2
-			if (fn->leaf==NULL) {
+			if (!fn->leaf) {
 				WARN_ON(!fn->leaf);
 				fn->leaf = net->ipv6.ip6_null_entry;
 			}
@@ -1058,7 +1140,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 
 		read_lock(&fib6_walker_lock);
 		FOR_WALKERS(w) {
-			if (child == NULL) {
+			if (!child) {
 				if (w->root == fn) {
 					w->root = w->node = NULL;
 					RT6_TRACE("W %p adjusted by delroot 1\n", w);
@@ -1087,7 +1169,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 		read_unlock(&fib6_walker_lock);
 
 		node_free(fn);
-		if (pn->fn_flags&RTN_RTINFO || FIB6_SUBTREE(pn))
+		if (pn->fn_flags & RTN_RTINFO || FIB6_SUBTREE(pn))
 			return pn;
 
 		rt6_release(pn->leaf);
@@ -1121,7 +1203,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 		if (w->state == FWS_C && w->leaf == rt) {
 			RT6_TRACE("walker %p adjusted by delroute\n", w);
 			w->leaf = rt->dst.rt6_next;
-			if (w->leaf == NULL)
+			if (!w->leaf)
 				w->state = FWS_U;
 		}
 	}
@@ -1130,7 +1212,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 	rt->dst.rt6_next = NULL;
 
 	/* If it was last route, expunge its radix tree node */
-	if (fn->leaf == NULL) {
+	if (!fn->leaf) {
 		fn->fn_flags &= ~RTN_RTINFO;
 		net->ipv6.rt6_stats->fib_route_nodes--;
 		fn = fib6_repair_tree(net, fn);
@@ -1144,7 +1226,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
 		 * to still alive ones.
 		 */
 		while (fn) {
-			if (!(fn->fn_flags&RTN_RTINFO) && fn->leaf == rt) {
+			if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
 				fn->leaf = fib6_find_prefix(net, fn);
 				atomic_inc(&fn->leaf->rt6i_ref);
 				rt6_release(rt);
@@ -1171,17 +1253,17 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
 		return -ENOENT;
 	}
 #endif
-	if (fn == NULL || rt == net->ipv6.ip6_null_entry)
+	if (!fn || rt == net->ipv6.ip6_null_entry)
 		return -ENOENT;
 
 	WARN_ON(!(fn->fn_flags & RTN_RTINFO));
 
-	if (!(rt->rt6i_flags&RTF_CACHE)) {
+	if (!(rt->rt6i_flags & RTF_CACHE)) {
 		struct fib6_node *pn = fn;
 #ifdef CONFIG_IPV6_SUBTREES
 		/* clones of this route might be in another subtree */
 		if (rt->rt6i_src.plen) {
-			while (!(pn->fn_flags&RTN_ROOT))
+			while (!(pn->fn_flags & RTN_ROOT))
 				pn = pn->parent;
 			pn = pn->parent;
 		}
@@ -1232,11 +1314,11 @@ static int fib6_walk_continue(struct fib6_walker_t *w)
 
 	for (;;) {
 		fn = w->node;
-		if (fn == NULL)
+		if (!fn)
 			return 0;
 
 		if (w->prune && fn != w->root &&
-		    fn->fn_flags&RTN_RTINFO && w->state < FWS_C) {
+		    fn->fn_flags & RTN_RTINFO && w->state < FWS_C) {
 			w->state = FWS_C;
 			w->leaf = fn->leaf;
 		}
@@ -1265,7 +1347,7 @@ static int fib6_walk_continue(struct fib6_walker_t *w)
 			w->state = FWS_C;
 			w->leaf = fn->leaf;
 		case FWS_C:
-			if (w->leaf && fn->fn_flags&RTN_RTINFO) {
+			if (w->leaf && fn->fn_flags & RTN_RTINFO) {
 				int err;
 
 				if (w->count < w->skip) {
@@ -1439,7 +1521,7 @@ static int fib6_age(struct rt6_info *rt, void *arg)
 	 *	only if they are not in use now.
 	 */
 
-	if (rt->rt6i_flags&RTF_EXPIRES && rt->rt6i_expires) {
+	if (rt->rt6i_flags & RTF_EXPIRES && rt->rt6i_expires) {
 		if (time_after(now, rt->rt6i_expires)) {
 			RT6_TRACE("expiring %p\n", rt);
 			return -1;
@@ -1451,7 +1533,7 @@ static int fib6_age(struct rt6_info *rt, void *arg)
 			RT6_TRACE("aging clone %p\n", rt);
 			return -1;
 		} else if ((rt->rt6i_flags & RTF_GATEWAY) &&
-			   (!(dst_get_neighbour_raw(&rt->dst)->flags & NTF_ROUTER))) {
+			   (!(dst_get_neighbour_noref_raw(&rt->dst)->flags & NTF_ROUTER))) {
 			RT6_TRACE("purging route %p via non-router but gateway\n",
 				  rt);
 			return -1;
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 4566dbd..b7867a1 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -386,7 +386,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 		err = -EINVAL;
 		goto done;
 	}
-	ipv6_addr_copy(&fl->dst, &freq->flr_dst);
+	fl->dst = freq->flr_dst;
 	atomic_set(&fl->users, 1);
 	switch (fl->share) {
 	case IPV6_FL_S_EXCL:
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index 027c7ff..1ca5d45 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -111,6 +111,14 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 	    ipv6_addr_loopback(&hdr->daddr))
 		goto err;
 
+	/*
+	 * RFC4291 2.7
+	 * Multicast addresses must not be used as source addresses in IPv6
+	 * packets or appear in any Routing header.
+	 */
+	if (ipv6_addr_is_multicast(&hdr->saddr))
+		goto err;
+
 	skb->transport_header = skb->network_header + sizeof(*hdr);
 	IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr);
 
@@ -272,6 +280,7 @@ int ip6_mc_input(struct sk_buff *skb)
 			u8 *ptr = skb_network_header(skb) + opt->ra;
 			struct icmp6hdr *icmp6;
 			u8 nexthdr = hdr->nexthdr;
+			__be16 frag_off;
 			int offset;
 
 			/* Check if the value of Router Alert
@@ -285,7 +294,7 @@ int ip6_mc_input(struct sk_buff *skb)
 					goto out;
 				}
 				offset = ipv6_skip_exthdr(skb, sizeof(*hdr),
-							  &nexthdr);
+							  &nexthdr, &frag_off);
 				if (offset < 0)
 					goto out;
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 84d0bd5..71d2699 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -136,7 +136,7 @@ static int ip6_finish_output2(struct sk_buff *skb)
 	}
 
 	rcu_read_lock();
-	neigh = dst_get_neighbour(dst);
+	neigh = dst_get_neighbour_noref(dst);
 	if (neigh) {
 		int res = neigh_output(neigh, skb);
 
@@ -238,8 +238,8 @@ int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 	hdr->nexthdr = proto;
 	hdr->hop_limit = hlimit;
 
-	ipv6_addr_copy(&hdr->saddr, &fl6->saddr);
-	ipv6_addr_copy(&hdr->daddr, first_hop);
+	hdr->saddr = fl6->saddr;
+	hdr->daddr = *first_hop;
 
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
@@ -290,8 +290,8 @@ int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, struct net_device *dev,
 	hdr->nexthdr = proto;
 	hdr->hop_limit = np->hop_limit;
 
-	ipv6_addr_copy(&hdr->saddr, saddr);
-	ipv6_addr_copy(&hdr->daddr, daddr);
+	hdr->saddr = *saddr;
+	hdr->daddr = *daddr;
 
 	return 0;
 }
@@ -329,10 +329,11 @@ static int ip6_forward_proxy_check(struct sk_buff *skb)
 {
 	struct ipv6hdr *hdr = ipv6_hdr(skb);
 	u8 nexthdr = hdr->nexthdr;
+	__be16 frag_off;
 	int offset;
 
 	if (ipv6_ext_hdr(nexthdr)) {
-		offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr);
+		offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr, &frag_off);
 		if (offset < 0)
 			return 0;
 	} else
@@ -462,7 +463,7 @@ int ip6_forward(struct sk_buff *skb)
 	   send redirects to source routed frames.
 	   We don't send redirects to frames decapsulated from IPsec.
 	 */
-	n = dst_get_neighbour(dst);
+	n = dst_get_neighbour_noref(dst);
 	if (skb->dev == dst->dev && n && opt->srcrt == 0 && !skb_sec_path(skb)) {
 		struct in6_addr *target = NULL;
 		struct rt6_info *rt;
@@ -631,6 +632,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 	struct ipv6hdr *tmp_hdr;
 	struct frag_hdr *fh;
 	unsigned int mtu, hlen, left, len;
+	int hroom, troom;
 	__be32 frag_id = 0;
 	int ptr, offset = 0, err=0;
 	u8 *prevhdr, nexthdr = 0;
@@ -797,6 +799,8 @@ slow_path:
 	 */
 
 	*prevhdr = NEXTHDR_FRAGMENT;
+	hroom = LL_RESERVED_SPACE(rt->dst.dev);
+	troom = rt->dst.dev->needed_tailroom;
 
 	/*
 	 *	Keep copying data until we run out.
@@ -815,7 +819,8 @@ slow_path:
 		 *	Allocate buffer.
 		 */
 
-		if ((frag = alloc_skb(len+hlen+sizeof(struct frag_hdr)+LL_ALLOCATED_SPACE(rt->dst.dev), GFP_ATOMIC)) == NULL) {
+		if ((frag = alloc_skb(len + hlen + sizeof(struct frag_hdr) +
+				      hroom + troom, GFP_ATOMIC)) == NULL) {
 			NETDEBUG(KERN_INFO "IPv6: frag: no memory for new fragment!\n");
 			IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 				      IPSTATS_MIB_FRAGFAILS);
@@ -828,7 +833,7 @@ slow_path:
 		 */
 
 		ip6_copy_metadata(frag, skb);
-		skb_reserve(frag, LL_RESERVED_SPACE(rt->dst.dev));
+		skb_reserve(frag, hroom);
 		skb_put(frag, len + hlen + sizeof(struct frag_hdr));
 		skb_reset_network_header(frag);
 		fh = (struct frag_hdr *)(skb_network_header(frag) + hlen);
@@ -978,7 +983,7 @@ static int ip6_dst_lookup_tail(struct sock *sk,
 	 * dst entry of the nexthop router
 	 */
 	rcu_read_lock();
-	n = dst_get_neighbour(*dst);
+	n = dst_get_neighbour_noref(*dst);
 	if (n && !(n->nud_state & NUD_VALID)) {
 		struct inet6_ifaddr *ifp;
 		struct flowi6 fl_gw6;
@@ -1059,7 +1064,7 @@ struct dst_entry *ip6_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 	if (err)
 		return ERR_PTR(err);
 	if (final_dst)
-		ipv6_addr_copy(&fl6->daddr, final_dst);
+		fl6->daddr = *final_dst;
 	if (can_sleep)
 		fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP;
 
@@ -1095,7 +1100,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6,
 	if (err)
 		return ERR_PTR(err);
 	if (final_dst)
-		ipv6_addr_copy(&fl6->daddr, final_dst);
+		fl6->daddr = *final_dst;
 	if (can_sleep)
 		fl6->flowi6_flags |= FLOWI_FLAG_CAN_SLEEP;
 
@@ -1588,7 +1593,7 @@ int ip6_push_pending_frames(struct sock *sk)
 	if (np->pmtudisc < IPV6_PMTUDISC_DO)
 		skb->local_df = 1;
 
-	ipv6_addr_copy(final_dst, &fl6->daddr);
+	*final_dst = fl6->daddr;
 	__skb_pull(skb, skb_network_header_len(skb));
 	if (opt && opt->opt_flen)
 		ipv6_push_frag_opts(skb, opt, &proto);
@@ -1604,8 +1609,8 @@ int ip6_push_pending_frames(struct sock *sk)
 
 	hdr->hop_limit = np->cork.hop_limit;
 	hdr->nexthdr = proto;
-	ipv6_addr_copy(&hdr->saddr, &fl6->saddr);
-	ipv6_addr_copy(&hdr->daddr, final_dst);
+	hdr->saddr = fl6->saddr;
+	hdr->daddr = *final_dst;
 
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index bdc15c9..f5f98f5 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -93,7 +93,7 @@ struct pcpu_tstats {
 	unsigned long	rx_bytes;
 	unsigned long	tx_packets;
 	unsigned long	tx_bytes;
-};
+} __attribute__((aligned(4*sizeof(unsigned long))));
 
 static struct net_device_stats *ip6_get_stats(struct net_device *dev)
 {
@@ -289,6 +289,8 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p)
 	if ((err = register_netdevice(dev)) < 0)
 		goto failed_free;
 
+	strcpy(t->parms.name, dev->name);
+
 	dev_hold(dev);
 	ip6_tnl_link(ip6n, t);
 	return t;
@@ -977,8 +979,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
 	ipv6_change_dsfield(ipv6h, ~INET_ECN_MASK, dsfield);
 	ipv6h->hop_limit = t->parms.hop_limit;
 	ipv6h->nexthdr = proto;
-	ipv6_addr_copy(&ipv6h->saddr, &fl6->saddr);
-	ipv6_addr_copy(&ipv6h->daddr, &fl6->daddr);
+	ipv6h->saddr = fl6->saddr;
+	ipv6h->daddr = fl6->daddr;
 	nf_reset(skb);
 	pkt_len = skb->len;
 	err = ip6_local_out(skb);
@@ -1153,8 +1155,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 	memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
 
 	/* Set up flowi template */
-	ipv6_addr_copy(&fl6->saddr, &p->laddr);
-	ipv6_addr_copy(&fl6->daddr, &p->raddr);
+	fl6->saddr = p->laddr;
+	fl6->daddr = p->raddr;
 	fl6->flowi6_oif = p->link;
 	fl6->flowlabel = 0;
 
@@ -1210,8 +1212,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 static int
 ip6_tnl_change(struct ip6_tnl *t, struct ip6_tnl_parm *p)
 {
-	ipv6_addr_copy(&t->parms.laddr, &p->laddr);
-	ipv6_addr_copy(&t->parms.raddr, &p->raddr);
+	t->parms.laddr = p->laddr;
+	t->parms.raddr = p->raddr;
 	t->parms.flags = p->flags;
 	t->parms.hop_limit = p->hop_limit;
 	t->parms.encap_limit = p->encap_limit;
@@ -1407,7 +1409,6 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
 	struct ip6_tnl *t = netdev_priv(dev);
 
 	t->dev = dev;
-	strcpy(t->parms.name, dev->name);
 	dev->tstats = alloc_percpu(struct pcpu_tstats);
 	if (!dev->tstats)
 		return -ENOMEM;
@@ -1487,6 +1488,7 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
 static int __net_init ip6_tnl_init_net(struct net *net)
 {
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+	struct ip6_tnl *t = NULL;
 	int err;
 
 	ip6n->tnls[0] = ip6n->tnls_wc;
@@ -1507,6 +1509,10 @@ static int __net_init ip6_tnl_init_net(struct net *net)
 	err = register_netdev(ip6n->fb_tnl_dev);
 	if (err < 0)
 		goto err_register;
+
+	t = netdev_priv(ip6n->fb_tnl_dev);
+
+	strcpy(t->parms.name, ip6n->fb_tnl_dev->name);
 	return 0;
 
 err_register:
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 449a918..c7e95c8 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1105,8 +1105,8 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
 		msg->im6_msgtype = MRT6MSG_WHOLEPKT;
 		msg->im6_mif = mrt->mroute_reg_vif_num;
 		msg->im6_pad = 0;
-		ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr);
-		ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr);
+		msg->im6_src = ipv6_hdr(pkt)->saddr;
+		msg->im6_dst = ipv6_hdr(pkt)->daddr;
 
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 	} else
@@ -1131,8 +1131,8 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
 	msg->im6_msgtype = assert;
 	msg->im6_mif = mifi;
 	msg->im6_pad = 0;
-	ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr);
-	ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr);
+	msg->im6_src = ipv6_hdr(pkt)->saddr;
+	msg->im6_dst = ipv6_hdr(pkt)->daddr;
 
 	skb_dst_set(skb, dst_clone(skb_dst(pkt)));
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -2181,8 +2181,8 @@ int ip6mr_get_route(struct net *net,
 		iph->payload_len = 0;
 		iph->nexthdr = IPPROTO_NONE;
 		iph->hop_limit = 0;
-		ipv6_addr_copy(&iph->saddr, &rt->rt6i_src.addr);
-		ipv6_addr_copy(&iph->daddr, &rt->rt6i_dst.addr);
+		iph->saddr = rt->rt6i_src.addr;
+		iph->daddr = rt->rt6i_dst.addr;
 
 		err = ip6mr_cache_unresolved(mrt, vif, skb2);
 		read_unlock(&mrt_lock);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index c99e3ee..18a2719 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -435,7 +435,7 @@ sticky_done:
 			goto e_inval;
 
 		np->sticky_pktinfo.ipi6_ifindex = pkt.ipi6_ifindex;
-		ipv6_addr_copy(&np->sticky_pktinfo.ipi6_addr, &pkt.ipi6_addr);
+		np->sticky_pktinfo.ipi6_addr = pkt.ipi6_addr;
 		retv = 0;
 		break;
 	}
@@ -503,7 +503,7 @@ done:
 			goto e_inval;
 		if (val > 255 || val < -1)
 			goto e_inval;
-		np->mcast_hops = val;
+		np->mcast_hops = (val == -1 ? IPV6_DEFAULT_MCASTHOPS : val);
 		retv = 0;
 		break;
 
@@ -980,8 +980,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 				struct in6_pktinfo src_info;
 				src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
 					np->sticky_pktinfo.ipi6_ifindex;
-				np->mcast_oif? ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr) :
-					ipv6_addr_copy(&src_info.ipi6_addr, &(np->sticky_pktinfo.ipi6_addr));
+				src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr;
 				put_cmsg(&msg, SOL_IPV6, IPV6_PKTINFO, sizeof(src_info), &src_info);
 			}
 			if (np->rxopt.bits.rxhlim) {
@@ -992,8 +991,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 				struct in6_pktinfo src_info;
 				src_info.ipi6_ifindex = np->mcast_oif ? np->mcast_oif :
 					np->sticky_pktinfo.ipi6_ifindex;
-				np->mcast_oif? ipv6_addr_copy(&src_info.ipi6_addr, &np->daddr) :
-					ipv6_addr_copy(&src_info.ipi6_addr, &(np->sticky_pktinfo.ipi6_addr));
+				src_info.ipi6_addr = np->mcast_oif ? np->daddr : np->sticky_pktinfo.ipi6_addr;
 				put_cmsg(&msg, SOL_IPV6, IPV6_2292PKTINFO, sizeof(src_info), &src_info);
 			}
 			if (np->rxopt.bits.rxohlim) {
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index ee7839f..ea34d58 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -155,7 +155,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 		return -ENOMEM;
 
 	mc_lst->next = NULL;
-	ipv6_addr_copy(&mc_lst->addr, addr);
+	mc_lst->addr = *addr;
 
 	rcu_read_lock();
 	if (ifindex == 0) {
@@ -858,7 +858,7 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr)
 
 	setup_timer(&mc->mca_timer, igmp6_timer_handler, (unsigned long)mc);
 
-	ipv6_addr_copy(&mc->mca_addr, addr);
+	mc->mca_addr = *addr;
 	mc->idev = idev; /* (reference taken) */
 	mc->mca_users = 1;
 	/* mca_stamp should be updated upon changes */
@@ -1343,13 +1343,15 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size)
 	struct mld2_report *pmr;
 	struct in6_addr addr_buf;
 	const struct in6_addr *saddr;
+	int hlen = LL_RESERVED_SPACE(dev);
+	int tlen = dev->needed_tailroom;
 	int err;
 	u8 ra[8] = { IPPROTO_ICMPV6, 0,
 		     IPV6_TLV_ROUTERALERT, 2, 0, 0,
 		     IPV6_TLV_PADN, 0 };
 
 	/* we assume size > sizeof(ra) here */
-	size += LL_ALLOCATED_SPACE(dev);
+	size += hlen + tlen;
 	/* limit our allocations to order-0 page */
 	size = min_t(int, size, SKB_MAX_ORDER(0, 0));
 	skb = sock_alloc_send_skb(sk, size, 1, &err);
@@ -1357,7 +1359,7 @@ static struct sk_buff *mld_newpack(struct net_device *dev, int size)
 	if (!skb)
 		return NULL;
 
-	skb_reserve(skb, LL_RESERVED_SPACE(dev));
+	skb_reserve(skb, hlen);
 
 	if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) {
 		/* <draft-ietf-magma-mld-source-05.txt>:
@@ -1408,18 +1410,11 @@ static void mld_sendpack(struct sk_buff *skb)
 					   csum_partial(skb_transport_header(skb),
 							mldlen, 0));
 
-	dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr);
-
-	if (!dst) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-
 	icmpv6_flow_init(net->ipv6.igmp_sk, &fl6, ICMPV6_MLD2_REPORT,
 			 &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
 			 skb->dev->ifindex);
+	dst = icmp6_dst_alloc(skb->dev, NULL, &fl6);
 
-	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
 	err = 0;
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
@@ -1723,6 +1718,8 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
 	struct mld_msg *hdr;
 	const struct in6_addr *snd_addr, *saddr;
 	struct in6_addr addr_buf;
+	int hlen = LL_RESERVED_SPACE(dev);
+	int tlen = dev->needed_tailroom;
 	int err, len, payload_len, full_len;
 	u8 ra[8] = { IPPROTO_ICMPV6, 0,
 		     IPV6_TLV_ROUTERALERT, 2, 0, 0,
@@ -1744,7 +1741,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
 		      IPSTATS_MIB_OUT, full_len);
 	rcu_read_unlock();
 
-	skb = sock_alloc_send_skb(sk, LL_ALLOCATED_SPACE(dev) + full_len, 1, &err);
+	skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err);
 
 	if (skb == NULL) {
 		rcu_read_lock();
@@ -1754,7 +1751,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
 		return;
 	}
 
-	skb_reserve(skb, LL_RESERVED_SPACE(dev));
+	skb_reserve(skb, hlen);
 
 	if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) {
 		/* <draft-ietf-magma-mld-source-05.txt>:
@@ -1772,7 +1769,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
 	hdr = (struct mld_msg *) skb_put(skb, sizeof(struct mld_msg));
 	memset(hdr, 0, sizeof(struct mld_msg));
 	hdr->mld_type = type;
-	ipv6_addr_copy(&hdr->mld_mca, addr);
+	hdr->mld_mca = *addr;
 
 	hdr->mld_cksum = csum_ipv6_magic(saddr, snd_addr, len,
 					 IPPROTO_ICMPV6,
@@ -1781,17 +1778,10 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type)
 	rcu_read_lock();
 	idev = __in6_dev_get(skb->dev);
 
-	dst = icmp6_dst_alloc(skb->dev, NULL, &ipv6_hdr(skb)->daddr);
-	if (!dst) {
-		err = -ENOMEM;
-		goto err_out;
-	}
-
 	icmpv6_flow_init(sk, &fl6, type,
 			 &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
 			 skb->dev->ifindex);
-
-	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
+	dst = icmp6_dst_alloc(skb->dev, NULL, &fl6);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		goto err_out;
@@ -1914,7 +1904,7 @@ static int ip6_mc_del_src(struct inet6_dev *idev, const struct in6_addr *pmca,
  * Add multicast single-source filter to the interface list
  */
 static int ip6_mc_add1_src(struct ifmcaddr6 *pmc, int sfmode,
-	const struct in6_addr *psfsrc, int delta)
+	const struct in6_addr *psfsrc)
 {
 	struct ip6_sf_list *psf, *psf_prev;
 
@@ -2045,7 +2035,7 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca,
 		pmc->mca_sfcount[sfmode]++;
 	err = 0;
 	for (i=0; i<sfcount; i++) {
-		err = ip6_mc_add1_src(pmc, sfmode, &psfsrc[i], delta);
+		err = ip6_mc_add1_src(pmc, sfmode, &psfsrc[i]);
 		if (err)
 			break;
 	}
diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c
index 43242e6..7e1e0fb 100644
--- a/net/ipv6/mip6.c
+++ b/net/ipv6/mip6.c
@@ -195,8 +195,8 @@ static inline int mip6_report_rl_allow(struct timeval *stamp,
 		mip6_report_rl.stamp.tv_sec = stamp->tv_sec;
 		mip6_report_rl.stamp.tv_usec = stamp->tv_usec;
 		mip6_report_rl.iif = iif;
-		ipv6_addr_copy(&mip6_report_rl.src, src);
-		ipv6_addr_copy(&mip6_report_rl.dst, dst);
+		mip6_report_rl.src = *src;
+		mip6_report_rl.dst = *dst;
 		allow = 1;
 	}
 	spin_unlock_bh(&mip6_report_rl.lock);
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 44e5b7f..f3e50c2 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -126,7 +126,6 @@ static const struct neigh_ops ndisc_direct_ops = {
 
 struct neigh_table nd_tbl = {
 	.family =	AF_INET6,
-	.entry_size =	sizeof(struct neighbour) + sizeof(struct in6_addr),
 	.key_len =	sizeof(struct in6_addr),
 	.hash =		ndisc_hash,
 	.constructor =	ndisc_constructor,
@@ -141,7 +140,7 @@ struct neigh_table nd_tbl = {
 		.gc_staletime		= 60 * HZ,
 		.reachable_time		= ND_REACHABLE_TIME,
 		.delay_probe_time	= 5 * HZ,
-		.queue_len		= 3,
+		.queue_len_bytes	= 64*1024,
 		.ucast_probes		= 3,
 		.mcast_probes		= 3,
 		.anycast_delay		= 1 * HZ,
@@ -446,6 +445,8 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev,
 	struct sock *sk = net->ipv6.ndisc_sk;
 	struct sk_buff *skb;
 	struct icmp6hdr *hdr;
+	int hlen = LL_RESERVED_SPACE(dev);
+	int tlen = dev->needed_tailroom;
 	int len;
 	int err;
 	u8 *opt;
@@ -459,7 +460,7 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev,
 
 	skb = sock_alloc_send_skb(sk,
 				  (MAX_HEADER + sizeof(struct ipv6hdr) +
-				   len + LL_ALLOCATED_SPACE(dev)),
+				   len + hlen + tlen),
 				  1, &err);
 	if (!skb) {
 		ND_PRINTK0(KERN_ERR
@@ -468,7 +469,7 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev,
 		return NULL;
 	}
 
-	skb_reserve(skb, LL_RESERVED_SPACE(dev));
+	skb_reserve(skb, hlen);
 	ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len);
 
 	skb->transport_header = skb->tail;
@@ -479,7 +480,7 @@ struct sk_buff *ndisc_build_skb(struct net_device *dev,
 
 	opt = skb_transport_header(skb) + sizeof(struct icmp6hdr);
 	if (target) {
-		ipv6_addr_copy((struct in6_addr *)opt, target);
+		*(struct in6_addr *)opt = *target;
 		opt += sizeof(*target);
 	}
 
@@ -515,14 +516,7 @@ void ndisc_send_skb(struct sk_buff *skb,
 	type = icmp6h->icmp6_type;
 
 	icmpv6_flow_init(sk, &fl6, type, saddr, daddr, dev->ifindex);
-
-	dst = icmp6_dst_alloc(dev, neigh, daddr);
-	if (!dst) {
-		kfree_skb(skb);
-		return;
-	}
-
-	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
+	dst = icmp6_dst_alloc(dev, neigh, &fl6);
 	if (IS_ERR(dst)) {
 		kfree_skb(skb);
 		return;
@@ -1237,7 +1231,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 	rt = rt6_get_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev);
 
 	if (rt)
-		neigh = dst_get_neighbour(&rt->dst);
+		neigh = dst_get_neighbour_noref(&rt->dst);
 
 	if (rt && lifetime == 0) {
 		neigh_clone(neigh);
@@ -1257,7 +1251,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
 			return;
 		}
 
-		neigh = dst_get_neighbour(&rt->dst);
+		neigh = dst_get_neighbour_noref(&rt->dst);
 		if (neigh == NULL) {
 			ND_PRINTK0(KERN_ERR
 				   "ICMPv6 RA: %s() got default router without neighbour.\n",
@@ -1533,6 +1527,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
 	struct inet6_dev *idev;
 	struct flowi6 fl6;
 	u8 *opt;
+	int hlen, tlen;
 	int rd_len;
 	int err;
 	u8 ha_buf[MAX_ADDR_LEN], *ha = NULL;
@@ -1571,7 +1566,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
 	}
 	if (!rt->rt6i_peer)
 		rt6_bind_peer(rt, 1);
-	if (inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ))
+	if (!inet_peer_xrlim_allow(rt->rt6i_peer, 1*HZ))
 		goto release;
 
 	if (dev->addr_len) {
@@ -1590,9 +1585,11 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
 	rd_len &= ~0x7;
 	len += rd_len;
 
+	hlen = LL_RESERVED_SPACE(dev);
+	tlen = dev->needed_tailroom;
 	buff = sock_alloc_send_skb(sk,
 				   (MAX_HEADER + sizeof(struct ipv6hdr) +
-				    len + LL_ALLOCATED_SPACE(dev)),
+				    len + hlen + tlen),
 				   1, &err);
 	if (buff == NULL) {
 		ND_PRINTK0(KERN_ERR
@@ -1601,7 +1598,7 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
 		goto release;
 	}
 
-	skb_reserve(buff, LL_RESERVED_SPACE(dev));
+	skb_reserve(buff, hlen);
 	ip6_nd_hdr(sk, buff, dev, &saddr_buf, &ipv6_hdr(skb)->saddr,
 		   IPPROTO_ICMPV6, len);
 
@@ -1617,9 +1614,9 @@ void ndisc_send_redirect(struct sk_buff *skb, struct neighbour *neigh,
 	 */
 
 	addrp = (struct in6_addr *)(icmph + 1);
-	ipv6_addr_copy(addrp, target);
+	*addrp = *target;
 	addrp++;
-	ipv6_addr_copy(addrp, &ipv6_hdr(skb)->daddr);
+	*addrp = ipv6_hdr(skb)->daddr;
 
 	opt = (u8*) (addrp + 1);
 
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 4484648..f792b34 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -186,7 +186,6 @@ config IP6_NF_MANGLE
 
 config IP6_NF_RAW
 	tristate  'raw table support (required for TRACE)'
-	depends on NETFILTER_ADVANCED
 	help
 	  This option adds a `raw' table to ip6tables. This table is the very
 	  first in the netfilter framework and hooks in at the PREROUTING
diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c
index e63c397..fb80a23 100644
--- a/net/ipv6/netfilter/ip6_queue.c
+++ b/net/ipv6/netfilter/ip6_queue.c
@@ -405,6 +405,7 @@ __ipq_rcv_skb(struct sk_buff *skb)
 	int status, type, pid, flags;
 	unsigned int nlmsglen, skblen;
 	struct nlmsghdr *nlh;
+	bool enable_timestamp = false;
 
 	skblen = skb->len;
 	if (skblen < sizeof(*nlh))
@@ -442,11 +443,13 @@ __ipq_rcv_skb(struct sk_buff *skb)
 			RCV_SKB_FAIL(-EBUSY);
 		}
 	} else {
-		net_enable_timestamp();
+		enable_timestamp = true;
 		peer_pid = pid;
 	}
 
 	spin_unlock_bh(&queue_lock);
+	if (enable_timestamp)
+		net_enable_timestamp();
 
 	status = ipq_receive_peer(NLMSG_DATA(nlh), type,
 				  nlmsglen - NLMSG_LENGTH(0));
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index a5a4c5d..aad2fa4 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -49,6 +49,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
 	const __u8 tclass = DEFAULT_TOS_VALUE;
 	struct dst_entry *dst = NULL;
 	u8 proto;
+	__be16 frag_off;
 	struct flowi6 fl6;
 
 	if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
@@ -58,7 +59,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
 	}
 
 	proto = oip6h->nexthdr;
-	tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto);
+	tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto, &frag_off);
 
 	if ((tcphoff < 0) || (tcphoff > oldskb->len)) {
 		pr_debug("Cannot get TCP header.\n");
@@ -93,8 +94,8 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
 
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_proto = IPPROTO_TCP;
-	ipv6_addr_copy(&fl6.saddr, &oip6h->daddr);
-	ipv6_addr_copy(&fl6.daddr, &oip6h->saddr);
+	fl6.saddr = oip6h->daddr;
+	fl6.daddr = oip6h->saddr;
 	fl6.fl6_sport = otcph.dest;
 	fl6.fl6_dport = otcph.source;
 	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
@@ -129,8 +130,8 @@ static void send_reset(struct net *net, struct sk_buff *oldskb)
 	*(__be32 *)ip6h =  htonl(0x60000000 | (tclass << 20));
 	ip6h->hop_limit = ip6_dst_hoplimit(dst);
 	ip6h->nexthdr = IPPROTO_TCP;
-	ipv6_addr_copy(&ip6h->saddr, &oip6h->daddr);
-	ipv6_addr_copy(&ip6h->daddr, &oip6h->saddr);
+	ip6h->saddr = oip6h->daddr;
+	ip6h->daddr = oip6h->saddr;
 
 	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
 	/* Truncate to length (no data) */
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 1008ce9..fdeb6d0 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -142,11 +142,7 @@ static const struct snmp_mib snmp6_udplite6_list[] = {
 	SNMP_MIB_SENTINEL
 };
 
-/* can be called either with percpu mib (pcpumib != NULL),
- * or shared one (smib != NULL)
- */
-static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **pcpumib,
-				     atomic_long_t *smib)
+static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, atomic_long_t *smib)
 {
 	char name[32];
 	int i;
@@ -163,14 +159,14 @@ static void snmp6_seq_show_icmpv6msg(struct seq_file *seq, void __percpu **pcpum
 		snprintf(name, sizeof(name), "Icmp6%s%s",
 			i & 0x100 ? "Out" : "In", p);
 		seq_printf(seq, "%-32s\t%lu\n", name,
-			pcpumib ? snmp_fold_field(pcpumib, i) : atomic_long_read(smib + i));
+			   atomic_long_read(smib + i));
 	}
 
 	/* print by number (nonzero only) - ICMPMsgStat format */
 	for (i = 0; i < ICMP6MSG_MIB_MAX; i++) {
 		unsigned long val;
 
-		val = pcpumib ? snmp_fold_field(pcpumib, i) : atomic_long_read(smib + i);
+		val = atomic_long_read(smib + i);
 		if (!val)
 			continue;
 		snprintf(name, sizeof(name), "Icmp6%sType%u",
@@ -215,8 +211,7 @@ static int snmp6_seq_show(struct seq_file *seq, void *v)
 			    snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp));
 	snmp6_seq_show_item(seq, (void __percpu **)net->mib.icmpv6_statistics,
 			    NULL, snmp6_icmp6_list);
-	snmp6_seq_show_icmpv6msg(seq,
-			    (void __percpu **)net->mib.icmpv6msg_statistics, NULL);
+	snmp6_seq_show_icmpv6msg(seq, net->mib.icmpv6msg_statistics->mibs);
 	snmp6_seq_show_item(seq, (void __percpu **)net->mib.udp_stats_in6,
 			    NULL, snmp6_udp6_list);
 	snmp6_seq_show_item(seq, (void __percpu **)net->mib.udplite_stats_in6,
@@ -246,7 +241,7 @@ static int snmp6_dev_seq_show(struct seq_file *seq, void *v)
 			    snmp6_ipstats_list);
 	snmp6_seq_show_item(seq, NULL, idev->stats.icmpv6dev->mibs,
 			    snmp6_icmp6_list);
-	snmp6_seq_show_icmpv6msg(seq, NULL, idev->stats.icmpv6msgdev->mibs);
+	snmp6_seq_show_icmpv6msg(seq, idev->stats.icmpv6msgdev->mibs);
 	return 0;
 }
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 331af3b8..a4894f4 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -299,9 +299,9 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	}
 
 	inet->inet_rcv_saddr = inet->inet_saddr = v4addr;
-	ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr);
+	np->rcv_saddr = addr->sin6_addr;
 	if (!(addr_type & IPV6_ADDR_MULTICAST))
-		ipv6_addr_copy(&np->saddr, &addr->sin6_addr);
+		np->saddr = addr->sin6_addr;
 	err = 0;
 out_unlock:
 	rcu_read_unlock();
@@ -383,7 +383,8 @@ static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	}
 
 	/* Charge it to the socket. */
-	if (ip_queue_rcv_skb(sk, skb) < 0) {
+	skb_dst_drop(skb);
+	if (sock_queue_rcv_skb(sk, skb) < 0) {
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
@@ -494,7 +495,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 	if (sin6) {
 		sin6->sin6_family = AF_INET6;
 		sin6->sin6_port = 0;
-		ipv6_addr_copy(&sin6->sin6_addr, &ipv6_hdr(skb)->saddr);
+		sin6->sin6_addr = ipv6_hdr(skb)->saddr;
 		sin6->sin6_flowinfo = 0;
 		sin6->sin6_scope_id = 0;
 		if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
@@ -610,6 +611,8 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
 	struct sk_buff *skb;
 	int err;
 	struct rt6_info *rt = (struct rt6_info *)*dstp;
+	int hlen = LL_RESERVED_SPACE(rt->dst.dev);
+	int tlen = rt->dst.dev->needed_tailroom;
 
 	if (length > rt->dst.dev->mtu) {
 		ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu);
@@ -619,11 +622,11 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
 		goto out;
 
 	skb = sock_alloc_send_skb(sk,
-				  length + LL_ALLOCATED_SPACE(rt->dst.dev) + 15,
+				  length + hlen + tlen + 15,
 				  flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto error;
-	skb_reserve(skb, LL_RESERVED_SPACE(rt->dst.dev));
+	skb_reserve(skb, hlen);
 
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
@@ -843,11 +846,11 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 		goto out;
 
 	if (!ipv6_addr_any(daddr))
-		ipv6_addr_copy(&fl6.daddr, daddr);
+		fl6.daddr = *daddr;
 	else
 		fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
 	if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
-		ipv6_addr_copy(&fl6.saddr, &np->saddr);
+		fl6.saddr = np->saddr;
 
 	final_p = fl6_update_dst(&fl6, opt, &final);
 
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index dfb164e..b69fae7 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -153,8 +153,8 @@ void ip6_frag_init(struct inet_frag_queue *q, void *a)
 
 	fq->id = arg->id;
 	fq->user = arg->user;
-	ipv6_addr_copy(&fq->saddr, arg->src);
-	ipv6_addr_copy(&fq->daddr, arg->dst);
+	fq->saddr = *arg->src;
+	fq->daddr = *arg->dst;
 }
 EXPORT_SYMBOL(ip6_frag_init);
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8473016..ad43854 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -77,7 +77,7 @@ static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort,
 				    const struct in6_addr *dest);
 static struct dst_entry	*ip6_dst_check(struct dst_entry *dst, u32 cookie);
 static unsigned int	 ip6_default_advmss(const struct dst_entry *dst);
-static unsigned int	 ip6_default_mtu(const struct dst_entry *dst);
+static unsigned int	 ip6_mtu(const struct dst_entry *dst);
 static struct dst_entry *ip6_negative_advice(struct dst_entry *);
 static void		ip6_dst_destroy(struct dst_entry *);
 static void		ip6_dst_ifdown(struct dst_entry *,
@@ -144,7 +144,7 @@ static struct dst_ops ip6_dst_ops_template = {
 	.gc_thresh		=	1024,
 	.check			=	ip6_dst_check,
 	.default_advmss		=	ip6_default_advmss,
-	.default_mtu		=	ip6_default_mtu,
+	.mtu			=	ip6_mtu,
 	.cow_metrics		=	ipv6_cow_metrics,
 	.destroy		=	ip6_dst_destroy,
 	.ifdown			=	ip6_dst_ifdown,
@@ -155,9 +155,11 @@ static struct dst_ops ip6_dst_ops_template = {
 	.neigh_lookup		=	ip6_neigh_lookup,
 };
 
-static unsigned int ip6_blackhole_default_mtu(const struct dst_entry *dst)
+static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst)
 {
-	return 0;
+	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+	return mtu ? : dst->dev->mtu;
 }
 
 static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
@@ -175,7 +177,7 @@ static struct dst_ops ip6_dst_blackhole_ops = {
 	.protocol		=	cpu_to_be16(ETH_P_IPV6),
 	.destroy		=	ip6_dst_destroy,
 	.check			=	ip6_dst_check,
-	.default_mtu		=	ip6_blackhole_default_mtu,
+	.mtu			=	ip6_blackhole_mtu,
 	.default_advmss		=	ip6_default_advmss,
 	.update_pmtu		=	ip6_rt_blackhole_update_pmtu,
 	.cow_metrics		=	ip6_rt_blackhole_cow_metrics,
@@ -245,9 +247,9 @@ static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops,
 {
 	struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, flags);
 
-	if (rt != NULL)
+	if (rt)
 		memset(&rt->rt6i_table, 0,
-			sizeof(*rt) - sizeof(struct dst_entry));
+		       sizeof(*rt) - sizeof(struct dst_entry));
 
 	return rt;
 }
@@ -261,7 +263,7 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 	if (!(rt->dst.flags & DST_HOST))
 		dst_destroy_metrics_generic(dst);
 
-	if (idev != NULL) {
+	if (idev) {
 		rt->rt6i_idev = NULL;
 		in6_dev_put(idev);
 	}
@@ -297,10 +299,10 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
 	struct net_device *loopback_dev =
 		dev_net(dev)->loopback_dev;
 
-	if (dev != loopback_dev && idev != NULL && idev->dev == dev) {
+	if (dev != loopback_dev && idev && idev->dev == dev) {
 		struct inet6_dev *loopback_idev =
 			in6_dev_get(loopback_dev);
-		if (loopback_idev != NULL) {
+		if (loopback_idev) {
 			rt->rt6i_idev = loopback_idev;
 			in6_dev_put(idev);
 		}
@@ -342,7 +344,7 @@ static inline struct rt6_info *rt6_device_match(struct net *net,
 			if (dev->ifindex == oif)
 				return sprt;
 			if (dev->flags & IFF_LOOPBACK) {
-				if (sprt->rt6i_idev == NULL ||
+				if (!sprt->rt6i_idev ||
 				    sprt->rt6i_idev->dev->ifindex != oif) {
 					if (flags & RT6_LOOKUP_F_IFACE && oif)
 						continue;
@@ -383,7 +385,7 @@ static void rt6_probe(struct rt6_info *rt)
 	 * to no more than one per minute.
 	 */
 	rcu_read_lock();
-	neigh = rt ? dst_get_neighbour(&rt->dst) : NULL;
+	neigh = rt ? dst_get_neighbour_noref(&rt->dst) : NULL;
 	if (!neigh || (neigh->nud_state & NUD_VALID))
 		goto out;
 	read_lock_bh(&neigh->lock);
@@ -430,7 +432,7 @@ static inline int rt6_check_neigh(struct rt6_info *rt)
 	int m;
 
 	rcu_read_lock();
-	neigh = dst_get_neighbour(&rt->dst);
+	neigh = dst_get_neighbour_noref(&rt->dst);
 	if (rt->rt6i_flags & RTF_NONEXTHOP ||
 	    !(rt->rt6i_flags & RTF_GATEWAY))
 		m = 1;
@@ -634,7 +636,7 @@ do { \
 				goto restart; \
 		} \
 	} \
-} while(0)
+} while (0)
 
 static struct rt6_info *ip6_pol_route_lookup(struct net *net,
 					     struct fib6_table *table,
@@ -725,24 +727,25 @@ static struct rt6_info *rt6_alloc_cow(const struct rt6_info *ort,
 		struct neighbour *neigh;
 		int attempts = !in_softirq();
 
-		if (!(rt->rt6i_flags&RTF_GATEWAY)) {
-			if (rt->rt6i_dst.plen != 128 &&
+		if (!(rt->rt6i_flags & RTF_GATEWAY)) {
+			if (ort->rt6i_dst.plen != 128 &&
 			    ipv6_addr_equal(&ort->rt6i_dst.addr, daddr))
 				rt->rt6i_flags |= RTF_ANYCAST;
-			ipv6_addr_copy(&rt->rt6i_gateway, daddr);
+			rt->rt6i_gateway = *daddr;
 		}
 
 		rt->rt6i_flags |= RTF_CACHE;
 
 #ifdef CONFIG_IPV6_SUBTREES
 		if (rt->rt6i_src.plen && saddr) {
-			ipv6_addr_copy(&rt->rt6i_src.addr, saddr);
+			rt->rt6i_src.addr = *saddr;
 			rt->rt6i_src.plen = 128;
 		}
 #endif
 
 	retry:
-		neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
+		neigh = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway,
+					     rt->rt6i_dev);
 		if (IS_ERR(neigh)) {
 			struct net *net = dev_net(rt->rt6i_dev);
 			int saved_rt_min_interval =
@@ -783,7 +786,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort,
 
 	if (rt) {
 		rt->rt6i_flags |= RTF_CACHE;
-		dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_raw(&ort->dst)));
+		dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour_noref_raw(&ort->dst)));
 	}
 	return rt;
 }
@@ -817,7 +820,7 @@ restart:
 	dst_hold(&rt->dst);
 	read_unlock_bh(&table->tb6_lock);
 
-	if (!dst_get_neighbour_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
+	if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
 		nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
 	else if (!(rt->dst.flags & DST_HOST))
 		nrt = rt6_alloc_clone(rt, &fl6->daddr);
@@ -873,7 +876,7 @@ void ip6_route_input(struct sk_buff *skb)
 		.flowi6_iif = skb->dev->ifindex,
 		.daddr = iph->daddr,
 		.saddr = iph->saddr,
-		.flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK,
+		.flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK,
 		.flowi6_mark = skb->mark,
 		.flowi6_proto = iph->nexthdr,
 	};
@@ -932,7 +935,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
 			in6_dev_hold(rt->rt6i_idev);
 		rt->rt6i_expires = 0;
 
-		ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway);
+		rt->rt6i_gateway = ort->rt6i_gateway;
 		rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
 		rt->rt6i_metric = 0;
 
@@ -995,7 +998,7 @@ static void ip6_link_failure(struct sk_buff *skb)
 
 	rt = (struct rt6_info *) skb_dst(skb);
 	if (rt) {
-		if (rt->rt6i_flags&RTF_CACHE) {
+		if (rt->rt6i_flags & RTF_CACHE) {
 			dst_set_expires(&rt->dst, 0);
 			rt->rt6i_flags |= RTF_EXPIRES;
 		} else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT))
@@ -1041,10 +1044,15 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst)
 	return mtu;
 }
 
-static unsigned int ip6_default_mtu(const struct dst_entry *dst)
+static unsigned int ip6_mtu(const struct dst_entry *dst)
 {
-	unsigned int mtu = IPV6_MIN_MTU;
 	struct inet6_dev *idev;
+	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+	if (mtu)
+		return mtu;
+
+	mtu = IPV6_MIN_MTU;
 
 	rcu_read_lock();
 	idev = __in6_dev_get(dst->dev);
@@ -1060,34 +1068,38 @@ static DEFINE_SPINLOCK(icmp6_dst_lock);
 
 struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 				  struct neighbour *neigh,
-				  const struct in6_addr *addr)
+				  struct flowi6 *fl6)
 {
+	struct dst_entry *dst;
 	struct rt6_info *rt;
 	struct inet6_dev *idev = in6_dev_get(dev);
 	struct net *net = dev_net(dev);
 
-	if (unlikely(idev == NULL))
+	if (unlikely(!idev))
 		return NULL;
 
 	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0);
-	if (unlikely(rt == NULL)) {
+	if (unlikely(!rt)) {
 		in6_dev_put(idev);
+		dst = ERR_PTR(-ENOMEM);
 		goto out;
 	}
 
 	if (neigh)
 		neigh_hold(neigh);
 	else {
-		neigh = ndisc_get_neigh(dev, addr);
-		if (IS_ERR(neigh))
-			neigh = NULL;
+		neigh = __neigh_lookup_errno(&nd_tbl, &fl6->daddr, dev);
+		if (IS_ERR(neigh)) {
+			dst_free(&rt->dst);
+			return ERR_CAST(neigh);
+		}
 	}
 
 	rt->dst.flags |= DST_HOST;
 	rt->dst.output  = ip6_output;
 	dst_set_neighbour(&rt->dst, neigh);
 	atomic_set(&rt->dst.__refcnt, 1);
-	ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
+	rt->rt6i_dst.addr = fl6->daddr;
 	rt->rt6i_dst.plen = 128;
 	rt->rt6i_idev     = idev;
 	dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255);
@@ -1099,8 +1111,10 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 
 	fib6_force_start_gc(net);
 
+	dst = xfrm_lookup(net, &rt->dst, flowi6_to_flowi(fl6), NULL, 0);
+
 out:
-	return &rt->dst;
+	return dst;
 }
 
 int icmp6_dst_gc(void)
@@ -1230,15 +1244,24 @@ int ip6_route_add(struct fib6_config *cfg)
 	if (cfg->fc_metric == 0)
 		cfg->fc_metric = IP6_RT_PRIO_USER;
 
-	table = fib6_new_table(net, cfg->fc_table);
-	if (table == NULL) {
-		err = -ENOBUFS;
-		goto out;
+	err = -ENOBUFS;
+	if (cfg->fc_nlinfo.nlh &&
+	    !(cfg->fc_nlinfo.nlh->nlmsg_flags & NLM_F_CREATE)) {
+		table = fib6_get_table(net, cfg->fc_table);
+		if (!table) {
+			printk(KERN_WARNING "IPv6: NLM_F_CREATE should be specified when creating new route\n");
+			table = fib6_new_table(net, cfg->fc_table);
+		}
+	} else {
+		table = fib6_new_table(net, cfg->fc_table);
 	}
 
+	if (!table)
+		goto out;
+
 	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, DST_NOCOUNT);
 
-	if (rt == NULL) {
+	if (!rt) {
 		err = -ENOMEM;
 		goto out;
 	}
@@ -1287,8 +1310,9 @@ int ip6_route_add(struct fib6_config *cfg)
 	   they would result in kernel looping; promote them to reject routes
 	 */
 	if ((cfg->fc_flags & RTF_REJECT) ||
-	    (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK)
-					      && !(cfg->fc_flags&RTF_LOCAL))) {
+	    (dev && (dev->flags & IFF_LOOPBACK) &&
+	     !(addr_type & IPV6_ADDR_LOOPBACK) &&
+	     !(cfg->fc_flags & RTF_LOCAL))) {
 		/* hold loopback dev/idev if we haven't done so. */
 		if (dev != net->loopback_dev) {
 			if (dev) {
@@ -1315,7 +1339,7 @@ int ip6_route_add(struct fib6_config *cfg)
 		int gwa_type;
 
 		gw_addr = &cfg->fc_gateway;
-		ipv6_addr_copy(&rt->rt6i_gateway, gw_addr);
+		rt->rt6i_gateway = *gw_addr;
 		gwa_type = ipv6_addr_type(gw_addr);
 
 		if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) {
@@ -1329,13 +1353,13 @@ int ip6_route_add(struct fib6_config *cfg)
 			   some exceptions. --ANK
 			 */
 			err = -EINVAL;
-			if (!(gwa_type&IPV6_ADDR_UNICAST))
+			if (!(gwa_type & IPV6_ADDR_UNICAST))
 				goto out;
 
 			grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, 1);
 
 			err = -EHOSTUNREACH;
-			if (grt == NULL)
+			if (!grt)
 				goto out;
 			if (dev) {
 				if (dev != grt->rt6i_dev) {
@@ -1348,7 +1372,7 @@ int ip6_route_add(struct fib6_config *cfg)
 				dev_hold(dev);
 				in6_dev_hold(grt->rt6i_idev);
 			}
-			if (!(grt->rt6i_flags&RTF_GATEWAY))
+			if (!(grt->rt6i_flags & RTF_GATEWAY))
 				err = 0;
 			dst_release(&grt->dst);
 
@@ -1356,12 +1380,12 @@ int ip6_route_add(struct fib6_config *cfg)
 				goto out;
 		}
 		err = -EINVAL;
-		if (dev == NULL || (dev->flags&IFF_LOOPBACK))
+		if (!dev || (dev->flags & IFF_LOOPBACK))
 			goto out;
 	}
 
 	err = -ENODEV;
-	if (dev == NULL)
+	if (!dev)
 		goto out;
 
 	if (!ipv6_addr_any(&cfg->fc_prefsrc)) {
@@ -1369,7 +1393,7 @@ int ip6_route_add(struct fib6_config *cfg)
 			err = -EINVAL;
 			goto out;
 		}
-		ipv6_addr_copy(&rt->rt6i_prefsrc.addr, &cfg->fc_prefsrc);
+		rt->rt6i_prefsrc.addr = cfg->fc_prefsrc;
 		rt->rt6i_prefsrc.plen = 128;
 	} else
 		rt->rt6i_prefsrc.plen = 0;
@@ -1458,7 +1482,7 @@ static int ip6_route_del(struct fib6_config *cfg)
 	int err = -ESRCH;
 
 	table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table);
-	if (table == NULL)
+	if (!table)
 		return err;
 
 	read_lock_bh(&table->tb6_lock);
@@ -1470,7 +1494,7 @@ static int ip6_route_del(struct fib6_config *cfg)
 	if (fn) {
 		for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
 			if (cfg->fc_ifindex &&
-			    (rt->rt6i_dev == NULL ||
+			    (!rt->rt6i_dev ||
 			     rt->rt6i_dev->ifindex != cfg->fc_ifindex))
 				continue;
 			if (cfg->fc_flags & RTF_GATEWAY &&
@@ -1566,7 +1590,7 @@ static struct rt6_info *ip6_route_redirect(const struct in6_addr *dest,
 		},
 	};
 
-	ipv6_addr_copy(&rdfl.gateway, gateway);
+	rdfl.gateway = *gateway;
 
 	if (rt6_need_strict(dest))
 		flags |= RT6_LOOKUP_F_IFACE;
@@ -1611,18 +1635,18 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src,
 	dst_confirm(&rt->dst);
 
 	/* Duplicate redirect: silently ignore. */
-	if (neigh == dst_get_neighbour_raw(&rt->dst))
+	if (neigh == dst_get_neighbour_noref_raw(&rt->dst))
 		goto out;
 
 	nrt = ip6_rt_copy(rt, dest);
-	if (nrt == NULL)
+	if (!nrt)
 		goto out;
 
 	nrt->rt6i_flags = RTF_GATEWAY|RTF_UP|RTF_DYNAMIC|RTF_CACHE;
 	if (on_link)
 		nrt->rt6i_flags &= ~RTF_GATEWAY;
 
-	ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key);
+	nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
 	dst_set_neighbour(&nrt->dst, neigh_clone(neigh));
 
 	if (ip6_ins_rt(nrt))
@@ -1632,7 +1656,7 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src,
 	netevent.new = &nrt->dst;
 	call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
 
-	if (rt->rt6i_flags&RTF_CACHE) {
+	if (rt->rt6i_flags & RTF_CACHE) {
 		ip6_del_rt(rt);
 		return;
 	}
@@ -1653,7 +1677,7 @@ static void rt6_do_pmtu_disc(const struct in6_addr *daddr, const struct in6_addr
 	int allfrag = 0;
 again:
 	rt = rt6_lookup(net, daddr, saddr, ifindex, 0);
-	if (rt == NULL)
+	if (!rt)
 		return;
 
 	if (rt6_check_expired(rt)) {
@@ -1703,7 +1727,7 @@ again:
 	   1. It is connected route. Action: COW
 	   2. It is gatewayed route or NONEXTHOP route. Action: clone it.
 	 */
-	if (!dst_get_neighbour_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
+	if (!dst_get_neighbour_noref_raw(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP))
 		nrt = rt6_alloc_cow(rt, daddr, saddr);
 	else
 		nrt = rt6_alloc_clone(rt, daddr);
@@ -1768,7 +1792,7 @@ static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort,
 		rt->dst.output = ort->dst.output;
 		rt->dst.flags |= DST_HOST;
 
-		ipv6_addr_copy(&rt->rt6i_dst.addr, dest);
+		rt->rt6i_dst.addr = *dest;
 		rt->rt6i_dst.plen = 128;
 		dst_copy_metrics(&rt->dst, &ort->dst);
 		rt->dst.error = ort->dst.error;
@@ -1778,7 +1802,7 @@ static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort,
 		rt->dst.lastuse = jiffies;
 		rt->rt6i_expires = 0;
 
-		ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway);
+		rt->rt6i_gateway = ort->rt6i_gateway;
 		rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
 		rt->rt6i_metric = 0;
 
@@ -1801,7 +1825,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
 	struct fib6_table *table;
 
 	table = fib6_get_table(net, RT6_TABLE_INFO);
-	if (table == NULL)
+	if (!table)
 		return NULL;
 
 	write_lock_bh(&table->tb6_lock);
@@ -1841,8 +1865,8 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
 		.fc_nlinfo.nl_net = net,
 	};
 
-	ipv6_addr_copy(&cfg.fc_dst, prefix);
-	ipv6_addr_copy(&cfg.fc_gateway, gwaddr);
+	cfg.fc_dst = *prefix;
+	cfg.fc_gateway = *gwaddr;
 
 	/* We should treat it as a default route if prefix length is 0. */
 	if (!prefixlen)
@@ -1860,7 +1884,7 @@ struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_dev
 	struct fib6_table *table;
 
 	table = fib6_get_table(dev_net(dev), RT6_TABLE_DFLT);
-	if (table == NULL)
+	if (!table)
 		return NULL;
 
 	write_lock_bh(&table->tb6_lock);
@@ -1891,7 +1915,7 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
 		.fc_nlinfo.nl_net = dev_net(dev),
 	};
 
-	ipv6_addr_copy(&cfg.fc_gateway, gwaddr);
+	cfg.fc_gateway = *gwaddr;
 
 	ip6_route_add(&cfg);
 
@@ -1905,7 +1929,7 @@ void rt6_purge_dflt_routers(struct net *net)
 
 	/* NOTE: Keep consistent with rt6_get_dflt_router */
 	table = fib6_get_table(net, RT6_TABLE_DFLT);
-	if (table == NULL)
+	if (!table)
 		return;
 
 restart:
@@ -1937,9 +1961,9 @@ static void rtmsg_to_fib6_config(struct net *net,
 
 	cfg->fc_nlinfo.nl_net = net;
 
-	ipv6_addr_copy(&cfg->fc_dst, &rtmsg->rtmsg_dst);
-	ipv6_addr_copy(&cfg->fc_src, &rtmsg->rtmsg_src);
-	ipv6_addr_copy(&cfg->fc_gateway, &rtmsg->rtmsg_gateway);
+	cfg->fc_dst = rtmsg->rtmsg_dst;
+	cfg->fc_src = rtmsg->rtmsg_src;
+	cfg->fc_gateway = rtmsg->rtmsg_gateway;
 }
 
 int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg)
@@ -2038,14 +2062,14 @@ static int ip6_pkt_prohibit_out(struct sk_buff *skb)
 
 struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 				    const struct in6_addr *addr,
-				    int anycast)
+				    bool anycast)
 {
 	struct net *net = dev_net(idev->dev);
 	struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops,
 					    net->loopback_dev, 0);
 	struct neighbour *neigh;
 
-	if (rt == NULL) {
+	if (!rt) {
 		if (net_ratelimit())
 			pr_warning("IPv6:  Maximum number of routes reached,"
 				   " consider increasing route/max_size.\n");
@@ -2065,7 +2089,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 		rt->rt6i_flags |= RTF_ANYCAST;
 	else
 		rt->rt6i_flags |= RTF_LOCAL;
-	neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
+	neigh = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, rt->rt6i_dev);
 	if (IS_ERR(neigh)) {
 		dst_free(&rt->dst);
 
@@ -2073,7 +2097,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
 	}
 	dst_set_neighbour(&rt->dst, neigh);
 
-	ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
+	rt->rt6i_dst.addr = *addr;
 	rt->rt6i_dst.plen = 128;
 	rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);
 
@@ -2091,7 +2115,7 @@ int ip6_route_get_saddr(struct net *net,
 	struct inet6_dev *idev = ip6_dst_idev((struct dst_entry*)rt);
 	int err = 0;
 	if (rt->rt6i_prefsrc.plen)
-		ipv6_addr_copy(saddr, &rt->rt6i_prefsrc.addr);
+		*saddr = rt->rt6i_prefsrc.addr;
 	else
 		err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
 					 daddr, prefs, saddr);
@@ -2111,7 +2135,7 @@ static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg)
 	struct net *net = ((struct arg_dev_net_ip *)arg)->net;
 	struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
 
-	if (((void *)rt->rt6i_dev == dev || dev == NULL) &&
+	if (((void *)rt->rt6i_dev == dev || !dev) &&
 	    rt != net->ipv6.ip6_null_entry &&
 	    ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) {
 		/* remove prefsrc entry */
@@ -2141,7 +2165,7 @@ static int fib6_ifdown(struct rt6_info *rt, void *arg)
 	const struct arg_dev_net *adn = arg;
 	const struct net_device *dev = adn->dev;
 
-	if ((rt->rt6i_dev == dev || dev == NULL) &&
+	if ((rt->rt6i_dev == dev || !dev) &&
 	    rt != adn->net->ipv6.ip6_null_entry) {
 		RT6_TRACE("deleted by ifdown %p\n", rt);
 		return -1;
@@ -2178,7 +2202,7 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
 	*/
 
 	idev = __in6_dev_get(arg->dev);
-	if (idev == NULL)
+	if (!idev)
 		return 0;
 
 	/* For administrative MTU increase, there is no way to discover
@@ -2358,7 +2382,7 @@ static int rt6_fill_node(struct net *net,
 	}
 
 	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtm), flags);
-	if (nlh == NULL)
+	if (!nlh)
 		return -EMSGSIZE;
 
 	rtm = nlmsg_data(nlh);
@@ -2372,25 +2396,25 @@ static int rt6_fill_node(struct net *net,
 		table = RT6_TABLE_UNSPEC;
 	rtm->rtm_table = table;
 	NLA_PUT_U32(skb, RTA_TABLE, table);
-	if (rt->rt6i_flags&RTF_REJECT)
+	if (rt->rt6i_flags & RTF_REJECT)
 		rtm->rtm_type = RTN_UNREACHABLE;
-	else if (rt->rt6i_flags&RTF_LOCAL)
+	else if (rt->rt6i_flags & RTF_LOCAL)
 		rtm->rtm_type = RTN_LOCAL;
-	else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK))
+	else if (rt->rt6i_dev && (rt->rt6i_dev->flags & IFF_LOOPBACK))
 		rtm->rtm_type = RTN_LOCAL;
 	else
 		rtm->rtm_type = RTN_UNICAST;
 	rtm->rtm_flags = 0;
 	rtm->rtm_scope = RT_SCOPE_UNIVERSE;
 	rtm->rtm_protocol = rt->rt6i_protocol;
-	if (rt->rt6i_flags&RTF_DYNAMIC)
+	if (rt->rt6i_flags & RTF_DYNAMIC)
 		rtm->rtm_protocol = RTPROT_REDIRECT;
 	else if (rt->rt6i_flags & RTF_ADDRCONF)
 		rtm->rtm_protocol = RTPROT_KERNEL;
-	else if (rt->rt6i_flags&RTF_DEFAULT)
+	else if (rt->rt6i_flags & RTF_DEFAULT)
 		rtm->rtm_protocol = RTPROT_RA;
 
-	if (rt->rt6i_flags&RTF_CACHE)
+	if (rt->rt6i_flags & RTF_CACHE)
 		rtm->rtm_flags |= RTM_F_CLONED;
 
 	if (dst) {
@@ -2430,7 +2454,7 @@ static int rt6_fill_node(struct net *net,
 
 	if (rt->rt6i_prefsrc.plen) {
 		struct in6_addr saddr_buf;
-		ipv6_addr_copy(&saddr_buf, &rt->rt6i_prefsrc.addr);
+		saddr_buf = rt->rt6i_prefsrc.addr;
 		NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
 	}
 
@@ -2438,7 +2462,7 @@ static int rt6_fill_node(struct net *net,
 		goto nla_put_failure;
 
 	rcu_read_lock();
-	n = dst_get_neighbour(&rt->dst);
+	n = dst_get_neighbour_noref(&rt->dst);
 	if (n)
 		NLA_PUT(skb, RTA_GATEWAY, 16, &n->primary_key);
 	rcu_read_unlock();
@@ -2504,14 +2528,14 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
 		if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
 			goto errout;
 
-		ipv6_addr_copy(&fl6.saddr, nla_data(tb[RTA_SRC]));
+		fl6.saddr = *(struct in6_addr *)nla_data(tb[RTA_SRC]);
 	}
 
 	if (tb[RTA_DST]) {
 		if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr))
 			goto errout;
 
-		ipv6_addr_copy(&fl6.daddr, nla_data(tb[RTA_DST]));
+		fl6.daddr = *(struct in6_addr *)nla_data(tb[RTA_DST]);
 	}
 
 	if (tb[RTA_IIF])
@@ -2530,7 +2554,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void
 	}
 
 	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
-	if (skb == NULL) {
+	if (!skb) {
 		err = -ENOBUFS;
 		goto errout;
 	}
@@ -2565,10 +2589,10 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info)
 	int err;
 
 	err = -ENOBUFS;
-	seq = info->nlh != NULL ? info->nlh->nlmsg_seq : 0;
+	seq = info->nlh ? info->nlh->nlmsg_seq : 0;
 
 	skb = nlmsg_new(rt6_nlmsg_size(), gfp_any());
-	if (skb == NULL)
+	if (!skb)
 		goto errout;
 
 	err = rt6_fill_node(net, skb, rt, NULL, NULL, 0,
@@ -2635,7 +2659,7 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg)
 	seq_puts(m, "00000000000000000000000000000000 00 ");
 #endif
 	rcu_read_lock();
-	n = dst_get_neighbour(&rt->dst);
+	n = dst_get_neighbour_noref(&rt->dst);
 	if (n) {
 		seq_printf(m, "%pi6", n->primary_key);
 	} else {
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a7a1860..3b6dac9 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -91,7 +91,7 @@ struct pcpu_tstats {
 	unsigned long	rx_bytes;
 	unsigned long	tx_packets;
 	unsigned long	tx_bytes;
-};
+} __attribute__((aligned(4*sizeof(unsigned long))));
 
 static struct net_device_stats *ipip6_get_stats(struct net_device *dev)
 {
@@ -263,6 +263,8 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
 	if (register_netdevice(dev) < 0)
 		goto failed_free;
 
+	strcpy(nt->parms.name, dev->name);
+
 	dev_hold(dev);
 
 	ipip6_tunnel_link(sitn, nt);
@@ -680,7 +682,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		struct neighbour *neigh = NULL;
 
 		if (skb_dst(skb))
-			neigh = dst_get_neighbour(skb_dst(skb));
+			neigh = dst_get_neighbour_noref(skb_dst(skb));
 
 		if (neigh == NULL) {
 			if (net_ratelimit())
@@ -705,7 +707,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
 		struct neighbour *neigh = NULL;
 
 		if (skb_dst(skb))
-			neigh = dst_get_neighbour(skb_dst(skb));
+			neigh = dst_get_neighbour_noref(skb_dst(skb));
 
 		if (neigh == NULL) {
 			if (net_ratelimit())
@@ -914,7 +916,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 				goto done;
 #ifdef CONFIG_IPV6_SIT_6RD
 		} else {
-			ipv6_addr_copy(&ip6rd.prefix, &t->ip6rd.prefix);
+			ip6rd.prefix = t->ip6rd.prefix;
 			ip6rd.relay_prefix = t->ip6rd.relay_prefix;
 			ip6rd.prefixlen = t->ip6rd.prefixlen;
 			ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen;
@@ -1082,7 +1084,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
 			if (relay_prefix != ip6rd.relay_prefix)
 				goto done;
 
-			ipv6_addr_copy(&t->ip6rd.prefix, &prefix);
+			t->ip6rd.prefix = prefix;
 			t->ip6rd.relay_prefix = relay_prefix;
 			t->ip6rd.prefixlen = ip6rd.prefixlen;
 			t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen;
@@ -1144,7 +1146,6 @@ static int ipip6_tunnel_init(struct net_device *dev)
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 
 	tunnel->dev = dev;
-	strcpy(tunnel->parms.name, dev->name);
 
 	memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
 	memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
@@ -1207,6 +1208,7 @@ static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_hea
 static int __net_init sit_init_net(struct net *net)
 {
 	struct sit_net *sitn = net_generic(net, sit_net_id);
+	struct ip_tunnel *t;
 	int err;
 
 	sitn->tunnels[0] = sitn->tunnels_wc;
@@ -1231,6 +1233,9 @@ static int __net_init sit_init_net(struct net *net)
 	if ((err = register_netdev(sitn->fb_tunnel_dev)))
 		goto err_reg_dev;
 
+	t = netdev_priv(sitn->fb_tunnel_dev);
+
+	strcpy(t->parms.name, sitn->fb_tunnel_dev->name);
 	return 0;
 
 err_reg_dev:
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 5a0d664..8e951d8 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -200,8 +200,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	req->mss = mss;
 	ireq->rmt_port = th->source;
 	ireq->loc_port = th->dest;
-	ipv6_addr_copy(&ireq6->rmt_addr, &ipv6_hdr(skb)->saddr);
-	ipv6_addr_copy(&ireq6->loc_addr, &ipv6_hdr(skb)->daddr);
+	ireq6->rmt_addr = ipv6_hdr(skb)->saddr;
+	ireq6->loc_addr = ipv6_hdr(skb)->daddr;
 	if (ipv6_opt_accepted(sk, skb) ||
 	    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
 	    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
@@ -237,9 +237,9 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		struct flowi6 fl6;
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_proto = IPPROTO_TCP;
-		ipv6_addr_copy(&fl6.daddr, &ireq6->rmt_addr);
+		fl6.daddr = ireq6->rmt_addr;
 		final_p = fl6_update_dst(&fl6, np->opt, &final);
-		ipv6_addr_copy(&fl6.saddr, &ireq6->loc_addr);
+		fl6.saddr = ireq6->loc_addr;
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 		fl6.flowi6_mark = sk->sk_mark;
 		fl6.fl6_dport = inet_rsk(req)->rmt_port;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 36131d1..906c7ca 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -62,6 +62,7 @@
 #include <net/netdma.h>
 #include <net/inet_common.h>
 #include <net/secure_seq.h>
+#include <net/tcp_memcontrol.h>
 
 #include <asm/uaccess.h>
 
@@ -153,7 +154,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
 			if (flowlabel == NULL)
 				return -EINVAL;
-			ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
+			usin->sin6_addr = flowlabel->dst;
 			fl6_sock_release(flowlabel);
 		}
 	}
@@ -195,7 +196,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		tp->write_seq = 0;
 	}
 
-	ipv6_addr_copy(&np->daddr, &usin->sin6_addr);
+	np->daddr = usin->sin6_addr;
 	np->flow_label = fl6.flowlabel;
 
 	/*
@@ -244,9 +245,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 		saddr = &np->rcv_saddr;
 
 	fl6.flowi6_proto = IPPROTO_TCP;
-	ipv6_addr_copy(&fl6.daddr, &np->daddr);
-	ipv6_addr_copy(&fl6.saddr,
-		       (saddr ? saddr : &np->saddr));
+	fl6.daddr = np->daddr;
+	fl6.saddr = saddr ? *saddr : np->saddr;
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.fl6_dport = usin->sin6_port;
@@ -264,11 +264,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 
 	if (saddr == NULL) {
 		saddr = &fl6.saddr;
-		ipv6_addr_copy(&np->rcv_saddr, saddr);
+		np->rcv_saddr = *saddr;
 	}
 
 	/* set the source address */
-	ipv6_addr_copy(&np->saddr, saddr);
+	np->saddr = *saddr;
 	inet->inet_rcv_saddr = LOOPBACK4_IPV6;
 
 	sk->sk_gso_type = SKB_GSO_TCPV6;
@@ -398,8 +398,8 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 			 */
 			memset(&fl6, 0, sizeof(fl6));
 			fl6.flowi6_proto = IPPROTO_TCP;
-			ipv6_addr_copy(&fl6.daddr, &np->daddr);
-			ipv6_addr_copy(&fl6.saddr, &np->saddr);
+			fl6.daddr = np->daddr;
+			fl6.saddr = np->saddr;
 			fl6.flowi6_oif = sk->sk_bound_dev_if;
 			fl6.flowi6_mark = sk->sk_mark;
 			fl6.fl6_dport = inet->inet_dport;
@@ -489,8 +489,8 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
 
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_proto = IPPROTO_TCP;
-	ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr);
-	ipv6_addr_copy(&fl6.saddr, &treq->loc_addr);
+	fl6.daddr = treq->rmt_addr;
+	fl6.saddr = treq->loc_addr;
 	fl6.flowlabel = 0;
 	fl6.flowi6_oif = treq->iif;
 	fl6.flowi6_mark = sk->sk_mark;
@@ -512,7 +512,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
 	if (skb) {
 		__tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr);
 
-		ipv6_addr_copy(&fl6.daddr, &treq->rmt_addr);
+		fl6.daddr = treq->rmt_addr;
 		err = ip6_xmit(sk, skb, &fl6, opt, np->tclass);
 		err = net_xmit_eval(err);
 	}
@@ -617,8 +617,7 @@ static int tcp_v6_md5_do_add(struct sock *sk, const struct in6_addr *peer,
 			tp->md5sig_info->alloced6++;
 		}
 
-		ipv6_addr_copy(&tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr,
-			       peer);
+		tp->md5sig_info->keys6[tp->md5sig_info->entries6].addr = *peer;
 		tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.key = newkey;
 		tp->md5sig_info->keys6[tp->md5sig_info->entries6].base.keylen = newkeylen;
 
@@ -750,8 +749,8 @@ static int tcp_v6_md5_hash_pseudoheader(struct tcp_md5sig_pool *hp,
 
 	bp = &hp->md5_blk.ip6;
 	/* 1. TCP pseudo-header (RFC2460) */
-	ipv6_addr_copy(&bp->saddr, saddr);
-	ipv6_addr_copy(&bp->daddr, daddr);
+	bp->saddr = *saddr;
+	bp->daddr = *daddr;
 	bp->protocol = cpu_to_be32(IPPROTO_TCP);
 	bp->len = cpu_to_be32(nbytes);
 
@@ -1039,8 +1038,8 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 #endif
 
 	memset(&fl6, 0, sizeof(fl6));
-	ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->saddr);
-	ipv6_addr_copy(&fl6.saddr, &ipv6_hdr(skb)->daddr);
+	fl6.daddr = ipv6_hdr(skb)->saddr;
+	fl6.saddr = ipv6_hdr(skb)->daddr;
 
 	buff->ip_summed = CHECKSUM_PARTIAL;
 	buff->csum = 0;
@@ -1250,11 +1249,18 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	tcp_openreq_init(req, &tmp_opt, skb);
 
 	treq = inet6_rsk(req);
-	ipv6_addr_copy(&treq->rmt_addr, &ipv6_hdr(skb)->saddr);
-	ipv6_addr_copy(&treq->loc_addr, &ipv6_hdr(skb)->daddr);
+	treq->rmt_addr = ipv6_hdr(skb)->saddr;
+	treq->loc_addr = ipv6_hdr(skb)->daddr;
 	if (!want_cookie || tmp_opt.tstamp_ok)
 		TCP_ECN_create_request(req, tcp_hdr(skb));
 
+	treq->iif = sk->sk_bound_dev_if;
+
+	/* So that link locals have meaning */
+	if (!sk->sk_bound_dev_if &&
+	    ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL)
+		treq->iif = inet6_iif(skb);
+
 	if (!isn) {
 		struct inet_peer *peer = NULL;
 
@@ -1264,12 +1270,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 			atomic_inc(&skb->users);
 			treq->pktopts = skb;
 		}
-		treq->iif = sk->sk_bound_dev_if;
-
-		/* So that link locals have meaning */
-		if (!sk->sk_bound_dev_if &&
-		    ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL)
-			treq->iif = inet6_iif(skb);
 
 		if (want_cookie) {
 			isn = cookie_v6_init_sequence(sk, skb, &req->mss);
@@ -1380,7 +1380,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 		ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr);
 
-		ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr);
+		newnp->rcv_saddr = newnp->saddr;
 
 		inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
 		newsk->sk_backlog_rcv = tcp_v4_do_rcv;
@@ -1444,9 +1444,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
-	ipv6_addr_copy(&newnp->daddr, &treq->rmt_addr);
-	ipv6_addr_copy(&newnp->saddr, &treq->loc_addr);
-	ipv6_addr_copy(&newnp->rcv_saddr, &treq->loc_addr);
+	newnp->daddr = treq->rmt_addr;
+	newnp->saddr = treq->loc_addr;
+	newnp->rcv_saddr = treq->loc_addr;
 	newsk->sk_bound_dev_if = treq->iif;
 
 	/* Now IPv6 options...
@@ -1995,7 +1995,8 @@ static int tcp_v6_init_sock(struct sock *sk)
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
 	local_bh_disable();
-	percpu_counter_inc(&tcp_sockets_allocated);
+	sock_update_memcg(sk);
+	sk_sockets_allocated_inc(sk);
 	local_bh_enable();
 
 	return 0;
@@ -2214,7 +2215,6 @@ struct proto tcpv6_prot = {
 	.memory_allocated	= &tcp_memory_allocated,
 	.memory_pressure	= &tcp_memory_pressure,
 	.orphan_count		= &tcp_orphan_count,
-	.sysctl_mem		= sysctl_tcp_mem,
 	.sysctl_wmem		= sysctl_tcp_wmem,
 	.sysctl_rmem		= sysctl_tcp_rmem,
 	.max_header		= MAX_TCP_HEADER,
@@ -2228,6 +2228,9 @@ struct proto tcpv6_prot = {
 	.compat_setsockopt	= compat_tcp_setsockopt,
 	.compat_getsockopt	= compat_tcp_getsockopt,
 #endif
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+	.proto_cgroup		= tcp_proto_cgroup,
+#endif
 };
 
 static const struct inet6_protocol tcpv6_protocol = {
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 846f4757..4f96b5c 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -238,7 +238,7 @@ exact_match:
 	return result;
 }
 
-static struct sock *__udp6_lib_lookup(struct net *net,
+struct sock *__udp6_lib_lookup(struct net *net,
 				      const struct in6_addr *saddr, __be16 sport,
 				      const struct in6_addr *daddr, __be16 dport,
 				      int dif, struct udp_table *udptable)
@@ -305,6 +305,7 @@ begin:
 	rcu_read_unlock();
 	return result;
 }
+EXPORT_SYMBOL_GPL(__udp6_lib_lookup);
 
 static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
 					  __be16 sport, __be16 dport,
@@ -340,7 +341,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct inet_sock *inet = inet_sk(sk);
 	struct sk_buff *skb;
-	unsigned int ulen;
+	unsigned int ulen, copied;
 	int peeked;
 	int err;
 	int is_udplite = IS_UDPLITE(sk);
@@ -363,9 +364,10 @@ try_again:
 		goto out;
 
 	ulen = skb->len - sizeof(struct udphdr);
-	if (len > ulen)
-		len = ulen;
-	else if (len < ulen)
+	copied = len;
+	if (copied > ulen)
+		copied = ulen;
+	else if (copied < ulen)
 		msg->msg_flags |= MSG_TRUNC;
 
 	is_udp4 = (skb->protocol == htons(ETH_P_IP));
@@ -376,14 +378,14 @@ try_again:
 	 * coverage checksum (UDP-Lite), do it before the copy.
 	 */
 
-	if (len < ulen || UDP_SKB_CB(skb)->partial_cov) {
+	if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
 		if (udp_lib_checksum_complete(skb))
 			goto csum_copy_err;
 	}
 
 	if (skb_csum_unnecessary(skb))
 		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
-					      msg->msg_iov,len);
+					      msg->msg_iov, copied       );
 	else {
 		err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov);
 		if (err == -EINVAL)
@@ -417,8 +419,7 @@ try_again:
 			ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr,
 					       &sin6->sin6_addr);
 		else {
-			ipv6_addr_copy(&sin6->sin6_addr,
-				       &ipv6_hdr(skb)->saddr);
+			sin6->sin6_addr = ipv6_hdr(skb)->saddr;
 			if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
 				sin6->sin6_scope_id = IP6CB(skb)->iif;
 		}
@@ -432,7 +433,7 @@ try_again:
 			datagram_recv_ctl(sk, msg, skb);
 	}
 
-	err = len;
+	err = copied;
 	if (flags & MSG_TRUNC)
 		err = ulen;
 
@@ -538,7 +539,9 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
 			goto drop;
 	}
 
-	if ((rc = ip_queue_rcv_skb(sk, skb)) < 0) {
+	skb_dst_drop(skb);
+	rc = sock_queue_rcv_skb(sk, skb);
+	if (rc < 0) {
 		/* Note that an ENOMEM error is charged twice */
 		if (rc == -ENOMEM)
 			UDP6_INC_STATS_BH(sock_net(sk),
@@ -1113,11 +1116,11 @@ do_udp_sendmsg:
 
 	fl6.flowi6_proto = sk->sk_protocol;
 	if (!ipv6_addr_any(daddr))
-		ipv6_addr_copy(&fl6.daddr, daddr);
+		fl6.daddr = *daddr;
 	else
 		fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
 	if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
-		ipv6_addr_copy(&fl6.saddr, &np->saddr);
+		fl6.saddr = np->saddr;
 	fl6.fl6_sport = inet->inet_sport;
 
 	final_p = fl6_update_dst(&fl6, opt, &final);
@@ -1298,7 +1301,8 @@ static int udp6_ufo_send_check(struct sk_buff *skb)
 	return 0;
 }
 
-static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u32 features)
+static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
+	netdev_features_t features)
 {
 	struct sk_buff *segs = ERR_PTR(-EINVAL);
 	unsigned int mss;
diff --git a/net/ipv6/xfrm6_mode_beet.c b/net/ipv6/xfrm6_mode_beet.c
index 3437d7d..a81ce94 100644
--- a/net/ipv6/xfrm6_mode_beet.c
+++ b/net/ipv6/xfrm6_mode_beet.c
@@ -72,8 +72,8 @@ static int xfrm6_beet_output(struct xfrm_state *x, struct sk_buff *skb)
 		top_iph->nexthdr = IPPROTO_BEETPH;
 	}
 
-	ipv6_addr_copy(&top_iph->saddr, (struct in6_addr *)&x->props.saddr);
-	ipv6_addr_copy(&top_iph->daddr, (struct in6_addr *)&x->id.daddr);
+	top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
+	top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
 	return 0;
 }
 
@@ -99,8 +99,8 @@ static int xfrm6_beet_input(struct xfrm_state *x, struct sk_buff *skb)
 
 	ip6h = ipv6_hdr(skb);
 	ip6h->payload_len = htons(skb->len - size);
-	ipv6_addr_copy(&ip6h->daddr, (struct in6_addr *) &x->sel.daddr.a6);
-	ipv6_addr_copy(&ip6h->saddr, (struct in6_addr *) &x->sel.saddr.a6);
+	ip6h->daddr = *(struct in6_addr *)&x->sel.daddr.a6;
+	ip6h->saddr = *(struct in6_addr *)&x->sel.saddr.a6;
 	err = 0;
 out:
 	return err;
diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c
index 4d6edff..261e6e6 100644
--- a/net/ipv6/xfrm6_mode_tunnel.c
+++ b/net/ipv6/xfrm6_mode_tunnel.c
@@ -55,8 +55,8 @@ static int xfrm6_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
 		dsfield &= ~INET_ECN_MASK;
 	ipv6_change_dsfield(top_iph, 0, dsfield);
 	top_iph->hop_limit = ip6_dst_hoplimit(dst->child);
-	ipv6_addr_copy(&top_iph->saddr, (const struct in6_addr *)&x->props.saddr);
-	ipv6_addr_copy(&top_iph->daddr, (const struct in6_addr *)&x->id.daddr);
+	top_iph->saddr = *(struct in6_addr *)&x->props.saddr;
+	top_iph->daddr = *(struct in6_addr *)&x->id.daddr;
 	return 0;
 }
 
diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index faae417..4eeff89 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -49,7 +49,7 @@ static void xfrm6_local_rxpmtu(struct sk_buff *skb, u32 mtu)
 	struct sock *sk = skb->sk;
 
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
-	ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->daddr);
+	fl6.daddr = ipv6_hdr(skb)->daddr;
 
 	ipv6_local_rxpmtu(sk, &fl6, mtu);
 }
@@ -60,7 +60,7 @@ static void xfrm6_local_error(struct sk_buff *skb, u32 mtu)
 	struct sock *sk = skb->sk;
 
 	fl6.fl6_dport = inet_sk(sk)->inet_dport;
-	ipv6_addr_copy(&fl6.daddr, &ipv6_hdr(skb)->daddr);
+	fl6.daddr = ipv6_hdr(skb)->daddr;
 
 	ipv6_local_error(sk, EMSGSIZE, &fl6, mtu);
 }
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index d879f7e..8ea65e0 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -132,8 +132,8 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse)
 	memset(fl6, 0, sizeof(struct flowi6));
 	fl6->flowi6_mark = skb->mark;
 
-	ipv6_addr_copy(&fl6->daddr, reverse ? &hdr->saddr : &hdr->daddr);
-	ipv6_addr_copy(&fl6->saddr, reverse ? &hdr->daddr : &hdr->saddr);
+	fl6->daddr = reverse ? hdr->saddr : hdr->daddr;
+	fl6->saddr = reverse ? hdr->daddr : hdr->saddr;
 
 	while (nh + offset + 1 < skb->data ||
 	       pskb_may_pull(skb, nh + offset + 1 - skb->data)) {
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index f2d72b8..3f2f7c4 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -27,8 +27,8 @@ __xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl)
 
 	/* Initialize temporary selector matching only
 	 * to current session. */
-	ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl6->daddr);
-	ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl6->saddr);
+	*(struct in6_addr *)&sel->daddr = fl6->daddr;
+	*(struct in6_addr *)&sel->saddr = fl6->saddr;
 	sel->dport = xfrm_flowi_dport(fl, &fl6->uli);
 	sel->dport_mask = htons(0xffff);
 	sel->sport = xfrm_flowi_sport(fl, &fl6->uli);
diff --git a/net/irda/irttp.c b/net/irda/irttp.c
index 32e3bb0..5c93f29 100644
--- a/net/irda/irttp.c
+++ b/net/irda/irttp.c
@@ -1461,14 +1461,12 @@ struct tsap_cb *irttp_dup(struct tsap_cb *orig, void *instance)
 	}
 
 	/* Allocate a new instance */
-	new = kmalloc(sizeof(struct tsap_cb), GFP_ATOMIC);
+	new = kmemdup(orig, sizeof(struct tsap_cb), GFP_ATOMIC);
 	if (!new) {
 		IRDA_DEBUG(0, "%s(), unable to kmalloc\n", __func__);
 		spin_unlock_irqrestore(&irttp->tsaps->hb_spinlock, flags);
 		return NULL;
 	}
-	/* Dup */
-	memcpy(new, orig, sizeof(struct tsap_cb));
 	spin_lock_init(&new->lock);
 
 	/* We don't need the old instance any more */
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 1e733e9..11dbb22 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -375,7 +375,7 @@ static int verify_address_len(const void *p)
 	const struct sadb_address *sp = p;
 	const struct sockaddr *addr = (const struct sockaddr *)(sp + 1);
 	const struct sockaddr_in *sin;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	const struct sockaddr_in6 *sin6;
 #endif
 	int len;
@@ -387,7 +387,7 @@ static int verify_address_len(const void *p)
 		    sp->sadb_address_prefixlen > 32)
 			return -EINVAL;
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		len = DIV_ROUND_UP(sizeof(*sp) + sizeof(*sin6), sizeof(uint64_t));
 		if (sp->sadb_address_len != len ||
@@ -469,7 +469,7 @@ static int present_and_same_family(const struct sadb_address *src,
 	if (s_addr->sa_family != d_addr->sa_family)
 		return 0;
 	if (s_addr->sa_family != AF_INET
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	    && s_addr->sa_family != AF_INET6
 #endif
 		)
@@ -579,7 +579,7 @@ static inline int pfkey_sockaddr_len(sa_family_t family)
 	switch (family) {
 	case AF_INET:
 		return sizeof(struct sockaddr_in);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		return sizeof(struct sockaddr_in6);
 #endif
@@ -595,7 +595,7 @@ int pfkey_sockaddr_extract(const struct sockaddr *sa, xfrm_address_t *xaddr)
 		xaddr->a4 =
 			((struct sockaddr_in *)sa)->sin_addr.s_addr;
 		return AF_INET;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		memcpy(xaddr->a6,
 		       &((struct sockaddr_in6 *)sa)->sin6_addr,
@@ -639,7 +639,7 @@ static struct  xfrm_state *pfkey_xfrm_state_lookup(struct net *net, const struct
 	case AF_INET:
 		xaddr = (xfrm_address_t *)&((const struct sockaddr_in *)(addr + 1))->sin_addr;
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		xaddr = (xfrm_address_t *)&((const struct sockaddr_in6 *)(addr + 1))->sin6_addr;
 		break;
@@ -705,14 +705,14 @@ static unsigned int pfkey_sockaddr_fill(const xfrm_address_t *xaddr, __be16 port
 		memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
 		return 32;
 	    }
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 	    {
 		struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sa;
 		sin6->sin6_family = AF_INET6;
 		sin6->sin6_port = port;
 		sin6->sin6_flowinfo = 0;
-		ipv6_addr_copy(&sin6->sin6_addr, (const struct in6_addr *)xaddr->a6);
+		sin6->sin6_addr = *(struct in6_addr *)xaddr->a6;
 		sin6->sin6_scope_id = 0;
 		return 128;
 	    }
@@ -1311,7 +1311,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_
 		xdaddr = (xfrm_address_t *)&((struct sockaddr_in *)(daddr + 1))->sin_addr.s_addr;
 		xsaddr = (xfrm_address_t *)&((struct sockaddr_in *)(saddr + 1))->sin_addr.s_addr;
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		xdaddr = (xfrm_address_t *)&((struct sockaddr_in6 *)(daddr + 1))->sin6_addr;
 		xsaddr = (xfrm_address_t *)&((struct sockaddr_in6 *)(saddr + 1))->sin6_addr;
@@ -3146,7 +3146,7 @@ static struct xfrm_policy *pfkey_compile_policy(struct sock *sk, int opt,
 			return NULL;
 		}
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		if (opt != IPV6_IPSEC_POLICY) {
 			*dir = -EOPNOTSUPP;
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index bf8d50c..89ff8c6 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -756,9 +756,6 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
 		goto error;
 	}
 
-	/* Point to L2TP header */
-	optr = ptr = skb->data;
-
 	/* Trace packet contents, if enabled */
 	if (tunnel->debug & L2TP_MSG_DATA) {
 		length = min(32u, skb->len);
@@ -769,12 +766,15 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
 
 		offset = 0;
 		do {
-			printk(" %02X", ptr[offset]);
+			printk(" %02X", skb->data[offset]);
 		} while (++offset < length);
 
 		printk("\n");
 	}
 
+	/* Point to L2TP header */
+	optr = ptr = skb->data;
+
 	/* Get L2TP header flags */
 	hdrflags = ntohs(*(__be16 *) ptr);
 
@@ -1072,7 +1072,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 
 	/* Get routing info from the tunnel socket */
 	skb_dst_drop(skb);
-	skb_dst_set(skb, dst_clone(__sk_dst_get(sk)));
+	skb_dst_set(skb, dst_clone(__sk_dst_check(sk, 0)));
 
 	inet = inet_sk(sk);
 	fl = &inet->cork.fl;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 8260b13..d5597b7 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -201,7 +201,6 @@ config NF_CONNTRACK_BROADCAST
 
 config NF_CONNTRACK_NETBIOS_NS
 	tristate "NetBIOS name service protocol support"
-	depends on NETFILTER_ADVANCED
 	select NF_CONNTRACK_BROADCAST
 	help
 	  NetBIOS name service requests are sent as broadcast messages from an
@@ -542,7 +541,6 @@ config NETFILTER_XT_TARGET_NOTRACK
 	tristate  '"NOTRACK" target support'
 	depends on IP_NF_RAW || IP6_NF_RAW
 	depends on NF_CONNTRACK
-	depends on NETFILTER_ADVANCED
 	help
 	  The NOTRACK target allows a select rule to specify
 	  which packets *not* to enter the conntrack/NAT
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index afca6c7..b4e8ff0 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -54,6 +54,12 @@ EXPORT_SYMBOL_GPL(nf_unregister_afinfo);
 
 struct list_head nf_hooks[NFPROTO_NUMPROTO][NF_MAX_HOOKS] __read_mostly;
 EXPORT_SYMBOL(nf_hooks);
+
+#if defined(CONFIG_JUMP_LABEL)
+struct jump_label_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS];
+EXPORT_SYMBOL(nf_hooks_needed);
+#endif
+
 static DEFINE_MUTEX(nf_hook_mutex);
 
 int nf_register_hook(struct nf_hook_ops *reg)
@@ -70,6 +76,9 @@ int nf_register_hook(struct nf_hook_ops *reg)
 	}
 	list_add_rcu(&reg->list, elem->list.prev);
 	mutex_unlock(&nf_hook_mutex);
+#if defined(CONFIG_JUMP_LABEL)
+	jump_label_inc(&nf_hooks_needed[reg->pf][reg->hooknum]);
+#endif
 	return 0;
 }
 EXPORT_SYMBOL(nf_register_hook);
@@ -79,7 +88,9 @@ void nf_unregister_hook(struct nf_hook_ops *reg)
 	mutex_lock(&nf_hook_mutex);
 	list_del_rcu(&reg->list);
 	mutex_unlock(&nf_hook_mutex);
-
+#if defined(CONFIG_JUMP_LABEL)
+	jump_label_dec(&nf_hooks_needed[reg->pf][reg->hooknum]);
+#endif
 	synchronize_net();
 }
 EXPORT_SYMBOL(nf_unregister_hook);
@@ -218,7 +229,7 @@ int skb_make_writable(struct sk_buff *skb, unsigned int writable_len)
 }
 EXPORT_SYMBOL(skb_make_writable);
 
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
 /* This does not belong here, but locally generated errors need it if connection
    tracking in use: without this, connection may not be in hash table, and hence
    manufactured ICMP or RST packets will not be associated with it. */
diff --git a/net/netfilter/ipset/ip_set_getport.c b/net/netfilter/ipset/ip_set_getport.c
index 052579f..1f03556 100644
--- a/net/netfilter/ipset/ip_set_getport.c
+++ b/net/netfilter/ipset/ip_set_getport.c
@@ -109,16 +109,18 @@ ip_set_get_ip4_port(const struct sk_buff *skb, bool src,
 }
 EXPORT_SYMBOL_GPL(ip_set_get_ip4_port);
 
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 bool
 ip_set_get_ip6_port(const struct sk_buff *skb, bool src,
 		    __be16 *port, u8 *proto)
 {
 	int protoff;
 	u8 nexthdr;
+	__be16 frag_off;
 
 	nexthdr = ipv6_hdr(skb)->nexthdr;
-	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr);
+	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
+				   &frag_off);
 	if (protoff < 0)
 		return false;
 
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index f2d576e..4015fca 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -241,7 +241,7 @@ hash_ip6_data_isnull(const struct hash_ip6_elem *elem)
 static inline void
 hash_ip6_data_copy(struct hash_ip6_elem *dst, const struct hash_ip6_elem *src)
 {
-	ipv6_addr_copy(&dst->ip.in6, &src->ip.in6);
+	dst->ip.in6 = src->ip.in6;
 }
 
 static inline void
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index 6ee10f5..37d667e 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -158,7 +158,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[],
 	const struct ip_set_hash *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipport4_elem data = { };
-	u32 ip, ip_to, p = 0, port, port_to;
+	u32 ip, ip_to = 0, p = 0, port, port_to;
 	u32 timeout = h->timeout;
 	bool with_ports = false;
 	int ret;
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index fb90e34..e69e271 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -162,7 +162,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[],
 	const struct ip_set_hash *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipportip4_elem data = { };
-	u32 ip, ip_to, p = 0, port, port_to;
+	u32 ip, ip_to = 0, p = 0, port, port_to;
 	u32 timeout = h->timeout;
 	bool with_ports = false;
 	int ret;
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index deb3e3d..64199b4 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -184,7 +184,7 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 	const struct ip_set_hash *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
 	struct hash_ipportnet4_elem data = { .cidr = HOST_MASK };
-	u32 ip, ip_to, p = 0, port, port_to;
+	u32 ip, ip_to = 0, p = 0, port, port_to;
 	u32 ip2_from = 0, ip2_to, ip2_last, ip2;
 	u32 timeout = h->timeout;
 	bool with_ports = false;
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 60d0165..2898819 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -267,7 +267,7 @@ static inline void
 hash_net6_data_copy(struct hash_net6_elem *dst,
 		    const struct hash_net6_elem *src)
 {
-	ipv6_addr_copy(&dst->ip.in6, &src->ip.in6);
+	dst->ip.in6 = src->ip.in6;
 	dst->cidr = src->cidr;
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 093cc32..611c335 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -983,7 +983,7 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
 	if (!cp)
 		return NF_ACCEPT;
 
-	ipv6_addr_copy(&snet.in6, &iph->saddr);
+	snet.in6 = iph->saddr;
 	return handle_response_icmp(AF_INET6, skb, &snet, cih->nexthdr, cp,
 				    pp, offset, sizeof(struct ipv6hdr));
 }
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 3cdd479..bcf5563 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -603,9 +603,9 @@ sloop:
 #ifdef CONFIG_IP_VS_IPV6
 	if (cp->af == AF_INET6) {
 		p += sizeof(struct ip_vs_sync_v6);
-		ipv6_addr_copy(&s->v6.caddr, &cp->caddr.in6);
-		ipv6_addr_copy(&s->v6.vaddr, &cp->vaddr.in6);
-		ipv6_addr_copy(&s->v6.daddr, &cp->daddr.in6);
+		s->v6.caddr = cp->caddr.in6;
+		s->v6.vaddr = cp->vaddr.in6;
+		s->v6.daddr = cp->daddr.in6;
 	} else
 #endif
 	{
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index aa2d720..72b82b8 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -235,7 +235,7 @@ __ip_vs_route_output_v6(struct net *net, struct in6_addr *daddr,
 			goto out_err;
 		}
 	}
-	ipv6_addr_copy(ret_saddr, &fl6.saddr);
+	*ret_saddr = fl6.saddr;
 	return dst;
 
 out_err:
@@ -279,7 +279,7 @@ __ip_vs_get_out_rt_v6(struct sk_buff *skb, struct ip_vs_dest *dest,
 				  atomic_read(&rt->dst.__refcnt));
 		}
 		if (ret_saddr)
-			ipv6_addr_copy(ret_saddr, &dest->dst_saddr.in6);
+			*ret_saddr = dest->dst_saddr.in6;
 		spin_unlock(&dest->dst_lock);
 	} else {
 		dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm);
@@ -541,7 +541,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	 * Avoid duplicate tuple in reply direction for NAT traffic
 	 * to local address when connection is sync-ed
 	 */
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	if (cp->flags & IP_VS_CONN_F_SYNC && local) {
 		enum ip_conntrack_info ctinfo;
 		struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
@@ -658,7 +658,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	 * Avoid duplicate tuple in reply direction for NAT traffic
 	 * to local address when connection is sync-ed
 	 */
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	if (cp->flags & IP_VS_CONN_F_SYNC && local) {
 		enum ip_conntrack_info ctinfo;
 		struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
@@ -705,7 +705,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	/* mangle the packet */
 	if (pp->dnat_handler && !pp->dnat_handler(skb, pp, cp))
 		goto tx_error;
-	ipv6_addr_copy(&ipv6_hdr(skb)->daddr, &cp->daddr.in6);
+	ipv6_hdr(skb)->daddr = cp->daddr.in6;
 
 	if (!local || !skb->dev) {
 		/* drop the old route when skb is not shared */
@@ -967,8 +967,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	be16_add_cpu(&iph->payload_len, sizeof(*old_iph));
 	iph->priority		=	old_iph->priority;
 	memset(&iph->flow_lbl, 0, sizeof(iph->flow_lbl));
-	ipv6_addr_copy(&iph->daddr, &cp->daddr.in6);
-	ipv6_addr_copy(&iph->saddr, &saddr);
+	iph->daddr = cp->daddr.in6;
+	iph->saddr = saddr;
 	iph->hop_limit		=	old_iph->hop_limit;
 
 	/* Another hack: avoid icmp_send in ip_fragment */
@@ -1173,7 +1173,7 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	 * Avoid duplicate tuple in reply direction for NAT traffic
 	 * to local address when connection is sync-ed
 	 */
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	if (cp->flags & IP_VS_CONN_F_SYNC && local) {
 		enum ip_conntrack_info ctinfo;
 		struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
@@ -1293,7 +1293,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp,
 	 * Avoid duplicate tuple in reply direction for NAT traffic
 	 * to local address when connection is sync-ed
 	 */
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
 	if (cp->flags & IP_VS_CONN_F_SYNC && local) {
 		enum ip_conntrack_info ctinfo;
 		struct nf_conn *ct = ct = nf_ct_get(skb, &ctinfo);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 7202b06..32279dc 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1087,7 +1087,7 @@ static struct nf_ct_ext_type nf_ct_zone_extend __read_mostly = {
 };
 #endif
 
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/nfnetlink_conntrack.h>
diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c
index 6b368be..b62c414 100644
--- a/net/netfilter/nf_conntrack_ecache.c
+++ b/net/netfilter/nf_conntrack_ecache.c
@@ -27,22 +27,17 @@
 
 static DEFINE_MUTEX(nf_ct_ecache_mutex);
 
-struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb __read_mostly;
-EXPORT_SYMBOL_GPL(nf_conntrack_event_cb);
-
-struct nf_exp_event_notifier __rcu *nf_expect_event_cb __read_mostly;
-EXPORT_SYMBOL_GPL(nf_expect_event_cb);
-
 /* deliver cached events and clear cache entry - must be called with locally
  * disabled softirqs */
 void nf_ct_deliver_cached_events(struct nf_conn *ct)
 {
+	struct net *net = nf_ct_net(ct);
 	unsigned long events;
 	struct nf_ct_event_notifier *notify;
 	struct nf_conntrack_ecache *e;
 
 	rcu_read_lock();
-	notify = rcu_dereference(nf_conntrack_event_cb);
+	notify = rcu_dereference(net->ct.nf_conntrack_event_cb);
 	if (notify == NULL)
 		goto out_unlock;
 
@@ -83,19 +78,20 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(nf_ct_deliver_cached_events);
 
-int nf_conntrack_register_notifier(struct nf_ct_event_notifier *new)
+int nf_conntrack_register_notifier(struct net *net,
+				   struct nf_ct_event_notifier *new)
 {
 	int ret = 0;
 	struct nf_ct_event_notifier *notify;
 
 	mutex_lock(&nf_ct_ecache_mutex);
-	notify = rcu_dereference_protected(nf_conntrack_event_cb,
+	notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb,
 					   lockdep_is_held(&nf_ct_ecache_mutex));
 	if (notify != NULL) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
-	RCU_INIT_POINTER(nf_conntrack_event_cb, new);
+	RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, new);
 	mutex_unlock(&nf_ct_ecache_mutex);
 	return ret;
 
@@ -105,32 +101,34 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_register_notifier);
 
-void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *new)
+void nf_conntrack_unregister_notifier(struct net *net,
+				      struct nf_ct_event_notifier *new)
 {
 	struct nf_ct_event_notifier *notify;
 
 	mutex_lock(&nf_ct_ecache_mutex);
-	notify = rcu_dereference_protected(nf_conntrack_event_cb,
+	notify = rcu_dereference_protected(net->ct.nf_conntrack_event_cb,
 					   lockdep_is_held(&nf_ct_ecache_mutex));
 	BUG_ON(notify != new);
-	RCU_INIT_POINTER(nf_conntrack_event_cb, NULL);
+	RCU_INIT_POINTER(net->ct.nf_conntrack_event_cb, NULL);
 	mutex_unlock(&nf_ct_ecache_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier);
 
-int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *new)
+int nf_ct_expect_register_notifier(struct net *net,
+				   struct nf_exp_event_notifier *new)
 {
 	int ret = 0;
 	struct nf_exp_event_notifier *notify;
 
 	mutex_lock(&nf_ct_ecache_mutex);
-	notify = rcu_dereference_protected(nf_expect_event_cb,
+	notify = rcu_dereference_protected(net->ct.nf_expect_event_cb,
 					   lockdep_is_held(&nf_ct_ecache_mutex));
 	if (notify != NULL) {
 		ret = -EBUSY;
 		goto out_unlock;
 	}
-	RCU_INIT_POINTER(nf_expect_event_cb, new);
+	RCU_INIT_POINTER(net->ct.nf_expect_event_cb, new);
 	mutex_unlock(&nf_ct_ecache_mutex);
 	return ret;
 
@@ -140,15 +138,16 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(nf_ct_expect_register_notifier);
 
-void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *new)
+void nf_ct_expect_unregister_notifier(struct net *net,
+				      struct nf_exp_event_notifier *new)
 {
 	struct nf_exp_event_notifier *notify;
 
 	mutex_lock(&nf_ct_ecache_mutex);
-	notify = rcu_dereference_protected(nf_expect_event_cb,
+	notify = rcu_dereference_protected(net->ct.nf_expect_event_cb,
 					   lockdep_is_held(&nf_ct_ecache_mutex));
 	BUG_ON(notify != new);
-	RCU_INIT_POINTER(nf_expect_event_cb, NULL);
+	RCU_INIT_POINTER(net->ct.nf_expect_event_cb, NULL);
 	mutex_unlock(&nf_ct_ecache_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier);
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index f03c2d4..813ad39 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -743,17 +743,16 @@ static int callforward_do_filter(const union nf_inet_addr *src,
 		}
 		break;
 	}
-#if defined(CONFIG_NF_CONNTRACK_IPV6) || \
-    defined(CONFIG_NF_CONNTRACK_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6)
 	case AF_INET6: {
 		struct flowi6 fl1, fl2;
 		struct rt6_info *rt1, *rt2;
 
 		memset(&fl1, 0, sizeof(fl1));
-		ipv6_addr_copy(&fl1.daddr, &src->in6);
+		fl1.daddr = src->in6;
 
 		memset(&fl2, 0, sizeof(fl2));
-		ipv6_addr_copy(&fl2.daddr, &dst->in6);
+		fl2.daddr = dst->in6;
 		if (!afinfo->route(&init_net, (struct dst_entry **)&rt1,
 				   flowi6_to_flowi(&fl1), false)) {
 			if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index e58aa9b..ef21b22 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -4,7 +4,7 @@
  * (C) 2001 by Jay Schulist <jschlst@samba.org>
  * (C) 2002-2006 by Harald Welte <laforge@gnumonks.org>
  * (C) 2003 by Patrick Mchardy <kaber@trash.net>
- * (C) 2005-2008 by Pablo Neira Ayuso <pablo@netfilter.org>
+ * (C) 2005-2011 by Pablo Neira Ayuso <pablo@netfilter.org>
  *
  * Initial connection tracking via netlink development funded and
  * generally made possible by Network Robots, Inc. (www.networkrobots.com)
@@ -2163,6 +2163,54 @@ MODULE_ALIAS("ip_conntrack_netlink");
 MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK);
 MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_CTNETLINK_EXP);
 
+static int __net_init ctnetlink_net_init(struct net *net)
+{
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+	int ret;
+
+	ret = nf_conntrack_register_notifier(net, &ctnl_notifier);
+	if (ret < 0) {
+		pr_err("ctnetlink_init: cannot register notifier.\n");
+		goto err_out;
+	}
+
+	ret = nf_ct_expect_register_notifier(net, &ctnl_notifier_exp);
+	if (ret < 0) {
+		pr_err("ctnetlink_init: cannot expect register notifier.\n");
+		goto err_unreg_notifier;
+	}
+#endif
+	return 0;
+
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+err_unreg_notifier:
+	nf_conntrack_unregister_notifier(net, &ctnl_notifier);
+err_out:
+	return ret;
+#endif
+}
+
+static void ctnetlink_net_exit(struct net *net)
+{
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+	nf_ct_expect_unregister_notifier(net, &ctnl_notifier_exp);
+	nf_conntrack_unregister_notifier(net, &ctnl_notifier);
+#endif
+}
+
+static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list)
+{
+	struct net *net;
+
+	list_for_each_entry(net, net_exit_list, exit_list)
+		ctnetlink_net_exit(net);
+}
+
+static struct pernet_operations ctnetlink_net_ops = {
+	.init		= ctnetlink_net_init,
+	.exit_batch	= ctnetlink_net_exit_batch,
+};
+
 static int __init ctnetlink_init(void)
 {
 	int ret;
@@ -2180,28 +2228,15 @@ static int __init ctnetlink_init(void)
 		goto err_unreg_subsys;
 	}
 
-#ifdef CONFIG_NF_CONNTRACK_EVENTS
-	ret = nf_conntrack_register_notifier(&ctnl_notifier);
-	if (ret < 0) {
-		pr_err("ctnetlink_init: cannot register notifier.\n");
+	if (register_pernet_subsys(&ctnetlink_net_ops)) {
+		pr_err("ctnetlink_init: cannot register pernet operations\n");
 		goto err_unreg_exp_subsys;
 	}
 
-	ret = nf_ct_expect_register_notifier(&ctnl_notifier_exp);
-	if (ret < 0) {
-		pr_err("ctnetlink_init: cannot expect register notifier.\n");
-		goto err_unreg_notifier;
-	}
-#endif
-
 	return 0;
 
-#ifdef CONFIG_NF_CONNTRACK_EVENTS
-err_unreg_notifier:
-	nf_conntrack_unregister_notifier(&ctnl_notifier);
 err_unreg_exp_subsys:
 	nfnetlink_subsys_unregister(&ctnl_exp_subsys);
-#endif
 err_unreg_subsys:
 	nfnetlink_subsys_unregister(&ctnl_subsys);
 err_out:
@@ -2213,11 +2248,7 @@ static void __exit ctnetlink_exit(void)
 	pr_info("ctnetlink: unregistering from nfnetlink.\n");
 
 	nf_ct_remove_userspace_expectations();
-#ifdef CONFIG_NF_CONNTRACK_EVENTS
-	nf_ct_expect_unregister_notifier(&ctnl_notifier_exp);
-	nf_conntrack_unregister_notifier(&ctnl_notifier);
-#endif
-
+	unregister_pernet_subsys(&ctnetlink_net_ops);
 	nfnetlink_subsys_unregister(&ctnl_exp_subsys);
 	nfnetlink_subsys_unregister(&ctnl_subsys);
 }
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index 2e664a6..d6dde6d 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -629,7 +629,7 @@ static int dccp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 	return seq_printf(s, "%s ", dccp_state_names[ct->proto.dccp.state]);
 }
 
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
 			  struct nf_conn *ct)
 {
@@ -770,7 +770,7 @@ static struct nf_conntrack_l4proto dccp_proto4 __read_mostly = {
 	.error			= dccp_error,
 	.print_tuple		= dccp_print_tuple,
 	.print_conntrack	= dccp_print_conntrack,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.to_nlattr		= dccp_to_nlattr,
 	.nlattr_size		= dccp_nlattr_size,
 	.from_nlattr		= nlattr_to_dccp,
@@ -792,7 +792,7 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = {
 	.error			= dccp_error,
 	.print_tuple		= dccp_print_tuple,
 	.print_conntrack	= dccp_print_conntrack,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.to_nlattr		= dccp_to_nlattr,
 	.nlattr_size		= dccp_nlattr_size,
 	.from_nlattr		= nlattr_to_dccp,
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index d69facd..f033879 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -291,7 +291,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = {
 	.new		 = gre_new,
 	.destroy	 = gre_destroy,
 	.me 		 = THIS_MODULE,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.tuple_to_nlattr = nf_ct_port_tuple_to_nlattr,
 	.nlattr_tuple_size = nf_ct_port_nlattr_tuple_size,
 	.nlattr_to_tuple = nf_ct_port_nlattr_to_tuple,
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 6772b11..afa6913 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -461,7 +461,7 @@ static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb,
 	return true;
 }
 
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/nfnetlink_conntrack.h>
@@ -666,7 +666,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = {
 	.packet 		= sctp_packet,
 	.new 			= sctp_new,
 	.me 			= THIS_MODULE,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.to_nlattr		= sctp_to_nlattr,
 	.nlattr_size		= sctp_nlattr_size,
 	.from_nlattr		= nlattr_to_sctp,
@@ -696,7 +696,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = {
 	.packet 		= sctp_packet,
 	.new 			= sctp_new,
 	.me 			= THIS_MODULE,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.to_nlattr		= sctp_to_nlattr,
 	.nlattr_size		= sctp_nlattr_size,
 	.from_nlattr		= nlattr_to_sctp,
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 8235b86..97b9f3e 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -1126,7 +1126,7 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
 	return true;
 }
 
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/nfnetlink_conntrack.h>
@@ -1447,7 +1447,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly =
 	.packet 		= tcp_packet,
 	.new 			= tcp_new,
 	.error			= tcp_error,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.to_nlattr		= tcp_to_nlattr,
 	.nlattr_size		= tcp_nlattr_size,
 	.from_nlattr		= nlattr_to_tcp,
@@ -1479,7 +1479,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 __read_mostly =
 	.packet 		= tcp_packet,
 	.new 			= tcp_new,
 	.error			= tcp_error,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.to_nlattr		= tcp_to_nlattr,
 	.nlattr_size		= tcp_nlattr_size,
 	.from_nlattr		= nlattr_to_tcp,
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index 8289088..5f35757 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -188,7 +188,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 __read_mostly =
 	.packet			= udp_packet,
 	.new			= udp_new,
 	.error			= udp_error,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.tuple_to_nlattr	= nf_ct_port_tuple_to_nlattr,
 	.nlattr_to_tuple	= nf_ct_port_nlattr_to_tuple,
 	.nlattr_tuple_size	= nf_ct_port_nlattr_tuple_size,
@@ -216,7 +216,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 __read_mostly =
 	.packet			= udp_packet,
 	.new			= udp_new,
 	.error			= udp_error,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.tuple_to_nlattr	= nf_ct_port_tuple_to_nlattr,
 	.nlattr_to_tuple	= nf_ct_port_nlattr_to_tuple,
 	.nlattr_tuple_size	= nf_ct_port_nlattr_tuple_size,
diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c
index 263b5a7..f52ca11 100644
--- a/net/netfilter/nf_conntrack_proto_udplite.c
+++ b/net/netfilter/nf_conntrack_proto_udplite.c
@@ -174,7 +174,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 __read_mostly =
 	.packet			= udplite_packet,
 	.new			= udplite_new,
 	.error			= udplite_error,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.tuple_to_nlattr	= nf_ct_port_tuple_to_nlattr,
 	.nlattr_tuple_size	= nf_ct_port_nlattr_tuple_size,
 	.nlattr_to_tuple	= nf_ct_port_nlattr_to_tuple,
@@ -198,7 +198,7 @@ static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly =
 	.packet			= udplite_packet,
 	.new			= udplite_new,
 	.error			= udplite_error,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 	.tuple_to_nlattr	= nf_ct_port_tuple_to_nlattr,
 	.nlattr_tuple_size	= nf_ct_port_nlattr_tuple_size,
 	.nlattr_to_tuple	= nf_ct_port_nlattr_to_tuple,
diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c
index 4bca15a..ba92824 100644
--- a/net/netfilter/xt_AUDIT.c
+++ b/net/netfilter/xt_AUDIT.c
@@ -98,6 +98,7 @@ static void audit_ip6(struct audit_buffer *ab, struct sk_buff *skb)
 	struct ipv6hdr _ip6h;
 	const struct ipv6hdr *ih;
 	u8 nexthdr;
+	__be16 frag_off;
 	int offset;
 
 	ih = skb_header_pointer(skb, skb_network_offset(skb), sizeof(_ip6h), &_ip6h);
@@ -108,7 +109,7 @@ static void audit_ip6(struct audit_buffer *ab, struct sk_buff *skb)
 
 	nexthdr = ih->nexthdr;
 	offset = ipv6_skip_exthdr(skb, skb_network_offset(skb) + sizeof(_ip6h),
-				  &nexthdr);
+				  &nexthdr, &frag_off);
 
 	audit_log_format(ab, " saddr=%pI6c daddr=%pI6c proto=%hhu",
 			 &ih->saddr, &ih->daddr, nexthdr);
diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c
index d4f4b5d..95237c8 100644
--- a/net/netfilter/xt_NFQUEUE.c
+++ b/net/netfilter/xt_NFQUEUE.c
@@ -49,7 +49,7 @@ static u32 hash_v4(const struct sk_buff *skb)
 	return jhash_2words((__force u32)ipaddr, iph->protocol, jhash_initval);
 }
 
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 static u32 hash_v6(const struct sk_buff *skb)
 {
 	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
@@ -74,7 +74,7 @@ nfqueue_tg_v1(struct sk_buff *skb, const struct xt_action_param *par)
 		if (par->family == NFPROTO_IPV4)
 			queue = (((u64) hash_v4(skb) * info->queues_total) >>
 				 32) + queue;
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 		else if (par->family == NFPROTO_IPV6)
 			queue = (((u64) hash_v6(skb) * info->queues_total) >>
 				 32) + queue;
diff --git a/net/netfilter/xt_TCPMSS.c b/net/netfilter/xt_TCPMSS.c
index 9e63b43..190ad37 100644
--- a/net/netfilter/xt_TCPMSS.c
+++ b/net/netfilter/xt_TCPMSS.c
@@ -161,7 +161,7 @@ static u_int32_t tcpmss_reverse_mtu(const struct sk_buff *skb,
 		struct flowi6 *fl6 = &fl.u.ip6;
 
 		memset(fl6, 0, sizeof(*fl6));
-		ipv6_addr_copy(&fl6->daddr, &ipv6_hdr(skb)->saddr);
+		fl6->daddr = ipv6_hdr(skb)->saddr;
 	}
 	rcu_read_lock();
 	ai = nf_get_afinfo(family);
@@ -198,17 +198,18 @@ tcpmss_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 	return XT_CONTINUE;
 }
 
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 static unsigned int
 tcpmss_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	u8 nexthdr;
+	__be16 frag_off;
 	int tcphoff;
 	int ret;
 
 	nexthdr = ipv6h->nexthdr;
-	tcphoff = ipv6_skip_exthdr(skb, sizeof(*ipv6h), &nexthdr);
+	tcphoff = ipv6_skip_exthdr(skb, sizeof(*ipv6h), &nexthdr, &frag_off);
 	if (tcphoff < 0)
 		return NF_DROP;
 	ret = tcpmss_mangle_packet(skb, par->targinfo,
@@ -259,7 +260,7 @@ static int tcpmss_tg4_check(const struct xt_tgchk_param *par)
 	return -EINVAL;
 }
 
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 static int tcpmss_tg6_check(const struct xt_tgchk_param *par)
 {
 	const struct xt_tcpmss_info *info = par->targinfo;
@@ -292,7 +293,7 @@ static struct xt_target tcpmss_tg_reg[] __read_mostly = {
 		.proto		= IPPROTO_TCP,
 		.me		= THIS_MODULE,
 	},
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	{
 		.family		= NFPROTO_IPV6,
 		.name		= "TCPMSS",
diff --git a/net/netfilter/xt_TCPOPTSTRIP.c b/net/netfilter/xt_TCPOPTSTRIP.c
index 9dc9ecf..25fd1c4 100644
--- a/net/netfilter/xt_TCPOPTSTRIP.c
+++ b/net/netfilter/xt_TCPOPTSTRIP.c
@@ -80,16 +80,17 @@ tcpoptstrip_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 	       sizeof(struct iphdr) + sizeof(struct tcphdr));
 }
 
-#if defined(CONFIG_IP6_NF_MANGLE) || defined(CONFIG_IP6_NF_MANGLE_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_MANGLE)
 static unsigned int
 tcpoptstrip_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	struct ipv6hdr *ipv6h = ipv6_hdr(skb);
 	int tcphoff;
 	u_int8_t nexthdr;
+	__be16 frag_off;
 
 	nexthdr = ipv6h->nexthdr;
-	tcphoff = ipv6_skip_exthdr(skb, sizeof(*ipv6h), &nexthdr);
+	tcphoff = ipv6_skip_exthdr(skb, sizeof(*ipv6h), &nexthdr, &frag_off);
 	if (tcphoff < 0)
 		return NF_DROP;
 
@@ -108,7 +109,7 @@ static struct xt_target tcpoptstrip_tg_reg[] __read_mostly = {
 		.targetsize = sizeof(struct xt_tcpoptstrip_target_info),
 		.me         = THIS_MODULE,
 	},
-#if defined(CONFIG_IP6_NF_MANGLE) || defined(CONFIG_IP6_NF_MANGLE_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_MANGLE)
 	{
 		.name       = "TCPOPTSTRIP",
 		.family     = NFPROTO_IPV6,
diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c
index 5f054a0..3aae66f 100644
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -25,13 +25,10 @@
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter/xt_TEE.h>
 
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #	define WITH_CONNTRACK 1
 #	include <net/netfilter/nf_conntrack.h>
 #endif
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-#	define WITH_IPV6 1
-#endif
 
 struct xt_tee_priv {
 	struct notifier_block	notifier;
@@ -136,7 +133,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 	return XT_CONTINUE;
 }
 
-#ifdef WITH_IPV6
+#if IS_ENABLED(CONFIG_IPV6)
 static bool
 tee_tg_route6(struct sk_buff *skb, const struct xt_tee_tginfo *info)
 {
@@ -196,7 +193,7 @@ tee_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 	}
 	return XT_CONTINUE;
 }
-#endif /* WITH_IPV6 */
+#endif
 
 static int tee_netdev_event(struct notifier_block *this, unsigned long event,
 			    void *ptr)
@@ -276,7 +273,7 @@ static struct xt_target tee_tg_reg[] __read_mostly = {
 		.destroy    = tee_tg_destroy,
 		.me         = THIS_MODULE,
 	},
-#ifdef WITH_IPV6
+#if IS_ENABLED(CONFIG_IPV6)
 	{
 		.name       = "TEE",
 		.revision   = 1,
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index dcfd57e..35a959a 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -22,7 +22,7 @@
 
 #include <net/netfilter/ipv4/nf_defrag_ipv4.h>
 
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 #define XT_TPROXY_HAVE_IPV6 1
 #include <net/if_inet6.h>
 #include <net/addrconf.h>
diff --git a/net/netfilter/xt_addrtype.c b/net/netfilter/xt_addrtype.c
index b77d383..49c5ff7 100644
--- a/net/netfilter/xt_addrtype.c
+++ b/net/netfilter/xt_addrtype.c
@@ -16,7 +16,7 @@
 #include <linux/ip.h>
 #include <net/route.h>
 
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
 #include <net/ip6_fib.h>
@@ -31,7 +31,7 @@ MODULE_DESCRIPTION("Xtables: address type match");
 MODULE_ALIAS("ipt_addrtype");
 MODULE_ALIAS("ip6t_addrtype");
 
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 static u32 match_lookup_rt6(struct net *net, const struct net_device *dev,
 			    const struct in6_addr *addr)
 {
@@ -42,7 +42,7 @@ static u32 match_lookup_rt6(struct net *net, const struct net_device *dev,
 	int route_err;
 
 	memset(&flow, 0, sizeof(flow));
-	ipv6_addr_copy(&flow.daddr, addr);
+	flow.daddr = *addr;
 	if (dev)
 		flow.flowi6_oif = dev->ifindex;
 
@@ -149,7 +149,7 @@ addrtype_mt_v1(const struct sk_buff *skb, struct xt_action_param *par)
 	else if (info->flags & XT_ADDRTYPE_LIMIT_IFACE_OUT)
 		dev = par->out;
 
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	if (par->family == NFPROTO_IPV6)
 		return addrtype_mt6(net, dev, skb, info);
 #endif
@@ -190,7 +190,7 @@ static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par)
 		return -EINVAL;
 	}
 
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	if (par->family == NFPROTO_IPV6) {
 		if ((info->source | info->dest) & XT_ADDRTYPE_BLACKHOLE) {
 			pr_err("ipv6 BLACKHOLE matching not supported\n");
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index dfd52ba..8e49921 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -21,7 +21,7 @@
 #include <linux/mm.h>
 #include <linux/in.h>
 #include <linux/ip.h>
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 #include <linux/ipv6.h>
 #include <net/ipv6.h>
 #endif
@@ -64,7 +64,7 @@ struct dsthash_dst {
 			__be32 src;
 			__be32 dst;
 		} ip;
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 		struct {
 			__be32 src[4];
 			__be32 dst[4];
@@ -413,7 +413,7 @@ static inline __be32 maskl(__be32 a, unsigned int l)
 	return l ? htonl(ntohl(a) & ~0 << (32 - l)) : 0;
 }
 
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 static void hashlimit_ipv6_mask(__be32 *i, unsigned int p)
 {
 	switch (p) {
@@ -445,6 +445,7 @@ hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo,
 {
 	__be16 _ports[2], *ports;
 	u8 nexthdr;
+	__be16 frag_off;
 	int poff;
 
 	memset(dst, 0, sizeof(*dst));
@@ -463,7 +464,7 @@ hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo,
 			return 0;
 		nexthdr = ip_hdr(skb)->protocol;
 		break;
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	case NFPROTO_IPV6:
 		if (hinfo->cfg.mode & XT_HASHLIMIT_HASH_DIP) {
 			memcpy(&dst->ip6.dst, &ipv6_hdr(skb)->daddr,
@@ -480,7 +481,7 @@ hashlimit_init_dst(const struct xt_hashlimit_htable *hinfo,
 		      (XT_HASHLIMIT_HASH_DPT | XT_HASHLIMIT_HASH_SPT)))
 			return 0;
 		nexthdr = ipv6_hdr(skb)->nexthdr;
-		protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr);
+		protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, &frag_off);
 		if ((int)protoff < 0)
 			return -1;
 		break;
@@ -615,7 +616,7 @@ static struct xt_match hashlimit_mt_reg[] __read_mostly = {
 		.destroy        = hashlimit_mt_destroy,
 		.me             = THIS_MODULE,
 	},
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	{
 		.name           = "hashlimit",
 		.revision       = 1,
@@ -692,7 +693,7 @@ static int dl_seq_real_show(struct dsthash_ent *ent, u_int8_t family,
 				 ent->rateinfo.credit, ent->rateinfo.credit_cap,
 				 ent->rateinfo.cost);
 		break;
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	case NFPROTO_IPV6:
 		res = seq_printf(s, "%ld %pI6:%u->%pI6:%u %u %u %u\n",
 				 (long)(ent->expires - jiffies)/HZ,
@@ -760,7 +761,7 @@ static int __net_init hashlimit_proc_net_init(struct net *net)
 	hashlimit_net->ipt_hashlimit = proc_mkdir("ipt_hashlimit", net->proc_net);
 	if (!hashlimit_net->ipt_hashlimit)
 		return -ENOMEM;
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	hashlimit_net->ip6t_hashlimit = proc_mkdir("ip6t_hashlimit", net->proc_net);
 	if (!hashlimit_net->ip6t_hashlimit) {
 		proc_net_remove(net, "ipt_hashlimit");
@@ -773,7 +774,7 @@ static int __net_init hashlimit_proc_net_init(struct net *net)
 static void __net_exit hashlimit_proc_net_exit(struct net *net)
 {
 	proc_net_remove(net, "ipt_hashlimit");
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	proc_net_remove(net, "ip6t_hashlimit");
 #endif
 }
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index fe39f7e..72bb07f 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -22,7 +22,7 @@
 #include <net/netfilter/nf_tproxy_core.h>
 #include <net/netfilter/ipv4/nf_defrag_ipv4.h>
 
-#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 #define XT_SOCKET_HAVE_IPV6 1
 #include <linux/netfilter_ipv6/ip6_tables.h>
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
@@ -30,7 +30,7 @@
 
 #include <linux/netfilter/xt_socket.h>
 
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #define XT_SOCKET_HAVE_CONNTRACK 1
 #include <net/netfilter/nf_conntrack.h>
 #endif
@@ -214,6 +214,7 @@ extract_icmp6_fields(const struct sk_buff *skb,
 	struct icmp6hdr *icmph, _icmph;
 	__be16 *ports, _ports[2];
 	u8 inside_nexthdr;
+	__be16 inside_fragoff;
 	int inside_hdrlen;
 
 	icmph = skb_header_pointer(skb, outside_hdrlen,
@@ -229,7 +230,8 @@ extract_icmp6_fields(const struct sk_buff *skb,
 		return 1;
 	inside_nexthdr = inside_iph->nexthdr;
 
-	inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) + sizeof(_inside_iph), &inside_nexthdr);
+	inside_hdrlen = ipv6_skip_exthdr(skb, outside_hdrlen + sizeof(_icmph) + sizeof(_inside_iph),
+					 &inside_nexthdr, &inside_fragoff);
 	if (inside_hdrlen < 0)
 		return 1; /* hjm: Packet has no/incomplete transport layer headers. */
 
diff --git a/net/netlabel/netlabel_addrlist.c b/net/netlabel/netlabel_addrlist.c
index 96b749d..6f17013 100644
--- a/net/netlabel/netlabel_addrlist.c
+++ b/net/netlabel/netlabel_addrlist.c
@@ -96,7 +96,7 @@ struct netlbl_af4list *netlbl_af4list_search_exact(__be32 addr,
 }
 
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 /**
  * netlbl_af6list_search - Search for a matching IPv6 address entry
  * @addr: IPv6 address
@@ -185,7 +185,7 @@ int netlbl_af4list_add(struct netlbl_af4list *entry, struct list_head *head)
 	return 0;
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 /**
  * netlbl_af6list_add - Add a new IPv6 address entry to a list
  * @entry: address entry
@@ -263,7 +263,7 @@ struct netlbl_af4list *netlbl_af4list_remove(__be32 addr, __be32 mask,
 	return entry;
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 /**
  * netlbl_af6list_remove_entry - Remove an IPv6 address entry
  * @entry: address entry
@@ -342,7 +342,7 @@ void netlbl_af4list_audit_addr(struct audit_buffer *audit_buf,
 	}
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 /**
  * netlbl_af6list_audit_addr - Audit an IPv6 address
  * @audit_buf: audit buffer
diff --git a/net/netlabel/netlabel_addrlist.h b/net/netlabel/netlabel_addrlist.h
index fdbc1d2..a1287ce 100644
--- a/net/netlabel/netlabel_addrlist.h
+++ b/net/netlabel/netlabel_addrlist.h
@@ -133,7 +133,7 @@ static inline void netlbl_af4list_audit_addr(struct audit_buffer *audit_buf,
 }
 #endif
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 
 #define __af6list_entry(ptr) container_of(ptr, struct netlbl_af6list, list)
 
diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c
index 3f905e5..3820411 100644
--- a/net/netlabel/netlabel_domainhash.c
+++ b/net/netlabel/netlabel_domainhash.c
@@ -78,7 +78,7 @@ static void netlbl_domhsh_free_entry(struct rcu_head *entry)
 	struct netlbl_dom_map *ptr;
 	struct netlbl_af4list *iter4;
 	struct netlbl_af4list *tmp4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct netlbl_af6list *iter6;
 	struct netlbl_af6list *tmp6;
 #endif /* IPv6 */
@@ -90,7 +90,7 @@ static void netlbl_domhsh_free_entry(struct rcu_head *entry)
 			netlbl_af4list_remove_entry(iter4);
 			kfree(netlbl_domhsh_addr4_entry(iter4));
 		}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		netlbl_af6list_foreach_safe(iter6, tmp6,
 					    &ptr->type_def.addrsel->list6) {
 			netlbl_af6list_remove_entry(iter6);
@@ -217,7 +217,7 @@ static void netlbl_domhsh_audit_add(struct netlbl_dom_map *entry,
 			cipsov4 = map4->type_def.cipsov4;
 			netlbl_af4list_audit_addr(audit_buf, 0, NULL,
 						  addr4->addr, addr4->mask);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		} else if (addr6 != NULL) {
 			struct netlbl_domaddr6_map *map6;
 			map6 = netlbl_domhsh_addr6_entry(addr6);
@@ -306,7 +306,7 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry,
 	struct netlbl_dom_map *entry_old;
 	struct netlbl_af4list *iter4;
 	struct netlbl_af4list *tmp4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct netlbl_af6list *iter6;
 	struct netlbl_af6list *tmp6;
 #endif /* IPv6 */
@@ -338,7 +338,7 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry,
 					       &entry->type_def.addrsel->list4)
 				netlbl_domhsh_audit_add(entry, iter4, NULL,
 							ret_val, audit_info);
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 			netlbl_af6list_foreach_rcu(iter6,
 					       &entry->type_def.addrsel->list6)
 				netlbl_domhsh_audit_add(entry, NULL, iter6,
@@ -365,7 +365,7 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry,
 				ret_val = -EEXIST;
 				goto add_return;
 			}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		netlbl_af6list_foreach_rcu(iter6,
 					   &entry->type_def.addrsel->list6)
 			if (netlbl_af6list_search_exact(&iter6->addr,
@@ -386,7 +386,7 @@ int netlbl_domhsh_add(struct netlbl_dom_map *entry,
 			if (ret_val != 0)
 				goto add_return;
 		}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		netlbl_af6list_foreach_safe(iter6, tmp6,
 					    &entry->type_def.addrsel->list6) {
 			netlbl_af6list_remove_entry(iter6);
@@ -510,7 +510,7 @@ int netlbl_domhsh_remove_af4(const char *domain,
 	struct netlbl_dom_map *entry_map;
 	struct netlbl_af4list *entry_addr;
 	struct netlbl_af4list *iter4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct netlbl_af6list *iter6;
 #endif /* IPv6 */
 	struct netlbl_domaddr4_map *entry;
@@ -533,7 +533,7 @@ int netlbl_domhsh_remove_af4(const char *domain,
 		goto remove_af4_failure;
 	netlbl_af4list_foreach_rcu(iter4, &entry_map->type_def.addrsel->list4)
 		goto remove_af4_single_addr;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	netlbl_af6list_foreach_rcu(iter6, &entry_map->type_def.addrsel->list6)
 		goto remove_af4_single_addr;
 #endif /* IPv6 */
@@ -644,7 +644,7 @@ struct netlbl_domaddr4_map *netlbl_domhsh_getentry_af4(const char *domain,
 	return netlbl_domhsh_addr4_entry(addr_iter);
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 /**
  * netlbl_domhsh_getentry_af6 - Get an entry from the domain hash table
  * @domain: the domain name to search for
diff --git a/net/netlabel/netlabel_domainhash.h b/net/netlabel/netlabel_domainhash.h
index bfcc0f7..90872c4 100644
--- a/net/netlabel/netlabel_domainhash.h
+++ b/net/netlabel/netlabel_domainhash.h
@@ -104,7 +104,7 @@ int netlbl_domhsh_walk(u32 *skip_bkt,
 		     int (*callback) (struct netlbl_dom_map *entry, void *arg),
 		     void *cb_arg);
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 struct netlbl_domaddr6_map *netlbl_domhsh_getentry_af6(const char *domain,
 						  const struct in6_addr *addr);
 #endif /* IPv6 */
diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c
index 9c24de1..2560e7b 100644
--- a/net/netlabel/netlabel_kapi.c
+++ b/net/netlabel/netlabel_kapi.c
@@ -111,8 +111,6 @@ int netlbl_cfg_unlbl_map_add(const char *domain,
 	struct netlbl_domaddr_map *addrmap = NULL;
 	struct netlbl_domaddr4_map *map4 = NULL;
 	struct netlbl_domaddr6_map *map6 = NULL;
-	const struct in_addr *addr4, *mask4;
-	const struct in6_addr *addr6, *mask6;
 
 	entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
 	if (entry == NULL)
@@ -133,9 +131,9 @@ int netlbl_cfg_unlbl_map_add(const char *domain,
 		INIT_LIST_HEAD(&addrmap->list6);
 
 		switch (family) {
-		case AF_INET:
-			addr4 = addr;
-			mask4 = mask;
+		case AF_INET: {
+			const struct in_addr *addr4 = addr;
+			const struct in_addr *mask4 = mask;
 			map4 = kzalloc(sizeof(*map4), GFP_ATOMIC);
 			if (map4 == NULL)
 				goto cfg_unlbl_map_add_failure;
@@ -148,25 +146,29 @@ int netlbl_cfg_unlbl_map_add(const char *domain,
 			if (ret_val != 0)
 				goto cfg_unlbl_map_add_failure;
 			break;
-		case AF_INET6:
-			addr6 = addr;
-			mask6 = mask;
+			}
+#if IS_ENABLED(CONFIG_IPV6)
+		case AF_INET6: {
+			const struct in6_addr *addr6 = addr;
+			const struct in6_addr *mask6 = mask;
 			map6 = kzalloc(sizeof(*map6), GFP_ATOMIC);
 			if (map6 == NULL)
 				goto cfg_unlbl_map_add_failure;
 			map6->type = NETLBL_NLTYPE_UNLABELED;
-			ipv6_addr_copy(&map6->list.addr, addr6);
+			map6->list.addr = *addr6;
 			map6->list.addr.s6_addr32[0] &= mask6->s6_addr32[0];
 			map6->list.addr.s6_addr32[1] &= mask6->s6_addr32[1];
 			map6->list.addr.s6_addr32[2] &= mask6->s6_addr32[2];
 			map6->list.addr.s6_addr32[3] &= mask6->s6_addr32[3];
-			ipv6_addr_copy(&map6->list.mask, mask6);
+			map6->list.mask = *mask6;
 			map6->list.valid = 1;
-			ret_val = netlbl_af4list_add(&map4->list,
-						     &addrmap->list4);
+			ret_val = netlbl_af6list_add(&map6->list,
+						     &addrmap->list6);
 			if (ret_val != 0)
 				goto cfg_unlbl_map_add_failure;
 			break;
+			}
+#endif /* IPv6 */
 		default:
 			goto cfg_unlbl_map_add_failure;
 			break;
@@ -225,9 +227,11 @@ int netlbl_cfg_unlbl_static_add(struct net *net,
 	case AF_INET:
 		addr_len = sizeof(struct in_addr);
 		break;
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		addr_len = sizeof(struct in6_addr);
 		break;
+#endif /* IPv6 */
 	default:
 		return -EPFNOSUPPORT;
 	}
@@ -266,9 +270,11 @@ int netlbl_cfg_unlbl_static_del(struct net *net,
 	case AF_INET:
 		addr_len = sizeof(struct in_addr);
 		break;
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		addr_len = sizeof(struct in6_addr);
 		break;
+#endif /* IPv6 */
 	default:
 		return -EPFNOSUPPORT;
 	}
@@ -667,7 +673,7 @@ int netlbl_sock_setattr(struct sock *sk,
 			ret_val = -ENOENT;
 		}
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		/* since we don't support any IPv6 labeling protocols right
 		 * now we can optimize everything away until we do */
@@ -718,7 +724,7 @@ int netlbl_sock_getattr(struct sock *sk,
 	case AF_INET:
 		ret_val = cipso_v4_sock_getattr(sk, secattr);
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		ret_val = -ENOMSG;
 		break;
@@ -776,7 +782,7 @@ int netlbl_conn_setattr(struct sock *sk,
 			ret_val = -ENOENT;
 		}
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		/* since we don't support any IPv6 labeling protocols right
 		 * now we can optimize everything away until we do */
@@ -847,7 +853,7 @@ int netlbl_req_setattr(struct request_sock *req,
 			ret_val = -ENOENT;
 		}
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		/* since we don't support any IPv6 labeling protocols right
 		 * now we can optimize everything away until we do */
@@ -920,7 +926,7 @@ int netlbl_skbuff_setattr(struct sk_buff *skb,
 			ret_val = -ENOENT;
 		}
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		/* since we don't support any IPv6 labeling protocols right
 		 * now we can optimize everything away until we do */
@@ -959,7 +965,7 @@ int netlbl_skbuff_getattr(const struct sk_buff *skb,
 		    cipso_v4_skbuff_getattr(skb, secattr) == 0)
 			return 0;
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		break;
 #endif /* IPv6 */
diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c
index bfa5558..4809e2e 100644
--- a/net/netlabel/netlabel_mgmt.c
+++ b/net/netlabel/netlabel_mgmt.c
@@ -184,7 +184,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 
 		entry->type = NETLBL_NLTYPE_ADDRSELECT;
 		entry->type_def.addrsel = addrmap;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	} else if (info->attrs[NLBL_MGMT_A_IPV6ADDR]) {
 		struct in6_addr *addr;
 		struct in6_addr *mask;
@@ -216,12 +216,12 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 			ret_val = -ENOMEM;
 			goto add_failure;
 		}
-		ipv6_addr_copy(&map->list.addr, addr);
+		map->list.addr = *addr;
 		map->list.addr.s6_addr32[0] &= mask->s6_addr32[0];
 		map->list.addr.s6_addr32[1] &= mask->s6_addr32[1];
 		map->list.addr.s6_addr32[2] &= mask->s6_addr32[2];
 		map->list.addr.s6_addr32[3] &= mask->s6_addr32[3];
-		ipv6_addr_copy(&map->list.mask, mask);
+		map->list.mask = *mask;
 		map->list.valid = 1;
 		map->type = entry->type;
 
@@ -270,7 +270,7 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb,
 	struct nlattr *nla_a;
 	struct nlattr *nla_b;
 	struct netlbl_af4list *iter4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct netlbl_af6list *iter6;
 #endif
 
@@ -324,7 +324,7 @@ static int netlbl_mgmt_listentry(struct sk_buff *skb,
 
 			nla_nest_end(skb, nla_b);
 		}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		netlbl_af6list_foreach_rcu(iter6,
 					   &entry->type_def.addrsel->list6) {
 			struct netlbl_domaddr6_map *map6;
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index e251c2c..4b5fa0f 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -170,7 +170,7 @@ static void netlbl_unlhsh_free_iface(struct rcu_head *entry)
 	struct netlbl_unlhsh_iface *iface;
 	struct netlbl_af4list *iter4;
 	struct netlbl_af4list *tmp4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct netlbl_af6list *iter6;
 	struct netlbl_af6list *tmp6;
 #endif /* IPv6 */
@@ -184,7 +184,7 @@ static void netlbl_unlhsh_free_iface(struct rcu_head *entry)
 		netlbl_af4list_remove_entry(iter4);
 		kfree(netlbl_unlhsh_addr4_entry(iter4));
 	}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	netlbl_af6list_foreach_safe(iter6, tmp6, &iface->addr6_list) {
 		netlbl_af6list_remove_entry(iter6);
 		kfree(netlbl_unlhsh_addr6_entry(iter6));
@@ -274,7 +274,7 @@ static int netlbl_unlhsh_add_addr4(struct netlbl_unlhsh_iface *iface,
 	return ret_val;
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 /**
  * netlbl_unlhsh_add_addr6 - Add a new IPv6 address entry to the hash table
  * @iface: the associated interface entry
@@ -300,12 +300,12 @@ static int netlbl_unlhsh_add_addr6(struct netlbl_unlhsh_iface *iface,
 	if (entry == NULL)
 		return -ENOMEM;
 
-	ipv6_addr_copy(&entry->list.addr, addr);
+	entry->list.addr = *addr;
 	entry->list.addr.s6_addr32[0] &= mask->s6_addr32[0];
 	entry->list.addr.s6_addr32[1] &= mask->s6_addr32[1];
 	entry->list.addr.s6_addr32[2] &= mask->s6_addr32[2];
 	entry->list.addr.s6_addr32[3] &= mask->s6_addr32[3];
-	ipv6_addr_copy(&entry->list.mask, mask);
+	entry->list.mask = *mask;
 	entry->list.valid = 1;
 	entry->secid = secid;
 
@@ -436,7 +436,7 @@ int netlbl_unlhsh_add(struct net *net,
 						  mask4->s_addr);
 		break;
 	}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case sizeof(struct in6_addr): {
 		const struct in6_addr *addr6 = addr;
 		const struct in6_addr *mask6 = mask;
@@ -531,7 +531,7 @@ static int netlbl_unlhsh_remove_addr4(struct net *net,
 	return 0;
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 /**
  * netlbl_unlhsh_remove_addr6 - Remove an IPv6 address entry
  * @net: network namespace
@@ -606,14 +606,14 @@ static int netlbl_unlhsh_remove_addr6(struct net *net,
 static void netlbl_unlhsh_condremove_iface(struct netlbl_unlhsh_iface *iface)
 {
 	struct netlbl_af4list *iter4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct netlbl_af6list *iter6;
 #endif /* IPv6 */
 
 	spin_lock(&netlbl_unlhsh_lock);
 	netlbl_af4list_foreach_rcu(iter4, &iface->addr4_list)
 		goto unlhsh_condremove_failure;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	netlbl_af6list_foreach_rcu(iter6, &iface->addr6_list)
 		goto unlhsh_condremove_failure;
 #endif /* IPv6 */
@@ -680,7 +680,7 @@ int netlbl_unlhsh_remove(struct net *net,
 						     iface, addr, mask,
 						     audit_info);
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case sizeof(struct in6_addr):
 		ret_val = netlbl_unlhsh_remove_addr6(net,
 						     iface, addr, mask,
@@ -1196,7 +1196,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb,
 	struct netlbl_unlhsh_iface *iface;
 	struct list_head *iter_list;
 	struct netlbl_af4list *addr4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct netlbl_af6list *addr6;
 #endif
 
@@ -1228,7 +1228,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb,
 					goto unlabel_staticlist_return;
 				}
 			}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 			netlbl_af6list_foreach_rcu(addr6,
 						   &iface->addr6_list) {
 				if (iter_addr6++ < skip_addr6)
@@ -1277,7 +1277,7 @@ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb,
 	u32 skip_addr6 = cb->args[1];
 	u32 iter_addr4 = 0;
 	struct netlbl_af4list *addr4;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	u32 iter_addr6 = 0;
 	struct netlbl_af6list *addr6;
 #endif
@@ -1303,7 +1303,7 @@ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb,
 			goto unlabel_staticlistdef_return;
 		}
 	}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	netlbl_af6list_foreach_rcu(addr6, &iface->addr6_list) {
 		if (iter_addr6++ < skip_addr6)
 			continue;
@@ -1494,7 +1494,7 @@ int netlbl_unlabel_getattr(const struct sk_buff *skb,
 		secattr->attr.secid = netlbl_unlhsh_addr4_entry(addr4)->secid;
 		break;
 	}
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case PF_INET6: {
 		struct ipv6hdr *hdr6;
 		struct netlbl_af6list *addr6;
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 482fa57..28453ae 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -33,6 +33,14 @@ void genl_unlock(void)
 }
 EXPORT_SYMBOL(genl_unlock);
 
+#ifdef CONFIG_PROVE_LOCKING
+int lockdep_genl_is_held(void)
+{
+	return lockdep_is_held(&genl_mutex);
+}
+EXPORT_SYMBOL(lockdep_genl_is_held);
+#endif
+
 #define GENL_FAM_TAB_SIZE	16
 #define GENL_FAM_TAB_MASK	(GENL_FAM_TAB_SIZE - 1)
 
@@ -946,3 +954,16 @@ int genlmsg_multicast_allns(struct sk_buff *skb, u32 pid, unsigned int group,
 	return genlmsg_mcast(skb, pid, group, flags);
 }
 EXPORT_SYMBOL(genlmsg_multicast_allns);
+
+void genl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group,
+		 struct nlmsghdr *nlh, gfp_t flags)
+{
+	struct sock *sk = net->genl_sock;
+	int report = 0;
+
+	if (nlh)
+		report = nlmsg_report(nlh);
+
+	nlmsg_notify(sk, skb, pid, group, report, flags);
+}
+EXPORT_SYMBOL(genl_notify);
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 732152f..c329b47 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -1244,7 +1244,8 @@ static int nr_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 	case SIOCADDRT:
 	case SIOCDELRT:
 	case SIOCNRDECOBS:
-		if (!capable(CAP_NET_ADMIN)) return -EPERM;
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
 		return nr_rt_ioctl(cmd, argp);
 
 	default:
diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c
index 915a87b..2cf3301 100644
--- a/net/netrom/nr_route.c
+++ b/net/netrom/nr_route.c
@@ -670,14 +670,17 @@ int nr_rt_ioctl(unsigned int cmd, void __user *arg)
 	case SIOCADDRT:
 		if (copy_from_user(&nr_route, arg, sizeof(struct nr_route_struct)))
 			return -EFAULT;
-		if ((dev = nr_ax25_dev_get(nr_route.device)) == NULL)
+		if (nr_route.ndigis > AX25_MAX_DIGIS)
 			return -EINVAL;
-		if (nr_route.ndigis < 0 || nr_route.ndigis > AX25_MAX_DIGIS) {
-			dev_put(dev);
+		if ((dev = nr_ax25_dev_get(nr_route.device)) == NULL)
 			return -EINVAL;
-		}
 		switch (nr_route.type) {
 		case NETROM_NODE:
+			if (strnlen(nr_route.mnemonic, 7) == 7) {
+				ret = -EINVAL;
+				break;
+			}
+
 			ret = nr_add_node(&nr_route.callsign,
 				nr_route.mnemonic,
 				&nr_route.neighbour,
diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig
new file mode 100644
index 0000000..d9ea33c
--- /dev/null
+++ b/net/openvswitch/Kconfig
@@ -0,0 +1,28 @@
+#
+# Open vSwitch
+#
+
+config OPENVSWITCH
+	tristate "Open vSwitch"
+	---help---
+	  Open vSwitch is a multilayer Ethernet switch targeted at virtualized
+	  environments.  In addition to supporting a variety of features
+	  expected in a traditional hardware switch, it enables fine-grained
+	  programmatic extension and flow-based control of the network.  This
+	  control is useful in a wide variety of applications but is
+	  particularly important in multi-server virtualization deployments,
+	  which are often characterized by highly dynamic endpoints and the
+	  need to maintain logical abstractions for multiple tenants.
+
+	  The Open vSwitch datapath provides an in-kernel fast path for packet
+	  forwarding.  It is complemented by a userspace daemon, ovs-vswitchd,
+	  which is able to accept configuration from a variety of sources and
+	  translate it into packet processing rules.
+
+	  See http://openvswitch.org for more information and userspace
+	  utilities.
+
+	  To compile this code as a module, choose M here: the module will be
+	  called openvswitch.
+
+	  If unsure, say N.
diff --git a/net/openvswitch/Makefile b/net/openvswitch/Makefile
new file mode 100644
index 0000000..15e7384
--- /dev/null
+++ b/net/openvswitch/Makefile
@@ -0,0 +1,14 @@
+#
+# Makefile for Open vSwitch.
+#
+
+obj-$(CONFIG_OPENVSWITCH) += openvswitch.o
+
+openvswitch-y := \
+	actions.o \
+	datapath.o \
+	dp_notify.o \
+	flow.o \
+	vport.o \
+	vport-internal_dev.o \
+	vport-netdev.o \
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
new file mode 100644
index 0000000..2725d1b
--- /dev/null
+++ b/net/openvswitch/actions.c
@@ -0,0 +1,415 @@
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/skbuff.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/openvswitch.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/in6.h>
+#include <linux/if_arp.h>
+#include <linux/if_vlan.h>
+#include <net/ip.h>
+#include <net/checksum.h>
+#include <net/dsfield.h>
+
+#include "datapath.h"
+#include "vport.h"
+
+static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
+			const struct nlattr *attr, int len, bool keep_skb);
+
+static int make_writable(struct sk_buff *skb, int write_len)
+{
+	if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
+		return 0;
+
+	return pskb_expand_head(skb, 0, 0, GFP_ATOMIC);
+}
+
+/* remove VLAN header from packet and update csum accrodingly. */
+static int __pop_vlan_tci(struct sk_buff *skb, __be16 *current_tci)
+{
+	struct vlan_hdr *vhdr;
+	int err;
+
+	err = make_writable(skb, VLAN_ETH_HLEN);
+	if (unlikely(err))
+		return err;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE)
+		skb->csum = csum_sub(skb->csum, csum_partial(skb->data
+					+ ETH_HLEN, VLAN_HLEN, 0));
+
+	vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
+	*current_tci = vhdr->h_vlan_TCI;
+
+	memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN);
+	__skb_pull(skb, VLAN_HLEN);
+
+	vlan_set_encap_proto(skb, vhdr);
+	skb->mac_header += VLAN_HLEN;
+	skb_reset_mac_len(skb);
+
+	return 0;
+}
+
+static int pop_vlan(struct sk_buff *skb)
+{
+	__be16 tci;
+	int err;
+
+	if (likely(vlan_tx_tag_present(skb))) {
+		skb->vlan_tci = 0;
+	} else {
+		if (unlikely(skb->protocol != htons(ETH_P_8021Q) ||
+			     skb->len < VLAN_ETH_HLEN))
+			return 0;
+
+		err = __pop_vlan_tci(skb, &tci);
+		if (err)
+			return err;
+	}
+	/* move next vlan tag to hw accel tag */
+	if (likely(skb->protocol != htons(ETH_P_8021Q) ||
+		   skb->len < VLAN_ETH_HLEN))
+		return 0;
+
+	err = __pop_vlan_tci(skb, &tci);
+	if (unlikely(err))
+		return err;
+
+	__vlan_hwaccel_put_tag(skb, ntohs(tci));
+	return 0;
+}
+
+static int push_vlan(struct sk_buff *skb, const struct ovs_action_push_vlan *vlan)
+{
+	if (unlikely(vlan_tx_tag_present(skb))) {
+		u16 current_tag;
+
+		/* push down current VLAN tag */
+		current_tag = vlan_tx_tag_get(skb);
+
+		if (!__vlan_put_tag(skb, current_tag))
+			return -ENOMEM;
+
+		if (skb->ip_summed == CHECKSUM_COMPLETE)
+			skb->csum = csum_add(skb->csum, csum_partial(skb->data
+					+ ETH_HLEN, VLAN_HLEN, 0));
+
+	}
+	__vlan_hwaccel_put_tag(skb, ntohs(vlan->vlan_tci) & ~VLAN_TAG_PRESENT);
+	return 0;
+}
+
+static int set_eth_addr(struct sk_buff *skb,
+			const struct ovs_key_ethernet *eth_key)
+{
+	int err;
+	err = make_writable(skb, ETH_HLEN);
+	if (unlikely(err))
+		return err;
+
+	memcpy(eth_hdr(skb)->h_source, eth_key->eth_src, ETH_ALEN);
+	memcpy(eth_hdr(skb)->h_dest, eth_key->eth_dst, ETH_ALEN);
+
+	return 0;
+}
+
+static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
+				__be32 *addr, __be32 new_addr)
+{
+	int transport_len = skb->len - skb_transport_offset(skb);
+
+	if (nh->protocol == IPPROTO_TCP) {
+		if (likely(transport_len >= sizeof(struct tcphdr)))
+			inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb,
+						 *addr, new_addr, 1);
+	} else if (nh->protocol == IPPROTO_UDP) {
+		if (likely(transport_len >= sizeof(struct udphdr)))
+			inet_proto_csum_replace4(&udp_hdr(skb)->check, skb,
+						 *addr, new_addr, 1);
+	}
+
+	csum_replace4(&nh->check, *addr, new_addr);
+	skb->rxhash = 0;
+	*addr = new_addr;
+}
+
+static void set_ip_ttl(struct sk_buff *skb, struct iphdr *nh, u8 new_ttl)
+{
+	csum_replace2(&nh->check, htons(nh->ttl << 8), htons(new_ttl << 8));
+	nh->ttl = new_ttl;
+}
+
+static int set_ipv4(struct sk_buff *skb, const struct ovs_key_ipv4 *ipv4_key)
+{
+	struct iphdr *nh;
+	int err;
+
+	err = make_writable(skb, skb_network_offset(skb) +
+				 sizeof(struct iphdr));
+	if (unlikely(err))
+		return err;
+
+	nh = ip_hdr(skb);
+
+	if (ipv4_key->ipv4_src != nh->saddr)
+		set_ip_addr(skb, nh, &nh->saddr, ipv4_key->ipv4_src);
+
+	if (ipv4_key->ipv4_dst != nh->daddr)
+		set_ip_addr(skb, nh, &nh->daddr, ipv4_key->ipv4_dst);
+
+	if (ipv4_key->ipv4_tos != nh->tos)
+		ipv4_change_dsfield(nh, 0, ipv4_key->ipv4_tos);
+
+	if (ipv4_key->ipv4_ttl != nh->ttl)
+		set_ip_ttl(skb, nh, ipv4_key->ipv4_ttl);
+
+	return 0;
+}
+
+/* Must follow make_writable() since that can move the skb data. */
+static void set_tp_port(struct sk_buff *skb, __be16 *port,
+			 __be16 new_port, __sum16 *check)
+{
+	inet_proto_csum_replace2(check, skb, *port, new_port, 0);
+	*port = new_port;
+	skb->rxhash = 0;
+}
+
+static int set_udp_port(struct sk_buff *skb,
+			const struct ovs_key_udp *udp_port_key)
+{
+	struct udphdr *uh;
+	int err;
+
+	err = make_writable(skb, skb_transport_offset(skb) +
+				 sizeof(struct udphdr));
+	if (unlikely(err))
+		return err;
+
+	uh = udp_hdr(skb);
+	if (udp_port_key->udp_src != uh->source)
+		set_tp_port(skb, &uh->source, udp_port_key->udp_src, &uh->check);
+
+	if (udp_port_key->udp_dst != uh->dest)
+		set_tp_port(skb, &uh->dest, udp_port_key->udp_dst, &uh->check);
+
+	return 0;
+}
+
+static int set_tcp_port(struct sk_buff *skb,
+			const struct ovs_key_tcp *tcp_port_key)
+{
+	struct tcphdr *th;
+	int err;
+
+	err = make_writable(skb, skb_transport_offset(skb) +
+				 sizeof(struct tcphdr));
+	if (unlikely(err))
+		return err;
+
+	th = tcp_hdr(skb);
+	if (tcp_port_key->tcp_src != th->source)
+		set_tp_port(skb, &th->source, tcp_port_key->tcp_src, &th->check);
+
+	if (tcp_port_key->tcp_dst != th->dest)
+		set_tp_port(skb, &th->dest, tcp_port_key->tcp_dst, &th->check);
+
+	return 0;
+}
+
+static int do_output(struct datapath *dp, struct sk_buff *skb, int out_port)
+{
+	struct vport *vport;
+
+	if (unlikely(!skb))
+		return -ENOMEM;
+
+	vport = rcu_dereference(dp->ports[out_port]);
+	if (unlikely(!vport)) {
+		kfree_skb(skb);
+		return -ENODEV;
+	}
+
+	ovs_vport_send(vport, skb);
+	return 0;
+}
+
+static int output_userspace(struct datapath *dp, struct sk_buff *skb,
+			    const struct nlattr *attr)
+{
+	struct dp_upcall_info upcall;
+	const struct nlattr *a;
+	int rem;
+
+	upcall.cmd = OVS_PACKET_CMD_ACTION;
+	upcall.key = &OVS_CB(skb)->flow->key;
+	upcall.userdata = NULL;
+	upcall.pid = 0;
+
+	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
+		 a = nla_next(a, &rem)) {
+		switch (nla_type(a)) {
+		case OVS_USERSPACE_ATTR_USERDATA:
+			upcall.userdata = a;
+			break;
+
+		case OVS_USERSPACE_ATTR_PID:
+			upcall.pid = nla_get_u32(a);
+			break;
+		}
+	}
+
+	return ovs_dp_upcall(dp, skb, &upcall);
+}
+
+static int sample(struct datapath *dp, struct sk_buff *skb,
+		  const struct nlattr *attr)
+{
+	const struct nlattr *acts_list = NULL;
+	const struct nlattr *a;
+	int rem;
+
+	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
+		 a = nla_next(a, &rem)) {
+		switch (nla_type(a)) {
+		case OVS_SAMPLE_ATTR_PROBABILITY:
+			if (net_random() >= nla_get_u32(a))
+				return 0;
+			break;
+
+		case OVS_SAMPLE_ATTR_ACTIONS:
+			acts_list = a;
+			break;
+		}
+	}
+
+	return do_execute_actions(dp, skb, nla_data(acts_list),
+						 nla_len(acts_list), true);
+}
+
+static int execute_set_action(struct sk_buff *skb,
+				 const struct nlattr *nested_attr)
+{
+	int err = 0;
+
+	switch (nla_type(nested_attr)) {
+	case OVS_KEY_ATTR_PRIORITY:
+		skb->priority = nla_get_u32(nested_attr);
+		break;
+
+	case OVS_KEY_ATTR_ETHERNET:
+		err = set_eth_addr(skb, nla_data(nested_attr));
+		break;
+
+	case OVS_KEY_ATTR_IPV4:
+		err = set_ipv4(skb, nla_data(nested_attr));
+		break;
+
+	case OVS_KEY_ATTR_TCP:
+		err = set_tcp_port(skb, nla_data(nested_attr));
+		break;
+
+	case OVS_KEY_ATTR_UDP:
+		err = set_udp_port(skb, nla_data(nested_attr));
+		break;
+	}
+
+	return err;
+}
+
+/* Execute a list of actions against 'skb'. */
+static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
+			const struct nlattr *attr, int len, bool keep_skb)
+{
+	/* Every output action needs a separate clone of 'skb', but the common
+	 * case is just a single output action, so that doing a clone and
+	 * then freeing the original skbuff is wasteful.  So the following code
+	 * is slightly obscure just to avoid that. */
+	int prev_port = -1;
+	const struct nlattr *a;
+	int rem;
+
+	for (a = attr, rem = len; rem > 0;
+	     a = nla_next(a, &rem)) {
+		int err = 0;
+
+		if (prev_port != -1) {
+			do_output(dp, skb_clone(skb, GFP_ATOMIC), prev_port);
+			prev_port = -1;
+		}
+
+		switch (nla_type(a)) {
+		case OVS_ACTION_ATTR_OUTPUT:
+			prev_port = nla_get_u32(a);
+			break;
+
+		case OVS_ACTION_ATTR_USERSPACE:
+			output_userspace(dp, skb, a);
+			break;
+
+		case OVS_ACTION_ATTR_PUSH_VLAN:
+			err = push_vlan(skb, nla_data(a));
+			if (unlikely(err)) /* skb already freed. */
+				return err;
+			break;
+
+		case OVS_ACTION_ATTR_POP_VLAN:
+			err = pop_vlan(skb);
+			break;
+
+		case OVS_ACTION_ATTR_SET:
+			err = execute_set_action(skb, nla_data(a));
+			break;
+
+		case OVS_ACTION_ATTR_SAMPLE:
+			err = sample(dp, skb, a);
+			break;
+		}
+
+		if (unlikely(err)) {
+			kfree_skb(skb);
+			return err;
+		}
+	}
+
+	if (prev_port != -1) {
+		if (keep_skb)
+			skb = skb_clone(skb, GFP_ATOMIC);
+
+		do_output(dp, skb, prev_port);
+	} else if (!keep_skb)
+		consume_skb(skb);
+
+	return 0;
+}
+
+/* Execute a list of actions against 'skb'. */
+int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb)
+{
+	struct sw_flow_actions *acts = rcu_dereference(OVS_CB(skb)->flow->sf_acts);
+
+	return do_execute_actions(dp, skb, acts->actions,
+					 acts->actions_len, false);
+}
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
new file mode 100644
index 0000000..9a27251
--- /dev/null
+++ b/net/openvswitch/datapath.c
@@ -0,0 +1,1912 @@
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/if_arp.h>
+#include <linux/if_vlan.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/jhash.h>
+#include <linux/delay.h>
+#include <linux/time.h>
+#include <linux/etherdevice.h>
+#include <linux/genetlink.h>
+#include <linux/kernel.h>
+#include <linux/kthread.h>
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+#include <linux/rcupdate.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/version.h>
+#include <linux/ethtool.h>
+#include <linux/wait.h>
+#include <asm/system.h>
+#include <asm/div64.h>
+#include <linux/highmem.h>
+#include <linux/netfilter_bridge.h>
+#include <linux/netfilter_ipv4.h>
+#include <linux/inetdevice.h>
+#include <linux/list.h>
+#include <linux/openvswitch.h>
+#include <linux/rculist.h>
+#include <linux/dmi.h>
+#include <linux/workqueue.h>
+#include <net/genetlink.h>
+
+#include "datapath.h"
+#include "flow.h"
+#include "vport-internal_dev.h"
+
+/**
+ * DOC: Locking:
+ *
+ * Writes to device state (add/remove datapath, port, set operations on vports,
+ * etc.) are protected by RTNL.
+ *
+ * Writes to other state (flow table modifications, set miscellaneous datapath
+ * parameters, etc.) are protected by genl_mutex.  The RTNL lock nests inside
+ * genl_mutex.
+ *
+ * Reads are protected by RCU.
+ *
+ * There are a few special cases (mostly stats) that have their own
+ * synchronization but they nest under all of above and don't interact with
+ * each other.
+ */
+
+/* Global list of datapaths to enable dumping them all out.
+ * Protected by genl_mutex.
+ */
+static LIST_HEAD(dps);
+
+#define REHASH_FLOW_INTERVAL (10 * 60 * HZ)
+static void rehash_flow_table(struct work_struct *work);
+static DECLARE_DELAYED_WORK(rehash_flow_wq, rehash_flow_table);
+
+static struct vport *new_vport(const struct vport_parms *);
+static int queue_gso_packets(int dp_ifindex, struct sk_buff *,
+			     const struct dp_upcall_info *);
+static int queue_userspace_packet(int dp_ifindex, struct sk_buff *,
+				  const struct dp_upcall_info *);
+
+/* Must be called with rcu_read_lock, genl_mutex, or RTNL lock. */
+static struct datapath *get_dp(int dp_ifindex)
+{
+	struct datapath *dp = NULL;
+	struct net_device *dev;
+
+	rcu_read_lock();
+	dev = dev_get_by_index_rcu(&init_net, dp_ifindex);
+	if (dev) {
+		struct vport *vport = ovs_internal_dev_get_vport(dev);
+		if (vport)
+			dp = vport->dp;
+	}
+	rcu_read_unlock();
+
+	return dp;
+}
+
+/* Must be called with rcu_read_lock or RTNL lock. */
+const char *ovs_dp_name(const struct datapath *dp)
+{
+	struct vport *vport = rcu_dereference_rtnl(dp->ports[OVSP_LOCAL]);
+	return vport->ops->get_name(vport);
+}
+
+static int get_dpifindex(struct datapath *dp)
+{
+	struct vport *local;
+	int ifindex;
+
+	rcu_read_lock();
+
+	local = rcu_dereference(dp->ports[OVSP_LOCAL]);
+	if (local)
+		ifindex = local->ops->get_ifindex(local);
+	else
+		ifindex = 0;
+
+	rcu_read_unlock();
+
+	return ifindex;
+}
+
+static void destroy_dp_rcu(struct rcu_head *rcu)
+{
+	struct datapath *dp = container_of(rcu, struct datapath, rcu);
+
+	ovs_flow_tbl_destroy((__force struct flow_table *)dp->table);
+	free_percpu(dp->stats_percpu);
+	kfree(dp);
+}
+
+/* Called with RTNL lock and genl_lock. */
+static struct vport *new_vport(const struct vport_parms *parms)
+{
+	struct vport *vport;
+
+	vport = ovs_vport_add(parms);
+	if (!IS_ERR(vport)) {
+		struct datapath *dp = parms->dp;
+
+		rcu_assign_pointer(dp->ports[parms->port_no], vport);
+		list_add(&vport->node, &dp->port_list);
+	}
+
+	return vport;
+}
+
+/* Called with RTNL lock. */
+void ovs_dp_detach_port(struct vport *p)
+{
+	ASSERT_RTNL();
+
+	/* First drop references to device. */
+	list_del(&p->node);
+	rcu_assign_pointer(p->dp->ports[p->port_no], NULL);
+
+	/* Then destroy it. */
+	ovs_vport_del(p);
+}
+
+/* Must be called with rcu_read_lock. */
+void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb)
+{
+	struct datapath *dp = p->dp;
+	struct sw_flow *flow;
+	struct dp_stats_percpu *stats;
+	struct sw_flow_key key;
+	u64 *stats_counter;
+	int error;
+	int key_len;
+
+	stats = per_cpu_ptr(dp->stats_percpu, smp_processor_id());
+
+	/* Extract flow from 'skb' into 'key'. */
+	error = ovs_flow_extract(skb, p->port_no, &key, &key_len);
+	if (unlikely(error)) {
+		kfree_skb(skb);
+		return;
+	}
+
+	/* Look up flow. */
+	flow = ovs_flow_tbl_lookup(rcu_dereference(dp->table), &key, key_len);
+	if (unlikely(!flow)) {
+		struct dp_upcall_info upcall;
+
+		upcall.cmd = OVS_PACKET_CMD_MISS;
+		upcall.key = &key;
+		upcall.userdata = NULL;
+		upcall.pid = p->upcall_pid;
+		ovs_dp_upcall(dp, skb, &upcall);
+		consume_skb(skb);
+		stats_counter = &stats->n_missed;
+		goto out;
+	}
+
+	OVS_CB(skb)->flow = flow;
+
+	stats_counter = &stats->n_hit;
+	ovs_flow_used(OVS_CB(skb)->flow, skb);
+	ovs_execute_actions(dp, skb);
+
+out:
+	/* Update datapath statistics. */
+	u64_stats_update_begin(&stats->sync);
+	(*stats_counter)++;
+	u64_stats_update_end(&stats->sync);
+}
+
+static struct genl_family dp_packet_genl_family = {
+	.id = GENL_ID_GENERATE,
+	.hdrsize = sizeof(struct ovs_header),
+	.name = OVS_PACKET_FAMILY,
+	.version = OVS_PACKET_VERSION,
+	.maxattr = OVS_PACKET_ATTR_MAX
+};
+
+int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
+	      const struct dp_upcall_info *upcall_info)
+{
+	struct dp_stats_percpu *stats;
+	int dp_ifindex;
+	int err;
+
+	if (upcall_info->pid == 0) {
+		err = -ENOTCONN;
+		goto err;
+	}
+
+	dp_ifindex = get_dpifindex(dp);
+	if (!dp_ifindex) {
+		err = -ENODEV;
+		goto err;
+	}
+
+	if (!skb_is_gso(skb))
+		err = queue_userspace_packet(dp_ifindex, skb, upcall_info);
+	else
+		err = queue_gso_packets(dp_ifindex, skb, upcall_info);
+	if (err)
+		goto err;
+
+	return 0;
+
+err:
+	stats = per_cpu_ptr(dp->stats_percpu, smp_processor_id());
+
+	u64_stats_update_begin(&stats->sync);
+	stats->n_lost++;
+	u64_stats_update_end(&stats->sync);
+
+	return err;
+}
+
+static int queue_gso_packets(int dp_ifindex, struct sk_buff *skb,
+			     const struct dp_upcall_info *upcall_info)
+{
+	struct dp_upcall_info later_info;
+	struct sw_flow_key later_key;
+	struct sk_buff *segs, *nskb;
+	int err;
+
+	segs = skb_gso_segment(skb, NETIF_F_SG | NETIF_F_HW_CSUM);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	/* Queue all of the segments. */
+	skb = segs;
+	do {
+		err = queue_userspace_packet(dp_ifindex, skb, upcall_info);
+		if (err)
+			break;
+
+		if (skb == segs && skb_shinfo(skb)->gso_type & SKB_GSO_UDP) {
+			/* The initial flow key extracted by ovs_flow_extract()
+			 * in this case is for a first fragment, so we need to
+			 * properly mark later fragments.
+			 */
+			later_key = *upcall_info->key;
+			later_key.ip.frag = OVS_FRAG_TYPE_LATER;
+
+			later_info = *upcall_info;
+			later_info.key = &later_key;
+			upcall_info = &later_info;
+		}
+	} while ((skb = skb->next));
+
+	/* Free all of the segments. */
+	skb = segs;
+	do {
+		nskb = skb->next;
+		if (err)
+			kfree_skb(skb);
+		else
+			consume_skb(skb);
+	} while ((skb = nskb));
+	return err;
+}
+
+static int queue_userspace_packet(int dp_ifindex, struct sk_buff *skb,
+				  const struct dp_upcall_info *upcall_info)
+{
+	struct ovs_header *upcall;
+	struct sk_buff *nskb = NULL;
+	struct sk_buff *user_skb; /* to be queued to userspace */
+	struct nlattr *nla;
+	unsigned int len;
+	int err;
+
+	if (vlan_tx_tag_present(skb)) {
+		nskb = skb_clone(skb, GFP_ATOMIC);
+		if (!nskb)
+			return -ENOMEM;
+
+		nskb = __vlan_put_tag(nskb, vlan_tx_tag_get(nskb));
+		if (!skb)
+			return -ENOMEM;
+
+		nskb->vlan_tci = 0;
+		skb = nskb;
+	}
+
+	if (nla_attr_size(skb->len) > USHRT_MAX) {
+		err = -EFBIG;
+		goto out;
+	}
+
+	len = sizeof(struct ovs_header);
+	len += nla_total_size(skb->len);
+	len += nla_total_size(FLOW_BUFSIZE);
+	if (upcall_info->cmd == OVS_PACKET_CMD_ACTION)
+		len += nla_total_size(8);
+
+	user_skb = genlmsg_new(len, GFP_ATOMIC);
+	if (!user_skb) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	upcall = genlmsg_put(user_skb, 0, 0, &dp_packet_genl_family,
+			     0, upcall_info->cmd);
+	upcall->dp_ifindex = dp_ifindex;
+
+	nla = nla_nest_start(user_skb, OVS_PACKET_ATTR_KEY);
+	ovs_flow_to_nlattrs(upcall_info->key, user_skb);
+	nla_nest_end(user_skb, nla);
+
+	if (upcall_info->userdata)
+		nla_put_u64(user_skb, OVS_PACKET_ATTR_USERDATA,
+			    nla_get_u64(upcall_info->userdata));
+
+	nla = __nla_reserve(user_skb, OVS_PACKET_ATTR_PACKET, skb->len);
+
+	skb_copy_and_csum_dev(skb, nla_data(nla));
+
+	err = genlmsg_unicast(&init_net, user_skb, upcall_info->pid);
+
+out:
+	kfree_skb(nskb);
+	return err;
+}
+
+/* Called with genl_mutex. */
+static int flush_flows(int dp_ifindex)
+{
+	struct flow_table *old_table;
+	struct flow_table *new_table;
+	struct datapath *dp;
+
+	dp = get_dp(dp_ifindex);
+	if (!dp)
+		return -ENODEV;
+
+	old_table = genl_dereference(dp->table);
+	new_table = ovs_flow_tbl_alloc(TBL_MIN_BUCKETS);
+	if (!new_table)
+		return -ENOMEM;
+
+	rcu_assign_pointer(dp->table, new_table);
+
+	ovs_flow_tbl_deferred_destroy(old_table);
+	return 0;
+}
+
+static int validate_actions(const struct nlattr *attr,
+				const struct sw_flow_key *key, int depth);
+
+static int validate_sample(const struct nlattr *attr,
+				const struct sw_flow_key *key, int depth)
+{
+	const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1];
+	const struct nlattr *probability, *actions;
+	const struct nlattr *a;
+	int rem;
+
+	memset(attrs, 0, sizeof(attrs));
+	nla_for_each_nested(a, attr, rem) {
+		int type = nla_type(a);
+		if (!type || type > OVS_SAMPLE_ATTR_MAX || attrs[type])
+			return -EINVAL;
+		attrs[type] = a;
+	}
+	if (rem)
+		return -EINVAL;
+
+	probability = attrs[OVS_SAMPLE_ATTR_PROBABILITY];
+	if (!probability || nla_len(probability) != sizeof(u32))
+		return -EINVAL;
+
+	actions = attrs[OVS_SAMPLE_ATTR_ACTIONS];
+	if (!actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN))
+		return -EINVAL;
+	return validate_actions(actions, key, depth + 1);
+}
+
+static int validate_set(const struct nlattr *a,
+			const struct sw_flow_key *flow_key)
+{
+	const struct nlattr *ovs_key = nla_data(a);
+	int key_type = nla_type(ovs_key);
+
+	/* There can be only one key in a action */
+	if (nla_total_size(nla_len(ovs_key)) != nla_len(a))
+		return -EINVAL;
+
+	if (key_type > OVS_KEY_ATTR_MAX ||
+	    nla_len(ovs_key) != ovs_key_lens[key_type])
+		return -EINVAL;
+
+	switch (key_type) {
+	const struct ovs_key_ipv4 *ipv4_key;
+
+	case OVS_KEY_ATTR_PRIORITY:
+	case OVS_KEY_ATTR_ETHERNET:
+		break;
+
+	case OVS_KEY_ATTR_IPV4:
+		if (flow_key->eth.type != htons(ETH_P_IP))
+			return -EINVAL;
+
+		if (!flow_key->ipv4.addr.src || !flow_key->ipv4.addr.dst)
+			return -EINVAL;
+
+		ipv4_key = nla_data(ovs_key);
+		if (ipv4_key->ipv4_proto != flow_key->ip.proto)
+			return -EINVAL;
+
+		if (ipv4_key->ipv4_frag != flow_key->ip.frag)
+			return -EINVAL;
+
+		break;
+
+	case OVS_KEY_ATTR_TCP:
+		if (flow_key->ip.proto != IPPROTO_TCP)
+			return -EINVAL;
+
+		if (!flow_key->ipv4.tp.src || !flow_key->ipv4.tp.dst)
+			return -EINVAL;
+
+		break;
+
+	case OVS_KEY_ATTR_UDP:
+		if (flow_key->ip.proto != IPPROTO_UDP)
+			return -EINVAL;
+
+		if (!flow_key->ipv4.tp.src || !flow_key->ipv4.tp.dst)
+			return -EINVAL;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int validate_userspace(const struct nlattr *attr)
+{
+	static const struct nla_policy userspace_policy[OVS_USERSPACE_ATTR_MAX + 1] =	{
+		[OVS_USERSPACE_ATTR_PID] = {.type = NLA_U32 },
+		[OVS_USERSPACE_ATTR_USERDATA] = {.type = NLA_U64 },
+	};
+	struct nlattr *a[OVS_USERSPACE_ATTR_MAX + 1];
+	int error;
+
+	error = nla_parse_nested(a, OVS_USERSPACE_ATTR_MAX,
+				 attr, userspace_policy);
+	if (error)
+		return error;
+
+	if (!a[OVS_USERSPACE_ATTR_PID] ||
+	    !nla_get_u32(a[OVS_USERSPACE_ATTR_PID]))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int validate_actions(const struct nlattr *attr,
+				const struct sw_flow_key *key,  int depth)
+{
+	const struct nlattr *a;
+	int rem, err;
+
+	if (depth >= SAMPLE_ACTION_DEPTH)
+		return -EOVERFLOW;
+
+	nla_for_each_nested(a, attr, rem) {
+		/* Expected argument lengths, (u32)-1 for variable length. */
+		static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = {
+			[OVS_ACTION_ATTR_OUTPUT] = sizeof(u32),
+			[OVS_ACTION_ATTR_USERSPACE] = (u32)-1,
+			[OVS_ACTION_ATTR_PUSH_VLAN] = sizeof(struct ovs_action_push_vlan),
+			[OVS_ACTION_ATTR_POP_VLAN] = 0,
+			[OVS_ACTION_ATTR_SET] = (u32)-1,
+			[OVS_ACTION_ATTR_SAMPLE] = (u32)-1
+		};
+		const struct ovs_action_push_vlan *vlan;
+		int type = nla_type(a);
+
+		if (type > OVS_ACTION_ATTR_MAX ||
+		    (action_lens[type] != nla_len(a) &&
+		     action_lens[type] != (u32)-1))
+			return -EINVAL;
+
+		switch (type) {
+		case OVS_ACTION_ATTR_UNSPEC:
+			return -EINVAL;
+
+		case OVS_ACTION_ATTR_USERSPACE:
+			err = validate_userspace(a);
+			if (err)
+				return err;
+			break;
+
+		case OVS_ACTION_ATTR_OUTPUT:
+			if (nla_get_u32(a) >= DP_MAX_PORTS)
+				return -EINVAL;
+			break;
+
+
+		case OVS_ACTION_ATTR_POP_VLAN:
+			break;
+
+		case OVS_ACTION_ATTR_PUSH_VLAN:
+			vlan = nla_data(a);
+			if (vlan->vlan_tpid != htons(ETH_P_8021Q))
+				return -EINVAL;
+			if (!(vlan->vlan_tci & htons(VLAN_TAG_PRESENT)))
+				return -EINVAL;
+			break;
+
+		case OVS_ACTION_ATTR_SET:
+			err = validate_set(a, key);
+			if (err)
+				return err;
+			break;
+
+		case OVS_ACTION_ATTR_SAMPLE:
+			err = validate_sample(a, key, depth);
+			if (err)
+				return err;
+			break;
+
+		default:
+			return -EINVAL;
+		}
+	}
+
+	if (rem > 0)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void clear_stats(struct sw_flow *flow)
+{
+	flow->used = 0;
+	flow->tcp_flags = 0;
+	flow->packet_count = 0;
+	flow->byte_count = 0;
+}
+
+static int ovs_packet_cmd_execute(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ovs_header *ovs_header = info->userhdr;
+	struct nlattr **a = info->attrs;
+	struct sw_flow_actions *acts;
+	struct sk_buff *packet;
+	struct sw_flow *flow;
+	struct datapath *dp;
+	struct ethhdr *eth;
+	int len;
+	int err;
+	int key_len;
+
+	err = -EINVAL;
+	if (!a[OVS_PACKET_ATTR_PACKET] || !a[OVS_PACKET_ATTR_KEY] ||
+	    !a[OVS_PACKET_ATTR_ACTIONS] ||
+	    nla_len(a[OVS_PACKET_ATTR_PACKET]) < ETH_HLEN)
+		goto err;
+
+	len = nla_len(a[OVS_PACKET_ATTR_PACKET]);
+	packet = __dev_alloc_skb(NET_IP_ALIGN + len, GFP_KERNEL);
+	err = -ENOMEM;
+	if (!packet)
+		goto err;
+	skb_reserve(packet, NET_IP_ALIGN);
+
+	memcpy(__skb_put(packet, len), nla_data(a[OVS_PACKET_ATTR_PACKET]), len);
+
+	skb_reset_mac_header(packet);
+	eth = eth_hdr(packet);
+
+	/* Normally, setting the skb 'protocol' field would be handled by a
+	 * call to eth_type_trans(), but it assumes there's a sending
+	 * device, which we may not have. */
+	if (ntohs(eth->h_proto) >= 1536)
+		packet->protocol = eth->h_proto;
+	else
+		packet->protocol = htons(ETH_P_802_2);
+
+	/* Build an sw_flow for sending this packet. */
+	flow = ovs_flow_alloc();
+	err = PTR_ERR(flow);
+	if (IS_ERR(flow))
+		goto err_kfree_skb;
+
+	err = ovs_flow_extract(packet, -1, &flow->key, &key_len);
+	if (err)
+		goto err_flow_free;
+
+	err = ovs_flow_metadata_from_nlattrs(&flow->key.phy.priority,
+					     &flow->key.phy.in_port,
+					     a[OVS_PACKET_ATTR_KEY]);
+	if (err)
+		goto err_flow_free;
+
+	err = validate_actions(a[OVS_PACKET_ATTR_ACTIONS], &flow->key, 0);
+	if (err)
+		goto err_flow_free;
+
+	flow->hash = ovs_flow_hash(&flow->key, key_len);
+
+	acts = ovs_flow_actions_alloc(a[OVS_PACKET_ATTR_ACTIONS]);
+	err = PTR_ERR(acts);
+	if (IS_ERR(acts))
+		goto err_flow_free;
+	rcu_assign_pointer(flow->sf_acts, acts);
+
+	OVS_CB(packet)->flow = flow;
+	packet->priority = flow->key.phy.priority;
+
+	rcu_read_lock();
+	dp = get_dp(ovs_header->dp_ifindex);
+	err = -ENODEV;
+	if (!dp)
+		goto err_unlock;
+
+	local_bh_disable();
+	err = ovs_execute_actions(dp, packet);
+	local_bh_enable();
+	rcu_read_unlock();
+
+	ovs_flow_free(flow);
+	return err;
+
+err_unlock:
+	rcu_read_unlock();
+err_flow_free:
+	ovs_flow_free(flow);
+err_kfree_skb:
+	kfree_skb(packet);
+err:
+	return err;
+}
+
+static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = {
+	[OVS_PACKET_ATTR_PACKET] = { .type = NLA_UNSPEC },
+	[OVS_PACKET_ATTR_KEY] = { .type = NLA_NESTED },
+	[OVS_PACKET_ATTR_ACTIONS] = { .type = NLA_NESTED },
+};
+
+static struct genl_ops dp_packet_genl_ops[] = {
+	{ .cmd = OVS_PACKET_CMD_EXECUTE,
+	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+	  .policy = packet_policy,
+	  .doit = ovs_packet_cmd_execute
+	}
+};
+
+static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats)
+{
+	int i;
+	struct flow_table *table = genl_dereference(dp->table);
+
+	stats->n_flows = ovs_flow_tbl_count(table);
+
+	stats->n_hit = stats->n_missed = stats->n_lost = 0;
+	for_each_possible_cpu(i) {
+		const struct dp_stats_percpu *percpu_stats;
+		struct dp_stats_percpu local_stats;
+		unsigned int start;
+
+		percpu_stats = per_cpu_ptr(dp->stats_percpu, i);
+
+		do {
+			start = u64_stats_fetch_begin_bh(&percpu_stats->sync);
+			local_stats = *percpu_stats;
+		} while (u64_stats_fetch_retry_bh(&percpu_stats->sync, start));
+
+		stats->n_hit += local_stats.n_hit;
+		stats->n_missed += local_stats.n_missed;
+		stats->n_lost += local_stats.n_lost;
+	}
+}
+
+static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
+	[OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED },
+	[OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED },
+	[OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG },
+};
+
+static struct genl_family dp_flow_genl_family = {
+	.id = GENL_ID_GENERATE,
+	.hdrsize = sizeof(struct ovs_header),
+	.name = OVS_FLOW_FAMILY,
+	.version = OVS_FLOW_VERSION,
+	.maxattr = OVS_FLOW_ATTR_MAX
+};
+
+static struct genl_multicast_group ovs_dp_flow_multicast_group = {
+	.name = OVS_FLOW_MCGROUP
+};
+
+/* Called with genl_lock. */
+static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp,
+				  struct sk_buff *skb, u32 pid,
+				  u32 seq, u32 flags, u8 cmd)
+{
+	const int skb_orig_len = skb->len;
+	const struct sw_flow_actions *sf_acts;
+	struct ovs_flow_stats stats;
+	struct ovs_header *ovs_header;
+	struct nlattr *nla;
+	unsigned long used;
+	u8 tcp_flags;
+	int err;
+
+	sf_acts = rcu_dereference_protected(flow->sf_acts,
+					    lockdep_genl_is_held());
+
+	ovs_header = genlmsg_put(skb, pid, seq, &dp_flow_genl_family, flags, cmd);
+	if (!ovs_header)
+		return -EMSGSIZE;
+
+	ovs_header->dp_ifindex = get_dpifindex(dp);
+
+	nla = nla_nest_start(skb, OVS_FLOW_ATTR_KEY);
+	if (!nla)
+		goto nla_put_failure;
+	err = ovs_flow_to_nlattrs(&flow->key, skb);
+	if (err)
+		goto error;
+	nla_nest_end(skb, nla);
+
+	spin_lock_bh(&flow->lock);
+	used = flow->used;
+	stats.n_packets = flow->packet_count;
+	stats.n_bytes = flow->byte_count;
+	tcp_flags = flow->tcp_flags;
+	spin_unlock_bh(&flow->lock);
+
+	if (used)
+		NLA_PUT_U64(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used));
+
+	if (stats.n_packets)
+		NLA_PUT(skb, OVS_FLOW_ATTR_STATS,
+			sizeof(struct ovs_flow_stats), &stats);
+
+	if (tcp_flags)
+		NLA_PUT_U8(skb, OVS_FLOW_ATTR_TCP_FLAGS, tcp_flags);
+
+	/* If OVS_FLOW_ATTR_ACTIONS doesn't fit, skip dumping the actions if
+	 * this is the first flow to be dumped into 'skb'.  This is unusual for
+	 * Netlink but individual action lists can be longer than
+	 * NLMSG_GOODSIZE and thus entirely undumpable if we didn't do this.
+	 * The userspace caller can always fetch the actions separately if it
+	 * really wants them.  (Most userspace callers in fact don't care.)
+	 *
+	 * This can only fail for dump operations because the skb is always
+	 * properly sized for single flows.
+	 */
+	err = nla_put(skb, OVS_FLOW_ATTR_ACTIONS, sf_acts->actions_len,
+		      sf_acts->actions);
+	if (err < 0 && skb_orig_len)
+		goto error;
+
+	return genlmsg_end(skb, ovs_header);
+
+nla_put_failure:
+	err = -EMSGSIZE;
+error:
+	genlmsg_cancel(skb, ovs_header);
+	return err;
+}
+
+static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow)
+{
+	const struct sw_flow_actions *sf_acts;
+	int len;
+
+	sf_acts = rcu_dereference_protected(flow->sf_acts,
+					    lockdep_genl_is_held());
+
+	/* OVS_FLOW_ATTR_KEY */
+	len = nla_total_size(FLOW_BUFSIZE);
+	/* OVS_FLOW_ATTR_ACTIONS */
+	len += nla_total_size(sf_acts->actions_len);
+	/* OVS_FLOW_ATTR_STATS */
+	len += nla_total_size(sizeof(struct ovs_flow_stats));
+	/* OVS_FLOW_ATTR_TCP_FLAGS */
+	len += nla_total_size(1);
+	/* OVS_FLOW_ATTR_USED */
+	len += nla_total_size(8);
+
+	len += NLMSG_ALIGN(sizeof(struct ovs_header));
+
+	return genlmsg_new(len, GFP_KERNEL);
+}
+
+static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow,
+					       struct datapath *dp,
+					       u32 pid, u32 seq, u8 cmd)
+{
+	struct sk_buff *skb;
+	int retval;
+
+	skb = ovs_flow_cmd_alloc_info(flow);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	retval = ovs_flow_cmd_fill_info(flow, dp, skb, pid, seq, 0, cmd);
+	BUG_ON(retval < 0);
+	return skb;
+}
+
+static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	struct ovs_header *ovs_header = info->userhdr;
+	struct sw_flow_key key;
+	struct sw_flow *flow;
+	struct sk_buff *reply;
+	struct datapath *dp;
+	struct flow_table *table;
+	int error;
+	int key_len;
+
+	/* Extract key. */
+	error = -EINVAL;
+	if (!a[OVS_FLOW_ATTR_KEY])
+		goto error;
+	error = ovs_flow_from_nlattrs(&key, &key_len, a[OVS_FLOW_ATTR_KEY]);
+	if (error)
+		goto error;
+
+	/* Validate actions. */
+	if (a[OVS_FLOW_ATTR_ACTIONS]) {
+		error = validate_actions(a[OVS_FLOW_ATTR_ACTIONS], &key,  0);
+		if (error)
+			goto error;
+	} else if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW) {
+		error = -EINVAL;
+		goto error;
+	}
+
+	dp = get_dp(ovs_header->dp_ifindex);
+	error = -ENODEV;
+	if (!dp)
+		goto error;
+
+	table = genl_dereference(dp->table);
+	flow = ovs_flow_tbl_lookup(table, &key, key_len);
+	if (!flow) {
+		struct sw_flow_actions *acts;
+
+		/* Bail out if we're not allowed to create a new flow. */
+		error = -ENOENT;
+		if (info->genlhdr->cmd == OVS_FLOW_CMD_SET)
+			goto error;
+
+		/* Expand table, if necessary, to make room. */
+		if (ovs_flow_tbl_need_to_expand(table)) {
+			struct flow_table *new_table;
+
+			new_table = ovs_flow_tbl_expand(table);
+			if (!IS_ERR(new_table)) {
+				rcu_assign_pointer(dp->table, new_table);
+				ovs_flow_tbl_deferred_destroy(table);
+				table = genl_dereference(dp->table);
+			}
+		}
+
+		/* Allocate flow. */
+		flow = ovs_flow_alloc();
+		if (IS_ERR(flow)) {
+			error = PTR_ERR(flow);
+			goto error;
+		}
+		flow->key = key;
+		clear_stats(flow);
+
+		/* Obtain actions. */
+		acts = ovs_flow_actions_alloc(a[OVS_FLOW_ATTR_ACTIONS]);
+		error = PTR_ERR(acts);
+		if (IS_ERR(acts))
+			goto error_free_flow;
+		rcu_assign_pointer(flow->sf_acts, acts);
+
+		/* Put flow in bucket. */
+		flow->hash = ovs_flow_hash(&key, key_len);
+		ovs_flow_tbl_insert(table, flow);
+
+		reply = ovs_flow_cmd_build_info(flow, dp, info->snd_pid,
+						info->snd_seq,
+						OVS_FLOW_CMD_NEW);
+	} else {
+		/* We found a matching flow. */
+		struct sw_flow_actions *old_acts;
+		struct nlattr *acts_attrs;
+
+		/* Bail out if we're not allowed to modify an existing flow.
+		 * We accept NLM_F_CREATE in place of the intended NLM_F_EXCL
+		 * because Generic Netlink treats the latter as a dump
+		 * request.  We also accept NLM_F_EXCL in case that bug ever
+		 * gets fixed.
+		 */
+		error = -EEXIST;
+		if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW &&
+		    info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL))
+			goto error;
+
+		/* Update actions. */
+		old_acts = rcu_dereference_protected(flow->sf_acts,
+						     lockdep_genl_is_held());
+		acts_attrs = a[OVS_FLOW_ATTR_ACTIONS];
+		if (acts_attrs &&
+		   (old_acts->actions_len != nla_len(acts_attrs) ||
+		   memcmp(old_acts->actions, nla_data(acts_attrs),
+			  old_acts->actions_len))) {
+			struct sw_flow_actions *new_acts;
+
+			new_acts = ovs_flow_actions_alloc(acts_attrs);
+			error = PTR_ERR(new_acts);
+			if (IS_ERR(new_acts))
+				goto error;
+
+			rcu_assign_pointer(flow->sf_acts, new_acts);
+			ovs_flow_deferred_free_acts(old_acts);
+		}
+
+		reply = ovs_flow_cmd_build_info(flow, dp, info->snd_pid,
+					       info->snd_seq, OVS_FLOW_CMD_NEW);
+
+		/* Clear stats. */
+		if (a[OVS_FLOW_ATTR_CLEAR]) {
+			spin_lock_bh(&flow->lock);
+			clear_stats(flow);
+			spin_unlock_bh(&flow->lock);
+		}
+	}
+
+	if (!IS_ERR(reply))
+		genl_notify(reply, genl_info_net(info), info->snd_pid,
+			   ovs_dp_flow_multicast_group.id, info->nlhdr,
+			   GFP_KERNEL);
+	else
+		netlink_set_err(init_net.genl_sock, 0,
+				ovs_dp_flow_multicast_group.id, PTR_ERR(reply));
+	return 0;
+
+error_free_flow:
+	ovs_flow_free(flow);
+error:
+	return error;
+}
+
+static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	struct ovs_header *ovs_header = info->userhdr;
+	struct sw_flow_key key;
+	struct sk_buff *reply;
+	struct sw_flow *flow;
+	struct datapath *dp;
+	struct flow_table *table;
+	int err;
+	int key_len;
+
+	if (!a[OVS_FLOW_ATTR_KEY])
+		return -EINVAL;
+	err = ovs_flow_from_nlattrs(&key, &key_len, a[OVS_FLOW_ATTR_KEY]);
+	if (err)
+		return err;
+
+	dp = get_dp(ovs_header->dp_ifindex);
+	if (!dp)
+		return -ENODEV;
+
+	table = genl_dereference(dp->table);
+	flow = ovs_flow_tbl_lookup(table, &key, key_len);
+	if (!flow)
+		return -ENOENT;
+
+	reply = ovs_flow_cmd_build_info(flow, dp, info->snd_pid,
+					info->snd_seq, OVS_FLOW_CMD_NEW);
+	if (IS_ERR(reply))
+		return PTR_ERR(reply);
+
+	return genlmsg_reply(reply, info);
+}
+
+static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	struct ovs_header *ovs_header = info->userhdr;
+	struct sw_flow_key key;
+	struct sk_buff *reply;
+	struct sw_flow *flow;
+	struct datapath *dp;
+	struct flow_table *table;
+	int err;
+	int key_len;
+
+	if (!a[OVS_FLOW_ATTR_KEY])
+		return flush_flows(ovs_header->dp_ifindex);
+	err = ovs_flow_from_nlattrs(&key, &key_len, a[OVS_FLOW_ATTR_KEY]);
+	if (err)
+		return err;
+
+	dp = get_dp(ovs_header->dp_ifindex);
+	if (!dp)
+		return -ENODEV;
+
+	table = genl_dereference(dp->table);
+	flow = ovs_flow_tbl_lookup(table, &key, key_len);
+	if (!flow)
+		return -ENOENT;
+
+	reply = ovs_flow_cmd_alloc_info(flow);
+	if (!reply)
+		return -ENOMEM;
+
+	ovs_flow_tbl_remove(table, flow);
+
+	err = ovs_flow_cmd_fill_info(flow, dp, reply, info->snd_pid,
+				     info->snd_seq, 0, OVS_FLOW_CMD_DEL);
+	BUG_ON(err < 0);
+
+	ovs_flow_deferred_free(flow);
+
+	genl_notify(reply, genl_info_net(info), info->snd_pid,
+		    ovs_dp_flow_multicast_group.id, info->nlhdr, GFP_KERNEL);
+	return 0;
+}
+
+static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct ovs_header *ovs_header = genlmsg_data(nlmsg_data(cb->nlh));
+	struct datapath *dp;
+	struct flow_table *table;
+
+	dp = get_dp(ovs_header->dp_ifindex);
+	if (!dp)
+		return -ENODEV;
+
+	table = genl_dereference(dp->table);
+
+	for (;;) {
+		struct sw_flow *flow;
+		u32 bucket, obj;
+
+		bucket = cb->args[0];
+		obj = cb->args[1];
+		flow = ovs_flow_tbl_next(table, &bucket, &obj);
+		if (!flow)
+			break;
+
+		if (ovs_flow_cmd_fill_info(flow, dp, skb,
+					   NETLINK_CB(cb->skb).pid,
+					   cb->nlh->nlmsg_seq, NLM_F_MULTI,
+					   OVS_FLOW_CMD_NEW) < 0)
+			break;
+
+		cb->args[0] = bucket;
+		cb->args[1] = obj;
+	}
+	return skb->len;
+}
+
+static struct genl_ops dp_flow_genl_ops[] = {
+	{ .cmd = OVS_FLOW_CMD_NEW,
+	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+	  .policy = flow_policy,
+	  .doit = ovs_flow_cmd_new_or_set
+	},
+	{ .cmd = OVS_FLOW_CMD_DEL,
+	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+	  .policy = flow_policy,
+	  .doit = ovs_flow_cmd_del
+	},
+	{ .cmd = OVS_FLOW_CMD_GET,
+	  .flags = 0,		    /* OK for unprivileged users. */
+	  .policy = flow_policy,
+	  .doit = ovs_flow_cmd_get,
+	  .dumpit = ovs_flow_cmd_dump
+	},
+	{ .cmd = OVS_FLOW_CMD_SET,
+	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+	  .policy = flow_policy,
+	  .doit = ovs_flow_cmd_new_or_set,
+	},
+};
+
+static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
+	[OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
+	[OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 },
+};
+
+static struct genl_family dp_datapath_genl_family = {
+	.id = GENL_ID_GENERATE,
+	.hdrsize = sizeof(struct ovs_header),
+	.name = OVS_DATAPATH_FAMILY,
+	.version = OVS_DATAPATH_VERSION,
+	.maxattr = OVS_DP_ATTR_MAX
+};
+
+static struct genl_multicast_group ovs_dp_datapath_multicast_group = {
+	.name = OVS_DATAPATH_MCGROUP
+};
+
+static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
+				u32 pid, u32 seq, u32 flags, u8 cmd)
+{
+	struct ovs_header *ovs_header;
+	struct ovs_dp_stats dp_stats;
+	int err;
+
+	ovs_header = genlmsg_put(skb, pid, seq, &dp_datapath_genl_family,
+				   flags, cmd);
+	if (!ovs_header)
+		goto error;
+
+	ovs_header->dp_ifindex = get_dpifindex(dp);
+
+	rcu_read_lock();
+	err = nla_put_string(skb, OVS_DP_ATTR_NAME, ovs_dp_name(dp));
+	rcu_read_unlock();
+	if (err)
+		goto nla_put_failure;
+
+	get_dp_stats(dp, &dp_stats);
+	NLA_PUT(skb, OVS_DP_ATTR_STATS, sizeof(struct ovs_dp_stats), &dp_stats);
+
+	return genlmsg_end(skb, ovs_header);
+
+nla_put_failure:
+	genlmsg_cancel(skb, ovs_header);
+error:
+	return -EMSGSIZE;
+}
+
+static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, u32 pid,
+					     u32 seq, u8 cmd)
+{
+	struct sk_buff *skb;
+	int retval;
+
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	retval = ovs_dp_cmd_fill_info(dp, skb, pid, seq, 0, cmd);
+	if (retval < 0) {
+		kfree_skb(skb);
+		return ERR_PTR(retval);
+	}
+	return skb;
+}
+
+/* Called with genl_mutex and optionally with RTNL lock also. */
+static struct datapath *lookup_datapath(struct ovs_header *ovs_header,
+					struct nlattr *a[OVS_DP_ATTR_MAX + 1])
+{
+	struct datapath *dp;
+
+	if (!a[OVS_DP_ATTR_NAME])
+		dp = get_dp(ovs_header->dp_ifindex);
+	else {
+		struct vport *vport;
+
+		rcu_read_lock();
+		vport = ovs_vport_locate(nla_data(a[OVS_DP_ATTR_NAME]));
+		dp = vport && vport->port_no == OVSP_LOCAL ? vport->dp : NULL;
+		rcu_read_unlock();
+	}
+	return dp ? dp : ERR_PTR(-ENODEV);
+}
+
+static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	struct vport_parms parms;
+	struct sk_buff *reply;
+	struct datapath *dp;
+	struct vport *vport;
+	int err;
+
+	err = -EINVAL;
+	if (!a[OVS_DP_ATTR_NAME] || !a[OVS_DP_ATTR_UPCALL_PID])
+		goto err;
+
+	rtnl_lock();
+	err = -ENODEV;
+	if (!try_module_get(THIS_MODULE))
+		goto err_unlock_rtnl;
+
+	err = -ENOMEM;
+	dp = kzalloc(sizeof(*dp), GFP_KERNEL);
+	if (dp == NULL)
+		goto err_put_module;
+	INIT_LIST_HEAD(&dp->port_list);
+
+	/* Allocate table. */
+	err = -ENOMEM;
+	rcu_assign_pointer(dp->table, ovs_flow_tbl_alloc(TBL_MIN_BUCKETS));
+	if (!dp->table)
+		goto err_free_dp;
+
+	dp->stats_percpu = alloc_percpu(struct dp_stats_percpu);
+	if (!dp->stats_percpu) {
+		err = -ENOMEM;
+		goto err_destroy_table;
+	}
+
+	/* Set up our datapath device. */
+	parms.name = nla_data(a[OVS_DP_ATTR_NAME]);
+	parms.type = OVS_VPORT_TYPE_INTERNAL;
+	parms.options = NULL;
+	parms.dp = dp;
+	parms.port_no = OVSP_LOCAL;
+	parms.upcall_pid = nla_get_u32(a[OVS_DP_ATTR_UPCALL_PID]);
+
+	vport = new_vport(&parms);
+	if (IS_ERR(vport)) {
+		err = PTR_ERR(vport);
+		if (err == -EBUSY)
+			err = -EEXIST;
+
+		goto err_destroy_percpu;
+	}
+
+	reply = ovs_dp_cmd_build_info(dp, info->snd_pid,
+				      info->snd_seq, OVS_DP_CMD_NEW);
+	err = PTR_ERR(reply);
+	if (IS_ERR(reply))
+		goto err_destroy_local_port;
+
+	list_add_tail(&dp->list_node, &dps);
+	rtnl_unlock();
+
+	genl_notify(reply, genl_info_net(info), info->snd_pid,
+		    ovs_dp_datapath_multicast_group.id, info->nlhdr,
+		    GFP_KERNEL);
+	return 0;
+
+err_destroy_local_port:
+	ovs_dp_detach_port(rtnl_dereference(dp->ports[OVSP_LOCAL]));
+err_destroy_percpu:
+	free_percpu(dp->stats_percpu);
+err_destroy_table:
+	ovs_flow_tbl_destroy(genl_dereference(dp->table));
+err_free_dp:
+	kfree(dp);
+err_put_module:
+	module_put(THIS_MODULE);
+err_unlock_rtnl:
+	rtnl_unlock();
+err:
+	return err;
+}
+
+static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info)
+{
+	struct vport *vport, *next_vport;
+	struct sk_buff *reply;
+	struct datapath *dp;
+	int err;
+
+	rtnl_lock();
+	dp = lookup_datapath(info->userhdr, info->attrs);
+	err = PTR_ERR(dp);
+	if (IS_ERR(dp))
+		goto exit_unlock;
+
+	reply = ovs_dp_cmd_build_info(dp, info->snd_pid,
+				      info->snd_seq, OVS_DP_CMD_DEL);
+	err = PTR_ERR(reply);
+	if (IS_ERR(reply))
+		goto exit_unlock;
+
+	list_for_each_entry_safe(vport, next_vport, &dp->port_list, node)
+		if (vport->port_no != OVSP_LOCAL)
+			ovs_dp_detach_port(vport);
+
+	list_del(&dp->list_node);
+	ovs_dp_detach_port(rtnl_dereference(dp->ports[OVSP_LOCAL]));
+
+	/* rtnl_unlock() will wait until all the references to devices that
+	 * are pending unregistration have been dropped.  We do it here to
+	 * ensure that any internal devices (which contain DP pointers) are
+	 * fully destroyed before freeing the datapath.
+	 */
+	rtnl_unlock();
+
+	call_rcu(&dp->rcu, destroy_dp_rcu);
+	module_put(THIS_MODULE);
+
+	genl_notify(reply, genl_info_net(info), info->snd_pid,
+		    ovs_dp_datapath_multicast_group.id, info->nlhdr,
+		    GFP_KERNEL);
+
+	return 0;
+
+exit_unlock:
+	rtnl_unlock();
+	return err;
+}
+
+static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info)
+{
+	struct sk_buff *reply;
+	struct datapath *dp;
+	int err;
+
+	dp = lookup_datapath(info->userhdr, info->attrs);
+	if (IS_ERR(dp))
+		return PTR_ERR(dp);
+
+	reply = ovs_dp_cmd_build_info(dp, info->snd_pid,
+				      info->snd_seq, OVS_DP_CMD_NEW);
+	if (IS_ERR(reply)) {
+		err = PTR_ERR(reply);
+		netlink_set_err(init_net.genl_sock, 0,
+				ovs_dp_datapath_multicast_group.id, err);
+		return 0;
+	}
+
+	genl_notify(reply, genl_info_net(info), info->snd_pid,
+		    ovs_dp_datapath_multicast_group.id, info->nlhdr,
+		    GFP_KERNEL);
+
+	return 0;
+}
+
+static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info)
+{
+	struct sk_buff *reply;
+	struct datapath *dp;
+
+	dp = lookup_datapath(info->userhdr, info->attrs);
+	if (IS_ERR(dp))
+		return PTR_ERR(dp);
+
+	reply = ovs_dp_cmd_build_info(dp, info->snd_pid,
+				      info->snd_seq, OVS_DP_CMD_NEW);
+	if (IS_ERR(reply))
+		return PTR_ERR(reply);
+
+	return genlmsg_reply(reply, info);
+}
+
+static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct datapath *dp;
+	int skip = cb->args[0];
+	int i = 0;
+
+	list_for_each_entry(dp, &dps, list_node) {
+		if (i < skip)
+			continue;
+		if (ovs_dp_cmd_fill_info(dp, skb, NETLINK_CB(cb->skb).pid,
+					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
+					 OVS_DP_CMD_NEW) < 0)
+			break;
+		i++;
+	}
+
+	cb->args[0] = i;
+
+	return skb->len;
+}
+
+static struct genl_ops dp_datapath_genl_ops[] = {
+	{ .cmd = OVS_DP_CMD_NEW,
+	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+	  .policy = datapath_policy,
+	  .doit = ovs_dp_cmd_new
+	},
+	{ .cmd = OVS_DP_CMD_DEL,
+	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+	  .policy = datapath_policy,
+	  .doit = ovs_dp_cmd_del
+	},
+	{ .cmd = OVS_DP_CMD_GET,
+	  .flags = 0,		    /* OK for unprivileged users. */
+	  .policy = datapath_policy,
+	  .doit = ovs_dp_cmd_get,
+	  .dumpit = ovs_dp_cmd_dump
+	},
+	{ .cmd = OVS_DP_CMD_SET,
+	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+	  .policy = datapath_policy,
+	  .doit = ovs_dp_cmd_set,
+	},
+};
+
+static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
+	[OVS_VPORT_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 },
+	[OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) },
+	[OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 },
+	[OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 },
+	[OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 },
+	[OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED },
+};
+
+static struct genl_family dp_vport_genl_family = {
+	.id = GENL_ID_GENERATE,
+	.hdrsize = sizeof(struct ovs_header),
+	.name = OVS_VPORT_FAMILY,
+	.version = OVS_VPORT_VERSION,
+	.maxattr = OVS_VPORT_ATTR_MAX
+};
+
+struct genl_multicast_group ovs_dp_vport_multicast_group = {
+	.name = OVS_VPORT_MCGROUP
+};
+
+/* Called with RTNL lock or RCU read lock. */
+static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb,
+				   u32 pid, u32 seq, u32 flags, u8 cmd)
+{
+	struct ovs_header *ovs_header;
+	struct ovs_vport_stats vport_stats;
+	int err;
+
+	ovs_header = genlmsg_put(skb, pid, seq, &dp_vport_genl_family,
+				 flags, cmd);
+	if (!ovs_header)
+		return -EMSGSIZE;
+
+	ovs_header->dp_ifindex = get_dpifindex(vport->dp);
+
+	NLA_PUT_U32(skb, OVS_VPORT_ATTR_PORT_NO, vport->port_no);
+	NLA_PUT_U32(skb, OVS_VPORT_ATTR_TYPE, vport->ops->type);
+	NLA_PUT_STRING(skb, OVS_VPORT_ATTR_NAME, vport->ops->get_name(vport));
+	NLA_PUT_U32(skb, OVS_VPORT_ATTR_UPCALL_PID, vport->upcall_pid);
+
+	ovs_vport_get_stats(vport, &vport_stats);
+	NLA_PUT(skb, OVS_VPORT_ATTR_STATS, sizeof(struct ovs_vport_stats),
+		&vport_stats);
+
+	err = ovs_vport_get_options(vport, skb);
+	if (err == -EMSGSIZE)
+		goto error;
+
+	return genlmsg_end(skb, ovs_header);
+
+nla_put_failure:
+	err = -EMSGSIZE;
+error:
+	genlmsg_cancel(skb, ovs_header);
+	return err;
+}
+
+/* Called with RTNL lock or RCU read lock. */
+struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 pid,
+					 u32 seq, u8 cmd)
+{
+	struct sk_buff *skb;
+	int retval;
+
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+
+	retval = ovs_vport_cmd_fill_info(vport, skb, pid, seq, 0, cmd);
+	if (retval < 0) {
+		kfree_skb(skb);
+		return ERR_PTR(retval);
+	}
+	return skb;
+}
+
+/* Called with RTNL lock or RCU read lock. */
+static struct vport *lookup_vport(struct ovs_header *ovs_header,
+				  struct nlattr *a[OVS_VPORT_ATTR_MAX + 1])
+{
+	struct datapath *dp;
+	struct vport *vport;
+
+	if (a[OVS_VPORT_ATTR_NAME]) {
+		vport = ovs_vport_locate(nla_data(a[OVS_VPORT_ATTR_NAME]));
+		if (!vport)
+			return ERR_PTR(-ENODEV);
+		return vport;
+	} else if (a[OVS_VPORT_ATTR_PORT_NO]) {
+		u32 port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]);
+
+		if (port_no >= DP_MAX_PORTS)
+			return ERR_PTR(-EFBIG);
+
+		dp = get_dp(ovs_header->dp_ifindex);
+		if (!dp)
+			return ERR_PTR(-ENODEV);
+
+		vport = rcu_dereference_rtnl(dp->ports[port_no]);
+		if (!vport)
+			return ERR_PTR(-ENOENT);
+		return vport;
+	} else
+		return ERR_PTR(-EINVAL);
+}
+
+static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	struct ovs_header *ovs_header = info->userhdr;
+	struct vport_parms parms;
+	struct sk_buff *reply;
+	struct vport *vport;
+	struct datapath *dp;
+	u32 port_no;
+	int err;
+
+	err = -EINVAL;
+	if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] ||
+	    !a[OVS_VPORT_ATTR_UPCALL_PID])
+		goto exit;
+
+	rtnl_lock();
+	dp = get_dp(ovs_header->dp_ifindex);
+	err = -ENODEV;
+	if (!dp)
+		goto exit_unlock;
+
+	if (a[OVS_VPORT_ATTR_PORT_NO]) {
+		port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]);
+
+		err = -EFBIG;
+		if (port_no >= DP_MAX_PORTS)
+			goto exit_unlock;
+
+		vport = rtnl_dereference(dp->ports[port_no]);
+		err = -EBUSY;
+		if (vport)
+			goto exit_unlock;
+	} else {
+		for (port_no = 1; ; port_no++) {
+			if (port_no >= DP_MAX_PORTS) {
+				err = -EFBIG;
+				goto exit_unlock;
+			}
+			vport = rtnl_dereference(dp->ports[port_no]);
+			if (!vport)
+				break;
+		}
+	}
+
+	parms.name = nla_data(a[OVS_VPORT_ATTR_NAME]);
+	parms.type = nla_get_u32(a[OVS_VPORT_ATTR_TYPE]);
+	parms.options = a[OVS_VPORT_ATTR_OPTIONS];
+	parms.dp = dp;
+	parms.port_no = port_no;
+	parms.upcall_pid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]);
+
+	vport = new_vport(&parms);
+	err = PTR_ERR(vport);
+	if (IS_ERR(vport))
+		goto exit_unlock;
+
+	reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq,
+					 OVS_VPORT_CMD_NEW);
+	if (IS_ERR(reply)) {
+		err = PTR_ERR(reply);
+		ovs_dp_detach_port(vport);
+		goto exit_unlock;
+	}
+	genl_notify(reply, genl_info_net(info), info->snd_pid,
+		    ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL);
+
+exit_unlock:
+	rtnl_unlock();
+exit:
+	return err;
+}
+
+static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	struct sk_buff *reply;
+	struct vport *vport;
+	int err;
+
+	rtnl_lock();
+	vport = lookup_vport(info->userhdr, a);
+	err = PTR_ERR(vport);
+	if (IS_ERR(vport))
+		goto exit_unlock;
+
+	err = 0;
+	if (a[OVS_VPORT_ATTR_TYPE] &&
+	    nla_get_u32(a[OVS_VPORT_ATTR_TYPE]) != vport->ops->type)
+		err = -EINVAL;
+
+	if (!err && a[OVS_VPORT_ATTR_OPTIONS])
+		err = ovs_vport_set_options(vport, a[OVS_VPORT_ATTR_OPTIONS]);
+	if (!err && a[OVS_VPORT_ATTR_UPCALL_PID])
+		vport->upcall_pid = nla_get_u32(a[OVS_VPORT_ATTR_UPCALL_PID]);
+
+	reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq,
+					 OVS_VPORT_CMD_NEW);
+	if (IS_ERR(reply)) {
+		err = PTR_ERR(reply);
+		netlink_set_err(init_net.genl_sock, 0,
+				ovs_dp_vport_multicast_group.id, err);
+		return 0;
+	}
+
+	genl_notify(reply, genl_info_net(info), info->snd_pid,
+		    ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL);
+
+exit_unlock:
+	rtnl_unlock();
+	return err;
+}
+
+static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	struct sk_buff *reply;
+	struct vport *vport;
+	int err;
+
+	rtnl_lock();
+	vport = lookup_vport(info->userhdr, a);
+	err = PTR_ERR(vport);
+	if (IS_ERR(vport))
+		goto exit_unlock;
+
+	if (vport->port_no == OVSP_LOCAL) {
+		err = -EINVAL;
+		goto exit_unlock;
+	}
+
+	reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq,
+					 OVS_VPORT_CMD_DEL);
+	err = PTR_ERR(reply);
+	if (IS_ERR(reply))
+		goto exit_unlock;
+
+	ovs_dp_detach_port(vport);
+
+	genl_notify(reply, genl_info_net(info), info->snd_pid,
+		    ovs_dp_vport_multicast_group.id, info->nlhdr, GFP_KERNEL);
+
+exit_unlock:
+	rtnl_unlock();
+	return err;
+}
+
+static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info)
+{
+	struct nlattr **a = info->attrs;
+	struct ovs_header *ovs_header = info->userhdr;
+	struct sk_buff *reply;
+	struct vport *vport;
+	int err;
+
+	rcu_read_lock();
+	vport = lookup_vport(ovs_header, a);
+	err = PTR_ERR(vport);
+	if (IS_ERR(vport))
+		goto exit_unlock;
+
+	reply = ovs_vport_cmd_build_info(vport, info->snd_pid, info->snd_seq,
+					 OVS_VPORT_CMD_NEW);
+	err = PTR_ERR(reply);
+	if (IS_ERR(reply))
+		goto exit_unlock;
+
+	rcu_read_unlock();
+
+	return genlmsg_reply(reply, info);
+
+exit_unlock:
+	rcu_read_unlock();
+	return err;
+}
+
+static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct ovs_header *ovs_header = genlmsg_data(nlmsg_data(cb->nlh));
+	struct datapath *dp;
+	u32 port_no;
+	int retval;
+
+	dp = get_dp(ovs_header->dp_ifindex);
+	if (!dp)
+		return -ENODEV;
+
+	rcu_read_lock();
+	for (port_no = cb->args[0]; port_no < DP_MAX_PORTS; port_no++) {
+		struct vport *vport;
+
+		vport = rcu_dereference(dp->ports[port_no]);
+		if (!vport)
+			continue;
+
+		if (ovs_vport_cmd_fill_info(vport, skb, NETLINK_CB(cb->skb).pid,
+					    cb->nlh->nlmsg_seq, NLM_F_MULTI,
+					    OVS_VPORT_CMD_NEW) < 0)
+			break;
+	}
+	rcu_read_unlock();
+
+	cb->args[0] = port_no;
+	retval = skb->len;
+
+	return retval;
+}
+
+static void rehash_flow_table(struct work_struct *work)
+{
+	struct datapath *dp;
+
+	genl_lock();
+
+	list_for_each_entry(dp, &dps, list_node) {
+		struct flow_table *old_table = genl_dereference(dp->table);
+		struct flow_table *new_table;
+
+		new_table = ovs_flow_tbl_rehash(old_table);
+		if (!IS_ERR(new_table)) {
+			rcu_assign_pointer(dp->table, new_table);
+			ovs_flow_tbl_deferred_destroy(old_table);
+		}
+	}
+
+	genl_unlock();
+
+	schedule_delayed_work(&rehash_flow_wq, REHASH_FLOW_INTERVAL);
+}
+
+static struct genl_ops dp_vport_genl_ops[] = {
+	{ .cmd = OVS_VPORT_CMD_NEW,
+	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+	  .policy = vport_policy,
+	  .doit = ovs_vport_cmd_new
+	},
+	{ .cmd = OVS_VPORT_CMD_DEL,
+	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+	  .policy = vport_policy,
+	  .doit = ovs_vport_cmd_del
+	},
+	{ .cmd = OVS_VPORT_CMD_GET,
+	  .flags = 0,		    /* OK for unprivileged users. */
+	  .policy = vport_policy,
+	  .doit = ovs_vport_cmd_get,
+	  .dumpit = ovs_vport_cmd_dump
+	},
+	{ .cmd = OVS_VPORT_CMD_SET,
+	  .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
+	  .policy = vport_policy,
+	  .doit = ovs_vport_cmd_set,
+	},
+};
+
+struct genl_family_and_ops {
+	struct genl_family *family;
+	struct genl_ops *ops;
+	int n_ops;
+	struct genl_multicast_group *group;
+};
+
+static const struct genl_family_and_ops dp_genl_families[] = {
+	{ &dp_datapath_genl_family,
+	  dp_datapath_genl_ops, ARRAY_SIZE(dp_datapath_genl_ops),
+	  &ovs_dp_datapath_multicast_group },
+	{ &dp_vport_genl_family,
+	  dp_vport_genl_ops, ARRAY_SIZE(dp_vport_genl_ops),
+	  &ovs_dp_vport_multicast_group },
+	{ &dp_flow_genl_family,
+	  dp_flow_genl_ops, ARRAY_SIZE(dp_flow_genl_ops),
+	  &ovs_dp_flow_multicast_group },
+	{ &dp_packet_genl_family,
+	  dp_packet_genl_ops, ARRAY_SIZE(dp_packet_genl_ops),
+	  NULL },
+};
+
+static void dp_unregister_genl(int n_families)
+{
+	int i;
+
+	for (i = 0; i < n_families; i++)
+		genl_unregister_family(dp_genl_families[i].family);
+}
+
+static int dp_register_genl(void)
+{
+	int n_registered;
+	int err;
+	int i;
+
+	n_registered = 0;
+	for (i = 0; i < ARRAY_SIZE(dp_genl_families); i++) {
+		const struct genl_family_and_ops *f = &dp_genl_families[i];
+
+		err = genl_register_family_with_ops(f->family, f->ops,
+						    f->n_ops);
+		if (err)
+			goto error;
+		n_registered++;
+
+		if (f->group) {
+			err = genl_register_mc_group(f->family, f->group);
+			if (err)
+				goto error;
+		}
+	}
+
+	return 0;
+
+error:
+	dp_unregister_genl(n_registered);
+	return err;
+}
+
+static int __init dp_init(void)
+{
+	struct sk_buff *dummy_skb;
+	int err;
+
+	BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof(dummy_skb->cb));
+
+	pr_info("Open vSwitch switching datapath\n");
+
+	err = ovs_flow_init();
+	if (err)
+		goto error;
+
+	err = ovs_vport_init();
+	if (err)
+		goto error_flow_exit;
+
+	err = register_netdevice_notifier(&ovs_dp_device_notifier);
+	if (err)
+		goto error_vport_exit;
+
+	err = dp_register_genl();
+	if (err < 0)
+		goto error_unreg_notifier;
+
+	schedule_delayed_work(&rehash_flow_wq, REHASH_FLOW_INTERVAL);
+
+	return 0;
+
+error_unreg_notifier:
+	unregister_netdevice_notifier(&ovs_dp_device_notifier);
+error_vport_exit:
+	ovs_vport_exit();
+error_flow_exit:
+	ovs_flow_exit();
+error:
+	return err;
+}
+
+static void dp_cleanup(void)
+{
+	cancel_delayed_work_sync(&rehash_flow_wq);
+	rcu_barrier();
+	dp_unregister_genl(ARRAY_SIZE(dp_genl_families));
+	unregister_netdevice_notifier(&ovs_dp_device_notifier);
+	ovs_vport_exit();
+	ovs_flow_exit();
+}
+
+module_init(dp_init);
+module_exit(dp_cleanup);
+
+MODULE_DESCRIPTION("Open vSwitch switching datapath");
+MODULE_LICENSE("GPL");
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
new file mode 100644
index 0000000..5b9f884
--- /dev/null
+++ b/net/openvswitch/datapath.h
@@ -0,0 +1,125 @@
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef DATAPATH_H
+#define DATAPATH_H 1
+
+#include <asm/page.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/u64_stats_sync.h>
+#include <linux/version.h>
+
+#include "flow.h"
+
+struct vport;
+
+#define DP_MAX_PORTS 1024
+#define SAMPLE_ACTION_DEPTH 3
+
+/**
+ * struct dp_stats_percpu - per-cpu packet processing statistics for a given
+ * datapath.
+ * @n_hit: Number of received packets for which a matching flow was found in
+ * the flow table.
+ * @n_miss: Number of received packets that had no matching flow in the flow
+ * table.  The sum of @n_hit and @n_miss is the number of packets that have
+ * been received by the datapath.
+ * @n_lost: Number of received packets that had no matching flow in the flow
+ * table that could not be sent to userspace (normally due to an overflow in
+ * one of the datapath's queues).
+ */
+struct dp_stats_percpu {
+	u64 n_hit;
+	u64 n_missed;
+	u64 n_lost;
+	struct u64_stats_sync sync;
+};
+
+/**
+ * struct datapath - datapath for flow-based packet switching
+ * @rcu: RCU callback head for deferred destruction.
+ * @list_node: Element in global 'dps' list.
+ * @n_flows: Number of flows currently in flow table.
+ * @table: Current flow table.  Protected by genl_lock and RCU.
+ * @ports: Map from port number to &struct vport.  %OVSP_LOCAL port
+ * always exists, other ports may be %NULL.  Protected by RTNL and RCU.
+ * @port_list: List of all ports in @ports in arbitrary order.  RTNL required
+ * to iterate or modify.
+ * @stats_percpu: Per-CPU datapath statistics.
+ *
+ * Context: See the comment on locking at the top of datapath.c for additional
+ * locking information.
+ */
+struct datapath {
+	struct rcu_head rcu;
+	struct list_head list_node;
+
+	/* Flow table. */
+	struct flow_table __rcu *table;
+
+	/* Switch ports. */
+	struct vport __rcu *ports[DP_MAX_PORTS];
+	struct list_head port_list;
+
+	/* Stats. */
+	struct dp_stats_percpu __percpu *stats_percpu;
+};
+
+/**
+ * struct ovs_skb_cb - OVS data in skb CB
+ * @flow: The flow associated with this packet.  May be %NULL if no flow.
+ */
+struct ovs_skb_cb {
+	struct sw_flow		*flow;
+};
+#define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
+
+/**
+ * struct dp_upcall - metadata to include with a packet to send to userspace
+ * @cmd: One of %OVS_PACKET_CMD_*.
+ * @key: Becomes %OVS_PACKET_ATTR_KEY.  Must be nonnull.
+ * @userdata: If nonnull, its u64 value is extracted and passed to userspace as
+ * %OVS_PACKET_ATTR_USERDATA.
+ * @pid: Netlink PID to which packet should be sent.  If @pid is 0 then no
+ * packet is sent and the packet is accounted in the datapath's @n_lost
+ * counter.
+ */
+struct dp_upcall_info {
+	u8 cmd;
+	const struct sw_flow_key *key;
+	const struct nlattr *userdata;
+	u32 pid;
+};
+
+extern struct notifier_block ovs_dp_device_notifier;
+extern struct genl_multicast_group ovs_dp_vport_multicast_group;
+
+void ovs_dp_process_received_packet(struct vport *, struct sk_buff *);
+void ovs_dp_detach_port(struct vport *);
+int ovs_dp_upcall(struct datapath *, struct sk_buff *,
+		  const struct dp_upcall_info *);
+
+const char *ovs_dp_name(const struct datapath *dp);
+struct sk_buff *ovs_vport_cmd_build_info(struct vport *, u32 pid, u32 seq,
+					 u8 cmd);
+
+int ovs_execute_actions(struct datapath *dp, struct sk_buff *skb);
+#endif /* datapath.h */
diff --git a/net/openvswitch/dp_notify.c b/net/openvswitch/dp_notify.c
new file mode 100644
index 0000000..4673651
--- /dev/null
+++ b/net/openvswitch/dp_notify.c
@@ -0,0 +1,66 @@
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include <linux/netdevice.h>
+#include <net/genetlink.h>
+
+#include "datapath.h"
+#include "vport-internal_dev.h"
+#include "vport-netdev.h"
+
+static int dp_device_event(struct notifier_block *unused, unsigned long event,
+			   void *ptr)
+{
+	struct net_device *dev = ptr;
+	struct vport *vport;
+
+	if (ovs_is_internal_dev(dev))
+		vport = ovs_internal_dev_get_vport(dev);
+	else
+		vport = ovs_netdev_get_vport(dev);
+
+	if (!vport)
+		return NOTIFY_DONE;
+
+	switch (event) {
+	case NETDEV_UNREGISTER:
+		if (!ovs_is_internal_dev(dev)) {
+			struct sk_buff *notify;
+
+			notify = ovs_vport_cmd_build_info(vport, 0, 0,
+							  OVS_VPORT_CMD_DEL);
+			ovs_dp_detach_port(vport);
+			if (IS_ERR(notify)) {
+				netlink_set_err(init_net.genl_sock, 0,
+						ovs_dp_vport_multicast_group.id,
+						PTR_ERR(notify));
+				break;
+			}
+
+			genlmsg_multicast(notify, 0, ovs_dp_vport_multicast_group.id,
+					  GFP_KERNEL);
+		}
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+struct notifier_block ovs_dp_device_notifier = {
+	.notifier_call = dp_device_event
+};
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
new file mode 100644
index 0000000..fe7f020
--- /dev/null
+++ b/net/openvswitch/flow.c
@@ -0,0 +1,1346 @@
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include "flow.h"
+#include "datapath.h"
+#include <linux/uaccess.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/if_ether.h>
+#include <linux/if_vlan.h>
+#include <net/llc_pdu.h>
+#include <linux/kernel.h>
+#include <linux/jhash.h>
+#include <linux/jiffies.h>
+#include <linux/llc.h>
+#include <linux/module.h>
+#include <linux/in.h>
+#include <linux/rcupdate.h>
+#include <linux/if_arp.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/rculist.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/ndisc.h>
+
+static struct kmem_cache *flow_cache;
+
+static int check_header(struct sk_buff *skb, int len)
+{
+	if (unlikely(skb->len < len))
+		return -EINVAL;
+	if (unlikely(!pskb_may_pull(skb, len)))
+		return -ENOMEM;
+	return 0;
+}
+
+static bool arphdr_ok(struct sk_buff *skb)
+{
+	return pskb_may_pull(skb, skb_network_offset(skb) +
+				  sizeof(struct arp_eth_header));
+}
+
+static int check_iphdr(struct sk_buff *skb)
+{
+	unsigned int nh_ofs = skb_network_offset(skb);
+	unsigned int ip_len;
+	int err;
+
+	err = check_header(skb, nh_ofs + sizeof(struct iphdr));
+	if (unlikely(err))
+		return err;
+
+	ip_len = ip_hdrlen(skb);
+	if (unlikely(ip_len < sizeof(struct iphdr) ||
+		     skb->len < nh_ofs + ip_len))
+		return -EINVAL;
+
+	skb_set_transport_header(skb, nh_ofs + ip_len);
+	return 0;
+}
+
+static bool tcphdr_ok(struct sk_buff *skb)
+{
+	int th_ofs = skb_transport_offset(skb);
+	int tcp_len;
+
+	if (unlikely(!pskb_may_pull(skb, th_ofs + sizeof(struct tcphdr))))
+		return false;
+
+	tcp_len = tcp_hdrlen(skb);
+	if (unlikely(tcp_len < sizeof(struct tcphdr) ||
+		     skb->len < th_ofs + tcp_len))
+		return false;
+
+	return true;
+}
+
+static bool udphdr_ok(struct sk_buff *skb)
+{
+	return pskb_may_pull(skb, skb_transport_offset(skb) +
+				  sizeof(struct udphdr));
+}
+
+static bool icmphdr_ok(struct sk_buff *skb)
+{
+	return pskb_may_pull(skb, skb_transport_offset(skb) +
+				  sizeof(struct icmphdr));
+}
+
+u64 ovs_flow_used_time(unsigned long flow_jiffies)
+{
+	struct timespec cur_ts;
+	u64 cur_ms, idle_ms;
+
+	ktime_get_ts(&cur_ts);
+	idle_ms = jiffies_to_msecs(jiffies - flow_jiffies);
+	cur_ms = (u64)cur_ts.tv_sec * MSEC_PER_SEC +
+		 cur_ts.tv_nsec / NSEC_PER_MSEC;
+
+	return cur_ms - idle_ms;
+}
+
+#define SW_FLOW_KEY_OFFSET(field)		\
+	(offsetof(struct sw_flow_key, field) +	\
+	 FIELD_SIZEOF(struct sw_flow_key, field))
+
+static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key,
+			 int *key_lenp)
+{
+	unsigned int nh_ofs = skb_network_offset(skb);
+	unsigned int nh_len;
+	int payload_ofs;
+	struct ipv6hdr *nh;
+	uint8_t nexthdr;
+	__be16 frag_off;
+	int err;
+
+	*key_lenp = SW_FLOW_KEY_OFFSET(ipv6.label);
+
+	err = check_header(skb, nh_ofs + sizeof(*nh));
+	if (unlikely(err))
+		return err;
+
+	nh = ipv6_hdr(skb);
+	nexthdr = nh->nexthdr;
+	payload_ofs = (u8 *)(nh + 1) - skb->data;
+
+	key->ip.proto = NEXTHDR_NONE;
+	key->ip.tos = ipv6_get_dsfield(nh);
+	key->ip.ttl = nh->hop_limit;
+	key->ipv6.label = *(__be32 *)nh & htonl(IPV6_FLOWINFO_FLOWLABEL);
+	key->ipv6.addr.src = nh->saddr;
+	key->ipv6.addr.dst = nh->daddr;
+
+	payload_ofs = ipv6_skip_exthdr(skb, payload_ofs, &nexthdr, &frag_off);
+	if (unlikely(payload_ofs < 0))
+		return -EINVAL;
+
+	if (frag_off) {
+		if (frag_off & htons(~0x7))
+			key->ip.frag = OVS_FRAG_TYPE_LATER;
+		else
+			key->ip.frag = OVS_FRAG_TYPE_FIRST;
+	}
+
+	nh_len = payload_ofs - nh_ofs;
+	skb_set_transport_header(skb, nh_ofs + nh_len);
+	key->ip.proto = nexthdr;
+	return nh_len;
+}
+
+static bool icmp6hdr_ok(struct sk_buff *skb)
+{
+	return pskb_may_pull(skb, skb_transport_offset(skb) +
+				  sizeof(struct icmp6hdr));
+}
+
+#define TCP_FLAGS_OFFSET 13
+#define TCP_FLAG_MASK 0x3f
+
+void ovs_flow_used(struct sw_flow *flow, struct sk_buff *skb)
+{
+	u8 tcp_flags = 0;
+
+	if (flow->key.eth.type == htons(ETH_P_IP) &&
+	    flow->key.ip.proto == IPPROTO_TCP) {
+		u8 *tcp = (u8 *)tcp_hdr(skb);
+		tcp_flags = *(tcp + TCP_FLAGS_OFFSET) & TCP_FLAG_MASK;
+	}
+
+	spin_lock(&flow->lock);
+	flow->used = jiffies;
+	flow->packet_count++;
+	flow->byte_count += skb->len;
+	flow->tcp_flags |= tcp_flags;
+	spin_unlock(&flow->lock);
+}
+
+struct sw_flow_actions *ovs_flow_actions_alloc(const struct nlattr *actions)
+{
+	int actions_len = nla_len(actions);
+	struct sw_flow_actions *sfa;
+
+	/* At least DP_MAX_PORTS actions are required to be able to flood a
+	 * packet to every port.  Factor of 2 allows for setting VLAN tags,
+	 * etc. */
+	if (actions_len > 2 * DP_MAX_PORTS * nla_total_size(4))
+		return ERR_PTR(-EINVAL);
+
+	sfa = kmalloc(sizeof(*sfa) + actions_len, GFP_KERNEL);
+	if (!sfa)
+		return ERR_PTR(-ENOMEM);
+
+	sfa->actions_len = actions_len;
+	memcpy(sfa->actions, nla_data(actions), actions_len);
+	return sfa;
+}
+
+struct sw_flow *ovs_flow_alloc(void)
+{
+	struct sw_flow *flow;
+
+	flow = kmem_cache_alloc(flow_cache, GFP_KERNEL);
+	if (!flow)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock_init(&flow->lock);
+	flow->sf_acts = NULL;
+
+	return flow;
+}
+
+static struct hlist_head *find_bucket(struct flow_table *table, u32 hash)
+{
+	hash = jhash_1word(hash, table->hash_seed);
+	return flex_array_get(table->buckets,
+				(hash & (table->n_buckets - 1)));
+}
+
+static struct flex_array *alloc_buckets(unsigned int n_buckets)
+{
+	struct flex_array *buckets;
+	int i, err;
+
+	buckets = flex_array_alloc(sizeof(struct hlist_head *),
+				   n_buckets, GFP_KERNEL);
+	if (!buckets)
+		return NULL;
+
+	err = flex_array_prealloc(buckets, 0, n_buckets, GFP_KERNEL);
+	if (err) {
+		flex_array_free(buckets);
+		return NULL;
+	}
+
+	for (i = 0; i < n_buckets; i++)
+		INIT_HLIST_HEAD((struct hlist_head *)
+					flex_array_get(buckets, i));
+
+	return buckets;
+}
+
+static void free_buckets(struct flex_array *buckets)
+{
+	flex_array_free(buckets);
+}
+
+struct flow_table *ovs_flow_tbl_alloc(int new_size)
+{
+	struct flow_table *table = kmalloc(sizeof(*table), GFP_KERNEL);
+
+	if (!table)
+		return NULL;
+
+	table->buckets = alloc_buckets(new_size);
+
+	if (!table->buckets) {
+		kfree(table);
+		return NULL;
+	}
+	table->n_buckets = new_size;
+	table->count = 0;
+	table->node_ver = 0;
+	table->keep_flows = false;
+	get_random_bytes(&table->hash_seed, sizeof(u32));
+
+	return table;
+}
+
+void ovs_flow_tbl_destroy(struct flow_table *table)
+{
+	int i;
+
+	if (!table)
+		return;
+
+	if (table->keep_flows)
+		goto skip_flows;
+
+	for (i = 0; i < table->n_buckets; i++) {
+		struct sw_flow *flow;
+		struct hlist_head *head = flex_array_get(table->buckets, i);
+		struct hlist_node *node, *n;
+		int ver = table->node_ver;
+
+		hlist_for_each_entry_safe(flow, node, n, head, hash_node[ver]) {
+			hlist_del_rcu(&flow->hash_node[ver]);
+			ovs_flow_free(flow);
+		}
+	}
+
+skip_flows:
+	free_buckets(table->buckets);
+	kfree(table);
+}
+
+static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
+{
+	struct flow_table *table = container_of(rcu, struct flow_table, rcu);
+
+	ovs_flow_tbl_destroy(table);
+}
+
+void ovs_flow_tbl_deferred_destroy(struct flow_table *table)
+{
+	if (!table)
+		return;
+
+	call_rcu(&table->rcu, flow_tbl_destroy_rcu_cb);
+}
+
+struct sw_flow *ovs_flow_tbl_next(struct flow_table *table, u32 *bucket, u32 *last)
+{
+	struct sw_flow *flow;
+	struct hlist_head *head;
+	struct hlist_node *n;
+	int ver;
+	int i;
+
+	ver = table->node_ver;
+	while (*bucket < table->n_buckets) {
+		i = 0;
+		head = flex_array_get(table->buckets, *bucket);
+		hlist_for_each_entry_rcu(flow, n, head, hash_node[ver]) {
+			if (i < *last) {
+				i++;
+				continue;
+			}
+			*last = i + 1;
+			return flow;
+		}
+		(*bucket)++;
+		*last = 0;
+	}
+
+	return NULL;
+}
+
+static void flow_table_copy_flows(struct flow_table *old, struct flow_table *new)
+{
+	int old_ver;
+	int i;
+
+	old_ver = old->node_ver;
+	new->node_ver = !old_ver;
+
+	/* Insert in new table. */
+	for (i = 0; i < old->n_buckets; i++) {
+		struct sw_flow *flow;
+		struct hlist_head *head;
+		struct hlist_node *n;
+
+		head = flex_array_get(old->buckets, i);
+
+		hlist_for_each_entry(flow, n, head, hash_node[old_ver])
+			ovs_flow_tbl_insert(new, flow);
+	}
+	old->keep_flows = true;
+}
+
+static struct flow_table *__flow_tbl_rehash(struct flow_table *table, int n_buckets)
+{
+	struct flow_table *new_table;
+
+	new_table = ovs_flow_tbl_alloc(n_buckets);
+	if (!new_table)
+		return ERR_PTR(-ENOMEM);
+
+	flow_table_copy_flows(table, new_table);
+
+	return new_table;
+}
+
+struct flow_table *ovs_flow_tbl_rehash(struct flow_table *table)
+{
+	return __flow_tbl_rehash(table, table->n_buckets);
+}
+
+struct flow_table *ovs_flow_tbl_expand(struct flow_table *table)
+{
+	return __flow_tbl_rehash(table, table->n_buckets * 2);
+}
+
+void ovs_flow_free(struct sw_flow *flow)
+{
+	if (unlikely(!flow))
+		return;
+
+	kfree((struct sf_flow_acts __force *)flow->sf_acts);
+	kmem_cache_free(flow_cache, flow);
+}
+
+/* RCU callback used by ovs_flow_deferred_free. */
+static void rcu_free_flow_callback(struct rcu_head *rcu)
+{
+	struct sw_flow *flow = container_of(rcu, struct sw_flow, rcu);
+
+	ovs_flow_free(flow);
+}
+
+/* Schedules 'flow' to be freed after the next RCU grace period.
+ * The caller must hold rcu_read_lock for this to be sensible. */
+void ovs_flow_deferred_free(struct sw_flow *flow)
+{
+	call_rcu(&flow->rcu, rcu_free_flow_callback);
+}
+
+/* RCU callback used by ovs_flow_deferred_free_acts. */
+static void rcu_free_acts_callback(struct rcu_head *rcu)
+{
+	struct sw_flow_actions *sf_acts = container_of(rcu,
+			struct sw_flow_actions, rcu);
+	kfree(sf_acts);
+}
+
+/* Schedules 'sf_acts' to be freed after the next RCU grace period.
+ * The caller must hold rcu_read_lock for this to be sensible. */
+void ovs_flow_deferred_free_acts(struct sw_flow_actions *sf_acts)
+{
+	call_rcu(&sf_acts->rcu, rcu_free_acts_callback);
+}
+
+static int parse_vlan(struct sk_buff *skb, struct sw_flow_key *key)
+{
+	struct qtag_prefix {
+		__be16 eth_type; /* ETH_P_8021Q */
+		__be16 tci;
+	};
+	struct qtag_prefix *qp;
+
+	if (unlikely(skb->len < sizeof(struct qtag_prefix) + sizeof(__be16)))
+		return 0;
+
+	if (unlikely(!pskb_may_pull(skb, sizeof(struct qtag_prefix) +
+					 sizeof(__be16))))
+		return -ENOMEM;
+
+	qp = (struct qtag_prefix *) skb->data;
+	key->eth.tci = qp->tci | htons(VLAN_TAG_PRESENT);
+	__skb_pull(skb, sizeof(struct qtag_prefix));
+
+	return 0;
+}
+
+static __be16 parse_ethertype(struct sk_buff *skb)
+{
+	struct llc_snap_hdr {
+		u8  dsap;  /* Always 0xAA */
+		u8  ssap;  /* Always 0xAA */
+		u8  ctrl;
+		u8  oui[3];
+		__be16 ethertype;
+	};
+	struct llc_snap_hdr *llc;
+	__be16 proto;
+
+	proto = *(__be16 *) skb->data;
+	__skb_pull(skb, sizeof(__be16));
+
+	if (ntohs(proto) >= 1536)
+		return proto;
+
+	if (skb->len < sizeof(struct llc_snap_hdr))
+		return htons(ETH_P_802_2);
+
+	if (unlikely(!pskb_may_pull(skb, sizeof(struct llc_snap_hdr))))
+		return htons(0);
+
+	llc = (struct llc_snap_hdr *) skb->data;
+	if (llc->dsap != LLC_SAP_SNAP ||
+	    llc->ssap != LLC_SAP_SNAP ||
+	    (llc->oui[0] | llc->oui[1] | llc->oui[2]) != 0)
+		return htons(ETH_P_802_2);
+
+	__skb_pull(skb, sizeof(struct llc_snap_hdr));
+	return llc->ethertype;
+}
+
+static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key,
+			int *key_lenp, int nh_len)
+{
+	struct icmp6hdr *icmp = icmp6_hdr(skb);
+	int error = 0;
+	int key_len;
+
+	/* The ICMPv6 type and code fields use the 16-bit transport port
+	 * fields, so we need to store them in 16-bit network byte order.
+	 */
+	key->ipv6.tp.src = htons(icmp->icmp6_type);
+	key->ipv6.tp.dst = htons(icmp->icmp6_code);
+	key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
+
+	if (icmp->icmp6_code == 0 &&
+	    (icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION ||
+	     icmp->icmp6_type == NDISC_NEIGHBOUR_ADVERTISEMENT)) {
+		int icmp_len = skb->len - skb_transport_offset(skb);
+		struct nd_msg *nd;
+		int offset;
+
+		key_len = SW_FLOW_KEY_OFFSET(ipv6.nd);
+
+		/* In order to process neighbor discovery options, we need the
+		 * entire packet.
+		 */
+		if (unlikely(icmp_len < sizeof(*nd)))
+			goto out;
+		if (unlikely(skb_linearize(skb))) {
+			error = -ENOMEM;
+			goto out;
+		}
+
+		nd = (struct nd_msg *)skb_transport_header(skb);
+		key->ipv6.nd.target = nd->target;
+		key_len = SW_FLOW_KEY_OFFSET(ipv6.nd);
+
+		icmp_len -= sizeof(*nd);
+		offset = 0;
+		while (icmp_len >= 8) {
+			struct nd_opt_hdr *nd_opt =
+				 (struct nd_opt_hdr *)(nd->opt + offset);
+			int opt_len = nd_opt->nd_opt_len * 8;
+
+			if (unlikely(!opt_len || opt_len > icmp_len))
+				goto invalid;
+
+			/* Store the link layer address if the appropriate
+			 * option is provided.  It is considered an error if
+			 * the same link layer option is specified twice.
+			 */
+			if (nd_opt->nd_opt_type == ND_OPT_SOURCE_LL_ADDR
+			    && opt_len == 8) {
+				if (unlikely(!is_zero_ether_addr(key->ipv6.nd.sll)))
+					goto invalid;
+				memcpy(key->ipv6.nd.sll,
+				    &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN);
+			} else if (nd_opt->nd_opt_type == ND_OPT_TARGET_LL_ADDR
+				   && opt_len == 8) {
+				if (unlikely(!is_zero_ether_addr(key->ipv6.nd.tll)))
+					goto invalid;
+				memcpy(key->ipv6.nd.tll,
+				    &nd->opt[offset+sizeof(*nd_opt)], ETH_ALEN);
+			}
+
+			icmp_len -= opt_len;
+			offset += opt_len;
+		}
+	}
+
+	goto out;
+
+invalid:
+	memset(&key->ipv6.nd.target, 0, sizeof(key->ipv6.nd.target));
+	memset(key->ipv6.nd.sll, 0, sizeof(key->ipv6.nd.sll));
+	memset(key->ipv6.nd.tll, 0, sizeof(key->ipv6.nd.tll));
+
+out:
+	*key_lenp = key_len;
+	return error;
+}
+
+/**
+ * ovs_flow_extract - extracts a flow key from an Ethernet frame.
+ * @skb: sk_buff that contains the frame, with skb->data pointing to the
+ * Ethernet header
+ * @in_port: port number on which @skb was received.
+ * @key: output flow key
+ * @key_lenp: length of output flow key
+ *
+ * The caller must ensure that skb->len >= ETH_HLEN.
+ *
+ * Returns 0 if successful, otherwise a negative errno value.
+ *
+ * Initializes @skb header pointers as follows:
+ *
+ *    - skb->mac_header: the Ethernet header.
+ *
+ *    - skb->network_header: just past the Ethernet header, or just past the
+ *      VLAN header, to the first byte of the Ethernet payload.
+ *
+ *    - skb->transport_header: If key->dl_type is ETH_P_IP or ETH_P_IPV6
+ *      on output, then just past the IP header, if one is present and
+ *      of a correct length, otherwise the same as skb->network_header.
+ *      For other key->dl_type values it is left untouched.
+ */
+int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key,
+		 int *key_lenp)
+{
+	int error = 0;
+	int key_len = SW_FLOW_KEY_OFFSET(eth);
+	struct ethhdr *eth;
+
+	memset(key, 0, sizeof(*key));
+
+	key->phy.priority = skb->priority;
+	key->phy.in_port = in_port;
+
+	skb_reset_mac_header(skb);
+
+	/* Link layer.  We are guaranteed to have at least the 14 byte Ethernet
+	 * header in the linear data area.
+	 */
+	eth = eth_hdr(skb);
+	memcpy(key->eth.src, eth->h_source, ETH_ALEN);
+	memcpy(key->eth.dst, eth->h_dest, ETH_ALEN);
+
+	__skb_pull(skb, 2 * ETH_ALEN);
+
+	if (vlan_tx_tag_present(skb))
+		key->eth.tci = htons(skb->vlan_tci);
+	else if (eth->h_proto == htons(ETH_P_8021Q))
+		if (unlikely(parse_vlan(skb, key)))
+			return -ENOMEM;
+
+	key->eth.type = parse_ethertype(skb);
+	if (unlikely(key->eth.type == htons(0)))
+		return -ENOMEM;
+
+	skb_reset_network_header(skb);
+	__skb_push(skb, skb->data - skb_mac_header(skb));
+
+	/* Network layer. */
+	if (key->eth.type == htons(ETH_P_IP)) {
+		struct iphdr *nh;
+		__be16 offset;
+
+		key_len = SW_FLOW_KEY_OFFSET(ipv4.addr);
+
+		error = check_iphdr(skb);
+		if (unlikely(error)) {
+			if (error == -EINVAL) {
+				skb->transport_header = skb->network_header;
+				error = 0;
+			}
+			goto out;
+		}
+
+		nh = ip_hdr(skb);
+		key->ipv4.addr.src = nh->saddr;
+		key->ipv4.addr.dst = nh->daddr;
+
+		key->ip.proto = nh->protocol;
+		key->ip.tos = nh->tos;
+		key->ip.ttl = nh->ttl;
+
+		offset = nh->frag_off & htons(IP_OFFSET);
+		if (offset) {
+			key->ip.frag = OVS_FRAG_TYPE_LATER;
+			goto out;
+		}
+		if (nh->frag_off & htons(IP_MF) ||
+			 skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+			key->ip.frag = OVS_FRAG_TYPE_FIRST;
+
+		/* Transport layer. */
+		if (key->ip.proto == IPPROTO_TCP) {
+			key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
+			if (tcphdr_ok(skb)) {
+				struct tcphdr *tcp = tcp_hdr(skb);
+				key->ipv4.tp.src = tcp->source;
+				key->ipv4.tp.dst = tcp->dest;
+			}
+		} else if (key->ip.proto == IPPROTO_UDP) {
+			key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
+			if (udphdr_ok(skb)) {
+				struct udphdr *udp = udp_hdr(skb);
+				key->ipv4.tp.src = udp->source;
+				key->ipv4.tp.dst = udp->dest;
+			}
+		} else if (key->ip.proto == IPPROTO_ICMP) {
+			key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
+			if (icmphdr_ok(skb)) {
+				struct icmphdr *icmp = icmp_hdr(skb);
+				/* The ICMP type and code fields use the 16-bit
+				 * transport port fields, so we need to store
+				 * them in 16-bit network byte order. */
+				key->ipv4.tp.src = htons(icmp->type);
+				key->ipv4.tp.dst = htons(icmp->code);
+			}
+		}
+
+	} else if (key->eth.type == htons(ETH_P_ARP) && arphdr_ok(skb)) {
+		struct arp_eth_header *arp;
+
+		arp = (struct arp_eth_header *)skb_network_header(skb);
+
+		if (arp->ar_hrd == htons(ARPHRD_ETHER)
+				&& arp->ar_pro == htons(ETH_P_IP)
+				&& arp->ar_hln == ETH_ALEN
+				&& arp->ar_pln == 4) {
+
+			/* We only match on the lower 8 bits of the opcode. */
+			if (ntohs(arp->ar_op) <= 0xff)
+				key->ip.proto = ntohs(arp->ar_op);
+
+			if (key->ip.proto == ARPOP_REQUEST
+					|| key->ip.proto == ARPOP_REPLY) {
+				memcpy(&key->ipv4.addr.src, arp->ar_sip, sizeof(key->ipv4.addr.src));
+				memcpy(&key->ipv4.addr.dst, arp->ar_tip, sizeof(key->ipv4.addr.dst));
+				memcpy(key->ipv4.arp.sha, arp->ar_sha, ETH_ALEN);
+				memcpy(key->ipv4.arp.tha, arp->ar_tha, ETH_ALEN);
+				key_len = SW_FLOW_KEY_OFFSET(ipv4.arp);
+			}
+		}
+	} else if (key->eth.type == htons(ETH_P_IPV6)) {
+		int nh_len;             /* IPv6 Header + Extensions */
+
+		nh_len = parse_ipv6hdr(skb, key, &key_len);
+		if (unlikely(nh_len < 0)) {
+			if (nh_len == -EINVAL)
+				skb->transport_header = skb->network_header;
+			else
+				error = nh_len;
+			goto out;
+		}
+
+		if (key->ip.frag == OVS_FRAG_TYPE_LATER)
+			goto out;
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+			key->ip.frag = OVS_FRAG_TYPE_FIRST;
+
+		/* Transport layer. */
+		if (key->ip.proto == NEXTHDR_TCP) {
+			key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
+			if (tcphdr_ok(skb)) {
+				struct tcphdr *tcp = tcp_hdr(skb);
+				key->ipv6.tp.src = tcp->source;
+				key->ipv6.tp.dst = tcp->dest;
+			}
+		} else if (key->ip.proto == NEXTHDR_UDP) {
+			key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
+			if (udphdr_ok(skb)) {
+				struct udphdr *udp = udp_hdr(skb);
+				key->ipv6.tp.src = udp->source;
+				key->ipv6.tp.dst = udp->dest;
+			}
+		} else if (key->ip.proto == NEXTHDR_ICMP) {
+			key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
+			if (icmp6hdr_ok(skb)) {
+				error = parse_icmpv6(skb, key, &key_len, nh_len);
+				if (error < 0)
+					goto out;
+			}
+		}
+	}
+
+out:
+	*key_lenp = key_len;
+	return error;
+}
+
+u32 ovs_flow_hash(const struct sw_flow_key *key, int key_len)
+{
+	return jhash2((u32 *)key, DIV_ROUND_UP(key_len, sizeof(u32)), 0);
+}
+
+struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *table,
+				struct sw_flow_key *key, int key_len)
+{
+	struct sw_flow *flow;
+	struct hlist_node *n;
+	struct hlist_head *head;
+	u32 hash;
+
+	hash = ovs_flow_hash(key, key_len);
+
+	head = find_bucket(table, hash);
+	hlist_for_each_entry_rcu(flow, n, head, hash_node[table->node_ver]) {
+
+		if (flow->hash == hash &&
+		    !memcmp(&flow->key, key, key_len)) {
+			return flow;
+		}
+	}
+	return NULL;
+}
+
+void ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow)
+{
+	struct hlist_head *head;
+
+	head = find_bucket(table, flow->hash);
+	hlist_add_head_rcu(&flow->hash_node[table->node_ver], head);
+	table->count++;
+}
+
+void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
+{
+	hlist_del_rcu(&flow->hash_node[table->node_ver]);
+	table->count--;
+	BUG_ON(table->count < 0);
+}
+
+/* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute.  */
+const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = {
+	[OVS_KEY_ATTR_ENCAP] = -1,
+	[OVS_KEY_ATTR_PRIORITY] = sizeof(u32),
+	[OVS_KEY_ATTR_IN_PORT] = sizeof(u32),
+	[OVS_KEY_ATTR_ETHERNET] = sizeof(struct ovs_key_ethernet),
+	[OVS_KEY_ATTR_VLAN] = sizeof(__be16),
+	[OVS_KEY_ATTR_ETHERTYPE] = sizeof(__be16),
+	[OVS_KEY_ATTR_IPV4] = sizeof(struct ovs_key_ipv4),
+	[OVS_KEY_ATTR_IPV6] = sizeof(struct ovs_key_ipv6),
+	[OVS_KEY_ATTR_TCP] = sizeof(struct ovs_key_tcp),
+	[OVS_KEY_ATTR_UDP] = sizeof(struct ovs_key_udp),
+	[OVS_KEY_ATTR_ICMP] = sizeof(struct ovs_key_icmp),
+	[OVS_KEY_ATTR_ICMPV6] = sizeof(struct ovs_key_icmpv6),
+	[OVS_KEY_ATTR_ARP] = sizeof(struct ovs_key_arp),
+	[OVS_KEY_ATTR_ND] = sizeof(struct ovs_key_nd),
+};
+
+static int ipv4_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_len,
+				  const struct nlattr *a[], u32 *attrs)
+{
+	const struct ovs_key_icmp *icmp_key;
+	const struct ovs_key_tcp *tcp_key;
+	const struct ovs_key_udp *udp_key;
+
+	switch (swkey->ip.proto) {
+	case IPPROTO_TCP:
+		if (!(*attrs & (1 << OVS_KEY_ATTR_TCP)))
+			return -EINVAL;
+		*attrs &= ~(1 << OVS_KEY_ATTR_TCP);
+
+		*key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
+		tcp_key = nla_data(a[OVS_KEY_ATTR_TCP]);
+		swkey->ipv4.tp.src = tcp_key->tcp_src;
+		swkey->ipv4.tp.dst = tcp_key->tcp_dst;
+		break;
+
+	case IPPROTO_UDP:
+		if (!(*attrs & (1 << OVS_KEY_ATTR_UDP)))
+			return -EINVAL;
+		*attrs &= ~(1 << OVS_KEY_ATTR_UDP);
+
+		*key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
+		udp_key = nla_data(a[OVS_KEY_ATTR_UDP]);
+		swkey->ipv4.tp.src = udp_key->udp_src;
+		swkey->ipv4.tp.dst = udp_key->udp_dst;
+		break;
+
+	case IPPROTO_ICMP:
+		if (!(*attrs & (1 << OVS_KEY_ATTR_ICMP)))
+			return -EINVAL;
+		*attrs &= ~(1 << OVS_KEY_ATTR_ICMP);
+
+		*key_len = SW_FLOW_KEY_OFFSET(ipv4.tp);
+		icmp_key = nla_data(a[OVS_KEY_ATTR_ICMP]);
+		swkey->ipv4.tp.src = htons(icmp_key->icmp_type);
+		swkey->ipv4.tp.dst = htons(icmp_key->icmp_code);
+		break;
+	}
+
+	return 0;
+}
+
+static int ipv6_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_len,
+				  const struct nlattr *a[], u32 *attrs)
+{
+	const struct ovs_key_icmpv6 *icmpv6_key;
+	const struct ovs_key_tcp *tcp_key;
+	const struct ovs_key_udp *udp_key;
+
+	switch (swkey->ip.proto) {
+	case IPPROTO_TCP:
+		if (!(*attrs & (1 << OVS_KEY_ATTR_TCP)))
+			return -EINVAL;
+		*attrs &= ~(1 << OVS_KEY_ATTR_TCP);
+
+		*key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
+		tcp_key = nla_data(a[OVS_KEY_ATTR_TCP]);
+		swkey->ipv6.tp.src = tcp_key->tcp_src;
+		swkey->ipv6.tp.dst = tcp_key->tcp_dst;
+		break;
+
+	case IPPROTO_UDP:
+		if (!(*attrs & (1 << OVS_KEY_ATTR_UDP)))
+			return -EINVAL;
+		*attrs &= ~(1 << OVS_KEY_ATTR_UDP);
+
+		*key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
+		udp_key = nla_data(a[OVS_KEY_ATTR_UDP]);
+		swkey->ipv6.tp.src = udp_key->udp_src;
+		swkey->ipv6.tp.dst = udp_key->udp_dst;
+		break;
+
+	case IPPROTO_ICMPV6:
+		if (!(*attrs & (1 << OVS_KEY_ATTR_ICMPV6)))
+			return -EINVAL;
+		*attrs &= ~(1 << OVS_KEY_ATTR_ICMPV6);
+
+		*key_len = SW_FLOW_KEY_OFFSET(ipv6.tp);
+		icmpv6_key = nla_data(a[OVS_KEY_ATTR_ICMPV6]);
+		swkey->ipv6.tp.src = htons(icmpv6_key->icmpv6_type);
+		swkey->ipv6.tp.dst = htons(icmpv6_key->icmpv6_code);
+
+		if (swkey->ipv6.tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) ||
+		    swkey->ipv6.tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) {
+			const struct ovs_key_nd *nd_key;
+
+			if (!(*attrs & (1 << OVS_KEY_ATTR_ND)))
+				return -EINVAL;
+			*attrs &= ~(1 << OVS_KEY_ATTR_ND);
+
+			*key_len = SW_FLOW_KEY_OFFSET(ipv6.nd);
+			nd_key = nla_data(a[OVS_KEY_ATTR_ND]);
+			memcpy(&swkey->ipv6.nd.target, nd_key->nd_target,
+			       sizeof(swkey->ipv6.nd.target));
+			memcpy(swkey->ipv6.nd.sll, nd_key->nd_sll, ETH_ALEN);
+			memcpy(swkey->ipv6.nd.tll, nd_key->nd_tll, ETH_ALEN);
+		}
+		break;
+	}
+
+	return 0;
+}
+
+static int parse_flow_nlattrs(const struct nlattr *attr,
+			      const struct nlattr *a[], u32 *attrsp)
+{
+	const struct nlattr *nla;
+	u32 attrs;
+	int rem;
+
+	attrs = 0;
+	nla_for_each_nested(nla, attr, rem) {
+		u16 type = nla_type(nla);
+		int expected_len;
+
+		if (type > OVS_KEY_ATTR_MAX || attrs & (1 << type))
+			return -EINVAL;
+
+		expected_len = ovs_key_lens[type];
+		if (nla_len(nla) != expected_len && expected_len != -1)
+			return -EINVAL;
+
+		attrs |= 1 << type;
+		a[type] = nla;
+	}
+	if (rem)
+		return -EINVAL;
+
+	*attrsp = attrs;
+	return 0;
+}
+
+/**
+ * ovs_flow_from_nlattrs - parses Netlink attributes into a flow key.
+ * @swkey: receives the extracted flow key.
+ * @key_lenp: number of bytes used in @swkey.
+ * @attr: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute
+ * sequence.
+ */
+int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp,
+		      const struct nlattr *attr)
+{
+	const struct nlattr *a[OVS_KEY_ATTR_MAX + 1];
+	const struct ovs_key_ethernet *eth_key;
+	int key_len;
+	u32 attrs;
+	int err;
+
+	memset(swkey, 0, sizeof(struct sw_flow_key));
+	key_len = SW_FLOW_KEY_OFFSET(eth);
+
+	err = parse_flow_nlattrs(attr, a, &attrs);
+	if (err)
+		return err;
+
+	/* Metadata attributes. */
+	if (attrs & (1 << OVS_KEY_ATTR_PRIORITY)) {
+		swkey->phy.priority = nla_get_u32(a[OVS_KEY_ATTR_PRIORITY]);
+		attrs &= ~(1 << OVS_KEY_ATTR_PRIORITY);
+	}
+	if (attrs & (1 << OVS_KEY_ATTR_IN_PORT)) {
+		u32 in_port = nla_get_u32(a[OVS_KEY_ATTR_IN_PORT]);
+		if (in_port >= DP_MAX_PORTS)
+			return -EINVAL;
+		swkey->phy.in_port = in_port;
+		attrs &= ~(1 << OVS_KEY_ATTR_IN_PORT);
+	} else {
+		swkey->phy.in_port = USHRT_MAX;
+	}
+
+	/* Data attributes. */
+	if (!(attrs & (1 << OVS_KEY_ATTR_ETHERNET)))
+		return -EINVAL;
+	attrs &= ~(1 << OVS_KEY_ATTR_ETHERNET);
+
+	eth_key = nla_data(a[OVS_KEY_ATTR_ETHERNET]);
+	memcpy(swkey->eth.src, eth_key->eth_src, ETH_ALEN);
+	memcpy(swkey->eth.dst, eth_key->eth_dst, ETH_ALEN);
+
+	if (attrs & (1u << OVS_KEY_ATTR_ETHERTYPE) &&
+	    nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]) == htons(ETH_P_8021Q)) {
+		const struct nlattr *encap;
+		__be16 tci;
+
+		if (attrs != ((1 << OVS_KEY_ATTR_VLAN) |
+			      (1 << OVS_KEY_ATTR_ETHERTYPE) |
+			      (1 << OVS_KEY_ATTR_ENCAP)))
+			return -EINVAL;
+
+		encap = a[OVS_KEY_ATTR_ENCAP];
+		tci = nla_get_be16(a[OVS_KEY_ATTR_VLAN]);
+		if (tci & htons(VLAN_TAG_PRESENT)) {
+			swkey->eth.tci = tci;
+
+			err = parse_flow_nlattrs(encap, a, &attrs);
+			if (err)
+				return err;
+		} else if (!tci) {
+			/* Corner case for truncated 802.1Q header. */
+			if (nla_len(encap))
+				return -EINVAL;
+
+			swkey->eth.type = htons(ETH_P_8021Q);
+			*key_lenp = key_len;
+			return 0;
+		} else {
+			return -EINVAL;
+		}
+	}
+
+	if (attrs & (1 << OVS_KEY_ATTR_ETHERTYPE)) {
+		swkey->eth.type = nla_get_be16(a[OVS_KEY_ATTR_ETHERTYPE]);
+		if (ntohs(swkey->eth.type) < 1536)
+			return -EINVAL;
+		attrs &= ~(1 << OVS_KEY_ATTR_ETHERTYPE);
+	} else {
+		swkey->eth.type = htons(ETH_P_802_2);
+	}
+
+	if (swkey->eth.type == htons(ETH_P_IP)) {
+		const struct ovs_key_ipv4 *ipv4_key;
+
+		if (!(attrs & (1 << OVS_KEY_ATTR_IPV4)))
+			return -EINVAL;
+		attrs &= ~(1 << OVS_KEY_ATTR_IPV4);
+
+		key_len = SW_FLOW_KEY_OFFSET(ipv4.addr);
+		ipv4_key = nla_data(a[OVS_KEY_ATTR_IPV4]);
+		if (ipv4_key->ipv4_frag > OVS_FRAG_TYPE_MAX)
+			return -EINVAL;
+		swkey->ip.proto = ipv4_key->ipv4_proto;
+		swkey->ip.tos = ipv4_key->ipv4_tos;
+		swkey->ip.ttl = ipv4_key->ipv4_ttl;
+		swkey->ip.frag = ipv4_key->ipv4_frag;
+		swkey->ipv4.addr.src = ipv4_key->ipv4_src;
+		swkey->ipv4.addr.dst = ipv4_key->ipv4_dst;
+
+		if (swkey->ip.frag != OVS_FRAG_TYPE_LATER) {
+			err = ipv4_flow_from_nlattrs(swkey, &key_len, a, &attrs);
+			if (err)
+				return err;
+		}
+	} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
+		const struct ovs_key_ipv6 *ipv6_key;
+
+		if (!(attrs & (1 << OVS_KEY_ATTR_IPV6)))
+			return -EINVAL;
+		attrs &= ~(1 << OVS_KEY_ATTR_IPV6);
+
+		key_len = SW_FLOW_KEY_OFFSET(ipv6.label);
+		ipv6_key = nla_data(a[OVS_KEY_ATTR_IPV6]);
+		if (ipv6_key->ipv6_frag > OVS_FRAG_TYPE_MAX)
+			return -EINVAL;
+		swkey->ipv6.label = ipv6_key->ipv6_label;
+		swkey->ip.proto = ipv6_key->ipv6_proto;
+		swkey->ip.tos = ipv6_key->ipv6_tclass;
+		swkey->ip.ttl = ipv6_key->ipv6_hlimit;
+		swkey->ip.frag = ipv6_key->ipv6_frag;
+		memcpy(&swkey->ipv6.addr.src, ipv6_key->ipv6_src,
+		       sizeof(swkey->ipv6.addr.src));
+		memcpy(&swkey->ipv6.addr.dst, ipv6_key->ipv6_dst,
+		       sizeof(swkey->ipv6.addr.dst));
+
+		if (swkey->ip.frag != OVS_FRAG_TYPE_LATER) {
+			err = ipv6_flow_from_nlattrs(swkey, &key_len, a, &attrs);
+			if (err)
+				return err;
+		}
+	} else if (swkey->eth.type == htons(ETH_P_ARP)) {
+		const struct ovs_key_arp *arp_key;
+
+		if (!(attrs & (1 << OVS_KEY_ATTR_ARP)))
+			return -EINVAL;
+		attrs &= ~(1 << OVS_KEY_ATTR_ARP);
+
+		key_len = SW_FLOW_KEY_OFFSET(ipv4.arp);
+		arp_key = nla_data(a[OVS_KEY_ATTR_ARP]);
+		swkey->ipv4.addr.src = arp_key->arp_sip;
+		swkey->ipv4.addr.dst = arp_key->arp_tip;
+		if (arp_key->arp_op & htons(0xff00))
+			return -EINVAL;
+		swkey->ip.proto = ntohs(arp_key->arp_op);
+		memcpy(swkey->ipv4.arp.sha, arp_key->arp_sha, ETH_ALEN);
+		memcpy(swkey->ipv4.arp.tha, arp_key->arp_tha, ETH_ALEN);
+	}
+
+	if (attrs)
+		return -EINVAL;
+	*key_lenp = key_len;
+
+	return 0;
+}
+
+/**
+ * ovs_flow_metadata_from_nlattrs - parses Netlink attributes into a flow key.
+ * @in_port: receives the extracted input port.
+ * @key: Netlink attribute holding nested %OVS_KEY_ATTR_* Netlink attribute
+ * sequence.
+ *
+ * This parses a series of Netlink attributes that form a flow key, which must
+ * take the same form accepted by flow_from_nlattrs(), but only enough of it to
+ * get the metadata, that is, the parts of the flow key that cannot be
+ * extracted from the packet itself.
+ */
+int ovs_flow_metadata_from_nlattrs(u32 *priority, u16 *in_port,
+			       const struct nlattr *attr)
+{
+	const struct nlattr *nla;
+	int rem;
+
+	*in_port = USHRT_MAX;
+	*priority = 0;
+
+	nla_for_each_nested(nla, attr, rem) {
+		int type = nla_type(nla);
+
+		if (type <= OVS_KEY_ATTR_MAX && ovs_key_lens[type] > 0) {
+			if (nla_len(nla) != ovs_key_lens[type])
+				return -EINVAL;
+
+			switch (type) {
+			case OVS_KEY_ATTR_PRIORITY:
+				*priority = nla_get_u32(nla);
+				break;
+
+			case OVS_KEY_ATTR_IN_PORT:
+				if (nla_get_u32(nla) >= DP_MAX_PORTS)
+					return -EINVAL;
+				*in_port = nla_get_u32(nla);
+				break;
+			}
+		}
+	}
+	if (rem)
+		return -EINVAL;
+	return 0;
+}
+
+int ovs_flow_to_nlattrs(const struct sw_flow_key *swkey, struct sk_buff *skb)
+{
+	struct ovs_key_ethernet *eth_key;
+	struct nlattr *nla, *encap;
+
+	if (swkey->phy.priority)
+		NLA_PUT_U32(skb, OVS_KEY_ATTR_PRIORITY, swkey->phy.priority);
+
+	if (swkey->phy.in_port != USHRT_MAX)
+		NLA_PUT_U32(skb, OVS_KEY_ATTR_IN_PORT, swkey->phy.in_port);
+
+	nla = nla_reserve(skb, OVS_KEY_ATTR_ETHERNET, sizeof(*eth_key));
+	if (!nla)
+		goto nla_put_failure;
+	eth_key = nla_data(nla);
+	memcpy(eth_key->eth_src, swkey->eth.src, ETH_ALEN);
+	memcpy(eth_key->eth_dst, swkey->eth.dst, ETH_ALEN);
+
+	if (swkey->eth.tci || swkey->eth.type == htons(ETH_P_8021Q)) {
+		NLA_PUT_BE16(skb, OVS_KEY_ATTR_ETHERTYPE, htons(ETH_P_8021Q));
+		NLA_PUT_BE16(skb, OVS_KEY_ATTR_VLAN, swkey->eth.tci);
+		encap = nla_nest_start(skb, OVS_KEY_ATTR_ENCAP);
+		if (!swkey->eth.tci)
+			goto unencap;
+	} else {
+		encap = NULL;
+	}
+
+	if (swkey->eth.type == htons(ETH_P_802_2))
+		goto unencap;
+
+	NLA_PUT_BE16(skb, OVS_KEY_ATTR_ETHERTYPE, swkey->eth.type);
+
+	if (swkey->eth.type == htons(ETH_P_IP)) {
+		struct ovs_key_ipv4 *ipv4_key;
+
+		nla = nla_reserve(skb, OVS_KEY_ATTR_IPV4, sizeof(*ipv4_key));
+		if (!nla)
+			goto nla_put_failure;
+		ipv4_key = nla_data(nla);
+		ipv4_key->ipv4_src = swkey->ipv4.addr.src;
+		ipv4_key->ipv4_dst = swkey->ipv4.addr.dst;
+		ipv4_key->ipv4_proto = swkey->ip.proto;
+		ipv4_key->ipv4_tos = swkey->ip.tos;
+		ipv4_key->ipv4_ttl = swkey->ip.ttl;
+		ipv4_key->ipv4_frag = swkey->ip.frag;
+	} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
+		struct ovs_key_ipv6 *ipv6_key;
+
+		nla = nla_reserve(skb, OVS_KEY_ATTR_IPV6, sizeof(*ipv6_key));
+		if (!nla)
+			goto nla_put_failure;
+		ipv6_key = nla_data(nla);
+		memcpy(ipv6_key->ipv6_src, &swkey->ipv6.addr.src,
+				sizeof(ipv6_key->ipv6_src));
+		memcpy(ipv6_key->ipv6_dst, &swkey->ipv6.addr.dst,
+				sizeof(ipv6_key->ipv6_dst));
+		ipv6_key->ipv6_label = swkey->ipv6.label;
+		ipv6_key->ipv6_proto = swkey->ip.proto;
+		ipv6_key->ipv6_tclass = swkey->ip.tos;
+		ipv6_key->ipv6_hlimit = swkey->ip.ttl;
+		ipv6_key->ipv6_frag = swkey->ip.frag;
+	} else if (swkey->eth.type == htons(ETH_P_ARP)) {
+		struct ovs_key_arp *arp_key;
+
+		nla = nla_reserve(skb, OVS_KEY_ATTR_ARP, sizeof(*arp_key));
+		if (!nla)
+			goto nla_put_failure;
+		arp_key = nla_data(nla);
+		memset(arp_key, 0, sizeof(struct ovs_key_arp));
+		arp_key->arp_sip = swkey->ipv4.addr.src;
+		arp_key->arp_tip = swkey->ipv4.addr.dst;
+		arp_key->arp_op = htons(swkey->ip.proto);
+		memcpy(arp_key->arp_sha, swkey->ipv4.arp.sha, ETH_ALEN);
+		memcpy(arp_key->arp_tha, swkey->ipv4.arp.tha, ETH_ALEN);
+	}
+
+	if ((swkey->eth.type == htons(ETH_P_IP) ||
+	     swkey->eth.type == htons(ETH_P_IPV6)) &&
+	     swkey->ip.frag != OVS_FRAG_TYPE_LATER) {
+
+		if (swkey->ip.proto == IPPROTO_TCP) {
+			struct ovs_key_tcp *tcp_key;
+
+			nla = nla_reserve(skb, OVS_KEY_ATTR_TCP, sizeof(*tcp_key));
+			if (!nla)
+				goto nla_put_failure;
+			tcp_key = nla_data(nla);
+			if (swkey->eth.type == htons(ETH_P_IP)) {
+				tcp_key->tcp_src = swkey->ipv4.tp.src;
+				tcp_key->tcp_dst = swkey->ipv4.tp.dst;
+			} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
+				tcp_key->tcp_src = swkey->ipv6.tp.src;
+				tcp_key->tcp_dst = swkey->ipv6.tp.dst;
+			}
+		} else if (swkey->ip.proto == IPPROTO_UDP) {
+			struct ovs_key_udp *udp_key;
+
+			nla = nla_reserve(skb, OVS_KEY_ATTR_UDP, sizeof(*udp_key));
+			if (!nla)
+				goto nla_put_failure;
+			udp_key = nla_data(nla);
+			if (swkey->eth.type == htons(ETH_P_IP)) {
+				udp_key->udp_src = swkey->ipv4.tp.src;
+				udp_key->udp_dst = swkey->ipv4.tp.dst;
+			} else if (swkey->eth.type == htons(ETH_P_IPV6)) {
+				udp_key->udp_src = swkey->ipv6.tp.src;
+				udp_key->udp_dst = swkey->ipv6.tp.dst;
+			}
+		} else if (swkey->eth.type == htons(ETH_P_IP) &&
+			   swkey->ip.proto == IPPROTO_ICMP) {
+			struct ovs_key_icmp *icmp_key;
+
+			nla = nla_reserve(skb, OVS_KEY_ATTR_ICMP, sizeof(*icmp_key));
+			if (!nla)
+				goto nla_put_failure;
+			icmp_key = nla_data(nla);
+			icmp_key->icmp_type = ntohs(swkey->ipv4.tp.src);
+			icmp_key->icmp_code = ntohs(swkey->ipv4.tp.dst);
+		} else if (swkey->eth.type == htons(ETH_P_IPV6) &&
+			   swkey->ip.proto == IPPROTO_ICMPV6) {
+			struct ovs_key_icmpv6 *icmpv6_key;
+
+			nla = nla_reserve(skb, OVS_KEY_ATTR_ICMPV6,
+						sizeof(*icmpv6_key));
+			if (!nla)
+				goto nla_put_failure;
+			icmpv6_key = nla_data(nla);
+			icmpv6_key->icmpv6_type = ntohs(swkey->ipv6.tp.src);
+			icmpv6_key->icmpv6_code = ntohs(swkey->ipv6.tp.dst);
+
+			if (icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_SOLICITATION ||
+			    icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_ADVERTISEMENT) {
+				struct ovs_key_nd *nd_key;
+
+				nla = nla_reserve(skb, OVS_KEY_ATTR_ND, sizeof(*nd_key));
+				if (!nla)
+					goto nla_put_failure;
+				nd_key = nla_data(nla);
+				memcpy(nd_key->nd_target, &swkey->ipv6.nd.target,
+							sizeof(nd_key->nd_target));
+				memcpy(nd_key->nd_sll, swkey->ipv6.nd.sll, ETH_ALEN);
+				memcpy(nd_key->nd_tll, swkey->ipv6.nd.tll, ETH_ALEN);
+			}
+		}
+	}
+
+unencap:
+	if (encap)
+		nla_nest_end(skb, encap);
+
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+/* Initializes the flow module.
+ * Returns zero if successful or a negative error code. */
+int ovs_flow_init(void)
+{
+	flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow), 0,
+					0, NULL);
+	if (flow_cache == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/* Uninitializes the flow module. */
+void ovs_flow_exit(void)
+{
+	kmem_cache_destroy(flow_cache);
+}
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
new file mode 100644
index 0000000..2747dc2
--- /dev/null
+++ b/net/openvswitch/flow.h
@@ -0,0 +1,199 @@
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef FLOW_H
+#define FLOW_H 1
+
+#include <linux/kernel.h>
+#include <linux/netlink.h>
+#include <linux/openvswitch.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+#include <linux/if_ether.h>
+#include <linux/in6.h>
+#include <linux/jiffies.h>
+#include <linux/time.h>
+#include <linux/flex_array.h>
+#include <net/inet_ecn.h>
+
+struct sk_buff;
+
+struct sw_flow_actions {
+	struct rcu_head rcu;
+	u32 actions_len;
+	struct nlattr actions[];
+};
+
+struct sw_flow_key {
+	struct {
+		u32	priority;	/* Packet QoS priority. */
+		u16	in_port;	/* Input switch port (or USHRT_MAX). */
+	} phy;
+	struct {
+		u8     src[ETH_ALEN];	/* Ethernet source address. */
+		u8     dst[ETH_ALEN];	/* Ethernet destination address. */
+		__be16 tci;		/* 0 if no VLAN, VLAN_TAG_PRESENT set otherwise. */
+		__be16 type;		/* Ethernet frame type. */
+	} eth;
+	struct {
+		u8     proto;		/* IP protocol or lower 8 bits of ARP opcode. */
+		u8     tos;		/* IP ToS. */
+		u8     ttl;		/* IP TTL/hop limit. */
+		u8     frag;		/* One of OVS_FRAG_TYPE_*. */
+	} ip;
+	union {
+		struct {
+			struct {
+				__be32 src;	/* IP source address. */
+				__be32 dst;	/* IP destination address. */
+			} addr;
+			union {
+				struct {
+					__be16 src;		/* TCP/UDP source port. */
+					__be16 dst;		/* TCP/UDP destination port. */
+				} tp;
+				struct {
+					u8 sha[ETH_ALEN];	/* ARP source hardware address. */
+					u8 tha[ETH_ALEN];	/* ARP target hardware address. */
+				} arp;
+			};
+		} ipv4;
+		struct {
+			struct {
+				struct in6_addr src;	/* IPv6 source address. */
+				struct in6_addr dst;	/* IPv6 destination address. */
+			} addr;
+			__be32 label;			/* IPv6 flow label. */
+			struct {
+				__be16 src;		/* TCP/UDP source port. */
+				__be16 dst;		/* TCP/UDP destination port. */
+			} tp;
+			struct {
+				struct in6_addr target;	/* ND target address. */
+				u8 sll[ETH_ALEN];	/* ND source link layer address. */
+				u8 tll[ETH_ALEN];	/* ND target link layer address. */
+			} nd;
+		} ipv6;
+	};
+};
+
+struct sw_flow {
+	struct rcu_head rcu;
+	struct hlist_node hash_node[2];
+	u32 hash;
+
+	struct sw_flow_key key;
+	struct sw_flow_actions __rcu *sf_acts;
+
+	spinlock_t lock;	/* Lock for values below. */
+	unsigned long used;	/* Last used time (in jiffies). */
+	u64 packet_count;	/* Number of packets matched. */
+	u64 byte_count;		/* Number of bytes matched. */
+	u8 tcp_flags;		/* Union of seen TCP flags. */
+};
+
+struct arp_eth_header {
+	__be16      ar_hrd;	/* format of hardware address   */
+	__be16      ar_pro;	/* format of protocol address   */
+	unsigned char   ar_hln;	/* length of hardware address   */
+	unsigned char   ar_pln;	/* length of protocol address   */
+	__be16      ar_op;	/* ARP opcode (command)     */
+
+	/* Ethernet+IPv4 specific members. */
+	unsigned char       ar_sha[ETH_ALEN];	/* sender hardware address  */
+	unsigned char       ar_sip[4];		/* sender IP address        */
+	unsigned char       ar_tha[ETH_ALEN];	/* target hardware address  */
+	unsigned char       ar_tip[4];		/* target IP address        */
+} __packed;
+
+int ovs_flow_init(void);
+void ovs_flow_exit(void);
+
+struct sw_flow *ovs_flow_alloc(void);
+void ovs_flow_deferred_free(struct sw_flow *);
+void ovs_flow_free(struct sw_flow *flow);
+
+struct sw_flow_actions *ovs_flow_actions_alloc(const struct nlattr *);
+void ovs_flow_deferred_free_acts(struct sw_flow_actions *);
+
+int ovs_flow_extract(struct sk_buff *, u16 in_port, struct sw_flow_key *,
+		     int *key_lenp);
+void ovs_flow_used(struct sw_flow *, struct sk_buff *);
+u64 ovs_flow_used_time(unsigned long flow_jiffies);
+
+/* Upper bound on the length of a nlattr-formatted flow key.  The longest
+ * nlattr-formatted flow key would be:
+ *
+ *                         struct  pad  nl hdr  total
+ *                         ------  ---  ------  -----
+ *  OVS_KEY_ATTR_PRIORITY      4    --     4      8
+ *  OVS_KEY_ATTR_IN_PORT       4    --     4      8
+ *  OVS_KEY_ATTR_ETHERNET     12    --     4     16
+ *  OVS_KEY_ATTR_8021Q         4    --     4      8
+ *  OVS_KEY_ATTR_ETHERTYPE     2     2     4      8
+ *  OVS_KEY_ATTR_IPV6         40    --     4     44
+ *  OVS_KEY_ATTR_ICMPV6        2     2     4      8
+ *  OVS_KEY_ATTR_ND           28    --     4     32
+ *  -------------------------------------------------
+ *  total                                       132
+ */
+#define FLOW_BUFSIZE 132
+
+int ovs_flow_to_nlattrs(const struct sw_flow_key *, struct sk_buff *);
+int ovs_flow_from_nlattrs(struct sw_flow_key *swkey, int *key_lenp,
+		      const struct nlattr *);
+int ovs_flow_metadata_from_nlattrs(u32 *priority, u16 *in_port,
+			       const struct nlattr *);
+
+#define TBL_MIN_BUCKETS		1024
+
+struct flow_table {
+	struct flex_array *buckets;
+	unsigned int count, n_buckets;
+	struct rcu_head rcu;
+	int node_ver;
+	u32 hash_seed;
+	bool keep_flows;
+};
+
+static inline int ovs_flow_tbl_count(struct flow_table *table)
+{
+	return table->count;
+}
+
+static inline int ovs_flow_tbl_need_to_expand(struct flow_table *table)
+{
+	return (table->count > table->n_buckets);
+}
+
+struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *table,
+				    struct sw_flow_key *key, int len);
+void ovs_flow_tbl_destroy(struct flow_table *table);
+void ovs_flow_tbl_deferred_destroy(struct flow_table *table);
+struct flow_table *ovs_flow_tbl_alloc(int new_size);
+struct flow_table *ovs_flow_tbl_expand(struct flow_table *table);
+struct flow_table *ovs_flow_tbl_rehash(struct flow_table *table);
+void ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow);
+void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow);
+u32 ovs_flow_hash(const struct sw_flow_key *key, int key_len);
+
+struct sw_flow *ovs_flow_tbl_next(struct flow_table *table, u32 *bucket, u32 *idx);
+extern const int ovs_key_lens[OVS_KEY_ATTR_MAX + 1];
+
+#endif /* flow.h */
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
new file mode 100644
index 0000000..8fc28b8
--- /dev/null
+++ b/net/openvswitch/vport-internal_dev.c
@@ -0,0 +1,241 @@
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include <linux/hardirq.h>
+#include <linux/if_vlan.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/ethtool.h>
+#include <linux/skbuff.h>
+#include <linux/version.h>
+
+#include "datapath.h"
+#include "vport-internal_dev.h"
+#include "vport-netdev.h"
+
+struct internal_dev {
+	struct vport *vport;
+};
+
+static struct internal_dev *internal_dev_priv(struct net_device *netdev)
+{
+	return netdev_priv(netdev);
+}
+
+/* This function is only called by the kernel network layer.*/
+static struct rtnl_link_stats64 *internal_dev_get_stats(struct net_device *netdev,
+							struct rtnl_link_stats64 *stats)
+{
+	struct vport *vport = ovs_internal_dev_get_vport(netdev);
+	struct ovs_vport_stats vport_stats;
+
+	ovs_vport_get_stats(vport, &vport_stats);
+
+	/* The tx and rx stats need to be swapped because the
+	 * switch and host OS have opposite perspectives. */
+	stats->rx_packets	= vport_stats.tx_packets;
+	stats->tx_packets	= vport_stats.rx_packets;
+	stats->rx_bytes		= vport_stats.tx_bytes;
+	stats->tx_bytes		= vport_stats.rx_bytes;
+	stats->rx_errors	= vport_stats.tx_errors;
+	stats->tx_errors	= vport_stats.rx_errors;
+	stats->rx_dropped	= vport_stats.tx_dropped;
+	stats->tx_dropped	= vport_stats.rx_dropped;
+
+	return stats;
+}
+
+static int internal_dev_mac_addr(struct net_device *dev, void *p)
+{
+	struct sockaddr *addr = p;
+
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EADDRNOTAVAIL;
+	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
+	return 0;
+}
+
+/* Called with rcu_read_lock_bh. */
+static int internal_dev_xmit(struct sk_buff *skb, struct net_device *netdev)
+{
+	rcu_read_lock();
+	ovs_vport_receive(internal_dev_priv(netdev)->vport, skb);
+	rcu_read_unlock();
+	return 0;
+}
+
+static int internal_dev_open(struct net_device *netdev)
+{
+	netif_start_queue(netdev);
+	return 0;
+}
+
+static int internal_dev_stop(struct net_device *netdev)
+{
+	netif_stop_queue(netdev);
+	return 0;
+}
+
+static void internal_dev_getinfo(struct net_device *netdev,
+				 struct ethtool_drvinfo *info)
+{
+	strcpy(info->driver, "openvswitch");
+}
+
+static const struct ethtool_ops internal_dev_ethtool_ops = {
+	.get_drvinfo	= internal_dev_getinfo,
+	.get_link	= ethtool_op_get_link,
+};
+
+static int internal_dev_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	if (new_mtu < 68)
+		return -EINVAL;
+
+	netdev->mtu = new_mtu;
+	return 0;
+}
+
+static void internal_dev_destructor(struct net_device *dev)
+{
+	struct vport *vport = ovs_internal_dev_get_vport(dev);
+
+	ovs_vport_free(vport);
+	free_netdev(dev);
+}
+
+static const struct net_device_ops internal_dev_netdev_ops = {
+	.ndo_open = internal_dev_open,
+	.ndo_stop = internal_dev_stop,
+	.ndo_start_xmit = internal_dev_xmit,
+	.ndo_set_mac_address = internal_dev_mac_addr,
+	.ndo_change_mtu = internal_dev_change_mtu,
+	.ndo_get_stats64 = internal_dev_get_stats,
+};
+
+static void do_setup(struct net_device *netdev)
+{
+	ether_setup(netdev);
+
+	netdev->netdev_ops = &internal_dev_netdev_ops;
+
+	netdev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	netdev->destructor = internal_dev_destructor;
+	SET_ETHTOOL_OPS(netdev, &internal_dev_ethtool_ops);
+	netdev->tx_queue_len = 0;
+
+	netdev->features = NETIF_F_LLTX | NETIF_F_SG | NETIF_F_FRAGLIST |
+				NETIF_F_HIGHDMA | NETIF_F_HW_CSUM | NETIF_F_TSO;
+
+	netdev->vlan_features = netdev->features;
+	netdev->features |= NETIF_F_HW_VLAN_TX;
+	netdev->hw_features = netdev->features & ~NETIF_F_LLTX;
+	random_ether_addr(netdev->dev_addr);
+}
+
+static struct vport *internal_dev_create(const struct vport_parms *parms)
+{
+	struct vport *vport;
+	struct netdev_vport *netdev_vport;
+	struct internal_dev *internal_dev;
+	int err;
+
+	vport = ovs_vport_alloc(sizeof(struct netdev_vport),
+				&ovs_internal_vport_ops, parms);
+	if (IS_ERR(vport)) {
+		err = PTR_ERR(vport);
+		goto error;
+	}
+
+	netdev_vport = netdev_vport_priv(vport);
+
+	netdev_vport->dev = alloc_netdev(sizeof(struct internal_dev),
+					 parms->name, do_setup);
+	if (!netdev_vport->dev) {
+		err = -ENOMEM;
+		goto error_free_vport;
+	}
+
+	internal_dev = internal_dev_priv(netdev_vport->dev);
+	internal_dev->vport = vport;
+
+	err = register_netdevice(netdev_vport->dev);
+	if (err)
+		goto error_free_netdev;
+
+	dev_set_promiscuity(netdev_vport->dev, 1);
+	netif_start_queue(netdev_vport->dev);
+
+	return vport;
+
+error_free_netdev:
+	free_netdev(netdev_vport->dev);
+error_free_vport:
+	ovs_vport_free(vport);
+error:
+	return ERR_PTR(err);
+}
+
+static void internal_dev_destroy(struct vport *vport)
+{
+	struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+
+	netif_stop_queue(netdev_vport->dev);
+	dev_set_promiscuity(netdev_vport->dev, -1);
+
+	/* unregister_netdevice() waits for an RCU grace period. */
+	unregister_netdevice(netdev_vport->dev);
+}
+
+static int internal_dev_recv(struct vport *vport, struct sk_buff *skb)
+{
+	struct net_device *netdev = netdev_vport_priv(vport)->dev;
+	int len;
+
+	len = skb->len;
+	skb->dev = netdev;
+	skb->pkt_type = PACKET_HOST;
+	skb->protocol = eth_type_trans(skb, netdev);
+
+	netif_rx(skb);
+
+	return len;
+}
+
+const struct vport_ops ovs_internal_vport_ops = {
+	.type		= OVS_VPORT_TYPE_INTERNAL,
+	.create		= internal_dev_create,
+	.destroy	= internal_dev_destroy,
+	.get_name	= ovs_netdev_get_name,
+	.get_ifindex	= ovs_netdev_get_ifindex,
+	.send		= internal_dev_recv,
+};
+
+int ovs_is_internal_dev(const struct net_device *netdev)
+{
+	return netdev->netdev_ops == &internal_dev_netdev_ops;
+}
+
+struct vport *ovs_internal_dev_get_vport(struct net_device *netdev)
+{
+	if (!ovs_is_internal_dev(netdev))
+		return NULL;
+
+	return internal_dev_priv(netdev)->vport;
+}
diff --git a/net/openvswitch/vport-internal_dev.h b/net/openvswitch/vport-internal_dev.h
new file mode 100644
index 0000000..3454447
--- /dev/null
+++ b/net/openvswitch/vport-internal_dev.h
@@ -0,0 +1,28 @@
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef VPORT_INTERNAL_DEV_H
+#define VPORT_INTERNAL_DEV_H 1
+
+#include "datapath.h"
+#include "vport.h"
+
+int ovs_is_internal_dev(const struct net_device *);
+struct vport *ovs_internal_dev_get_vport(struct net_device *);
+
+#endif /* vport-internal_dev.h */
diff --git a/net/openvswitch/vport-netdev.c b/net/openvswitch/vport-netdev.c
new file mode 100644
index 0000000..c1068ae
--- /dev/null
+++ b/net/openvswitch/vport-netdev.c
@@ -0,0 +1,198 @@
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/if_arp.h>
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
+#include <linux/kernel.h>
+#include <linux/llc.h>
+#include <linux/rtnetlink.h>
+#include <linux/skbuff.h>
+
+#include <net/llc.h>
+
+#include "datapath.h"
+#include "vport-internal_dev.h"
+#include "vport-netdev.h"
+
+/* Must be called with rcu_read_lock. */
+static void netdev_port_receive(struct vport *vport, struct sk_buff *skb)
+{
+	if (unlikely(!vport)) {
+		kfree_skb(skb);
+		return;
+	}
+
+	/* Make our own copy of the packet.  Otherwise we will mangle the
+	 * packet for anyone who came before us (e.g. tcpdump via AF_PACKET).
+	 * (No one comes after us, since we tell handle_bridge() that we took
+	 * the packet.) */
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (unlikely(!skb))
+		return;
+
+	skb_push(skb, ETH_HLEN);
+	ovs_vport_receive(vport, skb);
+}
+
+/* Called with rcu_read_lock and bottom-halves disabled. */
+static rx_handler_result_t netdev_frame_hook(struct sk_buff **pskb)
+{
+	struct sk_buff *skb = *pskb;
+	struct vport *vport;
+
+	if (unlikely(skb->pkt_type == PACKET_LOOPBACK))
+		return RX_HANDLER_PASS;
+
+	vport = ovs_netdev_get_vport(skb->dev);
+
+	netdev_port_receive(vport, skb);
+
+	return RX_HANDLER_CONSUMED;
+}
+
+static struct vport *netdev_create(const struct vport_parms *parms)
+{
+	struct vport *vport;
+	struct netdev_vport *netdev_vport;
+	int err;
+
+	vport = ovs_vport_alloc(sizeof(struct netdev_vport),
+				&ovs_netdev_vport_ops, parms);
+	if (IS_ERR(vport)) {
+		err = PTR_ERR(vport);
+		goto error;
+	}
+
+	netdev_vport = netdev_vport_priv(vport);
+
+	netdev_vport->dev = dev_get_by_name(&init_net, parms->name);
+	if (!netdev_vport->dev) {
+		err = -ENODEV;
+		goto error_free_vport;
+	}
+
+	if (netdev_vport->dev->flags & IFF_LOOPBACK ||
+	    netdev_vport->dev->type != ARPHRD_ETHER ||
+	    ovs_is_internal_dev(netdev_vport->dev)) {
+		err = -EINVAL;
+		goto error_put;
+	}
+
+	err = netdev_rx_handler_register(netdev_vport->dev, netdev_frame_hook,
+					 vport);
+	if (err)
+		goto error_put;
+
+	dev_set_promiscuity(netdev_vport->dev, 1);
+	netdev_vport->dev->priv_flags |= IFF_OVS_DATAPATH;
+
+	return vport;
+
+error_put:
+	dev_put(netdev_vport->dev);
+error_free_vport:
+	ovs_vport_free(vport);
+error:
+	return ERR_PTR(err);
+}
+
+static void netdev_destroy(struct vport *vport)
+{
+	struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+
+	netdev_vport->dev->priv_flags &= ~IFF_OVS_DATAPATH;
+	netdev_rx_handler_unregister(netdev_vport->dev);
+	dev_set_promiscuity(netdev_vport->dev, -1);
+
+	synchronize_rcu();
+
+	dev_put(netdev_vport->dev);
+	ovs_vport_free(vport);
+}
+
+const char *ovs_netdev_get_name(const struct vport *vport)
+{
+	const struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+	return netdev_vport->dev->name;
+}
+
+int ovs_netdev_get_ifindex(const struct vport *vport)
+{
+	const struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+	return netdev_vport->dev->ifindex;
+}
+
+static unsigned packet_length(const struct sk_buff *skb)
+{
+	unsigned length = skb->len - ETH_HLEN;
+
+	if (skb->protocol == htons(ETH_P_8021Q))
+		length -= VLAN_HLEN;
+
+	return length;
+}
+
+static int netdev_send(struct vport *vport, struct sk_buff *skb)
+{
+	struct netdev_vport *netdev_vport = netdev_vport_priv(vport);
+	int mtu = netdev_vport->dev->mtu;
+	int len;
+
+	if (unlikely(packet_length(skb) > mtu && !skb_is_gso(skb))) {
+		if (net_ratelimit())
+			pr_warn("%s: dropped over-mtu packet: %d > %d\n",
+				ovs_dp_name(vport->dp), packet_length(skb), mtu);
+		goto error;
+	}
+
+	if (unlikely(skb_warn_if_lro(skb)))
+		goto error;
+
+	skb->dev = netdev_vport->dev;
+	len = skb->len;
+	dev_queue_xmit(skb);
+
+	return len;
+
+error:
+	kfree_skb(skb);
+	ovs_vport_record_error(vport, VPORT_E_TX_DROPPED);
+	return 0;
+}
+
+/* Returns null if this device is not attached to a datapath. */
+struct vport *ovs_netdev_get_vport(struct net_device *dev)
+{
+	if (likely(dev->priv_flags & IFF_OVS_DATAPATH))
+		return (struct vport *)
+			rcu_dereference_rtnl(dev->rx_handler_data);
+	else
+		return NULL;
+}
+
+const struct vport_ops ovs_netdev_vport_ops = {
+	.type		= OVS_VPORT_TYPE_NETDEV,
+	.create		= netdev_create,
+	.destroy	= netdev_destroy,
+	.get_name	= ovs_netdev_get_name,
+	.get_ifindex	= ovs_netdev_get_ifindex,
+	.send		= netdev_send,
+};
diff --git a/net/openvswitch/vport-netdev.h b/net/openvswitch/vport-netdev.h
new file mode 100644
index 0000000..fd9b008
--- /dev/null
+++ b/net/openvswitch/vport-netdev.h
@@ -0,0 +1,42 @@
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef VPORT_NETDEV_H
+#define VPORT_NETDEV_H 1
+
+#include <linux/netdevice.h>
+
+#include "vport.h"
+
+struct vport *ovs_netdev_get_vport(struct net_device *dev);
+
+struct netdev_vport {
+	struct net_device *dev;
+};
+
+static inline struct netdev_vport *
+netdev_vport_priv(const struct vport *vport)
+{
+	return vport_priv(vport);
+}
+
+const char *ovs_netdev_get_name(const struct vport *);
+const char *ovs_netdev_get_config(const struct vport *);
+int ovs_netdev_get_ifindex(const struct vport *);
+
+#endif /* vport_netdev.h */
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
new file mode 100644
index 0000000..7f0ef37
--- /dev/null
+++ b/net/openvswitch/vport.c
@@ -0,0 +1,398 @@
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#include <linux/dcache.h>
+#include <linux/etherdevice.h>
+#include <linux/if.h>
+#include <linux/if_vlan.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/percpu.h>
+#include <linux/rcupdate.h>
+#include <linux/rtnetlink.h>
+#include <linux/compat.h>
+#include <linux/version.h>
+
+#include "vport.h"
+#include "vport-internal_dev.h"
+
+/* List of statically compiled vport implementations.  Don't forget to also
+ * add yours to the list at the bottom of vport.h. */
+static const struct vport_ops *vport_ops_list[] = {
+	&ovs_netdev_vport_ops,
+	&ovs_internal_vport_ops,
+};
+
+/* Protected by RCU read lock for reading, RTNL lock for writing. */
+static struct hlist_head *dev_table;
+#define VPORT_HASH_BUCKETS 1024
+
+/**
+ *	ovs_vport_init - initialize vport subsystem
+ *
+ * Called at module load time to initialize the vport subsystem.
+ */
+int ovs_vport_init(void)
+{
+	dev_table = kzalloc(VPORT_HASH_BUCKETS * sizeof(struct hlist_head),
+			    GFP_KERNEL);
+	if (!dev_table)
+		return -ENOMEM;
+
+	return 0;
+}
+
+/**
+ *	ovs_vport_exit - shutdown vport subsystem
+ *
+ * Called at module exit time to shutdown the vport subsystem.
+ */
+void ovs_vport_exit(void)
+{
+	kfree(dev_table);
+}
+
+static struct hlist_head *hash_bucket(const char *name)
+{
+	unsigned int hash = full_name_hash(name, strlen(name));
+	return &dev_table[hash & (VPORT_HASH_BUCKETS - 1)];
+}
+
+/**
+ *	ovs_vport_locate - find a port that has already been created
+ *
+ * @name: name of port to find
+ *
+ * Must be called with RTNL or RCU read lock.
+ */
+struct vport *ovs_vport_locate(const char *name)
+{
+	struct hlist_head *bucket = hash_bucket(name);
+	struct vport *vport;
+	struct hlist_node *node;
+
+	hlist_for_each_entry_rcu(vport, node, bucket, hash_node)
+		if (!strcmp(name, vport->ops->get_name(vport)))
+			return vport;
+
+	return NULL;
+}
+
+/**
+ *	ovs_vport_alloc - allocate and initialize new vport
+ *
+ * @priv_size: Size of private data area to allocate.
+ * @ops: vport device ops
+ *
+ * Allocate and initialize a new vport defined by @ops.  The vport will contain
+ * a private data area of size @priv_size that can be accessed using
+ * vport_priv().  vports that are no longer needed should be released with
+ * vport_free().
+ */
+struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
+			  const struct vport_parms *parms)
+{
+	struct vport *vport;
+	size_t alloc_size;
+
+	alloc_size = sizeof(struct vport);
+	if (priv_size) {
+		alloc_size = ALIGN(alloc_size, VPORT_ALIGN);
+		alloc_size += priv_size;
+	}
+
+	vport = kzalloc(alloc_size, GFP_KERNEL);
+	if (!vport)
+		return ERR_PTR(-ENOMEM);
+
+	vport->dp = parms->dp;
+	vport->port_no = parms->port_no;
+	vport->upcall_pid = parms->upcall_pid;
+	vport->ops = ops;
+
+	vport->percpu_stats = alloc_percpu(struct vport_percpu_stats);
+	if (!vport->percpu_stats) {
+		kfree(vport);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	spin_lock_init(&vport->stats_lock);
+
+	return vport;
+}
+
+/**
+ *	ovs_vport_free - uninitialize and free vport
+ *
+ * @vport: vport to free
+ *
+ * Frees a vport allocated with vport_alloc() when it is no longer needed.
+ *
+ * The caller must ensure that an RCU grace period has passed since the last
+ * time @vport was in a datapath.
+ */
+void ovs_vport_free(struct vport *vport)
+{
+	free_percpu(vport->percpu_stats);
+	kfree(vport);
+}
+
+/**
+ *	ovs_vport_add - add vport device (for kernel callers)
+ *
+ * @parms: Information about new vport.
+ *
+ * Creates a new vport with the specified configuration (which is dependent on
+ * device type).  RTNL lock must be held.
+ */
+struct vport *ovs_vport_add(const struct vport_parms *parms)
+{
+	struct vport *vport;
+	int err = 0;
+	int i;
+
+	ASSERT_RTNL();
+
+	for (i = 0; i < ARRAY_SIZE(vport_ops_list); i++) {
+		if (vport_ops_list[i]->type == parms->type) {
+			vport = vport_ops_list[i]->create(parms);
+			if (IS_ERR(vport)) {
+				err = PTR_ERR(vport);
+				goto out;
+			}
+
+			hlist_add_head_rcu(&vport->hash_node,
+					   hash_bucket(vport->ops->get_name(vport)));
+			return vport;
+		}
+	}
+
+	err = -EAFNOSUPPORT;
+
+out:
+	return ERR_PTR(err);
+}
+
+/**
+ *	ovs_vport_set_options - modify existing vport device (for kernel callers)
+ *
+ * @vport: vport to modify.
+ * @port: New configuration.
+ *
+ * Modifies an existing device with the specified configuration (which is
+ * dependent on device type).  RTNL lock must be held.
+ */
+int ovs_vport_set_options(struct vport *vport, struct nlattr *options)
+{
+	ASSERT_RTNL();
+
+	if (!vport->ops->set_options)
+		return -EOPNOTSUPP;
+	return vport->ops->set_options(vport, options);
+}
+
+/**
+ *	ovs_vport_del - delete existing vport device
+ *
+ * @vport: vport to delete.
+ *
+ * Detaches @vport from its datapath and destroys it.  It is possible to fail
+ * for reasons such as lack of memory.  RTNL lock must be held.
+ */
+void ovs_vport_del(struct vport *vport)
+{
+	ASSERT_RTNL();
+
+	hlist_del_rcu(&vport->hash_node);
+
+	vport->ops->destroy(vport);
+}
+
+/**
+ *	ovs_vport_get_stats - retrieve device stats
+ *
+ * @vport: vport from which to retrieve the stats
+ * @stats: location to store stats
+ *
+ * Retrieves transmit, receive, and error stats for the given device.
+ *
+ * Must be called with RTNL lock or rcu_read_lock.
+ */
+void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats)
+{
+	int i;
+
+	memset(stats, 0, sizeof(*stats));
+
+	/* We potentially have 2 sources of stats that need to be combined:
+	 * those we have collected (split into err_stats and percpu_stats) from
+	 * set_stats() and device error stats from netdev->get_stats() (for
+	 * errors that happen  downstream and therefore aren't reported through
+	 * our vport_record_error() function).
+	 * Stats from first source are reported by ovs (OVS_VPORT_ATTR_STATS).
+	 * netdev-stats can be directly read over netlink-ioctl.
+	 */
+
+	spin_lock_bh(&vport->stats_lock);
+
+	stats->rx_errors	= vport->err_stats.rx_errors;
+	stats->tx_errors	= vport->err_stats.tx_errors;
+	stats->tx_dropped	= vport->err_stats.tx_dropped;
+	stats->rx_dropped	= vport->err_stats.rx_dropped;
+
+	spin_unlock_bh(&vport->stats_lock);
+
+	for_each_possible_cpu(i) {
+		const struct vport_percpu_stats *percpu_stats;
+		struct vport_percpu_stats local_stats;
+		unsigned int start;
+
+		percpu_stats = per_cpu_ptr(vport->percpu_stats, i);
+
+		do {
+			start = u64_stats_fetch_begin_bh(&percpu_stats->sync);
+			local_stats = *percpu_stats;
+		} while (u64_stats_fetch_retry_bh(&percpu_stats->sync, start));
+
+		stats->rx_bytes		+= local_stats.rx_bytes;
+		stats->rx_packets	+= local_stats.rx_packets;
+		stats->tx_bytes		+= local_stats.tx_bytes;
+		stats->tx_packets	+= local_stats.tx_packets;
+	}
+}
+
+/**
+ *	ovs_vport_get_options - retrieve device options
+ *
+ * @vport: vport from which to retrieve the options.
+ * @skb: sk_buff where options should be appended.
+ *
+ * Retrieves the configuration of the given device, appending an
+ * %OVS_VPORT_ATTR_OPTIONS attribute that in turn contains nested
+ * vport-specific attributes to @skb.
+ *
+ * Returns 0 if successful, -EMSGSIZE if @skb has insufficient room, or another
+ * negative error code if a real error occurred.  If an error occurs, @skb is
+ * left unmodified.
+ *
+ * Must be called with RTNL lock or rcu_read_lock.
+ */
+int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb)
+{
+	struct nlattr *nla;
+
+	nla = nla_nest_start(skb, OVS_VPORT_ATTR_OPTIONS);
+	if (!nla)
+		return -EMSGSIZE;
+
+	if (vport->ops->get_options) {
+		int err = vport->ops->get_options(vport, skb);
+		if (err) {
+			nla_nest_cancel(skb, nla);
+			return err;
+		}
+	}
+
+	nla_nest_end(skb, nla);
+	return 0;
+}
+
+/**
+ *	ovs_vport_receive - pass up received packet to the datapath for processing
+ *
+ * @vport: vport that received the packet
+ * @skb: skb that was received
+ *
+ * Must be called with rcu_read_lock.  The packet cannot be shared and
+ * skb->data should point to the Ethernet header.  The caller must have already
+ * called compute_ip_summed() to initialize the checksumming fields.
+ */
+void ovs_vport_receive(struct vport *vport, struct sk_buff *skb)
+{
+	struct vport_percpu_stats *stats;
+
+	stats = per_cpu_ptr(vport->percpu_stats, smp_processor_id());
+
+	u64_stats_update_begin(&stats->sync);
+	stats->rx_packets++;
+	stats->rx_bytes += skb->len;
+	u64_stats_update_end(&stats->sync);
+
+	ovs_dp_process_received_packet(vport, skb);
+}
+
+/**
+ *	ovs_vport_send - send a packet on a device
+ *
+ * @vport: vport on which to send the packet
+ * @skb: skb to send
+ *
+ * Sends the given packet and returns the length of data sent.  Either RTNL
+ * lock or rcu_read_lock must be held.
+ */
+int ovs_vport_send(struct vport *vport, struct sk_buff *skb)
+{
+	int sent = vport->ops->send(vport, skb);
+
+	if (likely(sent)) {
+		struct vport_percpu_stats *stats;
+
+		stats = per_cpu_ptr(vport->percpu_stats, smp_processor_id());
+
+		u64_stats_update_begin(&stats->sync);
+		stats->tx_packets++;
+		stats->tx_bytes += sent;
+		u64_stats_update_end(&stats->sync);
+	}
+	return sent;
+}
+
+/**
+ *	ovs_vport_record_error - indicate device error to generic stats layer
+ *
+ * @vport: vport that encountered the error
+ * @err_type: one of enum vport_err_type types to indicate the error type
+ *
+ * If using the vport generic stats layer indicate that an error of the given
+ * type has occured.
+ */
+void ovs_vport_record_error(struct vport *vport, enum vport_err_type err_type)
+{
+	spin_lock(&vport->stats_lock);
+
+	switch (err_type) {
+	case VPORT_E_RX_DROPPED:
+		vport->err_stats.rx_dropped++;
+		break;
+
+	case VPORT_E_RX_ERROR:
+		vport->err_stats.rx_errors++;
+		break;
+
+	case VPORT_E_TX_DROPPED:
+		vport->err_stats.tx_dropped++;
+		break;
+
+	case VPORT_E_TX_ERROR:
+		vport->err_stats.tx_errors++;
+		break;
+	};
+
+	spin_unlock(&vport->stats_lock);
+}
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
new file mode 100644
index 0000000..1960962
--- /dev/null
+++ b/net/openvswitch/vport.h
@@ -0,0 +1,205 @@
+/*
+ * Copyright (c) 2007-2011 Nicira Networks.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA
+ */
+
+#ifndef VPORT_H
+#define VPORT_H 1
+
+#include <linux/list.h>
+#include <linux/openvswitch.h>
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+#include <linux/u64_stats_sync.h>
+
+#include "datapath.h"
+
+struct vport;
+struct vport_parms;
+
+/* The following definitions are for users of the vport subsytem: */
+
+int ovs_vport_init(void);
+void ovs_vport_exit(void);
+
+struct vport *ovs_vport_add(const struct vport_parms *);
+void ovs_vport_del(struct vport *);
+
+struct vport *ovs_vport_locate(const char *name);
+
+void ovs_vport_get_stats(struct vport *, struct ovs_vport_stats *);
+
+int ovs_vport_set_options(struct vport *, struct nlattr *options);
+int ovs_vport_get_options(const struct vport *, struct sk_buff *);
+
+int ovs_vport_send(struct vport *, struct sk_buff *);
+
+/* The following definitions are for implementers of vport devices: */
+
+struct vport_percpu_stats {
+	u64 rx_bytes;
+	u64 rx_packets;
+	u64 tx_bytes;
+	u64 tx_packets;
+	struct u64_stats_sync sync;
+};
+
+struct vport_err_stats {
+	u64 rx_dropped;
+	u64 rx_errors;
+	u64 tx_dropped;
+	u64 tx_errors;
+};
+
+/**
+ * struct vport - one port within a datapath
+ * @rcu: RCU callback head for deferred destruction.
+ * @port_no: Index into @dp's @ports array.
+ * @dp: Datapath to which this port belongs.
+ * @node: Element in @dp's @port_list.
+ * @upcall_pid: The Netlink port to use for packets received on this port that
+ * miss the flow table.
+ * @hash_node: Element in @dev_table hash table in vport.c.
+ * @ops: Class structure.
+ * @percpu_stats: Points to per-CPU statistics used and maintained by vport
+ * @stats_lock: Protects @err_stats;
+ * @err_stats: Points to error statistics used and maintained by vport
+ */
+struct vport {
+	struct rcu_head rcu;
+	u16 port_no;
+	struct datapath	*dp;
+	struct list_head node;
+	u32 upcall_pid;
+
+	struct hlist_node hash_node;
+	const struct vport_ops *ops;
+
+	struct vport_percpu_stats __percpu *percpu_stats;
+
+	spinlock_t stats_lock;
+	struct vport_err_stats err_stats;
+};
+
+/**
+ * struct vport_parms - parameters for creating a new vport
+ *
+ * @name: New vport's name.
+ * @type: New vport's type.
+ * @options: %OVS_VPORT_ATTR_OPTIONS attribute from Netlink message, %NULL if
+ * none was supplied.
+ * @dp: New vport's datapath.
+ * @port_no: New vport's port number.
+ */
+struct vport_parms {
+	const char *name;
+	enum ovs_vport_type type;
+	struct nlattr *options;
+
+	/* For ovs_vport_alloc(). */
+	struct datapath *dp;
+	u16 port_no;
+	u32 upcall_pid;
+};
+
+/**
+ * struct vport_ops - definition of a type of virtual port
+ *
+ * @type: %OVS_VPORT_TYPE_* value for this type of virtual port.
+ * @create: Create a new vport configured as specified.  On success returns
+ * a new vport allocated with ovs_vport_alloc(), otherwise an ERR_PTR() value.
+ * @destroy: Destroys a vport.  Must call vport_free() on the vport but not
+ * before an RCU grace period has elapsed.
+ * @set_options: Modify the configuration of an existing vport.  May be %NULL
+ * if modification is not supported.
+ * @get_options: Appends vport-specific attributes for the configuration of an
+ * existing vport to a &struct sk_buff.  May be %NULL for a vport that does not
+ * have any configuration.
+ * @get_name: Get the device's name.
+ * @get_config: Get the device's configuration.
+ * @get_ifindex: Get the system interface index associated with the device.
+ * May be null if the device does not have an ifindex.
+ * @send: Send a packet on the device.  Returns the length of the packet sent.
+ */
+struct vport_ops {
+	enum ovs_vport_type type;
+
+	/* Called with RTNL lock. */
+	struct vport *(*create)(const struct vport_parms *);
+	void (*destroy)(struct vport *);
+
+	int (*set_options)(struct vport *, struct nlattr *);
+	int (*get_options)(const struct vport *, struct sk_buff *);
+
+	/* Called with rcu_read_lock or RTNL lock. */
+	const char *(*get_name)(const struct vport *);
+	void (*get_config)(const struct vport *, void *);
+	int (*get_ifindex)(const struct vport *);
+
+	int (*send)(struct vport *, struct sk_buff *);
+};
+
+enum vport_err_type {
+	VPORT_E_RX_DROPPED,
+	VPORT_E_RX_ERROR,
+	VPORT_E_TX_DROPPED,
+	VPORT_E_TX_ERROR,
+};
+
+struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *,
+			      const struct vport_parms *);
+void ovs_vport_free(struct vport *);
+
+#define VPORT_ALIGN 8
+
+/**
+ *	vport_priv - access private data area of vport
+ *
+ * @vport: vport to access
+ *
+ * If a nonzero size was passed in priv_size of vport_alloc() a private data
+ * area was allocated on creation.  This allows that area to be accessed and
+ * used for any purpose needed by the vport implementer.
+ */
+static inline void *vport_priv(const struct vport *vport)
+{
+	return (u8 *)vport + ALIGN(sizeof(struct vport), VPORT_ALIGN);
+}
+
+/**
+ *	vport_from_priv - lookup vport from private data pointer
+ *
+ * @priv: Start of private data area.
+ *
+ * It is sometimes useful to translate from a pointer to the private data
+ * area to the vport, such as in the case where the private data pointer is
+ * the result of a hash table lookup.  @priv must point to the start of the
+ * private data area.
+ */
+static inline struct vport *vport_from_priv(const void *priv)
+{
+	return (struct vport *)(priv - ALIGN(sizeof(struct vport), VPORT_ALIGN));
+}
+
+void ovs_vport_receive(struct vport *, struct sk_buff *);
+void ovs_vport_record_error(struct vport *, enum vport_err_type err_type);
+
+/* List of statically compiled vport implementations.  Don't forget to also
+ * add yours to the list at the top of vport.c. */
+extern const struct vport_ops ovs_netdev_vport_ops;
+extern const struct vport_ops ovs_internal_vport_ops;
+
+#endif /* vport.h */
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 82a6f34..0da505c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1499,10 +1499,11 @@ retry:
 
 	if (!skb) {
 		size_t reserved = LL_RESERVED_SPACE(dev);
+		int tlen = dev->needed_tailroom;
 		unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0;
 
 		rcu_read_unlock();
-		skb = sock_wmalloc(sk, len + reserved, 0, GFP_KERNEL);
+		skb = sock_wmalloc(sk, len + reserved + tlen, 0, GFP_KERNEL);
 		if (skb == NULL)
 			return -ENOBUFS;
 		/* FIXME: Save some space for broken drivers that write a hard
@@ -1944,7 +1945,7 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 
 static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		void *frame, struct net_device *dev, int size_max,
-		__be16 proto, unsigned char *addr)
+		__be16 proto, unsigned char *addr, int hlen)
 {
 	union {
 		struct tpacket_hdr *h1;
@@ -1978,7 +1979,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 		return -EMSGSIZE;
 	}
 
-	skb_reserve(skb, LL_RESERVED_SPACE(dev));
+	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
 
 	data = ph.raw + po->tp_hdrlen - sizeof(struct sockaddr_ll);
@@ -2053,6 +2054,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	unsigned char *addr;
 	int len_sum = 0;
 	int status = 0;
+	int hlen, tlen;
 
 	mutex_lock(&po->pg_vec_lock);
 
@@ -2101,16 +2103,17 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 		}
 
 		status = TP_STATUS_SEND_REQUEST;
+		hlen = LL_RESERVED_SPACE(dev);
+		tlen = dev->needed_tailroom;
 		skb = sock_alloc_send_skb(&po->sk,
-				LL_ALLOCATED_SPACE(dev)
-				+ sizeof(struct sockaddr_ll),
+				hlen + tlen + sizeof(struct sockaddr_ll),
 				0, &err);
 
 		if (unlikely(skb == NULL))
 			goto out_status;
 
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
-				addr);
+				addr, hlen);
 
 		if (unlikely(tp_len < 0)) {
 			if (po->tp_loss) {
@@ -2207,6 +2210,7 @@ static int packet_snd(struct socket *sock,
 	int vnet_hdr_len;
 	struct packet_sock *po = pkt_sk(sk);
 	unsigned short gso_type = 0;
+	int hlen, tlen;
 
 	/*
 	 *	Get and verify the address.
@@ -2291,8 +2295,9 @@ static int packet_snd(struct socket *sock,
 		goto out_unlock;
 
 	err = -ENOBUFS;
-	skb = packet_alloc_skb(sk, LL_ALLOCATED_SPACE(dev),
-			       LL_RESERVED_SPACE(dev), len, vnet_hdr.hdr_len,
+	hlen = LL_RESERVED_SPACE(dev);
+	tlen = dev->needed_tailroom;
+	skb = packet_alloc_skb(sk, hlen + tlen, hlen, len, vnet_hdr.hdr_len,
 			       msg->msg_flags & MSG_DONTWAIT, &err);
 	if (skb == NULL)
 		goto out_unlock;
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 2ba6e9f..9f60008 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -534,6 +534,29 @@ static int pep_connresp_rcv(struct sock *sk, struct sk_buff *skb)
 	return pipe_handler_send_created_ind(sk);
 }
 
+static int pep_enableresp_rcv(struct sock *sk, struct sk_buff *skb)
+{
+	struct pnpipehdr *hdr = pnp_hdr(skb);
+
+	if (hdr->error_code != PN_PIPE_NO_ERROR)
+		return -ECONNREFUSED;
+
+	return pep_indicate(sk, PNS_PIPE_ENABLED_IND, 0 /* sub-blocks */,
+		NULL, 0, GFP_ATOMIC);
+
+}
+
+static void pipe_start_flow_control(struct sock *sk)
+{
+	struct pep_sock *pn = pep_sk(sk);
+
+	if (!pn_flow_safe(pn->tx_fc)) {
+		atomic_set(&pn->tx_credits, 1);
+		sk->sk_write_space(sk);
+	}
+	pipe_grant_credits(sk, GFP_ATOMIC);
+}
+
 /* Queue an skb to an actively connected sock.
  * Socket lock must be held. */
 static int pipe_handler_do_rcv(struct sock *sk, struct sk_buff *skb)
@@ -579,13 +602,25 @@ static int pipe_handler_do_rcv(struct sock *sk, struct sk_buff *skb)
 			sk->sk_state = TCP_CLOSE_WAIT;
 			break;
 		}
+		if (pn->init_enable == PN_PIPE_DISABLE)
+			sk->sk_state = TCP_SYN_RECV;
+		else {
+			sk->sk_state = TCP_ESTABLISHED;
+			pipe_start_flow_control(sk);
+		}
+		break;
 
-		sk->sk_state = TCP_ESTABLISHED;
-		if (!pn_flow_safe(pn->tx_fc)) {
-			atomic_set(&pn->tx_credits, 1);
-			sk->sk_write_space(sk);
+	case PNS_PEP_ENABLE_RESP:
+		if (sk->sk_state != TCP_SYN_SENT)
+			break;
+
+		if (pep_enableresp_rcv(sk, skb)) {
+			sk->sk_state = TCP_CLOSE_WAIT;
+			break;
 		}
-		pipe_grant_credits(sk, GFP_ATOMIC);
+
+		sk->sk_state = TCP_ESTABLISHED;
+		pipe_start_flow_control(sk);
 		break;
 
 	case PNS_PEP_DISCONNECT_RESP:
@@ -864,14 +899,32 @@ static int pep_sock_connect(struct sock *sk, struct sockaddr *addr, int len)
 	int err;
 	u8 data[4] = { 0 /* sub-blocks */, PAD, PAD, PAD };
 
-	pn->pipe_handle = 1; /* anything but INVALID_HANDLE */
+	if (pn->pipe_handle == PN_PIPE_INVALID_HANDLE)
+		pn->pipe_handle = 1; /* anything but INVALID_HANDLE */
+
 	err = pipe_handler_request(sk, PNS_PEP_CONNECT_REQ,
-					PN_PIPE_ENABLE, data, 4);
+				pn->init_enable, data, 4);
 	if (err) {
 		pn->pipe_handle = PN_PIPE_INVALID_HANDLE;
 		return err;
 	}
+
 	sk->sk_state = TCP_SYN_SENT;
+
+	return 0;
+}
+
+static int pep_sock_enable(struct sock *sk, struct sockaddr *addr, int len)
+{
+	int err;
+
+	err = pipe_handler_request(sk, PNS_PEP_ENABLE_REQ, PAD,
+				NULL, 0);
+	if (err)
+		return err;
+
+	sk->sk_state = TCP_SYN_SENT;
+
 	return 0;
 }
 
@@ -879,11 +932,14 @@ static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg)
 {
 	struct pep_sock *pn = pep_sk(sk);
 	int answ;
+	int ret = -ENOIOCTLCMD;
 
 	switch (cmd) {
 	case SIOCINQ:
-		if (sk->sk_state == TCP_LISTEN)
-			return -EINVAL;
+		if (sk->sk_state == TCP_LISTEN) {
+			ret = -EINVAL;
+			break;
+		}
 
 		lock_sock(sk);
 		if (sock_flag(sk, SOCK_URGINLINE) &&
@@ -894,10 +950,22 @@ static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg)
 		else
 			answ = 0;
 		release_sock(sk);
-		return put_user(answ, (int __user *)arg);
+		ret = put_user(answ, (int __user *)arg);
+		break;
+
+	case SIOCPNENABLEPIPE:
+		lock_sock(sk);
+		if (sk->sk_state == TCP_SYN_SENT)
+			ret =  -EBUSY;
+		else if (sk->sk_state == TCP_ESTABLISHED)
+			ret = -EISCONN;
+		else
+			ret = pep_sock_enable(sk, NULL, 0);
+		release_sock(sk);
+		break;
 	}
 
-	return -ENOIOCTLCMD;
+	return ret;
 }
 
 static int pep_init(struct sock *sk)
@@ -960,6 +1028,18 @@ static int pep_setsockopt(struct sock *sk, int level, int optname,
 		}
 		goto out_norel;
 
+	case PNPIPE_HANDLE:
+		if ((sk->sk_state == TCP_CLOSE) &&
+			(val >= 0) && (val < PN_PIPE_INVALID_HANDLE))
+			pn->pipe_handle = val;
+		else
+			err = -EINVAL;
+		break;
+
+	case PNPIPE_INITSTATE:
+		pn->init_enable = !!val;
+		break;
+
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -995,6 +1075,10 @@ static int pep_getsockopt(struct sock *sk, int level, int optname,
 			return -EINVAL;
 		break;
 
+	case PNPIPE_INITSTATE:
+		val = pn->init_enable;
+		break;
+
 	default:
 		return -ENOPROTOOPT;
 	}
diff --git a/net/rds/Kconfig b/net/rds/Kconfig
index 4cf6dc7..ec753b3 100644
--- a/net/rds/Kconfig
+++ b/net/rds/Kconfig
@@ -9,7 +9,6 @@ config RDS
 
 config RDS_RDMA
 	tristate "RDS over Infiniband and iWARP"
-	select LLIST
 	depends on RDS && INFINIBAND && INFINIBAND_ADDR_TRANS
 	---help---
 	  Allow RDS to use Infiniband and iWARP as a transport.
diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c
index 43ea7de..4cba13e 100644
--- a/net/rxrpc/ar-key.c
+++ b/net/rxrpc/ar-key.c
@@ -306,10 +306,9 @@ static int rxrpc_krb5_decode_tagged_data(struct krb5_tagged_data *td,
 	td->data_len = len;
 
 	if (len > 0) {
-		td->data = kmalloc(len, GFP_KERNEL);
+		td->data = kmemdup(xdr, len, GFP_KERNEL);
 		if (!td->data)
 			return -ENOMEM;
-		memcpy(td->data, xdr, len);
 		len = (len + 3) & ~3;
 		toklen -= len;
 		xdr += len >> 2;
@@ -401,10 +400,9 @@ static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen,
 	_debug("ticket len %u", len);
 
 	if (len > 0) {
-		*_ticket = kmalloc(len, GFP_KERNEL);
+		*_ticket = kmemdup(xdr, len, GFP_KERNEL);
 		if (!*_ticket)
 			return -ENOMEM;
-		memcpy(*_ticket, xdr, len);
 		len = (len + 3) & ~3;
 		toklen -= len;
 		xdr += len >> 2;
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 7b58230..1d8bd0d 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -26,6 +26,8 @@
 #include <net/pkt_cls.h>
 #include <net/ip.h>
 #include <net/route.h>
+#include <net/flow_keys.h>
+
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 #include <net/netfilter/nf_conntrack.h>
 #endif
@@ -66,134 +68,37 @@ static inline u32 addr_fold(void *addr)
 	return (a & 0xFFFFFFFF) ^ (BITS_PER_LONG > 32 ? a >> 32 : 0);
 }
 
-static u32 flow_get_src(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_src(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	__be32 *data = NULL, hdata;
-
-	switch (skb->protocol) {
-	case htons(ETH_P_IP):
-		data = skb_header_pointer(skb,
-					  nhoff + offsetof(struct iphdr,
-							   saddr),
-					  4, &hdata);
-		break;
-	case htons(ETH_P_IPV6):
-		data = skb_header_pointer(skb,
-					 nhoff + offsetof(struct ipv6hdr,
-							  saddr.s6_addr32[3]),
-					 4, &hdata);
-		break;
-	}
-
-	if (data)
-		return ntohl(*data);
+	if (flow->src)
+		return ntohl(flow->src);
 	return addr_fold(skb->sk);
 }
 
-static u32 flow_get_dst(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	__be32 *data = NULL, hdata;
-
-	switch (skb->protocol) {
-	case htons(ETH_P_IP):
-		data = skb_header_pointer(skb,
-					  nhoff + offsetof(struct iphdr,
-							   daddr),
-					  4, &hdata);
-		break;
-	case htons(ETH_P_IPV6):
-		data = skb_header_pointer(skb,
-					 nhoff + offsetof(struct ipv6hdr,
-							  daddr.s6_addr32[3]),
-					 4, &hdata);
-		break;
-	}
-
-	if (data)
-		return ntohl(*data);
+	if (flow->dst)
+		return ntohl(flow->dst);
 	return addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol;
 }
 
-static u32 flow_get_proto(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_proto(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	__u8 *data = NULL, hdata;
-
-	switch (skb->protocol) {
-	case htons(ETH_P_IP):
-		data = skb_header_pointer(skb,
-					  nhoff + offsetof(struct iphdr,
-							   protocol),
-					  1, &hdata);
-		break;
-	case htons(ETH_P_IPV6):
-		data = skb_header_pointer(skb,
-					 nhoff + offsetof(struct ipv6hdr,
-							  nexthdr),
-					 1, &hdata);
-		break;
-	}
-	if (data)
-		return *data;
-	return 0;
+	return flow->ip_proto;
 }
 
-/* helper function to get either src or dst port */
-static __be16 *flow_get_proto_common(const struct sk_buff *skb, int nhoff,
-				     __be16 *_port, int dst)
+static u32 flow_get_proto_src(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	__be16 *port = NULL;
-	int poff;
-
-	switch (skb->protocol) {
-	case htons(ETH_P_IP): {
-		struct iphdr *iph, _iph;
-
-		iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
-		if (!iph)
-			break;
-		if (ip_is_fragment(iph))
-			break;
-		poff = proto_ports_offset(iph->protocol);
-		if (poff >= 0)
-			port = skb_header_pointer(skb,
-					nhoff + iph->ihl * 4 + poff + dst,
-					sizeof(*_port), _port);
-		break;
-	}
-	case htons(ETH_P_IPV6): {
-		struct ipv6hdr *iph, _iph;
-
-		iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
-		if (!iph)
-			break;
-		poff = proto_ports_offset(iph->nexthdr);
-		if (poff >= 0)
-			port = skb_header_pointer(skb,
-					nhoff + sizeof(*iph) + poff + dst,
-					sizeof(*_port), _port);
-		break;
-	}
-	}
-
-	return port;
-}
-
-static u32 flow_get_proto_src(const struct sk_buff *skb, int nhoff)
-{
-	__be16 _port, *port = flow_get_proto_common(skb, nhoff, &_port, 0);
-
-	if (port)
-		return ntohs(*port);
+	if (flow->ports)
+		return ntohs(flow->port16[0]);
 
 	return addr_fold(skb->sk);
 }
 
-static u32 flow_get_proto_dst(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_proto_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 {
-	__be16 _port, *port = flow_get_proto_common(skb, nhoff, &_port, 2);
-
-	if (port)
-		return ntohs(*port);
+	if (flow->ports)
+		return ntohs(flow->port16[1]);
 
 	return addr_fold(skb_dst(skb)) ^ (__force u16)skb->protocol;
 }
@@ -239,7 +144,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb)
 })
 #endif
 
-static u32 flow_get_nfct_src(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_nfct_src(const struct sk_buff *skb, const struct flow_keys *flow)
 {
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
@@ -248,10 +153,10 @@ static u32 flow_get_nfct_src(const struct sk_buff *skb, int nhoff)
 		return ntohl(CTTUPLE(skb, src.u3.ip6[3]));
 	}
 fallback:
-	return flow_get_src(skb, nhoff);
+	return flow_get_src(skb, flow);
 }
 
-static u32 flow_get_nfct_dst(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_nfct_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 {
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
@@ -260,21 +165,21 @@ static u32 flow_get_nfct_dst(const struct sk_buff *skb, int nhoff)
 		return ntohl(CTTUPLE(skb, dst.u3.ip6[3]));
 	}
 fallback:
-	return flow_get_dst(skb, nhoff);
+	return flow_get_dst(skb, flow);
 }
 
-static u32 flow_get_nfct_proto_src(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_nfct_proto_src(const struct sk_buff *skb, const struct flow_keys *flow)
 {
 	return ntohs(CTTUPLE(skb, src.u.all));
 fallback:
-	return flow_get_proto_src(skb, nhoff);
+	return flow_get_proto_src(skb, flow);
 }
 
-static u32 flow_get_nfct_proto_dst(const struct sk_buff *skb, int nhoff)
+static u32 flow_get_nfct_proto_dst(const struct sk_buff *skb, const struct flow_keys *flow)
 {
 	return ntohs(CTTUPLE(skb, dst.u.all));
 fallback:
-	return flow_get_proto_dst(skb, nhoff);
+	return flow_get_proto_dst(skb, flow);
 }
 
 static u32 flow_get_rtclassid(const struct sk_buff *skb)
@@ -314,21 +219,19 @@ static u32 flow_get_rxhash(struct sk_buff *skb)
 	return skb_get_rxhash(skb);
 }
 
-static u32 flow_key_get(struct sk_buff *skb, int key)
+static u32 flow_key_get(struct sk_buff *skb, int key, struct flow_keys *flow)
 {
-	int nhoff = skb_network_offset(skb);
-
 	switch (key) {
 	case FLOW_KEY_SRC:
-		return flow_get_src(skb, nhoff);
+		return flow_get_src(skb, flow);
 	case FLOW_KEY_DST:
-		return flow_get_dst(skb, nhoff);
+		return flow_get_dst(skb, flow);
 	case FLOW_KEY_PROTO:
-		return flow_get_proto(skb, nhoff);
+		return flow_get_proto(skb, flow);
 	case FLOW_KEY_PROTO_SRC:
-		return flow_get_proto_src(skb, nhoff);
+		return flow_get_proto_src(skb, flow);
 	case FLOW_KEY_PROTO_DST:
-		return flow_get_proto_dst(skb, nhoff);
+		return flow_get_proto_dst(skb, flow);
 	case FLOW_KEY_IIF:
 		return flow_get_iif(skb);
 	case FLOW_KEY_PRIORITY:
@@ -338,13 +241,13 @@ static u32 flow_key_get(struct sk_buff *skb, int key)
 	case FLOW_KEY_NFCT:
 		return flow_get_nfct(skb);
 	case FLOW_KEY_NFCT_SRC:
-		return flow_get_nfct_src(skb, nhoff);
+		return flow_get_nfct_src(skb, flow);
 	case FLOW_KEY_NFCT_DST:
-		return flow_get_nfct_dst(skb, nhoff);
+		return flow_get_nfct_dst(skb, flow);
 	case FLOW_KEY_NFCT_PROTO_SRC:
-		return flow_get_nfct_proto_src(skb, nhoff);
+		return flow_get_nfct_proto_src(skb, flow);
 	case FLOW_KEY_NFCT_PROTO_DST:
-		return flow_get_nfct_proto_dst(skb, nhoff);
+		return flow_get_nfct_proto_dst(skb, flow);
 	case FLOW_KEY_RTCLASSID:
 		return flow_get_rtclassid(skb);
 	case FLOW_KEY_SKUID:
@@ -361,6 +264,16 @@ static u32 flow_key_get(struct sk_buff *skb, int key)
 	}
 }
 
+#define FLOW_KEYS_NEEDED ((1 << FLOW_KEY_SRC) | 		\
+			  (1 << FLOW_KEY_DST) |			\
+			  (1 << FLOW_KEY_PROTO) |		\
+			  (1 << FLOW_KEY_PROTO_SRC) |		\
+			  (1 << FLOW_KEY_PROTO_DST) | 		\
+			  (1 << FLOW_KEY_NFCT_SRC) |		\
+			  (1 << FLOW_KEY_NFCT_DST) |		\
+			  (1 << FLOW_KEY_NFCT_PROTO_SRC) |	\
+			  (1 << FLOW_KEY_NFCT_PROTO_DST))
+
 static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			 struct tcf_result *res)
 {
@@ -372,17 +285,20 @@ static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 	int r;
 
 	list_for_each_entry(f, &head->filters, list) {
-		u32 keys[f->nkeys];
+		u32 keys[FLOW_KEY_MAX + 1];
+		struct flow_keys flow_keys;
 
 		if (!tcf_em_tree_match(skb, &f->ematches, NULL))
 			continue;
 
 		keymask = f->keymask;
+		if (keymask & FLOW_KEYS_NEEDED)
+			skb_flow_dissect(skb, &flow_keys);
 
 		for (n = 0; n < f->nkeys; n++) {
 			key = ffs(keymask) - 1;
 			keymask &= ~(1 << key);
-			keys[n] = flow_key_get(skb, key);
+			keys[n] = flow_key_get(skb, key, &flow_keys);
 		}
 
 		if (f->mode == FLOW_MODE_HASH)
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 3422b25..bef00ac 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -19,10 +19,7 @@
 #include <net/pkt_sched.h>
 #include <net/inet_ecn.h>
 #include <net/red.h>
-#include <linux/ip.h>
-#include <net/ip.h>
-#include <linux/ipv6.h>
-#include <net/ipv6.h>
+#include <net/flow_keys.h>
 
 /*
    CHOKe stateless AQM for fair bandwidth allocation
@@ -142,85 +139,10 @@ static void choke_drop_by_idx(struct Qdisc *sch, unsigned int idx)
 	--sch->q.qlen;
 }
 
-/*
- * Compare flow of two packets
- *  Returns true only if source and destination address and port match.
- *          false for special cases
- */
-static bool choke_match_flow(struct sk_buff *skb1,
-			     struct sk_buff *skb2)
-{
-	int off1, off2, poff;
-	const u32 *ports1, *ports2;
-	u8 ip_proto;
-	__u32 hash1;
-
-	if (skb1->protocol != skb2->protocol)
-		return false;
-
-	/* Use hash value as quick check
-	 * Assumes that __skb_get_rxhash makes IP header and ports linear
-	 */
-	hash1 = skb_get_rxhash(skb1);
-	if (!hash1 || hash1 != skb_get_rxhash(skb2))
-		return false;
-
-	/* Probably match, but be sure to avoid hash collisions */
-	off1 = skb_network_offset(skb1);
-	off2 = skb_network_offset(skb2);
-
-	switch (skb1->protocol) {
-	case __constant_htons(ETH_P_IP): {
-		const struct iphdr *ip1, *ip2;
-
-		ip1 = (const struct iphdr *) (skb1->data + off1);
-		ip2 = (const struct iphdr *) (skb2->data + off2);
-
-		ip_proto = ip1->protocol;
-		if (ip_proto != ip2->protocol ||
-		    ip1->saddr != ip2->saddr || ip1->daddr != ip2->daddr)
-			return false;
-
-		if (ip_is_fragment(ip1) | ip_is_fragment(ip2))
-			ip_proto = 0;
-		off1 += ip1->ihl * 4;
-		off2 += ip2->ihl * 4;
-		break;
-	}
-
-	case __constant_htons(ETH_P_IPV6): {
-		const struct ipv6hdr *ip1, *ip2;
-
-		ip1 = (const struct ipv6hdr *) (skb1->data + off1);
-		ip2 = (const struct ipv6hdr *) (skb2->data + off2);
-
-		ip_proto = ip1->nexthdr;
-		if (ip_proto != ip2->nexthdr ||
-		    ipv6_addr_cmp(&ip1->saddr, &ip2->saddr) ||
-		    ipv6_addr_cmp(&ip1->daddr, &ip2->daddr))
-			return false;
-		off1 += 40;
-		off2 += 40;
-	}
-
-	default: /* Maybe compare MAC header here? */
-		return false;
-	}
-
-	poff = proto_ports_offset(ip_proto);
-	if (poff < 0)
-		return true;
-
-	off1 += poff;
-	off2 += poff;
-
-	ports1 = (__force u32 *)(skb1->data + off1);
-	ports2 = (__force u32 *)(skb2->data + off2);
-	return *ports1 == *ports2;
-}
-
 struct choke_skb_cb {
-	u16 classid;
+	u16			classid;
+	u8			keys_valid;
+	struct flow_keys	keys;
 };
 
 static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb)
@@ -241,6 +163,32 @@ static u16 choke_get_classid(const struct sk_buff *skb)
 }
 
 /*
+ * Compare flow of two packets
+ *  Returns true only if source and destination address and port match.
+ *          false for special cases
+ */
+static bool choke_match_flow(struct sk_buff *skb1,
+			     struct sk_buff *skb2)
+{
+	if (skb1->protocol != skb2->protocol)
+		return false;
+
+	if (!choke_skb_cb(skb1)->keys_valid) {
+		choke_skb_cb(skb1)->keys_valid = 1;
+		skb_flow_dissect(skb1, &choke_skb_cb(skb1)->keys);
+	}
+
+	if (!choke_skb_cb(skb2)->keys_valid) {
+		choke_skb_cb(skb2)->keys_valid = 1;
+		skb_flow_dissect(skb2, &choke_skb_cb(skb2)->keys);
+	}
+
+	return !memcmp(&choke_skb_cb(skb1)->keys,
+		       &choke_skb_cb(skb2)->keys,
+		       sizeof(struct flow_keys));
+}
+
+/*
  * Classify flow using either:
  *  1. pre-existing classification result in skb
  *  2. fast internal classification
@@ -326,6 +274,7 @@ static int choke_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 			goto other_drop;	/* Packet was eaten by filter */
 	}
 
+	choke_skb_cb(skb)->keys_valid = 0;
 	/* Compute average queue usage (see RED) */
 	p->qavg = red_calc_qavg(p, sch->q.qlen);
 	if (red_is_idling(p))
@@ -445,6 +394,7 @@ static void choke_reset(struct Qdisc *sch)
 static const struct nla_policy choke_policy[TCA_CHOKE_MAX + 1] = {
 	[TCA_CHOKE_PARMS]	= { .len = sizeof(struct tc_red_qopt) },
 	[TCA_CHOKE_STAB]	= { .len = RED_STAB_SIZE },
+	[TCA_CHOKE_MAX_P]	= { .type = NLA_U32 },
 };
 
 
@@ -466,6 +416,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 	int err;
 	struct sk_buff **old = NULL;
 	unsigned int mask;
+	u32 max_P;
 
 	if (opt == NULL)
 		return -EINVAL;
@@ -478,6 +429,8 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 	    tb[TCA_CHOKE_STAB] == NULL)
 		return -EINVAL;
 
+	max_P = tb[TCA_CHOKE_MAX_P] ? nla_get_u32(tb[TCA_CHOKE_MAX_P]) : 0;
+
 	ctl = nla_data(tb[TCA_CHOKE_PARMS]);
 
 	if (ctl->limit > CHOKE_MAX_QUEUE)
@@ -527,7 +480,8 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt)
 
 	red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog,
 		      ctl->Plog, ctl->Scell_log,
-		      nla_data(tb[TCA_CHOKE_STAB]));
+		      nla_data(tb[TCA_CHOKE_STAB]),
+		      max_P);
 
 	if (q->head == q->tail)
 		red_end_of_idle_period(&q->parms);
@@ -561,6 +515,7 @@ static int choke_dump(struct Qdisc *sch, struct sk_buff *skb)
 		goto nla_put_failure;
 
 	NLA_PUT(skb, TCA_CHOKE_PARMS, sizeof(opt), &opt);
+	NLA_PUT_U32(skb, TCA_CHOKE_MAX_P, q->parms.max_P);
 	return nla_nest_end(skb, opts);
 
 nla_put_failure:
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 69fca27..67fc573 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -60,7 +60,7 @@ static inline struct sk_buff *dequeue_skb(struct Qdisc *q)
 
 		/* check the reason of requeuing without tx lock first */
 		txq = netdev_get_tx_queue(dev, skb_get_queue_mapping(skb));
-		if (!netif_tx_queue_frozen_or_stopped(txq)) {
+		if (!netif_xmit_frozen_or_stopped(txq)) {
 			q->gso_skb = NULL;
 			q->q.qlen--;
 		} else
@@ -121,7 +121,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 	spin_unlock(root_lock);
 
 	HARD_TX_LOCK(dev, txq, smp_processor_id());
-	if (!netif_tx_queue_frozen_or_stopped(txq))
+	if (!netif_xmit_frozen_or_stopped(txq))
 		ret = dev_hard_start_xmit(skb, dev, txq);
 
 	HARD_TX_UNLOCK(dev, txq);
@@ -143,7 +143,7 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 		ret = dev_requeue_skb(skb, q);
 	}
 
-	if (ret && netif_tx_queue_frozen_or_stopped(txq))
+	if (ret && netif_xmit_frozen_or_stopped(txq))
 		ret = 0;
 
 	return ret;
@@ -242,10 +242,11 @@ static void dev_watchdog(unsigned long arg)
 				 * old device drivers set dev->trans_start
 				 */
 				trans_start = txq->trans_start ? : dev->trans_start;
-				if (netif_tx_queue_stopped(txq) &&
+				if (netif_xmit_stopped(txq) &&
 				    time_after(jiffies, (trans_start +
 							 dev->watchdog_timeo))) {
 					some_queue_timedout = 1;
+					txq->trans_timeout++;
 					break;
 				}
 			}
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index b9493a0..53204de 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -34,7 +34,7 @@ struct gred_sched;
 
 struct gred_sched_data {
 	u32		limit;		/* HARD maximal queue length	*/
-	u32      	DP;		/* the drop pramaters */
+	u32		DP;		/* the drop parameters */
 	u32		bytesin;	/* bytes seen on virtualQ so far*/
 	u32		packetsin;	/* packets seen on virtualQ so far*/
 	u32		backlog;	/* bytes on the virtualQ */
@@ -379,18 +379,20 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps)
 }
 
 static inline int gred_change_vq(struct Qdisc *sch, int dp,
-				 struct tc_gred_qopt *ctl, int prio, u8 *stab)
+				 struct tc_gred_qopt *ctl, int prio,
+				 u8 *stab, u32 max_P,
+				 struct gred_sched_data **prealloc)
 {
 	struct gred_sched *table = qdisc_priv(sch);
-	struct gred_sched_data *q;
+	struct gred_sched_data *q = table->tab[dp];
 
-	if (table->tab[dp] == NULL) {
-		table->tab[dp] = kzalloc(sizeof(*q), GFP_KERNEL);
-		if (table->tab[dp] == NULL)
+	if (!q) {
+		table->tab[dp] = q = *prealloc;
+		*prealloc = NULL;
+		if (!q)
 			return -ENOMEM;
 	}
 
-	q = table->tab[dp];
 	q->DP = dp;
 	q->prio = prio;
 	q->limit = ctl->limit;
@@ -400,7 +402,7 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp,
 
 	red_set_parms(&q->parms,
 		      ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Plog,
-		      ctl->Scell_log, stab);
+		      ctl->Scell_log, stab, max_P);
 
 	return 0;
 }
@@ -409,6 +411,7 @@ static const struct nla_policy gred_policy[TCA_GRED_MAX + 1] = {
 	[TCA_GRED_PARMS]	= { .len = sizeof(struct tc_gred_qopt) },
 	[TCA_GRED_STAB]		= { .len = 256 },
 	[TCA_GRED_DPS]		= { .len = sizeof(struct tc_gred_sopt) },
+	[TCA_GRED_MAX_P]	= { .type = NLA_U32 },
 };
 
 static int gred_change(struct Qdisc *sch, struct nlattr *opt)
@@ -418,6 +421,8 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt)
 	struct nlattr *tb[TCA_GRED_MAX + 1];
 	int err, prio = GRED_DEF_PRIO;
 	u8 *stab;
+	u32 max_P;
+	struct gred_sched_data *prealloc;
 
 	if (opt == NULL)
 		return -EINVAL;
@@ -433,6 +438,8 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt)
 	    tb[TCA_GRED_STAB] == NULL)
 		return -EINVAL;
 
+	max_P = tb[TCA_GRED_MAX_P] ? nla_get_u32(tb[TCA_GRED_MAX_P]) : 0;
+
 	err = -EINVAL;
 	ctl = nla_data(tb[TCA_GRED_PARMS]);
 	stab = nla_data(tb[TCA_GRED_STAB]);
@@ -455,9 +462,10 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt)
 			prio = ctl->prio;
 	}
 
+	prealloc = kzalloc(sizeof(*prealloc), GFP_KERNEL);
 	sch_tree_lock(sch);
 
-	err = gred_change_vq(sch, ctl->DP, ctl, prio, stab);
+	err = gred_change_vq(sch, ctl->DP, ctl, prio, stab, max_P, &prealloc);
 	if (err < 0)
 		goto errout_locked;
 
@@ -471,6 +479,7 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt)
 
 errout_locked:
 	sch_tree_unlock(sch);
+	kfree(prealloc);
 errout:
 	return err;
 }
@@ -498,6 +507,7 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct gred_sched *table = qdisc_priv(sch);
 	struct nlattr *parms, *opts = NULL;
 	int i;
+	u32 max_p[MAX_DPs];
 	struct tc_gred_sopt sopt = {
 		.DPs	= table->DPs,
 		.def_DP	= table->def,
@@ -509,6 +519,14 @@ static int gred_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (opts == NULL)
 		goto nla_put_failure;
 	NLA_PUT(skb, TCA_GRED_DPS, sizeof(sopt), &sopt);
+
+	for (i = 0; i < MAX_DPs; i++) {
+		struct gred_sched_data *q = table->tab[i];
+
+		max_p[i] = q ? q->parms.max_P : 0;
+	}
+	NLA_PUT(skb, TCA_GRED_MAX_P, sizeof(max_p), max_p);
+
 	parms = nla_nest_start(skb, TCA_GRED_PARMS);
 	if (parms == NULL)
 		goto nla_put_failure;
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index edc1950..49131d7 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -107,7 +107,8 @@ static struct sk_buff *multiq_dequeue(struct Qdisc *sch)
 		/* Check that target subqueue is available before
 		 * pulling an skb to avoid head-of-line blocking.
 		 */
-		if (!__netif_subqueue_stopped(qdisc_dev(sch), q->curband)) {
+		if (!netif_xmit_stopped(
+		    netdev_get_tx_queue(qdisc_dev(sch), q->curband))) {
 			qdisc = q->queues[q->curband];
 			skb = qdisc->dequeue(qdisc);
 			if (skb) {
@@ -138,7 +139,8 @@ static struct sk_buff *multiq_peek(struct Qdisc *sch)
 		/* Check that target subqueue is available before
 		 * pulling an skb to avoid head-of-line blocking.
 		 */
-		if (!__netif_subqueue_stopped(qdisc_dev(sch), curband)) {
+		if (!netif_xmit_stopped(
+		    netdev_get_tx_queue(qdisc_dev(sch), curband))) {
 			qdisc = q->queues[curband];
 			skb = qdisc->ops->peek(qdisc);
 			if (skb)
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index eb3b9a8..1fa2f90 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -22,6 +22,7 @@
 #include <linux/skbuff.h>
 #include <linux/vmalloc.h>
 #include <linux/rtnetlink.h>
+#include <linux/reciprocal_div.h>
 
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
@@ -79,6 +80,11 @@ struct netem_sched_data {
 	u32 duplicate;
 	u32 reorder;
 	u32 corrupt;
+	u32 rate;
+	s32 packet_overhead;
+	u32 cell_size;
+	u32 cell_size_reciprocal;
+	s32 cell_overhead;
 
 	struct crndstate {
 		u32 last;
@@ -298,6 +304,26 @@ static psched_tdiff_t tabledist(psched_tdiff_t mu, psched_tdiff_t sigma,
 	return  x / NETEM_DIST_SCALE + (sigma / NETEM_DIST_SCALE) * t + mu;
 }
 
+static psched_time_t packet_len_2_sched_time(unsigned int len, struct netem_sched_data *q)
+{
+	u64 ticks;
+
+	len += q->packet_overhead;
+
+	if (q->cell_size) {
+		u32 cells = reciprocal_divide(len, q->cell_size_reciprocal);
+
+		if (len > cells * q->cell_size)	/* extra cell needed for remainder */
+			cells++;
+		len = cells * (q->cell_size + q->cell_overhead);
+	}
+
+	ticks = (u64)len * NSEC_PER_SEC;
+
+	do_div(ticks, q->rate);
+	return PSCHED_NS2TICKS(ticks);
+}
+
 /*
  * Insert one skb into qdisc.
  * Note: parent depends on return value to account for queue length.
@@ -371,6 +397,24 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 				  &q->delay_cor, q->delay_dist);
 
 		now = psched_get_time();
+
+		if (q->rate) {
+			struct sk_buff_head *list = &q->qdisc->q;
+
+			delay += packet_len_2_sched_time(skb->len, q);
+
+			if (!skb_queue_empty(list)) {
+				/*
+				 * Last packet in queue is reference point (now).
+				 * First packet in queue is already in flight,
+				 * calculate this time bonus and substract
+				 * from delay.
+				 */
+				delay -= now - netem_skb_cb(skb_peek(list))->time_to_send;
+				now = netem_skb_cb(skb_peek_tail(list))->time_to_send;
+			}
+		}
+
 		cb->time_to_send = now + delay;
 		++q->counter;
 		ret = qdisc_enqueue(skb, q->qdisc);
@@ -535,6 +579,19 @@ static void get_corrupt(struct Qdisc *sch, const struct nlattr *attr)
 	init_crandom(&q->corrupt_cor, r->correlation);
 }
 
+static void get_rate(struct Qdisc *sch, const struct nlattr *attr)
+{
+	struct netem_sched_data *q = qdisc_priv(sch);
+	const struct tc_netem_rate *r = nla_data(attr);
+
+	q->rate = r->rate;
+	q->packet_overhead = r->packet_overhead;
+	q->cell_size = r->cell_size;
+	if (q->cell_size)
+		q->cell_size_reciprocal = reciprocal_value(q->cell_size);
+	q->cell_overhead = r->cell_overhead;
+}
+
 static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr)
 {
 	struct netem_sched_data *q = qdisc_priv(sch);
@@ -594,6 +651,7 @@ static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = {
 	[TCA_NETEM_CORR]	= { .len = sizeof(struct tc_netem_corr) },
 	[TCA_NETEM_REORDER]	= { .len = sizeof(struct tc_netem_reorder) },
 	[TCA_NETEM_CORRUPT]	= { .len = sizeof(struct tc_netem_corrupt) },
+	[TCA_NETEM_RATE]	= { .len = sizeof(struct tc_netem_rate) },
 	[TCA_NETEM_LOSS]	= { .type = NLA_NESTED },
 };
 
@@ -666,6 +724,9 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt)
 	if (tb[TCA_NETEM_CORRUPT])
 		get_corrupt(sch, tb[TCA_NETEM_CORRUPT]);
 
+	if (tb[TCA_NETEM_RATE])
+		get_rate(sch, tb[TCA_NETEM_RATE]);
+
 	q->loss_model = CLG_RANDOM;
 	if (tb[TCA_NETEM_LOSS])
 		ret = get_loss_clg(sch, tb[TCA_NETEM_LOSS]);
@@ -846,6 +907,7 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct tc_netem_corr cor;
 	struct tc_netem_reorder reorder;
 	struct tc_netem_corrupt corrupt;
+	struct tc_netem_rate rate;
 
 	qopt.latency = q->latency;
 	qopt.jitter = q->jitter;
@@ -868,6 +930,12 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 	corrupt.correlation = q->corrupt_cor.rho;
 	NLA_PUT(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt);
 
+	rate.rate = q->rate;
+	rate.packet_overhead = q->packet_overhead;
+	rate.cell_size = q->cell_size;
+	rate.cell_overhead = q->cell_overhead;
+	NLA_PUT(skb, TCA_NETEM_RATE, sizeof(rate), &rate);
+
 	if (dump_loss_model(q, skb) != 0)
 		goto nla_put_failure;
 
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index 6649463..ce2256a 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -39,6 +39,7 @@
 struct red_sched_data {
 	u32			limit;		/* HARD maximal queue length */
 	unsigned char		flags;
+	struct timer_list	adapt_timer;
 	struct red_parms	parms;
 	struct red_stats	stats;
 	struct Qdisc		*qdisc;
@@ -161,12 +162,15 @@ static void red_reset(struct Qdisc *sch)
 static void red_destroy(struct Qdisc *sch)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
+
+	del_timer_sync(&q->adapt_timer);
 	qdisc_destroy(q->qdisc);
 }
 
 static const struct nla_policy red_policy[TCA_RED_MAX + 1] = {
 	[TCA_RED_PARMS]	= { .len = sizeof(struct tc_red_qopt) },
 	[TCA_RED_STAB]	= { .len = RED_STAB_SIZE },
+	[TCA_RED_MAX_P] = { .type = NLA_U32 },
 };
 
 static int red_change(struct Qdisc *sch, struct nlattr *opt)
@@ -176,6 +180,7 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
 	struct tc_red_qopt *ctl;
 	struct Qdisc *child = NULL;
 	int err;
+	u32 max_P;
 
 	if (opt == NULL)
 		return -EINVAL;
@@ -188,6 +193,8 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
 	    tb[TCA_RED_STAB] == NULL)
 		return -EINVAL;
 
+	max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0;
+
 	ctl = nla_data(tb[TCA_RED_PARMS]);
 
 	if (ctl->limit > 0) {
@@ -206,21 +213,39 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt)
 	}
 
 	red_set_parms(&q->parms, ctl->qth_min, ctl->qth_max, ctl->Wlog,
-				 ctl->Plog, ctl->Scell_log,
-				 nla_data(tb[TCA_RED_STAB]));
+		      ctl->Plog, ctl->Scell_log,
+		      nla_data(tb[TCA_RED_STAB]),
+		      max_P);
 
-	if (skb_queue_empty(&sch->q))
-		red_end_of_idle_period(&q->parms);
+	del_timer(&q->adapt_timer);
+	if (ctl->flags & TC_RED_ADAPTATIVE)
+		mod_timer(&q->adapt_timer, jiffies + HZ/2);
+
+	if (!q->qdisc->q.qlen)
+		red_start_of_idle_period(&q->parms);
 
 	sch_tree_unlock(sch);
 	return 0;
 }
 
+static inline void red_adaptative_timer(unsigned long arg)
+{
+	struct Qdisc *sch = (struct Qdisc *)arg;
+	struct red_sched_data *q = qdisc_priv(sch);
+	spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch));
+
+	spin_lock(root_lock);
+	red_adaptative_algo(&q->parms);
+	mod_timer(&q->adapt_timer, jiffies + HZ/2);
+	spin_unlock(root_lock);
+}
+
 static int red_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct red_sched_data *q = qdisc_priv(sch);
 
 	q->qdisc = &noop_qdisc;
+	setup_timer(&q->adapt_timer, red_adaptative_timer, (unsigned long)sch);
 	return red_change(sch, opt);
 }
 
@@ -243,6 +268,7 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (opts == NULL)
 		goto nla_put_failure;
 	NLA_PUT(skb, TCA_RED_PARMS, sizeof(opt), &opt);
+	NLA_PUT_U32(skb, TCA_RED_MAX_P, q->parms.max_P);
 	return nla_nest_end(skb, opts);
 
 nla_put_failure:
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index e83c272..96e42ca 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -26,6 +26,7 @@
 #include <net/ip.h>
 #include <net/pkt_sched.h>
 #include <net/inet_ecn.h>
+#include <net/flow_keys.h>
 
 /*
  * SFB uses two B[l][n] : L x N arrays of bins (L levels, N bins per level)
@@ -286,6 +287,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	u32 minqlen = ~0;
 	u32 r, slot, salt, sfbhash;
 	int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
+	struct flow_keys keys;
 
 	if (unlikely(sch->q.qlen >= q->limit)) {
 		sch->qstats.overlimits++;
@@ -309,13 +311,19 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		/* If using external classifiers, get result and record it. */
 		if (!sfb_classify(skb, q, &ret, &salt))
 			goto other_drop;
+		keys.src = salt;
+		keys.dst = 0;
+		keys.ports = 0;
 	} else {
-		salt = skb_get_rxhash(skb);
+		skb_flow_dissect(skb, &keys);
 	}
 
 	slot = q->slot;
 
-	sfbhash = jhash_1word(salt, q->bins[slot].perturbation);
+	sfbhash = jhash_3words((__force u32)keys.dst,
+			       (__force u32)keys.src,
+			       (__force u32)keys.ports,
+			       q->bins[slot].perturbation);
 	if (!sfbhash)
 		sfbhash = 1;
 	sfb_skb_cb(skb)->hashes[slot] = sfbhash;
@@ -347,7 +355,10 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (unlikely(p_min >= SFB_MAX_PROB)) {
 		/* Inelastic flow */
 		if (q->double_buffering) {
-			sfbhash = jhash_1word(salt, q->bins[slot].perturbation);
+			sfbhash = jhash_3words((__force u32)keys.dst,
+					       (__force u32)keys.src,
+					       (__force u32)keys.ports,
+					       q->bins[slot].perturbation);
 			if (!sfbhash)
 				sfbhash = 1;
 			sfb_skb_cb(skb)->hashes[slot] = sfbhash;
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 4f5510e..30cda70 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -17,14 +17,13 @@
 #include <linux/in.h>
 #include <linux/errno.h>
 #include <linux/init.h>
-#include <linux/ipv6.h>
 #include <linux/skbuff.h>
 #include <linux/jhash.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
-#include <net/ip.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
+#include <net/flow_keys.h>
 
 
 /*	Stochastic Fairness Queuing algorithm.
@@ -137,61 +136,17 @@ static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index
 	return &q->dep[val - SFQ_SLOTS];
 }
 
-static unsigned int sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1)
+static unsigned int sfq_hash(const struct sfq_sched_data *q,
+			     const struct sk_buff *skb)
 {
-	return jhash_2words(h, h1, q->perturbation) & (q->divisor - 1);
-}
-
-static unsigned int sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb)
-{
-	u32 h, h2;
-
-	switch (skb->protocol) {
-	case htons(ETH_P_IP):
-	{
-		const struct iphdr *iph;
-		int poff;
-
-		if (!pskb_network_may_pull(skb, sizeof(*iph)))
-			goto err;
-		iph = ip_hdr(skb);
-		h = (__force u32)iph->daddr;
-		h2 = (__force u32)iph->saddr ^ iph->protocol;
-		if (ip_is_fragment(iph))
-			break;
-		poff = proto_ports_offset(iph->protocol);
-		if (poff >= 0 &&
-		    pskb_network_may_pull(skb, iph->ihl * 4 + 4 + poff)) {
-			iph = ip_hdr(skb);
-			h2 ^= *(u32 *)((void *)iph + iph->ihl * 4 + poff);
-		}
-		break;
-	}
-	case htons(ETH_P_IPV6):
-	{
-		const struct ipv6hdr *iph;
-		int poff;
-
-		if (!pskb_network_may_pull(skb, sizeof(*iph)))
-			goto err;
-		iph = ipv6_hdr(skb);
-		h = (__force u32)iph->daddr.s6_addr32[3];
-		h2 = (__force u32)iph->saddr.s6_addr32[3] ^ iph->nexthdr;
-		poff = proto_ports_offset(iph->nexthdr);
-		if (poff >= 0 &&
-		    pskb_network_may_pull(skb, sizeof(*iph) + 4 + poff)) {
-			iph = ipv6_hdr(skb);
-			h2 ^= *(u32 *)((void *)iph + sizeof(*iph) + poff);
-		}
-		break;
-	}
-	default:
-err:
-		h = (unsigned long)skb_dst(skb) ^ (__force u32)skb->protocol;
-		h2 = (unsigned long)skb->sk;
-	}
+	struct flow_keys keys;
+	unsigned int hash;
 
-	return sfq_fold_hash(q, h, h2);
+	skb_flow_dissect(skb, &keys);
+	hash = jhash_3words((__force u32)keys.dst,
+			    (__force u32)keys.src ^ keys.ip_proto,
+			    (__force u32)keys.ports, q->perturbation);
+	return hash & (q->divisor - 1);
 }
 
 static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch,
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index a3b7120..4532659 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -225,11 +225,11 @@ static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt)
 
 
 static int
-__teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device *dev)
+__teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res,
+	       struct net_device *dev, struct netdev_queue *txq,
+	       struct neighbour *mn)
 {
-	struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, 0);
-	struct teql_sched_data *q = qdisc_priv(dev_queue->qdisc);
-	struct neighbour *mn = dst_get_neighbour(skb_dst(skb));
+	struct teql_sched_data *q = qdisc_priv(txq->qdisc);
 	struct neighbour *n = q->ncache;
 
 	if (mn->tbl == NULL)
@@ -262,17 +262,26 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device *
 }
 
 static inline int teql_resolve(struct sk_buff *skb,
-			       struct sk_buff *skb_res, struct net_device *dev)
+			       struct sk_buff *skb_res,
+			       struct net_device *dev,
+			       struct netdev_queue *txq)
 {
-	struct netdev_queue *txq = netdev_get_tx_queue(dev, 0);
+	struct dst_entry *dst = skb_dst(skb);
+	struct neighbour *mn;
+	int res;
+
 	if (txq->qdisc == &noop_qdisc)
 		return -ENODEV;
 
-	if (dev->header_ops == NULL ||
-	    skb_dst(skb) == NULL ||
-	    dst_get_neighbour(skb_dst(skb)) == NULL)
+	if (!dev->header_ops || !dst)
 		return 0;
-	return __teql_resolve(skb, skb_res, dev);
+
+	rcu_read_lock();
+	mn = dst_get_neighbour_noref(dst);
+	res = mn ? __teql_resolve(skb, skb_res, dev, txq, mn) : 0;
+	rcu_read_unlock();
+
+	return res;
 }
 
 static netdev_tx_t teql_master_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -301,18 +310,18 @@ restart:
 
 		if (slave_txq->qdisc_sleeping != q)
 			continue;
-		if (__netif_subqueue_stopped(slave, subq) ||
+		if (netif_xmit_stopped(netdev_get_tx_queue(slave, subq)) ||
 		    !netif_running(slave)) {
 			busy = 1;
 			continue;
 		}
 
-		switch (teql_resolve(skb, skb_res, slave)) {
+		switch (teql_resolve(skb, skb_res, slave, slave_txq)) {
 		case 0:
 			if (__netif_tx_trylock(slave_txq)) {
 				unsigned int length = qdisc_pkt_len(skb);
 
-				if (!netif_tx_queue_frozen_or_stopped(slave_txq) &&
+				if (!netif_xmit_frozen_or_stopped(slave_txq) &&
 				    slave_ops->ndo_start_xmit(skb, slave) == NETDEV_TX_OK) {
 					txq_trans_update(slave_txq);
 					__netif_tx_unlock(slave_txq);
@@ -324,7 +333,7 @@ restart:
 				}
 				__netif_tx_unlock(slave_txq);
 			}
-			if (netif_queue_stopped(dev))
+			if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)))
 				busy = 1;
 			break;
 		case 1:
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 865e68f..bf81204 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -82,7 +82,7 @@ static struct sctp_auth_bytes *sctp_auth_create_key(__u32 key_len, gfp_t gfp)
 	struct sctp_auth_bytes *key;
 
 	/* Verify that we are not going to overflow INT_MAX */
-	if ((INT_MAX - key_len) < sizeof(struct sctp_auth_bytes))
+	if (key_len > (INT_MAX - sizeof(struct sctp_auth_bytes)))
 		return NULL;
 
 	/* Allocate the shared key */
diff --git a/net/sctp/input.c b/net/sctp/input.c
index b7692aa..80f71af 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -105,7 +105,7 @@ static inline int sctp_rcv_checksum(struct sk_buff *skb)
 struct sctp_input_cb {
 	union {
 		struct inet_skb_parm	h4;
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		struct inet6_skb_parm	h6;
 #endif
 	} header;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 8104278..91f4791 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -107,7 +107,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev,
 		if (addr) {
 			addr->a.v6.sin6_family = AF_INET6;
 			addr->a.v6.sin6_port = 0;
-			ipv6_addr_copy(&addr->a.v6.sin6_addr, &ifa->addr);
+			addr->a.v6.sin6_addr = ifa->addr;
 			addr->a.v6.sin6_scope_id = ifa->idev->dev->ifindex;
 			addr->valid = 1;
 			spin_lock_bh(&sctp_local_addr_lock);
@@ -219,8 +219,8 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 	/* Fill in the dest address from the route entry passed with the skb
 	 * and the source address from the transport.
 	 */
-	ipv6_addr_copy(&fl6.daddr, &transport->ipaddr.v6.sin6_addr);
-	ipv6_addr_copy(&fl6.saddr, &transport->saddr.v6.sin6_addr);
+	fl6.daddr = transport->ipaddr.v6.sin6_addr;
+	fl6.saddr = transport->saddr.v6.sin6_addr;
 
 	fl6.flowlabel = np->flow_label;
 	IP6_ECN_flow_xmit(sk, fl6.flowlabel);
@@ -231,7 +231,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 
 	if (np->opt && np->opt->srcrt) {
 		struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt;
-		ipv6_addr_copy(&fl6.daddr, rt0->addr);
+		fl6.daddr = *rt0->addr;
 	}
 
 	SCTP_DEBUG_PRINTK("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n",
@@ -265,7 +265,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	sctp_scope_t scope;
 
 	memset(fl6, 0, sizeof(struct flowi6));
-	ipv6_addr_copy(&fl6->daddr, &daddr->v6.sin6_addr);
+	fl6->daddr = daddr->v6.sin6_addr;
 	fl6->fl6_dport = daddr->v6.sin6_port;
 	fl6->flowi6_proto = IPPROTO_SCTP;
 	if (ipv6_addr_type(&daddr->v6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
@@ -277,7 +277,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		fl6->fl6_sport = htons(asoc->base.bind_addr.port);
 
 	if (saddr) {
-		ipv6_addr_copy(&fl6->saddr, &saddr->v6.sin6_addr);
+		fl6->saddr = saddr->v6.sin6_addr;
 		fl6->fl6_sport = saddr->v6.sin6_port;
 		SCTP_DEBUG_PRINTK("SRC=%pI6 - ", &fl6->saddr);
 	}
@@ -334,7 +334,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	}
 	rcu_read_unlock();
 	if (baddr) {
-		ipv6_addr_copy(&fl6->saddr, &baddr->v6.sin6_addr);
+		fl6->saddr = baddr->v6.sin6_addr;
 		fl6->fl6_sport = baddr->v6.sin6_port;
 		dst = ip6_dst_lookup_flow(sk, fl6, NULL, false);
 	}
@@ -375,7 +375,7 @@ static void sctp_v6_get_saddr(struct sctp_sock *sk,
 
 	if (t->dst) {
 		saddr->v6.sin6_family = AF_INET6;
-		ipv6_addr_copy(&saddr->v6.sin6_addr, &fl6->saddr);
+		saddr->v6.sin6_addr = fl6->saddr;
 	}
 }
 
@@ -400,7 +400,7 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist,
 		if (addr) {
 			addr->a.v6.sin6_family = AF_INET6;
 			addr->a.v6.sin6_port = 0;
-			ipv6_addr_copy(&addr->a.v6.sin6_addr, &ifp->addr);
+			addr->a.v6.sin6_addr = ifp->addr;
 			addr->a.v6.sin6_scope_id = dev->ifindex;
 			addr->valid = 1;
 			INIT_LIST_HEAD(&addr->list);
@@ -416,7 +416,6 @@ static void sctp_v6_copy_addrlist(struct list_head *addrlist,
 static void sctp_v6_from_skb(union sctp_addr *addr,struct sk_buff *skb,
 			     int is_saddr)
 {
-	void *from;
 	__be16 *port;
 	struct sctphdr *sh;
 
@@ -428,12 +427,11 @@ static void sctp_v6_from_skb(union sctp_addr *addr,struct sk_buff *skb,
 	sh = sctp_hdr(skb);
 	if (is_saddr) {
 		*port  = sh->source;
-		from = &ipv6_hdr(skb)->saddr;
+		addr->v6.sin6_addr = ipv6_hdr(skb)->saddr;
 	} else {
 		*port = sh->dest;
-		from = &ipv6_hdr(skb)->daddr;
+		addr->v6.sin6_addr = ipv6_hdr(skb)->daddr;
 	}
-	ipv6_addr_copy(&addr->v6.sin6_addr, from);
 }
 
 /* Initialize an sctp_addr from a socket. */
@@ -441,7 +439,7 @@ static void sctp_v6_from_sk(union sctp_addr *addr, struct sock *sk)
 {
 	addr->v6.sin6_family = AF_INET6;
 	addr->v6.sin6_port = 0;
-	ipv6_addr_copy(&addr->v6.sin6_addr, &inet6_sk(sk)->rcv_saddr);
+	addr->v6.sin6_addr = inet6_sk(sk)->rcv_saddr;
 }
 
 /* Initialize sk->sk_rcv_saddr from sctp_addr. */
@@ -454,7 +452,7 @@ static void sctp_v6_to_sk_saddr(union sctp_addr *addr, struct sock *sk)
 		inet6_sk(sk)->rcv_saddr.s6_addr32[3] =
 			addr->v4.sin_addr.s_addr;
 	} else {
-		ipv6_addr_copy(&inet6_sk(sk)->rcv_saddr, &addr->v6.sin6_addr);
+		inet6_sk(sk)->rcv_saddr = addr->v6.sin6_addr;
 	}
 }
 
@@ -467,7 +465,7 @@ static void sctp_v6_to_sk_daddr(union sctp_addr *addr, struct sock *sk)
 		inet6_sk(sk)->daddr.s6_addr32[2] = htonl(0x0000ffff);
 		inet6_sk(sk)->daddr.s6_addr32[3] = addr->v4.sin_addr.s_addr;
 	} else {
-		ipv6_addr_copy(&inet6_sk(sk)->daddr, &addr->v6.sin6_addr);
+		inet6_sk(sk)->daddr = addr->v6.sin6_addr;
 	}
 }
 
@@ -479,7 +477,7 @@ static void sctp_v6_from_addr_param(union sctp_addr *addr,
 	addr->v6.sin6_family = AF_INET6;
 	addr->v6.sin6_port = port;
 	addr->v6.sin6_flowinfo = 0; /* BUG */
-	ipv6_addr_copy(&addr->v6.sin6_addr, &param->v6.addr);
+	addr->v6.sin6_addr = param->v6.addr;
 	addr->v6.sin6_scope_id = iif;
 }
 
@@ -493,7 +491,7 @@ static int sctp_v6_to_addr_param(const union sctp_addr *addr,
 
 	param->v6.param_hdr.type = SCTP_PARAM_IPV6_ADDRESS;
 	param->v6.param_hdr.length = htons(length);
-	ipv6_addr_copy(&param->v6.addr, &addr->v6.sin6_addr);
+	param->v6.addr = addr->v6.sin6_addr;
 
 	return length;
 }
@@ -504,7 +502,7 @@ static void sctp_v6_to_addr(union sctp_addr *addr, struct in6_addr *saddr,
 {
 	addr->sa.sa_family = AF_INET6;
 	addr->v6.sin6_port = port;
-	ipv6_addr_copy(&addr->v6.sin6_addr, saddr);
+	addr->v6.sin6_addr = *saddr;
 }
 
 /* Compare addresses exactly.
@@ -759,7 +757,7 @@ static void sctp_inet6_event_msgname(struct sctp_ulpevent *event,
 		}
 
 		sin6from = &asoc->peer.primary_addr.v6;
-		ipv6_addr_copy(&sin6->sin6_addr, &sin6from->sin6_addr);
+		sin6->sin6_addr = sin6from->sin6_addr;
 		if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
 			sin6->sin6_scope_id = sin6from->sin6_scope_id;
 	}
@@ -787,7 +785,7 @@ static void sctp_inet6_skb_msgname(struct sk_buff *skb, char *msgname,
 		}
 
 		/* Otherwise, just copy the v6 address. */
-		ipv6_addr_copy(&sin6->sin6_addr, &ipv6_hdr(skb)->saddr);
+		sin6->sin6_addr = ipv6_hdr(skb)->saddr;
 		if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) {
 			struct sctp_ulpevent *ev = sctp_skb2event(skb);
 			sin6->sin6_scope_id = ev->iif;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 61b9fca..544a9b6 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -637,7 +637,7 @@ void sctp_addr_wq_timeout_handler(unsigned long arg)
 		    " for cmd %d at entry %p\n", &sctp_addr_waitq, &addrw->a, addrw->state,
 		    addrw);
 
-#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		/* Now we send an ASCONF for each association */
 		/* Note. we currently don't handle link local IPv6 addressees */
 		if (addrw->a.sa.sa_family == AF_INET6) {
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index 0121e0a..a85eeeb 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -3400,8 +3400,10 @@ int sctp_process_asconf_ack(struct sctp_association *asoc,
 		asconf_len -= length;
 	}
 
-	if (no_err && asoc->src_out_of_asoc_ok)
+	if (no_err && asoc->src_out_of_asoc_ok) {
 		asoc->src_out_of_asoc_ok = 0;
+		sctp_transport_immediate_rtx(asoc->peer.primary_path);
+	}
 
 	/* Free the cached last sent asconf chunk. */
 	list_del_init(&asconf->transmitted_list);
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 76388b0..1ff51c9 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -666,6 +666,7 @@ static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds,
 				  struct sctp_chunk *chunk)
 {
 	sctp_sender_hb_info_t *hbinfo;
+	int was_unconfirmed = 0;
 
 	/* 8.3 Upon the receipt of the HEARTBEAT ACK, the sender of the
 	 * HEARTBEAT should clear the error counter of the destination
@@ -692,9 +693,11 @@ static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds,
 	/* Mark the destination transport address as active if it is not so
 	 * marked.
 	 */
-	if ((t->state == SCTP_INACTIVE) || (t->state == SCTP_UNCONFIRMED))
+	if ((t->state == SCTP_INACTIVE) || (t->state == SCTP_UNCONFIRMED)) {
+		was_unconfirmed = 1;
 		sctp_assoc_control_transport(asoc, t, SCTP_TRANSPORT_UP,
 					     SCTP_HEARTBEAT_SUCCESS);
+	}
 
 	/* The receiver of the HEARTBEAT ACK should also perform an
 	 * RTT measurement for that destination transport address
@@ -712,6 +715,9 @@ static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds,
 	/* Update the heartbeat timer.  */
 	if (!mod_timer(&t->hb_timer, sctp_transport_timeout(t)))
 		sctp_transport_hold(t);
+
+	if (was_unconfirmed && asoc->peer.transport_count == 1)
+		sctp_transport_immediate_rtx(t);
 }
 
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 13bf5fc..db03083 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -804,7 +804,7 @@ static int sctp_send_asconf_del_ip(struct sock		*sk,
 				struct sockaddr_in6 *sin6;
 
 				sin6 = (struct sockaddr_in6 *)addrs;
-				ipv6_addr_copy(&asoc->asconf_addr_del_pending->v6.sin6_addr, &sin6->sin6_addr);
+				asoc->asconf_addr_del_pending->v6.sin6_addr = sin6->sin6_addr;
 			}
 			SCTP_DEBUG_PRINTK_IPADDR("send_asconf_del_ip: keep the last address asoc: %p ",
 			    " at %p\n", asoc, asoc->asconf_addr_del_pending,
@@ -6841,7 +6841,7 @@ struct proto sctp_prot = {
 	.sockets_allocated = &sctp_sockets_allocated,
 };
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 
 struct proto sctpv6_prot = {
 	.name		= "SCTPv6",
@@ -6872,4 +6872,4 @@ struct proto sctpv6_prot = {
 	.memory_allocated = &sctp_memory_allocated,
 	.sockets_allocated = &sctp_sockets_allocated,
 };
-#endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#endif /* IS_ENABLED(CONFIG_IPV6) */
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 394c57c..3889330 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -641,3 +641,19 @@ void sctp_transport_reset(struct sctp_transport *t)
 	t->cacc.next_tsn_at_change = 0;
 	t->cacc.cacc_saw_newack = 0;
 }
+
+/* Schedule retransmission on the given transport */
+void sctp_transport_immediate_rtx(struct sctp_transport *t)
+{
+	/* Stop pending T3_rtx_timer */
+	if (timer_pending(&t->T3_rtx_timer)) {
+		(void)del_timer(&t->T3_rtx_timer);
+		sctp_transport_put(t);
+	}
+	sctp_retransmit(&t->asoc->outqueue, t, SCTP_RTXR_T3_RTX);
+	if (!timer_pending(&t->T3_rtx_timer)) {
+		if (!mod_timer(&t->T3_rtx_timer, jiffies + t->rto))
+			sctp_transport_hold(t);
+	}
+	return;
+}
diff --git a/net/socket.c b/net/socket.c
index 425ef42..e62b4f0 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -551,6 +551,8 @@ static inline int __sock_sendmsg_nosec(struct kiocb *iocb, struct socket *sock,
 
 	sock_update_classid(sock->sk);
 
+	sock_update_netprioidx(sock->sk);
+
 	si->sock = sock;
 	si->scm = NULL;
 	si->msg = msg;
diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c
index 67a655e..ee77742 100644
--- a/net/sunrpc/addr.c
+++ b/net/sunrpc/addr.c
@@ -21,7 +21,7 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 
 static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap,
 				  char *buf, const int buflen)
@@ -91,7 +91,7 @@ static size_t rpc_ntop6(const struct sockaddr *sap,
 	return len;
 }
 
-#else	/* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */
+#else	/* !IS_ENABLED(CONFIG_IPV6) */
 
 static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap,
 				  char *buf, const int buflen)
@@ -105,7 +105,7 @@ static size_t rpc_ntop6(const struct sockaddr *sap,
 	return 0;
 }
 
-#endif	/* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */
+#endif	/* !IS_ENABLED(CONFIG_IPV6) */
 
 static int rpc_ntop4(const struct sockaddr *sap,
 		     char *buf, const size_t buflen)
@@ -155,7 +155,7 @@ static size_t rpc_pton4(const char *buf, const size_t buflen,
 	return sizeof(struct sockaddr_in);
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 static int rpc_parse_scope_id(const char *buf, const size_t buflen,
 			      const char *delim, struct sockaddr_in6 *sin6)
 {
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 6e03888..9d01d46 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -826,7 +826,7 @@ static int __svc_rpcb_register4(const u32 program, const u32 version,
 	return error;
 }
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 /*
  * Register an "inet6" protocol family netid with the local
  * rpcbind daemon via an rpcbind v4 SET request.
@@ -872,7 +872,7 @@ static int __svc_rpcb_register6(const u32 program, const u32 version,
 
 	return error;
 }
-#endif	/* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#endif	/* IS_ENABLED(CONFIG_IPV6) */
 
 /*
  * Register a kernel RPC service via rpcbind version 4.
@@ -893,11 +893,11 @@ static int __svc_register(const char *progname,
 		error = __svc_rpcb_register4(program, version,
 						protocol, port);
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case PF_INET6:
 		error = __svc_rpcb_register6(program, version,
 						protocol, port);
-#endif	/* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#endif
 	}
 
 	if (error < 0)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 447cd0e..38649cf 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -179,13 +179,13 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
 		.sin_addr.s_addr	= htonl(INADDR_ANY),
 		.sin_port		= htons(port),
 	};
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	struct sockaddr_in6 sin6 = {
 		.sin6_family		= AF_INET6,
 		.sin6_addr		= IN6ADDR_ANY_INIT,
 		.sin6_port		= htons(port),
 	};
-#endif	/* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#endif
 	struct sockaddr *sap;
 	size_t len;
 
@@ -194,12 +194,12 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
 		sap = (struct sockaddr *)&sin;
 		len = sizeof(sin);
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case PF_INET6:
 		sap = (struct sockaddr *)&sin6;
 		len = sizeof(sin6);
 		break;
-#endif	/* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
+#endif
 	default:
 		return ERR_PTR(-EAFNOSUPPORT);
 	}
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index ce13632..01153ea 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -134,7 +134,7 @@ static void ip_map_init(struct cache_head *cnew, struct cache_head *citem)
 	struct ip_map *item = container_of(citem, struct ip_map, h);
 
 	strcpy(new->m_class, item->m_class);
-	ipv6_addr_copy(&new->m_addr, &item->m_addr);
+	new->m_addr = item->m_addr;
 }
 static void update(struct cache_head *cnew, struct cache_head *citem)
 {
@@ -220,7 +220,7 @@ static int ip_map_parse(struct cache_detail *cd,
 		ipv6_addr_set_v4mapped(address.s4.sin_addr.s_addr,
 				&sin6.sin6_addr);
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		memcpy(&sin6, &address.s6, sizeof(sin6));
 		break;
@@ -274,7 +274,7 @@ static int ip_map_show(struct seq_file *m,
 	}
 	im = container_of(h, struct ip_map, h);
 	/* class addr domain */
-	ipv6_addr_copy(&addr, &im->m_addr);
+	addr = im->m_addr;
 
 	if (test_bit(CACHE_VALID, &h->flags) &&
 	    !test_bit(CACHE_NEGATIVE, &h->flags))
@@ -297,7 +297,7 @@ static struct ip_map *__ip_map_lookup(struct cache_detail *cd, char *class,
 	struct cache_head *ch;
 
 	strcpy(ip.m_class, class);
-	ipv6_addr_copy(&ip.m_addr, addr);
+	ip.m_addr = *addr;
 	ch = sunrpc_cache_lookup(cd, &ip.h,
 				 hash_str(class, IP_HASHBITS) ^
 				 hash_ip6(*addr));
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 71bed1c..4653286 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -157,7 +157,7 @@ static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh)
 			cmh->cmsg_level = SOL_IPV6;
 			cmh->cmsg_type = IPV6_PKTINFO;
 			pki->ipi6_ifindex = daddr->sin6_scope_id;
-			ipv6_addr_copy(&pki->ipi6_addr,	&daddr->sin6_addr);
+			pki->ipi6_addr = daddr->sin6_addr;
 			cmh->cmsg_len = CMSG_LEN(sizeof(*pki));
 		}
 		break;
@@ -523,7 +523,7 @@ static int svc_udp_get_dest_address6(struct svc_rqst *rqstp,
 		return 0;
 
 	daddr->sin6_family = AF_INET6;
-	ipv6_addr_copy(&daddr->sin6_addr, &pki->ipi6_addr);
+	daddr->sin6_addr = pki->ipi6_addr;
 	daddr->sin6_scope_id = pki->ipi6_ifindex;
 	return 1;
 }
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index d7f97ef..55472c4 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -496,7 +496,7 @@ static int xs_nospace(struct rpc_task *task)
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_xprt *xprt = req->rq_xprt;
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
-	int ret = 0;
+	int ret = -EAGAIN;
 
 	dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
 			task->tk_pid, req->rq_slen - req->rq_bytes_sent,
@@ -508,7 +508,6 @@ static int xs_nospace(struct rpc_task *task)
 	/* Don't race with disconnect */
 	if (xprt_connected(xprt)) {
 		if (test_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags)) {
-			ret = -EAGAIN;
 			/*
 			 * Notify TCP that we're limited by the application
 			 * window size
@@ -2530,8 +2529,10 @@ static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args,
 		int err;
 		err = xs_init_anyaddr(args->dstaddr->sa_family,
 					(struct sockaddr *)&new->srcaddr);
-		if (err != 0)
+		if (err != 0) {
+			xprt_free(xprt);
 			return ERR_PTR(err);
+		}
 	}
 
 	return xprt;
diff --git a/net/unix/Kconfig b/net/unix/Kconfig
index 5a69733..c2128b1 100644
--- a/net/unix/Kconfig
+++ b/net/unix/Kconfig
@@ -19,3 +19,10 @@ config UNIX
 
 	  Say Y unless you know what you are doing.
 
+config UNIX_DIAG
+	tristate "UNIX: socket monitoring interface"
+	depends on UNIX
+	default UNIX
+	---help---
+	  Support for UNIX socket monitoring interface used by the ss tool.
+	  If unsure, say Y.
diff --git a/net/unix/Makefile b/net/unix/Makefile
index b852a2b..b663c60 100644
--- a/net/unix/Makefile
+++ b/net/unix/Makefile
@@ -6,3 +6,6 @@ obj-$(CONFIG_UNIX)	+= unix.o
 
 unix-y			:= af_unix.o garbage.o
 unix-$(CONFIG_SYSCTL)	+= sysctl_net_unix.o
+
+obj-$(CONFIG_UNIX_DIAG)	+= unix_diag.o
+unix_diag-y		:= diag.o
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 466fbcc..e1b9358 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -115,8 +115,10 @@
 #include <net/checksum.h>
 #include <linux/security.h>
 
-static struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
-static DEFINE_SPINLOCK(unix_table_lock);
+struct hlist_head unix_socket_table[UNIX_HASH_SIZE + 1];
+EXPORT_SYMBOL_GPL(unix_socket_table);
+DEFINE_SPINLOCK(unix_table_lock);
+EXPORT_SYMBOL_GPL(unix_table_lock);
 static atomic_long_t unix_nr_socks;
 
 #define unix_sockets_unbound	(&unix_socket_table[UNIX_HASH_SIZE])
@@ -172,7 +174,7 @@ static inline int unix_recvq_full(struct sock const *sk)
 	return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog;
 }
 
-static struct sock *unix_peer_get(struct sock *s)
+struct sock *unix_peer_get(struct sock *s)
 {
 	struct sock *peer;
 
@@ -183,6 +185,7 @@ static struct sock *unix_peer_get(struct sock *s)
 	unix_state_unlock(s);
 	return peer;
 }
+EXPORT_SYMBOL_GPL(unix_peer_get);
 
 static inline void unix_release_addr(struct unix_address *addr)
 {
@@ -1957,6 +1960,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 			if ((UNIXCB(skb).pid  != siocb->scm->pid) ||
 			    (UNIXCB(skb).cred != siocb->scm->cred)) {
 				skb_queue_head(&sk->sk_receive_queue, skb);
+				sk->sk_data_ready(sk, skb->len);
 				break;
 			}
 		} else {
@@ -1974,6 +1978,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		chunk = min_t(unsigned int, skb->len, size);
 		if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) {
 			skb_queue_head(&sk->sk_receive_queue, skb);
+			sk->sk_data_ready(sk, skb->len);
 			if (copied == 0)
 				copied = -EFAULT;
 			break;
@@ -1991,6 +1996,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 			/* put the skb back if we didn't use it up.. */
 			if (skb->len) {
 				skb_queue_head(&sk->sk_receive_queue, skb);
+				sk->sk_data_ready(sk, skb->len);
 				break;
 			}
 
@@ -2006,6 +2012,7 @@ static int unix_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 
 			/* put message back and return */
 			skb_queue_head(&sk->sk_receive_queue, skb);
+			sk->sk_data_ready(sk, skb->len);
 			break;
 		}
 	} while (size);
diff --git a/net/unix/diag.c b/net/unix/diag.c
new file mode 100644
index 0000000..a5c4aab
--- /dev/null
+++ b/net/unix/diag.c
@@ -0,0 +1,313 @@
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/sock_diag.h>
+#include <linux/unix_diag.h>
+#include <linux/skbuff.h>
+#include <net/netlink.h>
+#include <net/af_unix.h>
+#include <net/tcp_states.h>
+
+#define UNIX_DIAG_PUT(skb, attrtype, attrlen) \
+	RTA_DATA(__RTA_PUT(skb, attrtype, attrlen))
+
+static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb)
+{
+	struct unix_address *addr = unix_sk(sk)->addr;
+	char *s;
+
+	if (addr) {
+		s = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_NAME, addr->len - sizeof(short));
+		memcpy(s, addr->name->sun_path, addr->len - sizeof(short));
+	}
+
+	return 0;
+
+rtattr_failure:
+	return -EMSGSIZE;
+}
+
+static int sk_diag_dump_vfs(struct sock *sk, struct sk_buff *nlskb)
+{
+	struct dentry *dentry = unix_sk(sk)->dentry;
+	struct unix_diag_vfs *uv;
+
+	if (dentry) {
+		uv = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_VFS, sizeof(*uv));
+		uv->udiag_vfs_ino = dentry->d_inode->i_ino;
+		uv->udiag_vfs_dev = dentry->d_sb->s_dev;
+	}
+
+	return 0;
+
+rtattr_failure:
+	return -EMSGSIZE;
+}
+
+static int sk_diag_dump_peer(struct sock *sk, struct sk_buff *nlskb)
+{
+	struct sock *peer;
+	int ino;
+
+	peer = unix_peer_get(sk);
+	if (peer) {
+		unix_state_lock(peer);
+		ino = sock_i_ino(peer);
+		unix_state_unlock(peer);
+		sock_put(peer);
+
+		RTA_PUT_U32(nlskb, UNIX_DIAG_PEER, ino);
+	}
+
+	return 0;
+rtattr_failure:
+	return -EMSGSIZE;
+}
+
+static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
+{
+	struct sk_buff *skb;
+	u32 *buf;
+	int i;
+
+	if (sk->sk_state == TCP_LISTEN) {
+		spin_lock(&sk->sk_receive_queue.lock);
+		buf = UNIX_DIAG_PUT(nlskb, UNIX_DIAG_ICONS, sk->sk_receive_queue.qlen);
+		i = 0;
+		skb_queue_walk(&sk->sk_receive_queue, skb) {
+			struct sock *req, *peer;
+
+			req = skb->sk;
+			/*
+			 * The state lock is outer for the same sk's
+			 * queue lock. With the other's queue locked it's
+			 * OK to lock the state.
+			 */
+			unix_state_lock_nested(req);
+			peer = unix_sk(req)->peer;
+			if (peer)
+				buf[i++] = sock_i_ino(peer);
+			unix_state_unlock(req);
+		}
+		spin_unlock(&sk->sk_receive_queue.lock);
+	}
+
+	return 0;
+
+rtattr_failure:
+	spin_unlock(&sk->sk_receive_queue.lock);
+	return -EMSGSIZE;
+}
+
+static int sk_diag_show_rqlen(struct sock *sk, struct sk_buff *nlskb)
+{
+	RTA_PUT_U32(nlskb, UNIX_DIAG_RQLEN, sk->sk_receive_queue.qlen);
+	return 0;
+
+rtattr_failure:
+	return -EMSGSIZE;
+}
+
+static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
+		u32 pid, u32 seq, u32 flags, int sk_ino)
+{
+	unsigned char *b = skb_tail_pointer(skb);
+	struct nlmsghdr *nlh;
+	struct unix_diag_msg *rep;
+
+	nlh = NLMSG_PUT(skb, pid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*rep));
+	nlh->nlmsg_flags = flags;
+
+	rep = NLMSG_DATA(nlh);
+
+	rep->udiag_family = AF_UNIX;
+	rep->udiag_type = sk->sk_type;
+	rep->udiag_state = sk->sk_state;
+	rep->udiag_ino = sk_ino;
+	sock_diag_save_cookie(sk, rep->udiag_cookie);
+
+	if ((req->udiag_show & UDIAG_SHOW_NAME) &&
+			sk_diag_dump_name(sk, skb))
+		goto nlmsg_failure;
+
+	if ((req->udiag_show & UDIAG_SHOW_VFS) &&
+			sk_diag_dump_vfs(sk, skb))
+		goto nlmsg_failure;
+
+	if ((req->udiag_show & UDIAG_SHOW_PEER) &&
+			sk_diag_dump_peer(sk, skb))
+		goto nlmsg_failure;
+
+	if ((req->udiag_show & UDIAG_SHOW_ICONS) &&
+			sk_diag_dump_icons(sk, skb))
+		goto nlmsg_failure;
+
+	if ((req->udiag_show & UDIAG_SHOW_RQLEN) &&
+			sk_diag_show_rqlen(sk, skb))
+		goto nlmsg_failure;
+
+	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
+	return skb->len;
+
+nlmsg_failure:
+	nlmsg_trim(skb, b);
+	return -EMSGSIZE;
+}
+
+static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, struct unix_diag_req *req,
+		u32 pid, u32 seq, u32 flags)
+{
+	int sk_ino;
+
+	unix_state_lock(sk);
+	sk_ino = sock_i_ino(sk);
+	unix_state_unlock(sk);
+
+	if (!sk_ino)
+		return 0;
+
+	return sk_diag_fill(sk, skb, req, pid, seq, flags, sk_ino);
+}
+
+static int unix_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct unix_diag_req *req;
+	int num, s_num, slot, s_slot;
+
+	req = NLMSG_DATA(cb->nlh);
+
+	s_slot = cb->args[0];
+	num = s_num = cb->args[1];
+
+	spin_lock(&unix_table_lock);
+	for (slot = s_slot; slot <= UNIX_HASH_SIZE; s_num = 0, slot++) {
+		struct sock *sk;
+		struct hlist_node *node;
+
+		num = 0;
+		sk_for_each(sk, node, &unix_socket_table[slot]) {
+			if (num < s_num)
+				goto next;
+			if (!(req->udiag_states & (1 << sk->sk_state)))
+				goto next;
+			if (sk_diag_dump(sk, skb, req,
+						NETLINK_CB(cb->skb).pid,
+						cb->nlh->nlmsg_seq,
+						NLM_F_MULTI) < 0)
+				goto done;
+next:
+			num++;
+		}
+	}
+done:
+	spin_unlock(&unix_table_lock);
+	cb->args[0] = slot;
+	cb->args[1] = num;
+
+	return skb->len;
+}
+
+static struct sock *unix_lookup_by_ino(int ino)
+{
+	int i;
+	struct sock *sk;
+
+	spin_lock(&unix_table_lock);
+	for (i = 0; i <= UNIX_HASH_SIZE; i++) {
+		struct hlist_node *node;
+
+		sk_for_each(sk, node, &unix_socket_table[i])
+			if (ino == sock_i_ino(sk)) {
+				sock_hold(sk);
+				spin_unlock(&unix_table_lock);
+
+				return sk;
+			}
+	}
+
+	spin_unlock(&unix_table_lock);
+	return NULL;
+}
+
+static int unix_diag_get_exact(struct sk_buff *in_skb,
+			       const struct nlmsghdr *nlh,
+			       struct unix_diag_req *req)
+{
+	int err = -EINVAL;
+	struct sock *sk;
+	struct sk_buff *rep;
+	unsigned int extra_len;
+
+	if (req->udiag_ino == 0)
+		goto out_nosk;
+
+	sk = unix_lookup_by_ino(req->udiag_ino);
+	err = -ENOENT;
+	if (sk == NULL)
+		goto out_nosk;
+
+	err = sock_diag_check_cookie(sk, req->udiag_cookie);
+	if (err)
+		goto out;
+
+	extra_len = 256;
+again:
+	err = -ENOMEM;
+	rep = alloc_skb(NLMSG_SPACE((sizeof(struct unix_diag_msg) + extra_len)),
+			GFP_KERNEL);
+	if (!rep)
+		goto out;
+
+	err = sk_diag_fill(sk, rep, req, NETLINK_CB(in_skb).pid,
+			   nlh->nlmsg_seq, 0, req->udiag_ino);
+	if (err < 0) {
+		kfree_skb(rep);
+		extra_len += 256;
+		if (extra_len >= PAGE_SIZE)
+			goto out;
+
+		goto again;
+	}
+	err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid,
+			      MSG_DONTWAIT);
+	if (err > 0)
+		err = 0;
+out:
+	if (sk)
+		sock_put(sk);
+out_nosk:
+	return err;
+}
+
+static int unix_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
+{
+	int hdrlen = sizeof(struct unix_diag_req);
+
+	if (nlmsg_len(h) < hdrlen)
+		return -EINVAL;
+
+	if (h->nlmsg_flags & NLM_F_DUMP)
+		return netlink_dump_start(sock_diag_nlsk, skb, h,
+					  unix_diag_dump, NULL, 0);
+	else
+		return unix_diag_get_exact(skb, h, (struct unix_diag_req *)NLMSG_DATA(h));
+}
+
+static struct sock_diag_handler unix_diag_handler = {
+	.family = AF_UNIX,
+	.dump = unix_diag_handler_dump,
+};
+
+static int __init unix_diag_init(void)
+{
+	return sock_diag_register(&unix_diag_handler);
+}
+
+static void __exit unix_diag_exit(void)
+{
+	sock_diag_unregister(&unix_diag_handler);
+}
+
+module_init(unix_diag_init);
+module_exit(unix_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 1 /* AF_LOCAL */);
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 3e16c6a..a306bc6 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -232,7 +232,7 @@ static int x25_device_event(struct notifier_block *this, unsigned long event,
 		return NOTIFY_DONE;
 
 	if (dev->type == ARPHRD_X25
-#if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE)
+#if IS_ENABLED(CONFIG_LLC)
 	 || dev->type == ARPHRD_ETHER
 #endif
 	 ) {
diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c
index fa2b418..f0ce862 100644
--- a/net/x25/x25_dev.c
+++ b/net/x25/x25_dev.c
@@ -161,7 +161,7 @@ void x25_establish_link(struct x25_neigh *nb)
 		*ptr = X25_IFACE_CONNECT;
 		break;
 
-#if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE)
+#if IS_ENABLED(CONFIG_LLC)
 	case ARPHRD_ETHER:
 		return;
 #endif
@@ -180,7 +180,7 @@ void x25_terminate_link(struct x25_neigh *nb)
 	struct sk_buff *skb;
 	unsigned char *ptr;
 
-#if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE)
+#if IS_ENABLED(CONFIG_LLC)
 	if (nb->dev->type == ARPHRD_ETHER)
 		return;
 #endif
@@ -213,7 +213,7 @@ void x25_send_frame(struct sk_buff *skb, struct x25_neigh *nb)
 		*dptr = X25_IFACE_DATA;
 		break;
 
-#if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE)
+#if IS_ENABLED(CONFIG_LLC)
 	case ARPHRD_ETHER:
 		kfree_skb(skb);
 		return;
diff --git a/net/x25/x25_route.c b/net/x25/x25_route.c
index 97d77c5..cf63662 100644
--- a/net/x25/x25_route.c
+++ b/net/x25/x25_route.c
@@ -134,7 +134,7 @@ struct net_device *x25_dev_get(char *devname)
 
 	if (dev &&
 	    (!(dev->flags & IFF_UP) || (dev->type != ARPHRD_X25
-#if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE)
+#if IS_ENABLED(CONFIG_LLC)
 					&& dev->type != ARPHRD_ETHER
 #endif
 					))){
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 552df27..eb6b0b7 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -61,8 +61,8 @@ __xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl)
 {
 	const struct flowi4 *fl4 = &fl->u.ip4;
 
-	return  addr_match(&fl4->daddr, &sel->daddr, sel->prefixlen_d) &&
-		addr_match(&fl4->saddr, &sel->saddr, sel->prefixlen_s) &&
+	return  addr4_match(fl4->daddr, sel->daddr.a4, sel->prefixlen_d) &&
+		addr4_match(fl4->saddr, sel->saddr.a4, sel->prefixlen_s) &&
 		!((xfrm_flowi_dport(fl, &fl4->uli) ^ sel->dport) & sel->dport_mask) &&
 		!((xfrm_flowi_sport(fl, &fl4->uli) ^ sel->sport) & sel->sport_mask) &&
 		(fl4->flowi4_proto == sel->proto || !sel->proto) &&
@@ -1340,7 +1340,7 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
 	case AF_INET:
 		dst_ops = &net->xfrm.xfrm4_dst_ops;
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		dst_ops = &net->xfrm.xfrm6_dst_ops;
 		break;
@@ -1499,7 +1499,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 		goto free_dst;
 
 	/* Copy neighbour for reachability confirmation */
-	dst_set_neighbour(dst0, neigh_clone(dst_get_neighbour(dst)));
+	dst_set_neighbour(dst0, neigh_clone(dst_get_neighbour_noref(dst)));
 
 	xfrm_init_path((struct xfrm_dst *)dst0, dst, nfheader_len);
 	xfrm_init_pmtu(dst_prev);
@@ -2382,9 +2382,11 @@ static unsigned int xfrm_default_advmss(const struct dst_entry *dst)
 	return dst_metric_advmss(dst->path);
 }
 
-static unsigned int xfrm_default_mtu(const struct dst_entry *dst)
+static unsigned int xfrm_mtu(const struct dst_entry *dst)
 {
-	return dst_mtu(dst->path);
+	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+	return mtu ? : dst_mtu(dst->path);
 }
 
 static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, const void *daddr)
@@ -2411,8 +2413,8 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
 			dst_ops->check = xfrm_dst_check;
 		if (likely(dst_ops->default_advmss == NULL))
 			dst_ops->default_advmss = xfrm_default_advmss;
-		if (likely(dst_ops->default_mtu == NULL))
-			dst_ops->default_mtu = xfrm_default_mtu;
+		if (likely(dst_ops->mtu == NULL))
+			dst_ops->mtu = xfrm_mtu;
 		if (likely(dst_ops->negative_advice == NULL))
 			dst_ops->negative_advice = xfrm_negative_advice;
 		if (likely(dst_ops->link_failure == NULL))
@@ -2433,7 +2435,7 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo)
 		case AF_INET:
 			xfrm_dst_ops = &net->xfrm.xfrm4_dst_ops;
 			break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		case AF_INET6:
 			xfrm_dst_ops = &net->xfrm.xfrm6_dst_ops;
 			break;
@@ -2483,7 +2485,7 @@ static void __net_init xfrm_dst_ops_init(struct net *net)
 	afinfo = xfrm_policy_afinfo[AF_INET];
 	if (afinfo)
 		net->xfrm.xfrm4_dst_ops = *afinfo->dst_ops;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	afinfo = xfrm_policy_afinfo[AF_INET6];
 	if (afinfo)
 		net->xfrm.xfrm6_dst_ops = *afinfo->dst_ops;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 9414b9c..5b228f9 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1035,16 +1035,12 @@ static struct xfrm_state *__find_acq_core(struct net *net, struct xfrm_mark *m,
 			break;
 
 		case AF_INET6:
-			ipv6_addr_copy((struct in6_addr *)x->sel.daddr.a6,
-				       (const struct in6_addr *)daddr);
-			ipv6_addr_copy((struct in6_addr *)x->sel.saddr.a6,
-				       (const struct in6_addr *)saddr);
+			*(struct in6_addr *)x->sel.daddr.a6 = *(struct in6_addr *)daddr;
+			*(struct in6_addr *)x->sel.saddr.a6 = *(struct in6_addr *)saddr;
 			x->sel.prefixlen_d = 128;
 			x->sel.prefixlen_s = 128;
-			ipv6_addr_copy((struct in6_addr *)x->props.saddr.a6,
-				       (const struct in6_addr *)saddr);
-			ipv6_addr_copy((struct in6_addr *)x->id.daddr.a6,
-				       (const struct in6_addr *)daddr);
+			*(struct in6_addr *)x->props.saddr.a6 = *(struct in6_addr *)saddr;
+			*(struct in6_addr *)x->id.daddr.a6 = *(struct in6_addr *)daddr;
 			break;
 		}
 
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index d0a42df..e0d747a 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -28,7 +28,7 @@
 #include <net/netlink.h>
 #include <net/ah.h>
 #include <asm/uaccess.h>
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 #include <linux/in6.h>
 #endif
 
@@ -150,7 +150,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
 		break;
 
 	case AF_INET6:
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		break;
 #else
 		err = -EAFNOSUPPORT;
@@ -201,7 +201,7 @@ static int verify_newsa_info(struct xfrm_usersa_info *p,
 			goto out;
 		break;
 
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case IPPROTO_DSTOPTS:
 	case IPPROTO_ROUTING:
 		if (attrs[XFRMA_ALG_COMP]	||
@@ -1160,7 +1160,7 @@ static int verify_newpolicy_info(struct xfrm_userpolicy_info *p)
 		break;
 
 	case AF_INET6:
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		break;
 #else
 		return  -EAFNOSUPPORT;
@@ -1231,7 +1231,7 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family)
 		switch (ut[i].family) {
 		case AF_INET:
 			break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 		case AF_INET6:
 			break;
 #endif
@@ -2604,7 +2604,7 @@ static struct xfrm_policy *xfrm_compile_policy(struct sock *sk, int opt,
 			return NULL;
 		}
 		break;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		if (opt != IPV6_XFRM_POLICY) {
 			*dir = -EOPNOTSUPP;
diff --git a/security/keys/encrypted-keys/Makefile b/security/keys/encrypted-keys/Makefile
index 6bc7a86..d6f8433 100644
--- a/security/keys/encrypted-keys/Makefile
+++ b/security/keys/encrypted-keys/Makefile
@@ -2,5 +2,9 @@
 # Makefile for encrypted keys
 #
 
-obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted.o ecryptfs_format.o
-obj-$(CONFIG_TRUSTED_KEYS) += masterkey_trusted.o
+obj-$(CONFIG_ENCRYPTED_KEYS) += encrypted-keys.o
+
+encrypted-keys-y := encrypted.o ecryptfs_format.o
+masterkey-$(CONFIG_TRUSTED_KEYS) := masterkey_trusted.o
+masterkey-$(CONFIG_TRUSTED_KEYS)-$(CONFIG_ENCRYPTED_KEYS) := masterkey_trusted.o
+encrypted-keys-y += $(masterkey-y) $(masterkey-m-m)
diff --git a/security/keys/encrypted-keys/encrypted.c b/security/keys/encrypted-keys/encrypted.c
index dcc843c..41144f7 100644
--- a/security/keys/encrypted-keys/encrypted.c
+++ b/security/keys/encrypted-keys/encrypted.c
@@ -444,7 +444,7 @@ static struct key *request_master_key(struct encrypted_key_payload *epayload,
 		goto out;
 
 	if (IS_ERR(mkey)) {
-		int ret = PTR_ERR(epayload);
+		int ret = PTR_ERR(mkey);
 
 		if (ret == -ENOTSUPP)
 			pr_info("encrypted_key: key %s not supported",
diff --git a/security/keys/encrypted-keys/encrypted.h b/security/keys/encrypted-keys/encrypted.h
index b6ade89..8136a2d 100644
--- a/security/keys/encrypted-keys/encrypted.h
+++ b/security/keys/encrypted-keys/encrypted.h
@@ -2,7 +2,8 @@
 #define __ENCRYPTED_KEY_H
 
 #define ENCRYPTED_DEBUG 0
-#ifdef CONFIG_TRUSTED_KEYS
+#if defined(CONFIG_TRUSTED_KEYS) || \
+  (defined(CONFIG_TRUSTED_KEYS_MODULE) && defined(CONFIG_ENCRYPTED_KEYS_MODULE))
 extern struct key *request_trusted_key(const char *trusted_desc,
 				       u8 **master_key, size_t *master_keylen);
 #else
diff --git a/security/keys/user_defined.c b/security/keys/user_defined.c
index 5b366d7..69ff52c 100644
--- a/security/keys/user_defined.c
+++ b/security/keys/user_defined.c
@@ -102,7 +102,8 @@ int user_update(struct key *key, const void *data, size_t datalen)
 		key->expiry = 0;
 	}
 
-	kfree_rcu(zap, rcu);
+	if (zap)
+		kfree_rcu(zap, rcu);
 
 error:
 	return ret;
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 893af8a..7bd6f13 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -114,19 +114,20 @@ int ipv6_skb_to_auditdata(struct sk_buff *skb,
 	int offset, ret = 0;
 	struct ipv6hdr *ip6;
 	u8 nexthdr;
+	__be16 frag_off;
 
 	ip6 = ipv6_hdr(skb);
 	if (ip6 == NULL)
 		return -EINVAL;
-	ipv6_addr_copy(&ad->u.net.v6info.saddr, &ip6->saddr);
-	ipv6_addr_copy(&ad->u.net.v6info.daddr, &ip6->daddr);
+	ad->u.net.v6info.saddr = ip6->saddr;
+	ad->u.net.v6info.daddr = ip6->daddr;
 	ret = 0;
 	/* IPv6 can have several extension header before the Transport header
 	 * skip them */
 	offset = skb_network_offset(skb);
 	offset += sizeof(*ip6);
 	nexthdr = ip6->nexthdr;
-	offset = ipv6_skip_exthdr(skb, offset, &nexthdr);
+	offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
 	if (offset < 0)
 		return 0;
 	if (proto)
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 1126c10..86305c2 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -1090,7 +1090,7 @@ static inline u16 socket_type_to_security_class(int family, int type, int protoc
 			return SECCLASS_NETLINK_ROUTE_SOCKET;
 		case NETLINK_FIREWALL:
 			return SECCLASS_NETLINK_FIREWALL_SOCKET;
-		case NETLINK_INET_DIAG:
+		case NETLINK_SOCK_DIAG:
 			return SECCLASS_NETLINK_TCPDIAG_SOCKET;
 		case NETLINK_NFLOG:
 			return SECCLASS_NETLINK_NFLOG_SOCKET;
@@ -3561,19 +3561,20 @@ static int selinux_parse_skb_ipv6(struct sk_buff *skb,
 	u8 nexthdr;
 	int ret = -EINVAL, offset;
 	struct ipv6hdr _ipv6h, *ip6;
+	__be16 frag_off;
 
 	offset = skb_network_offset(skb);
 	ip6 = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h);
 	if (ip6 == NULL)
 		goto out;
 
-	ipv6_addr_copy(&ad->u.net.v6info.saddr, &ip6->saddr);
-	ipv6_addr_copy(&ad->u.net.v6info.daddr, &ip6->daddr);
+	ad->u.net.v6info.saddr = ip6->saddr;
+	ad->u.net.v6info.daddr = ip6->daddr;
 	ret = 0;
 
 	nexthdr = ip6->nexthdr;
 	offset += sizeof(_ipv6h);
-	offset = ipv6_skip_exthdr(skb, offset, &nexthdr);
+	offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off);
 	if (offset < 0)
 		goto out;
 
@@ -3871,7 +3872,7 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in
 		if (family == PF_INET)
 			ad.u.net.v4info.saddr = addr4->sin_addr.s_addr;
 		else
-			ipv6_addr_copy(&ad.u.net.v6info.saddr, &addr6->sin6_addr);
+			ad.u.net.v6info.saddr = addr6->sin6_addr;
 
 		err = avc_has_perm(sksec->sid, sid,
 				   sksec->sclass, node_perm, &ad);
diff --git a/security/selinux/netnode.c b/security/selinux/netnode.c
index 3bf46ab..8636585 100644
--- a/security/selinux/netnode.c
+++ b/security/selinux/netnode.c
@@ -220,7 +220,7 @@ static int sel_netnode_sid_slow(void *addr, u16 family, u32 *sid)
 	case PF_INET6:
 		ret = security_node_sid(PF_INET6,
 					addr, sizeof(struct in6_addr), sid);
-		ipv6_addr_copy(&new->nsec.addr.ipv6, addr);
+		new->nsec.addr.ipv6 = *(struct in6_addr *)addr;
 		break;
 	default:
 		BUG();
diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
index 6aceef5..5c32f36 100644
--- a/security/smack/smackfs.c
+++ b/security/smack/smackfs.c
@@ -102,9 +102,6 @@ static int smk_cipso_doi_value = SMACK_CIPSO_DOI_DEFAULT;
 
 const char *smack_cipso_option = SMACK_CIPSO_OPTION;
 
-
-#define	SEQ_READ_FINISHED	((loff_t)-1)
-
 /*
  * Values for parsing cipso rules
  * SMK_DIGITLEN: Length of a digit field in a rule.
@@ -357,10 +354,12 @@ static ssize_t smk_write_load_list(struct file *file, const char __user *buf,
 
 	rc = count;
 	/*
+	 * If this is "load" as opposed to "load-self" and a new rule
+	 * it needs to get added for reporting.
 	 * smk_set_access returns true if there was already a rule
 	 * for the subject/object pair, and false if it was new.
 	 */
-	if (!smk_set_access(rule, rule_list, rule_lock)) {
+	if (load && !smk_set_access(rule, rule_list, rule_lock)) {
 		smlp = kzalloc(sizeof(*smlp), GFP_KERNEL);
 		if (smlp != NULL) {
 			smlp->smk_rule = rule;
@@ -377,12 +376,12 @@ out:
 	return rc;
 }
 
-
 /*
- * Seq_file read operations for /smack/load
+ * Core logic for smackfs seq list operations.
  */
 
-static void *load_seq_start(struct seq_file *s, loff_t *pos)
+static void *smk_seq_start(struct seq_file *s, loff_t *pos,
+				struct list_head *head)
 {
 	struct list_head *list;
 
@@ -390,7 +389,7 @@ static void *load_seq_start(struct seq_file *s, loff_t *pos)
 	 * This is 0 the first time through.
 	 */
 	if (s->index == 0)
-		s->private = &smack_rule_list;
+		s->private = head;
 
 	if (s->private == NULL)
 		return NULL;
@@ -404,11 +403,12 @@ static void *load_seq_start(struct seq_file *s, loff_t *pos)
 	return list;
 }
 
-static void *load_seq_next(struct seq_file *s, void *v, loff_t *pos)
+static void *smk_seq_next(struct seq_file *s, void *v, loff_t *pos,
+				struct list_head *head)
 {
 	struct list_head *list = v;
 
-	if (list_is_last(list, &smack_rule_list)) {
+	if (list_is_last(list, head)) {
 		s->private = NULL;
 		return NULL;
 	}
@@ -416,6 +416,25 @@ static void *load_seq_next(struct seq_file *s, void *v, loff_t *pos)
 	return list->next;
 }
 
+static void smk_seq_stop(struct seq_file *s, void *v)
+{
+	/* No-op */
+}
+
+/*
+ * Seq_file read operations for /smack/load
+ */
+
+static void *load_seq_start(struct seq_file *s, loff_t *pos)
+{
+	return smk_seq_start(s, pos, &smack_rule_list);
+}
+
+static void *load_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	return smk_seq_next(s, v, pos, &smack_rule_list);
+}
+
 static int load_seq_show(struct seq_file *s, void *v)
 {
 	struct list_head *list = v;
@@ -446,16 +465,11 @@ static int load_seq_show(struct seq_file *s, void *v)
 	return 0;
 }
 
-static void load_seq_stop(struct seq_file *s, void *v)
-{
-	/* No-op */
-}
-
 static const struct seq_operations load_seq_ops = {
 	.start = load_seq_start,
 	.next  = load_seq_next,
 	.show  = load_seq_show,
-	.stop  = load_seq_stop,
+	.stop  = smk_seq_stop,
 };
 
 /**
@@ -574,28 +588,12 @@ static void smk_unlbl_ambient(char *oldambient)
 
 static void *cipso_seq_start(struct seq_file *s, loff_t *pos)
 {
-	if (*pos == SEQ_READ_FINISHED)
-		return NULL;
-	if (list_empty(&smack_known_list))
-		return NULL;
-
-	return smack_known_list.next;
+	return smk_seq_start(s, pos, &smack_known_list);
 }
 
 static void *cipso_seq_next(struct seq_file *s, void *v, loff_t *pos)
 {
-	struct list_head  *list = v;
-
-	/*
-	 * labels with no associated cipso value wont be printed
-	 * in cipso_seq_show
-	 */
-	if (list_is_last(list, &smack_known_list)) {
-		*pos = SEQ_READ_FINISHED;
-		return NULL;
-	}
-
-	return list->next;
+	return smk_seq_next(s, v, pos, &smack_known_list);
 }
 
 /*
@@ -634,16 +632,11 @@ static int cipso_seq_show(struct seq_file *s, void *v)
 	return 0;
 }
 
-static void cipso_seq_stop(struct seq_file *s, void *v)
-{
-	/* No-op */
-}
-
 static const struct seq_operations cipso_seq_ops = {
 	.start = cipso_seq_start,
-	.stop  = cipso_seq_stop,
 	.next  = cipso_seq_next,
 	.show  = cipso_seq_show,
+	.stop  = smk_seq_stop,
 };
 
 /**
@@ -788,23 +781,12 @@ static const struct file_operations smk_cipso_ops = {
 
 static void *netlbladdr_seq_start(struct seq_file *s, loff_t *pos)
 {
-	if (*pos == SEQ_READ_FINISHED)
-		return NULL;
-	if (list_empty(&smk_netlbladdr_list))
-		return NULL;
-	return smk_netlbladdr_list.next;
+	return smk_seq_start(s, pos, &smk_netlbladdr_list);
 }
 
 static void *netlbladdr_seq_next(struct seq_file *s, void *v, loff_t *pos)
 {
-	struct list_head *list = v;
-
-	if (list_is_last(list, &smk_netlbladdr_list)) {
-		*pos = SEQ_READ_FINISHED;
-		return NULL;
-	}
-
-	return list->next;
+	return smk_seq_next(s, v, pos, &smk_netlbladdr_list);
 }
 #define BEBITS	(sizeof(__be32) * 8)
 
@@ -828,16 +810,11 @@ static int netlbladdr_seq_show(struct seq_file *s, void *v)
 	return 0;
 }
 
-static void netlbladdr_seq_stop(struct seq_file *s, void *v)
-{
-	/* No-op */
-}
-
 static const struct seq_operations netlbladdr_seq_ops = {
 	.start = netlbladdr_seq_start,
-	.stop  = netlbladdr_seq_stop,
 	.next  = netlbladdr_seq_next,
 	.show  = netlbladdr_seq_show,
+	.stop  = smk_seq_stop,
 };
 
 /**
@@ -1405,23 +1382,14 @@ static void *load_self_seq_start(struct seq_file *s, loff_t *pos)
 {
 	struct task_smack *tsp = current_security();
 
-	if (*pos == SEQ_READ_FINISHED)
-		return NULL;
-	if (list_empty(&tsp->smk_rules))
-		return NULL;
-	return tsp->smk_rules.next;
+	return smk_seq_start(s, pos, &tsp->smk_rules);
 }
 
 static void *load_self_seq_next(struct seq_file *s, void *v, loff_t *pos)
 {
 	struct task_smack *tsp = current_security();
-	struct list_head *list = v;
 
-	if (list_is_last(list, &tsp->smk_rules)) {
-		*pos = SEQ_READ_FINISHED;
-		return NULL;
-	}
-	return list->next;
+	return smk_seq_next(s, v, pos, &tsp->smk_rules);
 }
 
 static int load_self_seq_show(struct seq_file *s, void *v)
@@ -1453,16 +1421,11 @@ static int load_self_seq_show(struct seq_file *s, void *v)
 	return 0;
 }
 
-static void load_self_seq_stop(struct seq_file *s, void *v)
-{
-	/* No-op */
-}
-
 static const struct seq_operations load_self_seq_ops = {
 	.start = load_self_seq_start,
 	.next  = load_self_seq_next,
 	.show  = load_self_seq_show,
-	.stop  = load_self_seq_stop,
+	.stop  = smk_seq_stop,
 };
 
 
diff --git a/sound/pci/cs5535audio/cs5535audio_pcm.c b/sound/pci/cs5535audio/cs5535audio_pcm.c
index e083122..dbf94b1 100644
--- a/sound/pci/cs5535audio/cs5535audio_pcm.c
+++ b/sound/pci/cs5535audio/cs5535audio_pcm.c
@@ -148,7 +148,7 @@ static int cs5535audio_build_dma_packets(struct cs5535audio *cs5535au,
 		struct cs5535audio_dma_desc *desc =
 			&((struct cs5535audio_dma_desc *) dma->desc_buf.area)[i];
 		desc->addr = cpu_to_le32(addr);
-		desc->size = cpu_to_le32(period_bytes);
+		desc->size = cpu_to_le16(period_bytes);
 		desc->ctlreserved = cpu_to_le16(PRD_EOP);
 		desc_addr += sizeof(struct cs5535audio_dma_desc);
 		addr += period_bytes;
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index e44b107..4562e9d 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -4046,9 +4046,9 @@ int snd_hda_check_board_codec_sid_config(struct hda_codec *codec,
 
 	/* Search for codec ID */
 	for (q = tbl; q->subvendor; q++) {
-		unsigned long vendorid = (q->subdevice) | (q->subvendor << 16);
-
-		if (vendorid == codec->subsystem_id)
+		unsigned int mask = 0xffff0000 | q->subdevice_mask;
+		unsigned int id = (q->subdevice | (q->subvendor << 16)) & mask;
+		if ((codec->subsystem_id & mask) == id)
 			break;
 	}
 
diff --git a/sound/pci/hda/hda_eld.c b/sound/pci/hda/hda_eld.c
index 1c8ddf5..c1da422 100644
--- a/sound/pci/hda/hda_eld.c
+++ b/sound/pci/hda/hda_eld.c
@@ -297,10 +297,18 @@ static int hdmi_update_eld(struct hdmi_eld *e,
 					buf + ELD_FIXED_BYTES + mnl + 3 * i);
 	}
 
+	/*
+	 * HDMI sink's ELD info cannot always be retrieved for now, e.g.
+	 * in console or for audio devices. Assume the highest speakers
+	 * configuration, to _not_ prohibit multi-channel audio playback.
+	 */
+	if (!e->spk_alloc)
+		e->spk_alloc = 0xffff;
+
+	e->eld_valid = true;
 	return 0;
 
 out_fail:
-	e->eld_ver = 0;
 	return -EINVAL;
 }
 
@@ -323,9 +331,6 @@ int snd_hdmi_get_eld(struct hdmi_eld *eld,
 	 * ELD is valid, actual eld_size is assigned in hdmi_update_eld()
 	 */
 
-	if (!eld->eld_valid)
-		return -ENOENT;
-
 	size = snd_hdmi_get_eld_size(codec, nid);
 	if (size == 0) {
 		/* wfg: workaround for ASUS P5E-VM HDMI board */
@@ -342,18 +347,28 @@ int snd_hdmi_get_eld(struct hdmi_eld *eld,
 
 	for (i = 0; i < size; i++) {
 		unsigned int val = hdmi_get_eld_data(codec, nid, i);
+		/*
+		 * Graphics driver might be writing to ELD buffer right now.
+		 * Just abort. The caller will repoll after a while.
+		 */
 		if (!(val & AC_ELDD_ELD_VALID)) {
-			if (!i) {
-				snd_printd(KERN_INFO
-					   "HDMI: invalid ELD data\n");
-				ret = -EINVAL;
-				goto error;
-			}
 			snd_printd(KERN_INFO
 				  "HDMI: invalid ELD data byte %d\n", i);
-			val = 0;
-		} else
-			val &= AC_ELDD_ELD_DATA;
+			ret = -EINVAL;
+			goto error;
+		}
+		val &= AC_ELDD_ELD_DATA;
+		/*
+		 * The first byte cannot be zero. This can happen on some DVI
+		 * connections. Some Intel chips may also need some 250ms delay
+		 * to return non-zero ELD data, even when the graphics driver
+		 * correctly writes ELD content before setting ELD_valid bit.
+		 */
+		if (!val && !i) {
+			snd_printdd(KERN_INFO "HDMI: 0 ELD data\n");
+			ret = -EINVAL;
+			goto error;
+		}
 		buf[i] = val;
 	}
 
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 096507d..7d98240 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2508,7 +2508,6 @@ static struct snd_pci_quirk position_fix_list[] __devinitdata = {
 	SND_PCI_QUIRK(0x1043, 0x81b3, "ASUS", POS_FIX_LPIB),
 	SND_PCI_QUIRK(0x1043, 0x81e7, "ASUS M2V", POS_FIX_LPIB),
 	SND_PCI_QUIRK(0x104d, 0x9069, "Sony VPCS11V9E", POS_FIX_LPIB),
-	SND_PCI_QUIRK(0x1106, 0x3288, "ASUS M2V-MX SE", POS_FIX_LPIB),
 	SND_PCI_QUIRK(0x1297, 0x3166, "Shuttle", POS_FIX_LPIB),
 	SND_PCI_QUIRK(0x1458, 0xa022, "ga-ma770-ud3", POS_FIX_LPIB),
 	SND_PCI_QUIRK(0x1462, 0x1002, "MSI Wind U115", POS_FIX_LPIB),
diff --git a/sound/pci/hda/hda_local.h b/sound/pci/hda/hda_local.h
index 6579e0f..618ddad 100644
--- a/sound/pci/hda/hda_local.h
+++ b/sound/pci/hda/hda_local.h
@@ -653,6 +653,9 @@ struct hdmi_eld {
 	int	spk_alloc;
 	int	sad_count;
 	struct cea_sad sad[ELD_MAX_SAD];
+	/*
+	 * all fields above eld_buffer will be cleared before updating ELD
+	 */
 	char    eld_buffer[ELD_MAX_SIZE];
 #ifdef CONFIG_PROC_FS
 	struct snd_info_entry *proc_entry;
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index 2a2d864..70a7abd 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -58,6 +58,8 @@ struct cs_spec {
 	unsigned int gpio_mask;
 	unsigned int gpio_dir;
 	unsigned int gpio_data;
+	unsigned int gpio_eapd_hp; /* EAPD GPIO bit for headphones */
+	unsigned int gpio_eapd_speaker; /* EAPD GPIO bit for speakers */
 
 	struct hda_pcm pcm_rec[2];	/* PCM information */
 
@@ -76,6 +78,7 @@ enum {
 	CS420X_MBP53,
 	CS420X_MBP55,
 	CS420X_IMAC27,
+	CS420X_APPLE,
 	CS420X_AUTO,
 	CS420X_MODELS
 };
@@ -237,6 +240,15 @@ static int cs_dig_playback_pcm_cleanup(struct hda_pcm_stream *hinfo,
 	return snd_hda_multi_out_dig_cleanup(codec, &spec->multiout);
 }
 
+static void cs_update_input_select(struct hda_codec *codec)
+{
+	struct cs_spec *spec = codec->spec;
+	if (spec->cur_adc)
+		snd_hda_codec_write(codec, spec->cur_adc, 0,
+				    AC_VERB_SET_CONNECT_SEL,
+				    spec->adc_idx[spec->cur_input]);
+}
+
 /*
  * Analog capture
  */
@@ -250,6 +262,7 @@ static int cs_capture_pcm_prepare(struct hda_pcm_stream *hinfo,
 	spec->cur_adc = spec->adc_nid[spec->cur_input];
 	spec->cur_adc_stream_tag = stream_tag;
 	spec->cur_adc_format = format;
+	cs_update_input_select(codec);
 	snd_hda_codec_setup_stream(codec, spec->cur_adc, stream_tag, 0, format);
 	return 0;
 }
@@ -689,10 +702,8 @@ static int change_cur_input(struct hda_codec *codec, unsigned int idx,
 					   spec->cur_adc_stream_tag, 0,
 					   spec->cur_adc_format);
 	}
-	snd_hda_codec_write(codec, spec->cur_adc, 0,
-			    AC_VERB_SET_CONNECT_SEL,
-			    spec->adc_idx[idx]);
 	spec->cur_input = idx;
+	cs_update_input_select(codec);
 	return 1;
 }
 
@@ -920,10 +931,9 @@ static void cs_automute(struct hda_codec *codec)
 					spdif_present ? 0 : PIN_OUT);
 		}
 	}
-	if (spec->board_config == CS420X_MBP53 ||
-	    spec->board_config == CS420X_MBP55 ||
-	    spec->board_config == CS420X_IMAC27) {
-		unsigned int gpio = hp_present ? 0x02 : 0x08;
+	if (spec->gpio_eapd_hp) {
+		unsigned int gpio = hp_present ?
+			spec->gpio_eapd_hp : spec->gpio_eapd_speaker;
 		snd_hda_codec_write(codec, 0x01, 0,
 				    AC_VERB_SET_GPIO_DATA, gpio);
 	}
@@ -973,10 +983,7 @@ static void cs_automic(struct hda_codec *codec)
 		} else  {
 			spec->cur_input = spec->last_input;
 		}
-
-		snd_hda_codec_write_cache(codec, spec->cur_adc, 0,
-					AC_VERB_SET_CONNECT_SEL,
-					spec->adc_idx[spec->cur_input]);
+		cs_update_input_select(codec);
 	} else {
 		if (present)
 			change_cur_input(codec, spec->automic_idx, 0);
@@ -1073,9 +1080,7 @@ static void init_input(struct hda_codec *codec)
 			cs_automic(codec);
 		else  {
 			spec->cur_adc = spec->adc_nid[spec->cur_input];
-			snd_hda_codec_write(codec, spec->cur_adc, 0,
-					AC_VERB_SET_CONNECT_SEL,
-					spec->adc_idx[spec->cur_input]);
+			cs_update_input_select(codec);
 		}
 	} else {
 		change_cur_input(codec, spec->cur_input, 1);
@@ -1273,6 +1278,7 @@ static const char * const cs420x_models[CS420X_MODELS] = {
 	[CS420X_MBP53] = "mbp53",
 	[CS420X_MBP55] = "mbp55",
 	[CS420X_IMAC27] = "imac27",
+	[CS420X_APPLE] = "apple",
 	[CS420X_AUTO] = "auto",
 };
 
@@ -1282,7 +1288,13 @@ static const struct snd_pci_quirk cs420x_cfg_tbl[] = {
 	SND_PCI_QUIRK(0x10de, 0x0d94, "MacBookAir 3,1(2)", CS420X_MBP55),
 	SND_PCI_QUIRK(0x10de, 0xcb79, "MacBookPro 5,5", CS420X_MBP55),
 	SND_PCI_QUIRK(0x10de, 0xcb89, "MacBookPro 7,1", CS420X_MBP55),
-	SND_PCI_QUIRK(0x8086, 0x7270, "IMac 27 Inch", CS420X_IMAC27),
+	/* this conflicts with too many other models */
+	/*SND_PCI_QUIRK(0x8086, 0x7270, "IMac 27 Inch", CS420X_IMAC27),*/
+	{} /* terminator */
+};
+
+static const struct snd_pci_quirk cs420x_codec_cfg_tbl[] = {
+	SND_PCI_QUIRK_VENDOR(0x106b, "Apple", CS420X_APPLE),
 	{} /* terminator */
 };
 
@@ -1364,6 +1376,10 @@ static int patch_cs420x(struct hda_codec *codec)
 	spec->board_config =
 		snd_hda_check_board_config(codec, CS420X_MODELS,
 					   cs420x_models, cs420x_cfg_tbl);
+	if (spec->board_config < 0)
+		spec->board_config =
+			snd_hda_check_board_codec_sid_config(codec,
+				CS420X_MODELS, NULL, cs420x_codec_cfg_tbl);
 	if (spec->board_config >= 0)
 		fix_pincfg(codec, spec->board_config, cs_pincfgs);
 
@@ -1371,10 +1387,11 @@ static int patch_cs420x(struct hda_codec *codec)
 	case CS420X_IMAC27:
 	case CS420X_MBP53:
 	case CS420X_MBP55:
-		/* GPIO1 = headphones */
-		/* GPIO3 = speakers */
-		spec->gpio_mask = 0x0a;
-		spec->gpio_dir = 0x0a;
+	case CS420X_APPLE:
+		spec->gpio_eapd_hp = 2; /* GPIO1 = headphones */
+		spec->gpio_eapd_speaker = 8; /* GPIO3 = speakers */
+		spec->gpio_mask = spec->gpio_dir =
+			spec->gpio_eapd_hp | spec->gpio_eapd_speaker;
 		break;
 	}
 
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 81b7b79..c505fd5 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -65,7 +65,11 @@ struct hdmi_spec_per_pin {
 	hda_nid_t pin_nid;
 	int num_mux_nids;
 	hda_nid_t mux_nids[HDA_MAX_CONNECTIONS];
+
+	struct hda_codec *codec;
 	struct hdmi_eld sink_eld;
+	struct delayed_work work;
+	int repoll_count;
 };
 
 struct hdmi_spec {
@@ -745,8 +749,7 @@ static void hdmi_setup_audio_infoframe(struct hda_codec *codec, int pin_idx,
  * Unsolicited events
  */
 
-static void hdmi_present_sense(struct hda_codec *codec, hda_nid_t pin_nid,
-			       struct hdmi_eld *eld);
+static void hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll);
 
 static void hdmi_intrinsic_event(struct hda_codec *codec, unsigned int res)
 {
@@ -755,7 +758,6 @@ static void hdmi_intrinsic_event(struct hda_codec *codec, unsigned int res)
 	int pd = !!(res & AC_UNSOL_RES_PD);
 	int eldv = !!(res & AC_UNSOL_RES_ELDV);
 	int pin_idx;
-	struct hdmi_eld *eld;
 
 	printk(KERN_INFO
 		"HDMI hot plug event: Codec=%d Pin=%d Presence_Detect=%d ELD_Valid=%d\n",
@@ -764,17 +766,8 @@ static void hdmi_intrinsic_event(struct hda_codec *codec, unsigned int res)
 	pin_idx = pin_nid_to_pin_index(spec, pin_nid);
 	if (pin_idx < 0)
 		return;
-	eld = &spec->pins[pin_idx].sink_eld;
-
-	hdmi_present_sense(codec, pin_nid, eld);
 
-	/*
-	 * HDMI sink's ELD info cannot always be retrieved for now, e.g.
-	 * in console or for audio devices. Assume the highest speakers
-	 * configuration, to _not_ prohibit multi-channel audio playback.
-	 */
-	if (!eld->spk_alloc)
-		eld->spk_alloc = 0xffff;
+	hdmi_present_sense(&spec->pins[pin_idx], 1);
 }
 
 static void hdmi_non_intrinsic_event(struct hda_codec *codec, unsigned int res)
@@ -968,9 +961,11 @@ static int hdmi_read_pin_conn(struct hda_codec *codec, int pin_idx)
 	return 0;
 }
 
-static void hdmi_present_sense(struct hda_codec *codec, hda_nid_t pin_nid,
-			       struct hdmi_eld *eld)
+static void hdmi_present_sense(struct hdmi_spec_per_pin *per_pin, int repoll)
 {
+	struct hda_codec *codec = per_pin->codec;
+	struct hdmi_eld *eld = &per_pin->sink_eld;
+	hda_nid_t pin_nid = per_pin->pin_nid;
 	/*
 	 * Always execute a GetPinSense verb here, even when called from
 	 * hdmi_intrinsic_event; for some NVIDIA HW, the unsolicited
@@ -980,26 +975,42 @@ static void hdmi_present_sense(struct hda_codec *codec, hda_nid_t pin_nid,
 	 * the unsolicited response to avoid custom WARs.
 	 */
 	int present = snd_hda_pin_sense(codec, pin_nid);
+	bool eld_valid = false;
 
-	memset(eld, 0, sizeof(*eld));
+	memset(eld, 0, offsetof(struct hdmi_eld, eld_buffer));
 
 	eld->monitor_present	= !!(present & AC_PINSENSE_PRESENCE);
 	if (eld->monitor_present)
-		eld->eld_valid	= !!(present & AC_PINSENSE_ELDV);
-	else
-		eld->eld_valid	= 0;
+		eld_valid	= !!(present & AC_PINSENSE_ELDV);
 
 	printk(KERN_INFO
 		"HDMI status: Codec=%d Pin=%d Presence_Detect=%d ELD_Valid=%d\n",
-		codec->addr, pin_nid, eld->monitor_present, eld->eld_valid);
+		codec->addr, pin_nid, eld->monitor_present, eld_valid);
 
-	if (eld->eld_valid)
+	if (eld_valid) {
 		if (!snd_hdmi_get_eld(eld, codec, pin_nid))
 			snd_hdmi_show_eld(eld);
+		else if (repoll) {
+			queue_delayed_work(codec->bus->workq,
+					   &per_pin->work,
+					   msecs_to_jiffies(300));
+		}
+	}
 
 	snd_hda_input_jack_report(codec, pin_nid);
 }
 
+static void hdmi_repoll_eld(struct work_struct *work)
+{
+	struct hdmi_spec_per_pin *per_pin =
+	container_of(to_delayed_work(work), struct hdmi_spec_per_pin, work);
+
+	if (per_pin->repoll_count++ > 6)
+		per_pin->repoll_count = 0;
+
+	hdmi_present_sense(per_pin, per_pin->repoll_count);
+}
+
 static int hdmi_add_pin(struct hda_codec *codec, hda_nid_t pin_nid)
 {
 	struct hdmi_spec *spec = codec->spec;
@@ -1228,7 +1239,7 @@ static int generic_hdmi_build_jack(struct hda_codec *codec, int pin_idx)
 	if (err < 0)
 		return err;
 
-	hdmi_present_sense(codec, per_pin->pin_nid, &per_pin->sink_eld);
+	hdmi_present_sense(per_pin, 0);
 	return 0;
 }
 
@@ -1279,6 +1290,8 @@ static int generic_hdmi_init(struct hda_codec *codec)
 				    AC_VERB_SET_UNSOLICITED_ENABLE,
 				    AC_USRSP_EN | pin_nid);
 
+		per_pin->codec = codec;
+		INIT_DELAYED_WORK(&per_pin->work, hdmi_repoll_eld);
 		snd_hda_eld_proc_new(codec, eld, pin_idx);
 	}
 	return 0;
@@ -1293,10 +1306,12 @@ static void generic_hdmi_free(struct hda_codec *codec)
 		struct hdmi_spec_per_pin *per_pin = &spec->pins[pin_idx];
 		struct hdmi_eld *eld = &per_pin->sink_eld;
 
+		cancel_delayed_work(&per_pin->work);
 		snd_hda_eld_proc_free(codec, eld);
 	}
 	snd_hda_input_jack_free(codec);
 
+	flush_workqueue(codec->bus->workq);
 	kfree(spec);
 }
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 308bb57..cbde019 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -277,6 +277,12 @@ static bool alc_dyn_adc_pcm_resetup(struct hda_codec *codec, int cur)
 	return false;
 }
 
+static inline hda_nid_t get_capsrc(struct alc_spec *spec, int idx)
+{
+	return spec->capsrc_nids ?
+		spec->capsrc_nids[idx] : spec->adc_nids[idx];
+}
+
 /* select the given imux item; either unmute exclusively or select the route */
 static int alc_mux_select(struct hda_codec *codec, unsigned int adc_idx,
 			  unsigned int idx, bool force)
@@ -303,8 +309,7 @@ static int alc_mux_select(struct hda_codec *codec, unsigned int adc_idx,
 		adc_idx = spec->dyn_adc_idx[idx];
 	}
 
-	nid = spec->capsrc_nids ?
-		spec->capsrc_nids[adc_idx] : spec->adc_nids[adc_idx];
+	nid = get_capsrc(spec, adc_idx);
 
 	/* no selection? */
 	num_conns = snd_hda_get_conn_list(codec, nid, NULL);
@@ -1054,8 +1059,19 @@ static bool alc_rebuild_imux_for_auto_mic(struct hda_codec *codec)
 	spec->imux_pins[2] = spec->dock_mic_pin;
 	for (i = 0; i < 3; i++) {
 		strcpy(imux->items[i].label, texts[i]);
-		if (spec->imux_pins[i])
+		if (spec->imux_pins[i]) {
+			hda_nid_t pin = spec->imux_pins[i];
+			int c;
+			for (c = 0; c < spec->num_adc_nids; c++) {
+				hda_nid_t cap = get_capsrc(spec, c);
+				int idx = get_connection_index(codec, cap, pin);
+				if (idx >= 0) {
+					imux->items[i].index = idx;
+					break;
+				}
+			}
 			imux->num_items = i + 1;
+		}
 	}
 	spec->num_mux_defs = 1;
 	spec->input_mux = imux;
@@ -1452,7 +1468,7 @@ static void alc_apply_fixup(struct hda_codec *codec, int action)
 		switch (fix->type) {
 		case ALC_FIXUP_SKU:
 			if (action != ALC_FIXUP_ACT_PRE_PROBE || !fix->v.sku)
-				break;;
+				break;
 			snd_printdd(KERN_INFO "hda_codec: %s: "
 				    "Apply sku override for %s\n",
 				    codec->chip_name, modelname);
@@ -1957,10 +1973,8 @@ static int alc_build_controls(struct hda_codec *codec)
 		if (!kctl)
 			kctl = snd_hda_find_mixer_ctl(codec, "Input Source");
 		for (i = 0; kctl && i < kctl->count; i++) {
-			const hda_nid_t *nids = spec->capsrc_nids;
-			if (!nids)
-				nids = spec->adc_nids;
-			err = snd_hda_add_nid(codec, kctl, i, nids[i]);
+			err = snd_hda_add_nid(codec, kctl, i,
+					      get_capsrc(spec, i));
 			if (err < 0)
 				return err;
 		}
@@ -2747,8 +2761,7 @@ static int alc_auto_create_input_ctls(struct hda_codec *codec)
 		}
 
 		for (c = 0; c < num_adcs; c++) {
-			hda_nid_t cap = spec->capsrc_nids ?
-				spec->capsrc_nids[c] : spec->adc_nids[c];
+			hda_nid_t cap = get_capsrc(spec, c);
 			idx = get_connection_index(codec, cap, pin);
 			if (idx >= 0) {
 				spec->imux_pins[imux->num_items] = pin;
@@ -3694,8 +3707,7 @@ static int init_capsrc_for_pin(struct hda_codec *codec, hda_nid_t pin)
 	if (!pin)
 		return 0;
 	for (i = 0; i < spec->num_adc_nids; i++) {
-		hda_nid_t cap = spec->capsrc_nids ?
-			spec->capsrc_nids[i] : spec->adc_nids[i];
+		hda_nid_t cap = get_capsrc(spec, i);
 		int idx;
 
 		idx = get_connection_index(codec, cap, pin);
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index edc2b7b..d8d2f9d 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -227,7 +227,6 @@ struct sigmatel_spec {
 
 	/* power management */
 	unsigned int num_pwrs;
-	const unsigned int *pwr_mapping;
 	const hda_nid_t *pwr_nids;
 	const hda_nid_t *dac_list;
 
@@ -374,18 +373,15 @@ static const unsigned long stac92hd73xx_capvols[] = {
 
 #define STAC92HD83_DAC_COUNT 3
 
-static const hda_nid_t stac92hd83xxx_pwr_nids[4] = {
-	0xa, 0xb, 0xd, 0xe,
+static const hda_nid_t stac92hd83xxx_pwr_nids[7] = {
+	0x0a, 0x0b, 0x0c, 0xd, 0x0e,
+	0x0f, 0x10
 };
 
 static const hda_nid_t stac92hd83xxx_slave_dig_outs[2] = {
 	0x1e, 0,
 };
 
-static const unsigned int stac92hd83xxx_pwr_mapping[4] = {
-	0x03, 0x0c, 0x20, 0x40,
-};
-
 static const hda_nid_t stac92hd83xxx_dmic_nids[] = {
 		0x11, 0x20,
 };
@@ -1645,6 +1641,8 @@ static const struct snd_pci_quirk stac92hd73xx_codec_id_cfg_tbl[] = {
 		      "Alienware M17x", STAC_ALIENWARE_M17X),
 	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x043a,
 		      "Alienware M17x", STAC_ALIENWARE_M17X),
+	SND_PCI_QUIRK(PCI_VENDOR_ID_DELL, 0x0490,
+		      "Alienware M17x", STAC_ALIENWARE_M17X),
 	{} /* terminator */
 };
 
@@ -4443,7 +4441,9 @@ static int stac92xx_init(struct hda_codec *codec)
 		int pinctl, def_conf;
 
 		/* power on when no jack detection is available */
-		if (!spec->hp_detect) {
+		/* or when the VREF is used for controlling LED */
+		if (!spec->hp_detect ||
+		    (spec->gpio_led > 8 && spec->gpio_led == nid)) {
 			stac_toggle_power_map(codec, nid, 1);
 			continue;
 		}
@@ -4470,8 +4470,12 @@ static int stac92xx_init(struct hda_codec *codec)
 				stac_toggle_power_map(codec, nid, 1);
 			continue;
 		}
-		if (enable_pin_detect(codec, nid, STAC_PWR_EVENT))
+		if (enable_pin_detect(codec, nid, STAC_PWR_EVENT)) {
 			stac_issue_unsol_event(codec, nid);
+			continue;
+		}
+		/* none of the above, turn the port OFF */
+		stac_toggle_power_map(codec, nid, 0);
 	}
 
 	/* sync mute LED */
@@ -4727,11 +4731,7 @@ static void stac_toggle_power_map(struct hda_codec *codec, hda_nid_t nid,
 	if (idx >= spec->num_pwrs)
 		return;
 
-	/* several codecs have two power down bits */
-	if (spec->pwr_mapping)
-		idx = spec->pwr_mapping[idx];
-	else
-		idx = 1 << idx;
+	idx = 1 << idx;
 
 	val = snd_hda_codec_read(codec, codec->afg, 0, 0x0fec, 0x0) & 0xff;
 	if (enable)
@@ -5057,20 +5057,6 @@ static int stac92xx_pre_resume(struct hda_codec *codec)
 	return 0;
 }
 
-static int stac92xx_post_suspend(struct hda_codec *codec)
-{
-	struct sigmatel_spec *spec = codec->spec;
-	if (spec->gpio_led > 8) {
-		/* with vref-out pin used for mute led control
-		 * codec AFG is prevented from D3 state, but on
-		 * system suspend it can (and should) be used
-		 */
-		snd_hda_codec_read(codec, codec->afg, 0,
-				AC_VERB_SET_POWER_STATE, AC_PWRST_D3);
-	}
-	return 0;
-}
-
 static void stac92xx_set_power_state(struct hda_codec *codec, hda_nid_t fg,
 				unsigned int power_state)
 {
@@ -5629,9 +5615,6 @@ static int patch_stac92hd83xxx(struct hda_codec *codec)
 		snd_hda_codec_set_pincfg(codec, 0xf, 0x2181205e);
 	}
 
-	/* reset pin power-down; Windows may leave these bits after reboot */
-	snd_hda_codec_write_cache(codec, codec->afg, 0, 0x7EC, 0);
-	snd_hda_codec_write_cache(codec, codec->afg, 0, 0x7ED, 0);
 	codec->no_trigger_sense = 1;
 	codec->spec = spec;
 
@@ -5641,7 +5624,6 @@ static int patch_stac92hd83xxx(struct hda_codec *codec)
 	codec->slave_dig_outs = stac92hd83xxx_slave_dig_outs;
 	spec->digbeep_nid = 0x21;
 	spec->pwr_nids = stac92hd83xxx_pwr_nids;
-	spec->pwr_mapping = stac92hd83xxx_pwr_mapping;
 	spec->num_pwrs = ARRAY_SIZE(stac92hd83xxx_pwr_nids);
 	spec->multiout.dac_nids = spec->dac_nids;
 	spec->init = stac92hd83xxx_core_init;
@@ -5658,9 +5640,6 @@ again:
 		stac92xx_set_config_regs(codec,
 				stac92hd83xxx_brd_tbl[spec->board_config]);
 
-	if (spec->board_config != STAC_92HD83XXX_PWR_REF)
-		spec->num_pwrs = 0;
-
 	codec->patch_ops = stac92xx_patch_ops;
 
 	if (find_mute_led_gpio(codec, 0))
@@ -5677,8 +5656,6 @@ again:
 		} else {
 			codec->patch_ops.set_power_state =
 					stac92xx_set_power_state;
-			codec->patch_ops.post_suspend =
-					stac92xx_post_suspend;
 		}
 		codec->patch_ops.pre_resume = stac92xx_pre_resume;
 		codec->patch_ops.check_power_status =
@@ -5869,8 +5846,6 @@ again:
 		    (codec->revision_id & 0xf) == 1)
 			spec->stream_delay = 40; /* 40 milliseconds */
 
-		/* no output amps */
-		spec->num_pwrs = 0;
 		/* disable VSW */
 		spec->init = stac92hd71bxx_core_init;
 		unmute_init++;
@@ -5885,8 +5860,6 @@ again:
 		if ((codec->revision_id & 0xf) == 1)
 			spec->stream_delay = 40; /* 40 milliseconds */
 
-		/* no output amps */
-		spec->num_pwrs = 0;
 		/* fallthru */
 	default:
 		spec->init = stac92hd71bxx_core_init;
@@ -5996,8 +5969,6 @@ again:
 		} else {
 			codec->patch_ops.set_power_state =
 					stac92xx_set_power_state;
-			codec->patch_ops.post_suspend =
-					stac92xx_post_suspend;
 		}
 		codec->patch_ops.pre_resume = stac92xx_pre_resume;
 		codec->patch_ops.check_power_status =
diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c
index 431c0d4..b513762 100644
--- a/sound/pci/hda/patch_via.c
+++ b/sound/pci/hda/patch_via.c
@@ -208,6 +208,7 @@ struct via_spec {
 	/* work to check hp jack state */
 	struct hda_codec *codec;
 	struct delayed_work vt1708_hp_work;
+	int hp_work_active;
 	int vt1708_jack_detect;
 	int vt1708_hp_present;
 
@@ -305,27 +306,35 @@ enum {
 static void analog_low_current_mode(struct hda_codec *codec);
 static bool is_aa_path_mute(struct hda_codec *codec);
 
-static void vt1708_start_hp_work(struct via_spec *spec)
+#define hp_detect_with_aa(codec) \
+	(snd_hda_get_bool_hint(codec, "analog_loopback_hp_detect") == 1 && \
+	 !is_aa_path_mute(codec))
+
+static void vt1708_stop_hp_work(struct via_spec *spec)
 {
 	if (spec->codec_type != VT1708 || spec->autocfg.hp_pins[0] == 0)
 		return;
-	snd_hda_codec_write(spec->codec, 0x1, 0, 0xf81,
-			    !spec->vt1708_jack_detect);
-	if (!delayed_work_pending(&spec->vt1708_hp_work))
-		schedule_delayed_work(&spec->vt1708_hp_work,
-				      msecs_to_jiffies(100));
+	if (spec->hp_work_active) {
+		snd_hda_codec_write(spec->codec, 0x1, 0, 0xf81, 1);
+		cancel_delayed_work_sync(&spec->vt1708_hp_work);
+		spec->hp_work_active = 0;
+	}
 }
 
-static void vt1708_stop_hp_work(struct via_spec *spec)
+static void vt1708_update_hp_work(struct via_spec *spec)
 {
 	if (spec->codec_type != VT1708 || spec->autocfg.hp_pins[0] == 0)
 		return;
-	if (snd_hda_get_bool_hint(spec->codec, "analog_loopback_hp_detect") == 1
-	    && !is_aa_path_mute(spec->codec))
-		return;
-	snd_hda_codec_write(spec->codec, 0x1, 0, 0xf81,
-			    !spec->vt1708_jack_detect);
-	cancel_delayed_work_sync(&spec->vt1708_hp_work);
+	if (spec->vt1708_jack_detect &&
+	    (spec->active_streams || hp_detect_with_aa(spec->codec))) {
+		if (!spec->hp_work_active) {
+			snd_hda_codec_write(spec->codec, 0x1, 0, 0xf81, 0);
+			schedule_delayed_work(&spec->vt1708_hp_work,
+					      msecs_to_jiffies(100));
+			spec->hp_work_active = 1;
+		}
+	} else if (!hp_detect_with_aa(spec->codec))
+		vt1708_stop_hp_work(spec);
 }
 
 static void set_widgets_power_state(struct hda_codec *codec)
@@ -343,12 +352,7 @@ static int analog_input_switch_put(struct snd_kcontrol *kcontrol,
 
 	set_widgets_power_state(codec);
 	analog_low_current_mode(snd_kcontrol_chip(kcontrol));
-	if (snd_hda_get_bool_hint(codec, "analog_loopback_hp_detect") == 1) {
-		if (is_aa_path_mute(codec))
-			vt1708_start_hp_work(codec->spec);
-		else
-			vt1708_stop_hp_work(codec->spec);
-	}
+	vt1708_update_hp_work(codec->spec);
 	return change;
 }
 
@@ -1154,7 +1158,7 @@ static int via_playback_multi_pcm_prepare(struct hda_pcm_stream *hinfo,
 	spec->cur_dac_stream_tag = stream_tag;
 	spec->cur_dac_format = format;
 	mutex_unlock(&spec->config_mutex);
-	vt1708_start_hp_work(spec);
+	vt1708_update_hp_work(spec);
 	return 0;
 }
 
@@ -1174,7 +1178,7 @@ static int via_playback_hp_pcm_prepare(struct hda_pcm_stream *hinfo,
 	spec->cur_hp_stream_tag = stream_tag;
 	spec->cur_hp_format = format;
 	mutex_unlock(&spec->config_mutex);
-	vt1708_start_hp_work(spec);
+	vt1708_update_hp_work(spec);
 	return 0;
 }
 
@@ -1188,7 +1192,7 @@ static int via_playback_multi_pcm_cleanup(struct hda_pcm_stream *hinfo,
 	snd_hda_multi_out_analog_cleanup(codec, &spec->multiout);
 	spec->active_streams &= ~STREAM_MULTI_OUT;
 	mutex_unlock(&spec->config_mutex);
-	vt1708_stop_hp_work(spec);
+	vt1708_update_hp_work(spec);
 	return 0;
 }
 
@@ -1203,7 +1207,7 @@ static int via_playback_hp_pcm_cleanup(struct hda_pcm_stream *hinfo,
 		snd_hda_codec_setup_stream(codec, spec->hp_dac_nid, 0, 0, 0);
 	spec->active_streams &= ~STREAM_INDEP_HP;
 	mutex_unlock(&spec->config_mutex);
-	vt1708_stop_hp_work(spec);
+	vt1708_update_hp_work(spec);
 	return 0;
 }
 
@@ -1645,7 +1649,8 @@ static void via_hp_automute(struct hda_codec *codec)
 	int nums;
 	struct via_spec *spec = codec->spec;
 
-	if (!spec->hp_independent_mode && spec->autocfg.hp_pins[0])
+	if (!spec->hp_independent_mode && spec->autocfg.hp_pins[0] &&
+	    (spec->codec_type != VT1708 || spec->vt1708_jack_detect))
 		present = snd_hda_jack_detect(codec, spec->autocfg.hp_pins[0]);
 
 	if (spec->smart51_enabled)
@@ -2612,8 +2617,6 @@ static int vt1708_jack_detect_get(struct snd_kcontrol *kcontrol,
 
 	if (spec->codec_type != VT1708)
 		return 0;
-	spec->vt1708_jack_detect =
-		!((snd_hda_codec_read(codec, 0x1, 0, 0xf84, 0) >> 8) & 0x1);
 	ucontrol->value.integer.value[0] = spec->vt1708_jack_detect;
 	return 0;
 }
@@ -2623,18 +2626,22 @@ static int vt1708_jack_detect_put(struct snd_kcontrol *kcontrol,
 {
 	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct via_spec *spec = codec->spec;
-	int change;
+	int val;
 
 	if (spec->codec_type != VT1708)
 		return 0;
-	spec->vt1708_jack_detect = ucontrol->value.integer.value[0];
-	change = (0x1 & (snd_hda_codec_read(codec, 0x1, 0, 0xf84, 0) >> 8))
-		== !spec->vt1708_jack_detect;
-	if (spec->vt1708_jack_detect) {
+	val = !!ucontrol->value.integer.value[0];
+	if (spec->vt1708_jack_detect == val)
+		return 0;
+	spec->vt1708_jack_detect = val;
+	if (spec->vt1708_jack_detect &&
+	    snd_hda_get_bool_hint(codec, "analog_loopback_hp_detect") != 1) {
 		mute_aa_path(codec, 1);
 		notify_aa_path_ctls(codec);
 	}
-	return change;
+	via_hp_automute(codec);
+	vt1708_update_hp_work(spec);
+	return 1;
 }
 
 static const struct snd_kcontrol_new vt1708_jack_detect_ctl = {
@@ -2771,6 +2778,7 @@ static int via_init(struct hda_codec *codec)
 	via_auto_init_unsol_event(codec);
 
 	via_hp_automute(codec);
+	vt1708_update_hp_work(spec);
 
 	return 0;
 }
@@ -2787,7 +2795,9 @@ static void vt1708_update_hp_jack_state(struct work_struct *work)
 		spec->vt1708_hp_present ^= 1;
 		via_hp_automute(spec->codec);
 	}
-	vt1708_start_hp_work(spec);
+	if (spec->vt1708_jack_detect)
+		schedule_delayed_work(&spec->vt1708_hp_work,
+				      msecs_to_jiffies(100));
 }
 
 static int get_mux_nids(struct hda_codec *codec)
diff --git a/sound/pci/lx6464es/lx_core.c b/sound/pci/lx6464es/lx_core.c
index 5c8717e..8c3e7fc 100644
--- a/sound/pci/lx6464es/lx_core.c
+++ b/sound/pci/lx6464es/lx_core.c
@@ -78,10 +78,15 @@ unsigned long lx_dsp_reg_read(struct lx6464es *chip, int port)
 	return ioread32(address);
 }
 
-void lx_dsp_reg_readbuf(struct lx6464es *chip, int port, u32 *data, u32 len)
+static void lx_dsp_reg_readbuf(struct lx6464es *chip, int port, u32 *data,
+			       u32 len)
 {
-	void __iomem *address = lx_dsp_register(chip, port);
-	memcpy_fromio(data, address, len*sizeof(u32));
+	u32 __iomem *address = lx_dsp_register(chip, port);
+	int i;
+
+	/* we cannot use memcpy_fromio */
+	for (i = 0; i != len; ++i)
+		data[i] = ioread32(address + i);
 }
 
 
@@ -91,11 +96,15 @@ void lx_dsp_reg_write(struct lx6464es *chip, int port, unsigned data)
 	iowrite32(data, address);
 }
 
-void lx_dsp_reg_writebuf(struct lx6464es *chip, int port, const u32 *data,
-			 u32 len)
+static void lx_dsp_reg_writebuf(struct lx6464es *chip, int port,
+				const u32 *data, u32 len)
 {
-	void __iomem *address = lx_dsp_register(chip, port);
-	memcpy_toio(address, data, len*sizeof(u32));
+	u32 __iomem *address = lx_dsp_register(chip, port);
+	int i;
+
+	/* we cannot use memcpy_to */
+	for (i = 0; i != len; ++i)
+		iowrite32(data[i], address + i);
 }
 
 
diff --git a/sound/pci/lx6464es/lx_core.h b/sound/pci/lx6464es/lx_core.h
index 1dd5629..4d7ff79 100644
--- a/sound/pci/lx6464es/lx_core.h
+++ b/sound/pci/lx6464es/lx_core.h
@@ -72,10 +72,7 @@ enum {
 };
 
 unsigned long lx_dsp_reg_read(struct lx6464es *chip, int port);
-void lx_dsp_reg_readbuf(struct lx6464es *chip, int port, u32 *data, u32 len);
 void lx_dsp_reg_write(struct lx6464es *chip, int port, unsigned data);
-void lx_dsp_reg_writebuf(struct lx6464es *chip, int port, const u32 *data,
-			 u32 len);
 
 /* plx register access */
 enum {
diff --git a/sound/pci/rme9652/hdspm.c b/sound/pci/rme9652/hdspm.c
index e760ada..19ee220 100644
--- a/sound/pci/rme9652/hdspm.c
+++ b/sound/pci/rme9652/hdspm.c
@@ -6518,7 +6518,7 @@ static int __devinit snd_hdspm_create(struct snd_card *card,
 			hdspm->io_type = AES32;
 			hdspm->card_name = "RME AES32";
 			hdspm->midiPorts = 2;
-		} else if ((hdspm->firmware_rev == 0xd5) ||
+		} else if ((hdspm->firmware_rev == 0xd2) ||
 			((hdspm->firmware_rev >= 0xc8)  &&
 				(hdspm->firmware_rev <= 0xcf))) {
 			hdspm->io_type = MADI;
diff --git a/sound/soc/atmel/Kconfig b/sound/soc/atmel/Kconfig
index bee3c94..d1fcc81 100644
--- a/sound/soc/atmel/Kconfig
+++ b/sound/soc/atmel/Kconfig
@@ -1,6 +1,6 @@
 config SND_ATMEL_SOC
 	tristate "SoC Audio for the Atmel System-on-Chip"
-	depends on ARCH_AT91 || AVR32
+	depends on ARCH_AT91
 	help
 	  Say Y or M if you want to add support for codecs attached to
 	  the ATMEL SSC interface. You will also need
@@ -24,25 +24,6 @@ config SND_AT91_SOC_SAM9G20_WM8731
 	  Say Y if you want to add support for SoC audio on WM8731-based
 	  AT91sam9g20 evaluation board.
 
-config SND_AT32_SOC_PLAYPAQ
-        tristate "SoC Audio support for PlayPaq with WM8510"
-        depends on SND_ATMEL_SOC && BOARD_PLAYPAQ && AT91_PROGRAMMABLE_CLOCKS
-        select SND_ATMEL_SOC_SSC
-        select SND_SOC_WM8510
-        help
-          Say Y or M here if you want to add support for SoC audio
-          on the LRS PlayPaq.
-
-config SND_AT32_SOC_PLAYPAQ_SLAVE
-        bool "Run CODEC on PlayPaq in slave mode"
-        depends on SND_AT32_SOC_PLAYPAQ
-        default n
-        help
-          Say Y if you want to run with the AT32 SSC generating the BCLK
-          and FRAME signals on the PlayPaq.  Unless you want to play
-          with the AT32 as the SSC master, you probably want to say N here,
-          as this will give you better sound quality.
-
 config SND_AT91_SOC_AFEB9260
 	tristate "SoC Audio support for AFEB9260 board"
 	depends on ARCH_AT91 && MACH_AFEB9260 && SND_ATMEL_SOC
diff --git a/sound/soc/atmel/Makefile b/sound/soc/atmel/Makefile
index e7ea56b..a5c0bf1 100644
--- a/sound/soc/atmel/Makefile
+++ b/sound/soc/atmel/Makefile
@@ -8,9 +8,5 @@ obj-$(CONFIG_SND_ATMEL_SOC_SSC) += snd-soc-atmel_ssc_dai.o
 # AT91 Machine Support
 snd-soc-sam9g20-wm8731-objs := sam9g20_wm8731.o
 
-# AT32 Machine Support
-snd-soc-playpaq-objs := playpaq_wm8510.o
-
 obj-$(CONFIG_SND_AT91_SOC_SAM9G20_WM8731) += snd-soc-sam9g20-wm8731.o
-obj-$(CONFIG_SND_AT32_SOC_PLAYPAQ) += snd-soc-playpaq.o
 obj-$(CONFIG_SND_AT91_SOC_AFEB9260) += snd-soc-afeb9260.o
diff --git a/sound/soc/atmel/playpaq_wm8510.c b/sound/soc/atmel/playpaq_wm8510.c
deleted file mode 100644
index 73ae99a..0000000
--- a/sound/soc/atmel/playpaq_wm8510.c
+++ /dev/null
@@ -1,473 +0,0 @@
-/* sound/soc/at32/playpaq_wm8510.c
- * ASoC machine driver for PlayPaq using WM8510 codec
- *
- * Copyright (C) 2008 Long Range Systems
- *    Geoffrey Wossum <gwossum@acm.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This code is largely inspired by sound/soc/at91/eti_b1_wm8731.c
- *
- * NOTE: If you don't have the AT32 enhanced portmux configured (which
- * isn't currently in the mainline or Atmel patched kernel), you will
- * need to set the MCLK pin (PA30) to peripheral A in your board initialization
- * code.  Something like:
- *	at32_select_periph(GPIO_PIN_PA(30), GPIO_PERIPH_A, 0);
- *
- */
-
-/* #define DEBUG */
-
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/clk.h>
-#include <linux/timer.h>
-#include <linux/interrupt.h>
-#include <linux/platform_device.h>
-
-#include <sound/core.h>
-#include <sound/pcm.h>
-#include <sound/pcm_params.h>
-#include <sound/soc.h>
-
-#include <mach/at32ap700x.h>
-#include <mach/portmux.h>
-
-#include "../codecs/wm8510.h"
-#include "atmel-pcm.h"
-#include "atmel_ssc_dai.h"
-
-
-/*-------------------------------------------------------------------------*\
- * constants
-\*-------------------------------------------------------------------------*/
-#define MCLK_PIN		GPIO_PIN_PA(30)
-#define MCLK_PERIPH		GPIO_PERIPH_A
-
-
-/*-------------------------------------------------------------------------*\
- * data types
-\*-------------------------------------------------------------------------*/
-/* SSC clocking data */
-struct ssc_clock_data {
-	/* CMR div */
-	unsigned int cmr_div;
-
-	/* Frame period (as needed by xCMR.PERIOD) */
-	unsigned int period;
-
-	/* The SSC clock rate these settings where calculated for */
-	unsigned long ssc_rate;
-};
-
-
-/*-------------------------------------------------------------------------*\
- * module data
-\*-------------------------------------------------------------------------*/
-static struct clk *_gclk0;
-static struct clk *_pll0;
-
-#define CODEC_CLK (_gclk0)
-
-
-/*-------------------------------------------------------------------------*\
- * Sound SOC operations
-\*-------------------------------------------------------------------------*/
-#if defined CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE
-static struct ssc_clock_data playpaq_wm8510_calc_ssc_clock(
-	struct snd_pcm_hw_params *params,
-	struct snd_soc_dai *cpu_dai)
-{
-	struct at32_ssc_info *ssc_p = snd_soc_dai_get_drvdata(cpu_dai);
-	struct ssc_device *ssc = ssc_p->ssc;
-	struct ssc_clock_data cd;
-	unsigned int rate, width_bits, channels;
-	unsigned int bitrate, ssc_div;
-	unsigned actual_rate;
-
-
-	/*
-	 * Figure out required bitrate
-	 */
-	rate = params_rate(params);
-	channels = params_channels(params);
-	width_bits = snd_pcm_format_physical_width(params_format(params));
-	bitrate = rate * width_bits * channels;
-
-
-	/*
-	 * Figure out required SSC divider and period for required bitrate
-	 */
-	cd.ssc_rate = clk_get_rate(ssc->clk);
-	ssc_div = cd.ssc_rate / bitrate;
-	cd.cmr_div = ssc_div / 2;
-	if (ssc_div & 1) {
-		/* round cmr_div up */
-		cd.cmr_div++;
-	}
-	cd.period = width_bits - 1;
-
-
-	/*
-	 * Find actual rate, compare to requested rate
-	 */
-	actual_rate = (cd.ssc_rate / (cd.cmr_div * 2)) / (2 * (cd.period + 1));
-	pr_debug("playpaq_wm8510: Request rate = %u, actual rate = %u\n",
-		 rate, actual_rate);
-
-
-	return cd;
-}
-#endif /* CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE */
-
-
-
-static int playpaq_wm8510_hw_params(struct snd_pcm_substream *substream,
-				    struct snd_pcm_hw_params *params)
-{
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_dai *codec_dai = rtd->codec_dai;
-	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
-	struct at32_ssc_info *ssc_p = snd_soc_dai_get_drvdata(cpu_dai);
-	struct ssc_device *ssc = ssc_p->ssc;
-	unsigned int pll_out = 0, bclk = 0, mclk_div = 0;
-	int ret;
-
-
-	/* Due to difficulties with getting the correct clocks from the AT32's
-	 * PLL0, we're going to let the CODEC be in charge of all the clocks
-	 */
-#if !defined CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE
-	const unsigned int fmt = (SND_SOC_DAIFMT_I2S |
-				  SND_SOC_DAIFMT_NB_NF |
-				  SND_SOC_DAIFMT_CBM_CFM);
-#else
-	struct ssc_clock_data cd;
-	const unsigned int fmt = (SND_SOC_DAIFMT_I2S |
-				  SND_SOC_DAIFMT_NB_NF |
-				  SND_SOC_DAIFMT_CBS_CFS);
-#endif
-
-	if (ssc == NULL) {
-		pr_warning("playpaq_wm8510_hw_params: ssc is NULL!\n");
-		return -EINVAL;
-	}
-
-
-	/*
-	 * Figure out PLL and BCLK dividers for WM8510
-	 */
-	switch (params_rate(params)) {
-	case 48000:
-		pll_out = 24576000;
-		mclk_div = WM8510_MCLKDIV_2;
-		bclk = WM8510_BCLKDIV_8;
-		break;
-
-	case 44100:
-		pll_out = 22579200;
-		mclk_div = WM8510_MCLKDIV_2;
-		bclk = WM8510_BCLKDIV_8;
-		break;
-
-	case 22050:
-		pll_out = 22579200;
-		mclk_div = WM8510_MCLKDIV_4;
-		bclk = WM8510_BCLKDIV_8;
-		break;
-
-	case 16000:
-		pll_out = 24576000;
-		mclk_div = WM8510_MCLKDIV_6;
-		bclk = WM8510_BCLKDIV_8;
-		break;
-
-	case 11025:
-		pll_out = 22579200;
-		mclk_div = WM8510_MCLKDIV_8;
-		bclk = WM8510_BCLKDIV_8;
-		break;
-
-	case 8000:
-		pll_out = 24576000;
-		mclk_div = WM8510_MCLKDIV_12;
-		bclk = WM8510_BCLKDIV_8;
-		break;
-
-	default:
-		pr_warning("playpaq_wm8510: Unsupported sample rate %d\n",
-			   params_rate(params));
-		return -EINVAL;
-	}
-
-
-	/*
-	 * set CPU and CODEC DAI configuration
-	 */
-	ret = snd_soc_dai_set_fmt(codec_dai, fmt);
-	if (ret < 0) {
-		pr_warning("playpaq_wm8510: "
-			   "Failed to set CODEC DAI format (%d)\n",
-			   ret);
-		return ret;
-	}
-	ret = snd_soc_dai_set_fmt(cpu_dai, fmt);
-	if (ret < 0) {
-		pr_warning("playpaq_wm8510: "
-			   "Failed to set CPU DAI format (%d)\n",
-			   ret);
-		return ret;
-	}
-
-
-	/*
-	 * Set CPU clock configuration
-	 */
-#if defined CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE
-	cd = playpaq_wm8510_calc_ssc_clock(params, cpu_dai);
-	pr_debug("playpaq_wm8510: cmr_div = %d, period = %d\n",
-		 cd.cmr_div, cd.period);
-	ret = snd_soc_dai_set_clkdiv(cpu_dai, AT32_SSC_CMR_DIV, cd.cmr_div);
-	if (ret < 0) {
-		pr_warning("playpaq_wm8510: Failed to set CPU CMR_DIV (%d)\n",
-			   ret);
-		return ret;
-	}
-	ret = snd_soc_dai_set_clkdiv(cpu_dai, AT32_SSC_TCMR_PERIOD,
-					  cd.period);
-	if (ret < 0) {
-		pr_warning("playpaq_wm8510: "
-			   "Failed to set CPU transmit period (%d)\n",
-			   ret);
-		return ret;
-	}
-#endif /* CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE */
-
-
-	/*
-	 * Set CODEC clock configuration
-	 */
-	pr_debug("playpaq_wm8510: "
-		 "pll_in = %ld, pll_out = %u, bclk = %x, mclk = %x\n",
-		 clk_get_rate(CODEC_CLK), pll_out, bclk, mclk_div);
-
-
-#if !defined CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE
-	ret = snd_soc_dai_set_clkdiv(codec_dai, WM8510_BCLKDIV, bclk);
-	if (ret < 0) {
-		pr_warning
-		    ("playpaq_wm8510: Failed to set CODEC DAI BCLKDIV (%d)\n",
-		     ret);
-		return ret;
-	}
-#endif /* CONFIG_SND_AT32_SOC_PLAYPAQ_SLAVE */
-
-
-	ret = snd_soc_dai_set_pll(codec_dai, 0, 0,
-					 clk_get_rate(CODEC_CLK), pll_out);
-	if (ret < 0) {
-		pr_warning("playpaq_wm8510: Failed to set CODEC DAI PLL (%d)\n",
-			   ret);
-		return ret;
-	}
-
-
-	ret = snd_soc_dai_set_clkdiv(codec_dai, WM8510_MCLKDIV, mclk_div);
-	if (ret < 0) {
-		pr_warning("playpaq_wm8510: Failed to set CODEC MCLKDIV (%d)\n",
-			   ret);
-		return ret;
-	}
-
-
-	return 0;
-}
-
-
-
-static struct snd_soc_ops playpaq_wm8510_ops = {
-	.hw_params = playpaq_wm8510_hw_params,
-};
-
-
-
-static const struct snd_soc_dapm_widget playpaq_dapm_widgets[] = {
-	SND_SOC_DAPM_MIC("Int Mic", NULL),
-	SND_SOC_DAPM_SPK("Ext Spk", NULL),
-};
-
-
-
-static const struct snd_soc_dapm_route intercon[] = {
-	/* speaker connected to SPKOUT */
-	{"Ext Spk", NULL, "SPKOUTP"},
-	{"Ext Spk", NULL, "SPKOUTN"},
-
-	{"Mic Bias", NULL, "Int Mic"},
-	{"MICN", NULL, "Mic Bias"},
-	{"MICP", NULL, "Mic Bias"},
-};
-
-
-
-static int playpaq_wm8510_init(struct snd_soc_pcm_runtime *rtd)
-{
-	struct snd_soc_codec *codec = rtd->codec;
-	struct snd_soc_dapm_context *dapm = &codec->dapm;
-	int i;
-
-	/*
-	 * Add DAPM widgets
-	 */
-	for (i = 0; i < ARRAY_SIZE(playpaq_dapm_widgets); i++)
-		snd_soc_dapm_new_control(dapm, &playpaq_dapm_widgets[i]);
-
-
-
-	/*
-	 * Setup audio path interconnects
-	 */
-	snd_soc_dapm_add_routes(dapm, intercon, ARRAY_SIZE(intercon));
-
-
-
-	/* always connected pins */
-	snd_soc_dapm_enable_pin(dapm, "Int Mic");
-	snd_soc_dapm_enable_pin(dapm, "Ext Spk");
-
-
-
-	/* Make CSB show PLL rate */
-	snd_soc_dai_set_clkdiv(rtd->codec_dai, WM8510_OPCLKDIV,
-				       WM8510_OPCLKDIV_1 | 4);
-
-	return 0;
-}
-
-
-
-static struct snd_soc_dai_link playpaq_wm8510_dai = {
-	.name = "WM8510",
-	.stream_name = "WM8510 PCM",
-	.cpu_dai_name= "atmel-ssc-dai.0",
-	.platform_name = "atmel-pcm-audio",
-	.codec_name = "wm8510-codec.0-0x1a",
-	.codec_dai_name = "wm8510-hifi",
-	.init = playpaq_wm8510_init,
-	.ops = &playpaq_wm8510_ops,
-};
-
-
-
-static struct snd_soc_card snd_soc_playpaq = {
-	.name = "LRS_PlayPaq_WM8510",
-	.dai_link = &playpaq_wm8510_dai,
-	.num_links = 1,
-};
-
-static struct platform_device *playpaq_snd_device;
-
-
-static int __init playpaq_asoc_init(void)
-{
-	int ret = 0;
-
-	/*
-	 * Configure MCLK for WM8510
-	 */
-	_gclk0 = clk_get(NULL, "gclk0");
-	if (IS_ERR(_gclk0)) {
-		_gclk0 = NULL;
-		ret = PTR_ERR(_gclk0);
-		goto err_gclk0;
-	}
-	_pll0 = clk_get(NULL, "pll0");
-	if (IS_ERR(_pll0)) {
-		_pll0 = NULL;
-		ret = PTR_ERR(_pll0);
-		goto err_pll0;
-	}
-	ret = clk_set_parent(_gclk0, _pll0);
-	if (ret) {
-		pr_warning("snd-soc-playpaq: "
-			   "Failed to set PLL0 as parent for DAC clock\n");
-		goto err_set_clk;
-	}
-	clk_set_rate(CODEC_CLK, 12000000);
-	clk_enable(CODEC_CLK);
-
-#if defined CONFIG_AT32_ENHANCED_PORTMUX
-	at32_select_periph(MCLK_PIN, MCLK_PERIPH, 0);
-#endif
-
-
-	/*
-	 * Create and register platform device
-	 */
-	playpaq_snd_device = platform_device_alloc("soc-audio", 0);
-	if (playpaq_snd_device == NULL) {
-		ret = -ENOMEM;
-		goto err_device_alloc;
-	}
-
-	platform_set_drvdata(playpaq_snd_device, &snd_soc_playpaq);
-
-	ret = platform_device_add(playpaq_snd_device);
-	if (ret) {
-		pr_warning("playpaq_wm8510: platform_device_add failed (%d)\n",
-			   ret);
-		goto err_device_add;
-	}
-
-	return 0;
-
-
-err_device_add:
-	if (playpaq_snd_device != NULL) {
-		platform_device_put(playpaq_snd_device);
-		playpaq_snd_device = NULL;
-	}
-err_device_alloc:
-err_set_clk:
-	if (_pll0 != NULL) {
-		clk_put(_pll0);
-		_pll0 = NULL;
-	}
-err_pll0:
-	if (_gclk0 != NULL) {
-		clk_put(_gclk0);
-		_gclk0 = NULL;
-	}
-	return ret;
-}
-
-
-static void __exit playpaq_asoc_exit(void)
-{
-	if (_gclk0 != NULL) {
-		clk_put(_gclk0);
-		_gclk0 = NULL;
-	}
-	if (_pll0 != NULL) {
-		clk_put(_pll0);
-		_pll0 = NULL;
-	}
-
-#if defined CONFIG_AT32_ENHANCED_PORTMUX
-	at32_free_pin(MCLK_PIN);
-#endif
-
-	platform_device_unregister(playpaq_snd_device);
-	playpaq_snd_device = NULL;
-}
-
-module_init(playpaq_asoc_init);
-module_exit(playpaq_asoc_exit);
-
-MODULE_AUTHOR("Geoffrey Wossum <gwossum@acm.org>");
-MODULE_DESCRIPTION("ASoC machine driver for LRS PlayPaq");
-MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/ad1836.h b/sound/soc/codecs/ad1836.h
index 444747f..dd7be0d 100644
--- a/sound/soc/codecs/ad1836.h
+++ b/sound/soc/codecs/ad1836.h
@@ -34,7 +34,7 @@
 
 #define AD1836_ADC_CTRL2               13
 #define AD1836_ADC_WORD_LEN_MASK       0x30
-#define AD1836_ADC_WORD_OFFSET         5
+#define AD1836_ADC_WORD_OFFSET         4
 #define AD1836_ADC_SERFMT_MASK         (7 << 6)
 #define AD1836_ADC_SERFMT_PCK256       (0x4 << 6)
 #define AD1836_ADC_SERFMT_PCK128       (0x5 << 6)
diff --git a/sound/soc/codecs/adau1373.c b/sound/soc/codecs/adau1373.c
index 1ccf8dd..45c6302 100644
--- a/sound/soc/codecs/adau1373.c
+++ b/sound/soc/codecs/adau1373.c
@@ -245,7 +245,7 @@ static const char *adau1373_bass_hpf_cutoff_text[] = {
 };
 
 static const unsigned int adau1373_bass_tlv[] = {
-	TLV_DB_RANGE_HEAD(4),
+	TLV_DB_RANGE_HEAD(3),
 	0, 2, TLV_DB_SCALE_ITEM(-600, 600, 1),
 	3, 4, TLV_DB_SCALE_ITEM(950, 250, 0),
 	5, 7, TLV_DB_SCALE_ITEM(1400, 150, 0),
diff --git a/sound/soc/codecs/cs4270.c b/sound/soc/codecs/cs4270.c
index f1f237e..73f46eb 100644
--- a/sound/soc/codecs/cs4270.c
+++ b/sound/soc/codecs/cs4270.c
@@ -601,7 +601,6 @@ static int cs4270_soc_suspend(struct snd_soc_codec *codec, pm_message_t mesg)
 static int cs4270_soc_resume(struct snd_soc_codec *codec)
 {
 	struct cs4270_private *cs4270 = snd_soc_codec_get_drvdata(codec);
-	struct i2c_client *i2c_client = to_i2c_client(codec->dev);
 	int reg;
 
 	regulator_bulk_enable(ARRAY_SIZE(cs4270->supplies),
@@ -612,14 +611,7 @@ static int cs4270_soc_resume(struct snd_soc_codec *codec)
 	ndelay(500);
 
 	/* first restore the entire register cache ... */
-	for (reg = CS4270_FIRSTREG; reg <= CS4270_LASTREG; reg++) {
-		u8 val = snd_soc_read(codec, reg);
-
-		if (i2c_smbus_write_byte_data(i2c_client, reg, val)) {
-			dev_err(codec->dev, "i2c write failed\n");
-			return -EIO;
-		}
-	}
+	snd_soc_cache_sync(codec);
 
 	/* ... then disable the power-down bits */
 	reg = snd_soc_read(codec, CS4270_PWRCTL);
diff --git a/sound/soc/codecs/cs4271.c b/sound/soc/codecs/cs4271.c
index 23d1bd5..69fde15 100644
--- a/sound/soc/codecs/cs4271.c
+++ b/sound/soc/codecs/cs4271.c
@@ -434,7 +434,8 @@ static int cs4271_soc_suspend(struct snd_soc_codec *codec, pm_message_t mesg)
 {
 	int ret;
 	/* Set power-down bit */
-	ret = snd_soc_update_bits(codec, CS4271_MODE2, 0, CS4271_MODE2_PDN);
+	ret = snd_soc_update_bits(codec, CS4271_MODE2, CS4271_MODE2_PDN,
+				  CS4271_MODE2_PDN);
 	if (ret < 0)
 		return ret;
 	return 0;
@@ -501,8 +502,9 @@ static int cs4271_probe(struct snd_soc_codec *codec)
 		return ret;
 	}
 
-	ret = snd_soc_update_bits(codec, CS4271_MODE2, 0,
-		CS4271_MODE2_PDN | CS4271_MODE2_CPEN);
+	ret = snd_soc_update_bits(codec, CS4271_MODE2,
+				  CS4271_MODE2_PDN | CS4271_MODE2_CPEN,
+				  CS4271_MODE2_PDN | CS4271_MODE2_CPEN);
 	if (ret < 0)
 		return ret;
 	ret = snd_soc_update_bits(codec, CS4271_MODE2, CS4271_MODE2_PDN, 0);
diff --git a/sound/soc/codecs/cs42l51.c b/sound/soc/codecs/cs42l51.c
index 8c3c820..1ee66361 100644
--- a/sound/soc/codecs/cs42l51.c
+++ b/sound/soc/codecs/cs42l51.c
@@ -555,7 +555,7 @@ static int cs42l51_probe(struct snd_soc_codec *codec)
 
 static struct snd_soc_codec_driver soc_codec_device_cs42l51 = {
 	.probe =	cs42l51_probe,
-	.reg_cache_size = CS42L51_NUMREGS,
+	.reg_cache_size = CS42L51_NUMREGS + 1,
 	.reg_word_size = sizeof(u8),
 };
 
diff --git a/sound/soc/codecs/max9877.c b/sound/soc/codecs/max9877.c
index 9e7e964..dcf6f2a 100644
--- a/sound/soc/codecs/max9877.c
+++ b/sound/soc/codecs/max9877.c
@@ -106,13 +106,13 @@ static int max9877_set_2reg(struct snd_kcontrol *kcontrol,
 	unsigned int mask = mc->max;
 	unsigned int val = (ucontrol->value.integer.value[0] & mask);
 	unsigned int val2 = (ucontrol->value.integer.value[1] & mask);
-	unsigned int change = 1;
+	unsigned int change = 0;
 
-	if (((max9877_regs[reg] >> shift) & mask) == val)
-		change = 0;
+	if (((max9877_regs[reg] >> shift) & mask) != val)
+		change = 1;
 
-	if (((max9877_regs[reg2] >> shift) & mask) == val2)
-		change = 0;
+	if (((max9877_regs[reg2] >> shift) & mask) != val2)
+		change = 1;
 
 	if (change) {
 		max9877_regs[reg] &= ~(mask << shift);
diff --git a/sound/soc/codecs/rt5631.c b/sound/soc/codecs/rt5631.c
index 27a078c..4646e80 100644
--- a/sound/soc/codecs/rt5631.c
+++ b/sound/soc/codecs/rt5631.c
@@ -177,7 +177,7 @@ static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -95625, 375, 0);
 static const DECLARE_TLV_DB_SCALE(in_vol_tlv, -3450, 150, 0);
 /* {0, +20, +24, +30, +35, +40, +44, +50, +52}dB */
 static unsigned int mic_bst_tlv[] = {
-	TLV_DB_RANGE_HEAD(6),
+	TLV_DB_RANGE_HEAD(7),
 	0, 0, TLV_DB_SCALE_ITEM(0, 0, 0),
 	1, 1, TLV_DB_SCALE_ITEM(2000, 0, 0),
 	2, 2, TLV_DB_SCALE_ITEM(2400, 0, 0),
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index d15695d..bbcf921 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -365,7 +365,7 @@ static const DECLARE_TLV_DB_SCALE(capture_6db_attenuate, -600, 600, 0);
 
 /* tlv for mic gain, 0db 20db 30db 40db */
 static const unsigned int mic_gain_tlv[] = {
-	TLV_DB_RANGE_HEAD(4),
+	TLV_DB_RANGE_HEAD(2),
 	0, 0, TLV_DB_SCALE_ITEM(0, 0, 0),
 	1, 3, TLV_DB_SCALE_ITEM(2000, 1000, 0),
 };
diff --git a/sound/soc/codecs/sta32x.c b/sound/soc/codecs/sta32x.c
index bb82408..d2f3715 100644
--- a/sound/soc/codecs/sta32x.c
+++ b/sound/soc/codecs/sta32x.c
@@ -76,6 +76,8 @@ struct sta32x_priv {
 
 	unsigned int mclk;
 	unsigned int format;
+
+	u32 coef_shadow[STA32X_COEF_COUNT];
 };
 
 static const DECLARE_TLV_DB_SCALE(mvol_tlv, -12700, 50, 1);
@@ -227,6 +229,7 @@ static int sta32x_coefficient_put(struct snd_kcontrol *kcontrol,
 				  struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct sta32x_priv *sta32x = snd_soc_codec_get_drvdata(codec);
 	int numcoef = kcontrol->private_value >> 16;
 	int index = kcontrol->private_value & 0xffff;
 	unsigned int cfud;
@@ -239,6 +242,11 @@ static int sta32x_coefficient_put(struct snd_kcontrol *kcontrol,
 	snd_soc_write(codec, STA32X_CFUD, cfud);
 
 	snd_soc_write(codec, STA32X_CFADDR2, index);
+	for (i = 0; i < numcoef && (index + i < STA32X_COEF_COUNT); i++)
+		sta32x->coef_shadow[index + i] =
+			  (ucontrol->value.bytes.data[3 * i] << 16)
+			| (ucontrol->value.bytes.data[3 * i + 1] << 8)
+			| (ucontrol->value.bytes.data[3 * i + 2]);
 	for (i = 0; i < 3 * numcoef; i++)
 		snd_soc_write(codec, STA32X_B1CF1 + i,
 			      ucontrol->value.bytes.data[i]);
@@ -252,6 +260,48 @@ static int sta32x_coefficient_put(struct snd_kcontrol *kcontrol,
 	return 0;
 }
 
+int sta32x_sync_coef_shadow(struct snd_soc_codec *codec)
+{
+	struct sta32x_priv *sta32x = snd_soc_codec_get_drvdata(codec);
+	unsigned int cfud;
+	int i;
+
+	/* preserve reserved bits in STA32X_CFUD */
+	cfud = snd_soc_read(codec, STA32X_CFUD) & 0xf0;
+
+	for (i = 0; i < STA32X_COEF_COUNT; i++) {
+		snd_soc_write(codec, STA32X_CFADDR2, i);
+		snd_soc_write(codec, STA32X_B1CF1,
+			      (sta32x->coef_shadow[i] >> 16) & 0xff);
+		snd_soc_write(codec, STA32X_B1CF2,
+			      (sta32x->coef_shadow[i] >> 8) & 0xff);
+		snd_soc_write(codec, STA32X_B1CF3,
+			      (sta32x->coef_shadow[i]) & 0xff);
+		/* chip documentation does not say if the bits are
+		 * self-clearing, so do it explicitly */
+		snd_soc_write(codec, STA32X_CFUD, cfud);
+		snd_soc_write(codec, STA32X_CFUD, cfud | 0x01);
+	}
+	return 0;
+}
+
+int sta32x_cache_sync(struct snd_soc_codec *codec)
+{
+	unsigned int mute;
+	int rc;
+
+	if (!codec->cache_sync)
+		return 0;
+
+	/* mute during register sync */
+	mute = snd_soc_read(codec, STA32X_MMUTE);
+	snd_soc_write(codec, STA32X_MMUTE, mute | STA32X_MMUTE_MMUTE);
+	sta32x_sync_coef_shadow(codec);
+	rc = snd_soc_cache_sync(codec);
+	snd_soc_write(codec, STA32X_MMUTE, mute);
+	return rc;
+}
+
 #define SINGLE_COEF(xname, index) \
 {	.iface = SNDRV_CTL_ELEM_IFACE_MIXER, .name = xname, \
 	.info = sta32x_coefficient_info, \
@@ -661,7 +711,7 @@ static int sta32x_set_bias_level(struct snd_soc_codec *codec,
 				return ret;
 			}
 
-			snd_soc_cache_sync(codec);
+			sta32x_cache_sync(codec);
 		}
 
 		/* Power up to mute */
@@ -790,6 +840,17 @@ static int sta32x_probe(struct snd_soc_codec *codec)
 			    STA32X_CxCFG_OM_MASK,
 			    2 << STA32X_CxCFG_OM_SHIFT);
 
+	/* initialize coefficient shadow RAM with reset values */
+	for (i = 4; i <= 49; i += 5)
+		sta32x->coef_shadow[i] = 0x400000;
+	for (i = 50; i <= 54; i++)
+		sta32x->coef_shadow[i] = 0x7fffff;
+	sta32x->coef_shadow[55] = 0x5a9df7;
+	sta32x->coef_shadow[56] = 0x7fffff;
+	sta32x->coef_shadow[59] = 0x7fffff;
+	sta32x->coef_shadow[60] = 0x400000;
+	sta32x->coef_shadow[61] = 0x400000;
+
 	sta32x_set_bias_level(codec, SND_SOC_BIAS_STANDBY);
 	/* Bias level configuration will have done an extra enable */
 	regulator_bulk_disable(ARRAY_SIZE(sta32x->supplies), sta32x->supplies);
diff --git a/sound/soc/codecs/sta32x.h b/sound/soc/codecs/sta32x.h
index b97ee5a..d8e32a6 100644
--- a/sound/soc/codecs/sta32x.h
+++ b/sound/soc/codecs/sta32x.h
@@ -19,6 +19,7 @@
 /* STA326 register addresses */
 
 #define STA32X_REGISTER_COUNT	0x2d
+#define STA32X_COEF_COUNT 62
 
 #define STA32X_CONFA	0x00
 #define STA32X_CONFB    0x01
diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c
index 7e5ec03..a7c9ae1 100644
--- a/sound/soc/codecs/wm8731.c
+++ b/sound/soc/codecs/wm8731.c
@@ -453,6 +453,7 @@ static int wm8731_set_bias_level(struct snd_soc_codec *codec,
 		snd_soc_write(codec, WM8731_PWR, 0xffff);
 		regulator_bulk_disable(ARRAY_SIZE(wm8731->supplies),
 				       wm8731->supplies);
+		codec->cache_sync = 1;
 		break;
 	}
 	codec->dapm.bias_level = level;
diff --git a/sound/soc/codecs/wm8753.c b/sound/soc/codecs/wm8753.c
index a950471..3a629d0 100644
--- a/sound/soc/codecs/wm8753.c
+++ b/sound/soc/codecs/wm8753.c
@@ -190,6 +190,9 @@ static int wm8753_set_dai(struct snd_kcontrol *kcontrol,
 	struct wm8753_priv *wm8753 = snd_soc_codec_get_drvdata(codec);
 	u16 ioctl;
 
+	if (wm8753->dai_func == ucontrol->value.integer.value[0])
+		return 0;
+
 	if (codec->active)
 		return -EBUSY;
 
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index 91d3c6d..53edd9a 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -1973,7 +1973,7 @@ static int wm8962_reset(struct snd_soc_codec *codec)
 static const DECLARE_TLV_DB_SCALE(inpga_tlv, -2325, 75, 0);
 static const DECLARE_TLV_DB_SCALE(mixin_tlv, -1500, 300, 0);
 static const unsigned int mixinpga_tlv[] = {
-	TLV_DB_RANGE_HEAD(7),
+	TLV_DB_RANGE_HEAD(5),
 	0, 1, TLV_DB_SCALE_ITEM(0, 600, 0),
 	2, 2, TLV_DB_SCALE_ITEM(1300, 1300, 0),
 	3, 4, TLV_DB_SCALE_ITEM(1800, 200, 0),
@@ -1988,7 +1988,7 @@ static const DECLARE_TLV_DB_SCALE(bypass_tlv, -1500, 300, 0);
 static const DECLARE_TLV_DB_SCALE(out_tlv, -12100, 100, 1);
 static const DECLARE_TLV_DB_SCALE(hp_tlv, -700, 100, 0);
 static const unsigned int classd_tlv[] = {
-	TLV_DB_RANGE_HEAD(7),
+	TLV_DB_RANGE_HEAD(2),
 	0, 6, TLV_DB_SCALE_ITEM(0, 150, 0),
 	7, 7, TLV_DB_SCALE_ITEM(1200, 0, 0),
 };
diff --git a/sound/soc/codecs/wm8993.c b/sound/soc/codecs/wm8993.c
index eec8e14..d1a142f4 100644
--- a/sound/soc/codecs/wm8993.c
+++ b/sound/soc/codecs/wm8993.c
@@ -512,7 +512,7 @@ static const DECLARE_TLV_DB_SCALE(drc_comp_threash, -4500, 75, 0);
 static const DECLARE_TLV_DB_SCALE(drc_comp_amp, -2250, 75, 0);
 static const DECLARE_TLV_DB_SCALE(drc_min_tlv, -1800, 600, 0);
 static const unsigned int drc_max_tlv[] = {
-	TLV_DB_RANGE_HEAD(4),
+	TLV_DB_RANGE_HEAD(2),
 	0, 2, TLV_DB_SCALE_ITEM(1200, 600, 0),
 	3, 3, TLV_DB_SCALE_ITEM(3600, 0, 0),
 };
diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index 9c982e4..6c29885 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -2357,6 +2357,11 @@ static int wm8994_hw_params(struct snd_pcm_substream *substream,
 	bclk |= best << WM8994_AIF1_BCLK_DIV_SHIFT;
 
 	lrclk = bclk_rate / params_rate(params);
+	if (!lrclk) {
+		dev_err(dai->dev, "Unable to generate LRCLK from %dHz BCLK\n",
+			bclk_rate);
+		return -EINVAL;
+	}
 	dev_dbg(dai->dev, "Using LRCLK rate %d for actual LRCLK %dHz\n",
 		lrclk, bclk_rate / lrclk);
 
@@ -3178,6 +3183,8 @@ static int wm8994_codec_probe(struct snd_soc_codec *codec)
 		switch (wm8994->revision) {
 		case 0:
 		case 1:
+		case 2:
+		case 3:
 			wm8994->hubs.dcs_codes_l = -9;
 			wm8994->hubs.dcs_codes_r = -5;
 			break;
diff --git a/sound/soc/codecs/wm9081.c b/sound/soc/codecs/wm9081.c
index 3cd35a0..4a398c3 100644
--- a/sound/soc/codecs/wm9081.c
+++ b/sound/soc/codecs/wm9081.c
@@ -807,7 +807,6 @@ static int wm9081_set_bias_level(struct snd_soc_codec *codec,
 			mdelay(100);
 
 			/* Normal bias enable & soft start off */
-			reg |= WM9081_BIAS_ENA;
 			reg &= ~WM9081_VMID_RAMP;
 			snd_soc_write(codec, WM9081_VMID_CONTROL, reg);
 
@@ -818,7 +817,7 @@ static int wm9081_set_bias_level(struct snd_soc_codec *codec,
 		}
 
 		/* VMID 2*240k */
-		reg = snd_soc_read(codec, WM9081_BIAS_CONTROL_1);
+		reg = snd_soc_read(codec, WM9081_VMID_CONTROL);
 		reg &= ~WM9081_VMID_SEL_MASK;
 		reg |= 0x04;
 		snd_soc_write(codec, WM9081_VMID_CONTROL, reg);
@@ -830,14 +829,15 @@ static int wm9081_set_bias_level(struct snd_soc_codec *codec,
 		break;
 
 	case SND_SOC_BIAS_OFF:
-		/* Startup bias source */
+		/* Startup bias source and disable bias */
 		reg = snd_soc_read(codec, WM9081_BIAS_CONTROL_1);
 		reg |= WM9081_BIAS_SRC;
+		reg &= ~WM9081_BIAS_ENA;
 		snd_soc_write(codec, WM9081_BIAS_CONTROL_1, reg);
 
-		/* Disable VMID and biases with soft ramping */
+		/* Disable VMID with soft ramping */
 		reg = snd_soc_read(codec, WM9081_VMID_CONTROL);
-		reg &= ~(WM9081_VMID_SEL_MASK | WM9081_BIAS_ENA);
+		reg &= ~WM9081_VMID_SEL_MASK;
 		reg |= WM9081_VMID_RAMP;
 		snd_soc_write(codec, WM9081_VMID_CONTROL, reg);
 
diff --git a/sound/soc/codecs/wm9090.c b/sound/soc/codecs/wm9090.c
index 2b5252c..f94c060 100644
--- a/sound/soc/codecs/wm9090.c
+++ b/sound/soc/codecs/wm9090.c
@@ -177,19 +177,19 @@ static void wait_for_dc_servo(struct snd_soc_codec *codec)
 }
 
 static const unsigned int in_tlv[] = {
-	TLV_DB_RANGE_HEAD(6),
+	TLV_DB_RANGE_HEAD(3),
 	0, 0, TLV_DB_SCALE_ITEM(-600, 0, 0),
 	1, 3, TLV_DB_SCALE_ITEM(-350, 350, 0),
 	4, 6, TLV_DB_SCALE_ITEM(600, 600, 0),
 };
 static const unsigned int mix_tlv[] = {
-	TLV_DB_RANGE_HEAD(4),
+	TLV_DB_RANGE_HEAD(2),
 	0, 2, TLV_DB_SCALE_ITEM(-1200, 300, 0),
 	3, 3, TLV_DB_SCALE_ITEM(0, 0, 0),
 };
 static const DECLARE_TLV_DB_SCALE(out_tlv, -5700, 100, 0);
 static const unsigned int spkboost_tlv[] = {
-	TLV_DB_RANGE_HEAD(7),
+	TLV_DB_RANGE_HEAD(2),
 	0, 6, TLV_DB_SCALE_ITEM(0, 150, 0),
 	7, 7, TLV_DB_SCALE_ITEM(1200, 0, 0),
 };
diff --git a/sound/soc/codecs/wm_hubs.c b/sound/soc/codecs/wm_hubs.c
index 84f33d4..48e61e9 100644
--- a/sound/soc/codecs/wm_hubs.c
+++ b/sound/soc/codecs/wm_hubs.c
@@ -40,7 +40,7 @@ static const DECLARE_TLV_DB_SCALE(outmix_tlv, -2100, 300, 0);
 static const DECLARE_TLV_DB_SCALE(spkmixout_tlv, -1800, 600, 1);
 static const DECLARE_TLV_DB_SCALE(outpga_tlv, -5700, 100, 0);
 static const unsigned int spkboost_tlv[] = {
-	TLV_DB_RANGE_HEAD(7),
+	TLV_DB_RANGE_HEAD(2),
 	0, 6, TLV_DB_SCALE_ITEM(0, 150, 0),
 	7, 7, TLV_DB_SCALE_ITEM(1200, 0, 0),
 };
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index 0268cf9..83c4bd5 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -694,6 +694,7 @@ static int __devinit fsl_ssi_probe(struct platform_device *pdev)
 
 	/* Initialize the the device_attribute structure */
 	dev_attr = &ssi_private->dev_attr;
+	sysfs_attr_init(&dev_attr->attr);
 	dev_attr->attr.name = "statistics";
 	dev_attr->attr.mode = S_IRUGO;
 	dev_attr->show = fsl_sysfs_ssi_show;
diff --git a/sound/soc/fsl/mpc8610_hpcd.c b/sound/soc/fsl/mpc8610_hpcd.c
index 31af405..ae49f1c 100644
--- a/sound/soc/fsl/mpc8610_hpcd.c
+++ b/sound/soc/fsl/mpc8610_hpcd.c
@@ -392,7 +392,8 @@ static int mpc8610_hpcd_probe(struct platform_device *pdev)
 	}
 
 	if (strcasecmp(sprop, "i2s-slave") == 0) {
-		machine_data->dai_format = SND_SOC_DAIFMT_I2S;
+		machine_data->dai_format =
+			SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBM_CFM;
 		machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
 		machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
 
@@ -409,31 +410,38 @@ static int mpc8610_hpcd_probe(struct platform_device *pdev)
 		}
 		machine_data->clk_frequency = be32_to_cpup(iprop);
 	} else if (strcasecmp(sprop, "i2s-master") == 0) {
-		machine_data->dai_format = SND_SOC_DAIFMT_I2S;
+		machine_data->dai_format =
+			SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_CBS_CFS;
 		machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
 		machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
 	} else if (strcasecmp(sprop, "lj-slave") == 0) {
-		machine_data->dai_format = SND_SOC_DAIFMT_LEFT_J;
+		machine_data->dai_format =
+			SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBM_CFM;
 		machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
 		machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
 	} else if (strcasecmp(sprop, "lj-master") == 0) {
-		machine_data->dai_format = SND_SOC_DAIFMT_LEFT_J;
+		machine_data->dai_format =
+			SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_CBS_CFS;
 		machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
 		machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
 	} else if (strcasecmp(sprop, "rj-slave") == 0) {
-		machine_data->dai_format = SND_SOC_DAIFMT_RIGHT_J;
+		machine_data->dai_format =
+			SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBM_CFM;
 		machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
 		machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
 	} else if (strcasecmp(sprop, "rj-master") == 0) {
-		machine_data->dai_format = SND_SOC_DAIFMT_RIGHT_J;
+		machine_data->dai_format =
+			SND_SOC_DAIFMT_RIGHT_J | SND_SOC_DAIFMT_CBS_CFS;
 		machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
 		machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
 	} else if (strcasecmp(sprop, "ac97-slave") == 0) {
-		machine_data->dai_format = SND_SOC_DAIFMT_AC97;
+		machine_data->dai_format =
+			SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBM_CFM;
 		machine_data->codec_clk_direction = SND_SOC_CLOCK_OUT;
 		machine_data->cpu_clk_direction = SND_SOC_CLOCK_IN;
 	} else if (strcasecmp(sprop, "ac97-master") == 0) {
-		machine_data->dai_format = SND_SOC_DAIFMT_AC97;
+		machine_data->dai_format =
+			SND_SOC_DAIFMT_AC97 | SND_SOC_DAIFMT_CBS_CFS;
 		machine_data->codec_clk_direction = SND_SOC_CLOCK_IN;
 		machine_data->cpu_clk_direction = SND_SOC_CLOCK_OUT;
 	} else {
diff --git a/sound/soc/nuc900/nuc900-ac97.c b/sound/soc/nuc900/nuc900-ac97.c
index 9c0edad..a4e3237 100644
--- a/sound/soc/nuc900/nuc900-ac97.c
+++ b/sound/soc/nuc900/nuc900-ac97.c
@@ -365,7 +365,8 @@ static int __devinit nuc900_ac97_drvprobe(struct platform_device *pdev)
 	if (ret)
 		goto out3;
 
-	mfp_set_groupg(nuc900_audio->dev); /* enbale ac97 multifunction pin*/
+	/* enbale ac97 multifunction pin */
+	mfp_set_groupg(nuc900_audio->dev, "nuc900-audio");
 
 	return 0;
 
diff --git a/sound/soc/samsung/smdk_wm8994.c b/sound/soc/samsung/smdk_wm8994.c
index f75e439..ad9ac42 100644
--- a/sound/soc/samsung/smdk_wm8994.c
+++ b/sound/soc/samsung/smdk_wm8994.c
@@ -9,6 +9,7 @@
 
 #include "../codecs/wm8994.h"
 #include <sound/pcm_params.h>
+#include <linux/module.h>
 
  /*
   * Default CFG switch settings to use this driver:
diff --git a/sound/soc/samsung/speyside.c b/sound/soc/samsung/speyside.c
index 85bf541..4b8e354 100644
--- a/sound/soc/samsung/speyside.c
+++ b/sound/soc/samsung/speyside.c
@@ -191,7 +191,7 @@ static int speyside_late_probe(struct snd_soc_card *card)
 	snd_soc_dapm_ignore_suspend(&card->dapm, "Headset Mic");
 	snd_soc_dapm_ignore_suspend(&card->dapm, "Main AMIC");
 	snd_soc_dapm_ignore_suspend(&card->dapm, "Main DMIC");
-	snd_soc_dapm_ignore_suspend(&card->dapm, "Speaker");
+	snd_soc_dapm_ignore_suspend(&card->dapm, "Main Speaker");
 	snd_soc_dapm_ignore_suspend(&card->dapm, "WM1250 Output");
 	snd_soc_dapm_ignore_suspend(&card->dapm, "WM1250 Input");
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index a5d3685..a25fa63 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -709,6 +709,12 @@ int snd_soc_resume(struct device *dev)
 	struct snd_soc_card *card = dev_get_drvdata(dev);
 	int i, ac97_control = 0;
 
+	/* If the initialization of this soc device failed, there is no codec
+	 * associated with it. Just bail out in this case.
+	 */
+	if (list_empty(&card->codec_dev_list))
+		return 0;
+
 	/* AC97 devices might have other drivers hanging off them so
 	 * need to resume immediately.  Other drivers don't have that
 	 * problem and may take a substantial amount of time to resume
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index b61945f..32d2a21 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -1633,6 +1633,37 @@ YAMAHA_DEVICE(0x7010, "UB99"),
 	}
 },
 {
+	/* Roland GAIA SH-01 */
+	USB_DEVICE(0x0582, 0x0111),
+	.driver_info = (unsigned long) &(const struct snd_usb_audio_quirk) {
+		.vendor_name = "Roland",
+		.product_name = "GAIA",
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = (const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 1,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 2,
+				.type = QUIRK_MIDI_FIXED_ENDPOINT,
+				.data = &(const struct snd_usb_midi_endpoint_info) {
+				.out_cables = 0x0003,
+				.in_cables  = 0x0003
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+{
 	USB_DEVICE(0x0582, 0x0113),
 	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
 		/* .vendor_name = "BOSS", */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index e426264..d7915d4 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -34,6 +34,16 @@ int __perf_evsel__sample_size(u64 sample_type)
 	return size;
 }
 
+static void hists__init(struct hists *hists)
+{
+	memset(hists, 0, sizeof(*hists));
+	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
+	hists->entries_in = &hists->entries_in_array[0];
+	hists->entries_collapsed = RB_ROOT;
+	hists->entries = RB_ROOT;
+	pthread_mutex_init(&hists->lock, NULL);
+}
+
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx)
 {
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index a36a3fa..abef270 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -1211,13 +1211,3 @@ size_t hists__fprintf_nr_events(struct hists *hists, FILE *fp)
 
 	return ret;
 }
-
-void hists__init(struct hists *hists)
-{
-	memset(hists, 0, sizeof(*hists));
-	hists->entries_in_array[0] = hists->entries_in_array[1] = RB_ROOT;
-	hists->entries_in = &hists->entries_in_array[0];
-	hists->entries_collapsed = RB_ROOT;
-	hists->entries = RB_ROOT;
-	pthread_mutex_init(&hists->lock, NULL);
-}
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index c86c1d2..89289c8 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -63,8 +63,6 @@ struct hists {
 	struct callchain_cursor	callchain_cursor;
 };
 
-void hists__init(struct hists *hists);
-
 struct hist_entry *__hists__add_entry(struct hists *self,
 				      struct addr_location *al,
 				      struct symbol *parent, u64 period);
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 85c1e6b7..0f4555c 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1333,6 +1333,10 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 	}
 
 	map = cpu_map__new(cpu_list);
+	if (map == NULL) {
+		pr_err("Invalid cpu_list\n");
+		return -1;
+	}
 
 	for (i = 0; i < map->nr; i++) {
 		int cpu = map->map[i];
diff --git a/tools/perf/util/trace-event-parse.c b/tools/perf/util/trace-event-parse.c
index 0a7ed5b..6c164dc 100644
--- a/tools/perf/util/trace-event-parse.c
+++ b/tools/perf/util/trace-event-parse.c
@@ -1537,6 +1537,8 @@ process_flags(struct event *event, struct print_arg *arg, char **tok)
 	field = malloc_or_die(sizeof(*field));
 
 	type = process_arg(event, field, &token);
+	while (type == EVENT_OP)
+		type = process_op(event, field, &token);
 	if (test_type_token(type, token, EVENT_DELIM, ","))
 		goto out_free;
 
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 30e2bef..8b4c253 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -747,6 +747,18 @@ sub __eval_option {
     # Add space to evaluate the character before $
     $option = " $option";
     my $retval = "";
+    my $repeated = 0;
+    my $parent = 0;
+
+    foreach my $test (keys %repeat_tests) {
+	if ($i >= $test &&
+	    $i < $test + $repeat_tests{$test}) {
+
+	    $repeated = 1;
+	    $parent = $test;
+	    last;
+	}
+    }
 
     while ($option =~ /(.*?[^\\])\$\{(.*?)\}(.*)/) {
 	my $start = $1;
@@ -760,10 +772,14 @@ sub __eval_option {
 	# otherwise see if the default OPT (without [$i]) exists.
 
 	my $o = "$var\[$i\]";
+	my $parento = "$var\[$parent\]";
 
 	if (defined($opt{$o})) {
 	    $o = $opt{$o};
 	    $retval = "$retval$o";
+	} elsif ($repeated && defined($opt{$parento})) {
+	    $o = $opt{$parento};
+	    $retval = "$retval$o";
 	} elsif (defined($opt{$var})) {
 	    $o = $opt{$var};
 	    $retval = "$retval$o";