diff options
422 files changed, 6473 insertions, 3699 deletions
diff --git a/Documentation/DocBook/debugobjects.tmpl b/Documentation/DocBook/debugobjects.tmpl index 08ff908..24979f6 100644 --- a/Documentation/DocBook/debugobjects.tmpl +++ b/Documentation/DocBook/debugobjects.tmpl @@ -96,6 +96,7 @@ <listitem><para>debug_object_deactivate</para></listitem> <listitem><para>debug_object_destroy</para></listitem> <listitem><para>debug_object_free</para></listitem> + <listitem><para>debug_object_assert_init</para></listitem> </itemizedlist> Each of these functions takes the address of the real object and a pointer to the object type specific debug description @@ -273,6 +274,26 @@ debug checks. </para> </sect1> + + <sect1 id="debug_object_assert_init"> + <title>debug_object_assert_init</title> + <para> + This function is called to assert that an object has been + initialized. + </para> + <para> + When the real object is not tracked by debugobjects, it calls + fixup_assert_init of the object type description structure + provided by the caller, with the hardcoded object state + ODEBUG_NOT_AVAILABLE. The fixup function can correct the problem + by calling debug_object_init and other specific initializing + functions. + </para> + <para> + When the real object is already tracked by debugobjects it is + ignored. + </para> + </sect1> </chapter> <chapter id="fixupfunctions"> <title>Fixup functions</title> @@ -381,6 +402,35 @@ statistics. </para> </sect1> + <sect1 id="fixup_assert_init"> + <title>fixup_assert_init</title> + <para> + This function is called from the debug code whenever a problem + in debug_object_assert_init is detected. + </para> + <para> + Called from debug_object_assert_init() with a hardcoded state + ODEBUG_STATE_NOTAVAILABLE when the object is not found in the + debug bucket. + </para> + <para> + The function returns 1 when the fixup was successful, + otherwise 0. The return value is used to update the + statistics. + </para> + <para> + Note, this function should make sure debug_object_init() is + called before returning. + </para> + <para> + The handling of statically initialized objects is a special + case. The fixup function should check if this is a legitimate + case of a statically initialized object or not. In this case only + debug_object_init() should be called to make the object known to + the tracker. Then the function should return 0 because this is not + a real fixup. + </para> + </sect1> </chapter> <chapter id="bugs"> <title>Known Bugs And Assumptions</title> diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt index 0c134f8..bff2d8b 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.txt @@ -328,6 +328,12 @@ over a rather long period of time, but improvements are always welcome! RCU rather than SRCU, because RCU is almost always faster and easier to use than is SRCU. + If you need to enter your read-side critical section in a + hardirq or exception handler, and then exit that same read-side + critical section in the task that was interrupted, then you need + to srcu_read_lock_raw() and srcu_read_unlock_raw(), which avoid + the lockdep checking that would otherwise this practice illegal. + Also unlike other forms of RCU, explicit initialization and cleanup is required via init_srcu_struct() and cleanup_srcu_struct(). These are passed a "struct srcu_struct" diff --git a/Documentation/RCU/rcu.txt b/Documentation/RCU/rcu.txt index 3185270..bf77833 100644 --- a/Documentation/RCU/rcu.txt +++ b/Documentation/RCU/rcu.txt @@ -38,11 +38,11 @@ o How can the updater tell when a grace period has completed Preemptible variants of RCU (CONFIG_TREE_PREEMPT_RCU) get the same effect, but require that the readers manipulate CPU-local - counters. These counters allow limited types of blocking - within RCU read-side critical sections. SRCU also uses - CPU-local counters, and permits general blocking within - RCU read-side critical sections. These two variants of - RCU detect grace periods by sampling these counters. + counters. These counters allow limited types of blocking within + RCU read-side critical sections. SRCU also uses CPU-local + counters, and permits general blocking within RCU read-side + critical sections. These variants of RCU detect grace periods + by sampling these counters. o If I am running on a uniprocessor kernel, which can only do one thing at a time, why should I wait for a grace period? diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt index 4e95920..083d88c 100644 --- a/Documentation/RCU/stallwarn.txt +++ b/Documentation/RCU/stallwarn.txt @@ -101,6 +101,11 @@ o A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that CONFIG_TREE_PREEMPT_RCU case, you might see stall-warning messages. +o A hardware or software issue shuts off the scheduler-clock + interrupt on a CPU that is not in dyntick-idle mode. This + problem really has happened, and seems to be most likely to + result in RCU CPU stall warnings for CONFIG_NO_HZ=n kernels. + o A bug in the RCU implementation. o A hardware failure. This is quite unlikely, but has occurred @@ -109,12 +114,11 @@ o A hardware failure. This is quite unlikely, but has occurred This resulted in a series of RCU CPU stall warnings, eventually leading the realization that the CPU had failed. -The RCU, RCU-sched, and RCU-bh implementations have CPU stall -warning. SRCU does not have its own CPU stall warnings, but its -calls to synchronize_sched() will result in RCU-sched detecting -RCU-sched-related CPU stalls. Please note that RCU only detects -CPU stalls when there is a grace period in progress. No grace period, -no CPU stall warnings. +The RCU, RCU-sched, and RCU-bh implementations have CPU stall warning. +SRCU does not have its own CPU stall warnings, but its calls to +synchronize_sched() will result in RCU-sched detecting RCU-sched-related +CPU stalls. Please note that RCU only detects CPU stalls when there is +a grace period in progress. No grace period, no CPU stall warnings. To diagnose the cause of the stall, inspect the stack traces. The offending function will usually be near the top of the stack. diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt index 783d6c1..d67068d 100644 --- a/Documentation/RCU/torture.txt +++ b/Documentation/RCU/torture.txt @@ -61,11 +61,24 @@ nreaders This is the number of RCU reading threads supported. To properly exercise RCU implementations with preemptible read-side critical sections. +onoff_interval + The number of seconds between each attempt to execute a + randomly selected CPU-hotplug operation. Defaults to + zero, which disables CPU hotplugging. In HOTPLUG_CPU=n + kernels, rcutorture will silently refuse to do any + CPU-hotplug operations regardless of what value is + specified for onoff_interval. + shuffle_interval The number of seconds to keep the test threads affinitied to a particular subset of the CPUs, defaults to 3 seconds. Used in conjunction with test_no_idle_hz. +shutdown_secs The number of seconds to run the test before terminating + the test and powering off the system. The default is + zero, which disables test termination and system shutdown. + This capability is useful for automated testing. + stat_interval The number of seconds between output of torture statistics (via printk()). Regardless of the interval, statistics are printed when the module is unloaded. diff --git a/Documentation/RCU/trace.txt b/Documentation/RCU/trace.txt index aaf65f6..49587ab 100644 --- a/Documentation/RCU/trace.txt +++ b/Documentation/RCU/trace.txt @@ -105,14 +105,10 @@ o "dt" is the current value of the dyntick counter that is incremented or one greater than the interrupt-nesting depth otherwise. The number after the second "/" is the NMI nesting depth. - This field is displayed only for CONFIG_NO_HZ kernels. - o "df" is the number of times that some other CPU has forced a quiescent state on behalf of this CPU due to this CPU being in dynticks-idle state. - This field is displayed only for CONFIG_NO_HZ kernels. - o "of" is the number of times that some other CPU has forced a quiescent state on behalf of this CPU due to this CPU being offline. In a perfect world, this might never happen, but it diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt index 6ef6926..6bbe8dc 100644 --- a/Documentation/RCU/whatisRCU.txt +++ b/Documentation/RCU/whatisRCU.txt @@ -4,6 +4,7 @@ to start learning about RCU: 1. What is RCU, Fundamentally? http://lwn.net/Articles/262464/ 2. What is RCU? Part 2: Usage http://lwn.net/Articles/263130/ 3. RCU part 3: the RCU API http://lwn.net/Articles/264090/ +4. The RCU API, 2010 Edition http://lwn.net/Articles/418853/ What is RCU? @@ -834,6 +835,8 @@ SRCU: Critical sections Grace period Barrier srcu_read_lock synchronize_srcu N/A srcu_read_unlock synchronize_srcu_expedited + srcu_read_lock_raw + srcu_read_unlock_raw srcu_dereference SRCU: Initialization/cleanup @@ -855,27 +858,33 @@ list can be helpful: a. Will readers need to block? If so, you need SRCU. -b. What about the -rt patchset? If readers would need to block +b. Is it necessary to start a read-side critical section in a + hardirq handler or exception handler, and then to complete + this read-side critical section in the task that was + interrupted? If so, you need SRCU's srcu_read_lock_raw() and + srcu_read_unlock_raw() primitives. + +c. What about the -rt patchset? If readers would need to block in an non-rt kernel, you need SRCU. If readers would block in a -rt kernel, but not in a non-rt kernel, SRCU is not necessary. -c. Do you need to treat NMI handlers, hardirq handlers, +d. Do you need to treat NMI handlers, hardirq handlers, and code segments with preemption disabled (whether via preempt_disable(), local_irq_save(), local_bh_disable(), or some other mechanism) as if they were explicit RCU readers? If so, you need RCU-sched. -d. Do you need RCU grace periods to complete even in the face +e. Do you need RCU grace periods to complete even in the face of softirq monopolization of one or more of the CPUs? For example, is your code subject to network-based denial-of-service attacks? If so, you need RCU-bh. -e. Is your workload too update-intensive for normal use of +f. Is your workload too update-intensive for normal use of RCU, but inappropriate for other synchronization mechanisms? If so, consider SLAB_DESTROY_BY_RCU. But please be careful! -f. Otherwise, use RCU. +g. Otherwise, use RCU. Of course, this all assumes that you have determined that RCU is in fact the right tool for your job. diff --git a/Documentation/atomic_ops.txt b/Documentation/atomic_ops.txt index 3bd585b..27f2b21 100644 --- a/Documentation/atomic_ops.txt +++ b/Documentation/atomic_ops.txt @@ -84,6 +84,93 @@ compiler optimizes the section accessing atomic_t variables. *** YOU HAVE BEEN WARNED! *** +Properly aligned pointers, longs, ints, and chars (and unsigned +equivalents) may be atomically loaded from and stored to in the same +sense as described for atomic_read() and atomic_set(). The ACCESS_ONCE() +macro should be used to prevent the compiler from using optimizations +that might otherwise optimize accesses out of existence on the one hand, +or that might create unsolicited accesses on the other. + +For example consider the following code: + + while (a > 0) + do_something(); + +If the compiler can prove that do_something() does not store to the +variable a, then the compiler is within its rights transforming this to +the following: + + tmp = a; + if (a > 0) + for (;;) + do_something(); + +If you don't want the compiler to do this (and you probably don't), then +you should use something like the following: + + while (ACCESS_ONCE(a) < 0) + do_something(); + +Alternatively, you could place a barrier() call in the loop. + +For another example, consider the following code: + + tmp_a = a; + do_something_with(tmp_a); + do_something_else_with(tmp_a); + +If the compiler can prove that do_something_with() does not store to the +variable a, then the compiler is within its rights to manufacture an +additional load as follows: + + tmp_a = a; + do_something_with(tmp_a); + tmp_a = a; + do_something_else_with(tmp_a); + +This could fatally confuse your code if it expected the same value +to be passed to do_something_with() and do_something_else_with(). + +The compiler would be likely to manufacture this additional load if +do_something_with() was an inline function that made very heavy use +of registers: reloading from variable a could save a flush to the +stack and later reload. To prevent the compiler from attacking your +code in this manner, write the following: + + tmp_a = ACCESS_ONCE(a); + do_something_with(tmp_a); + do_something_else_with(tmp_a); + +For a final example, consider the following code, assuming that the +variable a is set at boot time before the second CPU is brought online +and never changed later, so that memory barriers are not needed: + + if (a) + b = 9; + else + b = 42; + +The compiler is within its rights to manufacture an additional store +by transforming the above code into the following: + + b = 42; + if (a) + b = 9; + +This could come as a fatal surprise to other code running concurrently +that expected b to never have the value 42 if a was zero. To prevent +the compiler from doing this, write something like: + + if (a) + ACCESS_ONCE(b) = 9; + else + ACCESS_ONCE(b) = 42; + +Don't even -think- about doing this without proper use of memory barriers, +locks, or atomic operations if variable a can change at runtime! + +*** WARNING: ACCESS_ONCE() DOES NOT IMPLY A BARRIER! *** + Now, we move onto the atomic operation interfaces typically implemented with the help of assembly code. diff --git a/Documentation/lockdep-design.txt b/Documentation/lockdep-design.txt index abf768c..5dbc99c 100644 --- a/Documentation/lockdep-design.txt +++ b/Documentation/lockdep-design.txt @@ -221,3 +221,66 @@ when the chain is validated for the first time, is then put into a hash table, which hash-table can be checked in a lockfree manner. If the locking chain occurs again later on, the hash table tells us that we dont have to validate the chain again. + +Troubleshooting: +---------------- + +The validator tracks a maximum of MAX_LOCKDEP_KEYS number of lock classes. +Exceeding this number will trigger the following lockdep warning: + + (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) + +By default, MAX_LOCKDEP_KEYS is currently set to 8191, and typical +desktop systems have less than 1,000 lock classes, so this warning +normally results from lock-class leakage or failure to properly +initialize locks. These two problems are illustrated below: + +1. Repeated module loading and unloading while running the validator + will result in lock-class leakage. The issue here is that each + load of the module will create a new set of lock classes for + that module's locks, but module unloading does not remove old + classes (see below discussion of reuse of lock classes for why). + Therefore, if that module is loaded and unloaded repeatedly, + the number of lock classes will eventually reach the maximum. + +2. Using structures such as arrays that have large numbers of + locks that are not explicitly initialized. For example, + a hash table with 8192 buckets where each bucket has its own + spinlock_t will consume 8192 lock classes -unless- each spinlock + is explicitly initialized at runtime, for example, using the + run-time spin_lock_init() as opposed to compile-time initializers + such as __SPIN_LOCK_UNLOCKED(). Failure to properly initialize + the per-bucket spinlocks would guarantee lock-class overflow. + In contrast, a loop that called spin_lock_init() on each lock + would place all 8192 locks into a single lock class. + + The moral of this story is that you should always explicitly + initialize your locks. + +One might argue that the validator should be modified to allow +lock classes to be reused. However, if you are tempted to make this +argument, first review the code and think through the changes that would +be required, keeping in mind that the lock classes to be removed are +likely to be linked into the lock-dependency graph. This turns out to +be harder to do than to say. + +Of course, if you do run out of lock classes, the next thing to do is +to find the offending lock classes. First, the following command gives +you the number of lock classes currently in use along with the maximum: + + grep "lock-classes" /proc/lockdep_stats + +This command produces the following output on a modest system: + + lock-classes: 748 [max: 8191] + +If the number allocated (748 above) increases continually over time, +then there is likely a leak. The following command can be used to +identify the leaking lock classes: + + grep "BD" /proc/lockdep + +Run the command and save the output, then compare against the output from +a later run of this command to identify the leakers. This same output +can also help you find situations where runtime lock initialization has +been omitted. diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 7945b0b..e2a4b52 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1100,6 +1100,15 @@ emulate them efficiently. The fields in each entry are defined as follows: eax, ebx, ecx, edx: the values returned by the cpuid instruction for this function/index combination +The TSC deadline timer feature (CPUID leaf 1, ecx[24]) is always returned +as false, since the feature depends on KVM_CREATE_IRQCHIP for local APIC +support. Instead it is reported via + + ioctl(KVM_CHECK_EXTENSION, KVM_CAP_TSC_DEADLINE_TIMER) + +if that returns true and you use KVM_CREATE_IRQCHIP, or if you emulate the +feature in userspace, then you can enable the feature for KVM_SET_CPUID2. + 4.47 KVM_PPC_GET_PVINFO Capability: KVM_CAP_PPC_GET_PVINFO @@ -1151,6 +1160,13 @@ following flags are specified: /* Depends on KVM_CAP_IOMMU */ #define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0) +The KVM_DEV_ASSIGN_ENABLE_IOMMU flag is a mandatory option to ensure +isolation of the device. Usages not specifying this flag are deprecated. + +Only PCI header type 0 devices with PCI BAR resources are supported by +device assignment. The user requesting this ioctl must have read/write +access to the PCI sysfs resource files associated with the device. + 4.49 KVM_DEASSIGN_PCI_DEVICE Capability: KVM_CAP_DEVICE_DEASSIGNMENT diff --git a/MAINTAINERS b/MAINTAINERS index b9db108..62f1cd3 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1698,11 +1698,9 @@ F: arch/x86/include/asm/tce.h CAN NETWORK LAYER M: Oliver Hartkopp <socketcan@hartkopp.net> -M: Oliver Hartkopp <oliver.hartkopp@volkswagen.de> -M: Urs Thuermann <urs.thuermann@volkswagen.de> L: linux-can@vger.kernel.org -L: netdev@vger.kernel.org -W: http://developer.berlios.de/projects/socketcan/ +W: http://gitorious.org/linux-can +T: git git://gitorious.org/linux-can/linux-can-next.git S: Maintained F: net/can/ F: include/linux/can.h @@ -1713,9 +1711,10 @@ F: include/linux/can/gw.h CAN NETWORK DRIVERS M: Wolfgang Grandegger <wg@grandegger.com> +M: Marc Kleine-Budde <mkl@pengutronix.de> L: linux-can@vger.kernel.org -L: netdev@vger.kernel.org -W: http://developer.berlios.de/projects/socketcan/ +W: http://gitorious.org/linux-can +T: git git://gitorious.org/linux-can/linux-can-next.git S: Maintained F: drivers/net/can/ F: include/linux/can/dev.h @@ -2700,7 +2699,7 @@ FIREWIRE SUBSYSTEM M: Stefan Richter <stefanr@s5r6.in-berlin.de> L: linux1394-devel@lists.sourceforge.net W: http://ieee1394.wiki.kernel.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394/linux1394-2.6.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394/linux1394.git S: Maintained F: drivers/firewire/ F: include/linux/firewire*.h @@ -3101,6 +3100,7 @@ F: include/linux/hid* HIGH-RESOLUTION TIMERS, CLOCKEVENTS, DYNTICKS M: Thomas Gleixner <tglx@linutronix.de> +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core S: Maintained F: Documentation/timers/ F: kernel/hrtimer.c @@ -3610,7 +3610,7 @@ F: net/irda/ IRQ SUBSYSTEM M: Thomas Gleixner <tglx@linutronix.de> S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git irq/core +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core F: kernel/irq/ ISAPNP @@ -4098,7 +4098,7 @@ F: drivers/hwmon/lm90.c LOCKDEP AND LOCKSTAT M: Peter Zijlstra <peterz@infradead.org> M: Ingo Molnar <mingo@redhat.com> -T: git git://git.kernel.org/pub/scm/linux/kernel/git/peterz/linux-2.6-lockdep.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core/locking S: Maintained F: Documentation/lockdep*.txt F: Documentation/lockstat.txt @@ -4280,7 +4280,9 @@ T: git git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-2.6.git S: Maintained F: Documentation/dvb/ F: Documentation/video4linux/ +F: Documentation/DocBook/media/ F: drivers/media/ +F: drivers/staging/media/ F: include/media/ F: include/linux/dvb/ F: include/linux/videodev*.h @@ -5086,6 +5088,7 @@ M: Peter Zijlstra <a.p.zijlstra@chello.nl> M: Paul Mackerras <paulus@samba.org> M: Ingo Molnar <mingo@elte.hu> M: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core S: Supported F: kernel/events/* F: include/linux/perf_event.h @@ -5165,6 +5168,7 @@ F: drivers/scsi/pm8001/ POSIX CLOCKS and TIMERS M: Thomas Gleixner <tglx@linutronix.de> +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core S: Supported F: fs/timerfd.c F: include/linux/timer* @@ -5680,6 +5684,7 @@ F: drivers/dma/dw_dmac.c TIMEKEEPING, NTP M: John Stultz <johnstul@us.ibm.com> M: Thomas Gleixner <tglx@linutronix.de> +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git timers/core S: Supported F: include/linux/clocksource.h F: include/linux/time.h @@ -5704,6 +5709,7 @@ F: drivers/watchdog/sc1200wdt.c SCHEDULER M: Ingo Molnar <mingo@elte.hu> M: Peter Zijlstra <peterz@infradead.org> +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched/core S: Maintained F: kernel/sched* F: include/linux/sched.h @@ -6631,7 +6637,7 @@ TRACING M: Steven Rostedt <rostedt@goodmis.org> M: Frederic Weisbecker <fweisbec@gmail.com> M: Ingo Molnar <mingo@redhat.com> -T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf/core +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git perf/core S: Maintained F: Documentation/trace/ftrace.txt F: arch/*/*/*/ftrace.h @@ -7381,7 +7387,7 @@ M: Thomas Gleixner <tglx@linutronix.de> M: Ingo Molnar <mingo@redhat.com> M: "H. Peter Anvin" <hpa@zytor.com> M: x86@kernel.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/x86/linux-2.6-x86.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/core S: Maintained F: Documentation/x86/ F: arch/x86/ @@ -1,7 +1,7 @@ VERSION = 3 PATCHLEVEL = 2 SUBLEVEL = 0 -EXTRAVERSION = -rc6 +EXTRAVERSION = NAME = Saber-toothed Squirrel # *DOCUMENTATION* diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 776d76b..b259c7c 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1246,7 +1246,7 @@ config PL310_ERRATA_588369 config ARM_ERRATA_720789 bool "ARM errata: TLBIASIDIS and TLBIMVAIS operations can broadcast a faulty ASID" - depends on CPU_V7 && SMP + depends on CPU_V7 help This option enables the workaround for the 720789 Cortex-A9 (prior to r2p0) erratum. A faulty ASID can be sent to the other CPUs for the @@ -1282,7 +1282,7 @@ config ARM_ERRATA_743622 config ARM_ERRATA_751472 bool "ARM errata: Interrupted ICIALLUIS may prevent completion of broadcasted operation" - depends on CPU_V7 && SMP + depends on CPU_V7 help This option enables the workaround for the 751472 Cortex-A9 (prior to r3p0) erratum. An interrupted ICIALLUIS operation may prevent the diff --git a/arch/arm/common/pl330.c b/arch/arm/common/pl330.c index f407a6b..8d8df74 100644 --- a/arch/arm/common/pl330.c +++ b/arch/arm/common/pl330.c @@ -221,17 +221,6 @@ */ #define MCODE_BUFF_PER_REQ 256 -/* - * Mark a _pl330_req as free. - * We do it by writing DMAEND as the first instruction - * because no valid request is going to have DMAEND as - * its first instruction to execute. - */ -#define MARK_FREE(req) do { \ - _emit_END(0, (req)->mc_cpu); \ - (req)->mc_len = 0; \ - } while (0) - /* If the _pl330_req is available to the client */ #define IS_FREE(req) (*((u8 *)((req)->mc_cpu)) == CMD_DMAEND) @@ -301,8 +290,10 @@ struct pl330_thread { struct pl330_dmac *dmac; /* Only two at a time */ struct _pl330_req req[2]; - /* Index of the last submitted request */ + /* Index of the last enqueued request */ unsigned lstenq; + /* Index of the last submitted request or -1 if the DMA is stopped */ + int req_running; }; enum pl330_dmac_state { @@ -778,6 +769,22 @@ static inline void _execute_DBGINSN(struct pl330_thread *thrd, writel(0, regs + DBGCMD); } +/* + * Mark a _pl330_req as free. + * We do it by writing DMAEND as the first instruction + * because no valid request is going to have DMAEND as + * its first instruction to execute. + */ +static void mark_free(struct pl330_thread *thrd, int idx) +{ + struct _pl330_req *req = &thrd->req[idx]; + + _emit_END(0, req->mc_cpu); + req->mc_len = 0; + + thrd->req_running = -1; +} + static inline u32 _state(struct pl330_thread *thrd) { void __iomem *regs = thrd->dmac->pinfo->base; @@ -836,31 +843,6 @@ static inline u32 _state(struct pl330_thread *thrd) } } -/* If the request 'req' of thread 'thrd' is currently active */ -static inline bool _req_active(struct pl330_thread *thrd, - struct _pl330_req *req) -{ - void __iomem *regs = thrd->dmac->pinfo->base; - u32 buf = req->mc_bus, pc = readl(regs + CPC(thrd->id)); - - if (IS_FREE(req)) - return false; - - return (pc >= buf && pc <= buf + req->mc_len) ? true : false; -} - -/* Returns 0 if the thread is inactive, ID of active req + 1 otherwise */ -static inline unsigned _thrd_active(struct pl330_thread *thrd) -{ - if (_req_active(thrd, &thrd->req[0])) - return 1; /* First req active */ - - if (_req_active(thrd, &thrd->req[1])) - return 2; /* Second req active */ - - return 0; -} - static void _stop(struct pl330_thread *thrd) { void __iomem *regs = thrd->dmac->pinfo->base; @@ -892,17 +874,22 @@ static bool _trigger(struct pl330_thread *thrd) struct _arg_GO go; unsigned ns; u8 insn[6] = {0, 0, 0, 0, 0, 0}; + int idx; /* Return if already ACTIVE */ if (_state(thrd) != PL330_STATE_STOPPED) return true; - if (!IS_FREE(&thrd->req[1 - thrd->lstenq])) - req = &thrd->req[1 - thrd->lstenq]; - else if (!IS_FREE(&thrd->req[thrd->lstenq])) - req = &thrd->req[thrd->lstenq]; - else - req = NULL; + idx = 1 - thrd->lstenq; + if (!IS_FREE(&thrd->req[idx])) + req = &thrd->req[idx]; + else { + idx = thrd->lstenq; + if (!IS_FREE(&thrd->req[idx])) + req = &thrd->req[idx]; + else + req = NULL; + } /* Return if no request */ if (!req || !req->r) @@ -933,6 +920,8 @@ static bool _trigger(struct pl330_thread *thrd) /* Only manager can execute GO */ _execute_DBGINSN(thrd, insn, true); + thrd->req_running = idx; + return true; } @@ -1382,8 +1371,8 @@ static void pl330_dotask(unsigned long data) thrd->req[0].r = NULL; thrd->req[1].r = NULL; - MARK_FREE(&thrd->req[0]); - MARK_FREE(&thrd->req[1]); + mark_free(thrd, 0); + mark_free(thrd, 1); /* Clear the reset flag */ pl330->dmac_tbd.reset_chan &= ~(1 << i); @@ -1461,14 +1450,12 @@ int pl330_update(const struct pl330_info *pi) thrd = &pl330->channels[id]; - active = _thrd_active(thrd); - if (!active) /* Aborted */ + active = thrd->req_running; + if (active == -1) /* Aborted */ continue; - active -= 1; - rqdone = &thrd->req[active]; - MARK_FREE(rqdone); + mark_free(thrd, active); /* Get going again ASAP */ _start(thrd); @@ -1509,7 +1496,7 @@ int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op) struct pl330_thread *thrd = ch_id; struct pl330_dmac *pl330; unsigned long flags; - int ret = 0, active; + int ret = 0, active = thrd->req_running; if (!thrd || thrd->free || thrd->dmac->state == DYING) return -EINVAL; @@ -1525,28 +1512,24 @@ int pl330_chan_ctrl(void *ch_id, enum pl330_chan_op op) thrd->req[0].r = NULL; thrd->req[1].r = NULL; - MARK_FREE(&thrd->req[0]); - MARK_FREE(&thrd->req[1]); + mark_free(thrd, 0); + mark_free(thrd, 1); break; case PL330_OP_ABORT: - active = _thrd_active(thrd); - /* Make sure the channel is stopped */ _stop(thrd); /* ABORT is only for the active req */ - if (!active) + if (active == -1) break; - active--; - thrd->req[active].r = NULL; - MARK_FREE(&thrd->req[active]); + mark_free(thrd, active); /* Start the next */ case PL330_OP_START: - if (!_thrd_active(thrd) && !_start(thrd)) + if ((active == -1) && !_start(thrd)) ret = -EIO; break; @@ -1587,14 +1570,13 @@ int pl330_chan_status(void *ch_id, struct pl330_chanstatus *pstatus) else pstatus->faulting = false; - active = _thrd_active(thrd); + active = thrd->req_running; - if (!active) { + if (active == -1) { /* Indicate that the thread is not running */ pstatus->top_req = NULL; pstatus->wait_req = NULL; } else { - active--; pstatus->top_req = thrd->req[active].r; pstatus->wait_req = !IS_FREE(&thrd->req[1 - active]) ? thrd->req[1 - active].r : NULL; @@ -1659,9 +1641,9 @@ void *pl330_request_channel(const struct pl330_info *pi) thrd->free = false; thrd->lstenq = 1; thrd->req[0].r = NULL; - MARK_FREE(&thrd->req[0]); + mark_free(thrd, 0); thrd->req[1].r = NULL; - MARK_FREE(&thrd->req[1]); + mark_free(thrd, 1); break; } } @@ -1767,14 +1749,14 @@ static inline void _reset_thread(struct pl330_thread *thrd) thrd->req[0].mc_bus = pl330->mcode_bus + (thrd->id * pi->mcbufsz); thrd->req[0].r = NULL; - MARK_FREE(&thrd->req[0]); + mark_free(thrd, 0); thrd->req[1].mc_cpu = thrd->req[0].mc_cpu + pi->mcbufsz / 2; thrd->req[1].mc_bus = thrd->req[0].mc_bus + pi->mcbufsz / 2; thrd->req[1].r = NULL; - MARK_FREE(&thrd->req[1]); + mark_free(thrd, 1); } static int dmac_alloc_threads(struct pl330_dmac *pl330) diff --git a/arch/arm/configs/imx_v4_v5_defconfig b/arch/arm/configs/imx_v4_v5_defconfig index 11a4192..cf497ce 100644 --- a/arch/arm/configs/imx_v4_v5_defconfig +++ b/arch/arm/configs/imx_v4_v5_defconfig @@ -18,9 +18,10 @@ CONFIG_ARCH_MXC=y CONFIG_ARCH_IMX_V4_V5=y CONFIG_ARCH_MX1ADS=y CONFIG_MACH_SCB9328=y +CONFIG_MACH_APF9328=y CONFIG_MACH_MX21ADS=y CONFIG_MACH_MX25_3DS=y -CONFIG_MACH_EUKREA_CPUIMX25=y +CONFIG_MACH_EUKREA_CPUIMX25SD=y CONFIG_MACH_MX27ADS=y CONFIG_MACH_PCM038=y CONFIG_MACH_CPUIMX27=y @@ -72,17 +73,16 @@ CONFIG_MTD_CFI_GEOMETRY=y CONFIG_MTD_CFI_INTELEXT=y CONFIG_MTD_PHYSMAP=y CONFIG_MTD_NAND=y +CONFIG_MTD_NAND_MXC=y CONFIG_MTD_UBI=y CONFIG_MISC_DEVICES=y CONFIG_EEPROM_AT24=y CONFIG_EEPROM_AT25=y CONFIG_NETDEVICES=y -CONFIG_NET_ETHERNET=y -CONFIG_SMC91X=y CONFIG_DM9000=y +CONFIG_SMC91X=y CONFIG_SMC911X=y -# CONFIG_NETDEV_1000 is not set -# CONFIG_NETDEV_10000 is not set +CONFIG_SMSC_PHY=y # CONFIG_INPUT_MOUSEDEV is not set CONFIG_INPUT_EVDEV=y # CONFIG_INPUT_KEYBOARD is not set @@ -100,6 +100,7 @@ CONFIG_I2C_CHARDEV=y CONFIG_I2C_IMX=y CONFIG_SPI=y CONFIG_SPI_IMX=y +CONFIG_SPI_SPIDEV=y CONFIG_W1=y CONFIG_W1_MASTER_MXC=y CONFIG_W1_SLAVE_THERM=y @@ -139,6 +140,7 @@ CONFIG_MMC=y CONFIG_MMC_MXC=y CONFIG_NEW_LEDS=y CONFIG_LEDS_CLASS=y +CONFIG_LEDS_GPIO=y CONFIG_LEDS_MC13783=y CONFIG_LEDS_TRIGGERS=y CONFIG_LEDS_TRIGGER_TIMER=y diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c index 3d0c6fb..e8e8fe5 100644 --- a/arch/arm/kernel/process.c +++ b/arch/arm/kernel/process.c @@ -183,7 +183,8 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + rcu_idle_enter(); leds_event(led_idle_start); while (!need_resched()) { #ifdef CONFIG_HOTPLUG_CPU @@ -213,7 +214,8 @@ void cpu_idle(void) } } leds_event(led_idle_end); - tick_nohz_restart_sched_tick(); + rcu_idle_exit(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); schedule(); preempt_disable(); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 8fc2c8f..c0b59bf 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -52,6 +52,7 @@ #include <asm/mach/time.h> #include <asm/traps.h> #include <asm/unwind.h> +#include <asm/memblock.h> #if defined(CONFIG_DEPRECATED_PARAM_STRUCT) #include "compat.h" diff --git a/arch/arm/mach-exynos/cpu.c b/arch/arm/mach-exynos/cpu.c index 90ec247..cc8d4bd 100644 --- a/arch/arm/mach-exynos/cpu.c +++ b/arch/arm/mach-exynos/cpu.c @@ -111,11 +111,6 @@ static struct map_desc exynos4_iodesc[] __initdata = { .length = SZ_4K, .type = MT_DEVICE, }, { - .virtual = (unsigned long)S5P_VA_SROMC, - .pfn = __phys_to_pfn(EXYNOS4_PA_SROMC), - .length = SZ_4K, - .type = MT_DEVICE, - }, { .virtual = (unsigned long)S3C_VA_USB_HSPHY, .pfn = __phys_to_pfn(EXYNOS4_PA_HSPHY), .length = SZ_4K, diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig index c44aa97..0e6f1af 100644 --- a/arch/arm/mach-imx/Kconfig +++ b/arch/arm/mach-imx/Kconfig @@ -132,7 +132,7 @@ config MACH_MX25_3DS select IMX_HAVE_PLATFORM_MXC_NAND select IMX_HAVE_PLATFORM_SDHCI_ESDHC_IMX -config MACH_EUKREA_CPUIMX25 +config MACH_EUKREA_CPUIMX25SD bool "Support Eukrea CPUIMX25 Platform" select SOC_IMX25 select IMX_HAVE_PLATFORM_FLEXCAN @@ -148,7 +148,7 @@ config MACH_EUKREA_CPUIMX25 choice prompt "Baseboard" - depends on MACH_EUKREA_CPUIMX25 + depends on MACH_EUKREA_CPUIMX25SD default MACH_EUKREA_MBIMXSD25_BASEBOARD config MACH_EUKREA_MBIMXSD25_BASEBOARD @@ -542,7 +542,7 @@ config MACH_MX35_3DS Include support for MX35PDK platform. This includes specific configurations for the board and its peripherals. -config MACH_EUKREA_CPUIMX35 +config MACH_EUKREA_CPUIMX35SD bool "Support Eukrea CPUIMX35 Platform" select SOC_IMX35 select IMX_HAVE_PLATFORM_FLEXCAN @@ -560,7 +560,7 @@ config MACH_EUKREA_CPUIMX35 choice prompt "Baseboard" - depends on MACH_EUKREA_CPUIMX35 + depends on MACH_EUKREA_CPUIMX35SD default MACH_EUKREA_MBIMXSD35_BASEBOARD config MACH_EUKREA_MBIMXSD35_BASEBOARD diff --git a/arch/arm/mach-imx/Makefile b/arch/arm/mach-imx/Makefile index aba7321..d97f409 100644 --- a/arch/arm/mach-imx/Makefile +++ b/arch/arm/mach-imx/Makefile @@ -24,7 +24,7 @@ obj-$(CONFIG_MACH_MX21ADS) += mach-mx21ads.o # i.MX25 based machines obj-$(CONFIG_MACH_MX25_3DS) += mach-mx25_3ds.o -obj-$(CONFIG_MACH_EUKREA_CPUIMX25) += mach-eukrea_cpuimx25.o +obj-$(CONFIG_MACH_EUKREA_CPUIMX25SD) += mach-eukrea_cpuimx25.o obj-$(CONFIG_MACH_EUKREA_MBIMXSD25_BASEBOARD) += eukrea_mbimxsd25-baseboard.o # i.MX27 based machines @@ -57,7 +57,7 @@ obj-$(CONFIG_MACH_BUG) += mach-bug.o # i.MX35 based machines obj-$(CONFIG_MACH_PCM043) += mach-pcm043.o obj-$(CONFIG_MACH_MX35_3DS) += mach-mx35_3ds.o -obj-$(CONFIG_MACH_EUKREA_CPUIMX35) += mach-cpuimx35.o +obj-$(CONFIG_MACH_EUKREA_CPUIMX35SD) += mach-cpuimx35.o obj-$(CONFIG_MACH_EUKREA_MBIMXSD35_BASEBOARD) += eukrea_mbimxsd35-baseboard.o obj-$(CONFIG_MACH_VPR200) += mach-vpr200.o diff --git a/arch/arm/mach-imx/clock-imx35.c b/arch/arm/mach-imx/clock-imx35.c index 8116f11..ac8238c 100644 --- a/arch/arm/mach-imx/clock-imx35.c +++ b/arch/arm/mach-imx/clock-imx35.c @@ -507,7 +507,7 @@ static struct clk_lookup lookups[] = { int __init mx35_clocks_init() { - unsigned int cgr2 = 3 << 26, cgr3 = 0; + unsigned int cgr2 = 3 << 26; #if defined(CONFIG_DEBUG_LL) && !defined(CONFIG_DEBUG_ICEDCC) cgr2 |= 3 << 16; @@ -521,6 +521,12 @@ int __init mx35_clocks_init() __raw_writel((3 << 18), CCM_BASE + CCM_CGR0); __raw_writel((3 << 2) | (3 << 4) | (3 << 6) | (3 << 8) | (3 << 16), CCM_BASE + CCM_CGR1); + __raw_writel(cgr2, CCM_BASE + CCM_CGR2); + __raw_writel(0, CCM_BASE + CCM_CGR3); + + clk_enable(&iim_clk); + imx_print_silicon_rev("i.MX35", mx35_revision()); + clk_disable(&iim_clk); /* * Check if we came up in internal boot mode. If yes, we need some @@ -529,17 +535,11 @@ int __init mx35_clocks_init() */ if (!(__raw_readl(CCM_BASE + CCM_RCSR) & (3 << 10))) { /* Additionally turn on UART1, SCC, and IIM clocks */ - cgr2 |= 3 << 16 | 3 << 4; - cgr3 |= 3 << 2; + clk_enable(&iim_clk); + clk_enable(&uart1_clk); + clk_enable(&scc_clk); } - __raw_writel(cgr2, CCM_BASE + CCM_CGR2); - __raw_writel(cgr3, CCM_BASE + CCM_CGR3); - - clk_enable(&iim_clk); - imx_print_silicon_rev("i.MX35", mx35_revision()); - clk_disable(&iim_clk); - #ifdef CONFIG_MXC_USE_EPIT epit_timer_init(&epit1_clk, MX35_IO_ADDRESS(MX35_EPIT1_BASE_ADDR), MX35_INT_EPIT1); diff --git a/arch/arm/mach-imx/mach-cpuimx35.c b/arch/arm/mach-imx/mach-cpuimx35.c index 66af2e8..362aae7 100644 --- a/arch/arm/mach-imx/mach-cpuimx35.c +++ b/arch/arm/mach-imx/mach-cpuimx35.c @@ -53,12 +53,18 @@ static const struct imxi2c_platform_data .bitrate = 100000, }; +#define TSC2007_IRQGPIO IMX_GPIO_NR(3, 2) +static int tsc2007_get_pendown_state(void) +{ + return !gpio_get_value(TSC2007_IRQGPIO); +} + static struct tsc2007_platform_data tsc2007_info = { .model = 2007, .x_plate_ohms = 180, + .get_pendown_state = tsc2007_get_pendown_state, }; -#define TSC2007_IRQGPIO IMX_GPIO_NR(3, 2) static struct i2c_board_info eukrea_cpuimx35_i2c_devices[] = { { I2C_BOARD_INFO("pcf8563", 0x51), diff --git a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c index 7f8915a..eef43e2 100644 --- a/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c +++ b/arch/arm/mach-omap2/omap_hwmod_3xxx_data.c @@ -3247,18 +3247,14 @@ static __initdata struct omap_hwmod *omap3xxx_hwmods[] = { /* 3430ES1-only hwmods */ static __initdata struct omap_hwmod *omap3430es1_hwmods[] = { - &omap3xxx_iva_hwmod, &omap3430es1_dss_core_hwmod, - &omap3xxx_mailbox_hwmod, NULL }; /* 3430ES2+-only hwmods */ static __initdata struct omap_hwmod *omap3430es2plus_hwmods[] = { - &omap3xxx_iva_hwmod, &omap3xxx_dss_core_hwmod, &omap3xxx_usbhsotg_hwmod, - &omap3xxx_mailbox_hwmod, NULL }; diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c index b862e9f..7119b87 100644 --- a/arch/arm/mach-shmobile/board-ag5evm.c +++ b/arch/arm/mach-shmobile/board-ag5evm.c @@ -607,6 +607,7 @@ struct sys_timer ag5evm_timer = { MACHINE_START(AG5EVM, "ag5evm") .map_io = ag5evm_map_io, + .nr_irqs = NR_IRQS_LEGACY, .init_irq = sh73a0_init_irq, .handle_irq = shmobile_handle_irq_gic, .init_machine = ag5evm_init, diff --git a/arch/arm/mach-shmobile/board-kota2.c b/arch/arm/mach-shmobile/board-kota2.c index bd9a784..f44150b 100644 --- a/arch/arm/mach-shmobile/board-kota2.c +++ b/arch/arm/mach-shmobile/board-kota2.c @@ -33,6 +33,7 @@ #include <linux/input/sh_keysc.h> #include <linux/gpio_keys.h> #include <linux/leds.h> +#include <linux/platform_data/leds-renesas-tpu.h> #include <linux/mmc/host.h> #include <linux/mmc/sh_mmcif.h> #include <linux/mfd/tmio.h> @@ -56,7 +57,7 @@ static struct resource smsc9220_resources[] = { .flags = IORESOURCE_MEM, }, [1] = { - .start = gic_spi(33), /* PINTA2 @ PORT144 */ + .start = SH73A0_PINT0_IRQ(2), /* PINTA2 */ .flags = IORESOURCE_IRQ, }, }; @@ -157,10 +158,6 @@ static struct platform_device gpio_keys_device = { #define GPIO_LED(n, g) { .name = n, .gpio = g } static struct gpio_led gpio_leds[] = { - GPIO_LED("V2513", GPIO_PORT153), /* PORT153 [TPU1T02] -> V2513 */ - GPIO_LED("V2514", GPIO_PORT199), /* PORT199 [TPU4TO1] -> V2514 */ - GPIO_LED("V2515", GPIO_PORT197), /* PORT197 [TPU2TO1] -> V2515 */ - GPIO_LED("KEYLED", GPIO_PORT163), /* PORT163 [TPU3TO0] -> KEYLED */ GPIO_LED("G", GPIO_PORT20), /* PORT20 [GPO0] -> LED7 -> "G" */ GPIO_LED("H", GPIO_PORT21), /* PORT21 [GPO1] -> LED8 -> "H" */ GPIO_LED("J", GPIO_PORT22), /* PORT22 [GPO2] -> LED9 -> "J" */ @@ -179,6 +176,119 @@ static struct platform_device gpio_leds_device = { }, }; +/* TPU LED */ +static struct led_renesas_tpu_config led_renesas_tpu12_pdata = { + .name = "V2513", + .pin_gpio_fn = GPIO_FN_TPU1TO2, + .pin_gpio = GPIO_PORT153, + .channel_offset = 0x90, + .timer_bit = 2, + .max_brightness = 1000, +}; + +static struct resource tpu12_resources[] = { + [0] = { + .name = "TPU12", + .start = 0xe6610090, + .end = 0xe66100b5, + .flags = IORESOURCE_MEM, + }, +}; + +static struct platform_device leds_tpu12_device = { + .name = "leds-renesas-tpu", + .id = 12, + .dev = { + .platform_data = &led_renesas_tpu12_pdata, + }, + .num_resources = ARRAY_SIZE(tpu12_resources), + .resource = tpu12_resources, +}; + +static struct led_renesas_tpu_config led_renesas_tpu41_pdata = { + .name = "V2514", + .pin_gpio_fn = GPIO_FN_TPU4TO1, + .pin_gpio = GPIO_PORT199, + .channel_offset = 0x50, + .timer_bit = 1, + .max_brightness = 1000, +}; + +static struct resource tpu41_resources[] = { + [0] = { + .name = "TPU41", + .start = 0xe6640050, + .end = 0xe6640075, + .flags = IORESOURCE_MEM, + }, +}; + +static struct platform_device leds_tpu41_device = { + .name = "leds-renesas-tpu", + .id = 41, + .dev = { + .platform_data = &led_renesas_tpu41_pdata, + }, + .num_resources = ARRAY_SIZE(tpu41_resources), + .resource = tpu41_resources, +}; + +static struct led_renesas_tpu_config led_renesas_tpu21_pdata = { + .name = "V2515", + .pin_gpio_fn = GPIO_FN_TPU2TO1, + .pin_gpio = GPIO_PORT197, + .channel_offset = 0x50, + .timer_bit = 1, + .max_brightness = 1000, +}; + +static struct resource tpu21_resources[] = { + [0] = { + .name = "TPU21", + .start = 0xe6620050, + .end = 0xe6620075, + .flags = IORESOURCE_MEM, + }, +}; + +static struct platform_device leds_tpu21_device = { + .name = "leds-renesas-tpu", + .id = 21, + .dev = { + .platform_data = &led_renesas_tpu21_pdata, + }, + .num_resources = ARRAY_SIZE(tpu21_resources), + .resource = tpu21_resources, +}; + +static struct led_renesas_tpu_config led_renesas_tpu30_pdata = { + .name = "KEYLED", + .pin_gpio_fn = GPIO_FN_TPU3TO0, + .pin_gpio = GPIO_PORT163, + .channel_offset = 0x10, + .timer_bit = 0, + .max_brightness = 1000, +}; + +static struct resource tpu30_resources[] = { + [0] = { + .name = "TPU30", + .start = 0xe6630010, + .end = 0xe6630035, + .flags = IORESOURCE_MEM, + }, +}; + +static struct platform_device leds_tpu30_device = { + .name = "leds-renesas-tpu", + .id = 30, + .dev = { + .platform_data = &led_renesas_tpu30_pdata, + }, + .num_resources = ARRAY_SIZE(tpu30_resources), + .resource = tpu30_resources, +}; + /* MMCIF */ static struct resource mmcif_resources[] = { [0] = { @@ -291,6 +401,10 @@ static struct platform_device *kota2_devices[] __initdata = { &keysc_device, &gpio_keys_device, &gpio_leds_device, + &leds_tpu12_device, + &leds_tpu41_device, + &leds_tpu21_device, + &leds_tpu30_device, &mmcif_device, &sdhi0_device, &sdhi1_device, @@ -317,18 +431,6 @@ static void __init kota2_map_io(void) shmobile_setup_console(); } -#define PINTER0A 0xe69000a0 -#define PINTCR0A 0xe69000b0 - -void __init kota2_init_irq(void) -{ - sh73a0_init_irq(); - - /* setup PINT: enable PINTA2 as active low */ - __raw_writel(1 << 29, PINTER0A); - __raw_writew(2 << 10, PINTCR0A); -} - static void __init kota2_init(void) { sh73a0_pinmux_init(); @@ -447,7 +549,8 @@ struct sys_timer kota2_timer = { MACHINE_START(KOTA2, "kota2") .map_io = kota2_map_io, - .init_irq = kota2_init_irq, + .nr_irqs = NR_IRQS_LEGACY, + .init_irq = sh73a0_init_irq, .handle_irq = shmobile_handle_irq_gic, .init_machine = kota2_init, .timer = &kota2_timer, diff --git a/arch/arm/mach-shmobile/clock-sh73a0.c b/arch/arm/mach-shmobile/clock-sh73a0.c index 61a846b..1370a89 100644 --- a/arch/arm/mach-shmobile/clock-sh73a0.c +++ b/arch/arm/mach-shmobile/clock-sh73a0.c @@ -113,6 +113,12 @@ static struct clk main_clk = { .ops = &main_clk_ops, }; +/* Divide Main clock by two */ +static struct clk main_div2_clk = { + .ops = &div2_clk_ops, + .parent = &main_clk, +}; + /* PLL0, PLL1, PLL2, PLL3 */ static unsigned long pll_recalc(struct clk *clk) { @@ -181,6 +187,7 @@ static struct clk *main_clks[] = { &extal1_div2_clk, &extal2_div2_clk, &main_clk, + &main_div2_clk, &pll0_clk, &pll1_clk, &pll2_clk, @@ -243,7 +250,7 @@ static struct clk div6_clks[DIV6_NR] = { [DIV6_VCK1] = SH_CLK_DIV6(&pll1_div2_clk, VCLKCR1, 0), [DIV6_VCK2] = SH_CLK_DIV6(&pll1_div2_clk, VCLKCR2, 0), [DIV6_VCK3] = SH_CLK_DIV6(&pll1_div2_clk, VCLKCR3, 0), - [DIV6_ZB1] = SH_CLK_DIV6(&pll1_div2_clk, ZBCKCR, 0), + [DIV6_ZB1] = SH_CLK_DIV6(&pll1_div2_clk, ZBCKCR, CLK_ENABLE_ON_INIT), [DIV6_FLCTL] = SH_CLK_DIV6(&pll1_div2_clk, FLCKCR, 0), [DIV6_SDHI0] = SH_CLK_DIV6(&pll1_div2_clk, SD0CKCR, 0), [DIV6_SDHI1] = SH_CLK_DIV6(&pll1_div2_clk, SD1CKCR, 0), @@ -268,6 +275,7 @@ enum { MSTP001, MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200, MSTP331, MSTP329, MSTP325, MSTP323, MSTP318, MSTP314, MSTP313, MSTP312, MSTP311, + MSTP303, MSTP302, MSTP301, MSTP300, MSTP411, MSTP410, MSTP403, MSTP_NR }; @@ -301,6 +309,10 @@ static struct clk mstp_clks[MSTP_NR] = { [MSTP313] = MSTP(&div6_clks[DIV6_SDHI1], SMSTPCR3, 13, 0), /* SDHI1 */ [MSTP312] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 12, 0), /* MMCIF0 */ [MSTP311] = MSTP(&div6_clks[DIV6_SDHI2], SMSTPCR3, 11, 0), /* SDHI2 */ + [MSTP303] = MSTP(&main_div2_clk, SMSTPCR3, 3, 0), /* TPU1 */ + [MSTP302] = MSTP(&main_div2_clk, SMSTPCR3, 2, 0), /* TPU2 */ + [MSTP301] = MSTP(&main_div2_clk, SMSTPCR3, 1, 0), /* TPU3 */ + [MSTP300] = MSTP(&main_div2_clk, SMSTPCR3, 0, 0), /* TPU4 */ [MSTP411] = MSTP(&div4_clks[DIV4_HP], SMSTPCR4, 11, 0), /* IIC3 */ [MSTP410] = MSTP(&div4_clks[DIV4_HP], SMSTPCR4, 10, 0), /* IIC4 */ [MSTP403] = MSTP(&r_clk, SMSTPCR4, 3, 0), /* KEYSC */ @@ -350,6 +362,10 @@ static struct clk_lookup lookups[] = { CLKDEV_DEV_ID("sh_mobile_sdhi.1", &mstp_clks[MSTP313]), /* SDHI1 */ CLKDEV_DEV_ID("sh_mmcif.0", &mstp_clks[MSTP312]), /* MMCIF0 */ CLKDEV_DEV_ID("sh_mobile_sdhi.2", &mstp_clks[MSTP311]), /* SDHI2 */ + CLKDEV_DEV_ID("leds-renesas-tpu.12", &mstp_clks[MSTP303]), /* TPU1 */ + CLKDEV_DEV_ID("leds-renesas-tpu.21", &mstp_clks[MSTP302]), /* TPU2 */ + CLKDEV_DEV_ID("leds-renesas-tpu.30", &mstp_clks[MSTP301]), /* TPU3 */ + CLKDEV_DEV_ID("leds-renesas-tpu.41", &mstp_clks[MSTP300]), /* TPU4 */ CLKDEV_DEV_ID("i2c-sh_mobile.3", &mstp_clks[MSTP411]), /* I2C3 */ CLKDEV_DEV_ID("i2c-sh_mobile.4", &mstp_clks[MSTP410]), /* I2C4 */ CLKDEV_DEV_ID("sh_keysc.0", &mstp_clks[MSTP403]), /* KEYSC */ diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index fbdd12e..7c38474 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -32,6 +32,7 @@ #include <asm/mach/arch.h> #include <asm/mach/map.h> +#include <asm/memblock.h> #include "mm.h" @@ -332,7 +333,6 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL); - memblock_init(); for (i = 0; i < mi->nr_banks; i++) memblock_add(mi->bank[i].start, mi->bank[i].size); @@ -371,7 +371,7 @@ void __init arm_memblock_init(struct meminfo *mi, struct machine_desc *mdesc) if (mdesc->reserve) mdesc->reserve(); - memblock_analyze(); + memblock_allow_resize(); memblock_dump_all(); } diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S index 2c559ac..e70a737 100644 --- a/arch/arm/mm/proc-v7.S +++ b/arch/arm/mm/proc-v7.S @@ -363,11 +363,13 @@ __v7_setup: orreq r10, r10, #1 << 6 @ set bit #6 mcreq p15, 0, r10, c15, c0, 1 @ write diagnostic register #endif -#ifdef CONFIG_ARM_ERRATA_751472 - cmp r6, #0x30 @ present prior to r3p0 +#if defined(CONFIG_ARM_ERRATA_751472) && defined(CONFIG_SMP) + ALT_SMP(cmp r6, #0x30) @ present prior to r3p0 + ALT_UP_B(1f) mrclt p15, 0, r10, c15, c0, 1 @ read diagnostic register orrlt r10, r10, #1 << 11 @ set bit #11 mcrlt p15, 0, r10, c15, c0, 1 @ write diagnostic register +1: #endif 3: mov r10, #0 diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c index c074e66..4e0a371 100644 --- a/arch/arm/oprofile/common.c +++ b/arch/arm/oprofile/common.c @@ -116,7 +116,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) return oprofile_perf_init(ops); } -void __exit oprofile_arch_exit(void) +void oprofile_arch_exit(void) { oprofile_perf_exit(); } diff --git a/arch/arm/plat-mxc/cpufreq.c b/arch/arm/plat-mxc/cpufreq.c index adbff70..73db34b 100644 --- a/arch/arm/plat-mxc/cpufreq.c +++ b/arch/arm/plat-mxc/cpufreq.c @@ -98,7 +98,7 @@ static int mxc_set_target(struct cpufreq_policy *policy, return ret; } -static int __init mxc_cpufreq_init(struct cpufreq_policy *policy) +static int mxc_cpufreq_init(struct cpufreq_policy *policy) { int ret; int i; diff --git a/arch/arm/plat-mxc/include/mach/uncompress.h b/arch/arm/plat-mxc/include/mach/uncompress.h index 88fd404..477971b 100644 --- a/arch/arm/plat-mxc/include/mach/uncompress.h +++ b/arch/arm/plat-mxc/include/mach/uncompress.h @@ -98,6 +98,7 @@ static __inline__ void __arch_decomp_setup(unsigned long arch_id) case MACH_TYPE_PCM043: case MACH_TYPE_LILLY1131: case MACH_TYPE_VPR200: + case MACH_TYPE_EUKREA_CPUIMX35SD: uart_base = MX3X_UART1_BASE_ADDR; break; case MACH_TYPE_MAGX_ZN5: diff --git a/arch/arm/plat-mxc/pwm.c b/arch/arm/plat-mxc/pwm.c index 845de59..e032717 100644 --- a/arch/arm/plat-mxc/pwm.c +++ b/arch/arm/plat-mxc/pwm.c @@ -77,6 +77,15 @@ int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns) do_div(c, period_ns); duty_cycles = c; + /* + * according to imx pwm RM, the real period value should be + * PERIOD value in PWMPR plus 2. + */ + if (period_cycles > 2) + period_cycles -= 2; + else + period_cycles = 0; + writel(duty_cycles, pwm->mmio_base + MX3_PWMSAR); writel(period_cycles, pwm->mmio_base + MX3_PWMPR); diff --git a/arch/arm/plat-orion/gpio.c b/arch/arm/plat-orion/gpio.c index 41ab97e..10d1608 100644 --- a/arch/arm/plat-orion/gpio.c +++ b/arch/arm/plat-orion/gpio.c @@ -384,12 +384,16 @@ void __init orion_gpio_init(int gpio_base, int ngpio, struct orion_gpio_chip *ochip; struct irq_chip_generic *gc; struct irq_chip_type *ct; + char gc_label[16]; if (orion_gpio_chip_count == ARRAY_SIZE(orion_gpio_chips)) return; + snprintf(gc_label, sizeof(gc_label), "orion_gpio%d", + orion_gpio_chip_count); + ochip = orion_gpio_chips + orion_gpio_chip_count; - ochip->chip.label = "orion_gpio"; + ochip->chip.label = kstrdup(gc_label, GFP_KERNEL); ochip->chip.request = orion_gpio_request; ochip->chip.direction_input = orion_gpio_direction_input; ochip->chip.get = orion_gpio_get; diff --git a/arch/arm/plat-samsung/include/plat/cpu-freq-core.h b/arch/arm/plat-samsung/include/plat/cpu-freq-core.h index dac4760..95509d8 100644 --- a/arch/arm/plat-samsung/include/plat/cpu-freq-core.h +++ b/arch/arm/plat-samsung/include/plat/cpu-freq-core.h @@ -202,14 +202,6 @@ extern int s3c_plltab_register(struct cpufreq_frequency_table *plls, extern struct s3c_cpufreq_config *s3c_cpufreq_getconfig(void); extern struct s3c_iotimings *s3c_cpufreq_getiotimings(void); -extern void s3c2410_iotiming_debugfs(struct seq_file *seq, - struct s3c_cpufreq_config *cfg, - union s3c_iobank *iob); - -extern void s3c2412_iotiming_debugfs(struct seq_file *seq, - struct s3c_cpufreq_config *cfg, - union s3c_iobank *iob); - #ifdef CONFIG_CPU_FREQ_S3C24XX_DEBUGFS #define s3c_cpufreq_debugfs_call(x) x #else @@ -226,6 +218,10 @@ extern void s3c2410_cpufreq_setrefresh(struct s3c_cpufreq_config *cfg); extern void s3c2410_set_fvco(struct s3c_cpufreq_config *cfg); #ifdef CONFIG_S3C2410_IOTIMING +extern void s3c2410_iotiming_debugfs(struct seq_file *seq, + struct s3c_cpufreq_config *cfg, + union s3c_iobank *iob); + extern int s3c2410_iotiming_calc(struct s3c_cpufreq_config *cfg, struct s3c_iotimings *iot); @@ -235,6 +231,7 @@ extern int s3c2410_iotiming_get(struct s3c_cpufreq_config *cfg, extern void s3c2410_iotiming_set(struct s3c_cpufreq_config *cfg, struct s3c_iotimings *iot); #else +#define s3c2410_iotiming_debugfs NULL #define s3c2410_iotiming_calc NULL #define s3c2410_iotiming_get NULL #define s3c2410_iotiming_set NULL @@ -242,8 +239,10 @@ extern void s3c2410_iotiming_set(struct s3c_cpufreq_config *cfg, /* S3C2412 compatible routines */ -extern int s3c2412_iotiming_get(struct s3c_cpufreq_config *cfg, - struct s3c_iotimings *timings); +#ifdef CONFIG_S3C2412_IOTIMING +extern void s3c2412_iotiming_debugfs(struct seq_file *seq, + struct s3c_cpufreq_config *cfg, + union s3c_iobank *iob); extern int s3c2412_iotiming_get(struct s3c_cpufreq_config *cfg, struct s3c_iotimings *timings); @@ -253,6 +252,12 @@ extern int s3c2412_iotiming_calc(struct s3c_cpufreq_config *cfg, extern void s3c2412_iotiming_set(struct s3c_cpufreq_config *cfg, struct s3c_iotimings *iot); +#else +#define s3c2412_iotiming_debugfs NULL +#define s3c2412_iotiming_calc NULL +#define s3c2412_iotiming_get NULL +#define s3c2412_iotiming_set NULL +#endif /* CONFIG_S3C2412_IOTIMING */ #ifdef CONFIG_CPU_FREQ_S3C24XX_DEBUG #define s3c_freq_dbg(x...) printk(KERN_INFO x) diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c index ef5a2a0..ea33957 100644 --- a/arch/avr32/kernel/process.c +++ b/arch/avr32/kernel/process.c @@ -34,10 +34,12 @@ void cpu_idle(void) { /* endless idle loop with no priority at all */ while (1) { - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + rcu_idle_enter(); while (!need_resched()) cpu_idle_sleep(); - tick_nohz_restart_sched_tick(); + rcu_idle_exit(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); schedule(); preempt_disable(); diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c index 6a80a9e..8dd0416 100644 --- a/arch/blackfin/kernel/process.c +++ b/arch/blackfin/kernel/process.c @@ -88,10 +88,12 @@ void cpu_idle(void) #endif if (!idle) idle = default_idle; - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + rcu_idle_enter(); while (!need_resched()) idle(); - tick_nohz_restart_sched_tick(); + rcu_idle_exit(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); schedule(); preempt_disable(); diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 27489b6..3b7a7c4 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -23,6 +23,9 @@ config IA64 select HAVE_ARCH_TRACEHOOK select HAVE_DMA_API_DEBUG select HAVE_GENERIC_HARDIRQS + select HAVE_MEMBLOCK + select HAVE_MEMBLOCK_NODE_MAP + select ARCH_DISCARD_MEMBLOCK select GENERIC_IRQ_PROBE select GENERIC_PENDING_IRQ if SMP select IRQ_PER_CPU @@ -474,9 +477,6 @@ config NODES_SHIFT MAX_NUMNODES will be 2^(This value). If in doubt, use the default. -config ARCH_POPULATES_NODE_MAP - def_bool y - # VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent. # VIRTUAL_MEM_MAP has been retained for historical reasons. config VIRTUAL_MEM_MAP diff --git a/arch/ia64/include/asm/cputime.h b/arch/ia64/include/asm/cputime.h index 6073b18..5a274af 100644 --- a/arch/ia64/include/asm/cputime.h +++ b/arch/ia64/include/asm/cputime.h @@ -60,6 +60,7 @@ typedef u64 cputime64_t; */ #define cputime_to_usecs(__ct) ((__ct) / NSEC_PER_USEC) #define usecs_to_cputime(__usecs) ((__usecs) * NSEC_PER_USEC) +#define usecs_to_cputime64(__usecs) usecs_to_cputime(__usecs) /* * Convert cputime <-> seconds diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index f114a3b..1516d1d 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -16,6 +16,7 @@ */ #include <linux/bootmem.h> #include <linux/efi.h> +#include <linux/memblock.h> #include <linux/mm.h> #include <linux/nmi.h> #include <linux/swap.h> @@ -348,7 +349,7 @@ paging_init (void) printk("Virtual mem_map starts at 0x%p\n", mem_map); } #else /* !CONFIG_VIRTUAL_MEM_MAP */ - add_active_range(0, 0, max_low_pfn); + memblock_add_node(0, PFN_PHYS(max_low_pfn), 0); free_area_init_nodes(max_zone_pfns); #endif /* !CONFIG_VIRTUAL_MEM_MAP */ zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page)); diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 00cb0e2..13df239d 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -10,6 +10,7 @@ #include <linux/bootmem.h> #include <linux/efi.h> #include <linux/elf.h> +#include <linux/memblock.h> #include <linux/mm.h> #include <linux/mmzone.h> #include <linux/module.h> @@ -557,8 +558,7 @@ int __init register_active_ranges(u64 start, u64 len, int nid) #endif if (start < end) - add_active_range(nid, __pa(start) >> PAGE_SHIFT, - __pa(end) >> PAGE_SHIFT); + memblock_add_node(__pa(start), end - start, nid); return 0; } diff --git a/arch/microblaze/include/asm/memblock.h b/arch/microblaze/include/asm/memblock.h deleted file mode 100644 index 20a8e25..0000000 --- a/arch/microblaze/include/asm/memblock.h +++ /dev/null @@ -1,14 +0,0 @@ -/* - * Copyright (C) 2008 Michal Simek <monstr@monstr.eu> - * - * 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_MEMBLOCK_H -#define _ASM_MICROBLAZE_MEMBLOCK_H - -#endif /* _ASM_MICROBLAZE_MEMBLOCK_H */ - - diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c index 95cc295..7dcb5bf 100644 --- a/arch/microblaze/kernel/process.c +++ b/arch/microblaze/kernel/process.c @@ -103,10 +103,12 @@ void cpu_idle(void) if (!idle) idle = default_idle; - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + rcu_idle_enter(); while (!need_resched()) idle(); - tick_nohz_restart_sched_tick(); + rcu_idle_exit(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); schedule(); diff --git a/arch/microblaze/kernel/prom.c b/arch/microblaze/kernel/prom.c index 977484a..80d314e 100644 --- a/arch/microblaze/kernel/prom.c +++ b/arch/microblaze/kernel/prom.c @@ -122,7 +122,6 @@ void __init early_init_devtree(void *params) of_scan_flat_dt(early_init_dt_scan_chosen, cmd_line); /* Scan memory nodes and rebuild MEMBLOCKs */ - memblock_init(); of_scan_flat_dt(early_init_dt_scan_root, NULL); of_scan_flat_dt(early_init_dt_scan_memory, NULL); @@ -130,7 +129,7 @@ void __init early_init_devtree(void *params) strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE); parse_early_param(); - memblock_analyze(); + memblock_allow_resize(); pr_debug("Phys. mem: %lx\n", (unsigned long) memblock_phys_mem_size()); diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index d46f1da..9c652eb 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -25,6 +25,9 @@ config MIPS select GENERIC_IRQ_SHOW select HAVE_ARCH_JUMP_LABEL select IRQ_FORCED_THREADING + select HAVE_MEMBLOCK + select HAVE_MEMBLOCK_NODE_MAP + select ARCH_DISCARD_MEMBLOCK menu "Machine selection" @@ -2064,9 +2067,6 @@ config ARCH_DISCONTIGMEM_ENABLE or have huge holes in the physical address space for other reasons. See <file:Documentation/vm/numa> for more. -config ARCH_POPULATES_NODE_MAP - def_bool y - config ARCH_SPARSEMEM_ENABLE bool select SPARSEMEM_STATIC diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index c47f96e..7955409 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -56,7 +56,8 @@ void __noreturn cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + rcu_idle_enter(); while (!need_resched() && cpu_online(cpu)) { #ifdef CONFIG_MIPS_MT_SMTC extern void smtc_idle_loop_hook(void); @@ -77,7 +78,8 @@ void __noreturn cpu_idle(void) system_state == SYSTEM_BOOTING)) play_dead(); #endif - tick_nohz_restart_sched_tick(); + rcu_idle_exit(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); schedule(); preempt_disable(); diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 84af26a..b1cb8f8 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -14,6 +14,7 @@ #include <linux/ioport.h> #include <linux/export.h> #include <linux/screen_info.h> +#include <linux/memblock.h> #include <linux/bootmem.h> #include <linux/initrd.h> #include <linux/root_dev.h> @@ -352,7 +353,7 @@ static void __init bootmem_init(void) continue; #endif - add_active_range(0, start, end); + memblock_add_node(PFN_PHYS(start), PFN_PHYS(end - start), 0); } /* diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index bc12971..b105eca 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -12,6 +12,7 @@ */ #include <linux/init.h> #include <linux/kernel.h> +#include <linux/memblock.h> #include <linux/mm.h> #include <linux/mmzone.h> #include <linux/module.h> @@ -381,8 +382,8 @@ static void __init szmem(void) continue; } num_physpages += slot_psize; - add_active_range(node, slot_getbasepfn(node, slot), - slot_getbasepfn(node, slot) + slot_psize); + memblock_add_node(PFN_PHYS(slot_getbasepfn(node, slot)), + PFN_PHYS(slot_psize), node); } } } diff --git a/arch/openrisc/include/asm/memblock.h b/arch/openrisc/include/asm/memblock.h deleted file mode 100644 index bbe5a1c..0000000 --- a/arch/openrisc/include/asm/memblock.h +++ /dev/null @@ -1,24 +0,0 @@ -/* - * OpenRISC Linux - * - * Linux architectural port borrowing liberally from similar works of - * others. All original copyrights apply as per the original source - * declaration. - * - * OpenRISC implementation: - * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com> - * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se> - * et al. - * - * 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 __ASM_OPENRISC_MEMBLOCK_H -#define __ASM_OPENRISC_MEMBLOCK_H - -/* empty */ - -#endif /* __ASM_OPENRISC_MEMBLOCK_H */ diff --git a/arch/openrisc/kernel/idle.c b/arch/openrisc/kernel/idle.c index d5bc5f8..e5fc7887 100644 --- a/arch/openrisc/kernel/idle.c +++ b/arch/openrisc/kernel/idle.c @@ -51,7 +51,8 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + rcu_idle_enter(); while (!need_resched()) { check_pgt_cache(); @@ -69,7 +70,8 @@ void cpu_idle(void) set_thread_flag(TIF_POLLING_NRFLAG); } - tick_nohz_restart_sched_tick(); + rcu_idle_exit(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); schedule(); preempt_disable(); diff --git a/arch/openrisc/kernel/prom.c b/arch/openrisc/kernel/prom.c index 1bb58ba..3d4478f 100644 --- a/arch/openrisc/kernel/prom.c +++ b/arch/openrisc/kernel/prom.c @@ -76,14 +76,13 @@ void __init early_init_devtree(void *params) of_scan_flat_dt(early_init_dt_scan_chosen, cmd_line); /* Scan memory nodes and rebuild MEMBLOCKs */ - memblock_init(); of_scan_flat_dt(early_init_dt_scan_root, NULL); of_scan_flat_dt(early_init_dt_scan_memory, NULL); /* Save command line for /proc/cmdline and then parse parameters */ strlcpy(boot_command_line, cmd_line, COMMAND_LINE_SIZE); - memblock_analyze(); + memblock_allow_resize(); /* We must copy the flattend device tree from init memory to regular * memory because the device tree references the strings in it diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 951e18f..ead0bc6 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -117,6 +117,7 @@ config PPC select HAVE_KRETPROBES select HAVE_ARCH_TRACEHOOK select HAVE_MEMBLOCK + select HAVE_MEMBLOCK_NODE_MAP select HAVE_DMA_ATTRS select HAVE_DMA_API_DEBUG select USE_GENERIC_SMP_HELPERS if SMP @@ -421,9 +422,6 @@ config ARCH_SPARSEMEM_DEFAULT def_bool y depends on (SMP && PPC_PSERIES) || PPC_PS3 -config ARCH_POPULATES_NODE_MAP - def_bool y - config SYS_SUPPORTS_HUGETLBFS bool diff --git a/arch/powerpc/include/asm/cputime.h b/arch/powerpc/include/asm/cputime.h index 1cf20bd..98b7c4b 100644 --- a/arch/powerpc/include/asm/cputime.h +++ b/arch/powerpc/include/asm/cputime.h @@ -150,6 +150,8 @@ static inline cputime_t usecs_to_cputime(const unsigned long us) return ct; } +#define usecs_to_cputime64(us) usecs_to_cputime(us) + /* * Convert cputime <-> seconds */ diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index d4df013..69c7377 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -381,39 +381,6 @@ static inline bool kvmppc_critical_section(struct kvm_vcpu *vcpu) } #endif -static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, - unsigned long pte_index) -{ - unsigned long rb, va_low; - - rb = (v & ~0x7fUL) << 16; /* AVA field */ - va_low = pte_index >> 3; - if (v & HPTE_V_SECONDARY) - va_low = ~va_low; - /* xor vsid from AVA */ - if (!(v & HPTE_V_1TB_SEG)) - va_low ^= v >> 12; - else - va_low ^= v >> 24; - va_low &= 0x7ff; - if (v & HPTE_V_LARGE) { - rb |= 1; /* L field */ - if (cpu_has_feature(CPU_FTR_ARCH_206) && - (r & 0xff000)) { - /* non-16MB large page, must be 64k */ - /* (masks depend on page size) */ - rb |= 0x1000; /* page encoding in LP field */ - rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */ - rb |= (va_low & 0xfe); /* AVAL field (P7 doesn't seem to care) */ - } - } else { - /* 4kB page */ - rb |= (va_low & 0x7ff) << 12; /* remaining 11b of VA */ - } - rb |= (v >> 54) & 0x300; /* B field */ - return rb; -} - /* Magic register values loaded into r3 and r4 before the 'sc' assembly * instruction for the OSI hypercalls */ #define OSI_SC_MAGIC_R3 0x113724FA diff --git a/arch/powerpc/include/asm/kvm_book3s_64.h b/arch/powerpc/include/asm/kvm_book3s_64.h index e43fe42..d0ac94f 100644 --- a/arch/powerpc/include/asm/kvm_book3s_64.h +++ b/arch/powerpc/include/asm/kvm_book3s_64.h @@ -29,4 +29,37 @@ static inline struct kvmppc_book3s_shadow_vcpu *to_svcpu(struct kvm_vcpu *vcpu) #define SPAPR_TCE_SHIFT 12 +static inline unsigned long compute_tlbie_rb(unsigned long v, unsigned long r, + unsigned long pte_index) +{ + unsigned long rb, va_low; + + rb = (v & ~0x7fUL) << 16; /* AVA field */ + va_low = pte_index >> 3; + if (v & HPTE_V_SECONDARY) + va_low = ~va_low; + /* xor vsid from AVA */ + if (!(v & HPTE_V_1TB_SEG)) + va_low ^= v >> 12; + else + va_low ^= v >> 24; + va_low &= 0x7ff; + if (v & HPTE_V_LARGE) { + rb |= 1; /* L field */ + if (cpu_has_feature(CPU_FTR_ARCH_206) && + (r & 0xff000)) { + /* non-16MB large page, must be 64k */ + /* (masks depend on page size) */ + rb |= 0x1000; /* page encoding in LP field */ + rb |= (va_low & 0x7f) << 16; /* 7b of VA in AVA/LP field */ + rb |= (va_low & 0xfe); /* AVAL field (P7 doesn't seem to care) */ + } + } else { + /* 4kB page */ + rb |= (va_low & 0x7ff) << 12; /* remaining 11b of VA */ + } + rb |= (v >> 54) & 0x300; /* B field */ + return rb; +} + #endif /* __ASM_KVM_BOOK3S_64_H__ */ diff --git a/arch/powerpc/include/asm/memblock.h b/arch/powerpc/include/asm/memblock.h deleted file mode 100644 index 43efc34..0000000 --- a/arch/powerpc/include/asm/memblock.h +++ /dev/null @@ -1,8 +0,0 @@ -#ifndef _ASM_POWERPC_MEMBLOCK_H -#define _ASM_POWERPC_MEMBLOCK_H - -#include <asm/udbg.h> - -#define MEMBLOCK_DBG(fmt...) udbg_printf(fmt) - -#endif /* _ASM_POWERPC_MEMBLOCK_H */ diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c index 39a2baa..9c3cd49 100644 --- a/arch/powerpc/kernel/idle.c +++ b/arch/powerpc/kernel/idle.c @@ -46,6 +46,12 @@ static int __init powersave_off(char *arg) } __setup("powersave=off", powersave_off); +#if defined(CONFIG_PPC_PSERIES) && defined(CONFIG_TRACEPOINTS) +static const bool idle_uses_rcu = 1; +#else +static const bool idle_uses_rcu; +#endif + /* * The body of the idle task. */ @@ -56,7 +62,10 @@ void cpu_idle(void) set_thread_flag(TIF_POLLING_NRFLAG); while (1) { - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + if (!idle_uses_rcu) + rcu_idle_enter(); + while (!need_resched() && !cpu_should_die()) { ppc64_runlatch_off(); @@ -93,7 +102,9 @@ void cpu_idle(void) HMT_medium(); ppc64_runlatch_on(); - tick_nohz_restart_sched_tick(); + if (!idle_uses_rcu) + rcu_idle_exit(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); if (cpu_should_die()) cpu_die(); diff --git a/arch/powerpc/kernel/machine_kexec.c b/arch/powerpc/kernel/machine_kexec.c index 9ce1672..a2158a3 100644 --- a/arch/powerpc/kernel/machine_kexec.c +++ b/arch/powerpc/kernel/machine_kexec.c @@ -107,9 +107,6 @@ void __init reserve_crashkernel(void) unsigned long long crash_size, crash_base; int ret; - /* this is necessary because of memblock_phys_mem_size() */ - memblock_analyze(); - /* use common parsing */ ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), &crash_size, &crash_base); diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index fa1235b..abe405d 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -733,8 +733,6 @@ void __init early_init_devtree(void *params) of_scan_flat_dt(early_init_dt_scan_chosen_ppc, cmd_line); /* Scan memory nodes and rebuild MEMBLOCKs */ - memblock_init(); - of_scan_flat_dt(early_init_dt_scan_root, NULL); of_scan_flat_dt(early_init_dt_scan_memory_ppc, NULL); @@ -756,20 +754,14 @@ void __init early_init_devtree(void *params) early_reserve_mem(); phyp_dump_reserve_mem(); - limit = memory_limit; - if (! limit) { - phys_addr_t memsize; - - /* Ensure that total memory size is page-aligned, because - * otherwise mark_bootmem() gets upset. */ - memblock_analyze(); - memsize = memblock_phys_mem_size(); - if ((memsize & PAGE_MASK) != memsize) - limit = memsize & PAGE_MASK; - } + /* + * Ensure that total memory size is page-aligned, because otherwise + * mark_bootmem() gets upset. + */ + limit = ALIGN(memory_limit ?: memblock_phys_mem_size(), PAGE_SIZE); memblock_enforce_memory_limit(limit); - memblock_analyze(); + memblock_allow_resize(); memblock_dump_all(); DBG("Phys. mem: %llx\n", memblock_phys_mem_size()); diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 0cb137a..336983d 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -538,7 +538,7 @@ static void kvmppc_start_thread(struct kvm_vcpu *vcpu) tpaca->kvm_hstate.napping = 0; vcpu->cpu = vc->pcpu; smp_wmb(); -#ifdef CONFIG_PPC_ICP_NATIVE +#if defined(CONFIG_PPC_ICP_NATIVE) && defined(CONFIG_SMP) if (vcpu->arch.ptid) { tpaca->cpu_start = 0x80; wmb(); diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c index 3c791e1..e2cfb9e 100644 --- a/arch/powerpc/kvm/book3s_pr.c +++ b/arch/powerpc/kvm/book3s_pr.c @@ -658,10 +658,12 @@ program_interrupt: ulong cmd = kvmppc_get_gpr(vcpu, 3); int i; +#ifdef CONFIG_KVM_BOOK3S_64_PR if (kvmppc_h_pr(vcpu, cmd) == EMULATE_DONE) { r = RESUME_GUEST; break; } +#endif run->papr_hcall.nr = cmd; for (i = 0; i < 9; ++i) { diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c index 26d2090..8c0d45a 100644 --- a/arch/powerpc/kvm/e500.c +++ b/arch/powerpc/kvm/e500.c @@ -15,6 +15,7 @@ #include <linux/kvm_host.h> #include <linux/slab.h> #include <linux/err.h> +#include <linux/export.h> #include <asm/reg.h> #include <asm/cputable.h> diff --git a/arch/powerpc/mm/init_32.c b/arch/powerpc/mm/init_32.c index 161cefd..58861fa 100644 --- a/arch/powerpc/mm/init_32.c +++ b/arch/powerpc/mm/init_32.c @@ -134,8 +134,7 @@ void __init MMU_init(void) if (memblock.memory.cnt > 1) { #ifndef CONFIG_WII - memblock.memory.cnt = 1; - memblock_analyze(); + memblock_enforce_memory_limit(memblock.memory.regions[0].size); printk(KERN_WARNING "Only using first contiguous memory region"); #else wii_memory_fixups(); @@ -158,7 +157,6 @@ void __init MMU_init(void) #ifndef CONFIG_HIGHMEM total_memory = total_lowmem; memblock_enforce_memory_limit(total_lowmem); - memblock_analyze(); #endif /* CONFIG_HIGHMEM */ } diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index 2dd6bdd..8e2eb66 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -199,7 +199,7 @@ void __init do_init_bootmem(void) unsigned long start_pfn, end_pfn; start_pfn = memblock_region_memory_base_pfn(reg); end_pfn = memblock_region_memory_end_pfn(reg); - add_active_range(0, start_pfn, end_pfn); + memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0); } /* Add all physical memory to the bootmem map, mark each area diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b22a83a..e6eea0a 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -127,45 +127,25 @@ static int __cpuinit fake_numa_create_new_node(unsigned long end_pfn, } /* - * get_active_region_work_fn - A helper function for get_node_active_region - * Returns datax set to the start_pfn and end_pfn if they contain - * the initial value of datax->start_pfn between them - * @start_pfn: start page(inclusive) of region to check - * @end_pfn: end page(exclusive) of region to check - * @datax: comes in with ->start_pfn set to value to search for and - * goes out with active range if it contains it - * Returns 1 if search value is in range else 0 - */ -static int __init get_active_region_work_fn(unsigned long start_pfn, - unsigned long end_pfn, void *datax) -{ - struct node_active_region *data; - data = (struct node_active_region *)datax; - - if (start_pfn <= data->start_pfn && end_pfn > data->start_pfn) { - data->start_pfn = start_pfn; - data->end_pfn = end_pfn; - return 1; - } - return 0; - -} - -/* - * get_node_active_region - Return active region containing start_pfn + * get_node_active_region - Return active region containing pfn * Active range returned is empty if none found. - * @start_pfn: The page to return the region for. - * @node_ar: Returned set to the active region containing start_pfn + * @pfn: The page to return the region for + * @node_ar: Returned set to the active region containing @pfn */ -static void __init get_node_active_region(unsigned long start_pfn, - struct node_active_region *node_ar) +static void __init get_node_active_region(unsigned long pfn, + struct node_active_region *node_ar) { - int nid = early_pfn_to_nid(start_pfn); + unsigned long start_pfn, end_pfn; + int i, nid; - node_ar->nid = nid; - node_ar->start_pfn = start_pfn; - node_ar->end_pfn = start_pfn; - work_with_active_regions(nid, get_active_region_work_fn, node_ar); + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + if (pfn >= start_pfn && pfn < end_pfn) { + node_ar->nid = nid; + node_ar->start_pfn = start_pfn; + node_ar->end_pfn = end_pfn; + break; + } + } } static void map_cpu_to_node(int cpu, int node) @@ -710,9 +690,7 @@ static void __init parse_drconf_memory(struct device_node *memory) node_set_online(nid); sz = numa_enforce_memory_limit(base, size); if (sz) - add_active_range(nid, base >> PAGE_SHIFT, - (base >> PAGE_SHIFT) - + (sz >> PAGE_SHIFT)); + memblock_set_node(base, sz, nid); } while (--ranges); } } @@ -802,8 +780,7 @@ new_range: continue; } - add_active_range(nid, start >> PAGE_SHIFT, - (start >> PAGE_SHIFT) + (size >> PAGE_SHIFT)); + memblock_set_node(start, size, nid); if (--ranges) goto new_range; @@ -839,7 +816,8 @@ static void __init setup_nonnuma(void) end_pfn = memblock_region_memory_end_pfn(reg); fake_numa_create_new_node(end_pfn, &nid); - add_active_range(nid, start_pfn, end_pfn); + memblock_set_node(PFN_PHYS(start_pfn), + PFN_PHYS(end_pfn - start_pfn), nid); node_set_online(nid); } } diff --git a/arch/powerpc/mm/tlb_nohash.c b/arch/powerpc/mm/tlb_nohash.c index 4e13d6f..573ba3b 100644 --- a/arch/powerpc/mm/tlb_nohash.c +++ b/arch/powerpc/mm/tlb_nohash.c @@ -615,7 +615,6 @@ static void __early_init_mmu(int boot_cpu) /* limit memory so we dont have linear faults */ memblock_enforce_memory_limit(linear_map_top); - memblock_analyze(); patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e); patch_exception(0x1e0, exc_instruction_tlb_miss_bolted_book3e); diff --git a/arch/powerpc/platforms/embedded6xx/wii.c b/arch/powerpc/platforms/embedded6xx/wii.c index 1b5dc1a..6d8dadf 100644 --- a/arch/powerpc/platforms/embedded6xx/wii.c +++ b/arch/powerpc/platforms/embedded6xx/wii.c @@ -79,24 +79,19 @@ void __init wii_memory_fixups(void) BUG_ON(memblock.memory.cnt != 2); BUG_ON(!page_aligned(p[0].base) || !page_aligned(p[1].base)); - p[0].size = _ALIGN_DOWN(p[0].size, PAGE_SIZE); - p[1].size = _ALIGN_DOWN(p[1].size, PAGE_SIZE); + /* trim unaligned tail */ + memblock_remove(ALIGN(p[1].base + p[1].size, PAGE_SIZE), + (phys_addr_t)ULLONG_MAX); - wii_hole_start = p[0].base + p[0].size; + /* determine hole, add & reserve them */ + wii_hole_start = ALIGN(p[0].base + p[0].size, PAGE_SIZE); wii_hole_size = p[1].base - wii_hole_start; - - pr_info("MEM1: <%08llx %08llx>\n", p[0].base, p[0].size); - pr_info("HOLE: <%08lx %08lx>\n", wii_hole_start, wii_hole_size); - pr_info("MEM2: <%08llx %08llx>\n", p[1].base, p[1].size); - - p[0].size += wii_hole_size + p[1].size; - - memblock.memory.cnt = 1; - memblock_analyze(); - - /* reserve the hole */ + memblock_add(wii_hole_start, wii_hole_size); memblock_reserve(wii_hole_start, wii_hole_size); + BUG_ON(memblock.memory.cnt != 1); + __memblock_dump_all(); + /* allow ioremapping the address space in the hole */ __allow_ioremap_reserved = 1; } diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c index ea0acbd..8fc6258 100644 --- a/arch/powerpc/platforms/iseries/setup.c +++ b/arch/powerpc/platforms/iseries/setup.c @@ -563,7 +563,8 @@ static void yield_shared_processor(void) static void iseries_shared_idle(void) { while (1) { - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + rcu_idle_enter(); while (!need_resched() && !hvlpevent_is_pending()) { local_irq_disable(); ppc64_runlatch_off(); @@ -577,7 +578,8 @@ static void iseries_shared_idle(void) } ppc64_runlatch_on(); - tick_nohz_restart_sched_tick(); + rcu_idle_exit(); + tick_nohz_idle_exit(); if (hvlpevent_is_pending()) process_iSeries_events(); @@ -593,7 +595,8 @@ static void iseries_dedicated_idle(void) set_thread_flag(TIF_POLLING_NRFLAG); while (1) { - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + rcu_idle_enter(); if (!need_resched()) { while (!need_resched()) { ppc64_runlatch_off(); @@ -610,7 +613,8 @@ static void iseries_dedicated_idle(void) } ppc64_runlatch_on(); - tick_nohz_restart_sched_tick(); + rcu_idle_exit(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); schedule(); preempt_disable(); diff --git a/arch/powerpc/platforms/ps3/mm.c b/arch/powerpc/platforms/ps3/mm.c index 72714ad..8bd6ba5 100644 --- a/arch/powerpc/platforms/ps3/mm.c +++ b/arch/powerpc/platforms/ps3/mm.c @@ -319,7 +319,6 @@ static int __init ps3_mm_add_memory(void) } memblock_add(start_addr, map.r1.size); - memblock_analyze(); result = online_pages(start_pfn, nr_pages); diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c index 27a4950..52d429b 100644 --- a/arch/powerpc/platforms/pseries/lpar.c +++ b/arch/powerpc/platforms/pseries/lpar.c @@ -555,6 +555,8 @@ void __trace_hcall_entry(unsigned long opcode, unsigned long *args) (*depth)++; trace_hcall_entry(opcode, args); + if (opcode == H_CEDE) + rcu_idle_enter(); (*depth)--; out: @@ -575,6 +577,8 @@ void __trace_hcall_exit(long opcode, unsigned long retval, goto out; (*depth)++; + if (opcode == H_CEDE) + rcu_idle_exit(); trace_hcall_exit(opcode, retval, retbuf); (*depth)--; diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 373679b..d48ede3 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -92,6 +92,9 @@ config S390 select HAVE_ARCH_JUMP_LABEL if !MARCH_G5 select HAVE_RCU_TABLE_FREE if SMP select ARCH_SAVE_PAGE_KEYS if HIBERNATION + select HAVE_MEMBLOCK + select HAVE_MEMBLOCK_NODE_MAP + select ARCH_DISCARD_MEMBLOCK select ARCH_INLINE_SPIN_TRYLOCK select ARCH_INLINE_SPIN_TRYLOCK_BH select ARCH_INLINE_SPIN_LOCK @@ -345,9 +348,6 @@ config WARN_DYNAMIC_STACK Say N if you are unsure. -config ARCH_POPULATES_NODE_MAP - def_bool y - comment "Kernel preemption" source "kernel/Kconfig.preempt" diff --git a/arch/s390/include/asm/cputime.h b/arch/s390/include/asm/cputime.h index 0814348..b9acaaa 100644 --- a/arch/s390/include/asm/cputime.h +++ b/arch/s390/include/asm/cputime.h @@ -87,6 +87,8 @@ usecs_to_cputime(const unsigned int m) return (cputime_t) m * 4096; } +#define usecs_to_cputime64(m) usecs_to_cputime(m) + /* * Convert cputime to milliseconds and back. */ diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c index 9451b21..3201ae4 100644 --- a/arch/s390/kernel/process.c +++ b/arch/s390/kernel/process.c @@ -91,10 +91,12 @@ static void default_idle(void) void cpu_idle(void) { for (;;) { - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + rcu_idle_enter(); while (!need_resched()) default_idle(); - tick_nohz_restart_sched_tick(); + rcu_idle_exit(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); schedule(); preempt_disable(); diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index e54c4ff..f11d1b0 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -21,6 +21,7 @@ #include <linux/module.h> #include <linux/sched.h> #include <linux/kernel.h> +#include <linux/memblock.h> #include <linux/mm.h> #include <linux/stddef.h> #include <linux/unistd.h> @@ -820,7 +821,8 @@ setup_memory(void) end_chunk = min(end_chunk, end_pfn); if (start_chunk >= end_chunk) continue; - add_active_range(0, start_chunk, end_chunk); + memblock_add_node(PFN_PHYS(start_chunk), + PFN_PHYS(end_chunk - start_chunk), 0); pfn = max(start_chunk, start_pfn); for (; pfn < end_chunk; pfn++) page_set_storage_key(PFN_PHYS(pfn), diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c index 6cf2286..2297be4 100644 --- a/arch/s390/oprofile/init.c +++ b/arch/s390/oprofile/init.c @@ -123,7 +123,7 @@ static ssize_t hwsampler_write(struct file *file, char const __user *buf, return -EINVAL; retval = oprofilefs_ulong_from_user(&val, buf, count); - if (retval) + if (retval <= 0) return retval; if (val != 0 && val != 1) diff --git a/arch/score/Kconfig b/arch/score/Kconfig index df169e8..8b0c946 100644 --- a/arch/score/Kconfig +++ b/arch/score/Kconfig @@ -4,6 +4,9 @@ config SCORE def_bool y select HAVE_GENERIC_HARDIRQS select GENERIC_IRQ_SHOW + select HAVE_MEMBLOCK + select HAVE_MEMBLOCK_NODE_MAP + select ARCH_DISCARD_MEMBLOCK choice prompt "System type" @@ -60,9 +63,6 @@ config 32BIT config ARCH_FLATMEM_ENABLE def_bool y -config ARCH_POPULATES_NODE_MAP - def_bool y - source "mm/Kconfig" config MEMORY_START diff --git a/arch/score/kernel/setup.c b/arch/score/kernel/setup.c index 6f898c0..b48459a 100644 --- a/arch/score/kernel/setup.c +++ b/arch/score/kernel/setup.c @@ -26,6 +26,7 @@ #include <linux/bootmem.h> #include <linux/initrd.h> #include <linux/ioport.h> +#include <linux/memblock.h> #include <linux/mm.h> #include <linux/seq_file.h> #include <linux/screen_info.h> @@ -54,7 +55,8 @@ static void __init bootmem_init(void) /* Initialize the boot-time allocator with low memory only. */ bootmap_size = init_bootmem_node(NODE_DATA(0), start_pfn, min_low_pfn, max_low_pfn); - add_active_range(0, min_low_pfn, max_low_pfn); + memblock_add_node(PFN_PHYS(min_low_pfn), + PFN_PHYS(max_low_pfn - min_low_pfn), 0); free_bootmem(PFN_PHYS(start_pfn), (max_low_pfn - start_pfn) << PAGE_SHIFT); diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 5629e20..47a2f1c 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -4,6 +4,7 @@ config SUPERH select CLKDEV_LOOKUP select HAVE_IDE if HAS_IOPORT select HAVE_MEMBLOCK + select HAVE_MEMBLOCK_NODE_MAP select HAVE_OPROFILE select HAVE_GENERIC_DMA_COHERENT select HAVE_ARCH_TRACEHOOK diff --git a/arch/sh/boards/board-sh7757lcr.c b/arch/sh/boards/board-sh7757lcr.c index ec8c84c..895e337 100644 --- a/arch/sh/boards/board-sh7757lcr.c +++ b/arch/sh/boards/board-sh7757lcr.c @@ -50,9 +50,9 @@ static struct platform_device heartbeat_device = { #define GBECONT 0xffc10100 #define GBECONT_RMII1 BIT(17) #define GBECONT_RMII0 BIT(16) -static void sh7757_eth_set_mdio_gate(unsigned long addr) +static void sh7757_eth_set_mdio_gate(void *addr) { - if ((addr & 0x00000fff) < 0x0800) + if (((unsigned long)addr & 0x00000fff) < 0x0800) writel(readl(GBECONT) | GBECONT_RMII0, GBECONT); else writel(readl(GBECONT) | GBECONT_RMII1, GBECONT); @@ -116,9 +116,9 @@ static struct platform_device sh7757_eth1_device = { }, }; -static void sh7757_eth_giga_set_mdio_gate(unsigned long addr) +static void sh7757_eth_giga_set_mdio_gate(void *addr) { - if ((addr & 0x00000fff) < 0x0800) { + if (((unsigned long)addr & 0x00000fff) < 0x0800) { gpio_set_value(GPIO_PTT4, 1); writel(readl(GBECONT) & ~GBECONT_RMII0, GBECONT); } else { @@ -210,8 +210,12 @@ static struct resource sh_mmcif_resources[] = { }; static struct sh_mmcif_dma sh7757lcr_mmcif_dma = { - .chan_priv_tx = SHDMA_SLAVE_MMCIF_TX, - .chan_priv_rx = SHDMA_SLAVE_MMCIF_RX, + .chan_priv_tx = { + .slave_id = SHDMA_SLAVE_MMCIF_TX, + }, + .chan_priv_rx = { + .slave_id = SHDMA_SLAVE_MMCIF_RX, + } }; static struct sh_mmcif_plat_data sh_mmcif_plat = { diff --git a/arch/sh/include/asm/memblock.h b/arch/sh/include/asm/memblock.h deleted file mode 100644 index e87063f..0000000 --- a/arch/sh/include/asm/memblock.h +++ /dev/null @@ -1,4 +0,0 @@ -#ifndef __ASM_SH_MEMBLOCK_H -#define __ASM_SH_MEMBLOCK_H - -#endif /* __ASM_SH_MEMBLOCK_H */ diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c index db4ecd7..406508d 100644 --- a/arch/sh/kernel/idle.c +++ b/arch/sh/kernel/idle.c @@ -89,7 +89,8 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + rcu_idle_enter(); while (!need_resched()) { check_pgt_cache(); @@ -111,7 +112,8 @@ void cpu_idle(void) start_critical_timings(); } - tick_nohz_restart_sched_tick(); + rcu_idle_exit(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); schedule(); preempt_disable(); diff --git a/arch/sh/kernel/machine_kexec.c b/arch/sh/kernel/machine_kexec.c index c5a33f0..9fea49f 100644 --- a/arch/sh/kernel/machine_kexec.c +++ b/arch/sh/kernel/machine_kexec.c @@ -157,9 +157,6 @@ void __init reserve_crashkernel(void) unsigned long long crash_size, crash_base; int ret; - /* this is necessary because of memblock_phys_mem_size() */ - memblock_analyze(); - ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), &crash_size, &crash_base); if (ret == 0 && crash_size > 0) { diff --git a/arch/sh/kernel/setup.c b/arch/sh/kernel/setup.c index 1a0e946..7b57bf1 100644 --- a/arch/sh/kernel/setup.c +++ b/arch/sh/kernel/setup.c @@ -230,7 +230,8 @@ void __init __add_active_range(unsigned int nid, unsigned long start_pfn, pmb_bolt_mapping((unsigned long)__va(start), start, end - start, PAGE_KERNEL); - add_active_range(nid, start_pfn, end_pfn); + memblock_set_node(PFN_PHYS(start_pfn), + PFN_PHYS(end_pfn - start_pfn), nid); } void __init __weak plat_early_device_setup(void) diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig index c3e61b3..cb8f992 100644 --- a/arch/sh/mm/Kconfig +++ b/arch/sh/mm/Kconfig @@ -143,9 +143,6 @@ config MAX_ACTIVE_REGIONS CPU_SUBTYPE_SH7785) default "1" -config ARCH_POPULATES_NODE_MAP - def_bool y - config ARCH_SELECT_MEMORY_MODEL def_bool y diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 939ca0f..82cc576 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -324,7 +324,6 @@ void __init paging_init(void) unsigned long vaddr, end; int nid; - memblock_init(); sh_mv.mv_mem_init(); early_reserve_mem(); @@ -337,7 +336,7 @@ void __init paging_init(void) sh_mv.mv_mem_reserve(); memblock_enforce_memory_limit(memory_limit); - memblock_analyze(); + memblock_allow_resize(); memblock_dump_all(); diff --git a/arch/sh/oprofile/common.c b/arch/sh/oprofile/common.c index b4c2d2b..e4dd5d5 100644 --- a/arch/sh/oprofile/common.c +++ b/arch/sh/oprofile/common.c @@ -49,7 +49,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) return oprofile_perf_init(ops); } -void __exit oprofile_arch_exit(void) +void oprofile_arch_exit(void) { oprofile_perf_exit(); kfree(sh_pmu_op_name); @@ -60,5 +60,5 @@ int __init oprofile_arch_init(struct oprofile_operations *ops) ops->backtrace = sh_backtrace; return -ENODEV; } -void __exit oprofile_arch_exit(void) {} +void oprofile_arch_exit(void) {} #endif /* CONFIG_HW_PERF_EVENTS */ diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index f92602e..70ae9d8 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -43,6 +43,7 @@ config SPARC64 select HAVE_KPROBES select HAVE_RCU_TABLE_FREE if SMP select HAVE_MEMBLOCK + select HAVE_MEMBLOCK_NODE_MAP select HAVE_SYSCALL_WRAPPERS select HAVE_DYNAMIC_FTRACE select HAVE_FTRACE_MCOUNT_RECORD @@ -352,9 +353,6 @@ config NODES_SPAN_OTHER_NODES def_bool y depends on NEED_MULTIPLE_NODES -config ARCH_POPULATES_NODE_MAP - def_bool y if SPARC64 - config ARCH_SELECT_MEMORY_MODEL def_bool y if SPARC64 diff --git a/arch/sparc/include/asm/memblock.h b/arch/sparc/include/asm/memblock.h deleted file mode 100644 index c67b047..0000000 --- a/arch/sparc/include/asm/memblock.h +++ /dev/null @@ -1,8 +0,0 @@ -#ifndef _SPARC64_MEMBLOCK_H -#define _SPARC64_MEMBLOCK_H - -#include <asm/oplib.h> - -#define MEMBLOCK_DBG(fmt...) prom_printf(fmt) - -#endif /* !(_SPARC64_MEMBLOCK_H) */ diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c index b272cda..af5755d 100644 --- a/arch/sparc/kernel/pci_sun4v.c +++ b/arch/sparc/kernel/pci_sun4v.c @@ -849,10 +849,10 @@ static int pci_sun4v_msiq_build_irq(struct pci_pbm_info *pbm, if (!irq) return -ENOMEM; - if (pci_sun4v_msiq_setstate(pbm->devhandle, msiqid, HV_MSIQSTATE_IDLE)) - return -EINVAL; if (pci_sun4v_msiq_setvalid(pbm->devhandle, msiqid, HV_MSIQ_VALID)) return -EINVAL; + if (pci_sun4v_msiq_setstate(pbm->devhandle, msiqid, HV_MSIQSTATE_IDLE)) + return -EINVAL; return irq; } diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c index 3739a06..39d8b05 100644 --- a/arch/sparc/kernel/process_64.c +++ b/arch/sparc/kernel/process_64.c @@ -95,12 +95,14 @@ void cpu_idle(void) set_thread_flag(TIF_POLLING_NRFLAG); while(1) { - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + rcu_idle_enter(); while (!need_resched() && !cpu_is_offline(cpu)) sparc64_yield(cpu); - tick_nohz_restart_sched_tick(); + rcu_idle_exit(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c index fe1e3fc..ffb883d 100644 --- a/arch/sparc/kernel/setup_32.c +++ b/arch/sparc/kernel/setup_32.c @@ -84,7 +84,7 @@ static void prom_sync_me(void) prom_printf("PROM SYNC COMMAND...\n"); show_free_areas(0); - if(current->pid != 0) { + if (!is_idle_task(current)) { local_irq_enable(); sys_sync(); local_irq_disable(); diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 8e073d8..b3f5e7d 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -790,7 +790,7 @@ static int find_node(unsigned long addr) return -1; } -u64 memblock_nid_range(u64 start, u64 end, int *nid) +static u64 memblock_nid_range(u64 start, u64 end, int *nid) { *nid = find_node(start); start += PAGE_SIZE; @@ -808,7 +808,7 @@ u64 memblock_nid_range(u64 start, u64 end, int *nid) return start; } #else -u64 memblock_nid_range(u64 start, u64 end, int *nid) +static u64 memblock_nid_range(u64 start, u64 end, int *nid) { *nid = 0; return end; @@ -816,7 +816,7 @@ u64 memblock_nid_range(u64 start, u64 end, int *nid) #endif /* This must be invoked after performing all of the necessary - * add_active_range() calls for 'nid'. We need to be able to get + * memblock_set_node() calls for 'nid'. We need to be able to get * correct data from get_pfn_range_for_nid(). */ static void __init allocate_node_data(int nid) @@ -987,14 +987,11 @@ static void __init add_node_ranges(void) this_end = memblock_nid_range(start, end, &nid); - numadbg("Adding active range nid[%d] " + numadbg("Setting memblock NUMA node nid[%d] " "start[%lx] end[%lx]\n", nid, start, this_end); - add_active_range(nid, - start >> PAGE_SHIFT, - this_end >> PAGE_SHIFT); - + memblock_set_node(start, this_end - start, nid); start = this_end; } } @@ -1282,7 +1279,6 @@ static void __init bootmem_init_nonnuma(void) { unsigned long top_of_ram = memblock_end_of_DRAM(); unsigned long total_ram = memblock_phys_mem_size(); - struct memblock_region *reg; numadbg("bootmem_init_nonnuma()\n"); @@ -1292,20 +1288,8 @@ static void __init bootmem_init_nonnuma(void) (top_of_ram - total_ram) >> 20); init_node_masks_nonnuma(); - - for_each_memblock(memory, reg) { - unsigned long start_pfn, end_pfn; - - if (!reg->size) - continue; - - start_pfn = memblock_region_memory_base_pfn(reg); - end_pfn = memblock_region_memory_end_pfn(reg); - add_active_range(0, start_pfn, end_pfn); - } - + memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0); allocate_node_data(0); - node_set_online(0); } @@ -1769,8 +1753,6 @@ void __init paging_init(void) sun4v_ktsb_init(); } - memblock_init(); - /* Find available physical memory... * * Read it twice in order to work around a bug in openfirmware. @@ -1796,7 +1778,7 @@ void __init paging_init(void) memblock_enforce_memory_limit(cmdline_memory_size); - memblock_analyze(); + memblock_allow_resize(); memblock_dump_all(); set_bit(0, mmu_context_bmap); diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c index 9c45d8b..4c1ac6e 100644 --- a/arch/tile/kernel/process.c +++ b/arch/tile/kernel/process.c @@ -85,7 +85,8 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + rcu_idle_enter(); while (!need_resched()) { if (cpu_is_offline(cpu)) BUG(); /* no HOTPLUG_CPU */ @@ -105,7 +106,8 @@ void cpu_idle(void) local_irq_enable(); current_thread_info()->status |= TS_POLLING; } - tick_nohz_restart_sched_tick(); + rcu_idle_exit(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); schedule(); preempt_disable(); diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c index 25b7b90..c1eaaa1 100644 --- a/arch/tile/mm/fault.c +++ b/arch/tile/mm/fault.c @@ -54,7 +54,7 @@ static noinline void force_sig_info_fault(const char *type, int si_signo, if (unlikely(tsk->pid < 2)) { panic("Signal %d (code %d) at %#lx sent to %s!", si_signo, si_code & 0xffff, address, - tsk->pid ? "init" : "the idle task"); + is_idle_task(tsk) ? "the idle task" : "init"); } info.si_signo = si_signo; @@ -515,7 +515,7 @@ no_context: if (unlikely(tsk->pid < 2)) { panic("Kernel page fault running %s!", - tsk->pid ? "init" : "the idle task"); + is_idle_task(tsk) ? "the idle task" : "init"); } /* diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c index c533835..69f2490 100644 --- a/arch/um/kernel/process.c +++ b/arch/um/kernel/process.c @@ -246,10 +246,12 @@ void default_idle(void) if (need_resched()) schedule(); - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + rcu_idle_enter(); nsecs = disable_timer(); idle_sleep(nsecs); - tick_nohz_restart_sched_tick(); + rcu_idle_exit(); + tick_nohz_idle_exit(); } } diff --git a/arch/unicore32/kernel/process.c b/arch/unicore32/kernel/process.c index ba401df..52edc2b 100644 --- a/arch/unicore32/kernel/process.c +++ b/arch/unicore32/kernel/process.c @@ -55,7 +55,8 @@ void cpu_idle(void) { /* endless idle loop with no priority at all */ while (1) { - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + rcu_idle_enter(); while (!need_resched()) { local_irq_disable(); stop_critical_timings(); @@ -63,7 +64,8 @@ void cpu_idle(void) local_irq_enable(); start_critical_timings(); } - tick_nohz_restart_sched_tick(); + rcu_idle_exit(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); schedule(); preempt_disable(); diff --git a/arch/unicore32/kernel/setup.c b/arch/unicore32/kernel/setup.c index 471b6bc..673d7a8 100644 --- a/arch/unicore32/kernel/setup.c +++ b/arch/unicore32/kernel/setup.c @@ -37,6 +37,7 @@ #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/traps.h> +#include <asm/memblock.h> #include "setup.h" diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c index 3b379cd..de186bd 100644 --- a/arch/unicore32/mm/init.c +++ b/arch/unicore32/mm/init.c @@ -26,6 +26,7 @@ #include <asm/setup.h> #include <asm/sizes.h> #include <asm/tlb.h> +#include <asm/memblock.h> #include <mach/map.h> #include "mm.h" @@ -245,7 +246,6 @@ void __init uc32_memblock_init(struct meminfo *mi) sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL); - memblock_init(); for (i = 0; i < mi->nr_banks; i++) memblock_add(mi->bank[i].start, mi->bank[i].size); @@ -264,7 +264,7 @@ void __init uc32_memblock_init(struct meminfo *mi) uc32_mm_memblock_reserve(); - memblock_analyze(); + memblock_allow_resize(); memblock_dump_all(); } diff --git a/arch/unicore32/mm/mmu.c b/arch/unicore32/mm/mmu.c index 3e5c3e5..43c20b4 100644 --- a/arch/unicore32/mm/mmu.c +++ b/arch/unicore32/mm/mmu.c @@ -25,6 +25,7 @@ #include <asm/setup.h> #include <asm/sizes.h> #include <asm/tlb.h> +#include <asm/memblock.h> #include <mach/map.h> diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index efb4294..67d6af3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -26,6 +26,8 @@ config X86 select HAVE_IOREMAP_PROT select HAVE_KPROBES select HAVE_MEMBLOCK + select HAVE_MEMBLOCK_NODE_MAP + select ARCH_DISCARD_MEMBLOCK select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_FRAME_POINTERS select HAVE_DMA_ATTRS @@ -204,9 +206,6 @@ config ZONE_DMA32 bool default X86_64 -config ARCH_POPULATES_NODE_MAP - def_bool y - config AUDIT_ARCH bool default X86_64 diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 908b969..3778256 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -117,7 +117,7 @@ static inline void early_memtest(unsigned long start, unsigned long end) extern unsigned long e820_end_of_ram_pfn(void); extern unsigned long e820_end_of_low_ram_pfn(void); -extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align); +extern u64 early_reserve_e820(u64 sizet, u64 align); void memblock_x86_fill(void); void memblock_find_dma_reserve(void); diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h deleted file mode 100644 index 0cd3800..0000000 --- a/arch/x86/include/asm/memblock.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef _X86_MEMBLOCK_H -#define _X86_MEMBLOCK_H - -#define ARCH_DISCARD_MEMBLOCK - -u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align); - -void memblock_x86_reserve_range(u64 start, u64 end, char *name); -void memblock_x86_free_range(u64 start, u64 end); -struct range; -int __get_free_all_memory_range(struct range **range, int nodeid, - unsigned long start_pfn, unsigned long end_pfn); -int get_free_all_memory_range(struct range **rangep, int nodeid); - -void memblock_x86_register_active_regions(int nid, unsigned long start_pfn, - unsigned long last_pfn); -u64 memblock_x86_hole_size(u64 start, u64 end); -u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align); -u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit); -u64 memblock_x86_memory_in_range(u64 addr, u64 limit); -bool memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align); - -#endif diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 3d2661c..6e76c19 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -88,13 +88,13 @@ static u32 __init allocate_aperture(void) */ addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR, aper_size, aper_size); - if (addr == MEMBLOCK_ERROR || addr + aper_size > GART_MAX_ADDR) { + if (!addr || addr + aper_size > GART_MAX_ADDR) { printk(KERN_ERR "Cannot allocate aperture memory hole (%lx,%uK)\n", addr, aper_size>>10); return 0; } - memblock_x86_reserve_range(addr, addr + aper_size, "aperture64"); + memblock_reserve(addr, aper_size); /* * Kmemleak should not scan this block as it may not be mapped via the * kernel direct mapping. diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index f98d84c..2cd2d93 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -876,8 +876,8 @@ void __irq_entry smp_apic_timer_interrupt(struct pt_regs *regs) * Besides, if we don't timer interrupts ignore the global * interrupt lock, which is the WrongThing (tm) to do. */ - exit_idle(); irq_enter(); + exit_idle(); local_apic_timer_interrupt(); irq_exit(); @@ -1809,8 +1809,8 @@ void smp_spurious_interrupt(struct pt_regs *regs) { u32 v; - exit_idle(); irq_enter(); + exit_idle(); /* * Check if this really is a spurious interrupt and ACK it * if it is a vectored one. Just in case... @@ -1846,8 +1846,8 @@ void smp_error_interrupt(struct pt_regs *regs) "Illegal register address", /* APIC Error Bit 7 */ }; - exit_idle(); irq_enter(); + exit_idle(); /* First tickle the hardware, only then report what went on. -- REW */ v0 = apic_read(APIC_ESR); apic_write(APIC_ESR, 0); diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 6d939d7..8980555 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2421,8 +2421,8 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void) unsigned vector, me; ack_APIC_irq(); - exit_idle(); irq_enter(); + exit_idle(); me = smp_processor_id(); for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) { diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index 452932d..5da1269 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -62,7 +62,8 @@ early_param("memory_corruption_check_size", set_corruption_check_size); void __init setup_bios_corruption_check(void) { - u64 addr = PAGE_SIZE; /* assume first page is reserved anyway */ + phys_addr_t start, end; + u64 i; if (memory_corruption_check == -1) { memory_corruption_check = @@ -82,28 +83,23 @@ void __init setup_bios_corruption_check(void) corruption_check_size = round_up(corruption_check_size, PAGE_SIZE); - while (addr < corruption_check_size && num_scan_areas < MAX_SCAN_AREAS) { - u64 size; - addr = memblock_x86_find_in_range_size(addr, &size, PAGE_SIZE); + for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) { + start = clamp_t(phys_addr_t, round_up(start, PAGE_SIZE), + PAGE_SIZE, corruption_check_size); + end = clamp_t(phys_addr_t, round_down(end, PAGE_SIZE), + PAGE_SIZE, corruption_check_size); + if (start >= end) + continue; - if (addr == MEMBLOCK_ERROR) - break; - - if (addr >= corruption_check_size) - break; - - if ((addr + size) > corruption_check_size) - size = corruption_check_size - addr; - - memblock_x86_reserve_range(addr, addr + size, "SCAN RAM"); - scan_areas[num_scan_areas].addr = addr; - scan_areas[num_scan_areas].size = size; - num_scan_areas++; + memblock_reserve(start, end - start); + scan_areas[num_scan_areas].addr = start; + scan_areas[num_scan_areas].size = end - start; /* Assume we've already mapped this early memory */ - memset(__va(addr), 0, size); + memset(__va(start), 0, end - start); - addr += size; + if (++num_scan_areas >= MAX_SCAN_AREAS) + break; } if (num_scan_areas) diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 787e06c..ce21561 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -397,8 +397,8 @@ static void (*smp_thermal_vector)(void) = unexpected_thermal_interrupt; asmlinkage void smp_thermal_interrupt(struct pt_regs *regs) { - exit_idle(); irq_enter(); + exit_idle(); inc_irq_stat(irq_thermal_count); smp_thermal_vector(); irq_exit(); diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c index d746df2..aa578ca 100644 --- a/arch/x86/kernel/cpu/mcheck/threshold.c +++ b/arch/x86/kernel/cpu/mcheck/threshold.c @@ -19,8 +19,8 @@ void (*mce_threshold_vector)(void) = default_threshold_interrupt; asmlinkage void smp_threshold_interrupt(void) { - exit_idle(); irq_enter(); + exit_idle(); inc_irq_stat(irq_threshold_count); mce_threshold_vector(); irq_exit(); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index cbfaaa2..3bd37bd 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -1165,7 +1165,7 @@ again: */ c = &unconstrained; } else if (intel_try_alt_er(event, orig_idx)) { - raw_spin_unlock(&era->lock); + raw_spin_unlock_irqrestore(&era->lock, flags); goto again; } raw_spin_unlock_irqrestore(&era->lock, flags); diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 3b97a80..c99f9ed 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -116,16 +116,16 @@ void show_registers(struct pt_regs *regs) for (i = 0; i < code_len; i++, ip++) { if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { - printk(" Bad EIP value."); + printk(KERN_CONT " Bad EIP value."); break; } if (ip == (u8 *)regs->ip) - printk("<%02x> ", c); + printk(KERN_CONT "<%02x> ", c); else - printk("%02x ", c); + printk(KERN_CONT "%02x ", c); } } - printk("\n"); + printk(KERN_CONT "\n"); } int is_valid_bugaddr(unsigned long ip) diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 19853ad..6d728d9 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -284,16 +284,16 @@ void show_registers(struct pt_regs *regs) for (i = 0; i < code_len; i++, ip++) { if (ip < (u8 *)PAGE_OFFSET || probe_kernel_address(ip, c)) { - printk(" Bad RIP value."); + printk(KERN_CONT " Bad RIP value."); break; } if (ip == (u8 *)regs->ip) - printk("<%02x> ", c); + printk(KERN_CONT "<%02x> ", c); else - printk("%02x ", c); + printk(KERN_CONT "%02x ", c); } } - printk("\n"); + printk(KERN_CONT "\n"); } int is_valid_bugaddr(unsigned long ip) diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 303a0e4..8071e2f 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -738,35 +738,17 @@ core_initcall(e820_mark_nvs_memory); /* * pre allocated 4k and reserved it in memblock and e820_saved */ -u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) +u64 __init early_reserve_e820(u64 size, u64 align) { - u64 size = 0; u64 addr; - u64 start; - for (start = startt; ; start += size) { - start = memblock_x86_find_in_range_size(start, &size, align); - if (start == MEMBLOCK_ERROR) - return 0; - if (size >= sizet) - break; + addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); + if (addr) { + e820_update_range_saved(addr, size, E820_RAM, E820_RESERVED); + printk(KERN_INFO "update e820_saved for early_reserve_e820\n"); + update_e820_saved(); } -#ifdef CONFIG_X86_32 - if (start >= MAXMEM) - return 0; - if (start + size > MAXMEM) - size = MAXMEM - start; -#endif - - addr = round_down(start + size - sizet, align); - if (addr < start) - return 0; - memblock_x86_reserve_range(addr, addr + sizet, "new next"); - e820_update_range_saved(addr, sizet, E820_RAM, E820_RESERVED); - printk(KERN_INFO "update e820_saved for early_reserve_e820\n"); - update_e820_saved(); - return addr; } @@ -1090,7 +1072,7 @@ void __init memblock_x86_fill(void) * We are safe to enable resizing, beause memblock_x86_fill() * is rather later for x86 */ - memblock_can_resize = 1; + memblock_allow_resize(); for (i = 0; i < e820.nr_map; i++) { struct e820entry *ei = &e820.map[i]; @@ -1105,22 +1087,36 @@ void __init memblock_x86_fill(void) memblock_add(ei->addr, ei->size); } - memblock_analyze(); memblock_dump_all(); } void __init memblock_find_dma_reserve(void) { #ifdef CONFIG_X86_64 - u64 free_size_pfn; - u64 mem_size_pfn; + u64 nr_pages = 0, nr_free_pages = 0; + unsigned long start_pfn, end_pfn; + phys_addr_t start, end; + int i; + u64 u; + /* * need to find out used area below MAX_DMA_PFN * need to use memblock to get free size in [0, MAX_DMA_PFN] * at first, and assume boot_mem will not take below MAX_DMA_PFN */ - mem_size_pfn = memblock_x86_memory_in_range(0, MAX_DMA_PFN << PAGE_SHIFT) >> PAGE_SHIFT; - free_size_pfn = memblock_x86_free_memory_in_range(0, MAX_DMA_PFN << PAGE_SHIFT) >> PAGE_SHIFT; - set_dma_reserve(mem_size_pfn - free_size_pfn); + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { + start_pfn = min_t(unsigned long, start_pfn, MAX_DMA_PFN); + end_pfn = min_t(unsigned long, end_pfn, MAX_DMA_PFN); + nr_pages += end_pfn - start_pfn; + } + + for_each_free_mem_range(u, MAX_NUMNODES, &start, &end, NULL) { + start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN); + end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN); + if (start_pfn < end_pfn) + nr_free_pages += end_pfn - start_pfn; + } + + set_dma_reserve(nr_pages - nr_free_pages); #endif } diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c index af0699b..48d9d4e 100644 --- a/arch/x86/kernel/head.c +++ b/arch/x86/kernel/head.c @@ -52,5 +52,5 @@ void __init reserve_ebda_region(void) lowmem = 0x9f000; /* reserve all memory between lowmem and the 1MB mark */ - memblock_x86_reserve_range(lowmem, 0x100000, "* BIOS reserved"); + memblock_reserve(lowmem, 0x100000 - lowmem); } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 3bb0850..51ff186 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -31,9 +31,8 @@ static void __init i386_default_early_setup(void) void __init i386_start_kernel(void) { - memblock_init(); - - memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); + memblock_reserve(__pa_symbol(&_text), + __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ @@ -42,7 +41,7 @@ void __init i386_start_kernel(void) u64 ramdisk_image = boot_params.hdr.ramdisk_image; u64 ramdisk_size = boot_params.hdr.ramdisk_size; u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); - memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK"); + memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image); } #endif diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 5655c22..3a3b779 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -98,9 +98,8 @@ void __init x86_64_start_reservations(char *real_mode_data) { copy_bootdata(__va(real_mode_data)); - memblock_init(); - - memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); + memblock_reserve(__pa_symbol(&_text), + __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ @@ -109,7 +108,7 @@ void __init x86_64_start_reservations(char *real_mode_data) unsigned long ramdisk_image = boot_params.hdr.ramdisk_image; unsigned long ramdisk_size = boot_params.hdr.ramdisk_size; unsigned long ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); - memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK"); + memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image); } #endif diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 429e0c9..5d31e5b 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -181,8 +181,8 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs) unsigned vector = ~regs->orig_ax; unsigned irq; - exit_idle(); irq_enter(); + exit_idle(); irq = __this_cpu_read(vector_irq[vector]); @@ -209,10 +209,10 @@ void smp_x86_platform_ipi(struct pt_regs *regs) ack_APIC_irq(); - exit_idle(); - irq_enter(); + exit_idle(); + inc_irq_stat(x86_platform_ipis); if (x86_platform_ipi_callback) diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 0741b062..ca470e4 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -564,9 +564,7 @@ void __init default_get_smp_config(unsigned int early) static void __init smp_reserve_memory(struct mpf_intel *mpf) { - unsigned long size = get_mpc_size(mpf->physptr); - - memblock_x86_reserve_range(mpf->physptr, mpf->physptr+size, "* MP-table mpc"); + memblock_reserve(mpf->physptr, get_mpc_size(mpf->physptr)); } static int __init smp_scan_config(unsigned long base, unsigned long length) @@ -595,7 +593,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) mpf, (u64)virt_to_phys(mpf)); mem = virt_to_phys(mpf); - memblock_x86_reserve_range(mem, mem + sizeof(*mpf), "* MP-table mpf"); + memblock_reserve(mem, sizeof(*mpf)); if (mpf->physptr) smp_reserve_memory(mpf); @@ -836,10 +834,8 @@ early_param("alloc_mptable", parse_alloc_mptable_opt); void __init early_reserve_e820_mpc_new(void) { - if (enable_update_mptable && alloc_mptable) { - u64 startt = 0; - mpc_new_phys = early_reserve_e820(startt, mpc_new_length, 4); - } + if (enable_update_mptable && alloc_mptable) + mpc_new_phys = early_reserve_e820(mpc_new_length, 4); } static int __init update_mp_table(void) diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 795b79f..485204f 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -99,7 +99,8 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); + rcu_idle_enter(); while (!need_resched()) { check_pgt_cache(); @@ -116,7 +117,8 @@ void cpu_idle(void) pm_idle(); start_critical_timings(); } - tick_nohz_restart_sched_tick(); + rcu_idle_exit(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); schedule(); preempt_disable(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 3bd7e6e..64e926c 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -122,7 +122,7 @@ void cpu_idle(void) /* endless idle loop with no priority at all */ while (1) { - tick_nohz_stop_sched_tick(1); + tick_nohz_idle_enter(); while (!need_resched()) { rmb(); @@ -139,8 +139,14 @@ void cpu_idle(void) enter_idle(); /* Don't trace irqs off for idle */ stop_critical_timings(); + + /* enter_idle() needs rcu for notifiers */ + rcu_idle_enter(); + if (cpuidle_idle_call()) pm_idle(); + + rcu_idle_exit(); start_critical_timings(); /* In many cases the interrupt that ended idle @@ -149,7 +155,7 @@ void cpu_idle(void) __exit_idle(); } - tick_nohz_restart_sched_tick(); + tick_nohz_idle_exit(); preempt_enable_no_resched(); schedule(); preempt_disable(); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index cf0ef98..d05444a 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -306,7 +306,8 @@ static void __init cleanup_highmap(void) static void __init reserve_brk(void) { if (_brk_end > _brk_start) - memblock_x86_reserve_range(__pa(_brk_start), __pa(_brk_end), "BRK"); + memblock_reserve(__pa(_brk_start), + __pa(_brk_end) - __pa(_brk_start)); /* Mark brk area as locked down and no longer taking any new allocations */ @@ -331,13 +332,13 @@ static void __init relocate_initrd(void) ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size, PAGE_SIZE); - if (ramdisk_here == MEMBLOCK_ERROR) + if (!ramdisk_here) panic("Cannot find place for new RAMDISK of size %lld\n", ramdisk_size); /* Note: this includes all the lowmem currently occupied by the initrd, we rely on that fact to keep the data intact. */ - memblock_x86_reserve_range(ramdisk_here, ramdisk_here + area_size, "NEW RAMDISK"); + memblock_reserve(ramdisk_here, area_size); initrd_start = ramdisk_here + PAGE_OFFSET; initrd_end = initrd_start + ramdisk_size; printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n", @@ -393,7 +394,7 @@ static void __init reserve_initrd(void) initrd_start = 0; if (ramdisk_size >= (end_of_lowmem>>1)) { - memblock_x86_free_range(ramdisk_image, ramdisk_end); + memblock_free(ramdisk_image, ramdisk_end - ramdisk_image); printk(KERN_ERR "initrd too large to handle, " "disabling initrd\n"); return; @@ -416,7 +417,7 @@ static void __init reserve_initrd(void) relocate_initrd(); - memblock_x86_free_range(ramdisk_image, ramdisk_end); + memblock_free(ramdisk_image, ramdisk_end - ramdisk_image); } #else static void __init reserve_initrd(void) @@ -490,15 +491,13 @@ static void __init memblock_x86_reserve_range_setup_data(void) { struct setup_data *data; u64 pa_data; - char buf[32]; if (boot_params.hdr.version < 0x0209) return; pa_data = boot_params.hdr.setup_data; while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); - sprintf(buf, "setup data %x", data->type); - memblock_x86_reserve_range(pa_data, pa_data+sizeof(*data)+data->len, buf); + memblock_reserve(pa_data, sizeof(*data) + data->len); pa_data = data->next; early_iounmap(data, sizeof(*data)); } @@ -554,7 +553,7 @@ static void __init reserve_crashkernel(void) crash_base = memblock_find_in_range(alignment, CRASH_KERNEL_ADDR_MAX, crash_size, alignment); - if (crash_base == MEMBLOCK_ERROR) { + if (!crash_base) { pr_info("crashkernel reservation failed - No suitable area found.\n"); return; } @@ -568,7 +567,7 @@ static void __init reserve_crashkernel(void) return; } } - memblock_x86_reserve_range(crash_base, crash_base + crash_size, "CRASH KERNEL"); + memblock_reserve(crash_base, crash_size); printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " "for crashkernel (System RAM: %ldMB)\n", @@ -626,7 +625,7 @@ static __init void reserve_ibft_region(void) addr = find_ibft_region(&size); if (size) - memblock_x86_reserve_range(addr, addr + size, "* ibft"); + memblock_reserve(addr, size); } static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10; diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c index a91ae77..a73b610 100644 --- a/arch/x86/kernel/trampoline.c +++ b/arch/x86/kernel/trampoline.c @@ -14,11 +14,11 @@ void __init setup_trampolines(void) /* Has to be in very low memory so we can execute real-mode AP code. */ mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE); - if (mem == MEMBLOCK_ERROR) + if (!mem) panic("Cannot allocate trampoline\n"); x86_trampoline_base = __va(mem); - memblock_x86_reserve_range(mem, mem + size, "TRAMPOLINE"); + memblock_reserve(mem, size); printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n", x86_trampoline_base, (unsigned long long)mem, size); diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 76e3f1c..405f262 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -338,11 +338,15 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) return HRTIMER_NORESTART; } -static void create_pit_timer(struct kvm_kpit_state *ps, u32 val, int is_period) +static void create_pit_timer(struct kvm *kvm, u32 val, int is_period) { + struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state; struct kvm_timer *pt = &ps->pit_timer; s64 interval; + if (!irqchip_in_kernel(kvm)) + return; + interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ); pr_debug("create pit timer, interval is %llu nsec\n", interval); @@ -394,13 +398,13 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val) /* FIXME: enhance mode 4 precision */ case 4: if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)) { - create_pit_timer(ps, val, 0); + create_pit_timer(kvm, val, 0); } break; case 2: case 3: if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)){ - create_pit_timer(ps, val, 1); + create_pit_timer(kvm, val, 1); } break; default: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c38efd7..4c938da 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -602,7 +602,6 @@ static void update_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; struct kvm_lapic *apic = vcpu->arch.apic; - u32 timer_mode_mask; best = kvm_find_cpuid_entry(vcpu, 1, 0); if (!best) @@ -615,15 +614,12 @@ static void update_cpuid(struct kvm_vcpu *vcpu) best->ecx |= bit(X86_FEATURE_OSXSAVE); } - if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && - best->function == 0x1) { - best->ecx |= bit(X86_FEATURE_TSC_DEADLINE_TIMER); - timer_mode_mask = 3 << 17; - } else - timer_mode_mask = 1 << 17; - - if (apic) - apic->lapic_timer.timer_mode_mask = timer_mode_mask; + if (apic) { + if (best->ecx & bit(X86_FEATURE_TSC_DEADLINE_TIMER)) + apic->lapic_timer.timer_mode_mask = 3 << 17; + else + apic->lapic_timer.timer_mode_mask = 1 << 17; + } } int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) @@ -2135,6 +2131,9 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_TSC_CONTROL: r = kvm_has_tsc_control; break; + case KVM_CAP_TSC_DEADLINE_TIMER: + r = boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER); + break; default: r = 0; break; diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 3d11327..23d8e5f 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -27,6 +27,4 @@ obj-$(CONFIG_AMD_NUMA) += amdtopology.o obj-$(CONFIG_ACPI_NUMA) += srat.o obj-$(CONFIG_NUMA_EMU) += numa_emulation.o -obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o - obj-$(CONFIG_MEMTEST) += memtest.o diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 87488b9..a298914 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -67,7 +67,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse, good_end = max_pfn_mapped << PAGE_SHIFT; base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE); - if (base == MEMBLOCK_ERROR) + if (!base) panic("Cannot find space for the kernel page tables"); pgt_buf_start = base >> PAGE_SHIFT; @@ -80,7 +80,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse, void __init native_pagetable_reserve(u64 start, u64 end) { - memblock_x86_reserve_range(start, end, "PGTABLE"); + memblock_reserve(start, end - start); } struct map_range { @@ -279,8 +279,8 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, * pgt_buf_end) and free the other ones (pgt_buf_end - pgt_buf_top) * so that they can be reused for other purposes. * - * On native it just means calling memblock_x86_reserve_range, on Xen it - * also means marking RW the pagetable pages that we allocated before + * On native it just means calling memblock_reserve, on Xen it also + * means marking RW the pagetable pages that we allocated before * but that haven't been used. * * In fact on xen we mark RO the whole range pgt_buf_start - diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 29f7c6d..0c1da39 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -427,23 +427,17 @@ static void __init add_one_highpage_init(struct page *page) void __init add_highpages_with_active_regions(int nid, unsigned long start_pfn, unsigned long end_pfn) { - struct range *range; - int nr_range; - int i; - - nr_range = __get_free_all_memory_range(&range, nid, start_pfn, end_pfn); - - for (i = 0; i < nr_range; i++) { - struct page *page; - int node_pfn; - - for (node_pfn = range[i].start; node_pfn < range[i].end; - node_pfn++) { - if (!pfn_valid(node_pfn)) - continue; - page = pfn_to_page(node_pfn); - add_one_highpage_init(page); - } + phys_addr_t start, end; + u64 i; + + for_each_free_mem_range(i, nid, &start, &end, NULL) { + unsigned long pfn = clamp_t(unsigned long, PFN_UP(start), + start_pfn, end_pfn); + unsigned long e_pfn = clamp_t(unsigned long, PFN_DOWN(end), + start_pfn, end_pfn); + for ( ; pfn < e_pfn; pfn++) + if (pfn_valid(pfn)) + add_one_highpage_init(pfn_to_page(pfn)); } } #else @@ -650,18 +644,18 @@ void __init initmem_init(void) highstart_pfn = highend_pfn = max_pfn; if (max_pfn > max_low_pfn) highstart_pfn = max_low_pfn; - memblock_x86_register_active_regions(0, 0, highend_pfn); - sparse_memory_present_with_active_regions(0); printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", pages_to_mb(highend_pfn - highstart_pfn)); num_physpages = highend_pfn; high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; #else - memblock_x86_register_active_regions(0, 0, max_low_pfn); - sparse_memory_present_with_active_regions(0); num_physpages = max_low_pfn; high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; #endif + + memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0); + sparse_memory_present_with_active_regions(0); + #ifdef CONFIG_FLATMEM max_mapnr = num_physpages; #endif diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index bbaaa00..a8a56ce 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -608,7 +608,7 @@ kernel_physical_mapping_init(unsigned long start, #ifndef CONFIG_NUMA void __init initmem_init(void) { - memblock_x86_register_active_regions(0, 0, max_pfn); + memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0); } #endif diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c deleted file mode 100644 index 992da5e..0000000 --- a/arch/x86/mm/memblock.c +++ /dev/null @@ -1,348 +0,0 @@ -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/init.h> -#include <linux/bitops.h> -#include <linux/memblock.h> -#include <linux/bootmem.h> -#include <linux/mm.h> -#include <linux/range.h> - -/* Check for already reserved areas */ -bool __init memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align) -{ - struct memblock_region *r; - u64 addr = *addrp, last; - u64 size = *sizep; - bool changed = false; - -again: - last = addr + size; - for_each_memblock(reserved, r) { - if (last > r->base && addr < r->base) { - size = r->base - addr; - changed = true; - goto again; - } - if (last > (r->base + r->size) && addr < (r->base + r->size)) { - addr = round_up(r->base + r->size, align); - size = last - addr; - changed = true; - goto again; - } - if (last <= (r->base + r->size) && addr >= r->base) { - *sizep = 0; - return false; - } - } - if (changed) { - *addrp = addr; - *sizep = size; - } - return changed; -} - -/* - * Find next free range after start, and size is returned in *sizep - */ -u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align) -{ - struct memblock_region *r; - - for_each_memblock(memory, r) { - u64 ei_start = r->base; - u64 ei_last = ei_start + r->size; - u64 addr; - - addr = round_up(ei_start, align); - if (addr < start) - addr = round_up(start, align); - if (addr >= ei_last) - continue; - *sizep = ei_last - addr; - while (memblock_x86_check_reserved_size(&addr, sizep, align)) - ; - - if (*sizep) - return addr; - } - - return MEMBLOCK_ERROR; -} - -static __init struct range *find_range_array(int count) -{ - u64 end, size, mem; - struct range *range; - - size = sizeof(struct range) * count; - end = memblock.current_limit; - - mem = memblock_find_in_range(0, end, size, sizeof(struct range)); - if (mem == MEMBLOCK_ERROR) - panic("can not find more space for range array"); - - /* - * This range is tempoaray, so don't reserve it, it will not be - * overlapped because We will not alloccate new buffer before - * We discard this one - */ - range = __va(mem); - memset(range, 0, size); - - return range; -} - -static void __init memblock_x86_subtract_reserved(struct range *range, int az) -{ - u64 final_start, final_end; - struct memblock_region *r; - - /* Take out region array itself at first*/ - memblock_free_reserved_regions(); - - memblock_dbg("Subtract (%ld early reservations)\n", memblock.reserved.cnt); - - for_each_memblock(reserved, r) { - memblock_dbg(" [%010llx-%010llx]\n", (u64)r->base, (u64)r->base + r->size - 1); - final_start = PFN_DOWN(r->base); - final_end = PFN_UP(r->base + r->size); - if (final_start >= final_end) - continue; - subtract_range(range, az, final_start, final_end); - } - - /* Put region array back ? */ - memblock_reserve_reserved_regions(); -} - -struct count_data { - int nr; -}; - -static int __init count_work_fn(unsigned long start_pfn, - unsigned long end_pfn, void *datax) -{ - struct count_data *data = datax; - - data->nr++; - - return 0; -} - -static int __init count_early_node_map(int nodeid) -{ - struct count_data data; - - data.nr = 0; - work_with_active_regions(nodeid, count_work_fn, &data); - - return data.nr; -} - -int __init __get_free_all_memory_range(struct range **rangep, int nodeid, - unsigned long start_pfn, unsigned long end_pfn) -{ - int count; - struct range *range; - int nr_range; - - count = (memblock.reserved.cnt + count_early_node_map(nodeid)) * 2; - - range = find_range_array(count); - nr_range = 0; - - /* - * Use early_node_map[] and memblock.reserved.region to get range array - * at first - */ - nr_range = add_from_early_node_map(range, count, nr_range, nodeid); - subtract_range(range, count, 0, start_pfn); - subtract_range(range, count, end_pfn, -1ULL); - - memblock_x86_subtract_reserved(range, count); - nr_range = clean_sort_range(range, count); - - *rangep = range; - return nr_range; -} - -int __init get_free_all_memory_range(struct range **rangep, int nodeid) -{ - unsigned long end_pfn = -1UL; - -#ifdef CONFIG_X86_32 - end_pfn = max_low_pfn; -#endif - return __get_free_all_memory_range(rangep, nodeid, 0, end_pfn); -} - -static u64 __init __memblock_x86_memory_in_range(u64 addr, u64 limit, bool get_free) -{ - int i, count; - struct range *range; - int nr_range; - u64 final_start, final_end; - u64 free_size; - struct memblock_region *r; - - count = (memblock.reserved.cnt + memblock.memory.cnt) * 2; - - range = find_range_array(count); - nr_range = 0; - - addr = PFN_UP(addr); - limit = PFN_DOWN(limit); - - for_each_memblock(memory, r) { - final_start = PFN_UP(r->base); - final_end = PFN_DOWN(r->base + r->size); - if (final_start >= final_end) - continue; - if (final_start >= limit || final_end <= addr) - continue; - - nr_range = add_range(range, count, nr_range, final_start, final_end); - } - subtract_range(range, count, 0, addr); - subtract_range(range, count, limit, -1ULL); - - /* Subtract memblock.reserved.region in range ? */ - if (!get_free) - goto sort_and_count_them; - for_each_memblock(reserved, r) { - final_start = PFN_DOWN(r->base); - final_end = PFN_UP(r->base + r->size); - if (final_start >= final_end) - continue; - if (final_start >= limit || final_end <= addr) - continue; - - subtract_range(range, count, final_start, final_end); - } - -sort_and_count_them: - nr_range = clean_sort_range(range, count); - - free_size = 0; - for (i = 0; i < nr_range; i++) - free_size += range[i].end - range[i].start; - - return free_size << PAGE_SHIFT; -} - -u64 __init memblock_x86_free_memory_in_range(u64 addr, u64 limit) -{ - return __memblock_x86_memory_in_range(addr, limit, true); -} - -u64 __init memblock_x86_memory_in_range(u64 addr, u64 limit) -{ - return __memblock_x86_memory_in_range(addr, limit, false); -} - -void __init memblock_x86_reserve_range(u64 start, u64 end, char *name) -{ - if (start == end) - return; - - if (WARN_ONCE(start > end, "memblock_x86_reserve_range: wrong range [%#llx, %#llx)\n", start, end)) - return; - - memblock_dbg(" memblock_x86_reserve_range: [%#010llx-%#010llx] %16s\n", start, end - 1, name); - - memblock_reserve(start, end - start); -} - -void __init memblock_x86_free_range(u64 start, u64 end) -{ - if (start == end) - return; - - if (WARN_ONCE(start > end, "memblock_x86_free_range: wrong range [%#llx, %#llx)\n", start, end)) - return; - - memblock_dbg(" memblock_x86_free_range: [%#010llx-%#010llx]\n", start, end - 1); - - memblock_free(start, end - start); -} - -/* - * Need to call this function after memblock_x86_register_active_regions, - * so early_node_map[] is filled already. - */ -u64 __init memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align) -{ - u64 addr; - addr = find_memory_core_early(nid, size, align, start, end); - if (addr != MEMBLOCK_ERROR) - return addr; - - /* Fallback, should already have start end within node range */ - return memblock_find_in_range(start, end, size, align); -} - -/* - * Finds an active region in the address range from start_pfn to last_pfn and - * returns its range in ei_startpfn and ei_endpfn for the memblock entry. - */ -static int __init memblock_x86_find_active_region(const struct memblock_region *ei, - unsigned long start_pfn, - unsigned long last_pfn, - unsigned long *ei_startpfn, - unsigned long *ei_endpfn) -{ - u64 align = PAGE_SIZE; - - *ei_startpfn = round_up(ei->base, align) >> PAGE_SHIFT; - *ei_endpfn = round_down(ei->base + ei->size, align) >> PAGE_SHIFT; - - /* Skip map entries smaller than a page */ - if (*ei_startpfn >= *ei_endpfn) - return 0; - - /* Skip if map is outside the node */ - if (*ei_endpfn <= start_pfn || *ei_startpfn >= last_pfn) - return 0; - - /* Check for overlaps */ - if (*ei_startpfn < start_pfn) - *ei_startpfn = start_pfn; - if (*ei_endpfn > last_pfn) - *ei_endpfn = last_pfn; - - return 1; -} - -/* Walk the memblock.memory map and register active regions within a node */ -void __init memblock_x86_register_active_regions(int nid, unsigned long start_pfn, - unsigned long last_pfn) -{ - unsigned long ei_startpfn; - unsigned long ei_endpfn; - struct memblock_region *r; - - for_each_memblock(memory, r) - if (memblock_x86_find_active_region(r, start_pfn, last_pfn, - &ei_startpfn, &ei_endpfn)) - add_active_range(nid, ei_startpfn, ei_endpfn); -} - -/* - * Find the hole size (in bytes) in the memory range. - * @start: starting address of the memory range to scan - * @end: ending address of the memory range to scan - */ -u64 __init memblock_x86_hole_size(u64 start, u64 end) -{ - unsigned long start_pfn = start >> PAGE_SHIFT; - unsigned long last_pfn = end >> PAGE_SHIFT; - unsigned long ei_startpfn, ei_endpfn, ram = 0; - struct memblock_region *r; - - for_each_memblock(memory, r) - if (memblock_x86_find_active_region(r, start_pfn, last_pfn, - &ei_startpfn, &ei_endpfn)) - ram += ei_endpfn - ei_startpfn; - - return end - start - ((u64)ram << PAGE_SHIFT); -} diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c index 92faf3a..c80b9fb 100644 --- a/arch/x86/mm/memtest.c +++ b/arch/x86/mm/memtest.c @@ -34,7 +34,7 @@ static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad) (unsigned long long) pattern, (unsigned long long) start_bad, (unsigned long long) end_bad); - memblock_x86_reserve_range(start_bad, end_bad, "BAD RAM"); + memblock_reserve(start_bad, end_bad - start_bad); } static void __init memtest(u64 pattern, u64 start_phys, u64 size) @@ -70,24 +70,19 @@ static void __init memtest(u64 pattern, u64 start_phys, u64 size) static void __init do_one_pass(u64 pattern, u64 start, u64 end) { - u64 size = 0; - - while (start < end) { - start = memblock_x86_find_in_range_size(start, &size, 1); - - /* done ? */ - if (start >= end) - break; - if (start + size > end) - size = end - start; - - printk(KERN_INFO " %010llx - %010llx pattern %016llx\n", - (unsigned long long) start, - (unsigned long long) start + size, - (unsigned long long) cpu_to_be64(pattern)); - memtest(pattern, start, size); - - start += size; + u64 i; + phys_addr_t this_start, this_end; + + for_each_free_mem_range(i, MAX_NUMNODES, &this_start, &this_end, NULL) { + this_start = clamp_t(phys_addr_t, this_start, start, end); + this_end = clamp_t(phys_addr_t, this_end, start, end); + if (this_start < this_end) { + printk(KERN_INFO " %010llx - %010llx pattern %016llx\n", + (unsigned long long)this_start, + (unsigned long long)this_end, + (unsigned long long)cpu_to_be64(pattern)); + memtest(pattern, this_start, this_end - this_start); + } } } diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index fbeaaf4..496f494 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -192,8 +192,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end) /* Initialize NODE_DATA for a node on the local memory */ static void __init setup_node_data(int nid, u64 start, u64 end) { - const u64 nd_low = PFN_PHYS(MAX_DMA_PFN); - const u64 nd_high = PFN_PHYS(max_pfn_mapped); const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE); bool remapped = false; u64 nd_pa; @@ -224,17 +222,12 @@ static void __init setup_node_data(int nid, u64 start, u64 end) nd_pa = __pa(nd); remapped = true; } else { - nd_pa = memblock_x86_find_in_range_node(nid, nd_low, nd_high, - nd_size, SMP_CACHE_BYTES); - if (nd_pa == MEMBLOCK_ERROR) - nd_pa = memblock_find_in_range(nd_low, nd_high, - nd_size, SMP_CACHE_BYTES); - if (nd_pa == MEMBLOCK_ERROR) { + nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid); + if (!nd_pa) { pr_err("Cannot find %zu bytes in node %d\n", nd_size, nid); return; } - memblock_x86_reserve_range(nd_pa, nd_pa + nd_size, "NODE_DATA"); nd = __va(nd_pa); } @@ -371,8 +364,7 @@ void __init numa_reset_distance(void) /* numa_distance could be 1LU marking allocation failure, test cnt */ if (numa_distance_cnt) - memblock_x86_free_range(__pa(numa_distance), - __pa(numa_distance) + size); + memblock_free(__pa(numa_distance), size); numa_distance_cnt = 0; numa_distance = NULL; /* enable table creation */ } @@ -395,13 +387,13 @@ static int __init numa_alloc_distance(void) phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), size, PAGE_SIZE); - if (phys == MEMBLOCK_ERROR) { + if (!phys) { pr_warning("NUMA: Warning: can't allocate distance table!\n"); /* don't retry until explicitly reset */ numa_distance = (void *)1LU; return -ENOMEM; } - memblock_x86_reserve_range(phys, phys + size, "NUMA DIST"); + memblock_reserve(phys, size); numa_distance = __va(phys); numa_distance_cnt = cnt; @@ -482,8 +474,8 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi) numaram = 0; } - e820ram = max_pfn - (memblock_x86_hole_size(0, - PFN_PHYS(max_pfn)) >> PAGE_SHIFT); + e820ram = max_pfn - absent_pages_in_range(0, max_pfn); + /* We seem to lose 3 pages somewhere. Allow 1M of slack. */ if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) { printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n", @@ -505,13 +497,10 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) if (WARN_ON(nodes_empty(node_possible_map))) return -EINVAL; - for (i = 0; i < mi->nr_blks; i++) - memblock_x86_register_active_regions(mi->blk[i].nid, - mi->blk[i].start >> PAGE_SHIFT, - mi->blk[i].end >> PAGE_SHIFT); - - /* for out of order entries */ - sort_node_map(); + for (i = 0; i < mi->nr_blks; i++) { + struct numa_memblk *mb = &mi->blk[i]; + memblock_set_node(mb->start, mb->end - mb->start, mb->nid); + } /* * If sections array is gonna be used for pfn -> nid mapping, check @@ -545,6 +534,8 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) setup_node_data(nid, start, end); } + /* Dump memblock with node info and return. */ + memblock_dump_all(); return 0; } @@ -582,7 +573,7 @@ static int __init numa_init(int (*init_func)(void)) nodes_clear(node_possible_map); nodes_clear(node_online_map); memset(&numa_meminfo, 0, sizeof(numa_meminfo)); - remove_all_active_ranges(); + WARN_ON(memblock_set_node(0, ULLONG_MAX, MAX_NUMNODES)); numa_reset_distance(); ret = init_func(); diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 3adebe7..534255a 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -199,23 +199,23 @@ void __init init_alloc_remap(int nid, u64 start, u64 end) /* allocate node memory and the lowmem remap area */ node_pa = memblock_find_in_range(start, end, size, LARGE_PAGE_BYTES); - if (node_pa == MEMBLOCK_ERROR) { + if (!node_pa) { pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n", size, nid); return; } - memblock_x86_reserve_range(node_pa, node_pa + size, "KVA RAM"); + memblock_reserve(node_pa, size); remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT, size, LARGE_PAGE_BYTES); - if (remap_pa == MEMBLOCK_ERROR) { + if (!remap_pa) { pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n", size, nid); - memblock_x86_free_range(node_pa, node_pa + size); + memblock_free(node_pa, size); return; } - memblock_x86_reserve_range(remap_pa, remap_pa + size, "KVA PG"); + memblock_reserve(remap_pa, size); remap_va = phys_to_virt(remap_pa); /* perform actual remap */ diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index dd27f40..92e2711 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -19,7 +19,7 @@ unsigned long __init numa_free_all_bootmem(void) for_each_online_node(i) pages += free_all_bootmem_node(NODE_DATA(i)); - pages += free_all_memory_core_early(MAX_NUMNODES); + pages += free_low_memory_core_early(MAX_NUMNODES); return pages; } diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index d0ed086..46db568 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -28,6 +28,16 @@ static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi) return -ENOENT; } +static u64 mem_hole_size(u64 start, u64 end) +{ + unsigned long start_pfn = PFN_UP(start); + unsigned long end_pfn = PFN_DOWN(end); + + if (start_pfn < end_pfn) + return PFN_PHYS(absent_pages_in_range(start_pfn, end_pfn)); + return 0; +} + /* * Sets up nid to range from @start to @end. The return value is -errno if * something went wrong, 0 otherwise. @@ -89,7 +99,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei, * Calculate target node size. x86_32 freaks on __udivdi3() so do * the division in ulong number of pages and convert back. */ - size = max_addr - addr - memblock_x86_hole_size(addr, max_addr); + size = max_addr - addr - mem_hole_size(addr, max_addr); size = PFN_PHYS((unsigned long)(size >> PAGE_SHIFT) / nr_nodes); /* @@ -135,8 +145,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei, * Continue to add memory to this fake node if its * non-reserved memory is less than the per-node size. */ - while (end - start - - memblock_x86_hole_size(start, end) < size) { + while (end - start - mem_hole_size(start, end) < size) { end += FAKE_NODE_MIN_SIZE; if (end > limit) { end = limit; @@ -150,7 +159,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei, * this one must extend to the boundary. */ if (end < dma32_end && dma32_end - end - - memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) + mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) end = dma32_end; /* @@ -158,8 +167,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei, * next node, this one must extend to the end of the * physical node. */ - if (limit - end - - memblock_x86_hole_size(end, limit) < size) + if (limit - end - mem_hole_size(end, limit) < size) end = limit; ret = emu_setup_memblk(ei, pi, nid++ % nr_nodes, @@ -180,7 +188,7 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size) { u64 end = start + size; - while (end - start - memblock_x86_hole_size(start, end) < size) { + while (end - start - mem_hole_size(start, end) < size) { end += FAKE_NODE_MIN_SIZE; if (end > max_addr) { end = max_addr; @@ -211,8 +219,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, * creates a uniform distribution of node sizes across the entire * machine (but not necessarily over physical nodes). */ - min_size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / - MAX_NUMNODES; + min_size = (max_addr - addr - mem_hole_size(addr, max_addr)) / MAX_NUMNODES; min_size = max(min_size, FAKE_NODE_MIN_SIZE); if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size) min_size = (min_size + FAKE_NODE_MIN_SIZE) & @@ -252,7 +259,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, * this one must extend to the boundary. */ if (end < dma32_end && dma32_end - end - - memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) + mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) end = dma32_end; /* @@ -260,8 +267,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, * next node, this one must extend to the end of the * physical node. */ - if (limit - end - - memblock_x86_hole_size(end, limit) < size) + if (limit - end - mem_hole_size(end, limit) < size) end = limit; ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES, @@ -351,11 +357,11 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), phys_size, PAGE_SIZE); - if (phys == MEMBLOCK_ERROR) { + if (!phys) { pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n"); goto no_emu; } - memblock_x86_reserve_range(phys, phys + phys_size, "TMP NUMA DIST"); + memblock_reserve(phys, phys_size); phys_dist = __va(phys); for (i = 0; i < numa_dist_cnt; i++) @@ -424,7 +430,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) /* free the copied physical distance table */ if (phys_dist) - memblock_x86_free_range(__pa(phys_dist), __pa(phys_dist) + phys_size); + memblock_free(__pa(phys_dist), phys_size); return; no_emu: diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index bfab3fa..7b65f75 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -568,8 +568,8 @@ cond_branch: f_offset = addrs[i + filter[i].jf] - addrs[i]; break; } if (filter[i].jt != 0) { - if (filter[i].jf) - t_offset += is_near(f_offset) ? 2 : 6; + if (filter[i].jf && f_offset) + t_offset += is_near(f_offset) ? 2 : 5; EMIT_COND_JMP(t_op, t_offset); if (filter[i].jf) EMIT_JMP(f_offset); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 37718f0..4a01967 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -352,8 +352,7 @@ void __init efi_memblock_x86_reserve_range(void) boot_params.efi_info.efi_memdesc_size; memmap.desc_version = boot_params.efi_info.efi_memdesc_version; memmap.desc_size = boot_params.efi_info.efi_memdesc_size; - memblock_x86_reserve_range(pmap, pmap + memmap.nr_map * memmap.desc_size, - "EFI memmap"); + memblock_reserve(pmap, memmap.nr_map * memmap.desc_size); } #if EFI_DEBUG @@ -397,16 +396,14 @@ void __init efi_reserve_boot_services(void) if ((start+size >= virt_to_phys(_text) && start <= virt_to_phys(_end)) || !e820_all_mapped(start, start+size, E820_RAM) || - memblock_x86_check_reserved_size(&start, &size, - 1<<EFI_PAGE_SHIFT)) { + memblock_is_region_reserved(start, size)) { /* Could not reserve, skip it */ md->num_pages = 0; memblock_dbg(PFX "Could not reserve boot range " "[0x%010llx-0x%010llx]\n", start, start+size-1); } else - memblock_x86_reserve_range(start, start+size, - "EFI Boot"); + memblock_reserve(start, size); } } diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 1f92865..12eb07b 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1215,8 +1215,6 @@ asmlinkage void __init xen_start_kernel(void) local_irq_disable(); early_boot_irqs_disabled = true; - memblock_init(); - xen_raw_console_write("mapping kernel into physical memory\n"); pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages); xen_ident_map_ISA(); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 87f6673..f4bf8aa 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1774,10 +1774,8 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, __xen_write_cr3(true, __pa(pgd)); xen_mc_issue(PARAVIRT_LAZY_CPU); - memblock_x86_reserve_range(__pa(xen_start_info->pt_base), - __pa(xen_start_info->pt_base + - xen_start_info->nr_pt_frames * PAGE_SIZE), - "XEN PAGETABLES"); + memblock_reserve(__pa(xen_start_info->pt_base), + xen_start_info->nr_pt_frames * PAGE_SIZE); return pgd; } @@ -1853,10 +1851,8 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, PFN_DOWN(__pa(initial_page_table))); xen_write_cr3(__pa(initial_page_table)); - memblock_x86_reserve_range(__pa(xen_start_info->pt_base), - __pa(xen_start_info->pt_base + - xen_start_info->nr_pt_frames * PAGE_SIZE), - "XEN PAGETABLES"); + memblock_reserve(__pa(xen_start_info->pt_base), + xen_start_info->nr_pt_frames * PAGE_SIZE)); return initial_page_table; } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index b2c7179..e03c636 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -75,7 +75,7 @@ static void __init xen_add_extra_mem(u64 start, u64 size) if (i == XEN_EXTRA_MEM_MAX_REGIONS) printk(KERN_WARNING "Warning: not enough extra memory regions\n"); - memblock_x86_reserve_range(start, start + size, "XEN EXTRA"); + memblock_reserve(start, size); xen_max_p2m_pfn = PFN_DOWN(start + size); @@ -311,9 +311,8 @@ char * __init xen_memory_setup(void) * - xen_start_info * See comment above "struct start_info" in <xen/interface/xen.h> */ - memblock_x86_reserve_range(__pa(xen_start_info->mfn_list), - __pa(xen_start_info->pt_base), - "XEN START INFO"); + memblock_reserve(__pa(xen_start_info->mfn_list), + xen_start_info->pt_base - xen_start_info->mfn_list); sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); diff --git a/block/blk-map.c b/block/blk-map.c index 164cd00..623e1cd 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -311,7 +311,7 @@ int blk_rq_map_kern(struct request_queue *q, struct request *rq, void *kbuf, if (IS_ERR(bio)) return PTR_ERR(bio); - if (rq_data_dir(rq) == WRITE) + if (!reading) bio->bi_rw |= REQ_WRITE; if (do_copy) diff --git a/block/blk-tag.c b/block/blk-tag.c index e74d6d1..4af6f5c 100644 --- a/block/blk-tag.c +++ b/block/blk-tag.c @@ -282,18 +282,9 @@ EXPORT_SYMBOL(blk_queue_resize_tags); void blk_queue_end_tag(struct request_queue *q, struct request *rq) { struct blk_queue_tag *bqt = q->queue_tags; - int tag = rq->tag; + unsigned tag = rq->tag; /* negative tags invalid */ - BUG_ON(tag == -1); - - if (unlikely(tag >= bqt->max_depth)) { - /* - * This can happen after tag depth has been reduced. - * But tag shouldn't be larger than real_max_depth. - */ - WARN_ON(tag >= bqt->real_max_depth); - return; - } + BUG_ON(tag >= bqt->real_max_depth); list_del_init(&rq->queuelist); rq->cmd_flags &= ~REQ_QUEUED; diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 4c12869..3548705 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -1655,6 +1655,8 @@ cfq_merged_requests(struct request_queue *q, struct request *rq, struct request *next) { struct cfq_queue *cfqq = RQ_CFQQ(rq); + struct cfq_data *cfqd = q->elevator->elevator_data; + /* * reposition in fifo if next is older than rq */ @@ -1669,6 +1671,16 @@ cfq_merged_requests(struct request_queue *q, struct request *rq, cfq_remove_request(next); cfq_blkiocg_update_io_merged_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(next), rq_is_sync(next)); + + cfqq = RQ_CFQQ(next); + /* + * all requests of this queue are merged to other queues, delete it + * from the service tree. If it's the active_queue, + * cfq_dispatch_requests() will choose to expire it or do idle + */ + if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY_ROOT(&cfqq->sort_list) && + cfqq != cfqd->active_queue) + cfq_del_cfqq_rr(cfqd, cfqq); } static int cfq_allow_merge(struct request_queue *q, struct request *rq, diff --git a/block/ioctl.c b/block/ioctl.c index ca939fc..d510c2a 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -180,6 +180,26 @@ int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode, EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl); /* + * Is it an unrecognized ioctl? The correct returns are either + * ENOTTY (final) or ENOIOCTLCMD ("I don't know this one, try a + * fallback"). ENOIOCTLCMD gets turned into ENOTTY by the ioctl + * code before returning. + * + * Confused drivers sometimes return EINVAL, which is wrong. It + * means "I understood the ioctl command, but the parameters to + * it were wrong". + * + * We should aim to just fix the broken drivers, the EINVAL case + * should go away. + */ +static inline int is_unrecognized_ioctl(int ret) +{ + return ret == -EINVAL || + ret == -ENOTTY || + ret == -ENOIOCTLCMD; +} + +/* * always keep this in sync with compat_blkdev_ioctl() */ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, @@ -196,8 +216,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, return -EACCES; ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg); - /* -EINVAL to handle old uncorrected drivers */ - if (ret != -EINVAL && ret != -ENOTTY) + if (!is_unrecognized_ioctl(ret)) return ret; fsync_bdev(bdev); @@ -206,8 +225,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKROSET: ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg); - /* -EINVAL to handle old uncorrected drivers */ - if (ret != -EINVAL && ret != -ENOTTY) + if (!is_unrecognized_ioctl(ret)) return ret; if (!capable(CAP_SYS_ADMIN)) return -EACCES; diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index 6bdedd7..cf047c4 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -820,7 +820,7 @@ config PATA_PLATFORM config PATA_OF_PLATFORM tristate "OpenFirmware platform device PATA support" - depends on PATA_PLATFORM && OF + depends on PATA_PLATFORM && OF && OF_IRQ help This option enables support for generic directly connected ATA devices commonly found on embedded systems with OpenFirmware diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c index 251acea..3991502 100644 --- a/drivers/base/cpu.c +++ b/drivers/base/cpu.c @@ -247,6 +247,13 @@ struct sys_device *get_cpu_sysdev(unsigned cpu) } EXPORT_SYMBOL_GPL(get_cpu_sysdev); +bool cpu_is_hotpluggable(unsigned cpu) +{ + struct sys_device *dev = get_cpu_sysdev(cpu); + return dev && container_of(dev, struct cpu, sysdev)->hotpluggable; +} +EXPORT_SYMBOL_GPL(cpu_is_hotpluggable); + int __init cpu_dev_init(void) { int err; diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c index c2917ffa..34767a6 100644 --- a/drivers/char/ipmi/ipmi_watchdog.c +++ b/drivers/char/ipmi/ipmi_watchdog.c @@ -139,6 +139,8 @@ #define IPMI_WDOG_SET_TIMER 0x24 #define IPMI_WDOG_GET_TIMER 0x25 +#define IPMI_WDOG_TIMER_NOT_INIT_RESP 0x80 + /* These are here until the real ones get into the watchdog.h interface. */ #ifndef WDIOC_GETTIMEOUT #define WDIOC_GETTIMEOUT _IOW(WATCHDOG_IOCTL_BASE, 20, int) @@ -596,6 +598,7 @@ static int ipmi_heartbeat(void) struct kernel_ipmi_msg msg; int rv; struct ipmi_system_interface_addr addr; + int timeout_retries = 0; if (ipmi_ignore_heartbeat) return 0; @@ -616,6 +619,7 @@ static int ipmi_heartbeat(void) mutex_lock(&heartbeat_lock); +restart: atomic_set(&heartbeat_tofree, 2); /* @@ -653,7 +657,33 @@ static int ipmi_heartbeat(void) /* Wait for the heartbeat to be sent. */ wait_for_completion(&heartbeat_wait); - if (heartbeat_recv_msg.msg.data[0] != 0) { + if (heartbeat_recv_msg.msg.data[0] == IPMI_WDOG_TIMER_NOT_INIT_RESP) { + timeout_retries++; + if (timeout_retries > 3) { + printk(KERN_ERR PFX ": Unable to restore the IPMI" + " watchdog's settings, giving up.\n"); + rv = -EIO; + goto out_unlock; + } + + /* + * The timer was not initialized, that means the BMC was + * probably reset and lost the watchdog information. Attempt + * to restore the timer's info. Note that we still hold + * the heartbeat lock, to keep a heartbeat from happening + * in this process, so must say no heartbeat to avoid a + * deadlock on this mutex. + */ + rv = ipmi_set_timeout(IPMI_SET_TIMEOUT_NO_HB); + if (rv) { + printk(KERN_ERR PFX ": Unable to send the command to" + " set the watchdog's settings, giving up.\n"); + goto out_unlock; + } + + /* We might need a new heartbeat, so do it now */ + goto restart; + } else if (heartbeat_recv_msg.msg.data[0] != 0) { /* * Got an error in the heartbeat response. It was already * reported in ipmi_wdog_msg_handler, but we should return @@ -662,6 +692,7 @@ static int ipmi_heartbeat(void) rv = -EINVAL; } +out_unlock: mutex_unlock(&heartbeat_lock); return rv; @@ -922,11 +953,15 @@ static struct miscdevice ipmi_wdog_miscdev = { static void ipmi_wdog_msg_handler(struct ipmi_recv_msg *msg, void *handler_data) { - if (msg->msg.data[0] != 0) { + if (msg->msg.cmd == IPMI_WDOG_RESET_TIMER && + msg->msg.data[0] == IPMI_WDOG_TIMER_NOT_INIT_RESP) + printk(KERN_INFO PFX "response: The IPMI controller appears" + " to have been reset, will attempt to reinitialize" + " the watchdog timer\n"); + else if (msg->msg.data[0] != 0) printk(KERN_ERR PFX "response: Error %x on cmd %x\n", msg->msg.data[0], msg->msg.cmd); - } ipmi_free_recv_msg(msg); } diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig index ab8f469..5a99bb3 100644 --- a/drivers/dma/Kconfig +++ b/drivers/dma/Kconfig @@ -124,7 +124,7 @@ config MV_XOR config MX3_IPU bool "MX3x Image Processing Unit support" - depends on ARCH_MX3 + depends on SOC_IMX31 ||Â SOC_IMX35 select DMA_ENGINE default y help @@ -216,7 +216,7 @@ config PCH_DMA config IMX_SDMA tristate "i.MX SDMA support" - depends on ARCH_MX25 || ARCH_MX3 || ARCH_MX5 + depends on ARCH_MX25 || SOC_IMX31 ||Â SOC_IMX35 || ARCH_MX5 select DMA_ENGINE help Support the i.MX SDMA engine. This engine is integrated into diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index c681dc1..b9da890 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -756,9 +756,9 @@ intel_enable_semaphores(struct drm_device *dev) if (i915_semaphores >= 0) return i915_semaphores; - /* Enable semaphores on SNB when IO remapping is off */ + /* Disable semaphores on SNB */ if (INTEL_INFO(dev)->gen == 6) - return !intel_iommu_enabled; + return 0; return 1; } diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index d809b03..daa5743 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -7922,13 +7922,11 @@ static bool intel_enable_rc6(struct drm_device *dev) return 0; /* - * Enable rc6 on Sandybridge if DMA remapping is disabled + * Disable rc6 on Sandybridge */ if (INTEL_INFO(dev)->gen == 6) { - DRM_DEBUG_DRIVER("Sandybridge: intel_iommu_enabled %s -- RC6 %sabled\n", - intel_iommu_enabled ? "true" : "false", - !intel_iommu_enabled ? "en" : "dis"); - return !intel_iommu_enabled; + DRM_DEBUG_DRIVER("Sandybridge: RC6 disabled\n"); + return 0; } DRM_DEBUG_DRIVER("RC6 enabled\n"); return 1; diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c index 5e00d16..92c9628 100644 --- a/drivers/gpu/drm/radeon/evergreen.c +++ b/drivers/gpu/drm/radeon/evergreen.c @@ -3276,6 +3276,18 @@ int evergreen_init(struct radeon_device *rdev) rdev->accel_working = false; } } + + /* Don't start up if the MC ucode is missing on BTC parts. + * The default clocks and voltages before the MC ucode + * is loaded are not suffient for advanced operations. + */ + if (ASIC_IS_DCE5(rdev)) { + if (!rdev->mc_fw && !(rdev->flags & RADEON_IS_IGP)) { + DRM_ERROR("radeon: MC ucode required for NI+.\n"); + return -EINVAL; + } + } + return 0; } diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index d24baf3..5082d17 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -2560,7 +2560,11 @@ void radeon_atombios_get_power_modes(struct radeon_device *rdev) rdev->pm.current_power_state_index = rdev->pm.default_power_state_index; rdev->pm.current_clock_mode_index = 0; - rdev->pm.current_vddc = rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.voltage; + if (rdev->pm.default_power_state_index >= 0) + rdev->pm.current_vddc = + rdev->pm.power_state[rdev->pm.default_power_state_index].clock_info[0].voltage.voltage; + else + rdev->pm.current_vddc = 0; } void radeon_atom_set_clock_gating(struct radeon_device *rdev, int enable) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 8cca91a..dc27970 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -390,6 +390,11 @@ extern int vmw_context_check(struct vmw_private *dev_priv, struct ttm_object_file *tfile, int id, struct vmw_resource **p_res); +extern int vmw_user_lookup_handle(struct vmw_private *dev_priv, + struct ttm_object_file *tfile, + uint32_t handle, + struct vmw_surface **out_surf, + struct vmw_dma_buffer **out_buf); extern void vmw_surface_res_free(struct vmw_resource *res); extern int vmw_surface_init(struct vmw_private *dev_priv, struct vmw_surface *srf, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c index 03bbc2a..a0c2f12 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c @@ -33,6 +33,7 @@ bool vmw_fifo_have_3d(struct vmw_private *dev_priv) { __le32 __iomem *fifo_mem = dev_priv->mmio_virt; uint32_t fifo_min, hwversion; + const struct vmw_fifo_state *fifo = &dev_priv->fifo; if (!(dev_priv->capabilities & SVGA_CAP_EXTENDED_FIFO)) return false; @@ -41,7 +42,12 @@ bool vmw_fifo_have_3d(struct vmw_private *dev_priv) if (fifo_min <= SVGA_FIFO_3D_HWVERSION * sizeof(unsigned int)) return false; - hwversion = ioread32(fifo_mem + SVGA_FIFO_3D_HWVERSION); + hwversion = ioread32(fifo_mem + + ((fifo->capabilities & + SVGA_FIFO_CAP_3D_HWVERSION_REVISED) ? + SVGA_FIFO_3D_HWVERSION_REVISED : + SVGA_FIFO_3D_HWVERSION)); + if (hwversion == 0) return false; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c index 5ff561d..66917c6 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c @@ -58,8 +58,14 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data, case DRM_VMW_PARAM_FIFO_HW_VERSION: { __le32 __iomem *fifo_mem = dev_priv->mmio_virt; - - param->value = ioread32(fifo_mem + SVGA_FIFO_3D_HWVERSION); + const struct vmw_fifo_state *fifo = &dev_priv->fifo; + + param->value = + ioread32(fifo_mem + + ((fifo->capabilities & + SVGA_FIFO_CAP_3D_HWVERSION_REVISED) ? + SVGA_FIFO_3D_HWVERSION_REVISED : + SVGA_FIFO_3D_HWVERSION)); break; } default: @@ -166,13 +172,7 @@ int vmw_present_ioctl(struct drm_device *dev, void *data, ret = -EINVAL; goto out_no_fb; } - vfb = vmw_framebuffer_to_vfb(obj_to_fb(obj)); - if (!vfb->dmabuf) { - DRM_ERROR("Framebuffer not dmabuf backed.\n"); - ret = -EINVAL; - goto out_no_fb; - } ret = ttm_read_lock(&vmaster->lock, true); if (unlikely(ret != 0)) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 37d4054..f94b33a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -31,6 +31,44 @@ /* Might need a hrtimer here? */ #define VMWGFX_PRESENT_RATE ((HZ / 60 > 0) ? HZ / 60 : 1) + +struct vmw_clip_rect { + int x1, x2, y1, y2; +}; + +/** + * Clip @num_rects number of @rects against @clip storing the + * results in @out_rects and the number of passed rects in @out_num. + */ +void vmw_clip_cliprects(struct drm_clip_rect *rects, + int num_rects, + struct vmw_clip_rect clip, + SVGASignedRect *out_rects, + int *out_num) +{ + int i, k; + + for (i = 0, k = 0; i < num_rects; i++) { + int x1 = max_t(int, clip.x1, rects[i].x1); + int y1 = max_t(int, clip.y1, rects[i].y1); + int x2 = min_t(int, clip.x2, rects[i].x2); + int y2 = min_t(int, clip.y2, rects[i].y2); + + if (x1 >= x2) + continue; + if (y1 >= y2) + continue; + + out_rects[k].left = x1; + out_rects[k].top = y1; + out_rects[k].right = x2; + out_rects[k].bottom = y2; + k++; + } + + *out_num = k; +} + void vmw_display_unit_cleanup(struct vmw_display_unit *du) { if (du->cursor_surface) @@ -82,6 +120,43 @@ int vmw_cursor_update_image(struct vmw_private *dev_priv, return 0; } +int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv, + struct vmw_dma_buffer *dmabuf, + u32 width, u32 height, + u32 hotspotX, u32 hotspotY) +{ + struct ttm_bo_kmap_obj map; + unsigned long kmap_offset; + unsigned long kmap_num; + void *virtual; + bool dummy; + int ret; + + kmap_offset = 0; + kmap_num = (width*height*4 + PAGE_SIZE - 1) >> PAGE_SHIFT; + + ret = ttm_bo_reserve(&dmabuf->base, true, false, false, 0); + if (unlikely(ret != 0)) { + DRM_ERROR("reserve failed\n"); + return -EINVAL; + } + + ret = ttm_bo_kmap(&dmabuf->base, kmap_offset, kmap_num, &map); + if (unlikely(ret != 0)) + goto err_unreserve; + + virtual = ttm_kmap_obj_virtual(&map, &dummy); + ret = vmw_cursor_update_image(dev_priv, virtual, width, height, + hotspotX, hotspotY); + + ttm_bo_kunmap(&map); +err_unreserve: + ttm_bo_unreserve(&dmabuf->base); + + return ret; +} + + void vmw_cursor_update_position(struct vmw_private *dev_priv, bool show, int x, int y) { @@ -110,24 +185,21 @@ int vmw_du_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv, return -EINVAL; if (handle) { - ret = vmw_user_surface_lookup_handle(dev_priv, tfile, - handle, &surface); - if (!ret) { - if (!surface->snooper.image) { - DRM_ERROR("surface not suitable for cursor\n"); - vmw_surface_unreference(&surface); - return -EINVAL; - } - } else { - ret = vmw_user_dmabuf_lookup(tfile, - handle, &dmabuf); - if (ret) { - DRM_ERROR("failed to find surface or dmabuf: %i\n", ret); - return -EINVAL; - } + ret = vmw_user_lookup_handle(dev_priv, tfile, + handle, &surface, &dmabuf); + if (ret) { + DRM_ERROR("failed to find surface or dmabuf: %i\n", ret); + return -EINVAL; } } + /* need to do this before taking down old image */ + if (surface && !surface->snooper.image) { + DRM_ERROR("surface not suitable for cursor\n"); + vmw_surface_unreference(&surface); + return -EINVAL; + } + /* takedown old cursor */ if (du->cursor_surface) { du->cursor_surface->snooper.crtc = NULL; @@ -146,36 +218,11 @@ int vmw_du_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv, vmw_cursor_update_image(dev_priv, surface->snooper.image, 64, 64, du->hotspot_x, du->hotspot_y); } else if (dmabuf) { - struct ttm_bo_kmap_obj map; - unsigned long kmap_offset; - unsigned long kmap_num; - void *virtual; - bool dummy; - /* vmw_user_surface_lookup takes one reference */ du->cursor_dmabuf = dmabuf; - kmap_offset = 0; - kmap_num = (64*64*4) >> PAGE_SHIFT; - - ret = ttm_bo_reserve(&dmabuf->base, true, false, false, 0); - if (unlikely(ret != 0)) { - DRM_ERROR("reserve failed\n"); - return -EINVAL; - } - - ret = ttm_bo_kmap(&dmabuf->base, kmap_offset, kmap_num, &map); - if (unlikely(ret != 0)) - goto err_unreserve; - - virtual = ttm_kmap_obj_virtual(&map, &dummy); - vmw_cursor_update_image(dev_priv, virtual, 64, 64, - du->hotspot_x, du->hotspot_y); - - ttm_bo_kunmap(&map); -err_unreserve: - ttm_bo_unreserve(&dmabuf->base); - + ret = vmw_cursor_update_dmabuf(dev_priv, dmabuf, width, height, + du->hotspot_x, du->hotspot_y); } else { vmw_cursor_update_position(dev_priv, false, 0, 0); return 0; @@ -377,8 +424,9 @@ static int do_surface_dirty_sou(struct vmw_private *dev_priv, struct drm_clip_rect *clips, unsigned num_clips, int inc) { - struct drm_clip_rect *clips_ptr; struct vmw_display_unit *units[VMWGFX_NUM_DISPLAY_UNITS]; + struct drm_clip_rect *clips_ptr; + struct drm_clip_rect *tmp; struct drm_crtc *crtc; size_t fifo_size; int i, num_units; @@ -391,7 +439,6 @@ static int do_surface_dirty_sou(struct vmw_private *dev_priv, } *cmd; SVGASignedRect *blits; - num_units = 0; list_for_each_entry(crtc, &dev_priv->dev->mode_config.crtc_list, head) { @@ -402,13 +449,24 @@ static int do_surface_dirty_sou(struct vmw_private *dev_priv, BUG_ON(!clips || !num_clips); + tmp = kzalloc(sizeof(*tmp) * num_clips, GFP_KERNEL); + if (unlikely(tmp == NULL)) { + DRM_ERROR("Temporary cliprect memory alloc failed.\n"); + return -ENOMEM; + } + fifo_size = sizeof(*cmd) + sizeof(SVGASignedRect) * num_clips; cmd = kzalloc(fifo_size, GFP_KERNEL); if (unlikely(cmd == NULL)) { DRM_ERROR("Temporary fifo memory alloc failed.\n"); - return -ENOMEM; + ret = -ENOMEM; + goto out_free_tmp; } + /* setup blits pointer */ + blits = (SVGASignedRect *)&cmd[1]; + + /* initial clip region */ left = clips->x1; right = clips->x2; top = clips->y1; @@ -434,45 +492,60 @@ static int do_surface_dirty_sou(struct vmw_private *dev_priv, cmd->body.srcRect.bottom = bottom; clips_ptr = clips; - blits = (SVGASignedRect *)&cmd[1]; for (i = 0; i < num_clips; i++, clips_ptr += inc) { - blits[i].left = clips_ptr->x1 - left; - blits[i].right = clips_ptr->x2 - left; - blits[i].top = clips_ptr->y1 - top; - blits[i].bottom = clips_ptr->y2 - top; + tmp[i].x1 = clips_ptr->x1 - left; + tmp[i].x2 = clips_ptr->x2 - left; + tmp[i].y1 = clips_ptr->y1 - top; + tmp[i].y2 = clips_ptr->y2 - top; } /* do per unit writing, reuse fifo for each */ for (i = 0; i < num_units; i++) { struct vmw_display_unit *unit = units[i]; - int clip_x1 = left - unit->crtc.x; - int clip_y1 = top - unit->crtc.y; - int clip_x2 = right - unit->crtc.x; - int clip_y2 = bottom - unit->crtc.y; + struct vmw_clip_rect clip; + int num; + + clip.x1 = left - unit->crtc.x; + clip.y1 = top - unit->crtc.y; + clip.x2 = right - unit->crtc.x; + clip.y2 = bottom - unit->crtc.y; /* skip any crtcs that misses the clip region */ - if (clip_x1 >= unit->crtc.mode.hdisplay || - clip_y1 >= unit->crtc.mode.vdisplay || - clip_x2 <= 0 || clip_y2 <= 0) + if (clip.x1 >= unit->crtc.mode.hdisplay || + clip.y1 >= unit->crtc.mode.vdisplay || + clip.x2 <= 0 || clip.y2 <= 0) continue; + /* + * In order for the clip rects to be correctly scaled + * the src and dest rects needs to be the same size. + */ + cmd->body.destRect.left = clip.x1; + cmd->body.destRect.right = clip.x2; + cmd->body.destRect.top = clip.y1; + cmd->body.destRect.bottom = clip.y2; + + /* create a clip rect of the crtc in dest coords */ + clip.x2 = unit->crtc.mode.hdisplay - clip.x1; + clip.y2 = unit->crtc.mode.vdisplay - clip.y1; + clip.x1 = 0 - clip.x1; + clip.y1 = 0 - clip.y1; + /* need to reset sid as it is changed by execbuf */ cmd->body.srcImage.sid = cpu_to_le32(framebuffer->user_handle); - cmd->body.destScreenId = unit->unit; - /* - * The blit command is a lot more resilient then the - * readback command when it comes to clip rects. So its - * okay to go out of bounds. - */ + /* clip and write blits to cmd stream */ + vmw_clip_cliprects(tmp, num_clips, clip, blits, &num); - cmd->body.destRect.left = clip_x1; - cmd->body.destRect.right = clip_x2; - cmd->body.destRect.top = clip_y1; - cmd->body.destRect.bottom = clip_y2; + /* if no cliprects hit skip this */ + if (num == 0) + continue; + /* recalculate package length */ + fifo_size = sizeof(*cmd) + sizeof(SVGASignedRect) * num; + cmd->header.size = cpu_to_le32(fifo_size - sizeof(cmd->header)); ret = vmw_execbuf_process(file_priv, dev_priv, NULL, cmd, fifo_size, 0, NULL); @@ -480,7 +553,10 @@ static int do_surface_dirty_sou(struct vmw_private *dev_priv, break; } + kfree(cmd); +out_free_tmp: + kfree(tmp); return ret; } @@ -556,6 +632,10 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv, * Sanity checks. */ + /* Surface must be marked as a scanout. */ + if (unlikely(!surface->scanout)) + return -EINVAL; + if (unlikely(surface->mip_levels[0] != 1 || surface->num_sizes != 1 || surface->sizes[0].width < mode_cmd->width || @@ -782,6 +862,7 @@ static int do_dmabuf_dirty_sou(struct drm_file *file_priv, int clip_y1 = clips_ptr->y1 - unit->crtc.y; int clip_x2 = clips_ptr->x2 - unit->crtc.x; int clip_y2 = clips_ptr->y2 - unit->crtc.y; + int move_x, move_y; /* skip any crtcs that misses the clip region */ if (clip_x1 >= unit->crtc.mode.hdisplay || @@ -789,12 +870,21 @@ static int do_dmabuf_dirty_sou(struct drm_file *file_priv, clip_x2 <= 0 || clip_y2 <= 0) continue; + /* clip size to crtc size */ + clip_x2 = min_t(int, clip_x2, unit->crtc.mode.hdisplay); + clip_y2 = min_t(int, clip_y2, unit->crtc.mode.vdisplay); + + /* translate both src and dest to bring clip into screen */ + move_x = min_t(int, clip_x1, 0); + move_y = min_t(int, clip_y1, 0); + + /* actual translate done here */ blits[hit_num].header = SVGA_CMD_BLIT_GMRFB_TO_SCREEN; blits[hit_num].body.destScreenId = unit->unit; - blits[hit_num].body.srcOrigin.x = clips_ptr->x1; - blits[hit_num].body.srcOrigin.y = clips_ptr->y1; - blits[hit_num].body.destRect.left = clip_x1; - blits[hit_num].body.destRect.top = clip_y1; + blits[hit_num].body.srcOrigin.x = clips_ptr->x1 - move_x; + blits[hit_num].body.srcOrigin.y = clips_ptr->y1 - move_y; + blits[hit_num].body.destRect.left = clip_x1 - move_x; + blits[hit_num].body.destRect.top = clip_y1 - move_y; blits[hit_num].body.destRect.right = clip_x2; blits[hit_num].body.destRect.bottom = clip_y2; hit_num++; @@ -1003,7 +1093,6 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev, struct vmw_surface *surface = NULL; struct vmw_dma_buffer *bo = NULL; struct ttm_base_object *user_obj; - u64 required_size; int ret; /** @@ -1012,8 +1101,9 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev, * requested framebuffer. */ - required_size = mode_cmd->pitch * mode_cmd->height; - if (unlikely(required_size > (u64) dev_priv->vram_size)) { + if (!vmw_kms_validate_mode_vram(dev_priv, + mode_cmd->pitch, + mode_cmd->height)) { DRM_ERROR("VRAM size is too small for requested mode.\n"); return ERR_PTR(-ENOMEM); } @@ -1033,46 +1123,29 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev, return ERR_PTR(-ENOENT); } - /** - * End conditioned code. - */ - - ret = vmw_user_surface_lookup_handle(dev_priv, tfile, - mode_cmd->handle, &surface); + /* returns either a dmabuf or surface */ + ret = vmw_user_lookup_handle(dev_priv, tfile, + mode_cmd->handle, + &surface, &bo); if (ret) - goto try_dmabuf; - - if (!surface->scanout) - goto err_not_scanout; - - ret = vmw_kms_new_framebuffer_surface(dev_priv, file_priv, surface, - &vfb, mode_cmd); - - /* vmw_user_surface_lookup takes one ref so does new_fb */ - vmw_surface_unreference(&surface); - - if (ret) { - DRM_ERROR("failed to create vmw_framebuffer: %i\n", ret); - ttm_base_object_unref(&user_obj); - return ERR_PTR(ret); - } else - vfb->user_obj = user_obj; - return &vfb->base; - -try_dmabuf: - DRM_INFO("%s: trying buffer\n", __func__); - - ret = vmw_user_dmabuf_lookup(tfile, mode_cmd->handle, &bo); - if (ret) { - DRM_ERROR("failed to find buffer: %i\n", ret); - return ERR_PTR(-ENOENT); - } - - ret = vmw_kms_new_framebuffer_dmabuf(dev_priv, bo, &vfb, - mode_cmd); + goto err_out; + + /* Create the new framebuffer depending one what we got back */ + if (bo) + ret = vmw_kms_new_framebuffer_dmabuf(dev_priv, bo, &vfb, + mode_cmd); + else if (surface) + ret = vmw_kms_new_framebuffer_surface(dev_priv, file_priv, + surface, &vfb, mode_cmd); + else + BUG(); - /* vmw_user_dmabuf_lookup takes one ref so does new_fb */ - vmw_dmabuf_unreference(&bo); +err_out: + /* vmw_user_lookup_handle takes one ref so does new_fb */ + if (bo) + vmw_dmabuf_unreference(&bo); + if (surface) + vmw_surface_unreference(&surface); if (ret) { DRM_ERROR("failed to create vmw_framebuffer: %i\n", ret); @@ -1082,14 +1155,6 @@ try_dmabuf: vfb->user_obj = user_obj; return &vfb->base; - -err_not_scanout: - DRM_ERROR("surface not marked as scanout\n"); - /* vmw_user_surface_lookup takes one ref */ - vmw_surface_unreference(&surface); - ttm_base_object_unref(&user_obj); - - return ERR_PTR(-EINVAL); } static struct drm_mode_config_funcs vmw_kms_funcs = { @@ -1106,10 +1171,12 @@ int vmw_kms_present(struct vmw_private *dev_priv, uint32_t num_clips) { struct vmw_display_unit *units[VMWGFX_NUM_DISPLAY_UNITS]; + struct drm_clip_rect *tmp; struct drm_crtc *crtc; size_t fifo_size; int i, k, num_units; int ret = 0; /* silence warning */ + int left, right, top, bottom; struct { SVGA3dCmdHeader header; @@ -1127,60 +1194,95 @@ int vmw_kms_present(struct vmw_private *dev_priv, BUG_ON(surface == NULL); BUG_ON(!clips || !num_clips); + tmp = kzalloc(sizeof(*tmp) * num_clips, GFP_KERNEL); + if (unlikely(tmp == NULL)) { + DRM_ERROR("Temporary cliprect memory alloc failed.\n"); + return -ENOMEM; + } + fifo_size = sizeof(*cmd) + sizeof(SVGASignedRect) * num_clips; cmd = kmalloc(fifo_size, GFP_KERNEL); if (unlikely(cmd == NULL)) { DRM_ERROR("Failed to allocate temporary fifo memory.\n"); - return -ENOMEM; + ret = -ENOMEM; + goto out_free_tmp; + } + + left = clips->x; + right = clips->x + clips->w; + top = clips->y; + bottom = clips->y + clips->h; + + for (i = 1; i < num_clips; i++) { + left = min_t(int, left, (int)clips[i].x); + right = max_t(int, right, (int)clips[i].x + clips[i].w); + top = min_t(int, top, (int)clips[i].y); + bottom = max_t(int, bottom, (int)clips[i].y + clips[i].h); } /* only need to do this once */ memset(cmd, 0, fifo_size); cmd->header.id = cpu_to_le32(SVGA_3D_CMD_BLIT_SURFACE_TO_SCREEN); - cmd->header.size = cpu_to_le32(fifo_size - sizeof(cmd->header)); - - cmd->body.srcRect.left = 0; - cmd->body.srcRect.right = surface->sizes[0].width; - cmd->body.srcRect.top = 0; - cmd->body.srcRect.bottom = surface->sizes[0].height; blits = (SVGASignedRect *)&cmd[1]; + + cmd->body.srcRect.left = left; + cmd->body.srcRect.right = right; + cmd->body.srcRect.top = top; + cmd->body.srcRect.bottom = bottom; + for (i = 0; i < num_clips; i++) { - blits[i].left = clips[i].x; - blits[i].right = clips[i].x + clips[i].w; - blits[i].top = clips[i].y; - blits[i].bottom = clips[i].y + clips[i].h; + tmp[i].x1 = clips[i].x - left; + tmp[i].x2 = clips[i].x + clips[i].w - left; + tmp[i].y1 = clips[i].y - top; + tmp[i].y2 = clips[i].y + clips[i].h - top; } for (k = 0; k < num_units; k++) { struct vmw_display_unit *unit = units[k]; - int clip_x1 = destX - unit->crtc.x; - int clip_y1 = destY - unit->crtc.y; - int clip_x2 = clip_x1 + surface->sizes[0].width; - int clip_y2 = clip_y1 + surface->sizes[0].height; + struct vmw_clip_rect clip; + int num; + + clip.x1 = left + destX - unit->crtc.x; + clip.y1 = top + destY - unit->crtc.y; + clip.x2 = right + destX - unit->crtc.x; + clip.y2 = bottom + destY - unit->crtc.y; /* skip any crtcs that misses the clip region */ - if (clip_x1 >= unit->crtc.mode.hdisplay || - clip_y1 >= unit->crtc.mode.vdisplay || - clip_x2 <= 0 || clip_y2 <= 0) + if (clip.x1 >= unit->crtc.mode.hdisplay || + clip.y1 >= unit->crtc.mode.vdisplay || + clip.x2 <= 0 || clip.y2 <= 0) continue; + /* + * In order for the clip rects to be correctly scaled + * the src and dest rects needs to be the same size. + */ + cmd->body.destRect.left = clip.x1; + cmd->body.destRect.right = clip.x2; + cmd->body.destRect.top = clip.y1; + cmd->body.destRect.bottom = clip.y2; + + /* create a clip rect of the crtc in dest coords */ + clip.x2 = unit->crtc.mode.hdisplay - clip.x1; + clip.y2 = unit->crtc.mode.vdisplay - clip.y1; + clip.x1 = 0 - clip.x1; + clip.y1 = 0 - clip.y1; + /* need to reset sid as it is changed by execbuf */ cmd->body.srcImage.sid = sid; - cmd->body.destScreenId = unit->unit; - /* - * The blit command is a lot more resilient then the - * readback command when it comes to clip rects. So its - * okay to go out of bounds. - */ + /* clip and write blits to cmd stream */ + vmw_clip_cliprects(tmp, num_clips, clip, blits, &num); - cmd->body.destRect.left = clip_x1; - cmd->body.destRect.right = clip_x2; - cmd->body.destRect.top = clip_y1; - cmd->body.destRect.bottom = clip_y2; + /* if no cliprects hit skip this */ + if (num == 0) + continue; + /* recalculate package length */ + fifo_size = sizeof(*cmd) + sizeof(SVGASignedRect) * num; + cmd->header.size = cpu_to_le32(fifo_size - sizeof(cmd->header)); ret = vmw_execbuf_process(file_priv, dev_priv, NULL, cmd, fifo_size, 0, NULL); @@ -1189,6 +1291,8 @@ int vmw_kms_present(struct vmw_private *dev_priv, } kfree(cmd); +out_free_tmp: + kfree(tmp); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h index af8e6e5..e1cb855 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h @@ -62,9 +62,14 @@ struct vmw_framebuffer { int vmw_cursor_update_image(struct vmw_private *dev_priv, u32 *image, u32 width, u32 height, u32 hotspotX, u32 hotspotY); +int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv, + struct vmw_dma_buffer *dmabuf, + u32 width, u32 height, + u32 hotspotX, u32 hotspotY); void vmw_cursor_update_position(struct vmw_private *dev_priv, bool show, int x, int y); + /** * Base class display unit. * diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c index 90c5e39..8f8dbd4 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c @@ -74,9 +74,10 @@ static int vmw_ldu_commit_list(struct vmw_private *dev_priv) { struct vmw_legacy_display *lds = dev_priv->ldu_priv; struct vmw_legacy_display_unit *entry; + struct vmw_display_unit *du = NULL; struct drm_framebuffer *fb = NULL; struct drm_crtc *crtc = NULL; - int i = 0; + int i = 0, ret; /* If there is no display topology the host just assumes * that the guest will set the same layout as the host. @@ -129,6 +130,25 @@ static int vmw_ldu_commit_list(struct vmw_private *dev_priv) lds->last_num_active = lds->num_active; + + /* Find the first du with a cursor. */ + list_for_each_entry(entry, &lds->active, active) { + du = &entry->base; + + if (!du->cursor_dmabuf) + continue; + + ret = vmw_cursor_update_dmabuf(dev_priv, + du->cursor_dmabuf, + 64, 64, + du->hotspot_x, + du->hotspot_y); + if (ret == 0) + break; + + DRM_ERROR("Could not update cursor image\n"); + } + return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 86c5e4c..1c7f09e 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -1190,6 +1190,29 @@ void vmw_resource_unreserve(struct list_head *list) write_unlock(lock); } +/** + * Helper function that looks either a surface or dmabuf. + * + * The pointer this pointed at by out_surf and out_buf needs to be null. + */ +int vmw_user_lookup_handle(struct vmw_private *dev_priv, + struct ttm_object_file *tfile, + uint32_t handle, + struct vmw_surface **out_surf, + struct vmw_dma_buffer **out_buf) +{ + int ret; + + BUG_ON(*out_surf || *out_buf); + + ret = vmw_user_surface_lookup_handle(dev_priv, tfile, handle, out_surf); + if (!ret) + return 0; + + ret = vmw_user_dmabuf_lookup(tfile, handle, out_buf); + return ret; +} + int vmw_user_surface_lookup_handle(struct vmw_private *dev_priv, struct ttm_object_file *tfile, diff --git a/drivers/i2c/busses/i2c-eg20t.c b/drivers/i2c/busses/i2c-eg20t.c index 8cebef4..18936ac 100644 --- a/drivers/i2c/busses/i2c-eg20t.c +++ b/drivers/i2c/busses/i2c-eg20t.c @@ -893,6 +893,13 @@ static int __devinit pch_i2c_probe(struct pci_dev *pdev, /* Set the number of I2C channel instance */ adap_info->ch_num = id->driver_data; + ret = request_irq(pdev->irq, pch_i2c_handler, IRQF_SHARED, + KBUILD_MODNAME, adap_info); + if (ret) { + pch_pci_err(pdev, "request_irq FAILED\n"); + goto err_request_irq; + } + for (i = 0; i < adap_info->ch_num; i++) { pch_adap = &adap_info->pch_data[i].pch_adapter; adap_info->pch_i2c_suspended = false; @@ -910,28 +917,23 @@ static int __devinit pch_i2c_probe(struct pci_dev *pdev, pch_adap->dev.parent = &pdev->dev; + pch_i2c_init(&adap_info->pch_data[i]); ret = i2c_add_adapter(pch_adap); if (ret) { pch_pci_err(pdev, "i2c_add_adapter[ch:%d] FAILED\n", i); - goto err_i2c_add_adapter; + goto err_add_adapter; } - - pch_i2c_init(&adap_info->pch_data[i]); - } - ret = request_irq(pdev->irq, pch_i2c_handler, IRQF_SHARED, - KBUILD_MODNAME, adap_info); - if (ret) { - pch_pci_err(pdev, "request_irq FAILED\n"); - goto err_i2c_add_adapter; } pci_set_drvdata(pdev, adap_info); pch_pci_dbg(pdev, "returns %d.\n", ret); return 0; -err_i2c_add_adapter: +err_add_adapter: for (j = 0; j < i; j++) i2c_del_adapter(&adap_info->pch_data[j].pch_adapter); + free_irq(pdev->irq, adap_info); +err_request_irq: pci_iounmap(pdev, base_addr); err_pci_iomap: pci_release_regions(pdev); diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c index a43d002..fa23faa 100644 --- a/drivers/i2c/busses/i2c-omap.c +++ b/drivers/i2c/busses/i2c-omap.c @@ -1047,13 +1047,14 @@ omap_i2c_probe(struct platform_device *pdev) * size. This is to ensure that we can handle the status on int * call back latencies. */ - if (dev->rev >= OMAP_I2C_REV_ON_3530_4430) { - dev->fifo_size = 0; + + dev->fifo_size = (dev->fifo_size / 2); + + if (dev->rev >= OMAP_I2C_REV_ON_3530_4430) dev->b_hw = 0; /* Disable hardware fixes */ - } else { - dev->fifo_size = (dev->fifo_size / 2); + else dev->b_hw = 1; /* Enable hardware fixes */ - } + /* calculate wakeup latency constraint for MPU */ if (dev->set_mpu_wkup_lat != NULL) dev->latency = (1000000 * dev->fifo_size) / diff --git a/drivers/i2c/busses/i2c-s3c2410.c b/drivers/i2c/busses/i2c-s3c2410.c index 2754cef..4c17180 100644 --- a/drivers/i2c/busses/i2c-s3c2410.c +++ b/drivers/i2c/busses/i2c-s3c2410.c @@ -534,6 +534,7 @@ static int s3c24xx_i2c_doxfer(struct s3c24xx_i2c *i2c, /* first, try busy waiting briefly */ do { + cpu_relax(); iicstat = readl(i2c->regs + S3C2410_IICSTAT); } while ((iicstat & S3C2410_IICSTAT_START) && --spins); @@ -786,7 +787,7 @@ static void s3c24xx_i2c_dt_gpio_free(struct s3c24xx_i2c *i2c) #else static int s3c24xx_i2c_parse_dt_gpio(struct s3c24xx_i2c *i2c) { - return -EINVAL; + return 0; } static void s3c24xx_i2c_dt_gpio_free(struct s3c24xx_i2c *i2c) diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c index 75ff821..d0d4aa9 100644 --- a/drivers/infiniband/core/cma.c +++ b/drivers/infiniband/core/cma.c @@ -2513,6 +2513,9 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv, req.private_data_len = sizeof(struct cma_hdr) + conn_param->private_data_len; + if (req.private_data_len < conn_param->private_data_len) + return -EINVAL; + req.private_data = kzalloc(req.private_data_len, GFP_ATOMIC); if (!req.private_data) return -ENOMEM; @@ -2562,6 +2565,9 @@ static int cma_connect_ib(struct rdma_id_private *id_priv, memset(&req, 0, sizeof req); offset = cma_user_data_offset(id_priv->id.ps); req.private_data_len = offset + conn_param->private_data_len; + if (req.private_data_len < conn_param->private_data_len) + return -EINVAL; + private_data = kzalloc(req.private_data_len, GFP_ATOMIC); if (!private_data) return -ENOMEM; diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 77f3dbc..18836cd 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1244,7 +1244,8 @@ err_reg: err_counter: for (; i; --i) - mlx4_counter_free(ibdev->dev, ibdev->counters[i - 1]); + if (ibdev->counters[i - 1] != -1) + mlx4_counter_free(ibdev->dev, ibdev->counters[i - 1]); err_map: iounmap(ibdev->uar_map); @@ -1275,7 +1276,8 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr) } iounmap(ibdev->uar_map); for (p = 0; p < ibdev->num_ports; ++p) - mlx4_counter_free(ibdev->dev, ibdev->counters[p]); + if (ibdev->counters[p] != -1) + mlx4_counter_free(ibdev->dev, ibdev->counters[p]); mlx4_foreach_port(p, dev, MLX4_PORT_TYPE_IB) mlx4_CLOSE_PORT(dev, p); diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c index 574600e..a740324 100644 --- a/drivers/infiniband/hw/qib/qib_file_ops.c +++ b/drivers/infiniband/hw/qib/qib_file_ops.c @@ -1285,7 +1285,7 @@ static int setup_ctxt(struct qib_pportdata *ppd, int ctxt, strlcpy(rcd->comm, current->comm, sizeof(rcd->comm)); ctxt_fp(fp) = rcd; qib_stats.sps_ctxts++; - dd->freectxts++; + dd->freectxts--; ret = 0; goto bail; @@ -1794,7 +1794,7 @@ static int qib_close(struct inode *in, struct file *fp) if (dd->pageshadow) unlock_expected_tids(rcd); qib_stats.sps_ctxts--; - dd->freectxts--; + dd->freectxts++; } mutex_unlock(&qib_mutex); diff --git a/drivers/input/misc/cma3000_d0x.c b/drivers/input/misc/cma3000_d0x.c index 80793f1..06517e6 100644 --- a/drivers/input/misc/cma3000_d0x.c +++ b/drivers/input/misc/cma3000_d0x.c @@ -115,8 +115,8 @@ static void decode_mg(struct cma3000_accl_data *data, int *datax, static irqreturn_t cma3000_thread_irq(int irq, void *dev_id) { struct cma3000_accl_data *data = dev_id; - int datax, datay, dataz; - u8 ctrl, mode, range, intr_status; + int datax, datay, dataz, intr_status; + u8 ctrl, mode, range; intr_status = CMA3000_READ(data, CMA3000_INTSTATUS, "interrupt status"); if (intr_status < 0) diff --git a/drivers/input/mouse/sentelic.c b/drivers/input/mouse/sentelic.c index c5b12d2..86d6f39 100644 --- a/drivers/input/mouse/sentelic.c +++ b/drivers/input/mouse/sentelic.c @@ -2,7 +2,7 @@ * Finger Sensing Pad PS/2 mouse driver. * * Copyright (C) 2005-2007 Asia Vital Components Co., Ltd. - * Copyright (C) 2005-2010 Tai-hwa Liang, Sentelic Corporation. + * Copyright (C) 2005-2011 Tai-hwa Liang, Sentelic Corporation. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -162,7 +162,7 @@ static int fsp_reg_write(struct psmouse *psmouse, int reg_addr, int reg_val) ps2_sendbyte(ps2dev, v, FSP_CMD_TIMEOUT2); if (ps2_sendbyte(ps2dev, 0xf3, FSP_CMD_TIMEOUT) < 0) - return -1; + goto out; if ((v = fsp_test_invert_cmd(reg_val)) != reg_val) { /* inversion is required */ @@ -261,7 +261,7 @@ static int fsp_page_reg_write(struct psmouse *psmouse, int reg_val) ps2_sendbyte(ps2dev, 0x88, FSP_CMD_TIMEOUT2); if (ps2_sendbyte(ps2dev, 0xf3, FSP_CMD_TIMEOUT) < 0) - return -1; + goto out; if ((v = fsp_test_invert_cmd(reg_val)) != reg_val) { ps2_sendbyte(ps2dev, 0x47, FSP_CMD_TIMEOUT2); @@ -309,7 +309,7 @@ static int fsp_get_buttons(struct psmouse *psmouse, int *btn) }; int val; - if (fsp_reg_read(psmouse, FSP_REG_TMOD_STATUS1, &val) == -1) + if (fsp_reg_read(psmouse, FSP_REG_TMOD_STATUS, &val) == -1) return -EIO; *btn = buttons[(val & 0x30) >> 4]; diff --git a/drivers/input/mouse/sentelic.h b/drivers/input/mouse/sentelic.h index ed1395a..2e4af24 100644 --- a/drivers/input/mouse/sentelic.h +++ b/drivers/input/mouse/sentelic.h @@ -2,7 +2,7 @@ * Finger Sensing Pad PS/2 mouse driver. * * Copyright (C) 2005-2007 Asia Vital Components Co., Ltd. - * Copyright (C) 2005-2009 Tai-hwa Liang, Sentelic Corporation. + * Copyright (C) 2005-2011 Tai-hwa Liang, Sentelic Corporation. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -33,6 +33,7 @@ /* Finger-sensing Pad control registers */ #define FSP_REG_SYSCTL1 0x10 #define FSP_BIT_EN_REG_CLK BIT(5) +#define FSP_REG_TMOD_STATUS 0x20 #define FSP_REG_OPC_QDOWN 0x31 #define FSP_BIT_EN_OPC_TAG BIT(7) #define FSP_REG_OPTZ_XLO 0x34 diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index c080b82..a6dcd18 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -24,6 +24,7 @@ */ #include <linux/module.h> +#include <linux/delay.h> #include <linux/dmi.h> #include <linux/input/mt.h> #include <linux/serio.h> @@ -1220,6 +1221,16 @@ static int synaptics_reconnect(struct psmouse *psmouse) do { psmouse_reset(psmouse); + if (retry) { + /* + * On some boxes, right after resuming, the touchpad + * needs some time to finish initializing (I assume + * it needs time to calibrate) and start responding + * to Synaptics-specific queries, so let's wait a + * bit. + */ + ssleep(1); + } error = synaptics_detect(psmouse, 0); } while (error && ++retry < 3); diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c index da0d876..2ee47d0 100644 --- a/drivers/input/tablet/wacom_wac.c +++ b/drivers/input/tablet/wacom_wac.c @@ -1470,6 +1470,9 @@ static const struct wacom_features wacom_features_0xE3 = static const struct wacom_features wacom_features_0xE6 = { "Wacom ISDv4 E6", WACOM_PKGLEN_TPC2FG, 27760, 15694, 255, 0, TABLETPC2FG, WACOM_INTUOS_RES, WACOM_INTUOS_RES }; +static const struct wacom_features wacom_features_0xEC = + { "Wacom ISDv4 EC", WACOM_PKGLEN_GRAPHIRE, 25710, 14500, 255, + 0, TABLETPC, WACOM_INTUOS_RES, WACOM_INTUOS_RES }; static const struct wacom_features wacom_features_0x47 = { "Wacom Intuos2 6x8", WACOM_PKGLEN_INTUOS, 20320, 16240, 1023, 31, INTUOS, WACOM_INTUOS_RES, WACOM_INTUOS_RES }; @@ -1611,6 +1614,7 @@ const struct usb_device_id wacom_ids[] = { { USB_DEVICE_WACOM(0xE2) }, { USB_DEVICE_WACOM(0xE3) }, { USB_DEVICE_WACOM(0xE6) }, + { USB_DEVICE_WACOM(0xEC) }, { USB_DEVICE_WACOM(0x47) }, { USB_DEVICE_LENOVO(0x6004) }, { } diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index bdc447f..31053a9 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -41,6 +41,7 @@ #include <linux/tboot.h> #include <linux/dmi.h> #include <linux/pci-ats.h> +#include <linux/memblock.h> #include <asm/cacheflush.h> #include <asm/iommu.h> @@ -2188,18 +2189,6 @@ static inline void iommu_prepare_isa(void) static int md_domain_init(struct dmar_domain *domain, int guest_width); -static int __init si_domain_work_fn(unsigned long start_pfn, - unsigned long end_pfn, void *datax) -{ - int *ret = datax; - - *ret = iommu_domain_identity_map(si_domain, - (uint64_t)start_pfn << PAGE_SHIFT, - (uint64_t)end_pfn << PAGE_SHIFT); - return *ret; - -} - static int __init si_domain_init(int hw) { struct dmar_drhd_unit *drhd; @@ -2231,9 +2220,15 @@ static int __init si_domain_init(int hw) return 0; for_each_online_node(nid) { - work_with_active_regions(nid, si_domain_work_fn, &ret); - if (ret) - return ret; + unsigned long start_pfn, end_pfn; + int i; + + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { + ret = iommu_domain_identity_map(si_domain, + PFN_PHYS(start_pfn), PFN_PHYS(end_pfn)); + if (ret) + return ret; + } } return 0; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 2fb2963..5b5fa5c 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -90,7 +90,7 @@ struct iommu_domain *iommu_domain_alloc(struct bus_type *bus) if (bus == NULL || bus->iommu_ops == NULL) return NULL; - domain = kmalloc(sizeof(*domain), GFP_KERNEL); + domain = kzalloc(sizeof(*domain), GFP_KERNEL); if (!domain) return NULL; diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index b690711..6d03774 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -1393,9 +1393,6 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto atomic_read(&bitmap->behind_writes), bitmap->mddev->bitmap_info.max_write_behind); } - if (bitmap->mddev->degraded) - /* Never clear bits or update events_cleared when degraded */ - success = 0; while (sectors) { sector_t blocks; @@ -1409,7 +1406,7 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto return; } - if (success && + if (success && !bitmap->mddev->degraded && bitmap->events_cleared < bitmap->mddev->events) { bitmap->events_cleared = bitmap->mddev->events; bitmap->need_sync = 1; diff --git a/drivers/md/linear.c b/drivers/md/linear.c index c3273ef..6274565 100644 --- a/drivers/md/linear.c +++ b/drivers/md/linear.c @@ -230,6 +230,7 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev) return -EINVAL; rdev->raid_disk = rdev->saved_raid_disk; + rdev->saved_raid_disk = -1; newconf = linear_conf(mddev,mddev->raid_disks+1); diff --git a/drivers/md/md.c b/drivers/md/md.c index ee98173..f47f1f8 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -7360,8 +7360,7 @@ static int remove_and_add_spares(struct mddev *mddev) spares++; md_new_event(mddev); set_bit(MD_CHANGE_DEVS, &mddev->flags); - } else - break; + } } } } diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 31670f8..858fdbb 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -3065,11 +3065,17 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s) } } else if (test_bit(In_sync, &rdev->flags)) set_bit(R5_Insync, &dev->flags); - else { + else if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset) /* in sync if before recovery_offset */ - if (sh->sector + STRIPE_SECTORS <= rdev->recovery_offset) - set_bit(R5_Insync, &dev->flags); - } + set_bit(R5_Insync, &dev->flags); + else if (test_bit(R5_UPTODATE, &dev->flags) && + test_bit(R5_Expanded, &dev->flags)) + /* If we've reshaped into here, we assume it is Insync. + * We will shortly update recovery_offset to make + * it official. + */ + set_bit(R5_Insync, &dev->flags); + if (rdev && test_bit(R5_WriteError, &dev->flags)) { clear_bit(R5_Insync, &dev->flags); if (!test_bit(Faulty, &rdev->flags)) { diff --git a/drivers/media/common/tuners/mxl5007t.c b/drivers/media/common/tuners/mxl5007t.c index 7eb1bf7..5d02221 100644 --- a/drivers/media/common/tuners/mxl5007t.c +++ b/drivers/media/common/tuners/mxl5007t.c @@ -488,9 +488,10 @@ static int mxl5007t_write_regs(struct mxl5007t_state *state, static int mxl5007t_read_reg(struct mxl5007t_state *state, u8 reg, u8 *val) { + u8 buf[2] = { 0xfb, reg }; struct i2c_msg msg[] = { { .addr = state->i2c_props.addr, .flags = 0, - .buf = ®, .len = 1 }, + .buf = buf, .len = 2 }, { .addr = state->i2c_props.addr, .flags = I2C_M_RD, .buf = val, .len = 1 }, }; diff --git a/drivers/media/common/tuners/tda18218.c b/drivers/media/common/tuners/tda18218.c index aacfe23..4fc2973 100644 --- a/drivers/media/common/tuners/tda18218.c +++ b/drivers/media/common/tuners/tda18218.c @@ -141,7 +141,7 @@ static int tda18218_set_params(struct dvb_frontend *fe, switch (params->u.ofdm.bandwidth) { case BANDWIDTH_6_MHZ: LP_Fc = 0; - LO_Frac = params->frequency + 4000000; + LO_Frac = params->frequency + 3000000; break; case BANDWIDTH_7_MHZ: LP_Fc = 1; diff --git a/drivers/media/rc/ati_remote.c b/drivers/media/rc/ati_remote.c index 303f22e..01bb8da 100644 --- a/drivers/media/rc/ati_remote.c +++ b/drivers/media/rc/ati_remote.c @@ -189,7 +189,7 @@ struct ati_remote { dma_addr_t inbuf_dma; dma_addr_t outbuf_dma; - unsigned char old_data[2]; /* Detect duplicate events */ + unsigned char old_data; /* Detect duplicate events */ unsigned long old_jiffies; unsigned long acc_jiffies; /* handle acceleration */ unsigned long first_jiffies; @@ -221,35 +221,35 @@ struct ati_remote { /* Translation table from hardware messages to input events. */ static const struct { short kind; - unsigned char data1, data2; + unsigned char data; int type; unsigned int code; int value; } ati_remote_tbl[] = { /* Directional control pad axes */ - {KIND_ACCEL, 0x35, 0x70, EV_REL, REL_X, -1}, /* left */ - {KIND_ACCEL, 0x36, 0x71, EV_REL, REL_X, 1}, /* right */ - {KIND_ACCEL, 0x37, 0x72, EV_REL, REL_Y, -1}, /* up */ - {KIND_ACCEL, 0x38, 0x73, EV_REL, REL_Y, 1}, /* down */ + {KIND_ACCEL, 0x70, EV_REL, REL_X, -1}, /* left */ + {KIND_ACCEL, 0x71, EV_REL, REL_X, 1}, /* right */ + {KIND_ACCEL, 0x72, EV_REL, REL_Y, -1}, /* up */ + {KIND_ACCEL, 0x73, EV_REL, REL_Y, 1}, /* down */ /* Directional control pad diagonals */ - {KIND_LU, 0x39, 0x74, EV_REL, 0, 0}, /* left up */ - {KIND_RU, 0x3a, 0x75, EV_REL, 0, 0}, /* right up */ - {KIND_LD, 0x3c, 0x77, EV_REL, 0, 0}, /* left down */ - {KIND_RD, 0x3b, 0x76, EV_REL, 0, 0}, /* right down */ + {KIND_LU, 0x74, EV_REL, 0, 0}, /* left up */ + {KIND_RU, 0x75, EV_REL, 0, 0}, /* right up */ + {KIND_LD, 0x77, EV_REL, 0, 0}, /* left down */ + {KIND_RD, 0x76, EV_REL, 0, 0}, /* right down */ /* "Mouse button" buttons */ - {KIND_LITERAL, 0x3d, 0x78, EV_KEY, BTN_LEFT, 1}, /* left btn down */ - {KIND_LITERAL, 0x3e, 0x79, EV_KEY, BTN_LEFT, 0}, /* left btn up */ - {KIND_LITERAL, 0x41, 0x7c, EV_KEY, BTN_RIGHT, 1},/* right btn down */ - {KIND_LITERAL, 0x42, 0x7d, EV_KEY, BTN_RIGHT, 0},/* right btn up */ + {KIND_LITERAL, 0x78, EV_KEY, BTN_LEFT, 1}, /* left btn down */ + {KIND_LITERAL, 0x79, EV_KEY, BTN_LEFT, 0}, /* left btn up */ + {KIND_LITERAL, 0x7c, EV_KEY, BTN_RIGHT, 1},/* right btn down */ + {KIND_LITERAL, 0x7d, EV_KEY, BTN_RIGHT, 0},/* right btn up */ /* Artificial "doubleclick" events are generated by the hardware. * They are mapped to the "side" and "extra" mouse buttons here. */ - {KIND_FILTERED, 0x3f, 0x7a, EV_KEY, BTN_SIDE, 1}, /* left dblclick */ - {KIND_FILTERED, 0x43, 0x7e, EV_KEY, BTN_EXTRA, 1},/* right dblclick */ + {KIND_FILTERED, 0x7a, EV_KEY, BTN_SIDE, 1}, /* left dblclick */ + {KIND_FILTERED, 0x7e, EV_KEY, BTN_EXTRA, 1},/* right dblclick */ /* Non-mouse events are handled by rc-core */ - {KIND_END, 0x00, 0x00, EV_MAX + 1, 0, 0} + {KIND_END, 0x00, EV_MAX + 1, 0, 0} }; /* Local function prototypes */ @@ -397,25 +397,6 @@ static int ati_remote_sendpacket(struct ati_remote *ati_remote, u16 cmd, unsigne } /* - * ati_remote_event_lookup - */ -static int ati_remote_event_lookup(int rem, unsigned char d1, unsigned char d2) -{ - int i; - - for (i = 0; ati_remote_tbl[i].kind != KIND_END; i++) { - /* - * Decide if the table entry matches the remote input. - */ - if (ati_remote_tbl[i].data1 == d1 && - ati_remote_tbl[i].data2 == d2) - return i; - - } - return -1; -} - -/* * ati_remote_compute_accel * * Implements acceleration curve for directional control pad @@ -463,7 +444,15 @@ static void ati_remote_input_report(struct urb *urb) int index = -1; int acc; int remote_num; - unsigned char scancode[2]; + unsigned char scancode; + int i; + + /* + * data[0] = 0x14 + * data[1] = data[2] + data[3] + 0xd5 (a checksum byte) + * data[2] = the key code (with toggle bit in MSB with some models) + * data[3] = channel << 4 (the low 4 bits must be zero) + */ /* Deal with strange looking inputs */ if ( (urb->actual_length != 4) || (data[0] != 0x14) || @@ -472,6 +461,13 @@ static void ati_remote_input_report(struct urb *urb) return; } + if (data[1] != ((data[2] + data[3] + 0xd5) & 0xff)) { + dbginfo(&ati_remote->interface->dev, + "wrong checksum in input: %02x %02x %02x %02x\n", + data[0], data[1], data[2], data[3]); + return; + } + /* Mask unwanted remote channels. */ /* note: remote_num is 0-based, channel 1 on remote == 0 here */ remote_num = (data[3] >> 4) & 0x0f; @@ -482,31 +478,30 @@ static void ati_remote_input_report(struct urb *urb) return; } - scancode[0] = (((data[1] - ((remote_num + 1) << 4)) & 0xf0) | (data[1] & 0x0f)); - /* - * Some devices (e.g. SnapStream Firefly) use 8080 as toggle code, - * so we have to clear them. The first bit is a bit tricky as the - * "non-toggled" state depends on remote_num, so we xor it with the - * second bit which is only used for toggle. + * MSB is a toggle code, though only used by some devices + * (e.g. SnapStream Firefly) */ - scancode[0] ^= (data[2] & 0x80); - - scancode[1] = data[2] & ~0x80; + scancode = data[2] & 0x7f; - /* Look up event code index in mouse translation table. */ - index = ati_remote_event_lookup(remote_num, scancode[0], scancode[1]); + /* Look up event code index in the mouse translation table. */ + for (i = 0; ati_remote_tbl[i].kind != KIND_END; i++) { + if (scancode == ati_remote_tbl[i].data) { + index = i; + break; + } + } if (index >= 0) { dbginfo(&ati_remote->interface->dev, - "channel 0x%02x; mouse data %02x,%02x; index %d; keycode %d\n", - remote_num, data[1], data[2], index, ati_remote_tbl[index].code); + "channel 0x%02x; mouse data %02x; index %d; keycode %d\n", + remote_num, data[2], index, ati_remote_tbl[index].code); if (!dev) return; /* no mouse device */ } else dbginfo(&ati_remote->interface->dev, - "channel 0x%02x; key data %02x,%02x, scancode %02x,%02x\n", - remote_num, data[1], data[2], scancode[0], scancode[1]); + "channel 0x%02x; key data %02x, scancode %02x\n", + remote_num, data[2], scancode); if (index >= 0 && ati_remote_tbl[index].kind == KIND_LITERAL) { @@ -523,8 +518,7 @@ static void ati_remote_input_report(struct urb *urb) unsigned long now = jiffies; /* Filter duplicate events which happen "too close" together. */ - if (ati_remote->old_data[0] == data[1] && - ati_remote->old_data[1] == data[2] && + if (ati_remote->old_data == data[2] && time_before(now, ati_remote->old_jiffies + msecs_to_jiffies(repeat_filter))) { ati_remote->repeat_count++; @@ -533,8 +527,7 @@ static void ati_remote_input_report(struct urb *urb) ati_remote->first_jiffies = now; } - ati_remote->old_data[0] = data[1]; - ati_remote->old_data[1] = data[2]; + ati_remote->old_data = data[2]; ati_remote->old_jiffies = now; /* Ensure we skip at least the 4 first duplicate events (generated @@ -549,14 +542,13 @@ static void ati_remote_input_report(struct urb *urb) if (index < 0) { /* Not a mouse event, hand it to rc-core. */ - u32 rc_code = (scancode[0] << 8) | scancode[1]; /* * We don't use the rc-core repeat handling yet as * it would cause ghost repeats which would be a * regression for this driver. */ - rc_keydown_notimeout(ati_remote->rdev, rc_code, + rc_keydown_notimeout(ati_remote->rdev, scancode, data[2]); rc_keyup(ati_remote->rdev); return; @@ -607,8 +599,7 @@ static void ati_remote_input_report(struct urb *urb) input_sync(dev); ati_remote->old_jiffies = jiffies; - ati_remote->old_data[0] = data[1]; - ati_remote->old_data[1] = data[2]; + ati_remote->old_data = data[2]; } } diff --git a/drivers/media/rc/keymaps/rc-ati-x10.c b/drivers/media/rc/keymaps/rc-ati-x10.c index e1b8b26..8150644 100644 --- a/drivers/media/rc/keymaps/rc-ati-x10.c +++ b/drivers/media/rc/keymaps/rc-ati-x10.c @@ -27,55 +27,55 @@ #include <media/rc-map.h> static struct rc_map_table ati_x10[] = { - { 0xd20d, KEY_1 }, - { 0xd30e, KEY_2 }, - { 0xd40f, KEY_3 }, - { 0xd510, KEY_4 }, - { 0xd611, KEY_5 }, - { 0xd712, KEY_6 }, - { 0xd813, KEY_7 }, - { 0xd914, KEY_8 }, - { 0xda15, KEY_9 }, - { 0xdc17, KEY_0 }, - { 0xc500, KEY_A }, - { 0xc601, KEY_B }, - { 0xde19, KEY_C }, - { 0xe01b, KEY_D }, - { 0xe621, KEY_E }, - { 0xe823, KEY_F }, + { 0x0d, KEY_1 }, + { 0x0e, KEY_2 }, + { 0x0f, KEY_3 }, + { 0x10, KEY_4 }, + { 0x11, KEY_5 }, + { 0x12, KEY_6 }, + { 0x13, KEY_7 }, + { 0x14, KEY_8 }, + { 0x15, KEY_9 }, + { 0x17, KEY_0 }, + { 0x00, KEY_A }, + { 0x01, KEY_B }, + { 0x19, KEY_C }, + { 0x1b, KEY_D }, + { 0x21, KEY_E }, + { 0x23, KEY_F }, - { 0xdd18, KEY_KPENTER }, /* "check" */ - { 0xdb16, KEY_MENU }, /* "menu" */ - { 0xc702, KEY_POWER }, /* Power */ - { 0xc803, KEY_TV }, /* TV */ - { 0xc904, KEY_DVD }, /* DVD */ - { 0xca05, KEY_WWW }, /* WEB */ - { 0xcb06, KEY_BOOKMARKS }, /* "book" */ - { 0xcc07, KEY_EDIT }, /* "hand" */ - { 0xe11c, KEY_COFFEE }, /* "timer" */ - { 0xe520, KEY_FRONT }, /* "max" */ - { 0xe21d, KEY_LEFT }, /* left */ - { 0xe41f, KEY_RIGHT }, /* right */ - { 0xe722, KEY_DOWN }, /* down */ - { 0xdf1a, KEY_UP }, /* up */ - { 0xe31e, KEY_OK }, /* "OK" */ - { 0xce09, KEY_VOLUMEDOWN }, /* VOL + */ - { 0xcd08, KEY_VOLUMEUP }, /* VOL - */ - { 0xcf0a, KEY_MUTE }, /* MUTE */ - { 0xd00b, KEY_CHANNELUP }, /* CH + */ - { 0xd10c, KEY_CHANNELDOWN },/* CH - */ - { 0xec27, KEY_RECORD }, /* ( o) red */ - { 0xea25, KEY_PLAY }, /* ( >) */ - { 0xe924, KEY_REWIND }, /* (<<) */ - { 0xeb26, KEY_FORWARD }, /* (>>) */ - { 0xed28, KEY_STOP }, /* ([]) */ - { 0xee29, KEY_PAUSE }, /* ('') */ - { 0xf02b, KEY_PREVIOUS }, /* (<-) */ - { 0xef2a, KEY_NEXT }, /* (>+) */ - { 0xf22d, KEY_INFO }, /* PLAYING */ - { 0xf32e, KEY_HOME }, /* TOP */ - { 0xf42f, KEY_END }, /* END */ - { 0xf530, KEY_SELECT }, /* SELECT */ + { 0x18, KEY_KPENTER }, /* "check" */ + { 0x16, KEY_MENU }, /* "menu" */ + { 0x02, KEY_POWER }, /* Power */ + { 0x03, KEY_TV }, /* TV */ + { 0x04, KEY_DVD }, /* DVD */ + { 0x05, KEY_WWW }, /* WEB */ + { 0x06, KEY_BOOKMARKS }, /* "book" */ + { 0x07, KEY_EDIT }, /* "hand" */ + { 0x1c, KEY_COFFEE }, /* "timer" */ + { 0x20, KEY_FRONT }, /* "max" */ + { 0x1d, KEY_LEFT }, /* left */ + { 0x1f, KEY_RIGHT }, /* right */ + { 0x22, KEY_DOWN }, /* down */ + { 0x1a, KEY_UP }, /* up */ + { 0x1e, KEY_OK }, /* "OK" */ + { 0x09, KEY_VOLUMEDOWN }, /* VOL + */ + { 0x08, KEY_VOLUMEUP }, /* VOL - */ + { 0x0a, KEY_MUTE }, /* MUTE */ + { 0x0b, KEY_CHANNELUP }, /* CH + */ + { 0x0c, KEY_CHANNELDOWN },/* CH - */ + { 0x27, KEY_RECORD }, /* ( o) red */ + { 0x25, KEY_PLAY }, /* ( >) */ + { 0x24, KEY_REWIND }, /* (<<) */ + { 0x26, KEY_FORWARD }, /* (>>) */ + { 0x28, KEY_STOP }, /* ([]) */ + { 0x29, KEY_PAUSE }, /* ('') */ + { 0x2b, KEY_PREVIOUS }, /* (<-) */ + { 0x2a, KEY_NEXT }, /* (>+) */ + { 0x2d, KEY_INFO }, /* PLAYING */ + { 0x2e, KEY_HOME }, /* TOP */ + { 0x2f, KEY_END }, /* END */ + { 0x30, KEY_SELECT }, /* SELECT */ }; static struct rc_map_list ati_x10_map = { diff --git a/drivers/media/rc/keymaps/rc-medion-x10.c b/drivers/media/rc/keymaps/rc-medion-x10.c index 09e2cc0..479cdb8 100644 --- a/drivers/media/rc/keymaps/rc-medion-x10.c +++ b/drivers/media/rc/keymaps/rc-medion-x10.c @@ -25,70 +25,70 @@ #include <media/rc-map.h> static struct rc_map_table medion_x10[] = { - { 0xf12c, KEY_TV }, /* TV */ - { 0xf22d, KEY_VCR }, /* VCR */ - { 0xc904, KEY_DVD }, /* DVD */ - { 0xcb06, KEY_AUDIO }, /* MUSIC */ - - { 0xf32e, KEY_RADIO }, /* RADIO */ - { 0xca05, KEY_DIRECTORY }, /* PHOTO */ - { 0xf42f, KEY_INFO }, /* TV-PREVIEW */ - { 0xf530, KEY_LIST }, /* CHANNEL-LST */ - - { 0xe01b, KEY_SETUP }, /* SETUP */ - { 0xf631, KEY_VIDEO }, /* VIDEO DESKTOP */ - - { 0xcd08, KEY_VOLUMEDOWN }, /* VOL - */ - { 0xce09, KEY_VOLUMEUP }, /* VOL + */ - { 0xd00b, KEY_CHANNELUP }, /* CHAN + */ - { 0xd10c, KEY_CHANNELDOWN }, /* CHAN - */ - { 0xc500, KEY_MUTE }, /* MUTE */ - - { 0xf732, KEY_RED }, /* red */ - { 0xf833, KEY_GREEN }, /* green */ - { 0xf934, KEY_YELLOW }, /* yellow */ - { 0xfa35, KEY_BLUE }, /* blue */ - { 0xdb16, KEY_TEXT }, /* TXT */ - - { 0xd20d, KEY_1 }, - { 0xd30e, KEY_2 }, - { 0xd40f, KEY_3 }, - { 0xd510, KEY_4 }, - { 0xd611, KEY_5 }, - { 0xd712, KEY_6 }, - { 0xd813, KEY_7 }, - { 0xd914, KEY_8 }, - { 0xda15, KEY_9 }, - { 0xdc17, KEY_0 }, - { 0xe11c, KEY_SEARCH }, /* TV/RAD, CH SRC */ - { 0xe520, KEY_DELETE }, /* DELETE */ - - { 0xfb36, KEY_KEYBOARD }, /* RENAME */ - { 0xdd18, KEY_SCREEN }, /* SNAPSHOT */ - - { 0xdf1a, KEY_UP }, /* up */ - { 0xe722, KEY_DOWN }, /* down */ - { 0xe21d, KEY_LEFT }, /* left */ - { 0xe41f, KEY_RIGHT }, /* right */ - { 0xe31e, KEY_OK }, /* OK */ - - { 0xfc37, KEY_SELECT }, /* ACQUIRE IMAGE */ - { 0xfd38, KEY_EDIT }, /* EDIT IMAGE */ - - { 0xe924, KEY_REWIND }, /* rewind (<<) */ - { 0xea25, KEY_PLAY }, /* play ( >) */ - { 0xeb26, KEY_FORWARD }, /* forward (>>) */ - { 0xec27, KEY_RECORD }, /* record ( o) */ - { 0xed28, KEY_STOP }, /* stop ([]) */ - { 0xee29, KEY_PAUSE }, /* pause ('') */ - - { 0xe621, KEY_PREVIOUS }, /* prev */ - { 0xfe39, KEY_SWITCHVIDEOMODE }, /* F SCR */ - { 0xe823, KEY_NEXT }, /* next */ - { 0xde19, KEY_MENU }, /* MENU */ - { 0xff3a, KEY_LANGUAGE }, /* AUDIO */ - - { 0xc702, KEY_POWER }, /* POWER */ + { 0x2c, KEY_TV }, /* TV */ + { 0x2d, KEY_VCR }, /* VCR */ + { 0x04, KEY_DVD }, /* DVD */ + { 0x06, KEY_AUDIO }, /* MUSIC */ + + { 0x2e, KEY_RADIO }, /* RADIO */ + { 0x05, KEY_DIRECTORY }, /* PHOTO */ + { 0x2f, KEY_INFO }, /* TV-PREVIEW */ + { 0x30, KEY_LIST }, /* CHANNEL-LST */ + + { 0x1b, KEY_SETUP }, /* SETUP */ + { 0x31, KEY_VIDEO }, /* VIDEO DESKTOP */ + + { 0x08, KEY_VOLUMEDOWN }, /* VOL - */ + { 0x09, KEY_VOLUMEUP }, /* VOL + */ + { 0x0b, KEY_CHANNELUP }, /* CHAN + */ + { 0x0c, KEY_CHANNELDOWN }, /* CHAN - */ + { 0x00, KEY_MUTE }, /* MUTE */ + + { 0x32, KEY_RED }, /* red */ + { 0x33, KEY_GREEN }, /* green */ + { 0x34, KEY_YELLOW }, /* yellow */ + { 0x35, KEY_BLUE }, /* blue */ + { 0x16, KEY_TEXT }, /* TXT */ + + { 0x0d, KEY_1 }, + { 0x0e, KEY_2 }, + { 0x0f, KEY_3 }, + { 0x10, KEY_4 }, + { 0x11, KEY_5 }, + { 0x12, KEY_6 }, + { 0x13, KEY_7 }, + { 0x14, KEY_8 }, + { 0x15, KEY_9 }, + { 0x17, KEY_0 }, + { 0x1c, KEY_SEARCH }, /* TV/RAD, CH SRC */ + { 0x20, KEY_DELETE }, /* DELETE */ + + { 0x36, KEY_KEYBOARD }, /* RENAME */ + { 0x18, KEY_SCREEN }, /* SNAPSHOT */ + + { 0x1a, KEY_UP }, /* up */ + { 0x22, KEY_DOWN }, /* down */ + { 0x1d, KEY_LEFT }, /* left */ + { 0x1f, KEY_RIGHT }, /* right */ + { 0x1e, KEY_OK }, /* OK */ + + { 0x37, KEY_SELECT }, /* ACQUIRE IMAGE */ + { 0x38, KEY_EDIT }, /* EDIT IMAGE */ + + { 0x24, KEY_REWIND }, /* rewind (<<) */ + { 0x25, KEY_PLAY }, /* play ( >) */ + { 0x26, KEY_FORWARD }, /* forward (>>) */ + { 0x27, KEY_RECORD }, /* record ( o) */ + { 0x28, KEY_STOP }, /* stop ([]) */ + { 0x29, KEY_PAUSE }, /* pause ('') */ + + { 0x21, KEY_PREVIOUS }, /* prev */ + { 0x39, KEY_SWITCHVIDEOMODE }, /* F SCR */ + { 0x23, KEY_NEXT }, /* next */ + { 0x19, KEY_MENU }, /* MENU */ + { 0x3a, KEY_LANGUAGE }, /* AUDIO */ + + { 0x02, KEY_POWER }, /* POWER */ }; static struct rc_map_list medion_x10_map = { diff --git a/drivers/media/rc/keymaps/rc-snapstream-firefly.c b/drivers/media/rc/keymaps/rc-snapstream-firefly.c index ef14652..c7f33ec 100644 --- a/drivers/media/rc/keymaps/rc-snapstream-firefly.c +++ b/drivers/media/rc/keymaps/rc-snapstream-firefly.c @@ -22,63 +22,63 @@ #include <media/rc-map.h> static struct rc_map_table snapstream_firefly[] = { - { 0xf12c, KEY_ZOOM }, /* Maximize */ - { 0xc702, KEY_CLOSE }, - - { 0xd20d, KEY_1 }, - { 0xd30e, KEY_2 }, - { 0xd40f, KEY_3 }, - { 0xd510, KEY_4 }, - { 0xd611, KEY_5 }, - { 0xd712, KEY_6 }, - { 0xd813, KEY_7 }, - { 0xd914, KEY_8 }, - { 0xda15, KEY_9 }, - { 0xdc17, KEY_0 }, - { 0xdb16, KEY_BACK }, - { 0xdd18, KEY_KPENTER }, /* ent */ - - { 0xce09, KEY_VOLUMEUP }, - { 0xcd08, KEY_VOLUMEDOWN }, - { 0xcf0a, KEY_MUTE }, - { 0xd00b, KEY_CHANNELUP }, - { 0xd10c, KEY_CHANNELDOWN }, - { 0xc500, KEY_VENDOR }, /* firefly */ - - { 0xf32e, KEY_INFO }, - { 0xf42f, KEY_OPTION }, - - { 0xe21d, KEY_LEFT }, - { 0xe41f, KEY_RIGHT }, - { 0xe722, KEY_DOWN }, - { 0xdf1a, KEY_UP }, - { 0xe31e, KEY_OK }, - - { 0xe11c, KEY_MENU }, - { 0xe520, KEY_EXIT }, - - { 0xec27, KEY_RECORD }, - { 0xea25, KEY_PLAY }, - { 0xed28, KEY_STOP }, - { 0xe924, KEY_REWIND }, - { 0xeb26, KEY_FORWARD }, - { 0xee29, KEY_PAUSE }, - { 0xf02b, KEY_PREVIOUS }, - { 0xef2a, KEY_NEXT }, - - { 0xcb06, KEY_AUDIO }, /* Music */ - { 0xca05, KEY_IMAGES }, /* Photos */ - { 0xc904, KEY_DVD }, - { 0xc803, KEY_TV }, - { 0xcc07, KEY_VIDEO }, - - { 0xc601, KEY_HELP }, - { 0xf22d, KEY_MODE }, /* Mouse */ - - { 0xde19, KEY_A }, - { 0xe01b, KEY_B }, - { 0xe621, KEY_C }, - { 0xe823, KEY_D }, + { 0x2c, KEY_ZOOM }, /* Maximize */ + { 0x02, KEY_CLOSE }, + + { 0x0d, KEY_1 }, + { 0x0e, KEY_2 }, + { 0x0f, KEY_3 }, + { 0x10, KEY_4 }, + { 0x11, KEY_5 }, + { 0x12, KEY_6 }, + { 0x13, KEY_7 }, + { 0x14, KEY_8 }, + { 0x15, KEY_9 }, + { 0x17, KEY_0 }, + { 0x16, KEY_BACK }, + { 0x18, KEY_KPENTER }, /* ent */ + + { 0x09, KEY_VOLUMEUP }, + { 0x08, KEY_VOLUMEDOWN }, + { 0x0a, KEY_MUTE }, + { 0x0b, KEY_CHANNELUP }, + { 0x0c, KEY_CHANNELDOWN }, + { 0x00, KEY_VENDOR }, /* firefly */ + + { 0x2e, KEY_INFO }, + { 0x2f, KEY_OPTION }, + + { 0x1d, KEY_LEFT }, + { 0x1f, KEY_RIGHT }, + { 0x22, KEY_DOWN }, + { 0x1a, KEY_UP }, + { 0x1e, KEY_OK }, + + { 0x1c, KEY_MENU }, + { 0x20, KEY_EXIT }, + + { 0x27, KEY_RECORD }, + { 0x25, KEY_PLAY }, + { 0x28, KEY_STOP }, + { 0x24, KEY_REWIND }, + { 0x26, KEY_FORWARD }, + { 0x29, KEY_PAUSE }, + { 0x2b, KEY_PREVIOUS }, + { 0x2a, KEY_NEXT }, + + { 0x06, KEY_AUDIO }, /* Music */ + { 0x05, KEY_IMAGES }, /* Photos */ + { 0x04, KEY_DVD }, + { 0x03, KEY_TV }, + { 0x07, KEY_VIDEO }, + + { 0x01, KEY_HELP }, + { 0x2d, KEY_MODE }, /* Mouse */ + + { 0x19, KEY_A }, + { 0x1b, KEY_B }, + { 0x21, KEY_C }, + { 0x23, KEY_D }, }; static struct rc_map_list snapstream_firefly_map = { diff --git a/drivers/media/video/au0828/au0828-cards.c b/drivers/media/video/au0828/au0828-cards.c index 39fc923..1c6015a 100644 --- a/drivers/media/video/au0828/au0828-cards.c +++ b/drivers/media/video/au0828/au0828-cards.c @@ -162,11 +162,14 @@ static void hauppauge_eeprom(struct au0828_dev *dev, u8 *eeprom_data) switch (tv.model) { case 72000: /* WinTV-HVR950q (Retail, IR, ATSC/QAM */ case 72001: /* WinTV-HVR950q (Retail, IR, ATSC/QAM and analog video */ + case 72101: /* WinTV-HVR950q (Retail, IR, ATSC/QAM and analog video */ + case 72201: /* WinTV-HVR950q (OEM, IR, ATSC/QAM and analog video */ case 72211: /* WinTV-HVR950q (OEM, IR, ATSC/QAM and analog video */ case 72221: /* WinTV-HVR950q (OEM, IR, ATSC/QAM and analog video */ case 72231: /* WinTV-HVR950q (OEM, IR, ATSC/QAM and analog video */ case 72241: /* WinTV-HVR950q (OEM, No IR, ATSC/QAM and analog video */ case 72251: /* WinTV-HVR950q (Retail, IR, ATSC/QAM and analog video */ + case 72261: /* WinTV-HVR950q (OEM, IR, ATSC/QAM and analog video */ case 72301: /* WinTV-HVR850 (Retail, IR, ATSC and analog video */ case 72500: /* WinTV-HVR950q (OEM, No IR, ATSC/QAM */ break; @@ -324,6 +327,10 @@ struct usb_device_id au0828_usb_id_table[] = { .driver_info = AU0828_BOARD_HAUPPAUGE_HVR950Q_MXL }, { USB_DEVICE(0x2040, 0x8200), .driver_info = AU0828_BOARD_HAUPPAUGE_WOODBURY }, + { USB_DEVICE(0x2040, 0x7260), + .driver_info = AU0828_BOARD_HAUPPAUGE_HVR950Q }, + { USB_DEVICE(0x2040, 0x7213), + .driver_info = AU0828_BOARD_HAUPPAUGE_HVR950Q }, { }, }; diff --git a/drivers/media/video/gspca/gspca.c b/drivers/media/video/gspca/gspca.c index 881e04c..2ca10df 100644 --- a/drivers/media/video/gspca/gspca.c +++ b/drivers/media/video/gspca/gspca.c @@ -838,13 +838,13 @@ static int gspca_init_transfer(struct gspca_dev *gspca_dev) gspca_dev->usb_err = 0; /* do the specific subdriver stuff before endpoint selection */ - gspca_dev->alt = 0; + intf = usb_ifnum_to_if(gspca_dev->dev, gspca_dev->iface); + gspca_dev->alt = gspca_dev->cam.bulk ? intf->num_altsetting : 0; if (gspca_dev->sd_desc->isoc_init) { ret = gspca_dev->sd_desc->isoc_init(gspca_dev); if (ret < 0) goto unlock; } - intf = usb_ifnum_to_if(gspca_dev->dev, gspca_dev->iface); xfer = gspca_dev->cam.bulk ? USB_ENDPOINT_XFER_BULK : USB_ENDPOINT_XFER_ISOC; @@ -957,7 +957,7 @@ retry: ret = -EIO; goto out; } - alt = ep_tb[--alt_idx].alt; + gspca_dev->alt = ep_tb[--alt_idx].alt; } } out: diff --git a/drivers/media/video/m5mols/m5mols.h b/drivers/media/video/m5mols/m5mols.h index 89d09a8..82c8817 100644 --- a/drivers/media/video/m5mols/m5mols.h +++ b/drivers/media/video/m5mols/m5mols.h @@ -162,7 +162,6 @@ struct m5mols_version { * @pad: media pad * @ffmt: current fmt according to resolution type * @res_type: current resolution type - * @code: current code * @irq_waitq: waitqueue for the capture * @work_irq: workqueue for the IRQ * @flags: state variable for the interrupt handler @@ -192,7 +191,6 @@ struct m5mols_info { struct media_pad pad; struct v4l2_mbus_framefmt ffmt[M5MOLS_RESTYPE_MAX]; int res_type; - enum v4l2_mbus_pixelcode code; wait_queue_head_t irq_waitq; struct work_struct work_irq; unsigned long flags; diff --git a/drivers/media/video/m5mols/m5mols_core.c b/drivers/media/video/m5mols/m5mols_core.c index 05ab370..e0f09e5 100644 --- a/drivers/media/video/m5mols/m5mols_core.c +++ b/drivers/media/video/m5mols/m5mols_core.c @@ -334,7 +334,7 @@ int m5mols_mode(struct m5mols_info *info, u8 mode) int ret = -EINVAL; u8 reg; - if (mode < REG_PARAMETER && mode > REG_CAPTURE) + if (mode < REG_PARAMETER || mode > REG_CAPTURE) return ret; ret = m5mols_read_u8(sd, SYSTEM_SYSMODE, ®); @@ -511,9 +511,6 @@ static int m5mols_get_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh, struct m5mols_info *info = to_m5mols(sd); struct v4l2_mbus_framefmt *format; - if (fmt->pad != 0) - return -EINVAL; - format = __find_format(info, fh, fmt->which, info->res_type); if (!format) return -EINVAL; @@ -532,9 +529,6 @@ static int m5mols_set_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh, u32 resolution = 0; int ret; - if (fmt->pad != 0) - return -EINVAL; - ret = __find_resolution(sd, format, &type, &resolution); if (ret < 0) return ret; @@ -543,13 +537,14 @@ static int m5mols_set_fmt(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh, if (!sfmt) return 0; - *sfmt = m5mols_default_ffmt[type]; - sfmt->width = format->width; - sfmt->height = format->height; + + format->code = m5mols_default_ffmt[type].code; + format->colorspace = V4L2_COLORSPACE_JPEG; + format->field = V4L2_FIELD_NONE; if (fmt->which == V4L2_SUBDEV_FORMAT_ACTIVE) { + *sfmt = *format; info->resolution = resolution; - info->code = format->code; info->res_type = type; } @@ -626,13 +621,14 @@ static int m5mols_start_monitor(struct m5mols_info *info) static int m5mols_s_stream(struct v4l2_subdev *sd, int enable) { struct m5mols_info *info = to_m5mols(sd); + u32 code = info->ffmt[info->res_type].code; if (enable) { int ret = -EINVAL; - if (is_code(info->code, M5MOLS_RESTYPE_MONITOR)) + if (is_code(code, M5MOLS_RESTYPE_MONITOR)) ret = m5mols_start_monitor(info); - if (is_code(info->code, M5MOLS_RESTYPE_CAPTURE)) + if (is_code(code, M5MOLS_RESTYPE_CAPTURE)) ret = m5mols_start_capture(info); return ret; diff --git a/drivers/media/video/mt9m111.c b/drivers/media/video/mt9m111.c index cf2c0fb..398f96f 100644 --- a/drivers/media/video/mt9m111.c +++ b/drivers/media/video/mt9m111.c @@ -955,6 +955,7 @@ static int mt9m111_probe(struct i2c_client *client, mt9m111->rect.height = MT9M111_MAX_HEIGHT; mt9m111->fmt = &mt9m111_colour_fmts[0]; mt9m111->lastpage = -1; + mutex_init(&mt9m111->power_lock); ret = mt9m111_video_probe(client); if (ret) { diff --git a/drivers/media/video/mt9t112.c b/drivers/media/video/mt9t112.c index 32114a3..7b34b11 100644 --- a/drivers/media/video/mt9t112.c +++ b/drivers/media/video/mt9t112.c @@ -1083,8 +1083,10 @@ static int mt9t112_probe(struct i2c_client *client, v4l2_i2c_subdev_init(&priv->subdev, client, &mt9t112_subdev_ops); ret = mt9t112_camera_probe(client); - if (ret) + if (ret) { kfree(priv); + return ret; + } /* Cannot fail: using the default supported pixel code */ mt9t112_set_params(priv, &rect, V4L2_MBUS_FMT_UYVY8_2X8); diff --git a/drivers/media/video/omap/omap_vout.c b/drivers/media/video/omap/omap_vout.c index 9c5c19f..ee0d0b3 100644 --- a/drivers/media/video/omap/omap_vout.c +++ b/drivers/media/video/omap/omap_vout.c @@ -38,6 +38,7 @@ #include <linux/irq.h> #include <linux/videodev2.h> #include <linux/dma-mapping.h> +#include <linux/slab.h> #include <media/videobuf-dma-contig.h> #include <media/v4l2-device.h> @@ -2169,6 +2170,14 @@ static int __init omap_vout_probe(struct platform_device *pdev) vid_dev->num_displays = 0; for_each_dss_dev(dssdev) { omap_dss_get_device(dssdev); + + if (!dssdev->driver) { + dev_warn(&pdev->dev, "no driver for display: %s\n", + dssdev->name); + omap_dss_put_device(dssdev); + continue; + } + vid_dev->displays[vid_dev->num_displays++] = dssdev; } diff --git a/drivers/media/video/omap1_camera.c b/drivers/media/video/omap1_camera.c index e87ae2f..6a6cf38 100644 --- a/drivers/media/video/omap1_camera.c +++ b/drivers/media/video/omap1_camera.c @@ -24,6 +24,7 @@ #include <linux/clk.h> #include <linux/dma-mapping.h> #include <linux/interrupt.h> +#include <linux/module.h> #include <linux/platform_device.h> #include <linux/slab.h> diff --git a/drivers/media/video/omap24xxcam-dma.c b/drivers/media/video/omap24xxcam-dma.c index 1d54b86..3ea38a8 100644 --- a/drivers/media/video/omap24xxcam-dma.c +++ b/drivers/media/video/omap24xxcam-dma.c @@ -506,7 +506,7 @@ int omap24xxcam_sgdma_queue(struct omap24xxcam_sgdma *sgdma, unsigned long flags; struct sgdma_state *sg_state; - if ((sglen < 0) || ((sglen > 0) & !sglist)) + if ((sglen < 0) || ((sglen > 0) && !sglist)) return -EINVAL; spin_lock_irqsave(&sgdma->lock, flags); diff --git a/drivers/media/video/omap3isp/ispccdc.c b/drivers/media/video/omap3isp/ispccdc.c index b0b0fa5..54a4a3f 100644 --- a/drivers/media/video/omap3isp/ispccdc.c +++ b/drivers/media/video/omap3isp/ispccdc.c @@ -1408,7 +1408,7 @@ static void ccdc_hs_vs_isr(struct isp_ccdc_device *ccdc) { struct isp_pipeline *pipe = to_isp_pipeline(&ccdc->video_out.video.entity); - struct video_device *vdev = &ccdc->subdev.devnode; + struct video_device *vdev = ccdc->subdev.devnode; struct v4l2_event event; memset(&event, 0, sizeof(event)); diff --git a/drivers/media/video/omap3isp/ispstat.c b/drivers/media/video/omap3isp/ispstat.c index 68d5394..bc0b2c7 100644 --- a/drivers/media/video/omap3isp/ispstat.c +++ b/drivers/media/video/omap3isp/ispstat.c @@ -496,7 +496,7 @@ static int isp_stat_bufs_alloc(struct ispstat *stat, u32 size) static void isp_stat_queue_event(struct ispstat *stat, int err) { - struct video_device *vdev = &stat->subdev.devnode; + struct video_device *vdev = stat->subdev.devnode; struct v4l2_event event; struct omap3isp_stat_event_status *status = (void *)event.u.data; diff --git a/drivers/media/video/omap3isp/ispvideo.c b/drivers/media/video/omap3isp/ispvideo.c index d100072..f229057 100644 --- a/drivers/media/video/omap3isp/ispvideo.c +++ b/drivers/media/video/omap3isp/ispvideo.c @@ -26,6 +26,7 @@ #include <asm/cacheflush.h> #include <linux/clk.h> #include <linux/mm.h> +#include <linux/module.h> #include <linux/pagemap.h> #include <linux/scatterlist.h> #include <linux/sched.h> diff --git a/drivers/media/video/ov6650.c b/drivers/media/video/ov6650.c index 9f2d26b..6806345 100644 --- a/drivers/media/video/ov6650.c +++ b/drivers/media/video/ov6650.c @@ -540,7 +540,7 @@ static u8 to_clkrc(struct v4l2_fract *timeperframe, static int ov6650_s_fmt(struct v4l2_subdev *sd, struct v4l2_mbus_framefmt *mf) { struct i2c_client *client = v4l2_get_subdevdata(sd); - struct soc_camera_device *icd = (struct soc_camera_device *)sd->grp_id; + struct soc_camera_device *icd = v4l2_get_subdev_hostdata(sd); struct soc_camera_sense *sense = icd->sense; struct ov6650 *priv = to_ov6650(client); bool half_scale = !is_unscaled_ok(mf->width, mf->height, &priv->rect); diff --git a/drivers/media/video/s5p-fimc/fimc-capture.c b/drivers/media/video/s5p-fimc/fimc-capture.c index c8d91b0..2cc3b91 100644 --- a/drivers/media/video/s5p-fimc/fimc-capture.c +++ b/drivers/media/video/s5p-fimc/fimc-capture.c @@ -98,6 +98,10 @@ static int fimc_capture_state_cleanup(struct fimc_dev *fimc, bool suspend) vb2_buffer_done(&buf->vb, VB2_BUF_STATE_ERROR); } set_bit(ST_CAPT_SUSPENDED, &fimc->state); + + fimc_hw_reset(fimc); + cap->buf_index = 0; + spin_unlock_irqrestore(&fimc->slock, flags); if (streaming) @@ -137,7 +141,7 @@ int fimc_capture_config_update(struct fimc_ctx *ctx) struct fimc_dev *fimc = ctx->fimc_dev; int ret; - if (test_bit(ST_CAPT_APPLY_CFG, &fimc->state)) + if (!test_bit(ST_CAPT_APPLY_CFG, &fimc->state)) return 0; spin_lock(&ctx->slock); @@ -150,7 +154,7 @@ int fimc_capture_config_update(struct fimc_ctx *ctx) fimc_hw_set_rotation(ctx); fimc_prepare_dma_offset(ctx, &ctx->d_frame); fimc_hw_set_out_dma(ctx); - set_bit(ST_CAPT_APPLY_CFG, &fimc->state); + clear_bit(ST_CAPT_APPLY_CFG, &fimc->state); } spin_unlock(&ctx->slock); return ret; @@ -164,7 +168,6 @@ static int start_streaming(struct vb2_queue *q, unsigned int count) int min_bufs; int ret; - fimc_hw_reset(fimc); vid_cap->frame_count = 0; ret = fimc_init_capture(fimc); @@ -523,7 +526,7 @@ static struct fimc_fmt *fimc_capture_try_format(struct fimc_ctx *ctx, max_w = rotation ? pl->out_rot_en_w : pl->out_rot_dis_w; min_w = ctx->state & FIMC_DST_CROP ? dst->width : var->min_out_pixsize; min_h = ctx->state & FIMC_DST_CROP ? dst->height : var->min_out_pixsize; - if (fimc->id == 1 && var->pix_hoff) + if (var->min_vsize_align == 1 && !rotation) align_h = fimc_fmt_is_rgb(ffmt->color) ? 0 : 1; depth = fimc_get_format_depth(ffmt); @@ -1239,6 +1242,7 @@ static int fimc_subdev_set_fmt(struct v4l2_subdev *sd, mutex_lock(&fimc->lock); set_frame_bounds(ff, mf->width, mf->height); + fimc->vid_cap.mf = *mf; ff->fmt = ffmt; /* Reset the crop rectangle if required. */ @@ -1375,7 +1379,7 @@ static void fimc_destroy_capture_subdev(struct fimc_dev *fimc) media_entity_cleanup(&sd->entity); v4l2_device_unregister_subdev(sd); kfree(sd); - sd = NULL; + fimc->vid_cap.subdev = NULL; } /* Set default format at the sensor and host interface */ diff --git a/drivers/media/video/s5p-fimc/fimc-core.c b/drivers/media/video/s5p-fimc/fimc-core.c index 19ca6db..07c6254 100644 --- a/drivers/media/video/s5p-fimc/fimc-core.c +++ b/drivers/media/video/s5p-fimc/fimc-core.c @@ -37,7 +37,7 @@ static char *fimc_clocks[MAX_FIMC_CLOCKS] = { static struct fimc_fmt fimc_formats[] = { { .name = "RGB565", - .fourcc = V4L2_PIX_FMT_RGB565X, + .fourcc = V4L2_PIX_FMT_RGB565, .depth = { 16 }, .color = S5P_FIMC_RGB565, .memplanes = 1, @@ -1038,12 +1038,11 @@ static int fimc_try_fmt_mplane(struct fimc_ctx *ctx, struct v4l2_format *f) mod_x = 6; /* 64 x 32 pixels tile */ mod_y = 5; } else { - if (fimc->id == 1 && variant->pix_hoff) + if (variant->min_vsize_align == 1) mod_y = fimc_fmt_is_rgb(fmt->color) ? 0 : 1; else - mod_y = mod_x; + mod_y = ffs(variant->min_vsize_align) - 1; } - dbg("mod_x: %d, mod_y: %d, max_w: %d", mod_x, mod_y, max_w); v4l_bound_align_image(&pix->width, 16, max_w, mod_x, &pix->height, 8, variant->pix_limit->scaler_dis_w, mod_y, 0); @@ -1226,10 +1225,10 @@ static int fimc_m2m_try_crop(struct fimc_ctx *ctx, struct v4l2_crop *cr) fimc->variant->min_inp_pixsize : fimc->variant->min_out_pixsize; /* Get pixel alignment constraints. */ - if (fimc->id == 1 && fimc->variant->pix_hoff) + if (fimc->variant->min_vsize_align == 1) halign = fimc_fmt_is_rgb(f->fmt->color) ? 0 : 1; else - halign = ffs(min_size) - 1; + halign = ffs(fimc->variant->min_vsize_align) - 1; for (i = 0; i < f->fmt->colplanes; i++) depth += f->fmt->depth[i]; @@ -1615,7 +1614,6 @@ static int fimc_probe(struct platform_device *pdev) pdata = pdev->dev.platform_data; fimc->pdata = pdata; - set_bit(ST_LPM, &fimc->state); init_waitqueue_head(&fimc->irq_queue); spin_lock_init(&fimc->slock); @@ -1707,8 +1705,6 @@ static int fimc_runtime_resume(struct device *dev) /* Enable clocks and perform basic initalization */ clk_enable(fimc->clock[CLK_GATE]); fimc_hw_reset(fimc); - if (fimc->variant->out_buf_count > 4) - fimc_hw_set_dma_seq(fimc, 0xF); /* Resume the capture or mem-to-mem device */ if (fimc_capture_busy(fimc)) @@ -1750,8 +1746,6 @@ static int fimc_resume(struct device *dev) return 0; } fimc_hw_reset(fimc); - if (fimc->variant->out_buf_count > 4) - fimc_hw_set_dma_seq(fimc, 0xF); spin_unlock_irqrestore(&fimc->slock, flags); if (fimc_capture_busy(fimc)) @@ -1780,7 +1774,6 @@ static int __devexit fimc_remove(struct platform_device *pdev) struct fimc_dev *fimc = platform_get_drvdata(pdev); pm_runtime_disable(&pdev->dev); - fimc_runtime_suspend(&pdev->dev); pm_runtime_set_suspended(&pdev->dev); vb2_dma_contig_cleanup_ctx(fimc->alloc_ctx); @@ -1840,6 +1833,7 @@ static struct samsung_fimc_variant fimc0_variant_s5p = { .min_inp_pixsize = 16, .min_out_pixsize = 16, .hor_offs_align = 8, + .min_vsize_align = 16, .out_buf_count = 4, .pix_limit = &s5p_pix_limit[0], }; @@ -1849,6 +1843,7 @@ static struct samsung_fimc_variant fimc2_variant_s5p = { .min_inp_pixsize = 16, .min_out_pixsize = 16, .hor_offs_align = 8, + .min_vsize_align = 16, .out_buf_count = 4, .pix_limit = &s5p_pix_limit[1], }; @@ -1861,6 +1856,7 @@ static struct samsung_fimc_variant fimc0_variant_s5pv210 = { .min_inp_pixsize = 16, .min_out_pixsize = 16, .hor_offs_align = 8, + .min_vsize_align = 16, .out_buf_count = 4, .pix_limit = &s5p_pix_limit[1], }; @@ -1874,6 +1870,7 @@ static struct samsung_fimc_variant fimc1_variant_s5pv210 = { .min_inp_pixsize = 16, .min_out_pixsize = 16, .hor_offs_align = 1, + .min_vsize_align = 1, .out_buf_count = 4, .pix_limit = &s5p_pix_limit[2], }; @@ -1884,6 +1881,7 @@ static struct samsung_fimc_variant fimc2_variant_s5pv210 = { .min_inp_pixsize = 16, .min_out_pixsize = 16, .hor_offs_align = 8, + .min_vsize_align = 16, .out_buf_count = 4, .pix_limit = &s5p_pix_limit[2], }; @@ -1898,6 +1896,7 @@ static struct samsung_fimc_variant fimc0_variant_exynos4 = { .min_inp_pixsize = 16, .min_out_pixsize = 16, .hor_offs_align = 2, + .min_vsize_align = 1, .out_buf_count = 32, .pix_limit = &s5p_pix_limit[1], }; @@ -1910,6 +1909,7 @@ static struct samsung_fimc_variant fimc3_variant_exynos4 = { .min_inp_pixsize = 16, .min_out_pixsize = 16, .hor_offs_align = 2, + .min_vsize_align = 1, .out_buf_count = 32, .pix_limit = &s5p_pix_limit[3], }; diff --git a/drivers/media/video/s5p-fimc/fimc-core.h b/drivers/media/video/s5p-fimc/fimc-core.h index a6936da..c7f01c4 100644 --- a/drivers/media/video/s5p-fimc/fimc-core.h +++ b/drivers/media/video/s5p-fimc/fimc-core.h @@ -377,6 +377,7 @@ struct fimc_pix_limit { * @min_inp_pixsize: minimum input pixel size * @min_out_pixsize: minimum output pixel size * @hor_offs_align: horizontal pixel offset aligment + * @min_vsize_align: minimum vertical pixel size alignment * @out_buf_count: the number of buffers in output DMA sequence */ struct samsung_fimc_variant { @@ -390,6 +391,7 @@ struct samsung_fimc_variant { u16 min_inp_pixsize; u16 min_out_pixsize; u16 hor_offs_align; + u16 min_vsize_align; u16 out_buf_count; }; diff --git a/drivers/media/video/s5p-fimc/fimc-mdevice.c b/drivers/media/video/s5p-fimc/fimc-mdevice.c index cc337b1..615c862 100644 --- a/drivers/media/video/s5p-fimc/fimc-mdevice.c +++ b/drivers/media/video/s5p-fimc/fimc-mdevice.c @@ -220,6 +220,7 @@ static struct v4l2_subdev *fimc_md_register_sensor(struct fimc_md *fmd, sd = v4l2_i2c_new_subdev_board(&fmd->v4l2_dev, adapter, s_info->pdata->board_info, NULL); if (IS_ERR_OR_NULL(sd)) { + i2c_put_adapter(adapter); v4l2_err(&fmd->v4l2_dev, "Failed to acquire subdev\n"); return NULL; } @@ -234,12 +235,15 @@ static struct v4l2_subdev *fimc_md_register_sensor(struct fimc_md *fmd, static void fimc_md_unregister_sensor(struct v4l2_subdev *sd) { struct i2c_client *client = v4l2_get_subdevdata(sd); + struct i2c_adapter *adapter; if (!client) return; v4l2_device_unregister_subdev(sd); + adapter = client->adapter; i2c_unregister_device(client); - i2c_put_adapter(client->adapter); + if (adapter) + i2c_put_adapter(adapter); } static int fimc_md_register_sensor_entities(struct fimc_md *fmd) @@ -381,20 +385,28 @@ static void fimc_md_unregister_entities(struct fimc_md *fmd) static int fimc_md_register_video_nodes(struct fimc_md *fmd) { + struct video_device *vdev; int i, ret = 0; for (i = 0; i < FIMC_MAX_DEVS && !ret; i++) { if (!fmd->fimc[i]) continue; - if (fmd->fimc[i]->m2m.vfd) - ret = video_register_device(fmd->fimc[i]->m2m.vfd, - VFL_TYPE_GRABBER, -1); - if (ret) - break; - if (fmd->fimc[i]->vid_cap.vfd) - ret = video_register_device(fmd->fimc[i]->vid_cap.vfd, - VFL_TYPE_GRABBER, -1); + vdev = fmd->fimc[i]->m2m.vfd; + if (vdev) { + ret = video_register_device(vdev, VFL_TYPE_GRABBER, -1); + if (ret) + break; + v4l2_info(&fmd->v4l2_dev, "Registered %s as /dev/%s\n", + vdev->name, video_device_node_name(vdev)); + } + + vdev = fmd->fimc[i]->vid_cap.vfd; + if (vdev == NULL) + continue; + ret = video_register_device(vdev, VFL_TYPE_GRABBER, -1); + v4l2_info(&fmd->v4l2_dev, "Registered %s as /dev/%s\n", + vdev->name, video_device_node_name(vdev)); } return ret; @@ -502,7 +514,7 @@ static int fimc_md_create_links(struct fimc_md *fmd) if (WARN(csis == NULL, "MIPI-CSI interface specified " "but s5p-csis module is not loaded!\n")) - continue; + return -EINVAL; ret = media_entity_create_link(&sensor->entity, 0, &csis->entity, CSIS_PAD_SINK, @@ -742,9 +754,6 @@ static int __devinit fimc_md_probe(struct platform_device *pdev) struct fimc_md *fmd; int ret; - if (WARN(!pdev->dev.platform_data, "Platform data not specified!\n")) - return -EINVAL; - fmd = kzalloc(sizeof(struct fimc_md), GFP_KERNEL); if (!fmd) return -ENOMEM; @@ -782,9 +791,11 @@ static int __devinit fimc_md_probe(struct platform_device *pdev) if (ret) goto err3; - ret = fimc_md_register_sensor_entities(fmd); - if (ret) - goto err3; + if (pdev->dev.platform_data) { + ret = fimc_md_register_sensor_entities(fmd); + if (ret) + goto err3; + } ret = fimc_md_create_links(fmd); if (ret) goto err3; diff --git a/drivers/media/video/s5p-fimc/fimc-reg.c b/drivers/media/video/s5p-fimc/fimc-reg.c index 20e664e..44f5c2d 100644 --- a/drivers/media/video/s5p-fimc/fimc-reg.c +++ b/drivers/media/video/s5p-fimc/fimc-reg.c @@ -35,6 +35,9 @@ void fimc_hw_reset(struct fimc_dev *dev) cfg = readl(dev->regs + S5P_CIGCTRL); cfg &= ~S5P_CIGCTRL_SWRST; writel(cfg, dev->regs + S5P_CIGCTRL); + + if (dev->variant->out_buf_count > 4) + fimc_hw_set_dma_seq(dev, 0xF); } static u32 fimc_hw_get_in_flip(struct fimc_ctx *ctx) @@ -251,7 +254,14 @@ static void fimc_hw_set_scaler(struct fimc_ctx *ctx) struct fimc_scaler *sc = &ctx->scaler; struct fimc_frame *src_frame = &ctx->s_frame; struct fimc_frame *dst_frame = &ctx->d_frame; - u32 cfg = 0; + + u32 cfg = readl(dev->regs + S5P_CISCCTRL); + + cfg &= ~(S5P_CISCCTRL_CSCR2Y_WIDE | S5P_CISCCTRL_CSCY2R_WIDE | + S5P_CISCCTRL_SCALEUP_H | S5P_CISCCTRL_SCALEUP_V | + S5P_CISCCTRL_SCALERBYPASS | S5P_CISCCTRL_ONE2ONE | + S5P_CISCCTRL_INRGB_FMT_MASK | S5P_CISCCTRL_OUTRGB_FMT_MASK | + S5P_CISCCTRL_INTERLACE | S5P_CISCCTRL_RGB_EXT); if (!(ctx->flags & FIMC_COLOR_RANGE_NARROW)) cfg |= (S5P_CISCCTRL_CSCR2Y_WIDE | S5P_CISCCTRL_CSCY2R_WIDE); @@ -308,9 +318,9 @@ void fimc_hw_set_mainscaler(struct fimc_ctx *ctx) fimc_hw_set_scaler(ctx); cfg = readl(dev->regs + S5P_CISCCTRL); + cfg &= ~(S5P_CISCCTRL_MHRATIO_MASK | S5P_CISCCTRL_MVRATIO_MASK); if (variant->has_mainscaler_ext) { - cfg &= ~(S5P_CISCCTRL_MHRATIO_MASK | S5P_CISCCTRL_MVRATIO_MASK); cfg |= S5P_CISCCTRL_MHRATIO_EXT(sc->main_hratio); cfg |= S5P_CISCCTRL_MVRATIO_EXT(sc->main_vratio); writel(cfg, dev->regs + S5P_CISCCTRL); @@ -323,7 +333,6 @@ void fimc_hw_set_mainscaler(struct fimc_ctx *ctx) cfg |= S5P_CIEXTEN_MVRATIO_EXT(sc->main_vratio); writel(cfg, dev->regs + S5P_CIEXTEN); } else { - cfg &= ~(S5P_CISCCTRL_MHRATIO_MASK | S5P_CISCCTRL_MVRATIO_MASK); cfg |= S5P_CISCCTRL_MHRATIO(sc->main_hratio); cfg |= S5P_CISCCTRL_MVRATIO(sc->main_vratio); writel(cfg, dev->regs + S5P_CISCCTRL); diff --git a/drivers/media/video/s5p-mfc/s5p_mfc_enc.c b/drivers/media/video/s5p-mfc/s5p_mfc_enc.c index 1e8cdb7..dff9dc7 100644 --- a/drivers/media/video/s5p-mfc/s5p_mfc_enc.c +++ b/drivers/media/video/s5p-mfc/s5p_mfc_enc.c @@ -61,7 +61,7 @@ static struct s5p_mfc_fmt formats[] = { .num_planes = 1, }, { - .name = "H264 Encoded Stream", + .name = "H263 Encoded Stream", .fourcc = V4L2_PIX_FMT_H263, .codec_mode = S5P_FIMV_CODEC_H263_ENC, .type = MFC_FMT_ENC, diff --git a/drivers/media/video/s5p-tv/mixer_video.c b/drivers/media/video/s5p-tv/mixer_video.c index e16d3a4..b47d0c0 100644 --- a/drivers/media/video/s5p-tv/mixer_video.c +++ b/drivers/media/video/s5p-tv/mixer_video.c @@ -16,6 +16,7 @@ #include <media/v4l2-ioctl.h> #include <linux/videodev2.h> #include <linux/mm.h> +#include <linux/module.h> #include <linux/version.h> #include <linux/timer.h> #include <media/videobuf2-dma-contig.h> diff --git a/drivers/media/video/sh_mobile_ceu_camera.c b/drivers/media/video/sh_mobile_ceu_camera.c index f390682..c51decf 100644 --- a/drivers/media/video/sh_mobile_ceu_camera.c +++ b/drivers/media/video/sh_mobile_ceu_camera.c @@ -566,8 +566,10 @@ static int sh_mobile_ceu_add_device(struct soc_camera_device *icd) ret = sh_mobile_ceu_soft_reset(pcdev); csi2_sd = find_csi2(pcdev); - if (csi2_sd) - csi2_sd->grp_id = (long)icd; + if (csi2_sd) { + csi2_sd->grp_id = soc_camera_grp_id(icd); + v4l2_set_subdev_hostdata(csi2_sd, icd); + } ret = v4l2_subdev_call(csi2_sd, core, s_power, 1); if (ret < 0 && ret != -ENOIOCTLCMD && ret != -ENODEV) { @@ -768,7 +770,7 @@ static struct v4l2_subdev *find_bus_subdev(struct sh_mobile_ceu_dev *pcdev, { if (pcdev->csi2_pdev) { struct v4l2_subdev *csi2_sd = find_csi2(pcdev); - if (csi2_sd && csi2_sd->grp_id == (u32)icd) + if (csi2_sd && csi2_sd->grp_id == soc_camera_grp_id(icd)) return csi2_sd; } @@ -1089,8 +1091,9 @@ static int sh_mobile_ceu_get_formats(struct soc_camera_device *icd, unsigned int /* Try 2560x1920, 1280x960, 640x480, 320x240 */ mf.width = 2560 >> shift; mf.height = 1920 >> shift; - ret = v4l2_device_call_until_err(sd->v4l2_dev, (long)icd, video, - s_mbus_fmt, &mf); + ret = v4l2_device_call_until_err(sd->v4l2_dev, + soc_camera_grp_id(icd), video, + s_mbus_fmt, &mf); if (ret < 0) return ret; shift++; @@ -1389,7 +1392,8 @@ static int client_s_fmt(struct soc_camera_device *icd, bool ceu_1to1; int ret; - ret = v4l2_device_call_until_err(sd->v4l2_dev, (long)icd, video, + ret = v4l2_device_call_until_err(sd->v4l2_dev, + soc_camera_grp_id(icd), video, s_mbus_fmt, mf); if (ret < 0) return ret; @@ -1426,8 +1430,9 @@ static int client_s_fmt(struct soc_camera_device *icd, tmp_h = min(2 * tmp_h, max_height); mf->width = tmp_w; mf->height = tmp_h; - ret = v4l2_device_call_until_err(sd->v4l2_dev, (long)icd, video, - s_mbus_fmt, mf); + ret = v4l2_device_call_until_err(sd->v4l2_dev, + soc_camera_grp_id(icd), video, + s_mbus_fmt, mf); dev_geo(dev, "Camera scaled to %ux%u\n", mf->width, mf->height); if (ret < 0) { @@ -1580,8 +1585,9 @@ static int sh_mobile_ceu_set_crop(struct soc_camera_device *icd, } if (interm_width < icd->user_width || interm_height < icd->user_height) { - ret = v4l2_device_call_until_err(sd->v4l2_dev, (int)icd, video, - s_mbus_fmt, &mf); + ret = v4l2_device_call_until_err(sd->v4l2_dev, + soc_camera_grp_id(icd), video, + s_mbus_fmt, &mf); if (ret < 0) return ret; @@ -1867,7 +1873,8 @@ static int sh_mobile_ceu_try_fmt(struct soc_camera_device *icd, mf.code = xlate->code; mf.colorspace = pix->colorspace; - ret = v4l2_device_call_until_err(sd->v4l2_dev, (long)icd, video, try_mbus_fmt, &mf); + ret = v4l2_device_call_until_err(sd->v4l2_dev, soc_camera_grp_id(icd), + video, try_mbus_fmt, &mf); if (ret < 0) return ret; @@ -1891,8 +1898,9 @@ static int sh_mobile_ceu_try_fmt(struct soc_camera_device *icd, */ mf.width = 2560; mf.height = 1920; - ret = v4l2_device_call_until_err(sd->v4l2_dev, (long)icd, video, - try_mbus_fmt, &mf); + ret = v4l2_device_call_until_err(sd->v4l2_dev, + soc_camera_grp_id(icd), video, + try_mbus_fmt, &mf); if (ret < 0) { /* Shouldn't actually happen... */ dev_err(icd->parent, diff --git a/drivers/media/video/sh_mobile_csi2.c b/drivers/media/video/sh_mobile_csi2.c index ea4f047..8a652b5 100644 --- a/drivers/media/video/sh_mobile_csi2.c +++ b/drivers/media/video/sh_mobile_csi2.c @@ -143,7 +143,7 @@ static int sh_csi2_s_mbus_config(struct v4l2_subdev *sd, const struct v4l2_mbus_config *cfg) { struct sh_csi2 *priv = container_of(sd, struct sh_csi2, subdev); - struct soc_camera_device *icd = (struct soc_camera_device *)sd->grp_id; + struct soc_camera_device *icd = v4l2_get_subdev_hostdata(sd); struct v4l2_subdev *client_sd = soc_camera_to_subdev(icd); struct v4l2_mbus_config client_cfg = {.type = V4L2_MBUS_CSI2, .flags = priv->mipi_flags}; @@ -202,7 +202,7 @@ static void sh_csi2_hwinit(struct sh_csi2 *priv) static int sh_csi2_client_connect(struct sh_csi2 *priv) { struct sh_csi2_pdata *pdata = priv->pdev->dev.platform_data; - struct soc_camera_device *icd = (struct soc_camera_device *)priv->subdev.grp_id; + struct soc_camera_device *icd = v4l2_get_subdev_hostdata(&priv->subdev); struct v4l2_subdev *client_sd = soc_camera_to_subdev(icd); struct device *dev = v4l2_get_subdevdata(&priv->subdev); struct v4l2_mbus_config cfg; diff --git a/drivers/media/video/soc_camera.c b/drivers/media/video/soc_camera.c index b72580c..62e4312 100644 --- a/drivers/media/video/soc_camera.c +++ b/drivers/media/video/soc_camera.c @@ -1103,7 +1103,8 @@ static int soc_camera_probe(struct soc_camera_device *icd) } sd = soc_camera_to_subdev(icd); - sd->grp_id = (long)icd; + sd->grp_id = soc_camera_grp_id(icd); + v4l2_set_subdev_hostdata(sd, icd); if (v4l2_ctrl_add_handler(&icd->ctrl_handler, sd->ctrl_handler)) goto ectrl; diff --git a/drivers/mfd/ab5500-debugfs.c b/drivers/mfd/ab5500-debugfs.c index 43c0ebb..b7b2d348 100644 --- a/drivers/mfd/ab5500-debugfs.c +++ b/drivers/mfd/ab5500-debugfs.c @@ -4,7 +4,7 @@ * Debugfs support for the AB5500 MFD driver */ -#include <linux/export.h> +#include <linux/module.h> #include <linux/debugfs.h> #include <linux/seq_file.h> #include <linux/mfd/ab5500/ab5500.h> diff --git a/drivers/mfd/ab8500-core.c b/drivers/mfd/ab8500-core.c index 1e91738..d3d572b 100644 --- a/drivers/mfd/ab8500-core.c +++ b/drivers/mfd/ab8500-core.c @@ -620,6 +620,7 @@ static struct resource __devinitdata ab8500_fg_resources[] = { static struct resource __devinitdata ab8500_chargalg_resources[] = {}; +#ifdef CONFIG_DEBUG_FS static struct resource __devinitdata ab8500_debug_resources[] = { { .name = "IRQ_FIRST", @@ -634,6 +635,7 @@ static struct resource __devinitdata ab8500_debug_resources[] = { .flags = IORESOURCE_IRQ, }, }; +#endif static struct resource __devinitdata ab8500_usb_resources[] = { { diff --git a/drivers/mfd/adp5520.c b/drivers/mfd/adp5520.c index f1d8848..8d816cc 100644 --- a/drivers/mfd/adp5520.c +++ b/drivers/mfd/adp5520.c @@ -109,7 +109,7 @@ int adp5520_set_bits(struct device *dev, int reg, uint8_t bit_mask) ret = __adp5520_read(chip->client, reg, ®_val); - if (!ret && ((reg_val & bit_mask) == 0)) { + if (!ret && ((reg_val & bit_mask) != bit_mask)) { reg_val |= bit_mask; ret = __adp5520_write(chip->client, reg, reg_val); } diff --git a/drivers/mfd/da903x.c b/drivers/mfd/da903x.c index 1b79c37..1924b85 100644 --- a/drivers/mfd/da903x.c +++ b/drivers/mfd/da903x.c @@ -182,7 +182,7 @@ int da903x_set_bits(struct device *dev, int reg, uint8_t bit_mask) if (ret) goto out; - if ((reg_val & bit_mask) == 0) { + if ((reg_val & bit_mask) != bit_mask) { reg_val |= bit_mask; ret = __da903x_write(chip->client, reg, reg_val); } @@ -549,6 +549,7 @@ static int __devexit da903x_remove(struct i2c_client *client) struct da903x_chip *chip = i2c_get_clientdata(client); da903x_remove_subdevs(chip); + free_irq(client->irq, chip); kfree(chip); return 0; } diff --git a/drivers/mfd/jz4740-adc.c b/drivers/mfd/jz4740-adc.c index 1e9ee53..ef39528 100644 --- a/drivers/mfd/jz4740-adc.c +++ b/drivers/mfd/jz4740-adc.c @@ -16,6 +16,7 @@ */ #include <linux/err.h> +#include <linux/io.h> #include <linux/irq.h> #include <linux/interrupt.h> #include <linux/kernel.h> diff --git a/drivers/mfd/tps6586x.c b/drivers/mfd/tps6586x.c index bba26d9..a5ddf31 100644 --- a/drivers/mfd/tps6586x.c +++ b/drivers/mfd/tps6586x.c @@ -197,7 +197,7 @@ int tps6586x_set_bits(struct device *dev, int reg, uint8_t bit_mask) if (ret) goto out; - if ((reg_val & bit_mask) == 0) { + if ((reg_val & bit_mask) != bit_mask) { reg_val |= bit_mask; ret = __tps6586x_write(to_i2c_client(dev), reg, reg_val); } diff --git a/drivers/mfd/tps65910.c b/drivers/mfd/tps65910.c index 6f5b8cf..c1da84b 100644 --- a/drivers/mfd/tps65910.c +++ b/drivers/mfd/tps65910.c @@ -120,7 +120,7 @@ int tps65910_clear_bits(struct tps65910 *tps65910, u8 reg, u8 mask) goto out; } - data &= mask; + data &= ~mask; err = tps65910_i2c_write(tps65910, reg, 1, &data); if (err) dev_err(tps65910->dev, "write to reg %x failed\n", reg); diff --git a/drivers/mfd/twl-core.c b/drivers/mfd/twl-core.c index bfbd660..61e70cf 100644 --- a/drivers/mfd/twl-core.c +++ b/drivers/mfd/twl-core.c @@ -363,13 +363,13 @@ int twl_i2c_write(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes) pr_err("%s: invalid module number %d\n", DRIVER_NAME, mod_no); return -EPERM; } - sid = twl_map[mod_no].sid; - twl = &twl_modules[sid]; - if (unlikely(!inuse)) { - pr_err("%s: client %d is not initialized\n", DRIVER_NAME, sid); + pr_err("%s: not initialized\n", DRIVER_NAME); return -EPERM; } + sid = twl_map[mod_no].sid; + twl = &twl_modules[sid]; + mutex_lock(&twl->xfer_lock); /* * [MSG1]: fill the register address data @@ -420,13 +420,13 @@ int twl_i2c_read(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes) pr_err("%s: invalid module number %d\n", DRIVER_NAME, mod_no); return -EPERM; } - sid = twl_map[mod_no].sid; - twl = &twl_modules[sid]; - if (unlikely(!inuse)) { - pr_err("%s: client %d is not initialized\n", DRIVER_NAME, sid); + pr_err("%s: not initialized\n", DRIVER_NAME); return -EPERM; } + sid = twl_map[mod_no].sid; + twl = &twl_modules[sid]; + mutex_lock(&twl->xfer_lock); /* [MSG1] fill the register address data */ msg = &twl->xfer_msg[0]; diff --git a/drivers/mfd/twl4030-irq.c b/drivers/mfd/twl4030-irq.c index f062c8c..29f11e0 100644 --- a/drivers/mfd/twl4030-irq.c +++ b/drivers/mfd/twl4030-irq.c @@ -432,6 +432,7 @@ struct sih_agent { u32 edge_change; struct mutex irq_lock; + char *irq_name; }; /*----------------------------------------------------------------------*/ @@ -589,7 +590,7 @@ static inline int sih_read_isr(const struct sih *sih) * Generic handler for SIH interrupts ... we "know" this is called * in task context, with IRQs enabled. */ -static void handle_twl4030_sih(unsigned irq, struct irq_desc *desc) +static irqreturn_t handle_twl4030_sih(int irq, void *data) { struct sih_agent *agent = irq_get_handler_data(irq); const struct sih *sih = agent->sih; @@ -602,7 +603,7 @@ static void handle_twl4030_sih(unsigned irq, struct irq_desc *desc) pr_err("twl4030: %s SIH, read ISR error %d\n", sih->name, isr); /* REVISIT: recover; eventually mask it all, etc */ - return; + return IRQ_HANDLED; } while (isr) { @@ -616,6 +617,7 @@ static void handle_twl4030_sih(unsigned irq, struct irq_desc *desc) pr_err("twl4030: %s SIH, invalid ISR bit %d\n", sih->name, irq); } + return IRQ_HANDLED; } static unsigned twl4030_irq_next; @@ -668,18 +670,19 @@ int twl4030_sih_setup(int module) activate_irq(irq); } - status = irq_base; twl4030_irq_next += i; /* replace generic PIH handler (handle_simple_irq) */ irq = sih_mod + twl4030_irq_base; irq_set_handler_data(irq, agent); - irq_set_chained_handler(irq, handle_twl4030_sih); + agent->irq_name = kasprintf(GFP_KERNEL, "twl4030_%s", sih->name); + status = request_threaded_irq(irq, NULL, handle_twl4030_sih, 0, + agent->irq_name ?: sih->name, NULL); pr_info("twl4030: %s (irq %d) chaining IRQs %d..%d\n", sih->name, irq, irq_base, twl4030_irq_next - 1); - return status; + return status < 0 ? status : irq_base; } /* FIXME need a call to reverse twl4030_sih_setup() ... */ @@ -733,8 +736,9 @@ int twl4030_init_irq(int irq_num, unsigned irq_base, unsigned irq_end) } /* install an irq handler to demultiplex the TWL4030 interrupt */ - status = request_threaded_irq(irq_num, NULL, handle_twl4030_pih, 0, - "TWL4030-PIH", NULL); + status = request_threaded_irq(irq_num, NULL, handle_twl4030_pih, + IRQF_ONESHOT, + "TWL4030-PIH", NULL); if (status < 0) { pr_err("twl4030: could not claim irq%d: %d\n", irq_num, status); goto fail_rqirq; diff --git a/drivers/mfd/wm8994-core.c b/drivers/mfd/wm8994-core.c index 5d6ba13..61894fc 100644 --- a/drivers/mfd/wm8994-core.c +++ b/drivers/mfd/wm8994-core.c @@ -239,6 +239,7 @@ static int wm8994_suspend(struct device *dev) switch (wm8994->type) { case WM8958: + case WM1811: ret = wm8994_reg_read(wm8994, WM8958_MIC_DETECT_1); if (ret < 0) { dev_err(dev, "Failed to read power status: %d\n", ret); diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c index e8a5eb3..d31c78b 100644 --- a/drivers/mmc/core/host.c +++ b/drivers/mmc/core/host.c @@ -302,17 +302,6 @@ struct mmc_host *mmc_alloc_host(int extra, struct device *dev) host->max_blk_size = 512; host->max_blk_count = PAGE_CACHE_SIZE / 512; - /* - * Enable runtime power management by default. This flag was added due - * to runtime power management causing disruption for some users, but - * the power on/off code has been improved since then. - * - * We'll enable this flag by default as an experiment, and if no - * problems are reported, we will follow up later and remove the flag - * altogether. - */ - host->caps = MMC_CAP_POWER_OFF_CARD; - return host; free: diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c index 50b5f99..0726e59 100644 --- a/drivers/mmc/host/mmci.c +++ b/drivers/mmc/host/mmci.c @@ -675,7 +675,8 @@ mmci_data_irq(struct mmci_host *host, struct mmc_data *data, unsigned int status) { /* First check for errors */ - if (status & (MCI_DATACRCFAIL|MCI_DATATIMEOUT|MCI_TXUNDERRUN|MCI_RXOVERRUN)) { + if (status & (MCI_DATACRCFAIL|MCI_DATATIMEOUT|MCI_STARTBITERR| + MCI_TXUNDERRUN|MCI_RXOVERRUN)) { u32 remain, success; /* Terminate the DMA transfer */ @@ -754,8 +755,12 @@ mmci_cmd_irq(struct mmci_host *host, struct mmc_command *cmd, } if (!cmd->data || cmd->error) { - if (host->data) + if (host->data) { + /* Terminate the DMA transfer */ + if (dma_inprogress(host)) + mmci_dma_data_error(host); mmci_stop_data(host); + } mmci_request_end(host, cmd->mrq); } else if (!(cmd->data->flags & MMC_DATA_READ)) { mmci_start_data(host, cmd->data); @@ -955,8 +960,9 @@ static irqreturn_t mmci_irq(int irq, void *dev_id) dev_dbg(mmc_dev(host->mmc), "irq0 (data+cmd) %08x\n", status); data = host->data; - if (status & (MCI_DATACRCFAIL|MCI_DATATIMEOUT|MCI_TXUNDERRUN| - MCI_RXOVERRUN|MCI_DATAEND|MCI_DATABLOCKEND) && data) + if (status & (MCI_DATACRCFAIL|MCI_DATATIMEOUT|MCI_STARTBITERR| + MCI_TXUNDERRUN|MCI_RXOVERRUN|MCI_DATAEND| + MCI_DATABLOCKEND) && data) mmci_data_irq(host, data, status); cmd = host->cmd; diff --git a/drivers/mmc/host/sdhci-cns3xxx.c b/drivers/mmc/host/sdhci-cns3xxx.c index 87b6f07..b4257e7 100644 --- a/drivers/mmc/host/sdhci-cns3xxx.c +++ b/drivers/mmc/host/sdhci-cns3xxx.c @@ -109,13 +109,10 @@ static struct platform_driver sdhci_cns3xxx_driver = { .driver = { .name = "sdhci-cns3xxx", .owner = THIS_MODULE, + .pm = SDHCI_PLTFM_PMOPS, }, .probe = sdhci_cns3xxx_probe, .remove = __devexit_p(sdhci_cns3xxx_remove), -#ifdef CONFIG_PM - .suspend = sdhci_pltfm_suspend, - .resume = sdhci_pltfm_resume, -#endif }; static int __init sdhci_cns3xxx_init(void) diff --git a/drivers/mmc/host/sdhci-dove.c b/drivers/mmc/host/sdhci-dove.c index f2d29dc..a81312c 100644 --- a/drivers/mmc/host/sdhci-dove.c +++ b/drivers/mmc/host/sdhci-dove.c @@ -82,13 +82,10 @@ static struct platform_driver sdhci_dove_driver = { .driver = { .name = "sdhci-dove", .owner = THIS_MODULE, + .pm = SDHCI_PLTFM_PMOPS, }, .probe = sdhci_dove_probe, .remove = __devexit_p(sdhci_dove_remove), -#ifdef CONFIG_PM - .suspend = sdhci_pltfm_suspend, - .resume = sdhci_pltfm_resume, -#endif }; static int __init sdhci_dove_init(void) diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c index 4b976f0..38ebc4e 100644 --- a/drivers/mmc/host/sdhci-esdhc-imx.c +++ b/drivers/mmc/host/sdhci-esdhc-imx.c @@ -599,14 +599,11 @@ static struct platform_driver sdhci_esdhc_imx_driver = { .name = "sdhci-esdhc-imx", .owner = THIS_MODULE, .of_match_table = imx_esdhc_dt_ids, + .pm = SDHCI_PLTFM_PMOPS, }, .id_table = imx_esdhc_devtype, .probe = sdhci_esdhc_imx_probe, .remove = __devexit_p(sdhci_esdhc_imx_remove), -#ifdef CONFIG_PM - .suspend = sdhci_pltfm_suspend, - .resume = sdhci_pltfm_resume, -#endif }; static int __init sdhci_esdhc_imx_init(void) diff --git a/drivers/mmc/host/sdhci-of-esdhc.c b/drivers/mmc/host/sdhci-of-esdhc.c index 59e9d00..01e5f62 100644 --- a/drivers/mmc/host/sdhci-of-esdhc.c +++ b/drivers/mmc/host/sdhci-of-esdhc.c @@ -125,13 +125,10 @@ static struct platform_driver sdhci_esdhc_driver = { .name = "sdhci-esdhc", .owner = THIS_MODULE, .of_match_table = sdhci_esdhc_of_match, + .pm = SDHCI_PLTFM_PMOPS, }, .probe = sdhci_esdhc_probe, .remove = __devexit_p(sdhci_esdhc_remove), -#ifdef CONFIG_PM - .suspend = sdhci_pltfm_suspend, - .resume = sdhci_pltfm_resume, -#endif }; static int __init sdhci_esdhc_init(void) diff --git a/drivers/mmc/host/sdhci-of-hlwd.c b/drivers/mmc/host/sdhci-of-hlwd.c index 9b0d794..3619adc 100644 --- a/drivers/mmc/host/sdhci-of-hlwd.c +++ b/drivers/mmc/host/sdhci-of-hlwd.c @@ -87,13 +87,10 @@ static struct platform_driver sdhci_hlwd_driver = { .name = "sdhci-hlwd", .owner = THIS_MODULE, .of_match_table = sdhci_hlwd_of_match, + .pm = SDHCI_PLTFM_PMOPS, }, .probe = sdhci_hlwd_probe, .remove = __devexit_p(sdhci_hlwd_remove), -#ifdef CONFIG_PM - .suspend = sdhci_pltfm_suspend, - .resume = sdhci_pltfm_resume, -#endif }; static int __init sdhci_hlwd_init(void) diff --git a/drivers/mmc/host/sdhci-pci.c b/drivers/mmc/host/sdhci-pci.c index d833d9c..6878a946 100644 --- a/drivers/mmc/host/sdhci-pci.c +++ b/drivers/mmc/host/sdhci-pci.c @@ -54,8 +54,7 @@ struct sdhci_pci_fixes { int (*probe_slot) (struct sdhci_pci_slot *); void (*remove_slot) (struct sdhci_pci_slot *, int); - int (*suspend) (struct sdhci_pci_chip *, - pm_message_t); + int (*suspend) (struct sdhci_pci_chip *); int (*resume) (struct sdhci_pci_chip *); }; @@ -549,7 +548,7 @@ static void jmicron_remove_slot(struct sdhci_pci_slot *slot, int dead) jmicron_enable_mmc(slot->host, 0); } -static int jmicron_suspend(struct sdhci_pci_chip *chip, pm_message_t state) +static int jmicron_suspend(struct sdhci_pci_chip *chip) { int i; @@ -993,8 +992,9 @@ static struct sdhci_ops sdhci_pci_ops = { #ifdef CONFIG_PM -static int sdhci_pci_suspend(struct pci_dev *pdev, pm_message_t state) +static int sdhci_pci_suspend(struct device *dev) { + struct pci_dev *pdev = to_pci_dev(dev); struct sdhci_pci_chip *chip; struct sdhci_pci_slot *slot; mmc_pm_flag_t slot_pm_flags; @@ -1010,7 +1010,7 @@ static int sdhci_pci_suspend(struct pci_dev *pdev, pm_message_t state) if (!slot) continue; - ret = sdhci_suspend_host(slot->host, state); + ret = sdhci_suspend_host(slot->host); if (ret) { for (i--; i >= 0; i--) @@ -1026,7 +1026,7 @@ static int sdhci_pci_suspend(struct pci_dev *pdev, pm_message_t state) } if (chip->fixes && chip->fixes->suspend) { - ret = chip->fixes->suspend(chip, state); + ret = chip->fixes->suspend(chip); if (ret) { for (i = chip->num_slots - 1; i >= 0; i--) sdhci_resume_host(chip->slots[i]->host); @@ -1042,16 +1042,17 @@ static int sdhci_pci_suspend(struct pci_dev *pdev, pm_message_t state) } pci_set_power_state(pdev, PCI_D3hot); } else { - pci_enable_wake(pdev, pci_choose_state(pdev, state), 0); + pci_enable_wake(pdev, PCI_D3hot, 0); pci_disable_device(pdev); - pci_set_power_state(pdev, pci_choose_state(pdev, state)); + pci_set_power_state(pdev, PCI_D3hot); } return 0; } -static int sdhci_pci_resume(struct pci_dev *pdev) +static int sdhci_pci_resume(struct device *dev) { + struct pci_dev *pdev = to_pci_dev(dev); struct sdhci_pci_chip *chip; struct sdhci_pci_slot *slot; int i, ret; @@ -1099,7 +1100,6 @@ static int sdhci_pci_runtime_suspend(struct device *dev) struct pci_dev *pdev = container_of(dev, struct pci_dev, dev); struct sdhci_pci_chip *chip; struct sdhci_pci_slot *slot; - pm_message_t state = { .event = PM_EVENT_SUSPEND }; int i, ret; chip = pci_get_drvdata(pdev); @@ -1121,7 +1121,7 @@ static int sdhci_pci_runtime_suspend(struct device *dev) } if (chip->fixes && chip->fixes->suspend) { - ret = chip->fixes->suspend(chip, state); + ret = chip->fixes->suspend(chip); if (ret) { for (i = chip->num_slots - 1; i >= 0; i--) sdhci_runtime_resume_host(chip->slots[i]->host); @@ -1176,6 +1176,8 @@ static int sdhci_pci_runtime_idle(struct device *dev) #endif static const struct dev_pm_ops sdhci_pci_pm_ops = { + .suspend = sdhci_pci_suspend, + .resume = sdhci_pci_resume, .runtime_suspend = sdhci_pci_runtime_suspend, .runtime_resume = sdhci_pci_runtime_resume, .runtime_idle = sdhci_pci_runtime_idle, @@ -1428,8 +1430,6 @@ static struct pci_driver sdhci_driver = { .id_table = pci_ids, .probe = sdhci_pci_probe, .remove = __devexit_p(sdhci_pci_remove), - .suspend = sdhci_pci_suspend, - .resume = sdhci_pci_resume, .driver = { .pm = &sdhci_pci_pm_ops }, diff --git a/drivers/mmc/host/sdhci-pltfm.c b/drivers/mmc/host/sdhci-pltfm.c index a9e12ea..03970bc 100644 --- a/drivers/mmc/host/sdhci-pltfm.c +++ b/drivers/mmc/host/sdhci-pltfm.c @@ -194,21 +194,25 @@ int sdhci_pltfm_unregister(struct platform_device *pdev) EXPORT_SYMBOL_GPL(sdhci_pltfm_unregister); #ifdef CONFIG_PM -int sdhci_pltfm_suspend(struct platform_device *dev, pm_message_t state) +static int sdhci_pltfm_suspend(struct device *dev) { - struct sdhci_host *host = platform_get_drvdata(dev); + struct sdhci_host *host = dev_get_drvdata(dev); - return sdhci_suspend_host(host, state); + return sdhci_suspend_host(host); } -EXPORT_SYMBOL_GPL(sdhci_pltfm_suspend); -int sdhci_pltfm_resume(struct platform_device *dev) +static int sdhci_pltfm_resume(struct device *dev) { - struct sdhci_host *host = platform_get_drvdata(dev); + struct sdhci_host *host = dev_get_drvdata(dev); return sdhci_resume_host(host); } -EXPORT_SYMBOL_GPL(sdhci_pltfm_resume); + +const struct dev_pm_ops sdhci_pltfm_pmops = { + .suspend = sdhci_pltfm_suspend, + .resume = sdhci_pltfm_resume, +}; +EXPORT_SYMBOL_GPL(sdhci_pltfm_pmops); #endif /* CONFIG_PM */ static int __init sdhci_pltfm_drv_init(void) diff --git a/drivers/mmc/host/sdhci-pltfm.h b/drivers/mmc/host/sdhci-pltfm.h index 3a9fc3f..37e0e18 100644 --- a/drivers/mmc/host/sdhci-pltfm.h +++ b/drivers/mmc/host/sdhci-pltfm.h @@ -99,8 +99,10 @@ extern int sdhci_pltfm_register(struct platform_device *pdev, extern int sdhci_pltfm_unregister(struct platform_device *pdev); #ifdef CONFIG_PM -extern int sdhci_pltfm_suspend(struct platform_device *dev, pm_message_t state); -extern int sdhci_pltfm_resume(struct platform_device *dev); +extern const struct dev_pm_ops sdhci_pltfm_pmops; +#define SDHCI_PLTFM_PMOPS (&sdhci_pltfm_pmops) +#else +#define SDHCI_PLTFM_PMOPS NULL #endif #endif /* _DRIVERS_MMC_SDHCI_PLTFM_H */ diff --git a/drivers/mmc/host/sdhci-pxav2.c b/drivers/mmc/host/sdhci-pxav2.c index d4bf6d3..7a039c3 100644 --- a/drivers/mmc/host/sdhci-pxav2.c +++ b/drivers/mmc/host/sdhci-pxav2.c @@ -218,13 +218,10 @@ static struct platform_driver sdhci_pxav2_driver = { .driver = { .name = "sdhci-pxav2", .owner = THIS_MODULE, + .pm = SDHCI_PLTFM_PMOPS, }, .probe = sdhci_pxav2_probe, .remove = __devexit_p(sdhci_pxav2_remove), -#ifdef CONFIG_PM - .suspend = sdhci_pltfm_suspend, - .resume = sdhci_pltfm_resume, -#endif }; static int __init sdhci_pxav2_init(void) { diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c index cff4ad3..15673a7 100644 --- a/drivers/mmc/host/sdhci-pxav3.c +++ b/drivers/mmc/host/sdhci-pxav3.c @@ -264,13 +264,10 @@ static struct platform_driver sdhci_pxav3_driver = { .driver = { .name = "sdhci-pxav3", .owner = THIS_MODULE, + .pm = SDHCI_PLTFM_PMOPS, }, .probe = sdhci_pxav3_probe, .remove = __devexit_p(sdhci_pxav3_remove), -#ifdef CONFIG_PM - .suspend = sdhci_pltfm_suspend, - .resume = sdhci_pltfm_resume, -#endif }; static int __init sdhci_pxav3_init(void) { diff --git a/drivers/mmc/host/sdhci-s3c.c b/drivers/mmc/host/sdhci-s3c.c index cb60c41..0d33ff0 100644 --- a/drivers/mmc/host/sdhci-s3c.c +++ b/drivers/mmc/host/sdhci-s3c.c @@ -622,23 +622,29 @@ static int __devexit sdhci_s3c_remove(struct platform_device *pdev) #ifdef CONFIG_PM -static int sdhci_s3c_suspend(struct platform_device *dev, pm_message_t pm) +static int sdhci_s3c_suspend(struct device *dev) { - struct sdhci_host *host = platform_get_drvdata(dev); + struct sdhci_host *host = dev_get_drvdata(dev); - return sdhci_suspend_host(host, pm); + return sdhci_suspend_host(host); } -static int sdhci_s3c_resume(struct platform_device *dev) +static int sdhci_s3c_resume(struct device *dev) { - struct sdhci_host *host = platform_get_drvdata(dev); + struct sdhci_host *host = dev_get_drvdata(dev); return sdhci_resume_host(host); } +static const struct dev_pm_ops sdhci_s3c_pmops = { + .suspend = sdhci_s3c_suspend, + .resume = sdhci_s3c_resume, +}; + +#define SDHCI_S3C_PMOPS (&sdhci_s3c_pmops) + #else -#define sdhci_s3c_suspend NULL -#define sdhci_s3c_resume NULL +#define SDHCI_S3C_PMOPS NULL #endif static struct platform_driver sdhci_s3c_driver = { @@ -647,6 +653,7 @@ static struct platform_driver sdhci_s3c_driver = { .driver = { .owner = THIS_MODULE, .name = "s3c-sdhci", + .pm = SDHCI_S3C_PMOPS, }, }; diff --git a/drivers/mmc/host/sdhci-tegra.c b/drivers/mmc/host/sdhci-tegra.c index 89699e8..e2e18d3 100644 --- a/drivers/mmc/host/sdhci-tegra.c +++ b/drivers/mmc/host/sdhci-tegra.c @@ -318,13 +318,10 @@ static struct platform_driver sdhci_tegra_driver = { .name = "sdhci-tegra", .owner = THIS_MODULE, .of_match_table = sdhci_tegra_dt_match, + .pm = SDHCI_PLTFM_PMOPS, }, .probe = sdhci_tegra_probe, .remove = __devexit_p(sdhci_tegra_remove), -#ifdef CONFIG_PM - .suspend = sdhci_pltfm_suspend, - .resume = sdhci_pltfm_resume, -#endif }; static int __init sdhci_tegra_init(void) diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 6d8eea3..19ed580 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -2327,7 +2327,7 @@ out: #ifdef CONFIG_PM -int sdhci_suspend_host(struct sdhci_host *host, pm_message_t state) +int sdhci_suspend_host(struct sdhci_host *host) { int ret; diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h index 0a5b654..a04d4d0 100644 --- a/drivers/mmc/host/sdhci.h +++ b/drivers/mmc/host/sdhci.h @@ -374,7 +374,7 @@ extern int sdhci_add_host(struct sdhci_host *host); extern void sdhci_remove_host(struct sdhci_host *host, int dead); #ifdef CONFIG_PM -extern int sdhci_suspend_host(struct sdhci_host *host, pm_message_t state); +extern int sdhci_suspend_host(struct sdhci_host *host); extern int sdhci_resume_host(struct sdhci_host *host); extern void sdhci_enable_irq_wakeups(struct sdhci_host *host); #endif diff --git a/drivers/mmc/host/vub300.c b/drivers/mmc/host/vub300.c index e8f6e65..2ec978b 100644 --- a/drivers/mmc/host/vub300.c +++ b/drivers/mmc/host/vub300.c @@ -259,7 +259,7 @@ static int firmware_rom_wait_states = 0x04; static int firmware_rom_wait_states = 0x1C; #endif -module_param(firmware_rom_wait_states, bool, 0644); +module_param(firmware_rom_wait_states, int, 0644); MODULE_PARM_DESC(firmware_rom_wait_states, "ROM wait states byte=RRRIIEEE (Reserved Internal External)"); diff --git a/drivers/mtd/maps/plat-ram.c b/drivers/mtd/maps/plat-ram.c index 94f5534..45876d0 100644 --- a/drivers/mtd/maps/plat-ram.c +++ b/drivers/mtd/maps/plat-ram.c @@ -227,10 +227,14 @@ static int platram_probe(struct platform_device *pdev) if (!err) dev_info(&pdev->dev, "registered mtd device\n"); - /* add the whole device. */ - err = mtd_device_register(info->mtd, NULL, 0); - if (err) - dev_err(&pdev->dev, "failed to register the entire device\n"); + if (pdata->nr_partitions) { + /* add the whole device. */ + err = mtd_device_register(info->mtd, NULL, 0); + if (err) { + dev_err(&pdev->dev, + "failed to register the entire device\n"); + } + } return err; diff --git a/drivers/mtd/maps/pxa2xx-flash.c b/drivers/mtd/maps/pxa2xx-flash.c index 411a17d..2a25b67 100644 --- a/drivers/mtd/maps/pxa2xx-flash.c +++ b/drivers/mtd/maps/pxa2xx-flash.c @@ -98,7 +98,7 @@ static int __devinit pxa2xx_flash_probe(struct platform_device *pdev) } info->mtd->owner = THIS_MODULE; - mtd_device_parse_register(info->mtd, probes, 0, NULL, 0); + mtd_device_parse_register(info->mtd, probes, 0, flash->parts, flash->nr_parts); platform_set_drvdata(pdev, info); return 0; diff --git a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c index 071b634..493ec2f 100644 --- a/drivers/mtd/nand/gpmi-nand/gpmi-nand.c +++ b/drivers/mtd/nand/gpmi-nand/gpmi-nand.c @@ -21,9 +21,9 @@ #include <linux/clk.h> #include <linux/slab.h> #include <linux/interrupt.h> +#include <linux/module.h> #include <linux/mtd/gpmi-nand.h> #include <linux/mtd/partitions.h> - #include "gpmi-nand.h" /* add our owner bbt descriptor */ diff --git a/drivers/mtd/nand/ndfc.c b/drivers/mtd/nand/ndfc.c index ee17139..f8aacf4 100644 --- a/drivers/mtd/nand/ndfc.c +++ b/drivers/mtd/nand/ndfc.c @@ -188,7 +188,7 @@ static int ndfc_chip_init(struct ndfc_controller *ndfc, if (!flash_np) return -ENODEV; - ppdata->of_node = flash_np; + ppdata.of_node = flash_np; ndfc->mtd.name = kasprintf(GFP_KERNEL, "%s.%s", dev_name(&ndfc->ofdev->dev), flash_np->name); if (!ndfc->mtd.name) { diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index 5272f9d..9de3764 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -23,8 +23,8 @@ if NET_VENDOR_FREESCALE config FEC bool "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 + ARCH_MXC || SOC_IMX28) + default ARCH_MXC || SOC_IMX28 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/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index c7b6083..dea0cb4 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -2606,6 +2606,9 @@ static int skge_up(struct net_device *dev) spin_unlock_irq(&hw->hw_lock); napi_enable(&skge->napi); + + skge_set_multicast(dev); + return 0; free_tx_ring: diff --git a/drivers/net/ethernet/mellanox/mlx4/en_cq.c b/drivers/net/ethernet/mellanox/mlx4/en_cq.c index 227997d..5829e0b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_cq.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_cq.c @@ -147,6 +147,7 @@ void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq) mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size); if (priv->mdev->dev->caps.comp_pool && cq->vector) mlx4_release_eq(priv->mdev->dev, cq->vector); + cq->vector = 0; cq->buf_size = 0; cq->buf = NULL; } diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 67bf078..c8f47f1 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -477,7 +477,6 @@ enum rtl_register_content { /* Config1 register p.24 */ LEDS1 = (1 << 7), LEDS0 = (1 << 6), - MSIEnable = (1 << 5), /* Enable Message Signaled Interrupt */ Speed_down = (1 << 4), MEMMAP = (1 << 3), IOMAP = (1 << 2), @@ -485,6 +484,7 @@ enum rtl_register_content { PMEnable = (1 << 0), /* Power Management Enable */ /* Config2 register p. 25 */ + MSIEnable = (1 << 5), /* 8169 only. Reserved in the 8168. */ PCI_Clock_66MHz = 0x01, PCI_Clock_33MHz = 0x00, @@ -3426,22 +3426,24 @@ static const struct rtl_cfg_info { }; /* Cfg9346_Unlock assumed. */ -static unsigned rtl_try_msi(struct pci_dev *pdev, void __iomem *ioaddr, +static unsigned rtl_try_msi(struct rtl8169_private *tp, const struct rtl_cfg_info *cfg) { + void __iomem *ioaddr = tp->mmio_addr; unsigned msi = 0; u8 cfg2; cfg2 = RTL_R8(Config2) & ~MSIEnable; if (cfg->features & RTL_FEATURE_MSI) { - if (pci_enable_msi(pdev)) { - dev_info(&pdev->dev, "no MSI. Back to INTx.\n"); + if (pci_enable_msi(tp->pci_dev)) { + netif_info(tp, hw, tp->dev, "no MSI. Back to INTx.\n"); } else { cfg2 |= MSIEnable; msi = RTL_FEATURE_MSI; } } - RTL_W8(Config2, cfg2); + if (tp->mac_version <= RTL_GIGA_MAC_VER_06) + RTL_W8(Config2, cfg2); return msi; } @@ -4077,7 +4079,7 @@ rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->features |= RTL_FEATURE_WOL; if ((RTL_R8(Config5) & (UWF | BWF | MWF)) != 0) tp->features |= RTL_FEATURE_WOL; - tp->features |= rtl_try_msi(pdev, ioaddr, cfg); + tp->features |= rtl_try_msi(tp, cfg); RTL_W8(Cfg9346, Cfg9346_Lock); if (rtl_tbi_enabled(tp)) { diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c index dca9d33..c97d2f5 100644 --- a/drivers/net/ethernet/ti/davinci_cpdma.c +++ b/drivers/net/ethernet/ti/davinci_cpdma.c @@ -836,11 +836,13 @@ int cpdma_chan_stop(struct cpdma_chan *chan) chan_write(chan, cp, CPDMA_TEARDOWN_VALUE); /* handle completed packets */ + spin_unlock_irqrestore(&chan->lock, flags); do { ret = __cpdma_chan_process(chan); if (ret < 0) break; } while ((ret & CPDMA_DESC_TD_COMPLETE) == 0); + spin_lock_irqsave(&chan->lock, flags); /* remaining packets haven't been tx/rx'ed, clean them up */ while (chan->head) { diff --git a/drivers/net/usb/asix.c b/drivers/net/usb/asix.c index e6fed4d..e95f0e6 100644 --- a/drivers/net/usb/asix.c +++ b/drivers/net/usb/asix.c @@ -1655,6 +1655,10 @@ static const struct usb_device_id products [] = { // ASIX 88772a USB_DEVICE(0x0db0, 0xa877), .driver_info = (unsigned long) &ax88772_info, +}, { + // Asus USB Ethernet Adapter + USB_DEVICE (0x0b95, 0x7e2b), + .driver_info = (unsigned long) &ax88772_info, }, { }, // END }; diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index d2348a5..a9c5ae7 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -1843,6 +1843,9 @@ static void ath9k_sta_notify(struct ieee80211_hw *hw, struct ath_softc *sc = hw->priv; struct ath_node *an = (struct ath_node *) sta->drv_priv; + if (!(sc->sc_flags & SC_OP_TXAGGR)) + return; + switch (cmd) { case STA_NOTIFY_SLEEP: an->sleeping = true; diff --git a/drivers/net/wireless/ath/ath9k/rc.c b/drivers/net/wireless/ath/ath9k/rc.c index 888abc2..528d5f3 100644 --- a/drivers/net/wireless/ath/ath9k/rc.c +++ b/drivers/net/wireless/ath/ath9k/rc.c @@ -1271,7 +1271,9 @@ static void ath_rc_init(struct ath_softc *sc, ath_rc_priv->max_valid_rate = k; ath_rc_sort_validrates(rate_table, ath_rc_priv); - ath_rc_priv->rate_max_phy = ath_rc_priv->valid_rate_index[k-4]; + ath_rc_priv->rate_max_phy = (k > 4) ? + ath_rc_priv->valid_rate_index[k-4] : + ath_rc_priv->valid_rate_index[k-1]; ath_rc_priv->rate_table = rate_table; ath_dbg(common, ATH_DBG_CONFIG, diff --git a/drivers/net/wireless/b43/pio.c b/drivers/net/wireless/b43/pio.c index fcff923..279a53e 100644 --- a/drivers/net/wireless/b43/pio.c +++ b/drivers/net/wireless/b43/pio.c @@ -617,9 +617,19 @@ static bool pio_rx_frame(struct b43_pio_rxqueue *q) const char *err_msg = NULL; struct b43_rxhdr_fw4 *rxhdr = (struct b43_rxhdr_fw4 *)wl->pio_scratchspace; + size_t rxhdr_size = sizeof(*rxhdr); BUILD_BUG_ON(sizeof(wl->pio_scratchspace) < sizeof(*rxhdr)); - memset(rxhdr, 0, sizeof(*rxhdr)); + switch (dev->fw.hdr_format) { + case B43_FW_HDR_410: + case B43_FW_HDR_351: + rxhdr_size -= sizeof(rxhdr->format_598) - + sizeof(rxhdr->format_351); + break; + case B43_FW_HDR_598: + break; + } + memset(rxhdr, 0, rxhdr_size); /* Check if we have data and wait for it to get ready. */ if (q->rev >= 8) { @@ -657,11 +667,11 @@ data_ready: /* Get the preamble (RX header) */ if (q->rev >= 8) { - b43_block_read(dev, rxhdr, sizeof(*rxhdr), + b43_block_read(dev, rxhdr, rxhdr_size, q->mmio_base + B43_PIO8_RXDATA, sizeof(u32)); } else { - b43_block_read(dev, rxhdr, sizeof(*rxhdr), + b43_block_read(dev, rxhdr, rxhdr_size, q->mmio_base + B43_PIO_RXDATA, sizeof(u16)); } diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c b/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c index a7a6def..5c7c17c 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c @@ -606,8 +606,8 @@ int iwlagn_mac_config(struct ieee80211_hw *hw, u32 changed) if (ctx->ht.enabled) { /* if HT40 is used, it should not change * after associated except channel switch */ - if (iwl_is_associated_ctx(ctx) && - !ctx->ht.is_40mhz) + if (!ctx->ht.is_40mhz || + !iwl_is_associated_ctx(ctx)) iwlagn_config_ht40(conf, ctx); } else ctx->ht.is_40mhz = false; diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-tx.c b/drivers/net/wireless/iwlwifi/iwl-agn-tx.c index 35a6b71..df1540c 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-tx.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-tx.c @@ -91,7 +91,10 @@ static void iwlagn_tx_cmd_build_basic(struct iwl_priv *priv, tx_cmd->tid_tspec = qc[0] & 0xf; tx_flags &= ~TX_CMD_FLG_SEQ_CTL_MSK; } else { - tx_flags |= TX_CMD_FLG_SEQ_CTL_MSK; + if (info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ) + tx_flags |= TX_CMD_FLG_SEQ_CTL_MSK; + else + tx_flags &= ~TX_CMD_FLG_SEQ_CTL_MSK; } iwlagn_tx_cmd_protection(priv, info, fc, &tx_flags); diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c index bacc06c..e0e9a3d 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn.c @@ -2850,6 +2850,9 @@ static int iwlagn_mac_tx_sync(struct ieee80211_hw *hw, int ret; u8 sta_id; + if (ctx->ctxid != IWL_RXON_CTX_PAN) + return 0; + IWL_DEBUG_MAC80211(priv, "enter\n"); mutex_lock(&priv->shrd->mutex); @@ -2898,6 +2901,9 @@ static void iwlagn_mac_finish_tx_sync(struct ieee80211_hw *hw, struct iwl_vif_priv *vif_priv = (void *)vif->drv_priv; struct iwl_rxon_context *ctx = vif_priv->ctx; + if (ctx->ctxid != IWL_RXON_CTX_PAN) + return; + IWL_DEBUG_MAC80211(priv, "enter\n"); mutex_lock(&priv->shrd->mutex); diff --git a/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c b/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c index ce91898..5f17ab8 100644 --- a/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c +++ b/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c @@ -1197,9 +1197,7 @@ static int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb, iwl_print_hex_dump(trans, IWL_DL_TX, (u8 *)tx_cmd->hdr, hdr_len); /* Set up entry for this TFD in Tx byte-count array */ - if (is_agg) - iwl_trans_txq_update_byte_cnt_tbl(trans, txq, - le16_to_cpu(tx_cmd->len)); + iwl_trans_txq_update_byte_cnt_tbl(trans, txq, le16_to_cpu(tx_cmd->len)); dma_sync_single_for_device(bus(trans)->dev, txcmd_phys, firstlen, DMA_BIDIRECTIONAL); diff --git a/drivers/net/wireless/mwifiex/cmdevt.c b/drivers/net/wireless/mwifiex/cmdevt.c index ac27815..6e0a3ea 100644 --- a/drivers/net/wireless/mwifiex/cmdevt.c +++ b/drivers/net/wireless/mwifiex/cmdevt.c @@ -939,7 +939,6 @@ mwifiex_cancel_pending_ioctl(struct mwifiex_adapter *adapter) { struct cmd_ctrl_node *cmd_node = NULL, *tmp_node = NULL; unsigned long cmd_flags; - unsigned long cmd_pending_q_flags; unsigned long scan_pending_q_flags; uint16_t cancel_scan_cmd = false; @@ -949,12 +948,9 @@ mwifiex_cancel_pending_ioctl(struct mwifiex_adapter *adapter) cmd_node = adapter->curr_cmd; cmd_node->wait_q_enabled = false; cmd_node->cmd_flag |= CMD_F_CANCELED; - spin_lock_irqsave(&adapter->cmd_pending_q_lock, - cmd_pending_q_flags); - list_del(&cmd_node->list); - spin_unlock_irqrestore(&adapter->cmd_pending_q_lock, - cmd_pending_q_flags); mwifiex_insert_cmd_to_free_q(adapter, cmd_node); + mwifiex_complete_cmd(adapter, adapter->curr_cmd); + adapter->curr_cmd = NULL; spin_unlock_irqrestore(&adapter->mwifiex_cmd_lock, cmd_flags); } @@ -981,7 +977,6 @@ mwifiex_cancel_pending_ioctl(struct mwifiex_adapter *adapter) spin_unlock_irqrestore(&adapter->mwifiex_cmd_lock, cmd_flags); } adapter->cmd_wait_q.status = -1; - mwifiex_complete_cmd(adapter, adapter->curr_cmd); } /* diff --git a/drivers/net/wireless/mwifiex/sta_ioctl.c b/drivers/net/wireless/mwifiex/sta_ioctl.c index ea4a29b..1679c25 100644 --- a/drivers/net/wireless/mwifiex/sta_ioctl.c +++ b/drivers/net/wireless/mwifiex/sta_ioctl.c @@ -55,9 +55,14 @@ int mwifiex_wait_queue_complete(struct mwifiex_adapter *adapter) { bool cancel_flag = false; int status = adapter->cmd_wait_q.status; - struct cmd_ctrl_node *cmd_queued = adapter->cmd_queued; + struct cmd_ctrl_node *cmd_queued; + if (!adapter->cmd_queued) + return 0; + + cmd_queued = adapter->cmd_queued; adapter->cmd_queued = NULL; + dev_dbg(adapter->dev, "cmd pending\n"); atomic_inc(&adapter->cmd_pending); diff --git a/drivers/of/platform.c b/drivers/of/platform.c index cbd5d70..63b3ec4 100644 --- a/drivers/of/platform.c +++ b/drivers/of/platform.c @@ -314,7 +314,7 @@ static const struct of_dev_auxdata *of_dev_lookup(const struct of_dev_auxdata *l if (!lookup) return NULL; - for(; lookup->name != NULL; lookup++) { + for(; lookup->compatible != NULL; lookup++) { if (!of_device_is_compatible(np, lookup->compatible)) continue; if (of_address_to_resource(np, 0, &res)) diff --git a/drivers/oprofile/oprofile_files.c b/drivers/oprofile/oprofile_files.c index 89f6345..84a208d 100644 --- a/drivers/oprofile/oprofile_files.c +++ b/drivers/oprofile/oprofile_files.c @@ -45,7 +45,7 @@ static ssize_t timeout_write(struct file *file, char const __user *buf, return -EINVAL; retval = oprofilefs_ulong_from_user(&val, buf, count); - if (retval) + if (retval <= 0) return retval; retval = oprofile_set_timeout(val); @@ -84,7 +84,7 @@ static ssize_t depth_write(struct file *file, char const __user *buf, size_t cou return -EINVAL; retval = oprofilefs_ulong_from_user(&val, buf, count); - if (retval) + if (retval <= 0) return retval; retval = oprofile_set_ulong(&oprofile_backtrace_depth, val); @@ -141,9 +141,10 @@ static ssize_t enable_write(struct file *file, char const __user *buf, size_t co return -EINVAL; retval = oprofilefs_ulong_from_user(&val, buf, count); - if (retval) + if (retval <= 0) return retval; + retval = 0; if (val) retval = oprofile_start(); else diff --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c index d0de6cc..2f0aa0f 100644 --- a/drivers/oprofile/oprofilefs.c +++ b/drivers/oprofile/oprofilefs.c @@ -60,6 +60,13 @@ ssize_t oprofilefs_ulong_to_user(unsigned long val, char __user *buf, size_t cou } +/* + * Note: If oprofilefs_ulong_from_user() returns 0, then *val remains + * unchanged and might be uninitialized. This follows write syscall + * implementation when count is zero: "If count is zero ... [and if] + * no errors are detected, 0 will be returned without causing any + * other effect." (man 2 write) + */ int oprofilefs_ulong_from_user(unsigned long *val, char const __user *buf, size_t count) { char tmpbuf[TMPBUFSIZE]; @@ -79,7 +86,7 @@ int oprofilefs_ulong_from_user(unsigned long *val, char const __user *buf, size_ raw_spin_lock_irqsave(&oprofilefs_lock, flags); *val = simple_strtoul(tmpbuf, NULL, 0); raw_spin_unlock_irqrestore(&oprofilefs_lock, flags); - return 0; + return count; } @@ -99,7 +106,7 @@ static ssize_t ulong_write_file(struct file *file, char const __user *buf, size_ return -EINVAL; retval = oprofilefs_ulong_from_user(&value, buf, count); - if (retval) + if (retval <= 0) return retval; retval = oprofile_set_ulong(file->private_data, value); diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c index 7ec56fb..b0dd08e 100644 --- a/drivers/pci/ats.c +++ b/drivers/pci/ats.c @@ -13,6 +13,7 @@ #include <linux/export.h> #include <linux/pci-ats.h> #include <linux/pci.h> +#include <linux/slab.h> #include "pci.h" diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index fce1c54..9ddf69e 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -132,6 +132,18 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv) if (!acpi_pci_check_ejectable(pbus, handle) && !is_dock_device(handle)) return AE_OK; + pdev = pbus->self; + if (pdev && pci_is_pcie(pdev)) { + tmp = acpi_find_root_bridge_handle(pdev); + if (tmp) { + struct acpi_pci_root *root = acpi_pci_find_root(tmp); + + if (root && (root->osc_control_set & + OSC_PCI_EXPRESS_NATIVE_HP_CONTROL)) + return AE_OK; + } + } + acpi_evaluate_integer(handle, "_ADR", NULL, &adr); device = (adr >> 16) & 0xffff; function = adr & 0xffff; @@ -213,7 +225,6 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv) pdev = pci_get_slot(pbus, PCI_DEVFN(device, function)); if (pdev) { - pdev->current_state = PCI_D0; slot->flags |= (SLOT_ENABLED | SLOT_POWEREDON); pci_dev_put(pdev); } @@ -459,17 +470,8 @@ 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)) { @@ -1385,19 +1387,11 @@ 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)) 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); diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index b82c155..1969a3e 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -283,6 +283,7 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) struct resource *res; struct pci_dev *pdev; struct pci_sriov *iov = dev->sriov; + int bars = 0; if (!nr_virtfn) return 0; @@ -307,6 +308,7 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) nres = 0; for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { + bars |= (1 << (i + PCI_IOV_RESOURCES)); res = dev->resource + PCI_IOV_RESOURCES + i; if (res->parent) nres++; @@ -324,6 +326,11 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) return -ENOMEM; } + if (pci_enable_resources(dev, bars)) { + dev_err(&dev->dev, "SR-IOV: IOV BARS not allocated\n"); + return -ENOMEM; + } + if (iov->link != dev->devfn) { pdev = pci_get_slot(dev->bus, iov->link); if (!pdev) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 6f45a73..6d4a531 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -664,6 +664,9 @@ static int pci_platform_power_transition(struct pci_dev *dev, pci_power_t state) error = platform_pci_set_power_state(dev, state); if (!error) pci_update_current_state(dev, state); + /* Fall back to PCI_D0 if native PM is not supported */ + if (!dev->pm_cap) + dev->current_state = PCI_D0; } else { error = -ENODEV; /* Fall back to PCI_D0 if native PM is not supported */ @@ -1126,7 +1129,11 @@ static int __pci_enable_device_flags(struct pci_dev *dev, if (atomic_add_return(1, &dev->enable_cnt) > 1) return 0; /* already enabled */ - for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) + /* only skip sriov related */ + for (i = 0; i <= PCI_ROM_RESOURCE; i++) + if (dev->resource[i].flags & flags) + bars |= (1 << i); + for (i = PCI_BRIDGE_RESOURCES; i < DEVICE_COUNT_RESOURCE; i++) if (dev->resource[i].flags & flags) bars |= (1 << i); diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c index fa4d9f3..8e28625 100644 --- a/drivers/rtc/interface.c +++ b/drivers/rtc/interface.c @@ -319,20 +319,6 @@ 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; @@ -356,7 +342,14 @@ static int __rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) * over right here, before we set the alarm. */ - return ___rtc_set_alarm(rtc, 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; } int rtc_set_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm) @@ -770,20 +763,6 @@ 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 @@ -805,10 +784,8 @@ 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) { - rtc_alarm_disable(rtc); + if (!next) return; - } alarm.time = rtc_ktime_to_tm(next->expires); alarm.enabled = 1; err = __rtc_set_alarm(rtc, &alarm); @@ -870,8 +847,7 @@ 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-m41t80.c b/drivers/rtc/rtc-m41t80.c index eda128f..64aedd8 100644 --- a/drivers/rtc/rtc-m41t80.c +++ b/drivers/rtc/rtc-m41t80.c @@ -357,10 +357,19 @@ static int m41t80_rtc_read_alarm(struct device *dev, struct rtc_wkalrm *t) static struct rtc_class_ops m41t80_rtc_ops = { .read_time = m41t80_rtc_read_time, .set_time = m41t80_rtc_set_time, + /* + * XXX - m41t80 alarm functionality is reported broken. + * until it is fixed, don't register alarm functions. + * .read_alarm = m41t80_rtc_read_alarm, .set_alarm = m41t80_rtc_set_alarm, + */ .proc = m41t80_rtc_proc, + /* + * See above comment on broken alarm + * .alarm_irq_enable = m41t80_rtc_alarm_irq_enable, + */ }; #if defined(CONFIG_RTC_INTF_SYSFS) || defined(CONFIG_RTC_INTF_SYSFS_MODULE) diff --git a/drivers/s390/scsi/zfcp_scsi.c b/drivers/s390/scsi/zfcp_scsi.c index 11f07f8..b79576b 100644 --- a/drivers/s390/scsi/zfcp_scsi.c +++ b/drivers/s390/scsi/zfcp_scsi.c @@ -55,6 +55,10 @@ static void zfcp_scsi_slave_destroy(struct scsi_device *sdev) { struct zfcp_scsi_dev *zfcp_sdev = sdev_to_zfcp(sdev); + /* if previous slave_alloc returned early, there is nothing to do */ + if (!zfcp_sdev->port) + return; + zfcp_erp_lun_shutdown_wait(sdev, "scssd_1"); put_device(&zfcp_sdev->port->dev); } diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c index dba72a4..1ad0b82 100644 --- a/drivers/scsi/bnx2i/bnx2i_hwi.c +++ b/drivers/scsi/bnx2i/bnx2i_hwi.c @@ -1906,18 +1906,19 @@ static int bnx2i_queue_scsi_cmd_resp(struct iscsi_session *session, spin_lock(&session->lock); task = iscsi_itt_to_task(bnx2i_conn->cls_conn->dd_data, cqe->itt & ISCSI_CMD_RESPONSE_INDEX); - if (!task) { + if (!task || !task->sc) { spin_unlock(&session->lock); return -EINVAL; } sc = task->sc; - spin_unlock(&session->lock); if (!blk_rq_cpu_valid(sc->request)) cpu = smp_processor_id(); else cpu = sc->request->cpu; + spin_unlock(&session->lock); + p = &per_cpu(bnx2i_percpu, cpu); spin_lock(&p->p_work_lock); if (unlikely(!p->iothread)) { diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c index cefbe44..8d67467 100644 --- a/drivers/scsi/fcoe/fcoe.c +++ b/drivers/scsi/fcoe/fcoe.c @@ -31,6 +31,8 @@ #include <linux/sysfs.h> #include <linux/ctype.h> #include <linux/workqueue.h> +#include <net/dcbnl.h> +#include <net/dcbevent.h> #include <scsi/scsi_tcq.h> #include <scsi/scsicam.h> #include <scsi/scsi_transport.h> @@ -101,6 +103,8 @@ static int fcoe_ddp_done(struct fc_lport *, u16); static int fcoe_ddp_target(struct fc_lport *, u16, struct scatterlist *, unsigned int); static int fcoe_cpu_callback(struct notifier_block *, unsigned long, void *); +static int fcoe_dcb_app_notification(struct notifier_block *notifier, + ulong event, void *ptr); static bool fcoe_match(struct net_device *netdev); static int fcoe_create(struct net_device *netdev, enum fip_state fip_mode); @@ -129,6 +133,11 @@ static struct notifier_block fcoe_cpu_notifier = { .notifier_call = fcoe_cpu_callback, }; +/* notification function for DCB events */ +static struct notifier_block dcb_notifier = { + .notifier_call = fcoe_dcb_app_notification, +}; + static struct scsi_transport_template *fcoe_nport_scsi_transport; static struct scsi_transport_template *fcoe_vport_scsi_transport; @@ -1522,6 +1531,8 @@ int fcoe_xmit(struct fc_lport *lport, struct fc_frame *fp) skb_reset_network_header(skb); skb->mac_len = elen; skb->protocol = htons(ETH_P_FCOE); + skb->priority = port->priority; + if (fcoe->netdev->priv_flags & IFF_802_1Q_VLAN && fcoe->realdev->features & NETIF_F_HW_VLAN_TX) { skb->vlan_tci = VLAN_TAG_PRESENT | @@ -1624,6 +1635,7 @@ static inline int fcoe_filter_frames(struct fc_lport *lport, stats->InvalidCRCCount++; if (stats->InvalidCRCCount < 5) printk(KERN_WARNING "fcoe: dropping frame with CRC error\n"); + put_cpu(); return -EINVAL; } @@ -1746,6 +1758,7 @@ int fcoe_percpu_receive_thread(void *arg) */ static void fcoe_dev_setup(void) { + register_dcbevent_notifier(&dcb_notifier); register_netdevice_notifier(&fcoe_notifier); } @@ -1754,9 +1767,69 @@ static void fcoe_dev_setup(void) */ static void fcoe_dev_cleanup(void) { + unregister_dcbevent_notifier(&dcb_notifier); unregister_netdevice_notifier(&fcoe_notifier); } +static struct fcoe_interface * +fcoe_hostlist_lookup_realdev_port(struct net_device *netdev) +{ + struct fcoe_interface *fcoe; + struct net_device *real_dev; + + list_for_each_entry(fcoe, &fcoe_hostlist, list) { + if (fcoe->netdev->priv_flags & IFF_802_1Q_VLAN) + real_dev = vlan_dev_real_dev(fcoe->netdev); + else + real_dev = fcoe->netdev; + + if (netdev == real_dev) + return fcoe; + } + return NULL; +} + +static int fcoe_dcb_app_notification(struct notifier_block *notifier, + ulong event, void *ptr) +{ + struct dcb_app_type *entry = ptr; + struct fcoe_interface *fcoe; + struct net_device *netdev; + struct fcoe_port *port; + int prio; + + if (entry->app.selector != DCB_APP_IDTYPE_ETHTYPE) + return NOTIFY_OK; + + netdev = dev_get_by_index(&init_net, entry->ifindex); + if (!netdev) + return NOTIFY_OK; + + fcoe = fcoe_hostlist_lookup_realdev_port(netdev); + dev_put(netdev); + if (!fcoe) + return NOTIFY_OK; + + if (entry->dcbx & DCB_CAP_DCBX_VER_CEE) + prio = ffs(entry->app.priority) - 1; + else + prio = entry->app.priority; + + if (prio < 0) + return NOTIFY_OK; + + if (entry->app.protocol == ETH_P_FIP || + entry->app.protocol == ETH_P_FCOE) + fcoe->ctlr.priority = prio; + + if (entry->app.protocol == ETH_P_FCOE) { + port = lport_priv(fcoe->ctlr.lp); + port->priority = prio; + } + + return NOTIFY_OK; +} + /** * fcoe_device_notification() - Handler for net device events * @notifier: The context of the notification @@ -1965,6 +2038,46 @@ static bool fcoe_match(struct net_device *netdev) } /** + * fcoe_dcb_create() - Initialize DCB attributes and hooks + * @netdev: The net_device object of the L2 link that should be queried + * @port: The fcoe_port to bind FCoE APP priority with + * @ + */ +static void fcoe_dcb_create(struct fcoe_interface *fcoe) +{ +#ifdef CONFIG_DCB + int dcbx; + u8 fup, up; + struct net_device *netdev = fcoe->realdev; + struct fcoe_port *port = lport_priv(fcoe->ctlr.lp); + struct dcb_app app = { + .priority = 0, + .protocol = ETH_P_FCOE + }; + + /* setup DCB priority attributes. */ + if (netdev && netdev->dcbnl_ops && netdev->dcbnl_ops->getdcbx) { + dcbx = netdev->dcbnl_ops->getdcbx(netdev); + + if (dcbx & DCB_CAP_DCBX_VER_IEEE) { + app.selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE; + up = dcb_ieee_getapp_mask(netdev, &app); + app.protocol = ETH_P_FIP; + fup = dcb_ieee_getapp_mask(netdev, &app); + } else { + app.selector = DCB_APP_IDTYPE_ETHTYPE; + up = dcb_getapp(netdev, &app); + app.protocol = ETH_P_FIP; + fup = dcb_getapp(netdev, &app); + } + + port->priority = ffs(up) ? ffs(up) - 1 : 0; + fcoe->ctlr.priority = ffs(fup) ? ffs(fup) - 1 : port->priority; + } +#endif +} + +/** * fcoe_create() - Create a fcoe interface * @netdev : The net_device object the Ethernet interface to create on * @fip_mode: The FIP mode for this creation @@ -2007,6 +2120,9 @@ static int fcoe_create(struct net_device *netdev, enum fip_state fip_mode) /* Make this the "master" N_Port */ fcoe->ctlr.lp = lport; + /* setup DCB priority attributes. */ + fcoe_dcb_create(fcoe); + /* add to lports list */ fcoe_hostlist_add(lport); diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c index c74c4b8..e7522dc 100644 --- a/drivers/scsi/fcoe/fcoe_ctlr.c +++ b/drivers/scsi/fcoe/fcoe_ctlr.c @@ -320,6 +320,7 @@ static void fcoe_ctlr_solicit(struct fcoe_ctlr *fip, struct fcoe_fcf *fcf) skb_put(skb, sizeof(*sol)); skb->protocol = htons(ETH_P_FIP); + skb->priority = fip->priority; skb_reset_mac_header(skb); skb_reset_network_header(skb); fip->send(fip, skb); @@ -474,6 +475,7 @@ static void fcoe_ctlr_send_keep_alive(struct fcoe_ctlr *fip, } skb_put(skb, len); skb->protocol = htons(ETH_P_FIP); + skb->priority = fip->priority; skb_reset_mac_header(skb); skb_reset_network_header(skb); fip->send(fip, skb); @@ -566,6 +568,7 @@ static int fcoe_ctlr_encaps(struct fcoe_ctlr *fip, struct fc_lport *lport, cap->fip.fip_dl_len = htons(dlen / FIP_BPW); skb->protocol = htons(ETH_P_FIP); + skb->priority = fip->priority; skb_reset_mac_header(skb); skb_reset_network_header(skb); return 0; @@ -1911,6 +1914,7 @@ static void fcoe_ctlr_vn_send(struct fcoe_ctlr *fip, skb_put(skb, len); skb->protocol = htons(ETH_P_FIP); + skb->priority = fip->priority; skb_reset_mac_header(skb); skb_reset_network_header(skb); diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c index 4e041f6..d570573 100644 --- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c +++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c @@ -4335,7 +4335,7 @@ _scsih_smart_predicted_fault(struct MPT2SAS_ADAPTER *ioc, u16 handle) /* insert into event log */ sz = offsetof(Mpi2EventNotificationReply_t, EventData) + sizeof(Mpi2EventDataSasDeviceStatusChange_t); - event_reply = kzalloc(sz, GFP_KERNEL); + event_reply = kzalloc(sz, GFP_ATOMIC); if (!event_reply) { printk(MPT2SAS_ERR_FMT "failure at %s:%d/%s()!\n", ioc->name, __FILE__, __LINE__, __func__); diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c index ac326c4..6465dae 100644 --- a/drivers/scsi/qla2xxx/qla_attr.c +++ b/drivers/scsi/qla2xxx/qla_attr.c @@ -1762,12 +1762,31 @@ qla2x00_get_host_port_state(struct Scsi_Host *shost) scsi_qla_host_t *vha = shost_priv(shost); struct scsi_qla_host *base_vha = pci_get_drvdata(vha->hw->pdev); - if (!base_vha->flags.online) + if (!base_vha->flags.online) { fc_host_port_state(shost) = FC_PORTSTATE_OFFLINE; - else if (atomic_read(&base_vha->loop_state) == LOOP_TIMEOUT) - fc_host_port_state(shost) = FC_PORTSTATE_UNKNOWN; - else + return; + } + + switch (atomic_read(&base_vha->loop_state)) { + case LOOP_UPDATE: + fc_host_port_state(shost) = FC_PORTSTATE_DIAGNOSTICS; + break; + case LOOP_DOWN: + if (test_bit(LOOP_RESYNC_NEEDED, &base_vha->dpc_flags)) + fc_host_port_state(shost) = FC_PORTSTATE_DIAGNOSTICS; + else + fc_host_port_state(shost) = FC_PORTSTATE_LINKDOWN; + break; + case LOOP_DEAD: + fc_host_port_state(shost) = FC_PORTSTATE_LINKDOWN; + break; + case LOOP_READY: fc_host_port_state(shost) = FC_PORTSTATE_ONLINE; + break; + default: + fc_host_port_state(shost) = FC_PORTSTATE_UNKNOWN; + break; + } } static int diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c index 9df4787..f3cddd5 100644 --- a/drivers/scsi/qla2xxx/qla_dbg.c +++ b/drivers/scsi/qla2xxx/qla_dbg.c @@ -12,17 +12,17 @@ * | Level | Last Value Used | Holes | * ---------------------------------------------------------------------- * | Module Init and Probe | 0x0116 | | - * | Mailbox commands | 0x1129 | | + * | Mailbox commands | 0x112b | | * | Device Discovery | 0x2083 | | * | Queue Command and IO tracing | 0x302e | 0x3008 | * | DPC Thread | 0x401c | | * | Async Events | 0x5059 | | - * | Timer Routines | 0x600d | | + * | Timer Routines | 0x6010 | 0x600e,0x600f | * | User Space Interactions | 0x709d | | - * | Task Management | 0x8041 | | + * | Task Management | 0x8041 | 0x800b | * | AER/EEH | 0x900f | | * | Virtual Port | 0xa007 | | - * | ISP82XX Specific | 0xb051 | | + * | ISP82XX Specific | 0xb052 | | * | MultiQ | 0xc00b | | * | Misc | 0xd00b | | * ---------------------------------------------------------------------- diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h index ce32d81..c0c11af 100644 --- a/drivers/scsi/qla2xxx/qla_gbl.h +++ b/drivers/scsi/qla2xxx/qla_gbl.h @@ -578,6 +578,7 @@ extern int qla82xx_check_md_needed(scsi_qla_host_t *); extern void qla82xx_chip_reset_cleanup(scsi_qla_host_t *); extern int qla82xx_mbx_beacon_ctl(scsi_qla_host_t *, int); extern char *qdev_state(uint32_t); +extern void qla82xx_clear_pending_mbx(scsi_qla_host_t *); /* BSG related functions */ extern int qla24xx_bsg_request(struct fc_bsg_job *); diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index f03e915f..54ea68c 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -1509,7 +1509,8 @@ enable_82xx_npiv: &ha->fw_xcb_count, NULL, NULL, &ha->max_npiv_vports, NULL); - if (!fw_major_version && ql2xallocfwdump) + if (!fw_major_version && ql2xallocfwdump + && !IS_QLA82XX(ha)) qla2x00_alloc_fw_dump(vha); } } else { diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index dbec896..a4b267e 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -120,11 +120,10 @@ qla2x00_prep_cont_type0_iocb(struct scsi_qla_host *vha) * Returns a pointer to the continuation type 1 IOCB packet. */ static inline cont_a64_entry_t * -qla2x00_prep_cont_type1_iocb(scsi_qla_host_t *vha) +qla2x00_prep_cont_type1_iocb(scsi_qla_host_t *vha, struct req_que *req) { cont_a64_entry_t *cont_pkt; - struct req_que *req = vha->req; /* Adjust ring index. */ req->ring_index++; if (req->ring_index == req->length) { @@ -292,7 +291,7 @@ void qla2x00_build_scsi_iocbs_64(srb_t *sp, cmd_entry_t *cmd_pkt, * Five DSDs are available in the Continuation * Type 1 IOCB. */ - cont_pkt = qla2x00_prep_cont_type1_iocb(vha); + cont_pkt = qla2x00_prep_cont_type1_iocb(vha, vha->req); cur_dsd = (uint32_t *)cont_pkt->dseg_0_address; avail_dsds = 5; } @@ -684,7 +683,7 @@ qla24xx_build_scsi_iocbs(srb_t *sp, struct cmd_type_7 *cmd_pkt, * Five DSDs are available in the Continuation * Type 1 IOCB. */ - cont_pkt = qla2x00_prep_cont_type1_iocb(vha); + cont_pkt = qla2x00_prep_cont_type1_iocb(vha, vha->req); cur_dsd = (uint32_t *)cont_pkt->dseg_0_address; avail_dsds = 5; } @@ -2070,7 +2069,8 @@ qla2x00_ct_iocb(srb_t *sp, ms_iocb_entry_t *ct_iocb) * Five DSDs are available in the Cont. * Type 1 IOCB. */ - cont_pkt = qla2x00_prep_cont_type1_iocb(vha); + cont_pkt = qla2x00_prep_cont_type1_iocb(vha, + vha->hw->req_q_map[0]); cur_dsd = (uint32_t *) cont_pkt->dseg_0_address; avail_dsds = 5; cont_iocb_prsnt = 1; @@ -2096,6 +2096,7 @@ qla24xx_ct_iocb(srb_t *sp, struct ct_entry_24xx *ct_iocb) int index; uint16_t tot_dsds; scsi_qla_host_t *vha = sp->fcport->vha; + struct qla_hw_data *ha = vha->hw; struct fc_bsg_job *bsg_job = ((struct srb_ctx *)sp->ctx)->u.bsg_job; int loop_iterartion = 0; int cont_iocb_prsnt = 0; @@ -2141,7 +2142,8 @@ qla24xx_ct_iocb(srb_t *sp, struct ct_entry_24xx *ct_iocb) * Five DSDs are available in the Cont. * Type 1 IOCB. */ - cont_pkt = qla2x00_prep_cont_type1_iocb(vha); + cont_pkt = qla2x00_prep_cont_type1_iocb(vha, + ha->req_q_map[0]); cur_dsd = (uint32_t *) cont_pkt->dseg_0_address; avail_dsds = 5; cont_iocb_prsnt = 1; diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c index 2516adf..7b91b29 100644 --- a/drivers/scsi/qla2xxx/qla_isr.c +++ b/drivers/scsi/qla2xxx/qla_isr.c @@ -1741,7 +1741,7 @@ qla2x00_status_entry(scsi_qla_host_t *vha, struct rsp_que *rsp, void *pkt) resid, scsi_bufflen(cp)); cp->result = DID_ERROR << 16 | lscsi_status; - break; + goto check_scsi_status; } if (!lscsi_status && diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c index 3b3cec9..82a3353 100644 --- a/drivers/scsi/qla2xxx/qla_mbx.c +++ b/drivers/scsi/qla2xxx/qla_mbx.c @@ -79,8 +79,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) mcp->mb[0] = MBS_LINK_DOWN_ERROR; ql_log(ql_log_warn, base_vha, 0x1004, "FW hung = %d.\n", ha->flags.isp82xx_fw_hung); - rval = QLA_FUNCTION_FAILED; - goto premature_exit; + return QLA_FUNCTION_TIMEOUT; } /* @@ -163,6 +162,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) HINT_MBX_INT_PENDING) { spin_unlock_irqrestore(&ha->hardware_lock, flags); + ha->flags.mbox_busy = 0; ql_dbg(ql_dbg_mbx, base_vha, 0x1010, "Pending mailbox timeout, exiting.\n"); rval = QLA_FUNCTION_TIMEOUT; @@ -188,6 +188,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) HINT_MBX_INT_PENDING) { spin_unlock_irqrestore(&ha->hardware_lock, flags); + ha->flags.mbox_busy = 0; ql_dbg(ql_dbg_mbx, base_vha, 0x1012, "Pending mailbox timeout, exiting.\n"); rval = QLA_FUNCTION_TIMEOUT; @@ -302,7 +303,15 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) if (!test_bit(ISP_ABORT_NEEDED, &vha->dpc_flags) && !test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags) && !test_bit(ISP_ABORT_RETRY, &vha->dpc_flags)) { - + if (IS_QLA82XX(ha)) { + ql_dbg(ql_dbg_mbx, vha, 0x112a, + "disabling pause transmit on port " + "0 & 1.\n"); + qla82xx_wr_32(ha, + QLA82XX_CRB_NIU + 0x98, + CRB_NIU_XG_PAUSE_CTL_P0| + CRB_NIU_XG_PAUSE_CTL_P1); + } ql_log(ql_log_info, base_vha, 0x101c, "Mailbox cmd timeout occured. " "Scheduling ISP abort eeh_busy=0x%x.\n", @@ -318,7 +327,15 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp) if (!test_bit(ISP_ABORT_NEEDED, &vha->dpc_flags) && !test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags) && !test_bit(ISP_ABORT_RETRY, &vha->dpc_flags)) { - + if (IS_QLA82XX(ha)) { + ql_dbg(ql_dbg_mbx, vha, 0x112b, + "disabling pause transmit on port " + "0 & 1.\n"); + qla82xx_wr_32(ha, + QLA82XX_CRB_NIU + 0x98, + CRB_NIU_XG_PAUSE_CTL_P0| + CRB_NIU_XG_PAUSE_CTL_P1); + } ql_log(ql_log_info, base_vha, 0x101e, "Mailbox cmd timeout occured. " "Scheduling ISP abort.\n"); diff --git a/drivers/scsi/qla2xxx/qla_nx.c b/drivers/scsi/qla2xxx/qla_nx.c index 94bded5..0355493 100644 --- a/drivers/scsi/qla2xxx/qla_nx.c +++ b/drivers/scsi/qla2xxx/qla_nx.c @@ -3817,6 +3817,20 @@ exit: return rval; } +void qla82xx_clear_pending_mbx(scsi_qla_host_t *vha) +{ + struct qla_hw_data *ha = vha->hw; + + if (ha->flags.mbox_busy) { + ha->flags.mbox_int = 1; + ha->flags.mbox_busy = 0; + ql_log(ql_log_warn, vha, 0x6010, + "Doing premature completion of mbx command.\n"); + if (test_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags)) + complete(&ha->mbx_intr_comp); + } +} + void qla82xx_watchdog(scsi_qla_host_t *vha) { uint32_t dev_state, halt_status; @@ -3839,9 +3853,13 @@ void qla82xx_watchdog(scsi_qla_host_t *vha) qla2xxx_wake_dpc(vha); } else { if (qla82xx_check_fw_alive(vha)) { + ql_dbg(ql_dbg_timer, vha, 0x6011, + "disabling pause transmit on port 0 & 1.\n"); + qla82xx_wr_32(ha, QLA82XX_CRB_NIU + 0x98, + CRB_NIU_XG_PAUSE_CTL_P0|CRB_NIU_XG_PAUSE_CTL_P1); halt_status = qla82xx_rd_32(ha, QLA82XX_PEG_HALT_STATUS1); - ql_dbg(ql_dbg_timer, vha, 0x6005, + ql_log(ql_log_info, vha, 0x6005, "dumping hw/fw registers:.\n " " PEG_HALT_STATUS1: 0x%x, PEG_HALT_STATUS2: 0x%x,.\n " " PEG_NET_0_PC: 0x%x, PEG_NET_1_PC: 0x%x,.\n " @@ -3858,6 +3876,11 @@ void qla82xx_watchdog(scsi_qla_host_t *vha) QLA82XX_CRB_PEG_NET_3 + 0x3c), qla82xx_rd_32(ha, QLA82XX_CRB_PEG_NET_4 + 0x3c)); + if (LSW(MSB(halt_status)) == 0x67) + ql_log(ql_log_warn, vha, 0xb052, + "Firmware aborted with " + "error code 0x00006700. Device is " + "being reset.\n"); if (halt_status & HALT_STATUS_UNRECOVERABLE) { set_bit(ISP_UNRECOVERABLE, &vha->dpc_flags); @@ -3869,16 +3892,8 @@ void qla82xx_watchdog(scsi_qla_host_t *vha) } qla2xxx_wake_dpc(vha); ha->flags.isp82xx_fw_hung = 1; - if (ha->flags.mbox_busy) { - ha->flags.mbox_int = 1; - ql_log(ql_log_warn, vha, 0x6007, - "Due to FW hung, doing " - "premature completion of mbx " - "command.\n"); - if (test_bit(MBX_INTR_WAIT, - &ha->mbx_cmd_flags)) - complete(&ha->mbx_intr_comp); - } + ql_log(ql_log_warn, vha, 0x6007, "Firmware hung.\n"); + qla82xx_clear_pending_mbx(vha); } } } @@ -4073,10 +4088,7 @@ qla82xx_chip_reset_cleanup(scsi_qla_host_t *vha) msleep(1000); if (qla82xx_check_fw_alive(vha)) { ha->flags.isp82xx_fw_hung = 1; - if (ha->flags.mbox_busy) { - ha->flags.mbox_int = 1; - complete(&ha->mbx_intr_comp); - } + qla82xx_clear_pending_mbx(vha); break; } } diff --git a/drivers/scsi/qla2xxx/qla_nx.h b/drivers/scsi/qla2xxx/qla_nx.h index 57820c1..57a226b 100644 --- a/drivers/scsi/qla2xxx/qla_nx.h +++ b/drivers/scsi/qla2xxx/qla_nx.h @@ -1173,4 +1173,8 @@ struct qla82xx_md_entry_queue { static const int MD_MIU_TEST_AGT_RDDATA[] = { 0x410000A8, 0x410000AC, 0x410000B8, 0x410000BC }; + +#define CRB_NIU_XG_PAUSE_CTL_P0 0x1 +#define CRB_NIU_XG_PAUSE_CTL_P1 0x8 + #endif diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index fd14c7b..f9e5b85 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -201,12 +201,12 @@ MODULE_PARM_DESC(ql2xmdcapmask, "Set the Minidump driver capture mask level. " "Default is 0x7F - Can be set to 0x3, 0x7, 0xF, 0x1F, 0x7F."); -int ql2xmdenable; +int ql2xmdenable = 1; module_param(ql2xmdenable, int, S_IRUGO); MODULE_PARM_DESC(ql2xmdenable, "Enable/disable MiniDump. " - "0 (Default) - MiniDump disabled. " - "1 - MiniDump enabled."); + "0 - MiniDump disabled. " + "1 (Default) - MiniDump enabled."); /* * SCSI host template entry points @@ -423,6 +423,7 @@ fail2: qla25xx_delete_queues(vha); destroy_workqueue(ha->wq); ha->wq = NULL; + vha->req = ha->req_q_map[0]; fail: ha->mqenable = 0; kfree(ha->req_q_map); @@ -814,49 +815,6 @@ qla2x00_wait_for_chip_reset(scsi_qla_host_t *vha) return return_status; } -/* - * qla2x00_wait_for_loop_ready - * Wait for MAX_LOOP_TIMEOUT(5 min) value for loop - * to be in LOOP_READY state. - * Input: - * ha - pointer to host adapter structure - * - * Note: - * Does context switching-Release SPIN_LOCK - * (if any) before calling this routine. - * - * - * Return: - * Success (LOOP_READY) : 0 - * Failed (LOOP_NOT_READY) : 1 - */ -static inline int -qla2x00_wait_for_loop_ready(scsi_qla_host_t *vha) -{ - int return_status = QLA_SUCCESS; - unsigned long loop_timeout ; - struct qla_hw_data *ha = vha->hw; - scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev); - - /* wait for 5 min at the max for loop to be ready */ - loop_timeout = jiffies + (MAX_LOOP_TIMEOUT * HZ); - - while ((!atomic_read(&base_vha->loop_down_timer) && - atomic_read(&base_vha->loop_state) == LOOP_DOWN) || - atomic_read(&base_vha->loop_state) != LOOP_READY) { - if (atomic_read(&base_vha->loop_state) == LOOP_DEAD) { - return_status = QLA_FUNCTION_FAILED; - break; - } - msleep(1000); - if (time_after_eq(jiffies, loop_timeout)) { - return_status = QLA_FUNCTION_FAILED; - break; - } - } - return (return_status); -} - static void sp_get(struct srb *sp) { @@ -1035,12 +993,6 @@ __qla2xxx_eh_generic_reset(char *name, enum nexus_wait_type type, "Wait for hba online failed for cmd=%p.\n", cmd); goto eh_reset_failed; } - err = 1; - if (qla2x00_wait_for_loop_ready(vha) != QLA_SUCCESS) { - ql_log(ql_log_warn, vha, 0x800b, - "Wait for loop ready failed for cmd=%p.\n", cmd); - goto eh_reset_failed; - } err = 2; if (do_reset(fcport, cmd->device->lun, cmd->request->cpu + 1) != QLA_SUCCESS) { @@ -1137,10 +1089,9 @@ qla2xxx_eh_bus_reset(struct scsi_cmnd *cmd) goto eh_bus_reset_done; } - if (qla2x00_wait_for_loop_ready(vha) == QLA_SUCCESS) { - if (qla2x00_loop_reset(vha) == QLA_SUCCESS) - ret = SUCCESS; - } + if (qla2x00_loop_reset(vha) == QLA_SUCCESS) + ret = SUCCESS; + if (ret == FAILED) goto eh_bus_reset_done; @@ -1206,15 +1157,6 @@ qla2xxx_eh_host_reset(struct scsi_cmnd *cmd) if (qla2x00_wait_for_reset_ready(vha) != QLA_SUCCESS) goto eh_host_reset_lock; - /* - * Fixme-may be dpc thread is active and processing - * loop_resync,so wait a while for it to - * be completed and then issue big hammer.Otherwise - * it may cause I/O failure as big hammer marks the - * devices as lost kicking of the port_down_timer - * while dpc is stuck for the mailbox to complete. - */ - qla2x00_wait_for_loop_ready(vha); if (vha != base_vha) { if (qla2x00_vp_abort_isp(vha)) goto eh_host_reset_lock; @@ -1297,16 +1239,13 @@ qla2x00_loop_reset(scsi_qla_host_t *vha) atomic_set(&vha->loop_state, LOOP_DOWN); atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME); qla2x00_mark_all_devices_lost(vha, 0); - qla2x00_wait_for_loop_ready(vha); } if (ha->flags.enable_lip_reset) { ret = qla2x00_lip_reset(vha); - if (ret != QLA_SUCCESS) { + if (ret != QLA_SUCCESS) ql_dbg(ql_dbg_taskm, vha, 0x802e, "lip_reset failed (%d).\n", ret); - } else - qla2x00_wait_for_loop_ready(vha); } /* Issue marker command only when we are going to start the I/O */ @@ -4070,13 +4009,8 @@ qla2xxx_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state) /* For ISP82XX complete any pending mailbox cmd */ if (IS_QLA82XX(ha)) { ha->flags.isp82xx_fw_hung = 1; - if (ha->flags.mbox_busy) { - ha->flags.mbox_int = 1; - ql_dbg(ql_dbg_aer, vha, 0x9001, - "Due to pci channel io frozen, doing premature " - "completion of mbx command.\n"); - complete(&ha->mbx_intr_comp); - } + ql_dbg(ql_dbg_aer, vha, 0x9001, "Pci channel io frozen\n"); + qla82xx_clear_pending_mbx(vha); } qla2x00_free_irqs(vha); pci_disable_device(pdev); diff --git a/drivers/scsi/qla2xxx/qla_version.h b/drivers/scsi/qla2xxx/qla_version.h index 13b6357..23f33a6 100644 --- a/drivers/scsi/qla2xxx/qla_version.h +++ b/drivers/scsi/qla2xxx/qla_version.h @@ -7,7 +7,7 @@ /* * Driver version */ -#define QLA2XXX_VERSION "8.03.07.07-k" +#define QLA2XXX_VERSION "8.03.07.12-k" #define QLA_DRIVER_MAJOR_VER 8 #define QLA_DRIVER_MINOR_VER 3 diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h index ace637b..fd5edc6 100644 --- a/drivers/scsi/qla4xxx/ql4_def.h +++ b/drivers/scsi/qla4xxx/ql4_def.h @@ -147,7 +147,7 @@ #define ISCSI_ALIAS_SIZE 32 /* ISCSI Alias name size */ #define ISCSI_NAME_SIZE 0xE0 /* ISCSI Name size */ -#define QL4_SESS_RECOVERY_TMO 30 /* iSCSI session */ +#define QL4_SESS_RECOVERY_TMO 120 /* iSCSI session */ /* recovery timeout */ #define LSDW(x) ((u32)((u64)(x))) @@ -173,6 +173,8 @@ #define ISNS_DEREG_TOV 5 #define HBA_ONLINE_TOV 30 #define DISABLE_ACB_TOV 30 +#define IP_CONFIG_TOV 30 +#define LOGIN_TOV 12 #define MAX_RESET_HA_RETRIES 2 @@ -240,6 +242,45 @@ struct ddb_entry { uint16_t fw_ddb_index; /* DDB firmware index */ uint32_t fw_ddb_device_state; /* F/W Device State -- see ql4_fw.h */ + uint16_t ddb_type; +#define FLASH_DDB 0x01 + + struct dev_db_entry fw_ddb_entry; + int (*unblock_sess)(struct iscsi_cls_session *cls_session); + int (*ddb_change)(struct scsi_qla_host *ha, uint32_t fw_ddb_index, + struct ddb_entry *ddb_entry, uint32_t state); + + /* Driver Re-login */ + unsigned long flags; /* DDB Flags */ + uint16_t default_relogin_timeout; /* Max time to wait for + * relogin to complete */ + atomic_t retry_relogin_timer; /* Min Time between relogins + * (4000 only) */ + atomic_t relogin_timer; /* Max Time to wait for + * relogin to complete */ + atomic_t relogin_retry_count; /* Num of times relogin has been + * retried */ + uint32_t default_time2wait; /* Default Min time between + * relogins (+aens) */ + +}; + +struct qla_ddb_index { + struct list_head list; + uint16_t fw_ddb_idx; + struct dev_db_entry fw_ddb; +}; + +#define DDB_IPADDR_LEN 64 + +struct ql4_tuple_ddb { + int port; + int tpgt; + char ip_addr[DDB_IPADDR_LEN]; + char iscsi_name[ISCSI_NAME_SIZE]; + uint16_t options; +#define DDB_OPT_IPV6 0x0e0e +#define DDB_OPT_IPV4 0x0f0f }; /* @@ -411,7 +452,7 @@ struct scsi_qla_host { #define AF_FW_RECOVERY 19 /* 0x00080000 */ #define AF_EEH_BUSY 20 /* 0x00100000 */ #define AF_PCI_CHANNEL_IO_PERM_FAILURE 21 /* 0x00200000 */ - +#define AF_BUILD_DDB_LIST 22 /* 0x00400000 */ unsigned long dpc_flags; #define DPC_RESET_HA 1 /* 0x00000002 */ @@ -604,6 +645,7 @@ struct scsi_qla_host { uint16_t bootload_minor; uint16_t bootload_patch; uint16_t bootload_build; + uint16_t def_timeout; /* Default login timeout */ uint32_t flash_state; #define QLFLASH_WAITING 0 @@ -623,6 +665,11 @@ struct scsi_qla_host { uint16_t iscsi_pci_func_cnt; uint8_t model_name[16]; struct completion disable_acb_comp; + struct dma_pool *fw_ddb_dma_pool; +#define DDB_DMA_BLOCK_SIZE 512 + uint16_t pri_ddb_idx; + uint16_t sec_ddb_idx; + int is_reset; }; struct ql4_task_data { @@ -835,6 +882,10 @@ static inline int ql4xxx_reset_active(struct scsi_qla_host *ha) /*---------------------------------------------------------------------------*/ /* Defines for qla4xxx_initialize_adapter() and qla4xxx_recover_adapter() */ + +#define INIT_ADAPTER 0 +#define RESET_ADAPTER 1 + #define PRESERVE_DDB_LIST 0 #define REBUILD_DDB_LIST 1 diff --git a/drivers/scsi/qla4xxx/ql4_fw.h b/drivers/scsi/qla4xxx/ql4_fw.h index cbd5a20..4ac07f8 100644 --- a/drivers/scsi/qla4xxx/ql4_fw.h +++ b/drivers/scsi/qla4xxx/ql4_fw.h @@ -12,6 +12,7 @@ #define MAX_PRST_DEV_DB_ENTRIES 64 #define MIN_DISC_DEV_DB_ENTRY MAX_PRST_DEV_DB_ENTRIES #define MAX_DEV_DB_ENTRIES 512 +#define MAX_DEV_DB_ENTRIES_40XX 256 /************************************************************************* * @@ -604,6 +605,13 @@ struct addr_ctrl_blk { uint8_t res14[140]; /* 274-2FF */ }; +#define IP_ADDR_COUNT 4 /* Total 4 IP address supported in one interface + * One IPv4, one IPv6 link local and 2 IPv6 + */ + +#define IP_STATE_MASK 0x0F000000 +#define IP_STATE_SHIFT 24 + struct init_fw_ctrl_blk { struct addr_ctrl_blk pri; /* struct addr_ctrl_blk sec;*/ diff --git a/drivers/scsi/qla4xxx/ql4_glbl.h b/drivers/scsi/qla4xxx/ql4_glbl.h index 160db9d..d0dd4b3 100644 --- a/drivers/scsi/qla4xxx/ql4_glbl.h +++ b/drivers/scsi/qla4xxx/ql4_glbl.h @@ -13,7 +13,7 @@ struct iscsi_cls_conn; int qla4xxx_hw_reset(struct scsi_qla_host *ha); int ql4xxx_lock_drvr_wait(struct scsi_qla_host *a); int qla4xxx_send_command_to_isp(struct scsi_qla_host *ha, struct srb *srb); -int qla4xxx_initialize_adapter(struct scsi_qla_host *ha); +int qla4xxx_initialize_adapter(struct scsi_qla_host *ha, int is_reset); int qla4xxx_soft_reset(struct scsi_qla_host *ha); irqreturn_t qla4xxx_intr_handler(int irq, void *dev_id); @@ -153,10 +153,13 @@ int qla4xxx_req_ddb_entry(struct scsi_qla_host *ha, uint32_t fw_ddb_index, uint32_t *mbx_sts); int qla4xxx_clear_ddb_entry(struct scsi_qla_host *ha, uint32_t fw_ddb_index); int qla4xxx_send_passthru0(struct iscsi_task *task); +void qla4xxx_free_ddb_index(struct scsi_qla_host *ha); int qla4xxx_get_mgmt_data(struct scsi_qla_host *ha, uint16_t fw_ddb_index, uint16_t stats_size, dma_addr_t stats_dma); void qla4xxx_update_session_conn_param(struct scsi_qla_host *ha, struct ddb_entry *ddb_entry); +void qla4xxx_update_session_conn_fwddb_param(struct scsi_qla_host *ha, + struct ddb_entry *ddb_entry); int qla4xxx_bootdb_by_index(struct scsi_qla_host *ha, struct dev_db_entry *fw_ddb_entry, dma_addr_t fw_ddb_entry_dma, uint16_t ddb_index); @@ -169,11 +172,22 @@ int qla4xxx_set_nvram(struct scsi_qla_host *ha, dma_addr_t nvram_dma, int qla4xxx_restore_factory_defaults(struct scsi_qla_host *ha, uint32_t region, uint32_t field0, uint32_t field1); +int qla4xxx_get_ddb_index(struct scsi_qla_host *ha, uint16_t *ddb_index); +void qla4xxx_login_flash_ddb(struct iscsi_cls_session *cls_session); +int qla4xxx_unblock_ddb(struct iscsi_cls_session *cls_session); +int qla4xxx_unblock_flash_ddb(struct iscsi_cls_session *cls_session); +int qla4xxx_flash_ddb_change(struct scsi_qla_host *ha, uint32_t fw_ddb_index, + struct ddb_entry *ddb_entry, uint32_t state); +int qla4xxx_ddb_change(struct scsi_qla_host *ha, uint32_t fw_ddb_index, + struct ddb_entry *ddb_entry, uint32_t state); +void qla4xxx_build_ddb_list(struct scsi_qla_host *ha, int is_reset); /* BSG Functions */ int qla4xxx_bsg_request(struct bsg_job *bsg_job); int qla4xxx_process_vendor_specific(struct bsg_job *bsg_job); +void qla4xxx_arm_relogin_timer(struct ddb_entry *ddb_entry); + extern int ql4xextended_error_logging; extern int ql4xdontresethba; extern int ql4xenablemsix; diff --git a/drivers/scsi/qla4xxx/ql4_init.c b/drivers/scsi/qla4xxx/ql4_init.c index 3075fba..1bdfa81 100644 --- a/drivers/scsi/qla4xxx/ql4_init.c +++ b/drivers/scsi/qla4xxx/ql4_init.c @@ -773,22 +773,24 @@ int qla4xxx_start_firmware(struct scsi_qla_host *ha) * be freed so that when login happens from user space there are free DDB * indices available. **/ -static void qla4xxx_free_ddb_index(struct scsi_qla_host *ha) +void qla4xxx_free_ddb_index(struct scsi_qla_host *ha) { int max_ddbs; int ret; uint32_t idx = 0, next_idx = 0; uint32_t state = 0, conn_err = 0; - max_ddbs = is_qla40XX(ha) ? MAX_PRST_DEV_DB_ENTRIES : + max_ddbs = is_qla40XX(ha) ? MAX_DEV_DB_ENTRIES_40XX : MAX_DEV_DB_ENTRIES; for (idx = 0; idx < max_ddbs; idx = next_idx) { ret = qla4xxx_get_fwddb_entry(ha, idx, NULL, 0, NULL, &next_idx, &state, &conn_err, NULL, NULL); - if (ret == QLA_ERROR) + if (ret == QLA_ERROR) { + next_idx++; continue; + } if (state == DDB_DS_NO_CONNECTION_ACTIVE || state == DDB_DS_SESSION_FAILED) { DEBUG2(ql4_printk(KERN_INFO, ha, @@ -804,7 +806,6 @@ static void qla4xxx_free_ddb_index(struct scsi_qla_host *ha) } } - /** * qla4xxx_initialize_adapter - initiailizes hba * @ha: Pointer to host adapter structure. @@ -812,7 +813,7 @@ static void qla4xxx_free_ddb_index(struct scsi_qla_host *ha) * This routine parforms all of the steps necessary to initialize the adapter. * **/ -int qla4xxx_initialize_adapter(struct scsi_qla_host *ha) +int qla4xxx_initialize_adapter(struct scsi_qla_host *ha, int is_reset) { int status = QLA_ERROR; @@ -840,7 +841,8 @@ int qla4xxx_initialize_adapter(struct scsi_qla_host *ha) if (status == QLA_ERROR) goto exit_init_hba; - qla4xxx_free_ddb_index(ha); + if (is_reset == RESET_ADAPTER) + qla4xxx_build_ddb_list(ha, is_reset); set_bit(AF_ONLINE, &ha->flags); exit_init_hba: @@ -855,38 +857,12 @@ exit_init_hba: return status; } -/** - * qla4xxx_process_ddb_changed - process ddb state change - * @ha - Pointer to host adapter structure. - * @fw_ddb_index - Firmware's device database index - * @state - Device state - * - * This routine processes a Decive Database Changed AEN Event. - **/ -int qla4xxx_process_ddb_changed(struct scsi_qla_host *ha, uint32_t fw_ddb_index, - uint32_t state, uint32_t conn_err) +int qla4xxx_ddb_change(struct scsi_qla_host *ha, uint32_t fw_ddb_index, + struct ddb_entry *ddb_entry, uint32_t state) { - struct ddb_entry * ddb_entry; uint32_t old_fw_ddb_device_state; int status = QLA_ERROR; - /* check for out of range index */ - if (fw_ddb_index >= MAX_DDB_ENTRIES) - goto exit_ddb_event; - - /* Get the corresponging ddb entry */ - ddb_entry = qla4xxx_lookup_ddb_by_fw_index(ha, fw_ddb_index); - /* Device does not currently exist in our database. */ - if (ddb_entry == NULL) { - ql4_printk(KERN_ERR, ha, "%s: No ddb_entry at FW index [%d]\n", - __func__, fw_ddb_index); - - if (state == DDB_DS_NO_CONNECTION_ACTIVE) - clear_bit(fw_ddb_index, ha->ddb_idx_map); - - goto exit_ddb_event; - } - old_fw_ddb_device_state = ddb_entry->fw_ddb_device_state; DEBUG2(ql4_printk(KERN_INFO, ha, "%s: DDB - old state = 0x%x, new state = 0x%x for " @@ -900,9 +876,7 @@ int qla4xxx_process_ddb_changed(struct scsi_qla_host *ha, uint32_t fw_ddb_index, switch (state) { case DDB_DS_SESSION_ACTIVE: case DDB_DS_DISCOVERY: - iscsi_conn_start(ddb_entry->conn); - iscsi_conn_login_event(ddb_entry->conn, - ISCSI_CONN_STATE_LOGGED_IN); + ddb_entry->unblock_sess(ddb_entry->sess); qla4xxx_update_session_conn_param(ha, ddb_entry); status = QLA_SUCCESS; break; @@ -936,9 +910,7 @@ int qla4xxx_process_ddb_changed(struct scsi_qla_host *ha, uint32_t fw_ddb_index, switch (state) { case DDB_DS_SESSION_ACTIVE: case DDB_DS_DISCOVERY: - iscsi_conn_start(ddb_entry->conn); - iscsi_conn_login_event(ddb_entry->conn, - ISCSI_CONN_STATE_LOGGED_IN); + ddb_entry->unblock_sess(ddb_entry->sess); qla4xxx_update_session_conn_param(ha, ddb_entry); status = QLA_SUCCESS; break; @@ -954,7 +926,198 @@ int qla4xxx_process_ddb_changed(struct scsi_qla_host *ha, uint32_t fw_ddb_index, __func__)); break; } + return status; +} + +void qla4xxx_arm_relogin_timer(struct ddb_entry *ddb_entry) +{ + /* + * This triggers a relogin. After the relogin_timer + * expires, the relogin gets scheduled. We must wait a + * minimum amount of time since receiving an 0x8014 AEN + * with failed device_state or a logout response before + * we can issue another relogin. + * + * Firmware pads this timeout: (time2wait +1). + * Driver retry to login should be longer than F/W. + * Otherwise F/W will fail + * set_ddb() mbx cmd with 0x4005 since it still + * counting down its time2wait. + */ + atomic_set(&ddb_entry->relogin_timer, 0); + atomic_set(&ddb_entry->retry_relogin_timer, + ddb_entry->default_time2wait + 4); + +} + +int qla4xxx_flash_ddb_change(struct scsi_qla_host *ha, uint32_t fw_ddb_index, + struct ddb_entry *ddb_entry, uint32_t state) +{ + uint32_t old_fw_ddb_device_state; + int status = QLA_ERROR; + + old_fw_ddb_device_state = ddb_entry->fw_ddb_device_state; + DEBUG2(ql4_printk(KERN_INFO, ha, + "%s: DDB - old state = 0x%x, new state = 0x%x for " + "index [%d]\n", __func__, + ddb_entry->fw_ddb_device_state, state, fw_ddb_index)); + + ddb_entry->fw_ddb_device_state = state; + + switch (old_fw_ddb_device_state) { + case DDB_DS_LOGIN_IN_PROCESS: + case DDB_DS_NO_CONNECTION_ACTIVE: + switch (state) { + case DDB_DS_SESSION_ACTIVE: + ddb_entry->unblock_sess(ddb_entry->sess); + qla4xxx_update_session_conn_fwddb_param(ha, ddb_entry); + status = QLA_SUCCESS; + break; + case DDB_DS_SESSION_FAILED: + iscsi_block_session(ddb_entry->sess); + if (!test_bit(DF_RELOGIN, &ddb_entry->flags)) + qla4xxx_arm_relogin_timer(ddb_entry); + status = QLA_SUCCESS; + break; + } + break; + case DDB_DS_SESSION_ACTIVE: + switch (state) { + case DDB_DS_SESSION_FAILED: + iscsi_block_session(ddb_entry->sess); + if (!test_bit(DF_RELOGIN, &ddb_entry->flags)) + qla4xxx_arm_relogin_timer(ddb_entry); + status = QLA_SUCCESS; + break; + } + break; + case DDB_DS_SESSION_FAILED: + switch (state) { + case DDB_DS_SESSION_ACTIVE: + ddb_entry->unblock_sess(ddb_entry->sess); + qla4xxx_update_session_conn_fwddb_param(ha, ddb_entry); + status = QLA_SUCCESS; + break; + case DDB_DS_SESSION_FAILED: + if (!test_bit(DF_RELOGIN, &ddb_entry->flags)) + qla4xxx_arm_relogin_timer(ddb_entry); + status = QLA_SUCCESS; + break; + } + break; + default: + DEBUG2(ql4_printk(KERN_INFO, ha, "%s: Unknown Event\n", + __func__)); + break; + } + return status; +} + +/** + * qla4xxx_process_ddb_changed - process ddb state change + * @ha - Pointer to host adapter structure. + * @fw_ddb_index - Firmware's device database index + * @state - Device state + * + * This routine processes a Decive Database Changed AEN Event. + **/ +int qla4xxx_process_ddb_changed(struct scsi_qla_host *ha, + uint32_t fw_ddb_index, + uint32_t state, uint32_t conn_err) +{ + struct ddb_entry *ddb_entry; + int status = QLA_ERROR; + + /* check for out of range index */ + if (fw_ddb_index >= MAX_DDB_ENTRIES) + goto exit_ddb_event; + + /* Get the corresponging ddb entry */ + ddb_entry = qla4xxx_lookup_ddb_by_fw_index(ha, fw_ddb_index); + /* Device does not currently exist in our database. */ + if (ddb_entry == NULL) { + ql4_printk(KERN_ERR, ha, "%s: No ddb_entry at FW index [%d]\n", + __func__, fw_ddb_index); + + if (state == DDB_DS_NO_CONNECTION_ACTIVE) + clear_bit(fw_ddb_index, ha->ddb_idx_map); + + goto exit_ddb_event; + } + + ddb_entry->ddb_change(ha, fw_ddb_index, ddb_entry, state); exit_ddb_event: return status; } + +/** + * qla4xxx_login_flash_ddb - Login to target (DDB) + * @cls_session: Pointer to the session to login + * + * This routine logins to the target. + * Issues setddb and conn open mbx + **/ +void qla4xxx_login_flash_ddb(struct iscsi_cls_session *cls_session) +{ + struct iscsi_session *sess; + struct ddb_entry *ddb_entry; + struct scsi_qla_host *ha; + struct dev_db_entry *fw_ddb_entry = NULL; + dma_addr_t fw_ddb_dma; + uint32_t mbx_sts = 0; + int ret; + + sess = cls_session->dd_data; + ddb_entry = sess->dd_data; + ha = ddb_entry->ha; + + if (!test_bit(AF_LINK_UP, &ha->flags)) + return; + + if (ddb_entry->ddb_type != FLASH_DDB) { + DEBUG2(ql4_printk(KERN_INFO, ha, + "Skipping login to non FLASH DB")); + goto exit_login; + } + + fw_ddb_entry = dma_pool_alloc(ha->fw_ddb_dma_pool, GFP_KERNEL, + &fw_ddb_dma); + if (fw_ddb_entry == NULL) { + DEBUG2(ql4_printk(KERN_ERR, ha, "Out of memory\n")); + goto exit_login; + } + + if (ddb_entry->fw_ddb_index == INVALID_ENTRY) { + ret = qla4xxx_get_ddb_index(ha, &ddb_entry->fw_ddb_index); + if (ret == QLA_ERROR) + goto exit_login; + + ha->fw_ddb_index_map[ddb_entry->fw_ddb_index] = ddb_entry; + ha->tot_ddbs++; + } + + memcpy(fw_ddb_entry, &ddb_entry->fw_ddb_entry, + sizeof(struct dev_db_entry)); + ddb_entry->sess->target_id = ddb_entry->fw_ddb_index; + + ret = qla4xxx_set_ddb_entry(ha, ddb_entry->fw_ddb_index, + fw_ddb_dma, &mbx_sts); + if (ret == QLA_ERROR) { + DEBUG2(ql4_printk(KERN_ERR, ha, "Set DDB failed\n")); + goto exit_login; + } + + ddb_entry->fw_ddb_device_state = DDB_DS_LOGIN_IN_PROCESS; + ret = qla4xxx_conn_open(ha, ddb_entry->fw_ddb_index); + if (ret == QLA_ERROR) { + ql4_printk(KERN_ERR, ha, "%s: Login failed: %s\n", __func__, + sess->targetname); + goto exit_login; + } + +exit_login: + if (fw_ddb_entry) + dma_pool_free(ha->fw_ddb_dma_pool, fw_ddb_entry, fw_ddb_dma); +} + diff --git a/drivers/scsi/qla4xxx/ql4_mbx.c b/drivers/scsi/qla4xxx/ql4_mbx.c index 4c2b848..c259378 100644 --- a/drivers/scsi/qla4xxx/ql4_mbx.c +++ b/drivers/scsi/qla4xxx/ql4_mbx.c @@ -41,6 +41,16 @@ int qla4xxx_mailbox_command(struct scsi_qla_host *ha, uint8_t inCount, return status; } + if (is_qla40XX(ha)) { + if (test_bit(AF_HA_REMOVAL, &ha->flags)) { + DEBUG2(ql4_printk(KERN_WARNING, ha, "scsi%ld: %s: " + "prematurely completing mbx cmd as " + "adapter removal detected\n", + ha->host_no, __func__)); + return status; + } + } + if (is_qla8022(ha)) { if (test_bit(AF_FW_RECOVERY, &ha->flags)) { DEBUG2(ql4_printk(KERN_WARNING, ha, "scsi%ld: %s: " @@ -413,6 +423,7 @@ qla4xxx_update_local_ifcb(struct scsi_qla_host *ha, memcpy(ha->name_string, init_fw_cb->iscsi_name, min(sizeof(ha->name_string), sizeof(init_fw_cb->iscsi_name))); + ha->def_timeout = le16_to_cpu(init_fw_cb->def_timeout); /*memcpy(ha->alias, init_fw_cb->Alias, min(sizeof(ha->alias), sizeof(init_fw_cb->Alias)));*/ diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c index 30f31b1..4169c8b 100644 --- a/drivers/scsi/qla4xxx/ql4_os.c +++ b/drivers/scsi/qla4xxx/ql4_os.c @@ -8,6 +8,7 @@ #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/iscsi_boot_sysfs.h> +#include <linux/inet.h> #include <scsi/scsi_tcq.h> #include <scsi/scsicam.h> @@ -31,6 +32,13 @@ static struct kmem_cache *srb_cachep; /* * Module parameter information and variables */ +int ql4xdisablesysfsboot = 1; +module_param(ql4xdisablesysfsboot, int, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(ql4xdisablesysfsboot, + "Set to disable exporting boot targets to sysfs\n" + " 0 - Export boot targets\n" + " 1 - Do not export boot targets (Default)"); + int ql4xdontresethba = 0; module_param(ql4xdontresethba, int, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(ql4xdontresethba, @@ -63,7 +71,7 @@ static int ql4xsess_recovery_tmo = QL4_SESS_RECOVERY_TMO; module_param(ql4xsess_recovery_tmo, int, S_IRUGO); MODULE_PARM_DESC(ql4xsess_recovery_tmo, "Target Session Recovery Timeout.\n" - " Default: 30 sec."); + " Default: 120 sec."); static int qla4xxx_wait_for_hba_online(struct scsi_qla_host *ha); /* @@ -415,7 +423,7 @@ static int qla4xxx_ep_poll(struct iscsi_endpoint *ep, int timeout_ms) qla_ep = ep->dd_data; ha = to_qla_host(qla_ep->host); - if (adapter_up(ha)) + if (adapter_up(ha) && !test_bit(AF_BUILD_DDB_LIST, &ha->flags)) ret = 1; return ret; @@ -975,6 +983,150 @@ static int qla4xxx_conn_get_param(struct iscsi_cls_conn *cls_conn, } +int qla4xxx_get_ddb_index(struct scsi_qla_host *ha, uint16_t *ddb_index) +{ + uint32_t mbx_sts = 0; + uint16_t tmp_ddb_index; + int ret; + +get_ddb_index: + tmp_ddb_index = find_first_zero_bit(ha->ddb_idx_map, MAX_DDB_ENTRIES); + + if (tmp_ddb_index >= MAX_DDB_ENTRIES) { + DEBUG2(ql4_printk(KERN_INFO, ha, + "Free DDB index not available\n")); + ret = QLA_ERROR; + goto exit_get_ddb_index; + } + + if (test_and_set_bit(tmp_ddb_index, ha->ddb_idx_map)) + goto get_ddb_index; + + DEBUG2(ql4_printk(KERN_INFO, ha, + "Found a free DDB index at %d\n", tmp_ddb_index)); + ret = qla4xxx_req_ddb_entry(ha, tmp_ddb_index, &mbx_sts); + if (ret == QLA_ERROR) { + if (mbx_sts == MBOX_STS_COMMAND_ERROR) { + ql4_printk(KERN_INFO, ha, + "DDB index = %d not available trying next\n", + tmp_ddb_index); + goto get_ddb_index; + } + DEBUG2(ql4_printk(KERN_INFO, ha, + "Free FW DDB not available\n")); + } + + *ddb_index = tmp_ddb_index; + +exit_get_ddb_index: + return ret; +} + +static int qla4xxx_match_ipaddress(struct scsi_qla_host *ha, + struct ddb_entry *ddb_entry, + char *existing_ipaddr, + char *user_ipaddr) +{ + uint8_t dst_ipaddr[IPv6_ADDR_LEN]; + char formatted_ipaddr[DDB_IPADDR_LEN]; + int status = QLA_SUCCESS, ret = 0; + + if (ddb_entry->fw_ddb_entry.options & DDB_OPT_IPV6_DEVICE) { + ret = in6_pton(user_ipaddr, strlen(user_ipaddr), dst_ipaddr, + '\0', NULL); + if (ret == 0) { + status = QLA_ERROR; + goto out_match; + } + ret = sprintf(formatted_ipaddr, "%pI6", dst_ipaddr); + } else { + ret = in4_pton(user_ipaddr, strlen(user_ipaddr), dst_ipaddr, + '\0', NULL); + if (ret == 0) { + status = QLA_ERROR; + goto out_match; + } + ret = sprintf(formatted_ipaddr, "%pI4", dst_ipaddr); + } + + if (strcmp(existing_ipaddr, formatted_ipaddr)) + status = QLA_ERROR; + +out_match: + return status; +} + +static int qla4xxx_match_fwdb_session(struct scsi_qla_host *ha, + struct iscsi_cls_conn *cls_conn) +{ + int idx = 0, max_ddbs, rval; + struct iscsi_cls_session *cls_sess = iscsi_conn_to_session(cls_conn); + struct iscsi_session *sess, *existing_sess; + struct iscsi_conn *conn, *existing_conn; + struct ddb_entry *ddb_entry; + + sess = cls_sess->dd_data; + conn = cls_conn->dd_data; + + if (sess->targetname == NULL || + conn->persistent_address == NULL || + conn->persistent_port == 0) + return QLA_ERROR; + + max_ddbs = is_qla40XX(ha) ? MAX_DEV_DB_ENTRIES_40XX : + MAX_DEV_DB_ENTRIES; + + for (idx = 0; idx < max_ddbs; idx++) { + ddb_entry = qla4xxx_lookup_ddb_by_fw_index(ha, idx); + if (ddb_entry == NULL) + continue; + + if (ddb_entry->ddb_type != FLASH_DDB) + continue; + + existing_sess = ddb_entry->sess->dd_data; + existing_conn = ddb_entry->conn->dd_data; + + if (existing_sess->targetname == NULL || + existing_conn->persistent_address == NULL || + existing_conn->persistent_port == 0) + continue; + + DEBUG2(ql4_printk(KERN_INFO, ha, + "IQN = %s User IQN = %s\n", + existing_sess->targetname, + sess->targetname)); + + DEBUG2(ql4_printk(KERN_INFO, ha, + "IP = %s User IP = %s\n", + existing_conn->persistent_address, + conn->persistent_address)); + + DEBUG2(ql4_printk(KERN_INFO, ha, + "Port = %d User Port = %d\n", + existing_conn->persistent_port, + conn->persistent_port)); + + if (strcmp(existing_sess->targetname, sess->targetname)) + continue; + rval = qla4xxx_match_ipaddress(ha, ddb_entry, + existing_conn->persistent_address, + conn->persistent_address); + if (rval == QLA_ERROR) + continue; + if (existing_conn->persistent_port != conn->persistent_port) + continue; + break; + } + + if (idx == max_ddbs) + return QLA_ERROR; + + DEBUG2(ql4_printk(KERN_INFO, ha, + "Match found in fwdb sessions\n")); + return QLA_SUCCESS; +} + static struct iscsi_cls_session * qla4xxx_session_create(struct iscsi_endpoint *ep, uint16_t cmds_max, uint16_t qdepth, @@ -984,8 +1136,7 @@ qla4xxx_session_create(struct iscsi_endpoint *ep, struct scsi_qla_host *ha; struct qla_endpoint *qla_ep; struct ddb_entry *ddb_entry; - uint32_t ddb_index; - uint32_t mbx_sts = 0; + uint16_t ddb_index; struct iscsi_session *sess; struct sockaddr *dst_addr; int ret; @@ -1000,32 +1151,9 @@ qla4xxx_session_create(struct iscsi_endpoint *ep, dst_addr = (struct sockaddr *)&qla_ep->dst_addr; ha = to_qla_host(qla_ep->host); -get_ddb_index: - ddb_index = find_first_zero_bit(ha->ddb_idx_map, MAX_DDB_ENTRIES); - - if (ddb_index >= MAX_DDB_ENTRIES) { - DEBUG2(ql4_printk(KERN_INFO, ha, - "Free DDB index not available\n")); - return NULL; - } - - if (test_and_set_bit(ddb_index, ha->ddb_idx_map)) - goto get_ddb_index; - - DEBUG2(ql4_printk(KERN_INFO, ha, - "Found a free DDB index at %d\n", ddb_index)); - ret = qla4xxx_req_ddb_entry(ha, ddb_index, &mbx_sts); - if (ret == QLA_ERROR) { - if (mbx_sts == MBOX_STS_COMMAND_ERROR) { - ql4_printk(KERN_INFO, ha, - "DDB index = %d not available trying next\n", - ddb_index); - goto get_ddb_index; - } - DEBUG2(ql4_printk(KERN_INFO, ha, - "Free FW DDB not available\n")); + ret = qla4xxx_get_ddb_index(ha, &ddb_index); + if (ret == QLA_ERROR) return NULL; - } cls_sess = iscsi_session_setup(&qla4xxx_iscsi_transport, qla_ep->host, cmds_max, sizeof(struct ddb_entry), @@ -1040,6 +1168,8 @@ get_ddb_index: ddb_entry->fw_ddb_device_state = DDB_DS_NO_CONNECTION_ACTIVE; ddb_entry->ha = ha; ddb_entry->sess = cls_sess; + ddb_entry->unblock_sess = qla4xxx_unblock_ddb; + ddb_entry->ddb_change = qla4xxx_ddb_change; cls_sess->recovery_tmo = ql4xsess_recovery_tmo; ha->fw_ddb_index_map[ddb_entry->fw_ddb_index] = ddb_entry; ha->tot_ddbs++; @@ -1077,6 +1207,9 @@ qla4xxx_conn_create(struct iscsi_cls_session *cls_sess, uint32_t conn_idx) DEBUG2(printk(KERN_INFO "Func: %s\n", __func__)); cls_conn = iscsi_conn_setup(cls_sess, sizeof(struct qla_conn), conn_idx); + if (!cls_conn) + return NULL; + sess = cls_sess->dd_data; ddb_entry = sess->dd_data; ddb_entry->conn = cls_conn; @@ -1109,7 +1242,7 @@ static int qla4xxx_conn_start(struct iscsi_cls_conn *cls_conn) struct iscsi_session *sess; struct ddb_entry *ddb_entry; struct scsi_qla_host *ha; - struct dev_db_entry *fw_ddb_entry; + struct dev_db_entry *fw_ddb_entry = NULL; dma_addr_t fw_ddb_entry_dma; uint32_t mbx_sts = 0; int ret = 0; @@ -1120,12 +1253,25 @@ static int qla4xxx_conn_start(struct iscsi_cls_conn *cls_conn) ddb_entry = sess->dd_data; ha = ddb_entry->ha; + /* Check if we have matching FW DDB, if yes then do not + * login to this target. This could cause target to logout previous + * connection + */ + ret = qla4xxx_match_fwdb_session(ha, cls_conn); + if (ret == QLA_SUCCESS) { + ql4_printk(KERN_INFO, ha, + "Session already exist in FW.\n"); + ret = -EEXIST; + goto exit_conn_start; + } + fw_ddb_entry = dma_alloc_coherent(&ha->pdev->dev, sizeof(*fw_ddb_entry), &fw_ddb_entry_dma, GFP_KERNEL); if (!fw_ddb_entry) { ql4_printk(KERN_ERR, ha, "%s: Unable to allocate dma buffer\n", __func__); - return -ENOMEM; + ret = -ENOMEM; + goto exit_conn_start; } ret = qla4xxx_set_param_ddbentry(ha, ddb_entry, cls_conn, &mbx_sts); @@ -1138,9 +1284,7 @@ static int qla4xxx_conn_start(struct iscsi_cls_conn *cls_conn) if (mbx_sts) if (ddb_entry->fw_ddb_device_state == DDB_DS_SESSION_ACTIVE) { - iscsi_conn_start(ddb_entry->conn); - iscsi_conn_login_event(ddb_entry->conn, - ISCSI_CONN_STATE_LOGGED_IN); + ddb_entry->unblock_sess(ddb_entry->sess); goto exit_set_param; } @@ -1167,8 +1311,9 @@ exit_set_param: ret = 0; exit_conn_start: - dma_free_coherent(&ha->pdev->dev, sizeof(*fw_ddb_entry), - fw_ddb_entry, fw_ddb_entry_dma); + if (fw_ddb_entry) + dma_free_coherent(&ha->pdev->dev, sizeof(*fw_ddb_entry), + fw_ddb_entry, fw_ddb_entry_dma); return ret; } @@ -1344,6 +1489,101 @@ static int qla4xxx_task_xmit(struct iscsi_task *task) return -ENOSYS; } +static void qla4xxx_copy_fwddb_param(struct scsi_qla_host *ha, + struct dev_db_entry *fw_ddb_entry, + struct iscsi_cls_session *cls_sess, + struct iscsi_cls_conn *cls_conn) +{ + int buflen = 0; + struct iscsi_session *sess; + struct iscsi_conn *conn; + char ip_addr[DDB_IPADDR_LEN]; + uint16_t options = 0; + + sess = cls_sess->dd_data; + conn = cls_conn->dd_data; + + conn->max_recv_dlength = BYTE_UNITS * + le16_to_cpu(fw_ddb_entry->iscsi_max_rcv_data_seg_len); + + conn->max_xmit_dlength = BYTE_UNITS * + le16_to_cpu(fw_ddb_entry->iscsi_max_snd_data_seg_len); + + sess->initial_r2t_en = + (BIT_10 & le16_to_cpu(fw_ddb_entry->iscsi_options)); + + sess->max_r2t = le16_to_cpu(fw_ddb_entry->iscsi_max_outsnd_r2t); + + sess->imm_data_en = (BIT_11 & le16_to_cpu(fw_ddb_entry->iscsi_options)); + + sess->first_burst = BYTE_UNITS * + le16_to_cpu(fw_ddb_entry->iscsi_first_burst_len); + + sess->max_burst = BYTE_UNITS * + le16_to_cpu(fw_ddb_entry->iscsi_max_burst_len); + + sess->time2wait = le16_to_cpu(fw_ddb_entry->iscsi_def_time2wait); + + sess->time2retain = le16_to_cpu(fw_ddb_entry->iscsi_def_time2retain); + + conn->persistent_port = le16_to_cpu(fw_ddb_entry->port); + + sess->tpgt = le32_to_cpu(fw_ddb_entry->tgt_portal_grp); + + options = le16_to_cpu(fw_ddb_entry->options); + if (options & DDB_OPT_IPV6_DEVICE) + sprintf(ip_addr, "%pI6", fw_ddb_entry->ip_addr); + else + sprintf(ip_addr, "%pI4", fw_ddb_entry->ip_addr); + + iscsi_set_param(cls_conn, ISCSI_PARAM_TARGET_NAME, + (char *)fw_ddb_entry->iscsi_name, buflen); + iscsi_set_param(cls_conn, ISCSI_PARAM_INITIATOR_NAME, + (char *)ha->name_string, buflen); + iscsi_set_param(cls_conn, ISCSI_PARAM_PERSISTENT_ADDRESS, + (char *)ip_addr, buflen); +} + +void qla4xxx_update_session_conn_fwddb_param(struct scsi_qla_host *ha, + struct ddb_entry *ddb_entry) +{ + struct iscsi_cls_session *cls_sess; + struct iscsi_cls_conn *cls_conn; + uint32_t ddb_state; + dma_addr_t fw_ddb_entry_dma; + struct dev_db_entry *fw_ddb_entry; + + fw_ddb_entry = dma_alloc_coherent(&ha->pdev->dev, sizeof(*fw_ddb_entry), + &fw_ddb_entry_dma, GFP_KERNEL); + if (!fw_ddb_entry) { + ql4_printk(KERN_ERR, ha, + "%s: Unable to allocate dma buffer\n", __func__); + goto exit_session_conn_fwddb_param; + } + + if (qla4xxx_get_fwddb_entry(ha, ddb_entry->fw_ddb_index, fw_ddb_entry, + fw_ddb_entry_dma, NULL, NULL, &ddb_state, + NULL, NULL, NULL) == QLA_ERROR) { + DEBUG2(ql4_printk(KERN_ERR, ha, "scsi%ld: %s: failed " + "get_ddb_entry for fw_ddb_index %d\n", + ha->host_no, __func__, + ddb_entry->fw_ddb_index)); + goto exit_session_conn_fwddb_param; + } + + cls_sess = ddb_entry->sess; + + cls_conn = ddb_entry->conn; + + /* Update params */ + qla4xxx_copy_fwddb_param(ha, fw_ddb_entry, cls_sess, cls_conn); + +exit_session_conn_fwddb_param: + if (fw_ddb_entry) + dma_free_coherent(&ha->pdev->dev, sizeof(*fw_ddb_entry), + fw_ddb_entry, fw_ddb_entry_dma); +} + void qla4xxx_update_session_conn_param(struct scsi_qla_host *ha, struct ddb_entry *ddb_entry) { @@ -1360,7 +1600,7 @@ void qla4xxx_update_session_conn_param(struct scsi_qla_host *ha, if (!fw_ddb_entry) { ql4_printk(KERN_ERR, ha, "%s: Unable to allocate dma buffer\n", __func__); - return; + goto exit_session_conn_param; } if (qla4xxx_get_fwddb_entry(ha, ddb_entry->fw_ddb_index, fw_ddb_entry, @@ -1370,7 +1610,7 @@ void qla4xxx_update_session_conn_param(struct scsi_qla_host *ha, "get_ddb_entry for fw_ddb_index %d\n", ha->host_no, __func__, ddb_entry->fw_ddb_index)); - return; + goto exit_session_conn_param; } cls_sess = ddb_entry->sess; @@ -1379,6 +1619,12 @@ void qla4xxx_update_session_conn_param(struct scsi_qla_host *ha, cls_conn = ddb_entry->conn; conn = cls_conn->dd_data; + /* Update timers after login */ + ddb_entry->default_relogin_timeout = + le16_to_cpu(fw_ddb_entry->def_timeout); + ddb_entry->default_time2wait = + le16_to_cpu(fw_ddb_entry->iscsi_def_time2wait); + /* Update params */ conn->max_recv_dlength = BYTE_UNITS * le16_to_cpu(fw_ddb_entry->iscsi_max_rcv_data_seg_len); @@ -1407,6 +1653,11 @@ void qla4xxx_update_session_conn_param(struct scsi_qla_host *ha, memcpy(sess->initiatorname, ha->name_string, min(sizeof(ha->name_string), sizeof(sess->initiatorname))); + +exit_session_conn_param: + if (fw_ddb_entry) + dma_free_coherent(&ha->pdev->dev, sizeof(*fw_ddb_entry), + fw_ddb_entry, fw_ddb_entry_dma); } /* @@ -1607,6 +1858,9 @@ static void qla4xxx_mem_free(struct scsi_qla_host *ha) vfree(ha->chap_list); ha->chap_list = NULL; + if (ha->fw_ddb_dma_pool) + dma_pool_destroy(ha->fw_ddb_dma_pool); + /* release io space registers */ if (is_qla8022(ha)) { if (ha->nx_pcibase) @@ -1689,6 +1943,16 @@ static int qla4xxx_mem_alloc(struct scsi_qla_host *ha) goto mem_alloc_error_exit; } + ha->fw_ddb_dma_pool = dma_pool_create("ql4_fw_ddb", &ha->pdev->dev, + DDB_DMA_BLOCK_SIZE, 8, 0); + + if (ha->fw_ddb_dma_pool == NULL) { + ql4_printk(KERN_WARNING, ha, + "%s: fw_ddb_dma_pool allocation failed..\n", + __func__); + goto mem_alloc_error_exit; + } + return QLA_SUCCESS; mem_alloc_error_exit: @@ -1800,6 +2064,60 @@ void qla4_8xxx_watchdog(struct scsi_qla_host *ha) } } +void qla4xxx_check_relogin_flash_ddb(struct iscsi_cls_session *cls_sess) +{ + struct iscsi_session *sess; + struct ddb_entry *ddb_entry; + struct scsi_qla_host *ha; + + sess = cls_sess->dd_data; + ddb_entry = sess->dd_data; + ha = ddb_entry->ha; + + if (!(ddb_entry->ddb_type == FLASH_DDB)) + return; + + if (adapter_up(ha) && !test_bit(DF_RELOGIN, &ddb_entry->flags) && + !iscsi_is_session_online(cls_sess)) { + if (atomic_read(&ddb_entry->retry_relogin_timer) != + INVALID_ENTRY) { + if (atomic_read(&ddb_entry->retry_relogin_timer) == + 0) { + atomic_set(&ddb_entry->retry_relogin_timer, + INVALID_ENTRY); + set_bit(DPC_RELOGIN_DEVICE, &ha->dpc_flags); + set_bit(DF_RELOGIN, &ddb_entry->flags); + DEBUG2(ql4_printk(KERN_INFO, ha, + "%s: index [%d] login device\n", + __func__, ddb_entry->fw_ddb_index)); + } else + atomic_dec(&ddb_entry->retry_relogin_timer); + } + } + + /* Wait for relogin to timeout */ + if (atomic_read(&ddb_entry->relogin_timer) && + (atomic_dec_and_test(&ddb_entry->relogin_timer) != 0)) { + /* + * If the relogin times out and the device is + * still NOT ONLINE then try and relogin again. + */ + if (!iscsi_is_session_online(cls_sess)) { + /* Reset retry relogin timer */ + atomic_inc(&ddb_entry->relogin_retry_count); + DEBUG2(ql4_printk(KERN_INFO, ha, + "%s: index[%d] relogin timed out-retrying" + " relogin (%d), retry (%d)\n", __func__, + ddb_entry->fw_ddb_index, + atomic_read(&ddb_entry->relogin_retry_count), + ddb_entry->default_time2wait + 4)); + set_bit(DPC_RELOGIN_DEVICE, &ha->dpc_flags); + atomic_set(&ddb_entry->retry_relogin_timer, + ddb_entry->default_time2wait + 4); + } + } +} + /** * qla4xxx_timer - checks every second for work to do. * @ha: Pointer to host adapter structure. @@ -1809,6 +2127,8 @@ static void qla4xxx_timer(struct scsi_qla_host *ha) int start_dpc = 0; uint16_t w; + iscsi_host_for_each_session(ha->host, qla4xxx_check_relogin_flash_ddb); + /* If we are in the middle of AER/EEH processing * skip any processing and reschedule the timer */ @@ -2078,7 +2398,12 @@ static void qla4xxx_fail_session(struct iscsi_cls_session *cls_session) sess = cls_session->dd_data; ddb_entry = sess->dd_data; ddb_entry->fw_ddb_device_state = DDB_DS_SESSION_FAILED; - iscsi_session_failure(cls_session->dd_data, ISCSI_ERR_CONN_FAILED); + + if (ddb_entry->ddb_type == FLASH_DDB) + iscsi_block_session(ddb_entry->sess); + else + iscsi_session_failure(cls_session->dd_data, + ISCSI_ERR_CONN_FAILED); } /** @@ -2163,7 +2488,7 @@ recover_ha_init_adapter: /* NOTE: AF_ONLINE flag set upon successful completion of * qla4xxx_initialize_adapter */ - status = qla4xxx_initialize_adapter(ha); + status = qla4xxx_initialize_adapter(ha, RESET_ADAPTER); } /* Retry failed adapter initialization, if necessary @@ -2245,17 +2570,108 @@ static void qla4xxx_relogin_devices(struct iscsi_cls_session *cls_session) iscsi_unblock_session(ddb_entry->sess); } else { /* Trigger relogin */ - iscsi_session_failure(cls_session->dd_data, - ISCSI_ERR_CONN_FAILED); + if (ddb_entry->ddb_type == FLASH_DDB) { + if (!test_bit(DF_RELOGIN, &ddb_entry->flags)) + qla4xxx_arm_relogin_timer(ddb_entry); + } else + iscsi_session_failure(cls_session->dd_data, + ISCSI_ERR_CONN_FAILED); } } } +int qla4xxx_unblock_flash_ddb(struct iscsi_cls_session *cls_session) +{ + struct iscsi_session *sess; + struct ddb_entry *ddb_entry; + struct scsi_qla_host *ha; + + sess = cls_session->dd_data; + ddb_entry = sess->dd_data; + ha = ddb_entry->ha; + ql4_printk(KERN_INFO, ha, "scsi%ld: %s: ddb[%d]" + " unblock session\n", ha->host_no, __func__, + ddb_entry->fw_ddb_index); + + iscsi_unblock_session(ddb_entry->sess); + + /* Start scan target */ + if (test_bit(AF_ONLINE, &ha->flags)) { + ql4_printk(KERN_INFO, ha, "scsi%ld: %s: ddb[%d]" + " start scan\n", ha->host_no, __func__, + ddb_entry->fw_ddb_index); + scsi_queue_work(ha->host, &ddb_entry->sess->scan_work); + } + return QLA_SUCCESS; +} + +int qla4xxx_unblock_ddb(struct iscsi_cls_session *cls_session) +{ + struct iscsi_session *sess; + struct ddb_entry *ddb_entry; + struct scsi_qla_host *ha; + + sess = cls_session->dd_data; + ddb_entry = sess->dd_data; + ha = ddb_entry->ha; + ql4_printk(KERN_INFO, ha, "scsi%ld: %s: ddb[%d]" + " unblock user space session\n", ha->host_no, __func__, + ddb_entry->fw_ddb_index); + iscsi_conn_start(ddb_entry->conn); + iscsi_conn_login_event(ddb_entry->conn, + ISCSI_CONN_STATE_LOGGED_IN); + + return QLA_SUCCESS; +} + static void qla4xxx_relogin_all_devices(struct scsi_qla_host *ha) { iscsi_host_for_each_session(ha->host, qla4xxx_relogin_devices); } +static void qla4xxx_relogin_flash_ddb(struct iscsi_cls_session *cls_sess) +{ + uint16_t relogin_timer; + struct iscsi_session *sess; + struct ddb_entry *ddb_entry; + struct scsi_qla_host *ha; + + sess = cls_sess->dd_data; + ddb_entry = sess->dd_data; + ha = ddb_entry->ha; + + relogin_timer = max(ddb_entry->default_relogin_timeout, + (uint16_t)RELOGIN_TOV); + atomic_set(&ddb_entry->relogin_timer, relogin_timer); + + DEBUG2(ql4_printk(KERN_INFO, ha, + "scsi%ld: Relogin index [%d]. TOV=%d\n", ha->host_no, + ddb_entry->fw_ddb_index, relogin_timer)); + + qla4xxx_login_flash_ddb(cls_sess); +} + +static void qla4xxx_dpc_relogin(struct iscsi_cls_session *cls_sess) +{ + struct iscsi_session *sess; + struct ddb_entry *ddb_entry; + struct scsi_qla_host *ha; + + sess = cls_sess->dd_data; + ddb_entry = sess->dd_data; + ha = ddb_entry->ha; + + if (!(ddb_entry->ddb_type == FLASH_DDB)) + return; + + if (test_and_clear_bit(DF_RELOGIN, &ddb_entry->flags) && + !iscsi_is_session_online(cls_sess)) { + DEBUG2(ql4_printk(KERN_INFO, ha, + "relogin issued\n")); + qla4xxx_relogin_flash_ddb(cls_sess); + } +} + void qla4xxx_wake_dpc(struct scsi_qla_host *ha) { if (ha->dpc_thread) @@ -2356,6 +2772,12 @@ dpc_post_reset_ha: if (test_and_clear_bit(DPC_GET_DHCP_IP_ADDR, &ha->dpc_flags)) qla4xxx_get_dhcp_ip_address(ha); + /* ---- relogin device? --- */ + if (adapter_up(ha) && + test_and_clear_bit(DPC_RELOGIN_DEVICE, &ha->dpc_flags)) { + iscsi_host_for_each_session(ha->host, qla4xxx_dpc_relogin); + } + /* ---- link change? --- */ if (test_and_clear_bit(DPC_LINK_CHANGED, &ha->dpc_flags)) { if (!test_bit(AF_LINK_UP, &ha->flags)) { @@ -2368,8 +2790,12 @@ dpc_post_reset_ha: * fatal error recovery. Therefore, the driver must * manually relogin to devices when recovering from * connection failures, logouts, expired KATO, etc. */ - - qla4xxx_relogin_all_devices(ha); + if (test_and_clear_bit(AF_BUILD_DDB_LIST, &ha->flags)) { + qla4xxx_build_ddb_list(ha, ha->is_reset); + iscsi_host_for_each_session(ha->host, + qla4xxx_login_flash_ddb); + } else + qla4xxx_relogin_all_devices(ha); } } } @@ -2867,6 +3293,9 @@ static int get_fw_boot_info(struct scsi_qla_host *ha, uint16_t ddb_index[]) " target ID %d\n", __func__, ddb_index[0], ddb_index[1])); + ha->pri_ddb_idx = ddb_index[0]; + ha->sec_ddb_idx = ddb_index[1]; + exit_boot_info_free: dma_free_coherent(&ha->pdev->dev, size, buf, buf_dma); exit_boot_info: @@ -3034,6 +3463,9 @@ static int qla4xxx_get_boot_info(struct scsi_qla_host *ha) return ret; } + if (ql4xdisablesysfsboot) + return QLA_SUCCESS; + if (ddb_index[0] == 0xffff) goto sec_target; @@ -3066,7 +3498,15 @@ static int qla4xxx_setup_boot_info(struct scsi_qla_host *ha) struct iscsi_boot_kobj *boot_kobj; if (qla4xxx_get_boot_info(ha) != QLA_SUCCESS) - return 0; + return QLA_ERROR; + + if (ql4xdisablesysfsboot) { + ql4_printk(KERN_INFO, ha, + "%s: syfsboot disabled - driver will trigger login" + "and publish session for discovery .\n", __func__); + return QLA_SUCCESS; + } + ha->boot_kset = iscsi_boot_create_host_kset(ha->host->host_no); if (!ha->boot_kset) @@ -3108,7 +3548,7 @@ static int qla4xxx_setup_boot_info(struct scsi_qla_host *ha) if (!boot_kobj) goto put_host; - return 0; + return QLA_SUCCESS; put_host: scsi_host_put(ha->host); @@ -3174,9 +3614,507 @@ static void qla4xxx_create_chap_list(struct scsi_qla_host *ha) exit_chap_list: dma_free_coherent(&ha->pdev->dev, chap_size, chap_flash_data, chap_dma); - return; } +static void qla4xxx_get_param_ddb(struct ddb_entry *ddb_entry, + struct ql4_tuple_ddb *tddb) +{ + struct scsi_qla_host *ha; + struct iscsi_cls_session *cls_sess; + struct iscsi_cls_conn *cls_conn; + struct iscsi_session *sess; + struct iscsi_conn *conn; + + DEBUG2(printk(KERN_INFO "Func: %s\n", __func__)); + ha = ddb_entry->ha; + cls_sess = ddb_entry->sess; + sess = cls_sess->dd_data; + cls_conn = ddb_entry->conn; + conn = cls_conn->dd_data; + + tddb->tpgt = sess->tpgt; + tddb->port = conn->persistent_port; + strncpy(tddb->iscsi_name, sess->targetname, ISCSI_NAME_SIZE); + strncpy(tddb->ip_addr, conn->persistent_address, DDB_IPADDR_LEN); +} + +static void qla4xxx_convert_param_ddb(struct dev_db_entry *fw_ddb_entry, + struct ql4_tuple_ddb *tddb) +{ + uint16_t options = 0; + + tddb->tpgt = le32_to_cpu(fw_ddb_entry->tgt_portal_grp); + memcpy(&tddb->iscsi_name[0], &fw_ddb_entry->iscsi_name[0], + min(sizeof(tddb->iscsi_name), sizeof(fw_ddb_entry->iscsi_name))); + + options = le16_to_cpu(fw_ddb_entry->options); + if (options & DDB_OPT_IPV6_DEVICE) + sprintf(tddb->ip_addr, "%pI6", fw_ddb_entry->ip_addr); + else + sprintf(tddb->ip_addr, "%pI4", fw_ddb_entry->ip_addr); + + tddb->port = le16_to_cpu(fw_ddb_entry->port); +} + +static int qla4xxx_compare_tuple_ddb(struct scsi_qla_host *ha, + struct ql4_tuple_ddb *old_tddb, + struct ql4_tuple_ddb *new_tddb) +{ + if (strcmp(old_tddb->iscsi_name, new_tddb->iscsi_name)) + return QLA_ERROR; + + if (strcmp(old_tddb->ip_addr, new_tddb->ip_addr)) + return QLA_ERROR; + + if (old_tddb->port != new_tddb->port) + return QLA_ERROR; + + DEBUG2(ql4_printk(KERN_INFO, ha, + "Match Found, fw[%d,%d,%s,%s], [%d,%d,%s,%s]", + old_tddb->port, old_tddb->tpgt, old_tddb->ip_addr, + old_tddb->iscsi_name, new_tddb->port, new_tddb->tpgt, + new_tddb->ip_addr, new_tddb->iscsi_name)); + + return QLA_SUCCESS; +} + +static int qla4xxx_is_session_exists(struct scsi_qla_host *ha, + struct dev_db_entry *fw_ddb_entry) +{ + struct ddb_entry *ddb_entry; + struct ql4_tuple_ddb *fw_tddb = NULL; + struct ql4_tuple_ddb *tmp_tddb = NULL; + int idx; + int ret = QLA_ERROR; + + fw_tddb = vzalloc(sizeof(*fw_tddb)); + if (!fw_tddb) { + DEBUG2(ql4_printk(KERN_WARNING, ha, + "Memory Allocation failed.\n")); + ret = QLA_SUCCESS; + goto exit_check; + } + + tmp_tddb = vzalloc(sizeof(*tmp_tddb)); + if (!tmp_tddb) { + DEBUG2(ql4_printk(KERN_WARNING, ha, + "Memory Allocation failed.\n")); + ret = QLA_SUCCESS; + goto exit_check; + } + + qla4xxx_convert_param_ddb(fw_ddb_entry, fw_tddb); + + for (idx = 0; idx < MAX_DDB_ENTRIES; idx++) { + ddb_entry = qla4xxx_lookup_ddb_by_fw_index(ha, idx); + if (ddb_entry == NULL) + continue; + + qla4xxx_get_param_ddb(ddb_entry, tmp_tddb); + if (!qla4xxx_compare_tuple_ddb(ha, fw_tddb, tmp_tddb)) { + ret = QLA_SUCCESS; /* found */ + goto exit_check; + } + } + +exit_check: + if (fw_tddb) + vfree(fw_tddb); + if (tmp_tddb) + vfree(tmp_tddb); + return ret; +} + +static int qla4xxx_is_flash_ddb_exists(struct scsi_qla_host *ha, + struct list_head *list_nt, + struct dev_db_entry *fw_ddb_entry) +{ + struct qla_ddb_index *nt_ddb_idx, *nt_ddb_idx_tmp; + struct ql4_tuple_ddb *fw_tddb = NULL; + struct ql4_tuple_ddb *tmp_tddb = NULL; + int ret = QLA_ERROR; + + fw_tddb = vzalloc(sizeof(*fw_tddb)); + if (!fw_tddb) { + DEBUG2(ql4_printk(KERN_WARNING, ha, + "Memory Allocation failed.\n")); + ret = QLA_SUCCESS; + goto exit_check; + } + + tmp_tddb = vzalloc(sizeof(*tmp_tddb)); + if (!tmp_tddb) { + DEBUG2(ql4_printk(KERN_WARNING, ha, + "Memory Allocation failed.\n")); + ret = QLA_SUCCESS; + goto exit_check; + } + + qla4xxx_convert_param_ddb(fw_ddb_entry, fw_tddb); + + list_for_each_entry_safe(nt_ddb_idx, nt_ddb_idx_tmp, list_nt, list) { + qla4xxx_convert_param_ddb(&nt_ddb_idx->fw_ddb, tmp_tddb); + if (!qla4xxx_compare_tuple_ddb(ha, fw_tddb, tmp_tddb)) { + ret = QLA_SUCCESS; /* found */ + goto exit_check; + } + } + +exit_check: + if (fw_tddb) + vfree(fw_tddb); + if (tmp_tddb) + vfree(tmp_tddb); + return ret; +} + +static void qla4xxx_free_nt_list(struct list_head *list_nt) +{ + struct qla_ddb_index *nt_ddb_idx, *nt_ddb_idx_tmp; + + /* Free up the normaltargets list */ + list_for_each_entry_safe(nt_ddb_idx, nt_ddb_idx_tmp, list_nt, list) { + list_del_init(&nt_ddb_idx->list); + vfree(nt_ddb_idx); + } + +} + +static struct iscsi_endpoint *qla4xxx_get_ep_fwdb(struct scsi_qla_host *ha, + struct dev_db_entry *fw_ddb_entry) +{ + struct iscsi_endpoint *ep; + struct sockaddr_in *addr; + struct sockaddr_in6 *addr6; + struct sockaddr *dst_addr; + char *ip; + + /* TODO: need to destroy on unload iscsi_endpoint*/ + dst_addr = vmalloc(sizeof(*dst_addr)); + if (!dst_addr) + return NULL; + + if (fw_ddb_entry->options & DDB_OPT_IPV6_DEVICE) { + dst_addr->sa_family = AF_INET6; + addr6 = (struct sockaddr_in6 *)dst_addr; + ip = (char *)&addr6->sin6_addr; + memcpy(ip, fw_ddb_entry->ip_addr, IPv6_ADDR_LEN); + addr6->sin6_port = htons(le16_to_cpu(fw_ddb_entry->port)); + + } else { + dst_addr->sa_family = AF_INET; + addr = (struct sockaddr_in *)dst_addr; + ip = (char *)&addr->sin_addr; + memcpy(ip, fw_ddb_entry->ip_addr, IP_ADDR_LEN); + addr->sin_port = htons(le16_to_cpu(fw_ddb_entry->port)); + } + + ep = qla4xxx_ep_connect(ha->host, dst_addr, 0); + vfree(dst_addr); + return ep; +} + +static int qla4xxx_verify_boot_idx(struct scsi_qla_host *ha, uint16_t idx) +{ + if (ql4xdisablesysfsboot) + return QLA_SUCCESS; + if (idx == ha->pri_ddb_idx || idx == ha->sec_ddb_idx) + return QLA_ERROR; + return QLA_SUCCESS; +} + +static void qla4xxx_setup_flash_ddb_entry(struct scsi_qla_host *ha, + struct ddb_entry *ddb_entry) +{ + ddb_entry->ddb_type = FLASH_DDB; + ddb_entry->fw_ddb_index = INVALID_ENTRY; + ddb_entry->fw_ddb_device_state = DDB_DS_NO_CONNECTION_ACTIVE; + ddb_entry->ha = ha; + ddb_entry->unblock_sess = qla4xxx_unblock_flash_ddb; + ddb_entry->ddb_change = qla4xxx_flash_ddb_change; + + atomic_set(&ddb_entry->retry_relogin_timer, INVALID_ENTRY); + atomic_set(&ddb_entry->relogin_timer, 0); + atomic_set(&ddb_entry->relogin_retry_count, 0); + + ddb_entry->default_relogin_timeout = + le16_to_cpu(ddb_entry->fw_ddb_entry.def_timeout); + ddb_entry->default_time2wait = + le16_to_cpu(ddb_entry->fw_ddb_entry.iscsi_def_time2wait); +} + +static void qla4xxx_wait_for_ip_configuration(struct scsi_qla_host *ha) +{ + uint32_t idx = 0; + uint32_t ip_idx[IP_ADDR_COUNT] = {0, 1, 2, 3}; /* 4 IP interfaces */ + uint32_t sts[MBOX_REG_COUNT]; + uint32_t ip_state; + unsigned long wtime; + int ret; + + wtime = jiffies + (HZ * IP_CONFIG_TOV); + do { + for (idx = 0; idx < IP_ADDR_COUNT; idx++) { + if (ip_idx[idx] == -1) + continue; + + ret = qla4xxx_get_ip_state(ha, 0, ip_idx[idx], sts); + + if (ret == QLA_ERROR) { + ip_idx[idx] = -1; + continue; + } + + ip_state = (sts[1] & IP_STATE_MASK) >> IP_STATE_SHIFT; + + DEBUG2(ql4_printk(KERN_INFO, ha, + "Waiting for IP state for idx = %d, state = 0x%x\n", + ip_idx[idx], ip_state)); + if (ip_state == IP_ADDRSTATE_UNCONFIGURED || + ip_state == IP_ADDRSTATE_INVALID || + ip_state == IP_ADDRSTATE_PREFERRED || + ip_state == IP_ADDRSTATE_DEPRICATED || + ip_state == IP_ADDRSTATE_DISABLING) + ip_idx[idx] = -1; + + } + + /* Break if all IP states checked */ + if ((ip_idx[0] == -1) && + (ip_idx[1] == -1) && + (ip_idx[2] == -1) && + (ip_idx[3] == -1)) + break; + schedule_timeout_uninterruptible(HZ); + } while (time_after(wtime, jiffies)); +} + +void qla4xxx_build_ddb_list(struct scsi_qla_host *ha, int is_reset) +{ + int max_ddbs; + int ret; + uint32_t idx = 0, next_idx = 0; + uint32_t state = 0, conn_err = 0; + uint16_t conn_id; + struct dev_db_entry *fw_ddb_entry; + struct ddb_entry *ddb_entry = NULL; + dma_addr_t fw_ddb_dma; + struct iscsi_cls_session *cls_sess; + struct iscsi_session *sess; + struct iscsi_cls_conn *cls_conn; + struct iscsi_endpoint *ep; + uint16_t cmds_max = 32, tmo = 0; + uint32_t initial_cmdsn = 0; + struct list_head list_st, list_nt; /* List of sendtargets */ + struct qla_ddb_index *st_ddb_idx, *st_ddb_idx_tmp; + int fw_idx_size; + unsigned long wtime; + struct qla_ddb_index *nt_ddb_idx; + + if (!test_bit(AF_LINK_UP, &ha->flags)) { + set_bit(AF_BUILD_DDB_LIST, &ha->flags); + ha->is_reset = is_reset; + return; + } + max_ddbs = is_qla40XX(ha) ? MAX_DEV_DB_ENTRIES_40XX : + MAX_DEV_DB_ENTRIES; + + fw_ddb_entry = dma_pool_alloc(ha->fw_ddb_dma_pool, GFP_KERNEL, + &fw_ddb_dma); + if (fw_ddb_entry == NULL) { + DEBUG2(ql4_printk(KERN_ERR, ha, "Out of memory\n")); + goto exit_ddb_list; + } + + INIT_LIST_HEAD(&list_st); + INIT_LIST_HEAD(&list_nt); + fw_idx_size = sizeof(struct qla_ddb_index); + + for (idx = 0; idx < max_ddbs; idx = next_idx) { + ret = qla4xxx_get_fwddb_entry(ha, idx, fw_ddb_entry, + fw_ddb_dma, NULL, + &next_idx, &state, &conn_err, + NULL, &conn_id); + if (ret == QLA_ERROR) + break; + + if (qla4xxx_verify_boot_idx(ha, idx) != QLA_SUCCESS) + goto continue_next_st; + + /* Check if ST, add to the list_st */ + if (strlen((char *) fw_ddb_entry->iscsi_name) != 0) + goto continue_next_st; + + st_ddb_idx = vzalloc(fw_idx_size); + if (!st_ddb_idx) + break; + + st_ddb_idx->fw_ddb_idx = idx; + + list_add_tail(&st_ddb_idx->list, &list_st); +continue_next_st: + if (next_idx == 0) + break; + } + + /* Before issuing conn open mbox, ensure all IPs states are configured + * Note, conn open fails if IPs are not configured + */ + qla4xxx_wait_for_ip_configuration(ha); + + /* Go thru the STs and fire the sendtargets by issuing conn open mbx */ + list_for_each_entry_safe(st_ddb_idx, st_ddb_idx_tmp, &list_st, list) { + qla4xxx_conn_open(ha, st_ddb_idx->fw_ddb_idx); + } + + /* Wait to ensure all sendtargets are done for min 12 sec wait */ + tmo = ((ha->def_timeout < LOGIN_TOV) ? LOGIN_TOV : ha->def_timeout); + DEBUG2(ql4_printk(KERN_INFO, ha, + "Default time to wait for build ddb %d\n", tmo)); + + wtime = jiffies + (HZ * tmo); + do { + list_for_each_entry_safe(st_ddb_idx, st_ddb_idx_tmp, &list_st, + list) { + ret = qla4xxx_get_fwddb_entry(ha, + st_ddb_idx->fw_ddb_idx, + NULL, 0, NULL, &next_idx, + &state, &conn_err, NULL, + NULL); + if (ret == QLA_ERROR) + continue; + + if (state == DDB_DS_NO_CONNECTION_ACTIVE || + state == DDB_DS_SESSION_FAILED) { + list_del_init(&st_ddb_idx->list); + vfree(st_ddb_idx); + } + } + schedule_timeout_uninterruptible(HZ / 10); + } while (time_after(wtime, jiffies)); + + /* Free up the sendtargets list */ + list_for_each_entry_safe(st_ddb_idx, st_ddb_idx_tmp, &list_st, list) { + list_del_init(&st_ddb_idx->list); + vfree(st_ddb_idx); + } + + for (idx = 0; idx < max_ddbs; idx = next_idx) { + ret = qla4xxx_get_fwddb_entry(ha, idx, fw_ddb_entry, + fw_ddb_dma, NULL, + &next_idx, &state, &conn_err, + NULL, &conn_id); + if (ret == QLA_ERROR) + break; + + if (qla4xxx_verify_boot_idx(ha, idx) != QLA_SUCCESS) + goto continue_next_nt; + + /* Check if NT, then add to list it */ + if (strlen((char *) fw_ddb_entry->iscsi_name) == 0) + goto continue_next_nt; + + if (state == DDB_DS_NO_CONNECTION_ACTIVE || + state == DDB_DS_SESSION_FAILED) { + DEBUG2(ql4_printk(KERN_INFO, ha, + "Adding DDB to session = 0x%x\n", + idx)); + if (is_reset == INIT_ADAPTER) { + nt_ddb_idx = vmalloc(fw_idx_size); + if (!nt_ddb_idx) + break; + + nt_ddb_idx->fw_ddb_idx = idx; + + memcpy(&nt_ddb_idx->fw_ddb, fw_ddb_entry, + sizeof(struct dev_db_entry)); + + if (qla4xxx_is_flash_ddb_exists(ha, &list_nt, + fw_ddb_entry) == QLA_SUCCESS) { + vfree(nt_ddb_idx); + goto continue_next_nt; + } + list_add_tail(&nt_ddb_idx->list, &list_nt); + } else if (is_reset == RESET_ADAPTER) { + if (qla4xxx_is_session_exists(ha, + fw_ddb_entry) == QLA_SUCCESS) + goto continue_next_nt; + } + + /* Create session object, with INVALID_ENTRY, + * the targer_id would get set when we issue the login + */ + cls_sess = iscsi_session_setup(&qla4xxx_iscsi_transport, + ha->host, cmds_max, + sizeof(struct ddb_entry), + sizeof(struct ql4_task_data), + initial_cmdsn, INVALID_ENTRY); + if (!cls_sess) + goto exit_ddb_list; + + /* + * iscsi_session_setup increments the driver reference + * count which wouldn't let the driver to be unloaded. + * so calling module_put function to decrement the + * reference count. + **/ + module_put(qla4xxx_iscsi_transport.owner); + sess = cls_sess->dd_data; + ddb_entry = sess->dd_data; + ddb_entry->sess = cls_sess; + + cls_sess->recovery_tmo = ql4xsess_recovery_tmo; + memcpy(&ddb_entry->fw_ddb_entry, fw_ddb_entry, + sizeof(struct dev_db_entry)); + + qla4xxx_setup_flash_ddb_entry(ha, ddb_entry); + + cls_conn = iscsi_conn_setup(cls_sess, + sizeof(struct qla_conn), + conn_id); + if (!cls_conn) + goto exit_ddb_list; + + ddb_entry->conn = cls_conn; + + /* Setup ep, for displaying attributes in sysfs */ + ep = qla4xxx_get_ep_fwdb(ha, fw_ddb_entry); + if (ep) { + ep->conn = cls_conn; + cls_conn->ep = ep; + } else { + DEBUG2(ql4_printk(KERN_ERR, ha, + "Unable to get ep\n")); + } + + /* Update sess/conn params */ + qla4xxx_copy_fwddb_param(ha, fw_ddb_entry, cls_sess, + cls_conn); + + if (is_reset == RESET_ADAPTER) { + iscsi_block_session(cls_sess); + /* Use the relogin path to discover new devices + * by short-circuting the logic of setting + * timer to relogin - instead set the flags + * to initiate login right away. + */ + set_bit(DPC_RELOGIN_DEVICE, &ha->dpc_flags); + set_bit(DF_RELOGIN, &ddb_entry->flags); + } + } +continue_next_nt: + if (next_idx == 0) + break; + } +exit_ddb_list: + qla4xxx_free_nt_list(&list_nt); + if (fw_ddb_entry) + dma_pool_free(ha->fw_ddb_dma_pool, fw_ddb_entry, fw_ddb_dma); + + qla4xxx_free_ddb_index(ha); +} + + /** * qla4xxx_probe_adapter - callback function to probe HBA * @pdev: pointer to pci_dev structure @@ -3298,7 +4236,7 @@ static int __devinit qla4xxx_probe_adapter(struct pci_dev *pdev, * firmware * NOTE: interrupts enabled upon successful completion */ - status = qla4xxx_initialize_adapter(ha); + status = qla4xxx_initialize_adapter(ha, INIT_ADAPTER); while ((!test_bit(AF_ONLINE, &ha->flags)) && init_retry_count++ < MAX_INIT_RETRIES) { @@ -3319,7 +4257,7 @@ static int __devinit qla4xxx_probe_adapter(struct pci_dev *pdev, if (ha->isp_ops->reset_chip(ha) == QLA_ERROR) continue; - status = qla4xxx_initialize_adapter(ha); + status = qla4xxx_initialize_adapter(ha, INIT_ADAPTER); } if (!test_bit(AF_ONLINE, &ha->flags)) { @@ -3386,12 +4324,16 @@ static int __devinit qla4xxx_probe_adapter(struct pci_dev *pdev, ha->host_no, ha->firmware_version[0], ha->firmware_version[1], ha->patch_number, ha->build_number); - qla4xxx_create_chap_list(ha); - if (qla4xxx_setup_boot_info(ha)) ql4_printk(KERN_ERR, ha, "%s:ISCSI boot info setup failed\n", __func__); + /* Perform the build ddb list and login to each */ + qla4xxx_build_ddb_list(ha, INIT_ADAPTER); + iscsi_host_for_each_session(ha->host, qla4xxx_login_flash_ddb); + + qla4xxx_create_chap_list(ha); + qla4xxx_create_ifaces(ha); return 0; @@ -3449,6 +4391,38 @@ static void qla4xxx_prevent_other_port_reinit(struct scsi_qla_host *ha) } } +static void qla4xxx_destroy_fw_ddb_session(struct scsi_qla_host *ha) +{ + struct ddb_entry *ddb_entry; + int options; + int idx; + + for (idx = 0; idx < MAX_DDB_ENTRIES; idx++) { + + ddb_entry = qla4xxx_lookup_ddb_by_fw_index(ha, idx); + if ((ddb_entry != NULL) && + (ddb_entry->ddb_type == FLASH_DDB)) { + + options = LOGOUT_OPTION_CLOSE_SESSION; + if (qla4xxx_session_logout_ddb(ha, ddb_entry, options) + == QLA_ERROR) + ql4_printk(KERN_ERR, ha, "%s: Logout failed\n", + __func__); + + qla4xxx_clear_ddb_entry(ha, ddb_entry->fw_ddb_index); + /* + * we have decremented the reference count of the driver + * when we setup the session to have the driver unload + * to be seamless without actually destroying the + * session + **/ + try_module_get(qla4xxx_iscsi_transport.owner); + iscsi_destroy_endpoint(ddb_entry->conn->ep); + qla4xxx_free_ddb(ha, ddb_entry); + iscsi_session_teardown(ddb_entry->sess); + } + } +} /** * qla4xxx_remove_adapter - calback function to remove adapter. * @pci_dev: PCI device pointer @@ -3465,9 +4439,11 @@ static void __devexit qla4xxx_remove_adapter(struct pci_dev *pdev) /* destroy iface from sysfs */ qla4xxx_destroy_ifaces(ha); - if (ha->boot_kset) + if ((!ql4xdisablesysfsboot) && ha->boot_kset) iscsi_boot_destroy_kset(ha->boot_kset); + qla4xxx_destroy_fw_ddb_session(ha); + scsi_remove_host(ha->host); qla4xxx_free_adapter(ha); @@ -4115,7 +5091,7 @@ static uint32_t qla4_8xxx_error_recovery(struct scsi_qla_host *ha) qla4_8xxx_idc_unlock(ha); clear_bit(AF_FW_RECOVERY, &ha->flags); - rval = qla4xxx_initialize_adapter(ha); + rval = qla4xxx_initialize_adapter(ha, RESET_ADAPTER); qla4_8xxx_idc_lock(ha); if (rval != QLA_SUCCESS) { @@ -4151,7 +5127,7 @@ static uint32_t qla4_8xxx_error_recovery(struct scsi_qla_host *ha) if ((qla4_8xxx_rd_32(ha, QLA82XX_CRB_DEV_STATE) == QLA82XX_DEV_READY)) { clear_bit(AF_FW_RECOVERY, &ha->flags); - rval = qla4xxx_initialize_adapter(ha); + rval = qla4xxx_initialize_adapter(ha, RESET_ADAPTER); if (rval == QLA_SUCCESS) { ret = qla4xxx_request_irqs(ha); if (ret) { diff --git a/drivers/scsi/qla4xxx/ql4_version.h b/drivers/scsi/qla4xxx/ql4_version.h index c15347d..5254e57 100644 --- a/drivers/scsi/qla4xxx/ql4_version.h +++ b/drivers/scsi/qla4xxx/ql4_version.h @@ -5,4 +5,4 @@ * See LICENSE.qla4xxx for copyright and licensing details. */ -#define QLA4XXX_DRIVER_VERSION "5.02.00-k8" +#define QLA4XXX_DRIVER_VERSION "5.02.00-k9" diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 717ebc9..600d823 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -264,7 +264,7 @@ static int __devinit dwc3_core_init(struct dwc3 *dwc) ret = -ENODEV; goto err0; } - dwc->revision = reg & DWC3_GSNPSREV_MASK; + dwc->revision = reg; dwc3_core_soft_reset(dwc); diff --git a/drivers/usb/gadget/epautoconf.c b/drivers/usb/gadget/epautoconf.c index 596a0b4..4dff83d 100644 --- a/drivers/usb/gadget/epautoconf.c +++ b/drivers/usb/gadget/epautoconf.c @@ -130,9 +130,6 @@ ep_matches ( num_req_streams = ep_comp->bmAttributes & 0x1f; if (num_req_streams > ep->max_streams) return 0; - /* Update the ep_comp descriptor if needed */ - if (num_req_streams != ep->max_streams) - ep_comp->bmAttributes = ep->max_streams; } } diff --git a/drivers/usb/host/isp1760-if.c b/drivers/usb/host/isp1760-if.c index a7dc1e1..2ac4ac2 100644 --- a/drivers/usb/host/isp1760-if.c +++ b/drivers/usb/host/isp1760-if.c @@ -18,7 +18,7 @@ #include "isp1760-hcd.h" -#ifdef CONFIG_OF +#if defined(CONFIG_OF) && defined(CONFIG_OF_IRQ) #include <linux/slab.h> #include <linux/of.h> #include <linux/of_platform.h> @@ -31,7 +31,7 @@ #include <linux/pci.h> #endif -#ifdef CONFIG_OF +#if defined(CONFIG_OF) && defined(CONFIG_OF_IRQ) struct isp1760 { struct usb_hcd *hcd; int rst_gpio; @@ -437,7 +437,7 @@ static int __init isp1760_init(void) ret = platform_driver_register(&isp1760_plat_driver); if (!ret) any_ret = 0; -#ifdef CONFIG_OF +#if defined(CONFIG_OF) && defined(CONFIG_OF_IRQ) ret = platform_driver_register(&isp1760_of_driver); if (!ret) any_ret = 0; @@ -457,7 +457,7 @@ module_init(isp1760_init); static void __exit isp1760_exit(void) { platform_driver_unregister(&isp1760_plat_driver); -#ifdef CONFIG_OF +#if defined(CONFIG_OF) && defined(CONFIG_OF_IRQ) platform_driver_unregister(&isp1760_of_driver); #endif #ifdef CONFIG_PCI diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 60ddba8..79cb0af 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -774,6 +774,10 @@ static void musb_ep_program(struct musb *musb, u8 epnum, if (musb->double_buffer_not_ok) musb_writew(epio, MUSB_TXMAXP, hw_ep->max_packet_sz_tx); + else if (can_bulk_split(musb, qh->type)) + musb_writew(epio, MUSB_TXMAXP, packet_sz + | ((hw_ep->max_packet_sz_tx / + packet_sz) - 1) << 11); else musb_writew(epio, MUSB_TXMAXP, qh->maxpacket | diff --git a/drivers/watchdog/coh901327_wdt.c b/drivers/watchdog/coh901327_wdt.c index 03f449a..5b89f7d 100644 --- a/drivers/watchdog/coh901327_wdt.c +++ b/drivers/watchdog/coh901327_wdt.c @@ -76,8 +76,6 @@ static int irq; static void __iomem *virtbase; static unsigned long coh901327_users; static unsigned long boot_status; -static u16 wdogenablestore; -static u16 irqmaskstore; static struct device *parent; /* @@ -461,6 +459,10 @@ out: } #ifdef CONFIG_PM + +static u16 wdogenablestore; +static u16 irqmaskstore; + static int coh901327_suspend(struct platform_device *pdev, pm_message_t state) { irqmaskstore = readw(virtbase + U300_WDOG_IMR) & 0x0001U; diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c index 3774c9b..8464ea1 100644 --- a/drivers/watchdog/hpwdt.c +++ b/drivers/watchdog/hpwdt.c @@ -231,6 +231,7 @@ static int __devinit cru_detect(unsigned long map_entry, cmn_regs.u1.reax = CRU_BIOS_SIGNATURE_VALUE; + set_memory_x((unsigned long)bios32_entrypoint, (2 * PAGE_SIZE)); asminline_call(&cmn_regs, bios32_entrypoint); if (cmn_regs.u1.ral != 0) { @@ -248,8 +249,10 @@ static int __devinit cru_detect(unsigned long map_entry, if ((physical_bios_base + physical_bios_offset)) { cru_rom_addr = ioremap(cru_physical_address, cru_length); - if (cru_rom_addr) + if (cru_rom_addr) { + set_memory_x((unsigned long)cru_rom_addr, cru_length); retval = 0; + } } printk(KERN_DEBUG "hpwdt: CRU Base Address: 0x%lx\n", diff --git a/drivers/watchdog/iTCO_wdt.c b/drivers/watchdog/iTCO_wdt.c index ba6ad66..99796c5 100644 --- a/drivers/watchdog/iTCO_wdt.c +++ b/drivers/watchdog/iTCO_wdt.c @@ -384,10 +384,10 @@ MODULE_PARM_DESC(nowayout, "Watchdog cannot be stopped once started (default=" __MODULE_STRING(WATCHDOG_NOWAYOUT) ")"); -static int turn_SMI_watchdog_clear_off = 0; +static int turn_SMI_watchdog_clear_off = 1; module_param(turn_SMI_watchdog_clear_off, int, 0); MODULE_PARM_DESC(turn_SMI_watchdog_clear_off, - "Turn off SMI clearing watchdog (default=0)"); + "Turn off SMI clearing watchdog (depends on TCO-version)(default=1)"); /* * Some TCO specific functions @@ -813,7 +813,7 @@ static int __devinit iTCO_wdt_init(struct pci_dev *pdev, ret = -EIO; goto out_unmap; } - if (turn_SMI_watchdog_clear_off) { + if (turn_SMI_watchdog_clear_off >= iTCO_wdt_private.iTCO_version) { /* Bit 13: TCO_EN -> 0 = Disables TCO logic generating an SMI# */ val32 = inl(SMI_EN); val32 &= 0xffffdfff; /* Turn off SMI clearing watchdog */ diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c index cc2cfbe..bfaf9bb 100644 --- a/drivers/watchdog/sp805_wdt.c +++ b/drivers/watchdog/sp805_wdt.c @@ -351,7 +351,7 @@ static int __devexit sp805_wdt_remove(struct amba_device *adev) return 0; } -static struct amba_id sp805_wdt_ids[] __initdata = { +static struct amba_id sp805_wdt_ids[] = { { .id = 0x00141805, .mask = 0x00ffffff, diff --git a/drivers/xen/xenbus/xenbus_xs.c b/drivers/xen/xenbus/xenbus_xs.c index b3b8f2f..ede860f 100644 --- a/drivers/xen/xenbus/xenbus_xs.c +++ b/drivers/xen/xenbus/xenbus_xs.c @@ -621,15 +621,6 @@ static struct xenbus_watch *find_watch(const char *token) return NULL; } -static void xs_reset_watches(void) -{ - int err; - - err = xs_error(xs_single(XBT_NIL, XS_RESET_WATCHES, "", NULL)); - if (err && err != -EEXIST) - printk(KERN_WARNING "xs_reset_watches failed: %d\n", err); -} - /* Register callback to watch this node. */ int register_xenbus_watch(struct xenbus_watch *watch) { @@ -906,9 +897,5 @@ int xs_init(void) if (IS_ERR(task)) return PTR_ERR(task); - /* shutdown watches for kexec boot */ - if (xen_hvm_domain()) - xs_reset_watches(); - return 0; } diff --git a/firmware/README.AddingFirmware b/firmware/README.AddingFirmware index e24cd89..ea78c3a 100644 --- a/firmware/README.AddingFirmware +++ b/firmware/README.AddingFirmware @@ -12,7 +12,7 @@ here. This directory is _NOT_ for adding arbitrary new firmware images. The place to add those is the separate linux-firmware repository: - git://git.kernel.org/pub/scm/linux/kernel/git/dwmw2/linux-firmware.git + git://git.kernel.org/pub/scm/linux/kernel/git/firmware/linux-firmware.git That repository contains all these firmware images which have been extracted from older drivers, as well various new firmware images which @@ -22,6 +22,7 @@ been permitted to redistribute under separate cover. To submit firmware to that repository, please send either a git binary diff or preferably a git pull request to: David Woodhouse <dwmw2@infradead.org> + Ben Hutchings <ben@decadent.org.uk> Your commit should include an update to the WHENCE file clearly identifying the licence under which the firmware is available, and diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index cb97174..0b39458 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -563,8 +563,8 @@ static struct btrfs_worker_thread *find_worker(struct btrfs_workers *workers) struct list_head *fallback; int ret; -again: spin_lock_irqsave(&workers->lock, flags); +again: worker = next_worker(workers); if (!worker) { @@ -579,6 +579,7 @@ again: spin_unlock_irqrestore(&workers->lock, flags); /* we're below the limit, start another worker */ ret = __btrfs_start_workers(workers); + spin_lock_irqsave(&workers->lock, flags); if (ret) goto fallback; goto again; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 0a6b928..fd1a06d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4590,10 +4590,6 @@ static int btrfs_add_nondir(struct btrfs_trans_handle *trans, int err = btrfs_add_link(trans, dir, inode, dentry->d_name.name, dentry->d_name.len, backref, index); - if (!err) { - d_instantiate(dentry, inode); - return 0; - } if (err > 0) err = -EEXIST; return err; @@ -4655,6 +4651,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry, else { init_special_inode(inode, inode->i_mode, rdev); btrfs_update_inode(trans, root, inode); + d_instantiate(dentry, inode); } out_unlock: nr = trans->blocks_used; @@ -4722,6 +4719,7 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry, inode->i_mapping->a_ops = &btrfs_aops; inode->i_mapping->backing_dev_info = &root->fs_info->bdi; BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops; + d_instantiate(dentry, inode); } out_unlock: nr = trans->blocks_used; @@ -4779,6 +4777,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *parent = dentry->d_parent; err = btrfs_update_inode(trans, root, inode); BUG_ON(err); + d_instantiate(dentry, inode); btrfs_log_new_name(trans, inode, NULL, parent); } @@ -7245,6 +7244,8 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry, drop_inode = 1; out_unlock: + if (!err) + d_instantiate(dentry, inode); nr = trans->blocks_used; btrfs_end_transaction_throttle(trans, root); if (drop_inode) { diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 3eeb976..9895400 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1094,42 +1094,19 @@ static int ceph_snapdir_d_revalidate(struct dentry *dentry, /* * Set/clear/test dir complete flag on the dir's dentry. */ -static struct dentry * __d_find_any_alias(struct inode *inode) -{ - struct dentry *alias; - - if (list_empty(&inode->i_dentry)) - return NULL; - alias = list_first_entry(&inode->i_dentry, struct dentry, d_alias); - return alias; -} - void ceph_dir_set_complete(struct inode *inode) { - struct dentry *dentry = __d_find_any_alias(inode); - - if (dentry && ceph_dentry(dentry)) { - dout(" marking %p (%p) complete\n", inode, dentry); - set_bit(CEPH_D_COMPLETE, &ceph_dentry(dentry)->flags); - } + /* not yet implemented */ } void ceph_dir_clear_complete(struct inode *inode) { - struct dentry *dentry = __d_find_any_alias(inode); - - if (dentry && ceph_dentry(dentry)) { - dout(" marking %p (%p) NOT complete\n", inode, dentry); - clear_bit(CEPH_D_COMPLETE, &ceph_dentry(dentry)->flags); - } + /* not yet implemented */ } bool ceph_dir_test_complete(struct inode *inode) { - struct dentry *dentry = __d_find_any_alias(inode); - - if (dentry && ceph_dentry(dentry)) - return test_bit(CEPH_D_COMPLETE, &ceph_dentry(dentry)->flags); + /* not yet implemented */ return false; } diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 8cd4b52..f3670cf 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -282,7 +282,7 @@ static int coalesce_t2(struct smb_hdr *psecond, struct smb_hdr *pTargetSMB) byte_count = be32_to_cpu(pTargetSMB->smb_buf_length); byte_count += total_in_buf2; /* don't allow buffer to overflow */ - if (byte_count > CIFSMaxBufSize) + if (byte_count > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) return -ENOBUFS; pTargetSMB->smb_buf_length = cpu_to_be32(byte_count); @@ -2122,7 +2122,7 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb_vol *volume_info) warned_on_ntlm = true; cERROR(1, "default security mechanism requested. The default " "security mechanism will be upgraded from ntlm to " - "ntlmv2 in kernel release 3.2"); + "ntlmv2 in kernel release 3.3"); } ses->overrideSecFlg = volume_info->secFlg; diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 51352de..a10e428 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -1506,35 +1506,6 @@ static long do_ioctl_trans(int fd, unsigned int cmd, return -ENOIOCTLCMD; } -static void compat_ioctl_error(struct file *filp, unsigned int fd, - unsigned int cmd, unsigned long arg) -{ - char buf[10]; - char *fn = "?"; - char *path; - - /* find the name of the device. */ - path = (char *)__get_free_page(GFP_KERNEL); - if (path) { - fn = d_path(&filp->f_path, path, PAGE_SIZE); - if (IS_ERR(fn)) - fn = "?"; - } - - sprintf(buf,"'%c'", (cmd>>_IOC_TYPESHIFT) & _IOC_TYPEMASK); - if (!isprint(buf[1])) - sprintf(buf, "%02x", buf[1]); - compat_printk("ioctl32(%s:%d): Unknown cmd fd(%d) " - "cmd(%08x){t:%s;sz:%u} arg(%08x) on %s\n", - current->comm, current->pid, - (int)fd, (unsigned int)cmd, buf, - (cmd >> _IOC_SIZESHIFT) & _IOC_SIZEMASK, - (unsigned int)arg, fn); - - if (path) - free_page((unsigned long)path); -} - static int compat_ioctl_check_table(unsigned int xcmd) { int i; @@ -1621,13 +1592,8 @@ asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd, goto found_handler; error = do_ioctl_trans(fd, cmd, arg, filp); - if (error == -ENOIOCTLCMD) { - static int count; - - if (++count <= 50) - compat_ioctl_error(filp, fd, cmd, arg); - error = -EINVAL; - } + if (error == -ENOIOCTLCMD) + error = -ENOTTY; goto out_fput; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index ac86f8b..517f211 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -47,17 +47,6 @@ struct wb_writeback_work { struct completion *done; /* set if the caller waits */ }; -const char *wb_reason_name[] = { - [WB_REASON_BACKGROUND] = "background", - [WB_REASON_TRY_TO_FREE_PAGES] = "try_to_free_pages", - [WB_REASON_SYNC] = "sync", - [WB_REASON_PERIODIC] = "periodic", - [WB_REASON_LAPTOP_TIMER] = "laptop_timer", - [WB_REASON_FREE_MORE_MEM] = "free_more_memory", - [WB_REASON_FS_FREE_SPACE] = "fs_free_space", - [WB_REASON_FORKER_THREAD] = "forker_thread" -}; - /* * Include the creation of the trace points after defining the * wb_writeback_work structure so that the definition remains local to this @@ -42,7 +42,7 @@ static long vfs_ioctl(struct file *filp, unsigned int cmd, error = filp->f_op->unlocked_ioctl(filp, cmd, arg); if (error == -ENOIOCTLCMD) - error = -EINVAL; + error = -ENOTTY; out: return error; } @@ -1205,6 +1205,8 @@ int __break_lease(struct inode *inode, unsigned int mode) int want_write = (mode & O_ACCMODE) != O_RDONLY; new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK); + if (IS_ERR(new_fl)) + return PTR_ERR(new_fl); lock_flocks(); @@ -1221,12 +1223,6 @@ int __break_lease(struct inode *inode, unsigned int mode) if (fl->fl_owner == current->files) i_have_this_lease = 1; - if (IS_ERR(new_fl) && !i_have_this_lease - && ((mode & O_NONBLOCK) == 0)) { - error = PTR_ERR(new_fl); - goto out; - } - break_time = 0; if (lease_break_time > 0) { break_time = jiffies + lease_break_time * HZ; @@ -1284,8 +1280,7 @@ restart: out: unlock_flocks(); - if (!IS_ERR(new_fl)) - locks_free_lock(new_fl); + locks_free_lock(new_fl); return error; } diff --git a/fs/minix/inode.c b/fs/minix/inode.c index 1d9e339..4d46a6a 100644 --- a/fs/minix/inode.c +++ b/fs/minix/inode.c @@ -263,23 +263,6 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) goto out_no_root; } - ret = -ENOMEM; - s->s_root = d_alloc_root(root_inode); - if (!s->s_root) - goto out_iput; - - if (!(s->s_flags & MS_RDONLY)) { - if (sbi->s_version != MINIX_V3) /* s_state is now out from V3 sb */ - ms->s_state &= ~MINIX_VALID_FS; - mark_buffer_dirty(bh); - } - if (!(sbi->s_mount_state & MINIX_VALID_FS)) - printk("MINIX-fs: mounting unchecked file system, " - "running fsck is recommended\n"); - 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. @@ -300,6 +283,23 @@ static int minix_fill_super(struct super_block *s, void *data, int silent) goto out_iput; } + ret = -ENOMEM; + s->s_root = d_alloc_root(root_inode); + if (!s->s_root) + goto out_iput; + + if (!(s->s_flags & MS_RDONLY)) { + if (sbi->s_version != MINIX_V3) /* s_state is now out from V3 sb */ + ms->s_state &= ~MINIX_VALID_FS; + mark_buffer_dirty(bh); + } + if (!(sbi->s_mount_state & MINIX_VALID_FS)) + printk("MINIX-fs: mounting unchecked file system, " + "running fsck is recommended\n"); + else if (sbi->s_mount_state & MINIX_ERROR_FS) + printk("MINIX-fs: mounting file system with errors, " + "running fsck is recommended\n"); + return 0; out_iput: diff --git a/fs/nfs/file.c b/fs/nfs/file.c index eca56d4..606ef0f 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -147,7 +147,7 @@ static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin) * origin == SEEK_END || SEEK_DATA || SEEK_HOLE => we must revalidate * the cached file length */ - if (origin != SEEK_SET || origin != SEEK_CUR) { + if (origin != SEEK_SET && origin != SEEK_CUR) { struct inode *inode = filp->f_mapping->host; int retval = nfs_revalidate_file_size(inode, filp); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index be2bbac..d9f4d78 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -39,6 +39,8 @@ #include <linux/delay.h> #include <linux/errno.h> #include <linux/string.h> +#include <linux/ratelimit.h> +#include <linux/printk.h> #include <linux/slab.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/gss_api.h> @@ -894,6 +896,8 @@ out: static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode) { + if (delegation == NULL) + return 0; if ((delegation->type & fmode) != fmode) return 0; if (test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags)) @@ -1036,8 +1040,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata) } rcu_read_lock(); delegation = rcu_dereference(nfsi->delegation); - if (delegation == NULL || - !can_open_delegated(delegation, fmode)) { + if (!can_open_delegated(delegation, fmode)) { rcu_read_unlock(); break; } @@ -1091,7 +1094,12 @@ static struct nfs4_state *nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data if (delegation) delegation_flags = delegation->flags; rcu_read_unlock(); - if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0) + if (data->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR) { + pr_err_ratelimited("NFS: Broken NFSv4 server %s is " + "returning a delegation for " + "OPEN(CLAIM_DELEGATE_CUR)\n", + NFS_CLIENT(inode)->cl_server); + } else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0) nfs_inode_set_delegation(state->inode, data->owner->so_cred, &data->o_res); @@ -1423,11 +1431,9 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) goto out_no_action; rcu_read_lock(); delegation = rcu_dereference(NFS_I(data->state->inode)->delegation); - if (delegation != NULL && - test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags) == 0) { - rcu_read_unlock(); - goto out_no_action; - } + if (data->o_arg.claim != NFS4_OPEN_CLAIM_DELEGATE_CUR && + can_open_delegated(delegation, data->o_arg.fmode)) + goto unlock_no_action; rcu_read_unlock(); } /* Update sequence id. */ @@ -1444,6 +1450,8 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata) return; rpc_call_start(task); return; +unlock_no_action: + rcu_read_unlock(); out_no_action: task->tk_action = NULL; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 39914be..6a7107a 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1156,11 +1156,13 @@ restart: if (status >= 0) { status = nfs4_reclaim_locks(state, ops); if (status >= 0) { + spin_lock(&state->state_lock); list_for_each_entry(lock, &state->lock_states, ls_locks) { if (!(lock->ls_flags & NFS_LOCK_INITIALIZED)) printk("%s: Lock reclaim failed!\n", __func__); } + spin_unlock(&state->state_lock); nfs4_put_open_state(state); goto restart; } @@ -1224,10 +1226,12 @@ static void nfs4_clear_open_state(struct nfs4_state *state) clear_bit(NFS_O_RDONLY_STATE, &state->flags); clear_bit(NFS_O_WRONLY_STATE, &state->flags); clear_bit(NFS_O_RDWR_STATE, &state->flags); + spin_lock(&state->state_lock); list_for_each_entry(lock, &state->lock_states, ls_locks) { lock->ls_seqid.flags = 0; lock->ls_flags &= ~NFS_LOCK_INITIALIZED; } + spin_unlock(&state->state_lock); } static void nfs4_reset_seqids(struct nfs_server *server, @@ -1350,12 +1354,14 @@ static void nfs4_warn_keyexpired(const char *s) static int nfs4_recovery_handle_error(struct nfs_client *clp, int error) { switch (error) { + case 0: + break; case -NFS4ERR_CB_PATH_DOWN: nfs_handle_cb_pathdown(clp); - return 0; + break; case -NFS4ERR_NO_GRACE: nfs4_state_end_reclaim_reboot(clp); - return 0; + break; case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_LEASE_MOVED: set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); @@ -1375,13 +1381,15 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error) case -NFS4ERR_SEQ_MISORDERED: set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); /* Zero session reset errors */ - return 0; + break; case -EKEYEXPIRED: /* Nothing we can do */ nfs4_warn_keyexpired(clp->cl_hostname); - return 0; + break; + default: + return error; } - return error; + return 0; } static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recovery_ops *ops) @@ -1428,7 +1436,7 @@ static int nfs4_check_lease(struct nfs_client *clp) struct rpc_cred *cred; const struct nfs4_state_maintenance_ops *ops = clp->cl_mvops->state_renewal_ops; - int status = -NFS4ERR_EXPIRED; + int status; /* Is the client already known to have an expired lease? */ if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) @@ -1438,6 +1446,7 @@ static int nfs4_check_lease(struct nfs_client *clp) spin_unlock(&clp->cl_lock); if (cred == NULL) { cred = nfs4_get_setclientid_cred(clp); + status = -ENOKEY; if (cred == NULL) goto out; } @@ -1525,16 +1534,16 @@ void nfs41_handle_sequence_flag_errors(struct nfs_client *clp, u32 flags) { if (!flags) return; - else if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED) + if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED) nfs41_handle_server_reboot(clp); - else if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED | + if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED | SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED | SEQ4_STATUS_ADMIN_STATE_REVOKED | SEQ4_STATUS_LEASE_MOVED)) nfs41_handle_state_revoked(clp); - else if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED) + if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED) nfs41_handle_recallable_state_revoked(clp); - else if (flags & (SEQ4_STATUS_CB_PATH_DOWN | + if (flags & (SEQ4_STATUS_CB_PATH_DOWN | SEQ4_STATUS_BACKCHANNEL_FAULT | SEQ4_STATUS_CB_PATH_DOWN_SESSION)) nfs41_handle_cb_path_down(clp); @@ -1662,10 +1671,10 @@ static void nfs4_state_manager(struct nfs_client *clp) if (test_and_clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state)) { status = nfs4_check_lease(clp); + if (status < 0) + goto out_error; if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) continue; - if (status < 0 && status != -NFS4ERR_CB_PATH_DOWN) - goto out_error; } /* Initialize or reset the session */ diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 41d6743..ac258be 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -625,6 +625,9 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp, if (argv[n].v_nmembs > nsegs * nilfs->ns_blocks_per_segment) goto out_free; + if (argv[n].v_nmembs >= UINT_MAX / argv[n].v_size) + goto out_free; + len = argv[n].v_size * argv[n].v_nmembs; base = (void __user *)(unsigned long)argv[n].v_base; if (len == 0) { @@ -842,6 +845,19 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case FS_IOC32_GETVERSION: cmd = FS_IOC_GETVERSION; break; + case NILFS_IOCTL_CHANGE_CPMODE: + case NILFS_IOCTL_DELETE_CHECKPOINT: + case NILFS_IOCTL_GET_CPINFO: + case NILFS_IOCTL_GET_CPSTAT: + case NILFS_IOCTL_GET_SUINFO: + case NILFS_IOCTL_GET_SUSTAT: + case NILFS_IOCTL_GET_VINFO: + case NILFS_IOCTL_GET_BDESCS: + case NILFS_IOCTL_CLEAN_SEGMENTS: + case NILFS_IOCTL_SYNC: + case NILFS_IOCTL_RESIZE: + case NILFS_IOCTL_SET_ALLOC_RANGE: + break; default: return -ENOIOCTLCMD; } diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 2a30d67..0855e6f2 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -32,7 +32,7 @@ static cputime64_t get_idle_time(int cpu) idle = kstat_cpu(cpu).cpustat.idle; idle = cputime64_add(idle, arch_idle_time(cpu)); } else - idle = nsecs_to_jiffies64(1000 * idle_time); + idle = usecs_to_cputime64(idle_time); return idle; } @@ -46,7 +46,7 @@ static cputime64_t get_iowait_time(int cpu) /* !NO_HZ so we can rely on cpustat.iowait */ iowait = kstat_cpu(cpu).cpustat.iowait; else - iowait = nsecs_to_jiffies64(1000 * iowait_time); + iowait = usecs_to_cputime64(iowait_time); return iowait; } diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 3eca58f..8a89949 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -869,27 +869,6 @@ xfs_fs_dirty_inode( } STATIC int -xfs_log_inode( - struct xfs_inode *ip) -{ - struct xfs_mount *mp = ip->i_mount; - struct xfs_trans *tp; - int error; - - tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS); - error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0); - if (error) { - xfs_trans_cancel(tp, 0); - return error; - } - - xfs_ilock(ip, XFS_ILOCK_EXCL); - xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); - return xfs_trans_commit(tp, 0); -} - -STATIC int xfs_fs_write_inode( struct inode *inode, struct writeback_control *wbc) @@ -902,10 +881,8 @@ xfs_fs_write_inode( if (XFS_FORCED_SHUTDOWN(mp)) return -XFS_ERROR(EIO); - if (!ip->i_update_core) - return 0; - if (wbc->sync_mode == WB_SYNC_ALL) { + if (wbc->sync_mode == WB_SYNC_ALL || wbc->for_kupdate) { /* * Make sure the inode has made it it into the log. Instead * of forcing it all the way to stable storage using a @@ -913,11 +890,14 @@ xfs_fs_write_inode( * ->sync_fs call do that for thus, which reduces the number * of synchronous log forces dramatically. */ - error = xfs_log_inode(ip); + error = xfs_log_dirty_inode(ip, NULL, 0); if (error) goto out; return 0; } else { + if (!ip->i_update_core) + return 0; + /* * We make this non-blocking if the inode is contended, return * EAGAIN to indicate to the caller that they did not succeed. diff --git a/fs/xfs/xfs_sync.c b/fs/xfs/xfs_sync.c index be5c51d..f0994aedc 100644 --- a/fs/xfs/xfs_sync.c +++ b/fs/xfs/xfs_sync.c @@ -336,6 +336,32 @@ xfs_sync_fsdata( return error; } +int +xfs_log_dirty_inode( + struct xfs_inode *ip, + struct xfs_perag *pag, + int flags) +{ + struct xfs_mount *mp = ip->i_mount; + struct xfs_trans *tp; + int error; + + if (!ip->i_update_core) + return 0; + + tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS); + error = xfs_trans_reserve(tp, 0, XFS_FSYNC_TS_LOG_RES(mp), 0, 0, 0); + if (error) { + xfs_trans_cancel(tp, 0); + return error; + } + + xfs_ilock(ip, XFS_ILOCK_EXCL); + xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL); + xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); + return xfs_trans_commit(tp, 0); +} + /* * When remounting a filesystem read-only or freezing the filesystem, we have * two phases to execute. This first phase is syncing the data before we @@ -359,6 +385,16 @@ xfs_quiesce_data( { int error, error2 = 0; + /* + * Log all pending size and timestamp updates. The vfs writeback + * code is supposed to do this, but due to its overagressive + * livelock detection it will skip inodes where appending writes + * were written out in the first non-blocking sync phase if their + * completion took long enough that it happened after taking the + * timestamp for the cut-off in the blocking phase. + */ + xfs_inode_ag_iterator(mp, xfs_log_dirty_inode, 0); + xfs_qm_sync(mp, SYNC_TRYLOCK); xfs_qm_sync(mp, SYNC_WAIT); diff --git a/fs/xfs/xfs_sync.h b/fs/xfs/xfs_sync.h index 941202e..fa96547 100644 --- a/fs/xfs/xfs_sync.h +++ b/fs/xfs/xfs_sync.h @@ -34,6 +34,8 @@ void xfs_quiesce_attr(struct xfs_mount *mp); void xfs_flush_inodes(struct xfs_inode *ip); +int xfs_log_dirty_inode(struct xfs_inode *ip, struct xfs_perag *pag, int flags); + int xfs_reclaim_inodes(struct xfs_mount *mp, int mode); int xfs_reclaim_inodes_count(struct xfs_mount *mp); void xfs_reclaim_inodes_nr(struct xfs_mount *mp, int nr_to_scan); diff --git a/include/asm-generic/cputime.h b/include/asm-generic/cputime.h index 62ce682..12a1764 100644 --- a/include/asm-generic/cputime.h +++ b/include/asm-generic/cputime.h @@ -40,6 +40,7 @@ typedef u64 cputime64_t; */ #define cputime_to_usecs(__ct) jiffies_to_usecs(__ct) #define usecs_to_cputime(__msecs) usecs_to_jiffies(__msecs) +#define usecs_to_cputime64(__msecs) nsecs_to_jiffies64((__msecs) * 1000) /* * Convert cputime to seconds and back. diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index ab344a5..66d3e95 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -44,7 +44,7 @@ extern unsigned long init_bootmem_node(pg_data_t *pgdat, unsigned long endpfn); extern unsigned long init_bootmem(unsigned long addr, unsigned long memend); -unsigned long free_all_memory_core_early(int nodeid); +extern unsigned long free_low_memory_core_early(int nodeid); extern unsigned long free_all_bootmem_node(pg_data_t *pgdat); extern unsigned long free_all_bootmem(void); diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index c86c940..081147d 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -71,7 +71,7 @@ struct timecounter { /** * cyclecounter_cyc2ns - converts cycle counter cycles to nanoseconds - * @tc: Pointer to cycle counter. + * @cc: Pointer to cycle counter. * @cycles: Cycles * * XXX - This could use some mult_lxl_ll() asm optimization. Same code @@ -114,7 +114,7 @@ extern u64 timecounter_read(struct timecounter *tc); * time base as values returned by * timecounter_read() * @tc: Pointer to time counter. - * @cycle: a value returned by tc->cc->read() + * @cycle_tstamp: a value returned by tc->cc->read() * * Cycle counts that are converted correctly as long as they * fall into the interval [-1/2 max cycle count, +1/2 max cycle count], @@ -156,11 +156,12 @@ 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%) + * @maxadj: maximum adjustment value to mult (~11%) * @flags: flags describing special properties * @archdata: arch-specific data * @suspend: suspend function for the clocksource, if necessary * @resume: resume function for the clocksource, if necessary + * @cycle_last: most recent cycle counter value seen by ::read() */ struct clocksource { /* @@ -187,6 +188,7 @@ struct clocksource { void (*suspend)(struct clocksource *cs); void (*resume)(struct clocksource *cs); + /* private: */ #ifdef CONFIG_CLOCKSOURCE_WATCHDOG /* Watchdog related data, used by the framework */ struct list_head wd_list; @@ -261,6 +263,9 @@ static inline u32 clocksource_hz2mult(u32 hz, u32 shift_constant) /** * clocksource_cyc2ns - converts clocksource cycles to nanoseconds + * @cycles: cycles + * @mult: cycle to nanosecond multiplier + * @shift: cycle to nanosecond divisor (power of two) * * Converts cycles to nanoseconds, using the given mult and shift. * diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 6cb60fd..305c263 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -27,6 +27,7 @@ struct cpu { extern int register_cpu(struct cpu *cpu, int num); extern struct sys_device *get_cpu_sysdev(unsigned cpu); +extern bool cpu_is_hotpluggable(unsigned cpu); extern int cpu_add_sysdev_attr(struct sysdev_attribute *attr); extern void cpu_remove_sysdev_attr(struct sysdev_attribute *attr); diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h index 65970b8..0e5f578 100644 --- a/include/linux/debugobjects.h +++ b/include/linux/debugobjects.h @@ -46,6 +46,8 @@ struct debug_obj { * fails * @fixup_free: fixup function, which is called when the free check * fails + * @fixup_assert_init: fixup function, which is called when the assert_init + * check fails */ struct debug_obj_descr { const char *name; @@ -54,6 +56,7 @@ struct debug_obj_descr { int (*fixup_activate) (void *addr, enum debug_obj_state state); int (*fixup_destroy) (void *addr, enum debug_obj_state state); int (*fixup_free) (void *addr, enum debug_obj_state state); + int (*fixup_assert_init)(void *addr, enum debug_obj_state state); }; #ifdef CONFIG_DEBUG_OBJECTS @@ -64,6 +67,7 @@ extern void debug_object_activate (void *addr, struct debug_obj_descr *descr); extern void debug_object_deactivate(void *addr, struct debug_obj_descr *descr); extern void debug_object_destroy (void *addr, struct debug_obj_descr *descr); extern void debug_object_free (void *addr, struct debug_obj_descr *descr); +extern void debug_object_assert_init(void *addr, struct debug_obj_descr *descr); /* * Active state: @@ -89,6 +93,8 @@ static inline void debug_object_destroy (void *addr, struct debug_obj_descr *descr) { } static inline void debug_object_free (void *addr, struct debug_obj_descr *descr) { } +static inline void +debug_object_assert_init(void *addr, struct debug_obj_descr *descr) { } static inline void debug_objects_early_init(void) { } static inline void debug_objects_mem_init(void) { } diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h index f743883..bb7f309 100644 --- a/include/linux/hardirq.h +++ b/include/linux/hardirq.h @@ -139,20 +139,7 @@ static inline void account_system_vtime(struct task_struct *tsk) extern void account_system_vtime(struct task_struct *tsk); #endif -#if defined(CONFIG_NO_HZ) #if defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU) -extern void rcu_enter_nohz(void); -extern void rcu_exit_nohz(void); - -static inline void rcu_irq_enter(void) -{ - rcu_exit_nohz(); -} - -static inline void rcu_irq_exit(void) -{ - rcu_enter_nohz(); -} static inline void rcu_nmi_enter(void) { @@ -163,17 +150,9 @@ static inline void rcu_nmi_exit(void) } #else -extern void rcu_irq_enter(void); -extern void rcu_irq_exit(void); extern void rcu_nmi_enter(void); extern void rcu_nmi_exit(void); #endif -#else -# define rcu_irq_enter() do { } while (0) -# define rcu_irq_exit() do { } while (0) -# define rcu_nmi_enter() do { } while (0) -# define rcu_nmi_exit() do { } while (0) -#endif /* #if defined(CONFIG_NO_HZ) */ /* * It is safe to do non-atomic ops on ->hardirq_context, diff --git a/include/linux/kvm.h b/include/linux/kvm.h index c3892fc..68e67e5 100644 --- a/include/linux/kvm.h +++ b/include/linux/kvm.h @@ -557,6 +557,7 @@ struct kvm_ppc_pvinfo { #define KVM_CAP_MAX_VCPUS 66 /* returns max vcpus per vm */ #define KVM_CAP_PPC_PAPR 68 #define KVM_CAP_S390_GMAP 71 +#define KVM_CAP_TSC_DEADLINE_TIMER 72 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/include/linux/lglock.h b/include/linux/lglock.h index f549056..87f402c 100644 --- a/include/linux/lglock.h +++ b/include/linux/lglock.h @@ -22,6 +22,7 @@ #include <linux/spinlock.h> #include <linux/lockdep.h> #include <linux/percpu.h> +#include <linux/cpu.h> /* can make br locks by using local lock for read side, global lock for write */ #define br_lock_init(name) name##_lock_init() @@ -72,9 +73,31 @@ #define DEFINE_LGLOCK(name) \ \ + DEFINE_SPINLOCK(name##_cpu_lock); \ + cpumask_t name##_cpus __read_mostly; \ DEFINE_PER_CPU(arch_spinlock_t, name##_lock); \ DEFINE_LGLOCK_LOCKDEP(name); \ \ + static int \ + name##_lg_cpu_callback(struct notifier_block *nb, \ + unsigned long action, void *hcpu) \ + { \ + switch (action & ~CPU_TASKS_FROZEN) { \ + case CPU_UP_PREPARE: \ + spin_lock(&name##_cpu_lock); \ + cpu_set((unsigned long)hcpu, name##_cpus); \ + spin_unlock(&name##_cpu_lock); \ + break; \ + case CPU_UP_CANCELED: case CPU_DEAD: \ + spin_lock(&name##_cpu_lock); \ + cpu_clear((unsigned long)hcpu, name##_cpus); \ + spin_unlock(&name##_cpu_lock); \ + } \ + return NOTIFY_OK; \ + } \ + static struct notifier_block name##_lg_cpu_notifier = { \ + .notifier_call = name##_lg_cpu_callback, \ + }; \ void name##_lock_init(void) { \ int i; \ LOCKDEP_INIT_MAP(&name##_lock_dep_map, #name, &name##_lock_key, 0); \ @@ -83,6 +106,11 @@ lock = &per_cpu(name##_lock, i); \ *lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; \ } \ + register_hotcpu_notifier(&name##_lg_cpu_notifier); \ + get_online_cpus(); \ + for_each_online_cpu(i) \ + cpu_set(i, name##_cpus); \ + put_online_cpus(); \ } \ EXPORT_SYMBOL(name##_lock_init); \ \ @@ -124,9 +152,9 @@ \ void name##_global_lock_online(void) { \ int i; \ - preempt_disable(); \ + spin_lock(&name##_cpu_lock); \ rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_); \ - for_each_online_cpu(i) { \ + for_each_cpu(i, &name##_cpus) { \ arch_spinlock_t *lock; \ lock = &per_cpu(name##_lock, i); \ arch_spin_lock(lock); \ @@ -137,12 +165,12 @@ void name##_global_unlock_online(void) { \ int i; \ rwlock_release(&name##_lock_dep_map, 1, _RET_IP_); \ - for_each_online_cpu(i) { \ + for_each_cpu(i, &name##_cpus) { \ arch_spinlock_t *lock; \ lock = &per_cpu(name##_lock, i); \ arch_spin_unlock(lock); \ } \ - preempt_enable(); \ + spin_unlock(&name##_cpu_lock); \ } \ EXPORT_SYMBOL(name##_global_unlock_online); \ \ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index b6a56e3..d36619e 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -343,6 +343,8 @@ extern void lockdep_trace_alloc(gfp_t mask); #define lockdep_assert_held(l) WARN_ON(debug_locks && !lockdep_is_held(l)) +#define lockdep_recursing(tsk) ((tsk)->lockdep_recursion) + #else /* !LOCKDEP */ static inline void lockdep_off(void) @@ -392,6 +394,8 @@ struct lock_class_key { }; #define lockdep_assert_held(l) do { } while (0) +#define lockdep_recursing(tsk) (0) + #endif /* !LOCKDEP */ #ifdef CONFIG_LOCK_STAT diff --git a/include/linux/memblock.h b/include/linux/memblock.h index e6b843e..a6bb102 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -2,8 +2,6 @@ #define _LINUX_MEMBLOCK_H #ifdef __KERNEL__ -#define MEMBLOCK_ERROR 0 - #ifdef CONFIG_HAVE_MEMBLOCK /* * Logical memory blocks. @@ -19,81 +17,161 @@ #include <linux/init.h> #include <linux/mm.h> -#include <asm/memblock.h> - #define INIT_MEMBLOCK_REGIONS 128 struct memblock_region { phys_addr_t base; phys_addr_t size; +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP + int nid; +#endif }; struct memblock_type { unsigned long cnt; /* number of regions */ unsigned long max; /* size of the allocated array */ + phys_addr_t total_size; /* size of all regions */ struct memblock_region *regions; }; struct memblock { phys_addr_t current_limit; - phys_addr_t memory_size; /* Updated by memblock_analyze() */ struct memblock_type memory; struct memblock_type reserved; }; extern struct memblock memblock; extern int memblock_debug; -extern int memblock_can_resize; #define memblock_dbg(fmt, ...) \ if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) -u64 memblock_find_in_range(u64 start, u64 end, u64 size, u64 align); +phys_addr_t memblock_find_in_range_node(phys_addr_t start, phys_addr_t end, + phys_addr_t size, phys_addr_t align, int nid); +phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end, + phys_addr_t size, phys_addr_t align); int memblock_free_reserved_regions(void); int memblock_reserve_reserved_regions(void); -extern void memblock_init(void); -extern void memblock_analyze(void); -extern long memblock_add(phys_addr_t base, phys_addr_t size); -extern long memblock_remove(phys_addr_t base, phys_addr_t size); -extern long memblock_free(phys_addr_t base, phys_addr_t size); -extern long memblock_reserve(phys_addr_t base, phys_addr_t size); +void memblock_allow_resize(void); +int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); +int memblock_add(phys_addr_t base, phys_addr_t size); +int memblock_remove(phys_addr_t base, phys_addr_t size); +int memblock_free(phys_addr_t base, phys_addr_t size); +int memblock_reserve(phys_addr_t base, phys_addr_t size); + +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, + unsigned long *out_end_pfn, int *out_nid); + +/** + * for_each_mem_pfn_range - early memory pfn range iterator + * @i: an integer used as loop variable + * @nid: node selector, %MAX_NUMNODES for all nodes + * @p_start: ptr to ulong for start pfn of the range, can be %NULL + * @p_end: ptr to ulong for end pfn of the range, can be %NULL + * @p_nid: ptr to int for nid of the range, can be %NULL + * + * Walks over configured memory ranges. Available after early_node_map is + * populated. + */ +#define for_each_mem_pfn_range(i, nid, p_start, p_end, p_nid) \ + for (i = -1, __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid); \ + i >= 0; __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid)) +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ + +void __next_free_mem_range(u64 *idx, int nid, phys_addr_t *out_start, + phys_addr_t *out_end, int *out_nid); + +/** + * for_each_free_mem_range - iterate through free memblock areas + * @i: u64 used as loop variable + * @nid: node selector, %MAX_NUMNODES for all nodes + * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL + * @p_nid: ptr to int for nid of the range, can be %NULL + * + * Walks over free (memory && !reserved) areas of memblock. Available as + * soon as memblock is initialized. + */ +#define for_each_free_mem_range(i, nid, p_start, p_end, p_nid) \ + for (i = 0, \ + __next_free_mem_range(&i, nid, p_start, p_end, p_nid); \ + i != (u64)ULLONG_MAX; \ + __next_free_mem_range(&i, nid, p_start, p_end, p_nid)) + +void __next_free_mem_range_rev(u64 *idx, int nid, phys_addr_t *out_start, + phys_addr_t *out_end, int *out_nid); -/* The numa aware allocator is only available if - * CONFIG_ARCH_POPULATES_NODE_MAP is set +/** + * for_each_free_mem_range_reverse - rev-iterate through free memblock areas + * @i: u64 used as loop variable + * @nid: node selector, %MAX_NUMNODES for all nodes + * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL + * @p_nid: ptr to int for nid of the range, can be %NULL + * + * Walks over free (memory && !reserved) areas of memblock in reverse + * order. Available as soon as memblock is initialized. */ -extern phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align, - int nid); -extern phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, - int nid); +#define for_each_free_mem_range_reverse(i, nid, p_start, p_end, p_nid) \ + for (i = (u64)ULLONG_MAX, \ + __next_free_mem_range_rev(&i, nid, p_start, p_end, p_nid); \ + i != (u64)ULLONG_MAX; \ + __next_free_mem_range_rev(&i, nid, p_start, p_end, p_nid)) -extern phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align); +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +int memblock_set_node(phys_addr_t base, phys_addr_t size, int nid); + +static inline void memblock_set_region_node(struct memblock_region *r, int nid) +{ + r->nid = nid; +} + +static inline int memblock_get_region_node(const struct memblock_region *r) +{ + return r->nid; +} +#else +static inline void memblock_set_region_node(struct memblock_region *r, int nid) +{ +} + +static inline int memblock_get_region_node(const struct memblock_region *r) +{ + return 0; +} +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ + +phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid); +phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); + +phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align); /* Flags for memblock_alloc_base() amd __memblock_alloc_base() */ #define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) #define MEMBLOCK_ALLOC_ACCESSIBLE 0 -extern phys_addr_t memblock_alloc_base(phys_addr_t size, - phys_addr_t align, - phys_addr_t max_addr); -extern phys_addr_t __memblock_alloc_base(phys_addr_t size, - phys_addr_t align, - phys_addr_t max_addr); -extern phys_addr_t memblock_phys_mem_size(void); -extern phys_addr_t memblock_start_of_DRAM(void); -extern phys_addr_t memblock_end_of_DRAM(void); -extern void memblock_enforce_memory_limit(phys_addr_t memory_limit); -extern int memblock_is_memory(phys_addr_t addr); -extern int memblock_is_region_memory(phys_addr_t base, phys_addr_t size); -extern int memblock_is_reserved(phys_addr_t addr); -extern int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size); - -extern void memblock_dump_all(void); - -/* Provided by the architecture */ -extern phys_addr_t memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid); -extern int memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1, - phys_addr_t addr2, phys_addr_t size2); +phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align, + phys_addr_t max_addr); +phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align, + phys_addr_t max_addr); +phys_addr_t memblock_phys_mem_size(void); +phys_addr_t memblock_start_of_DRAM(void); +phys_addr_t memblock_end_of_DRAM(void); +void memblock_enforce_memory_limit(phys_addr_t memory_limit); +int memblock_is_memory(phys_addr_t addr); +int memblock_is_region_memory(phys_addr_t base, phys_addr_t size); +int memblock_is_reserved(phys_addr_t addr); +int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size); + +extern void __memblock_dump_all(void); + +static inline void memblock_dump_all(void) +{ + if (memblock_debug) + __memblock_dump_all(); +} /** * memblock_set_current_limit - Set the current allocation limit to allow @@ -101,7 +179,7 @@ extern int memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1, * accessible during boot * @limit: New limit value (physical address) */ -extern void memblock_set_current_limit(phys_addr_t limit); +void memblock_set_current_limit(phys_addr_t limit); /* @@ -154,9 +232,9 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo region++) -#ifdef ARCH_DISCARD_MEMBLOCK -#define __init_memblock __init -#define __initdata_memblock __initdata +#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK +#define __init_memblock __meminit +#define __initdata_memblock __meminitdata #else #define __init_memblock #define __initdata_memblock @@ -165,7 +243,7 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo #else static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align) { - return MEMBLOCK_ERROR; + return 0; } #endif /* CONFIG_HAVE_MEMBLOCK */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 4baadd1..5d9b4c9 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1253,41 +1253,34 @@ static inline void pgtable_page_dtor(struct page *page) extern void free_area_init(unsigned long * zones_size); extern void free_area_init_node(int nid, unsigned long * zones_size, unsigned long zone_start_pfn, unsigned long *zholes_size); -#ifdef CONFIG_ARCH_POPULATES_NODE_MAP +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP /* - * With CONFIG_ARCH_POPULATES_NODE_MAP set, an architecture may initialise its + * With CONFIG_HAVE_MEMBLOCK_NODE_MAP set, an architecture may initialise its * zones, allocate the backing mem_map and account for memory holes in a more * architecture independent manner. This is a substitute for creating the * zone_sizes[] and zholes_size[] arrays and passing them to * free_area_init_node() * * An architecture is expected to register range of page frames backed by - * physical memory with add_active_range() before calling + * physical memory with memblock_add[_node]() before calling * free_area_init_nodes() passing in the PFN each zone ends at. At a basic * usage, an architecture is expected to do something like * * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() - * add_active_range(node_id, start_pfn, end_pfn) + * memblock_add_node(base, size, nid) * free_area_init_nodes(max_zone_pfns); * - * If the architecture guarantees that there are no holes in the ranges - * registered with add_active_range(), free_bootmem_active_regions() - * will call free_bootmem_node() for each registered physical page range. - * Similarly sparse_memory_present_with_active_regions() calls - * memory_present() for each range when SPARSEMEM is enabled. + * free_bootmem_with_active_regions() calls free_bootmem_node() for each + * registered physical page range. Similarly + * sparse_memory_present_with_active_regions() calls memory_present() for + * each range when SPARSEMEM is enabled. * * See mm/page_alloc.c for more information on each function exposed by - * CONFIG_ARCH_POPULATES_NODE_MAP + * CONFIG_HAVE_MEMBLOCK_NODE_MAP. */ extern void free_area_init_nodes(unsigned long *max_zone_pfn); -extern void add_active_range(unsigned int nid, unsigned long start_pfn, - unsigned long end_pfn); -extern void remove_active_range(unsigned int nid, unsigned long start_pfn, - unsigned long end_pfn); -extern void remove_all_active_ranges(void); -void sort_node_map(void); unsigned long node_map_pfn_alignment(void); unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn, unsigned long end_pfn); @@ -1300,14 +1293,11 @@ extern void free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn); int add_from_early_node_map(struct range *range, int az, int nr_range, int nid); -u64 __init find_memory_core_early(int nid, u64 size, u64 align, - u64 goal, u64 limit); -typedef int (*work_fn_t)(unsigned long, unsigned long, void *); -extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data); extern void sparse_memory_present_with_active_regions(int nid); -#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ -#if !defined(CONFIG_ARCH_POPULATES_NODE_MAP) && \ +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ + +#if !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) && \ !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) static inline int __early_pfn_to_nid(unsigned long pfn) { diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 188cb2f..3ac040f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -598,13 +598,13 @@ struct zonelist { #endif }; -#ifdef CONFIG_ARCH_POPULATES_NODE_MAP +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP struct node_active_region { unsigned long start_pfn; unsigned long end_pfn; int nid; }; -#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #ifndef CONFIG_DISCONTIGMEM /* The array of struct pages - for discontigmem use pgdat->lmem_map */ @@ -720,7 +720,7 @@ extern int movable_zone; static inline int zone_movable_is_highmem(void) { -#if defined(CONFIG_HIGHMEM) && defined(CONFIG_ARCH_POPULATES_NODE_MAP) +#if defined(CONFIG_HIGHMEM) && defined(CONFIG_HAVE_MEMBLOCK_NODE) return movable_zone == ZONE_HIGHMEM; #else return 0; @@ -938,7 +938,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist, #endif #if !defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) && \ - !defined(CONFIG_ARCH_POPULATES_NODE_MAP) + !defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) static inline unsigned long early_pfn_to_nid(unsigned long pfn) { return 0; diff --git a/include/linux/poison.h b/include/linux/poison.h index 79159de..2110a81 100644 --- a/include/linux/poison.h +++ b/include/linux/poison.h @@ -40,12 +40,6 @@ #define RED_INACTIVE 0x09F911029D74E35BULL /* when obj is inactive */ #define RED_ACTIVE 0xD84156C5635688C0ULL /* when obj is active */ -#ifdef CONFIG_PHYS_ADDR_T_64BIT -#define MEMBLOCK_INACTIVE 0x3a84fb0144c9e71bULL -#else -#define MEMBLOCK_INACTIVE 0x44c9e71bUL -#endif - #define SLUB_RED_INACTIVE 0xbb #define SLUB_RED_ACTIVE 0xcc diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 2cf4226..81c04f4 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -51,6 +51,8 @@ extern int rcutorture_runnable; /* for sysctl */ #if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) extern void rcutorture_record_test_transition(void); extern void rcutorture_record_progress(unsigned long vernum); +extern void do_trace_rcu_torture_read(char *rcutorturename, + struct rcu_head *rhp); #else static inline void rcutorture_record_test_transition(void) { @@ -58,6 +60,12 @@ static inline void rcutorture_record_test_transition(void) static inline void rcutorture_record_progress(unsigned long vernum) { } +#ifdef CONFIG_RCU_TRACE +extern void do_trace_rcu_torture_read(char *rcutorturename, + struct rcu_head *rhp); +#else +#define do_trace_rcu_torture_read(rcutorturename, rhp) do { } while (0) +#endif #endif #define UINT_CMP_GE(a, b) (UINT_MAX / 2 >= (a) - (b)) @@ -177,23 +185,10 @@ extern void rcu_sched_qs(int cpu); extern void rcu_bh_qs(int cpu); extern void rcu_check_callbacks(int cpu, int user); struct notifier_block; - -#ifdef CONFIG_NO_HZ - -extern void rcu_enter_nohz(void); -extern void rcu_exit_nohz(void); - -#else /* #ifdef CONFIG_NO_HZ */ - -static inline void rcu_enter_nohz(void) -{ -} - -static inline void rcu_exit_nohz(void) -{ -} - -#endif /* #else #ifdef CONFIG_NO_HZ */ +extern void rcu_idle_enter(void); +extern void rcu_idle_exit(void); +extern void rcu_irq_enter(void); +extern void rcu_irq_exit(void); /* * Infrastructure to implement the synchronize_() primitives in @@ -233,22 +228,30 @@ static inline void destroy_rcu_head_on_stack(struct rcu_head *head) #ifdef CONFIG_DEBUG_LOCK_ALLOC -extern struct lockdep_map rcu_lock_map; -# define rcu_read_acquire() \ - lock_acquire(&rcu_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_) -# define rcu_read_release() lock_release(&rcu_lock_map, 1, _THIS_IP_) +#ifdef CONFIG_PROVE_RCU +extern int rcu_is_cpu_idle(void); +#else /* !CONFIG_PROVE_RCU */ +static inline int rcu_is_cpu_idle(void) +{ + return 0; +} +#endif /* else !CONFIG_PROVE_RCU */ -extern struct lockdep_map rcu_bh_lock_map; -# define rcu_read_acquire_bh() \ - lock_acquire(&rcu_bh_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_) -# define rcu_read_release_bh() lock_release(&rcu_bh_lock_map, 1, _THIS_IP_) +static inline void rcu_lock_acquire(struct lockdep_map *map) +{ + WARN_ON_ONCE(rcu_is_cpu_idle()); + lock_acquire(map, 0, 0, 2, 1, NULL, _THIS_IP_); +} -extern struct lockdep_map rcu_sched_lock_map; -# define rcu_read_acquire_sched() \ - lock_acquire(&rcu_sched_lock_map, 0, 0, 2, 1, NULL, _THIS_IP_) -# define rcu_read_release_sched() \ - lock_release(&rcu_sched_lock_map, 1, _THIS_IP_) +static inline void rcu_lock_release(struct lockdep_map *map) +{ + WARN_ON_ONCE(rcu_is_cpu_idle()); + lock_release(map, 1, _THIS_IP_); +} +extern struct lockdep_map rcu_lock_map; +extern struct lockdep_map rcu_bh_lock_map; +extern struct lockdep_map rcu_sched_lock_map; extern int debug_lockdep_rcu_enabled(void); /** @@ -262,11 +265,18 @@ extern int debug_lockdep_rcu_enabled(void); * * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. + * + * Note that rcu_read_lock() and the matching rcu_read_unlock() must + * occur in the same context, for example, it is illegal to invoke + * rcu_read_unlock() in process context if the matching rcu_read_lock() + * was invoked from within an irq handler. */ static inline int rcu_read_lock_held(void) { if (!debug_lockdep_rcu_enabled()) return 1; + if (rcu_is_cpu_idle()) + return 0; return lock_is_held(&rcu_lock_map); } @@ -290,6 +300,19 @@ extern int rcu_read_lock_bh_held(void); * * Check debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. + * + * Note that if the CPU is in the idle loop from an RCU point of + * view (ie: that we are in the section between rcu_idle_enter() and + * rcu_idle_exit()) then rcu_read_lock_held() returns false even if the CPU + * did an rcu_read_lock(). The reason for this is that RCU ignores CPUs + * that are in such a section, considering these as in extended quiescent + * state, so such a CPU is effectively never in an RCU read-side critical + * section regardless of what RCU primitives it invokes. This state of + * affairs is required --- we need to keep an RCU-free window in idle + * where the CPU may possibly enter into low power mode. This way we can + * notice an extended quiescent state to other CPUs that started a grace + * period. Otherwise we would delay any grace period as long as we run in + * the idle task. */ #ifdef CONFIG_PREEMPT_COUNT static inline int rcu_read_lock_sched_held(void) @@ -298,6 +321,8 @@ static inline int rcu_read_lock_sched_held(void) if (!debug_lockdep_rcu_enabled()) return 1; + if (rcu_is_cpu_idle()) + return 0; if (debug_locks) lockdep_opinion = lock_is_held(&rcu_sched_lock_map); return lockdep_opinion || preempt_count() != 0 || irqs_disabled(); @@ -311,12 +336,8 @@ static inline int rcu_read_lock_sched_held(void) #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ -# define rcu_read_acquire() do { } while (0) -# define rcu_read_release() do { } while (0) -# define rcu_read_acquire_bh() do { } while (0) -# define rcu_read_release_bh() do { } while (0) -# define rcu_read_acquire_sched() do { } while (0) -# define rcu_read_release_sched() do { } while (0) +# define rcu_lock_acquire(a) do { } while (0) +# define rcu_lock_release(a) do { } while (0) static inline int rcu_read_lock_held(void) { @@ -637,7 +658,7 @@ static inline void rcu_read_lock(void) { __rcu_read_lock(); __acquire(RCU); - rcu_read_acquire(); + rcu_lock_acquire(&rcu_lock_map); } /* @@ -657,7 +678,7 @@ static inline void rcu_read_lock(void) */ static inline void rcu_read_unlock(void) { - rcu_read_release(); + rcu_lock_release(&rcu_lock_map); __release(RCU); __rcu_read_unlock(); } @@ -673,12 +694,17 @@ static inline void rcu_read_unlock(void) * critical sections in interrupt context can use just rcu_read_lock(), * though this should at least be commented to avoid confusing people * reading the code. + * + * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() + * must occur in the same context, for example, it is illegal to invoke + * rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh() + * was invoked from some other task. */ static inline void rcu_read_lock_bh(void) { local_bh_disable(); __acquire(RCU_BH); - rcu_read_acquire_bh(); + rcu_lock_acquire(&rcu_bh_lock_map); } /* @@ -688,7 +714,7 @@ static inline void rcu_read_lock_bh(void) */ static inline void rcu_read_unlock_bh(void) { - rcu_read_release_bh(); + rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); local_bh_enable(); } @@ -700,12 +726,17 @@ static inline void rcu_read_unlock_bh(void) * are being done using call_rcu_sched() or synchronize_rcu_sched(). * Read-side critical sections can also be introduced by anything that * disables preemption, including local_irq_disable() and friends. + * + * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() + * must occur in the same context, for example, it is illegal to invoke + * rcu_read_unlock_sched() from process context if the matching + * rcu_read_lock_sched() was invoked from an NMI handler. */ static inline void rcu_read_lock_sched(void) { preempt_disable(); __acquire(RCU_SCHED); - rcu_read_acquire_sched(); + rcu_lock_acquire(&rcu_sched_lock_map); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ @@ -722,7 +753,7 @@ static inline notrace void rcu_read_lock_sched_notrace(void) */ static inline void rcu_read_unlock_sched(void) { - rcu_read_release_sched(); + rcu_lock_release(&rcu_sched_lock_map); __release(RCU_SCHED); preempt_enable(); } diff --git a/include/linux/sched.h b/include/linux/sched.h index 1c4f3e9..4a7e4d3 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2070,6 +2070,14 @@ extern int sched_setscheduler(struct task_struct *, int, extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern struct task_struct *idle_task(int cpu); +/** + * is_idle_task - is the specified task an idle task? + * @tsk: the task in question. + */ +static inline bool is_idle_task(struct task_struct *p) +{ + return p->pid == 0; +} extern struct task_struct *curr_task(int cpu); extern void set_curr_task(int cpu, struct task_struct *p); diff --git a/include/linux/security.h b/include/linux/security.h index 19d8e04..e8c619d 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -2056,7 +2056,7 @@ static inline int security_old_inode_init_security(struct inode *inode, char **name, void **value, size_t *len) { - return 0; + return -EOPNOTSUPP; } static inline int security_inode_create(struct inode *dir, diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 58971e8..e1b0059 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -28,6 +28,7 @@ #define _LINUX_SRCU_H #include <linux/mutex.h> +#include <linux/rcupdate.h> struct srcu_struct_array { int c[2]; @@ -60,18 +61,10 @@ int __init_srcu_struct(struct srcu_struct *sp, const char *name, __init_srcu_struct((sp), #sp, &__srcu_key); \ }) -# define srcu_read_acquire(sp) \ - lock_acquire(&(sp)->dep_map, 0, 0, 2, 1, NULL, _THIS_IP_) -# define srcu_read_release(sp) \ - lock_release(&(sp)->dep_map, 1, _THIS_IP_) - #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ int init_srcu_struct(struct srcu_struct *sp); -# define srcu_read_acquire(sp) do { } while (0) -# define srcu_read_release(sp) do { } while (0) - #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ void cleanup_srcu_struct(struct srcu_struct *sp); @@ -90,12 +83,32 @@ long srcu_batches_completed(struct srcu_struct *sp); * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, * this assumes we are in an SRCU read-side critical section unless it can * prove otherwise. + * + * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot + * and while lockdep is disabled. + * + * Note that if the CPU is in the idle loop from an RCU point of view + * (ie: that we are in the section between rcu_idle_enter() and + * rcu_idle_exit()) then srcu_read_lock_held() returns false even if + * the CPU did an srcu_read_lock(). The reason for this is that RCU + * ignores CPUs that are in such a section, considering these as in + * extended quiescent state, so such a CPU is effectively never in an + * RCU read-side critical section regardless of what RCU primitives it + * invokes. This state of affairs is required --- we need to keep an + * RCU-free window in idle where the CPU may possibly enter into low + * power mode. This way we can notice an extended quiescent state to + * other CPUs that started a grace period. Otherwise we would delay any + * grace period as long as we run in the idle task. */ static inline int srcu_read_lock_held(struct srcu_struct *sp) { - if (debug_locks) - return lock_is_held(&sp->dep_map); - return 1; + if (rcu_is_cpu_idle()) + return 0; + + if (!debug_lockdep_rcu_enabled()) + return 1; + + return lock_is_held(&sp->dep_map); } #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ @@ -145,12 +158,17 @@ static inline int srcu_read_lock_held(struct srcu_struct *sp) * one way to indirectly wait on an SRCU grace period is to acquire * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). + * + * Note that srcu_read_lock() and the matching srcu_read_unlock() must + * occur in the same context, for example, it is illegal to invoke + * srcu_read_unlock() in an irq handler if the matching srcu_read_lock() + * was invoked in process context. */ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) { int retval = __srcu_read_lock(sp); - srcu_read_acquire(sp); + rcu_lock_acquire(&(sp)->dep_map); return retval; } @@ -164,8 +182,51 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp) static inline void srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp) { - srcu_read_release(sp); + rcu_lock_release(&(sp)->dep_map); + __srcu_read_unlock(sp, idx); +} + +/** + * srcu_read_lock_raw - register a new reader for an SRCU-protected structure. + * @sp: srcu_struct in which to register the new reader. + * + * Enter an SRCU read-side critical section. Similar to srcu_read_lock(), + * but avoids the RCU-lockdep checking. This means that it is legal to + * use srcu_read_lock_raw() in one context, for example, in an exception + * handler, and then have the matching srcu_read_unlock_raw() in another + * context, for example in the task that took the exception. + * + * However, the entire SRCU read-side critical section must reside within a + * single task. For example, beware of using srcu_read_lock_raw() in + * a device interrupt handler and srcu_read_unlock() in the interrupted + * task: This will not work if interrupts are threaded. + */ +static inline int srcu_read_lock_raw(struct srcu_struct *sp) +{ + unsigned long flags; + int ret; + + local_irq_save(flags); + ret = __srcu_read_lock(sp); + local_irq_restore(flags); + return ret; +} + +/** + * srcu_read_unlock_raw - unregister reader from an SRCU-protected structure. + * @sp: srcu_struct in which to unregister the old reader. + * @idx: return value from corresponding srcu_read_lock_raw(). + * + * Exit an SRCU read-side critical section without lockdep-RCU checking. + * See srcu_read_lock_raw() for more details. + */ +static inline void srcu_read_unlock_raw(struct srcu_struct *sp, int idx) +{ + unsigned long flags; + + local_irq_save(flags); __srcu_read_unlock(sp, idx); + local_irq_restore(flags); } #endif diff --git a/include/linux/tick.h b/include/linux/tick.h index b232ccc..ab8be90 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -7,6 +7,7 @@ #define _LINUX_TICK_H #include <linux/clockchips.h> +#include <linux/irqflags.h> #ifdef CONFIG_GENERIC_CLOCKEVENTS @@ -121,14 +122,16 @@ static inline int tick_oneshot_mode_active(void) { return 0; } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ # ifdef CONFIG_NO_HZ -extern void tick_nohz_stop_sched_tick(int inidle); -extern void tick_nohz_restart_sched_tick(void); +extern void tick_nohz_idle_enter(void); +extern void tick_nohz_idle_exit(void); +extern void tick_nohz_irq_exit(void); extern ktime_t tick_nohz_get_sleep_length(void); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); # else -static inline void tick_nohz_stop_sched_tick(int inidle) { } -static inline void tick_nohz_restart_sched_tick(void) { } +static inline void tick_nohz_idle_enter(void) { } +static inline void tick_nohz_idle_exit(void) { } + static inline ktime_t tick_nohz_get_sleep_length(void) { ktime_t len = { .tv64 = NSEC_PER_SEC/HZ }; diff --git a/include/linux/wait.h b/include/linux/wait.h index 3efc9f3..a9ce45e 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -77,13 +77,13 @@ struct task_struct; #define __WAIT_BIT_KEY_INITIALIZER(word, bit) \ { .flags = word, .bit_nr = bit, } -extern void __init_waitqueue_head(wait_queue_head_t *q, struct lock_class_key *); +extern void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *); #define init_waitqueue_head(q) \ do { \ static struct lock_class_key __key; \ \ - __init_waitqueue_head((q), &__key); \ + __init_waitqueue_head((q), #q, &__key); \ } while (0) #ifdef CONFIG_LOCKDEP diff --git a/include/media/soc_camera.h b/include/media/soc_camera.h index b1377b9..5fb2c3d 100644 --- a/include/media/soc_camera.h +++ b/include/media/soc_camera.h @@ -254,7 +254,7 @@ unsigned long soc_camera_apply_board_flags(struct soc_camera_link *icl, static inline struct video_device *soc_camera_i2c_to_vdev(const struct i2c_client *client) { struct v4l2_subdev *sd = i2c_get_clientdata(client); - struct soc_camera_device *icd = (struct soc_camera_device *)sd->grp_id; + struct soc_camera_device *icd = v4l2_get_subdev_hostdata(sd); return icd ? icd->vdev : NULL; } @@ -279,6 +279,11 @@ static inline struct soc_camera_device *soc_camera_from_vbq(const struct videobu return container_of(vq, struct soc_camera_device, vb_vidq); } +static inline u32 soc_camera_grp_id(const struct soc_camera_device *icd) +{ + return (icd->iface << 8) | (icd->devnum + 1); +} + void soc_camera_lock(struct vb2_queue *vq); void soc_camera_unlock(struct vb2_queue *vq); diff --git a/include/net/dst.h b/include/net/dst.h index 6faec1a..75766b4 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -53,6 +53,7 @@ struct dst_entry { #define DST_NOHASH 0x0008 #define DST_NOCACHE 0x0010 #define DST_NOCOUNT 0x0020 +#define DST_NOPEER 0x0040 short error; short obsolete; diff --git a/include/net/flow.h b/include/net/flow.h index a094477..57f15a7 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -207,6 +207,7 @@ extern struct flow_cache_object *flow_cache_lookup( u8 dir, flow_resolve_t resolver, void *ctx); extern void flow_cache_flush(void); +extern void flow_cache_flush_deferred(void); extern atomic_t flow_cache_genid; #endif diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 873d5be..e5a7b9a 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -1207,7 +1207,7 @@ extern void ip_vs_control_cleanup(void); extern struct ip_vs_dest * ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr, __be16 dport, const union nf_inet_addr *vaddr, __be16 vport, - __u16 protocol, __u32 fwmark); + __u16 protocol, __u32 fwmark, __u32 flags); extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index e90e7a9..a15432da 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -241,6 +241,9 @@ extern struct sctp_globals { * bits is an indicator of when to send and window update SACK. */ int rwnd_update_shift; + + /* Threshold for autoclose timeout, in seconds. */ + unsigned long max_autoclose; } sctp_globals; #define sctp_rto_initial (sctp_globals.rto_initial) @@ -281,6 +284,7 @@ extern struct sctp_globals { #define sctp_auth_enable (sctp_globals.auth_enable) #define sctp_checksum_disable (sctp_globals.checksum_disable) #define sctp_rwnd_upd_shift (sctp_globals.rwnd_update_shift) +#define sctp_max_autoclose (sctp_globals.max_autoclose) /* SCTP Socket type: UDP or TCP style. */ typedef enum { diff --git a/include/net/sock.h b/include/net/sock.h index abb6e0f..32e3937 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -637,12 +637,14 @@ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) /* * Take into account size of receive queue and backlog queue + * Do not take into account this skb truesize, + * to allow even a single big packet to come. */ static inline bool sk_rcvqueues_full(const struct sock *sk, const struct sk_buff *skb) { unsigned int qsize = sk->sk_backlog.len + atomic_read(&sk->sk_rmem_alloc); - return qsize + skb->truesize > sk->sk_rcvbuf; + return qsize > sk->sk_rcvbuf; } /* The per-socket spinlock must be held here. */ diff --git a/include/scsi/libfcoe.h b/include/scsi/libfcoe.h index d1e95c6..5a35a2a 100644 --- a/include/scsi/libfcoe.h +++ b/include/scsi/libfcoe.h @@ -147,6 +147,7 @@ struct fcoe_ctlr { u8 map_dest; u8 spma; u8 probe_tries; + u8 priority; u8 dest_addr[ETH_ALEN]; u8 ctl_src_addr[ETH_ALEN]; @@ -301,6 +302,7 @@ struct fcoe_percpu_s { * @lport: The associated local port * @fcoe_pending_queue: The pending Rx queue of skbs * @fcoe_pending_queue_active: Indicates if the pending queue is active + * @priority: Packet priority (DCB) * @max_queue_depth: Max queue depth of pending queue * @min_queue_depth: Min queue depth of pending queue * @timer: The queue timer @@ -316,6 +318,7 @@ struct fcoe_port { struct fc_lport *lport; struct sk_buff_head fcoe_pending_queue; u8 fcoe_pending_queue_active; + u8 priority; u32 max_queue_depth; u32 min_queue_depth; struct timer_list timer; diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 669fbd6..d2d88be 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -241,24 +241,73 @@ TRACE_EVENT(rcu_fqs, /* * Tracepoint for dyntick-idle entry/exit events. These take a string - * as argument: "Start" for entering dyntick-idle mode and "End" for - * leaving it. + * as argument: "Start" for entering dyntick-idle mode, "End" for + * leaving it, "--=" for events moving towards idle, and "++=" for events + * moving away from idle. "Error on entry: not idle task" and "Error on + * exit: not idle task" indicate that a non-idle task is erroneously + * toying with the idle loop. + * + * These events also take a pair of numbers, which indicate the nesting + * depth before and after the event of interest. Note that task-related + * events use the upper bits of each number, while interrupt-related + * events use the lower bits. */ TRACE_EVENT(rcu_dyntick, - TP_PROTO(char *polarity), + TP_PROTO(char *polarity, long long oldnesting, long long newnesting), - TP_ARGS(polarity), + TP_ARGS(polarity, oldnesting, newnesting), TP_STRUCT__entry( __field(char *, polarity) + __field(long long, oldnesting) + __field(long long, newnesting) ), TP_fast_assign( __entry->polarity = polarity; + __entry->oldnesting = oldnesting; + __entry->newnesting = newnesting; + ), + + TP_printk("%s %llx %llx", __entry->polarity, + __entry->oldnesting, __entry->newnesting) +); + +/* + * Tracepoint for RCU preparation for idle, the goal being to get RCU + * processing done so that the current CPU can shut off its scheduling + * clock and enter dyntick-idle mode. One way to accomplish this is + * to drain all RCU callbacks from this CPU, and the other is to have + * done everything RCU requires for the current grace period. In this + * latter case, the CPU will be awakened at the end of the current grace + * period in order to process the remainder of its callbacks. + * + * These tracepoints take a string as argument: + * + * "No callbacks": Nothing to do, no callbacks on this CPU. + * "In holdoff": Nothing to do, holding off after unsuccessful attempt. + * "Begin holdoff": Attempt failed, don't retry until next jiffy. + * "Dyntick with callbacks": Entering dyntick-idle despite callbacks. + * "More callbacks": Still more callbacks, try again to clear them out. + * "Callbacks drained": All callbacks processed, off to dyntick idle! + * "Timer": Timer fired to cause CPU to continue processing callbacks. + */ +TRACE_EVENT(rcu_prep_idle, + + TP_PROTO(char *reason), + + TP_ARGS(reason), + + TP_STRUCT__entry( + __field(char *, reason) + ), + + TP_fast_assign( + __entry->reason = reason; ), - TP_printk("%s", __entry->polarity) + TP_printk("%s", __entry->reason) ); /* @@ -412,27 +461,71 @@ TRACE_EVENT(rcu_invoke_kfree_callback, /* * Tracepoint for exiting rcu_do_batch after RCU callbacks have been - * invoked. The first argument is the name of the RCU flavor and - * the second argument is number of callbacks actually invoked. + * invoked. The first argument is the name of the RCU flavor, + * the second argument is number of callbacks actually invoked, + * the third argument (cb) is whether or not any of the callbacks that + * were ready to invoke at the beginning of this batch are still + * queued, the fourth argument (nr) is the return value of need_resched(), + * the fifth argument (iit) is 1 if the current task is the idle task, + * and the sixth argument (risk) is the return value from + * rcu_is_callbacks_kthread(). */ TRACE_EVENT(rcu_batch_end, - TP_PROTO(char *rcuname, int callbacks_invoked), + TP_PROTO(char *rcuname, int callbacks_invoked, + bool cb, bool nr, bool iit, bool risk), - TP_ARGS(rcuname, callbacks_invoked), + TP_ARGS(rcuname, callbacks_invoked, cb, nr, iit, risk), TP_STRUCT__entry( __field(char *, rcuname) __field(int, callbacks_invoked) + __field(bool, cb) + __field(bool, nr) + __field(bool, iit) + __field(bool, risk) ), TP_fast_assign( __entry->rcuname = rcuname; __entry->callbacks_invoked = callbacks_invoked; + __entry->cb = cb; + __entry->nr = nr; + __entry->iit = iit; + __entry->risk = risk; + ), + + TP_printk("%s CBs-invoked=%d idle=%c%c%c%c", + __entry->rcuname, __entry->callbacks_invoked, + __entry->cb ? 'C' : '.', + __entry->nr ? 'S' : '.', + __entry->iit ? 'I' : '.', + __entry->risk ? 'R' : '.') +); + +/* + * Tracepoint for rcutorture readers. The first argument is the name + * of the RCU flavor from rcutorture's viewpoint and the second argument + * is the callback address. + */ +TRACE_EVENT(rcu_torture_read, + + TP_PROTO(char *rcutorturename, struct rcu_head *rhp), + + TP_ARGS(rcutorturename, rhp), + + TP_STRUCT__entry( + __field(char *, rcutorturename) + __field(struct rcu_head *, rhp) + ), + + TP_fast_assign( + __entry->rcutorturename = rcutorturename; + __entry->rhp = rhp; ), - TP_printk("%s CBs-invoked=%d", - __entry->rcuname, __entry->callbacks_invoked) + TP_printk("%s torture read %p", + __entry->rcutorturename, __entry->rhp) ); #else /* #ifdef CONFIG_RCU_TRACE */ @@ -443,13 +536,16 @@ TRACE_EVENT(rcu_batch_end, #define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0) #define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks) do { } while (0) #define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0) -#define trace_rcu_dyntick(polarity) do { } while (0) +#define trace_rcu_dyntick(polarity, oldnesting, newnesting) do { } while (0) +#define trace_rcu_prep_idle(reason) do { } while (0) #define trace_rcu_callback(rcuname, rhp, qlen) do { } while (0) #define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen) do { } while (0) #define trace_rcu_batch_start(rcuname, qlen, blimit) do { } while (0) #define trace_rcu_invoke_callback(rcuname, rhp) do { } while (0) #define trace_rcu_invoke_kfree_callback(rcuname, rhp, offset) do { } while (0) -#define trace_rcu_batch_end(rcuname, callbacks_invoked) do { } while (0) +#define trace_rcu_batch_end(rcuname, callbacks_invoked, cb, nr, iit, risk) \ + do { } while (0) +#define trace_rcu_torture_read(rcutorturename, rhp) do { } while (0) #endif /* #else #ifdef CONFIG_RCU_TRACE */ diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index b99caa8..99d1d0d 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -21,6 +21,16 @@ {I_REFERENCED, "I_REFERENCED"} \ ) +#define WB_WORK_REASON \ + {WB_REASON_BACKGROUND, "background"}, \ + {WB_REASON_TRY_TO_FREE_PAGES, "try_to_free_pages"}, \ + {WB_REASON_SYNC, "sync"}, \ + {WB_REASON_PERIODIC, "periodic"}, \ + {WB_REASON_LAPTOP_TIMER, "laptop_timer"}, \ + {WB_REASON_FREE_MORE_MEM, "free_more_memory"}, \ + {WB_REASON_FS_FREE_SPACE, "fs_free_space"}, \ + {WB_REASON_FORKER_THREAD, "forker_thread"} + struct wb_writeback_work; DECLARE_EVENT_CLASS(writeback_work_class, @@ -55,7 +65,7 @@ DECLARE_EVENT_CLASS(writeback_work_class, __entry->for_kupdate, __entry->range_cyclic, __entry->for_background, - wb_reason_name[__entry->reason] + __print_symbolic(__entry->reason, WB_WORK_REASON) ) ); #define DEFINE_WRITEBACK_WORK_EVENT(name) \ @@ -184,7 +194,8 @@ TRACE_EVENT(writeback_queue_io, __entry->older, /* older_than_this in jiffies */ __entry->age, /* older_than_this in relative milliseconds */ __entry->moved, - wb_reason_name[__entry->reason]) + __print_symbolic(__entry->reason, WB_WORK_REASON) + ) ); TRACE_EVENT(global_dirty_state, diff --git a/include/xen/interface/io/xs_wire.h b/include/xen/interface/io/xs_wire.h index f0b6890..f6f07aa 100644 --- a/include/xen/interface/io/xs_wire.h +++ b/include/xen/interface/io/xs_wire.h @@ -29,8 +29,7 @@ enum xsd_sockmsg_type XS_IS_DOMAIN_INTRODUCED, XS_RESUME, XS_SET_TARGET, - XS_RESTRICT, - XS_RESET_WATCHES + XS_RESTRICT }; #define XS_WRITE_NONE "NONE" diff --git a/init/Kconfig b/init/Kconfig index 43298f9..82b6a4c 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -469,14 +469,14 @@ config RCU_FANOUT_EXACT config RCU_FAST_NO_HZ bool "Accelerate last non-dyntick-idle CPU's grace periods" - depends on TREE_RCU && NO_HZ && SMP + depends on NO_HZ && SMP default n help This option causes RCU to attempt to accelerate grace periods - in order to allow the final CPU to enter dynticks-idle state - more quickly. On the other hand, this option increases the - overhead of the dynticks-idle checking, particularly on systems - with large numbers of CPUs. + in order to allow CPUs to enter dynticks-idle state more + quickly. On the other hand, this option increases the overhead + of the dynticks-idle checking, particularly on systems with + large numbers of CPUs. Say Y if energy efficiency is critically important, particularly if you have relatively few CPUs. diff --git a/init/main.c b/init/main.c index 217ed23..2c76efb 100644 --- a/init/main.c +++ b/init/main.c @@ -469,13 +469,12 @@ asmlinkage void __init start_kernel(void) char * command_line; extern const struct kernel_param __start___param[], __stop___param[]; - smp_setup_processor_id(); - /* * Need to run as early as possible, to initialize the * lockdep hash: */ lockdep_init(); + smp_setup_processor_id(); debug_objects_early_init(); /* diff --git a/kernel/cgroup.c b/kernel/cgroup.c index d9d5648..a184470 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2098,11 +2098,6 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) continue; /* get old css_set pointer */ task_lock(tsk); - if (tsk->flags & PF_EXITING) { - /* ignore this task if it's going away */ - task_unlock(tsk); - continue; - } oldcg = tsk->cgroups; get_css_set(oldcg); task_unlock(tsk); diff --git a/kernel/cpu.c b/kernel/cpu.c index 563f136..9d448dd 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -380,6 +380,7 @@ out: cpu_maps_update_done(); return err; } +EXPORT_SYMBOL_GPL(cpu_up); #ifdef CONFIG_PM_SLEEP_SMP static cpumask_var_t frozen_cpus; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 9fe58c4..0b1712d 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -123,6 +123,19 @@ static inline struct cpuset *task_cs(struct task_struct *task) struct cpuset, css); } +#ifdef CONFIG_NUMA +static inline bool task_has_mempolicy(struct task_struct *task) +{ + return task->mempolicy; +} +#else +static inline bool task_has_mempolicy(struct task_struct *task) +{ + return false; +} +#endif + + /* bits in struct cpuset flags field */ typedef enum { CS_CPU_EXCLUSIVE, @@ -949,7 +962,7 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, static void cpuset_change_task_nodemask(struct task_struct *tsk, nodemask_t *newmems) { - bool masks_disjoint = !nodes_intersects(*newmems, tsk->mems_allowed); + bool need_loop; repeat: /* @@ -962,6 +975,14 @@ repeat: return; task_lock(tsk); + /* + * Determine if a loop is necessary if another thread is doing + * get_mems_allowed(). If at least one node remains unchanged and + * tsk does not have a mempolicy, then an empty nodemask will not be + * possible when mems_allowed is larger than a word. + */ + need_loop = task_has_mempolicy(tsk) || + !nodes_intersects(*newmems, tsk->mems_allowed); nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1); @@ -981,11 +1002,9 @@ repeat: /* * Allocation of memory is very fast, we needn't sleep when waiting - * for the read-side. No wait is necessary, however, if at least one - * node remains unchanged. + * for the read-side. */ - while (masks_disjoint && - ACCESS_ONCE(tsk->mems_allowed_change_disable)) { + while (need_loop && ACCESS_ONCE(tsk->mems_allowed_change_disable)) { task_unlock(tsk); if (!task_curr(tsk)) yield(); diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index 5532dd3..7d6fb40 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -636,7 +636,7 @@ char kdb_task_state_char (const struct task_struct *p) (p->exit_state & EXIT_ZOMBIE) ? 'Z' : (p->exit_state & EXIT_DEAD) ? 'E' : (p->state & TASK_INTERRUPTIBLE) ? 'S' : '?'; - if (p->pid == 0) { + if (is_idle_task(p)) { /* Idle task. Is it really idle, apart from the kdb * interrupt? */ if (!kdb_task_has_cpu(p) || kgdb_info[cpu].irq_depth == 1) { diff --git a/kernel/events/core.c b/kernel/events/core.c index 2f8f3f1..890eb02 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -3360,9 +3360,13 @@ static void ring_buffer_wakeup(struct perf_event *event) rcu_read_lock(); rb = rcu_dereference(event->rb); - list_for_each_entry_rcu(event, &rb->event_list, rb_entry) { + if (!rb) + goto unlock; + + list_for_each_entry_rcu(event, &rb->event_list, rb_entry) wake_up_all(&event->waitq); - } + +unlock: rcu_read_unlock(); } @@ -5169,7 +5173,7 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer) regs = get_irq_regs(); if (regs && !perf_exclude_event(event, regs)) { - if (!(event->attr.exclude_idle && current->pid == 0)) + if (!(event->attr.exclude_idle && is_idle_task(current))) if (perf_event_overflow(event, &data, regs)) ret = HRTIMER_NORESTART; } diff --git a/kernel/exit.c b/kernel/exit.c index d0b7d98..e6e01b9 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -1540,8 +1540,15 @@ static int wait_consider_task(struct wait_opts *wo, int ptrace, } /* dead body doesn't have much to contribute */ - if (p->exit_state == EXIT_DEAD) + if (unlikely(p->exit_state == EXIT_DEAD)) { + /* + * But do not ignore this task until the tracer does + * wait_task_zombie()->do_notify_parent(). + */ + if (likely(!ptrace) && unlikely(ptrace_reparented(p))) + wo->notask_error = 0; return 0; + } /* slay zombie? */ if (p->exit_state == EXIT_ZOMBIE) { diff --git a/kernel/futex.c b/kernel/futex.c index ea87f4d..1614be2 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -314,17 +314,29 @@ again: #endif lock_page(page_head); + + /* + * If page_head->mapping is NULL, then it cannot be a PageAnon + * page; but it might be the ZERO_PAGE or in the gate area or + * in a special mapping (all cases which we are happy to fail); + * or it may have been a good file page when get_user_pages_fast + * found it, but truncated or holepunched or subjected to + * invalidate_complete_page2 before we got the page lock (also + * cases which we are happy to fail). And we hold a reference, + * so refcount care in invalidate_complete_page's remove_mapping + * prevents drop_caches from setting mapping to NULL beneath us. + * + * The case we do have to guard against is when memory pressure made + * shmem_writepage move it from filecache to swapcache beneath us: + * an unlikely race, but we do need to retry for page_head->mapping. + */ if (!page_head->mapping) { + int shmem_swizzled = PageSwapCache(page_head); unlock_page(page_head); put_page(page_head); - /* - * ZERO_PAGE pages don't have a mapping. Avoid a busy loop - * trying to find one. RW mapping would have COW'd (and thus - * have a mapping) so this page is RO and won't ever change. - */ - if ((page_head == ZERO_PAGE(address))) - return -EFAULT; - goto again; + if (shmem_swizzled) + goto again; + return -EFAULT; } /* diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 8b1748d..2e48ec0 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -74,11 +74,17 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) /* * Ensure the task is not frozen. - * Also, when a freshly created task is scheduled once, changes - * its state to TASK_UNINTERRUPTIBLE without having ever been - * switched out once, it musn't be checked. + * Also, skip vfork and any other user process that freezer should skip. */ - if (unlikely(t->flags & PF_FROZEN || !switch_count)) + if (unlikely(t->flags & (PF_FROZEN | PF_FREEZER_SKIP))) + return; + + /* + * When a freshly created task is scheduled once, changes its state to + * TASK_UNINTERRUPTIBLE without having ever been switched out once, it + * musn't be checked. + */ + if (unlikely(!switch_count)) return; if (switch_count != t->last_switch_count) { diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 24f176c..8889f7d 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -431,6 +431,7 @@ unsigned int max_lockdep_depth; * about it later on, in lockdep_info(). */ static int lockdep_init_error; +static const char *lock_init_error; static unsigned long lockdep_init_trace_data[20]; static struct stack_trace lockdep_init_trace = { .max_entries = ARRAY_SIZE(lockdep_init_trace_data), @@ -564,11 +565,12 @@ static void lockdep_print_held_locks(struct task_struct *curr) } } -static void print_kernel_version(void) +static void print_kernel_ident(void) { - printk("%s %.*s\n", init_utsname()->release, + printk("%s %.*s %s\n", init_utsname()->release, (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); + init_utsname()->version, + print_tainted()); } static int very_verbose(struct lock_class *class) @@ -652,6 +654,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) if (unlikely(!lockdep_initialized)) { lockdep_init(); lockdep_init_error = 1; + lock_init_error = lock->name; save_stack_trace(&lockdep_init_trace); } #endif @@ -719,7 +722,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) class = look_up_lock_class(lock, subclass); if (likely(class)) - return class; + goto out_set_class_cache; /* * Debug-check: all keys must be persistent! @@ -804,6 +807,7 @@ out_unlock_set: graph_unlock(); raw_local_irq_restore(flags); +out_set_class_cache: if (!subclass || force) lock->class_cache[0] = class; else if (subclass < NR_LOCKDEP_CACHING_CLASSES) @@ -1145,7 +1149,7 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth, printk("\n"); printk("======================================================\n"); printk("[ INFO: possible circular locking dependency detected ]\n"); - print_kernel_version(); + print_kernel_ident(); printk("-------------------------------------------------------\n"); printk("%s/%d is trying to acquire lock:\n", curr->comm, task_pid_nr(curr)); @@ -1484,7 +1488,7 @@ print_bad_irq_dependency(struct task_struct *curr, printk("======================================================\n"); printk("[ INFO: %s-safe -> %s-unsafe lock order detected ]\n", irqclass, irqclass); - print_kernel_version(); + print_kernel_ident(); printk("------------------------------------------------------\n"); printk("%s/%d [HC%u[%lu]:SC%u[%lu]:HE%u:SE%u] is trying to acquire:\n", curr->comm, task_pid_nr(curr), @@ -1713,7 +1717,7 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev, printk("\n"); printk("=============================================\n"); printk("[ INFO: possible recursive locking detected ]\n"); - print_kernel_version(); + print_kernel_ident(); printk("---------------------------------------------\n"); printk("%s/%d is trying to acquire lock:\n", curr->comm, task_pid_nr(curr)); @@ -2220,7 +2224,7 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this, printk("\n"); printk("=================================\n"); printk("[ INFO: inconsistent lock state ]\n"); - print_kernel_version(); + print_kernel_ident(); printk("---------------------------------\n"); printk("inconsistent {%s} -> {%s} usage.\n", @@ -2285,7 +2289,7 @@ print_irq_inversion_bug(struct task_struct *curr, printk("\n"); printk("=========================================================\n"); printk("[ INFO: possible irq lock inversion dependency detected ]\n"); - print_kernel_version(); + print_kernel_ident(); printk("---------------------------------------------------------\n"); printk("%s/%d just changed the state of lock:\n", curr->comm, task_pid_nr(curr)); @@ -3171,6 +3175,7 @@ print_unlock_inbalance_bug(struct task_struct *curr, struct lockdep_map *lock, printk("\n"); printk("=====================================\n"); printk("[ BUG: bad unlock balance detected! ]\n"); + print_kernel_ident(); printk("-------------------------------------\n"); printk("%s/%d is trying to release lock (", curr->comm, task_pid_nr(curr)); @@ -3615,6 +3620,7 @@ print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock, printk("\n"); printk("=================================\n"); printk("[ BUG: bad contention detected! ]\n"); + print_kernel_ident(); printk("---------------------------------\n"); printk("%s/%d is trying to contend lock (", curr->comm, task_pid_nr(curr)); @@ -3970,7 +3976,8 @@ void __init lockdep_info(void) #ifdef CONFIG_DEBUG_LOCKDEP if (lockdep_init_error) { - printk("WARNING: lockdep init error! Arch code didn't call lockdep_init() early enough?\n"); + printk("WARNING: lockdep init error! lock-%s was acquired" + "before lockdep_init\n", lock_init_error); printk("Call stack leading to lockdep invocation was:\n"); print_stack_trace(&lockdep_init_trace, 0); } @@ -3989,6 +3996,7 @@ print_freed_lock_bug(struct task_struct *curr, const void *mem_from, printk("\n"); printk("=========================\n"); printk("[ BUG: held lock freed! ]\n"); + print_kernel_ident(); printk("-------------------------\n"); printk("%s/%d is freeing memory %p-%p, with a lock still held there!\n", curr->comm, task_pid_nr(curr), mem_from, mem_to-1); @@ -4046,6 +4054,7 @@ static void print_held_locks_bug(struct task_struct *curr) printk("\n"); printk("=====================================\n"); printk("[ BUG: lock held at task exit time! ]\n"); + print_kernel_ident(); printk("-------------------------------------\n"); printk("%s/%d is exiting with locks still held!\n", curr->comm, task_pid_nr(curr)); @@ -4143,6 +4152,7 @@ void lockdep_sys_exit(void) printk("\n"); printk("================================================\n"); printk("[ BUG: lock held when returning to user space! ]\n"); + print_kernel_ident(); printk("------------------------------------------------\n"); printk("%s/%d is leaving the kernel with locks still held!\n", curr->comm, curr->pid); @@ -4162,10 +4172,33 @@ void lockdep_rcu_suspicious(const char *file, const int line, const char *s) printk("\n"); printk("===============================\n"); printk("[ INFO: suspicious RCU usage. ]\n"); + print_kernel_ident(); printk("-------------------------------\n"); printk("%s:%d %s!\n", file, line, s); printk("\nother info that might help us debug this:\n\n"); printk("\nrcu_scheduler_active = %d, debug_locks = %d\n", rcu_scheduler_active, debug_locks); + + /* + * If a CPU is in the RCU-free window in idle (ie: in the section + * between rcu_idle_enter() and rcu_idle_exit(), then RCU + * considers that CPU to be in an "extended quiescent state", + * which means that RCU will be completely ignoring that CPU. + * Therefore, rcu_read_lock() and friends have absolutely no + * effect on a CPU running in that state. In other words, even if + * such an RCU-idle CPU has called rcu_read_lock(), RCU might well + * delete data structures out from under it. RCU really has no + * choice here: we need to keep an RCU-free window in idle where + * the CPU may possibly enter into low power mode. This way we can + * notice an extended quiescent state to other CPUs that started a grace + * period. Otherwise we would delay any grace period as long as we run + * in the idle task. + * + * So complain bitterly if someone does call rcu_read_lock(), + * rcu_read_lock_bh() and so on from extended quiescent states. + */ + if (rcu_is_cpu_idle()) + printk("RCU used illegally from extended quiescent state!\n"); + lockdep_print_held_locks(curr); printk("\nstack backtrace:\n"); dump_stack(); diff --git a/kernel/panic.c b/kernel/panic.c index b2659360..3458469 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -237,11 +237,20 @@ void add_taint(unsigned flag) * Can't trust the integrity of the kernel anymore. * We don't call directly debug_locks_off() because the issue * is not necessarily serious enough to set oops_in_progress to 1 - * Also we want to keep up lockdep for staging development and - * post-warning case. + * Also we want to keep up lockdep for staging/out-of-tree + * development and post-warning case. */ - if (flag != TAINT_CRAP && flag != TAINT_WARN && __debug_locks_off()) - printk(KERN_WARNING "Disabling lock debugging due to kernel taint\n"); + switch (flag) { + case TAINT_CRAP: + case TAINT_OOT_MODULE: + case TAINT_WARN: + case TAINT_FIRMWARE_WORKAROUND: + break; + + default: + if (__debug_locks_off()) + printk(KERN_WARNING "Disabling lock debugging due to kernel taint\n"); + } set_bit(flag, &tainted_mask); } diff --git a/kernel/printk.c b/kernel/printk.c index 7982a0a..989e4a5 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -199,7 +199,7 @@ void __init setup_log_buf(int early) unsigned long mem; mem = memblock_alloc(new_log_buf_len, PAGE_SIZE); - if (mem == MEMBLOCK_ERROR) + if (!mem) return; new_log_buf = __va(mem); } else { @@ -688,6 +688,7 @@ static void zap_locks(void) oops_timestamp = jiffies; + debug_locks_off(); /* If a crash is occurring, make sure we can't deadlock */ raw_spin_lock_init(&logbuf_lock); /* And make sure that we print immediately */ @@ -840,9 +841,8 @@ asmlinkage int vprintk(const char *fmt, va_list args) boot_delay_msec(); printk_delay(); - preempt_disable(); /* This stops the holder of console_sem just where we want him */ - raw_local_irq_save(flags); + local_irq_save(flags); this_cpu = smp_processor_id(); /* @@ -856,7 +856,7 @@ asmlinkage int vprintk(const char *fmt, va_list args) * recursion and return - but flag the recursion so that * it can be printed at the next appropriate moment: */ - if (!oops_in_progress) { + if (!oops_in_progress && !lockdep_recursing(current)) { recursion_bug = 1; goto out_restore_irqs; } @@ -962,9 +962,8 @@ asmlinkage int vprintk(const char *fmt, va_list args) lockdep_on(); out_restore_irqs: - raw_local_irq_restore(flags); + local_irq_restore(flags); - preempt_enable(); return printed_len; } EXPORT_SYMBOL(printk); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 24d0447..78ab24a 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -96,9 +96,20 @@ void __ptrace_unlink(struct task_struct *child) */ if (!(child->flags & PF_EXITING) && (child->signal->flags & SIGNAL_STOP_STOPPED || - child->signal->group_stop_count)) + child->signal->group_stop_count)) { child->jobctl |= JOBCTL_STOP_PENDING; + /* + * This is only possible if this thread was cloned by the + * traced task running in the stopped group, set the signal + * for the future reports. + * FIXME: we should change ptrace_init_task() to handle this + * case. + */ + if (!(child->jobctl & JOBCTL_STOP_SIGMASK)) + child->jobctl |= SIGSTOP; + } + /* * If transition to TASK_STOPPED is pending or in TASK_TRACED, kick * @child in the butt. Note that @resume should be used iff @child diff --git a/kernel/rcu.h b/kernel/rcu.h index f600868..aa88baa 100644 --- a/kernel/rcu.h +++ b/kernel/rcu.h @@ -30,6 +30,13 @@ #endif /* #else #ifdef CONFIG_RCU_TRACE */ /* + * Process-level increment to ->dynticks_nesting field. This allows for + * architectures that use half-interrupts and half-exceptions from + * process context. + */ +#define DYNTICK_TASK_NESTING (LLONG_MAX / 2 - 1) + +/* * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally * by call_rcu() and rcu callback execution, and are therefore not part of the * RCU API. Leaving in rcupdate.h because they are used by all RCU flavors. diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index c5b98e5..2bc4e13 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -93,6 +93,8 @@ int rcu_read_lock_bh_held(void) { if (!debug_lockdep_rcu_enabled()) return 1; + if (rcu_is_cpu_idle()) + return 0; return in_softirq() || irqs_disabled(); } EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); @@ -316,3 +318,13 @@ struct debug_obj_descr rcuhead_debug_descr = { }; EXPORT_SYMBOL_GPL(rcuhead_debug_descr); #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */ + +#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) || defined(CONFIG_RCU_TRACE) +void do_trace_rcu_torture_read(char *rcutorturename, struct rcu_head *rhp) +{ + trace_rcu_torture_read(rcutorturename, rhp); +} +EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read); +#else +#define do_trace_rcu_torture_read(rcutorturename, rhp) do { } while (0) +#endif diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 636af6d..977296d 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -53,31 +53,137 @@ static void __call_rcu(struct rcu_head *head, #include "rcutiny_plugin.h" -#ifdef CONFIG_NO_HZ +static long long rcu_dynticks_nesting = DYNTICK_TASK_NESTING; -static long rcu_dynticks_nesting = 1; +/* Common code for rcu_idle_enter() and rcu_irq_exit(), see kernel/rcutree.c. */ +static void rcu_idle_enter_common(long long oldval) +{ + if (rcu_dynticks_nesting) { + RCU_TRACE(trace_rcu_dyntick("--=", + oldval, rcu_dynticks_nesting)); + return; + } + RCU_TRACE(trace_rcu_dyntick("Start", oldval, rcu_dynticks_nesting)); + if (!is_idle_task(current)) { + struct task_struct *idle = idle_task(smp_processor_id()); + + RCU_TRACE(trace_rcu_dyntick("Error on entry: not idle task", + oldval, rcu_dynticks_nesting)); + ftrace_dump(DUMP_ALL); + WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", + current->pid, current->comm, + idle->pid, idle->comm); /* must be idle task! */ + } + rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */ +} /* - * Enter dynticks-idle mode, which is an extended quiescent state - * if we have fully entered that mode (i.e., if the new value of - * dynticks_nesting is zero). + * Enter idle, which is an extended quiescent state if we have fully + * entered that mode (i.e., if the new value of dynticks_nesting is zero). */ -void rcu_enter_nohz(void) +void rcu_idle_enter(void) { - if (--rcu_dynticks_nesting == 0) - rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */ + unsigned long flags; + long long oldval; + + local_irq_save(flags); + oldval = rcu_dynticks_nesting; + rcu_dynticks_nesting = 0; + rcu_idle_enter_common(oldval); + local_irq_restore(flags); } /* - * Exit dynticks-idle mode, so that we are no longer in an extended - * quiescent state. + * Exit an interrupt handler towards idle. */ -void rcu_exit_nohz(void) +void rcu_irq_exit(void) +{ + unsigned long flags; + long long oldval; + + local_irq_save(flags); + oldval = rcu_dynticks_nesting; + rcu_dynticks_nesting--; + WARN_ON_ONCE(rcu_dynticks_nesting < 0); + rcu_idle_enter_common(oldval); + local_irq_restore(flags); +} + +/* Common code for rcu_idle_exit() and rcu_irq_enter(), see kernel/rcutree.c. */ +static void rcu_idle_exit_common(long long oldval) { + if (oldval) { + RCU_TRACE(trace_rcu_dyntick("++=", + oldval, rcu_dynticks_nesting)); + return; + } + RCU_TRACE(trace_rcu_dyntick("End", oldval, rcu_dynticks_nesting)); + if (!is_idle_task(current)) { + struct task_struct *idle = idle_task(smp_processor_id()); + + RCU_TRACE(trace_rcu_dyntick("Error on exit: not idle task", + oldval, rcu_dynticks_nesting)); + ftrace_dump(DUMP_ALL); + WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", + current->pid, current->comm, + idle->pid, idle->comm); /* must be idle task! */ + } +} + +/* + * Exit idle, so that we are no longer in an extended quiescent state. + */ +void rcu_idle_exit(void) +{ + unsigned long flags; + long long oldval; + + local_irq_save(flags); + oldval = rcu_dynticks_nesting; + WARN_ON_ONCE(oldval != 0); + rcu_dynticks_nesting = DYNTICK_TASK_NESTING; + rcu_idle_exit_common(oldval); + local_irq_restore(flags); +} + +/* + * Enter an interrupt handler, moving away from idle. + */ +void rcu_irq_enter(void) +{ + unsigned long flags; + long long oldval; + + local_irq_save(flags); + oldval = rcu_dynticks_nesting; rcu_dynticks_nesting++; + WARN_ON_ONCE(rcu_dynticks_nesting == 0); + rcu_idle_exit_common(oldval); + local_irq_restore(flags); +} + +#ifdef CONFIG_PROVE_RCU + +/* + * Test whether RCU thinks that the current CPU is idle. + */ +int rcu_is_cpu_idle(void) +{ + return !rcu_dynticks_nesting; } +EXPORT_SYMBOL(rcu_is_cpu_idle); + +#endif /* #ifdef CONFIG_PROVE_RCU */ -#endif /* #ifdef CONFIG_NO_HZ */ +/* + * Test whether the current CPU was interrupted from idle. Nested + * interrupts don't count, we must be running at the first interrupt + * level. + */ +int rcu_is_cpu_rrupt_from_idle(void) +{ + return rcu_dynticks_nesting <= 0; +} /* * Helper function for rcu_sched_qs() and rcu_bh_qs(). @@ -126,14 +232,13 @@ void rcu_bh_qs(int cpu) /* * Check to see if the scheduling-clock interrupt came from an extended - * quiescent state, and, if so, tell RCU about it. + * quiescent state, and, if so, tell RCU about it. This function must + * be called from hardirq context. It is normally called from the + * scheduling-clock interrupt. */ void rcu_check_callbacks(int cpu, int user) { - if (user || - (idle_cpu(cpu) && - !in_softirq() && - hardirq_count() <= (1 << HARDIRQ_SHIFT))) + if (user || rcu_is_cpu_rrupt_from_idle()) rcu_sched_qs(cpu); else if (!in_softirq()) rcu_bh_qs(cpu); @@ -154,7 +259,11 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) /* If no RCU callbacks ready to invoke, just return. */ if (&rcp->rcucblist == rcp->donetail) { RCU_TRACE(trace_rcu_batch_start(rcp->name, 0, -1)); - RCU_TRACE(trace_rcu_batch_end(rcp->name, 0)); + RCU_TRACE(trace_rcu_batch_end(rcp->name, 0, + ACCESS_ONCE(rcp->rcucblist), + need_resched(), + is_idle_task(current), + rcu_is_callbacks_kthread())); return; } @@ -183,7 +292,9 @@ static void __rcu_process_callbacks(struct rcu_ctrlblk *rcp) RCU_TRACE(cb_count++); } RCU_TRACE(rcu_trace_sub_qlen(rcp, cb_count)); - RCU_TRACE(trace_rcu_batch_end(rcp->name, cb_count)); + RCU_TRACE(trace_rcu_batch_end(rcp->name, cb_count, 0, need_resched(), + is_idle_task(current), + rcu_is_callbacks_kthread())); } static void rcu_process_callbacks(struct softirq_action *unused) diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index 2b0484a..9cb1ae4 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -312,8 +312,8 @@ static int rcu_boost(void) rt_mutex_lock(&mtx); rt_mutex_unlock(&mtx); /* Keep lockdep happy. */ - return rcu_preempt_ctrlblk.boost_tasks != NULL || - rcu_preempt_ctrlblk.exp_tasks != NULL; + return ACCESS_ONCE(rcu_preempt_ctrlblk.boost_tasks) != NULL || + ACCESS_ONCE(rcu_preempt_ctrlblk.exp_tasks) != NULL; } /* @@ -885,6 +885,19 @@ static void invoke_rcu_callbacks(void) wake_up(&rcu_kthread_wq); } +#ifdef CONFIG_RCU_TRACE + +/* + * Is the current CPU running the RCU-callbacks kthread? + * Caller must have preemption disabled. + */ +static bool rcu_is_callbacks_kthread(void) +{ + return rcu_kthread_task == current; +} + +#endif /* #ifdef CONFIG_RCU_TRACE */ + /* * This kthread invokes RCU callbacks whose grace periods have * elapsed. It is awakened as needed, and takes the place of the @@ -938,6 +951,18 @@ void invoke_rcu_callbacks(void) raise_softirq(RCU_SOFTIRQ); } +#ifdef CONFIG_RCU_TRACE + +/* + * There is no callback kthread, so this thread is never it. + */ +static bool rcu_is_callbacks_kthread(void) +{ + return false; +} + +#endif /* #ifdef CONFIG_RCU_TRACE */ + void rcu_init(void) { open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 764825c..88f17b8 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -61,9 +61,11 @@ static int test_no_idle_hz; /* Test RCU's support for tickless idle CPUs. */ static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/ static int stutter = 5; /* Start/stop testing interval (in sec) */ static int irqreader = 1; /* RCU readers from irq (timers). */ -static int fqs_duration = 0; /* Duration of bursts (us), 0 to disable. */ -static int fqs_holdoff = 0; /* Hold time within burst (us). */ +static int fqs_duration; /* Duration of bursts (us), 0 to disable. */ +static int fqs_holdoff; /* Hold time within burst (us). */ static int fqs_stutter = 3; /* Wait time between bursts (s). */ +static int onoff_interval; /* Wait time between CPU hotplugs, 0=disable. */ +static int shutdown_secs; /* Shutdown time (s). <=0 for no shutdown. */ static int test_boost = 1; /* Test RCU prio boost: 0=no, 1=maybe, 2=yes. */ static int test_boost_interval = 7; /* Interval between boost tests, seconds. */ static int test_boost_duration = 4; /* Duration of each boost test, seconds. */ @@ -91,6 +93,10 @@ module_param(fqs_holdoff, int, 0444); MODULE_PARM_DESC(fqs_holdoff, "Holdoff time within fqs bursts (us)"); module_param(fqs_stutter, int, 0444); MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)"); +module_param(onoff_interval, int, 0444); +MODULE_PARM_DESC(onoff_interval, "Time between CPU hotplugs (s), 0=disable"); +module_param(shutdown_secs, int, 0444); +MODULE_PARM_DESC(shutdown_secs, "Shutdown time (s), zero to disable."); module_param(test_boost, int, 0444); MODULE_PARM_DESC(test_boost, "Test RCU prio boost: 0=no, 1=maybe, 2=yes."); module_param(test_boost_interval, int, 0444); @@ -119,6 +125,10 @@ static struct task_struct *shuffler_task; static struct task_struct *stutter_task; static struct task_struct *fqs_task; static struct task_struct *boost_tasks[NR_CPUS]; +static struct task_struct *shutdown_task; +#ifdef CONFIG_HOTPLUG_CPU +static struct task_struct *onoff_task; +#endif /* #ifdef CONFIG_HOTPLUG_CPU */ #define RCU_TORTURE_PIPE_LEN 10 @@ -149,6 +159,10 @@ static long n_rcu_torture_boost_rterror; static long n_rcu_torture_boost_failure; static long n_rcu_torture_boosts; static long n_rcu_torture_timers; +static long n_offline_attempts; +static long n_offline_successes; +static long n_online_attempts; +static long n_online_successes; static struct list_head rcu_torture_removed; static cpumask_var_t shuffle_tmp_mask; @@ -160,6 +174,8 @@ static int stutter_pause_test; #define RCUTORTURE_RUNNABLE_INIT 0 #endif int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT; +module_param(rcutorture_runnable, int, 0444); +MODULE_PARM_DESC(rcutorture_runnable, "Start rcutorture at boot"); #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) #define rcu_can_boost() 1 @@ -167,6 +183,7 @@ int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT; #define rcu_can_boost() 0 #endif /* #else #if defined(CONFIG_RCU_BOOST) && !defined(CONFIG_HOTPLUG_CPU) */ +static unsigned long shutdown_time; /* jiffies to system shutdown. */ static unsigned long boost_starttime; /* jiffies of next boost test start. */ DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ /* and boost task create/destroy. */ @@ -182,6 +199,9 @@ static int fullstop = FULLSTOP_RMMOD; */ static DEFINE_MUTEX(fullstop_mutex); +/* Forward reference. */ +static void rcu_torture_cleanup(void); + /* * Detect and respond to a system shutdown. */ @@ -612,6 +632,30 @@ static struct rcu_torture_ops srcu_ops = { .name = "srcu" }; +static int srcu_torture_read_lock_raw(void) __acquires(&srcu_ctl) +{ + return srcu_read_lock_raw(&srcu_ctl); +} + +static void srcu_torture_read_unlock_raw(int idx) __releases(&srcu_ctl) +{ + srcu_read_unlock_raw(&srcu_ctl, idx); +} + +static struct rcu_torture_ops srcu_raw_ops = { + .init = srcu_torture_init, + .cleanup = srcu_torture_cleanup, + .readlock = srcu_torture_read_lock_raw, + .read_delay = srcu_read_delay, + .readunlock = srcu_torture_read_unlock_raw, + .completed = srcu_torture_completed, + .deferred_free = rcu_sync_torture_deferred_free, + .sync = srcu_torture_synchronize, + .cb_barrier = NULL, + .stats = srcu_torture_stats, + .name = "srcu_raw" +}; + static void srcu_torture_synchronize_expedited(void) { synchronize_srcu_expedited(&srcu_ctl); @@ -913,6 +957,18 @@ rcu_torture_fakewriter(void *arg) return 0; } +void rcutorture_trace_dump(void) +{ + static atomic_t beenhere = ATOMIC_INIT(0); + + if (atomic_read(&beenhere)) + return; + if (atomic_xchg(&beenhere, 1) != 0) + return; + do_trace_rcu_torture_read(cur_ops->name, (struct rcu_head *)~0UL); + ftrace_dump(DUMP_ALL); +} + /* * RCU torture reader from timer handler. Dereferences rcu_torture_current, * incrementing the corresponding element of the pipeline array. The @@ -934,6 +990,7 @@ static void rcu_torture_timer(unsigned long unused) rcu_read_lock_bh_held() || rcu_read_lock_sched_held() || srcu_read_lock_held(&srcu_ctl)); + do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu); if (p == NULL) { /* Leave because rcu_torture_writer is not yet underway */ cur_ops->readunlock(idx); @@ -951,6 +1008,8 @@ static void rcu_torture_timer(unsigned long unused) /* Should not happen, but... */ pipe_count = RCU_TORTURE_PIPE_LEN; } + if (pipe_count > 1) + rcutorture_trace_dump(); __this_cpu_inc(rcu_torture_count[pipe_count]); completed = cur_ops->completed() - completed; if (completed > RCU_TORTURE_PIPE_LEN) { @@ -994,6 +1053,7 @@ rcu_torture_reader(void *arg) rcu_read_lock_bh_held() || rcu_read_lock_sched_held() || srcu_read_lock_held(&srcu_ctl)); + do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu); if (p == NULL) { /* Wait for rcu_torture_writer to get underway */ cur_ops->readunlock(idx); @@ -1009,6 +1069,8 @@ rcu_torture_reader(void *arg) /* Should not happen, but... */ pipe_count = RCU_TORTURE_PIPE_LEN; } + if (pipe_count > 1) + rcutorture_trace_dump(); __this_cpu_inc(rcu_torture_count[pipe_count]); completed = cur_ops->completed() - completed; if (completed > RCU_TORTURE_PIPE_LEN) { @@ -1056,7 +1118,8 @@ rcu_torture_printk(char *page) cnt += sprintf(&page[cnt], "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d " "rtmbe: %d rtbke: %ld rtbre: %ld " - "rtbf: %ld rtb: %ld nt: %ld", + "rtbf: %ld rtb: %ld nt: %ld " + "onoff: %ld/%ld:%ld/%ld", rcu_torture_current, rcu_torture_current_version, list_empty(&rcu_torture_freelist), @@ -1068,7 +1131,11 @@ rcu_torture_printk(char *page) n_rcu_torture_boost_rterror, n_rcu_torture_boost_failure, n_rcu_torture_boosts, - n_rcu_torture_timers); + n_rcu_torture_timers, + n_online_successes, + n_online_attempts, + n_offline_successes, + n_offline_attempts); if (atomic_read(&n_rcu_torture_mberror) != 0 || n_rcu_torture_boost_ktrerror != 0 || n_rcu_torture_boost_rterror != 0 || @@ -1232,12 +1299,14 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, char *tag) "shuffle_interval=%d stutter=%d irqreader=%d " "fqs_duration=%d fqs_holdoff=%d fqs_stutter=%d " "test_boost=%d/%d test_boost_interval=%d " - "test_boost_duration=%d\n", + "test_boost_duration=%d shutdown_secs=%d " + "onoff_interval=%d\n", torture_type, tag, nrealreaders, nfakewriters, stat_interval, verbose, test_no_idle_hz, shuffle_interval, stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter, test_boost, cur_ops->can_boost, - test_boost_interval, test_boost_duration); + test_boost_interval, test_boost_duration, shutdown_secs, + onoff_interval); } static struct notifier_block rcutorture_shutdown_nb = { @@ -1287,6 +1356,131 @@ static int rcutorture_booster_init(int cpu) return 0; } +/* + * Cause the rcutorture test to shutdown the system after the test has + * run for the time specified by the shutdown_secs module parameter. + */ +static int +rcu_torture_shutdown(void *arg) +{ + long delta; + unsigned long jiffies_snap; + + VERBOSE_PRINTK_STRING("rcu_torture_shutdown task started"); + jiffies_snap = ACCESS_ONCE(jiffies); + while (ULONG_CMP_LT(jiffies_snap, shutdown_time) && + !kthread_should_stop()) { + delta = shutdown_time - jiffies_snap; + if (verbose) + printk(KERN_ALERT "%s" TORTURE_FLAG + "rcu_torture_shutdown task: %lu " + "jiffies remaining\n", + torture_type, delta); + schedule_timeout_interruptible(delta); + jiffies_snap = ACCESS_ONCE(jiffies); + } + if (kthread_should_stop()) { + VERBOSE_PRINTK_STRING("rcu_torture_shutdown task stopping"); + return 0; + } + + /* OK, shut down the system. */ + + VERBOSE_PRINTK_STRING("rcu_torture_shutdown task shutting down system"); + shutdown_task = NULL; /* Avoid self-kill deadlock. */ + rcu_torture_cleanup(); /* Get the success/failure message. */ + kernel_power_off(); /* Shut down the system. */ + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU + +/* + * Execute random CPU-hotplug operations at the interval specified + * by the onoff_interval. + */ +static int +rcu_torture_onoff(void *arg) +{ + int cpu; + int maxcpu = -1; + DEFINE_RCU_RANDOM(rand); + + VERBOSE_PRINTK_STRING("rcu_torture_onoff task started"); + for_each_online_cpu(cpu) + maxcpu = cpu; + WARN_ON(maxcpu < 0); + while (!kthread_should_stop()) { + cpu = (rcu_random(&rand) >> 4) % (maxcpu + 1); + if (cpu_online(cpu) && cpu_is_hotpluggable(cpu)) { + if (verbose) + printk(KERN_ALERT "%s" TORTURE_FLAG + "rcu_torture_onoff task: offlining %d\n", + torture_type, cpu); + n_offline_attempts++; + if (cpu_down(cpu) == 0) { + if (verbose) + printk(KERN_ALERT "%s" TORTURE_FLAG + "rcu_torture_onoff task: " + "offlined %d\n", + torture_type, cpu); + n_offline_successes++; + } + } else if (cpu_is_hotpluggable(cpu)) { + if (verbose) + printk(KERN_ALERT "%s" TORTURE_FLAG + "rcu_torture_onoff task: onlining %d\n", + torture_type, cpu); + n_online_attempts++; + if (cpu_up(cpu) == 0) { + if (verbose) + printk(KERN_ALERT "%s" TORTURE_FLAG + "rcu_torture_onoff task: " + "onlined %d\n", + torture_type, cpu); + n_online_successes++; + } + } + schedule_timeout_interruptible(onoff_interval * HZ); + } + VERBOSE_PRINTK_STRING("rcu_torture_onoff task stopping"); + return 0; +} + +static int +rcu_torture_onoff_init(void) +{ + if (onoff_interval <= 0) + return 0; + onoff_task = kthread_run(rcu_torture_onoff, NULL, "rcu_torture_onoff"); + if (IS_ERR(onoff_task)) { + onoff_task = NULL; + return PTR_ERR(onoff_task); + } + return 0; +} + +static void rcu_torture_onoff_cleanup(void) +{ + if (onoff_task == NULL) + return; + VERBOSE_PRINTK_STRING("Stopping rcu_torture_onoff task"); + kthread_stop(onoff_task); +} + +#else /* #ifdef CONFIG_HOTPLUG_CPU */ + +static void +rcu_torture_onoff_init(void) +{ +} + +static void rcu_torture_onoff_cleanup(void) +{ +} + +#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */ + static int rcutorture_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -1391,6 +1585,11 @@ rcu_torture_cleanup(void) for_each_possible_cpu(i) rcutorture_booster_cleanup(i); } + if (shutdown_task != NULL) { + VERBOSE_PRINTK_STRING("Stopping rcu_torture_shutdown task"); + kthread_stop(shutdown_task); + } + rcu_torture_onoff_cleanup(); /* Wait for all RCU callbacks to fire. */ @@ -1416,7 +1615,7 @@ rcu_torture_init(void) static struct rcu_torture_ops *torture_ops[] = { &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops, &rcu_bh_ops, &rcu_bh_sync_ops, &rcu_bh_expedited_ops, - &srcu_ops, &srcu_expedited_ops, + &srcu_ops, &srcu_raw_ops, &srcu_expedited_ops, &sched_ops, &sched_sync_ops, &sched_expedited_ops, }; mutex_lock(&fullstop_mutex); @@ -1607,6 +1806,18 @@ rcu_torture_init(void) } } } + if (shutdown_secs > 0) { + shutdown_time = jiffies + shutdown_secs * HZ; + shutdown_task = kthread_run(rcu_torture_shutdown, NULL, + "rcu_torture_shutdown"); + if (IS_ERR(shutdown_task)) { + firsterr = PTR_ERR(shutdown_task); + VERBOSE_PRINTK_ERRSTRING("Failed to create shutdown"); + shutdown_task = NULL; + goto unwind; + } + } + rcu_torture_onoff_init(); register_reboot_notifier(&rcutorture_shutdown_nb); rcutorture_record_test_transition(); mutex_unlock(&fullstop_mutex); diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 6b76d81..6c4a672 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -69,7 +69,7 @@ static struct lock_class_key rcu_node_class[NUM_RCU_LVLS]; NUM_RCU_LVL_3, \ NUM_RCU_LVL_4, /* == MAX_RCU_LVLS */ \ }, \ - .signaled = RCU_GP_IDLE, \ + .fqs_state = RCU_GP_IDLE, \ .gpnum = -300, \ .completed = -300, \ .onofflock = __RAW_SPIN_LOCK_UNLOCKED(&structname##_state.onofflock), \ @@ -195,12 +195,10 @@ void rcu_note_context_switch(int cpu) } EXPORT_SYMBOL_GPL(rcu_note_context_switch); -#ifdef CONFIG_NO_HZ DEFINE_PER_CPU(struct rcu_dynticks, rcu_dynticks) = { - .dynticks_nesting = 1, + .dynticks_nesting = DYNTICK_TASK_NESTING, .dynticks = ATOMIC_INIT(1), }; -#endif /* #ifdef CONFIG_NO_HZ */ static int blimit = 10; /* Maximum callbacks per rcu_do_batch. */ static int qhimark = 10000; /* If this many pending, ignore blimit. */ @@ -328,11 +326,11 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp) return 1; } - /* If preemptible RCU, no point in sending reschedule IPI. */ - if (rdp->preemptible) - return 0; - - /* The CPU is online, so send it a reschedule IPI. */ + /* + * The CPU is online, so send it a reschedule IPI. This forces + * it through the scheduler, and (inefficiently) also handles cases + * where idle loops fail to inform RCU about the CPU being idle. + */ if (rdp->cpu != smp_processor_id()) smp_send_reschedule(rdp->cpu); else @@ -343,59 +341,181 @@ static int rcu_implicit_offline_qs(struct rcu_data *rdp) #endif /* #ifdef CONFIG_SMP */ -#ifdef CONFIG_NO_HZ +/* + * rcu_idle_enter_common - inform RCU that current CPU is moving towards idle + * + * If the new value of the ->dynticks_nesting counter now is zero, + * we really have entered idle, and must do the appropriate accounting. + * The caller must have disabled interrupts. + */ +static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval) +{ + trace_rcu_dyntick("Start", oldval, 0); + if (!is_idle_task(current)) { + struct task_struct *idle = idle_task(smp_processor_id()); + + trace_rcu_dyntick("Error on entry: not idle task", oldval, 0); + ftrace_dump(DUMP_ALL); + WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", + current->pid, current->comm, + idle->pid, idle->comm); /* must be idle task! */ + } + rcu_prepare_for_idle(smp_processor_id()); + /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */ + smp_mb__before_atomic_inc(); /* See above. */ + atomic_inc(&rdtp->dynticks); + smp_mb__after_atomic_inc(); /* Force ordering with next sojourn. */ + WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); +} /** - * rcu_enter_nohz - inform RCU that current CPU is entering nohz + * rcu_idle_enter - inform RCU that current CPU is entering idle * - * Enter nohz mode, in other words, -leave- the mode in which RCU + * Enter idle mode, in other words, -leave- the mode in which RCU * read-side critical sections can occur. (Though RCU read-side - * critical sections can occur in irq handlers in nohz mode, a possibility - * handled by rcu_irq_enter() and rcu_irq_exit()). + * critical sections can occur in irq handlers in idle, a possibility + * handled by irq_enter() and irq_exit().) + * + * We crowbar the ->dynticks_nesting field to zero to allow for + * the possibility of usermode upcalls having messed up our count + * of interrupt nesting level during the prior busy period. */ -void rcu_enter_nohz(void) +void rcu_idle_enter(void) { unsigned long flags; + long long oldval; struct rcu_dynticks *rdtp; local_irq_save(flags); rdtp = &__get_cpu_var(rcu_dynticks); - if (--rdtp->dynticks_nesting) { - local_irq_restore(flags); - return; - } - trace_rcu_dyntick("Start"); - /* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */ - smp_mb__before_atomic_inc(); /* See above. */ - atomic_inc(&rdtp->dynticks); - smp_mb__after_atomic_inc(); /* Force ordering with next sojourn. */ - WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); + oldval = rdtp->dynticks_nesting; + rdtp->dynticks_nesting = 0; + rcu_idle_enter_common(rdtp, oldval); local_irq_restore(flags); } -/* - * rcu_exit_nohz - inform RCU that current CPU is leaving nohz +/** + * rcu_irq_exit - inform RCU that current CPU is exiting irq towards idle + * + * Exit from an interrupt handler, which might possibly result in entering + * idle mode, in other words, leaving the mode in which read-side critical + * sections can occur. * - * Exit nohz mode, in other words, -enter- the mode in which RCU - * read-side critical sections normally occur. + * This code assumes that the idle loop never does anything that might + * result in unbalanced calls to irq_enter() and irq_exit(). If your + * architecture violates this assumption, RCU will give you what you + * deserve, good and hard. But very infrequently and irreproducibly. + * + * Use things like work queues to work around this limitation. + * + * You have been warned. */ -void rcu_exit_nohz(void) +void rcu_irq_exit(void) { unsigned long flags; + long long oldval; struct rcu_dynticks *rdtp; local_irq_save(flags); rdtp = &__get_cpu_var(rcu_dynticks); - if (rdtp->dynticks_nesting++) { - local_irq_restore(flags); - return; - } + oldval = rdtp->dynticks_nesting; + rdtp->dynticks_nesting--; + WARN_ON_ONCE(rdtp->dynticks_nesting < 0); + if (rdtp->dynticks_nesting) + trace_rcu_dyntick("--=", oldval, rdtp->dynticks_nesting); + else + rcu_idle_enter_common(rdtp, oldval); + local_irq_restore(flags); +} + +/* + * rcu_idle_exit_common - inform RCU that current CPU is moving away from idle + * + * If the new value of the ->dynticks_nesting counter was previously zero, + * we really have exited idle, and must do the appropriate accounting. + * The caller must have disabled interrupts. + */ +static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval) +{ smp_mb__before_atomic_inc(); /* Force ordering w/previous sojourn. */ atomic_inc(&rdtp->dynticks); /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */ smp_mb__after_atomic_inc(); /* See above. */ WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1)); - trace_rcu_dyntick("End"); + rcu_cleanup_after_idle(smp_processor_id()); + trace_rcu_dyntick("End", oldval, rdtp->dynticks_nesting); + if (!is_idle_task(current)) { + struct task_struct *idle = idle_task(smp_processor_id()); + + trace_rcu_dyntick("Error on exit: not idle task", + oldval, rdtp->dynticks_nesting); + ftrace_dump(DUMP_ALL); + WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", + current->pid, current->comm, + idle->pid, idle->comm); /* must be idle task! */ + } +} + +/** + * rcu_idle_exit - inform RCU that current CPU is leaving idle + * + * Exit idle mode, in other words, -enter- the mode in which RCU + * read-side critical sections can occur. + * + * We crowbar the ->dynticks_nesting field to DYNTICK_TASK_NESTING to + * allow for the possibility of usermode upcalls messing up our count + * of interrupt nesting level during the busy period that is just + * now starting. + */ +void rcu_idle_exit(void) +{ + unsigned long flags; + struct rcu_dynticks *rdtp; + long long oldval; + + local_irq_save(flags); + rdtp = &__get_cpu_var(rcu_dynticks); + oldval = rdtp->dynticks_nesting; + WARN_ON_ONCE(oldval != 0); + rdtp->dynticks_nesting = DYNTICK_TASK_NESTING; + rcu_idle_exit_common(rdtp, oldval); + local_irq_restore(flags); +} + +/** + * rcu_irq_enter - inform RCU that current CPU is entering irq away from idle + * + * Enter an interrupt handler, which might possibly result in exiting + * idle mode, in other words, entering the mode in which read-side critical + * sections can occur. + * + * Note that the Linux kernel is fully capable of entering an interrupt + * handler that it never exits, for example when doing upcalls to + * user mode! This code assumes that the idle loop never does upcalls to + * user mode. If your architecture does do upcalls from the idle loop (or + * does anything else that results in unbalanced calls to the irq_enter() + * and irq_exit() functions), RCU will give you what you deserve, good + * and hard. But very infrequently and irreproducibly. + * + * Use things like work queues to work around this limitation. + * + * You have been warned. + */ +void rcu_irq_enter(void) +{ + unsigned long flags; + struct rcu_dynticks *rdtp; + long long oldval; + + local_irq_save(flags); + rdtp = &__get_cpu_var(rcu_dynticks); + oldval = rdtp->dynticks_nesting; + rdtp->dynticks_nesting++; + WARN_ON_ONCE(rdtp->dynticks_nesting == 0); + if (oldval) + trace_rcu_dyntick("++=", oldval, rdtp->dynticks_nesting); + else + rcu_idle_exit_common(rdtp, oldval); local_irq_restore(flags); } @@ -442,27 +562,37 @@ void rcu_nmi_exit(void) WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); } +#ifdef CONFIG_PROVE_RCU + /** - * rcu_irq_enter - inform RCU of entry to hard irq context + * rcu_is_cpu_idle - see if RCU thinks that the current CPU is idle * - * If the CPU was idle with dynamic ticks active, this updates the - * rdtp->dynticks to let the RCU handling know that the CPU is active. + * If the current CPU is in its idle loop and is neither in an interrupt + * or NMI handler, return true. */ -void rcu_irq_enter(void) +int rcu_is_cpu_idle(void) { - rcu_exit_nohz(); + int ret; + + preempt_disable(); + ret = (atomic_read(&__get_cpu_var(rcu_dynticks).dynticks) & 0x1) == 0; + preempt_enable(); + return ret; } +EXPORT_SYMBOL(rcu_is_cpu_idle); + +#endif /* #ifdef CONFIG_PROVE_RCU */ /** - * rcu_irq_exit - inform RCU of exit from hard irq context + * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle * - * If the CPU was idle with dynamic ticks active, update the rdp->dynticks - * to put let the RCU handling be aware that the CPU is going back to idle - * with no ticks. + * If the current CPU is idle or running at a first-level (not nested) + * interrupt from idle, return true. The caller must have at least + * disabled preemption. */ -void rcu_irq_exit(void) +int rcu_is_cpu_rrupt_from_idle(void) { - rcu_enter_nohz(); + return __get_cpu_var(rcu_dynticks).dynticks_nesting <= 1; } #ifdef CONFIG_SMP @@ -475,7 +605,7 @@ void rcu_irq_exit(void) static int dyntick_save_progress_counter(struct rcu_data *rdp) { rdp->dynticks_snap = atomic_add_return(0, &rdp->dynticks->dynticks); - return 0; + return (rdp->dynticks_snap & 0x1) == 0; } /* @@ -512,26 +642,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) #endif /* #ifdef CONFIG_SMP */ -#else /* #ifdef CONFIG_NO_HZ */ - -#ifdef CONFIG_SMP - -static int dyntick_save_progress_counter(struct rcu_data *rdp) -{ - return 0; -} - -static int rcu_implicit_dynticks_qs(struct rcu_data *rdp) -{ - return rcu_implicit_offline_qs(rdp); -} - -#endif /* #ifdef CONFIG_SMP */ - -#endif /* #else #ifdef CONFIG_NO_HZ */ - -int rcu_cpu_stall_suppress __read_mostly; - static void record_gp_stall_check_time(struct rcu_state *rsp) { rsp->gp_start = jiffies; @@ -866,8 +976,8 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) /* Advance to a new grace period and initialize state. */ rsp->gpnum++; trace_rcu_grace_period(rsp->name, rsp->gpnum, "start"); - WARN_ON_ONCE(rsp->signaled == RCU_GP_INIT); - rsp->signaled = RCU_GP_INIT; /* Hold off force_quiescent_state. */ + WARN_ON_ONCE(rsp->fqs_state == RCU_GP_INIT); + rsp->fqs_state = RCU_GP_INIT; /* Hold off force_quiescent_state. */ rsp->jiffies_force_qs = jiffies + RCU_JIFFIES_TILL_FORCE_QS; record_gp_stall_check_time(rsp); @@ -877,7 +987,7 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) rnp->qsmask = rnp->qsmaskinit; rnp->gpnum = rsp->gpnum; rnp->completed = rsp->completed; - rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state OK. */ + rsp->fqs_state = RCU_SIGNAL_INIT; /* force_quiescent_state OK */ rcu_start_gp_per_cpu(rsp, rnp, rdp); rcu_preempt_boost_start_gp(rnp); trace_rcu_grace_period_init(rsp->name, rnp->gpnum, @@ -927,7 +1037,7 @@ rcu_start_gp(struct rcu_state *rsp, unsigned long flags) rnp = rcu_get_root(rsp); raw_spin_lock(&rnp->lock); /* irqs already disabled. */ - rsp->signaled = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */ + rsp->fqs_state = RCU_SIGNAL_INIT; /* force_quiescent_state now OK. */ raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ raw_spin_unlock_irqrestore(&rsp->onofflock, flags); } @@ -991,7 +1101,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) rsp->completed = rsp->gpnum; /* Declare the grace period complete. */ trace_rcu_grace_period(rsp->name, rsp->completed, "end"); - rsp->signaled = RCU_GP_IDLE; + rsp->fqs_state = RCU_GP_IDLE; rcu_start_gp(rsp, flags); /* releases root node's rnp->lock. */ } @@ -1221,7 +1331,7 @@ static void __rcu_offline_cpu(int cpu, struct rcu_state *rsp) else raw_spin_unlock_irqrestore(&rnp->lock, flags); if (need_report & RCU_OFL_TASKS_EXP_GP) - rcu_report_exp_rnp(rsp, rnp); + rcu_report_exp_rnp(rsp, rnp, true); rcu_node_kthread_setaffinity(rnp, -1); } @@ -1263,7 +1373,9 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) /* If no callbacks are ready, just return.*/ if (!cpu_has_callbacks_ready_to_invoke(rdp)) { trace_rcu_batch_start(rsp->name, 0, 0); - trace_rcu_batch_end(rsp->name, 0); + trace_rcu_batch_end(rsp->name, 0, !!ACCESS_ONCE(rdp->nxtlist), + need_resched(), is_idle_task(current), + rcu_is_callbacks_kthread()); return; } @@ -1291,12 +1403,17 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) debug_rcu_head_unqueue(list); __rcu_reclaim(rsp->name, list); list = next; - if (++count >= bl) + /* Stop only if limit reached and CPU has something to do. */ + if (++count >= bl && + (need_resched() || + (!is_idle_task(current) && !rcu_is_callbacks_kthread()))) break; } local_irq_save(flags); - trace_rcu_batch_end(rsp->name, count); + trace_rcu_batch_end(rsp->name, count, !!list, need_resched(), + is_idle_task(current), + rcu_is_callbacks_kthread()); /* Update count, and requeue any remaining callbacks. */ rdp->qlen -= count; @@ -1334,16 +1451,14 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) * (user mode or idle loop for rcu, non-softirq execution for rcu_bh). * Also schedule RCU core processing. * - * This function must be called with hardirqs disabled. It is normally + * This function must be called from hardirq context. It is normally * invoked from the scheduling-clock interrupt. If rcu_pending returns * false, there is no point in invoking rcu_check_callbacks(). */ void rcu_check_callbacks(int cpu, int user) { trace_rcu_utilization("Start scheduler-tick"); - if (user || - (idle_cpu(cpu) && rcu_scheduler_active && - !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) { + if (user || rcu_is_cpu_rrupt_from_idle()) { /* * Get here if this CPU took its interrupt from user @@ -1457,7 +1572,7 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) goto unlock_fqs_ret; /* no GP in progress, time updated. */ } rsp->fqs_active = 1; - switch (rsp->signaled) { + switch (rsp->fqs_state) { case RCU_GP_IDLE: case RCU_GP_INIT: @@ -1473,7 +1588,7 @@ static void force_quiescent_state(struct rcu_state *rsp, int relaxed) force_qs_rnp(rsp, dyntick_save_progress_counter); raw_spin_lock(&rnp->lock); /* irqs already disabled */ if (rcu_gp_in_progress(rsp)) - rsp->signaled = RCU_FORCE_QS; + rsp->fqs_state = RCU_FORCE_QS; break; case RCU_FORCE_QS: @@ -1812,7 +1927,7 @@ static int rcu_pending(int cpu) * by the current CPU, even if none need be done immediately, returning * 1 if so. */ -static int rcu_needs_cpu_quick_check(int cpu) +static int rcu_cpu_has_callbacks(int cpu) { /* RCU callbacks either ready or pending? */ return per_cpu(rcu_sched_data, cpu).nxtlist || @@ -1913,9 +2028,9 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) for (i = 0; i < RCU_NEXT_SIZE; i++) rdp->nxttail[i] = &rdp->nxtlist; rdp->qlen = 0; -#ifdef CONFIG_NO_HZ rdp->dynticks = &per_cpu(rcu_dynticks, cpu); -#endif /* #ifdef CONFIG_NO_HZ */ + WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_NESTING); + WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); rdp->cpu = cpu; rdp->rsp = rsp; raw_spin_unlock_irqrestore(&rnp->lock, flags); @@ -1942,6 +2057,10 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptible) rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = rsp->n_force_qs; rdp->blimit = blimit; + rdp->dynticks->dynticks_nesting = DYNTICK_TASK_NESTING; + atomic_set(&rdp->dynticks->dynticks, + (atomic_read(&rdp->dynticks->dynticks) & ~0x1) + 1); + rcu_prepare_for_idle_init(cpu); raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */ /* @@ -2023,6 +2142,7 @@ static int __cpuinit rcu_cpu_notify(struct notifier_block *self, rcu_send_cbs_to_online(&rcu_bh_state); rcu_send_cbs_to_online(&rcu_sched_state); rcu_preempt_send_cbs_to_online(); + rcu_cleanup_after_idle(cpu); break; case CPU_DEAD: case CPU_DEAD_FROZEN: diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 849ce9e..fddff92 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -84,9 +84,10 @@ * Dynticks per-CPU state. */ struct rcu_dynticks { - int dynticks_nesting; /* Track irq/process nesting level. */ - int dynticks_nmi_nesting; /* Track NMI nesting level. */ - atomic_t dynticks; /* Even value for dynticks-idle, else odd. */ + long long dynticks_nesting; /* Track irq/process nesting level. */ + /* Process level is worth LLONG_MAX/2. */ + int dynticks_nmi_nesting; /* Track NMI nesting level. */ + atomic_t dynticks; /* Even value for idle, else odd. */ }; /* RCU's kthread states for tracing. */ @@ -274,16 +275,12 @@ struct rcu_data { /* did other CPU force QS recently? */ long blimit; /* Upper limit on a processed batch */ -#ifdef CONFIG_NO_HZ /* 3) dynticks interface. */ struct rcu_dynticks *dynticks; /* Shared per-CPU dynticks state. */ int dynticks_snap; /* Per-GP tracking for dynticks. */ -#endif /* #ifdef CONFIG_NO_HZ */ /* 4) reasons this CPU needed to be kicked by force_quiescent_state */ -#ifdef CONFIG_NO_HZ unsigned long dynticks_fqs; /* Kicked due to dynticks idle. */ -#endif /* #ifdef CONFIG_NO_HZ */ unsigned long offline_fqs; /* Kicked due to being offline. */ unsigned long resched_ipi; /* Sent a resched IPI. */ @@ -302,16 +299,12 @@ struct rcu_data { struct rcu_state *rsp; }; -/* Values for signaled field in struct rcu_state. */ +/* Values for fqs_state field in struct rcu_state. */ #define RCU_GP_IDLE 0 /* No grace period in progress. */ #define RCU_GP_INIT 1 /* Grace period being initialized. */ #define RCU_SAVE_DYNTICK 2 /* Need to scan dyntick state. */ #define RCU_FORCE_QS 3 /* Need to force quiescent state. */ -#ifdef CONFIG_NO_HZ #define RCU_SIGNAL_INIT RCU_SAVE_DYNTICK -#else /* #ifdef CONFIG_NO_HZ */ -#define RCU_SIGNAL_INIT RCU_FORCE_QS -#endif /* #else #ifdef CONFIG_NO_HZ */ #define RCU_JIFFIES_TILL_FORCE_QS 3 /* for rsp->jiffies_force_qs */ @@ -361,7 +354,7 @@ struct rcu_state { /* The following fields are guarded by the root rcu_node's lock. */ - u8 signaled ____cacheline_internodealigned_in_smp; + u8 fqs_state ____cacheline_internodealigned_in_smp; /* Force QS state. */ u8 fqs_active; /* force_quiescent_state() */ /* is running. */ @@ -451,7 +444,8 @@ static void rcu_preempt_check_callbacks(int cpu); static void rcu_preempt_process_callbacks(void); void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) -static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp); +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, + bool wake); #endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */ static int rcu_preempt_pending(int cpu); static int rcu_preempt_needs_cpu(int cpu); @@ -461,6 +455,7 @@ static void __init __rcu_init_preempt(void); static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); static void invoke_rcu_callbacks_kthread(void); +static bool rcu_is_callbacks_kthread(void); #ifdef CONFIG_RCU_BOOST static void rcu_preempt_do_callbacks(void); static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, @@ -473,5 +468,8 @@ static void rcu_yield(void (*f)(unsigned long), unsigned long arg); #endif /* #ifdef CONFIG_RCU_BOOST */ static void rcu_cpu_kthread_setrt(int cpu, int to_rt); static void __cpuinit rcu_prepare_kthreads(int cpu); +static void rcu_prepare_for_idle_init(int cpu); +static void rcu_cleanup_after_idle(int cpu); +static void rcu_prepare_for_idle(int cpu); #endif /* #ifndef RCU_TREE_NONCORE */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 4b9b9f8..8bb35d7 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -312,6 +312,7 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; + int empty_exp_now; unsigned long flags; struct list_head *np; #ifdef CONFIG_RCU_BOOST @@ -382,8 +383,10 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) /* * If this was the last task on the current list, and if * we aren't waiting on any CPUs, report the quiescent state. - * Note that rcu_report_unblock_qs_rnp() releases rnp->lock. + * Note that rcu_report_unblock_qs_rnp() releases rnp->lock, + * so we must take a snapshot of the expedited state. */ + empty_exp_now = !rcu_preempted_readers_exp(rnp); if (!empty && !rcu_preempt_blocked_readers_cgp(rnp)) { trace_rcu_quiescent_state_report("preempt_rcu", rnp->gpnum, @@ -406,8 +409,8 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) * If this was the last task on the expedited lists, * then we need to report up the rcu_node hierarchy. */ - if (!empty_exp && !rcu_preempted_readers_exp(rnp)) - rcu_report_exp_rnp(&rcu_preempt_state, rnp); + if (!empty_exp && empty_exp_now) + rcu_report_exp_rnp(&rcu_preempt_state, rnp, true); } else { local_irq_restore(flags); } @@ -729,9 +732,13 @@ static int sync_rcu_preempt_exp_done(struct rcu_node *rnp) * recursively up the tree. (Calm down, calm down, we do the recursion * iteratively!) * + * Most callers will set the "wake" flag, but the task initiating the + * expedited grace period need not wake itself. + * * Caller must hold sync_rcu_preempt_exp_mutex. */ -static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, + bool wake) { unsigned long flags; unsigned long mask; @@ -744,7 +751,8 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) } if (rnp->parent == NULL) { raw_spin_unlock_irqrestore(&rnp->lock, flags); - wake_up(&sync_rcu_preempt_exp_wq); + if (wake) + wake_up(&sync_rcu_preempt_exp_wq); break; } mask = rnp->grpmask; @@ -777,7 +785,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp) must_wait = 1; } if (!must_wait) - rcu_report_exp_rnp(rsp, rnp); + rcu_report_exp_rnp(rsp, rnp, false); /* Don't wake self. */ } /* @@ -1069,9 +1077,9 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); * report on tasks preempted in RCU read-side critical sections during * expedited RCU grace periods. */ -static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, + bool wake) { - return; } #endif /* #ifdef CONFIG_HOTPLUG_CPU */ @@ -1157,8 +1165,6 @@ static void rcu_initiate_boost_trace(struct rcu_node *rnp) #endif /* #else #ifdef CONFIG_RCU_TRACE */ -static struct lock_class_key rcu_boost_class; - /* * Carry out RCU priority boosting on the task indicated by ->exp_tasks * or ->boost_tasks, advancing the pointer to the next task in the @@ -1221,15 +1227,13 @@ static int rcu_boost(struct rcu_node *rnp) */ t = container_of(tb, struct task_struct, rcu_node_entry); rt_mutex_init_proxy_locked(&mtx, t); - /* Avoid lockdep false positives. This rt_mutex is its own thing. */ - lockdep_set_class_and_name(&mtx.wait_lock, &rcu_boost_class, - "rcu_boost_mutex"); t->rcu_boost_mutex = &mtx; raw_spin_unlock_irqrestore(&rnp->lock, flags); rt_mutex_lock(&mtx); /* Side effect: boosts task t's priority. */ rt_mutex_unlock(&mtx); /* Keep lockdep happy. */ - return rnp->exp_tasks != NULL || rnp->boost_tasks != NULL; + return ACCESS_ONCE(rnp->exp_tasks) != NULL || + ACCESS_ONCE(rnp->boost_tasks) != NULL; } /* @@ -1329,6 +1333,15 @@ static void invoke_rcu_callbacks_kthread(void) } /* + * Is the current CPU running the RCU-callbacks kthread? + * Caller must have preemption disabled. + */ +static bool rcu_is_callbacks_kthread(void) +{ + return __get_cpu_var(rcu_cpu_kthread_task) == current; +} + +/* * Set the affinity of the boost kthread. The CPU-hotplug locks are * held, so no one should be messing with the existence of the boost * kthread. @@ -1772,6 +1785,11 @@ static void invoke_rcu_callbacks_kthread(void) WARN_ON_ONCE(1); } +static bool rcu_is_callbacks_kthread(void) +{ + return false; +} + static void rcu_preempt_boost_start_gp(struct rcu_node *rnp) { } @@ -1907,7 +1925,7 @@ void synchronize_sched_expedited(void) * grace period works for us. */ get_online_cpus(); - snap = atomic_read(&sync_sched_expedited_started) - 1; + snap = atomic_read(&sync_sched_expedited_started); smp_mb(); /* ensure read is before try_stop_cpus(). */ } @@ -1939,88 +1957,243 @@ EXPORT_SYMBOL_GPL(synchronize_sched_expedited); * 1 if so. This function is part of the RCU implementation; it is -not- * an exported member of the RCU API. * - * Because we have preemptible RCU, just check whether this CPU needs - * any flavor of RCU. Do not chew up lots of CPU cycles with preemption - * disabled in a most-likely vain attempt to cause RCU not to need this CPU. + * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs + * any flavor of RCU. */ int rcu_needs_cpu(int cpu) { - return rcu_needs_cpu_quick_check(cpu); + return rcu_cpu_has_callbacks(cpu); +} + +/* + * Because we do not have RCU_FAST_NO_HZ, don't bother initializing for it. + */ +static void rcu_prepare_for_idle_init(int cpu) +{ +} + +/* + * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up + * after it. + */ +static void rcu_cleanup_after_idle(int cpu) +{ +} + +/* + * Do the idle-entry grace-period work, which, because CONFIG_RCU_FAST_NO_HZ=y, + * is nothing. + */ +static void rcu_prepare_for_idle(int cpu) +{ } #else /* #if !defined(CONFIG_RCU_FAST_NO_HZ) */ -#define RCU_NEEDS_CPU_FLUSHES 5 +/* + * This code is invoked when a CPU goes idle, at which point we want + * to have the CPU do everything required for RCU so that it can enter + * the energy-efficient dyntick-idle mode. This is handled by a + * state machine implemented by rcu_prepare_for_idle() below. + * + * The following three proprocessor symbols control this state machine: + * + * RCU_IDLE_FLUSHES gives the maximum number of times that we will attempt + * to satisfy RCU. Beyond this point, it is better to incur a periodic + * scheduling-clock interrupt than to loop through the state machine + * at full power. + * RCU_IDLE_OPT_FLUSHES gives the number of RCU_IDLE_FLUSHES that are + * optional if RCU does not need anything immediately from this + * CPU, even if this CPU still has RCU callbacks queued. The first + * times through the state machine are mandatory: we need to give + * the state machine a chance to communicate a quiescent state + * to the RCU core. + * RCU_IDLE_GP_DELAY gives the number of jiffies that a CPU is permitted + * to sleep in dyntick-idle mode with RCU callbacks pending. This + * is sized to be roughly one RCU grace period. Those energy-efficiency + * benchmarkers who might otherwise be tempted to set this to a large + * number, be warned: Setting RCU_IDLE_GP_DELAY too high can hang your + * system. And if you are -that- concerned about energy efficiency, + * just power the system down and be done with it! + * + * The values below work well in practice. If future workloads require + * adjustment, they can be converted into kernel config parameters, though + * making the state machine smarter might be a better option. + */ +#define RCU_IDLE_FLUSHES 5 /* Number of dyntick-idle tries. */ +#define RCU_IDLE_OPT_FLUSHES 3 /* Optional dyntick-idle tries. */ +#define RCU_IDLE_GP_DELAY 6 /* Roughly one grace period. */ + static DEFINE_PER_CPU(int, rcu_dyntick_drain); static DEFINE_PER_CPU(unsigned long, rcu_dyntick_holdoff); +static DEFINE_PER_CPU(struct hrtimer, rcu_idle_gp_timer); +static ktime_t rcu_idle_gp_wait; /* - * Check to see if any future RCU-related work will need to be done - * by the current CPU, even if none need be done immediately, returning - * 1 if so. This function is part of the RCU implementation; it is -not- - * an exported member of the RCU API. + * Allow the CPU to enter dyntick-idle mode if either: (1) There are no + * callbacks on this CPU, (2) this CPU has not yet attempted to enter + * dyntick-idle mode, or (3) this CPU is in the process of attempting to + * enter dyntick-idle mode. Otherwise, if we have recently tried and failed + * to enter dyntick-idle mode, we refuse to try to enter it. After all, + * it is better to incur scheduling-clock interrupts than to spin + * continuously for the same time duration! + */ +int rcu_needs_cpu(int cpu) +{ + /* If no callbacks, RCU doesn't need the CPU. */ + if (!rcu_cpu_has_callbacks(cpu)) + return 0; + /* Otherwise, RCU needs the CPU only if it recently tried and failed. */ + return per_cpu(rcu_dyntick_holdoff, cpu) == jiffies; +} + +/* + * Timer handler used to force CPU to start pushing its remaining RCU + * callbacks in the case where it entered dyntick-idle mode with callbacks + * pending. The hander doesn't really need to do anything because the + * real work is done upon re-entry to idle, or by the next scheduling-clock + * interrupt should idle not be re-entered. + */ +static enum hrtimer_restart rcu_idle_gp_timer_func(struct hrtimer *hrtp) +{ + trace_rcu_prep_idle("Timer"); + return HRTIMER_NORESTART; +} + +/* + * Initialize the timer used to pull CPUs out of dyntick-idle mode. + */ +static void rcu_prepare_for_idle_init(int cpu) +{ + static int firsttime = 1; + struct hrtimer *hrtp = &per_cpu(rcu_idle_gp_timer, cpu); + + hrtimer_init(hrtp, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtp->function = rcu_idle_gp_timer_func; + if (firsttime) { + unsigned int upj = jiffies_to_usecs(RCU_IDLE_GP_DELAY); + + rcu_idle_gp_wait = ns_to_ktime(upj * (u64)1000); + firsttime = 0; + } +} + +/* + * Clean up for exit from idle. Because we are exiting from idle, there + * is no longer any point to rcu_idle_gp_timer, so cancel it. This will + * do nothing if this timer is not active, so just cancel it unconditionally. + */ +static void rcu_cleanup_after_idle(int cpu) +{ + hrtimer_cancel(&per_cpu(rcu_idle_gp_timer, cpu)); +} + +/* + * Check to see if any RCU-related work can be done by the current CPU, + * and if so, schedule a softirq to get it done. This function is part + * of the RCU implementation; it is -not- an exported member of the RCU API. * - * Because we are not supporting preemptible RCU, attempt to accelerate - * any current grace periods so that RCU no longer needs this CPU, but - * only if all other CPUs are already in dynticks-idle mode. This will - * allow the CPU cores to be powered down immediately, as opposed to after - * waiting many milliseconds for grace periods to elapse. + * The idea is for the current CPU to clear out all work required by the + * RCU core for the current grace period, so that this CPU can be permitted + * to enter dyntick-idle mode. In some cases, it will need to be awakened + * at the end of the grace period by whatever CPU ends the grace period. + * This allows CPUs to go dyntick-idle more quickly, and to reduce the + * number of wakeups by a modest integer factor. * * Because it is not legal to invoke rcu_process_callbacks() with irqs * disabled, we do one pass of force_quiescent_state(), then do a * invoke_rcu_core() to cause rcu_process_callbacks() to be invoked * later. The per-cpu rcu_dyntick_drain variable controls the sequencing. + * + * The caller must have disabled interrupts. */ -int rcu_needs_cpu(int cpu) +static void rcu_prepare_for_idle(int cpu) { - int c = 0; - int snap; - int thatcpu; - - /* Check for being in the holdoff period. */ - if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies) - return rcu_needs_cpu_quick_check(cpu); - - /* Don't bother unless we are the last non-dyntick-idle CPU. */ - for_each_online_cpu(thatcpu) { - if (thatcpu == cpu) - continue; - snap = atomic_add_return(0, &per_cpu(rcu_dynticks, - thatcpu).dynticks); - smp_mb(); /* Order sampling of snap with end of grace period. */ - if ((snap & 0x1) != 0) { - per_cpu(rcu_dyntick_drain, cpu) = 0; - per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1; - return rcu_needs_cpu_quick_check(cpu); - } + unsigned long flags; + + local_irq_save(flags); + + /* + * If there are no callbacks on this CPU, enter dyntick-idle mode. + * Also reset state to avoid prejudicing later attempts. + */ + if (!rcu_cpu_has_callbacks(cpu)) { + per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1; + per_cpu(rcu_dyntick_drain, cpu) = 0; + local_irq_restore(flags); + trace_rcu_prep_idle("No callbacks"); + return; + } + + /* + * If in holdoff mode, just return. We will presumably have + * refrained from disabling the scheduling-clock tick. + */ + if (per_cpu(rcu_dyntick_holdoff, cpu) == jiffies) { + local_irq_restore(flags); + trace_rcu_prep_idle("In holdoff"); + return; } /* Check and update the rcu_dyntick_drain sequencing. */ if (per_cpu(rcu_dyntick_drain, cpu) <= 0) { /* First time through, initialize the counter. */ - per_cpu(rcu_dyntick_drain, cpu) = RCU_NEEDS_CPU_FLUSHES; + per_cpu(rcu_dyntick_drain, cpu) = RCU_IDLE_FLUSHES; + } else if (per_cpu(rcu_dyntick_drain, cpu) <= RCU_IDLE_OPT_FLUSHES && + !rcu_pending(cpu)) { + /* Can we go dyntick-idle despite still having callbacks? */ + trace_rcu_prep_idle("Dyntick with callbacks"); + per_cpu(rcu_dyntick_drain, cpu) = 0; + per_cpu(rcu_dyntick_holdoff, cpu) = jiffies - 1; + hrtimer_start(&per_cpu(rcu_idle_gp_timer, cpu), + rcu_idle_gp_wait, HRTIMER_MODE_REL); + return; /* Nothing more to do immediately. */ } else if (--per_cpu(rcu_dyntick_drain, cpu) <= 0) { /* We have hit the limit, so time to give up. */ per_cpu(rcu_dyntick_holdoff, cpu) = jiffies; - return rcu_needs_cpu_quick_check(cpu); + local_irq_restore(flags); + trace_rcu_prep_idle("Begin holdoff"); + invoke_rcu_core(); /* Force the CPU out of dyntick-idle. */ + return; } - /* Do one step pushing remaining RCU callbacks through. */ + /* + * Do one step of pushing the remaining RCU callbacks through + * the RCU core state machine. + */ +#ifdef CONFIG_TREE_PREEMPT_RCU + if (per_cpu(rcu_preempt_data, cpu).nxtlist) { + local_irq_restore(flags); + rcu_preempt_qs(cpu); + force_quiescent_state(&rcu_preempt_state, 0); + local_irq_save(flags); + } +#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ if (per_cpu(rcu_sched_data, cpu).nxtlist) { + local_irq_restore(flags); rcu_sched_qs(cpu); force_quiescent_state(&rcu_sched_state, 0); - c = c || per_cpu(rcu_sched_data, cpu).nxtlist; + local_irq_save(flags); } if (per_cpu(rcu_bh_data, cpu).nxtlist) { + local_irq_restore(flags); rcu_bh_qs(cpu); force_quiescent_state(&rcu_bh_state, 0); - c = c || per_cpu(rcu_bh_data, cpu).nxtlist; + local_irq_save(flags); } - /* If RCU callbacks are still pending, RCU still needs this CPU. */ - if (c) + /* + * If RCU callbacks are still pending, RCU still needs this CPU. + * So try forcing the callbacks through the grace period. + */ + if (rcu_cpu_has_callbacks(cpu)) { + local_irq_restore(flags); + trace_rcu_prep_idle("More callbacks"); invoke_rcu_core(); - return c; + } else { + local_irq_restore(flags); + trace_rcu_prep_idle("Callbacks drained"); + } } #endif /* #else #if !defined(CONFIG_RCU_FAST_NO_HZ) */ diff --git a/kernel/rcutree_trace.c b/kernel/rcutree_trace.c index 9feffa4..654cfe6 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -67,13 +67,11 @@ static void print_one_rcu_data(struct seq_file *m, struct rcu_data *rdp) rdp->completed, rdp->gpnum, rdp->passed_quiesce, rdp->passed_quiesce_gpnum, rdp->qs_pending); -#ifdef CONFIG_NO_HZ - seq_printf(m, " dt=%d/%d/%d df=%lu", + seq_printf(m, " dt=%d/%llx/%d df=%lu", atomic_read(&rdp->dynticks->dynticks), rdp->dynticks->dynticks_nesting, rdp->dynticks->dynticks_nmi_nesting, rdp->dynticks_fqs); -#endif /* #ifdef CONFIG_NO_HZ */ seq_printf(m, " of=%lu ri=%lu", rdp->offline_fqs, rdp->resched_ipi); seq_printf(m, " ql=%ld qs=%c%c%c%c", rdp->qlen, @@ -141,13 +139,11 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) rdp->completed, rdp->gpnum, rdp->passed_quiesce, rdp->passed_quiesce_gpnum, rdp->qs_pending); -#ifdef CONFIG_NO_HZ - seq_printf(m, ",%d,%d,%d,%lu", + seq_printf(m, ",%d,%llx,%d,%lu", atomic_read(&rdp->dynticks->dynticks), rdp->dynticks->dynticks_nesting, rdp->dynticks->dynticks_nmi_nesting, rdp->dynticks_fqs); -#endif /* #ifdef CONFIG_NO_HZ */ seq_printf(m, ",%lu,%lu", rdp->offline_fqs, rdp->resched_ipi); seq_printf(m, ",%ld,\"%c%c%c%c\"", rdp->qlen, ".N"[rdp->nxttail[RCU_NEXT_READY_TAIL] != @@ -171,9 +167,7 @@ static void print_one_rcu_data_csv(struct seq_file *m, struct rcu_data *rdp) static int show_rcudata_csv(struct seq_file *m, void *unused) { seq_puts(m, "\"CPU\",\"Online?\",\"c\",\"g\",\"pq\",\"pgp\",\"pq\","); -#ifdef CONFIG_NO_HZ seq_puts(m, "\"dt\",\"dt nesting\",\"dt NMI nesting\",\"df\","); -#endif /* #ifdef CONFIG_NO_HZ */ seq_puts(m, "\"of\",\"ri\",\"ql\",\"qs\""); #ifdef CONFIG_RCU_BOOST seq_puts(m, "\"kt\",\"ktl\""); @@ -278,7 +272,7 @@ static void print_one_rcu_state(struct seq_file *m, struct rcu_state *rsp) gpnum = rsp->gpnum; seq_printf(m, "c=%lu g=%lu s=%d jfq=%ld j=%x " "nfqs=%lu/nfqsng=%lu(%lu) fqlh=%lu\n", - rsp->completed, gpnum, rsp->signaled, + rsp->completed, gpnum, rsp->fqs_state, (long)(rsp->jiffies_force_qs - jiffies), (int)(jiffies & 0xffff), rsp->n_force_qs, rsp->n_force_qs_ngp, diff --git a/kernel/rtmutex-debug.c b/kernel/rtmutex-debug.c index 8eafd1b..16502d3 100644 --- a/kernel/rtmutex-debug.c +++ b/kernel/rtmutex-debug.c @@ -101,6 +101,7 @@ void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter) printk("\n============================================\n"); printk( "[ BUG: circular locking deadlock detected! ]\n"); + printk("%s\n", print_tainted()); printk( "--------------------------------------------\n"); printk("%s/%d is deadlocking current task %s/%d\n\n", task->comm, task_pid_nr(task), diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c index f9d8482..a242e69 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -579,7 +579,6 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, struct rt_mutex_waiter *waiter) { int ret = 0; - int was_disabled; for (;;) { /* Try to acquire the lock: */ @@ -602,17 +601,10 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, raw_spin_unlock(&lock->wait_lock); - was_disabled = irqs_disabled(); - if (was_disabled) - local_irq_enable(); - debug_rt_mutex_print_deadlock(waiter); schedule_rt_mutex(lock); - if (was_disabled) - local_irq_disable(); - raw_spin_lock(&lock->wait_lock); set_current_state(state); } diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index a78ed27..8a39fa3 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -2352,13 +2352,11 @@ again: if (!smt && (sd->flags & SD_SHARE_CPUPOWER)) continue; - if (!(sd->flags & SD_SHARE_PKG_RESOURCES)) { - if (!smt) { - smt = 1; - goto again; - } + if (smt && !(sd->flags & SD_SHARE_CPUPOWER)) + break; + + if (!(sd->flags & SD_SHARE_PKG_RESOURCES)) break; - } sg = sd->groups; do { @@ -2378,6 +2376,10 @@ next: sg = sg->next; } while (sg != sd->groups); } + if (!smt) { + smt = 1; + goto again; + } done: rcu_read_unlock(); diff --git a/kernel/signal.c b/kernel/signal.c index b3f78d0..2065515 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1994,8 +1994,6 @@ static bool do_signal_stop(int signr) */ if (!(sig->flags & SIGNAL_STOP_STOPPED)) sig->group_exit_code = signr; - else - WARN_ON_ONCE(!current->ptrace); sig->group_stop_count = 0; diff --git a/kernel/softirq.c b/kernel/softirq.c index 2c71d91..4eb3a0f 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -347,12 +347,12 @@ void irq_exit(void) if (!in_interrupt() && local_softirq_pending()) invoke_softirq(); - rcu_irq_exit(); #ifdef CONFIG_NO_HZ /* Make sure that timer wheel updates are propagated */ if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched()) - tick_nohz_stop_sched_tick(0); + tick_nohz_irq_exit(); #endif + rcu_irq_exit(); preempt_enable_no_resched(); } diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index 6318b51..a650694 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1354,7 +1354,7 @@ static ssize_t binary_sysctl(const int *name, int nlen, fput(file); out_putname: - putname(pathname); + __putname(pathname); out: return result; } diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index c4eb71c..1ecd6ba 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -387,7 +387,6 @@ 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 da2f760..d3ad022 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -647,7 +647,7 @@ static void clocksource_enqueue(struct clocksource *cs) /** * __clocksource_updatefreq_scale - Used update clocksource with new freq - * @t: clocksource to be registered + * @cs: clocksource to be registered * @scale: Scale factor multiplied against freq to get clocksource hz * @freq: clocksource frequency (cycles per second) divided by scale * @@ -699,7 +699,7 @@ EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale); /** * __clocksource_register_scale - Used to install new clocksources - * @t: clocksource to be registered + * @cs: clocksource to be registered * @scale: Scale factor multiplied against freq to get clocksource hz * @freq: clocksource frequency (cycles per second) divided by scale * @@ -727,7 +727,7 @@ EXPORT_SYMBOL_GPL(__clocksource_register_scale); /** * clocksource_register - Used to install new clocksources - * @t: clocksource to be registered + * @cs: clocksource to be registered * * Returns -EBUSY if registration fails, zero otherwise. */ @@ -761,6 +761,8 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating) /** * clocksource_change_rating - Change the rating of a registered clocksource + * @cs: clocksource to be changed + * @rating: new rating */ void clocksource_change_rating(struct clocksource *cs, int rating) { @@ -772,6 +774,7 @@ EXPORT_SYMBOL(clocksource_change_rating); /** * clocksource_unregister - remove a registered clocksource + * @cs: clocksource to be unregistered */ void clocksource_unregister(struct clocksource *cs) { @@ -787,6 +790,7 @@ EXPORT_SYMBOL(clocksource_unregister); /** * sysfs_show_current_clocksources - sysfs interface for current clocksource * @dev: unused + * @attr: unused * @buf: char buffer to be filled with clocksource list * * Provides sysfs interface for listing current clocksource. @@ -807,6 +811,7 @@ sysfs_show_current_clocksources(struct sys_device *dev, /** * sysfs_override_clocksource - interface for manually overriding clocksource * @dev: unused + * @attr: unused * @buf: name of override clocksource * @count: length of buffer * @@ -842,6 +847,7 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev, /** * sysfs_show_available_clocksources - sysfs interface for listing clocksource * @dev: unused + * @attr: unused * @buf: char buffer to be filled with clocksource list * * Provides sysfs interface for listing registered clocksources diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 4042064..0ec8b83 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -275,42 +275,17 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) } EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us); -/** - * tick_nohz_stop_sched_tick - stop the idle tick from the idle task - * - * When the next event is more than a tick into the future, stop the idle tick - * Called either from the idle loop or from irq_exit() when an idle period was - * just interrupted by an interrupt which did not cause a reschedule. - */ -void tick_nohz_stop_sched_tick(int inidle) +static void tick_nohz_stop_sched_tick(struct tick_sched *ts) { - unsigned long seq, last_jiffies, next_jiffies, delta_jiffies, flags; - struct tick_sched *ts; + unsigned long seq, last_jiffies, next_jiffies, delta_jiffies; ktime_t last_update, expires, now; struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev; u64 time_delta; int cpu; - local_irq_save(flags); - cpu = smp_processor_id(); ts = &per_cpu(tick_cpu_sched, cpu); - /* - * Call to tick_nohz_start_idle stops the last_update_time from being - * updated. Thus, it must not be called in the event we are called from - * irq_exit() with the prior state different than idle. - */ - if (!inidle && !ts->inidle) - goto end; - - /* - * Set ts->inidle unconditionally. Even if the system did not - * switch to NOHZ mode the cpu frequency governers rely on the - * update of the idle time accounting in tick_nohz_start_idle(). - */ - ts->inidle = 1; - now = tick_nohz_start_idle(cpu, ts); /* @@ -326,10 +301,10 @@ void tick_nohz_stop_sched_tick(int inidle) } if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) - goto end; + return; if (need_resched()) - goto end; + return; if (unlikely(local_softirq_pending() && cpu_online(cpu))) { static int ratelimit; @@ -339,7 +314,7 @@ void tick_nohz_stop_sched_tick(int inidle) (unsigned int) local_softirq_pending()); ratelimit++; } - goto end; + return; } ts->idle_calls++; @@ -434,7 +409,6 @@ void tick_nohz_stop_sched_tick(int inidle) ts->idle_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; ts->idle_jiffies = last_jiffies; - rcu_enter_nohz(); } ts->idle_sleeps++; @@ -472,8 +446,56 @@ out: ts->next_jiffies = next_jiffies; ts->last_jiffies = last_jiffies; ts->sleep_length = ktime_sub(dev->next_event, now); -end: - local_irq_restore(flags); +} + +/** + * tick_nohz_idle_enter - stop the idle tick from the idle task + * + * When the next event is more than a tick into the future, stop the idle tick + * Called when we start the idle loop. + * + * The arch is responsible of calling: + * + * - rcu_idle_enter() after its last use of RCU before the CPU is put + * to sleep. + * - rcu_idle_exit() before the first use of RCU after the CPU is woken up. + */ +void tick_nohz_idle_enter(void) +{ + struct tick_sched *ts; + + WARN_ON_ONCE(irqs_disabled()); + + local_irq_disable(); + + ts = &__get_cpu_var(tick_cpu_sched); + /* + * set ts->inidle unconditionally. even if the system did not + * switch to nohz mode the cpu frequency governers rely on the + * update of the idle time accounting in tick_nohz_start_idle(). + */ + ts->inidle = 1; + tick_nohz_stop_sched_tick(ts); + + local_irq_enable(); +} + +/** + * tick_nohz_irq_exit - update next tick event from interrupt exit + * + * When an interrupt fires while we are idle and it doesn't cause + * a reschedule, it may still add, modify or delete a timer, enqueue + * an RCU callback, etc... + * So we need to re-calculate and reprogram the next tick event. + */ +void tick_nohz_irq_exit(void) +{ + struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); + + if (!ts->inidle) + return; + + tick_nohz_stop_sched_tick(ts); } /** @@ -515,11 +537,13 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) } /** - * tick_nohz_restart_sched_tick - restart the idle tick from the idle task + * tick_nohz_idle_exit - restart the idle tick from the idle task * * Restart the idle tick when the CPU is woken up from idle + * This also exit the RCU extended quiescent state. The CPU + * can use RCU again after this function is called. */ -void tick_nohz_restart_sched_tick(void) +void tick_nohz_idle_exit(void) { int cpu = smp_processor_id(); struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); @@ -529,6 +553,7 @@ void tick_nohz_restart_sched_tick(void) ktime_t now; local_irq_disable(); + if (ts->idle_active || (ts->inidle && ts->tick_stopped)) now = ktime_get(); @@ -543,8 +568,6 @@ void tick_nohz_restart_sched_tick(void) ts->inidle = 0; - rcu_exit_nohz(); - /* Update jiffies first */ select_nohz_load_balancer(0); tick_do_update_jiffies64(now); diff --git a/kernel/timer.c b/kernel/timer.c index 9c3c62b..a297ffc 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -427,6 +427,12 @@ static int timer_fixup_init(void *addr, enum debug_obj_state state) } } +/* Stub timer callback for improperly used timers. */ +static void stub_timer(unsigned long data) +{ + WARN_ON(1); +} + /* * fixup_activate is called when: * - an active object is activated @@ -450,7 +456,8 @@ static int timer_fixup_activate(void *addr, enum debug_obj_state state) debug_object_activate(timer, &timer_debug_descr); return 0; } else { - WARN_ON_ONCE(1); + setup_timer(timer, stub_timer, 0); + return 1; } return 0; @@ -480,12 +487,40 @@ static int timer_fixup_free(void *addr, enum debug_obj_state state) } } +/* + * fixup_assert_init is called when: + * - an untracked/uninit-ed object is found + */ +static int timer_fixup_assert_init(void *addr, enum debug_obj_state state) +{ + struct timer_list *timer = addr; + + switch (state) { + case ODEBUG_STATE_NOTAVAILABLE: + if (timer->entry.prev == TIMER_ENTRY_STATIC) { + /* + * This is not really a fixup. The timer was + * statically initialized. We just make sure that it + * is tracked in the object tracker. + */ + debug_object_init(timer, &timer_debug_descr); + return 0; + } else { + setup_timer(timer, stub_timer, 0); + return 1; + } + default: + return 0; + } +} + static struct debug_obj_descr timer_debug_descr = { - .name = "timer_list", - .debug_hint = timer_debug_hint, - .fixup_init = timer_fixup_init, - .fixup_activate = timer_fixup_activate, - .fixup_free = timer_fixup_free, + .name = "timer_list", + .debug_hint = timer_debug_hint, + .fixup_init = timer_fixup_init, + .fixup_activate = timer_fixup_activate, + .fixup_free = timer_fixup_free, + .fixup_assert_init = timer_fixup_assert_init, }; static inline void debug_timer_init(struct timer_list *timer) @@ -508,6 +543,11 @@ static inline void debug_timer_free(struct timer_list *timer) debug_object_free(timer, &timer_debug_descr); } +static inline void debug_timer_assert_init(struct timer_list *timer) +{ + debug_object_assert_init(timer, &timer_debug_descr); +} + static void __init_timer(struct timer_list *timer, const char *name, struct lock_class_key *key); @@ -531,6 +571,7 @@ EXPORT_SYMBOL_GPL(destroy_timer_on_stack); static inline void debug_timer_init(struct timer_list *timer) { } static inline void debug_timer_activate(struct timer_list *timer) { } static inline void debug_timer_deactivate(struct timer_list *timer) { } +static inline void debug_timer_assert_init(struct timer_list *timer) { } #endif static inline void debug_init(struct timer_list *timer) @@ -552,6 +593,11 @@ static inline void debug_deactivate(struct timer_list *timer) trace_timer_cancel(timer); } +static inline void debug_assert_init(struct timer_list *timer) +{ + debug_timer_assert_init(timer); +} + static void __init_timer(struct timer_list *timer, const char *name, struct lock_class_key *key) @@ -902,6 +948,8 @@ int del_timer(struct timer_list *timer) unsigned long flags; int ret = 0; + debug_assert_init(timer); + timer_stats_timer_clear_start_info(timer); if (timer_pending(timer)) { base = lock_timer_base(timer, &flags); @@ -932,6 +980,8 @@ int try_to_del_timer_sync(struct timer_list *timer) unsigned long flags; int ret = -1; + debug_assert_init(timer); + base = lock_timer_base(timer, &flags); if (base->running_timer == timer) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 7392070..91dc4bc 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -4828,6 +4828,7 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { __ftrace_dump(true, oops_dump_mode); } +EXPORT_SYMBOL_GPL(ftrace_dump); __init static int tracer_alloc_buffers(void) { diff --git a/kernel/wait.c b/kernel/wait.c index 26fa779..7fdd9ea 100644 --- a/kernel/wait.c +++ b/kernel/wait.c @@ -10,10 +10,10 @@ #include <linux/wait.h> #include <linux/hash.h> -void __init_waitqueue_head(wait_queue_head_t *q, struct lock_class_key *key) +void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *key) { spin_lock_init(&q->lock); - lockdep_set_class(&q->lock, key); + lockdep_set_class_and_name(&q->lock, key, name); INIT_LIST_HEAD(&q->task_list); } diff --git a/lib/debugobjects.c b/lib/debugobjects.c index a78b7c6..77cb245 100644 --- a/lib/debugobjects.c +++ b/lib/debugobjects.c @@ -268,12 +268,16 @@ static void debug_print_object(struct debug_obj *obj, char *msg) * Try to repair the damage, so we have a better chance to get useful * debug output. */ -static void +static int debug_object_fixup(int (*fixup)(void *addr, enum debug_obj_state state), void * addr, enum debug_obj_state state) { + int fixed = 0; + if (fixup) - debug_objects_fixups += fixup(addr, state); + fixed = fixup(addr, state); + debug_objects_fixups += fixed; + return fixed; } static void debug_object_is_on_stack(void *addr, int onstack) @@ -386,6 +390,9 @@ void debug_object_activate(void *addr, struct debug_obj_descr *descr) struct debug_bucket *db; struct debug_obj *obj; unsigned long flags; + struct debug_obj o = { .object = addr, + .state = ODEBUG_STATE_NOTAVAILABLE, + .descr = descr }; if (!debug_objects_enabled) return; @@ -425,8 +432,9 @@ void debug_object_activate(void *addr, struct debug_obj_descr *descr) * let the type specific code decide whether this is * true or not. */ - debug_object_fixup(descr->fixup_activate, addr, - ODEBUG_STATE_NOTAVAILABLE); + if (debug_object_fixup(descr->fixup_activate, addr, + ODEBUG_STATE_NOTAVAILABLE)) + debug_print_object(&o, "activate"); } /** @@ -563,6 +571,44 @@ out_unlock: } /** + * debug_object_assert_init - debug checks when object should be init-ed + * @addr: address of the object + * @descr: pointer to an object specific debug description structure + */ +void debug_object_assert_init(void *addr, struct debug_obj_descr *descr) +{ + struct debug_bucket *db; + struct debug_obj *obj; + unsigned long flags; + + if (!debug_objects_enabled) + return; + + db = get_bucket((unsigned long) addr); + + raw_spin_lock_irqsave(&db->lock, flags); + + obj = lookup_object(addr, db); + if (!obj) { + struct debug_obj o = { .object = addr, + .state = ODEBUG_STATE_NOTAVAILABLE, + .descr = descr }; + + raw_spin_unlock_irqrestore(&db->lock, flags); + /* + * Maybe the object is static. Let the type specific + * code decide what to do. + */ + if (debug_object_fixup(descr->fixup_assert_init, addr, + ODEBUG_STATE_NOTAVAILABLE)) + debug_print_object(&o, "assert_init"); + return; + } + + raw_spin_unlock_irqrestore(&db->lock, flags); +} + +/** * debug_object_active_state - debug checks object usage state machine * @addr: address of the object * @descr: pointer to an object specific debug description structure @@ -131,6 +131,12 @@ config SPARSEMEM_VMEMMAP config HAVE_MEMBLOCK boolean +config HAVE_MEMBLOCK_NODE_MAP + boolean + +config ARCH_DISCARD_MEMBLOCK + boolean + config NO_BOOTMEM boolean diff --git a/mm/filemap.c b/mm/filemap.c index c106d3b..5f0a3c9 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1828,7 +1828,7 @@ repeat: page = __page_cache_alloc(gfp | __GFP_COLD); if (!page) return ERR_PTR(-ENOMEM); - err = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL); + err = add_to_page_cache_lru(page, mapping, index, gfp); if (unlikely(err)) { page_cache_release(page); if (err == -EEXIST) @@ -1925,10 +1925,7 @@ static struct page *wait_on_page_read(struct page *page) * @gfp: the page allocator flags to use if allocating * * This is the same as "read_mapping_page(mapping, index, NULL)", but with - * any new page allocations done using the specified allocation flags. Note - * that the Radix tree operations will still use GFP_KERNEL, so you can't - * expect to do this atomically or anything like that - but you can pass in - * other page requirements. + * any new page allocations done using the specified allocation flags. * * If the page does not get brought uptodate, return -EIO. */ diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 73f17c0..2316840 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -901,7 +901,6 @@ retry: h->resv_huge_pages += delta; ret = 0; - spin_unlock(&hugetlb_lock); /* Free the needed pages to the hugetlb pool */ list_for_each_entry_safe(page, tmp, &surplus_list, lru) { if ((--needed) < 0) @@ -915,6 +914,7 @@ retry: VM_BUG_ON(page_count(page)); enqueue_huge_page(h, page); } + spin_unlock(&hugetlb_lock); /* Free unnecessary surplus pages to the buddy allocator */ free: diff --git a/mm/memblock.c b/mm/memblock.c index 84bec49..2f55f19 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -20,12 +20,23 @@ #include <linux/seq_file.h> #include <linux/memblock.h> -struct memblock memblock __initdata_memblock; +static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; +static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; + +struct memblock memblock __initdata_memblock = { + .memory.regions = memblock_memory_init_regions, + .memory.cnt = 1, /* empty dummy entry */ + .memory.max = INIT_MEMBLOCK_REGIONS, + + .reserved.regions = memblock_reserved_init_regions, + .reserved.cnt = 1, /* empty dummy entry */ + .reserved.max = INIT_MEMBLOCK_REGIONS, + + .current_limit = MEMBLOCK_ALLOC_ANYWHERE, +}; int memblock_debug __initdata_memblock; -int memblock_can_resize __initdata_memblock; -static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS + 1] __initdata_memblock; -static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS + 1] __initdata_memblock; +static int memblock_can_resize __initdata_memblock; /* inline so we don't get a warning when pr_debug is compiled out */ static inline const char *memblock_type_name(struct memblock_type *type) @@ -38,20 +49,15 @@ static inline const char *memblock_type_name(struct memblock_type *type) return "unknown"; } -/* - * Address comparison utilities - */ - -static phys_addr_t __init_memblock memblock_align_down(phys_addr_t addr, phys_addr_t size) -{ - return addr & ~(size - 1); -} - -static phys_addr_t __init_memblock memblock_align_up(phys_addr_t addr, phys_addr_t size) +/* adjust *@size so that (@base + *@size) doesn't overflow, return new size */ +static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size) { - return (addr + (size - 1)) & ~(size - 1); + return *size = min(*size, (phys_addr_t)ULLONG_MAX - base); } +/* + * Address comparison utilities + */ static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, phys_addr_t base2, phys_addr_t size2) { @@ -73,83 +79,66 @@ static long __init_memblock memblock_overlaps_region(struct memblock_type *type, return (i < type->cnt) ? i : -1; } -/* - * Find, allocate, deallocate or reserve unreserved regions. All allocations - * are top-down. +/** + * memblock_find_in_range_node - find free area in given range and node + * @start: start of candidate range + * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} + * @size: size of free area to find + * @align: alignment of free area to find + * @nid: nid of the free area to find, %MAX_NUMNODES for any node + * + * Find @size free area aligned to @align in the specified range and node. + * + * RETURNS: + * Found address on success, %0 on failure. */ - -static phys_addr_t __init_memblock memblock_find_region(phys_addr_t start, phys_addr_t end, - phys_addr_t size, phys_addr_t align) +phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start, + phys_addr_t end, phys_addr_t size, + phys_addr_t align, int nid) { - phys_addr_t base, res_base; - long j; - - /* In case, huge size is requested */ - if (end < size) - return MEMBLOCK_ERROR; - - base = memblock_align_down((end - size), align); + phys_addr_t this_start, this_end, cand; + u64 i; - /* Prevent allocations returning 0 as it's also used to - * indicate an allocation failure - */ - if (start == 0) - start = PAGE_SIZE; - - while (start <= base) { - j = memblock_overlaps_region(&memblock.reserved, base, size); - if (j < 0) - return base; - res_base = memblock.reserved.regions[j].base; - if (res_base < size) - break; - base = memblock_align_down(res_base - size, align); - } + /* align @size to avoid excessive fragmentation on reserved array */ + size = round_up(size, align); - return MEMBLOCK_ERROR; -} - -static phys_addr_t __init_memblock memblock_find_base(phys_addr_t size, - phys_addr_t align, phys_addr_t start, phys_addr_t end) -{ - long i; - - BUG_ON(0 == size); - - /* Pump up max_addr */ + /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE) end = memblock.current_limit; - /* We do a top-down search, this tends to limit memory - * fragmentation by keeping early boot allocs near the - * top of memory - */ - for (i = memblock.memory.cnt - 1; i >= 0; i--) { - phys_addr_t memblockbase = memblock.memory.regions[i].base; - phys_addr_t memblocksize = memblock.memory.regions[i].size; - phys_addr_t bottom, top, found; + /* adjust @start to avoid underflow and allocating the first page */ + start = max3(start, size, (phys_addr_t)PAGE_SIZE); + end = max(start, end); - if (memblocksize < size) - continue; - if ((memblockbase + memblocksize) <= start) - break; - bottom = max(memblockbase, start); - top = min(memblockbase + memblocksize, end); - if (bottom >= top) - continue; - found = memblock_find_region(bottom, top, size, align); - if (found != MEMBLOCK_ERROR) - return found; + for_each_free_mem_range_reverse(i, nid, &this_start, &this_end, NULL) { + this_start = clamp(this_start, start, end); + this_end = clamp(this_end, start, end); + + cand = round_down(this_end - size, align); + if (cand >= this_start) + return cand; } - return MEMBLOCK_ERROR; + return 0; } -/* - * Find a free area with specified alignment in a specific range. +/** + * memblock_find_in_range - find free area in given range + * @start: start of candidate range + * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE} + * @size: size of free area to find + * @align: alignment of free area to find + * + * Find @size free area aligned to @align in the specified range. + * + * RETURNS: + * Found address on success, %0 on failure. */ -u64 __init_memblock memblock_find_in_range(u64 start, u64 end, u64 size, u64 align) +phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, + phys_addr_t end, phys_addr_t size, + phys_addr_t align) { - return memblock_find_base(size, align, start, end); + return memblock_find_in_range_node(start, end, size, align, + MAX_NUMNODES); } /* @@ -178,25 +167,21 @@ int __init_memblock memblock_reserve_reserved_regions(void) static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r) { - unsigned long i; - - for (i = r; i < type->cnt - 1; i++) { - type->regions[i].base = type->regions[i + 1].base; - type->regions[i].size = type->regions[i + 1].size; - } + type->total_size -= type->regions[r].size; + memmove(&type->regions[r], &type->regions[r + 1], + (type->cnt - (r + 1)) * sizeof(type->regions[r])); type->cnt--; /* Special case for empty arrays */ if (type->cnt == 0) { + WARN_ON(type->total_size != 0); type->cnt = 1; type->regions[0].base = 0; type->regions[0].size = 0; + memblock_set_region_node(&type->regions[0], MAX_NUMNODES); } } -/* Defined below but needed now */ -static long memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size); - static int __init_memblock memblock_double_array(struct memblock_type *type) { struct memblock_region *new_array, *old_array; @@ -226,10 +211,10 @@ static int __init_memblock memblock_double_array(struct memblock_type *type) */ if (use_slab) { new_array = kmalloc(new_size, GFP_KERNEL); - addr = new_array == NULL ? MEMBLOCK_ERROR : __pa(new_array); + addr = new_array ? __pa(new_array) : 0; } else - addr = memblock_find_base(new_size, sizeof(phys_addr_t), 0, MEMBLOCK_ALLOC_ACCESSIBLE); - if (addr == MEMBLOCK_ERROR) { + addr = memblock_find_in_range(0, MEMBLOCK_ALLOC_ACCESSIBLE, new_size, sizeof(phys_addr_t)); + if (!addr) { pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n", memblock_type_name(type), type->max, type->max * 2); return -1; @@ -254,7 +239,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type) return 0; /* Add the new reserved region now. Should not fail ! */ - BUG_ON(memblock_add_region(&memblock.reserved, addr, new_size)); + BUG_ON(memblock_reserve(addr, new_size)); /* If the array wasn't our static init one, then free it. We only do * that before SLAB is available as later on, we don't know whether @@ -268,343 +253,514 @@ static int __init_memblock memblock_double_array(struct memblock_type *type) return 0; } -int __init_memblock __weak memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1, - phys_addr_t addr2, phys_addr_t size2) -{ - return 1; -} - -static long __init_memblock memblock_add_region(struct memblock_type *type, - phys_addr_t base, phys_addr_t size) +/** + * memblock_merge_regions - merge neighboring compatible regions + * @type: memblock type to scan + * + * Scan @type and merge neighboring compatible regions. + */ +static void __init_memblock memblock_merge_regions(struct memblock_type *type) { - phys_addr_t end = base + size; - int i, slot = -1; - - /* First try and coalesce this MEMBLOCK with others */ - for (i = 0; i < type->cnt; i++) { - struct memblock_region *rgn = &type->regions[i]; - phys_addr_t rend = rgn->base + rgn->size; + int i = 0; - /* Exit if there's no possible hits */ - if (rgn->base > end || rgn->size == 0) - break; + /* cnt never goes below 1 */ + while (i < type->cnt - 1) { + struct memblock_region *this = &type->regions[i]; + struct memblock_region *next = &type->regions[i + 1]; - /* Check if we are fully enclosed within an existing - * block - */ - if (rgn->base <= base && rend >= end) - return 0; + if (this->base + this->size != next->base || + memblock_get_region_node(this) != + memblock_get_region_node(next)) { + BUG_ON(this->base + this->size > next->base); + i++; + continue; + } - /* Check if we overlap or are adjacent with the bottom - * of a block. - */ - if (base < rgn->base && end >= rgn->base) { - /* If we can't coalesce, create a new block */ - if (!memblock_memory_can_coalesce(base, size, - rgn->base, - rgn->size)) { - /* Overlap & can't coalesce are mutually - * exclusive, if you do that, be prepared - * for trouble - */ - WARN_ON(end != rgn->base); - goto new_block; - } - /* We extend the bottom of the block down to our - * base - */ - rgn->base = base; - rgn->size = rend - base; + this->size += next->size; + memmove(next, next + 1, (type->cnt - (i + 1)) * sizeof(*next)); + type->cnt--; + } +} - /* Return if we have nothing else to allocate - * (fully coalesced) - */ - if (rend >= end) - return 0; +/** + * memblock_insert_region - insert new memblock region + * @type: memblock type to insert into + * @idx: index for the insertion point + * @base: base address of the new region + * @size: size of the new region + * + * Insert new memblock region [@base,@base+@size) into @type at @idx. + * @type must already have extra room to accomodate the new region. + */ +static void __init_memblock memblock_insert_region(struct memblock_type *type, + int idx, phys_addr_t base, + phys_addr_t size, int nid) +{ + struct memblock_region *rgn = &type->regions[idx]; - /* We continue processing from the end of the - * coalesced block. - */ - base = rend; - size = end - base; - } + BUG_ON(type->cnt >= type->max); + memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn)); + rgn->base = base; + rgn->size = size; + memblock_set_region_node(rgn, nid); + type->cnt++; + type->total_size += size; +} - /* Now check if we overlap or are adjacent with the - * top of a block - */ - if (base <= rend && end >= rend) { - /* If we can't coalesce, create a new block */ - if (!memblock_memory_can_coalesce(rgn->base, - rgn->size, - base, size)) { - /* Overlap & can't coalesce are mutually - * exclusive, if you do that, be prepared - * for trouble - */ - WARN_ON(rend != base); - goto new_block; - } - /* We adjust our base down to enclose the - * original block and destroy it. It will be - * part of our new allocation. Since we've - * freed an entry, we know we won't fail - * to allocate one later, so we won't risk - * losing the original block allocation. - */ - size += (base - rgn->base); - base = rgn->base; - memblock_remove_region(type, i--); - } - } +/** + * memblock_add_region - add new memblock region + * @type: memblock type to add new region into + * @base: base address of the new region + * @size: size of the new region + * @nid: nid of the new region + * + * Add new memblock region [@base,@base+@size) into @type. The new region + * is allowed to overlap with existing ones - overlaps don't affect already + * existing regions. @type is guaranteed to be minimal (all neighbouring + * compatible regions are merged) after the addition. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +static int __init_memblock memblock_add_region(struct memblock_type *type, + phys_addr_t base, phys_addr_t size, int nid) +{ + bool insert = false; + phys_addr_t obase = base; + phys_addr_t end = base + memblock_cap_size(base, &size); + int i, nr_new; - /* If the array is empty, special case, replace the fake - * filler region and return - */ - if ((type->cnt == 1) && (type->regions[0].size == 0)) { + /* special case for empty array */ + if (type->regions[0].size == 0) { + WARN_ON(type->cnt != 1 || type->total_size); type->regions[0].base = base; type->regions[0].size = size; + memblock_set_region_node(&type->regions[0], nid); + type->total_size = size; return 0; } - - new_block: - /* If we are out of space, we fail. It's too late to resize the array - * but then this shouldn't have happened in the first place. +repeat: + /* + * The following is executed twice. Once with %false @insert and + * then with %true. The first counts the number of regions needed + * to accomodate the new area. The second actually inserts them. */ - if (WARN_ON(type->cnt >= type->max)) - return -1; + base = obase; + nr_new = 0; - /* Couldn't coalesce the MEMBLOCK, so add it to the sorted table. */ - for (i = type->cnt - 1; i >= 0; i--) { - if (base < type->regions[i].base) { - type->regions[i+1].base = type->regions[i].base; - type->regions[i+1].size = type->regions[i].size; - } else { - type->regions[i+1].base = base; - type->regions[i+1].size = size; - slot = i + 1; + for (i = 0; i < type->cnt; i++) { + struct memblock_region *rgn = &type->regions[i]; + phys_addr_t rbase = rgn->base; + phys_addr_t rend = rbase + rgn->size; + + if (rbase >= end) break; + if (rend <= base) + continue; + /* + * @rgn overlaps. If it separates the lower part of new + * area, insert that portion. + */ + if (rbase > base) { + nr_new++; + if (insert) + memblock_insert_region(type, i++, base, + rbase - base, nid); } + /* area below @rend is dealt with, forget about it */ + base = min(rend, end); } - if (base < type->regions[0].base) { - type->regions[0].base = base; - type->regions[0].size = size; - slot = 0; + + /* insert the remaining portion */ + if (base < end) { + nr_new++; + if (insert) + memblock_insert_region(type, i, base, end - base, nid); } - type->cnt++; - /* The array is full ? Try to resize it. If that fails, we undo - * our allocation and return an error + /* + * If this was the first round, resize array and repeat for actual + * insertions; otherwise, merge and return. */ - if (type->cnt == type->max && memblock_double_array(type)) { - BUG_ON(slot < 0); - memblock_remove_region(type, slot); - return -1; + if (!insert) { + while (type->cnt + nr_new > type->max) + if (memblock_double_array(type) < 0) + return -ENOMEM; + insert = true; + goto repeat; + } else { + memblock_merge_regions(type); + return 0; } - - return 0; } -long __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) +int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, + int nid) { - return memblock_add_region(&memblock.memory, base, size); + return memblock_add_region(&memblock.memory, base, size, nid); +} +int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) +{ + return memblock_add_region(&memblock.memory, base, size, MAX_NUMNODES); } -static long __init_memblock __memblock_remove(struct memblock_type *type, - phys_addr_t base, phys_addr_t size) +/** + * memblock_isolate_range - isolate given range into disjoint memblocks + * @type: memblock type to isolate range for + * @base: base of range to isolate + * @size: size of range to isolate + * @start_rgn: out parameter for the start of isolated region + * @end_rgn: out parameter for the end of isolated region + * + * Walk @type and ensure that regions don't cross the boundaries defined by + * [@base,@base+@size). Crossing regions are split at the boundaries, + * which may create at most two more regions. The index of the first + * region inside the range is returned in *@start_rgn and end in *@end_rgn. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +static int __init_memblock memblock_isolate_range(struct memblock_type *type, + phys_addr_t base, phys_addr_t size, + int *start_rgn, int *end_rgn) { - phys_addr_t end = base + size; + phys_addr_t end = base + memblock_cap_size(base, &size); int i; - /* Walk through the array for collisions */ + *start_rgn = *end_rgn = 0; + + /* we'll create at most two more regions */ + while (type->cnt + 2 > type->max) + if (memblock_double_array(type) < 0) + return -ENOMEM; + for (i = 0; i < type->cnt; i++) { struct memblock_region *rgn = &type->regions[i]; - phys_addr_t rend = rgn->base + rgn->size; + phys_addr_t rbase = rgn->base; + phys_addr_t rend = rbase + rgn->size; - /* Nothing more to do, exit */ - if (rgn->base > end || rgn->size == 0) + if (rbase >= end) break; - - /* If we fully enclose the block, drop it */ - if (base <= rgn->base && end >= rend) { - memblock_remove_region(type, i--); + if (rend <= base) continue; - } - /* If we are fully enclosed within a block - * then we need to split it and we are done - */ - if (base > rgn->base && end < rend) { - rgn->size = base - rgn->base; - if (!memblock_add_region(type, end, rend - end)) - return 0; - /* Failure to split is bad, we at least - * restore the block before erroring + if (rbase < base) { + /* + * @rgn intersects from below. Split and continue + * to process the next region - the new top half. + */ + rgn->base = base; + rgn->size -= base - rbase; + type->total_size -= base - rbase; + memblock_insert_region(type, i, rbase, base - rbase, + memblock_get_region_node(rgn)); + } else if (rend > end) { + /* + * @rgn intersects from above. Split and redo the + * current region - the new bottom half. */ - rgn->size = rend - rgn->base; - WARN_ON(1); - return -1; - } - - /* Check if we need to trim the bottom of a block */ - if (rgn->base < end && rend > end) { - rgn->size -= end - rgn->base; rgn->base = end; - break; + rgn->size -= end - rbase; + type->total_size -= end - rbase; + memblock_insert_region(type, i--, rbase, end - rbase, + memblock_get_region_node(rgn)); + } else { + /* @rgn is fully contained, record it */ + if (!*end_rgn) + *start_rgn = i; + *end_rgn = i + 1; } + } - /* And check if we need to trim the top of a block */ - if (base < rend) - rgn->size -= rend - base; + return 0; +} - } +static int __init_memblock __memblock_remove(struct memblock_type *type, + phys_addr_t base, phys_addr_t size) +{ + int start_rgn, end_rgn; + int i, ret; + + ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); + if (ret) + return ret; + + for (i = end_rgn - 1; i >= start_rgn; i--) + memblock_remove_region(type, i); return 0; } -long __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) +int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) { return __memblock_remove(&memblock.memory, base, size); } -long __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) +int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) { + memblock_dbg(" memblock_free: [%#016llx-%#016llx] %pF\n", + (unsigned long long)base, + (unsigned long long)base + size, + (void *)_RET_IP_); + return __memblock_remove(&memblock.reserved, base, size); } -long __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) +int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) { struct memblock_type *_rgn = &memblock.reserved; + memblock_dbg("memblock_reserve: [%#016llx-%#016llx] %pF\n", + (unsigned long long)base, + (unsigned long long)base + size, + (void *)_RET_IP_); BUG_ON(0 == size); - return memblock_add_region(_rgn, base, size); + return memblock_add_region(_rgn, base, size, MAX_NUMNODES); } -phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr) +/** + * __next_free_mem_range - next function for for_each_free_mem_range() + * @idx: pointer to u64 loop variable + * @nid: nid: node selector, %MAX_NUMNODES for all nodes + * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL + * @p_nid: ptr to int for nid of the range, can be %NULL + * + * Find the first free area from *@idx which matches @nid, fill the out + * parameters, and update *@idx for the next iteration. The lower 32bit of + * *@idx contains index into memory region and the upper 32bit indexes the + * areas before each reserved region. For example, if reserved regions + * look like the following, + * + * 0:[0-16), 1:[32-48), 2:[128-130) + * + * The upper 32bit indexes the following regions. + * + * 0:[0-0), 1:[16-32), 2:[48-128), 3:[130-MAX) + * + * As both region arrays are sorted, the function advances the two indices + * in lockstep and returns each intersection. + */ +void __init_memblock __next_free_mem_range(u64 *idx, int nid, + phys_addr_t *out_start, + phys_addr_t *out_end, int *out_nid) { - phys_addr_t found; + struct memblock_type *mem = &memblock.memory; + struct memblock_type *rsv = &memblock.reserved; + int mi = *idx & 0xffffffff; + int ri = *idx >> 32; - /* We align the size to limit fragmentation. Without this, a lot of - * small allocs quickly eat up the whole reserve array on sparc - */ - size = memblock_align_up(size, align); + for ( ; mi < mem->cnt; mi++) { + struct memblock_region *m = &mem->regions[mi]; + phys_addr_t m_start = m->base; + phys_addr_t m_end = m->base + m->size; - found = memblock_find_base(size, align, 0, max_addr); - if (found != MEMBLOCK_ERROR && - !memblock_add_region(&memblock.reserved, found, size)) - return found; + /* only memory regions are associated with nodes, check it */ + if (nid != MAX_NUMNODES && nid != memblock_get_region_node(m)) + continue; - return 0; + /* scan areas before each reservation for intersection */ + for ( ; ri < rsv->cnt + 1; ri++) { + struct memblock_region *r = &rsv->regions[ri]; + phys_addr_t r_start = ri ? r[-1].base + r[-1].size : 0; + phys_addr_t r_end = ri < rsv->cnt ? r->base : ULLONG_MAX; + + /* if ri advanced past mi, break out to advance mi */ + if (r_start >= m_end) + break; + /* if the two regions intersect, we're done */ + if (m_start < r_end) { + if (out_start) + *out_start = max(m_start, r_start); + if (out_end) + *out_end = min(m_end, r_end); + if (out_nid) + *out_nid = memblock_get_region_node(m); + /* + * The region which ends first is advanced + * for the next iteration. + */ + if (m_end <= r_end) + mi++; + else + ri++; + *idx = (u32)mi | (u64)ri << 32; + return; + } + } + } + + /* signal end of iteration */ + *idx = ULLONG_MAX; } -phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr) +/** + * __next_free_mem_range_rev - next function for for_each_free_mem_range_reverse() + * @idx: pointer to u64 loop variable + * @nid: nid: node selector, %MAX_NUMNODES for all nodes + * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL + * @p_nid: ptr to int for nid of the range, can be %NULL + * + * Reverse of __next_free_mem_range(). + */ +void __init_memblock __next_free_mem_range_rev(u64 *idx, int nid, + phys_addr_t *out_start, + phys_addr_t *out_end, int *out_nid) { - phys_addr_t alloc; + struct memblock_type *mem = &memblock.memory; + struct memblock_type *rsv = &memblock.reserved; + int mi = *idx & 0xffffffff; + int ri = *idx >> 32; - alloc = __memblock_alloc_base(size, align, max_addr); + if (*idx == (u64)ULLONG_MAX) { + mi = mem->cnt - 1; + ri = rsv->cnt; + } - if (alloc == 0) - panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n", - (unsigned long long) size, (unsigned long long) max_addr); + for ( ; mi >= 0; mi--) { + struct memblock_region *m = &mem->regions[mi]; + phys_addr_t m_start = m->base; + phys_addr_t m_end = m->base + m->size; - return alloc; -} + /* only memory regions are associated with nodes, check it */ + if (nid != MAX_NUMNODES && nid != memblock_get_region_node(m)) + continue; -phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); -} + /* scan areas before each reservation for intersection */ + for ( ; ri >= 0; ri--) { + struct memblock_region *r = &rsv->regions[ri]; + phys_addr_t r_start = ri ? r[-1].base + r[-1].size : 0; + phys_addr_t r_end = ri < rsv->cnt ? r->base : ULLONG_MAX; + + /* if ri advanced past mi, break out to advance mi */ + if (r_end <= m_start) + break; + /* if the two regions intersect, we're done */ + if (m_end > r_start) { + if (out_start) + *out_start = max(m_start, r_start); + if (out_end) + *out_end = min(m_end, r_end); + if (out_nid) + *out_nid = memblock_get_region_node(m); + + if (m_start >= r_start) + mi--; + else + ri--; + *idx = (u32)mi | (u64)ri << 32; + return; + } + } + } + *idx = ULLONG_MAX; +} +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP /* - * Additional node-local allocators. Search for node memory is bottom up - * and walks memblock regions within that node bottom-up as well, but allocation - * within an memblock region is top-down. XXX I plan to fix that at some stage - * - * WARNING: Only available after early_node_map[] has been populated, - * on some architectures, that is after all the calls to add_active_range() - * have been done to populate it. + * Common iterator interface used to define for_each_mem_range(). */ - -phys_addr_t __weak __init memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid) +void __init_memblock __next_mem_pfn_range(int *idx, int nid, + unsigned long *out_start_pfn, + unsigned long *out_end_pfn, int *out_nid) { -#ifdef CONFIG_ARCH_POPULATES_NODE_MAP - /* - * This code originates from sparc which really wants use to walk by addresses - * and returns the nid. This is not very convenient for early_pfn_map[] users - * as the map isn't sorted yet, and it really wants to be walked by nid. - * - * For now, I implement the inefficient method below which walks the early - * map multiple times. Eventually we may want to use an ARCH config option - * to implement a completely different method for both case. - */ - unsigned long start_pfn, end_pfn; - int i; + struct memblock_type *type = &memblock.memory; + struct memblock_region *r; - for (i = 0; i < MAX_NUMNODES; i++) { - get_pfn_range_for_nid(i, &start_pfn, &end_pfn); - if (start < PFN_PHYS(start_pfn) || start >= PFN_PHYS(end_pfn)) + while (++*idx < type->cnt) { + r = &type->regions[*idx]; + + if (PFN_UP(r->base) >= PFN_DOWN(r->base + r->size)) continue; - *nid = i; - return min(end, PFN_PHYS(end_pfn)); + if (nid == MAX_NUMNODES || nid == r->nid) + break; + } + if (*idx >= type->cnt) { + *idx = -1; + return; } -#endif - *nid = 0; - return end; + if (out_start_pfn) + *out_start_pfn = PFN_UP(r->base); + if (out_end_pfn) + *out_end_pfn = PFN_DOWN(r->base + r->size); + if (out_nid) + *out_nid = r->nid; } -static phys_addr_t __init memblock_alloc_nid_region(struct memblock_region *mp, - phys_addr_t size, - phys_addr_t align, int nid) +/** + * memblock_set_node - set node ID on memblock regions + * @base: base of area to set node ID for + * @size: size of area to set node ID for + * @nid: node ID to set + * + * Set the nid of memblock memory regions in [@base,@base+@size) to @nid. + * Regions which cross the area boundaries are split as necessary. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, + int nid) { - phys_addr_t start, end; + struct memblock_type *type = &memblock.memory; + int start_rgn, end_rgn; + int i, ret; - start = mp->base; - end = start + mp->size; + ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn); + if (ret) + return ret; - start = memblock_align_up(start, align); - while (start < end) { - phys_addr_t this_end; - int this_nid; + for (i = start_rgn; i < end_rgn; i++) + type->regions[i].nid = nid; - this_end = memblock_nid_range(start, end, &this_nid); - if (this_nid == nid) { - phys_addr_t ret = memblock_find_region(start, this_end, size, align); - if (ret != MEMBLOCK_ERROR && - !memblock_add_region(&memblock.reserved, ret, size)) - return ret; - } - start = this_end; - } + memblock_merge_regions(type); + return 0; +} +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ + +static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size, + phys_addr_t align, phys_addr_t max_addr, + int nid) +{ + phys_addr_t found; - return MEMBLOCK_ERROR; + found = memblock_find_in_range_node(0, max_addr, size, align, nid); + if (found && !memblock_reserve(found, size)) + return found; + + return 0; } phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid) { - struct memblock_type *mem = &memblock.memory; - int i; + return memblock_alloc_base_nid(size, align, MEMBLOCK_ALLOC_ACCESSIBLE, nid); +} - BUG_ON(0 == size); +phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr) +{ + return memblock_alloc_base_nid(size, align, max_addr, MAX_NUMNODES); +} - /* We align the size to limit fragmentation. Without this, a lot of - * small allocs quickly eat up the whole reserve array on sparc - */ - size = memblock_align_up(size, align); +phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr) +{ + phys_addr_t alloc; - /* We do a bottom-up search for a region with the right - * nid since that's easier considering how memblock_nid_range() - * works - */ - for (i = 0; i < mem->cnt; i++) { - phys_addr_t ret = memblock_alloc_nid_region(&mem->regions[i], - size, align, nid); - if (ret != MEMBLOCK_ERROR) - return ret; - } + alloc = __memblock_alloc_base(size, align, max_addr); - return 0; + if (alloc == 0) + panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n", + (unsigned long long) size, (unsigned long long) max_addr); + + return alloc; +} + +phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align) +{ + return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); } phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) @@ -613,7 +769,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i if (res) return res; - return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE); + return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); } @@ -621,10 +777,9 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i * Remaining API functions */ -/* You must call memblock_analyze() before this. */ phys_addr_t __init memblock_phys_mem_size(void) { - return memblock.memory_size; + return memblock.memory.total_size; } /* lowest address */ @@ -640,45 +795,28 @@ phys_addr_t __init_memblock memblock_end_of_DRAM(void) return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size); } -/* You must call memblock_analyze() after this. */ -void __init memblock_enforce_memory_limit(phys_addr_t memory_limit) +void __init memblock_enforce_memory_limit(phys_addr_t limit) { unsigned long i; - phys_addr_t limit; - struct memblock_region *p; + phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX; - if (!memory_limit) + if (!limit) return; - /* Truncate the memblock regions to satisfy the memory limit. */ - limit = memory_limit; + /* find out max address */ for (i = 0; i < memblock.memory.cnt; i++) { - if (limit > memblock.memory.regions[i].size) { - limit -= memblock.memory.regions[i].size; - continue; - } - - memblock.memory.regions[i].size = limit; - memblock.memory.cnt = i + 1; - break; - } - - memory_limit = memblock_end_of_DRAM(); + struct memblock_region *r = &memblock.memory.regions[i]; - /* And truncate any reserves above the limit also. */ - for (i = 0; i < memblock.reserved.cnt; i++) { - p = &memblock.reserved.regions[i]; - - if (p->base > memory_limit) - p->size = 0; - else if ((p->base + p->size) > memory_limit) - p->size = memory_limit - p->base; - - if (p->size == 0) { - memblock_remove_region(&memblock.reserved, i); - i--; + if (limit <= r->size) { + max_addr = r->base + limit; + break; } + limit -= r->size; } + + /* truncate both memory and reserved regions */ + __memblock_remove(&memblock.memory, max_addr, (phys_addr_t)ULLONG_MAX); + __memblock_remove(&memblock.reserved, max_addr, (phys_addr_t)ULLONG_MAX); } static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr) @@ -712,16 +850,18 @@ int __init_memblock memblock_is_memory(phys_addr_t addr) int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size) { int idx = memblock_search(&memblock.memory, base); + phys_addr_t end = base + memblock_cap_size(base, &size); if (idx == -1) return 0; return memblock.memory.regions[idx].base <= base && (memblock.memory.regions[idx].base + - memblock.memory.regions[idx].size) >= (base + size); + memblock.memory.regions[idx].size) >= end; } int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size) { + memblock_cap_size(base, &size); return memblock_overlaps_region(&memblock.reserved, base, size) >= 0; } @@ -731,86 +871,45 @@ void __init_memblock memblock_set_current_limit(phys_addr_t limit) memblock.current_limit = limit; } -static void __init_memblock memblock_dump(struct memblock_type *region, char *name) +static void __init_memblock memblock_dump(struct memblock_type *type, char *name) { unsigned long long base, size; int i; - pr_info(" %s.cnt = 0x%lx\n", name, region->cnt); + pr_info(" %s.cnt = 0x%lx\n", name, type->cnt); - for (i = 0; i < region->cnt; i++) { - base = region->regions[i].base; - size = region->regions[i].size; - - pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes\n", - name, i, base, base + size - 1, size); + for (i = 0; i < type->cnt; i++) { + struct memblock_region *rgn = &type->regions[i]; + char nid_buf[32] = ""; + + base = rgn->base; + size = rgn->size; +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP + if (memblock_get_region_node(rgn) != MAX_NUMNODES) + snprintf(nid_buf, sizeof(nid_buf), " on node %d", + memblock_get_region_node(rgn)); +#endif + pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s\n", + name, i, base, base + size - 1, size, nid_buf); } } -void __init_memblock memblock_dump_all(void) +void __init_memblock __memblock_dump_all(void) { - if (!memblock_debug) - return; - pr_info("MEMBLOCK configuration:\n"); - pr_info(" memory size = 0x%llx\n", (unsigned long long)memblock.memory_size); + pr_info(" memory size = %#llx reserved size = %#llx\n", + (unsigned long long)memblock.memory.total_size, + (unsigned long long)memblock.reserved.total_size); memblock_dump(&memblock.memory, "memory"); memblock_dump(&memblock.reserved, "reserved"); } -void __init memblock_analyze(void) +void __init memblock_allow_resize(void) { - int i; - - /* Check marker in the unused last array entry */ - WARN_ON(memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS].base - != MEMBLOCK_INACTIVE); - WARN_ON(memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS].base - != MEMBLOCK_INACTIVE); - - memblock.memory_size = 0; - - for (i = 0; i < memblock.memory.cnt; i++) - memblock.memory_size += memblock.memory.regions[i].size; - - /* We allow resizing from there */ memblock_can_resize = 1; } -void __init memblock_init(void) -{ - static int init_done __initdata = 0; - - if (init_done) - return; - init_done = 1; - - /* Hookup the initial arrays */ - memblock.memory.regions = memblock_memory_init_regions; - memblock.memory.max = INIT_MEMBLOCK_REGIONS; - memblock.reserved.regions = memblock_reserved_init_regions; - memblock.reserved.max = INIT_MEMBLOCK_REGIONS; - - /* Write a marker in the unused last array entry */ - memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = MEMBLOCK_INACTIVE; - memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = MEMBLOCK_INACTIVE; - - /* Create a dummy zero size MEMBLOCK which will get coalesced away later. - * This simplifies the memblock_add() code below... - */ - memblock.memory.regions[0].base = 0; - memblock.memory.regions[0].size = 0; - memblock.memory.cnt = 1; - - /* Ditto. */ - memblock.reserved.regions[0].base = 0; - memblock.reserved.regions[0].size = 0; - memblock.reserved.cnt = 1; - - memblock.current_limit = MEMBLOCK_ALLOC_ANYWHERE; -} - static int __init early_memblock(char *p) { if (p && strstr(p, "debug")) @@ -819,7 +918,7 @@ static int __init early_memblock(char *p) } early_param("memblock", early_memblock); -#if defined(CONFIG_DEBUG_FS) && !defined(ARCH_DISCARD_MEMBLOCK) +#if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_ARCH_DISCARD_MEMBLOCK) static int memblock_debug_show(struct seq_file *m, void *private) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 6aff93c..b63f5f7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4907,9 +4907,9 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) int cpu; enable_swap_cgroup(); parent = NULL; - root_mem_cgroup = memcg; if (mem_cgroup_soft_limit_tree_init()) goto free_out; + root_mem_cgroup = memcg; for_each_possible_cpu(cpu) { struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); @@ -4948,7 +4948,6 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) return &memcg->css; free_out: __mem_cgroup_free(memcg); - root_mem_cgroup = NULL; return ERR_PTR(error); } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index adc3954..c3fdbcb 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -636,6 +636,7 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, struct vm_area_struct *prev; struct vm_area_struct *vma; int err = 0; + pgoff_t pgoff; unsigned long vmstart; unsigned long vmend; @@ -643,13 +644,21 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, if (!vma || vma->vm_start > start) return -EFAULT; + if (start > vma->vm_start) + prev = vma; + for (; vma && vma->vm_start < end; prev = vma, vma = next) { next = vma->vm_next; vmstart = max(start, vma->vm_start); vmend = min(end, vma->vm_end); + if (mpol_equal(vma_policy(vma), new_pol)) + continue; + + pgoff = vma->vm_pgoff + + ((vmstart - vma->vm_start) >> PAGE_SHIFT); prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, - vma->anon_vma, vma->vm_file, vma->vm_pgoff, + vma->anon_vma, vma->vm_file, pgoff, new_pol); if (prev) { vma = prev; diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 7fa41b4..24f0fc1 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -41,14 +41,13 @@ static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, if (limit > memblock.current_limit) limit = memblock.current_limit; - addr = find_memory_core_early(nid, size, align, goal, limit); - - if (addr == MEMBLOCK_ERROR) + addr = memblock_find_in_range_node(goal, limit, size, align, nid); + if (!addr) return NULL; ptr = phys_to_virt(addr); memset(ptr, 0, size); - memblock_x86_reserve_range(addr, addr + size, "BOOTMEM"); + memblock_reserve(addr, size); /* * The min_count is set to 0 so that bootmem allocated blocks * are never reported as leaks. @@ -107,23 +106,27 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end) __free_pages_bootmem(pfn_to_page(i), 0); } -unsigned long __init free_all_memory_core_early(int nodeid) +unsigned long __init free_low_memory_core_early(int nodeid) { - int i; - u64 start, end; unsigned long count = 0; - struct range *range = NULL; - int nr_range; - - nr_range = get_free_all_memory_range(&range, nodeid); - - for (i = 0; i < nr_range; i++) { - start = range[i].start; - end = range[i].end; - count += end - start; - __free_pages_memory(start, end); + phys_addr_t start, end; + u64 i; + + /* free reserved array temporarily so that it's treated as free area */ + memblock_free_reserved_regions(); + + for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) { + unsigned long start_pfn = PFN_UP(start); + unsigned long end_pfn = min_t(unsigned long, + PFN_DOWN(end), max_low_pfn); + if (start_pfn < end_pfn) { + __free_pages_memory(start_pfn, end_pfn); + count += end_pfn - start_pfn; + } } + /* put region array back? */ + memblock_reserve_reserved_regions(); return count; } @@ -137,7 +140,7 @@ unsigned long __init free_all_bootmem_node(pg_data_t *pgdat) { register_page_bootmem_info_node(pgdat); - /* free_all_memory_core_early(MAX_NUMNODES) will be called later */ + /* free_low_memory_core_early(MAX_NUMNODES) will be called later */ return 0; } @@ -155,7 +158,7 @@ unsigned long __init free_all_bootmem(void) * Use MAX_NUMNODES will make sure all ranges in early_node_map[] * will be used instead of only Node0 related */ - return free_all_memory_core_early(MAX_NUMNODES); + return free_low_memory_core_early(MAX_NUMNODES); } /** @@ -172,7 +175,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, unsigned long size) { kmemleak_free_part(__va(physaddr), size); - memblock_x86_free_range(physaddr, physaddr + size); + memblock_free(physaddr, size); } /** @@ -187,7 +190,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, void __init free_bootmem(unsigned long addr, unsigned long size) { kmemleak_free_part(__va(addr), size); - memblock_x86_free_range(addr, addr + size); + memblock_free(addr, size); } static void * __init ___alloc_bootmem_nopanic(unsigned long size, diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 76f2c5a..069b64e 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -176,7 +176,7 @@ static bool oom_unkillable_task(struct task_struct *p, unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, const nodemask_t *nodemask, unsigned long totalpages) { - int points; + long points; if (oom_unkillable_task(p, mem, nodemask)) return 0; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2b8ba3a..bdc804c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -181,39 +181,17 @@ static unsigned long __meminitdata nr_kernel_pages; static unsigned long __meminitdata nr_all_pages; static unsigned long __meminitdata dma_reserve; -#ifdef CONFIG_ARCH_POPULATES_NODE_MAP - /* - * MAX_ACTIVE_REGIONS determines the maximum number of distinct - * ranges of memory (RAM) that may be registered with add_active_range(). - * Ranges passed to add_active_range() will be merged if possible - * so the number of times add_active_range() can be called is - * related to the number of nodes and the number of holes - */ - #ifdef CONFIG_MAX_ACTIVE_REGIONS - /* Allow an architecture to set MAX_ACTIVE_REGIONS to save memory */ - #define MAX_ACTIVE_REGIONS CONFIG_MAX_ACTIVE_REGIONS - #else - #if MAX_NUMNODES >= 32 - /* If there can be many nodes, allow up to 50 holes per node */ - #define MAX_ACTIVE_REGIONS (MAX_NUMNODES*50) - #else - /* By default, allow up to 256 distinct regions */ - #define MAX_ACTIVE_REGIONS 256 - #endif - #endif - - static struct node_active_region __meminitdata early_node_map[MAX_ACTIVE_REGIONS]; - static int __meminitdata nr_nodemap_entries; - static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES]; - static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES]; - static unsigned long __initdata required_kernelcore; - static unsigned long __initdata required_movablecore; - static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES]; - - /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */ - int movable_zone; - EXPORT_SYMBOL(movable_zone); -#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES]; +static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES]; +static unsigned long __initdata required_kernelcore; +static unsigned long __initdata required_movablecore; +static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES]; + +/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */ +int movable_zone; +EXPORT_SYMBOL(movable_zone); +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ #if MAX_NUMNODES > 1 int nr_node_ids __read_mostly = MAX_NUMNODES; @@ -706,10 +684,10 @@ void __meminit __free_pages_bootmem(struct page *page, unsigned int order) int loop; prefetchw(page); - for (loop = 0; loop < BITS_PER_LONG; loop++) { + for (loop = 0; loop < (1 << order); loop++) { struct page *p = &page[loop]; - if (loop + 1 < BITS_PER_LONG) + if (loop + 1 < (1 << order)) prefetchw(p + 1); __ClearPageReserved(p); set_page_count(p, 0); @@ -3737,35 +3715,7 @@ __meminit int init_currently_empty_zone(struct zone *zone, return 0; } -#ifdef CONFIG_ARCH_POPULATES_NODE_MAP -/* - * Basic iterator support. Return the first range of PFNs for a node - * Note: nid == MAX_NUMNODES returns first region regardless of node - */ -static int __meminit first_active_region_index_in_nid(int nid) -{ - int i; - - for (i = 0; i < nr_nodemap_entries; i++) - if (nid == MAX_NUMNODES || early_node_map[i].nid == nid) - return i; - - return -1; -} - -/* - * Basic iterator support. Return the next active range of PFNs for a node - * Note: nid == MAX_NUMNODES returns next region regardless of node - */ -static int __meminit next_active_region_index_in_nid(int index, int nid) -{ - for (index = index + 1; index < nr_nodemap_entries; index++) - if (nid == MAX_NUMNODES || early_node_map[index].nid == nid) - return index; - - return -1; -} - +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP #ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID /* * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. @@ -3775,15 +3725,12 @@ static int __meminit next_active_region_index_in_nid(int index, int nid) */ int __meminit __early_pfn_to_nid(unsigned long pfn) { - int i; - - for (i = 0; i < nr_nodemap_entries; i++) { - unsigned long start_pfn = early_node_map[i].start_pfn; - unsigned long end_pfn = early_node_map[i].end_pfn; + unsigned long start_pfn, end_pfn; + int i, nid; + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) if (start_pfn <= pfn && pfn < end_pfn) - return early_node_map[i].nid; - } + return nid; /* This is a memory hole */ return -1; } @@ -3812,11 +3759,6 @@ bool __meminit early_pfn_in_nid(unsigned long pfn, int node) } #endif -/* Basic iterator support to walk early_node_map[] */ -#define for_each_active_range_index_in_nid(i, nid) \ - for (i = first_active_region_index_in_nid(nid); i != -1; \ - i = next_active_region_index_in_nid(i, nid)) - /** * free_bootmem_with_active_regions - Call free_bootmem_node for each active range * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed. @@ -3826,122 +3768,34 @@ bool __meminit early_pfn_in_nid(unsigned long pfn, int node) * add_active_ranges() contain no holes and may be freed, this * this function may be used instead of calling free_bootmem() manually. */ -void __init free_bootmem_with_active_regions(int nid, - unsigned long max_low_pfn) -{ - int i; - - for_each_active_range_index_in_nid(i, nid) { - unsigned long size_pages = 0; - unsigned long end_pfn = early_node_map[i].end_pfn; - - if (early_node_map[i].start_pfn >= max_low_pfn) - continue; - - if (end_pfn > max_low_pfn) - end_pfn = max_low_pfn; - - size_pages = end_pfn - early_node_map[i].start_pfn; - free_bootmem_node(NODE_DATA(early_node_map[i].nid), - PFN_PHYS(early_node_map[i].start_pfn), - size_pages << PAGE_SHIFT); - } -} - -#ifdef CONFIG_HAVE_MEMBLOCK -/* - * Basic iterator support. Return the last range of PFNs for a node - * Note: nid == MAX_NUMNODES returns last region regardless of node - */ -static int __meminit last_active_region_index_in_nid(int nid) +void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn) { - int i; - - for (i = nr_nodemap_entries - 1; i >= 0; i--) - if (nid == MAX_NUMNODES || early_node_map[i].nid == nid) - return i; - - return -1; -} - -/* - * Basic iterator support. Return the previous active range of PFNs for a node - * Note: nid == MAX_NUMNODES returns next region regardless of node - */ -static int __meminit previous_active_region_index_in_nid(int index, int nid) -{ - for (index = index - 1; index >= 0; index--) - if (nid == MAX_NUMNODES || early_node_map[index].nid == nid) - return index; - - return -1; -} - -#define for_each_active_range_index_in_nid_reverse(i, nid) \ - for (i = last_active_region_index_in_nid(nid); i != -1; \ - i = previous_active_region_index_in_nid(i, nid)) - -u64 __init find_memory_core_early(int nid, u64 size, u64 align, - u64 goal, u64 limit) -{ - int i; - - /* Need to go over early_node_map to find out good range for node */ - for_each_active_range_index_in_nid_reverse(i, nid) { - u64 addr; - u64 ei_start, ei_last; - u64 final_start, final_end; - - ei_last = early_node_map[i].end_pfn; - ei_last <<= PAGE_SHIFT; - ei_start = early_node_map[i].start_pfn; - ei_start <<= PAGE_SHIFT; - - final_start = max(ei_start, goal); - final_end = min(ei_last, limit); - - if (final_start >= final_end) - continue; - - addr = memblock_find_in_range(final_start, final_end, size, align); + unsigned long start_pfn, end_pfn; + int i, this_nid; - if (addr == MEMBLOCK_ERROR) - continue; + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid) { + start_pfn = min(start_pfn, max_low_pfn); + end_pfn = min(end_pfn, max_low_pfn); - return addr; + if (start_pfn < end_pfn) + free_bootmem_node(NODE_DATA(this_nid), + PFN_PHYS(start_pfn), + (end_pfn - start_pfn) << PAGE_SHIFT); } - - return MEMBLOCK_ERROR; } -#endif int __init add_from_early_node_map(struct range *range, int az, int nr_range, int nid) { + unsigned long start_pfn, end_pfn; int i; - u64 start, end; /* need to go over early_node_map to find out good range for node */ - for_each_active_range_index_in_nid(i, nid) { - start = early_node_map[i].start_pfn; - end = early_node_map[i].end_pfn; - nr_range = add_range(range, az, nr_range, start, end); - } + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) + nr_range = add_range(range, az, nr_range, start_pfn, end_pfn); return nr_range; } -void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data) -{ - int i; - int ret; - - for_each_active_range_index_in_nid(i, nid) { - ret = work_fn(early_node_map[i].start_pfn, - early_node_map[i].end_pfn, data); - if (ret) - break; - } -} /** * sparse_memory_present_with_active_regions - Call memory_present for each active range * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used. @@ -3952,12 +3806,11 @@ void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data) */ void __init sparse_memory_present_with_active_regions(int nid) { - int i; + unsigned long start_pfn, end_pfn; + int i, this_nid; - for_each_active_range_index_in_nid(i, nid) - memory_present(early_node_map[i].nid, - early_node_map[i].start_pfn, - early_node_map[i].end_pfn); + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid) + memory_present(this_nid, start_pfn, end_pfn); } /** @@ -3974,13 +3827,15 @@ void __init sparse_memory_present_with_active_regions(int nid) void __meminit get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn) { + unsigned long this_start_pfn, this_end_pfn; int i; + *start_pfn = -1UL; *end_pfn = 0; - for_each_active_range_index_in_nid(i, nid) { - *start_pfn = min(*start_pfn, early_node_map[i].start_pfn); - *end_pfn = max(*end_pfn, early_node_map[i].end_pfn); + for_each_mem_pfn_range(i, nid, &this_start_pfn, &this_end_pfn, NULL) { + *start_pfn = min(*start_pfn, this_start_pfn); + *end_pfn = max(*end_pfn, this_end_pfn); } if (*start_pfn == -1UL) @@ -4083,46 +3938,16 @@ unsigned long __meminit __absent_pages_in_range(int nid, unsigned long range_start_pfn, unsigned long range_end_pfn) { - int i = 0; - unsigned long prev_end_pfn = 0, hole_pages = 0; - unsigned long start_pfn; - - /* Find the end_pfn of the first active range of pfns in the node */ - i = first_active_region_index_in_nid(nid); - if (i == -1) - return 0; - - prev_end_pfn = min(early_node_map[i].start_pfn, range_end_pfn); - - /* Account for ranges before physical memory on this node */ - if (early_node_map[i].start_pfn > range_start_pfn) - hole_pages = prev_end_pfn - range_start_pfn; - - /* Find all holes for the zone within the node */ - for (; i != -1; i = next_active_region_index_in_nid(i, nid)) { - - /* No need to continue if prev_end_pfn is outside the zone */ - if (prev_end_pfn >= range_end_pfn) - break; - - /* Make sure the end of the zone is not within the hole */ - start_pfn = min(early_node_map[i].start_pfn, range_end_pfn); - prev_end_pfn = max(prev_end_pfn, range_start_pfn); + unsigned long nr_absent = range_end_pfn - range_start_pfn; + unsigned long start_pfn, end_pfn; + int i; - /* Update the hole size cound and move on */ - if (start_pfn > range_start_pfn) { - BUG_ON(prev_end_pfn > start_pfn); - hole_pages += start_pfn - prev_end_pfn; - } - prev_end_pfn = early_node_map[i].end_pfn; + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { + start_pfn = clamp(start_pfn, range_start_pfn, range_end_pfn); + end_pfn = clamp(end_pfn, range_start_pfn, range_end_pfn); + nr_absent -= end_pfn - start_pfn; } - - /* Account for ranges past physical memory on this node */ - if (range_end_pfn > prev_end_pfn) - hole_pages += range_end_pfn - - max(range_start_pfn, prev_end_pfn); - - return hole_pages; + return nr_absent; } /** @@ -4143,14 +3968,14 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid, unsigned long zone_type, unsigned long *ignored) { + unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type]; + unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; unsigned long node_start_pfn, node_end_pfn; unsigned long zone_start_pfn, zone_end_pfn; get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn); - zone_start_pfn = max(arch_zone_lowest_possible_pfn[zone_type], - node_start_pfn); - zone_end_pfn = min(arch_zone_highest_possible_pfn[zone_type], - node_end_pfn); + zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high); + zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high); adjust_zone_range_for_zone_movable(nid, zone_type, node_start_pfn, node_end_pfn, @@ -4158,7 +3983,7 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid, return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn); } -#else +#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ static inline unsigned long __meminit zone_spanned_pages_in_node(int nid, unsigned long zone_type, unsigned long *zones_size) @@ -4176,7 +4001,7 @@ static inline unsigned long __meminit zone_absent_pages_in_node(int nid, return zholes_size[zone_type]; } -#endif +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat, unsigned long *zones_size, unsigned long *zholes_size) @@ -4399,10 +4224,10 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat) */ if (pgdat == NODE_DATA(0)) { mem_map = NODE_DATA(0)->node_mem_map; -#ifdef CONFIG_ARCH_POPULATES_NODE_MAP +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP if (page_to_pfn(mem_map) != pgdat->node_start_pfn) mem_map -= (pgdat->node_start_pfn - ARCH_PFN_OFFSET); -#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ } #endif #endif /* CONFIG_FLAT_NODE_MEM_MAP */ @@ -4427,7 +4252,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, free_area_init_core(pgdat, zones_size, zholes_size); } -#ifdef CONFIG_ARCH_POPULATES_NODE_MAP +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP #if MAX_NUMNODES > 1 /* @@ -4449,170 +4274,6 @@ static inline void setup_nr_node_ids(void) #endif /** - * add_active_range - Register a range of PFNs backed by physical memory - * @nid: The node ID the range resides on - * @start_pfn: The start PFN of the available physical memory - * @end_pfn: The end PFN of the available physical memory - * - * These ranges are stored in an early_node_map[] and later used by - * free_area_init_nodes() to calculate zone sizes and holes. If the - * range spans a memory hole, it is up to the architecture to ensure - * the memory is not freed by the bootmem allocator. If possible - * the range being registered will be merged with existing ranges. - */ -void __init add_active_range(unsigned int nid, unsigned long start_pfn, - unsigned long end_pfn) -{ - int i; - - mminit_dprintk(MMINIT_TRACE, "memory_register", - "Entering add_active_range(%d, %#lx, %#lx) " - "%d entries of %d used\n", - nid, start_pfn, end_pfn, - nr_nodemap_entries, MAX_ACTIVE_REGIONS); - - mminit_validate_memmodel_limits(&start_pfn, &end_pfn); - - /* Merge with existing active regions if possible */ - for (i = 0; i < nr_nodemap_entries; i++) { - if (early_node_map[i].nid != nid) - continue; - - /* Skip if an existing region covers this new one */ - if (start_pfn >= early_node_map[i].start_pfn && - end_pfn <= early_node_map[i].end_pfn) - return; - - /* Merge forward if suitable */ - if (start_pfn <= early_node_map[i].end_pfn && - end_pfn > early_node_map[i].end_pfn) { - early_node_map[i].end_pfn = end_pfn; - return; - } - - /* Merge backward if suitable */ - if (start_pfn < early_node_map[i].start_pfn && - end_pfn >= early_node_map[i].start_pfn) { - early_node_map[i].start_pfn = start_pfn; - return; - } - } - - /* Check that early_node_map is large enough */ - if (i >= MAX_ACTIVE_REGIONS) { - printk(KERN_CRIT "More than %d memory regions, truncating\n", - MAX_ACTIVE_REGIONS); - return; - } - - early_node_map[i].nid = nid; - early_node_map[i].start_pfn = start_pfn; - early_node_map[i].end_pfn = end_pfn; - nr_nodemap_entries = i + 1; -} - -/** - * remove_active_range - Shrink an existing registered range of PFNs - * @nid: The node id the range is on that should be shrunk - * @start_pfn: The new PFN of the range - * @end_pfn: The new PFN of the range - * - * i386 with NUMA use alloc_remap() to store a node_mem_map on a local node. - * The map is kept near the end physical page range that has already been - * registered. This function allows an arch to shrink an existing registered - * range. - */ -void __init remove_active_range(unsigned int nid, unsigned long start_pfn, - unsigned long end_pfn) -{ - int i, j; - int removed = 0; - - printk(KERN_DEBUG "remove_active_range (%d, %lu, %lu)\n", - nid, start_pfn, end_pfn); - - /* Find the old active region end and shrink */ - for_each_active_range_index_in_nid(i, nid) { - if (early_node_map[i].start_pfn >= start_pfn && - early_node_map[i].end_pfn <= end_pfn) { - /* clear it */ - early_node_map[i].start_pfn = 0; - early_node_map[i].end_pfn = 0; - removed = 1; - continue; - } - if (early_node_map[i].start_pfn < start_pfn && - early_node_map[i].end_pfn > start_pfn) { - unsigned long temp_end_pfn = early_node_map[i].end_pfn; - early_node_map[i].end_pfn = start_pfn; - if (temp_end_pfn > end_pfn) - add_active_range(nid, end_pfn, temp_end_pfn); - continue; - } - if (early_node_map[i].start_pfn >= start_pfn && - early_node_map[i].end_pfn > end_pfn && - early_node_map[i].start_pfn < end_pfn) { - early_node_map[i].start_pfn = end_pfn; - continue; - } - } - - if (!removed) - return; - - /* remove the blank ones */ - for (i = nr_nodemap_entries - 1; i > 0; i--) { - if (early_node_map[i].nid != nid) - continue; - if (early_node_map[i].end_pfn) - continue; - /* we found it, get rid of it */ - for (j = i; j < nr_nodemap_entries - 1; j++) - memcpy(&early_node_map[j], &early_node_map[j+1], - sizeof(early_node_map[j])); - j = nr_nodemap_entries - 1; - memset(&early_node_map[j], 0, sizeof(early_node_map[j])); - nr_nodemap_entries--; - } -} - -/** - * remove_all_active_ranges - Remove all currently registered regions - * - * During discovery, it may be found that a table like SRAT is invalid - * and an alternative discovery method must be used. This function removes - * all currently registered regions. - */ -void __init remove_all_active_ranges(void) -{ - memset(early_node_map, 0, sizeof(early_node_map)); - nr_nodemap_entries = 0; -} - -/* Compare two active node_active_regions */ -static int __init cmp_node_active_region(const void *a, const void *b) -{ - struct node_active_region *arange = (struct node_active_region *)a; - struct node_active_region *brange = (struct node_active_region *)b; - - /* Done this way to avoid overflows */ - if (arange->start_pfn > brange->start_pfn) - return 1; - if (arange->start_pfn < brange->start_pfn) - return -1; - - return 0; -} - -/* sort the node_map by start_pfn */ -void __init sort_node_map(void) -{ - sort(early_node_map, (size_t)nr_nodemap_entries, - sizeof(struct node_active_region), - cmp_node_active_region, NULL); -} - -/** * node_map_pfn_alignment - determine the maximum internode alignment * * This function should be called after node map is populated and sorted. @@ -4634,15 +4295,11 @@ void __init sort_node_map(void) unsigned long __init node_map_pfn_alignment(void) { unsigned long accl_mask = 0, last_end = 0; + unsigned long start, end, mask; int last_nid = -1; - int i; - - for_each_active_range_index_in_nid(i, MAX_NUMNODES) { - int nid = early_node_map[i].nid; - unsigned long start = early_node_map[i].start_pfn; - unsigned long end = early_node_map[i].end_pfn; - unsigned long mask; + int i, nid; + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) { if (!start || last_nid < 0 || last_nid == nid) { last_nid = nid; last_end = end; @@ -4669,12 +4326,12 @@ unsigned long __init node_map_pfn_alignment(void) /* Find the lowest pfn for a node */ static unsigned long __init find_min_pfn_for_node(int nid) { - int i; unsigned long min_pfn = ULONG_MAX; + unsigned long start_pfn; + int i; - /* Assuming a sorted map, the first range found has the starting pfn */ - for_each_active_range_index_in_nid(i, nid) - min_pfn = min(min_pfn, early_node_map[i].start_pfn); + for_each_mem_pfn_range(i, nid, &start_pfn, NULL, NULL) + min_pfn = min(min_pfn, start_pfn); if (min_pfn == ULONG_MAX) { printk(KERN_WARNING @@ -4703,15 +4360,16 @@ unsigned long __init find_min_pfn_with_active_regions(void) */ static unsigned long __init early_calculate_totalpages(void) { - int i; unsigned long totalpages = 0; + unsigned long start_pfn, end_pfn; + int i, nid; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + unsigned long pages = end_pfn - start_pfn; - for (i = 0; i < nr_nodemap_entries; i++) { - unsigned long pages = early_node_map[i].end_pfn - - early_node_map[i].start_pfn; totalpages += pages; if (pages) - node_set_state(early_node_map[i].nid, N_HIGH_MEMORY); + node_set_state(nid, N_HIGH_MEMORY); } return totalpages; } @@ -4766,6 +4424,8 @@ restart: /* Spread kernelcore memory as evenly as possible throughout nodes */ kernelcore_node = required_kernelcore / usable_nodes; for_each_node_state(nid, N_HIGH_MEMORY) { + unsigned long start_pfn, end_pfn; + /* * Recalculate kernelcore_node if the division per node * now exceeds what is necessary to satisfy the requested @@ -4782,13 +4442,10 @@ restart: kernelcore_remaining = kernelcore_node; /* Go through each range of PFNs within this node */ - for_each_active_range_index_in_nid(i, nid) { - unsigned long start_pfn, end_pfn; + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { unsigned long size_pages; - start_pfn = max(early_node_map[i].start_pfn, - zone_movable_pfn[nid]); - end_pfn = early_node_map[i].end_pfn; + start_pfn = max(start_pfn, zone_movable_pfn[nid]); if (start_pfn >= end_pfn) continue; @@ -4890,11 +4547,8 @@ static void check_for_regular_memory(pg_data_t *pgdat) */ void __init free_area_init_nodes(unsigned long *max_zone_pfn) { - unsigned long nid; - int i; - - /* Sort early_node_map as initialisation assumes it is sorted */ - sort_node_map(); + unsigned long start_pfn, end_pfn; + int i, nid; /* Record where the zone boundaries are */ memset(arch_zone_lowest_possible_pfn, 0, @@ -4941,11 +4595,9 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) } /* Print out the early_node_map[] */ - printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries); - for (i = 0; i < nr_nodemap_entries; i++) - printk(" %3d: %0#10lx -> %0#10lx\n", early_node_map[i].nid, - early_node_map[i].start_pfn, - early_node_map[i].end_pfn); + printk("Early memory PFN ranges\n"); + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) + printk(" %3d: %0#10lx -> %0#10lx\n", nid, start_pfn, end_pfn); /* Initialise every node */ mminit_verify_pageflags_layout(); @@ -4998,7 +4650,7 @@ static int __init cmdline_parse_movablecore(char *p) early_param("kernelcore", cmdline_parse_kernelcore); early_param("movablecore", cmdline_parse_movablecore); -#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ /** * set_dma_reserve - set the specified number of pages reserved in the first zone diff --git a/mm/percpu.c b/mm/percpu.c index 3bb810a..716eb4a 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1023,9 +1023,11 @@ phys_addr_t per_cpu_ptr_to_phys(void *addr) if (!is_vmalloc_addr(addr)) return __pa(addr); else - return page_to_phys(vmalloc_to_page(addr)); + return page_to_phys(vmalloc_to_page(addr)) + + offset_in_page(addr); } else - return page_to_phys(pcpu_addr_to_page(addr)); + return page_to_phys(pcpu_addr_to_page(addr)) + + offset_in_page(addr); } /** diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 1d8b32f..27be2f0 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1290,7 +1290,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long align, unsigned long flags, unsigned long start, unsigned long end, int node, gfp_t gfp_mask, void *caller) { - static struct vmap_area *va; + struct vmap_area *va; struct vm_struct *area; BUG_ON(in_interrupt()); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index e0af723..c1c597e 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -673,7 +673,7 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) goto encrypt; auth: - if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend)) + if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend)) return 0; if (!hci_conn_auth(conn, sec_level, auth_type)) diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index be84ae3..b84458d 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -613,7 +613,7 @@ static int hci_dev_do_close(struct hci_dev *hdev) if (!test_bit(HCI_RAW, &hdev->flags)) { set_bit(HCI_INIT, &hdev->flags); __hci_request(hdev, hci_reset_req, 0, - msecs_to_jiffies(HCI_INIT_TIMEOUT)); + msecs_to_jiffies(250)); clear_bit(HCI_INIT, &hdev->flags); } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 5ea94a1..17b5b1c 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -2152,7 +2152,7 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, voi void *ptr = req->data; int type, olen; unsigned long val; - struct l2cap_conf_rfc rfc; + struct l2cap_conf_rfc rfc = { .mode = L2CAP_MODE_BASIC }; BT_DBG("chan %p, rsp %p, len %d, req %p", chan, rsp, len, data); @@ -2271,6 +2271,16 @@ static void l2cap_conf_rfc_get(struct l2cap_chan *chan, void *rsp, int len) } } + /* Use sane default values in case a misbehaving remote device + * did not send an RFC option. + */ + rfc.mode = chan->mode; + rfc.retrans_timeout = cpu_to_le16(L2CAP_DEFAULT_RETRANS_TO); + rfc.monitor_timeout = cpu_to_le16(L2CAP_DEFAULT_MONITOR_TO); + rfc.max_pdu_size = cpu_to_le16(chan->imtu); + + BT_ERR("Expected RFC option was not found, using defaults"); + done: switch (rfc.mode) { case L2CAP_MODE_ERTM: diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 4e32e18..2d28dfe 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1146,6 +1146,7 @@ static int rfcomm_recv_ua(struct rfcomm_session *s, u8 dlci) if (list_empty(&s->dlcs)) { s->state = BT_DISCONN; rfcomm_send_disc(s, 0); + rfcomm_session_clear_timer(s); } break; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index d6ec372..fa8b8f7 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -114,12 +114,18 @@ static struct neighbour *fake_neigh_lookup(const struct dst_entry *dst, const vo return NULL; } +static unsigned int fake_mtu(const struct dst_entry *dst) +{ + return dst->dev->mtu; +} + static struct dst_ops fake_dst_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), .update_pmtu = fake_update_pmtu, .cow_metrics = fake_cow_metrics, .neigh_lookup = fake_neigh_lookup, + .mtu = fake_mtu, }; /* @@ -141,7 +147,7 @@ void br_netfilter_rtable_init(struct net_bridge *br) rt->dst.dev = br->dev; rt->dst.path = &rt->dst; dst_init_metrics(&rt->dst, br_dst_default_metrics, true); - rt->dst.flags = DST_NOXFRM; + rt->dst.flags = DST_NOXFRM | DST_NOPEER; rt->dst.ops = &fake_dst_ops; } diff --git a/net/core/flow.c b/net/core/flow.c index 8ae42de..e318c7e 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -358,6 +358,18 @@ void flow_cache_flush(void) put_online_cpus(); } +static void flow_cache_flush_task(struct work_struct *work) +{ + flow_cache_flush(); +} + +static DECLARE_WORK(flow_cache_flush_work, flow_cache_flush_task); + +void flow_cache_flush_deferred(void) +{ + schedule_work(&flow_cache_flush_work); +} + static int __cpuinit flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) { struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index c71c434..385aefe 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -665,11 +665,14 @@ static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, if (count) { int i; - if (count > 1<<30) { + if (count > INT_MAX) + return -EINVAL; + count = roundup_pow_of_two(count); + if (count > (ULONG_MAX - sizeof(struct rps_dev_flow_table)) + / sizeof(struct rps_dev_flow)) { /* Enforce a limit to prevent overflow */ return -EINVAL; } - count = roundup_pow_of_two(count); table = vmalloc(RPS_DEV_FLOW_TABLE_SIZE(count)); if (!table) return -ENOMEM; diff --git a/net/core/sock.c b/net/core/sock.c index 4ed7b1d..b23f174 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -288,11 +288,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) unsigned long flags; struct sk_buff_head *list = &sk->sk_receive_queue; - /* Cast sk->rcvbuf to unsigned... It's pointless, but reduces - number of warnings when compiling with -W --ANK - */ - if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned)sk->sk_rcvbuf) { + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) { atomic_inc(&sk->sk_drops); trace_sock_rcvqueue_full(sk, skb); return -ENOMEM; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 0da2afc..99ec116 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -253,6 +253,10 @@ static int __init ic_open_devs(void) } } + /* no point in waiting if we could not bring up at least one device */ + if (!ic_first_dev) + goto have_carrier; + /* wait for a carrier on at least one device */ start = jiffies; while (jiffies - start < msecs_to_jiffies(CONF_CARRIER_TIMEOUT)) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 46af623..94cdbc5 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -91,6 +91,7 @@ #include <linux/rcupdate.h> #include <linux/times.h> #include <linux/slab.h> +#include <linux/prefetch.h> #include <net/dst.h> #include <net/net_namespace.h> #include <net/protocol.h> @@ -120,6 +121,7 @@ static int ip_rt_max_size; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; +static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_redirect_number __read_mostly = 9; static int ip_rt_redirect_load __read_mostly = HZ / 50; @@ -133,6 +135,9 @@ static int ip_rt_min_advmss __read_mostly = 256; static int rt_chain_length_max __read_mostly = 20; static int redirect_genid; +static struct delayed_work expires_work; +static unsigned long expires_ljiffies; + /* * Interface to generic destination cache. */ @@ -830,6 +835,97 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth) return ONE; } +static void rt_check_expire(void) +{ + static unsigned int rover; + unsigned int i = rover, goal; + struct rtable *rth; + struct rtable __rcu **rthp; + unsigned long samples = 0; + unsigned long sum = 0, sum2 = 0; + unsigned long delta; + u64 mult; + + delta = jiffies - expires_ljiffies; + expires_ljiffies = jiffies; + mult = ((u64)delta) << rt_hash_log; + if (ip_rt_gc_timeout > 1) + do_div(mult, ip_rt_gc_timeout); + goal = (unsigned int)mult; + if (goal > rt_hash_mask) + goal = rt_hash_mask + 1; + for (; goal > 0; goal--) { + unsigned long tmo = ip_rt_gc_timeout; + unsigned long length; + + i = (i + 1) & rt_hash_mask; + rthp = &rt_hash_table[i].chain; + + if (need_resched()) + cond_resched(); + + samples++; + + if (rcu_dereference_raw(*rthp) == NULL) + continue; + length = 0; + spin_lock_bh(rt_hash_lock_addr(i)); + while ((rth = rcu_dereference_protected(*rthp, + lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) { + prefetch(rth->dst.rt_next); + if (rt_is_expired(rth)) { + *rthp = rth->dst.rt_next; + rt_free(rth); + continue; + } + if (rth->dst.expires) { + /* Entry is expired even if it is in use */ + if (time_before_eq(jiffies, rth->dst.expires)) { +nofree: + tmo >>= 1; + rthp = &rth->dst.rt_next; + /* + * We only count entries on + * a chain with equal hash inputs once + * so that entries for different QOS + * levels, and other non-hash input + * attributes don't unfairly skew + * the length computation + */ + length += has_noalias(rt_hash_table[i].chain, rth); + continue; + } + } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) + goto nofree; + + /* Cleanup aged off entries. */ + *rthp = rth->dst.rt_next; + rt_free(rth); + } + spin_unlock_bh(rt_hash_lock_addr(i)); + sum += length; + sum2 += length*length; + } + if (samples) { + unsigned long avg = sum / samples; + unsigned long sd = int_sqrt(sum2 / samples - avg*avg); + rt_chain_length_max = max_t(unsigned long, + ip_rt_gc_elasticity, + (avg + 4*sd) >> FRACT_BITS); + } + rover = i; +} + +/* + * rt_worker_func() is run in process context. + * we call rt_check_expire() to scan part of the hash table + */ +static void rt_worker_func(struct work_struct *work) +{ + rt_check_expire(); + schedule_delayed_work(&expires_work, ip_rt_gc_interval); +} + /* * Perturbation of rt_genid by a small quantity [1..256] * Using 8 bits of shuffling ensure we can call rt_cache_invalidate() @@ -1271,7 +1367,7 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) { struct rtable *rt = (struct rtable *) dst; - if (rt) { + if (rt && !(rt->dst.flags & DST_NOPEER)) { if (rt->peer == NULL) rt_bind_peer(rt, rt->rt_dst, 1); @@ -1282,7 +1378,7 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) iph->id = htons(inet_getid(rt->peer, more)); return; } - } else + } else if (!rt) printk(KERN_DEBUG "rt_bind_peer(0) @%p\n", __builtin_return_address(0)); @@ -3179,6 +3275,13 @@ static ctl_table ipv4_route_table[] = { .proc_handler = proc_dointvec_jiffies, }, { + .procname = "gc_interval", + .data = &ip_rt_gc_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { .procname = "redirect_load", .data = &ip_rt_redirect_load, .maxlen = sizeof(int), @@ -3388,6 +3491,11 @@ int __init ip_rt_init(void) devinet_init(); ip_fib_init(); + INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func); + expires_ljiffies = jiffies; + schedule_delayed_work(&expires_work, + net_random() % ip_rt_gc_interval + ip_rt_gc_interval); + if (ip_rt_proc_init()) printk(KERN_ERR "Unable to create route proc files\n"); #ifdef CONFIG_XFRM diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 84d0bd5..ec56271 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -603,7 +603,7 @@ void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) static atomic_t ipv6_fragmentation_id; int old, new; - if (rt) { + if (rt && !(rt->dst.flags & DST_NOPEER)) { struct inet_peer *peer; if (!rt->rt6i_peer) diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index dfd3a64..a18e6c3 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -833,15 +833,15 @@ static int llc_ui_recvmsg(struct kiocb *iocb, struct socket *sock, copied += used; len -= used; + /* For non stream protcols we get one packet per recvmsg call */ + if (sk->sk_type != SOCK_STREAM) + goto copy_uaddr; + if (!(flags & MSG_PEEK)) { sk_eat_skb(sk, skb, 0); *seq = 0; } - /* For non stream protcols we get one packet per recvmsg call */ - if (sk->sk_type != SOCK_STREAM) - goto copy_uaddr; - /* Partial read */ if (used + offset < skb->len) continue; @@ -857,6 +857,12 @@ copy_uaddr: } if (llc_sk(sk)->cmsg_flags) llc_cmsg_rcv(msg, skb); + + if (!(flags & MSG_PEEK)) { + sk_eat_skb(sk, skb, 0); + *seq = 0; + } + goto out; } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index 12571fb..29fa5ba 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -616,7 +616,7 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp) if ((cp) && (!cp->dest)) { dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, &cp->daddr, cp->dport, &cp->vaddr, cp->vport, - cp->protocol, cp->fwmark); + cp->protocol, cp->fwmark, cp->flags); ip_vs_bind_dest(cp, dest); return dest; } else diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 008bf97..e1a66cf 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -619,15 +619,21 @@ struct ip_vs_dest *ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr, __be16 dport, const union nf_inet_addr *vaddr, - __be16 vport, __u16 protocol, __u32 fwmark) + __be16 vport, __u16 protocol, __u32 fwmark, + __u32 flags) { struct ip_vs_dest *dest; struct ip_vs_service *svc; + __be16 port = dport; svc = ip_vs_service_get(net, af, fwmark, protocol, vaddr, vport); if (!svc) return NULL; - dest = ip_vs_lookup_dest(svc, daddr, dport); + if (fwmark && (flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) + port = 0; + dest = ip_vs_lookup_dest(svc, daddr, port); + if (!dest) + dest = ip_vs_lookup_dest(svc, daddr, port ^ dport); if (dest) atomic_inc(&dest->refcnt); ip_vs_service_put(svc); diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 3cdd479..2b6678c0 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -740,7 +740,7 @@ static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, * but still handled. */ dest = ip_vs_find_dest(net, type, daddr, dport, param->vaddr, - param->vport, protocol, fwmark); + param->vport, protocol, fwmark, flags); /* Set the approprite ativity flag */ if (protocol == IPPROTO_TCP) { diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index ef21b22..257e772 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -135,7 +135,7 @@ nla_put_failure: static inline int ctnetlink_dump_timeout(struct sk_buff *skb, const struct nf_conn *ct) { - long timeout = (ct->timeout.expires - jiffies) / HZ; + long timeout = ((long)ct->timeout.expires - (long)jiffies) / HZ; if (timeout < 0) timeout = 0; @@ -1358,12 +1358,15 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, nf_ct_protonum(ct)); if (helper == NULL) { rcu_read_unlock(); + spin_unlock_bh(&nf_conntrack_lock); #ifdef CONFIG_MODULES if (request_module("nfct-helper-%s", helpname) < 0) { + spin_lock_bh(&nf_conntrack_lock); err = -EOPNOTSUPP; goto err1; } + spin_lock_bh(&nf_conntrack_lock); rcu_read_lock(); helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct), @@ -1638,7 +1641,7 @@ ctnetlink_exp_dump_expect(struct sk_buff *skb, const struct nf_conntrack_expect *exp) { struct nf_conn *master = exp->master; - long timeout = (exp->timeout.expires - jiffies) / HZ; + long timeout = ((long)exp->timeout.expires - (long)jiffies) / HZ; struct nf_conn_help *help; if (timeout < 0) @@ -1869,25 +1872,30 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, err = -ENOMEM; skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (skb2 == NULL) + if (skb2 == NULL) { + nf_ct_expect_put(exp); goto out; + } rcu_read_lock(); err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp); rcu_read_unlock(); + nf_ct_expect_put(exp); if (err <= 0) goto free; - nf_ct_expect_put(exp); + err = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + if (err < 0) + goto out; - return netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); + return 0; free: kfree_skb(skb2); out: - nf_ct_expect_put(exp); - return err; + /* this avoids a loop in nfnetlink. */ + return err == -EAGAIN ? -ENOBUFS : err; } static int diff --git a/net/netfilter/xt_connbytes.c b/net/netfilter/xt_connbytes.c index 5b13850..9ddf1c3 100644 --- a/net/netfilter/xt_connbytes.c +++ b/net/netfilter/xt_connbytes.c @@ -87,10 +87,10 @@ connbytes_mt(const struct sk_buff *skb, struct xt_action_param *par) break; } - if (sinfo->count.to) + if (sinfo->count.to >= sinfo->count.from) return what <= sinfo->count.to && what >= sinfo->count.from; - else - return what >= sinfo->count.from; + else /* inverted */ + return what < sinfo->count.to || what > sinfo->count.from; } static int connbytes_mt_check(const struct xt_mtchk_param *par) diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 3925c65..ea66034 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -69,7 +69,7 @@ static int __nci_request(struct nci_dev *ndev, __u32 timeout) { int rc = 0; - unsigned long completion_rc; + long completion_rc; ndev->req_status = NCI_REQ_PEND; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 82a6f34..d9d4970 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1630,8 +1630,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, if (snaplen > res) snaplen = res; - if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned)sk->sk_rcvbuf) + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) goto drop_n_acct; if (skb_shared(skb)) { @@ -1762,8 +1761,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { if (po->copy_thresh && - atomic_read(&sk->sk_rmem_alloc) + skb->truesize - < (unsigned)sk->sk_rcvbuf) { + atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) { if (skb_shared(skb)) { copy_skb = skb_clone(skb, GFP_ATOMIC); } else { @@ -2450,8 +2448,12 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protoc { struct packet_sock *po = pkt_sk(sk); - if (po->fanout) + if (po->fanout) { + if (dev) + dev_put(dev); + return -EINVAL; + } lock_sock(sk); diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index f88256c..28de430 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -107,7 +107,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) if (!netif_is_multiqueue(dev)) return -EOPNOTSUPP; - if (nla_len(opt) < sizeof(*qopt)) + if (!opt || nla_len(opt) < sizeof(*qopt)) return -EINVAL; qopt = nla_data(opt); diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index eb3b9a8..a4ab207 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -488,7 +488,7 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) return -EINVAL; s = sizeof(struct disttable) + n * sizeof(s16); - d = kmalloc(s, GFP_KERNEL); + d = kmalloc(s, GFP_KERNEL | __GFP_NOWARN); if (!d) d = vmalloc(s); if (!d) @@ -501,9 +501,10 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) root_lock = qdisc_root_sleeping_lock(sch); spin_lock_bh(root_lock); - dist_free(q->delay_dist); - q->delay_dist = d; + swap(q->delay_dist, d); spin_unlock_bh(root_lock); + + dist_free(d); return 0; } diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 1033434..7b03254 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -817,11 +817,11 @@ skip_unblock: static void qfq_update_start(struct qfq_sched *q, struct qfq_class *cl) { unsigned long mask; - uint32_t limit, roundedF; + u64 limit, roundedF; int slot_shift = cl->grp->slot_shift; roundedF = qfq_round_down(cl->F, slot_shift); - limit = qfq_round_down(q->V, slot_shift) + (1UL << slot_shift); + limit = qfq_round_down(q->V, slot_shift) + (1ULL << slot_shift); if (!qfq_gt(cl->F, q->V) || qfq_gt(roundedF, limit)) { /* timestamp was stale */ diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 152b5b3..acd2edb 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -173,7 +173,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->timeouts[SCTP_EVENT_TIMEOUT_HEARTBEAT] = 0; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = - (unsigned long)sp->autoclose * HZ; + min_t(unsigned long, sp->autoclose, sctp_max_autoclose) * HZ; /* Initializes the timers */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) diff --git a/net/sctp/output.c b/net/sctp/output.c index 08b3cea..817174e 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -697,13 +697,7 @@ static void sctp_packet_append_data(struct sctp_packet *packet, /* Keep track of how many bytes are in flight to the receiver. */ asoc->outqueue.outstanding_bytes += datasize; - /* Update our view of the receiver's rwnd. Include sk_buff overhead - * while updating peer.rwnd so that it reduces the chances of a - * receiver running out of receive buffer space even when receive - * window is still open. This can happen when a sender is sending - * sending small messages. - */ - datasize += sizeof(struct sk_buff); + /* Update our view of the receiver's rwnd. */ if (datasize < rwnd) rwnd -= datasize; else diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 14c2b06..cfeb1d4 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -411,8 +411,7 @@ void sctp_retransmit_mark(struct sctp_outq *q, chunk->transport->flight_size -= sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); - q->asoc->peer.rwnd += (sctp_data_size(chunk) + - sizeof(struct sk_buff)); + q->asoc->peer.rwnd += sctp_data_size(chunk); } continue; } @@ -432,8 +431,7 @@ void sctp_retransmit_mark(struct sctp_outq *q, * (Section 7.2.4)), add the data size of those * chunks to the rwnd. */ - q->asoc->peer.rwnd += (sctp_data_size(chunk) + - sizeof(struct sk_buff)); + q->asoc->peer.rwnd += sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); if (chunk->transport) transport->flight_size -= sctp_data_size(chunk); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 61b9fca..6f6ad86 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1285,6 +1285,9 @@ SCTP_STATIC __init int sctp_init(void) sctp_max_instreams = SCTP_DEFAULT_INSTREAMS; sctp_max_outstreams = SCTP_DEFAULT_OUTSTREAMS; + /* Initialize maximum autoclose timeout. */ + sctp_max_autoclose = INT_MAX / HZ; + /* Initialize handle used for association ids. */ idr_init(&sctp_assocs_id); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 13bf5fc..54a7cd2 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2200,8 +2200,6 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, return -EINVAL; if (copy_from_user(&sp->autoclose, optval, optlen)) return -EFAULT; - /* make sure it won't exceed MAX_SCHEDULE_TIMEOUT */ - sp->autoclose = min_t(long, sp->autoclose, MAX_SCHEDULE_TIMEOUT / HZ); return 0; } diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 6b39529..60ffbd0 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -53,6 +53,10 @@ static int sack_timer_min = 1; static int sack_timer_max = 500; static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */ static int rwnd_scale_max = 16; +static unsigned long max_autoclose_min = 0; +static unsigned long max_autoclose_max = + (MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX) + ? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ; extern long sysctl_sctp_mem[3]; extern int sysctl_sctp_rmem[3]; @@ -258,6 +262,15 @@ static ctl_table sctp_table[] = { .extra1 = &one, .extra2 = &rwnd_scale_max, }, + { + .procname = "max_autoclose", + .data = &sctp_max_autoclose, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = &proc_doulongvec_minmax, + .extra1 = &max_autoclose_min, + .extra2 = &max_autoclose_max, + }, { /* sentinel */ } }; diff --git a/net/socket.c b/net/socket.c index 2877647..a005375 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2883,7 +2883,7 @@ static int bond_ioctl(struct net *net, unsigned int cmd, return dev_ioctl(net, cmd, uifr); default: - return -EINVAL; + return -ENOIOCTLCMD; } } @@ -3210,20 +3210,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, return sock_do_ioctl(net, sock, cmd, arg); } - /* Prevent warning from compat_sys_ioctl, these always - * result in -EINVAL in the native case anyway. */ - switch (cmd) { - case SIOCRTMSG: - case SIOCGIFCOUNT: - case SIOCSRARP: - case SIOCGRARP: - case SIOCDRARP: - case SIOCSIFLINK: - case SIOCGIFSLAVE: - case SIOCSIFSLAVE: - return -EINVAL; - } - return -ENOIOCTLCMD; } diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index d12ffa5..00a1a2a 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -590,6 +590,27 @@ void rpc_prepare_task(struct rpc_task *task) task->tk_ops->rpc_call_prepare(task, task->tk_calldata); } +static void +rpc_init_task_statistics(struct rpc_task *task) +{ + /* Initialize retry counters */ + task->tk_garb_retry = 2; + task->tk_cred_retry = 2; + task->tk_rebind_retry = 2; + + /* starting timestamp */ + task->tk_start = ktime_get(); +} + +static void +rpc_reset_task_statistics(struct rpc_task *task) +{ + task->tk_timeouts = 0; + task->tk_flags &= ~(RPC_CALL_MAJORSEEN|RPC_TASK_KILLED|RPC_TASK_SENT); + + rpc_init_task_statistics(task); +} + /* * Helper that calls task->tk_ops->rpc_call_done if it exists */ @@ -602,6 +623,7 @@ void rpc_exit_task(struct rpc_task *task) WARN_ON(RPC_ASSASSINATED(task)); /* Always release the RPC slot and buffer memory */ xprt_release(task); + rpc_reset_task_statistics(task); } } } @@ -804,11 +826,6 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta task->tk_calldata = task_setup_data->callback_data; INIT_LIST_HEAD(&task->tk_task); - /* Initialize retry counters */ - task->tk_garb_retry = 2; - task->tk_cred_retry = 2; - task->tk_rebind_retry = 2; - task->tk_priority = task_setup_data->priority - RPC_PRIORITY_LOW; task->tk_owner = current->tgid; @@ -818,8 +835,7 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta if (task->tk_ops->rpc_call_prepare != NULL) task->tk_action = rpc_prepare_task; - /* starting timestamp */ - task->tk_start = ktime_get(); + rpc_init_task_statistics(task); dprintk("RPC: new task initialized, procpid %u\n", task_pid_nr(current)); diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index f4385e4..c64c0ef 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -995,13 +995,11 @@ out_init_req: static void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req) { - if (xprt_dynamic_free_slot(xprt, req)) - return; - - memset(req, 0, sizeof(*req)); /* mark unused */ - spin_lock(&xprt->reserve_lock); - list_add(&req->rq_list, &xprt->free); + if (!xprt_dynamic_free_slot(xprt, req)) { + memset(req, 0, sizeof(*req)); /* mark unused */ + list_add(&req->rq_list, &xprt->free); + } rpc_wake_up_next(&xprt->backlog); spin_unlock(&xprt->reserve_lock); } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 2118d64..9049a5c 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2276,8 +2276,6 @@ static void __xfrm_garbage_collect(struct net *net) { struct dst_entry *head, *next; - flow_cache_flush(); - spin_lock_bh(&xfrm_policy_sk_bundle_lock); head = xfrm_policy_sk_bundles; xfrm_policy_sk_bundles = NULL; @@ -2290,6 +2288,18 @@ static void __xfrm_garbage_collect(struct net *net) } } +static void xfrm_garbage_collect(struct net *net) +{ + flow_cache_flush(); + __xfrm_garbage_collect(net); +} + +static void xfrm_garbage_collect_deferred(struct net *net) +{ + flow_cache_flush_deferred(); + __xfrm_garbage_collect(net); +} + static void xfrm_init_pmtu(struct dst_entry *dst) { do { @@ -2422,7 +2432,7 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) if (likely(dst_ops->neigh_lookup == NULL)) dst_ops->neigh_lookup = xfrm_neigh_lookup; if (likely(afinfo->garbage_collect == NULL)) - afinfo->garbage_collect = __xfrm_garbage_collect; + afinfo->garbage_collect = xfrm_garbage_collect_deferred; xfrm_policy_afinfo[afinfo->family] = afinfo; } write_unlock_bh(&xfrm_policy_afinfo_lock); @@ -2516,7 +2526,7 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void switch (event) { case NETDEV_DOWN: - __xfrm_garbage_collect(dev_net(dev)); + xfrm_garbage_collect(dev_net(dev)); } return NOTIFY_DONE; } diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile index ba573fe..914833d 100644 --- a/scripts/kconfig/Makefile +++ b/scripts/kconfig/Makefile @@ -60,8 +60,8 @@ update-po-config: $(obj)/kxgettext $(obj)/gconf.glade.h --directory=$(srctree) --directory=$(objtree) \ --output $(obj)/config.pot $(Q)sed -i s/CHARSET/UTF-8/ $(obj)/config.pot - $(Q)ln -fs Kconfig.x86 arch/um/Kconfig - $(Q)(for i in `ls $(srctree)/arch/*/Kconfig`; \ + $(Q)(for i in `ls $(srctree)/arch/*/Kconfig \ + $(srctree)/arch/*/um/Kconfig`; \ do \ echo " GEN $$i"; \ $(obj)/kxgettext $$i \ @@ -69,7 +69,6 @@ update-po-config: $(obj)/kxgettext $(obj)/gconf.glade.h done ) $(Q)msguniq --sort-by-file --to-code=UTF-8 $(obj)/config.pot \ --output $(obj)/linux.pot - $(Q)rm -f $(srctree)/arch/um/Kconfig $(Q)rm -f $(obj)/config.pot PHONY += allnoconfig allyesconfig allmodconfig alldefconfig randconfig diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c index 5dd5b140..8738def 100644 --- a/security/integrity/evm/evm_crypto.c +++ b/security/integrity/evm/evm_crypto.c @@ -27,20 +27,35 @@ static int evmkey_len = MAX_KEY_SIZE; struct crypto_shash *hmac_tfm; +static DEFINE_MUTEX(mutex); + static struct shash_desc *init_desc(void) { int rc; struct shash_desc *desc; if (hmac_tfm == NULL) { + mutex_lock(&mutex); + if (hmac_tfm) + goto out; hmac_tfm = crypto_alloc_shash(evm_hmac, 0, CRYPTO_ALG_ASYNC); if (IS_ERR(hmac_tfm)) { pr_err("Can not allocate %s (reason: %ld)\n", evm_hmac, PTR_ERR(hmac_tfm)); rc = PTR_ERR(hmac_tfm); hmac_tfm = NULL; + mutex_unlock(&mutex); + return ERR_PTR(rc); + } + rc = crypto_shash_setkey(hmac_tfm, evmkey, evmkey_len); + if (rc) { + crypto_free_shash(hmac_tfm); + hmac_tfm = NULL; + mutex_unlock(&mutex); return ERR_PTR(rc); } +out: + mutex_unlock(&mutex); } desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(hmac_tfm), @@ -51,11 +66,7 @@ static struct shash_desc *init_desc(void) desc->tfm = hmac_tfm; desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP; - rc = crypto_shash_setkey(hmac_tfm, evmkey, evmkey_len); - if (rc) - goto out; rc = crypto_shash_init(desc); -out: if (rc) { kfree(desc); return ERR_PTR(rc); diff --git a/security/security.c b/security/security.c index 0c6cc69..e2f684a 100644 --- a/security/security.c +++ b/security/security.c @@ -381,7 +381,7 @@ int security_old_inode_init_security(struct inode *inode, struct inode *dir, void **value, size_t *len) { if (unlikely(IS_PRIVATE(inode))) - return 0; + return -EOPNOTSUPP; return security_ops->inode_init_security(inode, dir, qstr, name, value, len); } diff --git a/security/selinux/netport.c b/security/selinux/netport.c index 0b62bd1..7b9eb1f 100644 --- a/security/selinux/netport.c +++ b/security/selinux/netport.c @@ -123,7 +123,9 @@ static void sel_netport_insert(struct sel_netport *port) if (sel_netport_hash[idx].size == SEL_NETPORT_HASH_BKT_LIMIT) { struct sel_netport *tail; tail = list_entry( - rcu_dereference(sel_netport_hash[idx].list.prev), + rcu_dereference_protected( + sel_netport_hash[idx].list.prev, + lockdep_is_held(&sel_netport_lock)), struct sel_netport, list); list_del_rcu(&tail->list); kfree_rcu(tail, rcu); diff --git a/sound/atmel/ac97c.c b/sound/atmel/ac97c.c index 6e5adde..73516f6 100644 --- a/sound/atmel/ac97c.c +++ b/sound/atmel/ac97c.c @@ -899,6 +899,10 @@ static void atmel_ac97c_reset(struct atmel_ac97c *chip) /* AC97 v2.2 specifications says minimum 1 us. */ udelay(2); gpio_set_value(chip->reset_pin, 1); + } else { + ac97c_writel(chip, MR, AC97C_MR_WRST | AC97C_MR_ENA); + udelay(2); + ac97c_writel(chip, MR, AC97C_MR_ENA); } } diff --git a/sound/soc/codecs/wm8776.c b/sound/soc/codecs/wm8776.c index bfdc523..d3b0a20 100644 --- a/sound/soc/codecs/wm8776.c +++ b/sound/soc/codecs/wm8776.c @@ -235,6 +235,7 @@ static int wm8776_hw_params(struct snd_pcm_substream *substream, switch (snd_pcm_format_width(params_format(params))) { case 16: iface = 0; + break; case 20: iface = 0x10; break; diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c index 3ad0925..758e3b3 100644 --- a/virt/kvm/assigned-dev.c +++ b/virt/kvm/assigned-dev.c @@ -17,6 +17,8 @@ #include <linux/pci.h> #include <linux/interrupt.h> #include <linux/slab.h> +#include <linux/namei.h> +#include <linux/fs.h> #include "irq.h" static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head, @@ -480,12 +482,76 @@ out: return r; } +/* + * We want to test whether the caller has been granted permissions to + * use this device. To be able to configure and control the device, + * the user needs access to PCI configuration space and BAR resources. + * These are accessed through PCI sysfs. PCI config space is often + * passed to the process calling this ioctl via file descriptor, so we + * can't rely on access to that file. We can check for permissions + * on each of the BAR resource files, which is a pretty clear + * indicator that the user has been granted access to the device. + */ +static int probe_sysfs_permissions(struct pci_dev *dev) +{ +#ifdef CONFIG_SYSFS + int i; + bool bar_found = false; + + for (i = PCI_STD_RESOURCES; i <= PCI_STD_RESOURCE_END; i++) { + char *kpath, *syspath; + struct path path; + struct inode *inode; + int r; + + if (!pci_resource_len(dev, i)) + continue; + + kpath = kobject_get_path(&dev->dev.kobj, GFP_KERNEL); + if (!kpath) + return -ENOMEM; + + /* Per sysfs-rules, sysfs is always at /sys */ + syspath = kasprintf(GFP_KERNEL, "/sys%s/resource%d", kpath, i); + kfree(kpath); + if (!syspath) + return -ENOMEM; + + r = kern_path(syspath, LOOKUP_FOLLOW, &path); + kfree(syspath); + if (r) + return r; + + inode = path.dentry->d_inode; + + r = inode_permission(inode, MAY_READ | MAY_WRITE | MAY_ACCESS); + path_put(&path); + if (r) + return r; + + bar_found = true; + } + + /* If no resources, probably something special */ + if (!bar_found) + return -EPERM; + + return 0; +#else + return -EINVAL; /* No way to control the device without sysfs */ +#endif +} + static int kvm_vm_ioctl_assign_device(struct kvm *kvm, struct kvm_assigned_pci_dev *assigned_dev) { int r = 0, idx; struct kvm_assigned_dev_kernel *match; struct pci_dev *dev; + u8 header_type; + + if (!(assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU)) + return -EINVAL; mutex_lock(&kvm->lock); idx = srcu_read_lock(&kvm->srcu); @@ -513,6 +579,18 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, r = -EINVAL; goto out_free; } + + /* Don't allow bridges to be assigned */ + pci_read_config_byte(dev, PCI_HEADER_TYPE, &header_type); + if ((header_type & PCI_HEADER_TYPE) != PCI_HEADER_TYPE_NORMAL) { + r = -EPERM; + goto out_put; + } + + r = probe_sysfs_permissions(dev); + if (r) + goto out_put; + if (pci_enable_device(dev)) { printk(KERN_INFO "%s: Could not enable PCI device\n", __func__); r = -EBUSY; @@ -544,16 +622,14 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm, list_add(&match->list, &kvm->arch.assigned_dev_head); - if (assigned_dev->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) { - if (!kvm->arch.iommu_domain) { - r = kvm_iommu_map_guest(kvm); - if (r) - goto out_list_del; - } - r = kvm_assign_device(kvm, match); + if (!kvm->arch.iommu_domain) { + r = kvm_iommu_map_guest(kvm); if (r) goto out_list_del; } + r = kvm_assign_device(kvm, match); + if (r) + goto out_list_del; out: srcu_read_unlock(&kvm->srcu, idx); @@ -593,8 +669,7 @@ static int kvm_vm_ioctl_deassign_device(struct kvm *kvm, goto out; } - if (match->flags & KVM_DEV_ASSIGN_ENABLE_IOMMU) - kvm_deassign_device(kvm, match); + kvm_deassign_device(kvm, match); kvm_free_assigned_device(kvm, match); |