Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking changes from David Miller:

1) Allow to dump, monitor, and change the bridge multicast database
   using netlink.  From Cong Wang.

2) RFC 5961 TCP blind data injection attack mitigation, from Eric
   Dumazet.

3) Networking user namespace support from Eric W. Biederman.

4) tuntap/virtio-net multiqueue support by Jason Wang.

5) Support for checksum offload of encapsulated packets (basically,
   tunneled traffic can still be checksummed by HW).  From Joseph
   Gasparakis.

6) Allow BPF filter access to VLAN tags, from Eric Dumazet and
   Daniel Borkmann.

7) Bridge port parameters over netlink and BPDU blocking support
   from Stephen Hemminger.

8) Improve data access patterns during inet socket demux by rearranging
   socket layout, from Eric Dumazet.

9) TIPC protocol updates and cleanups from Ying Xue, Paul Gortmaker, and
   Jon Maloy.

10) Update TCP socket hash sizing to be more in line with current day
    realities.  The existing heurstics were choosen a decade ago.
    From Eric Dumazet.

11) Fix races, queue bloat, and excessive wakeups in ATM and
    associated drivers, from Krzysztof Mazur and David Woodhouse.

12) Support DOVE (Distributed Overlay Virtual Ethernet) extensions
    in VXLAN driver, from David Stevens.

13) Add "oops_only" mode to netconsole, from Amerigo Wang.

14) Support set and query of VEB/VEPA bridge mode via PF_BRIDGE, also
    allow DCB netlink to work on namespaces other than the initial
    namespace.  From John Fastabend.

15) Support PTP in the Tigon3 driver, from Matt Carlson.

16) tun/vhost zero copy fixes and improvements, plus turn it on
    by default, from Michael S. Tsirkin.

17) Support per-association statistics in SCTP, from Michele
    Baldessari.

And many, many, driver updates, cleanups, and improvements.  Too
numerous to mention individually.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1722 commits)
  net/mlx4_en: Add support for destination MAC in steering rules
  net/mlx4_en: Use generic etherdevice.h functions.
  net: ethtool: Add destination MAC address to flow steering API
  bridge: add support of adding and deleting mdb entries
  bridge: notify mdb changes via netlink
  ndisc: Unexport ndisc_{build,send}_skb().
  uapi: add missing netconf.h to export list
  pkt_sched: avoid requeues if possible
  solos-pci: fix double-free of TX skb in DMA mode
  bnx2: Fix accidental reversions.
  bna: Driver Version Updated to 3.1.2.1
  bna: Firmware update
  bna: Add RX State
  bna: Rx Page Based Allocation
  bna: TX Intr Coalescing Fix
  bna: Tx and Rx Optimizations
  bna: Code Cleanup and Enhancements
  ath9k: check pdata variable before dereferencing it
  ath5k: RX timestamp is reported at end of frame
  ath9k_htc: RX timestamp is reported at end of frame
  ...

1 files changed, 99 insertions, 3 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6a2c34e..320e976 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -235,11 +235,13 @@ enum {
 /*
  * The callback notifies userspace to release buffers when skb DMA is done in
  * lower device, the skb last reference should be 0 when calling this.
+ * The zerocopy_success argument is true if zero copy transmit occurred,
+ * false on data copy or out of memory error caused by data copy attempt.
  * The ctx field is used to track device context.
  * The desc field is used to track userspace buffer index.
  */
 struct ubuf_info {
-	void (*callback)(struct ubuf_info *);
+	void (*callback)(struct ubuf_info *, bool zerocopy_success);
 	void *ctx;
 	unsigned long desc;
 };
@@ -374,6 +376,8 @@ typedef unsigned char *sk_buff_data_t;
  *	@mark: Generic packet mark
  *	@dropcount: total number of sk_receive_queue overflows
  *	@vlan_tci: vlan tag control information
+ *	@inner_transport_header: Inner transport layer header (encapsulation)
+ *	@inner_network_header: Network layer header (encapsulation)
  *	@transport_header: Transport layer header
  *	@network_header: Network layer header
  *	@mac_header: Link layer header
@@ -469,7 +473,13 @@ struct sk_buff {
 	__u8			wifi_acked:1;
 	__u8			no_fcs:1;
 	__u8			head_frag:1;
-	/* 8/10 bit hole (depending on ndisc_nodetype presence) */
+	/* Encapsulation protocol and NIC drivers should use
+	 * this flag to indicate to each other if the skb contains
+	 * encapsulated packet or not and maybe use the inner packet
+	 * headers if needed
+	 */
+	__u8			encapsulation:1;
+	/* 7/9 bit hole (depending on ndisc_nodetype presence) */
 	kmemcheck_bitfield_end(flags2);
 
 #ifdef CONFIG_NET_DMA
@@ -484,6 +494,8 @@ struct sk_buff {
 		__u32		avail_size;
 	};
 
+	sk_buff_data_t		inner_transport_header;
+	sk_buff_data_t		inner_network_header;
 	sk_buff_data_t		transport_header;
 	sk_buff_data_t		network_header;
 	sk_buff_data_t		mac_header;
@@ -566,6 +578,7 @@ static inline struct rtable *skb_rtable(const struct sk_buff *skb)
 }
 
 extern void kfree_skb(struct sk_buff *skb);
+extern void skb_tx_error(struct sk_buff *skb);
 extern void consume_skb(struct sk_buff *skb);
 extern void	       __kfree_skb(struct sk_buff *skb);
 extern struct kmem_cache *skbuff_head_cache;
@@ -643,7 +656,7 @@ extern unsigned int   skb_find_text(struct sk_buff *skb, unsigned int from,
 extern void __skb_get_rxhash(struct sk_buff *skb);
 static inline __u32 skb_get_rxhash(struct sk_buff *skb)
 {
-	if (!skb->rxhash)
+	if (!skb->l4_rxhash)
 		__skb_get_rxhash(skb);
 
 	return skb->rxhash;
@@ -1432,12 +1445,53 @@ static inline void skb_reserve(struct sk_buff *skb, int len)
 	skb->tail += len;
 }
 
+static inline void skb_reset_inner_headers(struct sk_buff *skb)
+{
+	skb->inner_network_header = skb->network_header;
+	skb->inner_transport_header = skb->transport_header;
+}
+
 static inline void skb_reset_mac_len(struct sk_buff *skb)
 {
 	skb->mac_len = skb->network_header - skb->mac_header;
 }
 
 #ifdef NET_SKBUFF_DATA_USES_OFFSET
+static inline unsigned char *skb_inner_transport_header(const struct sk_buff
+							*skb)
+{
+	return skb->head + skb->inner_transport_header;
+}
+
+static inline void skb_reset_inner_transport_header(struct sk_buff *skb)
+{
+	skb->inner_transport_header = skb->data - skb->head;
+}
+
+static inline void skb_set_inner_transport_header(struct sk_buff *skb,
+						   const int offset)
+{
+	skb_reset_inner_transport_header(skb);
+	skb->inner_transport_header += offset;
+}
+
+static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb)
+{
+	return skb->head + skb->inner_network_header;
+}
+
+static inline void skb_reset_inner_network_header(struct sk_buff *skb)
+{
+	skb->inner_network_header = skb->data - skb->head;
+}
+
+static inline void skb_set_inner_network_header(struct sk_buff *skb,
+						const int offset)
+{
+	skb_reset_inner_network_header(skb);
+	skb->inner_network_header += offset;
+}
+
 static inline unsigned char *skb_transport_header(const struct sk_buff *skb)
 {
 	return skb->head + skb->transport_header;
@@ -1493,6 +1547,38 @@ static inline void skb_set_mac_header(struct sk_buff *skb, const int offset)
 }
 
 #else /* NET_SKBUFF_DATA_USES_OFFSET */
+static inline unsigned char *skb_inner_transport_header(const struct sk_buff
+							*skb)
+{
+	return skb->inner_transport_header;
+}
+
+static inline void skb_reset_inner_transport_header(struct sk_buff *skb)
+{
+	skb->inner_transport_header = skb->data;
+}
+
+static inline void skb_set_inner_transport_header(struct sk_buff *skb,
+						   const int offset)
+{
+	skb->inner_transport_header = skb->data + offset;
+}
+
+static inline unsigned char *skb_inner_network_header(const struct sk_buff *skb)
+{
+	return skb->inner_network_header;
+}
+
+static inline void skb_reset_inner_network_header(struct sk_buff *skb)
+{
+	skb->inner_network_header = skb->data;
+}
+
+static inline void skb_set_inner_network_header(struct sk_buff *skb,
+						const int offset)
+{
+	skb->inner_network_header = skb->data + offset;
+}
 
 static inline unsigned char *skb_transport_header(const struct sk_buff *skb)
 {
@@ -1571,11 +1657,21 @@ static inline u32 skb_network_header_len(const struct sk_buff *skb)
 	return skb->transport_header - skb->network_header;
 }
 
+static inline u32 skb_inner_network_header_len(const struct sk_buff *skb)
+{
+	return skb->inner_transport_header - skb->inner_network_header;
+}
+
 static inline int skb_network_offset(const struct sk_buff *skb)
 {
 	return skb_network_header(skb) - skb->data;
 }
 
+static inline int skb_inner_network_offset(const struct sk_buff *skb)
+{
+	return skb_inner_network_header(skb) - skb->data;
+}
+
 static inline int pskb_network_may_pull(struct sk_buff *skb, unsigned int len)
 {
 	return pskb_may_pull(skb, skb_network_offset(skb) + len);