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

Pull networking changes from David S Miller:

 1) Remove the ipv4 routing cache.  Now lookups go directly into the FIB
    trie and use prebuilt routes cached there.

    No more garbage collection, no more rDOS attacks on the routing
    cache.  Instead we now get predictable and consistent performance,
    no matter what the pattern of traffic we service.

    This has been almost 2 years in the making.  Special thanks to
    Julian Anastasov, Eric Dumazet, Steffen Klassert, and others who
    have helped along the way.

    I'm sure that with a change of this magnitude there will be some
    kind of fallout, but such things ought the be simple to fix at this
    point.  Luckily I'm not European so I'll be around all of August to
    fix things :-)

    The major stages of this work here are each fronted by a forced
    merge commit whose commit message contains a top-level description
    of the motivations and implementation issues.

 2) Pre-demux of established ipv4 TCP sockets, saves a route demux on
    input.

 3) TCP SYN/ACK performance tweaks from Eric Dumazet.

 4) Add namespace support for netfilter L4 conntrack helpers, from Gao
    Feng.

 5) Add config mechanism for Energy Efficient Ethernet to ethtool, from
    Yuval Mintz.

 6) Remove quadratic behavior from /proc/net/unix, from Eric Dumazet.

 7) Support for connection tracker helpers in userspace, from Pablo
    Neira Ayuso.

 8) Allow userspace driven TX load balancing functions in TEAM driver,
    from Jiri Pirko.

 9) Kill off NLMSG_PUT and RTA_PUT macros, more gross stuff with
    embedded gotos.

10) TCP Small Queues, essentially minimize the amount of TCP data queued
    up in the packet scheduler layer.  Whereas the existing BQL (Byte
    Queue Limits) limits the pkt_sched --> netdevice queuing levels,
    this controls the TCP --> pkt_sched queueing levels.

    From Eric Dumazet.

11) Reduce the number of get_page/put_page ops done on SKB fragments,
    from Alexander Duyck.

12) Implement protection against blind resets in TCP (RFC 5961), from
    Eric Dumazet.

13) Support the client side of TCP Fast Open, basically the ability to
    send data in the SYN exchange, from Yuchung Cheng.

    Basically, the sender queues up data with a sendmsg() call using
    MSG_FASTOPEN, then they do the connect() which emits the queued up
    fastopen data.

14) Avoid all the problems we get into in TCP when timers or PMTU events
    hit a locked socket.  The TCP Small Queues changes added a
    tcp_release_cb() that allows us to queue work up to the
    release_sock() caller, and that's what we use here too.  From Eric
    Dumazet.

15) Zero copy on TX support for TUN driver, from Michael S. Tsirkin.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1870 commits)
  genetlink: define lockdep_genl_is_held() when CONFIG_LOCKDEP
  r8169: revert "add byte queue limit support".
  ipv4: Change rt->rt_iif encoding.
  net: Make skb->skb_iif always track skb->dev
  ipv4: Prepare for change of rt->rt_iif encoding.
  ipv4: Remove all RTCF_DIRECTSRC handliing.
  ipv4: Really ignore ICMP address requests/replies.
  decnet: Don't set RTCF_DIRECTSRC.
  net/ipv4/ip_vti.c: Fix __rcu warnings detected by sparse.
  ipv4: Remove redundant assignment
  rds: set correct msg_namelen
  openvswitch: potential NULL deref in sample()
  tcp: dont drop MTU reduction indications
  bnx2x: Add new 57840 device IDs
  tcp: avoid oops in tcp_metrics and reset tcpm_stamp
  niu: Change niu_rbr_fill() to use unlikely() to check niu_rbr_add_page() return value
  niu: Fix to check for dma mapping errors.
  net: Fix references to out-of-scope variables in put_cmsg_compat()
  net: ethernet: davinci_emac: add pm_runtime support
  net: ethernet: davinci_emac: Remove unnecessary #include
  ...

1 files changed, 39 insertions, 32 deletions

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index d124306b81f..368f65c15e4 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -160,8 +160,8 @@ static void skb_under_panic(struct sk_buff *skb, int sz, void *here)
  *	@node: numa node to allocate memory on
  *
  *	Allocate a new &sk_buff. The returned buffer has no headroom and a
- *	tail room of size bytes. The object has a reference count of one.
- *	The return is the buffer. On a failure the return is %NULL.
+ *	tail room of at least size bytes. The object has a reference count
+ *	of one. The return is the buffer. On a failure the return is %NULL.
  *
  *	Buffers may only be allocated from interrupts using a @gfp_mask of
  *	%GFP_ATOMIC.
@@ -296,9 +296,12 @@ EXPORT_SYMBOL(build_skb);
 struct netdev_alloc_cache {
 	struct page *page;
 	unsigned int offset;
+	unsigned int pagecnt_bias;
 };
 static DEFINE_PER_CPU(struct netdev_alloc_cache, netdev_alloc_cache);
 
+#define NETDEV_PAGECNT_BIAS (PAGE_SIZE / SMP_CACHE_BYTES)
+
 /**
  * netdev_alloc_frag - allocate a page fragment
  * @fragsz: fragment size
@@ -317,17 +320,26 @@ void *netdev_alloc_frag(unsigned int fragsz)
 	if (unlikely(!nc->page)) {
 refill:
 		nc->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
+		if (unlikely(!nc->page))
+			goto end;
+recycle:
+		atomic_set(&nc->page->_count, NETDEV_PAGECNT_BIAS);
+		nc->pagecnt_bias = NETDEV_PAGECNT_BIAS;
 		nc->offset = 0;
 	}
-	if (likely(nc->page)) {
-		if (nc->offset + fragsz > PAGE_SIZE) {
-			put_page(nc->page);
-			goto refill;
-		}
-		data = page_address(nc->page) + nc->offset;
-		nc->offset += fragsz;
-		get_page(nc->page);
+
+	if (nc->offset + fragsz > PAGE_SIZE) {
+		/* avoid unnecessary locked operations if possible */
+		if ((atomic_read(&nc->page->_count) == nc->pagecnt_bias) ||
+		    atomic_sub_and_test(nc->pagecnt_bias, &nc->page->_count))
+			goto recycle;
+		goto refill;
 	}
+
+	data = page_address(nc->page) + nc->offset;
+	nc->offset += fragsz;
+	nc->pagecnt_bias--;
+end:
 	local_irq_restore(flags);
 	return data;
 }
@@ -713,7 +725,8 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src)
 }
 EXPORT_SYMBOL_GPL(skb_morph);
 
-/*	skb_copy_ubufs	-	copy userspace skb frags buffers to kernel
+/**
+ *	skb_copy_ubufs	-	copy userspace skb frags buffers to kernel
  *	@skb: the skb to modify
  *	@gfp_mask: allocation priority
  *
@@ -738,7 +751,7 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
 		u8 *vaddr;
 		skb_frag_t *f = &skb_shinfo(skb)->frags[i];
 
-		page = alloc_page(GFP_ATOMIC);
+		page = alloc_page(gfp_mask);
 		if (!page) {
 			while (head) {
 				struct page *next = (struct page *)head->private;
@@ -756,22 +769,22 @@ int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask)
 	}
 
 	/* skb frags release userspace buffers */
-	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
+	for (i = 0; i < num_frags; i++)
 		skb_frag_unref(skb, i);
 
 	uarg->callback(uarg);
 
 	/* skb frags point to kernel buffers */
-	for (i = skb_shinfo(skb)->nr_frags; i > 0; i--) {
-		__skb_fill_page_desc(skb, i-1, head, 0,
-				     skb_shinfo(skb)->frags[i - 1].size);
+	for (i = num_frags - 1; i >= 0; i--) {
+		__skb_fill_page_desc(skb, i, head, 0,
+				     skb_shinfo(skb)->frags[i].size);
 		head = (struct page *)head->private;
 	}
 
 	skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY;
 	return 0;
 }
-
+EXPORT_SYMBOL_GPL(skb_copy_ubufs);
 
 /**
  *	skb_clone	-	duplicate an sk_buff
@@ -791,10 +804,8 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 {
 	struct sk_buff *n;
 
-	if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
-		if (skb_copy_ubufs(skb, gfp_mask))
-			return NULL;
-	}
+	if (skb_orphan_frags(skb, gfp_mask))
+		return NULL;
 
 	n = skb + 1;
 	if (skb->fclone == SKB_FCLONE_ORIG &&
@@ -914,12 +925,10 @@ struct sk_buff *__pskb_copy(struct sk_buff *skb, int headroom, gfp_t gfp_mask)
 	if (skb_shinfo(skb)->nr_frags) {
 		int i;
 
-		if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
-			if (skb_copy_ubufs(skb, gfp_mask)) {
-				kfree_skb(n);
-				n = NULL;
-				goto out;
-			}
+		if (skb_orphan_frags(skb, gfp_mask)) {
+			kfree_skb(n);
+			n = NULL;
+			goto out;
 		}
 		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 			skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i];
@@ -992,10 +1001,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail,
 	 */
 	if (skb_cloned(skb)) {
 		/* copy this zero copy skb frags */
-		if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) {
-			if (skb_copy_ubufs(skb, gfp_mask))
-				goto nofrags;
-		}
+		if (skb_orphan_frags(skb, gfp_mask))
+			goto nofrags;
 		for (i = 0; i < skb_shinfo(skb)->nr_frags; i++)
 			skb_frag_ref(skb, i);
 
@@ -2614,7 +2621,7 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from,
 EXPORT_SYMBOL(skb_find_text);
 
 /**
- * skb_append_datato_frags: - append the user data to a skb
+ * skb_append_datato_frags - append the user data to a skb
  * @sk: sock  structure
  * @skb: skb structure to be appened with user data.
  * @getfrag: call back function to be used for getting the user data