tcp: avoid order-1 allocations on wifi and tx path

[ This combines upstream commit
  a21d45726acacc963d8baddf74607d9b74e2b723 and the follow-on bug fix
  commit a21d45726acacc963d8baddf74607d9b74e2b723 ]

Marc Merlin reported many order-1 allocations failures in TX path on its
wireless setup, that dont make any sense with MTU=1500 network, and non
SG capable hardware.

After investigation, it turns out TCP uses sk_stream_alloc_skb() and
used as a convention skb_tailroom(skb) to know how many bytes of data
payload could be put in this skb (for non SG capable devices)

Note : these skb used kmalloc-4096 (MTU=1500 + MAX_HEADER +
sizeof(struct skb_shared_info) being above 2048)

Later, mac80211 layer need to add some bytes at the tail of skb
(IEEE80211_ENCRYPT_TAILROOM = 18 bytes) and since no more tailroom is
available has to call pskb_expand_head() and request order-1
allocations.

This patch changes sk_stream_alloc_skb() so that only
sk->sk_prot->max_header bytes of headroom are reserved, and use a new
skb field, avail_size to hold the data payload limit.

This way, order-0 allocations done by TCP stack can leave more than 2 KB
of tailroom and no more allocation is performed in mac80211 layer (or
any layer needing some tailroom)

avail_size is unioned with mark/dropcount, since mark will be set later
in IP stack for output packets. Therefore, skb size is unchanged.

Reported-by: Marc MERLIN <marc@merlins.org>
Tested-by: Marc MERLIN <marc@merlins.org>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 19 insertions, 5 deletions

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ae86adee374..42854cee6fc 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -468,6 +468,7 @@ struct sk_buff {
 	union {
 		__u32		mark;
 		__u32		dropcount;
+		__u32		avail_size;
 	};
 
 	__u16			vlan_tci;
@@ -1338,6 +1339,18 @@ static inline int skb_tailroom(const struct sk_buff *skb)
 }
 
 /**
+ *	skb_availroom - bytes at buffer end
+ *	@skb: buffer to check
+ *
+ *	Return the number of bytes of free space at the tail of an sk_buff
+ *	allocated by sk_stream_alloc()
+ */
+static inline int skb_availroom(const struct sk_buff *skb)
+{
+	return skb_is_nonlinear(skb) ? 0 : skb->avail_size - skb->len;
+}
+
+/**
  *	skb_reserve - adjust headroom
  *	@skb: buffer to alter
  *	@len: bytes to move
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 86014bbd3e3..8c850211916 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -699,11 +699,12 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp)
 	skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp);
 	if (skb) {
 		if (sk_wmem_schedule(sk, skb->truesize)) {
+			skb_reserve(skb, sk->sk_prot->max_header);
 			/*
 			 * Make sure that we have exactly size bytes
 			 * available to the caller, no more, no less.
 			 */
-			skb_reserve(skb, skb_tailroom(skb) - size);
+			skb->avail_size = size;
 			return skb;
 		}
 		__kfree_skb(skb);
@@ -993,10 +994,9 @@ new_segment:
 				copy = seglen;
 
 			/* Where to copy to? */
-			if (skb_tailroom(skb) > 0) {
+			if (skb_availroom(skb) > 0) {
 				/* We have some space in skb head. Superb! */
-				if (copy > skb_tailroom(skb))
-					copy = skb_tailroom(skb);
+				copy = min_t(int, copy, skb_availroom(skb));
 				err = skb_add_data_nocache(sk, skb, from, copy);
 				if (err)
 					goto do_fault;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4ff3b6dc74f..e2c6722f717 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1096,6 +1096,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
 	eat = min_t(int, len, skb_headlen(skb));
 	if (eat) {
 		__skb_pull(skb, eat);
+		skb->avail_size -= eat;
 		len -= eat;
 		if (!len)
 			return;
@@ -2060,7 +2061,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
 		/* Punt if not enough space exists in the first SKB for
 		 * the data in the second
 		 */
-		if (skb->len > skb_tailroom(to))
+		if (skb->len > skb_availroom(to))
 			break;
 
 		if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp)))