summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorEric Dumazet <eric.dumazet@gmail.com>2012-04-24 23:01:22 -0400
committerBen Hutchings <ben@decadent.org.uk>2012-05-11 13:14:22 +0100
commit8d34d1f1b61169add8bdcad2e8b9ddf4f52889cd (patch)
tree4da057c4bfda5601987621d5c54be4027eb72928 /net
parent91bb95f240936feb98f7d540027c78773e4b84cb (diff)
tcp: avoid order-1 allocations on wifi and tx path
[ This combines upstream commit a21d45726acacc963d8baddf74607d9b74e2b723 and the follow-on bug fix commit 22b4a4f22da4b39c6f7f679fd35f3d35c91bf851 ] 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> [bwh: Correct commit hash for follow-on bug fix] Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Diffstat (limited to 'net')
-rw-r--r--net/ipv4/tcp.c8
-rw-r--r--net/ipv4/tcp_output.c3
2 files changed, 6 insertions, 5 deletions
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 36611ab36652..7904db453578 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -701,11 +701,12 @@ 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);
@@ -995,10 +996,9 @@ 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 7413437efc8d..c51dd5b2cbd5 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)))