| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1335988709.22133.632.camel@edumazet-glaptop>
Date: Wed, 02 May 2012 21:58:29 +0200
From: Eric Dumazet <eric.dumazet@...il.com>
To: David Miller <davem@...emloft.net>
Cc: Alexander Duyck <alexander.duyck@...il.com>,
Alexander Duyck <alexander.h.duyck@...el.com>,
netdev <netdev@...r.kernel.org>,
Neal Cardwell <ncardwell@...gle.com>,
Tom Herbert <therbert@...gle.com>,
Jeff Kirsher <jeffrey.t.kirsher@...el.com>,
Michael Chan <mchan@...adcom.com>,
Matt Carlson <mcarlson@...adcom.com>,
Herbert Xu <herbert@...dor.apana.org.au>,
Ben Hutchings <bhutchings@...arflare.com>,
Ilpo Järvinen <ilpo.jarvinen@...sinki.fi>,
Maciej Żenczykowski <maze@...gle.com>
Subject: [PATCH net-next] net: implement tcp coalescing in tcp_queue_rcv()
From: Eric Dumazet <edumazet@...gle.com>
Extend tcp coalescing implementing it from tcp_queue_rcv(), the main
receiver function when application is not blocked in recvmsg().
Function tcp_queue_rcv() is moved a bit to allow its call from
tcp_data_queue()
This gives good results especially if GRO could not kick, and if skb
head is a fragment.
Signed-off-by: Eric Dumazet <edumazet@...gle.com>
Cc: Alexander Duyck <alexander.h.duyck@...el.com>
Cc: Neal Cardwell <ncardwell@...gle.com>
Cc: Tom Herbert <therbert@...gle.com>
---
To be applied after "[PATCH v2 net-next] net: take care of cloned skbs
in tcp_try_coalesce()"
include/net/tcp.h | 3 ++-
net/ipv4/tcp.c | 10 +++++-----
net/ipv4/tcp_input.c | 40 +++++++++++++++++++++-------------------
3 files changed, 28 insertions(+), 25 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0fb84de..a9d2fb8 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -438,7 +438,8 @@ extern int tcp_disconnect(struct sock *sk, int flags);
void tcp_connect_init(struct sock *sk);
void tcp_finish_connect(struct sock *sk, struct sk_buff *skb);
-void tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int hdrlen);
+int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb,
+ int hdrlen, bool *fragstolen);
/* From syncookies.c */
extern __u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS];
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 9670af3..bd5deff 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -980,8 +980,8 @@ static inline int select_size(const struct sock *sk, bool sg)
static int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
{
struct sk_buff *skb;
- struct tcp_skb_cb *cb;
struct tcphdr *th;
+ bool fragstolen;
skb = alloc_skb(size + sizeof(*th), sk->sk_allocation);
if (!skb)
@@ -994,14 +994,14 @@ static int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
if (memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size))
goto err_free;
- cb = TCP_SKB_CB(skb);
-
TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + size;
TCP_SKB_CB(skb)->ack_seq = tcp_sk(sk)->snd_una - 1;
- tcp_queue_rcv(sk, skb, sizeof(*th));
-
+ if (tcp_queue_rcv(sk, skb, sizeof(*th), &fragstolen)) {
+ WARN_ON_ONCE(fragstolen); /* should not happen */
+ __kfree_skb(skb);
+ }
return size;
err_free:
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index f891a5e..2233468 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4662,6 +4662,22 @@ end:
skb_set_owner_r(skb, sk);
}
+int tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int hdrlen,
+ bool *fragstolen)
+{
+ int eaten;
+ struct sk_buff *tail = skb_peek_tail(&sk->sk_receive_queue);
+
+ __skb_pull(skb, hdrlen);
+ eaten = (tail &&
+ tcp_try_coalesce(sk, tail, skb, fragstolen)) ? 1 : 0;
+ tcp_sk(sk)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+ if (!eaten) {
+ __skb_queue_tail(&sk->sk_receive_queue, skb);
+ skb_set_owner_r(skb, sk);
+ }
+ return eaten;
+}
static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
{
@@ -4708,20 +4724,12 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
}
if (eaten <= 0) {
- struct sk_buff *tail;
queue_and_out:
if (eaten < 0 &&
tcp_try_rmem_schedule(sk, skb->truesize))
goto drop;
- tail = skb_peek_tail(&sk->sk_receive_queue);
- eaten = (tail &&
- tcp_try_coalesce(sk, tail, skb,
- &fragstolen)) ? 1 : 0;
- if (eaten <= 0) {
- skb_set_owner_r(skb, sk);
- __skb_queue_tail(&sk->sk_receive_queue, skb);
- }
+ eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
}
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
if (skb->len)
@@ -5416,14 +5424,6 @@ discard:
return 0;
}
-void tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int hdrlen)
-{
- __skb_pull(skb, hdrlen);
- __skb_queue_tail(&sk->sk_receive_queue, skb);
- skb_set_owner_r(skb, sk);
- tcp_sk(sk)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
-}
-
/*
* TCP receive function for the ESTABLISHED state.
*
@@ -5532,6 +5532,7 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
} else {
int eaten = 0;
int copied_early = 0;
+ bool fragstolen = false;
if (tp->copied_seq == tp->rcv_nxt &&
len - tcp_header_len <= tp->ucopy.len) {
@@ -5589,7 +5590,8 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPHPHITS);
/* Bulk data transfer: receiver */
- tcp_queue_rcv(sk, skb, tcp_header_len);
+ eaten = tcp_queue_rcv(sk, skb, tcp_header_len,
+ &fragstolen);
}
tcp_event_data_recv(sk, skb);
@@ -5611,7 +5613,7 @@ no_ack:
else
#endif
if (eaten)
- __kfree_skb(skb);
+ kfree_skb_partial(skb, fragstolen);
else
sk->sk_data_ready(sk, 0);
return 0;
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists