[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20120917003633.203529175@decadent.org.uk>
Date: Mon, 17 Sep 2012 01:37:15 +0100
From: Ben Hutchings <ben@...adent.org.uk>
To: linux-kernel@...r.kernel.org, stable@...r.kernel.org
Cc: torvalds@...ux-foundation.org, akpm@...ux-foundation.org,
alan@...rguk.ukuu.org.uk,
Ben Hutchings <bhutchings@...arflare.com>,
"David S. Miller" <davem@...emloft.net>
Subject: [ 050/135] tcp: Apply device TSO segment limit earlier
3.2-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ben Hutchings <bhutchings@...arflare.com>
[ Upstream commit 1485348d2424e1131ea42efc033cbd9366462b01 ]
Cache the device gso_max_segs in sock::sk_gso_max_segs and use it to
limit the size of TSO skbs. This avoids the need to fall back to
software GSO for local TCP senders.
Signed-off-by: Ben Hutchings <bhutchings@...arflare.com>
Signed-off-by: David S. Miller <davem@...emloft.net>
Signed-off-by: Ben Hutchings <ben@...adent.org.uk>
---
include/net/sock.h | 2 ++
net/core/sock.c | 1 +
net/ipv4/tcp.c | 4 +++-
net/ipv4/tcp_cong.c | 3 ++-
net/ipv4/tcp_output.c | 21 ++++++++++++---------
5 files changed, 20 insertions(+), 11 deletions(-)
diff --git a/include/net/sock.h b/include/net/sock.h
index 32e3937..ddf523c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -194,6 +194,7 @@ struct sock_common {
* @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK)
* @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
* @sk_gso_max_size: Maximum GSO segment size to build
+ * @sk_gso_max_segs: Maximum number of GSO segments
* @sk_lingertime: %SO_LINGER l_linger setting
* @sk_backlog: always used with the per-socket spinlock held
* @sk_callback_lock: used with the callbacks in the end of this struct
@@ -310,6 +311,7 @@ struct sock {
int sk_route_nocaps;
int sk_gso_type;
unsigned int sk_gso_max_size;
+ u16 sk_gso_max_segs;
int sk_rcvlowat;
unsigned long sk_lingertime;
struct sk_buff_head sk_error_queue;
diff --git a/net/core/sock.c b/net/core/sock.c
index 8d095b9..018fd41 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1308,6 +1308,7 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
} else {
sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM;
sk->sk_gso_max_size = dst->dev->gso_max_size;
+ sk->sk_gso_max_segs = dst->dev->gso_max_segs;
}
}
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index ad466a7..043d49b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -740,7 +740,9 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
old_size_goal + mss_now > xmit_size_goal)) {
xmit_size_goal = old_size_goal;
} else {
- tp->xmit_size_goal_segs = xmit_size_goal / mss_now;
+ tp->xmit_size_goal_segs =
+ min_t(u16, xmit_size_goal / mss_now,
+ sk->sk_gso_max_segs);
xmit_size_goal = tp->xmit_size_goal_segs * mss_now;
}
}
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 850c737..6cebfd2 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -290,7 +290,8 @@ int tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight)
left = tp->snd_cwnd - in_flight;
if (sk_can_gso(sk) &&
left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd &&
- left * tp->mss_cache < sk->sk_gso_max_size)
+ left * tp->mss_cache < sk->sk_gso_max_size &&
+ left < sk->sk_gso_max_segs)
return 1;
return left <= tcp_max_burst(tp);
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c51dd5b..921cbac 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1318,21 +1318,21 @@ static void tcp_cwnd_validate(struct sock *sk)
* when we would be allowed to send the split-due-to-Nagle skb fully.
*/
static unsigned int tcp_mss_split_point(const struct sock *sk, const struct sk_buff *skb,
- unsigned int mss_now, unsigned int cwnd)
+ unsigned int mss_now, unsigned int max_segs)
{
const struct tcp_sock *tp = tcp_sk(sk);
- u32 needed, window, cwnd_len;
+ u32 needed, window, max_len;
window = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
- cwnd_len = mss_now * cwnd;
+ max_len = mss_now * max_segs;
- if (likely(cwnd_len <= window && skb != tcp_write_queue_tail(sk)))
- return cwnd_len;
+ if (likely(max_len <= window && skb != tcp_write_queue_tail(sk)))
+ return max_len;
needed = min(skb->len, window);
- if (cwnd_len <= needed)
- return cwnd_len;
+ if (max_len <= needed)
+ return max_len;
return needed - needed % mss_now;
}
@@ -1560,7 +1560,8 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
limit = min(send_win, cong_win);
/* If a full-sized TSO skb can be sent, do it. */
- if (limit >= sk->sk_gso_max_size)
+ if (limit >= min_t(unsigned int, sk->sk_gso_max_size,
+ sk->sk_gso_max_segs * tp->mss_cache))
goto send_now;
/* Middle in queue won't get any more data, full sendable already? */
@@ -1786,7 +1787,9 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
limit = mss_now;
if (tso_segs > 1 && !tcp_urg_mode(tp))
limit = tcp_mss_split_point(sk, skb, mss_now,
- cwnd_quota);
+ min_t(unsigned int,
+ cwnd_quota,
+ sk->sk_gso_max_segs));
if (skb->len > limit &&
unlikely(tso_fragment(sk, skb, limit, mss_now, gfp)))
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists