[PATCH net] tcp/dccp: block bh before arming time_wait timer

Subsystems: networking [general], networking [tcp], the rest

STALE3239d

4 messages, 3 authors, 2017-12-01 · open the first message on its own page

[PATCH net] tcp/dccp: block bh before arming time_wait timer

From: Eric Dumazet <hidden>
Date: 2017-12-01 18:06:59

From: Eric Dumazet <redacted>

Maciej Żenczykowski reported some panics in tcp_twsk_destructor()
that might be caused by the following bug.

timewait timer is pinned to the cpu, because we want to transition
timwewait refcount from 0 to 4 in one go, once everything has been
initialized.

At the time commit ed2e92394589 ("tcp/dccp: fix timewait races in timer
handling") was merged, TCP was always running from BH habdler.

After commit 5413d1babe8f ("net: do not block BH while processing
socket backlog") we definitely can run tcp_time_wait() from process
context.

We need to block BH in the critical section so that the pinned timer
has still its purpose.

This bug is more likely to happen under stress and when very small RTO
are used in datacenter flows.

Fixes: 5413d1babe8f ("net: do not block BH while processing socket backlog")
Signed-off-by: Eric Dumazet <redacted>
Reported-by: Maciej Żenczykowski <redacted>
---
 net/dccp/minisocks.c     |    6 ++++++
 net/ipv4/tcp_minisocks.c |    6 ++++++
 2 files changed, 12 insertions(+)

diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index abd07a443219853b022bef41cb072e90ff8f07f0..178bb9833311f83205317b07fe64cb2e45a9f734 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -57,10 +57,16 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
 		if (state == DCCP_TIME_WAIT)
 			timeo = DCCP_TIMEWAIT_LEN;
 
+		/* tw_timer is pinned, so we need to make sure BH are disabled
+		 * in following section, otherwise timer handler could run before
+		 * we complete the initialization.
+		 */
+		local_bh_disable();
 		inet_twsk_schedule(tw, timeo);
 		/* Linkage updates. */
 		__inet_twsk_hashdance(tw, sk, &dccp_hashinfo);
 		inet_twsk_put(tw);
+		local_bh_enable();
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
 		 * socket up.  We've got bigger problems than
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index e36eff0403f4e80c4f7291a70614f40125652133..b079b619b60ca577d5ef20a5065fce87acecd96c 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -310,10 +310,16 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
 		if (state == TCP_TIME_WAIT)
 			timeo = TCP_TIMEWAIT_LEN;
 
+		/* tw_timer is pinned, so we need to make sure BH are disabled
+		 * in following section, otherwise timer handler could run before
+		 * we complete the initialization.
+		 */
+		local_bh_disable();
 		inet_twsk_schedule(tw, timeo);
 		/* Linkage updates. */
 		__inet_twsk_hashdance(tw, sk, &tcp_hashinfo);
 		inet_twsk_put(tw);
+		local_bh_enable();
 	} else {
 		/* Sorry, if we're out of memory, just CLOSE this
 		 * socket up.  We've got bigger problems than

Re: [PATCH net] tcp/dccp: block bh before arming time_wait timer

From: Maciej Żenczykowski <hidden>
Date: 2017-12-01 18:48:22

Acked-by: Maciej Żenczykowski <redacted>

Re: [PATCH net] tcp/dccp: block bh before arming time_wait timer

From: David Miller <davem@davemloft.net>
Date: 2017-12-01 20:12:46

From: Eric Dumazet <redacted>
Date: Fri, 01 Dec 2017 10:06:56 -0800
From: Eric Dumazet <redacted>

Maciej Żenczykowski reported some panics in tcp_twsk_destructor()
that might be caused by the following bug.

timewait timer is pinned to the cpu, because we want to transition
timwewait refcount from 0 to 4 in one go, once everything has been
initialized.

At the time commit ed2e92394589 ("tcp/dccp: fix timewait races in timer
handling") was merged, TCP was always running from BH habdler.

After commit 5413d1babe8f ("net: do not block BH while processing
socket backlog") we definitely can run tcp_time_wait() from process
context.

We need to block BH in the critical section so that the pinned timer
has still its purpose.

This bug is more likely to happen under stress and when very small RTO
are used in datacenter flows.

Fixes: 5413d1babe8f ("net: do not block BH while processing socket backlog")
Signed-off-by: Eric Dumazet <redacted>
Reported-by: Maciej Żenczykowski <redacted>
Applied and queued up for -stable, thanks Eric.

Re: [PATCH net] tcp/dccp: block bh before arming time_wait timer

From: Eric Dumazet <hidden>
Date: 2017-12-01 20:51:29

On Fri, 2017-12-01 at 15:12 -0500, David Miller wrote:
From: Eric Dumazet <redacted>
Date: Fri, 01 Dec 2017 10:06:56 -0800
quoted
From: Eric Dumazet <redacted>

Maciej Żenczykowski reported some panics in tcp_twsk_destructor()
that might be caused by the following bug.

timewait timer is pinned to the cpu, because we want to transition
timwewait refcount from 0 to 4 in one go, once everything has been
initialized.

At the time commit ed2e92394589 ("tcp/dccp: fix timewait races in
timer
quoted
handling") was merged, TCP was always running from BH habdler.

After commit 5413d1babe8f ("net: do not block BH while processing
socket backlog") we definitely can run tcp_time_wait() from process
context.

We need to block BH in the critical section so that the pinned
timer
quoted
has still its purpose.

This bug is more likely to happen under stress and when very small
RTO
quoted
are used in datacenter flows.

Fixes: 5413d1babe8f ("net: do not block BH while processing socket
backlog")
quoted
Signed-off-by: Eric Dumazet <redacted>
Reported-by: Maciej Żenczykowski <redacted>
Applied and queued up for -stable, thanks Eric.
It just occurred to me that we can now revert 614bdd4d6e61d26
("tcp: must block bh in __inet_twsk_hashdance()")
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help