From: Valentin Schneider <vschneid@redhat.com>
To: dccp@vger.kernel.org, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-rt-users@vger.kernel.org
Cc: "David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
mleitner@redhat.com, David Ahern <dsahern@kernel.org>,
Juri Lelli <juri.lelli@redhat.com>,
Tomas Glozar <tglozar@redhat.com>,
Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
Thomas Gleixner <tglx@linutronix.de>
Subject: [PATCH v4 1/1] tcp/dcpp: Un-pin tw_timer
Date: Thu, 11 Apr 2024 14:05:35 +0200 [thread overview]
Message-ID: <20240411120535.2494067-2-vschneid@redhat.com> (raw)
In-Reply-To: <20240411120535.2494067-1-vschneid@redhat.com>
The TCP timewait timer is proving to be problematic for setups where scheduler
CPU isolation is achieved at runtime via cpusets (as opposed to statically via
isolcpus=domains).
What happens there is a CPU goes through tcp_time_wait(), arming the time_wait
timer, then gets isolated. TCP_TIMEWAIT_LEN later, the timer fires, causing
interference for the now-isolated CPU. This is conceptually similar to the issue
described in
e02b93124855 ("workqueue: Unbind kworkers before sending them to exit()")
Move inet_twsk_schedule() to within inet_twsk_hashdance(), with the ehash
lock held. Expand the lock's critical section from inet_twsk_kill() to
inet_twsk_deschedule_put(), serializing the scheduling vs descheduling of
the timer. IOW, this prevents the following race:
tcp_time_wait()
inet_twsk_hashdance()
inet_twsk_deschedule_put()
del_timer_sync()
inet_twsk_schedule()
This partially reverts
ec94c2696f0b ("tcp/dccp: avoid one atomic operation for timewait hashdance")
This also reinstores a comment from
ec94c2696f0b ("tcp/dccp: avoid one atomic operation for timewait hashdance")
as inet_twsk_hashdance() had a "Step 1" and "Step 3" comment, but the "Step
2" had gone missing.
Thanks to Paolo for suggesting to leverage the ehash lock.
Link: https://lore.kernel.org/all/ZPhpfMjSiHVjQkTk@localhost.localdomain/
Signed-off-by: Valentin Schneider <vschneid@redhat.com>
---
include/net/inet_timewait_sock.h | 6 ++--
net/dccp/minisocks.c | 9 +++--
net/ipv4/inet_timewait_sock.c | 59 +++++++++++++++++++++++---------
net/ipv4/tcp_minisocks.c | 9 +++--
4 files changed, 55 insertions(+), 28 deletions(-)
diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
index f28da08a37b4e..d696d10dc8aec 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -93,8 +93,10 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
struct inet_timewait_death_row *dr,
const int state);
-void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
- struct inet_hashinfo *hashinfo);
+void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw,
+ struct sock *sk,
+ struct inet_hashinfo *hashinfo,
+ int timeo);
void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo,
bool rearm);
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 64d805b27adde..dd0b09553f142 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -58,11 +58,10 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
* we complete the initialization.
*/
local_bh_disable();
- inet_twsk_schedule(tw, timeo);
- /* Linkage updates.
- * Note that access to tw after this point is illegal.
- */
- inet_twsk_hashdance(tw, sk, &dccp_hashinfo);
+ /* Linkage updates. */
+ inet_twsk_hashdance_schedule(tw, sk, &dccp_hashinfo, timeo);
+ /* Access to tw after this point is illegal. */
+ inet_twsk_put(tw);
local_bh_enable();
} else {
/* Sorry, if we're out of memory, just CLOSE this
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index e8de45d34d56a..f3d349e6e373b 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -44,14 +44,14 @@ void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
__sock_put((struct sock *)tw);
}
-/* Must be called with locally disabled BHs. */
-static void inet_twsk_kill(struct inet_timewait_sock *tw)
+static void __inet_twsk_kill(struct inet_timewait_sock *tw, spinlock_t *lock)
+__releases(lock)
{
struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo;
- spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
struct inet_bind_hashbucket *bhead, *bhead2;
- spin_lock(lock);
+ lockdep_assert_held(lock);
+
sk_nulls_del_node_init_rcu((struct sock *)tw);
spin_unlock(lock);
@@ -71,6 +71,16 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw)
inet_twsk_put(tw);
}
+/* Must be called with locally disabled BHs. */
+static void inet_twsk_kill(struct inet_timewait_sock *tw)
+{
+ struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo;
+ spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
+
+ spin_lock(lock);
+ __inet_twsk_kill(tw, lock);
+}
+
void inet_twsk_free(struct inet_timewait_sock *tw)
{
struct module *owner = tw->tw_prot->owner;
@@ -97,8 +107,10 @@ static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
* Essentially we whip up a timewait bucket, copy the relevant info into it
* from the SK, and mess with hash chains and list linkage.
*/
-void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
- struct inet_hashinfo *hashinfo)
+void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw,
+ struct sock *sk,
+ struct inet_hashinfo *hashinfo,
+ int timeo)
{
const struct inet_sock *inet = inet_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -129,26 +141,33 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
spin_lock(lock);
+ /* Step 2: Hash TW into tcp ehash chain */
inet_twsk_add_node_rcu(tw, &ehead->chain);
/* Step 3: Remove SK from hash chain */
if (__sk_nulls_del_node_init_rcu(sk))
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
- spin_unlock(lock);
- /* tw_refcnt is set to 3 because we have :
+ /* Ensure above writes are committed into memory before updating the
+ * refcount.
+ * Provides ordering vs later refcount_inc().
+ */
+ smp_wmb();
+ /* tw_refcnt is set to 4 because we have :
* - one reference for bhash chain.
* - one reference for ehash chain.
* - one reference for timer.
- * We can use atomic_set() because prior spin_lock()/spin_unlock()
- * committed into memory all tw fields.
- * Also note that after this point, we lost our implicit reference
- * so we are not allowed to use tw anymore.
+ * - one reference for ourself (our caller will release it).
*/
- refcount_set(&tw->tw_refcnt, 3);
+ refcount_set(&tw->tw_refcnt, 4);
+
+ inet_twsk_schedule(tw, timeo);
+
+ spin_unlock(lock);
+
}
-EXPORT_SYMBOL_GPL(inet_twsk_hashdance);
+EXPORT_SYMBOL_GPL(inet_twsk_hashdance_schedule);
static void tw_timer_handler(struct timer_list *t)
{
@@ -217,8 +236,16 @@ EXPORT_SYMBOL_GPL(inet_twsk_alloc);
*/
void inet_twsk_deschedule_put(struct inet_timewait_sock *tw)
{
- if (del_timer_sync(&tw->tw_timer))
- inet_twsk_kill(tw);
+ struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo;
+ spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
+
+ spin_lock(lock);
+ if (timer_shutdown_sync(&tw->tw_timer)) {
+ /* releases @lock */
+ __inet_twsk_kill(tw, lock);
+ } else {
+ spin_unlock(lock);
+ }
inet_twsk_put(tw);
}
EXPORT_SYMBOL(inet_twsk_deschedule_put);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index f0761f060a837..77e2515409e40 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -343,11 +343,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
* we complete the initialization.
*/
local_bh_disable();
- inet_twsk_schedule(tw, timeo);
- /* Linkage updates.
- * Note that access to tw after this point is illegal.
- */
- inet_twsk_hashdance(tw, sk, net->ipv4.tcp_death_row.hashinfo);
+ /* Linkage updates. */
+ inet_twsk_hashdance_schedule(tw, sk, net->ipv4.tcp_death_row.hashinfo, timeo);
+ /* Access to tw after this point is illegal. */
+ inet_twsk_put(tw);
local_bh_enable();
} else {
/* Sorry, if we're out of memory, just CLOSE this
--
2.43.0
next prev parent reply other threads:[~2024-04-11 12:05 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-11 12:05 [PATCH v4 0/1] tcp/dcpp: Un-pin tw_timer Valentin Schneider
2024-04-11 12:05 ` Valentin Schneider [this message]
2024-04-11 17:05 ` [PATCH v4 1/1] " Jakub Kicinski
2024-04-12 12:20 ` Valentin Schneider
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240411120535.2494067-2-vschneid@redhat.com \
--to=vschneid@redhat.com \
--cc=bigeasy@linutronix.de \
--cc=davem@davemloft.net \
--cc=dccp@vger.kernel.org \
--cc=dsahern@kernel.org \
--cc=edumazet@google.com \
--cc=juri.lelli@redhat.com \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rt-users@vger.kernel.org \
--cc=mleitner@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=tglozar@redhat.com \
--cc=tglx@linutronix.de \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).