From: Eric Dumazet edumazet@google.com
[ Upstream commit 62c07983bef9d3e78e71189441e1a470f0d1e653 ]
Christophe Leroy reported a ~80ms latency spike happening at first TCP connect() time.
This is because __inet_hash_connect() uses get_random_once() to populate a perturbation table which became quite big after commit 4c2c8f03a5ab ("tcp: increase source port perturb table to 2^16")
get_random_once() uses DO_ONCE(), which block hard irqs for the duration of the operation.
This patch adds DO_ONCE_SLOW() which uses a mutex instead of a spinlock for operations where we prefer to stay in process context.
Then __inet_hash_connect() can use get_random_slow_once() to populate its perturbation table.
Fixes: 4c2c8f03a5ab ("tcp: increase source port perturb table to 2^16") Fixes: 190cc82489f4 ("tcp: change source port randomizarion at connect() time") Reported-by: Christophe Leroy christophe.leroy@csgroup.eu Link: https://lore.kernel.org/netdev/CANn89iLAEYBaoYajy0Y9UmGFff5GPxDUoG-ErVB2jDdR... Signed-off-by: Eric Dumazet edumazet@google.com Cc: Willy Tarreau w@1wt.eu Tested-by: Christophe Leroy christophe.leroy@csgroup.eu Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/once.h | 28 ++++++++++++++++++++++++++++ lib/once.c | 30 ++++++++++++++++++++++++++++++ net/ipv4/inet_hashtables.c | 4 ++-- 3 files changed, 60 insertions(+), 2 deletions(-)
diff --git a/include/linux/once.h b/include/linux/once.h index b14d8b309d52..176ab75b42df 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -5,10 +5,18 @@ #include <linux/types.h> #include <linux/jump_label.h>
+/* Helpers used from arbitrary contexts. + * Hard irqs are blocked, be cautious. + */ bool __do_once_start(bool *done, unsigned long *flags); void __do_once_done(bool *done, struct static_key_true *once_key, unsigned long *flags, struct module *mod);
+/* Variant for process contexts only. */ +bool __do_once_slow_start(bool *done); +void __do_once_slow_done(bool *done, struct static_key_true *once_key, + struct module *mod); + /* Call a function exactly once. The idea of DO_ONCE() is to perform * a function call such as initialization of random seeds, etc, only * once, where DO_ONCE() can live in the fast-path. After @func has @@ -52,7 +60,27 @@ void __do_once_done(bool *done, struct static_key_true *once_key, ___ret; \ })
+/* Variant of DO_ONCE() for process/sleepable contexts. */ +#define DO_ONCE_SLOW(func, ...) \ + ({ \ + bool ___ret = false; \ + static bool __section(".data.once") ___done = false; \ + static DEFINE_STATIC_KEY_TRUE(___once_key); \ + if (static_branch_unlikely(&___once_key)) { \ + ___ret = __do_once_slow_start(&___done); \ + if (unlikely(___ret)) { \ + func(__VA_ARGS__); \ + __do_once_slow_done(&___done, &___once_key, \ + THIS_MODULE); \ + } \ + } \ + ___ret; \ + }) + #define get_random_once(buf, nbytes) \ DO_ONCE(get_random_bytes, (buf), (nbytes))
+#define get_random_slow_once(buf, nbytes) \ + DO_ONCE_SLOW(get_random_bytes, (buf), (nbytes)) + #endif /* _LINUX_ONCE_H */ diff --git a/lib/once.c b/lib/once.c index 59149bf3bfb4..351f66aad310 100644 --- a/lib/once.c +++ b/lib/once.c @@ -66,3 +66,33 @@ void __do_once_done(bool *done, struct static_key_true *once_key, once_disable_jump(once_key, mod); } EXPORT_SYMBOL(__do_once_done); + +static DEFINE_MUTEX(once_mutex); + +bool __do_once_slow_start(bool *done) + __acquires(once_mutex) +{ + mutex_lock(&once_mutex); + if (*done) { + mutex_unlock(&once_mutex); + /* Keep sparse happy by restoring an even lock count on + * this mutex. In case we return here, we don't call into + * __do_once_done but return early in the DO_ONCE_SLOW() macro. + */ + __acquire(once_mutex); + return false; + } + + return true; +} +EXPORT_SYMBOL(__do_once_slow_start); + +void __do_once_slow_done(bool *done, struct static_key_true *once_key, + struct module *mod) + __releases(once_mutex) +{ + *done = true; + mutex_unlock(&once_mutex); + once_disable_jump(once_key, mod); +} +EXPORT_SYMBOL(__do_once_slow_done); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index b9d995b5ce24..f5950a7172d6 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -729,8 +729,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, if (likely(remaining > 1)) remaining &= ~1U;
- net_get_random_once(table_perturb, - INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb)); + get_random_slow_once(table_perturb, + INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb)); index = port_offset & (INET_TABLE_PERTURB_SIZE - 1);
offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32);