Message ID | 20090702063624.GC3429@jolsa.lab.eng.brq.redhat.com |
---|---|
State | Superseded, archived |
Delegated to: | David Miller |
Headers | show |
Jiri Olsa a écrit : > Adding smp_mb__after_lock define to be used as a smp_mb call after > a lock. > > Making it nop for x86, since {read|write|spin}_lock() on x86 are > full memory barriers. > > wbr, > jirka > > > Signed-off-by: Jiri Olsa <jolsa@redhat.com> Maybe we should remind that sk_has_helper() is always called right after a call to read_lock() as in : read_lock(&sk->sk_callback_lock); if (sk_has_sleeper(sk)) wake_up_interruptible_all(sk->sk_sleep); Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Thanks Jiri > > --- > arch/x86/include/asm/spinlock.h | 3 +++ > include/linux/spinlock.h | 5 +++++ > include/net/sock.h | 2 +- > 3 files changed, 9 insertions(+), 1 deletions(-) > > diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h > index b7e5db8..39ecc5f 100644 > --- a/arch/x86/include/asm/spinlock.h > +++ b/arch/x86/include/asm/spinlock.h > @@ -302,4 +302,7 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw) > #define _raw_read_relax(lock) cpu_relax() > #define _raw_write_relax(lock) cpu_relax() > > +/* The {read|write|spin}_lock() on x86 are full memory barriers. */ > +#define smp_mb__after_lock() do { } while (0) > + > #endif /* _ASM_X86_SPINLOCK_H */ > diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h > index 252b245..ae053bd 100644 > --- a/include/linux/spinlock.h > +++ b/include/linux/spinlock.h > @@ -132,6 +132,11 @@ do { \ > #endif /*__raw_spin_is_contended*/ > #endif > > +/* The lock does not imply full memory barrier. */ > +#ifndef smp_mb__after_lock > +#define smp_mb__after_lock() smp_mb() > +#endif > + > /** > * spin_unlock_wait - wait until the spinlock gets unlocked > * @lock: the spinlock in question. > diff --git a/include/net/sock.h b/include/net/sock.h > index 4eb8409..b3e96a4 100644 > --- a/include/net/sock.h > +++ b/include/net/sock.h > @@ -1280,7 +1280,7 @@ static inline int sk_has_sleeper(struct sock *sk) > * > * This memory barrier is paired in the sock_poll_wait. > */ > - smp_mb(); > + smp_mb__after_lock(); > return sk->sk_sleep && waitqueue_active(sk->sk_sleep); > } > > -- -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Thu, 2 Jul 2009, Eric Dumazet wrote: > Jiri Olsa a écrit : > > Adding smp_mb__after_lock define to be used as a smp_mb call after > > a lock. > > > > Making it nop for x86, since {read|write|spin}_lock() on x86 are > > full memory barriers. > > > > wbr, > > jirka > > > > > > Signed-off-by: Jiri Olsa <jolsa@redhat.com> > > > Maybe we should remind that sk_has_helper() is always called > right after a call to read_lock() as in : > > read_lock(&sk->sk_callback_lock); > if (sk_has_sleeper(sk)) > wake_up_interruptible_all(sk->sk_sleep); Agreed, that'd be to have it in the source code comment. - Davide
On Thu, Jul 02, 2009 at 07:39:04AM -0700, Davide Libenzi wrote: > On Thu, 2 Jul 2009, Eric Dumazet wrote: > > > Jiri Olsa a écrit : > > > Adding smp_mb__after_lock define to be used as a smp_mb call after > > > a lock. > > > > > > Making it nop for x86, since {read|write|spin}_lock() on x86 are > > > full memory barriers. > > > > > > wbr, > > > jirka > > > > > > > > > Signed-off-by: Jiri Olsa <jolsa@redhat.com> > > > > > > Maybe we should remind that sk_has_helper() is always called > > right after a call to read_lock() as in : > > > > read_lock(&sk->sk_callback_lock); > > if (sk_has_sleeper(sk)) > > wake_up_interruptible_all(sk->sk_sleep); > > Agreed, that'd be to have it in the source code comment. > > > - Davide > ok, I'll add it to the 1/2 part in v5 jirka -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Fri, Jul 03, 2009 at 09:41:26AM +0200, Jiri Olsa wrote: > On Thu, Jul 02, 2009 at 07:39:04AM -0700, Davide Libenzi wrote: > > On Thu, 2 Jul 2009, Eric Dumazet wrote: > > > > > Jiri Olsa a écrit : > > > > Adding smp_mb__after_lock define to be used as a smp_mb call after > > > > a lock. > > > > > > > > Making it nop for x86, since {read|write|spin}_lock() on x86 are > > > > full memory barriers. > > > > > > > > wbr, > > > > jirka > > > > > > > > > > > > Signed-off-by: Jiri Olsa <jolsa@redhat.com> > > > > > > > > > Maybe we should remind that sk_has_helper() is always called > > > right after a call to read_lock() as in : > > > > > > read_lock(&sk->sk_callback_lock); > > > if (sk_has_sleeper(sk)) > > > wake_up_interruptible_all(sk->sk_sleep); > > > > Agreed, that'd be to have it in the source code comment. > > > > > > - Davide > > > > ok, I'll add it to the 1/2 part in v5 > Btw., there is a tiny typo: - receive callbacks. Adding fuctions sock_poll_wait and sock_has_sleeper + receive callbacks. Adding fuctions sock_poll_wait and sk_has_sleeper Jarek P. -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Fri, Jul 03, 2009 at 09:41:26AM +0200, Jiri Olsa wrote: > On Thu, Jul 02, 2009 at 07:39:04AM -0700, Davide Libenzi wrote: > > On Thu, 2 Jul 2009, Eric Dumazet wrote: > > > > > Jiri Olsa a écrit : > > > > Adding smp_mb__after_lock define to be used as a smp_mb call after > > > > a lock. > > > > > > > > Making it nop for x86, since {read|write|spin}_lock() on x86 are > > > > full memory barriers. > > > > > > > > wbr, > > > > jirka > > > > > > > > > > > > Signed-off-by: Jiri Olsa <jolsa@redhat.com> > > > > > > > > > Maybe we should remind that sk_has_helper() is always called > > > right after a call to read_lock() as in : > > > > > > read_lock(&sk->sk_callback_lock); > > > if (sk_has_sleeper(sk)) > > > wake_up_interruptible_all(sk->sk_sleep); > > > > Agreed, that'd be to have it in the source code comment. > > > > > > - Davide > > > > ok, I'll add it to the 1/2 part in v5 > > jirka actually I see the 2/2 would be better :) jirka -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Fri, Jul 03, 2009 at 07:47:31AM +0000, Jarek Poplawski wrote: > On Fri, Jul 03, 2009 at 09:41:26AM +0200, Jiri Olsa wrote: > > On Thu, Jul 02, 2009 at 07:39:04AM -0700, Davide Libenzi wrote: > > > On Thu, 2 Jul 2009, Eric Dumazet wrote: > > > > > > > Jiri Olsa a écrit : > > > > > Adding smp_mb__after_lock define to be used as a smp_mb call after > > > > > a lock. > > > > > > > > > > Making it nop for x86, since {read|write|spin}_lock() on x86 are > > > > > full memory barriers. > > > > > > > > > > wbr, > > > > > jirka > > > > > > > > > > > > > > > Signed-off-by: Jiri Olsa <jolsa@redhat.com> > > > > > > > > > > > > Maybe we should remind that sk_has_helper() is always called > > > > right after a call to read_lock() as in : > > > > > > > > read_lock(&sk->sk_callback_lock); > > > > if (sk_has_sleeper(sk)) > > > > wake_up_interruptible_all(sk->sk_sleep); > > > > > > Agreed, that'd be to have it in the source code comment. > > > > > > > > > - Davide > > > > > > > ok, I'll add it to the 1/2 part in v5 > > > > Btw., there is a tiny typo: > > - receive callbacks. Adding fuctions sock_poll_wait and sock_has_sleeper > + receive callbacks. Adding fuctions sock_poll_wait and sk_has_sleeper > > Jarek P. thanks, jirka -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index b7e5db8..39ecc5f 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -302,4 +302,7 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw) #define _raw_read_relax(lock) cpu_relax() #define _raw_write_relax(lock) cpu_relax() +/* The {read|write|spin}_lock() on x86 are full memory barriers. */ +#define smp_mb__after_lock() do { } while (0) + #endif /* _ASM_X86_SPINLOCK_H */ diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 252b245..ae053bd 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -132,6 +132,11 @@ do { \ #endif /*__raw_spin_is_contended*/ #endif +/* The lock does not imply full memory barrier. */ +#ifndef smp_mb__after_lock +#define smp_mb__after_lock() smp_mb() +#endif + /** * spin_unlock_wait - wait until the spinlock gets unlocked * @lock: the spinlock in question. diff --git a/include/net/sock.h b/include/net/sock.h index 4eb8409..b3e96a4 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1280,7 +1280,7 @@ static inline int sk_has_sleeper(struct sock *sk) * * This memory barrier is paired in the sock_poll_wait. */ - smp_mb(); + smp_mb__after_lock(); return sk->sk_sleep && waitqueue_active(sk->sk_sleep); }
Adding smp_mb__after_lock define to be used as a smp_mb call after a lock. Making it nop for x86, since {read|write|spin}_lock() on x86 are full memory barriers. wbr, jirka Signed-off-by: Jiri Olsa <jolsa@redhat.com> --- arch/x86/include/asm/spinlock.h | 3 +++ include/linux/spinlock.h | 5 +++++ include/net/sock.h | 2 +- 3 files changed, 9 insertions(+), 1 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html