Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]


Groups > linux.kernel > #1362148 > unrolled thread

[PATCH] Documentation,barriers: Mention smp_cond_acquire()

Started byDavidlohr Bueso <dave@stgolabs.net>
First post2016-03-21 22:10 +0100
Last post2016-03-23 17:20 +0100
Articles 2 — 2 participants

Back to article view | Back to linux.kernel


Contents

  [PATCH] Documentation,barriers: Mention smp_cond_acquire() Davidlohr Bueso <dave@stgolabs.net> - 2016-03-21 22:10 +0100
    Re: [PATCH] Documentation,barriers: Mention smp_cond_acquire() "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> - 2016-03-23 17:20 +0100

#1362148 — [PATCH] Documentation,barriers: Mention smp_cond_acquire()

FromDavidlohr Bueso <dave@stgolabs.net>
Date2016-03-21 22:10 +0100
Subject[PATCH] Documentation,barriers: Mention smp_cond_acquire()
Message-ID<rfffk-2ON-7@gated-at.bofh.it>
... do this next to smp_load_acquire when first mentioning
ACQUIRE. While this call is briefly explained and ctrl
dependencies are mentioned later, it does not hurt the reader.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
---
 Documentation/memory-barriers.txt | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 3729cbe60e41..2b5ea9d01a8f 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -430,8 +430,9 @@ And a couple of implicit varieties:
      This acts as a one-way permeable barrier.  It guarantees that all memory
      operations after the ACQUIRE operation will appear to happen after the
      ACQUIRE operation with respect to the other components of the system.
-     ACQUIRE operations include LOCK operations and smp_load_acquire()
-     operations.
+     ACQUIRE operations include LOCK operations and both smp_load_acquire()
+     and smp_cond_acquire() operations. The later builds the necessary ACQUIRE
+     semantics from relying on a control dependency and smp_rmb().
 
      Memory operations that occur before an ACQUIRE operation may appear to
      happen after it completes.
-- 
2.1.4

[toc] | [next] | [standalone]


#1363516

From"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date2016-03-23 17:20 +0100
Message-ID<rfTFL-60M-5@gated-at.bofh.it>
In reply to#1362148
On Mon, Mar 21, 2016 at 02:07:19PM -0700, Davidlohr Bueso wrote:
> ... do this next to smp_load_acquire when first mentioning
> ACQUIRE. While this call is briefly explained and ctrl
> dependencies are mentioned later, it does not hurt the reader.
> 
> Signed-off-by: Davidlohr Bueso <dbueso@suse.de>

Queued for review, thank you, Davidlohr!

							Thanx, Paul

> ---
>  Documentation/memory-barriers.txt | 5 +++--
>  1 file changed, 3 insertions(+), 2 deletions(-)
> 
> diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
> index 3729cbe60e41..2b5ea9d01a8f 100644
> --- a/Documentation/memory-barriers.txt
> +++ b/Documentation/memory-barriers.txt
> @@ -430,8 +430,9 @@ And a couple of implicit varieties:
>       This acts as a one-way permeable barrier.  It guarantees that all memory
>       operations after the ACQUIRE operation will appear to happen after the
>       ACQUIRE operation with respect to the other components of the system.
> -     ACQUIRE operations include LOCK operations and smp_load_acquire()
> -     operations.
> +     ACQUIRE operations include LOCK operations and both smp_load_acquire()
> +     and smp_cond_acquire() operations. The later builds the necessary ACQUIRE
> +     semantics from relying on a control dependency and smp_rmb().
> 
>       Memory operations that occur before an ACQUIRE operation may appear to
>       happen after it completes.
> -- 
> 2.1.4
> 

[toc] | [prev] | [standalone]


Back to top | Article view | linux.kernel


csiph-web