linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Michel Lespinasse <walken@google.com>
To: Linus Torvalds <torvalds@linux-foundation.org>,
	David Howells <dhowells@redhat.com>, Ingo Molnar <mingo@elte.hu>,
	Thomas Gleixner <tglx@linutronix.de>
Cc: LKML <linux-kernel@vger.kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Mike Waychison <mikew@google.com>,
	Suleiman Souhlal <suleiman@google.com>,
	Ying Han <yinghan@google.com>,
	Michel Lespinasse <walken@google.com>
Subject: [PATCH 01/10] x86 rwsem: minor cleanups
Date: Mon, 17 May 2010 15:25:45 -0700	[thread overview]
Message-ID: <1274135154-24082-2-git-send-email-walken@google.com> (raw)
In-Reply-To: <1274135154-24082-1-git-send-email-walken@google.com>

The only functional change here is that __up_write won't call
call_rwsem_wake anymore if the new rwsem value is >0. This makes
no real difference since call_rwsem_wake would have noticed the
active count being nonzero and done nothing anyway.

Besides that, I clarified a few comments.

Feel free to drop this patch from the series if you don't like it;
nothing else depends on it.

Signed-off-by: Michel Lespinasse <walken@google.com>
---
 arch/x86/include/asm/rwsem.h |   17 ++++++++---------
 1 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index 606ede1..86e0473 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -118,7 +118,7 @@ static inline void __down_read(struct rw_semaphore *sem)
 {
 	asm volatile("# beginning down_read\n\t"
 		     LOCK_PREFIX _ASM_INC "(%1)\n\t"
-		     /* adds 0x00000001, returns the old value */
+		     /* adds 0x00000001 */
 		     "  jns        1f\n"
 		     "  call call_rwsem_down_read_failed\n"
 		     "1:\n\t"
@@ -160,7 +160,7 @@ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
 	tmp = RWSEM_ACTIVE_WRITE_BIAS;
 	asm volatile("# beginning down_write\n\t"
 		     LOCK_PREFIX "  xadd      %1,(%2)\n\t"
-		     /* subtract 0x0000ffff, returns the old value */
+		     /* adds 0xffff0001, returns the old value */
 		     "  test      %1,%1\n\t"
 		     /* was the count 0 before? */
 		     "  jz        1f\n"
@@ -200,7 +200,7 @@ static inline void __up_read(struct rw_semaphore *sem)
 		     LOCK_PREFIX "  xadd      %1,(%2)\n\t"
 		     /* subtracts 1, returns the old value */
 		     "  jns        1f\n\t"
-		     "  call call_rwsem_wake\n"
+		     "  call call_rwsem_wake\n" /* expects old value in %edx */
 		     "1:\n"
 		     "# ending __up_read\n"
 		     : "+m" (sem->count), "=d" (tmp)
@@ -213,17 +213,16 @@ static inline void __up_read(struct rw_semaphore *sem)
  */
 static inline void __up_write(struct rw_semaphore *sem)
 {
-	rwsem_count_t tmp;
+	rwsem_count_t tmp = -RWSEM_ACTIVE_WRITE_BIAS;
 	asm volatile("# beginning __up_write\n\t"
 		     LOCK_PREFIX "  xadd      %1,(%2)\n\t"
-		     /* tries to transition
-			0xffff0001 -> 0x00000000 */
-		     "  jz       1f\n"
-		     "  call call_rwsem_wake\n"
+		     /* substracts 0xffff0001, returns the old value */
+		     "  jns        1f\n\t"
+		     "  call call_rwsem_wake\n" /* expects old value in %edx */
 		     "1:\n\t"
 		     "# ending __up_write\n"
 		     : "+m" (sem->count), "=d" (tmp)
-		     : "a" (sem), "1" (-RWSEM_ACTIVE_WRITE_BIAS)
+		     : "a" (sem), "1" (tmp)
 		     : "memory", "cc");
 }
 
-- 
1.7.0.1


  reply	other threads:[~2010-05-17 22:27 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-05-17 22:25 [PATCH 00/10] V3: rwsem changes + down_read_critical() proposal Michel Lespinasse
2010-05-17 22:25 ` Michel Lespinasse [this message]
2010-05-17 22:25 ` [PATCH 02/10] rwsem: fully separate code pathes to wake writers vs readers Michel Lespinasse
2010-05-17 22:25 ` [PATCH 03/10] rwsem: lighter active count checks when waking up readers Michel Lespinasse
2010-05-17 22:25 ` [PATCH 04/10] rwsem: let RWSEM_WAITING_BIAS represent any number of waiting threads Michel Lespinasse
2010-05-17 22:25 ` [PATCH 05/10] rwsem: wake queued readers when writer blocks on active read lock Michel Lespinasse
2010-05-17 22:25 ` [PATCH 06/10] rwsem: smaller wrappers around rwsem_down_failed_common Michel Lespinasse
2010-05-17 22:25 ` [PATCH 07/10] generic rwsem: implement down_read_critical() / up_read_critical() Michel Lespinasse
2010-05-17 22:44   ` Linus Torvalds
2010-05-17 23:13     ` Michel Lespinasse
2010-05-17 23:20       ` Michel Lespinasse
2010-05-19 13:21       ` David Howells
2010-05-19 23:47         ` Michel Lespinasse
2010-05-21  3:35         ` Michel Lespinasse
2010-05-17 22:25 ` [PATCH 08/10] rwsem: down_read_critical infrastructure support Michel Lespinasse
2010-05-17 22:25 ` [PATCH 09/10] x86 rwsem: down_read_critical implementation Michel Lespinasse
2010-05-17 22:25 ` [PATCH 10/10] Use down_read_critical() for /sys/<pid>/exe and /sys/<pid>/maps files Michel Lespinasse
2010-05-19 11:47 ` [PATCH 01/10] x86 rwsem: minor cleanups David Howells
2010-05-20 21:37   ` Michel Lespinasse
2010-05-19 12:04 ` [PATCH 02/10] rwsem: fully separate code pathes to wake writers vs readers David Howells
2010-05-20 21:48   ` Michel Lespinasse
2010-05-19 12:25 ` [PATCH 03/10] rwsem: lighter active count checks when waking up readers David Howells
2010-05-20 22:33   ` Michel Lespinasse
2010-05-21  8:06   ` David Howells
2010-05-19 12:33 ` [PATCH 04/10] rwsem: let RWSEM_WAITING_BIAS represent any number of waiting threads David Howells
2010-05-19 12:44 ` [PATCH 05/10] rwsem: wake queued readers when writer blocks on active read lock David Howells
2010-05-19 12:51 ` [PATCH 06/10] rwsem: smaller wrappers around rwsem_down_failed_common David Howells
2010-05-19 13:34 ` [PATCH 08/10] rwsem: down_read_critical infrastructure support David Howells
2010-05-20 23:30   ` Michel Lespinasse
2010-05-21  8:03   ` David Howells
2010-05-19 14:36 ` [PATCH 09/10] x86 rwsem: down_read_critical implementation David Howells
2010-05-19 15:21 ` [PATCH 10/10] Use down_read_critical() for /sys/<pid>/exe and /sys/<pid>/maps files David Howells
2010-05-21  2:44   ` Michel Lespinasse
2010-05-22  1:49   ` Michel Lespinasse
2010-05-25  9:42   ` David Howells
  -- strict thread matches above, loose matches on Subject: below --
2010-05-14 12:39 [PATCH 00/10] V2: rwsem changes + down_read_unfair() proposal Michel Lespinasse
2010-05-14 12:39 ` [PATCH 01/10] x86 rwsem: minor cleanups Michel Lespinasse

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=1274135154-24082-2-git-send-email-walken@google.com \
    --to=walken@google.com \
    --cc=akpm@linux-foundation.org \
    --cc=dhowells@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mikew@google.com \
    --cc=mingo@elte.hu \
    --cc=suleiman@google.com \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=yinghan@google.com \
    /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 NNTP newsgroup(s).