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>
Subject: [PATCH 03/11] rwsem: fully separate code pathes to wake writers vs readers
Date: Mon, 24 May 2010 13:31:13 -0700 [thread overview]
Message-ID: <1274733081-4623-4-git-send-email-walken@google.com> (raw)
In-Reply-To: <1274733081-4623-1-git-send-email-walken@google.com>
This is in preparation to later changes in the series.
In __rwsem_do_wake(), the first queued waiter is checked first in order
to determine whether it's a writer or a reader. The code paths diverge
at this point. The code that checks and increments the rwsem active count
is duplicated on both sides - the point is that later changes in the
series will be able to independently modify both sides.
Signed-off-by: Michel Lespinasse <walken@google.com>
---
lib/rwsem.c | 61 ++++++++++++++++++++++++++++++++--------------------------
1 files changed, 34 insertions(+), 27 deletions(-)
diff --git a/lib/rwsem.c b/lib/rwsem.c
index ceba8e2..917fd94 100644
--- a/lib/rwsem.c
+++ b/lib/rwsem.c
@@ -41,7 +41,7 @@ struct rwsem_waiter {
* - if we come here from up_xxxx(), then:
* - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed)
* - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so)
- * - there must be someone on the queue
+ * - there must be someone on the queue
* - the spinlock must be held by the caller
* - woken process blocks are discarded from the list after having task zeroed
* - writers are only woken if downgrading is false
@@ -54,26 +54,23 @@ __rwsem_do_wake(struct rw_semaphore *sem, int downgrading)
struct list_head *next;
signed long oldcount, woken, loop;
+ waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+ if (!(waiter->flags & RWSEM_WAITING_FOR_WRITE))
+ goto readers_only;
+
if (downgrading)
- goto dont_wake_writers;
+ goto out;
- /* if we came through an up_xxxx() call, we only only wake someone up
- * if we can transition the active part of the count from 0 -> 1
+ /* There's a writer at the front of the queue - try to grant it the
+ * write lock. However, we only wake this writer if we can transition
+ * the active part of the count from 0 -> 1
*/
- try_again:
+ try_again_write:
oldcount = rwsem_atomic_update(RWSEM_ACTIVE_BIAS, sem)
- RWSEM_ACTIVE_BIAS;
if (oldcount & RWSEM_ACTIVE_MASK)
- goto undo;
-
- waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
-
- /* try to grant a single write lock if there's a writer at the front
- * of the queue - note we leave the 'active part' of the count
- * incremented by 1 and the waiting part incremented by 0x00010000
- */
- if (!(waiter->flags & RWSEM_WAITING_FOR_WRITE))
- goto readers_only;
+ /* Someone grabbed the sem already */
+ goto undo_write;
/* We must be careful not to touch 'waiter' after we set ->task = NULL.
* It is an allocated on the waiter's stack and may become invalid at
@@ -87,18 +84,24 @@ __rwsem_do_wake(struct rw_semaphore *sem, int downgrading)
put_task_struct(tsk);
goto out;
- /* don't want to wake any writers */
- dont_wake_writers:
- waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
- if (waiter->flags & RWSEM_WAITING_FOR_WRITE)
- goto out;
+ readers_only:
+ if (downgrading)
+ goto wake_readers;
+
+ /* if we came through an up_xxxx() call, we only only wake someone up
+ * if we can transition the active part of the count from 0 -> 1 */
+ try_again_read:
+ oldcount = rwsem_atomic_update(RWSEM_ACTIVE_BIAS, sem)
+ - RWSEM_ACTIVE_BIAS;
+ if (oldcount & RWSEM_ACTIVE_MASK)
+ /* Someone grabbed the sem already */
+ goto undo_read;
- /* grant an infinite number of read locks to the readers at the front
- * of the queue
- * - note we increment the 'active part' of the count by the number of
- * readers before waking any processes up
+ wake_readers:
+ /* Grant an infinite number of read locks to the readers at the front
+ * of the queue. Note we increment the 'active part' of the count by
+ * the number of readers before waking any processes up.
*/
- readers_only:
woken = 0;
do {
woken++;
@@ -138,10 +141,14 @@ __rwsem_do_wake(struct rw_semaphore *sem, int downgrading)
/* undo the change to the active count, but check for a transition
* 1->0 */
- undo:
+ undo_write:
+ if (rwsem_atomic_update(-RWSEM_ACTIVE_BIAS, sem) & RWSEM_ACTIVE_MASK)
+ goto out;
+ goto try_again_write;
+ undo_read:
if (rwsem_atomic_update(-RWSEM_ACTIVE_BIAS, sem) & RWSEM_ACTIVE_MASK)
goto out;
- goto try_again;
+ goto try_again_read;
}
/*
--
1.7.0.1
next prev parent reply other threads:[~2010-05-24 20:32 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-05-24 20:31 [PATCH 00/11] V4: rwsem changes + down_read_critical() proposal Michel Lespinasse
2010-05-24 20:31 ` [PATCH 01/11] x86 rwsem: stay on fast path when count>0 in __up_write() Michel Lespinasse
2010-05-24 20:31 ` [PATCH 02/11] x86 rwsem: minor cleanups Michel Lespinasse
2010-05-24 20:31 ` Michel Lespinasse [this message]
2010-05-24 20:31 ` [PATCH 04/11] rwsem: lighter active count checks when waking up readers Michel Lespinasse
2010-05-24 20:49 ` Daniel Walker
2010-05-24 20:31 ` [PATCH 05/11] rwsem: let RWSEM_WAITING_BIAS represent any number of waiting threads Michel Lespinasse
2010-05-24 20:31 ` [PATCH 06/11] rwsem: wake queued readers when writer blocks on active read lock Michel Lespinasse
2010-08-12 1:24 ` Tony Luck
2010-08-12 5:02 ` Michel Lespinasse
2010-08-12 5:09 ` Michel Lespinasse
2010-08-12 15:57 ` Linus Torvalds
2010-08-12 16:24 ` Tony Luck
2010-08-12 22:23 ` Tony Luck
2010-08-13 16:09 ` Tony Luck
2010-08-13 21:19 ` Tony Luck
2010-08-13 23:38 ` Tony Luck
2010-08-13 23:48 ` Michel Lespinasse
2010-08-12 16:22 ` Tony Luck
2010-05-24 20:31 ` [PATCH 07/11] rwsem: smaller wrappers around rwsem_down_failed_common Michel Lespinasse
2010-05-24 20:31 ` [PATCH 08/11] generic rwsem: implement down_read_critical() / up_read_critical() Michel Lespinasse
2010-05-24 20:31 ` [PATCH 09/11] rwsem: down_read_critical infrastructure support Michel Lespinasse
2010-05-24 20:31 ` [PATCH 10/11] x86 rwsem: down_read_critical implementation Michel Lespinasse
2010-05-24 20:31 ` [PATCH 11/11] Use down_read_critical() for /proc/<pid>/exe and /proc/<pid>/maps files Michel Lespinasse
2010-05-24 21:12 ` Daniel Walker
2010-05-27 14:12 ` Arjan van de Ven
2010-05-25 8:47 ` [PATCH 00/11] V4: rwsem changes + down_read_critical() proposal Peter Zijlstra
2010-05-25 9:12 ` Michel Lespinasse
2010-05-25 9:27 ` Peter Zijlstra
2010-05-26 1:23 ` KAMEZAWA Hiroyuki
2010-05-27 11:02 ` Michel Lespinasse
2010-05-27 11:45 ` Peter Zijlstra
2010-05-27 10:59 ` Michel Lespinasse
2010-05-27 11:18 ` Peter Zijlstra
2010-05-27 11:47 ` Michel Lespinasse
2010-05-25 15:16 ` Linus Torvalds
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=1274733081-4623-4-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
Powered by JetHome