public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: npiggin@suse.de
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Manfred Spraul <manfred@colorfullife.com>,
	Nadia Derbey <Nadia.Derbey@bull.net>,
	Pierre Peiffer <peifferp@gmail.com>,
	linux-kernel@vger.kernel.org
Subject: [patch 2/4] ipc: sem use list operations
Date: Tue, 11 Aug 2009 21:09:04 +1000	[thread overview]
Message-ID: <20090811111606.997443191@suse.de> (raw)
In-Reply-To: 20090811110902.255877673@suse.de

[-- Attachment #1: ipc-sem-use-list-ops.patch --]
[-- Type: text/plain, Size: 2838 bytes --]

Signed-off-by: Nick Piggin <npiggin@suse.de>
---
 ipc/sem.c |   79 +++++++++++++++++++++++++-------------------------------------
 1 file changed, 33 insertions(+), 46 deletions(-)

Index: linux-2.6/ipc/sem.c
===================================================================
--- linux-2.6.orig/ipc/sem.c
+++ linux-2.6/ipc/sem.c
@@ -402,58 +402,45 @@ undo:
  */
 static void update_queue (struct sem_array * sma)
 {
-	int error;
-	struct sem_queue * q;
+	struct sem_queue *q, *tq;
+
+again:
+	list_for_each_entry_safe(q, tq, &sma->sem_pending, list) {
+		int error;
+		int alter;
 
-	q = list_entry(sma->sem_pending.next, struct sem_queue, list);
-	while (&q->list != &sma->sem_pending) {
 		error = try_atomic_semop(sma, q->sops, q->nsops,
 					 q->undo, q->pid);
 
 		/* Does q->sleeper still need to sleep? */
-		if (error <= 0) {
-			struct sem_queue *n;
+		if (error > 0)
+			continue;
+
+		list_del(&q->list);
+
+		/*
+		 * The next operation that must be checked depends on the type
+		 * of the completed operation:
+		 * - if the operation modified the array, then restart from the
+		 *   head of the queue and check for threads that might be
+		 *   waiting for semaphore values to become 0.
+		 * - if the operation didn't modify the array, then just
+		 *   continue.
+		 */
+		alter = q->alter;
+
+		/* wake up the waiting thread */
+		q->status = IN_WAKEUP;
+
+		wake_up_process(q->sleeper);
+		/* hands-off: q will disappear immediately after
+		 * writing q->status.
+		 */
+		smp_wmb();
+		q->status = error;
 
-			/*
-			 * Continue scanning. The next operation
-			 * that must be checked depends on the type of the
-			 * completed operation:
-			 * - if the operation modified the array, then
-			 *   restart from the head of the queue and
-			 *   check for threads that might be waiting
-			 *   for semaphore values to become 0.
-			 * - if the operation didn't modify the array,
-			 *   then just continue.
-			 * The order of list_del() and reading ->next
-			 * is crucial: In the former case, the list_del()
-			 * must be done first [because we might be the
-			 * first entry in ->sem_pending], in the latter
-			 * case the list_del() must be done last
-			 * [because the list is invalid after the list_del()]
-			 */
-			if (q->alter) {
-				list_del(&q->list);
-				n = list_entry(sma->sem_pending.next,
-						struct sem_queue, list);
-			} else {
-				n = list_entry(q->list.next, struct sem_queue,
-						list);
-				list_del(&q->list);
-			}
-
-			/* wake up the waiting thread */
-			q->status = IN_WAKEUP;
-
-			wake_up_process(q->sleeper);
-			/* hands-off: q will disappear immediately after
-			 * writing q->status.
-			 */
-			smp_wmb();
-			q->status = error;
-			q = n;
-		} else {
-			q = list_entry(q->list.next, struct sem_queue, list);
-		}
+		if (alter)
+			goto again;
 	}
 }
 



  parent reply	other threads:[~2009-08-11 11:54 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-08-11 11:09 [patch 0/4] ipc sem improvements npiggin
2009-08-11 11:09 ` [patch 1/4] ipc: sem optimise undo list search npiggin
2009-08-16 13:17   ` Manfred Spraul
2009-08-11 11:09 ` npiggin [this message]
2009-08-16 13:18   ` [patch 2/4] ipc: sem use list operations Manfred Spraul
2009-08-11 11:09 ` [patch 3/4] ipc: sem preempt improve npiggin
2009-08-16 13:20   ` Manfred Spraul
2009-08-11 11:09 ` [patch 4/4] ipc: sem optimise simple operations npiggin
2009-08-11 18:19   ` Manfred Spraul
2009-08-11 18:23     ` Zach Brown
2009-08-12  4:07       ` Nick Piggin
2009-08-12 18:35         ` Manfred Spraul
2009-08-14  8:58           ` Nick Piggin
2009-08-14 17:53             ` Manfred Spraul
2009-08-11 20:07   ` Cyrill Gorcunov
2009-08-12  4:48     ` Nick Piggin
2009-08-12  5:43       ` Cyrill Gorcunov
2009-08-14 18:48   ` Manfred Spraul

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=20090811111606.997443191@suse.de \
    --to=npiggin@suse.de \
    --cc=Nadia.Derbey@bull.net \
    --cc=akpm@linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=manfred@colorfullife.com \
    --cc=peifferp@gmail.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