linux-kernel - [PATCH 02/10] rwsem: fully separate code pathes to wake writers vs readers

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Mon, 17 May 2010 15:25:46 -0700
From:	Michel Lespinasse <walken@...gle.com>
To:	Linus Torvalds <torvalds@...ux-foundation.org>,
	David Howells <dhowells@...hat.com>,
	Ingo Molnar <mingo@...e.hu>,
	Thomas Gleixner <tglx@...utronix.de>
Cc:	LKML <linux-kernel@...r.kernel.org>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Mike Waychison <mikew@...gle.com>,
	Suleiman Souhlal <suleiman@...gle.com>,
	Ying Han <yinghan@...gle.com>,
	Michel Lespinasse <walken@...gle.com>
Subject: [PATCH 02/10] rwsem: fully separate code pathes to wake writers vs readers

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 incremetns 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@...gle.com>
---
 lib/rwsem.c |   54 +++++++++++++++++++++++++++++++-----------------------
 1 files changed, 31 insertions(+), 23 deletions(-)

diff --git a/lib/rwsem.c b/lib/rwsem.c
index ceba8e2..874c0c1 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
@@ -54,27 +54,24 @@ __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:
 	oldcount = rwsem_atomic_update(RWSEM_ACTIVE_BIAS, sem)
 						- RWSEM_ACTIVE_BIAS;
 	if (oldcount & RWSEM_ACTIVE_MASK)
+		/* Someone grabbed the sem already */
 		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;
-
 	/* 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
 	 * any time after that point (due to a wakeup from another source).
@@ -87,18 +84,25 @@ __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) {
+
+		/* 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
+	/* 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++;
@@ -142,6 +146,10 @@ __rwsem_do_wake(struct rw_semaphore *sem, int downgrading)
 	if (rwsem_atomic_update(-RWSEM_ACTIVE_BIAS, sem) & RWSEM_ACTIVE_MASK)
 		goto out;
 	goto try_again;
+ undo_read:
+	if (rwsem_atomic_update(-RWSEM_ACTIVE_BIAS, sem) & RWSEM_ACTIVE_MASK)
+		goto out;
+	goto try_again_read;
 }
 
 /*
-- 
1.7.0.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/