The patch titled
rwsem: fully separate code paths to wake writers vs readers
has been added to the -mm tree. Its filename is
rwsem-fully-separate-code-pathes-to-wake-writers-vs-readers.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: rwsem: fully separate code paths to wake writers vs readers
From: Michel Lespinasse <walken@xxxxxxxxxx>
This is in preparation for 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@xxxxxxxxxx>
Cc: David Howells <dhowells@xxxxxxxxxx>
Cc: Mike Waychison <mikew@xxxxxxxxxx>
Cc: Suleiman Souhlal <suleiman@xxxxxxxxxx>
Cc: Ying Han <yinghan@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
lib/rwsem.c | 61 +++++++++++++++++++++++++++-----------------------
1 file changed, 34 insertions(+), 27 deletions(-)
diff -puN lib/rwsem.c~rwsem-fully-separate-code-pathes-to-wake-writers-vs-readers lib/rwsem.c
--- a/lib/rwsem.c~rwsem-fully-separate-code-pathes-to-wake-writers-vs-readers
+++ a/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
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
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
/* 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;
}
/*
_
Patches currently in -mm which might be from walken@xxxxxxxxxx are
x86-rwsem-stay-on-fast-path-when-count0-in-__up_write.patch
x86-rwsem-minor-cleanups.patch
rwsem-fully-separate-code-pathes-to-wake-writers-vs-readers.patch
rwsem-lighter-active-count-checks-when-waking-up-readers.patch
rwsem-let-rwsem_waiting_bias-represent-any-number-of-waiting-threads.patch
rwsem-wake-queued-readers-when-writer-blocks-on-active-read-lock.patch
rwsem-smaller-wrappers-around-rwsem_down_failed_common.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
