| 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
| ||
|
Message-Id: <1463165787-25937-2-git-send-email-dave@stgolabs.net>
Date: Fri, 13 May 2016 11:56:26 -0700
From: Davidlohr Bueso <dave@...olabs.net>
To: mingo@...nel.org, peterz@...radead.org, tglx@...utronix.de
Cc: Waiman.Long@....com, jason.low2@...com, peter@...leysoftware.com,
dave@...olabs.net, linux-kernel@...r.kernel.org,
Davidlohr Bueso <dbueso@...e.de>
Subject: [PATCH 1/2] locking/rwsem: Enable lockless waiter wakeup(s)
As wake_qs gain users, we can teach rwsems about them such that
waiters can be awoken without the wait_lock. This is for both
readers and writer, the former being the most ideal candidate
as we can batch the wakeups shortening the critical region that
much more -- ie writer task blocking a bunch of tasks waiting to
service page-faults (mmap_sem readers).
In general applying wake_qs to rwsem (xadd) is not difficult as
the wait_lock is intended to be released soon _anyways_, with
the exception of when a writer slowpath will proactively wakeup
any queued readers if it sees that the lock is owned by a reader,
in which we simply do the wakeups with the lock held (see comment
in __rwsem_down_write_failed_common()).
Similar to other locking primitives, delaying the waiter being
awoken does allow, at least in theory, the lock to be stolen in
the case of writers, however no harm was seen in this (in fact
lock stealing tends to be a _good_ thing in most workloads), and
this is a tiny window anyways.
Some page-fault (pft) and mmap_sem intensive benchmarks show some
pretty constant reduction in systime (by up to ~8 and ~10%) on a
2-socket, 12 core AMD box. In addition, on an 8-core Westmere doing
page allocations (page_test)
aim9
4.6-rc6 4.6-rc6
rwsemv2
Min page_test 378167.89 ( 0.00%) 382613.33 ( 1.18%)
Min exec_test 499.00 ( 0.00%) 502.67 ( 0.74%)
Min fork_test 3395.47 ( 0.00%) 3537.64 ( 4.19%)
Hmean page_test 395433.06 ( 0.00%) 414693.68 ( 4.87%)
Hmean exec_test 499.67 ( 0.00%) 505.30 ( 1.13%)
Hmean fork_test 3504.22 ( 0.00%) 3594.95 ( 2.59%)
Stddev page_test 17426.57 ( 0.00%) 26649.92 (-52.93%)
Stddev exec_test 0.47 ( 0.00%) 1.41 (-199.05%)
Stddev fork_test 63.74 ( 0.00%) 32.59 ( 48.86%)
Max page_test 429873.33 ( 0.00%) 456960.00 ( 6.30%)
Max exec_test 500.33 ( 0.00%) 507.66 ( 1.47%)
Max fork_test 3653.33 ( 0.00%) 3650.90 ( -0.07%)
4.6-rc6 4.6-rc6
rwsemv2
User 1.12 0.04
System 0.23 0.04
Elapsed 727.27 721.98
Signed-off-by: Davidlohr Bueso <dbueso@...e.de>
---
kernel/locking/rwsem-xadd.c | 58 ++++++++++++++++++++++++++++++++-------------
1 file changed, 42 insertions(+), 16 deletions(-)
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 09e30c6225e5..80b05ac0f015 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -114,12 +114,16 @@ enum rwsem_wake_type {
* - 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
- * - the spinlock must be held by the caller
+ * - the wait_lock must be held by the caller
+ * - tasks are marked for wakeup, the caller must later invoke wake_up_q()
+ * to actually wakeup the blocked task(s) and drop the reference count,
+ * preferably when the wait_lock is released
* - woken process blocks are discarded from the list after having task zeroed
- * - writers are only woken if downgrading is false
+ * - writers are only marked woken if downgrading is false
*/
static struct rw_semaphore *
-__rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
+__rwsem_mark_wake(struct rw_semaphore *sem,
+ enum rwsem_wake_type wake_type, struct wake_q_head *wake_q)
{
struct rwsem_waiter *waiter;
struct task_struct *tsk;
@@ -128,13 +132,16 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
- if (wake_type == RWSEM_WAKE_ANY)
- /* Wake writer at the front of the queue, but do not
- * grant it the lock yet as we want other writers
- * to be able to steal it. Readers, on the other hand,
- * will block as they will notice the queued writer.
+ if (wake_type == RWSEM_WAKE_ANY) {
+ /*
+ * Mark writer at the front of the queue for wakeup.
+ * Until the task is actually later awoken later by
+ * the caller, other writers are able to steal it.
+ * Readers, on the other hand, will block as they
+ * will notice the queued writer.
*/
- wake_up_process(waiter->task);
+ wake_q_add(wake_q, waiter->task);
+ }
goto out;
}
@@ -196,7 +203,7 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
*/
smp_mb();
waiter->task = NULL;
- wake_up_process(tsk);
+ wake_q_add(wake_q, tsk);
put_task_struct(tsk);
} while (--loop);
@@ -216,6 +223,7 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
struct rwsem_waiter waiter;
struct task_struct *tsk = current;
+ WAKE_Q(wake_q);
/* set up my own style of waitqueue */
waiter.task = tsk;
@@ -238,9 +246,10 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
if (count == RWSEM_WAITING_BIAS ||
(count > RWSEM_WAITING_BIAS &&
adjustment != -RWSEM_ACTIVE_READ_BIAS))
- sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+ sem = __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
raw_spin_unlock_irq(&sem->wait_lock);
+ wake_up_q(&wake_q);
/* wait to be given the lock */
while (true) {
@@ -440,6 +449,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
bool waiting = true; /* any queued threads before us */
struct rwsem_waiter waiter;
struct rw_semaphore *ret = sem;
+ WAKE_Q(wake_q);
/* undo write bias from down_write operation, stop active locking */
count = rwsem_atomic_update(-RWSEM_ACTIVE_WRITE_BIAS, sem);
@@ -472,8 +482,19 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
* no active writers, the lock must be read owned; so we try to
* wake any read locks that were queued ahead of us.
*/
- if (count > RWSEM_WAITING_BIAS)
- sem = __rwsem_do_wake(sem, RWSEM_WAKE_READERS);
+ if (count > RWSEM_WAITING_BIAS) {
+ WAKE_Q(wake_q);
+
+ sem = __rwsem_mark_wake(sem, RWSEM_WAKE_READERS, &wake_q);
+ /*
+ * The wakeup is normally called _after_ the wait_lock
+ * is released, but given that we are proactively waking
+ * readers we can deal with the wake_q overhead as it is
+ * similar to releasing and taking the wait_lock again
+ * for attempting rwsem_try_write_lock().
+ */
+ wake_up_q(&wake_q);
+ }
} else
count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
@@ -509,8 +530,9 @@ out_nolock:
if (list_empty(&sem->wait_list))
rwsem_atomic_update(-RWSEM_WAITING_BIAS, sem);
else
- __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+ __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
raw_spin_unlock_irq(&sem->wait_lock);
+ wake_up_q(&wake_q);
return ERR_PTR(-EINTR);
}
@@ -537,6 +559,7 @@ __visible
struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
{
unsigned long flags;
+ WAKE_Q(wake_q);
/*
* If a spinner is present, it is not necessary to do the wakeup.
@@ -573,9 +596,10 @@ locked:
/* do nothing if list empty */
if (!list_empty(&sem->wait_list))
- sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
+ sem = __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+ wake_up_q(&wake_q);
return sem;
}
@@ -590,14 +614,16 @@ __visible
struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
{
unsigned long flags;
+ WAKE_Q(wake_q);
raw_spin_lock_irqsave(&sem->wait_lock, flags);
/* do nothing if list empty */
if (!list_empty(&sem->wait_list))
- sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED);
+ sem = __rwsem_mark_wake(sem, RWSEM_WAKE_READ_OWNED, &wake_q);
raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+ wake_up_q(&wake_q);
return sem;
}
--
2.8.1
Powered by blists - more mailing lists