linux-kernel - [PATCH v5 6/6] locking/rwsem: Update handoff lock events tracking

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:   Thu,  3 Nov 2022 14:29:36 -0400
From:   Waiman Long <longman@...hat.com>
To:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...hat.com>, Will Deacon <will@...nel.org>,
        Boqun Feng <boqun.feng@...il.com>
Cc:     linux-kernel@...r.kernel.org, john.p.donnelly@...cle.com,
        Hillf Danton <hdanton@...a.com>,
        Mukesh Ojha <quic_mojha@...cinc.com>,
        Ting11 Wang 王婷 
        <wangting11@...omi.com>, Waiman Long <longman@...hat.com>
Subject: [PATCH v5 6/6] locking/rwsem: Update handoff lock events tracking

With the new direct rwsem lock handoff, the corresponding handoff lock
events are updated to also track the number of secondary lock handoffs
in rwsem_down_read_slowpath() to see how prevalent those handoff
events are. The number of primary lock handoffs in the unlock paths is
(rwsem_handoff_read + rwsem_handoff_write - rwsem_handoff_rslow).

After running a 96-thread rwsem microbenchmark with equal number
of readers and writers on a 2-socket 96-thread system for 40s, the
following handoff stats were obtained:

  rwsem_handoff_read=189
  rwsem_handoff_rslow=1
  rwsem_handoff_write=6678
  rwsem_handoff_wspin=6681

The number of primary handoffs was 6866, whereas there was only one
secondary handoff for this test run.

Signed-off-by: Waiman Long <longman@...hat.com>
---
 kernel/locking/lock_events_list.h | 6 ++++--
 kernel/locking/rwsem.c            | 9 +++++----
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/kernel/locking/lock_events_list.h b/kernel/locking/lock_events_list.h
index 97fb6f3f840a..04d101767c2c 100644
--- a/kernel/locking/lock_events_list.h
+++ b/kernel/locking/lock_events_list.h
@@ -63,7 +63,9 @@ LOCK_EVENT(rwsem_rlock)		/* # of read locks acquired		*/
 LOCK_EVENT(rwsem_rlock_steal)	/* # of read locks by lock stealing	*/
 LOCK_EVENT(rwsem_rlock_fast)	/* # of fast read locks acquired	*/
 LOCK_EVENT(rwsem_rlock_fail)	/* # of failed read lock acquisitions	*/
-LOCK_EVENT(rwsem_rlock_handoff)	/* # of read lock handoffs		*/
 LOCK_EVENT(rwsem_wlock)		/* # of write locks acquired		*/
 LOCK_EVENT(rwsem_wlock_fail)	/* # of failed write lock acquisitions	*/
-LOCK_EVENT(rwsem_wlock_handoff)	/* # of write lock handoffs		*/
+LOCK_EVENT(rwsem_handoff_read)	/* # of read lock handoffs		*/
+LOCK_EVENT(rwsem_handoff_write)	/* # of write lock handoffs		*/
+LOCK_EVENT(rwsem_handoff_rslow)	/* # of handoffs in read slowpath	*/
+LOCK_EVENT(rwsem_handoff_wspin)	/* # of handoff spins in write slowpath	*/
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index c9f24ed8757d..84bdb4fd18c3 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -469,10 +469,8 @@ static void rwsem_mark_wake(struct rw_semaphore *sem,
 			 * force the issue.
 			 */
 			if (time_after(jiffies, waiter->timeout)) {
-				if (!(oldcount & RWSEM_FLAG_HANDOFF)) {
+				if (!(oldcount & RWSEM_FLAG_HANDOFF))
 					adjustment -= RWSEM_FLAG_HANDOFF;
-					lockevent_inc(rwsem_rlock_handoff);
-				}
 				WRITE_ONCE(waiter->handoff_state, HANDOFF_REQUESTED);
 			}
 
@@ -677,7 +675,6 @@ static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
 	 */
 	if (new & RWSEM_FLAG_HANDOFF) {
 		WRITE_ONCE(first->handoff_state, HANDOFF_REQUESTED);
-		lockevent_inc(rwsem_wlock_handoff);
 		return false;
 	}
 
@@ -1011,10 +1008,12 @@ static void rwsem_handoff(struct rw_semaphore *sem, long adj,
 		wake_type = RWSEM_WAKE_ANY;
 		adj += RWSEM_WRITER_LOCKED;
 		atomic_long_set(&sem->owner, (long)waiter->task);
+		lockevent_inc(rwsem_handoff_write);
 	} else {
 		wake_type = RWSEM_WAKE_READ_OWNED;
 		adj += RWSEM_READER_BIAS;
 		__rwsem_set_reader_owned(sem, waiter->task);
+		lockevent_inc(rwsem_handoff_read);
 	}
 	atomic_long_add(adj, &sem->count);
 	rwsem_mark_wake(sem, wake_type, wake_q);
@@ -1123,6 +1122,7 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int stat
 		if (rwsem_first_waiter(sem)->type == RWSEM_WAITING_FOR_READ)
 			adjustment = 0;
 		rwsem_handoff(sem, adjustment, &wake_q);
+		lockevent_inc(rwsem_handoff_rslow);
 
 		if (!adjustment) {
 			raw_spin_unlock_irq(&sem->wait_lock);
@@ -1253,6 +1253,7 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 			if (handoff == HANDOFF_REQUESTED) {
 				rwsem_spin_on_owner(sem);
 				handoff = READ_ONCE(waiter.handoff_state);
+				lockevent_inc(rwsem_handoff_wspin);
 			}
 
 			if (handoff == HANDOFF_GRANTED)
-- 
2.31.1