[tip:locking/core] locking/mutex: Break out of expensive busy-loop on {mutex,rwsem}_spin_on_owner() when owner vCPU is preempted

[tip-bot for Pan Xinhui]

Commit-ID:  05ffc951392df57edecc2519327b169210c3df75
Gitweb:     http://git.kernel.org/tip/05ffc951392df57edecc2519327b169210c3df75
Author:     Pan Xinhui <xinhui.pan@xxxxxxxxxxxxxxxxxx>
AuthorDate: Wed, 2 Nov 2016 05:08:30 -0400
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Tue, 22 Nov 2016 12:48:10 +0100

locking/mutex: Break out of expensive busy-loop on {mutex,rwsem}_spin_on_owner() when owner vCPU is preempted

An over-committed guest with more vCPUs than pCPUs has a heavy overload
in the two spin_on_owner. This blames on the lock holder preemption
issue.

Break out of the loop if the vCPU is preempted: if vcpu_is_preempted(cpu)
is true.

test-case:
perf record -a perf bench sched messaging -g 400 -p && perf report

before patch:
20.68%  sched-messaging  [kernel.vmlinux]  [k] mutex_spin_on_owner
 8.45%  sched-messaging  [kernel.vmlinux]  [k] mutex_unlock
 4.12%  sched-messaging  [kernel.vmlinux]  [k] system_call
 3.01%  sched-messaging  [kernel.vmlinux]  [k] system_call_common
 2.83%  sched-messaging  [kernel.vmlinux]  [k] copypage_power7
 2.64%  sched-messaging  [kernel.vmlinux]  [k] rwsem_spin_on_owner
 2.00%  sched-messaging  [kernel.vmlinux]  [k] osq_lock

after patch:
 9.99%  sched-messaging  [kernel.vmlinux]  [k] mutex_unlock
 5.28%  sched-messaging  [unknown]         [H] 0xc0000000000768e0
 4.27%  sched-messaging  [kernel.vmlinux]  [k] __copy_tofrom_user_power7
 3.77%  sched-messaging  [kernel.vmlinux]  [k] copypage_power7
 3.24%  sched-messaging  [kernel.vmlinux]  [k] _raw_write_lock_irq
 3.02%  sched-messaging  [kernel.vmlinux]  [k] system_call
 2.69%  sched-messaging  [kernel.vmlinux]  [k] wait_consider_task

Tested-by: Juergen Gross <jgross@xxxxxxxx>
Signed-off-by: Pan Xinhui <xinhui.pan@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Acked-by: Christian Borntraeger <borntraeger@xxxxxxxxxx>
Acked-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: David.Laight@xxxxxxxxxx
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: benh@xxxxxxxxxxxxxxxxxxx
Cc: boqun.feng@xxxxxxxxx
Cc: bsingharora@xxxxxxxxx
Cc: dave@xxxxxxxxxxxx
Cc: kernellwp@xxxxxxxxx
Cc: konrad.wilk@xxxxxxxxxx
Cc: linuxppc-dev@xxxxxxxxxxxxxxxx
Cc: mpe@xxxxxxxxxxxxxx
Cc: paulmck@xxxxxxxxxxxxxxxxxx
Cc: paulus@xxxxxxxxx
Cc: rkrcmar@xxxxxxxxxx
Cc: virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx
Cc: will.deacon@xxxxxxx
Cc: xen-devel-request@xxxxxxxxxxxxxxxxxxxx
Cc: xen-devel@xxxxxxxxxxxxxxxxxxxx
Link: http://lkml.kernel.org/r/1478077718-37424-4-git-send-email-xinhui.pan@xxxxxxxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 kernel/locking/mutex.c      | 13 +++++++++++--
 kernel/locking/rwsem-xadd.c | 14 +++++++++++---
 2 files changed, 22 insertions(+), 5 deletions(-)

diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index c073168..9b34961 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -364,7 +364,11 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
 		 */
 		barrier();
 
-		if (!owner->on_cpu || need_resched()) {
+		/*
+		 * Use vcpu_is_preempted to detect lock holder preemption issue.
+		 */
+		if (!owner->on_cpu || need_resched() ||
+				vcpu_is_preempted(task_cpu(owner))) {
 			ret = false;
 			break;
 		}
@@ -389,8 +393,13 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
 
 	rcu_read_lock();
 	owner = __mutex_owner(lock);
+
+	/*
+	 * As lock holder preemption issue, we both skip spinning if task is not
+	 * on cpu or its cpu is preempted
+	 */
 	if (owner)
-		retval = owner->on_cpu;
+		retval = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
 	rcu_read_unlock();
 
 	/*
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 263e744..6315060 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -336,7 +336,11 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 		goto done;
 	}
 
-	ret = owner->on_cpu;
+	/*
+	 * As lock holder preemption issue, we both skip spinning if task is not
+	 * on cpu or its cpu is preempted
+	 */
+	ret = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
 done:
 	rcu_read_unlock();
 	return ret;
@@ -362,8 +366,12 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
 		 */
 		barrier();
 
-		/* abort spinning when need_resched or owner is not running */
-		if (!owner->on_cpu || need_resched()) {
+		/*
+		 * abort spinning when need_resched or owner is not running or
+		 * owner's cpu is preempted.
+		 */
+		if (!owner->on_cpu || need_resched() ||
+				vcpu_is_preempted(task_cpu(owner))) {
 			rcu_read_unlock();
 			return false;
 		}