--- v7
+++ v5
@@ -1,13 +1,12 @@
-An over-committed guest with more vCPUs than pCPUs has a heavy overload
-in osq_lock().
+An over-committed guest with more vCPUs than pCPUs has a heavy overload in
+osq_lock().
-This is because vCPU A hold the osq lock and yield out, vCPU B wait
-per_cpu node->locked to be set. IOW, vCPU B wait vCPU A to run and
-unlock the osq lock.
+This is because vCPU A hold the osq lock and yield out, vCPU B wait per_cpu
+node->locked to be set. IOW, vCPU B wait vCPU A to run and unlock the osq
+lock.
-Kernel has an interface bool vcpu_is_preempted(int cpu) to detect if a
-vCPU is currently running or not. So break the spin loops on true
-condition.
+Kernel has an interface bool vcpu_is_preempted(int cpu) to see if a vCPU is
+currently running or not. So break the spin loops on true condition.
test case:
perf record -a perf bench sched messaging -g 400 -p && perf report
@@ -33,14 +32,13 @@
Suggested-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
-Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Juergen Gross <jgross@suse.com>
---
- kernel/locking/osq_lock.c | 8 +++++++-
- 1 file changed, 7 insertions(+), 1 deletion(-)
+ kernel/locking/osq_lock.c | 10 +++++++++-
+ 1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
-index 05a3785..091f97f 100644
+index 05a3785..39d1385 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -21,6 +21,11 @@ static inline int encode_cpu(int cpu_nr)
@@ -55,11 +53,13 @@
static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
{
int cpu_nr = encoded_cpu_val - 1;
-@@ -118,8 +123,9 @@ bool osq_lock(struct optimistic_spin_queue *lock)
+@@ -118,8 +123,11 @@ bool osq_lock(struct optimistic_spin_queue *lock)
while (!READ_ONCE(node->locked)) {
/*
* If we need to reschedule bail... so we can block.
-+ * Use vcpu_is_preempted to detect lock holder preemption issue.
++ * Use vcpu_is_preempted to detech lock holder preemption issue
++ * and break. vcpu_is_preempted is a macro defined by false if
++ * arch does not support vcpu preempted check,
*/
- if (need_resched())
+ if (need_resched() || vcpu_is_preempted(node_cpu(node->prev)))