@@ -236,7 +236,13 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
*/
barrier();
- if (!owner->on_cpu || need_resched()) {
+ /*
+ * 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 (!owner->on_cpu || need_resched() ||
+ vcpu_is_preempted(task_cpu(owner))) {
ret = false;
break;
}
@@ -261,8 +267,13 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
rcu_read_lock();
owner = READ_ONCE(lock->owner);
+
+ /*
+ * 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();
/*
* if lock->owner is not set, the mutex owner may have just acquired
@@ -319,7 +319,11 @@ 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;
@@ -340,8 +344,14 @@ bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner)
*/
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. vcpu_is_preempted is a macro
+ * defined by false if arch does not support vcpu preempted
+ * check
+ */
+ if (!owner->on_cpu || need_resched() ||
+ vcpu_is_preempted(task_cpu(owner))) {
rcu_read_unlock();
return false;
}
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. 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 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 Signed-off-by: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com> --- kernel/locking/mutex.c | 15 +++++++++++++-- kernel/locking/rwsem-xadd.c | 16 +++++++++++++--- 2 files changed, 26 insertions(+), 5 deletions(-)