From 05ffc951392df57edecc2519327b169210c3df75 Mon Sep 17 00:00:00 2001 From: Pan Xinhui Date: Wed, 2 Nov 2016 05:08:30 -0400 Subject: [PATCH] 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 Signed-off-by: Pan Xinhui Signed-off-by: Peter Zijlstra (Intel) Acked-by: Christian Borntraeger Acked-by: Paolo Bonzini Cc: David.Laight@ACULAB.COM Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: benh@kernel.crashing.org Cc: boqun.feng@gmail.com Cc: bsingharora@gmail.com Cc: dave@stgolabs.net Cc: kernellwp@gmail.com Cc: konrad.wilk@oracle.com Cc: linuxppc-dev@lists.ozlabs.org Cc: mpe@ellerman.id.au Cc: paulmck@linux.vnet.ibm.com Cc: paulus@samba.org Cc: rkrcmar@redhat.com Cc: virtualization@lists.linux-foundation.org Cc: will.deacon@arm.com Cc: xen-devel-request@lists.xenproject.org Cc: xen-devel@lists.xenproject.org Link: http://lkml.kernel.org/r/1478077718-37424-4-git-send-email-xinhui.pan@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- 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 c0731685603f..9b349619f431 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 263e7449282a..631506004f9e 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; } -- 2.20.1