linux/kernel/locking/osq_lock.c
Pan Xinhui 5aff60a191 locking/osq: Break out of spin-wait busy waiting loop for a preempted vCPU in osq_lock()
An over-committed guest with more vCPUs than pCPUs has a heavy overload
in osq_lock().

This is because if vCPU-A holds the osq lock and yields out, vCPU-B ends
up waiting for per_cpu node->locked to be set. IOW, vCPU-B waits for
vCPU-A to run and unlock the osq lock.

Use the new vcpu_is_preempted(cpu) interface to detect if a vCPU is
currently running or not, and break out of the spin-loop if so.

test case:

 $ perf record -a perf bench sched messaging -g 400 -p && perf report

 before patch:
 18.09%  sched-messaging  [kernel.vmlinux]  [k] osq_lock
 12.28%  sched-messaging  [kernel.vmlinux]  [k] rwsem_spin_on_owner
  5.27%  sched-messaging  [kernel.vmlinux]  [k] mutex_unlock
  3.89%  sched-messaging  [kernel.vmlinux]  [k] wait_consider_task
  3.64%  sched-messaging  [kernel.vmlinux]  [k] _raw_write_lock_irq
  3.41%  sched-messaging  [kernel.vmlinux]  [k] mutex_spin_on_owner.is
  2.49%  sched-messaging  [kernel.vmlinux]  [k] system_call

 after 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

Suggested-by: Boqun Feng <boqun.feng@gmail.com>
Tested-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Pan Xinhui <xinhui.pan@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: David.Laight@ACULAB.COM
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: benh@kernel.crashing.org
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/1478077718-37424-3-git-send-email-xinhui.pan@linux.vnet.ibm.com
[ Translated to English. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-11-22 12:48:10 +01:00

218 lines
5.3 KiB
C

#include <linux/percpu.h>
#include <linux/sched.h>
#include <linux/osq_lock.h>
/*
* An MCS like lock especially tailored for optimistic spinning for sleeping
* lock implementations (mutex, rwsem, etc).
*
* Using a single mcs node per CPU is safe because sleeping locks should not be
* called from interrupt context and we have preemption disabled while
* spinning.
*/
static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_node, osq_node);
/*
* We use the value 0 to represent "no CPU", thus the encoded value
* will be the CPU number incremented by 1.
*/
static inline int encode_cpu(int cpu_nr)
{
return cpu_nr + 1;
}
static inline int node_cpu(struct optimistic_spin_node *node)
{
return node->cpu - 1;
}
static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
{
int cpu_nr = encoded_cpu_val - 1;
return per_cpu_ptr(&osq_node, cpu_nr);
}
/*
* Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
* Can return NULL in case we were the last queued and we updated @lock instead.
*/
static inline struct optimistic_spin_node *
osq_wait_next(struct optimistic_spin_queue *lock,
struct optimistic_spin_node *node,
struct optimistic_spin_node *prev)
{
struct optimistic_spin_node *next = NULL;
int curr = encode_cpu(smp_processor_id());
int old;
/*
* If there is a prev node in queue, then the 'old' value will be
* the prev node's CPU #, else it's set to OSQ_UNLOCKED_VAL since if
* we're currently last in queue, then the queue will then become empty.
*/
old = prev ? prev->cpu : OSQ_UNLOCKED_VAL;
for (;;) {
if (atomic_read(&lock->tail) == curr &&
atomic_cmpxchg_acquire(&lock->tail, curr, old) == curr) {
/*
* We were the last queued, we moved @lock back. @prev
* will now observe @lock and will complete its
* unlock()/unqueue().
*/
break;
}
/*
* We must xchg() the @node->next value, because if we were to
* leave it in, a concurrent unlock()/unqueue() from
* @node->next might complete Step-A and think its @prev is
* still valid.
*
* If the concurrent unlock()/unqueue() wins the race, we'll
* wait for either @lock to point to us, through its Step-B, or
* wait for a new @node->next from its Step-C.
*/
if (node->next) {
next = xchg(&node->next, NULL);
if (next)
break;
}
cpu_relax();
}
return next;
}
bool osq_lock(struct optimistic_spin_queue *lock)
{
struct optimistic_spin_node *node = this_cpu_ptr(&osq_node);
struct optimistic_spin_node *prev, *next;
int curr = encode_cpu(smp_processor_id());
int old;
node->locked = 0;
node->next = NULL;
node->cpu = curr;
/*
* We need both ACQUIRE (pairs with corresponding RELEASE in
* unlock() uncontended, or fastpath) and RELEASE (to publish
* the node fields we just initialised) semantics when updating
* the lock tail.
*/
old = atomic_xchg(&lock->tail, curr);
if (old == OSQ_UNLOCKED_VAL)
return true;
prev = decode_cpu(old);
node->prev = prev;
WRITE_ONCE(prev->next, node);
/*
* Normally @prev is untouchable after the above store; because at that
* moment unlock can proceed and wipe the node element from stack.
*
* However, since our nodes are static per-cpu storage, we're
* guaranteed their existence -- this allows us to apply
* cmpxchg in an attempt to undo our queueing.
*/
while (!READ_ONCE(node->locked)) {
/*
* If we need to reschedule bail... so we can block.
* Use vcpu_is_preempted() to avoid waiting for a preempted
* lock holder:
*/
if (need_resched() || vcpu_is_preempted(node_cpu(node->prev)))
goto unqueue;
cpu_relax();
}
return true;
unqueue:
/*
* Step - A -- stabilize @prev
*
* Undo our @prev->next assignment; this will make @prev's
* unlock()/unqueue() wait for a next pointer since @lock points to us
* (or later).
*/
for (;;) {
if (prev->next == node &&
cmpxchg(&prev->next, node, NULL) == node)
break;
/*
* We can only fail the cmpxchg() racing against an unlock(),
* in which case we should observe @node->locked becomming
* true.
*/
if (smp_load_acquire(&node->locked))
return true;
cpu_relax();
/*
* Or we race against a concurrent unqueue()'s step-B, in which
* case its step-C will write us a new @node->prev pointer.
*/
prev = READ_ONCE(node->prev);
}
/*
* Step - B -- stabilize @next
*
* Similar to unlock(), wait for @node->next or move @lock from @node
* back to @prev.
*/
next = osq_wait_next(lock, node, prev);
if (!next)
return false;
/*
* Step - C -- unlink
*
* @prev is stable because its still waiting for a new @prev->next
* pointer, @next is stable because our @node->next pointer is NULL and
* it will wait in Step-A.
*/
WRITE_ONCE(next->prev, prev);
WRITE_ONCE(prev->next, next);
return false;
}
void osq_unlock(struct optimistic_spin_queue *lock)
{
struct optimistic_spin_node *node, *next;
int curr = encode_cpu(smp_processor_id());
/*
* Fast path for the uncontended case.
*/
if (likely(atomic_cmpxchg_release(&lock->tail, curr,
OSQ_UNLOCKED_VAL) == curr))
return;
/*
* Second most likely case.
*/
node = this_cpu_ptr(&osq_node);
next = xchg(&node->next, NULL);
if (next) {
WRITE_ONCE(next->locked, 1);
return;
}
next = osq_wait_next(lock, node, NULL);
if (next)
WRITE_ONCE(next->locked, 1);
}