summaryrefslogtreecommitdiff
path: root/kernel/locking/qspinlock_paravirt.h
diff options
context:
space:
mode:
authorWaiman Long <Waiman.Long@hpe.com>2015-11-10 16:18:56 -0500
committerIngo Molnar <mingo@kernel.org>2015-12-04 11:39:51 +0100
commit1c4941fd53afb46ab15826628e4819866d008a28 (patch)
treeeaf0f35a79725bf10476a90634245824a7ccb8c3 /kernel/locking/qspinlock_paravirt.h
parent45e898b735620f426eddf105fc886d2966593a58 (diff)
locking/pvqspinlock: Allow limited lock stealing
This patch allows one attempt for the lock waiter to steal the lock when entering the PV slowpath. To prevent lock starvation, the pending bit will be set by the queue head vCPU when it is in the active lock spinning loop to disable any lock stealing attempt. This helps to reduce the performance penalty caused by lock waiter preemption while not having much of the downsides of a real unfair lock. The pv_wait_head() function was renamed as pv_wait_head_or_lock() as it was modified to acquire the lock before returning. This is necessary because of possible lock stealing attempts from other tasks. Linux kernel builds were run in KVM guest on an 8-socket, 4 cores/socket Westmere-EX system and a 4-socket, 8 cores/socket Haswell-EX system. Both systems are configured to have 32 physical CPUs. The kernel build times before and after the patch were: Westmere Haswell Patch 32 vCPUs 48 vCPUs 32 vCPUs 48 vCPUs ----- -------- -------- -------- -------- Before patch 3m15.6s 10m56.1s 1m44.1s 5m29.1s After patch 3m02.3s 5m00.2s 1m43.7s 3m03.5s For the overcommited case (48 vCPUs), this patch is able to reduce kernel build time by more than 54% for Westmere and 44% for Haswell. Signed-off-by: Waiman Long <Waiman.Long@hpe.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Douglas Hatch <doug.hatch@hpe.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hpe.com> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1447190336-53317-1-git-send-email-Waiman.Long@hpe.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/locking/qspinlock_paravirt.h')
-rw-r--r--kernel/locking/qspinlock_paravirt.h141
1 files changed, 119 insertions, 22 deletions
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index aaeeefb791f8..ace60a451b4f 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -41,6 +41,89 @@ struct pv_node {
};
/*
+ * By replacing the regular queued_spin_trylock() with the function below,
+ * it will be called once when a lock waiter enter the PV slowpath before
+ * being queued. By allowing one lock stealing attempt here when the pending
+ * bit is off, it helps to reduce the performance impact of lock waiter
+ * preemption without the drawback of lock starvation.
+ */
+#define queued_spin_trylock(l) pv_queued_spin_steal_lock(l)
+static inline bool pv_queued_spin_steal_lock(struct qspinlock *lock)
+{
+ struct __qspinlock *l = (void *)lock;
+
+ return !(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) &&
+ (cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0);
+}
+
+/*
+ * The pending bit is used by the queue head vCPU to indicate that it
+ * is actively spinning on the lock and no lock stealing is allowed.
+ */
+#if _Q_PENDING_BITS == 8
+static __always_inline void set_pending(struct qspinlock *lock)
+{
+ struct __qspinlock *l = (void *)lock;
+
+ WRITE_ONCE(l->pending, 1);
+}
+
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+ struct __qspinlock *l = (void *)lock;
+
+ WRITE_ONCE(l->pending, 0);
+}
+
+/*
+ * The pending bit check in pv_queued_spin_steal_lock() isn't a memory
+ * barrier. Therefore, an atomic cmpxchg() is used to acquire the lock
+ * just to be sure that it will get it.
+ */
+static __always_inline int trylock_clear_pending(struct qspinlock *lock)
+{
+ struct __qspinlock *l = (void *)lock;
+
+ return !READ_ONCE(l->locked) &&
+ (cmpxchg(&l->locked_pending, _Q_PENDING_VAL, _Q_LOCKED_VAL)
+ == _Q_PENDING_VAL);
+}
+#else /* _Q_PENDING_BITS == 8 */
+static __always_inline void set_pending(struct qspinlock *lock)
+{
+ atomic_set_mask(_Q_PENDING_VAL, &lock->val);
+}
+
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+ atomic_clear_mask(_Q_PENDING_VAL, &lock->val);
+}
+
+static __always_inline int trylock_clear_pending(struct qspinlock *lock)
+{
+ int val = atomic_read(&lock->val);
+
+ for (;;) {
+ int old, new;
+
+ if (val & _Q_LOCKED_MASK)
+ break;
+
+ /*
+ * Try to clear pending bit & set locked bit
+ */
+ old = val;
+ new = (val & ~_Q_PENDING_MASK) | _Q_LOCKED_VAL;
+ val = atomic_cmpxchg(&lock->val, old, new);
+
+ if (val == old)
+ return 1;
+ }
+ return 0;
+}
+#endif /* _Q_PENDING_BITS == 8 */
+
+/*
* Include queued spinlock statistics code
*/
#include "qspinlock_stat.h"
@@ -202,8 +285,8 @@ static void pv_wait_node(struct mcs_spinlock *node)
/*
* If pv_kick_node() changed us to vcpu_hashed, retain that
- * value so that pv_wait_head() knows to not also try to hash
- * this lock.
+ * value so that pv_wait_head_or_lock() knows to not also try
+ * to hash this lock.
*/
cmpxchg(&pn->state, vcpu_halted, vcpu_running);
@@ -227,8 +310,9 @@ static void pv_wait_node(struct mcs_spinlock *node)
/*
* Called after setting next->locked = 1 when we're the lock owner.
*
- * Instead of waking the waiters stuck in pv_wait_node() advance their state such
- * that they're waiting in pv_wait_head(), this avoids a wake/sleep cycle.
+ * Instead of waking the waiters stuck in pv_wait_node() advance their state
+ * such that they're waiting in pv_wait_head_or_lock(), this avoids a
+ * wake/sleep cycle.
*/
static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
{
@@ -257,10 +341,14 @@ static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
}
/*
- * Wait for l->locked to become clear; halt the vcpu after a short spin.
+ * Wait for l->locked to become clear and acquire the lock;
+ * halt the vcpu after a short spin.
* __pv_queued_spin_unlock() will wake us.
+ *
+ * The current value of the lock will be returned for additional processing.
*/
-static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node)
+static u32
+pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
{
struct pv_node *pn = (struct pv_node *)node;
struct __qspinlock *l = (void *)lock;
@@ -276,11 +364,18 @@ static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node)
lp = (struct qspinlock **)1;
for (;; waitcnt++) {
+ /*
+ * Set the pending bit in the active lock spinning loop to
+ * disable lock stealing before attempting to acquire the lock.
+ */
+ set_pending(lock);
for (loop = SPIN_THRESHOLD; loop; loop--) {
- if (!READ_ONCE(l->locked))
- return;
+ if (trylock_clear_pending(lock))
+ goto gotlock;
cpu_relax();
}
+ clear_pending(lock);
+
if (!lp) { /* ONCE */
lp = pv_hash(lock, pn);
@@ -296,36 +391,38 @@ static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node)
*
* Matches the smp_rmb() in __pv_queued_spin_unlock().
*/
- if (!cmpxchg(&l->locked, _Q_LOCKED_VAL, _Q_SLOW_VAL)) {
+ if (xchg(&l->locked, _Q_SLOW_VAL) == 0) {
/*
- * The lock is free and _Q_SLOW_VAL has never
- * been set. Therefore we need to unhash before
- * getting the lock.
+ * The lock was free and now we own the lock.
+ * Change the lock value back to _Q_LOCKED_VAL
+ * and unhash the table.
*/
+ WRITE_ONCE(l->locked, _Q_LOCKED_VAL);
WRITE_ONCE(*lp, NULL);
- return;
+ goto gotlock;
}
}
qstat_inc(qstat_pv_wait_head, true);
qstat_inc(qstat_pv_wait_again, waitcnt);
pv_wait(&l->locked, _Q_SLOW_VAL);
- if (!READ_ONCE(l->locked))
- return;
/*
* The unlocker should have freed the lock before kicking the
* CPU. So if the lock is still not free, it is a spurious
- * wakeup and so the vCPU should wait again after spinning for
- * a while.
+ * wakeup or another vCPU has stolen the lock. The current
+ * vCPU should spin again.
*/
- qstat_inc(qstat_pv_spurious_wakeup, true);
+ qstat_inc(qstat_pv_spurious_wakeup, READ_ONCE(l->locked));
}
/*
- * Lock is unlocked now; the caller will acquire it without waiting.
- * As with pv_wait_node() we rely on the caller to do a load-acquire
- * for us.
+ * The cmpxchg() or xchg() call before coming here provides the
+ * acquire semantics for locking. The dummy ORing of _Q_LOCKED_VAL
+ * here is to indicate to the compiler that the value will always
+ * be nozero to enable better code optimization.
*/
+gotlock:
+ return (u32)(atomic_read(&lock->val) | _Q_LOCKED_VAL);
}
/*
@@ -350,7 +447,7 @@ __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
* so we need a barrier to order the read of the node data in
* pv_unhash *after* we've read the lock being _Q_SLOW_VAL.
*
- * Matches the cmpxchg() in pv_wait_head() setting _Q_SLOW_VAL.
+ * Matches the cmpxchg() in pv_wait_head_or_lock() setting _Q_SLOW_VAL.
*/
smp_rmb();