locking/qspinlock/x86: Fix performance regression under unaccelerated VMs

Dave ran into horrible performance on a VM without PARAVIRT_SPINLOCKS
set and Linus noted that the test-and-set implementation was retarded.

One should spin on the variable with a load, not a RMW.

While there, remove 'queued' from the name, as the lock isn't queued
at all, but a simple test-and-set.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Dave Chinner <david@fromorbit.com>
Tested-by: Dave Chinner <david@fromorbit.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <Waiman.Long@hp.com>
Cc: stable@vger.kernel.org # v4.2+
Link: http://lkml.kernel.org/r/20150904152523.GR18673@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 15 insertions, 7 deletions

diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 9d51fae1cba3..8dde3bdc4a05 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -39,15 +39,23 @@ static inline void queued_spin_unlock(struct qspinlock *lock)
 }
 #endif
 
-#define virt_queued_spin_lock virt_queued_spin_lock
+#define virt_spin_lock virt_spin_lock
 
-static inline bool virt_queued_spin_lock(struct qspinlock *lock)
+static inline bool virt_spin_lock(struct qspinlock *lock)
 {
         if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
                 return false;
 
-        while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0)
-                cpu_relax();
+        /*
+         * On hypervisors without PARAVIRT_SPINLOCKS support we fall
+         * back to a Test-and-Set spinlock, because fair locks have
+         * horrible lock 'holder' preemption issues.
+         */
+
+        do {
+                while (atomic_read(&lock->val) != 0)
+                        cpu_relax();
+        } while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0);
 
         return true;
 }
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 83bfb87f5bf1..e2aadbc7151f 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -111,8 +111,8 @@ static inline void queued_spin_unlock_wait(struct qspinlock *lock)
                 cpu_relax();
 }
 
-#ifndef virt_queued_spin_lock
-static __always_inline bool virt_queued_spin_lock(struct qspinlock *lock)
+#ifndef virt_spin_lock
+static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 {
         return false;
 }
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 337c8818541d..87e9ce6a63c5 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -289,7 +289,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
         if (pv_enabled())
                 goto queue;
 
-        if (virt_queued_spin_lock(lock))
+        if (virt_spin_lock(lock))
                 return;
 
         /*