xen: allow interrupts to be enabled while doing a blocking spin

If spin_lock is called in an interrupts-enabled context, we can safely
enable interrupts while spinning.  We don't bother for the actual spin
loop, but if we timeout and fall back to blocking, it's definitely
worthwhile enabling interrupts if possible.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Acked-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 0d8f3b2..e6061f2 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -23,6 +23,7 @@
 	u32 taken_slow_nested;
 	u32 taken_slow_pickup;
 	u32 taken_slow_spurious;
+	u32 taken_slow_irqenable;
 
 	u64 released;
 	u32 released_slow;
@@ -167,12 +168,13 @@
 	__get_cpu_var(lock_spinners) = prev;
 }
 
-static noinline int xen_spin_lock_slow(struct raw_spinlock *lock)
+static noinline int xen_spin_lock_slow(struct raw_spinlock *lock, bool irq_enable)
 {
 	struct xen_spinlock *xl = (struct xen_spinlock *)lock;
 	struct xen_spinlock *prev;
 	int irq = __get_cpu_var(lock_kicker_irq);
 	int ret;
+	unsigned long flags;
 
 	/* If kicker interrupts not initialized yet, just spin */
 	if (irq == -1)
@@ -181,6 +183,12 @@
 	/* announce we're spinning */
 	prev = spinning_lock(xl);
 
+	flags = __raw_local_save_flags();
+	if (irq_enable) {
+		ADD_STATS(taken_slow_irqenable, 1);
+		raw_local_irq_enable();
+	}
+
 	ADD_STATS(taken_slow, 1);
 	ADD_STATS(taken_slow_nested, prev != NULL);
 
@@ -220,11 +228,12 @@
 	kstat_this_cpu.irqs[irq]++;
 
 out:
+	raw_local_irq_restore(flags);
 	unspinning_lock(xl, prev);
 	return ret;
 }
 
-static void xen_spin_lock(struct raw_spinlock *lock)
+static inline void __xen_spin_lock(struct raw_spinlock *lock, bool irq_enable)
 {
 	struct xen_spinlock *xl = (struct xen_spinlock *)lock;
 	unsigned timeout;
@@ -254,11 +263,23 @@
 		    : "memory");
 
 		spin_time_accum_fast(start_spin_fast);
-	} while (unlikely(oldval != 0 && (TIMEOUT == ~0 || !xen_spin_lock_slow(lock))));
+
+	} while (unlikely(oldval != 0 &&
+			  (TIMEOUT == ~0 || !xen_spin_lock_slow(lock, irq_enable))));
 
 	spin_time_accum(start_spin);
 }
 
+static void xen_spin_lock(struct raw_spinlock *lock)
+{
+	__xen_spin_lock(lock, false);
+}
+
+static void xen_spin_lock_flags(struct raw_spinlock *lock, unsigned long flags)
+{
+	__xen_spin_lock(lock, !raw_irqs_disabled_flags(flags));
+}
+
 static noinline void xen_spin_unlock_slow(struct xen_spinlock *xl)
 {
 	int cpu;
@@ -323,6 +344,7 @@
 	pv_lock_ops.spin_is_locked = xen_spin_is_locked;
 	pv_lock_ops.spin_is_contended = xen_spin_is_contended;
 	pv_lock_ops.spin_lock = xen_spin_lock;
+	pv_lock_ops.spin_lock_flags = xen_spin_lock_flags;
 	pv_lock_ops.spin_trylock = xen_spin_trylock;
 	pv_lock_ops.spin_unlock = xen_spin_unlock;
 }
@@ -353,6 +375,8 @@
 			   &spinlock_stats.taken_slow_pickup);
 	debugfs_create_u32("taken_slow_spurious", 0444, d_spin_debug,
 			   &spinlock_stats.taken_slow_spurious);
+	debugfs_create_u32("taken_slow_irqenable", 0444, d_spin_debug,
+			   &spinlock_stats.taken_slow_irqenable);
 
 	debugfs_create_u64("released", 0444, d_spin_debug, &spinlock_stats.released);
 	debugfs_create_u32("released_slow", 0444, d_spin_debug,