1 files changed, 20 insertions, 26 deletions

diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 973f10e05211..1c8a8816a402 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -9,6 +9,7 @@
 #include <linux/log2.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
+#include <linux/atomic.h>
 
 #include <asm/paravirt.h>
 #include <asm/qspinlock.h>
@@ -21,6 +22,7 @@
 
 static DEFINE_PER_CPU(int, lock_kicker_irq) = -1;
 static DEFINE_PER_CPU(char *, irq_name);
+static DEFINE_PER_CPU(atomic_t, xen_qlock_wait_nest);
 static bool xen_pvspin = true;
 
 static void xen_qlock_kick(int cpu)
@@ -40,33 +42,24 @@ static void xen_qlock_kick(int cpu)
 static void xen_qlock_wait(u8 *byte, u8 val)
 {
 	int irq = __this_cpu_read(lock_kicker_irq);
+	atomic_t *nest_cnt = this_cpu_ptr(&xen_qlock_wait_nest);
 
 	/* If kicker interrupts not initialized yet, just spin */
-	if (irq == -1)
+	if (irq == -1 || in_nmi())
 		return;
 
-	/* clear pending */
-	xen_clear_irq_pending(irq);
-	barrier();
-
-	/*
-	 * We check the byte value after clearing pending IRQ to make sure
-	 * that we won't miss a wakeup event because of the clearing.
-	 *
-	 * The sync_clear_bit() call in xen_clear_irq_pending() is atomic.
-	 * So it is effectively a memory barrier for x86.
-	 */
-	if (READ_ONCE(*byte) != val)
-		return;
+	/* Detect reentry. */
+	atomic_inc(nest_cnt);
 
-	/*
-	 * If an interrupt happens here, it will leave the wakeup irq
-	 * pending, which will cause xen_poll_irq() to return
-	 * immediately.
-	 */
+	/* If irq pending already and no nested call clear it. */
+	if (atomic_read(nest_cnt) == 1 && xen_test_irq_pending(irq)) {
+		xen_clear_irq_pending(irq);
+	} else if (READ_ONCE(*byte) == val) {
+		/* Block until irq becomes pending (or a spurious wakeup) */
+		xen_poll_irq(irq);
+	}
 
-	/* Block until irq becomes pending (or perhaps a spurious wakeup) */
-	xen_poll_irq(irq);
+	atomic_dec(nest_cnt);
 }
 
 static irqreturn_t dummy_handler(int irq, void *dev_id)
@@ -141,11 +134,12 @@ void __init xen_init_spinlocks(void)
 	printk(KERN_DEBUG "xen: PV spinlocks enabled\n");
 
 	__pv_init_lock_hash();
-	pv_lock_ops.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
-	pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
-	pv_lock_ops.wait = xen_qlock_wait;
-	pv_lock_ops.kick = xen_qlock_kick;
-	pv_lock_ops.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen);
+	pv_ops.lock.queued_spin_lock_slowpath = __pv_queued_spin_lock_slowpath;
+	pv_ops.lock.queued_spin_unlock =
+		PV_CALLEE_SAVE(__pv_queued_spin_unlock);
+	pv_ops.lock.wait = xen_qlock_wait;
+	pv_ops.lock.kick = xen_qlock_kick;
+	pv_ops.lock.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen);
 }
 
 static __init int xen_parse_nopvspin(char *arg)