xen: make xen_qlock_wait() nestable

xen_qlock_wait() isn't safe for nested calls due to interrupts. A call
of xen_qlock_kick() might be ignored in case a deeper nesting level
was active right before the call of xen_poll_irq():

CPU 1:                                   CPU 2:
spin_lock(lock1)
                                         spin_lock(lock1)
                                         -> xen_qlock_wait()
                                            -> xen_clear_irq_pending()
                                            Interrupt happens
spin_unlock(lock1)
-> xen_qlock_kick(CPU 2)
spin_lock_irqsave(lock2)
                                         spin_lock_irqsave(lock2)
                                         -> xen_qlock_wait()
                                            -> xen_clear_irq_pending()
                                               clears kick for lock1
                                            -> xen_poll_irq()
spin_unlock_irq_restore(lock2)
-> xen_qlock_kick(CPU 2)
                                            wakes up
                                         spin_unlock_irq_restore(lock2)
                                         IRET
                                           resumes in xen_qlock_wait()
                                           -> xen_poll_irq()
                                           never wakes up

The solution is to disable interrupts in xen_qlock_wait() and not to
poll for the irq in case xen_qlock_wait() is called in nmi context.

Cc: stable@vger.kernel.org
Cc: Waiman.Long@hp.com
Cc: peterz@infradead.org
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>

diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 290a69ec7d4df6e394941b689e368cfbb1047e77..441c8826216982a4fb9532b68d68a37cbb0d3e05 100644 (file)
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -39,29 +39,25 @@ static void xen_qlock_kick(int cpu)
  */
 static void xen_qlock_wait(u8 *byte, u8 val)
 {
+       unsigned long flags;
        int irq = __this_cpu_read(lock_kicker_irq);
 
        /* If kicker interrupts not initialized yet, just spin */
-       if (irq == -1)
+       if (irq == -1 || in_nmi())
                return;
 
-       /* If irq pending already clear it and return. */
+       /* Guard against reentry. */
+       local_irq_save(flags);
+
+       /* If irq pending already clear it. */
        if (xen_test_irq_pending(irq)) {
                xen_clear_irq_pending(irq);
-               return;
+       } else if (READ_ONCE(*byte) == val) {
+               /* Block until irq becomes pending (or a spurious wakeup) */
+               xen_poll_irq(irq);
        }
 
-       if (READ_ONCE(*byte) != val)
-               return;
-
-       /*
-        * If an interrupt happens here, it will leave the wakeup irq
-        * pending, which will cause xen_poll_irq() to return
-        * immediately.
-        */
-
-       /* Block until irq becomes pending (or perhaps a spurious wakeup) */
-       xen_poll_irq(irq);
+       local_irq_restore(flags);
 }
 
 static irqreturn_t dummy_handler(int irq, void *dev_id)