KVM: x86: Prevent deadlock against tk_core.seq

syzbot reported a possible deadlock in pvclock_gtod_notify():

CPU 0  		  	   	    	    CPU 1
write_seqcount_begin(&tk_core.seq);
  pvclock_gtod_notify()			    spin_lock(&pool->lock);
    queue_work(..., &pvclock_gtod_work)	    ktime_get()
     spin_lock(&pool->lock);		      do {
     						seq = read_seqcount_begin(tk_core.seq)
						...
				              } while (read_seqcount_retry(&tk_core.seq, seq);

While this is unlikely to happen, it's possible.

Delegate queue_work() to irq_work() which postpones it until the
tk_core.seq write held region is left and interrupts are reenabled.

Fixes: 16e8d74d2da9 ("KVM: x86: notifier for clocksource changes")
Reported-by: syzbot+6beae4000559d41d80f8@syzkaller.appspotmail.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Message-Id: <87h7jgm1zy.ffs@nanos.tec.linutronix.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 18 insertions, 4 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 259139a145cb..5bd550eaf683 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8095,6 +8095,18 @@ static void pvclock_gtod_update_fn(struct work_struct *work)
 static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn);
 
 /*
+ * Indirection to move queue_work() out of the tk_core.seq write held
+ * region to prevent possible deadlocks against time accessors which
+ * are invoked with work related locks held.
+ */
+static void pvclock_irq_work_fn(struct irq_work *w)
+{
+	queue_work(system_long_wq, &pvclock_gtod_work);
+}
+
+static DEFINE_IRQ_WORK(pvclock_irq_work, pvclock_irq_work_fn);
+
+/*
  * Notification about pvclock gtod data update.
  */
 static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused,
@@ -8105,13 +8117,14 @@ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused,
 
 	update_pvclock_gtod(tk);
 
-	/* disable master clock if host does not trust, or does not
-	 * use, TSC based clocksource.
+	/*
+	 * Disable master clock if host does not trust, or does not use,
+	 * TSC based clocksource. Delegate queue_work() to irq_work as
+	 * this is invoked with tk_core.seq write held.
 	 */
 	if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) &&
 	    atomic_read(&kvm_guest_has_master_clock) != 0)
-		queue_work(system_long_wq, &pvclock_gtod_work);
-
+		irq_work_queue(&pvclock_irq_work);
 	return 0;
 }
 
@@ -8224,6 +8237,7 @@ void kvm_arch_exit(void)
 	cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE);
 #ifdef CONFIG_X86_64
 	pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier);
+	irq_work_sync(&pvclock_irq_work);
 	cancel_work_sync(&pvclock_gtod_work);
 #endif
 	kvm_x86_ops.hardware_enable = NULL;