pstore: Avoid deadlock in panic and emergency-restart path

[Issue]

When pstore is in panic and emergency-restart paths, it may be blocked
in those paths because it simply takes spin_lock.

This is an example scenario which pstore may hang up in a panic path:

 - cpuA grabs psinfo->buf_lock
 - cpuB panics and calls smp_send_stop
 - smp_send_stop sends IRQ to cpuA
 - after 1 second, cpuB gives up on cpuA and sends an NMI instead
 - cpuA is now in an NMI handler while still holding buf_lock
 - cpuB is deadlocked

This case may happen if a firmware has a bug and
cpuA is stuck talking with it more than one second.

Also, this is a similar scenario in an emergency-restart path:

 - cpuA grabs psinfo->buf_lock and stucks in a firmware
 - cpuB kicks emergency-restart via either sysrq-b or hangcheck timer.
   And then, cpuB is deadlocked by taking psinfo->buf_lock again.

[Solution]

This patch avoids the deadlocking issues in both panic and emergency_restart
paths by introducing a function, is_non_blocking_path(), to check if a cpu
can be blocked in current path.

With this patch, pstore is not blocked even if another cpu has
taken a spin_lock, in those paths by changing from spin_lock_irqsave
to spin_trylock_irqsave.

In addition, according to a comment of emergency_restart() in kernel/sys.c,
spin_lock shouldn't be taken in an emergency_restart path to avoid
deadlock. This patch fits the comment below.

<snip>
/**
 *      emergency_restart - reboot the system
 *
 *      Without shutting down any hardware or taking any locks
 *      reboot the system.  This is called when we know we are in
 *      trouble so this is our best effort to reboot.  This is
 *      safe to call in interrupt context.
 */
void emergency_restart(void)
<snip>

Signed-off-by: Seiji Aguchi <seiji.aguchi@hds.com>
Acked-by: Don Zickus <dzickus@redhat.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>

1 files changed, 29 insertions, 6 deletions

diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 5ea2e77..86d1038 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -96,6 +96,27 @@ static const char *get_reason_str(enum kmsg_dump_reason reason)
 	}
 }
 
+bool pstore_cannot_block_path(enum kmsg_dump_reason reason)
+{
+	/*
+	 * In case of NMI path, pstore shouldn't be blocked
+	 * regardless of reason.
+	 */
+	if (in_nmi())
+		return true;
+
+	switch (reason) {
+	/* In panic case, other cpus are stopped by smp_send_stop(). */
+	case KMSG_DUMP_PANIC:
+	/* Emergency restart shouldn't be blocked by spin lock. */
+	case KMSG_DUMP_EMERG:
+		return true;
+	default:
+		return false;
+	}
+}
+EXPORT_SYMBOL_GPL(pstore_cannot_block_path);
+
 /*
  * callback from kmsg_dump. (s2,l2) has the most recently
  * written bytes, older bytes are in (s1,l1). Save as much
@@ -114,10 +135,12 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 
 	why = get_reason_str(reason);
 
-	if (in_nmi()) {
-		is_locked = spin_trylock(&psinfo->buf_lock);
-		if (!is_locked)
-			pr_err("pstore dump routine blocked in NMI, may corrupt error record\n");
+	if (pstore_cannot_block_path(reason)) {
+		is_locked = spin_trylock_irqsave(&psinfo->buf_lock, flags);
+		if (!is_locked) {
+			pr_err("pstore dump routine blocked in %s path, may corrupt error record\n"
+				       , in_nmi() ? "NMI" : why);
+		}
 	} else
 		spin_lock_irqsave(&psinfo->buf_lock, flags);
 	oopscount++;
@@ -143,9 +166,9 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 		total += hsize + len;
 		part++;
 	}
-	if (in_nmi()) {
+	if (pstore_cannot_block_path(reason)) {
 		if (is_locked)
-			spin_unlock(&psinfo->buf_lock);
+			spin_unlock_irqrestore(&psinfo->buf_lock, flags);
 	} else
 		spin_unlock_irqrestore(&psinfo->buf_lock, flags);
 }