[PATCH] dump_stack: Avoid the livelock of the dump_lock

[Kevin Hao]

In the current code, we uses the atomic_cmpxchg() to serialize the
output of the dump_stack(), but this implementation suffers the
thundering herd problem. We have observed such kind of livelock on a
Marvell cn96xx board(24 cpus) when heavily using the dump_stack() in
a kprobe handler. Actually we can use a spinlock here and leverage the
implementation of the spinlock(either ticket or queued spinlock) to
mediate such kind of livelock. Since the dump_stack() runs with the
irq disabled, so use the raw_spinlock_t to make it safe for rt kernel.

Signed-off-by: Kevin Hao <haokexin@xxxxxxxxx>
---
 lib/dump_stack.c | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index 5cff72f18c4a..fa971f75f1e2 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -83,37 +83,35 @@ static void __dump_stack(void)
  * Architectures can override this implementation by implementing its own.
  */
 #ifdef CONFIG_SMP
-static atomic_t dump_lock = ATOMIC_INIT(-1);
+static DEFINE_RAW_SPINLOCK(dump_lock);
+static int dump_cpu = -1;
 
 asmlinkage __visible void dump_stack(void)
 {
 	unsigned long flags;
 	int was_locked;
-	int old;
 	int cpu;
 
 	/*
 	 * Permit this cpu to perform nested stack dumps while serialising
 	 * against other CPUs
 	 */
-retry:
 	local_irq_save(flags);
 	cpu = smp_processor_id();
-	old = atomic_cmpxchg(&dump_lock, -1, cpu);
-	if (old == -1) {
+
+	if (READ_ONCE(dump_cpu) != cpu) {
+		raw_spin_lock(&dump_lock);
+		dump_cpu = cpu;
 		was_locked = 0;
-	} else if (old == cpu) {
+	} else
 		was_locked = 1;
-	} else {
-		local_irq_restore(flags);
-		cpu_relax();
-		goto retry;
-	}
 
 	__dump_stack();
 
-	if (!was_locked)
-		atomic_set(&dump_lock, -1);
+	if (!was_locked) {
+		dump_cpu = -1;
+		raw_spin_unlock(&dump_lock);
+	}
 
 	local_irq_restore(flags);
 }
-- 
2.14.4