percpu_ref: Dump mem_dump_obj() info upon reference-count underflow

Reference-count underflow for percpu_ref is detected in the RCU callback
percpu_ref_switch_to_atomic_rcu(), and the resulting warning does not
print anything allowing easy identification of which percpu_ref use
case is underflowing.  This is of course not normally a problem when
developing a new percpu_ref use case because it is most likely that
the problem resides in this new use case.  However, when deploying a
new kernel to a large set of servers, the underflow might well be a new
corner case in any of the old percpu_ref use cases.

This commit therefore calls mem_dump_obj() to dump out any additional
available information on the underflowing percpu_ref instance.

Cc: Ming Lei <ming.lei@redhat.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Reported-by: Andrii Nakryiko <andrii@kernel.org>
Tested-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>

diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index e59eda0..a1071cd 100644 (file)
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -5,6 +5,7 @@
 #include <linux/sched.h>
 #include <linux/wait.h>
 #include <linux/slab.h>
+#include <linux/mm.h>
 #include <linux/percpu-refcount.h>
 
 /*
@@ -168,6 +169,7 @@ static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu)
                        struct percpu_ref_data, rcu);
        struct percpu_ref *ref = data->ref;
        unsigned long __percpu *percpu_count = percpu_count_ptr(ref);
+       static atomic_t underflows;
        unsigned long count = 0;
        int cpu;
 
@@ -191,9 +193,13 @@ static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu)
         */
        atomic_long_add((long)count - PERCPU_COUNT_BIAS, &data->count);
 
-       WARN_ONCE(atomic_long_read(&data->count) <= 0,
-                 "percpu ref (%ps) <= 0 (%ld) after switching to atomic",
-                 data->release, atomic_long_read(&data->count));
+       if (WARN_ONCE(atomic_long_read(&data->count) <= 0,
+                     "percpu ref (%ps) <= 0 (%ld) after switching to atomic",
+                     data->release, atomic_long_read(&data->count)) &&
+           atomic_inc_return(&underflows) < 4) {
+               pr_err("%s(): percpu_ref underflow", __func__);
+               mem_dump_obj(data);
+       }
 
        /* @ref is viewed as dead on all CPUs, send out switch confirmation */
        percpu_ref_call_confirm_rcu(rcu);