[PATCH v2 07/10] srcu: Detect duplicate callback enqueue at registration

[Kunwu Chan]

Move the duplicate-callback check from srcu_do_enqueue() to
__call_srcu() entry so that detected duplicate registrations
are rejected before they reach the deferred-list enqueue path.
Use __ratelimit() to limit the diagnostic output (error message,
object dump, and stack trace) as a group.

Suggested-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
Signed-off-by: Kunwu Chan <chentao@xxxxxxxxxx>
---
 kernel/rcu/srcutree.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 1993ddbdb828..81423b3dffae 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -23,10 +23,12 @@
 #include <linux/kasan.h>
 #include <linux/llist.h>
 #include <linux/rcupdate_wait.h>
+#include <linux/ratelimit.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
 #include <linux/delay.h>
 #include <linux/module.h>
+#include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/srcu.h>
 
@@ -1511,12 +1513,6 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp,
 static void srcu_do_enqueue(struct srcu_struct *ssp, struct rcu_head *rhp,
 			    rcu_callback_t func, bool do_norm)
 {
-	if (debug_rcu_head_queue(rhp)) {
-		/* Probable double call_srcu(), so leak the callback. */
-		WRITE_ONCE(rhp->func, srcu_leak_callback);
-		WARN_ONCE(1, "call_srcu(): Leaked duplicate callback\n");
-		return;
-	}
 	rhp->func = func;
 	(void)srcu_gp_start_if_needed(ssp, rhp, do_norm);
 }
@@ -1526,6 +1522,10 @@ static void srcu_do_enqueue(struct srcu_struct *ssp, struct rcu_head *rhp,
  * disabled, so defer when interrupts are already off rather than enqueue into
  * an operation that may be in flight on this CPU.
  */
+static DEFINE_RATELIMIT_STATE(rcu_srcu_dup_rs,
+			      DEFAULT_RATELIMIT_INTERVAL,
+			      DEFAULT_RATELIMIT_BURST);
+
 static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
 			rcu_callback_t func, bool do_norm)
 {
@@ -1539,6 +1539,17 @@ static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
 	if (WARN_ON_ONCE(ssp->srcu_reader_flavor == SRCU_READ_FLAVOR_ATOMIC))
 		return; // Leak the callback rather than corrupt SRCU state.
 
+	if (debug_rcu_head_queue(rhp)) {
+		if (__ratelimit(&rcu_srcu_dup_rs)) {
+			pr_err("%s(): Duplicate call_srcu() CB %p->%pS()\n",
+			       __func__, rhp, rhp->func);
+			mem_dump_obj(rhp);
+			dump_stack();
+		}
+		WRITE_ONCE(rhp->func, srcu_leak_callback);
+		return;
+	}
+
 	/* Record the caller: the irq_work's stack says nothing about it. */
 	kasan_record_aux_stack(rhp);
 
@@ -1554,6 +1565,7 @@ static void __call_srcu(struct srcu_struct *ssp, struct rcu_head *rhp,
 		if (READ_ONCE(sndp->draining) && !in_nmi()) {
 			WARN_ONCE(IS_ENABLED(CONFIG_PROVE_RCU),
 				  "call_srcu() re-entered during callback drain; leaking callback\n");
+			debug_rcu_head_unqueue(rhp);
 			return;
 		}
 		sdp = this_cpu_ptr(ssp->sda);
-- 
2.43.0