linux-kernel - [PATCH rcu 04/14] rcuscale: Dump stacks of stalled rcu_scale

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20240816070256.60993-4-neeraj.upadhyay@kernel.org>
Date: Fri, 16 Aug 2024 12:32:46 +0530
From: neeraj.upadhyay@...nel.org
To: rcu@...r.kernel.org
Cc: linux-kernel@...r.kernel.org,
	kernel-team@...a.com,
	rostedt@...dmis.org,
	paulmck@...nel.org,
	neeraj.upadhyay@...nel.org,
	neeraj.upadhyay@....com,
	boqun.feng@...il.com,
	joel@...lfernandes.org,
	urezki@...il.com,
	frederic@...nel.org
Subject: [PATCH rcu 04/14] rcuscale: Dump stacks of stalled rcu_scale_writer() instances

From: "Paul E. McKenney" <paulmck@...nel.org>

This commit improves debuggability by dumping the stacks of
rcu_scale_writer() instances that have not completed in a reasonable
timeframe.  These stacks are dumped remotely, but they will be accurate
in the thus-far common case where the stalled rcu_scale_writer() instances
are blocked.

[ paulmck: Apply kernel test robot feedback. ]

Signed-off-by: "Paul E. McKenney" <paulmck@...nel.org>
Signed-off-by: Neeraj Upadhyay <neeraj.upadhyay@...nel.org>
---
 kernel/rcu/rcuscale.c | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c
index 3269dd9c639f..5087ca7062d9 100644
--- a/kernel/rcu/rcuscale.c
+++ b/kernel/rcu/rcuscale.c
@@ -39,6 +39,7 @@
 #include <linux/torture.h>
 #include <linux/vmalloc.h>
 #include <linux/rcupdate_trace.h>
+#include <linux/sched/debug.h>
 
 #include "rcu.h"
 
@@ -111,6 +112,7 @@ static struct task_struct **reader_tasks;
 static struct task_struct *shutdown_task;
 
 static u64 **writer_durations;
+static bool *writer_done;
 static int *writer_n_durations;
 static atomic_t n_rcu_scale_reader_started;
 static atomic_t n_rcu_scale_writer_started;
@@ -524,6 +526,7 @@ rcu_scale_writer(void *arg)
 			started = true;
 		if (!done && i >= MIN_MEAS && time_after(jiffies, jdone)) {
 			done = true;
+			WRITE_ONCE(writer_done[me], true);
 			sched_set_normal(current, 0);
 			pr_alert("%s%s rcu_scale_writer %ld has %d measurements\n",
 				 scale_type, SCALE_FLAG, me, MIN_MEAS);
@@ -549,6 +552,19 @@ rcu_scale_writer(void *arg)
 		if (done && !alldone &&
 		    atomic_read(&n_rcu_scale_writer_finished) >= nrealwriters)
 			alldone = true;
+		if (done && !alldone && time_after(jiffies, jdone + HZ * 60)) {
+			static atomic_t dumped;
+			int i;
+
+			if (!atomic_xchg(&dumped, 1)) {
+				for (i = 0; i < nrealwriters; i++) {
+					if (writer_done[i])
+						continue;
+					pr_info("%s: Task %ld flags writer %d:\n", __func__, me, i);
+					sched_show_task(writer_tasks[i]);
+				}
+			}
+		}
 		if (started && !alldone && i < MAX_MEAS - 1)
 			i++;
 		rcu_scale_wait_shutdown();
@@ -921,6 +937,8 @@ rcu_scale_cleanup(void)
 		kfree(writer_tasks);
 		kfree(writer_durations);
 		kfree(writer_n_durations);
+		kfree(writer_done);
+		writer_done = NULL;
 	}
 
 	/* Do torture-type-specific cleanup operations.  */
@@ -1015,10 +1033,11 @@ rcu_scale_init(void)
 	}
 	while (atomic_read(&n_rcu_scale_reader_started) < nrealreaders)
 		schedule_timeout_uninterruptible(1);
-	writer_tasks = kcalloc(nrealwriters, sizeof(reader_tasks[0]), GFP_KERNEL);
+	writer_tasks = kcalloc(nrealwriters, sizeof(writer_tasks[0]), GFP_KERNEL);
 	writer_durations = kcalloc(nrealwriters, sizeof(*writer_durations), GFP_KERNEL);
 	writer_n_durations = kcalloc(nrealwriters, sizeof(*writer_n_durations), GFP_KERNEL);
-	if (!writer_tasks || !writer_durations || !writer_n_durations) {
+	writer_done = kcalloc(nrealwriters, sizeof(writer_done[0]), GFP_KERNEL);
+	if (!writer_tasks || !writer_durations || !writer_n_durations || !writer_done) {
 		SCALEOUT_ERRSTRING("out of memory");
 		firsterr = -ENOMEM;
 		goto unwind;
-- 
2.40.1