hung_task: show the blocker task if the task is hung on semaphore

Inspired by mutex blocker tracking[1], this patch makes a trade-off to
balance the overhead and utility of the hung task detector.

Unlike mutexes, semaphores lack explicit ownership tracking, making it
challenging to identify the root cause of hangs.  To address this, we
introduce a last_holder field to the semaphore structure, which is updated
when a task successfully calls down() and cleared during up().

The assumption is that if a task is blocked on a semaphore, the holders
must not have released it.  While this does not guarantee that the last
holder is one of the current blockers, it likely provides a practical hint
for diagnosing semaphore-related stalls.

With this change, the hung task detector can now show blocker task's info
like below:

[Tue Apr  8 12:19:07 2025] INFO: task cat:945 blocked for more than 120 seconds.
[Tue Apr  8 12:19:07 2025]       Tainted: G            E      6.14.0-rc6+ #1
[Tue Apr  8 12:19:07 2025] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[Tue Apr  8 12:19:07 2025] task:cat             state:D stack:0     pid:945   tgid:945   ppid:828    task_flags:0x400000 flags:0x00000000
[Tue Apr  8 12:19:07 2025] Call Trace:
[Tue Apr  8 12:19:07 2025]  <TASK>
[Tue Apr  8 12:19:07 2025]  __schedule+0x491/0xbd0
[Tue Apr  8 12:19:07 2025]  schedule+0x27/0xf0
[Tue Apr  8 12:19:07 2025]  schedule_timeout+0xe3/0xf0
[Tue Apr  8 12:19:07 2025]  ? __folio_mod_stat+0x2a/0x80
[Tue Apr  8 12:19:07 2025]  ? set_ptes.constprop.0+0x27/0x90
[Tue Apr  8 12:19:07 2025]  __down_common+0x155/0x280
[Tue Apr  8 12:19:07 2025]  down+0x53/0x70
[Tue Apr  8 12:19:07 2025]  read_dummy_semaphore+0x23/0x60
[Tue Apr  8 12:19:07 2025]  full_proxy_read+0x5f/0xa0
[Tue Apr  8 12:19:07 2025]  vfs_read+0xbc/0x350
[Tue Apr  8 12:19:07 2025]  ? __count_memcg_events+0xa5/0x140
[Tue Apr  8 12:19:07 2025]  ? count_memcg_events.constprop.0+0x1a/0x30
[Tue Apr  8 12:19:07 2025]  ? handle_mm_fault+0x180/0x260
[Tue Apr  8 12:19:07 2025]  ksys_read+0x66/0xe0
[Tue Apr  8 12:19:07 2025]  do_syscall_64+0x51/0x120
[Tue Apr  8 12:19:07 2025]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[Tue Apr  8 12:19:07 2025] RIP: 0033:0x7f419478f46e
[Tue Apr  8 12:19:07 2025] RSP: 002b:00007fff1c4d2668 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
[Tue Apr  8 12:19:07 2025] RAX: ffffffffffffffda RBX: 0000000000020000 RCX: 00007f419478f46e
[Tue Apr  8 12:19:07 2025] RDX: 0000000000020000 RSI: 00007f4194683000 RDI: 0000000000000003
[Tue Apr  8 12:19:07 2025] RBP: 00007f4194683000 R08: 00007f4194682010 R09: 0000000000000000
[Tue Apr  8 12:19:07 2025] R10: fffffffffffffbc5 R11: 0000000000000246 R12: 0000000000000000
[Tue Apr  8 12:19:07 2025] R13: 0000000000000003 R14: 0000000000020000 R15: 0000000000020000
[Tue Apr  8 12:19:07 2025]  </TASK>
[Tue Apr  8 12:19:07 2025] INFO: task cat:945 blocked on a semaphore likely last held by task cat:938
[Tue Apr  8 12:19:07 2025] task:cat             state:S stack:0     pid:938   tgid:938   ppid:584    task_flags:0x400000 flags:0x00000000
[Tue Apr  8 12:19:07 2025] Call Trace:
[Tue Apr  8 12:19:07 2025]  <TASK>
[Tue Apr  8 12:19:07 2025]  __schedule+0x491/0xbd0
[Tue Apr  8 12:19:07 2025]  ? _raw_spin_unlock_irqrestore+0xe/0x40
[Tue Apr  8 12:19:07 2025]  schedule+0x27/0xf0
[Tue Apr  8 12:19:07 2025]  schedule_timeout+0x77/0xf0
[Tue Apr  8 12:19:07 2025]  ? __pfx_process_timeout+0x10/0x10
[Tue Apr  8 12:19:07 2025]  msleep_interruptible+0x49/0x60
[Tue Apr  8 12:19:07 2025]  read_dummy_semaphore+0x2d/0x60
[Tue Apr  8 12:19:07 2025]  full_proxy_read+0x5f/0xa0
[Tue Apr  8 12:19:07 2025]  vfs_read+0xbc/0x350
[Tue Apr  8 12:19:07 2025]  ? __count_memcg_events+0xa5/0x140
[Tue Apr  8 12:19:07 2025]  ? count_memcg_events.constprop.0+0x1a/0x30
[Tue Apr  8 12:19:07 2025]  ? handle_mm_fault+0x180/0x260
[Tue Apr  8 12:19:07 2025]  ksys_read+0x66/0xe0
[Tue Apr  8 12:19:07 2025]  do_syscall_64+0x51/0x120
[Tue Apr  8 12:19:07 2025]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[Tue Apr  8 12:19:07 2025] RIP: 0033:0x7f7c584a646e
[Tue Apr  8 12:19:07 2025] RSP: 002b:00007ffdba8ce158 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
[Tue Apr  8 12:19:07 2025] RAX: ffffffffffffffda RBX: 0000000000020000 RCX: 00007f7c584a646e
[Tue Apr  8 12:19:07 2025] RDX: 0000000000020000 RSI: 00007f7c5839a000 RDI: 0000000000000003
[Tue Apr  8 12:19:07 2025] RBP: 00007f7c5839a000 R08: 00007f7c58399010 R09: 0000000000000000
[Tue Apr  8 12:19:07 2025] R10: fffffffffffffbc5 R11: 0000000000000246 R12: 0000000000000000
[Tue Apr  8 12:19:07 2025] R13: 0000000000000003 R14: 0000000000020000 R15: 0000000000020000
[Tue Apr  8 12:19:07 2025]  </TASK>

[1] https://lore.kernel.org/all/174046694331.2194069.15472952050240807469.stgit@mhiramat.tok.corp.google.com

Link: https://lkml.kernel.org/r/20250414145945.84916-3-ioworker0@gmail.com
Signed-off-by: Mingzhe Yang <mingzhe.yang@ly.com>
Signed-off-by: Lance Yang <ioworker0@gmail.com>
Suggested-by: Andrew Morton <akpm@linux-foundation.org>
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Anna Schumaker <anna.schumaker@oracle.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Joel Granados <joel.granados@kernel.org>
Cc: John Stultz <jstultz@google.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tomasz Figa <tfiga@chromium.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yongliang Gao <leonylgao@tencent.com>
Cc: Zi Li <amaindex@outlook.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 41 insertions, 11 deletions

diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 79558d76ef06..d2432df2b905 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -99,32 +99,62 @@ static struct notifier_block panic_block = {
 static void debug_show_blocker(struct task_struct *task)
 {
 	struct task_struct *g, *t;
-	unsigned long owner, blocker;
+	unsigned long owner, blocker, blocker_type;
 
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "No rcu lock held");
 
 	blocker = READ_ONCE(task->blocker);
-	if (!blocker ||
-	    hung_task_get_blocker_type(blocker) != BLOCKER_TYPE_MUTEX)
+	if (!blocker)
 		return;
 
-	owner = mutex_get_owner(
-		(struct mutex *)hung_task_blocker_to_lock(blocker));
+	blocker_type = hung_task_get_blocker_type(blocker);
+
+	switch (blocker_type) {
+	case BLOCKER_TYPE_MUTEX:
+		owner = mutex_get_owner(
+			(struct mutex *)hung_task_blocker_to_lock(blocker));
+		break;
+	case BLOCKER_TYPE_SEM:
+		owner = sem_last_holder(
+			(struct semaphore *)hung_task_blocker_to_lock(blocker));
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return;
+	}
+
 
 	if (unlikely(!owner)) {
-		pr_err("INFO: task %s:%d is blocked on a mutex, but the owner is not found.\n",
-			task->comm, task->pid);
+		switch (blocker_type) {
+		case BLOCKER_TYPE_MUTEX:
+			pr_err("INFO: task %s:%d is blocked on a mutex, but the owner is not found.\n",
+			       task->comm, task->pid);
+			break;
+		case BLOCKER_TYPE_SEM:
+			pr_err("INFO: task %s:%d is blocked on a semaphore, but the last holder is not found.\n",
+			       task->comm, task->pid);
+			break;
+		}
 		return;
 	}
 
 	/* Ensure the owner information is correct. */
 	for_each_process_thread(g, t) {
-		if ((unsigned long)t == owner) {
+		if ((unsigned long)t != owner)
+			continue;
+
+		switch (blocker_type) {
+		case BLOCKER_TYPE_MUTEX:
 			pr_err("INFO: task %s:%d is blocked on a mutex likely owned by task %s:%d.\n",
-				task->comm, task->pid, t->comm, t->pid);
-			sched_show_task(t);
-			return;
+			       task->comm, task->pid, t->comm, t->pid);
+			break;
+		case BLOCKER_TYPE_SEM:
+			pr_err("INFO: task %s:%d blocked on a semaphore likely last held by task %s:%d\n",
+			       task->comm, task->pid, t->comm, t->pid);
+			break;
 		}
+		sched_show_task(t);
+		return;
 	}
 }
 #else