* [PATCH v3 1/3] hung_task: replace blocker_mutex with encoded blocker
2025-03-19 8:11 [PATCH v3 0/3] hung_task: extend blocking task stacktrace dump to semaphore Lance Yang
@ 2025-03-19 8:11 ` Lance Yang
2025-03-19 13:51 ` Masami Hiramatsu
2025-03-19 8:11 ` [PATCH v3 2/3] hung_task: show the blocker task if the task is hung on semaphore Lance Yang
2025-03-19 8:11 ` [PATCH v3 3/3] samples: extend hung_task detector test with semaphore support Lance Yang
2 siblings, 1 reply; 8+ messages in thread
From: Lance Yang @ 2025-03-19 8:11 UTC (permalink / raw)
To: akpm
Cc: will, peterz, mingo, longman, mhiramat, anna.schumaker,
boqun.feng, joel.granados, kent.overstreet, leonylgao,
linux-kernel, rostedt, senozhatsky, tfiga, amaindex, jstultz,
Lance Yang, Mingzhe Yang
This patch replaces 'struct mutex *blocker_mutex' with 'unsigned long
blocker', as only one blocker is active at a time.
The blocker filed can store both the lock addrees and the lock type, with
LSB used to encode the type as Masami suggested, making it easier to extend
the feature to cover other types of locks.
Also, once the lock type is determined, we can directly extract the address
and cast it to a lock pointer ;)
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Mingzhe Yang <mingzhe.yang@ly.com>
Signed-off-by: Lance Yang <ioworker0@gmail.com>
---
include/linux/hung_task.h | 93 +++++++++++++++++++++++++++++++++++++++
include/linux/sched.h | 2 +-
kernel/hung_task.c | 12 ++---
kernel/locking/mutex.c | 5 ++-
4 files changed, 104 insertions(+), 8 deletions(-)
create mode 100644 include/linux/hung_task.h
diff --git a/include/linux/hung_task.h b/include/linux/hung_task.h
new file mode 100644
index 000000000000..c772bca6775b
--- /dev/null
+++ b/include/linux/hung_task.h
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Detect Hung Task: detecting tasks stuck in D state
+ *
+ * Copyright (C) 2025 Tongcheng Travel (www.ly.com)
+ * Author: Lance Yang <mingzhe.yang@ly.com>
+ */
+#ifndef __LINUX_HUNG_TASK_H
+#define __LINUX_HUNG_TASK_H
+
+#include <linux/bug.h>
+#include <linux/sched.h>
+#include <linux/compiler.h>
+
+/*
+ * @blocker: Combines lock address and blocking type.
+ *
+ * Since lock pointers are at least 4-byte aligned(32-bit) or 8-byte
+ * aligned(64-bit). This leaves the 2 least bits (LSBs) of the pointer
+ * always zero. So we can use these bits to encode the specific blocking
+ * type.
+ *
+ * Type encoding:
+ * 00 - Blocked on mutex (BLOCKER_TYPE_MUTEX)
+ * 01 - Blocked on semaphore (BLOCKER_TYPE_SEM)
+ * 10 - Blocked on rt-mutex (BLOCKER_TYPE_RTMUTEX)
+ * 11 - Blocked on rw-semaphore (BLOCKER_TYPE_RWSEM)
+ */
+#define BLOCKER_TYPE_MUTEX 0x00UL
+#define BLOCKER_TYPE_SEM 0x01UL
+#define BLOCKER_TYPE_RTMUTEX 0x02UL
+#define BLOCKER_TYPE_RWSEM 0x03UL
+
+#define BLOCKER_TYPE_MASK 0x03UL
+
+#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
+static inline void hung_task_set_blocker(void *lock, unsigned long type)
+{
+ unsigned long lock_ptr = (unsigned long)lock;
+
+ WARN_ON_ONCE(!lock_ptr);
+ WARN_ON_ONCE(READ_ONCE(current->blocker));
+
+ /*
+ * If the lock pointer matches the BLOCKER_TYPE_MASK, return
+ * without writing anything.
+ */
+ if (WARN_ON_ONCE(lock_ptr & BLOCKER_TYPE_MASK))
+ return;
+
+ WRITE_ONCE(current->blocker, lock_ptr | type);
+}
+
+static inline void hung_task_clear_blocker(void)
+{
+ WARN_ON_ONCE(!READ_ONCE(current->blocker));
+
+ WRITE_ONCE(current->blocker, 0UL);
+}
+
+static inline bool hung_task_blocker_is_type(unsigned long blocker,
+ unsigned long type)
+{
+ WARN_ON_ONCE(!blocker);
+
+ return (blocker & BLOCKER_TYPE_MASK) == type;
+}
+
+static inline void *hung_task_blocker_to_lock(unsigned long blocker)
+{
+ WARN_ON_ONCE(!blocker);
+
+ return (void *)(blocker & ~BLOCKER_TYPE_MASK);
+}
+#else
+static inline void hung_task_set_blocker(void *lock, unsigned long type)
+{
+}
+static inline void hung_task_clear_blocker(void)
+{
+}
+static inline bool hung_task_blocker_is_type(unsigned long blocker,
+ unsigned long type)
+{
+ return false;
+}
+static inline void *hung_task_blocker_to_lock(unsigned long blocker)
+{
+ return NULL;
+}
+#endif
+
+#endif /* __LINUX_HUNG_TASK_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1419d94c8e87..f27060dac499 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1218,7 +1218,7 @@ struct task_struct {
#endif
#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
- struct mutex *blocker_mutex;
+ unsigned long blocker;
#endif
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index dc898ec93463..75dc1048f2c1 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -22,6 +22,7 @@
#include <linux/sched/signal.h>
#include <linux/sched/debug.h>
#include <linux/sched/sysctl.h>
+#include <linux/hung_task.h>
#include <trace/events/sched.h>
@@ -98,16 +99,17 @@ static struct notifier_block panic_block = {
static void debug_show_blocker(struct task_struct *task)
{
struct task_struct *g, *t;
- unsigned long owner;
- struct mutex *lock;
+ unsigned long owner, blocker;
RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "No rcu lock held");
- lock = READ_ONCE(task->blocker_mutex);
- if (!lock)
+ blocker = READ_ONCE(task->blocker);
+ if (!blocker || !hung_task_blocker_is_type(blocker, BLOCKER_TYPE_MUTEX))
return;
- owner = mutex_get_owner(lock);
+ owner = mutex_get_owner(
+ (struct mutex *)hung_task_blocker_to_lock(blocker));
+
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);
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 6a543c204a14..e9ef70a6cb5f 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -29,6 +29,7 @@
#include <linux/interrupt.h>
#include <linux/debug_locks.h>
#include <linux/osq_lock.h>
+#include <linux/hung_task.h>
#define CREATE_TRACE_POINTS
#include <trace/events/lock.h>
@@ -189,7 +190,7 @@ __mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
struct list_head *list)
{
#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
- WRITE_ONCE(current->blocker_mutex, lock);
+ hung_task_set_blocker(lock, BLOCKER_TYPE_MUTEX);
#endif
debug_mutex_add_waiter(lock, waiter, current);
@@ -207,7 +208,7 @@ __mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter)
debug_mutex_remove_waiter(lock, waiter, current);
#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
- WRITE_ONCE(current->blocker_mutex, NULL);
+ hung_task_clear_blocker();
#endif
}
--
2.45.2
^ permalink raw reply related [flat|nested] 8+ messages in thread* Re: [PATCH v3 1/3] hung_task: replace blocker_mutex with encoded blocker
2025-03-19 8:11 ` [PATCH v3 1/3] hung_task: replace blocker_mutex with encoded blocker Lance Yang
@ 2025-03-19 13:51 ` Masami Hiramatsu
0 siblings, 0 replies; 8+ messages in thread
From: Masami Hiramatsu @ 2025-03-19 13:51 UTC (permalink / raw)
To: Lance Yang
Cc: akpm, will, peterz, mingo, longman, mhiramat, anna.schumaker,
boqun.feng, joel.granados, kent.overstreet, leonylgao,
linux-kernel, rostedt, senozhatsky, tfiga, amaindex, jstultz,
Mingzhe Yang
On Wed, 19 Mar 2025 16:11:36 +0800
Lance Yang <ioworker0@gmail.com> wrote:
> This patch replaces 'struct mutex *blocker_mutex' with 'unsigned long
> blocker', as only one blocker is active at a time.
>
> The blocker filed can store both the lock addrees and the lock type, with
> LSB used to encode the type as Masami suggested, making it easier to extend
> the feature to cover other types of locks.
>
> Also, once the lock type is determined, we can directly extract the address
> and cast it to a lock pointer ;)
This looks good to me.
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Thank you!
>
> Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
> Signed-off-by: Mingzhe Yang <mingzhe.yang@ly.com>
> Signed-off-by: Lance Yang <ioworker0@gmail.com>
> ---
> include/linux/hung_task.h | 93 +++++++++++++++++++++++++++++++++++++++
> include/linux/sched.h | 2 +-
> kernel/hung_task.c | 12 ++---
> kernel/locking/mutex.c | 5 ++-
> 4 files changed, 104 insertions(+), 8 deletions(-)
> create mode 100644 include/linux/hung_task.h
>
> diff --git a/include/linux/hung_task.h b/include/linux/hung_task.h
> new file mode 100644
> index 000000000000..c772bca6775b
> --- /dev/null
> +++ b/include/linux/hung_task.h
> @@ -0,0 +1,93 @@
> +/* SPDX-License-Identifier: GPL-2.0-only */
> +/*
> + * Detect Hung Task: detecting tasks stuck in D state
> + *
> + * Copyright (C) 2025 Tongcheng Travel (www.ly.com)
> + * Author: Lance Yang <mingzhe.yang@ly.com>
> + */
> +#ifndef __LINUX_HUNG_TASK_H
> +#define __LINUX_HUNG_TASK_H
> +
> +#include <linux/bug.h>
> +#include <linux/sched.h>
> +#include <linux/compiler.h>
> +
> +/*
> + * @blocker: Combines lock address and blocking type.
> + *
> + * Since lock pointers are at least 4-byte aligned(32-bit) or 8-byte
> + * aligned(64-bit). This leaves the 2 least bits (LSBs) of the pointer
> + * always zero. So we can use these bits to encode the specific blocking
> + * type.
> + *
> + * Type encoding:
> + * 00 - Blocked on mutex (BLOCKER_TYPE_MUTEX)
> + * 01 - Blocked on semaphore (BLOCKER_TYPE_SEM)
> + * 10 - Blocked on rt-mutex (BLOCKER_TYPE_RTMUTEX)
> + * 11 - Blocked on rw-semaphore (BLOCKER_TYPE_RWSEM)
> + */
> +#define BLOCKER_TYPE_MUTEX 0x00UL
> +#define BLOCKER_TYPE_SEM 0x01UL
> +#define BLOCKER_TYPE_RTMUTEX 0x02UL
> +#define BLOCKER_TYPE_RWSEM 0x03UL
> +
> +#define BLOCKER_TYPE_MASK 0x03UL
> +
> +#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
> +static inline void hung_task_set_blocker(void *lock, unsigned long type)
> +{
> + unsigned long lock_ptr = (unsigned long)lock;
> +
> + WARN_ON_ONCE(!lock_ptr);
> + WARN_ON_ONCE(READ_ONCE(current->blocker));
> +
> + /*
> + * If the lock pointer matches the BLOCKER_TYPE_MASK, return
> + * without writing anything.
> + */
> + if (WARN_ON_ONCE(lock_ptr & BLOCKER_TYPE_MASK))
> + return;
> +
> + WRITE_ONCE(current->blocker, lock_ptr | type);
> +}
> +
> +static inline void hung_task_clear_blocker(void)
> +{
> + WARN_ON_ONCE(!READ_ONCE(current->blocker));
> +
> + WRITE_ONCE(current->blocker, 0UL);
> +}
> +
> +static inline bool hung_task_blocker_is_type(unsigned long blocker,
> + unsigned long type)
> +{
> + WARN_ON_ONCE(!blocker);
> +
> + return (blocker & BLOCKER_TYPE_MASK) == type;
> +}
> +
> +static inline void *hung_task_blocker_to_lock(unsigned long blocker)
> +{
> + WARN_ON_ONCE(!blocker);
> +
> + return (void *)(blocker & ~BLOCKER_TYPE_MASK);
> +}
> +#else
> +static inline void hung_task_set_blocker(void *lock, unsigned long type)
> +{
> +}
> +static inline void hung_task_clear_blocker(void)
> +{
> +}
> +static inline bool hung_task_blocker_is_type(unsigned long blocker,
> + unsigned long type)
> +{
> + return false;
> +}
> +static inline void *hung_task_blocker_to_lock(unsigned long blocker)
> +{
> + return NULL;
> +}
> +#endif
> +
> +#endif /* __LINUX_HUNG_TASK_H */
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 1419d94c8e87..f27060dac499 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1218,7 +1218,7 @@ struct task_struct {
> #endif
>
> #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
> - struct mutex *blocker_mutex;
> + unsigned long blocker;
> #endif
>
> #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
> diff --git a/kernel/hung_task.c b/kernel/hung_task.c
> index dc898ec93463..75dc1048f2c1 100644
> --- a/kernel/hung_task.c
> +++ b/kernel/hung_task.c
> @@ -22,6 +22,7 @@
> #include <linux/sched/signal.h>
> #include <linux/sched/debug.h>
> #include <linux/sched/sysctl.h>
> +#include <linux/hung_task.h>
>
> #include <trace/events/sched.h>
>
> @@ -98,16 +99,17 @@ static struct notifier_block panic_block = {
> static void debug_show_blocker(struct task_struct *task)
> {
> struct task_struct *g, *t;
> - unsigned long owner;
> - struct mutex *lock;
> + unsigned long owner, blocker;
>
> RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "No rcu lock held");
>
> - lock = READ_ONCE(task->blocker_mutex);
> - if (!lock)
> + blocker = READ_ONCE(task->blocker);
> + if (!blocker || !hung_task_blocker_is_type(blocker, BLOCKER_TYPE_MUTEX))
> return;
>
> - owner = mutex_get_owner(lock);
> + owner = mutex_get_owner(
> + (struct mutex *)hung_task_blocker_to_lock(blocker));
> +
> 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);
> diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
> index 6a543c204a14..e9ef70a6cb5f 100644
> --- a/kernel/locking/mutex.c
> +++ b/kernel/locking/mutex.c
> @@ -29,6 +29,7 @@
> #include <linux/interrupt.h>
> #include <linux/debug_locks.h>
> #include <linux/osq_lock.h>
> +#include <linux/hung_task.h>
>
> #define CREATE_TRACE_POINTS
> #include <trace/events/lock.h>
> @@ -189,7 +190,7 @@ __mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
> struct list_head *list)
> {
> #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
> - WRITE_ONCE(current->blocker_mutex, lock);
> + hung_task_set_blocker(lock, BLOCKER_TYPE_MUTEX);
> #endif
> debug_mutex_add_waiter(lock, waiter, current);
>
> @@ -207,7 +208,7 @@ __mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter)
>
> debug_mutex_remove_waiter(lock, waiter, current);
> #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
> - WRITE_ONCE(current->blocker_mutex, NULL);
> + hung_task_clear_blocker();
> #endif
> }
>
> --
> 2.45.2
>
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply [flat|nested] 8+ messages in thread
* [PATCH v3 2/3] hung_task: show the blocker task if the task is hung on semaphore
2025-03-19 8:11 [PATCH v3 0/3] hung_task: extend blocking task stacktrace dump to semaphore Lance Yang
2025-03-19 8:11 ` [PATCH v3 1/3] hung_task: replace blocker_mutex with encoded blocker Lance Yang
@ 2025-03-19 8:11 ` Lance Yang
2025-03-19 13:53 ` Masami Hiramatsu
2025-03-19 8:11 ` [PATCH v3 3/3] samples: extend hung_task detector test with semaphore support Lance Yang
2 siblings, 1 reply; 8+ messages in thread
From: Lance Yang @ 2025-03-19 8:11 UTC (permalink / raw)
To: akpm
Cc: will, peterz, mingo, longman, mhiramat, anna.schumaker,
boqun.feng, joel.granados, kent.overstreet, leonylgao,
linux-kernel, rostedt, senozhatsky, tfiga, amaindex, jstultz,
Lance Yang, Mingzhe Yang
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:
[Thu Mar 13 15:18:38 2025] INFO: task cat:1803 blocked for more than 122 seconds.
[Thu Mar 13 15:18:38 2025] Tainted: G OE 6.14.0-rc3+ #14
[Thu Mar 13 15:18:38 2025] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[Thu Mar 13 15:18:38 2025] task:cat state:D stack:0 pid:1803 tgid:1803 ppid:1057 task_flags:0x400000 flags:0x00000004
[Thu Mar 13 15:18:38 2025] Call trace:
[Thu Mar 13 15:18:38 2025] __switch_to+0x1ec/0x380 (T)
[Thu Mar 13 15:18:38 2025] __schedule+0xc30/0x44f8
[Thu Mar 13 15:18:38 2025] schedule+0xb8/0x3b0
[Thu Mar 13 15:18:38 2025] schedule_timeout+0x1d0/0x208
[Thu Mar 13 15:18:38 2025] __down_common+0x2d4/0x6f8
[Thu Mar 13 15:18:38 2025] __down+0x24/0x50
[Thu Mar 13 15:18:38 2025] down+0xd0/0x140
[Thu Mar 13 15:18:38 2025] read_dummy+0x3c/0xa0 [hung_task_sem]
[Thu Mar 13 15:18:38 2025] full_proxy_read+0xfc/0x1d0
[Thu Mar 13 15:18:38 2025] vfs_read+0x1a0/0x858
[Thu Mar 13 15:18:38 2025] ksys_read+0x100/0x220
[Thu Mar 13 15:18:38 2025] __arm64_sys_read+0x78/0xc8
[Thu Mar 13 15:18:38 2025] invoke_syscall+0xd8/0x278
[Thu Mar 13 15:18:38 2025] el0_svc_common.constprop.0+0xb8/0x298
[Thu Mar 13 15:18:38 2025] do_el0_svc+0x4c/0x88
[Thu Mar 13 15:18:38 2025] el0_svc+0x44/0x108
[Thu Mar 13 15:18:38 2025] el0t_64_sync_handler+0x134/0x160
[Thu Mar 13 15:18:38 2025] el0t_64_sync+0x1b8/0x1c0
[Thu Mar 13 15:18:38 2025] INFO: task cat:1803 blocked on a semaphore likely last held by task cat:1802
[Thu Mar 13 15:18:38 2025] task:cat state:S stack:0 pid:1802 tgid:1802 ppid:1057 task_flags:0x400000 flags:0x00000004
[Thu Mar 13 15:18:38 2025] Call trace:
[Thu Mar 13 15:18:38 2025] __switch_to+0x1ec/0x380 (T)
[Thu Mar 13 15:18:38 2025] __schedule+0xc30/0x44f8
[Thu Mar 13 15:18:38 2025] schedule+0xb8/0x3b0
[Thu Mar 13 15:18:38 2025] schedule_timeout+0xf4/0x208
[Thu Mar 13 15:18:38 2025] msleep_interruptible+0x70/0x130
[Thu Mar 13 15:18:38 2025] read_dummy+0x48/0xa0 [hung_task_sem]
[Thu Mar 13 15:18:38 2025] full_proxy_read+0xfc/0x1d0
[Thu Mar 13 15:18:38 2025] vfs_read+0x1a0/0x858
[Thu Mar 13 15:18:38 2025] ksys_read+0x100/0x220
[Thu Mar 13 15:18:38 2025] __arm64_sys_read+0x78/0xc8
[Thu Mar 13 15:18:38 2025] invoke_syscall+0xd8/0x278
[Thu Mar 13 15:18:38 2025] el0_svc_common.constprop.0+0xb8/0x298
[Thu Mar 13 15:18:38 2025] do_el0_svc+0x4c/0x88
[Thu Mar 13 15:18:38 2025] el0_svc+0x44/0x108
[Thu Mar 13 15:18:38 2025] el0t_64_sync_handler+0x134/0x160
[Thu Mar 13 15:18:38 2025] el0t_64_sync+0x1b8/0x1c0
[1] https://lore.kernel.org/all/174046694331.2194069.15472952050240807469.stgit@mhiramat.tok.corp.google.com
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Mingzhe Yang <mingzhe.yang@ly.com>
Signed-off-by: Lance Yang <ioworker0@gmail.com>
---
include/linux/semaphore.h | 15 ++++++++++-
kernel/hung_task.c | 45 +++++++++++++++++++++++++--------
kernel/locking/semaphore.c | 52 +++++++++++++++++++++++++++++++++-----
3 files changed, 95 insertions(+), 17 deletions(-)
diff --git a/include/linux/semaphore.h b/include/linux/semaphore.h
index 04655faadc2d..89706157e622 100644
--- a/include/linux/semaphore.h
+++ b/include/linux/semaphore.h
@@ -16,13 +16,25 @@ struct semaphore {
raw_spinlock_t lock;
unsigned int count;
struct list_head wait_list;
+
+#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
+ unsigned long last_holder;
+#endif
};
+#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
+#define __LAST_HOLDER_SEMAPHORE_INITIALIZER \
+ , .last_holder = 0UL
+#else
+#define __LAST_HOLDER_SEMAPHORE_INITIALIZER
+#endif
+
#define __SEMAPHORE_INITIALIZER(name, n) \
{ \
.lock = __RAW_SPIN_LOCK_UNLOCKED((name).lock), \
.count = n, \
- .wait_list = LIST_HEAD_INIT((name).wait_list), \
+ .wait_list = LIST_HEAD_INIT((name).wait_list) \
+ __LAST_HOLDER_SEMAPHORE_INITIALIZER \
}
/*
@@ -47,5 +59,6 @@ extern int __must_check down_killable(struct semaphore *sem);
extern int __must_check down_trylock(struct semaphore *sem);
extern int __must_check down_timeout(struct semaphore *sem, long jiffies);
extern void up(struct semaphore *sem);
+extern unsigned long sem_last_holder(struct semaphore *sem);
#endif /* __LINUX_SEMAPHORE_H */
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 75dc1048f2c1..1403e71df039 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -99,31 +99,56 @@ 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_lock_type;
RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "No rcu lock held");
blocker = READ_ONCE(task->blocker);
- if (!blocker || !hung_task_blocker_is_type(blocker, BLOCKER_TYPE_MUTEX))
+ if (!blocker)
return;
- owner = mutex_get_owner(
- (struct mutex *)hung_task_blocker_to_lock(blocker));
+ if (hung_task_blocker_is_type(blocker, BLOCKER_TYPE_MUTEX)) {
+ owner = mutex_get_owner(
+ (struct mutex *)hung_task_blocker_to_lock(blocker));
+ blocker_lock_type = BLOCKER_TYPE_MUTEX;
+ } else if (hung_task_blocker_is_type(blocker, BLOCKER_TYPE_SEM)) {
+ owner = sem_last_holder(
+ (struct semaphore *)hung_task_blocker_to_lock(blocker));
+ blocker_lock_type = BLOCKER_TYPE_SEM;
+ } else
+ 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_lock_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_lock_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
diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index 34bfae72f295..3d06d4adc05b 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -33,12 +33,14 @@
#include <linux/spinlock.h>
#include <linux/ftrace.h>
#include <trace/events/lock.h>
+#include <linux/hung_task.h>
static noinline void __down(struct semaphore *sem);
static noinline int __down_interruptible(struct semaphore *sem);
static noinline int __down_killable(struct semaphore *sem);
static noinline int __down_timeout(struct semaphore *sem, long timeout);
static noinline void __up(struct semaphore *sem);
+static inline void __sem_acquire(struct semaphore *sem);
/**
* down - acquire the semaphore
@@ -58,7 +60,7 @@ void __sched down(struct semaphore *sem)
might_sleep();
raw_spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
- sem->count--;
+ __sem_acquire(sem);
else
__down(sem);
raw_spin_unlock_irqrestore(&sem->lock, flags);
@@ -82,7 +84,7 @@ int __sched down_interruptible(struct semaphore *sem)
might_sleep();
raw_spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
- sem->count--;
+ __sem_acquire(sem);
else
result = __down_interruptible(sem);
raw_spin_unlock_irqrestore(&sem->lock, flags);
@@ -109,7 +111,7 @@ int __sched down_killable(struct semaphore *sem)
might_sleep();
raw_spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
- sem->count--;
+ __sem_acquire(sem);
else
result = __down_killable(sem);
raw_spin_unlock_irqrestore(&sem->lock, flags);
@@ -139,7 +141,7 @@ int __sched down_trylock(struct semaphore *sem)
raw_spin_lock_irqsave(&sem->lock, flags);
count = sem->count - 1;
if (likely(count >= 0))
- sem->count = count;
+ __sem_acquire(sem);
raw_spin_unlock_irqrestore(&sem->lock, flags);
return (count < 0);
@@ -164,7 +166,7 @@ int __sched down_timeout(struct semaphore *sem, long timeout)
might_sleep();
raw_spin_lock_irqsave(&sem->lock, flags);
if (likely(sem->count > 0))
- sem->count--;
+ __sem_acquire(sem);
else
result = __down_timeout(sem, timeout);
raw_spin_unlock_irqrestore(&sem->lock, flags);
@@ -185,6 +187,12 @@ void __sched up(struct semaphore *sem)
unsigned long flags;
raw_spin_lock_irqsave(&sem->lock, flags);
+
+#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
+ if (READ_ONCE(sem->last_holder) == (unsigned long)current)
+ WRITE_ONCE(sem->last_holder, 0UL);
+#endif
+
if (likely(list_empty(&sem->wait_list)))
sem->count++;
else
@@ -224,8 +232,12 @@ static inline int __sched ___down_common(struct semaphore *sem, long state,
raw_spin_unlock_irq(&sem->lock);
timeout = schedule_timeout(timeout);
raw_spin_lock_irq(&sem->lock);
- if (waiter.up)
+ if (waiter.up) {
+#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
+ WRITE_ONCE(sem->last_holder, (unsigned long)current);
+#endif
return 0;
+ }
}
timed_out:
@@ -242,10 +254,18 @@ static inline int __sched __down_common(struct semaphore *sem, long state,
{
int ret;
+#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
+ hung_task_set_blocker(sem, BLOCKER_TYPE_SEM);
+#endif
+
trace_contention_begin(sem, 0);
ret = ___down_common(sem, state, timeout);
trace_contention_end(sem, ret);
+#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
+ hung_task_clear_blocker();
+#endif
+
return ret;
}
@@ -277,3 +297,23 @@ static noinline void __sched __up(struct semaphore *sem)
waiter->up = true;
wake_up_process(waiter->task);
}
+
+#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
+unsigned long sem_last_holder(struct semaphore *sem)
+{
+ return READ_ONCE(sem->last_holder);
+}
+#else
+unsigned long sem_last_holder(struct semaphore *sem)
+{
+ return 0UL;
+}
+#endif
+
+static inline void __sem_acquire(struct semaphore *sem)
+{
+ sem->count--;
+#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
+ WRITE_ONCE(sem->last_holder, (unsigned long)current);
+#endif
+}
--
2.45.2
^ permalink raw reply related [flat|nested] 8+ messages in thread* Re: [PATCH v3 2/3] hung_task: show the blocker task if the task is hung on semaphore
2025-03-19 8:11 ` [PATCH v3 2/3] hung_task: show the blocker task if the task is hung on semaphore Lance Yang
@ 2025-03-19 13:53 ` Masami Hiramatsu
0 siblings, 0 replies; 8+ messages in thread
From: Masami Hiramatsu @ 2025-03-19 13:53 UTC (permalink / raw)
To: Lance Yang
Cc: akpm, will, peterz, mingo, longman, mhiramat, anna.schumaker,
boqun.feng, joel.granados, kent.overstreet, leonylgao,
linux-kernel, rostedt, senozhatsky, tfiga, amaindex, jstultz,
Mingzhe Yang
On Wed, 19 Mar 2025 16:11:37 +0800
Lance Yang <ioworker0@gmail.com> wrote:
> 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:
>
> [Thu Mar 13 15:18:38 2025] INFO: task cat:1803 blocked for more than 122 seconds.
> [Thu Mar 13 15:18:38 2025] Tainted: G OE 6.14.0-rc3+ #14
> [Thu Mar 13 15:18:38 2025] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> [Thu Mar 13 15:18:38 2025] task:cat state:D stack:0 pid:1803 tgid:1803 ppid:1057 task_flags:0x400000 flags:0x00000004
> [Thu Mar 13 15:18:38 2025] Call trace:
> [Thu Mar 13 15:18:38 2025] __switch_to+0x1ec/0x380 (T)
> [Thu Mar 13 15:18:38 2025] __schedule+0xc30/0x44f8
> [Thu Mar 13 15:18:38 2025] schedule+0xb8/0x3b0
> [Thu Mar 13 15:18:38 2025] schedule_timeout+0x1d0/0x208
> [Thu Mar 13 15:18:38 2025] __down_common+0x2d4/0x6f8
> [Thu Mar 13 15:18:38 2025] __down+0x24/0x50
> [Thu Mar 13 15:18:38 2025] down+0xd0/0x140
> [Thu Mar 13 15:18:38 2025] read_dummy+0x3c/0xa0 [hung_task_sem]
> [Thu Mar 13 15:18:38 2025] full_proxy_read+0xfc/0x1d0
> [Thu Mar 13 15:18:38 2025] vfs_read+0x1a0/0x858
> [Thu Mar 13 15:18:38 2025] ksys_read+0x100/0x220
> [Thu Mar 13 15:18:38 2025] __arm64_sys_read+0x78/0xc8
> [Thu Mar 13 15:18:38 2025] invoke_syscall+0xd8/0x278
> [Thu Mar 13 15:18:38 2025] el0_svc_common.constprop.0+0xb8/0x298
> [Thu Mar 13 15:18:38 2025] do_el0_svc+0x4c/0x88
> [Thu Mar 13 15:18:38 2025] el0_svc+0x44/0x108
> [Thu Mar 13 15:18:38 2025] el0t_64_sync_handler+0x134/0x160
> [Thu Mar 13 15:18:38 2025] el0t_64_sync+0x1b8/0x1c0
> [Thu Mar 13 15:18:38 2025] INFO: task cat:1803 blocked on a semaphore likely last held by task cat:1802
> [Thu Mar 13 15:18:38 2025] task:cat state:S stack:0 pid:1802 tgid:1802 ppid:1057 task_flags:0x400000 flags:0x00000004
> [Thu Mar 13 15:18:38 2025] Call trace:
> [Thu Mar 13 15:18:38 2025] __switch_to+0x1ec/0x380 (T)
> [Thu Mar 13 15:18:38 2025] __schedule+0xc30/0x44f8
> [Thu Mar 13 15:18:38 2025] schedule+0xb8/0x3b0
> [Thu Mar 13 15:18:38 2025] schedule_timeout+0xf4/0x208
> [Thu Mar 13 15:18:38 2025] msleep_interruptible+0x70/0x130
> [Thu Mar 13 15:18:38 2025] read_dummy+0x48/0xa0 [hung_task_sem]
> [Thu Mar 13 15:18:38 2025] full_proxy_read+0xfc/0x1d0
> [Thu Mar 13 15:18:38 2025] vfs_read+0x1a0/0x858
> [Thu Mar 13 15:18:38 2025] ksys_read+0x100/0x220
> [Thu Mar 13 15:18:38 2025] __arm64_sys_read+0x78/0xc8
> [Thu Mar 13 15:18:38 2025] invoke_syscall+0xd8/0x278
> [Thu Mar 13 15:18:38 2025] el0_svc_common.constprop.0+0xb8/0x298
> [Thu Mar 13 15:18:38 2025] do_el0_svc+0x4c/0x88
> [Thu Mar 13 15:18:38 2025] el0_svc+0x44/0x108
> [Thu Mar 13 15:18:38 2025] el0t_64_sync_handler+0x134/0x160
> [Thu Mar 13 15:18:38 2025] el0t_64_sync+0x1b8/0x1c0
>
> [1] https://lore.kernel.org/all/174046694331.2194069.15472952050240807469.stgit@mhiramat.tok.corp.google.com
>
> Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
> Signed-off-by: Mingzhe Yang <mingzhe.yang@ly.com>
> Signed-off-by: Lance Yang <ioworker0@gmail.com>
> ---
> include/linux/semaphore.h | 15 ++++++++++-
> kernel/hung_task.c | 45 +++++++++++++++++++++++++--------
> kernel/locking/semaphore.c | 52 +++++++++++++++++++++++++++++++++-----
> 3 files changed, 95 insertions(+), 17 deletions(-)
>
> diff --git a/include/linux/semaphore.h b/include/linux/semaphore.h
> index 04655faadc2d..89706157e622 100644
> --- a/include/linux/semaphore.h
> +++ b/include/linux/semaphore.h
> @@ -16,13 +16,25 @@ struct semaphore {
> raw_spinlock_t lock;
> unsigned int count;
> struct list_head wait_list;
> +
> +#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
> + unsigned long last_holder;
> +#endif
> };
>
> +#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
> +#define __LAST_HOLDER_SEMAPHORE_INITIALIZER \
> + , .last_holder = 0UL
> +#else
> +#define __LAST_HOLDER_SEMAPHORE_INITIALIZER
> +#endif
> +
> #define __SEMAPHORE_INITIALIZER(name, n) \
> { \
> .lock = __RAW_SPIN_LOCK_UNLOCKED((name).lock), \
> .count = n, \
> - .wait_list = LIST_HEAD_INIT((name).wait_list), \
> + .wait_list = LIST_HEAD_INIT((name).wait_list) \
> + __LAST_HOLDER_SEMAPHORE_INITIALIZER \
> }
>
> /*
> @@ -47,5 +59,6 @@ extern int __must_check down_killable(struct semaphore *sem);
> extern int __must_check down_trylock(struct semaphore *sem);
> extern int __must_check down_timeout(struct semaphore *sem, long jiffies);
> extern void up(struct semaphore *sem);
> +extern unsigned long sem_last_holder(struct semaphore *sem);
>
> #endif /* __LINUX_SEMAPHORE_H */
> diff --git a/kernel/hung_task.c b/kernel/hung_task.c
> index 75dc1048f2c1..1403e71df039 100644
> --- a/kernel/hung_task.c
> +++ b/kernel/hung_task.c
> @@ -99,31 +99,56 @@ 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_lock_type;
>
> RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "No rcu lock held");
>
> blocker = READ_ONCE(task->blocker);
> - if (!blocker || !hung_task_blocker_is_type(blocker, BLOCKER_TYPE_MUTEX))
> + if (!blocker)
> return;
>
> - owner = mutex_get_owner(
> - (struct mutex *)hung_task_blocker_to_lock(blocker));
> + if (hung_task_blocker_is_type(blocker, BLOCKER_TYPE_MUTEX)) {
> + owner = mutex_get_owner(
> + (struct mutex *)hung_task_blocker_to_lock(blocker));
> + blocker_lock_type = BLOCKER_TYPE_MUTEX;
> + } else if (hung_task_blocker_is_type(blocker, BLOCKER_TYPE_SEM)) {
> + owner = sem_last_holder(
> + (struct semaphore *)hung_task_blocker_to_lock(blocker));
> + blocker_lock_type = BLOCKER_TYPE_SEM;
> + } else
> + return;
So if you fix above part I don't see any problem.
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Thank you!
>
> 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_lock_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_lock_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
> diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
> index 34bfae72f295..3d06d4adc05b 100644
> --- a/kernel/locking/semaphore.c
> +++ b/kernel/locking/semaphore.c
> @@ -33,12 +33,14 @@
> #include <linux/spinlock.h>
> #include <linux/ftrace.h>
> #include <trace/events/lock.h>
> +#include <linux/hung_task.h>
>
> static noinline void __down(struct semaphore *sem);
> static noinline int __down_interruptible(struct semaphore *sem);
> static noinline int __down_killable(struct semaphore *sem);
> static noinline int __down_timeout(struct semaphore *sem, long timeout);
> static noinline void __up(struct semaphore *sem);
> +static inline void __sem_acquire(struct semaphore *sem);
>
> /**
> * down - acquire the semaphore
> @@ -58,7 +60,7 @@ void __sched down(struct semaphore *sem)
> might_sleep();
> raw_spin_lock_irqsave(&sem->lock, flags);
> if (likely(sem->count > 0))
> - sem->count--;
> + __sem_acquire(sem);
> else
> __down(sem);
> raw_spin_unlock_irqrestore(&sem->lock, flags);
> @@ -82,7 +84,7 @@ int __sched down_interruptible(struct semaphore *sem)
> might_sleep();
> raw_spin_lock_irqsave(&sem->lock, flags);
> if (likely(sem->count > 0))
> - sem->count--;
> + __sem_acquire(sem);
> else
> result = __down_interruptible(sem);
> raw_spin_unlock_irqrestore(&sem->lock, flags);
> @@ -109,7 +111,7 @@ int __sched down_killable(struct semaphore *sem)
> might_sleep();
> raw_spin_lock_irqsave(&sem->lock, flags);
> if (likely(sem->count > 0))
> - sem->count--;
> + __sem_acquire(sem);
> else
> result = __down_killable(sem);
> raw_spin_unlock_irqrestore(&sem->lock, flags);
> @@ -139,7 +141,7 @@ int __sched down_trylock(struct semaphore *sem)
> raw_spin_lock_irqsave(&sem->lock, flags);
> count = sem->count - 1;
> if (likely(count >= 0))
> - sem->count = count;
> + __sem_acquire(sem);
> raw_spin_unlock_irqrestore(&sem->lock, flags);
>
> return (count < 0);
> @@ -164,7 +166,7 @@ int __sched down_timeout(struct semaphore *sem, long timeout)
> might_sleep();
> raw_spin_lock_irqsave(&sem->lock, flags);
> if (likely(sem->count > 0))
> - sem->count--;
> + __sem_acquire(sem);
> else
> result = __down_timeout(sem, timeout);
> raw_spin_unlock_irqrestore(&sem->lock, flags);
> @@ -185,6 +187,12 @@ void __sched up(struct semaphore *sem)
> unsigned long flags;
>
> raw_spin_lock_irqsave(&sem->lock, flags);
> +
> +#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
> + if (READ_ONCE(sem->last_holder) == (unsigned long)current)
> + WRITE_ONCE(sem->last_holder, 0UL);
> +#endif
> +
> if (likely(list_empty(&sem->wait_list)))
> sem->count++;
> else
> @@ -224,8 +232,12 @@ static inline int __sched ___down_common(struct semaphore *sem, long state,
> raw_spin_unlock_irq(&sem->lock);
> timeout = schedule_timeout(timeout);
> raw_spin_lock_irq(&sem->lock);
> - if (waiter.up)
> + if (waiter.up) {
> +#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
> + WRITE_ONCE(sem->last_holder, (unsigned long)current);
> +#endif
> return 0;
> + }
> }
>
> timed_out:
> @@ -242,10 +254,18 @@ static inline int __sched __down_common(struct semaphore *sem, long state,
> {
> int ret;
>
> +#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
> + hung_task_set_blocker(sem, BLOCKER_TYPE_SEM);
> +#endif
> +
> trace_contention_begin(sem, 0);
> ret = ___down_common(sem, state, timeout);
> trace_contention_end(sem, ret);
>
> +#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
> + hung_task_clear_blocker();
> +#endif
> +
> return ret;
> }
>
> @@ -277,3 +297,23 @@ static noinline void __sched __up(struct semaphore *sem)
> waiter->up = true;
> wake_up_process(waiter->task);
> }
> +
> +#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
> +unsigned long sem_last_holder(struct semaphore *sem)
> +{
> + return READ_ONCE(sem->last_holder);
> +}
> +#else
> +unsigned long sem_last_holder(struct semaphore *sem)
> +{
> + return 0UL;
> +}
> +#endif
> +
> +static inline void __sem_acquire(struct semaphore *sem)
> +{
> + sem->count--;
> +#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
> + WRITE_ONCE(sem->last_holder, (unsigned long)current);
> +#endif
> +}
> --
> 2.45.2
>
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply [flat|nested] 8+ messages in thread
* [PATCH v3 3/3] samples: extend hung_task detector test with semaphore support
2025-03-19 8:11 [PATCH v3 0/3] hung_task: extend blocking task stacktrace dump to semaphore Lance Yang
2025-03-19 8:11 ` [PATCH v3 1/3] hung_task: replace blocker_mutex with encoded blocker Lance Yang
2025-03-19 8:11 ` [PATCH v3 2/3] hung_task: show the blocker task if the task is hung on semaphore Lance Yang
@ 2025-03-19 8:11 ` Lance Yang
2025-03-19 13:49 ` Masami Hiramatsu
2 siblings, 1 reply; 8+ messages in thread
From: Lance Yang @ 2025-03-19 8:11 UTC (permalink / raw)
To: akpm
Cc: will, peterz, mingo, longman, mhiramat, anna.schumaker,
boqun.feng, joel.granados, kent.overstreet, leonylgao,
linux-kernel, rostedt, senozhatsky, tfiga, amaindex, jstultz,
Lance Yang
From: Zi Li <amaindex@outlook.com>
Extend the existing hung_task detector test module to support multiple lock
types, including mutex and semaphore, with room for future additions (e.g.,
spinlock, etc.). This module creates dummy files under <debugfs>/hung_task,
such as 'mutex' and 'semaphore'. The read process on any of these files will
sleep for enough long time (256 seconds) while holding the respective lock.
As a result, the second process will wait on the lock for a prolonged
duration and be detected by the hung_task detector.
This change unifies the previous mutex-only sample into a single,
extensible hung_task_tests module, reducing code duplication and improving
maintainability.
Usage is:
> cd /sys/kernel/debug/hung_task
> cat mutex & cat mutex # Test mutex blocking
> cat semaphore & cat semaphore # Test semaphore blocking
Update the Kconfig description to reflect multiple debugfs files support.
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Lance Yang <ioworker0@gmail.com>
Signed-off-by: Zi Li <amaindex@outlook.com>
---
samples/Kconfig | 9 +--
samples/hung_task/Makefile | 2 +-
samples/hung_task/hung_task_mutex.c | 66 --------------------
samples/hung_task/hung_task_tests.c | 97 +++++++++++++++++++++++++++++
4 files changed, 103 insertions(+), 71 deletions(-)
delete mode 100644 samples/hung_task/hung_task_mutex.c
create mode 100644 samples/hung_task/hung_task_tests.c
diff --git a/samples/Kconfig b/samples/Kconfig
index 09011be2391a..753ed1f170b5 100644
--- a/samples/Kconfig
+++ b/samples/Kconfig
@@ -304,10 +304,11 @@ config SAMPLE_HUNG_TASK
tristate "Hung task detector test code"
depends on DETECT_HUNG_TASK && DEBUG_FS
help
- Build a module which provide a simple debugfs file. If user reads
- the file, it will sleep long time (256 seconds) with holding a
- mutex. Thus if there are 2 or more processes read this file, it
- will be detected by the hung_task watchdog.
+ Build a module that provides debugfs files (e.g., mutex, semaphore,
+ etc.) under <debugfs>/hung_task. If user reads one of these files,
+ it will sleep long time (256 seconds) with holding a lock. Thus,
+ if 2 or more processes read the same file concurrently, it will
+ be detected by the hung_task watchdog.
source "samples/rust/Kconfig"
diff --git a/samples/hung_task/Makefile b/samples/hung_task/Makefile
index fe9dde799880..86036f1a204d 100644
--- a/samples/hung_task/Makefile
+++ b/samples/hung_task/Makefile
@@ -1,2 +1,2 @@
# SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_SAMPLE_HUNG_TASK) += hung_task_mutex.o
\ No newline at end of file
+obj-$(CONFIG_SAMPLE_HUNG_TASK) += hung_task_tests.o
diff --git a/samples/hung_task/hung_task_mutex.c b/samples/hung_task/hung_task_mutex.c
deleted file mode 100644
index 7a29f2246d22..000000000000
--- a/samples/hung_task/hung_task_mutex.c
+++ /dev/null
@@ -1,66 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * hung_task_mutex.c - Sample code which causes hung task by mutex
- *
- * Usage: load this module and read `<debugfs>/hung_task/mutex`
- * by 2 or more processes.
- *
- * This is for testing kernel hung_task error message.
- * Note that this will make your system freeze and maybe
- * cause panic. So do not use this except for the test.
- */
-
-#include <linux/debugfs.h>
-#include <linux/delay.h>
-#include <linux/fs.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-
-#define HUNG_TASK_DIR "hung_task"
-#define HUNG_TASK_FILE "mutex"
-#define SLEEP_SECOND 256
-
-static const char dummy_string[] = "This is a dummy string.";
-static DEFINE_MUTEX(dummy_mutex);
-struct dentry *hung_task_dir;
-
-static ssize_t read_dummy(struct file *file, char __user *user_buf,
- size_t count, loff_t *ppos)
-{
- /* If the second task waits on the lock, it is uninterruptible sleep. */
- guard(mutex)(&dummy_mutex);
-
- /* When the first task sleep here, it is interruptible. */
- msleep_interruptible(SLEEP_SECOND * 1000);
-
- return simple_read_from_buffer(user_buf, count, ppos,
- dummy_string, sizeof(dummy_string));
-}
-
-static const struct file_operations hung_task_fops = {
- .read = read_dummy,
-};
-
-static int __init hung_task_sample_init(void)
-{
- hung_task_dir = debugfs_create_dir(HUNG_TASK_DIR, NULL);
- if (IS_ERR(hung_task_dir))
- return PTR_ERR(hung_task_dir);
-
- debugfs_create_file(HUNG_TASK_FILE, 0400, hung_task_dir,
- NULL, &hung_task_fops);
-
- return 0;
-}
-
-static void __exit hung_task_sample_exit(void)
-{
- debugfs_remove_recursive(hung_task_dir);
-}
-
-module_init(hung_task_sample_init);
-module_exit(hung_task_sample_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Masami Hiramatsu");
-MODULE_DESCRIPTION("Simple sleep under mutex file for testing hung task");
diff --git a/samples/hung_task/hung_task_tests.c b/samples/hung_task/hung_task_tests.c
new file mode 100644
index 000000000000..a5c09bd3a47d
--- /dev/null
+++ b/samples/hung_task/hung_task_tests.c
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * hung_task_tests.c - Sample code for testing hung tasks with mutex,
+ * semaphore, etc.
+ *
+ * Usage: Load this module and read `<debugfs>/hung_task/mutex`,
+ * `<debugfs>/hung_task/semaphore`, etc., with 2 or more processes.
+ *
+ * This is for testing kernel hung_task error messages with various locking
+ * mechanisms (e.g., mutex, semaphore, etc.). Note that this may freeze
+ * your system or cause a panic. Use only for testing purposes.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/semaphore.h>
+
+#define HUNG_TASK_DIR "hung_task"
+#define HUNG_TASK_MUTEX_FILE "mutex"
+#define HUNG_TASK_SEM_FILE "semaphore"
+#define SLEEP_SECOND 256
+
+static const char dummy_string[] = "This is a dummy string.";
+static DEFINE_MUTEX(dummy_mutex);
+static DEFINE_SEMAPHORE(dummy_sem, 1);
+static struct dentry *hung_task_dir;
+
+/* Mutex-based read function */
+static ssize_t read_dummy_mutex(struct file *file, char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ /* Second task waits on mutex, entering uninterruptible sleep */
+ guard(mutex)(&dummy_mutex);
+
+ /* First task sleeps here, interruptible */
+ msleep_interruptible(SLEEP_SECOND * 1000);
+
+ return simple_read_from_buffer(user_buf, count, ppos, dummy_string,
+ sizeof(dummy_string));
+}
+
+/* Semaphore-based read function */
+static ssize_t read_dummy_semaphore(struct file *file, char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ /* Second task waits on semaphore, entering uninterruptible sleep */
+ down(&dummy_sem);
+
+ /* First task sleeps here, interruptible */
+ msleep_interruptible(SLEEP_SECOND * 1000);
+
+ up(&dummy_sem);
+
+ return simple_read_from_buffer(user_buf, count, ppos, dummy_string,
+ sizeof(dummy_string));
+}
+
+/* File operations for mutex */
+static const struct file_operations hung_task_mutex_fops = {
+ .read = read_dummy_mutex,
+};
+
+/* File operations for semaphore */
+static const struct file_operations hung_task_sem_fops = {
+ .read = read_dummy_semaphore,
+};
+
+static int __init hung_task_tests_init(void)
+{
+ hung_task_dir = debugfs_create_dir(HUNG_TASK_DIR, NULL);
+ if (IS_ERR(hung_task_dir))
+ return PTR_ERR(hung_task_dir);
+
+ /* Create debugfs files for mutex and semaphore tests */
+ debugfs_create_file(HUNG_TASK_MUTEX_FILE, 0400, hung_task_dir, NULL,
+ &hung_task_mutex_fops);
+ debugfs_create_file(HUNG_TASK_SEM_FILE, 0400, hung_task_dir, NULL,
+ &hung_task_sem_fops);
+
+ return 0;
+}
+
+static void __exit hung_task_tests_exit(void)
+{
+ debugfs_remove_recursive(hung_task_dir);
+}
+
+module_init(hung_task_tests_init);
+module_exit(hung_task_tests_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Masami Hiramatsu <mhiramat@kernel.org>");
+MODULE_AUTHOR("Zi Li <amaindex@outlook.com>");
+MODULE_DESCRIPTION("Simple sleep under lock files for testing hung task");
--
2.45.2
^ permalink raw reply related [flat|nested] 8+ messages in thread* Re: [PATCH v3 3/3] samples: extend hung_task detector test with semaphore support
2025-03-19 8:11 ` [PATCH v3 3/3] samples: extend hung_task detector test with semaphore support Lance Yang
@ 2025-03-19 13:49 ` Masami Hiramatsu
2025-03-19 14:59 ` Lance Yang
0 siblings, 1 reply; 8+ messages in thread
From: Masami Hiramatsu @ 2025-03-19 13:49 UTC (permalink / raw)
To: Lance Yang
Cc: akpm, will, peterz, mingo, longman, mhiramat, anna.schumaker,
boqun.feng, joel.granados, kent.overstreet, leonylgao,
linux-kernel, rostedt, senozhatsky, tfiga, amaindex, jstultz
On Wed, 19 Mar 2025 16:11:38 +0800
Lance Yang <ioworker0@gmail.com> wrote:
> From: Zi Li <amaindex@outlook.com>
>
> Extend the existing hung_task detector test module to support multiple lock
> types, including mutex and semaphore, with room for future additions (e.g.,
> spinlock, etc.). This module creates dummy files under <debugfs>/hung_task,
> such as 'mutex' and 'semaphore'. The read process on any of these files will
> sleep for enough long time (256 seconds) while holding the respective lock.
> As a result, the second process will wait on the lock for a prolonged
> duration and be detected by the hung_task detector.
>
> This change unifies the previous mutex-only sample into a single,
> extensible hung_task_tests module, reducing code duplication and improving
> maintainability.
>
> Usage is:
>
> > cd /sys/kernel/debug/hung_task
> > cat mutex & cat mutex # Test mutex blocking
> > cat semaphore & cat semaphore # Test semaphore blocking
>
> Update the Kconfig description to reflect multiple debugfs files support.
>
This looks good to me. (but have a nit comment below)
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
> Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
> Signed-off-by: Lance Yang <ioworker0@gmail.com>
> Signed-off-by: Zi Li <amaindex@outlook.com>
> ---
> samples/Kconfig | 9 +--
> samples/hung_task/Makefile | 2 +-
> samples/hung_task/hung_task_mutex.c | 66 --------------------
> samples/hung_task/hung_task_tests.c | 97 +++++++++++++++++++++++++++++
> 4 files changed, 103 insertions(+), 71 deletions(-)
> delete mode 100644 samples/hung_task/hung_task_mutex.c
> create mode 100644 samples/hung_task/hung_task_tests.c
>
> diff --git a/samples/Kconfig b/samples/Kconfig
> index 09011be2391a..753ed1f170b5 100644
> --- a/samples/Kconfig
> +++ b/samples/Kconfig
> @@ -304,10 +304,11 @@ config SAMPLE_HUNG_TASK
> tristate "Hung task detector test code"
> depends on DETECT_HUNG_TASK && DEBUG_FS
> help
> - Build a module which provide a simple debugfs file. If user reads
> - the file, it will sleep long time (256 seconds) with holding a
> - mutex. Thus if there are 2 or more processes read this file, it
> - will be detected by the hung_task watchdog.
> + Build a module that provides debugfs files (e.g., mutex, semaphore,
> + etc.) under <debugfs>/hung_task. If user reads one of these files,
> + it will sleep long time (256 seconds) with holding a lock. Thus,
> + if 2 or more processes read the same file concurrently, it will
> + be detected by the hung_task watchdog.
>
> source "samples/rust/Kconfig"
>
> diff --git a/samples/hung_task/Makefile b/samples/hung_task/Makefile
> index fe9dde799880..86036f1a204d 100644
> --- a/samples/hung_task/Makefile
> +++ b/samples/hung_task/Makefile
> @@ -1,2 +1,2 @@
> # SPDX-License-Identifier: GPL-2.0-only
> -obj-$(CONFIG_SAMPLE_HUNG_TASK) += hung_task_mutex.o
> \ No newline at end of file
> +obj-$(CONFIG_SAMPLE_HUNG_TASK) += hung_task_tests.o
> diff --git a/samples/hung_task/hung_task_mutex.c b/samples/hung_task/hung_task_mutex.c
> deleted file mode 100644
> index 7a29f2246d22..000000000000
> --- a/samples/hung_task/hung_task_mutex.c
> +++ /dev/null
> @@ -1,66 +0,0 @@
> -// SPDX-License-Identifier: GPL-2.0-or-later
> -/*
> - * hung_task_mutex.c - Sample code which causes hung task by mutex
> - *
> - * Usage: load this module and read `<debugfs>/hung_task/mutex`
> - * by 2 or more processes.
> - *
> - * This is for testing kernel hung_task error message.
> - * Note that this will make your system freeze and maybe
> - * cause panic. So do not use this except for the test.
> - */
> -
> -#include <linux/debugfs.h>
> -#include <linux/delay.h>
> -#include <linux/fs.h>
> -#include <linux/module.h>
> -#include <linux/mutex.h>
> -
> -#define HUNG_TASK_DIR "hung_task"
> -#define HUNG_TASK_FILE "mutex"
> -#define SLEEP_SECOND 256
> -
> -static const char dummy_string[] = "This is a dummy string.";
> -static DEFINE_MUTEX(dummy_mutex);
> -struct dentry *hung_task_dir;
Note that Andrew already fixed this (static)
https://web.git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/samples-add-hung_task-detector-mutex-blocking-sample-fix.patch
Thank you,
> -
> -static ssize_t read_dummy(struct file *file, char __user *user_buf,
> - size_t count, loff_t *ppos)
> -{
> - /* If the second task waits on the lock, it is uninterruptible sleep. */
> - guard(mutex)(&dummy_mutex);
> -
> - /* When the first task sleep here, it is interruptible. */
> - msleep_interruptible(SLEEP_SECOND * 1000);
> -
> - return simple_read_from_buffer(user_buf, count, ppos,
> - dummy_string, sizeof(dummy_string));
> -}
> -
> -static const struct file_operations hung_task_fops = {
> - .read = read_dummy,
> -};
> -
> -static int __init hung_task_sample_init(void)
> -{
> - hung_task_dir = debugfs_create_dir(HUNG_TASK_DIR, NULL);
> - if (IS_ERR(hung_task_dir))
> - return PTR_ERR(hung_task_dir);
> -
> - debugfs_create_file(HUNG_TASK_FILE, 0400, hung_task_dir,
> - NULL, &hung_task_fops);
> -
> - return 0;
> -}
> -
> -static void __exit hung_task_sample_exit(void)
> -{
> - debugfs_remove_recursive(hung_task_dir);
> -}
> -
> -module_init(hung_task_sample_init);
> -module_exit(hung_task_sample_exit);
> -
> -MODULE_LICENSE("GPL");
> -MODULE_AUTHOR("Masami Hiramatsu");
> -MODULE_DESCRIPTION("Simple sleep under mutex file for testing hung task");
> diff --git a/samples/hung_task/hung_task_tests.c b/samples/hung_task/hung_task_tests.c
> new file mode 100644
> index 000000000000..a5c09bd3a47d
> --- /dev/null
> +++ b/samples/hung_task/hung_task_tests.c
> @@ -0,0 +1,97 @@
> +// SPDX-License-Identifier: GPL-2.0-or-later
> +/*
> + * hung_task_tests.c - Sample code for testing hung tasks with mutex,
> + * semaphore, etc.
> + *
> + * Usage: Load this module and read `<debugfs>/hung_task/mutex`,
> + * `<debugfs>/hung_task/semaphore`, etc., with 2 or more processes.
> + *
> + * This is for testing kernel hung_task error messages with various locking
> + * mechanisms (e.g., mutex, semaphore, etc.). Note that this may freeze
> + * your system or cause a panic. Use only for testing purposes.
> + */
> +
> +#include <linux/debugfs.h>
> +#include <linux/delay.h>
> +#include <linux/fs.h>
> +#include <linux/module.h>
> +#include <linux/mutex.h>
> +#include <linux/semaphore.h>
> +
> +#define HUNG_TASK_DIR "hung_task"
> +#define HUNG_TASK_MUTEX_FILE "mutex"
> +#define HUNG_TASK_SEM_FILE "semaphore"
> +#define SLEEP_SECOND 256
> +
> +static const char dummy_string[] = "This is a dummy string.";
> +static DEFINE_MUTEX(dummy_mutex);
> +static DEFINE_SEMAPHORE(dummy_sem, 1);
> +static struct dentry *hung_task_dir;
> +
> +/* Mutex-based read function */
> +static ssize_t read_dummy_mutex(struct file *file, char __user *user_buf,
> + size_t count, loff_t *ppos)
> +{
> + /* Second task waits on mutex, entering uninterruptible sleep */
> + guard(mutex)(&dummy_mutex);
> +
> + /* First task sleeps here, interruptible */
> + msleep_interruptible(SLEEP_SECOND * 1000);
> +
> + return simple_read_from_buffer(user_buf, count, ppos, dummy_string,
> + sizeof(dummy_string));
> +}
> +
> +/* Semaphore-based read function */
> +static ssize_t read_dummy_semaphore(struct file *file, char __user *user_buf,
> + size_t count, loff_t *ppos)
> +{
> + /* Second task waits on semaphore, entering uninterruptible sleep */
> + down(&dummy_sem);
> +
> + /* First task sleeps here, interruptible */
> + msleep_interruptible(SLEEP_SECOND * 1000);
> +
> + up(&dummy_sem);
> +
> + return simple_read_from_buffer(user_buf, count, ppos, dummy_string,
> + sizeof(dummy_string));
> +}
> +
> +/* File operations for mutex */
> +static const struct file_operations hung_task_mutex_fops = {
> + .read = read_dummy_mutex,
> +};
> +
> +/* File operations for semaphore */
> +static const struct file_operations hung_task_sem_fops = {
> + .read = read_dummy_semaphore,
> +};
> +
> +static int __init hung_task_tests_init(void)
> +{
> + hung_task_dir = debugfs_create_dir(HUNG_TASK_DIR, NULL);
> + if (IS_ERR(hung_task_dir))
> + return PTR_ERR(hung_task_dir);
> +
> + /* Create debugfs files for mutex and semaphore tests */
> + debugfs_create_file(HUNG_TASK_MUTEX_FILE, 0400, hung_task_dir, NULL,
> + &hung_task_mutex_fops);
> + debugfs_create_file(HUNG_TASK_SEM_FILE, 0400, hung_task_dir, NULL,
> + &hung_task_sem_fops);
> +
> + return 0;
> +}
> +
> +static void __exit hung_task_tests_exit(void)
> +{
> + debugfs_remove_recursive(hung_task_dir);
> +}
> +
> +module_init(hung_task_tests_init);
> +module_exit(hung_task_tests_exit);
> +
> +MODULE_LICENSE("GPL");
> +MODULE_AUTHOR("Masami Hiramatsu <mhiramat@kernel.org>");
> +MODULE_AUTHOR("Zi Li <amaindex@outlook.com>");
> +MODULE_DESCRIPTION("Simple sleep under lock files for testing hung task");
> --
> 2.45.2
>
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply [flat|nested] 8+ messages in thread* Re: [PATCH v3 3/3] samples: extend hung_task detector test with semaphore support
2025-03-19 13:49 ` Masami Hiramatsu
@ 2025-03-19 14:59 ` Lance Yang
0 siblings, 0 replies; 8+ messages in thread
From: Lance Yang @ 2025-03-19 14:59 UTC (permalink / raw)
To: Masami Hiramatsu
Cc: akpm, will, peterz, mingo, longman, anna.schumaker, boqun.feng,
joel.granados, kent.overstreet, leonylgao, linux-kernel, rostedt,
senozhatsky, tfiga, amaindex, jstultz
On Wed, Mar 19, 2025 at 9:49 PM Masami Hiramatsu <mhiramat@kernel.org> wrote:
>
> On Wed, 19 Mar 2025 16:11:38 +0800
> Lance Yang <ioworker0@gmail.com> wrote:
>
> > From: Zi Li <amaindex@outlook.com>
> >
> > Extend the existing hung_task detector test module to support multiple lock
> > types, including mutex and semaphore, with room for future additions (e.g.,
> > spinlock, etc.). This module creates dummy files under <debugfs>/hung_task,
> > such as 'mutex' and 'semaphore'. The read process on any of these files will
> > sleep for enough long time (256 seconds) while holding the respective lock.
> > As a result, the second process will wait on the lock for a prolonged
> > duration and be detected by the hung_task detector.
> >
> > This change unifies the previous mutex-only sample into a single,
> > extensible hung_task_tests module, reducing code duplication and improving
> > maintainability.
> >
> > Usage is:
> >
> > > cd /sys/kernel/debug/hung_task
> > > cat mutex & cat mutex # Test mutex blocking
> > > cat semaphore & cat semaphore # Test semaphore blocking
> >
> > Update the Kconfig description to reflect multiple debugfs files support.
> >
>
> This looks good to me. (but have a nit comment below)
>
> Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Thanks a lot for taking time to review!
>
> > Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
> > Signed-off-by: Lance Yang <ioworker0@gmail.com>
> > Signed-off-by: Zi Li <amaindex@outlook.com>
> > ---
> > samples/Kconfig | 9 +--
> > samples/hung_task/Makefile | 2 +-
> > samples/hung_task/hung_task_mutex.c | 66 --------------------
> > samples/hung_task/hung_task_tests.c | 97 +++++++++++++++++++++++++++++
> > 4 files changed, 103 insertions(+), 71 deletions(-)
> > delete mode 100644 samples/hung_task/hung_task_mutex.c
> > create mode 100644 samples/hung_task/hung_task_tests.c
> >
> > diff --git a/samples/Kconfig b/samples/Kconfig
> > index 09011be2391a..753ed1f170b5 100644
> > --- a/samples/Kconfig
> > +++ b/samples/Kconfig
> > @@ -304,10 +304,11 @@ config SAMPLE_HUNG_TASK
> > tristate "Hung task detector test code"
> > depends on DETECT_HUNG_TASK && DEBUG_FS
> > help
> > - Build a module which provide a simple debugfs file. If user reads
> > - the file, it will sleep long time (256 seconds) with holding a
> > - mutex. Thus if there are 2 or more processes read this file, it
> > - will be detected by the hung_task watchdog.
> > + Build a module that provides debugfs files (e.g., mutex, semaphore,
> > + etc.) under <debugfs>/hung_task. If user reads one of these files,
> > + it will sleep long time (256 seconds) with holding a lock. Thus,
> > + if 2 or more processes read the same file concurrently, it will
> > + be detected by the hung_task watchdog.
> >
> > source "samples/rust/Kconfig"
> >
> > diff --git a/samples/hung_task/Makefile b/samples/hung_task/Makefile
> > index fe9dde799880..86036f1a204d 100644
> > --- a/samples/hung_task/Makefile
> > +++ b/samples/hung_task/Makefile
> > @@ -1,2 +1,2 @@
> > # SPDX-License-Identifier: GPL-2.0-only
> > -obj-$(CONFIG_SAMPLE_HUNG_TASK) += hung_task_mutex.o
> > \ No newline at end of file
> > +obj-$(CONFIG_SAMPLE_HUNG_TASK) += hung_task_tests.o
> > diff --git a/samples/hung_task/hung_task_mutex.c b/samples/hung_task/hung_task_mutex.c
> > deleted file mode 100644
> > index 7a29f2246d22..000000000000
> > --- a/samples/hung_task/hung_task_mutex.c
> > +++ /dev/null
> > @@ -1,66 +0,0 @@
> > -// SPDX-License-Identifier: GPL-2.0-or-later
> > -/*
> > - * hung_task_mutex.c - Sample code which causes hung task by mutex
> > - *
> > - * Usage: load this module and read `<debugfs>/hung_task/mutex`
> > - * by 2 or more processes.
> > - *
> > - * This is for testing kernel hung_task error message.
> > - * Note that this will make your system freeze and maybe
> > - * cause panic. So do not use this except for the test.
> > - */
> > -
> > -#include <linux/debugfs.h>
> > -#include <linux/delay.h>
> > -#include <linux/fs.h>
> > -#include <linux/module.h>
> > -#include <linux/mutex.h>
> > -
> > -#define HUNG_TASK_DIR "hung_task"
> > -#define HUNG_TASK_FILE "mutex"
> > -#define SLEEP_SECOND 256
> > -
> > -static const char dummy_string[] = "This is a dummy string.";
> > -static DEFINE_MUTEX(dummy_mutex);
> > -struct dentry *hung_task_dir;
>
> Note that Andrew already fixed this (static)
>
> https://web.git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/samples-add-hung_task-detector-mutex-blocking-sample-fix.patch
Good catch! I’ll rebase this patch on that.
Thanks again for your time!
Lance
>
> Thank you,
>
> > -
> > -static ssize_t read_dummy(struct file *file, char __user *user_buf,
> > - size_t count, loff_t *ppos)
> > -{
> > - /* If the second task waits on the lock, it is uninterruptible sleep. */
> > - guard(mutex)(&dummy_mutex);
> > -
> > - /* When the first task sleep here, it is interruptible. */
> > - msleep_interruptible(SLEEP_SECOND * 1000);
> > -
> > - return simple_read_from_buffer(user_buf, count, ppos,
> > - dummy_string, sizeof(dummy_string));
> > -}
> > -
> > -static const struct file_operations hung_task_fops = {
> > - .read = read_dummy,
> > -};
> > -
> > -static int __init hung_task_sample_init(void)
> > -{
> > - hung_task_dir = debugfs_create_dir(HUNG_TASK_DIR, NULL);
> > - if (IS_ERR(hung_task_dir))
> > - return PTR_ERR(hung_task_dir);
> > -
> > - debugfs_create_file(HUNG_TASK_FILE, 0400, hung_task_dir,
> > - NULL, &hung_task_fops);
> > -
> > - return 0;
> > -}
> > -
> > -static void __exit hung_task_sample_exit(void)
> > -{
> > - debugfs_remove_recursive(hung_task_dir);
> > -}
> > -
> > -module_init(hung_task_sample_init);
> > -module_exit(hung_task_sample_exit);
> > -
> > -MODULE_LICENSE("GPL");
> > -MODULE_AUTHOR("Masami Hiramatsu");
> > -MODULE_DESCRIPTION("Simple sleep under mutex file for testing hung task");
> > diff --git a/samples/hung_task/hung_task_tests.c b/samples/hung_task/hung_task_tests.c
> > new file mode 100644
> > index 000000000000..a5c09bd3a47d
> > --- /dev/null
> > +++ b/samples/hung_task/hung_task_tests.c
> > @@ -0,0 +1,97 @@
> > +// SPDX-License-Identifier: GPL-2.0-or-later
> > +/*
> > + * hung_task_tests.c - Sample code for testing hung tasks with mutex,
> > + * semaphore, etc.
> > + *
> > + * Usage: Load this module and read `<debugfs>/hung_task/mutex`,
> > + * `<debugfs>/hung_task/semaphore`, etc., with 2 or more processes.
> > + *
> > + * This is for testing kernel hung_task error messages with various locking
> > + * mechanisms (e.g., mutex, semaphore, etc.). Note that this may freeze
> > + * your system or cause a panic. Use only for testing purposes.
> > + */
> > +
> > +#include <linux/debugfs.h>
> > +#include <linux/delay.h>
> > +#include <linux/fs.h>
> > +#include <linux/module.h>
> > +#include <linux/mutex.h>
> > +#include <linux/semaphore.h>
> > +
> > +#define HUNG_TASK_DIR "hung_task"
> > +#define HUNG_TASK_MUTEX_FILE "mutex"
> > +#define HUNG_TASK_SEM_FILE "semaphore"
> > +#define SLEEP_SECOND 256
> > +
> > +static const char dummy_string[] = "This is a dummy string.";
> > +static DEFINE_MUTEX(dummy_mutex);
> > +static DEFINE_SEMAPHORE(dummy_sem, 1);
> > +static struct dentry *hung_task_dir;
> > +
> > +/* Mutex-based read function */
> > +static ssize_t read_dummy_mutex(struct file *file, char __user *user_buf,
> > + size_t count, loff_t *ppos)
> > +{
> > + /* Second task waits on mutex, entering uninterruptible sleep */
> > + guard(mutex)(&dummy_mutex);
> > +
> > + /* First task sleeps here, interruptible */
> > + msleep_interruptible(SLEEP_SECOND * 1000);
> > +
> > + return simple_read_from_buffer(user_buf, count, ppos, dummy_string,
> > + sizeof(dummy_string));
> > +}
> > +
> > +/* Semaphore-based read function */
> > +static ssize_t read_dummy_semaphore(struct file *file, char __user *user_buf,
> > + size_t count, loff_t *ppos)
> > +{
> > + /* Second task waits on semaphore, entering uninterruptible sleep */
> > + down(&dummy_sem);
> > +
> > + /* First task sleeps here, interruptible */
> > + msleep_interruptible(SLEEP_SECOND * 1000);
> > +
> > + up(&dummy_sem);
> > +
> > + return simple_read_from_buffer(user_buf, count, ppos, dummy_string,
> > + sizeof(dummy_string));
> > +}
> > +
> > +/* File operations for mutex */
> > +static const struct file_operations hung_task_mutex_fops = {
> > + .read = read_dummy_mutex,
> > +};
> > +
> > +/* File operations for semaphore */
> > +static const struct file_operations hung_task_sem_fops = {
> > + .read = read_dummy_semaphore,
> > +};
> > +
> > +static int __init hung_task_tests_init(void)
> > +{
> > + hung_task_dir = debugfs_create_dir(HUNG_TASK_DIR, NULL);
> > + if (IS_ERR(hung_task_dir))
> > + return PTR_ERR(hung_task_dir);
> > +
> > + /* Create debugfs files for mutex and semaphore tests */
> > + debugfs_create_file(HUNG_TASK_MUTEX_FILE, 0400, hung_task_dir, NULL,
> > + &hung_task_mutex_fops);
> > + debugfs_create_file(HUNG_TASK_SEM_FILE, 0400, hung_task_dir, NULL,
> > + &hung_task_sem_fops);
> > +
> > + return 0;
> > +}
> > +
> > +static void __exit hung_task_tests_exit(void)
> > +{
> > + debugfs_remove_recursive(hung_task_dir);
> > +}
> > +
> > +module_init(hung_task_tests_init);
> > +module_exit(hung_task_tests_exit);
> > +
> > +MODULE_LICENSE("GPL");
> > +MODULE_AUTHOR("Masami Hiramatsu <mhiramat@kernel.org>");
> > +MODULE_AUTHOR("Zi Li <amaindex@outlook.com>");
> > +MODULE_DESCRIPTION("Simple sleep under lock files for testing hung task");
> > --
> > 2.45.2
> >
>
>
> --
> Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply [flat|nested] 8+ messages in thread