Re: [PATCH v3 1/3] hung_task: replace blocker_mutex with encoded blocker

[Masami Hiramatsu (Google) <mhiramat@kernel.org>]

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>