Commit 1dcb98bb authored by Tejun Heo's avatar Tejun Heo
Browse files

sched_ext: Pass locked CPU parameter to scx_hardlockup() and add docs 



With the buddy lockup detector, smp_processor_id() returns the detecting CPU,
not the locked CPU, making scx_hardlockup()'s printouts confusing. Pass the
locked CPU number from watchdog_hardlockup_check() as a parameter instead.

Also add kerneldoc comments to handle_lockup(), scx_hardlockup(), and
scx_rcu_cpu_stall() documenting their return value semantics.

Suggested-by: default avatarDoug Anderson <dianders@chromium.org>
Reviewed-by: default avatarDouglas Anderson <dianders@chromium.org>
Acked-by: default avatarAndrea Righi <arighi@nvidia.com>
Reviewed-by: default avatarEmil Tsalapatis <emil@etsalapatis.com>
Signed-off-by: default avatarTejun Heo <tj@kernel.org>
parent 67932f69

include/linux/sched/ext.h

+2 −2
Original line number Diff line number Diff line
@@ -230,7 +230,7 @@ struct sched_ext_entity { 
void sched_ext_dead(struct task_struct *p);

void print_scx_info(const char *log_lvl, struct task_struct *p);

void scx_softlockup(u32 dur_s);

bool scx_hardlockup(void);

bool scx_hardlockup(int cpu);

bool scx_rcu_cpu_stall(void);



#else	/* !CONFIG_SCHED_CLASS_EXT */
@@ -238,7 +238,7 @@ bool scx_rcu_cpu_stall(void); 
static inline void sched_ext_dead(struct task_struct *p) {}

static inline void print_scx_info(const char *log_lvl, struct task_struct *p) {}

static inline void scx_softlockup(u32 dur_s) {}

static inline bool scx_hardlockup(void) { return false; }

static inline bool scx_hardlockup(int cpu) { return false; }

static inline bool scx_rcu_cpu_stall(void) { return false; }



#endif	/* CONFIG_SCHED_CLASS_EXT */

kernel/sched/ext.c

+22 −3
Original line number Diff line number Diff line
@@ -3687,6 +3687,17 @@ bool scx_allow_ttwu_queue(const struct task_struct *p) 
	return false;

}



/**

 * handle_lockup - sched_ext common lockup handler

 * @fmt: format string

 *

 * Called on system stall or lockup condition and initiates abort of sched_ext

 * if enabled, which may resolve the reported lockup.

 *

 * Returns %true if sched_ext is enabled and abort was initiated, which may

 * resolve the lockup. %false if sched_ext is not enabled or abort was already

 * initiated by someone else.

 */

static __printf(1, 2) bool handle_lockup(const char *fmt, ...)

{

	struct scx_sched *sch;
@@ -3718,6 +3729,10 @@ static __printf(1, 2) bool handle_lockup(const char *fmt, ...) 
 * that may not be caused by the current BPF scheduler, try kicking out the

 * current scheduler in an attempt to recover the system to a good state before

 * issuing panics.

 *

 * Returns %true if sched_ext is enabled and abort was initiated, which may

 * resolve the reported RCU stall. %false if sched_ext is not enabled or someone

 * else already initiated abort.

 */

bool scx_rcu_cpu_stall(void)

{
@@ -3750,14 +3765,18 @@ void scx_softlockup(u32 dur_s) 
 * numerous affinitized tasks in a single queue and directing all CPUs at it.

 * Try kicking out the current scheduler in an attempt to recover the system to

 * a good state before taking more drastic actions.

 *

 * Returns %true if sched_ext is enabled and abort was initiated, which may

 * resolve the reported hardlockdup. %false if sched_ext is not enabled or

 * someone else already initiated abort.

 */

bool scx_hardlockup(void)

bool scx_hardlockup(int cpu)

{

	if (!handle_lockup("hard lockup - CPU %d", smp_processor_id()))

	if (!handle_lockup("hard lockup - CPU %d", cpu))

		return false;



	printk_deferred(KERN_ERR "sched_ext: Hard lockup - CPU %d, disabling BPF scheduler\n",

			smp_processor_id());

			cpu);

	return true;

}

kernel/watchdog.c

+1 −1
Original line number Diff line number Diff line
@@ -203,7 +203,7 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs) 
		 * only once when sched_ext is enabled and will immediately

		 * abort the BPF scheduler and print out a warning message.

		 */

		if (scx_hardlockup())

		if (scx_hardlockup(cpu))

			return;



		/* Only print hardlockups once. */