Commit 4e58aaee authored by Paul E. McKenney's avatar Paul E. McKenney Committed by Neeraj Upadhyay (AMD)
Browse files

rcu: Restrict access to RCU CPU stall notifiers 



Although the RCU CPU stall notifiers can be useful for dumping state when
tracking down delicate forward-progress bugs where NUMA effects cause
cache lines to be delivered to a given CPU regularly, but always in a
state that prevents that CPU from making forward progress.  These bugs can
be detected by the RCU CPU stall-warning mechanism, but in some cases,
the stall-warnings printk()s disrupt the forward-progress bug before
any useful state can be obtained.

Unfortunately, the notifier mechanism added by commit 5b404fda ("rcu:
Add RCU CPU stall notifier") can make matters worse if used at all
carelessly. For example, if the stall warning was caused by a lock not
being released, then any attempt to acquire that lock in the notifier
will hang. This will prevent not only the notifier from producing any
useful output, but it will also prevent the stall-warning message from
ever appearing.

This commit therefore hides this new RCU CPU stall notifier
mechanism under a new RCU_CPU_STALL_NOTIFIER Kconfig option that
depends on both DEBUG_KERNEL and RCU_EXPERT.  In addition, the
rcupdate.rcu_cpu_stall_notifiers=1 kernel boot parameter must also
be specified.  The RCU_CPU_STALL_NOTIFIER Kconfig option's help text
contains a warning and explains the dangers of careless use, recommending
lockless notifier code.  In addition, a WARN() is triggered each time
that an attempt is made to register a stall-warning notifier in kernels
built with CONFIG_RCU_CPU_STALL_NOTIFIER=y.

This combination of measures will keep use of this mechanism confined to
debug kernels and away from routine deployments.

[ paulmck: Apply Dan Carpenter feedback. ]

Fixes: 5b404fda ("rcu: Add RCU CPU stall notifier")
Reported-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: default avatarPaul E. McKenney <paulmck@kernel.org>
Reviewed-by: default avatarJoel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: default avatarNeeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
parent 98b1cc82

Documentation/admin-guide/kernel-parameters.txt

+6 −0
Original line number Diff line number Diff line
@@ -5302,6 +5302,12 @@ 
			Dump ftrace buffer after reporting RCU CPU

			stall warning.



	rcupdate.rcu_cpu_stall_notifiers= [KNL]

			Provide RCU CPU stall notifiers, but see the

			warnings in the RCU_CPU_STALL_NOTIFIER Kconfig

			option's help text.  TL;DR:  You almost certainly

			do not want rcupdate.rcu_cpu_stall_notifiers.



	rcupdate.rcu_cpu_stall_suppress= [KNL]

			Suppress RCU CPU stall warning messages.

include/linux/rcu_notifier.h

+3 −3
Original line number Diff line number Diff line
@@ -13,7 +13,7 @@ 
#define RCU_STALL_NOTIFY_NORM	1

#define RCU_STALL_NOTIFY_EXP	2



#ifdef CONFIG_RCU_STALL_COMMON

#if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)



#include <linux/notifier.h>

#include <linux/types.h>
@@ -21,12 +21,12 @@ 
int rcu_stall_chain_notifier_register(struct notifier_block *n);

int rcu_stall_chain_notifier_unregister(struct notifier_block *n);



#else // #ifdef CONFIG_RCU_STALL_COMMON

#else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)



// No RCU CPU stall warnings in Tiny RCU.

static inline int rcu_stall_chain_notifier_register(struct notifier_block *n) { return -EEXIST; }

static inline int rcu_stall_chain_notifier_unregister(struct notifier_block *n) { return -ENOENT; }



#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON

#endif // #else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)



#endif /* __LINUX_RCU_NOTIFIER_H */

kernel/rcu/Kconfig.debug

+25 −0
Original line number Diff line number Diff line
@@ -105,6 +105,31 @@ config RCU_CPU_STALL_CPUTIME 
	  The boot option rcupdate.rcu_cpu_stall_cputime has the same function

	  as this one, but will override this if it exists.



config RCU_CPU_STALL_NOTIFIER

	bool "Provide RCU CPU-stall notifiers"

	depends on RCU_STALL_COMMON

	depends on DEBUG_KERNEL

	depends on RCU_EXPERT

	default n

	help

	  WARNING:  You almost certainly do not want this!!!



	  Enable RCU CPU-stall notifiers, which are invoked just before

	  printing the RCU CPU stall warning.  As such, bugs in notifier

	  callbacks can prevent stall warnings from being printed.

	  And the whole reason that a stall warning is being printed is

	  that something is hung up somewhere.	Therefore, the notifier

	  callbacks must be written extremely carefully, preferably

	  containing only lockless code.  After all, it is quite possible

	  that the whole reason that the RCU CPU stall is happening in

	  the first place is that someone forgot to release whatever lock

	  that you are thinking of acquiring.  In which case, having your

	  notifier callback acquire that lock will hang, preventing the

	  RCU CPU stall warning from appearing.



	  Say Y here if you want RCU CPU stall notifiers (you don't want them)

	  Say N if you are unsure.



config RCU_TRACE

	bool "Enable tracing for RCU"

	depends on DEBUG_KERNEL

kernel/rcu/rcu.h

+5 −3
Original line number Diff line number Diff line
@@ -262,6 +262,8 @@ static inline bool rcu_stall_is_suppressed_at_boot(void) 
	return rcu_cpu_stall_suppress_at_boot && !rcu_inkernel_boot_has_ended();

}



extern int rcu_cpu_stall_notifiers;



#ifdef CONFIG_RCU_STALL_COMMON



extern int rcu_cpu_stall_ftrace_dump;
@@ -659,10 +661,10 @@ static inline bool rcu_cpu_beenfullyonline(int cpu) { return true; } 
bool rcu_cpu_beenfullyonline(int cpu);

#endif



#ifdef CONFIG_RCU_STALL_COMMON

#if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)

int rcu_stall_notifier_call_chain(unsigned long val, void *v);

#else // #ifdef CONFIG_RCU_STALL_COMMON

#else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)

static inline int rcu_stall_notifier_call_chain(unsigned long val, void *v) { return NOTIFY_DONE; }

#endif // #else // #ifdef CONFIG_RCU_STALL_COMMON

#endif // #else // #if defined(CONFIG_RCU_STALL_COMMON) && defined(CONFIG_RCU_CPU_STALL_NOTIFIER)



#endif /* __LINUX_RCU_H */

kernel/rcu/rcutorture.c

+7 −5
Original line number Diff line number Diff line
@@ -2450,10 +2450,12 @@ static int rcu_torture_stall(void *args) 
	unsigned long stop_at;



	VERBOSE_TOROUT_STRING("rcu_torture_stall task started");

	if (rcu_cpu_stall_notifiers) {

		ret = rcu_stall_chain_notifier_register(&rcu_torture_stall_block);

		if (ret)

			pr_info("%s: rcu_stall_chain_notifier_register() returned %d, %sexpected.\n",

				__func__, ret, !IS_ENABLED(CONFIG_RCU_STALL_COMMON) ? "un" : "");

	}

	if (stall_cpu_holdoff > 0) {

		VERBOSE_TOROUT_STRING("rcu_torture_stall begin holdoff");

		schedule_timeout_interruptible(stall_cpu_holdoff * HZ);
@@ -2497,7 +2499,7 @@ static int rcu_torture_stall(void *args) 
		cur_ops->readunlock(idx);

	}

	pr_alert("%s end.\n", __func__);

	if (!ret) {

	if (rcu_cpu_stall_notifiers && !ret) {

		ret = rcu_stall_chain_notifier_unregister(&rcu_torture_stall_block);

		if (ret)

			pr_info("%s: rcu_stall_chain_notifier_unregister() returned %d.\n", __func__, ret);