summaryrefslogtreecommitdiff
path: root/kernel/rcu
diff options
context:
space:
mode:
authorPaul E. McKenney <paulmck@kernel.org>2023-11-01 18:28:38 -0700
committerNeeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>2023-12-12 02:31:22 +0530
commit4e58aaeebb3c27993c734c99eae6881b196b1ddb (patch)
treea3d94fb2b8dd013fa8fc3415026c59511874a12d /kernel/rcu
parent98b1cc82c4affc16f5598d4fa14b1858671b2263 (diff)
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 5b404fdabacf ("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: 5b404fdabacf ("rcu: Add RCU CPU stall notifier") Reported-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Paul E. McKenney <paulmck@kernel.org> Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org> Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.iitr10@gmail.com>
Diffstat (limited to 'kernel/rcu')
-rw-r--r--kernel/rcu/Kconfig.debug25
-rw-r--r--kernel/rcu/rcu.h8
-rw-r--r--kernel/rcu/rcutorture.c12
-rw-r--r--kernel/rcu/tree_stall.h11
-rw-r--r--kernel/rcu/update.c6
5 files changed, 53 insertions, 9 deletions
diff --git a/kernel/rcu/Kconfig.debug b/kernel/rcu/Kconfig.debug
index 2984de629f74..9b0b52e1836f 100644
--- a/kernel/rcu/Kconfig.debug
+++ b/kernel/rcu/Kconfig.debug
@@ -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
diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index b531c33e9545..f94f65877f2b 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -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 */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 30fc9d34e329..07a6a183c555 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -2450,10 +2450,12 @@ static int rcu_torture_stall(void *args)
unsigned long stop_at;
VERBOSE_TOROUT_STRING("rcu_torture_stall task started");
- 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 (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);
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index ac8e86babe44..5d666428546b 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -1061,6 +1061,7 @@ static int __init rcu_sysrq_init(void)
}
early_initcall(rcu_sysrq_init);
+#ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
//////////////////////////////////////////////////////////////////////////////
//
@@ -1081,7 +1082,13 @@ static ATOMIC_NOTIFIER_HEAD(rcu_cpu_stall_notifier_list);
*/
int rcu_stall_chain_notifier_register(struct notifier_block *n)
{
- return atomic_notifier_chain_register(&rcu_cpu_stall_notifier_list, n);
+ int rcsn = rcu_cpu_stall_notifiers;
+
+ WARN(1, "Adding %pS() to RCU stall notifier list (%s).\n", n->notifier_call,
+ rcsn ? "possibly suppressing RCU CPU stall warnings" : "failed, so all is well");
+ if (rcsn)
+ return atomic_notifier_chain_register(&rcu_cpu_stall_notifier_list, n);
+ return -EEXIST;
}
EXPORT_SYMBOL_GPL(rcu_stall_chain_notifier_register);
@@ -1115,3 +1122,5 @@ int rcu_stall_notifier_call_chain(unsigned long val, void *v)
{
return atomic_notifier_call_chain(&rcu_cpu_stall_notifier_list, val, v);
}
+
+#endif // #ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index c534d6806d3d..46aaaa9fe339 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -538,9 +538,15 @@ long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
EXPORT_SYMBOL_GPL(torture_sched_setaffinity);
#endif
+int rcu_cpu_stall_notifiers __read_mostly; // !0 = provide stall notifiers (rarely useful)
+EXPORT_SYMBOL_GPL(rcu_cpu_stall_notifiers);
+
#ifdef CONFIG_RCU_STALL_COMMON
int rcu_cpu_stall_ftrace_dump __read_mostly;
module_param(rcu_cpu_stall_ftrace_dump, int, 0644);
+#ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
+module_param(rcu_cpu_stall_notifiers, int, 0444);
+#endif // #ifdef CONFIG_RCU_CPU_STALL_NOTIFIER
int rcu_cpu_stall_suppress __read_mostly; // !0 = suppress stall warnings.
EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);
module_param(rcu_cpu_stall_suppress, int, 0644);