From 4e58aaeebb3c27993c734c99eae6881b196b1ddb Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 1 Nov 2023 18:28:38 -0700 Subject: 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 Signed-off-by: Paul E. McKenney Reviewed-by: Joel Fernandes (Google) Signed-off-by: Neeraj Upadhyay (AMD) --- include/linux/rcu_notifier.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcu_notifier.h b/include/linux/rcu_notifier.h index ebf371364581..5640f024773b 100644 --- a/include/linux/rcu_notifier.h +++ b/include/linux/rcu_notifier.h @@ -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 #include @@ -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 */ -- cgit v1.2.3 From 23d90b2404050c00c15058710d56bb46e1c5ab36 Mon Sep 17 00:00:00 2001 From: Pedro Falcato Date: Fri, 20 Oct 2023 18:30:15 +0100 Subject: rcu: Remove unused macros from rcupdate.h ulong2long, USHORT_CMP_GE and USHORT_CMP_LT are redundant and have been unused for quite a few releases. Signed-off-by: Pedro Falcato Signed-off-by: Paul E. McKenney Signed-off-by: Neeraj Upadhyay (AMD) --- include/linux/rcupdate.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index f7206b2623c9..aa87c82236dd 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -34,9 +34,6 @@ #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) -#define ulong2long(a) (*(long *)(&(a))) -#define USHORT_CMP_GE(a, b) (USHRT_MAX / 2 >= (unsigned short)((a) - (b))) -#define USHORT_CMP_LT(a, b) (USHRT_MAX / 2 < (unsigned short)((a) - (b))) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); -- cgit v1.2.3 From 3c6b0c1c28184038d90dffe8eb542bedcb8ccf98 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Thu, 30 Nov 2023 14:27:29 +0100 Subject: srcu: Use try-lock lockdep annotation for NMI-safe access. It is claimed that srcu_read_lock_nmisafe() NMI-safe. However it triggers a lockdep if used from NMI because lockdep expects a deadlock since nothing disables NMIs while the lock is acquired. This is because commit f0f44752f5f61 ("rcu: Annotate SRCU's update-side lockdep dependencies") annotates synchronize_srcu() as a write lock usage. This helps to detect a deadlocks such as srcu_read_lock(); synchronize_srcu(); srcu_read_unlock(); The side effect is that the lock srcu_struct now has a USED usage in normal contexts, so it conflicts with a USED_READ usage in NMI. But this shouldn't cause a real deadlock because the write lock usage from synchronize_srcu() is a fake one and only used for read/write deadlock detection. Use a try-lock annotation for srcu_read_lock_nmisafe() to avoid lockdep complains if used from NMI. Fixes: f0f44752f5f6 ("rcu: Annotate SRCU's update-side lockdep dependencies") Link: https://lore.kernel.org/r/20230927160231.XRCDDSK4@linutronix.de Reviewed-by: Boqun Feng Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Paul E. McKenney Signed-off-by: Neeraj Upadhyay (AMD) --- include/linux/rcupdate.h | 6 ++++++ include/linux/srcu.h | 2 +- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index f7206b2623c9..31d523c4e089 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -301,6 +301,11 @@ static inline void rcu_lock_acquire(struct lockdep_map *map) lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } +static inline void rcu_try_lock_acquire(struct lockdep_map *map) +{ + lock_acquire(map, 0, 1, 2, 0, NULL, _THIS_IP_); +} + static inline void rcu_lock_release(struct lockdep_map *map) { lock_release(map, _THIS_IP_); @@ -315,6 +320,7 @@ int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ # define rcu_lock_acquire(a) do { } while (0) +# define rcu_try_lock_acquire(a) do { } while (0) # define rcu_lock_release(a) do { } while (0) static inline int rcu_read_lock_held(void) diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 127ef3b2e607..236610e4a8fa 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -229,7 +229,7 @@ static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp srcu_check_nmi_safety(ssp, true); retval = __srcu_read_lock_nmisafe(ssp); - rcu_lock_acquire(&ssp->dep_map); + rcu_try_lock_acquire(&ssp->dep_map); return retval; } -- cgit v1.2.3