From 92a708dc1fb8c33b0017ad77dc7ff6e434f96ee2 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 27 Jul 2023 13:13:46 -0700 Subject: rcu-tasks: Add printk()s to localize boot-time self-test hang Currently, rcu_tasks_initiate_self_tests() prints a message and then initiates self tests on up to three different RCU Tasks flavors. If one of the flavors has a grace-period hang, it is not easy to work out which of the three hung. This commit therefore prints a message prior to each individual test. Reported-by: Guenter Roeck Signed-off-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker --- kernel/rcu/tasks.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/rcu/tasks.h') diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 8d65f7d576a3..83049a893de5 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -1979,20 +1979,22 @@ static void test_rcu_tasks_callback(struct rcu_head *rhp) static void rcu_tasks_initiate_self_tests(void) { - pr_info("Running RCU-tasks wait API self tests\n"); #ifdef CONFIG_TASKS_RCU + pr_info("Running RCU Tasks wait API self tests\n"); tests[0].runstart = jiffies; synchronize_rcu_tasks(); call_rcu_tasks(&tests[0].rh, test_rcu_tasks_callback); #endif #ifdef CONFIG_TASKS_RUDE_RCU + pr_info("Running RCU Tasks Rude wait API self tests\n"); tests[1].runstart = jiffies; synchronize_rcu_tasks_rude(); call_rcu_tasks_rude(&tests[1].rh, test_rcu_tasks_callback); #endif #ifdef CONFIG_TASKS_TRACE_RCU + pr_info("Running RCU Tasks Trace wait API self tests\n"); tests[2].runstart = jiffies; synchronize_rcu_tasks_trace(); call_rcu_tasks_trace(&tests[2].rh, test_rcu_tasks_callback); -- cgit From e62d8ae4620865411d1b2347980aa28ccf891a3d Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 2 Aug 2023 13:42:00 -0700 Subject: rcu-tasks: Pull sampling of ->percpu_dequeue_lim out of loop The rcu_tasks_need_gpcb() samples ->percpu_dequeue_lim as part of the condition clause of a "for" loop, which is a bit confusing. This commit therefore hoists this sampling out of the loop, using the result loaded in the condition clause. So why does this work in the face of a concurrent switch from single-CPU queueing to per-CPU queueing? o The call_rcu_tasks_generic() that makes the change has already enqueued its callback, which means that all of the other CPU's callback queues are empty. o For the call_rcu_tasks_generic() that first notices the switch to per-CPU queues, the smp_store_release() used to update ->percpu_enqueue_lim pairs with the raw_spin_trylock_rcu_node()'s full barrier that is between the READ_ONCE(rtp->percpu_enqueue_shift) and the rcu_segcblist_enqueue() that enqueues the callback. o Because this CPU's queue is empty (unless it happens to be the original single queue, in which case there is no need for synchronization), this call_rcu_tasks_generic() will do an irq_work_queue() to schedule a handler for the needed rcuwait_wake_up() call. This call will be ordered after the first call_rcu_tasks_generic() function's change to ->percpu_dequeue_lim. o This rcuwait_wake_up() will either happen before or after the set_current_state() in rcuwait_wait_event(). If it happens before, the "condition" argument's call to rcu_tasks_need_gpcb() will be ordered after the original change, and all callbacks on all CPUs will be visible. Otherwise, if it happens after, then the grace-period kthread's state will be set back to running, which will result in a later call to rcuwait_wait_event() and thus to rcu_tasks_need_gpcb(), which will again see the change. So it all works out. Suggested-by: Linus Torvalds Signed-off-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker --- kernel/rcu/tasks.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/rcu/tasks.h') diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 83049a893de5..94bb5abdbb37 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -432,6 +432,7 @@ static void rcu_barrier_tasks_generic(struct rcu_tasks *rtp) static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp) { int cpu; + int dequeue_limit; unsigned long flags; bool gpdone = poll_state_synchronize_rcu(rtp->percpu_dequeue_gpseq); long n; @@ -439,7 +440,8 @@ static int rcu_tasks_need_gpcb(struct rcu_tasks *rtp) long ncbsnz = 0; int needgpcb = 0; - for (cpu = 0; cpu < smp_load_acquire(&rtp->percpu_dequeue_lim); cpu++) { + dequeue_limit = smp_load_acquire(&rtp->percpu_dequeue_lim); + for (cpu = 0; cpu < dequeue_limit; cpu++) { struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rtp->rtpcpu, cpu); /* Advance and accelerate any new callbacks. */ -- cgit From 0325e8a1282dfd30c3e44928c6384bb978649c63 Mon Sep 17 00:00:00 2001 From: Jiapeng Chong Date: Thu, 3 Aug 2023 16:06:59 +0800 Subject: rcu-tasks: Make rcu_tasks_lazy_ms static The rcu_tasks_lazy_ms variable is not used outside the file tasks.h, so this commit marks it static. kernel/rcu/tasks.h:1085:5: warning: symbol 'rcu_tasks_lazy_ms' was not declared. Should it be static? Reported-by: Abaci Robot Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=6086 Signed-off-by: Jiapeng Chong Reviewed-by: Joel Fernandes (Google) Signed-off-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker --- kernel/rcu/tasks.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/rcu/tasks.h') diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 94bb5abdbb37..018f03f20629 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -1086,7 +1086,7 @@ void rcu_barrier_tasks(void) } EXPORT_SYMBOL_GPL(rcu_barrier_tasks); -int rcu_tasks_lazy_ms = -1; +static int rcu_tasks_lazy_ms = -1; module_param(rcu_tasks_lazy_ms, int, 0444); static int __init rcu_spawn_tasks_kthread(void) -- cgit From 2cbc482d325ee58001472c4359b311958c4efdd1 Mon Sep 17 00:00:00 2001 From: Zhen Lei Date: Sat, 5 Aug 2023 11:17:26 +0800 Subject: rcu: Dump memory object info if callback function is invalid When a structure containing an RCU callback rhp is (incorrectly) freed and reallocated after rhp is passed to call_rcu(), it is not unusual for rhp->func to be set to NULL. This defeats the debugging prints used by __call_rcu_common() in kernels built with CONFIG_DEBUG_OBJECTS_RCU_HEAD=y, which expect to identify the offending code using the identity of this function. And in kernels build without CONFIG_DEBUG_OBJECTS_RCU_HEAD=y, things are even worse, as can be seen from this splat: Unable to handle kernel NULL pointer dereference at virtual address 0 ... ... PC is at 0x0 LR is at rcu_do_batch+0x1c0/0x3b8 ... ... (rcu_do_batch) from (rcu_core+0x1d4/0x284) (rcu_core) from (__do_softirq+0x24c/0x344) (__do_softirq) from (__irq_exit_rcu+0x64/0x108) (__irq_exit_rcu) from (irq_exit+0x8/0x10) (irq_exit) from (__handle_domain_irq+0x74/0x9c) (__handle_domain_irq) from (gic_handle_irq+0x8c/0x98) (gic_handle_irq) from (__irq_svc+0x5c/0x94) (__irq_svc) from (arch_cpu_idle+0x20/0x3c) (arch_cpu_idle) from (default_idle_call+0x4c/0x78) (default_idle_call) from (do_idle+0xf8/0x150) (do_idle) from (cpu_startup_entry+0x18/0x20) (cpu_startup_entry) from (0xc01530) This commit therefore adds calls to mem_dump_obj(rhp) to output some information, for example: slab kmalloc-256 start ffff410c45019900 pointer offset 0 size 256 This provides the rough size of the memory block and the offset of the rcu_head structure, which as least provides at least a few clues to help locate the problem. If the problem is reproducible, additional slab debugging can be enabled, for example, CONFIG_DEBUG_SLAB=y, which can provide significantly more information. Signed-off-by: Zhen Lei Signed-off-by: Paul E. McKenney Signed-off-by: Frederic Weisbecker --- kernel/rcu/tasks.h | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/rcu/tasks.h') diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 8d65f7d576a3..7c845532a50a 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -538,6 +538,7 @@ static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpu raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags); len = rcl.len; for (rhp = rcu_cblist_dequeue(&rcl); rhp; rhp = rcu_cblist_dequeue(&rcl)) { + debug_rcu_head_callback(rhp); local_bh_disable(); rhp->func(rhp); local_bh_enable(); -- cgit