From 8315f42295d2667a7f942f154b73a86fd7cb2227 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 27 Jun 2014 13:42:20 -0700 Subject: rcu: Add call_rcu_tasks() This commit adds a new RCU-tasks flavor of RCU, which provides call_rcu_tasks(). This RCU flavor's quiescent states are voluntary context switch (not preemption!) and userspace execution (not the idle loop -- use some sort of schedule_on_each_cpu() if you need to handle the idle tasks. Note that unlike other RCU flavors, these quiescent states occur in tasks, not necessarily CPUs. Includes fixes from Steven Rostedt. This RCU flavor is assumed to have very infrequent latency-tolerant updaters. This assumption permits significant simplifications, including a single global callback list protected by a single global lock, along with a single task-private linked list containing all tasks that have not yet passed through a quiescent state. If experience shows this assumption to be incorrect, the required additional complexity will be added. Suggested-by: Steven Rostedt Signed-off-by: Paul E. McKenney --- kernel/rcu/update.c | 171 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 171 insertions(+) (limited to 'kernel/rcu/update.c') diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 4056d7992a6c..19b3dacb0753 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -47,6 +47,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS @@ -347,3 +348,173 @@ static int __init check_cpu_stall_init(void) early_initcall(check_cpu_stall_init); #endif /* #ifdef CONFIG_RCU_STALL_COMMON */ + +#ifdef CONFIG_TASKS_RCU + +/* + * Simple variant of RCU whose quiescent states are voluntary context switch, + * user-space execution, and idle. As such, grace periods can take one good + * long time. There are no read-side primitives similar to rcu_read_lock() + * and rcu_read_unlock() because this implementation is intended to get + * the system into a safe state for some of the manipulations involved in + * tracing and the like. Finally, this implementation does not support + * high call_rcu_tasks() rates from multiple CPUs. If this is required, + * per-CPU callback lists will be needed. + */ + +/* Global list of callbacks and associated lock. */ +static struct rcu_head *rcu_tasks_cbs_head; +static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head; +static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock); + +/* Post an RCU-tasks callback. */ +void call_rcu_tasks(struct rcu_head *rhp, void (*func)(struct rcu_head *rhp)) +{ + unsigned long flags; + + rhp->next = NULL; + rhp->func = func; + raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags); + *rcu_tasks_cbs_tail = rhp; + rcu_tasks_cbs_tail = &rhp->next; + raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags); +} +EXPORT_SYMBOL_GPL(call_rcu_tasks); + +/* See if the current task has stopped holding out, remove from list if so. */ +static void check_holdout_task(struct task_struct *t) +{ + if (!ACCESS_ONCE(t->rcu_tasks_holdout) || + t->rcu_tasks_nvcsw != ACCESS_ONCE(t->nvcsw) || + !ACCESS_ONCE(t->on_rq)) { + ACCESS_ONCE(t->rcu_tasks_holdout) = false; + list_del_rcu(&t->rcu_tasks_holdout_list); + put_task_struct(t); + } +} + +/* RCU-tasks kthread that detects grace periods and invokes callbacks. */ +static int __noreturn rcu_tasks_kthread(void *arg) +{ + unsigned long flags; + struct task_struct *g, *t; + struct rcu_head *list; + struct rcu_head *next; + LIST_HEAD(rcu_tasks_holdouts); + + /* FIXME: Add housekeeping affinity. */ + + /* + * Each pass through the following loop makes one check for + * newly arrived callbacks, and, if there are some, waits for + * one RCU-tasks grace period and then invokes the callbacks. + * This loop is terminated by the system going down. ;-) + */ + for (;;) { + + /* Pick up any new callbacks. */ + raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags); + list = rcu_tasks_cbs_head; + rcu_tasks_cbs_head = NULL; + rcu_tasks_cbs_tail = &rcu_tasks_cbs_head; + raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags); + + /* If there were none, wait a bit and start over. */ + if (!list) { + schedule_timeout_interruptible(HZ); + WARN_ON(signal_pending(current)); + continue; + } + + /* + * Wait for all pre-existing t->on_rq and t->nvcsw + * transitions to complete. Invoking synchronize_sched() + * suffices because all these transitions occur with + * interrupts disabled. Without this synchronize_sched(), + * a read-side critical section that started before the + * grace period might be incorrectly seen as having started + * after the grace period. + * + * This synchronize_sched() also dispenses with the + * need for a memory barrier on the first store to + * ->rcu_tasks_holdout, as it forces the store to happen + * after the beginning of the grace period. + */ + synchronize_sched(); + + /* + * There were callbacks, so we need to wait for an + * RCU-tasks grace period. Start off by scanning + * the task list for tasks that are not already + * voluntarily blocked. Mark these tasks and make + * a list of them in rcu_tasks_holdouts. + */ + rcu_read_lock(); + for_each_process_thread(g, t) { + if (t != current && ACCESS_ONCE(t->on_rq) && + !is_idle_task(t)) { + get_task_struct(t); + t->rcu_tasks_nvcsw = ACCESS_ONCE(t->nvcsw); + ACCESS_ONCE(t->rcu_tasks_holdout) = true; + list_add(&t->rcu_tasks_holdout_list, + &rcu_tasks_holdouts); + } + } + rcu_read_unlock(); + + /* + * Each pass through the following loop scans the list + * of holdout tasks, removing any that are no longer + * holdouts. When the list is empty, we are done. + */ + while (!list_empty(&rcu_tasks_holdouts)) { + schedule_timeout_interruptible(HZ); + WARN_ON(signal_pending(current)); + rcu_read_lock(); + list_for_each_entry_rcu(t, &rcu_tasks_holdouts, + rcu_tasks_holdout_list) + check_holdout_task(t); + rcu_read_unlock(); + } + + /* + * Because ->on_rq and ->nvcsw are not guaranteed + * to have a full memory barriers prior to them in the + * schedule() path, memory reordering on other CPUs could + * cause their RCU-tasks read-side critical sections to + * extend past the end of the grace period. However, + * because these ->nvcsw updates are carried out with + * interrupts disabled, we can use synchronize_sched() + * to force the needed ordering on all such CPUs. + * + * This synchronize_sched() also confines all + * ->rcu_tasks_holdout accesses to be within the grace + * period, avoiding the need for memory barriers for + * ->rcu_tasks_holdout accesses. + */ + synchronize_sched(); + + /* Invoke the callbacks. */ + while (list) { + next = list->next; + local_bh_disable(); + list->func(list); + local_bh_enable(); + list = next; + cond_resched(); + } + } +} + +/* Spawn rcu_tasks_kthread() at boot time. */ +static int __init rcu_spawn_tasks_kthread(void) +{ + struct task_struct __maybe_unused *t; + + t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread"); + BUG_ON(IS_ERR(t)); + return 0; +} +early_initcall(rcu_spawn_tasks_kthread); + +#endif /* #ifdef CONFIG_TASKS_RCU */ -- cgit v1.2.3-58-ga151 From 53c6d4edf874d3cbc031a53738c6cba9277faea5 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 1 Jul 2014 12:22:23 -0700 Subject: rcu: Add synchronous grace-period waiting for RCU-tasks It turns out to be easier to add the synchronous grace-period waiting functions to RCU-tasks than to work around their absense in rcutorture, so this commit adds them. The key point is that the existence of call_rcu_tasks() means that rcutorture needs an rcu_barrier_tasks(). Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 2 ++ kernel/rcu/update.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) (limited to 'kernel/rcu/update.c') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 473350462d04..640152fedcde 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -216,6 +216,8 @@ void synchronize_sched(void); * memory ordering guarantees. */ void call_rcu_tasks(struct rcu_head *head, void (*func)(struct rcu_head *head)); +void synchronize_rcu_tasks(void); +void rcu_barrier_tasks(void); #ifdef CONFIG_PREEMPT_RCU diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 19b3dacb0753..5fd1ddbfcc55 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -381,6 +381,61 @@ void call_rcu_tasks(struct rcu_head *rhp, void (*func)(struct rcu_head *rhp)) } EXPORT_SYMBOL_GPL(call_rcu_tasks); +/** + * synchronize_rcu_tasks - wait until an rcu-tasks grace period has elapsed. + * + * Control will return to the caller some time after a full rcu-tasks + * grace period has elapsed, in other words after all currently + * executing rcu-tasks read-side critical sections have elapsed. These + * read-side critical sections are delimited by calls to schedule(), + * cond_resched_rcu_qs(), idle execution, userspace execution, calls + * to synchronize_rcu_tasks(), and (in theory, anyway) cond_resched(). + * + * This is a very specialized primitive, intended only for a few uses in + * tracing and other situations requiring manipulation of function + * preambles and profiling hooks. The synchronize_rcu_tasks() function + * is not (yet) intended for heavy use from multiple CPUs. + * + * Note that this guarantee implies further memory-ordering guarantees. + * On systems with more than one CPU, when synchronize_rcu_tasks() returns, + * each CPU is guaranteed to have executed a full memory barrier since the + * end of its last RCU-tasks read-side critical section whose beginning + * preceded the call to synchronize_rcu_tasks(). In addition, each CPU + * having an RCU-tasks read-side critical section that extends beyond + * the return from synchronize_rcu_tasks() is guaranteed to have executed + * a full memory barrier after the beginning of synchronize_rcu_tasks() + * and before the beginning of that RCU-tasks read-side critical section. + * Note that these guarantees include CPUs that are offline, idle, or + * executing in user mode, as well as CPUs that are executing in the kernel. + * + * Furthermore, if CPU A invoked synchronize_rcu_tasks(), which returned + * to its caller on CPU B, then both CPU A and CPU B are guaranteed + * to have executed a full memory barrier during the execution of + * synchronize_rcu_tasks() -- even if CPU A and CPU B are the same CPU + * (but again only if the system has more than one CPU). + */ +void synchronize_rcu_tasks(void) +{ + /* Complain if the scheduler has not started. */ + rcu_lockdep_assert(!rcu_scheduler_active, + "synchronize_rcu_tasks called too soon"); + + /* Wait for the grace period. */ + wait_rcu_gp(call_rcu_tasks); +} + +/** + * rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks. + * + * Although the current implementation is guaranteed to wait, it is not + * obligated to, for example, if there are no pending callbacks. + */ +void rcu_barrier_tasks(void) +{ + /* There is only one callback queue, so this is easy. ;-) */ + synchronize_rcu_tasks(); +} + /* See if the current task has stopped holding out, remove from list if so. */ static void check_holdout_task(struct task_struct *t) { -- cgit v1.2.3-58-ga151 From 3f95aa81d265223fdb13ea2b59883766a05adbdf Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 4 Aug 2014 06:10:23 -0700 Subject: rcu: Make TASKS_RCU handle tasks that are almost done exiting Once a task has passed exit_notify() in the do_exit() code path, it is no longer on the task lists, and is therefore no longer visible to rcu_tasks_kthread(). This means that an almost-exited task might be preempted while within a trampoline, and this task won't be waited on by rcu_tasks_kthread(). This commit fixes this bug by adding an srcu_struct. An exiting task does srcu_read_lock() just before calling exit_notify(), and does the corresponding srcu_read_unlock() after doing the final preempt_disable(). This means that rcu_tasks_kthread() can do synchronize_srcu() to wait for all mostly-exited tasks to reach their final preempt_disable() region, and then use synchronize_sched() to wait for those tasks to finish exiting. Reported-by: Oleg Nesterov Suggested-by: Lai Jiangshan Signed-off-by: Paul E. McKenney --- include/linux/rcupdate.h | 3 +++ kernel/exit.c | 3 +++ kernel/rcu/update.c | 21 +++++++++++++++++++++ 3 files changed, 27 insertions(+) (limited to 'kernel/rcu/update.c') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 640152fedcde..54b2ebb20313 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -321,6 +321,8 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev, * macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU +#define TASKS_RCU(x) x +extern struct srcu_struct tasks_rcu_exit_srcu; #define rcu_note_voluntary_context_switch(t) \ do { \ preempt_disable(); /* Exclude synchronize_sched(); */ \ @@ -329,6 +331,7 @@ static inline void rcu_user_hooks_switch(struct task_struct *prev, preempt_enable(); \ } while (0) #else /* #ifdef CONFIG_TASKS_RCU */ +#define TASKS_RCU(x) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #endif /* #else #ifdef CONFIG_TASKS_RCU */ diff --git a/kernel/exit.c b/kernel/exit.c index 32c58f7433a3..d13f2eec4bb8 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -667,6 +667,7 @@ void do_exit(long code) { struct task_struct *tsk = current; int group_dead; + TASKS_RCU(int tasks_rcu_i); profile_task_exit(tsk); @@ -775,6 +776,7 @@ void do_exit(long code) */ flush_ptrace_hw_breakpoint(tsk); + TASKS_RCU(tasks_rcu_i = __srcu_read_lock(&tasks_rcu_exit_srcu)); exit_notify(tsk, group_dead); proc_exit_connector(tsk); #ifdef CONFIG_NUMA @@ -814,6 +816,7 @@ void do_exit(long code) if (tsk->nr_dirtied) __this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied); exit_rcu(); + TASKS_RCU(__srcu_read_unlock(&tasks_rcu_exit_srcu, tasks_rcu_i)); /* * The setting of TASK_RUNNING by try_to_wake_up() may be delayed diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 5fd1ddbfcc55..403fc4ae539e 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -367,6 +367,13 @@ static struct rcu_head *rcu_tasks_cbs_head; static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head; static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock); +/* Track exiting tasks in order to allow them to be waited for. */ +DEFINE_SRCU(tasks_rcu_exit_srcu); + +/* Control stall timeouts. Disable with <= 0, otherwise jiffies till stall. */ +static int rcu_task_stall_timeout __read_mostly = HZ * 60 * 3; +module_param(rcu_task_stall_timeout, int, 0644); + /* Post an RCU-tasks callback. */ void call_rcu_tasks(struct rcu_head *rhp, void (*func)(struct rcu_head *rhp)) { @@ -517,6 +524,15 @@ static int __noreturn rcu_tasks_kthread(void *arg) } rcu_read_unlock(); + /* + * Wait for tasks that are in the process of exiting. + * This does only part of the job, ensuring that all + * tasks that were previously exiting reach the point + * where they have disabled preemption, allowing the + * later synchronize_sched() to finish the job. + */ + synchronize_srcu(&tasks_rcu_exit_srcu); + /* * Each pass through the following loop scans the list * of holdout tasks, removing any that are no longer @@ -546,6 +562,11 @@ static int __noreturn rcu_tasks_kthread(void *arg) * ->rcu_tasks_holdout accesses to be within the grace * period, avoiding the need for memory barriers for * ->rcu_tasks_holdout accesses. + * + * In addition, this synchronize_sched() waits for exiting + * tasks to complete their final preempt_disable() region + * of execution, cleaning up after the synchronize_srcu() + * above. */ synchronize_sched(); -- cgit v1.2.3-58-ga151 From 06c2a9238fad48ec38f1be00455bf942d54377ee Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 2 Jul 2014 18:17:19 -0700 Subject: rcu: Export RCU-tasks APIs to GPL modules This commit exports the RCU-tasks synchronous APIs, synchronize_rcu_tasks() and rcu_barrier_tasks(), to GPL-licensed kernel modules. Signed-off-by: Steven Rostedt Signed-off-by: Paul E. McKenney Reviewed-by: Josh Triplett --- kernel/rcu/update.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/rcu/update.c') diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 403fc4ae539e..aef8109152ce 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -430,6 +430,7 @@ void synchronize_rcu_tasks(void) /* Wait for the grace period. */ wait_rcu_gp(call_rcu_tasks); } +EXPORT_SYMBOL_GPL(synchronize_rcu_tasks); /** * rcu_barrier_tasks - Wait for in-flight call_rcu_tasks() callbacks. @@ -442,6 +443,7 @@ void rcu_barrier_tasks(void) /* There is only one callback queue, so this is easy. ;-) */ synchronize_rcu_tasks(); } +EXPORT_SYMBOL_GPL(rcu_barrier_tasks); /* See if the current task has stopped holding out, remove from list if so. */ static void check_holdout_task(struct task_struct *t) -- cgit v1.2.3-58-ga151 From 52db30ab23b6d00cf80b22a510c4ea4be4458031 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 1 Jul 2014 18:16:30 -0700 Subject: rcu: Add stall-warning checks for RCU-tasks This commit adds a ten-minute RCU-tasks stall warning. The actual time is controlled by the boot/sysfs parameter rcu_task_stall_timeout, with values less than or equal to zero disabling the stall warnings. The default value is ten minutes, which means that the tasks that have not yet responded will get their stacks dumped every ten minutes, until they pass through a voluntary context switch. Signed-off-by: Paul E. McKenney --- Documentation/kernel-parameters.txt | 5 +++++ kernel/rcu/update.c | 29 +++++++++++++++++++++++++---- 2 files changed, 30 insertions(+), 4 deletions(-) (limited to 'kernel/rcu/update.c') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 5ae8608ca9f5..e98be953d96c 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2982,6 +2982,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. rcupdate.rcu_cpu_stall_timeout= [KNL] Set timeout for RCU CPU stall warning messages. + rcupdate.rcu_task_stall_timeout= [KNL] + Set timeout in jiffies for RCU task stall warning + messages. Disable with a value less than or equal + to zero. + rdinit= [KNL] Format: Run specified binary instead of /init from the ramdisk, diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index aef8109152ce..bad7dbd4c2e3 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -371,7 +371,7 @@ static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock); DEFINE_SRCU(tasks_rcu_exit_srcu); /* Control stall timeouts. Disable with <= 0, otherwise jiffies till stall. */ -static int rcu_task_stall_timeout __read_mostly = HZ * 60 * 3; +static int rcu_task_stall_timeout __read_mostly = HZ * 60 * 10; module_param(rcu_task_stall_timeout, int, 0644); /* Post an RCU-tasks callback. */ @@ -445,8 +445,9 @@ void rcu_barrier_tasks(void) } EXPORT_SYMBOL_GPL(rcu_barrier_tasks); -/* See if the current task has stopped holding out, remove from list if so. */ -static void check_holdout_task(struct task_struct *t) +/* See if tasks are still holding out, complain if so. */ +static void check_holdout_task(struct task_struct *t, + bool needreport, bool *firstreport) { if (!ACCESS_ONCE(t->rcu_tasks_holdout) || t->rcu_tasks_nvcsw != ACCESS_ONCE(t->nvcsw) || @@ -454,7 +455,15 @@ static void check_holdout_task(struct task_struct *t) ACCESS_ONCE(t->rcu_tasks_holdout) = false; list_del_rcu(&t->rcu_tasks_holdout_list); put_task_struct(t); + return; } + if (!needreport) + return; + if (*firstreport) { + pr_err("INFO: rcu_tasks detected stalls on tasks:\n"); + *firstreport = false; + } + sched_show_task(t); } /* RCU-tasks kthread that detects grace periods and invokes callbacks. */ @@ -462,6 +471,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) { unsigned long flags; struct task_struct *g, *t; + unsigned long lastreport; struct rcu_head *list; struct rcu_head *next; LIST_HEAD(rcu_tasks_holdouts); @@ -540,13 +550,24 @@ static int __noreturn rcu_tasks_kthread(void *arg) * of holdout tasks, removing any that are no longer * holdouts. When the list is empty, we are done. */ + lastreport = jiffies; while (!list_empty(&rcu_tasks_holdouts)) { + bool firstreport; + bool needreport; + int rtst; + schedule_timeout_interruptible(HZ); + rtst = ACCESS_ONCE(rcu_task_stall_timeout); + needreport = rtst > 0 && + time_after(jiffies, lastreport + rtst); + if (needreport) + lastreport = jiffies; + firstreport = true; WARN_ON(signal_pending(current)); rcu_read_lock(); list_for_each_entry_rcu(t, &rcu_tasks_holdouts, rcu_tasks_holdout_list) - check_holdout_task(t); + check_holdout_task(t, needreport, &firstreport); rcu_read_unlock(); } -- cgit v1.2.3-58-ga151 From c7b24d2b9a0f2ce19fdf631d3148c80a8f6010b1 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 28 Jul 2014 14:39:25 -0700 Subject: rcu: Improve RCU-tasks energy efficiency The current RCU-tasks implementation uses strict polling to detect callback arrivals. This works quite well, but is not so good for energy efficiency. This commit therefore replaces the strict polling with a wait queue. Signed-off-by: Paul E. McKenney --- kernel/rcu/update.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'kernel/rcu/update.c') diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index bad7dbd4c2e3..444c8a303963 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -365,6 +365,7 @@ early_initcall(check_cpu_stall_init); /* Global list of callbacks and associated lock. */ static struct rcu_head *rcu_tasks_cbs_head; static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head; +static DECLARE_WAIT_QUEUE_HEAD(rcu_tasks_cbs_wq); static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock); /* Track exiting tasks in order to allow them to be waited for. */ @@ -378,13 +379,17 @@ module_param(rcu_task_stall_timeout, int, 0644); void call_rcu_tasks(struct rcu_head *rhp, void (*func)(struct rcu_head *rhp)) { unsigned long flags; + bool needwake; rhp->next = NULL; rhp->func = func; raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags); + needwake = !rcu_tasks_cbs_head; *rcu_tasks_cbs_tail = rhp; rcu_tasks_cbs_tail = &rhp->next; raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags); + if (needwake) + wake_up(&rcu_tasks_cbs_wq); } EXPORT_SYMBOL_GPL(call_rcu_tasks); @@ -495,8 +500,12 @@ static int __noreturn rcu_tasks_kthread(void *arg) /* If there were none, wait a bit and start over. */ if (!list) { - schedule_timeout_interruptible(HZ); - WARN_ON(signal_pending(current)); + wait_event_interruptible(rcu_tasks_cbs_wq, + rcu_tasks_cbs_head); + if (!rcu_tasks_cbs_head) { + WARN_ON(signal_pending(current)); + schedule_timeout_interruptible(HZ/10); + } continue; } @@ -602,6 +611,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) list = next; cond_resched(); } + schedule_timeout_uninterruptible(HZ/10); } } -- cgit v1.2.3-58-ga151 From 84a8f446ffd70c2799a96268aaa4d47c22a83ff0 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 4 Aug 2014 07:24:21 -0700 Subject: rcu: Defer rcu_tasks_kthread() creation till first call_rcu_tasks() It is expected that many sites will have CONFIG_TASKS_RCU=y, but will never actually invoke call_rcu_tasks(). For such sites, creating rcu_tasks_kthread() at boot is wasteful. This commit therefore defers creation of this kthread until the time of the first call_rcu_tasks(). This of course means that the first call_rcu_tasks() must be invoked from process context after the scheduler is fully operational. Signed-off-by: Paul E. McKenney --- kernel/rcu/update.c | 33 ++++++++++++++++++++++++++------- 1 file changed, 26 insertions(+), 7 deletions(-) (limited to 'kernel/rcu/update.c') diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 444c8a303963..e1d71741958f 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -375,7 +375,12 @@ DEFINE_SRCU(tasks_rcu_exit_srcu); static int rcu_task_stall_timeout __read_mostly = HZ * 60 * 10; module_param(rcu_task_stall_timeout, int, 0644); -/* Post an RCU-tasks callback. */ +static void rcu_spawn_tasks_kthread(void); + +/* + * Post an RCU-tasks callback. First call must be from process context + * after the scheduler if fully operational. + */ void call_rcu_tasks(struct rcu_head *rhp, void (*func)(struct rcu_head *rhp)) { unsigned long flags; @@ -388,8 +393,10 @@ void call_rcu_tasks(struct rcu_head *rhp, void (*func)(struct rcu_head *rhp)) *rcu_tasks_cbs_tail = rhp; rcu_tasks_cbs_tail = &rhp->next; raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags); - if (needwake) + if (needwake) { + rcu_spawn_tasks_kthread(); wake_up(&rcu_tasks_cbs_wq); + } } EXPORT_SYMBOL_GPL(call_rcu_tasks); @@ -615,15 +622,27 @@ static int __noreturn rcu_tasks_kthread(void *arg) } } -/* Spawn rcu_tasks_kthread() at boot time. */ -static int __init rcu_spawn_tasks_kthread(void) +/* Spawn rcu_tasks_kthread() at first call to call_rcu_tasks(). */ +static void rcu_spawn_tasks_kthread(void) { - struct task_struct __maybe_unused *t; + static DEFINE_MUTEX(rcu_tasks_kthread_mutex); + static struct task_struct *rcu_tasks_kthread_ptr; + struct task_struct *t; + if (ACCESS_ONCE(rcu_tasks_kthread_ptr)) { + smp_mb(); /* Ensure caller sees full kthread. */ + return; + } + mutex_lock(&rcu_tasks_kthread_mutex); + if (rcu_tasks_kthread_ptr) { + mutex_unlock(&rcu_tasks_kthread_mutex); + return; + } t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread"); BUG_ON(IS_ERR(t)); - return 0; + smp_mb(); /* Ensure others see full kthread. */ + ACCESS_ONCE(rcu_tasks_kthread_ptr) = t; + mutex_unlock(&rcu_tasks_kthread_mutex); } -early_initcall(rcu_spawn_tasks_kthread); #endif /* #ifdef CONFIG_TASKS_RCU */ -- cgit v1.2.3-58-ga151 From 176f8f7a52cc6d09d686f0d900abda6942a52fbb Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 4 Aug 2014 17:43:50 -0700 Subject: rcu: Make TASKS_RCU handle nohz_full= CPUs Currently TASKS_RCU would ignore a CPU running a task in nohz_full= usermode execution. There would be neither a context switch nor a scheduling-clock interrupt to tell TASKS_RCU that the task in question had passed through a quiescent state. The grace period would therefore extend indefinitely. This commit therefore makes RCU's dyntick-idle subsystem record the task_struct structure of the task that is running in dyntick-idle mode on each CPU. The TASKS_RCU grace period can then access this information and record a quiescent state on behalf of any CPU running in dyntick-idle usermode. Signed-off-by: Paul E. McKenney --- include/linux/init_task.h | 3 ++- include/linux/sched.h | 2 ++ kernel/rcu/tree.c | 2 ++ kernel/rcu/tree.h | 2 ++ kernel/rcu/tree_plugin.h | 16 ++++++++++++++++ kernel/rcu/update.c | 4 +++- 6 files changed, 27 insertions(+), 2 deletions(-) (limited to 'kernel/rcu/update.c') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index dffd9258ee60..03b274873b06 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -121,7 +121,8 @@ extern struct group_info init_groups; #define INIT_TASK_RCU_TASKS(tsk) \ .rcu_tasks_holdout = false, \ .rcu_tasks_holdout_list = \ - LIST_HEAD_INIT(tsk.rcu_tasks_holdout_list), + LIST_HEAD_INIT(tsk.rcu_tasks_holdout_list), \ + .rcu_tasks_idle_cpu = -1, #else #define INIT_TASK_RCU_TASKS(tsk) #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index eaacac4ae77d..ec8b34722bcc 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1274,6 +1274,7 @@ struct task_struct { unsigned long rcu_tasks_nvcsw; bool rcu_tasks_holdout; struct list_head rcu_tasks_holdout_list; + int rcu_tasks_idle_cpu; #endif /* #ifdef CONFIG_TASKS_RCU */ #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) @@ -2020,6 +2021,7 @@ static inline void rcu_copy_process(struct task_struct *p) #ifdef CONFIG_TASKS_RCU p->rcu_tasks_holdout = false; INIT_LIST_HEAD(&p->rcu_tasks_holdout_list); + p->rcu_tasks_idle_cpu = -1; #endif /* #ifdef CONFIG_TASKS_RCU */ } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index e23dad0661e2..c880f5387b1f 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -526,6 +526,7 @@ static void rcu_eqs_enter_common(struct rcu_dynticks *rdtp, long long oldval, atomic_inc(&rdtp->dynticks); smp_mb__after_atomic(); /* Force ordering with next sojourn. */ WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); + rcu_dynticks_task_enter(); /* * It is illegal to enter an extended quiescent state while @@ -642,6 +643,7 @@ void rcu_irq_exit(void) static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval, int user) { + rcu_dynticks_task_exit(); smp_mb__before_atomic(); /* Force ordering w/previous sojourn. */ atomic_inc(&rdtp->dynticks); /* CPUs seeing atomic_inc() must see later RCU read-side crit sects */ diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 6a86eb7bac45..3a92000c354f 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -605,6 +605,8 @@ static void rcu_sysidle_report_gp(struct rcu_state *rsp, int isidle, static void rcu_bind_gp_kthread(void); static void rcu_sysidle_init_percpu_data(struct rcu_dynticks *rdtp); static bool rcu_nohz_full_cpu(struct rcu_state *rsp); +static void rcu_dynticks_task_enter(void); +static void rcu_dynticks_task_exit(void); #endif /* #ifndef RCU_TREE_NONCORE */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 7672586d3920..e466b40052a7 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -3036,3 +3036,19 @@ static void rcu_bind_gp_kthread(void) housekeeping_affine(current); #endif /* #else #ifdef CONFIG_NO_HZ_FULL_SYSIDLE */ } + +/* Record the current task on dyntick-idle entry. */ +static void rcu_dynticks_task_enter(void) +{ +#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) + ACCESS_ONCE(current->rcu_tasks_idle_cpu) = smp_processor_id(); +#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */ +} + +/* Record no current task on dyntick-idle exit. */ +static void rcu_dynticks_task_exit(void) +{ +#if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) + ACCESS_ONCE(current->rcu_tasks_idle_cpu) = -1; +#endif /* #if defined(CONFIG_TASKS_RCU) && defined(CONFIG_NO_HZ_FULL) */ +} diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index e1d71741958f..2658de4a5975 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -463,7 +463,9 @@ static void check_holdout_task(struct task_struct *t, { if (!ACCESS_ONCE(t->rcu_tasks_holdout) || t->rcu_tasks_nvcsw != ACCESS_ONCE(t->nvcsw) || - !ACCESS_ONCE(t->on_rq)) { + !ACCESS_ONCE(t->on_rq) || + (IS_ENABLED(CONFIG_NO_HZ_FULL) && + !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) { ACCESS_ONCE(t->rcu_tasks_holdout) = false; list_del_rcu(&t->rcu_tasks_holdout_list); put_task_struct(t); -- cgit v1.2.3-58-ga151 From 8f20a5e83d2c5d0e126a2fc9bca67f7430dac907 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 5 Aug 2014 05:10:24 -0700 Subject: rcu: Make rcu_tasks_kthread()'s GP-wait loop allow preemption The grace-period-wait loop in rcu_tasks_kthread() is under (unnecessary) RCU protection, and therefore has no preemption points in a PREEMPT=n kernel. This commit therefore removes the RCU protection and inserts cond_resched(). Reported-by: Frederic Weisbecker Signed-off-by: Paul E. McKenney --- kernel/rcu/update.c | 11 ++++++----- 1 file changed, 6 insertions(+), 5 deletions(-) (limited to 'kernel/rcu/update.c') diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 2658de4a5975..f86d1ae50005 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -467,7 +467,7 @@ static void check_holdout_task(struct task_struct *t, (IS_ENABLED(CONFIG_NO_HZ_FULL) && !is_idle_task(t) && t->rcu_tasks_idle_cpu >= 0)) { ACCESS_ONCE(t->rcu_tasks_holdout) = false; - list_del_rcu(&t->rcu_tasks_holdout_list); + list_del_init(&t->rcu_tasks_holdout_list); put_task_struct(t); return; } @@ -573,6 +573,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) bool firstreport; bool needreport; int rtst; + struct task_struct *t1; schedule_timeout_interruptible(HZ); rtst = ACCESS_ONCE(rcu_task_stall_timeout); @@ -582,11 +583,11 @@ static int __noreturn rcu_tasks_kthread(void *arg) lastreport = jiffies; firstreport = true; WARN_ON(signal_pending(current)); - rcu_read_lock(); - list_for_each_entry_rcu(t, &rcu_tasks_holdouts, - rcu_tasks_holdout_list) + list_for_each_entry_safe(t, t1, &rcu_tasks_holdouts, + rcu_tasks_holdout_list) { check_holdout_task(t, needreport, &firstreport); - rcu_read_unlock(); + cond_resched(); + } } /* -- cgit v1.2.3-58-ga151 From 4ff475ed4cf61a7f56bbfbc424147189d0022b38 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 10 Aug 2014 19:47:12 -0700 Subject: rcu: Additional information on RCU-tasks stall-warning messages Signed-off-by: Paul E. McKenney --- kernel/rcu/update.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'kernel/rcu/update.c') diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index f86d1ae50005..9487b4898e51 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -48,6 +48,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS @@ -461,6 +462,8 @@ EXPORT_SYMBOL_GPL(rcu_barrier_tasks); static void check_holdout_task(struct task_struct *t, bool needreport, bool *firstreport) { + int cpu; + if (!ACCESS_ONCE(t->rcu_tasks_holdout) || t->rcu_tasks_nvcsw != ACCESS_ONCE(t->nvcsw) || !ACCESS_ONCE(t->on_rq) || @@ -477,6 +480,12 @@ static void check_holdout_task(struct task_struct *t, pr_err("INFO: rcu_tasks detected stalls on tasks:\n"); *firstreport = false; } + cpu = task_cpu(t); + pr_alert("%p: %c%c nvcsw: %lu/%lu holdout: %d idle_cpu: %d/%d\n", + t, ".I"[is_idle_task(t)], + "N."[cpu < 0 || !tick_nohz_full_cpu(cpu)], + t->rcu_tasks_nvcsw, t->nvcsw, t->rcu_tasks_holdout, + t->rcu_tasks_idle_cpu, cpu); sched_show_task(t); } -- cgit v1.2.3-58-ga151 From 1d082fd061884a587c490c4fc8a2056ce1e47624 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 14 Aug 2014 16:01:53 -0700 Subject: rcu: Remove local_irq_disable() in rcu_preempt_note_context_switch() The rcu_preempt_note_context_switch() function is on a scheduling fast path, so it would be good to avoid disabling irqs. The reason that irqs are disabled is to synchronize process-level and irq-handler access to the task_struct ->rcu_read_unlock_special bitmask. This commit therefore makes ->rcu_read_unlock_special instead be a union of bools with a short allowing single-access checks in RCU's __rcu_read_unlock(). This results in the process-level and irq-handler accesses being simple loads and stores, so that irqs need no longer be disabled. This commit therefore removes the irq disabling from rcu_preempt_note_context_switch(). Reported-by: Peter Zijlstra Signed-off-by: Paul E. McKenney --- include/linux/init_task.h | 2 +- include/linux/sched.h | 16 +++++++++------- kernel/rcu/tree_plugin.h | 32 +++++++++++++++----------------- kernel/rcu/update.c | 2 +- 4 files changed, 26 insertions(+), 26 deletions(-) (limited to 'kernel/rcu/update.c') diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 03b274873b06..77fc43f8fb72 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -111,7 +111,7 @@ extern struct group_info init_groups; #ifdef CONFIG_PREEMPT_RCU #define INIT_TASK_RCU_PREEMPT(tsk) \ .rcu_read_lock_nesting = 0, \ - .rcu_read_unlock_special = 0, \ + .rcu_read_unlock_special.s = 0, \ .rcu_node_entry = LIST_HEAD_INIT(tsk.rcu_node_entry), \ INIT_TASK_RCU_TREE_PREEMPT() #else diff --git a/include/linux/sched.h b/include/linux/sched.h index ec8b34722bcc..42888d715fb1 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1212,6 +1212,13 @@ struct sched_dl_entity { struct hrtimer dl_timer; }; +union rcu_special { + struct { + bool blocked; + bool need_qs; + } b; + short s; +}; struct rcu_node; enum perf_event_task_context { @@ -1264,7 +1271,7 @@ struct task_struct { #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; - char rcu_read_unlock_special; + union rcu_special rcu_read_unlock_special; struct list_head rcu_node_entry; #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TREE_PREEMPT_RCU @@ -2005,16 +2012,11 @@ extern void task_clear_jobctl_trapping(struct task_struct *task); extern void task_clear_jobctl_pending(struct task_struct *task, unsigned int mask); -#ifdef CONFIG_PREEMPT_RCU -#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */ -#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */ -#endif /* #ifdef CONFIG_PREEMPT_RCU */ - static inline void rcu_copy_process(struct task_struct *p) { #ifdef CONFIG_PREEMPT_RCU p->rcu_read_lock_nesting = 0; - p->rcu_read_unlock_special = 0; + p->rcu_read_unlock_special.s = 0; p->rcu_blocked_node = NULL; INIT_LIST_HEAD(&p->rcu_node_entry); #endif /* #ifdef CONFIG_PREEMPT_RCU */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index e466b40052a7..0981c0cd70fe 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -155,9 +155,8 @@ EXPORT_SYMBOL_GPL(rcu_batches_completed); * not in a quiescent state. There might be any number of tasks blocked * while in an RCU read-side critical section. * - * Unlike the other rcu_*_qs() functions, callers to this function - * must disable irqs in order to protect the assignment to - * ->rcu_read_unlock_special. + * As with the other rcu_*_qs() functions, callers to this function + * must disable preemption. */ static void rcu_preempt_qs(int cpu) { @@ -166,7 +165,7 @@ static void rcu_preempt_qs(int cpu) if (rdp->passed_quiesce == 0) trace_rcu_grace_period(TPS("rcu_preempt"), rdp->gpnum, TPS("cpuqs")); rdp->passed_quiesce = 1; - current->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_NEED_QS; + current->rcu_read_unlock_special.b.need_qs = false; } /* @@ -190,14 +189,14 @@ static void rcu_preempt_note_context_switch(int cpu) struct rcu_node *rnp; if (t->rcu_read_lock_nesting > 0 && - (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) { + !t->rcu_read_unlock_special.b.blocked) { /* Possibly blocking in an RCU read-side critical section. */ rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu); rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); - t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED; + t->rcu_read_unlock_special.b.blocked = true; t->rcu_blocked_node = rnp; /* @@ -239,7 +238,7 @@ static void rcu_preempt_note_context_switch(int cpu) : rnp->gpnum + 1); raw_spin_unlock_irqrestore(&rnp->lock, flags); } else if (t->rcu_read_lock_nesting < 0 && - t->rcu_read_unlock_special) { + t->rcu_read_unlock_special.s) { /* * Complete exit from RCU read-side critical section on @@ -257,9 +256,7 @@ static void rcu_preempt_note_context_switch(int cpu) * grace period, then the fact that the task has been enqueued * means that we continue to block the current grace period. */ - local_irq_save(flags); rcu_preempt_qs(cpu); - local_irq_restore(flags); } /* @@ -340,7 +337,7 @@ void rcu_read_unlock_special(struct task_struct *t) bool drop_boost_mutex = false; #endif /* #ifdef CONFIG_RCU_BOOST */ struct rcu_node *rnp; - int special; + union rcu_special special; /* NMI handlers cannot block and cannot safely manipulate state. */ if (in_nmi()) @@ -350,12 +347,13 @@ void rcu_read_unlock_special(struct task_struct *t) /* * If RCU core is waiting for this CPU to exit critical section, - * let it know that we have done so. + * let it know that we have done so. Because irqs are disabled, + * t->rcu_read_unlock_special cannot change. */ special = t->rcu_read_unlock_special; - if (special & RCU_READ_UNLOCK_NEED_QS) { + if (special.b.need_qs) { rcu_preempt_qs(smp_processor_id()); - if (!t->rcu_read_unlock_special) { + if (!t->rcu_read_unlock_special.s) { local_irq_restore(flags); return; } @@ -368,8 +366,8 @@ void rcu_read_unlock_special(struct task_struct *t) } /* Clean up if blocked during RCU read-side critical section. */ - if (special & RCU_READ_UNLOCK_BLOCKED) { - t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BLOCKED; + if (special.b.blocked) { + t->rcu_read_unlock_special.b.blocked = false; /* * Remove this task from the list it blocked on. The @@ -658,7 +656,7 @@ static void rcu_preempt_check_callbacks(int cpu) } if (t->rcu_read_lock_nesting > 0 && per_cpu(rcu_preempt_data, cpu).qs_pending) - t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS; + t->rcu_read_unlock_special.b.need_qs = true; } #ifdef CONFIG_RCU_BOOST @@ -941,7 +939,7 @@ void exit_rcu(void) return; t->rcu_read_lock_nesting = 1; barrier(); - t->rcu_read_unlock_special = RCU_READ_UNLOCK_BLOCKED; + t->rcu_read_unlock_special.b.blocked = true; __rcu_read_unlock(); } diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 9487b4898e51..6fb911558562 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -93,7 +93,7 @@ void __rcu_read_unlock(void) barrier(); /* critical section before exit code. */ t->rcu_read_lock_nesting = INT_MIN; barrier(); /* assign before ->rcu_read_unlock_special load */ - if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) + if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special.s))) rcu_read_unlock_special(t); barrier(); /* ->rcu_read_unlock_special load before assign */ t->rcu_read_lock_nesting = 0; -- cgit v1.2.3-58-ga151