diff options
24 files changed, 614 insertions, 94 deletions
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt index 68fe3ad..ef5a2fd 100644 --- a/Documentation/RCU/stallwarn.txt +++ b/Documentation/RCU/stallwarn.txt @@ -56,8 +56,20 @@ RCU_STALL_RAT_DELAY two jiffies. (This is a cpp macro, not a kernel configuration parameter.) -When a CPU detects that it is stalling, it will print a message similar -to the following: +rcupdate.rcu_task_stall_timeout + + This boot/sysfs parameter controls the RCU-tasks stall warning + interval. A value of zero or less suppresses RCU-tasks stall + warnings. A positive value sets the stall-warning interval + in jiffies. An RCU-tasks stall warning starts wtih the line: + + INFO: rcu_tasks detected stalls on tasks: + + And continues with the output of sched_show_task() for each + task stalling the current RCU-tasks grace period. + +For non-RCU-tasks flavors of RCU, when a CPU detects that it is stalling, +it will print a message similar to the following: INFO: rcu_sched_state detected stall on CPU 5 (t=2500 jiffies) @@ -174,8 +186,12 @@ o A CPU looping with preemption disabled. This condition can o A CPU looping with bottom halves disabled. This condition can result in RCU-sched and RCU-bh stalls. -o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel - without invoking schedule(). +o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the + kernel without invoking schedule(). Note that cond_resched() + does not necessarily prevent RCU CPU stall warnings. Therefore, + if the looping in the kernel is really expected and desirable + behavior, you might need to replace some of the cond_resched() + calls with calls to cond_resched_rcu_qs(). o A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might happen to preempt a low-priority task in the middle of an RCU @@ -208,11 +224,10 @@ o A hardware failure. This is quite unlikely, but has occurred This resulted in a series of RCU CPU stall warnings, eventually leading the realization that the CPU had failed. -The RCU, RCU-sched, and RCU-bh implementations have CPU stall warning. -SRCU does not have its own CPU stall warnings, but its calls to -synchronize_sched() will result in RCU-sched detecting RCU-sched-related -CPU stalls. Please note that RCU only detects CPU stalls when there is -a grace period in progress. No grace period, no CPU stall warnings. +The RCU, RCU-sched, RCU-bh, and RCU-tasks implementations have CPU stall +warning. Note that SRCU does -not- have CPU stall warnings. Please note +that RCU only detects CPU stalls when there is a grace period in progress. +No grace period, no CPU stall warnings. To diagnose the cause of the stall, inspect the stack traces. The offending function will usually be near the top of the stack. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 0a104be..e1147bc 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3000,6 +3000,11 @@ 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: <full_path> Run specified binary instead of /init from the ramdisk, @@ -367,7 +367,7 @@ static struct fdtable *close_files(struct files_struct * files) struct file * file = xchg(&fdt->fd[i], NULL); if (file) { filp_close(file, files); - cond_resched(); + cond_resched_rcu_qs(); } } i++; diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 2bb4c4f3..77fc43f 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -111,12 +111,21 @@ 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 #define INIT_TASK_RCU_PREEMPT(tsk) #endif +#ifdef CONFIG_TASKS_RCU +#define INIT_TASK_RCU_TASKS(tsk) \ + .rcu_tasks_holdout = false, \ + .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 extern struct cred init_cred; @@ -224,6 +233,7 @@ extern struct task_group root_task_group; INIT_FTRACE_GRAPH \ INIT_TRACE_RECURSION \ INIT_TASK_RCU_PREEMPT(tsk) \ + INIT_TASK_RCU_TASKS(tsk) \ INIT_CPUSET_SEQ(tsk) \ INIT_RT_MUTEXES(tsk) \ INIT_VTIME(tsk) \ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 334ff89..5cafd60 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -55,6 +55,7 @@ enum rcutorture_type { RCU_FLAVOR, RCU_BH_FLAVOR, RCU_SCHED_FLAVOR, + RCU_TASKS_FLAVOR, SRCU_FLAVOR, INVALID_RCU_FLAVOR }; @@ -197,6 +198,28 @@ void call_rcu_sched(struct rcu_head *head, void synchronize_sched(void); +/** + * call_rcu_tasks() - Queue an RCU for invocation task-based grace period + * @head: structure to be used for queueing the RCU updates. + * @func: actual callback function to be invoked after the grace period + * + * The callback function will be invoked some time after a full grace + * period elapses, in other words after all currently executing RCU + * read-side critical sections have completed. call_rcu_tasks() assumes + * that the read-side critical sections end at a voluntary context + * switch (not a preemption!), entry into idle, or transition to usermode + * execution. As such, there are no read-side primitives analogous to + * rcu_read_lock() and rcu_read_unlock() because this primitive is intended + * to determine that all tasks have passed through a safe state, not so + * much for data-strcuture synchronization. + * + * See the description of call_rcu() for more detailed information on + * 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 void __rcu_read_lock(void); @@ -238,8 +261,8 @@ static inline int rcu_preempt_depth(void) /* Internal to kernel */ void rcu_init(void); -void rcu_sched_qs(int cpu); -void rcu_bh_qs(int cpu); +void rcu_sched_qs(void); +void rcu_bh_qs(void); void rcu_check_callbacks(int cpu, int user); struct notifier_block; void rcu_idle_enter(void); @@ -302,6 +325,36 @@ static inline void rcu_init_nohz(void) rcu_irq_exit(); \ } while (0) +/* + * Note a voluntary context switch for RCU-tasks benefit. This is a + * 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 { \ + if (ACCESS_ONCE((t)->rcu_tasks_holdout)) \ + ACCESS_ONCE((t)->rcu_tasks_holdout) = false; \ + } 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 */ + +/** + * cond_resched_rcu_qs - Report potential quiescent states to RCU + * + * This macro resembles cond_resched(), except that it is defined to + * report potential quiescent states to RCU-tasks even if the cond_resched() + * machinery were to be shut off, as some advocate for PREEMPT kernels. + */ +#define cond_resched_rcu_qs() \ +do { \ + rcu_note_voluntary_context_switch(current); \ + cond_resched(); \ +} while (0) + #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) bool __rcu_is_watching(void); #endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_RCU_TRACE) || defined(CONFIG_SMP) */ diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index d40a6a4..38cc5b1 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -80,7 +80,7 @@ static inline void kfree_call_rcu(struct rcu_head *head, static inline void rcu_note_context_switch(int cpu) { - rcu_sched_qs(cpu); + rcu_sched_qs(); } /* diff --git a/include/linux/sched.h b/include/linux/sched.h index 5c2c885..42888d7 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 { @@ -1264,12 +1271,18 @@ 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 struct rcu_node *rcu_blocked_node; #endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ +#ifdef CONFIG_TASKS_RCU + 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) struct sched_info sched_info; @@ -1999,29 +2012,21 @@ 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. */ - 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; -#ifdef CONFIG_TREE_PREEMPT_RCU + p->rcu_read_unlock_special.s = 0; p->rcu_blocked_node = NULL; -#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */ INIT_LIST_HEAD(&p->rcu_node_entry); +#endif /* #ifdef CONFIG_PREEMPT_RCU */ +#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 */ } -#else - -static inline void rcu_copy_process(struct task_struct *p) -{ -} - -#endif - static inline void tsk_restore_flags(struct task_struct *task, unsigned long orig_flags, unsigned long flags) { diff --git a/init/Kconfig b/init/Kconfig index 64ee4d9..4fe5500 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -507,6 +507,16 @@ config PREEMPT_RCU This option enables preemptible-RCU code that is common between TREE_PREEMPT_RCU and, in the old days, TINY_PREEMPT_RCU. +config TASKS_RCU + bool "Task_based RCU implementation using voluntary context switch" + default n + help + This option enables a task-based RCU implementation that uses + only voluntary context switch (not preemption!), idle, and + user-mode execution as quiescent states. + + If unsure, say N. + config RCU_STALL_COMMON def_bool ( TREE_RCU || TREE_PREEMPT_RCU || RCU_TRACE ) help diff --git a/kernel/exit.c b/kernel/exit.c index 32c58f7..d13f2ee 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/rcutorture.c b/kernel/rcu/rcutorture.c index 0bcd53a..6d15095 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -612,6 +612,52 @@ static struct rcu_torture_ops sched_ops = { .name = "sched" }; +#ifdef CONFIG_TASKS_RCU + +/* + * Definitions for RCU-tasks torture testing. + */ + +static int tasks_torture_read_lock(void) +{ + return 0; +} + +static void tasks_torture_read_unlock(int idx) +{ +} + +static void rcu_tasks_torture_deferred_free(struct rcu_torture *p) +{ + call_rcu_tasks(&p->rtort_rcu, rcu_torture_cb); +} + +static struct rcu_torture_ops tasks_ops = { + .ttype = RCU_TASKS_FLAVOR, + .init = rcu_sync_torture_init, + .readlock = tasks_torture_read_lock, + .read_delay = rcu_read_delay, /* just reuse rcu's version. */ + .readunlock = tasks_torture_read_unlock, + .completed = rcu_no_completed, + .deferred_free = rcu_tasks_torture_deferred_free, + .sync = synchronize_rcu_tasks, + .exp_sync = synchronize_rcu_tasks, + .call = call_rcu_tasks, + .cb_barrier = rcu_barrier_tasks, + .fqs = NULL, + .stats = NULL, + .irq_capable = 1, + .name = "tasks" +}; + +#define RCUTORTURE_TASKS_OPS &tasks_ops, + +#else /* #ifdef CONFIG_TASKS_RCU */ + +#define RCUTORTURE_TASKS_OPS + +#endif /* #else #ifdef CONFIG_TASKS_RCU */ + /* * RCU torture priority-boost testing. Runs one real-time thread per * CPU for moderate bursts, repeatedly registering RCU callbacks and @@ -678,7 +724,7 @@ static int rcu_torture_boost(void *arg) } call_rcu_time = jiffies; } - cond_resched(); + cond_resched_rcu_qs(); stutter_wait("rcu_torture_boost"); if (torture_must_stop()) goto checkwait; @@ -1082,7 +1128,7 @@ rcu_torture_reader(void *arg) __this_cpu_inc(rcu_torture_batch[completed]); preempt_enable(); cur_ops->readunlock(idx); - cond_resched(); + cond_resched_rcu_qs(); stutter_wait("rcu_torture_reader"); } while (!torture_must_stop()); if (irqreader && cur_ops->irq_capable) { @@ -1344,7 +1390,8 @@ static int rcu_torture_barrier_cbs(void *arg) if (atomic_dec_and_test(&barrier_cbs_count)) wake_up(&barrier_wq); } while (!torture_must_stop()); - cur_ops->cb_barrier(); + if (cur_ops->cb_barrier != NULL) + cur_ops->cb_barrier(); destroy_rcu_head_on_stack(&rcu); torture_kthread_stopping("rcu_torture_barrier_cbs"); return 0; @@ -1585,6 +1632,7 @@ rcu_torture_init(void) int firsterr = 0; static struct rcu_torture_ops *torture_ops[] = { &rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &sched_ops, + RCUTORTURE_TASKS_OPS }; if (!torture_init_begin(torture_type, verbose, &rcutorture_runnable)) diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index 4a55a24..c0623fc 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -72,7 +72,7 @@ static void rcu_idle_enter_common(long long newval) current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ } - rcu_sched_qs(0); /* implies rcu_bh_qsctr_inc(0) */ + rcu_sched_qs(); /* implies rcu_bh_inc() */ barrier(); rcu_dynticks_nesting = newval; } @@ -217,7 +217,7 @@ static int rcu_qsctr_help(struct rcu_ctrlblk *rcp) * are at it, given that any rcu quiescent state is also an rcu_bh * quiescent state. Use "+" instead of "||" to defeat short circuiting. */ -void rcu_sched_qs(int cpu) +void rcu_sched_qs(void) { unsigned long flags; @@ -231,7 +231,7 @@ void rcu_sched_qs(int cpu) /* * Record an rcu_bh quiescent state. */ -void rcu_bh_qs(int cpu) +void rcu_bh_qs(void) { unsigned long flags; @@ -251,9 +251,11 @@ void rcu_check_callbacks(int cpu, int user) { RCU_TRACE(check_cpu_stalls()); if (user || rcu_is_cpu_rrupt_from_idle()) - rcu_sched_qs(cpu); + rcu_sched_qs(); else if (!in_softirq()) - rcu_bh_qs(cpu); + rcu_bh_qs(); + if (user) + rcu_note_voluntary_context_switch(current); } /* diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index be0d0a1b..d7a3b13 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -197,22 +197,24 @@ static int rcu_gp_in_progress(struct rcu_state *rsp) * one since the start of the grace period, this just sets a flag. * The caller must have disabled preemption. */ -void rcu_sched_qs(int cpu) +void rcu_sched_qs(void) { - struct rcu_data *rdp = &per_cpu(rcu_sched_data, cpu); - - if (rdp->passed_quiesce == 0) - trace_rcu_grace_period(TPS("rcu_sched"), rdp->gpnum, TPS("cpuqs")); - rdp->passed_quiesce = 1; + if (!__this_cpu_read(rcu_sched_data.passed_quiesce)) { + trace_rcu_grace_period(TPS("rcu_sched"), + __this_cpu_read(rcu_sched_data.gpnum), + TPS("cpuqs")); + __this_cpu_write(rcu_sched_data.passed_quiesce, 1); + } } -void rcu_bh_qs(int cpu) +void rcu_bh_qs(void) { - struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu); - - if (rdp->passed_quiesce == 0) - trace_rcu_grace_period(TPS("rcu_bh"), rdp->gpnum, TPS("cpuqs")); - rdp->passed_quiesce = 1; + if (!__this_cpu_read(rcu_bh_data.passed_quiesce)) { + trace_rcu_grace_period(TPS("rcu_bh"), + __this_cpu_read(rcu_bh_data.gpnum), + TPS("cpuqs")); + __this_cpu_write(rcu_bh_data.passed_quiesce, 1); + } } static DEFINE_PER_CPU(int, rcu_sched_qs_mask); @@ -287,7 +289,7 @@ static void rcu_momentary_dyntick_idle(void) void rcu_note_context_switch(int cpu) { trace_rcu_utilization(TPS("Start context switch")); - rcu_sched_qs(cpu); + rcu_sched_qs(); rcu_preempt_note_context_switch(cpu); if (unlikely(raw_cpu_read(rcu_sched_qs_mask))) rcu_momentary_dyntick_idle(); @@ -535,6 +537,7 @@ 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 @@ -651,6 +654,7 @@ 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 */ @@ -1656,7 +1660,7 @@ static int rcu_gp_init(struct rcu_state *rsp) rnp->level, rnp->grplo, rnp->grphi, rnp->qsmask); raw_spin_unlock_irq(&rnp->lock); - cond_resched(); + cond_resched_rcu_qs(); } mutex_unlock(&rsp->onoff_mutex); @@ -1746,7 +1750,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) /* smp_mb() provided by prior unlock-lock pair. */ nocb += rcu_future_gp_cleanup(rsp, rnp); raw_spin_unlock_irq(&rnp->lock); - cond_resched(); + cond_resched_rcu_qs(); } rnp = rcu_get_root(rsp); raw_spin_lock_irq(&rnp->lock); @@ -1795,7 +1799,7 @@ static int __noreturn rcu_gp_kthread(void *arg) /* Locking provides needed memory barrier. */ if (rcu_gp_init(rsp)) break; - cond_resched(); + cond_resched_rcu_qs(); WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), @@ -1838,10 +1842,10 @@ static int __noreturn rcu_gp_kthread(void *arg) trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), TPS("fqsend")); - cond_resched(); + cond_resched_rcu_qs(); } else { /* Deal with stray signal. */ - cond_resched(); + cond_resched_rcu_qs(); WARN_ON(signal_pending(current)); trace_rcu_grace_period(rsp->name, ACCESS_ONCE(rsp->gpnum), @@ -2401,8 +2405,8 @@ void rcu_check_callbacks(int cpu, int user) * at least not while the corresponding CPU is online. */ - rcu_sched_qs(cpu); - rcu_bh_qs(cpu); + rcu_sched_qs(); + rcu_bh_qs(); } else if (!in_softirq()) { @@ -2413,11 +2417,13 @@ void rcu_check_callbacks(int cpu, int user) * critical section, so note it. */ - rcu_bh_qs(cpu); + rcu_bh_qs(); } rcu_preempt_check_callbacks(cpu); if (rcu_pending(cpu)) invoke_rcu_core(); + if (user) + rcu_note_voluntary_context_switch(current); trace_rcu_utilization(TPS("End scheduler-tick")); } @@ -2440,7 +2446,7 @@ static void force_qs_rnp(struct rcu_state *rsp, struct rcu_node *rnp; rcu_for_each_leaf_node(rsp, rnp) { - cond_resched(); + cond_resched_rcu_qs(); mask = 0; raw_spin_lock_irqsave(&rnp->lock, flags); smp_mb__after_unlock_lock(); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index ffedcb9..d037646 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -615,6 +615,8 @@ 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 59318ea..e2c5910 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -128,18 +128,19 @@ 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. - */ -static void rcu_preempt_qs(int cpu) -{ - struct rcu_data *rdp = &per_cpu(rcu_preempt_data, 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; + * As with the other rcu_*_qs() functions, callers to this function + * must disable preemption. + */ +static void rcu_preempt_qs(void) +{ + if (!__this_cpu_read(rcu_preempt_data.passed_quiesce)) { + trace_rcu_grace_period(TPS("rcu_preempt"), + __this_cpu_read(rcu_preempt_data.gpnum), + TPS("cpuqs")); + __this_cpu_write(rcu_preempt_data.passed_quiesce, 1); + barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */ + current->rcu_read_unlock_special.b.need_qs = false; + } } /* @@ -163,14 +164,14 @@ 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; /* @@ -212,7 +213,7 @@ 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 @@ -230,9 +231,7 @@ 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); + rcu_preempt_qs(); } /* @@ -313,7 +312,7 @@ 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()) @@ -323,12 +322,13 @@ 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) { - rcu_preempt_qs(smp_processor_id()); - if (!t->rcu_read_unlock_special) { + if (special.b.need_qs) { + rcu_preempt_qs(); + if (!t->rcu_read_unlock_special.s) { local_irq_restore(flags); return; } @@ -341,8 +341,8 @@ 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 @@ -626,12 +626,13 @@ static void rcu_preempt_check_callbacks(int cpu) struct task_struct *t = current; if (t->rcu_read_lock_nesting == 0) { - rcu_preempt_qs(cpu); + rcu_preempt_qs(); return; } 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; + per_cpu(rcu_preempt_data, cpu).qs_pending && + !per_cpu(rcu_preempt_data, cpu).passed_quiesce) + t->rcu_read_unlock_special.b.need_qs = true; } #ifdef CONFIG_RCU_BOOST @@ -915,7 +916,7 @@ 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(); } @@ -1816,7 +1817,7 @@ static int rcu_oom_notify(struct notifier_block *self, get_online_cpus(); for_each_online_cpu(cpu) { smp_call_function_single(cpu, rcu_oom_notify_cpu, NULL, 1); - cond_resched(); + cond_resched_rcu_qs(); } put_online_cpus(); @@ -3162,3 +3163,19 @@ 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 ea8ea7b..3ef8ba5 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -47,6 +47,8 @@ #include <linux/hardirq.h> #include <linux/delay.h> #include <linux/module.h> +#include <linux/kthread.h> +#include <linux/tick.h> #define CREATE_TRACE_POINTS @@ -91,7 +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; @@ -379,3 +381,312 @@ 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 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. */ +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 * 10; +module_param(rcu_task_stall_timeout, int, 0644); + +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; + 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) { + rcu_spawn_tasks_kthread(); + wake_up(&rcu_tasks_cbs_wq); + } +} +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); +} +EXPORT_SYMBOL_GPL(synchronize_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(); +} +EXPORT_SYMBOL_GPL(rcu_barrier_tasks); + +/* See if tasks are still holding out, complain if so. */ +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) || + (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_init(&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; + } + 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); +} + +/* 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; + unsigned long lastreport; + 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) { + 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; + } + + /* + * 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(); + + /* + * 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 + * holdouts. When the list is empty, we are done. + */ + lastreport = jiffies; + while (!list_empty(&rcu_tasks_holdouts)) { + bool firstreport; + bool needreport; + int rtst; + struct task_struct *t1; + + 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)); + list_for_each_entry_safe(t, t1, &rcu_tasks_holdouts, + rcu_tasks_holdout_list) { + check_holdout_task(t, needreport, &firstreport); + cond_resched(); + } + } + + /* + * 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. + * + * 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(); + + /* Invoke the callbacks. */ + while (list) { + next = list->next; + local_bh_disable(); + list->func(list); + local_bh_enable(); + list = next; + cond_resched(); + } + schedule_timeout_uninterruptible(HZ/10); + } +} + +/* Spawn rcu_tasks_kthread() at first call to call_rcu_tasks(). */ +static void rcu_spawn_tasks_kthread(void) +{ + 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)); + smp_mb(); /* Ensure others see full kthread. */ + ACCESS_ONCE(rcu_tasks_kthread_ptr) = t; + mutex_unlock(&rcu_tasks_kthread_mutex); +} + +#endif /* #ifdef CONFIG_TASKS_RCU */ diff --git a/kernel/softirq.c b/kernel/softirq.c index 5918d22..348ec76 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -278,7 +278,7 @@ restart: pending >>= softirq_bit; } - rcu_bh_qs(smp_processor_id()); + rcu_bh_qs(); local_irq_disable(); pending = local_softirq_pending(); @@ -789,7 +789,7 @@ static int do_mlockall(int flags) /* Ignore errors */ mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags); - cond_resched(); + cond_resched_rcu_qs(); } out: return 0; diff --git a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST index cd3d29c..a3a1a05 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/CFLIST +++ b/tools/testing/selftests/rcutorture/configs/rcu/CFLIST @@ -11,3 +11,6 @@ SRCU-N SRCU-P TINY01 TINY02 +TASKS01 +TASKS02 +TASKS03 diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 new file mode 100644 index 0000000..97f0a0b --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01 @@ -0,0 +1,9 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=2 +CONFIG_HOTPLUG_CPU=y +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y +CONFIG_DEBUG_LOCK_ALLOC=y +CONFIG_PROVE_RCU=y +CONFIG_TASKS_RCU=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot new file mode 100644 index 0000000..cd2a188 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS01.boot @@ -0,0 +1 @@ +rcutorture.torture_type=tasks diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 new file mode 100644 index 0000000..696d2ea7 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02 @@ -0,0 +1,5 @@ +CONFIG_SMP=n +CONFIG_PREEMPT_NONE=y +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=n +CONFIG_TASKS_RCU=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot new file mode 100644 index 0000000..cd2a188 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS02.boot @@ -0,0 +1 @@ +rcutorture.torture_type=tasks diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 new file mode 100644 index 0000000..9c60da5 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 @@ -0,0 +1,13 @@ +CONFIG_SMP=y +CONFIG_NR_CPUS=2 +CONFIG_HOTPLUG_CPU=n +CONFIG_SUSPEND=n +CONFIG_HIBERNATION=n +CONFIG_PREEMPT_NONE=n +CONFIG_PREEMPT_VOLUNTARY=n +CONFIG_PREEMPT=y +CONFIG_TASKS_RCU=y +CONFIG_HZ_PERIODIC=n +CONFIG_NO_HZ_IDLE=n +CONFIG_NO_HZ_FULL=y +CONFIG_NO_HZ_FULL_ALL=y diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot new file mode 100644 index 0000000..cd2a188 --- /dev/null +++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot @@ -0,0 +1 @@ +rcutorture.torture_type=tasks |
