diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt index 375d3fb71437..4ddf3913fd8c 100644 --- a/Documentation/RCU/torture.txt +++ b/Documentation/RCU/torture.txt @@ -47,6 +47,16 @@ irqreader Says to invoke RCU readers from irq level. This is currently permit this. (Or, more accurately, variants of RCU that do -not- permit this know to ignore this variable.) +n_barrier_cbs If this is nonzero, RCU barrier testing will be conducted, + in which case n_barrier_cbs specifies the number of + RCU callbacks (and corresponding kthreads) to use for + this testing. The value cannot be negative. If you + specify this to be non-zero when torture_type indicates a + synchronous RCU implementation (one for which a member of + the synchronize_rcu() rather than the call_rcu() family is + used -- see the documentation for torture_type below), an + error will be reported and no testing will be carried out. + nfakewriters This is the number of RCU fake writer threads to run. Fake writer threads repeatedly use the synchronous "wait for current readers" function of the interface selected by @@ -188,7 +198,7 @@ OUTPUT The statistics output is as follows: rcu-torture:--- Start of test: nreaders=16 nfakewriters=4 stat_interval=30 verbose=0 test_no_idle_hz=1 shuffle_interval=3 stutter=5 irqreader=1 fqs_duration=0 fqs_holdoff=0 fqs_stutter=3 test_boost=1/0 test_boost_interval=7 test_boost_duration=4 - rcu-torture: rtc: (null) ver: 155441 tfle: 0 rta: 155441 rtaf: 8884 rtf: 155440 rtmbe: 0 rtbke: 0 rtbre: 0 rtbf: 0 rtb: 0 nt: 3055767 + rcu-torture: rtc: (null) ver: 155441 tfle: 0 rta: 155441 rtaf: 8884 rtf: 155440 rtmbe: 0 rtbe: 0 rtbke: 0 rtbre: 0 rtbf: 0 rtb: 0 nt: 3055767 rcu-torture: Reader Pipe: 727860534 34213 0 0 0 0 0 0 0 0 0 rcu-torture: Reader Batch: 727877838 17003 0 0 0 0 0 0 0 0 0 rcu-torture: Free-Block Circulation: 155440 155440 155440 155440 155440 155440 155440 155440 155440 155440 0 @@ -230,6 +240,9 @@ o "rtmbe": A non-zero value indicates that rcutorture believes that rcu_assign_pointer() and rcu_dereference() are not working correctly. This value should be zero. +o "rtbe": A non-zero value indicates that one of the rcu_barrier() + family of functions is not working correctly. + o "rtbke": rcutorture was unable to create the real-time kthreads used to force RCU priority inversion. This value should be zero. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index c1601e5a8b71..ab84a01c8d68 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2330,18 +2330,100 @@ bytes respectively. Such letter suffixes can also be entirely omitted. ramdisk_size= [RAM] Sizes of RAM disks in kilobytes See Documentation/blockdev/ramdisk.txt. - rcupdate.blimit= [KNL,BOOT] + rcutree.blimit= [KNL,BOOT] Set maximum number of finished RCU callbacks to process in one batch. - rcupdate.qhimark= [KNL,BOOT] + rcutree.qhimark= [KNL,BOOT] Set threshold of queued RCU callbacks over which batch limiting is disabled. - rcupdate.qlowmark= [KNL,BOOT] + rcutree.qlowmark= [KNL,BOOT] Set threshold of queued RCU callbacks below which batch limiting is re-enabled. + rcutree.rcu_cpu_stall_suppress= [KNL,BOOT] + Suppress RCU CPU stall warning messages. + + rcutree.rcu_cpu_stall_timeout= [KNL,BOOT] + Set timeout for RCU CPU stall warning messages. + + rcutorture.fqs_duration= [KNL,BOOT] + Set duration of force_quiescent_state bursts. + + rcutorture.fqs_holdoff= [KNL,BOOT] + Set holdoff time within force_quiescent_state bursts. + + rcutorture.fqs_stutter= [KNL,BOOT] + Set wait time between force_quiescent_state bursts. + + rcutorture.irqreader= [KNL,BOOT] + Test RCU readers from irq handlers. + + rcutorture.n_barrier_cbs= [KNL,BOOT] + Set callbacks/threads for rcu_barrier() testing. + + rcutorture.nfakewriters= [KNL,BOOT] + Set number of concurrent RCU writers. These just + stress RCU, they don't participate in the actual + test, hence the "fake". + + rcutorture.nreaders= [KNL,BOOT] + Set number of RCU readers. + + rcutorture.onoff_holdoff= [KNL,BOOT] + Set time (s) after boot for CPU-hotplug testing. + + rcutorture.onoff_interval= [KNL,BOOT] + Set time (s) between CPU-hotplug operations, or + zero to disable CPU-hotplug testing. + + rcutorture.shuffle_interval= [KNL,BOOT] + Set task-shuffle interval (s). Shuffling tasks + allows some CPUs to go into dyntick-idle mode + during the rcutorture test. + + rcutorture.shutdown_secs= [KNL,BOOT] + Set time (s) after boot system shutdown. This + is useful for hands-off automated testing. + + rcutorture.stall_cpu= [KNL,BOOT] + Duration of CPU stall (s) to test RCU CPU stall + warnings, zero to disable. + + rcutorture.stall_cpu_holdoff= [KNL,BOOT] + Time to wait (s) after boot before inducing stall. + + rcutorture.stat_interval= [KNL,BOOT] + Time (s) between statistics printk()s. + + rcutorture.stutter= [KNL,BOOT] + Time (s) to stutter testing, for example, specifying + five seconds causes the test to run for five seconds, + wait for five seconds, and so on. This tests RCU's + ability to transition abruptly to and from idle. + + rcutorture.test_boost= [KNL,BOOT] + Test RCU priority boosting? 0=no, 1=maybe, 2=yes. + "Maybe" means test if the RCU implementation + under test support RCU priority boosting. + + rcutorture.test_boost_duration= [KNL,BOOT] + Duration (s) of each individual boost test. + + rcutorture.test_boost_interval= [KNL,BOOT] + Interval (s) between each boost test. + + rcutorture.test_no_idle_hz= [KNL,BOOT] + Test RCU's dyntick-idle handling. See also the + rcutorture.shuffle_interval parameter. + + rcutorture.torture_type= [KNL,BOOT] + Specify the RCU implementation to test. + + rcutorture.verbose= [KNL,BOOT] + Enable additional printk() statements. + rdinit= [KNL] Format: Run specified binary instead of /init from the ramdisk, diff --git a/MAINTAINERS b/MAINTAINERS index 1a2f8f5823e0..a1c2ab2c6d60 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5607,14 +5607,13 @@ F: net/rds/ READ-COPY UPDATE (RCU) M: Dipankar Sarma M: "Paul E. McKenney" -W: http://www.rdrop.com/users/paulmck/rclock/ +W: http://www.rdrop.com/users/paulmck/RCU/ S: Supported T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git F: Documentation/RCU/ +X: Documentation/RCU/torture.txt F: include/linux/rcu* -F: include/linux/srcu* F: kernel/rcu* -F: kernel/srcu* X: kernel/rcutorture.c REAL TIME CLOCK (RTC) SUBSYSTEM @@ -6131,6 +6130,15 @@ S: Maintained F: include/linux/sl?b*.h F: mm/sl?b.c +SLEEPABLE READ-COPY UPDATE (SRCU) +M: Lai Jiangshan +M: "Paul E. McKenney" +W: http://www.rdrop.com/users/paulmck/RCU/ +S: Supported +T: git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git +F: include/linux/srcu* +F: kernel/srcu* + SMC91x ETHERNET DRIVER M: Nicolas Pitre S: Odd Fixes diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 43b39d61b538..88e466b159dc 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -705,6 +705,7 @@ static void stack_proc(void *arg) struct task_struct *from = current, *to = arg; to->thread.saved_task = from; + rcu_switch_from(from); switch_to(from, to, from); } diff --git a/include/linux/rculist.h b/include/linux/rculist.h index d079290843a9..e0f0fab20415 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -30,6 +30,7 @@ * This is only for internal list manipulation where we know * the prev/next entries already! */ +#ifndef CONFIG_DEBUG_LIST static inline void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { @@ -38,6 +39,10 @@ static inline void __list_add_rcu(struct list_head *new, rcu_assign_pointer(list_next_rcu(prev), new); next->prev = new; } +#else +extern void __list_add_rcu(struct list_head *new, + struct list_head *prev, struct list_head *next); +#endif /** * list_add_rcu - add a new entry to rcu-protected list @@ -108,7 +113,7 @@ static inline void list_add_tail_rcu(struct list_head *new, */ static inline void list_del_rcu(struct list_head *entry) { - __list_del(entry->prev, entry->next); + __list_del_entry(entry); entry->prev = LIST_POISON2; } @@ -228,18 +233,43 @@ static inline void list_splice_init_rcu(struct list_head *list, }) /** - * list_first_entry_rcu - get the first element from a list + * Where are list_empty_rcu() and list_first_entry_rcu()? + * + * Implementing those functions following their counterparts list_empty() and + * list_first_entry() is not advisable because they lead to subtle race + * conditions as the following snippet shows: + * + * if (!list_empty_rcu(mylist)) { + * struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member); + * do_something(bar); + * } + * + * The list may not be empty when list_empty_rcu checks it, but it may be when + * list_first_entry_rcu rereads the ->next pointer. + * + * Rereading the ->next pointer is not a problem for list_empty() and + * list_first_entry() because they would be protected by a lock that blocks + * writers. + * + * See list_first_or_null_rcu for an alternative. + */ + +/** + * list_first_or_null_rcu - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_struct within the struct. * - * Note, that list is expected to be not empty. + * Note that if the list is empty, it returns NULL. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ -#define list_first_entry_rcu(ptr, type, member) \ - list_entry_rcu((ptr)->next, type, member) +#define list_first_or_null_rcu(ptr, type, member) \ + ({struct list_head *__ptr = (ptr); \ + struct list_head __rcu *__next = list_next_rcu(__ptr); \ + likely(__ptr != __next) ? container_of(__next, type, member) : NULL; \ + }) /** * list_for_each_entry_rcu - iterate over rcu list of given type diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 20fb776a1d4a..26d1a47591f1 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -184,12 +184,14 @@ static inline int rcu_preempt_depth(void) /* Internal to kernel */ extern void rcu_sched_qs(int cpu); extern void rcu_bh_qs(int cpu); +extern void rcu_preempt_note_context_switch(void); extern void rcu_check_callbacks(int cpu, int user); struct notifier_block; extern void rcu_idle_enter(void); extern void rcu_idle_exit(void); extern void rcu_irq_enter(void); extern void rcu_irq_exit(void); +extern void exit_rcu(void); /** * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers @@ -922,6 +924,21 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset) kfree_call_rcu(head, (rcu_callback)offset); } +/* + * Does the specified offset indicate that the corresponding rcu_head + * structure can be handled by kfree_rcu()? + */ +#define __is_kfree_rcu_offset(offset) ((offset) < 4096) + +/* + * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain. + */ +#define __kfree_rcu(head, offset) \ + do { \ + BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \ + call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \ + } while (0) + /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree @@ -944,6 +961,9 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset) * * Note that the allowable offset might decrease in the future, for example, * to allow something like kmem_cache_free_rcu(). + * + * The BUILD_BUG_ON check must not involve any function calls, hence the + * checks are done in macros here. */ #define kfree_rcu(ptr, rcu_head) \ __kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head)) diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index e93df77176d1..adb5e5a38cae 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -87,14 +87,6 @@ static inline void kfree_call_rcu(struct rcu_head *head, #ifdef CONFIG_TINY_RCU -static inline void rcu_preempt_note_context_switch(void) -{ -} - -static inline void exit_rcu(void) -{ -} - static inline int rcu_needs_cpu(int cpu) { return 0; @@ -102,8 +94,6 @@ static inline int rcu_needs_cpu(int cpu) #else /* #ifdef CONFIG_TINY_RCU */ -void rcu_preempt_note_context_switch(void); -extern void exit_rcu(void); int rcu_preempt_needs_cpu(void); static inline int rcu_needs_cpu(int cpu) @@ -116,7 +106,6 @@ static inline int rcu_needs_cpu(int cpu) static inline void rcu_note_context_switch(int cpu) { rcu_sched_qs(cpu); - rcu_preempt_note_context_switch(); } /* diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index e8ee5dd0854c..3c6083cde4fc 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -45,18 +45,6 @@ static inline void rcu_virt_note_context_switch(int cpu) rcu_note_context_switch(cpu); } -#ifdef CONFIG_TREE_PREEMPT_RCU - -extern void exit_rcu(void); - -#else /* #ifdef CONFIG_TREE_PREEMPT_RCU */ - -static inline void exit_rcu(void) -{ -} - -#endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */ - extern void synchronize_rcu_bh(void); extern void synchronize_sched_expedited(void); extern void synchronize_rcu_expedited(void); @@ -98,13 +86,6 @@ extern void rcu_force_quiescent_state(void); extern void rcu_bh_force_quiescent_state(void); extern void rcu_sched_force_quiescent_state(void); -/* A context switch is a grace period for RCU-sched and RCU-bh. */ -static inline int rcu_blocking_is_gp(void) -{ - might_sleep(); /* Check for RCU read-side critical section. */ - return num_online_cpus() == 1; -} - extern void rcu_scheduler_starting(void); extern int rcu_scheduler_active __read_mostly; diff --git a/include/linux/sched.h b/include/linux/sched.h index 81a173c0897d..8f3fd945070f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1905,12 +1905,22 @@ static inline void rcu_copy_process(struct task_struct *p) INIT_LIST_HEAD(&p->rcu_node_entry); } +static inline void rcu_switch_from(struct task_struct *prev) +{ + if (prev->rcu_read_lock_nesting != 0) + rcu_preempt_note_context_switch(); +} + #else static inline void rcu_copy_process(struct task_struct *p) { } +static inline void rcu_switch_from(struct task_struct *prev) +{ +} + #endif #ifdef CONFIG_SMP diff --git a/include/linux/srcu.h b/include/linux/srcu.h index d3d5fa54f25e..55a5c52cbb25 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -29,26 +29,35 @@ #include #include +#include struct srcu_struct_array { - int c[2]; + unsigned long c[2]; + unsigned long seq[2]; +}; + +struct rcu_batch { + struct rcu_head *head, **tail; }; struct srcu_struct { - int completed; + unsigned completed; struct srcu_struct_array __percpu *per_cpu_ref; - struct mutex mutex; + spinlock_t queue_lock; /* protect ->batch_queue, ->running */ + bool running; + /* callbacks just queued */ + struct rcu_batch batch_queue; + /* callbacks try to do the first check_zero */ + struct rcu_batch batch_check0; + /* callbacks done with the first check_zero and the flip */ + struct rcu_batch batch_check1; + struct rcu_batch batch_done; + struct delayed_work work; #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map dep_map; #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ }; -#ifndef CONFIG_PREEMPT -#define srcu_barrier() barrier() -#else /* #ifndef CONFIG_PREEMPT */ -#define srcu_barrier() -#endif /* #else #ifndef CONFIG_PREEMPT */ - #ifdef CONFIG_DEBUG_LOCK_ALLOC int __init_srcu_struct(struct srcu_struct *sp, const char *name, @@ -67,12 +76,33 @@ int init_srcu_struct(struct srcu_struct *sp); #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ +/** + * call_srcu() - Queue a callback for invocation after an SRCU grace period + * @sp: srcu_struct in queue the callback + * @head: structure to be used for queueing the SRCU callback. + * @func: function to be invoked after the SRCU grace period + * + * The callback function will be invoked some time after a full SRCU + * grace period elapses, in other words after all pre-existing SRCU + * read-side critical sections have completed. However, the callback + * function might well execute concurrently with other SRCU read-side + * critical sections that started after call_srcu() was invoked. SRCU + * read-side critical sections are delimited by srcu_read_lock() and + * srcu_read_unlock(), and may be nested. + * + * The callback will be invoked from process context, but must nevertheless + * be fast and must not block. + */ +void call_srcu(struct srcu_struct *sp, struct rcu_head *head, + void (*func)(struct rcu_head *head)); + void cleanup_srcu_struct(struct srcu_struct *sp); int __srcu_read_lock(struct srcu_struct *sp) __acquires(sp); void __srcu_read_unlock(struct srcu_struct *sp, int idx) __releases(sp); void synchronize_srcu(struct srcu_struct *sp); void synchronize_srcu_expedited(struct srcu_struct *sp); long srcu_batches_completed(struct srcu_struct *sp); +void srcu_barrier(struct srcu_struct *sp); #ifdef CONFIG_DEBUG_LOCK_ALLOC diff --git a/init/Kconfig b/init/Kconfig index 6cfd71d06463..6d18ef8071b5 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -458,6 +458,33 @@ config RCU_FANOUT Select a specific number if testing RCU itself. Take the default if unsure. +config RCU_FANOUT_LEAF + int "Tree-based hierarchical RCU leaf-level fanout value" + range 2 RCU_FANOUT if 64BIT + range 2 RCU_FANOUT if !64BIT + depends on TREE_RCU || TREE_PREEMPT_RCU + default 16 + help + This option controls the leaf-level fanout of hierarchical + implementations of RCU, and allows trading off cache misses + against lock contention. Systems that synchronize their + scheduling-clock interrupts for energy-efficiency reasons will + want the default because the smaller leaf-level fanout keeps + lock contention levels acceptably low. Very large systems + (hundreds or thousands of CPUs) will instead want to set this + value to the maximum value possible in order to reduce the + number of cache misses incurred during RCU's grace-period + initialization. These systems tend to run CPU-bound, and thus + are not helped by synchronized interrupts, and thus tend to + skew them, which reduces lock contention enough that large + leaf-level fanouts work well. + + Select a specific number if testing RCU itself. + + Select the maximum permissible value for large systems. + + Take the default if unsure. + config RCU_FANOUT_EXACT bool "Disable tree-based hierarchical RCU auto-balancing" depends on TREE_RCU || TREE_PREEMPT_RCU @@ -515,10 +542,25 @@ config RCU_BOOST_PRIO depends on RCU_BOOST default 1 help - This option specifies the real-time priority to which preempted - RCU readers are to be boosted. If you are working with CPU-bound - real-time applications, you should specify a priority higher then - the highest-priority CPU-bound application. + This option specifies the real-time priority to which long-term + preempted RCU readers are to be boosted. If you are working + with a real-time application that has one or more CPU-bound + threads running at a real-time priority level, you should set + RCU_BOOST_PRIO to a priority higher then the highest-priority + real-time CPU-bound thread. The default RCU_BOOST_PRIO value + of 1 is appropriate in the common case, which is real-time + applications that do not have any CPU-bound threads. + + Some real-time applications might not have a single real-time + thread that saturates a given CPU, but instead might have + multiple real-time threads that, taken together, fully utilize + that CPU. In this case, you should set RCU_BOOST_PRIO to + a priority higher than the lowest-priority thread that is + conspiring to prevent the CPU from running any non-real-time + tasks. For example, if one thread at priority 10 and another + thread at priority 5 are between themselves fully consuming + the CPU time on a given CPU, then RCU_BOOST_PRIO should be + set to priority 6 or higher. Specify the real-time priority, or take the default if unsure. diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index a86f1741cc27..95cba41ce1e9 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -51,6 +51,34 @@ #include "rcu.h" +#ifdef CONFIG_PREEMPT_RCU + +/* + * Check for a task exiting while in a preemptible-RCU read-side + * critical section, clean up if so. No need to issue warnings, + * as debug_check_no_locks_held() already does this if lockdep + * is enabled. + */ +void exit_rcu(void) +{ + struct task_struct *t = current; + + if (likely(list_empty(¤t->rcu_node_entry))) + return; + t->rcu_read_lock_nesting = 1; + barrier(); + t->rcu_read_unlock_special = RCU_READ_UNLOCK_BLOCKED; + __rcu_read_unlock(); +} + +#else /* #ifdef CONFIG_PREEMPT_RCU */ + +void exit_rcu(void) +{ +} + +#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key rcu_lock_key; struct lockdep_map rcu_lock_map = diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index 22ecea0dfb62..fc31a2d65100 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -851,22 +851,6 @@ int rcu_preempt_needs_cpu(void) return rcu_preempt_ctrlblk.rcb.rcucblist != NULL; } -/* - * Check for a task exiting while in a preemptible -RCU read-side - * critical section, clean up if so. No need to issue warnings, - * as debug_check_no_locks_held() already does this if lockdep - * is enabled. - */ -void exit_rcu(void) -{ - struct task_struct *t = current; - - if (t->rcu_read_lock_nesting == 0) - return; - t->rcu_read_lock_nesting = 1; - __rcu_read_unlock(); -} - #else /* #ifdef CONFIG_TINY_PREEMPT_RCU */ #ifdef CONFIG_RCU_TRACE diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index a89b381a8c6e..e66b34ab7555 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -64,6 +64,7 @@ static int irqreader = 1; /* RCU readers from irq (timers). */ static int fqs_duration; /* Duration of bursts (us), 0 to disable. */ static int fqs_holdoff; /* Hold time within burst (us). */ static int fqs_stutter = 3; /* Wait time between bursts (s). */ +static int n_barrier_cbs; /* Number of callbacks to test RCU barriers. */ static int onoff_interval; /* Wait time between CPU hotplugs, 0=disable. */ static int onoff_holdoff; /* Seconds after boot before CPU hotplugs. */ static int shutdown_secs; /* Shutdown time (s). <=0 for no shutdown. */ @@ -96,6 +97,8 @@ module_param(fqs_holdoff, int, 0444); MODULE_PARM_DESC(fqs_holdoff, "Holdoff time within fqs bursts (us)"); module_param(fqs_stutter, int, 0444); MODULE_PARM_DESC(fqs_stutter, "Wait time between fqs bursts (s)"); +module_param(n_barrier_cbs, int, 0444); +MODULE_PARM_DESC(n_barrier_cbs, "# of callbacks/kthreads for barrier testing"); module_param(onoff_interval, int, 0444); MODULE_PARM_DESC(onoff_interval, "Time between CPU hotplugs (s), 0=disable"); module_param(onoff_holdoff, int, 0444); @@ -139,6 +142,8 @@ static struct task_struct *shutdown_task; static struct task_struct *onoff_task; #endif /* #ifdef CONFIG_HOTPLUG_CPU */ static struct task_struct *stall_task; +static struct task_struct **barrier_cbs_tasks; +static struct task_struct *barrier_task; #define RCU_TORTURE_PIPE_LEN 10 @@ -164,6 +169,7 @@ static atomic_t n_rcu_torture_alloc_fail; static atomic_t n_rcu_torture_free; static atomic_t n_rcu_torture_mberror; static atomic_t n_rcu_torture_error; +static long n_rcu_torture_barrier_error; static long n_rcu_torture_boost_ktrerror; static long n_rcu_torture_boost_rterror; static long n_rcu_torture_boost_failure; @@ -173,6 +179,8 @@ static long n_offline_attempts; static long n_offline_successes; static long n_online_attempts; static long n_online_successes; +static long n_barrier_attempts; +static long n_barrier_successes; static struct list_head rcu_torture_removed; static cpumask_var_t shuffle_tmp_mask; @@ -197,6 +205,10 @@ static unsigned long shutdown_time; /* jiffies to system shutdown. */ static unsigned long boost_starttime; /* jiffies of next boost test start. */ DEFINE_MUTEX(boost_mutex); /* protect setting boost_starttime */ /* and boost task create/destroy. */ +static atomic_t barrier_cbs_count; /* Barrier callbacks registered. */ +static atomic_t barrier_cbs_invoked; /* Barrier callbacks invoked. */ +static wait_queue_head_t *barrier_cbs_wq; /* Coordinate barrier testing. */ +static DECLARE_WAIT_QUEUE_HEAD(barrier_wq); /* Mediate rmmod and system shutdown. Concurrent rmmod & shutdown illegal! */ @@ -327,6 +339,7 @@ struct rcu_torture_ops { int (*completed)(void); void (*deferred_free)(struct rcu_torture *p); void (*sync)(void); + void (*call)(struct rcu_head *head, void (*func)(struct rcu_head *rcu)); void (*cb_barrier)(void); void (*fqs)(void); int (*stats)(char *page); @@ -417,6 +430,7 @@ static struct rcu_torture_ops rcu_ops = { .completed = rcu_torture_completed, .deferred_free = rcu_torture_deferred_free, .sync = synchronize_rcu, + .call = call_rcu, .cb_barrier = rcu_barrier, .fqs = rcu_force_quiescent_state, .stats = NULL, @@ -460,6 +474,7 @@ static struct rcu_torture_ops rcu_sync_ops = { .completed = rcu_torture_completed, .deferred_free = rcu_sync_torture_deferred_free, .sync = synchronize_rcu, + .call = NULL, .cb_barrier = NULL, .fqs = rcu_force_quiescent_state, .stats = NULL, @@ -477,6 +492,7 @@ static struct rcu_torture_ops rcu_expedited_ops = { .completed = rcu_no_completed, .deferred_free = rcu_sync_torture_deferred_free, .sync = synchronize_rcu_expedited, + .call = NULL, .cb_barrier = NULL, .fqs = rcu_force_quiescent_state, .stats = NULL, @@ -519,6 +535,7 @@ static struct rcu_torture_ops rcu_bh_ops = { .completed = rcu_bh_torture_completed, .deferred_free = rcu_bh_torture_deferred_free, .sync = synchronize_rcu_bh, + .call = call_rcu_bh, .cb_barrier = rcu_barrier_bh, .fqs = rcu_bh_force_quiescent_state, .stats = NULL, @@ -535,6 +552,7 @@ static struct rcu_torture_ops rcu_bh_sync_ops = { .completed = rcu_bh_torture_completed, .deferred_free = rcu_sync_torture_deferred_free, .sync = synchronize_rcu_bh, + .call = NULL, .cb_barrier = NULL, .fqs = rcu_bh_force_quiescent_state, .stats = NULL, @@ -551,6 +569,7 @@ static struct rcu_torture_ops rcu_bh_expedited_ops = { .completed = rcu_bh_torture_completed, .deferred_free = rcu_sync_torture_deferred_free, .sync = synchronize_rcu_bh_expedited, + .call = NULL, .cb_barrier = NULL, .fqs = rcu_bh_force_quiescent_state, .stats = NULL, @@ -606,6 +625,11 @@ static int srcu_torture_completed(void) return srcu_batches_completed(&srcu_ctl); } +static void srcu_torture_deferred_free(struct rcu_torture *rp) +{ + call_srcu(&srcu_ctl, &rp->rtort_rcu, rcu_torture_cb); +} + static void srcu_torture_synchronize(void) { synchronize_srcu(&srcu_ctl); @@ -620,7 +644,7 @@ static int srcu_torture_stats(char *page) cnt += sprintf(&page[cnt], "%s%s per-CPU(idx=%d):", torture_type, TORTURE_FLAG, idx); for_each_possible_cpu(cpu) { - cnt += sprintf(&page[cnt], " %d(%d,%d)", cpu, + cnt += sprintf(&page[cnt], " %d(%lu,%lu)", cpu, per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[!idx], per_cpu_ptr(srcu_ctl.per_cpu_ref, cpu)->c[idx]); } @@ -635,13 +659,29 @@ static struct rcu_torture_ops srcu_ops = { .read_delay = srcu_read_delay, .readunlock = srcu_torture_read_unlock, .completed = srcu_torture_completed, - .deferred_free = rcu_sync_torture_deferred_free, + .deferred_free = srcu_torture_deferred_free, .sync = srcu_torture_synchronize, + .call = NULL, .cb_barrier = NULL, .stats = srcu_torture_stats, .name = "srcu" }; +static struct rcu_torture_ops srcu_sync_ops = { + .init = srcu_torture_init, + .cleanup = srcu_torture_cleanup, + .readlock = srcu_torture_read_lock, + .read_delay = srcu_read_delay, + .readunlock = srcu_torture_read_unlock, + .completed = srcu_torture_completed, + .deferred_free = rcu_sync_torture_deferred_free, + .sync = srcu_torture_synchronize, + .call = NULL, + .cb_barrier = NULL, + .stats = srcu_torture_stats, + .name = "srcu_sync" +}; + static int srcu_torture_read_lock_raw(void) __acquires(&srcu_ctl) { return srcu_read_lock_raw(&srcu_ctl); @@ -659,13 +699,29 @@ static struct rcu_torture_ops srcu_raw_ops = { .read_delay = srcu_read_delay, .readunlock = srcu_torture_read_unlock_raw, .completed = srcu_torture_completed, - .deferred_free = rcu_sync_torture_deferred_free, + .deferred_free = srcu_torture_deferred_free, .sync = srcu_torture_synchronize, + .call = NULL, .cb_barrier = NULL, .stats = srcu_torture_stats, .name = "srcu_raw" }; +static struct rcu_torture_ops srcu_raw_sync_ops = { + .init = srcu_torture_init, + .cleanup = srcu_torture_cleanup, + .readlock = srcu_torture_read_lock_raw, + .read_delay = srcu_read_delay, + .readunlock = srcu_torture_read_unlock_raw, + .completed = srcu_torture_completed, + .deferred_free = rcu_sync_torture_deferred_free, + .sync = srcu_torture_synchronize, + .call = NULL, + .cb_barrier = NULL, + .stats = srcu_torture_stats, + .name = "srcu_raw_sync" +}; + static void srcu_torture_synchronize_expedited(void) { synchronize_srcu_expedited(&srcu_ctl); @@ -680,6 +736,7 @@ static struct rcu_torture_ops srcu_expedited_ops = { .completed = srcu_torture_completed, .deferred_free = rcu_sync_torture_deferred_free, .sync = srcu_torture_synchronize_expedited, + .call = NULL, .cb_barrier = NULL, .stats = srcu_torture_stats, .name = "srcu_expedited" @@ -1129,7 +1186,8 @@ rcu_torture_printk(char *page) "rtc: %p ver: %lu tfle: %d rta: %d rtaf: %d rtf: %d " "rtmbe: %d rtbke: %ld rtbre: %ld " "rtbf: %ld rtb: %ld nt: %ld " - "onoff: %ld/%ld:%ld/%ld", + "onoff: %ld/%ld:%ld/%ld " + "barrier: %ld/%ld:%ld", rcu_torture_current, rcu_torture_current_version, list_empty(&rcu_torture_freelist), @@ -1145,14 +1203,17 @@ rcu_torture_printk(char *page) n_online_successes, n_online_attempts, n_offline_successes, - n_offline_attempts); + n_offline_attempts, + n_barrier_successes, + n_barrier_attempts, + n_rcu_torture_barrier_error); + cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG); if (atomic_read(&n_rcu_torture_mberror) != 0 || + n_rcu_torture_barrier_error != 0 || n_rcu_torture_boost_ktrerror != 0 || n_rcu_torture_boost_rterror != 0 || - n_rcu_torture_boost_failure != 0) - cnt += sprintf(&page[cnt], " !!!"); - cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG); - if (i > 1) { + n_rcu_torture_boost_failure != 0 || + i > 1) { cnt += sprintf(&page[cnt], "!!! "); atomic_inc(&n_rcu_torture_error); WARN_ON_ONCE(1); @@ -1337,6 +1398,7 @@ static void rcutorture_booster_cleanup(int cpu) /* This must be outside of the mutex, otherwise deadlock! */ kthread_stop(t); + boost_tasks[cpu] = NULL; } static int rcutorture_booster_init(int cpu) @@ -1484,13 +1546,15 @@ static void rcu_torture_onoff_cleanup(void) return; VERBOSE_PRINTK_STRING("Stopping rcu_torture_onoff task"); kthread_stop(onoff_task); + onoff_task = NULL; } #else /* #ifdef CONFIG_HOTPLUG_CPU */ -static void +static int rcu_torture_onoff_init(void) { + return 0; } static void rcu_torture_onoff_cleanup(void) @@ -1554,6 +1618,152 @@ static void rcu_torture_stall_cleanup(void) return; VERBOSE_PRINTK_STRING("Stopping rcu_torture_stall_task."); kthread_stop(stall_task); + stall_task = NULL; +} + +/* Callback function for RCU barrier testing. */ +void rcu_torture_barrier_cbf(struct rcu_head *rcu) +{ + atomic_inc(&barrier_cbs_invoked); +} + +/* kthread function to register callbacks used to test RCU barriers. */ +static int rcu_torture_barrier_cbs(void *arg) +{ + long myid = (long)arg; + struct rcu_head rcu; + + init_rcu_head_on_stack(&rcu); + VERBOSE_PRINTK_STRING("rcu_torture_barrier_cbs task started"); + set_user_nice(current, 19); + do { + wait_event(barrier_cbs_wq[myid], + atomic_read(&barrier_cbs_count) == n_barrier_cbs || + kthread_should_stop() || + fullstop != FULLSTOP_DONTSTOP); + if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP) + break; + cur_ops->call(&rcu, rcu_torture_barrier_cbf); + if (atomic_dec_and_test(&barrier_cbs_count)) + wake_up(&barrier_wq); + } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); + VERBOSE_PRINTK_STRING("rcu_torture_barrier_cbs task stopping"); + rcutorture_shutdown_absorb("rcu_torture_barrier_cbs"); + while (!kthread_should_stop()) + schedule_timeout_interruptible(1); + cur_ops->cb_barrier(); + destroy_rcu_head_on_stack(&rcu); + return 0; +} + +/* kthread function to drive and coordinate RCU barrier testing. */ +static int rcu_torture_barrier(void *arg) +{ + int i; + + VERBOSE_PRINTK_STRING("rcu_torture_barrier task starting"); + do { + atomic_set(&barrier_cbs_invoked, 0); + atomic_set(&barrier_cbs_count, n_barrier_cbs); + /* wake_up() path contains the required barriers. */ + for (i = 0; i < n_barrier_cbs; i++) + wake_up(&barrier_cbs_wq[i]); + wait_event(barrier_wq, + atomic_read(&barrier_cbs_count) == 0 || + kthread_should_stop() || + fullstop != FULLSTOP_DONTSTOP); + if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP) + break; + n_barrier_attempts++; + cur_ops->cb_barrier(); + if (atomic_read(&barrier_cbs_invoked) != n_barrier_cbs) { + n_rcu_torture_barrier_error++; + WARN_ON_ONCE(1); + } + n_barrier_successes++; + schedule_timeout_interruptible(HZ / 10); + } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); + VERBOSE_PRINTK_STRING("rcu_torture_barrier task stopping"); + rcutorture_shutdown_absorb("rcu_torture_barrier_cbs"); + while (!kthread_should_stop()) + schedule_timeout_interruptible(1); + return 0; +} + +/* Initialize RCU barrier testing. */ +static int rcu_torture_barrier_init(void) +{ + int i; + int ret; + + if (n_barrier_cbs == 0) + return 0; + if (cur_ops->call == NULL || cur_ops->cb_barrier == NULL) { + printk(KERN_ALERT "%s" TORTURE_FLAG + " Call or barrier ops missing for %s,\n", + torture_type, cur_ops->name); + printk(KERN_ALERT "%s" TORTURE_FLAG + " RCU barrier testing omitted from run.\n", + torture_type); + return 0; + } + atomic_set(&barrier_cbs_count, 0); + atomic_set(&barrier_cbs_invoked, 0); + barrier_cbs_tasks = + kzalloc(n_barrier_cbs * sizeof(barrier_cbs_tasks[0]), + GFP_KERNEL); + barrier_cbs_wq = + kzalloc(n_barrier_cbs * sizeof(barrier_cbs_wq[0]), + GFP_KERNEL); + if (barrier_cbs_tasks == NULL || barrier_cbs_wq == 0) + return -ENOMEM; + for (i = 0; i < n_barrier_cbs; i++) { + init_waitqueue_head(&barrier_cbs_wq[i]); + barrier_cbs_tasks[i] = kthread_run(rcu_torture_barrier_cbs, + (void *)(long)i, + "rcu_torture_barrier_cbs"); + if (IS_ERR(barrier_cbs_tasks[i])) { + ret = PTR_ERR(barrier_cbs_tasks[i]); + VERBOSE_PRINTK_ERRSTRING("Failed to create rcu_torture_barrier_cbs"); + barrier_cbs_tasks[i] = NULL; + return ret; + } + } + barrier_task = kthread_run(rcu_torture_barrier, NULL, + "rcu_torture_barrier"); + if (IS_ERR(barrier_task)) { + ret = PTR_ERR(barrier_task); + VERBOSE_PRINTK_ERRSTRING("Failed to create rcu_torture_barrier"); + barrier_task = NULL; + } + return 0; +} + +/* Clean up after RCU barrier testing. */ +static void rcu_torture_barrier_cleanup(void) +{ + int i; + + if (barrier_task != NULL) { + VERBOSE_PRINTK_STRING("Stopping rcu_torture_barrier task"); + kthread_stop(barrier_task); + barrier_task = NULL; + } + if (barrier_cbs_tasks != NULL) { + for (i = 0; i < n_barrier_cbs; i++) { + if (barrier_cbs_tasks[i] != NULL) { + VERBOSE_PRINTK_STRING("Stopping rcu_torture_barrier_cbs task"); + kthread_stop(barrier_cbs_tasks[i]); + barrier_cbs_tasks[i] = NULL; + } + } + kfree(barrier_cbs_tasks); + barrier_cbs_tasks = NULL; + } + if (barrier_cbs_wq != NULL) { + kfree(barrier_cbs_wq); + barrier_cbs_wq = NULL; + } } static int rcutorture_cpu_notify(struct notifier_block *self, @@ -1598,6 +1808,7 @@ rcu_torture_cleanup(void) fullstop = FULLSTOP_RMMOD; mutex_unlock(&fullstop_mutex); unregister_reboot_notifier(&rcutorture_shutdown_nb); + rcu_torture_barrier_cleanup(); rcu_torture_stall_cleanup(); if (stutter_task) { VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task"); @@ -1665,6 +1876,7 @@ rcu_torture_cleanup(void) VERBOSE_PRINTK_STRING("Stopping rcu_torture_shutdown task"); kthread_stop(shutdown_task); } + shutdown_task = NULL; rcu_torture_onoff_cleanup(); /* Wait for all RCU callbacks to fire. */ @@ -1676,7 +1888,7 @@ rcu_torture_cleanup(void) if (cur_ops->cleanup) cur_ops->cleanup(); - if (atomic_read(&n_rcu_torture_error)) + if (atomic_read(&n_rcu_torture_error) || n_rcu_torture_barrier_error) rcu_torture_print_module_parms(cur_ops, "End of test: FAILURE"); else if (n_online_successes != n_online_attempts || n_offline_successes != n_offline_attempts) @@ -1692,10 +1904,12 @@ rcu_torture_init(void) int i; int cpu; int firsterr = 0; + int retval; static struct rcu_torture_ops *torture_ops[] = { &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops, &rcu_bh_ops, &rcu_bh_sync_ops, &rcu_bh_expedited_ops, - &srcu_ops, &srcu_raw_ops, &srcu_expedited_ops, + &srcu_ops, &srcu_sync_ops, &srcu_raw_ops, + &srcu_raw_sync_ops, &srcu_expedited_ops, &sched_ops, &sched_sync_ops, &sched_expedited_ops, }; mutex_lock(&fullstop_mutex); @@ -1749,6 +1963,7 @@ rcu_torture_init(void) atomic_set(&n_rcu_torture_free, 0); atomic_set(&n_rcu_torture_mberror, 0); atomic_set(&n_rcu_torture_error, 0); + n_rcu_torture_barrier_error = 0; n_rcu_torture_boost_ktrerror = 0; n_rcu_torture_boost_rterror = 0; n_rcu_torture_boost_failure = 0; @@ -1872,7 +2087,6 @@ rcu_torture_init(void) test_boost_duration = 2; if ((test_boost == 1 && cur_ops->can_boost) || test_boost == 2) { - int retval; boost_starttime = jiffies + test_boost_interval * HZ; register_cpu_notifier(&rcutorture_cpu_nb); @@ -1897,9 +2111,22 @@ rcu_torture_init(void) goto unwind; } } - rcu_torture_onoff_init(); + i = rcu_torture_onoff_init(); + if (i != 0) { + firsterr = i; + goto unwind; + } register_reboot_notifier(&rcutorture_shutdown_nb); - rcu_torture_stall_init(); + i = rcu_torture_stall_init(); + if (i != 0) { + firsterr = i; + goto unwind; + } + retval = rcu_torture_barrier_init(); + if (retval != 0) { + firsterr = retval; + goto unwind; + } rcutorture_record_test_transition(); mutex_unlock(&fullstop_mutex); return 0; diff --git a/kernel/rcutree.c b/kernel/rcutree.c index e578dd327c64..b3ea3ac3a2b5 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -201,7 +201,6 @@ void rcu_note_context_switch(int cpu) { trace_rcu_utilization("Start context switch"); rcu_sched_qs(cpu); - rcu_preempt_note_context_switch(cpu); trace_rcu_utilization("End context switch"); } EXPORT_SYMBOL_GPL(rcu_note_context_switch); @@ -1953,6 +1952,38 @@ void call_rcu_bh(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) } EXPORT_SYMBOL_GPL(call_rcu_bh); +/* + * Because a context switch is a grace period for RCU-sched and RCU-bh, + * any blocking grace-period wait automatically implies a grace period + * if there is only one CPU online at any point time during execution + * of either synchronize_sched() or synchronize_rcu_bh(). It is OK to + * occasionally incorrectly indicate that there are multiple CPUs online + * when there was in fact only one the whole time, as this just adds + * some overhead: RCU still operates correctly. + * + * Of course, sampling num_online_cpus() with preemption enabled can + * give erroneous results if there are concurrent CPU-hotplug operations. + * For example, given a demonic sequence of preemptions in num_online_cpus() + * and CPU-hotplug operations, there could be two or more CPUs online at + * all times, but num_online_cpus() might well return one (or even zero). + * + * However, all such demonic sequences require at least one CPU-offline + * operation. Furthermore, rcu_blocking_is_gp() giving the wrong answer + * is only a problem if there is an RCU read-side critical section executing + * throughout. But RCU-sched and RCU-bh read-side critical sections + * disable either preemption or bh, which prevents a CPU from going offline. + * Therefore, the only way that rcu_blocking_is_gp() can incorrectly return + * that there is only one CPU when in fact there was more than one throughout + * is when there were no RCU readers in the system. If there are no + * RCU readers, the grace period by definition can be of zero length, + * regardless of the number of online CPUs. + */ +static inline int rcu_blocking_is_gp(void) +{ + might_sleep(); /* Check for RCU read-side critical section. */ + return num_online_cpus() <= 1; +} + /** * synchronize_sched - wait until an rcu-sched grace period has elapsed. * @@ -2543,7 +2574,7 @@ static void __init rcu_init_levelspread(struct rcu_state *rsp) for (i = NUM_RCU_LVLS - 1; i > 0; i--) rsp->levelspread[i] = CONFIG_RCU_FANOUT; - rsp->levelspread[0] = RCU_FANOUT_LEAF; + rsp->levelspread[0] = CONFIG_RCU_FANOUT_LEAF; } #else /* #ifdef CONFIG_RCU_FANOUT_EXACT */ static void __init rcu_init_levelspread(struct rcu_state *rsp) diff --git a/kernel/rcutree.h b/kernel/rcutree.h index 1e49c5685960..7f5d138dedf5 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -29,18 +29,14 @@ #include /* - * Define shape of hierarchy based on NR_CPUS and CONFIG_RCU_FANOUT. + * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and + * CONFIG_RCU_FANOUT_LEAF. * In theory, it should be possible to add more levels straightforwardly. * In practice, this did work well going from three levels to four. * Of course, your mileage may vary. */ #define MAX_RCU_LVLS 4 -#if CONFIG_RCU_FANOUT > 16 -#define RCU_FANOUT_LEAF 16 -#else /* #if CONFIG_RCU_FANOUT > 16 */ -#define RCU_FANOUT_LEAF (CONFIG_RCU_FANOUT) -#endif /* #else #if CONFIG_RCU_FANOUT > 16 */ -#define RCU_FANOUT_1 (RCU_FANOUT_LEAF) +#define RCU_FANOUT_1 (CONFIG_RCU_FANOUT_LEAF) #define RCU_FANOUT_2 (RCU_FANOUT_1 * CONFIG_RCU_FANOUT) #define RCU_FANOUT_3 (RCU_FANOUT_2 * CONFIG_RCU_FANOUT) #define RCU_FANOUT_4 (RCU_FANOUT_3 * CONFIG_RCU_FANOUT) @@ -434,7 +430,6 @@ DECLARE_PER_CPU(char, rcu_cpu_has_work); /* Forward declarations for rcutree_plugin.h */ static void rcu_bootup_announce(void); long rcu_batches_completed(void); -static void rcu_preempt_note_context_switch(int cpu); static int rcu_preempt_blocked_readers_cgp(struct rcu_node *rnp); #ifdef CONFIG_HOTPLUG_CPU static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 7082ea93566f..2411000d9869 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -153,7 +153,7 @@ static void rcu_preempt_qs(int cpu) * * Caller must disable preemption. */ -static void rcu_preempt_note_context_switch(int cpu) +void rcu_preempt_note_context_switch(void) { struct task_struct *t = current; unsigned long flags; @@ -164,7 +164,7 @@ static void rcu_preempt_note_context_switch(int cpu) (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) { /* Possibly blocking in an RCU read-side critical section. */ - rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu); + rdp = __this_cpu_ptr(rcu_preempt_state.rda); rnp = rdp->mynode; raw_spin_lock_irqsave(&rnp->lock, flags); t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED; @@ -228,7 +228,7 @@ static void rcu_preempt_note_context_switch(int cpu) * means that we continue to block the current grace period. */ local_irq_save(flags); - rcu_preempt_qs(cpu); + rcu_preempt_qs(smp_processor_id()); local_irq_restore(flags); } @@ -969,22 +969,6 @@ static void __init __rcu_init_preempt(void) rcu_init_one(&rcu_preempt_state, &rcu_preempt_data); } -/* - * Check for a task exiting while in a preemptible-RCU read-side - * critical section, clean up if so. No need to issue warnings, - * as debug_check_no_locks_held() already does this if lockdep - * is enabled. - */ -void exit_rcu(void) -{ - struct task_struct *t = current; - - if (t->rcu_read_lock_nesting == 0) - return; - t->rcu_read_lock_nesting = 1; - __rcu_read_unlock(); -} - #else /* #ifdef CONFIG_TREE_PREEMPT_RCU */ static struct rcu_state *rcu_state = &rcu_sched_state; @@ -1017,14 +1001,6 @@ void rcu_force_quiescent_state(void) } EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); -/* - * Because preemptible RCU does not exist, we never have to check for - * CPUs being in quiescent states. - */ -static void rcu_preempt_note_context_switch(int cpu) -{ -} - /* * Because preemptible RCU does not exist, there are never any preempted * RCU readers. diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4603b9d8f30a..5d89eb93f7e4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2083,6 +2083,7 @@ context_switch(struct rq *rq, struct task_struct *prev, #endif /* Here we just switch the register state and the stack. */ + rcu_switch_from(prev); switch_to(prev, next, prev); barrier(); diff --git a/kernel/srcu.c b/kernel/srcu.c index ba35f3a4a1f4..2095be3318d5 100644 --- a/kernel/srcu.c +++ b/kernel/srcu.c @@ -34,10 +34,77 @@ #include #include +/* + * Initialize an rcu_batch structure to empty. + */ +static inline void rcu_batch_init(struct rcu_batch *b) +{ + b->head = NULL; + b->tail = &b->head; +} + +/* + * Enqueue a callback onto the tail of the specified rcu_batch structure. + */ +static inline void rcu_batch_queue(struct rcu_batch *b, struct rcu_head *head) +{ + *b->tail = head; + b->tail = &head->next; +} + +/* + * Is the specified rcu_batch structure empty? + */ +static inline bool rcu_batch_empty(struct rcu_batch *b) +{ + return b->tail == &b->head; +} + +/* + * Remove the callback at the head of the specified rcu_batch structure + * and return a pointer to it, or return NULL if the structure is empty. + */ +static inline struct rcu_head *rcu_batch_dequeue(struct rcu_batch *b) +{ + struct rcu_head *head; + + if (rcu_batch_empty(b)) + return NULL; + + head = b->head; + b->head = head->next; + if (b->tail == &head->next) + rcu_batch_init(b); + + return head; +} + +/* + * Move all callbacks from the rcu_batch structure specified by "from" to + * the structure specified by "to". + */ +static inline void rcu_batch_move(struct rcu_batch *to, struct rcu_batch *from) +{ + if (!rcu_batch_empty(from)) { + *to->tail = from->head; + to->tail = from->tail; + rcu_batch_init(from); + } +} + +/* single-thread state-machine */ +static void process_srcu(struct work_struct *work); + static int init_srcu_struct_fields(struct srcu_struct *sp) { sp->completed = 0; - mutex_init(&sp->mutex); + spin_lock_init(&sp->queue_lock); + sp->running = false; + rcu_batch_init(&sp->batch_queue); + rcu_batch_init(&sp->batch_check0); + rcu_batch_init(&sp->batch_check1); + rcu_batch_init(&sp->batch_done); + INIT_DELAYED_WORK(&sp->work, process_srcu); sp->per_cpu_ref = alloc_percpu(struct srcu_struct_array); return sp->per_cpu_ref ? 0 : -ENOMEM; } @@ -73,21 +140,116 @@ EXPORT_SYMBOL_GPL(init_srcu_struct); #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /* - * srcu_readers_active_idx -- returns approximate number of readers - * active on the specified rank of per-CPU counters. + * Returns approximate total of the readers' ->seq[] values for the + * rank of per-CPU counters specified by idx. */ - -static int srcu_readers_active_idx(struct srcu_struct *sp, int idx) +static unsigned long srcu_readers_seq_idx(struct srcu_struct *sp, int idx) { int cpu; - int sum; + unsigned long sum = 0; + unsigned long t; - sum = 0; - for_each_possible_cpu(cpu) - sum += per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]; + for_each_possible_cpu(cpu) { + t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->seq[idx]); + sum += t; + } return sum; } +/* + * Returns approximate number of readers active on the specified rank + * of the per-CPU ->c[] counters. + */ +static unsigned long srcu_readers_active_idx(struct srcu_struct *sp, int idx) +{ + int cpu; + unsigned long sum = 0; + unsigned long t; + + for_each_possible_cpu(cpu) { + t = ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[idx]); + sum += t; + } + return sum; +} + +/* + * Return true if the number of pre-existing readers is determined to + * be stably zero. An example unstable zero can occur if the call + * to srcu_readers_active_idx() misses an __srcu_read_lock() increment, + * but due to task migration, sees the corresponding __srcu_read_unlock() + * decrement. This can happen because srcu_readers_active_idx() takes + * time to sum the array, and might in fact be interrupted or preempted + * partway through the summation. + */ +static bool srcu_readers_active_idx_check(struct srcu_struct *sp, int idx) +{ + unsigned long seq; + + seq = srcu_readers_seq_idx(sp, idx); + + /* + * The following smp_mb() A pairs with the smp_mb() B located in + * __srcu_read_lock(). This pairing ensures that if an + * __srcu_read_lock() increments its counter after the summation + * in srcu_readers_active_idx(), then the corresponding SRCU read-side + * critical section will see any changes made prior to the start + * of the current SRCU grace period. + * + * Also, if the above call to srcu_readers_seq_idx() saw the + * increment of ->seq[], then the call to srcu_readers_active_idx() + * must see the increment of ->c[]. + */ + smp_mb(); /* A */ + + /* + * Note that srcu_readers_active_idx() can incorrectly return + * zero even though there is a pre-existing reader throughout. + * To see this, suppose that task A is in a very long SRCU + * read-side critical section that started on CPU 0, and that + * no other reader exists, so that the sum of the counters + * is equal to one. Then suppose that task B starts executing + * srcu_readers_active_idx(), summing up to CPU 1, and then that + * task C starts reading on CPU 0, so that its increment is not + * summed, but finishes reading on CPU 2, so that its decrement + * -is- summed. Then when task B completes its sum, it will + * incorrectly get zero, despite the fact that task A has been + * in its SRCU read-side critical section the whole time. + * + * We therefore do a validation step should srcu_readers_active_idx() + * return zero. + */ + if (srcu_readers_active_idx(sp, idx) != 0) + return false; + + /* + * The remainder of this function is the validation step. + * The following smp_mb() D pairs with the smp_mb() C in + * __srcu_read_unlock(). If the __srcu_read_unlock() was seen + * by srcu_readers_active_idx() above, then any destructive + * operation performed after the grace period will happen after + * the corresponding SRCU read-side critical section. + * + * Note that there can be at most NR_CPUS worth of readers using + * the old index, which is not enough to overflow even a 32-bit + * integer. (Yes, this does mean that systems having more than + * a billion or so CPUs need to be 64-bit systems.) Therefore, + * the sum of the ->seq[] counters cannot possibly overflow. + * Therefore, the only way that the return values of the two + * calls to srcu_readers_seq_idx() can be equal is if there were + * no increments of the corresponding rank of ->seq[] counts + * in the interim. But the missed-increment scenario laid out + * above includes an increment of the ->seq[] counter by + * the corresponding __srcu_read_lock(). Therefore, if this + * scenario occurs, the return values from the two calls to + * srcu_readers_seq_idx() will differ, and thus the validation + * step below suffices. + */ + smp_mb(); /* D */ + + return srcu_readers_seq_idx(sp, idx) == seq; +} + /** * srcu_readers_active - returns approximate number of readers. * @sp: which srcu_struct to count active readers (holding srcu_read_lock). @@ -98,7 +260,14 @@ static int srcu_readers_active_idx(struct srcu_struct *sp, int idx) */ static int srcu_readers_active(struct srcu_struct *sp) { - return srcu_readers_active_idx(sp, 0) + srcu_readers_active_idx(sp, 1); + int cpu; + unsigned long sum = 0; + + for_each_possible_cpu(cpu) { + sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[0]); + sum += ACCESS_ONCE(per_cpu_ptr(sp->per_cpu_ref, cpu)->c[1]); + } + return sum; } /** @@ -131,10 +300,11 @@ int __srcu_read_lock(struct srcu_struct *sp) int idx; preempt_disable(); - idx = sp->completed & 0x1; - barrier(); /* ensure compiler looks -once- at sp->completed. */ - per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]++; - srcu_barrier(); /* ensure compiler won't misorder critical section. */ + idx = rcu_dereference_index_check(sp->completed, + rcu_read_lock_sched_held()) & 0x1; + ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) += 1; + smp_mb(); /* B */ /* Avoid leaking the critical section. */ + ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->seq[idx]) += 1; preempt_enable(); return idx; } @@ -149,8 +319,8 @@ EXPORT_SYMBOL_GPL(__srcu_read_lock); void __srcu_read_unlock(struct srcu_struct *sp, int idx) { preempt_disable(); - srcu_barrier(); /* ensure compiler won't misorder critical section. */ - per_cpu_ptr(sp->per_cpu_ref, smp_processor_id())->c[idx]--; + smp_mb(); /* C */ /* Avoid leaking the critical section. */ + ACCESS_ONCE(this_cpu_ptr(sp->per_cpu_ref)->c[idx]) -= 1; preempt_enable(); } EXPORT_SYMBOL_GPL(__srcu_read_unlock); @@ -163,14 +333,86 @@ EXPORT_SYMBOL_GPL(__srcu_read_unlock); * we repeatedly block for 1-millisecond time periods. This approach * has done well in testing, so there is no need for a config parameter. */ -#define SYNCHRONIZE_SRCU_READER_DELAY 10 +#define SRCU_RETRY_CHECK_DELAY 5 +#define SYNCHRONIZE_SRCU_TRYCOUNT 2 +#define SYNCHRONIZE_SRCU_EXP_TRYCOUNT 12 + +/* + * @@@ Wait until all pre-existing readers complete. Such readers + * will have used the index specified by "idx". + * the caller should ensures the ->completed is not changed while checking + * and idx = (->completed & 1) ^ 1 + */ +static bool try_check_zero(struct srcu_struct *sp, int idx, int trycount) +{ + for (;;) { + if (srcu_readers_active_idx_check(sp, idx)) + return true; + if (--trycount <= 0) + return false; + udelay(SRCU_RETRY_CHECK_DELAY); + } +} + +/* + * Increment the ->completed counter so that future SRCU readers will + * use the other rank of the ->c[] and ->seq[] arrays. This allows + * us to wait for pre-existing readers in a starvation-free manner. + */ +static void srcu_flip(struct srcu_struct *sp) +{ + sp->completed++; +} + +/* + * Enqueue an SRCU callback on the specified srcu_struct structure, + * initiating grace-period processing if it is not already running. + */ +void call_srcu(struct srcu_struct *sp, struct rcu_head *head, + void (*func)(struct rcu_head *head)) +{ + unsigned long flags; + + head->next = NULL; + head->func = func; + spin_lock_irqsave(&sp->queue_lock, flags); + rcu_batch_queue(&sp->batch_queue, head); + if (!sp->running) { + sp->running = true; + queue_delayed_work(system_nrt_wq, &sp->work, 0); + } + spin_unlock_irqrestore(&sp->queue_lock, flags); +} +EXPORT_SYMBOL_GPL(call_srcu); + +struct rcu_synchronize { + struct rcu_head head; + struct completion completion; +}; + +/* + * Awaken the corresponding synchronize_srcu() instance now that a + * grace period has elapsed. + */ +static void wakeme_after_rcu(struct rcu_head *head) +{ + struct rcu_synchronize *rcu; + + rcu = container_of(head, struct rcu_synchronize, head); + complete(&rcu->completion); +} + +static void srcu_advance_batches(struct srcu_struct *sp, int trycount); +static void srcu_reschedule(struct srcu_struct *sp); /* * Helper function for synchronize_srcu() and synchronize_srcu_expedited(). */ -static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void)) +static void __synchronize_srcu(struct srcu_struct *sp, int trycount) { - int idx; + struct rcu_synchronize rcu; + struct rcu_head *head = &rcu.head; + bool done = false; rcu_lockdep_assert(!lock_is_held(&sp->dep_map) && !lock_is_held(&rcu_bh_lock_map) && @@ -178,91 +420,32 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void)) !lock_is_held(&rcu_sched_lock_map), "Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section"); - idx = sp->completed; - mutex_lock(&sp->mutex); + init_completion(&rcu.completion); - /* - * Check to see if someone else did the work for us while we were - * waiting to acquire the lock. We need -two- advances of - * the counter, not just one. If there was but one, we might have - * shown up -after- our helper's first synchronize_sched(), thus - * having failed to prevent CPU-reordering races with concurrent - * srcu_read_unlock()s on other CPUs (see comment below). So we - * either (1) wait for two or (2) supply the second ourselves. - */ + head->next = NULL; + head->func = wakeme_after_rcu; + spin_lock_irq(&sp->queue_lock); + if (!sp->running) { + /* steal the processing owner */ + sp->running = true; + rcu_batch_queue(&sp->batch_check0, head); + spin_unlock_irq(&sp->queue_lock); - if ((sp->completed - idx) >= 2) { - mutex_unlock(&sp->mutex); - return; + srcu_advance_batches(sp, trycount); + if (!rcu_batch_empty(&sp->batch_done)) { + BUG_ON(sp->batch_done.head != head); + rcu_batch_dequeue(&sp->batch_done); + done = true; + } + /* give the processing owner to work_struct */ + srcu_reschedule(sp); + } else { + rcu_batch_queue(&sp->batch_queue, head); + spin_unlock_irq(&sp->queue_lock); } - sync_func(); /* Force memory barrier on all CPUs. */ - - /* - * The preceding synchronize_sched() ensures that any CPU that - * sees the new value of sp->completed will also see any preceding - * changes to data structures made by this CPU. This prevents - * some other CPU from reordering the accesses in its SRCU - * read-side critical section to precede the corresponding - * srcu_read_lock() -- ensuring that such references will in - * fact be protected. - * - * So it is now safe to do the flip. - */ - - idx = sp->completed & 0x1; - sp->completed++; - - sync_func(); /* Force memory barrier on all CPUs. */ - - /* - * At this point, because of the preceding synchronize_sched(), - * all srcu_read_lock() calls using the old counters have completed. - * Their corresponding critical sections might well be still - * executing, but the srcu_read_lock() primitives themselves - * will have finished executing. We initially give readers - * an arbitrarily chosen 10 microseconds to get out of their - * SRCU read-side critical sections, then loop waiting 1/HZ - * seconds per iteration. The 10-microsecond value has done - * very well in testing. - */ - - if (srcu_readers_active_idx(sp, idx)) - udelay(SYNCHRONIZE_SRCU_READER_DELAY); - while (srcu_readers_active_idx(sp, idx)) - schedule_timeout_interruptible(1); - - sync_func(); /* Force memory barrier on all CPUs. */ - - /* - * The preceding synchronize_sched() forces all srcu_read_unlock() - * primitives that were executing concurrently with the preceding - * for_each_possible_cpu() loop to have completed by this point. - * More importantly, it also forces the corresponding SRCU read-side - * critical sections to have also completed, and the corresponding - * references to SRCU-protected data items to be dropped. - * - * Note: - * - * Despite what you might think at first glance, the - * preceding synchronize_sched() -must- be within the - * critical section ended by the following mutex_unlock(). - * Otherwise, a task taking the early exit can race - * with a srcu_read_unlock(), which might have executed - * just before the preceding srcu_readers_active() check, - * and whose CPU might have reordered the srcu_read_unlock() - * with the preceding critical section. In this case, there - * is nothing preventing the synchronize_sched() task that is - * taking the early exit from freeing a data structure that - * is still being referenced (out of order) by the task - * doing the srcu_read_unlock(). - * - * Alternatively, the comparison with "2" on the early exit - * could be changed to "3", but this increases synchronize_srcu() - * latency for bulk loads. So the current code is preferred. - */ - - mutex_unlock(&sp->mutex); + if (!done) + wait_for_completion(&rcu.completion); } /** @@ -281,7 +464,7 @@ static void __synchronize_srcu(struct srcu_struct *sp, void (*sync_func)(void)) */ void synchronize_srcu(struct srcu_struct *sp) { - __synchronize_srcu(sp, synchronize_sched); + __synchronize_srcu(sp, SYNCHRONIZE_SRCU_TRYCOUNT); } EXPORT_SYMBOL_GPL(synchronize_srcu); @@ -289,18 +472,11 @@ EXPORT_SYMBOL_GPL(synchronize_srcu); * synchronize_srcu_expedited - Brute-force SRCU grace period * @sp: srcu_struct with which to synchronize. * - * Wait for an SRCU grace period to elapse, but use a "big hammer" - * approach to force the grace period to end quickly. This consumes - * significant time on all CPUs and is unfriendly to real-time workloads, - * so is thus not recommended for any sort of common-case code. In fact, - * if you are using synchronize_srcu_expedited() in a loop, please - * restructure your code to batch your updates, and then use a single - * synchronize_srcu() instead. + * Wait for an SRCU grace period to elapse, but be more aggressive about + * spinning rather than blocking when waiting. * * Note that it is illegal to call this function while holding any lock - * that is acquired by a CPU-hotplug notifier. And yes, it is also illegal - * to call this function from a CPU-hotplug notifier. Failing to observe - * these restriction will result in deadlock. It is also illegal to call + * that is acquired by a CPU-hotplug notifier. It is also illegal to call * synchronize_srcu_expedited() from the corresponding SRCU read-side * critical section; doing so will result in deadlock. However, it is * perfectly legal to call synchronize_srcu_expedited() on one srcu_struct @@ -309,10 +485,19 @@ EXPORT_SYMBOL_GPL(synchronize_srcu); */ void synchronize_srcu_expedited(struct srcu_struct *sp) { - __synchronize_srcu(sp, synchronize_sched_expedited); + __synchronize_srcu(sp, SYNCHRONIZE_SRCU_EXP_TRYCOUNT); } EXPORT_SYMBOL_GPL(synchronize_srcu_expedited); +/** + * srcu_barrier - Wait until all in-flight call_srcu() callbacks complete. + */ +void srcu_barrier(struct srcu_struct *sp) +{ + synchronize_srcu(sp); +} +EXPORT_SYMBOL_GPL(srcu_barrier); + /** * srcu_batches_completed - return batches completed. * @sp: srcu_struct on which to report batch completion. @@ -320,9 +505,146 @@ EXPORT_SYMBOL_GPL(synchronize_srcu_expedited); * Report the number of batches, correlated with, but not necessarily * precisely the same as, the number of grace periods that have elapsed. */ - long srcu_batches_completed(struct srcu_struct *sp) { return sp->completed; } EXPORT_SYMBOL_GPL(srcu_batches_completed); + +#define SRCU_CALLBACK_BATCH 10 +#define SRCU_INTERVAL 1 + +/* + * Move any new SRCU callbacks to the first stage of the SRCU grace + * period pipeline. + */ +static void srcu_collect_new(struct srcu_struct *sp) +{ + if (!rcu_batch_empty(&sp->batch_queue)) { + spin_lock_irq(&sp->queue_lock); + rcu_batch_move(&sp->batch_check0, &sp->batch_queue); + spin_unlock_irq(&sp->queue_lock); + } +} + +/* + * Core SRCU state machine. Advance callbacks from ->batch_check0 to + * ->batch_check1 and then to ->batch_done as readers drain. + */ +static void srcu_advance_batches(struct srcu_struct *sp, int trycount) +{ + int idx = 1 ^ (sp->completed & 1); + + /* + * Because readers might be delayed for an extended period after + * fetching ->completed for their index, at any point in time there + * might well be readers using both idx=0 and idx=1. We therefore + * need to wait for readers to clear from both index values before + * invoking a callback. + */ + + if (rcu_batch_empty(&sp->batch_check0) && + rcu_batch_empty(&sp->batch_check1)) + return; /* no callbacks need to be advanced */ + + if (!try_check_zero(sp, idx, trycount)) + return; /* failed to advance, will try after SRCU_INTERVAL */ + + /* + * The callbacks in ->batch_check1 have already done with their + * first zero check and flip back when they were enqueued on + * ->batch_check0 in a previous invocation of srcu_advance_batches(). + * (Presumably try_check_zero() returned false during that + * invocation, leaving the callbacks stranded on ->batch_check1.) + * They are therefore ready to invoke, so move them to ->batch_done. + */ + rcu_batch_move(&sp->batch_done, &sp->batch_check1); + + if (rcu_batch_empty(&sp->batch_check0)) + return; /* no callbacks need to be advanced */ + srcu_flip(sp); + + /* + * The callbacks in ->batch_check0 just finished their + * first check zero and flip, so move them to ->batch_check1 + * for future checking on the other idx. + */ + rcu_batch_move(&sp->batch_check1, &sp->batch_check0); + + /* + * SRCU read-side critical sections are normally short, so check + * at least twice in quick succession after a flip. + */ + trycount = trycount < 2 ? 2 : trycount; + if (!try_check_zero(sp, idx^1, trycount)) + return; /* failed to advance, will try after SRCU_INTERVAL */ + + /* + * The callbacks in ->batch_check1 have now waited for all + * pre-existing readers using both idx values. They are therefore + * ready to invoke, so move them to ->batch_done. + */ + rcu_batch_move(&sp->batch_done, &sp->batch_check1); +} + +/* + * Invoke a limited number of SRCU callbacks that have passed through + * their grace period. If there are more to do, SRCU will reschedule + * the workqueue. + */ +static void srcu_invoke_callbacks(struct srcu_struct *sp) +{ + int i; + struct rcu_head *head; + + for (i = 0; i < SRCU_CALLBACK_BATCH; i++) { + head = rcu_batch_dequeue(&sp->batch_done); + if (!head) + break; + local_bh_disable(); + head->func(head); + local_bh_enable(); + } +} + +/* + * Finished one round of SRCU grace period. Start another if there are + * more SRCU callbacks queued, otherwise put SRCU into not-running state. + */ +static void srcu_reschedule(struct srcu_struct *sp) +{ + bool pending = true; + + if (rcu_batch_empty(&sp->batch_done) && + rcu_batch_empty(&sp->batch_check1) && + rcu_batch_empty(&sp->batch_check0) && + rcu_batch_empty(&sp->batch_queue)) { + spin_lock_irq(&sp->queue_lock); + if (rcu_batch_empty(&sp->batch_done) && + rcu_batch_empty(&sp->batch_check1) && + rcu_batch_empty(&sp->batch_check0) && + rcu_batch_empty(&sp->batch_queue)) { + sp->running = false; + pending = false; + } + spin_unlock_irq(&sp->queue_lock); + } + + if (pending) + queue_delayed_work(system_nrt_wq, &sp->work, SRCU_INTERVAL); +} + +/* + * This is the work-queue function that handles SRCU grace periods. + */ +static void process_srcu(struct work_struct *work) +{ + struct srcu_struct *sp; + + sp = container_of(work, struct srcu_struct, work.work); + + srcu_collect_new(sp); + srcu_advance_batches(sp, 1); + srcu_invoke_callbacks(sp); + srcu_reschedule(sp); +} diff --git a/kernel/timer.c b/kernel/timer.c index a297ffcf888e..837c552fe838 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -861,7 +861,13 @@ EXPORT_SYMBOL(mod_timer); * * mod_timer_pinned() is a way to update the expire field of an * active timer (if the timer is inactive it will be activated) - * and not allow the timer to be migrated to a different CPU. + * and to ensure that the timer is scheduled on the current CPU. + * + * Note that this does not prevent the timer from being migrated + * when the current CPU goes offline. If this is a problem for + * you, use CPU-hotplug notifiers to handle it correctly, for + * example, cancelling the timer when the corresponding CPU goes + * offline. * * mod_timer_pinned(timer, expires) is equivalent to: * diff --git a/lib/list_debug.c b/lib/list_debug.c index 982b850d4e7a..3810b481f940 100644 --- a/lib/list_debug.c +++ b/lib/list_debug.c @@ -10,6 +10,7 @@ #include #include #include +#include /* * Insert a new entry between two known consecutive entries. @@ -75,3 +76,24 @@ void list_del(struct list_head *entry) entry->prev = LIST_POISON2; } EXPORT_SYMBOL(list_del); + +/* + * RCU variants. + */ +void __list_add_rcu(struct list_head *new, + struct list_head *prev, struct list_head *next) +{ + WARN(next->prev != prev, + "list_add_rcu corruption. next->prev should be " + "prev (%p), but was %p. (next=%p).\n", + prev, next->prev, next); + WARN(prev->next != next, + "list_add_rcu corruption. prev->next should be " + "next (%p), but was %p. (prev=%p).\n", + next, prev->next, prev); + new->next = next; + new->prev = prev; + rcu_assign_pointer(list_next_rcu(prev), new); + next->prev = new; +} +EXPORT_SYMBOL(__list_add_rcu);