diff options
| -rw-r--r-- | Documentation/RCU/checklist.txt | 39 | ||||
| -rw-r--r-- | Documentation/RCU/rcubarrier.txt | 15 | ||||
| -rw-r--r-- | Documentation/RCU/torture.txt | 9 | ||||
| -rw-r--r-- | Documentation/RCU/whatisRCU.txt | 6 | ||||
| -rw-r--r-- | include/linux/init_task.h | 4 | ||||
| -rw-r--r-- | include/linux/key.h | 4 | ||||
| -rw-r--r-- | include/linux/rcupdate.h | 50 | ||||
| -rw-r--r-- | kernel/rcupdate.c | 44 | ||||
| -rw-r--r-- | kernel/rcutiny.c | 4 | ||||
| -rw-r--r-- | kernel/rcutiny_plugin.h | 49 | ||||
| -rw-r--r-- | kernel/rcutorture.c | 36 | ||||
| -rw-r--r-- | kernel/rcutree.c | 164 | ||||
| -rw-r--r-- | kernel/rcutree.h | 1 | ||||
| -rw-r--r-- | kernel/rcutree_plugin.h | 81 | ||||
| -rw-r--r-- | kernel/time/tick-sched.c | 2 |
15 files changed, 251 insertions, 257 deletions
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt index 5c8d74968090..fc103d7a0474 100644 --- a/Documentation/RCU/checklist.txt +++ b/Documentation/RCU/checklist.txt @@ -162,9 +162,9 @@ over a rather long period of time, but improvements are always welcome! when publicizing a pointer to a structure that can be traversed by an RCU read-side critical section. -5. If call_rcu(), or a related primitive such as call_rcu_bh() or - call_rcu_sched(), is used, the callback function must be - written to be called from softirq context. In particular, +5. If call_rcu(), or a related primitive such as call_rcu_bh(), + call_rcu_sched(), or call_srcu() is used, the callback function + must be written to be called from softirq context. In particular, it cannot block. 6. Since synchronize_rcu() can block, it cannot be called from @@ -202,11 +202,12 @@ over a rather long period of time, but improvements are always welcome! updater uses call_rcu_sched() or synchronize_sched(), then the corresponding readers must disable preemption, possibly by calling rcu_read_lock_sched() and rcu_read_unlock_sched(). - If the updater uses synchronize_srcu(), the the corresponding - readers must use srcu_read_lock() and srcu_read_unlock(), - and with the same srcu_struct. The rules for the expedited - primitives are the same as for their non-expedited counterparts. - Mixing things up will result in confusion and broken kernels. + If the updater uses synchronize_srcu() or call_srcu(), + the the corresponding readers must use srcu_read_lock() and + srcu_read_unlock(), and with the same srcu_struct. The rules for + the expedited primitives are the same as for their non-expedited + counterparts. Mixing things up will result in confusion and + broken kernels. One exception to this rule: rcu_read_lock() and rcu_read_unlock() may be substituted for rcu_read_lock_bh() and rcu_read_unlock_bh() @@ -333,14 +334,14 @@ over a rather long period of time, but improvements are always welcome! victim CPU from ever going offline.) 14. SRCU (srcu_read_lock(), srcu_read_unlock(), srcu_dereference(), - synchronize_srcu(), and synchronize_srcu_expedited()) may only - be invoked from process context. Unlike other forms of RCU, it - -is- permissible to block in an SRCU read-side critical section - (demarked by srcu_read_lock() and srcu_read_unlock()), hence the - "SRCU": "sleepable RCU". Please note that if you don't need - to sleep in read-side critical sections, you should be using - RCU rather than SRCU, because RCU is almost always faster and - easier to use than is SRCU. + synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu()) + may only be invoked from process context. Unlike other forms of + RCU, it -is- permissible to block in an SRCU read-side critical + section (demarked by srcu_read_lock() and srcu_read_unlock()), + hence the "SRCU": "sleepable RCU". Please note that if you + don't need to sleep in read-side critical sections, you should be + using RCU rather than SRCU, because RCU is almost always faster + and easier to use than is SRCU. If you need to enter your read-side critical section in a hardirq or exception handler, and then exit that same read-side @@ -353,8 +354,8 @@ over a rather long period of time, but improvements are always welcome! cleanup_srcu_struct(). These are passed a "struct srcu_struct" that defines the scope of a given SRCU domain. Once initialized, the srcu_struct is passed to srcu_read_lock(), srcu_read_unlock() - synchronize_srcu(), and synchronize_srcu_expedited(). A given - synchronize_srcu() waits only for SRCU read-side critical + synchronize_srcu(), synchronize_srcu_expedited(), and call_srcu(). + A given synchronize_srcu() waits only for SRCU read-side critical sections governed by srcu_read_lock() and srcu_read_unlock() calls that have been passed the same srcu_struct. This property is what makes sleeping read-side critical sections tolerable -- @@ -374,7 +375,7 @@ over a rather long period of time, but improvements are always welcome! requiring SRCU's read-side deadlock immunity or low read-side realtime latency. - Note that, rcu_assign_pointer() relates to SRCU just as they do + Note that, rcu_assign_pointer() relates to SRCU just as it does to other forms of RCU. 15. The whole point of call_rcu(), synchronize_rcu(), and friends diff --git a/Documentation/RCU/rcubarrier.txt b/Documentation/RCU/rcubarrier.txt index e439a0edee22..38428c125135 100644 --- a/Documentation/RCU/rcubarrier.txt +++ b/Documentation/RCU/rcubarrier.txt @@ -79,8 +79,6 @@ complete. Pseudo-code using rcu_barrier() is as follows: 2. Execute rcu_barrier(). 3. Allow the module to be unloaded. -Quick Quiz #1: Why is there no srcu_barrier()? - The rcutorture module makes use of rcu_barrier in its exit function as follows: @@ -162,7 +160,7 @@ for any pre-existing callbacks to complete. Then lines 55-62 print status and do operation-specific cleanup, and then return, permitting the module-unload operation to be completed. -Quick Quiz #2: Is there any other situation where rcu_barrier() might +Quick Quiz #1: Is there any other situation where rcu_barrier() might be required? Your module might have additional complications. For example, if your @@ -242,7 +240,7 @@ reaches zero, as follows: 4 complete(&rcu_barrier_completion); 5 } -Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes +Quick Quiz #2: What happens if CPU 0's rcu_barrier_func() executes immediately (thus incrementing rcu_barrier_cpu_count to the value one), but the other CPU's rcu_barrier_func() invocations are delayed for a full grace period? Couldn't this result in @@ -259,12 +257,7 @@ so that your module may be safely unloaded. Answers to Quick Quizzes -Quick Quiz #1: Why is there no srcu_barrier()? - -Answer: Since there is no call_srcu(), there can be no outstanding SRCU - callbacks. Therefore, there is no need to wait for them. - -Quick Quiz #2: Is there any other situation where rcu_barrier() might +Quick Quiz #1: Is there any other situation where rcu_barrier() might be required? Answer: Interestingly enough, rcu_barrier() was not originally @@ -278,7 +271,7 @@ Answer: Interestingly enough, rcu_barrier() was not originally implementing rcutorture, and found that rcu_barrier() solves this problem as well. -Quick Quiz #3: What happens if CPU 0's rcu_barrier_func() executes +Quick Quiz #2: What happens if CPU 0's rcu_barrier_func() executes immediately (thus incrementing rcu_barrier_cpu_count to the value one), but the other CPU's rcu_barrier_func() invocations are delayed for a full grace period? Couldn't this result in diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt index 4ddf3913fd8c..7dce8a17eac2 100644 --- a/Documentation/RCU/torture.txt +++ b/Documentation/RCU/torture.txt @@ -174,11 +174,20 @@ torture_type The type of RCU to test, with string values as follows: and synchronize_rcu_bh_expedited(). "srcu": srcu_read_lock(), srcu_read_unlock() and + call_srcu(). + + "srcu_sync": srcu_read_lock(), srcu_read_unlock() and synchronize_srcu(). "srcu_expedited": srcu_read_lock(), srcu_read_unlock() and synchronize_srcu_expedited(). + "srcu_raw": srcu_read_lock_raw(), srcu_read_unlock_raw(), + and call_srcu(). + + "srcu_raw_sync": srcu_read_lock_raw(), srcu_read_unlock_raw(), + and synchronize_srcu(). + "sched": preempt_disable(), preempt_enable(), and call_rcu_sched(). diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt index 6bbe8dcdc3da..69ee188515e7 100644 --- a/Documentation/RCU/whatisRCU.txt +++ b/Documentation/RCU/whatisRCU.txt @@ -833,9 +833,9 @@ sched: Critical sections Grace period Barrier SRCU: Critical sections Grace period Barrier - srcu_read_lock synchronize_srcu N/A - srcu_read_unlock synchronize_srcu_expedited - srcu_read_lock_raw + srcu_read_lock synchronize_srcu srcu_barrier + srcu_read_unlock call_srcu + srcu_read_lock_raw synchronize_srcu_expedited srcu_read_unlock_raw srcu_dereference diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 9e65eff6af3b..8a7476186990 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -168,8 +168,8 @@ extern struct cred init_cred; .children = LIST_HEAD_INIT(tsk.children), \ .sibling = LIST_HEAD_INIT(tsk.sibling), \ .group_leader = &tsk, \ - RCU_INIT_POINTER(.real_cred, &init_cred), \ - RCU_INIT_POINTER(.cred, &init_cred), \ + RCU_POINTER_INITIALIZER(real_cred, &init_cred), \ + RCU_POINTER_INITIALIZER(cred, &init_cred), \ .comm = INIT_TASK_COMM, \ .thread = INIT_THREAD, \ .fs = &init_fs, \ diff --git a/include/linux/key.h b/include/linux/key.h index 4cd22ed627ef..cef3b315ba7c 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -303,7 +303,9 @@ static inline bool key_is_instantiated(const struct key *key) rwsem_is_locked(&((struct key *)(KEY))->sem))) #define rcu_assign_keypointer(KEY, PAYLOAD) \ - (rcu_assign_pointer((KEY)->payload.rcudata, PAYLOAD)) +do { \ + rcu_assign_pointer((KEY)->payload.rcudata, (PAYLOAD)); \ +} while (0) #ifdef CONFIG_SYSCTL extern ctl_table key_sysctls[]; diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 9cac722b169c..c2c0d86dd3ac 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -147,6 +147,7 @@ extern void synchronize_sched(void); extern void __rcu_read_lock(void); extern void __rcu_read_unlock(void); +extern void rcu_read_unlock_special(struct task_struct *t); void synchronize_rcu(void); /* @@ -255,6 +256,10 @@ static inline void destroy_rcu_head_on_stack(struct rcu_head *head) } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +#if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP) +extern int rcu_is_cpu_idle(void); +#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP) */ + #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ @@ -266,15 +271,6 @@ static inline bool rcu_lockdep_current_cpu_online(void) #ifdef CONFIG_DEBUG_LOCK_ALLOC -#ifdef CONFIG_PROVE_RCU -extern int rcu_is_cpu_idle(void); -#else /* !CONFIG_PROVE_RCU */ -static inline int rcu_is_cpu_idle(void) -{ - return 0; -} -#endif /* else !CONFIG_PROVE_RCU */ - static inline void rcu_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 0, 2, 1, NULL, _THIS_IP_); @@ -513,10 +509,10 @@ static inline void rcu_preempt_sleep_check(void) (_________p1); \ }) #define __rcu_assign_pointer(p, v, space) \ - ({ \ + do { \ smp_wmb(); \ (p) = (typeof(*v) __force space *)(v); \ - }) + } while (0) /** @@ -851,7 +847,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * * Assigns the specified value to the specified RCU-protected * pointer, ensuring that any concurrent RCU readers will see - * any prior initialization. Returns the value assigned. + * any prior initialization. * * Inserts memory barriers on architectures that require them * (which is most of them), and also prevents the compiler from @@ -903,25 +899,17 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * the reader-accessible portions of the linked structure. */ #define RCU_INIT_POINTER(p, v) \ - p = (typeof(*v) __force __rcu *)(v) - -static __always_inline bool __is_kfree_rcu_offset(unsigned long offset) -{ - return offset < 4096; -} - -static __always_inline -void __kfree_rcu(struct rcu_head *head, unsigned long offset) -{ - typedef void (*rcu_callback)(struct rcu_head *); - - BUILD_BUG_ON(!__builtin_constant_p(offset)); - - /* See the kfree_rcu() header comment. */ - BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); + do { \ + p = (typeof(*v) __force __rcu *)(v); \ + } while (0) - kfree_call_rcu(head, (rcu_callback)offset); -} +/** + * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer + * + * GCC-style initialization for an RCU-protected pointer in a structure field. + */ +#define RCU_POINTER_INITIALIZER(p, v) \ + .p = (typeof(*v) __force __rcu *)(v) /* * Does the specified offset indicate that the corresponding rcu_head @@ -935,7 +923,7 @@ void __kfree_rcu(struct rcu_head *head, unsigned long offset) #define __kfree_rcu(head, offset) \ do { \ BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \ - call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \ + kfree_call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \ } while (0) /** diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index 95cba41ce1e9..4e6a61b15e86 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -54,6 +54,50 @@ #ifdef CONFIG_PREEMPT_RCU /* + * Preemptible RCU implementation for rcu_read_lock(). + * Just increment ->rcu_read_lock_nesting, shared state will be updated + * if we block. + */ +void __rcu_read_lock(void) +{ + current->rcu_read_lock_nesting++; + barrier(); /* critical section after entry code. */ +} +EXPORT_SYMBOL_GPL(__rcu_read_lock); + +/* + * Preemptible RCU implementation for rcu_read_unlock(). + * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost + * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then + * invoke rcu_read_unlock_special() to clean up after a context switch + * in an RCU read-side critical section and other special cases. + */ +void __rcu_read_unlock(void) +{ + struct task_struct *t = current; + + if (t->rcu_read_lock_nesting != 1) { + --t->rcu_read_lock_nesting; + } else { + 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))) + rcu_read_unlock_special(t); + barrier(); /* ->rcu_read_unlock_special load before assign */ + t->rcu_read_lock_nesting = 0; + } +#ifdef CONFIG_PROVE_LOCKING + { + int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); + + WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); + } +#endif /* #ifdef CONFIG_PROVE_LOCKING */ +} +EXPORT_SYMBOL_GPL(__rcu_read_unlock); + +/* * 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 diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c index 37a5444204d2..547b1fe5b052 100644 --- a/kernel/rcutiny.c +++ b/kernel/rcutiny.c @@ -172,7 +172,7 @@ void rcu_irq_enter(void) local_irq_restore(flags); } -#ifdef CONFIG_PROVE_RCU +#ifdef CONFIG_DEBUG_LOCK_ALLOC /* * Test whether RCU thinks that the current CPU is idle. @@ -183,7 +183,7 @@ int rcu_is_cpu_idle(void) } EXPORT_SYMBOL(rcu_is_cpu_idle); -#endif /* #ifdef CONFIG_PROVE_RCU */ +#endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /* * Test whether the current CPU was interrupted from idle. Nested diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h index fc31a2d65100..116725b5edfb 100644 --- a/kernel/rcutiny_plugin.h +++ b/kernel/rcutiny_plugin.h @@ -132,7 +132,6 @@ static struct rcu_preempt_ctrlblk rcu_preempt_ctrlblk = { RCU_TRACE(.rcb.name = "rcu_preempt") }; -static void rcu_read_unlock_special(struct task_struct *t); static int rcu_preempted_readers_exp(void); static void rcu_report_exp_done(void); @@ -527,23 +526,11 @@ void rcu_preempt_note_context_switch(void) } /* - * Tiny-preemptible RCU implementation for rcu_read_lock(). - * Just increment ->rcu_read_lock_nesting, shared state will be updated - * if we block. - */ -void __rcu_read_lock(void) -{ - current->rcu_read_lock_nesting++; - barrier(); /* needed if we ever invoke rcu_read_lock in rcutiny.c */ -} -EXPORT_SYMBOL_GPL(__rcu_read_lock); - -/* * Handle special cases during rcu_read_unlock(), such as needing to * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -static noinline void rcu_read_unlock_special(struct task_struct *t) +void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; @@ -627,38 +614,6 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) } /* - * Tiny-preemptible RCU implementation for rcu_read_unlock(). - * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost - * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then - * invoke rcu_read_unlock_special() to clean up after a context switch - * in an RCU read-side critical section and other special cases. - */ -void __rcu_read_unlock(void) -{ - struct task_struct *t = current; - - barrier(); /* needed if we ever invoke rcu_read_unlock in rcutiny.c */ - if (t->rcu_read_lock_nesting != 1) - --t->rcu_read_lock_nesting; - else { - t->rcu_read_lock_nesting = INT_MIN; - barrier(); /* assign before ->rcu_read_unlock_special load */ - if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special))) - rcu_read_unlock_special(t); - barrier(); /* ->rcu_read_unlock_special load before assign */ - t->rcu_read_lock_nesting = 0; - } -#ifdef CONFIG_PROVE_LOCKING - { - int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); - - WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); - } -#endif /* #ifdef CONFIG_PROVE_LOCKING */ -} -EXPORT_SYMBOL_GPL(__rcu_read_unlock); - -/* * Check for a quiescent state from the current CPU. When a task blocks, * the task is recorded in the rcu_preempt_ctrlblk structure, which is * checked elsewhere. This is called from the scheduling-clock interrupt. @@ -846,8 +801,6 @@ EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); */ int rcu_preempt_needs_cpu(void) { - if (!rcu_preempt_running_reader()) - rcu_preempt_cpu_qs(); return rcu_preempt_ctrlblk.rcb.rcucblist != NULL; } diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index e66b34ab7555..c279ee920947 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -206,6 +206,7 @@ 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 bool barrier_phase; /* Test phase. */ 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); @@ -635,6 +636,17 @@ static void srcu_torture_synchronize(void) synchronize_srcu(&srcu_ctl); } +static void srcu_torture_call(struct rcu_head *head, + void (*func)(struct rcu_head *head)) +{ + call_srcu(&srcu_ctl, head, func); +} + +static void srcu_torture_barrier(void) +{ + srcu_barrier(&srcu_ctl); +} + static int srcu_torture_stats(char *page) { int cnt = 0; @@ -661,8 +673,8 @@ static struct rcu_torture_ops srcu_ops = { .completed = srcu_torture_completed, .deferred_free = srcu_torture_deferred_free, .sync = srcu_torture_synchronize, - .call = NULL, - .cb_barrier = NULL, + .call = srcu_torture_call, + .cb_barrier = srcu_torture_barrier, .stats = srcu_torture_stats, .name = "srcu" }; @@ -1013,7 +1025,11 @@ rcu_torture_fakewriter(void *arg) do { schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10); udelay(rcu_random(&rand) & 0x3ff); - cur_ops->sync(); + if (cur_ops->cb_barrier != NULL && + rcu_random(&rand) % (nfakewriters * 8) == 0) + cur_ops->cb_barrier(); + else + cur_ops->sync(); rcu_stutter_wait("rcu_torture_fakewriter"); } while (!kthread_should_stop() && fullstop == FULLSTOP_DONTSTOP); @@ -1631,6 +1647,7 @@ void rcu_torture_barrier_cbf(struct rcu_head *rcu) static int rcu_torture_barrier_cbs(void *arg) { long myid = (long)arg; + bool lastphase = 0; struct rcu_head rcu; init_rcu_head_on_stack(&rcu); @@ -1638,9 +1655,11 @@ static int rcu_torture_barrier_cbs(void *arg) set_user_nice(current, 19); do { wait_event(barrier_cbs_wq[myid], - atomic_read(&barrier_cbs_count) == n_barrier_cbs || + barrier_phase != lastphase || kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP); + lastphase = barrier_phase; + smp_mb(); /* ensure barrier_phase load before ->call(). */ if (kthread_should_stop() || fullstop != FULLSTOP_DONTSTOP) break; cur_ops->call(&rcu, rcu_torture_barrier_cbf); @@ -1665,7 +1684,8 @@ static int rcu_torture_barrier(void *arg) do { atomic_set(&barrier_cbs_invoked, 0); atomic_set(&barrier_cbs_count, n_barrier_cbs); - /* wake_up() path contains the required barriers. */ + smp_mb(); /* Ensure barrier_phase after prior assignments. */ + barrier_phase = !barrier_phase; for (i = 0; i < n_barrier_cbs; i++) wake_up(&barrier_cbs_wq[i]); wait_event(barrier_wq, @@ -1684,7 +1704,7 @@ static int rcu_torture_barrier(void *arg) 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"); + rcutorture_shutdown_absorb("rcu_torture_barrier"); while (!kthread_should_stop()) schedule_timeout_interruptible(1); return 0; @@ -1908,8 +1928,8 @@ rcu_torture_init(void) 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_sync_ops, &srcu_raw_ops, - &srcu_raw_sync_ops, &srcu_expedited_ops, + &srcu_ops, &srcu_sync_ops, &srcu_expedited_ops, + &srcu_raw_ops, &srcu_raw_sync_ops, &sched_ops, &sched_sync_ops, &sched_expedited_ops, }; mutex_lock(&fullstop_mutex); diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 967b4bed2cf3..117218a43724 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -359,7 +359,7 @@ static void rcu_idle_enter_common(struct rcu_dynticks *rdtp, long long oldval) struct task_struct *idle = idle_task(smp_processor_id()); trace_rcu_dyntick("Error on entry: not idle task", oldval, 0); - ftrace_dump(DUMP_ALL); + ftrace_dump(DUMP_ORIG); WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ @@ -469,7 +469,7 @@ static void rcu_idle_exit_common(struct rcu_dynticks *rdtp, long long oldval) trace_rcu_dyntick("Error on exit: not idle task", oldval, rdtp->dynticks_nesting); - ftrace_dump(DUMP_ALL); + ftrace_dump(DUMP_ORIG); WARN_ONCE(1, "Current pid: %d comm: %s / Idle pid: %d comm: %s", current->pid, current->comm, idle->pid, idle->comm); /* must be idle task! */ @@ -586,8 +586,6 @@ void rcu_nmi_exit(void) WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1); } -#ifdef CONFIG_PROVE_RCU - /** * rcu_is_cpu_idle - see if RCU thinks that the current CPU is idle * @@ -605,7 +603,7 @@ int rcu_is_cpu_idle(void) } EXPORT_SYMBOL(rcu_is_cpu_idle); -#ifdef CONFIG_HOTPLUG_CPU +#if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) /* * Is the current CPU online? Disable preemption to avoid false positives @@ -646,9 +644,7 @@ bool rcu_lockdep_current_cpu_online(void) } EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online); -#endif /* #ifdef CONFIG_HOTPLUG_CPU */ - -#endif /* #ifdef CONFIG_PROVE_RCU */ +#endif /* #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU) */ /** * rcu_is_cpu_rrupt_from_idle - see if idle or immediately interrupted from idle @@ -734,7 +730,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) int cpu; long delta; unsigned long flags; - int ndetected; + int ndetected = 0; struct rcu_node *rnp = rcu_get_root(rsp); /* Only let one CPU complain about others per time interval. */ @@ -775,7 +771,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp) */ rnp = rcu_get_root(rsp); raw_spin_lock_irqsave(&rnp->lock, flags); - ndetected = rcu_print_task_stall(rnp); + ndetected += rcu_print_task_stall(rnp); raw_spin_unlock_irqrestore(&rnp->lock, flags); print_cpu_stall_info_end(); @@ -939,6 +935,18 @@ check_for_new_grace_period(struct rcu_state *rsp, struct rcu_data *rdp) } /* + * Initialize the specified rcu_data structure's callback list to empty. + */ +static void init_callback_list(struct rcu_data *rdp) +{ + int i; + + rdp->nxtlist = NULL; + for (i = 0; i < RCU_NEXT_SIZE; i++) + rdp->nxttail[i] = &rdp->nxtlist; +} + +/* * Advance this CPU's callbacks, but only if the current grace period * has ended. This may be called only from the CPU to whom the rdp * belongs. In addition, the corresponding leaf rcu_node structure's @@ -1330,8 +1338,6 @@ static void rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, struct rcu_node *rnp, struct rcu_data *rdp) { - int i; - /* * Orphan the callbacks. First adjust the counts. This is safe * because ->onofflock excludes _rcu_barrier()'s adoption of @@ -1342,7 +1348,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, rsp->qlen += rdp->qlen; rdp->n_cbs_orphaned += rdp->qlen; rdp->qlen_lazy = 0; - rdp->qlen = 0; + ACCESS_ONCE(rdp->qlen) = 0; } /* @@ -1371,9 +1377,7 @@ rcu_send_cbs_to_orphanage(int cpu, struct rcu_state *rsp, } /* Finally, initialize the rcu_data structure's list to empty. */ - rdp->nxtlist = NULL; - for (i = 0; i < RCU_NEXT_SIZE; i++) - rdp->nxttail[i] = &rdp->nxtlist; + init_callback_list(rdp); } /* @@ -1507,6 +1511,9 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp) raw_spin_unlock_irqrestore(&rnp->lock, flags); if (need_report & RCU_OFL_TASKS_EXP_GP) rcu_report_exp_rnp(rsp, rnp, true); + WARN_ONCE(rdp->qlen != 0 || rdp->nxtlist != NULL, + "rcu_cleanup_dead_cpu: Callbacks on offline CPU %d: qlen=%lu, nxtlist=%p\n", + cpu, rdp->qlen, rdp->nxtlist); } #else /* #ifdef CONFIG_HOTPLUG_CPU */ @@ -1594,7 +1601,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) } smp_mb(); /* List handling before counting for rcu_barrier(). */ rdp->qlen_lazy -= count_lazy; - rdp->qlen -= count; + ACCESS_ONCE(rdp->qlen) -= count; rdp->n_cbs_invoked += count; /* Reinstate batch limit if we have worked down the excess. */ @@ -1607,6 +1614,7 @@ static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp) rdp->n_force_qs_snap = rsp->n_force_qs; } else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark) rdp->qlen_last_fqs_check = rdp->qlen; + WARN_ON_ONCE((rdp->nxtlist == NULL) != (rdp->qlen == 0)); local_irq_restore(flags); @@ -1858,6 +1866,56 @@ static void invoke_rcu_core(void) raise_softirq(RCU_SOFTIRQ); } +/* + * Handle any core-RCU processing required by a call_rcu() invocation. + */ +static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, + struct rcu_head *head, unsigned long flags) +{ + /* + * If called from an extended quiescent state, invoke the RCU + * core in order to force a re-evaluation of RCU's idleness. + */ + if (rcu_is_cpu_idle() && cpu_online(smp_processor_id())) + invoke_rcu_core(); + + /* If interrupts were disabled or CPU offline, don't invoke RCU core. */ + if (irqs_disabled_flags(flags) || cpu_is_offline(smp_processor_id())) + return; + + /* + * Force the grace period if too many callbacks or too long waiting. + * Enforce hysteresis, and don't invoke force_quiescent_state() + * if some other CPU has recently done so. Also, don't bother + * invoking force_quiescent_state() if the newly enqueued callback + * is the only one waiting for a grace period to complete. + */ + if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) { + + /* Are we ignoring a completed grace period? */ + rcu_process_gp_end(rsp, rdp); + check_for_new_grace_period(rsp, rdp); + + /* Start a new grace period if one not already started. */ + if (!rcu_gp_in_progress(rsp)) { + unsigned long nestflag; + struct rcu_node *rnp_root = rcu_get_root(rsp); + + raw_spin_lock_irqsave(&rnp_root->lock, nestflag); + rcu_start_gp(rsp, nestflag); /* rlses rnp_root->lock */ + } else { + /* Give the grace period a kick. */ + rdp->blimit = LONG_MAX; + if (rsp->n_force_qs == rdp->n_force_qs_snap && + *rdp->nxttail[RCU_DONE_TAIL] != head) + force_quiescent_state(rsp, 0); + rdp->n_force_qs_snap = rsp->n_force_qs; + rdp->qlen_last_fqs_check = rdp->qlen; + } + } else if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies)) + force_quiescent_state(rsp, 1); +} + static void __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), struct rcu_state *rsp, bool lazy) @@ -1882,7 +1940,7 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), rdp = this_cpu_ptr(rsp->rda); /* Add the callback to our list. */ - rdp->qlen++; + ACCESS_ONCE(rdp->qlen)++; if (lazy) rdp->qlen_lazy++; else @@ -1897,43 +1955,8 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu), else trace_rcu_callback(rsp->name, head, rdp->qlen_lazy, rdp->qlen); - /* If interrupts were disabled, don't dive into RCU core. */ - if (irqs_disabled_flags(flags)) { - local_irq_restore(flags); - return; - } - - /* - * Force the grace period if too many callbacks or too long waiting. - * Enforce hysteresis, and don't invoke force_quiescent_state() - * if some other CPU has recently done so. Also, don't bother - * invoking force_quiescent_state() if the newly enqueued callback - * is the only one waiting for a grace period to complete. - */ - if (unlikely(rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) { - - /* Are we ignoring a completed grace period? */ - rcu_process_gp_end(rsp, rdp); - check_for_new_grace_period(rsp, rdp); - - /* Start a new grace period if one not already started. */ - if (!rcu_gp_in_progress(rsp)) { - unsigned long nestflag; - struct rcu_node *rnp_root = rcu_get_root(rsp); - - raw_spin_lock_irqsave(&rnp_root->lock, nestflag); - rcu_start_gp(rsp, nestflag); /* rlses rnp_root->lock */ - } else { - /* Give the grace period a kick. */ - rdp->blimit = LONG_MAX; - if (rsp->n_force_qs == rdp->n_force_qs_snap && - *rdp->nxttail[RCU_DONE_TAIL] != head) - force_quiescent_state(rsp, 0); - rdp->n_force_qs_snap = rsp->n_force_qs; - rdp->qlen_last_fqs_check = rdp->qlen; - } - } else if (ULONG_CMP_LT(ACCESS_ONCE(rsp->jiffies_force_qs), jiffies)) - force_quiescent_state(rsp, 1); + /* Go handle any RCU core processing required. */ + __call_rcu_core(rsp, rdp, head, flags); local_irq_restore(flags); } @@ -1963,28 +1986,16 @@ EXPORT_SYMBOL_GPL(call_rcu_bh); * 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) { + int ret; + might_sleep(); /* Check for RCU read-side critical section. */ - return num_online_cpus() <= 1; + preempt_disable(); + ret = num_online_cpus() <= 1; + preempt_enable(); + return ret; } /** @@ -2473,18 +2484,15 @@ static void __init rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) { unsigned long flags; - int i; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rcu_get_root(rsp); /* Set up local state, ensuring consistent view of global state. */ raw_spin_lock_irqsave(&rnp->lock, flags); rdp->grpmask = 1UL << (cpu - rdp->mynode->grplo); - rdp->nxtlist = NULL; - for (i = 0; i < RCU_NEXT_SIZE; i++) - rdp->nxttail[i] = &rdp->nxtlist; + init_callback_list(rdp); rdp->qlen_lazy = 0; - rdp->qlen = 0; + ACCESS_ONCE(rdp->qlen) = 0; rdp->dynticks = &per_cpu(rcu_dynticks, cpu); WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != DYNTICK_TASK_EXIT_IDLE); WARN_ON_ONCE(atomic_read(&rdp->dynticks->dynticks) != 1); diff --git a/kernel/rcutree.h b/kernel/rcutree.h index b92c4550a6e6..4d29169f2124 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -100,6 +100,7 @@ struct rcu_dynticks { /* # times non-lazy CBs posted to CPU. */ unsigned long nonlazy_posted_snap; /* idle-period nonlazy_posted snapshot. */ + int tick_nohz_enabled_snap; /* Previously seen value from sysfs. */ #endif /* #ifdef CONFIG_RCU_FAST_NO_HZ */ }; diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index d18b4d383afe..a9194d5606c4 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -83,7 +83,6 @@ struct rcu_state rcu_preempt_state = DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data); static struct rcu_state *rcu_state = &rcu_preempt_state; -static void rcu_read_unlock_special(struct task_struct *t); static int rcu_preempted_readers_exp(struct rcu_node *rnp); /* @@ -238,18 +237,6 @@ static void rcu_preempt_note_context_switch(int cpu) } /* - * Tree-preemptible RCU implementation for rcu_read_lock(). - * Just increment ->rcu_read_lock_nesting, shared state will be updated - * if we block. - */ -void __rcu_read_lock(void) -{ - current->rcu_read_lock_nesting++; - barrier(); /* needed if we ever invoke rcu_read_lock in rcutree.c */ -} -EXPORT_SYMBOL_GPL(__rcu_read_lock); - -/* * Check for preempted RCU readers blocking the current grace period * for the specified rcu_node structure. If the caller needs a reliable * answer, it must hold the rcu_node's ->lock. @@ -315,7 +302,7 @@ static struct list_head *rcu_next_node_entry(struct task_struct *t, * notify RCU core processing or task having blocked during the RCU * read-side critical section. */ -static noinline void rcu_read_unlock_special(struct task_struct *t) +void rcu_read_unlock_special(struct task_struct *t) { int empty; int empty_exp; @@ -423,38 +410,6 @@ static noinline void rcu_read_unlock_special(struct task_struct *t) } } -/* - * Tree-preemptible RCU implementation for rcu_read_unlock(). - * Decrement ->rcu_read_lock_nesting. If the result is zero (outermost - * rcu_read_unlock()) and ->rcu_read_unlock_special is non-zero, then - * invoke rcu_read_unlock_special() to clean up after a context switch - * in an RCU read-side critical section and other special cases. - */ -void __rcu_read_unlock(void) -{ - struct task_struct *t = current; - - if (t->rcu_read_lock_nesting != 1) - --t->rcu_read_lock_nesting; - else { - 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))) - rcu_read_unlock_special(t); - barrier(); /* ->rcu_read_unlock_special load before assign */ - t->rcu_read_lock_nesting = 0; - } -#ifdef CONFIG_PROVE_LOCKING - { - int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting); - - WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2); - } -#endif /* #ifdef CONFIG_PROVE_LOCKING */ -} -EXPORT_SYMBOL_GPL(__rcu_read_unlock); - #ifdef CONFIG_RCU_CPU_STALL_VERBOSE /* @@ -1856,9 +1811,11 @@ static void rcu_idle_count_callbacks_posted(void) */ #define RCU_IDLE_FLUSHES 5 /* Number of dyntick-idle tries. */ #define RCU_IDLE_OPT_FLUSHES 3 /* Optional dyntick-idle tries. */ -#define RCU_IDLE_GP_DELAY 6 /* Roughly one grace period. */ +#define RCU_IDLE_GP_DELAY 4 /* Roughly one grace period. */ #define RCU_IDLE_LAZY_GP_DELAY (6 * HZ) /* Roughly six seconds. */ +extern int tick_nohz_enabled; + /* * Does the specified flavor of RCU have non-lazy callbacks pending on * the specified CPU? Both RCU flavor and CPU are specified by the @@ -1935,10 +1892,13 @@ int rcu_needs_cpu(int cpu, unsigned long *delta_jiffies) return 1; } /* Set up for the possibility that RCU will post a timer. */ - if (rcu_cpu_has_nonlazy_callbacks(cpu)) - *delta_jiffies = RCU_IDLE_GP_DELAY; - else - *delta_jiffies = RCU_IDLE_LAZY_GP_DELAY; + if (rcu_cpu_has_nonlazy_callbacks(cpu)) { + *delta_jiffies = round_up(RCU_IDLE_GP_DELAY + jiffies, + RCU_IDLE_GP_DELAY) - jiffies; + } else { + *delta_jiffies = jiffies + RCU_IDLE_LAZY_GP_DELAY; + *delta_jiffies = round_jiffies(*delta_jiffies) - jiffies; + } return 0; } @@ -1997,6 +1957,7 @@ static void rcu_cleanup_after_idle(int cpu) del_timer(&rdtp->idle_gp_timer); trace_rcu_prep_idle("Cleanup after idle"); + rdtp->tick_nohz_enabled_snap = ACCESS_ONCE(tick_nohz_enabled); } /* @@ -2022,6 +1983,18 @@ static void rcu_prepare_for_idle(int cpu) { struct timer_list *tp; struct rcu_dynticks *rdtp = &per_cpu(rcu_dynticks, cpu); + int tne; + + /* Handle nohz enablement switches conservatively. */ + tne = ACCESS_ONCE(tick_nohz_enabled); + if (tne != rdtp->tick_nohz_enabled_snap) { + if (rcu_cpu_has_callbacks(cpu)) + invoke_rcu_core(); /* force nohz to see update. */ + rdtp->tick_nohz_enabled_snap = tne; + return; + } + if (!tne) + return; /* * If this is an idle re-entry, for example, due to use of @@ -2075,10 +2048,11 @@ static void rcu_prepare_for_idle(int cpu) if (rcu_cpu_has_nonlazy_callbacks(cpu)) { trace_rcu_prep_idle("Dyntick with callbacks"); rdtp->idle_gp_timer_expires = - jiffies + RCU_IDLE_GP_DELAY; + round_up(jiffies + RCU_IDLE_GP_DELAY, + RCU_IDLE_GP_DELAY); } else { rdtp->idle_gp_timer_expires = - jiffies + RCU_IDLE_LAZY_GP_DELAY; + round_jiffies(jiffies + RCU_IDLE_LAZY_GP_DELAY); trace_rcu_prep_idle("Dyntick with lazy callbacks"); } tp = &rdtp->idle_gp_timer; @@ -2157,6 +2131,7 @@ static void print_cpu_stall_fast_no_hz(char *cp, int cpu) static void print_cpu_stall_fast_no_hz(char *cp, int cpu) { + *cp = '\0'; } #endif /* #else #ifdef CONFIG_RCU_FAST_NO_HZ */ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 869997833928..66ff07f6184c 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -105,7 +105,7 @@ static ktime_t tick_init_jiffy_update(void) /* * NO HZ enabled ? */ -static int tick_nohz_enabled __read_mostly = 1; +int tick_nohz_enabled __read_mostly = 1; /* * Enable / Disable tickless mode |