diff options
Diffstat (limited to 'include/linux/rcupdate.h')
| -rw-r--r-- | include/linux/rcupdate.h | 322 |
1 files changed, 223 insertions, 99 deletions
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 03abf883a281..c5b30054cd01 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -24,23 +24,22 @@ #include <linux/compiler.h> #include <linux/atomic.h> #include <linux/irqflags.h> -#include <linux/preempt.h> +#include <linux/sched.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> +#include <linux/cleanup.h> #include <asm/processor.h> -#include <linux/cpumask.h> #include <linux/context_tracking_irq.h> #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) -#define ulong2long(a) (*(long *)(&(a))) -#define USHORT_CMP_GE(a, b) (USHRT_MAX / 2 >= (unsigned short)((a) - (b))) -#define USHORT_CMP_LT(a, b) (USHRT_MAX / 2 < (unsigned short)((a) - (b))) + +#define RCU_SEQ_CTR_SHIFT 2 +#define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); -void rcu_barrier_tasks_rude(void); void synchronize_rcu(void); struct rcu_gp_oldstate; @@ -96,9 +95,9 @@ static inline void __rcu_read_lock(void) static inline void __rcu_read_unlock(void) { - preempt_enable(); if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) rcu_read_unlock_strict(); + preempt_enable(); } static inline int rcu_preempt_depth(void) @@ -121,14 +120,6 @@ static inline void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func) void rcu_init(void); extern int rcu_scheduler_active; void rcu_sched_clock_irq(int user); -void rcu_report_dead(unsigned int cpu); -void rcutree_migrate_callbacks(int cpu); - -#ifdef CONFIG_TASKS_RCU_GENERIC -void rcu_init_tasks_generic(void); -#else -static inline void rcu_init_tasks_generic(void) { } -#endif #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); @@ -138,10 +129,10 @@ static inline void rcu_sysrq_start(void) { } static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ -#if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)) +#if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_VIRT_XFER_TO_GUEST_WORK)) void rcu_irq_work_resched(void); #else -static inline void rcu_irq_work_resched(void) { } +static __always_inline void rcu_irq_work_resched(void) { } #endif #ifdef CONFIG_RCU_NOCB_CPU @@ -149,37 +140,19 @@ void rcu_init_nohz(void); int rcu_nocb_cpu_offload(int cpu); int rcu_nocb_cpu_deoffload(int cpu); void rcu_nocb_flush_deferred_wakeup(void); + +#define RCU_NOCB_LOCKDEP_WARN(c, s) RCU_LOCKDEP_WARN(c, s) + #else /* #ifdef CONFIG_RCU_NOCB_CPU */ + static inline void rcu_init_nohz(void) { } static inline int rcu_nocb_cpu_offload(int cpu) { return -EINVAL; } static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; } static inline void rcu_nocb_flush_deferred_wakeup(void) { } -#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ -/** - * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers - * @a: Code that RCU needs to pay attention to. - * - * RCU read-side critical sections are forbidden in the inner idle loop, - * that is, between the ct_idle_enter() and the ct_idle_exit() -- RCU - * will happily ignore any such read-side critical sections. However, - * things like powertop need tracepoints in the inner idle loop. - * - * This macro provides the way out: RCU_NONIDLE(do_something_with_RCU()) - * will tell RCU that it needs to pay attention, invoke its argument - * (in this example, calling the do_something_with_RCU() function), - * and then tell RCU to go back to ignoring this CPU. It is permissible - * to nest RCU_NONIDLE() wrappers, but not indefinitely (but the limit is - * on the order of a million or so, even on 32-bit systems). It is - * not legal to block within RCU_NONIDLE(), nor is it permissible to - * transfer control either into or out of RCU_NONIDLE()'s statement. - */ -#define RCU_NONIDLE(a) \ - do { \ - ct_irq_enter_irqson(); \ - do { a; } while (0); \ - ct_irq_exit_irqson(); \ - } while (0) +#define RCU_NOCB_LOCKDEP_WARN(c, s) + +#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /* * Note a quasi-voluntary context switch for RCU-tasks's benefit. @@ -195,6 +168,7 @@ static inline void rcu_nocb_flush_deferred_wakeup(void) { } } while (0) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); +void rcu_tasks_torture_stats_print(char *tt, char *tf); # else # define rcu_tasks_classic_qs(t, preempt) do { } while (0) # define call_rcu_tasks call_rcu @@ -213,14 +187,15 @@ void rcu_tasks_trace_qs_blkd(struct task_struct *t); do { \ int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \ \ - if (likely(!READ_ONCE((t)->trc_reader_special.b.need_qs)) && \ + if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) && \ likely(!___rttq_nesting)) { \ - rcu_trc_cmpxchg_need_qs((t), 0, TRC_NEED_QS_CHECKED); \ + rcu_trc_cmpxchg_need_qs((t), TRC_NEED_QS, TRC_NEED_QS_CHECKED); \ } else if (___rttq_nesting && ___rttq_nesting != INT_MIN && \ !READ_ONCE((t)->trc_reader_special.b.blocked)) { \ rcu_tasks_trace_qs_blkd(t); \ } \ } while (0) +void rcu_tasks_trace_torture_stats_print(char *tt, char *tf); # else # define rcu_tasks_trace_qs(t) do { } while (0) # endif @@ -232,8 +207,8 @@ do { \ } while (0) # ifdef CONFIG_TASKS_RUDE_RCU -void call_rcu_tasks_rude(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks_rude(void); +void rcu_tasks_rude_torture_stats_print(char *tt, char *tf); # endif #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false) @@ -274,6 +249,37 @@ do { \ cond_resched(); \ } while (0) +/** + * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states + * @old_ts: jiffies at start of processing. + * + * This helper is for long-running softirq handlers, such as NAPI threads in + * networking. The caller should initialize the variable passed in as @old_ts + * at the beginning of the softirq handler. When invoked frequently, this macro + * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will + * provide both RCU and RCU-Tasks quiescent states. Note that this macro + * modifies its old_ts argument. + * + * Because regions of code that have disabled softirq act as RCU read-side + * critical sections, this macro should be invoked with softirq (and + * preemption) enabled. + * + * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would + * have more chance to invoke schedule() calls and provide necessary quiescent + * states. As a contrast, calling cond_resched() only won't achieve the same + * effect because cond_resched() does not provide RCU-Tasks quiescent states. + */ +#define rcu_softirq_qs_periodic(old_ts) \ +do { \ + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ + time_after(jiffies, (old_ts) + HZ / 10)) { \ + preempt_disable(); \ + rcu_softirq_qs(); \ + preempt_enable(); \ + (old_ts) = jiffies; \ + } \ +} while (0) + /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. @@ -325,6 +331,11 @@ static inline void rcu_lock_acquire(struct lockdep_map *map) lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } +static inline void rcu_try_lock_acquire(struct lockdep_map *map) +{ + lock_acquire(map, 0, 1, 2, 0, NULL, _THIS_IP_); +} + static inline void rcu_lock_release(struct lockdep_map *map) { lock_release(map, _THIS_IP_); @@ -339,6 +350,7 @@ int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ # define rcu_lock_acquire(a) do { } while (0) +# define rcu_try_lock_acquire(a) do { } while (0) # define rcu_lock_release(a) do { } while (0) static inline int rcu_read_lock_held(void) @@ -374,25 +386,32 @@ static inline int debug_lockdep_rcu_enabled(void) * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met * @c: condition to check * @s: informative message + * + * This checks debug_lockdep_rcu_enabled() before checking (c) to + * prevent early boot splats due to lockdep not yet being initialized, + * and rechecks it after checking (c) to prevent false-positive splats + * due to races with lockdep being disabled. See commit 3066820034b5dd + * ("rcu: Reject RCU_LOCKDEP_WARN() false positives") for more detail. */ #define RCU_LOCKDEP_WARN(c, s) \ do { \ - static bool __section(".data.unlikely") __warned; \ - if ((c) && debug_lockdep_rcu_enabled() && !__warned) { \ + static bool __section(".data..unlikely") __warned; \ + if (debug_lockdep_rcu_enabled() && (c) && \ + debug_lockdep_rcu_enabled() && !__warned) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ } while (0) -#if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU) +#ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } -#else /* #ifdef CONFIG_PROVE_RCU */ +#else // #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { } -#endif /* #else #ifdef CONFIG_PROVE_RCU */ +#endif // #else // #ifndef CONFIG_PREEMPT_RCU #define rcu_sleep_check() \ do { \ @@ -404,11 +423,71 @@ static inline void rcu_preempt_sleep_check(void) { } "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) +// See RCU_LOCKDEP_WARN() for an explanation of the double call to +// debug_lockdep_rcu_enabled(). +static inline bool lockdep_assert_rcu_helper(bool c) +{ + return debug_lockdep_rcu_enabled() && + (c || !rcu_is_watching() || !rcu_lockdep_current_cpu_online()) && + debug_lockdep_rcu_enabled(); +} + +/** + * lockdep_assert_in_rcu_read_lock - WARN if not protected by rcu_read_lock() + * + * Splats if lockdep is enabled and there is no rcu_read_lock() in effect. + */ +#define lockdep_assert_in_rcu_read_lock() \ + WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map))) + +/** + * lockdep_assert_in_rcu_read_lock_bh - WARN if not protected by rcu_read_lock_bh() + * + * Splats if lockdep is enabled and there is no rcu_read_lock_bh() in effect. + * Note that local_bh_disable() and friends do not suffice here, instead an + * actual rcu_read_lock_bh() is required. + */ +#define lockdep_assert_in_rcu_read_lock_bh() \ + WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_bh_lock_map))) + +/** + * lockdep_assert_in_rcu_read_lock_sched - WARN if not protected by rcu_read_lock_sched() + * + * Splats if lockdep is enabled and there is no rcu_read_lock_sched() + * in effect. Note that preempt_disable() and friends do not suffice here, + * instead an actual rcu_read_lock_sched() is required. + */ +#define lockdep_assert_in_rcu_read_lock_sched() \ + WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_sched_lock_map))) + +/** + * lockdep_assert_in_rcu_reader - WARN if not within some type of RCU reader + * + * Splats if lockdep is enabled and there is no RCU reader of any + * type in effect. Note that regions of code protected by things like + * preempt_disable, local_bh_disable(), and local_irq_disable() all qualify + * as RCU readers. + * + * Note that this will never trigger in PREEMPT_NONE or PREEMPT_VOLUNTARY + * kernels that are not also built with PREEMPT_COUNT. But if you have + * lockdep enabled, you might as well also enable PREEMPT_COUNT. + */ +#define lockdep_assert_in_rcu_reader() \ + WARN_ON_ONCE(lockdep_assert_rcu_helper(!lock_is_held(&rcu_lock_map) && \ + !lock_is_held(&rcu_bh_lock_map) && \ + !lock_is_held(&rcu_sched_lock_map) && \ + preemptible())) + #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN(c, s) do { } while (0 && (c)) #define rcu_sleep_check() do { } while (0) +#define lockdep_assert_in_rcu_read_lock() do { } while (0) +#define lockdep_assert_in_rcu_read_lock_bh() do { } while (0) +#define lockdep_assert_in_rcu_read_lock_sched() do { } while (0) +#define lockdep_assert_in_rcu_reader() do { } while (0) + #endif /* #else #ifdef CONFIG_PROVE_RCU */ /* @@ -634,6 +713,24 @@ do { \ (c) || rcu_read_lock_sched_held(), \ __rcu) +/** + * rcu_dereference_all_check() - rcu_dereference_all with debug checking + * @p: The pointer to read, prior to dereferencing + * @c: The conditions under which the dereference will take place + * + * This is similar to rcu_dereference_check(), but allows protection + * by all forms of vanilla RCU readers, including preemption disabled, + * bh-disabled, and interrupt-disabled regions of code. Note that "vanilla + * RCU" excludes SRCU and the various Tasks RCU flavors. Please note + * that this macro should not be backported to any Linux-kernel version + * preceding v5.0 due to changes in synchronize_rcu() semantics prior + * to that version. + */ +#define rcu_dereference_all_check(p, c) \ + __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ + (c) || rcu_read_lock_any_held(), \ + __rcu) + /* * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. @@ -689,6 +786,14 @@ do { \ #define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0) /** + * rcu_dereference_all() - fetch RCU-all-protected pointer for dereferencing + * @p: The pointer to read, prior to dereferencing + * + * Makes rcu_dereference_check() do the dirty work. + */ +#define rcu_dereference_all(p) rcu_dereference_all_check(p, 0) + +/** * rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism * @p: The pointer to hand off * @@ -721,11 +826,9 @@ do { \ * sections, invocation of the corresponding RCU callback is deferred * until after the all the other CPUs exit their critical sections. * - * In v5.0 and later kernels, synchronize_rcu() and call_rcu() also - * wait for regions of code with preemption disabled, including regions of - * code with interrupts or softirqs disabled. In pre-v5.0 kernels, which - * define synchronize_sched(), only code enclosed within rcu_read_lock() - * and rcu_read_unlock() are guaranteed to be waited for. + * Both synchronize_rcu() and call_rcu() also wait for regions of code + * with preemption disabled, including regions of code with interrupts or + * softirqs disabled. * * Note, however, that RCU callbacks are permitted to run concurrently * with new RCU read-side critical sections. One way that this can happen @@ -780,11 +883,10 @@ static __always_inline void rcu_read_lock(void) * rcu_read_unlock() - marks the end of an RCU read-side critical section. * * In almost all situations, rcu_read_unlock() is immune from deadlock. - * In recent kernels that have consolidated synchronize_sched() and - * synchronize_rcu_bh() into synchronize_rcu(), this deadlock immunity - * also extends to the scheduler's runqueue and priority-inheritance - * spinlocks, courtesy of the quiescent-state deferral that is carried - * out when rcu_read_unlock() is invoked with interrupts disabled. + * This deadlock immunity also extends to the scheduler's runqueue + * and priority-inheritance spinlocks, courtesy of the quiescent-state + * deferral that is carried out when rcu_read_unlock() is invoked with + * interrupts disabled. * * See rcu_read_lock() for more information. */ @@ -792,9 +894,9 @@ static inline void rcu_read_unlock(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); + rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ __release(RCU); __rcu_read_unlock(); - rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ } /** @@ -886,6 +988,20 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) preempt_enable_notrace(); } +static __always_inline void rcu_read_lock_dont_migrate(void) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RCU)) + migrate_disable(); + rcu_read_lock(); +} + +static inline void rcu_read_unlock_migrate(void) +{ + rcu_read_unlock(); + if (IS_ENABLED(CONFIG_PREEMPT_RCU)) + migrate_enable(); +} + /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * @p: The pointer to be initialized. @@ -940,59 +1056,46 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define RCU_POINTER_INITIALIZER(p, v) \ .p = RCU_INITIALIZER(v) -/* - * Does the specified offset indicate that the corresponding rcu_head - * structure can be handled by kvfree_rcu()? - */ -#define __is_kvfree_rcu_offset(offset) ((offset) < 4096) - /** * kfree_rcu() - kfree an object after a grace period. - * @ptr: pointer to kfree for both single- and double-argument invocations. - * @rhf: the name of the struct rcu_head within the type of @ptr, - * but only for double-argument invocations. + * @ptr: pointer to kfree for double-argument invocations. + * @rhf: the name of the struct rcu_head within the type of @ptr. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore * when they are used in a kernel module, that module must invoke the * high-latency rcu_barrier() function at module-unload time. * - * The kfree_rcu() function handles this issue. Rather than encoding a - * function address in the embedded rcu_head structure, kfree_rcu() instead - * encodes the offset of the rcu_head structure within the base structure. - * Because the functions are not allowed in the low-order 4096 bytes of - * kernel virtual memory, offsets up to 4095 bytes can be accommodated. + * The kfree_rcu() function handles this issue. In order to have a universal + * callback function handling different offsets of rcu_head, the callback needs + * to determine the starting address of the freed object, which can be a large + * kmalloc or vmalloc allocation. To allow simply aligning the pointer down to + * page boundary for those, only offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will * be generated in kvfree_rcu_arg_2(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * - * Note that the allowable offset might decrease in the future, for example, - * to allow something like kmem_cache_free_rcu(). + * The object to be freed can be allocated either by kmalloc() or + * kmem_cache_alloc(). + * + * Note that the allowable offset might decrease in the future. * * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ -#define kfree_rcu(ptr, rhf...) kvfree_rcu(ptr, ## rhf) +#define kfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) +#define kvfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) /** - * kvfree_rcu() - kvfree an object after a grace period. - * - * This macro consists of one or two arguments and it is - * based on whether an object is head-less or not. If it - * has a head then a semantic stays the same as it used - * to be before: - * - * kvfree_rcu(ptr, rhf); - * - * where @ptr is a pointer to kvfree(), @rhf is the name - * of the rcu_head structure within the type of @ptr. + * kfree_rcu_mightsleep() - kfree an object after a grace period. + * @ptr: pointer to kfree for single-argument invocations. * * When it comes to head-less variant, only one argument * is passed and that is just a pointer which has to be * freed after a grace period. Therefore the semantic is * - * kvfree_rcu(ptr); + * kfree_rcu_mightsleep(ptr); * * where @ptr is the pointer to be freed by kvfree(). * @@ -1001,19 +1104,26 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * annotation. Otherwise, please switch and embed the * rcu_head structure within the type of @ptr. */ -#define kvfree_rcu(...) KVFREE_GET_MACRO(__VA_ARGS__, \ - kvfree_rcu_arg_2, kvfree_rcu_arg_1)(__VA_ARGS__) +#define kfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) +#define kvfree_rcu_mightsleep(ptr) kvfree_rcu_arg_1(ptr) + +/* + * In mm/slab_common.c, no suitable header to include here. + */ +void kvfree_call_rcu(struct rcu_head *head, void *ptr); -#define KVFREE_GET_MACRO(_1, _2, NAME, ...) NAME +/* + * The BUILD_BUG_ON() makes sure the rcu_head offset can be handled. See the + * comment of kfree_rcu() for details. + */ #define kvfree_rcu_arg_2(ptr, rhf) \ do { \ typeof (ptr) ___p = (ptr); \ \ - if (___p) { \ - BUILD_BUG_ON(!__is_kvfree_rcu_offset(offsetof(typeof(*(ptr)), rhf))); \ - kvfree_call_rcu(&((___p)->rhf), (rcu_callback_t)(unsigned long) \ - (offsetof(typeof(*(ptr)), rhf))); \ - } \ + if (___p) { \ + BUILD_BUG_ON(offsetof(typeof(*(ptr)), rhf) >= 4096); \ + kvfree_call_rcu(&((___p)->rhf), (void *) (___p)); \ + } \ } while (0) #define kvfree_rcu_arg_1(ptr) \ @@ -1021,7 +1131,7 @@ do { \ typeof(ptr) ___p = (ptr); \ \ if (___p) \ - kvfree_call_rcu(NULL, (rcu_callback_t) (___p)); \ + kvfree_call_rcu(NULL, (void *) (___p)); \ } while (0) /* @@ -1082,4 +1192,18 @@ rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) extern int rcu_expedited; extern int rcu_normal; +DEFINE_LOCK_GUARD_0(rcu, + do { + rcu_read_lock(); + /* + * sparse doesn't call the cleanup function, + * so just release immediately and don't track + * the context. We don't need to anyway, since + * the whole point of the guard is to not need + * the explicit unlock. + */ + __release(RCU); + } while (0), + rcu_read_unlock()) + #endif /* __LINUX_RCUPDATE_H */ |