diff options
Diffstat (limited to 'include/linux/rcupdate.h')
| -rw-r--r-- | include/linux/rcupdate.h | 519 |
1 files changed, 353 insertions, 166 deletions
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 7c1ceff02852..120536f4c6eb 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -27,19 +27,46 @@ #include <linux/preempt.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 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; +unsigned long get_completed_synchronize_rcu(void); +void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); + +// Maximum number of unsigned long values corresponding to +// not-yet-completed RCU grace periods. +#define NUM_ACTIVE_RCU_POLL_OLDSTATE 2 + +/** + * same_state_synchronize_rcu - Are two old-state values identical? + * @oldstate1: First old-state value. + * @oldstate2: Second old-state value. + * + * The two old-state values must have been obtained from either + * get_state_synchronize_rcu(), start_poll_synchronize_rcu(), or + * get_completed_synchronize_rcu(). Returns @true if the two values are + * identical and @false otherwise. This allows structures whose lifetimes + * are tracked by old-state values to push these values to a list header, + * allowing those structures to be slightly smaller. + */ +static inline bool same_state_synchronize_rcu(unsigned long oldstate1, unsigned long oldstate2) +{ + return oldstate1 == oldstate2; +} + #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); @@ -51,7 +78,7 @@ void __rcu_read_unlock(void); * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ -#define rcu_preempt_depth() (current->rcu_read_lock_nesting) +#define rcu_preempt_depth() READ_ONCE(current->rcu_read_lock_nesting) #else /* #ifdef CONFIG_PREEMPT_RCU */ @@ -68,8 +95,9 @@ static inline void __rcu_read_lock(void) static inline void __rcu_read_unlock(void) { + if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) + rcu_read_unlock_strict(); preempt_enable(); - rcu_read_unlock_strict(); } static inline int rcu_preempt_depth(void) @@ -79,12 +107,19 @@ static inline int rcu_preempt_depth(void) #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ +#ifdef CONFIG_RCU_LAZY +void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func); +#else +static inline void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func) +{ + call_rcu(head, func); +} +#endif + /* Internal to kernel */ void rcu_init(void); -extern int rcu_scheduler_active __read_mostly; +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_RCU_STALL_COMMON void rcu_sysrq_start(void); @@ -94,44 +129,30 @@ static inline void rcu_sysrq_start(void) { } static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ -#ifdef CONFIG_NO_HZ_FULL -void rcu_user_enter(void); -void rcu_user_exit(void); +#if defined(CONFIG_NO_HZ_FULL) && (!defined(CONFIG_GENERIC_ENTRY) || !defined(CONFIG_KVM_XFER_TO_GUEST_WORK)) +void rcu_irq_work_resched(void); #else -static inline void rcu_user_enter(void) { } -static inline void rcu_user_exit(void) { } -#endif /* CONFIG_NO_HZ_FULL */ +static __always_inline void rcu_irq_work_resched(void) { } +#endif #ifdef CONFIG_RCU_NOCB_CPU 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) { } -#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ +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) { } -/** - * 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 rcu_idle_enter() and the rcu_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 { \ - rcu_irq_enter_irqson(); \ - do { a; } while (0); \ - rcu_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. @@ -147,21 +168,34 @@ static inline void rcu_init_nohz(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 # define synchronize_rcu_tasks synchronize_rcu # endif -# ifdef CONFIG_TASKS_RCU_TRACE -# define rcu_tasks_trace_qs(t) \ - do { \ - if (!likely(READ_ONCE((t)->trc_reader_checked)) && \ - !unlikely(READ_ONCE((t)->trc_reader_nesting))) { \ - smp_store_release(&(t)->trc_reader_checked, true); \ - smp_mb(); /* Readers partitioned by store. */ \ - } \ +# ifdef CONFIG_TASKS_TRACE_RCU +// Bits for ->trc_reader_special.b.need_qs field. +#define TRC_NEED_QS 0x1 // Task needs a quiescent state. +#define TRC_NEED_QS_CHECKED 0x2 // Task has been checked for needing quiescent state. + +u8 rcu_trc_cmpxchg_need_qs(struct task_struct *t, u8 old, u8 new); +void rcu_tasks_trace_qs_blkd(struct task_struct *t); + +# define rcu_tasks_trace_qs(t) \ + do { \ + int ___rttq_nesting = READ_ONCE((t)->trc_reader_nesting); \ + \ + if (unlikely(READ_ONCE((t)->trc_reader_special.b.need_qs) == TRC_NEED_QS) && \ + likely(!___rttq_nesting)) { \ + 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 @@ -169,18 +203,19 @@ void synchronize_rcu_tasks(void); #define rcu_tasks_qs(t, preempt) \ do { \ rcu_tasks_classic_qs((t), (preempt)); \ - rcu_tasks_trace_qs((t)); \ + rcu_tasks_trace_qs(t); \ } 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) void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ +#define rcu_tasks_classic_qs(t, preempt) do { } while (0) #define rcu_tasks_qs(t, preempt) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu @@ -190,6 +225,18 @@ static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ /** + * rcu_trace_implies_rcu_gp - does an RCU Tasks Trace grace period imply an RCU grace period? + * + * As an accident of implementation, an RCU Tasks Trace grace period also + * acts as an RCU grace period. However, this could change at any time. + * Code relying on this accident must call this function to verify that + * this accident is still happening. + * + * You have been warned! + */ +static inline bool rcu_trace_implies_rcu_gp(void) { return true; } + +/** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to @@ -202,6 +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. @@ -241,6 +319,11 @@ bool rcu_lockdep_current_cpu_online(void); static inline bool rcu_lockdep_current_cpu_online(void) { return true; } #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ +extern struct lockdep_map rcu_lock_map; +extern struct lockdep_map rcu_bh_lock_map; +extern struct lockdep_map rcu_sched_lock_map; +extern struct lockdep_map rcu_callback_map; + #ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void rcu_lock_acquire(struct lockdep_map *map) @@ -248,15 +331,16 @@ 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_); } -extern struct lockdep_map rcu_lock_map; -extern struct lockdep_map rcu_bh_lock_map; -extern struct lockdep_map rcu_sched_lock_map; -extern struct lockdep_map rcu_callback_map; int debug_lockdep_rcu_enabled(void); int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); @@ -266,6 +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) @@ -288,6 +373,11 @@ static inline int rcu_read_lock_any_held(void) return !preemptible(); } +static inline int debug_lockdep_rcu_enabled(void) +{ + return 0; +} + #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU @@ -296,40 +386,108 @@ static inline int rcu_read_lock_any_held(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 (debug_lockdep_rcu_enabled() && !__warned && (c)) { \ + 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 { \ rcu_preempt_sleep_check(); \ - RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) \ + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh read-side critical section"); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \ "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) +#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 */ /* @@ -347,32 +505,48 @@ static inline void rcu_preempt_sleep_check(void) { } #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ -#define __rcu_access_pointer(p, space) \ +#define __unrcu_pointer(p, local) \ +({ \ + typeof(*p) *local = (typeof(*p) *__force)(p); \ + rcu_check_sparse(p, __rcu); \ + ((typeof(*p) __force __kernel *)(local)); \ +}) +/** + * unrcu_pointer - mark a pointer as not being RCU protected + * @p: pointer needing to lose its __rcu property + * + * Converts @p from an __rcu pointer to a __kernel pointer. + * This allows an __rcu pointer to be used with xchg() and friends. + */ +#define unrcu_pointer(p) __unrcu_pointer(p, __UNIQUE_ID(rcu)) + +#define __rcu_access_pointer(p, local, space) \ ({ \ - typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ + typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ rcu_check_sparse(p, space); \ - ((typeof(*p) __force __kernel *)(_________p1)); \ + ((typeof(*p) __force __kernel *)(local)); \ }) -#define __rcu_dereference_check(p, c, space) \ +#define __rcu_dereference_check(p, local, c, space) \ ({ \ /* Dependency order vs. p above. */ \ - typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \ + typeof(*p) *local = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_check_sparse(p, space); \ - ((typeof(*p) __force __kernel *)(________p1)); \ + ((typeof(*p) __force __kernel *)(local)); \ }) -#define __rcu_dereference_protected(p, c, space) \ +#define __rcu_dereference_protected(p, local, c, space) \ ({ \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) -#define rcu_dereference_raw(p) \ +#define __rcu_dereference_raw(p, local) \ ({ \ /* Dependency order vs. p above. */ \ - typeof(p) ________p1 = READ_ONCE(p); \ - ((typeof(*p) __force __kernel *)(________p1)); \ + typeof(p) local = READ_ONCE(p); \ + ((typeof(*p) __force __kernel *)(local)); \ }) +#define rcu_dereference_raw(p) __rcu_dereference_raw(p, __UNIQUE_ID(rcu)) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable @@ -451,15 +625,23 @@ do { \ * against NULL. Although rcu_access_pointer() may also be used in cases * where update-side locks prevent the value of the pointer from changing, * you should instead use rcu_dereference_protected() for this use case. + * Within an RCU read-side critical section, there is little reason to + * use rcu_access_pointer(). + * + * It is usually best to test the rcu_access_pointer() return value + * directly in order to avoid accidental dereferences being introduced + * by later inattentive changes. In other words, assigning the + * rcu_access_pointer() return value to a local variable results in an + * accident waiting to happen. * * It is also permissible to use rcu_access_pointer() when read-side - * access to the pointer was removed at least one grace period ago, as - * is the case in the context of the RCU callback that is freeing up - * the data, or after a synchronize_rcu() returns. This can be useful - * when tearing down multi-linked structures after a grace period - * has elapsed. + * access to the pointer was removed at least one grace period ago, as is + * the case in the context of the RCU callback that is freeing up the data, + * or after a synchronize_rcu() returns. This can be useful when tearing + * down multi-linked structures after a grace period has elapsed. However, + * rcu_dereference_protected() is normally preferred for this use case. */ -#define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu) +#define rcu_access_pointer(p) __rcu_access_pointer((p), __UNIQUE_ID(rcu), __rcu) /** * rcu_dereference_check() - rcu_dereference with debug checking @@ -495,17 +677,24 @@ do { \ * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ - __rcu_dereference_check((p), (c) || rcu_read_lock_held(), __rcu) + __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ + (c) || rcu_read_lock_held(), __rcu) /** * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * - * This is the RCU-bh counterpart to rcu_dereference_check(). + * This is the RCU-bh counterpart to rcu_dereference_check(). However, + * please note that starting in v5.0 kernels, vanilla RCU grace periods + * wait for local_bh_disable() regions of code in addition to regions of + * code demarked by rcu_read_lock() and rcu_read_unlock(). This means + * that synchronize_rcu(), call_rcu, and friends all take not only + * rcu_read_lock() but also rcu_read_lock_bh() into account. */ #define rcu_dereference_bh_check(p, c) \ - __rcu_dereference_check((p), (c) || rcu_read_lock_bh_held(), __rcu) + __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ + (c) || rcu_read_lock_bh_held(), __rcu) /** * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking @@ -513,9 +702,15 @@ do { \ * @c: The conditions under which the dereference will take place * * This is the RCU-sched counterpart to rcu_dereference_check(). + * However, please note that starting in v5.0 kernels, vanilla RCU grace + * periods wait for preempt_disable() regions of code in addition to + * regions of code demarked by rcu_read_lock() and rcu_read_unlock(). + * This means that synchronize_rcu(), call_rcu, and friends all take not + * only rcu_read_lock() but also rcu_read_lock_sched() into account. */ #define rcu_dereference_sched_check(p, c) \ - __rcu_dereference_check((p), (c) || rcu_read_lock_sched_held(), \ + __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ + (c) || rcu_read_lock_sched_held(), \ __rcu) /* @@ -525,7 +720,8 @@ do { \ * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ -#define rcu_dereference_raw_check(p) __rcu_dereference_check((p), 1, __rcu) +#define rcu_dereference_raw_check(p) \ + __rcu_dereference_check((p), __UNIQUE_ID(rcu), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented @@ -544,7 +740,7 @@ do { \ * but very ugly failures. */ #define rcu_dereference_protected(p, c) \ - __rcu_dereference_protected((p), (c), __rcu) + __rcu_dereference_protected((p), __UNIQUE_ID(rcu), (c), __rcu) /** @@ -604,6 +800,10 @@ do { \ * sections, invocation of the corresponding RCU callback is deferred * until after the all the other CPUs exit their critical sections. * + * 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 * is via the following sequence of events: (1) CPU 0 enters an RCU @@ -656,33 +856,11 @@ static __always_inline void rcu_read_lock(void) /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * - * In most situations, rcu_read_unlock() is immune from deadlock. - * However, in kernels built with CONFIG_RCU_BOOST, rcu_read_unlock() - * is responsible for deboosting, which it does via rt_mutex_unlock(). - * Unfortunately, this function acquires the scheduler's runqueue and - * priority-inheritance spinlocks. This means that deadlock could result - * if the caller of rcu_read_unlock() already holds one of these locks or - * any lock that is ever acquired while holding them. - * - * That said, RCU readers are never priority boosted unless they were - * preempted. Therefore, one way to avoid deadlock is to make sure - * that preemption never happens within any RCU read-side critical - * section whose outermost rcu_read_unlock() is called with one of - * rt_mutex_unlock()'s locks held. Such preemption can be avoided in - * a number of ways, for example, by invoking preempt_disable() before - * critical section's outermost rcu_read_lock(). - * - * Given that the set of locks acquired by rt_mutex_unlock() might change - * at any time, a somewhat more future-proofed approach is to make sure - * that that preemption never happens within any RCU read-side critical - * section whose outermost rcu_read_unlock() is called with irqs disabled. - * This approach relies on the fact that rt_mutex_unlock() currently only - * acquires irq-disabled locks. - * - * The second of these two approaches is best in most situations, - * however, the first approach can also be useful, at least to those - * developers willing to keep abreast of the set of locks acquired by - * rt_mutex_unlock(). + * In almost all situations, rcu_read_unlock() is immune from deadlock. + * 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. */ @@ -690,17 +868,19 @@ 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. */ } /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * - * This is equivalent of rcu_read_lock(), but also disables softirqs. - * Note that anything else that disables softirqs can also serve as - * an RCU read-side critical section. + * This is equivalent to rcu_read_lock(), but also disables softirqs. + * Note that anything else that disables softirqs can also serve as an RCU + * read-side critical section. However, please note that this equivalence + * applies only to v5.0 and later. Before v5.0, rcu_read_lock() and + * rcu_read_lock_bh() were unrelated. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke @@ -733,9 +913,12 @@ static inline void rcu_read_unlock_bh(void) /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * - * This is equivalent of rcu_read_lock(), but disables preemption. - * Read-side critical sections can also be introduced by anything else - * that disables preemption, including local_irq_disable() and friends. + * This is equivalent to rcu_read_lock(), but also disables preemption. + * Read-side critical sections can also be introduced by anything else that + * disables preemption, including local_irq_disable() and friends. However, + * please note that the equivalence to rcu_read_lock() applies only to + * v5.0 and later. Before v5.0, rcu_read_lock() and rcu_read_lock_sched() + * were unrelated. * * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() * must occur in the same context, for example, it is illegal to invoke @@ -833,92 +1016,82 @@ 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) - -/* - * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain. - */ -#define __kvfree_rcu(head, offset) \ - do { \ - BUILD_BUG_ON(!__is_kvfree_rcu_offset(offset)); \ - kvfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \ - } while (0) - /** * kfree_rcu() - kfree an object after a grace period. - * @ptr: pointer to kfree - * @rhf: the name of the struct rcu_head within the type of @ptr. + * @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(). If this error is triggered, you can + * 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) \ -do { \ - typeof (ptr) ___p = (ptr); \ - \ - if (___p) \ - __kvfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ -} while (0) +#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 a pointer to kvfree(). + * where @ptr is the pointer to be freed by kvfree(). * * Please note, head-less way of freeing is permitted to * use from a context that has to follow might_sleep() * 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); + +/* + * 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(offsetof(typeof(*(ptr)), rhf) >= 4096); \ + kvfree_call_rcu(&((___p)->rhf), (void *) (___p)); \ + } \ +} while (0) -#define KVFREE_GET_MACRO(_1, _2, NAME, ...) NAME -#define kvfree_rcu_arg_2(ptr, rhf) kfree_rcu(ptr, rhf) #define kvfree_rcu_arg_1(ptr) \ do { \ typeof(ptr) ___p = (ptr); \ \ if (___p) \ - kvfree_call_rcu(NULL, (rcu_callback_t) (___p)); \ + kvfree_call_rcu(NULL, (void *) (___p)); \ } while (0) /* @@ -979,4 +1152,18 @@ 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 */ |