/* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion * * Copyright IBM Corporation, 2001 * * Author: Dipankar Sarma <[email protected]> * * Based on the original work by Paul McKenney <[email protected]> * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * Papers: * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) * * For detailed explanation of Read-Copy Update mechanism see - * http://lse.sourceforge.net/locking/rcupdate.html * */ #ifndef __LINUX_RCUPDATE_H #define __LINUX_RCUPDATE_H #include <linux/types.h> #include <linux/compiler.h> #include <linux/atomic.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/processor.h> #include <linux/context_tracking_irq.h> #define ULONG_CMP_GE(a, b) … #define ULONG_CMP_LT(a, b) … #define RCU_SEQ_CTR_SHIFT … #define RCU_SEQ_STATE_MASK … /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(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 … /** * 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) { … } #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); void __rcu_read_unlock(void); /* * Defined as a macro as it is a very low level header included from * areas that don't even know about current. This gives the rcu_read_lock() * 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() … #else /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TINY_RCU #define rcu_read_unlock_strict … #else void rcu_read_unlock_strict(void); #endif static inline void __rcu_read_lock(void) { preempt_disable(); } static inline void __rcu_read_unlock(void) { preempt_enable(); if (IS_ENABLED(CONFIG_RCU_STRICT_GRACE_PERIOD)) rcu_read_unlock_strict(); } static inline int rcu_preempt_depth(void) { return 0; } #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; void rcu_sched_clock_irq(int user); #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); void rcu_sysrq_end(void); #else /* #ifdef CONFIG_RCU_STALL_COMMON */ 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)) void rcu_irq_work_resched(void); #else static 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) … #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) { } #define RCU_NOCB_LOCKDEP_WARN … #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /* * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU_GENERIC # ifdef CONFIG_TASKS_RCU #define rcu_tasks_classic_qs(t, preempt) … 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 … #define call_rcu_tasks … #define synchronize_rcu_tasks … # endif # ifdef CONFIG_TASKS_TRACE_RCU // Bits for ->trc_reader_special.b.need_qs field. #define TRC_NEED_QS … #define TRC_NEED_QS_CHECKED … 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) … void rcu_tasks_trace_torture_stats_print(char *tt, char *tf); # else #define rcu_tasks_trace_qs … # endif #define rcu_tasks_qs(t, preempt) … # ifdef CONFIG_TASKS_RUDE_RCU 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) … void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ #define rcu_tasks_classic_qs … #define rcu_tasks_qs … #define rcu_note_voluntary_context_switch … #define call_rcu_tasks … #define synchronize_rcu_tasks … static inline void exit_tasks_rcu_start(void) { } 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) { … } /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to * report potential quiescent states to RCU-tasks even if the cond_resched() * machinery were to be shut off, as some advocate for PREEMPTION kernels. */ #define cond_resched_tasks_rcu_qs() … /** * 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) … /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ #if defined(CONFIG_TREE_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) #include <linux/rcutiny.h> #else #error "Unknown RCU implementation specified to kernel configuration" #endif /* * The init_rcu_head_on_stack() and destroy_rcu_head_on_stack() calls * are needed for dynamic initialization and destruction of rcu_head * on the stack, and init_rcu_head()/destroy_rcu_head() are needed for * dynamic initialization and destruction of statically allocated rcu_head * structures. However, rcu_head structures allocated dynamically in the * heap don't need any initialization. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head); void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ static inline void init_rcu_head(struct rcu_head *head) { } static inline void destroy_rcu_head(struct rcu_head *head) { } static inline void init_rcu_head_on_stack(struct rcu_head *head) { } static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #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) */ 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) { … } static inline void rcu_try_lock_acquire(struct lockdep_map *map) { … } static inline void rcu_lock_release(struct lockdep_map *map) { … } int debug_lockdep_rcu_enabled(void); int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); int rcu_read_lock_sched_held(void); int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #define rcu_lock_acquire … #define rcu_try_lock_acquire … #define rcu_lock_release … static inline int rcu_read_lock_held(void) { return 1; } static inline int rcu_read_lock_bh_held(void) { return 1; } static inline int rcu_read_lock_sched_held(void) { return !preemptible(); } 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 /** * 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) … #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 // #ifndef CONFIG_PREEMPT_RCU static inline void rcu_preempt_sleep_check(void) { … } #endif // #else // #ifndef CONFIG_PREEMPT_RCU #define rcu_sleep_check() … // 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) { … } /** * 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() … /** * 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() … /** * 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() … /** * 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() … #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN … #define rcu_sleep_check … #define lockdep_assert_in_rcu_read_lock … #define lockdep_assert_in_rcu_read_lock_bh … #define lockdep_assert_in_rcu_read_lock_sched … #define lockdep_assert_in_rcu_reader … #endif /* #else #ifdef CONFIG_PROVE_RCU */ /* * Helper functions for rcu_dereference_check(), rcu_dereference_protected() * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of * multiple pointers markings to match different RCU implementations * (e.g., __srcu), should this make sense in the future. */ #ifdef __CHECKER__ #define rcu_check_sparse … #else /* #ifdef __CHECKER__ */ #define rcu_check_sparse(p, space) … #endif /* #else #ifdef __CHECKER__ */ #define __unrcu_pointer(p, 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) … #define __rcu_access_pointer(p, local, space) … #define __rcu_dereference_check(p, local, c, space) … #define __rcu_dereference_protected(p, local, c, space) … #define __rcu_dereference_raw(p, local) … #define rcu_dereference_raw(p) … /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable * @v: The value to statically initialize with. */ #define RCU_INITIALIZER(v) … /** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) * * Assigns the specified value to the specified RCU-protected * pointer, ensuring that any concurrent RCU readers will see * any prior initialization. * * Inserts memory barriers on architectures that require them * (which is most of them), and also prevents the compiler from * reordering the code that initializes the structure after the pointer * assignment. More importantly, this call documents which pointers * will be dereferenced by RCU read-side code. * * In some special cases, you may use RCU_INIT_POINTER() instead * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due * to the fact that it does not constrain either the CPU or the compiler. * That said, using RCU_INIT_POINTER() when you should have used * rcu_assign_pointer() is a very bad thing that results in * impossible-to-diagnose memory corruption. So please be careful. * See the RCU_INIT_POINTER() comment header for details. * * Note that rcu_assign_pointer() evaluates each of its arguments only * once, appearances notwithstanding. One of the "extra" evaluations * is in typeof() and the other visible only to sparse (__CHECKER__), * neither of which actually execute the argument. As with most cpp * macros, this execute-arguments-only-once property is important, so * please be careful when making changes to rcu_assign_pointer() and the * other macros that it invokes. */ #define rcu_assign_pointer(p, v) … /** * rcu_replace_pointer() - replace an RCU pointer, returning its old value * @rcu_ptr: RCU pointer, whose old value is returned * @ptr: regular pointer * @c: the lockdep conditions under which the dereference will take place * * Perform a replacement, where @rcu_ptr is an RCU-annotated * pointer and @c is the lockdep argument that is passed to the * rcu_dereference_protected() call used to read that pointer. The old * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr. */ #define rcu_replace_pointer(rcu_ptr, ptr, c) … /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing * @p: The pointer to read * * Return the value of the specified RCU-protected pointer, but omit the * lockdep checks for being in an RCU read-side critical section. This is * useful when the value of this pointer is accessed, but the pointer is * not dereferenced, for example, when testing an RCU-protected pointer * 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. However, * rcu_dereference_protected() is normally preferred for this use case. */ #define rcu_access_pointer(p) … /** * rcu_dereference_check() - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Do an rcu_dereference(), but check that the conditions under which the * dereference will take place are correct. Typically the conditions * indicate the various locking conditions that should be held at that * point. The check should return true if the conditions are satisfied. * An implicit check for being in an RCU read-side critical section * (rcu_read_lock()) is included. * * For example: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock)); * * could be used to indicate to lockdep that foo->bar may only be dereferenced * if either rcu_read_lock() is held, or that the lock required to replace * the bar struct at foo->bar is held. * * Note that the list of conditions may also include indications of when a lock * need not be held, for example during initialisation or destruction of the * target struct: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) || * atomic_read(&foo->usage) == 0); * * Inserts memory barriers on architectures that require them * (currently only the Alpha), prevents the compiler from refetching * (and from merging fetches), and, more importantly, documents exactly * which pointers are protected by RCU and checks that the pointer is * annotated as __rcu. */ #define rcu_dereference_check(p, c) … /** * 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(). 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_sched_check() - rcu_dereference_sched 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-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) … /* * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_check(p) … /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit * the READ_ONCE(). This is useful in cases where update-side locks * prevent the value of the pointer from changing. Please note that this * primitive does *not* prevent the compiler from repeating this reference * or combining it with other references, so it should not be used without * protection of appropriate locks. * * This function is only for update-side use. Using this function * when protected only by rcu_read_lock() will result in infrequent * but very ugly failures. */ #define rcu_dereference_protected(p, c) … /** * rcu_dereference() - fetch RCU-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * This is a simple wrapper around rcu_dereference_check(). */ #define rcu_dereference(p) … /** * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_bh(p) … /** * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_sched(p) … /** * rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism * @p: The pointer to hand off * * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to * kill_dependency(). It could be used as follows:: * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); * if (long_lived) { * if (!atomic_inc_not_zero(p->refcnt)) * long_lived = false; * else * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); */ #define rcu_pointer_handoff(p) … /** * rcu_read_lock() - mark the beginning of an RCU read-side critical section * * When synchronize_rcu() is invoked on one CPU while other CPUs * are within RCU read-side critical sections, then the * synchronize_rcu() is guaranteed to block until after all the other * CPUs exit their critical sections. Similarly, if call_rcu() is invoked * on one CPU while other CPUs are within RCU read-side critical * 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. * * 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 * read-side critical section, (2) CPU 1 invokes call_rcu() to register * an RCU callback, (3) CPU 0 exits the RCU read-side critical section, * (4) CPU 2 enters a RCU read-side critical section, (5) the RCU * callback is invoked. This is legal, because the RCU read-side critical * section that was running concurrently with the call_rcu() (and which * therefore might be referencing something that the corresponding RCU * callback would free up) has completed before the corresponding * RCU callback is invoked. * * RCU read-side critical sections may be nested. Any deferred actions * will be deferred until the outermost RCU read-side critical section * completes. * * You can avoid reading and understanding the next paragraph by * following this rule: don't put anything in an rcu_read_lock() RCU * read-side critical section that would block in a !PREEMPTION kernel. * But if you want the full story, read on! * * In non-preemptible RCU implementations (pure TREE_RCU and TINY_RCU), * it is illegal to block while in an RCU read-side critical section. * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPTION * kernel builds, RCU read-side critical sections may be preempted, * but explicit blocking is illegal. Finally, in preemptible RCU * implementations in real-time (with -rt patchset) kernel builds, RCU * read-side critical sections may be preempted and they may also block, but * only when acquiring spinlocks that are subject to priority inheritance. */ static __always_inline void rcu_read_lock(void) { … } /* * So where is rcu_write_lock()? It does not exist, as there is no * way for writers to lock out RCU readers. This is a feature, not * a bug -- this property is what provides RCU's performance benefits. * Of course, writers must coordinate with each other. The normal * spinlock primitives work well for this, but any other technique may be * used as well. RCU does not care how the writers keep out of each * others' way, as long as they do so. */ /** * 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. * * See rcu_read_lock() for more information. */ static inline void rcu_read_unlock(void) { … } /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh 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 * rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh() * was invoked from some other task. */ static inline void rcu_read_lock_bh(void) { … } /** * rcu_read_unlock_bh() - marks the end of a softirq-only RCU critical section * * See rcu_read_lock_bh() for more information. */ static inline void rcu_read_unlock_bh(void) { … } /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * * 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 * rcu_read_unlock_sched() from process context if the matching * rcu_read_lock_sched() was invoked from an NMI handler. */ static inline void rcu_read_lock_sched(void) { … } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_lock_sched_notrace(void) { … } /** * rcu_read_unlock_sched() - marks the end of a RCU-classic critical section * * See rcu_read_lock_sched() for more information. */ static inline void rcu_read_unlock_sched(void) { … } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_unlock_sched_notrace(void) { … } /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * Initialize an RCU-protected pointer in special cases where readers * do not need ordering constraints on the CPU or the compiler. These * special cases are: * * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer *or* * 2. The caller has taken whatever steps are required to prevent * RCU readers from concurrently accessing this pointer *or* * 3. The referenced data structure has already been exposed to * readers either at compile time or via rcu_assign_pointer() *and* * * a. You have not made *any* reader-visible changes to * this structure since then *or* * b. It is OK for readers accessing this structure from its * new location to see the old state of the structure. (For * example, the changes were to statistical counters or to * other state where exact synchronization is not required.) * * Failure to follow these rules governing use of RCU_INIT_POINTER() will * result in impossible-to-diagnose memory corruption. As in the structures * will look OK in crash dumps, but any concurrent RCU readers might * see pre-initialized values of the referenced data structure. So * please be very careful how you use RCU_INIT_POINTER()!!! * * If you are creating an RCU-protected linked structure that is accessed * by a single external-to-structure RCU-protected pointer, then you may * use RCU_INIT_POINTER() to initialize the internal RCU-protected * pointers, but you must use rcu_assign_pointer() to initialize the * external-to-structure pointer *after* you have completely initialized * the reader-accessible portions of the linked structure. * * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no * ordering guarantees for either the CPU or the compiler. */ #define RCU_INIT_POINTER(p, v) … /** * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * GCC-style initialization for an RCU-protected pointer in a structure field. */ #define RCU_POINTER_INITIALIZER(p, v) … /* * Does the specified offset indicate that the corresponding rcu_head * structure can be handled by kvfree_rcu()? */ #define __is_kvfree_rcu_offset(offset) … /** * kfree_rcu() - kfree an object after a grace period. * @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. * 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. * * 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) … #define kvfree_rcu(ptr, rhf) … /** * 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 * * kfree_rcu_mightsleep(ptr); * * 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 kfree_rcu_mightsleep(ptr) … #define kvfree_rcu_mightsleep(ptr) … #define kvfree_rcu_arg_2(ptr, rhf) … #define kvfree_rcu_arg_1(ptr) … /* * Place this after a lock-acquisition primitive to guarantee that * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies * if the UNLOCK and LOCK are executed by the same CPU or if the * UNLOCK and LOCK operate on the same lock variable. */ #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE #define smp_mb__after_unlock_lock … #else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ #define smp_mb__after_unlock_lock() … #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ /* Has the specified rcu_head structure been handed to call_rcu()? */ /** * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() * @rhp: The rcu_head structure to initialize. * * If you intend to invoke rcu_head_after_call_rcu() to test whether a * given rcu_head structure has already been passed to call_rcu(), then * you must also invoke this rcu_head_init() function on it just after * allocating that structure. Calls to this function must not race with * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation. */ static inline void rcu_head_init(struct rcu_head *rhp) { … } /** * rcu_head_after_call_rcu() - Has this rcu_head been passed to call_rcu()? * @rhp: The rcu_head structure to test. * @f: The function passed to call_rcu() along with @rhp. * * Returns @true if the @rhp has been passed to call_rcu() with @func, * and @false otherwise. Emits a warning in any other case, including * the case where @rhp has already been invoked after a grace period. * Calls to this function must not race with callback invocation. One way * to avoid such races is to enclose the call to rcu_head_after_call_rcu() * in an RCU read-side critical section that includes a read-side fetch * of the pointer to the structure containing @rhp. */ static inline bool rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) { … } /* kernel/ksysfs.c definitions */ extern int rcu_expedited; extern int rcu_normal; DEFINE_LOCK_GUARD_0(rcu, do { … } #endif /* __LINUX_RCUPDATE_H */
Codebase Browser
linux