// SPDX-License-Identifier: GPL-2.0+ /* * Read-Copy Update mechanism for mutual exclusion * * Copyright IBM Corporation, 2001 * * Authors: Dipankar Sarma <[email protected]> * Manfred Spraul <[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 * */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/smp.h> #include <linux/interrupt.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> #include <linux/torture.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/cpu.h> #include <linux/mutex.h> #include <linux/export.h> #include <linux/hardirq.h> #include <linux/delay.h> #include <linux/moduleparam.h> #include <linux/kthread.h> #include <linux/tick.h> #include <linux/rcupdate_wait.h> #include <linux/sched/isolation.h> #include <linux/kprobes.h> #include <linux/slab.h> #include <linux/irq_work.h> #include <linux/rcupdate_trace.h> #define CREATE_TRACE_POINTS #include "rcu.h" #ifdef MODULE_PARAM_PREFIX #undef MODULE_PARAM_PREFIX #endif #define MODULE_PARAM_PREFIX … #ifndef CONFIG_TINY_RCU module_param(rcu_expedited, int, 0444); module_param(rcu_normal, int, 0444); static int rcu_normal_after_boot = … IS_ENABLED(…); #if !defined(CONFIG_PREEMPT_RT) || defined(CONFIG_NO_HZ_FULL) module_param(rcu_normal_after_boot, int, 0444); #endif #endif /* #ifndef CONFIG_TINY_RCU */ #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * rcu_read_lock_held_common() - might we be in RCU-sched read-side critical section? * @ret: Best guess answer if lockdep cannot be relied on * * Returns true if lockdep must be ignored, in which case ``*ret`` contains * the best guess described below. Otherwise returns false, in which * case ``*ret`` tells the caller nothing and the caller should instead * consult lockdep. * * If CONFIG_DEBUG_LOCK_ALLOC is selected, set ``*ret`` to nonzero iff in an * RCU-sched read-side critical section. In absence of * CONFIG_DEBUG_LOCK_ALLOC, this assumes we are in an RCU-sched read-side * critical section unless it can prove otherwise. Note that disabling * of preemption (including disabling irqs) counts as an RCU-sched * read-side critical section. This is useful for debug checks in functions * that required that they be called within an RCU-sched read-side * critical section. * * Check debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. * * Note that if the CPU is in the idle loop from an RCU point of view (ie: * that we are in the section between ct_idle_enter() and ct_idle_exit()) * then rcu_read_lock_held() sets ``*ret`` to false even if the CPU did an * rcu_read_lock(). The reason for this is that RCU ignores CPUs that are * in such a section, considering these as in extended quiescent state, * so such a CPU is effectively never in an RCU read-side critical section * regardless of what RCU primitives it invokes. This state of affairs is * required --- we need to keep an RCU-free window in idle where the CPU may * possibly enter into low power mode. This way we can notice an extended * quiescent state to other CPUs that started a grace period. Otherwise * we would delay any grace period as long as we run in the idle task. * * Similarly, we avoid claiming an RCU read lock held if the current * CPU is offline. */ static bool rcu_read_lock_held_common(bool *ret) { … } int rcu_read_lock_sched_held(void) { … } EXPORT_SYMBOL(…); #endif #ifndef CONFIG_TINY_RCU /* * Should expedited grace-period primitives always fall back to their * non-expedited counterparts? Intended for use within RCU. Note * that if the user specifies both rcu_expedited and rcu_normal, then * rcu_normal wins. (Except during the time period during boot from * when the first task is spawned until the rcu_set_runtime_mode() * core_initcall() is invoked, at which point everything is expedited.) */ bool rcu_gp_is_normal(void) { … } EXPORT_SYMBOL_GPL(…); static atomic_t rcu_async_hurry_nesting = …; /* * Should call_rcu() callbacks be processed with urgency or are * they OK being executed with arbitrary delays? */ bool rcu_async_should_hurry(void) { … } EXPORT_SYMBOL_GPL(…); /** * rcu_async_hurry - Make future async RCU callbacks not lazy. * * After a call to this function, future calls to call_rcu() * will be processed in a timely fashion. */ void rcu_async_hurry(void) { … } EXPORT_SYMBOL_GPL(…); /** * rcu_async_relax - Make future async RCU callbacks lazy. * * After a call to this function, future calls to call_rcu() * will be processed in a lazy fashion. */ void rcu_async_relax(void) { … } EXPORT_SYMBOL_GPL(…); static atomic_t rcu_expedited_nesting = …; /* * Should normal grace-period primitives be expedited? Intended for * use within RCU. Note that this function takes the rcu_expedited * sysfs/boot variable and rcu_scheduler_active into account as well * as the rcu_expedite_gp() nesting. So looping on rcu_unexpedite_gp() * until rcu_gp_is_expedited() returns false is a -really- bad idea. */ bool rcu_gp_is_expedited(void) { … } EXPORT_SYMBOL_GPL(…); /** * rcu_expedite_gp - Expedite future RCU grace periods * * After a call to this function, future calls to synchronize_rcu() and * friends act as the corresponding synchronize_rcu_expedited() function * had instead been called. */ void rcu_expedite_gp(void) { … } EXPORT_SYMBOL_GPL(…); /** * rcu_unexpedite_gp - Cancel prior rcu_expedite_gp() invocation * * Undo a prior call to rcu_expedite_gp(). If all prior calls to * rcu_expedite_gp() are undone by a subsequent call to rcu_unexpedite_gp(), * and if the rcu_expedited sysfs/boot parameter is not set, then all * subsequent calls to synchronize_rcu() and friends will return to * their normal non-expedited behavior. */ void rcu_unexpedite_gp(void) { … } EXPORT_SYMBOL_GPL(…); static bool rcu_boot_ended __read_mostly; /* * Inform RCU of the end of the in-kernel boot sequence. */ void rcu_end_inkernel_boot(void) { … } /* * Let rcutorture know when it is OK to turn it up to eleven. */ bool rcu_inkernel_boot_has_ended(void) { … } EXPORT_SYMBOL_GPL(…); #endif /* #ifndef CONFIG_TINY_RCU */ /* * Test each non-SRCU synchronous grace-period wait API. This is * useful just after a change in mode for these primitives, and * during early boot. */ void rcu_test_sync_prims(void) { … } #if !defined(CONFIG_TINY_RCU) /* * Switch to run-time mode once RCU has fully initialized. */ static int __init rcu_set_runtime_mode(void) { … } core_initcall(rcu_set_runtime_mode); #endif /* #if !defined(CONFIG_TINY_RCU) */ #ifdef CONFIG_DEBUG_LOCK_ALLOC static struct lock_class_key rcu_lock_key; struct lockdep_map rcu_lock_map = …; EXPORT_SYMBOL_GPL(…); static struct lock_class_key rcu_bh_lock_key; struct lockdep_map rcu_bh_lock_map = …; EXPORT_SYMBOL_GPL(…); static struct lock_class_key rcu_sched_lock_key; struct lockdep_map rcu_sched_lock_map = …; EXPORT_SYMBOL_GPL(…); // Tell lockdep when RCU callbacks are being invoked. static struct lock_class_key rcu_callback_key; struct lockdep_map rcu_callback_map = …; EXPORT_SYMBOL_GPL(…); noinstr int notrace debug_lockdep_rcu_enabled(void) { … } EXPORT_SYMBOL_GPL(…); /** * rcu_read_lock_held() - might we be in RCU read-side critical section? * * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an RCU * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, * this assumes we are in an RCU read-side critical section unless it can * prove otherwise. This is useful for debug checks in functions that * require that they be called within an RCU read-side critical section. * * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. * * Note that rcu_read_lock() and the matching rcu_read_unlock() must * occur in the same context, for example, it is illegal to invoke * rcu_read_unlock() in process context if the matching rcu_read_lock() * was invoked from within an irq handler. * * Note that rcu_read_lock() is disallowed if the CPU is either idle or * offline from an RCU perspective, so check for those as well. */ int rcu_read_lock_held(void) { … } EXPORT_SYMBOL_GPL(…); /** * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section? * * Check for bottom half being disabled, which covers both the * CONFIG_PROVE_RCU and not cases. Note that if someone uses * rcu_read_lock_bh(), but then later enables BH, lockdep (if enabled) * will show the situation. This is useful for debug checks in functions * that require that they be called within an RCU read-side critical * section. * * Check debug_lockdep_rcu_enabled() to prevent false positives during boot. * * Note that rcu_read_lock_bh() is disallowed if the CPU is either idle or * offline from an RCU perspective, so check for those as well. */ int rcu_read_lock_bh_held(void) { … } EXPORT_SYMBOL_GPL(…); int rcu_read_lock_any_held(void) { … } EXPORT_SYMBOL_GPL(…); #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /** * wakeme_after_rcu() - Callback function to awaken a task after grace period * @head: Pointer to rcu_head member within rcu_synchronize structure * * Awaken the corresponding task now that a grace period has elapsed. */ void wakeme_after_rcu(struct rcu_head *head) { … } EXPORT_SYMBOL_GPL(…); void __wait_rcu_gp(bool checktiny, unsigned int state, int n, call_rcu_func_t *crcu_array, struct rcu_synchronize *rs_array) { … } EXPORT_SYMBOL_GPL(…); void finish_rcuwait(struct rcuwait *w) { … } EXPORT_SYMBOL_GPL(…); #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head) { … } EXPORT_SYMBOL_GPL(…); void destroy_rcu_head(struct rcu_head *head) { … } EXPORT_SYMBOL_GPL(…); static bool rcuhead_is_static_object(void *addr) { … } /** * init_rcu_head_on_stack() - initialize on-stack rcu_head for debugobjects * @head: pointer to rcu_head structure to be initialized * * This function informs debugobjects of a new rcu_head structure that * has been allocated as an auto variable on the stack. This function * is not required for rcu_head structures that are statically defined or * that are dynamically allocated on the heap. This function has no * effect for !CONFIG_DEBUG_OBJECTS_RCU_HEAD kernel builds. */ void init_rcu_head_on_stack(struct rcu_head *head) { … } EXPORT_SYMBOL_GPL(…); /** * destroy_rcu_head_on_stack() - destroy on-stack rcu_head for debugobjects * @head: pointer to rcu_head structure to be initialized * * This function informs debugobjects that an on-stack rcu_head structure * is about to go out of scope. As with init_rcu_head_on_stack(), this * function is not required for rcu_head structures that are statically * defined or that are dynamically allocated on the heap. Also as with * init_rcu_head_on_stack(), this function has no effect for * !CONFIG_DEBUG_OBJECTS_RCU_HEAD kernel builds. */ void destroy_rcu_head_on_stack(struct rcu_head *head) { … } EXPORT_SYMBOL_GPL(…); const struct debug_obj_descr rcuhead_debug_descr = …; EXPORT_SYMBOL_GPL(…); #endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_TREE_RCU) || defined(CONFIG_RCU_TRACE) void do_trace_rcu_torture_read(const char *rcutorturename, struct rcu_head *rhp, unsigned long secs, unsigned long c_old, unsigned long c) { … } EXPORT_SYMBOL_GPL(…); #else #define do_trace_rcu_torture_read … #endif #if IS_ENABLED(CONFIG_RCU_TORTURE_TEST) || IS_MODULE(CONFIG_RCU_TORTURE_TEST) || IS_ENABLED(CONFIG_LOCK_TORTURE_TEST) || IS_MODULE(CONFIG_LOCK_TORTURE_TEST) /* Get rcutorture access to sched_setaffinity(). */ long torture_sched_setaffinity(pid_t pid, const struct cpumask *in_mask) { … } EXPORT_SYMBOL_GPL(…); #endif int rcu_cpu_stall_notifiers __read_mostly; // !0 = provide stall notifiers (rarely useful) EXPORT_SYMBOL_GPL(…); #ifdef CONFIG_RCU_STALL_COMMON int rcu_cpu_stall_ftrace_dump __read_mostly; module_param(rcu_cpu_stall_ftrace_dump, int, 0644); #ifdef CONFIG_RCU_CPU_STALL_NOTIFIER module_param(rcu_cpu_stall_notifiers, int, 0444); #endif // #ifdef CONFIG_RCU_CPU_STALL_NOTIFIER int rcu_cpu_stall_suppress __read_mostly; // !0 = suppress stall warnings. EXPORT_SYMBOL_GPL(…); module_param(rcu_cpu_stall_suppress, int, 0644); int rcu_cpu_stall_timeout __read_mostly = …; module_param(rcu_cpu_stall_timeout, int, 0644); int rcu_exp_cpu_stall_timeout __read_mostly = …; module_param(rcu_exp_cpu_stall_timeout, int, 0644); int rcu_cpu_stall_cputime __read_mostly = … IS_ENABLED(…); module_param(rcu_cpu_stall_cputime, int, 0644); bool rcu_exp_stall_task_details __read_mostly; module_param(rcu_exp_stall_task_details, bool, 0644); #endif /* #ifdef CONFIG_RCU_STALL_COMMON */ // Suppress boot-time RCU CPU stall warnings and rcutorture writer stall // warnings. Also used by rcutorture even if stall warnings are excluded. int rcu_cpu_stall_suppress_at_boot __read_mostly; // !0 = suppress boot stalls. EXPORT_SYMBOL_GPL(…); module_param(rcu_cpu_stall_suppress_at_boot, int, 0444); /** * get_completed_synchronize_rcu - Return a pre-completed polled state cookie * * Returns a value that will always be treated by functions like * poll_state_synchronize_rcu() as a cookie whose grace period has already * completed. */ unsigned long get_completed_synchronize_rcu(void) { … } EXPORT_SYMBOL_GPL(…); #ifdef CONFIG_PROVE_RCU /* * Early boot self test parameters. */ static bool rcu_self_test; module_param(rcu_self_test, bool, 0444); static int rcu_self_test_counter; static void test_callback(struct rcu_head *r) { … } DEFINE_STATIC_SRCU(…); static unsigned long early_srcu_cookie; struct early_boot_kfree_rcu { … }; static void early_boot_test_call_rcu(void) { … } void rcu_early_boot_tests(void) { … } static int rcu_verify_early_boot_tests(void) { … } late_initcall(rcu_verify_early_boot_tests); #else void rcu_early_boot_tests(void) {} #endif /* CONFIG_PROVE_RCU */ #include "tasks.h" #ifndef CONFIG_TINY_RCU /* * Print any significant non-default boot-time settings. */ void __init rcupdate_announce_bootup_oddness(void) { … } #endif /* #ifndef CONFIG_TINY_RCU */