880 lines · 27.9 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0+/* * Read-Copy Update mechanism for mutual exclusion * * Copyright IBM Corporation, 2001 * * Authors: Dipankar Sarma <dipankar@in.ibm.com> *	    Manfred Spraul <manfred@colorfullife.com> * * Based on the original work by Paul McKenney <paulmck@linux.ibm.com> * 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/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> #define CREATE_TRACE_POINTS #include "rcu.h" #ifdef MODULE_PARAM_PREFIX#undef MODULE_PARAM_PREFIX#endif#define MODULE_PARAM_PREFIX "rcupdate." #ifndef CONFIG_TINY_RCUextern int rcu_expedited; /* from sysctl */module_param(rcu_expedited, int, 0);extern int rcu_normal; /* from sysctl */module_param(rcu_normal, int, 0);static int rcu_normal_after_boot;module_param(rcu_normal_after_boot, int, 0);#endif /* #ifndef CONFIG_TINY_RCU */ #ifdef CONFIG_DEBUG_LOCK_ALLOC/** * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section? * * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns 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 rcu_idle_enter() and * rcu_idle_exit()) then rcu_read_lock_held() returns 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 SRCU read lock held if the current * CPU is offline. */int rcu_read_lock_sched_held(void){	int lockdep_opinion = 0; 	if (!debug_lockdep_rcu_enabled())		return 1;	if (!rcu_is_watching())		return 0;	if (!rcu_lockdep_current_cpu_online())		return 0;	if (debug_locks)		lockdep_opinion = lock_is_held(&rcu_sched_lock_map);	return lockdep_opinion || !preemptible();}EXPORT_SYMBOL(rcu_read_lock_sched_held);#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){	return READ_ONCE(rcu_normal) &&	       rcu_scheduler_active != RCU_SCHEDULER_INIT;}EXPORT_SYMBOL_GPL(rcu_gp_is_normal); static atomic_t rcu_expedited_nesting = ATOMIC_INIT(1); /* * 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){	return rcu_expedited || atomic_read(&rcu_expedited_nesting) ||	       rcu_scheduler_active == RCU_SCHEDULER_INIT;}EXPORT_SYMBOL_GPL(rcu_gp_is_expedited); /** * 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){	atomic_inc(&rcu_expedited_nesting);}EXPORT_SYMBOL_GPL(rcu_expedite_gp); /** * 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){	atomic_dec(&rcu_expedited_nesting);}EXPORT_SYMBOL_GPL(rcu_unexpedite_gp); /* * Inform RCU of the end of the in-kernel boot sequence. */void rcu_end_inkernel_boot(void){	rcu_unexpedite_gp();	if (rcu_normal_after_boot)		WRITE_ONCE(rcu_normal, 1);} #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 (!IS_ENABLED(CONFIG_PROVE_RCU))		return;	synchronize_rcu();	synchronize_rcu_expedited();} #if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU) /* * Switch to run-time mode once RCU has fully initialized. */static int __init rcu_set_runtime_mode(void){	rcu_test_sync_prims();	rcu_scheduler_active = RCU_SCHEDULER_RUNNING;	rcu_test_sync_prims();	return 0;}core_initcall(rcu_set_runtime_mode); #endif /* #if !defined(CONFIG_TINY_RCU) || defined(CONFIG_SRCU) */ #ifdef CONFIG_DEBUG_LOCK_ALLOCstatic struct lock_class_key rcu_lock_key;struct lockdep_map rcu_lock_map =	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock", &rcu_lock_key);EXPORT_SYMBOL_GPL(rcu_lock_map); static struct lock_class_key rcu_bh_lock_key;struct lockdep_map rcu_bh_lock_map =	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_bh", &rcu_bh_lock_key);EXPORT_SYMBOL_GPL(rcu_bh_lock_map); static struct lock_class_key rcu_sched_lock_key;struct lockdep_map rcu_sched_lock_map =	STATIC_LOCKDEP_MAP_INIT("rcu_read_lock_sched", &rcu_sched_lock_key);EXPORT_SYMBOL_GPL(rcu_sched_lock_map); static struct lock_class_key rcu_callback_key;struct lockdep_map rcu_callback_map =	STATIC_LOCKDEP_MAP_INIT("rcu_callback", &rcu_callback_key);EXPORT_SYMBOL_GPL(rcu_callback_map); int notrace debug_lockdep_rcu_enabled(void){	return rcu_scheduler_active != RCU_SCHEDULER_INACTIVE && debug_locks &&	       current->lockdep_recursion == 0;}EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);NOKPROBE_SYMBOL(debug_lockdep_rcu_enabled); /** * 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){	if (!debug_lockdep_rcu_enabled())		return 1;	if (!rcu_is_watching())		return 0;	if (!rcu_lockdep_current_cpu_online())		return 0;	return lock_is_held(&rcu_lock_map);}EXPORT_SYMBOL_GPL(rcu_read_lock_held); /** * 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){	if (!debug_lockdep_rcu_enabled())		return 1;	if (!rcu_is_watching())		return 0;	if (!rcu_lockdep_current_cpu_online())		return 0;	return in_softirq() || irqs_disabled();}EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); #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){	struct rcu_synchronize *rcu; 	rcu = container_of(head, struct rcu_synchronize, head);	complete(&rcu->completion);}EXPORT_SYMBOL_GPL(wakeme_after_rcu); void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,		   struct rcu_synchronize *rs_array){	int i;	int j; 	/* Initialize and register callbacks for each crcu_array element. */	for (i = 0; i < n; i++) {		if (checktiny &&		    (crcu_array[i] == call_rcu)) {			might_sleep();			continue;		}		init_rcu_head_on_stack(&rs_array[i].head);		init_completion(&rs_array[i].completion);		for (j = 0; j < i; j++)			if (crcu_array[j] == crcu_array[i])				break;		if (j == i)			(crcu_array[i])(&rs_array[i].head, wakeme_after_rcu);	} 	/* Wait for all callbacks to be invoked. */	for (i = 0; i < n; i++) {		if (checktiny &&		    (crcu_array[i] == call_rcu))			continue;		for (j = 0; j < i; j++)			if (crcu_array[j] == crcu_array[i])				break;		if (j == i)			wait_for_completion(&rs_array[i].completion);		destroy_rcu_head_on_stack(&rs_array[i].head);	}}EXPORT_SYMBOL_GPL(__wait_rcu_gp); #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEADvoid init_rcu_head(struct rcu_head *head){	debug_object_init(head, &rcuhead_debug_descr);}EXPORT_SYMBOL_GPL(init_rcu_head); void destroy_rcu_head(struct rcu_head *head){	debug_object_free(head, &rcuhead_debug_descr);}EXPORT_SYMBOL_GPL(destroy_rcu_head); static bool rcuhead_is_static_object(void *addr){	return true;} /** * 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){	debug_object_init_on_stack(head, &rcuhead_debug_descr);}EXPORT_SYMBOL_GPL(init_rcu_head_on_stack); /** * 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){	debug_object_free(head, &rcuhead_debug_descr);}EXPORT_SYMBOL_GPL(destroy_rcu_head_on_stack); struct debug_obj_descr rcuhead_debug_descr = {	.name = "rcu_head",	.is_static_object = rcuhead_is_static_object,};EXPORT_SYMBOL_GPL(rcuhead_debug_descr);#endif /* #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_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){	trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c);}EXPORT_SYMBOL_GPL(do_trace_rcu_torture_read);#else#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \	do { } while (0)#endif #ifdef CONFIG_RCU_STALL_COMMONint rcu_cpu_stall_suppress __read_mostly; /* 1 = suppress stall warnings. */EXPORT_SYMBOL_GPL(rcu_cpu_stall_suppress);module_param(rcu_cpu_stall_suppress, int, 0644);int rcu_cpu_stall_timeout __read_mostly = CONFIG_RCU_CPU_STALL_TIMEOUT;module_param(rcu_cpu_stall_timeout, int, 0644);#endif /* #ifdef CONFIG_RCU_STALL_COMMON */ #ifdef CONFIG_TASKS_RCU /* * Simple variant of RCU whose quiescent states are voluntary context * switch, cond_resched_rcu_qs(), user-space execution, and idle. * As such, grace periods can take one good long time.  There are no * read-side primitives similar to rcu_read_lock() and rcu_read_unlock() * because this implementation is intended to get the system into a safe * state for some of the manipulations involved in tracing and the like. * Finally, this implementation does not support high call_rcu_tasks() * rates from multiple CPUs.  If this is required, per-CPU callback lists * will be needed. */ /* Global list of callbacks and associated lock. */static struct rcu_head *rcu_tasks_cbs_head;static struct rcu_head **rcu_tasks_cbs_tail = &rcu_tasks_cbs_head;static DECLARE_WAIT_QUEUE_HEAD(rcu_tasks_cbs_wq);static DEFINE_RAW_SPINLOCK(rcu_tasks_cbs_lock); /* Track exiting tasks in order to allow them to be waited for. */DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu); /* Control stall timeouts.  Disable with <= 0, otherwise jiffies till stall. */#define RCU_TASK_STALL_TIMEOUT (HZ * 60 * 10)static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;module_param(rcu_task_stall_timeout, int, 0644); static struct task_struct *rcu_tasks_kthread_ptr; /** * call_rcu_tasks() - Queue an RCU for invocation task-based grace period * @rhp: structure to be used for queueing the RCU updates. * @func: actual callback function to be invoked after the grace period * * The callback function will be invoked some time after a full grace * period elapses, in other words after all currently executing RCU * read-side critical sections have completed. call_rcu_tasks() assumes * that the read-side critical sections end at a voluntary context * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle, * or transition to usermode execution.  As such, there are no read-side * primitives analogous to rcu_read_lock() and rcu_read_unlock() because * this primitive is intended to determine that all tasks have passed * through a safe state, not so much for data-strcuture synchronization. * * See the description of call_rcu() for more detailed information on * memory ordering guarantees. */void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func){	unsigned long flags;	bool needwake; 	rhp->next = NULL;	rhp->func = func;	raw_spin_lock_irqsave(&rcu_tasks_cbs_lock, flags);	needwake = !rcu_tasks_cbs_head;	*rcu_tasks_cbs_tail = rhp;	rcu_tasks_cbs_tail = &rhp->next;	raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);	/* We can't create the thread unless interrupts are enabled. */	if (needwake && READ_ONCE(rcu_tasks_kthread_ptr))		wake_up(&rcu_tasks_cbs_wq);}EXPORT_SYMBOL_GPL(call_rcu_tasks); /**

Lines 1–500 of 880.