diff options
Diffstat (limited to 'include/linux/rcupdate.h')
| -rw-r--r-- | include/linux/rcupdate.h | 1319 |
1 files changed, 755 insertions, 564 deletions
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 4b14bdc911d7..c5b30054cd01 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -1,25 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * * Copyright IBM Corporation, 2001 * * Author: Dipankar Sarma <dipankar@in.ibm.com> * - * Based on the original work by Paul McKenney <paulmck@us.ibm.com> + * Based on the original work by Paul McKenney <paulmck@vnet.ibm.com> * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * Papers: * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf @@ -34,154 +21,56 @@ #define __LINUX_RCUPDATE_H #include <linux/types.h> -#include <linux/cache.h> -#include <linux/spinlock.h> -#include <linux/threads.h> -#include <linux/cpumask.h> -#include <linux/seqlock.h> -#include <linux/lockdep.h> -#include <linux/completion.h> -#include <linux/debugobjects.h> -#include <linux/bug.h> #include <linux/compiler.h> +#include <linux/atomic.h> +#include <linux/irqflags.h> +#include <linux/sched.h> +#include <linux/bottom_half.h> +#include <linux/lockdep.h> +#include <linux/cleanup.h> +#include <asm/processor.h> +#include <linux/context_tracking_irq.h> -#ifdef CONFIG_RCU_TORTURE_TEST -extern int rcutorture_runnable; /* for sysctl */ -#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ - -#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) -extern void rcutorture_record_test_transition(void); -extern void rcutorture_record_progress(unsigned long vernum); -extern void do_trace_rcu_torture_read(char *rcutorturename, - struct rcu_head *rhp, - unsigned long secs, - unsigned long c_old, - unsigned long c); -#else -static inline void rcutorture_record_test_transition(void) -{ -} -static inline void rcutorture_record_progress(unsigned long vernum) -{ -} -#ifdef CONFIG_RCU_TRACE -extern void do_trace_rcu_torture_read(char *rcutorturename, - struct rcu_head *rhp, - unsigned long secs, - unsigned long c_old, - unsigned long c); -#else -#define do_trace_rcu_torture_read(rcutorturename, rhp, secs, c_old, c) \ - do { } while (0) -#endif -#endif - -#define UINT_CMP_GE(a, b) (UINT_MAX / 2 >= (a) - (b)) -#define UINT_CMP_LT(a, b) (UINT_MAX / 2 < (a) - (b)) #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))) - -/* Exported common interfaces */ - -#ifdef CONFIG_PREEMPT_RCU -/** - * call_rcu() - Queue an RCU callback for invocation after a grace period. - * @head: 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 pre-existing RCU read-side - * critical sections have completed. However, the callback function - * might well execute concurrently with RCU read-side critical sections - * that started after call_rcu() was invoked. RCU read-side critical - * sections are delimited by rcu_read_lock() and rcu_read_unlock(), - * and may be nested. - * - * Note that all CPUs must agree that the grace period extended beyond - * all pre-existing RCU read-side critical section. On systems with more - * than one CPU, this means that when "func()" is invoked, each CPU is - * guaranteed to have executed a full memory barrier since the end of its - * last RCU read-side critical section whose beginning preceded the call - * to call_rcu(). It also means that each CPU executing an RCU read-side - * critical section that continues beyond the start of "func()" must have - * executed a memory barrier after the call_rcu() but before the beginning - * of that RCU read-side critical section. Note that these guarantees - * include CPUs that are offline, idle, or executing in user mode, as - * well as CPUs that are executing in the kernel. - * - * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the - * resulting RCU callback function "func()", then both CPU A and CPU B are - * guaranteed to execute a full memory barrier during the time interval - * between the call to call_rcu() and the invocation of "func()" -- even - * if CPU A and CPU B are the same CPU (but again only if the system has - * more than one CPU). - */ -extern void call_rcu(struct rcu_head *head, - void (*func)(struct rcu_head *head)); +#define RCU_SEQ_CTR_SHIFT 2 +#define RCU_SEQ_STATE_MASK ((1 << RCU_SEQ_CTR_SHIFT) - 1) -#else /* #ifdef CONFIG_PREEMPT_RCU */ +/* Exported common interfaces */ +void call_rcu(struct rcu_head *head, rcu_callback_t func); +void rcu_barrier_tasks(void); +void synchronize_rcu(void); -/* In classic RCU, call_rcu() is just call_rcu_sched(). */ -#define call_rcu call_rcu_sched +struct rcu_gp_oldstate; +unsigned long get_completed_synchronize_rcu(void); +void get_completed_synchronize_rcu_full(struct rcu_gp_oldstate *rgosp); -#endif /* #else #ifdef CONFIG_PREEMPT_RCU */ - -/** - * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. - * @head: 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_bh() assumes - * that the read-side critical sections end on completion of a softirq - * handler. This means that read-side critical sections in process - * context must not be interrupted by softirqs. This interface is to be - * used when most of the read-side critical sections are in softirq context. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock() and rcu_read_unlock(), if in interrupt context. - * OR - * - rcu_read_lock_bh() and rcu_read_unlock_bh(), if in process context. - * These may be nested. - * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. - */ -extern void call_rcu_bh(struct rcu_head *head, - void (*func)(struct rcu_head *head)); +// Maximum number of unsigned long values corresponding to +// not-yet-completed RCU grace periods. +#define NUM_ACTIVE_RCU_POLL_OLDSTATE 2 /** - * call_rcu_sched() - Queue an RCU for invocation after sched grace period. - * @head: 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_sched() assumes - * that the read-side critical sections end on enabling of preemption - * or on voluntary preemption. - * RCU read-side critical sections are delimited by : - * - rcu_read_lock_sched() and rcu_read_unlock_sched(), - * OR - * anything that disables preemption. - * These may be nested. - * - * See the description of call_rcu() for more detailed information on - * memory ordering guarantees. + * 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. */ -extern void call_rcu_sched(struct rcu_head *head, - void (*func)(struct rcu_head *rcu)); - -extern void synchronize_sched(void); +static inline bool same_state_synchronize_rcu(unsigned long oldstate1, unsigned long oldstate2) +{ + return oldstate1 == oldstate2; +} #ifdef CONFIG_PREEMPT_RCU -extern void __rcu_read_lock(void); -extern void __rcu_read_unlock(void); -extern void rcu_read_unlock_special(struct task_struct *t); -void synchronize_rcu(void); +void __rcu_read_lock(void); +void __rcu_read_unlock(void); /* * Defined as a macro as it is a very low level header included from @@ -189,10 +78,16 @@ void synchronize_rcu(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 */ +#ifdef CONFIG_TINY_RCU +#define rcu_read_unlock_strict() do { } while (0) +#else +void rcu_read_unlock_strict(void); +#endif + static inline void __rcu_read_lock(void) { preempt_disable(); @@ -200,14 +95,11 @@ 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(); } -static inline void synchronize_rcu(void) -{ - synchronize_sched(); -} - static inline int rcu_preempt_depth(void) { return 0; @@ -215,66 +107,185 @@ 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 */ -extern void rcu_init(void); -extern void rcu_sched_qs(int cpu); -extern void rcu_bh_qs(int cpu); -extern void rcu_check_callbacks(int cpu, int user); -struct notifier_block; -extern void rcu_idle_enter(void); -extern void rcu_idle_exit(void); -extern void rcu_irq_enter(void); -extern void rcu_irq_exit(void); - -#ifdef CONFIG_RCU_USER_QS -extern void rcu_user_enter(void); -extern void rcu_user_exit(void); -extern void rcu_user_enter_after_irq(void); -extern void rcu_user_exit_after_irq(void); +void rcu_init(void); +extern int rcu_scheduler_active; +void rcu_sched_clock_irq(int user); + +#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_VIRT_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) { } -static inline void rcu_user_enter_after_irq(void) { } -static inline void rcu_user_exit_after_irq(void) { } -static inline void rcu_user_hooks_switch(struct task_struct *prev, - struct task_struct *next) { } -#endif /* CONFIG_RCU_USER_QS */ - -/** - * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers - * @a: Code that RCU needs to pay attention to. - * - * RCU, RCU-bh, and RCU-sched 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 attending, invoke its argument - * (in this example, a call to 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 the nesting level is currently - * quite limited. If deeper nesting is required, it will be necessary - * to adjust DYNTICK_TASK_NESTING_VALUE accordingly. - */ -#define RCU_NONIDLE(a) \ - do { \ - rcu_irq_enter(); \ - do { a; } while (0); \ - rcu_irq_exit(); \ +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) { } +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(c, s) + +#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) \ + do { \ + if (!(preempt) && READ_ONCE((t)->rcu_tasks_holdout)) \ + WRITE_ONCE((t)->rcu_tasks_holdout, false); \ + } 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_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 + +#define rcu_tasks_qs(t, preempt) \ +do { \ + rcu_tasks_classic_qs((t), (preempt)); \ + rcu_tasks_trace_qs(t); \ +} while (0) + +# 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) 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 +#define synchronize_rcu_tasks synchronize_rcu +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) { return true; } + +/** + * 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() \ +do { \ + rcu_tasks_qs(current, false); \ + 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. */ -typedef void call_rcu_func_t(struct rcu_head *head, - void (*func)(struct rcu_head *head)); -void wait_rcu_gp(call_rcu_func_t crf); - -#if defined(CONFIG_TREE_RCU) || defined(CONFIG_TREE_PREEMPT_RCU) +#if defined(CONFIG_TREE_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) #include <linux/rcutiny.h> @@ -283,147 +294,63 @@ void wait_rcu_gp(call_rcu_func_t crf); #endif /* - * init_rcu_head_on_stack()/destroy_rcu_head_on_stack() are needed for dynamic - * initialization and destruction of rcu_head on the stack. rcu_head structures - * allocated dynamically in the heap or defined statically don't need any - * initialization. + * 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 -extern void init_rcu_head_on_stack(struct rcu_head *head); -extern void destroy_rcu_head_on_stack(struct rcu_head *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_on_stack(struct rcu_head *head) -{ -} - -static inline void destroy_rcu_head_on_stack(struct rcu_head *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_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP) -extern int rcu_is_cpu_idle(void); -#endif /* #if defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_SMP) */ - #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 1; -} +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) { - lock_acquire(map, 0, 0, 2, 1, NULL, _THIS_IP_); + lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } -static inline void rcu_lock_release(struct lockdep_map *map) +static inline void rcu_try_lock_acquire(struct lockdep_map *map) { - lock_release(map, 1, _THIS_IP_); + lock_acquire(map, 0, 1, 2, 0, NULL, _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 int debug_lockdep_rcu_enabled(void); - -/** - * 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. - */ -static inline int rcu_read_lock_held(void) +static inline void rcu_lock_release(struct lockdep_map *map) { - if (!debug_lockdep_rcu_enabled()) - return 1; - if (rcu_is_cpu_idle()) - return 0; - if (!rcu_lockdep_current_cpu_online()) - return 0; - return lock_is_held(&rcu_lock_map); + lock_release(map, _THIS_IP_); } -/* - * rcu_read_lock_bh_held() is defined out of line to avoid #include-file - * hell. - */ -extern int rcu_read_lock_bh_held(void); - -/** - * 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. - */ -#ifdef CONFIG_PREEMPT_COUNT -static inline int rcu_read_lock_sched_held(void) -{ - int lockdep_opinion = 0; - - if (!debug_lockdep_rcu_enabled()) - return 1; - if (rcu_is_cpu_idle()) - 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 || preempt_count() != 0 || irqs_disabled(); -} -#else /* #ifdef CONFIG_PREEMPT_COUNT */ -static inline int rcu_read_lock_sched_held(void) -{ - return 1; -} -#endif /* #else #ifdef CONFIG_PREEMPT_COUNT */ +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(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) @@ -436,149 +363,285 @@ static inline int rcu_read_lock_bh_held(void) return 1; } -#ifdef CONFIG_PREEMPT_COUNT static inline int rcu_read_lock_sched_held(void) { - return preempt_count() != 0 || irqs_disabled(); + return !preemptible(); } -#else /* #ifdef CONFIG_PREEMPT_COUNT */ -static inline int rcu_read_lock_sched_held(void) + +static inline int rcu_read_lock_any_held(void) { - return 1; + return !preemptible(); +} + +static inline int debug_lockdep_rcu_enabled(void) +{ + return 0; } -#endif /* #else #ifdef CONFIG_PREEMPT_COUNT */ #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU -extern int rcu_my_thread_group_empty(void); - /** - * rcu_lockdep_assert - emit lockdep splat if specified condition not met + * 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_assert(c, s) \ +#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_assert(!lock_is_held(&rcu_lock_map), - "Illegal context switch in RCU read-side critical section"); + RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), + "Illegal context switch in RCU read-side critical section"); } -#else /* #ifdef CONFIG_PROVE_RCU */ -static inline void rcu_preempt_sleep_check(void) -{ -} -#endif /* #else #ifdef CONFIG_PROVE_RCU */ +#else // #ifndef CONFIG_PREEMPT_RCU +static inline void rcu_preempt_sleep_check(void) { } +#endif // #else // #ifndef CONFIG_PREEMPT_RCU #define rcu_sleep_check() \ do { \ rcu_preempt_sleep_check(); \ - rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map), \ - "Illegal context switch in RCU-bh" \ - " read-side critical section"); \ - rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map), \ - "Illegal context switch in RCU-sched"\ - " read-side critical section"); \ + 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_assert(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 */ /* * 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 flavors of pointers to match the multiple flavors of RCU - * (e.g., __rcu_bh, * __rcu_sched, and __srcu), should this make sense in - * the future. + * multiple pointers markings to match different RCU implementations + * (e.g., __srcu), should this make sense in the future. */ #ifdef __CHECKER__ -#define rcu_dereference_sparse(p, space) \ +#define rcu_check_sparse(p, space) \ ((void)(((typeof(*p) space *)p) == p)) #else /* #ifdef __CHECKER__ */ -#define rcu_dereference_sparse(p, space) +#define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ -#define __rcu_access_pointer(p, space) \ - ({ \ - typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \ - rcu_dereference_sparse(p, space); \ - ((typeof(*p) __force __kernel *)(_________p1)); \ - }) -#define __rcu_dereference_check(p, c, space) \ - ({ \ - typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \ - rcu_lockdep_assert(c, "suspicious rcu_dereference_check()" \ - " usage"); \ - rcu_dereference_sparse(p, space); \ - smp_read_barrier_depends(); \ - ((typeof(*p) __force __kernel *)(_________p1)); \ - }) -#define __rcu_dereference_protected(p, c, space) \ - ({ \ - rcu_lockdep_assert(c, "suspicious rcu_dereference_protected()" \ - " usage"); \ - rcu_dereference_sparse(p, space); \ - ((typeof(*p) __force __kernel *)(p)); \ - }) - -#define __rcu_access_index(p, space) \ - ({ \ - typeof(p) _________p1 = ACCESS_ONCE(p); \ - rcu_dereference_sparse(p, space); \ - (_________p1); \ - }) -#define __rcu_dereference_index_check(p, c) \ - ({ \ - typeof(p) _________p1 = ACCESS_ONCE(p); \ - rcu_lockdep_assert(c, \ - "suspicious rcu_dereference_index_check()" \ - " usage"); \ - smp_read_barrier_depends(); \ - (_________p1); \ - }) -#define __rcu_assign_pointer(p, v, space) \ - do { \ - smp_wmb(); \ - (p) = (typeof(*v) __force space *)(v); \ - } while (0) +#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) *local = (typeof(*p) *__force)READ_ONCE(p); \ + rcu_check_sparse(p, space); \ + ((typeof(*p) __force __kernel *)(local)); \ +}) +#define __rcu_dereference_check(p, local, c, space) \ +({ \ + /* Dependency order vs. p above. */ \ + 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 *)(local)); \ +}) +#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, local) \ +({ \ + /* Dependency order vs. p above. */ \ + 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 + * @v: The value to statically initialize with. + */ +#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(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) \ +do { \ + uintptr_t _r_a_p__v = (uintptr_t)(v); \ + rcu_check_sparse(p, __rcu); \ + \ + if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ + WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ + else \ + smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ +} while (0) +/** + * 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) \ +({ \ + typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ + rcu_assign_pointer((rcu_ptr), (ptr)); \ + __tmp; \ +}) /** * 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 - * smp_read_barrier_depends() and keep the ACCESS_ONCE(). 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. + * 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. + * 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 @@ -614,17 +677,24 @@ static inline void rcu_preempt_sleep_check(void) * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ - __rcu_dereference_check((p), rcu_read_lock_held() || (c), __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), rcu_read_lock_bh_held() || (c), __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 @@ -632,56 +702,44 @@ static inline void rcu_preempt_sleep_check(void) * @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), rcu_read_lock_sched_held() || (c), \ + __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ + (c) || rcu_read_lock_sched_held(), \ __rcu) -#define rcu_dereference_raw(p) rcu_dereference_check(p, 1) /*@@@ needed? @@@*/ +/** + * rcu_dereference_all_check() - rcu_dereference_all with debug checking + * @p: The pointer to read, prior to dereferencing + * @c: The conditions under which the dereference will take place + * + * This is similar to rcu_dereference_check(), but allows protection + * by all forms of vanilla RCU readers, including preemption disabled, + * bh-disabled, and interrupt-disabled regions of code. Note that "vanilla + * RCU" excludes SRCU and the various Tasks RCU flavors. Please note + * that this macro should not be backported to any Linux-kernel version + * preceding v5.0 due to changes in synchronize_rcu() semantics prior + * to that version. + */ +#define rcu_dereference_all_check(p, c) \ + __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ + (c) || rcu_read_lock_any_held(), \ + __rcu) /* * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * - * The tracing version of rcu_dereference_raw() must not call + * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ -#define rcu_dereference_raw_notrace(p) __rcu_dereference_check((p), 1, __rcu) - -/** - * rcu_access_index() - fetch RCU index with no dereferencing - * @p: The index to read - * - * Return the value of the specified RCU-protected index, but omit the - * smp_read_barrier_depends() and keep the ACCESS_ONCE(). This is useful - * when the value of this index is accessed, but the index is not - * dereferenced, for example, when testing an RCU-protected index against - * -1. Although rcu_access_index() may also be used in cases where - * update-side locks prevent the value of the index from changing, you - * should instead use rcu_dereference_index_protected() for this use case. - */ -#define rcu_access_index(p) __rcu_access_index((p), __rcu) - -/** - * rcu_dereference_index_check() - rcu_dereference for indices with debug checking - * @p: The pointer to read, prior to dereferencing - * @c: The conditions under which the dereference will take place - * - * Similar to rcu_dereference_check(), but omits the sparse checking. - * This allows rcu_dereference_index_check() to be used on integers, - * which can then be used as array indices. Attempting to use - * rcu_dereference_check() on an integer will give compiler warnings - * because the sparse address-space mechanism relies on dereferencing - * the RCU-protected pointer. Dereferencing integers is not something - * that even gcc will put up with. - * - * Note that this function does not implicitly check for RCU read-side - * critical sections. If this function gains lots of uses, it might - * make sense to provide versions for each flavor of RCU, but it does - * not make sense as of early 2010. - */ -#define rcu_dereference_index_check(p, c) \ - __rcu_dereference_index_check((p), (c)) +#define rcu_dereference_raw_check(p) \ + __rcu_dereference_check((p), __UNIQUE_ID(rcu), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented @@ -689,19 +747,18 @@ static inline void rcu_preempt_sleep_check(void) * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit - * both the smp_read_barrier_depends() and the ACCESS_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. + * 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_protected((p), (c), __rcu) + __rcu_dereference_protected((p), __UNIQUE_ID(rcu), (c), __rcu) /** @@ -729,6 +786,36 @@ static inline void rcu_preempt_sleep_check(void) #define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0) /** + * rcu_dereference_all() - fetch RCU-all-protected pointer for dereferencing + * @p: The pointer to read, prior to dereferencing + * + * Makes rcu_dereference_check() do the dirty work. + */ +#define rcu_dereference_all(p) rcu_dereference_all_check(p, 0) + +/** + * rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism + * @p: The pointer to hand off + * + * 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) (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 @@ -739,6 +826,10 @@ static inline void rcu_preempt_sleep_check(void) * 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 @@ -757,26 +848,25 @@ static inline void rcu_preempt_sleep_check(void) * * 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 !PREEMPT kernel. + * 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 (TREE_RCU and TINY_RCU), it - * is illegal to block while in an RCU read-side critical section. In - * preemptible RCU implementations (TREE_PREEMPT_RCU and TINY_PREEMPT_RCU) - * in CONFIG_PREEMPT 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 inline void rcu_read_lock(void) + * 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) { __rcu_read_lock(); __acquire(RCU); rcu_lock_acquire(&rcu_lock_map); - rcu_lockdep_assert(!rcu_is_cpu_idle(), - "rcu_read_lock() used illegally while idle"); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_lock() used illegally while idle"); } /* @@ -792,13 +882,19 @@ static inline void rcu_read_lock(void) /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * + * In almost all situations, rcu_read_unlock() is immune from deadlock. + * 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_lockdep_assert(!rcu_is_cpu_idle(), - "rcu_read_unlock() used illegally while idle"); - rcu_lock_release(&rcu_lock_map); + 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(); } @@ -806,14 +902,11 @@ static inline void rcu_read_unlock(void) /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * - * This is equivalent of rcu_read_lock(), but to be used when updates - * are being done using call_rcu_bh() or synchronize_rcu_bh(). Since - * both call_rcu_bh() and synchronize_rcu_bh() consider completion of a - * softirq handler to be a quiescent state, a process in RCU read-side - * critical section must be protected by disabling softirqs. Read-side - * critical sections in interrupt context can use just rcu_read_lock(), - * though this should at least be commented to avoid confusing people - * reading the code. + * 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 @@ -825,19 +918,19 @@ static inline void rcu_read_lock_bh(void) local_bh_disable(); __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); - rcu_lockdep_assert(!rcu_is_cpu_idle(), - "rcu_read_lock_bh() used illegally while idle"); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_lock_bh() used illegally while idle"); } -/* - * rcu_read_unlock_bh - marks the end of a softirq-only RCU critical section +/** + * 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_lockdep_assert(!rcu_is_cpu_idle(), - "rcu_read_unlock_bh() used illegally while idle"); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); local_bh_enable(); @@ -846,10 +939,12 @@ 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 to be used when updates - * are being done using call_rcu_sched() or synchronize_rcu_sched(). - * Read-side critical sections can also be introduced by anything 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 @@ -861,8 +956,8 @@ static inline void rcu_read_lock_sched(void) preempt_disable(); __acquire(RCU_SCHED); rcu_lock_acquire(&rcu_sched_lock_map); - rcu_lockdep_assert(!rcu_is_cpu_idle(), - "rcu_read_lock_sched() used illegally while idle"); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_lock_sched() used illegally while idle"); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ @@ -872,15 +967,15 @@ static inline notrace void rcu_read_lock_sched_notrace(void) __acquire(RCU_SCHED); } -/* - * rcu_read_unlock_sched - marks the end of a RCU-classic critical section +/** + * rcu_read_unlock_sched() - marks the end of a RCU-classic critical section * - * See rcu_read_lock_sched for more information. + * See rcu_read_lock_sched() for more information. */ static inline void rcu_read_unlock_sched(void) { - rcu_lockdep_assert(!rcu_is_cpu_idle(), - "rcu_read_unlock_sched() used illegally while idle"); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release(RCU_SCHED); preempt_enable(); @@ -893,46 +988,37 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) preempt_enable_notrace(); } -/** - * 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. - */ -#define rcu_assign_pointer(p, v) \ - __rcu_assign_pointer((p), (v), __rcu) +static __always_inline void rcu_read_lock_dont_migrate(void) +{ + if (IS_ENABLED(CONFIG_PREEMPT_RCU)) + migrate_disable(); + rcu_read_lock(); +} + +static inline void rcu_read_unlock_migrate(void) +{ + rcu_read_unlock(); + if (IS_ENABLED(CONFIG_PREEMPT_RCU)) + migrate_enable(); +} /** * RCU_INIT_POINTER() - initialize an RCU protected pointer + * @p: The pointer to be initialized. + * @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- + * 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- + * 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- + * 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 @@ -948,71 +1034,176 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * 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 + * 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) \ do { \ - p = (typeof(*v) __force __rcu *)(v); \ + rcu_check_sparse(p, __rcu); \ + WRITE_ONCE(p, RCU_INITIALIZER(v)); \ } while (0) /** * 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) \ - .p = (typeof(*v) __force __rcu *)(v) - -/* - * Does the specified offset indicate that the corresponding rcu_head - * structure can be handled by kfree_rcu()? - */ -#define __is_kfree_rcu_offset(offset) ((offset) < 4096) - -/* - * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain. - */ -#define __kfree_rcu(head, offset) \ - do { \ - BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \ - kfree_call_rcu(head, (void (*)(struct rcu_head *))(unsigned long)(offset)); \ - } while (0) + .p = RCU_INITIALIZER(v) /** * kfree_rcu() - kfree an object after a grace period. - * @ptr: pointer to kfree - * @rcu_head: 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 __kfree_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, rcu_head) \ - __kfree_rcu(&((ptr)->rcu_head), offsetof(typeof(*(ptr)), rcu_head)) +#define kfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) +#define kvfree_rcu(ptr, rhf) kvfree_rcu_arg_2(ptr, rhf) -#ifdef CONFIG_RCU_NOCB_CPU -extern bool rcu_is_nocb_cpu(int cpu); -#else -static inline bool rcu_is_nocb_cpu(int cpu) { return false; } -#endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ +/** + * 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) 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_rcu_arg_1(ptr) \ +do { \ + typeof(ptr) ___p = (ptr); \ + \ + if (___p) \ + kvfree_call_rcu(NULL, (void *) (___p)); \ +} while (0) + +/* + * 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() smp_mb() /* Full ordering for lock. */ +#else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ +#define smp_mb__after_unlock_lock() do { } while (0) +#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) +{ + rhp->func = (rcu_callback_t)~0L; +} + +/** + * 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) +{ + rcu_callback_t func = READ_ONCE(rhp->func); + + if (func == f) + return true; + WARN_ON_ONCE(func != (rcu_callback_t)~0L); + return false; +} +/* kernel/ksysfs.c definitions */ +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 */ |