From d1ec4c34c7a9f328e43ea87522119258194f28f8 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Date: Wed, 13 May 2015 10:41:58 -0700 Subject: rcu: Drop RCU_USER_QS in favor of NO_HZ_FULL The RCU_USER_QS Kconfig parameter is now just a synonym for NO_HZ_FULL, so this commit eliminates RCU_USER_QS, replacing all uses with NO_HZ_FULL. Reported-by: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> --- include/linux/rcupdate.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 4cf5f51b4c9c..237f7b8d38ba 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -309,7 +309,7 @@ static inline void rcu_sysrq_end(void) } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ -#ifdef CONFIG_RCU_USER_QS +#ifdef CONFIG_NO_HZ_FULL void rcu_user_enter(void); void rcu_user_exit(void); #else @@ -317,7 +317,7 @@ static inline void rcu_user_enter(void) { } static inline void rcu_user_exit(void) { } static inline void rcu_user_hooks_switch(struct task_struct *prev, struct task_struct *next) { } -#endif /* CONFIG_RCU_USER_QS */ +#endif /* CONFIG_NO_HZ_FULL */ #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); -- cgit v1.2.3 From d5671f6bf2a672cfa72ef2cbac5cc53a4539690d Mon Sep 17 00:00:00 2001 From: Denys Vlasenko <dvlasenk@redhat.com> Date: Tue, 26 May 2015 17:48:34 +0200 Subject: rcu: Deinline rcu_read_lock_sched_held() if DEBUG_LOCK_ALLOC DEBUG_LOCK_ALLOC=y is not a production setting, but it is not very unusual either. Many developers routinely use kernels built with it enabled. Apart from being selected by hand, it is also auto-selected by PROVE_LOCKING "Lock debugging: prove locking correctness" and LOCK_STAT "Lock usage statistics" config options. LOCK STAT is necessary for "perf lock" to work. I wouldn't spend too much time optimizing it, but this particular function has a very large cost in code size: when it is deinlined, code size decreases by 830,000 bytes: text data bss dec hex filename 85674192 22294776 20627456 128596424 7aa39c8 vmlinux.before 84837612 22294424 20627456 127759492 79d7484 vmlinux (with this config: http://busybox.net/~vda/kernel_config) Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com> CC: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> CC: Josh Triplett <josh@joshtriplett.org> CC: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> CC: Lai Jiangshan <laijs@cn.fujitsu.com> CC: Tejun Heo <tj@kernel.org> CC: Oleg Nesterov <oleg@redhat.com> CC: linux-kernel@vger.kernel.org Reviewed-by: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> --- include/linux/rcupdate.h | 40 ++------------------------------------- kernel/rcu/update.c | 49 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+), 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 237f7b8d38ba..def6d45ad61c 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -469,46 +469,10 @@ int rcu_read_lock_bh_held(void); * 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. + * critical section unless it can prove otherwise. */ #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_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 || preempt_count() != 0 || irqs_disabled(); -} +int rcu_read_lock_sched_held(void); #else /* #ifdef CONFIG_PREEMPT_COUNT */ static inline int rcu_read_lock_sched_held(void) { diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index afaecb7a799a..fec5f48b8860 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -62,6 +62,55 @@ MODULE_ALIAS("rcupdate"); module_param(rcu_expedited, int, 0); +#if defined(CONFIG_DEBUG_LOCK_ALLOC) && defined(CONFIG_PREEMPT_COUNT) +/** + * 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 || preempt_count() != 0 || irqs_disabled(); +} +EXPORT_SYMBOL(rcu_read_lock_sched_held); +#endif + #ifndef CONFIG_TINY_RCU static atomic_t rcu_expedited_nesting = -- cgit v1.2.3 From 24560056de61d86153cecb84d04e4237437f5888 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Date: Sat, 30 May 2015 10:11:24 -0700 Subject: rcu: Add RCU-sched flavors of get-state and cond-sync The get_state_synchronize_rcu() and cond_synchronize_rcu() functions allow polling for grace-period completion, with an actual wait for a grace period occurring only when cond_synchronize_rcu() is called too soon after the corresponding get_state_synchronize_rcu(). However, these functions work only for vanilla RCU. This commit adds the get_state_synchronize_sched() and cond_synchronize_sched(), which provide the same capability for RCU-sched. Reported-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> --- include/linux/rcutiny.h | 10 ++++++++++ include/linux/rcutree.h | 2 ++ kernel/rcu/rcutorture.c | 2 ++ kernel/rcu/tree.c | 52 +++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 66 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index 3df6c1ec4e25..ff968b7af3a4 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -37,6 +37,16 @@ static inline void cond_synchronize_rcu(unsigned long oldstate) might_sleep(); } +static inline unsigned long get_state_synchronize_sched(void) +{ + return 0; +} + +static inline void cond_synchronize_sched(unsigned long oldstate) +{ + might_sleep(); +} + static inline void rcu_barrier_bh(void) { wait_rcu_gp(call_rcu_bh); diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 456879143f89..5abec82f325e 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -76,6 +76,8 @@ void rcu_barrier_bh(void); void rcu_barrier_sched(void); unsigned long get_state_synchronize_rcu(void); void cond_synchronize_rcu(unsigned long oldstate); +unsigned long get_state_synchronize_sched(void); +void cond_synchronize_sched(unsigned long oldstate); extern unsigned long rcutorture_testseq; extern unsigned long rcutorture_vernum; diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 59e32684c23b..0f2cb55f0ab3 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -635,6 +635,8 @@ static struct rcu_torture_ops sched_ops = { .deferred_free = rcu_sched_torture_deferred_free, .sync = synchronize_sched, .exp_sync = synchronize_sched_expedited, + .get_state = get_state_synchronize_sched, + .cond_sync = cond_synchronize_sched, .call = call_rcu_sched, .cb_barrier = rcu_barrier_sched, .fqs = rcu_sched_force_quiescent_state, diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 8b5dd8ba9495..9629298eea24 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3253,6 +3253,58 @@ void cond_synchronize_rcu(unsigned long oldstate) } EXPORT_SYMBOL_GPL(cond_synchronize_rcu); +/** + * get_state_synchronize_sched - Snapshot current RCU-sched state + * + * Returns a cookie that is used by a later call to cond_synchronize_sched() + * to determine whether or not a full grace period has elapsed in the + * meantime. + */ +unsigned long get_state_synchronize_sched(void) +{ + /* + * Any prior manipulation of RCU-protected data must happen + * before the load from ->gpnum. + */ + smp_mb(); /* ^^^ */ + + /* + * Make sure this load happens before the purportedly + * time-consuming work between get_state_synchronize_sched() + * and cond_synchronize_sched(). + */ + return smp_load_acquire(&rcu_sched_state.gpnum); +} +EXPORT_SYMBOL_GPL(get_state_synchronize_sched); + +/** + * cond_synchronize_sched - Conditionally wait for an RCU-sched grace period + * + * @oldstate: return value from earlier call to get_state_synchronize_sched() + * + * If a full RCU-sched grace period has elapsed since the earlier call to + * get_state_synchronize_sched(), just return. Otherwise, invoke + * synchronize_sched() to wait for a full grace period. + * + * Yes, this function does not take counter wrap into account. But + * counter wrap is harmless. If the counter wraps, we have waited for + * more than 2 billion grace periods (and way more on a 64-bit system!), + * so waiting for one additional grace period should be just fine. + */ +void cond_synchronize_sched(unsigned long oldstate) +{ + unsigned long newstate; + + /* + * Ensure that this load happens before any RCU-destructive + * actions the caller might carry out after we return. + */ + newstate = smp_load_acquire(&rcu_sched_state.completed); + if (ULONG_CMP_GE(oldstate, newstate)) + synchronize_sched(); +} +EXPORT_SYMBOL_GPL(cond_synchronize_sched); + static int synchronize_sched_expedited_cpu_stop(void *data) { /* -- cgit v1.2.3 From 155d1d12786386d21732f9bba036343ffa43847d Mon Sep 17 00:00:00 2001 From: Peter Zijlstra <peterz@infradead.org> Date: Tue, 2 Jun 2015 17:26:48 +0200 Subject: rcu: Use WRITE_ONCE in RCU_INIT_POINTER For the paranoid amongst us GCC would be in its right to use byte stores to write our NULL value, tell it not to do that. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> --- include/linux/rcupdate.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index def6d45ad61c..c63428c1ed8a 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -995,7 +995,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) #define RCU_INIT_POINTER(p, v) \ do { \ rcu_dereference_sparse(p, __rcu); \ - p = RCU_INITIALIZER(v); \ + WRITE_ONCE(p, RCU_INITIALIZER(v)); \ } while (0) /** -- cgit v1.2.3 From ec90a194ae2cb8b8e9fe4f6f70dd3d4dc0269b4b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Date: Wed, 10 Jun 2015 12:53:06 -0700 Subject: rcu: Create a synchronize_rcu_mult() There have been several requests for a primitive that waits for grace periods for several RCU flavors concurrently, so this commit creates it. This is a variadic macro, and you pass in the call_rcu() functions of the flavors of RCU that you wish to wait for. Note that you cannot pass in call_srcu() for two reasons: (1) This would result in a type mismatch and (2) You need to specify which srcu_struct you want to use. Handle this by creating a wrapper function for your SRCU domain, for example: void call_srcu_mine(struct rcu_head *head, rcu_callback_t func) { call_srcu(&ss_mine, head, func); } You can then do something like this: synchronize_rcu_mult(call_srcu_mine, call_rcu, call_rcu_sched); Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> --- include/linux/rcupdate.h | 35 +++++++++++++++++++++++++++++++---- include/linux/types.h | 3 +++ kernel/rcu/update.c | 37 +++++++++++++++++++++++++++---------- 3 files changed, 61 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index c63428c1ed8a..33ec16b9c2ee 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -226,6 +226,37 @@ struct rcu_synchronize { }; void wakeme_after_rcu(struct rcu_head *head); +void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, + struct rcu_synchronize *rs_array); + +#define _wait_rcu_gp(checktiny, ...) \ +do { \ + call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \ + const int __n = ARRAY_SIZE(__crcu_array); \ + struct rcu_synchronize __rs_array[__n]; \ + \ + __wait_rcu_gp(checktiny, __n, __crcu_array, __rs_array); \ +} while (0) + +#define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__) + +/** + * synchronize_rcu_mult - Wait concurrently for multiple grace periods + * @...: List of call_rcu() functions for the flavors to wait on. + * + * This macro waits concurrently for multiple flavors of RCU grace periods. + * For example, synchronize_rcu_mult(call_rcu, call_rcu_bh) would wait + * on concurrent RCU and RCU-bh grace periods. Waiting on a give SRCU + * domain requires you to write a wrapper function for that SRCU domain's + * call_srcu() function, supplying the corresponding srcu_struct. + * + * If Tiny RCU, tell _wait_rcu_gp() not to bother waiting for RCU + * or RCU-bh, given that anywhere synchronize_rcu_mult() can be called + * is automatically a grace period. + */ +#define synchronize_rcu_mult(...) \ + _wait_rcu_gp(IS_ENABLED(CONFIG_TINY_RCU), __VA_ARGS__) + /** * call_rcu_tasks() - Queue an RCU for invocation task-based grace period * @head: structure to be used for queueing the RCU updates. @@ -392,10 +423,6 @@ bool __rcu_is_watching(void); * 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_PREEMPT_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) diff --git a/include/linux/types.h b/include/linux/types.h index 8715287c3b1f..c314989d9158 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -212,6 +212,9 @@ struct callback_head { }; #define rcu_head callback_head +typedef void (*rcu_callback_t)(struct rcu_head *head); +typedef void (*call_rcu_func_t)(struct rcu_head *head, rcu_callback_t func); + /* clocksource cycle base type */ typedef u64 cycle_t; diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index fec5f48b8860..a0a0dd03c73a 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -318,20 +318,37 @@ void wakeme_after_rcu(struct rcu_head *head) rcu = container_of(head, struct rcu_synchronize, head); complete(&rcu->completion); } +EXPORT_SYMBOL_GPL(wakeme_after_rcu); -void wait_rcu_gp(call_rcu_func_t crf) +void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array, + struct rcu_synchronize *rs_array) { - struct rcu_synchronize rcu; + int i; - init_rcu_head_on_stack(&rcu.head); - init_completion(&rcu.completion); - /* Will wake me after RCU finished. */ - crf(&rcu.head, wakeme_after_rcu); - /* Wait for it. */ - wait_for_completion(&rcu.completion); - destroy_rcu_head_on_stack(&rcu.head); + /* Initialize and register callbacks for each flavor specified. */ + for (i = 0; i < n; i++) { + if (checktiny && + (crcu_array[i] == call_rcu || + crcu_array[i] == call_rcu_bh)) { + might_sleep(); + continue; + } + init_rcu_head_on_stack(&rs_array[i].head); + init_completion(&rs_array[i].completion); + (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 || + crcu_array[i] == call_rcu_bh)) + continue; + wait_for_completion(&rs_array[i].completion); + destroy_rcu_head_on_stack(&rs_array[i].head); + } } -EXPORT_SYMBOL_GPL(wait_rcu_gp); +EXPORT_SYMBOL_GPL(__wait_rcu_gp); #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head) -- cgit v1.2.3 From f78f5b90c4ffa559e400c3919a02236101f29f3f Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Date: Thu, 18 Jun 2015 15:50:02 -0700 Subject: rcu: Rename rcu_lockdep_assert() to RCU_LOCKDEP_WARN() This commit renames rcu_lockdep_assert() to RCU_LOCKDEP_WARN() for consistency with the WARN() series of macros. This also requires inverting the sense of the conditional, which this commit also does. Reported-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Ingo Molnar <mingo@kernel.org> --- Documentation/RCU/whatisRCU.txt | 2 +- arch/x86/kernel/cpu/mcheck/mce.c | 6 ++-- arch/x86/kernel/traps.c | 2 +- drivers/base/power/opp.c | 4 +-- include/linux/fdtable.h | 4 +-- include/linux/rcupdate.h | 63 ++++++++++++++++++++++++++-------------- kernel/cgroup.c | 4 +-- kernel/pid.c | 5 ++-- kernel/rcu/srcu.c | 10 +++---- kernel/rcu/tiny.c | 8 ++--- kernel/rcu/tree.c | 28 +++++++++--------- kernel/rcu/tree_plugin.h | 8 ++--- kernel/rcu/update.c | 4 +-- kernel/sched/core.c | 8 ++--- kernel/workqueue.c | 20 ++++++------- security/device_cgroup.c | 6 ++-- 16 files changed, 101 insertions(+), 81 deletions(-) (limited to 'include/linux') diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt index 5746b0c77f3e..adc2184009c5 100644 --- a/Documentation/RCU/whatisRCU.txt +++ b/Documentation/RCU/whatisRCU.txt @@ -883,7 +883,7 @@ All: lockdep-checked RCU-protected pointer access rcu_access_pointer rcu_dereference_raw - rcu_lockdep_assert + RCU_LOCKDEP_WARN rcu_sleep_check RCU_NONIDLE diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index df919ff103c3..3d6b5269fb2e 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -54,9 +54,9 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); #define rcu_dereference_check_mce(p) \ ({ \ - rcu_lockdep_assert(rcu_read_lock_sched_held() || \ - lockdep_is_held(&mce_chrdev_read_mutex), \ - "suspicious rcu_dereference_check_mce() usage"); \ + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ + !lockdep_is_held(&mce_chrdev_read_mutex), \ + "suspicious rcu_dereference_check_mce() usage"); \ smp_load_acquire(&(p)); \ }) diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index f5791927aa64..c5a5231d1d11 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -136,7 +136,7 @@ enum ctx_state ist_enter(struct pt_regs *regs) preempt_count_add(HARDIRQ_OFFSET); /* This code is a bit fragile. Test it. */ - rcu_lockdep_assert(rcu_is_watching(), "ist_enter didn't work"); + RCU_LOCKDEP_WARN(!rcu_is_watching(), "ist_enter didn't work"); return prev_state; } diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c index 677fb2843553..3b188f20b43f 100644 --- a/drivers/base/power/opp.c +++ b/drivers/base/power/opp.c @@ -110,8 +110,8 @@ static DEFINE_MUTEX(dev_opp_list_lock); #define opp_rcu_lockdep_assert() \ do { \ - rcu_lockdep_assert(rcu_read_lock_held() || \ - lockdep_is_held(&dev_opp_list_lock), \ + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ + !lockdep_is_held(&dev_opp_list_lock), \ "Missing rcu_read_lock() or " \ "dev_opp_list_lock protection"); \ } while (0) diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h index fbb88740634a..674e3e226465 100644 --- a/include/linux/fdtable.h +++ b/include/linux/fdtable.h @@ -86,8 +86,8 @@ static inline struct file *__fcheck_files(struct files_struct *files, unsigned i static inline struct file *fcheck_files(struct files_struct *files, unsigned int fd) { - rcu_lockdep_assert(rcu_read_lock_held() || - lockdep_is_held(&files->file_lock), + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && + !lockdep_is_held(&files->file_lock), "suspicious rcu_dereference_check() usage"); return __fcheck_files(files, fd); } diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index 33ec16b9c2ee..ff476515f716 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -536,6 +536,11 @@ static inline int rcu_read_lock_sched_held(void) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ +/* Deprecate rcu_lockdep_assert(): Use RCU_LOCKDEP_WARN() instead. */ +static inline void __attribute((deprecated)) deprecate_rcu_lockdep_assert(void) +{ +} + #ifdef CONFIG_PROVE_RCU /** @@ -546,17 +551,32 @@ static inline int rcu_read_lock_sched_held(void) #define rcu_lockdep_assert(c, s) \ do { \ static bool __section(.data.unlikely) __warned; \ + deprecate_rcu_lockdep_assert(); \ if (debug_lockdep_rcu_enabled() && !__warned && !(c)) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ } while (0) +/** + * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met + * @c: condition to check + * @s: informative message + */ +#define RCU_LOCKDEP_WARN(c, s) \ + do { \ + static bool __section(.data.unlikely) __warned; \ + if (debug_lockdep_rcu_enabled() && !__warned && (c)) { \ + __warned = true; \ + lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ + } \ + } while (0) + #if defined(CONFIG_PROVE_RCU) && !defined(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) @@ -567,15 +587,16 @@ static inline void rcu_preempt_sleep_check(void) #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"); \ + 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) #else /* #ifdef CONFIG_PROVE_RCU */ -#define rcu_lockdep_assert(c, s) do { } while (0) +#define rcu_lockdep_assert(c, s) deprecate_rcu_lockdep_assert() +#define RCU_LOCKDEP_WARN(c, s) do { } while (0) #define rcu_sleep_check() do { } while (0) #endif /* #else #ifdef CONFIG_PROVE_RCU */ @@ -606,13 +627,13 @@ static inline void rcu_preempt_sleep_check(void) ({ \ /* Dependency order vs. p above. */ \ typeof(*p) *________p1 = (typeof(*p) *__force)lockless_dereference(p); \ - rcu_lockdep_assert(c, "suspicious rcu_dereference_check() usage"); \ + RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_dereference_sparse(p, space); \ ((typeof(*p) __force __kernel *)(________p1)); \ }) #define __rcu_dereference_protected(p, c, space) \ ({ \ - rcu_lockdep_assert(c, "suspicious rcu_dereference_protected() usage"); \ + RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_dereference_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) @@ -836,8 +857,8 @@ static inline void rcu_read_lock(void) __rcu_read_lock(); __acquire(RCU); rcu_lock_acquire(&rcu_lock_map); - rcu_lockdep_assert(rcu_is_watching(), - "rcu_read_lock() used illegally while idle"); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_lock() used illegally while idle"); } /* @@ -887,8 +908,8 @@ static inline void rcu_read_lock(void) */ static inline void rcu_read_unlock(void) { - rcu_lockdep_assert(rcu_is_watching(), - "rcu_read_unlock() used illegally while idle"); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_unlock() used illegally while idle"); __release(RCU); __rcu_read_unlock(); rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ @@ -916,8 +937,8 @@ 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_watching(), - "rcu_read_lock_bh() used illegally while idle"); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_lock_bh() used illegally while idle"); } /* @@ -927,8 +948,8 @@ static inline void rcu_read_lock_bh(void) */ static inline void rcu_read_unlock_bh(void) { - rcu_lockdep_assert(rcu_is_watching(), - "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(); @@ -952,8 +973,8 @@ 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_watching(), - "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. */ @@ -970,8 +991,8 @@ static inline notrace void rcu_read_lock_sched_notrace(void) */ static inline void rcu_read_unlock_sched(void) { - rcu_lockdep_assert(rcu_is_watching(), - "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(); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index f89d9292eee6..b89f3168411b 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -107,8 +107,8 @@ static DEFINE_SPINLOCK(release_agent_path_lock); struct percpu_rw_semaphore cgroup_threadgroup_rwsem; #define cgroup_assert_mutex_or_rcu_locked() \ - rcu_lockdep_assert(rcu_read_lock_held() || \ - lockdep_is_held(&cgroup_mutex), \ + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ + !lockdep_is_held(&cgroup_mutex), \ "cgroup_mutex or RCU read lock required"); /* diff --git a/kernel/pid.c b/kernel/pid.c index 4fd07d5b7baf..ca368793808e 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -451,9 +451,8 @@ EXPORT_SYMBOL(pid_task); */ struct task_struct *find_task_by_pid_ns(pid_t nr, struct pid_namespace *ns) { - rcu_lockdep_assert(rcu_read_lock_held(), - "find_task_by_pid_ns() needs rcu_read_lock()" - " protection"); + RCU_LOCKDEP_WARN(!rcu_read_lock_held(), + "find_task_by_pid_ns() needs rcu_read_lock() protection"); return pid_task(find_pid_ns(nr, ns), PIDTYPE_PID); } diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c index de35087c92a5..d3fcb2ec8536 100644 --- a/kernel/rcu/srcu.c +++ b/kernel/rcu/srcu.c @@ -415,11 +415,11 @@ static void __synchronize_srcu(struct srcu_struct *sp, int trycount) struct rcu_head *head = &rcu.head; bool done = false; - rcu_lockdep_assert(!lock_is_held(&sp->dep_map) && - !lock_is_held(&rcu_bh_lock_map) && - !lock_is_held(&rcu_lock_map) && - !lock_is_held(&rcu_sched_lock_map), - "Illegal synchronize_srcu() in same-type SRCU (or RCU) read-side critical section"); + RCU_LOCKDEP_WARN(lock_is_held(&sp->dep_map) || + lock_is_held(&rcu_bh_lock_map) || + lock_is_held(&rcu_lock_map) || + lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_srcu() in same-type SRCU (or in RCU) read-side critical section"); might_sleep(); init_completion(&rcu.completion); diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index c291bd65d2cb..d0471056d0af 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -191,10 +191,10 @@ static void rcu_process_callbacks(struct softirq_action *unused) */ void synchronize_sched(void) { - rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && - !lock_is_held(&rcu_lock_map) && - !lock_is_held(&rcu_sched_lock_map), - "Illegal synchronize_sched() in RCU read-side critical section"); + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || + lock_is_held(&rcu_lock_map) || + lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_sched() in RCU read-side critical section"); cond_resched(); } EXPORT_SYMBOL_GPL(synchronize_sched); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index cb64d7e13d24..0a73d26357a2 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -649,12 +649,12 @@ static void rcu_eqs_enter_common(long long oldval, bool user) * It is illegal to enter an extended quiescent state while * in an RCU read-side critical section. */ - rcu_lockdep_assert(!lock_is_held(&rcu_lock_map), - "Illegal idle entry in RCU read-side critical section."); - rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map), - "Illegal idle entry in RCU-bh read-side critical section."); - rcu_lockdep_assert(!lock_is_held(&rcu_sched_lock_map), - "Illegal idle entry in RCU-sched read-side critical section."); + RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), + "Illegal idle entry in RCU read-side critical section."); + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), + "Illegal idle entry in RCU-bh read-side critical section."); + RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), + "Illegal idle entry in RCU-sched read-side critical section."); } /* @@ -3161,10 +3161,10 @@ static inline int rcu_blocking_is_gp(void) */ void synchronize_sched(void) { - rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && - !lock_is_held(&rcu_lock_map) && - !lock_is_held(&rcu_sched_lock_map), - "Illegal synchronize_sched() in RCU-sched read-side critical section"); + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || + lock_is_held(&rcu_lock_map) || + lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_sched() in RCU-sched read-side critical section"); if (rcu_blocking_is_gp()) return; if (rcu_gp_is_expedited()) @@ -3188,10 +3188,10 @@ EXPORT_SYMBOL_GPL(synchronize_sched); */ void synchronize_rcu_bh(void) { - rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && - !lock_is_held(&rcu_lock_map) && - !lock_is_held(&rcu_sched_lock_map), - "Illegal synchronize_rcu_bh() in RCU-bh read-side critical section"); + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || + lock_is_held(&rcu_lock_map) || + lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_rcu_bh() in RCU-bh read-side critical section"); if (rcu_blocking_is_gp()) return; if (rcu_gp_is_expedited()) diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index a983bc68a146..9e922f111d63 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -538,10 +538,10 @@ EXPORT_SYMBOL_GPL(call_rcu); */ void synchronize_rcu(void) { - rcu_lockdep_assert(!lock_is_held(&rcu_bh_lock_map) && - !lock_is_held(&rcu_lock_map) && - !lock_is_held(&rcu_sched_lock_map), - "Illegal synchronize_rcu() in RCU read-side critical section"); + RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map) || + lock_is_held(&rcu_lock_map) || + lock_is_held(&rcu_sched_lock_map), + "Illegal synchronize_rcu() in RCU read-side critical section"); if (!rcu_scheduler_active) return; if (rcu_gp_is_expedited()) diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index a0a0dd03c73a..47268fb1d27b 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -589,8 +589,8 @@ EXPORT_SYMBOL_GPL(call_rcu_tasks); void synchronize_rcu_tasks(void) { /* Complain if the scheduler has not started. */ - rcu_lockdep_assert(!rcu_scheduler_active, - "synchronize_rcu_tasks called too soon"); + RCU_LOCKDEP_WARN(rcu_scheduler_active, + "synchronize_rcu_tasks called too soon"); /* Wait for the grace period. */ wait_rcu_gp(call_rcu_tasks); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 78b4bad10081..5e73c79fadd0 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2200,8 +2200,8 @@ unsigned long to_ratio(u64 period, u64 runtime) #ifdef CONFIG_SMP inline struct dl_bw *dl_bw_of(int i) { - rcu_lockdep_assert(rcu_read_lock_sched_held(), - "sched RCU must be held"); + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), + "sched RCU must be held"); return &cpu_rq(i)->rd->dl_bw; } @@ -2210,8 +2210,8 @@ static inline int dl_bw_cpus(int i) struct root_domain *rd = cpu_rq(i)->rd; int cpus = 0; - rcu_lockdep_assert(rcu_read_lock_sched_held(), - "sched RCU must be held"); + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(), + "sched RCU must be held"); for_each_cpu_and(i, rd->span, cpu_active_mask) cpus++; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 4c4f06176f74..cb91c63b4f4a 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -338,20 +338,20 @@ static void workqueue_sysfs_unregister(struct workqueue_struct *wq); #include <trace/events/workqueue.h> #define assert_rcu_or_pool_mutex() \ - rcu_lockdep_assert(rcu_read_lock_sched_held() || \ - lockdep_is_held(&wq_pool_mutex), \ - "sched RCU or wq_pool_mutex should be held") + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ + !lockdep_is_held(&wq_pool_mutex), \ + "sched RCU or wq_pool_mutex should be held") #define assert_rcu_or_wq_mutex(wq) \ - rcu_lockdep_assert(rcu_read_lock_sched_held() || \ - lockdep_is_held(&wq->mutex), \ - "sched RCU or wq->mutex should be held") + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ + !lockdep_is_held(&wq->mutex), \ + "sched RCU or wq->mutex should be held") #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ - rcu_lockdep_assert(rcu_read_lock_sched_held() || \ - lockdep_is_held(&wq->mutex) || \ - lockdep_is_held(&wq_pool_mutex), \ - "sched RCU, wq->mutex or wq_pool_mutex should be held") + RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ + !lockdep_is_held(&wq->mutex) && \ + !lockdep_is_held(&wq_pool_mutex), \ + "sched RCU, wq->mutex or wq_pool_mutex should be held") #define for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ diff --git a/security/device_cgroup.c b/security/device_cgroup.c index 188c1d26393b..73455089feef 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -400,9 +400,9 @@ static bool verify_new_ex(struct dev_cgroup *dev_cgroup, { bool match = false; - rcu_lockdep_assert(rcu_read_lock_held() || - lockdep_is_held(&devcgroup_mutex), - "device_cgroup:verify_new_ex called without proper synchronization"); + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && + lockdep_is_held(&devcgroup_mutex), + "device_cgroup:verify_new_ex called without proper synchronization"); if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) { if (behavior == DEVCG_DEFAULT_ALLOW) { -- cgit v1.2.3 From 12d560f4ea87030667438a169912380be00cea4b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Date: Tue, 14 Jul 2015 18:35:23 -0700 Subject: rcu,locking: Privatize smp_mb__after_unlock_lock() RCU is the only thing that uses smp_mb__after_unlock_lock(), and is likely the only thing that ever will use it, so this commit makes this macro private to RCU. Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: "linux-arch@vger.kernel.org" <linux-arch@vger.kernel.org> --- Documentation/memory-barriers.txt | 71 +++---------------------------------- arch/powerpc/include/asm/spinlock.h | 2 -- include/linux/spinlock.h | 10 ------ kernel/rcu/tree.h | 12 +++++++ 4 files changed, 16 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt index 318523872db5..eafa6a53f72c 100644 --- a/Documentation/memory-barriers.txt +++ b/Documentation/memory-barriers.txt @@ -1854,16 +1854,10 @@ RELEASE are to the same lock variable, but only from the perspective of another CPU not holding that lock. In short, a ACQUIRE followed by an RELEASE may -not- be assumed to be a full memory barrier. -Similarly, the reverse case of a RELEASE followed by an ACQUIRE does not -imply a full memory barrier. If it is necessary for a RELEASE-ACQUIRE -pair to produce a full barrier, the ACQUIRE can be followed by an -smp_mb__after_unlock_lock() invocation. This will produce a full barrier -(including transitivity) if either (a) the RELEASE and the ACQUIRE are -executed by the same CPU or task, or (b) the RELEASE and ACQUIRE act on -the same variable. The smp_mb__after_unlock_lock() primitive is free -on many architectures. Without smp_mb__after_unlock_lock(), the CPU's -execution of the critical sections corresponding to the RELEASE and the -ACQUIRE can cross, so that: +Similarly, the reverse case of a RELEASE followed by an ACQUIRE does +not imply a full memory barrier. Therefore, the CPU's execution of the +critical sections corresponding to the RELEASE and the ACQUIRE can cross, +so that: *A = a; RELEASE M @@ -1901,29 +1895,6 @@ the RELEASE would simply complete, thereby avoiding the deadlock. a sleep-unlock race, but the locking primitive needs to resolve such races properly in any case. -With smp_mb__after_unlock_lock(), the two critical sections cannot overlap. -For example, with the following code, the store to *A will always be -seen by other CPUs before the store to *B: - - *A = a; - RELEASE M - ACQUIRE N - smp_mb__after_unlock_lock(); - *B = b; - -The operations will always occur in one of the following orders: - - STORE *A, RELEASE, ACQUIRE, smp_mb__after_unlock_lock(), STORE *B - STORE *A, ACQUIRE, RELEASE, smp_mb__after_unlock_lock(), STORE *B - ACQUIRE, STORE *A, RELEASE, smp_mb__after_unlock_lock(), STORE *B - -If the RELEASE and ACQUIRE were instead both operating on the same lock -variable, only the first of these alternatives can occur. In addition, -the more strongly ordered systems may rule out some of the above orders. -But in any case, as noted earlier, the smp_mb__after_unlock_lock() -ensures that the store to *A will always be seen as happening before -the store to *B. - Locks and semaphores may not provide any guarantee of ordering on UP compiled systems, and so cannot be counted on in such a situation to actually achieve anything at all - especially with respect to I/O accesses - unless combined @@ -2154,40 +2125,6 @@ But it won't see any of: *E, *F or *G following RELEASE Q -However, if the following occurs: - - CPU 1 CPU 2 - =============================== =============================== - WRITE_ONCE(*A, a); - ACQUIRE M [1] - WRITE_ONCE(*B, b); - WRITE_ONCE(*C, c); - RELEASE M [1] - WRITE_ONCE(*D, d); WRITE_ONCE(*E, e); - ACQUIRE M [2] - smp_mb__after_unlock_lock(); - WRITE_ONCE(*F, f); - WRITE_ONCE(*G, g); - RELEASE M [2] - WRITE_ONCE(*H, h); - -CPU 3 might see: - - *E, ACQUIRE M [1], *C, *B, *A, RELEASE M [1], - ACQUIRE M [2], *H, *F, *G, RELEASE M [2], *D - -But assuming CPU 1 gets the lock first, CPU 3 won't see any of: - - *B, *C, *D, *F, *G or *H preceding ACQUIRE M [1] - *A, *B or *C following RELEASE M [1] - *F, *G or *H preceding ACQUIRE M [2] - *A, *B, *C, *E, *F or *G following RELEASE M [2] - -Note that the smp_mb__after_unlock_lock() is critically important -here: Without it CPU 3 might see some of the above orderings. -Without smp_mb__after_unlock_lock(), the accesses are not guaranteed -to be seen in order unless CPU 3 holds lock M. - ACQUIRES VS I/O ACCESSES ------------------------ diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h index 4dbe072eecbe..523673d7583c 100644 --- a/arch/powerpc/include/asm/spinlock.h +++ b/arch/powerpc/include/asm/spinlock.h @@ -28,8 +28,6 @@ #include <asm/synch.h> #include <asm/ppc-opcode.h> -#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ - #ifdef CONFIG_PPC64 /* use 0x800000yy when locked, where yy == CPU number */ #ifdef __BIG_ENDIAN__ diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h index 0063b24b4f36..16c5ed5a627c 100644 --- a/include/linux/spinlock.h +++ b/include/linux/spinlock.h @@ -130,16 +130,6 @@ do { \ #define smp_mb__before_spinlock() smp_wmb() #endif -/* - * Place this after a lock-acquisition primitive to guarantee that - * an UNLOCK+LOCK pair act 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. - */ -#ifndef smp_mb__after_unlock_lock -#define smp_mb__after_unlock_lock() do { } while (0) -#endif - /** * raw_spin_unlock_wait - wait until the spinlock gets unlocked * @lock: the spinlock in question. diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 0412030ca882..2e991f8361e4 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -653,3 +653,15 @@ static inline void rcu_nocb_q_lengths(struct rcu_data *rdp, long *ql, long *qll) #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ } #endif /* #ifdef CONFIG_RCU_TRACE */ + +/* + * Place this after a lock-acquisition primitive to guarantee that + * an UNLOCK+LOCK pair act 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_PPC +#define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ +#else /* #ifdef CONFIG_PPC */ +#define smp_mb__after_unlock_lock() do { } while (0) +#endif /* #else #ifdef CONFIG_PPC */ -- cgit v1.2.3