From 90127d605f403d814f4986436871210bf8ceb335 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 9 May 2018 10:29:18 -0700 Subject: torture: Make online/offline messages appear only for verbose=2 Some bugs reproduce quickly only at high CPU-hotplug rates, so the rcutorture TREE03 scenario now has only 200 milliseconds spacing between CPU-hotplug operations. At this rate, the torture-test pair of console messages per operation becomes a bit voluminous. This commit therefore converts the torture-test set of "verbose" kernel-boot arguments from bool to int, and prints the extra console messages only when verbose=2. The default is still verbose=1. Signed-off-by: Paul E. McKenney --- kernel/locking/locktorture.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/locking') diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 8402b3349dca..4a2e13870a9b 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -57,7 +57,7 @@ torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable."); torture_param(int, stat_interval, 60, "Number of seconds between stats printk()s"); torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable"); -torture_param(bool, verbose, true, +torture_param(int, verbose, 1, "Enable verbose debugging printk()s"); static char *torture_type = "spin_lock"; -- cgit From 60500037637397dcc8ea3d3c2f16e05ea6695a86 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Tue, 15 May 2018 12:25:05 -0700 Subject: torture: Keep old-school dmesg format This commit adds "#define pr_fmt(fmt) fmt" to the torture-test files in order to keep the current dmesg format. Once Joe's commits have hit mainline, these definitions will be changed in order to automatically generate the dmesg line prefix that the scripts expect. This will have the beneficial side-effect of allowing printk() formats to be used more widely and of shortening some pr_*() lines. Signed-off-by: Paul E. McKenney Cc: Joe Perches --- kernel/locking/locktorture.c | 3 +++ kernel/rcu/rcuperf.c | 3 +++ kernel/rcu/rcutorture.c | 3 +++ kernel/torture.c | 3 +++ 4 files changed, 12 insertions(+) (limited to 'kernel/locking') diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 4a2e13870a9b..57bef4fbfb31 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -21,6 +21,9 @@ * Davidlohr Bueso * Based on kernel/rcu/torture.c. */ + +#define pr_fmt(fmt) fmt + #include #include #include diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c index fb8094848906..df29119b2013 100644 --- a/kernel/rcu/rcuperf.c +++ b/kernel/rcu/rcuperf.c @@ -19,6 +19,9 @@ * * Authors: Paul E. McKenney */ + +#define pr_fmt(fmt) fmt + #include #include #include diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index a5540bd831c4..5604bfac8df4 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -22,6 +22,9 @@ * * See also: Documentation/RCU/torture.txt */ + +#define pr_fmt(fmt) fmt + #include #include #include diff --git a/kernel/torture.c b/kernel/torture.c index 840fd33c1cda..1ac24a826589 100644 --- a/kernel/torture.c +++ b/kernel/torture.c @@ -20,6 +20,9 @@ * Author: Paul E. McKenney * Based on kernel/rcu/torture.c. */ + +#define pr_fmt(fmt) fmt + #include #include #include -- cgit From 55f036ca7e74b85e34958af3d22121c656796413 Mon Sep 17 00:00:00 2001 From: Peter Ziljstra Date: Fri, 15 Jun 2018 10:07:12 +0200 Subject: locking: WW mutex cleanup Make the WW mutex code more readable by adding comments, splitting up functions and pointing out that we're actually using the Wait-Die algorithm. Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Gustavo Padovan Cc: Maarten Lankhorst Cc: Sean Paul Cc: David Airlie Cc: Davidlohr Bueso Cc: "Paul E. McKenney" Cc: Josh Triplett Cc: Thomas Gleixner Cc: Kate Stewart Cc: Philippe Ombredanne Cc: Greg Kroah-Hartman Cc: linux-doc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Co-authored-by: Thomas Hellstrom Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Thomas Hellstrom Acked-by: Ingo Molnar --- Documentation/locking/ww-mutex-design.txt | 12 +- include/linux/ww_mutex.h | 28 ++--- kernel/locking/mutex.c | 202 ++++++++++++++++++------------ 3 files changed, 145 insertions(+), 97 deletions(-) (limited to 'kernel/locking') diff --git a/Documentation/locking/ww-mutex-design.txt b/Documentation/locking/ww-mutex-design.txt index 34c3a1b50b9a..2fd7f2a2af21 100644 --- a/Documentation/locking/ww-mutex-design.txt +++ b/Documentation/locking/ww-mutex-design.txt @@ -32,10 +32,10 @@ the oldest task) wins, and the one with the higher reservation id (i.e. the younger task) unlocks all of the buffers that it has already locked, and then tries again. -In the RDBMS literature this deadlock handling approach is called wait/wound: +In the RDBMS literature this deadlock handling approach is called wait/die: The older tasks waits until it can acquire the contended lock. The younger tasks needs to back off and drop all the locks it is currently holding, i.e. the -younger task is wounded. +younger task dies. Concepts -------- @@ -56,9 +56,9 @@ Furthermore there are three different class of w/w lock acquire functions: * Normal lock acquisition with a context, using ww_mutex_lock. -* Slowpath lock acquisition on the contending lock, used by the wounded task - after having dropped all already acquired locks. These functions have the - _slow postfix. +* Slowpath lock acquisition on the contending lock, used by the task that just + killed its transaction after having dropped all already acquired locks. + These functions have the _slow postfix. From a simple semantics point-of-view the _slow functions are not strictly required, since simply calling the normal ww_mutex_lock functions on the @@ -220,7 +220,7 @@ mutexes are a natural fit for such a case for two reasons: Note that this approach differs in two important ways from the above methods: - Since the list of objects is dynamically constructed (and might very well be - different when retrying due to hitting the -EDEADLK wound condition) there's + different when retrying due to hitting the -EDEADLK die condition) there's no need to keep any object on a persistent list when it's not locked. We can therefore move the list_head into the object itself. - On the other hand the dynamic object list construction also means that the -EALREADY return diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index 39fda195bf78..f82fce2229c8 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -6,7 +6,7 @@ * * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar * - * Wound/wait implementation: + * Wait/Die implementation: * Copyright (C) 2013 Canonical Ltd. * * This file contains the main data structure and API definitions. @@ -28,9 +28,9 @@ struct ww_class { struct ww_acquire_ctx { struct task_struct *task; unsigned long stamp; - unsigned acquired; + unsigned int acquired; #ifdef CONFIG_DEBUG_MUTEXES - unsigned done_acquire; + unsigned int done_acquire; struct ww_class *ww_class; struct ww_mutex *contending_lock; #endif @@ -38,8 +38,8 @@ struct ww_acquire_ctx { struct lockdep_map dep_map; #endif #ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH - unsigned deadlock_inject_interval; - unsigned deadlock_inject_countdown; + unsigned int deadlock_inject_interval; + unsigned int deadlock_inject_countdown; #endif }; @@ -102,7 +102,7 @@ static inline void ww_mutex_init(struct ww_mutex *lock, * * Context-based w/w mutex acquiring can be done in any order whatsoever within * a given lock class. Deadlocks will be detected and handled with the - * wait/wound logic. + * wait/die logic. * * Mixing of context-based w/w mutex acquiring and single w/w mutex locking can * result in undetected deadlocks and is so forbidden. Mixing different contexts @@ -195,13 +195,13 @@ static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx) * Lock the w/w mutex exclusively for this task. * * Deadlocks within a given w/w class of locks are detected and handled with the - * wait/wound algorithm. If the lock isn't immediately avaiable this function + * wait/die algorithm. If the lock isn't immediately available this function * will either sleep until it is (wait case). Or it selects the current context - * for backing off by returning -EDEADLK (wound case). Trying to acquire the + * for backing off by returning -EDEADLK (die case). Trying to acquire the * same lock with the same context twice is also detected and signalled by * returning -EALREADY. Returns 0 if the mutex was successfully acquired. * - * In the wound case the caller must release all currently held w/w mutexes for + * In the die case the caller must release all currently held w/w mutexes for * the given context and then wait for this contending lock to be available by * calling ww_mutex_lock_slow. Alternatively callers can opt to not acquire this * lock and proceed with trying to acquire further w/w mutexes (e.g. when @@ -226,14 +226,14 @@ extern int /* __must_check */ ww_mutex_lock(struct ww_mutex *lock, struct ww_acq * Lock the w/w mutex exclusively for this task. * * Deadlocks within a given w/w class of locks are detected and handled with the - * wait/wound algorithm. If the lock isn't immediately avaiable this function + * wait/die algorithm. If the lock isn't immediately available this function * will either sleep until it is (wait case). Or it selects the current context - * for backing off by returning -EDEADLK (wound case). Trying to acquire the + * for backing off by returning -EDEADLK (die case). Trying to acquire the * same lock with the same context twice is also detected and signalled by * returning -EALREADY. Returns 0 if the mutex was successfully acquired. If a * signal arrives while waiting for the lock then this function returns -EINTR. * - * In the wound case the caller must release all currently held w/w mutexes for + * In the die case the caller must release all currently held w/w mutexes for * the given context and then wait for this contending lock to be available by * calling ww_mutex_lock_slow_interruptible. Alternatively callers can opt to * not acquire this lock and proceed with trying to acquire further w/w mutexes @@ -256,7 +256,7 @@ extern int __must_check ww_mutex_lock_interruptible(struct ww_mutex *lock, * @lock: the mutex to be acquired * @ctx: w/w acquire context * - * Acquires a w/w mutex with the given context after a wound case. This function + * Acquires a w/w mutex with the given context after a die case. This function * will sleep until the lock becomes available. * * The caller must have released all w/w mutexes already acquired with the @@ -290,7 +290,7 @@ ww_mutex_lock_slow(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) * @lock: the mutex to be acquired * @ctx: w/w acquire context * - * Acquires a w/w mutex with the given context after a wound case. This function + * Acquires a w/w mutex with the given context after a die case. This function * will sleep until the lock becomes available and returns 0 when the lock has * been acquired. If a signal arrives while waiting for the lock then this * function returns -EINTR. diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index f44f658ae629..cfe48419b7d0 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -244,6 +244,17 @@ void __sched mutex_lock(struct mutex *lock) EXPORT_SYMBOL(mutex_lock); #endif +/* + * Wait-Die: + * The newer transactions are killed when: + * It (the new transaction) makes a request for a lock being held + * by an older transaction. + */ + +/* + * Associate the ww_mutex @ww with the context @ww_ctx under which we acquired + * it. + */ static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) { @@ -282,26 +293,53 @@ ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx) DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); #endif ww_ctx->acquired++; + ww->ctx = ww_ctx; } +/* + * Determine if context @a is 'after' context @b. IOW, @a is a younger + * transaction than @b and depending on algorithm either needs to wait for + * @b or die. + */ static inline bool __sched __ww_ctx_stamp_after(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b) { - return a->stamp - b->stamp <= LONG_MAX && - (a->stamp != b->stamp || a > b); + + return (signed long)(a->stamp - b->stamp) > 0; +} + +/* + * Wait-Die; wake a younger waiter context (when locks held) such that it can + * die. + * + * Among waiters with context, only the first one can have other locks acquired + * already (ctx->acquired > 0), because __ww_mutex_add_waiter() and + * __ww_mutex_check_kill() wake any but the earliest context. + */ +static bool __sched +__ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter, + struct ww_acquire_ctx *ww_ctx) +{ + if (waiter->ww_ctx->acquired > 0 && + __ww_ctx_stamp_after(waiter->ww_ctx, ww_ctx)) { + debug_mutex_wake_waiter(lock, waiter); + wake_up_process(waiter->task); + } + + return true; } /* - * Wake up any waiters that may have to back off when the lock is held by the - * given context. + * We just acquired @lock under @ww_ctx, if there are later contexts waiting + * behind us on the wait-list, check if they need to die. * - * Due to the invariants on the wait list, this can only affect the first - * waiter with a context. + * See __ww_mutex_add_waiter() for the list-order construction; basically the + * list is ordered by stamp, smallest (oldest) first. * * The current task must not be on the wait list. */ static void __sched -__ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) +__ww_mutex_check_waiters(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) { struct mutex_waiter *cur; @@ -311,30 +349,23 @@ __ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) if (!cur->ww_ctx) continue; - if (cur->ww_ctx->acquired > 0 && - __ww_ctx_stamp_after(cur->ww_ctx, ww_ctx)) { - debug_mutex_wake_waiter(lock, cur); - wake_up_process(cur->task); - } - - break; + if (__ww_mutex_die(lock, cur, ww_ctx)) + break; } } /* - * After acquiring lock with fastpath or when we lost out in contested - * slowpath, set ctx and wake up any waiters so they can recheck. + * After acquiring lock with fastpath, where we do not hold wait_lock, set ctx + * and wake up any waiters so they can recheck. */ static __always_inline void ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { ww_mutex_lock_acquired(lock, ctx); - lock->ctx = ctx; - /* * The lock->ctx update should be visible on all cores before - * the atomic read is done, otherwise contended waiters might be + * the WAITERS check is done, otherwise contended waiters might be * missed. The contended waiters will either see ww_ctx == NULL * and keep spinning, or it will acquire wait_lock, add itself * to waiter list and sleep. @@ -348,29 +379,14 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) return; /* - * Uh oh, we raced in fastpath, wake up everyone in this case, - * so they can see the new lock->ctx. + * Uh oh, we raced in fastpath, check if any of the waiters need to + * die. */ spin_lock(&lock->base.wait_lock); - __ww_mutex_wakeup_for_backoff(&lock->base, ctx); + __ww_mutex_check_waiters(&lock->base, ctx); spin_unlock(&lock->base.wait_lock); } -/* - * After acquiring lock in the slowpath set ctx. - * - * Unlike for the fast path, the caller ensures that waiters are woken up where - * necessary. - * - * Callers must hold the mutex wait_lock. - */ -static __always_inline void -ww_mutex_set_context_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) -{ - ww_mutex_lock_acquired(lock, ctx); - lock->ctx = ctx; -} - #ifdef CONFIG_MUTEX_SPIN_ON_OWNER static inline @@ -646,37 +662,73 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock) } EXPORT_SYMBOL(ww_mutex_unlock); + +static __always_inline int __sched +__ww_mutex_kill(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) +{ + if (ww_ctx->acquired > 0) { +#ifdef CONFIG_DEBUG_MUTEXES + struct ww_mutex *ww; + + ww = container_of(lock, struct ww_mutex, base); + DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock); + ww_ctx->contending_lock = ww; +#endif + return -EDEADLK; + } + + return 0; +} + + +/* + * Check whether we need to kill the transaction for the current lock acquire. + * + * Wait-Die: If we're trying to acquire a lock already held by an older + * context, kill ourselves. + * + * Since __ww_mutex_add_waiter() orders the wait-list on stamp, we only have to + * look at waiters before us in the wait-list. + */ static inline int __sched -__ww_mutex_lock_check_stamp(struct mutex *lock, struct mutex_waiter *waiter, - struct ww_acquire_ctx *ctx) +__ww_mutex_check_kill(struct mutex *lock, struct mutex_waiter *waiter, + struct ww_acquire_ctx *ctx) { struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx); struct mutex_waiter *cur; + if (ctx->acquired == 0) + return 0; + if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx)) - goto deadlock; + return __ww_mutex_kill(lock, ctx); /* * If there is a waiter in front of us that has a context, then its - * stamp is earlier than ours and we must back off. + * stamp is earlier than ours and we must kill ourself. */ cur = waiter; list_for_each_entry_continue_reverse(cur, &lock->wait_list, list) { - if (cur->ww_ctx) - goto deadlock; + if (!cur->ww_ctx) + continue; + + return __ww_mutex_kill(lock, ctx); } return 0; - -deadlock: -#ifdef CONFIG_DEBUG_MUTEXES - DEBUG_LOCKS_WARN_ON(ctx->contending_lock); - ctx->contending_lock = ww; -#endif - return -EDEADLK; } +/* + * Add @waiter to the wait-list, keep the wait-list ordered by stamp, smallest + * first. Such that older contexts are preferred to acquire the lock over + * younger contexts. + * + * Waiters without context are interspersed in FIFO order. + * + * Furthermore, for Wait-Die kill ourself immediately when possible (there are + * older contexts already waiting) to avoid unnecessary waiting. + */ static inline int __sched __ww_mutex_add_waiter(struct mutex_waiter *waiter, struct mutex *lock, @@ -693,7 +745,7 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, /* * Add the waiter before the first waiter with a higher stamp. * Waiters without a context are skipped to avoid starving - * them. + * them. Wait-Die waiters may die here. */ pos = &lock->wait_list; list_for_each_entry_reverse(cur, &lock->wait_list, list) { @@ -701,34 +753,27 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, continue; if (__ww_ctx_stamp_after(ww_ctx, cur->ww_ctx)) { - /* Back off immediately if necessary. */ - if (ww_ctx->acquired > 0) { -#ifdef CONFIG_DEBUG_MUTEXES - struct ww_mutex *ww; + /* + * Wait-Die: if we find an older context waiting, there + * is no point in queueing behind it, as we'd have to + * die the moment it would acquire the lock. + */ + int ret = __ww_mutex_kill(lock, ww_ctx); - ww = container_of(lock, struct ww_mutex, base); - DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock); - ww_ctx->contending_lock = ww; -#endif - return -EDEADLK; - } + if (ret) + return ret; break; } pos = &cur->list; - /* - * Wake up the waiter so that it gets a chance to back - * off. - */ - if (cur->ww_ctx->acquired > 0) { - debug_mutex_wake_waiter(lock, cur); - wake_up_process(cur->task); - } + /* Wait-Die: ensure younger waiters die. */ + __ww_mutex_die(lock, cur, ww_ctx); } list_add_tail(&waiter->list, pos); + return 0; } @@ -772,7 +817,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, */ if (__mutex_trylock(lock)) { if (use_ww_ctx && ww_ctx) - __ww_mutex_wakeup_for_backoff(lock, ww_ctx); + __ww_mutex_check_waiters(lock, ww_ctx); goto skip_wait; } @@ -790,10 +835,13 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, waiter.ww_ctx = MUTEX_POISON_WW_CTX; #endif } else { - /* Add in stamp order, waking up waiters that must back off. */ + /* + * Add in stamp order, waking up waiters that must kill + * themselves. + */ ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx); if (ret) - goto err_early_backoff; + goto err_early_kill; waiter.ww_ctx = ww_ctx; } @@ -815,7 +863,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, goto acquired; /* - * Check for signals and wound conditions while holding + * Check for signals and kill conditions while holding * wait_lock. This ensures the lock cancellation is ordered * against mutex_unlock() and wake-ups do not go missing. */ @@ -824,8 +872,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, goto err; } - if (use_ww_ctx && ww_ctx && ww_ctx->acquired > 0) { - ret = __ww_mutex_lock_check_stamp(lock, &waiter, ww_ctx); + if (use_ww_ctx && ww_ctx) { + ret = __ww_mutex_check_kill(lock, &waiter, ww_ctx); if (ret) goto err; } @@ -870,7 +918,7 @@ skip_wait: lock_acquired(&lock->dep_map, ip); if (use_ww_ctx && ww_ctx) - ww_mutex_set_context_slowpath(ww, ww_ctx); + ww_mutex_lock_acquired(ww, ww_ctx); spin_unlock(&lock->wait_lock); preempt_enable(); @@ -879,7 +927,7 @@ skip_wait: err: __set_current_state(TASK_RUNNING); mutex_remove_waiter(lock, &waiter, current); -err_early_backoff: +err_early_kill: spin_unlock(&lock->wait_lock); debug_mutex_free_waiter(&waiter); mutex_release(&lock->dep_map, 1, ip); -- cgit From 08295b3b5beec9aac0f7a9db86f0fc3792039da3 Mon Sep 17 00:00:00 2001 From: Thomas Hellstrom Date: Fri, 15 Jun 2018 10:17:38 +0200 Subject: locking: Implement an algorithm choice for Wound-Wait mutexes The current Wound-Wait mutex algorithm is actually not Wound-Wait but Wait-Die. Implement also Wound-Wait as a per-ww-class choice. Wound-Wait is, contrary to Wait-Die a preemptive algorithm and is known to generate fewer backoffs. Testing reveals that this is true if the number of simultaneous contending transactions is small. As the number of simultaneous contending threads increases, Wait-Wound becomes inferior to Wait-Die in terms of elapsed time. Possibly due to the larger number of held locks of sleeping transactions. Update documentation and callers. Timings using git://people.freedesktop.org/~thomash/ww_mutex_test tag patch-18-06-15 Each thread runs 100000 batches of lock / unlock 800 ww mutexes randomly chosen out of 100000. Four core Intel x86_64: Algorithm #threads Rollbacks time Wound-Wait 4 ~100 ~17s. Wait-Die 4 ~150000 ~19s. Wound-Wait 16 ~360000 ~109s. Wait-Die 16 ~450000 ~82s. Cc: Ingo Molnar Cc: Jonathan Corbet Cc: Gustavo Padovan Cc: Maarten Lankhorst Cc: Sean Paul Cc: David Airlie Cc: Davidlohr Bueso Cc: "Paul E. McKenney" Cc: Josh Triplett Cc: Thomas Gleixner Cc: Kate Stewart Cc: Philippe Ombredanne Cc: Greg Kroah-Hartman Cc: linux-doc@vger.kernel.org Cc: linux-media@vger.kernel.org Cc: linaro-mm-sig@lists.linaro.org Co-authored-by: Peter Zijlstra Signed-off-by: Thomas Hellstrom Acked-by: Peter Zijlstra (Intel) Acked-by: Ingo Molnar --- Documentation/locking/ww-mutex-design.txt | 57 +++++++++-- drivers/dma-buf/reservation.c | 2 +- drivers/gpu/drm/drm_modeset_lock.c | 2 +- include/linux/ww_mutex.h | 17 ++- kernel/locking/locktorture.c | 2 +- kernel/locking/mutex.c | 165 +++++++++++++++++++++++++++--- kernel/locking/test-ww_mutex.c | 2 +- lib/locking-selftest.c | 2 +- 8 files changed, 213 insertions(+), 36 deletions(-) (limited to 'kernel/locking') diff --git a/Documentation/locking/ww-mutex-design.txt b/Documentation/locking/ww-mutex-design.txt index 2fd7f2a2af21..f0ed7c30e695 100644 --- a/Documentation/locking/ww-mutex-design.txt +++ b/Documentation/locking/ww-mutex-design.txt @@ -1,4 +1,4 @@ -Wait/Wound Deadlock-Proof Mutex Design +Wound/Wait Deadlock-Proof Mutex Design ====================================== Please read mutex-design.txt first, as it applies to wait/wound mutexes too. @@ -32,10 +32,26 @@ the oldest task) wins, and the one with the higher reservation id (i.e. the younger task) unlocks all of the buffers that it has already locked, and then tries again. -In the RDBMS literature this deadlock handling approach is called wait/die: -The older tasks waits until it can acquire the contended lock. The younger tasks -needs to back off and drop all the locks it is currently holding, i.e. the -younger task dies. +In the RDBMS literature, a reservation ticket is associated with a transaction. +and the deadlock handling approach is called Wait-Die. The name is based on +the actions of a locking thread when it encounters an already locked mutex. +If the transaction holding the lock is younger, the locking transaction waits. +If the transaction holding the lock is older, the locking transaction backs off +and dies. Hence Wait-Die. +There is also another algorithm called Wound-Wait: +If the transaction holding the lock is younger, the locking transaction +wounds the transaction holding the lock, requesting it to die. +If the transaction holding the lock is older, it waits for the other +transaction. Hence Wound-Wait. +The two algorithms are both fair in that a transaction will eventually succeed. +However, the Wound-Wait algorithm is typically stated to generate fewer backoffs +compared to Wait-Die, but is, on the other hand, associated with more work than +Wait-Die when recovering from a backoff. Wound-Wait is also a preemptive +algorithm in that transactions are wounded by other transactions, and that +requires a reliable way to pick up up the wounded condition and preempt the +running transaction. Note that this is not the same as process preemption. A +Wound-Wait transaction is considered preempted when it dies (returning +-EDEADLK) following a wound. Concepts -------- @@ -47,10 +63,12 @@ Acquire context: To ensure eventual forward progress it is important the a task trying to acquire locks doesn't grab a new reservation id, but keeps the one it acquired when starting the lock acquisition. This ticket is stored in the acquire context. Furthermore the acquire context keeps track of debugging state -to catch w/w mutex interface abuse. +to catch w/w mutex interface abuse. An acquire context is representing a +transaction. W/w class: In contrast to normal mutexes the lock class needs to be explicit for -w/w mutexes, since it is required to initialize the acquire context. +w/w mutexes, since it is required to initialize the acquire context. The lock +class also specifies what algorithm to use, Wound-Wait or Wait-Die. Furthermore there are three different class of w/w lock acquire functions: @@ -90,6 +108,12 @@ provided. Usage ----- +The algorithm (Wait-Die vs Wound-Wait) is chosen by using either +DEFINE_WW_CLASS() (Wound-Wait) or DEFINE_WD_CLASS() (Wait-Die) +As a rough rule of thumb, use Wound-Wait iff you +expect the number of simultaneous competing transactions to be typically small, +and you want to reduce the number of rollbacks. + Three different ways to acquire locks within the same w/w class. Common definitions for methods #1 and #2: @@ -312,12 +336,23 @@ Design: We maintain the following invariants for the wait list: (1) Waiters with an acquire context are sorted by stamp order; waiters without an acquire context are interspersed in FIFO order. - (2) Among waiters with contexts, only the first one can have other locks - acquired already (ctx->acquired > 0). Note that this waiter may come - after other waiters without contexts in the list. + (2) For Wait-Die, among waiters with contexts, only the first one can have + other locks acquired already (ctx->acquired > 0). Note that this waiter + may come after other waiters without contexts in the list. + + The Wound-Wait preemption is implemented with a lazy-preemption scheme: + The wounded status of the transaction is checked only when there is + contention for a new lock and hence a true chance of deadlock. In that + situation, if the transaction is wounded, it backs off, clears the + wounded status and retries. A great benefit of implementing preemption in + this way is that the wounded transaction can identify a contending lock to + wait for before restarting the transaction. Just blindly restarting the + transaction would likely make the transaction end up in a situation where + it would have to back off again. In general, not much contention is expected. The locks are typically used to - serialize access to resources for devices. + serialize access to resources for devices, and optimization focus should + therefore be directed towards the uncontended cases. Lockdep: Special care has been taken to warn for as many cases of api abuse diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c index 314eb1071cce..20bf90f4ee63 100644 --- a/drivers/dma-buf/reservation.c +++ b/drivers/dma-buf/reservation.c @@ -46,7 +46,7 @@ * write-side updates. */ -DEFINE_WW_CLASS(reservation_ww_class); +DEFINE_WD_CLASS(reservation_ww_class); EXPORT_SYMBOL(reservation_ww_class); struct lock_class_key reservation_seqcount_class; diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c index 8a5100685875..638be2eb67b4 100644 --- a/drivers/gpu/drm/drm_modeset_lock.c +++ b/drivers/gpu/drm/drm_modeset_lock.c @@ -70,7 +70,7 @@ * lists and lookup data structures. */ -static DEFINE_WW_CLASS(crtc_ww_class); +static DEFINE_WD_CLASS(crtc_ww_class); /** * drm_modeset_lock_all - take all modeset locks diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h index f82fce2229c8..3af7c0e03be5 100644 --- a/include/linux/ww_mutex.h +++ b/include/linux/ww_mutex.h @@ -8,6 +8,8 @@ * * Wait/Die implementation: * Copyright (C) 2013 Canonical Ltd. + * Choice of algorithm: + * Copyright (C) 2018 WMWare Inc. * * This file contains the main data structure and API definitions. */ @@ -23,12 +25,15 @@ struct ww_class { struct lock_class_key mutex_key; const char *acquire_name; const char *mutex_name; + unsigned int is_wait_die; }; struct ww_acquire_ctx { struct task_struct *task; unsigned long stamp; unsigned int acquired; + unsigned short wounded; + unsigned short is_wait_die; #ifdef CONFIG_DEBUG_MUTEXES unsigned int done_acquire; struct ww_class *ww_class; @@ -58,17 +63,21 @@ struct ww_mutex { # define __WW_CLASS_MUTEX_INITIALIZER(lockname, class) #endif -#define __WW_CLASS_INITIALIZER(ww_class) \ +#define __WW_CLASS_INITIALIZER(ww_class, _is_wait_die) \ { .stamp = ATOMIC_LONG_INIT(0) \ , .acquire_name = #ww_class "_acquire" \ - , .mutex_name = #ww_class "_mutex" } + , .mutex_name = #ww_class "_mutex" \ + , .is_wait_die = _is_wait_die } #define __WW_MUTEX_INITIALIZER(lockname, class) \ { .base = __MUTEX_INITIALIZER(lockname.base) \ __WW_CLASS_MUTEX_INITIALIZER(lockname, class) } +#define DEFINE_WD_CLASS(classname) \ + struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 1) + #define DEFINE_WW_CLASS(classname) \ - struct ww_class classname = __WW_CLASS_INITIALIZER(classname) + struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 0) #define DEFINE_WW_MUTEX(mutexname, ww_class) \ struct ww_mutex mutexname = __WW_MUTEX_INITIALIZER(mutexname, ww_class) @@ -123,6 +132,8 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx, ctx->task = current; ctx->stamp = atomic_long_inc_return_relaxed(&ww_class->stamp); ctx->acquired = 0; + ctx->wounded = false; + ctx->is_wait_die = ww_class->is_wait_die; #ifdef CONFIG_DEBUG_MUTEXES ctx->ww_class = ww_class; ctx->done_acquire = 0; diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index 8402b3349dca..c28224347d69 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -365,7 +365,7 @@ static struct lock_torture_ops mutex_lock_ops = { }; #include -static DEFINE_WW_CLASS(torture_ww_class); +static DEFINE_WD_CLASS(torture_ww_class); static DEFINE_WW_MUTEX(torture_ww_mutex_0, &torture_ww_class); static DEFINE_WW_MUTEX(torture_ww_mutex_1, &torture_ww_class); static DEFINE_WW_MUTEX(torture_ww_mutex_2, &torture_ww_class); diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index cfe48419b7d0..1a81a1257b3f 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -173,6 +173,21 @@ static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_wait return list_first_entry(&lock->wait_list, struct mutex_waiter, list) == waiter; } +/* + * Add @waiter to a given location in the lock wait_list and set the + * FLAG_WAITERS flag if it's the first waiter. + */ +static void __sched +__mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter, + struct list_head *list) +{ + debug_mutex_add_waiter(lock, waiter, current); + + list_add_tail(&waiter->list, list); + if (__mutex_waiter_is_first(lock, waiter)) + __mutex_set_flag(lock, MUTEX_FLAG_WAITERS); +} + /* * Give up ownership to a specific task, when @task = NULL, this is equivalent * to a regular unlock. Sets PICKUP on a handoff, clears HANDOF, preserves @@ -249,6 +264,11 @@ EXPORT_SYMBOL(mutex_lock); * The newer transactions are killed when: * It (the new transaction) makes a request for a lock being held * by an older transaction. + * + * Wound-Wait: + * The newer transactions are wounded when: + * An older transaction makes a request for a lock being held by + * the newer transaction. */ /* @@ -320,6 +340,9 @@ static bool __sched __ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter, struct ww_acquire_ctx *ww_ctx) { + if (!ww_ctx->is_wait_die) + return false; + if (waiter->ww_ctx->acquired > 0 && __ww_ctx_stamp_after(waiter->ww_ctx, ww_ctx)) { debug_mutex_wake_waiter(lock, waiter); @@ -329,13 +352,65 @@ __ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter, return true; } +/* + * Wound-Wait; wound a younger @hold_ctx if it holds the lock. + * + * Wound the lock holder if there are waiters with older transactions than + * the lock holders. Even if multiple waiters may wound the lock holder, + * it's sufficient that only one does. + */ +static bool __ww_mutex_wound(struct mutex *lock, + struct ww_acquire_ctx *ww_ctx, + struct ww_acquire_ctx *hold_ctx) +{ + struct task_struct *owner = __mutex_owner(lock); + + lockdep_assert_held(&lock->wait_lock); + + /* + * Possible through __ww_mutex_add_waiter() when we race with + * ww_mutex_set_context_fastpath(). In that case we'll get here again + * through __ww_mutex_check_waiters(). + */ + if (!hold_ctx) + return false; + + /* + * Can have !owner because of __mutex_unlock_slowpath(), but if owner, + * it cannot go away because we'll have FLAG_WAITERS set and hold + * wait_lock. + */ + if (!owner) + return false; + + if (ww_ctx->acquired > 0 && __ww_ctx_stamp_after(hold_ctx, ww_ctx)) { + hold_ctx->wounded = 1; + + /* + * wake_up_process() paired with set_current_state() + * inserts sufficient barriers to make sure @owner either sees + * it's wounded in __ww_mutex_lock_check_stamp() or has a + * wakeup pending to re-read the wounded state. + */ + if (owner != current) + wake_up_process(owner); + + return true; + } + + return false; +} + /* * We just acquired @lock under @ww_ctx, if there are later contexts waiting - * behind us on the wait-list, check if they need to die. + * behind us on the wait-list, check if they need to die, or wound us. * * See __ww_mutex_add_waiter() for the list-order construction; basically the * list is ordered by stamp, smallest (oldest) first. * + * This relies on never mixing wait-die/wound-wait on the same wait-list; + * which is currently ensured by that being a ww_class property. + * * The current task must not be on the wait list. */ static void __sched @@ -349,7 +424,8 @@ __ww_mutex_check_waiters(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) if (!cur->ww_ctx) continue; - if (__ww_mutex_die(lock, cur, ww_ctx)) + if (__ww_mutex_die(lock, cur, ww_ctx) || + __ww_mutex_wound(lock, cur->ww_ctx, ww_ctx)) break; } } @@ -370,17 +446,23 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) * and keep spinning, or it will acquire wait_lock, add itself * to waiter list and sleep. */ - smp_mb(); /* ^^^ */ + smp_mb(); /* See comments above and below. */ /* - * Check if lock is contended, if not there is nobody to wake up + * [W] ww->ctx = ctx [W] MUTEX_FLAG_WAITERS + * MB MB + * [R] MUTEX_FLAG_WAITERS [R] ww->ctx + * + * The memory barrier above pairs with the memory barrier in + * __ww_mutex_add_waiter() and makes sure we either observe ww->ctx + * and/or !empty list. */ if (likely(!(atomic_long_read(&lock->base.owner) & MUTEX_FLAG_WAITERS))) return; /* * Uh oh, we raced in fastpath, check if any of the waiters need to - * die. + * die or wound us. */ spin_lock(&lock->base.wait_lock); __ww_mutex_check_waiters(&lock->base, ctx); @@ -682,7 +764,9 @@ __ww_mutex_kill(struct mutex *lock, struct ww_acquire_ctx *ww_ctx) /* - * Check whether we need to kill the transaction for the current lock acquire. + * Check the wound condition for the current lock acquire. + * + * Wound-Wait: If we're wounded, kill ourself. * * Wait-Die: If we're trying to acquire a lock already held by an older * context, kill ourselves. @@ -701,6 +785,13 @@ __ww_mutex_check_kill(struct mutex *lock, struct mutex_waiter *waiter, if (ctx->acquired == 0) return 0; + if (!ctx->is_wait_die) { + if (ctx->wounded) + return __ww_mutex_kill(lock, ctx); + + return 0; + } + if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx)) return __ww_mutex_kill(lock, ctx); @@ -727,7 +818,8 @@ __ww_mutex_check_kill(struct mutex *lock, struct mutex_waiter *waiter, * Waiters without context are interspersed in FIFO order. * * Furthermore, for Wait-Die kill ourself immediately when possible (there are - * older contexts already waiting) to avoid unnecessary waiting. + * older contexts already waiting) to avoid unnecessary waiting and for + * Wound-Wait ensure we wound the owning context when it is younger. */ static inline int __sched __ww_mutex_add_waiter(struct mutex_waiter *waiter, @@ -736,16 +828,21 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, { struct mutex_waiter *cur; struct list_head *pos; + bool is_wait_die; if (!ww_ctx) { - list_add_tail(&waiter->list, &lock->wait_list); + __mutex_add_waiter(lock, waiter, &lock->wait_list); return 0; } + is_wait_die = ww_ctx->is_wait_die; + /* * Add the waiter before the first waiter with a higher stamp. * Waiters without a context are skipped to avoid starving - * them. Wait-Die waiters may die here. + * them. Wait-Die waiters may die here. Wound-Wait waiters + * never die here, but they are sorted in stamp order and + * may wound the lock holder. */ pos = &lock->wait_list; list_for_each_entry_reverse(cur, &lock->wait_list, list) { @@ -758,10 +855,12 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, * is no point in queueing behind it, as we'd have to * die the moment it would acquire the lock. */ - int ret = __ww_mutex_kill(lock, ww_ctx); + if (is_wait_die) { + int ret = __ww_mutex_kill(lock, ww_ctx); - if (ret) - return ret; + if (ret) + return ret; + } break; } @@ -772,7 +871,23 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter, __ww_mutex_die(lock, cur, ww_ctx); } - list_add_tail(&waiter->list, pos); + __mutex_add_waiter(lock, waiter, pos); + + /* + * Wound-Wait: if we're blocking on a mutex owned by a younger context, + * wound that such that we might proceed. + */ + if (!is_wait_die) { + struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); + + /* + * See ww_mutex_set_context_fastpath(). Orders setting + * MUTEX_FLAG_WAITERS vs the ww->ctx load, + * such that either we or the fastpath will wound @ww->ctx. + */ + smp_mb(); + __ww_mutex_wound(lock, ww_ctx, ww->ctx); + } return 0; } @@ -796,6 +911,14 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, if (use_ww_ctx && ww_ctx) { if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) return -EALREADY; + + /* + * Reset the wounded flag after a kill. No other process can + * race and wound us here since they can't have a valid owner + * pointer if we don't have any locks held. + */ + if (ww_ctx->acquired == 0) + ww_ctx->wounded = 0; } preempt_disable(); @@ -829,7 +952,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, if (!use_ww_ctx) { /* add waiting tasks to the end of the waitqueue (FIFO): */ - list_add_tail(&waiter.list, &lock->wait_list); + __mutex_add_waiter(lock, &waiter, &lock->wait_list); + #ifdef CONFIG_DEBUG_MUTEXES waiter.ww_ctx = MUTEX_POISON_WW_CTX; @@ -848,9 +972,6 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, waiter.task = current; - if (__mutex_waiter_is_first(lock, &waiter)) - __mutex_set_flag(lock, MUTEX_FLAG_WAITERS); - set_current_state(state); for (;;) { /* @@ -907,6 +1028,16 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, acquired: __set_current_state(TASK_RUNNING); + if (use_ww_ctx && ww_ctx) { + /* + * Wound-Wait; we stole the lock (!first_waiter), check the + * waiters as anyone might want to wound us. + */ + if (!ww_ctx->is_wait_die && + !__mutex_waiter_is_first(lock, &waiter)) + __ww_mutex_check_waiters(lock, ww_ctx); + } + mutex_remove_waiter(lock, &waiter, current); if (likely(list_empty(&lock->wait_list))) __mutex_clear_flag(lock, MUTEX_FLAGS); diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c index 0e4cd64ad2c0..5b915b370d5a 100644 --- a/kernel/locking/test-ww_mutex.c +++ b/kernel/locking/test-ww_mutex.c @@ -26,7 +26,7 @@ #include #include -static DEFINE_WW_CLASS(ww_class); +static DEFINE_WD_CLASS(ww_class); struct workqueue_struct *wq; struct test_mutex { diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c index b5c1293ce147..1e1bbf171eca 100644 --- a/lib/locking-selftest.c +++ b/lib/locking-selftest.c @@ -29,7 +29,7 @@ */ static unsigned int debug_locks_verbose; -static DEFINE_WW_CLASS(ww_lockdep); +static DEFINE_WD_CLASS(ww_lockdep); static int __init setup_debug_locks_verbose(char *str) { -- cgit From 62cedf3e60af03e47849fe2bd6a03ec179422a8a Mon Sep 17 00:00:00 2001 From: Peter Rosin Date: Fri, 20 Jul 2018 10:39:13 +0200 Subject: locking/rtmutex: Allow specifying a subclass for nested locking Needed for annotating rt_mutex locks. Tested-by: John Sperbeck Signed-off-by: Peter Rosin Signed-off-by: Peter Zijlstra (Intel) Cc: Davidlohr Bueso Cc: Deepa Dinamani Cc: Greg Kroah-Hartman Cc: Linus Torvalds Cc: Peter Chang Cc: Peter Zijlstra Cc: Philippe Ombredanne Cc: Thomas Gleixner Cc: Will Deacon Cc: Wolfram Sang Link: http://lkml.kernel.org/r/20180720083914.1950-2-peda@axentia.se Signed-off-by: Ingo Molnar --- include/linux/rtmutex.h | 7 +++++++ kernel/locking/rtmutex.c | 29 +++++++++++++++++++++++++---- 2 files changed, 32 insertions(+), 4 deletions(-) (limited to 'kernel/locking') diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h index 1b92a28dd672..6fd615a0eea9 100644 --- a/include/linux/rtmutex.h +++ b/include/linux/rtmutex.h @@ -106,7 +106,14 @@ static inline int rt_mutex_is_locked(struct rt_mutex *lock) extern void __rt_mutex_init(struct rt_mutex *lock, const char *name, struct lock_class_key *key); extern void rt_mutex_destroy(struct rt_mutex *lock); +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern void rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass); +#define rt_mutex_lock(lock) rt_mutex_lock_nested(lock, 0) +#else extern void rt_mutex_lock(struct rt_mutex *lock); +#define rt_mutex_lock_nested(lock, subclass) rt_mutex_lock(lock) +#endif + extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); extern int rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout); diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 4f014be7a4b8..2823d4163a37 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1465,6 +1465,29 @@ rt_mutex_fastunlock(struct rt_mutex *lock, rt_mutex_postunlock(&wake_q); } +static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass) +{ + might_sleep(); + + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); +} + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +/** + * rt_mutex_lock_nested - lock a rt_mutex + * + * @lock: the rt_mutex to be locked + * @subclass: the lockdep subclass + */ +void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass) +{ + __rt_mutex_lock(lock, subclass); +} +EXPORT_SYMBOL_GPL(rt_mutex_lock_nested); +#endif + +#ifndef CONFIG_DEBUG_LOCK_ALLOC /** * rt_mutex_lock - lock a rt_mutex * @@ -1472,12 +1495,10 @@ rt_mutex_fastunlock(struct rt_mutex *lock, */ void __sched rt_mutex_lock(struct rt_mutex *lock) { - might_sleep(); - - mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); - rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); + __rt_mutex_lock(lock, 0); } EXPORT_SYMBOL_GPL(rt_mutex_lock); +#endif /** * rt_mutex_lock_interruptible - lock a rt_mutex interruptible -- cgit From 01f38497c6f6525f57eb445887b9ed1867dbd05c Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Mon, 30 Jul 2018 15:24:21 -0700 Subject: lockdep: Use this_cpu_ptr instead of get_cpu_var stats get_cpu_var disables preemption which has the potential to call into the preemption disable trace points causing some complications. There's also no need to disable preemption in uses of get_lock_stats anyway since preempt is already disabled. So lets simplify the code. Link: http://lkml.kernel.org/r/20180730222423.196630-2-joel@joelfernandes.org Suggested-by: Peter Zijlstra Acked-by: Peter Zijlstra Signed-off-by: Joel Fernandes (Google) Signed-off-by: Steven Rostedt (VMware) --- kernel/locking/lockdep.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) (limited to 'kernel/locking') diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 5fa4d3138bf1..fbbb79d5cfa0 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -248,12 +248,7 @@ void clear_lock_stats(struct lock_class *class) static struct lock_class_stats *get_lock_stats(struct lock_class *class) { - return &get_cpu_var(cpu_lock_stats)[class - lock_classes]; -} - -static void put_lock_stats(struct lock_class_stats *stats) -{ - put_cpu_var(cpu_lock_stats); + return &this_cpu_ptr(cpu_lock_stats)[class - lock_classes]; } static void lock_release_holdtime(struct held_lock *hlock) @@ -271,7 +266,6 @@ static void lock_release_holdtime(struct held_lock *hlock) lock_time_inc(&stats->read_holdtime, holdtime); else lock_time_inc(&stats->write_holdtime, holdtime); - put_lock_stats(stats); } #else static inline void lock_release_holdtime(struct held_lock *hlock) @@ -4090,7 +4084,6 @@ __lock_contended(struct lockdep_map *lock, unsigned long ip) stats->contending_point[contending_point]++; if (lock->cpu != smp_processor_id()) stats->bounces[bounce_contended + !!hlock->read]++; - put_lock_stats(stats); } static void @@ -4138,7 +4131,6 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip) } if (lock->cpu != cpu) stats->bounces[bounce_acquired + !!hlock->read]++; - put_lock_stats(stats); lock->cpu = cpu; lock->ip = ip; -- cgit From c3bc8fd637a9623f5c507bd18f9677effbddf584 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Mon, 30 Jul 2018 15:24:23 -0700 Subject: tracing: Centralize preemptirq tracepoints and unify their usage This patch detaches the preemptirq tracepoints from the tracers and keeps it separate. Advantages: * Lockdep and irqsoff event can now run in parallel since they no longer have their own calls. * This unifies the usecase of adding hooks to an irqsoff and irqson event, and a preemptoff and preempton event. 3 users of the events exist: - Lockdep - irqsoff and preemptoff tracers - irqs and preempt trace events The unification cleans up several ifdefs and makes the code in preempt tracer and irqsoff tracers simpler. It gets rid of all the horrific ifdeferry around PROVE_LOCKING and makes configuration of the different users of the tracepoints more easy and understandable. It also gets rid of the time_* function calls from the lockdep hooks used to call into the preemptirq tracer which is not needed anymore. The negative delta in lines of code in this patch is quite large too. In the patch we introduce a new CONFIG option PREEMPTIRQ_TRACEPOINTS as a single point for registering probes onto the tracepoints. With this, the web of config options for preempt/irq toggle tracepoints and its users becomes: PREEMPT_TRACER PREEMPTIRQ_EVENTS IRQSOFF_TRACER PROVE_LOCKING | | \ | | \ (selects) / \ \ (selects) / TRACE_PREEMPT_TOGGLE ----> TRACE_IRQFLAGS \ / \ (depends on) / PREEMPTIRQ_TRACEPOINTS Other than the performance tests mentioned in the previous patch, I also ran the locking API test suite. I verified that all tests cases are passing. I also injected issues by not registering lockdep probes onto the tracepoints and I see failures to confirm that the probes are indeed working. This series + lockdep probes not registered (just to inject errors): [ 0.000000] hard-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] soft-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/12:FAILED|FAILED| ok | [ 0.000000] sirq-safe-A => hirqs-on/21:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + irqs-on/12:FAILED|FAILED| ok | [ 0.000000] soft-safe-A + irqs-on/12:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + irqs-on/21:FAILED|FAILED| ok | [ 0.000000] soft-safe-A + irqs-on/21:FAILED|FAILED| ok | [ 0.000000] hard-safe-A + unsafe-B #1/123: ok | ok | ok | [ 0.000000] soft-safe-A + unsafe-B #1/123: ok | ok | ok | With this series + lockdep probes registered, all locking tests pass: [ 0.000000] hard-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] soft-irqs-on + irq-safe-A/21: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/12: ok | ok | ok | [ 0.000000] sirq-safe-A => hirqs-on/21: ok | ok | ok | [ 0.000000] hard-safe-A + irqs-on/12: ok | ok | ok | [ 0.000000] soft-safe-A + irqs-on/12: ok | ok | ok | [ 0.000000] hard-safe-A + irqs-on/21: ok | ok | ok | [ 0.000000] soft-safe-A + irqs-on/21: ok | ok | ok | [ 0.000000] hard-safe-A + unsafe-B #1/123: ok | ok | ok | [ 0.000000] soft-safe-A + unsafe-B #1/123: ok | ok | ok | Link: http://lkml.kernel.org/r/20180730222423.196630-4-joel@joelfernandes.org Acked-by: Peter Zijlstra (Intel) Reviewed-by: Namhyung Kim Signed-off-by: Joel Fernandes (Google) Signed-off-by: Steven Rostedt (VMware) --- include/linux/ftrace.h | 11 +- include/linux/irqflags.h | 11 +- include/linux/lockdep.h | 8 +- include/linux/preempt.h | 2 +- include/trace/events/preemptirq.h | 23 ++-- init/main.c | 5 +- kernel/locking/lockdep.c | 35 +++--- kernel/sched/core.c | 2 +- kernel/trace/Kconfig | 22 +++- kernel/trace/Makefile | 2 +- kernel/trace/trace_irqsoff.c | 231 ++++++++++---------------------------- kernel/trace/trace_preemptirq.c | 72 ++++++++++++ 12 files changed, 195 insertions(+), 229 deletions(-) create mode 100644 kernel/trace/trace_preemptirq.c (limited to 'kernel/locking') diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 63af5eb0ff46..a397907e8d72 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -701,16 +701,7 @@ static inline unsigned long get_lock_parent_ip(void) return CALLER_ADDR2; } -#ifdef CONFIG_IRQSOFF_TRACER - extern void time_hardirqs_on(unsigned long a0, unsigned long a1); - extern void time_hardirqs_off(unsigned long a0, unsigned long a1); -#else - static inline void time_hardirqs_on(unsigned long a0, unsigned long a1) { } - static inline void time_hardirqs_off(unsigned long a0, unsigned long a1) { } -#endif - -#if defined(CONFIG_PREEMPT_TRACER) || \ - (defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_PREEMPTIRQ_EVENTS)) +#ifdef CONFIG_TRACE_PREEMPT_TOGGLE extern void trace_preempt_on(unsigned long a0, unsigned long a1); extern void trace_preempt_off(unsigned long a0, unsigned long a1); #else diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 9700f00bbc04..50edb9cbbd26 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -15,9 +15,16 @@ #include #include -#ifdef CONFIG_TRACE_IRQFLAGS +/* Currently trace_softirqs_on/off is used only by lockdep */ +#ifdef CONFIG_PROVE_LOCKING extern void trace_softirqs_on(unsigned long ip); extern void trace_softirqs_off(unsigned long ip); +#else +# define trace_softirqs_on(ip) do { } while (0) +# define trace_softirqs_off(ip) do { } while (0) +#endif + +#ifdef CONFIG_TRACE_IRQFLAGS extern void trace_hardirqs_on(void); extern void trace_hardirqs_off(void); # define trace_hardirq_context(p) ((p)->hardirq_context) @@ -43,8 +50,6 @@ do { \ #else # define trace_hardirqs_on() do { } while (0) # define trace_hardirqs_off() do { } while (0) -# define trace_softirqs_on(ip) do { } while (0) -# define trace_softirqs_off(ip) do { } while (0) # define trace_hardirq_context(p) 0 # define trace_softirq_context(p) 0 # define trace_hardirqs_enabled(p) 0 diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 6fc77d4dbdcd..a8113357ceeb 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -266,7 +266,8 @@ struct held_lock { /* * Initialization, self-test and debugging-output methods: */ -extern void lockdep_info(void); +extern void lockdep_init(void); +extern void lockdep_init_early(void); extern void lockdep_reset(void); extern void lockdep_reset_lock(struct lockdep_map *lock); extern void lockdep_free_key_range(void *start, unsigned long size); @@ -406,7 +407,8 @@ static inline void lockdep_on(void) # define lock_downgrade(l, i) do { } while (0) # define lock_set_class(l, n, k, s, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) -# define lockdep_info() do { } while (0) +# define lockdep_init() do { } while (0) +# define lockdep_init_early() do { } while (0) # define lockdep_init_map(lock, name, key, sub) \ do { (void)(name); (void)(key); } while (0) # define lockdep_set_class(lock, key) do { (void)(key); } while (0) @@ -532,7 +534,7 @@ do { \ #endif /* CONFIG_LOCKDEP */ -#ifdef CONFIG_TRACE_IRQFLAGS +#ifdef CONFIG_PROVE_LOCKING extern void print_irqtrace_events(struct task_struct *curr); #else static inline void print_irqtrace_events(struct task_struct *curr) diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 5bd3f151da78..c01813c3fbe9 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -150,7 +150,7 @@ */ #define in_atomic_preempt_off() (preempt_count() != PREEMPT_DISABLE_OFFSET) -#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER) +#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE) extern void preempt_count_add(int val); extern void preempt_count_sub(int val); #define preempt_count_dec_and_test() \ diff --git a/include/trace/events/preemptirq.h b/include/trace/events/preemptirq.h index 9c4eb33c5a1d..9a0d4ceeb166 100644 --- a/include/trace/events/preemptirq.h +++ b/include/trace/events/preemptirq.h @@ -1,4 +1,4 @@ -#ifdef CONFIG_PREEMPTIRQ_EVENTS +#ifdef CONFIG_PREEMPTIRQ_TRACEPOINTS #undef TRACE_SYSTEM #define TRACE_SYSTEM preemptirq @@ -32,7 +32,7 @@ DECLARE_EVENT_CLASS(preemptirq_template, (void *)((unsigned long)(_stext) + __entry->parent_offs)) ); -#ifndef CONFIG_PROVE_LOCKING +#ifdef CONFIG_TRACE_IRQFLAGS DEFINE_EVENT(preemptirq_template, irq_disable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); @@ -40,9 +40,14 @@ DEFINE_EVENT(preemptirq_template, irq_disable, DEFINE_EVENT(preemptirq_template, irq_enable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); +#else +#define trace_irq_enable(...) +#define trace_irq_disable(...) +#define trace_irq_enable_rcuidle(...) +#define trace_irq_disable_rcuidle(...) #endif -#ifdef CONFIG_DEBUG_PREEMPT +#ifdef CONFIG_TRACE_PREEMPT_TOGGLE DEFINE_EVENT(preemptirq_template, preempt_disable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); @@ -50,22 +55,22 @@ DEFINE_EVENT(preemptirq_template, preempt_disable, DEFINE_EVENT(preemptirq_template, preempt_enable, TP_PROTO(unsigned long ip, unsigned long parent_ip), TP_ARGS(ip, parent_ip)); +#else +#define trace_preempt_enable(...) +#define trace_preempt_disable(...) +#define trace_preempt_enable_rcuidle(...) +#define trace_preempt_disable_rcuidle(...) #endif #endif /* _TRACE_PREEMPTIRQ_H */ #include -#endif /* !CONFIG_PREEMPTIRQ_EVENTS */ - -#if !defined(CONFIG_PREEMPTIRQ_EVENTS) || defined(CONFIG_PROVE_LOCKING) +#else /* !CONFIG_PREEMPTIRQ_TRACEPOINTS */ #define trace_irq_enable(...) #define trace_irq_disable(...) #define trace_irq_enable_rcuidle(...) #define trace_irq_disable_rcuidle(...) -#endif - -#if !defined(CONFIG_PREEMPTIRQ_EVENTS) || !defined(CONFIG_DEBUG_PREEMPT) #define trace_preempt_enable(...) #define trace_preempt_disable(...) #define trace_preempt_enable_rcuidle(...) diff --git a/init/main.c b/init/main.c index 3b4ada11ed52..44fe43be84c1 100644 --- a/init/main.c +++ b/init/main.c @@ -648,6 +648,9 @@ asmlinkage __visible void __init start_kernel(void) profile_init(); call_function_init(); WARN(!irqs_disabled(), "Interrupts were enabled early\n"); + + lockdep_init_early(); + early_boot_irqs_disabled = false; local_irq_enable(); @@ -663,7 +666,7 @@ asmlinkage __visible void __init start_kernel(void) panic("Too many boot %s vars at `%s'", panic_later, panic_param); - lockdep_info(); + lockdep_init(); /* * Need to run this when irqs are enabled, because it wants diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index fbbb79d5cfa0..03bfaeb9f4e6 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -55,6 +55,7 @@ #include "lockdep_internals.h" +#include #define CREATE_TRACE_POINTS #include @@ -2839,10 +2840,9 @@ static void __trace_hardirqs_on_caller(unsigned long ip) debug_atomic_inc(hardirqs_on_events); } -__visible void trace_hardirqs_on_caller(unsigned long ip) +static void lockdep_hardirqs_on(void *none, unsigned long ignore, + unsigned long ip) { - time_hardirqs_on(CALLER_ADDR0, ip); - if (unlikely(!debug_locks || current->lockdep_recursion)) return; @@ -2881,23 +2881,15 @@ __visible void trace_hardirqs_on_caller(unsigned long ip) __trace_hardirqs_on_caller(ip); current->lockdep_recursion = 0; } -EXPORT_SYMBOL(trace_hardirqs_on_caller); - -void trace_hardirqs_on(void) -{ - trace_hardirqs_on_caller(CALLER_ADDR0); -} -EXPORT_SYMBOL(trace_hardirqs_on); /* * Hardirqs were disabled: */ -__visible void trace_hardirqs_off_caller(unsigned long ip) +static void lockdep_hardirqs_off(void *none, unsigned long ignore, + unsigned long ip) { struct task_struct *curr = current; - time_hardirqs_off(CALLER_ADDR0, ip); - if (unlikely(!debug_locks || current->lockdep_recursion)) return; @@ -2919,13 +2911,6 @@ __visible void trace_hardirqs_off_caller(unsigned long ip) } else debug_atomic_inc(redundant_hardirqs_off); } -EXPORT_SYMBOL(trace_hardirqs_off_caller); - -void trace_hardirqs_off(void) -{ - trace_hardirqs_off_caller(CALLER_ADDR0); -} -EXPORT_SYMBOL(trace_hardirqs_off); /* * Softirqs will be enabled: @@ -4330,7 +4315,15 @@ out_restore: raw_local_irq_restore(flags); } -void __init lockdep_info(void) +void __init lockdep_init_early(void) +{ +#ifdef CONFIG_PROVE_LOCKING + register_trace_prio_irq_disable(lockdep_hardirqs_off, NULL, INT_MAX); + register_trace_prio_irq_enable(lockdep_hardirqs_on, NULL, INT_MIN); +#endif +} + +void __init lockdep_init(void) { printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n"); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index fe365c9a08e9..5de1a4343424 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3189,7 +3189,7 @@ static inline void sched_tick_stop(int cpu) { } #endif #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ - defined(CONFIG_PREEMPT_TRACER)) + defined(CONFIG_TRACE_PREEMPT_TOGGLE)) /* * If the value passed in is equal to the current preempt count * then we just disabled preemption. Start timing the latency. diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 4d4eb15cc7fd..036cec1fcd24 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -82,6 +82,15 @@ config RING_BUFFER_ALLOW_SWAP Allow the use of ring_buffer_swap_cpu. Adds a very slight overhead to tracing when enabled. +config PREEMPTIRQ_TRACEPOINTS + bool + depends on TRACE_PREEMPT_TOGGLE || TRACE_IRQFLAGS + select TRACING + default y + help + Create preempt/irq toggle tracepoints if needed, so that other parts + of the kernel can use them to generate or add hooks to them. + # All tracer options should select GENERIC_TRACER. For those options that are # enabled by all tracers (context switch and event tracer) they select TRACING. # This allows those options to appear when no other tracer is selected. But the @@ -155,18 +164,20 @@ config FUNCTION_GRAPH_TRACER the return value. This is done by setting the current return address on the current task structure into a stack of calls. +config TRACE_PREEMPT_TOGGLE + bool + help + Enables hooks which will be called when preemption is first disabled, + and last enabled. config PREEMPTIRQ_EVENTS bool "Enable trace events for preempt and irq disable/enable" select TRACE_IRQFLAGS - depends on DEBUG_PREEMPT || !PROVE_LOCKING - depends on TRACING + select TRACE_PREEMPT_TOGGLE if PREEMPT + select GENERIC_TRACER default n help Enable tracing of disable and enable events for preemption and irqs. - For tracing preempt disable/enable events, DEBUG_PREEMPT must be - enabled. For tracing irq disable/enable events, PROVE_LOCKING must - be disabled. config IRQSOFF_TRACER bool "Interrupts-off Latency Tracer" @@ -203,6 +214,7 @@ config PREEMPT_TRACER select RING_BUFFER_ALLOW_SWAP select TRACER_SNAPSHOT select TRACER_SNAPSHOT_PER_CPU_SWAP + select TRACE_PREEMPT_TOGGLE help This option measures the time spent in preemption-off critical sections, with microsecond accuracy. diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile index 81902a79e049..98d53b39a8ee 100644 --- a/kernel/trace/Makefile +++ b/kernel/trace/Makefile @@ -41,7 +41,7 @@ obj-$(CONFIG_TRACING_MAP) += tracing_map.o obj-$(CONFIG_PREEMPTIRQ_DELAY_TEST) += preemptirq_delay_test.o obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o obj-$(CONFIG_FUNCTION_TRACER) += trace_functions.o -obj-$(CONFIG_PREEMPTIRQ_EVENTS) += trace_irqsoff.o +obj-$(CONFIG_PREEMPTIRQ_TRACEPOINTS) += trace_preemptirq.o obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index f8daa754cce2..770cd30cda40 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -16,7 +16,6 @@ #include "trace.h" -#define CREATE_TRACE_POINTS #include #if defined(CONFIG_IRQSOFF_TRACER) || defined(CONFIG_PREEMPT_TRACER) @@ -450,66 +449,6 @@ void stop_critical_timings(void) } EXPORT_SYMBOL_GPL(stop_critical_timings); -#ifdef CONFIG_IRQSOFF_TRACER -#ifdef CONFIG_PROVE_LOCKING -void time_hardirqs_on(unsigned long a0, unsigned long a1) -{ - if (!preempt_trace() && irq_trace()) - stop_critical_timing(a0, a1); -} - -void time_hardirqs_off(unsigned long a0, unsigned long a1) -{ - if (!preempt_trace() && irq_trace()) - start_critical_timing(a0, a1); -} - -#else /* !CONFIG_PROVE_LOCKING */ - -/* - * We are only interested in hardirq on/off events: - */ -static inline void tracer_hardirqs_on(void) -{ - if (!preempt_trace() && irq_trace()) - stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); -} - -static inline void tracer_hardirqs_off(void) -{ - if (!preempt_trace() && irq_trace()) - start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); -} - -static inline void tracer_hardirqs_on_caller(unsigned long caller_addr) -{ - if (!preempt_trace() && irq_trace()) - stop_critical_timing(CALLER_ADDR0, caller_addr); -} - -static inline void tracer_hardirqs_off_caller(unsigned long caller_addr) -{ - if (!preempt_trace() && irq_trace()) - start_critical_timing(CALLER_ADDR0, caller_addr); -} - -#endif /* CONFIG_PROVE_LOCKING */ -#endif /* CONFIG_IRQSOFF_TRACER */ - -#ifdef CONFIG_PREEMPT_TRACER -static inline void tracer_preempt_on(unsigned long a0, unsigned long a1) -{ - if (preempt_trace() && !irq_trace()) - stop_critical_timing(a0, a1); -} - -static inline void tracer_preempt_off(unsigned long a0, unsigned long a1) -{ - if (preempt_trace() && !irq_trace()) - start_critical_timing(a0, a1); -} -#endif /* CONFIG_PREEMPT_TRACER */ - #ifdef CONFIG_FUNCTION_TRACER static bool function_enabled; @@ -659,15 +598,34 @@ static void irqsoff_tracer_stop(struct trace_array *tr) } #ifdef CONFIG_IRQSOFF_TRACER +/* + * We are only interested in hardirq on/off events: + */ +static void tracer_hardirqs_on(void *none, unsigned long a0, unsigned long a1) +{ + if (!preempt_trace() && irq_trace()) + stop_critical_timing(a0, a1); +} + +static void tracer_hardirqs_off(void *none, unsigned long a0, unsigned long a1) +{ + if (!preempt_trace() && irq_trace()) + start_critical_timing(a0, a1); +} + static int irqsoff_tracer_init(struct trace_array *tr) { trace_type = TRACER_IRQS_OFF; + register_trace_irq_disable(tracer_hardirqs_off, NULL); + register_trace_irq_enable(tracer_hardirqs_on, NULL); return __irqsoff_tracer_init(tr); } static void irqsoff_tracer_reset(struct trace_array *tr) { + unregister_trace_irq_disable(tracer_hardirqs_off, NULL); + unregister_trace_irq_enable(tracer_hardirqs_on, NULL); __irqsoff_tracer_reset(tr); } @@ -690,21 +648,34 @@ static struct tracer irqsoff_tracer __read_mostly = .allow_instances = true, .use_max_tr = true, }; -# define register_irqsoff(trace) register_tracer(&trace) -#else -# define register_irqsoff(trace) do { } while (0) -#endif +#endif /* CONFIG_IRQSOFF_TRACER */ #ifdef CONFIG_PREEMPT_TRACER +static void tracer_preempt_on(void *none, unsigned long a0, unsigned long a1) +{ + if (preempt_trace() && !irq_trace()) + stop_critical_timing(a0, a1); +} + +static void tracer_preempt_off(void *none, unsigned long a0, unsigned long a1) +{ + if (preempt_trace() && !irq_trace()) + start_critical_timing(a0, a1); +} + static int preemptoff_tracer_init(struct trace_array *tr) { trace_type = TRACER_PREEMPT_OFF; + register_trace_preempt_disable(tracer_preempt_off, NULL); + register_trace_preempt_enable(tracer_preempt_on, NULL); return __irqsoff_tracer_init(tr); } static void preemptoff_tracer_reset(struct trace_array *tr) { + unregister_trace_preempt_disable(tracer_preempt_off, NULL); + unregister_trace_preempt_enable(tracer_preempt_on, NULL); __irqsoff_tracer_reset(tr); } @@ -727,23 +698,29 @@ static struct tracer preemptoff_tracer __read_mostly = .allow_instances = true, .use_max_tr = true, }; -# define register_preemptoff(trace) register_tracer(&trace) -#else -# define register_preemptoff(trace) do { } while (0) -#endif +#endif /* CONFIG_PREEMPT_TRACER */ -#if defined(CONFIG_IRQSOFF_TRACER) && \ - defined(CONFIG_PREEMPT_TRACER) +#if defined(CONFIG_IRQSOFF_TRACER) && defined(CONFIG_PREEMPT_TRACER) static int preemptirqsoff_tracer_init(struct trace_array *tr) { trace_type = TRACER_IRQS_OFF | TRACER_PREEMPT_OFF; + register_trace_irq_disable(tracer_hardirqs_off, NULL); + register_trace_irq_enable(tracer_hardirqs_on, NULL); + register_trace_preempt_disable(tracer_preempt_off, NULL); + register_trace_preempt_enable(tracer_preempt_on, NULL); + return __irqsoff_tracer_init(tr); } static void preemptirqsoff_tracer_reset(struct trace_array *tr) { + unregister_trace_irq_disable(tracer_hardirqs_off, NULL); + unregister_trace_irq_enable(tracer_hardirqs_on, NULL); + unregister_trace_preempt_disable(tracer_preempt_off, NULL); + unregister_trace_preempt_enable(tracer_preempt_on, NULL); + __irqsoff_tracer_reset(tr); } @@ -766,115 +743,21 @@ static struct tracer preemptirqsoff_tracer __read_mostly = .allow_instances = true, .use_max_tr = true, }; - -# define register_preemptirqsoff(trace) register_tracer(&trace) -#else -# define register_preemptirqsoff(trace) do { } while (0) #endif __init static int init_irqsoff_tracer(void) { - register_irqsoff(irqsoff_tracer); - register_preemptoff(preemptoff_tracer); - register_preemptirqsoff(preemptirqsoff_tracer); - - return 0; -} -core_initcall(init_irqsoff_tracer); -#endif /* IRQSOFF_TRACER || PREEMPTOFF_TRACER */ - -#ifndef CONFIG_IRQSOFF_TRACER -static inline void tracer_hardirqs_on(void) { } -static inline void tracer_hardirqs_off(void) { } -static inline void tracer_hardirqs_on_caller(unsigned long caller_addr) { } -static inline void tracer_hardirqs_off_caller(unsigned long caller_addr) { } +#ifdef CONFIG_IRQSOFF_TRACER + register_tracer(&irqsoff_tracer); #endif - -#ifndef CONFIG_PREEMPT_TRACER -static inline void tracer_preempt_on(unsigned long a0, unsigned long a1) { } -static inline void tracer_preempt_off(unsigned long a0, unsigned long a1) { } +#ifdef CONFIG_PREEMPT_TRACER + register_tracer(&preemptoff_tracer); #endif - -#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PROVE_LOCKING) -/* Per-cpu variable to prevent redundant calls when IRQs already off */ -static DEFINE_PER_CPU(int, tracing_irq_cpu); - -void trace_hardirqs_on(void) -{ - if (!this_cpu_read(tracing_irq_cpu)) - return; - - trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); - tracer_hardirqs_on(); - - this_cpu_write(tracing_irq_cpu, 0); -} -EXPORT_SYMBOL(trace_hardirqs_on); - -void trace_hardirqs_off(void) -{ - if (this_cpu_read(tracing_irq_cpu)) - return; - - this_cpu_write(tracing_irq_cpu, 1); - - trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); - tracer_hardirqs_off(); -} -EXPORT_SYMBOL(trace_hardirqs_off); - -__visible void trace_hardirqs_on_caller(unsigned long caller_addr) -{ - if (!this_cpu_read(tracing_irq_cpu)) - return; - - trace_irq_enable_rcuidle(CALLER_ADDR0, caller_addr); - tracer_hardirqs_on_caller(caller_addr); - - this_cpu_write(tracing_irq_cpu, 0); -} -EXPORT_SYMBOL(trace_hardirqs_on_caller); - -__visible void trace_hardirqs_off_caller(unsigned long caller_addr) -{ - if (this_cpu_read(tracing_irq_cpu)) - return; - - this_cpu_write(tracing_irq_cpu, 1); - - trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr); - tracer_hardirqs_off_caller(caller_addr); -} -EXPORT_SYMBOL(trace_hardirqs_off_caller); - -/* - * Stubs: - */ - -void trace_softirqs_on(unsigned long ip) -{ -} - -void trace_softirqs_off(unsigned long ip) -{ -} - -inline void print_irqtrace_events(struct task_struct *curr) -{ -} +#if defined(CONFIG_IRQSOFF_TRACER) && defined(CONFIG_PREEMPT_TRACER) + register_tracer(&preemptirqsoff_tracer); #endif -#if defined(CONFIG_PREEMPT_TRACER) || \ - (defined(CONFIG_DEBUG_PREEMPT) && defined(CONFIG_PREEMPTIRQ_EVENTS)) -void trace_preempt_on(unsigned long a0, unsigned long a1) -{ - trace_preempt_enable_rcuidle(a0, a1); - tracer_preempt_on(a0, a1); -} - -void trace_preempt_off(unsigned long a0, unsigned long a1) -{ - trace_preempt_disable_rcuidle(a0, a1); - tracer_preempt_off(a0, a1); + return 0; } -#endif +core_initcall(init_irqsoff_tracer); +#endif /* IRQSOFF_TRACER || PREEMPTOFF_TRACER */ diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c new file mode 100644 index 000000000000..e76b78bf258e --- /dev/null +++ b/kernel/trace/trace_preemptirq.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * preemptoff and irqoff tracepoints + * + * Copyright (C) Joel Fernandes (Google) + */ + +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include + +#ifdef CONFIG_TRACE_IRQFLAGS +/* Per-cpu variable to prevent redundant calls when IRQs already off */ +static DEFINE_PER_CPU(int, tracing_irq_cpu); + +void trace_hardirqs_on(void) +{ + if (!this_cpu_read(tracing_irq_cpu)) + return; + + trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); + this_cpu_write(tracing_irq_cpu, 0); +} +EXPORT_SYMBOL(trace_hardirqs_on); + +void trace_hardirqs_off(void) +{ + if (this_cpu_read(tracing_irq_cpu)) + return; + + this_cpu_write(tracing_irq_cpu, 1); + trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); +} +EXPORT_SYMBOL(trace_hardirqs_off); + +__visible void trace_hardirqs_on_caller(unsigned long caller_addr) +{ + if (!this_cpu_read(tracing_irq_cpu)) + return; + + trace_irq_enable_rcuidle(CALLER_ADDR0, caller_addr); + this_cpu_write(tracing_irq_cpu, 0); +} +EXPORT_SYMBOL(trace_hardirqs_on_caller); + +__visible void trace_hardirqs_off_caller(unsigned long caller_addr) +{ + if (this_cpu_read(tracing_irq_cpu)) + return; + + this_cpu_write(tracing_irq_cpu, 1); + trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr); +} +EXPORT_SYMBOL(trace_hardirqs_off_caller); +#endif /* CONFIG_TRACE_IRQFLAGS */ + +#ifdef CONFIG_TRACE_PREEMPT_TOGGLE + +void trace_preempt_on(unsigned long a0, unsigned long a1) +{ + trace_preempt_enable_rcuidle(a0, a1); +} + +void trace_preempt_off(unsigned long a0, unsigned long a1) +{ + trace_preempt_disable_rcuidle(a0, a1); +} +#endif -- cgit From bff1b208a5d1dbb2355822ef859edcb9be0379e4 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (VMware)" Date: Mon, 6 Aug 2018 15:50:58 -0400 Subject: tracing: Partial revert of "tracing: Centralize preemptirq tracepoints and unify their usage" Joel Fernandes created a nice patch that cleaned up the duplicate hooks used by lockdep and irqsoff latency tracer. It made both use tracepoints. But it caused lockdep to trigger several false positives. We have not figured out why yet, but removing lockdep from using the trace event hooks and just call its helper functions directly (like it use to), makes the problem go away. This is a partial revert of the clean up patch c3bc8fd637a9 ("tracing: Centralize preemptirq tracepoints and unify their usage") that adds direct calls for lockdep, but also keeps most of the clean up done to get rid of the horrible preprocessor if statements. Link: http://lkml.kernel.org/r/20180806155058.5ee875f4@gandalf.local.home Cc: Peter Zijlstra Reviewed-by: Joel Fernandes (Google) Fixes: c3bc8fd637a9 ("tracing: Centralize preemptirq tracepoints and unify their usage") Signed-off-by: Steven Rostedt (VMware) --- include/linux/irqflags.h | 8 ++++++-- include/linux/lockdep.h | 2 -- init/main.c | 2 -- kernel/locking/lockdep.c | 14 ++------------ kernel/trace/trace_preemptirq.c | 36 ++++++++++++++++++++---------------- 5 files changed, 28 insertions(+), 34 deletions(-) (limited to 'kernel/locking') diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 50edb9cbbd26..21619c92c377 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -19,9 +19,13 @@ #ifdef CONFIG_PROVE_LOCKING extern void trace_softirqs_on(unsigned long ip); extern void trace_softirqs_off(unsigned long ip); + extern void lockdep_hardirqs_on(unsigned long ip); + extern void lockdep_hardirqs_off(unsigned long ip); #else -# define trace_softirqs_on(ip) do { } while (0) -# define trace_softirqs_off(ip) do { } while (0) + static inline void trace_softirqs_on(unsigned long ip) { } + static inline void trace_softirqs_off(unsigned long ip) { } + static inline void lockdep_hardirqs_on(unsigned long ip) { } + static inline void lockdep_hardirqs_off(unsigned long ip) { } #endif #ifdef CONFIG_TRACE_IRQFLAGS diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index a8113357ceeb..b0d0b51c4d85 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -267,7 +267,6 @@ struct held_lock { * Initialization, self-test and debugging-output methods: */ extern void lockdep_init(void); -extern void lockdep_init_early(void); extern void lockdep_reset(void); extern void lockdep_reset_lock(struct lockdep_map *lock); extern void lockdep_free_key_range(void *start, unsigned long size); @@ -408,7 +407,6 @@ static inline void lockdep_on(void) # define lock_set_class(l, n, k, s, i) do { } while (0) # define lock_set_subclass(l, s, i) do { } while (0) # define lockdep_init() do { } while (0) -# define lockdep_init_early() do { } while (0) # define lockdep_init_map(lock, name, key, sub) \ do { (void)(name); (void)(key); } while (0) # define lockdep_set_class(lock, key) do { (void)(key); } while (0) diff --git a/init/main.c b/init/main.c index 44fe43be84c1..5d42e577643a 100644 --- a/init/main.c +++ b/init/main.c @@ -649,8 +649,6 @@ asmlinkage __visible void __init start_kernel(void) call_function_init(); WARN(!irqs_disabled(), "Interrupts were enabled early\n"); - lockdep_init_early(); - early_boot_irqs_disabled = false; local_irq_enable(); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 03bfaeb9f4e6..e406c5fdb41e 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -2840,8 +2840,7 @@ static void __trace_hardirqs_on_caller(unsigned long ip) debug_atomic_inc(hardirqs_on_events); } -static void lockdep_hardirqs_on(void *none, unsigned long ignore, - unsigned long ip) +void lockdep_hardirqs_on(unsigned long ip) { if (unlikely(!debug_locks || current->lockdep_recursion)) return; @@ -2885,8 +2884,7 @@ static void lockdep_hardirqs_on(void *none, unsigned long ignore, /* * Hardirqs were disabled: */ -static void lockdep_hardirqs_off(void *none, unsigned long ignore, - unsigned long ip) +void lockdep_hardirqs_off(unsigned long ip) { struct task_struct *curr = current; @@ -4315,14 +4313,6 @@ out_restore: raw_local_irq_restore(flags); } -void __init lockdep_init_early(void) -{ -#ifdef CONFIG_PROVE_LOCKING - register_trace_prio_irq_disable(lockdep_hardirqs_off, NULL, INT_MAX); - register_trace_prio_irq_enable(lockdep_hardirqs_on, NULL, INT_MIN); -#endif -} - void __init lockdep_init(void) { printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n"); diff --git a/kernel/trace/trace_preemptirq.c b/kernel/trace/trace_preemptirq.c index e76b78bf258e..fa656b25f427 100644 --- a/kernel/trace/trace_preemptirq.c +++ b/kernel/trace/trace_preemptirq.c @@ -19,41 +19,45 @@ static DEFINE_PER_CPU(int, tracing_irq_cpu); void trace_hardirqs_on(void) { - if (!this_cpu_read(tracing_irq_cpu)) - return; + if (this_cpu_read(tracing_irq_cpu)) { + trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); + this_cpu_write(tracing_irq_cpu, 0); + } - trace_irq_enable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); - this_cpu_write(tracing_irq_cpu, 0); + lockdep_hardirqs_on(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_on); void trace_hardirqs_off(void) { - if (this_cpu_read(tracing_irq_cpu)) - return; + if (!this_cpu_read(tracing_irq_cpu)) { + this_cpu_write(tracing_irq_cpu, 1); + trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); + } - this_cpu_write(tracing_irq_cpu, 1); - trace_irq_disable_rcuidle(CALLER_ADDR0, CALLER_ADDR1); + lockdep_hardirqs_off(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_off); __visible void trace_hardirqs_on_caller(unsigned long caller_addr) { - if (!this_cpu_read(tracing_irq_cpu)) - return; + if (this_cpu_read(tracing_irq_cpu)) { + trace_irq_enable_rcuidle(CALLER_ADDR0, caller_addr); + this_cpu_write(tracing_irq_cpu, 0); + } - trace_irq_enable_rcuidle(CALLER_ADDR0, caller_addr); - this_cpu_write(tracing_irq_cpu, 0); + lockdep_hardirqs_on(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_on_caller); __visible void trace_hardirqs_off_caller(unsigned long caller_addr) { - if (this_cpu_read(tracing_irq_cpu)) - return; + if (!this_cpu_read(tracing_irq_cpu)) { + this_cpu_write(tracing_irq_cpu, 1); + trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr); + } - this_cpu_write(tracing_irq_cpu, 1); - trace_irq_disable_rcuidle(CALLER_ADDR0, caller_addr); + lockdep_hardirqs_off(CALLER_ADDR0); } EXPORT_SYMBOL(trace_hardirqs_off_caller); #endif /* CONFIG_TRACE_IRQFLAGS */ -- cgit