diff options
Diffstat (limited to 'kernel/locking')
| -rw-r--r-- | kernel/locking/Makefile | 1 | ||||
| -rw-r--r-- | kernel/locking/lglock.c | 111 | ||||
| -rw-r--r-- | kernel/locking/lockdep.c | 141 | ||||
| -rw-r--r-- | kernel/locking/lockdep_internals.h | 20 | ||||
| -rw-r--r-- | kernel/locking/lockdep_proc.c | 2 | ||||
| -rw-r--r-- | kernel/locking/mcs_spinlock.h | 4 | ||||
| -rw-r--r-- | kernel/locking/mutex-debug.c | 13 | ||||
| -rw-r--r-- | kernel/locking/mutex-debug.h | 10 | ||||
| -rw-r--r-- | kernel/locking/mutex.c | 588 | ||||
| -rw-r--r-- | kernel/locking/mutex.h | 26 | ||||
| -rw-r--r-- | kernel/locking/osq_lock.c | 15 | ||||
| -rw-r--r-- | kernel/locking/percpu-rwsem.c | 228 | ||||
| -rw-r--r-- | kernel/locking/qrwlock.c | 6 | ||||
| -rw-r--r-- | kernel/locking/qspinlock_paravirt.h | 26 | ||||
| -rw-r--r-- | kernel/locking/qspinlock_stat.h | 16 | ||||
| -rw-r--r-- | kernel/locking/rtmutex.c | 86 | ||||
| -rw-r--r-- | kernel/locking/rtmutex_common.h | 6 | ||||
| -rw-r--r-- | kernel/locking/rwsem-xadd.c | 120 |
18 files changed, 735 insertions, 684 deletions
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile index 31322a4275cd..6f88e352cd4f 100644 --- a/kernel/locking/Makefile +++ b/kernel/locking/Makefile @@ -18,7 +18,6 @@ obj-$(CONFIG_LOCKDEP) += lockdep_proc.o endif obj-$(CONFIG_SMP) += spinlock.o obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o -obj-$(CONFIG_SMP) += lglock.o obj-$(CONFIG_PROVE_LOCKING) += spinlock.o obj-$(CONFIG_QUEUED_SPINLOCKS) += qspinlock.o obj-$(CONFIG_RT_MUTEXES) += rtmutex.o diff --git a/kernel/locking/lglock.c b/kernel/locking/lglock.c deleted file mode 100644 index 951cfcd10b4a..000000000000 --- a/kernel/locking/lglock.c +++ /dev/null @@ -1,111 +0,0 @@ -/* See include/linux/lglock.h for description */ -#include <linux/module.h> -#include <linux/lglock.h> -#include <linux/cpu.h> -#include <linux/string.h> - -/* - * Note there is no uninit, so lglocks cannot be defined in - * modules (but it's fine to use them from there) - * Could be added though, just undo lg_lock_init - */ - -void lg_lock_init(struct lglock *lg, char *name) -{ - LOCKDEP_INIT_MAP(&lg->lock_dep_map, name, &lg->lock_key, 0); -} -EXPORT_SYMBOL(lg_lock_init); - -void lg_local_lock(struct lglock *lg) -{ - arch_spinlock_t *lock; - - preempt_disable(); - lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); - lock = this_cpu_ptr(lg->lock); - arch_spin_lock(lock); -} -EXPORT_SYMBOL(lg_local_lock); - -void lg_local_unlock(struct lglock *lg) -{ - arch_spinlock_t *lock; - - lock_release(&lg->lock_dep_map, 1, _RET_IP_); - lock = this_cpu_ptr(lg->lock); - arch_spin_unlock(lock); - preempt_enable(); -} -EXPORT_SYMBOL(lg_local_unlock); - -void lg_local_lock_cpu(struct lglock *lg, int cpu) -{ - arch_spinlock_t *lock; - - preempt_disable(); - lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); - lock = per_cpu_ptr(lg->lock, cpu); - arch_spin_lock(lock); -} -EXPORT_SYMBOL(lg_local_lock_cpu); - -void lg_local_unlock_cpu(struct lglock *lg, int cpu) -{ - arch_spinlock_t *lock; - - lock_release(&lg->lock_dep_map, 1, _RET_IP_); - lock = per_cpu_ptr(lg->lock, cpu); - arch_spin_unlock(lock); - preempt_enable(); -} -EXPORT_SYMBOL(lg_local_unlock_cpu); - -void lg_double_lock(struct lglock *lg, int cpu1, int cpu2) -{ - BUG_ON(cpu1 == cpu2); - - /* lock in cpu order, just like lg_global_lock */ - if (cpu2 < cpu1) - swap(cpu1, cpu2); - - preempt_disable(); - lock_acquire_shared(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); - arch_spin_lock(per_cpu_ptr(lg->lock, cpu1)); - arch_spin_lock(per_cpu_ptr(lg->lock, cpu2)); -} - -void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2) -{ - lock_release(&lg->lock_dep_map, 1, _RET_IP_); - arch_spin_unlock(per_cpu_ptr(lg->lock, cpu1)); - arch_spin_unlock(per_cpu_ptr(lg->lock, cpu2)); - preempt_enable(); -} - -void lg_global_lock(struct lglock *lg) -{ - int i; - - preempt_disable(); - lock_acquire_exclusive(&lg->lock_dep_map, 0, 0, NULL, _RET_IP_); - for_each_possible_cpu(i) { - arch_spinlock_t *lock; - lock = per_cpu_ptr(lg->lock, i); - arch_spin_lock(lock); - } -} -EXPORT_SYMBOL(lg_global_lock); - -void lg_global_unlock(struct lglock *lg) -{ - int i; - - lock_release(&lg->lock_dep_map, 1, _RET_IP_); - for_each_possible_cpu(i) { - arch_spinlock_t *lock; - lock = per_cpu_ptr(lg->lock, i); - arch_spin_unlock(lock); - } - preempt_enable(); -} -EXPORT_SYMBOL(lg_global_unlock); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 589d763a49b3..7c38f8f3d97b 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -506,13 +506,13 @@ static void __print_lock_name(struct lock_class *class) name = class->name; if (!name) { name = __get_key_name(class->key, str); - printk("%s", name); + printk(KERN_CONT "%s", name); } else { - printk("%s", name); + printk(KERN_CONT "%s", name); if (class->name_version > 1) - printk("#%d", class->name_version); + printk(KERN_CONT "#%d", class->name_version); if (class->subclass) - printk("/%d", class->subclass); + printk(KERN_CONT "/%d", class->subclass); } } @@ -522,9 +522,9 @@ static void print_lock_name(struct lock_class *class) get_usage_chars(class, usage); - printk(" ("); + printk(KERN_CONT " ("); __print_lock_name(class); - printk("){%s}", usage); + printk(KERN_CONT "){%s}", usage); } static void print_lockdep_cache(struct lockdep_map *lock) @@ -536,7 +536,7 @@ static void print_lockdep_cache(struct lockdep_map *lock) if (!name) name = __get_key_name(lock->key->subkeys, str); - printk("%s", name); + printk(KERN_CONT "%s", name); } static void print_lock(struct held_lock *hlock) @@ -551,13 +551,13 @@ static void print_lock(struct held_lock *hlock) barrier(); if (!class_idx || (class_idx - 1) >= MAX_LOCKDEP_KEYS) { - printk("<RELEASED>\n"); + printk(KERN_CONT "<RELEASED>\n"); return; } print_lock_name(lock_classes + class_idx - 1); - printk(", at: "); - print_ip_sym(hlock->acquire_ip); + printk(KERN_CONT ", at: [<%p>] %pS\n", + (void *)hlock->acquire_ip, (void *)hlock->acquire_ip); } static void lockdep_print_held_locks(struct task_struct *curr) @@ -792,8 +792,8 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) printk("\nnew class %p: %s", class->key, class->name); if (class->name_version > 1) - printk("#%d", class->name_version); - printk("\n"); + printk(KERN_CONT "#%d", class->name_version); + printk(KERN_CONT "\n"); dump_stack(); if (!graph_lock()) { @@ -840,9 +840,9 @@ static struct lock_list *alloc_list_entry(void) /* * Add a new dependency to the head of the list: */ -static int add_lock_to_list(struct lock_class *class, struct lock_class *this, - struct list_head *head, unsigned long ip, - int distance, struct stack_trace *trace) +static int add_lock_to_list(struct lock_class *this, struct list_head *head, + unsigned long ip, int distance, + struct stack_trace *trace) { struct lock_list *entry; /* @@ -1071,7 +1071,7 @@ print_circular_bug_entry(struct lock_list *target, int depth) return 0; printk("\n-> #%u", depth); print_lock_name(target->class); - printk(":\n"); + printk(KERN_CONT ":\n"); print_stack_trace(&target->trace, 6); return 0; @@ -1102,11 +1102,11 @@ print_circular_lock_scenario(struct held_lock *src, if (parent != source) { printk("Chain exists of:\n "); __print_lock_name(source); - printk(" --> "); + printk(KERN_CONT " --> "); __print_lock_name(parent); - printk(" --> "); + printk(KERN_CONT " --> "); __print_lock_name(target); - printk("\n\n"); + printk(KERN_CONT "\n\n"); } printk(" Possible unsafe locking scenario:\n\n"); @@ -1114,16 +1114,16 @@ print_circular_lock_scenario(struct held_lock *src, printk(" ---- ----\n"); printk(" lock("); __print_lock_name(target); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" lock("); __print_lock_name(parent); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" lock("); __print_lock_name(target); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" lock("); __print_lock_name(source); - printk(");\n"); + printk(KERN_CONT ");\n"); printk("\n *** DEADLOCK ***\n\n"); } @@ -1359,22 +1359,22 @@ static void print_lock_class_header(struct lock_class *class, int depth) printk("%*s->", depth, ""); print_lock_name(class); - printk(" ops: %lu", class->ops); - printk(" {\n"); + printk(KERN_CONT " ops: %lu", class->ops); + printk(KERN_CONT " {\n"); for (bit = 0; bit < LOCK_USAGE_STATES; bit++) { if (class->usage_mask & (1 << bit)) { int len = depth; len += printk("%*s %s", depth, "", usage_str[bit]); - len += printk(" at:\n"); + len += printk(KERN_CONT " at:\n"); print_stack_trace(class->usage_traces + bit, len); } } printk("%*s }\n", depth, ""); - printk("%*s ... key at: ",depth,""); - print_ip_sym((unsigned long)class->key); + printk("%*s ... key at: [<%p>] %pS\n", + depth, "", class->key, class->key); } /* @@ -1437,11 +1437,11 @@ print_irq_lock_scenario(struct lock_list *safe_entry, if (middle_class != unsafe_class) { printk("Chain exists of:\n "); __print_lock_name(safe_class); - printk(" --> "); + printk(KERN_CONT " --> "); __print_lock_name(middle_class); - printk(" --> "); + printk(KERN_CONT " --> "); __print_lock_name(unsafe_class); - printk("\n\n"); + printk(KERN_CONT "\n\n"); } printk(" Possible interrupt unsafe locking scenario:\n\n"); @@ -1449,18 +1449,18 @@ print_irq_lock_scenario(struct lock_list *safe_entry, printk(" ---- ----\n"); printk(" lock("); __print_lock_name(unsafe_class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" local_irq_disable();\n"); printk(" lock("); __print_lock_name(safe_class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" lock("); __print_lock_name(middle_class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" <Interrupt>\n"); printk(" lock("); __print_lock_name(safe_class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk("\n *** DEADLOCK ***\n\n"); } @@ -1497,9 +1497,9 @@ print_bad_irq_dependency(struct task_struct *curr, print_lock(prev); printk("which would create a new lock dependency:\n"); print_lock_name(hlock_class(prev)); - printk(" ->"); + printk(KERN_CONT " ->"); print_lock_name(hlock_class(next)); - printk("\n"); + printk(KERN_CONT "\n"); printk("\nbut this new dependency connects a %s-irq-safe lock:\n", irqclass); @@ -1521,8 +1521,7 @@ print_bad_irq_dependency(struct task_struct *curr, lockdep_print_held_locks(curr); - printk("\nthe dependencies between %s-irq-safe lock", irqclass); - printk(" and the holding lock:\n"); + printk("\nthe dependencies between %s-irq-safe lock and the holding lock:\n", irqclass); if (!save_trace(&prev_root->trace)) return 0; print_shortest_lock_dependencies(backwards_entry, prev_root); @@ -1694,10 +1693,10 @@ print_deadlock_scenario(struct held_lock *nxt, printk(" ----\n"); printk(" lock("); __print_lock_name(prev); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" lock("); __print_lock_name(next); - printk(");\n"); + printk(KERN_CONT ");\n"); printk("\n *** DEADLOCK ***\n\n"); printk(" May be due to missing lock nesting notation\n\n"); } @@ -1869,14 +1868,14 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, * Ok, all validations passed, add the new lock * to the previous lock's dependency list: */ - ret = add_lock_to_list(hlock_class(prev), hlock_class(next), + ret = add_lock_to_list(hlock_class(next), &hlock_class(prev)->locks_after, next->acquire_ip, distance, &trace); if (!ret) return 0; - ret = add_lock_to_list(hlock_class(next), hlock_class(prev), + ret = add_lock_to_list(hlock_class(prev), &hlock_class(next)->locks_before, next->acquire_ip, distance, &trace); if (!ret) @@ -1891,9 +1890,9 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, graph_unlock(); printk("\n new dependency: "); print_lock_name(hlock_class(prev)); - printk(" => "); + printk(KERN_CONT " => "); print_lock_name(hlock_class(next)); - printk("\n"); + printk(KERN_CONT "\n"); dump_stack(); return graph_lock(); } @@ -2343,11 +2342,11 @@ print_usage_bug_scenario(struct held_lock *lock) printk(" ----\n"); printk(" lock("); __print_lock_name(class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk(" <Interrupt>\n"); printk(" lock("); __print_lock_name(class); - printk(");\n"); + printk(KERN_CONT ");\n"); printk("\n *** DEADLOCK ***\n\n"); } @@ -2522,14 +2521,18 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this, void print_irqtrace_events(struct task_struct *curr) { printk("irq event stamp: %u\n", curr->irq_events); - printk("hardirqs last enabled at (%u): ", curr->hardirq_enable_event); - print_ip_sym(curr->hardirq_enable_ip); - printk("hardirqs last disabled at (%u): ", curr->hardirq_disable_event); - print_ip_sym(curr->hardirq_disable_ip); - printk("softirqs last enabled at (%u): ", curr->softirq_enable_event); - print_ip_sym(curr->softirq_enable_ip); - printk("softirqs last disabled at (%u): ", curr->softirq_disable_event); - print_ip_sym(curr->softirq_disable_ip); + printk("hardirqs last enabled at (%u): [<%p>] %pS\n", + curr->hardirq_enable_event, (void *)curr->hardirq_enable_ip, + (void *)curr->hardirq_enable_ip); + printk("hardirqs last disabled at (%u): [<%p>] %pS\n", + curr->hardirq_disable_event, (void *)curr->hardirq_disable_ip, + (void *)curr->hardirq_disable_ip); + printk("softirqs last enabled at (%u): [<%p>] %pS\n", + curr->softirq_enable_event, (void *)curr->softirq_enable_ip, + (void *)curr->softirq_enable_ip); + printk("softirqs last disabled at (%u): [<%p>] %pS\n", + curr->softirq_disable_event, (void *)curr->softirq_disable_ip, + (void *)curr->softirq_disable_ip); } static int HARDIRQ_verbose(struct lock_class *class) @@ -3188,7 +3191,7 @@ print_lock_nested_lock_not_held(struct task_struct *curr, return 0; } -static int __lock_is_held(struct lockdep_map *lock); +static int __lock_is_held(struct lockdep_map *lock, int read); /* * This gets called for every mutex_lock*()/spin_lock*() operation. @@ -3235,8 +3238,8 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, if (very_verbose(class)) { printk("\nacquire class [%p] %s", class->key, class->name); if (class->name_version > 1) - printk("#%d", class->name_version); - printk("\n"); + printk(KERN_CONT "#%d", class->name_version); + printk(KERN_CONT "\n"); dump_stack(); } @@ -3329,7 +3332,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, } chain_key = iterate_chain_key(chain_key, class_idx); - if (nest_lock && !__lock_is_held(nest_lock)) + if (nest_lock && !__lock_is_held(nest_lock, -1)) return print_lock_nested_lock_not_held(curr, hlock, ip); if (!validate_chain(curr, lock, hlock, chain_head, chain_key)) @@ -3378,7 +3381,7 @@ print_unlock_imbalance_bug(struct task_struct *curr, struct lockdep_map *lock, printk("%s/%d is trying to release lock (", curr->comm, task_pid_nr(curr)); print_lockdep_cache(lock); - printk(") at:\n"); + printk(KERN_CONT ") at:\n"); print_ip_sym(ip); printk("but there are no more locks to release!\n"); printk("\nother info that might help us debug this:\n"); @@ -3576,7 +3579,7 @@ found_it: return 1; } -static int __lock_is_held(struct lockdep_map *lock) +static int __lock_is_held(struct lockdep_map *lock, int read) { struct task_struct *curr = current; int i; @@ -3584,8 +3587,12 @@ static int __lock_is_held(struct lockdep_map *lock) for (i = 0; i < curr->lockdep_depth; i++) { struct held_lock *hlock = curr->held_locks + i; - if (match_held_lock(hlock, lock)) - return 1; + if (match_held_lock(hlock, lock)) { + if (read == -1 || hlock->read == read) + return 1; + + return 0; + } } return 0; @@ -3769,7 +3776,7 @@ void lock_release(struct lockdep_map *lock, int nested, } EXPORT_SYMBOL_GPL(lock_release); -int lock_is_held(struct lockdep_map *lock) +int lock_is_held_type(struct lockdep_map *lock, int read) { unsigned long flags; int ret = 0; @@ -3781,13 +3788,13 @@ int lock_is_held(struct lockdep_map *lock) check_flags(flags); current->lockdep_recursion = 1; - ret = __lock_is_held(lock); + ret = __lock_is_held(lock, read); current->lockdep_recursion = 0; raw_local_irq_restore(flags); return ret; } -EXPORT_SYMBOL_GPL(lock_is_held); +EXPORT_SYMBOL_GPL(lock_is_held_type); struct pin_cookie lock_pin_lock(struct lockdep_map *lock) { @@ -3871,7 +3878,7 @@ print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock, printk("%s/%d is trying to contend lock (", curr->comm, task_pid_nr(curr)); print_lockdep_cache(lock); - printk(") at:\n"); + printk(KERN_CONT ") at:\n"); print_ip_sym(ip); printk("but there are no locks held!\n"); printk("\nother info that might help us debug this:\n"); diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index 51c4b24b6328..c2b88490d857 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -46,6 +46,14 @@ enum { (LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ) /* + * CONFIG_PROVE_LOCKING_SMALL is defined for sparc. Sparc requires .text, + * .data and .bss to fit in required 32MB limit for the kernel. With + * PROVE_LOCKING we could go over this limit and cause system boot-up problems. + * So, reduce the static allocations for lockdeps related structures so that + * everything fits in current required size limit. + */ +#ifdef CONFIG_PROVE_LOCKING_SMALL +/* * MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies * we track. * @@ -54,18 +62,24 @@ enum { * table (if it's not there yet), and we check it for lock order * conflicts and deadlocks. */ +#define MAX_LOCKDEP_ENTRIES 16384UL +#define MAX_LOCKDEP_CHAINS_BITS 15 +#define MAX_STACK_TRACE_ENTRIES 262144UL +#else #define MAX_LOCKDEP_ENTRIES 32768UL #define MAX_LOCKDEP_CHAINS_BITS 16 -#define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) - -#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) /* * Stack-trace: tightly packed array of stack backtrace * addresses. Protected by the hash_lock. */ #define MAX_STACK_TRACE_ENTRIES 524288UL +#endif + +#define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) + +#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) extern struct list_head all_lock_classes; extern struct lock_chain lock_chains[]; diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c index a0f61effad25..6d1fcc786081 100644 --- a/kernel/locking/lockdep_proc.c +++ b/kernel/locking/lockdep_proc.c @@ -18,7 +18,7 @@ #include <linux/debug_locks.h> #include <linux/vmalloc.h> #include <linux/sort.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/div64.h> #include "lockdep_internals.h" diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index c835270f0c2f..6a385aabcce7 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -28,7 +28,7 @@ struct mcs_spinlock { #define arch_mcs_spin_lock_contended(l) \ do { \ while (!(smp_load_acquire(l))) \ - cpu_relax_lowlatency(); \ + cpu_relax(); \ } while (0) #endif @@ -108,7 +108,7 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node) return; /* Wait until the next pointer is set */ while (!(next = READ_ONCE(node->next))) - cpu_relax_lowlatency(); + cpu_relax(); } /* Pass lock to next waiter. */ diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c index 9c951fade415..9aa713629387 100644 --- a/kernel/locking/mutex-debug.c +++ b/kernel/locking/mutex-debug.c @@ -73,21 +73,8 @@ void debug_mutex_unlock(struct mutex *lock) { if (likely(debug_locks)) { DEBUG_LOCKS_WARN_ON(lock->magic != lock); - - if (!lock->owner) - DEBUG_LOCKS_WARN_ON(!lock->owner); - else - DEBUG_LOCKS_WARN_ON(lock->owner != current); - DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); } - - /* - * __mutex_slowpath_needs_to_unlock() is explicitly 0 for debug - * mutexes so that we can do it here after we've verified state. - */ - mutex_clear_owner(lock); - atomic_set(&lock->count, 1); } void debug_mutex_init(struct mutex *lock, const char *name, diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h index 57a871ae3c81..a459faa48987 100644 --- a/kernel/locking/mutex-debug.h +++ b/kernel/locking/mutex-debug.h @@ -27,16 +27,6 @@ extern void debug_mutex_unlock(struct mutex *lock); extern void debug_mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key); -static inline void mutex_set_owner(struct mutex *lock) -{ - WRITE_ONCE(lock->owner, current); -} - -static inline void mutex_clear_owner(struct mutex *lock) -{ - WRITE_ONCE(lock->owner, NULL); -} - #define spin_lock_mutex(lock, flags) \ do { \ struct mutex *l = container_of(lock, struct mutex, wait_lock); \ diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index a70b90db3909..9b349619f431 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -27,41 +27,176 @@ #include <linux/debug_locks.h> #include <linux/osq_lock.h> -/* - * In the DEBUG case we are using the "NULL fastpath" for mutexes, - * which forces all calls into the slowpath: - */ #ifdef CONFIG_DEBUG_MUTEXES # include "mutex-debug.h" -# include <asm-generic/mutex-null.h> -/* - * Must be 0 for the debug case so we do not do the unlock outside of the - * wait_lock region. debug_mutex_unlock() will do the actual unlock in this - * case. - */ -# undef __mutex_slowpath_needs_to_unlock -# define __mutex_slowpath_needs_to_unlock() 0 #else # include "mutex.h" -# include <asm/mutex.h> #endif void __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key) { - atomic_set(&lock->count, 1); + atomic_long_set(&lock->owner, 0); spin_lock_init(&lock->wait_lock); INIT_LIST_HEAD(&lock->wait_list); - mutex_clear_owner(lock); #ifdef CONFIG_MUTEX_SPIN_ON_OWNER osq_lock_init(&lock->osq); #endif debug_mutex_init(lock, name, key); } - EXPORT_SYMBOL(__mutex_init); +/* + * @owner: contains: 'struct task_struct *' to the current lock owner, + * NULL means not owned. Since task_struct pointers are aligned at + * ARCH_MIN_TASKALIGN (which is at least sizeof(void *)), we have low + * bits to store extra state. + * + * Bit0 indicates a non-empty waiter list; unlock must issue a wakeup. + * Bit1 indicates unlock needs to hand the lock to the top-waiter + */ +#define MUTEX_FLAG_WAITERS 0x01 +#define MUTEX_FLAG_HANDOFF 0x02 + +#define MUTEX_FLAGS 0x03 + +static inline struct task_struct *__owner_task(unsigned long owner) +{ + return (struct task_struct *)(owner & ~MUTEX_FLAGS); +} + +static inline unsigned long __owner_flags(unsigned long owner) +{ + return owner & MUTEX_FLAGS; +} + +/* + * Actual trylock that will work on any unlocked state. + * + * When setting the owner field, we must preserve the low flag bits. + * + * Be careful with @handoff, only set that in a wait-loop (where you set + * HANDOFF) to avoid recursive lock attempts. + */ +static inline bool __mutex_trylock(struct mutex *lock, const bool handoff) +{ + unsigned long owner, curr = (unsigned long)current; + + owner = atomic_long_read(&lock->owner); + for (;;) { /* must loop, can race against a flag */ + unsigned long old, flags = __owner_flags(owner); + + if (__owner_task(owner)) { + if (handoff && unlikely(__owner_task(owner) == current)) { + /* + * Provide ACQUIRE semantics for the lock-handoff. + * + * We cannot easily use load-acquire here, since + * the actual load is a failed cmpxchg, which + * doesn't imply any barriers. + * + * Also, this is a fairly unlikely scenario, and + * this contains the cost. + */ + smp_mb(); /* ACQUIRE */ + return true; + } + + return false; + } + + /* + * We set the HANDOFF bit, we must make sure it doesn't live + * past the point where we acquire it. This would be possible + * if we (accidentally) set the bit on an unlocked mutex. + */ + if (handoff) + flags &= ~MUTEX_FLAG_HANDOFF; + + old = atomic_long_cmpxchg_acquire(&lock->owner, owner, curr | flags); + if (old == owner) + return true; + + owner = old; + } +} + +#ifndef CONFIG_DEBUG_LOCK_ALLOC +/* + * Lockdep annotations are contained to the slow paths for simplicity. + * There is nothing that would stop spreading the lockdep annotations outwards + * except more code. + */ + +/* + * Optimistic trylock that only works in the uncontended case. Make sure to + * follow with a __mutex_trylock() before failing. + */ +static __always_inline bool __mutex_trylock_fast(struct mutex *lock) +{ + unsigned long curr = (unsigned long)current; + + if (!atomic_long_cmpxchg_acquire(&lock->owner, 0UL, curr)) + return true; + + return false; +} + +static __always_inline bool __mutex_unlock_fast(struct mutex *lock) +{ + unsigned long curr = (unsigned long)current; + + if (atomic_long_cmpxchg_release(&lock->owner, curr, 0UL) == curr) + return true; + + return false; +} +#endif + +static inline void __mutex_set_flag(struct mutex *lock, unsigned long flag) +{ + atomic_long_or(flag, &lock->owner); +} + +static inline void __mutex_clear_flag(struct mutex *lock, unsigned long flag) +{ + atomic_long_andnot(flag, &lock->owner); +} + +static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_waiter *waiter) +{ + return list_first_entry(&lock->wait_list, struct mutex_waiter, list) == waiter; +} + +/* + * Give up ownership to a specific task, when @task = NULL, this is equivalent + * to a regular unlock. Clears HANDOFF, preserves WAITERS. Provides RELEASE + * semantics like a regular unlock, the __mutex_trylock() provides matching + * ACQUIRE semantics for the handoff. + */ +static void __mutex_handoff(struct mutex *lock, struct task_struct *task) +{ + unsigned long owner = atomic_long_read(&lock->owner); + + for (;;) { + unsigned long old, new; + +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current); +#endif + + new = (owner & MUTEX_FLAG_WAITERS); + new |= (unsigned long)task; + + old = atomic_long_cmpxchg_release(&lock->owner, owner, new); + if (old == owner) + break; + + owner = old; + } +} + #ifndef CONFIG_DEBUG_LOCK_ALLOC /* * We split the mutex lock/unlock logic into separate fastpath and @@ -69,7 +204,7 @@ EXPORT_SYMBOL(__mutex_init); * We also put the fastpath first in the kernel image, to make sure the * branch is predicted by the CPU as default-untaken. */ -__visible void __sched __mutex_lock_slowpath(atomic_t *lock_count); +static void __sched __mutex_lock_slowpath(struct mutex *lock); /** * mutex_lock - acquire the mutex @@ -95,14 +230,10 @@ __visible void __sched __mutex_lock_slowpath(atomic_t *lock_count); void __sched mutex_lock(struct mutex *lock) { might_sleep(); - /* - * The locking fastpath is the 1->0 transition from - * 'unlocked' into 'locked' state. - */ - __mutex_fastpath_lock(&lock->count, __mutex_lock_slowpath); - mutex_set_owner(lock); -} + if (!__mutex_trylock_fast(lock)) + __mutex_lock_slowpath(lock); +} EXPORT_SYMBOL(mutex_lock); #endif @@ -149,9 +280,6 @@ static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, /* * After acquiring lock with fastpath or when we lost out in contested * slowpath, set ctx and wake up any waiters so they can recheck. - * - * This function is never called when CONFIG_DEBUG_LOCK_ALLOC is set, - * as the fastpath and opportunistic spinning are disabled in that case. */ static __always_inline void ww_mutex_set_context_fastpath(struct ww_mutex *lock, @@ -176,7 +304,7 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, /* * Check if lock is contended, if not there is nobody to wake up */ - if (likely(atomic_read(&lock->base.count) == 0)) + if (likely(!(atomic_long_read(&lock->base.owner) & MUTEX_FLAG_WAITERS))) return; /* @@ -227,7 +355,7 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) bool ret = true; rcu_read_lock(); - while (lock->owner == owner) { + while (__mutex_owner(lock) == owner) { /* * Ensure we emit the owner->on_cpu, dereference _after_ * checking lock->owner still matches owner. If that fails, @@ -236,12 +364,16 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) */ barrier(); - if (!owner->on_cpu || need_resched()) { + /* + * Use vcpu_is_preempted to detect lock holder preemption issue. + */ + if (!owner->on_cpu || need_resched() || + vcpu_is_preempted(task_cpu(owner))) { ret = false; break; } - cpu_relax_lowlatency(); + cpu_relax(); } rcu_read_unlock(); @@ -260,27 +392,25 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock) return 0; rcu_read_lock(); - owner = READ_ONCE(lock->owner); + owner = __mutex_owner(lock); + + /* + * As lock holder preemption issue, we both skip spinning if task is not + * on cpu or its cpu is preempted + */ if (owner) - retval = owner->on_cpu; + retval = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner)); rcu_read_unlock(); + /* - * if lock->owner is not set, the mutex owner may have just acquired - * it and not set the owner yet or the mutex has been released. + * If lock->owner is not set, the mutex has been released. Return true + * such that we'll trylock in the spin path, which is a faster option + * than the blocking slow path. */ return retval; } /* - * Atomically try to take the lock when it is available - */ -static inline bool mutex_try_to_acquire(struct mutex *lock) -{ - return !mutex_is_locked(lock) && - (atomic_cmpxchg_acquire(&lock->count, 1, 0) == 1); -} - -/* * Optimistic spinning. * * We try to spin for acquisition when we find that the lock owner @@ -288,13 +418,6 @@ static inline bool mutex_try_to_acquire(struct mutex *lock) * need to reschedule. The rationale is that if the lock owner is * running, it is likely to release the lock soon. * - * Since this needs the lock owner, and this mutex implementation - * doesn't track the owner atomically in the lock field, we need to - * track it non-atomically. - * - * We can't do this for DEBUG_MUTEXES because that relies on wait_lock - * to serialize everything. - * * The mutex spinners are queued up using MCS lock so that only one * spinner can compete for the mutex. However, if mutex spinning isn't * going to happen, there is no point in going through the lock/unlock @@ -302,24 +425,39 @@ static inline bool mutex_try_to_acquire(struct mutex *lock) * * Returns true when the lock was taken, otherwise false, indicating * that we need to jump to the slowpath and sleep. + * + * The waiter flag is set to true if the spinner is a waiter in the wait + * queue. The waiter-spinner will spin on the lock directly and concurrently + * with the spinner at the head of the OSQ, if present, until the owner is + * changed to itself. */ static bool mutex_optimistic_spin(struct mutex *lock, - struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) + struct ww_acquire_ctx *ww_ctx, + const bool use_ww_ctx, const bool waiter) { struct task_struct *task = current; - if (!mutex_can_spin_on_owner(lock)) - goto done; + if (!waiter) { + /* + * The purpose of the mutex_can_spin_on_owner() function is + * to eliminate the overhead of osq_lock() and osq_unlock() + * in case spinning isn't possible. As a waiter-spinner + * is not going to take OSQ lock anyway, there is no need + * to call mutex_can_spin_on_owner(). + */ + if (!mutex_can_spin_on_owner(lock)) + goto fail; - /* - * In order to avoid a stampede of mutex spinners trying to - * acquire the mutex all at once, the spinners need to take a - * MCS (queued) lock first before spinning on the owner field. - */ - if (!osq_lock(&lock->osq)) - goto done; + /* + * In order to avoid a stampede of mutex spinners trying to + * acquire the mutex all at once, the spinners need to take a + * MCS (queued) lock first before spinning on the owner field. + */ + if (!osq_lock(&lock->osq)) + goto fail; + } - while (true) { + for (;;) { struct task_struct *owner; if (use_ww_ctx && ww_ctx->acquired > 0) { @@ -335,40 +473,26 @@ static bool mutex_optimistic_spin(struct mutex *lock, * performed the optimistic spinning cannot be done. */ if (READ_ONCE(ww->ctx)) - break; + goto fail_unlock; } /* * If there's an owner, wait for it to either * release the lock or go to sleep. */ - owner = READ_ONCE(lock->owner); - if (owner && !mutex_spin_on_owner(lock, owner)) - break; - - /* Try to acquire the mutex if it is unlocked. */ - if (mutex_try_to_acquire(lock)) { - lock_acquired(&lock->dep_map, ip); - - if (use_ww_ctx) { - struct ww_mutex *ww; - ww = container_of(lock, struct ww_mutex, base); - - ww_mutex_set_context_fastpath(ww, ww_ctx); + owner = __mutex_owner(lock); + if (owner) { + if (waiter && owner == task) { + smp_mb(); /* ACQUIRE */ + break; } - mutex_set_owner(lock); - osq_unlock(&lock->osq); - return true; + if (!mutex_spin_on_owner(lock, owner)) + goto fail_unlock; } - /* - * When there's no owner, we might have preempted between the - * owner acquiring the lock and setting the owner field. If - * we're an RT task that will live-lock because we won't let - * the owner complete. - */ - if (!owner && (need_resched() || rt_task(task))) + /* Try to acquire the mutex if it is unlocked. */ + if (__mutex_trylock(lock, waiter)) break; /* @@ -377,11 +501,20 @@ static bool mutex_optimistic_spin(struct mutex *lock, * memory barriers as we'll eventually observe the right * values at the cost of a few extra spins. */ - cpu_relax_lowlatency(); + cpu_relax(); } - osq_unlock(&lock->osq); -done: + if (!waiter) + osq_unlock(&lock->osq); + + return true; + + +fail_unlock: + if (!waiter) + osq_unlock(&lock->osq); + +fail: /* * If we fell out of the spin path because of need_resched(), * reschedule now, before we try-lock the mutex. This avoids getting @@ -400,14 +533,14 @@ done: } #else static bool mutex_optimistic_spin(struct mutex *lock, - struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx) + struct ww_acquire_ctx *ww_ctx, + const bool use_ww_ctx, const bool waiter) { return false; } #endif -__visible __used noinline -void __sched __mutex_unlock_slowpath(atomic_t *lock_count); +static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip); /** * mutex_unlock - release the mutex @@ -422,21 +555,12 @@ void __sched __mutex_unlock_slowpath(atomic_t *lock_count); */ void __sched mutex_unlock(struct mutex *lock) { - /* - * The unlocking fastpath is the 0->1 transition from 'locked' - * into 'unlocked' state: - */ -#ifndef CONFIG_DEBUG_MUTEXES - /* - * When debugging is enabled we must not clear the owner before time, - * the slow path will always be taken, and that clears the owner field - * after verifying that it was indeed current. - */ - mutex_clear_owner(lock); +#ifndef CONFIG_DEBUG_LOCK_ALLOC + if (__mutex_unlock_fast(lock)) + return; #endif - __mutex_fastpath_unlock(&lock->count, __mutex_unlock_slowpath); + __mutex_unlock_slowpath(lock, _RET_IP_); } - EXPORT_SYMBOL(mutex_unlock); /** @@ -465,15 +589,7 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock) lock->ctx = NULL; } -#ifndef CONFIG_DEBUG_MUTEXES - /* - * When debugging is enabled we must not clear the owner before time, - * the slow path will always be taken, and that clears the owner field - * after verifying that it was indeed current. - */ - mutex_clear_owner(&lock->base); -#endif - __mutex_fastpath_unlock(&lock->base.count, __mutex_unlock_slowpath); + mutex_unlock(&lock->base); } EXPORT_SYMBOL(ww_mutex_unlock); @@ -509,10 +625,12 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, struct task_struct *task = current; struct mutex_waiter waiter; unsigned long flags; + bool first = false; + struct ww_mutex *ww; int ret; if (use_ww_ctx) { - struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); + ww = container_of(lock, struct ww_mutex, base); if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) return -EALREADY; } @@ -520,20 +638,21 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, preempt_disable(); mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip); - if (mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) { + if (__mutex_trylock(lock, false) || + mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, false)) { /* got the lock, yay! */ + lock_acquired(&lock->dep_map, ip); + if (use_ww_ctx) + ww_mutex_set_context_fastpath(ww, ww_ctx); preempt_enable(); return 0; } spin_lock_mutex(&lock->wait_lock, flags); - /* - * Once more, try to acquire the lock. Only try-lock the mutex if - * it is unlocked to reduce unnecessary xchg() operations. + * After waiting to acquire the wait_lock, try again. */ - if (!mutex_is_locked(lock) && - (atomic_xchg_acquire(&lock->count, 0) == 1)) + if (__mutex_trylock(lock, false)) goto skip_wait; debug_mutex_lock_common(lock, &waiter); @@ -543,26 +662,26 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, list_add_tail(&waiter.list, &lock->wait_list); waiter.task = task; + if (__mutex_waiter_is_first(lock, &waiter)) + __mutex_set_flag(lock, MUTEX_FLAG_WAITERS); + lock_contended(&lock->dep_map, ip); + set_task_state(task, state); for (;;) { /* - * Lets try to take the lock again - this is needed even if - * we get here for the first time (shortly after failing to - * acquire the lock), to make sure that we get a wakeup once - * it's unlocked. Later on, if we sleep, this is the - * operation that gives us the lock. We xchg it to -1, so - * that when we release the lock, we properly wake up the - * other waiters. We only attempt the xchg if the count is - * non-negative in order to avoid unnecessary xchg operations: + * Once we hold wait_lock, we're serialized against + * mutex_unlock() handing the lock off to us, do a trylock + * before testing the error conditions to make sure we pick up + * the handoff. */ - if (atomic_read(&lock->count) >= 0 && - (atomic_xchg_acquire(&lock->count, -1) == 1)) - break; + if (__mutex_trylock(lock, first)) + goto acquired; /* - * got a signal? (This code gets eliminated in the - * TASK_UNINTERRUPTIBLE case.) + * Check for signals and wound conditions while holding + * wait_lock. This ensures the lock cancellation is ordered + * against mutex_unlock() and wake-ups do not go missing. */ if (unlikely(signal_pending_state(state, task))) { ret = -EINTR; @@ -575,36 +694,49 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, goto err; } - __set_task_state(task, state); - - /* didn't get the lock, go to sleep: */ spin_unlock_mutex(&lock->wait_lock, flags); schedule_preempt_disabled(); + + if (!first && __mutex_waiter_is_first(lock, &waiter)) { + first = true; + __mutex_set_flag(lock, MUTEX_FLAG_HANDOFF); + } + + set_task_state(task, state); + /* + * Here we order against unlock; we must either see it change + * state back to RUNNING and fall through the next schedule(), + * or we must see its unlock and acquire. + */ + if ((first && mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, true)) || + __mutex_trylock(lock, first)) + break; + spin_lock_mutex(&lock->wait_lock, flags); } + spin_lock_mutex(&lock->wait_lock, flags); +acquired: __set_task_state(task, TASK_RUNNING); mutex_remove_waiter(lock, &waiter, task); - /* set it to 0 if there are no waiters left: */ if (likely(list_empty(&lock->wait_list))) - atomic_set(&lock->count, 0); + __mutex_clear_flag(lock, MUTEX_FLAGS); + debug_mutex_free_waiter(&waiter); skip_wait: /* got the lock - cleanup and rejoice! */ lock_acquired(&lock->dep_map, ip); - mutex_set_owner(lock); - if (use_ww_ctx) { - struct ww_mutex *ww = container_of(lock, struct ww_mutex, base); + if (use_ww_ctx) ww_mutex_set_context_slowpath(ww, ww_ctx); - } spin_unlock_mutex(&lock->wait_lock, flags); preempt_enable(); return 0; err: + __set_task_state(task, TASK_RUNNING); mutex_remove_waiter(lock, &waiter, task); spin_unlock_mutex(&lock->wait_lock, flags); debug_mutex_free_waiter(&waiter); @@ -631,7 +763,6 @@ _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, nest, _RET_IP_, NULL, 0); } - EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock); int __sched @@ -650,7 +781,6 @@ mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass) return __mutex_lock_common(lock, TASK_INTERRUPTIBLE, subclass, NULL, _RET_IP_, NULL, 0); } - EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested); static inline int @@ -715,54 +845,64 @@ EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible); /* * Release the lock, slowpath: */ -static inline void -__mutex_unlock_common_slowpath(struct mutex *lock, int nested) +static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip) { - unsigned long flags; - WAKE_Q(wake_q); + struct task_struct *next = NULL; + unsigned long owner, flags; + DEFINE_WAKE_Q(wake_q); + + mutex_release(&lock->dep_map, 1, ip); /* - * As a performance measurement, release the lock before doing other - * wakeup related duties to follow. This allows other tasks to acquire - * the lock sooner, while still handling cleanups in past unlock calls. - * This can be done as we do not enforce strict equivalence between the - * mutex counter and wait_list. - * + * Release the lock before (potentially) taking the spinlock such that + * other contenders can get on with things ASAP. * - * Some architectures leave the lock unlocked in the fastpath failure - * case, others need to leave it locked. In the later case we have to - * unlock it here - as the lock counter is currently 0 or negative. + * Except when HANDOFF, in that case we must not clear the owner field, + * but instead set it to the top waiter. */ - if (__mutex_slowpath_needs_to_unlock()) - atomic_set(&lock->count, 1); + owner = atomic_long_read(&lock->owner); + for (;;) { + unsigned long old; + +#ifdef CONFIG_DEBUG_MUTEXES + DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current); +#endif + + if (owner & MUTEX_FLAG_HANDOFF) + break; + + old = atomic_long_cmpxchg_release(&lock->owner, owner, + __owner_flags(owner)); + if (old == owner) { + if (owner & MUTEX_FLAG_WAITERS) + break; + + return; + } + + owner = old; + } spin_lock_mutex(&lock->wait_lock, flags); - mutex_release(&lock->dep_map, nested, _RET_IP_); debug_mutex_unlock(lock); - if (!list_empty(&lock->wait_list)) { /* get the first entry from the wait-list: */ struct mutex_waiter *waiter = - list_entry(lock->wait_list.next, - struct mutex_waiter, list); + list_first_entry(&lock->wait_list, + struct mutex_waiter, list); + + next = waiter->task; debug_mutex_wake_waiter(lock, waiter); - wake_q_add(&wake_q, waiter->task); + wake_q_add(&wake_q, next); } - spin_unlock_mutex(&lock->wait_lock, flags); - wake_up_q(&wake_q); -} + if (owner & MUTEX_FLAG_HANDOFF) + __mutex_handoff(lock, next); -/* - * Release the lock, slowpath: - */ -__visible void -__mutex_unlock_slowpath(atomic_t *lock_count) -{ - struct mutex *lock = container_of(lock_count, struct mutex, count); + spin_unlock_mutex(&lock->wait_lock, flags); - __mutex_unlock_common_slowpath(lock, 1); + wake_up_q(&wake_q); } #ifndef CONFIG_DEBUG_LOCK_ALLOC @@ -789,38 +929,30 @@ __mutex_lock_interruptible_slowpath(struct mutex *lock); */ int __sched mutex_lock_interruptible(struct mutex *lock) { - int ret; - might_sleep(); - ret = __mutex_fastpath_lock_retval(&lock->count); - if (likely(!ret)) { - mutex_set_owner(lock); + + if (__mutex_trylock_fast(lock)) return 0; - } else - return __mutex_lock_interruptible_slowpath(lock); + + return __mutex_lock_interruptible_slowpath(lock); } EXPORT_SYMBOL(mutex_lock_interruptible); int __sched mutex_lock_killable(struct mutex *lock) { - int ret; - might_sleep(); - ret = __mutex_fastpath_lock_retval(&lock->count); - if (likely(!ret)) { - mutex_set_owner(lock); + + if (__mutex_trylock_fast(lock)) return 0; - } else - return __mutex_lock_killable_slowpath(lock); + + return __mutex_lock_killable_slowpath(lock); } EXPORT_SYMBOL(mutex_lock_killable); -__visible void __sched -__mutex_lock_slowpath(atomic_t *lock_count) +static noinline void __sched +__mutex_lock_slowpath(struct mutex *lock) { - struct mutex *lock = container_of(lock_count, struct mutex, count); - __mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0, NULL, _RET_IP_, NULL, 0); } @@ -856,37 +988,6 @@ __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock, #endif -/* - * Spinlock based trylock, we take the spinlock and check whether we - * can get the lock: - */ -static inline int __mutex_trylock_slowpath(atomic_t *lock_count) -{ - struct mutex *lock = container_of(lock_count, struct mutex, count); - unsigned long flags; - int prev; - - /* No need to trylock if the mutex is locked. */ - if (mutex_is_locked(lock)) - return 0; - - spin_lock_mutex(&lock->wait_lock, flags); - - prev = atomic_xchg_acquire(&lock->count, -1); - if (likely(prev == 1)) { - mutex_set_owner(lock); - mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); - } - - /* Set it back to 0 if there are no waiters: */ - if (likely(list_empty(&lock->wait_list))) - atomic_set(&lock->count, 0); - - spin_unlock_mutex(&lock->wait_lock, flags); - - return prev == 1; -} - /** * mutex_trylock - try to acquire the mutex, without waiting * @lock: the mutex to be acquired @@ -903,13 +1004,12 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count) */ int __sched mutex_trylock(struct mutex *lock) { - int ret; + bool locked = __mutex_trylock(lock, false); - ret = __mutex_fastpath_trylock(&lock->count, __mutex_trylock_slowpath); - if (ret) - mutex_set_owner(lock); + if (locked) + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); - return ret; + return locked; } EXPORT_SYMBOL(mutex_trylock); @@ -917,36 +1017,28 @@ EXPORT_SYMBOL(mutex_trylock); int __sched __ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { - int ret; - might_sleep(); - ret = __mutex_fastpath_lock_retval(&lock->base.count); - - if (likely(!ret)) { + if (__mutex_trylock_fast(&lock->base)) { ww_mutex_set_context_fastpath(lock, ctx); - mutex_set_owner(&lock->base); - } else - ret = __ww_mutex_lock_slowpath(lock, ctx); - return ret; + return 0; + } + + return __ww_mutex_lock_slowpath(lock, ctx); } EXPORT_SYMBOL(__ww_mutex_lock); int __sched __ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) { - int ret; - might_sleep(); - ret = __mutex_fastpath_lock_retval(&lock->base.count); - - if (likely(!ret)) { + if (__mutex_trylock_fast(&lock->base)) { ww_mutex_set_context_fastpath(lock, ctx); - mutex_set_owner(&lock->base); - } else - ret = __ww_mutex_lock_interruptible_slowpath(lock, ctx); - return ret; + return 0; + } + + return __ww_mutex_lock_interruptible_slowpath(lock, ctx); } EXPORT_SYMBOL(__ww_mutex_lock_interruptible); diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h index 6cd6b8e9efd7..4410a4af42a3 100644 --- a/kernel/locking/mutex.h +++ b/kernel/locking/mutex.h @@ -16,32 +16,6 @@ #define mutex_remove_waiter(lock, waiter, task) \ __list_del((waiter)->list.prev, (waiter)->list.next) -#ifdef CONFIG_MUTEX_SPIN_ON_OWNER -/* - * The mutex owner can get read and written to locklessly. - * We should use WRITE_ONCE when writing the owner value to - * avoid store tearing, otherwise, a thread could potentially - * read a partially written and incomplete owner value. - */ -static inline void mutex_set_owner(struct mutex *lock) -{ - WRITE_ONCE(lock->owner, current); -} - -static inline void mutex_clear_owner(struct mutex *lock) -{ - WRITE_ONCE(lock->owner, NULL); -} -#else -static inline void mutex_set_owner(struct mutex *lock) -{ -} - -static inline void mutex_clear_owner(struct mutex *lock) -{ -} -#endif - #define debug_mutex_wake_waiter(lock, waiter) do { } while (0) #define debug_mutex_free_waiter(waiter) do { } while (0) #define debug_mutex_add_waiter(lock, waiter, ti) do { } while (0) diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c index 05a37857ab55..a3167941093b 100644 --- a/kernel/locking/osq_lock.c +++ b/kernel/locking/osq_lock.c @@ -21,6 +21,11 @@ static inline int encode_cpu(int cpu_nr) return cpu_nr + 1; } +static inline int node_cpu(struct optimistic_spin_node *node) +{ + return node->cpu - 1; +} + static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val) { int cpu_nr = encoded_cpu_val - 1; @@ -75,7 +80,7 @@ osq_wait_next(struct optimistic_spin_queue *lock, break; } - cpu_relax_lowlatency(); + cpu_relax(); } return next; @@ -118,11 +123,13 @@ bool osq_lock(struct optimistic_spin_queue *lock) while (!READ_ONCE(node->locked)) { /* * If we need to reschedule bail... so we can block. + * Use vcpu_is_preempted() to avoid waiting for a preempted + * lock holder: */ - if (need_resched()) + if (need_resched() || vcpu_is_preempted(node_cpu(node->prev))) goto unqueue; - cpu_relax_lowlatency(); + cpu_relax(); } return true; @@ -148,7 +155,7 @@ unqueue: if (smp_load_acquire(&node->locked)) return true; - cpu_relax_lowlatency(); + cpu_relax(); /* * Or we race against a concurrent unqueue()'s step-B, in which diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index bec0b647f9cc..ce182599cf2e 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -8,152 +8,186 @@ #include <linux/sched.h> #include <linux/errno.h> -int __percpu_init_rwsem(struct percpu_rw_semaphore *brw, +int __percpu_init_rwsem(struct percpu_rw_semaphore *sem, const char *name, struct lock_class_key *rwsem_key) { - brw->fast_read_ctr = alloc_percpu(int); - if (unlikely(!brw->fast_read_ctr)) + sem->read_count = alloc_percpu(int); + if (unlikely(!sem->read_count)) return -ENOMEM; /* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */ - __init_rwsem(&brw->rw_sem, name, rwsem_key); - rcu_sync_init(&brw->rss, RCU_SCHED_SYNC); - atomic_set(&brw->slow_read_ctr, 0); - init_waitqueue_head(&brw->write_waitq); + rcu_sync_init(&sem->rss, RCU_SCHED_SYNC); + __init_rwsem(&sem->rw_sem, name, rwsem_key); + init_waitqueue_head(&sem->writer); + sem->readers_block = 0; return 0; } EXPORT_SYMBOL_GPL(__percpu_init_rwsem); -void percpu_free_rwsem(struct percpu_rw_semaphore *brw) +void percpu_free_rwsem(struct percpu_rw_semaphore *sem) { /* * XXX: temporary kludge. The error path in alloc_super() * assumes that percpu_free_rwsem() is safe after kzalloc(). */ - if (!brw->fast_read_ctr) + if (!sem->read_count) return; - rcu_sync_dtor(&brw->rss); - free_percpu(brw->fast_read_ctr); - brw->fast_read_ctr = NULL; /* catch use after free bugs */ + rcu_sync_dtor(&sem->rss); + free_percpu(sem->read_count); + sem->read_count = NULL; /* catch use after free bugs */ } EXPORT_SYMBOL_GPL(percpu_free_rwsem); -/* - * This is the fast-path for down_read/up_read. If it succeeds we rely - * on the barriers provided by rcu_sync_enter/exit; see the comments in - * percpu_down_write() and percpu_up_write(). - * - * If this helper fails the callers rely on the normal rw_semaphore and - * atomic_dec_and_test(), so in this case we have the necessary barriers. - */ -static bool update_fast_ctr(struct percpu_rw_semaphore *brw, unsigned int val) +int __percpu_down_read(struct percpu_rw_semaphore *sem, int try) { - bool success; + /* + * Due to having preemption disabled the decrement happens on + * the same CPU as the increment, avoiding the + * increment-on-one-CPU-and-decrement-on-another problem. + * + * If the reader misses the writer's assignment of readers_block, then + * the writer is guaranteed to see the reader's increment. + * + * Conversely, any readers that increment their sem->read_count after + * the writer looks are guaranteed to see the readers_block value, + * which in turn means that they are guaranteed to immediately + * decrement their sem->read_count, so that it doesn't matter that the + * writer missed them. + */ - preempt_disable(); - success = rcu_sync_is_idle(&brw->rss); - if (likely(success)) - __this_cpu_add(*brw->fast_read_ctr, val); - preempt_enable(); + smp_mb(); /* A matches D */ - return success; -} + /* + * If !readers_block the critical section starts here, matched by the + * release in percpu_up_write(). + */ + if (likely(!smp_load_acquire(&sem->readers_block))) + return 1; -/* - * Like the normal down_read() this is not recursive, the writer can - * come after the first percpu_down_read() and create the deadlock. - * - * Note: returns with lock_is_held(brw->rw_sem) == T for lockdep, - * percpu_up_read() does rwsem_release(). This pairs with the usage - * of ->rw_sem in percpu_down/up_write(). - */ -void percpu_down_read(struct percpu_rw_semaphore *brw) -{ - might_sleep(); - rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 0, _RET_IP_); + /* + * Per the above comment; we still have preemption disabled and + * will thus decrement on the same CPU as we incremented. + */ + __percpu_up_read(sem); - if (likely(update_fast_ctr(brw, +1))) - return; + if (try) + return 0; - /* Avoid rwsem_acquire_read() and rwsem_release() */ - __down_read(&brw->rw_sem); - atomic_inc(&brw->slow_read_ctr); - __up_read(&brw->rw_sem); -} -EXPORT_SYMBOL_GPL(percpu_down_read); + /* + * We either call schedule() in the wait, or we'll fall through + * and reschedule on the preempt_enable() in percpu_down_read(). + */ + preempt_enable_no_resched(); -int percpu_down_read_trylock(struct percpu_rw_semaphore *brw) -{ - if (unlikely(!update_fast_ctr(brw, +1))) { - if (!__down_read_trylock(&brw->rw_sem)) - return 0; - atomic_inc(&brw->slow_read_ctr); - __up_read(&brw->rw_sem); - } - - rwsem_acquire_read(&brw->rw_sem.dep_map, 0, 1, _RET_IP_); + /* + * Avoid lockdep for the down/up_read() we already have them. + */ + __down_read(&sem->rw_sem); + this_cpu_inc(*sem->read_count); + __up_read(&sem->rw_sem); + + preempt_disable(); return 1; } +EXPORT_SYMBOL_GPL(__percpu_down_read); -void percpu_up_read(struct percpu_rw_semaphore *brw) +void __percpu_up_read(struct percpu_rw_semaphore *sem) { - rwsem_release(&brw->rw_sem.dep_map, 1, _RET_IP_); - - if (likely(update_fast_ctr(brw, -1))) - return; + smp_mb(); /* B matches C */ + /* + * In other words, if they see our decrement (presumably to aggregate + * zero, as that is the only time it matters) they will also see our + * critical section. + */ + __this_cpu_dec(*sem->read_count); - /* false-positive is possible but harmless */ - if (atomic_dec_and_test(&brw->slow_read_ctr)) - wake_up_all(&brw->write_waitq); + /* Prod writer to recheck readers_active */ + wake_up(&sem->writer); } -EXPORT_SYMBOL_GPL(percpu_up_read); +EXPORT_SYMBOL_GPL(__percpu_up_read); + +#define per_cpu_sum(var) \ +({ \ + typeof(var) __sum = 0; \ + int cpu; \ + compiletime_assert_atomic_type(__sum); \ + for_each_possible_cpu(cpu) \ + __sum += per_cpu(var, cpu); \ + __sum; \ +}) -static int clear_fast_ctr(struct percpu_rw_semaphore *brw) +/* + * Return true if the modular sum of the sem->read_count per-CPU variable is + * zero. If this sum is zero, then it is stable due to the fact that if any + * newly arriving readers increment a given counter, they will immediately + * decrement that same counter. + */ +static bool readers_active_check(struct percpu_rw_semaphore *sem) { - unsigned int sum = 0; - int cpu; + if (per_cpu_sum(*sem->read_count) != 0) + return false; + + /* + * If we observed the decrement; ensure we see the entire critical + * section. + */ - for_each_possible_cpu(cpu) { - sum += per_cpu(*brw->fast_read_ctr, cpu); - per_cpu(*brw->fast_read_ctr, cpu) = 0; - } + smp_mb(); /* C matches B */ - return sum; + return true; } -void percpu_down_write(struct percpu_rw_semaphore *brw) +void percpu_down_write(struct percpu_rw_semaphore *sem) { + /* Notify readers to take the slow path. */ + rcu_sync_enter(&sem->rss); + + down_write(&sem->rw_sem); + /* - * Make rcu_sync_is_idle() == F and thus disable the fast-path in - * percpu_down_read() and percpu_up_read(), and wait for gp pass. - * - * The latter synchronises us with the preceding readers which used - * the fast-past, so we can not miss the result of __this_cpu_add() - * or anything else inside their criticial sections. + * Notify new readers to block; up until now, and thus throughout the + * longish rcu_sync_enter() above, new readers could still come in. */ - rcu_sync_enter(&brw->rss); + WRITE_ONCE(sem->readers_block, 1); - /* exclude other writers, and block the new readers completely */ - down_write(&brw->rw_sem); + smp_mb(); /* D matches A */ - /* nobody can use fast_read_ctr, move its sum into slow_read_ctr */ - atomic_add(clear_fast_ctr(brw), &brw->slow_read_ctr); + /* + * If they don't see our writer of readers_block, then we are + * guaranteed to see their sem->read_count increment, and therefore + * will wait for them. + */ - /* wait for all readers to complete their percpu_up_read() */ - wait_event(brw->write_waitq, !atomic_read(&brw->slow_read_ctr)); + /* Wait for all now active readers to complete. */ + wait_event(sem->writer, readers_active_check(sem)); } EXPORT_SYMBOL_GPL(percpu_down_write); -void percpu_up_write(struct percpu_rw_semaphore *brw) +void percpu_up_write(struct percpu_rw_semaphore *sem) { - /* release the lock, but the readers can't use the fast-path */ - up_write(&brw->rw_sem); /* - * Enable the fast-path in percpu_down_read() and percpu_up_read() - * but only after another gp pass; this adds the necessary barrier - * to ensure the reader can't miss the changes done by us. + * Signal the writer is done, no fast path yet. + * + * One reason that we cannot just immediately flip to readers_fast is + * that new readers might fail to see the results of this writer's + * critical section. + * + * Therefore we force it through the slow path which guarantees an + * acquire and thereby guarantees the critical section's consistency. + */ + smp_store_release(&sem->readers_block, 0); + + /* + * Release the write lock, this will allow readers back in the game. + */ + up_write(&sem->rw_sem); + + /* + * Once this completes (at least one RCU-sched grace period hence) the + * reader fast path will be available again. Safe to use outside the + * exclusive write lock because its counting. */ - rcu_sync_exit(&brw->rss); + rcu_sync_exit(&sem->rss); } EXPORT_SYMBOL_GPL(percpu_up_write); diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c index 19248ddf37ce..cc3ed0ccdfa2 100644 --- a/kernel/locking/qrwlock.c +++ b/kernel/locking/qrwlock.c @@ -54,7 +54,7 @@ static __always_inline void rspin_until_writer_unlock(struct qrwlock *lock, u32 cnts) { while ((cnts & _QW_WMASK) == _QW_LOCKED) { - cpu_relax_lowlatency(); + cpu_relax(); cnts = atomic_read_acquire(&lock->cnts); } } @@ -130,7 +130,7 @@ void queued_write_lock_slowpath(struct qrwlock *lock) (cmpxchg_relaxed(&l->wmode, 0, _QW_WAITING) == 0)) break; - cpu_relax_lowlatency(); + cpu_relax(); } /* When no more readers, set the locked flag */ @@ -141,7 +141,7 @@ void queued_write_lock_slowpath(struct qrwlock *lock) _QW_LOCKED) == _QW_WAITING)) break; - cpu_relax_lowlatency(); + cpu_relax(); } unlock: arch_spin_unlock(&lock->wait_lock); diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 8a99abf58080..e3b5520005db 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -70,11 +70,14 @@ struct pv_node { static inline bool pv_queued_spin_steal_lock(struct qspinlock *lock) { struct __qspinlock *l = (void *)lock; - int ret = !(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) && - (cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0); - qstat_inc(qstat_pv_lock_stealing, ret); - return ret; + if (!(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) && + (cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0)) { + qstat_inc(qstat_pv_lock_stealing, true); + return true; + } + + return false; } /* @@ -257,7 +260,6 @@ static struct pv_node *pv_unhash(struct qspinlock *lock) static inline bool pv_wait_early(struct pv_node *prev, int loop) { - if ((loop & PV_PREV_CHECK_MASK) != 0) return false; @@ -286,12 +288,10 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev) { struct pv_node *pn = (struct pv_node *)node; struct pv_node *pp = (struct pv_node *)prev; - int waitcnt = 0; int loop; bool wait_early; - /* waitcnt processing will be compiled out if !QUEUED_LOCK_STAT */ - for (;; waitcnt++) { + for (;;) { for (wait_early = false, loop = SPIN_THRESHOLD; loop; loop--) { if (READ_ONCE(node->locked)) return; @@ -315,7 +315,6 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev) if (!READ_ONCE(node->locked)) { qstat_inc(qstat_pv_wait_node, true); - qstat_inc(qstat_pv_wait_again, waitcnt); qstat_inc(qstat_pv_wait_early, wait_early); pv_wait(&pn->state, vcpu_halted); } @@ -456,12 +455,9 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node) pv_wait(&l->locked, _Q_SLOW_VAL); /* - * The unlocker should have freed the lock before kicking the - * CPU. So if the lock is still not free, it is a spurious - * wakeup or another vCPU has stolen the lock. The current - * vCPU should spin again. + * Because of lock stealing, the queue head vCPU may not be + * able to acquire the lock before it has to wait again. */ - qstat_inc(qstat_pv_spurious_wakeup, READ_ONCE(l->locked)); } /* @@ -544,7 +540,7 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock) * unhash. Otherwise it would be possible to have multiple @lock * entries, which would be BAD. */ - locked = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0); + locked = cmpxchg_release(&l->locked, _Q_LOCKED_VAL, 0); if (likely(locked == _Q_LOCKED_VAL)) return; diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h index b9d031516254..e852be4851fc 100644 --- a/kernel/locking/qspinlock_stat.h +++ b/kernel/locking/qspinlock_stat.h @@ -24,8 +24,8 @@ * pv_latency_wake - average latency (ns) from vCPU kick to wakeup * pv_lock_slowpath - # of locking operations via the slowpath * pv_lock_stealing - # of lock stealing operations - * pv_spurious_wakeup - # of spurious wakeups - * pv_wait_again - # of vCPU wait's that happened after a vCPU kick + * pv_spurious_wakeup - # of spurious wakeups in non-head vCPUs + * pv_wait_again - # of wait's after a queue head vCPU kick * pv_wait_early - # of early vCPU wait's * pv_wait_head - # of vCPU wait's at the queue head * pv_wait_node - # of vCPU wait's at a non-head queue node @@ -108,11 +108,7 @@ static ssize_t qstat_read(struct file *file, char __user *user_buf, /* * Get the counter ID stored in file->f_inode->i_private */ - if (!file->f_inode) { - WARN_ON_ONCE(1); - return -EBADF; - } - counter = (long)(file->f_inode->i_private); + counter = (long)file_inode(file)->i_private; if (counter >= qstat_num) return -EBADF; @@ -177,11 +173,7 @@ static ssize_t qstat_write(struct file *file, const char __user *user_buf, /* * Get the counter ID stored in file->f_inode->i_private */ - if (!file->f_inode) { - WARN_ON_ONCE(1); - return -EBADF; - } - if ((long)(file->f_inode->i_private) != qstat_reset_cnts) + if ((long)file_inode(file)->i_private != qstat_reset_cnts) return count; for_each_possible_cpu(cpu) { diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 1ec0f48962b3..2f443ed2320a 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -65,8 +65,72 @@ static inline void clear_rt_mutex_waiters(struct rt_mutex *lock) static void fixup_rt_mutex_waiters(struct rt_mutex *lock) { - if (!rt_mutex_has_waiters(lock)) - clear_rt_mutex_waiters(lock); + unsigned long owner, *p = (unsigned long *) &lock->owner; + + if (rt_mutex_has_waiters(lock)) + return; + + /* + * The rbtree has no waiters enqueued, now make sure that the + * lock->owner still has the waiters bit set, otherwise the + * following can happen: + * + * CPU 0 CPU 1 CPU2 + * l->owner=T1 + * rt_mutex_lock(l) + * lock(l->lock) + * l->owner = T1 | HAS_WAITERS; + * enqueue(T2) + * boost() + * unlock(l->lock) + * block() + * + * rt_mutex_lock(l) + * lock(l->lock) + * l->owner = T1 | HAS_WAITERS; + * enqueue(T3) + * boost() + * unlock(l->lock) + * block() + * signal(->T2) signal(->T3) + * lock(l->lock) + * dequeue(T2) + * deboost() + * unlock(l->lock) + * lock(l->lock) + * dequeue(T3) + * ==> wait list is empty + * deboost() + * unlock(l->lock) + * lock(l->lock) + * fixup_rt_mutex_waiters() + * if (wait_list_empty(l) { + * l->owner = owner + * owner = l->owner & ~HAS_WAITERS; + * ==> l->owner = T1 + * } + * lock(l->lock) + * rt_mutex_unlock(l) fixup_rt_mutex_waiters() + * if (wait_list_empty(l) { + * owner = l->owner & ~HAS_WAITERS; + * cmpxchg(l->owner, T1, NULL) + * ===> Success (l->owner = NULL) + * + * l->owner = owner + * ==> l->owner = T1 + * } + * + * With the check for the waiter bit in place T3 on CPU2 will not + * overwrite. All tasks fiddling with the waiters bit are + * serialized by l->lock, so nothing else can modify the waiters + * bit. If the bit is set then nothing can change l->owner either + * so the simple RMW is safe. The cmpxchg() will simply fail if it + * happens in the middle of the RMW because the waiters bit is + * still set. + */ + owner = READ_ONCE(*p); + if (owner & RT_MUTEX_HAS_WAITERS) + WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS); } /* @@ -1382,7 +1446,7 @@ rt_mutex_fastunlock(struct rt_mutex *lock, bool (*slowfn)(struct rt_mutex *lock, struct wake_q_head *wqh)) { - WAKE_Q(wake_q); + DEFINE_WAKE_Q(wake_q); if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) { rt_mutex_deadlock_account_unlock(current); @@ -1555,11 +1619,15 @@ EXPORT_SYMBOL_GPL(__rt_mutex_init); * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a * proxy owner * - * @lock: the rt_mutex to be locked + * @lock: the rt_mutex to be locked * @proxy_owner:the task to set as owner * * No locking. Caller has to do serializing itself - * Special API call for PI-futex support + * + * Special API call for PI-futex support. This initializes the rtmutex and + * assigns it to @proxy_owner. Concurrent operations on the rtmutex are not + * possible at this point because the pi_state which contains the rtmutex + * is not yet visible to other tasks. */ void rt_mutex_init_proxy_locked(struct rt_mutex *lock, struct task_struct *proxy_owner) @@ -1573,10 +1641,14 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock, /** * rt_mutex_proxy_unlock - release a lock on behalf of owner * - * @lock: the rt_mutex to be locked + * @lock: the rt_mutex to be locked * * No locking. Caller has to do serializing itself - * Special API call for PI-futex support + * + * Special API call for PI-futex support. This merrily cleans up the rtmutex + * (debugging) state. Concurrent operations on this rt_mutex are not + * possible because it belongs to the pi_state which is about to be freed + * and it is not longer visible to other tasks. */ void rt_mutex_proxy_unlock(struct rt_mutex *lock, struct task_struct *proxy_owner) diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h index 4f5f83c7d2d3..990134617b4c 100644 --- a/kernel/locking/rtmutex_common.h +++ b/kernel/locking/rtmutex_common.h @@ -71,12 +71,12 @@ task_top_pi_waiter(struct task_struct *p) * lock->owner state tracking: */ #define RT_MUTEX_HAS_WAITERS 1UL -#define RT_MUTEX_OWNER_MASKALL 1UL static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock) { - return (struct task_struct *) - ((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL); + unsigned long owner = (unsigned long) READ_ONCE(lock->owner); + + return (struct task_struct *) (owner & ~RT_MUTEX_HAS_WAITERS); } /* diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c index 447e08de1fab..631506004f9e 100644 --- a/kernel/locking/rwsem-xadd.c +++ b/kernel/locking/rwsem-xadd.c @@ -121,16 +121,19 @@ enum rwsem_wake_type { * - woken process blocks are discarded from the list after having task zeroed * - writers are only marked woken if downgrading is false */ -static struct rw_semaphore * -__rwsem_mark_wake(struct rw_semaphore *sem, - enum rwsem_wake_type wake_type, struct wake_q_head *wake_q) +static void __rwsem_mark_wake(struct rw_semaphore *sem, + enum rwsem_wake_type wake_type, + struct wake_q_head *wake_q) { - struct rwsem_waiter *waiter; - struct task_struct *tsk; - struct list_head *next; - long oldcount, woken, loop, adjustment; + struct rwsem_waiter *waiter, *tmp; + long oldcount, woken = 0, adjustment = 0; + + /* + * Take a peek at the queue head waiter such that we can determine + * the wakeup(s) to perform. + */ + waiter = list_first_entry(&sem->wait_list, struct rwsem_waiter, list); - waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list); if (waiter->type == RWSEM_WAITING_FOR_WRITE) { if (wake_type == RWSEM_WAKE_ANY) { /* @@ -142,19 +145,19 @@ __rwsem_mark_wake(struct rw_semaphore *sem, */ wake_q_add(wake_q, waiter->task); } - goto out; + + return; } - /* Writers might steal the lock before we grant it to the next reader. + /* + * Writers might steal the lock before we grant it to the next reader. * We prefer to do the first reader grant before counting readers * so we can bail out early if a writer stole the lock. */ - adjustment = 0; if (wake_type != RWSEM_WAKE_READ_OWNED) { adjustment = RWSEM_ACTIVE_READ_BIAS; try_reader_grant: oldcount = atomic_long_fetch_add(adjustment, &sem->count); - if (unlikely(oldcount < RWSEM_WAITING_BIAS)) { /* * If the count is still less than RWSEM_WAITING_BIAS @@ -164,7 +167,8 @@ __rwsem_mark_wake(struct rw_semaphore *sem, */ if (atomic_long_add_return(-adjustment, &sem->count) < RWSEM_WAITING_BIAS) - goto out; + return; + /* Last active locker left. Retry waking readers. */ goto try_reader_grant; } @@ -176,38 +180,23 @@ __rwsem_mark_wake(struct rw_semaphore *sem, rwsem_set_reader_owned(sem); } - /* Grant an infinite number of read locks to the readers at the front - * of the queue. Note we increment the 'active part' of the count by - * the number of readers before waking any processes up. + /* + * Grant an infinite number of read locks to the readers at the front + * of the queue. We know that woken will be at least 1 as we accounted + * for above. Note we increment the 'active part' of the count by the + * number of readers before waking any processes up. */ - woken = 0; - do { - woken++; + list_for_each_entry_safe(waiter, tmp, &sem->wait_list, list) { + struct task_struct *tsk; - if (waiter->list.next == &sem->wait_list) + if (waiter->type == RWSEM_WAITING_FOR_WRITE) break; - waiter = list_entry(waiter->list.next, - struct rwsem_waiter, list); - - } while (waiter->type != RWSEM_WAITING_FOR_WRITE); - - adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment; - if (waiter->type != RWSEM_WAITING_FOR_WRITE) - /* hit end of list above */ - adjustment -= RWSEM_WAITING_BIAS; - - if (adjustment) - atomic_long_add(adjustment, &sem->count); - - next = sem->wait_list.next; - loop = woken; - do { - waiter = list_entry(next, struct rwsem_waiter, list); - next = waiter->list.next; + woken++; tsk = waiter->task; wake_q_add(wake_q, tsk); + list_del(&waiter->list); /* * Ensure that the last operation is setting the reader * waiter to nil such that rwsem_down_read_failed() cannot @@ -215,13 +204,16 @@ __rwsem_mark_wake(struct rw_semaphore *sem, * to the task to wakeup. */ smp_store_release(&waiter->task, NULL); - } while (--loop); + } - sem->wait_list.next = next; - next->prev = &sem->wait_list; + adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment; + if (list_empty(&sem->wait_list)) { + /* hit end of list above */ + adjustment -= RWSEM_WAITING_BIAS; + } - out: - return sem; + if (adjustment) + atomic_long_add(adjustment, &sem->count); } /* @@ -233,9 +225,8 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) long count, adjustment = -RWSEM_ACTIVE_READ_BIAS; struct rwsem_waiter waiter; struct task_struct *tsk = current; - WAKE_Q(wake_q); + DEFINE_WAKE_Q(wake_q); - /* set up my own style of waitqueue */ waiter.task = tsk; waiter.type = RWSEM_WAITING_FOR_READ; @@ -247,7 +238,8 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) /* we're now waiting on the lock, but no longer actively locking */ count = atomic_long_add_return(adjustment, &sem->count); - /* If there are no active locks, wake the front queued process(es). + /* + * If there are no active locks, wake the front queued process(es). * * If there are no writers and we are first in the queue, * wake our own waiter to join the existing active readers ! @@ -255,7 +247,7 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem) if (count == RWSEM_WAITING_BIAS || (count > RWSEM_WAITING_BIAS && adjustment != -RWSEM_ACTIVE_READ_BIAS)) - sem = __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q); + __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q); raw_spin_unlock_irq(&sem->wait_lock); wake_up_q(&wake_q); @@ -344,7 +336,11 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem) goto done; } - ret = owner->on_cpu; + /* + * As lock holder preemption issue, we both skip spinning if task is not + * on cpu or its cpu is preempted + */ + ret = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner)); done: rcu_read_unlock(); return ret; @@ -370,13 +366,17 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem) */ barrier(); - /* abort spinning when need_resched or owner is not running */ - if (!owner->on_cpu || need_resched()) { + /* + * abort spinning when need_resched or owner is not running or + * owner's cpu is preempted. + */ + if (!owner->on_cpu || need_resched() || + vcpu_is_preempted(task_cpu(owner))) { rcu_read_unlock(); return false; } - cpu_relax_lowlatency(); + cpu_relax(); } rcu_read_unlock(); out: @@ -431,7 +431,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem) * memory barriers as we'll eventually observe the right * values at the cost of a few extra spins. */ - cpu_relax_lowlatency(); + cpu_relax(); } osq_unlock(&sem->osq); done: @@ -469,7 +469,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state) bool waiting = true; /* any queued threads before us */ struct rwsem_waiter waiter; struct rw_semaphore *ret = sem; - WAKE_Q(wake_q); + DEFINE_WAKE_Q(wake_q); /* undo write bias from down_write operation, stop active locking */ count = atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS, &sem->count); @@ -503,9 +503,9 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state) * wake any read locks that were queued ahead of us. */ if (count > RWSEM_WAITING_BIAS) { - WAKE_Q(wake_q); + DEFINE_WAKE_Q(wake_q); - sem = __rwsem_mark_wake(sem, RWSEM_WAKE_READERS, &wake_q); + __rwsem_mark_wake(sem, RWSEM_WAKE_READERS, &wake_q); /* * The wakeup is normally called _after_ the wait_lock * is released, but given that we are proactively waking @@ -579,7 +579,7 @@ __visible struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) { unsigned long flags; - WAKE_Q(wake_q); + DEFINE_WAKE_Q(wake_q); /* * If a spinner is present, it is not necessary to do the wakeup. @@ -614,9 +614,8 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem) raw_spin_lock_irqsave(&sem->wait_lock, flags); locked: - /* do nothing if list empty */ if (!list_empty(&sem->wait_list)) - sem = __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q); + __rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); wake_up_q(&wake_q); @@ -634,13 +633,12 @@ __visible struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem) { unsigned long flags; - WAKE_Q(wake_q); + DEFINE_WAKE_Q(wake_q); raw_spin_lock_irqsave(&sem->wait_lock, flags); - /* do nothing if list empty */ if (!list_empty(&sem->wait_list)) - sem = __rwsem_mark_wake(sem, RWSEM_WAKE_READ_OWNED, &wake_q); + __rwsem_mark_wake(sem, RWSEM_WAKE_READ_OWNED, &wake_q); raw_spin_unlock_irqrestore(&sem->wait_lock, flags); wake_up_q(&wake_q); |