diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/futex.c | 137 | ||||
| -rw-r--r-- | kernel/hrtimer.c | 53 | ||||
| -rw-r--r-- | kernel/module.c | 1 | ||||
| -rw-r--r-- | kernel/perf_event.c | 2 | ||||
| -rw-r--r-- | kernel/relay.c | 2 | ||||
| -rw-r--r-- | kernel/sched_clock.c | 4 | ||||
| -rw-r--r-- | kernel/time/clocksource.c | 4 | ||||
| -rw-r--r-- | kernel/trace/ftrace.c | 23 | ||||
| -rw-r--r-- | kernel/trace/trace.c | 2 | ||||
| -rw-r--r-- | kernel/trace/trace_events.c | 7 |
10 files changed, 132 insertions, 103 deletions
diff --git a/kernel/futex.c b/kernel/futex.c index 248dd11..b911adc 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -89,36 +89,36 @@ struct futex_pi_state { union futex_key key; }; -/* - * We use this hashed waitqueue instead of a normal wait_queue_t, so +/** + * struct futex_q - The hashed futex queue entry, one per waiting task + * @task: the task waiting on the futex + * @lock_ptr: the hash bucket lock + * @key: the key the futex is hashed on + * @pi_state: optional priority inheritance state + * @rt_waiter: rt_waiter storage for use with requeue_pi + * @requeue_pi_key: the requeue_pi target futex key + * @bitset: bitset for the optional bitmasked wakeup + * + * We use this hashed waitqueue, instead of a normal wait_queue_t, so * we can wake only the relevant ones (hashed queues may be shared). * * A futex_q has a woken state, just like tasks have TASK_RUNNING. * It is considered woken when plist_node_empty(&q->list) || q->lock_ptr == 0. * The order of wakup is always to make the first condition true, then - * wake up q->waiter, then make the second condition true. + * the second. + * + * PI futexes are typically woken before they are removed from the hash list via + * the rt_mutex code. See unqueue_me_pi(). */ struct futex_q { struct plist_node list; - /* Waiter reference */ - struct task_struct *task; - /* Which hash list lock to use: */ + struct task_struct *task; spinlock_t *lock_ptr; - - /* Key which the futex is hashed on: */ union futex_key key; - - /* Optional priority inheritance state: */ struct futex_pi_state *pi_state; - - /* rt_waiter storage for requeue_pi: */ struct rt_mutex_waiter *rt_waiter; - - /* The expected requeue pi target futex key: */ union futex_key *requeue_pi_key; - - /* Bitset for the optional bitmasked wakeup */ u32 bitset; }; @@ -198,11 +198,12 @@ static void drop_futex_key_refs(union futex_key *key) } /** - * get_futex_key - Get parameters which are the keys for a futex. - * @uaddr: virtual address of the futex - * @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED - * @key: address where result is stored. - * @rw: mapping needs to be read/write (values: VERIFY_READ, VERIFY_WRITE) + * get_futex_key() - Get parameters which are the keys for a futex + * @uaddr: virtual address of the futex + * @fshared: 0 for a PROCESS_PRIVATE futex, 1 for PROCESS_SHARED + * @key: address where result is stored. + * @rw: mapping needs to be read/write (values: VERIFY_READ, + * VERIFY_WRITE) * * Returns a negative error code or 0 * The key words are stored in *key on success. @@ -288,8 +289,8 @@ void put_futex_key(int fshared, union futex_key *key) drop_futex_key_refs(key); } -/* - * fault_in_user_writeable - fault in user address and verify RW access +/** + * fault_in_user_writeable() - Fault in user address and verify RW access * @uaddr: pointer to faulting user space address * * Slow path to fixup the fault we just took in the atomic write @@ -309,8 +310,8 @@ static int fault_in_user_writeable(u32 __user *uaddr) /** * futex_top_waiter() - Return the highest priority waiter on a futex - * @hb: the hash bucket the futex_q's reside in - * @key: the futex key (to distinguish it from other futex futex_q's) + * @hb: the hash bucket the futex_q's reside in + * @key: the futex key (to distinguish it from other futex futex_q's) * * Must be called with the hb lock held. */ @@ -588,7 +589,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb, } /** - * futex_lock_pi_atomic() - atomic work required to acquire a pi aware futex + * futex_lock_pi_atomic() - Atomic work required to acquire a pi aware futex * @uaddr: the pi futex user address * @hb: the pi futex hash bucket * @key: the futex key associated with uaddr and hb @@ -1011,9 +1012,9 @@ void requeue_futex(struct futex_q *q, struct futex_hash_bucket *hb1, /** * requeue_pi_wake_futex() - Wake a task that acquired the lock during requeue - * q: the futex_q - * key: the key of the requeue target futex - * hb: the hash_bucket of the requeue target futex + * @q: the futex_q + * @key: the key of the requeue target futex + * @hb: the hash_bucket of the requeue target futex * * During futex_requeue, with requeue_pi=1, it is possible to acquire the * target futex if it is uncontended or via a lock steal. Set the futex_q key @@ -1350,6 +1351,25 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) return hb; } +static inline void +queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb) +{ + spin_unlock(&hb->lock); + drop_futex_key_refs(&q->key); +} + +/** + * queue_me() - Enqueue the futex_q on the futex_hash_bucket + * @q: The futex_q to enqueue + * @hb: The destination hash bucket + * + * The hb->lock must be held by the caller, and is released here. A call to + * queue_me() is typically paired with exactly one call to unqueue_me(). The + * exceptions involve the PI related operations, which may use unqueue_me_pi() + * or nothing if the unqueue is done as part of the wake process and the unqueue + * state is implicit in the state of woken task (see futex_wait_requeue_pi() for + * an example). + */ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb) { int prio; @@ -1373,19 +1393,17 @@ static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb) spin_unlock(&hb->lock); } -static inline void -queue_unlock(struct futex_q *q, struct futex_hash_bucket *hb) -{ - spin_unlock(&hb->lock); - drop_futex_key_refs(&q->key); -} - -/* - * queue_me and unqueue_me must be called as a pair, each - * exactly once. They are called with the hashed spinlock held. +/** + * unqueue_me() - Remove the futex_q from its futex_hash_bucket + * @q: The futex_q to unqueue + * + * The q->lock_ptr must not be held by the caller. A call to unqueue_me() must + * be paired with exactly one earlier call to queue_me(). + * + * Returns: + * 1 - if the futex_q was still queued (and we removed unqueued it) + * 0 - if the futex_q was already removed by the waking thread */ - -/* Return 1 if we were still queued (ie. 0 means we were woken) */ static int unqueue_me(struct futex_q *q) { spinlock_t *lock_ptr; @@ -1638,17 +1656,14 @@ out: static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q, struct hrtimer_sleeper *timeout) { - queue_me(q, hb); - /* - * There might have been scheduling since the queue_me(), as we - * cannot hold a spinlock across the get_user() in case it - * faults, and we cannot just set TASK_INTERRUPTIBLE state when - * queueing ourselves into the futex hash. This code thus has to - * rely on the futex_wake() code removing us from hash when it - * wakes us up. + * The task state is guaranteed to be set before another task can + * wake it. set_current_state() is implemented using set_mb() and + * queue_me() calls spin_unlock() upon completion, both serializing + * access to the hash list and forcing another memory barrier. */ set_current_state(TASK_INTERRUPTIBLE); + queue_me(q, hb); /* Arm the timer */ if (timeout) { @@ -1658,8 +1673,8 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q, } /* - * !plist_node_empty() is safe here without any lock. - * q.lock_ptr != 0 is not safe, because of ordering against wakeup. + * If we have been removed from the hash list, then another task + * has tried to wake us, and we can skip the call to schedule(). */ if (likely(!plist_node_empty(&q->list))) { /* @@ -2114,12 +2129,12 @@ int handle_early_requeue_pi_wakeup(struct futex_hash_bucket *hb, /** * futex_wait_requeue_pi() - Wait on uaddr and take uaddr2 - * @uaddr: the futex we initialyl wait on (non-pi) + * @uaddr: the futex we initially wait on (non-pi) * @fshared: whether the futexes are shared (1) or not (0). They must be * the same type, no requeueing from private to shared, etc. * @val: the expected value of uaddr * @abs_time: absolute timeout - * @bitset: 32 bit wakeup bitset set by userspace, defaults to all. + * @bitset: 32 bit wakeup bitset set by userspace, defaults to all * @clockrt: whether to use CLOCK_REALTIME (1) or CLOCK_MONOTONIC (0) * @uaddr2: the pi futex we will take prior to returning to user-space * @@ -2246,7 +2261,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, int fshared, res = fixup_owner(uaddr2, fshared, &q, !ret); /* * If fixup_owner() returned an error, proprogate that. If it - * acquired the lock, clear our -ETIMEDOUT or -EINTR. + * acquired the lock, clear -ETIMEDOUT or -EINTR. */ if (res) ret = (res < 0) ? res : 0; @@ -2302,9 +2317,9 @@ out: */ /** - * sys_set_robust_list - set the robust-futex list head of a task - * @head: pointer to the list-head - * @len: length of the list-head, as userspace expects + * sys_set_robust_list() - Set the robust-futex list head of a task + * @head: pointer to the list-head + * @len: length of the list-head, as userspace expects */ SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, size_t, len) @@ -2323,10 +2338,10 @@ SYSCALL_DEFINE2(set_robust_list, struct robust_list_head __user *, head, } /** - * sys_get_robust_list - get the robust-futex list head of a task - * @pid: pid of the process [zero for current task] - * @head_ptr: pointer to a list-head pointer, the kernel fills it in - * @len_ptr: pointer to a length field, the kernel fills in the header size + * sys_get_robust_list() - Get the robust-futex list head of a task + * @pid: pid of the process [zero for current task] + * @head_ptr: pointer to a list-head pointer, the kernel fills it in + * @len_ptr: pointer to a length field, the kernel fills in the header size */ SYSCALL_DEFINE3(get_robust_list, int, pid, struct robust_list_head __user * __user *, head_ptr, diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index e5d98ce..6d70204 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -509,13 +509,14 @@ static inline int hrtimer_hres_active(void) * next event * Called with interrupts disabled and base->lock held */ -static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base) +static void +hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) { int i; struct hrtimer_clock_base *base = cpu_base->clock_base; - ktime_t expires; + ktime_t expires, expires_next; - cpu_base->expires_next.tv64 = KTIME_MAX; + expires_next.tv64 = KTIME_MAX; for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) { struct hrtimer *timer; @@ -531,10 +532,15 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base) */ if (expires.tv64 < 0) expires.tv64 = 0; - if (expires.tv64 < cpu_base->expires_next.tv64) - cpu_base->expires_next = expires; + if (expires.tv64 < expires_next.tv64) + expires_next = expires; } + if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64) + return; + + cpu_base->expires_next.tv64 = expires_next.tv64; + if (cpu_base->expires_next.tv64 != KTIME_MAX) tick_program_event(cpu_base->expires_next, 1); } @@ -617,7 +623,7 @@ static void retrigger_next_event(void *arg) base->clock_base[CLOCK_REALTIME].offset = timespec_to_ktime(realtime_offset); - hrtimer_force_reprogram(base); + hrtimer_force_reprogram(base, 0); spin_unlock(&base->lock); } @@ -730,7 +736,8 @@ static int hrtimer_switch_to_hres(void) static inline int hrtimer_hres_active(void) { return 0; } static inline int hrtimer_is_hres_enabled(void) { return 0; } static inline int hrtimer_switch_to_hres(void) { return 0; } -static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base) { } +static inline void +hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { } static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, struct hrtimer_clock_base *base, int wakeup) @@ -873,19 +880,29 @@ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, unsigned long newstate, int reprogram) { - if (timer->state & HRTIMER_STATE_ENQUEUED) { - /* - * Remove the timer from the rbtree and replace the - * first entry pointer if necessary. - */ - if (base->first == &timer->node) { - base->first = rb_next(&timer->node); - /* Reprogram the clock event device. if enabled */ - if (reprogram && hrtimer_hres_active()) - hrtimer_force_reprogram(base->cpu_base); + if (!(timer->state & HRTIMER_STATE_ENQUEUED)) + goto out; + + /* + * Remove the timer from the rbtree and replace the first + * entry pointer if necessary. + */ + if (base->first == &timer->node) { + base->first = rb_next(&timer->node); +#ifdef CONFIG_HIGH_RES_TIMERS + /* Reprogram the clock event device. if enabled */ + if (reprogram && hrtimer_hres_active()) { + ktime_t expires; + + expires = ktime_sub(hrtimer_get_expires(timer), + base->offset); + if (base->cpu_base->expires_next.tv64 == expires.tv64) + hrtimer_force_reprogram(base->cpu_base, 1); } - rb_erase(&timer->node, &base->active); +#endif } + rb_erase(&timer->node, &base->active); +out: timer->state = newstate; } diff --git a/kernel/module.c b/kernel/module.c index 5a29397..fe748a8 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3091,7 +3091,6 @@ void module_layout(struct module *mod, struct modversion_info *ver, struct kernel_param *kp, struct kernel_symbol *ks, - struct marker *marker, struct tracepoint *tp) { } diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 76ac4db..0f86feb 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -2253,7 +2253,7 @@ static void perf_mmap_close(struct vm_area_struct *vma) } } -static struct vm_operations_struct perf_mmap_vmops = { +static const struct vm_operations_struct perf_mmap_vmops = { .open = perf_mmap_open, .close = perf_mmap_close, .fault = perf_mmap_fault, diff --git a/kernel/relay.c b/kernel/relay.c index bc18854..760c262 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -60,7 +60,7 @@ static int relay_buf_fault(struct vm_area_struct *vma, struct vm_fault *vmf) /* * vm_ops for relay file mappings. */ -static struct vm_operations_struct relay_file_mmap_ops = { +static const struct vm_operations_struct relay_file_mmap_ops = { .fault = relay_buf_fault, .close = relay_file_mmap_close, }; diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c index ac2e1dc..479ce56 100644 --- a/kernel/sched_clock.c +++ b/kernel/sched_clock.c @@ -127,7 +127,7 @@ again: clock = wrap_max(clock, min_clock); clock = wrap_min(clock, max_clock); - if (cmpxchg(&scd->clock, old_clock, clock) != old_clock) + if (cmpxchg64(&scd->clock, old_clock, clock) != old_clock) goto again; return clock; @@ -163,7 +163,7 @@ again: val = remote_clock; } - if (cmpxchg(ptr, old_val, val) != old_val) + if (cmpxchg64(ptr, old_val, val) != old_val) goto again; return val; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 0911334..5e18c6a 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -394,15 +394,11 @@ void clocksource_resume(void) { struct clocksource *cs; - mutex_lock(&clocksource_mutex); - list_for_each_entry(cs, &clocksource_list, list) if (cs->resume) cs->resume(); clocksource_resume_watchdog(); - - mutex_unlock(&clocksource_mutex); } /** diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index a142579..46592fe 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1621,8 +1621,10 @@ ftrace_regex_open(struct inode *inode, struct file *file, int enable) if (!ret) { struct seq_file *m = file->private_data; m->private = iter; - } else + } else { + trace_parser_put(&iter->parser); kfree(iter); + } } else file->private_data = iter; mutex_unlock(&ftrace_regex_lock); @@ -2202,7 +2204,7 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, struct trace_parser *parser; ssize_t ret, read; - if (!cnt || cnt < 0) + if (!cnt) return 0; mutex_lock(&ftrace_regex_lock); @@ -2216,7 +2218,7 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, parser = &iter->parser; read = trace_get_user(parser, ubuf, cnt, ppos); - if (trace_parser_loaded(parser) && + if (read >= 0 && trace_parser_loaded(parser) && !trace_parser_cont(parser)) { ret = ftrace_process_regex(parser->buffer, parser->idx, enable); @@ -2552,8 +2554,7 @@ ftrace_graph_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_parser parser; - size_t read = 0; - ssize_t ret; + ssize_t read, ret; if (!cnt || cnt < 0) return 0; @@ -2562,29 +2563,31 @@ ftrace_graph_write(struct file *file, const char __user *ubuf, if (ftrace_graph_count >= FTRACE_GRAPH_MAX_FUNCS) { ret = -EBUSY; - goto out; + goto out_unlock; } if (trace_parser_get_init(&parser, FTRACE_BUFF_MAX)) { ret = -ENOMEM; - goto out; + goto out_unlock; } read = trace_get_user(&parser, ubuf, cnt, ppos); - if (trace_parser_loaded((&parser))) { + if (read >= 0 && trace_parser_loaded((&parser))) { parser.buffer[parser.idx] = 0; /* we allow only one expression at a time */ ret = ftrace_set_func(ftrace_graph_funcs, &ftrace_graph_count, parser.buffer); if (ret) - goto out; + goto out_free; } ret = read; - out: + +out_free: trace_parser_put(&parser); +out_unlock: mutex_unlock(&graph_lock); return ret; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 411af37..4506826 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -415,7 +415,7 @@ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, /* read the non-space input */ while (cnt && !isspace(ch)) { - if (parser->idx < parser->size) + if (parser->idx < parser->size - 1) parser->buffer[parser->idx++] = ch; else { ret = -EINVAL; diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 6f03c8a..d128f65 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -232,10 +232,9 @@ ftrace_event_write(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_parser parser; - size_t read = 0; - ssize_t ret; + ssize_t read, ret; - if (!cnt || cnt < 0) + if (!cnt) return 0; ret = tracing_update_buffers(); @@ -247,7 +246,7 @@ ftrace_event_write(struct file *file, const char __user *ubuf, read = trace_get_user(&parser, ubuf, cnt, ppos); - if (trace_parser_loaded((&parser))) { + if (read >= 0 && trace_parser_loaded((&parser))) { int set = 1; if (*parser.buffer == '!') |