diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/cgroup.c | 15 | ||||
-rw-r--r-- | kernel/futex.c | 137 | ||||
-rw-r--r-- | kernel/hrtimer.c | 53 | ||||
-rw-r--r-- | kernel/kprobes.c | 4 | ||||
-rw-r--r-- | kernel/module.c | 8 | ||||
-rw-r--r-- | kernel/perf_event.c | 2 | ||||
-rw-r--r-- | kernel/rcutree_trace.c | 10 | ||||
-rw-r--r-- | kernel/relay.c | 2 | ||||
-rw-r--r-- | kernel/res_counter.c | 18 | ||||
-rw-r--r-- | kernel/sched.c | 2 | ||||
-rw-r--r-- | kernel/sched_clock.c | 4 | ||||
-rw-r--r-- | kernel/time/clocksource.c | 4 | ||||
-rw-r--r-- | kernel/time/timer_list.c | 2 | ||||
-rw-r--r-- | kernel/time/timer_stats.c | 2 | ||||
-rw-r--r-- | kernel/trace/blktrace.c | 39 | ||||
-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 |
18 files changed, 196 insertions, 138 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 7ccba4bc5e3b..ca83b73fba19 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -703,7 +703,7 @@ static int cgroup_mkdir(struct inode *dir, struct dentry *dentry, int mode); static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry); static int cgroup_populate_dir(struct cgroup *cgrp); static const struct inode_operations cgroup_dir_inode_operations; -static struct file_operations proc_cgroupstats_operations; +static const struct file_operations proc_cgroupstats_operations; static struct backing_dev_info cgroup_backing_dev_info = { .name = "cgroup", @@ -1863,7 +1863,7 @@ static int cgroup_seqfile_release(struct inode *inode, struct file *file) return single_release(inode, file); } -static struct file_operations cgroup_seqfile_operations = { +static const struct file_operations cgroup_seqfile_operations = { .read = seq_read, .write = cgroup_file_write, .llseek = seq_lseek, @@ -1922,7 +1922,7 @@ static int cgroup_rename(struct inode *old_dir, struct dentry *old_dentry, return simple_rename(old_dir, old_dentry, new_dir, new_dentry); } -static struct file_operations cgroup_file_operations = { +static const struct file_operations cgroup_file_operations = { .read = cgroup_file_read, .write = cgroup_file_write, .llseek = generic_file_llseek, @@ -3369,7 +3369,7 @@ static int cgroup_open(struct inode *inode, struct file *file) return single_open(file, proc_cgroup_show, pid); } -struct file_operations proc_cgroup_operations = { +const struct file_operations proc_cgroup_operations = { .open = cgroup_open, .read = seq_read, .llseek = seq_lseek, @@ -3398,7 +3398,7 @@ static int cgroupstats_open(struct inode *inode, struct file *file) return single_open(file, proc_cgroupstats_show, NULL); } -static struct file_operations proc_cgroupstats_operations = { +static const struct file_operations proc_cgroupstats_operations = { .open = cgroupstats_open, .read = seq_read, .llseek = seq_lseek, @@ -3708,8 +3708,10 @@ static void check_for_release(struct cgroup *cgrp) void __css_put(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; + int val; rcu_read_lock(); - if (atomic_dec_return(&css->refcnt) == 1) { + val = atomic_dec_return(&css->refcnt); + if (val == 1) { if (notify_on_release(cgrp)) { set_bit(CGRP_RELEASABLE, &cgrp->flags); check_for_release(cgrp); @@ -3717,6 +3719,7 @@ void __css_put(struct cgroup_subsys_state *css) cgroup_wakeup_rmdir_waiter(cgrp); } rcu_read_unlock(); + WARN_ON_ONCE(val < 1); } /* diff --git a/kernel/futex.c b/kernel/futex.c index 248dd119a86e..b911adceb2c4 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 e5d98ce50f89..6d7020490f94 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/kprobes.c b/kernel/kprobes.c index cfadc1291d0b..5240d75f4c60 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1333,7 +1333,7 @@ static int __kprobes kprobes_open(struct inode *inode, struct file *filp) return seq_open(filp, &kprobes_seq_ops); } -static struct file_operations debugfs_kprobes_operations = { +static const struct file_operations debugfs_kprobes_operations = { .open = kprobes_open, .read = seq_read, .llseek = seq_lseek, @@ -1515,7 +1515,7 @@ static ssize_t write_enabled_file_bool(struct file *file, return count; } -static struct file_operations fops_kp = { +static const struct file_operations fops_kp = { .read = read_enabled_file_bool, .write = write_enabled_file_bool, }; diff --git a/kernel/module.c b/kernel/module.c index 5a29397ca4b6..8b7d8805819d 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1992,12 +1992,14 @@ static inline unsigned long layout_symtab(struct module *mod, Elf_Shdr *sechdrs, unsigned int symindex, unsigned int strindex, - const Elf_Hdr *hdr, + const Elf_Ehdr *hdr, const char *secstrings, unsigned long *pstroffs, unsigned long *strmap) { + return 0; } + static inline void add_kallsyms(struct module *mod, Elf_Shdr *sechdrs, unsigned int shnum, @@ -2081,9 +2083,8 @@ static noinline struct module *load_module(void __user *umod, struct module *mod; long err = 0; void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */ -#ifdef CONFIG_KALLSYMS unsigned long symoffs, stroffs, *strmap; -#endif + mm_segment_t old_fs; DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n", @@ -3091,7 +3092,6 @@ 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 76ac4db405e9..0f86feb6db0c 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/rcutree_trace.c b/kernel/rcutree_trace.c index c89f5e9fd173..179e6ad80dc0 100644 --- a/kernel/rcutree_trace.c +++ b/kernel/rcutree_trace.c @@ -93,7 +93,7 @@ static int rcudata_open(struct inode *inode, struct file *file) return single_open(file, show_rcudata, NULL); } -static struct file_operations rcudata_fops = { +static const struct file_operations rcudata_fops = { .owner = THIS_MODULE, .open = rcudata_open, .read = seq_read, @@ -145,7 +145,7 @@ static int rcudata_csv_open(struct inode *inode, struct file *file) return single_open(file, show_rcudata_csv, NULL); } -static struct file_operations rcudata_csv_fops = { +static const struct file_operations rcudata_csv_fops = { .owner = THIS_MODULE, .open = rcudata_csv_open, .read = seq_read, @@ -196,7 +196,7 @@ static int rcuhier_open(struct inode *inode, struct file *file) return single_open(file, show_rcuhier, NULL); } -static struct file_operations rcuhier_fops = { +static const struct file_operations rcuhier_fops = { .owner = THIS_MODULE, .open = rcuhier_open, .read = seq_read, @@ -222,7 +222,7 @@ static int rcugp_open(struct inode *inode, struct file *file) return single_open(file, show_rcugp, NULL); } -static struct file_operations rcugp_fops = { +static const struct file_operations rcugp_fops = { .owner = THIS_MODULE, .open = rcugp_open, .read = seq_read, @@ -276,7 +276,7 @@ static int rcu_pending_open(struct inode *inode, struct file *file) return single_open(file, show_rcu_pending, NULL); } -static struct file_operations rcu_pending_fops = { +static const struct file_operations rcu_pending_fops = { .owner = THIS_MODULE, .open = rcu_pending_open, .read = seq_read, diff --git a/kernel/relay.c b/kernel/relay.c index bc188549788f..760c26209a3c 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/res_counter.c b/kernel/res_counter.c index 88faec23e833..bcdabf37c40b 100644 --- a/kernel/res_counter.c +++ b/kernel/res_counter.c @@ -37,27 +37,17 @@ int res_counter_charge_locked(struct res_counter *counter, unsigned long val) } int res_counter_charge(struct res_counter *counter, unsigned long val, - struct res_counter **limit_fail_at, - struct res_counter **soft_limit_fail_at) + struct res_counter **limit_fail_at) { int ret; unsigned long flags; struct res_counter *c, *u; *limit_fail_at = NULL; - if (soft_limit_fail_at) - *soft_limit_fail_at = NULL; local_irq_save(flags); for (c = counter; c != NULL; c = c->parent) { spin_lock(&c->lock); ret = res_counter_charge_locked(c, val); - /* - * With soft limits, we return the highest ancestor - * that exceeds its soft limit - */ - if (soft_limit_fail_at && - !res_counter_soft_limit_check_locked(c)) - *soft_limit_fail_at = c; spin_unlock(&c->lock); if (ret < 0) { *limit_fail_at = c; @@ -85,8 +75,7 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val) counter->usage -= val; } -void res_counter_uncharge(struct res_counter *counter, unsigned long val, - bool *was_soft_limit_excess) +void res_counter_uncharge(struct res_counter *counter, unsigned long val) { unsigned long flags; struct res_counter *c; @@ -94,9 +83,6 @@ void res_counter_uncharge(struct res_counter *counter, unsigned long val, local_irq_save(flags); for (c = counter; c != NULL; c = c->parent) { spin_lock(&c->lock); - if (was_soft_limit_excess) - *was_soft_limit_excess = - !res_counter_soft_limit_check_locked(c); res_counter_uncharge_locked(c, val); spin_unlock(&c->lock); } diff --git a/kernel/sched.c b/kernel/sched.c index ee61f454a98b..1535f3884b88 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -780,7 +780,7 @@ static int sched_feat_open(struct inode *inode, struct file *filp) return single_open(filp, sched_feat_show, NULL); } -static struct file_operations sched_feat_fops = { +static const struct file_operations sched_feat_fops = { .open = sched_feat_open, .write = sched_feat_write, .read = seq_read, diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c index ac2e1dc708bd..479ce5682d7c 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 09113347d328..5e18c6ab2c6a 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/time/timer_list.c b/kernel/time/timer_list.c index fddd69d16e03..1b5b7aa2fdfd 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -275,7 +275,7 @@ static int timer_list_open(struct inode *inode, struct file *filp) return single_open(filp, timer_list_show, NULL); } -static struct file_operations timer_list_fops = { +static const struct file_operations timer_list_fops = { .open = timer_list_open, .read = seq_read, .llseek = seq_lseek, diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c index 4cde8b9c716f..ee5681f8d7ec 100644 --- a/kernel/time/timer_stats.c +++ b/kernel/time/timer_stats.c @@ -395,7 +395,7 @@ static int tstats_open(struct inode *inode, struct file *filp) return single_open(filp, tstats_show, NULL); } -static struct file_operations tstats_fops = { +static const struct file_operations tstats_fops = { .open = tstats_open, .read = seq_read, .write = tstats_write, diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 3eb159c277c8..d9d6206e0b14 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -856,6 +856,37 @@ static void blk_add_trace_remap(struct request_queue *q, struct bio *bio, } /** + * blk_add_trace_rq_remap - Add a trace for a request-remap operation + * @q: queue the io is for + * @rq: the source request + * @dev: target device + * @from: source sector + * + * Description: + * Device mapper remaps request to other devices. + * Add a trace for that action. + * + **/ +static void blk_add_trace_rq_remap(struct request_queue *q, + struct request *rq, dev_t dev, + sector_t from) +{ + struct blk_trace *bt = q->blk_trace; + struct blk_io_trace_remap r; + + if (likely(!bt)) + return; + + r.device_from = cpu_to_be32(dev); + r.device_to = cpu_to_be32(disk_devt(rq->rq_disk)); + r.sector_from = cpu_to_be64(from); + + __blk_add_trace(bt, blk_rq_pos(rq), blk_rq_bytes(rq), + rq_data_dir(rq), BLK_TA_REMAP, !!rq->errors, + sizeof(r), &r); +} + +/** * blk_add_driver_data - Add binary message with driver-specific data * @q: queue the io is for * @rq: io request @@ -922,10 +953,13 @@ static void blk_register_tracepoints(void) WARN_ON(ret); ret = register_trace_block_remap(blk_add_trace_remap); WARN_ON(ret); + ret = register_trace_block_rq_remap(blk_add_trace_rq_remap); + WARN_ON(ret); } static void blk_unregister_tracepoints(void) { + unregister_trace_block_rq_remap(blk_add_trace_rq_remap); unregister_trace_block_remap(blk_add_trace_remap); unregister_trace_block_split(blk_add_trace_split); unregister_trace_block_unplug_io(blk_add_trace_unplug_io); @@ -1657,6 +1691,11 @@ int blk_trace_init_sysfs(struct device *dev) return sysfs_create_group(&dev->kobj, &blk_trace_attr_group); } +void blk_trace_remove_sysfs(struct device *dev) +{ + sysfs_remove_group(&dev->kobj, &blk_trace_attr_group); +} + #endif /* CONFIG_BLK_DEV_IO_TRACE */ #ifdef CONFIG_EVENT_TRACING diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index a142579765bf..46592feab5a6 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 411af37f4be4..45068269ebb1 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 6f03c8a1105e..d128f65778e6 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 == '!') |