diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/cgroup.c | 110 | ||||
| -rw-r--r-- | kernel/events/core.c | 114 | ||||
| -rw-r--r-- | kernel/fork.c | 4 | ||||
| -rw-r--r-- | kernel/irq/proc.c | 19 | ||||
| -rw-r--r-- | kernel/locking/lockdep.c | 10 | ||||
| -rw-r--r-- | kernel/rcu/tree.c | 5 | ||||
| -rw-r--r-- | kernel/sched/core.c | 14 | ||||
| -rw-r--r-- | kernel/sched/wait.c | 7 | ||||
| -rw-r--r-- | kernel/time/clocksource.c | 2 |
9 files changed, 211 insertions, 74 deletions
diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 2cf0f79f1fc9..2c9eae6ad970 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -46,7 +46,6 @@ #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/rwsem.h> -#include <linux/percpu-rwsem.h> #include <linux/string.h> #include <linux/sort.h> #include <linux/kmod.h> @@ -104,8 +103,6 @@ static DEFINE_SPINLOCK(cgroup_idr_lock); */ static DEFINE_SPINLOCK(release_agent_path_lock); -struct percpu_rw_semaphore cgroup_threadgroup_rwsem; - #define cgroup_assert_mutex_or_rcu_locked() \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&cgroup_mutex), \ @@ -874,6 +871,48 @@ static struct css_set *find_css_set(struct css_set *old_cset, return cset; } +void cgroup_threadgroup_change_begin(struct task_struct *tsk) +{ + down_read(&tsk->signal->group_rwsem); +} + +void cgroup_threadgroup_change_end(struct task_struct *tsk) +{ + up_read(&tsk->signal->group_rwsem); +} + +/** + * threadgroup_lock - lock threadgroup + * @tsk: member task of the threadgroup to lock + * + * Lock the threadgroup @tsk belongs to. No new task is allowed to enter + * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or + * change ->group_leader/pid. This is useful for cases where the threadgroup + * needs to stay stable across blockable operations. + * + * fork and exit explicitly call threadgroup_change_{begin|end}() for + * synchronization. While held, no new task will be added to threadgroup + * and no existing live task will have its PF_EXITING set. + * + * de_thread() does threadgroup_change_{begin|end}() when a non-leader + * sub-thread becomes a new leader. + */ +static void threadgroup_lock(struct task_struct *tsk) +{ + down_write(&tsk->signal->group_rwsem); +} + +/** + * threadgroup_unlock - unlock threadgroup + * @tsk: member task of the threadgroup to unlock + * + * Reverse threadgroup_lock(). + */ +static inline void threadgroup_unlock(struct task_struct *tsk) +{ + up_write(&tsk->signal->group_rwsem); +} + static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root) { struct cgroup *root_cgrp = kf_root->kn->priv; @@ -2074,9 +2113,9 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp, lockdep_assert_held(&css_set_rwsem); /* - * We are synchronized through cgroup_threadgroup_rwsem against - * PF_EXITING setting such that we can't race against cgroup_exit() - * changing the css_set to init_css_set and dropping the old one. + * We are synchronized through threadgroup_lock() against PF_EXITING + * setting such that we can't race against cgroup_exit() changing the + * css_set to init_css_set and dropping the old one. */ WARN_ON_ONCE(tsk->flags & PF_EXITING); old_cset = task_css_set(tsk); @@ -2133,11 +2172,10 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets) * @src_cset and add it to @preloaded_csets, which should later be cleaned * up by cgroup_migrate_finish(). * - * This function may be called without holding cgroup_threadgroup_rwsem - * even if the target is a process. Threads may be created and destroyed - * but as long as cgroup_mutex is not dropped, no new css_set can be put - * into play and the preloaded css_sets are guaranteed to cover all - * migrations. + * This function may be called without holding threadgroup_lock even if the + * target is a process. Threads may be created and destroyed but as long + * as cgroup_mutex is not dropped, no new css_set can be put into play and + * the preloaded css_sets are guaranteed to cover all migrations. */ static void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, @@ -2240,7 +2278,7 @@ err: * @threadgroup: whether @leader points to the whole process or a single task * * Migrate a process or task denoted by @leader to @cgrp. If migrating a - * process, the caller must be holding cgroup_threadgroup_rwsem. The + * process, the caller must be holding threadgroup_lock of @leader. The * caller is also responsible for invoking cgroup_migrate_add_src() and * cgroup_migrate_prepare_dst() on the targets before invoking this * function and following up with cgroup_migrate_finish(). @@ -2368,7 +2406,7 @@ out_release_tset: * @leader: the task or the leader of the threadgroup to be attached * @threadgroup: attach the whole threadgroup? * - * Call holding cgroup_mutex and cgroup_threadgroup_rwsem. + * Call holding cgroup_mutex and threadgroup_lock of @leader. */ static int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup) @@ -2460,13 +2498,14 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, if (!cgrp) return -ENODEV; - percpu_down_write(&cgroup_threadgroup_rwsem); +retry_find_task: rcu_read_lock(); if (pid) { tsk = find_task_by_vpid(pid); if (!tsk) { + rcu_read_unlock(); ret = -ESRCH; - goto out_unlock_rcu; + goto out_unlock_cgroup; } } else { tsk = current; @@ -2482,23 +2521,37 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, */ if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) { ret = -EINVAL; - goto out_unlock_rcu; + rcu_read_unlock(); + goto out_unlock_cgroup; } get_task_struct(tsk); rcu_read_unlock(); + threadgroup_lock(tsk); + if (threadgroup) { + if (!thread_group_leader(tsk)) { + /* + * a race with de_thread from another thread's exec() + * may strip us of our leadership, if this happens, + * there is no choice but to throw this task away and + * try again; this is + * "double-double-toil-and-trouble-check locking". + */ + threadgroup_unlock(tsk); + put_task_struct(tsk); + goto retry_find_task; + } + } + ret = cgroup_procs_write_permission(tsk, cgrp, of); if (!ret) ret = cgroup_attach_task(cgrp, tsk, threadgroup); - put_task_struct(tsk); - goto out_unlock_threadgroup; + threadgroup_unlock(tsk); -out_unlock_rcu: - rcu_read_unlock(); -out_unlock_threadgroup: - percpu_up_write(&cgroup_threadgroup_rwsem); + put_task_struct(tsk); +out_unlock_cgroup: cgroup_kn_unlock(of->kn); return ret ?: nbytes; } @@ -2643,8 +2696,6 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) lockdep_assert_held(&cgroup_mutex); - percpu_down_write(&cgroup_threadgroup_rwsem); - /* look up all csses currently attached to @cgrp's subtree */ down_read(&css_set_rwsem); css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) { @@ -2700,8 +2751,17 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) goto out_finish; last_task = task; + threadgroup_lock(task); + /* raced against de_thread() from another thread? */ + if (!thread_group_leader(task)) { + threadgroup_unlock(task); + put_task_struct(task); + continue; + } + ret = cgroup_migrate(src_cset->dfl_cgrp, task, true); + threadgroup_unlock(task); put_task_struct(task); if (WARN(ret, "cgroup: failed to update controllers for the default hierarchy (%d), further operations may crash or hang\n", ret)) @@ -2711,7 +2771,6 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp) out_finish: cgroup_migrate_finish(&preloaded_csets); - percpu_up_write(&cgroup_threadgroup_rwsem); return ret; } @@ -5024,7 +5083,6 @@ int __init cgroup_init(void) unsigned long key; int ssid, err; - BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files)); diff --git a/kernel/events/core.c b/kernel/events/core.c index f548f69c4299..b11756f9b6dc 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1243,11 +1243,7 @@ static inline void perf_event__state_init(struct perf_event *event) PERF_EVENT_STATE_INACTIVE; } -/* - * Called at perf_event creation and when events are attached/detached from a - * group. - */ -static void perf_event__read_size(struct perf_event *event) +static void __perf_event_read_size(struct perf_event *event, int nr_siblings) { int entry = sizeof(u64); /* value */ int size = 0; @@ -1263,7 +1259,7 @@ static void perf_event__read_size(struct perf_event *event) entry += sizeof(u64); if (event->attr.read_format & PERF_FORMAT_GROUP) { - nr += event->group_leader->nr_siblings; + nr += nr_siblings; size += sizeof(u64); } @@ -1271,14 +1267,11 @@ static void perf_event__read_size(struct perf_event *event) event->read_size = size; } -static void perf_event__header_size(struct perf_event *event) +static void __perf_event_header_size(struct perf_event *event, u64 sample_type) { struct perf_sample_data *data; - u64 sample_type = event->attr.sample_type; u16 size = 0; - perf_event__read_size(event); - if (sample_type & PERF_SAMPLE_IP) size += sizeof(data->ip); @@ -1303,6 +1296,17 @@ static void perf_event__header_size(struct perf_event *event) event->header_size = size; } +/* + * Called at perf_event creation and when events are attached/detached from a + * group. + */ +static void perf_event__header_size(struct perf_event *event) +{ + __perf_event_read_size(event, + event->group_leader->nr_siblings); + __perf_event_header_size(event, event->attr.sample_type); +} + static void perf_event__id_header_size(struct perf_event *event) { struct perf_sample_data *data; @@ -1330,6 +1334,27 @@ static void perf_event__id_header_size(struct perf_event *event) event->id_header_size = size; } +static bool perf_event_validate_size(struct perf_event *event) +{ + /* + * The values computed here will be over-written when we actually + * attach the event. + */ + __perf_event_read_size(event, event->group_leader->nr_siblings + 1); + __perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ); + perf_event__id_header_size(event); + + /* + * Sum the lot; should not exceed the 64k limit we have on records. + * Conservative limit to allow for callchains and other variable fields. + */ + if (event->read_size + event->header_size + + event->id_header_size + sizeof(struct perf_event_header) >= 16*1024) + return false; + + return true; +} + static void perf_group_attach(struct perf_event *event) { struct perf_event *group_leader = event->group_leader, *pos; @@ -8297,13 +8322,35 @@ SYSCALL_DEFINE5(perf_event_open, if (move_group) { gctx = group_leader->ctx; + mutex_lock_double(&gctx->mutex, &ctx->mutex); + } else { + mutex_lock(&ctx->mutex); + } + if (!perf_event_validate_size(event)) { + err = -E2BIG; + goto err_locked; + } + + /* + * Must be under the same ctx::mutex as perf_install_in_context(), + * because we need to serialize with concurrent event creation. + */ + if (!exclusive_event_installable(event, ctx)) { + /* exclusive and group stuff are assumed mutually exclusive */ + WARN_ON_ONCE(move_group); + + err = -EBUSY; + goto err_locked; + } + + WARN_ON_ONCE(ctx->parent_ctx); + + if (move_group) { /* * See perf_event_ctx_lock() for comments on the details * of swizzling perf_event::ctx. */ - mutex_lock_double(&gctx->mutex, &ctx->mutex); - perf_remove_from_context(group_leader, false); list_for_each_entry(sibling, &group_leader->sibling_list, @@ -8311,13 +8358,7 @@ SYSCALL_DEFINE5(perf_event_open, perf_remove_from_context(sibling, false); put_ctx(gctx); } - } else { - mutex_lock(&ctx->mutex); - } - WARN_ON_ONCE(ctx->parent_ctx); - - if (move_group) { /* * Wait for everybody to stop referencing the events through * the old lists, before installing it on new lists. @@ -8349,22 +8390,29 @@ SYSCALL_DEFINE5(perf_event_open, perf_event__state_init(group_leader); perf_install_in_context(ctx, group_leader, group_leader->cpu); get_ctx(ctx); - } - if (!exclusive_event_installable(event, ctx)) { - err = -EBUSY; - mutex_unlock(&ctx->mutex); - fput(event_file); - goto err_context; + /* + * Now that all events are installed in @ctx, nothing + * references @gctx anymore, so drop the last reference we have + * on it. + */ + put_ctx(gctx); } + /* + * Precalculate sample_data sizes; do while holding ctx::mutex such + * that we're serialized against further additions and before + * perf_install_in_context() which is the point the event is active and + * can use these values. + */ + perf_event__header_size(event); + perf_event__id_header_size(event); + perf_install_in_context(ctx, event, event->cpu); perf_unpin_context(ctx); - if (move_group) { + if (move_group) mutex_unlock(&gctx->mutex); - put_ctx(gctx); - } mutex_unlock(&ctx->mutex); put_online_cpus(); @@ -8376,12 +8424,6 @@ SYSCALL_DEFINE5(perf_event_open, mutex_unlock(¤t->perf_event_mutex); /* - * Precalculate sample_data sizes - */ - perf_event__header_size(event); - perf_event__id_header_size(event); - - /* * Drop the reference on the group_event after placing the * new event on the sibling_list. This ensures destruction * of the group leader will find the pointer to itself in @@ -8391,6 +8433,12 @@ SYSCALL_DEFINE5(perf_event_open, fd_install(event_fd, event_file); return event_fd; +err_locked: + if (move_group) + mutex_unlock(&gctx->mutex); + mutex_unlock(&ctx->mutex); +/* err_file: */ + fput(event_file); err_context: perf_unpin_context(ctx); put_ctx(ctx); diff --git a/kernel/fork.c b/kernel/fork.c index 7d5f0f118a63..2845623fb582 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1149,6 +1149,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) tty_audit_fork(sig); sched_autogroup_fork(sig); +#ifdef CONFIG_CGROUPS + init_rwsem(&sig->group_rwsem); +#endif + sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index e3a8c9577ba6..a50ddc9417ff 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -12,6 +12,7 @@ #include <linux/seq_file.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> +#include <linux/mutex.h> #include "internals.h" @@ -323,18 +324,29 @@ void register_handler_proc(unsigned int irq, struct irqaction *action) void register_irq_proc(unsigned int irq, struct irq_desc *desc) { + static DEFINE_MUTEX(register_lock); char name [MAX_NAMELEN]; - if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip) || desc->dir) + if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip)) return; + /* + * irq directories are registered only when a handler is + * added, not when the descriptor is created, so multiple + * tasks might try to register at the same time. + */ + mutex_lock(®ister_lock); + + if (desc->dir) + goto out_unlock; + memset(name, 0, MAX_NAMELEN); sprintf(name, "%d", irq); /* create /proc/irq/1234 */ desc->dir = proc_mkdir(name, root_irq_dir); if (!desc->dir) - return; + goto out_unlock; #ifdef CONFIG_SMP /* create /proc/irq/<irq>/smp_affinity */ @@ -355,6 +367,9 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) proc_create_data("spurious", 0444, desc->dir, &irq_spurious_proc_fops, (void *)(long)irq); + +out_unlock: + mutex_unlock(®ister_lock); } void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 8acfbf773e06..4e49cc4c9952 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -3068,7 +3068,7 @@ static int __lock_is_held(struct lockdep_map *lock); static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, int trylock, int read, int check, int hardirqs_off, struct lockdep_map *nest_lock, unsigned long ip, - int references) + int references, int pin_count) { struct task_struct *curr = current; struct lock_class *class = NULL; @@ -3157,7 +3157,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, hlock->waittime_stamp = 0; hlock->holdtime_stamp = lockstat_clock(); #endif - hlock->pin_count = 0; + hlock->pin_count = pin_count; if (check && !mark_irqflags(curr, hlock)) return 0; @@ -3343,7 +3343,7 @@ found_it: hlock_class(hlock)->subclass, hlock->trylock, hlock->read, hlock->check, hlock->hardirqs_off, hlock->nest_lock, hlock->acquire_ip, - hlock->references)) + hlock->references, hlock->pin_count)) return 0; } @@ -3433,7 +3433,7 @@ found_it: hlock_class(hlock)->subclass, hlock->trylock, hlock->read, hlock->check, hlock->hardirqs_off, hlock->nest_lock, hlock->acquire_ip, - hlock->references)) + hlock->references, hlock->pin_count)) return 0; } @@ -3583,7 +3583,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, current->lockdep_recursion = 1; trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip); __lock_acquire(lock, subclass, trylock, read, check, - irqs_disabled_flags(flags), nest_lock, ip, 0); + irqs_disabled_flags(flags), nest_lock, ip, 0, 0); current->lockdep_recursion = 0; raw_local_irq_restore(flags); } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 9f75f25cc5d9..775d36cc0050 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -3868,6 +3868,7 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf) static void __init rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) { + static struct lock_class_key rcu_exp_sched_rdp_class; unsigned long flags; struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu); struct rcu_node *rnp = rcu_get_root(rsp); @@ -3883,6 +3884,10 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp) mutex_init(&rdp->exp_funnel_mutex); rcu_boot_init_nocb_percpu_data(rdp); raw_spin_unlock_irqrestore(&rnp->lock, flags); + if (rsp == &rcu_sched_state) + lockdep_set_class_and_name(&rdp->exp_funnel_mutex, + &rcu_exp_sched_rdp_class, + "rcu_data_exp_sched"); } /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2f9c92884817..615953141951 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4934,7 +4934,15 @@ void init_idle(struct task_struct *idle, int cpu) idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); - do_set_cpus_allowed(idle, cpumask_of(cpu)); +#ifdef CONFIG_SMP + /* + * Its possible that init_idle() gets called multiple times on a task, + * in that case do_set_cpus_allowed() will not do the right thing. + * + * And since this is boot we can forgo the serialization. + */ + set_cpus_allowed_common(idle, cpumask_of(cpu)); +#endif /* * We're having a chicken and egg problem, even though we are * holding rq->lock, the cpu isn't yet set to this cpu so the @@ -4951,7 +4959,7 @@ void init_idle(struct task_struct *idle, int cpu) rq->curr = rq->idle = idle; idle->on_rq = TASK_ON_RQ_QUEUED; -#if defined(CONFIG_SMP) +#ifdef CONFIG_SMP idle->on_cpu = 1; #endif raw_spin_unlock(&rq->lock); @@ -4966,7 +4974,7 @@ void init_idle(struct task_struct *idle, int cpu) idle->sched_class = &idle_sched_class; ftrace_graph_init_idle_task(idle, cpu); vtime_init_idle(idle, cpu); -#if defined(CONFIG_SMP) +#ifdef CONFIG_SMP sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); #endif } diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 272d9322bc5d..052e02672d12 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -106,10 +106,9 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr) } EXPORT_SYMBOL_GPL(__wake_up_locked); -void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, int nr, - void *key) +void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) { - __wake_up_common(q, mode, nr, 0, key); + __wake_up_common(q, mode, 1, 0, key); } EXPORT_SYMBOL_GPL(__wake_up_locked_key); @@ -284,7 +283,7 @@ void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, if (!list_empty(&wait->task_list)) list_del_init(&wait->task_list); else if (waitqueue_active(q)) - __wake_up_locked_key(q, mode, 1, key); + __wake_up_locked_key(q, mode, key); spin_unlock_irqrestore(&q->lock, flags); } EXPORT_SYMBOL(abort_exclusive_wait); diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 841b72f720e8..3a38775b50c2 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -217,7 +217,7 @@ static void clocksource_watchdog(unsigned long data) continue; /* Check the deviation from the watchdog clocksource. */ - if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) { + if (abs64(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) { pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable because the skew is too large:\n", cs->name); pr_warn(" '%s' wd_now: %llx wd_last: %llx mask: %llx\n", |