diff options
Diffstat (limited to 'kernel')
65 files changed, 2929 insertions, 2001 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index b0799bced518..89ebbc4d1164 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -291,10 +291,13 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd) { struct perf_event *event; const struct perf_event_attr *attr; + struct file *file; - event = perf_event_get(fd); - if (IS_ERR(event)) - return event; + file = perf_event_get(fd); + if (IS_ERR(file)) + return file; + + event = file->private_data; attr = perf_event_attrs(event); if (IS_ERR(attr)) @@ -304,24 +307,22 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd) goto err; if (attr->type == PERF_TYPE_RAW) - return event; + return file; if (attr->type == PERF_TYPE_HARDWARE) - return event; + return file; if (attr->type == PERF_TYPE_SOFTWARE && attr->config == PERF_COUNT_SW_BPF_OUTPUT) - return event; + return file; err: - perf_event_release_kernel(event); + fput(file); return ERR_PTR(-EINVAL); } static void perf_event_fd_array_put_ptr(void *ptr) { - struct perf_event *event = ptr; - - perf_event_release_kernel(event); + fput((struct file *)ptr); } static const struct bpf_map_ops perf_event_array_ops = { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index d1d3e8f57de9..2e7f7ab739e4 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -2082,7 +2082,7 @@ static void adjust_branches(struct bpf_prog *prog, int pos, int delta) /* adjust offset of jmps if necessary */ if (i < pos && i + insn->off + 1 > pos) insn->off += delta; - else if (i > pos && i + insn->off + 1 < pos) + else if (i > pos + delta && i + insn->off + 1 <= pos + delta) insn->off -= delta; } } diff --git a/kernel/cgroup.c b/kernel/cgroup.c index c03a640ef6da..d27904c193da 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -58,6 +58,7 @@ #include <linux/kthread.h> #include <linux/delay.h> #include <linux/atomic.h> +#include <linux/cpuset.h> #include <net/sock.h> /* @@ -2739,6 +2740,7 @@ out_unlock_rcu: out_unlock_threadgroup: percpu_up_write(&cgroup_threadgroup_rwsem); cgroup_kn_unlock(of->kn); + cpuset_post_attach_flush(); return ret ?: nbytes; } @@ -4655,14 +4657,15 @@ static void css_free_work_fn(struct work_struct *work) if (ss) { /* css free path */ + struct cgroup_subsys_state *parent = css->parent; int id = css->id; - if (css->parent) - css_put(css->parent); - ss->css_free(css); cgroup_idr_remove(&ss->css_idr, id); cgroup_put(cgrp); + + if (parent) + css_put(parent); } else { /* cgroup free path */ atomic_dec(&cgrp->root->nr_cgrps); @@ -4758,6 +4761,7 @@ static void init_and_link_css(struct cgroup_subsys_state *css, INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); css->serial_nr = css_serial_nr_next++; + atomic_set(&css->online_cnt, 0); if (cgroup_parent(cgrp)) { css->parent = cgroup_css(cgroup_parent(cgrp), ss); @@ -4780,6 +4784,10 @@ static int online_css(struct cgroup_subsys_state *css) if (!ret) { css->flags |= CSS_ONLINE; rcu_assign_pointer(css->cgroup->subsys[ss->id], css); + + atomic_inc(&css->online_cnt); + if (css->parent) + atomic_inc(&css->parent->online_cnt); } return ret; } @@ -5017,10 +5025,15 @@ static void css_killed_work_fn(struct work_struct *work) container_of(work, struct cgroup_subsys_state, destroy_work); mutex_lock(&cgroup_mutex); - offline_css(css); - mutex_unlock(&cgroup_mutex); - css_put(css); + do { + offline_css(css); + css_put(css); + /* @css can't go away while we're holding cgroup_mutex */ + css = css->parent; + } while (css && atomic_dec_and_test(&css->online_cnt)); + + mutex_unlock(&cgroup_mutex); } /* css kill confirmation processing requires process context, bounce */ @@ -5029,8 +5042,10 @@ static void css_killed_ref_fn(struct percpu_ref *ref) struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); - INIT_WORK(&css->destroy_work, css_killed_work_fn); - queue_work(cgroup_destroy_wq, &css->destroy_work); + if (atomic_dec_and_test(&css->online_cnt)) { + INIT_WORK(&css->destroy_work, css_killed_work_fn); + queue_work(cgroup_destroy_wq, &css->destroy_work); + } } /** diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 3e945fcd8179..41989ab4db57 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -287,6 +287,8 @@ static struct cpuset top_cpuset = { static DEFINE_MUTEX(cpuset_mutex); static DEFINE_SPINLOCK(callback_lock); +static struct workqueue_struct *cpuset_migrate_mm_wq; + /* * CPU / memory hotplug is handled asynchronously. */ @@ -972,31 +974,51 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, } /* - * cpuset_migrate_mm - * - * Migrate memory region from one set of nodes to another. - * - * Temporarilly set tasks mems_allowed to target nodes of migration, - * so that the migration code can allocate pages on these nodes. - * - * While the mm_struct we are migrating is typically from some - * other task, the task_struct mems_allowed that we are hacking - * is for our current task, which must allocate new pages for that - * migrating memory region. + * Migrate memory region from one set of nodes to another. This is + * performed asynchronously as it can be called from process migration path + * holding locks involved in process management. All mm migrations are + * performed in the queued order and can be waited for by flushing + * cpuset_migrate_mm_wq. */ +struct cpuset_migrate_mm_work { + struct work_struct work; + struct mm_struct *mm; + nodemask_t from; + nodemask_t to; +}; + +static void cpuset_migrate_mm_workfn(struct work_struct *work) +{ + struct cpuset_migrate_mm_work *mwork = + container_of(work, struct cpuset_migrate_mm_work, work); + + /* on a wq worker, no need to worry about %current's mems_allowed */ + do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL); + mmput(mwork->mm); + kfree(mwork); +} + static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to) { - struct task_struct *tsk = current; - - tsk->mems_allowed = *to; + struct cpuset_migrate_mm_work *mwork; - do_migrate_pages(mm, from, to, MPOL_MF_MOVE_ALL); + mwork = kzalloc(sizeof(*mwork), GFP_KERNEL); + if (mwork) { + mwork->mm = mm; + mwork->from = *from; + mwork->to = *to; + INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn); + queue_work(cpuset_migrate_mm_wq, &mwork->work); + } else { + mmput(mm); + } +} - rcu_read_lock(); - guarantee_online_mems(task_cs(tsk), &tsk->mems_allowed); - rcu_read_unlock(); +void cpuset_post_attach_flush(void) +{ + flush_workqueue(cpuset_migrate_mm_wq); } /* @@ -1097,7 +1119,8 @@ static void update_tasks_nodemask(struct cpuset *cs) mpol_rebind_mm(mm, &cs->mems_allowed); if (migrate) cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); - mmput(mm); + else + mmput(mm); } css_task_iter_end(&it); @@ -1545,11 +1568,11 @@ static void cpuset_attach(struct cgroup_taskset *tset) * @old_mems_allowed is the right nodesets that we * migrate mm from. */ - if (is_memory_migrate(cs)) { + if (is_memory_migrate(cs)) cpuset_migrate_mm(mm, &oldcs->old_mems_allowed, &cpuset_attach_nodemask_to); - } - mmput(mm); + else + mmput(mm); } } @@ -1714,6 +1737,7 @@ out_unlock: mutex_unlock(&cpuset_mutex); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); + flush_workqueue(cpuset_migrate_mm_wq); return retval ?: nbytes; } @@ -2359,6 +2383,9 @@ void __init cpuset_init_smp(void) top_cpuset.effective_mems = node_states[N_MEMORY]; register_hotmemory_notifier(&cpuset_track_online_nodes_nb); + + cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0); + BUG_ON(!cpuset_migrate_mm_wq); } /** diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c index e1dbf4a2c69e..90ff129c88a2 100644 --- a/kernel/debug/kdb/kdb_bp.c +++ b/kernel/debug/kdb/kdb_bp.c @@ -153,13 +153,11 @@ static int _kdb_bp_install(struct pt_regs *regs, kdb_bp_t *bp) } else { kdb_printf("%s: failed to set breakpoint at 0x%lx\n", __func__, bp->bp_addr); -#ifdef CONFIG_DEBUG_RODATA if (!bp->bp_type) { kdb_printf("Software breakpoints are unavailable.\n" - " Change the kernel CONFIG_DEBUG_RODATA=n\n" + " Boot the kernel with rodata=off\n" " OR use hw breaks: help bph\n"); } -#endif return 1; } return 0; diff --git a/kernel/events/core.c b/kernel/events/core.c index 06ae52e99ac2..712570dddacd 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -49,8 +49,6 @@ #include <asm/irq_regs.h> -static struct workqueue_struct *perf_wq; - typedef int (*remote_function_f)(void *); struct remote_function_call { @@ -66,8 +64,17 @@ static void remote_function(void *data) struct task_struct *p = tfc->p; if (p) { - tfc->ret = -EAGAIN; - if (task_cpu(p) != smp_processor_id() || !task_curr(p)) + /* -EAGAIN */ + if (task_cpu(p) != smp_processor_id()) + return; + + /* + * Now that we're on right CPU with IRQs disabled, we can test + * if we hit the right task without races. + */ + + tfc->ret = -ESRCH; /* No such (running) process */ + if (p != current) return; } @@ -94,13 +101,17 @@ task_function_call(struct task_struct *p, remote_function_f func, void *info) .p = p, .func = func, .info = info, - .ret = -ESRCH, /* No such (running) process */ + .ret = -EAGAIN, }; + int ret; - if (task_curr(p)) - smp_call_function_single(task_cpu(p), remote_function, &data, 1); + do { + ret = smp_call_function_single(task_cpu(p), remote_function, &data, 1); + if (!ret) + ret = data.ret; + } while (ret == -EAGAIN); - return data.ret; + return ret; } /** @@ -126,44 +137,170 @@ static int cpu_function_call(int cpu, remote_function_f func, void *info) return data.ret; } -static void event_function_call(struct perf_event *event, - int (*active)(void *), - void (*inactive)(void *), - void *data) +static inline struct perf_cpu_context * +__get_cpu_context(struct perf_event_context *ctx) +{ + return this_cpu_ptr(ctx->pmu->pmu_cpu_context); +} + +static void perf_ctx_lock(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + raw_spin_lock(&cpuctx->ctx.lock); + if (ctx) + raw_spin_lock(&ctx->lock); +} + +static void perf_ctx_unlock(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + if (ctx) + raw_spin_unlock(&ctx->lock); + raw_spin_unlock(&cpuctx->ctx.lock); +} + +#define TASK_TOMBSTONE ((void *)-1L) + +static bool is_kernel_event(struct perf_event *event) +{ + return READ_ONCE(event->owner) == TASK_TOMBSTONE; +} + +/* + * On task ctx scheduling... + * + * When !ctx->nr_events a task context will not be scheduled. This means + * we can disable the scheduler hooks (for performance) without leaving + * pending task ctx state. + * + * This however results in two special cases: + * + * - removing the last event from a task ctx; this is relatively straight + * forward and is done in __perf_remove_from_context. + * + * - adding the first event to a task ctx; this is tricky because we cannot + * rely on ctx->is_active and therefore cannot use event_function_call(). + * See perf_install_in_context(). + * + * If ctx->nr_events, then ctx->is_active and cpuctx->task_ctx are set. + */ + +typedef void (*event_f)(struct perf_event *, struct perf_cpu_context *, + struct perf_event_context *, void *); + +struct event_function_struct { + struct perf_event *event; + event_f func; + void *data; +}; + +static int event_function(void *info) +{ + struct event_function_struct *efs = info; + struct perf_event *event = efs->event; + struct perf_event_context *ctx = event->ctx; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + struct perf_event_context *task_ctx = cpuctx->task_ctx; + int ret = 0; + + WARN_ON_ONCE(!irqs_disabled()); + + perf_ctx_lock(cpuctx, task_ctx); + /* + * Since we do the IPI call without holding ctx->lock things can have + * changed, double check we hit the task we set out to hit. + */ + if (ctx->task) { + if (ctx->task != current) { + ret = -ESRCH; + goto unlock; + } + + /* + * We only use event_function_call() on established contexts, + * and event_function() is only ever called when active (or + * rather, we'll have bailed in task_function_call() or the + * above ctx->task != current test), therefore we must have + * ctx->is_active here. + */ + WARN_ON_ONCE(!ctx->is_active); + /* + * And since we have ctx->is_active, cpuctx->task_ctx must + * match. + */ + WARN_ON_ONCE(task_ctx != ctx); + } else { + WARN_ON_ONCE(&cpuctx->ctx != ctx); + } + + efs->func(event, cpuctx, ctx, efs->data); +unlock: + perf_ctx_unlock(cpuctx, task_ctx); + + return ret; +} + +static void event_function_local(struct perf_event *event, event_f func, void *data) +{ + struct event_function_struct efs = { + .event = event, + .func = func, + .data = data, + }; + + int ret = event_function(&efs); + WARN_ON_ONCE(ret); +} + +static void event_function_call(struct perf_event *event, event_f func, void *data) { struct perf_event_context *ctx = event->ctx; - struct task_struct *task = ctx->task; + struct task_struct *task = READ_ONCE(ctx->task); /* verified in event_function */ + struct event_function_struct efs = { + .event = event, + .func = func, + .data = data, + }; + + if (!event->parent) { + /* + * If this is a !child event, we must hold ctx::mutex to + * stabilize the the event->ctx relation. See + * perf_event_ctx_lock(). + */ + lockdep_assert_held(&ctx->mutex); + } if (!task) { - cpu_function_call(event->cpu, active, data); + cpu_function_call(event->cpu, event_function, &efs); return; } + if (task == TASK_TOMBSTONE) + return; + again: - if (!task_function_call(task, active, data)) + if (!task_function_call(task, event_function, &efs)) return; raw_spin_lock_irq(&ctx->lock); + /* + * Reload the task pointer, it might have been changed by + * a concurrent perf_event_context_sched_out(). + */ + task = ctx->task; + if (task == TASK_TOMBSTONE) { + raw_spin_unlock_irq(&ctx->lock); + return; + } if (ctx->is_active) { - /* - * Reload the task pointer, it might have been changed by - * a concurrent perf_event_context_sched_out(). - */ - task = ctx->task; raw_spin_unlock_irq(&ctx->lock); goto again; } - inactive(data); + func(event, NULL, ctx, data); raw_spin_unlock_irq(&ctx->lock); } -#define EVENT_OWNER_KERNEL ((void *) -1) - -static bool is_kernel_event(struct perf_event *event) -{ - return event->owner == EVENT_OWNER_KERNEL; -} - #define PERF_FLAG_ALL (PERF_FLAG_FD_NO_GROUP |\ PERF_FLAG_FD_OUTPUT |\ PERF_FLAG_PID_CGROUP |\ @@ -179,6 +316,7 @@ static bool is_kernel_event(struct perf_event *event) enum event_type_t { EVENT_FLEXIBLE = 0x1, EVENT_PINNED = 0x2, + EVENT_TIME = 0x4, EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED, }; @@ -186,7 +324,13 @@ enum event_type_t { * perf_sched_events : >0 events exist * perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu */ -struct static_key_deferred perf_sched_events __read_mostly; + +static void perf_sched_delayed(struct work_struct *work); +DEFINE_STATIC_KEY_FALSE(perf_sched_events); +static DECLARE_DELAYED_WORK(perf_sched_work, perf_sched_delayed); +static DEFINE_MUTEX(perf_sched_mutex); +static atomic_t perf_sched_count; + static DEFINE_PER_CPU(atomic_t, perf_cgroup_events); static DEFINE_PER_CPU(int, perf_sched_cb_usages); @@ -368,28 +512,6 @@ static inline u64 perf_event_clock(struct perf_event *event) return event->clock(); } -static inline struct perf_cpu_context * -__get_cpu_context(struct perf_event_context *ctx) -{ - return this_cpu_ptr(ctx->pmu->pmu_cpu_context); -} - -static void perf_ctx_lock(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx) -{ - raw_spin_lock(&cpuctx->ctx.lock); - if (ctx) - raw_spin_lock(&ctx->lock); -} - -static void perf_ctx_unlock(struct perf_cpu_context *cpuctx, - struct perf_event_context *ctx) -{ - if (ctx) - raw_spin_unlock(&ctx->lock); - raw_spin_unlock(&cpuctx->ctx.lock); -} - #ifdef CONFIG_CGROUP_PERF static inline bool @@ -579,13 +701,7 @@ static inline void perf_cgroup_sched_out(struct task_struct *task, * we are holding the rcu lock */ cgrp1 = perf_cgroup_from_task(task, NULL); - - /* - * next is NULL when called from perf_event_enable_on_exec() - * that will systematically cause a cgroup_switch() - */ - if (next) - cgrp2 = perf_cgroup_from_task(next, NULL); + cgrp2 = perf_cgroup_from_task(next, NULL); /* * only schedule out current cgroup events if we know @@ -611,8 +727,6 @@ static inline void perf_cgroup_sched_in(struct task_struct *prev, * we are holding the rcu lock */ cgrp1 = perf_cgroup_from_task(task, NULL); - - /* prev can never be NULL */ cgrp2 = perf_cgroup_from_task(prev, NULL); /* @@ -917,7 +1031,7 @@ static void put_ctx(struct perf_event_context *ctx) if (atomic_dec_and_test(&ctx->refcount)) { if (ctx->parent_ctx) put_ctx(ctx->parent_ctx); - if (ctx->task) + if (ctx->task && ctx->task != TASK_TOMBSTONE) put_task_struct(ctx->task); call_rcu(&ctx->rcu_head, free_ctx); } @@ -934,9 +1048,8 @@ static void put_ctx(struct perf_event_context *ctx) * perf_event_context::mutex nests and those are: * * - perf_event_exit_task_context() [ child , 0 ] - * __perf_event_exit_task() - * sync_child_event() - * put_event() [ parent, 1 ] + * perf_event_exit_event() + * put_event() [ parent, 1 ] * * - perf_event_init_context() [ parent, 0 ] * inherit_task_group() @@ -979,8 +1092,8 @@ static void put_ctx(struct perf_event_context *ctx) * Lock order: * task_struct::perf_event_mutex * perf_event_context::mutex - * perf_event_context::lock * perf_event::child_mutex; + * perf_event_context::lock * perf_event::mmap_mutex * mmap_sem */ @@ -1078,6 +1191,7 @@ static u64 primary_event_id(struct perf_event *event) /* * Get the perf_event_context for a task and lock it. + * * This has to cope with with the fact that until it is locked, * the context could get moved to another task. */ @@ -1118,9 +1232,12 @@ retry: goto retry; } - if (!atomic_inc_not_zero(&ctx->refcount)) { + if (ctx->task == TASK_TOMBSTONE || + !atomic_inc_not_zero(&ctx->refcount)) { raw_spin_unlock(&ctx->lock); ctx = NULL; + } else { + WARN_ON_ONCE(ctx->task != task); } } rcu_read_unlock(); @@ -1180,16 +1297,18 @@ static u64 perf_event_time(struct perf_event *event) /* * Update the total_time_enabled and total_time_running fields for a event. - * The caller of this function needs to hold the ctx->lock. */ static void update_event_times(struct perf_event *event) { struct perf_event_context *ctx = event->ctx; u64 run_end; + lockdep_assert_held(&ctx->lock); + if (event->state < PERF_EVENT_STATE_INACTIVE || event->group_leader->state < PERF_EVENT_STATE_INACTIVE) return; + /* * in cgroup mode, time_enabled represents * the time the event was enabled AND active @@ -1246,6 +1365,8 @@ ctx_group_list(struct perf_event *event, struct perf_event_context *ctx) static void list_add_event(struct perf_event *event, struct perf_event_context *ctx) { + lockdep_assert_held(&ctx->lock); + WARN_ON_ONCE(event->attach_state & PERF_ATTACH_CONTEXT); event->attach_state |= PERF_ATTACH_CONTEXT; @@ -1448,11 +1569,14 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx) if (is_cgroup_event(event)) { ctx->nr_cgroups--; + /* + * Because cgroup events are always per-cpu events, this will + * always be called from the right CPU. + */ cpuctx = __get_cpu_context(ctx); /* - * if there are no more cgroup events - * then cler cgrp to avoid stale pointer - * in update_cgrp_time_from_cpuctx() + * If there are no more cgroup events then clear cgrp to avoid + * stale pointer in update_cgrp_time_from_cpuctx(). */ if (!ctx->nr_cgroups) cpuctx->cgrp = NULL; @@ -1530,45 +1654,11 @@ out: perf_event__header_size(tmp); } -/* - * User event without the task. - */ static bool is_orphaned_event(struct perf_event *event) { - return event && !is_kernel_event(event) && !event->owner; -} - -/* - * Event has a parent but parent's task finished and it's - * alive only because of children holding refference. - */ -static bool is_orphaned_child(struct perf_event *event) -{ - return is_orphaned_event(event->parent); + return event->state == PERF_EVENT_STATE_DEAD; } -static void orphans_remove_work(struct work_struct *work); - -static void schedule_orphans_remove(struct perf_event_context *ctx) -{ - if (!ctx->task || ctx->orphans_remove_sched || !perf_wq) - return; - - if (queue_delayed_work(perf_wq, &ctx->orphans_remove, 1)) { - get_ctx(ctx); - ctx->orphans_remove_sched = true; - } -} - -static int __init perf_workqueue_init(void) -{ - perf_wq = create_singlethread_workqueue("perf"); - WARN(!perf_wq, "failed to create perf workqueue\n"); - return perf_wq ? 0 : -1; -} - -core_initcall(perf_workqueue_init); - static inline int pmu_filter_match(struct perf_event *event) { struct pmu *pmu = event->pmu; @@ -1611,14 +1701,14 @@ event_sched_out(struct perf_event *event, perf_pmu_disable(event->pmu); + event->tstamp_stopped = tstamp; + event->pmu->del(event, 0); + event->oncpu = -1; event->state = PERF_EVENT_STATE_INACTIVE; if (event->pending_disable) { event->pending_disable = 0; event->state = PERF_EVENT_STATE_OFF; } - event->tstamp_stopped = tstamp; - event->pmu->del(event, 0); - event->oncpu = -1; if (!is_software_event(event)) cpuctx->active_oncpu--; @@ -1629,9 +1719,6 @@ event_sched_out(struct perf_event *event, if (event->attr.exclusive || !cpuctx->active_oncpu) cpuctx->exclusive = 0; - if (is_orphaned_child(event)) - schedule_orphans_remove(ctx); - perf_pmu_enable(event->pmu); } @@ -1655,21 +1742,7 @@ group_sched_out(struct perf_event *group_event, cpuctx->exclusive = 0; } -struct remove_event { - struct perf_event *event; - bool detach_group; -}; - -static void ___perf_remove_from_context(void *info) -{ - struct remove_event *re = info; - struct perf_event *event = re->event; - struct perf_event_context *ctx = event->ctx; - - if (re->detach_group) - perf_group_detach(event); - list_del_event(event, ctx); -} +#define DETACH_GROUP 0x01UL /* * Cross CPU call to remove a performance event @@ -1677,33 +1750,31 @@ static void ___perf_remove_from_context(void *info) * We disable the event on the hardware level first. After that we * remove it from the context list. */ -static int __perf_remove_from_context(void *info) +static void +__perf_remove_from_context(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx, + void *info) { - struct remove_event *re = info; - struct perf_event *event = re->event; - struct perf_event_context *ctx = event->ctx; - struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + unsigned long flags = (unsigned long)info; - raw_spin_lock(&ctx->lock); event_sched_out(event, cpuctx, ctx); - if (re->detach_group) + if (flags & DETACH_GROUP) perf_group_detach(event); list_del_event(event, ctx); - if (!ctx->nr_events && cpuctx->task_ctx == ctx) { + + if (!ctx->nr_events && ctx->is_active) { ctx->is_active = 0; - cpuctx->task_ctx = NULL; + if (ctx->task) { + WARN_ON_ONCE(cpuctx->task_ctx != ctx); + cpuctx->task_ctx = NULL; + } } - raw_spin_unlock(&ctx->lock); - - return 0; } /* * Remove the event from a task's (or a CPU's) list of events. * - * CPU events are removed with a smp call. For task events we only - * call when the task is on a CPU. - * * If event->ctx is a cloned context, callers must make sure that * every task struct that event->ctx->task could possibly point to * remains valid. This is OK when called from perf_release since @@ -1711,73 +1782,32 @@ static int __perf_remove_from_context(void *info) * When called from perf_event_exit_task, it's OK because the * context has been detached from its task. */ -static void perf_remove_from_context(struct perf_event *event, bool detach_group) +static void perf_remove_from_context(struct perf_event *event, unsigned long flags) { - struct perf_event_context *ctx = event->ctx; - struct remove_event re = { - .event = event, - .detach_group = detach_group, - }; - - lockdep_assert_held(&ctx->mutex); + lockdep_assert_held(&event->ctx->mutex); - event_function_call(event, __perf_remove_from_context, - ___perf_remove_from_context, &re); + event_function_call(event, __perf_remove_from_context, (void *)flags); } /* * Cross CPU call to disable a performance event */ -int __perf_event_disable(void *info) -{ - struct perf_event *event = info; - struct perf_event_context *ctx = event->ctx; - struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); - - /* - * If this is a per-task event, need to check whether this - * event's task is the current task on this cpu. - * - * Can trigger due to concurrent perf_event_context_sched_out() - * flipping contexts around. - */ - if (ctx->task && cpuctx->task_ctx != ctx) - return -EINVAL; - - raw_spin_lock(&ctx->lock); - - /* - * If the event is on, turn it off. - * If it is in error state, leave it in error state. - */ - if (event->state >= PERF_EVENT_STATE_INACTIVE) { - update_context_time(ctx); - update_cgrp_time_from_event(event); - update_group_times(event); - if (event == event->group_leader) - group_sched_out(event, cpuctx, ctx); - else - event_sched_out(event, cpuctx, ctx); - event->state = PERF_EVENT_STATE_OFF; - } - - raw_spin_unlock(&ctx->lock); - - return 0; -} - -void ___perf_event_disable(void *info) +static void __perf_event_disable(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx, + void *info) { - struct perf_event *event = info; + if (event->state < PERF_EVENT_STATE_INACTIVE) + return; - /* - * Since we have the lock this context can't be scheduled - * in, so we can change the state safely. - */ - if (event->state == PERF_EVENT_STATE_INACTIVE) { - update_group_times(event); - event->state = PERF_EVENT_STATE_OFF; - } + update_context_time(ctx); + update_cgrp_time_from_event(event); + update_group_times(event); + if (event == event->group_leader) + group_sched_out(event, cpuctx, ctx); + else + event_sched_out(event, cpuctx, ctx); + event->state = PERF_EVENT_STATE_OFF; } /* @@ -1788,7 +1818,8 @@ void ___perf_event_disable(void *info) * remains valid. This condition is satisifed when called through * perf_event_for_each_child or perf_event_for_each because they * hold the top-level event's child_mutex, so any descendant that - * goes to exit will block in sync_child_event. + * goes to exit will block in perf_event_exit_event(). + * * When called from perf_pending_event it's OK because event->ctx * is the current context on this CPU and preemption is disabled, * hence we can't get into perf_event_task_sched_out for this context. @@ -1804,8 +1835,12 @@ static void _perf_event_disable(struct perf_event *event) } raw_spin_unlock_irq(&ctx->lock); - event_function_call(event, __perf_event_disable, - ___perf_event_disable, event); + event_function_call(event, __perf_event_disable, NULL); +} + +void perf_event_disable_local(struct perf_event *event) +{ + event_function_local(event, __perf_event_disable, NULL); } /* @@ -1918,9 +1953,6 @@ event_sched_in(struct perf_event *event, if (event->attr.exclusive) cpuctx->exclusive = 1; - if (is_orphaned_child(event)) - schedule_orphans_remove(ctx); - out: perf_pmu_enable(event->pmu); @@ -2039,13 +2071,27 @@ static void add_event_to_ctx(struct perf_event *event, event->tstamp_stopped = tstamp; } -static void task_ctx_sched_out(struct perf_event_context *ctx); +static void ctx_sched_out(struct perf_event_context *ctx, + struct perf_cpu_context *cpuctx, + enum event_type_t event_type); static void ctx_sched_in(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, enum event_type_t event_type, struct task_struct *task); +static void task_ctx_sched_out(struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx) +{ + if (!cpuctx->task_ctx) + return; + + if (WARN_ON_ONCE(ctx != cpuctx->task_ctx)) + return; + + ctx_sched_out(ctx, cpuctx, EVENT_ALL); +} + static void perf_event_sched_in(struct perf_cpu_context *cpuctx, struct perf_event_context *ctx, struct task_struct *task) @@ -2058,22 +2104,22 @@ static void perf_event_sched_in(struct perf_cpu_context *cpuctx, ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task); } -static void ___perf_install_in_context(void *info) +static void ctx_resched(struct perf_cpu_context *cpuctx, + struct perf_event_context *task_ctx) { - struct perf_event *event = info; - struct perf_event_context *ctx = event->ctx; - - /* - * Since the task isn't running, its safe to add the event, us holding - * the ctx->lock ensures the task won't get scheduled in. - */ - add_event_to_ctx(event, ctx); + perf_pmu_disable(cpuctx->ctx.pmu); + if (task_ctx) + task_ctx_sched_out(cpuctx, task_ctx); + cpu_ctx_sched_out(cpuctx, EVENT_ALL); + perf_event_sched_in(cpuctx, task_ctx, current); + perf_pmu_enable(cpuctx->ctx.pmu); } /* * Cross CPU call to install and enable a performance event * - * Must be called with ctx->mutex held + * Very similar to remote_function() + event_function() but cannot assume that + * things like ctx->is_active and cpuctx->task_ctx are set. */ static int __perf_install_in_context(void *info) { @@ -2081,79 +2127,106 @@ static int __perf_install_in_context(void *info) struct perf_event_context *ctx = event->ctx; struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); struct perf_event_context *task_ctx = cpuctx->task_ctx; - struct task_struct *task = current; - - perf_ctx_lock(cpuctx, task_ctx); - perf_pmu_disable(cpuctx->ctx.pmu); - - /* - * If there was an active task_ctx schedule it out. - */ - if (task_ctx) - task_ctx_sched_out(task_ctx); + bool activate = true; + int ret = 0; - /* - * If the context we're installing events in is not the - * active task_ctx, flip them. - */ - if (ctx->task && task_ctx != ctx) { - if (task_ctx) - raw_spin_unlock(&task_ctx->lock); + raw_spin_lock(&cpuctx->ctx.lock); + if (ctx->task) { raw_spin_lock(&ctx->lock); task_ctx = ctx; - } - if (task_ctx) { - cpuctx->task_ctx = task_ctx; - task = task_ctx->task; - } - - cpu_ctx_sched_out(cpuctx, EVENT_ALL); + /* If we're on the wrong CPU, try again */ + if (task_cpu(ctx->task) != smp_processor_id()) { + ret = -ESRCH; + goto unlock; + } - update_context_time(ctx); - /* - * update cgrp time only if current cgrp - * matches event->cgrp. Must be done before - * calling add_event_to_ctx() - */ - update_cgrp_time_from_event(event); + /* + * If we're on the right CPU, see if the task we target is + * current, if not we don't have to activate the ctx, a future + * context switch will do that for us. + */ + if (ctx->task != current) + activate = false; + else + WARN_ON_ONCE(cpuctx->task_ctx && cpuctx->task_ctx != ctx); - add_event_to_ctx(event, ctx); + } else if (task_ctx) { + raw_spin_lock(&task_ctx->lock); + } - /* - * Schedule everything back in - */ - perf_event_sched_in(cpuctx, task_ctx, task); + if (activate) { + ctx_sched_out(ctx, cpuctx, EVENT_TIME); + add_event_to_ctx(event, ctx); + ctx_resched(cpuctx, task_ctx); + } else { + add_event_to_ctx(event, ctx); + } - perf_pmu_enable(cpuctx->ctx.pmu); +unlock: perf_ctx_unlock(cpuctx, task_ctx); - return 0; + return ret; } /* - * Attach a performance event to a context - * - * First we add the event to the list with the hardware enable bit - * in event->hw_config cleared. + * Attach a performance event to a context. * - * If the event is attached to a task which is on a CPU we use a smp - * call to enable it in the task context. The task might have been - * scheduled away, but we check this in the smp call again. + * Very similar to event_function_call, see comment there. */ static void perf_install_in_context(struct perf_event_context *ctx, struct perf_event *event, int cpu) { + struct task_struct *task = READ_ONCE(ctx->task); + lockdep_assert_held(&ctx->mutex); event->ctx = ctx; if (event->cpu != -1) event->cpu = cpu; - event_function_call(event, __perf_install_in_context, - ___perf_install_in_context, event); + if (!task) { + cpu_function_call(cpu, __perf_install_in_context, event); + return; + } + + /* + * Should not happen, we validate the ctx is still alive before calling. + */ + if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) + return; + + /* + * Installing events is tricky because we cannot rely on ctx->is_active + * to be set in case this is the nr_events 0 -> 1 transition. + */ +again: + /* + * Cannot use task_function_call() because we need to run on the task's + * CPU regardless of whether its current or not. + */ + if (!cpu_function_call(task_cpu(task), __perf_install_in_context, event)) + return; + + raw_spin_lock_irq(&ctx->lock); + task = ctx->task; + if (WARN_ON_ONCE(task == TASK_TOMBSTONE)) { + /* + * Cannot happen because we already checked above (which also + * cannot happen), and we hold ctx->mutex, which serializes us + * against perf_event_exit_task_context(). + */ + raw_spin_unlock_irq(&ctx->lock); + return; + } + raw_spin_unlock_irq(&ctx->lock); + /* + * Since !ctx->is_active doesn't mean anything, we must IPI + * unconditionally. + */ + goto again; } /* @@ -2180,85 +2253,47 @@ static void __perf_event_mark_enabled(struct perf_event *event) /* * Cross CPU call to enable a performance event */ -static int __perf_event_enable(void *info) +static void __perf_event_enable(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx, + void *info) { - struct perf_event *event = info; - struct perf_event_context *ctx = event->ctx; struct perf_event *leader = event->group_leader; - struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); - int err; - - /* - * There's a time window between 'ctx->is_active' check - * in perf_event_enable function and this place having: - * - IRQs on - * - ctx->lock unlocked - * - * where the task could be killed and 'ctx' deactivated - * by perf_event_exit_task. - */ - if (!ctx->is_active) - return -EINVAL; - - raw_spin_lock(&ctx->lock); - update_context_time(ctx); + struct perf_event_context *task_ctx; - if (event->state >= PERF_EVENT_STATE_INACTIVE) - goto unlock; + if (event->state >= PERF_EVENT_STATE_INACTIVE || + event->state <= PERF_EVENT_STATE_ERROR) + return; - /* - * set current task's cgroup time reference point - */ - perf_cgroup_set_timestamp(current, ctx); + if (ctx->is_active) + ctx_sched_out(ctx, cpuctx, EVENT_TIME); __perf_event_mark_enabled(event); + if (!ctx->is_active) + return; + if (!event_filter_match(event)) { if (is_cgroup_event(event)) perf_cgroup_defer_enabled(event); - goto unlock; + ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + return; } /* * If the event is in a group and isn't the group leader, * then don't put it on unless the group is on. */ - if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) - goto unlock; - - if (!group_can_go_on(event, cpuctx, 1)) { - err = -EEXIST; - } else { - if (event == leader) - err = group_sched_in(event, cpuctx, ctx); - else - err = event_sched_in(event, cpuctx, ctx); - } - - if (err) { - /* - * If this event can't go on and it's part of a - * group, then the whole group has to come off. - */ - if (leader != event) { - group_sched_out(leader, cpuctx, ctx); - perf_mux_hrtimer_restart(cpuctx); - } - if (leader->attr.pinned) { - update_group_times(leader); - leader->state = PERF_EVENT_STATE_ERROR; - } + if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) { + ctx_sched_in(ctx, cpuctx, EVENT_TIME, current); + return; } -unlock: - raw_spin_unlock(&ctx->lock); + task_ctx = cpuctx->task_ctx; + if (ctx->task) + WARN_ON_ONCE(task_ctx != ctx); - return 0; -} - -void ___perf_event_enable(void *info) -{ - __perf_event_mark_enabled((struct perf_event *)info); + ctx_resched(cpuctx, task_ctx); } /* @@ -2275,7 +2310,8 @@ static void _perf_event_enable(struct perf_event *event) struct perf_event_context *ctx = event->ctx; raw_spin_lock_irq(&ctx->lock); - if (event->state >= PERF_EVENT_STATE_INACTIVE) { + if (event->state >= PERF_EVENT_STATE_INACTIVE || + event->state < PERF_EVENT_STATE_ERROR) { raw_spin_unlock_irq(&ctx->lock); return; } @@ -2291,8 +2327,7 @@ static void _perf_event_enable(struct perf_event *event) event->state = PERF_EVENT_STATE_OFF; raw_spin_unlock_irq(&ctx->lock); - event_function_call(event, __perf_event_enable, - ___perf_event_enable, event); + event_function_call(event, __perf_event_enable, NULL); } /* @@ -2342,25 +2377,49 @@ static void ctx_sched_out(struct perf_event_context *ctx, struct perf_cpu_context *cpuctx, enum event_type_t event_type) { - struct perf_event *event; int is_active = ctx->is_active; + struct perf_event *event; - ctx->is_active &= ~event_type; - if (likely(!ctx->nr_events)) + lockdep_assert_held(&ctx->lock); + + if (likely(!ctx->nr_events)) { + /* + * See __perf_remove_from_context(). + */ + WARN_ON_ONCE(ctx->is_active); + if (ctx->task) + WARN_ON_ONCE(cpuctx->task_ctx); return; + } - update_context_time(ctx); - update_cgrp_time_from_cpuctx(cpuctx); - if (!ctx->nr_active) + ctx->is_active &= ~event_type; + if (!(ctx->is_active & EVENT_ALL)) + ctx->is_active = 0; + + if (ctx->task) { + WARN_ON_ONCE(cpuctx->task_ctx != ctx); + if (!ctx->is_active) + cpuctx->task_ctx = NULL; + } + + is_active ^= ctx->is_active; /* changed bits */ + + if (is_active & EVENT_TIME) { + /* update (and stop) ctx time */ + update_context_time(ctx); + update_cgrp_time_from_cpuctx(cpuctx); + } + + if (!ctx->nr_active || !(is_active & EVENT_ALL)) return; perf_pmu_disable(ctx->pmu); - if ((is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) { + if (is_active & EVENT_PINNED) { list_for_each_entry(event, &ctx->pinned_groups, group_entry) group_sched_out(event, cpuctx, ctx); } - if ((is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) { + if (is_active & EVENT_FLEXIBLE) { list_for_each_entry(event, &ctx->flexible_groups, group_entry) group_sched_out(event, cpuctx, ctx); } @@ -2518,17 +2577,21 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn, raw_spin_lock(&ctx->lock); raw_spin_lock_nested(&next_ctx->lock, SINGLE_DEPTH_NESTING); if (context_equiv(ctx, next_ctx)) { - /* - * XXX do we need a memory barrier of sorts - * wrt to rcu_dereference() of perf_event_ctxp - */ - task->perf_event_ctxp[ctxn] = next_ctx; - next->perf_event_ctxp[ctxn] = ctx; - ctx->task = next; - next_ctx->task = task; + WRITE_ONCE(ctx->task, next); + WRITE_ONCE(next_ctx->task, task); swap(ctx->task_ctx_data, next_ctx->task_ctx_data); + /* + * RCU_INIT_POINTER here is safe because we've not + * modified the ctx and the above modification of + * ctx->task and ctx->task_ctx_data are immaterial + * since those values are always verified under + * ctx->lock which we're now holding. + */ + RCU_INIT_POINTER(task->perf_event_ctxp[ctxn], next_ctx); + RCU_INIT_POINTER(next->perf_event_ctxp[ctxn], ctx); + do_switch = 0; perf_event_sync_stat(ctx, next_ctx); @@ -2541,8 +2604,7 @@ unlock: if (do_switch) { raw_spin_lock(&ctx->lock); - ctx_sched_out(ctx, cpuctx, EVENT_ALL); - cpuctx->task_ctx = NULL; + task_ctx_sched_out(cpuctx, ctx); raw_spin_unlock(&ctx->lock); } } @@ -2637,20 +2699,6 @@ void __perf_event_task_sched_out(struct task_struct *task, perf_cgroup_sched_out(task, next); } -static void task_ctx_sched_out(struct perf_event_context *ctx) -{ - struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); - - if (!cpuctx->task_ctx) - return; - - if (WARN_ON_ONCE(ctx != cpuctx->task_ctx)) - return; - - ctx_sched_out(ctx, cpuctx, EVENT_ALL); - cpuctx->task_ctx = NULL; -} - /* * Called with IRQs disabled */ @@ -2725,25 +2773,40 @@ ctx_sched_in(struct perf_event_context *ctx, enum event_type_t event_type, struct task_struct *task) { - u64 now; int is_active = ctx->is_active; + u64 now; + + lockdep_assert_held(&ctx->lock); - ctx->is_active |= event_type; if (likely(!ctx->nr_events)) return; - now = perf_clock(); - ctx->timestamp = now; - perf_cgroup_set_timestamp(task, ctx); + ctx->is_active |= (event_type | EVENT_TIME); + if (ctx->task) { + if (!is_active) + cpuctx->task_ctx = ctx; + else + WARN_ON_ONCE(cpuctx->task_ctx != ctx); + } + + is_active ^= ctx->is_active; /* changed bits */ + + if (is_active & EVENT_TIME) { + /* start ctx time */ + now = perf_clock(); + ctx->timestamp = now; + perf_cgroup_set_timestamp(task, ctx); + } + /* * First go through the list and put on any pinned groups * in order to give them the best chance of going on. */ - if (!(is_active & EVENT_PINNED) && (event_type & EVENT_PINNED)) + if (is_active & EVENT_PINNED) ctx_pinned_sched_in(ctx, cpuctx); /* Then walk through the lower prio flexible groups */ - if (!(is_active & EVENT_FLEXIBLE) && (event_type & EVENT_FLEXIBLE)) + if (is_active & EVENT_FLEXIBLE) ctx_flexible_sched_in(ctx, cpuctx); } @@ -2773,12 +2836,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx, * cpu flexible, task flexible. */ cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE); - - if (ctx->nr_events) - cpuctx->task_ctx = ctx; - - perf_event_sched_in(cpuctx, cpuctx->task_ctx, task); - + perf_event_sched_in(cpuctx, ctx, task); perf_pmu_enable(ctx->pmu); perf_ctx_unlock(cpuctx, ctx); } @@ -2800,6 +2858,16 @@ void __perf_event_task_sched_in(struct task_struct *prev, struct perf_event_context *ctx; int ctxn; + /* + * If cgroup events exist on this CPU, then we need to check if we have + * to switch in PMU state; cgroup event are system-wide mode only. + * + * Since cgroup events are CPU events, we must schedule these in before + * we schedule in the task events. + */ + if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) + perf_cgroup_sched_in(prev, task); + for_each_task_context_nr(ctxn) { ctx = task->perf_event_ctxp[ctxn]; if (likely(!ctx)) @@ -2807,13 +2875,6 @@ void __perf_event_task_sched_in(struct task_struct *prev, perf_event_context_sched_in(ctx, task); } - /* - * if cgroup events exist on this CPU, then we need - * to check if we have to switch in PMU state. - * cgroup event are system-wide mode only - */ - if (atomic_read(this_cpu_ptr(&perf_cgroup_events))) - perf_cgroup_sched_in(prev, task); if (atomic_read(&nr_switch_events)) perf_event_switch(task, prev, true); @@ -3051,17 +3112,6 @@ done: return rotate; } -#ifdef CONFIG_NO_HZ_FULL -bool perf_event_can_stop_tick(void) -{ - if (atomic_read(&nr_freq_events) || - __this_cpu_read(perf_throttled_count)) - return false; - else - return true; -} -#endif - void perf_event_task_tick(void) { struct list_head *head = this_cpu_ptr(&active_ctx_list); @@ -3072,6 +3122,7 @@ void perf_event_task_tick(void) __this_cpu_inc(perf_throttled_seq); throttled = __this_cpu_xchg(perf_throttled_count, 0); + tick_dep_clear_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS); list_for_each_entry_safe(ctx, tmp, head, active_ctx_list) perf_adjust_freq_unthr_context(ctx, throttled); @@ -3099,46 +3150,31 @@ static int event_enable_on_exec(struct perf_event *event, static void perf_event_enable_on_exec(int ctxn) { struct perf_event_context *ctx, *clone_ctx = NULL; + struct perf_cpu_context *cpuctx; struct perf_event *event; unsigned long flags; int enabled = 0; - int ret; local_irq_save(flags); ctx = current->perf_event_ctxp[ctxn]; if (!ctx || !ctx->nr_events) goto out; - /* - * We must ctxsw out cgroup events to avoid conflict - * when invoking perf_task_event_sched_in() later on - * in this function. Otherwise we end up trying to - * ctxswin cgroup events which are already scheduled - * in. - */ - perf_cgroup_sched_out(current, NULL); - - raw_spin_lock(&ctx->lock); - task_ctx_sched_out(ctx); - - list_for_each_entry(event, &ctx->event_list, event_entry) { - ret = event_enable_on_exec(event, ctx); - if (ret) - enabled = 1; - } + cpuctx = __get_cpu_context(ctx); + perf_ctx_lock(cpuctx, ctx); + ctx_sched_out(ctx, cpuctx, EVENT_TIME); + list_for_each_entry(event, &ctx->event_list, event_entry) + enabled |= event_enable_on_exec(event, ctx); /* - * Unclone this context if we enabled any event. + * Unclone and reschedule this context if we enabled any event. */ - if (enabled) + if (enabled) { clone_ctx = unclone_ctx(ctx); + ctx_resched(cpuctx, ctx); + } + perf_ctx_unlock(cpuctx, ctx); - raw_spin_unlock(&ctx->lock); - - /* - * Also calls ctxswin for cgroup events, if any: - */ - perf_event_context_sched_in(ctx, ctx->task); out: local_irq_restore(flags); @@ -3334,7 +3370,6 @@ static void __perf_event_init_context(struct perf_event_context *ctx) INIT_LIST_HEAD(&ctx->flexible_groups); INIT_LIST_HEAD(&ctx->event_list); atomic_set(&ctx->refcount, 1); - INIT_DELAYED_WORK(&ctx->orphans_remove, orphans_remove_work); } static struct perf_event_context * @@ -3519,13 +3554,37 @@ static void unaccount_event_cpu(struct perf_event *event, int cpu) atomic_dec(&per_cpu(perf_cgroup_events, cpu)); } +#ifdef CONFIG_NO_HZ_FULL +static DEFINE_SPINLOCK(nr_freq_lock); +#endif + +static void unaccount_freq_event_nohz(void) +{ +#ifdef CONFIG_NO_HZ_FULL + spin_lock(&nr_freq_lock); + if (atomic_dec_and_test(&nr_freq_events)) + tick_nohz_dep_clear(TICK_DEP_BIT_PERF_EVENTS); + spin_unlock(&nr_freq_lock); +#endif +} + +static void unaccount_freq_event(void) +{ + if (tick_nohz_full_enabled()) + unaccount_freq_event_nohz(); + else + atomic_dec(&nr_freq_events); +} + static void unaccount_event(struct perf_event *event) { + bool dec = false; + if (event->parent) return; if (event->attach_state & PERF_ATTACH_TASK) - static_key_slow_dec_deferred(&perf_sched_events); + dec = true; if (event->attr.mmap || event->attr.mmap_data) atomic_dec(&nr_mmap_events); if (event->attr.comm) @@ -3533,19 +3592,32 @@ static void unaccount_event(struct perf_event *event) if (event->attr.task) atomic_dec(&nr_task_events); if (event->attr.freq) - atomic_dec(&nr_freq_events); + unaccount_freq_event(); if (event->attr.context_switch) { - static_key_slow_dec_deferred(&perf_sched_events); + dec = true; atomic_dec(&nr_switch_events); } if (is_cgroup_event(event)) - static_key_slow_dec_deferred(&perf_sched_events); + dec = true; if (has_branch_stack(event)) - static_key_slow_dec_deferred(&perf_sched_events); + dec = true; + + if (dec) { + if (!atomic_add_unless(&perf_sched_count, -1, 1)) + schedule_delayed_work(&perf_sched_work, HZ); + } unaccount_event_cpu(event, event->cpu); } +static void perf_sched_delayed(struct work_struct *work) +{ + mutex_lock(&perf_sched_mutex); + if (atomic_dec_and_test(&perf_sched_count)) + static_branch_disable(&perf_sched_events); + mutex_unlock(&perf_sched_mutex); +} + /* * The following implement mutual exclusion of events on "exclusive" pmus * (PERF_PMU_CAP_EXCLUSIVE). Such pmus can only have one event scheduled @@ -3556,7 +3628,7 @@ static void unaccount_event(struct perf_event *event) * 3) two matching events on the same context. * * The former two cases are handled in the allocation path (perf_event_alloc(), - * __free_event()), the latter -- before the first perf_install_in_context(). + * _free_event()), the latter -- before the first perf_install_in_context(). */ static int exclusive_event_init(struct perf_event *event) { @@ -3631,29 +3703,6 @@ static bool exclusive_event_installable(struct perf_event *event, return true; } -static void __free_event(struct perf_event *event) -{ - if (!event->parent) { - if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) - put_callchain_buffers(); - } - - perf_event_free_bpf_prog(event); - - if (event->destroy) - event->destroy(event); - - if (event->ctx) - put_ctx(event->ctx); - - if (event->pmu) { - exclusive_event_destroy(event); - module_put(event->pmu->module); - } - - call_rcu(&event->rcu_head, free_event_rcu); -} - static void _free_event(struct perf_event *event) { irq_work_sync(&event->pending); @@ -3675,7 +3724,25 @@ static void _free_event(struct perf_event *event) if (is_cgroup_event(event)) perf_detach_cgroup(event); - __free_event(event); + if (!event->parent) { + if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) + put_callchain_buffers(); + } + + perf_event_free_bpf_prog(event); + + if (event->destroy) + event->destroy(event); + + if (event->ctx) + put_ctx(event->ctx); + + if (event->pmu) { + exclusive_event_destroy(event); + module_put(event->pmu->module); + } + + call_rcu(&event->rcu_head, free_event_rcu); } /* @@ -3702,14 +3769,13 @@ static void perf_remove_from_owner(struct perf_event *event) struct task_struct *owner; rcu_read_lock(); - owner = ACCESS_ONCE(event->owner); /* - * Matches the smp_wmb() in perf_event_exit_task(). If we observe - * !owner it means the list deletion is complete and we can indeed - * free this event, otherwise we need to serialize on + * Matches the smp_store_release() in perf_event_exit_task(). If we + * observe !owner it means the list deletion is complete and we can + * indeed free this event, otherwise we need to serialize on * owner->perf_event_mutex. */ - smp_read_barrier_depends(); + owner = lockless_dereference(event->owner); if (owner) { /* * Since delayed_put_task_struct() also drops the last @@ -3737,8 +3803,10 @@ static void perf_remove_from_owner(struct perf_event *event) * ensured they're done, and we can proceed with freeing the * event. */ - if (event->owner) + if (event->owner) { list_del_init(&event->owner_entry); + smp_store_release(&event->owner, NULL); + } mutex_unlock(&owner->perf_event_mutex); put_task_struct(owner); } @@ -3746,37 +3814,111 @@ static void perf_remove_from_owner(struct perf_event *event) static void put_event(struct perf_event *event) { - struct perf_event_context *ctx; - if (!atomic_long_dec_and_test(&event->refcount)) return; + _free_event(event); +} + +/* + * Kill an event dead; while event:refcount will preserve the event + * object, it will not preserve its functionality. Once the last 'user' + * gives up the object, we'll destroy the thing. + */ +int perf_event_release_kernel(struct perf_event *event) +{ + struct perf_event_context *ctx = event->ctx; + struct perf_event *child, *tmp; + + /* + * If we got here through err_file: fput(event_file); we will not have + * attached to a context yet. + */ + if (!ctx) { + WARN_ON_ONCE(event->attach_state & + (PERF_ATTACH_CONTEXT|PERF_ATTACH_GROUP)); + goto no_ctx; + } + if (!is_kernel_event(event)) perf_remove_from_owner(event); + ctx = perf_event_ctx_lock(event); + WARN_ON_ONCE(ctx->parent_ctx); + perf_remove_from_context(event, DETACH_GROUP); + + raw_spin_lock_irq(&ctx->lock); /* - * There are two ways this annotation is useful: + * Mark this even as STATE_DEAD, there is no external reference to it + * anymore. * - * 1) there is a lock recursion from perf_event_exit_task - * see the comment there. + * Anybody acquiring event->child_mutex after the below loop _must_ + * also see this, most importantly inherit_event() which will avoid + * placing more children on the list. * - * 2) there is a lock-inversion with mmap_sem through - * perf_read_group(), which takes faults while - * holding ctx->mutex, however this is called after - * the last filedesc died, so there is no possibility - * to trigger the AB-BA case. + * Thus this guarantees that we will in fact observe and kill _ALL_ + * child events. */ - ctx = perf_event_ctx_lock_nested(event, SINGLE_DEPTH_NESTING); - WARN_ON_ONCE(ctx->parent_ctx); - perf_remove_from_context(event, true); + event->state = PERF_EVENT_STATE_DEAD; + raw_spin_unlock_irq(&ctx->lock); + perf_event_ctx_unlock(event, ctx); - _free_event(event); -} +again: + mutex_lock(&event->child_mutex); + list_for_each_entry(child, &event->child_list, child_list) { -int perf_event_release_kernel(struct perf_event *event) -{ - put_event(event); + /* + * Cannot change, child events are not migrated, see the + * comment with perf_event_ctx_lock_nested(). + */ + ctx = lockless_dereference(child->ctx); + /* + * Since child_mutex nests inside ctx::mutex, we must jump + * through hoops. We start by grabbing a reference on the ctx. + * + * Since the event cannot get freed while we hold the + * child_mutex, the context must also exist and have a !0 + * reference count. + */ + get_ctx(ctx); + + /* + * Now that we have a ctx ref, we can drop child_mutex, and + * acquire ctx::mutex without fear of it going away. Then we + * can re-acquire child_mutex. + */ + mutex_unlock(&event->child_mutex); + mutex_lock(&ctx->mutex); + mutex_lock(&event->child_mutex); + + /* + * Now that we hold ctx::mutex and child_mutex, revalidate our + * state, if child is still the first entry, it didn't get freed + * and we can continue doing so. + */ + tmp = list_first_entry_or_null(&event->child_list, + struct perf_event, child_list); + if (tmp == child) { + perf_remove_from_context(child, DETACH_GROUP); + list_del(&child->child_list); + free_event(child); + /* + * This matches the refcount bump in inherit_event(); + * this can't be the last reference. + */ + put_event(event); + } + + mutex_unlock(&event->child_mutex); + mutex_unlock(&ctx->mutex); + put_ctx(ctx); + goto again; + } + mutex_unlock(&event->child_mutex); + +no_ctx: + put_event(event); /* Must be the 'last' reference */ return 0; } EXPORT_SYMBOL_GPL(perf_event_release_kernel); @@ -3786,46 +3928,10 @@ EXPORT_SYMBOL_GPL(perf_event_release_kernel); */ static int perf_release(struct inode *inode, struct file *file) { - put_event(file->private_data); + perf_event_release_kernel(file->private_data); return 0; } -/* - * Remove all orphanes events from the context. - */ -static void orphans_remove_work(struct work_struct *work) -{ - struct perf_event_context *ctx; - struct perf_event *event, *tmp; - - ctx = container_of(work, struct perf_event_context, - orphans_remove.work); - - mutex_lock(&ctx->mutex); - list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) { - struct perf_event *parent_event = event->parent; - - if (!is_orphaned_child(event)) - continue; - - perf_remove_from_context(event, true); - - mutex_lock(&parent_event->child_mutex); - list_del_init(&event->child_list); - mutex_unlock(&parent_event->child_mutex); - - free_event(event); - put_event(parent_event); - } - - raw_spin_lock_irq(&ctx->lock); - ctx->orphans_remove_sched = false; - raw_spin_unlock_irq(&ctx->lock); - mutex_unlock(&ctx->mutex); - - put_ctx(ctx); -} - u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running) { struct perf_event *child; @@ -3969,7 +4075,7 @@ static bool is_event_hup(struct perf_event *event) { bool no_children; - if (event->state != PERF_EVENT_STATE_EXIT) + if (event->state > PERF_EVENT_STATE_EXIT) return false; mutex_lock(&event->child_mutex); @@ -4054,7 +4160,7 @@ static void _perf_event_reset(struct perf_event *event) /* * Holding the top-level event's child_mutex means that any * descendant process that has inherited this event will block - * in sync_child_event if it goes to exit, thus satisfying the + * in perf_event_exit_event() if it goes to exit, thus satisfying the * task existence requirements of perf_event_enable/disable. */ static void perf_event_for_each_child(struct perf_event *event, @@ -4086,36 +4192,14 @@ static void perf_event_for_each(struct perf_event *event, perf_event_for_each_child(sibling, func); } -struct period_event { - struct perf_event *event; - u64 value; -}; - -static void ___perf_event_period(void *info) -{ - struct period_event *pe = info; - struct perf_event *event = pe->event; - u64 value = pe->value; - - if (event->attr.freq) { - event->attr.sample_freq = value; - } else { - event->attr.sample_period = value; - event->hw.sample_period = value; - } - - local64_set(&event->hw.period_left, 0); -} - -static int __perf_event_period(void *info) +static void __perf_event_period(struct perf_event *event, + struct perf_cpu_context *cpuctx, + struct perf_event_context *ctx, + void *info) { - struct period_event *pe = info; - struct perf_event *event = pe->event; - struct perf_event_context *ctx = event->ctx; - u64 value = pe->value; + u64 value = *((u64 *)info); bool active; - raw_spin_lock(&ctx->lock); if (event->attr.freq) { event->attr.sample_freq = value; } else { @@ -4135,14 +4219,10 @@ static int __perf_event_period(void *info) event->pmu->start(event, PERF_EF_RELOAD); perf_pmu_enable(ctx->pmu); } - raw_spin_unlock(&ctx->lock); - - return 0; } static int perf_event_period(struct perf_event *event, u64 __user *arg) { - struct period_event pe = { .event = event, }; u64 value; if (!is_sampling_event(event)) @@ -4157,10 +4237,7 @@ static int perf_event_period(struct perf_event *event, u64 __user *arg) if (event->attr.freq && value > sysctl_perf_event_sample_rate) return -EINVAL; - pe.value = value; - - event_function_call(event, __perf_event_period, - ___perf_event_period, &pe); + event_function_call(event, __perf_event_period, &value); return 0; } @@ -4932,7 +5009,7 @@ static void perf_pending_event(struct irq_work *entry) if (event->pending_disable) { event->pending_disable = 0; - __perf_event_disable(event); + perf_event_disable_local(event); } if (event->pending_wakeup) { @@ -6359,9 +6436,9 @@ static int __perf_event_overflow(struct perf_event *event, if (unlikely(throttle && hwc->interrupts >= max_samples_per_tick)) { __this_cpu_inc(perf_throttled_count); + tick_dep_set_cpu(smp_processor_id(), TICK_DEP_BIT_PERF_EVENTS); hwc->interrupts = MAX_INTERRUPTS; perf_log_throttle(event, 0); - tick_nohz_full_kick(); ret = 1; } } @@ -6720,7 +6797,7 @@ static void swevent_hlist_release(struct swevent_htable *swhash) kfree_rcu(hlist, rcu_head); } -static void swevent_hlist_put_cpu(struct perf_event *event, int cpu) +static void swevent_hlist_put_cpu(int cpu) { struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); @@ -6732,15 +6809,15 @@ static void swevent_hlist_put_cpu(struct perf_event *event, int cpu) mutex_unlock(&swhash->hlist_mutex); } -static void swevent_hlist_put(struct perf_event *event) +static void swevent_hlist_put(void) { int cpu; for_each_possible_cpu(cpu) - swevent_hlist_put_cpu(event, cpu); + swevent_hlist_put_cpu(cpu); } -static int swevent_hlist_get_cpu(struct perf_event *event, int cpu) +static int swevent_hlist_get_cpu(int cpu) { struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); int err = 0; @@ -6763,14 +6840,13 @@ exit: return err; } -static int swevent_hlist_get(struct perf_event *event) +static int swevent_hlist_get(void) { - int err; - int cpu, failed_cpu; + int err, cpu, failed_cpu; get_online_cpus(); for_each_possible_cpu(cpu) { - err = swevent_hlist_get_cpu(event, cpu); + err = swevent_hlist_get_cpu(cpu); if (err) { failed_cpu = cpu; goto fail; @@ -6783,7 +6859,7 @@ fail: for_each_possible_cpu(cpu) { if (cpu == failed_cpu) break; - swevent_hlist_put_cpu(event, cpu); + swevent_hlist_put_cpu(cpu); } put_online_cpus(); @@ -6799,7 +6875,7 @@ static void sw_perf_event_destroy(struct perf_event *event) WARN_ON(event->parent); static_key_slow_dec(&perf_swevent_enabled[event_id]); - swevent_hlist_put(event); + swevent_hlist_put(); } static int perf_swevent_init(struct perf_event *event) @@ -6830,7 +6906,7 @@ static int perf_swevent_init(struct perf_event *event) if (!event->parent) { int err; - err = swevent_hlist_get(event); + err = swevent_hlist_get(); if (err) return err; @@ -7751,31 +7827,75 @@ static void account_event_cpu(struct perf_event *event, int cpu) atomic_inc(&per_cpu(perf_cgroup_events, cpu)); } +/* Freq events need the tick to stay alive (see perf_event_task_tick). */ +static void account_freq_event_nohz(void) +{ +#ifdef CONFIG_NO_HZ_FULL + /* Lock so we don't race with concurrent unaccount */ + spin_lock(&nr_freq_lock); + if (atomic_inc_return(&nr_freq_events) == 1) + tick_nohz_dep_set(TICK_DEP_BIT_PERF_EVENTS); + spin_unlock(&nr_freq_lock); +#endif +} + +static void account_freq_event(void) +{ + if (tick_nohz_full_enabled()) + account_freq_event_nohz(); + else + atomic_inc(&nr_freq_events); +} + + static void account_event(struct perf_event *event) { + bool inc = false; + if (event->parent) return; if (event->attach_state & PERF_ATTACH_TASK) - static_key_slow_inc(&perf_sched_events.key); + inc = true; if (event->attr.mmap || event->attr.mmap_data) atomic_inc(&nr_mmap_events); if (event->attr.comm) atomic_inc(&nr_comm_events); if (event->attr.task) atomic_inc(&nr_task_events); - if (event->attr.freq) { - if (atomic_inc_return(&nr_freq_events) == 1) - tick_nohz_full_kick_all(); - } + if (event->attr.freq) + account_freq_event(); if (event->attr.context_switch) { atomic_inc(&nr_switch_events); - static_key_slow_inc(&perf_sched_events.key); + inc = true; } if (has_branch_stack(event)) - static_key_slow_inc(&perf_sched_events.key); + inc = true; if (is_cgroup_event(event)) - static_key_slow_inc(&perf_sched_events.key); + inc = true; + + if (inc) { + if (atomic_inc_not_zero(&perf_sched_count)) + goto enabled; + + mutex_lock(&perf_sched_mutex); + if (!atomic_read(&perf_sched_count)) { + static_branch_enable(&perf_sched_events); + /* + * Guarantee that all CPUs observe they key change and + * call the perf scheduling hooks before proceeding to + * install events that need them. + */ + synchronize_sched(); + } + /* + * Now that we have waited for the sync_sched(), allow further + * increments to by-pass the mutex. + */ + atomic_inc(&perf_sched_count); + mutex_unlock(&perf_sched_mutex); + } +enabled: account_event_cpu(event, event->cpu); } @@ -7911,6 +8031,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, } } + /* symmetric to unaccount_event() in _free_event() */ + account_event(event); + return event; err_per_task: @@ -8274,8 +8397,6 @@ SYSCALL_DEFINE5(perf_event_open, } } - account_event(event); - /* * Special case software events and allow them to be part of * any hardware group. @@ -8394,10 +8515,19 @@ SYSCALL_DEFINE5(perf_event_open, if (move_group) { gctx = group_leader->ctx; mutex_lock_double(&gctx->mutex, &ctx->mutex); + if (gctx->task == TASK_TOMBSTONE) { + err = -ESRCH; + goto err_locked; + } } else { mutex_lock(&ctx->mutex); } + if (ctx->task == TASK_TOMBSTONE) { + err = -ESRCH; + goto err_locked; + } + if (!perf_event_validate_size(event)) { err = -E2BIG; goto err_locked; @@ -8422,11 +8552,11 @@ SYSCALL_DEFINE5(perf_event_open, * See perf_event_ctx_lock() for comments on the details * of swizzling perf_event::ctx. */ - perf_remove_from_context(group_leader, false); + perf_remove_from_context(group_leader, 0); list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { - perf_remove_from_context(sibling, false); + perf_remove_from_context(sibling, 0); put_ctx(gctx); } @@ -8479,6 +8609,8 @@ SYSCALL_DEFINE5(perf_event_open, perf_event__header_size(event); perf_event__id_header_size(event); + event->owner = current; + perf_install_in_context(ctx, event, event->cpu); perf_unpin_context(ctx); @@ -8488,8 +8620,6 @@ SYSCALL_DEFINE5(perf_event_open, put_online_cpus(); - event->owner = current; - mutex_lock(¤t->perf_event_mutex); list_add_tail(&event->owner_entry, ¤t->perf_event_list); mutex_unlock(¤t->perf_event_mutex); @@ -8514,7 +8644,12 @@ err_context: perf_unpin_context(ctx); put_ctx(ctx); err_alloc: - free_event(event); + /* + * If event_file is set, the fput() above will have called ->release() + * and that will take care of freeing the event. + */ + if (!event_file) + free_event(event); err_cpus: put_online_cpus(); err_task: @@ -8556,9 +8691,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, } /* Mark owner so we could distinguish it from user events. */ - event->owner = EVENT_OWNER_KERNEL; - - account_event(event); + event->owner = TASK_TOMBSTONE; ctx = find_get_context(event->pmu, task, event); if (IS_ERR(ctx)) { @@ -8568,12 +8701,14 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, WARN_ON_ONCE(ctx->parent_ctx); mutex_lock(&ctx->mutex); + if (ctx->task == TASK_TOMBSTONE) { + err = -ESRCH; + goto err_unlock; + } + if (!exclusive_event_installable(event, ctx)) { - mutex_unlock(&ctx->mutex); - perf_unpin_context(ctx); - put_ctx(ctx); err = -EBUSY; - goto err_free; + goto err_unlock; } perf_install_in_context(ctx, event, cpu); @@ -8582,6 +8717,10 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, return event; +err_unlock: + mutex_unlock(&ctx->mutex); + perf_unpin_context(ctx); + put_ctx(ctx); err_free: free_event(event); err: @@ -8606,7 +8745,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu) mutex_lock_double(&src_ctx->mutex, &dst_ctx->mutex); list_for_each_entry_safe(event, tmp, &src_ctx->event_list, event_entry) { - perf_remove_from_context(event, false); + perf_remove_from_context(event, 0); unaccount_event_cpu(event, src_cpu); put_ctx(src_ctx); list_add(&event->migrate_entry, &events); @@ -8673,33 +8812,15 @@ static void sync_child_event(struct perf_event *child_event, &parent_event->child_total_time_enabled); atomic64_add(child_event->total_time_running, &parent_event->child_total_time_running); - - /* - * Remove this event from the parent's list - */ - WARN_ON_ONCE(parent_event->ctx->parent_ctx); - mutex_lock(&parent_event->child_mutex); - list_del_init(&child_event->child_list); - mutex_unlock(&parent_event->child_mutex); - - /* - * Make sure user/parent get notified, that we just - * lost one event. - */ - perf_event_wakeup(parent_event); - - /* - * Release the parent event, if this was the last - * reference to it. - */ - put_event(parent_event); } static void -__perf_event_exit_task(struct perf_event *child_event, - struct perf_event_context *child_ctx, - struct task_struct *child) +perf_event_exit_event(struct perf_event *child_event, + struct perf_event_context *child_ctx, + struct task_struct *child) { + struct perf_event *parent_event = child_event->parent; + /* * Do not destroy the 'original' grouping; because of the context * switch optimization the original events could've ended up in a @@ -8712,57 +8833,86 @@ __perf_event_exit_task(struct perf_event *child_event, * Do destroy all inherited groups, we don't care about those * and being thorough is better. */ - perf_remove_from_context(child_event, !!child_event->parent); + raw_spin_lock_irq(&child_ctx->lock); + WARN_ON_ONCE(child_ctx->is_active); + + if (parent_event) + perf_group_detach(child_event); + list_del_event(child_event, child_ctx); + child_event->state = PERF_EVENT_STATE_EXIT; /* is_event_hup() */ + raw_spin_unlock_irq(&child_ctx->lock); /* - * It can happen that the parent exits first, and has events - * that are still around due to the child reference. These - * events need to be zapped. + * Parent events are governed by their filedesc, retain them. */ - if (child_event->parent) { - sync_child_event(child_event, child); - free_event(child_event); - } else { - child_event->state = PERF_EVENT_STATE_EXIT; + if (!parent_event) { perf_event_wakeup(child_event); + return; } + /* + * Child events can be cleaned up. + */ + + sync_child_event(child_event, child); + + /* + * Remove this event from the parent's list + */ + WARN_ON_ONCE(parent_event->ctx->parent_ctx); + mutex_lock(&parent_event->child_mutex); + list_del_init(&child_event->child_list); + mutex_unlock(&parent_event->child_mutex); + + /* + * Kick perf_poll() for is_event_hup(). + */ + perf_event_wakeup(parent_event); + free_event(child_event); + put_event(parent_event); } static void perf_event_exit_task_context(struct task_struct *child, int ctxn) { - struct perf_event *child_event, *next; struct perf_event_context *child_ctx, *clone_ctx = NULL; - unsigned long flags; + struct perf_event *child_event, *next; + + WARN_ON_ONCE(child != current); - if (likely(!child->perf_event_ctxp[ctxn])) + child_ctx = perf_pin_task_context(child, ctxn); + if (!child_ctx) return; - local_irq_save(flags); /* - * We can't reschedule here because interrupts are disabled, - * and either child is current or it is a task that can't be - * scheduled, so we are now safe from rescheduling changing - * our context. + * In order to reduce the amount of tricky in ctx tear-down, we hold + * ctx::mutex over the entire thing. This serializes against almost + * everything that wants to access the ctx. + * + * The exception is sys_perf_event_open() / + * perf_event_create_kernel_count() which does find_get_context() + * without ctx::mutex (it cannot because of the move_group double mutex + * lock thing). See the comments in perf_install_in_context(). */ - child_ctx = rcu_dereference_raw(child->perf_event_ctxp[ctxn]); + mutex_lock(&child_ctx->mutex); /* - * Take the context lock here so that if find_get_context is - * reading child->perf_event_ctxp, we wait until it has - * incremented the context's refcount before we do put_ctx below. + * In a single ctx::lock section, de-schedule the events and detach the + * context from the task such that we cannot ever get it scheduled back + * in. */ - raw_spin_lock(&child_ctx->lock); - task_ctx_sched_out(child_ctx); - child->perf_event_ctxp[ctxn] = NULL; + raw_spin_lock_irq(&child_ctx->lock); + task_ctx_sched_out(__get_cpu_context(child_ctx), child_ctx); /* - * If this context is a clone; unclone it so it can't get - * swapped to another process while we're removing all - * the events from it. + * Now that the context is inactive, destroy the task <-> ctx relation + * and mark the context dead. */ + RCU_INIT_POINTER(child->perf_event_ctxp[ctxn], NULL); + put_ctx(child_ctx); /* cannot be last */ + WRITE_ONCE(child_ctx->task, TASK_TOMBSTONE); + put_task_struct(current); /* cannot be last */ + clone_ctx = unclone_ctx(child_ctx); - update_context_time(child_ctx); - raw_spin_unlock_irqrestore(&child_ctx->lock, flags); + raw_spin_unlock_irq(&child_ctx->lock); if (clone_ctx) put_ctx(clone_ctx); @@ -8774,20 +8924,8 @@ static void perf_event_exit_task_context(struct task_struct *child, int ctxn) */ perf_event_task(child, child_ctx, 0); - /* - * We can recurse on the same lock type through: - * - * __perf_event_exit_task() - * sync_child_event() - * put_event() - * mutex_lock(&ctx->mutex) - * - * But since its the parent context it won't be the same instance. - */ - mutex_lock(&child_ctx->mutex); - list_for_each_entry_safe(child_event, next, &child_ctx->event_list, event_entry) - __perf_event_exit_task(child_event, child_ctx, child); + perf_event_exit_event(child_event, child_ctx, child); mutex_unlock(&child_ctx->mutex); @@ -8812,8 +8950,7 @@ void perf_event_exit_task(struct task_struct *child) * the owner, closes a race against perf_release() where * we need to serialize on the owner->perf_event_mutex. */ - smp_wmb(); - event->owner = NULL; + smp_store_release(&event->owner, NULL); } mutex_unlock(&child->perf_event_mutex); @@ -8896,21 +9033,20 @@ void perf_event_delayed_put(struct task_struct *task) WARN_ON_ONCE(task->perf_event_ctxp[ctxn]); } -struct perf_event *perf_event_get(unsigned int fd) +struct file *perf_event_get(unsigned int fd) { - int err; - struct fd f; - struct perf_event *event; + struct file *file; - err = perf_fget_light(fd, &f); - if (err) - return ERR_PTR(err); + file = fget_raw(fd); + if (!file) + return ERR_PTR(-EBADF); - event = f.file->private_data; - atomic_long_inc(&event->refcount); - fdput(f); + if (file->f_op != &perf_fops) { + fput(file); + return ERR_PTR(-EBADF); + } - return event; + return file; } const struct perf_event_attr *perf_event_attrs(struct perf_event *event) @@ -8953,8 +9089,16 @@ inherit_event(struct perf_event *parent_event, if (IS_ERR(child_event)) return child_event; + /* + * is_orphaned_event() and list_add_tail(&parent_event->child_list) + * must be under the same lock in order to serialize against + * perf_event_release_kernel(), such that either we must observe + * is_orphaned_event() or they will observe us on the child_list. + */ + mutex_lock(&parent_event->child_mutex); if (is_orphaned_event(parent_event) || !atomic_long_inc_not_zero(&parent_event->refcount)) { + mutex_unlock(&parent_event->child_mutex); free_event(child_event); return NULL; } @@ -9002,8 +9146,6 @@ inherit_event(struct perf_event *parent_event, /* * Link this into the parent event's child list */ - WARN_ON_ONCE(parent_event->ctx->parent_ctx); - mutex_lock(&parent_event->child_mutex); list_add_tail(&child_event->child_list, &parent_event->child_list); mutex_unlock(&parent_event->child_mutex); @@ -9208,7 +9350,7 @@ static void perf_event_init_cpu(int cpu) struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu); mutex_lock(&swhash->hlist_mutex); - if (swhash->hlist_refcount > 0) { + if (swhash->hlist_refcount > 0 && !swevent_hlist_deref(swhash)) { struct swevent_hlist *hlist; hlist = kzalloc_node(sizeof(*hlist), GFP_KERNEL, cpu_to_node(cpu)); @@ -9221,13 +9363,14 @@ static void perf_event_init_cpu(int cpu) #if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC_CORE static void __perf_event_exit_context(void *__info) { - struct remove_event re = { .detach_group = true }; struct perf_event_context *ctx = __info; + struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); + struct perf_event *event; - rcu_read_lock(); - list_for_each_entry_rcu(re.event, &ctx->event_list, event_entry) - __perf_remove_from_context(&re); - rcu_read_unlock(); + raw_spin_lock(&ctx->lock); + list_for_each_entry(event, &ctx->event_list, event_entry) + __perf_remove_from_context(event, cpuctx, ctx, (void *)DETACH_GROUP); + raw_spin_unlock(&ctx->lock); } static void perf_event_exit_cpu_context(int cpu) @@ -9283,11 +9426,9 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - case CPU_DOWN_FAILED: perf_event_init_cpu(cpu); break; - case CPU_UP_CANCELED: case CPU_DOWN_PREPARE: perf_event_exit_cpu(cpu); break; @@ -9316,9 +9457,6 @@ void __init perf_event_init(void) ret = init_hw_breakpoint(); WARN(ret, "hw_breakpoint initialization failed with: %d", ret); - /* do not patch jump label more than once per second */ - jump_label_rate_limit(&perf_sched_events, HZ); - /* * Build time assertion that we keep the data_head at the intended * location. IOW, validation we got the __reserved[] size right. @@ -9338,6 +9476,7 @@ ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, return 0; } +EXPORT_SYMBOL_GPL(perf_event_sysfs_show); static int __init perf_event_sysfs_init(void) { diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index 92ce5f4ccc26..3f8cb1e14588 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -444,7 +444,7 @@ int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *att * current task. */ if (irqs_disabled() && bp->ctx && bp->ctx->task == current) - __perf_event_disable(bp); + perf_event_disable_local(bp); else perf_event_disable(bp); diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index adfdc0536117..1faad2cfdb9e 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -459,6 +459,25 @@ static void rb_free_aux_page(struct ring_buffer *rb, int idx) __free_page(page); } +static void __rb_free_aux(struct ring_buffer *rb) +{ + int pg; + + if (rb->aux_priv) { + rb->free_aux(rb->aux_priv); + rb->free_aux = NULL; + rb->aux_priv = NULL; + } + + if (rb->aux_nr_pages) { + for (pg = 0; pg < rb->aux_nr_pages; pg++) + rb_free_aux_page(rb, pg); + + kfree(rb->aux_pages); + rb->aux_nr_pages = 0; + } +} + int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event, pgoff_t pgoff, int nr_pages, long watermark, int flags) { @@ -547,30 +566,11 @@ out: if (!ret) rb->aux_pgoff = pgoff; else - rb_free_aux(rb); + __rb_free_aux(rb); return ret; } -static void __rb_free_aux(struct ring_buffer *rb) -{ - int pg; - - if (rb->aux_priv) { - rb->free_aux(rb->aux_priv); - rb->free_aux = NULL; - rb->aux_priv = NULL; - } - - if (rb->aux_nr_pages) { - for (pg = 0; pg < rb->aux_nr_pages; pg++) - rb_free_aux_page(rb, pg); - - kfree(rb->aux_pages); - rb->aux_nr_pages = 0; - } -} - void rb_free_aux(struct ring_buffer *rb) { if (atomic_dec_and_test(&rb->aux_refcount)) diff --git a/kernel/futex.c b/kernel/futex.c index 0773f2b23b10..a5d2e74c89e0 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -124,16 +124,16 @@ * futex_wait(futex, val); * * waiters++; (a) - * mb(); (A) <-- paired with -. - * | - * lock(hash_bucket(futex)); | - * | - * uval = *futex; | - * | *futex = newval; - * | sys_futex(WAKE, futex); - * | futex_wake(futex); - * | - * `-------> mb(); (B) + * smp_mb(); (A) <-- paired with -. + * | + * lock(hash_bucket(futex)); | + * | + * uval = *futex; | + * | *futex = newval; + * | sys_futex(WAKE, futex); + * | futex_wake(futex); + * | + * `--------> smp_mb(); (B) * if (uval == val) * queue(); * unlock(hash_bucket(futex)); @@ -334,7 +334,7 @@ static inline void futex_get_mm(union futex_key *key) /* * Ensure futex_get_mm() implies a full barrier such that * get_futex_key() implies a full barrier. This is relied upon - * as full barrier (B), see the ordering comment above. + * as smp_mb(); (B), see the ordering comment above. */ smp_mb__after_atomic(); } @@ -407,10 +407,10 @@ static void get_futex_key_refs(union futex_key *key) switch (key->both.offset & (FUT_OFF_INODE|FUT_OFF_MMSHARED)) { case FUT_OFF_INODE: - ihold(key->shared.inode); /* implies MB (B) */ + ihold(key->shared.inode); /* implies smp_mb(); (B) */ break; case FUT_OFF_MMSHARED: - futex_get_mm(key); /* implies MB (B) */ + futex_get_mm(key); /* implies smp_mb(); (B) */ break; default: /* @@ -418,7 +418,7 @@ static void get_futex_key_refs(union futex_key *key) * mm, therefore the only purpose of calling get_futex_key_refs * is because we need the barrier for the lockless waiter check. */ - smp_mb(); /* explicit MB (B) */ + smp_mb(); /* explicit smp_mb(); (B) */ } } @@ -497,7 +497,7 @@ get_futex_key(u32 __user *uaddr, int fshared, union futex_key *key, int rw) if (!fshared) { key->private.mm = mm; key->private.address = address; - get_futex_key_refs(key); /* implies MB (B) */ + get_futex_key_refs(key); /* implies smp_mb(); (B) */ return 0; } @@ -520,7 +520,20 @@ again: else err = 0; - lock_page(page); + /* + * The treatment of mapping from this point on is critical. The page + * lock protects many things but in this context the page lock + * stabilizes mapping, prevents inode freeing in the shared + * file-backed region case and guards against movement to swap cache. + * + * Strictly speaking the page lock is not needed in all cases being + * considered here and page lock forces unnecessarily serialization + * From this point on, mapping will be re-verified if necessary and + * page lock will be acquired only if it is unavoidable + */ + page = compound_head(page); + mapping = READ_ONCE(page->mapping); + /* * If page->mapping is NULL, then it cannot be a PageAnon * page; but it might be the ZERO_PAGE or in the gate area or @@ -536,19 +549,31 @@ again: * shmem_writepage move it from filecache to swapcache beneath us: * an unlikely race, but we do need to retry for page->mapping. */ - mapping = compound_head(page)->mapping; - if (!mapping) { - int shmem_swizzled = PageSwapCache(page); + if (unlikely(!mapping)) { + int shmem_swizzled; + + /* + * Page lock is required to identify which special case above + * applies. If this is really a shmem page then the page lock + * will prevent unexpected transitions. + */ + lock_page(page); + shmem_swizzled = PageSwapCache(page) || page->mapping; unlock_page(page); put_page(page); + if (shmem_swizzled) goto again; + return -EFAULT; } /* * Private mappings are handled in a simple way. * + * If the futex key is stored on an anonymous page, then the associated + * object is the mm which is implicitly pinned by the calling process. + * * NOTE: When userspace waits on a MAP_SHARED mapping, even if * it's a read-only handle, it's expected that futexes attach to * the object not the particular process. @@ -566,16 +591,74 @@ again: key->both.offset |= FUT_OFF_MMSHARED; /* ref taken on mm */ key->private.mm = mm; key->private.address = address; + + get_futex_key_refs(key); /* implies smp_mb(); (B) */ + } else { + struct inode *inode; + + /* + * The associated futex object in this case is the inode and + * the page->mapping must be traversed. Ordinarily this should + * be stabilised under page lock but it's not strictly + * necessary in this case as we just want to pin the inode, not + * update the radix tree or anything like that. + * + * The RCU read lock is taken as the inode is finally freed + * under RCU. If the mapping still matches expectations then the + * mapping->host can be safely accessed as being a valid inode. + */ + rcu_read_lock(); + + if (READ_ONCE(page->mapping) != mapping) { + rcu_read_unlock(); + put_page(page); + + goto again; + } + + inode = READ_ONCE(mapping->host); + if (!inode) { + rcu_read_unlock(); + put_page(page); + + goto again; + } + + /* + * Take a reference unless it is about to be freed. Previously + * this reference was taken by ihold under the page lock + * pinning the inode in place so i_lock was unnecessary. The + * only way for this check to fail is if the inode was + * truncated in parallel so warn for now if this happens. + * + * We are not calling into get_futex_key_refs() in file-backed + * cases, therefore a successful atomic_inc return below will + * guarantee that get_futex_key() will still imply smp_mb(); (B). + */ + if (WARN_ON_ONCE(!atomic_inc_not_zero(&inode->i_count))) { + rcu_read_unlock(); + put_page(page); + + goto again; + } + + /* Should be impossible but lets be paranoid for now */ + if (WARN_ON_ONCE(inode->i_mapping != mapping)) { + err = -EFAULT; + rcu_read_unlock(); + iput(inode); + + goto out; + } + key->both.offset |= FUT_OFF_INODE; /* inode-based key */ - key->shared.inode = mapping->host; + key->shared.inode = inode; key->shared.pgoff = basepage_index(page); + rcu_read_unlock(); } - get_futex_key_refs(key); /* implies MB (B) */ - out: - unlock_page(page); put_page(page); return err; } @@ -1191,7 +1274,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this, if (pi_state->owner != current) return -EINVAL; - raw_spin_lock(&pi_state->pi_mutex.wait_lock); + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); new_owner = rt_mutex_next_owner(&pi_state->pi_mutex); /* @@ -1217,22 +1300,22 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this, else if (curval != uval) ret = -EINVAL; if (ret) { - raw_spin_unlock(&pi_state->pi_mutex.wait_lock); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); return ret; } - raw_spin_lock_irq(&pi_state->owner->pi_lock); + raw_spin_lock(&pi_state->owner->pi_lock); WARN_ON(list_empty(&pi_state->list)); list_del_init(&pi_state->list); - raw_spin_unlock_irq(&pi_state->owner->pi_lock); + raw_spin_unlock(&pi_state->owner->pi_lock); - raw_spin_lock_irq(&new_owner->pi_lock); + raw_spin_lock(&new_owner->pi_lock); WARN_ON(!list_empty(&pi_state->list)); list_add(&pi_state->list, &new_owner->pi_state_list); pi_state->owner = new_owner; - raw_spin_unlock_irq(&new_owner->pi_lock); + raw_spin_unlock(&new_owner->pi_lock); - raw_spin_unlock(&pi_state->pi_mutex.wait_lock); + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); @@ -1864,7 +1947,7 @@ static inline struct futex_hash_bucket *queue_lock(struct futex_q *q) q->lock_ptr = &hb->lock; - spin_lock(&hb->lock); /* implies MB (A) */ + spin_lock(&hb->lock); /* implies smp_mb(); (A) */ return hb; } @@ -1927,8 +2010,12 @@ static int unqueue_me(struct futex_q *q) /* In the common case we don't take the spinlock, which is nice. */ retry: - lock_ptr = q->lock_ptr; - barrier(); + /* + * q->lock_ptr can change between this read and the following spin_lock. + * Use READ_ONCE to forbid the compiler from reloading q->lock_ptr and + * optimizing lock_ptr out of the logic below. + */ + lock_ptr = READ_ONCE(q->lock_ptr); if (lock_ptr != NULL) { spin_lock(lock_ptr); /* @@ -2127,11 +2214,11 @@ static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked) * we returned due to timeout or signal without taking the * rt_mutex. Too late. */ - raw_spin_lock(&q->pi_state->pi_mutex.wait_lock); + raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock); owner = rt_mutex_owner(&q->pi_state->pi_mutex); if (!owner) owner = rt_mutex_next_owner(&q->pi_state->pi_mutex); - raw_spin_unlock(&q->pi_state->pi_mutex.wait_lock); + raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock); ret = fixup_pi_state_owner(uaddr, q, owner); goto out; } diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index a302cf9a2126..57bff7857e87 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -138,7 +138,8 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) unsigned int flags = 0, irq = desc->irq_data.irq; struct irqaction *action = desc->action; - do { + /* action might have become NULL since we dropped the lock */ + while (action) { irqreturn_t res; trace_irq_handler_entry(irq, action); @@ -173,7 +174,7 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc) retval |= res; action = action->next; - } while (action); + } add_interrupt_randomness(irq, flags); diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 6e655f7acd3b..3e56d2f03e24 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -575,10 +575,15 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) unsigned int type = IRQ_TYPE_NONE; int virq; - if (fwspec->fwnode) - domain = irq_find_matching_fwnode(fwspec->fwnode, DOMAIN_BUS_ANY); - else + if (fwspec->fwnode) { + domain = irq_find_matching_fwnode(fwspec->fwnode, + DOMAIN_BUS_WIRED); + if (!domain) + domain = irq_find_matching_fwnode(fwspec->fwnode, + DOMAIN_BUS_ANY); + } else { domain = irq_default_domain; + } if (!domain) { pr_warn("no irq domain found for %s !\n", diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index 8dc659144869..8d34308ea449 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -66,13 +66,15 @@ struct resource crashk_res = { .name = "Crash kernel", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, + .desc = IORES_DESC_CRASH_KERNEL }; struct resource crashk_low_res = { .name = "Crash kernel", .start = 0, .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_MEM + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, + .desc = IORES_DESC_CRASH_KERNEL }; int kexec_should_crash(struct task_struct *p) @@ -959,7 +961,7 @@ int crash_shrink_memory(unsigned long new_size) ram_res->start = end; ram_res->end = crashk_res.end; - ram_res->flags = IORESOURCE_BUSY | IORESOURCE_MEM; + ram_res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM; ram_res->name = "System RAM"; crashk_res.end = end - 1; diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 007b791f676d..56b18eb1f001 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -524,10 +524,10 @@ int kexec_add_buffer(struct kimage *image, char *buffer, unsigned long bufsz, /* Walk the RAM ranges and allocate a suitable range for the buffer */ if (image->type == KEXEC_TYPE_CRASH) - ret = walk_iomem_res("Crash kernel", - IORESOURCE_MEM | IORESOURCE_BUSY, - crashk_res.start, crashk_res.end, kbuf, - locate_mem_hole_callback); + ret = walk_iomem_res_desc(crashk_res.desc, + IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY, + crashk_res.start, crashk_res.end, kbuf, + locate_mem_hole_callback); else ret = walk_system_ram_res(0, -1, kbuf, locate_mem_hole_callback); diff --git a/kernel/latencytop.c b/kernel/latencytop.c index a02812743a7e..b5c30d9f46c5 100644 --- a/kernel/latencytop.c +++ b/kernel/latencytop.c @@ -47,12 +47,12 @@ * of times) */ -#include <linux/latencytop.h> #include <linux/kallsyms.h> #include <linux/seq_file.h> #include <linux/notifier.h> #include <linux/spinlock.h> #include <linux/proc_fs.h> +#include <linux/latencytop.h> #include <linux/export.h> #include <linux/sched.h> #include <linux/list.h> @@ -289,4 +289,16 @@ static int __init init_lstats_procfs(void) proc_create("latency_stats", 0644, NULL, &lstats_fops); return 0; } + +int sysctl_latencytop(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int err; + + err = proc_dointvec(table, write, buffer, lenp, ppos); + if (latencytop_enabled) + force_schedstat_enabled(); + + return err; +} device_initcall(init_lstats_procfs); diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 60ace56618f6..f894a2cd9b2a 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -123,8 +123,6 @@ static inline int debug_locks_off_graph_unlock(void) return ret; } -static int lockdep_initialized; - unsigned long nr_list_entries; static struct lock_list list_entries[MAX_LOCKDEP_ENTRIES]; @@ -292,7 +290,7 @@ LIST_HEAD(all_lock_classes); #define __classhashfn(key) hash_long((unsigned long)key, CLASSHASH_BITS) #define classhashentry(key) (classhash_table + __classhashfn((key))) -static struct list_head classhash_table[CLASSHASH_SIZE]; +static struct hlist_head classhash_table[CLASSHASH_SIZE]; /* * We put the lock dependency chains into a hash-table as well, to cache @@ -303,7 +301,7 @@ static struct list_head classhash_table[CLASSHASH_SIZE]; #define __chainhashfn(chain) hash_long(chain, CHAINHASH_BITS) #define chainhashentry(chain) (chainhash_table + __chainhashfn((chain))) -static struct list_head chainhash_table[CHAINHASH_SIZE]; +static struct hlist_head chainhash_table[CHAINHASH_SIZE]; /* * The hash key of the lock dependency chains is a hash itself too: @@ -434,19 +432,6 @@ unsigned int max_lockdep_depth; #ifdef CONFIG_DEBUG_LOCKDEP /* - * We cannot printk in early bootup code. Not even early_printk() - * might work. So we mark any initialization errors and printk - * about it later on, in lockdep_info(). - */ -static int lockdep_init_error; -static const char *lock_init_error; -static unsigned long lockdep_init_trace_data[20]; -static struct stack_trace lockdep_init_trace = { - .max_entries = ARRAY_SIZE(lockdep_init_trace_data), - .entries = lockdep_init_trace_data, -}; - -/* * Various lockdep statistics: */ DEFINE_PER_CPU(struct lockdep_stats, lockdep_stats); @@ -666,23 +651,9 @@ static inline struct lock_class * look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) { struct lockdep_subclass_key *key; - struct list_head *hash_head; + struct hlist_head *hash_head; struct lock_class *class; -#ifdef CONFIG_DEBUG_LOCKDEP - /* - * If the architecture calls into lockdep before initializing - * the hashes then we'll warn about it later. (we cannot printk - * right now) - */ - if (unlikely(!lockdep_initialized)) { - lockdep_init(); - lockdep_init_error = 1; - lock_init_error = lock->name; - save_stack_trace(&lockdep_init_trace); - } -#endif - if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) { debug_locks_off(); printk(KERN_ERR @@ -719,7 +690,7 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return NULL; - list_for_each_entry_rcu(class, hash_head, hash_entry) { + hlist_for_each_entry_rcu(class, hash_head, hash_entry) { if (class->key == key) { /* * Huh! same key, different name? Did someone trample @@ -742,7 +713,7 @@ static inline struct lock_class * register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) { struct lockdep_subclass_key *key; - struct list_head *hash_head; + struct hlist_head *hash_head; struct lock_class *class; DEBUG_LOCKS_WARN_ON(!irqs_disabled()); @@ -774,7 +745,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) * We have to do the hash-walk again, to avoid races * with another CPU: */ - list_for_each_entry_rcu(class, hash_head, hash_entry) { + hlist_for_each_entry_rcu(class, hash_head, hash_entry) { if (class->key == key) goto out_unlock_set; } @@ -805,7 +776,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) * We use RCU's safe list-add method to make * parallel walking of the hash-list safe: */ - list_add_tail_rcu(&class->hash_entry, hash_head); + hlist_add_head_rcu(&class->hash_entry, hash_head); /* * Add it to the global list of classes: */ @@ -1822,7 +1793,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next, */ static int check_prev_add(struct task_struct *curr, struct held_lock *prev, - struct held_lock *next, int distance, int trylock_loop) + struct held_lock *next, int distance, int *stack_saved) { struct lock_list *entry; int ret; @@ -1883,8 +1854,11 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, } } - if (!trylock_loop && !save_trace(&trace)) - return 0; + if (!*stack_saved) { + if (!save_trace(&trace)) + return 0; + *stack_saved = 1; + } /* * Ok, all validations passed, add the new lock @@ -1907,6 +1881,8 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev, * Debugging printouts: */ if (verbose(hlock_class(prev)) || verbose(hlock_class(next))) { + /* We drop graph lock, so another thread can overwrite trace. */ + *stack_saved = 0; graph_unlock(); printk("\n new dependency: "); print_lock_name(hlock_class(prev)); @@ -1929,7 +1905,7 @@ static int check_prevs_add(struct task_struct *curr, struct held_lock *next) { int depth = curr->lockdep_depth; - int trylock_loop = 0; + int stack_saved = 0; struct held_lock *hlock; /* @@ -1956,7 +1932,7 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next) */ if (hlock->read != 2 && hlock->check) { if (!check_prev_add(curr, hlock, next, - distance, trylock_loop)) + distance, &stack_saved)) return 0; /* * Stop after the first non-trylock entry, @@ -1979,7 +1955,6 @@ check_prevs_add(struct task_struct *curr, struct held_lock *next) if (curr->held_locks[depth].irq_context != curr->held_locks[depth-1].irq_context) break; - trylock_loop = 1; } return 1; out_bug: @@ -2007,6 +1982,53 @@ struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i) } /* + * Returns the index of the first held_lock of the current chain + */ +static inline int get_first_held_lock(struct task_struct *curr, + struct held_lock *hlock) +{ + int i; + struct held_lock *hlock_curr; + + for (i = curr->lockdep_depth - 1; i >= 0; i--) { + hlock_curr = curr->held_locks + i; + if (hlock_curr->irq_context != hlock->irq_context) + break; + + } + + return ++i; +} + +/* + * Checks whether the chain and the current held locks are consistent + * in depth and also in content. If they are not it most likely means + * that there was a collision during the calculation of the chain_key. + * Returns: 0 not passed, 1 passed + */ +static int check_no_collision(struct task_struct *curr, + struct held_lock *hlock, + struct lock_chain *chain) +{ +#ifdef CONFIG_DEBUG_LOCKDEP + int i, j, id; + + i = get_first_held_lock(curr, hlock); + + if (DEBUG_LOCKS_WARN_ON(chain->depth != curr->lockdep_depth - (i - 1))) + return 0; + + for (j = 0; j < chain->depth - 1; j++, i++) { + id = curr->held_locks[i].class_idx - 1; + + if (DEBUG_LOCKS_WARN_ON(chain_hlocks[chain->base + j] != id)) + return 0; + } +#endif + return 1; +} + +/* * Look up a dependency chain. If the key is not present yet then * add it and return 1 - in this case the new dependency chain is * validated. If the key is already hashed, return 0. @@ -2017,9 +2039,8 @@ static inline int lookup_chain_cache(struct task_struct *curr, u64 chain_key) { struct lock_class *class = hlock_class(hlock); - struct list_head *hash_head = chainhashentry(chain_key); + struct hlist_head *hash_head = chainhashentry(chain_key); struct lock_chain *chain; - struct held_lock *hlock_curr; int i, j; /* @@ -2033,10 +2054,13 @@ static inline int lookup_chain_cache(struct task_struct *curr, * We can walk it lock-free, because entries only get added * to the hash: */ - list_for_each_entry_rcu(chain, hash_head, entry) { + hlist_for_each_entry_rcu(chain, hash_head, entry) { if (chain->chain_key == chain_key) { cache_hit: debug_atomic_inc(chain_lookup_hits); + if (!check_no_collision(curr, hlock, chain)) + return 0; + if (very_verbose(class)) printk("\nhash chain already cached, key: " "%016Lx tail class: [%p] %s\n", @@ -2057,7 +2081,7 @@ cache_hit: /* * We have to walk the chain again locked - to avoid duplicates: */ - list_for_each_entry(chain, hash_head, entry) { + hlist_for_each_entry(chain, hash_head, entry) { if (chain->chain_key == chain_key) { graph_unlock(); goto cache_hit; @@ -2074,13 +2098,7 @@ cache_hit: chain = lock_chains + nr_lock_chains++; chain->chain_key = chain_key; chain->irq_context = hlock->irq_context; - /* Find the first held_lock of current chain */ - for (i = curr->lockdep_depth - 1; i >= 0; i--) { - hlock_curr = curr->held_locks + i; - if (hlock_curr->irq_context != hlock->irq_context) - break; - } - i++; + i = get_first_held_lock(curr, hlock); chain->depth = curr->lockdep_depth + 1 - i; if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) { chain->base = nr_chain_hlocks; @@ -2091,7 +2109,7 @@ cache_hit: } chain_hlocks[chain->base + j] = class - lock_classes; } - list_add_tail_rcu(&chain->entry, hash_head); + hlist_add_head_rcu(&chain->entry, hash_head); debug_atomic_inc(chain_lookup_misses); inc_chains(); @@ -2168,7 +2186,7 @@ static void check_chain_key(struct task_struct *curr) { #ifdef CONFIG_DEBUG_LOCKDEP struct held_lock *hlock, *prev_hlock = NULL; - unsigned int i, id; + unsigned int i; u64 chain_key = 0; for (i = 0; i < curr->lockdep_depth; i++) { @@ -2185,17 +2203,16 @@ static void check_chain_key(struct task_struct *curr) (unsigned long long)hlock->prev_chain_key); return; } - id = hlock->class_idx - 1; /* * Whoops ran out of static storage again? */ - if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) + if (DEBUG_LOCKS_WARN_ON(hlock->class_idx > MAX_LOCKDEP_KEYS)) return; if (prev_hlock && (prev_hlock->irq_context != hlock->irq_context)) chain_key = 0; - chain_key = iterate_chain_key(chain_key, id); + chain_key = iterate_chain_key(chain_key, hlock->class_idx); prev_hlock = hlock; } if (chain_key != curr->curr_chain_key) { @@ -3073,7 +3090,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, struct task_struct *curr = current; struct lock_class *class = NULL; struct held_lock *hlock; - unsigned int depth, id; + unsigned int depth; int chain_head = 0; int class_idx; u64 chain_key; @@ -3176,11 +3193,10 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, * The 'key ID' is what is the most compact key value to drive * the hash, not class->key. */ - id = class - lock_classes; /* * Whoops, we did it again.. ran straight out of our static allocation. */ - if (DEBUG_LOCKS_WARN_ON(id >= MAX_LOCKDEP_KEYS)) + if (DEBUG_LOCKS_WARN_ON(class_idx > MAX_LOCKDEP_KEYS)) return 0; chain_key = curr->curr_chain_key; @@ -3198,7 +3214,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass, chain_key = 0; chain_head = 1; } - chain_key = iterate_chain_key(chain_key, id); + chain_key = iterate_chain_key(chain_key, class_idx); if (nest_lock && !__lock_is_held(nest_lock)) return print_lock_nested_lock_not_held(curr, hlock, ip); @@ -3875,7 +3891,7 @@ void lockdep_reset(void) nr_process_chains = 0; debug_locks = 1; for (i = 0; i < CHAINHASH_SIZE; i++) - INIT_LIST_HEAD(chainhash_table + i); + INIT_HLIST_HEAD(chainhash_table + i); raw_local_irq_restore(flags); } @@ -3894,7 +3910,7 @@ static void zap_class(struct lock_class *class) /* * Unhash the class and remove it from the all_lock_classes list: */ - list_del_rcu(&class->hash_entry); + hlist_del_rcu(&class->hash_entry); list_del_rcu(&class->lock_entry); RCU_INIT_POINTER(class->key, NULL); @@ -3917,7 +3933,7 @@ static inline int within(const void *addr, void *start, unsigned long size) void lockdep_free_key_range(void *start, unsigned long size) { struct lock_class *class; - struct list_head *head; + struct hlist_head *head; unsigned long flags; int i; int locked; @@ -3930,9 +3946,7 @@ void lockdep_free_key_range(void *start, unsigned long size) */ for (i = 0; i < CLASSHASH_SIZE; i++) { head = classhash_table + i; - if (list_empty(head)) - continue; - list_for_each_entry_rcu(class, head, hash_entry) { + hlist_for_each_entry_rcu(class, head, hash_entry) { if (within(class->key, start, size)) zap_class(class); else if (within(class->name, start, size)) @@ -3962,7 +3976,7 @@ void lockdep_free_key_range(void *start, unsigned long size) void lockdep_reset_lock(struct lockdep_map *lock) { struct lock_class *class; - struct list_head *head; + struct hlist_head *head; unsigned long flags; int i, j; int locked; @@ -3987,9 +4001,7 @@ void lockdep_reset_lock(struct lockdep_map *lock) locked = graph_lock(); for (i = 0; i < CLASSHASH_SIZE; i++) { head = classhash_table + i; - if (list_empty(head)) - continue; - list_for_each_entry_rcu(class, head, hash_entry) { + hlist_for_each_entry_rcu(class, head, hash_entry) { int match = 0; for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++) @@ -4013,28 +4025,6 @@ out_restore: raw_local_irq_restore(flags); } -void lockdep_init(void) -{ - int i; - - /* - * Some architectures have their own start_kernel() - * code which calls lockdep_init(), while we also - * call lockdep_init() from the start_kernel() itself, - * and we want to initialize the hashes only once: - */ - if (lockdep_initialized) - return; - - for (i = 0; i < CLASSHASH_SIZE; i++) - INIT_LIST_HEAD(classhash_table + i); - - for (i = 0; i < CHAINHASH_SIZE; i++) - INIT_LIST_HEAD(chainhash_table + i); - - lockdep_initialized = 1; -} - void __init lockdep_info(void) { printk("Lock dependency validator: Copyright (c) 2006 Red Hat, Inc., Ingo Molnar\n"); @@ -4061,14 +4051,6 @@ void __init lockdep_info(void) printk(" per task-struct memory footprint: %lu bytes\n", sizeof(struct held_lock) * MAX_LOCK_DEPTH); - -#ifdef CONFIG_DEBUG_LOCKDEP - if (lockdep_init_error) { - printk("WARNING: lockdep init error: lock '%s' was acquired before lockdep_init().\n", lock_init_error); - printk("Call stack leading to lockdep invocation was:\n"); - print_stack_trace(&lockdep_init_trace, 0); - } -#endif } static void diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h index 5b9102a47ea5..c835270f0c2f 100644 --- a/kernel/locking/mcs_spinlock.h +++ b/kernel/locking/mcs_spinlock.h @@ -67,7 +67,13 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node) node->locked = 0; node->next = NULL; - prev = xchg_acquire(lock, node); + /* + * We rely on the full barrier with global transitivity implied by the + * below xchg() to order the initialization stores above against any + * observation of @node. And to provide the ACQUIRE ordering associated + * with a LOCK primitive. + */ + prev = xchg(lock, node); if (likely(prev == NULL)) { /* * Lock acquired, don't need to set node->locked to 1. Threads diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c index 0551c219c40e..e364b424b019 100644 --- a/kernel/locking/mutex.c +++ b/kernel/locking/mutex.c @@ -716,6 +716,7 @@ static inline void __mutex_unlock_common_slowpath(struct mutex *lock, int nested) { unsigned long flags; + WAKE_Q(wake_q); /* * As a performance measurement, release the lock before doing other @@ -743,11 +744,11 @@ __mutex_unlock_common_slowpath(struct mutex *lock, int nested) struct mutex_waiter, list); debug_mutex_wake_waiter(lock, waiter); - - wake_up_process(waiter->task); + wake_q_add(&wake_q, waiter->task); } spin_unlock_mutex(&lock->wait_lock, flags); + wake_up_q(&wake_q); } /* diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c index 393d1874b9e0..ce2f75e32ae1 100644 --- a/kernel/locking/qspinlock.c +++ b/kernel/locking/qspinlock.c @@ -358,8 +358,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) * sequentiality; this is because not all clear_pending_set_locked() * implementations imply full barriers. */ - while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_MASK) - cpu_relax(); + smp_cond_acquire(!(atomic_read(&lock->val) & _Q_LOCKED_MASK)); /* * take ownership and clear the pending bit. @@ -435,7 +434,7 @@ queue: * * The PV pv_wait_head_or_lock function, if active, will acquire * the lock and return a non-zero value. So we have to skip the - * smp_load_acquire() call. As the next PV queue head hasn't been + * smp_cond_acquire() call. As the next PV queue head hasn't been * designated yet, there is no way for the locked value to become * _Q_SLOW_VAL. So both the set_locked() and the * atomic_cmpxchg_relaxed() calls will be safe. @@ -466,7 +465,7 @@ locked: break; } /* - * The smp_load_acquire() call above has provided the necessary + * The smp_cond_acquire() call above has provided the necessary * acquire semantics required for locking. At most two * iterations of this loop may be ran. */ diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 87bb235c3448..21ede57f68b3 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -55,6 +55,11 @@ struct pv_node { }; /* + * Include queued spinlock statistics code + */ +#include "qspinlock_stat.h" + +/* * By replacing the regular queued_spin_trylock() with the function below, * it will be called once when a lock waiter enter the PV slowpath before * being queued. By allowing one lock stealing attempt here when the pending @@ -65,9 +70,11 @@ 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); - return !(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; } /* @@ -138,11 +145,6 @@ static __always_inline int trylock_clear_pending(struct qspinlock *lock) #endif /* _Q_PENDING_BITS == 8 */ /* - * Include queued spinlock statistics code - */ -#include "qspinlock_stat.h" - -/* * Lock and MCS node addresses hash table for fast lookup * * Hashing is done on a per-cacheline basis to minimize the need to access @@ -398,6 +400,11 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node) if (READ_ONCE(pn->state) == vcpu_hashed) lp = (struct qspinlock **)1; + /* + * Tracking # of slowpath locking operations + */ + qstat_inc(qstat_pv_lock_slowpath, true); + for (;; waitcnt++) { /* * Set correct vCPU state to be used by queue node wait-early diff --git a/kernel/locking/qspinlock_stat.h b/kernel/locking/qspinlock_stat.h index 640dcecdd1df..eb2a2c9bc3fc 100644 --- a/kernel/locking/qspinlock_stat.h +++ b/kernel/locking/qspinlock_stat.h @@ -22,6 +22,7 @@ * pv_kick_wake - # of vCPU kicks used for computing pv_latency_wake * pv_latency_kick - average latency (ns) of vCPU kick operation * 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 @@ -45,6 +46,7 @@ enum qlock_stats { qstat_pv_kick_wake, qstat_pv_latency_kick, qstat_pv_latency_wake, + qstat_pv_lock_slowpath, qstat_pv_lock_stealing, qstat_pv_spurious_wakeup, qstat_pv_wait_again, @@ -70,6 +72,7 @@ static const char * const qstat_names[qstat_num + 1] = { [qstat_pv_spurious_wakeup] = "pv_spurious_wakeup", [qstat_pv_latency_kick] = "pv_latency_kick", [qstat_pv_latency_wake] = "pv_latency_wake", + [qstat_pv_lock_slowpath] = "pv_lock_slowpath", [qstat_pv_lock_stealing] = "pv_lock_stealing", [qstat_pv_wait_again] = "pv_wait_again", [qstat_pv_wait_early] = "pv_wait_early", @@ -279,19 +282,6 @@ static inline void __pv_wait(u8 *ptr, u8 val) #define pv_kick(c) __pv_kick(c) #define pv_wait(p, v) __pv_wait(p, v) -/* - * PV unfair trylock count tracking function - */ -static inline int qstat_spin_steal_lock(struct qspinlock *lock) -{ - int ret = pv_queued_spin_steal_lock(lock); - - qstat_inc(qstat_pv_lock_stealing, ret); - return ret; -} -#undef queued_spin_trylock -#define queued_spin_trylock(l) qstat_spin_steal_lock(l) - #else /* CONFIG_QUEUED_LOCK_STAT */ static inline void qstat_inc(enum qlock_stats stat, bool cond) { } diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 8251e75dd9c0..3e746607abe5 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -99,13 +99,14 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) * 2) Drop lock->wait_lock * 3) Try to unlock the lock with cmpxchg */ -static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) +static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, + unsigned long flags) __releases(lock->wait_lock) { struct task_struct *owner = rt_mutex_owner(lock); clear_rt_mutex_waiters(lock); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); /* * If a new waiter comes in between the unlock and the cmpxchg * we have two situations: @@ -147,11 +148,12 @@ static inline void mark_rt_mutex_waiters(struct rt_mutex *lock) /* * Simple slow path only version: lock->owner is protected by lock->wait_lock. */ -static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock) +static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock, + unsigned long flags) __releases(lock->wait_lock) { lock->owner = NULL; - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); return true; } #endif @@ -433,7 +435,6 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, int ret = 0, depth = 0; struct rt_mutex *lock; bool detect_deadlock; - unsigned long flags; bool requeue = true; detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk); @@ -476,7 +477,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, /* * [1] Task cannot go away as we did a get_task() before ! */ - raw_spin_lock_irqsave(&task->pi_lock, flags); + raw_spin_lock_irq(&task->pi_lock); /* * [2] Get the waiter on which @task is blocked on. @@ -560,7 +561,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * operations. */ if (!raw_spin_trylock(&lock->wait_lock)) { - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock_irq(&task->pi_lock); cpu_relax(); goto retry; } @@ -591,7 +592,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, /* * No requeue[7] here. Just release @task [8] */ - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock(&task->pi_lock); put_task_struct(task); /* @@ -599,14 +600,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, * If there is no owner of the lock, end of chain. */ if (!rt_mutex_owner(lock)) { - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); return 0; } /* [10] Grab the next task, i.e. owner of @lock */ task = rt_mutex_owner(lock); get_task_struct(task); - raw_spin_lock_irqsave(&task->pi_lock, flags); + raw_spin_lock(&task->pi_lock); /* * No requeue [11] here. We just do deadlock detection. @@ -621,8 +622,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, top_waiter = rt_mutex_top_waiter(lock); /* [13] Drop locks */ - raw_spin_unlock_irqrestore(&task->pi_lock, flags); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock(&task->pi_lock); + raw_spin_unlock_irq(&lock->wait_lock); /* If owner is not blocked, end of chain. */ if (!next_lock) @@ -643,7 +644,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, rt_mutex_enqueue(lock, waiter); /* [8] Release the task */ - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock(&task->pi_lock); put_task_struct(task); /* @@ -661,14 +662,14 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, */ if (prerequeue_top_waiter != rt_mutex_top_waiter(lock)) wake_up_process(rt_mutex_top_waiter(lock)->task); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); return 0; } /* [10] Grab the next task, i.e. the owner of @lock */ task = rt_mutex_owner(lock); get_task_struct(task); - raw_spin_lock_irqsave(&task->pi_lock, flags); + raw_spin_lock(&task->pi_lock); /* [11] requeue the pi waiters if necessary */ if (waiter == rt_mutex_top_waiter(lock)) { @@ -722,8 +723,8 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, top_waiter = rt_mutex_top_waiter(lock); /* [13] Drop the locks */ - raw_spin_unlock_irqrestore(&task->pi_lock, flags); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock(&task->pi_lock); + raw_spin_unlock_irq(&lock->wait_lock); /* * Make the actual exit decisions [12], based on the stored @@ -746,7 +747,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, goto again; out_unlock_pi: - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock_irq(&task->pi_lock); out_put_task: put_task_struct(task); @@ -756,7 +757,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, /* * Try to take an rt-mutex * - * Must be called with lock->wait_lock held. + * Must be called with lock->wait_lock held and interrupts disabled * * @lock: The lock to be acquired. * @task: The task which wants to acquire the lock @@ -766,8 +767,6 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task, static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, struct rt_mutex_waiter *waiter) { - unsigned long flags; - /* * Before testing whether we can acquire @lock, we set the * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all @@ -852,7 +851,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, * case, but conditionals are more expensive than a redundant * store. */ - raw_spin_lock_irqsave(&task->pi_lock, flags); + raw_spin_lock(&task->pi_lock); task->pi_blocked_on = NULL; /* * Finish the lock acquisition. @task is the new owner. If @@ -861,7 +860,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, */ if (rt_mutex_has_waiters(lock)) rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock)); - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock(&task->pi_lock); takeit: /* We got the lock. */ @@ -883,7 +882,7 @@ takeit: * * Prepare waiter and propagate pi chain * - * This must be called with lock->wait_lock held. + * This must be called with lock->wait_lock held and interrupts disabled */ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, @@ -894,7 +893,6 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, struct rt_mutex_waiter *top_waiter = waiter; struct rt_mutex *next_lock; int chain_walk = 0, res; - unsigned long flags; /* * Early deadlock detection. We really don't want the task to @@ -908,7 +906,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, if (owner == task) return -EDEADLK; - raw_spin_lock_irqsave(&task->pi_lock, flags); + raw_spin_lock(&task->pi_lock); __rt_mutex_adjust_prio(task); waiter->task = task; waiter->lock = lock; @@ -921,12 +919,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, task->pi_blocked_on = waiter; - raw_spin_unlock_irqrestore(&task->pi_lock, flags); + raw_spin_unlock(&task->pi_lock); if (!owner) return 0; - raw_spin_lock_irqsave(&owner->pi_lock, flags); + raw_spin_lock(&owner->pi_lock); if (waiter == rt_mutex_top_waiter(lock)) { rt_mutex_dequeue_pi(owner, top_waiter); rt_mutex_enqueue_pi(owner, waiter); @@ -941,7 +939,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, /* Store the lock on which owner is blocked or NULL */ next_lock = task_blocked_on_lock(owner); - raw_spin_unlock_irqrestore(&owner->pi_lock, flags); + raw_spin_unlock(&owner->pi_lock); /* * Even if full deadlock detection is on, if the owner is not * blocked itself, we can avoid finding this out in the chain @@ -957,12 +955,12 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, */ get_task_struct(owner); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); res = rt_mutex_adjust_prio_chain(owner, chwalk, lock, next_lock, waiter, task); - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irq(&lock->wait_lock); return res; } @@ -971,15 +969,14 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock, * Remove the top waiter from the current tasks pi waiter tree and * queue it up. * - * Called with lock->wait_lock held. + * Called with lock->wait_lock held and interrupts disabled. */ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, struct rt_mutex *lock) { struct rt_mutex_waiter *waiter; - unsigned long flags; - raw_spin_lock_irqsave(¤t->pi_lock, flags); + raw_spin_lock(¤t->pi_lock); waiter = rt_mutex_top_waiter(lock); @@ -1001,7 +998,7 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, */ lock->owner = (void *) RT_MUTEX_HAS_WAITERS; - raw_spin_unlock_irqrestore(¤t->pi_lock, flags); + raw_spin_unlock(¤t->pi_lock); wake_q_add(wake_q, waiter->task); } @@ -1009,7 +1006,7 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, /* * Remove a waiter from a lock and give up * - * Must be called with lock->wait_lock held and + * Must be called with lock->wait_lock held and interrupts disabled. I must * have just failed to try_to_take_rt_mutex(). */ static void remove_waiter(struct rt_mutex *lock, @@ -1018,12 +1015,11 @@ static void remove_waiter(struct rt_mutex *lock, bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); struct task_struct *owner = rt_mutex_owner(lock); struct rt_mutex *next_lock; - unsigned long flags; - raw_spin_lock_irqsave(¤t->pi_lock, flags); + raw_spin_lock(¤t->pi_lock); rt_mutex_dequeue(lock, waiter); current->pi_blocked_on = NULL; - raw_spin_unlock_irqrestore(¤t->pi_lock, flags); + raw_spin_unlock(¤t->pi_lock); /* * Only update priority if the waiter was the highest priority @@ -1032,7 +1028,7 @@ static void remove_waiter(struct rt_mutex *lock, if (!owner || !is_top_waiter) return; - raw_spin_lock_irqsave(&owner->pi_lock, flags); + raw_spin_lock(&owner->pi_lock); rt_mutex_dequeue_pi(owner, waiter); @@ -1044,7 +1040,7 @@ static void remove_waiter(struct rt_mutex *lock, /* Store the lock on which owner is blocked or NULL */ next_lock = task_blocked_on_lock(owner); - raw_spin_unlock_irqrestore(&owner->pi_lock, flags); + raw_spin_unlock(&owner->pi_lock); /* * Don't walk the chain, if the owner task is not blocked @@ -1056,12 +1052,12 @@ static void remove_waiter(struct rt_mutex *lock, /* gets dropped in rt_mutex_adjust_prio_chain()! */ get_task_struct(owner); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock, next_lock, NULL, current); - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irq(&lock->wait_lock); } /* @@ -1097,11 +1093,11 @@ void rt_mutex_adjust_pi(struct task_struct *task) * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop * @lock: the rt_mutex to take * @state: the state the task should block in (TASK_INTERRUPTIBLE - * or TASK_UNINTERRUPTIBLE) + * or TASK_UNINTERRUPTIBLE) * @timeout: the pre-initialized and started timer, or NULL for none * @waiter: the pre-initialized rt_mutex_waiter * - * lock->wait_lock must be held by the caller. + * Must be called with lock->wait_lock held and interrupts disabled */ static int __sched __rt_mutex_slowlock(struct rt_mutex *lock, int state, @@ -1129,13 +1125,13 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state, break; } - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); debug_rt_mutex_print_deadlock(waiter); schedule(); - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irq(&lock->wait_lock); set_current_state(state); } @@ -1172,17 +1168,26 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, enum rtmutex_chainwalk chwalk) { struct rt_mutex_waiter waiter; + unsigned long flags; int ret = 0; debug_rt_mutex_init_waiter(&waiter); RB_CLEAR_NODE(&waiter.pi_tree_entry); RB_CLEAR_NODE(&waiter.tree_entry); - raw_spin_lock(&lock->wait_lock); + /* + * Technically we could use raw_spin_[un]lock_irq() here, but this can + * be called in early boot if the cmpxchg() fast path is disabled + * (debug, no architecture support). In this case we will acquire the + * rtmutex with lock->wait_lock held. But we cannot unconditionally + * enable interrupts in that early boot case. So we need to use the + * irqsave/restore variants. + */ + raw_spin_lock_irqsave(&lock->wait_lock, flags); /* Try to acquire the lock again: */ if (try_to_take_rt_mutex(lock, current, NULL)) { - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); return 0; } @@ -1211,7 +1216,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, */ fixup_rt_mutex_waiters(lock); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); /* Remove pending timer: */ if (unlikely(timeout)) @@ -1227,6 +1232,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, */ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) { + unsigned long flags; int ret; /* @@ -1238,10 +1244,10 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) return 0; /* - * The mutex has currently no owner. Lock the wait lock and - * try to acquire the lock. + * The mutex has currently no owner. Lock the wait lock and try to + * acquire the lock. We use irqsave here to support early boot calls. */ - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irqsave(&lock->wait_lock, flags); ret = try_to_take_rt_mutex(lock, current, NULL); @@ -1251,7 +1257,7 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) */ fixup_rt_mutex_waiters(lock); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); return ret; } @@ -1263,7 +1269,10 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock) static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, struct wake_q_head *wake_q) { - raw_spin_lock(&lock->wait_lock); + unsigned long flags; + + /* irqsave required to support early boot calls */ + raw_spin_lock_irqsave(&lock->wait_lock, flags); debug_rt_mutex_unlock(lock); @@ -1302,10 +1311,10 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, */ while (!rt_mutex_has_waiters(lock)) { /* Drops lock->wait_lock ! */ - if (unlock_rt_mutex_safe(lock) == true) + if (unlock_rt_mutex_safe(lock, flags) == true) return false; /* Relock the rtmutex and try again */ - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irqsave(&lock->wait_lock, flags); } /* @@ -1316,7 +1325,7 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, */ mark_wakeup_next_waiter(wake_q, lock); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); /* check PI boosting */ return true; @@ -1596,10 +1605,10 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, { int ret; - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irq(&lock->wait_lock); if (try_to_take_rt_mutex(lock, task, NULL)) { - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); return 1; } @@ -1620,7 +1629,7 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock, if (unlikely(ret)) remove_waiter(lock, waiter); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); debug_rt_mutex_print_deadlock(waiter); @@ -1668,7 +1677,7 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, { int ret; - raw_spin_lock(&lock->wait_lock); + raw_spin_lock_irq(&lock->wait_lock); set_current_state(TASK_INTERRUPTIBLE); @@ -1684,7 +1693,7 @@ int rt_mutex_finish_proxy_lock(struct rt_mutex *lock, */ fixup_rt_mutex_waiters(lock); - raw_spin_unlock(&lock->wait_lock); + raw_spin_unlock_irq(&lock->wait_lock); return ret; } diff --git a/kernel/memremap.c b/kernel/memremap.c index e517a16cb426..fb9b88787ebc 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -29,10 +29,10 @@ __weak void __iomem *ioremap_cache(resource_size_t offset, unsigned long size) static void *try_ram_remap(resource_size_t offset, size_t size) { - struct page *page = pfn_to_page(offset >> PAGE_SHIFT); + unsigned long pfn = PHYS_PFN(offset); /* In the simple case just return the existing linear address */ - if (!PageHighMem(page)) + if (pfn_valid(pfn) && !PageHighMem(pfn_to_page(pfn))) return __va(offset); return NULL; /* fallback to ioremap_cache */ } @@ -47,7 +47,7 @@ static void *try_ram_remap(resource_size_t offset, size_t size) * being mapped does not have i/o side effects and the __iomem * annotation is not applicable. * - * MEMREMAP_WB - matches the default mapping for "System RAM" on + * MEMREMAP_WB - matches the default mapping for System RAM on * the architecture. This is usually a read-allocate write-back cache. * Morever, if MEMREMAP_WB is specified and the requested remap region is RAM * memremap() will bypass establishing a new mapping and instead return @@ -56,11 +56,12 @@ static void *try_ram_remap(resource_size_t offset, size_t size) * MEMREMAP_WT - establish a mapping whereby writes either bypass the * cache or are written through to memory and never exist in a * cache-dirty state with respect to program visibility. Attempts to - * map "System RAM" with this mapping type will fail. + * map System RAM with this mapping type will fail. */ void *memremap(resource_size_t offset, size_t size, unsigned long flags) { - int is_ram = region_intersects(offset, size, "System RAM"); + int is_ram = region_intersects(offset, size, + IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); void *addr = NULL; if (is_ram == REGION_MIXED) { @@ -76,7 +77,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) * MEMREMAP_WB is special in that it can be satisifed * from the direct map. Some archs depend on the * capability of memremap() to autodetect cases where - * the requested range is potentially in "System RAM" + * the requested range is potentially in System RAM. */ if (is_ram == REGION_INTERSECTS) addr = try_ram_remap(offset, size); @@ -88,7 +89,7 @@ void *memremap(resource_size_t offset, size_t size, unsigned long flags) * If we don't have a mapping yet and more request flags are * pending then we will be attempting to establish a new virtual * address mapping. Enforce that this mapping is not aliasing - * "System RAM" + * System RAM. */ if (!addr && is_ram == REGION_INTERSECTS && flags) { WARN_ONCE(1, "memremap attempted on ram %pa size: %#lx\n", @@ -114,7 +115,7 @@ EXPORT_SYMBOL(memunmap); static void devm_memremap_release(struct device *dev, void *res) { - memunmap(res); + memunmap(*(void **)res); } static int devm_memremap_match(struct device *dev, void *res, void *match_data) @@ -136,8 +137,10 @@ void *devm_memremap(struct device *dev, resource_size_t offset, if (addr) { *ptr = addr; devres_add(dev, ptr); - } else + } else { devres_free(ptr); + return ERR_PTR(-ENXIO); + } return addr; } @@ -150,7 +153,7 @@ void devm_memunmap(struct device *dev, void *addr) } EXPORT_SYMBOL(devm_memunmap); -pfn_t phys_to_pfn_t(dma_addr_t addr, unsigned long flags) +pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags) { return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags); } @@ -183,7 +186,11 @@ EXPORT_SYMBOL(put_zone_device_page); static void pgmap_radix_release(struct resource *res) { - resource_size_t key; + resource_size_t key, align_start, align_size, align_end; + + align_start = res->start & ~(SECTION_SIZE - 1); + align_size = ALIGN(resource_size(res), SECTION_SIZE); + align_end = align_start + align_size - 1; mutex_lock(&pgmap_lock); for (key = res->start; key <= res->end; key += SECTION_SIZE) @@ -226,12 +233,11 @@ static void devm_memremap_pages_release(struct device *dev, void *data) percpu_ref_put(pgmap->ref); } - pgmap_radix_release(res); - /* pages are dead and unused, undo the arch mapping */ align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(resource_size(res), SECTION_SIZE); arch_remove_memory(align_start, align_size); + pgmap_radix_release(res); dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc, "%s: failed to free all reserved pages\n", __func__); } @@ -265,13 +271,17 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys) void *devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, struct vmem_altmap *altmap) { - int is_ram = region_intersects(res->start, resource_size(res), - "System RAM"); - resource_size_t key, align_start, align_size; + resource_size_t key, align_start, align_size, align_end; struct dev_pagemap *pgmap; struct page_map *page_map; + int error, nid, is_ram; unsigned long pfn; - int error, nid; + + align_start = res->start & ~(SECTION_SIZE - 1); + align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) + - align_start; + is_ram = region_intersects(align_start, align_size, + IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE); if (is_ram == REGION_MIXED) { WARN_ONCE(1, "%s attempted on mixed region %pr\n", @@ -309,7 +319,8 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, mutex_lock(&pgmap_lock); error = 0; - for (key = res->start; key <= res->end; key += SECTION_SIZE) { + align_end = align_start + align_size - 1; + for (key = align_start; key <= align_end; key += SECTION_SIZE) { struct dev_pagemap *dup; rcu_read_lock(); @@ -336,8 +347,6 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, if (nid < 0) nid = numa_mem_id(); - align_start = res->start & ~(SECTION_SIZE - 1); - align_size = ALIGN(resource_size(res), SECTION_SIZE); error = arch_add_memory(nid, align_start, align_size, true); if (error) goto err_add_memory; @@ -345,8 +354,13 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, for_each_device_pfn(pfn, page_map) { struct page *page = pfn_to_page(pfn); - /* ZONE_DEVICE pages must never appear on a slab lru */ - list_force_poison(&page->lru); + /* + * ZONE_DEVICE pages union ->lru with a ->pgmap back + * pointer. It is a bug if a ZONE_DEVICE page is ever + * freed or placed on a driver-private list. Seed the + * storage with LIST_POISON* values. + */ + list_del(&page->lru); page->pgmap = pgmap; } devres_add(dev, page_map); diff --git a/kernel/module.c b/kernel/module.c index 8358f4697c0c..794ebe8e878d 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -303,6 +303,9 @@ struct load_info { struct _ddebug *debug; unsigned int num_debug; bool sig_ok; +#ifdef CONFIG_KALLSYMS + unsigned long mod_kallsyms_init_off; +#endif struct { unsigned int sym, str, mod, vers, info, pcpu; } index; @@ -981,6 +984,8 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, mod->exit(); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); + ftrace_release_mod(mod); + async_synchronize_full(); /* Store the name of the last unloaded module for diagnostic purposes */ @@ -2480,10 +2485,21 @@ static void layout_symtab(struct module *mod, struct load_info *info) strsect->sh_flags |= SHF_ALLOC; strsect->sh_entsize = get_offset(mod, &mod->init_layout.size, strsect, info->index.str) | INIT_OFFSET_MASK; - mod->init_layout.size = debug_align(mod->init_layout.size); pr_debug("\t%s\n", info->secstrings + strsect->sh_name); + + /* We'll tack temporary mod_kallsyms on the end. */ + mod->init_layout.size = ALIGN(mod->init_layout.size, + __alignof__(struct mod_kallsyms)); + info->mod_kallsyms_init_off = mod->init_layout.size; + mod->init_layout.size += sizeof(struct mod_kallsyms); + mod->init_layout.size = debug_align(mod->init_layout.size); } +/* + * We use the full symtab and strtab which layout_symtab arranged to + * be appended to the init section. Later we switch to the cut-down + * core-only ones. + */ static void add_kallsyms(struct module *mod, const struct load_info *info) { unsigned int i, ndst; @@ -2492,29 +2508,34 @@ static void add_kallsyms(struct module *mod, const struct load_info *info) char *s; Elf_Shdr *symsec = &info->sechdrs[info->index.sym]; - mod->symtab = (void *)symsec->sh_addr; - mod->num_symtab = symsec->sh_size / sizeof(Elf_Sym); + /* Set up to point into init section. */ + mod->kallsyms = mod->init_layout.base + info->mod_kallsyms_init_off; + + mod->kallsyms->symtab = (void *)symsec->sh_addr; + mod->kallsyms->num_symtab = symsec->sh_size / sizeof(Elf_Sym); /* Make sure we get permanent strtab: don't use info->strtab. */ - mod->strtab = (void *)info->sechdrs[info->index.str].sh_addr; + mod->kallsyms->strtab = (void *)info->sechdrs[info->index.str].sh_addr; /* Set types up while we still have access to sections. */ - for (i = 0; i < mod->num_symtab; i++) - mod->symtab[i].st_info = elf_type(&mod->symtab[i], info); - - mod->core_symtab = dst = mod->core_layout.base + info->symoffs; - mod->core_strtab = s = mod->core_layout.base + info->stroffs; - src = mod->symtab; - for (ndst = i = 0; i < mod->num_symtab; i++) { + for (i = 0; i < mod->kallsyms->num_symtab; i++) + mod->kallsyms->symtab[i].st_info + = elf_type(&mod->kallsyms->symtab[i], info); + + /* Now populate the cut down core kallsyms for after init. */ + mod->core_kallsyms.symtab = dst = mod->core_layout.base + info->symoffs; + mod->core_kallsyms.strtab = s = mod->core_layout.base + info->stroffs; + src = mod->kallsyms->symtab; + for (ndst = i = 0; i < mod->kallsyms->num_symtab; i++) { if (i == 0 || is_core_symbol(src+i, info->sechdrs, info->hdr->e_shnum, info->index.pcpu)) { dst[ndst] = src[i]; - dst[ndst++].st_name = s - mod->core_strtab; - s += strlcpy(s, &mod->strtab[src[i].st_name], + dst[ndst++].st_name = s - mod->core_kallsyms.strtab; + s += strlcpy(s, &mod->kallsyms->strtab[src[i].st_name], KSYM_NAME_LEN) + 1; } } - mod->core_num_syms = ndst; + mod->core_kallsyms.num_symtab = ndst; } #else static inline void layout_symtab(struct module *mod, struct load_info *info) @@ -3263,9 +3284,8 @@ static noinline int do_init_module(struct module *mod) module_put(mod); trim_init_extable(mod); #ifdef CONFIG_KALLSYMS - mod->num_symtab = mod->core_num_syms; - mod->symtab = mod->core_symtab; - mod->strtab = mod->core_strtab; + /* Switch to core kallsyms now init is done: kallsyms may be walking! */ + rcu_assign_pointer(mod->kallsyms, &mod->core_kallsyms); #endif mod_tree_remove_init(mod); disable_ro_nx(&mod->init_layout); @@ -3295,6 +3315,7 @@ fail: module_put(mod); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_GOING, mod); + ftrace_release_mod(mod); free_module(mod); wake_up_all(&module_wq); return ret; @@ -3371,6 +3392,7 @@ static int complete_formation(struct module *mod, struct load_info *info) mod->state = MODULE_STATE_COMING; mutex_unlock(&module_mutex); + ftrace_module_enable(mod); blocking_notifier_call_chain(&module_notify_list, MODULE_STATE_COMING, mod); return 0; @@ -3496,7 +3518,7 @@ static int load_module(struct load_info *info, const char __user *uargs, /* Module is ready to execute: parsing args may do that. */ after_dashes = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, - -32768, 32767, NULL, + -32768, 32767, mod, unknown_module_param_cb); if (IS_ERR(after_dashes)) { err = PTR_ERR(after_dashes); @@ -3627,6 +3649,11 @@ static inline int is_arm_mapping_symbol(const char *str) && (str[2] == '\0' || str[2] == '.'); } +static const char *symname(struct mod_kallsyms *kallsyms, unsigned int symnum) +{ + return kallsyms->strtab + kallsyms->symtab[symnum].st_name; +} + static const char *get_ksymbol(struct module *mod, unsigned long addr, unsigned long *size, @@ -3634,6 +3661,7 @@ static const char *get_ksymbol(struct module *mod, { unsigned int i, best = 0; unsigned long nextval; + struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms); /* At worse, next value is at end of module */ if (within_module_init(addr, mod)) @@ -3643,32 +3671,32 @@ static const char *get_ksymbol(struct module *mod, /* Scan for closest preceding symbol, and next symbol. (ELF starts real symbols at 1). */ - for (i = 1; i < mod->num_symtab; i++) { - if (mod->symtab[i].st_shndx == SHN_UNDEF) + for (i = 1; i < kallsyms->num_symtab; i++) { + if (kallsyms->symtab[i].st_shndx == SHN_UNDEF) continue; /* We ignore unnamed symbols: they're uninformative * and inserted at a whim. */ - if (mod->symtab[i].st_value <= addr - && mod->symtab[i].st_value > mod->symtab[best].st_value - && *(mod->strtab + mod->symtab[i].st_name) != '\0' - && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name)) + if (*symname(kallsyms, i) == '\0' + || is_arm_mapping_symbol(symname(kallsyms, i))) + continue; + + if (kallsyms->symtab[i].st_value <= addr + && kallsyms->symtab[i].st_value > kallsyms->symtab[best].st_value) best = i; - if (mod->symtab[i].st_value > addr - && mod->symtab[i].st_value < nextval - && *(mod->strtab + mod->symtab[i].st_name) != '\0' - && !is_arm_mapping_symbol(mod->strtab + mod->symtab[i].st_name)) - nextval = mod->symtab[i].st_value; + if (kallsyms->symtab[i].st_value > addr + && kallsyms->symtab[i].st_value < nextval) + nextval = kallsyms->symtab[i].st_value; } if (!best) return NULL; if (size) - *size = nextval - mod->symtab[best].st_value; + *size = nextval - kallsyms->symtab[best].st_value; if (offset) - *offset = addr - mod->symtab[best].st_value; - return mod->strtab + mod->symtab[best].st_name; + *offset = addr - kallsyms->symtab[best].st_value; + return symname(kallsyms, best); } /* For kallsyms to ask for address resolution. NULL means not found. Careful @@ -3758,19 +3786,21 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, preempt_disable(); list_for_each_entry_rcu(mod, &modules, list) { + struct mod_kallsyms *kallsyms; + if (mod->state == MODULE_STATE_UNFORMED) continue; - if (symnum < mod->num_symtab) { - *value = mod->symtab[symnum].st_value; - *type = mod->symtab[symnum].st_info; - strlcpy(name, mod->strtab + mod->symtab[symnum].st_name, - KSYM_NAME_LEN); + kallsyms = rcu_dereference_sched(mod->kallsyms); + if (symnum < kallsyms->num_symtab) { + *value = kallsyms->symtab[symnum].st_value; + *type = kallsyms->symtab[symnum].st_info; + strlcpy(name, symname(kallsyms, symnum), KSYM_NAME_LEN); strlcpy(module_name, mod->name, MODULE_NAME_LEN); *exported = is_exported(name, *value, mod); preempt_enable(); return 0; } - symnum -= mod->num_symtab; + symnum -= kallsyms->num_symtab; } preempt_enable(); return -ERANGE; @@ -3779,11 +3809,12 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, static unsigned long mod_find_symname(struct module *mod, const char *name) { unsigned int i; + struct mod_kallsyms *kallsyms = rcu_dereference_sched(mod->kallsyms); - for (i = 0; i < mod->num_symtab; i++) - if (strcmp(name, mod->strtab+mod->symtab[i].st_name) == 0 && - mod->symtab[i].st_info != 'U') - return mod->symtab[i].st_value; + for (i = 0; i < kallsyms->num_symtab; i++) + if (strcmp(name, symname(kallsyms, i)) == 0 && + kallsyms->symtab[i].st_info != 'U') + return kallsyms->symtab[i].st_value; return 0; } @@ -3822,11 +3853,14 @@ int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *, module_assert_mutex(); list_for_each_entry(mod, &modules, list) { + /* We hold module_mutex: no need for rcu_dereference_sched */ + struct mod_kallsyms *kallsyms = mod->kallsyms; + if (mod->state == MODULE_STATE_UNFORMED) continue; - for (i = 0; i < mod->num_symtab; i++) { - ret = fn(data, mod->strtab + mod->symtab[i].st_name, - mod, mod->symtab[i].st_value); + for (i = 0; i < kallsyms->num_symtab; i++) { + ret = fn(data, symname(kallsyms, i), + mod, kallsyms->symtab[i].st_value); if (ret != 0) return ret; } diff --git a/kernel/pid.c b/kernel/pid.c index f4ad91b746f1..4d73a834c7e6 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -588,7 +588,7 @@ void __init pidhash_init(void) void __init pidmap_init(void) { - /* Veryify no one has done anything silly */ + /* Verify no one has done anything silly: */ BUILD_BUG_ON(PID_MAX_LIMIT >= PIDNS_HASH_ADDING); /* bump default and minimum pid_max based on number of cpus */ diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 02e8dfaa1ce2..68d3ebc12601 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -235,7 +235,7 @@ config PM_TRACE_RTC config APM_EMULATION tristate "Advanced Power Management Emulation" - depends on PM && SYS_SUPPORTS_APM_EMULATION + depends on SYS_SUPPORTS_APM_EMULATION help APM is a BIOS specification for saving power using several different techniques. This is mostly useful for battery powered laptops with diff --git a/kernel/profile.c b/kernel/profile.c index 99513e1160e5..51369697466e 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -59,6 +59,7 @@ int profile_setup(char *str) if (!strncmp(str, sleepstr, strlen(sleepstr))) { #ifdef CONFIG_SCHEDSTATS + force_schedstat_enabled(); prof_on = SLEEP_PROFILING; if (str[strlen(sleepstr)] == ',') str += strlen(sleepstr) + 1; diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 39f9c73d33c5..55cea189783f 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1613,7 +1613,6 @@ static int rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) int needmore; struct rcu_data *rdp = this_cpu_ptr(rsp->rda); - rcu_nocb_gp_cleanup(rsp, rnp); rnp->need_future_gp[c & 0x1] = 0; needmore = rnp->need_future_gp[(c + 1) & 0x1]; trace_rcu_future_gp(rnp, rdp, c, @@ -1634,7 +1633,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp) !READ_ONCE(rsp->gp_flags) || !rsp->gp_kthread) return; - wake_up(&rsp->gp_wq); + swake_up(&rsp->gp_wq); } /* @@ -2009,6 +2008,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) int nocb = 0; struct rcu_data *rdp; struct rcu_node *rnp = rcu_get_root(rsp); + struct swait_queue_head *sq; WRITE_ONCE(rsp->gp_activity, jiffies); raw_spin_lock_irq_rcu_node(rnp); @@ -2045,7 +2045,9 @@ static void rcu_gp_cleanup(struct rcu_state *rsp) needgp = __note_gp_changes(rsp, rnp, rdp) || needgp; /* smp_mb() provided by prior unlock-lock pair. */ nocb += rcu_future_gp_cleanup(rsp, rnp); + sq = rcu_nocb_gp_get(rnp); raw_spin_unlock_irq_rcu_node(rnp); + rcu_nocb_gp_cleanup(sq); cond_resched_rcu_qs(); WRITE_ONCE(rsp->gp_activity, jiffies); rcu_gp_slow(rsp, gp_cleanup_delay); @@ -2091,7 +2093,7 @@ static int __noreturn rcu_gp_kthread(void *arg) READ_ONCE(rsp->gpnum), TPS("reqwait")); rsp->gp_state = RCU_GP_WAIT_GPS; - wait_event_interruptible(rsp->gp_wq, + swait_event_interruptible(rsp->gp_wq, READ_ONCE(rsp->gp_flags) & RCU_GP_FLAG_INIT); rsp->gp_state = RCU_GP_DONE_GPS; @@ -2121,7 +2123,7 @@ static int __noreturn rcu_gp_kthread(void *arg) READ_ONCE(rsp->gpnum), TPS("fqswait")); rsp->gp_state = RCU_GP_WAIT_FQS; - ret = wait_event_interruptible_timeout(rsp->gp_wq, + ret = swait_event_interruptible_timeout(rsp->gp_wq, rcu_gp_fqs_check_wake(rsp, &gf), j); rsp->gp_state = RCU_GP_DOING_FQS; /* Locking provides needed memory barriers. */ @@ -2247,7 +2249,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags) WARN_ON_ONCE(!rcu_gp_in_progress(rsp)); WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); raw_spin_unlock_irqrestore_rcu_node(rcu_get_root(rsp), flags); - rcu_gp_kthread_wake(rsp); + swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */ } /* @@ -2897,7 +2899,7 @@ static void force_quiescent_state(struct rcu_state *rsp) } WRITE_ONCE(rsp->gp_flags, READ_ONCE(rsp->gp_flags) | RCU_GP_FLAG_FQS); raw_spin_unlock_irqrestore_rcu_node(rnp_old, flags); - rcu_gp_kthread_wake(rsp); + swake_up(&rsp->gp_wq); /* Memory barrier implied by swake_up() path. */ } /* @@ -3526,7 +3528,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp, raw_spin_unlock_irqrestore_rcu_node(rnp, flags); if (wake) { smp_mb(); /* EGP done before wake_up(). */ - wake_up(&rsp->expedited_wq); + swake_up(&rsp->expedited_wq); } break; } @@ -3777,7 +3779,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) jiffies_start = jiffies; for (;;) { - ret = wait_event_interruptible_timeout( + ret = swait_event_timeout( rsp->expedited_wq, sync_rcu_preempt_exp_done(rnp_root), jiffies_stall); @@ -3785,7 +3787,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp) return; if (ret < 0) { /* Hit a signal, disable CPU stall warnings. */ - wait_event(rsp->expedited_wq, + swait_event(rsp->expedited_wq, sync_rcu_preempt_exp_done(rnp_root)); return; } @@ -4479,8 +4481,8 @@ static void __init rcu_init_one(struct rcu_state *rsp) } } - init_waitqueue_head(&rsp->gp_wq); - init_waitqueue_head(&rsp->expedited_wq); + init_swait_queue_head(&rsp->gp_wq); + init_swait_queue_head(&rsp->expedited_wq); rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { while (i > rnp->grphi) diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 4886d6a03353..df668c0f9e64 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -27,6 +27,7 @@ #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/seqlock.h> +#include <linux/swait.h> #include <linux/stop_machine.h> /* @@ -244,7 +245,7 @@ struct rcu_node { /* Refused to boost: not sure why, though. */ /* This can happen due to race conditions. */ #ifdef CONFIG_RCU_NOCB_CPU - wait_queue_head_t nocb_gp_wq[2]; + struct swait_queue_head nocb_gp_wq[2]; /* Place for rcu_nocb_kthread() to wait GP. */ #endif /* #ifdef CONFIG_RCU_NOCB_CPU */ int need_future_gp[2]; @@ -400,7 +401,7 @@ struct rcu_data { atomic_long_t nocb_q_count_lazy; /* invocation (all stages). */ struct rcu_head *nocb_follower_head; /* CBs ready to invoke. */ struct rcu_head **nocb_follower_tail; - wait_queue_head_t nocb_wq; /* For nocb kthreads to sleep on. */ + struct swait_queue_head nocb_wq; /* For nocb kthreads to sleep on. */ struct task_struct *nocb_kthread; int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */ @@ -479,7 +480,7 @@ struct rcu_state { unsigned long gpnum; /* Current gp number. */ unsigned long completed; /* # of last completed gp. */ struct task_struct *gp_kthread; /* Task for grace periods. */ - wait_queue_head_t gp_wq; /* Where GP task waits. */ + struct swait_queue_head gp_wq; /* Where GP task waits. */ short gp_flags; /* Commands for GP task. */ short gp_state; /* GP kthread sleep state. */ @@ -507,7 +508,7 @@ struct rcu_state { unsigned long expedited_sequence; /* Take a ticket. */ atomic_long_t expedited_normal; /* # fallbacks to normal. */ atomic_t expedited_need_qs; /* # CPUs left to check in. */ - wait_queue_head_t expedited_wq; /* Wait for check-ins. */ + struct swait_queue_head expedited_wq; /* Wait for check-ins. */ int ncpus_snap; /* # CPUs seen last time. */ unsigned long jiffies_force_qs; /* Time at which to invoke */ @@ -622,7 +623,8 @@ static void zero_cpu_stall_ticks(struct rcu_data *rdp); static void increment_cpu_stall_ticks(void); static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu); static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq); -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp); +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp); +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq); static void rcu_init_one_nocb(struct rcu_node *rnp); static bool __call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *rhp, bool lazy, unsigned long flags); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 43e9b4a4bcd9..efdf7b61ce12 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1810,9 +1810,9 @@ early_param("rcu_nocb_poll", parse_rcu_nocb_poll); * Wake up any no-CBs CPUs' kthreads that were waiting on the just-ended * grace period. */ -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) { - wake_up_all(&rnp->nocb_gp_wq[rnp->completed & 0x1]); + swake_up_all(sq); } /* @@ -1828,10 +1828,15 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq) rnp->need_future_gp[(rnp->completed + 1) & 0x1] += nrq; } +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) +{ + return &rnp->nocb_gp_wq[rnp->completed & 0x1]; +} + static void rcu_init_one_nocb(struct rcu_node *rnp) { - init_waitqueue_head(&rnp->nocb_gp_wq[0]); - init_waitqueue_head(&rnp->nocb_gp_wq[1]); + init_swait_queue_head(&rnp->nocb_gp_wq[0]); + init_swait_queue_head(&rnp->nocb_gp_wq[1]); } #ifndef CONFIG_RCU_NOCB_CPU_ALL @@ -1856,7 +1861,7 @@ static void wake_nocb_leader(struct rcu_data *rdp, bool force) if (READ_ONCE(rdp_leader->nocb_leader_sleep) || force) { /* Prior smp_mb__after_atomic() orders against prior enqueue. */ WRITE_ONCE(rdp_leader->nocb_leader_sleep, false); - wake_up(&rdp_leader->nocb_wq); + swake_up(&rdp_leader->nocb_wq); } } @@ -2068,7 +2073,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp) */ trace_rcu_future_gp(rnp, rdp, c, TPS("StartWait")); for (;;) { - wait_event_interruptible( + swait_event_interruptible( rnp->nocb_gp_wq[c & 0x1], (d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c))); if (likely(d)) @@ -2096,7 +2101,7 @@ wait_again: /* Wait for callbacks to appear. */ if (!rcu_nocb_poll) { trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, "Sleep"); - wait_event_interruptible(my_rdp->nocb_wq, + swait_event_interruptible(my_rdp->nocb_wq, !READ_ONCE(my_rdp->nocb_leader_sleep)); /* Memory barrier handled by smp_mb() calls below and repoll. */ } else if (firsttime) { @@ -2171,7 +2176,7 @@ wait_again: * List was empty, wake up the follower. * Memory barriers supplied by atomic_long_add(). */ - wake_up(&rdp->nocb_wq); + swake_up(&rdp->nocb_wq); } } @@ -2192,7 +2197,7 @@ static void nocb_follower_wait(struct rcu_data *rdp) if (!rcu_nocb_poll) { trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, "FollowerSleep"); - wait_event_interruptible(rdp->nocb_wq, + swait_event_interruptible(rdp->nocb_wq, READ_ONCE(rdp->nocb_follower_head)); } else if (firsttime) { /* Don't drown trace log with "Poll"! */ @@ -2351,7 +2356,7 @@ void __init rcu_init_nohz(void) static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) { rdp->nocb_tail = &rdp->nocb_head; - init_waitqueue_head(&rdp->nocb_wq); + init_swait_queue_head(&rdp->nocb_wq); rdp->nocb_follower_tail = &rdp->nocb_follower_head; } @@ -2501,7 +2506,7 @@ static bool rcu_nocb_cpu_needs_barrier(struct rcu_state *rsp, int cpu) return false; } -static void rcu_nocb_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp) +static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq) { } @@ -2509,6 +2514,11 @@ static void rcu_nocb_gp_set(struct rcu_node *rnp, int nrq) { } +static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp) +{ + return NULL; +} + static void rcu_init_one_nocb(struct rcu_node *rnp) { } diff --git a/kernel/resource.c b/kernel/resource.c index 09c0597840b0..4d466052426b 100644 --- a/kernel/resource.c +++ b/kernel/resource.c @@ -333,13 +333,13 @@ int release_resource(struct resource *old) EXPORT_SYMBOL(release_resource); /* - * Finds the lowest iomem reosurce exists with-in [res->start.res->end) - * the caller must specify res->start, res->end, res->flags and "name". - * If found, returns 0, res is overwritten, if not found, returns -1. - * This walks through whole tree and not just first level children - * until and unless first_level_children_only is true. + * Finds the lowest iomem resource existing within [res->start.res->end). + * The caller must specify res->start, res->end, res->flags, and optionally + * desc. If found, returns 0, res is overwritten, if not found, returns -1. + * This function walks the whole tree and not just first level children until + * and unless first_level_children_only is true. */ -static int find_next_iomem_res(struct resource *res, char *name, +static int find_next_iomem_res(struct resource *res, unsigned long desc, bool first_level_children_only) { resource_size_t start, end; @@ -358,9 +358,9 @@ static int find_next_iomem_res(struct resource *res, char *name, read_lock(&resource_lock); for (p = iomem_resource.child; p; p = next_resource(p, sibling_only)) { - if (p->flags != res->flags) + if ((p->flags & res->flags) != res->flags) continue; - if (name && strcmp(p->name, name)) + if ((desc != IORES_DESC_NONE) && (desc != p->desc)) continue; if (p->start > end) { p = NULL; @@ -385,15 +385,18 @@ static int find_next_iomem_res(struct resource *res, char *name, * Walks through iomem resources and calls func() with matching resource * ranges. This walks through whole tree and not just first level children. * All the memory ranges which overlap start,end and also match flags and - * name are valid candidates. + * desc are valid candidates. * - * @name: name of resource - * @flags: resource flags + * @desc: I/O resource descriptor. Use IORES_DESC_NONE to skip @desc check. + * @flags: I/O resource flags * @start: start addr * @end: end addr + * + * NOTE: For a new descriptor search, define a new IORES_DESC in + * <linux/ioport.h> and set it in 'desc' of a target resource entry. */ -int walk_iomem_res(char *name, unsigned long flags, u64 start, u64 end, - void *arg, int (*func)(u64, u64, void *)) +int walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, + u64 end, void *arg, int (*func)(u64, u64, void *)) { struct resource res; u64 orig_end; @@ -403,23 +406,27 @@ int walk_iomem_res(char *name, unsigned long flags, u64 start, u64 end, res.end = end; res.flags = flags; orig_end = res.end; + while ((res.start < res.end) && - (!find_next_iomem_res(&res, name, false))) { + (!find_next_iomem_res(&res, desc, false))) { + ret = (*func)(res.start, res.end, arg); if (ret) break; + res.start = res.end + 1; res.end = orig_end; } + return ret; } /* - * This function calls callback against all memory range of "System RAM" - * which are marked as IORESOURCE_MEM and IORESOUCE_BUSY. - * Now, this function is only for "System RAM". This function deals with - * full ranges and not pfn. If resources are not pfn aligned, dealing - * with pfn can truncate ranges. + * This function calls the @func callback against all memory ranges of type + * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY. + * Now, this function is only for System RAM, it deals with full ranges and + * not PFNs. If resources are not PFN-aligned, dealing with PFNs can truncate + * ranges. */ int walk_system_ram_res(u64 start, u64 end, void *arg, int (*func)(u64, u64, void *)) @@ -430,10 +437,10 @@ int walk_system_ram_res(u64 start, u64 end, void *arg, res.start = start; res.end = end; - res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; orig_end = res.end; while ((res.start < res.end) && - (!find_next_iomem_res(&res, "System RAM", true))) { + (!find_next_iomem_res(&res, IORES_DESC_NONE, true))) { ret = (*func)(res.start, res.end, arg); if (ret) break; @@ -446,9 +453,9 @@ int walk_system_ram_res(u64 start, u64 end, void *arg, #if !defined(CONFIG_ARCH_HAS_WALK_MEMORY) /* - * This function calls callback against all memory range of "System RAM" - * which are marked as IORESOURCE_MEM and IORESOUCE_BUSY. - * Now, this function is only for "System RAM". + * This function calls the @func callback against all memory ranges of type + * System RAM which are marked as IORESOURCE_SYSTEM_RAM and IORESOUCE_BUSY. + * It is to be used only for System RAM. */ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, void *arg, int (*func)(unsigned long, unsigned long, void *)) @@ -460,10 +467,10 @@ int walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages, res.start = (u64) start_pfn << PAGE_SHIFT; res.end = ((u64)(start_pfn + nr_pages) << PAGE_SHIFT) - 1; - res.flags = IORESOURCE_MEM | IORESOURCE_BUSY; + res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; orig_end = res.end; while ((res.start < res.end) && - (find_next_iomem_res(&res, "System RAM", true) >= 0)) { + (find_next_iomem_res(&res, IORES_DESC_NONE, true) >= 0)) { pfn = (res.start + PAGE_SIZE - 1) >> PAGE_SHIFT; end_pfn = (res.end + 1) >> PAGE_SHIFT; if (end_pfn > pfn) @@ -484,7 +491,7 @@ static int __is_ram(unsigned long pfn, unsigned long nr_pages, void *arg) } /* * This generic page_is_ram() returns true if specified address is - * registered as "System RAM" in iomem_resource list. + * registered as System RAM in iomem_resource list. */ int __weak page_is_ram(unsigned long pfn) { @@ -496,30 +503,34 @@ EXPORT_SYMBOL_GPL(page_is_ram); * region_intersects() - determine intersection of region with known resources * @start: region start address * @size: size of region - * @name: name of resource (in iomem_resource) + * @flags: flags of resource (in iomem_resource) + * @desc: descriptor of resource (in iomem_resource) or IORES_DESC_NONE * * Check if the specified region partially overlaps or fully eclipses a - * resource identified by @name. Return REGION_DISJOINT if the region - * does not overlap @name, return REGION_MIXED if the region overlaps - * @type and another resource, and return REGION_INTERSECTS if the - * region overlaps @type and no other defined resource. Note, that - * REGION_INTERSECTS is also returned in the case when the specified - * region overlaps RAM and undefined memory holes. + * resource identified by @flags and @desc (optional with IORES_DESC_NONE). + * Return REGION_DISJOINT if the region does not overlap @flags/@desc, + * return REGION_MIXED if the region overlaps @flags/@desc and another + * resource, and return REGION_INTERSECTS if the region overlaps @flags/@desc + * and no other defined resource. Note that REGION_INTERSECTS is also + * returned in the case when the specified region overlaps RAM and undefined + * memory holes. * * region_intersect() is used by memory remapping functions to ensure * the user is not remapping RAM and is a vast speed up over walking * through the resource table page by page. */ -int region_intersects(resource_size_t start, size_t size, const char *name) +int region_intersects(resource_size_t start, size_t size, unsigned long flags, + unsigned long desc) { - unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY; resource_size_t end = start + size - 1; int type = 0; int other = 0; struct resource *p; read_lock(&resource_lock); for (p = iomem_resource.child; p ; p = p->sibling) { - bool is_type = strcmp(p->name, name) == 0 && p->flags == flags; + bool is_type = (((p->flags & flags) == flags) && + ((desc == IORES_DESC_NONE) || + (desc == p->desc))); if (start >= p->start && start <= p->end) is_type ? type++ : other++; @@ -538,6 +549,7 @@ int region_intersects(resource_size_t start, size_t size, const char *name) return REGION_DISJOINT; } +EXPORT_SYMBOL_GPL(region_intersects); void __weak arch_remove_reservations(struct resource *avail) { @@ -948,6 +960,7 @@ static void __init __reserve_region_with_split(struct resource *root, res->start = start; res->end = end; res->flags = IORESOURCE_BUSY; + res->desc = IORES_DESC_NONE; while (1) { @@ -982,6 +995,7 @@ static void __init __reserve_region_with_split(struct resource *root, next_res->start = conflict->end + 1; next_res->end = end; next_res->flags = IORESOURCE_BUSY; + next_res->desc = IORES_DESC_NONE; } } else { res->start = conflict->end + 1; @@ -1071,8 +1085,9 @@ struct resource * __request_region(struct resource *parent, res->name = name; res->start = start; res->end = start + n - 1; - res->flags = resource_type(parent); + res->flags = resource_type(parent) | resource_ext_type(parent); res->flags |= IORESOURCE_BUSY | flags; + res->desc = IORES_DESC_NONE; write_lock(&resource_lock); @@ -1083,9 +1098,10 @@ struct resource * __request_region(struct resource *parent, if (!conflict) break; if (conflict != parent) { - parent = conflict; - if (!(conflict->flags & IORESOURCE_BUSY)) + if (!(conflict->flags & IORESOURCE_BUSY)) { + parent = conflict; continue; + } } if (conflict->flags & flags & IORESOURCE_MUXED) { add_wait_queue(&muxed_resource_wait, &wait); @@ -1237,6 +1253,7 @@ int release_mem_region_adjustable(struct resource *parent, new_res->start = end + 1; new_res->end = res->end; new_res->flags = res->flags; + new_res->desc = res->desc; new_res->parent = res->parent; new_res->sibling = res->sibling; new_res->child = NULL; @@ -1412,6 +1429,7 @@ static int __init reserve_setup(char *str) res->start = io_start; res->end = io_start + io_num - 1; res->flags = IORESOURCE_BUSY; + res->desc = IORES_DESC_NONE; res->child = NULL; if (request_resource(res->start >= 0x10000 ? &iomem_resource : &ioport_resource, res) == 0) reserved = x+1; diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 67687973ce80..7d4cba227cbd 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -13,7 +13,7 @@ endif obj-y += core.o loadavg.o clock.o cputime.o obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o -obj-y += wait.o completion.o idle.o +obj-y += wait.o swait.o completion.o idle.o obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o obj-$(CONFIG_SCHEDSTATS) += stats.o diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index bc54e84675da..fedb967a9841 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -61,6 +61,7 @@ #include <linux/static_key.h> #include <linux/workqueue.h> #include <linux/compiler.h> +#include <linux/tick.h> /* * Scheduler clock - returns current time in nanosec units. @@ -89,6 +90,8 @@ static void __set_sched_clock_stable(void) { if (!sched_clock_stable()) static_key_slow_inc(&__sched_clock_stable); + + tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE); } void set_sched_clock_stable(void) @@ -108,6 +111,8 @@ static void __clear_sched_clock_stable(struct work_struct *work) /* XXX worry about clock continuity */ if (sched_clock_stable()) static_key_slow_dec(&__sched_clock_stable); + + tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE); } static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 63d3a24e081a..e5725b931bee 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -26,6 +26,7 @@ * Thomas Gleixner, Mike Kravetz */ +#include <linux/kasan.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/nmi.h> @@ -66,12 +67,10 @@ #include <linux/pagemap.h> #include <linux/hrtimer.h> #include <linux/tick.h> -#include <linux/debugfs.h> #include <linux/ctype.h> #include <linux/ftrace.h> #include <linux/slab.h> #include <linux/init_task.h> -#include <linux/binfmts.h> #include <linux/context_tracking.h> #include <linux/compiler.h> @@ -124,138 +123,6 @@ const_debug unsigned int sysctl_sched_features = #undef SCHED_FEAT -#ifdef CONFIG_SCHED_DEBUG -#define SCHED_FEAT(name, enabled) \ - #name , - -static const char * const sched_feat_names[] = { -#include "features.h" -}; - -#undef SCHED_FEAT - -static int sched_feat_show(struct seq_file *m, void *v) -{ - int i; - - for (i = 0; i < __SCHED_FEAT_NR; i++) { - if (!(sysctl_sched_features & (1UL << i))) - seq_puts(m, "NO_"); - seq_printf(m, "%s ", sched_feat_names[i]); - } - seq_puts(m, "\n"); - - return 0; -} - -#ifdef HAVE_JUMP_LABEL - -#define jump_label_key__true STATIC_KEY_INIT_TRUE -#define jump_label_key__false STATIC_KEY_INIT_FALSE - -#define SCHED_FEAT(name, enabled) \ - jump_label_key__##enabled , - -struct static_key sched_feat_keys[__SCHED_FEAT_NR] = { -#include "features.h" -}; - -#undef SCHED_FEAT - -static void sched_feat_disable(int i) -{ - static_key_disable(&sched_feat_keys[i]); -} - -static void sched_feat_enable(int i) -{ - static_key_enable(&sched_feat_keys[i]); -} -#else -static void sched_feat_disable(int i) { }; -static void sched_feat_enable(int i) { }; -#endif /* HAVE_JUMP_LABEL */ - -static int sched_feat_set(char *cmp) -{ - int i; - int neg = 0; - - if (strncmp(cmp, "NO_", 3) == 0) { - neg = 1; - cmp += 3; - } - - for (i = 0; i < __SCHED_FEAT_NR; i++) { - if (strcmp(cmp, sched_feat_names[i]) == 0) { - if (neg) { - sysctl_sched_features &= ~(1UL << i); - sched_feat_disable(i); - } else { - sysctl_sched_features |= (1UL << i); - sched_feat_enable(i); - } - break; - } - } - - return i; -} - -static ssize_t -sched_feat_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) -{ - char buf[64]; - char *cmp; - int i; - struct inode *inode; - - if (cnt > 63) - cnt = 63; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - cmp = strstrip(buf); - - /* Ensure the static_key remains in a consistent state */ - inode = file_inode(filp); - inode_lock(inode); - i = sched_feat_set(cmp); - inode_unlock(inode); - if (i == __SCHED_FEAT_NR) - return -EINVAL; - - *ppos += cnt; - - return cnt; -} - -static int sched_feat_open(struct inode *inode, struct file *filp) -{ - return single_open(filp, sched_feat_show, NULL); -} - -static const struct file_operations sched_feat_fops = { - .open = sched_feat_open, - .write = sched_feat_write, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static __init int sched_init_debug(void) -{ - debugfs_create_file("sched_features", 0644, NULL, NULL, - &sched_feat_fops); - - return 0; -} -late_initcall(sched_init_debug); -#endif /* CONFIG_SCHED_DEBUG */ - /* * Number of tasks to iterate in a single balance run. * Limited because this is done with IRQs disabled. @@ -453,20 +320,6 @@ static inline void init_hrtick(void) } #endif /* CONFIG_SCHED_HRTICK */ -/* - * cmpxchg based fetch_or, macro so it works for different integer types - */ -#define fetch_or(ptr, val) \ -({ typeof(*(ptr)) __old, __val = *(ptr); \ - for (;;) { \ - __old = cmpxchg((ptr), __val, __val | (val)); \ - if (__old == __val) \ - break; \ - __val = __old; \ - } \ - __old; \ -}) - #if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG) /* * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, @@ -715,31 +568,36 @@ static inline bool got_nohz_idle_kick(void) #endif /* CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_FULL -bool sched_can_stop_tick(void) +bool sched_can_stop_tick(struct rq *rq) { + int fifo_nr_running; + + /* Deadline tasks, even if single, need the tick */ + if (rq->dl.dl_nr_running) + return false; + /* - * FIFO realtime policy runs the highest priority task. Other runnable - * tasks are of a lower priority. The scheduler tick does nothing. + * FIFO realtime policy runs the highest priority task (after DEADLINE). + * Other runnable tasks are of a lower priority. The scheduler tick + * isn't needed. */ - if (current->policy == SCHED_FIFO) + fifo_nr_running = rq->rt.rt_nr_running - rq->rt.rr_nr_running; + if (fifo_nr_running) return true; /* * Round-robin realtime tasks time slice with other tasks at the same - * realtime priority. Is this task the only one at this priority? + * realtime priority. */ - if (current->policy == SCHED_RR) { - struct sched_rt_entity *rt_se = ¤t->rt; - - return list_is_singular(&rt_se->run_list); + if (rq->rt.rr_nr_running) { + if (rq->rt.rr_nr_running == 1) + return true; + else + return false; } - /* - * More than one running task need preemption. - * nr_running update is assumed to be visible - * after IPI is sent from wakers. - */ - if (this_rq()->nr_running > 1) + /* Normal multitasking need periodic preemption checks */ + if (rq->cfs.nr_running > 1) return false; return true; @@ -2093,7 +1951,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) ttwu_queue(p, cpu); stat: - ttwu_stat(p, cpu, wake_flags); + if (schedstat_enabled()) + ttwu_stat(p, cpu, wake_flags); out: raw_spin_unlock_irqrestore(&p->pi_lock, flags); @@ -2141,7 +2000,8 @@ static void try_to_wake_up_local(struct task_struct *p) ttwu_activate(rq, p, ENQUEUE_WAKEUP); ttwu_do_wakeup(rq, p, 0); - ttwu_stat(p, smp_processor_id(), 0); + if (schedstat_enabled()) + ttwu_stat(p, smp_processor_id(), 0); out: raw_spin_unlock(&p->pi_lock); } @@ -2183,7 +2043,6 @@ void __dl_clear_params(struct task_struct *p) dl_se->dl_bw = 0; dl_se->dl_throttled = 0; - dl_se->dl_new = 1; dl_se->dl_yielded = 0; } @@ -2210,6 +2069,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) #endif #ifdef CONFIG_SCHEDSTATS + /* Even if schedstat is disabled, there should not be garbage */ memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif @@ -2218,6 +2078,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) __dl_clear_params(p); INIT_LIST_HEAD(&p->rt.run_list); + p->rt.timeout = 0; + p->rt.time_slice = sched_rr_timeslice; + p->rt.on_rq = 0; + p->rt.on_list = 0; #ifdef CONFIG_PREEMPT_NOTIFIERS INIT_HLIST_HEAD(&p->preempt_notifiers); @@ -2281,6 +2145,69 @@ int sysctl_numa_balancing(struct ctl_table *table, int write, #endif #endif +DEFINE_STATIC_KEY_FALSE(sched_schedstats); + +#ifdef CONFIG_SCHEDSTATS +static void set_schedstats(bool enabled) +{ + if (enabled) + static_branch_enable(&sched_schedstats); + else + static_branch_disable(&sched_schedstats); +} + +void force_schedstat_enabled(void) +{ + if (!schedstat_enabled()) { + pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n"); + static_branch_enable(&sched_schedstats); + } +} + +static int __init setup_schedstats(char *str) +{ + int ret = 0; + if (!str) + goto out; + + if (!strcmp(str, "enable")) { + set_schedstats(true); + ret = 1; + } else if (!strcmp(str, "disable")) { + set_schedstats(false); + ret = 1; + } +out: + if (!ret) + pr_warn("Unable to parse schedstats=\n"); + + return ret; +} +__setup("schedstats=", setup_schedstats); + +#ifdef CONFIG_PROC_SYSCTL +int sysctl_schedstats(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + int err; + int state = static_branch_likely(&sched_schedstats); + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + t = *table; + t.data = &state; + err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + if (write) + set_schedstats(state); + return err; +} +#endif +#endif + /* * fork()/clone()-time setup: */ @@ -3010,16 +2937,6 @@ u64 scheduler_tick_max_deferment(void) } #endif -notrace unsigned long get_parent_ip(unsigned long addr) -{ - if (in_lock_functions(addr)) { - addr = CALLER_ADDR2; - if (in_lock_functions(addr)) - addr = CALLER_ADDR3; - } - return addr; -} - #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ defined(CONFIG_PREEMPT_TRACER)) @@ -3041,7 +2958,7 @@ void preempt_count_add(int val) PREEMPT_MASK - 10); #endif if (preempt_count() == val) { - unsigned long ip = get_parent_ip(CALLER_ADDR1); + unsigned long ip = get_lock_parent_ip(); #ifdef CONFIG_DEBUG_PREEMPT current->preempt_disable_ip = ip; #endif @@ -3068,7 +2985,7 @@ void preempt_count_sub(int val) #endif if (preempt_count() == val) - trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip()); __preempt_count_sub(val); } EXPORT_SYMBOL(preempt_count_sub); @@ -3280,7 +3197,6 @@ static void __sched notrace __schedule(bool preempt) trace_sched_switch(preempt, prev, next); rq = context_switch(rq, prev, next); /* unlocks the rq */ - cpu = cpu_of(rq); } else { lockdep_unpin_lock(&rq->lock); raw_spin_unlock_irq(&rq->lock); @@ -3466,7 +3382,7 @@ EXPORT_SYMBOL(default_wake_function); */ void rt_mutex_setprio(struct task_struct *p, int prio) { - int oldprio, queued, running, enqueue_flag = ENQUEUE_RESTORE; + int oldprio, queued, running, queue_flag = DEQUEUE_SAVE | DEQUEUE_MOVE; struct rq *rq; const struct sched_class *prev_class; @@ -3494,11 +3410,15 @@ void rt_mutex_setprio(struct task_struct *p, int prio) trace_sched_pi_setprio(p, prio); oldprio = p->prio; + + if (oldprio == prio) + queue_flag &= ~DEQUEUE_MOVE; + prev_class = p->sched_class; queued = task_on_rq_queued(p); running = task_current(rq, p); if (queued) - dequeue_task(rq, p, DEQUEUE_SAVE); + dequeue_task(rq, p, queue_flag); if (running) put_prev_task(rq, p); @@ -3516,7 +3436,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (!dl_prio(p->normal_prio) || (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) { p->dl.dl_boosted = 1; - enqueue_flag |= ENQUEUE_REPLENISH; + queue_flag |= ENQUEUE_REPLENISH; } else p->dl.dl_boosted = 0; p->sched_class = &dl_sched_class; @@ -3524,7 +3444,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (dl_prio(oldprio)) p->dl.dl_boosted = 0; if (oldprio < prio) - enqueue_flag |= ENQUEUE_HEAD; + queue_flag |= ENQUEUE_HEAD; p->sched_class = &rt_sched_class; } else { if (dl_prio(oldprio)) @@ -3539,7 +3459,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (running) p->sched_class->set_curr_task(rq); if (queued) - enqueue_task(rq, p, enqueue_flag); + enqueue_task(rq, p, queue_flag); check_class_changed(rq, p, prev_class, oldprio); out_unlock: @@ -3895,6 +3815,7 @@ static int __sched_setscheduler(struct task_struct *p, const struct sched_class *prev_class; struct rq *rq; int reset_on_fork; + int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE; /* may grab non-irq protected spin_locks */ BUG_ON(in_interrupt()); @@ -4077,17 +3998,14 @@ change: * itself. */ new_effective_prio = rt_mutex_get_effective_prio(p, newprio); - if (new_effective_prio == oldprio) { - __setscheduler_params(p, attr); - task_rq_unlock(rq, p, &flags); - return 0; - } + if (new_effective_prio == oldprio) + queue_flags &= ~DEQUEUE_MOVE; } queued = task_on_rq_queued(p); running = task_current(rq, p); if (queued) - dequeue_task(rq, p, DEQUEUE_SAVE); + dequeue_task(rq, p, queue_flags); if (running) put_prev_task(rq, p); @@ -4097,15 +4015,14 @@ change: if (running) p->sched_class->set_curr_task(rq); if (queued) { - int enqueue_flags = ENQUEUE_RESTORE; /* * We enqueue to tail when the priority of a task is * increased (user space view). */ - if (oldprio <= p->prio) - enqueue_flags |= ENQUEUE_HEAD; + if (oldprio < p->prio) + queue_flags |= ENQUEUE_HEAD; - enqueue_task(rq, p, enqueue_flags); + enqueue_task(rq, p, queue_flags); } check_class_changed(rq, p, prev_class, oldprio); @@ -5096,6 +5013,8 @@ void init_idle(struct task_struct *idle, int cpu) idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); + kasan_unpoison_task_stack(idle); + #ifdef CONFIG_SMP /* * Its possible that init_idle() gets called multiple times on a task, @@ -5405,183 +5324,6 @@ static void migrate_tasks(struct rq *dead_rq) } #endif /* CONFIG_HOTPLUG_CPU */ -#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) - -static struct ctl_table sd_ctl_dir[] = { - { - .procname = "sched_domain", - .mode = 0555, - }, - {} -}; - -static struct ctl_table sd_ctl_root[] = { - { - .procname = "kernel", - .mode = 0555, - .child = sd_ctl_dir, - }, - {} -}; - -static struct ctl_table *sd_alloc_ctl_entry(int n) -{ - struct ctl_table *entry = - kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); - - return entry; -} - -static void sd_free_ctl_entry(struct ctl_table **tablep) -{ - struct ctl_table *entry; - - /* - * In the intermediate directories, both the child directory and - * procname are dynamically allocated and could fail but the mode - * will always be set. In the lowest directory the names are - * static strings and all have proc handlers. - */ - for (entry = *tablep; entry->mode; entry++) { - if (entry->child) - sd_free_ctl_entry(&entry->child); - if (entry->proc_handler == NULL) - kfree(entry->procname); - } - - kfree(*tablep); - *tablep = NULL; -} - -static int min_load_idx = 0; -static int max_load_idx = CPU_LOAD_IDX_MAX-1; - -static void -set_table_entry(struct ctl_table *entry, - const char *procname, void *data, int maxlen, - umode_t mode, proc_handler *proc_handler, - bool load_idx) -{ - entry->procname = procname; - entry->data = data; - entry->maxlen = maxlen; - entry->mode = mode; - entry->proc_handler = proc_handler; - - if (load_idx) { - entry->extra1 = &min_load_idx; - entry->extra2 = &max_load_idx; - } -} - -static struct ctl_table * -sd_alloc_ctl_domain_table(struct sched_domain *sd) -{ - struct ctl_table *table = sd_alloc_ctl_entry(14); - - if (table == NULL) - return NULL; - - set_table_entry(&table[0], "min_interval", &sd->min_interval, - sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[1], "max_interval", &sd->max_interval, - sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[2], "busy_idx", &sd->busy_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[3], "idle_idx", &sd->idle_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[5], "wake_idx", &sd->wake_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, - sizeof(int), 0644, proc_dointvec_minmax, true); - set_table_entry(&table[7], "busy_factor", &sd->busy_factor, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[9], "cache_nice_tries", - &sd->cache_nice_tries, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[10], "flags", &sd->flags, - sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[11], "max_newidle_lb_cost", - &sd->max_newidle_lb_cost, - sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[12], "name", sd->name, - CORENAME_MAX_SIZE, 0444, proc_dostring, false); - /* &table[13] is terminator */ - - return table; -} - -static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu) -{ - struct ctl_table *entry, *table; - struct sched_domain *sd; - int domain_num = 0, i; - char buf[32]; - - for_each_domain(cpu, sd) - domain_num++; - entry = table = sd_alloc_ctl_entry(domain_num + 1); - if (table == NULL) - return NULL; - - i = 0; - for_each_domain(cpu, sd) { - snprintf(buf, 32, "domain%d", i); - entry->procname = kstrdup(buf, GFP_KERNEL); - entry->mode = 0555; - entry->child = sd_alloc_ctl_domain_table(sd); - entry++; - i++; - } - return table; -} - -static struct ctl_table_header *sd_sysctl_header; -static void register_sched_domain_sysctl(void) -{ - int i, cpu_num = num_possible_cpus(); - struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); - char buf[32]; - - WARN_ON(sd_ctl_dir[0].child); - sd_ctl_dir[0].child = entry; - - if (entry == NULL) - return; - - for_each_possible_cpu(i) { - snprintf(buf, 32, "cpu%d", i); - entry->procname = kstrdup(buf, GFP_KERNEL); - entry->mode = 0555; - entry->child = sd_alloc_ctl_cpu_table(i); - entry++; - } - - WARN_ON(sd_sysctl_header); - sd_sysctl_header = register_sysctl_table(sd_ctl_root); -} - -/* may be called multiple times per register */ -static void unregister_sched_domain_sysctl(void) -{ - unregister_sysctl_table(sd_sysctl_header); - sd_sysctl_header = NULL; - if (sd_ctl_dir[0].child) - sd_free_ctl_entry(&sd_ctl_dir[0].child); -} -#else -static void register_sched_domain_sysctl(void) -{ -} -static void unregister_sched_domain_sysctl(void) -{ -} -#endif /* CONFIG_SCHED_DEBUG && CONFIG_SYSCTL */ - static void set_rq_online(struct rq *rq) { if (!rq->online) { @@ -6173,11 +5915,16 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) /* Setup the mask of cpus configured for isolated domains */ static int __init isolated_cpu_setup(char *str) { + int ret; + alloc_bootmem_cpumask_var(&cpu_isolated_map); - cpulist_parse(str, cpu_isolated_map); + ret = cpulist_parse(str, cpu_isolated_map); + if (ret) { + pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids); + return 0; + } return 1; } - __setup("isolcpus=", isolated_cpu_setup); struct s_data { @@ -6840,7 +6587,7 @@ static void sched_init_numa(void) sched_domains_numa_masks[i][j] = mask; - for (k = 0; k < nr_node_ids; k++) { + for_each_node(k) { if (node_distance(j, k) > sched_domains_numa_distance[i]) continue; @@ -7860,11 +7607,9 @@ void sched_destroy_group(struct task_group *tg) void sched_offline_group(struct task_group *tg) { unsigned long flags; - int i; /* end participation in shares distribution */ - for_each_possible_cpu(i) - unregister_fair_sched_group(tg, i); + unregister_fair_sched_group(tg); spin_lock_irqsave(&task_group_lock, flags); list_del_rcu(&tg->list); @@ -7890,7 +7635,7 @@ void sched_move_task(struct task_struct *tsk) queued = task_on_rq_queued(tsk); if (queued) - dequeue_task(rq, tsk, DEQUEUE_SAVE); + dequeue_task(rq, tsk, DEQUEUE_SAVE | DEQUEUE_MOVE); if (unlikely(running)) put_prev_task(rq, tsk); @@ -7914,7 +7659,7 @@ void sched_move_task(struct task_struct *tsk) if (unlikely(running)) tsk->sched_class->set_curr_task(rq); if (queued) - enqueue_task(rq, tsk, ENQUEUE_RESTORE); + enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE); task_rq_unlock(rq, tsk, &flags); } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index b2ab2ffb1adc..75f98c5498d5 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -262,21 +262,21 @@ static __always_inline bool steal_account_process_tick(void) #ifdef CONFIG_PARAVIRT if (static_key_false(¶virt_steal_enabled)) { u64 steal; - cputime_t steal_ct; + unsigned long steal_jiffies; steal = paravirt_steal_clock(smp_processor_id()); steal -= this_rq()->prev_steal_time; /* - * cputime_t may be less precise than nsecs (eg: if it's - * based on jiffies). Lets cast the result to cputime + * steal is in nsecs but our caller is expecting steal + * time in jiffies. Lets cast the result to jiffies * granularity and account the rest on the next rounds. */ - steal_ct = nsecs_to_cputime(steal); - this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct); + steal_jiffies = nsecs_to_jiffies(steal); + this_rq()->prev_steal_time += jiffies_to_nsecs(steal_jiffies); - account_steal_time(steal_ct); - return steal_ct; + account_steal_time(jiffies_to_cputime(steal_jiffies)); + return steal_jiffies; } #endif return false; @@ -668,26 +668,25 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime #endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -static unsigned long long vtime_delta(struct task_struct *tsk) +static cputime_t vtime_delta(struct task_struct *tsk) { - unsigned long long clock; + unsigned long now = READ_ONCE(jiffies); - clock = local_clock(); - if (clock < tsk->vtime_snap) + if (time_before(now, (unsigned long)tsk->vtime_snap)) return 0; - return clock - tsk->vtime_snap; + return jiffies_to_cputime(now - tsk->vtime_snap); } static cputime_t get_vtime_delta(struct task_struct *tsk) { - unsigned long long delta = vtime_delta(tsk); + unsigned long now = READ_ONCE(jiffies); + unsigned long delta = now - tsk->vtime_snap; WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE); - tsk->vtime_snap += delta; + tsk->vtime_snap = now; - /* CHECKME: always safe to convert nsecs to cputime? */ - return nsecs_to_cputime(delta); + return jiffies_to_cputime(delta); } static void __vtime_account_system(struct task_struct *tsk) @@ -699,6 +698,9 @@ static void __vtime_account_system(struct task_struct *tsk) void vtime_account_system(struct task_struct *tsk) { + if (!vtime_delta(tsk)) + return; + write_seqcount_begin(&tsk->vtime_seqcount); __vtime_account_system(tsk); write_seqcount_end(&tsk->vtime_seqcount); @@ -707,7 +709,8 @@ void vtime_account_system(struct task_struct *tsk) void vtime_gen_account_irq_exit(struct task_struct *tsk) { write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); + if (vtime_delta(tsk)) + __vtime_account_system(tsk); if (context_tracking_in_user()) tsk->vtime_snap_whence = VTIME_USER; write_seqcount_end(&tsk->vtime_seqcount); @@ -718,16 +721,19 @@ void vtime_account_user(struct task_struct *tsk) cputime_t delta_cpu; write_seqcount_begin(&tsk->vtime_seqcount); - delta_cpu = get_vtime_delta(tsk); tsk->vtime_snap_whence = VTIME_SYS; - account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); + if (vtime_delta(tsk)) { + delta_cpu = get_vtime_delta(tsk); + account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); + } write_seqcount_end(&tsk->vtime_seqcount); } void vtime_user_enter(struct task_struct *tsk) { write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); + if (vtime_delta(tsk)) + __vtime_account_system(tsk); tsk->vtime_snap_whence = VTIME_USER; write_seqcount_end(&tsk->vtime_seqcount); } @@ -742,7 +748,8 @@ void vtime_guest_enter(struct task_struct *tsk) * that can thus safely catch up with a tickless delta. */ write_seqcount_begin(&tsk->vtime_seqcount); - __vtime_account_system(tsk); + if (vtime_delta(tsk)) + __vtime_account_system(tsk); current->flags |= PF_VCPU; write_seqcount_end(&tsk->vtime_seqcount); } @@ -772,7 +779,7 @@ void arch_vtime_task_switch(struct task_struct *prev) write_seqcount_begin(¤t->vtime_seqcount); current->vtime_snap_whence = VTIME_SYS; - current->vtime_snap = sched_clock_cpu(smp_processor_id()); + current->vtime_snap = jiffies; write_seqcount_end(¤t->vtime_seqcount); } @@ -783,7 +790,7 @@ void vtime_init_idle(struct task_struct *t, int cpu) local_irq_save(flags); write_seqcount_begin(&t->vtime_seqcount); t->vtime_snap_whence = VTIME_SYS; - t->vtime_snap = sched_clock_cpu(cpu); + t->vtime_snap = jiffies; write_seqcount_end(&t->vtime_seqcount); local_irq_restore(flags); } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index cd64c979d0e1..c7a036facbe1 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -352,7 +352,15 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - WARN_ON(!dl_se->dl_new || dl_se->dl_throttled); + WARN_ON(dl_time_before(rq_clock(rq), dl_se->deadline)); + + /* + * We are racing with the deadline timer. So, do nothing because + * the deadline timer handler will take care of properly recharging + * the runtime and postponing the deadline + */ + if (dl_se->dl_throttled) + return; /* * We use the regular wall clock time to set deadlines in the @@ -361,7 +369,6 @@ static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se, */ dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; dl_se->runtime = pi_se->dl_runtime; - dl_se->dl_new = 0; } /* @@ -399,6 +406,9 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, dl_se->runtime = pi_se->dl_runtime; } + if (dl_se->dl_yielded && dl_se->runtime > 0) + dl_se->runtime = 0; + /* * We keep moving the deadline away until we get some * available runtime for the entity. This ensures correct @@ -420,7 +430,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * entity. */ if (dl_time_before(dl_se->deadline, rq_clock(rq))) { - printk_deferred_once("sched: DL replenish lagged to much\n"); + printk_deferred_once("sched: DL replenish lagged too much\n"); dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; dl_se->runtime = pi_se->dl_runtime; } @@ -500,15 +510,6 @@ static void update_dl_entity(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - /* - * The arrival of a new instance needs special treatment, i.e., - * the actual scheduling parameters have to be "renewed". - */ - if (dl_se->dl_new) { - setup_new_dl_entity(dl_se, pi_se); - return; - } - if (dl_time_before(dl_se->deadline, rq_clock(rq)) || dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) { dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; @@ -605,16 +606,6 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) } /* - * This is possible if switched_from_dl() raced against a running - * callback that took the above !dl_task() path and we've since then - * switched back into SCHED_DEADLINE. - * - * There's nothing to do except drop our task reference. - */ - if (dl_se->dl_new) - goto unlock; - - /* * The task might have been boosted by someone else and might be in the * boosting/deboosting path, its not throttled. */ @@ -735,8 +726,11 @@ static void update_curr_dl(struct rq *rq) * approach need further study. */ delta_exec = rq_clock_task(rq) - curr->se.exec_start; - if (unlikely((s64)delta_exec <= 0)) + if (unlikely((s64)delta_exec <= 0)) { + if (unlikely(dl_se->dl_yielded)) + goto throttle; return; + } schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec)); @@ -749,8 +743,10 @@ static void update_curr_dl(struct rq *rq) sched_rt_avg_update(rq, delta_exec); - dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec; - if (dl_runtime_exceeded(dl_se)) { + dl_se->runtime -= delta_exec; + +throttle: + if (dl_runtime_exceeded(dl_se) || dl_se->dl_yielded) { dl_se->dl_throttled = 1; __dequeue_task_dl(rq, curr, 0); if (unlikely(dl_se->dl_boosted || !start_dl_timer(curr))) @@ -917,7 +913,7 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se, * parameters of the task might need updating. Otherwise, * we want a replenishment of its runtime. */ - if (dl_se->dl_new || flags & ENQUEUE_WAKEUP) + if (flags & ENQUEUE_WAKEUP) update_dl_entity(dl_se, pi_se); else if (flags & ENQUEUE_REPLENISH) replenish_dl_entity(dl_se, pi_se); @@ -994,18 +990,14 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) */ static void yield_task_dl(struct rq *rq) { - struct task_struct *p = rq->curr; - /* * We make the task go to sleep until its current deadline by * forcing its runtime to zero. This way, update_curr_dl() stops * it and the bandwidth timer will wake it up and will give it * new scheduling parameters (thanks to dl_yielded=1). */ - if (p->dl.runtime > 0) { - rq->curr->dl.dl_yielded = 1; - p->dl.runtime = 0; - } + rq->curr->dl.dl_yielded = 1; + update_rq_clock(rq); update_curr_dl(rq); /* @@ -1722,6 +1714,9 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p) */ static void switched_to_dl(struct rq *rq, struct task_struct *p) { + if (dl_time_before(p->dl.deadline, rq_clock(rq))) + setup_new_dl_entity(&p->dl, &p->dl); + if (task_on_rq_queued(p) && rq->curr != p) { #ifdef CONFIG_SMP if (p->nr_cpus_allowed > 1 && rq->dl.overloaded) @@ -1768,8 +1763,7 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p, */ resched_curr(rq); #endif /* CONFIG_SMP */ - } else - switched_to_dl(rq, p); + } } const struct sched_class dl_sched_class = { diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 641511771ae6..4fbc3bd5ff60 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -16,6 +16,7 @@ #include <linux/kallsyms.h> #include <linux/utsname.h> #include <linux/mempolicy.h> +#include <linux/debugfs.h> #include "sched.h" @@ -58,6 +59,309 @@ static unsigned long nsec_low(unsigned long long nsec) #define SPLIT_NS(x) nsec_high(x), nsec_low(x) +#define SCHED_FEAT(name, enabled) \ + #name , + +static const char * const sched_feat_names[] = { +#include "features.h" +}; + +#undef SCHED_FEAT + +static int sched_feat_show(struct seq_file *m, void *v) +{ + int i; + + for (i = 0; i < __SCHED_FEAT_NR; i++) { + if (!(sysctl_sched_features & (1UL << i))) + seq_puts(m, "NO_"); + seq_printf(m, "%s ", sched_feat_names[i]); + } + seq_puts(m, "\n"); + + return 0; +} + +#ifdef HAVE_JUMP_LABEL + +#define jump_label_key__true STATIC_KEY_INIT_TRUE +#define jump_label_key__false STATIC_KEY_INIT_FALSE + +#define SCHED_FEAT(name, enabled) \ + jump_label_key__##enabled , + +struct static_key sched_feat_keys[__SCHED_FEAT_NR] = { +#include "features.h" +}; + +#undef SCHED_FEAT + +static void sched_feat_disable(int i) +{ + static_key_disable(&sched_feat_keys[i]); +} + +static void sched_feat_enable(int i) +{ + static_key_enable(&sched_feat_keys[i]); +} +#else +static void sched_feat_disable(int i) { }; +static void sched_feat_enable(int i) { }; +#endif /* HAVE_JUMP_LABEL */ + +static int sched_feat_set(char *cmp) +{ + int i; + int neg = 0; + + if (strncmp(cmp, "NO_", 3) == 0) { + neg = 1; + cmp += 3; + } + + for (i = 0; i < __SCHED_FEAT_NR; i++) { + if (strcmp(cmp, sched_feat_names[i]) == 0) { + if (neg) { + sysctl_sched_features &= ~(1UL << i); + sched_feat_disable(i); + } else { + sysctl_sched_features |= (1UL << i); + sched_feat_enable(i); + } + break; + } + } + + return i; +} + +static ssize_t +sched_feat_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + char *cmp; + int i; + struct inode *inode; + + if (cnt > 63) + cnt = 63; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + cmp = strstrip(buf); + + /* Ensure the static_key remains in a consistent state */ + inode = file_inode(filp); + inode_lock(inode); + i = sched_feat_set(cmp); + inode_unlock(inode); + if (i == __SCHED_FEAT_NR) + return -EINVAL; + + *ppos += cnt; + + return cnt; +} + +static int sched_feat_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, sched_feat_show, NULL); +} + +static const struct file_operations sched_feat_fops = { + .open = sched_feat_open, + .write = sched_feat_write, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static __init int sched_init_debug(void) +{ + debugfs_create_file("sched_features", 0644, NULL, NULL, + &sched_feat_fops); + + return 0; +} +late_initcall(sched_init_debug); + +#ifdef CONFIG_SMP + +#ifdef CONFIG_SYSCTL + +static struct ctl_table sd_ctl_dir[] = { + { + .procname = "sched_domain", + .mode = 0555, + }, + {} +}; + +static struct ctl_table sd_ctl_root[] = { + { + .procname = "kernel", + .mode = 0555, + .child = sd_ctl_dir, + }, + {} +}; + +static struct ctl_table *sd_alloc_ctl_entry(int n) +{ + struct ctl_table *entry = + kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); + + return entry; +} + +static void sd_free_ctl_entry(struct ctl_table **tablep) +{ + struct ctl_table *entry; + + /* + * In the intermediate directories, both the child directory and + * procname are dynamically allocated and could fail but the mode + * will always be set. In the lowest directory the names are + * static strings and all have proc handlers. + */ + for (entry = *tablep; entry->mode; entry++) { + if (entry->child) + sd_free_ctl_entry(&entry->child); + if (entry->proc_handler == NULL) + kfree(entry->procname); + } + + kfree(*tablep); + *tablep = NULL; +} + +static int min_load_idx = 0; +static int max_load_idx = CPU_LOAD_IDX_MAX-1; + +static void +set_table_entry(struct ctl_table *entry, + const char *procname, void *data, int maxlen, + umode_t mode, proc_handler *proc_handler, + bool load_idx) +{ + entry->procname = procname; + entry->data = data; + entry->maxlen = maxlen; + entry->mode = mode; + entry->proc_handler = proc_handler; + + if (load_idx) { + entry->extra1 = &min_load_idx; + entry->extra2 = &max_load_idx; + } +} + +static struct ctl_table * +sd_alloc_ctl_domain_table(struct sched_domain *sd) +{ + struct ctl_table *table = sd_alloc_ctl_entry(14); + + if (table == NULL) + return NULL; + + set_table_entry(&table[0], "min_interval", &sd->min_interval, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[1], "max_interval", &sd->max_interval, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[2], "busy_idx", &sd->busy_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[3], "idle_idx", &sd->idle_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[5], "wake_idx", &sd->wake_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[7], "busy_factor", &sd->busy_factor, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[9], "cache_nice_tries", + &sd->cache_nice_tries, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[10], "flags", &sd->flags, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[11], "max_newidle_lb_cost", + &sd->max_newidle_lb_cost, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[12], "name", sd->name, + CORENAME_MAX_SIZE, 0444, proc_dostring, false); + /* &table[13] is terminator */ + + return table; +} + +static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu) +{ + struct ctl_table *entry, *table; + struct sched_domain *sd; + int domain_num = 0, i; + char buf[32]; + + for_each_domain(cpu, sd) + domain_num++; + entry = table = sd_alloc_ctl_entry(domain_num + 1); + if (table == NULL) + return NULL; + + i = 0; + for_each_domain(cpu, sd) { + snprintf(buf, 32, "domain%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_domain_table(sd); + entry++; + i++; + } + return table; +} + +static struct ctl_table_header *sd_sysctl_header; +void register_sched_domain_sysctl(void) +{ + int i, cpu_num = num_possible_cpus(); + struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); + char buf[32]; + + WARN_ON(sd_ctl_dir[0].child); + sd_ctl_dir[0].child = entry; + + if (entry == NULL) + return; + + for_each_possible_cpu(i) { + snprintf(buf, 32, "cpu%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_cpu_table(i); + entry++; + } + + WARN_ON(sd_sysctl_header); + sd_sysctl_header = register_sysctl_table(sd_ctl_root); +} + +/* may be called multiple times per register */ +void unregister_sched_domain_sysctl(void) +{ + unregister_sysctl_table(sd_sysctl_header); + sd_sysctl_header = NULL; + if (sd_ctl_dir[0].child) + sd_free_ctl_entry(&sd_ctl_dir[0].child); +} +#endif /* CONFIG_SYSCTL */ +#endif /* CONFIG_SMP */ + #ifdef CONFIG_FAIR_GROUP_SCHED static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg) { @@ -75,16 +379,18 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group PN(se->vruntime); PN(se->sum_exec_runtime); #ifdef CONFIG_SCHEDSTATS - PN(se->statistics.wait_start); - PN(se->statistics.sleep_start); - PN(se->statistics.block_start); - PN(se->statistics.sleep_max); - PN(se->statistics.block_max); - PN(se->statistics.exec_max); - PN(se->statistics.slice_max); - PN(se->statistics.wait_max); - PN(se->statistics.wait_sum); - P(se->statistics.wait_count); + if (schedstat_enabled()) { + PN(se->statistics.wait_start); + PN(se->statistics.sleep_start); + PN(se->statistics.block_start); + PN(se->statistics.sleep_max); + PN(se->statistics.block_max); + PN(se->statistics.exec_max); + PN(se->statistics.slice_max); + PN(se->statistics.wait_max); + PN(se->statistics.wait_sum); + P(se->statistics.wait_count); + } #endif P(se->load.weight); #ifdef CONFIG_SMP @@ -122,10 +428,12 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) (long long)(p->nvcsw + p->nivcsw), p->prio); #ifdef CONFIG_SCHEDSTATS - SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", - SPLIT_NS(p->se.statistics.wait_sum), - SPLIT_NS(p->se.sum_exec_runtime), - SPLIT_NS(p->se.statistics.sum_sleep_runtime)); + if (schedstat_enabled()) { + SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", + SPLIT_NS(p->se.statistics.wait_sum), + SPLIT_NS(p->se.sum_exec_runtime), + SPLIT_NS(p->se.statistics.sum_sleep_runtime)); + } #else SEQ_printf(m, "%9Ld.%06ld %9Ld.%06ld %9Ld.%06ld", 0LL, 0L, @@ -258,8 +566,17 @@ void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq) { + struct dl_bw *dl_bw; + SEQ_printf(m, "\ndl_rq[%d]:\n", cpu); SEQ_printf(m, " .%-30s: %ld\n", "dl_nr_running", dl_rq->dl_nr_running); +#ifdef CONFIG_SMP + dl_bw = &cpu_rq(cpu)->rd->dl_bw; +#else + dl_bw = &dl_rq->dl_bw; +#endif + SEQ_printf(m, " .%-30s: %lld\n", "dl_bw->bw", dl_bw->bw); + SEQ_printf(m, " .%-30s: %lld\n", "dl_bw->total_bw", dl_bw->total_bw); } extern __read_mostly int sched_clock_running; @@ -313,17 +630,18 @@ do { \ #define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n); #define P64(n) SEQ_printf(m, " .%-30s: %Ld\n", #n, rq->n); - P(yld_count); - - P(sched_count); - P(sched_goidle); #ifdef CONFIG_SMP P64(avg_idle); P64(max_idle_balance_cost); #endif - P(ttwu_count); - P(ttwu_local); + if (schedstat_enabled()) { + P(yld_count); + P(sched_count); + P(sched_goidle); + P(ttwu_count); + P(ttwu_local); + } #undef P #undef P64 @@ -569,38 +887,39 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) nr_switches = p->nvcsw + p->nivcsw; #ifdef CONFIG_SCHEDSTATS - PN(se.statistics.sum_sleep_runtime); - PN(se.statistics.wait_start); - PN(se.statistics.sleep_start); - PN(se.statistics.block_start); - PN(se.statistics.sleep_max); - PN(se.statistics.block_max); - PN(se.statistics.exec_max); - PN(se.statistics.slice_max); - PN(se.statistics.wait_max); - PN(se.statistics.wait_sum); - P(se.statistics.wait_count); - PN(se.statistics.iowait_sum); - P(se.statistics.iowait_count); P(se.nr_migrations); - P(se.statistics.nr_migrations_cold); - P(se.statistics.nr_failed_migrations_affine); - P(se.statistics.nr_failed_migrations_running); - P(se.statistics.nr_failed_migrations_hot); - P(se.statistics.nr_forced_migrations); - P(se.statistics.nr_wakeups); - P(se.statistics.nr_wakeups_sync); - P(se.statistics.nr_wakeups_migrate); - P(se.statistics.nr_wakeups_local); - P(se.statistics.nr_wakeups_remote); - P(se.statistics.nr_wakeups_affine); - P(se.statistics.nr_wakeups_affine_attempts); - P(se.statistics.nr_wakeups_passive); - P(se.statistics.nr_wakeups_idle); - { + if (schedstat_enabled()) { u64 avg_atom, avg_per_cpu; + PN(se.statistics.sum_sleep_runtime); + PN(se.statistics.wait_start); + PN(se.statistics.sleep_start); + PN(se.statistics.block_start); + PN(se.statistics.sleep_max); + PN(se.statistics.block_max); + PN(se.statistics.exec_max); + PN(se.statistics.slice_max); + PN(se.statistics.wait_max); + PN(se.statistics.wait_sum); + P(se.statistics.wait_count); + PN(se.statistics.iowait_sum); + P(se.statistics.iowait_count); + P(se.statistics.nr_migrations_cold); + P(se.statistics.nr_failed_migrations_affine); + P(se.statistics.nr_failed_migrations_running); + P(se.statistics.nr_failed_migrations_hot); + P(se.statistics.nr_forced_migrations); + P(se.statistics.nr_wakeups); + P(se.statistics.nr_wakeups_sync); + P(se.statistics.nr_wakeups_migrate); + P(se.statistics.nr_wakeups_local); + P(se.statistics.nr_wakeups_remote); + P(se.statistics.nr_wakeups_affine); + P(se.statistics.nr_wakeups_affine_attempts); + P(se.statistics.nr_wakeups_passive); + P(se.statistics.nr_wakeups_idle); + avg_atom = p->se.sum_exec_runtime; if (nr_switches) avg_atom = div64_ul(avg_atom, nr_switches); diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1926606ece80..33130529e9b5 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -20,8 +20,8 @@ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra */ -#include <linux/latencytop.h> #include <linux/sched.h> +#include <linux/latencytop.h> #include <linux/cpumask.h> #include <linux/cpuidle.h> #include <linux/slab.h> @@ -755,7 +755,9 @@ static void update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) { struct task_struct *p; - u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start; + u64 delta; + + delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start; if (entity_is_task(se)) { p = task_of(se); @@ -776,22 +778,12 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) se->statistics.wait_sum += delta; se->statistics.wait_start = 0; } -#else -static inline void -update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ -} - -static inline void -update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ -} -#endif /* * Task is being enqueued - update stats: */ -static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) +static inline void +update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) { /* * Are we enqueueing a waiting task? (for current tasks @@ -802,7 +794,7 @@ static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) } static inline void -update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) +update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { /* * Mark the end of the wait period if dequeueing a @@ -810,8 +802,41 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) */ if (se != cfs_rq->curr) update_stats_wait_end(cfs_rq, se); + + if (flags & DEQUEUE_SLEEP) { + if (entity_is_task(se)) { + struct task_struct *tsk = task_of(se); + + if (tsk->state & TASK_INTERRUPTIBLE) + se->statistics.sleep_start = rq_clock(rq_of(cfs_rq)); + if (tsk->state & TASK_UNINTERRUPTIBLE) + se->statistics.block_start = rq_clock(rq_of(cfs_rq)); + } + } + +} +#else +static inline void +update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ +} + +static inline void +update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ } +static inline void +update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ +} + +static inline void +update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) +{ +} +#endif + /* * We are picking a new current task - update its stats: */ @@ -907,10 +932,11 @@ struct numa_group { spinlock_t lock; /* nr_tasks, tasks */ int nr_tasks; pid_t gid; + int active_nodes; struct rcu_head rcu; - nodemask_t active_nodes; unsigned long total_faults; + unsigned long max_faults_cpu; /* * Faults_cpu is used to decide whether memory should move * towards the CPU. As a consequence, these stats are weighted @@ -969,6 +995,18 @@ static inline unsigned long group_faults_cpu(struct numa_group *group, int nid) group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)]; } +/* + * A node triggering more than 1/3 as many NUMA faults as the maximum is + * considered part of a numa group's pseudo-interleaving set. Migrations + * between these nodes are slowed down, to allow things to settle down. + */ +#define ACTIVE_NODE_FRACTION 3 + +static bool numa_is_active_node(int nid, struct numa_group *ng) +{ + return group_faults_cpu(ng, nid) * ACTIVE_NODE_FRACTION > ng->max_faults_cpu; +} + /* Handle placement on systems where not all nodes are directly connected. */ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, int maxdist, bool task) @@ -1118,27 +1156,23 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, return true; /* - * Do not migrate if the destination is not a node that - * is actively used by this numa group. - */ - if (!node_isset(dst_nid, ng->active_nodes)) - return false; - - /* - * Source is a node that is not actively used by this - * numa group, while the destination is. Migrate. + * Destination node is much more heavily used than the source + * node? Allow migration. */ - if (!node_isset(src_nid, ng->active_nodes)) + if (group_faults_cpu(ng, dst_nid) > group_faults_cpu(ng, src_nid) * + ACTIVE_NODE_FRACTION) return true; /* - * Both source and destination are nodes in active - * use by this numa group. Maximize memory bandwidth - * by migrating from more heavily used groups, to less - * heavily used ones, spreading the load around. - * Use a 1/4 hysteresis to avoid spurious page movement. + * Distribute memory according to CPU & memory use on each node, + * with 3/4 hysteresis to avoid unnecessary memory migrations: + * + * faults_cpu(dst) 3 faults_cpu(src) + * --------------- * - > --------------- + * faults_mem(dst) 4 faults_mem(src) */ - return group_faults(p, dst_nid) < (group_faults(p, src_nid) * 3 / 4); + return group_faults_cpu(ng, dst_nid) * group_faults(p, src_nid) * 3 > + group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4; } static unsigned long weighted_cpuload(const int cpu); @@ -1220,8 +1254,6 @@ static void task_numa_assign(struct task_numa_env *env, { if (env->best_task) put_task_struct(env->best_task); - if (p) - get_task_struct(p); env->best_task = p; env->best_imp = imp; @@ -1289,20 +1321,30 @@ static void task_numa_compare(struct task_numa_env *env, long imp = env->p->numa_group ? groupimp : taskimp; long moveimp = imp; int dist = env->dist; + bool assigned = false; rcu_read_lock(); raw_spin_lock_irq(&dst_rq->lock); cur = dst_rq->curr; /* - * No need to move the exiting task, and this ensures that ->curr - * wasn't reaped and thus get_task_struct() in task_numa_assign() - * is safe under RCU read lock. - * Note that rcu_read_lock() itself can't protect from the final - * put_task_struct() after the last schedule(). + * No need to move the exiting task or idle task. */ if ((cur->flags & PF_EXITING) || is_idle_task(cur)) cur = NULL; + else { + /* + * The task_struct must be protected here to protect the + * p->numa_faults access in the task_weight since the + * numa_faults could already be freed in the following path: + * finish_task_switch() + * --> put_task_struct() + * --> __put_task_struct() + * --> task_numa_free() + */ + get_task_struct(cur); + } + raw_spin_unlock_irq(&dst_rq->lock); /* @@ -1386,6 +1428,7 @@ balance: */ if (!load_too_imbalanced(src_load, dst_load, env)) { imp = moveimp - 1; + put_task_struct(cur); cur = NULL; goto assign; } @@ -1411,9 +1454,16 @@ balance: env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu); assign: + assigned = true; task_numa_assign(env, cur, imp); unlock: rcu_read_unlock(); + /* + * The dst_rq->curr isn't assigned. The protection for task_struct is + * finished. + */ + if (cur && !assigned) + put_task_struct(cur); } static void task_numa_find_cpu(struct task_numa_env *env, @@ -1468,7 +1518,7 @@ static int task_numa_migrate(struct task_struct *p) .best_task = NULL, .best_imp = 0, - .best_cpu = -1 + .best_cpu = -1, }; struct sched_domain *sd; unsigned long taskweight, groupweight; @@ -1520,8 +1570,7 @@ static int task_numa_migrate(struct task_struct *p) * multiple NUMA nodes; in order to better consolidate the group, * we need to check other locations. */ - if (env.best_cpu == -1 || (p->numa_group && - nodes_weight(p->numa_group->active_nodes) > 1)) { + if (env.best_cpu == -1 || (p->numa_group && p->numa_group->active_nodes > 1)) { for_each_online_node(nid) { if (nid == env.src_nid || nid == p->numa_preferred_nid) continue; @@ -1556,12 +1605,14 @@ static int task_numa_migrate(struct task_struct *p) * trying for a better one later. Do not set the preferred node here. */ if (p->numa_group) { + struct numa_group *ng = p->numa_group; + if (env.best_cpu == -1) nid = env.src_nid; else nid = env.dst_nid; - if (node_isset(nid, p->numa_group->active_nodes)) + if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng)) sched_setnuma(p, env.dst_nid); } @@ -1611,20 +1662,15 @@ static void numa_migrate_preferred(struct task_struct *p) } /* - * Find the nodes on which the workload is actively running. We do this by + * Find out how many nodes on the workload is actively running on. Do this by * tracking the nodes from which NUMA hinting faults are triggered. This can * be different from the set of nodes where the workload's memory is currently * located. - * - * The bitmask is used to make smarter decisions on when to do NUMA page - * migrations, To prevent flip-flopping, and excessive page migrations, nodes - * are added when they cause over 6/16 of the maximum number of faults, but - * only removed when they drop below 3/16. */ -static void update_numa_active_node_mask(struct numa_group *numa_group) +static void numa_group_count_active_nodes(struct numa_group *numa_group) { unsigned long faults, max_faults = 0; - int nid; + int nid, active_nodes = 0; for_each_online_node(nid) { faults = group_faults_cpu(numa_group, nid); @@ -1634,12 +1680,12 @@ static void update_numa_active_node_mask(struct numa_group *numa_group) for_each_online_node(nid) { faults = group_faults_cpu(numa_group, nid); - if (!node_isset(nid, numa_group->active_nodes)) { - if (faults > max_faults * 6 / 16) - node_set(nid, numa_group->active_nodes); - } else if (faults < max_faults * 3 / 16) - node_clear(nid, numa_group->active_nodes); + if (faults * ACTIVE_NODE_FRACTION > max_faults) + active_nodes++; } + + numa_group->max_faults_cpu = max_faults; + numa_group->active_nodes = active_nodes; } /* @@ -1930,7 +1976,7 @@ static void task_numa_placement(struct task_struct *p) update_task_scan_period(p, fault_types[0], fault_types[1]); if (p->numa_group) { - update_numa_active_node_mask(p->numa_group); + numa_group_count_active_nodes(p->numa_group); spin_unlock_irq(group_lock); max_nid = preferred_group_nid(p, max_group_nid); } @@ -1974,14 +2020,14 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, return; atomic_set(&grp->refcount, 1); + grp->active_nodes = 1; + grp->max_faults_cpu = 0; spin_lock_init(&grp->lock); grp->gid = p->pid; /* Second half of the array tracks nids where faults happen */ grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES * nr_node_ids; - node_set(task_node(current), grp->active_nodes); - for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) grp->faults[i] = p->numa_faults[i]; @@ -2095,6 +2141,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) bool migrated = flags & TNF_MIGRATED; int cpu_node = task_node(current); int local = !!(flags & TNF_FAULT_LOCAL); + struct numa_group *ng; int priv; if (!static_branch_likely(&sched_numa_balancing)) @@ -2135,9 +2182,10 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) * actively using should be counted as local. This allows the * scan rate to slow down when a workload has settled down. */ - if (!priv && !local && p->numa_group && - node_isset(cpu_node, p->numa_group->active_nodes) && - node_isset(mem_node, p->numa_group->active_nodes)) + ng = p->numa_group; + if (!priv && !local && ng && ng->active_nodes > 1 && + numa_is_active_node(cpu_node, ng) && + numa_is_active_node(mem_node, ng)) local = 1; task_numa_placement(p); @@ -3086,6 +3134,26 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) static void check_enqueue_throttle(struct cfs_rq *cfs_rq); +static inline void check_schedstat_required(void) +{ +#ifdef CONFIG_SCHEDSTATS + if (schedstat_enabled()) + return; + + /* Force schedstat enabled if a dependent tracepoint is active */ + if (trace_sched_stat_wait_enabled() || + trace_sched_stat_sleep_enabled() || + trace_sched_stat_iowait_enabled() || + trace_sched_stat_blocked_enabled() || + trace_sched_stat_runtime_enabled()) { + pr_warn_once("Scheduler tracepoints stat_sleep, stat_iowait, " + "stat_blocked and stat_runtime require the " + "kernel parameter schedstats=enabled or " + "kernel.sched_schedstats=1\n"); + } +#endif +} + static void enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { @@ -3106,11 +3174,15 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (flags & ENQUEUE_WAKEUP) { place_entity(cfs_rq, se, 0); - enqueue_sleeper(cfs_rq, se); + if (schedstat_enabled()) + enqueue_sleeper(cfs_rq, se); } - update_stats_enqueue(cfs_rq, se); - check_spread(cfs_rq, se); + check_schedstat_required(); + if (schedstat_enabled()) { + update_stats_enqueue(cfs_rq, se); + check_spread(cfs_rq, se); + } if (se != cfs_rq->curr) __enqueue_entity(cfs_rq, se); se->on_rq = 1; @@ -3177,19 +3249,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) update_curr(cfs_rq); dequeue_entity_load_avg(cfs_rq, se); - update_stats_dequeue(cfs_rq, se); - if (flags & DEQUEUE_SLEEP) { -#ifdef CONFIG_SCHEDSTATS - if (entity_is_task(se)) { - struct task_struct *tsk = task_of(se); - - if (tsk->state & TASK_INTERRUPTIBLE) - se->statistics.sleep_start = rq_clock(rq_of(cfs_rq)); - if (tsk->state & TASK_UNINTERRUPTIBLE) - se->statistics.block_start = rq_clock(rq_of(cfs_rq)); - } -#endif - } + if (schedstat_enabled()) + update_stats_dequeue(cfs_rq, se, flags); clear_buddies(cfs_rq, se); @@ -3263,7 +3324,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) * a CPU. So account for the time it spent waiting on the * runqueue. */ - update_stats_wait_end(cfs_rq, se); + if (schedstat_enabled()) + update_stats_wait_end(cfs_rq, se); __dequeue_entity(cfs_rq, se); update_load_avg(se, 1); } @@ -3276,7 +3338,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) * least twice that of our own weight (i.e. dont track it * when there are only lesser-weight tasks around): */ - if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) { + if (schedstat_enabled() && rq_of(cfs_rq)->load.weight >= 2*se->load.weight) { se->statistics.slice_max = max(se->statistics.slice_max, se->sum_exec_runtime - se->prev_sum_exec_runtime); } @@ -3359,9 +3421,13 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) /* throttle cfs_rqs exceeding runtime */ check_cfs_rq_runtime(cfs_rq); - check_spread(cfs_rq, prev); + if (schedstat_enabled()) { + check_spread(cfs_rq, prev); + if (prev->on_rq) + update_stats_wait_start(cfs_rq, prev); + } + if (prev->on_rq) { - update_stats_wait_start(cfs_rq, prev); /* Put 'current' back into the tree. */ __enqueue_entity(cfs_rq, prev); /* in !on_rq case, update occurred at dequeue */ @@ -4443,9 +4509,17 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, /* scale is effectively 1 << i now, and >> i divides by scale */ - old_load = this_rq->cpu_load[i] - tickless_load; + old_load = this_rq->cpu_load[i]; old_load = decay_load_missed(old_load, pending_updates - 1, i); - old_load += tickless_load; + if (tickless_load) { + old_load -= decay_load_missed(tickless_load, pending_updates - 1, i); + /* + * old_load can never be a negative value because a + * decayed tickless_load cannot be greater than the + * original tickless_load. + */ + old_load += tickless_load; + } new_load = this_load; /* * Round up the averaging division if load is increasing. This @@ -4468,6 +4542,25 @@ static unsigned long weighted_cpuload(const int cpu) } #ifdef CONFIG_NO_HZ_COMMON +static void __update_cpu_load_nohz(struct rq *this_rq, + unsigned long curr_jiffies, + unsigned long load, + int active) +{ + unsigned long pending_updates; + + pending_updates = curr_jiffies - this_rq->last_load_update_tick; + if (pending_updates) { + this_rq->last_load_update_tick = curr_jiffies; + /* + * In the regular NOHZ case, we were idle, this means load 0. + * In the NOHZ_FULL case, we were non-idle, we should consider + * its weighted load. + */ + __update_cpu_load(this_rq, load, pending_updates, active); + } +} + /* * There is no sane way to deal with nohz on smp when using jiffies because the * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading @@ -4485,22 +4578,15 @@ static unsigned long weighted_cpuload(const int cpu) * Called from nohz_idle_balance() to update the load ratings before doing the * idle balance. */ -static void update_idle_cpu_load(struct rq *this_rq) +static void update_cpu_load_idle(struct rq *this_rq) { - unsigned long curr_jiffies = READ_ONCE(jiffies); - unsigned long load = weighted_cpuload(cpu_of(this_rq)); - unsigned long pending_updates; - /* * bail if there's load or we're actually up-to-date. */ - if (load || curr_jiffies == this_rq->last_load_update_tick) + if (weighted_cpuload(cpu_of(this_rq))) return; - pending_updates = curr_jiffies - this_rq->last_load_update_tick; - this_rq->last_load_update_tick = curr_jiffies; - - __update_cpu_load(this_rq, load, pending_updates, 0); + __update_cpu_load_nohz(this_rq, READ_ONCE(jiffies), 0, 0); } /* @@ -4511,22 +4597,12 @@ void update_cpu_load_nohz(int active) struct rq *this_rq = this_rq(); unsigned long curr_jiffies = READ_ONCE(jiffies); unsigned long load = active ? weighted_cpuload(cpu_of(this_rq)) : 0; - unsigned long pending_updates; if (curr_jiffies == this_rq->last_load_update_tick) return; raw_spin_lock(&this_rq->lock); - pending_updates = curr_jiffies - this_rq->last_load_update_tick; - if (pending_updates) { - this_rq->last_load_update_tick = curr_jiffies; - /* - * In the regular NOHZ case, we were idle, this means load 0. - * In the NOHZ_FULL case, we were non-idle, we should consider - * its weighted load. - */ - __update_cpu_load(this_rq, load, pending_updates, active); - } + __update_cpu_load_nohz(this_rq, curr_jiffies, load, active); raw_spin_unlock(&this_rq->lock); } #endif /* CONFIG_NO_HZ */ @@ -4538,7 +4614,7 @@ void update_cpu_load_active(struct rq *this_rq) { unsigned long load = weighted_cpuload(cpu_of(this_rq)); /* - * See the mess around update_idle_cpu_load() / update_cpu_load_nohz(). + * See the mess around update_cpu_load_idle() / update_cpu_load_nohz(). */ this_rq->last_load_update_tick = jiffies; __update_cpu_load(this_rq, load, 1, 1); @@ -7832,7 +7908,7 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) if (time_after_eq(jiffies, rq->next_balance)) { raw_spin_lock_irq(&rq->lock); update_rq_clock(rq); - update_idle_cpu_load(rq); + update_cpu_load_idle(rq); raw_spin_unlock_irq(&rq->lock); rebalance_domains(rq, CPU_IDLE); } @@ -8218,11 +8294,8 @@ void free_fair_sched_group(struct task_group *tg) for_each_possible_cpu(i) { if (tg->cfs_rq) kfree(tg->cfs_rq[i]); - if (tg->se) { - if (tg->se[i]) - remove_entity_load_avg(tg->se[i]); + if (tg->se) kfree(tg->se[i]); - } } kfree(tg->cfs_rq); @@ -8270,21 +8343,29 @@ err: return 0; } -void unregister_fair_sched_group(struct task_group *tg, int cpu) +void unregister_fair_sched_group(struct task_group *tg) { - struct rq *rq = cpu_rq(cpu); unsigned long flags; + struct rq *rq; + int cpu; - /* - * Only empty task groups can be destroyed; so we can speculatively - * check on_list without danger of it being re-added. - */ - if (!tg->cfs_rq[cpu]->on_list) - return; + for_each_possible_cpu(cpu) { + if (tg->se[cpu]) + remove_entity_load_avg(tg->se[cpu]); - raw_spin_lock_irqsave(&rq->lock, flags); - list_del_leaf_cfs_rq(tg->cfs_rq[cpu]); - raw_spin_unlock_irqrestore(&rq->lock, flags); + /* + * Only empty task groups can be destroyed; so we can speculatively + * check on_list without danger of it being re-added. + */ + if (!tg->cfs_rq[cpu]->on_list) + continue; + + rq = cpu_rq(cpu); + + raw_spin_lock_irqsave(&rq->lock, flags); + list_del_leaf_cfs_rq(tg->cfs_rq[cpu]); + raw_spin_unlock_irqrestore(&rq->lock, flags); + } } void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, @@ -8366,7 +8447,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) return 1; } -void unregister_fair_sched_group(struct task_group *tg, int cpu) { } +void unregister_fair_sched_group(struct task_group *tg) { } #endif /* CONFIG_FAIR_GROUP_SCHED */ diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index de0e786b2667..544a7133cbd1 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -162,7 +162,7 @@ static void cpuidle_idle_call(void) */ if (idle_should_freeze()) { entered_state = cpuidle_enter_freeze(drv, dev); - if (entered_state >= 0) { + if (entered_state > 0) { local_irq_enable(); goto exit_idle; } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 8ec86abe0ea1..562471329487 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -58,7 +58,15 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) raw_spin_lock(&rt_b->rt_runtime_lock); if (!rt_b->rt_period_active) { rt_b->rt_period_active = 1; - hrtimer_forward_now(&rt_b->rt_period_timer, rt_b->rt_period); + /* + * SCHED_DEADLINE updates the bandwidth, as a run away + * RT task with a DL task could hog a CPU. But DL does + * not reset the period. If a deadline task was running + * without an RT task running, it can cause RT tasks to + * throttle when they start up. Kick the timer right away + * to update the period. + */ + hrtimer_forward_now(&rt_b->rt_period_timer, ns_to_ktime(0)); hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED); } raw_spin_unlock(&rt_b->rt_runtime_lock); @@ -436,7 +444,7 @@ static void dequeue_top_rt_rq(struct rt_rq *rt_rq); static inline int on_rt_rq(struct sched_rt_entity *rt_se) { - return !list_empty(&rt_se->run_list); + return rt_se->on_rq; } #ifdef CONFIG_RT_GROUP_SCHED @@ -482,8 +490,8 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se) return rt_se->my_q; } -static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head); -static void dequeue_rt_entity(struct sched_rt_entity *rt_se); +static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags); +static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags); static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) { @@ -499,7 +507,7 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) if (!rt_se) enqueue_top_rt_rq(rt_rq); else if (!on_rt_rq(rt_se)) - enqueue_rt_entity(rt_se, false); + enqueue_rt_entity(rt_se, 0); if (rt_rq->highest_prio.curr < curr->prio) resched_curr(rq); @@ -516,7 +524,7 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) if (!rt_se) dequeue_top_rt_rq(rt_rq); else if (on_rt_rq(rt_se)) - dequeue_rt_entity(rt_se); + dequeue_rt_entity(rt_se, 0); } static inline int rt_rq_throttled(struct rt_rq *rt_rq) @@ -1142,12 +1150,27 @@ unsigned int rt_se_nr_running(struct sched_rt_entity *rt_se) } static inline +unsigned int rt_se_rr_nr_running(struct sched_rt_entity *rt_se) +{ + struct rt_rq *group_rq = group_rt_rq(rt_se); + struct task_struct *tsk; + + if (group_rq) + return group_rq->rr_nr_running; + + tsk = rt_task_of(rt_se); + + return (tsk->policy == SCHED_RR) ? 1 : 0; +} + +static inline void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) { int prio = rt_se_prio(rt_se); WARN_ON(!rt_prio(prio)); rt_rq->rt_nr_running += rt_se_nr_running(rt_se); + rt_rq->rr_nr_running += rt_se_rr_nr_running(rt_se); inc_rt_prio(rt_rq, prio); inc_rt_migration(rt_se, rt_rq); @@ -1160,13 +1183,37 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) WARN_ON(!rt_prio(rt_se_prio(rt_se))); WARN_ON(!rt_rq->rt_nr_running); rt_rq->rt_nr_running -= rt_se_nr_running(rt_se); + rt_rq->rr_nr_running -= rt_se_rr_nr_running(rt_se); dec_rt_prio(rt_rq, rt_se_prio(rt_se)); dec_rt_migration(rt_se, rt_rq); dec_rt_group(rt_se, rt_rq); } -static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) +/* + * Change rt_se->run_list location unless SAVE && !MOVE + * + * assumes ENQUEUE/DEQUEUE flags match + */ +static inline bool move_entity(unsigned int flags) +{ + if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) == DEQUEUE_SAVE) + return false; + + return true; +} + +static void __delist_rt_entity(struct sched_rt_entity *rt_se, struct rt_prio_array *array) +{ + list_del_init(&rt_se->run_list); + + if (list_empty(array->queue + rt_se_prio(rt_se))) + __clear_bit(rt_se_prio(rt_se), array->bitmap); + + rt_se->on_list = 0; +} + +static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rt_rq *rt_rq = rt_rq_of_se(rt_se); struct rt_prio_array *array = &rt_rq->active; @@ -1179,26 +1226,37 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) * get throttled and the current group doesn't have any other * active members. */ - if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) + if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) { + if (rt_se->on_list) + __delist_rt_entity(rt_se, array); return; + } - if (head) - list_add(&rt_se->run_list, queue); - else - list_add_tail(&rt_se->run_list, queue); - __set_bit(rt_se_prio(rt_se), array->bitmap); + if (move_entity(flags)) { + WARN_ON_ONCE(rt_se->on_list); + if (flags & ENQUEUE_HEAD) + list_add(&rt_se->run_list, queue); + else + list_add_tail(&rt_se->run_list, queue); + + __set_bit(rt_se_prio(rt_se), array->bitmap); + rt_se->on_list = 1; + } + rt_se->on_rq = 1; inc_rt_tasks(rt_se, rt_rq); } -static void __dequeue_rt_entity(struct sched_rt_entity *rt_se) +static void __dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rt_rq *rt_rq = rt_rq_of_se(rt_se); struct rt_prio_array *array = &rt_rq->active; - list_del_init(&rt_se->run_list); - if (list_empty(array->queue + rt_se_prio(rt_se))) - __clear_bit(rt_se_prio(rt_se), array->bitmap); + if (move_entity(flags)) { + WARN_ON_ONCE(!rt_se->on_list); + __delist_rt_entity(rt_se, array); + } + rt_se->on_rq = 0; dec_rt_tasks(rt_se, rt_rq); } @@ -1207,7 +1265,7 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se) * Because the prio of an upper entry depends on the lower * entries, we must remove entries top - down. */ -static void dequeue_rt_stack(struct sched_rt_entity *rt_se) +static void dequeue_rt_stack(struct sched_rt_entity *rt_se, unsigned int flags) { struct sched_rt_entity *back = NULL; @@ -1220,31 +1278,31 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se) for (rt_se = back; rt_se; rt_se = rt_se->back) { if (on_rt_rq(rt_se)) - __dequeue_rt_entity(rt_se); + __dequeue_rt_entity(rt_se, flags); } } -static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) +static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rq *rq = rq_of_rt_se(rt_se); - dequeue_rt_stack(rt_se); + dequeue_rt_stack(rt_se, flags); for_each_sched_rt_entity(rt_se) - __enqueue_rt_entity(rt_se, head); + __enqueue_rt_entity(rt_se, flags); enqueue_top_rt_rq(&rq->rt); } -static void dequeue_rt_entity(struct sched_rt_entity *rt_se) +static void dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) { struct rq *rq = rq_of_rt_se(rt_se); - dequeue_rt_stack(rt_se); + dequeue_rt_stack(rt_se, flags); for_each_sched_rt_entity(rt_se) { struct rt_rq *rt_rq = group_rt_rq(rt_se); if (rt_rq && rt_rq->rt_nr_running) - __enqueue_rt_entity(rt_se, false); + __enqueue_rt_entity(rt_se, flags); } enqueue_top_rt_rq(&rq->rt); } @@ -1260,7 +1318,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) if (flags & ENQUEUE_WAKEUP) rt_se->timeout = 0; - enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD); + enqueue_rt_entity(rt_se, flags); if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); @@ -1271,7 +1329,7 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) struct sched_rt_entity *rt_se = &p->rt; update_curr_rt(rq); - dequeue_rt_entity(rt_se); + dequeue_rt_entity(rt_se, flags); dequeue_pushable_task(rq, p); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 10f16374df7f..b2ff5a2bd6df 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -3,6 +3,7 @@ #include <linux/sched/sysctl.h> #include <linux/sched/rt.h> #include <linux/sched/deadline.h> +#include <linux/binfmts.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/stop_machine.h> @@ -313,12 +314,11 @@ extern int tg_nop(struct task_group *tg, void *data); extern void free_fair_sched_group(struct task_group *tg); extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent); -extern void unregister_fair_sched_group(struct task_group *tg, int cpu); +extern void unregister_fair_sched_group(struct task_group *tg); extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, struct sched_entity *se, int cpu, struct sched_entity *parent); extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b); -extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b); extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b); @@ -450,6 +450,7 @@ static inline int rt_bandwidth_enabled(void) struct rt_rq { struct rt_prio_array active; unsigned int rt_nr_running; + unsigned int rr_nr_running; #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED struct { int curr; /* highest queued rt task prio */ @@ -909,6 +910,18 @@ static inline unsigned int group_first_cpu(struct sched_group *group) extern int group_balance_cpu(struct sched_group *sg); +#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) +void register_sched_domain_sysctl(void); +void unregister_sched_domain_sysctl(void); +#else +static inline void register_sched_domain_sysctl(void) +{ +} +static inline void unregister_sched_domain_sysctl(void) +{ +} +#endif + #else static inline void sched_ttwu_pending(void) { } @@ -1022,6 +1035,7 @@ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR]; #endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */ extern struct static_key_false sched_numa_balancing; +extern struct static_key_false sched_schedstats; static inline u64 global_rt_period(void) { @@ -1130,18 +1144,40 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) extern const int sched_prio_to_weight[40]; extern const u32 sched_prio_to_wmult[40]; +/* + * {de,en}queue flags: + * + * DEQUEUE_SLEEP - task is no longer runnable + * ENQUEUE_WAKEUP - task just became runnable + * + * SAVE/RESTORE - an otherwise spurious dequeue/enqueue, done to ensure tasks + * are in a known state which allows modification. Such pairs + * should preserve as much state as possible. + * + * MOVE - paired with SAVE/RESTORE, explicitly does not preserve the location + * in the runqueue. + * + * ENQUEUE_HEAD - place at front of runqueue (tail if not specified) + * ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline) + * ENQUEUE_WAKING - sched_class::task_waking was called + * + */ + +#define DEQUEUE_SLEEP 0x01 +#define DEQUEUE_SAVE 0x02 /* matches ENQUEUE_RESTORE */ +#define DEQUEUE_MOVE 0x04 /* matches ENQUEUE_MOVE */ + #define ENQUEUE_WAKEUP 0x01 -#define ENQUEUE_HEAD 0x02 +#define ENQUEUE_RESTORE 0x02 +#define ENQUEUE_MOVE 0x04 + +#define ENQUEUE_HEAD 0x08 +#define ENQUEUE_REPLENISH 0x10 #ifdef CONFIG_SMP -#define ENQUEUE_WAKING 0x04 /* sched_class::task_waking was called */ +#define ENQUEUE_WAKING 0x20 #else #define ENQUEUE_WAKING 0x00 #endif -#define ENQUEUE_REPLENISH 0x08 -#define ENQUEUE_RESTORE 0x10 - -#define DEQUEUE_SLEEP 0x01 -#define DEQUEUE_SAVE 0x02 #define RETRY_TASK ((void *)-1UL) @@ -1278,6 +1314,35 @@ unsigned long to_ratio(u64 period, u64 runtime); extern void init_entity_runnable_average(struct sched_entity *se); +#ifdef CONFIG_NO_HZ_FULL +extern bool sched_can_stop_tick(struct rq *rq); + +/* + * Tick may be needed by tasks in the runqueue depending on their policy and + * requirements. If tick is needed, lets send the target an IPI to kick it out of + * nohz mode if necessary. + */ +static inline void sched_update_tick_dependency(struct rq *rq) +{ + int cpu; + + if (!tick_nohz_full_enabled()) + return; + + cpu = cpu_of(rq); + + if (!tick_nohz_full_cpu(cpu)) + return; + + if (sched_can_stop_tick(rq)) + tick_nohz_dep_clear_cpu(cpu, TICK_DEP_BIT_SCHED); + else + tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED); +} +#else +static inline void sched_update_tick_dependency(struct rq *rq) { } +#endif + static inline void add_nr_running(struct rq *rq, unsigned count) { unsigned prev_nr = rq->nr_running; @@ -1289,26 +1354,16 @@ static inline void add_nr_running(struct rq *rq, unsigned count) if (!rq->rd->overload) rq->rd->overload = true; #endif - -#ifdef CONFIG_NO_HZ_FULL - if (tick_nohz_full_cpu(rq->cpu)) { - /* - * Tick is needed if more than one task runs on a CPU. - * Send the target an IPI to kick it out of nohz mode. - * - * We assume that IPI implies full memory barrier and the - * new value of rq->nr_running is visible on reception - * from the target. - */ - tick_nohz_full_kick_cpu(rq->cpu); - } -#endif } + + sched_update_tick_dependency(rq); } static inline void sub_nr_running(struct rq *rq, unsigned count) { rq->nr_running -= count; + /* Check if we still need preemption */ + sched_update_tick_dependency(rq); } static inline void rq_last_tick_reset(struct rq *rq) diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index b0fbc7632de5..70b3b6a20fb0 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -29,9 +29,10 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) if (rq) rq->rq_sched_info.run_delay += delta; } -# define schedstat_inc(rq, field) do { (rq)->field++; } while (0) -# define schedstat_add(rq, field, amt) do { (rq)->field += (amt); } while (0) -# define schedstat_set(var, val) do { var = (val); } while (0) +# define schedstat_enabled() static_branch_unlikely(&sched_schedstats) +# define schedstat_inc(rq, field) do { if (schedstat_enabled()) { (rq)->field++; } } while (0) +# define schedstat_add(rq, field, amt) do { if (schedstat_enabled()) { (rq)->field += (amt); } } while (0) +# define schedstat_set(var, val) do { if (schedstat_enabled()) { var = (val); } } while (0) #else /* !CONFIG_SCHEDSTATS */ static inline void rq_sched_info_arrive(struct rq *rq, unsigned long long delta) @@ -42,6 +43,7 @@ rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) static inline void rq_sched_info_depart(struct rq *rq, unsigned long long delta) {} +# define schedstat_enabled() 0 # define schedstat_inc(rq, field) do { } while (0) # define schedstat_add(rq, field, amt) do { } while (0) # define schedstat_set(var, val) do { } while (0) diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c new file mode 100644 index 000000000000..82f0dff90030 --- /dev/null +++ b/kernel/sched/swait.c @@ -0,0 +1,123 @@ +#include <linux/sched.h> +#include <linux/swait.h> + +void __init_swait_queue_head(struct swait_queue_head *q, const char *name, + struct lock_class_key *key) +{ + raw_spin_lock_init(&q->lock); + lockdep_set_class_and_name(&q->lock, key, name); + INIT_LIST_HEAD(&q->task_list); +} +EXPORT_SYMBOL(__init_swait_queue_head); + +/* + * The thing about the wake_up_state() return value; I think we can ignore it. + * + * If for some reason it would return 0, that means the previously waiting + * task is already running, so it will observe condition true (or has already). + */ +void swake_up_locked(struct swait_queue_head *q) +{ + struct swait_queue *curr; + + if (list_empty(&q->task_list)) + return; + + curr = list_first_entry(&q->task_list, typeof(*curr), task_list); + wake_up_process(curr->task); + list_del_init(&curr->task_list); +} +EXPORT_SYMBOL(swake_up_locked); + +void swake_up(struct swait_queue_head *q) +{ + unsigned long flags; + + if (!swait_active(q)) + return; + + raw_spin_lock_irqsave(&q->lock, flags); + swake_up_locked(q); + raw_spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(swake_up); + +/* + * Does not allow usage from IRQ disabled, since we must be able to + * release IRQs to guarantee bounded hold time. + */ +void swake_up_all(struct swait_queue_head *q) +{ + struct swait_queue *curr; + LIST_HEAD(tmp); + + if (!swait_active(q)) + return; + + raw_spin_lock_irq(&q->lock); + list_splice_init(&q->task_list, &tmp); + while (!list_empty(&tmp)) { + curr = list_first_entry(&tmp, typeof(*curr), task_list); + + wake_up_state(curr->task, TASK_NORMAL); + list_del_init(&curr->task_list); + + if (list_empty(&tmp)) + break; + + raw_spin_unlock_irq(&q->lock); + raw_spin_lock_irq(&q->lock); + } + raw_spin_unlock_irq(&q->lock); +} +EXPORT_SYMBOL(swake_up_all); + +void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait) +{ + wait->task = current; + if (list_empty(&wait->task_list)) + list_add(&wait->task_list, &q->task_list); +} + +void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&q->lock, flags); + __prepare_to_swait(q, wait); + set_current_state(state); + raw_spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(prepare_to_swait); + +long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state) +{ + if (signal_pending_state(state, current)) + return -ERESTARTSYS; + + prepare_to_swait(q, wait, state); + + return 0; +} +EXPORT_SYMBOL(prepare_to_swait_event); + +void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait) +{ + __set_current_state(TASK_RUNNING); + if (!list_empty(&wait->task_list)) + list_del_init(&wait->task_list); +} + +void finish_swait(struct swait_queue_head *q, struct swait_queue *wait) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + + if (!list_empty_careful(&wait->task_list)) { + raw_spin_lock_irqsave(&q->lock, flags); + list_del_init(&wait->task_list); + raw_spin_unlock_irqrestore(&q->lock, flags); + } +} +EXPORT_SYMBOL(finish_swait); diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 580ac2d4024f..15a1795bbba1 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -316,24 +316,24 @@ static inline void seccomp_sync_threads(void) put_seccomp_filter(thread); smp_store_release(&thread->seccomp.filter, caller->seccomp.filter); + + /* + * Don't let an unprivileged task work around + * the no_new_privs restriction by creating + * a thread that sets it up, enters seccomp, + * then dies. + */ + if (task_no_new_privs(caller)) + task_set_no_new_privs(thread); + /* * Opt the other thread into seccomp if needed. * As threads are considered to be trust-realm * equivalent (see ptrace_may_access), it is safe to * allow one thread to transition the other. */ - if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) { - /* - * Don't let an unprivileged task work around - * the no_new_privs restriction by creating - * a thread that sets it up, enters seccomp, - * then dies. - */ - if (task_no_new_privs(caller)) - task_set_no_new_privs(thread); - + if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) seccomp_assign_mode(thread, SECCOMP_MODE_FILTER); - } } } diff --git a/kernel/signal.c b/kernel/signal.c index f3f1f7a972fd..0508544c8ced 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -3508,8 +3508,10 @@ static int sigsuspend(sigset_t *set) current->saved_sigmask = current->blocked; set_current_blocked(set); - __set_current_state(TASK_INTERRUPTIBLE); - schedule(); + while (!signal_pending(current)) { + __set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } set_restore_sigmask(); return -ERESTARTNOHAND; } diff --git a/kernel/smp.c b/kernel/smp.c index d903c02223af..300d29391e07 100644 --- a/kernel/smp.c +++ b/kernel/smp.c @@ -105,13 +105,12 @@ void __init call_function_init(void) * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ -static void csd_lock_wait(struct call_single_data *csd) +static __always_inline void csd_lock_wait(struct call_single_data *csd) { - while (smp_load_acquire(&csd->flags) & CSD_FLAG_LOCK) - cpu_relax(); + smp_cond_acquire(!(csd->flags & CSD_FLAG_LOCK)); } -static void csd_lock(struct call_single_data *csd) +static __always_inline void csd_lock(struct call_single_data *csd) { csd_lock_wait(csd); csd->flags |= CSD_FLAG_LOCK; @@ -124,7 +123,7 @@ static void csd_lock(struct call_single_data *csd) smp_wmb(); } -static void csd_unlock(struct call_single_data *csd) +static __always_inline void csd_unlock(struct call_single_data *csd) { WARN_ON(!(csd->flags & CSD_FLAG_LOCK)); diff --git a/kernel/softirq.c b/kernel/softirq.c index 479e4436f787..8aae49dd7da8 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -116,9 +116,9 @@ void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) if (preempt_count() == cnt) { #ifdef CONFIG_DEBUG_PREEMPT - current->preempt_disable_ip = get_parent_ip(CALLER_ADDR1); + current->preempt_disable_ip = get_lock_parent_ip(); #endif - trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + trace_preempt_off(CALLER_ADDR0, get_lock_parent_ip()); } } EXPORT_SYMBOL(__local_bh_disable_ip); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 97715fd9e790..f5102fabef7f 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -350,6 +350,17 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, +#ifdef CONFIG_SCHEDSTATS + { + .procname = "sched_schedstats", + .data = NULL, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_schedstats, + .extra1 = &zero, + .extra2 = &one, + }, +#endif /* CONFIG_SCHEDSTATS */ #endif /* CONFIG_SMP */ #ifdef CONFIG_NUMA_BALANCING { @@ -505,7 +516,7 @@ static struct ctl_table kern_table[] = { .data = &latencytop_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = sysctl_latencytop, }, #endif #ifdef CONFIG_BLK_DEV_INITRD diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 435b8850dd80..fa909f9fd559 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -897,10 +897,10 @@ static int enqueue_hrtimer(struct hrtimer *timer, */ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, - unsigned long newstate, int reprogram) + u8 newstate, int reprogram) { struct hrtimer_cpu_base *cpu_base = base->cpu_base; - unsigned int state = timer->state; + u8 state = timer->state; timer->state = newstate; if (!(state & HRTIMER_STATE_ENQUEUED)) @@ -930,7 +930,7 @@ static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart) { if (hrtimer_is_queued(timer)) { - unsigned long state = timer->state; + u8 state = timer->state; int reprogram; /* @@ -954,6 +954,22 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool rest return 0; } +static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, + const enum hrtimer_mode mode) +{ +#ifdef CONFIG_TIME_LOW_RES + /* + * CONFIG_TIME_LOW_RES indicates that the system has no way to return + * granular time values. For relative timers we add hrtimer_resolution + * (i.e. one jiffie) to prevent short timeouts. + */ + timer->is_rel = mode & HRTIMER_MODE_REL; + if (timer->is_rel) + tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution)); +#endif + return tim; +} + /** * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU * @timer: the timer to be added @@ -974,19 +990,10 @@ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, /* Remove an active timer from the queue: */ remove_hrtimer(timer, base, true); - if (mode & HRTIMER_MODE_REL) { + if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, base->get_time()); - /* - * CONFIG_TIME_LOW_RES is a temporary way for architectures - * to signal that they simply return xtime in - * do_gettimeoffset(). In this case we want to round up by - * resolution when starting a relative timer, to avoid short - * timeouts. This will go away with the GTOD framework. - */ -#ifdef CONFIG_TIME_LOW_RES - tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution)); -#endif - } + + tim = hrtimer_update_lowres(timer, tim, mode); hrtimer_set_expires_range_ns(timer, tim, delta_ns); @@ -1074,19 +1081,23 @@ EXPORT_SYMBOL_GPL(hrtimer_cancel); /** * hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read + * @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y */ -ktime_t hrtimer_get_remaining(const struct hrtimer *timer) +ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust) { unsigned long flags; ktime_t rem; lock_hrtimer_base(timer, &flags); - rem = hrtimer_expires_remaining(timer); + if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust) + rem = hrtimer_expires_remaining_adjusted(timer); + else + rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; } -EXPORT_SYMBOL_GPL(hrtimer_get_remaining); +EXPORT_SYMBOL_GPL(__hrtimer_get_remaining); #ifdef CONFIG_NO_HZ_COMMON /** @@ -1220,6 +1231,14 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, fn = timer->function; /* + * Clear the 'is relative' flag for the TIME_LOW_RES case. If the + * timer is restarted with a period then it becomes an absolute + * timer. If its not restarted it does not matter. + */ + if (IS_ENABLED(CONFIG_TIME_LOW_RES)) + timer->is_rel = false; + + /* * Because we run timers from hardirq context, there is no chance * they get migrated to another cpu, therefore its safe to unlock * the timer base. diff --git a/kernel/time/itimer.c b/kernel/time/itimer.c index 8d262b467573..1d5c7204ddc9 100644 --- a/kernel/time/itimer.c +++ b/kernel/time/itimer.c @@ -26,7 +26,7 @@ */ static struct timeval itimer_get_remtime(struct hrtimer *timer) { - ktime_t rem = hrtimer_get_remaining(timer); + ktime_t rem = __hrtimer_get_remaining(timer, true); /* * Racy but safe: if the itimer expires after the above diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 36f2ca09aa5e..6df8927c58a5 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -685,8 +685,18 @@ int ntp_validate_timex(struct timex *txc) if (!capable(CAP_SYS_TIME)) return -EPERM; - if (!timeval_inject_offset_valid(&txc->time)) - return -EINVAL; + if (txc->modes & ADJ_NANO) { + struct timespec ts; + + ts.tv_sec = txc->time.tv_sec; + ts.tv_nsec = txc->time.tv_usec; + if (!timespec_inject_offset_valid(&ts)) + return -EINVAL; + + } else { + if (!timeval_inject_offset_valid(&txc->time)) + return -EINVAL; + } } /* diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index f5e86d282d52..1cafba860b08 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -333,7 +333,6 @@ static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp) return err; } - /* * Validate the clockid_t for a new CPU-clock timer, and initialize the timer. * This is called from sys_timer_create() and do_cpu_nanosleep() with the @@ -517,6 +516,10 @@ static void arm_timer(struct k_itimer *timer) cputime_expires->sched_exp = exp; break; } + if (CPUCLOCK_PERTHREAD(timer->it_clock)) + tick_dep_set_task(p, TICK_DEP_BIT_POSIX_TIMER); + else + tick_dep_set_signal(p->signal, TICK_DEP_BIT_POSIX_TIMER); } } @@ -582,39 +585,6 @@ static int cpu_timer_sample_group(const clockid_t which_clock, return 0; } -#ifdef CONFIG_NO_HZ_FULL -static void nohz_kick_work_fn(struct work_struct *work) -{ - tick_nohz_full_kick_all(); -} - -static DECLARE_WORK(nohz_kick_work, nohz_kick_work_fn); - -/* - * We need the IPIs to be sent from sane process context. - * The posix cpu timers are always set with irqs disabled. - */ -static void posix_cpu_timer_kick_nohz(void) -{ - if (context_tracking_is_enabled()) - schedule_work(&nohz_kick_work); -} - -bool posix_cpu_timers_can_stop_tick(struct task_struct *tsk) -{ - if (!task_cputime_zero(&tsk->cputime_expires)) - return false; - - /* Check if cputimer is running. This is accessed without locking. */ - if (READ_ONCE(tsk->signal->cputimer.running)) - return false; - - return true; -} -#else -static inline void posix_cpu_timer_kick_nohz(void) { } -#endif - /* * Guts of sys_timer_settime for CPU timers. * This is called with the timer locked and interrupts disabled. @@ -761,8 +731,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, sample_to_timespec(timer->it_clock, old_incr, &old->it_interval); } - if (!ret) - posix_cpu_timer_kick_nohz(); + return ret; } @@ -911,6 +880,8 @@ static void check_thread_timers(struct task_struct *tsk, __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk); } } + if (task_cputime_zero(tsk_expires)) + tick_dep_clear_task(tsk, TICK_DEP_BIT_POSIX_TIMER); } static inline void stop_process_timers(struct signal_struct *sig) @@ -919,6 +890,7 @@ static inline void stop_process_timers(struct signal_struct *sig) /* Turn off cputimer->running. This is done without locking. */ WRITE_ONCE(cputimer->running, false); + tick_dep_clear_signal(sig, TICK_DEP_BIT_POSIX_TIMER); } static u32 onecputick; @@ -1095,8 +1067,6 @@ void posix_cpu_timer_schedule(struct k_itimer *timer) arm_timer(timer); unlock_task_sighand(p, &flags); - /* Kick full dynticks CPUs in case they need to tick on the new timer */ - posix_cpu_timer_kick_nohz(); out: timer->it_overrun_last = timer->it_overrun; timer->it_overrun = -1; @@ -1270,7 +1240,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, } if (!*newval) - goto out; + return; *newval += now; } @@ -1288,8 +1258,8 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, tsk->signal->cputime_expires.virt_exp = *newval; break; } -out: - posix_cpu_timer_kick_nohz(); + + tick_dep_set_signal(tsk->signal, TICK_DEP_BIT_POSIX_TIMER); } static int do_cpu_nanosleep(const clockid_t which_clock, int flags, diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 31d11ac9fa47..f2826c35e918 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -760,7 +760,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv); - remaining = ktime_sub(hrtimer_get_expires(timer), now); + remaining = __hrtimer_expires_remaining_adjusted(timer, now); /* Return 0 only, when the timer is expired and not pending */ if (remaining.tv64 <= 0) { /* diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 9d7a053545f5..969e6704c3c9 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -22,7 +22,6 @@ #include <linux/module.h> #include <linux/irq_work.h> #include <linux/posix-timers.h> -#include <linux/perf_event.h> #include <linux/context_tracking.h> #include <asm/irq_regs.h> @@ -36,16 +35,17 @@ */ static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched); -/* - * The time, when the last jiffy update happened. Protected by jiffies_lock. - */ -static ktime_t last_jiffies_update; - struct tick_sched *tick_get_tick_sched(int cpu) { return &per_cpu(tick_cpu_sched, cpu); } +#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) +/* + * The time, when the last jiffy update happened. Protected by jiffies_lock. + */ +static ktime_t last_jiffies_update; + /* * Must be called with interrupts disabled ! */ @@ -151,59 +151,69 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) update_process_times(user_mode(regs)); profile_tick(CPU_PROFILING); } +#endif #ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; cpumask_var_t housekeeping_mask; bool tick_nohz_full_running; +static unsigned long tick_dep_mask; -static bool can_stop_full_tick(void) +static void trace_tick_dependency(unsigned long dep) +{ + if (dep & TICK_DEP_MASK_POSIX_TIMER) { + trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER); + return; + } + + if (dep & TICK_DEP_MASK_PERF_EVENTS) { + trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS); + return; + } + + if (dep & TICK_DEP_MASK_SCHED) { + trace_tick_stop(0, TICK_DEP_MASK_SCHED); + return; + } + + if (dep & TICK_DEP_MASK_CLOCK_UNSTABLE) + trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE); +} + +static bool can_stop_full_tick(struct tick_sched *ts) { WARN_ON_ONCE(!irqs_disabled()); - if (!sched_can_stop_tick()) { - trace_tick_stop(0, "more than 1 task in runqueue\n"); + if (tick_dep_mask) { + trace_tick_dependency(tick_dep_mask); return false; } - if (!posix_cpu_timers_can_stop_tick(current)) { - trace_tick_stop(0, "posix timers running\n"); + if (ts->tick_dep_mask) { + trace_tick_dependency(ts->tick_dep_mask); return false; } - if (!perf_event_can_stop_tick()) { - trace_tick_stop(0, "perf events running\n"); + if (current->tick_dep_mask) { + trace_tick_dependency(current->tick_dep_mask); return false; } - /* sched_clock_tick() needs us? */ -#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK - /* - * TODO: kick full dynticks CPUs when - * sched_clock_stable is set. - */ - if (!sched_clock_stable()) { - trace_tick_stop(0, "unstable sched clock\n"); - /* - * Don't allow the user to think they can get - * full NO_HZ with this machine. - */ - WARN_ONCE(tick_nohz_full_running, - "NO_HZ FULL will not work with unstable sched clock"); + if (current->signal->tick_dep_mask) { + trace_tick_dependency(current->signal->tick_dep_mask); return false; } -#endif return true; } -static void nohz_full_kick_work_func(struct irq_work *work) +static void nohz_full_kick_func(struct irq_work *work) { /* Empty, the tick restart happens on tick_nohz_irq_exit() */ } static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { - .func = nohz_full_kick_work_func, + .func = nohz_full_kick_func, }; /* @@ -212,7 +222,7 @@ static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { * This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(), * is NMI safe. */ -void tick_nohz_full_kick(void) +static void tick_nohz_full_kick(void) { if (!tick_nohz_full_cpu(smp_processor_id())) return; @@ -232,27 +242,112 @@ void tick_nohz_full_kick_cpu(int cpu) irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu); } -static void nohz_full_kick_ipi(void *info) -{ - /* Empty, the tick restart happens on tick_nohz_irq_exit() */ -} - /* * Kick all full dynticks CPUs in order to force these to re-evaluate * their dependency on the tick and restart it if necessary. */ -void tick_nohz_full_kick_all(void) +static void tick_nohz_full_kick_all(void) { + int cpu; + if (!tick_nohz_full_running) return; preempt_disable(); - smp_call_function_many(tick_nohz_full_mask, - nohz_full_kick_ipi, NULL, false); - tick_nohz_full_kick(); + for_each_cpu_and(cpu, tick_nohz_full_mask, cpu_online_mask) + tick_nohz_full_kick_cpu(cpu); preempt_enable(); } +static void tick_nohz_dep_set_all(unsigned long *dep, + enum tick_dep_bits bit) +{ + unsigned long prev; + + prev = fetch_or(dep, BIT_MASK(bit)); + if (!prev) + tick_nohz_full_kick_all(); +} + +/* + * Set a global tick dependency. Used by perf events that rely on freq and + * by unstable clock. + */ +void tick_nohz_dep_set(enum tick_dep_bits bit) +{ + tick_nohz_dep_set_all(&tick_dep_mask, bit); +} + +void tick_nohz_dep_clear(enum tick_dep_bits bit) +{ + clear_bit(bit, &tick_dep_mask); +} + +/* + * Set per-CPU tick dependency. Used by scheduler and perf events in order to + * manage events throttling. + */ +void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) +{ + unsigned long prev; + struct tick_sched *ts; + + ts = per_cpu_ptr(&tick_cpu_sched, cpu); + + prev = fetch_or(&ts->tick_dep_mask, BIT_MASK(bit)); + if (!prev) { + preempt_disable(); + /* Perf needs local kick that is NMI safe */ + if (cpu == smp_processor_id()) { + tick_nohz_full_kick(); + } else { + /* Remote irq work not NMI-safe */ + if (!WARN_ON_ONCE(in_nmi())) + tick_nohz_full_kick_cpu(cpu); + } + preempt_enable(); + } +} + +void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) +{ + struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); + + clear_bit(bit, &ts->tick_dep_mask); +} + +/* + * Set a per-task tick dependency. Posix CPU timers need this in order to elapse + * per task timers. + */ +void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) +{ + /* + * We could optimize this with just kicking the target running the task + * if that noise matters for nohz full users. + */ + tick_nohz_dep_set_all(&tsk->tick_dep_mask, bit); +} + +void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) +{ + clear_bit(bit, &tsk->tick_dep_mask); +} + +/* + * Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse + * per process timers. + */ +void tick_nohz_dep_set_signal(struct signal_struct *sig, enum tick_dep_bits bit) +{ + tick_nohz_dep_set_all(&sig->tick_dep_mask, bit); +} + +void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit) +{ + clear_bit(bit, &sig->tick_dep_mask); +} + /* * Re-evaluate the need for the tick as we switch the current task. * It might need the tick due to per task/process properties: @@ -261,15 +356,19 @@ void tick_nohz_full_kick_all(void) void __tick_nohz_task_switch(void) { unsigned long flags; + struct tick_sched *ts; local_irq_save(flags); if (!tick_nohz_full_cpu(smp_processor_id())) goto out; - if (tick_nohz_tick_stopped() && !can_stop_full_tick()) - tick_nohz_full_kick(); + ts = this_cpu_ptr(&tick_cpu_sched); + if (ts->tick_stopped) { + if (current->tick_dep_mask || current->signal->tick_dep_mask) + tick_nohz_full_kick(); + } out: local_irq_restore(flags); } @@ -687,7 +786,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, ts->last_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; - trace_tick_stop(1, " "); + trace_tick_stop(1, TICK_DEP_MASK_NONE); } /* @@ -738,7 +837,7 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts) if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE) return; - if (can_stop_full_tick()) + if (can_stop_full_tick(ts)) tick_nohz_stop_sched_tick(ts, ktime_get(), cpu); else if (ts->tick_stopped) tick_nohz_restart_sched_tick(ts, ktime_get(), 1); @@ -993,9 +1092,9 @@ static void tick_nohz_switch_to_nohz(void) /* Get the next period */ next = tick_init_jiffy_update(); - hrtimer_forward_now(&ts->sched_timer, tick_period); hrtimer_set_expires(&ts->sched_timer, next); - tick_program_event(next, 1); + hrtimer_forward_now(&ts->sched_timer, tick_period); + tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); tick_nohz_activate(ts, NOHZ_MODE_LOWRES); } diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index a4a8d4e9baa1..eb4e32566a83 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -60,6 +60,7 @@ struct tick_sched { u64 next_timer; ktime_t idle_expires; int do_timer_last; + unsigned long tick_dep_mask; }; extern struct tick_sched *tick_get_tick_sched(int cpu); diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index f75e35b60149..ba7d8b288bb3 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -69,7 +69,7 @@ print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer, print_name_offset(m, taddr); SEQ_printf(m, ", "); print_name_offset(m, timer->function); - SEQ_printf(m, ", S:%02lx", timer->state); + SEQ_printf(m, ", S:%02x", timer->state); #ifdef CONFIG_TIMER_STATS SEQ_printf(m, ", "); print_name_offset(m, timer->start_site); diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 45dd798bcd37..326a75e884db 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -191,14 +191,17 @@ static u64 bpf_perf_event_read(u64 r1, u64 index, u64 r3, u64 r4, u64 r5) struct bpf_map *map = (struct bpf_map *) (unsigned long) r1; struct bpf_array *array = container_of(map, struct bpf_array, map); struct perf_event *event; + struct file *file; if (unlikely(index >= array->map.max_entries)) return -E2BIG; - event = (struct perf_event *)array->ptrs[index]; - if (!event) + file = (struct file *)array->ptrs[index]; + if (unlikely(!file)) return -ENOENT; + event = file->private_data; + /* make sure event is local and doesn't have pmu::count */ if (event->oncpu != smp_processor_id() || event->pmu->count) @@ -228,6 +231,7 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size) void *data = (void *) (long) r4; struct perf_sample_data sample_data; struct perf_event *event; + struct file *file; struct perf_raw_record raw = { .size = size, .data = data, @@ -236,10 +240,12 @@ static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size) if (unlikely(index >= array->map.max_entries)) return -E2BIG; - event = (struct perf_event *)array->ptrs[index]; - if (unlikely(!event)) + file = (struct file *)array->ptrs[index]; + if (unlikely(!file)) return -ENOENT; + event = file->private_data; + if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE || event->attr.config != PERF_COUNT_SW_BPF_OUTPUT)) return -EINVAL; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index eca592f977b2..57a6eea84694 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4961,7 +4961,7 @@ void ftrace_release_mod(struct module *mod) mutex_unlock(&ftrace_lock); } -static void ftrace_module_enable(struct module *mod) +void ftrace_module_enable(struct module *mod) { struct dyn_ftrace *rec; struct ftrace_page *pg; @@ -5038,38 +5038,8 @@ void ftrace_module_init(struct module *mod) ftrace_process_locs(mod, mod->ftrace_callsites, mod->ftrace_callsites + mod->num_ftrace_callsites); } - -static int ftrace_module_notify(struct notifier_block *self, - unsigned long val, void *data) -{ - struct module *mod = data; - - switch (val) { - case MODULE_STATE_COMING: - ftrace_module_enable(mod); - break; - case MODULE_STATE_GOING: - ftrace_release_mod(mod); - break; - default: - break; - } - - return 0; -} -#else -static int ftrace_module_notify(struct notifier_block *self, - unsigned long val, void *data) -{ - return 0; -} #endif /* CONFIG_MODULES */ -struct notifier_block ftrace_module_nb = { - .notifier_call = ftrace_module_notify, - .priority = INT_MIN, /* Run after anything that can remove kprobes */ -}; - void __init ftrace_init(void) { extern unsigned long __start_mcount_loc[]; @@ -5098,10 +5068,6 @@ void __init ftrace_init(void) __start_mcount_loc, __stop_mcount_loc); - ret = register_module_notifier(&ftrace_module_nb); - if (ret) - pr_warning("Failed to register trace ftrace module exit notifier\n"); - set_ftrace_early_filters(); return; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 87fb9801bd9e..d9293402ee68 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1751,7 +1751,7 @@ void trace_buffer_unlock_commit_regs(struct trace_array *tr, { __buffer_unlock_commit(buffer, event); - ftrace_trace_stack(tr, buffer, flags, 6, pc, regs); + ftrace_trace_stack(tr, buffer, flags, 0, pc, regs); ftrace_trace_userstack(buffer, flags, pc); } EXPORT_SYMBOL_GPL(trace_buffer_unlock_commit_regs); diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index f333e57c4614..05ddc0820771 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -97,16 +97,16 @@ trace_find_event_field(struct trace_event_call *call, char *name) struct ftrace_event_field *field; struct list_head *head; - field = __find_event_field(&ftrace_generic_fields, name); + head = trace_get_fields(call); + field = __find_event_field(head, name); if (field) return field; - field = __find_event_field(&ftrace_common_fields, name); + field = __find_event_field(&ftrace_generic_fields, name); if (field) return field; - head = trace_get_fields(call); - return __find_event_field(head, name); + return __find_event_field(&ftrace_common_fields, name); } static int __trace_define_field(struct list_head *head, const char *type, @@ -171,8 +171,10 @@ static int trace_define_generic_fields(void) { int ret; - __generic_field(int, cpu, FILTER_OTHER); - __generic_field(char *, comm, FILTER_PTR_STRING); + __generic_field(int, CPU, FILTER_CPU); + __generic_field(int, cpu, FILTER_CPU); + __generic_field(char *, COMM, FILTER_COMM); + __generic_field(char *, comm, FILTER_COMM); return ret; } @@ -869,7 +871,8 @@ t_next(struct seq_file *m, void *v, loff_t *pos) * The ftrace subsystem is for showing formats only. * They can not be enabled or disabled via the event files. */ - if (call->class && call->class->reg) + if (call->class && call->class->reg && + !(call->flags & TRACE_EVENT_FL_IGNORE_ENABLE)) return file; } diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index f93a219b18da..6816302542b2 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -1043,13 +1043,14 @@ static int init_pred(struct filter_parse_state *ps, return -EINVAL; } - if (is_string_field(field)) { + if (field->filter_type == FILTER_COMM) { + filter_build_regex(pred); + fn = filter_pred_comm; + pred->regex.field_len = TASK_COMM_LEN; + } else if (is_string_field(field)) { filter_build_regex(pred); - if (!strcmp(field->name, "comm")) { - fn = filter_pred_comm; - pred->regex.field_len = TASK_COMM_LEN; - } else if (field->filter_type == FILTER_STATIC_STRING) { + if (field->filter_type == FILTER_STATIC_STRING) { fn = filter_pred_string; pred->regex.field_len = field->size; } else if (field->filter_type == FILTER_DYN_STRING) @@ -1072,7 +1073,7 @@ static int init_pred(struct filter_parse_state *ps, } pred->val = val; - if (!strcmp(field->name, "cpu")) + if (field->filter_type == FILTER_CPU) fn = filter_pred_cpu; else fn = select_comparison_fn(pred->op, field->size, diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index c9956440d0e6..21b81a41dae5 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -30,7 +30,7 @@ struct trace_kprobe { struct list_head list; struct kretprobe rp; /* Use rp.kp for kprobe use */ - unsigned long nhit; + unsigned long __percpu *nhit; const char *symbol; /* symbol name */ struct trace_probe tp; }; @@ -274,6 +274,10 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, if (!tk) return ERR_PTR(ret); + tk->nhit = alloc_percpu(unsigned long); + if (!tk->nhit) + goto error; + if (symbol) { tk->symbol = kstrdup(symbol, GFP_KERNEL); if (!tk->symbol) @@ -313,6 +317,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, error: kfree(tk->tp.call.name); kfree(tk->symbol); + free_percpu(tk->nhit); kfree(tk); return ERR_PTR(ret); } @@ -327,6 +332,7 @@ static void free_trace_kprobe(struct trace_kprobe *tk) kfree(tk->tp.call.class->system); kfree(tk->tp.call.name); kfree(tk->symbol); + free_percpu(tk->nhit); kfree(tk); } @@ -874,9 +880,14 @@ static const struct file_operations kprobe_events_ops = { static int probes_profile_seq_show(struct seq_file *m, void *v) { struct trace_kprobe *tk = v; + unsigned long nhit = 0; + int cpu; + + for_each_possible_cpu(cpu) + nhit += *per_cpu_ptr(tk->nhit, cpu); seq_printf(m, " %-44s %15lu %15lu\n", - trace_event_name(&tk->tp.call), tk->nhit, + trace_event_name(&tk->tp.call), nhit, tk->rp.kp.nmissed); return 0; @@ -1225,7 +1236,7 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs) { struct trace_kprobe *tk = container_of(kp, struct trace_kprobe, rp.kp); - tk->nhit++; + raw_cpu_inc(*tk->nhit); if (tk->tp.flags & TP_FLAG_TRACE) kprobe_trace_func(tk, regs); @@ -1242,7 +1253,7 @@ kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs) { struct trace_kprobe *tk = container_of(ri->rp, struct trace_kprobe, rp); - tk->nhit++; + raw_cpu_inc(*tk->nhit); if (tk->tp.flags & TP_FLAG_TRACE) kretprobe_trace_func(tk, ri, regs); diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index dda9e6742950..2a1abbaca10e 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -126,6 +126,13 @@ check_stack(unsigned long ip, unsigned long *stack) } /* + * Some archs may not have the passed in ip in the dump. + * If that happens, we need to show everything. + */ + if (i == stack_trace_max.nr_entries) + i = 0; + + /* * Now find where in the stack these are. */ x = 0; @@ -149,7 +156,11 @@ check_stack(unsigned long ip, unsigned long *stack) for (; p < top && i < stack_trace_max.nr_entries; p++) { if (stack_dump_trace[i] == ULONG_MAX) break; - if (*p == stack_dump_trace[i]) { + /* + * The READ_ONCE_NOCHECK is used to let KASAN know that + * this is not a stack-out-of-bounds error. + */ + if ((READ_ONCE_NOCHECK(*p)) == stack_dump_trace[i]) { stack_dump_trace[x] = stack_dump_trace[i++]; this_size = stack_trace_index[x++] = (top - p) * sizeof(unsigned long); diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index 0655afbea83f..d1663083d903 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -186,11 +186,11 @@ print_syscall_exit(struct trace_iterator *iter, int flags, extern char *__bad_type_size(void); -#define SYSCALL_FIELD(type, name) \ - sizeof(type) != sizeof(trace.name) ? \ +#define SYSCALL_FIELD(type, field, name) \ + sizeof(type) != sizeof(trace.field) ? \ __bad_type_size() : \ - #type, #name, offsetof(typeof(trace), name), \ - sizeof(trace.name), is_signed_type(type) + #type, #name, offsetof(typeof(trace), field), \ + sizeof(trace.field), is_signed_type(type) static int __init __set_enter_print_fmt(struct syscall_metadata *entry, char *buf, int len) @@ -261,7 +261,8 @@ static int __init syscall_enter_define_fields(struct trace_event_call *call) int i; int offset = offsetof(typeof(trace), args); - ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER); + ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr), + FILTER_OTHER); if (ret) return ret; @@ -281,11 +282,12 @@ static int __init syscall_exit_define_fields(struct trace_event_call *call) struct syscall_trace_exit trace; int ret; - ret = trace_define_field(call, SYSCALL_FIELD(int, nr), FILTER_OTHER); + ret = trace_define_field(call, SYSCALL_FIELD(int, nr, __syscall_nr), + FILTER_OTHER); if (ret) return ret; - ret = trace_define_field(call, SYSCALL_FIELD(long, ret), + ret = trace_define_field(call, SYSCALL_FIELD(long, ret, ret), FILTER_OTHER); return ret; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 975cb49e32bf..f8e26ab963ed 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -93,9 +93,11 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) { struct mm_struct *mm; - /* convert pages-usec to Mbyte-usec */ - stats->coremem = p->acct_rss_mem1 * PAGE_SIZE / MB; - stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE / MB; + /* convert pages-nsec/1024 to Mbyte-usec, see __acct_update_integrals */ + stats->coremem = p->acct_rss_mem1 * PAGE_SIZE; + do_div(stats->coremem, 1000 * KB); + stats->virtmem = p->acct_vm_mem1 * PAGE_SIZE; + do_div(stats->virtmem, 1000 * KB); mm = get_task_mm(p); if (mm) { /* adjust to KB unit */ @@ -123,27 +125,28 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p) static void __acct_update_integrals(struct task_struct *tsk, cputime_t utime, cputime_t stime) { - if (likely(tsk->mm)) { - cputime_t time, dtime; - struct timeval value; - unsigned long flags; - u64 delta; - - local_irq_save(flags); - time = stime + utime; - dtime = time - tsk->acct_timexpd; - jiffies_to_timeval(cputime_to_jiffies(dtime), &value); - delta = value.tv_sec; - delta = delta * USEC_PER_SEC + value.tv_usec; - - if (delta == 0) - goto out; - tsk->acct_timexpd = time; - tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm); - tsk->acct_vm_mem1 += delta * tsk->mm->total_vm; - out: - local_irq_restore(flags); - } + cputime_t time, dtime; + u64 delta; + + if (!likely(tsk->mm)) + return; + + time = stime + utime; + dtime = time - tsk->acct_timexpd; + /* Avoid division: cputime_t is often in nanoseconds already. */ + delta = cputime_to_nsecs(dtime); + + if (delta < TICK_NSEC) + return; + + tsk->acct_timexpd = time; + /* + * Divide by 1024 to avoid overflow, and to avoid division. + * The final unit reported to userspace is Mbyte-usecs, + * the rest of the math is done in xacct_add_tsk. + */ + tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm) >> 10; + tsk->acct_vm_mem1 += delta * tsk->mm->total_vm >> 10; } /** @@ -153,9 +156,12 @@ static void __acct_update_integrals(struct task_struct *tsk, void acct_update_integrals(struct task_struct *tsk) { cputime_t utime, stime; + unsigned long flags; + local_irq_save(flags); task_cputime(tsk, &utime, &stime); __acct_update_integrals(tsk, utime, stime); + local_irq_restore(flags); } /** diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 61a0264e28f9..7ff5dc7d2ac5 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -301,7 +301,23 @@ static DEFINE_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ -static cpumask_var_t wq_unbound_cpumask; /* PL: low level cpumask for all unbound wqs */ +/* PL: allowable cpus for unbound wqs and work items */ +static cpumask_var_t wq_unbound_cpumask; + +/* CPU where unbound work was last round robin scheduled from this CPU */ +static DEFINE_PER_CPU(int, wq_rr_cpu_last); + +/* + * Local execution of unbound work items is no longer guaranteed. The + * following always forces round-robin CPU selection on unbound work items + * to uncover usages which depend on it. + */ +#ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU +static bool wq_debug_force_rr_cpu = true; +#else +static bool wq_debug_force_rr_cpu = false; +#endif +module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644); /* the per-cpu worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], @@ -570,6 +586,16 @@ static struct pool_workqueue *unbound_pwq_by_node(struct workqueue_struct *wq, int node) { assert_rcu_or_wq_mutex_or_pool_mutex(wq); + + /* + * XXX: @node can be NUMA_NO_NODE if CPU goes offline while a + * delayed item is pending. The plan is to keep CPU -> NODE + * mapping valid and stable across CPU on/offlines. Once that + * happens, this workaround can be removed. + */ + if (unlikely(node == NUMA_NO_NODE)) + return wq->dfl_pwq; + return rcu_dereference_raw(wq->numa_pwq_tbl[node]); } @@ -1298,6 +1324,39 @@ static bool is_chained_work(struct workqueue_struct *wq) return worker && worker->current_pwq->wq == wq; } +/* + * When queueing an unbound work item to a wq, prefer local CPU if allowed + * by wq_unbound_cpumask. Otherwise, round robin among the allowed ones to + * avoid perturbing sensitive tasks. + */ +static int wq_select_unbound_cpu(int cpu) +{ + static bool printed_dbg_warning; + int new_cpu; + + if (likely(!wq_debug_force_rr_cpu)) { + if (cpumask_test_cpu(cpu, wq_unbound_cpumask)) + return cpu; + } else if (!printed_dbg_warning) { + pr_warn("workqueue: round-robin CPU selection forced, expect performance impact\n"); + printed_dbg_warning = true; + } + + if (cpumask_empty(wq_unbound_cpumask)) + return cpu; + + new_cpu = __this_cpu_read(wq_rr_cpu_last); + new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask); + if (unlikely(new_cpu >= nr_cpu_ids)) { + new_cpu = cpumask_first_and(wq_unbound_cpumask, cpu_online_mask); + if (unlikely(new_cpu >= nr_cpu_ids)) + return cpu; + } + __this_cpu_write(wq_rr_cpu_last, new_cpu); + + return new_cpu; +} + static void __queue_work(int cpu, struct workqueue_struct *wq, struct work_struct *work) { @@ -1323,7 +1382,7 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, return; retry: if (req_cpu == WORK_CPU_UNBOUND) - cpu = raw_smp_processor_id(); + cpu = wq_select_unbound_cpu(raw_smp_processor_id()); /* pwq which will be used unless @work is executing elsewhere */ if (!(wq->flags & WQ_UNBOUND)) @@ -1464,13 +1523,13 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, timer_stats_timer_set_start_info(&dwork->timer); dwork->wq = wq; - /* timer isn't guaranteed to run in this cpu, record earlier */ - if (cpu == WORK_CPU_UNBOUND) - cpu = raw_smp_processor_id(); dwork->cpu = cpu; timer->expires = jiffies + delay; - add_timer_on(timer, cpu); + if (unlikely(cpu != WORK_CPU_UNBOUND)) + add_timer_on(timer, cpu); + else + add_timer(timer); } /** @@ -2355,7 +2414,8 @@ static void check_flush_dependency(struct workqueue_struct *target_wq, WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%pf", current->pid, current->comm, target_wq->name, target_func); - WARN_ONCE(worker && (worker->current_pwq->wq->flags & WQ_MEM_RECLAIM), + WARN_ONCE(worker && ((worker->current_pwq->wq->flags & + (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM), "workqueue: WQ_MEM_RECLAIM %s:%pf is flushing !WQ_MEM_RECLAIM %s:%pf", worker->current_pwq->wq->name, worker->current_func, target_wq->name, target_func); |