diff options
Diffstat (limited to 'kernel')
52 files changed, 1890 insertions, 985 deletions
diff --git a/kernel/audit.c b/kernel/audit.c index 21c7fa615bd3..91e53d04b6a9 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1056,7 +1056,7 @@ static inline void audit_get_stamp(struct audit_context *ctx, static void wait_for_auditd(unsigned long sleep_time) { DECLARE_WAITQUEUE(wait, current); - set_current_state(TASK_INTERRUPTIBLE); + set_current_state(TASK_UNINTERRUPTIBLE); add_wait_queue(&audit_backlog_wait, &wait); if (audit_backlog_limit && diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index a291aa23fb3f..43c307dc9453 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -658,6 +658,7 @@ int audit_add_tree_rule(struct audit_krule *rule) struct vfsmount *mnt; int err; + rule->tree = NULL; list_for_each_entry(tree, &tree_list, list) { if (!strcmp(seed->pathname, tree->pathname)) { put_tree(seed); diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 83a2970295d1..6bd4a90d1991 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -1021,9 +1021,6 @@ static void audit_log_rule_change(char *action, struct audit_krule *rule, int re * @seq: netlink audit message sequence (serial) number * @data: payload data * @datasz: size of payload data - * @loginuid: loginuid of sender - * @sessionid: sessionid for netlink audit message - * @sid: SE Linux Security ID of sender */ int audit_receive_filter(int type, int pid, int seq, void *data, size_t datasz) { diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 2a9926275f80..a7c9e6ddb979 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1686,11 +1686,14 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, */ cgroup_drop_root(opts.new_root); - if (((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) && - root->flags != opts.flags) { - pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n"); - ret = -EINVAL; - goto drop_new_super; + if (root->flags != opts.flags) { + if ((root->flags | opts.flags) & CGRP_ROOT_SANE_BEHAVIOR) { + pr_err("cgroup: sane_behavior: new mount options should match the existing superblock\n"); + ret = -EINVAL; + goto drop_new_super; + } else { + pr_warning("cgroup: new mount options do not match the existing superblock, will be ignored\n"); + } } /* no subsys rebinding, so refcounts don't change */ @@ -2699,13 +2702,14 @@ static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys, goto out; } + cfe->type = (void *)cft; + cfe->dentry = dentry; + dentry->d_fsdata = cfe; + simple_xattrs_init(&cfe->xattrs); + mode = cgroup_file_mode(cft); error = cgroup_create_file(dentry, mode | S_IFREG, cgrp->root->sb); if (!error) { - cfe->type = (void *)cft; - cfe->dentry = dentry; - dentry->d_fsdata = cfe; - simple_xattrs_init(&cfe->xattrs); list_add_tail(&cfe->node, &parent->files); cfe = NULL; } @@ -2953,11 +2957,8 @@ struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, WARN_ON_ONCE(!rcu_read_lock_held()); /* if first iteration, pretend we just visited @cgroup */ - if (!pos) { - if (list_empty(&cgroup->children)) - return NULL; + if (!pos) pos = cgroup; - } /* visit the first child if exists */ next = list_first_or_null_rcu(&pos->children, struct cgroup, sibling); @@ -2965,14 +2966,14 @@ struct cgroup *cgroup_next_descendant_pre(struct cgroup *pos, return next; /* no child, visit my or the closest ancestor's next sibling */ - do { + while (pos != cgroup) { next = list_entry_rcu(pos->sibling.next, struct cgroup, sibling); if (&next->sibling != &pos->parent->children) return next; pos = pos->parent; - } while (pos != cgroup); + } return NULL; } diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 65349f07b878..383f8231e436 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -15,7 +15,6 @@ */ #include <linux/context_tracking.h> -#include <linux/kvm_host.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/hardirq.h> @@ -71,6 +70,46 @@ void user_enter(void) local_irq_restore(flags); } +#ifdef CONFIG_PREEMPT +/** + * preempt_schedule_context - preempt_schedule called by tracing + * + * The tracing infrastructure uses preempt_enable_notrace to prevent + * recursion and tracing preempt enabling caused by the tracing + * infrastructure itself. But as tracing can happen in areas coming + * from userspace or just about to enter userspace, a preempt enable + * can occur before user_exit() is called. This will cause the scheduler + * to be called when the system is still in usermode. + * + * To prevent this, the preempt_enable_notrace will use this function + * instead of preempt_schedule() to exit user context if needed before + * calling the scheduler. + */ +void __sched notrace preempt_schedule_context(void) +{ + struct thread_info *ti = current_thread_info(); + enum ctx_state prev_ctx; + + if (likely(ti->preempt_count || irqs_disabled())) + return; + + /* + * Need to disable preemption in case user_exit() is traced + * and the tracer calls preempt_enable_notrace() causing + * an infinite recursion. + */ + preempt_disable_notrace(); + prev_ctx = exception_enter(); + preempt_enable_no_resched_notrace(); + + preempt_schedule(); + + preempt_disable_notrace(); + exception_exit(prev_ctx); + preempt_enable_notrace(); +} +EXPORT_SYMBOL_GPL(preempt_schedule_context); +#endif /* CONFIG_PREEMPT */ /** * user_exit - Inform the context tracking that the CPU is diff --git a/kernel/cpu.c b/kernel/cpu.c index b5e4ab2d427e..198a38883e64 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -133,6 +133,27 @@ static void cpu_hotplug_done(void) mutex_unlock(&cpu_hotplug.lock); } +/* + * Wait for currently running CPU hotplug operations to complete (if any) and + * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects + * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the + * hotplug path before performing hotplug operations. So acquiring that lock + * guarantees mutual exclusion from any currently running hotplug operations. + */ +void cpu_hotplug_disable(void) +{ + cpu_maps_update_begin(); + cpu_hotplug_disabled = 1; + cpu_maps_update_done(); +} + +void cpu_hotplug_enable(void) +{ + cpu_maps_update_begin(); + cpu_hotplug_disabled = 0; + cpu_maps_update_done(); +} + #else /* #if CONFIG_HOTPLUG_CPU */ static void cpu_hotplug_begin(void) {} static void cpu_hotplug_done(void) {} @@ -541,36 +562,6 @@ static int __init alloc_frozen_cpus(void) core_initcall(alloc_frozen_cpus); /* - * Prevent regular CPU hotplug from racing with the freezer, by disabling CPU - * hotplug when tasks are about to be frozen. Also, don't allow the freezer - * to continue until any currently running CPU hotplug operation gets - * completed. - * To modify the 'cpu_hotplug_disabled' flag, we need to acquire the - * 'cpu_add_remove_lock'. And this same lock is also taken by the regular - * CPU hotplug path and released only after it is complete. Thus, we - * (and hence the freezer) will block here until any currently running CPU - * hotplug operation gets completed. - */ -void cpu_hotplug_disable_before_freeze(void) -{ - cpu_maps_update_begin(); - cpu_hotplug_disabled = 1; - cpu_maps_update_done(); -} - - -/* - * When tasks have been thawed, re-enable regular CPU hotplug (which had been - * disabled while beginning to freeze tasks). - */ -void cpu_hotplug_enable_after_thaw(void) -{ - cpu_maps_update_begin(); - cpu_hotplug_disabled = 0; - cpu_maps_update_done(); -} - -/* * When callbacks for CPU hotplug notifications are being executed, we must * ensure that the state of the system with respect to the tasks being frozen * or not, as reported by the notification, remains unchanged *throughout the @@ -589,12 +580,12 @@ cpu_hotplug_pm_callback(struct notifier_block *nb, case PM_SUSPEND_PREPARE: case PM_HIBERNATION_PREPARE: - cpu_hotplug_disable_before_freeze(); + cpu_hotplug_disable(); break; case PM_POST_SUSPEND: case PM_POST_HIBERNATION: - cpu_hotplug_enable_after_thaw(); + cpu_hotplug_enable(); break; default: diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c index 8b86c0c68edf..e695c0a0bcb5 100644 --- a/kernel/cpu/idle.c +++ b/kernel/cpu/idle.c @@ -5,6 +5,7 @@ #include <linux/cpu.h> #include <linux/tick.h> #include <linux/mm.h> +#include <linux/stackprotector.h> #include <asm/tlb.h> @@ -40,11 +41,13 @@ __setup("hlt", cpu_idle_nopoll_setup); static inline int cpu_idle_poll(void) { + rcu_idle_enter(); trace_cpu_idle_rcuidle(0, smp_processor_id()); local_irq_enable(); while (!need_resched()) cpu_relax(); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); + rcu_idle_exit(); return 1; } @@ -56,6 +59,7 @@ void __weak arch_cpu_idle_dead(void) { } void __weak arch_cpu_idle(void) { cpu_idle_force_poll = 1; + local_irq_enable(); } /* @@ -110,6 +114,21 @@ static void cpu_idle_loop(void) void cpu_startup_entry(enum cpuhp_state state) { + /* + * This #ifdef needs to die, but it's too late in the cycle to + * make this generic (arm and sh have never invoked the canary + * init for the non boot cpus!). Will be fixed in 3.11 + */ +#ifdef CONFIG_X86 + /* + * If we're the non-boot CPU, nothing set the stack canary up + * for us. The boot CPU already has it initialized but no harm + * in doing it again. This is a good place for updating it, as + * we wont ever return from this function (so the invalid + * canaries already on the stack wont ever trigger). + */ + boot_init_stack_canary(); +#endif current_set_polling(); arch_cpu_idle_prepare(); cpu_idle_loop(); diff --git a/kernel/events/core.c b/kernel/events/core.c index 6b41c1899a8b..b391907d5352 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -196,9 +196,6 @@ static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx, static void update_context_time(struct perf_event_context *ctx); static u64 perf_event_time(struct perf_event *event); -static void ring_buffer_attach(struct perf_event *event, - struct ring_buffer *rb); - void __weak perf_event_print_debug(void) { } extern __weak const char *perf_pmu_name(void) @@ -2918,6 +2915,7 @@ static void free_event_rcu(struct rcu_head *head) } static void ring_buffer_put(struct ring_buffer *rb); +static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb); static void free_event(struct perf_event *event) { @@ -2942,15 +2940,30 @@ static void free_event(struct perf_event *event) if (has_branch_stack(event)) { static_key_slow_dec_deferred(&perf_sched_events); /* is system-wide event */ - if (!(event->attach_state & PERF_ATTACH_TASK)) + if (!(event->attach_state & PERF_ATTACH_TASK)) { atomic_dec(&per_cpu(perf_branch_stack_events, event->cpu)); + } } } if (event->rb) { - ring_buffer_put(event->rb); - event->rb = NULL; + struct ring_buffer *rb; + + /* + * Can happen when we close an event with re-directed output. + * + * Since we have a 0 refcount, perf_mmap_close() will skip + * over us; possibly making our ring_buffer_put() the last. + */ + mutex_lock(&event->mmap_mutex); + rb = event->rb; + if (rb) { + rcu_assign_pointer(event->rb, NULL); + ring_buffer_detach(event, rb); + ring_buffer_put(rb); /* could be last */ + } + mutex_unlock(&event->mmap_mutex); } if (is_cgroup_event(event)) @@ -3188,30 +3201,13 @@ static unsigned int perf_poll(struct file *file, poll_table *wait) unsigned int events = POLL_HUP; /* - * Race between perf_event_set_output() and perf_poll(): perf_poll() - * grabs the rb reference but perf_event_set_output() overrides it. - * Here is the timeline for two threads T1, T2: - * t0: T1, rb = rcu_dereference(event->rb) - * t1: T2, old_rb = event->rb - * t2: T2, event->rb = new rb - * t3: T2, ring_buffer_detach(old_rb) - * t4: T1, ring_buffer_attach(rb1) - * t5: T1, poll_wait(event->waitq) - * - * To avoid this problem, we grab mmap_mutex in perf_poll() - * thereby ensuring that the assignment of the new ring buffer - * and the detachment of the old buffer appear atomic to perf_poll() + * Pin the event->rb by taking event->mmap_mutex; otherwise + * perf_event_set_output() can swizzle our rb and make us miss wakeups. */ mutex_lock(&event->mmap_mutex); - - rcu_read_lock(); - rb = rcu_dereference(event->rb); - if (rb) { - ring_buffer_attach(event, rb); + rb = event->rb; + if (rb) events = atomic_xchg(&rb->poll, 0); - } - rcu_read_unlock(); - mutex_unlock(&event->mmap_mutex); poll_wait(file, &event->waitq, wait); @@ -3521,16 +3517,12 @@ static void ring_buffer_attach(struct perf_event *event, return; spin_lock_irqsave(&rb->event_lock, flags); - if (!list_empty(&event->rb_entry)) - goto unlock; - - list_add(&event->rb_entry, &rb->event_list); -unlock: + if (list_empty(&event->rb_entry)) + list_add(&event->rb_entry, &rb->event_list); spin_unlock_irqrestore(&rb->event_lock, flags); } -static void ring_buffer_detach(struct perf_event *event, - struct ring_buffer *rb) +static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb) { unsigned long flags; @@ -3549,13 +3541,10 @@ static void ring_buffer_wakeup(struct perf_event *event) rcu_read_lock(); rb = rcu_dereference(event->rb); - if (!rb) - goto unlock; - - list_for_each_entry_rcu(event, &rb->event_list, rb_entry) - wake_up_all(&event->waitq); - -unlock: + if (rb) { + list_for_each_entry_rcu(event, &rb->event_list, rb_entry) + wake_up_all(&event->waitq); + } rcu_read_unlock(); } @@ -3584,18 +3573,10 @@ static struct ring_buffer *ring_buffer_get(struct perf_event *event) static void ring_buffer_put(struct ring_buffer *rb) { - struct perf_event *event, *n; - unsigned long flags; - if (!atomic_dec_and_test(&rb->refcount)) return; - spin_lock_irqsave(&rb->event_lock, flags); - list_for_each_entry_safe(event, n, &rb->event_list, rb_entry) { - list_del_init(&event->rb_entry); - wake_up_all(&event->waitq); - } - spin_unlock_irqrestore(&rb->event_lock, flags); + WARN_ON_ONCE(!list_empty(&rb->event_list)); call_rcu(&rb->rcu_head, rb_free_rcu); } @@ -3605,26 +3586,100 @@ static void perf_mmap_open(struct vm_area_struct *vma) struct perf_event *event = vma->vm_file->private_data; atomic_inc(&event->mmap_count); + atomic_inc(&event->rb->mmap_count); } +/* + * A buffer can be mmap()ed multiple times; either directly through the same + * event, or through other events by use of perf_event_set_output(). + * + * In order to undo the VM accounting done by perf_mmap() we need to destroy + * the buffer here, where we still have a VM context. This means we need + * to detach all events redirecting to us. + */ static void perf_mmap_close(struct vm_area_struct *vma) { struct perf_event *event = vma->vm_file->private_data; - if (atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) { - unsigned long size = perf_data_size(event->rb); - struct user_struct *user = event->mmap_user; - struct ring_buffer *rb = event->rb; + struct ring_buffer *rb = event->rb; + struct user_struct *mmap_user = rb->mmap_user; + int mmap_locked = rb->mmap_locked; + unsigned long size = perf_data_size(rb); + + atomic_dec(&rb->mmap_count); + + if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) + return; + + /* Detach current event from the buffer. */ + rcu_assign_pointer(event->rb, NULL); + ring_buffer_detach(event, rb); + mutex_unlock(&event->mmap_mutex); - atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm); - vma->vm_mm->pinned_vm -= event->mmap_locked; - rcu_assign_pointer(event->rb, NULL); - ring_buffer_detach(event, rb); + /* If there's still other mmap()s of this buffer, we're done. */ + if (atomic_read(&rb->mmap_count)) { + ring_buffer_put(rb); /* can't be last */ + return; + } + + /* + * No other mmap()s, detach from all other events that might redirect + * into the now unreachable buffer. Somewhat complicated by the + * fact that rb::event_lock otherwise nests inside mmap_mutex. + */ +again: + rcu_read_lock(); + list_for_each_entry_rcu(event, &rb->event_list, rb_entry) { + if (!atomic_long_inc_not_zero(&event->refcount)) { + /* + * This event is en-route to free_event() which will + * detach it and remove it from the list. + */ + continue; + } + rcu_read_unlock(); + + mutex_lock(&event->mmap_mutex); + /* + * Check we didn't race with perf_event_set_output() which can + * swizzle the rb from under us while we were waiting to + * acquire mmap_mutex. + * + * If we find a different rb; ignore this event, a next + * iteration will no longer find it on the list. We have to + * still restart the iteration to make sure we're not now + * iterating the wrong list. + */ + if (event->rb == rb) { + rcu_assign_pointer(event->rb, NULL); + ring_buffer_detach(event, rb); + ring_buffer_put(rb); /* can't be last, we still have one */ + } mutex_unlock(&event->mmap_mutex); + put_event(event); - ring_buffer_put(rb); - free_uid(user); + /* + * Restart the iteration; either we're on the wrong list or + * destroyed its integrity by doing a deletion. + */ + goto again; } + rcu_read_unlock(); + + /* + * It could be there's still a few 0-ref events on the list; they'll + * get cleaned up by free_event() -- they'll also still have their + * ref on the rb and will free it whenever they are done with it. + * + * Aside from that, this buffer is 'fully' detached and unmapped, + * undo the VM accounting. + */ + + atomic_long_sub((size >> PAGE_SHIFT) + 1, &mmap_user->locked_vm); + vma->vm_mm->pinned_vm -= mmap_locked; + free_uid(mmap_user); + + ring_buffer_put(rb); /* could be last */ } static const struct vm_operations_struct perf_mmap_vmops = { @@ -3674,12 +3729,24 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) return -EINVAL; WARN_ON_ONCE(event->ctx->parent_ctx); +again: mutex_lock(&event->mmap_mutex); if (event->rb) { - if (event->rb->nr_pages == nr_pages) - atomic_inc(&event->rb->refcount); - else + if (event->rb->nr_pages != nr_pages) { ret = -EINVAL; + goto unlock; + } + + if (!atomic_inc_not_zero(&event->rb->mmap_count)) { + /* + * Raced against perf_mmap_close() through + * perf_event_set_output(). Try again, hope for better + * luck. + */ + mutex_unlock(&event->mmap_mutex); + goto again; + } + goto unlock; } @@ -3720,12 +3787,16 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma) ret = -ENOMEM; goto unlock; } - rcu_assign_pointer(event->rb, rb); + + atomic_set(&rb->mmap_count, 1); + rb->mmap_locked = extra; + rb->mmap_user = get_current_user(); atomic_long_add(user_extra, &user->locked_vm); - event->mmap_locked = extra; - event->mmap_user = get_current_user(); - vma->vm_mm->pinned_vm += event->mmap_locked; + vma->vm_mm->pinned_vm += extra; + + ring_buffer_attach(event, rb); + rcu_assign_pointer(event->rb, rb); perf_event_update_userpage(event); @@ -3734,7 +3805,11 @@ unlock: atomic_inc(&event->mmap_count); mutex_unlock(&event->mmap_mutex); - vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP; + /* + * Since pinned accounting is per vm we cannot allow fork() to copy our + * vma. + */ + vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP; vma->vm_ops = &perf_mmap_vmops; return ret; @@ -4394,6 +4469,64 @@ perf_event_read_event(struct perf_event *event, perf_output_end(&handle); } +typedef int (perf_event_aux_match_cb)(struct perf_event *event, void *data); +typedef void (perf_event_aux_output_cb)(struct perf_event *event, void *data); + +static void +perf_event_aux_ctx(struct perf_event_context *ctx, + perf_event_aux_match_cb match, + perf_event_aux_output_cb output, + void *data) +{ + struct perf_event *event; + + list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { + if (event->state < PERF_EVENT_STATE_INACTIVE) + continue; + if (!event_filter_match(event)) + continue; + if (match(event, data)) + output(event, data); + } +} + +static void +perf_event_aux(perf_event_aux_match_cb match, + perf_event_aux_output_cb output, + void *data, + struct perf_event_context *task_ctx) +{ + struct perf_cpu_context *cpuctx; + struct perf_event_context *ctx; + struct pmu *pmu; + int ctxn; + + rcu_read_lock(); + list_for_each_entry_rcu(pmu, &pmus, entry) { + cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); + if (cpuctx->unique_pmu != pmu) + goto next; + perf_event_aux_ctx(&cpuctx->ctx, match, output, data); + if (task_ctx) + goto next; + ctxn = pmu->task_ctx_nr; + if (ctxn < 0) + goto next; + ctx = rcu_dereference(current->perf_event_ctxp[ctxn]); + if (ctx) + perf_event_aux_ctx(ctx, match, output, data); +next: + put_cpu_ptr(pmu->pmu_cpu_context); + } + + if (task_ctx) { + preempt_disable(); + perf_event_aux_ctx(task_ctx, match, output, data); + preempt_enable(); + } + rcu_read_unlock(); +} + /* * task tracking -- fork/exit * @@ -4416,8 +4549,9 @@ struct perf_task_event { }; static void perf_event_task_output(struct perf_event *event, - struct perf_task_event *task_event) + void *data) { + struct perf_task_event *task_event = data; struct perf_output_handle handle; struct perf_sample_data sample; struct task_struct *task = task_event->task; @@ -4445,62 +4579,11 @@ out: task_event->event_id.header.size = size; } -static int perf_event_task_match(struct perf_event *event) -{ - if (event->state < PERF_EVENT_STATE_INACTIVE) - return 0; - - if (!event_filter_match(event)) - return 0; - - if (event->attr.comm || event->attr.mmap || - event->attr.mmap_data || event->attr.task) - return 1; - - return 0; -} - -static void perf_event_task_ctx(struct perf_event_context *ctx, - struct perf_task_event *task_event) +static int perf_event_task_match(struct perf_event *event, + void *data __maybe_unused) { - struct perf_event *event; - - list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { - if (perf_event_task_match(event)) - perf_event_task_output(event, task_event); - } -} - -static void perf_event_task_event(struct perf_task_event *task_event) -{ - struct perf_cpu_context *cpuctx; - struct perf_event_context *ctx; - struct pmu *pmu; - int ctxn; - - rcu_read_lock(); - list_for_each_entry_rcu(pmu, &pmus, entry) { - cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); - if (cpuctx->unique_pmu != pmu) - goto next; - perf_event_task_ctx(&cpuctx->ctx, task_event); - - ctx = task_event->task_ctx; - if (!ctx) { - ctxn = pmu->task_ctx_nr; - if (ctxn < 0) - goto next; - ctx = rcu_dereference(current->perf_event_ctxp[ctxn]); - if (ctx) - perf_event_task_ctx(ctx, task_event); - } -next: - put_cpu_ptr(pmu->pmu_cpu_context); - } - if (task_event->task_ctx) - perf_event_task_ctx(task_event->task_ctx, task_event); - - rcu_read_unlock(); + return event->attr.comm || event->attr.mmap || + event->attr.mmap_data || event->attr.task; } static void perf_event_task(struct task_struct *task, @@ -4531,7 +4614,10 @@ static void perf_event_task(struct task_struct *task, }, }; - perf_event_task_event(&task_event); + perf_event_aux(perf_event_task_match, + perf_event_task_output, + &task_event, + task_ctx); } void perf_event_fork(struct task_struct *task) @@ -4557,8 +4643,9 @@ struct perf_comm_event { }; static void perf_event_comm_output(struct perf_event *event, - struct perf_comm_event *comm_event) + void *data) { + struct perf_comm_event *comm_event = data; struct perf_output_handle handle; struct perf_sample_data sample; int size = comm_event->event_id.header.size; @@ -4585,39 +4672,16 @@ out: comm_event->event_id.header.size = size; } -static int perf_event_comm_match(struct perf_event *event) +static int perf_event_comm_match(struct perf_event *event, + void *data __maybe_unused) { - if (event->state < PERF_EVENT_STATE_INACTIVE) - return 0; - - if (!event_filter_match(event)) - return 0; - - if (event->attr.comm) - return 1; - - return 0; -} - -static void perf_event_comm_ctx(struct perf_event_context *ctx, - struct perf_comm_event *comm_event) -{ - struct perf_event *event; - - list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { - if (perf_event_comm_match(event)) - perf_event_comm_output(event, comm_event); - } + return event->attr.comm; } static void perf_event_comm_event(struct perf_comm_event *comm_event) { - struct perf_cpu_context *cpuctx; - struct perf_event_context *ctx; char comm[TASK_COMM_LEN]; unsigned int size; - struct pmu *pmu; - int ctxn; memset(comm, 0, sizeof(comm)); strlcpy(comm, comm_event->task->comm, sizeof(comm)); @@ -4627,24 +4691,11 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event) comm_event->comm_size = size; comm_event->event_id.header.size = sizeof(comm_event->event_id) + size; - rcu_read_lock(); - list_for_each_entry_rcu(pmu, &pmus, entry) { - cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); - if (cpuctx->unique_pmu != pmu) - goto next; - perf_event_comm_ctx(&cpuctx->ctx, comm_event); - ctxn = pmu->task_ctx_nr; - if (ctxn < 0) - goto next; - - ctx = rcu_dereference(current->perf_event_ctxp[ctxn]); - if (ctx) - perf_event_comm_ctx(ctx, comm_event); -next: - put_cpu_ptr(pmu->pmu_cpu_context); - } - rcu_read_unlock(); + perf_event_aux(perf_event_comm_match, + perf_event_comm_output, + comm_event, + NULL); } void perf_event_comm(struct task_struct *task) @@ -4706,8 +4757,9 @@ struct perf_mmap_event { }; static void perf_event_mmap_output(struct perf_event *event, - struct perf_mmap_event *mmap_event) + void *data) { + struct perf_mmap_event *mmap_event = data; struct perf_output_handle handle; struct perf_sample_data sample; int size = mmap_event->event_id.header.size; @@ -4734,46 +4786,24 @@ out: } static int perf_event_mmap_match(struct perf_event *event, - struct perf_mmap_event *mmap_event, - int executable) + void *data) { - if (event->state < PERF_EVENT_STATE_INACTIVE) - return 0; - - if (!event_filter_match(event)) - return 0; - - if ((!executable && event->attr.mmap_data) || - (executable && event->attr.mmap)) - return 1; - - return 0; -} - -static void perf_event_mmap_ctx(struct perf_event_context *ctx, - struct perf_mmap_event *mmap_event, - int executable) -{ - struct perf_event *event; + struct perf_mmap_event *mmap_event = data; + struct vm_area_struct *vma = mmap_event->vma; + int executable = vma->vm_flags & VM_EXEC; - list_for_each_entry_rcu(event, &ctx->event_list, event_entry) { - if (perf_event_mmap_match(event, mmap_event, executable)) - perf_event_mmap_output(event, mmap_event); - } + return (!executable && event->attr.mmap_data) || + (executable && event->attr.mmap); } static void perf_event_mmap_event(struct perf_mmap_event *mmap_event) { - struct perf_cpu_context *cpuctx; - struct perf_event_context *ctx; struct vm_area_struct *vma = mmap_event->vma; struct file *file = vma->vm_file; unsigned int size; char tmp[16]; char *buf = NULL; const char *name; - struct pmu *pmu; - int ctxn; memset(tmp, 0, sizeof(tmp)); @@ -4829,27 +4859,10 @@ got_name: mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size; - rcu_read_lock(); - list_for_each_entry_rcu(pmu, &pmus, entry) { - cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); - if (cpuctx->unique_pmu != pmu) - goto next; - perf_event_mmap_ctx(&cpuctx->ctx, mmap_event, - vma->vm_flags & VM_EXEC); - - ctxn = pmu->task_ctx_nr; - if (ctxn < 0) - goto next; - - ctx = rcu_dereference(current->perf_event_ctxp[ctxn]); - if (ctx) { - perf_event_mmap_ctx(ctx, mmap_event, - vma->vm_flags & VM_EXEC); - } -next: - put_cpu_ptr(pmu->pmu_cpu_context); - } - rcu_read_unlock(); + perf_event_aux(perf_event_mmap_match, + perf_event_mmap_output, + mmap_event, + NULL); kfree(buf); } @@ -6474,6 +6487,8 @@ set: if (atomic_read(&event->mmap_count)) goto unlock; + old_rb = event->rb; + if (output_event) { /* get the rb we want to redirect to */ rb = ring_buffer_get(output_event); @@ -6481,16 +6496,28 @@ set: goto unlock; } - old_rb = event->rb; - rcu_assign_pointer(event->rb, rb); if (old_rb) ring_buffer_detach(event, old_rb); + + if (rb) + ring_buffer_attach(event, rb); + + rcu_assign_pointer(event->rb, rb); + + if (old_rb) { + ring_buffer_put(old_rb); + /* + * Since we detached before setting the new rb, so that we + * could attach the new rb, we could have missed a wakeup. + * Provide it now. + */ + wake_up_all(&event->waitq); + } + ret = 0; unlock: mutex_unlock(&event->mmap_mutex); - if (old_rb) - ring_buffer_put(old_rb); out: return ret; } diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index a64f8aeb5c1f..20185ea64aa6 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -120,7 +120,7 @@ static int task_bp_pinned(int cpu, struct perf_event *bp, enum bp_type_idx type) list_for_each_entry(iter, &bp_task_head, hw.bp_list) { if (iter->hw.bp_target == tsk && find_slot_idx(iter) == type && - cpu == iter->cpu) + (iter->cpu < 0 || cpu == iter->cpu)) count += hw_breakpoint_weight(iter); } @@ -149,7 +149,7 @@ fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp, return; } - for_each_online_cpu(cpu) { + for_each_possible_cpu(cpu) { unsigned int nr; nr = per_cpu(nr_cpu_bp_pinned[type], cpu); @@ -235,7 +235,7 @@ toggle_bp_slot(struct perf_event *bp, bool enable, enum bp_type_idx type, if (cpu >= 0) { toggle_bp_task_slot(bp, cpu, enable, type, weight); } else { - for_each_online_cpu(cpu) + for_each_possible_cpu(cpu) toggle_bp_task_slot(bp, cpu, enable, type, weight); } diff --git a/kernel/events/internal.h b/kernel/events/internal.h index eb675c4d59df..ca6599723be5 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -31,6 +31,10 @@ struct ring_buffer { spinlock_t event_lock; struct list_head event_list; + atomic_t mmap_count; + unsigned long mmap_locked; + struct user_struct *mmap_user; + struct perf_event_mmap_page *user_page; void *data_pages[0]; }; diff --git a/kernel/exit.c b/kernel/exit.c index af2eb3cbd499..7bb73f9d09db 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -649,7 +649,6 @@ static void exit_notify(struct task_struct *tsk, int group_dead) * jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ forget_original_parent(tsk); - exit_task_namespaces(tsk); write_lock_irq(&tasklist_lock); if (group_dead) @@ -795,6 +794,7 @@ void do_exit(long code) exit_shm(tsk); exit_files(tsk); exit_fs(tsk); + exit_task_namespaces(tsk); exit_task_work(tsk); check_stack_usage(); exit_thread(); diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index fd4b13b131f8..3a951d8d5770 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -721,17 +721,20 @@ static int hrtimer_switch_to_hres(void) return 1; } +static void clock_was_set_work(struct work_struct *work) +{ + clock_was_set(); +} + +static DECLARE_WORK(hrtimer_work, clock_was_set_work); + /* - * Called from timekeeping code to reprogramm the hrtimer interrupt - * device. If called from the timer interrupt context we defer it to - * softirq context. + * Called from timekeeping and resume code to reprogramm the hrtimer + * interrupt device on all cpus. */ void clock_was_set_delayed(void) { - struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); - - cpu_base->clock_was_set = 1; - __raise_softirq_irqoff(HRTIMER_SOFTIRQ); + schedule_work(&hrtimer_work); } #else @@ -773,15 +776,19 @@ void clock_was_set(void) /* * During resume we might have to reprogram the high resolution timer - * interrupt (on the local CPU): + * interrupt on all online CPUs. However, all other CPUs will be + * stopped with IRQs interrupts disabled so the clock_was_set() call + * must be deferred. */ void hrtimers_resume(void) { WARN_ONCE(!irqs_disabled(), KERN_INFO "hrtimers_resume() called with IRQs enabled!"); + /* Retrigger on the local CPU */ retrigger_next_event(NULL); - timerfd_clock_was_set(); + /* And schedule a retrigger for all others */ + clock_was_set_delayed(); } static inline void timer_stats_hrtimer_set_start_info(struct hrtimer *timer) @@ -1432,13 +1439,6 @@ void hrtimer_peek_ahead_timers(void) static void run_hrtimer_softirq(struct softirq_action *h) { - struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases); - - if (cpu_base->clock_was_set) { - cpu_base->clock_was_set = 0; - clock_was_set(); - } - hrtimer_peek_ahead_timers(); } diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 5a83dde8ca0c..54a4d5223238 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -143,7 +143,10 @@ static unsigned int irq_domain_legacy_revmap(struct irq_domain *domain, * irq_domain_add_simple() - Allocate and register a simple irq_domain. * @of_node: pointer to interrupt controller's device tree node. * @size: total number of irqs in mapping - * @first_irq: first number of irq block assigned to the domain + * @first_irq: first number of irq block assigned to the domain, + * pass zero to assign irqs on-the-fly. This will result in a + * linear IRQ domain so it is important to use irq_create_mapping() + * for each used IRQ, especially when SPARSE_IRQ is enabled. * @ops: map/unmap domain callbacks * @host_data: Controller private data pointer * @@ -191,6 +194,7 @@ struct irq_domain *irq_domain_add_simple(struct device_node *of_node, /* A linear domain is the default */ return irq_domain_add_linear(of_node, size, ops, host_data); } +EXPORT_SYMBOL_GPL(irq_domain_add_simple); /** * irq_domain_add_legacy() - Allocate and register a legacy revmap irq_domain. @@ -397,11 +401,12 @@ static void irq_domain_disassociate_many(struct irq_domain *domain, while (count--) { int irq = irq_base + count; struct irq_data *irq_data = irq_get_irq_data(irq); - irq_hw_number_t hwirq = irq_data->hwirq; + irq_hw_number_t hwirq; if (WARN_ON(!irq_data || irq_data->domain != domain)) continue; + hwirq = irq_data->hwirq; irq_set_status_flags(irq, IRQ_NOREQUEST); /* remove chip and handler */ diff --git a/kernel/kmod.c b/kernel/kmod.c index 1296e72e4161..8241906c4b61 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -569,6 +569,11 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, int wait) int retval = 0; helper_lock(); + if (!sub_info->path) { + retval = -EINVAL; + goto out; + } + if (sub_info->path[0] == '\0') goto out; diff --git a/kernel/kprobes.c b/kernel/kprobes.c index 3fed7f0cbcdf..bddf3b201a48 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -467,6 +467,7 @@ static struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr) /* Optimization staging list, protected by kprobe_mutex */ static LIST_HEAD(optimizing_list); static LIST_HEAD(unoptimizing_list); +static LIST_HEAD(freeing_list); static void kprobe_optimizer(struct work_struct *work); static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer); @@ -504,7 +505,7 @@ static __kprobes void do_optimize_kprobes(void) * Unoptimize (replace a jump with a breakpoint and remove the breakpoint * if need) kprobes listed on unoptimizing_list. */ -static __kprobes void do_unoptimize_kprobes(struct list_head *free_list) +static __kprobes void do_unoptimize_kprobes(void) { struct optimized_kprobe *op, *tmp; @@ -515,9 +516,9 @@ static __kprobes void do_unoptimize_kprobes(struct list_head *free_list) /* Ditto to do_optimize_kprobes */ get_online_cpus(); mutex_lock(&text_mutex); - arch_unoptimize_kprobes(&unoptimizing_list, free_list); + arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list); /* Loop free_list for disarming */ - list_for_each_entry_safe(op, tmp, free_list, list) { + list_for_each_entry_safe(op, tmp, &freeing_list, list) { /* Disarm probes if marked disabled */ if (kprobe_disabled(&op->kp)) arch_disarm_kprobe(&op->kp); @@ -536,11 +537,11 @@ static __kprobes void do_unoptimize_kprobes(struct list_head *free_list) } /* Reclaim all kprobes on the free_list */ -static __kprobes void do_free_cleaned_kprobes(struct list_head *free_list) +static __kprobes void do_free_cleaned_kprobes(void) { struct optimized_kprobe *op, *tmp; - list_for_each_entry_safe(op, tmp, free_list, list) { + list_for_each_entry_safe(op, tmp, &freeing_list, list) { BUG_ON(!kprobe_unused(&op->kp)); list_del_init(&op->list); free_aggr_kprobe(&op->kp); @@ -556,8 +557,6 @@ static __kprobes void kick_kprobe_optimizer(void) /* Kprobe jump optimizer */ static __kprobes void kprobe_optimizer(struct work_struct *work) { - LIST_HEAD(free_list); - mutex_lock(&kprobe_mutex); /* Lock modules while optimizing kprobes */ mutex_lock(&module_mutex); @@ -566,7 +565,7 @@ static __kprobes void kprobe_optimizer(struct work_struct *work) * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed) * kprobes before waiting for quiesence period. */ - do_unoptimize_kprobes(&free_list); + do_unoptimize_kprobes(); /* * Step 2: Wait for quiesence period to ensure all running interrupts @@ -581,7 +580,7 @@ static __kprobes void kprobe_optimizer(struct work_struct *work) do_optimize_kprobes(); /* Step 4: Free cleaned kprobes after quiesence period */ - do_free_cleaned_kprobes(&free_list); + do_free_cleaned_kprobes(); mutex_unlock(&module_mutex); mutex_unlock(&kprobe_mutex); @@ -723,8 +722,19 @@ static void __kprobes kill_optimized_kprobe(struct kprobe *p) if (!list_empty(&op->list)) /* Dequeue from the (un)optimization queue */ list_del_init(&op->list); - op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED; + + if (kprobe_unused(p)) { + /* Enqueue if it is unused */ + list_add(&op->list, &freeing_list); + /* + * Remove unused probes from the hash list. After waiting + * for synchronization, this probe is reclaimed. + * (reclaiming is done by do_free_cleaned_kprobes().) + */ + hlist_del_rcu(&op->kp.hlist); + } + /* Don't touch the code, because it is already freed. */ arch_remove_optimized_kprobe(op); } diff --git a/kernel/module.c b/kernel/module.c index b049939177f6..cab4bce49c23 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2431,10 +2431,10 @@ static void kmemleak_load_module(const struct module *mod, kmemleak_scan_area(mod, sizeof(struct module), GFP_KERNEL); for (i = 1; i < info->hdr->e_shnum; i++) { - const char *name = info->secstrings + info->sechdrs[i].sh_name; - if (!(info->sechdrs[i].sh_flags & SHF_ALLOC)) - continue; - if (!strstarts(name, ".data") && !strstarts(name, ".bss")) + /* Scan all writable sections that's not executable */ + if (!(info->sechdrs[i].sh_flags & SHF_ALLOC) || + !(info->sechdrs[i].sh_flags & SHF_WRITE) || + (info->sechdrs[i].sh_flags & SHF_EXECINSTR)) continue; kmemleak_scan_area((void *)info->sechdrs[i].sh_addr, @@ -2769,24 +2769,11 @@ static void find_module_sections(struct module *mod, struct load_info *info) mod->trace_events = section_objs(info, "_ftrace_events", sizeof(*mod->trace_events), &mod->num_trace_events); - /* - * This section contains pointers to allocated objects in the trace - * code and not scanning it leads to false positives. - */ - kmemleak_scan_area(mod->trace_events, sizeof(*mod->trace_events) * - mod->num_trace_events, GFP_KERNEL); #endif #ifdef CONFIG_TRACING mod->trace_bprintk_fmt_start = section_objs(info, "__trace_printk_fmt", sizeof(*mod->trace_bprintk_fmt_start), &mod->num_trace_bprintk_fmt); - /* - * This section contains pointers to allocated objects in the trace - * code and not scanning it leads to false positives. - */ - kmemleak_scan_area(mod->trace_bprintk_fmt_start, - sizeof(*mod->trace_bprintk_fmt_start) * - mod->num_trace_bprintk_fmt, GFP_KERNEL); #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD /* sechdrs[0].sh_size is always zero */ diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 42670e9b44e0..c7f31aa272f7 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -51,59 +51,28 @@ static int check_clock(const clockid_t which_clock) return error; } -static inline union cpu_time_count +static inline unsigned long long timespec_to_sample(const clockid_t which_clock, const struct timespec *tp) { - union cpu_time_count ret; - ret.sched = 0; /* high half always zero when .cpu used */ + unsigned long long ret; + + ret = 0; /* high half always zero when .cpu used */ if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { - ret.sched = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec; + ret = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec; } else { - ret.cpu = timespec_to_cputime(tp); + ret = cputime_to_expires(timespec_to_cputime(tp)); } return ret; } static void sample_to_timespec(const clockid_t which_clock, - union cpu_time_count cpu, + unsigned long long expires, struct timespec *tp) { if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) - *tp = ns_to_timespec(cpu.sched); + *tp = ns_to_timespec(expires); else - cputime_to_timespec(cpu.cpu, tp); -} - -static inline int cpu_time_before(const clockid_t which_clock, - union cpu_time_count now, - union cpu_time_count then) -{ - if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { - return now.sched < then.sched; - } else { - return now.cpu < then.cpu; - } -} -static inline void cpu_time_add(const clockid_t which_clock, - union cpu_time_count *acc, - union cpu_time_count val) -{ - if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { - acc->sched += val.sched; - } else { - acc->cpu += val.cpu; - } -} -static inline union cpu_time_count cpu_time_sub(const clockid_t which_clock, - union cpu_time_count a, - union cpu_time_count b) -{ - if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { - a.sched -= b.sched; - } else { - a.cpu -= b.cpu; - } - return a; + cputime_to_timespec((__force cputime_t)expires, tp); } /* @@ -111,47 +80,31 @@ static inline union cpu_time_count cpu_time_sub(const clockid_t which_clock, * given the current clock sample. */ static void bump_cpu_timer(struct k_itimer *timer, - union cpu_time_count now) + unsigned long long now) { int i; + unsigned long long delta, incr; - if (timer->it.cpu.incr.sched == 0) + if (timer->it.cpu.incr == 0) return; - if (CPUCLOCK_WHICH(timer->it_clock) == CPUCLOCK_SCHED) { - unsigned long long delta, incr; + if (now < timer->it.cpu.expires) + return; - if (now.sched < timer->it.cpu.expires.sched) - return; - incr = timer->it.cpu.incr.sched; - delta = now.sched + incr - timer->it.cpu.expires.sched; - /* Don't use (incr*2 < delta), incr*2 might overflow. */ - for (i = 0; incr < delta - incr; i++) - incr = incr << 1; - for (; i >= 0; incr >>= 1, i--) { - if (delta < incr) - continue; - timer->it.cpu.expires.sched += incr; - timer->it_overrun += 1 << i; - delta -= incr; - } - } else { - cputime_t delta, incr; + incr = timer->it.cpu.incr; + delta = now + incr - timer->it.cpu.expires; - if (now.cpu < timer->it.cpu.expires.cpu) - return; - incr = timer->it.cpu.incr.cpu; - delta = now.cpu + incr - timer->it.cpu.expires.cpu; - /* Don't use (incr*2 < delta), incr*2 might overflow. */ - for (i = 0; incr < delta - incr; i++) - incr += incr; - for (; i >= 0; incr = incr >> 1, i--) { - if (delta < incr) - continue; - timer->it.cpu.expires.cpu += incr; - timer->it_overrun += 1 << i; - delta -= incr; - } + /* Don't use (incr*2 < delta), incr*2 might overflow. */ + for (i = 0; incr < delta - incr; i++) + incr = incr << 1; + + for (; i >= 0; incr >>= 1, i--) { + if (delta < incr) + continue; + + timer->it.cpu.expires += incr; + timer->it_overrun += 1 << i; + delta -= incr; } } @@ -170,21 +123,21 @@ static inline int task_cputime_zero(const struct task_cputime *cputime) return 0; } -static inline cputime_t prof_ticks(struct task_struct *p) +static inline unsigned long long prof_ticks(struct task_struct *p) { cputime_t utime, stime; task_cputime(p, &utime, &stime); - return utime + stime; + return cputime_to_expires(utime + stime); } -static inline cputime_t virt_ticks(struct task_struct *p) +static inline unsigned long long virt_ticks(struct task_struct *p) { cputime_t utime; task_cputime(p, &utime, NULL); - return utime; + return cputime_to_expires(utime); } static int @@ -225,19 +178,19 @@ posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp) * Sample a per-thread clock for the given task. */ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, - union cpu_time_count *cpu) + unsigned long long *sample) { switch (CPUCLOCK_WHICH(which_clock)) { default: return -EINVAL; case CPUCLOCK_PROF: - cpu->cpu = prof_ticks(p); + *sample = prof_ticks(p); break; case CPUCLOCK_VIRT: - cpu->cpu = virt_ticks(p); + *sample = virt_ticks(p); break; case CPUCLOCK_SCHED: - cpu->sched = task_sched_runtime(p); + *sample = task_sched_runtime(p); break; } return 0; @@ -284,7 +237,7 @@ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times) */ static int cpu_clock_sample_group(const clockid_t which_clock, struct task_struct *p, - union cpu_time_count *cpu) + unsigned long long *sample) { struct task_cputime cputime; @@ -293,15 +246,15 @@ static int cpu_clock_sample_group(const clockid_t which_clock, return -EINVAL; case CPUCLOCK_PROF: thread_group_cputime(p, &cputime); - cpu->cpu = cputime.utime + cputime.stime; + *sample = cputime_to_expires(cputime.utime + cputime.stime); break; case CPUCLOCK_VIRT: thread_group_cputime(p, &cputime); - cpu->cpu = cputime.utime; + *sample = cputime_to_expires(cputime.utime); break; case CPUCLOCK_SCHED: thread_group_cputime(p, &cputime); - cpu->sched = cputime.sum_exec_runtime; + *sample = cputime.sum_exec_runtime; break; } return 0; @@ -312,7 +265,7 @@ static int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp) { const pid_t pid = CPUCLOCK_PID(which_clock); int error = -EINVAL; - union cpu_time_count rtn; + unsigned long long rtn; if (pid == 0) { /* @@ -446,6 +399,15 @@ static int posix_cpu_timer_del(struct k_itimer *timer) return ret; } +static void cleanup_timers_list(struct list_head *head, + unsigned long long curr) +{ + struct cpu_timer_list *timer, *next; + + list_for_each_entry_safe(timer, next, head, entry) + list_del_init(&timer->entry); +} + /* * Clean out CPU timers still ticking when a thread exited. The task * pointer is cleared, and the expiry time is replaced with the residual @@ -456,37 +418,12 @@ static void cleanup_timers(struct list_head *head, cputime_t utime, cputime_t stime, unsigned long long sum_exec_runtime) { - struct cpu_timer_list *timer, *next; - cputime_t ptime = utime + stime; - - list_for_each_entry_safe(timer, next, head, entry) { - list_del_init(&timer->entry); - if (timer->expires.cpu < ptime) { - timer->expires.cpu = 0; - } else { - timer->expires.cpu -= ptime; - } - } - ++head; - list_for_each_entry_safe(timer, next, head, entry) { - list_del_init(&timer->entry); - if (timer->expires.cpu < utime) { - timer->expires.cpu = 0; - } else { - timer->expires.cpu -= utime; - } - } + cputime_t ptime = utime + stime; - ++head; - list_for_each_entry_safe(timer, next, head, entry) { - list_del_init(&timer->entry); - if (timer->expires.sched < sum_exec_runtime) { - timer->expires.sched = 0; - } else { - timer->expires.sched -= sum_exec_runtime; - } - } + cleanup_timers_list(head, cputime_to_expires(ptime)); + cleanup_timers_list(++head, cputime_to_expires(utime)); + cleanup_timers_list(++head, sum_exec_runtime); } /* @@ -516,17 +453,21 @@ void posix_cpu_timers_exit_group(struct task_struct *tsk) tsk->se.sum_exec_runtime + sig->sum_sched_runtime); } -static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now) +static void clear_dead_task(struct k_itimer *itimer, unsigned long long now) { + struct cpu_timer_list *timer = &itimer->it.cpu; + /* * That's all for this thread or process. * We leave our residual in expires to be reported. */ - put_task_struct(timer->it.cpu.task); - timer->it.cpu.task = NULL; - timer->it.cpu.expires = cpu_time_sub(timer->it_clock, - timer->it.cpu.expires, - now); + put_task_struct(timer->task); + timer->task = NULL; + if (timer->expires < now) { + timer->expires = 0; + } else { + timer->expires -= now; + } } static inline int expires_gt(cputime_t expires, cputime_t new_exp) @@ -558,14 +499,14 @@ static void arm_timer(struct k_itimer *timer) listpos = head; list_for_each_entry(next, head, entry) { - if (cpu_time_before(timer->it_clock, nt->expires, next->expires)) + if (nt->expires < next->expires) break; listpos = &next->entry; } list_add(&nt->entry, listpos); if (listpos == head) { - union cpu_time_count *exp = &nt->expires; + unsigned long long exp = nt->expires; /* * We are the new earliest-expiring POSIX 1.b timer, hence @@ -576,17 +517,17 @@ static void arm_timer(struct k_itimer *timer) switch (CPUCLOCK_WHICH(timer->it_clock)) { case CPUCLOCK_PROF: - if (expires_gt(cputime_expires->prof_exp, exp->cpu)) - cputime_expires->prof_exp = exp->cpu; + if (expires_gt(cputime_expires->prof_exp, expires_to_cputime(exp))) + cputime_expires->prof_exp = expires_to_cputime(exp); break; case CPUCLOCK_VIRT: - if (expires_gt(cputime_expires->virt_exp, exp->cpu)) - cputime_expires->virt_exp = exp->cpu; + if (expires_gt(cputime_expires->virt_exp, expires_to_cputime(exp))) + cputime_expires->virt_exp = expires_to_cputime(exp); break; case CPUCLOCK_SCHED: if (cputime_expires->sched_exp == 0 || - cputime_expires->sched_exp > exp->sched) - cputime_expires->sched_exp = exp->sched; + cputime_expires->sched_exp > exp) + cputime_expires->sched_exp = exp; break; } } @@ -601,20 +542,20 @@ static void cpu_timer_fire(struct k_itimer *timer) /* * User don't want any signal. */ - timer->it.cpu.expires.sched = 0; + timer->it.cpu.expires = 0; } else if (unlikely(timer->sigq == NULL)) { /* * This a special case for clock_nanosleep, * not a normal timer from sys_timer_create. */ wake_up_process(timer->it_process); - timer->it.cpu.expires.sched = 0; - } else if (timer->it.cpu.incr.sched == 0) { + timer->it.cpu.expires = 0; + } else if (timer->it.cpu.incr == 0) { /* * One-shot timer. Clear it as soon as it's fired. */ posix_timer_event(timer, 0); - timer->it.cpu.expires.sched = 0; + timer->it.cpu.expires = 0; } else if (posix_timer_event(timer, ++timer->it_requeue_pending)) { /* * The signal did not get queued because the signal @@ -632,7 +573,7 @@ static void cpu_timer_fire(struct k_itimer *timer) */ static int cpu_timer_sample_group(const clockid_t which_clock, struct task_struct *p, - union cpu_time_count *cpu) + unsigned long long *sample) { struct task_cputime cputime; @@ -641,13 +582,13 @@ static int cpu_timer_sample_group(const clockid_t which_clock, default: return -EINVAL; case CPUCLOCK_PROF: - cpu->cpu = cputime.utime + cputime.stime; + *sample = cputime_to_expires(cputime.utime + cputime.stime); break; case CPUCLOCK_VIRT: - cpu->cpu = cputime.utime; + *sample = cputime_to_expires(cputime.utime); break; case CPUCLOCK_SCHED: - cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p); + *sample = cputime.sum_exec_runtime + task_delta_exec(p); break; } return 0; @@ -694,7 +635,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, struct itimerspec *new, struct itimerspec *old) { struct task_struct *p = timer->it.cpu.task; - union cpu_time_count old_expires, new_expires, old_incr, val; + unsigned long long old_expires, new_expires, old_incr, val; int ret; if (unlikely(p == NULL)) { @@ -749,7 +690,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, } if (old) { - if (old_expires.sched == 0) { + if (old_expires == 0) { old->it_value.tv_sec = 0; old->it_value.tv_nsec = 0; } else { @@ -764,11 +705,8 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, * new setting. */ bump_cpu_timer(timer, val); - if (cpu_time_before(timer->it_clock, val, - timer->it.cpu.expires)) { - old_expires = cpu_time_sub( - timer->it_clock, - timer->it.cpu.expires, val); + if (val < timer->it.cpu.expires) { + old_expires = timer->it.cpu.expires - val; sample_to_timespec(timer->it_clock, old_expires, &old->it_value); @@ -791,8 +729,8 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, goto out; } - if (new_expires.sched != 0 && !(flags & TIMER_ABSTIME)) { - cpu_time_add(timer->it_clock, &new_expires, val); + if (new_expires != 0 && !(flags & TIMER_ABSTIME)) { + new_expires += val; } /* @@ -801,8 +739,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, * arm the timer (we'll just fake it for timer_gettime). */ timer->it.cpu.expires = new_expires; - if (new_expires.sched != 0 && - cpu_time_before(timer->it_clock, val, new_expires)) { + if (new_expires != 0 && val < new_expires) { arm_timer(timer); } @@ -826,8 +763,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, timer->it_overrun_last = 0; timer->it_overrun = -1; - if (new_expires.sched != 0 && - !cpu_time_before(timer->it_clock, val, new_expires)) { + if (new_expires != 0 && !(val < new_expires)) { /* * The designated time already passed, so we notify * immediately, even if the thread never runs to @@ -849,7 +785,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int flags, static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) { - union cpu_time_count now; + unsigned long long now; struct task_struct *p = timer->it.cpu.task; int clear_dead; @@ -859,7 +795,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) sample_to_timespec(timer->it_clock, timer->it.cpu.incr, &itp->it_interval); - if (timer->it.cpu.expires.sched == 0) { /* Timer not armed at all. */ + if (timer->it.cpu.expires == 0) { /* Timer not armed at all. */ itp->it_value.tv_sec = itp->it_value.tv_nsec = 0; return; } @@ -891,7 +827,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) */ put_task_struct(p); timer->it.cpu.task = NULL; - timer->it.cpu.expires.sched = 0; + timer->it.cpu.expires = 0; read_unlock(&tasklist_lock); goto dead; } else { @@ -912,10 +848,9 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) goto dead; } - if (cpu_time_before(timer->it_clock, now, timer->it.cpu.expires)) { + if (now < timer->it.cpu.expires) { sample_to_timespec(timer->it_clock, - cpu_time_sub(timer->it_clock, - timer->it.cpu.expires, now), + timer->it.cpu.expires - now, &itp->it_value); } else { /* @@ -927,6 +862,28 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) } } +static unsigned long long +check_timers_list(struct list_head *timers, + struct list_head *firing, + unsigned long long curr) +{ + int maxfire = 20; + + while (!list_empty(timers)) { + struct cpu_timer_list *t; + + t = list_first_entry(timers, struct cpu_timer_list, entry); + + if (!--maxfire || curr < t->expires) + return t->expires; + + t->firing = 1; + list_move_tail(&t->entry, firing); + } + + return 0; +} + /* * Check for any per-thread CPU timers that have fired and move them off * the tsk->cpu_timers[N] list onto the firing list. Here we update the @@ -935,54 +892,20 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec *itp) static void check_thread_timers(struct task_struct *tsk, struct list_head *firing) { - int maxfire; struct list_head *timers = tsk->cpu_timers; struct signal_struct *const sig = tsk->signal; + struct task_cputime *tsk_expires = &tsk->cputime_expires; + unsigned long long expires; unsigned long soft; - maxfire = 20; - tsk->cputime_expires.prof_exp = 0; - while (!list_empty(timers)) { - struct cpu_timer_list *t = list_first_entry(timers, - struct cpu_timer_list, - entry); - if (!--maxfire || prof_ticks(tsk) < t->expires.cpu) { - tsk->cputime_expires.prof_exp = t->expires.cpu; - break; - } - t->firing = 1; - list_move_tail(&t->entry, firing); - } + expires = check_timers_list(timers, firing, prof_ticks(tsk)); + tsk_expires->prof_exp = expires_to_cputime(expires); - ++timers; - maxfire = 20; - tsk->cputime_expires.virt_exp = 0; - while (!list_empty(timers)) { - struct cpu_timer_list *t = list_first_entry(timers, - struct cpu_timer_list, - entry); - if (!--maxfire || virt_ticks(tsk) < t->expires.cpu) { - tsk->cputime_expires.virt_exp = t->expires.cpu; - break; - } - t->firing = 1; - list_move_tail(&t->entry, firing); - } + expires = check_timers_list(++timers, firing, virt_ticks(tsk)); + tsk_expires->virt_exp = expires_to_cputime(expires); - ++timers; - maxfire = 20; - tsk->cputime_expires.sched_exp = 0; - while (!list_empty(timers)) { - struct cpu_timer_list *t = list_first_entry(timers, - struct cpu_timer_list, - entry); - if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) { - tsk->cputime_expires.sched_exp = t->expires.sched; - break; - } - t->firing = 1; - list_move_tail(&t->entry, firing); - } + tsk_expires->sched_exp = check_timers_list(++timers, firing, + tsk->se.sum_exec_runtime); /* * Check for the special case thread timers. @@ -1030,7 +953,8 @@ static void stop_process_timers(struct signal_struct *sig) static u32 onecputick; static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it, - cputime_t *expires, cputime_t cur_time, int signo) + unsigned long long *expires, + unsigned long long cur_time, int signo) { if (!it->expires) return; @@ -1066,9 +990,8 @@ static void check_cpu_itimer(struct task_struct *tsk, struct cpu_itimer *it, static void check_process_timers(struct task_struct *tsk, struct list_head *firing) { - int maxfire; struct signal_struct *const sig = tsk->signal; - cputime_t utime, ptime, virt_expires, prof_expires; + unsigned long long utime, ptime, virt_expires, prof_expires; unsigned long long sum_sched_runtime, sched_expires; struct list_head *timers = sig->cpu_timers; struct task_cputime cputime; @@ -1078,52 +1001,13 @@ static void check_process_timers(struct task_struct *tsk, * Collect the current process totals. */ thread_group_cputimer(tsk, &cputime); - utime = cputime.utime; - ptime = utime + cputime.stime; + utime = cputime_to_expires(cputime.utime); + ptime = utime + cputime_to_expires(cputime.stime); sum_sched_runtime = cputime.sum_exec_runtime; - maxfire = 20; - prof_expires = 0; - while (!list_empty(timers)) { - struct cpu_timer_list *tl = list_first_entry(timers, - struct cpu_timer_list, - entry); - if (!--maxfire || ptime < tl->expires.cpu) { - prof_expires = tl->expires.cpu; - break; - } - tl->firing = 1; - list_move_tail(&tl->entry, firing); - } - ++timers; - maxfire = 20; - virt_expires = 0; - while (!list_empty(timers)) { - struct cpu_timer_list *tl = list_first_entry(timers, - struct cpu_timer_list, - entry); - if (!--maxfire || utime < tl->expires.cpu) { - virt_expires = tl->expires.cpu; - break; - } - tl->firing = 1; - list_move_tail(&tl->entry, firing); - } - - ++timers; - maxfire = 20; - sched_expires = 0; - while (!list_empty(timers)) { - struct cpu_timer_list *tl = list_first_entry(timers, - struct cpu_timer_list, - entry); - if (!--maxfire || sum_sched_runtime < tl->expires.sched) { - sched_expires = tl->expires.sched; - break; - } - tl->firing = 1; - list_move_tail(&tl->entry, firing); - } + prof_expires = check_timers_list(timers, firing, ptime); + virt_expires = check_timers_list(++timers, firing, utime); + sched_expires = check_timers_list(++timers, firing, sum_sched_runtime); /* * Check for the special case process timers. @@ -1162,8 +1046,8 @@ static void check_process_timers(struct task_struct *tsk, } } - sig->cputime_expires.prof_exp = prof_expires; - sig->cputime_expires.virt_exp = virt_expires; + sig->cputime_expires.prof_exp = expires_to_cputime(prof_expires); + sig->cputime_expires.virt_exp = expires_to_cputime(virt_expires); sig->cputime_expires.sched_exp = sched_expires; if (task_cputime_zero(&sig->cputime_expires)) stop_process_timers(sig); @@ -1176,7 +1060,7 @@ static void check_process_timers(struct task_struct *tsk, void posix_cpu_timer_schedule(struct k_itimer *timer) { struct task_struct *p = timer->it.cpu.task; - union cpu_time_count now; + unsigned long long now; if (unlikely(p == NULL)) /* @@ -1205,7 +1089,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer) */ put_task_struct(p); timer->it.cpu.task = p = NULL; - timer->it.cpu.expires.sched = 0; + timer->it.cpu.expires = 0; goto out_unlock; } else if (unlikely(p->exit_state) && thread_group_empty(p)) { /* @@ -1213,6 +1097,7 @@ void posix_cpu_timer_schedule(struct k_itimer *timer) * not yet reaped. Take this opportunity to * drop our task ref. */ + cpu_timer_sample_group(timer->it_clock, p, &now); clear_dead_task(timer, now); goto out_unlock; } @@ -1387,7 +1272,7 @@ void run_posix_cpu_timers(struct task_struct *tsk) void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, cputime_t *newval, cputime_t *oldval) { - union cpu_time_count now; + unsigned long long now; BUG_ON(clock_idx == CPUCLOCK_SCHED); cpu_timer_sample_group(clock_idx, tsk, &now); @@ -1399,17 +1284,17 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, * it to be absolute. */ if (*oldval) { - if (*oldval <= now.cpu) { + if (*oldval <= now) { /* Just about to fire. */ *oldval = cputime_one_jiffy; } else { - *oldval -= now.cpu; + *oldval -= now; } } if (!*newval) goto out; - *newval += now.cpu; + *newval += now; } /* @@ -1459,7 +1344,7 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, } while (!signal_pending(current)) { - if (timer.it.cpu.expires.sched == 0) { + if (timer.it.cpu.expires == 0) { /* * Our timer fired and was reset, below * deletion can not fail. diff --git a/kernel/printk.c b/kernel/printk.c index fa36e1494420..8212c1aef125 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -363,6 +363,53 @@ static void log_store(int facility, int level, log_next_seq++; } +#ifdef CONFIG_SECURITY_DMESG_RESTRICT +int dmesg_restrict = 1; +#else +int dmesg_restrict; +#endif + +static int syslog_action_restricted(int type) +{ + if (dmesg_restrict) + return 1; + /* + * Unless restricted, we allow "read all" and "get buffer size" + * for everybody. + */ + return type != SYSLOG_ACTION_READ_ALL && + type != SYSLOG_ACTION_SIZE_BUFFER; +} + +static int check_syslog_permissions(int type, bool from_file) +{ + /* + * If this is from /proc/kmsg and we've already opened it, then we've + * already done the capabilities checks at open time. + */ + if (from_file && type != SYSLOG_ACTION_OPEN) + return 0; + + if (syslog_action_restricted(type)) { + if (capable(CAP_SYSLOG)) + return 0; + /* + * For historical reasons, accept CAP_SYS_ADMIN too, with + * a warning. + */ + if (capable(CAP_SYS_ADMIN)) { + pr_warn_once("%s (%d): Attempt to access syslog with " + "CAP_SYS_ADMIN but no CAP_SYSLOG " + "(deprecated).\n", + current->comm, task_pid_nr(current)); + return 0; + } + return -EPERM; + } + return security_syslog(type); +} + + /* /dev/kmsg - userspace message inject/listen interface */ struct devkmsg_user { u64 seq; @@ -620,7 +667,8 @@ static int devkmsg_open(struct inode *inode, struct file *file) if ((file->f_flags & O_ACCMODE) == O_WRONLY) return 0; - err = security_syslog(SYSLOG_ACTION_READ_ALL); + err = check_syslog_permissions(SYSLOG_ACTION_READ_ALL, + SYSLOG_FROM_READER); if (err) return err; @@ -813,45 +861,6 @@ static inline void boot_delay_msec(int level) } #endif -#ifdef CONFIG_SECURITY_DMESG_RESTRICT -int dmesg_restrict = 1; -#else -int dmesg_restrict; -#endif - -static int syslog_action_restricted(int type) -{ - if (dmesg_restrict) - return 1; - /* Unless restricted, we allow "read all" and "get buffer size" for everybody */ - return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER; -} - -static int check_syslog_permissions(int type, bool from_file) -{ - /* - * If this is from /proc/kmsg and we've already opened it, then we've - * already done the capabilities checks at open time. - */ - if (from_file && type != SYSLOG_ACTION_OPEN) - return 0; - - if (syslog_action_restricted(type)) { - if (capable(CAP_SYSLOG)) - return 0; - /* For historical reasons, accept CAP_SYS_ADMIN too, with a warning */ - if (capable(CAP_SYS_ADMIN)) { - printk_once(KERN_WARNING "%s (%d): " - "Attempt to access syslog with CAP_SYS_ADMIN " - "but no CAP_SYSLOG (deprecated).\n", - current->comm, task_pid_nr(current)); - return 0; - } - return -EPERM; - } - return 0; -} - #if defined(CONFIG_PRINTK_TIME) static bool printk_time = 1; #else @@ -1249,7 +1258,7 @@ out: SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len) { - return do_syslog(type, buf, len, SYSLOG_FROM_CALL); + return do_syslog(type, buf, len, SYSLOG_FROM_READER); } /* diff --git a/kernel/ptrace.c b/kernel/ptrace.c index aed981a3f69c..335a7ae697f5 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -665,20 +665,22 @@ static int ptrace_peek_siginfo(struct task_struct *child, if (unlikely(is_compat_task())) { compat_siginfo_t __user *uinfo = compat_ptr(data); - ret = copy_siginfo_to_user32(uinfo, &info); - ret |= __put_user(info.si_code, &uinfo->si_code); + if (copy_siginfo_to_user32(uinfo, &info) || + __put_user(info.si_code, &uinfo->si_code)) { + ret = -EFAULT; + break; + } + } else #endif { siginfo_t __user *uinfo = (siginfo_t __user *) data; - ret = copy_siginfo_to_user(uinfo, &info); - ret |= __put_user(info.si_code, &uinfo->si_code); - } - - if (ret) { - ret = -EFAULT; - break; + if (copy_siginfo_to_user(uinfo, &info) || + __put_user(info.si_code, &uinfo->si_code)) { + ret = -EFAULT; + break; + } } data += sizeof(siginfo_t); diff --git a/kernel/range.c b/kernel/range.c index 071b0ab455cb..322ea8e93e4b 100644 --- a/kernel/range.c +++ b/kernel/range.c @@ -4,7 +4,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/sort.h> - +#include <linux/string.h> #include <linux/range.h> int add_range(struct range *range, int az, int nr_range, u64 start, u64 end) @@ -32,9 +32,8 @@ int add_range_with_merge(struct range *range, int az, int nr_range, if (start >= end) return nr_range; - /* Try to merge it with old one: */ + /* get new start/end: */ for (i = 0; i < nr_range; i++) { - u64 final_start, final_end; u64 common_start, common_end; if (!range[i].end) @@ -45,12 +44,16 @@ int add_range_with_merge(struct range *range, int az, int nr_range, if (common_start > common_end) continue; - final_start = min(range[i].start, start); - final_end = max(range[i].end, end); + /* new start/end, will add it back at last */ + start = min(range[i].start, start); + end = max(range[i].end, end); - range[i].start = final_start; - range[i].end = final_end; - return nr_range; + memmove(&range[i], &range[i + 1], + (nr_range - (i + 1)) * sizeof(range[i])); + range[nr_range - 1].start = 0; + range[nr_range - 1].end = 0; + nr_range--; + i--; } /* Need to add it: */ diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 16ea67925015..35380019f0fc 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -1451,9 +1451,9 @@ static int rcu_gp_init(struct rcu_state *rsp) rnp->grphi, rnp->qsmask); raw_spin_unlock_irq(&rnp->lock); #ifdef CONFIG_PROVE_RCU_DELAY - if ((prandom_u32() % (rcu_num_nodes * 8)) == 0 && + if ((prandom_u32() % (rcu_num_nodes + 1)) == 0 && system_state == SYSTEM_RUNNING) - schedule_timeout_uninterruptible(2); + udelay(200); #endif /* #ifdef CONFIG_PROVE_RCU_DELAY */ cond_resched(); } @@ -1613,6 +1613,14 @@ static int __noreturn rcu_gp_kthread(void *arg) } } +static void rsp_wakeup(struct irq_work *work) +{ + struct rcu_state *rsp = container_of(work, struct rcu_state, wakeup_work); + + /* Wake up rcu_gp_kthread() to start the grace period. */ + wake_up(&rsp->gp_wq); +} + /* * Start a new RCU grace period if warranted, re-initializing the hierarchy * in preparation for detecting the next grace period. The caller must hold @@ -1637,8 +1645,12 @@ rcu_start_gp_advanced(struct rcu_state *rsp, struct rcu_node *rnp, } rsp->gp_flags = RCU_GP_FLAG_INIT; - /* Wake up rcu_gp_kthread() to start the grace period. */ - wake_up(&rsp->gp_wq); + /* + * We can't do wakeups while holding the rnp->lock, as that + * could cause possible deadlocks with the rq->lock. Deter + * the wakeup to interrupt context. + */ + irq_work_queue(&rsp->wakeup_work); } /* @@ -3235,6 +3247,7 @@ static void __init rcu_init_one(struct rcu_state *rsp, rsp->rda = rda; init_waitqueue_head(&rsp->gp_wq); + init_irq_work(&rsp->wakeup_work, rsp_wakeup); rnp = rsp->level[rcu_num_lvls - 1]; for_each_possible_cpu(i) { while (i > rnp->grphi) diff --git a/kernel/rcutree.h b/kernel/rcutree.h index da77a8f57ff9..4df503470e42 100644 --- a/kernel/rcutree.h +++ b/kernel/rcutree.h @@ -27,6 +27,7 @@ #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/seqlock.h> +#include <linux/irq_work.h> /* * Define shape of hierarchy based on NR_CPUS, CONFIG_RCU_FANOUT, and @@ -442,6 +443,7 @@ struct rcu_state { char *name; /* Name of structure. */ char abbr; /* Abbreviated name. */ struct list_head flavors; /* List of RCU flavors. */ + struct irq_work wakeup_work; /* Postponed wakeups */ }; /* Values for rcu_state structure's gp_flags field. */ diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h index 170814dc418f..3db5a375d8dd 100644 --- a/kernel/rcutree_plugin.h +++ b/kernel/rcutree_plugin.h @@ -88,7 +88,7 @@ static void __init rcu_bootup_announce_oddness(void) #ifdef CONFIG_RCU_NOCB_CPU #ifndef CONFIG_RCU_NOCB_CPU_NONE if (!have_rcu_nocb_mask) { - alloc_bootmem_cpumask_var(&rcu_nocb_mask); + zalloc_cpumask_var(&rcu_nocb_mask, GFP_KERNEL); have_rcu_nocb_mask = true; } #ifdef CONFIG_RCU_NOCB_CPU_ZERO @@ -1667,7 +1667,7 @@ int rcu_needs_cpu(int cpu, unsigned long *dj) rdtp->last_accelerate = jiffies; /* Request timer delay depending on laziness, and round. */ - if (rdtp->all_lazy) { + if (!rdtp->all_lazy) { *dj = round_up(rcu_idle_gp_delay + jiffies, rcu_idle_gp_delay) - jiffies; } else { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 58453b8272fd..e8b335016c52 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -633,7 +633,19 @@ void wake_up_nohz_cpu(int cpu) static inline bool got_nohz_idle_kick(void) { int cpu = smp_processor_id(); - return idle_cpu(cpu) && test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)); + + if (!test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu))) + return false; + + if (idle_cpu(cpu) && !need_resched()) + return true; + + /* + * We can't run Idle Load Balance on this CPU for this time so we + * cancel it and clear NOHZ_BALANCE_KICK + */ + clear_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)); + return false; } #else /* CONFIG_NO_HZ_COMMON */ @@ -1393,8 +1405,9 @@ static void sched_ttwu_pending(void) void scheduler_ipi(void) { - if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick() - && !tick_nohz_full_cpu(smp_processor_id())) + if (llist_empty(&this_rq()->wake_list) + && !tick_nohz_full_cpu(smp_processor_id()) + && !got_nohz_idle_kick()) return; /* @@ -1417,7 +1430,7 @@ void scheduler_ipi(void) /* * Check if someone kicked us for doing the nohz idle load balance. */ - if (unlikely(got_nohz_idle_kick() && !need_resched())) { + if (unlikely(got_nohz_idle_kick())) { this_rq()->idle_balance = 1; raise_softirq_irqoff(SCHED_SOFTIRQ); } @@ -4745,7 +4758,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) */ idle->sched_class = &idle_sched_class; ftrace_graph_init_idle_task(idle, cpu); - vtime_init_idle(idle); + vtime_init_idle(idle, cpu); #if defined(CONFIG_SMP) sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); #endif diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index cc2dc3eea8a3..b5ccba22603b 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -747,17 +747,17 @@ void arch_vtime_task_switch(struct task_struct *prev) write_seqlock(¤t->vtime_seqlock); current->vtime_snap_whence = VTIME_SYS; - current->vtime_snap = sched_clock(); + current->vtime_snap = sched_clock_cpu(smp_processor_id()); write_sequnlock(¤t->vtime_seqlock); } -void vtime_init_idle(struct task_struct *t) +void vtime_init_idle(struct task_struct *t, int cpu) { unsigned long flags; write_seqlock_irqsave(&t->vtime_seqlock, flags); t->vtime_snap_whence = VTIME_SYS; - t->vtime_snap = sched_clock(); + t->vtime_snap = sched_clock_cpu(cpu); write_sequnlock_irqrestore(&t->vtime_seqlock, flags); } diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 2ef90a51ec5e..71bac979d5ee 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -162,6 +162,39 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next) */ /** + * cputimer_running - return true if cputimer is running + * + * @tsk: Pointer to target task. + */ +static inline bool cputimer_running(struct task_struct *tsk) + +{ + struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; + + if (!cputimer->running) + return false; + + /* + * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime + * in __exit_signal(), we won't account to the signal struct further + * cputime consumed by that task, even though the task can still be + * ticking after __exit_signal(). + * + * In order to keep a consistent behaviour between thread group cputime + * and thread group cputimer accounting, lets also ignore the cputime + * elapsing after __exit_signal() in any thread group timer running. + * + * This makes sure that POSIX CPU clocks and timers are synchronized, so + * that a POSIX CPU timer won't expire while the corresponding POSIX CPU + * clock delta is behind the expiring timer value. + */ + if (unlikely(!tsk->sighand)) + return false; + + return true; +} + +/** * account_group_user_time - Maintain utime for a thread group. * * @tsk: Pointer to task structure. @@ -176,7 +209,7 @@ static inline void account_group_user_time(struct task_struct *tsk, { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; - if (!cputimer->running) + if (!cputimer_running(tsk)) return; raw_spin_lock(&cputimer->lock); @@ -199,7 +232,7 @@ static inline void account_group_system_time(struct task_struct *tsk, { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; - if (!cputimer->running) + if (!cputimer_running(tsk)) return; raw_spin_lock(&cputimer->lock); @@ -222,7 +255,7 @@ static inline void account_group_exec_runtime(struct task_struct *tsk, { struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; - if (!cputimer->running) + if (!cputimer_running(tsk)) return; raw_spin_lock(&cputimer->lock); diff --git a/kernel/softirq.c b/kernel/softirq.c index b5197dcb0dad..3d6833f125d3 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -195,8 +195,12 @@ void local_bh_enable_ip(unsigned long ip) EXPORT_SYMBOL(local_bh_enable_ip); /* - * We restart softirq processing for at most 2 ms, - * and if need_resched() is not set. + * We restart softirq processing for at most MAX_SOFTIRQ_RESTART times, + * but break the loop if need_resched() is set or after 2 ms. + * The MAX_SOFTIRQ_TIME provides a nice upper bound in most cases, but in + * certain cases, such as stop_machine(), jiffies may cease to + * increment and so we need the MAX_SOFTIRQ_RESTART limit as + * well to make sure we eventually return from this method. * * These limits have been established via experimentation. * The two things to balance is latency against fairness - @@ -204,6 +208,7 @@ EXPORT_SYMBOL(local_bh_enable_ip); * should not be able to lock up the box. */ #define MAX_SOFTIRQ_TIME msecs_to_jiffies(2) +#define MAX_SOFTIRQ_RESTART 10 asmlinkage void __do_softirq(void) { @@ -212,6 +217,7 @@ asmlinkage void __do_softirq(void) unsigned long end = jiffies + MAX_SOFTIRQ_TIME; int cpu; unsigned long old_flags = current->flags; + int max_restart = MAX_SOFTIRQ_RESTART; /* * Mask out PF_MEMALLOC s current task context is borrowed for the @@ -265,7 +271,8 @@ restart: pending = local_softirq_pending(); if (pending) { - if (time_before(jiffies, end) && !need_resched()) + if (time_before(jiffies, end) && !need_resched() && + --max_restart) goto restart; wakeup_softirqd(); diff --git a/kernel/sys.c b/kernel/sys.c index b95d3c72ba21..2bbd9a73b54c 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -362,6 +362,29 @@ int unregister_reboot_notifier(struct notifier_block *nb) } EXPORT_SYMBOL(unregister_reboot_notifier); +/* Add backwards compatibility for stable trees. */ +#ifndef PF_NO_SETAFFINITY +#define PF_NO_SETAFFINITY PF_THREAD_BOUND +#endif + +static void migrate_to_reboot_cpu(void) +{ + /* The boot cpu is always logical cpu 0 */ + int cpu = 0; + + cpu_hotplug_disable(); + + /* Make certain the cpu I'm about to reboot on is online */ + if (!cpu_online(cpu)) + cpu = cpumask_first(cpu_online_mask); + + /* Prevent races with other tasks migrating this task */ + current->flags |= PF_NO_SETAFFINITY; + + /* Make certain I only run on the appropriate processor */ + set_cpus_allowed_ptr(current, cpumask_of(cpu)); +} + /** * kernel_restart - reboot the system * @cmd: pointer to buffer containing command to execute for restart @@ -373,7 +396,7 @@ EXPORT_SYMBOL(unregister_reboot_notifier); void kernel_restart(char *cmd) { kernel_restart_prepare(cmd); - disable_nonboot_cpus(); + migrate_to_reboot_cpu(); syscore_shutdown(); if (!cmd) printk(KERN_EMERG "Restarting system.\n"); @@ -400,7 +423,7 @@ static void kernel_shutdown_prepare(enum system_states state) void kernel_halt(void) { kernel_shutdown_prepare(SYSTEM_HALT); - disable_nonboot_cpus(); + migrate_to_reboot_cpu(); syscore_shutdown(); printk(KERN_EMERG "System halted.\n"); kmsg_dump(KMSG_DUMP_HALT); @@ -419,7 +442,7 @@ void kernel_power_off(void) kernel_shutdown_prepare(SYSTEM_POWER_OFF); if (pm_power_off_prepare) pm_power_off_prepare(); - disable_nonboot_cpus(); + migrate_to_reboot_cpu(); syscore_shutdown(); printk(KERN_EMERG "Power down.\n"); kmsg_dump(KMSG_DUMP_POWEROFF); diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index e4c07b0692bb..70f27e89012b 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -12,11 +12,6 @@ config CLOCKSOURCE_WATCHDOG config ARCH_CLOCKSOURCE_DATA bool -# Platforms has a persistent clock -config ALWAYS_USE_PERSISTENT_CLOCK - bool - default n - # Timekeeping vsyscall support config GENERIC_TIME_VSYSCALL bool diff --git a/kernel/time/Makefile b/kernel/time/Makefile index ff7d9d2ab504..9250130646f5 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -4,6 +4,8 @@ obj-y += timeconv.o posix-clock.o alarmtimer.o obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) += tick-broadcast.o +obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o obj-$(CONFIG_TIMER_STATS) += timer_stats.o +obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index f11d83b12949..eec50fcef9e4 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -199,6 +199,13 @@ static enum hrtimer_restart alarmtimer_fired(struct hrtimer *timer) } +ktime_t alarm_expires_remaining(const struct alarm *alarm) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + return ktime_sub(alarm->node.expires, base->gettime()); +} +EXPORT_SYMBOL_GPL(alarm_expires_remaining); + #ifdef CONFIG_RTC_CLASS /** * alarmtimer_suspend - Suspend time callback @@ -303,9 +310,10 @@ void alarm_init(struct alarm *alarm, enum alarmtimer_type type, alarm->type = type; alarm->state = ALARMTIMER_STATE_INACTIVE; } +EXPORT_SYMBOL_GPL(alarm_init); /** - * alarm_start - Sets an alarm to fire + * alarm_start - Sets an absolute alarm to fire * @alarm: ptr to alarm to set * @start: time to run the alarm */ @@ -323,6 +331,34 @@ int alarm_start(struct alarm *alarm, ktime_t start) spin_unlock_irqrestore(&base->lock, flags); return ret; } +EXPORT_SYMBOL_GPL(alarm_start); + +/** + * alarm_start_relative - Sets a relative alarm to fire + * @alarm: ptr to alarm to set + * @start: time relative to now to run the alarm + */ +int alarm_start_relative(struct alarm *alarm, ktime_t start) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + + start = ktime_add(start, base->gettime()); + return alarm_start(alarm, start); +} +EXPORT_SYMBOL_GPL(alarm_start_relative); + +void alarm_restart(struct alarm *alarm) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + unsigned long flags; + + spin_lock_irqsave(&base->lock, flags); + hrtimer_set_expires(&alarm->timer, alarm->node.expires); + hrtimer_restart(&alarm->timer); + alarmtimer_enqueue(base, alarm); + spin_unlock_irqrestore(&base->lock, flags); +} +EXPORT_SYMBOL_GPL(alarm_restart); /** * alarm_try_to_cancel - Tries to cancel an alarm timer @@ -344,6 +380,7 @@ int alarm_try_to_cancel(struct alarm *alarm) spin_unlock_irqrestore(&base->lock, flags); return ret; } +EXPORT_SYMBOL_GPL(alarm_try_to_cancel); /** @@ -361,6 +398,7 @@ int alarm_cancel(struct alarm *alarm) cpu_relax(); } } +EXPORT_SYMBOL_GPL(alarm_cancel); u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) @@ -393,8 +431,15 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) alarm->node.expires = ktime_add(alarm->node.expires, interval); return overrun; } +EXPORT_SYMBOL_GPL(alarm_forward); +u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) +{ + struct alarm_base *base = &alarm_bases[alarm->type]; + return alarm_forward(alarm, base->gettime(), interval); +} +EXPORT_SYMBOL_GPL(alarm_forward_now); /** diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index c6d6400ee137..38959c866789 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -15,20 +15,23 @@ #include <linux/hrtimer.h> #include <linux/init.h> #include <linux/module.h> -#include <linux/notifier.h> #include <linux/smp.h> +#include <linux/device.h> #include "tick-internal.h" /* The registered clock event devices */ static LIST_HEAD(clockevent_devices); static LIST_HEAD(clockevents_released); - -/* Notification for clock events */ -static RAW_NOTIFIER_HEAD(clockevents_chain); - /* Protection for the above */ static DEFINE_RAW_SPINLOCK(clockevents_lock); +/* Protection for unbind operations */ +static DEFINE_MUTEX(clockevents_mutex); + +struct ce_unbind { + struct clock_event_device *ce; + int res; +}; /** * clockevents_delta2ns - Convert a latch value (device ticks) to nanoseconds @@ -232,47 +235,107 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, return (rc && force) ? clockevents_program_min_delta(dev) : rc; } -/** - * clockevents_register_notifier - register a clock events change listener +/* + * Called after a notify add to make devices available which were + * released from the notifier call. */ -int clockevents_register_notifier(struct notifier_block *nb) +static void clockevents_notify_released(void) { - unsigned long flags; - int ret; + struct clock_event_device *dev; - raw_spin_lock_irqsave(&clockevents_lock, flags); - ret = raw_notifier_chain_register(&clockevents_chain, nb); - raw_spin_unlock_irqrestore(&clockevents_lock, flags); + while (!list_empty(&clockevents_released)) { + dev = list_entry(clockevents_released.next, + struct clock_event_device, list); + list_del(&dev->list); + list_add(&dev->list, &clockevent_devices); + tick_check_new_device(dev); + } +} - return ret; +/* + * Try to install a replacement clock event device + */ +static int clockevents_replace(struct clock_event_device *ced) +{ + struct clock_event_device *dev, *newdev = NULL; + + list_for_each_entry(dev, &clockevent_devices, list) { + if (dev == ced || dev->mode != CLOCK_EVT_MODE_UNUSED) + continue; + + if (!tick_check_replacement(newdev, dev)) + continue; + + if (!try_module_get(dev->owner)) + continue; + + if (newdev) + module_put(newdev->owner); + newdev = dev; + } + if (newdev) { + tick_install_replacement(newdev); + list_del_init(&ced->list); + } + return newdev ? 0 : -EBUSY; } /* - * Notify about a clock event change. Called with clockevents_lock - * held. + * Called with clockevents_mutex and clockevents_lock held */ -static void clockevents_do_notify(unsigned long reason, void *dev) +static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu) { - raw_notifier_call_chain(&clockevents_chain, reason, dev); + /* Fast track. Device is unused */ + if (ced->mode == CLOCK_EVT_MODE_UNUSED) { + list_del_init(&ced->list); + return 0; + } + + return ced == per_cpu(tick_cpu_device, cpu).evtdev ? -EAGAIN : -EBUSY; } /* - * Called after a notify add to make devices available which were - * released from the notifier call. + * SMP function call to unbind a device */ -static void clockevents_notify_released(void) +static void __clockevents_unbind(void *arg) { - struct clock_event_device *dev; + struct ce_unbind *cu = arg; + int res; + + raw_spin_lock(&clockevents_lock); + res = __clockevents_try_unbind(cu->ce, smp_processor_id()); + if (res == -EAGAIN) + res = clockevents_replace(cu->ce); + cu->res = res; + raw_spin_unlock(&clockevents_lock); +} - while (!list_empty(&clockevents_released)) { - dev = list_entry(clockevents_released.next, - struct clock_event_device, list); - list_del(&dev->list); - list_add(&dev->list, &clockevent_devices); - clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev); - } +/* + * Issues smp function call to unbind a per cpu device. Called with + * clockevents_mutex held. + */ +static int clockevents_unbind(struct clock_event_device *ced, int cpu) +{ + struct ce_unbind cu = { .ce = ced, .res = -ENODEV }; + + smp_call_function_single(cpu, __clockevents_unbind, &cu, 1); + return cu.res; } +/* + * Unbind a clockevents device. + */ +int clockevents_unbind_device(struct clock_event_device *ced, int cpu) +{ + int ret; + + mutex_lock(&clockevents_mutex); + ret = clockevents_unbind(ced, cpu); + mutex_unlock(&clockevents_mutex); + return ret; +} +EXPORT_SYMBOL_GPL(clockevents_unbind); + /** * clockevents_register_device - register a clock event device * @dev: device to register @@ -290,7 +353,7 @@ void clockevents_register_device(struct clock_event_device *dev) raw_spin_lock_irqsave(&clockevents_lock, flags); list_add(&dev->list, &clockevent_devices); - clockevents_do_notify(CLOCK_EVT_NOTIFY_ADD, dev); + tick_check_new_device(dev); clockevents_notify_released(); raw_spin_unlock_irqrestore(&clockevents_lock, flags); @@ -386,6 +449,7 @@ void clockevents_exchange_device(struct clock_event_device *old, * released list and do a notify add later. */ if (old) { + module_put(old->owner); clockevents_set_mode(old, CLOCK_EVT_MODE_UNUSED); list_del(&old->list); list_add(&old->list, &clockevents_released); @@ -433,10 +497,36 @@ void clockevents_notify(unsigned long reason, void *arg) int cpu; raw_spin_lock_irqsave(&clockevents_lock, flags); - clockevents_do_notify(reason, arg); switch (reason) { + case CLOCK_EVT_NOTIFY_BROADCAST_ON: + case CLOCK_EVT_NOTIFY_BROADCAST_OFF: + case CLOCK_EVT_NOTIFY_BROADCAST_FORCE: + tick_broadcast_on_off(reason, arg); + break; + + case CLOCK_EVT_NOTIFY_BROADCAST_ENTER: + case CLOCK_EVT_NOTIFY_BROADCAST_EXIT: + tick_broadcast_oneshot_control(reason); + break; + + case CLOCK_EVT_NOTIFY_CPU_DYING: + tick_handover_do_timer(arg); + break; + + case CLOCK_EVT_NOTIFY_SUSPEND: + tick_suspend(); + tick_suspend_broadcast(); + break; + + case CLOCK_EVT_NOTIFY_RESUME: + tick_resume(); + break; + case CLOCK_EVT_NOTIFY_CPU_DEAD: + tick_shutdown_broadcast_oneshot(arg); + tick_shutdown_broadcast(arg); + tick_shutdown(arg); /* * Unregister the clock event devices which were * released from the users in the notify chain. @@ -462,4 +552,123 @@ void clockevents_notify(unsigned long reason, void *arg) raw_spin_unlock_irqrestore(&clockevents_lock, flags); } EXPORT_SYMBOL_GPL(clockevents_notify); + +#ifdef CONFIG_SYSFS +struct bus_type clockevents_subsys = { + .name = "clockevents", + .dev_name = "clockevent", +}; + +static DEFINE_PER_CPU(struct device, tick_percpu_dev); +static struct tick_device *tick_get_tick_dev(struct device *dev); + +static ssize_t sysfs_show_current_tick_dev(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct tick_device *td; + ssize_t count = 0; + + raw_spin_lock_irq(&clockevents_lock); + td = tick_get_tick_dev(dev); + if (td && td->evtdev) + count = snprintf(buf, PAGE_SIZE, "%s\n", td->evtdev->name); + raw_spin_unlock_irq(&clockevents_lock); + return count; +} +static DEVICE_ATTR(current_device, 0444, sysfs_show_current_tick_dev, NULL); + +/* We don't support the abomination of removable broadcast devices */ +static ssize_t sysfs_unbind_tick_dev(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + char name[CS_NAME_LEN]; + size_t ret = sysfs_get_uname(buf, name, count); + struct clock_event_device *ce; + + if (ret < 0) + return ret; + + ret = -ENODEV; + mutex_lock(&clockevents_mutex); + raw_spin_lock_irq(&clockevents_lock); + list_for_each_entry(ce, &clockevent_devices, list) { + if (!strcmp(ce->name, name)) { + ret = __clockevents_try_unbind(ce, dev->id); + break; + } + } + raw_spin_unlock_irq(&clockevents_lock); + /* + * We hold clockevents_mutex, so ce can't go away + */ + if (ret == -EAGAIN) + ret = clockevents_unbind(ce, dev->id); + mutex_unlock(&clockevents_mutex); + return ret ? ret : count; +} +static DEVICE_ATTR(unbind_device, 0200, NULL, sysfs_unbind_tick_dev); + +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +static struct device tick_bc_dev = { + .init_name = "broadcast", + .id = 0, + .bus = &clockevents_subsys, +}; + +static struct tick_device *tick_get_tick_dev(struct device *dev) +{ + return dev == &tick_bc_dev ? tick_get_broadcast_device() : + &per_cpu(tick_cpu_device, dev->id); +} + +static __init int tick_broadcast_init_sysfs(void) +{ + int err = device_register(&tick_bc_dev); + + if (!err) + err = device_create_file(&tick_bc_dev, &dev_attr_current_device); + return err; +} +#else +static struct tick_device *tick_get_tick_dev(struct device *dev) +{ + return &per_cpu(tick_cpu_device, dev->id); +} +static inline int tick_broadcast_init_sysfs(void) { return 0; } #endif + +static int __init tick_init_sysfs(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct device *dev = &per_cpu(tick_percpu_dev, cpu); + int err; + + dev->id = cpu; + dev->bus = &clockevents_subsys; + err = device_register(dev); + if (!err) + err = device_create_file(dev, &dev_attr_current_device); + if (!err) + err = device_create_file(dev, &dev_attr_unbind_device); + if (err) + return err; + } + return tick_broadcast_init_sysfs(); +} + +static int __init clockevents_init_sysfs(void) +{ + int err = subsys_system_register(&clockevents_subsys, NULL); + + if (!err) + err = tick_init_sysfs(); + return err; +} +device_initcall(clockevents_init_sysfs); +#endif /* SYSFS */ + +#endif /* GENERIC_CLOCK_EVENTS */ diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index c9583382141a..50a8736757f3 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -31,6 +31,8 @@ #include <linux/tick.h> #include <linux/kthread.h> +#include "tick-internal.h" + void timecounter_init(struct timecounter *tc, const struct cyclecounter *cc, u64 start_tstamp) @@ -174,11 +176,12 @@ clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 maxsec) static struct clocksource *curr_clocksource; static LIST_HEAD(clocksource_list); static DEFINE_MUTEX(clocksource_mutex); -static char override_name[32]; +static char override_name[CS_NAME_LEN]; static int finished_booting; #ifdef CONFIG_CLOCKSOURCE_WATCHDOG static void clocksource_watchdog_work(struct work_struct *work); +static void clocksource_select(void); static LIST_HEAD(watchdog_list); static struct clocksource *watchdog; @@ -299,13 +302,30 @@ static void clocksource_watchdog(unsigned long data) if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) && (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) { + /* Mark it valid for high-res. */ cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; + + /* + * clocksource_done_booting() will sort it if + * finished_booting is not set yet. + */ + if (!finished_booting) + continue; + /* - * We just marked the clocksource as highres-capable, - * notify the rest of the system as well so that we - * transition into high-res mode: + * If this is not the current clocksource let + * the watchdog thread reselect it. Due to the + * change to high res this clocksource might + * be preferred now. If it is the current + * clocksource let the tick code know about + * that change. */ - tick_clock_notify(); + if (cs != curr_clocksource) { + cs->flags |= CLOCK_SOURCE_RESELECT; + schedule_work(&watchdog_work); + } else { + tick_clock_notify(); + } } } @@ -388,44 +408,39 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) static void clocksource_dequeue_watchdog(struct clocksource *cs) { - struct clocksource *tmp; unsigned long flags; spin_lock_irqsave(&watchdog_lock, flags); - if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { - /* cs is a watched clocksource. */ - list_del_init(&cs->wd_list); - } else if (cs == watchdog) { - /* Reset watchdog cycles */ - clocksource_reset_watchdog(); - /* Current watchdog is removed. Find an alternative. */ - watchdog = NULL; - list_for_each_entry(tmp, &clocksource_list, list) { - if (tmp == cs || tmp->flags & CLOCK_SOURCE_MUST_VERIFY) - continue; - if (!watchdog || tmp->rating > watchdog->rating) - watchdog = tmp; + if (cs != watchdog) { + if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { + /* cs is a watched clocksource. */ + list_del_init(&cs->wd_list); + /* Check if the watchdog timer needs to be stopped. */ + clocksource_stop_watchdog(); } } - cs->flags &= ~CLOCK_SOURCE_WATCHDOG; - /* Check if the watchdog timer needs to be stopped. */ - clocksource_stop_watchdog(); spin_unlock_irqrestore(&watchdog_lock, flags); } -static int clocksource_watchdog_kthread(void *data) +static int __clocksource_watchdog_kthread(void) { struct clocksource *cs, *tmp; unsigned long flags; LIST_HEAD(unstable); + int select = 0; - mutex_lock(&clocksource_mutex); spin_lock_irqsave(&watchdog_lock, flags); - list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) + list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) { if (cs->flags & CLOCK_SOURCE_UNSTABLE) { list_del_init(&cs->wd_list); list_add(&cs->wd_list, &unstable); + select = 1; } + if (cs->flags & CLOCK_SOURCE_RESELECT) { + cs->flags &= ~CLOCK_SOURCE_RESELECT; + select = 1; + } + } /* Check if the watchdog timer needs to be stopped. */ clocksource_stop_watchdog(); spin_unlock_irqrestore(&watchdog_lock, flags); @@ -435,10 +450,23 @@ static int clocksource_watchdog_kthread(void *data) list_del_init(&cs->wd_list); __clocksource_change_rating(cs, 0); } + return select; +} + +static int clocksource_watchdog_kthread(void *data) +{ + mutex_lock(&clocksource_mutex); + if (__clocksource_watchdog_kthread()) + clocksource_select(); mutex_unlock(&clocksource_mutex); return 0; } +static bool clocksource_is_watchdog(struct clocksource *cs) +{ + return cs == watchdog; +} + #else /* CONFIG_CLOCKSOURCE_WATCHDOG */ static void clocksource_enqueue_watchdog(struct clocksource *cs) @@ -449,7 +477,8 @@ static void clocksource_enqueue_watchdog(struct clocksource *cs) static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { } static inline void clocksource_resume_watchdog(void) { } -static inline int clocksource_watchdog_kthread(void *data) { return 0; } +static inline int __clocksource_watchdog_kthread(void) { return 0; } +static bool clocksource_is_watchdog(struct clocksource *cs) { return false; } #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */ @@ -553,24 +582,42 @@ static u64 clocksource_max_deferment(struct clocksource *cs) #ifndef CONFIG_ARCH_USES_GETTIMEOFFSET -/** - * clocksource_select - Select the best clocksource available - * - * Private function. Must hold clocksource_mutex when called. - * - * Select the clocksource with the best rating, or the clocksource, - * which is selected by userspace override. - */ -static void clocksource_select(void) +static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur) { - struct clocksource *best, *cs; + struct clocksource *cs; if (!finished_booting || list_empty(&clocksource_list)) + return NULL; + + /* + * We pick the clocksource with the highest rating. If oneshot + * mode is active, we pick the highres valid clocksource with + * the best rating. + */ + list_for_each_entry(cs, &clocksource_list, list) { + if (skipcur && cs == curr_clocksource) + continue; + if (oneshot && !(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES)) + continue; + return cs; + } + return NULL; +} + +static void __clocksource_select(bool skipcur) +{ + bool oneshot = tick_oneshot_mode_active(); + struct clocksource *best, *cs; + + /* Find the best suitable clocksource */ + best = clocksource_find_best(oneshot, skipcur); + if (!best) return; - /* First clocksource on the list has the best rating. */ - best = list_first_entry(&clocksource_list, struct clocksource, list); + /* Check for the override clocksource. */ list_for_each_entry(cs, &clocksource_list, list) { + if (skipcur && cs == curr_clocksource) + continue; if (strcmp(cs->name, override_name) != 0) continue; /* @@ -578,8 +625,7 @@ static void clocksource_select(void) * capable clocksource if the tick code is in oneshot * mode (highres or nohz) */ - if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && - tick_oneshot_mode_active()) { + if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && oneshot) { /* Override clocksource cannot be used. */ printk(KERN_WARNING "Override clocksource %s is not " "HRT compatible. Cannot switch while in " @@ -590,16 +636,35 @@ static void clocksource_select(void) best = cs; break; } - if (curr_clocksource != best) { - printk(KERN_INFO "Switching to clocksource %s\n", best->name); + + if (curr_clocksource != best && !timekeeping_notify(best)) { + pr_info("Switched to clocksource %s\n", best->name); curr_clocksource = best; - timekeeping_notify(curr_clocksource); } } +/** + * clocksource_select - Select the best clocksource available + * + * Private function. Must hold clocksource_mutex when called. + * + * Select the clocksource with the best rating, or the clocksource, + * which is selected by userspace override. + */ +static void clocksource_select(void) +{ + return __clocksource_select(false); +} + +static void clocksource_select_fallback(void) +{ + return __clocksource_select(true); +} + #else /* !CONFIG_ARCH_USES_GETTIMEOFFSET */ static inline void clocksource_select(void) { } +static inline void clocksource_select_fallback(void) { } #endif @@ -614,16 +679,11 @@ static int __init clocksource_done_booting(void) { mutex_lock(&clocksource_mutex); curr_clocksource = clocksource_default_clock(); - mutex_unlock(&clocksource_mutex); - finished_booting = 1; - /* * Run the watchdog first to eliminate unstable clock sources */ - clocksource_watchdog_kthread(NULL); - - mutex_lock(&clocksource_mutex); + __clocksource_watchdog_kthread(); clocksource_select(); mutex_unlock(&clocksource_mutex); return 0; @@ -756,7 +816,6 @@ static void __clocksource_change_rating(struct clocksource *cs, int rating) list_del(&cs->list); cs->rating = rating; clocksource_enqueue(cs); - clocksource_select(); } /** @@ -768,21 +827,47 @@ void clocksource_change_rating(struct clocksource *cs, int rating) { mutex_lock(&clocksource_mutex); __clocksource_change_rating(cs, rating); + clocksource_select(); mutex_unlock(&clocksource_mutex); } EXPORT_SYMBOL(clocksource_change_rating); +/* + * Unbind clocksource @cs. Called with clocksource_mutex held + */ +static int clocksource_unbind(struct clocksource *cs) +{ + /* + * I really can't convince myself to support this on hardware + * designed by lobotomized monkeys. + */ + if (clocksource_is_watchdog(cs)) + return -EBUSY; + + if (cs == curr_clocksource) { + /* Select and try to install a replacement clock source */ + clocksource_select_fallback(); + if (curr_clocksource == cs) + return -EBUSY; + } + clocksource_dequeue_watchdog(cs); + list_del_init(&cs->list); + return 0; +} + /** * clocksource_unregister - remove a registered clocksource * @cs: clocksource to be unregistered */ -void clocksource_unregister(struct clocksource *cs) +int clocksource_unregister(struct clocksource *cs) { + int ret = 0; + mutex_lock(&clocksource_mutex); - clocksource_dequeue_watchdog(cs); - list_del(&cs->list); - clocksource_select(); + if (!list_empty(&cs->list)) + ret = clocksource_unbind(cs); mutex_unlock(&clocksource_mutex); + return ret; } EXPORT_SYMBOL(clocksource_unregister); @@ -808,6 +893,23 @@ sysfs_show_current_clocksources(struct device *dev, return count; } +size_t sysfs_get_uname(const char *buf, char *dst, size_t cnt) +{ + size_t ret = cnt; + + /* strings from sysfs write are not 0 terminated! */ + if (!cnt || cnt >= CS_NAME_LEN) + return -EINVAL; + + /* strip of \n: */ + if (buf[cnt-1] == '\n') + cnt--; + if (cnt > 0) + memcpy(dst, buf, cnt); + dst[cnt] = 0; + return ret; +} + /** * sysfs_override_clocksource - interface for manually overriding clocksource * @dev: unused @@ -822,22 +924,13 @@ static ssize_t sysfs_override_clocksource(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - size_t ret = count; - - /* strings from sysfs write are not 0 terminated! */ - if (count >= sizeof(override_name)) - return -EINVAL; - - /* strip of \n: */ - if (buf[count-1] == '\n') - count--; + size_t ret; mutex_lock(&clocksource_mutex); - if (count > 0) - memcpy(override_name, buf, count); - override_name[count] = 0; - clocksource_select(); + ret = sysfs_get_uname(buf, override_name, count); + if (ret >= 0) + clocksource_select(); mutex_unlock(&clocksource_mutex); @@ -845,6 +938,40 @@ static ssize_t sysfs_override_clocksource(struct device *dev, } /** + * sysfs_unbind_current_clocksource - interface for manually unbinding clocksource + * @dev: unused + * @attr: unused + * @buf: unused + * @count: length of buffer + * + * Takes input from sysfs interface for manually unbinding a clocksource. + */ +static ssize_t sysfs_unbind_clocksource(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct clocksource *cs; + char name[CS_NAME_LEN]; + size_t ret; + + ret = sysfs_get_uname(buf, name, count); + if (ret < 0) + return ret; + + ret = -ENODEV; + mutex_lock(&clocksource_mutex); + list_for_each_entry(cs, &clocksource_list, list) { + if (strcmp(cs->name, name)) + continue; + ret = clocksource_unbind(cs); + break; + } + mutex_unlock(&clocksource_mutex); + + return ret ? ret : count; +} + +/** * sysfs_show_available_clocksources - sysfs interface for listing clocksource * @dev: unused * @attr: unused @@ -886,6 +1013,8 @@ sysfs_show_available_clocksources(struct device *dev, static DEVICE_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources, sysfs_override_clocksource); +static DEVICE_ATTR(unbind_clocksource, 0200, NULL, sysfs_unbind_clocksource); + static DEVICE_ATTR(available_clocksource, 0444, sysfs_show_available_clocksources, NULL); @@ -910,6 +1039,9 @@ static int __init init_clocksource_sysfs(void) &device_clocksource, &dev_attr_current_clocksource); if (!error) + error = device_create_file(&device_clocksource, + &dev_attr_unbind_clocksource); + if (!error) error = device_create_file( &device_clocksource, &dev_attr_available_clocksource); diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 12ff13a838c6..8f5b3b98577b 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -874,7 +874,6 @@ static void hardpps_update_phase(long error) void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts) { struct pps_normtime pts_norm, freq_norm; - unsigned long flags; pts_norm = pps_normalize_ts(*phase_ts); diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c new file mode 100644 index 000000000000..a326f27d7f09 --- /dev/null +++ b/kernel/time/sched_clock.c @@ -0,0 +1,212 @@ +/* + * sched_clock.c: support for extending counters to full 64-bit ns counter + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ +#include <linux/clocksource.h> +#include <linux/init.h> +#include <linux/jiffies.h> +#include <linux/kernel.h> +#include <linux/moduleparam.h> +#include <linux/sched.h> +#include <linux/syscore_ops.h> +#include <linux/timer.h> +#include <linux/sched_clock.h> + +struct clock_data { + u64 epoch_ns; + u32 epoch_cyc; + u32 epoch_cyc_copy; + unsigned long rate; + u32 mult; + u32 shift; + bool suspended; +}; + +static void sched_clock_poll(unsigned long wrap_ticks); +static DEFINE_TIMER(sched_clock_timer, sched_clock_poll, 0, 0); +static int irqtime = -1; + +core_param(irqtime, irqtime, int, 0400); + +static struct clock_data cd = { + .mult = NSEC_PER_SEC / HZ, +}; + +static u32 __read_mostly sched_clock_mask = 0xffffffff; + +static u32 notrace jiffy_sched_clock_read(void) +{ + return (u32)(jiffies - INITIAL_JIFFIES); +} + +static u32 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read; + +static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) +{ + return (cyc * mult) >> shift; +} + +static unsigned long long notrace sched_clock_32(void) +{ + u64 epoch_ns; + u32 epoch_cyc; + u32 cyc; + + if (cd.suspended) + return cd.epoch_ns; + + /* + * Load the epoch_cyc and epoch_ns atomically. We do this by + * ensuring that we always write epoch_cyc, epoch_ns and + * epoch_cyc_copy in strict order, and read them in strict order. + * If epoch_cyc and epoch_cyc_copy are not equal, then we're in + * the middle of an update, and we should repeat the load. + */ + do { + epoch_cyc = cd.epoch_cyc; + smp_rmb(); + epoch_ns = cd.epoch_ns; + smp_rmb(); + } while (epoch_cyc != cd.epoch_cyc_copy); + + cyc = read_sched_clock(); + cyc = (cyc - epoch_cyc) & sched_clock_mask; + return epoch_ns + cyc_to_ns(cyc, cd.mult, cd.shift); +} + +/* + * Atomically update the sched_clock epoch. + */ +static void notrace update_sched_clock(void) +{ + unsigned long flags; + u32 cyc; + u64 ns; + + cyc = read_sched_clock(); + ns = cd.epoch_ns + + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask, + cd.mult, cd.shift); + /* + * Write epoch_cyc and epoch_ns in a way that the update is + * detectable in cyc_to_fixed_sched_clock(). + */ + raw_local_irq_save(flags); + cd.epoch_cyc_copy = cyc; + smp_wmb(); + cd.epoch_ns = ns; + smp_wmb(); + cd.epoch_cyc = cyc; + raw_local_irq_restore(flags); +} + +static void sched_clock_poll(unsigned long wrap_ticks) +{ + mod_timer(&sched_clock_timer, round_jiffies(jiffies + wrap_ticks)); + update_sched_clock(); +} + +void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate) +{ + unsigned long r, w; + u64 res, wrap; + char r_unit; + + if (cd.rate > rate) + return; + + BUG_ON(bits > 32); + WARN_ON(!irqs_disabled()); + read_sched_clock = read; + sched_clock_mask = (1 << bits) - 1; + cd.rate = rate; + + /* calculate the mult/shift to convert counter ticks to ns. */ + clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 0); + + r = rate; + if (r >= 4000000) { + r /= 1000000; + r_unit = 'M'; + } else if (r >= 1000) { + r /= 1000; + r_unit = 'k'; + } else + r_unit = ' '; + + /* calculate how many ns until we wrap */ + wrap = cyc_to_ns((1ULL << bits) - 1, cd.mult, cd.shift); + do_div(wrap, NSEC_PER_MSEC); + w = wrap; + + /* calculate the ns resolution of this counter */ + res = cyc_to_ns(1ULL, cd.mult, cd.shift); + pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lums\n", + bits, r, r_unit, res, w); + + /* + * Start the timer to keep sched_clock() properly updated and + * sets the initial epoch. + */ + sched_clock_timer.data = msecs_to_jiffies(w - (w / 10)); + update_sched_clock(); + + /* + * Ensure that sched_clock() starts off at 0ns + */ + cd.epoch_ns = 0; + + /* Enable IRQ time accounting if we have a fast enough sched_clock */ + if (irqtime > 0 || (irqtime == -1 && rate >= 1000000)) + enable_sched_clock_irqtime(); + + pr_debug("Registered %pF as sched_clock source\n", read); +} + +unsigned long long __read_mostly (*sched_clock_func)(void) = sched_clock_32; + +unsigned long long notrace sched_clock(void) +{ + return sched_clock_func(); +} + +void __init sched_clock_postinit(void) +{ + /* + * If no sched_clock function has been provided at that point, + * make it the final one one. + */ + if (read_sched_clock == jiffy_sched_clock_read) + setup_sched_clock(jiffy_sched_clock_read, 32, HZ); + + sched_clock_poll(sched_clock_timer.data); +} + +static int sched_clock_suspend(void) +{ + sched_clock_poll(sched_clock_timer.data); + cd.suspended = true; + return 0; +} + +static void sched_clock_resume(void) +{ + cd.epoch_cyc = read_sched_clock(); + cd.epoch_cyc_copy = cd.epoch_cyc; + cd.suspended = false; +} + +static struct syscore_ops sched_clock_ops = { + .suspend = sched_clock_suspend, + .resume = sched_clock_resume, +}; + +static int __init sched_clock_syscore_init(void) +{ + register_syscore_ops(&sched_clock_ops); + return 0; +} +device_initcall(sched_clock_syscore_init); diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 206bbfb34e09..6d3f91631de6 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -19,6 +19,7 @@ #include <linux/profile.h> #include <linux/sched.h> #include <linux/smp.h> +#include <linux/module.h> #include "tick-internal.h" @@ -29,6 +30,7 @@ static struct tick_device tick_broadcast_device; static cpumask_var_t tick_broadcast_mask; +static cpumask_var_t tick_broadcast_on; static cpumask_var_t tmpmask; static DEFINE_RAW_SPINLOCK(tick_broadcast_lock); static int tick_broadcast_force; @@ -64,17 +66,34 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc) /* * Check, if the device can be utilized as broadcast device: */ -int tick_check_broadcast_device(struct clock_event_device *dev) +static bool tick_check_broadcast_device(struct clock_event_device *curdev, + struct clock_event_device *newdev) +{ + if ((newdev->features & CLOCK_EVT_FEAT_DUMMY) || + (newdev->features & CLOCK_EVT_FEAT_C3STOP)) + return false; + + if (tick_broadcast_device.mode == TICKDEV_MODE_ONESHOT && + !(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) + return false; + + return !curdev || newdev->rating > curdev->rating; +} + +/* + * Conditionally install/replace broadcast device + */ +void tick_install_broadcast_device(struct clock_event_device *dev) { struct clock_event_device *cur = tick_broadcast_device.evtdev; - if ((dev->features & CLOCK_EVT_FEAT_DUMMY) || - (tick_broadcast_device.evtdev && - tick_broadcast_device.evtdev->rating >= dev->rating) || - (dev->features & CLOCK_EVT_FEAT_C3STOP)) - return 0; + if (!tick_check_broadcast_device(cur, dev)) + return; + + if (!try_module_get(dev->owner)) + return; - clockevents_exchange_device(tick_broadcast_device.evtdev, dev); + clockevents_exchange_device(cur, dev); if (cur) cur->event_handler = clockevents_handle_noop; tick_broadcast_device.evtdev = dev; @@ -90,7 +109,6 @@ int tick_check_broadcast_device(struct clock_event_device *dev) */ if (dev->features & CLOCK_EVT_FEAT_ONESHOT) tick_clock_notify(); - return 1; } /* @@ -123,8 +141,9 @@ static void tick_device_setup_broadcast_func(struct clock_event_device *dev) */ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { + struct clock_event_device *bc = tick_broadcast_device.evtdev; unsigned long flags; - int ret = 0; + int ret; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); @@ -138,20 +157,59 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) dev->event_handler = tick_handle_periodic; tick_device_setup_broadcast_func(dev); cpumask_set_cpu(cpu, tick_broadcast_mask); - tick_broadcast_start_periodic(tick_broadcast_device.evtdev); + tick_broadcast_start_periodic(bc); ret = 1; } else { /* - * When the new device is not affected by the stop - * feature and the cpu is marked in the broadcast mask - * then clear the broadcast bit. + * Clear the broadcast bit for this cpu if the + * device is not power state affected. */ - if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) { - int cpu = smp_processor_id(); + if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) cpumask_clear_cpu(cpu, tick_broadcast_mask); - tick_broadcast_clear_oneshot(cpu); - } else { + else tick_device_setup_broadcast_func(dev); + + /* + * Clear the broadcast bit if the CPU is not in + * periodic broadcast on state. + */ + if (!cpumask_test_cpu(cpu, tick_broadcast_on)) + cpumask_clear_cpu(cpu, tick_broadcast_mask); + + switch (tick_broadcast_device.mode) { + case TICKDEV_MODE_ONESHOT: + /* + * If the system is in oneshot mode we can + * unconditionally clear the oneshot mask bit, + * because the CPU is running and therefore + * not in an idle state which causes the power + * state affected device to stop. Let the + * caller initialize the device. + */ + tick_broadcast_clear_oneshot(cpu); + ret = 0; + break; + + case TICKDEV_MODE_PERIODIC: + /* + * If the system is in periodic mode, check + * whether the broadcast device can be + * switched off now. + */ + if (cpumask_empty(tick_broadcast_mask) && bc) + clockevents_shutdown(bc); + /* + * If we kept the cpu in the broadcast mask, + * tell the caller to leave the per cpu device + * in shutdown state. The periodic interrupt + * is delivered by the broadcast device. + */ + ret = cpumask_test_cpu(cpu, tick_broadcast_mask); + break; + default: + /* Nothing to do */ + ret = 0; + break; } } raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); @@ -281,6 +339,7 @@ static void tick_do_broadcast_on_off(unsigned long *reason) switch (*reason) { case CLOCK_EVT_NOTIFY_BROADCAST_ON: case CLOCK_EVT_NOTIFY_BROADCAST_FORCE: + cpumask_set_cpu(cpu, tick_broadcast_on); if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) { if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) @@ -290,8 +349,12 @@ static void tick_do_broadcast_on_off(unsigned long *reason) tick_broadcast_force = 1; break; case CLOCK_EVT_NOTIFY_BROADCAST_OFF: - if (!tick_broadcast_force && - cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) { + if (tick_broadcast_force) + break; + cpumask_clear_cpu(cpu, tick_broadcast_on); + if (!tick_device_is_functional(dev)) + break; + if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) { if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) tick_setup_periodic(dev, 0); @@ -349,6 +412,7 @@ void tick_shutdown_broadcast(unsigned int *cpup) bc = tick_broadcast_device.evtdev; cpumask_clear_cpu(cpu, tick_broadcast_mask); + cpumask_clear_cpu(cpu, tick_broadcast_on); if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) { if (bc && cpumask_empty(tick_broadcast_mask)) @@ -475,7 +539,15 @@ void tick_check_oneshot_broadcast(int cpu) if (cpumask_test_cpu(cpu, tick_broadcast_oneshot_mask)) { struct tick_device *td = &per_cpu(tick_cpu_device, cpu); - clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_ONESHOT); + /* + * We might be in the middle of switching over from + * periodic to oneshot. If the CPU has not yet + * switched over, leave the device alone. + */ + if (td->mode == TICKDEV_MODE_ONESHOT) { + clockevents_set_mode(td->evtdev, + CLOCK_EVT_MODE_ONESHOT); + } } } @@ -511,11 +583,24 @@ again: } } + /* + * Remove the current cpu from the pending mask. The event is + * delivered immediately in tick_do_broadcast() ! + */ + cpumask_clear_cpu(smp_processor_id(), tick_broadcast_pending_mask); + /* Take care of enforced broadcast requests */ cpumask_or(tmpmask, tmpmask, tick_broadcast_force_mask); cpumask_clear(tick_broadcast_force_mask); /* + * Sanity check. Catch the case where we try to broadcast to + * offline cpus. + */ + if (WARN_ON_ONCE(!cpumask_subset(tmpmask, cpu_online_mask))) + cpumask_and(tmpmask, tmpmask, cpu_online_mask); + + /* * Wakeup the cpus which have an expired event. */ tick_do_broadcast(tmpmask); @@ -575,8 +660,8 @@ void tick_broadcast_oneshot_control(unsigned long reason) raw_spin_lock_irqsave(&tick_broadcast_lock, flags); if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) { - WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask)); if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) { + WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask)); clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN); /* * We only reprogram the broadcast timer if we @@ -593,8 +678,6 @@ void tick_broadcast_oneshot_control(unsigned long reason) } else { if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) { clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); - if (dev->next_event.tv64 == KTIME_MAX) - goto out; /* * The cpu which was handling the broadcast * timer marked this cpu in the broadcast @@ -609,6 +692,11 @@ void tick_broadcast_oneshot_control(unsigned long reason) goto out; /* + * Bail out if there is no next event. + */ + if (dev->next_event.tv64 == KTIME_MAX) + goto out; + /* * If the pending bit is not set, then we are * either the CPU handling the broadcast * interrupt or we got woken by something else. @@ -692,10 +780,6 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) bc->event_handler = tick_handle_oneshot_broadcast; - /* Take the do_timer update */ - if (!tick_nohz_full_cpu(cpu)) - tick_do_timer_cpu = cpu; - /* * We must be careful here. There might be other CPUs * waiting for periodic broadcast. We need to set the @@ -756,10 +840,12 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup) raw_spin_lock_irqsave(&tick_broadcast_lock, flags); /* - * Clear the broadcast mask flag for the dead cpu, but do not - * stop the broadcast device! + * Clear the broadcast masks for the dead cpu, but do not stop + * the broadcast device! */ cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); + cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); + cpumask_clear_cpu(cpu, tick_broadcast_force_mask); raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } @@ -786,11 +872,12 @@ bool tick_broadcast_oneshot_available(void) void __init tick_broadcast_init(void) { - alloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT); - alloc_cpumask_var(&tmpmask, GFP_NOWAIT); + zalloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT); + zalloc_cpumask_var(&tick_broadcast_on, GFP_NOWAIT); + zalloc_cpumask_var(&tmpmask, GFP_NOWAIT); #ifdef CONFIG_TICK_ONESHOT - alloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT); - alloc_cpumask_var(&tick_broadcast_pending_mask, GFP_NOWAIT); - alloc_cpumask_var(&tick_broadcast_force_mask, GFP_NOWAIT); + zalloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT); + zalloc_cpumask_var(&tick_broadcast_pending_mask, GFP_NOWAIT); + zalloc_cpumask_var(&tick_broadcast_force_mask, GFP_NOWAIT); #endif } diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 5d3fb100bc06..64522ecdfe0e 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -18,6 +18,7 @@ #include <linux/percpu.h> #include <linux/profile.h> #include <linux/sched.h> +#include <linux/module.h> #include <asm/irq_regs.h> @@ -33,7 +34,6 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device); ktime_t tick_next_period; ktime_t tick_period; int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT; -static DEFINE_RAW_SPINLOCK(tick_device_lock); /* * Debugging: see timer_list.c @@ -194,7 +194,8 @@ static void tick_setup_device(struct tick_device *td, * When global broadcasting is active, check if the current * device is registered as a placeholder for broadcast mode. * This allows us to handle this x86 misfeature in a generic - * way. + * way. This function also returns !=0 when we keep the + * current active broadcast state for this CPU. */ if (tick_device_uses_broadcast(newdev, cpu)) return; @@ -205,17 +206,75 @@ static void tick_setup_device(struct tick_device *td, tick_setup_oneshot(newdev, handler, next_event); } +void tick_install_replacement(struct clock_event_device *newdev) +{ + struct tick_device *td = &__get_cpu_var(tick_cpu_device); + int cpu = smp_processor_id(); + + clockevents_exchange_device(td->evtdev, newdev); + tick_setup_device(td, newdev, cpu, cpumask_of(cpu)); + if (newdev->features & CLOCK_EVT_FEAT_ONESHOT) + tick_oneshot_notify(); +} + +static bool tick_check_percpu(struct clock_event_device *curdev, + struct clock_event_device *newdev, int cpu) +{ + if (!cpumask_test_cpu(cpu, newdev->cpumask)) + return false; + if (cpumask_equal(newdev->cpumask, cpumask_of(cpu))) + return true; + /* Check if irq affinity can be set */ + if (newdev->irq >= 0 && !irq_can_set_affinity(newdev->irq)) + return false; + /* Prefer an existing cpu local device */ + if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu))) + return false; + return true; +} + +static bool tick_check_preferred(struct clock_event_device *curdev, + struct clock_event_device *newdev) +{ + /* Prefer oneshot capable device */ + if (!(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) { + if (curdev && (curdev->features & CLOCK_EVT_FEAT_ONESHOT)) + return false; + if (tick_oneshot_mode_active()) + return false; + } + + /* + * Use the higher rated one, but prefer a CPU local device with a lower + * rating than a non-CPU local device + */ + return !curdev || + newdev->rating > curdev->rating || + !cpumask_equal(curdev->cpumask, newdev->cpumask); +} + +/* + * Check whether the new device is a better fit than curdev. curdev + * can be NULL ! + */ +bool tick_check_replacement(struct clock_event_device *curdev, + struct clock_event_device *newdev) +{ + if (tick_check_percpu(curdev, newdev, smp_processor_id())) + return false; + + return tick_check_preferred(curdev, newdev); +} + /* - * Check, if the new registered device should be used. + * Check, if the new registered device should be used. Called with + * clockevents_lock held and interrupts disabled. */ -static int tick_check_new_device(struct clock_event_device *newdev) +void tick_check_new_device(struct clock_event_device *newdev) { struct clock_event_device *curdev; struct tick_device *td; - int cpu, ret = NOTIFY_OK; - unsigned long flags; - - raw_spin_lock_irqsave(&tick_device_lock, flags); + int cpu; cpu = smp_processor_id(); if (!cpumask_test_cpu(cpu, newdev->cpumask)) @@ -225,40 +284,15 @@ static int tick_check_new_device(struct clock_event_device *newdev) curdev = td->evtdev; /* cpu local device ? */ - if (!cpumask_equal(newdev->cpumask, cpumask_of(cpu))) { - - /* - * If the cpu affinity of the device interrupt can not - * be set, ignore it. - */ - if (!irq_can_set_affinity(newdev->irq)) - goto out_bc; + if (!tick_check_percpu(curdev, newdev, cpu)) + goto out_bc; - /* - * If we have a cpu local device already, do not replace it - * by a non cpu local device - */ - if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu))) - goto out_bc; - } + /* Preference decision */ + if (!tick_check_preferred(curdev, newdev)) + goto out_bc; - /* - * If we have an active device, then check the rating and the oneshot - * feature. - */ - if (curdev) { - /* - * Prefer one shot capable devices ! - */ - if ((curdev->features & CLOCK_EVT_FEAT_ONESHOT) && - !(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) - goto out_bc; - /* - * Check the rating - */ - if (curdev->rating >= newdev->rating) - goto out_bc; - } + if (!try_module_get(newdev->owner)) + return; /* * Replace the eventually existing device by the new @@ -273,20 +307,13 @@ static int tick_check_new_device(struct clock_event_device *newdev) tick_setup_device(td, newdev, cpu, cpumask_of(cpu)); if (newdev->features & CLOCK_EVT_FEAT_ONESHOT) tick_oneshot_notify(); - - raw_spin_unlock_irqrestore(&tick_device_lock, flags); - return NOTIFY_STOP; + return; out_bc: /* * Can the new device be used as a broadcast device ? */ - if (tick_check_broadcast_device(newdev)) - ret = NOTIFY_STOP; - - raw_spin_unlock_irqrestore(&tick_device_lock, flags); - - return ret; + tick_install_broadcast_device(newdev); } /* @@ -294,7 +321,7 @@ out_bc: * * Called with interrupts disabled. */ -static void tick_handover_do_timer(int *cpup) +void tick_handover_do_timer(int *cpup) { if (*cpup == tick_do_timer_cpu) { int cpu = cpumask_first(cpu_online_mask); @@ -311,13 +338,11 @@ static void tick_handover_do_timer(int *cpup) * access the hardware device itself. * We just set the mode and remove it from the lists. */ -static void tick_shutdown(unsigned int *cpup) +void tick_shutdown(unsigned int *cpup) { struct tick_device *td = &per_cpu(tick_cpu_device, *cpup); struct clock_event_device *dev = td->evtdev; - unsigned long flags; - raw_spin_lock_irqsave(&tick_device_lock, flags); td->mode = TICKDEV_MODE_PERIODIC; if (dev) { /* @@ -329,26 +354,20 @@ static void tick_shutdown(unsigned int *cpup) dev->event_handler = clockevents_handle_noop; td->evtdev = NULL; } - raw_spin_unlock_irqrestore(&tick_device_lock, flags); } -static void tick_suspend(void) +void tick_suspend(void) { struct tick_device *td = &__get_cpu_var(tick_cpu_device); - unsigned long flags; - raw_spin_lock_irqsave(&tick_device_lock, flags); clockevents_shutdown(td->evtdev); - raw_spin_unlock_irqrestore(&tick_device_lock, flags); } -static void tick_resume(void) +void tick_resume(void) { struct tick_device *td = &__get_cpu_var(tick_cpu_device); - unsigned long flags; int broadcast = tick_resume_broadcast(); - raw_spin_lock_irqsave(&tick_device_lock, flags); clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_RESUME); if (!broadcast) { @@ -357,68 +376,12 @@ static void tick_resume(void) else tick_resume_oneshot(); } - raw_spin_unlock_irqrestore(&tick_device_lock, flags); } -/* - * Notification about clock event devices - */ -static int tick_notify(struct notifier_block *nb, unsigned long reason, - void *dev) -{ - switch (reason) { - - case CLOCK_EVT_NOTIFY_ADD: - return tick_check_new_device(dev); - - case CLOCK_EVT_NOTIFY_BROADCAST_ON: - case CLOCK_EVT_NOTIFY_BROADCAST_OFF: - case CLOCK_EVT_NOTIFY_BROADCAST_FORCE: - tick_broadcast_on_off(reason, dev); - break; - - case CLOCK_EVT_NOTIFY_BROADCAST_ENTER: - case CLOCK_EVT_NOTIFY_BROADCAST_EXIT: - tick_broadcast_oneshot_control(reason); - break; - - case CLOCK_EVT_NOTIFY_CPU_DYING: - tick_handover_do_timer(dev); - break; - - case CLOCK_EVT_NOTIFY_CPU_DEAD: - tick_shutdown_broadcast_oneshot(dev); - tick_shutdown_broadcast(dev); - tick_shutdown(dev); - break; - - case CLOCK_EVT_NOTIFY_SUSPEND: - tick_suspend(); - tick_suspend_broadcast(); - break; - - case CLOCK_EVT_NOTIFY_RESUME: - tick_resume(); - break; - - default: - break; - } - - return NOTIFY_OK; -} - -static struct notifier_block tick_notifier = { - .notifier_call = tick_notify, -}; - /** * tick_init - initialize the tick control - * - * Register the notifier with the clockevents framework */ void __init tick_init(void) { - clockevents_register_notifier(&tick_notifier); tick_broadcast_init(); } diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index f0299eae4602..bc906cad709b 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -6,6 +6,8 @@ extern seqlock_t jiffies_lock; +#define CS_NAME_LEN 32 + #ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD #define TICK_DO_TIMER_NONE -1 @@ -18,9 +20,19 @@ extern int tick_do_timer_cpu __read_mostly; extern void tick_setup_periodic(struct clock_event_device *dev, int broadcast); extern void tick_handle_periodic(struct clock_event_device *dev); +extern void tick_check_new_device(struct clock_event_device *dev); +extern void tick_handover_do_timer(int *cpup); +extern void tick_shutdown(unsigned int *cpup); +extern void tick_suspend(void); +extern void tick_resume(void); +extern bool tick_check_replacement(struct clock_event_device *curdev, + struct clock_event_device *newdev); +extern void tick_install_replacement(struct clock_event_device *dev); extern void clockevents_shutdown(struct clock_event_device *dev); +extern size_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); + /* * NO_HZ / high resolution timer shared code */ @@ -90,7 +102,7 @@ static inline bool tick_broadcast_oneshot_available(void) { return false; } */ #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu); -extern int tick_check_broadcast_device(struct clock_event_device *dev); +extern void tick_install_broadcast_device(struct clock_event_device *dev); extern int tick_is_broadcast_device(struct clock_event_device *dev); extern void tick_broadcast_on_off(unsigned long reason, int *oncpu); extern void tick_shutdown_broadcast(unsigned int *cpup); @@ -102,9 +114,8 @@ tick_set_periodic_handler(struct clock_event_device *dev, int broadcast); #else /* !BROADCAST */ -static inline int tick_check_broadcast_device(struct clock_event_device *dev) +static inline void tick_install_broadcast_device(struct clock_event_device *dev) { - return 0; } static inline int tick_is_broadcast_device(struct clock_event_device *dev) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index bc67d4245e1d..0cf1c1453181 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -306,7 +306,7 @@ static int __cpuinit tick_nohz_cpu_down_callback(struct notifier_block *nfb, * we can't safely shutdown that CPU. */ if (have_nohz_full_mask && tick_do_timer_cpu == cpu) - return -EINVAL; + return NOTIFY_BAD; break; } return NOTIFY_OK; @@ -717,6 +717,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) if (unlikely(!cpu_online(cpu))) { if (cpu == tick_do_timer_cpu) tick_do_timer_cpu = TICK_DO_TIMER_NONE; + return false; } if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) @@ -1168,7 +1169,7 @@ void tick_cancel_sched_timer(int cpu) hrtimer_cancel(&ts->sched_timer); # endif - ts->nohz_mode = NOHZ_MODE_INACTIVE; + memset(ts, 0, sizeof(*ts)); } #endif diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 98cd470bbe49..48b9fffabdc2 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -25,6 +25,11 @@ #include "tick-internal.h" #include "ntp_internal.h" +#include "timekeeping_internal.h" + +#define TK_CLEAR_NTP (1 << 0) +#define TK_MIRROR (1 << 1) +#define TK_CLOCK_WAS_SET (1 << 2) static struct timekeeper timekeeper; static DEFINE_RAW_SPINLOCK(timekeeper_lock); @@ -200,9 +205,9 @@ static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk) static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); -static void update_pvclock_gtod(struct timekeeper *tk) +static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) { - raw_notifier_call_chain(&pvclock_gtod_chain, 0, tk); + raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk); } /** @@ -216,7 +221,7 @@ int pvclock_gtod_register_notifier(struct notifier_block *nb) raw_spin_lock_irqsave(&timekeeper_lock, flags); ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); - update_pvclock_gtod(tk); + update_pvclock_gtod(tk, true); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; @@ -241,16 +246,16 @@ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); /* must hold timekeeper_lock */ -static void timekeeping_update(struct timekeeper *tk, bool clearntp, bool mirror) +static void timekeeping_update(struct timekeeper *tk, unsigned int action) { - if (clearntp) { + if (action & TK_CLEAR_NTP) { tk->ntp_error = 0; ntp_clear(); } update_vsyscall(tk); - update_pvclock_gtod(tk); + update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); - if (mirror) + if (action & TK_MIRROR) memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper)); } @@ -508,7 +513,7 @@ int do_settimeofday(const struct timespec *tv) tk_set_xtime(tk, tv); - timekeeping_update(tk, true, true); + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -552,7 +557,7 @@ int timekeeping_inject_offset(struct timespec *ts) tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *ts)); error: /* even if we error out, we forwarded the time, so call update */ - timekeeping_update(tk, true, true); + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -627,13 +632,22 @@ static int change_clocksource(void *data) write_seqcount_begin(&timekeeper_seq); timekeeping_forward_now(tk); - if (!new->enable || new->enable(new) == 0) { - old = tk->clock; - tk_setup_internals(tk, new); - if (old->disable) - old->disable(old); + /* + * If the cs is in module, get a module reference. Succeeds + * for built-in code (owner == NULL) as well. + */ + if (try_module_get(new->owner)) { + if (!new->enable || new->enable(new) == 0) { + old = tk->clock; + tk_setup_internals(tk, new); + if (old->disable) + old->disable(old); + module_put(old->owner); + } else { + module_put(new->owner); + } } - timekeeping_update(tk, true, true); + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -648,14 +662,15 @@ static int change_clocksource(void *data) * This function is called from clocksource.c after a new, better clock * source has been registered. The caller holds the clocksource_mutex. */ -void timekeeping_notify(struct clocksource *clock) +int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &timekeeper; if (tk->clock == clock) - return; + return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); + return tk->clock == clock ? 0 : -1; } /** @@ -841,6 +856,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, tk_xtime_add(tk, delta); tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *delta)); tk_set_sleep_time(tk, timespec_add(tk->total_sleep_time, *delta)); + tk_debug_account_sleep_time(delta); } /** @@ -872,7 +888,7 @@ void timekeeping_inject_sleeptime(struct timespec *delta) __timekeeping_inject_sleeptime(tk, delta); - timekeeping_update(tk, true, true); + timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -954,7 +970,7 @@ static void timekeeping_resume(void) tk->cycle_last = clock->cycle_last = cycle_now; tk->ntp_error = 0; timekeeping_suspended = 0; - timekeeping_update(tk, false, true); + timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&timekeeper_seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -975,6 +991,14 @@ static int timekeeping_suspend(void) read_persistent_clock(&timekeeping_suspend_time); + /* + * On some systems the persistent_clock can not be detected at + * timekeeping_init by its return value, so if we see a valid + * value returned, update the persistent_clock_exists flag. + */ + if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) + persistent_clock_exist = true; + raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&timekeeper_seq); timekeeping_forward_now(tk); @@ -1228,9 +1252,10 @@ out_adjust: * It also calls into the NTP code to handle leapsecond processing. * */ -static inline void accumulate_nsecs_to_secs(struct timekeeper *tk) +static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { u64 nsecps = (u64)NSEC_PER_SEC << tk->shift; + unsigned int action = 0; while (tk->xtime_nsec >= nsecps) { int leap; @@ -1253,8 +1278,10 @@ static inline void accumulate_nsecs_to_secs(struct timekeeper *tk) __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); clock_was_set_delayed(); + action = TK_CLOCK_WAS_SET; } } + return action; } /** @@ -1339,6 +1366,7 @@ static void update_wall_time(void) struct timekeeper *tk = &shadow_timekeeper; cycle_t offset; int shift = 0, maxshift; + unsigned int action; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); @@ -1391,7 +1419,7 @@ static void update_wall_time(void) * Finally, make sure that after the rounding * xtime_nsec isn't larger than NSEC_PER_SEC */ - accumulate_nsecs_to_secs(tk); + action = accumulate_nsecs_to_secs(tk); write_seqcount_begin(&timekeeper_seq); /* Update clock->cycle_last with the new value */ @@ -1407,7 +1435,7 @@ static void update_wall_time(void) * updating. */ memcpy(real_tk, tk, sizeof(*tk)); - timekeeping_update(real_tk, false, false); + timekeeping_update(real_tk, action); write_seqcount_end(&timekeeper_seq); out: raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -1669,6 +1697,7 @@ int do_adjtimex(struct timex *txc) if (tai != orig_tai) { __timekeeping_set_tai_offset(tk, tai); + update_pvclock_gtod(tk, true); clock_was_set_delayed(); } write_seqcount_end(&timekeeper_seq); diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c new file mode 100644 index 000000000000..802433a4f5eb --- /dev/null +++ b/kernel/time/timekeeping_debug.c @@ -0,0 +1,72 @@ +/* + * debugfs file to track time spent in suspend + * + * Copyright (c) 2011, Google, Inc. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/debugfs.h> +#include <linux/err.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/seq_file.h> +#include <linux/time.h> + +static unsigned int sleep_time_bin[32] = {0}; + +static int tk_debug_show_sleep_time(struct seq_file *s, void *data) +{ + unsigned int bin; + seq_puts(s, " time (secs) count\n"); + seq_puts(s, "------------------------------\n"); + for (bin = 0; bin < 32; bin++) { + if (sleep_time_bin[bin] == 0) + continue; + seq_printf(s, "%10u - %-10u %4u\n", + bin ? 1 << (bin - 1) : 0, 1 << bin, + sleep_time_bin[bin]); + } + return 0; +} + +static int tk_debug_sleep_time_open(struct inode *inode, struct file *file) +{ + return single_open(file, tk_debug_show_sleep_time, NULL); +} + +static const struct file_operations tk_debug_sleep_time_fops = { + .open = tk_debug_sleep_time_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init tk_debug_sleep_time_init(void) +{ + struct dentry *d; + + d = debugfs_create_file("sleep_time", 0444, NULL, NULL, + &tk_debug_sleep_time_fops); + if (!d) { + pr_err("Failed to create sleep_time debug file\n"); + return -ENOMEM; + } + + return 0; +} +late_initcall(tk_debug_sleep_time_init); + +void tk_debug_account_sleep_time(struct timespec *t) +{ + sleep_time_bin[fls(t->tv_sec)]++; +} + diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h new file mode 100644 index 000000000000..13323ea08ffa --- /dev/null +++ b/kernel/time/timekeeping_internal.h @@ -0,0 +1,14 @@ +#ifndef _TIMEKEEPING_INTERNAL_H +#define _TIMEKEEPING_INTERNAL_H +/* + * timekeeping debug functions + */ +#include <linux/time.h> + +#ifdef CONFIG_DEBUG_FS +extern void tk_debug_account_sleep_time(struct timespec *t); +#else +#define tk_debug_account_sleep_time(x) +#endif + +#endif /* _TIMEKEEPING_INTERNAL_H */ diff --git a/kernel/timer.c b/kernel/timer.c index a860bba34412..15bc1b41021d 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -149,9 +149,11 @@ static unsigned long round_jiffies_common(unsigned long j, int cpu, /* now that we have rounded, subtract the extra skew again */ j -= cpu * 3; - if (j <= jiffies) /* rounding ate our timeout entirely; */ - return original; - return j; + /* + * Make sure j is still in the future. Otherwise return the + * unmodified value. + */ + return time_is_after_jiffies(j) ? j : original; } /** @@ -1539,12 +1541,12 @@ static int __cpuinit init_timers_cpu(int cpu) boot_done = 1; base = &boot_tvec_bases; } + spin_lock_init(&base->lock); tvec_base_done[cpu] = 1; } else { base = per_cpu(tvec_bases, cpu); } - spin_lock_init(&base->lock); for (j = 0; j < TVN_SIZE; j++) { INIT_LIST_HEAD(base->tv5.vec + j); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index b549b0f5b977..6c508ff33c62 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -120,22 +120,22 @@ static void ftrace_ops_no_ops(unsigned long ip, unsigned long parent_ip); /* * Traverse the ftrace_global_list, invoking all entries. The reason that we - * can use rcu_dereference_raw() is that elements removed from this list + * can use rcu_dereference_raw_notrace() is that elements removed from this list * are simply leaked, so there is no need to interact with a grace-period - * mechanism. The rcu_dereference_raw() calls are needed to handle + * mechanism. The rcu_dereference_raw_notrace() calls are needed to handle * concurrent insertions into the ftrace_global_list. * * Silly Alpha and silly pointer-speculation compiler optimizations! */ #define do_for_each_ftrace_op(op, list) \ - op = rcu_dereference_raw(list); \ + op = rcu_dereference_raw_notrace(list); \ do /* * Optimized for just a single item in the list (as that is the normal case). */ #define while_for_each_ftrace_op(op) \ - while (likely(op = rcu_dereference_raw((op)->next)) && \ + while (likely(op = rcu_dereference_raw_notrace((op)->next)) && \ unlikely((op) != &ftrace_list_end)) static inline void ftrace_ops_init(struct ftrace_ops *ops) @@ -779,7 +779,7 @@ ftrace_find_profiled_func(struct ftrace_profile_stat *stat, unsigned long ip) if (hlist_empty(hhd)) return NULL; - hlist_for_each_entry_rcu(rec, hhd, node) { + hlist_for_each_entry_rcu_notrace(rec, hhd, node) { if (rec->ip == ip) return rec; } @@ -1165,7 +1165,7 @@ ftrace_lookup_ip(struct ftrace_hash *hash, unsigned long ip) hhd = &hash->buckets[key]; - hlist_for_each_entry_rcu(entry, hhd, hlist) { + hlist_for_each_entry_rcu_notrace(entry, hhd, hlist) { if (entry->ip == ip) return entry; } @@ -1422,8 +1422,8 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip) struct ftrace_hash *notrace_hash; int ret; - filter_hash = rcu_dereference_raw(ops->filter_hash); - notrace_hash = rcu_dereference_raw(ops->notrace_hash); + filter_hash = rcu_dereference_raw_notrace(ops->filter_hash); + notrace_hash = rcu_dereference_raw_notrace(ops->notrace_hash); if ((ftrace_hash_empty(filter_hash) || ftrace_lookup_ip(filter_hash, ip)) && @@ -2920,7 +2920,7 @@ static void function_trace_probe_call(unsigned long ip, unsigned long parent_ip, * on the hash. rcu_read_lock is too dangerous here. */ preempt_disable_notrace(); - hlist_for_each_entry_rcu(entry, hhd, node) { + hlist_for_each_entry_rcu_notrace(entry, hhd, node) { if (entry->ip == ip) entry->ops->func(ip, parent_ip, &entry->data); } diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index b59aea2c48c2..e444ff88f0a4 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -620,6 +620,9 @@ int ring_buffer_poll_wait(struct ring_buffer *buffer, int cpu, if (cpu == RING_BUFFER_ALL_CPUS) work = &buffer->irq_work; else { + if (!cpumask_test_cpu(cpu, buffer->cpumask)) + return -EINVAL; + cpu_buffer = buffer->buffers[cpu]; work = &cpu_buffer->irq_work; } diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ae6fa2d1cdf7..e71a8be4a6ee 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -652,8 +652,6 @@ static struct { ARCH_TRACE_CLOCKS }; -int trace_clock_id; - /* * trace_parser_get_init - gets the buffer for trace parser */ @@ -843,7 +841,15 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) memcpy(max_data->comm, tsk->comm, TASK_COMM_LEN); max_data->pid = tsk->pid; - max_data->uid = task_uid(tsk); + /* + * If tsk == current, then use current_uid(), as that does not use + * RCU. The irq tracer can be called out of RCU scope. + */ + if (tsk == current) + max_data->uid = current_uid(); + else + max_data->uid = task_uid(tsk); + max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO; max_data->policy = tsk->policy; max_data->rt_priority = tsk->rt_priority; @@ -2818,7 +2824,7 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot) iter->iter_flags |= TRACE_FILE_ANNOTATE; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ - if (trace_clocks[trace_clock_id].in_ns) + if (trace_clocks[tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; /* stop the trace while dumping if we are not opening "snapshot" */ @@ -3817,7 +3823,7 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp) iter->iter_flags |= TRACE_FILE_LAT_FMT; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ - if (trace_clocks[trace_clock_id].in_ns) + if (trace_clocks[tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; iter->cpu_file = tc->cpu; @@ -5087,7 +5093,7 @@ tracing_stats_read(struct file *filp, char __user *ubuf, cnt = ring_buffer_bytes_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "bytes: %ld\n", cnt); - if (trace_clocks[trace_clock_id].in_ns) { + if (trace_clocks[tr->clock_id].in_ns) { /* local or global for trace_clock */ t = ns2usecs(ring_buffer_oldest_event_ts(trace_buf->buffer, cpu)); usec_rem = do_div(t, USEC_PER_SEC); @@ -6216,10 +6222,15 @@ __init static int tracer_alloc_buffers(void) trace_init_cmdlines(); - register_tracer(&nop_trace); - + /* + * register_tracer() might reference current_trace, so it + * needs to be set before we register anything. This is + * just a bootstrap of current_trace anyway. + */ global_trace.current_trace = &nop_trace; + register_tracer(&nop_trace); + /* All seems OK, enable tracing */ tracing_disabled = 0; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 711ca7d3e7f1..20572ed88c5c 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -700,8 +700,6 @@ enum print_line_t print_trace_line(struct trace_iterator *iter); extern unsigned long trace_flags; -extern int trace_clock_id; - /* Standard output formatting function used for function return traces */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 7a0cf68027cc..27963e2bf4bf 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -2072,8 +2072,10 @@ event_enable_func(struct ftrace_hash *hash, out_reg: /* Don't let event modules unload while probe registered */ ret = try_module_get(file->event_call->mod); - if (!ret) + if (!ret) { + ret = -EBUSY; goto out_free; + } ret = __ftrace_event_enable_disable(file, 1, 1); if (ret < 0) diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c index a6361178de5a..e1b653f7e1ca 100644 --- a/kernel/trace/trace_events_filter.c +++ b/kernel/trace/trace_events_filter.c @@ -750,7 +750,11 @@ static int filter_set_pred(struct event_filter *filter, static void __free_preds(struct event_filter *filter) { + int i; + if (filter->preds) { + for (i = 0; i < filter->n_preds; i++) + kfree(filter->preds[i].ops); kfree(filter->preds); filter->preds = NULL; } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 636d45fe69b3..9f46e98ba8f2 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -35,7 +35,7 @@ struct trace_probe { const char *symbol; /* symbol name */ struct ftrace_event_class class; struct ftrace_event_call call; - struct ftrace_event_file **files; + struct ftrace_event_file * __rcu *files; ssize_t size; /* trace entry size */ unsigned int nr_args; struct probe_arg args[]; @@ -185,9 +185,14 @@ static struct trace_probe *find_trace_probe(const char *event, static int trace_probe_nr_files(struct trace_probe *tp) { - struct ftrace_event_file **file = tp->files; + struct ftrace_event_file **file; int ret = 0; + /* + * Since all tp->files updater is protected by probe_enable_lock, + * we don't need to lock an rcu_read_lock. + */ + file = rcu_dereference_raw(tp->files); if (file) while (*(file++)) ret++; @@ -209,9 +214,10 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file) mutex_lock(&probe_enable_lock); if (file) { - struct ftrace_event_file **new, **old = tp->files; + struct ftrace_event_file **new, **old; int n = trace_probe_nr_files(tp); + old = rcu_dereference_raw(tp->files); /* 1 is for new one and 1 is for stopper */ new = kzalloc((n + 2) * sizeof(struct ftrace_event_file *), GFP_KERNEL); @@ -251,11 +257,17 @@ enable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file) static int trace_probe_file_index(struct trace_probe *tp, struct ftrace_event_file *file) { + struct ftrace_event_file **files; int i; - if (tp->files) { - for (i = 0; tp->files[i]; i++) - if (tp->files[i] == file) + /* + * Since all tp->files updater is protected by probe_enable_lock, + * we don't need to lock an rcu_read_lock. + */ + files = rcu_dereference_raw(tp->files); + if (files) { + for (i = 0; files[i]; i++) + if (files[i] == file) return i; } @@ -274,10 +286,11 @@ disable_trace_probe(struct trace_probe *tp, struct ftrace_event_file *file) mutex_lock(&probe_enable_lock); if (file) { - struct ftrace_event_file **new, **old = tp->files; + struct ftrace_event_file **new, **old; int n = trace_probe_nr_files(tp); int i, j; + old = rcu_dereference_raw(tp->files); if (n == 0 || trace_probe_file_index(tp, file) < 0) { ret = -EINVAL; goto out_unlock; @@ -872,9 +885,16 @@ __kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs, static __kprobes void kprobe_trace_func(struct trace_probe *tp, struct pt_regs *regs) { - struct ftrace_event_file **file = tp->files; + /* + * Note: preempt is already disabled around the kprobe handler. + * However, we still need an smp_read_barrier_depends() corresponding + * to smp_wmb() in rcu_assign_pointer() to access the pointer. + */ + struct ftrace_event_file **file = rcu_dereference_raw(tp->files); + + if (unlikely(!file)) + return; - /* Note: preempt is already disabled around the kprobe handler */ while (*file) { __kprobe_trace_func(tp, regs, *file); file++; @@ -925,9 +945,16 @@ static __kprobes void kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri, struct pt_regs *regs) { - struct ftrace_event_file **file = tp->files; + /* + * Note: preempt is already disabled around the kprobe handler. + * However, we still need an smp_read_barrier_depends() corresponding + * to smp_wmb() in rcu_assign_pointer() to access the pointer. + */ + struct ftrace_event_file **file = rcu_dereference_raw(tp->files); + + if (unlikely(!file)) + return; - /* Note: preempt is already disabled around the kprobe handler */ while (*file) { __kretprobe_trace_func(tp, ri, regs, *file); file++; @@ -935,7 +962,7 @@ kretprobe_trace_func(struct trace_probe *tp, struct kretprobe_instance *ri, } /* Event entry printers */ -enum print_line_t +static enum print_line_t print_kprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event) { @@ -971,7 +998,7 @@ partial: return TRACE_TYPE_PARTIAL_LINE; } -enum print_line_t +static enum print_line_t print_kretprobe_event(struct trace_iterator *iter, int flags, struct trace_event *event) { diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 55e2cf66967b..2901e3b88590 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -1159,7 +1159,7 @@ trace_selftest_startup_branch(struct tracer *trace, struct trace_array *tr) /* stop the tracing. */ tracing_stop(); /* check the trace buffer */ - ret = trace_test_buffer(tr, &count); + ret = trace_test_buffer(&tr->trace_buffer, &count); trace->reset(tr); tracing_start(); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 4aa9f5bc6b2d..ee8e29a2320c 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -296,7 +296,7 @@ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER); static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; struct workqueue_struct *system_wq __read_mostly; -EXPORT_SYMBOL_GPL(system_wq); +EXPORT_SYMBOL(system_wq); struct workqueue_struct *system_highpri_wq __read_mostly; EXPORT_SYMBOL_GPL(system_highpri_wq); struct workqueue_struct *system_long_wq __read_mostly; @@ -1411,7 +1411,7 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq, local_irq_restore(flags); return ret; } -EXPORT_SYMBOL_GPL(queue_work_on); +EXPORT_SYMBOL(queue_work_on); void delayed_work_timer_fn(unsigned long __data) { @@ -1485,7 +1485,7 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, local_irq_restore(flags); return ret; } -EXPORT_SYMBOL_GPL(queue_delayed_work_on); +EXPORT_SYMBOL(queue_delayed_work_on); /** * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU @@ -2059,6 +2059,7 @@ static bool manage_workers(struct worker *worker) if (unlikely(!mutex_trylock(&pool->manager_mutex))) { spin_unlock_irq(&pool->lock); mutex_lock(&pool->manager_mutex); + spin_lock_irq(&pool->lock); ret = true; } @@ -4311,6 +4312,12 @@ bool current_is_workqueue_rescuer(void) * no synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * + * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU. + * Note that both per-cpu and unbound workqueues may be associated with + * multiple pool_workqueues which have separate congested states. A + * workqueue being congested on one CPU doesn't mean the workqueue is also + * contested on other CPUs / NUMA nodes. + * * RETURNS: * %true if congested, %false otherwise. */ @@ -4321,6 +4328,9 @@ bool workqueue_congested(int cpu, struct workqueue_struct *wq) rcu_read_lock_sched(); + if (cpu == WORK_CPU_UNBOUND) + cpu = smp_processor_id(); + if (!(wq->flags & WQ_UNBOUND)) pwq = per_cpu_ptr(wq->cpu_pwqs, cpu); else @@ -4895,7 +4905,8 @@ static void __init wq_numa_init(void) BUG_ON(!tbl); for_each_node(node) - BUG_ON(!alloc_cpumask_var_node(&tbl[node], GFP_KERNEL, node)); + BUG_ON(!alloc_cpumask_var_node(&tbl[node], GFP_KERNEL, + node_online(node) ? node : NUMA_NO_NODE)); for_each_possible_cpu(cpu) { node = cpu_to_node(cpu); |