diff options
Diffstat (limited to 'kernel')
35 files changed, 586 insertions, 228 deletions
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index f6b4ac7..7d9731d 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -614,9 +614,9 @@ void audit_trim_trees(void) } spin_unlock(&hash_lock); trim_marked(tree); - put_tree(tree); drop_collected_mounts(root_mnt); skip_it: + put_tree(tree); mutex_lock(&audit_filter_mutex); } list_del(&cursor); diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 3948f0a..e4f8595 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -366,10 +366,19 @@ static void free_css_set_work(struct work_struct *work) struct cgroup *cgrp = link->cgrp; list_del(&link->cg_link_list); list_del(&link->cgrp_link_list); + + /* + * We may not be holding cgroup_mutex, and if cgrp->count is + * dropped to 0 the cgroup can be destroyed at any time, hence + * rcu_read_lock is used to keep it alive. + */ + rcu_read_lock(); if (atomic_dec_and_test(&cgrp->count)) { check_for_release(cgrp); cgroup_wakeup_rmdir_waiter(cgrp); } + rcu_read_unlock(); + kfree(link); } write_unlock(&css_set_lock); @@ -2028,7 +2037,7 @@ int cgroup_attach_proc(struct cgroup *cgrp, struct task_struct *leader) if (!group) return -ENOMEM; /* pre-allocate to guarantee space while iterating in rcu read-side. */ - retval = flex_array_prealloc(group, 0, group_size - 1, GFP_KERNEL); + retval = flex_array_prealloc(group, 0, group_size, GFP_KERNEL); if (retval) goto out_free_group_list; @@ -3525,6 +3534,7 @@ static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft, const char *buffer) { struct cgroup_event *event = NULL; + struct cgroup *cgrp_cfile; unsigned int efd, cfd; struct file *efile = NULL; struct file *cfile = NULL; @@ -3579,6 +3589,16 @@ static int cgroup_write_event_control(struct cgroup *cgrp, struct cftype *cft, goto fail; } + /* + * The file to be monitored must be in the same cgroup as + * cgroup.event_control is. + */ + cgrp_cfile = __d_cgrp(cfile->f_dentry->d_parent); + if (cgrp_cfile != cgrp) { + ret = -EINVAL; + goto fail; + } + if (!event->cft->register_event || !event->cft->unregister_event) { ret = -EINVAL; goto fail; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 6cbe033..ea76c9c 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2499,8 +2499,16 @@ void cpuset_print_task_mems_allowed(struct task_struct *tsk) dentry = task_cs(tsk)->css.cgroup->dentry; spin_lock(&cpuset_buffer_lock); - snprintf(cpuset_name, CPUSET_NAME_LEN, - dentry ? (const char *)dentry->d_name.name : "/"); + + if (!dentry) { + strcpy(cpuset_name, "/"); + } else { + spin_lock(&dentry->d_lock); + strlcpy(cpuset_name, (const char *)dentry->d_name.name, + CPUSET_NAME_LEN); + spin_unlock(&dentry->d_lock); + } + nodelist_scnprintf(cpuset_nodelist, CPUSET_NODELIST_LEN, tsk->mems_allowed); printk(KERN_INFO "%s cpuset=%s mems_allowed=%s\n", diff --git a/kernel/events/core.c b/kernel/events/core.c index b582650..acdc087 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -223,9 +223,9 @@ perf_cgroup_match(struct perf_event *event) return !event->cgrp || event->cgrp == cpuctx->cgrp; } -static inline void perf_get_cgroup(struct perf_event *event) +static inline bool perf_tryget_cgroup(struct perf_event *event) { - css_get(&event->cgrp->css); + return css_tryget(&event->cgrp->css); } static inline void perf_put_cgroup(struct perf_event *event) @@ -342,6 +342,8 @@ void perf_cgroup_switch(struct task_struct *task, int mode) list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); + if (cpuctx->unique_pmu != pmu) + continue; /* ensure we process each cpuctx once */ perf_pmu_disable(cpuctx->ctx.pmu); @@ -365,9 +367,10 @@ void perf_cgroup_switch(struct task_struct *task, int mode) if (mode & PERF_CGROUP_SWIN) { WARN_ON_ONCE(cpuctx->cgrp); - /* set cgrp before ctxsw in to - * allow event_filter_match() to not - * have to pass task around + /* + * set cgrp before ctxsw in to allow + * event_filter_match() to not have to pass + * task around */ cpuctx->cgrp = perf_cgroup_from_task(task); cpu_ctx_sched_in(cpuctx, EVENT_ALL, task); @@ -415,7 +418,11 @@ static inline int perf_cgroup_connect(int fd, struct perf_event *event, event->cgrp = cgrp; /* must be done before we fput() the file */ - perf_get_cgroup(event); + if (!perf_tryget_cgroup(event)) { + event->cgrp = NULL; + ret = -ENOENT; + goto out; + } /* * all events in a group must monitor @@ -651,8 +658,18 @@ perf_lock_task_context(struct task_struct *task, int ctxn, unsigned long *flags) { struct perf_event_context *ctx; - rcu_read_lock(); retry: + /* + * One of the few rules of preemptible RCU is that one cannot do + * rcu_read_unlock() while holding a scheduler (or nested) lock when + * part of the read side critical section was preemptible -- see + * rcu_read_unlock_special(). + * + * Since ctx->lock nests under rq->lock we must ensure the entire read + * side critical section is non-preemptible. + */ + preempt_disable(); + rcu_read_lock(); ctx = rcu_dereference(task->perf_event_ctxp[ctxn]); if (ctx) { /* @@ -668,6 +685,8 @@ retry: raw_spin_lock_irqsave(&ctx->lock, *flags); if (ctx != rcu_dereference(task->perf_event_ctxp[ctxn])) { raw_spin_unlock_irqrestore(&ctx->lock, *flags); + rcu_read_unlock(); + preempt_enable(); goto retry; } @@ -677,6 +696,7 @@ retry: } } rcu_read_unlock(); + preempt_enable(); return ctx; } @@ -826,6 +846,15 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx) } /* + * Initialize event state based on the perf_event_attr::disabled. + */ +static inline void perf_event__state_init(struct perf_event *event) +{ + event->state = event->attr.disabled ? PERF_EVENT_STATE_OFF : + PERF_EVENT_STATE_INACTIVE; +} + +/* * Called at perf_event creation and when events are attached/detached from a * group. */ @@ -1616,7 +1645,16 @@ static int __perf_event_enable(void *info) struct perf_cpu_context *cpuctx = __get_cpu_context(ctx); int err; - if (WARN_ON_ONCE(!ctx->is_active)) + /* + * There's a time window between 'ctx->is_active' check + * in perf_event_enable function and this place having: + * - IRQs on + * - ctx->lock unlocked + * + * where the task could be killed and 'ctx' deactivated + * by perf_event_exit_task. + */ + if (!ctx->is_active) return -EINVAL; raw_spin_lock(&ctx->lock); @@ -4544,7 +4582,7 @@ static void perf_event_task_event(struct perf_task_event *task_event) rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); - if (cpuctx->active_pmu != pmu) + if (cpuctx->unique_pmu != pmu) goto next; perf_event_task_ctx(&cpuctx->ctx, task_event); @@ -4690,7 +4728,7 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event) rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); - if (cpuctx->active_pmu != pmu) + if (cpuctx->unique_pmu != pmu) goto next; perf_event_comm_ctx(&cpuctx->ctx, comm_event); @@ -4886,7 +4924,7 @@ got_name: rcu_read_lock(); list_for_each_entry_rcu(pmu, &pmus, entry) { cpuctx = get_cpu_ptr(pmu->pmu_cpu_context); - if (cpuctx->active_pmu != pmu) + if (cpuctx->unique_pmu != pmu) goto next; perf_event_mmap_ctx(&cpuctx->ctx, mmap_event, vma->vm_flags & VM_EXEC); @@ -5912,8 +5950,8 @@ static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu) cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); - if (cpuctx->active_pmu == old_pmu) - cpuctx->active_pmu = pmu; + if (cpuctx->unique_pmu == old_pmu) + cpuctx->unique_pmu = pmu; } } @@ -6045,7 +6083,7 @@ skip_type: cpuctx->ctx.pmu = pmu; cpuctx->jiffies_interval = 1; INIT_LIST_HEAD(&cpuctx->rotation_list); - cpuctx->active_pmu = pmu; + cpuctx->unique_pmu = pmu; } got_cpu_context: @@ -6219,8 +6257,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu, event->overflow_handler = overflow_handler; - if (attr->disabled) - event->state = PERF_EVENT_STATE_OFF; + perf_event__state_init(event); pmu = NULL; @@ -6594,9 +6631,17 @@ SYSCALL_DEFINE5(perf_event_open, mutex_lock(&gctx->mutex); perf_remove_from_context(group_leader); + + /* + * Removing from the context ends up with disabled + * event. What we want here is event in the initial + * startup state, ready to be add into new context. + */ + perf_event__state_init(group_leader); list_for_each_entry(sibling, &group_leader->sibling_list, group_entry) { perf_remove_from_context(sibling); + perf_event__state_init(sibling); put_ctx(gctx); } mutex_unlock(&gctx->mutex); @@ -7064,7 +7109,7 @@ inherit_task_group(struct perf_event *event, struct task_struct *parent, * child. */ - child_ctx = alloc_perf_context(event->pmu, child); + child_ctx = alloc_perf_context(parent_ctx->pmu, child); if (!child_ctx) return -ENOMEM; diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c index 086adf2..d99cb4b 100644 --- a/kernel/events/hw_breakpoint.c +++ b/kernel/events/hw_breakpoint.c @@ -147,7 +147,7 @@ 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); @@ -233,7 +233,7 @@ 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/futex.c b/kernel/futex.c index ec372fd..c7c19cb 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -60,6 +60,7 @@ #include <linux/pid.h> #include <linux/nsproxy.h> #include <linux/ptrace.h> +#include <linux/hugetlb.h> #include <asm/futex.h> @@ -363,7 +364,7 @@ again: } else { key->both.offset |= FUT_OFF_INODE; /* inode-based key */ key->shared.inode = page_head->mapping->host; - key->shared.pgoff = page_head->index; + key->shared.pgoff = basepage_index(page); } get_futex_key_refs(key); diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 65a3195..4407e3e 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -62,6 +62,7 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = { + .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock), .clock_base = { { @@ -298,6 +299,10 @@ ktime_t ktime_sub_ns(const ktime_t kt, u64 nsec) } else { unsigned long rem = do_div(nsec, NSEC_PER_SEC); + /* Make sure nsec fits into long */ + if (unlikely(nsec > KTIME_SEC_MAX)) + return (ktime_t){ .tv64 = KTIME_MAX }; + tmp = ktime_set((long)nsec, rem); } @@ -641,21 +646,9 @@ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) * and expiry check is done in the hrtimer_interrupt or in the softirq. */ static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, - struct hrtimer_clock_base *base, - int wakeup) + struct hrtimer_clock_base *base) { - if (base->cpu_base->hres_active && hrtimer_reprogram(timer, base)) { - if (wakeup) { - raw_spin_unlock(&base->cpu_base->lock); - raise_softirq_irqoff(HRTIMER_SOFTIRQ); - raw_spin_lock(&base->cpu_base->lock); - } else - __raise_softirq_irqoff(HRTIMER_SOFTIRQ); - - return 1; - } - - return 0; + return base->cpu_base->hres_active && hrtimer_reprogram(timer, base); } static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) @@ -715,17 +708,20 @@ 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 @@ -736,8 +732,7 @@ static inline int hrtimer_switch_to_hres(void) { return 0; } static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { } static inline int hrtimer_enqueue_reprogram(struct hrtimer *timer, - struct hrtimer_clock_base *base, - int wakeup) + struct hrtimer_clock_base *base) { return 0; } @@ -775,8 +770,10 @@ 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) @@ -996,8 +993,21 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, * * XXX send_remote_softirq() ? */ - if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)) - hrtimer_enqueue_reprogram(timer, new_base, wakeup); + if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases) + && hrtimer_enqueue_reprogram(timer, new_base)) { + if (wakeup) { + /* + * We need to drop cpu_base->lock to avoid a + * lock ordering issue vs. rq->lock. + */ + raw_spin_unlock(&new_base->cpu_base->lock); + raise_softirq_irqoff(HRTIMER_SOFTIRQ); + local_irq_restore(flags); + return ret; + } else { + __raise_softirq_irqoff(HRTIMER_SOFTIRQ); + } + } unlock_hrtimer_base(timer, &flags); @@ -1310,6 +1320,8 @@ retry: expires = ktime_sub(hrtimer_get_expires(timer), base->offset); + if (expires.tv64 < 0) + expires.tv64 = KTIME_MAX; if (expires.tv64 < expires_next.tv64) expires_next = expires; break; @@ -1412,13 +1424,6 @@ 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(); } @@ -1643,8 +1648,6 @@ static void __cpuinit init_hrtimers_cpu(int cpu) struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); int i; - raw_spin_lock_init(&cpu_base->lock); - for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { cpu_base->clock_base[i].cpu_base = cpu_base; timerqueue_init_head(&cpu_base->clock_base[i].active); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 3e1bdf9..2f61278 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -536,9 +536,9 @@ int can_request_irq(unsigned int irq, unsigned long irqflags) return 0; if (irq_settings_can_request(desc)) { - if (desc->action) - if (irqflags & desc->action->flags & IRQF_SHARED) - canrequest =1; + if (!desc->action || + irqflags & desc->action->flags & IRQF_SHARED) + canrequest = 1; } irq_put_desc_unlock(desc, flags); return canrequest; diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c index dc813a9..63633a3 100644 --- a/kernel/irq/spurious.c +++ b/kernel/irq/spurious.c @@ -80,13 +80,11 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force) /* * All handlers must agree on IRQF_SHARED, so we test just the - * first. Check for action->next as well. + * first. */ action = desc->action; if (!action || !(action->flags & IRQF_SHARED) || - (action->flags & __IRQF_TIMER) || - (action->handler(irq, action->dev_id) == IRQ_HANDLED) || - !action->next) + (action->flags & __IRQF_TIMER)) goto out; /* Already running on another processor */ @@ -104,6 +102,7 @@ static int try_one_irq(int irq, struct irq_desc *desc, bool force) do { if (handle_irq_event(desc) == IRQ_HANDLED) ret = IRQ_HANDLED; + /* Make sure that there is still a valid action */ action = desc->action; } while ((desc->istate & IRQS_PENDING) && action); desc->istate &= ~IRQS_POLL_INPROGRESS; diff --git a/kernel/kmod.c b/kernel/kmod.c index fabfe54..f625b4f 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -421,6 +421,11 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, 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/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 640ded8..93d5e4a 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -1450,8 +1450,10 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, while (!signal_pending(current)) { if (timer.it.cpu.expires.sched == 0) { /* - * Our timer fired and was reset. + * Our timer fired and was reset, below + * deletion can not fail. */ + posix_cpu_timer_del(&timer); spin_unlock_irq(&timer.it_lock); return 0; } @@ -1469,9 +1471,26 @@ static int do_cpu_nanosleep(const clockid_t which_clock, int flags, * We were interrupted by a signal. */ sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp); - posix_cpu_timer_set(&timer, 0, &zero_it, it); + error = posix_cpu_timer_set(&timer, 0, &zero_it, it); + if (!error) { + /* + * Timer is now unarmed, deletion can not fail. + */ + posix_cpu_timer_del(&timer); + } spin_unlock_irq(&timer.it_lock); + while (error == TIMER_RETRY) { + /* + * We need to handle case when timer was or is in the + * middle of firing. In other cases we already freed + * resources. + */ + spin_lock_irq(&timer.it_lock); + error = posix_cpu_timer_del(&timer); + spin_unlock_irq(&timer.it_lock); + } + if ((it->it_value.tv_sec | it->it_value.tv_nsec) == 0) { /* * It actually did fire already. diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 4556182..d2da8ad 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -639,6 +639,13 @@ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags) { struct k_itimer *timr; + /* + * timer_t could be any type >= int and we want to make sure any + * @timer_id outside positive int range fails lookup. + */ + if ((unsigned long long)timer_id > INT_MAX) + return NULL; + rcu_read_lock(); timr = idr_find(&posix_timers_id, (int)timer_id); if (timr) { diff --git a/kernel/printk.c b/kernel/printk.c index 17b0c7a..d614ccd 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -684,8 +684,19 @@ static void call_console_drivers(unsigned start, unsigned end) start_print = start; while (cur_index != end) { if (msg_level < 0 && ((end - cur_index) > 2)) { + /* + * prepare buf_prefix, as a contiguous array, + * to be processed by log_prefix function + */ + char buf_prefix[SYSLOG_PRI_MAX_LENGTH+1]; + unsigned i; + for (i = 0; i < ((end - cur_index)) && (i < SYSLOG_PRI_MAX_LENGTH); i++) { + buf_prefix[i] = LOG_BUF(cur_index + i); + } + buf_prefix[i] = '\0'; /* force '\0' as last string character */ + /* strip log prefix */ - cur_index += log_prefix(&LOG_BUF(cur_index), &msg_level, NULL); + cur_index += log_prefix((const char *)&buf_prefix, &msg_level, NULL); start_print = cur_index; } while (cur_index != end) { diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 2df1157..40581ee 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -38,6 +38,36 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent) child->parent = new_parent; } +/* Ensure that nothing can wake it up, even SIGKILL */ +static bool ptrace_freeze_traced(struct task_struct *task) +{ + bool ret = false; + + spin_lock_irq(&task->sighand->siglock); + if (task_is_traced(task) && !__fatal_signal_pending(task)) { + task->state = __TASK_TRACED; + ret = true; + } + spin_unlock_irq(&task->sighand->siglock); + + return ret; +} + +static void ptrace_unfreeze_traced(struct task_struct *task) +{ + if (task->state != __TASK_TRACED) + return; + + WARN_ON(!task->ptrace || task->parent != current); + + spin_lock_irq(&task->sighand->siglock); + if (__fatal_signal_pending(task)) + wake_up_state(task, __TASK_TRACED); + else + task->state = TASK_TRACED; + spin_unlock_irq(&task->sighand->siglock); +} + /** * __ptrace_unlink - unlink ptracee and restore its execution state * @child: ptracee to be unlinked @@ -92,7 +122,7 @@ void __ptrace_unlink(struct task_struct *child) * TASK_KILLABLE sleeps. */ if (child->group_stop & GROUP_STOP_PENDING || task_is_traced(child)) - signal_wake_up(child, task_is_traced(child)); + ptrace_signal_wake_up(child, true); spin_unlock(&child->sighand->siglock); } @@ -112,23 +142,29 @@ int ptrace_check_attach(struct task_struct *child, int kill) * be changed by us so it's not changing right after this. */ read_lock(&tasklist_lock); - if ((child->ptrace & PT_PTRACED) && child->parent == current) { + if (child->ptrace && child->parent == current) { + WARN_ON(child->state == __TASK_TRACED); /* * child->sighand can't be NULL, release_task() * does ptrace_unlink() before __exit_signal(). */ - spin_lock_irq(&child->sighand->siglock); - WARN_ON_ONCE(task_is_stopped(child)); - if (task_is_traced(child) || kill) + if (kill || ptrace_freeze_traced(child)) ret = 0; - spin_unlock_irq(&child->sighand->siglock); } read_unlock(&tasklist_lock); - if (!ret && !kill) - ret = wait_task_inactive(child, TASK_TRACED) ? 0 : -ESRCH; + if (!ret && !kill) { + if (!wait_task_inactive(child, __TASK_TRACED)) { + /* + * This can only happen if may_ptrace_stop() fails and + * ptrace_stop() changes ->state back to TASK_RUNNING, + * so we should not worry about leaking __TASK_TRACED. + */ + WARN_ON(child->state == __TASK_TRACED); + ret = -ESRCH; + } + } - /* All systems go.. */ return ret; } @@ -245,7 +281,7 @@ static int ptrace_attach(struct task_struct *task) */ if (task_is_stopped(task)) { task->group_stop |= GROUP_STOP_PENDING | GROUP_STOP_TRAPPING; - signal_wake_up(task, 1); + signal_wake_up_state(task, __TASK_STOPPED); wait_trap = true; } @@ -777,6 +813,8 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, unsigned long, addr, goto out_put_task_struct; ret = arch_ptrace(child, request, addr, data); + if (ret || request != PTRACE_DETACH) + ptrace_unfreeze_traced(child); out_put_task_struct: put_task_struct(child); @@ -915,8 +953,11 @@ asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, } ret = ptrace_check_attach(child, request == PTRACE_KILL); - if (!ret) + if (!ret) { ret = compat_arch_ptrace(child, request, addr, data); + if (ret || request != PTRACE_DETACH) + ptrace_unfreeze_traced(child); + } out_put_task_struct: put_task_struct(child); diff --git a/kernel/relay.c b/kernel/relay.c index 2c242fb..a5be9af 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -1235,6 +1235,7 @@ static ssize_t subbuf_splice_actor(struct file *in, struct splice_pipe_desc spd = { .pages = pages, .nr_pages = 0, + .nr_pages_max = PIPE_DEF_BUFFERS, .partial = partial, .flags = flags, .ops = &relay_pipe_buf_ops, @@ -1302,8 +1303,8 @@ static ssize_t subbuf_splice_actor(struct file *in, ret += padding; out: - splice_shrink_spd(pipe, &spd); - return ret; + splice_shrink_spd(&spd); + return ret; } static ssize_t relay_file_splice_read(struct file *in, diff --git a/kernel/sched.c b/kernel/sched.c index e0c9d50..0b0d3dc 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2746,8 +2746,10 @@ static void try_to_wake_up_local(struct task_struct *p) { struct rq *rq = task_rq(p); - BUG_ON(rq != this_rq()); - BUG_ON(p == current); + if (WARN_ON_ONCE(rq != this_rq()) || + WARN_ON_ONCE(p == current)) + return; + lockdep_assert_held(&rq->lock); if (!raw_spin_trylock(&p->pi_lock)) { @@ -2781,7 +2783,8 @@ out: */ int wake_up_process(struct task_struct *p) { - return try_to_wake_up(p, TASK_ALL, 0); + WARN_ON(task_is_stopped_or_traced(p)); + return try_to_wake_up(p, TASK_NORMAL, 0); } EXPORT_SYMBOL(wake_up_process); diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c index a4cc338..e17ec39 100644 --- a/kernel/sched_clock.c +++ b/kernel/sched_clock.c @@ -164,10 +164,36 @@ static u64 sched_clock_remote(struct sched_clock_data *scd) u64 this_clock, remote_clock; u64 *ptr, old_val, val; +#if BITS_PER_LONG != 64 +again: + /* + * Careful here: The local and the remote clock values need to + * be read out atomic as we need to compare the values and + * then update either the local or the remote side. So the + * cmpxchg64 below only protects one readout. + * + * We must reread via sched_clock_local() in the retry case on + * 32bit as an NMI could use sched_clock_local() via the + * tracer and hit between the readout of + * the low32bit and the high 32bit portion. + */ + this_clock = sched_clock_local(my_scd); + /* + * We must enforce atomic readout on 32bit, otherwise the + * update on the remote cpu can hit inbetween the readout of + * the low32bit and the high 32bit portion. + */ + remote_clock = cmpxchg64(&scd->clock, 0, 0); +#else + /* + * On 64bit the read of [my]scd->clock is atomic versus the + * update, so we can avoid the above 32bit dance. + */ sched_clock_local(my_scd); again: this_clock = my_scd->clock; remote_clock = scd->clock; +#endif /* * Use the opportunity that we have both locks diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index c768588..fae7d67 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -4277,7 +4277,7 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task * idle runqueue: */ if (rq->cfs.load.weight) - rr_interval = NS_TO_JIFFIES(sched_slice(&rq->cfs, se)); + rr_interval = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se)); return rr_interval; } diff --git a/kernel/signal.c b/kernel/signal.c index 81ff97a..f15021b 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -437,7 +437,7 @@ flush_signal_handlers(struct task_struct *t, int force_default) if (force_default || ka->sa.sa_handler != SIG_IGN) ka->sa.sa_handler = SIG_DFL; ka->sa.sa_flags = 0; -#ifdef SA_RESTORER +#ifdef __ARCH_HAS_SA_RESTORER ka->sa.sa_restorer = NULL; #endif sigemptyset(&ka->sa.sa_mask); @@ -634,23 +634,17 @@ int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info) * No need to set need_resched since signal event passing * goes through ->blocked */ -void signal_wake_up(struct task_struct *t, int resume) +void signal_wake_up_state(struct task_struct *t, unsigned int state) { - unsigned int mask; - set_tsk_thread_flag(t, TIF_SIGPENDING); - /* - * For SIGKILL, we want to wake it up in the stopped/traced/killable + * TASK_WAKEKILL also means wake it up in the stopped/traced/killable * case. We don't check t->state here because there is a race with it * executing another processor and just now entering stopped state. * By using wake_up_state, we ensure the process will wake up and * handle its death signal. */ - mask = TASK_INTERRUPTIBLE; - if (resume) - mask |= TASK_WAKEKILL; - if (!wake_up_state(t, mask)) + if (!wake_up_state(t, state | TASK_INTERRUPTIBLE)) kick_process(t); } @@ -1678,6 +1672,10 @@ static inline int may_ptrace_stop(void) * If SIGKILL was already sent before the caller unlocked * ->siglock we must see ->core_state != NULL. Otherwise it * is safe to enter schedule(). + * + * This is almost outdated, a task with the pending SIGKILL can't + * block in TASK_TRACED. But PTRACE_EVENT_EXIT can be reported + * after SIGKILL was already dequeued. */ if (unlikely(current->mm->core_state) && unlikely(current->mm == current->parent->mm)) @@ -1809,6 +1807,7 @@ static void ptrace_stop(int exit_code, int why, int clear_code, siginfo_t *info) if (gstop_done) do_notify_parent_cldstop(current, false, why); + /* tasklist protects us from ptrace_freeze_traced() */ __set_current_state(TASK_RUNNING); if (clear_code) current->exit_code = 0; @@ -2665,7 +2664,7 @@ do_send_specific(pid_t tgid, pid_t pid, int sig, struct siginfo *info) static int do_tkill(pid_t tgid, pid_t pid, int sig) { - struct siginfo info; + struct siginfo info = {}; info.si_signo = sig; info.si_errno = 0; diff --git a/kernel/sys.c b/kernel/sys.c index a04708d..be53817 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -320,7 +320,6 @@ void kernel_restart_prepare(char *cmd) system_state = SYSTEM_RESTART; usermodehelper_disable(); device_shutdown(); - syscore_shutdown(); } /** @@ -365,6 +364,7 @@ static void kernel_shutdown_prepare(enum system_states state) void kernel_halt(void) { kernel_shutdown_prepare(SYSTEM_HALT); + disable_nonboot_cpus(); syscore_shutdown(); printk(KERN_EMERG "System halted.\n"); kmsg_dump(KMSG_DUMP_HALT); diff --git a/kernel/sysctl_binary.c b/kernel/sysctl_binary.c index e055e8b..17c20c7 100644 --- a/kernel/sysctl_binary.c +++ b/kernel/sysctl_binary.c @@ -1194,9 +1194,10 @@ static ssize_t bin_dn_node_address(struct file *file, /* Convert the decnet address to binary */ result = -EIO; - nodep = strchr(buf, '.') + 1; + nodep = strchr(buf, '.'); if (!nodep) goto out; + ++nodep; area = simple_strtoul(buf, NULL, 10); node = simple_strtoul(nodep, NULL, 10); diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 7a90d02..20ba7b4 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -66,12 +66,17 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc) */ int tick_check_broadcast_device(struct clock_event_device *dev) { - if ((tick_broadcast_device.evtdev && + 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; clockevents_exchange_device(tick_broadcast_device.evtdev, dev); + if (cur) + cur->event_handler = clockevents_handle_noop; tick_broadcast_device.evtdev = dev; if (!cpumask_empty(tick_get_broadcast_mask())) tick_broadcast_start_periodic(dev); @@ -391,7 +396,15 @@ void tick_check_oneshot_broadcast(int cpu) if (cpumask_test_cpu(cpu, to_cpumask(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); + } } } diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 119528d..c43b479 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -323,6 +323,7 @@ static void tick_shutdown(unsigned int *cpup) */ dev->mode = CLOCK_EVT_MODE_UNUSED; clockevents_exchange_device(dev, NULL); + dev->event_handler = clockevents_handle_noop; td->evtdev = NULL; } raw_spin_unlock_irqrestore(&tick_device_lock, flags); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index c473ce2..c0be5f2 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -811,7 +811,7 @@ 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/timer.c b/kernel/timer.c index 27982d9..5eac0d8 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -145,9 +145,11 @@ 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; } /** @@ -1630,12 +1632,12 @@ 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/Kconfig b/kernel/trace/Kconfig index 2ad39e5..57c92f2 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -386,24 +386,28 @@ config KPROBE_EVENT If you want to use perf tools, this option is strongly recommended. config DYNAMIC_FTRACE - bool "enable/disable ftrace tracepoints dynamically" + bool "enable/disable function tracing dynamically" depends on FUNCTION_TRACER depends on HAVE_DYNAMIC_FTRACE default y help - This option will modify all the calls to ftrace dynamically - (will patch them out of the binary image and replace them - with a No-Op instruction) as they are called. A table is - created to dynamically enable them again. + This option will modify all the calls to function tracing + dynamically (will patch them out of the binary image and + replace them with a No-Op instruction) on boot up. During + compile time, a table is made of all the locations that ftrace + can function trace, and this table is linked into the kernel + image. When this is enabled, functions can be individually + enabled, and the functions not enabled will not affect + performance of the system. + + See the files in /sys/kernel/debug/tracing: + available_filter_functions + set_ftrace_filter + set_ftrace_notrace This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but otherwise has native performance as long as no tracing is active. - The changes to the code are done by a kernel thread that - wakes up once a second and checks to see if any ftrace calls - were made. If so, it runs stop_machine (stops all CPUS) - and modifies the code to jump over the call to ftrace. - config FUNCTION_PROFILER bool "Kernel function profiler" depends on FUNCTION_TRACER diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index e96eee3..0d704b0 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -548,7 +548,7 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat) pages = DIV_ROUND_UP(functions, PROFILES_PER_PAGE); - for (i = 0; i < pages; i++) { + for (i = 1; i < pages; i++) { pg->next = (void *)get_zeroed_page(GFP_KERNEL); if (!pg->next) goto out_free; @@ -566,7 +566,6 @@ int ftrace_profile_pages_init(struct ftrace_profile_stat *stat) free_page(tmp); } - free_page((unsigned long)stat->pages); stat->pages = NULL; stat->start = NULL; @@ -934,6 +933,19 @@ static __init void ftrace_profile_debugfs(struct dentry *d_tracer) static struct pid * const ftrace_swapper_pid = &init_struct_pid; +static loff_t +ftrace_filter_lseek(struct file *file, loff_t offset, int whence) +{ + loff_t ret; + + if (file->f_mode & FMODE_READ) + ret = seq_lseek(file, offset, whence); + else + file->f_pos = ret = 1; + + return ret; +} + #ifdef CONFIG_DYNAMIC_FTRACE #ifndef CONFIG_FTRACE_MCOUNT_RECORD @@ -2300,19 +2312,6 @@ ftrace_notrace_open(struct inode *inode, struct file *file) inode, file); } -static loff_t -ftrace_regex_lseek(struct file *file, loff_t offset, int origin) -{ - loff_t ret; - - if (file->f_mode & FMODE_READ) - ret = seq_lseek(file, offset, origin); - else - file->f_pos = ret = 1; - - return ret; -} - static int ftrace_match(char *str, char *regex, int len, int type) { int matched = 0; @@ -2709,8 +2708,8 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, continue; } - hlist_del(&entry->node); - call_rcu(&entry->rcu, ftrace_free_entry_rcu); + hlist_del_rcu(&entry->node); + call_rcu_sched(&entry->rcu, ftrace_free_entry_rcu); } } __disable_ftrace_function_probe(); @@ -3119,7 +3118,7 @@ static const struct file_operations ftrace_filter_fops = { .open = ftrace_filter_open, .read = seq_read, .write = ftrace_filter_write, - .llseek = ftrace_regex_lseek, + .llseek = ftrace_filter_lseek, .release = ftrace_regex_release, }; @@ -3127,7 +3126,7 @@ static const struct file_operations ftrace_notrace_fops = { .open = ftrace_notrace_open, .read = seq_read, .write = ftrace_notrace_write, - .llseek = ftrace_regex_lseek, + .llseek = ftrace_filter_lseek, .release = ftrace_regex_release, }; @@ -3288,7 +3287,8 @@ out: if (fail) return -EINVAL; - ftrace_graph_filter_enabled = 1; + ftrace_graph_filter_enabled = !!(*idx); + return 0; } @@ -3335,8 +3335,8 @@ static const struct file_operations ftrace_graph_fops = { .open = ftrace_graph_open, .read = seq_read, .write = ftrace_graph_write, + .llseek = ftrace_filter_lseek, .release = ftrace_graph_release, - .llseek = seq_lseek, }; #endif /* CONFIG_FUNCTION_GRAPH_TRACER */ @@ -3432,37 +3432,51 @@ static void ftrace_init_module(struct module *mod, ftrace_process_locs(mod, start, end); } -static int ftrace_module_notify(struct notifier_block *self, - unsigned long val, void *data) +static int ftrace_module_notify_enter(struct notifier_block *self, + unsigned long val, void *data) { struct module *mod = data; - switch (val) { - case MODULE_STATE_COMING: + if (val == MODULE_STATE_COMING) ftrace_init_module(mod, mod->ftrace_callsites, mod->ftrace_callsites + mod->num_ftrace_callsites); - break; - case MODULE_STATE_GOING: + return 0; +} + +static int ftrace_module_notify_exit(struct notifier_block *self, + unsigned long val, void *data) +{ + struct module *mod = data; + + if (val == MODULE_STATE_GOING) ftrace_release_mod(mod); - break; - } return 0; } #else -static int ftrace_module_notify(struct notifier_block *self, - unsigned long val, void *data) +static int ftrace_module_notify_enter(struct notifier_block *self, + unsigned long val, void *data) +{ + return 0; +} +static int ftrace_module_notify_exit(struct notifier_block *self, + unsigned long val, void *data) { return 0; } #endif /* CONFIG_MODULES */ -struct notifier_block ftrace_module_nb = { - .notifier_call = ftrace_module_notify, +struct notifier_block ftrace_module_enter_nb = { + .notifier_call = ftrace_module_notify_enter, .priority = INT_MAX, /* Run before anything that can use kprobes */ }; +struct notifier_block ftrace_module_exit_nb = { + .notifier_call = ftrace_module_notify_exit, + .priority = INT_MIN, /* Run after anything that can remove kprobes */ +}; + extern unsigned long __start_mcount_loc[]; extern unsigned long __stop_mcount_loc[]; @@ -3494,9 +3508,13 @@ void __init ftrace_init(void) __start_mcount_loc, __stop_mcount_loc); - ret = register_module_notifier(&ftrace_module_nb); + ret = register_module_notifier(&ftrace_module_enter_nb); + if (ret) + pr_warning("Failed to register trace ftrace module enter notifier\n"); + + ret = register_module_notifier(&ftrace_module_exit_nb); if (ret) - pr_warning("Failed to register trace ftrace module notifier\n"); + pr_warning("Failed to register trace ftrace module exit notifier\n"); set_ftrace_early_filters(); @@ -3804,7 +3822,7 @@ static const struct file_operations ftrace_pid_fops = { .open = ftrace_pid_open, .write = ftrace_pid_write, .read = seq_read, - .llseek = seq_lseek, + .llseek = ftrace_filter_lseek, .release = ftrace_pid_release, }; @@ -3916,12 +3934,8 @@ ftrace_enable_sysctl(struct ctl_table *table, int write, ftrace_startup_sysctl(); /* we are starting ftrace again */ - if (ftrace_ops_list != &ftrace_list_end) { - if (ftrace_ops_list->next == &ftrace_list_end) - ftrace_trace_function = ftrace_ops_list->func; - else - ftrace_trace_function = ftrace_ops_list_func; - } + if (ftrace_ops_list != &ftrace_list_end) + update_ftrace_function(); } else { /* stopping ftrace calls (just send to ftrace_stub) */ diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 672a749..34d15ba 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -628,7 +628,15 @@ __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; @@ -649,7 +657,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { - struct ring_buffer *buf = tr->buffer; + struct ring_buffer *buf; if (trace_stop_count) return; @@ -661,6 +669,7 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) } arch_spin_lock(&ftrace_max_lock); + buf = tr->buffer; tr->buffer = max_tr.buffer; max_tr.buffer = buf; @@ -2526,11 +2535,25 @@ static int set_tracer_option(struct tracer *trace, char *cmp, int neg) return -EINVAL; } -static void set_tracer_flags(unsigned int mask, int enabled) +/* Some tracers require overwrite to stay enabled */ +int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) +{ + if (tracer->enabled && (mask & TRACE_ITER_OVERWRITE) && !set) + return -1; + + return 0; +} + +int set_tracer_flag(unsigned int mask, int enabled) { /* do nothing if flag is already set */ if (!!(trace_flags & mask) == !!enabled) - return; + return 0; + + /* Give the tracer a chance to approve the change */ + if (current_trace->flag_changed) + if (current_trace->flag_changed(current_trace, mask, !!enabled)) + return -EINVAL; if (enabled) trace_flags |= mask; @@ -2542,6 +2565,8 @@ static void set_tracer_flags(unsigned int mask, int enabled) if (mask == TRACE_ITER_OVERWRITE) ring_buffer_change_overwrite(global_trace.buffer, enabled); + + return 0; } static ssize_t @@ -2551,7 +2576,7 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf, char buf[64]; char *cmp; int neg = 0; - int ret; + int ret = -ENODEV; int i; if (cnt >= sizeof(buf)) @@ -2568,21 +2593,23 @@ tracing_trace_options_write(struct file *filp, const char __user *ubuf, cmp += 2; } + mutex_lock(&trace_types_lock); + for (i = 0; trace_options[i]; i++) { if (strcmp(cmp, trace_options[i]) == 0) { - set_tracer_flags(1 << i, !neg); + ret = set_tracer_flag(1 << i, !neg); break; } } /* If no option could be set, test the specific tracer options */ - if (!trace_options[i]) { - mutex_lock(&trace_types_lock); + if (!trace_options[i]) ret = set_tracer_option(current_trace, cmp, neg); - mutex_unlock(&trace_types_lock); - if (ret) - return ret; - } + + mutex_unlock(&trace_types_lock); + + if (ret < 0) + return ret; *ppos += cnt; @@ -2880,6 +2907,9 @@ static int tracing_set_tracer(const char *buf) goto out; trace_branch_disable(); + + current_trace->enabled = false; + if (current_trace && current_trace->reset) current_trace->reset(tr); if (current_trace && current_trace->use_max_tr) { @@ -2909,6 +2939,7 @@ static int tracing_set_tracer(const char *buf) goto out; } + current_trace->enabled = true; trace_branch_enable(tr); out: mutex_unlock(&trace_types_lock); @@ -3214,6 +3245,7 @@ waitagain: memset(&iter->seq, 0, sizeof(struct trace_iterator) - offsetof(struct trace_iterator, seq)); + cpumask_clear(iter->started); iter->pos = -1; trace_event_read_lock(); @@ -3332,6 +3364,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, .pages = pages_def, .partial = partial_def, .nr_pages = 0, /* This gets updated below. */ + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &tracing_pipe_buf_ops, .spd_release = tracing_spd_release_pipe, @@ -3403,7 +3436,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, ret = splice_to_pipe(pipe, &spd); out: - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return ret; out_err: @@ -3816,6 +3849,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages_def, .partial = partial_def, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &buffer_pipe_buf_ops, .spd_release = buffer_spd_release, @@ -3904,7 +3938,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, } ret = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); out: return ret; } @@ -4179,7 +4213,13 @@ trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, if (val != 0 && val != 1) return -EINVAL; - set_tracer_flags(1 << index, val); + + mutex_lock(&trace_types_lock); + ret = set_tracer_flag(1 << index, val); + mutex_unlock(&trace_types_lock); + + if (ret < 0) + return ret; *ppos += cnt; @@ -4331,6 +4371,8 @@ static __init int tracer_init_debugfs(void) trace_access_lock_init(); d_tracer = tracing_init_dentry(); + if (!d_tracer) + return 0; trace_create_file("tracing_enabled", 0644, d_tracer, &global_trace, &tracing_ctrl_fops); @@ -4458,30 +4500,32 @@ void trace_init_global_iter(struct trace_iterator *iter) iter->cpu_file = TRACE_PIPE_ALL_CPU; } -static void -__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) +void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { - static arch_spinlock_t ftrace_dump_lock = - (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; /* use static because iter can be a bit big for the stack */ static struct trace_iterator iter; + static atomic_t dump_running; unsigned int old_userobj; - static int dump_ran; unsigned long flags; int cnt = 0, cpu; - /* only one dump */ - local_irq_save(flags); - arch_spin_lock(&ftrace_dump_lock); - if (dump_ran) - goto out; - - dump_ran = 1; + /* Only allow one dump user at a time. */ + if (atomic_inc_return(&dump_running) != 1) { + atomic_dec(&dump_running); + return; + } + /* + * Always turn off tracing when we dump. + * We don't need to show trace output of what happens + * between multiple crashes. + * + * If the user does a sysrq-z, then they can re-enable + * tracing with echo 1 > tracing_on. + */ tracing_off(); - if (disable_tracing) - ftrace_kill(); + local_irq_save(flags); trace_init_global_iter(&iter); @@ -4552,26 +4596,15 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode) printk(KERN_TRACE "---------------------------------\n"); out_enable: - /* Re-enable tracing if requested */ - if (!disable_tracing) { - trace_flags |= old_userobj; + trace_flags |= old_userobj; - for_each_tracing_cpu(cpu) { - atomic_dec(&iter.tr->data[cpu]->disabled); - } - tracing_on(); + for_each_tracing_cpu(cpu) { + atomic_dec(&iter.tr->data[cpu]->disabled); } - - out: - arch_spin_unlock(&ftrace_dump_lock); + atomic_dec(&dump_running); local_irq_restore(flags); } - -/* By default: disable tracing after the dump */ -void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) -{ - __ftrace_dump(true, oops_dump_mode); -} +EXPORT_SYMBOL_GPL(ftrace_dump); __init static int tracer_alloc_buffers(void) { diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index f807407..123ee28 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -271,10 +271,14 @@ struct tracer { enum print_line_t (*print_line)(struct trace_iterator *iter); /* If you handled the flag setting, return 0 */ int (*set_flag)(u32 old_flags, u32 bit, int set); + /* Return 0 if OK with change, else return non-zero */ + int (*flag_changed)(struct tracer *tracer, + u32 mask, int set); struct tracer *next; struct tracer_flags *flags; int print_max; int use_max_tr; + bool enabled; }; @@ -776,6 +780,9 @@ extern struct list_head ftrace_events; extern const char *__start___trace_bprintk_fmt[]; extern const char *__stop___trace_bprintk_fmt[]; +int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set); +int set_tracer_flag(unsigned int mask, int enabled); + #undef FTRACE_ENTRY #define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \ extern struct ftrace_event_call \ diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c index c77424b..984aad8 100644 --- a/kernel/trace/trace_irqsoff.c +++ b/kernel/trace/trace_irqsoff.c @@ -32,7 +32,7 @@ enum { static int trace_type __read_mostly; -static int save_lat_flag; +static int save_flags; static void stop_irqsoff_tracer(struct trace_array *tr, int graph); static int start_irqsoff_tracer(struct trace_array *tr, int graph); @@ -544,8 +544,11 @@ static void stop_irqsoff_tracer(struct trace_array *tr, int graph) static void __irqsoff_tracer_init(struct trace_array *tr) { - save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT; - trace_flags |= TRACE_ITER_LATENCY_FMT; + save_flags = trace_flags; + + /* non overwrite screws up the latency tracers */ + set_tracer_flag(TRACE_ITER_OVERWRITE, 1); + set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1); tracing_max_latency = 0; irqsoff_trace = tr; @@ -559,10 +562,13 @@ static void __irqsoff_tracer_init(struct trace_array *tr) static void irqsoff_tracer_reset(struct trace_array *tr) { + int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT; + int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE; + stop_irqsoff_tracer(tr, is_graph()); - if (!save_lat_flag) - trace_flags &= ~TRACE_ITER_LATENCY_FMT; + set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag); + set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag); } static void irqsoff_tracer_start(struct trace_array *tr) @@ -595,6 +601,7 @@ static struct tracer irqsoff_tracer __read_mostly = .print_line = irqsoff_print_line, .flags = &tracer_flags, .set_flag = irqsoff_set_flag, + .flag_changed = trace_keep_overwrite, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_irqsoff, #endif @@ -628,6 +635,7 @@ static struct tracer preemptoff_tracer __read_mostly = .print_line = irqsoff_print_line, .flags = &tracer_flags, .set_flag = irqsoff_set_flag, + .flag_changed = trace_keep_overwrite, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_preemptoff, #endif @@ -663,6 +671,7 @@ static struct tracer preemptirqsoff_tracer __read_mostly = .print_line = irqsoff_print_line, .flags = &tracer_flags, .set_flag = irqsoff_set_flag, + .flag_changed = trace_keep_overwrite, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_preemptirqsoff, #endif diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index f029dd4..1beb25e 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -36,7 +36,7 @@ static void __wakeup_reset(struct trace_array *tr); static int wakeup_graph_entry(struct ftrace_graph_ent *trace); static void wakeup_graph_return(struct ftrace_graph_ret *trace); -static int save_lat_flag; +static int save_flags; #define TRACE_DISPLAY_GRAPH 1 @@ -526,8 +526,11 @@ static void stop_wakeup_tracer(struct trace_array *tr) static int __wakeup_tracer_init(struct trace_array *tr) { - save_lat_flag = trace_flags & TRACE_ITER_LATENCY_FMT; - trace_flags |= TRACE_ITER_LATENCY_FMT; + save_flags = trace_flags; + + /* non overwrite screws up the latency tracers */ + set_tracer_flag(TRACE_ITER_OVERWRITE, 1); + set_tracer_flag(TRACE_ITER_LATENCY_FMT, 1); tracing_max_latency = 0; wakeup_trace = tr; @@ -549,12 +552,15 @@ static int wakeup_rt_tracer_init(struct trace_array *tr) static void wakeup_tracer_reset(struct trace_array *tr) { + int lat_flag = save_flags & TRACE_ITER_LATENCY_FMT; + int overwrite_flag = save_flags & TRACE_ITER_OVERWRITE; + stop_wakeup_tracer(tr); /* make sure we put back any tasks we are tracing */ wakeup_reset(tr); - if (!save_lat_flag) - trace_flags &= ~TRACE_ITER_LATENCY_FMT; + set_tracer_flag(TRACE_ITER_LATENCY_FMT, lat_flag); + set_tracer_flag(TRACE_ITER_OVERWRITE, overwrite_flag); } static void wakeup_tracer_start(struct trace_array *tr) @@ -580,6 +586,7 @@ static struct tracer wakeup_tracer __read_mostly = .print_line = wakeup_print_line, .flags = &tracer_flags, .set_flag = wakeup_set_flag, + .flag_changed = trace_keep_overwrite, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_wakeup, #endif @@ -601,6 +608,7 @@ static struct tracer wakeup_rt_tracer __read_mostly = .print_line = wakeup_print_line, .flags = &tracer_flags, .set_flag = wakeup_set_flag, + .flag_changed = trace_keep_overwrite, #ifdef CONFIG_FTRACE_SELFTEST .selftest = trace_selftest_startup_wakeup, #endif diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c index 288541f..09fd98a 100644 --- a/kernel/trace/trace_selftest.c +++ b/kernel/trace/trace_selftest.c @@ -461,8 +461,6 @@ trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) /* Maximum number of functions to trace before diagnosing a hang */ #define GRAPH_MAX_FUNC_TEST 100000000 -static void -__ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode); static unsigned int graph_hang_thresh; /* Wrap the real function entry probe to avoid possible hanging */ @@ -472,8 +470,11 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace) if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) { ftrace_graph_stop(); printk(KERN_WARNING "BUG: Function graph tracer hang!\n"); - if (ftrace_dump_on_oops) - __ftrace_dump(false, DUMP_ALL); + if (ftrace_dump_on_oops) { + ftrace_dump(DUMP_ALL); + /* ftrace_dump() disables tracing */ + tracing_on(); + } return 0; } diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index b0b53b8..2d43977 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -17,13 +17,24 @@ #define STACK_TRACE_ENTRIES 500 +#ifdef CC_USING_FENTRY +# define fentry 1 +#else +# define fentry 0 +#endif + static unsigned long stack_dump_trace[STACK_TRACE_ENTRIES+1] = { [0 ... (STACK_TRACE_ENTRIES)] = ULONG_MAX }; static unsigned stack_dump_index[STACK_TRACE_ENTRIES]; +/* + * Reserve one entry for the passed in ip. This will allow + * us to remove most or all of the stack size overhead + * added by the stack tracer itself. + */ static struct stack_trace max_stack_trace = { - .max_entries = STACK_TRACE_ENTRIES, - .entries = stack_dump_trace, + .max_entries = STACK_TRACE_ENTRIES - 1, + .entries = &stack_dump_trace[1], }; static unsigned long max_stack_size; @@ -37,25 +48,34 @@ static DEFINE_MUTEX(stack_sysctl_mutex); int stack_tracer_enabled; static int last_stack_tracer_enabled; -static inline void check_stack(void) +static inline void +check_stack(unsigned long ip, unsigned long *stack) { unsigned long this_size, flags; unsigned long *p, *top, *start; + static int tracer_frame; + int frame_size = ACCESS_ONCE(tracer_frame); int i; - this_size = ((unsigned long)&this_size) & (THREAD_SIZE-1); + this_size = ((unsigned long)stack) & (THREAD_SIZE-1); this_size = THREAD_SIZE - this_size; + /* Remove the frame of the tracer */ + this_size -= frame_size; if (this_size <= max_stack_size) return; /* we do not handle interrupt stacks yet */ - if (!object_is_on_stack(&this_size)) + if (!object_is_on_stack(stack)) return; local_irq_save(flags); arch_spin_lock(&max_stack_lock); + /* In case another CPU set the tracer_frame on us */ + if (unlikely(!frame_size)) + this_size -= tracer_frame; + /* a race could have already updated it */ if (this_size <= max_stack_size) goto out; @@ -68,10 +88,18 @@ static inline void check_stack(void) save_stack_trace(&max_stack_trace); /* + * Add the passed in ip from the function tracer. + * Searching for this on the stack will skip over + * most of the overhead from the stack tracer itself. + */ + stack_dump_trace[0] = ip; + max_stack_trace.nr_entries++; + + /* * Now find where in the stack these are. */ i = 0; - start = &this_size; + start = stack; top = (unsigned long *) (((unsigned long)start & ~(THREAD_SIZE-1)) + THREAD_SIZE); @@ -95,6 +123,18 @@ static inline void check_stack(void) found = 1; /* Start the search from here */ start = p + 1; + /* + * We do not want to show the overhead + * of the stack tracer stack in the + * max stack. If we haven't figured + * out what that is, then figure it out + * now. + */ + if (unlikely(!tracer_frame) && i == 1) { + tracer_frame = (p - stack) * + sizeof(unsigned long); + max_stack_size -= tracer_frame; + } } } @@ -110,6 +150,7 @@ static inline void check_stack(void) static void stack_trace_call(unsigned long ip, unsigned long parent_ip) { + unsigned long stack; int cpu; if (unlikely(!ftrace_enabled || stack_trace_disabled)) @@ -122,7 +163,26 @@ stack_trace_call(unsigned long ip, unsigned long parent_ip) if (per_cpu(trace_active, cpu)++ != 0) goto out; - check_stack(); + /* + * When fentry is used, the traced function does not get + * its stack frame set up, and we lose the parent. + * The ip is pretty useless because the function tracer + * was called before that function set up its stack frame. + * In this case, we use the parent ip. + * + * By adding the return address of either the parent ip + * or the current ip we can disregard most of the stack usage + * caused by the stack tracer itself. + * + * The function tracer always reports the address of where the + * mcount call was, but the stack will hold the return address. + */ + if (fentry) + ip = parent_ip; + else + ip += MCOUNT_INSN_SIZE; + + check_stack(ip, &stack); out: per_cpu(trace_active, cpu)--; @@ -360,6 +420,8 @@ static __init int stack_trace_init(void) struct dentry *d_tracer; d_tracer = tracing_init_dentry(); + if (!d_tracer) + return 0; trace_create_file("stack_max_size", 0644, d_tracer, &max_stack_size, &stack_max_size_fops); diff --git a/kernel/trace/trace_stat.c b/kernel/trace/trace_stat.c index 96cffb2..847f88a 100644 --- a/kernel/trace/trace_stat.c +++ b/kernel/trace/trace_stat.c @@ -307,6 +307,8 @@ static int tracing_stat_init(void) struct dentry *d_tracing; d_tracing = tracing_init_dentry(); + if (!d_tracing) + return 0; stat_dir = debugfs_create_dir("trace_stat", d_tracing); if (!stat_dir) diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index ee7b5a0..5819cd5 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -304,6 +304,8 @@ void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) struct ring_buffer *buffer; int size; int syscall_nr; + unsigned long irq_flags; + int pc; syscall_nr = syscall_get_nr(current, regs); if (syscall_nr < 0) @@ -317,8 +319,11 @@ void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args; + local_save_flags(irq_flags); + pc = preempt_count(); + event = trace_current_buffer_lock_reserve(&buffer, - sys_data->enter_event->event.type, size, 0, 0); + sys_data->enter_event->event.type, size, irq_flags, pc); if (!event) return; @@ -328,7 +333,8 @@ void ftrace_syscall_enter(void *ignore, struct pt_regs *regs, long id) if (!filter_current_check_discard(buffer, sys_data->enter_event, entry, event)) - trace_current_buffer_unlock_commit(buffer, event, 0, 0); + trace_current_buffer_unlock_commit(buffer, event, + irq_flags, pc); } void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) @@ -338,6 +344,8 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) struct ring_buffer_event *event; struct ring_buffer *buffer; int syscall_nr; + unsigned long irq_flags; + int pc; syscall_nr = syscall_get_nr(current, regs); if (syscall_nr < 0) @@ -349,8 +357,12 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) if (!sys_data) return; + local_save_flags(irq_flags); + pc = preempt_count(); + event = trace_current_buffer_lock_reserve(&buffer, - sys_data->exit_event->event.type, sizeof(*entry), 0, 0); + sys_data->exit_event->event.type, sizeof(*entry), + irq_flags, pc); if (!event) return; @@ -360,7 +372,8 @@ void ftrace_syscall_exit(void *ignore, struct pt_regs *regs, long ret) if (!filter_current_check_discard(buffer, sys_data->exit_event, entry, event)) - trace_current_buffer_unlock_commit(buffer, event, 0, 0); + trace_current_buffer_unlock_commit(buffer, event, + irq_flags, pc); } int reg_event_syscall_enter(struct ftrace_event_call *call) |