diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index bcddac61422c1147d6d0b986fec616117198877f..de6569c04cd0474b053c25335b52e9cdfa85e79e 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -1154,7 +1154,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs) /* * event overflow */ - handled = 1; + handled++; data.period = event->hw.last_period; if (!x86_perf_event_set_period(event)) @@ -1200,12 +1200,20 @@ void perf_events_lapic_init(void) apic_write(APIC_LVTPC, APIC_DM_NMI); } +struct pmu_nmi_state { + unsigned int marked; + int handled; +}; + +static DEFINE_PER_CPU(struct pmu_nmi_state, pmu_nmi); + static int __kprobes perf_event_nmi_handler(struct notifier_block *self, unsigned long cmd, void *__args) { struct die_args *args = __args; - struct pt_regs *regs; + unsigned int this_nmi; + int handled; if (!atomic_read(&active_events)) return NOTIFY_DONE; @@ -1214,22 +1222,47 @@ perf_event_nmi_handler(struct notifier_block *self, case DIE_NMI: case DIE_NMI_IPI: break; - + case DIE_NMIUNKNOWN: + this_nmi = percpu_read(irq_stat.__nmi_count); + if (this_nmi != __get_cpu_var(pmu_nmi).marked) + /* let the kernel handle the unknown nmi */ + return NOTIFY_DONE; + /* + * This one is a PMU back-to-back nmi. Two events + * trigger 'simultaneously' raising two back-to-back + * NMIs. If the first NMI handles both, the latter + * will be empty and daze the CPU. So, we drop it to + * avoid false-positive 'unknown nmi' messages. + */ + return NOTIFY_STOP; default: return NOTIFY_DONE; } - regs = args->regs; - apic_write(APIC_LVTPC, APIC_DM_NMI); - /* - * Can't rely on the handled return value to say it was our NMI, two - * events could trigger 'simultaneously' raising two back-to-back NMIs. - * - * If the first NMI handles both, the latter will be empty and daze - * the CPU. - */ - x86_pmu.handle_irq(regs); + + handled = x86_pmu.handle_irq(args->regs); + if (!handled) + return NOTIFY_DONE; + + this_nmi = percpu_read(irq_stat.__nmi_count); + if ((handled > 1) || + /* the next nmi could be a back-to-back nmi */ + ((__get_cpu_var(pmu_nmi).marked == this_nmi) && + (__get_cpu_var(pmu_nmi).handled > 1))) { + /* + * We could have two subsequent back-to-back nmis: The + * first handles more than one counter, the 2nd + * handles only one counter and the 3rd handles no + * counter. + * + * This is the 2nd nmi because the previous was + * handling more than one counter. We will mark the + * next (3rd) and then drop it if unhandled. + */ + __get_cpu_var(pmu_nmi).marked = this_nmi + 1; + __get_cpu_var(pmu_nmi).handled = handled; + } return NOTIFY_STOP; } diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index d8d86d01400866c6320001fb715301276747cd52..ee05c90012d269e66de9ffb6a5952d1434317c1e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -712,7 +712,8 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) struct perf_sample_data data; struct cpu_hw_events *cpuc; int bit, loops; - u64 ack, status; + u64 status; + int handled = 0; perf_sample_data_init(&data, 0); @@ -728,6 +729,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) loops = 0; again: + intel_pmu_ack_status(status); if (++loops > 100) { WARN_ONCE(1, "perfevents: irq loop stuck!\n"); perf_event_print_debug(); @@ -736,19 +738,22 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) } inc_irq_stat(apic_perf_irqs); - ack = status; intel_pmu_lbr_read(); /* * PEBS overflow sets bit 62 in the global status register */ - if (__test_and_clear_bit(62, (unsigned long *)&status)) + if (__test_and_clear_bit(62, (unsigned long *)&status)) { + handled++; x86_pmu.drain_pebs(regs); + } for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) { struct perf_event *event = cpuc->events[bit]; + handled++; + if (!test_bit(bit, cpuc->active_mask)) continue; @@ -761,8 +766,6 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) x86_pmu_stop(event); } - intel_pmu_ack_status(ack); - /* * Repeat if there is more work to be done: */ @@ -772,7 +775,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs) done: intel_pmu_enable_all(0); - return 1; + return handled; } static struct event_constraint * diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index 4fe62c7165c8c257af573868ff5509be8a09d0ab..c70c878ee02a022b0a92a070139b57e78d3ef943 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -936,7 +936,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs) inc_irq_stat(apic_perf_irqs); } - return handled > 0; + return handled; } /* diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index f6b48f6c595176a59c8e2fe5fa145bc11acca118..cfe4faabb0f6792aebfb8330dd55f02406b148dc 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -568,8 +568,13 @@ static int __init init_sysfs(void) int error; error = sysdev_class_register(&oprofile_sysclass); - if (!error) - error = sysdev_register(&device_oprofile); + if (error) + return error; + + error = sysdev_register(&device_oprofile); + if (error) + sysdev_class_unregister(&oprofile_sysclass); + return error; } @@ -580,8 +585,10 @@ static void exit_sysfs(void) } #else -#define init_sysfs() do { } while (0) -#define exit_sysfs() do { } while (0) + +static inline int init_sysfs(void) { return 0; } +static inline void exit_sysfs(void) { } + #endif /* CONFIG_PM */ static int __init p4_init(char **cpu_type) @@ -695,6 +702,8 @@ int __init op_nmi_init(struct oprofile_operations *ops) char *cpu_type = NULL; int ret = 0; + using_nmi = 0; + if (!cpu_has_apic) return -ENODEV; @@ -774,7 +783,10 @@ int __init op_nmi_init(struct oprofile_operations *ops) mux_init(ops); - init_sysfs(); + ret = init_sysfs(); + if (ret) + return ret; + using_nmi = 1; printk(KERN_INFO "oprofile: using NMI interrupt.\n"); return 0; diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c index a9352b2c7ac430d4e4aafac3d65a1b46005ea505..b7e755f4178ad885332ccaaeeb5eda492e6dfcfd 100644 --- a/drivers/oprofile/buffer_sync.c +++ b/drivers/oprofile/buffer_sync.c @@ -141,16 +141,6 @@ static struct notifier_block module_load_nb = { .notifier_call = module_load_notify, }; - -static void end_sync(void) -{ - end_cpu_work(); - /* make sure we don't leak task structs */ - process_task_mortuary(); - process_task_mortuary(); -} - - int sync_start(void) { int err; @@ -158,7 +148,7 @@ int sync_start(void) if (!zalloc_cpumask_var(&marked_cpus, GFP_KERNEL)) return -ENOMEM; - start_cpu_work(); + mutex_lock(&buffer_mutex); err = task_handoff_register(&task_free_nb); if (err) @@ -173,7 +163,10 @@ int sync_start(void) if (err) goto out4; + start_cpu_work(); + out: + mutex_unlock(&buffer_mutex); return err; out4: profile_event_unregister(PROFILE_MUNMAP, &munmap_nb); @@ -182,7 +175,6 @@ int sync_start(void) out2: task_handoff_unregister(&task_free_nb); out1: - end_sync(); free_cpumask_var(marked_cpus); goto out; } @@ -190,11 +182,20 @@ int sync_start(void) void sync_stop(void) { + /* flush buffers */ + mutex_lock(&buffer_mutex); + end_cpu_work(); unregister_module_notifier(&module_load_nb); profile_event_unregister(PROFILE_MUNMAP, &munmap_nb); profile_event_unregister(PROFILE_TASK_EXIT, &task_exit_nb); task_handoff_unregister(&task_free_nb); - end_sync(); + mutex_unlock(&buffer_mutex); + flush_scheduled_work(); + + /* make sure we don't leak task structs */ + process_task_mortuary(); + process_task_mortuary(); + free_cpumask_var(marked_cpus); } diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c index 219f79e2210a3fcd561b94456c4960a0a1fbacd9..f179ac2ea80149423034d66a90b1e81251c5069b 100644 --- a/drivers/oprofile/cpu_buffer.c +++ b/drivers/oprofile/cpu_buffer.c @@ -120,8 +120,6 @@ void end_cpu_work(void) cancel_delayed_work(&b->work); } - - flush_scheduled_work(); } /* diff --git a/kernel/perf_event.c b/kernel/perf_event.c index 0d38f27ad8852cfabb050d05567c67b4c3df47eb..2d74f31220ade9e26f283d2689477ef1d463a41c 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -402,11 +402,31 @@ static void perf_group_detach(struct perf_event *event) } } +static inline int +event_filter_match(struct perf_event *event) +{ + return event->cpu == -1 || event->cpu == smp_processor_id(); +} + static void event_sched_out(struct perf_event *event, struct perf_cpu_context *cpuctx, struct perf_event_context *ctx) { + u64 delta; + /* + * An event which could not be activated because of + * filter mismatch still needs to have its timings + * maintained, otherwise bogus information is return + * via read() for time_enabled, time_running: + */ + if (event->state == PERF_EVENT_STATE_INACTIVE + && !event_filter_match(event)) { + delta = ctx->time - event->tstamp_stopped; + event->tstamp_running += delta; + event->tstamp_stopped = ctx->time; + } + if (event->state != PERF_EVENT_STATE_ACTIVE) return; @@ -432,9 +452,7 @@ group_sched_out(struct perf_event *group_event, struct perf_event_context *ctx) { struct perf_event *event; - - if (group_event->state != PERF_EVENT_STATE_ACTIVE) - return; + int state = group_event->state; event_sched_out(group_event, cpuctx, ctx); @@ -444,7 +462,7 @@ group_sched_out(struct perf_event *group_event, list_for_each_entry(event, &group_event->sibling_list, group_entry) event_sched_out(event, cpuctx, ctx); - if (group_event->attr.exclusive) + if (state == PERF_EVENT_STATE_ACTIVE && group_event->attr.exclusive) cpuctx->exclusive = 0; } @@ -5942,15 +5960,15 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { unsigned int cpu = (long)hcpu; - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: + case CPU_DOWN_FAILED: perf_event_init_cpu(cpu); break; + case CPU_UP_CANCELED: case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: perf_event_exit_cpu(cpu); break; diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 0d88ce9b9fb8828c9a81fdffcd47763ae5cc2543..83a16e9ee518e4bd3b03b059f7ac372547a0e23b 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -381,12 +381,19 @@ static int function_stat_show(struct seq_file *m, void *v) { struct ftrace_profile *rec = v; char str[KSYM_SYMBOL_LEN]; + int ret = 0; #ifdef CONFIG_FUNCTION_GRAPH_TRACER - static DEFINE_MUTEX(mutex); static struct trace_seq s; unsigned long long avg; unsigned long long stddev; #endif + mutex_lock(&ftrace_profile_lock); + + /* we raced with function_profile_reset() */ + if (unlikely(rec->counter == 0)) { + ret = -EBUSY; + goto out; + } kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); seq_printf(m, " %-30.30s %10lu", str, rec->counter); @@ -408,7 +415,6 @@ static int function_stat_show(struct seq_file *m, void *v) do_div(stddev, (rec->counter - 1) * 1000); } - mutex_lock(&mutex); trace_seq_init(&s); trace_print_graph_duration(rec->time, &s); trace_seq_puts(&s, " "); @@ -416,11 +422,12 @@ static int function_stat_show(struct seq_file *m, void *v) trace_seq_puts(&s, " "); trace_print_graph_duration(stddev, &s); trace_print_seq(m, &s); - mutex_unlock(&mutex); #endif seq_putc(m, '\n'); +out: + mutex_unlock(&ftrace_profile_lock); - return 0; + return ret; } static void ftrace_profile_reset(struct ftrace_profile_stat *stat) @@ -2409,7 +2416,7 @@ static const struct file_operations ftrace_filter_fops = { .open = ftrace_filter_open, .read = seq_read, .write = ftrace_filter_write, - .llseek = ftrace_regex_lseek, + .llseek = no_llseek, .release = ftrace_filter_release, }; diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c index 92f5477a006a5db34cf93709d167b182ac072861..f3bbcd1c90c8dd8a8aff1c008b83cf65f12635aa 100644 --- a/kernel/trace/trace_event_perf.c +++ b/kernel/trace/trace_event_perf.c @@ -91,6 +91,8 @@ int perf_trace_init(struct perf_event *p_event) tp_event->class && tp_event->class->reg && try_module_get(tp_event->mod)) { ret = perf_trace_event_init(tp_event, p_event); + if (ret) + module_put(tp_event->mod); break; } } @@ -147,6 +149,7 @@ void perf_trace_destroy(struct perf_event *p_event) } } out: + module_put(tp_event->mod); mutex_unlock(&event_mutex); } diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 8b27c9849b427905ea9a5ef83864a88526afe405..544301d29dee45b0dc089db788bcfe89687bfa45 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -514,8 +514,8 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs); static int kretprobe_dispatcher(struct kretprobe_instance *ri, struct pt_regs *regs); -/* Check the name is good for event/group */ -static int check_event_name(const char *name) +/* Check the name is good for event/group/fields */ +static int is_good_name(const char *name) { if (!isalpha(*name) && *name != '_') return 0; @@ -557,7 +557,7 @@ static struct trace_probe *alloc_trace_probe(const char *group, else tp->rp.kp.pre_handler = kprobe_dispatcher; - if (!event || !check_event_name(event)) { + if (!event || !is_good_name(event)) { ret = -EINVAL; goto error; } @@ -567,7 +567,7 @@ static struct trace_probe *alloc_trace_probe(const char *group, if (!tp->call.name) goto error; - if (!group || !check_event_name(group)) { + if (!group || !is_good_name(group)) { ret = -EINVAL; goto error; } @@ -883,7 +883,7 @@ static int create_trace_probe(int argc, char **argv) int i, ret = 0; int is_return = 0, is_delete = 0; char *symbol = NULL, *event = NULL, *group = NULL; - char *arg, *tmp; + char *arg; unsigned long offset = 0; void *addr = NULL; char buf[MAX_EVENT_NAME_LEN]; @@ -992,26 +992,36 @@ static int create_trace_probe(int argc, char **argv) /* parse arguments */ ret = 0; for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) { + /* Increment count for freeing args in error case */ + tp->nr_args++; + /* Parse argument name */ arg = strchr(argv[i], '='); - if (arg) + if (arg) { *arg++ = '\0'; - else + tp->args[i].name = kstrdup(argv[i], GFP_KERNEL); + } else { arg = argv[i]; + /* If argument name is omitted, set "argN" */ + snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1); + tp->args[i].name = kstrdup(buf, GFP_KERNEL); + } - tp->args[i].name = kstrdup(argv[i], GFP_KERNEL); if (!tp->args[i].name) { - pr_info("Failed to allocate argument%d name '%s'.\n", - i, argv[i]); + pr_info("Failed to allocate argument[%d] name.\n", i); ret = -ENOMEM; goto error; } - tmp = strchr(tp->args[i].name, ':'); - if (tmp) - *tmp = '_'; /* convert : to _ */ + + if (!is_good_name(tp->args[i].name)) { + pr_info("Invalid argument[%d] name: %s\n", + i, tp->args[i].name); + ret = -EINVAL; + goto error; + } if (conflict_field_name(tp->args[i].name, tp->args, i)) { - pr_info("Argument%d name '%s' conflicts with " + pr_info("Argument[%d] name '%s' conflicts with " "another field.\n", i, argv[i]); ret = -EINVAL; goto error; @@ -1020,12 +1030,9 @@ static int create_trace_probe(int argc, char **argv) /* Parse fetch argument */ ret = parse_probe_arg(arg, tp, &tp->args[i], is_return); if (ret) { - pr_info("Parse error at argument%d. (%d)\n", i, ret); - kfree(tp->args[i].name); + pr_info("Parse error at argument[%d]. (%d)\n", i, ret); goto error; } - - tp->nr_args++; } ret = register_trace_probe(tp); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 5b1ee4f4ca0ddaf6bdd7d219ed2bac93000740db..fa71aebda4ffbf0c72e2c39489c298163ed24cf0 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -121,7 +121,7 @@ static void __touch_watchdog(void) void touch_softlockup_watchdog(void) { - __get_cpu_var(watchdog_touch_ts) = 0; + __raw_get_cpu_var(watchdog_touch_ts) = 0; } EXPORT_SYMBOL(touch_softlockup_watchdog); @@ -141,7 +141,14 @@ void touch_all_softlockup_watchdogs(void) #ifdef CONFIG_HARDLOCKUP_DETECTOR void touch_nmi_watchdog(void) { - __get_cpu_var(watchdog_nmi_touch) = true; + if (watchdog_enabled) { + unsigned cpu; + + for_each_present_cpu(cpu) { + if (per_cpu(watchdog_nmi_touch, cpu) != true) + per_cpu(watchdog_nmi_touch, cpu) = true; + } + } touch_softlockup_watchdog(); } EXPORT_SYMBOL(touch_nmi_watchdog); @@ -422,6 +429,9 @@ static int watchdog_enable(int cpu) wake_up_process(p); } + /* if any cpu succeeds, watchdog is considered enabled for the system */ + watchdog_enabled = 1; + return 0; } @@ -444,9 +454,6 @@ static void watchdog_disable(int cpu) per_cpu(softlockup_watchdog, cpu) = NULL; kthread_stop(p); } - - /* if any cpu succeeds, watchdog is considered enabled for the system */ - watchdog_enabled = 1; } static void watchdog_enable_all_cpus(void) diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index e72f05c3bef09258311f7192afb179a10657c450..fcc16e4349df9f3353ac03f975d9c1be9938863a 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1539,6 +1539,7 @@ static int convert_to_probe_trace_events(struct perf_probe_event *pev, goto error; } tev->point.offset = pev->point.offset; + tev->point.retprobe = pev->point.retprobe; tev->nargs = pev->nargs; if (tev->nargs) { tev->args = zalloc(sizeof(struct probe_trace_arg) diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index 525136684d4ec170201b4d07c7b080b73851edf9..32b81f707ff5eb5d950a2d233d6c00c6b90fedb2 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -686,6 +686,25 @@ static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf) char buf[32], *ptr; int ret, nscopes; + if (!is_c_varname(pf->pvar->var)) { + /* Copy raw parameters */ + pf->tvar->value = strdup(pf->pvar->var); + if (pf->tvar->value == NULL) + return -ENOMEM; + if (pf->pvar->type) { + pf->tvar->type = strdup(pf->pvar->type); + if (pf->tvar->type == NULL) + return -ENOMEM; + } + if (pf->pvar->name) { + pf->tvar->name = strdup(pf->pvar->name); + if (pf->tvar->name == NULL) + return -ENOMEM; + } else + pf->tvar->name = NULL; + return 0; + } + if (pf->pvar->name) pf->tvar->name = strdup(pf->pvar->name); else { @@ -700,19 +719,6 @@ static int find_variable(Dwarf_Die *sp_die, struct probe_finder *pf) if (pf->tvar->name == NULL) return -ENOMEM; - if (!is_c_varname(pf->pvar->var)) { - /* Copy raw parameters */ - pf->tvar->value = strdup(pf->pvar->var); - if (pf->tvar->value == NULL) - return -ENOMEM; - if (pf->pvar->type) { - pf->tvar->type = strdup(pf->pvar->type); - if (pf->tvar->type == NULL) - return -ENOMEM; - } - return 0; - } - pr_debug("Searching '%s' variable in context.\n", pf->pvar->var); /* Search child die for local variables and parameters. */ @@ -783,6 +789,16 @@ static int convert_probe_point(Dwarf_Die *sp_die, struct probe_finder *pf) /* This function has no name. */ tev->point.offset = (unsigned long)pf->addr; + /* Return probe must be on the head of a subprogram */ + if (pf->pev->point.retprobe) { + if (tev->point.offset != 0) { + pr_warning("Return probe must be on the head of" + " a real function\n"); + return -EINVAL; + } + tev->point.retprobe = true; + } + pr_debug("Probe point found: %s+%lu\n", tev->point.symbol, tev->point.offset);