From 84e478c6f1eb9c4bfa1fff2f8108e9a061b46428 Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 5 Feb 2010 21:47:05 -0500 Subject: nmi_watchdog: Config option to enable new nmi_watchdog These are the bits that enable the new nmi_watchdog and safely isolate the old nmi_watchdog. Only one or the other can run, not both at the same time. Signed-off-by: Don Zickus Cc: Linus Torvalds Cc: Andrew Morton Cc: gorcunov@gmail.com Cc: aris@redhat.com Cc: peterz@infradead.org LKML-Reference: <1265424425-31562-4-git-send-email-dzickus@redhat.com> Signed-off-by: Ingo Molnar --- kernel/Makefile | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/Makefile') diff --git a/kernel/Makefile b/kernel/Makefile index 864ff75d65f2..8a5abe53ebad 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -76,6 +76,7 @@ obj-$(CONFIG_AUDIT_TREE) += audit_tree.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_KGDB) += kgdb.o obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o +obj-$(CONFIG_NMI_WATCHDOG) += nmi_watchdog.o obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o obj-$(CONFIG_GENERIC_HARDIRQS) += irq/ obj-$(CONFIG_SECCOMP) += seccomp.o -- cgit v1.2.3 From 58687acba59266735adb8ccd9b5b9aa2c7cd205b Mon Sep 17 00:00:00 2001 From: Don Zickus Date: Fri, 7 May 2010 17:11:44 -0400 Subject: lockup_detector: Combine nmi_watchdog and softlockup detector The new nmi_watchdog (which uses the perf event subsystem) is very similar in structure to the softlockup detector. Using Ingo's suggestion, I combined the two functionalities into one file: kernel/watchdog.c. Now both the nmi_watchdog (or hardlockup detector) and softlockup detector sit on top of the perf event subsystem, which is run every 60 seconds or so to see if there are any lockups. To detect hardlockups, cpus not responding to interrupts, I implemented an hrtimer that runs 5 times for every perf event overflow event. If that stops counting on a cpu, then the cpu is most likely in trouble. To detect softlockups, tasks not yielding to the scheduler, I used the previous kthread idea that now gets kicked every time the hrtimer fires. If the kthread isn't being scheduled neither is anyone else and the warning is printed to the console. I tested this on x86_64 and both the softlockup and hardlockup paths work. V2: - cleaned up the Kconfig and softlockup combination - surrounded hardlockup cases with #ifdef CONFIG_PERF_EVENTS_NMI - seperated out the softlockup case from perf event subsystem - re-arranged the enabling/disabling nmi watchdog from proc space - added cpumasks for hardlockup failure cases - removed fallback to soft events if no PMU exists for hard events V3: - comment cleanups - drop support for older softlockup code - per_cpu cleanups - completely remove software clock base hardlockup detector - use per_cpu masking on hard/soft lockup detection - #ifdef cleanups - rename config option NMI_WATCHDOG to LOCKUP_DETECTOR - documentation additions V4: - documentation fixes - convert per_cpu to __get_cpu_var - powerpc compile fixes V5: - split apart warn flags for hard and soft lockups TODO: - figure out how to make an arch-agnostic clock2cycles call (if possible) to feed into perf events as a sample period [fweisbec: merged conflict patch] Signed-off-by: Don Zickus Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Cyrill Gorcunov Cc: Eric Paris Cc: Randy Dunlap LKML-Reference: <1273266711-18706-2-git-send-email-dzickus@redhat.com> Signed-off-by: Frederic Weisbecker --- Documentation/kernel-parameters.txt | 2 + arch/x86/include/asm/nmi.h | 2 +- arch/x86/kernel/apic/Makefile | 4 +- arch/x86/kernel/apic/hw_nmi.c | 2 +- arch/x86/kernel/traps.c | 4 +- include/linux/nmi.h | 8 +- include/linux/sched.h | 6 + init/Kconfig | 5 +- kernel/Makefile | 3 +- kernel/sysctl.c | 21 +- kernel/watchdog.c | 592 ++++++++++++++++++++++++++++++++++++ lib/Kconfig.debug | 30 +- 12 files changed, 650 insertions(+), 29 deletions(-) create mode 100644 kernel/watchdog.c (limited to 'kernel/Makefile') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 839b21b0699a..dfe8d1c226c6 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1777,6 +1777,8 @@ and is between 256 and 4096 characters. It is defined in the file nousb [USB] Disable the USB subsystem + nowatchdog [KNL] Disable the lockup detector. + nowb [ARM] nox2apic [X86-64,APIC] Do not enable x2APIC mode. diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 5b41b0feb6db..932f0f86b4b7 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -17,7 +17,7 @@ int do_nmi_callback(struct pt_regs *regs, int cpu); extern void die_nmi(char *str, struct pt_regs *regs, int do_panic); extern int check_nmi_watchdog(void); -#if !defined(CONFIG_NMI_WATCHDOG) +#if !defined(CONFIG_LOCKUP_DETECTOR) extern int nmi_watchdog_enabled; #endif extern int avail_to_resrv_perfctr_nmi_bit(unsigned int); diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 1a4512e48d24..52f32e0ea194 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -3,10 +3,10 @@ # obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_noop.o probe_$(BITS).o ipi.o -ifneq ($(CONFIG_NMI_WATCHDOG),y) +ifneq ($(CONFIG_LOCKUP_DETECTOR),y) obj-$(CONFIG_X86_LOCAL_APIC) += nmi.o endif -obj-$(CONFIG_NMI_WATCHDOG) += hw_nmi.o +obj-$(CONFIG_LOCKUP_DETECTOR) += hw_nmi.o obj-$(CONFIG_X86_IO_APIC) += io_apic.o obj-$(CONFIG_SMP) += ipi.o diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index e8b78a0be5de..79425f96fcee 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -89,7 +89,7 @@ int hw_nmi_is_cpu_stuck(struct pt_regs *regs) u64 hw_nmi_get_sample_period(void) { - return cpu_khz * 1000; + return (u64)(cpu_khz) * 1000 * 60; } #ifdef ARCH_HAS_NMI_WATCHDOG diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index bdc7fab3ef3e..bd347c2b34dc 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -406,7 +406,7 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) == NOTIFY_STOP) return; -#ifndef CONFIG_NMI_WATCHDOG +#ifndef CONFIG_LOCKUP_DETECTOR /* * Ok, so this is none of the documented NMI sources, * so it must be the NMI watchdog. @@ -414,7 +414,7 @@ static notrace __kprobes void default_do_nmi(struct pt_regs *regs) if (nmi_watchdog_tick(regs, reason)) return; if (!do_nmi_callback(regs, cpu)) -#endif /* !CONFIG_NMI_WATCHDOG */ +#endif /* !CONFIG_LOCKUP_DETECTOR */ unknown_nmi_error(reason, regs); #else unknown_nmi_error(reason, regs); diff --git a/include/linux/nmi.h b/include/linux/nmi.h index 22cc7960b649..abd48aacaf79 100644 --- a/include/linux/nmi.h +++ b/include/linux/nmi.h @@ -20,7 +20,7 @@ extern void touch_nmi_watchdog(void); extern void acpi_nmi_disable(void); extern void acpi_nmi_enable(void); #else -#ifndef CONFIG_NMI_WATCHDOG +#ifndef CONFIG_LOCKUP_DETECTOR static inline void touch_nmi_watchdog(void) { touch_softlockup_watchdog(); @@ -51,12 +51,12 @@ static inline bool trigger_all_cpu_backtrace(void) } #endif -#ifdef CONFIG_NMI_WATCHDOG +#ifdef CONFIG_LOCKUP_DETECTOR int hw_nmi_is_cpu_stuck(struct pt_regs *); u64 hw_nmi_get_sample_period(void); -extern int nmi_watchdog_enabled; +extern int watchdog_enabled; struct ctl_table; -extern int proc_nmi_enabled(struct ctl_table *, int , +extern int proc_dowatchdog_enabled(struct ctl_table *, int , void __user *, size_t *, loff_t *); #endif diff --git a/include/linux/sched.h b/include/linux/sched.h index dad7f668ebf7..37efe8fa5306 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -346,6 +346,12 @@ extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, size_t *lenp, loff_t *ppos); #endif +#ifdef CONFIG_LOCKUP_DETECTOR +extern int proc_dowatchdog_thresh(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos); +#endif + /* Attach to any functions which should be ignored in wchan output. */ #define __sched __attribute__((__section__(".sched.text"))) diff --git a/init/Kconfig b/init/Kconfig index c6c8903cb534..e44e25422f22 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -944,8 +944,11 @@ config PERF_USE_VMALLOC config PERF_EVENTS_NMI bool + depends on PERF_EVENTS help - Arch has support for nmi_watchdog + System hardware can generate an NMI using the perf event + subsystem. Also has support for calculating CPU cycle events + to determine how many clock cycles in a given period. menu "Kernel Performance Events And Counters" diff --git a/kernel/Makefile b/kernel/Makefile index d5c30060ac14..6adeafc3e259 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -76,9 +76,8 @@ obj-$(CONFIG_GCOV_KERNEL) += gcov/ obj-$(CONFIG_AUDIT_TREE) += audit_tree.o obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_KGDB) += kgdb.o -obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o -obj-$(CONFIG_NMI_WATCHDOG) += nmi_watchdog.o obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o +obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o obj-$(CONFIG_GENERIC_HARDIRQS) += irq/ obj-$(CONFIG_SECCOMP) += seccomp.o obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o diff --git a/kernel/sysctl.c b/kernel/sysctl.c index a38af430f0d8..0f9adda85f97 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -74,7 +74,7 @@ #include #endif -#ifdef CONFIG_NMI_WATCHDOG +#ifdef CONFIG_LOCKUP_DETECTOR #include #endif @@ -686,16 +686,25 @@ static struct ctl_table kern_table[] = { .mode = 0444, .proc_handler = proc_dointvec, }, -#if defined(CONFIG_NMI_WATCHDOG) +#if defined(CONFIG_LOCKUP_DETECTOR) { - .procname = "nmi_watchdog", - .data = &nmi_watchdog_enabled, + .procname = "watchdog", + .data = &watchdog_enabled, .maxlen = sizeof (int), .mode = 0644, - .proc_handler = proc_nmi_enabled, + .proc_handler = proc_dowatchdog_enabled, + }, + { + .procname = "watchdog_thresh", + .data = &softlockup_thresh, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dowatchdog_thresh, + .extra1 = &neg_one, + .extra2 = &sixty, }, #endif -#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) && !defined(CONFIG_NMI_WATCHDOG) +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86) && !defined(CONFIG_LOCKUP_DETECTOR) { .procname = "unknown_nmi_panic", .data = &unknown_nmi_panic, diff --git a/kernel/watchdog.c b/kernel/watchdog.c new file mode 100644 index 000000000000..6b7fad8497af --- /dev/null +++ b/kernel/watchdog.c @@ -0,0 +1,592 @@ +/* + * Detect hard and soft lockups on a system + * + * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. + * + * this code detects hard lockups: incidents in where on a CPU + * the kernel does not respond to anything except NMI. + * + * Note: Most of this code is borrowed heavily from softlockup.c, + * so thanks to Ingo for the initial implementation. + * Some chunks also taken from arch/x86/kernel/apic/nmi.c, thanks + * to those contributors as well. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +int watchdog_enabled; +int __read_mostly softlockup_thresh = 60; + +static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); +static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog); +static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); +static DEFINE_PER_CPU(bool, softlockup_touch_sync); +static DEFINE_PER_CPU(bool, hard_watchdog_warn); +static DEFINE_PER_CPU(bool, soft_watchdog_warn); +#ifdef CONFIG_PERF_EVENTS_NMI +static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts); +static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); +static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); +#endif + +static int __read_mostly did_panic; +static int __initdata no_watchdog; + + +/* boot commands */ +/* + * Should we panic when a soft-lockup or hard-lockup occurs: + */ +#ifdef CONFIG_PERF_EVENTS_NMI +static int hardlockup_panic; + +static int __init hardlockup_panic_setup(char *str) +{ + if (!strncmp(str, "panic", 5)) + hardlockup_panic = 1; + return 1; +} +__setup("nmi_watchdog=", hardlockup_panic_setup); +#endif + +unsigned int __read_mostly softlockup_panic = + CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; + +static int __init softlockup_panic_setup(char *str) +{ + softlockup_panic = simple_strtoul(str, NULL, 0); + + return 1; +} +__setup("softlockup_panic=", softlockup_panic_setup); + +static int __init nowatchdog_setup(char *str) +{ + no_watchdog = 1; + return 1; +} +__setup("nowatchdog", nowatchdog_setup); + +/* deprecated */ +static int __init nosoftlockup_setup(char *str) +{ + no_watchdog = 1; + return 1; +} +__setup("nosoftlockup", nosoftlockup_setup); +/* */ + + +/* + * Returns seconds, approximately. We don't need nanosecond + * resolution, and we don't need to waste time with a big divide when + * 2^30ns == 1.074s. + */ +static unsigned long get_timestamp(int this_cpu) +{ + return cpu_clock(this_cpu) >> 30LL; /* 2^30 ~= 10^9 */ +} + +static unsigned long get_sample_period(void) +{ + /* + * convert softlockup_thresh from seconds to ns + * the divide by 5 is to give hrtimer 5 chances to + * increment before the hardlockup detector generates + * a warning + */ + return softlockup_thresh / 5 * NSEC_PER_SEC; +} + +/* Commands for resetting the watchdog */ +static void __touch_watchdog(void) +{ + int this_cpu = raw_smp_processor_id(); + + __get_cpu_var(watchdog_touch_ts) = get_timestamp(this_cpu); +} + +void touch_watchdog(void) +{ + __get_cpu_var(watchdog_touch_ts) = 0; +} +EXPORT_SYMBOL(touch_watchdog); + +void touch_all_watchdog(void) +{ + int cpu; + + /* + * this is done lockless + * do we care if a 0 races with a timestamp? + * all it means is the softlock check starts one cycle later + */ + for_each_online_cpu(cpu) + per_cpu(watchdog_touch_ts, cpu) = 0; +} + +void touch_nmi_watchdog(void) +{ + touch_watchdog(); +} +EXPORT_SYMBOL(touch_nmi_watchdog); + +void touch_all_nmi_watchdog(void) +{ + touch_all_watchdog(); +} + +void touch_softlockup_watchdog(void) +{ + touch_watchdog(); +} + +void touch_all_softlockup_watchdogs(void) +{ + touch_all_watchdog(); +} + +void touch_softlockup_watchdog_sync(void) +{ + __raw_get_cpu_var(softlockup_touch_sync) = true; + __raw_get_cpu_var(watchdog_touch_ts) = 0; +} + +void softlockup_tick(void) +{ +} + +#ifdef CONFIG_PERF_EVENTS_NMI +/* watchdog detector functions */ +static int is_hardlockup(int cpu) +{ + unsigned long hrint = per_cpu(hrtimer_interrupts, cpu); + + if (per_cpu(hrtimer_interrupts_saved, cpu) == hrint) + return 1; + + per_cpu(hrtimer_interrupts_saved, cpu) = hrint; + return 0; +} +#endif + +static int is_softlockup(unsigned long touch_ts, int cpu) +{ + unsigned long now = get_timestamp(cpu); + + /* Warn about unreasonable delays: */ + if (time_after(now, touch_ts + softlockup_thresh)) + return now - touch_ts; + + return 0; +} + +static int +watchdog_panic(struct notifier_block *this, unsigned long event, void *ptr) +{ + did_panic = 1; + + return NOTIFY_DONE; +} + +static struct notifier_block panic_block = { + .notifier_call = watchdog_panic, +}; + +#ifdef CONFIG_PERF_EVENTS_NMI +static struct perf_event_attr wd_hw_attr = { + .type = PERF_TYPE_HARDWARE, + .config = PERF_COUNT_HW_CPU_CYCLES, + .size = sizeof(struct perf_event_attr), + .pinned = 1, + .disabled = 1, +}; + +/* Callback function for perf event subsystem */ +void watchdog_overflow_callback(struct perf_event *event, int nmi, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + int this_cpu = smp_processor_id(); + unsigned long touch_ts = per_cpu(watchdog_touch_ts, this_cpu); + + if (touch_ts == 0) { + __touch_watchdog(); + return; + } + + /* check for a hardlockup + * This is done by making sure our timer interrupt + * is incrementing. The timer interrupt should have + * fired multiple times before we overflow'd. If it hasn't + * then this is a good indication the cpu is stuck + */ + if (is_hardlockup(this_cpu)) { + /* only print hardlockups once */ + if (__get_cpu_var(hard_watchdog_warn) == true) + return; + + if (hardlockup_panic) + panic("Watchdog detected hard LOCKUP on cpu %d", this_cpu); + else + WARN(1, "Watchdog detected hard LOCKUP on cpu %d", this_cpu); + + __get_cpu_var(hard_watchdog_warn) = true; + return; + } + + __get_cpu_var(hard_watchdog_warn) = false; + return; +} +static void watchdog_interrupt_count(void) +{ + __get_cpu_var(hrtimer_interrupts)++; +} +#else +static inline void watchdog_interrupt_count(void) { return; } +#endif /* CONFIG_PERF_EVENTS_NMI */ + +/* watchdog kicker functions */ +static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) +{ + int this_cpu = smp_processor_id(); + unsigned long touch_ts = __get_cpu_var(watchdog_touch_ts); + struct pt_regs *regs = get_irq_regs(); + int duration; + + /* kick the hardlockup detector */ + watchdog_interrupt_count(); + + /* kick the softlockup detector */ + wake_up_process(__get_cpu_var(softlockup_watchdog)); + + /* .. and repeat */ + hrtimer_forward_now(hrtimer, ns_to_ktime(get_sample_period())); + + if (touch_ts == 0) { + if (unlikely(per_cpu(softlockup_touch_sync, this_cpu))) { + /* + * If the time stamp was touched atomically + * make sure the scheduler tick is up to date. + */ + per_cpu(softlockup_touch_sync, this_cpu) = false; + sched_clock_tick(); + } + __touch_watchdog(); + return HRTIMER_RESTART; + } + + /* check for a softlockup + * This is done by making sure a high priority task is + * being scheduled. The task touches the watchdog to + * indicate it is getting cpu time. If it hasn't then + * this is a good indication some task is hogging the cpu + */ + duration = is_softlockup(touch_ts, this_cpu); + if (unlikely(duration)) { + /* only warn once */ + if (__get_cpu_var(soft_watchdog_warn) == true) + return HRTIMER_RESTART; + + printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", + this_cpu, duration, + current->comm, task_pid_nr(current)); + print_modules(); + print_irqtrace_events(current); + if (regs) + show_regs(regs); + else + dump_stack(); + + if (softlockup_panic) + panic("softlockup: hung tasks"); + __get_cpu_var(soft_watchdog_warn) = true; + } else + __get_cpu_var(soft_watchdog_warn) = false; + + return HRTIMER_RESTART; +} + + +/* + * The watchdog thread - touches the timestamp. + */ +static int watchdog(void *__bind_cpu) +{ + struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; + struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, (unsigned long)__bind_cpu); + + sched_setscheduler(current, SCHED_FIFO, ¶m); + + /* initialize timestamp */ + __touch_watchdog(); + + /* kick off the timer for the hardlockup detector */ + /* done here because hrtimer_start can only pin to smp_processor_id() */ + hrtimer_start(hrtimer, ns_to_ktime(get_sample_period()), + HRTIMER_MODE_REL_PINNED); + + set_current_state(TASK_INTERRUPTIBLE); + /* + * Run briefly once per second to reset the softlockup timestamp. + * If this gets delayed for more than 60 seconds then the + * debug-printout triggers in softlockup_tick(). + */ + while (!kthread_should_stop()) { + __touch_watchdog(); + schedule(); + + if (kthread_should_stop()) + break; + + set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); + + return 0; +} + + +#ifdef CONFIG_PERF_EVENTS_NMI +static int watchdog_nmi_enable(int cpu) +{ + struct perf_event_attr *wd_attr; + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + /* is it already setup and enabled? */ + if (event && event->state > PERF_EVENT_STATE_OFF) + goto out; + + /* it is setup but not enabled */ + if (event != NULL) + goto out_enable; + + /* Try to register using hardware perf events */ + wd_attr = &wd_hw_attr; + wd_attr->sample_period = hw_nmi_get_sample_period(); + event = perf_event_create_kernel_counter(wd_attr, cpu, -1, watchdog_overflow_callback); + if (!IS_ERR(event)) { + printk(KERN_INFO "NMI watchdog enabled, takes one hw-pmu counter.\n"); + goto out_save; + } + + printk(KERN_ERR "NMI watchdog failed to create perf event on cpu%i: %p\n", cpu, event); + return -1; + + /* success path */ +out_save: + per_cpu(watchdog_ev, cpu) = event; +out_enable: + perf_event_enable(per_cpu(watchdog_ev, cpu)); +out: + return 0; +} + +static void watchdog_nmi_disable(int cpu) +{ + struct perf_event *event = per_cpu(watchdog_ev, cpu); + + if (event) { + perf_event_disable(event); + per_cpu(watchdog_ev, cpu) = NULL; + + /* should be in cleanup, but blocks oprofile */ + perf_event_release_kernel(event); + } + return; +} +#else +static int watchdog_nmi_enable(int cpu) { return 0; } +static void watchdog_nmi_disable(int cpu) { return; } +#endif /* CONFIG_PERF_EVENTS_NMI */ + +/* prepare/enable/disable routines */ +static int watchdog_prepare_cpu(int cpu) +{ + struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu); + + WARN_ON(per_cpu(softlockup_watchdog, cpu)); + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer->function = watchdog_timer_fn; + + return 0; +} + +static int watchdog_enable(int cpu) +{ + struct task_struct *p = per_cpu(softlockup_watchdog, cpu); + + /* enable the perf event */ + if (watchdog_nmi_enable(cpu) != 0) + return -1; + + /* create the watchdog thread */ + if (!p) { + p = kthread_create(watchdog, (void *)(unsigned long)cpu, "watchdog/%d", cpu); + if (IS_ERR(p)) { + printk(KERN_ERR "softlockup watchdog for %i failed\n", cpu); + return -1; + } + kthread_bind(p, cpu); + per_cpu(watchdog_touch_ts, cpu) = 0; + per_cpu(softlockup_watchdog, cpu) = p; + wake_up_process(p); + } + + return 0; +} + +static void watchdog_disable(int cpu) +{ + struct task_struct *p = per_cpu(softlockup_watchdog, cpu); + struct hrtimer *hrtimer = &per_cpu(watchdog_hrtimer, cpu); + + /* + * cancel the timer first to stop incrementing the stats + * and waking up the kthread + */ + hrtimer_cancel(hrtimer); + + /* disable the perf event */ + watchdog_nmi_disable(cpu); + + /* stop the watchdog thread */ + if (p) { + 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) +{ + int cpu; + int result; + + for_each_online_cpu(cpu) + result += watchdog_enable(cpu); + + if (result) + printk(KERN_ERR "watchdog: failed to be enabled on some cpus\n"); + +} + +static void watchdog_disable_all_cpus(void) +{ + int cpu; + + for_each_online_cpu(cpu) + watchdog_disable(cpu); + + /* if all watchdogs are disabled, then they are disabled for the system */ + watchdog_enabled = 0; +} + + +/* sysctl functions */ +#ifdef CONFIG_SYSCTL +/* + * proc handler for /proc/sys/kernel/nmi_watchdog + */ + +int proc_dowatchdog_enabled(struct ctl_table *table, int write, + void __user *buffer, size_t *length, loff_t *ppos) +{ + proc_dointvec(table, write, buffer, length, ppos); + + if (watchdog_enabled) + watchdog_enable_all_cpus(); + else + watchdog_disable_all_cpus(); + return 0; +} + +int proc_dowatchdog_thresh(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + return proc_dointvec_minmax(table, write, buffer, lenp, ppos); +} + +/* stub functions */ +int proc_dosoftlockup_thresh(struct ctl_table *table, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + return proc_dowatchdog_thresh(table, write, buffer, lenp, ppos); +} +/* end of stub functions */ +#endif /* CONFIG_SYSCTL */ + + +/* + * Create/destroy watchdog threads as CPUs come and go: + */ +static int __cpuinit +cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) +{ + int hotcpu = (unsigned long)hcpu; + + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + if (watchdog_prepare_cpu(hotcpu)) + return NOTIFY_BAD; + break; + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + if (watchdog_enable(hotcpu)) + return NOTIFY_BAD; + break; +#ifdef CONFIG_HOTPLUG_CPU + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + watchdog_disable(hotcpu); + break; + case CPU_DEAD: + case CPU_DEAD_FROZEN: + watchdog_disable(hotcpu); + break; +#endif /* CONFIG_HOTPLUG_CPU */ + } + return NOTIFY_OK; +} + +static struct notifier_block __cpuinitdata cpu_nfb = { + .notifier_call = cpu_callback +}; + +static int __init spawn_watchdog_task(void) +{ + void *cpu = (void *)(long)smp_processor_id(); + int err; + + if (no_watchdog) + return 0; + + err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu); + WARN_ON(err == NOTIFY_BAD); + + cpu_callback(&cpu_nfb, CPU_ONLINE, cpu); + register_cpu_notifier(&cpu_nfb); + + atomic_notifier_chain_register(&panic_notifier_list, &panic_block); + + return 0; +} +early_initcall(spawn_watchdog_task); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 220ae6063b6f..49e285dcaf57 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -153,7 +153,7 @@ config DEBUG_SHIRQ points; some don't and need to be caught. config DETECT_SOFTLOCKUP - bool "Detect Soft Lockups" + bool depends on DEBUG_KERNEL && !S390 default y help @@ -171,17 +171,27 @@ config DETECT_SOFTLOCKUP can be detected via the NMI-watchdog, on platforms that support it.) -config NMI_WATCHDOG - bool "Detect Hard Lockups with an NMI Watchdog" - depends on DEBUG_KERNEL && PERF_EVENTS && PERF_EVENTS_NMI +config LOCKUP_DETECTOR + bool "Detect Hard and Soft Lockups" + depends on DEBUG_KERNEL + default DETECT_SOFTLOCKUP help - Say Y here to enable the kernel to use the NMI as a watchdog - to detect hard lockups. This is useful when a cpu hangs for no - reason but can still respond to NMIs. A backtrace is displayed - for reviewing and reporting. + Say Y here to enable the kernel to act as a watchdog to detect + hard and soft lockups. + + Softlockups are bugs that cause the kernel to loop in kernel + mode for more than 60 seconds, without giving other tasks a + chance to run. The current stack trace is displayed upon + detection and the system will stay locked up. + + Hardlockups are bugs that cause the CPU to loop in kernel mode + for more than 60 seconds, without letting other interrupts have a + chance to run. The current stack trace is displayed upon detection + and the system will stay locked up. - The overhead should be minimal, just an extra NMI every few - seconds. + The overhead should be minimal. A periodic hrtimer runs to + generate interrupts and kick the watchdog task every 10-12 seconds. + An NMI is generated every 60 seconds or so to check for hardlockups. config BOOTPARAM_SOFTLOCKUP_PANIC bool "Panic (Reboot) On Soft Lockups" -- cgit v1.2.3 From 181a51f6e040d0ac006d6adaf4a031ffa440f41c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 20 Jul 2010 22:09:02 +0200 Subject: slow-work: kill it slow-work doesn't have any user left. Kill it. Signed-off-by: Tejun Heo Acked-by: David Howells --- Documentation/slow-work.txt | 322 ------------- include/linux/slow-work.h | 163 ------- init/Kconfig | 24 - kernel/Makefile | 2 - kernel/slow-work-debugfs.c | 227 --------- kernel/slow-work.c | 1068 ------------------------------------------- kernel/slow-work.h | 72 --- kernel/sysctl.c | 8 - 8 files changed, 1886 deletions(-) delete mode 100644 Documentation/slow-work.txt delete mode 100644 include/linux/slow-work.h delete mode 100644 kernel/slow-work-debugfs.c delete mode 100644 kernel/slow-work.c delete mode 100644 kernel/slow-work.h (limited to 'kernel/Makefile') diff --git a/Documentation/slow-work.txt b/Documentation/slow-work.txt deleted file mode 100644 index 9dbf4470c7e1..000000000000 --- a/Documentation/slow-work.txt +++ /dev/null @@ -1,322 +0,0 @@ - ==================================== - SLOW WORK ITEM EXECUTION THREAD POOL - ==================================== - -By: David Howells - -The slow work item execution thread pool is a pool of threads for performing -things that take a relatively long time, such as making mkdir calls. -Typically, when processing something, these items will spend a lot of time -blocking a thread on I/O, thus making that thread unavailable for doing other -work. - -The standard workqueue model is unsuitable for this class of work item as that -limits the owner to a single thread or a single thread per CPU. For some -tasks, however, more threads - or fewer - are required. - -There is just one pool per system. It contains no threads unless something -wants to use it - and that something must register its interest first. When -the pool is active, the number of threads it contains is dynamic, varying -between a maximum and minimum setting, depending on the load. - - -==================== -CLASSES OF WORK ITEM -==================== - -This pool support two classes of work items: - - (*) Slow work items. - - (*) Very slow work items. - -The former are expected to finish much quicker than the latter. - -An operation of the very slow class may do a batch combination of several -lookups, mkdirs, and a create for instance. - -An operation of the ordinarily slow class may, for example, write stuff or -expand files, provided the time taken to do so isn't too long. - -Operations of both types may sleep during execution, thus tying up the thread -loaned to it. - -A further class of work item is available, based on the slow work item class: - - (*) Delayed slow work items. - -These are slow work items that have a timer to defer queueing of the item for -a while. - - -THREAD-TO-CLASS ALLOCATION --------------------------- - -Not all the threads in the pool are available to work on very slow work items. -The number will be between one and one fewer than the number of active threads. -This is configurable (see the "Pool Configuration" section). - -All the threads are available to work on ordinarily slow work items, but a -percentage of the threads will prefer to work on very slow work items. - -The configuration ensures that at least one thread will be available to work on -very slow work items, and at least one thread will be available that won't work -on very slow work items at all. - - -===================== -USING SLOW WORK ITEMS -===================== - -Firstly, a module or subsystem wanting to make use of slow work items must -register its interest: - - int ret = slow_work_register_user(struct module *module); - -This will return 0 if successful, or a -ve error upon failure. The module -pointer should be the module interested in using this facility (almost -certainly THIS_MODULE). - - -Slow work items may then be set up by: - - (1) Declaring a slow_work struct type variable: - - #include - - struct slow_work myitem; - - (2) Declaring the operations to be used for this item: - - struct slow_work_ops myitem_ops = { - .get_ref = myitem_get_ref, - .put_ref = myitem_put_ref, - .execute = myitem_execute, - }; - - [*] For a description of the ops, see section "Item Operations". - - (3) Initialising the item: - - slow_work_init(&myitem, &myitem_ops); - - or: - - delayed_slow_work_init(&myitem, &myitem_ops); - - or: - - vslow_work_init(&myitem, &myitem_ops); - - depending on its class. - -A suitably set up work item can then be enqueued for processing: - - int ret = slow_work_enqueue(&myitem); - -This will return a -ve error if the thread pool is unable to gain a reference -on the item, 0 otherwise, or (for delayed work): - - int ret = delayed_slow_work_enqueue(&myitem, my_jiffy_delay); - - -The items are reference counted, so there ought to be no need for a flush -operation. But as the reference counting is optional, means to cancel -existing work items are also included: - - cancel_slow_work(&myitem); - cancel_delayed_slow_work(&myitem); - -can be used to cancel pending work. The above cancel function waits for -existing work to have been executed (or prevent execution of them, depending -on timing). - - -When all a module's slow work items have been processed, and the -module has no further interest in the facility, it should unregister its -interest: - - slow_work_unregister_user(struct module *module); - -The module pointer is used to wait for all outstanding work items for that -module before completing the unregistration. This prevents the put_ref() code -from being taken away before it completes. module should almost certainly be -THIS_MODULE. - - -================ -HELPER FUNCTIONS -================ - -The slow-work facility provides a function by which it can be determined -whether or not an item is queued for later execution: - - bool queued = slow_work_is_queued(struct slow_work *work); - -If it returns false, then the item is not on the queue (it may be executing -with a requeue pending). This can be used to work out whether an item on which -another depends is on the queue, thus allowing a dependent item to be queued -after it. - -If the above shows an item on which another depends not to be queued, then the -owner of the dependent item might need to wait. However, to avoid locking up -the threads unnecessarily be sleeping in them, it can make sense under some -circumstances to return the work item to the queue, thus deferring it until -some other items have had a chance to make use of the yielded thread. - -To yield a thread and defer an item, the work function should simply enqueue -the work item again and return. However, this doesn't work if there's nothing -actually on the queue, as the thread just vacated will jump straight back into -the item's work function, thus busy waiting on a CPU. - -Instead, the item should use the thread to wait for the dependency to go away, -but rather than using schedule() or schedule_timeout() to sleep, it should use -the following function: - - bool requeue = slow_work_sleep_till_thread_needed( - struct slow_work *work, - signed long *_timeout); - -This will add a second wait and then sleep, such that it will be woken up if -either something appears on the queue that could usefully make use of the -thread - and behind which this item can be queued, or if the event the caller -set up to wait for happens. True will be returned if something else appeared -on the queue and this work function should perhaps return, of false if -something else woke it up. The timeout is as for schedule_timeout(). - -For example: - - wq = bit_waitqueue(&my_flags, MY_BIT); - init_wait(&wait); - requeue = false; - do { - prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE); - if (!test_bit(MY_BIT, &my_flags)) - break; - requeue = slow_work_sleep_till_thread_needed(&my_work, - &timeout); - } while (timeout > 0 && !requeue); - finish_wait(wq, &wait); - if (!test_bit(MY_BIT, &my_flags) - goto do_my_thing; - if (requeue) - return; // to slow_work - - -=============== -ITEM OPERATIONS -=============== - -Each work item requires a table of operations of type struct slow_work_ops. -Only ->execute() is required; the getting and putting of a reference and the -describing of an item are all optional. - - (*) Get a reference on an item: - - int (*get_ref)(struct slow_work *work); - - This allows the thread pool to attempt to pin an item by getting a - reference on it. This function should return 0 if the reference was - granted, or a -ve error otherwise. If an error is returned, - slow_work_enqueue() will fail. - - The reference is held whilst the item is queued and whilst it is being - executed. The item may then be requeued with the same reference held, or - the reference will be released. - - (*) Release a reference on an item: - - void (*put_ref)(struct slow_work *work); - - This allows the thread pool to unpin an item by releasing the reference on - it. The thread pool will not touch the item again once this has been - called. - - (*) Execute an item: - - void (*execute)(struct slow_work *work); - - This should perform the work required of the item. It may sleep, it may - perform disk I/O and it may wait for locks. - - (*) View an item through /proc: - - void (*desc)(struct slow_work *work, struct seq_file *m); - - If supplied, this should print to 'm' a small string describing the work - the item is to do. This should be no more than about 40 characters, and - shouldn't include a newline character. - - See the 'Viewing executing and queued items' section below. - - -================== -POOL CONFIGURATION -================== - -The slow-work thread pool has a number of configurables: - - (*) /proc/sys/kernel/slow-work/min-threads - - The minimum number of threads that should be in the pool whilst it is in - use. This may be anywhere between 2 and max-threads. - - (*) /proc/sys/kernel/slow-work/max-threads - - The maximum number of threads that should in the pool. This may be - anywhere between min-threads and 255 or NR_CPUS * 2, whichever is greater. - - (*) /proc/sys/kernel/slow-work/vslow-percentage - - The percentage of active threads in the pool that may be used to execute - very slow work items. This may be between 1 and 99. The resultant number - is bounded to between 1 and one fewer than the number of active threads. - This ensures there is always at least one thread that can process very - slow work items, and always at least one thread that won't. - - -================================== -VIEWING EXECUTING AND QUEUED ITEMS -================================== - -If CONFIG_SLOW_WORK_DEBUG is enabled, a debugfs file is made available: - - /sys/kernel/debug/slow_work/runqueue - -through which the list of work items being executed and the queues of items to -be executed may be viewed. The owner of a work item is given the chance to -add some information of its own. - -The contents look something like the following: - - THR PID ITEM ADDR FL MARK DESC - === ===== ================ == ===== ========== - 0 3005 ffff880023f52348 a 952ms FSC: OBJ17d3: LOOK - 1 3006 ffff880024e33668 2 160ms FSC: OBJ17e5 OP60d3b: Write1/Store fl=2 - 2 3165 ffff8800296dd180 a 424ms FSC: OBJ17e4: LOOK - 3 4089 ffff8800262c8d78 a 212ms FSC: OBJ17ea: CRTN - 4 4090 ffff88002792bed8 2 388ms FSC: OBJ17e8 OP60d36: Write1/Store fl=2 - 5 4092 ffff88002a0ef308 2 388ms FSC: OBJ17e7 OP60d2e: Write1/Store fl=2 - 6 4094 ffff88002abaf4b8 2 132ms FSC: OBJ17e2 OP60d4e: Write1/Store fl=2 - 7 4095 ffff88002bb188e0 a 388ms FSC: OBJ17e9: CRTN - vsq - ffff880023d99668 1 308ms FSC: OBJ17e0 OP60f91: Write1/EnQ fl=2 - vsq - ffff8800295d1740 1 212ms FSC: OBJ16be OP4d4b6: Write1/EnQ fl=2 - vsq - ffff880025ba3308 1 160ms FSC: OBJ179a OP58dec: Write1/EnQ fl=2 - vsq - ffff880024ec83e0 1 160ms FSC: OBJ17ae OP599f2: Write1/EnQ fl=2 - vsq - ffff880026618e00 1 160ms FSC: OBJ17e6 OP60d33: Write1/EnQ fl=2 - vsq - ffff880025a2a4b8 1 132ms FSC: OBJ16a2 OP4d583: Write1/EnQ fl=2 - vsq - ffff880023cbe6d8 9 212ms FSC: OBJ17eb: LOOK - vsq - ffff880024d37590 9 212ms FSC: OBJ17ec: LOOK - vsq - ffff880027746cb0 9 212ms FSC: OBJ17ed: LOOK - vsq - ffff880024d37ae8 9 212ms FSC: OBJ17ee: LOOK - vsq - ffff880024d37cb0 9 212ms FSC: OBJ17ef: LOOK - vsq - ffff880025036550 9 212ms FSC: OBJ17f0: LOOK - vsq - ffff8800250368e0 9 212ms FSC: OBJ17f1: LOOK - vsq - ffff880025036aa8 9 212ms FSC: OBJ17f2: LOOK - -In the 'THR' column, executing items show the thread they're occupying and -queued threads indicate which queue they're on. 'PID' shows the process ID of -a slow-work thread that's executing something. 'FL' shows the work item flags. -'MARK' indicates how long since an item was queued or began executing. Lastly, -the 'DESC' column permits the owner of an item to give some information. - diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h deleted file mode 100644 index 13337bf6c3f5..000000000000 --- a/include/linux/slow-work.h +++ /dev/null @@ -1,163 +0,0 @@ -/* Worker thread pool for slow items, such as filesystem lookups or mkdirs - * - * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. - * - * See Documentation/slow-work.txt - */ - -#ifndef _LINUX_SLOW_WORK_H -#define _LINUX_SLOW_WORK_H - -#ifdef CONFIG_SLOW_WORK - -#include -#include - -struct slow_work; -#ifdef CONFIG_SLOW_WORK_DEBUG -struct seq_file; -#endif - -/* - * The operations used to support slow work items - */ -struct slow_work_ops { - /* owner */ - struct module *owner; - - /* get a ref on a work item - * - return 0 if successful, -ve if not - */ - int (*get_ref)(struct slow_work *work); - - /* discard a ref to a work item */ - void (*put_ref)(struct slow_work *work); - - /* execute a work item */ - void (*execute)(struct slow_work *work); - -#ifdef CONFIG_SLOW_WORK_DEBUG - /* describe a work item for debugfs */ - void (*desc)(struct slow_work *work, struct seq_file *m); -#endif -}; - -/* - * A slow work item - * - A reference is held on the parent object by the thread pool when it is - * queued - */ -struct slow_work { - struct module *owner; /* the owning module */ - unsigned long flags; -#define SLOW_WORK_PENDING 0 /* item pending (further) execution */ -#define SLOW_WORK_EXECUTING 1 /* item currently executing */ -#define SLOW_WORK_ENQ_DEFERRED 2 /* item enqueue deferred */ -#define SLOW_WORK_VERY_SLOW 3 /* item is very slow */ -#define SLOW_WORK_CANCELLING 4 /* item is being cancelled, don't enqueue */ -#define SLOW_WORK_DELAYED 5 /* item is struct delayed_slow_work with active timer */ - const struct slow_work_ops *ops; /* operations table for this item */ - struct list_head link; /* link in queue */ -#ifdef CONFIG_SLOW_WORK_DEBUG - struct timespec mark; /* jiffies at which queued or exec begun */ -#endif -}; - -struct delayed_slow_work { - struct slow_work work; - struct timer_list timer; -}; - -/** - * slow_work_init - Initialise a slow work item - * @work: The work item to initialise - * @ops: The operations to use to handle the slow work item - * - * Initialise a slow work item. - */ -static inline void slow_work_init(struct slow_work *work, - const struct slow_work_ops *ops) -{ - work->flags = 0; - work->ops = ops; - INIT_LIST_HEAD(&work->link); -} - -/** - * slow_work_init - Initialise a delayed slow work item - * @work: The work item to initialise - * @ops: The operations to use to handle the slow work item - * - * Initialise a delayed slow work item. - */ -static inline void delayed_slow_work_init(struct delayed_slow_work *dwork, - const struct slow_work_ops *ops) -{ - init_timer(&dwork->timer); - slow_work_init(&dwork->work, ops); -} - -/** - * vslow_work_init - Initialise a very slow work item - * @work: The work item to initialise - * @ops: The operations to use to handle the slow work item - * - * Initialise a very slow work item. This item will be restricted such that - * only a certain number of the pool threads will be able to execute items of - * this type. - */ -static inline void vslow_work_init(struct slow_work *work, - const struct slow_work_ops *ops) -{ - work->flags = 1 << SLOW_WORK_VERY_SLOW; - work->ops = ops; - INIT_LIST_HEAD(&work->link); -} - -/** - * slow_work_is_queued - Determine if a slow work item is on the work queue - * work: The work item to test - * - * Determine if the specified slow-work item is on the work queue. This - * returns true if it is actually on the queue. - * - * If the item is executing and has been marked for requeue when execution - * finishes, then false will be returned. - * - * Anyone wishing to wait for completion of execution can wait on the - * SLOW_WORK_EXECUTING bit. - */ -static inline bool slow_work_is_queued(struct slow_work *work) -{ - unsigned long flags = work->flags; - return flags & SLOW_WORK_PENDING && !(flags & SLOW_WORK_EXECUTING); -} - -extern int slow_work_enqueue(struct slow_work *work); -extern void slow_work_cancel(struct slow_work *work); -extern int slow_work_register_user(struct module *owner); -extern void slow_work_unregister_user(struct module *owner); - -extern int delayed_slow_work_enqueue(struct delayed_slow_work *dwork, - unsigned long delay); - -static inline void delayed_slow_work_cancel(struct delayed_slow_work *dwork) -{ - slow_work_cancel(&dwork->work); -} - -extern bool slow_work_sleep_till_thread_needed(struct slow_work *work, - signed long *_timeout); - -#ifdef CONFIG_SYSCTL -extern ctl_table slow_work_sysctls[]; -#endif - -#endif /* CONFIG_SLOW_WORK */ -#endif /* _LINUX_SLOW_WORK_H */ diff --git a/init/Kconfig b/init/Kconfig index 5cff9a980c39..cb64c5889e02 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1143,30 +1143,6 @@ config TRACEPOINTS source "arch/Kconfig" -config SLOW_WORK - default n - bool - help - The slow work thread pool provides a number of dynamically allocated - threads that can be used by the kernel to perform operations that - take a relatively long time. - - An example of this would be CacheFiles doing a path lookup followed - by a series of mkdirs and a create call, all of which have to touch - disk. - - See Documentation/slow-work.txt. - -config SLOW_WORK_DEBUG - bool "Slow work debugging through debugfs" - default n - depends on SLOW_WORK && DEBUG_FS - help - Display the contents of the slow work run queue through debugfs, - including items currently executing. - - See Documentation/slow-work.txt. - endmenu # General setup config HAVE_GENERIC_DMA_COHERENT diff --git a/kernel/Makefile b/kernel/Makefile index 057472fbc272..2484ac39b2e2 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -99,8 +99,6 @@ obj-$(CONFIG_TRACING) += trace/ obj-$(CONFIG_X86_DS) += trace/ obj-$(CONFIG_RING_BUFFER) += trace/ obj-$(CONFIG_SMP) += sched_cpupri.o -obj-$(CONFIG_SLOW_WORK) += slow-work.o -obj-$(CONFIG_SLOW_WORK_DEBUG) += slow-work-debugfs.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o diff --git a/kernel/slow-work-debugfs.c b/kernel/slow-work-debugfs.c deleted file mode 100644 index e45c43645298..000000000000 --- a/kernel/slow-work-debugfs.c +++ /dev/null @@ -1,227 +0,0 @@ -/* Slow work debugging - * - * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. - */ - -#include -#include -#include -#include -#include -#include "slow-work.h" - -#define ITERATOR_SHIFT (BITS_PER_LONG - 4) -#define ITERATOR_SELECTOR (0xfUL << ITERATOR_SHIFT) -#define ITERATOR_COUNTER (~ITERATOR_SELECTOR) - -void slow_work_new_thread_desc(struct slow_work *work, struct seq_file *m) -{ - seq_puts(m, "Slow-work: New thread"); -} - -/* - * Render the time mark field on a work item into a 5-char time with units plus - * a space - */ -static void slow_work_print_mark(struct seq_file *m, struct slow_work *work) -{ - struct timespec now, diff; - - now = CURRENT_TIME; - diff = timespec_sub(now, work->mark); - - if (diff.tv_sec < 0) - seq_puts(m, " -ve "); - else if (diff.tv_sec == 0 && diff.tv_nsec < 1000) - seq_printf(m, "%3luns ", diff.tv_nsec); - else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000) - seq_printf(m, "%3luus ", diff.tv_nsec / 1000); - else if (diff.tv_sec == 0 && diff.tv_nsec < 1000000000) - seq_printf(m, "%3lums ", diff.tv_nsec / 1000000); - else if (diff.tv_sec <= 1) - seq_puts(m, " 1s "); - else if (diff.tv_sec < 60) - seq_printf(m, "%4lus ", diff.tv_sec); - else if (diff.tv_sec < 60 * 60) - seq_printf(m, "%4lum ", diff.tv_sec / 60); - else if (diff.tv_sec < 60 * 60 * 24) - seq_printf(m, "%4luh ", diff.tv_sec / 3600); - else - seq_puts(m, "exces "); -} - -/* - * Describe a slow work item for debugfs - */ -static int slow_work_runqueue_show(struct seq_file *m, void *v) -{ - struct slow_work *work; - struct list_head *p = v; - unsigned long id; - - switch ((unsigned long) v) { - case 1: - seq_puts(m, "THR PID ITEM ADDR FL MARK DESC\n"); - return 0; - case 2: - seq_puts(m, "=== ===== ================ == ===== ==========\n"); - return 0; - - case 3 ... 3 + SLOW_WORK_THREAD_LIMIT - 1: - id = (unsigned long) v - 3; - - read_lock(&slow_work_execs_lock); - work = slow_work_execs[id]; - if (work) { - smp_read_barrier_depends(); - - seq_printf(m, "%3lu %5d %16p %2lx ", - id, slow_work_pids[id], work, work->flags); - slow_work_print_mark(m, work); - - if (work->ops->desc) - work->ops->desc(work, m); - seq_putc(m, '\n'); - } - read_unlock(&slow_work_execs_lock); - return 0; - - default: - work = list_entry(p, struct slow_work, link); - seq_printf(m, "%3s - %16p %2lx ", - work->flags & SLOW_WORK_VERY_SLOW ? "vsq" : "sq", - work, work->flags); - slow_work_print_mark(m, work); - - if (work->ops->desc) - work->ops->desc(work, m); - seq_putc(m, '\n'); - return 0; - } -} - -/* - * map the iterator to a work item - */ -static void *slow_work_runqueue_index(struct seq_file *m, loff_t *_pos) -{ - struct list_head *p; - unsigned long count, id; - - switch (*_pos >> ITERATOR_SHIFT) { - case 0x0: - if (*_pos == 0) - *_pos = 1; - if (*_pos < 3) - return (void *)(unsigned long) *_pos; - if (*_pos < 3 + SLOW_WORK_THREAD_LIMIT) - for (id = *_pos - 3; - id < SLOW_WORK_THREAD_LIMIT; - id++, (*_pos)++) - if (slow_work_execs[id]) - return (void *)(unsigned long) *_pos; - *_pos = 0x1UL << ITERATOR_SHIFT; - - case 0x1: - count = *_pos & ITERATOR_COUNTER; - list_for_each(p, &slow_work_queue) { - if (count == 0) - return p; - count--; - } - *_pos = 0x2UL << ITERATOR_SHIFT; - - case 0x2: - count = *_pos & ITERATOR_COUNTER; - list_for_each(p, &vslow_work_queue) { - if (count == 0) - return p; - count--; - } - *_pos = 0x3UL << ITERATOR_SHIFT; - - default: - return NULL; - } -} - -/* - * set up the iterator to start reading from the first line - */ -static void *slow_work_runqueue_start(struct seq_file *m, loff_t *_pos) -{ - spin_lock_irq(&slow_work_queue_lock); - return slow_work_runqueue_index(m, _pos); -} - -/* - * move to the next line - */ -static void *slow_work_runqueue_next(struct seq_file *m, void *v, loff_t *_pos) -{ - struct list_head *p = v; - unsigned long selector = *_pos >> ITERATOR_SHIFT; - - (*_pos)++; - switch (selector) { - case 0x0: - return slow_work_runqueue_index(m, _pos); - - case 0x1: - if (*_pos >> ITERATOR_SHIFT == 0x1) { - p = p->next; - if (p != &slow_work_queue) - return p; - } - *_pos = 0x2UL << ITERATOR_SHIFT; - p = &vslow_work_queue; - - case 0x2: - if (*_pos >> ITERATOR_SHIFT == 0x2) { - p = p->next; - if (p != &vslow_work_queue) - return p; - } - *_pos = 0x3UL << ITERATOR_SHIFT; - - default: - return NULL; - } -} - -/* - * clean up after reading - */ -static void slow_work_runqueue_stop(struct seq_file *m, void *v) -{ - spin_unlock_irq(&slow_work_queue_lock); -} - -static const struct seq_operations slow_work_runqueue_ops = { - .start = slow_work_runqueue_start, - .stop = slow_work_runqueue_stop, - .next = slow_work_runqueue_next, - .show = slow_work_runqueue_show, -}; - -/* - * open "/sys/kernel/debug/slow_work/runqueue" to list queue contents - */ -static int slow_work_runqueue_open(struct inode *inode, struct file *file) -{ - return seq_open(file, &slow_work_runqueue_ops); -} - -const struct file_operations slow_work_runqueue_fops = { - .owner = THIS_MODULE, - .open = slow_work_runqueue_open, - .read = seq_read, - .llseek = seq_lseek, - .release = seq_release, -}; diff --git a/kernel/slow-work.c b/kernel/slow-work.c deleted file mode 100644 index 7d3f4fa9ef4f..000000000000 --- a/kernel/slow-work.c +++ /dev/null @@ -1,1068 +0,0 @@ -/* Worker thread pool for slow items, such as filesystem lookups or mkdirs - * - * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. - * - * See Documentation/slow-work.txt - */ - -#include -#include -#include -#include -#include -#include -#include "slow-work.h" - -static void slow_work_cull_timeout(unsigned long); -static void slow_work_oom_timeout(unsigned long); - -#ifdef CONFIG_SYSCTL -static int slow_work_min_threads_sysctl(struct ctl_table *, int, - void __user *, size_t *, loff_t *); - -static int slow_work_max_threads_sysctl(struct ctl_table *, int , - void __user *, size_t *, loff_t *); -#endif - -/* - * The pool of threads has at least min threads in it as long as someone is - * using the facility, and may have as many as max. - * - * A portion of the pool may be processing very slow operations. - */ -static unsigned slow_work_min_threads = 2; -static unsigned slow_work_max_threads = 4; -static unsigned vslow_work_proportion = 50; /* % of threads that may process - * very slow work */ - -#ifdef CONFIG_SYSCTL -static const int slow_work_min_min_threads = 2; -static int slow_work_max_max_threads = SLOW_WORK_THREAD_LIMIT; -static const int slow_work_min_vslow = 1; -static const int slow_work_max_vslow = 99; - -ctl_table slow_work_sysctls[] = { - { - .procname = "min-threads", - .data = &slow_work_min_threads, - .maxlen = sizeof(unsigned), - .mode = 0644, - .proc_handler = slow_work_min_threads_sysctl, - .extra1 = (void *) &slow_work_min_min_threads, - .extra2 = &slow_work_max_threads, - }, - { - .procname = "max-threads", - .data = &slow_work_max_threads, - .maxlen = sizeof(unsigned), - .mode = 0644, - .proc_handler = slow_work_max_threads_sysctl, - .extra1 = &slow_work_min_threads, - .extra2 = (void *) &slow_work_max_max_threads, - }, - { - .procname = "vslow-percentage", - .data = &vslow_work_proportion, - .maxlen = sizeof(unsigned), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = (void *) &slow_work_min_vslow, - .extra2 = (void *) &slow_work_max_vslow, - }, - {} -}; -#endif - -/* - * The active state of the thread pool - */ -static atomic_t slow_work_thread_count; -static atomic_t vslow_work_executing_count; - -static bool slow_work_may_not_start_new_thread; -static bool slow_work_cull; /* cull a thread due to lack of activity */ -static DEFINE_TIMER(slow_work_cull_timer, slow_work_cull_timeout, 0, 0); -static DEFINE_TIMER(slow_work_oom_timer, slow_work_oom_timeout, 0, 0); -static struct slow_work slow_work_new_thread; /* new thread starter */ - -/* - * slow work ID allocation (use slow_work_queue_lock) - */ -static DECLARE_BITMAP(slow_work_ids, SLOW_WORK_THREAD_LIMIT); - -/* - * Unregistration tracking to prevent put_ref() from disappearing during module - * unload - */ -#ifdef CONFIG_MODULES -static struct module *slow_work_thread_processing[SLOW_WORK_THREAD_LIMIT]; -static struct module *slow_work_unreg_module; -static struct slow_work *slow_work_unreg_work_item; -static DECLARE_WAIT_QUEUE_HEAD(slow_work_unreg_wq); -static DEFINE_MUTEX(slow_work_unreg_sync_lock); - -static void slow_work_set_thread_processing(int id, struct slow_work *work) -{ - if (work) - slow_work_thread_processing[id] = work->owner; -} -static void slow_work_done_thread_processing(int id, struct slow_work *work) -{ - struct module *module = slow_work_thread_processing[id]; - - slow_work_thread_processing[id] = NULL; - smp_mb(); - if (slow_work_unreg_work_item == work || - slow_work_unreg_module == module) - wake_up_all(&slow_work_unreg_wq); -} -static void slow_work_clear_thread_processing(int id) -{ - slow_work_thread_processing[id] = NULL; -} -#else -static void slow_work_set_thread_processing(int id, struct slow_work *work) {} -static void slow_work_done_thread_processing(int id, struct slow_work *work) {} -static void slow_work_clear_thread_processing(int id) {} -#endif - -/* - * Data for tracking currently executing items for indication through /proc - */ -#ifdef CONFIG_SLOW_WORK_DEBUG -struct slow_work *slow_work_execs[SLOW_WORK_THREAD_LIMIT]; -pid_t slow_work_pids[SLOW_WORK_THREAD_LIMIT]; -DEFINE_RWLOCK(slow_work_execs_lock); -#endif - -/* - * The queues of work items and the lock governing access to them. These are - * shared between all the CPUs. It doesn't make sense to have per-CPU queues - * as the number of threads bears no relation to the number of CPUs. - * - * There are two queues of work items: one for slow work items, and one for - * very slow work items. - */ -LIST_HEAD(slow_work_queue); -LIST_HEAD(vslow_work_queue); -DEFINE_SPINLOCK(slow_work_queue_lock); - -/* - * The following are two wait queues that get pinged when a work item is placed - * on an empty queue. These allow work items that are hogging a thread by - * sleeping in a way that could be deferred to yield their thread and enqueue - * themselves. - */ -static DECLARE_WAIT_QUEUE_HEAD(slow_work_queue_waits_for_occupation); -static DECLARE_WAIT_QUEUE_HEAD(vslow_work_queue_waits_for_occupation); - -/* - * The thread controls. A variable used to signal to the threads that they - * should exit when the queue is empty, a waitqueue used by the threads to wait - * for signals, and a completion set by the last thread to exit. - */ -static bool slow_work_threads_should_exit; -static DECLARE_WAIT_QUEUE_HEAD(slow_work_thread_wq); -static DECLARE_COMPLETION(slow_work_last_thread_exited); - -/* - * The number of users of the thread pool and its lock. Whilst this is zero we - * have no threads hanging around, and when this reaches zero, we wait for all - * active or queued work items to complete and kill all the threads we do have. - */ -static int slow_work_user_count; -static DEFINE_MUTEX(slow_work_user_lock); - -static inline int slow_work_get_ref(struct slow_work *work) -{ - if (work->ops->get_ref) - return work->ops->get_ref(work); - - return 0; -} - -static inline void slow_work_put_ref(struct slow_work *work) -{ - if (work->ops->put_ref) - work->ops->put_ref(work); -} - -/* - * Calculate the maximum number of active threads in the pool that are - * permitted to process very slow work items. - * - * The answer is rounded up to at least 1, but may not equal or exceed the - * maximum number of the threads in the pool. This means we always have at - * least one thread that can process slow work items, and we always have at - * least one thread that won't get tied up doing so. - */ -static unsigned slow_work_calc_vsmax(void) -{ - unsigned vsmax; - - vsmax = atomic_read(&slow_work_thread_count) * vslow_work_proportion; - vsmax /= 100; - vsmax = max(vsmax, 1U); - return min(vsmax, slow_work_max_threads - 1); -} - -/* - * Attempt to execute stuff queued on a slow thread. Return true if we managed - * it, false if there was nothing to do. - */ -static noinline bool slow_work_execute(int id) -{ - struct slow_work *work = NULL; - unsigned vsmax; - bool very_slow; - - vsmax = slow_work_calc_vsmax(); - - /* see if we can schedule a new thread to be started if we're not - * keeping up with the work */ - if (!waitqueue_active(&slow_work_thread_wq) && - (!list_empty(&slow_work_queue) || !list_empty(&vslow_work_queue)) && - atomic_read(&slow_work_thread_count) < slow_work_max_threads && - !slow_work_may_not_start_new_thread) - slow_work_enqueue(&slow_work_new_thread); - - /* find something to execute */ - spin_lock_irq(&slow_work_queue_lock); - if (!list_empty(&vslow_work_queue) && - atomic_read(&vslow_work_executing_count) < vsmax) { - work = list_entry(vslow_work_queue.next, - struct slow_work, link); - if (test_and_set_bit_lock(SLOW_WORK_EXECUTING, &work->flags)) - BUG(); - list_del_init(&work->link); - atomic_inc(&vslow_work_executing_count); - very_slow = true; - } else if (!list_empty(&slow_work_queue)) { - work = list_entry(slow_work_queue.next, - struct slow_work, link); - if (test_and_set_bit_lock(SLOW_WORK_EXECUTING, &work->flags)) - BUG(); - list_del_init(&work->link); - very_slow = false; - } else { - very_slow = false; /* avoid the compiler warning */ - } - - slow_work_set_thread_processing(id, work); - if (work) { - slow_work_mark_time(work); - slow_work_begin_exec(id, work); - } - - spin_unlock_irq(&slow_work_queue_lock); - - if (!work) - return false; - - if (!test_and_clear_bit(SLOW_WORK_PENDING, &work->flags)) - BUG(); - - /* don't execute if the work is in the process of being cancelled */ - if (!test_bit(SLOW_WORK_CANCELLING, &work->flags)) - work->ops->execute(work); - - if (very_slow) - atomic_dec(&vslow_work_executing_count); - clear_bit_unlock(SLOW_WORK_EXECUTING, &work->flags); - - /* wake up anyone waiting for this work to be complete */ - wake_up_bit(&work->flags, SLOW_WORK_EXECUTING); - - slow_work_end_exec(id, work); - - /* if someone tried to enqueue the item whilst we were executing it, - * then it'll be left unenqueued to avoid multiple threads trying to - * execute it simultaneously - * - * there is, however, a race between us testing the pending flag and - * getting the spinlock, and between the enqueuer setting the pending - * flag and getting the spinlock, so we use a deferral bit to tell us - * if the enqueuer got there first - */ - if (test_bit(SLOW_WORK_PENDING, &work->flags)) { - spin_lock_irq(&slow_work_queue_lock); - - if (!test_bit(SLOW_WORK_EXECUTING, &work->flags) && - test_and_clear_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags)) - goto auto_requeue; - - spin_unlock_irq(&slow_work_queue_lock); - } - - /* sort out the race between module unloading and put_ref() */ - slow_work_put_ref(work); - slow_work_done_thread_processing(id, work); - - return true; - -auto_requeue: - /* we must complete the enqueue operation - * - we transfer our ref on the item back to the appropriate queue - * - don't wake another thread up as we're awake already - */ - slow_work_mark_time(work); - if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) - list_add_tail(&work->link, &vslow_work_queue); - else - list_add_tail(&work->link, &slow_work_queue); - spin_unlock_irq(&slow_work_queue_lock); - slow_work_clear_thread_processing(id); - return true; -} - -/** - * slow_work_sleep_till_thread_needed - Sleep till thread needed by other work - * work: The work item under execution that wants to sleep - * _timeout: Scheduler sleep timeout - * - * Allow a requeueable work item to sleep on a slow-work processor thread until - * that thread is needed to do some other work or the sleep is interrupted by - * some other event. - * - * The caller must set up a wake up event before calling this and must have set - * the appropriate sleep mode (such as TASK_UNINTERRUPTIBLE) and tested its own - * condition before calling this function as no test is made here. - * - * False is returned if there is nothing on the queue; true is returned if the - * work item should be requeued - */ -bool slow_work_sleep_till_thread_needed(struct slow_work *work, - signed long *_timeout) -{ - wait_queue_head_t *wfo_wq; - struct list_head *queue; - - DEFINE_WAIT(wait); - - if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) { - wfo_wq = &vslow_work_queue_waits_for_occupation; - queue = &vslow_work_queue; - } else { - wfo_wq = &slow_work_queue_waits_for_occupation; - queue = &slow_work_queue; - } - - if (!list_empty(queue)) - return true; - - add_wait_queue_exclusive(wfo_wq, &wait); - if (list_empty(queue)) - *_timeout = schedule_timeout(*_timeout); - finish_wait(wfo_wq, &wait); - - return !list_empty(queue); -} -EXPORT_SYMBOL(slow_work_sleep_till_thread_needed); - -/** - * slow_work_enqueue - Schedule a slow work item for processing - * @work: The work item to queue - * - * Schedule a slow work item for processing. If the item is already undergoing - * execution, this guarantees not to re-enter the execution routine until the - * first execution finishes. - * - * The item is pinned by this function as it retains a reference to it, managed - * through the item operations. The item is unpinned once it has been - * executed. - * - * An item may hog the thread that is running it for a relatively large amount - * of time, sufficient, for example, to perform several lookup, mkdir, create - * and setxattr operations. It may sleep on I/O and may sleep to obtain locks. - * - * Conversely, if a number of items are awaiting processing, it may take some - * time before any given item is given attention. The number of threads in the - * pool may be increased to deal with demand, but only up to a limit. - * - * If SLOW_WORK_VERY_SLOW is set on the work item, then it will be placed in - * the very slow queue, from which only a portion of the threads will be - * allowed to pick items to execute. This ensures that very slow items won't - * overly block ones that are just ordinarily slow. - * - * Returns 0 if successful, -EAGAIN if not (or -ECANCELED if cancelled work is - * attempted queued) - */ -int slow_work_enqueue(struct slow_work *work) -{ - wait_queue_head_t *wfo_wq; - struct list_head *queue; - unsigned long flags; - int ret; - - if (test_bit(SLOW_WORK_CANCELLING, &work->flags)) - return -ECANCELED; - - BUG_ON(slow_work_user_count <= 0); - BUG_ON(!work); - BUG_ON(!work->ops); - - /* when honouring an enqueue request, we only promise that we will run - * the work function in the future; we do not promise to run it once - * per enqueue request - * - * we use the PENDING bit to merge together repeat requests without - * having to disable IRQs and take the spinlock, whilst still - * maintaining our promise - */ - if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) { - if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) { - wfo_wq = &vslow_work_queue_waits_for_occupation; - queue = &vslow_work_queue; - } else { - wfo_wq = &slow_work_queue_waits_for_occupation; - queue = &slow_work_queue; - } - - spin_lock_irqsave(&slow_work_queue_lock, flags); - - if (unlikely(test_bit(SLOW_WORK_CANCELLING, &work->flags))) - goto cancelled; - - /* we promise that we will not attempt to execute the work - * function in more than one thread simultaneously - * - * this, however, leaves us with a problem if we're asked to - * enqueue the work whilst someone is executing the work - * function as simply queueing the work immediately means that - * another thread may try executing it whilst it is already - * under execution - * - * to deal with this, we set the ENQ_DEFERRED bit instead of - * enqueueing, and the thread currently executing the work - * function will enqueue the work item when the work function - * returns and it has cleared the EXECUTING bit - */ - if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) { - set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags); - } else { - ret = slow_work_get_ref(work); - if (ret < 0) - goto failed; - slow_work_mark_time(work); - list_add_tail(&work->link, queue); - wake_up(&slow_work_thread_wq); - - /* if someone who could be requeued is sleeping on a - * thread, then ask them to yield their thread */ - if (work->link.prev == queue) - wake_up(wfo_wq); - } - - spin_unlock_irqrestore(&slow_work_queue_lock, flags); - } - return 0; - -cancelled: - ret = -ECANCELED; -failed: - spin_unlock_irqrestore(&slow_work_queue_lock, flags); - return ret; -} -EXPORT_SYMBOL(slow_work_enqueue); - -static int slow_work_wait(void *word) -{ - schedule(); - return 0; -} - -/** - * slow_work_cancel - Cancel a slow work item - * @work: The work item to cancel - * - * This function will cancel a previously enqueued work item. If we cannot - * cancel the work item, it is guarenteed to have run when this function - * returns. - */ -void slow_work_cancel(struct slow_work *work) -{ - bool wait = true, put = false; - - set_bit(SLOW_WORK_CANCELLING, &work->flags); - smp_mb(); - - /* if the work item is a delayed work item with an active timer, we - * need to wait for the timer to finish _before_ getting the spinlock, - * lest we deadlock against the timer routine - * - * the timer routine will leave DELAYED set if it notices the - * CANCELLING flag in time - */ - if (test_bit(SLOW_WORK_DELAYED, &work->flags)) { - struct delayed_slow_work *dwork = - container_of(work, struct delayed_slow_work, work); - del_timer_sync(&dwork->timer); - } - - spin_lock_irq(&slow_work_queue_lock); - - if (test_bit(SLOW_WORK_DELAYED, &work->flags)) { - /* the timer routine aborted or never happened, so we are left - * holding the timer's reference on the item and should just - * drop the pending flag and wait for any ongoing execution to - * finish */ - struct delayed_slow_work *dwork = - container_of(work, struct delayed_slow_work, work); - - BUG_ON(timer_pending(&dwork->timer)); - BUG_ON(!list_empty(&work->link)); - - clear_bit(SLOW_WORK_DELAYED, &work->flags); - put = true; - clear_bit(SLOW_WORK_PENDING, &work->flags); - - } else if (test_bit(SLOW_WORK_PENDING, &work->flags) && - !list_empty(&work->link)) { - /* the link in the pending queue holds a reference on the item - * that we will need to release */ - list_del_init(&work->link); - wait = false; - put = true; - clear_bit(SLOW_WORK_PENDING, &work->flags); - - } else if (test_and_clear_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags)) { - /* the executor is holding our only reference on the item, so - * we merely need to wait for it to finish executing */ - clear_bit(SLOW_WORK_PENDING, &work->flags); - } - - spin_unlock_irq(&slow_work_queue_lock); - - /* the EXECUTING flag is set by the executor whilst the spinlock is set - * and before the item is dequeued - so assuming the above doesn't - * actually dequeue it, simply waiting for the EXECUTING flag to be - * released here should be sufficient */ - if (wait) - wait_on_bit(&work->flags, SLOW_WORK_EXECUTING, slow_work_wait, - TASK_UNINTERRUPTIBLE); - - clear_bit(SLOW_WORK_CANCELLING, &work->flags); - if (put) - slow_work_put_ref(work); -} -EXPORT_SYMBOL(slow_work_cancel); - -/* - * Handle expiry of the delay timer, indicating that a delayed slow work item - * should now be queued if not cancelled - */ -static void delayed_slow_work_timer(unsigned long data) -{ - wait_queue_head_t *wfo_wq; - struct list_head *queue; - struct slow_work *work = (struct slow_work *) data; - unsigned long flags; - bool queued = false, put = false, first = false; - - if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags)) { - wfo_wq = &vslow_work_queue_waits_for_occupation; - queue = &vslow_work_queue; - } else { - wfo_wq = &slow_work_queue_waits_for_occupation; - queue = &slow_work_queue; - } - - spin_lock_irqsave(&slow_work_queue_lock, flags); - if (likely(!test_bit(SLOW_WORK_CANCELLING, &work->flags))) { - clear_bit(SLOW_WORK_DELAYED, &work->flags); - - if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) { - /* we discard the reference the timer was holding in - * favour of the one the executor holds */ - set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags); - put = true; - } else { - slow_work_mark_time(work); - list_add_tail(&work->link, queue); - queued = true; - if (work->link.prev == queue) - first = true; - } - } - - spin_unlock_irqrestore(&slow_work_queue_lock, flags); - if (put) - slow_work_put_ref(work); - if (first) - wake_up(wfo_wq); - if (queued) - wake_up(&slow_work_thread_wq); -} - -/** - * delayed_slow_work_enqueue - Schedule a delayed slow work item for processing - * @dwork: The delayed work item to queue - * @delay: When to start executing the work, in jiffies from now - * - * This is similar to slow_work_enqueue(), but it adds a delay before the work - * is actually queued for processing. - * - * The item can have delayed processing requested on it whilst it is being - * executed. The delay will begin immediately, and if it expires before the - * item finishes executing, the item will be placed back on the queue when it - * has done executing. - */ -int delayed_slow_work_enqueue(struct delayed_slow_work *dwork, - unsigned long delay) -{ - struct slow_work *work = &dwork->work; - unsigned long flags; - int ret; - - if (delay == 0) - return slow_work_enqueue(&dwork->work); - - BUG_ON(slow_work_user_count <= 0); - BUG_ON(!work); - BUG_ON(!work->ops); - - if (test_bit(SLOW_WORK_CANCELLING, &work->flags)) - return -ECANCELED; - - if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) { - spin_lock_irqsave(&slow_work_queue_lock, flags); - - if (test_bit(SLOW_WORK_CANCELLING, &work->flags)) - goto cancelled; - - /* the timer holds a reference whilst it is pending */ - ret = slow_work_get_ref(work); - if (ret < 0) - goto cant_get_ref; - - if (test_and_set_bit(SLOW_WORK_DELAYED, &work->flags)) - BUG(); - dwork->timer.expires = jiffies + delay; - dwork->timer.data = (unsigned long) work; - dwork->timer.function = delayed_slow_work_timer; - add_timer(&dwork->timer); - - spin_unlock_irqrestore(&slow_work_queue_lock, flags); - } - - return 0; - -cancelled: - ret = -ECANCELED; -cant_get_ref: - spin_unlock_irqrestore(&slow_work_queue_lock, flags); - return ret; -} -EXPORT_SYMBOL(delayed_slow_work_enqueue); - -/* - * Schedule a cull of the thread pool at some time in the near future - */ -static void slow_work_schedule_cull(void) -{ - mod_timer(&slow_work_cull_timer, - round_jiffies(jiffies + SLOW_WORK_CULL_TIMEOUT)); -} - -/* - * Worker thread culling algorithm - */ -static bool slow_work_cull_thread(void) -{ - unsigned long flags; - bool do_cull = false; - - spin_lock_irqsave(&slow_work_queue_lock, flags); - - if (slow_work_cull) { - slow_work_cull = false; - - if (list_empty(&slow_work_queue) && - list_empty(&vslow_work_queue) && - atomic_read(&slow_work_thread_count) > - slow_work_min_threads) { - slow_work_schedule_cull(); - do_cull = true; - } - } - - spin_unlock_irqrestore(&slow_work_queue_lock, flags); - return do_cull; -} - -/* - * Determine if there is slow work available for dispatch - */ -static inline bool slow_work_available(int vsmax) -{ - return !list_empty(&slow_work_queue) || - (!list_empty(&vslow_work_queue) && - atomic_read(&vslow_work_executing_count) < vsmax); -} - -/* - * Worker thread dispatcher - */ -static int slow_work_thread(void *_data) -{ - int vsmax, id; - - DEFINE_WAIT(wait); - - set_freezable(); - set_user_nice(current, -5); - - /* allocate ourselves an ID */ - spin_lock_irq(&slow_work_queue_lock); - id = find_first_zero_bit(slow_work_ids, SLOW_WORK_THREAD_LIMIT); - BUG_ON(id < 0 || id >= SLOW_WORK_THREAD_LIMIT); - __set_bit(id, slow_work_ids); - slow_work_set_thread_pid(id, current->pid); - spin_unlock_irq(&slow_work_queue_lock); - - sprintf(current->comm, "kslowd%03u", id); - - for (;;) { - vsmax = vslow_work_proportion; - vsmax *= atomic_read(&slow_work_thread_count); - vsmax /= 100; - - prepare_to_wait_exclusive(&slow_work_thread_wq, &wait, - TASK_INTERRUPTIBLE); - if (!freezing(current) && - !slow_work_threads_should_exit && - !slow_work_available(vsmax) && - !slow_work_cull) - schedule(); - finish_wait(&slow_work_thread_wq, &wait); - - try_to_freeze(); - - vsmax = vslow_work_proportion; - vsmax *= atomic_read(&slow_work_thread_count); - vsmax /= 100; - - if (slow_work_available(vsmax) && slow_work_execute(id)) { - cond_resched(); - if (list_empty(&slow_work_queue) && - list_empty(&vslow_work_queue) && - atomic_read(&slow_work_thread_count) > - slow_work_min_threads) - slow_work_schedule_cull(); - continue; - } - - if (slow_work_threads_should_exit) - break; - - if (slow_work_cull && slow_work_cull_thread()) - break; - } - - spin_lock_irq(&slow_work_queue_lock); - slow_work_set_thread_pid(id, 0); - __clear_bit(id, slow_work_ids); - spin_unlock_irq(&slow_work_queue_lock); - - if (atomic_dec_and_test(&slow_work_thread_count)) - complete_and_exit(&slow_work_last_thread_exited, 0); - return 0; -} - -/* - * Handle thread cull timer expiration - */ -static void slow_work_cull_timeout(unsigned long data) -{ - slow_work_cull = true; - wake_up(&slow_work_thread_wq); -} - -/* - * Start a new slow work thread - */ -static void slow_work_new_thread_execute(struct slow_work *work) -{ - struct task_struct *p; - - if (slow_work_threads_should_exit) - return; - - if (atomic_read(&slow_work_thread_count) >= slow_work_max_threads) - return; - - if (!mutex_trylock(&slow_work_user_lock)) - return; - - slow_work_may_not_start_new_thread = true; - atomic_inc(&slow_work_thread_count); - p = kthread_run(slow_work_thread, NULL, "kslowd"); - if (IS_ERR(p)) { - printk(KERN_DEBUG "Slow work thread pool: OOM\n"); - if (atomic_dec_and_test(&slow_work_thread_count)) - BUG(); /* we're running on a slow work thread... */ - mod_timer(&slow_work_oom_timer, - round_jiffies(jiffies + SLOW_WORK_OOM_TIMEOUT)); - } else { - /* ratelimit the starting of new threads */ - mod_timer(&slow_work_oom_timer, jiffies + 1); - } - - mutex_unlock(&slow_work_user_lock); -} - -static const struct slow_work_ops slow_work_new_thread_ops = { - .owner = THIS_MODULE, - .execute = slow_work_new_thread_execute, -#ifdef CONFIG_SLOW_WORK_DEBUG - .desc = slow_work_new_thread_desc, -#endif -}; - -/* - * post-OOM new thread start suppression expiration - */ -static void slow_work_oom_timeout(unsigned long data) -{ - slow_work_may_not_start_new_thread = false; -} - -#ifdef CONFIG_SYSCTL -/* - * Handle adjustment of the minimum number of threads - */ -static int slow_work_min_threads_sysctl(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) -{ - int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - int n; - - if (ret == 0) { - mutex_lock(&slow_work_user_lock); - if (slow_work_user_count > 0) { - /* see if we need to start or stop threads */ - n = atomic_read(&slow_work_thread_count) - - slow_work_min_threads; - - if (n < 0 && !slow_work_may_not_start_new_thread) - slow_work_enqueue(&slow_work_new_thread); - else if (n > 0) - slow_work_schedule_cull(); - } - mutex_unlock(&slow_work_user_lock); - } - - return ret; -} - -/* - * Handle adjustment of the maximum number of threads - */ -static int slow_work_max_threads_sysctl(struct ctl_table *table, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) -{ - int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - int n; - - if (ret == 0) { - mutex_lock(&slow_work_user_lock); - if (slow_work_user_count > 0) { - /* see if we need to stop threads */ - n = slow_work_max_threads - - atomic_read(&slow_work_thread_count); - - if (n < 0) - slow_work_schedule_cull(); - } - mutex_unlock(&slow_work_user_lock); - } - - return ret; -} -#endif /* CONFIG_SYSCTL */ - -/** - * slow_work_register_user - Register a user of the facility - * @module: The module about to make use of the facility - * - * Register a user of the facility, starting up the initial threads if there - * aren't any other users at this point. This will return 0 if successful, or - * an error if not. - */ -int slow_work_register_user(struct module *module) -{ - struct task_struct *p; - int loop; - - mutex_lock(&slow_work_user_lock); - - if (slow_work_user_count == 0) { - printk(KERN_NOTICE "Slow work thread pool: Starting up\n"); - init_completion(&slow_work_last_thread_exited); - - slow_work_threads_should_exit = false; - slow_work_init(&slow_work_new_thread, - &slow_work_new_thread_ops); - slow_work_may_not_start_new_thread = false; - slow_work_cull = false; - - /* start the minimum number of threads */ - for (loop = 0; loop < slow_work_min_threads; loop++) { - atomic_inc(&slow_work_thread_count); - p = kthread_run(slow_work_thread, NULL, "kslowd"); - if (IS_ERR(p)) - goto error; - } - printk(KERN_NOTICE "Slow work thread pool: Ready\n"); - } - - slow_work_user_count++; - mutex_unlock(&slow_work_user_lock); - return 0; - -error: - if (atomic_dec_and_test(&slow_work_thread_count)) - complete(&slow_work_last_thread_exited); - if (loop > 0) { - printk(KERN_ERR "Slow work thread pool:" - " Aborting startup on ENOMEM\n"); - slow_work_threads_should_exit = true; - wake_up_all(&slow_work_thread_wq); - wait_for_completion(&slow_work_last_thread_exited); - printk(KERN_ERR "Slow work thread pool: Aborted\n"); - } - mutex_unlock(&slow_work_user_lock); - return PTR_ERR(p); -} -EXPORT_SYMBOL(slow_work_register_user); - -/* - * wait for all outstanding items from the calling module to complete - * - note that more items may be queued whilst we're waiting - */ -static void slow_work_wait_for_items(struct module *module) -{ -#ifdef CONFIG_MODULES - DECLARE_WAITQUEUE(myself, current); - struct slow_work *work; - int loop; - - mutex_lock(&slow_work_unreg_sync_lock); - add_wait_queue(&slow_work_unreg_wq, &myself); - - for (;;) { - spin_lock_irq(&slow_work_queue_lock); - - /* first of all, we wait for the last queued item in each list - * to be processed */ - list_for_each_entry_reverse(work, &vslow_work_queue, link) { - if (work->owner == module) { - set_current_state(TASK_UNINTERRUPTIBLE); - slow_work_unreg_work_item = work; - goto do_wait; - } - } - list_for_each_entry_reverse(work, &slow_work_queue, link) { - if (work->owner == module) { - set_current_state(TASK_UNINTERRUPTIBLE); - slow_work_unreg_work_item = work; - goto do_wait; - } - } - - /* then we wait for the items being processed to finish */ - slow_work_unreg_module = module; - smp_mb(); - for (loop = 0; loop < SLOW_WORK_THREAD_LIMIT; loop++) { - if (slow_work_thread_processing[loop] == module) - goto do_wait; - } - spin_unlock_irq(&slow_work_queue_lock); - break; /* okay, we're done */ - - do_wait: - spin_unlock_irq(&slow_work_queue_lock); - schedule(); - slow_work_unreg_work_item = NULL; - slow_work_unreg_module = NULL; - } - - remove_wait_queue(&slow_work_unreg_wq, &myself); - mutex_unlock(&slow_work_unreg_sync_lock); -#endif /* CONFIG_MODULES */ -} - -/** - * slow_work_unregister_user - Unregister a user of the facility - * @module: The module whose items should be cleared - * - * Unregister a user of the facility, killing all the threads if this was the - * last one. - * - * This waits for all the work items belonging to the nominated module to go - * away before proceeding. - */ -void slow_work_unregister_user(struct module *module) -{ - /* first of all, wait for all outstanding items from the calling module - * to complete */ - if (module) - slow_work_wait_for_items(module); - - /* then we can actually go about shutting down the facility if need - * be */ - mutex_lock(&slow_work_user_lock); - - BUG_ON(slow_work_user_count <= 0); - - slow_work_user_count--; - if (slow_work_user_count == 0) { - printk(KERN_NOTICE "Slow work thread pool: Shutting down\n"); - slow_work_threads_should_exit = true; - del_timer_sync(&slow_work_cull_timer); - del_timer_sync(&slow_work_oom_timer); - wake_up_all(&slow_work_thread_wq); - wait_for_completion(&slow_work_last_thread_exited); - printk(KERN_NOTICE "Slow work thread pool:" - " Shut down complete\n"); - } - - mutex_unlock(&slow_work_user_lock); -} -EXPORT_SYMBOL(slow_work_unregister_user); - -/* - * Initialise the slow work facility - */ -static int __init init_slow_work(void) -{ - unsigned nr_cpus = num_possible_cpus(); - - if (slow_work_max_threads < nr_cpus) - slow_work_max_threads = nr_cpus; -#ifdef CONFIG_SYSCTL - if (slow_work_max_max_threads < nr_cpus * 2) - slow_work_max_max_threads = nr_cpus * 2; -#endif -#ifdef CONFIG_SLOW_WORK_DEBUG - { - struct dentry *dbdir; - - dbdir = debugfs_create_dir("slow_work", NULL); - if (dbdir && !IS_ERR(dbdir)) - debugfs_create_file("runqueue", S_IFREG | 0400, dbdir, - NULL, &slow_work_runqueue_fops); - } -#endif - return 0; -} - -subsys_initcall(init_slow_work); diff --git a/kernel/slow-work.h b/kernel/slow-work.h deleted file mode 100644 index a29ebd1ef41d..000000000000 --- a/kernel/slow-work.h +++ /dev/null @@ -1,72 +0,0 @@ -/* Slow work private definitions - * - * Copyright (C) 2009 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public Licence - * as published by the Free Software Foundation; either version - * 2 of the Licence, or (at your option) any later version. - */ - -#define SLOW_WORK_CULL_TIMEOUT (5 * HZ) /* cull threads 5s after running out of - * things to do */ -#define SLOW_WORK_OOM_TIMEOUT (5 * HZ) /* can't start new threads for 5s after - * OOM */ - -#define SLOW_WORK_THREAD_LIMIT 255 /* abs maximum number of slow-work threads */ - -/* - * slow-work.c - */ -#ifdef CONFIG_SLOW_WORK_DEBUG -extern struct slow_work *slow_work_execs[]; -extern pid_t slow_work_pids[]; -extern rwlock_t slow_work_execs_lock; -#endif - -extern struct list_head slow_work_queue; -extern struct list_head vslow_work_queue; -extern spinlock_t slow_work_queue_lock; - -/* - * slow-work-debugfs.c - */ -#ifdef CONFIG_SLOW_WORK_DEBUG -extern const struct file_operations slow_work_runqueue_fops; - -extern void slow_work_new_thread_desc(struct slow_work *, struct seq_file *); -#endif - -/* - * Helper functions - */ -static inline void slow_work_set_thread_pid(int id, pid_t pid) -{ -#ifdef CONFIG_SLOW_WORK_DEBUG - slow_work_pids[id] = pid; -#endif -} - -static inline void slow_work_mark_time(struct slow_work *work) -{ -#ifdef CONFIG_SLOW_WORK_DEBUG - work->mark = CURRENT_TIME; -#endif -} - -static inline void slow_work_begin_exec(int id, struct slow_work *work) -{ -#ifdef CONFIG_SLOW_WORK_DEBUG - slow_work_execs[id] = work; -#endif -} - -static inline void slow_work_end_exec(int id, struct slow_work *work) -{ -#ifdef CONFIG_SLOW_WORK_DEBUG - write_lock(&slow_work_execs_lock); - slow_work_execs[id] = NULL; - write_unlock(&slow_work_execs_lock); -#endif -} diff --git a/kernel/sysctl.c b/kernel/sysctl.c index d24f761f4876..5821365b9605 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -50,7 +50,6 @@ #include #include #include -#include #include #include #include @@ -906,13 +905,6 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif -#ifdef CONFIG_SLOW_WORK - { - .procname = "slow-work", - .mode = 0555, - .child = slow_work_sysctls, - }, -#endif #ifdef CONFIG_PERF_EVENTS { .procname = "perf_event_paranoid", -- cgit v1.2.3 From 939a67fc4cbab8ca11c90da8a769d7e965d66a9b Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Thu, 17 Dec 2009 20:12:06 -0500 Subject: Audit: split audit watch Kconfig Audit watch should depend on CONFIG_AUDIT_SYSCALL and should select FSNOTIFY. This splits the spagetti like mixing of audit_watch and audit_filter code so they can be configured seperately. Signed-off-by: Eric Paris --- init/Kconfig | 6 +++++- kernel/Makefile | 5 +++-- kernel/audit.h | 14 +++++++++++++- 3 files changed, 21 insertions(+), 4 deletions(-) (limited to 'kernel/Makefile') diff --git a/init/Kconfig b/init/Kconfig index 59f62548c2aa..05e932ef5169 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -307,7 +307,6 @@ config TASK_IO_ACCOUNTING config AUDIT bool "Auditing support" depends on NET - select FSNOTIFY help Enable auditing infrastructure that can be used with another kernel subsystem, such as SELinux (which requires this for @@ -323,6 +322,11 @@ config AUDITSYSCALL can be used independently or with another kernel subsystem, such as SELinux. +config AUDIT_WATCH + def_bool y + depends on AUDITSYSCALL + select FSNOTIFY + config AUDIT_TREE def_bool y depends on AUDITSYSCALL diff --git a/kernel/Makefile b/kernel/Makefile index 057472fbc272..202df4ece6a5 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -70,10 +70,11 @@ obj-$(CONFIG_IKCONFIG) += configs.o obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o obj-$(CONFIG_SMP) += stop_machine.o obj-$(CONFIG_KPROBES_SANITY_TEST) += test_kprobes.o -obj-$(CONFIG_AUDIT) += audit.o auditfilter.o audit_watch.o +obj-$(CONFIG_AUDIT) += audit.o auditfilter.o obj-$(CONFIG_AUDITSYSCALL) += auditsc.o -obj-$(CONFIG_GCOV_KERNEL) += gcov/ +obj-$(CONFIG_AUDIT_WATCH) += audit_watch.o obj-$(CONFIG_AUDIT_TREE) += audit_tree.o +obj-$(CONFIG_GCOV_KERNEL) += gcov/ obj-$(CONFIG_KPROBES) += kprobes.o obj-$(CONFIG_KGDB) += debug/ obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o diff --git a/kernel/audit.h b/kernel/audit.h index 100b454a7354..f7206db4e13d 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -103,7 +103,10 @@ extern struct mutex audit_filter_mutex; extern void audit_free_rule_rcu(struct rcu_head *); extern struct list_head audit_filter_list[]; +extern struct audit_entry *audit_dupe_rule(struct audit_krule *old); + /* audit watch functions */ +#ifdef CONFIG_AUDIT_WATCH extern void audit_put_watch(struct audit_watch *watch); extern void audit_get_watch(struct audit_watch *watch); extern int audit_to_watch(struct audit_krule *krule, char *path, int len, u32 op); @@ -111,7 +114,16 @@ extern int audit_add_watch(struct audit_krule *krule, struct list_head **list); extern void audit_remove_watch_rule(struct audit_krule *krule); extern char *audit_watch_path(struct audit_watch *watch); extern int audit_watch_compare(struct audit_watch *watch, unsigned long ino, dev_t dev); -extern struct audit_entry *audit_dupe_rule(struct audit_krule *old); +#else +#define audit_put_watch(w) {} +#define audit_get_watch(w) {} +#define audit_to_watch(k, p, l, o) (-EINVAL) +#define audit_add_watch(k, l) (-EINVAL) +#define audit_remove_watch_rule(k) BUG() +#define audit_watch_path(w) "" +#define audit_watch_compare(w, i, d) 0 + +#endif /* CONFIG_AUDIT_WATCH */ #ifdef CONFIG_AUDIT_TREE extern struct audit_chunk *audit_tree_lookup(const struct inode *); -- cgit v1.2.3