struct file *filp, void __user *buffer,
size_t *lenp, loff_t *ppos);
extern unsigned int softlockup_panic;
-extern unsigned long sysctl_hung_task_check_count;
-extern unsigned long sysctl_hung_task_timeout_secs;
-extern unsigned long sysctl_hung_task_warnings;
extern int softlockup_thresh;
#else
static inline void softlockup_tick(void)
{
}
-static inline void spawn_softlockup_task(void)
-{
-}
static inline void touch_softlockup_watchdog(void)
{
}
}
#endif
+#ifdef CONFIG_DETECT_HUNG_TASK
+extern unsigned int sysctl_hung_task_panic;
+extern unsigned long sysctl_hung_task_check_count;
+extern unsigned long sysctl_hung_task_timeout_secs;
+extern unsigned long sysctl_hung_task_warnings;
+extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
+ struct file *filp, 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")))
#define virt_exp utime
#define sched_exp sum_exec_runtime
+ #define INIT_CPUTIME \
+ (struct task_cputime) { \
+ .utime = cputime_zero, \
+ .stime = cputime_zero, \
+ .sum_exec_runtime = 0, \
+ }
+
/**
- * struct thread_group_cputime - thread group interval timer counts
- * @totals: thread group interval timers; substructure for
- * uniprocessor kernel, per-cpu for SMP kernel.
+ * struct thread_group_cputimer - thread group interval timer counts
+ * @cputime: thread group interval timers.
+ * @running: non-zero when there are timers running and
+ * @cputime receives updates.
+ * @lock: lock for fields in this struct.
*
* This structure contains the version of task_cputime, above, that is
- * used for thread group CPU clock calculations.
+ * used for thread group CPU timer calculations.
*/
- struct thread_group_cputime {
- struct task_cputime *totals;
+ struct thread_group_cputimer {
+ struct task_cputime cputime;
+ int running;
+ spinlock_t lock;
};
/*
cputime_t it_prof_incr, it_virt_incr;
/*
- * Thread group totals for process CPU clocks.
- * See thread_group_cputime(), et al, for details.
+ * Thread group totals for process CPU timers.
+ * See thread_group_cputimer(), et al, for details.
*/
- struct thread_group_cputime cputime;
+ struct thread_group_cputimer cputimer;
/* Earliest-expiration cache. */
struct task_cputime cputime_expires;
* Live threads maintain their own counters and add to these
* in __exit_signal, except for the group leader.
*/
- cputime_t cutime, cstime;
+ cputime_t utime, stime, cutime, cstime;
cputime_t gtime;
cputime_t cgtime;
unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
unsigned long inblock, oublock, cinblock, coublock;
struct task_io_accounting ioac;
+ /*
+ * Cumulative ns of schedule CPU time fo dead threads in the
+ * group, not including a zombie group leader, (This only differs
+ * from jiffies_to_ns(utime + stime) if sched_clock uses something
+ * other than jiffies.)
+ */
+ unsigned long long sum_sched_runtime;
+
/*
* We don't bother to synchronize most readers of this at all,
* because there is no reader checking a limit that actually needs
atomic_t inotify_devs; /* How many inotify devs does this user have opened? */
#endif
#ifdef CONFIG_EPOLL
- atomic_t epoll_devs; /* The number of epoll descriptors currently open */
atomic_t epoll_watches; /* The number of file descriptors currently watched */
#endif
#ifdef CONFIG_POSIX_MQUEUE
/* ipc stuff */
struct sysv_sem sysvsem;
#endif
-#ifdef CONFIG_DETECT_SOFTLOCKUP
+#ifdef CONFIG_DETECT_HUNG_TASK
/* hung task detection */
- unsigned long last_switch_timestamp;
unsigned long last_switch_count;
#endif
/* CPU-specific state of this task */
/*
* Thread group CPU time accounting.
*/
-
- extern int thread_group_cputime_alloc(struct task_struct *);
- extern void thread_group_cputime(struct task_struct *, struct task_cputime *);
+ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times);
+ void thread_group_cputimer(struct task_struct *tsk, struct task_cputime *times);
static inline void thread_group_cputime_init(struct signal_struct *sig)
{
- sig->cputime.totals = NULL;
- }
-
- static inline int thread_group_cputime_clone_thread(struct task_struct *curr)
- {
- if (curr->signal->cputime.totals)
- return 0;
- return thread_group_cputime_alloc(curr);
+ sig->cputimer.cputime = INIT_CPUTIME;
+ spin_lock_init(&sig->cputimer.lock);
+ sig->cputimer.running = 0;
}
static inline void thread_group_cputime_free(struct signal_struct *sig)
{
- free_percpu(sig->cputime.totals);
}
/*
obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
- ifeq ($(CONFIG_USE_GENERIC_SMP_HELPERS),y)
- obj-y += smp.o
- else
+ obj-$(CONFIG_USE_GENERIC_SMP_HELPERS) += smp.o
+ ifneq ($(CONFIG_SMP),y)
obj-y += up.o
endif
obj-$(CONFIG_SMP) += spinlock.o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_KGDB) += kgdb.o
obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o
+obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
obj-$(CONFIG_SECCOMP) += seccomp.o
obj-$(CONFIG_RCU_TORTURE_TEST) += rcutorture.o
tsk->min_flt = tsk->maj_flt = 0;
tsk->nvcsw = tsk->nivcsw = 0;
+#ifdef CONFIG_DETECT_HUNG_TASK
+ tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw;
+#endif
tsk->mm = NULL;
tsk->active_mm = NULL;
static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
{
struct signal_struct *sig;
- int ret;
if (clone_flags & CLONE_THREAD) {
- ret = thread_group_cputime_clone_thread(current);
- if (likely(!ret)) {
- atomic_inc(¤t->signal->count);
- atomic_inc(¤t->signal->live);
- }
- return ret;
+ atomic_inc(¤t->signal->count);
+ atomic_inc(¤t->signal->live);
+ return 0;
}
sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
+
+ if (sig)
+ posix_cpu_timers_init_group(sig);
+
tsk->signal = sig;
if (!sig)
return -ENOMEM;
sig->tty_old_pgrp = NULL;
sig->tty = NULL;
- sig->cutime = sig->cstime = cputime_zero;
+ sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
sig->gtime = cputime_zero;
sig->cgtime = cputime_zero;
sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
task_io_accounting_init(&sig->ioac);
+ sig->sum_sched_runtime = 0;
taskstats_tgid_init(sig);
task_lock(current->group_leader);
memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
task_unlock(current->group_leader);
- posix_cpu_timers_init_group(sig);
-
acct_init_pacct(&sig->pacct);
tty_audit_fork(sig);
clear_freeze_flag(p);
}
- asmlinkage long sys_set_tid_address(int __user *tidptr)
+ SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
{
current->clear_child_tid = tidptr;
* triggers too late. This doesn't hurt, the check is only there
* to stop root fork bombs.
*/
+ retval = -EAGAIN;
if (nr_threads >= max_threads)
goto bad_fork_cleanup_count;
p->default_timer_slack_ns = current->timer_slack_ns;
-#ifdef CONFIG_DETECT_SOFTLOCKUP
- p->last_switch_count = 0;
- p->last_switch_timestamp = 0;
-#endif
-
task_io_accounting_init(&p->ioac);
acct_clear_integrals(p);
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
- if (unlikely(ptrace_reparented(current)))
+ if (unlikely(current->ptrace))
ptrace_fork(p, clone_flags);
/* Perform scheduler related setup. Assign this task to a CPU. */
* constructed. Here we are modifying the current, active,
* task_struct.
*/
- asmlinkage long sys_unshare(unsigned long unshare_flags)
+ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
{
int err = 0;
struct fs_struct *fs, *new_fs = NULL;
static int zero;
static int one = 1;
+ static unsigned long one_ul = 1;
static int one_hundred = 100;
/* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
#ifdef CONFIG_IA64
extern int no_unaligned_warning;
+ extern int unaligned_dump_stack;
#endif
#ifdef CONFIG_RT_MUTEXES
.mode = 0644,
.proc_handler = &proc_dointvec,
},
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "unaligned-dump-stack",
+ .data = &unaligned_dump_stack,
+ .maxlen = sizeof (int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
#endif
#ifdef CONFIG_DETECT_SOFTLOCKUP
{
.extra1 = &neg_one,
.extra2 = &sixty,
},
+#endif
+#ifdef CONFIG_DETECT_HUNG_TASK
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "hung_task_panic",
+ .data = &sysctl_hung_task_panic,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .strategy = &sysctl_intvec,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
{
.ctl_name = CTL_UNNUMBERED,
.procname = "hung_task_check_count",
.data = &sysctl_hung_task_timeout_secs,
.maxlen = sizeof(unsigned long),
.mode = 0644,
- .proc_handler = &proc_doulongvec_minmax,
+ .proc_handler = &proc_dohung_task_timeout_secs,
.strategy = &sysctl_intvec,
},
{
.mode = 0644,
.proc_handler = &dirty_background_bytes_handler,
.strategy = &sysctl_intvec,
- .extra1 = &one,
+ .extra1 = &one_ul,
},
{
.ctl_name = VM_DIRTY_RATIO,
.mode = 0644,
.proc_handler = &dirty_bytes_handler,
.strategy = &sysctl_intvec,
- .extra1 = &one,
+ .extra1 = &one_ul,
},
{
.procname = "dirty_writeback_centisecs",
return error;
}
- asmlinkage long sys_sysctl(struct __sysctl_args __user *args)
+ SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args)
{
struct __sysctl_args tmp;
int error;
#else /* CONFIG_SYSCTL_SYSCALL */
- asmlinkage long sys_sysctl(struct __sysctl_args __user *args)
+ SYSCALL_DEFINE1(sysctl, struct __sysctl_args __user *, args)
{
struct __sysctl_args tmp;
int error;
default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC
default 1 if BOOTPARAM_SOFTLOCKUP_PANIC
+config DETECT_HUNG_TASK
+ bool "Detect Hung Tasks"
+ depends on DEBUG_KERNEL
+ default y
+ help
+ Say Y here to enable the kernel to detect "hung tasks",
+ which are bugs that cause the task to be stuck in
+ uninterruptible "D" state indefinitiley.
+
+ When a hung task is detected, the kernel will print the
+ current stack trace (which you should report), but the
+ task will stay in uninterruptible state. If lockdep is
+ enabled then all held locks will also be reported. This
+ feature has negligible overhead.
+
+config BOOTPARAM_HUNG_TASK_PANIC
+ bool "Panic (Reboot) On Hung Tasks"
+ depends on DETECT_HUNG_TASK
+ help
+ Say Y here to enable the kernel to panic on "hung tasks",
+ which are bugs that cause the kernel to leave a task stuck
+ in uninterruptible "D" state.
+
+ The panic can be used in combination with panic_timeout,
+ to cause the system to reboot automatically after a
+ hung task has been detected. This feature is useful for
+ high-availability systems that have uptime guarantees and
+ where a hung tasks must be resolved ASAP.
+
+ Say N if unsure.
+
+config BOOTPARAM_HUNG_TASK_PANIC_VALUE
+ int
+ depends on DETECT_HUNG_TASK
+ range 0 1
+ default 0 if !BOOTPARAM_HUNG_TASK_PANIC
+ default 1 if BOOTPARAM_HUNG_TASK_PANIC
+
config SCHED_DEBUG
bool "Collect scheduler debugging info"
depends on DEBUG_KERNEL && PROC_FS
This is a relatively cheap check but if you care about maximum
performance, say N.
+ #
+ # Select this config option from the architecture Kconfig, if it
+ # it is preferred to always offer frame pointers as a config
+ # option on the architecture (regardless of KERNEL_DEBUG):
+ #
+ config ARCH_WANT_FRAME_POINTERS
+ bool
+ help
+
config FRAME_POINTER
bool "Compile the kernel with frame pointers"
depends on DEBUG_KERNEL && \
Say N here if you want the RCU torture tests to start only
after being manually enabled via /proc.
- config RCU_CPU_STALL_DETECTOR
- bool "Check for stalled CPUs delaying RCU grace periods"
- depends on CLASSIC_RCU
- default n
- help
- This option causes RCU to printk information on which
- CPUs are delaying the current grace period, but only when
- the grace period extends for excessive time periods.
-
- Say Y if you want RCU to perform such checks.
-
- Say N if you are unsure.
-
config RCU_CPU_STALL_DETECTOR
bool "Check for stalled CPUs delaying RCU grace periods"
depends on CLASSIC_RCU || TREE_RCU