diff options
Diffstat (limited to 'kernel')
67 files changed, 11527 insertions, 1167 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 1c9938addb9..985ddb7da4d 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -3,7 +3,7 @@ # obj-y = sched.o fork.o exec_domain.o panic.o printk.o profile.o \ - exit.o itimer.o time.o softirq.o resource.o \ + cpu.o exit.o itimer.o time.o softirq.o resource.o \ sysctl.o capability.o ptrace.o timer.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o \ rcupdate.o extable.o params.o posix-timers.o \ @@ -11,6 +11,17 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o profile.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o pm_qos_params.o sched_clock.o +ifdef CONFIG_FTRACE +# Do not trace debug files and internal ftrace files +CFLAGS_REMOVE_lockdep.o = -pg +CFLAGS_REMOVE_lockdep_proc.o = -pg +CFLAGS_REMOVE_mutex-debug.o = -pg +CFLAGS_REMOVE_rtmutex-debug.o = -pg +CFLAGS_REMOVE_cgroup-debug.o = -pg +CFLAGS_REMOVE_sched_clock.o = -pg +CFLAGS_REMOVE_sched.o = -mno-spe -pg +endif + obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o obj-$(CONFIG_STACKTRACE) += stacktrace.o obj-y += time/ @@ -27,7 +38,8 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o -obj-$(CONFIG_SMP) += cpu.o spinlock.o +obj-$(CONFIG_USE_GENERIC_SMP_HELPERS) += smp.o +obj-$(CONFIG_SMP) += spinlock.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o obj-$(CONFIG_PROVE_LOCKING) += spinlock.o obj-$(CONFIG_UID16) += uid16.o @@ -69,6 +81,9 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o obj-$(CONFIG_MARKERS) += marker.o obj-$(CONFIG_LATENCYTOP) += latencytop.o +obj-$(CONFIG_FTRACE) += trace/ +obj-$(CONFIG_TRACING) += trace/ +obj-$(CONFIG_SMP) += sched_cpupri.o ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y) # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is diff --git a/kernel/backtracetest.c b/kernel/backtracetest.c index d1a7605c5b8..a5e026bc45c 100644 --- a/kernel/backtracetest.c +++ b/kernel/backtracetest.c @@ -10,30 +10,73 @@ * of the License. */ +#include <linux/completion.h> +#include <linux/delay.h> +#include <linux/interrupt.h> #include <linux/module.h> #include <linux/sched.h> -#include <linux/delay.h> +#include <linux/stacktrace.h> + +static void backtrace_test_normal(void) +{ + printk("Testing a backtrace from process context.\n"); + printk("The following trace is a kernel self test and not a bug!\n"); -static struct timer_list backtrace_timer; + dump_stack(); +} -static void backtrace_test_timer(unsigned long data) +static DECLARE_COMPLETION(backtrace_work); + +static void backtrace_test_irq_callback(unsigned long data) +{ + dump_stack(); + complete(&backtrace_work); +} + +static DECLARE_TASKLET(backtrace_tasklet, &backtrace_test_irq_callback, 0); + +static void backtrace_test_irq(void) { printk("Testing a backtrace from irq context.\n"); printk("The following trace is a kernel self test and not a bug!\n"); - dump_stack(); + + init_completion(&backtrace_work); + tasklet_schedule(&backtrace_tasklet); + wait_for_completion(&backtrace_work); +} + +#ifdef CONFIG_STACKTRACE +static void backtrace_test_saved(void) +{ + struct stack_trace trace; + unsigned long entries[8]; + + printk("Testing a saved backtrace.\n"); + printk("The following trace is a kernel self test and not a bug!\n"); + + trace.nr_entries = 0; + trace.max_entries = ARRAY_SIZE(entries); + trace.entries = entries; + trace.skip = 0; + + save_stack_trace(&trace); + print_stack_trace(&trace, 0); +} +#else +static void backtrace_test_saved(void) +{ + printk("Saved backtrace test skipped.\n"); } +#endif + static int backtrace_regression_test(void) { printk("====[ backtrace testing ]===========\n"); - printk("Testing a backtrace from process context.\n"); - printk("The following trace is a kernel self test and not a bug!\n"); - dump_stack(); - init_timer(&backtrace_timer); - backtrace_timer.function = backtrace_test_timer; - mod_timer(&backtrace_timer, jiffies + 10); + backtrace_test_normal(); + backtrace_test_irq(); + backtrace_test_saved(); - msleep(10); printk("====[ end of backtrace testing ]====\n"); return 0; } diff --git a/kernel/capability.c b/kernel/capability.c index cfbe4429948..901e0fdc3ff 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -121,6 +121,27 @@ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy) * uninteresting and/or not to be changed. */ +/* + * Atomically modify the effective capabilities returning the original + * value. No permission check is performed here - it is assumed that the + * caller is permitted to set the desired effective capabilities. + */ +kernel_cap_t cap_set_effective(const kernel_cap_t pE_new) +{ + kernel_cap_t pE_old; + + spin_lock(&task_capability_lock); + + pE_old = current->cap_effective; + current->cap_effective = pE_new; + + spin_unlock(&task_capability_lock); + + return pE_old; +} + +EXPORT_SYMBOL(cap_set_effective); + /** * sys_capget - get the capabilities of a given process. * @header: pointer to struct that contains capability version and diff --git a/kernel/cpu.c b/kernel/cpu.c index c77bc3a1c72..cfb1d43ab80 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -15,6 +15,28 @@ #include <linux/stop_machine.h> #include <linux/mutex.h> +/* + * Represents all cpu's present in the system + * In systems capable of hotplug, this map could dynamically grow + * as new cpu's are detected in the system via any platform specific + * method, such as ACPI for e.g. + */ +cpumask_t cpu_present_map __read_mostly; +EXPORT_SYMBOL(cpu_present_map); + +#ifndef CONFIG_SMP + +/* + * Represents all cpu's that are currently online. + */ +cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL; +EXPORT_SYMBOL(cpu_online_map); + +cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL; +EXPORT_SYMBOL(cpu_possible_map); + +#else /* CONFIG_SMP */ + /* Serializes the updates to cpu_online_map, cpu_present_map */ static DEFINE_MUTEX(cpu_add_remove_lock); @@ -277,6 +299,7 @@ int __ref cpu_down(unsigned int cpu) cpu_maps_update_done(); return err; } +EXPORT_SYMBOL(cpu_down); #endif /*CONFIG_HOTPLUG_CPU*/ /* Requires cpu_add_remove_lock to be held */ @@ -403,3 +426,5 @@ out: cpu_maps_update_done(); } #endif /* CONFIG_PM_SLEEP_SMP */ + +#endif /* CONFIG_SMP */ diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 9fceb97e989..459d601947a 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1194,6 +1194,15 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) return -ENOSPC; + if (tsk->flags & PF_THREAD_BOUND) { + cpumask_t mask; + + mutex_lock(&callback_mutex); + mask = cs->cpus_allowed; + mutex_unlock(&callback_mutex); + if (!cpus_equal(tsk->cpus_allowed, mask)) + return -EINVAL; + } return security_task_setscheduler(tsk, 0, NULL); } @@ -1207,11 +1216,14 @@ static void cpuset_attach(struct cgroup_subsys *ss, struct mm_struct *mm; struct cpuset *cs = cgroup_cs(cont); struct cpuset *oldcs = cgroup_cs(oldcont); + int err; mutex_lock(&callback_mutex); guarantee_online_cpus(cs, &cpus); - set_cpus_allowed_ptr(tsk, &cpus); + err = set_cpus_allowed_ptr(tsk, &cpus); mutex_unlock(&callback_mutex); + if (err) + return; from = oldcs->mems_allowed; to = cs->mems_allowed; @@ -1882,7 +1894,7 @@ static void scan_for_empty_cpusets(const struct cpuset *root) * in order to minimize text size. */ -static void common_cpu_mem_hotplug_unplug(void) +static void common_cpu_mem_hotplug_unplug(int rebuild_sd) { cgroup_lock(); @@ -1894,7 +1906,8 @@ static void common_cpu_mem_hotplug_unplug(void) * Scheduler destroys domains on hotplug events. * Rebuild them based on the current settings. */ - rebuild_sched_domains(); + if (rebuild_sd) + rebuild_sched_domains(); cgroup_unlock(); } @@ -1912,11 +1925,22 @@ static void common_cpu_mem_hotplug_unplug(void) static int cpuset_handle_cpuhp(struct notifier_block *unused_nb, unsigned long phase, void *unused_cpu) { - if (phase == CPU_DYING || phase == CPU_DYING_FROZEN) + switch (phase) { + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + case CPU_DOWN_FAILED: + case CPU_DOWN_FAILED_FROZEN: + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + case CPU_DEAD: + case CPU_DEAD_FROZEN: + common_cpu_mem_hotplug_unplug(1); + break; + default: return NOTIFY_DONE; + } - common_cpu_mem_hotplug_unplug(); - return 0; + return NOTIFY_OK; } #ifdef CONFIG_MEMORY_HOTPLUG @@ -1929,7 +1953,7 @@ static int cpuset_handle_cpuhp(struct notifier_block *unused_nb, void cpuset_track_online_nodes(void) { - common_cpu_mem_hotplug_unplug(); + common_cpu_mem_hotplug_unplug(0); } #endif diff --git a/kernel/exit.c b/kernel/exit.c index 8f6185e69b6..93d2711b938 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -13,6 +13,7 @@ #include <linux/personality.h> #include <linux/tty.h> #include <linux/mnt_namespace.h> +#include <linux/iocontext.h> #include <linux/key.h> #include <linux/security.h> #include <linux/cpu.h> @@ -70,7 +71,7 @@ static void __unhash_process(struct task_struct *p) __get_cpu_var(process_counts)--; } list_del_rcu(&p->thread_group); - remove_parent(p); + list_del_init(&p->sibling); } /* @@ -151,6 +152,18 @@ static void delayed_put_task_struct(struct rcu_head *rhp) put_task_struct(container_of(rhp, struct task_struct, rcu)); } +/* + * Do final ptrace-related cleanup of a zombie being reaped. + * + * Called with write_lock(&tasklist_lock) held. + */ +static void ptrace_release_task(struct task_struct *p) +{ + BUG_ON(!list_empty(&p->ptraced)); + ptrace_unlink(p); + BUG_ON(!list_empty(&p->ptrace_entry)); +} + void release_task(struct task_struct * p) { struct task_struct *leader; @@ -159,8 +172,7 @@ repeat: atomic_dec(&p->user->processes); proc_flush_task(p); write_lock_irq(&tasklist_lock); - ptrace_unlink(p); - BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children)); + ptrace_release_task(p); __exit_signal(p); /* @@ -314,9 +326,8 @@ static void reparent_to_kthreadd(void) ptrace_unlink(current); /* Reparent to init */ - remove_parent(current); current->real_parent = current->parent = kthreadd_task; - add_parent(current); + list_move_tail(¤t->sibling, ¤t->real_parent->children); /* Set the exit signal to SIGCHLD so we signal init on exit */ current->exit_signal = SIGCHLD; @@ -691,37 +702,97 @@ static void exit_mm(struct task_struct * tsk) mmput(mm); } -static void -reparent_thread(struct task_struct *p, struct task_struct *father, int traced) +/* + * Return nonzero if @parent's children should reap themselves. + * + * Called with write_lock_irq(&tasklist_lock) held. + */ +static int ignoring_children(struct task_struct *parent) { - if (p->pdeath_signal) - /* We already hold the tasklist_lock here. */ - group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p); + int ret; + struct sighand_struct *psig = parent->sighand; + unsigned long flags; + spin_lock_irqsave(&psig->siglock, flags); + ret = (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN || + (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT)); + spin_unlock_irqrestore(&psig->siglock, flags); + return ret; +} - /* Move the child from its dying parent to the new one. */ - if (unlikely(traced)) { - /* Preserve ptrace links if someone else is tracing this child. */ - list_del_init(&p->ptrace_list); - if (ptrace_reparented(p)) - list_add(&p->ptrace_list, &p->real_parent->ptrace_children); - } else { - /* If this child is being traced, then we're the one tracing it - * anyway, so let go of it. +/* + * Detach all tasks we were using ptrace on. + * Any that need to be release_task'd are put on the @dead list. + * + * Called with write_lock(&tasklist_lock) held. + */ +static void ptrace_exit(struct task_struct *parent, struct list_head *dead) +{ + struct task_struct *p, *n; + int ign = -1; + + list_for_each_entry_safe(p, n, &parent->ptraced, ptrace_entry) { + __ptrace_unlink(p); + + if (p->exit_state != EXIT_ZOMBIE) + continue; + + /* + * If it's a zombie, our attachedness prevented normal + * parent notification or self-reaping. Do notification + * now if it would have happened earlier. If it should + * reap itself, add it to the @dead list. We can't call + * release_task() here because we already hold tasklist_lock. + * + * If it's our own child, there is no notification to do. + * But if our normal children self-reap, then this child + * was prevented by ptrace and we must reap it now. */ - p->ptrace = 0; - remove_parent(p); - p->parent = p->real_parent; - add_parent(p); + if (!task_detached(p) && thread_group_empty(p)) { + if (!same_thread_group(p->real_parent, parent)) + do_notify_parent(p, p->exit_signal); + else { + if (ign < 0) + ign = ignoring_children(parent); + if (ign) + p->exit_signal = -1; + } + } - if (task_is_traced(p)) { + if (task_detached(p)) { /* - * If it was at a trace stop, turn it into - * a normal stop since it's no longer being - * traced. + * Mark it as in the process of being reaped. */ - ptrace_untrace(p); + p->exit_state = EXIT_DEAD; + list_add(&p->ptrace_entry, dead); } } +} + +/* + * Finish up exit-time ptrace cleanup. + * + * Called without locks. + */ +static void ptrace_exit_finish(struct task_struct *parent, + struct list_head *dead) +{ + struct task_struct *p, *n; + + BUG_ON(!list_empty(&parent->ptraced)); + + list_for_each_entry_safe(p, n, dead, ptrace_entry) { + list_del_init(&p->ptrace_entry); + release_task(p); + } +} + +static void reparent_thread(struct task_struct *p, struct task_struct *father) +{ + if (p->pdeath_signal) + /* We already hold the tasklist_lock here. */ + group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p); + + list_move_tail(&p->sibling, &p->real_parent->children); /* If this is a threaded reparent there is no need to * notify anyone anything has happened. @@ -736,7 +807,8 @@ reparent_thread(struct task_struct *p, struct task_struct *father, int traced) /* If we'd notified the old parent about this child's death, * also notify the new parent. */ - if (!traced && p->exit_state == EXIT_ZOMBIE && + if (!ptrace_reparented(p) && + p->exit_state == EXIT_ZOMBIE && !task_detached(p) && thread_group_empty(p)) do_notify_parent(p, p->exit_signal); @@ -753,12 +825,15 @@ reparent_thread(struct task_struct *p, struct task_struct *father, int traced) static void forget_original_parent(struct task_struct *father) { struct task_struct *p, *n, *reaper = father; - struct list_head ptrace_dead; - - INIT_LIST_HEAD(&ptrace_dead); + LIST_HEAD(ptrace_dead); write_lock_irq(&tasklist_lock); + /* + * First clean up ptrace if we were using it. + */ + ptrace_exit(father, &ptrace_dead); + do { reaper = next_thread(reaper); if (reaper == father) { @@ -767,58 +842,19 @@ static void forget_original_parent(struct task_struct *father) } } while (reaper->flags & PF_EXITING); - /* - * There are only two places where our children can be: - * - * - in our child list - * - in our ptraced child list - * - * Search them and reparent children. - */ list_for_each_entry_safe(p, n, &father->children, sibling) { - int ptrace; - - ptrace = p->ptrace; - - /* if father isn't the real parent, then ptrace must be enabled */ - BUG_ON(father != p->real_parent && !ptrace); - - if (father == p->real_parent) { - /* reparent with a reaper, real father it's us */ - p->real_parent = reaper; - reparent_thread(p, father, 0); - } else { - /* reparent ptraced task to its real parent */ - __ptrace_unlink (p); - if (p->exit_state == EXIT_ZOMBIE && !task_detached(p) && - thread_group_empty(p)) - do_notify_parent(p, p->exit_signal); - } - - /* - * if the ptraced child is a detached zombie we must collect - * it before we exit, or it will remain zombie forever since - * we prevented it from self-reap itself while it was being - * traced by us, to be able to see it in wait4. - */ - if (unlikely(ptrace && p->exit_state == EXIT_ZOMBIE && task_detached(p))) - list_add(&p->ptrace_list, &ptrace_dead); - } - - list_for_each_entry_safe(p, n, &father->ptrace_children, ptrace_list) { p->real_parent = reaper; - reparent_thread(p, father, 1); + if (p->parent == father) { + BUG_ON(p->ptrace); + p->parent = p->real_parent; + } + reparent_thread(p, father); } write_unlock_irq(&tasklist_lock); BUG_ON(!list_empty(&father->children)); - BUG_ON(!list_empty(&father->ptrace_children)); - - list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_list) { - list_del_init(&p->ptrace_list); - release_task(p); - } + ptrace_exit_finish(father, &ptrace_dead); } /* @@ -1179,13 +1215,6 @@ static int eligible_child(enum pid_type type, struct pid *pid, int options, return 0; } - /* - * Do not consider detached threads that are - * not ptraced: - */ - if (task_detached(p) && !p->ptrace) - return 0; - /* Wait for all children (clone and not) if __WALL is set; * otherwise, wait for clone children *only* if __WCLONE is * set; otherwise, wait for non-clone children *only*. (Note: @@ -1196,14 +1225,10 @@ static int eligible_child(enum pid_type type, struct pid *pid, int options, return 0; err = security_task_wait(p); - if (likely(!err)) - return 1; + if (err) + return err; - if (type != PIDTYPE_PID) - return 0; - /* This child was explicitly requested, abort */ - read_unlock(&tasklist_lock); - return err; + return 1; } static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid, @@ -1237,7 +1262,7 @@ static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid, * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ -static int wait_task_zombie(struct task_struct *p, int noreap, +static int wait_task_zombie(struct task_struct *p, int options, struct siginfo __user *infop, int __user *stat_addr, struct rusage __user *ru) { @@ -1245,7 +1270,10 @@ static int wait_task_zombie(struct task_struct *p, int noreap, int retval, status, traced; pid_t pid = task_pid_vnr(p); - if (unlikely(noreap)) { + if (!likely(options & WEXITED)) + return 0; + + if (unlikely(options & WNOWAIT)) { uid_t uid = p->uid; int exit_code = p->exit_code; int why, status; @@ -1395,21 +1423,24 @@ static int wait_task_zombie(struct task_struct *p, int noreap, * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ -static int wait_task_stopped(struct task_struct *p, - int noreap, struct siginfo __user *infop, +static int wait_task_stopped(int ptrace, struct task_struct *p, + int options, struct siginfo __user *infop, int __user *stat_addr, struct rusage __user *ru) { int retval, exit_code, why; uid_t uid = 0; /* unneeded, required by compiler */ pid_t pid; + if (!(options & WUNTRACED)) + return 0; + exit_code = 0; spin_lock_irq(&p->sighand->siglock); if (unlikely(!task_is_stopped_or_traced(p))) goto unlock_sig; - if (!(p->ptrace & PT_PTRACED) && p->signal->group_stop_count > 0) + if (!ptrace && p->signal->group_stop_count > 0) /* * A group stop is in progress and this is the group leader. * We won't report until all threads have stopped. @@ -1420,7 +1451,7 @@ static int wait_task_stopped(struct task_struct *p, if (!exit_code) goto unlock_sig; - if (!noreap) + if (!unlikely(options & WNOWAIT)) p->exit_code = 0; uid = p->uid; @@ -1438,10 +1469,10 @@ unlock_sig: */ get_task_struct(p); pid = task_pid_vnr(p); - why = (p->ptrace & PT_PTRACED) ? CLD_TRAPPED : CLD_STOPPED; + why = ptrace ? CLD_TRAPPED : CLD_STOPPED; read_unlock(&tasklist_lock); - if (unlikely(noreap)) + if (unlikely(options & WNOWAIT)) return wait_noreap_copyout(p, pid, uid, why, exit_code, infop, ru); @@ -1475,7 +1506,7 @@ unlock_sig: * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ -static int wait_task_continued(struct task_struct *p, int noreap, +static int wait_task_continued(struct task_struct *p, int options, struct siginfo __user *infop, int __user *stat_addr, struct rusage __user *ru) { @@ -1483,6 +1514,9 @@ static int wait_task_continued(struct task_struct *p, int noreap, pid_t pid; uid_t uid; + if (!unlikely(options & WCONTINUED)) + return 0; + if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) return 0; @@ -1492,7 +1526,7 @@ static int wait_task_continued(struct task_struct *p, int noreap, spin_unlock_irq(&p->sighand->siglock); return 0; } - if (!noreap) + if (!unlikely(options & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; spin_unlock_irq(&p->sighand->siglock); @@ -1518,89 +1552,161 @@ static int wait_task_continued(struct task_struct *p, int noreap, return retval; } +/* + * Consider @p for a wait by @parent. + * + * -ECHILD should be in *@notask_error before the first call. + * Returns nonzero for a final return, when we have unlocked tasklist_lock. + * Returns zero if the search for a child should continue; + * then *@notask_error is 0 if @p is an eligible child, + * or another error from security_task_wait(), or still -ECHILD. + */ +static int wait_consider_task(struct task_struct *parent, int ptrace, + struct task_struct *p, int *notask_error, + enum pid_type type, struct pid *pid, int options, + struct siginfo __user *infop, + int __user *stat_addr, struct rusage __user *ru) +{ + int ret = eligible_child(type, pid, options, p); + if (!ret) + return ret; + + if (unlikely(ret < 0)) { + /* + * If we have not yet seen any eligible child, + * then let this error code replace -ECHILD. + * A permission error will give the user a clue + * to look for security policy problems, rather + * than for mysterious wait bugs. + */ + if (*notask_error) + *notask_error = ret; + } + + if (likely(!ptrace) && unlikely(p->ptrace)) { + /* + * This child is hidden by ptrace. + * We aren't allowed to see it now, but eventually we will. + */ + *notask_error = 0; + return 0; + } + + if (p->exit_state == EXIT_DEAD) + return 0; + + /* + * We don't reap group leaders with subthreads. + */ + if (p->exit_state == EXIT_ZOMBIE && !delay_group_leader(p)) + return wait_task_zombie(p, options, infop, stat_addr, ru); + + /* + * It's stopped or running now, so it might + * later continue, exit, or stop again. + */ + *notask_error = 0; + + if (task_is_stopped_or_traced(p)) + return wait_task_stopped(ptrace, p, options, + infop, stat_addr, ru); + + return wait_task_continued(p, options, infop, stat_addr, ru); +} + +/* + * Do the work of do_wait() for one thread in the group, @tsk. + * + * -ECHILD should be in *@notask_error before the first call. + * Returns nonzero for a final return, when we have unlocked tasklist_lock. + * Returns zero if the search for a child should continue; then + * *@notask_error is 0 if there were any eligible children, + * or another error from security_task_wait(), or still -ECHILD. + */ +static int do_wait_thread(struct task_struct *tsk, int *notask_error, + enum pid_type type, struct pid *pid, int options, + struct siginfo __user *infop, int __user *stat_addr, + struct rusage __user *ru) +{ + struct task_struct *p; + + list_for_each_entry(p, &tsk->children, sibling) { + /* + * Do not consider detached threads. + */ + if (!task_detached(p)) { + int ret = wait_consider_task(tsk, 0, p, notask_error, + type, pid, options, + infop, stat_addr, ru); + if (ret) + return ret; + } + } + + return 0; +} + +static int ptrace_do_wait(struct task_struct *tsk, int *notask_error, + enum pid_type type, struct pid *pid, int options, + struct siginfo __user *infop, int __user *stat_addr, + struct rusage __user *ru) +{ + struct task_struct *p; + + /* + * Traditionally we see ptrace'd stopped tasks regardless of options. + */ + options |= WUNTRACED; + + list_for_each_entry(p, &tsk->ptraced, ptrace_entry) { + int ret = wait_consider_task(tsk, 1, p, notask_error, + type, pid, options, + infop, stat_addr, ru); + if (ret) + return ret; + } + + return 0; +} + static long do_wait(enum pid_type type, struct pid *pid, int options, struct siginfo __user *infop, int __user *stat_addr, struct rusage __user *ru) { DECLARE_WAITQUEUE(wait, current); struct task_struct *tsk; - int flag, retval; + int retval; add_wait_queue(¤t->signal->wait_chldexit,&wait); repeat: - /* If there is nothing that can match our critier just get out */ + /* + * If there is nothing that can match our critiera just get out. + * We will clear @retval to zero if we see any child that might later + * match our criteria, even if we are not able to reap it yet. + */ retval = -ECHILD; if ((type < PIDTYPE_MAX) && (!pid || hlist_empty(&pid->tasks[type]))) goto end; - /* - * We will set this flag if we see any child that might later - * match our criteria, even if we are not able to reap it yet. - */ - flag = retval = 0; current->state = TASK_INTERRUPTIBLE; read_lock(&tasklist_lock); tsk = current; do { - struct task_struct *p; - - list_for_each_entry(p, &tsk->children, sibling) { - int ret = eligible_child(type, pid, options, p); - if (!ret) - continue; - - if (unlikely(ret < 0)) { - retval = ret; - } else if (task_is_stopped_or_traced(p)) { - /* - * It's stopped now, so it might later - * continue, exit, or stop again. - */ - flag = 1; - if (!(p->ptrace & PT_PTRACED) && - !(options & WUNTRACED)) - continue; - - retval = wait_task_stopped(p, - (options & WNOWAIT), infop, - stat_addr, ru); - } else if (p->exit_state == EXIT_ZOMBIE && - !delay_group_leader(p)) { - /* - * We don't reap group leaders with subthreads. - */ - if (!likely(options & WEXITED)) - continue; - retval = wait_task_zombie(p, - (options & WNOWAIT), infop, - stat_addr, ru); - } else if (p->exit_state != EXIT_DEAD) { - /* - * It's running now, so it might later - * exit, stop, or stop and then continue. - */ - flag = 1; - if (!unlikely(options & WCONTINUED)) - continue; - retval = wait_task_continued(p, - (options & WNOWAIT), infop, - stat_addr, ru); - } - if (retval != 0) /* tasklist_lock released */ - goto end; - } - if (!flag) { - list_for_each_entry(p, &tsk->ptrace_children, - ptrace_list) { - flag = eligible_child(type, pid, options, p); - if (!flag) - continue; - if (likely(flag > 0)) - break; - retval = flag; - goto end; - } + int tsk_result = do_wait_thread(tsk, &retval, + type, pid, options, + infop, stat_addr, ru); + if (!tsk_result) + tsk_result = ptrace_do_wait(tsk, &retval, + type, pid, options, + infop, stat_addr, ru); + if (tsk_result) { + /* + * tasklist_lock is unlocked and we have a final result. + */ + retval = tsk_result; + goto end; } + if (options & __WNOTHREAD) break; tsk = next_thread(tsk); @@ -1608,16 +1714,14 @@ repeat: } while (tsk != current); read_unlock(&tasklist_lock); - if (flag) { - if (options & WNOHANG) - goto end; + if (!retval && !(options & WNOHANG)) { retval = -ERESTARTSYS; - if (signal_pending(current)) - goto end; - schedule(); - goto repeat; + if (!signal_pending(current)) { + schedule(); + goto repeat; + } } - retval = -ECHILD; + end: current->state = TASK_RUNNING; remove_wait_queue(¤t->signal->wait_chldexit,&wait); diff --git a/kernel/fork.c b/kernel/fork.c index 19908b26cf8..adefc1131f2 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -23,6 +23,7 @@ #include <linux/sem.h> #include <linux/file.h> #include <linux/fdtable.h> +#include <linux/iocontext.h> #include <linux/key.h> #include <linux/binfmts.h> #include <linux/mman.h> @@ -909,7 +910,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, rt_mutex_init_task(p); -#ifdef CONFIG_TRACE_IRQFLAGS +#ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled); DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif @@ -1124,8 +1125,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, */ p->group_leader = p; INIT_LIST_HEAD(&p->thread_group); - INIT_LIST_HEAD(&p->ptrace_children); - INIT_LIST_HEAD(&p->ptrace_list); + INIT_LIST_HEAD(&p->ptrace_entry); + INIT_LIST_HEAD(&p->ptraced); /* Now that the task is set up, run cgroup callbacks if * necessary. We need to run them before the task is visible @@ -1197,7 +1198,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, } if (likely(p->pid)) { - add_parent(p); + list_add_tail(&p->sibling, &p->real_parent->children); if (unlikely(p->ptrace & PT_PTRACED)) __ptrace_link(p, current->parent); diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 421be5fe5cc..b8e4dce80a7 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -300,11 +300,10 @@ EXPORT_SYMBOL_GPL(ktime_sub_ns); */ u64 ktime_divns(const ktime_t kt, s64 div) { - u64 dclc, inc, dns; + u64 dclc; int sft = 0; - dclc = dns = ktime_to_ns(kt); - inc = div; + dclc = ktime_to_ns(kt); /* Make sure the divisor is less than 2^32: */ while (div >> 32) { sft++; @@ -623,7 +622,7 @@ static void retrigger_next_event(void *arg) void clock_was_set(void) { /* Retrigger the CPU local events everywhere */ - on_each_cpu(retrigger_next_event, NULL, 0, 1); + on_each_cpu(retrigger_next_event, NULL, 1); } /* @@ -632,8 +631,6 @@ void clock_was_set(void) */ void hres_timers_resume(void) { - WARN_ON_ONCE(num_online_cpus() > 1); - /* Retrigger the CPU local events: */ retrigger_next_event(NULL); } @@ -1003,10 +1000,18 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) */ raise = timer->state == HRTIMER_STATE_PENDING; + /* + * We use preempt_disable to prevent this task from migrating after + * setting up the softirq and raising it. Otherwise, if me migrate + * we will raise the softirq on the wrong CPU. + */ + preempt_disable(); + unlock_hrtimer_base(timer, &flags); if (raise) hrtimer_raise_softirq(); + preempt_enable(); return ret; } @@ -1078,7 +1083,7 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer) } EXPORT_SYMBOL_GPL(hrtimer_get_remaining); -#if defined(CONFIG_NO_IDLE_HZ) || defined(CONFIG_NO_HZ) +#ifdef CONFIG_NO_HZ /** * hrtimer_get_next_event - get the time until next expiry event * @@ -1669,7 +1674,7 @@ void __init hrtimers_init(void) (void *)(long)smp_processor_id()); register_cpu_notifier(&hrtimers_nb); #ifdef CONFIG_HIGH_RES_TIMERS - open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq, NULL); + open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq); #endif } diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 46d6611a33b..77a51be3601 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -17,6 +17,8 @@ #ifdef CONFIG_SMP +cpumask_t irq_default_affinity = CPU_MASK_ALL; + /** * synchronize_irq - wait for pending IRQ handlers (on other CPUs) * @irq: interrupt number to wait for @@ -95,6 +97,27 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask) return 0; } +#ifndef CONFIG_AUTO_IRQ_AFFINITY +/* + * Generic version of the affinity autoselector. + */ +int irq_select_affinity(unsigned int irq) +{ + cpumask_t mask; + + if (!irq_can_set_affinity(irq)) + return 0; + + cpus_and(mask, cpu_online_map, irq_default_affinity); + + irq_desc[irq].affinity = mask; + irq_desc[irq].chip->set_affinity(irq, mask); + + set_balance_irq_affinity(irq, mask); + return 0; +} +#endif + #endif /** @@ -354,7 +377,7 @@ int setup_irq(unsigned int irq, struct irqaction *new) /* Setup the type (level, edge polarity) if configured: */ if (new->flags & IRQF_TRIGGER_MASK) { - if (desc->chip && desc->chip->set_type) + if (desc->chip->set_type) desc->chip->set_type(irq, new->flags & IRQF_TRIGGER_MASK); else @@ -364,8 +387,7 @@ int setup_irq(unsigned int irq, struct irqaction *new) */ printk(KERN_WARNING "No IRQF_TRIGGER set_type " "function for IRQ %d (%s)\n", irq, - desc->chip ? desc->chip->name : - "unknown"); + desc->chip->name); } else compat_irq_chip_set_default_handler(desc); @@ -382,6 +404,9 @@ int setup_irq(unsigned int irq, struct irqaction *new) } else /* Undo nested disables: */ desc->depth = 1; + + /* Set default affinity mask once everything is setup */ + irq_select_affinity(irq); } /* Reset broken irq detection when installing new handler */ desc->irq_count = 0; @@ -571,8 +596,6 @@ int request_irq(unsigned int irq, irq_handler_t handler, action->next = NULL; action->dev_id = dev_id; - select_smp_affinity(irq); - #ifdef CONFIG_DEBUG_SHIRQ if (irqflags & IRQF_SHARED) { /* diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index c2f2ccb0549..6c6d35d68ee 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -44,7 +44,7 @@ static int irq_affinity_write_proc(struct file *file, const char __user *buffer, unsigned long count, void *data) { unsigned int irq = (int)(long)data, full_count = count, err; - cpumask_t new_value, tmp; + cpumask_t new_value; if (!irq_desc[irq].chip->set_affinity || no_irq_affinity || irq_balancing_disabled(irq)) @@ -62,17 +62,51 @@ static int irq_affinity_write_proc(struct file *file, const char __user *buffer, * way to make the system unusable accidentally :-) At least * one online CPU still has to be targeted. */ - cpus_and(tmp, new_value, cpu_online_map); - if (cpus_empty(tmp)) + if (!cpus_intersects(new_value, cpu_online_map)) /* Special case for empty set - allow the architecture code to set default SMP affinity. */ - return select_smp_affinity(irq) ? -EINVAL : full_count; + return irq_select_affinity(irq) ? -EINVAL : full_count; irq_set_affinity(irq, new_value); return full_count; } +static int default_affinity_read(char *page, char **start, off_t off, + int count, int *eof, void *data) +{ + int len = cpumask_scnprintf(page, count, irq_default_affinity); + if (count - len < 2) + return -EINVAL; + len += sprintf(page + len, "\n"); + return len; +} + +static int default_affinity_write(struct file *file, const char __user *buffer, + unsigned long count, void *data) +{ + unsigned int full_count = count, err; + cpumask_t new_value; + + err = cpumask_parse_user(buffer, count, new_value); + if (err) + return err; + + if (!is_affinity_mask_valid(new_value)) + return -EINVAL; + + /* + * Do not allow disabling IRQs completely - it's a too easy + * way to make the system unusable accidentally :-) At least + * one online CPU still has to be targeted. + */ + if (!cpus_intersects(new_value, cpu_online_map)) + return -EINVAL; + + irq_default_affinity = new_value; + + return full_count; +} #endif static int irq_spurious_read(char *page, char **start, off_t off, @@ -171,6 +205,21 @@ void unregister_handler_proc(unsigned int irq, struct irqaction *action) remove_proc_entry(action->dir->name, irq_desc[irq].dir); } +void register_default_affinity_proc(void) +{ +#ifdef CONFIG_SMP + struct proc_dir_entry *entry; + + /* create /proc/irq/default_smp_affinity */ + entry = create_proc_entry("default_smp_affinity", 0600, root_irq_dir); + if (entry) { + entry->data = NULL; + entry->read_proc = default_affinity_read; + entry->write_proc = default_affinity_write; + } +#endif +} + void init_irq_proc(void) { int i; @@ -180,6 +229,8 @@ void init_irq_proc(void) if (!root_irq_dir) return; + register_default_affinity_proc(); + /* * Create entries for all existing IRQs. */ diff --git a/kernel/kprobes.c b/kernel/kprobes.c index d4998f81e22..1485ca8d0e0 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -79,7 +79,7 @@ static DEFINE_PER_CPU(struct kprobe *, kprobe_instance) = NULL; * * For such cases, we now have a blacklist */ -struct kprobe_blackpoint kprobe_blacklist[] = { +static struct kprobe_blackpoint kprobe_blacklist[] = { {"preempt_schedule",}, {NULL} /* Terminator */ }; diff --git a/kernel/kthread.c b/kernel/kthread.c index bd1b9ea024e..ac3fb732664 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -180,6 +180,7 @@ void kthread_bind(struct task_struct *k, unsigned int cpu) set_task_cpu(k, cpu); k->cpus_allowed = cpumask_of_cpu(cpu); k->rt.nr_cpus_allowed = 1; + k->flags |= PF_THREAD_BOUND; } EXPORT_SYMBOL(kthread_bind); @@ -234,7 +235,7 @@ int kthreadd(void *unused) set_user_nice(tsk, KTHREAD_NICE_LEVEL); set_cpus_allowed(tsk, CPU_MASK_ALL); - current->flags |= PF_NOFREEZE; + current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG; for (;;) { set_current_state(TASK_INTERRUPTIBLE); diff --git a/kernel/lockdep.c b/kernel/lockdep.c index 81a4e4a3f08..d38a6436297 100644 --- a/kernel/lockdep.c +++ b/kernel/lockdep.c @@ -39,6 +39,7 @@ #include <linux/irqflags.h> #include <linux/utsname.h> #include <linux/hash.h> +#include <linux/ftrace.h> #include <asm/sections.h> @@ -81,6 +82,8 @@ static int graph_lock(void) __raw_spin_unlock(&lockdep_lock); return 0; } + /* prevent any recursions within lockdep from causing deadlocks */ + current->lockdep_recursion++; return 1; } @@ -89,6 +92,7 @@ static inline int graph_unlock(void) if (debug_locks && !__raw_spin_is_locked(&lockdep_lock)) return DEBUG_LOCKS_WARN_ON(1); + current->lockdep_recursion--; __raw_spin_unlock(&lockdep_lock); return 0; } @@ -982,7 +986,7 @@ check_noncircular(struct lock_class *source, unsigned int depth) return 1; } -#ifdef CONFIG_TRACE_IRQFLAGS +#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) /* * Forwards and backwards subgraph searching, for the purposes of * proving that two subgraphs can be connected by a new dependency @@ -1458,7 +1462,14 @@ out_bug: } unsigned long nr_lock_chains; -static struct lock_chain lock_chains[MAX_LOCKDEP_CHAINS]; +struct lock_chain lock_chains[MAX_LOCKDEP_CHAINS]; +int nr_chain_hlocks; +static u16 chain_hlocks[MAX_LOCKDEP_CHAIN_HLOCKS]; + +struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i) +{ + return lock_classes + chain_hlocks[chain->base + i]; +} /* * Look up a dependency chain. If the key is not present yet then @@ -1466,10 +1477,15 @@ static struct lock_chain lock_chains[MAX_LOCKDEP_CHAINS]; * validated. If the key is already hashed, return 0. * (On return with 1 graph_lock is held.) */ -static inline int lookup_chain_cache(u64 chain_key, struct lock_class *class) +static inline int lookup_chain_cache(struct task_struct *curr, + struct held_lock *hlock, + u64 chain_key) { + struct lock_class *class = hlock->class; struct list_head *hash_head = chainhashentry(chain_key); struct lock_chain *chain; + struct held_lock *hlock_curr, *hlock_next; + int i, j, n, cn; if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) return 0; @@ -1517,6 +1533,32 @@ cache_hit: } chain = lock_chains + nr_lock_chains++; chain->chain_key = chain_key; + chain->irq_context = hlock->irq_context; + /* Find the first held_lock of current chain */ + hlock_next = hlock; + for (i = curr->lockdep_depth - 1; i >= 0; i--) { + hlock_curr = curr->held_locks + i; + if (hlock_curr->irq_context != hlock_next->irq_context) + break; + hlock_next = hlock; + } + i++; + chain->depth = curr->lockdep_depth + 1 - i; + cn = nr_chain_hlocks; + while (cn + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS) { + n = cmpxchg(&nr_chain_hlocks, cn, cn + chain->depth); + if (n == cn) + break; + cn = n; + } + if (likely(cn + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) { + chain->base = cn; + for (j = 0; j < chain->depth - 1; j++, i++) { + int lock_id = curr->held_locks[i].class - lock_classes; + chain_hlocks[chain->base + j] = lock_id; + } + chain_hlocks[chain->base + j] = class - lock_classes; + } list_add_tail_rcu(&chain->entry, hash_head); debug_atomic_inc(&chain_lookup_misses); inc_chains(); @@ -1538,7 +1580,7 @@ static int validate_chain(struct task_struct *curr, struct lockdep_map *lock, * graph_lock for us) */ if (!hlock->trylock && (hlock->check == 2) && - lookup_chain_cache(chain_key, hlock->class)) { + lookup_chain_cache(curr, hlock, chain_key)) { /* * Check whether last held lock: * @@ -1680,7 +1722,7 @@ valid_state(struct task_struct *curr, struct held_lock *this, static int mark_lock(struct task_struct *curr, struct held_lock *this, enum lock_usage_bit new_bit); -#ifdef CONFIG_TRACE_IRQFLAGS +#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) /* * print irq inversion bug: @@ -2013,11 +2055,13 @@ void early_boot_irqs_on(void) /* * Hardirqs will be enabled: */ -void trace_hardirqs_on(void) +void trace_hardirqs_on_caller(unsigned long a0) { struct task_struct *curr = current; unsigned long ip; + time_hardirqs_on(CALLER_ADDR0, a0); + if (unlikely(!debug_locks || current->lockdep_recursion)) return; @@ -2055,16 +2099,23 @@ void trace_hardirqs_on(void) curr->hardirq_enable_event = ++curr->irq_events; debug_atomic_inc(&hardirqs_on_events); } +EXPORT_SYMBOL(trace_hardirqs_on_caller); +void trace_hardirqs_on(void) +{ + trace_hardirqs_on_caller(CALLER_ADDR0); +} EXPORT_SYMBOL(trace_hardirqs_on); /* * Hardirqs were disabled: */ -void trace_hardirqs_off(void) +void trace_hardirqs_off_caller(unsigned long a0) { struct task_struct *curr = current; + time_hardirqs_off(CALLER_ADDR0, a0); + if (unlikely(!debug_locks || current->lockdep_recursion)) return; @@ -2082,7 +2133,12 @@ void trace_hardirqs_off(void) } else debug_atomic_inc(&redundant_hardirqs_off); } +EXPORT_SYMBOL(trace_hardirqs_off_caller); +void trace_hardirqs_off(void) +{ + trace_hardirqs_off_caller(CALLER_ADDR0); +} EXPORT_SYMBOL(trace_hardirqs_off); /* @@ -2246,7 +2302,7 @@ static inline int separate_irq_context(struct task_struct *curr, * Mark a lock with a usage bit, and validate the state transition: */ static int mark_lock(struct task_struct *curr, struct held_lock *this, - enum lock_usage_bit new_bit) + enum lock_usage_bit new_bit) { unsigned int new_mask = 1 << new_bit, ret = 1; @@ -2650,7 +2706,8 @@ __lock_release(struct lockdep_map *lock, int nested, unsigned long ip) */ static void check_flags(unsigned long flags) { -#if defined(CONFIG_DEBUG_LOCKDEP) && defined(CONFIG_TRACE_IRQFLAGS) +#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_DEBUG_LOCKDEP) && \ + defined(CONFIG_TRACE_IRQFLAGS) if (!debug_locks) return; @@ -2686,7 +2743,7 @@ static void check_flags(unsigned long flags) * and also avoid lockdep recursion: */ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, - int trylock, int read, int check, unsigned long ip) + int trylock, int read, int check, unsigned long ip) { unsigned long flags; @@ -2708,7 +2765,8 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass, EXPORT_SYMBOL_GPL(lock_acquire); -void lock_release(struct lockdep_map *lock, int nested, unsigned long ip) +void lock_release(struct lockdep_map *lock, int nested, + unsigned long ip) { unsigned long flags; diff --git a/kernel/lockdep_internals.h b/kernel/lockdep_internals.h index 8ce09bc4613..c3600a091a2 100644 --- a/kernel/lockdep_internals.h +++ b/kernel/lockdep_internals.h @@ -23,6 +23,8 @@ #define MAX_LOCKDEP_CHAINS_BITS 14 #define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) +#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) + /* * Stack-trace: tightly packed array of stack backtrace * addresses. Protected by the hash_lock. @@ -30,15 +32,19 @@ #define MAX_STACK_TRACE_ENTRIES 262144UL extern struct list_head all_lock_classes; +extern struct lock_chain lock_chains[]; extern void get_usage_chars(struct lock_class *class, char *c1, char *c2, char *c3, char *c4); extern const char * __get_key_name(struct lockdep_subclass_key *key, char *str); +struct lock_class *lock_chain_get_class(struct lock_chain *chain, int i); + extern unsigned long nr_lock_classes; extern unsigned long nr_list_entries; extern unsigned long nr_lock_chains; +extern int nr_chain_hlocks; extern unsigned long nr_stack_trace_entries; extern unsigned int nr_hardirq_chains; diff --git a/kernel/lockdep_proc.c b/kernel/lockdep_proc.c index dc5d29648d8..9b0e940e254 100644 --- a/kernel/lockdep_proc.c +++ b/kernel/lockdep_proc.c @@ -139,7 +139,7 @@ static int l_show(struct seq_file *m, void *v) list_for_each_entry(entry, &class->locks_after, entry) { if (entry->distance == 1) { - seq_printf(m, " -> [%p] ", entry->class); + seq_printf(m, " -> [%p] ", entry->class->key); print_name(m, entry->class); seq_puts(m, "\n"); } @@ -178,6 +178,95 @@ static const struct file_operations proc_lockdep_operations = { .release = seq_release, }; +#ifdef CONFIG_PROVE_LOCKING +static void *lc_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct lock_chain *chain; + + (*pos)++; + + if (v == SEQ_START_TOKEN) + chain = m->private; + else { + chain = v; + + if (*pos < nr_lock_chains) + chain = lock_chains + *pos; + else + chain = NULL; + } + + return chain; +} + +static void *lc_start(struct seq_file *m, loff_t *pos) +{ + if (*pos == 0) + return SEQ_START_TOKEN; + + if (*pos < nr_lock_chains) + return lock_chains + *pos; + + return NULL; +} + +static void lc_stop(struct seq_file *m, void *v) +{ +} + +static int lc_show(struct seq_file *m, void *v) +{ + struct lock_chain *chain = v; + struct lock_class *class; + int i; + + if (v == SEQ_START_TOKEN) { + seq_printf(m, "all lock chains:\n"); + return 0; + } + + seq_printf(m, "irq_context: %d\n", chain->irq_context); + + for (i = 0; i < chain->depth; i++) { + class = lock_chain_get_class(chain, i); + seq_printf(m, "[%p] ", class->key); + print_name(m, class); + seq_puts(m, "\n"); + } + seq_puts(m, "\n"); + + return 0; +} + +static const struct seq_operations lockdep_chains_ops = { + .start = lc_start, + .next = lc_next, + .stop = lc_stop, + .show = lc_show, +}; + +static int lockdep_chains_open(struct inode *inode, struct file *file) +{ + int res = seq_open(file, &lockdep_chains_ops); + if (!res) { + struct seq_file *m = file->private_data; + + if (nr_lock_chains) + m->private = lock_chains; + else + m->private = NULL; + } + return res; +} + +static const struct file_operations proc_lockdep_chains_operations = { + .open = lockdep_chains_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; +#endif /* CONFIG_PROVE_LOCKING */ + static void lockdep_stats_debug_show(struct seq_file *m) { #ifdef CONFIG_DEBUG_LOCKDEP @@ -294,6 +383,8 @@ static int lockdep_stats_show(struct seq_file *m, void *v) #ifdef CONFIG_PROVE_LOCKING seq_printf(m, " dependency chains: %11lu [max: %lu]\n", nr_lock_chains, MAX_LOCKDEP_CHAINS); + seq_printf(m, " dependency chain hlocks: %11d [max: %lu]\n", + nr_chain_hlocks, MAX_LOCKDEP_CHAIN_HLOCKS); #endif #ifdef CONFIG_TRACE_IRQFLAGS @@ -661,6 +752,10 @@ static const struct file_operations proc_lock_stat_operations = { static int __init lockdep_proc_init(void) { proc_create("lockdep", S_IRUSR, NULL, &proc_lockdep_operations); +#ifdef CONFIG_PROVE_LOCKING + proc_create("lockdep_chains", S_IRUSR, NULL, + &proc_lockdep_chains_operations); +#endif proc_create("lockdep_stats", S_IRUSR, NULL, &proc_lockdep_stats_operations); diff --git a/kernel/marker.c b/kernel/marker.c index b5a9fe1d50d..1abfb923b76 100644 --- a/kernel/marker.c +++ b/kernel/marker.c @@ -55,8 +55,8 @@ static DEFINE_MUTEX(markers_mutex); struct marker_entry { struct hlist_node hlist; char *format; - void (*call)(const struct marker *mdata, /* Probe wrapper */ - void *call_private, const char *fmt, ...); + /* Probe wrapper */ + void (*call)(const struct marker *mdata, void *call_private, ...); struct marker_probe_closure single; struct marker_probe_closure *multi; int refcount; /* Number of times armed. 0 if disarmed. */ @@ -91,15 +91,13 @@ EXPORT_SYMBOL_GPL(__mark_empty_function); * marker_probe_cb Callback that prepares the variable argument list for probes. * @mdata: pointer of type struct marker * @call_private: caller site private data - * @fmt: format string * @...: Variable argument list. * * Since we do not use "typical" pointer based RCU in the 1 argument case, we * need to put a full smp_rmb() in this branch. This is why we do not use * rcu_dereference() for the pointer read. */ -void marker_probe_cb(const struct marker *mdata, void *call_private, - const char *fmt, ...) +void marker_probe_cb(const struct marker *mdata, void *call_private, ...) { va_list args; char ptype; @@ -120,8 +118,9 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, /* Must read the ptr before private data. They are not data * dependant, so we put an explicit smp_rmb() here. */ smp_rmb(); - va_start(args, fmt); - func(mdata->single.probe_private, call_private, fmt, &args); + va_start(args, call_private); + func(mdata->single.probe_private, call_private, mdata->format, + &args); va_end(args); } else { struct marker_probe_closure *multi; @@ -136,9 +135,9 @@ void marker_probe_cb(const struct marker *mdata, void *call_private, smp_read_barrier_depends(); multi = mdata->multi; for (i = 0; multi[i].func; i++) { - va_start(args, fmt); - multi[i].func(multi[i].probe_private, call_private, fmt, - &args); + va_start(args, call_private); + multi[i].func(multi[i].probe_private, call_private, + mdata->format, &args); va_end(args); } } @@ -150,13 +149,11 @@ EXPORT_SYMBOL_GPL(marker_probe_cb); * marker_probe_cb Callback that does not prepare the variable argument list. * @mdata: pointer of type struct marker * @call_private: caller site private data - * @fmt: format string * @...: Variable argument list. * * Should be connected to markers "MARK_NOARGS". */ -void marker_probe_cb_noarg(const struct marker *mdata, - void *call_private, const char *fmt, ...) +void marker_probe_cb_noarg(const struct marker *mdata, void *call_private, ...) { va_list args; /* not initialized */ char ptype; @@ -172,7 +169,8 @@ void marker_probe_cb_noarg(const struct marker *mdata, /* Must read the ptr before private data. They are not data * dependant, so we put an explicit smp_rmb() here. */ smp_rmb(); - func(mdata->single.probe_private, call_private, fmt, &args); + func(mdata->single.probe_private, call_private, mdata->format, + &args); } else { struct marker_probe_closure *multi; int i; @@ -186,8 +184,8 @@ void marker_probe_cb_noarg(const struct marker *mdata, smp_read_barrier_depends(); multi = mdata->multi; for (i = 0; multi[i].func; i++) - multi[i].func(multi[i].probe_private, call_private, fmt, - &args); + multi[i].func(multi[i].probe_private, call_private, + mdata->format, &args); } preempt_enable(); } diff --git a/kernel/mutex-debug.c b/kernel/mutex-debug.c index 3aaa06c561d..1d94160eb53 100644 --- a/kernel/mutex-debug.c +++ b/kernel/mutex-debug.c @@ -79,8 +79,8 @@ void debug_mutex_unlock(struct mutex *lock) if (unlikely(!debug_locks)) return; - DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info()); DEBUG_LOCKS_WARN_ON(lock->magic != lock); + DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info()); DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next); DEBUG_LOCKS_WARN_ON(lock->owner != current_thread_info()); } diff --git a/kernel/mutex.c b/kernel/mutex.c index d046a345d36..bcdc9ac8ef6 100644 --- a/kernel/mutex.c +++ b/kernel/mutex.c @@ -165,10 +165,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass, * got a signal? (This code gets eliminated in the * TASK_UNINTERRUPTIBLE case.) */ - if (unlikely((state == TASK_INTERRUPTIBLE && - signal_pending(task)) || - (state == TASK_KILLABLE && - fatal_signal_pending(task)))) { + if (unlikely(signal_pending_state(state, task))) { mutex_remove_waiter(lock, &waiter, task_thread_info(task)); mutex_release(&lock->dep_map, 1, ip); diff --git a/kernel/pid.c b/kernel/pid.c index 20d59fa2d49..30bd5d4b2ac 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -30,6 +30,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/init.h> +#include <linux/rculist.h> #include <linux/bootmem.h> #include <linux/hash.h> #include <linux/pid_namespace.h> diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c index 0afe32be4c8..8cb75702638 100644 --- a/kernel/pm_qos_params.c +++ b/kernel/pm_qos_params.c @@ -29,6 +29,7 @@ #include <linux/pm_qos_params.h> #include <linux/sched.h> +#include <linux/smp_lock.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/time.h> @@ -358,15 +359,19 @@ static int pm_qos_power_open(struct inode *inode, struct file *filp) int ret; long pm_qos_class; + lock_kernel(); pm_qos_class = find_pm_qos_object_by_minor(iminor(inode)); if (pm_qos_class >= 0) { filp->private_data = (void *)pm_qos_class; sprintf(name, "process_%d", current->pid); ret = pm_qos_add_requirement(pm_qos_class, name, PM_QOS_DEFAULT_VALUE); - if (ret >= 0) + if (ret >= 0) { + unlock_kernel(); return 0; + } } + unlock_kernel(); return -EPERM; } diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index f1525ad06cb..c42a03aef36 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -1037,6 +1037,9 @@ static void check_thread_timers(struct task_struct *tsk, sig->rlim[RLIMIT_RTTIME].rlim_cur += USEC_PER_SEC; } + printk(KERN_INFO + "RT Watchdog Timeout: %s[%d]\n", + tsk->comm, task_pid_nr(tsk)); __group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk); } } diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 14a656cdc65..f011e0870b5 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -180,6 +180,17 @@ static void platform_restore_cleanup(int platform_mode) } /** + * platform_recover - recover the platform from a failure to suspend + * devices. + */ + +static void platform_recover(int platform_mode) +{ + if (platform_mode && hibernation_ops && hibernation_ops->recover) + hibernation_ops->recover(); +} + +/** * create_image - freeze devices that need to be frozen with interrupts * off, create the hibernation image and thaw those devices. Control * reappears in this routine after a restore. @@ -193,6 +204,7 @@ static int create_image(int platform_mode) if (error) return error; + device_pm_lock(); local_irq_disable(); /* At this point, device_suspend() has been called, but *not* * device_power_down(). We *must* call device_power_down() now. @@ -224,9 +236,11 @@ static int create_image(int platform_mode) /* NOTE: device_power_up() is just a resume() for devices * that suspended with irqs off ... no overall powerup. */ - device_power_up(); + device_power_up(in_suspend ? + (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); Enable_irqs: local_irq_enable(); + device_pm_unlock(); return error; } @@ -255,10 +269,10 @@ int hibernation_snapshot(int platform_mode) suspend_console(); error = device_suspend(PMSG_FREEZE); if (error) - goto Resume_console; + goto Recover_platform; if (hibernation_test(TEST_DEVICES)) - goto Resume_devices; + goto Recover_platform; error = platform_pre_snapshot(platform_mode); if (error || hibernation_test(TEST_PLATFORM)) @@ -280,12 +294,16 @@ int hibernation_snapshot(int platform_mode) Finish: platform_finish(platform_mode); Resume_devices: - device_resume(); - Resume_console: + device_resume(in_suspend ? + (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); resume_console(); Close: platform_end(platform_mode); return error; + + Recover_platform: + platform_recover(platform_mode); + goto Resume_devices; } /** @@ -300,8 +318,9 @@ static int resume_target_kernel(void) { int error; + device_pm_lock(); local_irq_disable(); - error = device_power_down(PMSG_PRETHAW); + error = device_power_down(PMSG_QUIESCE); if (error) { printk(KERN_ERR "PM: Some devices failed to power down, " "aborting resume\n"); @@ -329,9 +348,10 @@ static int resume_target_kernel(void) swsusp_free(); restore_processor_state(); touch_softlockup_watchdog(); - device_power_up(); + device_power_up(PMSG_RECOVER); Enable_irqs: local_irq_enable(); + device_pm_unlock(); return error; } @@ -350,7 +370,7 @@ int hibernation_restore(int platform_mode) pm_prepare_console(); suspend_console(); - error = device_suspend(PMSG_PRETHAW); + error = device_suspend(PMSG_QUIESCE); if (error) goto Finish; @@ -362,7 +382,7 @@ int hibernation_restore(int platform_mode) enable_nonboot_cpus(); } platform_restore_cleanup(platform_mode); - device_resume(); + device_resume(PMSG_RECOVER); Finish: resume_console(); pm_restore_console(); @@ -392,8 +412,11 @@ int hibernation_platform_enter(void) suspend_console(); error = device_suspend(PMSG_HIBERNATE); - if (error) - goto Resume_console; + if (error) { + if (hibernation_ops->recover) + hibernation_ops->recover(); + goto Resume_devices; + } error = hibernation_ops->prepare(); if (error) @@ -403,6 +426,7 @@ int hibernation_platform_enter(void) if (error) goto Finish; + device_pm_lock(); local_irq_disable(); error = device_power_down(PMSG_HIBERNATE); if (!error) { @@ -411,6 +435,7 @@ int hibernation_platform_enter(void) while (1); } local_irq_enable(); + device_pm_unlock(); /* * We don't need to reenable the nonboot CPUs or resume consoles, since @@ -419,8 +444,7 @@ int hibernation_platform_enter(void) Finish: hibernation_ops->finish(); Resume_devices: - device_resume(); - Resume_console: + device_resume(PMSG_RESTORE); resume_console(); Close: hibernation_ops->end(); diff --git a/kernel/power/main.c b/kernel/power/main.c index 6a6d5eb3524..3398f4651aa 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -228,6 +228,7 @@ static int suspend_enter(suspend_state_t state) { int error = 0; + device_pm_lock(); arch_suspend_disable_irqs(); BUG_ON(!irqs_disabled()); @@ -239,10 +240,11 @@ static int suspend_enter(suspend_state_t state) if (!suspend_test(TEST_CORE)) error = suspend_ops->enter(state); - device_power_up(); + device_power_up(PMSG_RESUME); Done: arch_suspend_enable_irqs(); BUG_ON(irqs_disabled()); + device_pm_unlock(); return error; } @@ -267,11 +269,11 @@ int suspend_devices_and_enter(suspend_state_t state) error = device_suspend(PMSG_SUSPEND); if (error) { printk(KERN_ERR "PM: Some devices failed to suspend\n"); - goto Resume_console; + goto Recover_platform; } if (suspend_test(TEST_DEVICES)) - goto Resume_devices; + goto Recover_platform; if (suspend_ops->prepare) { error = suspend_ops->prepare(); @@ -291,13 +293,17 @@ int suspend_devices_and_enter(suspend_state_t state) if (suspend_ops->finish) suspend_ops->finish(); Resume_devices: - device_resume(); - Resume_console: + device_resume(PMSG_RESUME); resume_console(); Close: if (suspend_ops->end) suspend_ops->end(); return error; + + Recover_platform: + if (suspend_ops->recover) + suspend_ops->recover(); + goto Resume_devices; } /** diff --git a/kernel/power/process.c b/kernel/power/process.c index f1d0b345c9b..5fb87652f21 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -19,9 +19,6 @@ */ #define TIMEOUT (20 * HZ) -#define FREEZER_KERNEL_THREADS 0 -#define FREEZER_USER_SPACE 1 - static inline int freezeable(struct task_struct * p) { if ((p == current) || @@ -84,63 +81,53 @@ static void fake_signal_wake_up(struct task_struct *p) spin_unlock_irqrestore(&p->sighand->siglock, flags); } -static int has_mm(struct task_struct *p) +static inline bool should_send_signal(struct task_struct *p) { - return (p->mm && !(p->flags & PF_BORROWED_MM)); + return !(p->flags & PF_FREEZER_NOSIG); } /** * freeze_task - send a freeze request to given task * @p: task to send the request to - * @with_mm_only: if set, the request will only be sent if the task has its - * own mm - * Return value: 0, if @with_mm_only is set and the task has no mm of its - * own or the task is frozen, 1, otherwise + * @sig_only: if set, the request will only be sent if the task has the + * PF_FREEZER_NOSIG flag unset + * Return value: 'false', if @sig_only is set and the task has + * PF_FREEZER_NOSIG set or the task is frozen, 'true', otherwise * - * The freeze request is sent by seting the tasks's TIF_FREEZE flag and + * The freeze request is sent by setting the tasks's TIF_FREEZE flag and * either sending a fake signal to it or waking it up, depending on whether - * or not it has its own mm (ie. it is a user land task). If @with_mm_only - * is set and the task has no mm of its own (ie. it is a kernel thread), - * its TIF_FREEZE flag should not be set. - * - * The task_lock() is necessary to prevent races with exit_mm() or - * use_mm()/unuse_mm() from occuring. + * or not it has PF_FREEZER_NOSIG set. If @sig_only is set and the task + * has PF_FREEZER_NOSIG set (ie. it is a typical kernel thread), its + * TIF_FREEZE flag will not be set. */ -static int freeze_task(struct task_struct *p, int with_mm_only) +static bool freeze_task(struct task_struct *p, bool sig_only) { - int ret = 1; + /* + * We first check if the task is freezing and next if it has already + * been frozen to avoid the race with frozen_process() which first marks + * the task as frozen and next clears its TIF_FREEZE. + */ + if (!freezing(p)) { + rmb(); + if (frozen(p)) + return false; - task_lock(p); - if (freezing(p)) { - if (has_mm(p)) { - if (!signal_pending(p)) - fake_signal_wake_up(p); - } else { - if (with_mm_only) - ret = 0; - else - wake_up_state(p, TASK_INTERRUPTIBLE); - } + if (!sig_only || should_send_signal(p)) + set_freeze_flag(p); + else + return false; + } + + if (should_send_signal(p)) { + if (!signal_pending(p)) + fake_signal_wake_up(p); + } else if (sig_only) { + return false; } else { - rmb(); - if (frozen(p)) { - ret = 0; - } else { - if (has_mm(p)) { - set_freeze_flag(p); - fake_signal_wake_up(p); - } else { - if (with_mm_only) { - ret = 0; - } else { - set_freeze_flag(p); - wake_up_state(p, TASK_INTERRUPTIBLE); - } - } - } + wake_up_state(p, TASK_INTERRUPTIBLE); } - task_unlock(p); - return ret; + + return true; } static void cancel_freezing(struct task_struct *p) @@ -156,7 +143,7 @@ static void cancel_freezing(struct task_struct *p) } } -static int try_to_freeze_tasks(int freeze_user_space) +static int try_to_freeze_tasks(bool sig_only) { struct task_struct *g, *p; unsigned long end_time; @@ -175,7 +162,7 @@ static int try_to_freeze_tasks(int freeze_user_space) if (frozen(p) || !freezeable(p)) continue; - if (!freeze_task(p, freeze_user_space)) + if (!freeze_task(p, sig_only)) continue; /* @@ -235,13 +222,13 @@ int freeze_processes(void) int error; printk("Freezing user space processes ... "); - error = try_to_freeze_tasks(FREEZER_USER_SPACE); + error = try_to_freeze_tasks(true); if (error) goto Exit; printk("done.\n"); printk("Freezing remaining freezable tasks ... "); - error = try_to_freeze_tasks(FREEZER_KERNEL_THREADS); + error = try_to_freeze_tasks(false); if (error) goto Exit; printk("done."); @@ -251,7 +238,7 @@ int freeze_processes(void) return error; } -static void thaw_tasks(int thaw_user_space) +static void thaw_tasks(bool nosig_only) { struct task_struct *g, *p; @@ -260,7 +247,7 @@ static void thaw_tasks(int thaw_user_space) if (!freezeable(p)) continue; - if (!p->mm == thaw_user_space) + if (nosig_only && should_send_signal(p)) continue; thaw_process(p); @@ -271,8 +258,8 @@ static void thaw_tasks(int thaw_user_space) void thaw_processes(void) { printk("Restarting tasks ... "); - thaw_tasks(FREEZER_KERNEL_THREADS); - thaw_tasks(FREEZER_USER_SPACE); + thaw_tasks(true); + thaw_tasks(false); schedule(); printk("done.\n"); } diff --git a/kernel/power/user.c b/kernel/power/user.c index f5512cb3aa8..a6332a31326 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -23,6 +23,7 @@ #include <linux/console.h> #include <linux/cpu.h> #include <linux/freezer.h> +#include <linux/smp_lock.h> #include <asm/uaccess.h> @@ -69,16 +70,22 @@ static int snapshot_open(struct inode *inode, struct file *filp) struct snapshot_data *data; int error; - if (!atomic_add_unless(&snapshot_device_available, -1, 0)) - return -EBUSY; + mutex_lock(&pm_mutex); + + if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { + error = -EBUSY; + goto Unlock; + } if ((filp->f_flags & O_ACCMODE) == O_RDWR) { atomic_inc(&snapshot_device_available); - return -ENOSYS; + error = -ENOSYS; + goto Unlock; } if(create_basic_memory_bitmaps()) { atomic_inc(&snapshot_device_available); - return -ENOMEM; + error = -ENOMEM; + goto Unlock; } nonseekable_open(inode, filp); data = &snapshot_state; @@ -98,33 +105,36 @@ static int snapshot_open(struct inode *inode, struct file *filp) if (error) pm_notifier_call_chain(PM_POST_HIBERNATION); } - if (error) { + if (error) atomic_inc(&snapshot_device_available); - return error; - } data->frozen = 0; data->ready = 0; data->platform_support = 0; - return 0; + Unlock: + mutex_unlock(&pm_mutex); + + return error; } static int snapshot_release(struct inode *inode, struct file *filp) { struct snapshot_data *data; + mutex_lock(&pm_mutex); + swsusp_free(); free_basic_memory_bitmaps(); data = filp->private_data; free_all_swap_pages(data->swap); - if (data->frozen) { - mutex_lock(&pm_mutex); + if (data->frozen) thaw_processes(); - mutex_unlock(&pm_mutex); - } pm_notifier_call_chain(data->mode == O_WRONLY ? PM_POST_HIBERNATION : PM_POST_RESTORE); atomic_inc(&snapshot_device_available); + + mutex_unlock(&pm_mutex); + return 0; } @@ -134,9 +144,13 @@ static ssize_t snapshot_read(struct file *filp, char __user *buf, struct snapshot_data *data; ssize_t res; + mutex_lock(&pm_mutex); + data = filp->private_data; - if (!data->ready) - return -ENODATA; + if (!data->ready) { + res = -ENODATA; + goto Unlock; + } res = snapshot_read_next(&data->handle, count); if (res > 0) { if (copy_to_user(buf, data_of(data->handle), res)) @@ -144,6 +158,10 @@ static ssize_t snapshot_read(struct file *filp, char __user *buf, else *offp = data->handle.offset; } + + Unlock: + mutex_unlock(&pm_mutex); + return res; } @@ -153,6 +171,8 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf, struct snapshot_data *data; ssize_t res; + mutex_lock(&pm_mutex); + data = filp->private_data; res = snapshot_write_next(&data->handle, count); if (res > 0) { @@ -161,11 +181,14 @@ static ssize_t snapshot_write(struct file *filp, const char __user *buf, else *offp = data->handle.offset; } + + mutex_unlock(&pm_mutex); + return res; } -static int snapshot_ioctl(struct inode *inode, struct file *filp, - unsigned int cmd, unsigned long arg) +static long snapshot_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg) { int error = 0; struct snapshot_data *data; @@ -179,6 +202,9 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, if (!capable(CAP_SYS_ADMIN)) return -EPERM; + if (!mutex_trylock(&pm_mutex)) + return -EBUSY; + data = filp->private_data; switch (cmd) { @@ -186,7 +212,6 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, case SNAPSHOT_FREEZE: if (data->frozen) break; - mutex_lock(&pm_mutex); printk("Syncing filesystems ... "); sys_sync(); printk("done.\n"); @@ -194,7 +219,6 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, error = freeze_processes(); if (error) thaw_processes(); - mutex_unlock(&pm_mutex); if (!error) data->frozen = 1; break; @@ -202,9 +226,7 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, case SNAPSHOT_UNFREEZE: if (!data->frozen || data->ready) break; - mutex_lock(&pm_mutex); thaw_processes(); - mutex_unlock(&pm_mutex); data->frozen = 0; break; @@ -307,16 +329,11 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, error = -EPERM; break; } - if (!mutex_trylock(&pm_mutex)) { - error = -EBUSY; - break; - } /* * Tasks are frozen and the notifiers have been called with * PM_HIBERNATION_PREPARE */ error = suspend_devices_and_enter(PM_SUSPEND_MEM); - mutex_unlock(&pm_mutex); break; case SNAPSHOT_PLATFORM_SUPPORT: @@ -390,6 +407,8 @@ static int snapshot_ioctl(struct inode *inode, struct file *filp, } + mutex_unlock(&pm_mutex); + return error; } @@ -399,7 +418,7 @@ static const struct file_operations snapshot_fops = { .read = snapshot_read, .write = snapshot_write, .llseek = no_llseek, - .ioctl = snapshot_ioctl, + .unlocked_ioctl = snapshot_ioctl, }; static struct miscdevice snapshot_device = { diff --git a/kernel/printk.c b/kernel/printk.c index 8fb01c32aa3..07ad9e7f7a6 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -38,7 +38,7 @@ /* * Architectures can override it: */ -void __attribute__((weak)) early_printk(const char *fmt, ...) +void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...) { } @@ -75,6 +75,8 @@ EXPORT_SYMBOL(oops_in_progress); static DECLARE_MUTEX(console_sem); static DECLARE_MUTEX(secondary_console_sem); struct console *console_drivers; +EXPORT_SYMBOL_GPL(console_drivers); + /* * This is used for debugging the mess that is the VT code by * keeping track if we have the console semaphore held. It's @@ -121,6 +123,8 @@ struct console_cmdline static struct console_cmdline console_cmdline[MAX_CMDLINECONSOLES]; static int selected_console = -1; static int preferred_console = -1; +int console_set_on_cmdline; +EXPORT_SYMBOL(console_set_on_cmdline); /* Flag: console code may call schedule() */ static int console_may_schedule; @@ -231,7 +235,7 @@ static inline void boot_delay_msec(void) /* * Return the number of unread characters in the log buffer. */ -int log_buf_get_len(void) +static int log_buf_get_len(void) { return logged_chars; } @@ -268,19 +272,6 @@ int log_buf_copy(char *dest, int idx, int len) } /* - * Extract a single character from the log buffer. - */ -int log_buf_read(int idx) -{ - char ret; - - if (log_buf_copy(&ret, idx, 1) == 1) - return ret; - else - return -1; -} - -/* * Commands to do_syslog: * * 0 -- Close the log. Currently a NOP. @@ -665,18 +656,17 @@ static int acquire_console_semaphore_for_printk(unsigned int cpu) spin_unlock(&logbuf_lock); return retval; } - -const char printk_recursion_bug_msg [] = - KERN_CRIT "BUG: recent printk recursion!\n"; -static int printk_recursion_bug; +static const char recursion_bug_msg [] = + KERN_CRIT "BUG: recent printk recursion!\n"; +static int recursion_bug; + static int new_text_line = 1; +static char printk_buf[1024]; asmlinkage int vprintk(const char *fmt, va_list args) { - static int log_level_unknown = 1; - static char printk_buf[1024]; - - unsigned long flags; int printed_len = 0; + int current_log_level = default_message_loglevel; + unsigned long flags; int this_cpu; char *p; @@ -699,7 +689,7 @@ asmlinkage int vprintk(const char *fmt, va_list args) * it can be printed at the next appropriate moment: */ if (!oops_in_progress) { - printk_recursion_bug = 1; + recursion_bug = 1; goto out_restore_irqs; } zap_locks(); @@ -709,70 +699,62 @@ asmlinkage int vprintk(const char *fmt, va_list args) spin_lock(&logbuf_lock); printk_cpu = this_cpu; - if (printk_recursion_bug) { - printk_recursion_bug = 0; - strcpy(printk_buf, printk_recursion_bug_msg); - printed_len = sizeof(printk_recursion_bug_msg); + if (recursion_bug) { + recursion_bug = 0; + strcpy(printk_buf, recursion_bug_msg); + printed_len = sizeof(recursion_bug_msg); } /* Emit the output into the temporary buffer */ printed_len += vscnprintf(printk_buf + printed_len, sizeof(printk_buf) - printed_len, fmt, args); + /* * Copy the output into log_buf. If the caller didn't provide * appropriate log level tags, we insert them here */ for (p = printk_buf; *p; p++) { - if (log_level_unknown) { - /* log_level_unknown signals the start of a new line */ + if (new_text_line) { + /* If a token, set current_log_level and skip over */ + if (p[0] == '<' && p[1] >= '0' && p[1] <= '7' && + p[2] == '>') { + current_log_level = p[1] - '0'; + p += 3; + printed_len -= 3; + } + + /* Always output the token */ + emit_log_char('<'); + emit_log_char(current_log_level + '0'); + emit_log_char('>'); + printed_len += 3; + new_text_line = 0; + if (printk_time) { - int loglev_char; + /* Follow the token with the time */ char tbuf[50], *tp; unsigned tlen; unsigned long long t; unsigned long nanosec_rem; - /* - * force the log level token to be - * before the time output. - */ - if (p[0] == '<' && p[1] >='0' && - p[1] <= '7' && p[2] == '>') { - loglev_char = p[1]; - p += 3; - printed_len -= 3; - } else { - loglev_char = default_message_loglevel - + '0'; - } t = cpu_clock(printk_cpu); nanosec_rem = do_div(t, 1000000000); - tlen = sprintf(tbuf, - "<%c>[%5lu.%06lu] ", - loglev_char, - (unsigned long)t, - nanosec_rem/1000); + tlen = sprintf(tbuf, "[%5lu.%06lu] ", + (unsigned long) t, + nanosec_rem / 1000); for (tp = tbuf; tp < tbuf + tlen; tp++) emit_log_char(*tp); printed_len += tlen; - } else { - if (p[0] != '<' || p[1] < '0' || - p[1] > '7' || p[2] != '>') { - emit_log_char('<'); - emit_log_char(default_message_loglevel - + '0'); - emit_log_char('>'); - printed_len += 3; - } } - log_level_unknown = 0; + if (!*p) break; } + emit_log_char(*p); if (*p == '\n') - log_level_unknown = 1; + new_text_line = 1; } /* @@ -890,6 +872,7 @@ static int __init console_setup(char *str) *s = 0; __add_preferred_console(buf, idx, options, brl_options); + console_set_on_cmdline = 1; return 1; } __setup("console=", console_setup); @@ -1041,7 +1024,9 @@ void release_console_sem(void) _log_end = log_end; con_start = log_end; /* Flush */ spin_unlock(&logbuf_lock); + stop_critical_timings(); /* don't trace print latency */ call_console_drivers(_con_start, _log_end); + start_critical_timings(); local_irq_restore(flags); } console_locked = 0; @@ -1172,8 +1157,11 @@ void register_console(struct console *console) console->index = 0; if (console->setup == NULL || console->setup(console, NULL) == 0) { - console->flags |= CON_ENABLED | CON_CONSDEV; - preferred_console = 0; + console->flags |= CON_ENABLED; + if (console->device) { + console->flags |= CON_CONSDEV; + preferred_console = 0; + } } } diff --git a/kernel/profile.c b/kernel/profile.c index ae7ead82cbc..58926411eb2 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -252,7 +252,7 @@ static void profile_flip_buffers(void) mutex_lock(&profile_flip_mutex); j = per_cpu(cpu_profile_flip, get_cpu()); put_cpu(); - on_each_cpu(__profile_flip_buffers, NULL, 0, 1); + on_each_cpu(__profile_flip_buffers, NULL, 1); for_each_online_cpu(cpu) { struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[j]; for (i = 0; i < NR_PROFILE_HIT; ++i) { @@ -275,7 +275,7 @@ static void profile_discard_flip_buffers(void) mutex_lock(&profile_flip_mutex); i = per_cpu(cpu_profile_flip, get_cpu()); put_cpu(); - on_each_cpu(__profile_flip_buffers, NULL, 0, 1); + on_each_cpu(__profile_flip_buffers, NULL, 1); for_each_online_cpu(cpu) { struct profile_hit *hits = per_cpu(cpu_profile_hits, cpu)[i]; memset(hits, 0, NR_PROFILE_HIT*sizeof(struct profile_hit)); @@ -558,7 +558,7 @@ static int __init create_hash_tables(void) out_cleanup: prof_on = 0; smp_mb(); - on_each_cpu(profile_nop, NULL, 0, 1); + on_each_cpu(profile_nop, NULL, 1); for_each_online_cpu(cpu) { struct page *page; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 6c19e94fd0a..8392a9da645 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -33,13 +33,9 @@ */ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent) { - BUG_ON(!list_empty(&child->ptrace_list)); - if (child->parent == new_parent) - return; - list_add(&child->ptrace_list, &child->parent->ptrace_children); - remove_parent(child); + BUG_ON(!list_empty(&child->ptrace_entry)); + list_add(&child->ptrace_entry, &new_parent->ptraced); child->parent = new_parent; - add_parent(child); } /* @@ -73,12 +69,8 @@ void __ptrace_unlink(struct task_struct *child) BUG_ON(!child->ptrace); child->ptrace = 0; - if (ptrace_reparented(child)) { - list_del_init(&child->ptrace_list); - remove_parent(child); - child->parent = child->real_parent; - add_parent(child); - } + child->parent = child->real_parent; + list_del_init(&child->ptrace_entry); if (task_is_traced(child)) ptrace_untrace(child); @@ -121,7 +113,7 @@ int ptrace_check_attach(struct task_struct *child, int kill) return ret; } -int __ptrace_may_attach(struct task_struct *task) +int __ptrace_may_access(struct task_struct *task, unsigned int mode) { /* May we inspect the given task? * This check is used both for attaching with ptrace @@ -148,16 +140,16 @@ int __ptrace_may_attach(struct task_struct *task) if (!dumpable && !capable(CAP_SYS_PTRACE)) return -EPERM; - return security_ptrace(current, task); + return security_ptrace(current, task, mode); } -int ptrace_may_attach(struct task_struct *task) +bool ptrace_may_access(struct task_struct *task, unsigned int mode) { int err; task_lock(task); - err = __ptrace_may_attach(task); + err = __ptrace_may_access(task, mode); task_unlock(task); - return !err; + return (!err ? true : false); } int ptrace_attach(struct task_struct *task) @@ -195,7 +187,7 @@ repeat: /* the same process cannot be attached many times */ if (task->ptrace & PT_PTRACED) goto bad; - retval = __ptrace_may_attach(task); + retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH); if (retval) goto bad; @@ -492,14 +484,34 @@ int ptrace_traceme(void) /* * Are we already being traced? */ +repeat: task_lock(current); if (!(current->ptrace & PT_PTRACED)) { - ret = security_ptrace(current->parent, current); + /* + * See ptrace_attach() comments about the locking here. + */ + unsigned long flags; + if (!write_trylock_irqsave(&tasklist_lock, flags)) { + task_unlock(current); + do { + cpu_relax(); + } while (!write_can_lock(&tasklist_lock)); + goto repeat; + } + + ret = security_ptrace(current->parent, current, + PTRACE_MODE_ATTACH); + /* * Set the ptrace bit in the process ptrace flags. + * Then link us on our parent's ptraced list. */ - if (!ret) + if (!ret) { current->ptrace |= PT_PTRACED; + __ptrace_link(current, current->real_parent); + } + + write_unlock_irqrestore(&tasklist_lock, flags); } task_unlock(current); return ret; diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c index a38895a5b8e..16eeeaa9d61 100644 --- a/kernel/rcuclassic.c +++ b/kernel/rcuclassic.c @@ -387,6 +387,10 @@ static void __rcu_offline_cpu(struct rcu_data *this_rdp, rcu_move_batch(this_rdp, rdp->donelist, rdp->donetail); rcu_move_batch(this_rdp, rdp->curlist, rdp->curtail); rcu_move_batch(this_rdp, rdp->nxtlist, rdp->nxttail); + + local_irq_disable(); + this_rdp->qlen += rdp->qlen; + local_irq_enable(); } static void rcu_offline_cpu(int cpu) @@ -516,10 +520,38 @@ void rcu_check_callbacks(int cpu, int user) if (user || (idle_cpu(cpu) && !in_softirq() && hardirq_count() <= (1 << HARDIRQ_SHIFT))) { + + /* + * Get here if this CPU took its interrupt from user + * mode or from the idle loop, and if this is not a + * nested interrupt. In this case, the CPU is in + * a quiescent state, so count it. + * + * Also do a memory barrier. This is needed to handle + * the case where writes from a preempt-disable section + * of code get reordered into schedule() by this CPU's + * write buffer. The memory barrier makes sure that + * the rcu_qsctr_inc() and rcu_bh_qsctr_inc() are see + * by other CPUs to happen after any such write. + */ + + smp_mb(); /* See above block comment. */ rcu_qsctr_inc(cpu); rcu_bh_qsctr_inc(cpu); - } else if (!in_softirq()) + + } else if (!in_softirq()) { + + /* + * Get here if this CPU did not take its interrupt from + * softirq, in other words, if it is not interrupting + * a rcu_bh read-side critical section. This is an _bh + * critical section, so count it. The memory barrier + * is needed for the same reason as is the above one. + */ + + smp_mb(); /* See above block comment. */ rcu_bh_qsctr_inc(cpu); + } raise_rcu_softirq(); } @@ -543,7 +575,7 @@ static void __cpuinit rcu_online_cpu(int cpu) rcu_init_percpu_data(cpu, &rcu_ctrlblk, rdp); rcu_init_percpu_data(cpu, &rcu_bh_ctrlblk, bh_rdp); - open_softirq(RCU_SOFTIRQ, rcu_process_callbacks, NULL); + open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); } static int __cpuinit rcu_cpu_notify(struct notifier_block *self, diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c index c09605f8d16..f14f372cf6f 100644 --- a/kernel/rcupdate.c +++ b/kernel/rcupdate.c @@ -39,16 +39,16 @@ #include <linux/sched.h> #include <asm/atomic.h> #include <linux/bitops.h> -#include <linux/completion.h> #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/cpu.h> #include <linux/mutex.h> #include <linux/module.h> -struct rcu_synchronize { - struct rcu_head head; - struct completion completion; +enum rcu_barrier { + RCU_BARRIER_STD, + RCU_BARRIER_BH, + RCU_BARRIER_SCHED, }; static DEFINE_PER_CPU(struct rcu_head, rcu_barrier_head) = {NULL}; @@ -60,7 +60,7 @@ static struct completion rcu_barrier_completion; * Awaken the corresponding synchronize_rcu() instance now that a * grace period has elapsed. */ -static void wakeme_after_rcu(struct rcu_head *head) +void wakeme_after_rcu(struct rcu_head *head) { struct rcu_synchronize *rcu; @@ -77,17 +77,7 @@ static void wakeme_after_rcu(struct rcu_head *head) * sections are delimited by rcu_read_lock() and rcu_read_unlock(), * and may be nested. */ -void synchronize_rcu(void) -{ - struct rcu_synchronize rcu; - - init_completion(&rcu.completion); - /* Will wake me after RCU finished */ - call_rcu(&rcu.head, wakeme_after_rcu); - - /* Wait for it */ - wait_for_completion(&rcu.completion); -} +synchronize_rcu_xxx(synchronize_rcu, call_rcu) EXPORT_SYMBOL_GPL(synchronize_rcu); static void rcu_barrier_callback(struct rcu_head *notused) @@ -99,19 +89,30 @@ static void rcu_barrier_callback(struct rcu_head *notused) /* * Called with preemption disabled, and from cross-cpu IRQ context. */ -static void rcu_barrier_func(void *notused) +static void rcu_barrier_func(void *type) { int cpu = smp_processor_id(); struct rcu_head *head = &per_cpu(rcu_barrier_head, cpu); atomic_inc(&rcu_barrier_cpu_count); - call_rcu(head, rcu_barrier_callback); + switch ((enum rcu_barrier)type) { + case RCU_BARRIER_STD: + call_rcu(head, rcu_barrier_callback); + break; + case RCU_BARRIER_BH: + call_rcu_bh(head, rcu_barrier_callback); + break; + case RCU_BARRIER_SCHED: + call_rcu_sched(head, rcu_barrier_callback); + break; + } } -/** - * rcu_barrier - Wait until all the in-flight RCUs are complete. +/* + * Orchestrate the specified type of RCU barrier, waiting for all + * RCU callbacks of the specified type to complete. */ -void rcu_barrier(void) +static void _rcu_barrier(enum rcu_barrier type) { BUG_ON(in_interrupt()); /* Take cpucontrol mutex to protect against CPU hotplug */ @@ -127,13 +128,39 @@ void rcu_barrier(void) * until all the callbacks are queued. */ rcu_read_lock(); - on_each_cpu(rcu_barrier_func, NULL, 0, 1); + on_each_cpu(rcu_barrier_func, (void *)type, 1); rcu_read_unlock(); wait_for_completion(&rcu_barrier_completion); mutex_unlock(&rcu_barrier_mutex); } + +/** + * rcu_barrier - Wait until all in-flight call_rcu() callbacks complete. + */ +void rcu_barrier(void) +{ + _rcu_barrier(RCU_BARRIER_STD); +} EXPORT_SYMBOL_GPL(rcu_barrier); +/** + * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. + */ +void rcu_barrier_bh(void) +{ + _rcu_barrier(RCU_BARRIER_BH); +} +EXPORT_SYMBOL_GPL(rcu_barrier_bh); + +/** + * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. + */ +void rcu_barrier_sched(void) +{ + _rcu_barrier(RCU_BARRIER_SCHED); +} +EXPORT_SYMBOL_GPL(rcu_barrier_sched); + void __init rcu_init(void) { __rcu_init(); diff --git a/kernel/rcupreempt.c b/kernel/rcupreempt.c index 5e02b774070..6f62b77d93c 100644 --- a/kernel/rcupreempt.c +++ b/kernel/rcupreempt.c @@ -46,11 +46,11 @@ #include <asm/atomic.h> #include <linux/bitops.h> #include <linux/module.h> +#include <linux/kthread.h> #include <linux/completion.h> #include <linux/moduleparam.h> #include <linux/percpu.h> #include <linux/notifier.h> -#include <linux/rcupdate.h> #include <linux/cpu.h> #include <linux/random.h> #include <linux/delay.h> @@ -82,14 +82,18 @@ struct rcu_data { spinlock_t lock; /* Protect rcu_data fields. */ long completed; /* Number of last completed batch. */ int waitlistcount; - struct tasklet_struct rcu_tasklet; struct rcu_head *nextlist; struct rcu_head **nexttail; struct rcu_head *waitlist[GP_STAGES]; struct rcu_head **waittail[GP_STAGES]; - struct rcu_head *donelist; + struct rcu_head *donelist; /* from waitlist & waitschedlist */ struct rcu_head **donetail; long rcu_flipctr[2]; + struct rcu_head *nextschedlist; + struct rcu_head **nextschedtail; + struct rcu_head *waitschedlist; + struct rcu_head **waitschedtail; + int rcu_sched_sleeping; #ifdef CONFIG_RCU_TRACE struct rcupreempt_trace trace; #endif /* #ifdef CONFIG_RCU_TRACE */ @@ -131,11 +135,24 @@ enum rcu_try_flip_states { rcu_try_flip_waitmb_state, }; +/* + * States for rcu_ctrlblk.rcu_sched_sleep. + */ + +enum rcu_sched_sleep_states { + rcu_sched_not_sleeping, /* Not sleeping, callbacks need GP. */ + rcu_sched_sleep_prep, /* Thinking of sleeping, rechecking. */ + rcu_sched_sleeping, /* Sleeping, awaken if GP needed. */ +}; + struct rcu_ctrlblk { spinlock_t fliplock; /* Protect state-machine transitions. */ long completed; /* Number of last completed batch. */ enum rcu_try_flip_states rcu_try_flip_state; /* The current state of the rcu state machine */ + spinlock_t schedlock; /* Protect rcu_sched sleep state. */ + enum rcu_sched_sleep_states sched_sleep; /* rcu_sched state. */ + wait_queue_head_t sched_wq; /* Place for rcu_sched to sleep. */ }; static DEFINE_PER_CPU(struct rcu_data, rcu_data); @@ -143,8 +160,12 @@ static struct rcu_ctrlblk rcu_ctrlblk = { .fliplock = __SPIN_LOCK_UNLOCKED(rcu_ctrlblk.fliplock), .completed = 0, .rcu_try_flip_state = rcu_try_flip_idle_state, + .schedlock = __SPIN_LOCK_UNLOCKED(rcu_ctrlblk.schedlock), + .sched_sleep = rcu_sched_not_sleeping, + .sched_wq = __WAIT_QUEUE_HEAD_INITIALIZER(rcu_ctrlblk.sched_wq), }; +static struct task_struct *rcu_sched_grace_period_task; #ifdef CONFIG_RCU_TRACE static char *rcu_try_flip_state_names[] = @@ -207,6 +228,8 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(enum rcu_mb_flag_values, rcu_mb_flag) */ #define RCU_TRACE_RDP(f, rdp) RCU_TRACE(f, &((rdp)->trace)); +#define RCU_SCHED_BATCH_TIME (HZ / 50) + /* * Return the number of RCU batches processed thus far. Useful * for debug and statistics. @@ -411,32 +434,34 @@ static void __rcu_advance_callbacks(struct rcu_data *rdp) } } -#ifdef CONFIG_NO_HZ +DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_dyntick_sched, rcu_dyntick_sched) = { + .dynticks = 1, +}; -DEFINE_PER_CPU(long, dynticks_progress_counter) = 1; -static DEFINE_PER_CPU(long, rcu_dyntick_snapshot); +#ifdef CONFIG_NO_HZ static DEFINE_PER_CPU(int, rcu_update_flag); /** * rcu_irq_enter - Called from Hard irq handlers and NMI/SMI. * * If the CPU was idle with dynamic ticks active, this updates the - * dynticks_progress_counter to let the RCU handling know that the + * rcu_dyntick_sched.dynticks to let the RCU handling know that the * CPU is active. */ void rcu_irq_enter(void) { int cpu = smp_processor_id(); + struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu); if (per_cpu(rcu_update_flag, cpu)) per_cpu(rcu_update_flag, cpu)++; /* * Only update if we are coming from a stopped ticks mode - * (dynticks_progress_counter is even). + * (rcu_dyntick_sched.dynticks is even). */ if (!in_interrupt() && - (per_cpu(dynticks_progress_counter, cpu) & 0x1) == 0) { + (rdssp->dynticks & 0x1) == 0) { /* * The following might seem like we could have a race * with NMI/SMIs. But this really isn't a problem. @@ -459,12 +484,12 @@ void rcu_irq_enter(void) * RCU read-side critical sections on this CPU would * have already completed. */ - per_cpu(dynticks_progress_counter, cpu)++; + rdssp->dynticks++; /* * The following memory barrier ensures that any * rcu_read_lock() primitives in the irq handler * are seen by other CPUs to follow the above - * increment to dynticks_progress_counter. This is + * increment to rcu_dyntick_sched.dynticks. This is * required in order for other CPUs to correctly * determine when it is safe to advance the RCU * grace-period state machine. @@ -472,7 +497,7 @@ void rcu_irq_enter(void) smp_mb(); /* see above block comment. */ /* * Since we can't determine the dynamic tick mode from - * the dynticks_progress_counter after this routine, + * the rcu_dyntick_sched.dynticks after this routine, * we use a second flag to acknowledge that we came * from an idle state with ticks stopped. */ @@ -480,7 +505,7 @@ void rcu_irq_enter(void) /* * If we take an NMI/SMI now, they will also increment * the rcu_update_flag, and will not update the - * dynticks_progress_counter on exit. That is for + * rcu_dyntick_sched.dynticks on exit. That is for * this IRQ to do. */ } @@ -490,12 +515,13 @@ void rcu_irq_enter(void) * rcu_irq_exit - Called from exiting Hard irq context. * * If the CPU was idle with dynamic ticks active, update the - * dynticks_progress_counter to put let the RCU handling be + * rcu_dyntick_sched.dynticks to put let the RCU handling be * aware that the CPU is going back to idle with no ticks. */ void rcu_irq_exit(void) { int cpu = smp_processor_id(); + struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu); /* * rcu_update_flag is set if we interrupted the CPU @@ -503,7 +529,7 @@ void rcu_irq_exit(void) * Once this occurs, we keep track of interrupt nesting * because a NMI/SMI could also come in, and we still * only want the IRQ that started the increment of the - * dynticks_progress_counter to be the one that modifies + * rcu_dyntick_sched.dynticks to be the one that modifies * it on exit. */ if (per_cpu(rcu_update_flag, cpu)) { @@ -515,28 +541,29 @@ void rcu_irq_exit(void) /* * If an NMI/SMI happens now we are still - * protected by the dynticks_progress_counter being odd. + * protected by the rcu_dyntick_sched.dynticks being odd. */ /* * The following memory barrier ensures that any * rcu_read_unlock() primitives in the irq handler * are seen by other CPUs to preceed the following - * increment to dynticks_progress_counter. This + * increment to rcu_dyntick_sched.dynticks. This * is required in order for other CPUs to determine * when it is safe to advance the RCU grace-period * state machine. */ smp_mb(); /* see above block comment. */ - per_cpu(dynticks_progress_counter, cpu)++; - WARN_ON(per_cpu(dynticks_progress_counter, cpu) & 0x1); + rdssp->dynticks++; + WARN_ON(rdssp->dynticks & 0x1); } } static void dyntick_save_progress_counter(int cpu) { - per_cpu(rcu_dyntick_snapshot, cpu) = - per_cpu(dynticks_progress_counter, cpu); + struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu); + + rdssp->dynticks_snap = rdssp->dynticks; } static inline int @@ -544,9 +571,10 @@ rcu_try_flip_waitack_needed(int cpu) { long curr; long snap; + struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu); - curr = per_cpu(dynticks_progress_counter, cpu); - snap = per_cpu(rcu_dyntick_snapshot, cpu); + curr = rdssp->dynticks; + snap = rdssp->dynticks_snap; smp_mb(); /* force ordering with cpu entering/leaving dynticks. */ /* @@ -567,7 +595,7 @@ rcu_try_flip_waitack_needed(int cpu) * that this CPU already acknowledged the counter. */ - if ((curr - snap) > 2 || (snap & 0x1) == 0) + if ((curr - snap) > 2 || (curr & 0x1) == 0) return 0; /* We need this CPU to explicitly acknowledge the counter flip. */ @@ -580,9 +608,10 @@ rcu_try_flip_waitmb_needed(int cpu) { long curr; long snap; + struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu); - curr = per_cpu(dynticks_progress_counter, cpu); - snap = per_cpu(rcu_dyntick_snapshot, cpu); + curr = rdssp->dynticks; + snap = rdssp->dynticks_snap; smp_mb(); /* force ordering with cpu entering/leaving dynticks. */ /* @@ -609,14 +638,86 @@ rcu_try_flip_waitmb_needed(int cpu) return 1; } +static void dyntick_save_progress_counter_sched(int cpu) +{ + struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu); + + rdssp->sched_dynticks_snap = rdssp->dynticks; +} + +static int rcu_qsctr_inc_needed_dyntick(int cpu) +{ + long curr; + long snap; + struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu); + + curr = rdssp->dynticks; + snap = rdssp->sched_dynticks_snap; + smp_mb(); /* force ordering with cpu entering/leaving dynticks. */ + + /* + * If the CPU remained in dynticks mode for the entire time + * and didn't take any interrupts, NMIs, SMIs, or whatever, + * then it cannot be in the middle of an rcu_read_lock(), so + * the next rcu_read_lock() it executes must use the new value + * of the counter. Therefore, this CPU has been in a quiescent + * state the entire time, and we don't need to wait for it. + */ + + if ((curr == snap) && ((curr & 0x1) == 0)) + return 0; + + /* + * If the CPU passed through or entered a dynticks idle phase with + * no active irq handlers, then, as above, this CPU has already + * passed through a quiescent state. + */ + + if ((curr - snap) > 2 || (snap & 0x1) == 0) + return 0; + + /* We need this CPU to go through a quiescent state. */ + + return 1; +} + #else /* !CONFIG_NO_HZ */ -# define dyntick_save_progress_counter(cpu) do { } while (0) -# define rcu_try_flip_waitack_needed(cpu) (1) -# define rcu_try_flip_waitmb_needed(cpu) (1) +# define dyntick_save_progress_counter(cpu) do { } while (0) +# define rcu_try_flip_waitack_needed(cpu) (1) +# define rcu_try_flip_waitmb_needed(cpu) (1) + +# define dyntick_save_progress_counter_sched(cpu) do { } while (0) +# define rcu_qsctr_inc_needed_dyntick(cpu) (1) #endif /* CONFIG_NO_HZ */ +static void save_qsctr_sched(int cpu) +{ + struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu); + + rdssp->sched_qs_snap = rdssp->sched_qs; +} + +static inline int rcu_qsctr_inc_needed(int cpu) +{ + struct rcu_dyntick_sched *rdssp = &per_cpu(rcu_dyntick_sched, cpu); + + /* + * If there has been a quiescent state, no more need to wait + * on this CPU. + */ + + if (rdssp->sched_qs != rdssp->sched_qs_snap) { + smp_mb(); /* force ordering with cpu entering schedule(). */ + return 0; + } + + /* We need this CPU to go through a quiescent state. */ + + return 1; +} + /* * Get here when RCU is idle. Decide whether we need to * move out of idle state, and return non-zero if so. @@ -819,6 +920,26 @@ void rcu_check_callbacks(int cpu, int user) unsigned long flags; struct rcu_data *rdp = RCU_DATA_CPU(cpu); + /* + * If this CPU took its interrupt from user mode or from the + * idle loop, and this is not a nested interrupt, then + * this CPU has to have exited all prior preept-disable + * sections of code. So increment the counter to note this. + * + * The memory barrier is needed to handle the case where + * writes from a preempt-disable section of code get reordered + * into schedule() by this CPU's write buffer. So the memory + * barrier makes sure that the rcu_qsctr_inc() is seen by other + * CPUs to happen after any such write. + */ + + if (user || + (idle_cpu(cpu) && !in_softirq() && + hardirq_count() <= (1 << HARDIRQ_SHIFT))) { + smp_mb(); /* Guard against aggressive schedule(). */ + rcu_qsctr_inc(cpu); + } + rcu_check_mb(cpu); if (rcu_ctrlblk.completed == rdp->completed) rcu_try_flip(); @@ -869,6 +990,8 @@ void rcu_offline_cpu(int cpu) struct rcu_head *list = NULL; unsigned long flags; struct rcu_data *rdp = RCU_DATA_CPU(cpu); + struct rcu_head *schedlist = NULL; + struct rcu_head **schedtail = &schedlist; struct rcu_head **tail = &list; /* @@ -882,6 +1005,11 @@ void rcu_offline_cpu(int cpu) rcu_offline_cpu_enqueue(rdp->waitlist[i], rdp->waittail[i], list, tail); rcu_offline_cpu_enqueue(rdp->nextlist, rdp->nexttail, list, tail); + rcu_offline_cpu_enqueue(rdp->waitschedlist, rdp->waitschedtail, + schedlist, schedtail); + rcu_offline_cpu_enqueue(rdp->nextschedlist, rdp->nextschedtail, + schedlist, schedtail); + rdp->rcu_sched_sleeping = 0; spin_unlock_irqrestore(&rdp->lock, flags); rdp->waitlistcount = 0; @@ -916,36 +1044,50 @@ void rcu_offline_cpu(int cpu) * fix. */ - local_irq_save(flags); + local_irq_save(flags); /* disable preempt till we know what lock. */ rdp = RCU_DATA_ME(); spin_lock(&rdp->lock); *rdp->nexttail = list; if (list) rdp->nexttail = tail; + *rdp->nextschedtail = schedlist; + if (schedlist) + rdp->nextschedtail = schedtail; spin_unlock_irqrestore(&rdp->lock, flags); } -void __devinit rcu_online_cpu(int cpu) +#else /* #ifdef CONFIG_HOTPLUG_CPU */ + +void rcu_offline_cpu(int cpu) +{ +} + +#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */ + +void __cpuinit rcu_online_cpu(int cpu) { unsigned long flags; + struct rcu_data *rdp; spin_lock_irqsave(&rcu_ctrlblk.fliplock, flags); cpu_set(cpu, rcu_cpu_online_map); spin_unlock_irqrestore(&rcu_ctrlblk.fliplock, flags); -} -#else /* #ifdef CONFIG_HOTPLUG_CPU */ - -void rcu_offline_cpu(int cpu) -{ -} + /* + * The rcu_sched grace-period processing might have bypassed + * this CPU, given that it was not in the rcu_cpu_online_map + * when the grace-period scan started. This means that the + * grace-period task might sleep. So make sure that if this + * should happen, the first callback posted to this CPU will + * wake up the grace-period task if need be. + */ -void __devinit rcu_online_cpu(int cpu) -{ + rdp = RCU_DATA_CPU(cpu); + spin_lock_irqsave(&rdp->lock, flags); + rdp->rcu_sched_sleeping = 1; + spin_unlock_irqrestore(&rdp->lock, flags); } -#endif /* #else #ifdef CONFIG_HOTPLUG_CPU */ - static void rcu_process_callbacks(struct softirq_action *unused) { unsigned long flags; @@ -986,31 +1128,196 @@ void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) *rdp->nexttail = head; rdp->nexttail = &head->next; RCU_TRACE_RDP(rcupreempt_trace_next_add, rdp); - spin_unlock(&rdp->lock); - local_irq_restore(flags); + spin_unlock_irqrestore(&rdp->lock, flags); } EXPORT_SYMBOL_GPL(call_rcu); +void call_rcu_sched(struct rcu_head *head, void (*func)(struct rcu_head *rcu)) +{ + unsigned long flags; + struct rcu_data *rdp; + int wake_gp = 0; + + head->func = func; + head->next = NULL; + local_irq_save(flags); + rdp = RCU_DATA_ME(); + spin_lock(&rdp->lock); + *rdp->nextschedtail = head; + rdp->nextschedtail = &head->next; + if (rdp->rcu_sched_sleeping) { + + /* Grace-period processing might be sleeping... */ + + rdp->rcu_sched_sleeping = 0; + wake_gp = 1; + } + spin_unlock_irqrestore(&rdp->lock, flags); + if (wake_gp) { + + /* Wake up grace-period processing, unless someone beat us. */ + + spin_lock_irqsave(&rcu_ctrlblk.schedlock, flags); + if (rcu_ctrlblk.sched_sleep != rcu_sched_sleeping) + wake_gp = 0; + rcu_ctrlblk.sched_sleep = rcu_sched_not_sleeping; + spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags); + if (wake_gp) + wake_up_interruptible(&rcu_ctrlblk.sched_wq); + } +} +EXPORT_SYMBOL_GPL(call_rcu_sched); + /* * Wait until all currently running preempt_disable() code segments * (including hardware-irq-disable segments) complete. Note that * in -rt this does -not- necessarily result in all currently executing * interrupt -handlers- having completed. */ -void __synchronize_sched(void) +synchronize_rcu_xxx(__synchronize_sched, call_rcu_sched) +EXPORT_SYMBOL_GPL(__synchronize_sched); + +/* + * kthread function that manages call_rcu_sched grace periods. + */ +static int rcu_sched_grace_period(void *arg) { - cpumask_t oldmask; + int couldsleep; /* might sleep after current pass. */ + int couldsleepnext = 0; /* might sleep after next pass. */ int cpu; + unsigned long flags; + struct rcu_data *rdp; + int ret; - if (sched_getaffinity(0, &oldmask) < 0) - oldmask = cpu_possible_map; - for_each_online_cpu(cpu) { - sched_setaffinity(0, &cpumask_of_cpu(cpu)); - schedule(); - } - sched_setaffinity(0, &oldmask); + /* + * Each pass through the following loop handles one + * rcu_sched grace period cycle. + */ + do { + /* Save each CPU's current state. */ + + for_each_online_cpu(cpu) { + dyntick_save_progress_counter_sched(cpu); + save_qsctr_sched(cpu); + } + + /* + * Sleep for about an RCU grace-period's worth to + * allow better batching and to consume less CPU. + */ + schedule_timeout_interruptible(RCU_SCHED_BATCH_TIME); + + /* + * If there was nothing to do last time, prepare to + * sleep at the end of the current grace period cycle. + */ + couldsleep = couldsleepnext; + couldsleepnext = 1; + if (couldsleep) { + spin_lock_irqsave(&rcu_ctrlblk.schedlock, flags); + rcu_ctrlblk.sched_sleep = rcu_sched_sleep_prep; + spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags); + } + + /* + * Wait on each CPU in turn to have either visited + * a quiescent state or been in dynticks-idle mode. + */ + for_each_online_cpu(cpu) { + while (rcu_qsctr_inc_needed(cpu) && + rcu_qsctr_inc_needed_dyntick(cpu)) { + /* resched_cpu(cpu); @@@ */ + schedule_timeout_interruptible(1); + } + } + + /* Advance callbacks for each CPU. */ + + for_each_online_cpu(cpu) { + + rdp = RCU_DATA_CPU(cpu); + spin_lock_irqsave(&rdp->lock, flags); + + /* + * We are running on this CPU irq-disabled, so no + * CPU can go offline until we re-enable irqs. + * The current CPU might have already gone + * offline (between the for_each_offline_cpu and + * the spin_lock_irqsave), but in that case all its + * callback lists will be empty, so no harm done. + * + * Advance the callbacks! We share normal RCU's + * donelist, since callbacks are invoked the + * same way in either case. + */ + if (rdp->waitschedlist != NULL) { + *rdp->donetail = rdp->waitschedlist; + rdp->donetail = rdp->waitschedtail; + + /* + * Next rcu_check_callbacks() will + * do the required raise_softirq(). + */ + } + if (rdp->nextschedlist != NULL) { + rdp->waitschedlist = rdp->nextschedlist; + rdp->waitschedtail = rdp->nextschedtail; + couldsleep = 0; + couldsleepnext = 0; + } else { + rdp->waitschedlist = NULL; + rdp->waitschedtail = &rdp->waitschedlist; + } + rdp->nextschedlist = NULL; + rdp->nextschedtail = &rdp->nextschedlist; + + /* Mark sleep intention. */ + + rdp->rcu_sched_sleeping = couldsleep; + + spin_unlock_irqrestore(&rdp->lock, flags); + } + + /* If we saw callbacks on the last scan, go deal with them. */ + + if (!couldsleep) + continue; + + /* Attempt to block... */ + + spin_lock_irqsave(&rcu_ctrlblk.schedlock, flags); + if (rcu_ctrlblk.sched_sleep != rcu_sched_sleep_prep) { + + /* + * Someone posted a callback after we scanned. + * Go take care of it. + */ + spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags); + couldsleepnext = 0; + continue; + } + + /* Block until the next person posts a callback. */ + + rcu_ctrlblk.sched_sleep = rcu_sched_sleeping; + spin_unlock_irqrestore(&rcu_ctrlblk.schedlock, flags); + ret = 0; + __wait_event_interruptible(rcu_ctrlblk.sched_wq, + rcu_ctrlblk.sched_sleep != rcu_sched_sleeping, + ret); + + /* + * Signals would prevent us from sleeping, and we cannot + * do much with them in any case. So flush them. + */ + if (ret) + flush_signals(current); + couldsleepnext = 0; + + } while (!kthread_should_stop()); + + return (0); } -EXPORT_SYMBOL_GPL(__synchronize_sched); /* * Check to see if any future RCU-related work will need to be done @@ -1027,7 +1334,9 @@ int rcu_needs_cpu(int cpu) return (rdp->donelist != NULL || !!rdp->waitlistcount || - rdp->nextlist != NULL); + rdp->nextlist != NULL || + rdp->nextschedlist != NULL || + rdp->waitschedlist != NULL); } int rcu_pending(int cpu) @@ -1038,7 +1347,9 @@ int rcu_pending(int cpu) if (rdp->donelist != NULL || !!rdp->waitlistcount || - rdp->nextlist != NULL) + rdp->nextlist != NULL || + rdp->nextschedlist != NULL || + rdp->waitschedlist != NULL) return 1; /* The RCU core needs an acknowledgement from this CPU. */ @@ -1105,6 +1416,11 @@ void __init __rcu_init(void) rdp->donetail = &rdp->donelist; rdp->rcu_flipctr[0] = 0; rdp->rcu_flipctr[1] = 0; + rdp->nextschedlist = NULL; + rdp->nextschedtail = &rdp->nextschedlist; + rdp->waitschedlist = NULL; + rdp->waitschedtail = &rdp->waitschedlist; + rdp->rcu_sched_sleeping = 0; } register_cpu_notifier(&rcu_nb); @@ -1123,15 +1439,19 @@ void __init __rcu_init(void) for_each_online_cpu(cpu) rcu_cpu_notify(&rcu_nb, CPU_UP_PREPARE, (void *)(long) cpu); - open_softirq(RCU_SOFTIRQ, rcu_process_callbacks, NULL); + open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); } /* - * Deprecated, use synchronize_rcu() or synchronize_sched() instead. + * Late-boot-time RCU initialization that must wait until after scheduler + * has been initialized. */ -void synchronize_kernel(void) +void __init rcu_init_sched(void) { - synchronize_rcu(); + rcu_sched_grace_period_task = kthread_run(rcu_sched_grace_period, + NULL, + "rcu_sched_grace_period"); + WARN_ON(IS_ERR(rcu_sched_grace_period_task)); } #ifdef CONFIG_RCU_TRACE diff --git a/kernel/rcupreempt_trace.c b/kernel/rcupreempt_trace.c index 49ac4947af2..5edf82c34bb 100644 --- a/kernel/rcupreempt_trace.c +++ b/kernel/rcupreempt_trace.c @@ -38,7 +38,6 @@ #include <linux/moduleparam.h> #include <linux/percpu.h> #include <linux/notifier.h> -#include <linux/rcupdate.h> #include <linux/cpu.h> #include <linux/mutex.h> #include <linux/rcupreempt_trace.h> diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 33acc424667..90b5b123f7a 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -57,7 +57,9 @@ static int stat_interval; /* Interval between stats, in seconds. */ /* Defaults to "only at end of test". */ static int verbose; /* Print more debug info. */ static int test_no_idle_hz; /* Test RCU's support for tickless idle CPUs. */ -static int shuffle_interval = 5; /* Interval between shuffles (in sec)*/ +static int shuffle_interval = 3; /* Interval between shuffles (in sec)*/ +static int stutter = 5; /* Start/stop testing interval (in sec) */ +static int irqreader = 1; /* RCU readers from irq (timers). */ static char *torture_type = "rcu"; /* What RCU implementation to torture. */ module_param(nreaders, int, 0444); @@ -72,6 +74,10 @@ module_param(test_no_idle_hz, bool, 0444); MODULE_PARM_DESC(test_no_idle_hz, "Test support for tickless idle CPUs"); module_param(shuffle_interval, int, 0444); MODULE_PARM_DESC(shuffle_interval, "Number of seconds between shuffles"); +module_param(stutter, int, 0444); +MODULE_PARM_DESC(stutter, "Number of seconds to run/halt test"); +module_param(irqreader, int, 0444); +MODULE_PARM_DESC(irqreader, "Allow RCU readers from irq handlers"); module_param(torture_type, charp, 0444); MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, rcu_bh, srcu)"); @@ -91,6 +97,7 @@ static struct task_struct **fakewriter_tasks; static struct task_struct **reader_tasks; static struct task_struct *stats_task; static struct task_struct *shuffler_task; +static struct task_struct *stutter_task; #define RCU_TORTURE_PIPE_LEN 10 @@ -117,8 +124,18 @@ static atomic_t n_rcu_torture_alloc_fail; static atomic_t n_rcu_torture_free; static atomic_t n_rcu_torture_mberror; static atomic_t n_rcu_torture_error; +static long n_rcu_torture_timers = 0; static struct list_head rcu_torture_removed; +static int stutter_pause_test = 0; + +#if defined(MODULE) || defined(CONFIG_RCU_TORTURE_TEST_RUNNABLE) +#define RCUTORTURE_RUNNABLE_INIT 1 +#else +#define RCUTORTURE_RUNNABLE_INIT 0 +#endif +int rcutorture_runnable = RCUTORTURE_RUNNABLE_INIT; + /* * Allocate an element from the rcu_tortures pool. */ @@ -179,6 +196,16 @@ rcu_random(struct rcu_random_state *rrsp) return swahw32(rrsp->rrs_state); } +static void +rcu_stutter_wait(void) +{ + while (stutter_pause_test || !rcutorture_runnable) + if (rcutorture_runnable) + schedule_timeout_interruptible(1); + else + schedule_timeout_interruptible(round_jiffies_relative(HZ)); +} + /* * Operations vector for selecting different types of tests. */ @@ -192,7 +219,9 @@ struct rcu_torture_ops { int (*completed)(void); void (*deferredfree)(struct rcu_torture *p); void (*sync)(void); + void (*cb_barrier)(void); int (*stats)(char *page); + int irqcapable; char *name; }; static struct rcu_torture_ops *cur_ops = NULL; @@ -265,7 +294,9 @@ static struct rcu_torture_ops rcu_ops = { .completed = rcu_torture_completed, .deferredfree = rcu_torture_deferred_free, .sync = synchronize_rcu, + .cb_barrier = rcu_barrier, .stats = NULL, + .irqcapable = 1, .name = "rcu" }; @@ -304,7 +335,9 @@ static struct rcu_torture_ops rcu_sync_ops = { .completed = rcu_torture_completed, .deferredfree = rcu_sync_torture_deferred_free, .sync = synchronize_rcu, + .cb_barrier = NULL, .stats = NULL, + .irqcapable = 1, .name = "rcu_sync" }; @@ -364,7 +397,9 @@ static struct rcu_torture_ops rcu_bh_ops = { .completed = rcu_bh_torture_completed, .deferredfree = rcu_bh_torture_deferred_free, .sync = rcu_bh_torture_synchronize, + .cb_barrier = rcu_barrier_bh, .stats = NULL, + .irqcapable = 1, .name = "rcu_bh" }; @@ -377,7 +412,9 @@ static struct rcu_torture_ops rcu_bh_sync_ops = { .completed = rcu_bh_torture_completed, .deferredfree = rcu_sync_torture_deferred_free, .sync = rcu_bh_torture_synchronize, + .cb_barrier = NULL, .stats = NULL, + .irqcapable = 1, .name = "rcu_bh_sync" }; @@ -458,6 +495,7 @@ static struct rcu_torture_ops srcu_ops = { .completed = srcu_torture_completed, .deferredfree = rcu_sync_torture_deferred_free, .sync = srcu_torture_synchronize, + .cb_barrier = NULL, .stats = srcu_torture_stats, .name = "srcu" }; @@ -482,6 +520,11 @@ static int sched_torture_completed(void) return 0; } +static void rcu_sched_torture_deferred_free(struct rcu_torture *p) +{ + call_rcu_sched(&p->rtort_rcu, rcu_torture_cb); +} + static void sched_torture_synchronize(void) { synchronize_sched(); @@ -494,12 +537,28 @@ static struct rcu_torture_ops sched_ops = { .readdelay = rcu_read_delay, /* just reuse rcu's version. */ .readunlock = sched_torture_read_unlock, .completed = sched_torture_completed, - .deferredfree = rcu_sync_torture_deferred_free, + .deferredfree = rcu_sched_torture_deferred_free, .sync = sched_torture_synchronize, + .cb_barrier = rcu_barrier_sched, .stats = NULL, + .irqcapable = 1, .name = "sched" }; +static struct rcu_torture_ops sched_ops_sync = { + .init = rcu_sync_torture_init, + .cleanup = NULL, + .readlock = sched_torture_read_lock, + .readdelay = rcu_read_delay, /* just reuse rcu's version. */ + .readunlock = sched_torture_read_unlock, + .completed = sched_torture_completed, + .deferredfree = rcu_sync_torture_deferred_free, + .sync = sched_torture_synchronize, + .cb_barrier = NULL, + .stats = NULL, + .name = "sched_sync" +}; + /* * RCU torture writer kthread. Repeatedly substitutes a new structure * for that pointed to by rcu_torture_current, freeing the old structure @@ -537,6 +596,7 @@ rcu_torture_writer(void *arg) } rcu_torture_current_version++; oldbatch = cur_ops->completed(); + rcu_stutter_wait(); } while (!kthread_should_stop() && !fullstop); VERBOSE_PRINTK_STRING("rcu_torture_writer task stopping"); while (!kthread_should_stop()) @@ -560,6 +620,7 @@ rcu_torture_fakewriter(void *arg) schedule_timeout_uninterruptible(1 + rcu_random(&rand)%10); udelay(rcu_random(&rand) & 0x3ff); cur_ops->sync(); + rcu_stutter_wait(); } while (!kthread_should_stop() && !fullstop); VERBOSE_PRINTK_STRING("rcu_torture_fakewriter task stopping"); @@ -569,6 +630,52 @@ rcu_torture_fakewriter(void *arg) } /* + * RCU torture reader from timer handler. Dereferences rcu_torture_current, + * incrementing the corresponding element of the pipeline array. The + * counter in the element should never be greater than 1, otherwise, the + * RCU implementation is broken. + */ +static void rcu_torture_timer(unsigned long unused) +{ + int idx; + int completed; + static DEFINE_RCU_RANDOM(rand); + static DEFINE_SPINLOCK(rand_lock); + struct rcu_torture *p; + int pipe_count; + + idx = cur_ops->readlock(); + completed = cur_ops->completed(); + p = rcu_dereference(rcu_torture_current); + if (p == NULL) { + /* Leave because rcu_torture_writer is not yet underway */ + cur_ops->readunlock(idx); + return; + } + if (p->rtort_mbtest == 0) + atomic_inc(&n_rcu_torture_mberror); + spin_lock(&rand_lock); + cur_ops->readdelay(&rand); + n_rcu_torture_timers++; + spin_unlock(&rand_lock); + preempt_disable(); + pipe_count = p->rtort_pipe_count; + if (pipe_count > RCU_TORTURE_PIPE_LEN) { + /* Should not happen, but... */ + pipe_count = RCU_TORTURE_PIPE_LEN; + } + ++__get_cpu_var(rcu_torture_count)[pipe_count]; + completed = cur_ops->completed() - completed; + if (completed > RCU_TORTURE_PIPE_LEN) { + /* Should not happen, but... */ + completed = RCU_TORTURE_PIPE_LEN; + } + ++__get_cpu_var(rcu_torture_batch)[completed]; + preempt_enable(); + cur_ops->readunlock(idx); +} + +/* * RCU torture reader kthread. Repeatedly dereferences rcu_torture_current, * incrementing the corresponding element of the pipeline array. The * counter in the element should never be greater than 1, otherwise, the @@ -582,11 +689,18 @@ rcu_torture_reader(void *arg) DEFINE_RCU_RANDOM(rand); struct rcu_torture *p; int pipe_count; + struct timer_list t; VERBOSE_PRINTK_STRING("rcu_torture_reader task started"); set_user_nice(current, 19); + if (irqreader && cur_ops->irqcapable) + setup_timer_on_stack(&t, rcu_torture_timer, 0); do { + if (irqreader && cur_ops->irqcapable) { + if (!timer_pending(&t)) + mod_timer(&t, 1); + } idx = cur_ops->readlock(); completed = cur_ops->completed(); p = rcu_dereference(rcu_torture_current); @@ -615,8 +729,11 @@ rcu_torture_reader(void *arg) preempt_enable(); cur_ops->readunlock(idx); schedule(); + rcu_stutter_wait(); } while (!kthread_should_stop() && !fullstop); VERBOSE_PRINTK_STRING("rcu_torture_reader task stopping"); + if (irqreader && cur_ops->irqcapable) + del_timer_sync(&t); while (!kthread_should_stop()) schedule_timeout_uninterruptible(1); return 0; @@ -647,20 +764,22 @@ rcu_torture_printk(char *page) cnt += sprintf(&page[cnt], "%s%s ", torture_type, TORTURE_FLAG); cnt += sprintf(&page[cnt], "rtc: %p ver: %ld tfle: %d rta: %d rtaf: %d rtf: %d " - "rtmbe: %d", + "rtmbe: %d nt: %ld", rcu_torture_current, rcu_torture_current_version, list_empty(&rcu_torture_freelist), atomic_read(&n_rcu_torture_alloc), atomic_read(&n_rcu_torture_alloc_fail), atomic_read(&n_rcu_torture_free), - atomic_read(&n_rcu_torture_mberror)); + atomic_read(&n_rcu_torture_mberror), + n_rcu_torture_timers); if (atomic_read(&n_rcu_torture_mberror) != 0) cnt += sprintf(&page[cnt], " !!!"); cnt += sprintf(&page[cnt], "\n%s%s ", torture_type, TORTURE_FLAG); if (i > 1) { cnt += sprintf(&page[cnt], "!!! "); atomic_inc(&n_rcu_torture_error); + WARN_ON_ONCE(1); } cnt += sprintf(&page[cnt], "Reader Pipe: "); for (i = 0; i < RCU_TORTURE_PIPE_LEN + 1; i++) @@ -785,15 +904,34 @@ rcu_torture_shuffle(void *arg) return 0; } +/* Cause the rcutorture test to "stutter", starting and stopping all + * threads periodically. + */ +static int +rcu_torture_stutter(void *arg) +{ + VERBOSE_PRINTK_STRING("rcu_torture_stutter task started"); + do { + schedule_timeout_interruptible(stutter * HZ); + stutter_pause_test = 1; + if (!kthread_should_stop()) + schedule_timeout_interruptible(stutter * HZ); + stutter_pause_test = 0; + } while (!kthread_should_stop()); + VERBOSE_PRINTK_STRING("rcu_torture_stutter task stopping"); + return 0; +} + static inline void rcu_torture_print_module_parms(char *tag) { printk(KERN_ALERT "%s" TORTURE_FLAG "--- %s: nreaders=%d nfakewriters=%d " "stat_interval=%d verbose=%d test_no_idle_hz=%d " - "shuffle_interval = %d\n", + "shuffle_interval=%d stutter=%d irqreader=%d\n", torture_type, tag, nrealreaders, nfakewriters, - stat_interval, verbose, test_no_idle_hz, shuffle_interval); + stat_interval, verbose, test_no_idle_hz, shuffle_interval, + stutter, irqreader); } static void @@ -802,6 +940,11 @@ rcu_torture_cleanup(void) int i; fullstop = 1; + if (stutter_task) { + VERBOSE_PRINTK_STRING("Stopping rcu_torture_stutter task"); + kthread_stop(stutter_task); + } + stutter_task = NULL; if (shuffler_task) { VERBOSE_PRINTK_STRING("Stopping rcu_torture_shuffle task"); kthread_stop(shuffler_task); @@ -848,7 +991,9 @@ rcu_torture_cleanup(void) stats_task = NULL; /* Wait for all RCU callbacks to fire. */ - rcu_barrier(); + + if (cur_ops->cb_barrier != NULL) + cur_ops->cb_barrier(); rcu_torture_stats_print(); /* -After- the stats thread is stopped! */ @@ -868,7 +1013,7 @@ rcu_torture_init(void) int firsterr = 0; static struct rcu_torture_ops *torture_ops[] = { &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops, - &srcu_ops, &sched_ops, }; + &srcu_ops, &sched_ops, &sched_ops_sync, }; /* Process args and tell the world that the torturer is on the job. */ for (i = 0; i < ARRAY_SIZE(torture_ops); i++) { @@ -988,6 +1133,19 @@ rcu_torture_init(void) goto unwind; } } + if (stutter < 0) + stutter = 0; + if (stutter) { + /* Create the stutter thread */ + stutter_task = kthread_run(rcu_torture_stutter, NULL, + "rcu_torture_stutter"); + if (IS_ERR(stutter_task)) { + firsterr = PTR_ERR(stutter_task); + VERBOSE_PRINTK_ERRSTRING("Failed to create stutter"); + stutter_task = NULL; + goto unwind; + } + } return 0; unwind: diff --git a/kernel/sched.c b/kernel/sched.c index 94ead43eda6..99e6d850eca 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -70,10 +70,13 @@ #include <linux/bootmem.h> #include <linux/debugfs.h> #include <linux/ctype.h> +#include <linux/ftrace.h> #include <asm/tlb.h> #include <asm/irq_regs.h> +#include "sched_cpupri.h" + /* * Convert user-nice values [ -20 ... 0 ... 19 ] * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], @@ -289,15 +292,15 @@ struct task_group root_task_group; static DEFINE_PER_CPU(struct sched_entity, init_sched_entity); /* Default task group's cfs_rq on each cpu */ static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp; -#endif +#endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity); static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp; -#endif -#else +#endif /* CONFIG_RT_GROUP_SCHED */ +#else /* !CONFIG_FAIR_GROUP_SCHED */ #define root_task_group init_task_group -#endif +#endif /* CONFIG_FAIR_GROUP_SCHED */ /* task_group_lock serializes add/remove of task groups and also changes to * a task group's cpu shares. @@ -307,9 +310,9 @@ static DEFINE_SPINLOCK(task_group_lock); #ifdef CONFIG_FAIR_GROUP_SCHED #ifdef CONFIG_USER_SCHED # define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD) -#else +#else /* !CONFIG_USER_SCHED */ # define INIT_TASK_GROUP_LOAD NICE_0_LOAD -#endif +#endif /* CONFIG_USER_SCHED */ /* * A weight of 0 or 1 can cause arithmetics problems. @@ -363,6 +366,10 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu) #else static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } +static inline struct task_group *task_group(struct task_struct *p) +{ + return NULL; +} #endif /* CONFIG_GROUP_SCHED */ @@ -373,6 +380,7 @@ struct cfs_rq { u64 exec_clock; u64 min_vruntime; + u64 pair_start; struct rb_root tasks_timeline; struct rb_node *rb_leftmost; @@ -401,6 +409,31 @@ struct cfs_rq { */ struct list_head leaf_cfs_rq_list; struct task_group *tg; /* group that "owns" this runqueue */ + +#ifdef CONFIG_SMP + /* + * the part of load.weight contributed by tasks + */ + unsigned long task_weight; + + /* + * h_load = weight * f(tg) + * + * Where f(tg) is the recursive weight fraction assigned to + * this group. + */ + unsigned long h_load; + + /* + * this cpu's part of tg->shares + */ + unsigned long shares; + + /* + * load.weight at the time we set shares + */ + unsigned long rq_weight; +#endif #endif }; @@ -452,6 +485,9 @@ struct root_domain { */ cpumask_t rto_mask; atomic_t rto_count; +#ifdef CONFIG_SMP + struct cpupri cpupri; +#endif }; /* @@ -526,6 +562,9 @@ struct rq { int push_cpu; /* cpu of this runqueue: */ int cpu; + int online; + + unsigned long avg_load_per_task; struct task_struct *migration_thread; struct list_head migration_queue; @@ -607,6 +646,24 @@ static inline void update_rq_clock(struct rq *rq) # define const_debug static const #endif +/** + * runqueue_is_locked + * + * Returns true if the current cpu runqueue is locked. + * This interface allows printk to be called with the runqueue lock + * held and know whether or not it is OK to wake up the klogd. + */ +int runqueue_is_locked(void) +{ + int cpu = get_cpu(); + struct rq *rq = cpu_rq(cpu); + int ret; + + ret = spin_is_locked(&rq->lock); + put_cpu(); + return ret; +} + /* * Debugging: various feature bits */ @@ -749,6 +806,12 @@ late_initcall(sched_init_debug); const_debug unsigned int sysctl_sched_nr_migrate = 32; /* + * ratelimit for updating the group shares. + * default: 0.5ms + */ +const_debug unsigned int sysctl_sched_shares_ratelimit = 500000; + +/* * period over which we measure -rt task cpu usage in us. * default: 1s */ @@ -775,82 +838,6 @@ static inline u64 global_rt_runtime(void) return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC; } -unsigned long long time_sync_thresh = 100000; - -static DEFINE_PER_CPU(unsigned long long, time_offset); -static DEFINE_PER_CPU(unsigned long long, prev_cpu_time); - -/* - * Global lock which we take every now and then to synchronize - * the CPUs time. This method is not warp-safe, but it's good - * enough to synchronize slowly diverging time sources and thus - * it's good enough for tracing: - */ -static DEFINE_SPINLOCK(time_sync_lock); -static unsigned long long prev_global_time; - -static unsigned long long __sync_cpu_clock(unsigned long long time, int cpu) -{ - /* - * We want this inlined, to not get tracer function calls - * in this critical section: - */ - spin_acquire(&time_sync_lock.dep_map, 0, 0, _THIS_IP_); - __raw_spin_lock(&time_sync_lock.raw_lock); - - if (time < prev_global_time) { - per_cpu(time_offset, cpu) += prev_global_time - time; - time = prev_global_time; - } else { - prev_global_time = time; - } - - __raw_spin_unlock(&time_sync_lock.raw_lock); - spin_release(&time_sync_lock.dep_map, 1, _THIS_IP_); - - return time; -} - -static unsigned long long __cpu_clock(int cpu) -{ - unsigned long long now; - - /* - * Only call sched_clock() if the scheduler has already been - * initialized (some code might call cpu_clock() very early): - */ - if (unlikely(!scheduler_running)) - return 0; - - now = sched_clock_cpu(cpu); - - return now; -} - -/* - * For kernel-internal use: high-speed (but slightly incorrect) per-cpu - * clock constructed from sched_clock(): - */ -unsigned long long cpu_clock(int cpu) -{ - unsigned long long prev_cpu_time, time, delta_time; - unsigned long flags; - - local_irq_save(flags); - prev_cpu_time = per_cpu(prev_cpu_time, cpu); - time = __cpu_clock(cpu) + per_cpu(time_offset, cpu); - delta_time = time-prev_cpu_time; - - if (unlikely(delta_time > time_sync_thresh)) { - time = __sync_cpu_clock(time, cpu); - per_cpu(prev_cpu_time, cpu) = time; - } - local_irq_restore(flags); - - return time; -} -EXPORT_SYMBOL_GPL(cpu_clock); - #ifndef prepare_arch_switch # define prepare_arch_switch(next) do { } while (0) #endif @@ -1313,15 +1300,15 @@ void wake_up_idle_cpu(int cpu) if (!tsk_is_polling(rq->idle)) smp_send_reschedule(cpu); } -#endif +#endif /* CONFIG_NO_HZ */ -#else +#else /* !CONFIG_SMP */ static void __resched_task(struct task_struct *p, int tif_bit) { assert_spin_locked(&task_rq(p)->lock); set_tsk_thread_flag(p, tif_bit); } -#endif +#endif /* CONFIG_SMP */ #if BITS_PER_LONG == 32 # define WMULT_CONST (~0UL) @@ -1336,6 +1323,9 @@ static void __resched_task(struct task_struct *p, int tif_bit) */ #define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y)) +/* + * delta *= weight / lw + */ static unsigned long calc_delta_mine(unsigned long delta_exec, unsigned long weight, struct load_weight *lw) @@ -1363,12 +1353,6 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight, return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX); } -static inline unsigned long -calc_delta_fair(unsigned long delta_exec, struct load_weight *lw) -{ - return calc_delta_mine(delta_exec, NICE_0_LOAD, lw); -} - static inline void update_load_add(struct load_weight *lw, unsigned long inc) { lw->weight += inc; @@ -1479,17 +1463,211 @@ static inline void dec_cpu_load(struct rq *rq, unsigned long load) #ifdef CONFIG_SMP static unsigned long source_load(int cpu, int type); static unsigned long target_load(int cpu, int type); -static unsigned long cpu_avg_load_per_task(int cpu); static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); -#else /* CONFIG_SMP */ + +static unsigned long cpu_avg_load_per_task(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (rq->nr_running) + rq->avg_load_per_task = rq->load.weight / rq->nr_running; + + return rq->avg_load_per_task; +} #ifdef CONFIG_FAIR_GROUP_SCHED -static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) + +typedef void (*tg_visitor)(struct task_group *, int, struct sched_domain *); + +/* + * Iterate the full tree, calling @down when first entering a node and @up when + * leaving it for the final time. + */ +static void +walk_tg_tree(tg_visitor down, tg_visitor up, int cpu, struct sched_domain *sd) { + struct task_group *parent, *child; + + rcu_read_lock(); + parent = &root_task_group; +down: + (*down)(parent, cpu, sd); + list_for_each_entry_rcu(child, &parent->children, siblings) { + parent = child; + goto down; + +up: + continue; + } + (*up)(parent, cpu, sd); + + child = parent; + parent = parent->parent; + if (parent) + goto up; + rcu_read_unlock(); } + +static void __set_se_shares(struct sched_entity *se, unsigned long shares); + +/* + * Calculate and set the cpu's group shares. + */ +static void +__update_group_shares_cpu(struct task_group *tg, int cpu, + unsigned long sd_shares, unsigned long sd_rq_weight) +{ + int boost = 0; + unsigned long shares; + unsigned long rq_weight; + + if (!tg->se[cpu]) + return; + + rq_weight = tg->cfs_rq[cpu]->load.weight; + + /* + * If there are currently no tasks on the cpu pretend there is one of + * average load so that when a new task gets to run here it will not + * get delayed by group starvation. + */ + if (!rq_weight) { + boost = 1; + rq_weight = NICE_0_LOAD; + } + + if (unlikely(rq_weight > sd_rq_weight)) + rq_weight = sd_rq_weight; + + /* + * \Sum shares * rq_weight + * shares = ----------------------- + * \Sum rq_weight + * + */ + shares = (sd_shares * rq_weight) / (sd_rq_weight + 1); + + /* + * record the actual number of shares, not the boosted amount. + */ + tg->cfs_rq[cpu]->shares = boost ? 0 : shares; + tg->cfs_rq[cpu]->rq_weight = rq_weight; + + if (shares < MIN_SHARES) + shares = MIN_SHARES; + else if (shares > MAX_SHARES) + shares = MAX_SHARES; + + __set_se_shares(tg->se[cpu], shares); +} + +/* + * Re-compute the task group their per cpu shares over the given domain. + * This needs to be done in a bottom-up fashion because the rq weight of a + * parent group depends on the shares of its child groups. + */ +static void +tg_shares_up(struct task_group *tg, int cpu, struct sched_domain *sd) +{ + unsigned long rq_weight = 0; + unsigned long shares = 0; + int i; + + for_each_cpu_mask(i, sd->span) { + rq_weight += tg->cfs_rq[i]->load.weight; + shares += tg->cfs_rq[i]->shares; + } + + if ((!shares && rq_weight) || shares > tg->shares) + shares = tg->shares; + + if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE)) + shares = tg->shares; + + if (!rq_weight) + rq_weight = cpus_weight(sd->span) * NICE_0_LOAD; + + for_each_cpu_mask(i, sd->span) { + struct rq *rq = cpu_rq(i); + unsigned long flags; + + spin_lock_irqsave(&rq->lock, flags); + __update_group_shares_cpu(tg, i, shares, rq_weight); + spin_unlock_irqrestore(&rq->lock, flags); + } +} + +/* + * Compute the cpu's hierarchical load factor for each task group. + * This needs to be done in a top-down fashion because the load of a child + * group is a fraction of its parents load. + */ +static void +tg_load_down(struct task_group *tg, int cpu, struct sched_domain *sd) +{ + unsigned long load; + + if (!tg->parent) { + load = cpu_rq(cpu)->load.weight; + } else { + load = tg->parent->cfs_rq[cpu]->h_load; + load *= tg->cfs_rq[cpu]->shares; + load /= tg->parent->cfs_rq[cpu]->load.weight + 1; + } + + tg->cfs_rq[cpu]->h_load = load; +} + +static void +tg_nop(struct task_group *tg, int cpu, struct sched_domain *sd) +{ +} + +static void update_shares(struct sched_domain *sd) +{ + u64 now = cpu_clock(raw_smp_processor_id()); + s64 elapsed = now - sd->last_update; + + if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) { + sd->last_update = now; + walk_tg_tree(tg_nop, tg_shares_up, 0, sd); + } +} + +static void update_shares_locked(struct rq *rq, struct sched_domain *sd) +{ + spin_unlock(&rq->lock); + update_shares(sd); + spin_lock(&rq->lock); +} + +static void update_h_load(int cpu) +{ + walk_tg_tree(tg_load_down, tg_nop, cpu, NULL); +} + +#else + +static inline void update_shares(struct sched_domain *sd) +{ +} + +static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd) +{ +} + #endif -#endif /* CONFIG_SMP */ +#endif + +#ifdef CONFIG_FAIR_GROUP_SCHED +static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) +{ +#ifdef CONFIG_SMP + cfs_rq->shares = shares; +#endif +} +#endif #include "sched_stats.h" #include "sched_idletask.c" @@ -1500,27 +1678,17 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) #endif #define sched_class_highest (&rt_sched_class) +#define for_each_class(class) \ + for (class = sched_class_highest; class; class = class->next) -static inline void inc_load(struct rq *rq, const struct task_struct *p) -{ - update_load_add(&rq->load, p->se.load.weight); -} - -static inline void dec_load(struct rq *rq, const struct task_struct *p) -{ - update_load_sub(&rq->load, p->se.load.weight); -} - -static void inc_nr_running(struct task_struct *p, struct rq *rq) +static void inc_nr_running(struct rq *rq) { rq->nr_running++; - inc_load(rq, p); } -static void dec_nr_running(struct task_struct *p, struct rq *rq) +static void dec_nr_running(struct rq *rq) { rq->nr_running--; - dec_load(rq, p); } static void set_load_weight(struct task_struct *p) @@ -1544,6 +1712,12 @@ static void set_load_weight(struct task_struct *p) p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO]; } +static void update_avg(u64 *avg, u64 sample) +{ + s64 diff = sample - *avg; + *avg += diff >> 3; +} + static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup) { sched_info_queued(p); @@ -1553,6 +1727,13 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup) static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep) { + if (sleep && p->se.last_wakeup) { + update_avg(&p->se.avg_overlap, + p->se.sum_exec_runtime - p->se.last_wakeup); + p->se.last_wakeup = 0; + } + + sched_info_dequeued(p); p->sched_class->dequeue_task(rq, p, sleep); p->se.on_rq = 0; } @@ -1612,7 +1793,7 @@ static void activate_task(struct rq *rq, struct task_struct *p, int wakeup) rq->nr_uninterruptible--; enqueue_task(rq, p, wakeup); - inc_nr_running(p, rq); + inc_nr_running(rq); } /* @@ -1624,7 +1805,7 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep) rq->nr_uninterruptible++; dequeue_task(rq, p, sleep); - dec_nr_running(p, rq); + dec_nr_running(rq); } /** @@ -1636,12 +1817,6 @@ inline int task_curr(const struct task_struct *p) return cpu_curr(task_cpu(p)) == p; } -/* Used instead of source_load when we know the type == 0 */ -unsigned long weighted_cpuload(const int cpu) -{ - return cpu_rq(cpu)->load.weight; -} - static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) { set_task_rq(p, cpu); @@ -1670,6 +1845,12 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p, #ifdef CONFIG_SMP +/* Used instead of source_load when we know the type == 0 */ +static unsigned long weighted_cpuload(const int cpu) +{ + return cpu_rq(cpu)->load.weight; +} + /* * Is this task likely cache-hot: */ @@ -1880,7 +2061,7 @@ static unsigned long source_load(int cpu, int type) struct rq *rq = cpu_rq(cpu); unsigned long total = weighted_cpuload(cpu); - if (type == 0) + if (type == 0 || !sched_feat(LB_BIAS)) return total; return min(rq->cpu_load[type-1], total); @@ -1895,25 +2076,13 @@ static unsigned long target_load(int cpu, int type) struct rq *rq = cpu_rq(cpu); unsigned long total = weighted_cpuload(cpu); - if (type == 0) + if (type == 0 || !sched_feat(LB_BIAS)) return total; return max(rq->cpu_load[type-1], total); } /* - * Return the average load per task on the cpu's run queue - */ -static unsigned long cpu_avg_load_per_task(int cpu) -{ - struct rq *rq = cpu_rq(cpu); - unsigned long total = weighted_cpuload(cpu); - unsigned long n = rq->nr_running; - - return n ? total / n : SCHED_LOAD_SCALE; -} - -/* * find_idlest_group finds and returns the least busy CPU group within the * domain. */ @@ -2019,6 +2188,9 @@ static int sched_balance_self(int cpu, int flag) sd = tmp; } + if (sd) + update_shares(sd); + while (sd) { cpumask_t span, tmpmask; struct sched_group *group; @@ -2085,6 +2257,22 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) if (!sched_feat(SYNC_WAKEUPS)) sync = 0; +#ifdef CONFIG_SMP + if (sched_feat(LB_WAKEUP_UPDATE)) { + struct sched_domain *sd; + + this_cpu = raw_smp_processor_id(); + cpu = task_cpu(p); + + for_each_domain(this_cpu, sd) { + if (cpu_isset(cpu, sd->span)) { + update_shares(sd); + break; + } + } + } +#endif + smp_wmb(); rq = task_rq_lock(p, &flags); old_state = p->state; @@ -2131,7 +2319,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) } } } -#endif +#endif /* CONFIG_SCHEDSTATS */ out_activate: #endif /* CONFIG_SMP */ @@ -2149,6 +2337,9 @@ out_activate: success = 1; out_running: + trace_mark(kernel_sched_wakeup, + "pid %d state %ld ## rq %p task %p rq->curr %p", + p->pid, p->state, rq, p, rq->curr); check_preempt_curr(rq, p); p->state = TASK_RUNNING; @@ -2157,6 +2348,8 @@ out_running: p->sched_class->task_wake_up(rq, p); #endif out: + current->se.last_wakeup = current->se.sum_exec_runtime; + task_rq_unlock(rq, &flags); return success; @@ -2277,8 +2470,11 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) * management (if any): */ p->sched_class->task_new(rq, p); - inc_nr_running(p, rq); + inc_nr_running(rq); } + trace_mark(kernel_sched_wakeup_new, + "pid %d state %ld ## rq %p task %p rq->curr %p", + p->pid, p->state, rq, p, rq->curr); check_preempt_curr(rq, p); #ifdef CONFIG_SMP if (p->sched_class->task_wake_up) @@ -2331,7 +2527,7 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr, notifier->ops->sched_out(notifier, next); } -#else +#else /* !CONFIG_PREEMPT_NOTIFIERS */ static void fire_sched_in_preempt_notifiers(struct task_struct *curr) { @@ -2343,7 +2539,7 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr, { } -#endif +#endif /* CONFIG_PREEMPT_NOTIFIERS */ /** * prepare_task_switch - prepare to switch tasks @@ -2451,6 +2647,11 @@ context_switch(struct rq *rq, struct task_struct *prev, struct mm_struct *mm, *oldmm; prepare_task_switch(rq, prev, next); + trace_mark(kernel_sched_schedule, + "prev_pid %d next_pid %d prev_state %ld " + "## rq %p prev %p next %p", + prev->pid, next->pid, prev->state, + rq, prev, next); mm = next->mm; oldmm = prev->active_mm; /* @@ -2785,7 +2986,7 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, enum cpu_idle_type idle, int *all_pinned, int *this_best_prio, struct rq_iterator *iterator) { - int loops = 0, pulled = 0, pinned = 0, skip_for_load; + int loops = 0, pulled = 0, pinned = 0; struct task_struct *p; long rem_load_move = max_load_move; @@ -2801,14 +3002,8 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, next: if (!p || loops++ > sysctl_sched_nr_migrate) goto out; - /* - * To help distribute high priority tasks across CPUs we don't - * skip a task if it will be the highest priority task (i.e. smallest - * prio value) on its new queue regardless of its load weight - */ - skip_for_load = (p->se.load.weight >> 1) > rem_load_move + - SCHED_LOAD_SCALE_FUZZ; - if ((skip_for_load && p->prio >= *this_best_prio) || + + if ((p->se.load.weight >> 1) > rem_load_move || !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) { p = iterator->next(iterator->arg); goto next; @@ -2863,6 +3058,10 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, max_load_move - total_load_moved, sd, idle, all_pinned, &this_best_prio); class = class->next; + + if (idle == CPU_NEWLY_IDLE && this_rq->nr_running) + break; + } while (class && max_load_move > total_load_moved); return total_load_moved > 0; @@ -2939,6 +3138,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, max_load = this_load = total_load = total_pwr = 0; busiest_load_per_task = busiest_nr_running = 0; this_load_per_task = this_nr_running = 0; + if (idle == CPU_NOT_IDLE) load_idx = sd->busy_idx; else if (idle == CPU_NEWLY_IDLE) @@ -2953,6 +3153,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, int __group_imb = 0; unsigned int balance_cpu = -1, first_idle_cpu = 0; unsigned long sum_nr_running, sum_weighted_load; + unsigned long sum_avg_load_per_task; + unsigned long avg_load_per_task; local_group = cpu_isset(this_cpu, group->cpumask); @@ -2961,6 +3163,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, /* Tally up the load of all CPUs in the group */ sum_weighted_load = sum_nr_running = avg_load = 0; + sum_avg_load_per_task = avg_load_per_task = 0; + max_cpu_load = 0; min_cpu_load = ~0UL; @@ -2994,6 +3198,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, avg_load += load; sum_nr_running += rq->nr_running; sum_weighted_load += weighted_cpuload(i); + + sum_avg_load_per_task += cpu_avg_load_per_task(i); } /* @@ -3015,7 +3221,20 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, avg_load = sg_div_cpu_power(group, avg_load * SCHED_LOAD_SCALE); - if ((max_cpu_load - min_cpu_load) > SCHED_LOAD_SCALE) + + /* + * Consider the group unbalanced when the imbalance is larger + * than the average weight of two tasks. + * + * APZ: with cgroup the avg task weight can vary wildly and + * might not be a suitable number - should we keep a + * normalized nr_running number somewhere that negates + * the hierarchy? + */ + avg_load_per_task = sg_div_cpu_power(group, + sum_avg_load_per_task * SCHED_LOAD_SCALE); + + if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task) __group_imb = 1; group_capacity = group->__cpu_power / SCHED_LOAD_SCALE; @@ -3156,9 +3375,9 @@ small_imbalance: if (busiest_load_per_task > this_load_per_task) imbn = 1; } else - this_load_per_task = SCHED_LOAD_SCALE; + this_load_per_task = cpu_avg_load_per_task(this_cpu); - if (max_load - this_load + SCHED_LOAD_SCALE_FUZZ >= + if (max_load - this_load + 2*busiest_load_per_task >= busiest_load_per_task * imbn) { *imbalance = busiest_load_per_task; return busiest; @@ -3284,6 +3503,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, schedstat_inc(sd, lb_count[idle]); redo: + update_shares(sd); group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle, cpus, balance); @@ -3386,8 +3606,9 @@ redo: if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER && !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - return -1; - return ld_moved; + ld_moved = -1; + + goto out; out_balanced: schedstat_inc(sd, lb_balanced[idle]); @@ -3402,8 +3623,13 @@ out_one_pinned: if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - return -1; - return 0; + ld_moved = -1; + else + ld_moved = 0; +out: + if (ld_moved) + update_shares(sd); + return ld_moved; } /* @@ -3438,6 +3664,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd, schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]); redo: + update_shares_locked(this_rq, sd); group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE, &sd_idle, cpus, NULL); if (!group) { @@ -3481,6 +3708,7 @@ redo: } else sd->nr_balance_failed = 0; + update_shares_locked(this_rq, sd); return ld_moved; out_balanced: @@ -3672,6 +3900,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) /* Earliest time when we have to do rebalance again */ unsigned long next_balance = jiffies + 60*HZ; int update_next_balance = 0; + int need_serialize; cpumask_t tmp; for_each_domain(cpu, sd) { @@ -3689,8 +3918,9 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) if (interval > HZ*NR_CPUS/10) interval = HZ*NR_CPUS/10; + need_serialize = sd->flags & SD_SERIALIZE; - if (sd->flags & SD_SERIALIZE) { + if (need_serialize) { if (!spin_trylock(&balancing)) goto out; } @@ -3706,7 +3936,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) } sd->last_balance = jiffies; } - if (sd->flags & SD_SERIALIZE) + if (need_serialize) spin_unlock(&balancing); out: if (time_after(next_balance, sd->last_balance + interval)) { @@ -4021,26 +4251,44 @@ void scheduler_tick(void) #endif } -#if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT) +#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ + defined(CONFIG_PREEMPT_TRACER)) + +static inline unsigned long get_parent_ip(unsigned long addr) +{ + if (in_lock_functions(addr)) { + addr = CALLER_ADDR2; + if (in_lock_functions(addr)) + addr = CALLER_ADDR3; + } + return addr; +} void __kprobes add_preempt_count(int val) { +#ifdef CONFIG_DEBUG_PREEMPT /* * Underflow? */ if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) return; +#endif preempt_count() += val; +#ifdef CONFIG_DEBUG_PREEMPT /* * Spinlock count overflowing soon? */ DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK - 10); +#endif + if (preempt_count() == val) + trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); } EXPORT_SYMBOL(add_preempt_count); void __kprobes sub_preempt_count(int val) { +#ifdef CONFIG_DEBUG_PREEMPT /* * Underflow? */ @@ -4052,7 +4300,10 @@ void __kprobes sub_preempt_count(int val) if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) && !(preempt_count() & PREEMPT_MASK))) return; +#endif + if (preempt_count() == val) + trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); preempt_count() -= val; } EXPORT_SYMBOL(sub_preempt_count); @@ -4070,6 +4321,7 @@ static noinline void __schedule_bug(struct task_struct *prev) prev->comm, prev->pid, preempt_count()); debug_show_held_locks(prev); + print_modules(); if (irqs_disabled()) print_irqtrace_events(prev); @@ -4143,7 +4395,7 @@ asmlinkage void __sched schedule(void) struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; - int cpu; + int cpu, hrtick = sched_feat(HRTICK); need_resched: preempt_disable(); @@ -4158,7 +4410,8 @@ need_resched_nonpreemptible: schedule_debug(prev); - hrtick_clear(rq); + if (hrtick) + hrtick_clear(rq); /* * Do the rq-clock update outside the rq lock: @@ -4204,7 +4457,8 @@ need_resched_nonpreemptible: } else spin_unlock_irq(&rq->lock); - hrtick_set(rq); + if (hrtick) + hrtick_set(rq); if (unlikely(reacquire_kernel_lock(current) < 0)) goto need_resched_nonpreemptible; @@ -4586,10 +4840,8 @@ void set_user_nice(struct task_struct *p, long nice) goto out_unlock; } on_rq = p->se.on_rq; - if (on_rq) { + if (on_rq) dequeue_task(rq, p, 0); - dec_load(rq, p); - } p->static_prio = NICE_TO_PRIO(nice); set_load_weight(p); @@ -4599,7 +4851,6 @@ void set_user_nice(struct task_struct *p, long nice) if (on_rq) { enqueue_task(rq, p, 0); - inc_load(rq, p); /* * If the task increased its priority or is running and * lowered its priority, then reschedule its CPU: @@ -4744,16 +4995,8 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) set_load_weight(p); } -/** - * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. - * @p: the task in question. - * @policy: new policy. - * @param: structure containing the new RT priority. - * - * NOTE that the task may be already dead. - */ -int sched_setscheduler(struct task_struct *p, int policy, - struct sched_param *param) +static int __sched_setscheduler(struct task_struct *p, int policy, + struct sched_param *param, bool user) { int retval, oldprio, oldpolicy = -1, on_rq, running; unsigned long flags; @@ -4785,7 +5028,7 @@ recheck: /* * Allow unprivileged RT tasks to decrease priority: */ - if (!capable(CAP_SYS_NICE)) { + if (user && !capable(CAP_SYS_NICE)) { if (rt_policy(policy)) { unsigned long rlim_rtprio; @@ -4821,7 +5064,8 @@ recheck: * Do not allow realtime tasks into groups that have no runtime * assigned. */ - if (rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0) + if (user + && rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0) return -EPERM; #endif @@ -4870,8 +5114,39 @@ recheck: return 0; } + +/** + * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * NOTE that the task may be already dead. + */ +int sched_setscheduler(struct task_struct *p, int policy, + struct sched_param *param) +{ + return __sched_setscheduler(p, policy, param, true); +} EXPORT_SYMBOL_GPL(sched_setscheduler); +/** + * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Just like sched_setscheduler, only don't bother checking if the + * current context has permission. For example, this is needed in + * stop_machine(): we create temporary high priority worker threads, + * but our caller might not have that capability. + */ +int sched_setscheduler_nocheck(struct task_struct *p, int policy, + struct sched_param *param) +{ + return __sched_setscheduler(p, policy, param, false); +} + static int do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) { @@ -5070,24 +5345,6 @@ asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len, return sched_setaffinity(pid, &new_mask); } -/* - * Represents all cpu's present in the system - * In systems capable of hotplug, this map could dynamically grow - * as new cpu's are detected in the system via any platform specific - * method, such as ACPI for e.g. - */ - -cpumask_t cpu_present_map __read_mostly; -EXPORT_SYMBOL(cpu_present_map); - -#ifndef CONFIG_SMP -cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL; -EXPORT_SYMBOL(cpu_online_map); - -cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL; -EXPORT_SYMBOL(cpu_possible_map); -#endif - long sched_getaffinity(pid_t pid, cpumask_t *mask) { struct task_struct *p; @@ -5384,7 +5641,7 @@ out_unlock: return retval; } -static const char stat_nam[] = "RSDTtZX"; +static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; void sched_show_task(struct task_struct *p) { @@ -5571,6 +5828,12 @@ int set_cpus_allowed_ptr(struct task_struct *p, const cpumask_t *new_mask) goto out; } + if (unlikely((p->flags & PF_THREAD_BOUND) && p != current && + !cpus_equal(p->cpus_allowed, *new_mask))) { + ret = -EINVAL; + goto out; + } + if (p->sched_class->set_cpus_allowed) p->sched_class->set_cpus_allowed(p, new_mask); else { @@ -5622,10 +5885,10 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) double_rq_lock(rq_src, rq_dest); /* Already moved. */ if (task_cpu(p) != src_cpu) - goto out; + goto done; /* Affinity changed (again). */ if (!cpu_isset(dest_cpu, p->cpus_allowed)) - goto out; + goto fail; on_rq = p->se.on_rq; if (on_rq) @@ -5636,8 +5899,9 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) activate_task(rq_dest, p, 0); check_preempt_curr(rq_dest, p); } +done: ret = 1; -out: +fail: double_rq_unlock(rq_src, rq_dest); return ret; } @@ -6059,6 +6323,36 @@ static void unregister_sched_domain_sysctl(void) } #endif +static void set_rq_online(struct rq *rq) +{ + if (!rq->online) { + const struct sched_class *class; + + cpu_set(rq->cpu, rq->rd->online); + rq->online = 1; + + for_each_class(class) { + if (class->rq_online) + class->rq_online(rq); + } + } +} + +static void set_rq_offline(struct rq *rq) +{ + if (rq->online) { + const struct sched_class *class; + + for_each_class(class) { + if (class->rq_offline) + class->rq_offline(rq); + } + + cpu_clear(rq->cpu, rq->rd->online); + rq->online = 0; + } +} + /* * migration_call - callback that gets triggered when a CPU is added. * Here we can start up the necessary migration thread for the new CPU. @@ -6096,7 +6390,8 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { BUG_ON(!cpu_isset(cpu, rq->rd->span)); - cpu_set(cpu, rq->rd->online); + + set_rq_online(rq); } spin_unlock_irqrestore(&rq->lock, flags); break; @@ -6157,7 +6452,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { BUG_ON(!cpu_isset(cpu, rq->rd->span)); - cpu_clear(cpu, rq->rd->online); + set_rq_offline(rq); } spin_unlock_irqrestore(&rq->lock, flags); break; @@ -6191,6 +6486,28 @@ void __init migration_init(void) #ifdef CONFIG_SCHED_DEBUG +static inline const char *sd_level_to_string(enum sched_domain_level lvl) +{ + switch (lvl) { + case SD_LV_NONE: + return "NONE"; + case SD_LV_SIBLING: + return "SIBLING"; + case SD_LV_MC: + return "MC"; + case SD_LV_CPU: + return "CPU"; + case SD_LV_NODE: + return "NODE"; + case SD_LV_ALLNODES: + return "ALLNODES"; + case SD_LV_MAX: + return "MAX"; + + } + return "MAX"; +} + static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, cpumask_t *groupmask) { @@ -6210,7 +6527,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, return -1; } - printk(KERN_CONT "span %s\n", str); + printk(KERN_CONT "span %s level %s\n", + str, sd_level_to_string(sd->level)); if (!cpu_isset(cpu, sd->span)) { printk(KERN_ERR "ERROR: domain->span does not contain " @@ -6294,9 +6612,9 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu) } kfree(groupmask); } -#else +#else /* !CONFIG_SCHED_DEBUG */ # define sched_domain_debug(sd, cpu) do { } while (0) -#endif +#endif /* CONFIG_SCHED_DEBUG */ static int sd_degenerate(struct sched_domain *sd) { @@ -6356,20 +6674,16 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) static void rq_attach_root(struct rq *rq, struct root_domain *rd) { unsigned long flags; - const struct sched_class *class; spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { struct root_domain *old_rd = rq->rd; - for (class = sched_class_highest; class; class = class->next) { - if (class->leave_domain) - class->leave_domain(rq); - } + if (cpu_isset(rq->cpu, old_rd->online)) + set_rq_offline(rq); cpu_clear(rq->cpu, old_rd->span); - cpu_clear(rq->cpu, old_rd->online); if (atomic_dec_and_test(&old_rd->refcount)) kfree(old_rd); @@ -6380,12 +6694,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) cpu_set(rq->cpu, rd->span); if (cpu_isset(rq->cpu, cpu_online_map)) - cpu_set(rq->cpu, rd->online); - - for (class = sched_class_highest; class; class = class->next) { - if (class->join_domain) - class->join_domain(rq); - } + set_rq_online(rq); spin_unlock_irqrestore(&rq->lock, flags); } @@ -6396,6 +6705,8 @@ static void init_rootdomain(struct root_domain *rd) cpus_clear(rd->span); cpus_clear(rd->online); + + cpupri_init(&rd->cpupri); } static void init_defrootdomain(void) @@ -6538,9 +6849,9 @@ static int find_next_best_node(int node, nodemask_t *used_nodes) min_val = INT_MAX; - for (i = 0; i < MAX_NUMNODES; i++) { + for (i = 0; i < nr_node_ids; i++) { /* Start at @node */ - n = (node + i) % MAX_NUMNODES; + n = (node + i) % nr_node_ids; if (!nr_cpus_node(n)) continue; @@ -6590,7 +6901,7 @@ static void sched_domain_node_span(int node, cpumask_t *span) cpus_or(*span, *span, *nodemask); } } -#endif +#endif /* CONFIG_NUMA */ int sched_smt_power_savings = 0, sched_mc_power_savings = 0; @@ -6609,7 +6920,7 @@ cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg, *sg = &per_cpu(sched_group_cpus, cpu); return cpu; } -#endif +#endif /* CONFIG_SCHED_SMT */ /* * multi-core sched-domains: @@ -6617,7 +6928,7 @@ cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg, #ifdef CONFIG_SCHED_MC static DEFINE_PER_CPU(struct sched_domain, core_domains); static DEFINE_PER_CPU(struct sched_group, sched_group_core); -#endif +#endif /* CONFIG_SCHED_MC */ #if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT) static int @@ -6719,7 +7030,7 @@ static void init_numa_sched_groups_power(struct sched_group *group_head) sg = sg->next; } while (sg != group_head); } -#endif +#endif /* CONFIG_NUMA */ #ifdef CONFIG_NUMA /* Free memory allocated for various sched_group structures */ @@ -6734,7 +7045,7 @@ static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask) if (!sched_group_nodes) continue; - for (i = 0; i < MAX_NUMNODES; i++) { + for (i = 0; i < nr_node_ids; i++) { struct sched_group *oldsg, *sg = sched_group_nodes[i]; *nodemask = node_to_cpumask(i); @@ -6756,11 +7067,11 @@ next_sg: sched_group_nodes_bycpu[cpu] = NULL; } } -#else +#else /* !CONFIG_NUMA */ static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask) { } -#endif +#endif /* CONFIG_NUMA */ /* * Initialize sched groups cpu_power. @@ -6927,7 +7238,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map, /* * Allocate the per-node list of sched groups */ - sched_group_nodes = kcalloc(MAX_NUMNODES, sizeof(struct sched_group *), + sched_group_nodes = kcalloc(nr_node_ids, sizeof(struct sched_group *), GFP_KERNEL); if (!sched_group_nodes) { printk(KERN_WARNING "Can not alloc sched group node list\n"); @@ -7066,7 +7377,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map, #endif /* Set up physical groups */ - for (i = 0; i < MAX_NUMNODES; i++) { + for (i = 0; i < nr_node_ids; i++) { SCHED_CPUMASK_VAR(nodemask, allmasks); SCHED_CPUMASK_VAR(send_covered, allmasks); @@ -7090,7 +7401,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map, send_covered, tmpmask); } - for (i = 0; i < MAX_NUMNODES; i++) { + for (i = 0; i < nr_node_ids; i++) { /* Set up node groups */ struct sched_group *sg, *prev; SCHED_CPUMASK_VAR(nodemask, allmasks); @@ -7129,9 +7440,9 @@ static int __build_sched_domains(const cpumask_t *cpu_map, cpus_or(*covered, *covered, *nodemask); prev = sg; - for (j = 0; j < MAX_NUMNODES; j++) { + for (j = 0; j < nr_node_ids; j++) { SCHED_CPUMASK_VAR(notcovered, allmasks); - int n = (i + j) % MAX_NUMNODES; + int n = (i + j) % nr_node_ids; node_to_cpumask_ptr(pnodemask, n); cpus_complement(*notcovered, *covered); @@ -7184,7 +7495,7 @@ static int __build_sched_domains(const cpumask_t *cpu_map, } #ifdef CONFIG_NUMA - for (i = 0; i < MAX_NUMNODES; i++) + for (i = 0; i < nr_node_ids; i++) init_numa_sched_groups_power(sched_group_nodes[i]); if (sd_allnodes) { @@ -7469,7 +7780,7 @@ int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) #endif return err; } -#endif +#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ /* * Force a reinitialization of the sched domains hierarchy. The domains @@ -7480,21 +7791,28 @@ int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) static int update_sched_domains(struct notifier_block *nfb, unsigned long action, void *hcpu) { + int cpu = (int)(long)hcpu; + switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: + disable_runtime(cpu_rq(cpu)); + /* fall-through */ + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: detach_destroy_domains(&cpu_online_map); free_sched_domains(); return NOTIFY_OK; - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: + case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: case CPU_ONLINE: case CPU_ONLINE_FROZEN: + enable_runtime(cpu_rq(cpu)); + /* fall-through */ + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: case CPU_DEAD: case CPU_DEAD_FROZEN: /* @@ -7694,8 +8012,8 @@ void __init sched_init(void) root_task_group.cfs_rq = (struct cfs_rq **)ptr; ptr += nr_cpu_ids * sizeof(void **); -#endif -#endif +#endif /* CONFIG_USER_SCHED */ +#endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED init_task_group.rt_se = (struct sched_rt_entity **)ptr; ptr += nr_cpu_ids * sizeof(void **); @@ -7709,8 +8027,8 @@ void __init sched_init(void) root_task_group.rt_rq = (struct rt_rq **)ptr; ptr += nr_cpu_ids * sizeof(void **); -#endif -#endif +#endif /* CONFIG_USER_SCHED */ +#endif /* CONFIG_RT_GROUP_SCHED */ } #ifdef CONFIG_SMP @@ -7726,8 +8044,8 @@ void __init sched_init(void) #ifdef CONFIG_USER_SCHED init_rt_bandwidth(&root_task_group.rt_bandwidth, global_rt_period(), RUNTIME_INF); -#endif -#endif +#endif /* CONFIG_USER_SCHED */ +#endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_GROUP_SCHED list_add(&init_task_group.list, &task_groups); @@ -7737,8 +8055,8 @@ void __init sched_init(void) INIT_LIST_HEAD(&root_task_group.children); init_task_group.parent = &root_task_group; list_add(&init_task_group.siblings, &root_task_group.children); -#endif -#endif +#endif /* CONFIG_USER_SCHED */ +#endif /* CONFIG_GROUP_SCHED */ for_each_possible_cpu(i) { struct rq *rq; @@ -7818,6 +8136,7 @@ void __init sched_init(void) rq->next_balance = jiffies; rq->push_cpu = 0; rq->cpu = i; + rq->online = 0; rq->migration_thread = NULL; INIT_LIST_HEAD(&rq->migration_queue); rq_attach_root(rq, &def_root_domain); @@ -7833,7 +8152,7 @@ void __init sched_init(void) #endif #ifdef CONFIG_SMP - open_softirq(SCHED_SOFTIRQ, run_rebalance_domains, NULL); + open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); #endif #ifdef CONFIG_RT_MUTEXES @@ -8057,7 +8376,7 @@ static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) { list_del_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list); } -#else +#else /* !CONFG_FAIR_GROUP_SCHED */ static inline void free_fair_sched_group(struct task_group *tg) { } @@ -8075,7 +8394,7 @@ static inline void register_fair_sched_group(struct task_group *tg, int cpu) static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) { } -#endif +#endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED static void free_rt_sched_group(struct task_group *tg) @@ -8146,7 +8465,7 @@ static inline void unregister_rt_sched_group(struct task_group *tg, int cpu) { list_del_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list); } -#else +#else /* !CONFIG_RT_GROUP_SCHED */ static inline void free_rt_sched_group(struct task_group *tg) { } @@ -8164,7 +8483,7 @@ static inline void register_rt_sched_group(struct task_group *tg, int cpu) static inline void unregister_rt_sched_group(struct task_group *tg, int cpu) { } -#endif +#endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_GROUP_SCHED static void free_sched_group(struct task_group *tg) @@ -8275,17 +8594,14 @@ void sched_move_task(struct task_struct *tsk) task_rq_unlock(rq, &flags); } -#endif +#endif /* CONFIG_GROUP_SCHED */ #ifdef CONFIG_FAIR_GROUP_SCHED -static void set_se_shares(struct sched_entity *se, unsigned long shares) +static void __set_se_shares(struct sched_entity *se, unsigned long shares) { struct cfs_rq *cfs_rq = se->cfs_rq; - struct rq *rq = cfs_rq->rq; int on_rq; - spin_lock_irq(&rq->lock); - on_rq = se->on_rq; if (on_rq) dequeue_entity(cfs_rq, se, 0); @@ -8295,8 +8611,17 @@ static void set_se_shares(struct sched_entity *se, unsigned long shares) if (on_rq) enqueue_entity(cfs_rq, se, 0); +} - spin_unlock_irq(&rq->lock); +static void set_se_shares(struct sched_entity *se, unsigned long shares) +{ + struct cfs_rq *cfs_rq = se->cfs_rq; + struct rq *rq = cfs_rq->rq; + unsigned long flags; + + spin_lock_irqsave(&rq->lock, flags); + __set_se_shares(se, shares); + spin_unlock_irqrestore(&rq->lock, flags); } static DEFINE_MUTEX(shares_mutex); @@ -8335,8 +8660,13 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) * w/o tripping rebalance_share or load_balance_fair. */ tg->shares = shares; - for_each_possible_cpu(i) + for_each_possible_cpu(i) { + /* + * force a rebalance + */ + cfs_rq_set_shares(tg->cfs_rq[i], 0); set_se_shares(tg->se[i], shares); + } /* * Enable load balance activity on this group, by inserting it back on @@ -8375,7 +8705,7 @@ static unsigned long to_ratio(u64 period, u64 runtime) #ifdef CONFIG_CGROUP_SCHED static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) { - struct task_group *tgi, *parent = tg ? tg->parent : NULL; + struct task_group *tgi, *parent = tg->parent; unsigned long total = 0; if (!parent) { @@ -8399,7 +8729,7 @@ static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) } rcu_read_unlock(); - return total + to_ratio(period, runtime) < + return total + to_ratio(period, runtime) <= to_ratio(ktime_to_ns(parent->rt_bandwidth.rt_period), parent->rt_bandwidth.rt_runtime); } @@ -8519,16 +8849,21 @@ long sched_group_rt_period(struct task_group *tg) static int sched_rt_global_constraints(void) { + struct task_group *tg = &root_task_group; + u64 rt_runtime, rt_period; int ret = 0; + rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period); + rt_runtime = tg->rt_bandwidth.rt_runtime; + mutex_lock(&rt_constraints_mutex); - if (!__rt_schedulable(NULL, 1, 0)) + if (!__rt_schedulable(tg, rt_period, rt_runtime)) ret = -EINVAL; mutex_unlock(&rt_constraints_mutex); return ret; } -#else +#else /* !CONFIG_RT_GROUP_SCHED */ static int sched_rt_global_constraints(void) { unsigned long flags; @@ -8546,7 +8881,7 @@ static int sched_rt_global_constraints(void) return 0; } -#endif +#endif /* CONFIG_RT_GROUP_SCHED */ int sched_rt_handler(struct ctl_table *table, int write, struct file *filp, void __user *buffer, size_t *lenp, @@ -8654,7 +8989,7 @@ static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft) return (u64) tg->shares; } -#endif +#endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED static int cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft, @@ -8678,7 +9013,7 @@ static u64 cpu_rt_period_read_uint(struct cgroup *cgrp, struct cftype *cft) { return sched_group_rt_period(cgroup_tg(cgrp)); } -#endif +#endif /* CONFIG_RT_GROUP_SCHED */ static struct cftype cpu_files[] = { #ifdef CONFIG_FAIR_GROUP_SCHED diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c index ce05271219a..22ed55d1167 100644 --- a/kernel/sched_clock.c +++ b/kernel/sched_clock.c @@ -3,6 +3,9 @@ * * Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> * + * Updates and enhancements: + * Copyright (C) 2008 Red Hat, Inc. Steven Rostedt <srostedt@redhat.com> + * * Based on code by: * Ingo Molnar <mingo@redhat.com> * Guillaume Chazarain <guichaz@gmail.com> @@ -32,6 +35,11 @@ #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK +#define MULTI_SHIFT 15 +/* Max is double, Min is 1/2 */ +#define MAX_MULTI (2LL << MULTI_SHIFT) +#define MIN_MULTI (1LL << (MULTI_SHIFT-1)) + struct sched_clock_data { /* * Raw spinlock - this is a special case: this might be called @@ -40,11 +48,15 @@ struct sched_clock_data { */ raw_spinlock_t lock; - unsigned long prev_jiffies; + unsigned long tick_jiffies; u64 prev_raw; u64 tick_raw; u64 tick_gtod; u64 clock; + s64 multi; +#ifdef CONFIG_NO_HZ + int check_max; +#endif }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data); @@ -71,41 +83,91 @@ void sched_clock_init(void) struct sched_clock_data *scd = cpu_sdc(cpu); scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; - scd->prev_jiffies = now_jiffies; + scd->tick_jiffies = now_jiffies; scd->prev_raw = 0; scd->tick_raw = 0; scd->tick_gtod = ktime_now; scd->clock = ktime_now; + scd->multi = 1 << MULTI_SHIFT; +#ifdef CONFIG_NO_HZ + scd->check_max = 1; +#endif } sched_clock_running = 1; } +#ifdef CONFIG_NO_HZ +/* + * The dynamic ticks makes the delta jiffies inaccurate. This + * prevents us from checking the maximum time update. + * Disable the maximum check during stopped ticks. + */ +void sched_clock_tick_stop(int cpu) +{ + struct sched_clock_data *scd = cpu_sdc(cpu); + + scd->check_max = 0; +} + +void sched_clock_tick_start(int cpu) +{ + struct sched_clock_data *scd = cpu_sdc(cpu); + + scd->check_max = 1; +} + +static int check_max(struct sched_clock_data *scd) +{ + return scd->check_max; +} +#else +static int check_max(struct sched_clock_data *scd) +{ + return 1; +} +#endif /* CONFIG_NO_HZ */ + /* * update the percpu scd from the raw @now value * * - filter out backward motion * - use jiffies to generate a min,max window to clip the raw values */ -static void __update_sched_clock(struct sched_clock_data *scd, u64 now) +static void __update_sched_clock(struct sched_clock_data *scd, u64 now, u64 *time) { unsigned long now_jiffies = jiffies; - long delta_jiffies = now_jiffies - scd->prev_jiffies; + long delta_jiffies = now_jiffies - scd->tick_jiffies; u64 clock = scd->clock; u64 min_clock, max_clock; s64 delta = now - scd->prev_raw; WARN_ON_ONCE(!irqs_disabled()); - min_clock = scd->tick_gtod + delta_jiffies * TICK_NSEC; + + /* + * At schedule tick the clock can be just under the gtod. We don't + * want to push it too prematurely. + */ + min_clock = scd->tick_gtod + (delta_jiffies * TICK_NSEC); + if (min_clock > TICK_NSEC) + min_clock -= TICK_NSEC / 2; if (unlikely(delta < 0)) { clock++; goto out; } - max_clock = min_clock + TICK_NSEC; + /* + * The clock must stay within a jiffie of the gtod. + * But since we may be at the start of a jiffy or the end of one + * we add another jiffy buffer. + */ + max_clock = scd->tick_gtod + (2 + delta_jiffies) * TICK_NSEC; + + delta *= scd->multi; + delta >>= MULTI_SHIFT; - if (unlikely(clock + delta > max_clock)) { + if (unlikely(clock + delta > max_clock) && check_max(scd)) { if (clock < max_clock) clock = max_clock; else @@ -118,9 +180,12 @@ static void __update_sched_clock(struct sched_clock_data *scd, u64 now) if (unlikely(clock < min_clock)) clock = min_clock; - scd->prev_raw = now; - scd->prev_jiffies = now_jiffies; - scd->clock = clock; + if (time) + *time = clock; + else { + scd->prev_raw = now; + scd->clock = clock; + } } static void lock_double_clock(struct sched_clock_data *data1, @@ -160,25 +225,30 @@ u64 sched_clock_cpu(int cpu) now -= my_scd->tick_raw; now += scd->tick_raw; - now -= my_scd->tick_gtod; - now += scd->tick_gtod; + now += my_scd->tick_gtod; + now -= scd->tick_gtod; __raw_spin_unlock(&my_scd->lock); + + __update_sched_clock(scd, now, &clock); + + __raw_spin_unlock(&scd->lock); + } else { __raw_spin_lock(&scd->lock); + __update_sched_clock(scd, now, NULL); + clock = scd->clock; + __raw_spin_unlock(&scd->lock); } - __update_sched_clock(scd, now); - clock = scd->clock; - - __raw_spin_unlock(&scd->lock); - return clock; } void sched_clock_tick(void) { struct sched_clock_data *scd = this_scd(); + unsigned long now_jiffies = jiffies; + s64 mult, delta_gtod, delta_raw; u64 now, now_gtod; if (unlikely(!sched_clock_running)) @@ -186,18 +256,33 @@ void sched_clock_tick(void) WARN_ON_ONCE(!irqs_disabled()); - now = sched_clock(); now_gtod = ktime_to_ns(ktime_get()); + now = sched_clock(); __raw_spin_lock(&scd->lock); - __update_sched_clock(scd, now); + __update_sched_clock(scd, now, NULL); /* * update tick_gtod after __update_sched_clock() because that will * already observe 1 new jiffy; adding a new tick_gtod to that would * increase the clock 2 jiffies. */ + delta_gtod = now_gtod - scd->tick_gtod; + delta_raw = now - scd->tick_raw; + + if ((long)delta_raw > 0) { + mult = delta_gtod << MULTI_SHIFT; + do_div(mult, delta_raw); + scd->multi = mult; + if (scd->multi > MAX_MULTI) + scd->multi = MAX_MULTI; + else if (scd->multi < MIN_MULTI) + scd->multi = MIN_MULTI; + } else + scd->multi = 1 << MULTI_SHIFT; + scd->tick_raw = now; scd->tick_gtod = now_gtod; + scd->tick_jiffies = now_jiffies; __raw_spin_unlock(&scd->lock); } @@ -227,6 +312,7 @@ void sched_clock_idle_wakeup_event(u64 delta_ns) __raw_spin_lock(&scd->lock); scd->prev_raw = now; scd->clock += delta_ns; + scd->multi = 1 << MULTI_SHIFT; __raw_spin_unlock(&scd->lock); touch_softlockup_watchdog(); @@ -244,3 +330,16 @@ unsigned long long __attribute__((weak)) sched_clock(void) { return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ); } + +unsigned long long cpu_clock(int cpu) +{ + unsigned long long clock; + unsigned long flags; + + local_irq_save(flags); + clock = sched_clock_cpu(cpu); + local_irq_restore(flags); + + return clock; +} +EXPORT_SYMBOL_GPL(cpu_clock); diff --git a/kernel/sched_cpupri.c b/kernel/sched_cpupri.c new file mode 100644 index 00000000000..52154fefab7 --- /dev/null +++ b/kernel/sched_cpupri.c @@ -0,0 +1,174 @@ +/* + * kernel/sched_cpupri.c + * + * CPU priority management + * + * Copyright (C) 2007-2008 Novell + * + * Author: Gregory Haskins <ghaskins@novell.com> + * + * This code tracks the priority of each CPU so that global migration + * decisions are easy to calculate. Each CPU can be in a state as follows: + * + * (INVALID), IDLE, NORMAL, RT1, ... RT99 + * + * going from the lowest priority to the highest. CPUs in the INVALID state + * are not eligible for routing. The system maintains this state with + * a 2 dimensional bitmap (the first for priority class, the second for cpus + * in that class). Therefore a typical application without affinity + * restrictions can find a suitable CPU with O(1) complexity (e.g. two bit + * searches). For tasks with affinity restrictions, the algorithm has a + * worst case complexity of O(min(102, nr_domcpus)), though the scenario that + * yields the worst case search is fairly contrived. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include "sched_cpupri.h" + +/* Convert between a 140 based task->prio, and our 102 based cpupri */ +static int convert_prio(int prio) +{ + int cpupri; + + if (prio == CPUPRI_INVALID) + cpupri = CPUPRI_INVALID; + else if (prio == MAX_PRIO) + cpupri = CPUPRI_IDLE; + else if (prio >= MAX_RT_PRIO) + cpupri = CPUPRI_NORMAL; + else + cpupri = MAX_RT_PRIO - prio + 1; + + return cpupri; +} + +#define for_each_cpupri_active(array, idx) \ + for (idx = find_first_bit(array, CPUPRI_NR_PRIORITIES); \ + idx < CPUPRI_NR_PRIORITIES; \ + idx = find_next_bit(array, CPUPRI_NR_PRIORITIES, idx+1)) + +/** + * cpupri_find - find the best (lowest-pri) CPU in the system + * @cp: The cpupri context + * @p: The task + * @lowest_mask: A mask to fill in with selected CPUs + * + * Note: This function returns the recommended CPUs as calculated during the + * current invokation. By the time the call returns, the CPUs may have in + * fact changed priorities any number of times. While not ideal, it is not + * an issue of correctness since the normal rebalancer logic will correct + * any discrepancies created by racing against the uncertainty of the current + * priority configuration. + * + * Returns: (int)bool - CPUs were found + */ +int cpupri_find(struct cpupri *cp, struct task_struct *p, + cpumask_t *lowest_mask) +{ + int idx = 0; + int task_pri = convert_prio(p->prio); + + for_each_cpupri_active(cp->pri_active, idx) { + struct cpupri_vec *vec = &cp->pri_to_cpu[idx]; + cpumask_t mask; + + if (idx >= task_pri) + break; + + cpus_and(mask, p->cpus_allowed, vec->mask); + + if (cpus_empty(mask)) + continue; + + *lowest_mask = mask; + return 1; + } + + return 0; +} + +/** + * cpupri_set - update the cpu priority setting + * @cp: The cpupri context + * @cpu: The target cpu + * @pri: The priority (INVALID-RT99) to assign to this CPU + * + * Note: Assumes cpu_rq(cpu)->lock is locked + * + * Returns: (void) + */ +void cpupri_set(struct cpupri *cp, int cpu, int newpri) +{ + int *currpri = &cp->cpu_to_pri[cpu]; + int oldpri = *currpri; + unsigned long flags; + + newpri = convert_prio(newpri); + + BUG_ON(newpri >= CPUPRI_NR_PRIORITIES); + + if (newpri == oldpri) + return; + + /* + * If the cpu was currently mapped to a different value, we + * first need to unmap the old value + */ + if (likely(oldpri != CPUPRI_INVALID)) { + struct cpupri_vec *vec = &cp->pri_to_cpu[oldpri]; + + spin_lock_irqsave(&vec->lock, flags); + + vec->count--; + if (!vec->count) + clear_bit(oldpri, cp->pri_active); + cpu_clear(cpu, vec->mask); + + spin_unlock_irqrestore(&vec->lock, flags); + } + + if (likely(newpri != CPUPRI_INVALID)) { + struct cpupri_vec *vec = &cp->pri_to_cpu[newpri]; + + spin_lock_irqsave(&vec->lock, flags); + + cpu_set(cpu, vec->mask); + vec->count++; + if (vec->count == 1) + set_bit(newpri, cp->pri_active); + + spin_unlock_irqrestore(&vec->lock, flags); + } + + *currpri = newpri; +} + +/** + * cpupri_init - initialize the cpupri structure + * @cp: The cpupri context + * + * Returns: (void) + */ +void cpupri_init(struct cpupri *cp) +{ + int i; + + memset(cp, 0, sizeof(*cp)); + + for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) { + struct cpupri_vec *vec = &cp->pri_to_cpu[i]; + + spin_lock_init(&vec->lock); + vec->count = 0; + cpus_clear(vec->mask); + } + + for_each_possible_cpu(i) + cp->cpu_to_pri[i] = CPUPRI_INVALID; +} + + diff --git a/kernel/sched_cpupri.h b/kernel/sched_cpupri.h new file mode 100644 index 00000000000..f25811b0f93 --- /dev/null +++ b/kernel/sched_cpupri.h @@ -0,0 +1,36 @@ +#ifndef _LINUX_CPUPRI_H +#define _LINUX_CPUPRI_H + +#include <linux/sched.h> + +#define CPUPRI_NR_PRIORITIES (MAX_RT_PRIO + 2) +#define CPUPRI_NR_PRI_WORDS BITS_TO_LONGS(CPUPRI_NR_PRIORITIES) + +#define CPUPRI_INVALID -1 +#define CPUPRI_IDLE 0 +#define CPUPRI_NORMAL 1 +/* values 2-101 are RT priorities 0-99 */ + +struct cpupri_vec { + spinlock_t lock; + int count; + cpumask_t mask; +}; + +struct cpupri { + struct cpupri_vec pri_to_cpu[CPUPRI_NR_PRIORITIES]; + long pri_active[CPUPRI_NR_PRI_WORDS]; + int cpu_to_pri[NR_CPUS]; +}; + +#ifdef CONFIG_SMP +int cpupri_find(struct cpupri *cp, + struct task_struct *p, cpumask_t *lowest_mask); +void cpupri_set(struct cpupri *cp, int cpu, int pri); +void cpupri_init(struct cpupri *cp); +#else +#define cpupri_set(cp, cpu, pri) do { } while (0) +#define cpupri_init() do { } while (0) +#endif + +#endif /* _LINUX_CPUPRI_H */ diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 8bb713040ac..bbe6b31c3c5 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -119,9 +119,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) struct sched_entity *last; unsigned long flags; -#if !defined(CONFIG_CGROUP_SCHED) || !defined(CONFIG_USER_SCHED) - SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu); -#else +#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_FAIR_GROUP_SCHED) char path[128] = ""; struct cgroup *cgroup = NULL; struct task_group *tg = cfs_rq->tg; @@ -133,6 +131,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) cgroup_path(cgroup, path, sizeof(path)); SEQ_printf(m, "\ncfs_rq[%d]:%s\n", cpu, path); +#else + SEQ_printf(m, "\ncfs_rq[%d]:\n", cpu); #endif SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "exec_clock", @@ -162,11 +162,64 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) SEQ_printf(m, " .%-30s: %ld\n", "nr_running", cfs_rq->nr_running); SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight); #ifdef CONFIG_SCHEDSTATS - SEQ_printf(m, " .%-30s: %d\n", "bkl_count", - rq->bkl_count); +#define P(n) SEQ_printf(m, " .%-30s: %d\n", #n, rq->n); + + P(yld_exp_empty); + P(yld_act_empty); + P(yld_both_empty); + P(yld_count); + + P(sched_switch); + P(sched_count); + P(sched_goidle); + + P(ttwu_count); + P(ttwu_local); + + P(bkl_count); + +#undef P #endif SEQ_printf(m, " .%-30s: %ld\n", "nr_spread_over", cfs_rq->nr_spread_over); +#ifdef CONFIG_FAIR_GROUP_SCHED +#ifdef CONFIG_SMP + SEQ_printf(m, " .%-30s: %lu\n", "shares", cfs_rq->shares); +#endif +#endif +} + +void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq) +{ +#if defined(CONFIG_CGROUP_SCHED) && defined(CONFIG_RT_GROUP_SCHED) + char path[128] = ""; + struct cgroup *cgroup = NULL; + struct task_group *tg = rt_rq->tg; + + if (tg) + cgroup = tg->css.cgroup; + + if (cgroup) + cgroup_path(cgroup, path, sizeof(path)); + + SEQ_printf(m, "\nrt_rq[%d]:%s\n", cpu, path); +#else + SEQ_printf(m, "\nrt_rq[%d]:\n", cpu); +#endif + + +#define P(x) \ + SEQ_printf(m, " .%-30s: %Ld\n", #x, (long long)(rt_rq->x)) +#define PN(x) \ + SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rt_rq->x)) + + P(rt_nr_running); + P(rt_throttled); + PN(rt_time); + PN(rt_runtime); + +#undef PN +#undef P } static void print_cpu(struct seq_file *m, int cpu) @@ -208,6 +261,7 @@ static void print_cpu(struct seq_file *m, int cpu) #undef PN print_cfs_stats(m, cpu); + print_rt_stats(m, cpu); print_rq(m, rq, cpu); } diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 08ae848b71d..f2aa987027d 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -63,13 +63,13 @@ unsigned int __read_mostly sysctl_sched_compat_yield; /* * SCHED_OTHER wake-up granularity. - * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds) + * (default: 5 msec * (1 + ilog(ncpus)), units: nanoseconds) * * This option delays the preemption effects of decoupled workloads * and reduces their over-scheduling. Synchronous workloads will still * have immediate wakeup/sleep latencies. */ -unsigned int sysctl_sched_wakeup_granularity = 10000000UL; +unsigned int sysctl_sched_wakeup_granularity = 5000000UL; const_debug unsigned int sysctl_sched_migration_cost = 500000UL; @@ -334,6 +334,34 @@ int sched_nr_latency_handler(struct ctl_table *table, int write, #endif /* + * delta *= w / rw + */ +static inline unsigned long +calc_delta_weight(unsigned long delta, struct sched_entity *se) +{ + for_each_sched_entity(se) { + delta = calc_delta_mine(delta, + se->load.weight, &cfs_rq_of(se)->load); + } + + return delta; +} + +/* + * delta *= rw / w + */ +static inline unsigned long +calc_delta_fair(unsigned long delta, struct sched_entity *se) +{ + for_each_sched_entity(se) { + delta = calc_delta_mine(delta, + cfs_rq_of(se)->load.weight, &se->load); + } + + return delta; +} + +/* * The idea is to set a period in which each task runs once. * * When there are too many tasks (sysctl_sched_nr_latency) we have to stretch @@ -362,47 +390,80 @@ static u64 __sched_period(unsigned long nr_running) */ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) { - u64 slice = __sched_period(cfs_rq->nr_running); - - for_each_sched_entity(se) { - cfs_rq = cfs_rq_of(se); - - slice *= se->load.weight; - do_div(slice, cfs_rq->load.weight); - } - - - return slice; + return calc_delta_weight(__sched_period(cfs_rq->nr_running), se); } /* * We calculate the vruntime slice of a to be inserted task * - * vs = s/w = p/rw + * vs = s*rw/w = p */ static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se) { unsigned long nr_running = cfs_rq->nr_running; - unsigned long weight; - u64 vslice; if (!se->on_rq) nr_running++; - vslice = __sched_period(nr_running); + return __sched_period(nr_running); +} + +/* + * The goal of calc_delta_asym() is to be asymmetrically around NICE_0_LOAD, in + * that it favours >=0 over <0. + * + * -20 | + * | + * 0 --------+------- + * .' + * 19 .' + * + */ +static unsigned long +calc_delta_asym(unsigned long delta, struct sched_entity *se) +{ + struct load_weight lw = { + .weight = NICE_0_LOAD, + .inv_weight = 1UL << (WMULT_SHIFT-NICE_0_SHIFT) + }; for_each_sched_entity(se) { - cfs_rq = cfs_rq_of(se); + struct load_weight *se_lw = &se->load; + unsigned long rw = cfs_rq_of(se)->load.weight; + +#ifdef CONFIG_FAIR_SCHED_GROUP + struct cfs_rq *cfs_rq = se->my_q; + struct task_group *tg = NULL + + if (cfs_rq) + tg = cfs_rq->tg; + + if (tg && tg->shares < NICE_0_LOAD) { + /* + * scale shares to what it would have been had + * tg->weight been NICE_0_LOAD: + * + * weight = 1024 * shares / tg->weight + */ + lw.weight *= se->load.weight; + lw.weight /= tg->shares; + + lw.inv_weight = 0; + + se_lw = &lw; + rw += lw.weight - se->load.weight; + } else +#endif - weight = cfs_rq->load.weight; - if (!se->on_rq) - weight += se->load.weight; + if (se->load.weight < NICE_0_LOAD) { + se_lw = &lw; + rw += NICE_0_LOAD - se->load.weight; + } - vslice *= NICE_0_LOAD; - do_div(vslice, weight); + delta = calc_delta_mine(delta, rw, se_lw); } - return vslice; + return delta; } /* @@ -419,11 +480,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr, curr->sum_exec_runtime += delta_exec; schedstat_add(cfs_rq, exec_clock, delta_exec); - delta_exec_weighted = delta_exec; - if (unlikely(curr->load.weight != NICE_0_LOAD)) { - delta_exec_weighted = calc_delta_fair(delta_exec_weighted, - &curr->load); - } + delta_exec_weighted = calc_delta_fair(delta_exec, curr); curr->vruntime += delta_exec_weighted; } @@ -510,10 +567,27 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) * Scheduling class queueing methods: */ +#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED +static void +add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight) +{ + cfs_rq->task_weight += weight; +} +#else +static inline void +add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight) +{ +} +#endif + static void account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) { update_load_add(&cfs_rq->load, se->load.weight); + if (!parent_entity(se)) + inc_cpu_load(rq_of(cfs_rq), se->load.weight); + if (entity_is_task(se)) + add_cfs_task_weight(cfs_rq, se->load.weight); cfs_rq->nr_running++; se->on_rq = 1; list_add(&se->group_node, &cfs_rq->tasks); @@ -523,6 +597,10 @@ static void account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) { update_load_sub(&cfs_rq->load, se->load.weight); + if (!parent_entity(se)) + dec_cpu_load(rq_of(cfs_rq), se->load.weight); + if (entity_is_task(se)) + add_cfs_task_weight(cfs_rq, -se->load.weight); cfs_rq->nr_running--; se->on_rq = 0; list_del_init(&se->group_node); @@ -609,8 +687,17 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) if (!initial) { /* sleeps upto a single latency don't count. */ - if (sched_feat(NEW_FAIR_SLEEPERS)) - vruntime -= sysctl_sched_latency; + if (sched_feat(NEW_FAIR_SLEEPERS)) { + unsigned long thresh = sysctl_sched_latency; + + /* + * convert the sleeper threshold into virtual time + */ + if (sched_feat(NORMALIZED_SLEEPER)) + thresh = calc_delta_fair(thresh, se); + + vruntime -= thresh; + } /* ensure we never gain time by being placed backwards. */ vruntime = max_vruntime(se->vruntime, vruntime); @@ -639,21 +726,6 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup) __enqueue_entity(cfs_rq, se); } -static void update_avg(u64 *avg, u64 sample) -{ - s64 diff = sample - *avg; - *avg += diff >> 3; -} - -static void update_avg_stats(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - if (!se->last_wakeup) - return; - - update_avg(&se->avg_overlap, se->sum_exec_runtime - se->last_wakeup); - se->last_wakeup = 0; -} - static void dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep) { @@ -664,7 +736,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep) update_stats_dequeue(cfs_rq, se); if (sleep) { - update_avg_stats(cfs_rq, se); #ifdef CONFIG_SCHEDSTATS if (entity_is_task(se)) { struct task_struct *tsk = task_of(se); @@ -726,17 +797,16 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) se->prev_sum_exec_runtime = se->sum_exec_runtime; } -static int -wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se); - static struct sched_entity * pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se) { - if (!cfs_rq->next) - return se; + struct rq *rq = rq_of(cfs_rq); + u64 pair_slice = rq->clock - cfs_rq->pair_start; - if (wakeup_preempt_entity(cfs_rq->next, se) != 0) + if (!cfs_rq->next || pair_slice > sched_slice(cfs_rq, cfs_rq->next)) { + cfs_rq->pair_start = rq->clock; return se; + } return cfs_rq->next; } @@ -835,7 +905,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) hrtick_start(rq, delta, requeue); } } -#else +#else /* !CONFIG_SCHED_HRTICK */ static inline void hrtick_start_fair(struct rq *rq, struct task_struct *p) { @@ -976,7 +1046,7 @@ static int wake_idle(int cpu, struct task_struct *p) } return cpu; } -#else +#else /* !ARCH_HAS_SCHED_WAKE_IDLE*/ static inline int wake_idle(int cpu, struct task_struct *p) { return cpu; @@ -987,6 +1057,89 @@ static inline int wake_idle(int cpu, struct task_struct *p) static const struct sched_class fair_sched_class; +#ifdef CONFIG_FAIR_GROUP_SCHED +/* + * effective_load() calculates the load change as seen from the root_task_group + * + * Adding load to a group doesn't make a group heavier, but can cause movement + * of group shares between cpus. Assuming the shares were perfectly aligned one + * can calculate the shift in shares. + * + * The problem is that perfectly aligning the shares is rather expensive, hence + * we try to avoid doing that too often - see update_shares(), which ratelimits + * this change. + * + * We compensate this by not only taking the current delta into account, but + * also considering the delta between when the shares were last adjusted and + * now. + * + * We still saw a performance dip, some tracing learned us that between + * cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased + * significantly. Therefore try to bias the error in direction of failing + * the affine wakeup. + * + */ +static long effective_load(struct task_group *tg, int cpu, + long wl, long wg) +{ + struct sched_entity *se = tg->se[cpu]; + long more_w; + + if (!tg->parent) + return wl; + + /* + * By not taking the decrease of shares on the other cpu into + * account our error leans towards reducing the affine wakeups. + */ + if (!wl && sched_feat(ASYM_EFF_LOAD)) + return wl; + + /* + * Instead of using this increment, also add the difference + * between when the shares were last updated and now. + */ + more_w = se->my_q->load.weight - se->my_q->rq_weight; + wl += more_w; + wg += more_w; + + for_each_sched_entity(se) { +#define D(n) (likely(n) ? (n) : 1) + + long S, rw, s, a, b; + + S = se->my_q->tg->shares; + s = se->my_q->shares; + rw = se->my_q->rq_weight; + + a = S*(rw + wl); + b = S*rw + s*wg; + + wl = s*(a-b)/D(b); + /* + * Assume the group is already running and will + * thus already be accounted for in the weight. + * + * That is, moving shares between CPUs, does not + * alter the group weight. + */ + wg = 0; +#undef D + } + + return wl; +} + +#else + +static inline unsigned long effective_load(struct task_group *tg, int cpu, + unsigned long wl, unsigned long wg) +{ + return wl; +} + +#endif + static int wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq, struct task_struct *p, int prev_cpu, int this_cpu, int sync, @@ -994,8 +1147,10 @@ wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq, unsigned int imbalance) { struct task_struct *curr = this_rq->curr; + struct task_group *tg; unsigned long tl = this_load; unsigned long tl_per_task; + unsigned long weight; int balanced; if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS)) @@ -1006,19 +1161,28 @@ wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq, * effect of the currently running task from the load * of the current CPU: */ - if (sync) - tl -= current->se.load.weight; + if (sync) { + tg = task_group(current); + weight = current->se.load.weight; + + tl += effective_load(tg, this_cpu, -weight, -weight); + load += effective_load(tg, prev_cpu, 0, -weight); + } - balanced = 100*(tl + p->se.load.weight) <= imbalance*load; + tg = task_group(p); + weight = p->se.load.weight; + + balanced = 100*(tl + effective_load(tg, this_cpu, weight, weight)) <= + imbalance*(load + effective_load(tg, prev_cpu, 0, weight)); /* * If the currently running task will sleep within * a reasonable amount of time then attract this newly * woken task: */ - if (sync && balanced && curr->sched_class == &fair_sched_class) { + if (sync && balanced) { if (curr->se.avg_overlap < sysctl_sched_migration_cost && - p->se.avg_overlap < sysctl_sched_migration_cost) + p->se.avg_overlap < sysctl_sched_migration_cost) return 1; } @@ -1111,11 +1275,13 @@ static unsigned long wakeup_gran(struct sched_entity *se) unsigned long gran = sysctl_sched_wakeup_granularity; /* - * More easily preempt - nice tasks, while not making - * it harder for + nice tasks. + * More easily preempt - nice tasks, while not making it harder for + * + nice tasks. */ - if (unlikely(se->load.weight > NICE_0_LOAD)) - gran = calc_delta_fair(gran, &se->load); + if (sched_feat(ASYM_GRAN)) + gran = calc_delta_asym(sysctl_sched_wakeup_granularity, se); + else + gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se); return gran; } @@ -1177,7 +1343,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p) return; } - se->last_wakeup = se->sum_exec_runtime; if (unlikely(se == pse)) return; @@ -1275,23 +1440,18 @@ __load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next) struct task_struct *p = NULL; struct sched_entity *se; - if (next == &cfs_rq->tasks) - return NULL; - - /* Skip over entities that are not tasks */ - do { + while (next != &cfs_rq->tasks) { se = list_entry(next, struct sched_entity, group_node); next = next->next; - } while (next != &cfs_rq->tasks && !entity_is_task(se)); - if (next == &cfs_rq->tasks) - return NULL; + /* Skip over entities that are not tasks */ + if (entity_is_task(se)) { + p = task_of(se); + break; + } + } cfs_rq->balance_iterator = next; - - if (entity_is_task(se)) - p = task_of(se); - return p; } @@ -1309,75 +1469,82 @@ static struct task_struct *load_balance_next_fair(void *arg) return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator); } -#ifdef CONFIG_FAIR_GROUP_SCHED -static int cfs_rq_best_prio(struct cfs_rq *cfs_rq) +static unsigned long +__load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, + unsigned long max_load_move, struct sched_domain *sd, + enum cpu_idle_type idle, int *all_pinned, int *this_best_prio, + struct cfs_rq *cfs_rq) { - struct sched_entity *curr; - struct task_struct *p; - - if (!cfs_rq->nr_running || !first_fair(cfs_rq)) - return MAX_PRIO; - - curr = cfs_rq->curr; - if (!curr) - curr = __pick_next_entity(cfs_rq); + struct rq_iterator cfs_rq_iterator; - p = task_of(curr); + cfs_rq_iterator.start = load_balance_start_fair; + cfs_rq_iterator.next = load_balance_next_fair; + cfs_rq_iterator.arg = cfs_rq; - return p->prio; + return balance_tasks(this_rq, this_cpu, busiest, + max_load_move, sd, idle, all_pinned, + this_best_prio, &cfs_rq_iterator); } -#endif +#ifdef CONFIG_FAIR_GROUP_SCHED static unsigned long load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, unsigned long max_load_move, struct sched_domain *sd, enum cpu_idle_type idle, int *all_pinned, int *this_best_prio) { - struct cfs_rq *busy_cfs_rq; long rem_load_move = max_load_move; - struct rq_iterator cfs_rq_iterator; - - cfs_rq_iterator.start = load_balance_start_fair; - cfs_rq_iterator.next = load_balance_next_fair; + int busiest_cpu = cpu_of(busiest); + struct task_group *tg; - for_each_leaf_cfs_rq(busiest, busy_cfs_rq) { -#ifdef CONFIG_FAIR_GROUP_SCHED - struct cfs_rq *this_cfs_rq; - long imbalance; - unsigned long maxload; + rcu_read_lock(); + update_h_load(busiest_cpu); - this_cfs_rq = cpu_cfs_rq(busy_cfs_rq, this_cpu); + list_for_each_entry(tg, &task_groups, list) { + struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu]; + unsigned long busiest_h_load = busiest_cfs_rq->h_load; + unsigned long busiest_weight = busiest_cfs_rq->load.weight; + u64 rem_load, moved_load; - imbalance = busy_cfs_rq->load.weight - this_cfs_rq->load.weight; - /* Don't pull if this_cfs_rq has more load than busy_cfs_rq */ - if (imbalance <= 0) + /* + * empty group + */ + if (!busiest_cfs_rq->task_weight) continue; - /* Don't pull more than imbalance/2 */ - imbalance /= 2; - maxload = min(rem_load_move, imbalance); + rem_load = (u64)rem_load_move * busiest_weight; + rem_load = div_u64(rem_load, busiest_h_load + 1); - *this_best_prio = cfs_rq_best_prio(this_cfs_rq); -#else -# define maxload rem_load_move -#endif - /* - * pass busy_cfs_rq argument into - * load_balance_[start|next]_fair iterators - */ - cfs_rq_iterator.arg = busy_cfs_rq; - rem_load_move -= balance_tasks(this_rq, this_cpu, busiest, - maxload, sd, idle, all_pinned, - this_best_prio, - &cfs_rq_iterator); + moved_load = __load_balance_fair(this_rq, this_cpu, busiest, + rem_load, sd, idle, all_pinned, this_best_prio, + tg->cfs_rq[busiest_cpu]); + + if (!moved_load) + continue; + + moved_load *= busiest_h_load; + moved_load = div_u64(moved_load, busiest_weight + 1); - if (rem_load_move <= 0) + rem_load_move -= moved_load; + if (rem_load_move < 0) break; } + rcu_read_unlock(); return max_load_move - rem_load_move; } +#else +static unsigned long +load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, + unsigned long max_load_move, + struct sched_domain *sd, enum cpu_idle_type idle, + int *all_pinned, int *this_best_prio) +{ + return __load_balance_fair(this_rq, this_cpu, busiest, + max_load_move, sd, idle, all_pinned, + this_best_prio, &busiest->cfs); +} +#endif static int move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, @@ -1402,7 +1569,7 @@ move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, return 0; } -#endif +#endif /* CONFIG_SMP */ /* * scheduler tick hitting a task of our scheduling class: diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 1c7283cb958..862b06bd560 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -1,4 +1,5 @@ SCHED_FEAT(NEW_FAIR_SLEEPERS, 1) +SCHED_FEAT(NORMALIZED_SLEEPER, 1) SCHED_FEAT(WAKEUP_PREEMPT, 1) SCHED_FEAT(START_DEBIT, 1) SCHED_FEAT(AFFINE_WAKEUPS, 1) @@ -6,5 +7,7 @@ SCHED_FEAT(CACHE_HOT_BUDDY, 1) SCHED_FEAT(SYNC_WAKEUPS, 1) SCHED_FEAT(HRTICK, 1) SCHED_FEAT(DOUBLE_TICK, 0) -SCHED_FEAT(NORMALIZED_SLEEPER, 1) -SCHED_FEAT(DEADLINE, 1) +SCHED_FEAT(ASYM_GRAN, 1) +SCHED_FEAT(LB_BIAS, 0) +SCHED_FEAT(LB_WAKEUP_UPDATE, 1) +SCHED_FEAT(ASYM_EFF_LOAD, 1) diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 0f3c19197fa..47ceac9e855 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -12,6 +12,9 @@ static inline int rt_overloaded(struct rq *rq) static inline void rt_set_overload(struct rq *rq) { + if (!rq->online) + return; + cpu_set(rq->cpu, rq->rd->rto_mask); /* * Make sure the mask is visible before we set @@ -26,6 +29,9 @@ static inline void rt_set_overload(struct rq *rq) static inline void rt_clear_overload(struct rq *rq) { + if (!rq->online) + return; + /* the order here really doesn't matter */ atomic_dec(&rq->rd->rto_count); cpu_clear(rq->cpu, rq->rd->rto_mask); @@ -155,7 +161,7 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) return &rt_rq->tg->rt_bandwidth; } -#else +#else /* !CONFIG_RT_GROUP_SCHED */ static inline u64 sched_rt_runtime(struct rt_rq *rt_rq) { @@ -220,49 +226,10 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) return &def_rt_bandwidth; } -#endif - -static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) -{ - int i, idle = 1; - cpumask_t span; - - if (rt_b->rt_runtime == RUNTIME_INF) - return 1; - - span = sched_rt_period_mask(); - for_each_cpu_mask(i, span) { - int enqueue = 0; - struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i); - struct rq *rq = rq_of_rt_rq(rt_rq); - - spin_lock(&rq->lock); - if (rt_rq->rt_time) { - u64 runtime; - - spin_lock(&rt_rq->rt_runtime_lock); - runtime = rt_rq->rt_runtime; - rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime); - if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) { - rt_rq->rt_throttled = 0; - enqueue = 1; - } - if (rt_rq->rt_time || rt_rq->rt_nr_running) - idle = 0; - spin_unlock(&rt_rq->rt_runtime_lock); - } else if (rt_rq->rt_nr_running) - idle = 0; - - if (enqueue) - sched_rt_rq_enqueue(rt_rq); - spin_unlock(&rq->lock); - } - - return idle; -} +#endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_SMP -static int balance_runtime(struct rt_rq *rt_rq) +static int do_balance_runtime(struct rt_rq *rt_rq) { struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); struct root_domain *rd = cpu_rq(smp_processor_id())->rd; @@ -281,6 +248,9 @@ static int balance_runtime(struct rt_rq *rt_rq) continue; spin_lock(&iter->rt_runtime_lock); + if (iter->rt_runtime == RUNTIME_INF) + goto next; + diff = iter->rt_runtime - iter->rt_time; if (diff > 0) { do_div(diff, weight); @@ -294,13 +264,163 @@ static int balance_runtime(struct rt_rq *rt_rq) break; } } +next: spin_unlock(&iter->rt_runtime_lock); } spin_unlock(&rt_b->rt_runtime_lock); return more; } -#endif + +static void __disable_runtime(struct rq *rq) +{ + struct root_domain *rd = rq->rd; + struct rt_rq *rt_rq; + + if (unlikely(!scheduler_running)) + return; + + for_each_leaf_rt_rq(rt_rq, rq) { + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + s64 want; + int i; + + spin_lock(&rt_b->rt_runtime_lock); + spin_lock(&rt_rq->rt_runtime_lock); + if (rt_rq->rt_runtime == RUNTIME_INF || + rt_rq->rt_runtime == rt_b->rt_runtime) + goto balanced; + spin_unlock(&rt_rq->rt_runtime_lock); + + want = rt_b->rt_runtime - rt_rq->rt_runtime; + + for_each_cpu_mask(i, rd->span) { + struct rt_rq *iter = sched_rt_period_rt_rq(rt_b, i); + s64 diff; + + if (iter == rt_rq) + continue; + + spin_lock(&iter->rt_runtime_lock); + if (want > 0) { + diff = min_t(s64, iter->rt_runtime, want); + iter->rt_runtime -= diff; + want -= diff; + } else { + iter->rt_runtime -= want; + want -= want; + } + spin_unlock(&iter->rt_runtime_lock); + + if (!want) + break; + } + + spin_lock(&rt_rq->rt_runtime_lock); + BUG_ON(want); +balanced: + rt_rq->rt_runtime = RUNTIME_INF; + spin_unlock(&rt_rq->rt_runtime_lock); + spin_unlock(&rt_b->rt_runtime_lock); + } +} + +static void disable_runtime(struct rq *rq) +{ + unsigned long flags; + + spin_lock_irqsave(&rq->lock, flags); + __disable_runtime(rq); + spin_unlock_irqrestore(&rq->lock, flags); +} + +static void __enable_runtime(struct rq *rq) +{ + struct rt_rq *rt_rq; + + if (unlikely(!scheduler_running)) + return; + + for_each_leaf_rt_rq(rt_rq, rq) { + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + spin_lock(&rt_b->rt_runtime_lock); + spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_runtime = rt_b->rt_runtime; + rt_rq->rt_time = 0; + spin_unlock(&rt_rq->rt_runtime_lock); + spin_unlock(&rt_b->rt_runtime_lock); + } +} + +static void enable_runtime(struct rq *rq) +{ + unsigned long flags; + + spin_lock_irqsave(&rq->lock, flags); + __enable_runtime(rq); + spin_unlock_irqrestore(&rq->lock, flags); +} + +static int balance_runtime(struct rt_rq *rt_rq) +{ + int more = 0; + + if (rt_rq->rt_time > rt_rq->rt_runtime) { + spin_unlock(&rt_rq->rt_runtime_lock); + more = do_balance_runtime(rt_rq); + spin_lock(&rt_rq->rt_runtime_lock); + } + + return more; +} +#else /* !CONFIG_SMP */ +static inline int balance_runtime(struct rt_rq *rt_rq) +{ + return 0; +} +#endif /* CONFIG_SMP */ + +static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) +{ + int i, idle = 1; + cpumask_t span; + + if (rt_b->rt_runtime == RUNTIME_INF) + return 1; + + span = sched_rt_period_mask(); + for_each_cpu_mask(i, span) { + int enqueue = 0; + struct rt_rq *rt_rq = sched_rt_period_rt_rq(rt_b, i); + struct rq *rq = rq_of_rt_rq(rt_rq); + + spin_lock(&rq->lock); + if (rt_rq->rt_time) { + u64 runtime; + + spin_lock(&rt_rq->rt_runtime_lock); + if (rt_rq->rt_throttled) + balance_runtime(rt_rq); + runtime = rt_rq->rt_runtime; + rt_rq->rt_time -= min(rt_rq->rt_time, overrun*runtime); + if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) { + rt_rq->rt_throttled = 0; + enqueue = 1; + } + if (rt_rq->rt_time || rt_rq->rt_nr_running) + idle = 0; + spin_unlock(&rt_rq->rt_runtime_lock); + } else if (rt_rq->rt_nr_running) + idle = 0; + + if (enqueue) + sched_rt_rq_enqueue(rt_rq); + spin_unlock(&rq->lock); + } + + return idle; +} static inline int rt_se_prio(struct sched_rt_entity *rt_se) { @@ -327,18 +447,10 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) if (sched_rt_runtime(rt_rq) >= sched_rt_period(rt_rq)) return 0; -#ifdef CONFIG_SMP - if (rt_rq->rt_time > runtime) { - int more; - - spin_unlock(&rt_rq->rt_runtime_lock); - more = balance_runtime(rt_rq); - spin_lock(&rt_rq->rt_runtime_lock); - - if (more) - runtime = sched_rt_runtime(rt_rq); - } -#endif + balance_runtime(rt_rq); + runtime = sched_rt_runtime(rt_rq); + if (runtime == RUNTIME_INF) + return 0; if (rt_rq->rt_time > runtime) { rt_rq->rt_throttled = 1; @@ -392,12 +504,21 @@ void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) WARN_ON(!rt_prio(rt_se_prio(rt_se))); rt_rq->rt_nr_running++; #if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED - if (rt_se_prio(rt_se) < rt_rq->highest_prio) + if (rt_se_prio(rt_se) < rt_rq->highest_prio) { + struct rq *rq = rq_of_rt_rq(rt_rq); + rt_rq->highest_prio = rt_se_prio(rt_se); +#ifdef CONFIG_SMP + if (rq->online) + cpupri_set(&rq->rd->cpupri, rq->cpu, + rt_se_prio(rt_se)); +#endif + } #endif #ifdef CONFIG_SMP if (rt_se->nr_cpus_allowed > 1) { struct rq *rq = rq_of_rt_rq(rt_rq); + rq->rt.rt_nr_migratory++; } @@ -417,6 +538,10 @@ void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) static inline void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) { +#ifdef CONFIG_SMP + int highest_prio = rt_rq->highest_prio; +#endif + WARN_ON(!rt_prio(rt_se_prio(rt_se))); WARN_ON(!rt_rq->rt_nr_running); rt_rq->rt_nr_running--; @@ -440,6 +565,14 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) rq->rt.rt_nr_migratory--; } + if (rt_rq->highest_prio != highest_prio) { + struct rq *rq = rq_of_rt_rq(rt_rq); + + if (rq->online) + cpupri_set(&rq->rd->cpupri, rq->cpu, + rt_rq->highest_prio); + } + update_rt_migration(rq_of_rt_rq(rt_rq)); #endif /* CONFIG_SMP */ #ifdef CONFIG_RT_GROUP_SCHED @@ -455,6 +588,7 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se) struct rt_rq *rt_rq = rt_rq_of_se(rt_se); struct rt_prio_array *array = &rt_rq->active; struct rt_rq *group_rq = group_rt_rq(rt_se); + struct list_head *queue = array->queue + rt_se_prio(rt_se); /* * Don't enqueue the group if its throttled, or when empty. @@ -465,7 +599,11 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se) if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running)) return; - list_add_tail(&rt_se->run_list, array->queue + rt_se_prio(rt_se)); + if (rt_se->nr_cpus_allowed == 1) + list_add(&rt_se->run_list, queue); + else + list_add_tail(&rt_se->run_list, queue); + __set_bit(rt_se_prio(rt_se), array->bitmap); inc_rt_tasks(rt_se, rt_rq); @@ -532,6 +670,8 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup) rt_se->timeout = 0; enqueue_rt_entity(rt_se); + + inc_cpu_load(rq, p->se.load.weight); } static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep) @@ -540,6 +680,8 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep) update_curr_rt(rq); dequeue_rt_entity(rt_se); + + dec_cpu_load(rq, p->se.load.weight); } /* @@ -550,10 +692,12 @@ static void requeue_rt_entity(struct rt_rq *rt_rq, struct sched_rt_entity *rt_se) { struct rt_prio_array *array = &rt_rq->active; - struct list_head *queue = array->queue + rt_se_prio(rt_se); - if (on_rt_rq(rt_se)) - list_move_tail(&rt_se->run_list, queue); + if (on_rt_rq(rt_se)) { + list_del_init(&rt_se->run_list); + list_add_tail(&rt_se->run_list, + array->queue + rt_se_prio(rt_se)); + } } static void requeue_task_rt(struct rq *rq, struct task_struct *p) @@ -616,8 +760,37 @@ static int select_task_rq_rt(struct task_struct *p, int sync) */ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p) { - if (p->prio < rq->curr->prio) + if (p->prio < rq->curr->prio) { resched_task(rq->curr); + return; + } + +#ifdef CONFIG_SMP + /* + * If: + * + * - the newly woken task is of equal priority to the current task + * - the newly woken task is non-migratable while current is migratable + * - current will be preempted on the next reschedule + * + * we should check to see if current can readily move to a different + * cpu. If so, we will reschedule to allow the push logic to try + * to move current somewhere else, making room for our non-migratable + * task. + */ + if((p->prio == rq->curr->prio) + && p->rt.nr_cpus_allowed == 1 + && rq->curr->rt.nr_cpus_allowed != 1) { + cpumask_t mask; + + if (cpupri_find(&rq->rd->cpupri, rq->curr, &mask)) + /* + * There appears to be other cpus that can accept + * current, so lets reschedule to try and push it away + */ + resched_task(rq->curr); + } +#endif } static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq, @@ -720,73 +893,6 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu) static DEFINE_PER_CPU(cpumask_t, local_cpu_mask); -static int find_lowest_cpus(struct task_struct *task, cpumask_t *lowest_mask) -{ - int lowest_prio = -1; - int lowest_cpu = -1; - int count = 0; - int cpu; - - cpus_and(*lowest_mask, task_rq(task)->rd->online, task->cpus_allowed); - - /* - * Scan each rq for the lowest prio. - */ - for_each_cpu_mask(cpu, *lowest_mask) { - struct rq *rq = cpu_rq(cpu); - - /* We look for lowest RT prio or non-rt CPU */ - if (rq->rt.highest_prio >= MAX_RT_PRIO) { - /* - * if we already found a low RT queue - * and now we found this non-rt queue - * clear the mask and set our bit. - * Otherwise just return the queue as is - * and the count==1 will cause the algorithm - * to use the first bit found. - */ - if (lowest_cpu != -1) { - cpus_clear(*lowest_mask); - cpu_set(rq->cpu, *lowest_mask); - } - return 1; - } - - /* no locking for now */ - if ((rq->rt.highest_prio > task->prio) - && (rq->rt.highest_prio >= lowest_prio)) { - if (rq->rt.highest_prio > lowest_prio) { - /* new low - clear old data */ - lowest_prio = rq->rt.highest_prio; - lowest_cpu = cpu; - count = 0; - } - count++; - } else - cpu_clear(cpu, *lowest_mask); - } - - /* - * Clear out all the set bits that represent - * runqueues that were of higher prio than - * the lowest_prio. - */ - if (lowest_cpu > 0) { - /* - * Perhaps we could add another cpumask op to - * zero out bits. Like cpu_zero_bits(cpumask, nrbits); - * Then that could be optimized to use memset and such. - */ - for_each_cpu_mask(cpu, *lowest_mask) { - if (cpu >= lowest_cpu) - break; - cpu_clear(cpu, *lowest_mask); - } - } - - return count; -} - static inline int pick_optimal_cpu(int this_cpu, cpumask_t *mask) { int first; @@ -808,17 +914,12 @@ static int find_lowest_rq(struct task_struct *task) cpumask_t *lowest_mask = &__get_cpu_var(local_cpu_mask); int this_cpu = smp_processor_id(); int cpu = task_cpu(task); - int count = find_lowest_cpus(task, lowest_mask); - if (!count) - return -1; /* No targets found */ + if (task->rt.nr_cpus_allowed == 1) + return -1; /* No other targets possible */ - /* - * There is no sense in performing an optimal search if only one - * target is found. - */ - if (count == 1) - return first_cpu(*lowest_mask); + if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask)) + return -1; /* No targets found */ /* * At this point we have built a mask of cpus representing the @@ -1163,17 +1264,25 @@ static void set_cpus_allowed_rt(struct task_struct *p, } /* Assumes rq->lock is held */ -static void join_domain_rt(struct rq *rq) +static void rq_online_rt(struct rq *rq) { if (rq->rt.overloaded) rt_set_overload(rq); + + __enable_runtime(rq); + + cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio); } /* Assumes rq->lock is held */ -static void leave_domain_rt(struct rq *rq) +static void rq_offline_rt(struct rq *rq) { if (rq->rt.overloaded) rt_clear_overload(rq); + + __disable_runtime(rq); + + cpupri_set(&rq->rd->cpupri, rq->cpu, CPUPRI_INVALID); } /* @@ -1336,8 +1445,8 @@ static const struct sched_class rt_sched_class = { .load_balance = load_balance_rt, .move_one_task = move_one_task_rt, .set_cpus_allowed = set_cpus_allowed_rt, - .join_domain = join_domain_rt, - .leave_domain = leave_domain_rt, + .rq_online = rq_online_rt, + .rq_offline = rq_offline_rt, .pre_schedule = pre_schedule_rt, .post_schedule = post_schedule_rt, .task_wake_up = task_wake_up_rt, @@ -1350,3 +1459,17 @@ static const struct sched_class rt_sched_class = { .prio_changed = prio_changed_rt, .switched_to = switched_to_rt, }; + +#ifdef CONFIG_SCHED_DEBUG +extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq); + +static void print_rt_stats(struct seq_file *m, int cpu) +{ + struct rt_rq *rt_rq; + + rcu_read_lock(); + for_each_leaf_rt_rq(rt_rq, cpu_rq(cpu)) + print_rt_rq(m, cpu, rt_rq); + rcu_read_unlock(); +} +#endif /* CONFIG_SCHED_DEBUG */ diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index 80179ef7450..8385d43987e 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -118,6 +118,13 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta) if (rq) rq->rq_sched_info.cpu_time += delta; } + +static inline void +rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) +{ + if (rq) + rq->rq_sched_info.run_delay += delta; +} # define schedstat_inc(rq, field) do { (rq)->field++; } while (0) # define schedstat_add(rq, field, amt) do { (rq)->field += (amt); } while (0) # define schedstat_set(var, val) do { var = (val); } while (0) @@ -126,6 +133,9 @@ static inline void rq_sched_info_arrive(struct rq *rq, unsigned long long delta) {} static inline void +rq_sched_info_dequeued(struct rq *rq, unsigned long long delta) +{} +static inline void rq_sched_info_depart(struct rq *rq, unsigned long long delta) {} # define schedstat_inc(rq, field) do { } while (0) @@ -134,6 +144,11 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta) #endif #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) +static inline void sched_info_reset_dequeued(struct task_struct *t) +{ + t->sched_info.last_queued = 0; +} + /* * Called when a process is dequeued from the active array and given * the cpu. We should note that with the exception of interactive @@ -143,15 +158,22 @@ rq_sched_info_depart(struct rq *rq, unsigned long long delta) * active queue, thus delaying tasks in the expired queue from running; * see scheduler_tick()). * - * This function is only called from sched_info_arrive(), rather than - * dequeue_task(). Even though a task may be queued and dequeued multiple - * times as it is shuffled about, we're really interested in knowing how - * long it was from the *first* time it was queued to the time that it - * finally hit a cpu. + * Though we are interested in knowing how long it was from the *first* time a + * task was queued to the time that it finally hit a cpu, we call this routine + * from dequeue_task() to account for possible rq->clock skew across cpus. The + * delta taken on each cpu would annul the skew. */ static inline void sched_info_dequeued(struct task_struct *t) { - t->sched_info.last_queued = 0; + unsigned long long now = task_rq(t)->clock, delta = 0; + + if (unlikely(sched_info_on())) + if (t->sched_info.last_queued) + delta = now - t->sched_info.last_queued; + sched_info_reset_dequeued(t); + t->sched_info.run_delay += delta; + + rq_sched_info_dequeued(task_rq(t), delta); } /* @@ -165,7 +187,7 @@ static void sched_info_arrive(struct task_struct *t) if (t->sched_info.last_queued) delta = now - t->sched_info.last_queued; - sched_info_dequeued(t); + sched_info_reset_dequeued(t); t->sched_info.run_delay += delta; t->sched_info.last_arrival = now; t->sched_info.pcount++; @@ -242,7 +264,9 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next) __sched_info_switch(prev, next); } #else -#define sched_info_queued(t) do { } while (0) -#define sched_info_switch(t, next) do { } while (0) +#define sched_info_queued(t) do { } while (0) +#define sched_info_reset_dequeued(t) do { } while (0) +#define sched_info_dequeued(t) do { } while (0) +#define sched_info_switch(t, next) do { } while (0) #endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */ diff --git a/kernel/semaphore.c b/kernel/semaphore.c index 5c2942e768c..aaaeae8244e 100644 --- a/kernel/semaphore.c +++ b/kernel/semaphore.c @@ -31,6 +31,7 @@ #include <linux/sched.h> #include <linux/semaphore.h> #include <linux/spinlock.h> +#include <linux/ftrace.h> static noinline void __down(struct semaphore *sem); static noinline int __down_interruptible(struct semaphore *sem); diff --git a/kernel/smp.c b/kernel/smp.c new file mode 100644 index 00000000000..462c785ca1e --- /dev/null +++ b/kernel/smp.c @@ -0,0 +1,383 @@ +/* + * Generic helpers for smp ipi calls + * + * (C) Jens Axboe <jens.axboe@oracle.com> 2008 + * + */ +#include <linux/init.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/rcupdate.h> +#include <linux/rculist.h> +#include <linux/smp.h> + +static DEFINE_PER_CPU(struct call_single_queue, call_single_queue); +static LIST_HEAD(call_function_queue); +__cacheline_aligned_in_smp DEFINE_SPINLOCK(call_function_lock); + +enum { + CSD_FLAG_WAIT = 0x01, + CSD_FLAG_ALLOC = 0x02, +}; + +struct call_function_data { + struct call_single_data csd; + spinlock_t lock; + unsigned int refs; + cpumask_t cpumask; + struct rcu_head rcu_head; +}; + +struct call_single_queue { + struct list_head list; + spinlock_t lock; +}; + +void __cpuinit init_call_single_data(void) +{ + int i; + + for_each_possible_cpu(i) { + struct call_single_queue *q = &per_cpu(call_single_queue, i); + + spin_lock_init(&q->lock); + INIT_LIST_HEAD(&q->list); + } +} + +static void csd_flag_wait(struct call_single_data *data) +{ + /* Wait for response */ + do { + /* + * We need to see the flags store in the IPI handler + */ + smp_mb(); + if (!(data->flags & CSD_FLAG_WAIT)) + break; + cpu_relax(); + } while (1); +} + +/* + * Insert a previously allocated call_single_data element for execution + * on the given CPU. data must already have ->func, ->info, and ->flags set. + */ +static void generic_exec_single(int cpu, struct call_single_data *data) +{ + struct call_single_queue *dst = &per_cpu(call_single_queue, cpu); + int wait = data->flags & CSD_FLAG_WAIT, ipi; + unsigned long flags; + + spin_lock_irqsave(&dst->lock, flags); + ipi = list_empty(&dst->list); + list_add_tail(&data->list, &dst->list); + spin_unlock_irqrestore(&dst->lock, flags); + + if (ipi) + arch_send_call_function_single_ipi(cpu); + + if (wait) + csd_flag_wait(data); +} + +static void rcu_free_call_data(struct rcu_head *head) +{ + struct call_function_data *data; + + data = container_of(head, struct call_function_data, rcu_head); + + kfree(data); +} + +/* + * Invoked by arch to handle an IPI for call function. Must be called with + * interrupts disabled. + */ +void generic_smp_call_function_interrupt(void) +{ + struct call_function_data *data; + int cpu = get_cpu(); + + /* + * It's ok to use list_for_each_rcu() here even though we may delete + * 'pos', since list_del_rcu() doesn't clear ->next + */ + rcu_read_lock(); + list_for_each_entry_rcu(data, &call_function_queue, csd.list) { + int refs; + + if (!cpu_isset(cpu, data->cpumask)) + continue; + + data->csd.func(data->csd.info); + + spin_lock(&data->lock); + cpu_clear(cpu, data->cpumask); + WARN_ON(data->refs == 0); + data->refs--; + refs = data->refs; + spin_unlock(&data->lock); + + if (refs) + continue; + + spin_lock(&call_function_lock); + list_del_rcu(&data->csd.list); + spin_unlock(&call_function_lock); + + if (data->csd.flags & CSD_FLAG_WAIT) { + /* + * serialize stores to data with the flag clear + * and wakeup + */ + smp_wmb(); + data->csd.flags &= ~CSD_FLAG_WAIT; + } else + call_rcu(&data->rcu_head, rcu_free_call_data); + } + rcu_read_unlock(); + + put_cpu(); +} + +/* + * Invoked by arch to handle an IPI for call function single. Must be called + * from the arch with interrupts disabled. + */ +void generic_smp_call_function_single_interrupt(void) +{ + struct call_single_queue *q = &__get_cpu_var(call_single_queue); + LIST_HEAD(list); + + /* + * Need to see other stores to list head for checking whether + * list is empty without holding q->lock + */ + smp_mb(); + while (!list_empty(&q->list)) { + unsigned int data_flags; + + spin_lock(&q->lock); + list_replace_init(&q->list, &list); + spin_unlock(&q->lock); + + while (!list_empty(&list)) { + struct call_single_data *data; + + data = list_entry(list.next, struct call_single_data, + list); + list_del(&data->list); + + /* + * 'data' can be invalid after this call if + * flags == 0 (when called through + * generic_exec_single(), so save them away before + * making the call. + */ + data_flags = data->flags; + + data->func(data->info); + + if (data_flags & CSD_FLAG_WAIT) { + smp_wmb(); + data->flags &= ~CSD_FLAG_WAIT; + } else if (data_flags & CSD_FLAG_ALLOC) + kfree(data); + } + /* + * See comment on outer loop + */ + smp_mb(); + } +} + +/* + * smp_call_function_single - Run a function on a specific CPU + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @wait: If true, wait until function has completed on other CPUs. + * + * Returns 0 on success, else a negative status code. Note that @wait + * will be implicitly turned on in case of allocation failures, since + * we fall back to on-stack allocation. + */ +int smp_call_function_single(int cpu, void (*func) (void *info), void *info, + int wait) +{ + struct call_single_data d; + unsigned long flags; + /* prevent preemption and reschedule on another processor */ + int me = get_cpu(); + + /* Can deadlock when called with interrupts disabled */ + WARN_ON(irqs_disabled()); + + if (cpu == me) { + local_irq_save(flags); + func(info); + local_irq_restore(flags); + } else { + struct call_single_data *data = NULL; + + if (!wait) { + data = kmalloc(sizeof(*data), GFP_ATOMIC); + if (data) + data->flags = CSD_FLAG_ALLOC; + } + if (!data) { + data = &d; + data->flags = CSD_FLAG_WAIT; + } + + data->func = func; + data->info = info; + generic_exec_single(cpu, data); + } + + put_cpu(); + return 0; +} +EXPORT_SYMBOL(smp_call_function_single); + +/** + * __smp_call_function_single(): Run a function on another CPU + * @cpu: The CPU to run on. + * @data: Pre-allocated and setup data structure + * + * Like smp_call_function_single(), but allow caller to pass in a pre-allocated + * data structure. Useful for embedding @data inside other structures, for + * instance. + * + */ +void __smp_call_function_single(int cpu, struct call_single_data *data) +{ + /* Can deadlock when called with interrupts disabled */ + WARN_ON((data->flags & CSD_FLAG_WAIT) && irqs_disabled()); + + generic_exec_single(cpu, data); +} + +/** + * smp_call_function_mask(): Run a function on a set of other CPUs. + * @mask: The set of cpus to run on. + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @wait: If true, wait (atomically) until function has completed on other CPUs. + * + * Returns 0 on success, else a negative status code. + * + * If @wait is true, then returns once @func has returned. Note that @wait + * will be implicitly turned on in case of allocation failures, since + * we fall back to on-stack allocation. + * + * You must not call this function with disabled interrupts or from a + * hardware interrupt handler or from a bottom half handler. Preemption + * must be disabled when calling this function. + */ +int smp_call_function_mask(cpumask_t mask, void (*func)(void *), void *info, + int wait) +{ + struct call_function_data d; + struct call_function_data *data = NULL; + cpumask_t allbutself; + unsigned long flags; + int cpu, num_cpus; + + /* Can deadlock when called with interrupts disabled */ + WARN_ON(irqs_disabled()); + + cpu = smp_processor_id(); + allbutself = cpu_online_map; + cpu_clear(cpu, allbutself); + cpus_and(mask, mask, allbutself); + num_cpus = cpus_weight(mask); + + /* + * If zero CPUs, return. If just a single CPU, turn this request + * into a targetted single call instead since it's faster. + */ + if (!num_cpus) + return 0; + else if (num_cpus == 1) { + cpu = first_cpu(mask); + return smp_call_function_single(cpu, func, info, wait); + } + + if (!wait) { + data = kmalloc(sizeof(*data), GFP_ATOMIC); + if (data) + data->csd.flags = CSD_FLAG_ALLOC; + } + if (!data) { + data = &d; + data->csd.flags = CSD_FLAG_WAIT; + wait = 1; + } + + spin_lock_init(&data->lock); + data->csd.func = func; + data->csd.info = info; + data->refs = num_cpus; + data->cpumask = mask; + + spin_lock_irqsave(&call_function_lock, flags); + list_add_tail_rcu(&data->csd.list, &call_function_queue); + spin_unlock_irqrestore(&call_function_lock, flags); + + /* Send a message to all CPUs in the map */ + arch_send_call_function_ipi(mask); + + /* optionally wait for the CPUs to complete */ + if (wait) + csd_flag_wait(&data->csd); + + return 0; +} +EXPORT_SYMBOL(smp_call_function_mask); + +/** + * smp_call_function(): Run a function on all other CPUs. + * @func: The function to run. This must be fast and non-blocking. + * @info: An arbitrary pointer to pass to the function. + * @wait: If true, wait (atomically) until function has completed on other CPUs. + * + * Returns 0 on success, else a negative status code. + * + * If @wait is true, then returns once @func has returned; otherwise + * it returns just before the target cpu calls @func. In case of allocation + * failure, @wait will be implicitly turned on. + * + * You must not call this function with disabled interrupts or from a + * hardware interrupt handler or from a bottom half handler. + */ +int smp_call_function(void (*func)(void *), void *info, int wait) +{ + int ret; + + preempt_disable(); + ret = smp_call_function_mask(cpu_online_map, func, info, wait); + preempt_enable(); + return ret; +} +EXPORT_SYMBOL(smp_call_function); + +void ipi_call_lock(void) +{ + spin_lock(&call_function_lock); +} + +void ipi_call_unlock(void) +{ + spin_unlock(&call_function_lock); +} + +void ipi_call_lock_irq(void) +{ + spin_lock_irq(&call_function_lock); +} + +void ipi_call_unlock_irq(void) +{ + spin_unlock_irq(&call_function_lock); +} diff --git a/kernel/softirq.c b/kernel/softirq.c index 36e06174004..81e2fe0f983 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -131,23 +131,17 @@ void _local_bh_enable(void) EXPORT_SYMBOL(_local_bh_enable); -void local_bh_enable(void) +static inline void _local_bh_enable_ip(unsigned long ip) { + WARN_ON_ONCE(in_irq() || irqs_disabled()); #ifdef CONFIG_TRACE_IRQFLAGS - unsigned long flags; - - WARN_ON_ONCE(in_irq()); -#endif - WARN_ON_ONCE(irqs_disabled()); - -#ifdef CONFIG_TRACE_IRQFLAGS - local_irq_save(flags); + local_irq_disable(); #endif /* * Are softirqs going to be turned on now: */ if (softirq_count() == SOFTIRQ_OFFSET) - trace_softirqs_on((unsigned long)__builtin_return_address(0)); + trace_softirqs_on(ip); /* * Keep preemption disabled until we are done with * softirq processing: @@ -159,40 +153,20 @@ void local_bh_enable(void) dec_preempt_count(); #ifdef CONFIG_TRACE_IRQFLAGS - local_irq_restore(flags); + local_irq_enable(); #endif preempt_check_resched(); } + +void local_bh_enable(void) +{ + _local_bh_enable_ip((unsigned long)__builtin_return_address(0)); +} EXPORT_SYMBOL(local_bh_enable); void local_bh_enable_ip(unsigned long ip) { -#ifdef CONFIG_TRACE_IRQFLAGS - unsigned long flags; - - WARN_ON_ONCE(in_irq()); - - local_irq_save(flags); -#endif - /* - * Are softirqs going to be turned on now: - */ - if (softirq_count() == SOFTIRQ_OFFSET) - trace_softirqs_on(ip); - /* - * Keep preemption disabled until we are done with - * softirq processing: - */ - sub_preempt_count(SOFTIRQ_OFFSET - 1); - - if (unlikely(!in_interrupt() && local_softirq_pending())) - do_softirq(); - - dec_preempt_count(); -#ifdef CONFIG_TRACE_IRQFLAGS - local_irq_restore(flags); -#endif - preempt_check_resched(); + _local_bh_enable_ip(ip); } EXPORT_SYMBOL(local_bh_enable_ip); @@ -347,9 +321,8 @@ void raise_softirq(unsigned int nr) local_irq_restore(flags); } -void open_softirq(int nr, void (*action)(struct softirq_action*), void *data) +void open_softirq(int nr, void (*action)(struct softirq_action *)) { - softirq_vec[nr].data = data; softirq_vec[nr].action = action; } @@ -360,10 +333,8 @@ struct tasklet_head struct tasklet_struct **tail; }; -/* Some compilers disobey section attribute on statics when not - initialized -- RR */ -static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec) = { NULL }; -static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec) = { NULL }; +static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec); +static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec); void __tasklet_schedule(struct tasklet_struct *t) { @@ -503,8 +474,8 @@ void __init softirq_init(void) &per_cpu(tasklet_hi_vec, cpu).head; } - open_softirq(TASKLET_SOFTIRQ, tasklet_action, NULL); - open_softirq(HI_SOFTIRQ, tasklet_hi_action, NULL); + open_softirq(TASKLET_SOFTIRQ, tasklet_action); + open_softirq(HI_SOFTIRQ, tasklet_hi_action); } static int ksoftirqd(void * __bind_cpu) @@ -645,7 +616,7 @@ static int __cpuinit cpu_callback(struct notifier_block *nfb, p = per_cpu(ksoftirqd, hotcpu); per_cpu(ksoftirqd, hotcpu) = NULL; - sched_setscheduler(p, SCHED_FIFO, ¶m); + sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m); kthread_stop(p); takeover_tasklets(hotcpu); break; @@ -674,12 +645,12 @@ __init int spawn_ksoftirqd(void) /* * Call a function on all processors */ -int on_each_cpu(void (*func) (void *info), void *info, int retry, int wait) +int on_each_cpu(void (*func) (void *info), void *info, int wait) { int ret = 0; preempt_disable(); - ret = smp_call_function(func, info, retry, wait); + ret = smp_call_function(func, info, wait); local_irq_disable(); func(info); local_irq_enable(); diff --git a/kernel/softlockup.c b/kernel/softlockup.c index c828c2339cc..a272d78185e 100644 --- a/kernel/softlockup.c +++ b/kernel/softlockup.c @@ -120,6 +120,7 @@ void softlockup_tick(void) printk(KERN_ERR "BUG: soft lockup - CPU#%d stuck for %lus! [%s:%d]\n", this_cpu, now - touch_timestamp, current->comm, task_pid_nr(current)); + print_modules(); if (regs) show_regs(regs); else diff --git a/kernel/spinlock.c b/kernel/spinlock.c index ae28c824512..a1fb54c93cd 100644 --- a/kernel/spinlock.c +++ b/kernel/spinlock.c @@ -436,7 +436,7 @@ int __lockfunc _spin_trylock_bh(spinlock_t *lock) } EXPORT_SYMBOL(_spin_trylock_bh); -int in_lock_functions(unsigned long addr) +notrace int in_lock_functions(unsigned long addr) { /* Linker adds these: start and end of __lockfunc functions */ extern char __lock_text_start[], __lock_text_end[]; diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c index b71816e47a3..94b527ef1d1 100644 --- a/kernel/stacktrace.c +++ b/kernel/stacktrace.c @@ -6,19 +6,21 @@ * Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> */ #include <linux/sched.h> +#include <linux/module.h> #include <linux/kallsyms.h> #include <linux/stacktrace.h> void print_stack_trace(struct stack_trace *trace, int spaces) { - int i, j; + int i; - for (i = 0; i < trace->nr_entries; i++) { - unsigned long ip = trace->entries[i]; + if (WARN_ON(!trace->entries)) + return; - for (j = 0; j < spaces + 1; j++) - printk(" "); - print_ip_sym(ip); + for (i = 0; i < trace->nr_entries; i++) { + printk("%*c", 1 + spaces, ' '); + print_ip_sym(trace->entries[i]); } } +EXPORT_SYMBOL_GPL(print_stack_trace); diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index b7350bbfb07..ba9b2054ecb 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -187,7 +187,7 @@ struct task_struct *__stop_machine_run(int (*fn)(void *), void *data, struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; /* One high-prio thread per cpu. We'll do this one. */ - sched_setscheduler(p, SCHED_FIFO, ¶m); + sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m); kthread_bind(p, cpu); wake_up_process(p); wait_for_completion(&smdata.done); diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 29116652dca..6b16e16428d 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -46,6 +46,7 @@ #include <linux/nfs_fs.h> #include <linux/acpi.h> #include <linux/reboot.h> +#include <linux/ftrace.h> #include <asm/uaccess.h> #include <asm/processor.h> @@ -82,6 +83,9 @@ extern int maps_protect; extern int sysctl_stat_interval; extern int latencytop_enabled; extern int sysctl_nr_open_min, sysctl_nr_open_max; +#ifdef CONFIG_RCU_TORTURE_TEST +extern int rcutorture_runnable; +#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */ /* Constants used for minimum and maximum */ #if defined(CONFIG_DETECT_SOFTLOCKUP) || defined(CONFIG_HIGHMEM) @@ -132,8 +136,6 @@ extern int sysctl_userprocess_debug; extern int spin_retry; #endif -extern int sysctl_hz_timer; - #ifdef CONFIG_BSD_PROCESS_ACCT extern int acct_parm[]; #endif @@ -266,6 +268,14 @@ static struct ctl_table kern_table[] = { }, { .ctl_name = CTL_UNNUMBERED, + .procname = "sched_shares_ratelimit", + .data = &sysctl_sched_shares_ratelimit, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = CTL_UNNUMBERED, .procname = "sched_child_runs_first", .data = &sysctl_sched_child_runs_first, .maxlen = sizeof(unsigned int), @@ -455,6 +465,16 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = &proc_dointvec, }, +#ifdef CONFIG_FTRACE + { + .ctl_name = CTL_UNNUMBERED, + .procname = "ftrace_enabled", + .data = &ftrace_enabled, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &ftrace_enable_sysctl, + }, +#endif #ifdef CONFIG_KMOD { .ctl_name = KERN_MODPROBE, @@ -563,16 +583,6 @@ static struct ctl_table kern_table[] = { .proc_handler = &proc_dointvec, }, #endif -#ifdef CONFIG_NO_IDLE_HZ - { - .ctl_name = KERN_HZ_TIMER, - .procname = "hz_timer", - .data = &sysctl_hz_timer, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = &proc_dointvec, - }, -#endif { .ctl_name = KERN_S390_USER_DEBUG_LOGGING, .procname = "userprocess_debug", @@ -813,6 +823,16 @@ static struct ctl_table kern_table[] = { .child = key_sysctls, }, #endif +#ifdef CONFIG_RCU_TORTURE_TEST + { + .ctl_name = CTL_UNNUMBERED, + .procname = "rcutorture_runnable", + .data = &rcutorture_runnable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, +#endif /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 57a1f02e5ec..f48d0f09d32 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -30,6 +30,7 @@ struct tick_device tick_broadcast_device; static cpumask_t tick_broadcast_mask; static DEFINE_SPINLOCK(tick_broadcast_lock); +static int tick_broadcast_force; #ifdef CONFIG_TICK_ONESHOT static void tick_broadcast_clear_oneshot(int cpu); @@ -232,10 +233,11 @@ static void tick_do_broadcast_on_off(void *why) CLOCK_EVT_MODE_SHUTDOWN); } if (*reason == CLOCK_EVT_NOTIFY_BROADCAST_FORCE) - dev->features |= CLOCK_EVT_FEAT_DUMMY; + tick_broadcast_force = 1; break; case CLOCK_EVT_NOTIFY_BROADCAST_OFF: - if (cpu_isset(cpu, tick_broadcast_mask)) { + if (!tick_broadcast_force && + cpu_isset(cpu, tick_broadcast_mask)) { cpu_clear(cpu, tick_broadcast_mask); if (td->mode == TICKDEV_MODE_PERIODIC) tick_setup_periodic(dev, 0); @@ -266,7 +268,7 @@ void tick_broadcast_on_off(unsigned long reason, int *oncpu) "offline CPU #%d\n", *oncpu); else smp_call_function_single(*oncpu, tick_do_broadcast_on_off, - &reason, 1, 1); + &reason, 1); } /* diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index b854a895591..beef7ccdf84 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -48,6 +48,13 @@ static void tick_do_update_jiffies64(ktime_t now) unsigned long ticks = 0; ktime_t delta; + /* + * Do a quick check without holding xtime_lock: + */ + delta = ktime_sub(now, last_jiffies_update); + if (delta.tv64 < tick_period.tv64) + return; + /* Reevalute with xtime_lock held */ write_seqlock(&xtime_lock); @@ -228,6 +235,7 @@ void tick_nohz_stop_sched_tick(void) local_softirq_pending()); ratelimit++; } + goto end; } ts->idle_calls++; @@ -276,6 +284,7 @@ void tick_nohz_stop_sched_tick(void) ts->tick_stopped = 1; ts->idle_jiffies = last_jiffies; rcu_enter_nohz(); + sched_clock_tick_stop(cpu); } /* @@ -375,6 +384,7 @@ void tick_nohz_restart_sched_tick(void) select_nohz_load_balancer(0); now = ktime_get(); tick_do_update_jiffies64(now); + sched_clock_tick_start(cpu); cpu_clear(cpu, nohz_cpu_mask); /* diff --git a/kernel/timer.c b/kernel/timer.c index ceacc662657..03bc7f1f159 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -812,7 +812,7 @@ static inline void __run_timers(struct tvec_base *base) spin_unlock_irq(&base->lock); } -#if defined(CONFIG_NO_IDLE_HZ) || defined(CONFIG_NO_HZ) +#ifdef CONFIG_NO_HZ /* * Find out when the next timer event is due to happen. This * is used on S/390 to stop all activity when a cpus is idle. @@ -947,14 +947,6 @@ unsigned long get_next_timer_interrupt(unsigned long now) return cmp_next_hrtimer_event(now, expires); } - -#ifdef CONFIG_NO_IDLE_HZ -unsigned long next_timer_interrupt(void) -{ - return get_next_timer_interrupt(jiffies); -} -#endif - #endif #ifndef CONFIG_VIRT_CPU_ACCOUNTING @@ -1502,7 +1494,7 @@ void __init init_timers(void) BUG_ON(err == NOTIFY_BAD); register_cpu_notifier(&timers_nb); - open_softirq(TIMER_SOFTIRQ, run_timer_softirq, NULL); + open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } /** diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig new file mode 100644 index 00000000000..263e9e6bbd6 --- /dev/null +++ b/kernel/trace/Kconfig @@ -0,0 +1,135 @@ +# +# Architectures that offer an FTRACE implementation should select HAVE_FTRACE: +# +config HAVE_FTRACE + bool + +config HAVE_DYNAMIC_FTRACE + bool + +config TRACER_MAX_TRACE + bool + +config TRACING + bool + select DEBUG_FS + select STACKTRACE + +config FTRACE + bool "Kernel Function Tracer" + depends on HAVE_FTRACE + select FRAME_POINTER + select TRACING + select CONTEXT_SWITCH_TRACER + help + Enable the kernel to trace every kernel function. This is done + by using a compiler feature to insert a small, 5-byte No-Operation + instruction to the beginning of every kernel function, which NOP + sequence is then dynamically patched into a tracer call when + tracing is enabled by the administrator. If it's runtime disabled + (the bootup default), then the overhead of the instructions is very + small and not measurable even in micro-benchmarks. + +config IRQSOFF_TRACER + bool "Interrupts-off Latency Tracer" + default n + depends on TRACE_IRQFLAGS_SUPPORT + depends on GENERIC_TIME + depends on HAVE_FTRACE + select TRACE_IRQFLAGS + select TRACING + select TRACER_MAX_TRACE + help + This option measures the time spent in irqs-off critical + sections, with microsecond accuracy. + + The default measurement method is a maximum search, which is + disabled by default and can be runtime (re-)started + via: + + echo 0 > /debugfs/tracing/tracing_max_latency + + (Note that kernel size and overhead increases with this option + enabled. This option and the preempt-off timing option can be + used together or separately.) + +config PREEMPT_TRACER + bool "Preemption-off Latency Tracer" + default n + depends on GENERIC_TIME + depends on PREEMPT + depends on HAVE_FTRACE + select TRACING + select TRACER_MAX_TRACE + help + This option measures the time spent in preemption off critical + sections, with microsecond accuracy. + + The default measurement method is a maximum search, which is + disabled by default and can be runtime (re-)started + via: + + echo 0 > /debugfs/tracing/tracing_max_latency + + (Note that kernel size and overhead increases with this option + enabled. This option and the irqs-off timing option can be + used together or separately.) + +config SYSPROF_TRACER + bool "Sysprof Tracer" + depends on X86 + select TRACING + help + This tracer provides the trace needed by the 'Sysprof' userspace + tool. + +config SCHED_TRACER + bool "Scheduling Latency Tracer" + depends on HAVE_FTRACE + select TRACING + select CONTEXT_SWITCH_TRACER + select TRACER_MAX_TRACE + help + This tracer tracks the latency of the highest priority task + to be scheduled in, starting from the point it has woken up. + +config CONTEXT_SWITCH_TRACER + bool "Trace process context switches" + depends on HAVE_FTRACE + select TRACING + select MARKERS + help + This tracer gets called from the context switch and records + all switching of tasks. + +config DYNAMIC_FTRACE + bool "enable/disable ftrace tracepoints dynamically" + depends on FTRACE + depends on HAVE_DYNAMIC_FTRACE + default y + help + This option will modify all the calls to ftrace dynamically + (will patch them out of the binary image and replaces them + with a No-Op instruction) as they are called. A table is + created to dynamically enable them again. + + This way a CONFIG_FTRACE kernel is slightly larger, but otherwise + has native performance as long as no tracing is active. + + The changes to the code are done by a kernel thread that + wakes up once a second and checks to see if any ftrace calls + were made. If so, it runs stop_machine (stops all CPUS) + and modifies the code to jump over the call to ftrace. + +config FTRACE_SELFTEST + bool + +config FTRACE_STARTUP_TEST + bool "Perform a startup test on ftrace" + depends on TRACING + select FTRACE_SELFTEST + help + This option performs a series of startup tests on ftrace. On bootup + a series of tests are made to verify that the tracer is + functioning properly. It will do tests on all the configured + tracers of ftrace. diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile new file mode 100644 index 00000000000..71d17de1728 --- /dev/null +++ b/kernel/trace/Makefile @@ -0,0 +1,24 @@ + +# Do not instrument the tracer itself: + +ifdef CONFIG_FTRACE +ORIG_CFLAGS := $(KBUILD_CFLAGS) +KBUILD_CFLAGS = $(subst -pg,,$(ORIG_CFLAGS)) + +# selftest needs instrumentation +CFLAGS_trace_selftest_dynamic.o = -pg +obj-y += trace_selftest_dynamic.o +endif + +obj-$(CONFIG_FTRACE) += libftrace.o + +obj-$(CONFIG_TRACING) += trace.o +obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o +obj-$(CONFIG_SYSPROF_TRACER) += trace_sysprof.o +obj-$(CONFIG_FTRACE) += trace_functions.o +obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o +obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o +obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o +obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o + +libftrace-y := ftrace.o diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c new file mode 100644 index 00000000000..4231a3dc224 --- /dev/null +++ b/kernel/trace/ftrace.c @@ -0,0 +1,1727 @@ +/* + * Infrastructure for profiling code inserted by 'gcc -pg'. + * + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * Copyright (C) 2004-2008 Ingo Molnar <mingo@redhat.com> + * + * Originally ported from the -rt patch by: + * Copyright (C) 2007 Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Based on code in the latency_tracer, that is: + * + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 William Lee Irwin III + */ + +#include <linux/stop_machine.h> +#include <linux/clocksource.h> +#include <linux/kallsyms.h> +#include <linux/seq_file.h> +#include <linux/debugfs.h> +#include <linux/hardirq.h> +#include <linux/kthread.h> +#include <linux/uaccess.h> +#include <linux/kprobes.h> +#include <linux/ftrace.h> +#include <linux/sysctl.h> +#include <linux/ctype.h> +#include <linux/hash.h> +#include <linux/list.h> + +#include <asm/ftrace.h> + +#include "trace.h" + +/* ftrace_enabled is a method to turn ftrace on or off */ +int ftrace_enabled __read_mostly; +static int last_ftrace_enabled; + +/* + * ftrace_disabled is set when an anomaly is discovered. + * ftrace_disabled is much stronger than ftrace_enabled. + */ +static int ftrace_disabled __read_mostly; + +static DEFINE_SPINLOCK(ftrace_lock); +static DEFINE_MUTEX(ftrace_sysctl_lock); + +static struct ftrace_ops ftrace_list_end __read_mostly = +{ + .func = ftrace_stub, +}; + +static struct ftrace_ops *ftrace_list __read_mostly = &ftrace_list_end; +ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub; + +static void ftrace_list_func(unsigned long ip, unsigned long parent_ip) +{ + struct ftrace_ops *op = ftrace_list; + + /* in case someone actually ports this to alpha! */ + read_barrier_depends(); + + while (op != &ftrace_list_end) { + /* silly alpha */ + read_barrier_depends(); + op->func(ip, parent_ip); + op = op->next; + }; +} + +/** + * clear_ftrace_function - reset the ftrace function + * + * This NULLs the ftrace function and in essence stops + * tracing. There may be lag + */ +void clear_ftrace_function(void) +{ + ftrace_trace_function = ftrace_stub; +} + +static int __register_ftrace_function(struct ftrace_ops *ops) +{ + /* Should never be called by interrupts */ + spin_lock(&ftrace_lock); + + ops->next = ftrace_list; + /* + * We are entering ops into the ftrace_list but another + * CPU might be walking that list. We need to make sure + * the ops->next pointer is valid before another CPU sees + * the ops pointer included into the ftrace_list. + */ + smp_wmb(); + ftrace_list = ops; + + if (ftrace_enabled) { + /* + * For one func, simply call it directly. + * For more than one func, call the chain. + */ + if (ops->next == &ftrace_list_end) + ftrace_trace_function = ops->func; + else + ftrace_trace_function = ftrace_list_func; + } + + spin_unlock(&ftrace_lock); + + return 0; +} + +static int __unregister_ftrace_function(struct ftrace_ops *ops) +{ + struct ftrace_ops **p; + int ret = 0; + + spin_lock(&ftrace_lock); + + /* + * If we are removing the last function, then simply point + * to the ftrace_stub. + */ + if (ftrace_list == ops && ops->next == &ftrace_list_end) { + ftrace_trace_function = ftrace_stub; + ftrace_list = &ftrace_list_end; + goto out; + } + + for (p = &ftrace_list; *p != &ftrace_list_end; p = &(*p)->next) + if (*p == ops) + break; + + if (*p != ops) { + ret = -1; + goto out; + } + + *p = (*p)->next; + + if (ftrace_enabled) { + /* If we only have one func left, then call that directly */ + if (ftrace_list == &ftrace_list_end || + ftrace_list->next == &ftrace_list_end) + ftrace_trace_function = ftrace_list->func; + } + + out: + spin_unlock(&ftrace_lock); + + return ret; +} + +#ifdef CONFIG_DYNAMIC_FTRACE + +static struct task_struct *ftraced_task; + +enum { + FTRACE_ENABLE_CALLS = (1 << 0), + FTRACE_DISABLE_CALLS = (1 << 1), + FTRACE_UPDATE_TRACE_FUNC = (1 << 2), + FTRACE_ENABLE_MCOUNT = (1 << 3), + FTRACE_DISABLE_MCOUNT = (1 << 4), +}; + +static int ftrace_filtered; +static int tracing_on; +static int frozen_record_count; + +static struct hlist_head ftrace_hash[FTRACE_HASHSIZE]; + +static DEFINE_PER_CPU(int, ftrace_shutdown_disable_cpu); + +static DEFINE_SPINLOCK(ftrace_shutdown_lock); +static DEFINE_MUTEX(ftraced_lock); +static DEFINE_MUTEX(ftrace_regex_lock); + +struct ftrace_page { + struct ftrace_page *next; + unsigned long index; + struct dyn_ftrace records[]; +}; + +#define ENTRIES_PER_PAGE \ + ((PAGE_SIZE - sizeof(struct ftrace_page)) / sizeof(struct dyn_ftrace)) + +/* estimate from running different kernels */ +#define NR_TO_INIT 10000 + +static struct ftrace_page *ftrace_pages_start; +static struct ftrace_page *ftrace_pages; + +static int ftraced_trigger; +static int ftraced_suspend; +static int ftraced_stop; + +static int ftrace_record_suspend; + +static struct dyn_ftrace *ftrace_free_records; + + +#ifdef CONFIG_KPROBES +static inline void freeze_record(struct dyn_ftrace *rec) +{ + if (!(rec->flags & FTRACE_FL_FROZEN)) { + rec->flags |= FTRACE_FL_FROZEN; + frozen_record_count++; + } +} + +static inline void unfreeze_record(struct dyn_ftrace *rec) +{ + if (rec->flags & FTRACE_FL_FROZEN) { + rec->flags &= ~FTRACE_FL_FROZEN; + frozen_record_count--; + } +} + +static inline int record_frozen(struct dyn_ftrace *rec) +{ + return rec->flags & FTRACE_FL_FROZEN; +} +#else +# define freeze_record(rec) ({ 0; }) +# define unfreeze_record(rec) ({ 0; }) +# define record_frozen(rec) ({ 0; }) +#endif /* CONFIG_KPROBES */ + +int skip_trace(unsigned long ip) +{ + unsigned long fl; + struct dyn_ftrace *rec; + struct hlist_node *t; + struct hlist_head *head; + + if (frozen_record_count == 0) + return 0; + + head = &ftrace_hash[hash_long(ip, FTRACE_HASHBITS)]; + hlist_for_each_entry_rcu(rec, t, head, node) { + if (rec->ip == ip) { + if (record_frozen(rec)) { + if (rec->flags & FTRACE_FL_FAILED) + return 1; + + if (!(rec->flags & FTRACE_FL_CONVERTED)) + return 1; + + if (!tracing_on || !ftrace_enabled) + return 1; + + if (ftrace_filtered) { + fl = rec->flags & (FTRACE_FL_FILTER | + FTRACE_FL_NOTRACE); + if (!fl || (fl & FTRACE_FL_NOTRACE)) + return 1; + } + } + break; + } + } + + return 0; +} + +static inline int +ftrace_ip_in_hash(unsigned long ip, unsigned long key) +{ + struct dyn_ftrace *p; + struct hlist_node *t; + int found = 0; + + hlist_for_each_entry_rcu(p, t, &ftrace_hash[key], node) { + if (p->ip == ip) { + found = 1; + break; + } + } + + return found; +} + +static inline void +ftrace_add_hash(struct dyn_ftrace *node, unsigned long key) +{ + hlist_add_head_rcu(&node->node, &ftrace_hash[key]); +} + +/* called from kstop_machine */ +static inline void ftrace_del_hash(struct dyn_ftrace *node) +{ + hlist_del(&node->node); +} + +static void ftrace_free_rec(struct dyn_ftrace *rec) +{ + /* no locking, only called from kstop_machine */ + + rec->ip = (unsigned long)ftrace_free_records; + ftrace_free_records = rec; + rec->flags |= FTRACE_FL_FREE; +} + +static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip) +{ + struct dyn_ftrace *rec; + + /* First check for freed records */ + if (ftrace_free_records) { + rec = ftrace_free_records; + + if (unlikely(!(rec->flags & FTRACE_FL_FREE))) { + WARN_ON_ONCE(1); + ftrace_free_records = NULL; + ftrace_disabled = 1; + ftrace_enabled = 0; + return NULL; + } + + ftrace_free_records = (void *)rec->ip; + memset(rec, 0, sizeof(*rec)); + return rec; + } + + if (ftrace_pages->index == ENTRIES_PER_PAGE) { + if (!ftrace_pages->next) + return NULL; + ftrace_pages = ftrace_pages->next; + } + + return &ftrace_pages->records[ftrace_pages->index++]; +} + +static void +ftrace_record_ip(unsigned long ip) +{ + struct dyn_ftrace *node; + unsigned long flags; + unsigned long key; + int resched; + int atomic; + int cpu; + + if (!ftrace_enabled || ftrace_disabled) + return; + + resched = need_resched(); + preempt_disable_notrace(); + + /* + * We simply need to protect against recursion. + * Use the the raw version of smp_processor_id and not + * __get_cpu_var which can call debug hooks that can + * cause a recursive crash here. + */ + cpu = raw_smp_processor_id(); + per_cpu(ftrace_shutdown_disable_cpu, cpu)++; + if (per_cpu(ftrace_shutdown_disable_cpu, cpu) != 1) + goto out; + + if (unlikely(ftrace_record_suspend)) + goto out; + + key = hash_long(ip, FTRACE_HASHBITS); + + WARN_ON_ONCE(key >= FTRACE_HASHSIZE); + + if (ftrace_ip_in_hash(ip, key)) + goto out; + + atomic = irqs_disabled(); + + spin_lock_irqsave(&ftrace_shutdown_lock, flags); + + /* This ip may have hit the hash before the lock */ + if (ftrace_ip_in_hash(ip, key)) + goto out_unlock; + + node = ftrace_alloc_dyn_node(ip); + if (!node) + goto out_unlock; + + node->ip = ip; + + ftrace_add_hash(node, key); + + ftraced_trigger = 1; + + out_unlock: + spin_unlock_irqrestore(&ftrace_shutdown_lock, flags); + out: + per_cpu(ftrace_shutdown_disable_cpu, cpu)--; + + /* prevent recursion with scheduler */ + if (resched) + preempt_enable_no_resched_notrace(); + else + preempt_enable_notrace(); +} + +#define FTRACE_ADDR ((long)(ftrace_caller)) + +static int +__ftrace_replace_code(struct dyn_ftrace *rec, + unsigned char *old, unsigned char *new, int enable) +{ + unsigned long ip, fl; + + ip = rec->ip; + + if (ftrace_filtered && enable) { + /* + * If filtering is on: + * + * If this record is set to be filtered and + * is enabled then do nothing. + * + * If this record is set to be filtered and + * it is not enabled, enable it. + * + * If this record is not set to be filtered + * and it is not enabled do nothing. + * + * If this record is set not to trace then + * do nothing. + * + * If this record is set not to trace and + * it is enabled then disable it. + * + * If this record is not set to be filtered and + * it is enabled, disable it. + */ + + fl = rec->flags & (FTRACE_FL_FILTER | FTRACE_FL_NOTRACE | + FTRACE_FL_ENABLED); + + if ((fl == (FTRACE_FL_FILTER | FTRACE_FL_ENABLED)) || + (fl == (FTRACE_FL_FILTER | FTRACE_FL_NOTRACE)) || + !fl || (fl == FTRACE_FL_NOTRACE)) + return 0; + + /* + * If it is enabled disable it, + * otherwise enable it! + */ + if (fl & FTRACE_FL_ENABLED) { + /* swap new and old */ + new = old; + old = ftrace_call_replace(ip, FTRACE_ADDR); + rec->flags &= ~FTRACE_FL_ENABLED; + } else { + new = ftrace_call_replace(ip, FTRACE_ADDR); + rec->flags |= FTRACE_FL_ENABLED; + } + } else { + + if (enable) { + /* + * If this record is set not to trace and is + * not enabled, do nothing. + */ + fl = rec->flags & (FTRACE_FL_NOTRACE | FTRACE_FL_ENABLED); + if (fl == FTRACE_FL_NOTRACE) + return 0; + + new = ftrace_call_replace(ip, FTRACE_ADDR); + } else + old = ftrace_call_replace(ip, FTRACE_ADDR); + + if (enable) { + if (rec->flags & FTRACE_FL_ENABLED) + return 0; + rec->flags |= FTRACE_FL_ENABLED; + } else { + if (!(rec->flags & FTRACE_FL_ENABLED)) + return 0; + rec->flags &= ~FTRACE_FL_ENABLED; + } + } + + return ftrace_modify_code(ip, old, new); +} + +static void ftrace_replace_code(int enable) +{ + int i, failed; + unsigned char *new = NULL, *old = NULL; + struct dyn_ftrace *rec; + struct ftrace_page *pg; + + if (enable) + old = ftrace_nop_replace(); + else + new = ftrace_nop_replace(); + + for (pg = ftrace_pages_start; pg; pg = pg->next) { + for (i = 0; i < pg->index; i++) { + rec = &pg->records[i]; + + /* don't modify code that has already faulted */ + if (rec->flags & FTRACE_FL_FAILED) + continue; + + /* ignore updates to this record's mcount site */ + if (get_kprobe((void *)rec->ip)) { + freeze_record(rec); + continue; + } else { + unfreeze_record(rec); + } + + failed = __ftrace_replace_code(rec, old, new, enable); + if (failed && (rec->flags & FTRACE_FL_CONVERTED)) { + rec->flags |= FTRACE_FL_FAILED; + if ((system_state == SYSTEM_BOOTING) || + !core_kernel_text(rec->ip)) { + ftrace_del_hash(rec); + ftrace_free_rec(rec); + } + } + } + } +} + +static void ftrace_shutdown_replenish(void) +{ + if (ftrace_pages->next) + return; + + /* allocate another page */ + ftrace_pages->next = (void *)get_zeroed_page(GFP_KERNEL); +} + +static int +ftrace_code_disable(struct dyn_ftrace *rec) +{ + unsigned long ip; + unsigned char *nop, *call; + int failed; + + ip = rec->ip; + + nop = ftrace_nop_replace(); + call = ftrace_call_replace(ip, MCOUNT_ADDR); + + failed = ftrace_modify_code(ip, call, nop); + if (failed) { + rec->flags |= FTRACE_FL_FAILED; + return 0; + } + return 1; +} + +static int __ftrace_update_code(void *ignore); + +static int __ftrace_modify_code(void *data) +{ + unsigned long addr; + int *command = data; + + if (*command & FTRACE_ENABLE_CALLS) { + /* + * Update any recorded ips now that we have the + * machine stopped + */ + __ftrace_update_code(NULL); + ftrace_replace_code(1); + tracing_on = 1; + } else if (*command & FTRACE_DISABLE_CALLS) { + ftrace_replace_code(0); + tracing_on = 0; + } + + if (*command & FTRACE_UPDATE_TRACE_FUNC) + ftrace_update_ftrace_func(ftrace_trace_function); + + if (*command & FTRACE_ENABLE_MCOUNT) { + addr = (unsigned long)ftrace_record_ip; + ftrace_mcount_set(&addr); + } else if (*command & FTRACE_DISABLE_MCOUNT) { + addr = (unsigned long)ftrace_stub; + ftrace_mcount_set(&addr); + } + + return 0; +} + +static void ftrace_run_update_code(int command) +{ + stop_machine_run(__ftrace_modify_code, &command, NR_CPUS); +} + +void ftrace_disable_daemon(void) +{ + /* Stop the daemon from calling kstop_machine */ + mutex_lock(&ftraced_lock); + ftraced_stop = 1; + mutex_unlock(&ftraced_lock); + + ftrace_force_update(); +} + +void ftrace_enable_daemon(void) +{ + mutex_lock(&ftraced_lock); + ftraced_stop = 0; + mutex_unlock(&ftraced_lock); + + ftrace_force_update(); +} + +static ftrace_func_t saved_ftrace_func; + +static void ftrace_startup(void) +{ + int command = 0; + + if (unlikely(ftrace_disabled)) + return; + + mutex_lock(&ftraced_lock); + ftraced_suspend++; + if (ftraced_suspend == 1) + command |= FTRACE_ENABLE_CALLS; + + if (saved_ftrace_func != ftrace_trace_function) { + saved_ftrace_func = ftrace_trace_function; + command |= FTRACE_UPDATE_TRACE_FUNC; + } + + if (!command || !ftrace_enabled) + goto out; + + ftrace_run_update_code(command); + out: + mutex_unlock(&ftraced_lock); +} + +static void ftrace_shutdown(void) +{ + int command = 0; + + if (unlikely(ftrace_disabled)) + return; + + mutex_lock(&ftraced_lock); + ftraced_suspend--; + if (!ftraced_suspend) + command |= FTRACE_DISABLE_CALLS; + + if (saved_ftrace_func != ftrace_trace_function) { + saved_ftrace_func = ftrace_trace_function; + command |= FTRACE_UPDATE_TRACE_FUNC; + } + + if (!command || !ftrace_enabled) + goto out; + + ftrace_run_update_code(command); + out: + mutex_unlock(&ftraced_lock); +} + +static void ftrace_startup_sysctl(void) +{ + int command = FTRACE_ENABLE_MCOUNT; + + if (unlikely(ftrace_disabled)) + return; + + mutex_lock(&ftraced_lock); + /* Force update next time */ + saved_ftrace_func = NULL; + /* ftraced_suspend is true if we want ftrace running */ + if (ftraced_suspend) + command |= FTRACE_ENABLE_CALLS; + + ftrace_run_update_code(command); + mutex_unlock(&ftraced_lock); +} + +static void ftrace_shutdown_sysctl(void) +{ + int command = FTRACE_DISABLE_MCOUNT; + + if (unlikely(ftrace_disabled)) + return; + + mutex_lock(&ftraced_lock); + /* ftraced_suspend is true if ftrace is running */ + if (ftraced_suspend) + command |= FTRACE_DISABLE_CALLS; + + ftrace_run_update_code(command); + mutex_unlock(&ftraced_lock); +} + +static cycle_t ftrace_update_time; +static unsigned long ftrace_update_cnt; +unsigned long ftrace_update_tot_cnt; + +static int __ftrace_update_code(void *ignore) +{ + int i, save_ftrace_enabled; + cycle_t start, stop; + struct dyn_ftrace *p; + struct hlist_node *t, *n; + struct hlist_head *head, temp_list; + + /* Don't be recording funcs now */ + ftrace_record_suspend++; + save_ftrace_enabled = ftrace_enabled; + ftrace_enabled = 0; + + start = ftrace_now(raw_smp_processor_id()); + ftrace_update_cnt = 0; + + /* No locks needed, the machine is stopped! */ + for (i = 0; i < FTRACE_HASHSIZE; i++) { + INIT_HLIST_HEAD(&temp_list); + head = &ftrace_hash[i]; + + /* all CPUS are stopped, we are safe to modify code */ + hlist_for_each_entry_safe(p, t, n, head, node) { + /* Skip over failed records which have not been + * freed. */ + if (p->flags & FTRACE_FL_FAILED) + continue; + + /* Unconverted records are always at the head of the + * hash bucket. Once we encounter a converted record, + * simply skip over to the next bucket. Saves ftraced + * some processor cycles (ftrace does its bid for + * global warming :-p ). */ + if (p->flags & (FTRACE_FL_CONVERTED)) + break; + + /* Ignore updates to this record's mcount site. + * Reintroduce this record at the head of this + * bucket to attempt to "convert" it again if + * the kprobe on it is unregistered before the + * next run. */ + if (get_kprobe((void *)p->ip)) { + ftrace_del_hash(p); + INIT_HLIST_NODE(&p->node); + hlist_add_head(&p->node, &temp_list); + freeze_record(p); + continue; + } else { + unfreeze_record(p); + } + + /* convert record (i.e, patch mcount-call with NOP) */ + if (ftrace_code_disable(p)) { + p->flags |= FTRACE_FL_CONVERTED; + ftrace_update_cnt++; + } else { + if ((system_state == SYSTEM_BOOTING) || + !core_kernel_text(p->ip)) { + ftrace_del_hash(p); + ftrace_free_rec(p); + } + } + } + + hlist_for_each_entry_safe(p, t, n, &temp_list, node) { + hlist_del(&p->node); + INIT_HLIST_NODE(&p->node); + hlist_add_head(&p->node, head); + } + } + + stop = ftrace_now(raw_smp_processor_id()); + ftrace_update_time = stop - start; + ftrace_update_tot_cnt += ftrace_update_cnt; + ftraced_trigger = 0; + + ftrace_enabled = save_ftrace_enabled; + ftrace_record_suspend--; + + return 0; +} + +static int ftrace_update_code(void) +{ + if (unlikely(ftrace_disabled) || + !ftrace_enabled || !ftraced_trigger) + return 0; + + stop_machine_run(__ftrace_update_code, NULL, NR_CPUS); + + return 1; +} + +static int ftraced(void *ignore) +{ + unsigned long usecs; + + while (!kthread_should_stop()) { + + set_current_state(TASK_INTERRUPTIBLE); + + /* check once a second */ + schedule_timeout(HZ); + + if (unlikely(ftrace_disabled)) + continue; + + mutex_lock(&ftrace_sysctl_lock); + mutex_lock(&ftraced_lock); + if (!ftraced_suspend && !ftraced_stop && + ftrace_update_code()) { + usecs = nsecs_to_usecs(ftrace_update_time); + if (ftrace_update_tot_cnt > 100000) { + ftrace_update_tot_cnt = 0; + pr_info("hm, dftrace overflow: %lu change%s" + " (%lu total) in %lu usec%s\n", + ftrace_update_cnt, + ftrace_update_cnt != 1 ? "s" : "", + ftrace_update_tot_cnt, + usecs, usecs != 1 ? "s" : ""); + ftrace_disabled = 1; + WARN_ON_ONCE(1); + } + } + mutex_unlock(&ftraced_lock); + mutex_unlock(&ftrace_sysctl_lock); + + ftrace_shutdown_replenish(); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +static int __init ftrace_dyn_table_alloc(void) +{ + struct ftrace_page *pg; + int cnt; + int i; + + /* allocate a few pages */ + ftrace_pages_start = (void *)get_zeroed_page(GFP_KERNEL); + if (!ftrace_pages_start) + return -1; + + /* + * Allocate a few more pages. + * + * TODO: have some parser search vmlinux before + * final linking to find all calls to ftrace. + * Then we can: + * a) know how many pages to allocate. + * and/or + * b) set up the table then. + * + * The dynamic code is still necessary for + * modules. + */ + + pg = ftrace_pages = ftrace_pages_start; + + cnt = NR_TO_INIT / ENTRIES_PER_PAGE; + + for (i = 0; i < cnt; i++) { + pg->next = (void *)get_zeroed_page(GFP_KERNEL); + + /* If we fail, we'll try later anyway */ + if (!pg->next) + break; + + pg = pg->next; + } + + return 0; +} + +enum { + FTRACE_ITER_FILTER = (1 << 0), + FTRACE_ITER_CONT = (1 << 1), + FTRACE_ITER_NOTRACE = (1 << 2), + FTRACE_ITER_FAILURES = (1 << 3), +}; + +#define FTRACE_BUFF_MAX (KSYM_SYMBOL_LEN+4) /* room for wildcards */ + +struct ftrace_iterator { + loff_t pos; + struct ftrace_page *pg; + unsigned idx; + unsigned flags; + unsigned char buffer[FTRACE_BUFF_MAX+1]; + unsigned buffer_idx; + unsigned filtered; +}; + +static void * +t_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct ftrace_iterator *iter = m->private; + struct dyn_ftrace *rec = NULL; + + (*pos)++; + + retry: + if (iter->idx >= iter->pg->index) { + if (iter->pg->next) { + iter->pg = iter->pg->next; + iter->idx = 0; + goto retry; + } + } else { + rec = &iter->pg->records[iter->idx++]; + if ((!(iter->flags & FTRACE_ITER_FAILURES) && + (rec->flags & FTRACE_FL_FAILED)) || + + ((iter->flags & FTRACE_ITER_FAILURES) && + (!(rec->flags & FTRACE_FL_FAILED) || + (rec->flags & FTRACE_FL_FREE))) || + + ((iter->flags & FTRACE_ITER_FILTER) && + !(rec->flags & FTRACE_FL_FILTER)) || + + ((iter->flags & FTRACE_ITER_NOTRACE) && + !(rec->flags & FTRACE_FL_NOTRACE))) { + rec = NULL; + goto retry; + } + } + + iter->pos = *pos; + + return rec; +} + +static void *t_start(struct seq_file *m, loff_t *pos) +{ + struct ftrace_iterator *iter = m->private; + void *p = NULL; + loff_t l = -1; + + if (*pos != iter->pos) { + for (p = t_next(m, p, &l); p && l < *pos; p = t_next(m, p, &l)) + ; + } else { + l = *pos; + p = t_next(m, p, &l); + } + + return p; +} + +static void t_stop(struct seq_file *m, void *p) +{ +} + +static int t_show(struct seq_file *m, void *v) +{ + struct dyn_ftrace *rec = v; + char str[KSYM_SYMBOL_LEN]; + + if (!rec) + return 0; + + kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); + + seq_printf(m, "%s\n", str); + + return 0; +} + +static struct seq_operations show_ftrace_seq_ops = { + .start = t_start, + .next = t_next, + .stop = t_stop, + .show = t_show, +}; + +static int +ftrace_avail_open(struct inode *inode, struct file *file) +{ + struct ftrace_iterator *iter; + int ret; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + iter->pg = ftrace_pages_start; + iter->pos = -1; + + ret = seq_open(file, &show_ftrace_seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + + m->private = iter; + } else { + kfree(iter); + } + + return ret; +} + +int ftrace_avail_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = (struct seq_file *)file->private_data; + struct ftrace_iterator *iter = m->private; + + seq_release(inode, file); + kfree(iter); + + return 0; +} + +static int +ftrace_failures_open(struct inode *inode, struct file *file) +{ + int ret; + struct seq_file *m; + struct ftrace_iterator *iter; + + ret = ftrace_avail_open(inode, file); + if (!ret) { + m = (struct seq_file *)file->private_data; + iter = (struct ftrace_iterator *)m->private; + iter->flags = FTRACE_ITER_FAILURES; + } + + return ret; +} + + +static void ftrace_filter_reset(int enable) +{ + struct ftrace_page *pg; + struct dyn_ftrace *rec; + unsigned long type = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; + unsigned i; + + /* keep kstop machine from running */ + preempt_disable(); + if (enable) + ftrace_filtered = 0; + pg = ftrace_pages_start; + while (pg) { + for (i = 0; i < pg->index; i++) { + rec = &pg->records[i]; + if (rec->flags & FTRACE_FL_FAILED) + continue; + rec->flags &= ~type; + } + pg = pg->next; + } + preempt_enable(); +} + +static int +ftrace_regex_open(struct inode *inode, struct file *file, int enable) +{ + struct ftrace_iterator *iter; + int ret = 0; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + mutex_lock(&ftrace_regex_lock); + if ((file->f_mode & FMODE_WRITE) && + !(file->f_flags & O_APPEND)) + ftrace_filter_reset(enable); + + if (file->f_mode & FMODE_READ) { + iter->pg = ftrace_pages_start; + iter->pos = -1; + iter->flags = enable ? FTRACE_ITER_FILTER : + FTRACE_ITER_NOTRACE; + + ret = seq_open(file, &show_ftrace_seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = iter; + } else + kfree(iter); + } else + file->private_data = iter; + mutex_unlock(&ftrace_regex_lock); + + return ret; +} + +static int +ftrace_filter_open(struct inode *inode, struct file *file) +{ + return ftrace_regex_open(inode, file, 1); +} + +static int +ftrace_notrace_open(struct inode *inode, struct file *file) +{ + return ftrace_regex_open(inode, file, 0); +} + +static ssize_t +ftrace_regex_read(struct file *file, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + if (file->f_mode & FMODE_READ) + return seq_read(file, ubuf, cnt, ppos); + else + return -EPERM; +} + +static loff_t +ftrace_regex_lseek(struct file *file, loff_t offset, int origin) +{ + loff_t ret; + + if (file->f_mode & FMODE_READ) + ret = seq_lseek(file, offset, origin); + else + file->f_pos = ret = 1; + + return ret; +} + +enum { + MATCH_FULL, + MATCH_FRONT_ONLY, + MATCH_MIDDLE_ONLY, + MATCH_END_ONLY, +}; + +static void +ftrace_match(unsigned char *buff, int len, int enable) +{ + char str[KSYM_SYMBOL_LEN]; + char *search = NULL; + struct ftrace_page *pg; + struct dyn_ftrace *rec; + int type = MATCH_FULL; + unsigned long flag = enable ? FTRACE_FL_FILTER : FTRACE_FL_NOTRACE; + unsigned i, match = 0, search_len = 0; + + for (i = 0; i < len; i++) { + if (buff[i] == '*') { + if (!i) { + search = buff + i + 1; + type = MATCH_END_ONLY; + search_len = len - (i + 1); + } else { + if (type == MATCH_END_ONLY) { + type = MATCH_MIDDLE_ONLY; + } else { + match = i; + type = MATCH_FRONT_ONLY; + } + buff[i] = 0; + break; + } + } + } + + /* keep kstop machine from running */ + preempt_disable(); + if (enable) + ftrace_filtered = 1; + pg = ftrace_pages_start; + while (pg) { + for (i = 0; i < pg->index; i++) { + int matched = 0; + char *ptr; + + rec = &pg->records[i]; + if (rec->flags & FTRACE_FL_FAILED) + continue; + kallsyms_lookup(rec->ip, NULL, NULL, NULL, str); + switch (type) { + case MATCH_FULL: + if (strcmp(str, buff) == 0) + matched = 1; + break; + case MATCH_FRONT_ONLY: + if (memcmp(str, buff, match) == 0) + matched = 1; + break; + case MATCH_MIDDLE_ONLY: + if (strstr(str, search)) + matched = 1; + break; + case MATCH_END_ONLY: + ptr = strstr(str, search); + if (ptr && (ptr[search_len] == 0)) + matched = 1; + break; + } + if (matched) + rec->flags |= flag; + } + pg = pg->next; + } + preempt_enable(); +} + +static ssize_t +ftrace_regex_write(struct file *file, const char __user *ubuf, + size_t cnt, loff_t *ppos, int enable) +{ + struct ftrace_iterator *iter; + char ch; + size_t read = 0; + ssize_t ret; + + if (!cnt || cnt < 0) + return 0; + + mutex_lock(&ftrace_regex_lock); + + if (file->f_mode & FMODE_READ) { + struct seq_file *m = file->private_data; + iter = m->private; + } else + iter = file->private_data; + + if (!*ppos) { + iter->flags &= ~FTRACE_ITER_CONT; + iter->buffer_idx = 0; + } + + ret = get_user(ch, ubuf++); + if (ret) + goto out; + read++; + cnt--; + + if (!(iter->flags & ~FTRACE_ITER_CONT)) { + /* skip white space */ + while (cnt && isspace(ch)) { + ret = get_user(ch, ubuf++); + if (ret) + goto out; + read++; + cnt--; + } + + if (isspace(ch)) { + file->f_pos += read; + ret = read; + goto out; + } + + iter->buffer_idx = 0; + } + + while (cnt && !isspace(ch)) { + if (iter->buffer_idx < FTRACE_BUFF_MAX) + iter->buffer[iter->buffer_idx++] = ch; + else { + ret = -EINVAL; + goto out; + } + ret = get_user(ch, ubuf++); + if (ret) + goto out; + read++; + cnt--; + } + + if (isspace(ch)) { + iter->filtered++; + iter->buffer[iter->buffer_idx] = 0; + ftrace_match(iter->buffer, iter->buffer_idx, enable); + iter->buffer_idx = 0; + } else + iter->flags |= FTRACE_ITER_CONT; + + + file->f_pos += read; + + ret = read; + out: + mutex_unlock(&ftrace_regex_lock); + + return ret; +} + +static ssize_t +ftrace_filter_write(struct file *file, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return ftrace_regex_write(file, ubuf, cnt, ppos, 1); +} + +static ssize_t +ftrace_notrace_write(struct file *file, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return ftrace_regex_write(file, ubuf, cnt, ppos, 0); +} + +static void +ftrace_set_regex(unsigned char *buf, int len, int reset, int enable) +{ + if (unlikely(ftrace_disabled)) + return; + + mutex_lock(&ftrace_regex_lock); + if (reset) + ftrace_filter_reset(enable); + if (buf) + ftrace_match(buf, len, enable); + mutex_unlock(&ftrace_regex_lock); +} + +/** + * ftrace_set_filter - set a function to filter on in ftrace + * @buf - the string that holds the function filter text. + * @len - the length of the string. + * @reset - non zero to reset all filters before applying this filter. + * + * Filters denote which functions should be enabled when tracing is enabled. + * If @buf is NULL and reset is set, all functions will be enabled for tracing. + */ +void ftrace_set_filter(unsigned char *buf, int len, int reset) +{ + ftrace_set_regex(buf, len, reset, 1); +} + +/** + * ftrace_set_notrace - set a function to not trace in ftrace + * @buf - the string that holds the function notrace text. + * @len - the length of the string. + * @reset - non zero to reset all filters before applying this filter. + * + * Notrace Filters denote which functions should not be enabled when tracing + * is enabled. If @buf is NULL and reset is set, all functions will be enabled + * for tracing. + */ +void ftrace_set_notrace(unsigned char *buf, int len, int reset) +{ + ftrace_set_regex(buf, len, reset, 0); +} + +static int +ftrace_regex_release(struct inode *inode, struct file *file, int enable) +{ + struct seq_file *m = (struct seq_file *)file->private_data; + struct ftrace_iterator *iter; + + mutex_lock(&ftrace_regex_lock); + if (file->f_mode & FMODE_READ) { + iter = m->private; + + seq_release(inode, file); + } else + iter = file->private_data; + + if (iter->buffer_idx) { + iter->filtered++; + iter->buffer[iter->buffer_idx] = 0; + ftrace_match(iter->buffer, iter->buffer_idx, enable); + } + + mutex_lock(&ftrace_sysctl_lock); + mutex_lock(&ftraced_lock); + if (iter->filtered && ftraced_suspend && ftrace_enabled) + ftrace_run_update_code(FTRACE_ENABLE_CALLS); + mutex_unlock(&ftraced_lock); + mutex_unlock(&ftrace_sysctl_lock); + + kfree(iter); + mutex_unlock(&ftrace_regex_lock); + return 0; +} + +static int +ftrace_filter_release(struct inode *inode, struct file *file) +{ + return ftrace_regex_release(inode, file, 1); +} + +static int +ftrace_notrace_release(struct inode *inode, struct file *file) +{ + return ftrace_regex_release(inode, file, 0); +} + +static ssize_t +ftraced_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + /* don't worry about races */ + char *buf = ftraced_stop ? "disabled\n" : "enabled\n"; + int r = strlen(buf); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +ftraced_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + long val; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + if (strncmp(buf, "enable", 6) == 0) + val = 1; + else if (strncmp(buf, "disable", 7) == 0) + val = 0; + else { + buf[cnt] = 0; + + ret = strict_strtoul(buf, 10, &val); + if (ret < 0) + return ret; + + val = !!val; + } + + if (val) + ftrace_enable_daemon(); + else + ftrace_disable_daemon(); + + filp->f_pos += cnt; + + return cnt; +} + +static struct file_operations ftrace_avail_fops = { + .open = ftrace_avail_open, + .read = seq_read, + .llseek = seq_lseek, + .release = ftrace_avail_release, +}; + +static struct file_operations ftrace_failures_fops = { + .open = ftrace_failures_open, + .read = seq_read, + .llseek = seq_lseek, + .release = ftrace_avail_release, +}; + +static struct file_operations ftrace_filter_fops = { + .open = ftrace_filter_open, + .read = ftrace_regex_read, + .write = ftrace_filter_write, + .llseek = ftrace_regex_lseek, + .release = ftrace_filter_release, +}; + +static struct file_operations ftrace_notrace_fops = { + .open = ftrace_notrace_open, + .read = ftrace_regex_read, + .write = ftrace_notrace_write, + .llseek = ftrace_regex_lseek, + .release = ftrace_notrace_release, +}; + +static struct file_operations ftraced_fops = { + .open = tracing_open_generic, + .read = ftraced_read, + .write = ftraced_write, +}; + +/** + * ftrace_force_update - force an update to all recording ftrace functions + */ +int ftrace_force_update(void) +{ + int ret = 0; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + mutex_lock(&ftrace_sysctl_lock); + mutex_lock(&ftraced_lock); + + /* + * If ftraced_trigger is not set, then there is nothing + * to update. + */ + if (ftraced_trigger && !ftrace_update_code()) + ret = -EBUSY; + + mutex_unlock(&ftraced_lock); + mutex_unlock(&ftrace_sysctl_lock); + + return ret; +} + +static void ftrace_force_shutdown(void) +{ + struct task_struct *task; + int command = FTRACE_DISABLE_CALLS | FTRACE_UPDATE_TRACE_FUNC; + + mutex_lock(&ftraced_lock); + task = ftraced_task; + ftraced_task = NULL; + ftraced_suspend = -1; + ftrace_run_update_code(command); + mutex_unlock(&ftraced_lock); + + if (task) + kthread_stop(task); +} + +static __init int ftrace_init_debugfs(void) +{ + struct dentry *d_tracer; + struct dentry *entry; + + d_tracer = tracing_init_dentry(); + + entry = debugfs_create_file("available_filter_functions", 0444, + d_tracer, NULL, &ftrace_avail_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'available_filter_functions' entry\n"); + + entry = debugfs_create_file("failures", 0444, + d_tracer, NULL, &ftrace_failures_fops); + if (!entry) + pr_warning("Could not create debugfs 'failures' entry\n"); + + entry = debugfs_create_file("set_ftrace_filter", 0644, d_tracer, + NULL, &ftrace_filter_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'set_ftrace_filter' entry\n"); + + entry = debugfs_create_file("set_ftrace_notrace", 0644, d_tracer, + NULL, &ftrace_notrace_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'set_ftrace_notrace' entry\n"); + + entry = debugfs_create_file("ftraced_enabled", 0644, d_tracer, + NULL, &ftraced_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'ftraced_enabled' entry\n"); + return 0; +} + +fs_initcall(ftrace_init_debugfs); + +static int __init ftrace_dynamic_init(void) +{ + struct task_struct *p; + unsigned long addr; + int ret; + + addr = (unsigned long)ftrace_record_ip; + + stop_machine_run(ftrace_dyn_arch_init, &addr, NR_CPUS); + + /* ftrace_dyn_arch_init places the return code in addr */ + if (addr) { + ret = (int)addr; + goto failed; + } + + ret = ftrace_dyn_table_alloc(); + if (ret) + goto failed; + + p = kthread_run(ftraced, NULL, "ftraced"); + if (IS_ERR(p)) { + ret = -1; + goto failed; + } + + last_ftrace_enabled = ftrace_enabled = 1; + ftraced_task = p; + + return 0; + + failed: + ftrace_disabled = 1; + return ret; +} + +core_initcall(ftrace_dynamic_init); +#else +# define ftrace_startup() do { } while (0) +# define ftrace_shutdown() do { } while (0) +# define ftrace_startup_sysctl() do { } while (0) +# define ftrace_shutdown_sysctl() do { } while (0) +# define ftrace_force_shutdown() do { } while (0) +#endif /* CONFIG_DYNAMIC_FTRACE */ + +/** + * ftrace_kill_atomic - kill ftrace from critical sections + * + * This function should be used by panic code. It stops ftrace + * but in a not so nice way. If you need to simply kill ftrace + * from a non-atomic section, use ftrace_kill. + */ +void ftrace_kill_atomic(void) +{ + ftrace_disabled = 1; + ftrace_enabled = 0; +#ifdef CONFIG_DYNAMIC_FTRACE + ftraced_suspend = -1; +#endif + clear_ftrace_function(); +} + +/** + * ftrace_kill - totally shutdown ftrace + * + * This is a safety measure. If something was detected that seems + * wrong, calling this function will keep ftrace from doing + * any more modifications, and updates. + * used when something went wrong. + */ +void ftrace_kill(void) +{ + mutex_lock(&ftrace_sysctl_lock); + ftrace_disabled = 1; + ftrace_enabled = 0; + + clear_ftrace_function(); + mutex_unlock(&ftrace_sysctl_lock); + + /* Try to totally disable ftrace */ + ftrace_force_shutdown(); +} + +/** + * register_ftrace_function - register a function for profiling + * @ops - ops structure that holds the function for profiling. + * + * Register a function to be called by all functions in the + * kernel. + * + * Note: @ops->func and all the functions it calls must be labeled + * with "notrace", otherwise it will go into a + * recursive loop. + */ +int register_ftrace_function(struct ftrace_ops *ops) +{ + int ret; + + if (unlikely(ftrace_disabled)) + return -1; + + mutex_lock(&ftrace_sysctl_lock); + ret = __register_ftrace_function(ops); + ftrace_startup(); + mutex_unlock(&ftrace_sysctl_lock); + + return ret; +} + +/** + * unregister_ftrace_function - unresgister a function for profiling. + * @ops - ops structure that holds the function to unregister + * + * Unregister a function that was added to be called by ftrace profiling. + */ +int unregister_ftrace_function(struct ftrace_ops *ops) +{ + int ret; + + mutex_lock(&ftrace_sysctl_lock); + ret = __unregister_ftrace_function(ops); + ftrace_shutdown(); + mutex_unlock(&ftrace_sysctl_lock); + + return ret; +} + +int +ftrace_enable_sysctl(struct ctl_table *table, int write, + struct file *file, void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + + if (unlikely(ftrace_disabled)) + return -ENODEV; + + mutex_lock(&ftrace_sysctl_lock); + + ret = proc_dointvec(table, write, file, buffer, lenp, ppos); + + if (ret || !write || (last_ftrace_enabled == ftrace_enabled)) + goto out; + + last_ftrace_enabled = ftrace_enabled; + + if (ftrace_enabled) { + + ftrace_startup_sysctl(); + + /* we are starting ftrace again */ + if (ftrace_list != &ftrace_list_end) { + if (ftrace_list->next == &ftrace_list_end) + ftrace_trace_function = ftrace_list->func; + else + ftrace_trace_function = ftrace_list_func; + } + + } else { + /* stopping ftrace calls (just send to ftrace_stub) */ + ftrace_trace_function = ftrace_stub; + + ftrace_shutdown_sysctl(); + } + + out: + mutex_unlock(&ftrace_sysctl_lock); + return ret; +} diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c new file mode 100644 index 00000000000..868e121c8e3 --- /dev/null +++ b/kernel/trace/trace.c @@ -0,0 +1,3161 @@ +/* + * ring buffer based function tracer + * + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> + * + * Originally taken from the RT patch by: + * Arnaldo Carvalho de Melo <acme@redhat.com> + * + * Based on code from the latency_tracer, that is: + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 William Lee Irwin III + */ +#include <linux/utsrelease.h> +#include <linux/kallsyms.h> +#include <linux/seq_file.h> +#include <linux/debugfs.h> +#include <linux/pagemap.h> +#include <linux/hardirq.h> +#include <linux/linkage.h> +#include <linux/uaccess.h> +#include <linux/ftrace.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/ctype.h> +#include <linux/init.h> +#include <linux/poll.h> +#include <linux/gfp.h> +#include <linux/fs.h> +#include <linux/kprobes.h> +#include <linux/writeback.h> + +#include <linux/stacktrace.h> + +#include "trace.h" + +unsigned long __read_mostly tracing_max_latency = (cycle_t)ULONG_MAX; +unsigned long __read_mostly tracing_thresh; + +static unsigned long __read_mostly tracing_nr_buffers; +static cpumask_t __read_mostly tracing_buffer_mask; + +#define for_each_tracing_cpu(cpu) \ + for_each_cpu_mask(cpu, tracing_buffer_mask) + +static int trace_alloc_page(void); +static int trace_free_page(void); + +static int tracing_disabled = 1; + +static unsigned long tracing_pages_allocated; + +long +ns2usecs(cycle_t nsec) +{ + nsec += 500; + do_div(nsec, 1000); + return nsec; +} + +cycle_t ftrace_now(int cpu) +{ + return cpu_clock(cpu); +} + +/* + * The global_trace is the descriptor that holds the tracing + * buffers for the live tracing. For each CPU, it contains + * a link list of pages that will store trace entries. The + * page descriptor of the pages in the memory is used to hold + * the link list by linking the lru item in the page descriptor + * to each of the pages in the buffer per CPU. + * + * For each active CPU there is a data field that holds the + * pages for the buffer for that CPU. Each CPU has the same number + * of pages allocated for its buffer. + */ +static struct trace_array global_trace; + +static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu); + +/* + * The max_tr is used to snapshot the global_trace when a maximum + * latency is reached. Some tracers will use this to store a maximum + * trace while it continues examining live traces. + * + * The buffers for the max_tr are set up the same as the global_trace. + * When a snapshot is taken, the link list of the max_tr is swapped + * with the link list of the global_trace and the buffers are reset for + * the global_trace so the tracing can continue. + */ +static struct trace_array max_tr; + +static DEFINE_PER_CPU(struct trace_array_cpu, max_data); + +/* tracer_enabled is used to toggle activation of a tracer */ +static int tracer_enabled = 1; + +/* function tracing enabled */ +int ftrace_function_enabled; + +/* + * trace_nr_entries is the number of entries that is allocated + * for a buffer. Note, the number of entries is always rounded + * to ENTRIES_PER_PAGE. + */ +static unsigned long trace_nr_entries = 65536UL; + +/* trace_types holds a link list of available tracers. */ +static struct tracer *trace_types __read_mostly; + +/* current_trace points to the tracer that is currently active */ +static struct tracer *current_trace __read_mostly; + +/* + * max_tracer_type_len is used to simplify the allocating of + * buffers to read userspace tracer names. We keep track of + * the longest tracer name registered. + */ +static int max_tracer_type_len; + +/* + * trace_types_lock is used to protect the trace_types list. + * This lock is also used to keep user access serialized. + * Accesses from userspace will grab this lock while userspace + * activities happen inside the kernel. + */ +static DEFINE_MUTEX(trace_types_lock); + +/* trace_wait is a waitqueue for tasks blocked on trace_poll */ +static DECLARE_WAIT_QUEUE_HEAD(trace_wait); + +/* trace_flags holds iter_ctrl options */ +unsigned long trace_flags = TRACE_ITER_PRINT_PARENT; + +static notrace void no_trace_init(struct trace_array *tr) +{ + int cpu; + + ftrace_function_enabled = 0; + if(tr->ctrl) + for_each_online_cpu(cpu) + tracing_reset(tr->data[cpu]); + tracer_enabled = 0; +} + +/* dummy trace to disable tracing */ +static struct tracer no_tracer __read_mostly = { + .name = "none", + .init = no_trace_init +}; + + +/** + * trace_wake_up - wake up tasks waiting for trace input + * + * Simply wakes up any task that is blocked on the trace_wait + * queue. These is used with trace_poll for tasks polling the trace. + */ +void trace_wake_up(void) +{ + /* + * The runqueue_is_locked() can fail, but this is the best we + * have for now: + */ + if (!(trace_flags & TRACE_ITER_BLOCK) && !runqueue_is_locked()) + wake_up(&trace_wait); +} + +#define ENTRIES_PER_PAGE (PAGE_SIZE / sizeof(struct trace_entry)) + +static int __init set_nr_entries(char *str) +{ + unsigned long nr_entries; + int ret; + + if (!str) + return 0; + ret = strict_strtoul(str, 0, &nr_entries); + /* nr_entries can not be zero */ + if (ret < 0 || nr_entries == 0) + return 0; + trace_nr_entries = nr_entries; + return 1; +} +__setup("trace_entries=", set_nr_entries); + +unsigned long nsecs_to_usecs(unsigned long nsecs) +{ + return nsecs / 1000; +} + +/* + * trace_flag_type is an enumeration that holds different + * states when a trace occurs. These are: + * IRQS_OFF - interrupts were disabled + * NEED_RESCED - reschedule is requested + * HARDIRQ - inside an interrupt handler + * SOFTIRQ - inside a softirq handler + */ +enum trace_flag_type { + TRACE_FLAG_IRQS_OFF = 0x01, + TRACE_FLAG_NEED_RESCHED = 0x02, + TRACE_FLAG_HARDIRQ = 0x04, + TRACE_FLAG_SOFTIRQ = 0x08, +}; + +/* + * TRACE_ITER_SYM_MASK masks the options in trace_flags that + * control the output of kernel symbols. + */ +#define TRACE_ITER_SYM_MASK \ + (TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR) + +/* These must match the bit postions in trace_iterator_flags */ +static const char *trace_options[] = { + "print-parent", + "sym-offset", + "sym-addr", + "verbose", + "raw", + "hex", + "bin", + "block", + "stacktrace", + "sched-tree", + NULL +}; + +/* + * ftrace_max_lock is used to protect the swapping of buffers + * when taking a max snapshot. The buffers themselves are + * protected by per_cpu spinlocks. But the action of the swap + * needs its own lock. + * + * This is defined as a raw_spinlock_t in order to help + * with performance when lockdep debugging is enabled. + */ +static raw_spinlock_t ftrace_max_lock = + (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; + +/* + * Copy the new maximum trace into the separate maximum-trace + * structure. (this way the maximum trace is permanently saved, + * for later retrieval via /debugfs/tracing/latency_trace) + */ +static void +__update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) +{ + struct trace_array_cpu *data = tr->data[cpu]; + + max_tr.cpu = cpu; + max_tr.time_start = data->preempt_timestamp; + + data = max_tr.data[cpu]; + data->saved_latency = tracing_max_latency; + + memcpy(data->comm, tsk->comm, TASK_COMM_LEN); + data->pid = tsk->pid; + data->uid = tsk->uid; + data->nice = tsk->static_prio - 20 - MAX_RT_PRIO; + data->policy = tsk->policy; + data->rt_priority = tsk->rt_priority; + + /* record this tasks comm */ + tracing_record_cmdline(current); +} + +#define CHECK_COND(cond) \ + if (unlikely(cond)) { \ + tracing_disabled = 1; \ + WARN_ON(1); \ + return -1; \ + } + +/** + * check_pages - integrity check of trace buffers + * + * As a safty measure we check to make sure the data pages have not + * been corrupted. + */ +int check_pages(struct trace_array_cpu *data) +{ + struct page *page, *tmp; + + CHECK_COND(data->trace_pages.next->prev != &data->trace_pages); + CHECK_COND(data->trace_pages.prev->next != &data->trace_pages); + + list_for_each_entry_safe(page, tmp, &data->trace_pages, lru) { + CHECK_COND(page->lru.next->prev != &page->lru); + CHECK_COND(page->lru.prev->next != &page->lru); + } + + return 0; +} + +/** + * head_page - page address of the first page in per_cpu buffer. + * + * head_page returns the page address of the first page in + * a per_cpu buffer. This also preforms various consistency + * checks to make sure the buffer has not been corrupted. + */ +void *head_page(struct trace_array_cpu *data) +{ + struct page *page; + + if (list_empty(&data->trace_pages)) + return NULL; + + page = list_entry(data->trace_pages.next, struct page, lru); + BUG_ON(&page->lru == &data->trace_pages); + + return page_address(page); +} + +/** + * trace_seq_printf - sequence printing of trace information + * @s: trace sequence descriptor + * @fmt: printf format string + * + * The tracer may use either sequence operations or its own + * copy to user routines. To simplify formating of a trace + * trace_seq_printf is used to store strings into a special + * buffer (@s). Then the output may be either used by + * the sequencer or pulled into another buffer. + */ +int +trace_seq_printf(struct trace_seq *s, const char *fmt, ...) +{ + int len = (PAGE_SIZE - 1) - s->len; + va_list ap; + int ret; + + if (!len) + return 0; + + va_start(ap, fmt); + ret = vsnprintf(s->buffer + s->len, len, fmt, ap); + va_end(ap); + + /* If we can't write it all, don't bother writing anything */ + if (ret >= len) + return 0; + + s->len += ret; + + return len; +} + +/** + * trace_seq_puts - trace sequence printing of simple string + * @s: trace sequence descriptor + * @str: simple string to record + * + * The tracer may use either the sequence operations or its own + * copy to user routines. This function records a simple string + * into a special buffer (@s) for later retrieval by a sequencer + * or other mechanism. + */ +static int +trace_seq_puts(struct trace_seq *s, const char *str) +{ + int len = strlen(str); + + if (len > ((PAGE_SIZE - 1) - s->len)) + return 0; + + memcpy(s->buffer + s->len, str, len); + s->len += len; + + return len; +} + +static int +trace_seq_putc(struct trace_seq *s, unsigned char c) +{ + if (s->len >= (PAGE_SIZE - 1)) + return 0; + + s->buffer[s->len++] = c; + + return 1; +} + +static int +trace_seq_putmem(struct trace_seq *s, void *mem, size_t len) +{ + if (len > ((PAGE_SIZE - 1) - s->len)) + return 0; + + memcpy(s->buffer + s->len, mem, len); + s->len += len; + + return len; +} + +#define HEX_CHARS 17 +static const char hex2asc[] = "0123456789abcdef"; + +static int +trace_seq_putmem_hex(struct trace_seq *s, void *mem, size_t len) +{ + unsigned char hex[HEX_CHARS]; + unsigned char *data = mem; + unsigned char byte; + int i, j; + + BUG_ON(len >= HEX_CHARS); + +#ifdef __BIG_ENDIAN + for (i = 0, j = 0; i < len; i++) { +#else + for (i = len-1, j = 0; i >= 0; i--) { +#endif + byte = data[i]; + + hex[j++] = hex2asc[byte & 0x0f]; + hex[j++] = hex2asc[byte >> 4]; + } + hex[j++] = ' '; + + return trace_seq_putmem(s, hex, j); +} + +static void +trace_seq_reset(struct trace_seq *s) +{ + s->len = 0; + s->readpos = 0; +} + +ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt) +{ + int len; + int ret; + + if (s->len <= s->readpos) + return -EBUSY; + + len = s->len - s->readpos; + if (cnt > len) + cnt = len; + ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt); + if (ret) + return -EFAULT; + + s->readpos += len; + return cnt; +} + +static void +trace_print_seq(struct seq_file *m, struct trace_seq *s) +{ + int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len; + + s->buffer[len] = 0; + seq_puts(m, s->buffer); + + trace_seq_reset(s); +} + +/* + * flip the trace buffers between two trace descriptors. + * This usually is the buffers between the global_trace and + * the max_tr to record a snapshot of a current trace. + * + * The ftrace_max_lock must be held. + */ +static void +flip_trace(struct trace_array_cpu *tr1, struct trace_array_cpu *tr2) +{ + struct list_head flip_pages; + + INIT_LIST_HEAD(&flip_pages); + + memcpy(&tr1->trace_head_idx, &tr2->trace_head_idx, + sizeof(struct trace_array_cpu) - + offsetof(struct trace_array_cpu, trace_head_idx)); + + check_pages(tr1); + check_pages(tr2); + list_splice_init(&tr1->trace_pages, &flip_pages); + list_splice_init(&tr2->trace_pages, &tr1->trace_pages); + list_splice_init(&flip_pages, &tr2->trace_pages); + BUG_ON(!list_empty(&flip_pages)); + check_pages(tr1); + check_pages(tr2); +} + +/** + * update_max_tr - snapshot all trace buffers from global_trace to max_tr + * @tr: tracer + * @tsk: the task with the latency + * @cpu: The cpu that initiated the trace. + * + * Flip the buffers between the @tr and the max_tr and record information + * about which task was the cause of this latency. + */ +void +update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) +{ + struct trace_array_cpu *data; + int i; + + WARN_ON_ONCE(!irqs_disabled()); + __raw_spin_lock(&ftrace_max_lock); + /* clear out all the previous traces */ + for_each_tracing_cpu(i) { + data = tr->data[i]; + flip_trace(max_tr.data[i], data); + tracing_reset(data); + } + + __update_max_tr(tr, tsk, cpu); + __raw_spin_unlock(&ftrace_max_lock); +} + +/** + * update_max_tr_single - only copy one trace over, and reset the rest + * @tr - tracer + * @tsk - task with the latency + * @cpu - the cpu of the buffer to copy. + * + * Flip the trace of a single CPU buffer between the @tr and the max_tr. + */ +void +update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) +{ + struct trace_array_cpu *data = tr->data[cpu]; + int i; + + WARN_ON_ONCE(!irqs_disabled()); + __raw_spin_lock(&ftrace_max_lock); + for_each_tracing_cpu(i) + tracing_reset(max_tr.data[i]); + + flip_trace(max_tr.data[cpu], data); + tracing_reset(data); + + __update_max_tr(tr, tsk, cpu); + __raw_spin_unlock(&ftrace_max_lock); +} + +/** + * register_tracer - register a tracer with the ftrace system. + * @type - the plugin for the tracer + * + * Register a new plugin tracer. + */ +int register_tracer(struct tracer *type) +{ + struct tracer *t; + int len; + int ret = 0; + + if (!type->name) { + pr_info("Tracer must have a name\n"); + return -1; + } + + mutex_lock(&trace_types_lock); + for (t = trace_types; t; t = t->next) { + if (strcmp(type->name, t->name) == 0) { + /* already found */ + pr_info("Trace %s already registered\n", + type->name); + ret = -1; + goto out; + } + } + +#ifdef CONFIG_FTRACE_STARTUP_TEST + if (type->selftest) { + struct tracer *saved_tracer = current_trace; + struct trace_array_cpu *data; + struct trace_array *tr = &global_trace; + int saved_ctrl = tr->ctrl; + int i; + /* + * Run a selftest on this tracer. + * Here we reset the trace buffer, and set the current + * tracer to be this tracer. The tracer can then run some + * internal tracing to verify that everything is in order. + * If we fail, we do not register this tracer. + */ + for_each_tracing_cpu(i) { + data = tr->data[i]; + if (!head_page(data)) + continue; + tracing_reset(data); + } + current_trace = type; + tr->ctrl = 0; + /* the test is responsible for initializing and enabling */ + pr_info("Testing tracer %s: ", type->name); + ret = type->selftest(type, tr); + /* the test is responsible for resetting too */ + current_trace = saved_tracer; + tr->ctrl = saved_ctrl; + if (ret) { + printk(KERN_CONT "FAILED!\n"); + goto out; + } + /* Only reset on passing, to avoid touching corrupted buffers */ + for_each_tracing_cpu(i) { + data = tr->data[i]; + if (!head_page(data)) + continue; + tracing_reset(data); + } + printk(KERN_CONT "PASSED\n"); + } +#endif + + type->next = trace_types; + trace_types = type; + len = strlen(type->name); + if (len > max_tracer_type_len) + max_tracer_type_len = len; + + out: + mutex_unlock(&trace_types_lock); + + return ret; +} + +void unregister_tracer(struct tracer *type) +{ + struct tracer **t; + int len; + + mutex_lock(&trace_types_lock); + for (t = &trace_types; *t; t = &(*t)->next) { + if (*t == type) + goto found; + } + pr_info("Trace %s not registered\n", type->name); + goto out; + + found: + *t = (*t)->next; + if (strlen(type->name) != max_tracer_type_len) + goto out; + + max_tracer_type_len = 0; + for (t = &trace_types; *t; t = &(*t)->next) { + len = strlen((*t)->name); + if (len > max_tracer_type_len) + max_tracer_type_len = len; + } + out: + mutex_unlock(&trace_types_lock); +} + +void tracing_reset(struct trace_array_cpu *data) +{ + data->trace_idx = 0; + data->overrun = 0; + data->trace_head = data->trace_tail = head_page(data); + data->trace_head_idx = 0; + data->trace_tail_idx = 0; +} + +#define SAVED_CMDLINES 128 +static unsigned map_pid_to_cmdline[PID_MAX_DEFAULT+1]; +static unsigned map_cmdline_to_pid[SAVED_CMDLINES]; +static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN]; +static int cmdline_idx; +static DEFINE_SPINLOCK(trace_cmdline_lock); + +/* temporary disable recording */ +atomic_t trace_record_cmdline_disabled __read_mostly; + +static void trace_init_cmdlines(void) +{ + memset(&map_pid_to_cmdline, -1, sizeof(map_pid_to_cmdline)); + memset(&map_cmdline_to_pid, -1, sizeof(map_cmdline_to_pid)); + cmdline_idx = 0; +} + +void trace_stop_cmdline_recording(void); + +static void trace_save_cmdline(struct task_struct *tsk) +{ + unsigned map; + unsigned idx; + + if (!tsk->pid || unlikely(tsk->pid > PID_MAX_DEFAULT)) + return; + + /* + * It's not the end of the world if we don't get + * the lock, but we also don't want to spin + * nor do we want to disable interrupts, + * so if we miss here, then better luck next time. + */ + if (!spin_trylock(&trace_cmdline_lock)) + return; + + idx = map_pid_to_cmdline[tsk->pid]; + if (idx >= SAVED_CMDLINES) { + idx = (cmdline_idx + 1) % SAVED_CMDLINES; + + map = map_cmdline_to_pid[idx]; + if (map <= PID_MAX_DEFAULT) + map_pid_to_cmdline[map] = (unsigned)-1; + + map_pid_to_cmdline[tsk->pid] = idx; + + cmdline_idx = idx; + } + + memcpy(&saved_cmdlines[idx], tsk->comm, TASK_COMM_LEN); + + spin_unlock(&trace_cmdline_lock); +} + +static char *trace_find_cmdline(int pid) +{ + char *cmdline = "<...>"; + unsigned map; + + if (!pid) + return "<idle>"; + + if (pid > PID_MAX_DEFAULT) + goto out; + + map = map_pid_to_cmdline[pid]; + if (map >= SAVED_CMDLINES) + goto out; + + cmdline = saved_cmdlines[map]; + + out: + return cmdline; +} + +void tracing_record_cmdline(struct task_struct *tsk) +{ + if (atomic_read(&trace_record_cmdline_disabled)) + return; + + trace_save_cmdline(tsk); +} + +static inline struct list_head * +trace_next_list(struct trace_array_cpu *data, struct list_head *next) +{ + /* + * Roundrobin - but skip the head (which is not a real page): + */ + next = next->next; + if (unlikely(next == &data->trace_pages)) + next = next->next; + BUG_ON(next == &data->trace_pages); + + return next; +} + +static inline void * +trace_next_page(struct trace_array_cpu *data, void *addr) +{ + struct list_head *next; + struct page *page; + + page = virt_to_page(addr); + + next = trace_next_list(data, &page->lru); + page = list_entry(next, struct page, lru); + + return page_address(page); +} + +static inline struct trace_entry * +tracing_get_trace_entry(struct trace_array *tr, struct trace_array_cpu *data) +{ + unsigned long idx, idx_next; + struct trace_entry *entry; + + data->trace_idx++; + idx = data->trace_head_idx; + idx_next = idx + 1; + + BUG_ON(idx * TRACE_ENTRY_SIZE >= PAGE_SIZE); + + entry = data->trace_head + idx * TRACE_ENTRY_SIZE; + + if (unlikely(idx_next >= ENTRIES_PER_PAGE)) { + data->trace_head = trace_next_page(data, data->trace_head); + idx_next = 0; + } + + if (data->trace_head == data->trace_tail && + idx_next == data->trace_tail_idx) { + /* overrun */ + data->overrun++; + data->trace_tail_idx++; + if (data->trace_tail_idx >= ENTRIES_PER_PAGE) { + data->trace_tail = + trace_next_page(data, data->trace_tail); + data->trace_tail_idx = 0; + } + } + + data->trace_head_idx = idx_next; + + return entry; +} + +static inline void +tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags) +{ + struct task_struct *tsk = current; + unsigned long pc; + + pc = preempt_count(); + + entry->preempt_count = pc & 0xff; + entry->pid = (tsk) ? tsk->pid : 0; + entry->t = ftrace_now(raw_smp_processor_id()); + entry->flags = (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) | + ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | + ((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) | + (need_resched() ? TRACE_FLAG_NEED_RESCHED : 0); +} + +void +trace_function(struct trace_array *tr, struct trace_array_cpu *data, + unsigned long ip, unsigned long parent_ip, unsigned long flags) +{ + struct trace_entry *entry; + unsigned long irq_flags; + + raw_local_irq_save(irq_flags); + __raw_spin_lock(&data->lock); + entry = tracing_get_trace_entry(tr, data); + tracing_generic_entry_update(entry, flags); + entry->type = TRACE_FN; + entry->fn.ip = ip; + entry->fn.parent_ip = parent_ip; + __raw_spin_unlock(&data->lock); + raw_local_irq_restore(irq_flags); +} + +void +ftrace(struct trace_array *tr, struct trace_array_cpu *data, + unsigned long ip, unsigned long parent_ip, unsigned long flags) +{ + if (likely(!atomic_read(&data->disabled))) + trace_function(tr, data, ip, parent_ip, flags); +} + +#ifdef CONFIG_MMIOTRACE +void __trace_mmiotrace_rw(struct trace_array *tr, struct trace_array_cpu *data, + struct mmiotrace_rw *rw) +{ + struct trace_entry *entry; + unsigned long irq_flags; + + raw_local_irq_save(irq_flags); + __raw_spin_lock(&data->lock); + + entry = tracing_get_trace_entry(tr, data); + tracing_generic_entry_update(entry, 0); + entry->type = TRACE_MMIO_RW; + entry->mmiorw = *rw; + + __raw_spin_unlock(&data->lock); + raw_local_irq_restore(irq_flags); + + trace_wake_up(); +} + +void __trace_mmiotrace_map(struct trace_array *tr, struct trace_array_cpu *data, + struct mmiotrace_map *map) +{ + struct trace_entry *entry; + unsigned long irq_flags; + + raw_local_irq_save(irq_flags); + __raw_spin_lock(&data->lock); + + entry = tracing_get_trace_entry(tr, data); + tracing_generic_entry_update(entry, 0); + entry->type = TRACE_MMIO_MAP; + entry->mmiomap = *map; + + __raw_spin_unlock(&data->lock); + raw_local_irq_restore(irq_flags); + + trace_wake_up(); +} +#endif + +void __trace_stack(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long flags, + int skip) +{ + struct trace_entry *entry; + struct stack_trace trace; + + if (!(trace_flags & TRACE_ITER_STACKTRACE)) + return; + + entry = tracing_get_trace_entry(tr, data); + tracing_generic_entry_update(entry, flags); + entry->type = TRACE_STACK; + + memset(&entry->stack, 0, sizeof(entry->stack)); + + trace.nr_entries = 0; + trace.max_entries = FTRACE_STACK_ENTRIES; + trace.skip = skip; + trace.entries = entry->stack.caller; + + save_stack_trace(&trace); +} + +void +__trace_special(void *__tr, void *__data, + unsigned long arg1, unsigned long arg2, unsigned long arg3) +{ + struct trace_array_cpu *data = __data; + struct trace_array *tr = __tr; + struct trace_entry *entry; + unsigned long irq_flags; + + raw_local_irq_save(irq_flags); + __raw_spin_lock(&data->lock); + entry = tracing_get_trace_entry(tr, data); + tracing_generic_entry_update(entry, 0); + entry->type = TRACE_SPECIAL; + entry->special.arg1 = arg1; + entry->special.arg2 = arg2; + entry->special.arg3 = arg3; + __trace_stack(tr, data, irq_flags, 4); + __raw_spin_unlock(&data->lock); + raw_local_irq_restore(irq_flags); + + trace_wake_up(); +} + +void +tracing_sched_switch_trace(struct trace_array *tr, + struct trace_array_cpu *data, + struct task_struct *prev, + struct task_struct *next, + unsigned long flags) +{ + struct trace_entry *entry; + unsigned long irq_flags; + + raw_local_irq_save(irq_flags); + __raw_spin_lock(&data->lock); + entry = tracing_get_trace_entry(tr, data); + tracing_generic_entry_update(entry, flags); + entry->type = TRACE_CTX; + entry->ctx.prev_pid = prev->pid; + entry->ctx.prev_prio = prev->prio; + entry->ctx.prev_state = prev->state; + entry->ctx.next_pid = next->pid; + entry->ctx.next_prio = next->prio; + entry->ctx.next_state = next->state; + __trace_stack(tr, data, flags, 5); + __raw_spin_unlock(&data->lock); + raw_local_irq_restore(irq_flags); +} + +void +tracing_sched_wakeup_trace(struct trace_array *tr, + struct trace_array_cpu *data, + struct task_struct *wakee, + struct task_struct *curr, + unsigned long flags) +{ + struct trace_entry *entry; + unsigned long irq_flags; + + raw_local_irq_save(irq_flags); + __raw_spin_lock(&data->lock); + entry = tracing_get_trace_entry(tr, data); + tracing_generic_entry_update(entry, flags); + entry->type = TRACE_WAKE; + entry->ctx.prev_pid = curr->pid; + entry->ctx.prev_prio = curr->prio; + entry->ctx.prev_state = curr->state; + entry->ctx.next_pid = wakee->pid; + entry->ctx.next_prio = wakee->prio; + entry->ctx.next_state = wakee->state; + __trace_stack(tr, data, flags, 6); + __raw_spin_unlock(&data->lock); + raw_local_irq_restore(irq_flags); + + trace_wake_up(); +} + +void +ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) +{ + struct trace_array *tr = &global_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + + if (tracing_disabled || current_trace == &no_tracer || !tr->ctrl) + return; + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) + __trace_special(tr, data, arg1, arg2, arg3); + + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + +#ifdef CONFIG_FTRACE +static void +function_trace_call(unsigned long ip, unsigned long parent_ip) +{ + struct trace_array *tr = &global_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + + if (unlikely(!ftrace_function_enabled)) + return; + + if (skip_trace(ip)) + return; + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) + trace_function(tr, data, ip, parent_ip, flags); + + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + +static struct ftrace_ops trace_ops __read_mostly = +{ + .func = function_trace_call, +}; + +void tracing_start_function_trace(void) +{ + ftrace_function_enabled = 0; + register_ftrace_function(&trace_ops); + if (tracer_enabled) + ftrace_function_enabled = 1; +} + +void tracing_stop_function_trace(void) +{ + ftrace_function_enabled = 0; + unregister_ftrace_function(&trace_ops); +} +#endif + +enum trace_file_type { + TRACE_FILE_LAT_FMT = 1, +}; + +static struct trace_entry * +trace_entry_idx(struct trace_array *tr, struct trace_array_cpu *data, + struct trace_iterator *iter, int cpu) +{ + struct page *page; + struct trace_entry *array; + + if (iter->next_idx[cpu] >= tr->entries || + iter->next_idx[cpu] >= data->trace_idx || + (data->trace_head == data->trace_tail && + data->trace_head_idx == data->trace_tail_idx)) + return NULL; + + if (!iter->next_page[cpu]) { + /* Initialize the iterator for this cpu trace buffer */ + WARN_ON(!data->trace_tail); + page = virt_to_page(data->trace_tail); + iter->next_page[cpu] = &page->lru; + iter->next_page_idx[cpu] = data->trace_tail_idx; + } + + page = list_entry(iter->next_page[cpu], struct page, lru); + BUG_ON(&data->trace_pages == &page->lru); + + array = page_address(page); + + WARN_ON(iter->next_page_idx[cpu] >= ENTRIES_PER_PAGE); + return &array[iter->next_page_idx[cpu]]; +} + +static struct trace_entry * +find_next_entry(struct trace_iterator *iter, int *ent_cpu) +{ + struct trace_array *tr = iter->tr; + struct trace_entry *ent, *next = NULL; + int next_cpu = -1; + int cpu; + + for_each_tracing_cpu(cpu) { + if (!head_page(tr->data[cpu])) + continue; + ent = trace_entry_idx(tr, tr->data[cpu], iter, cpu); + /* + * Pick the entry with the smallest timestamp: + */ + if (ent && (!next || ent->t < next->t)) { + next = ent; + next_cpu = cpu; + } + } + + if (ent_cpu) + *ent_cpu = next_cpu; + + return next; +} + +static void trace_iterator_increment(struct trace_iterator *iter) +{ + iter->idx++; + iter->next_idx[iter->cpu]++; + iter->next_page_idx[iter->cpu]++; + + if (iter->next_page_idx[iter->cpu] >= ENTRIES_PER_PAGE) { + struct trace_array_cpu *data = iter->tr->data[iter->cpu]; + + iter->next_page_idx[iter->cpu] = 0; + iter->next_page[iter->cpu] = + trace_next_list(data, iter->next_page[iter->cpu]); + } +} + +static void trace_consume(struct trace_iterator *iter) +{ + struct trace_array_cpu *data = iter->tr->data[iter->cpu]; + + data->trace_tail_idx++; + if (data->trace_tail_idx >= ENTRIES_PER_PAGE) { + data->trace_tail = trace_next_page(data, data->trace_tail); + data->trace_tail_idx = 0; + } + + /* Check if we empty it, then reset the index */ + if (data->trace_head == data->trace_tail && + data->trace_head_idx == data->trace_tail_idx) + data->trace_idx = 0; +} + +static void *find_next_entry_inc(struct trace_iterator *iter) +{ + struct trace_entry *next; + int next_cpu = -1; + + next = find_next_entry(iter, &next_cpu); + + iter->prev_ent = iter->ent; + iter->prev_cpu = iter->cpu; + + iter->ent = next; + iter->cpu = next_cpu; + + if (next) + trace_iterator_increment(iter); + + return next ? iter : NULL; +} + +static void *s_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct trace_iterator *iter = m->private; + void *last_ent = iter->ent; + int i = (int)*pos; + void *ent; + + (*pos)++; + + /* can't go backwards */ + if (iter->idx > i) + return NULL; + + if (iter->idx < 0) + ent = find_next_entry_inc(iter); + else + ent = iter; + + while (ent && iter->idx < i) + ent = find_next_entry_inc(iter); + + iter->pos = *pos; + + if (last_ent && !ent) + seq_puts(m, "\n\nvim:ft=help\n"); + + return ent; +} + +static void *s_start(struct seq_file *m, loff_t *pos) +{ + struct trace_iterator *iter = m->private; + void *p = NULL; + loff_t l = 0; + int i; + + mutex_lock(&trace_types_lock); + + if (!current_trace || current_trace != iter->trace) { + mutex_unlock(&trace_types_lock); + return NULL; + } + + atomic_inc(&trace_record_cmdline_disabled); + + /* let the tracer grab locks here if needed */ + if (current_trace->start) + current_trace->start(iter); + + if (*pos != iter->pos) { + iter->ent = NULL; + iter->cpu = 0; + iter->idx = -1; + iter->prev_ent = NULL; + iter->prev_cpu = -1; + + for_each_tracing_cpu(i) { + iter->next_idx[i] = 0; + iter->next_page[i] = NULL; + } + + for (p = iter; p && l < *pos; p = s_next(m, p, &l)) + ; + + } else { + l = *pos - 1; + p = s_next(m, p, &l); + } + + return p; +} + +static void s_stop(struct seq_file *m, void *p) +{ + struct trace_iterator *iter = m->private; + + atomic_dec(&trace_record_cmdline_disabled); + + /* let the tracer release locks here if needed */ + if (current_trace && current_trace == iter->trace && iter->trace->stop) + iter->trace->stop(iter); + + mutex_unlock(&trace_types_lock); +} + +#define KRETPROBE_MSG "[unknown/kretprobe'd]" + +#ifdef CONFIG_KRETPROBES +static inline int kretprobed(unsigned long addr) +{ + return addr == (unsigned long)kretprobe_trampoline; +} +#else +static inline int kretprobed(unsigned long addr) +{ + return 0; +} +#endif /* CONFIG_KRETPROBES */ + +static int +seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address) +{ +#ifdef CONFIG_KALLSYMS + char str[KSYM_SYMBOL_LEN]; + + kallsyms_lookup(address, NULL, NULL, NULL, str); + + return trace_seq_printf(s, fmt, str); +#endif + return 1; +} + +static int +seq_print_sym_offset(struct trace_seq *s, const char *fmt, + unsigned long address) +{ +#ifdef CONFIG_KALLSYMS + char str[KSYM_SYMBOL_LEN]; + + sprint_symbol(str, address); + return trace_seq_printf(s, fmt, str); +#endif + return 1; +} + +#ifndef CONFIG_64BIT +# define IP_FMT "%08lx" +#else +# define IP_FMT "%016lx" +#endif + +static int +seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags) +{ + int ret; + + if (!ip) + return trace_seq_printf(s, "0"); + + if (sym_flags & TRACE_ITER_SYM_OFFSET) + ret = seq_print_sym_offset(s, "%s", ip); + else + ret = seq_print_sym_short(s, "%s", ip); + + if (!ret) + return 0; + + if (sym_flags & TRACE_ITER_SYM_ADDR) + ret = trace_seq_printf(s, " <" IP_FMT ">", ip); + return ret; +} + +static void print_lat_help_header(struct seq_file *m) +{ + seq_puts(m, "# _------=> CPU# \n"); + seq_puts(m, "# / _-----=> irqs-off \n"); + seq_puts(m, "# | / _----=> need-resched \n"); + seq_puts(m, "# || / _---=> hardirq/softirq \n"); + seq_puts(m, "# ||| / _--=> preempt-depth \n"); + seq_puts(m, "# |||| / \n"); + seq_puts(m, "# ||||| delay \n"); + seq_puts(m, "# cmd pid ||||| time | caller \n"); + seq_puts(m, "# \\ / ||||| \\ | / \n"); +} + +static void print_func_help_header(struct seq_file *m) +{ + seq_puts(m, "# TASK-PID CPU# TIMESTAMP FUNCTION\n"); + seq_puts(m, "# | | | | |\n"); +} + + +static void +print_trace_header(struct seq_file *m, struct trace_iterator *iter) +{ + unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); + struct trace_array *tr = iter->tr; + struct trace_array_cpu *data = tr->data[tr->cpu]; + struct tracer *type = current_trace; + unsigned long total = 0; + unsigned long entries = 0; + int cpu; + const char *name = "preemption"; + + if (type) + name = type->name; + + for_each_tracing_cpu(cpu) { + if (head_page(tr->data[cpu])) { + total += tr->data[cpu]->trace_idx; + if (tr->data[cpu]->trace_idx > tr->entries) + entries += tr->entries; + else + entries += tr->data[cpu]->trace_idx; + } + } + + seq_printf(m, "%s latency trace v1.1.5 on %s\n", + name, UTS_RELEASE); + seq_puts(m, "-----------------------------------" + "---------------------------------\n"); + seq_printf(m, " latency: %lu us, #%lu/%lu, CPU#%d |" + " (M:%s VP:%d, KP:%d, SP:%d HP:%d", + nsecs_to_usecs(data->saved_latency), + entries, + total, + tr->cpu, +#if defined(CONFIG_PREEMPT_NONE) + "server", +#elif defined(CONFIG_PREEMPT_VOLUNTARY) + "desktop", +#elif defined(CONFIG_PREEMPT) + "preempt", +#else + "unknown", +#endif + /* These are reserved for later use */ + 0, 0, 0, 0); +#ifdef CONFIG_SMP + seq_printf(m, " #P:%d)\n", num_online_cpus()); +#else + seq_puts(m, ")\n"); +#endif + seq_puts(m, " -----------------\n"); + seq_printf(m, " | task: %.16s-%d " + "(uid:%d nice:%ld policy:%ld rt_prio:%ld)\n", + data->comm, data->pid, data->uid, data->nice, + data->policy, data->rt_priority); + seq_puts(m, " -----------------\n"); + + if (data->critical_start) { + seq_puts(m, " => started at: "); + seq_print_ip_sym(&iter->seq, data->critical_start, sym_flags); + trace_print_seq(m, &iter->seq); + seq_puts(m, "\n => ended at: "); + seq_print_ip_sym(&iter->seq, data->critical_end, sym_flags); + trace_print_seq(m, &iter->seq); + seq_puts(m, "\n"); + } + + seq_puts(m, "\n"); +} + +static void +lat_print_generic(struct trace_seq *s, struct trace_entry *entry, int cpu) +{ + int hardirq, softirq; + char *comm; + + comm = trace_find_cmdline(entry->pid); + + trace_seq_printf(s, "%8.8s-%-5d ", comm, entry->pid); + trace_seq_printf(s, "%d", cpu); + trace_seq_printf(s, "%c%c", + (entry->flags & TRACE_FLAG_IRQS_OFF) ? 'd' : '.', + ((entry->flags & TRACE_FLAG_NEED_RESCHED) ? 'N' : '.')); + + hardirq = entry->flags & TRACE_FLAG_HARDIRQ; + softirq = entry->flags & TRACE_FLAG_SOFTIRQ; + if (hardirq && softirq) { + trace_seq_putc(s, 'H'); + } else { + if (hardirq) { + trace_seq_putc(s, 'h'); + } else { + if (softirq) + trace_seq_putc(s, 's'); + else + trace_seq_putc(s, '.'); + } + } + + if (entry->preempt_count) + trace_seq_printf(s, "%x", entry->preempt_count); + else + trace_seq_puts(s, "."); +} + +unsigned long preempt_mark_thresh = 100; + +static void +lat_print_timestamp(struct trace_seq *s, unsigned long long abs_usecs, + unsigned long rel_usecs) +{ + trace_seq_printf(s, " %4lldus", abs_usecs); + if (rel_usecs > preempt_mark_thresh) + trace_seq_puts(s, "!: "); + else if (rel_usecs > 1) + trace_seq_puts(s, "+: "); + else + trace_seq_puts(s, " : "); +} + +static const char state_to_char[] = TASK_STATE_TO_CHAR_STR; + +static int +print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu) +{ + struct trace_seq *s = &iter->seq; + unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); + struct trace_entry *next_entry = find_next_entry(iter, NULL); + unsigned long verbose = (trace_flags & TRACE_ITER_VERBOSE); + struct trace_entry *entry = iter->ent; + unsigned long abs_usecs; + unsigned long rel_usecs; + char *comm; + int S, T; + int i; + unsigned state; + + if (!next_entry) + next_entry = entry; + rel_usecs = ns2usecs(next_entry->t - entry->t); + abs_usecs = ns2usecs(entry->t - iter->tr->time_start); + + if (verbose) { + comm = trace_find_cmdline(entry->pid); + trace_seq_printf(s, "%16s %5d %d %d %08x %08x [%08lx]" + " %ld.%03ldms (+%ld.%03ldms): ", + comm, + entry->pid, cpu, entry->flags, + entry->preempt_count, trace_idx, + ns2usecs(entry->t), + abs_usecs/1000, + abs_usecs % 1000, rel_usecs/1000, + rel_usecs % 1000); + } else { + lat_print_generic(s, entry, cpu); + lat_print_timestamp(s, abs_usecs, rel_usecs); + } + switch (entry->type) { + case TRACE_FN: + seq_print_ip_sym(s, entry->fn.ip, sym_flags); + trace_seq_puts(s, " ("); + if (kretprobed(entry->fn.parent_ip)) + trace_seq_puts(s, KRETPROBE_MSG); + else + seq_print_ip_sym(s, entry->fn.parent_ip, sym_flags); + trace_seq_puts(s, ")\n"); + break; + case TRACE_CTX: + case TRACE_WAKE: + T = entry->ctx.next_state < sizeof(state_to_char) ? + state_to_char[entry->ctx.next_state] : 'X'; + + state = entry->ctx.prev_state ? __ffs(entry->ctx.prev_state) + 1 : 0; + S = state < sizeof(state_to_char) - 1 ? state_to_char[state] : 'X'; + comm = trace_find_cmdline(entry->ctx.next_pid); + trace_seq_printf(s, " %5d:%3d:%c %s %5d:%3d:%c %s\n", + entry->ctx.prev_pid, + entry->ctx.prev_prio, + S, entry->type == TRACE_CTX ? "==>" : " +", + entry->ctx.next_pid, + entry->ctx.next_prio, + T, comm); + break; + case TRACE_SPECIAL: + trace_seq_printf(s, "# %ld %ld %ld\n", + entry->special.arg1, + entry->special.arg2, + entry->special.arg3); + break; + case TRACE_STACK: + for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { + if (i) + trace_seq_puts(s, " <= "); + seq_print_ip_sym(s, entry->stack.caller[i], sym_flags); + } + trace_seq_puts(s, "\n"); + break; + default: + trace_seq_printf(s, "Unknown type %d\n", entry->type); + } + return 1; +} + +static int print_trace_fmt(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + unsigned long sym_flags = (trace_flags & TRACE_ITER_SYM_MASK); + struct trace_entry *entry; + unsigned long usec_rem; + unsigned long long t; + unsigned long secs; + char *comm; + int ret; + int S, T; + int i; + + entry = iter->ent; + + comm = trace_find_cmdline(iter->ent->pid); + + t = ns2usecs(entry->t); + usec_rem = do_div(t, 1000000ULL); + secs = (unsigned long)t; + + ret = trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid); + if (!ret) + return 0; + ret = trace_seq_printf(s, "[%02d] ", iter->cpu); + if (!ret) + return 0; + ret = trace_seq_printf(s, "%5lu.%06lu: ", secs, usec_rem); + if (!ret) + return 0; + + switch (entry->type) { + case TRACE_FN: + ret = seq_print_ip_sym(s, entry->fn.ip, sym_flags); + if (!ret) + return 0; + if ((sym_flags & TRACE_ITER_PRINT_PARENT) && + entry->fn.parent_ip) { + ret = trace_seq_printf(s, " <-"); + if (!ret) + return 0; + if (kretprobed(entry->fn.parent_ip)) + ret = trace_seq_puts(s, KRETPROBE_MSG); + else + ret = seq_print_ip_sym(s, entry->fn.parent_ip, + sym_flags); + if (!ret) + return 0; + } + ret = trace_seq_printf(s, "\n"); + if (!ret) + return 0; + break; + case TRACE_CTX: + case TRACE_WAKE: + S = entry->ctx.prev_state < sizeof(state_to_char) ? + state_to_char[entry->ctx.prev_state] : 'X'; + T = entry->ctx.next_state < sizeof(state_to_char) ? + state_to_char[entry->ctx.next_state] : 'X'; + ret = trace_seq_printf(s, " %5d:%3d:%c %s %5d:%3d:%c\n", + entry->ctx.prev_pid, + entry->ctx.prev_prio, + S, + entry->type == TRACE_CTX ? "==>" : " +", + entry->ctx.next_pid, + entry->ctx.next_prio, + T); + if (!ret) + return 0; + break; + case TRACE_SPECIAL: + ret = trace_seq_printf(s, "# %ld %ld %ld\n", + entry->special.arg1, + entry->special.arg2, + entry->special.arg3); + if (!ret) + return 0; + break; + case TRACE_STACK: + for (i = 0; i < FTRACE_STACK_ENTRIES; i++) { + if (i) { + ret = trace_seq_puts(s, " <= "); + if (!ret) + return 0; + } + ret = seq_print_ip_sym(s, entry->stack.caller[i], + sym_flags); + if (!ret) + return 0; + } + ret = trace_seq_puts(s, "\n"); + if (!ret) + return 0; + break; + } + return 1; +} + +static int print_raw_fmt(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry; + int ret; + int S, T; + + entry = iter->ent; + + ret = trace_seq_printf(s, "%d %d %llu ", + entry->pid, iter->cpu, entry->t); + if (!ret) + return 0; + + switch (entry->type) { + case TRACE_FN: + ret = trace_seq_printf(s, "%x %x\n", + entry->fn.ip, entry->fn.parent_ip); + if (!ret) + return 0; + break; + case TRACE_CTX: + case TRACE_WAKE: + S = entry->ctx.prev_state < sizeof(state_to_char) ? + state_to_char[entry->ctx.prev_state] : 'X'; + T = entry->ctx.next_state < sizeof(state_to_char) ? + state_to_char[entry->ctx.next_state] : 'X'; + if (entry->type == TRACE_WAKE) + S = '+'; + ret = trace_seq_printf(s, "%d %d %c %d %d %c\n", + entry->ctx.prev_pid, + entry->ctx.prev_prio, + S, + entry->ctx.next_pid, + entry->ctx.next_prio, + T); + if (!ret) + return 0; + break; + case TRACE_SPECIAL: + case TRACE_STACK: + ret = trace_seq_printf(s, "# %ld %ld %ld\n", + entry->special.arg1, + entry->special.arg2, + entry->special.arg3); + if (!ret) + return 0; + break; + } + return 1; +} + +#define SEQ_PUT_FIELD_RET(s, x) \ +do { \ + if (!trace_seq_putmem(s, &(x), sizeof(x))) \ + return 0; \ +} while (0) + +#define SEQ_PUT_HEX_FIELD_RET(s, x) \ +do { \ + if (!trace_seq_putmem_hex(s, &(x), sizeof(x))) \ + return 0; \ +} while (0) + +static int print_hex_fmt(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + unsigned char newline = '\n'; + struct trace_entry *entry; + int S, T; + + entry = iter->ent; + + SEQ_PUT_HEX_FIELD_RET(s, entry->pid); + SEQ_PUT_HEX_FIELD_RET(s, iter->cpu); + SEQ_PUT_HEX_FIELD_RET(s, entry->t); + + switch (entry->type) { + case TRACE_FN: + SEQ_PUT_HEX_FIELD_RET(s, entry->fn.ip); + SEQ_PUT_HEX_FIELD_RET(s, entry->fn.parent_ip); + break; + case TRACE_CTX: + case TRACE_WAKE: + S = entry->ctx.prev_state < sizeof(state_to_char) ? + state_to_char[entry->ctx.prev_state] : 'X'; + T = entry->ctx.next_state < sizeof(state_to_char) ? + state_to_char[entry->ctx.next_state] : 'X'; + if (entry->type == TRACE_WAKE) + S = '+'; + SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.prev_pid); + SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.prev_prio); + SEQ_PUT_HEX_FIELD_RET(s, S); + SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.next_pid); + SEQ_PUT_HEX_FIELD_RET(s, entry->ctx.next_prio); + SEQ_PUT_HEX_FIELD_RET(s, entry->fn.parent_ip); + SEQ_PUT_HEX_FIELD_RET(s, T); + break; + case TRACE_SPECIAL: + case TRACE_STACK: + SEQ_PUT_HEX_FIELD_RET(s, entry->special.arg1); + SEQ_PUT_HEX_FIELD_RET(s, entry->special.arg2); + SEQ_PUT_HEX_FIELD_RET(s, entry->special.arg3); + break; + } + SEQ_PUT_FIELD_RET(s, newline); + + return 1; +} + +static int print_bin_fmt(struct trace_iterator *iter) +{ + struct trace_seq *s = &iter->seq; + struct trace_entry *entry; + + entry = iter->ent; + + SEQ_PUT_FIELD_RET(s, entry->pid); + SEQ_PUT_FIELD_RET(s, entry->cpu); + SEQ_PUT_FIELD_RET(s, entry->t); + + switch (entry->type) { + case TRACE_FN: + SEQ_PUT_FIELD_RET(s, entry->fn.ip); + SEQ_PUT_FIELD_RET(s, entry->fn.parent_ip); + break; + case TRACE_CTX: + SEQ_PUT_FIELD_RET(s, entry->ctx.prev_pid); + SEQ_PUT_FIELD_RET(s, entry->ctx.prev_prio); + SEQ_PUT_FIELD_RET(s, entry->ctx.prev_state); + SEQ_PUT_FIELD_RET(s, entry->ctx.next_pid); + SEQ_PUT_FIELD_RET(s, entry->ctx.next_prio); + SEQ_PUT_FIELD_RET(s, entry->ctx.next_state); + break; + case TRACE_SPECIAL: + case TRACE_STACK: + SEQ_PUT_FIELD_RET(s, entry->special.arg1); + SEQ_PUT_FIELD_RET(s, entry->special.arg2); + SEQ_PUT_FIELD_RET(s, entry->special.arg3); + break; + } + return 1; +} + +static int trace_empty(struct trace_iterator *iter) +{ + struct trace_array_cpu *data; + int cpu; + + for_each_tracing_cpu(cpu) { + data = iter->tr->data[cpu]; + + if (head_page(data) && data->trace_idx && + (data->trace_tail != data->trace_head || + data->trace_tail_idx != data->trace_head_idx)) + return 0; + } + return 1; +} + +static int print_trace_line(struct trace_iterator *iter) +{ + if (iter->trace && iter->trace->print_line) + return iter->trace->print_line(iter); + + if (trace_flags & TRACE_ITER_BIN) + return print_bin_fmt(iter); + + if (trace_flags & TRACE_ITER_HEX) + return print_hex_fmt(iter); + + if (trace_flags & TRACE_ITER_RAW) + return print_raw_fmt(iter); + + if (iter->iter_flags & TRACE_FILE_LAT_FMT) + return print_lat_fmt(iter, iter->idx, iter->cpu); + + return print_trace_fmt(iter); +} + +static int s_show(struct seq_file *m, void *v) +{ + struct trace_iterator *iter = v; + + if (iter->ent == NULL) { + if (iter->tr) { + seq_printf(m, "# tracer: %s\n", iter->trace->name); + seq_puts(m, "#\n"); + } + if (iter->iter_flags & TRACE_FILE_LAT_FMT) { + /* print nothing if the buffers are empty */ + if (trace_empty(iter)) + return 0; + print_trace_header(m, iter); + if (!(trace_flags & TRACE_ITER_VERBOSE)) + print_lat_help_header(m); + } else { + if (!(trace_flags & TRACE_ITER_VERBOSE)) + print_func_help_header(m); + } + } else { + print_trace_line(iter); + trace_print_seq(m, &iter->seq); + } + + return 0; +} + +static struct seq_operations tracer_seq_ops = { + .start = s_start, + .next = s_next, + .stop = s_stop, + .show = s_show, +}; + +static struct trace_iterator * +__tracing_open(struct inode *inode, struct file *file, int *ret) +{ + struct trace_iterator *iter; + + if (tracing_disabled) { + *ret = -ENODEV; + return NULL; + } + + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) { + *ret = -ENOMEM; + goto out; + } + + mutex_lock(&trace_types_lock); + if (current_trace && current_trace->print_max) + iter->tr = &max_tr; + else + iter->tr = inode->i_private; + iter->trace = current_trace; + iter->pos = -1; + + /* TODO stop tracer */ + *ret = seq_open(file, &tracer_seq_ops); + if (!*ret) { + struct seq_file *m = file->private_data; + m->private = iter; + + /* stop the trace while dumping */ + if (iter->tr->ctrl) { + tracer_enabled = 0; + ftrace_function_enabled = 0; + } + + if (iter->trace && iter->trace->open) + iter->trace->open(iter); + } else { + kfree(iter); + iter = NULL; + } + mutex_unlock(&trace_types_lock); + + out: + return iter; +} + +int tracing_open_generic(struct inode *inode, struct file *filp) +{ + if (tracing_disabled) + return -ENODEV; + + filp->private_data = inode->i_private; + return 0; +} + +int tracing_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = (struct seq_file *)file->private_data; + struct trace_iterator *iter = m->private; + + mutex_lock(&trace_types_lock); + if (iter->trace && iter->trace->close) + iter->trace->close(iter); + + /* reenable tracing if it was previously enabled */ + if (iter->tr->ctrl) { + tracer_enabled = 1; + /* + * It is safe to enable function tracing even if it + * isn't used + */ + ftrace_function_enabled = 1; + } + mutex_unlock(&trace_types_lock); + + seq_release(inode, file); + kfree(iter); + return 0; +} + +static int tracing_open(struct inode *inode, struct file *file) +{ + int ret; + + __tracing_open(inode, file, &ret); + + return ret; +} + +static int tracing_lt_open(struct inode *inode, struct file *file) +{ + struct trace_iterator *iter; + int ret; + + iter = __tracing_open(inode, file, &ret); + + if (!ret) + iter->iter_flags |= TRACE_FILE_LAT_FMT; + + return ret; +} + + +static void * +t_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct tracer *t = m->private; + + (*pos)++; + + if (t) + t = t->next; + + m->private = t; + + return t; +} + +static void *t_start(struct seq_file *m, loff_t *pos) +{ + struct tracer *t = m->private; + loff_t l = 0; + + mutex_lock(&trace_types_lock); + for (; t && l < *pos; t = t_next(m, t, &l)) + ; + + return t; +} + +static void t_stop(struct seq_file *m, void *p) +{ + mutex_unlock(&trace_types_lock); +} + +static int t_show(struct seq_file *m, void *v) +{ + struct tracer *t = v; + + if (!t) + return 0; + + seq_printf(m, "%s", t->name); + if (t->next) + seq_putc(m, ' '); + else + seq_putc(m, '\n'); + + return 0; +} + +static struct seq_operations show_traces_seq_ops = { + .start = t_start, + .next = t_next, + .stop = t_stop, + .show = t_show, +}; + +static int show_traces_open(struct inode *inode, struct file *file) +{ + int ret; + + if (tracing_disabled) + return -ENODEV; + + ret = seq_open(file, &show_traces_seq_ops); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = trace_types; + } + + return ret; +} + +static struct file_operations tracing_fops = { + .open = tracing_open, + .read = seq_read, + .llseek = seq_lseek, + .release = tracing_release, +}; + +static struct file_operations tracing_lt_fops = { + .open = tracing_lt_open, + .read = seq_read, + .llseek = seq_lseek, + .release = tracing_release, +}; + +static struct file_operations show_traces_fops = { + .open = show_traces_open, + .read = seq_read, + .release = seq_release, +}; + +/* + * Only trace on a CPU if the bitmask is set: + */ +static cpumask_t tracing_cpumask = CPU_MASK_ALL; + +/* + * When tracing/tracing_cpu_mask is modified then this holds + * the new bitmask we are about to install: + */ +static cpumask_t tracing_cpumask_new; + +/* + * The tracer itself will not take this lock, but still we want + * to provide a consistent cpumask to user-space: + */ +static DEFINE_MUTEX(tracing_cpumask_update_lock); + +/* + * Temporary storage for the character representation of the + * CPU bitmask (and one more byte for the newline): + */ +static char mask_str[NR_CPUS + 1]; + +static ssize_t +tracing_cpumask_read(struct file *filp, char __user *ubuf, + size_t count, loff_t *ppos) +{ + int len; + + mutex_lock(&tracing_cpumask_update_lock); + + len = cpumask_scnprintf(mask_str, count, tracing_cpumask); + if (count - len < 2) { + count = -EINVAL; + goto out_err; + } + len += sprintf(mask_str + len, "\n"); + count = simple_read_from_buffer(ubuf, count, ppos, mask_str, NR_CPUS+1); + +out_err: + mutex_unlock(&tracing_cpumask_update_lock); + + return count; +} + +static ssize_t +tracing_cpumask_write(struct file *filp, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + int err, cpu; + + mutex_lock(&tracing_cpumask_update_lock); + err = cpumask_parse_user(ubuf, count, tracing_cpumask_new); + if (err) + goto err_unlock; + + raw_local_irq_disable(); + __raw_spin_lock(&ftrace_max_lock); + for_each_tracing_cpu(cpu) { + /* + * Increase/decrease the disabled counter if we are + * about to flip a bit in the cpumask: + */ + if (cpu_isset(cpu, tracing_cpumask) && + !cpu_isset(cpu, tracing_cpumask_new)) { + atomic_inc(&global_trace.data[cpu]->disabled); + } + if (!cpu_isset(cpu, tracing_cpumask) && + cpu_isset(cpu, tracing_cpumask_new)) { + atomic_dec(&global_trace.data[cpu]->disabled); + } + } + __raw_spin_unlock(&ftrace_max_lock); + raw_local_irq_enable(); + + tracing_cpumask = tracing_cpumask_new; + + mutex_unlock(&tracing_cpumask_update_lock); + + return count; + +err_unlock: + mutex_unlock(&tracing_cpumask_update_lock); + + return err; +} + +static struct file_operations tracing_cpumask_fops = { + .open = tracing_open_generic, + .read = tracing_cpumask_read, + .write = tracing_cpumask_write, +}; + +static ssize_t +tracing_iter_ctrl_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char *buf; + int r = 0; + int len = 0; + int i; + + /* calulate max size */ + for (i = 0; trace_options[i]; i++) { + len += strlen(trace_options[i]); + len += 3; /* "no" and space */ + } + + /* +2 for \n and \0 */ + buf = kmalloc(len + 2, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + for (i = 0; trace_options[i]; i++) { + if (trace_flags & (1 << i)) + r += sprintf(buf + r, "%s ", trace_options[i]); + else + r += sprintf(buf + r, "no%s ", trace_options[i]); + } + + r += sprintf(buf + r, "\n"); + WARN_ON(r >= len + 2); + + r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + + kfree(buf); + + return r; +} + +static ssize_t +tracing_iter_ctrl_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + char *cmp = buf; + int neg = 0; + int i; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + if (strncmp(buf, "no", 2) == 0) { + neg = 1; + cmp += 2; + } + + for (i = 0; trace_options[i]; i++) { + int len = strlen(trace_options[i]); + + if (strncmp(cmp, trace_options[i], len) == 0) { + if (neg) + trace_flags &= ~(1 << i); + else + trace_flags |= (1 << i); + break; + } + } + /* + * If no option could be set, return an error: + */ + if (!trace_options[i]) + return -EINVAL; + + filp->f_pos += cnt; + + return cnt; +} + +static struct file_operations tracing_iter_fops = { + .open = tracing_open_generic, + .read = tracing_iter_ctrl_read, + .write = tracing_iter_ctrl_write, +}; + +static const char readme_msg[] = + "tracing mini-HOWTO:\n\n" + "# mkdir /debug\n" + "# mount -t debugfs nodev /debug\n\n" + "# cat /debug/tracing/available_tracers\n" + "wakeup preemptirqsoff preemptoff irqsoff ftrace sched_switch none\n\n" + "# cat /debug/tracing/current_tracer\n" + "none\n" + "# echo sched_switch > /debug/tracing/current_tracer\n" + "# cat /debug/tracing/current_tracer\n" + "sched_switch\n" + "# cat /debug/tracing/iter_ctrl\n" + "noprint-parent nosym-offset nosym-addr noverbose\n" + "# echo print-parent > /debug/tracing/iter_ctrl\n" + "# echo 1 > /debug/tracing/tracing_enabled\n" + "# cat /debug/tracing/trace > /tmp/trace.txt\n" + "echo 0 > /debug/tracing/tracing_enabled\n" +; + +static ssize_t +tracing_readme_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return simple_read_from_buffer(ubuf, cnt, ppos, + readme_msg, strlen(readme_msg)); +} + +static struct file_operations tracing_readme_fops = { + .open = tracing_open_generic, + .read = tracing_readme_read, +}; + +static ssize_t +tracing_ctrl_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + char buf[64]; + int r; + + r = sprintf(buf, "%ld\n", tr->ctrl); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +tracing_ctrl_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + char buf[64]; + long val; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + ret = strict_strtoul(buf, 10, &val); + if (ret < 0) + return ret; + + val = !!val; + + mutex_lock(&trace_types_lock); + if (tr->ctrl ^ val) { + if (val) + tracer_enabled = 1; + else + tracer_enabled = 0; + + tr->ctrl = val; + + if (current_trace && current_trace->ctrl_update) + current_trace->ctrl_update(tr); + } + mutex_unlock(&trace_types_lock); + + filp->f_pos += cnt; + + return cnt; +} + +static ssize_t +tracing_set_trace_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[max_tracer_type_len+2]; + int r; + + mutex_lock(&trace_types_lock); + if (current_trace) + r = sprintf(buf, "%s\n", current_trace->name); + else + r = sprintf(buf, "\n"); + mutex_unlock(&trace_types_lock); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +tracing_set_trace_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = &global_trace; + struct tracer *t; + char buf[max_tracer_type_len+1]; + int i; + + if (cnt > max_tracer_type_len) + cnt = max_tracer_type_len; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + /* strip ending whitespace. */ + for (i = cnt - 1; i > 0 && isspace(buf[i]); i--) + buf[i] = 0; + + mutex_lock(&trace_types_lock); + for (t = trace_types; t; t = t->next) { + if (strcmp(t->name, buf) == 0) + break; + } + if (!t || t == current_trace) + goto out; + + if (current_trace && current_trace->reset) + current_trace->reset(tr); + + current_trace = t; + if (t->init) + t->init(tr); + + out: + mutex_unlock(&trace_types_lock); + + filp->f_pos += cnt; + + return cnt; +} + +static ssize_t +tracing_max_lat_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + unsigned long *ptr = filp->private_data; + char buf[64]; + int r; + + r = snprintf(buf, sizeof(buf), "%ld\n", + *ptr == (unsigned long)-1 ? -1 : nsecs_to_usecs(*ptr)); + if (r > sizeof(buf)) + r = sizeof(buf); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +tracing_max_lat_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + long *ptr = filp->private_data; + char buf[64]; + long val; + int ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + ret = strict_strtoul(buf, 10, &val); + if (ret < 0) + return ret; + + *ptr = val * 1000; + + return cnt; +} + +static atomic_t tracing_reader; + +static int tracing_open_pipe(struct inode *inode, struct file *filp) +{ + struct trace_iterator *iter; + + if (tracing_disabled) + return -ENODEV; + + /* We only allow for reader of the pipe */ + if (atomic_inc_return(&tracing_reader) != 1) { + atomic_dec(&tracing_reader); + return -EBUSY; + } + + /* create a buffer to store the information to pass to userspace */ + iter = kzalloc(sizeof(*iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + + mutex_lock(&trace_types_lock); + iter->tr = &global_trace; + iter->trace = current_trace; + filp->private_data = iter; + + if (iter->trace->pipe_open) + iter->trace->pipe_open(iter); + mutex_unlock(&trace_types_lock); + + return 0; +} + +static int tracing_release_pipe(struct inode *inode, struct file *file) +{ + struct trace_iterator *iter = file->private_data; + + kfree(iter); + atomic_dec(&tracing_reader); + + return 0; +} + +static unsigned int +tracing_poll_pipe(struct file *filp, poll_table *poll_table) +{ + struct trace_iterator *iter = filp->private_data; + + if (trace_flags & TRACE_ITER_BLOCK) { + /* + * Always select as readable when in blocking mode + */ + return POLLIN | POLLRDNORM; + } else { + if (!trace_empty(iter)) + return POLLIN | POLLRDNORM; + poll_wait(filp, &trace_wait, poll_table); + if (!trace_empty(iter)) + return POLLIN | POLLRDNORM; + + return 0; + } +} + +/* + * Consumer reader. + */ +static ssize_t +tracing_read_pipe(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_iterator *iter = filp->private_data; + struct trace_array_cpu *data; + static cpumask_t mask; + unsigned long flags; +#ifdef CONFIG_FTRACE + int ftrace_save; +#endif + int cpu; + ssize_t sret; + + /* return any leftover data */ + sret = trace_seq_to_user(&iter->seq, ubuf, cnt); + if (sret != -EBUSY) + return sret; + sret = 0; + + trace_seq_reset(&iter->seq); + + mutex_lock(&trace_types_lock); + if (iter->trace->read) { + sret = iter->trace->read(iter, filp, ubuf, cnt, ppos); + if (sret) + goto out; + } + + while (trace_empty(iter)) { + + if ((filp->f_flags & O_NONBLOCK)) { + sret = -EAGAIN; + goto out; + } + + /* + * This is a make-shift waitqueue. The reason we don't use + * an actual wait queue is because: + * 1) we only ever have one waiter + * 2) the tracing, traces all functions, we don't want + * the overhead of calling wake_up and friends + * (and tracing them too) + * Anyway, this is really very primitive wakeup. + */ + set_current_state(TASK_INTERRUPTIBLE); + iter->tr->waiter = current; + + mutex_unlock(&trace_types_lock); + + /* sleep for 100 msecs, and try again. */ + schedule_timeout(HZ/10); + + mutex_lock(&trace_types_lock); + + iter->tr->waiter = NULL; + + if (signal_pending(current)) { + sret = -EINTR; + goto out; + } + + if (iter->trace != current_trace) + goto out; + + /* + * We block until we read something and tracing is disabled. + * We still block if tracing is disabled, but we have never + * read anything. This allows a user to cat this file, and + * then enable tracing. But after we have read something, + * we give an EOF when tracing is again disabled. + * + * iter->pos will be 0 if we haven't read anything. + */ + if (!tracer_enabled && iter->pos) + break; + + continue; + } + + /* stop when tracing is finished */ + if (trace_empty(iter)) + goto out; + + if (cnt >= PAGE_SIZE) + cnt = PAGE_SIZE - 1; + + /* reset all but tr, trace, and overruns */ + memset(&iter->seq, 0, + sizeof(struct trace_iterator) - + offsetof(struct trace_iterator, seq)); + iter->pos = -1; + + /* + * We need to stop all tracing on all CPUS to read the + * the next buffer. This is a bit expensive, but is + * not done often. We fill all what we can read, + * and then release the locks again. + */ + + cpus_clear(mask); + local_irq_save(flags); +#ifdef CONFIG_FTRACE + ftrace_save = ftrace_enabled; + ftrace_enabled = 0; +#endif + smp_wmb(); + for_each_tracing_cpu(cpu) { + data = iter->tr->data[cpu]; + + if (!head_page(data) || !data->trace_idx) + continue; + + atomic_inc(&data->disabled); + cpu_set(cpu, mask); + } + + for_each_cpu_mask(cpu, mask) { + data = iter->tr->data[cpu]; + __raw_spin_lock(&data->lock); + + if (data->overrun > iter->last_overrun[cpu]) + iter->overrun[cpu] += + data->overrun - iter->last_overrun[cpu]; + iter->last_overrun[cpu] = data->overrun; + } + + while (find_next_entry_inc(iter) != NULL) { + int ret; + int len = iter->seq.len; + + ret = print_trace_line(iter); + if (!ret) { + /* don't print partial lines */ + iter->seq.len = len; + break; + } + + trace_consume(iter); + + if (iter->seq.len >= cnt) + break; + } + + for_each_cpu_mask(cpu, mask) { + data = iter->tr->data[cpu]; + __raw_spin_unlock(&data->lock); + } + + for_each_cpu_mask(cpu, mask) { + data = iter->tr->data[cpu]; + atomic_dec(&data->disabled); + } +#ifdef CONFIG_FTRACE + ftrace_enabled = ftrace_save; +#endif + local_irq_restore(flags); + + /* Now copy what we have to the user */ + sret = trace_seq_to_user(&iter->seq, ubuf, cnt); + if (iter->seq.readpos >= iter->seq.len) + trace_seq_reset(&iter->seq); + if (sret == -EBUSY) + sret = 0; + +out: + mutex_unlock(&trace_types_lock); + + return sret; +} + +static ssize_t +tracing_entries_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + struct trace_array *tr = filp->private_data; + char buf[64]; + int r; + + r = sprintf(buf, "%lu\n", tr->entries); + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +tracing_entries_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + unsigned long val; + char buf[64]; + int i, ret; + + if (cnt >= sizeof(buf)) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + ret = strict_strtoul(buf, 10, &val); + if (ret < 0) + return ret; + + /* must have at least 1 entry */ + if (!val) + return -EINVAL; + + mutex_lock(&trace_types_lock); + + if (current_trace != &no_tracer) { + cnt = -EBUSY; + pr_info("ftrace: set current_tracer to none" + " before modifying buffer size\n"); + goto out; + } + + if (val > global_trace.entries) { + long pages_requested; + unsigned long freeable_pages; + + /* make sure we have enough memory before mapping */ + pages_requested = + (val + (ENTRIES_PER_PAGE-1)) / ENTRIES_PER_PAGE; + + /* account for each buffer (and max_tr) */ + pages_requested *= tracing_nr_buffers * 2; + + /* Check for overflow */ + if (pages_requested < 0) { + cnt = -ENOMEM; + goto out; + } + + freeable_pages = determine_dirtyable_memory(); + + /* we only allow to request 1/4 of useable memory */ + if (pages_requested > + ((freeable_pages + tracing_pages_allocated) / 4)) { + cnt = -ENOMEM; + goto out; + } + + while (global_trace.entries < val) { + if (trace_alloc_page()) { + cnt = -ENOMEM; + goto out; + } + /* double check that we don't go over the known pages */ + if (tracing_pages_allocated > pages_requested) + break; + } + + } else { + /* include the number of entries in val (inc of page entries) */ + while (global_trace.entries > val + (ENTRIES_PER_PAGE - 1)) + trace_free_page(); + } + + /* check integrity */ + for_each_tracing_cpu(i) + check_pages(global_trace.data[i]); + + filp->f_pos += cnt; + + /* If check pages failed, return ENOMEM */ + if (tracing_disabled) + cnt = -ENOMEM; + out: + max_tr.entries = global_trace.entries; + mutex_unlock(&trace_types_lock); + + return cnt; +} + +static struct file_operations tracing_max_lat_fops = { + .open = tracing_open_generic, + .read = tracing_max_lat_read, + .write = tracing_max_lat_write, +}; + +static struct file_operations tracing_ctrl_fops = { + .open = tracing_open_generic, + .read = tracing_ctrl_read, + .write = tracing_ctrl_write, +}; + +static struct file_operations set_tracer_fops = { + .open = tracing_open_generic, + .read = tracing_set_trace_read, + .write = tracing_set_trace_write, +}; + +static struct file_operations tracing_pipe_fops = { + .open = tracing_open_pipe, + .poll = tracing_poll_pipe, + .read = tracing_read_pipe, + .release = tracing_release_pipe, +}; + +static struct file_operations tracing_entries_fops = { + .open = tracing_open_generic, + .read = tracing_entries_read, + .write = tracing_entries_write, +}; + +#ifdef CONFIG_DYNAMIC_FTRACE + +static ssize_t +tracing_read_long(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + unsigned long *p = filp->private_data; + char buf[64]; + int r; + + r = sprintf(buf, "%ld\n", *p); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static struct file_operations tracing_read_long_fops = { + .open = tracing_open_generic, + .read = tracing_read_long, +}; +#endif + +static struct dentry *d_tracer; + +struct dentry *tracing_init_dentry(void) +{ + static int once; + + if (d_tracer) + return d_tracer; + + d_tracer = debugfs_create_dir("tracing", NULL); + + if (!d_tracer && !once) { + once = 1; + pr_warning("Could not create debugfs directory 'tracing'\n"); + return NULL; + } + + return d_tracer; +} + +#ifdef CONFIG_FTRACE_SELFTEST +/* Let selftest have access to static functions in this file */ +#include "trace_selftest.c" +#endif + +static __init void tracer_init_debugfs(void) +{ + struct dentry *d_tracer; + struct dentry *entry; + + d_tracer = tracing_init_dentry(); + + entry = debugfs_create_file("tracing_enabled", 0644, d_tracer, + &global_trace, &tracing_ctrl_fops); + if (!entry) + pr_warning("Could not create debugfs 'tracing_enabled' entry\n"); + + entry = debugfs_create_file("iter_ctrl", 0644, d_tracer, + NULL, &tracing_iter_fops); + if (!entry) + pr_warning("Could not create debugfs 'iter_ctrl' entry\n"); + + entry = debugfs_create_file("tracing_cpumask", 0644, d_tracer, + NULL, &tracing_cpumask_fops); + if (!entry) + pr_warning("Could not create debugfs 'tracing_cpumask' entry\n"); + + entry = debugfs_create_file("latency_trace", 0444, d_tracer, + &global_trace, &tracing_lt_fops); + if (!entry) + pr_warning("Could not create debugfs 'latency_trace' entry\n"); + + entry = debugfs_create_file("trace", 0444, d_tracer, + &global_trace, &tracing_fops); + if (!entry) + pr_warning("Could not create debugfs 'trace' entry\n"); + + entry = debugfs_create_file("available_tracers", 0444, d_tracer, + &global_trace, &show_traces_fops); + if (!entry) + pr_warning("Could not create debugfs 'trace' entry\n"); + + entry = debugfs_create_file("current_tracer", 0444, d_tracer, + &global_trace, &set_tracer_fops); + if (!entry) + pr_warning("Could not create debugfs 'trace' entry\n"); + + entry = debugfs_create_file("tracing_max_latency", 0644, d_tracer, + &tracing_max_latency, + &tracing_max_lat_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'tracing_max_latency' entry\n"); + + entry = debugfs_create_file("tracing_thresh", 0644, d_tracer, + &tracing_thresh, &tracing_max_lat_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'tracing_threash' entry\n"); + entry = debugfs_create_file("README", 0644, d_tracer, + NULL, &tracing_readme_fops); + if (!entry) + pr_warning("Could not create debugfs 'README' entry\n"); + + entry = debugfs_create_file("trace_pipe", 0644, d_tracer, + NULL, &tracing_pipe_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'tracing_threash' entry\n"); + + entry = debugfs_create_file("trace_entries", 0644, d_tracer, + &global_trace, &tracing_entries_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'tracing_threash' entry\n"); + +#ifdef CONFIG_DYNAMIC_FTRACE + entry = debugfs_create_file("dyn_ftrace_total_info", 0444, d_tracer, + &ftrace_update_tot_cnt, + &tracing_read_long_fops); + if (!entry) + pr_warning("Could not create debugfs " + "'dyn_ftrace_total_info' entry\n"); +#endif +#ifdef CONFIG_SYSPROF_TRACER + init_tracer_sysprof_debugfs(d_tracer); +#endif +} + +static int trace_alloc_page(void) +{ + struct trace_array_cpu *data; + struct page *page, *tmp; + LIST_HEAD(pages); + void *array; + unsigned pages_allocated = 0; + int i; + + /* first allocate a page for each CPU */ + for_each_tracing_cpu(i) { + array = (void *)__get_free_page(GFP_KERNEL); + if (array == NULL) { + printk(KERN_ERR "tracer: failed to allocate page" + "for trace buffer!\n"); + goto free_pages; + } + + pages_allocated++; + page = virt_to_page(array); + list_add(&page->lru, &pages); + +/* Only allocate if we are actually using the max trace */ +#ifdef CONFIG_TRACER_MAX_TRACE + array = (void *)__get_free_page(GFP_KERNEL); + if (array == NULL) { + printk(KERN_ERR "tracer: failed to allocate page" + "for trace buffer!\n"); + goto free_pages; + } + pages_allocated++; + page = virt_to_page(array); + list_add(&page->lru, &pages); +#endif + } + + /* Now that we successfully allocate a page per CPU, add them */ + for_each_tracing_cpu(i) { + data = global_trace.data[i]; + page = list_entry(pages.next, struct page, lru); + list_del_init(&page->lru); + list_add_tail(&page->lru, &data->trace_pages); + ClearPageLRU(page); + +#ifdef CONFIG_TRACER_MAX_TRACE + data = max_tr.data[i]; + page = list_entry(pages.next, struct page, lru); + list_del_init(&page->lru); + list_add_tail(&page->lru, &data->trace_pages); + SetPageLRU(page); +#endif + } + tracing_pages_allocated += pages_allocated; + global_trace.entries += ENTRIES_PER_PAGE; + + return 0; + + free_pages: + list_for_each_entry_safe(page, tmp, &pages, lru) { + list_del_init(&page->lru); + __free_page(page); + } + return -ENOMEM; +} + +static int trace_free_page(void) +{ + struct trace_array_cpu *data; + struct page *page; + struct list_head *p; + int i; + int ret = 0; + + /* free one page from each buffer */ + for_each_tracing_cpu(i) { + data = global_trace.data[i]; + p = data->trace_pages.next; + if (p == &data->trace_pages) { + /* should never happen */ + WARN_ON(1); + tracing_disabled = 1; + ret = -1; + break; + } + page = list_entry(p, struct page, lru); + ClearPageLRU(page); + list_del(&page->lru); + tracing_pages_allocated--; + tracing_pages_allocated--; + __free_page(page); + + tracing_reset(data); + +#ifdef CONFIG_TRACER_MAX_TRACE + data = max_tr.data[i]; + p = data->trace_pages.next; + if (p == &data->trace_pages) { + /* should never happen */ + WARN_ON(1); + tracing_disabled = 1; + ret = -1; + break; + } + page = list_entry(p, struct page, lru); + ClearPageLRU(page); + list_del(&page->lru); + __free_page(page); + + tracing_reset(data); +#endif + } + global_trace.entries -= ENTRIES_PER_PAGE; + + return ret; +} + +__init static int tracer_alloc_buffers(void) +{ + struct trace_array_cpu *data; + void *array; + struct page *page; + int pages = 0; + int ret = -ENOMEM; + int i; + + /* TODO: make the number of buffers hot pluggable with CPUS */ + tracing_nr_buffers = num_possible_cpus(); + tracing_buffer_mask = cpu_possible_map; + + /* Allocate the first page for all buffers */ + for_each_tracing_cpu(i) { + data = global_trace.data[i] = &per_cpu(global_trace_cpu, i); + max_tr.data[i] = &per_cpu(max_data, i); + + array = (void *)__get_free_page(GFP_KERNEL); + if (array == NULL) { + printk(KERN_ERR "tracer: failed to allocate page" + "for trace buffer!\n"); + goto free_buffers; + } + + /* set the array to the list */ + INIT_LIST_HEAD(&data->trace_pages); + page = virt_to_page(array); + list_add(&page->lru, &data->trace_pages); + /* use the LRU flag to differentiate the two buffers */ + ClearPageLRU(page); + + data->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; + max_tr.data[i]->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED; + +/* Only allocate if we are actually using the max trace */ +#ifdef CONFIG_TRACER_MAX_TRACE + array = (void *)__get_free_page(GFP_KERNEL); + if (array == NULL) { + printk(KERN_ERR "tracer: failed to allocate page" + "for trace buffer!\n"); + goto free_buffers; + } + + INIT_LIST_HEAD(&max_tr.data[i]->trace_pages); + page = virt_to_page(array); + list_add(&page->lru, &max_tr.data[i]->trace_pages); + SetPageLRU(page); +#endif + } + + /* + * Since we allocate by orders of pages, we may be able to + * round up a bit. + */ + global_trace.entries = ENTRIES_PER_PAGE; + pages++; + + while (global_trace.entries < trace_nr_entries) { + if (trace_alloc_page()) + break; + pages++; + } + max_tr.entries = global_trace.entries; + + pr_info("tracer: %d pages allocated for %ld entries of %ld bytes\n", + pages, trace_nr_entries, (long)TRACE_ENTRY_SIZE); + pr_info(" actual entries %ld\n", global_trace.entries); + + tracer_init_debugfs(); + + trace_init_cmdlines(); + + register_tracer(&no_tracer); + current_trace = &no_tracer; + + /* All seems OK, enable tracing */ + global_trace.ctrl = tracer_enabled; + tracing_disabled = 0; + + return 0; + + free_buffers: + for (i-- ; i >= 0; i--) { + struct page *page, *tmp; + struct trace_array_cpu *data = global_trace.data[i]; + + if (data) { + list_for_each_entry_safe(page, tmp, + &data->trace_pages, lru) { + list_del_init(&page->lru); + __free_page(page); + } + } + +#ifdef CONFIG_TRACER_MAX_TRACE + data = max_tr.data[i]; + if (data) { + list_for_each_entry_safe(page, tmp, + &data->trace_pages, lru) { + list_del_init(&page->lru); + __free_page(page); + } + } +#endif + } + return ret; +} +fs_initcall(tracer_alloc_buffers); diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h new file mode 100644 index 00000000000..f69f86788c2 --- /dev/null +++ b/kernel/trace/trace.h @@ -0,0 +1,339 @@ +#ifndef _LINUX_KERNEL_TRACE_H +#define _LINUX_KERNEL_TRACE_H + +#include <linux/fs.h> +#include <asm/atomic.h> +#include <linux/sched.h> +#include <linux/clocksource.h> +#include <linux/mmiotrace.h> + +enum trace_type { + __TRACE_FIRST_TYPE = 0, + + TRACE_FN, + TRACE_CTX, + TRACE_WAKE, + TRACE_STACK, + TRACE_SPECIAL, + TRACE_MMIO_RW, + TRACE_MMIO_MAP, + + __TRACE_LAST_TYPE +}; + +/* + * Function trace entry - function address and parent function addres: + */ +struct ftrace_entry { + unsigned long ip; + unsigned long parent_ip; +}; + +/* + * Context switch trace entry - which task (and prio) we switched from/to: + */ +struct ctx_switch_entry { + unsigned int prev_pid; + unsigned char prev_prio; + unsigned char prev_state; + unsigned int next_pid; + unsigned char next_prio; + unsigned char next_state; +}; + +/* + * Special (free-form) trace entry: + */ +struct special_entry { + unsigned long arg1; + unsigned long arg2; + unsigned long arg3; +}; + +/* + * Stack-trace entry: + */ + +#define FTRACE_STACK_ENTRIES 8 + +struct stack_entry { + unsigned long caller[FTRACE_STACK_ENTRIES]; +}; + +/* + * The trace entry - the most basic unit of tracing. This is what + * is printed in the end as a single line in the trace output, such as: + * + * bash-15816 [01] 235.197585: idle_cpu <- irq_enter + */ +struct trace_entry { + char type; + char cpu; + char flags; + char preempt_count; + int pid; + cycle_t t; + union { + struct ftrace_entry fn; + struct ctx_switch_entry ctx; + struct special_entry special; + struct stack_entry stack; + struct mmiotrace_rw mmiorw; + struct mmiotrace_map mmiomap; + }; +}; + +#define TRACE_ENTRY_SIZE sizeof(struct trace_entry) + +/* + * The CPU trace array - it consists of thousands of trace entries + * plus some other descriptor data: (for example which task started + * the trace, etc.) + */ +struct trace_array_cpu { + struct list_head trace_pages; + atomic_t disabled; + raw_spinlock_t lock; + struct lock_class_key lock_key; + + /* these fields get copied into max-trace: */ + unsigned trace_head_idx; + unsigned trace_tail_idx; + void *trace_head; /* producer */ + void *trace_tail; /* consumer */ + unsigned long trace_idx; + unsigned long overrun; + unsigned long saved_latency; + unsigned long critical_start; + unsigned long critical_end; + unsigned long critical_sequence; + unsigned long nice; + unsigned long policy; + unsigned long rt_priority; + cycle_t preempt_timestamp; + pid_t pid; + uid_t uid; + char comm[TASK_COMM_LEN]; +}; + +struct trace_iterator; + +/* + * The trace array - an array of per-CPU trace arrays. This is the + * highest level data structure that individual tracers deal with. + * They have on/off state as well: + */ +struct trace_array { + unsigned long entries; + long ctrl; + int cpu; + cycle_t time_start; + struct task_struct *waiter; + struct trace_array_cpu *data[NR_CPUS]; +}; + +/* + * A specific tracer, represented by methods that operate on a trace array: + */ +struct tracer { + const char *name; + void (*init)(struct trace_array *tr); + void (*reset)(struct trace_array *tr); + void (*open)(struct trace_iterator *iter); + void (*pipe_open)(struct trace_iterator *iter); + void (*close)(struct trace_iterator *iter); + void (*start)(struct trace_iterator *iter); + void (*stop)(struct trace_iterator *iter); + ssize_t (*read)(struct trace_iterator *iter, + struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos); + void (*ctrl_update)(struct trace_array *tr); +#ifdef CONFIG_FTRACE_STARTUP_TEST + int (*selftest)(struct tracer *trace, + struct trace_array *tr); +#endif + int (*print_line)(struct trace_iterator *iter); + struct tracer *next; + int print_max; +}; + +struct trace_seq { + unsigned char buffer[PAGE_SIZE]; + unsigned int len; + unsigned int readpos; +}; + +/* + * Trace iterator - used by printout routines who present trace + * results to users and which routines might sleep, etc: + */ +struct trace_iterator { + struct trace_array *tr; + struct tracer *trace; + void *private; + long last_overrun[NR_CPUS]; + long overrun[NR_CPUS]; + + /* The below is zeroed out in pipe_read */ + struct trace_seq seq; + struct trace_entry *ent; + int cpu; + + struct trace_entry *prev_ent; + int prev_cpu; + + unsigned long iter_flags; + loff_t pos; + unsigned long next_idx[NR_CPUS]; + struct list_head *next_page[NR_CPUS]; + unsigned next_page_idx[NR_CPUS]; + long idx; +}; + +void tracing_reset(struct trace_array_cpu *data); +int tracing_open_generic(struct inode *inode, struct file *filp); +struct dentry *tracing_init_dentry(void); +void init_tracer_sysprof_debugfs(struct dentry *d_tracer); + +void ftrace(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long ip, + unsigned long parent_ip, + unsigned long flags); +void tracing_sched_switch_trace(struct trace_array *tr, + struct trace_array_cpu *data, + struct task_struct *prev, + struct task_struct *next, + unsigned long flags); +void tracing_record_cmdline(struct task_struct *tsk); + +void tracing_sched_wakeup_trace(struct trace_array *tr, + struct trace_array_cpu *data, + struct task_struct *wakee, + struct task_struct *cur, + unsigned long flags); +void trace_special(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long arg1, + unsigned long arg2, + unsigned long arg3); +void trace_function(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long ip, + unsigned long parent_ip, + unsigned long flags); + +void tracing_start_cmdline_record(void); +void tracing_stop_cmdline_record(void); +int register_tracer(struct tracer *type); +void unregister_tracer(struct tracer *type); + +extern unsigned long nsecs_to_usecs(unsigned long nsecs); + +extern unsigned long tracing_max_latency; +extern unsigned long tracing_thresh; + +void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu); +void update_max_tr_single(struct trace_array *tr, + struct task_struct *tsk, int cpu); + +extern cycle_t ftrace_now(int cpu); + +#ifdef CONFIG_FTRACE +void tracing_start_function_trace(void); +void tracing_stop_function_trace(void); +#else +# define tracing_start_function_trace() do { } while (0) +# define tracing_stop_function_trace() do { } while (0) +#endif + +#ifdef CONFIG_CONTEXT_SWITCH_TRACER +typedef void +(*tracer_switch_func_t)(void *private, + void *__rq, + struct task_struct *prev, + struct task_struct *next); + +struct tracer_switch_ops { + tracer_switch_func_t func; + void *private; + struct tracer_switch_ops *next; +}; + +#endif /* CONFIG_CONTEXT_SWITCH_TRACER */ + +#ifdef CONFIG_DYNAMIC_FTRACE +extern unsigned long ftrace_update_tot_cnt; +#define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func +extern int DYN_FTRACE_TEST_NAME(void); +#endif + +#ifdef CONFIG_MMIOTRACE +extern void __trace_mmiotrace_rw(struct trace_array *tr, + struct trace_array_cpu *data, + struct mmiotrace_rw *rw); +extern void __trace_mmiotrace_map(struct trace_array *tr, + struct trace_array_cpu *data, + struct mmiotrace_map *map); +#endif + +#ifdef CONFIG_FTRACE_STARTUP_TEST +#ifdef CONFIG_FTRACE +extern int trace_selftest_startup_function(struct tracer *trace, + struct trace_array *tr); +#endif +#ifdef CONFIG_IRQSOFF_TRACER +extern int trace_selftest_startup_irqsoff(struct tracer *trace, + struct trace_array *tr); +#endif +#ifdef CONFIG_PREEMPT_TRACER +extern int trace_selftest_startup_preemptoff(struct tracer *trace, + struct trace_array *tr); +#endif +#if defined(CONFIG_IRQSOFF_TRACER) && defined(CONFIG_PREEMPT_TRACER) +extern int trace_selftest_startup_preemptirqsoff(struct tracer *trace, + struct trace_array *tr); +#endif +#ifdef CONFIG_SCHED_TRACER +extern int trace_selftest_startup_wakeup(struct tracer *trace, + struct trace_array *tr); +#endif +#ifdef CONFIG_CONTEXT_SWITCH_TRACER +extern int trace_selftest_startup_sched_switch(struct tracer *trace, + struct trace_array *tr); +#endif +#ifdef CONFIG_SYSPROF_TRACER +extern int trace_selftest_startup_sysprof(struct tracer *trace, + struct trace_array *tr); +#endif +#endif /* CONFIG_FTRACE_STARTUP_TEST */ + +extern void *head_page(struct trace_array_cpu *data); +extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...); +extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, + size_t cnt); +extern long ns2usecs(cycle_t nsec); + +extern unsigned long trace_flags; + +/* + * trace_iterator_flags is an enumeration that defines bit + * positions into trace_flags that controls the output. + * + * NOTE: These bits must match the trace_options array in + * trace.c. + */ +enum trace_iterator_flags { + TRACE_ITER_PRINT_PARENT = 0x01, + TRACE_ITER_SYM_OFFSET = 0x02, + TRACE_ITER_SYM_ADDR = 0x04, + TRACE_ITER_VERBOSE = 0x08, + TRACE_ITER_RAW = 0x10, + TRACE_ITER_HEX = 0x20, + TRACE_ITER_BIN = 0x40, + TRACE_ITER_BLOCK = 0x80, + TRACE_ITER_STACKTRACE = 0x100, + TRACE_ITER_SCHED_TREE = 0x200, +}; + +#endif /* _LINUX_KERNEL_TRACE_H */ diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c new file mode 100644 index 00000000000..31214489797 --- /dev/null +++ b/kernel/trace/trace_functions.c @@ -0,0 +1,81 @@ +/* + * ring buffer based function tracer + * + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> + * + * Based on code from the latency_tracer, that is: + * + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 William Lee Irwin III + */ +#include <linux/debugfs.h> +#include <linux/uaccess.h> +#include <linux/ftrace.h> +#include <linux/fs.h> + +#include "trace.h" + +static void function_reset(struct trace_array *tr) +{ + int cpu; + + tr->time_start = ftrace_now(tr->cpu); + + for_each_online_cpu(cpu) + tracing_reset(tr->data[cpu]); +} + +static void start_function_trace(struct trace_array *tr) +{ + tr->cpu = get_cpu(); + function_reset(tr); + put_cpu(); + + tracing_start_cmdline_record(); + tracing_start_function_trace(); +} + +static void stop_function_trace(struct trace_array *tr) +{ + tracing_stop_function_trace(); + tracing_stop_cmdline_record(); +} + +static void function_trace_init(struct trace_array *tr) +{ + if (tr->ctrl) + start_function_trace(tr); +} + +static void function_trace_reset(struct trace_array *tr) +{ + if (tr->ctrl) + stop_function_trace(tr); +} + +static void function_trace_ctrl_update(struct trace_array *tr) +{ + if (tr->ctrl) + start_function_trace(tr); + else + stop_function_trace(tr); +} + +static struct tracer function_trace __read_mostly = +{ + .name = "ftrace", + .init = function_trace_init, + .reset = function_trace_reset, + .ctrl_update = function_trace_ctrl_update, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_function, +#endif +}; + +static __init int init_function_trace(void) +{ + return register_tracer(&function_trace); +} + +device_initcall(init_function_trace); diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c new file mode 100644 index 00000000000..421d6fe3650 --- /dev/null +++ b/kernel/trace/trace_irqsoff.c @@ -0,0 +1,486 @@ +/* + * trace irqs off criticall timings + * + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> + * + * From code in the latency_tracer, that is: + * + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 William Lee Irwin III + */ +#include <linux/kallsyms.h> +#include <linux/debugfs.h> +#include <linux/uaccess.h> +#include <linux/module.h> +#include <linux/ftrace.h> +#include <linux/fs.h> + +#include "trace.h" + +static struct trace_array *irqsoff_trace __read_mostly; +static int tracer_enabled __read_mostly; + +static DEFINE_PER_CPU(int, tracing_cpu); + +static DEFINE_SPINLOCK(max_trace_lock); + +enum { + TRACER_IRQS_OFF = (1 << 1), + TRACER_PREEMPT_OFF = (1 << 2), +}; + +static int trace_type __read_mostly; + +#ifdef CONFIG_PREEMPT_TRACER +static inline int +preempt_trace(void) +{ + return ((trace_type & TRACER_PREEMPT_OFF) && preempt_count()); +} +#else +# define preempt_trace() (0) +#endif + +#ifdef CONFIG_IRQSOFF_TRACER +static inline int +irq_trace(void) +{ + return ((trace_type & TRACER_IRQS_OFF) && + irqs_disabled()); +} +#else +# define irq_trace() (0) +#endif + +/* + * Sequence count - we record it when starting a measurement and + * skip the latency if the sequence has changed - some other section + * did a maximum and could disturb our measurement with serial console + * printouts, etc. Truly coinciding maximum latencies should be rare + * and what happens together happens separately as well, so this doesnt + * decrease the validity of the maximum found: + */ +static __cacheline_aligned_in_smp unsigned long max_sequence; + +#ifdef CONFIG_FTRACE +/* + * irqsoff uses its own tracer function to keep the overhead down: + */ +static void +irqsoff_tracer_call(unsigned long ip, unsigned long parent_ip) +{ + struct trace_array *tr = irqsoff_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + + /* + * Does not matter if we preempt. We test the flags + * afterward, to see if irqs are disabled or not. + * If we preempt and get a false positive, the flags + * test will fail. + */ + cpu = raw_smp_processor_id(); + if (likely(!per_cpu(tracing_cpu, cpu))) + return; + + local_save_flags(flags); + /* slight chance to get a false positive on tracing_cpu */ + if (!irqs_disabled_flags(flags)) + return; + + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) + trace_function(tr, data, ip, parent_ip, flags); + + atomic_dec(&data->disabled); +} + +static struct ftrace_ops trace_ops __read_mostly = +{ + .func = irqsoff_tracer_call, +}; +#endif /* CONFIG_FTRACE */ + +/* + * Should this new latency be reported/recorded? + */ +static int report_latency(cycle_t delta) +{ + if (tracing_thresh) { + if (delta < tracing_thresh) + return 0; + } else { + if (delta <= tracing_max_latency) + return 0; + } + return 1; +} + +static void +check_critical_timing(struct trace_array *tr, + struct trace_array_cpu *data, + unsigned long parent_ip, + int cpu) +{ + unsigned long latency, t0, t1; + cycle_t T0, T1, delta; + unsigned long flags; + + /* + * usecs conversion is slow so we try to delay the conversion + * as long as possible: + */ + T0 = data->preempt_timestamp; + T1 = ftrace_now(cpu); + delta = T1-T0; + + local_save_flags(flags); + + if (!report_latency(delta)) + goto out; + + spin_lock_irqsave(&max_trace_lock, flags); + + /* check if we are still the max latency */ + if (!report_latency(delta)) + goto out_unlock; + + trace_function(tr, data, CALLER_ADDR0, parent_ip, flags); + + latency = nsecs_to_usecs(delta); + + if (data->critical_sequence != max_sequence) + goto out_unlock; + + tracing_max_latency = delta; + t0 = nsecs_to_usecs(T0); + t1 = nsecs_to_usecs(T1); + + data->critical_end = parent_ip; + + update_max_tr_single(tr, current, cpu); + + max_sequence++; + +out_unlock: + spin_unlock_irqrestore(&max_trace_lock, flags); + +out: + data->critical_sequence = max_sequence; + data->preempt_timestamp = ftrace_now(cpu); + tracing_reset(data); + trace_function(tr, data, CALLER_ADDR0, parent_ip, flags); +} + +static inline void +start_critical_timing(unsigned long ip, unsigned long parent_ip) +{ + int cpu; + struct trace_array *tr = irqsoff_trace; + struct trace_array_cpu *data; + unsigned long flags; + + if (likely(!tracer_enabled)) + return; + + cpu = raw_smp_processor_id(); + + if (per_cpu(tracing_cpu, cpu)) + return; + + data = tr->data[cpu]; + + if (unlikely(!data) || atomic_read(&data->disabled)) + return; + + atomic_inc(&data->disabled); + + data->critical_sequence = max_sequence; + data->preempt_timestamp = ftrace_now(cpu); + data->critical_start = parent_ip ? : ip; + tracing_reset(data); + + local_save_flags(flags); + + trace_function(tr, data, ip, parent_ip, flags); + + per_cpu(tracing_cpu, cpu) = 1; + + atomic_dec(&data->disabled); +} + +static inline void +stop_critical_timing(unsigned long ip, unsigned long parent_ip) +{ + int cpu; + struct trace_array *tr = irqsoff_trace; + struct trace_array_cpu *data; + unsigned long flags; + + cpu = raw_smp_processor_id(); + /* Always clear the tracing cpu on stopping the trace */ + if (unlikely(per_cpu(tracing_cpu, cpu))) + per_cpu(tracing_cpu, cpu) = 0; + else + return; + + if (!tracer_enabled) + return; + + data = tr->data[cpu]; + + if (unlikely(!data) || unlikely(!head_page(data)) || + !data->critical_start || atomic_read(&data->disabled)) + return; + + atomic_inc(&data->disabled); + + local_save_flags(flags); + trace_function(tr, data, ip, parent_ip, flags); + check_critical_timing(tr, data, parent_ip ? : ip, cpu); + data->critical_start = 0; + atomic_dec(&data->disabled); +} + +/* start and stop critical timings used to for stoppage (in idle) */ +void start_critical_timings(void) +{ + if (preempt_trace() || irq_trace()) + start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); +} + +void stop_critical_timings(void) +{ + if (preempt_trace() || irq_trace()) + stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); +} + +#ifdef CONFIG_IRQSOFF_TRACER +#ifdef CONFIG_PROVE_LOCKING +void time_hardirqs_on(unsigned long a0, unsigned long a1) +{ + if (!preempt_trace() && irq_trace()) + stop_critical_timing(a0, a1); +} + +void time_hardirqs_off(unsigned long a0, unsigned long a1) +{ + if (!preempt_trace() && irq_trace()) + start_critical_timing(a0, a1); +} + +#else /* !CONFIG_PROVE_LOCKING */ + +/* + * Stubs: + */ + +void early_boot_irqs_off(void) +{ +} + +void early_boot_irqs_on(void) +{ +} + +void trace_softirqs_on(unsigned long ip) +{ +} + +void trace_softirqs_off(unsigned long ip) +{ +} + +inline void print_irqtrace_events(struct task_struct *curr) +{ +} + +/* + * We are only interested in hardirq on/off events: + */ +void trace_hardirqs_on(void) +{ + if (!preempt_trace() && irq_trace()) + stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1); +} +EXPORT_SYMBOL(trace_hardirqs_on); + +void trace_hardirqs_off(void) +{ + if (!preempt_trace() && irq_trace()) + start_critical_timing(CALLER_ADDR0, CALLER_ADDR1); +} +EXPORT_SYMBOL(trace_hardirqs_off); + +void trace_hardirqs_on_caller(unsigned long caller_addr) +{ + if (!preempt_trace() && irq_trace()) + stop_critical_timing(CALLER_ADDR0, caller_addr); +} +EXPORT_SYMBOL(trace_hardirqs_on_caller); + +void trace_hardirqs_off_caller(unsigned long caller_addr) +{ + if (!preempt_trace() && irq_trace()) + start_critical_timing(CALLER_ADDR0, caller_addr); +} +EXPORT_SYMBOL(trace_hardirqs_off_caller); + +#endif /* CONFIG_PROVE_LOCKING */ +#endif /* CONFIG_IRQSOFF_TRACER */ + +#ifdef CONFIG_PREEMPT_TRACER +void trace_preempt_on(unsigned long a0, unsigned long a1) +{ + stop_critical_timing(a0, a1); +} + +void trace_preempt_off(unsigned long a0, unsigned long a1) +{ + start_critical_timing(a0, a1); +} +#endif /* CONFIG_PREEMPT_TRACER */ + +static void start_irqsoff_tracer(struct trace_array *tr) +{ + register_ftrace_function(&trace_ops); + tracer_enabled = 1; +} + +static void stop_irqsoff_tracer(struct trace_array *tr) +{ + tracer_enabled = 0; + unregister_ftrace_function(&trace_ops); +} + +static void __irqsoff_tracer_init(struct trace_array *tr) +{ + irqsoff_trace = tr; + /* make sure that the tracer is visible */ + smp_wmb(); + + if (tr->ctrl) + start_irqsoff_tracer(tr); +} + +static void irqsoff_tracer_reset(struct trace_array *tr) +{ + if (tr->ctrl) + stop_irqsoff_tracer(tr); +} + +static void irqsoff_tracer_ctrl_update(struct trace_array *tr) +{ + if (tr->ctrl) + start_irqsoff_tracer(tr); + else + stop_irqsoff_tracer(tr); +} + +static void irqsoff_tracer_open(struct trace_iterator *iter) +{ + /* stop the trace while dumping */ + if (iter->tr->ctrl) + stop_irqsoff_tracer(iter->tr); +} + +static void irqsoff_tracer_close(struct trace_iterator *iter) +{ + if (iter->tr->ctrl) + start_irqsoff_tracer(iter->tr); +} + +#ifdef CONFIG_IRQSOFF_TRACER +static void irqsoff_tracer_init(struct trace_array *tr) +{ + trace_type = TRACER_IRQS_OFF; + + __irqsoff_tracer_init(tr); +} +static struct tracer irqsoff_tracer __read_mostly = +{ + .name = "irqsoff", + .init = irqsoff_tracer_init, + .reset = irqsoff_tracer_reset, + .open = irqsoff_tracer_open, + .close = irqsoff_tracer_close, + .ctrl_update = irqsoff_tracer_ctrl_update, + .print_max = 1, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_irqsoff, +#endif +}; +# define register_irqsoff(trace) register_tracer(&trace) +#else +# define register_irqsoff(trace) do { } while (0) +#endif + +#ifdef CONFIG_PREEMPT_TRACER +static void preemptoff_tracer_init(struct trace_array *tr) +{ + trace_type = TRACER_PREEMPT_OFF; + + __irqsoff_tracer_init(tr); +} + +static struct tracer preemptoff_tracer __read_mostly = +{ + .name = "preemptoff", + .init = preemptoff_tracer_init, + .reset = irqsoff_tracer_reset, + .open = irqsoff_tracer_open, + .close = irqsoff_tracer_close, + .ctrl_update = irqsoff_tracer_ctrl_update, + .print_max = 1, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_preemptoff, +#endif +}; +# define register_preemptoff(trace) register_tracer(&trace) +#else +# define register_preemptoff(trace) do { } while (0) +#endif + +#if defined(CONFIG_IRQSOFF_TRACER) && \ + defined(CONFIG_PREEMPT_TRACER) + +static void preemptirqsoff_tracer_init(struct trace_array *tr) +{ + trace_type = TRACER_IRQS_OFF | TRACER_PREEMPT_OFF; + + __irqsoff_tracer_init(tr); +} + +static struct tracer preemptirqsoff_tracer __read_mostly = +{ + .name = "preemptirqsoff", + .init = preemptirqsoff_tracer_init, + .reset = irqsoff_tracer_reset, + .open = irqsoff_tracer_open, + .close = irqsoff_tracer_close, + .ctrl_update = irqsoff_tracer_ctrl_update, + .print_max = 1, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_preemptirqsoff, +#endif +}; + +# define register_preemptirqsoff(trace) register_tracer(&trace) +#else +# define register_preemptirqsoff(trace) do { } while (0) +#endif + +__init static int init_irqsoff_tracer(void) +{ + register_irqsoff(irqsoff_tracer); + register_preemptoff(preemptoff_tracer); + register_preemptirqsoff(preemptirqsoff_tracer); + + return 0; +} +device_initcall(init_irqsoff_tracer); diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c new file mode 100644 index 00000000000..b13dc19dcbb --- /dev/null +++ b/kernel/trace/trace_mmiotrace.c @@ -0,0 +1,295 @@ +/* + * Memory mapped I/O tracing + * + * Copyright (C) 2008 Pekka Paalanen <pq@iki.fi> + */ + +#define DEBUG 1 + +#include <linux/kernel.h> +#include <linux/mmiotrace.h> +#include <linux/pci.h> + +#include "trace.h" + +struct header_iter { + struct pci_dev *dev; +}; + +static struct trace_array *mmio_trace_array; +static bool overrun_detected; + +static void mmio_reset_data(struct trace_array *tr) +{ + int cpu; + + overrun_detected = false; + tr->time_start = ftrace_now(tr->cpu); + + for_each_online_cpu(cpu) + tracing_reset(tr->data[cpu]); +} + +static void mmio_trace_init(struct trace_array *tr) +{ + pr_debug("in %s\n", __func__); + mmio_trace_array = tr; + if (tr->ctrl) { + mmio_reset_data(tr); + enable_mmiotrace(); + } +} + +static void mmio_trace_reset(struct trace_array *tr) +{ + pr_debug("in %s\n", __func__); + if (tr->ctrl) + disable_mmiotrace(); + mmio_reset_data(tr); + mmio_trace_array = NULL; +} + +static void mmio_trace_ctrl_update(struct trace_array *tr) +{ + pr_debug("in %s\n", __func__); + if (tr->ctrl) { + mmio_reset_data(tr); + enable_mmiotrace(); + } else { + disable_mmiotrace(); + } +} + +static int mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev) +{ + int ret = 0; + int i; + resource_size_t start, end; + const struct pci_driver *drv = pci_dev_driver(dev); + + /* XXX: incomplete checks for trace_seq_printf() return value */ + ret += trace_seq_printf(s, "PCIDEV %02x%02x %04x%04x %x", + dev->bus->number, dev->devfn, + dev->vendor, dev->device, dev->irq); + /* + * XXX: is pci_resource_to_user() appropriate, since we are + * supposed to interpret the __ioremap() phys_addr argument based on + * these printed values? + */ + for (i = 0; i < 7; i++) { + pci_resource_to_user(dev, i, &dev->resource[i], &start, &end); + ret += trace_seq_printf(s, " %llx", + (unsigned long long)(start | + (dev->resource[i].flags & PCI_REGION_FLAG_MASK))); + } + for (i = 0; i < 7; i++) { + pci_resource_to_user(dev, i, &dev->resource[i], &start, &end); + ret += trace_seq_printf(s, " %llx", + dev->resource[i].start < dev->resource[i].end ? + (unsigned long long)(end - start) + 1 : 0); + } + if (drv) + ret += trace_seq_printf(s, " %s\n", drv->name); + else + ret += trace_seq_printf(s, " \n"); + return ret; +} + +static void destroy_header_iter(struct header_iter *hiter) +{ + if (!hiter) + return; + pci_dev_put(hiter->dev); + kfree(hiter); +} + +static void mmio_pipe_open(struct trace_iterator *iter) +{ + struct header_iter *hiter; + struct trace_seq *s = &iter->seq; + + trace_seq_printf(s, "VERSION 20070824\n"); + + hiter = kzalloc(sizeof(*hiter), GFP_KERNEL); + if (!hiter) + return; + + hiter->dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, NULL); + iter->private = hiter; +} + +/* XXX: This is not called when the pipe is closed! */ +static void mmio_close(struct trace_iterator *iter) +{ + struct header_iter *hiter = iter->private; + destroy_header_iter(hiter); + iter->private = NULL; +} + +static unsigned long count_overruns(struct trace_iterator *iter) +{ + int cpu; + unsigned long cnt = 0; + for_each_online_cpu(cpu) { + cnt += iter->overrun[cpu]; + iter->overrun[cpu] = 0; + } + return cnt; +} + +static ssize_t mmio_read(struct trace_iterator *iter, struct file *filp, + char __user *ubuf, size_t cnt, loff_t *ppos) +{ + ssize_t ret; + struct header_iter *hiter = iter->private; + struct trace_seq *s = &iter->seq; + unsigned long n; + + n = count_overruns(iter); + if (n) { + /* XXX: This is later than where events were lost. */ + trace_seq_printf(s, "MARK 0.000000 Lost %lu events.\n", n); + if (!overrun_detected) + pr_warning("mmiotrace has lost events.\n"); + overrun_detected = true; + goto print_out; + } + + if (!hiter) + return 0; + + mmio_print_pcidev(s, hiter->dev); + hiter->dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, hiter->dev); + + if (!hiter->dev) { + destroy_header_iter(hiter); + iter->private = NULL; + } + +print_out: + ret = trace_seq_to_user(s, ubuf, cnt); + return (ret == -EBUSY) ? 0 : ret; +} + +static int mmio_print_rw(struct trace_iterator *iter) +{ + struct trace_entry *entry = iter->ent; + struct mmiotrace_rw *rw = &entry->mmiorw; + struct trace_seq *s = &iter->seq; + unsigned long long t = ns2usecs(entry->t); + unsigned long usec_rem = do_div(t, 1000000ULL); + unsigned secs = (unsigned long)t; + int ret = 1; + + switch (entry->mmiorw.opcode) { + case MMIO_READ: + ret = trace_seq_printf(s, + "R %d %lu.%06lu %d 0x%llx 0x%lx 0x%lx %d\n", + rw->width, secs, usec_rem, rw->map_id, + (unsigned long long)rw->phys, + rw->value, rw->pc, 0); + break; + case MMIO_WRITE: + ret = trace_seq_printf(s, + "W %d %lu.%06lu %d 0x%llx 0x%lx 0x%lx %d\n", + rw->width, secs, usec_rem, rw->map_id, + (unsigned long long)rw->phys, + rw->value, rw->pc, 0); + break; + case MMIO_UNKNOWN_OP: + ret = trace_seq_printf(s, + "UNKNOWN %lu.%06lu %d 0x%llx %02x,%02x,%02x 0x%lx %d\n", + secs, usec_rem, rw->map_id, + (unsigned long long)rw->phys, + (rw->value >> 16) & 0xff, (rw->value >> 8) & 0xff, + (rw->value >> 0) & 0xff, rw->pc, 0); + break; + default: + ret = trace_seq_printf(s, "rw what?\n"); + break; + } + if (ret) + return 1; + return 0; +} + +static int mmio_print_map(struct trace_iterator *iter) +{ + struct trace_entry *entry = iter->ent; + struct mmiotrace_map *m = &entry->mmiomap; + struct trace_seq *s = &iter->seq; + unsigned long long t = ns2usecs(entry->t); + unsigned long usec_rem = do_div(t, 1000000ULL); + unsigned secs = (unsigned long)t; + int ret = 1; + + switch (entry->mmiorw.opcode) { + case MMIO_PROBE: + ret = trace_seq_printf(s, + "MAP %lu.%06lu %d 0x%llx 0x%lx 0x%lx 0x%lx %d\n", + secs, usec_rem, m->map_id, + (unsigned long long)m->phys, m->virt, m->len, + 0UL, 0); + break; + case MMIO_UNPROBE: + ret = trace_seq_printf(s, + "UNMAP %lu.%06lu %d 0x%lx %d\n", + secs, usec_rem, m->map_id, 0UL, 0); + break; + default: + ret = trace_seq_printf(s, "map what?\n"); + break; + } + if (ret) + return 1; + return 0; +} + +/* return 0 to abort printing without consuming current entry in pipe mode */ +static int mmio_print_line(struct trace_iterator *iter) +{ + switch (iter->ent->type) { + case TRACE_MMIO_RW: + return mmio_print_rw(iter); + case TRACE_MMIO_MAP: + return mmio_print_map(iter); + default: + return 1; /* ignore unknown entries */ + } +} + +static struct tracer mmio_tracer __read_mostly = +{ + .name = "mmiotrace", + .init = mmio_trace_init, + .reset = mmio_trace_reset, + .pipe_open = mmio_pipe_open, + .close = mmio_close, + .read = mmio_read, + .ctrl_update = mmio_trace_ctrl_update, + .print_line = mmio_print_line, +}; + +__init static int init_mmio_trace(void) +{ + return register_tracer(&mmio_tracer); +} +device_initcall(init_mmio_trace); + +void mmio_trace_rw(struct mmiotrace_rw *rw) +{ + struct trace_array *tr = mmio_trace_array; + struct trace_array_cpu *data = tr->data[smp_processor_id()]; + __trace_mmiotrace_rw(tr, data, rw); +} + +void mmio_trace_mapping(struct mmiotrace_map *map) +{ + struct trace_array *tr = mmio_trace_array; + struct trace_array_cpu *data; + + preempt_disable(); + data = tr->data[smp_processor_id()]; + __trace_mmiotrace_map(tr, data, map); + preempt_enable(); +} diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c new file mode 100644 index 00000000000..cb817a209aa --- /dev/null +++ b/kernel/trace/trace_sched_switch.c @@ -0,0 +1,286 @@ +/* + * trace context switch + * + * Copyright (C) 2007 Steven Rostedt <srostedt@redhat.com> + * + */ +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/debugfs.h> +#include <linux/kallsyms.h> +#include <linux/uaccess.h> +#include <linux/marker.h> +#include <linux/ftrace.h> + +#include "trace.h" + +static struct trace_array *ctx_trace; +static int __read_mostly tracer_enabled; +static atomic_t sched_ref; + +static void +sched_switch_func(void *private, void *__rq, struct task_struct *prev, + struct task_struct *next) +{ + struct trace_array **ptr = private; + struct trace_array *tr = *ptr; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + + tracing_record_cmdline(prev); + tracing_record_cmdline(next); + + if (!tracer_enabled) + return; + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) + tracing_sched_switch_trace(tr, data, prev, next, flags); + + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + +static notrace void +sched_switch_callback(void *probe_data, void *call_data, + const char *format, va_list *args) +{ + struct task_struct *prev; + struct task_struct *next; + struct rq *__rq; + + if (!atomic_read(&sched_ref)) + return; + + /* skip prev_pid %d next_pid %d prev_state %ld */ + (void)va_arg(*args, int); + (void)va_arg(*args, int); + (void)va_arg(*args, long); + __rq = va_arg(*args, typeof(__rq)); + prev = va_arg(*args, typeof(prev)); + next = va_arg(*args, typeof(next)); + + /* + * If tracer_switch_func only points to the local + * switch func, it still needs the ptr passed to it. + */ + sched_switch_func(probe_data, __rq, prev, next); +} + +static void +wakeup_func(void *private, void *__rq, struct task_struct *wakee, struct + task_struct *curr) +{ + struct trace_array **ptr = private; + struct trace_array *tr = *ptr; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int cpu; + + if (!tracer_enabled) + return; + + tracing_record_cmdline(curr); + + local_irq_save(flags); + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + + if (likely(disabled == 1)) + tracing_sched_wakeup_trace(tr, data, wakee, curr, flags); + + atomic_dec(&data->disabled); + local_irq_restore(flags); +} + +static notrace void +wake_up_callback(void *probe_data, void *call_data, + const char *format, va_list *args) +{ + struct task_struct *curr; + struct task_struct *task; + struct rq *__rq; + + if (likely(!tracer_enabled)) + return; + + /* Skip pid %d state %ld */ + (void)va_arg(*args, int); + (void)va_arg(*args, long); + /* now get the meat: "rq %p task %p rq->curr %p" */ + __rq = va_arg(*args, typeof(__rq)); + task = va_arg(*args, typeof(task)); + curr = va_arg(*args, typeof(curr)); + + tracing_record_cmdline(task); + tracing_record_cmdline(curr); + + wakeup_func(probe_data, __rq, task, curr); +} + +static void sched_switch_reset(struct trace_array *tr) +{ + int cpu; + + tr->time_start = ftrace_now(tr->cpu); + + for_each_online_cpu(cpu) + tracing_reset(tr->data[cpu]); +} + +static int tracing_sched_register(void) +{ + int ret; + + ret = marker_probe_register("kernel_sched_wakeup", + "pid %d state %ld ## rq %p task %p rq->curr %p", + wake_up_callback, + &ctx_trace); + if (ret) { + pr_info("wakeup trace: Couldn't add marker" + " probe to kernel_sched_wakeup\n"); + return ret; + } + + ret = marker_probe_register("kernel_sched_wakeup_new", + "pid %d state %ld ## rq %p task %p rq->curr %p", + wake_up_callback, + &ctx_trace); + if (ret) { + pr_info("wakeup trace: Couldn't add marker" + " probe to kernel_sched_wakeup_new\n"); + goto fail_deprobe; + } + + ret = marker_probe_register("kernel_sched_schedule", + "prev_pid %d next_pid %d prev_state %ld " + "## rq %p prev %p next %p", + sched_switch_callback, + &ctx_trace); + if (ret) { + pr_info("sched trace: Couldn't add marker" + " probe to kernel_sched_schedule\n"); + goto fail_deprobe_wake_new; + } + + return ret; +fail_deprobe_wake_new: + marker_probe_unregister("kernel_sched_wakeup_new", + wake_up_callback, + &ctx_trace); +fail_deprobe: + marker_probe_unregister("kernel_sched_wakeup", + wake_up_callback, + &ctx_trace); + return ret; +} + +static void tracing_sched_unregister(void) +{ + marker_probe_unregister("kernel_sched_schedule", + sched_switch_callback, + &ctx_trace); + marker_probe_unregister("kernel_sched_wakeup_new", + wake_up_callback, + &ctx_trace); + marker_probe_unregister("kernel_sched_wakeup", + wake_up_callback, + &ctx_trace); +} + +static void tracing_start_sched_switch(void) +{ + long ref; + + ref = atomic_inc_return(&sched_ref); + if (ref == 1) + tracing_sched_register(); +} + +static void tracing_stop_sched_switch(void) +{ + long ref; + + ref = atomic_dec_and_test(&sched_ref); + if (ref) + tracing_sched_unregister(); +} + +void tracing_start_cmdline_record(void) +{ + tracing_start_sched_switch(); +} + +void tracing_stop_cmdline_record(void) +{ + tracing_stop_sched_switch(); +} + +static void start_sched_trace(struct trace_array *tr) +{ + sched_switch_reset(tr); + tracing_start_cmdline_record(); + tracer_enabled = 1; +} + +static void stop_sched_trace(struct trace_array *tr) +{ + tracer_enabled = 0; + tracing_stop_cmdline_record(); +} + +static void sched_switch_trace_init(struct trace_array *tr) +{ + ctx_trace = tr; + + if (tr->ctrl) + start_sched_trace(tr); +} + +static void sched_switch_trace_reset(struct trace_array *tr) +{ + if (tr->ctrl) + stop_sched_trace(tr); +} + +static void sched_switch_trace_ctrl_update(struct trace_array *tr) +{ + /* When starting a new trace, reset the buffers */ + if (tr->ctrl) + start_sched_trace(tr); + else + stop_sched_trace(tr); +} + +static struct tracer sched_switch_trace __read_mostly = +{ + .name = "sched_switch", + .init = sched_switch_trace_init, + .reset = sched_switch_trace_reset, + .ctrl_update = sched_switch_trace_ctrl_update, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_sched_switch, +#endif +}; + +__init static int init_sched_switch_trace(void) +{ + int ret = 0; + + if (atomic_read(&sched_ref)) + ret = tracing_sched_register(); + if (ret) { + pr_info("error registering scheduler trace\n"); + return ret; + } + return register_tracer(&sched_switch_trace); +} +device_initcall(init_sched_switch_trace); diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c new file mode 100644 index 00000000000..3c8d61df447 --- /dev/null +++ b/kernel/trace/trace_sched_wakeup.c @@ -0,0 +1,448 @@ +/* + * trace task wakeup timings + * + * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com> + * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> + * + * Based on code from the latency_tracer, that is: + * + * Copyright (C) 2004-2006 Ingo Molnar + * Copyright (C) 2004 William Lee Irwin III + */ +#include <linux/module.h> +#include <linux/fs.h> +#include <linux/debugfs.h> +#include <linux/kallsyms.h> +#include <linux/uaccess.h> +#include <linux/ftrace.h> +#include <linux/marker.h> + +#include "trace.h" + +static struct trace_array *wakeup_trace; +static int __read_mostly tracer_enabled; + +static struct task_struct *wakeup_task; +static int wakeup_cpu; +static unsigned wakeup_prio = -1; + +static DEFINE_SPINLOCK(wakeup_lock); + +static void __wakeup_reset(struct trace_array *tr); + +#ifdef CONFIG_FTRACE +/* + * irqsoff uses its own tracer function to keep the overhead down: + */ +static void +wakeup_tracer_call(unsigned long ip, unsigned long parent_ip) +{ + struct trace_array *tr = wakeup_trace; + struct trace_array_cpu *data; + unsigned long flags; + long disabled; + int resched; + int cpu; + + if (likely(!wakeup_task)) + return; + + resched = need_resched(); + preempt_disable_notrace(); + + cpu = raw_smp_processor_id(); + data = tr->data[cpu]; + disabled = atomic_inc_return(&data->disabled); + if (unlikely(disabled != 1)) + goto out; + + spin_lock_irqsave(&wakeup_lock, flags); + + if (unlikely(!wakeup_task)) + goto unlock; + + /* + * The task can't disappear because it needs to + * wake up first, and we have the wakeup_lock. + */ + if (task_cpu(wakeup_task) != cpu) + goto unlock; + + trace_function(tr, data, ip, parent_ip, flags); + + unlock: + spin_unlock_irqrestore(&wakeup_lock, flags); + + out: + atomic_dec(&data->disabled); + + /* + * To prevent recursion from the scheduler, if the + * resched flag was set before we entered, then + * don't reschedule. + */ + if (resched) + preempt_enable_no_resched_notrace(); + else + preempt_enable_notrace(); +} + +static struct ftrace_ops trace_ops __read_mostly = +{ + .func = wakeup_tracer_call, +}; +#endif /* CONFIG_FTRACE */ + +/* + * Should this new latency be reported/recorded? + */ +static int report_latency(cycle_t delta) +{ + if (tracing_thresh) { + if (delta < tracing_thresh) + return 0; + } else { + if (delta <= tracing_max_latency) + return 0; + } + return 1; +} + +static void notrace +wakeup_sched_switch(void *private, void *rq, struct task_struct *prev, + struct task_struct *next) +{ + unsigned long latency = 0, t0 = 0, t1 = 0; + struct trace_array **ptr = private; + struct trace_array *tr = *ptr; + struct trace_array_cpu *data; + cycle_t T0, T1, delta; + unsigned long flags; + long disabled; + int cpu; + + if (unlikely(!tracer_enabled)) + return; + + /* + * When we start a new trace, we set wakeup_task to NULL + * and then set tracer_enabled = 1. We want to make sure + * that another CPU does not see the tracer_enabled = 1 + * and the wakeup_task with an older task, that might + * actually be the same as next. + */ + smp_rmb(); + + if (next != wakeup_task) + return; + + /* The task we are waiting for is waking up */ + data = tr->data[wakeup_cpu]; + + /* disable local data, not wakeup_cpu data */ + cpu = raw_smp_processor_id(); + disabled = atomic_inc_return(&tr->data[cpu]->disabled); + if (likely(disabled != 1)) + goto out; + + spin_lock_irqsave(&wakeup_lock, flags); + + /* We could race with grabbing wakeup_lock */ + if (unlikely(!tracer_enabled || next != wakeup_task)) + goto out_unlock; + + trace_function(tr, data, CALLER_ADDR1, CALLER_ADDR2, flags); + + /* + * usecs conversion is slow so we try to delay the conversion + * as long as possible: + */ + T0 = data->preempt_timestamp; + T1 = ftrace_now(cpu); + delta = T1-T0; + + if (!report_latency(delta)) + goto out_unlock; + + latency = nsecs_to_usecs(delta); + + tracing_max_latency = delta; + t0 = nsecs_to_usecs(T0); + t1 = nsecs_to_usecs(T1); + + update_max_tr(tr, wakeup_task, wakeup_cpu); + +out_unlock: + __wakeup_reset(tr); + spin_unlock_irqrestore(&wakeup_lock, flags); +out: + atomic_dec(&tr->data[cpu]->disabled); +} + +static notrace void +sched_switch_callback(void *probe_data, void *call_data, + const char *format, va_list *args) +{ + struct task_struct *prev; + struct task_struct *next; + struct rq *__rq; + + /* skip prev_pid %d next_pid %d prev_state %ld */ + (void)va_arg(*args, int); + (void)va_arg(*args, int); + (void)va_arg(*args, long); + __rq = va_arg(*args, typeof(__rq)); + prev = va_arg(*args, typeof(prev)); + next = va_arg(*args, typeof(next)); + + tracing_record_cmdline(prev); + + /* + * If tracer_switch_func only points to the local + * switch func, it still needs the ptr passed to it. + */ + wakeup_sched_switch(probe_data, __rq, prev, next); +} + +static void __wakeup_reset(struct trace_array *tr) +{ + struct trace_array_cpu *data; + int cpu; + + assert_spin_locked(&wakeup_lock); + + for_each_possible_cpu(cpu) { + data = tr->data[cpu]; + tracing_reset(data); + } + + wakeup_cpu = -1; + wakeup_prio = -1; + + if (wakeup_task) + put_task_struct(wakeup_task); + + wakeup_task = NULL; +} + +static void wakeup_reset(struct trace_array *tr) +{ + unsigned long flags; + + spin_lock_irqsave(&wakeup_lock, flags); + __wakeup_reset(tr); + spin_unlock_irqrestore(&wakeup_lock, flags); +} + +static void +wakeup_check_start(struct trace_array *tr, struct task_struct *p, + struct task_struct *curr) +{ + int cpu = smp_processor_id(); + unsigned long flags; + long disabled; + + if (likely(!rt_task(p)) || + p->prio >= wakeup_prio || + p->prio >= curr->prio) + return; + + disabled = atomic_inc_return(&tr->data[cpu]->disabled); + if (unlikely(disabled != 1)) + goto out; + + /* interrupts should be off from try_to_wake_up */ + spin_lock(&wakeup_lock); + + /* check for races. */ + if (!tracer_enabled || p->prio >= wakeup_prio) + goto out_locked; + + /* reset the trace */ + __wakeup_reset(tr); + + wakeup_cpu = task_cpu(p); + wakeup_prio = p->prio; + + wakeup_task = p; + get_task_struct(wakeup_task); + + local_save_flags(flags); + + tr->data[wakeup_cpu]->preempt_timestamp = ftrace_now(cpu); + trace_function(tr, tr->data[wakeup_cpu], + CALLER_ADDR1, CALLER_ADDR2, flags); + +out_locked: + spin_unlock(&wakeup_lock); +out: + atomic_dec(&tr->data[cpu]->disabled); +} + +static notrace void +wake_up_callback(void *probe_data, void *call_data, + const char *format, va_list *args) +{ + struct trace_array **ptr = probe_data; + struct trace_array *tr = *ptr; + struct task_struct *curr; + struct task_struct *task; + struct rq *__rq; + + if (likely(!tracer_enabled)) + return; + + /* Skip pid %d state %ld */ + (void)va_arg(*args, int); + (void)va_arg(*args, long); + /* now get the meat: "rq %p task %p rq->curr %p" */ + __rq = va_arg(*args, typeof(__rq)); + task = va_arg(*args, typeof(task)); + curr = va_arg(*args, typeof(curr)); + + tracing_record_cmdline(task); + tracing_record_cmdline(curr); + + wakeup_check_start(tr, task, curr); +} + +static void start_wakeup_tracer(struct trace_array *tr) +{ + int ret; + + ret = marker_probe_register("kernel_sched_wakeup", + "pid %d state %ld ## rq %p task %p rq->curr %p", + wake_up_callback, + &wakeup_trace); + if (ret) { + pr_info("wakeup trace: Couldn't add marker" + " probe to kernel_sched_wakeup\n"); + return; + } + + ret = marker_probe_register("kernel_sched_wakeup_new", + "pid %d state %ld ## rq %p task %p rq->curr %p", + wake_up_callback, + &wakeup_trace); + if (ret) { + pr_info("wakeup trace: Couldn't add marker" + " probe to kernel_sched_wakeup_new\n"); + goto fail_deprobe; + } + + ret = marker_probe_register("kernel_sched_schedule", + "prev_pid %d next_pid %d prev_state %ld " + "## rq %p prev %p next %p", + sched_switch_callback, + &wakeup_trace); + if (ret) { + pr_info("sched trace: Couldn't add marker" + " probe to kernel_sched_schedule\n"); + goto fail_deprobe_wake_new; + } + + wakeup_reset(tr); + + /* + * Don't let the tracer_enabled = 1 show up before + * the wakeup_task is reset. This may be overkill since + * wakeup_reset does a spin_unlock after setting the + * wakeup_task to NULL, but I want to be safe. + * This is a slow path anyway. + */ + smp_wmb(); + + register_ftrace_function(&trace_ops); + + tracer_enabled = 1; + + return; +fail_deprobe_wake_new: + marker_probe_unregister("kernel_sched_wakeup_new", + wake_up_callback, + &wakeup_trace); +fail_deprobe: + marker_probe_unregister("kernel_sched_wakeup", + wake_up_callback, + &wakeup_trace); +} + +static void stop_wakeup_tracer(struct trace_array *tr) +{ + tracer_enabled = 0; + unregister_ftrace_function(&trace_ops); + marker_probe_unregister("kernel_sched_schedule", + sched_switch_callback, + &wakeup_trace); + marker_probe_unregister("kernel_sched_wakeup_new", + wake_up_callback, + &wakeup_trace); + marker_probe_unregister("kernel_sched_wakeup", + wake_up_callback, + &wakeup_trace); +} + +static void wakeup_tracer_init(struct trace_array *tr) +{ + wakeup_trace = tr; + + if (tr->ctrl) + start_wakeup_tracer(tr); +} + +static void wakeup_tracer_reset(struct trace_array *tr) +{ + if (tr->ctrl) { + stop_wakeup_tracer(tr); + /* make sure we put back any tasks we are tracing */ + wakeup_reset(tr); + } +} + +static void wakeup_tracer_ctrl_update(struct trace_array *tr) +{ + if (tr->ctrl) + start_wakeup_tracer(tr); + else + stop_wakeup_tracer(tr); +} + +static void wakeup_tracer_open(struct trace_iterator *iter) +{ + /* stop the trace while dumping */ + if (iter->tr->ctrl) + stop_wakeup_tracer(iter->tr); +} + +static void wakeup_tracer_close(struct trace_iterator *iter) +{ + /* forget about any processes we were recording */ + if (iter->tr->ctrl) + start_wakeup_tracer(iter->tr); +} + +static struct tracer wakeup_tracer __read_mostly = +{ + .name = "wakeup", + .init = wakeup_tracer_init, + .reset = wakeup_tracer_reset, + .open = wakeup_tracer_open, + .close = wakeup_tracer_close, + .ctrl_update = wakeup_tracer_ctrl_update, + .print_max = 1, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_wakeup, +#endif +}; + +__init static int init_wakeup_tracer(void) +{ + int ret; + + ret = register_tracer(&wakeup_tracer); + if (ret) + return ret; + + return 0; +} +device_initcall(init_wakeup_tracer); diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c new file mode 100644 index 00000000000..0911b7e073b --- /dev/null +++ b/kernel/trace/trace_selftest.c @@ -0,0 +1,563 @@ +/* Include in trace.c */ + +#include <linux/kthread.h> +#include <linux/delay.h> + +static inline int trace_valid_entry(struct trace_entry *entry) +{ + switch (entry->type) { + case TRACE_FN: + case TRACE_CTX: + case TRACE_WAKE: + case TRACE_STACK: + case TRACE_SPECIAL: + return 1; + } + return 0; +} + +static int +trace_test_buffer_cpu(struct trace_array *tr, struct trace_array_cpu *data) +{ + struct trace_entry *entries; + struct page *page; + int idx = 0; + int i; + + BUG_ON(list_empty(&data->trace_pages)); + page = list_entry(data->trace_pages.next, struct page, lru); + entries = page_address(page); + + check_pages(data); + if (head_page(data) != entries) + goto failed; + + /* + * The starting trace buffer always has valid elements, + * if any element exists. + */ + entries = head_page(data); + + for (i = 0; i < tr->entries; i++) { + + if (i < data->trace_idx && !trace_valid_entry(&entries[idx])) { + printk(KERN_CONT ".. invalid entry %d ", + entries[idx].type); + goto failed; + } + + idx++; + if (idx >= ENTRIES_PER_PAGE) { + page = virt_to_page(entries); + if (page->lru.next == &data->trace_pages) { + if (i != tr->entries - 1) { + printk(KERN_CONT ".. entries buffer mismatch"); + goto failed; + } + } else { + page = list_entry(page->lru.next, struct page, lru); + entries = page_address(page); + } + idx = 0; + } + } + + page = virt_to_page(entries); + if (page->lru.next != &data->trace_pages) { + printk(KERN_CONT ".. too many entries"); + goto failed; + } + + return 0; + + failed: + /* disable tracing */ + tracing_disabled = 1; + printk(KERN_CONT ".. corrupted trace buffer .. "); + return -1; +} + +/* + * Test the trace buffer to see if all the elements + * are still sane. + */ +static int trace_test_buffer(struct trace_array *tr, unsigned long *count) +{ + unsigned long flags, cnt = 0; + int cpu, ret = 0; + + /* Don't allow flipping of max traces now */ + raw_local_irq_save(flags); + __raw_spin_lock(&ftrace_max_lock); + for_each_possible_cpu(cpu) { + if (!head_page(tr->data[cpu])) + continue; + + cnt += tr->data[cpu]->trace_idx; + + ret = trace_test_buffer_cpu(tr, tr->data[cpu]); + if (ret) + break; + } + __raw_spin_unlock(&ftrace_max_lock); + raw_local_irq_restore(flags); + + if (count) + *count = cnt; + + return ret; +} + +#ifdef CONFIG_FTRACE + +#ifdef CONFIG_DYNAMIC_FTRACE + +#define __STR(x) #x +#define STR(x) __STR(x) + +/* Test dynamic code modification and ftrace filters */ +int trace_selftest_startup_dynamic_tracing(struct tracer *trace, + struct trace_array *tr, + int (*func)(void)) +{ + unsigned long count; + int ret; + int save_ftrace_enabled = ftrace_enabled; + int save_tracer_enabled = tracer_enabled; + char *func_name; + + /* The ftrace test PASSED */ + printk(KERN_CONT "PASSED\n"); + pr_info("Testing dynamic ftrace: "); + + /* enable tracing, and record the filter function */ + ftrace_enabled = 1; + tracer_enabled = 1; + + /* passed in by parameter to fool gcc from optimizing */ + func(); + + /* update the records */ + ret = ftrace_force_update(); + if (ret) { + printk(KERN_CONT ".. ftraced failed .. "); + return ret; + } + + /* + * Some archs *cough*PowerPC*cough* add charachters to the + * start of the function names. We simply put a '*' to + * accomodate them. + */ + func_name = "*" STR(DYN_FTRACE_TEST_NAME); + + /* filter only on our function */ + ftrace_set_filter(func_name, strlen(func_name), 1); + + /* enable tracing */ + tr->ctrl = 1; + trace->init(tr); + /* Sleep for a 1/10 of a second */ + msleep(100); + + /* we should have nothing in the buffer */ + ret = trace_test_buffer(tr, &count); + if (ret) + goto out; + + if (count) { + ret = -1; + printk(KERN_CONT ".. filter did not filter .. "); + goto out; + } + + /* call our function again */ + func(); + + /* sleep again */ + msleep(100); + + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + ftrace_enabled = 0; + + /* check the trace buffer */ + ret = trace_test_buffer(tr, &count); + trace->reset(tr); + + /* we should only have one item */ + if (!ret && count != 1) { + printk(KERN_CONT ".. filter failed count=%ld ..", count); + ret = -1; + goto out; + } + out: + ftrace_enabled = save_ftrace_enabled; + tracer_enabled = save_tracer_enabled; + + /* Enable tracing on all functions again */ + ftrace_set_filter(NULL, 0, 1); + + return ret; +} +#else +# define trace_selftest_startup_dynamic_tracing(trace, tr, func) ({ 0; }) +#endif /* CONFIG_DYNAMIC_FTRACE */ +/* + * Simple verification test of ftrace function tracer. + * Enable ftrace, sleep 1/10 second, and then read the trace + * buffer to see if all is in order. + */ +int +trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr) +{ + unsigned long count; + int ret; + int save_ftrace_enabled = ftrace_enabled; + int save_tracer_enabled = tracer_enabled; + + /* make sure msleep has been recorded */ + msleep(1); + + /* force the recorded functions to be traced */ + ret = ftrace_force_update(); + if (ret) { + printk(KERN_CONT ".. ftraced failed .. "); + return ret; + } + + /* start the tracing */ + ftrace_enabled = 1; + tracer_enabled = 1; + + tr->ctrl = 1; + trace->init(tr); + /* Sleep for a 1/10 of a second */ + msleep(100); + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + ftrace_enabled = 0; + + /* check the trace buffer */ + ret = trace_test_buffer(tr, &count); + trace->reset(tr); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + goto out; + } + + ret = trace_selftest_startup_dynamic_tracing(trace, tr, + DYN_FTRACE_TEST_NAME); + + out: + ftrace_enabled = save_ftrace_enabled; + tracer_enabled = save_tracer_enabled; + + /* kill ftrace totally if we failed */ + if (ret) + ftrace_kill(); + + return ret; +} +#endif /* CONFIG_FTRACE */ + +#ifdef CONFIG_IRQSOFF_TRACER +int +trace_selftest_startup_irqsoff(struct tracer *trace, struct trace_array *tr) +{ + unsigned long save_max = tracing_max_latency; + unsigned long count; + int ret; + + /* start the tracing */ + tr->ctrl = 1; + trace->init(tr); + /* reset the max latency */ + tracing_max_latency = 0; + /* disable interrupts for a bit */ + local_irq_disable(); + udelay(100); + local_irq_enable(); + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + /* check both trace buffers */ + ret = trace_test_buffer(tr, NULL); + if (!ret) + ret = trace_test_buffer(&max_tr, &count); + trace->reset(tr); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + } + + tracing_max_latency = save_max; + + return ret; +} +#endif /* CONFIG_IRQSOFF_TRACER */ + +#ifdef CONFIG_PREEMPT_TRACER +int +trace_selftest_startup_preemptoff(struct tracer *trace, struct trace_array *tr) +{ + unsigned long save_max = tracing_max_latency; + unsigned long count; + int ret; + + /* start the tracing */ + tr->ctrl = 1; + trace->init(tr); + /* reset the max latency */ + tracing_max_latency = 0; + /* disable preemption for a bit */ + preempt_disable(); + udelay(100); + preempt_enable(); + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + /* check both trace buffers */ + ret = trace_test_buffer(tr, NULL); + if (!ret) + ret = trace_test_buffer(&max_tr, &count); + trace->reset(tr); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + } + + tracing_max_latency = save_max; + + return ret; +} +#endif /* CONFIG_PREEMPT_TRACER */ + +#if defined(CONFIG_IRQSOFF_TRACER) && defined(CONFIG_PREEMPT_TRACER) +int +trace_selftest_startup_preemptirqsoff(struct tracer *trace, struct trace_array *tr) +{ + unsigned long save_max = tracing_max_latency; + unsigned long count; + int ret; + + /* start the tracing */ + tr->ctrl = 1; + trace->init(tr); + + /* reset the max latency */ + tracing_max_latency = 0; + + /* disable preemption and interrupts for a bit */ + preempt_disable(); + local_irq_disable(); + udelay(100); + preempt_enable(); + /* reverse the order of preempt vs irqs */ + local_irq_enable(); + + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + /* check both trace buffers */ + ret = trace_test_buffer(tr, NULL); + if (ret) + goto out; + + ret = trace_test_buffer(&max_tr, &count); + if (ret) + goto out; + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + goto out; + } + + /* do the test by disabling interrupts first this time */ + tracing_max_latency = 0; + tr->ctrl = 1; + trace->ctrl_update(tr); + preempt_disable(); + local_irq_disable(); + udelay(100); + preempt_enable(); + /* reverse the order of preempt vs irqs */ + local_irq_enable(); + + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + /* check both trace buffers */ + ret = trace_test_buffer(tr, NULL); + if (ret) + goto out; + + ret = trace_test_buffer(&max_tr, &count); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + goto out; + } + + out: + trace->reset(tr); + tracing_max_latency = save_max; + + return ret; +} +#endif /* CONFIG_IRQSOFF_TRACER && CONFIG_PREEMPT_TRACER */ + +#ifdef CONFIG_SCHED_TRACER +static int trace_wakeup_test_thread(void *data) +{ + /* Make this a RT thread, doesn't need to be too high */ + struct sched_param param = { .sched_priority = 5 }; + struct completion *x = data; + + sched_setscheduler(current, SCHED_FIFO, ¶m); + + /* Make it know we have a new prio */ + complete(x); + + /* now go to sleep and let the test wake us up */ + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + + /* we are awake, now wait to disappear */ + while (!kthread_should_stop()) { + /* + * This is an RT task, do short sleeps to let + * others run. + */ + msleep(100); + } + + return 0; +} + +int +trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr) +{ + unsigned long save_max = tracing_max_latency; + struct task_struct *p; + struct completion isrt; + unsigned long count; + int ret; + + init_completion(&isrt); + + /* create a high prio thread */ + p = kthread_run(trace_wakeup_test_thread, &isrt, "ftrace-test"); + if (IS_ERR(p)) { + printk(KERN_CONT "Failed to create ftrace wakeup test thread "); + return -1; + } + + /* make sure the thread is running at an RT prio */ + wait_for_completion(&isrt); + + /* start the tracing */ + tr->ctrl = 1; + trace->init(tr); + /* reset the max latency */ + tracing_max_latency = 0; + + /* sleep to let the RT thread sleep too */ + msleep(100); + + /* + * Yes this is slightly racy. It is possible that for some + * strange reason that the RT thread we created, did not + * call schedule for 100ms after doing the completion, + * and we do a wakeup on a task that already is awake. + * But that is extremely unlikely, and the worst thing that + * happens in such a case, is that we disable tracing. + * Honestly, if this race does happen something is horrible + * wrong with the system. + */ + + wake_up_process(p); + + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + /* check both trace buffers */ + ret = trace_test_buffer(tr, NULL); + if (!ret) + ret = trace_test_buffer(&max_tr, &count); + + + trace->reset(tr); + + tracing_max_latency = save_max; + + /* kill the thread */ + kthread_stop(p); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + } + + return ret; +} +#endif /* CONFIG_SCHED_TRACER */ + +#ifdef CONFIG_CONTEXT_SWITCH_TRACER +int +trace_selftest_startup_sched_switch(struct tracer *trace, struct trace_array *tr) +{ + unsigned long count; + int ret; + + /* start the tracing */ + tr->ctrl = 1; + trace->init(tr); + /* Sleep for a 1/10 of a second */ + msleep(100); + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + /* check the trace buffer */ + ret = trace_test_buffer(tr, &count); + trace->reset(tr); + + if (!ret && !count) { + printk(KERN_CONT ".. no entries found .."); + ret = -1; + } + + return ret; +} +#endif /* CONFIG_CONTEXT_SWITCH_TRACER */ + +#ifdef CONFIG_SYSPROF_TRACER +int +trace_selftest_startup_sysprof(struct tracer *trace, struct trace_array *tr) +{ + unsigned long count; + int ret; + + /* start the tracing */ + tr->ctrl = 1; + trace->init(tr); + /* Sleep for a 1/10 of a second */ + msleep(100); + /* stop the tracing. */ + tr->ctrl = 0; + trace->ctrl_update(tr); + /* check the trace buffer */ + ret = trace_test_buffer(tr, &count); + trace->reset(tr); + + return ret; +} +#endif /* CONFIG_SYSPROF_TRACER */ diff --git a/kernel/trace/trace_selftest_dynamic.c b/kernel/trace/trace_selftest_dynamic.c new file mode 100644 index 00000000000..54dd77cce5b --- /dev/null +++ b/kernel/trace/trace_selftest_dynamic.c @@ -0,0 +1,7 @@ +#include "trace.h" + +int DYN_FTRACE_TEST_NAME(void) +{ + /* used to call mcount */ + return 0; +} diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c new file mode 100644 index 00000000000..2301e1e7c60 --- /dev/null +++ b/kernel/trace/trace_sysprof.c @@ -0,0 +1,363 @@ +/* + * trace stack traces + * + * Copyright (C) 2004-2008, Soeren Sandmann + * Copyright (C) 2007 Steven Rostedt <srostedt@redhat.com> + * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> + */ +#include <linux/kallsyms.h> +#include <linux/debugfs.h> +#include <linux/hrtimer.h> +#include <linux/uaccess.h> +#include <linux/ftrace.h> +#include <linux/module.h> +#include <linux/irq.h> +#include <linux/fs.h> + +#include <asm/stacktrace.h> + +#include "trace.h" + +static struct trace_array *sysprof_trace; +static int __read_mostly tracer_enabled; + +/* + * 1 msec sample interval by default: + */ +static unsigned long sample_period = 1000000; +static const unsigned int sample_max_depth = 512; + +static DEFINE_MUTEX(sample_timer_lock); +/* + * Per CPU hrtimers that do the profiling: + */ +static DEFINE_PER_CPU(struct hrtimer, stack_trace_hrtimer); + +struct stack_frame { + const void __user *next_fp; + unsigned long return_address; +}; + +static int copy_stack_frame(const void __user *fp, struct stack_frame *frame) +{ + int ret; + + if (!access_ok(VERIFY_READ, fp, sizeof(*frame))) + return 0; + + ret = 1; + pagefault_disable(); + if (__copy_from_user_inatomic(frame, fp, sizeof(*frame))) + ret = 0; + pagefault_enable(); + + return ret; +} + +struct backtrace_info { + struct trace_array_cpu *data; + struct trace_array *tr; + int pos; +}; + +static void +backtrace_warning_symbol(void *data, char *msg, unsigned long symbol) +{ + /* Ignore warnings */ +} + +static void backtrace_warning(void *data, char *msg) +{ + /* Ignore warnings */ +} + +static int backtrace_stack(void *data, char *name) +{ + /* Don't bother with IRQ stacks for now */ + return -1; +} + +static void backtrace_address(void *data, unsigned long addr, int reliable) +{ + struct backtrace_info *info = data; + + if (info->pos < sample_max_depth && reliable) { + __trace_special(info->tr, info->data, 1, addr, 0); + + info->pos++; + } +} + +const static struct stacktrace_ops backtrace_ops = { + .warning = backtrace_warning, + .warning_symbol = backtrace_warning_symbol, + .stack = backtrace_stack, + .address = backtrace_address, +}; + +static int +trace_kernel(struct pt_regs *regs, struct trace_array *tr, + struct trace_array_cpu *data) +{ + struct backtrace_info info; + unsigned long bp; + char *stack; + + info.tr = tr; + info.data = data; + info.pos = 1; + + __trace_special(info.tr, info.data, 1, regs->ip, 0); + + stack = ((char *)regs + sizeof(struct pt_regs)); +#ifdef CONFIG_FRAME_POINTER + bp = regs->bp; +#else + bp = 0; +#endif + + dump_trace(NULL, regs, (void *)stack, bp, &backtrace_ops, &info); + + return info.pos; +} + +static void timer_notify(struct pt_regs *regs, int cpu) +{ + struct trace_array_cpu *data; + struct stack_frame frame; + struct trace_array *tr; + const void __user *fp; + int is_user; + int i; + + if (!regs) + return; + + tr = sysprof_trace; + data = tr->data[cpu]; + is_user = user_mode(regs); + + if (!current || current->pid == 0) + return; + + if (is_user && current->state != TASK_RUNNING) + return; + + __trace_special(tr, data, 0, 0, current->pid); + + if (!is_user) + i = trace_kernel(regs, tr, data); + else + i = 0; + + /* + * Trace user stack if we are not a kernel thread + */ + if (current->mm && i < sample_max_depth) { + regs = (struct pt_regs *)current->thread.sp0 - 1; + + fp = (void __user *)regs->bp; + + __trace_special(tr, data, 2, regs->ip, 0); + + while (i < sample_max_depth) { + frame.next_fp = 0; + frame.return_address = 0; + if (!copy_stack_frame(fp, &frame)) + break; + if ((unsigned long)fp < regs->sp) + break; + + __trace_special(tr, data, 2, frame.return_address, + (unsigned long)fp); + fp = frame.next_fp; + + i++; + } + + } + + /* + * Special trace entry if we overflow the max depth: + */ + if (i == sample_max_depth) + __trace_special(tr, data, -1, -1, -1); + + __trace_special(tr, data, 3, current->pid, i); +} + +static enum hrtimer_restart stack_trace_timer_fn(struct hrtimer *hrtimer) +{ + /* trace here */ + timer_notify(get_irq_regs(), smp_processor_id()); + + hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); + + return HRTIMER_RESTART; +} + +static void start_stack_timer(int cpu) +{ + struct hrtimer *hrtimer = &per_cpu(stack_trace_hrtimer, cpu); + + hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer->function = stack_trace_timer_fn; + hrtimer->cb_mode = HRTIMER_CB_IRQSAFE_NO_SOFTIRQ; + + hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL); +} + +static void start_stack_timers(void) +{ + cpumask_t saved_mask = current->cpus_allowed; + int cpu; + + for_each_online_cpu(cpu) { + set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)); + start_stack_timer(cpu); + } + set_cpus_allowed_ptr(current, &saved_mask); +} + +static void stop_stack_timer(int cpu) +{ + struct hrtimer *hrtimer = &per_cpu(stack_trace_hrtimer, cpu); + + hrtimer_cancel(hrtimer); +} + +static void stop_stack_timers(void) +{ + int cpu; + + for_each_online_cpu(cpu) + stop_stack_timer(cpu); +} + +static void stack_reset(struct trace_array *tr) +{ + int cpu; + + tr->time_start = ftrace_now(tr->cpu); + + for_each_online_cpu(cpu) + tracing_reset(tr->data[cpu]); +} + +static void start_stack_trace(struct trace_array *tr) +{ + mutex_lock(&sample_timer_lock); + stack_reset(tr); + start_stack_timers(); + tracer_enabled = 1; + mutex_unlock(&sample_timer_lock); +} + +static void stop_stack_trace(struct trace_array *tr) +{ + mutex_lock(&sample_timer_lock); + stop_stack_timers(); + tracer_enabled = 0; + mutex_unlock(&sample_timer_lock); +} + +static void stack_trace_init(struct trace_array *tr) +{ + sysprof_trace = tr; + + if (tr->ctrl) + start_stack_trace(tr); +} + +static void stack_trace_reset(struct trace_array *tr) +{ + if (tr->ctrl) + stop_stack_trace(tr); +} + +static void stack_trace_ctrl_update(struct trace_array *tr) +{ + /* When starting a new trace, reset the buffers */ + if (tr->ctrl) + start_stack_trace(tr); + else + stop_stack_trace(tr); +} + +static struct tracer stack_trace __read_mostly = +{ + .name = "sysprof", + .init = stack_trace_init, + .reset = stack_trace_reset, + .ctrl_update = stack_trace_ctrl_update, +#ifdef CONFIG_FTRACE_SELFTEST + .selftest = trace_selftest_startup_sysprof, +#endif +}; + +__init static int init_stack_trace(void) +{ + return register_tracer(&stack_trace); +} +device_initcall(init_stack_trace); + +#define MAX_LONG_DIGITS 22 + +static ssize_t +sysprof_sample_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_LONG_DIGITS]; + int r; + + r = sprintf(buf, "%ld\n", nsecs_to_usecs(sample_period)); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); +} + +static ssize_t +sysprof_sample_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_LONG_DIGITS]; + unsigned long val; + + if (cnt > MAX_LONG_DIGITS-1) + cnt = MAX_LONG_DIGITS-1; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + val = simple_strtoul(buf, NULL, 10); + /* + * Enforce a minimum sample period of 100 usecs: + */ + if (val < 100) + val = 100; + + mutex_lock(&sample_timer_lock); + stop_stack_timers(); + sample_period = val * 1000; + start_stack_timers(); + mutex_unlock(&sample_timer_lock); + + return cnt; +} + +static struct file_operations sysprof_sample_fops = { + .read = sysprof_sample_read, + .write = sysprof_sample_write, +}; + +void init_tracer_sysprof_debugfs(struct dentry *d_tracer) +{ + struct dentry *entry; + + entry = debugfs_create_file("sysprof_sample_period", 0644, + d_tracer, NULL, &sysprof_sample_fops); + if (entry) + return; + pr_warning("Could not create debugfs 'dyn_ftrace_total_info' entry\n"); +} diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 29fc39f1029..ce7799540c9 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -13,7 +13,7 @@ * Kai Petzke <wpp@marie.physik.tu-berlin.de> * Theodore Ts'o <tytso@mit.edu> * - * Made to use alloc_percpu by Christoph Lameter <clameter@sgi.com>. + * Made to use alloc_percpu by Christoph Lameter. */ #include <linux/module.h> |