diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/compat.c | 100 | ||||
-rw-r--r-- | kernel/debug/debug_core.c | 2 | ||||
-rw-r--r-- | kernel/hrtimer.c | 15 | ||||
-rw-r--r-- | kernel/irq/chip.c | 48 | ||||
-rw-r--r-- | kernel/irq/handle.c | 5 | ||||
-rw-r--r-- | kernel/irq/internals.h | 9 | ||||
-rw-r--r-- | kernel/irq/irqdesc.c | 5 | ||||
-rw-r--r-- | kernel/irq/manage.c | 129 | ||||
-rw-r--r-- | kernel/irq/proc.c | 8 | ||||
-rw-r--r-- | kernel/kexec.c | 8 | ||||
-rw-r--r-- | kernel/ptrace.c | 4 | ||||
-rw-r--r-- | kernel/sched/core.c | 15 | ||||
-rw-r--r-- | kernel/sched/cputime.c | 16 | ||||
-rw-r--r-- | kernel/sched/sched.h | 10 | ||||
-rw-r--r-- | kernel/softirq.c | 1 | ||||
-rw-r--r-- | kernel/time/Kconfig | 2 | ||||
-rw-r--r-- | kernel/time/Makefile | 5 | ||||
-rw-r--r-- | kernel/time/clockevents.c | 40 | ||||
-rw-r--r-- | kernel/time/ntp.c | 5 | ||||
-rw-r--r-- | kernel/time/tick-broadcast-hrtimer.c | 106 | ||||
-rw-r--r-- | kernel/time/tick-broadcast.c | 85 | ||||
-rw-r--r-- | kernel/time/tick-common.c | 16 | ||||
-rw-r--r-- | kernel/time/tick-internal.h | 11 | ||||
-rw-r--r-- | kernel/time/timekeeping_debug.c | 2 | ||||
-rw-r--r-- | kernel/timer.c | 57 | ||||
-rw-r--r-- | kernel/workqueue.c | 7 |
26 files changed, 529 insertions, 182 deletions
diff --git a/kernel/compat.c b/kernel/compat.c index 0a09e481b70b..488ff8c4cf48 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -110,8 +110,8 @@ static int compat_put_timex(struct compat_timex __user *utp, struct timex *txc) return 0; } -asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz) +COMPAT_SYSCALL_DEFINE2(gettimeofday, struct compat_timeval __user *, tv, + struct timezone __user *, tz) { if (tv) { struct timeval ktv; @@ -127,8 +127,8 @@ asmlinkage long compat_sys_gettimeofday(struct compat_timeval __user *tv, return 0; } -asmlinkage long compat_sys_settimeofday(struct compat_timeval __user *tv, - struct timezone __user *tz) +COMPAT_SYSCALL_DEFINE2(settimeofday, struct compat_timeval __user *, tv, + struct timezone __user *, tz) { struct timespec kts; struct timezone ktz; @@ -236,8 +236,8 @@ static long compat_nanosleep_restart(struct restart_block *restart) return ret; } -asmlinkage long compat_sys_nanosleep(struct compat_timespec __user *rqtp, - struct compat_timespec __user *rmtp) +COMPAT_SYSCALL_DEFINE2(nanosleep, struct compat_timespec __user *, rqtp, + struct compat_timespec __user *, rmtp) { struct timespec tu, rmt; mm_segment_t oldfs; @@ -328,7 +328,7 @@ static compat_clock_t clock_t_to_compat_clock_t(clock_t x) return compat_jiffies_to_clock_t(clock_t_to_jiffies(x)); } -asmlinkage long compat_sys_times(struct compat_tms __user *tbuf) +COMPAT_SYSCALL_DEFINE1(times, struct compat_tms __user *, tbuf) { if (tbuf) { struct tms tms; @@ -354,7 +354,7 @@ asmlinkage long compat_sys_times(struct compat_tms __user *tbuf) * types that can be passed to put_user()/get_user(). */ -asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set) +COMPAT_SYSCALL_DEFINE1(sigpending, compat_old_sigset_t __user *, set) { old_sigset_t s; long ret; @@ -424,8 +424,8 @@ COMPAT_SYSCALL_DEFINE3(sigprocmask, int, how, #endif -asmlinkage long compat_sys_setrlimit(unsigned int resource, - struct compat_rlimit __user *rlim) +COMPAT_SYSCALL_DEFINE2(setrlimit, unsigned int, resource, + struct compat_rlimit __user *, rlim) { struct rlimit r; @@ -443,8 +443,8 @@ asmlinkage long compat_sys_setrlimit(unsigned int resource, #ifdef COMPAT_RLIM_OLD_INFINITY -asmlinkage long compat_sys_old_getrlimit(unsigned int resource, - struct compat_rlimit __user *rlim) +COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, + struct compat_rlimit __user *, rlim) { struct rlimit r; int ret; @@ -470,8 +470,8 @@ asmlinkage long compat_sys_old_getrlimit(unsigned int resource, #endif -asmlinkage long compat_sys_getrlimit(unsigned int resource, - struct compat_rlimit __user *rlim) +COMPAT_SYSCALL_DEFINE2(getrlimit, unsigned int, resource, + struct compat_rlimit __user *, rlim) { struct rlimit r; int ret; @@ -596,9 +596,9 @@ static int compat_get_user_cpu_mask(compat_ulong_t __user *user_mask_ptr, return compat_get_bitmap(k, user_mask_ptr, len * 8); } -asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid, - unsigned int len, - compat_ulong_t __user *user_mask_ptr) +COMPAT_SYSCALL_DEFINE3(sched_setaffinity, compat_pid_t, pid, + unsigned int, len, + compat_ulong_t __user *, user_mask_ptr) { cpumask_var_t new_mask; int retval; @@ -616,8 +616,8 @@ out: return retval; } -asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid, unsigned int len, - compat_ulong_t __user *user_mask_ptr) +COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t, pid, unsigned int, len, + compat_ulong_t __user *, user_mask_ptr) { int ret; cpumask_var_t mask; @@ -662,9 +662,9 @@ int put_compat_itimerspec(struct compat_itimerspec __user *dst, return 0; } -long compat_sys_timer_create(clockid_t which_clock, - struct compat_sigevent __user *timer_event_spec, - timer_t __user *created_timer_id) +COMPAT_SYSCALL_DEFINE3(timer_create, clockid_t, which_clock, + struct compat_sigevent __user *, timer_event_spec, + timer_t __user *, created_timer_id) { struct sigevent __user *event = NULL; @@ -680,9 +680,9 @@ long compat_sys_timer_create(clockid_t which_clock, return sys_timer_create(which_clock, event, created_timer_id); } -long compat_sys_timer_settime(timer_t timer_id, int flags, - struct compat_itimerspec __user *new, - struct compat_itimerspec __user *old) +COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, + struct compat_itimerspec __user *, new, + struct compat_itimerspec __user *, old) { long err; mm_segment_t oldfs; @@ -703,8 +703,8 @@ long compat_sys_timer_settime(timer_t timer_id, int flags, return err; } -long compat_sys_timer_gettime(timer_t timer_id, - struct compat_itimerspec __user *setting) +COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, + struct compat_itimerspec __user *, setting) { long err; mm_segment_t oldfs; @@ -720,8 +720,8 @@ long compat_sys_timer_gettime(timer_t timer_id, return err; } -long compat_sys_clock_settime(clockid_t which_clock, - struct compat_timespec __user *tp) +COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock, + struct compat_timespec __user *, tp) { long err; mm_segment_t oldfs; @@ -737,8 +737,8 @@ long compat_sys_clock_settime(clockid_t which_clock, return err; } -long compat_sys_clock_gettime(clockid_t which_clock, - struct compat_timespec __user *tp) +COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, + struct compat_timespec __user *, tp) { long err; mm_segment_t oldfs; @@ -754,8 +754,8 @@ long compat_sys_clock_gettime(clockid_t which_clock, return err; } -long compat_sys_clock_adjtime(clockid_t which_clock, - struct compat_timex __user *utp) +COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock, + struct compat_timex __user *, utp) { struct timex txc; mm_segment_t oldfs; @@ -777,8 +777,8 @@ long compat_sys_clock_adjtime(clockid_t which_clock, return ret; } -long compat_sys_clock_getres(clockid_t which_clock, - struct compat_timespec __user *tp) +COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, + struct compat_timespec __user *, tp) { long err; mm_segment_t oldfs; @@ -818,9 +818,9 @@ static long compat_clock_nanosleep_restart(struct restart_block *restart) return err; } -long compat_sys_clock_nanosleep(clockid_t which_clock, int flags, - struct compat_timespec __user *rqtp, - struct compat_timespec __user *rmtp) +COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, + struct compat_timespec __user *, rqtp, + struct compat_timespec __user *, rmtp) { long err; mm_segment_t oldfs; @@ -1010,7 +1010,7 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait, compat_sigset_t __user *, uthese, /* compat_time_t is a 32 bit "long" and needs to get converted. */ -asmlinkage long compat_sys_time(compat_time_t __user * tloc) +COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc) { compat_time_t i; struct timeval tv; @@ -1026,7 +1026,7 @@ asmlinkage long compat_sys_time(compat_time_t __user * tloc) return i; } -asmlinkage long compat_sys_stime(compat_time_t __user *tptr) +COMPAT_SYSCALL_DEFINE1(stime, compat_time_t __user *, tptr) { struct timespec tv; int err; @@ -1046,7 +1046,7 @@ asmlinkage long compat_sys_stime(compat_time_t __user *tptr) #endif /* __ARCH_WANT_COMPAT_SYS_TIME */ -asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp) +COMPAT_SYSCALL_DEFINE1(adjtimex, struct compat_timex __user *, utp) { struct timex txc; int err, ret; @@ -1065,11 +1065,11 @@ asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp) } #ifdef CONFIG_NUMA -asmlinkage long compat_sys_move_pages(pid_t pid, unsigned long nr_pages, - compat_uptr_t __user *pages32, - const int __user *nodes, - int __user *status, - int flags) +COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages, + compat_uptr_t __user *, pages32, + const int __user *, nodes, + int __user *, status, + int, flags) { const void __user * __user *pages; int i; @@ -1085,10 +1085,10 @@ asmlinkage long compat_sys_move_pages(pid_t pid, unsigned long nr_pages, return sys_move_pages(pid, nr_pages, pages, nodes, status, flags); } -asmlinkage long compat_sys_migrate_pages(compat_pid_t pid, - compat_ulong_t maxnode, - const compat_ulong_t __user *old_nodes, - const compat_ulong_t __user *new_nodes) +COMPAT_SYSCALL_DEFINE4(migrate_pages, compat_pid_t, pid, + compat_ulong_t, maxnode, + const compat_ulong_t __user *, old_nodes, + const compat_ulong_t __user *, new_nodes) { unsigned long __user *old = NULL; unsigned long __user *new = NULL; diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 334b3980ffc1..99982a70ddad 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -1035,7 +1035,7 @@ int dbg_io_get_char(void) * otherwise as a quick means to stop program execution and "break" into * the debugger. */ -void kgdb_breakpoint(void) +noinline void kgdb_breakpoint(void) { atomic_inc(&kgdb_setting_breakpoint); wmb(); /* Sync point before breakpoint */ diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index 09094361dce5..d55092ceee29 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -168,19 +168,6 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, } } - -/* - * Get the preferred target CPU for NOHZ - */ -static int hrtimer_get_target(int this_cpu, int pinned) -{ -#ifdef CONFIG_NO_HZ_COMMON - if (!pinned && get_sysctl_timer_migration() && idle_cpu(this_cpu)) - return get_nohz_timer_target(); -#endif - return this_cpu; -} - /* * With HIGHRES=y we do not migrate the timer when it is expiring * before the next event on the target cpu because we cannot reprogram @@ -214,7 +201,7 @@ switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, struct hrtimer_clock_base *new_base; struct hrtimer_cpu_base *new_cpu_base; int this_cpu = smp_processor_id(); - int cpu = hrtimer_get_target(this_cpu, pinned); + int cpu = get_nohz_timer_target(pinned); int basenum = base->index; again: diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c index dc04c166c54d..6397df2d6945 100644 --- a/kernel/irq/chip.c +++ b/kernel/irq/chip.c @@ -281,6 +281,19 @@ void unmask_irq(struct irq_desc *desc) } } +void unmask_threaded_irq(struct irq_desc *desc) +{ + struct irq_chip *chip = desc->irq_data.chip; + + if (chip->flags & IRQCHIP_EOI_THREADED) + chip->irq_eoi(&desc->irq_data); + + if (chip->irq_unmask) { + chip->irq_unmask(&desc->irq_data); + irq_state_clr_masked(desc); + } +} + /* * handle_nested_irq - Handle a nested irq from a irq thread * @irq: the interrupt number @@ -435,6 +448,27 @@ static inline void preflow_handler(struct irq_desc *desc) static inline void preflow_handler(struct irq_desc *desc) { } #endif +static void cond_unmask_eoi_irq(struct irq_desc *desc, struct irq_chip *chip) +{ + if (!(desc->istate & IRQS_ONESHOT)) { + chip->irq_eoi(&desc->irq_data); + return; + } + /* + * We need to unmask in the following cases: + * - Oneshot irq which did not wake the thread (caused by a + * spurious interrupt or a primary handler handling it + * completely). + */ + if (!irqd_irq_disabled(&desc->irq_data) && + irqd_irq_masked(&desc->irq_data) && !desc->threads_oneshot) { + chip->irq_eoi(&desc->irq_data); + unmask_irq(desc); + } else if (!(chip->flags & IRQCHIP_EOI_THREADED)) { + chip->irq_eoi(&desc->irq_data); + } +} + /** * handle_fasteoi_irq - irq handler for transparent controllers * @irq: the interrupt number @@ -448,6 +482,8 @@ static inline void preflow_handler(struct irq_desc *desc) { } void handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc) { + struct irq_chip *chip = desc->irq_data.chip; + raw_spin_lock(&desc->lock); if (unlikely(irqd_irq_inprogress(&desc->irq_data))) @@ -473,18 +509,14 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc) preflow_handler(desc); handle_irq_event(desc); - if (desc->istate & IRQS_ONESHOT) - cond_unmask_irq(desc); + cond_unmask_eoi_irq(desc, chip); -out_eoi: - desc->irq_data.chip->irq_eoi(&desc->irq_data); -out_unlock: raw_spin_unlock(&desc->lock); return; out: - if (!(desc->irq_data.chip->flags & IRQCHIP_EOI_IF_HANDLED)) - goto out_eoi; - goto out_unlock; + if (!(chip->flags & IRQCHIP_EOI_IF_HANDLED)) + chip->irq_eoi(&desc->irq_data); + raw_spin_unlock(&desc->lock); } /** diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c index 131ca176b497..635480270858 100644 --- a/kernel/irq/handle.c +++ b/kernel/irq/handle.c @@ -41,6 +41,7 @@ irqreturn_t no_action(int cpl, void *dev_id) { return IRQ_NONE; } +EXPORT_SYMBOL_GPL(no_action); static void warn_no_thread(unsigned int irq, struct irqaction *action) { @@ -51,7 +52,7 @@ static void warn_no_thread(unsigned int irq, struct irqaction *action) "but no thread function available.", irq, action->name); } -static void irq_wake_thread(struct irq_desc *desc, struct irqaction *action) +void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action) { /* * In case the thread crashed and was killed we just pretend that @@ -157,7 +158,7 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action) break; } - irq_wake_thread(desc, action); + __irq_wake_thread(desc, action); /* Fall through to add to randomness */ case IRQ_HANDLED: diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h index 001fa5bab490..ddf1ffeb79f1 100644 --- a/kernel/irq/internals.h +++ b/kernel/irq/internals.h @@ -6,6 +6,7 @@ * of this file for your non core code. */ #include <linux/irqdesc.h> +#include <linux/kernel_stat.h> #ifdef CONFIG_SPARSE_IRQ # define IRQ_BITMAP_BITS (NR_IRQS + 8196) @@ -73,6 +74,7 @@ extern void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu); extern void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu); extern void mask_irq(struct irq_desc *desc); extern void unmask_irq(struct irq_desc *desc); +extern void unmask_threaded_irq(struct irq_desc *desc); extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr); @@ -82,6 +84,7 @@ irqreturn_t handle_irq_event(struct irq_desc *desc); /* Resending of interrupts :*/ void check_irq_resend(struct irq_desc *desc, unsigned int irq); bool irq_wait_for_poll(struct irq_desc *desc); +void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action); #ifdef CONFIG_PROC_FS extern void register_irq_proc(unsigned int irq, struct irq_desc *desc); @@ -179,3 +182,9 @@ static inline bool irqd_has_set(struct irq_data *d, unsigned int mask) { return d->state_use_accessors & mask; } + +static inline void kstat_incr_irqs_this_cpu(unsigned int irq, struct irq_desc *desc) +{ + __this_cpu_inc(*desc->kstat_irqs); + __this_cpu_inc(kstat.irqs_sum); +} diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 8ab8e9390297..a7174617616b 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -489,6 +489,11 @@ void dynamic_irq_cleanup(unsigned int irq) raw_spin_unlock_irqrestore(&desc->lock, flags); } +void kstat_incr_irq_this_cpu(unsigned int irq) +{ + kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq)); +} + unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) { struct irq_desc *desc = irq_to_desc(irq); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index d3bf660cb57f..2486a4c1a710 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -32,24 +32,10 @@ static int __init setup_forced_irqthreads(char *arg) early_param("threadirqs", setup_forced_irqthreads); #endif -/** - * synchronize_irq - wait for pending IRQ handlers (on other CPUs) - * @irq: interrupt number to wait for - * - * This function waits for any pending IRQ handlers for this interrupt - * to complete before returning. If you use this function while - * holding a resource the IRQ handler may need you will deadlock. - * - * This function may be called - with care - from IRQ context. - */ -void synchronize_irq(unsigned int irq) +static void __synchronize_hardirq(struct irq_desc *desc) { - struct irq_desc *desc = irq_to_desc(irq); bool inprogress; - if (!desc) - return; - do { unsigned long flags; @@ -67,12 +53,56 @@ void synchronize_irq(unsigned int irq) /* Oops, that failed? */ } while (inprogress); +} - /* - * We made sure that no hardirq handler is running. Now verify - * that no threaded handlers are active. - */ - wait_event(desc->wait_for_threads, !atomic_read(&desc->threads_active)); +/** + * synchronize_hardirq - wait for pending hard IRQ handlers (on other CPUs) + * @irq: interrupt number to wait for + * + * This function waits for any pending hard IRQ handlers for this + * interrupt to complete before returning. If you use this + * function while holding a resource the IRQ handler may need you + * will deadlock. It does not take associated threaded handlers + * into account. + * + * Do not use this for shutdown scenarios where you must be sure + * that all parts (hardirq and threaded handler) have completed. + * + * This function may be called - with care - from IRQ context. + */ +void synchronize_hardirq(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (desc) + __synchronize_hardirq(desc); +} +EXPORT_SYMBOL(synchronize_hardirq); + +/** + * synchronize_irq - wait for pending IRQ handlers (on other CPUs) + * @irq: interrupt number to wait for + * + * This function waits for any pending IRQ handlers for this interrupt + * to complete before returning. If you use this function while + * holding a resource the IRQ handler may need you will deadlock. + * + * This function may be called - with care - from IRQ context. + */ +void synchronize_irq(unsigned int irq) +{ + struct irq_desc *desc = irq_to_desc(irq); + + if (desc) { + __synchronize_hardirq(desc); + /* + * We made sure that no hardirq handler is + * running. Now verify that no threaded handlers are + * active. + */ + wait_event(desc->wait_for_threads, + !atomic_read(&desc->threads_active)); + } } EXPORT_SYMBOL(synchronize_irq); @@ -718,7 +748,7 @@ again: if (!desc->threads_oneshot && !irqd_irq_disabled(&desc->irq_data) && irqd_irq_masked(&desc->irq_data)) - unmask_irq(desc); + unmask_threaded_irq(desc); out_unlock: raw_spin_unlock_irq(&desc->lock); @@ -727,7 +757,7 @@ out_unlock: #ifdef CONFIG_SMP /* - * Check whether we need to chasnge the affinity of the interrupt thread. + * Check whether we need to change the affinity of the interrupt thread. */ static void irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) @@ -880,6 +910,33 @@ static int irq_thread(void *data) return 0; } +/** + * irq_wake_thread - wake the irq thread for the action identified by dev_id + * @irq: Interrupt line + * @dev_id: Device identity for which the thread should be woken + * + */ +void irq_wake_thread(unsigned int irq, void *dev_id) +{ + struct irq_desc *desc = irq_to_desc(irq); + struct irqaction *action; + unsigned long flags; + + if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc))) + return; + + raw_spin_lock_irqsave(&desc->lock, flags); + for (action = desc->action; action; action = action->next) { + if (action->dev_id == dev_id) { + if (action->thread) + __irq_wake_thread(desc, action); + break; + } + } + raw_spin_unlock_irqrestore(&desc->lock, flags); +} +EXPORT_SYMBOL_GPL(irq_wake_thread); + static void irq_setup_forced_threading(struct irqaction *new) { if (!force_irqthreads) @@ -896,6 +953,23 @@ static void irq_setup_forced_threading(struct irqaction *new) } } +static int irq_request_resources(struct irq_desc *desc) +{ + struct irq_data *d = &desc->irq_data; + struct irq_chip *c = d->chip; + + return c->irq_request_resources ? c->irq_request_resources(d) : 0; +} + +static void irq_release_resources(struct irq_desc *desc) +{ + struct irq_data *d = &desc->irq_data; + struct irq_chip *c = d->chip; + + if (c->irq_release_resources) + c->irq_release_resources(d); +} + /* * Internal function to register an irqaction - typically used to * allocate special interrupts that are part of the architecture. @@ -1091,6 +1165,13 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new) } if (!shared) { + ret = irq_request_resources(desc); + if (ret) { + pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n", + new->name, irq, desc->irq_data.chip->name); + goto out_mask; + } + init_waitqueue_head(&desc->wait_for_threads); /* Setup the type (level, edge polarity) if configured: */ @@ -1261,8 +1342,10 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id) *action_ptr = action->next; /* If this was the last handler, shut down the IRQ line: */ - if (!desc->action) + if (!desc->action) { irq_shutdown(desc); + irq_release_resources(desc); + } #ifdef CONFIG_SMP /* make sure affinity_hint is cleaned up */ diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c index 36f6ee181b0c..ac1ba2f11032 100644 --- a/kernel/irq/proc.c +++ b/kernel/irq/proc.c @@ -324,15 +324,15 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc) #ifdef CONFIG_SMP /* create /proc/irq/<irq>/smp_affinity */ - proc_create_data("smp_affinity", 0600, desc->dir, + proc_create_data("smp_affinity", 0644, desc->dir, &irq_affinity_proc_fops, (void *)(long)irq); /* create /proc/irq/<irq>/affinity_hint */ - proc_create_data("affinity_hint", 0400, desc->dir, + proc_create_data("affinity_hint", 0444, desc->dir, &irq_affinity_hint_proc_fops, (void *)(long)irq); /* create /proc/irq/<irq>/smp_affinity_list */ - proc_create_data("smp_affinity_list", 0600, desc->dir, + proc_create_data("smp_affinity_list", 0644, desc->dir, &irq_affinity_list_proc_fops, (void *)(long)irq); proc_create_data("node", 0444, desc->dir, @@ -372,7 +372,7 @@ void unregister_handler_proc(unsigned int irq, struct irqaction *action) static void register_default_affinity_proc(void) { #ifdef CONFIG_SMP - proc_create("irq/default_smp_affinity", 0600, NULL, + proc_create("irq/default_smp_affinity", 0644, NULL, &default_affinity_proc_fops); #endif } diff --git a/kernel/kexec.c b/kernel/kexec.c index 60bafbed06ab..45601cf41bee 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -1039,10 +1039,10 @@ void __weak crash_unmap_reserved_pages(void) {} #ifdef CONFIG_COMPAT -asmlinkage long compat_sys_kexec_load(unsigned long entry, - unsigned long nr_segments, - struct compat_kexec_segment __user *segments, - unsigned long flags) +COMPAT_SYSCALL_DEFINE4(kexec_load, compat_ulong_t, entry, + compat_ulong_t, nr_segments, + struct compat_kexec_segment __user *, segments, + compat_ulong_t, flags) { struct compat_kexec_segment in; struct kexec_segment out, __user *ksegments; diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 1f4bcb3cc21c..adf98622cb32 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -1180,8 +1180,8 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request, return ret; } -asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid, - compat_long_t addr, compat_long_t data) +COMPAT_SYSCALL_DEFINE4(ptrace, compat_long_t, request, compat_long_t, pid, + compat_long_t, addr, compat_long_t, data) { struct task_struct *child; long ret; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index ae365aaa8181..3c4d096544ce 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -555,12 +555,15 @@ void resched_cpu(int cpu) * selecting an idle cpu will add more delays to the timers than intended * (as that cpu's timer base may not be uptodate wrt jiffies etc). */ -int get_nohz_timer_target(void) +int get_nohz_timer_target(int pinned) { int cpu = smp_processor_id(); int i; struct sched_domain *sd; + if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu)) + return cpu; + rcu_read_lock(); for_each_domain(cpu, sd) { for_each_cpu(i, sched_domain_span(sd)) { @@ -823,19 +826,13 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING if (static_key_false((¶virt_steal_rq_enabled))) { - u64 st; - steal = paravirt_steal_clock(cpu_of(rq)); steal -= rq->prev_steal_time_rq; if (unlikely(steal > delta)) steal = delta; - st = steal_ticks(steal); - steal = st * TICK_NSEC; - rq->prev_steal_time_rq += steal; - delta -= steal; } #endif @@ -4721,8 +4718,10 @@ void idle_task_exit(void) BUG_ON(cpu_online(smp_processor_id())); - if (mm != &init_mm) + if (mm != &init_mm) { switch_mm(mm, &init_mm, current); + finish_arch_post_lock_switch(); + } mmdrop(mm); } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 58624a65f124..a95097cb4591 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -258,16 +258,22 @@ static __always_inline bool steal_account_process_tick(void) { #ifdef CONFIG_PARAVIRT if (static_key_false(¶virt_steal_enabled)) { - u64 steal, st = 0; + u64 steal; + cputime_t steal_ct; steal = paravirt_steal_clock(smp_processor_id()); steal -= this_rq()->prev_steal_time; - st = steal_ticks(steal); - this_rq()->prev_steal_time += st * TICK_NSEC; + /* + * cputime_t may be less precise than nsecs (eg: if it's + * based on jiffies). Lets cast the result to cputime + * granularity and account the rest on the next rounds. + */ + steal_ct = nsecs_to_cputime(steal); + this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct); - account_steal_time(st); - return st; + account_steal_time(steal_ct); + return steal_ct; } #endif return false; diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index f2de7a175620..c9007f28d3a2 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1216,16 +1216,6 @@ extern void update_idle_cpu_load(struct rq *this_rq); extern void init_task_runnable_average(struct task_struct *p); -#ifdef CONFIG_PARAVIRT -static inline u64 steal_ticks(u64 steal) -{ - if (unlikely(steal > NSEC_PER_SEC)) - return div_u64(steal, TICK_NSEC); - - return __iter_div_u64_rem(steal, TICK_NSEC, &steal); -} -#endif - static inline void inc_nr_running(struct rq *rq) { rq->nr_running++; diff --git a/kernel/softirq.c b/kernel/softirq.c index 490fcbb1dc5b..b50990a5bea0 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -25,6 +25,7 @@ #include <linux/smp.h> #include <linux/smpboot.h> #include <linux/tick.h> +#include <linux/irq.h> #define CREATE_TRACE_POINTS #include <trace/events/irq.h> diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 3ce6e8c5f3fc..f448513a45ed 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -124,7 +124,7 @@ config NO_HZ_FULL endchoice config NO_HZ_FULL_ALL - bool "Full dynticks system on all CPUs by default" + bool "Full dynticks system on all CPUs by default (except CPU 0)" depends on NO_HZ_FULL help If the user doesn't pass the nohz_full boot option to diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 9250130646f5..57a413fd0ebf 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -3,7 +3,10 @@ obj-y += timeconv.o posix-clock.o alarmtimer.o obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o -obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) += tick-broadcast.o +ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y) + obj-y += tick-broadcast.o + obj-$(CONFIG_TICK_ONESHOT) += tick-broadcast-hrtimer.o +endif obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 086ad6043bcb..ad362c260ef4 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -439,6 +439,19 @@ void clockevents_config_and_register(struct clock_event_device *dev, } EXPORT_SYMBOL_GPL(clockevents_config_and_register); +int __clockevents_update_freq(struct clock_event_device *dev, u32 freq) +{ + clockevents_config(dev, freq); + + if (dev->mode == CLOCK_EVT_MODE_ONESHOT) + return clockevents_program_event(dev, dev->next_event, false); + + if (dev->mode == CLOCK_EVT_MODE_PERIODIC) + dev->set_mode(CLOCK_EVT_MODE_PERIODIC, dev); + + return 0; +} + /** * clockevents_update_freq - Update frequency and reprogram a clock event device. * @dev: device to modify @@ -446,17 +459,22 @@ EXPORT_SYMBOL_GPL(clockevents_config_and_register); * * Reconfigure and reprogram a clock event device in oneshot * mode. Must be called on the cpu for which the device delivers per - * cpu timer events with interrupts disabled! Returns 0 on success, - * -ETIME when the event is in the past. + * cpu timer events. If called for the broadcast device the core takes + * care of serialization. + * + * Returns 0 on success, -ETIME when the event is in the past. */ int clockevents_update_freq(struct clock_event_device *dev, u32 freq) { - clockevents_config(dev, freq); - - if (dev->mode != CLOCK_EVT_MODE_ONESHOT) - return 0; + unsigned long flags; + int ret; - return clockevents_program_event(dev, dev->next_event, false); + local_irq_save(flags); + ret = tick_broadcast_update_freq(dev, freq); + if (ret == -ENODEV) + ret = __clockevents_update_freq(dev, freq); + local_irq_restore(flags); + return ret; } /* @@ -524,12 +542,13 @@ void clockevents_resume(void) #ifdef CONFIG_GENERIC_CLOCKEVENTS /** * clockevents_notify - notification about relevant events + * Returns 0 on success, any other value on error */ -void clockevents_notify(unsigned long reason, void *arg) +int clockevents_notify(unsigned long reason, void *arg) { struct clock_event_device *dev, *tmp; unsigned long flags; - int cpu; + int cpu, ret = 0; raw_spin_lock_irqsave(&clockevents_lock, flags); @@ -542,7 +561,7 @@ void clockevents_notify(unsigned long reason, void *arg) case CLOCK_EVT_NOTIFY_BROADCAST_ENTER: case CLOCK_EVT_NOTIFY_BROADCAST_EXIT: - tick_broadcast_oneshot_control(reason); + ret = tick_broadcast_oneshot_control(reason); break; case CLOCK_EVT_NOTIFY_CPU_DYING: @@ -585,6 +604,7 @@ void clockevents_notify(unsigned long reason, void *arg) break; } raw_spin_unlock_irqrestore(&clockevents_lock, flags); + return ret; } EXPORT_SYMBOL_GPL(clockevents_notify); diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index af8d1d4f3d55..419a52cecd20 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -514,12 +514,13 @@ static void sync_cmos_clock(struct work_struct *work) next.tv_sec++; next.tv_nsec -= NSEC_PER_SEC; } - schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next)); + queue_delayed_work(system_power_efficient_wq, + &sync_cmos_work, timespec_to_jiffies(&next)); } void ntp_notify_cmos_timer(void) { - schedule_delayed_work(&sync_cmos_work, 0); + queue_delayed_work(system_power_efficient_wq, &sync_cmos_work, 0); } #else diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c new file mode 100644 index 000000000000..eb682d5c697c --- /dev/null +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -0,0 +1,106 @@ +/* + * linux/kernel/time/tick-broadcast-hrtimer.c + * This file emulates a local clock event device + * via a pseudo clock device. + */ +#include <linux/cpu.h> +#include <linux/err.h> +#include <linux/hrtimer.h> +#include <linux/interrupt.h> +#include <linux/percpu.h> +#include <linux/profile.h> +#include <linux/clockchips.h> +#include <linux/sched.h> +#include <linux/smp.h> +#include <linux/module.h> + +#include "tick-internal.h" + +static struct hrtimer bctimer; + +static void bc_set_mode(enum clock_event_mode mode, + struct clock_event_device *bc) +{ + switch (mode) { + case CLOCK_EVT_MODE_SHUTDOWN: + /* + * Note, we cannot cancel the timer here as we might + * run into the following live lock scenario: + * + * cpu 0 cpu1 + * lock(broadcast_lock); + * hrtimer_interrupt() + * bc_handler() + * tick_handle_oneshot_broadcast(); + * lock(broadcast_lock); + * hrtimer_cancel() + * wait_for_callback() + */ + hrtimer_try_to_cancel(&bctimer); + break; + default: + break; + } +} + +/* + * This is called from the guts of the broadcast code when the cpu + * which is about to enter idle has the earliest broadcast timer event. + */ +static int bc_set_next(ktime_t expires, struct clock_event_device *bc) +{ + /* + * We try to cancel the timer first. If the callback is on + * flight on some other cpu then we let it handle it. If we + * were able to cancel the timer nothing can rearm it as we + * own broadcast_lock. + * + * However we can also be called from the event handler of + * ce_broadcast_hrtimer itself when it expires. We cannot + * restart the timer because we are in the callback, but we + * can set the expiry time and let the callback return + * HRTIMER_RESTART. + */ + if (hrtimer_try_to_cancel(&bctimer) >= 0) { + hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED); + /* Bind the "device" to the cpu */ + bc->bound_on = smp_processor_id(); + } else if (bc->bound_on == smp_processor_id()) { + hrtimer_set_expires(&bctimer, expires); + } + return 0; +} + +static struct clock_event_device ce_broadcast_hrtimer = { + .set_mode = bc_set_mode, + .set_next_ktime = bc_set_next, + .features = CLOCK_EVT_FEAT_ONESHOT | + CLOCK_EVT_FEAT_KTIME | + CLOCK_EVT_FEAT_HRTIMER, + .rating = 0, + .bound_on = -1, + .min_delta_ns = 1, + .max_delta_ns = KTIME_MAX, + .min_delta_ticks = 1, + .max_delta_ticks = ULONG_MAX, + .mult = 1, + .shift = 0, + .cpumask = cpu_all_mask, +}; + +static enum hrtimer_restart bc_handler(struct hrtimer *t) +{ + ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer); + + if (ce_broadcast_hrtimer.next_event.tv64 == KTIME_MAX) + return HRTIMER_NORESTART; + + return HRTIMER_RESTART; +} + +void tick_setup_hrtimer_broadcast(void) +{ + hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + bctimer.function = bc_handler; + clockevents_register_device(&ce_broadcast_hrtimer); +} diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 98977a57ac72..64c5990fd500 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -120,6 +120,19 @@ int tick_is_broadcast_device(struct clock_event_device *dev) return (dev && tick_broadcast_device.evtdev == dev); } +int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq) +{ + int ret = -ENODEV; + + if (tick_is_broadcast_device(dev)) { + raw_spin_lock(&tick_broadcast_lock); + ret = __clockevents_update_freq(dev, freq); + raw_spin_unlock(&tick_broadcast_lock); + } + return ret; +} + + static void err_broadcast(const struct cpumask *mask) { pr_crit_once("Failed to broadcast timer tick. Some CPUs may be unresponsive.\n"); @@ -272,12 +285,8 @@ static void tick_do_broadcast(struct cpumask *mask) */ static void tick_do_periodic_broadcast(void) { - raw_spin_lock(&tick_broadcast_lock); - cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask); tick_do_broadcast(tmpmask); - - raw_spin_unlock(&tick_broadcast_lock); } /* @@ -287,13 +296,15 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) { ktime_t next; + raw_spin_lock(&tick_broadcast_lock); + tick_do_periodic_broadcast(); /* * The device is in periodic mode. No reprogramming necessary: */ if (dev->mode == CLOCK_EVT_MODE_PERIODIC) - return; + goto unlock; /* * Setup the next period for devices, which do not have @@ -306,9 +317,11 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) next = ktime_add(next, tick_period); if (!clockevents_program_event(dev, next, false)) - return; + goto unlock; tick_do_periodic_broadcast(); } +unlock: + raw_spin_unlock(&tick_broadcast_lock); } /* @@ -630,24 +643,61 @@ again: raw_spin_unlock(&tick_broadcast_lock); } +static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu) +{ + if (!(bc->features & CLOCK_EVT_FEAT_HRTIMER)) + return 0; + if (bc->next_event.tv64 == KTIME_MAX) + return 0; + return bc->bound_on == cpu ? -EBUSY : 0; +} + +static void broadcast_shutdown_local(struct clock_event_device *bc, + struct clock_event_device *dev) +{ + /* + * For hrtimer based broadcasting we cannot shutdown the cpu + * local device if our own event is the first one to expire or + * if we own the broadcast timer. + */ + if (bc->features & CLOCK_EVT_FEAT_HRTIMER) { + if (broadcast_needs_cpu(bc, smp_processor_id())) + return; + if (dev->next_event.tv64 < bc->next_event.tv64) + return; + } + clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN); +} + +static void broadcast_move_bc(int deadcpu) +{ + struct clock_event_device *bc = tick_broadcast_device.evtdev; + + if (!bc || !broadcast_needs_cpu(bc, deadcpu)) + return; + /* This moves the broadcast assignment to this cpu */ + clockevents_program_event(bc, bc->next_event, 1); +} + /* * Powerstate information: The system enters/leaves a state, where * affected devices might stop + * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups. */ -void tick_broadcast_oneshot_control(unsigned long reason) +int tick_broadcast_oneshot_control(unsigned long reason) { struct clock_event_device *bc, *dev; struct tick_device *td; unsigned long flags; ktime_t now; - int cpu; + int cpu, ret = 0; /* * Periodic mode does not care about the enter/exit of power * states */ if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) - return; + return 0; /* * We are called with preemtion disabled from the depth of the @@ -658,7 +708,7 @@ void tick_broadcast_oneshot_control(unsigned long reason) dev = td->evtdev; if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) - return; + return 0; bc = tick_broadcast_device.evtdev; @@ -666,7 +716,7 @@ void tick_broadcast_oneshot_control(unsigned long reason) if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) { if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) { WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask)); - clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN); + broadcast_shutdown_local(bc, dev); /* * We only reprogram the broadcast timer if we * did not mark ourself in the force mask and @@ -679,6 +729,16 @@ void tick_broadcast_oneshot_control(unsigned long reason) dev->next_event.tv64 < bc->next_event.tv64) tick_broadcast_set_event(bc, cpu, dev->next_event, 1); } + /* + * If the current CPU owns the hrtimer broadcast + * mechanism, it cannot go deep idle and we remove the + * CPU from the broadcast mask. We don't have to go + * through the EXIT path as the local timer is not + * shutdown. + */ + ret = broadcast_needs_cpu(bc, cpu); + if (ret) + cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); } else { if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) { clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT); @@ -746,6 +806,7 @@ void tick_broadcast_oneshot_control(unsigned long reason) } out: raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); + return ret; } /* @@ -852,6 +913,8 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup) cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); cpumask_clear_cpu(cpu, tick_broadcast_force_mask); + broadcast_move_bc(cpu); + raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 20b2fe37d105..015661279b68 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -98,18 +98,19 @@ static void tick_periodic(int cpu) void tick_handle_periodic(struct clock_event_device *dev) { int cpu = smp_processor_id(); - ktime_t next; + ktime_t next = dev->next_event; tick_periodic(cpu); if (dev->mode != CLOCK_EVT_MODE_ONESHOT) return; - /* - * Setup the next period for devices, which do not have - * periodic mode: - */ - next = ktime_add(dev->next_event, tick_period); for (;;) { + /* + * Setup the next period for devices, which do not have + * periodic mode: + */ + next = ktime_add(next, tick_period); + if (!clockevents_program_event(dev, next, false)) return; /* @@ -118,12 +119,11 @@ void tick_handle_periodic(struct clock_event_device *dev) * to be sure we're using a real hardware clocksource. * Otherwise we could get trapped in an infinite * loop, as the tick_periodic() increments jiffies, - * when then will increment time, posibly causing + * which then will increment time, possibly causing * the loop to trigger again and again. */ if (timekeeping_valid_for_hres()) tick_periodic(cpu); - next = ktime_add(next, tick_period); } } diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 8329669b51ec..7ab92b19965a 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -46,7 +46,7 @@ extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)); extern void tick_resume_oneshot(void); # ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc); -extern void tick_broadcast_oneshot_control(unsigned long reason); +extern int tick_broadcast_oneshot_control(unsigned long reason); extern void tick_broadcast_switch_to_oneshot(void); extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup); extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc); @@ -58,7 +58,7 @@ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); } -static inline void tick_broadcast_oneshot_control(unsigned long reason) { } +static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; } static inline void tick_broadcast_switch_to_oneshot(void) { } static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { } static inline int tick_broadcast_oneshot_active(void) { return 0; } @@ -87,7 +87,7 @@ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); } -static inline void tick_broadcast_oneshot_control(unsigned long reason) { } +static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; } static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { } static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc) { @@ -111,6 +111,7 @@ extern int tick_resume_broadcast(void); extern void tick_broadcast_init(void); extern void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast); +int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq); #else /* !BROADCAST */ @@ -133,6 +134,8 @@ static inline void tick_shutdown_broadcast(unsigned int *cpup) { } static inline void tick_suspend_broadcast(void) { } static inline int tick_resume_broadcast(void) { return 0; } static inline void tick_broadcast_init(void) { } +static inline int tick_broadcast_update_freq(struct clock_event_device *dev, + u32 freq) { return -ENODEV; } /* * Set the periodic handler in non broadcast mode @@ -152,6 +155,8 @@ static inline int tick_device_is_functional(struct clock_event_device *dev) return !(dev->features & CLOCK_EVT_FEAT_DUMMY); } +int __clockevents_update_freq(struct clock_event_device *dev, u32 freq); + #endif extern void do_timer(unsigned long ticks); diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index 802433a4f5eb..4d54f97558df 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -21,6 +21,8 @@ #include <linux/seq_file.h> #include <linux/time.h> +#include "timekeeping_internal.h" + static unsigned int sleep_time_bin[32] = {0}; static int tk_debug_show_sleep_time(struct seq_file *s, void *data) diff --git a/kernel/timer.c b/kernel/timer.c index d78de047599b..87bd529879c2 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -81,6 +81,7 @@ struct tvec_base { unsigned long timer_jiffies; unsigned long next_timer; unsigned long active_timers; + unsigned long all_timers; struct tvec_root tv1; struct tvec tv2; struct tvec tv3; @@ -337,6 +338,20 @@ void set_timer_slack(struct timer_list *timer, int slack_hz) } EXPORT_SYMBOL_GPL(set_timer_slack); +/* + * If the list is empty, catch up ->timer_jiffies to the current time. + * The caller must hold the tvec_base lock. Returns true if the list + * was empty and therefore ->timer_jiffies was updated. + */ +static bool catchup_timer_jiffies(struct tvec_base *base) +{ + if (!base->all_timers) { + base->timer_jiffies = jiffies; + return true; + } + return false; +} + static void __internal_add_timer(struct tvec_base *base, struct timer_list *timer) { @@ -383,15 +398,17 @@ __internal_add_timer(struct tvec_base *base, struct timer_list *timer) static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) { + (void)catchup_timer_jiffies(base); __internal_add_timer(base, timer); /* * Update base->active_timers and base->next_timer */ if (!tbase_get_deferrable(timer->base)) { - if (time_before(timer->expires, base->next_timer)) + if (!base->active_timers++ || + time_before(timer->expires, base->next_timer)) base->next_timer = timer->expires; - base->active_timers++; } + base->all_timers++; } #ifdef CONFIG_TIMER_STATS @@ -671,6 +688,8 @@ detach_expired_timer(struct timer_list *timer, struct tvec_base *base) detach_timer(timer, true); if (!tbase_get_deferrable(timer->base)) base->active_timers--; + base->all_timers--; + (void)catchup_timer_jiffies(base); } static int detach_if_pending(struct timer_list *timer, struct tvec_base *base, @@ -685,6 +704,8 @@ static int detach_if_pending(struct timer_list *timer, struct tvec_base *base, if (timer->expires == base->next_timer) base->next_timer = base->timer_jiffies; } + base->all_timers--; + (void)catchup_timer_jiffies(base); return 1; } @@ -739,12 +760,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, debug_activate(timer, expires); - cpu = smp_processor_id(); - -#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP) - if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) - cpu = get_nohz_timer_target(); -#endif + cpu = get_nohz_timer_target(pinned); new_base = per_cpu(tvec_bases, cpu); if (base != new_base) { @@ -939,8 +955,15 @@ void add_timer_on(struct timer_list *timer, int cpu) * with the timer by holding the timer base lock. This also * makes sure that a CPU on the way to stop its tick can not * evaluate the timer wheel. + * + * Spare the IPI for deferrable timers on idle targets though. + * The next busy ticks will take care of it. Except full dynticks + * require special care against races with idle_cpu(), lets deal + * with that later. */ - wake_up_nohz_cpu(cpu); + if (!tbase_get_deferrable(timer->base) || tick_nohz_full_cpu(cpu)) + wake_up_nohz_cpu(cpu); + spin_unlock_irqrestore(&base->lock, flags); } EXPORT_SYMBOL_GPL(add_timer_on); @@ -1146,6 +1169,10 @@ static inline void __run_timers(struct tvec_base *base) struct timer_list *timer; spin_lock_irq(&base->lock); + if (catchup_timer_jiffies(base)) { + spin_unlock_irq(&base->lock); + return; + } while (time_after_eq(jiffies, base->timer_jiffies)) { struct list_head work_list; struct list_head *head = &work_list; @@ -1160,7 +1187,7 @@ static inline void __run_timers(struct tvec_base *base) !cascade(base, &base->tv4, INDEX(2))) cascade(base, &base->tv5, INDEX(3)); ++base->timer_jiffies; - list_replace_init(base->tv1.vec + index, &work_list); + list_replace_init(base->tv1.vec + index, head); while (!list_empty(head)) { void (*fn)(unsigned long); unsigned long data; @@ -1523,9 +1550,8 @@ static int init_timers_cpu(int cpu) if (!base) return -ENOMEM; - /* Make sure that tvec_base is 2 byte aligned */ - if (tbase_get_deferrable(base)) { - WARN_ON(1); + /* Make sure tvec_base has TIMER_FLAG_MASK bits free */ + if (WARN_ON(base != tbase_get_base(base))) { kfree(base); return -ENOMEM; } @@ -1559,6 +1585,7 @@ static int init_timers_cpu(int cpu) base->timer_jiffies = jiffies; base->next_timer = base->timer_jiffies; base->active_timers = 0; + base->all_timers = 0; return 0; } @@ -1648,9 +1675,9 @@ void __init init_timers(void) err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE, (void *)(long)smp_processor_id()); - init_timer_stats(); - BUG_ON(err != NOTIFY_OK); + + init_timer_stats(); register_cpu_notifier(&timers_nb); open_softirq(TIMER_SOFTIRQ, run_timer_softirq); } diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 3fa5b8f3aae3..0ee63af30bd1 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -516,6 +516,13 @@ void destroy_work_on_stack(struct work_struct *work) } EXPORT_SYMBOL_GPL(destroy_work_on_stack); +void destroy_delayed_work_on_stack(struct delayed_work *work) +{ + destroy_timer_on_stack(&work->timer); + debug_object_free(&work->work, &work_debug_descr); +} +EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack); + #else static inline void debug_work_activate(struct work_struct *work) { } static inline void debug_work_deactivate(struct work_struct *work) { } |