diff options
| -rw-r--r-- | fs/proc/base.c | 48 | ||||
| -rw-r--r-- | include/linux/cleanup.h | 22 | ||||
| -rw-r--r-- | include/linux/hrtimer.h | 3 | ||||
| -rw-r--r-- | include/linux/posix-timers.h | 30 | ||||
| -rw-r--r-- | include/linux/sched/signal.h | 3 | ||||
| -rw-r--r-- | include/uapi/linux/prctl.h | 11 | ||||
| -rw-r--r-- | kernel/signal.c | 2 | ||||
| -rw-r--r-- | kernel/sys.c | 5 | ||||
| -rw-r--r-- | kernel/time/clocksource.c | 2 | ||||
| -rw-r--r-- | kernel/time/hrtimer.c | 29 | ||||
| -rw-r--r-- | kernel/time/posix-clock.c | 24 | ||||
| -rw-r--r-- | kernel/time/posix-timers.c | 551 | ||||
| -rw-r--r-- | kernel/time/timekeeping.c | 94 | ||||
| -rw-r--r-- | kernel/time/timer_list.c | 4 | ||||
| -rw-r--r-- | tools/testing/selftests/timers/posix_timers.c | 73 | ||||
| -rw-r--r-- | tools/testing/selftests/timers/skew_consistency.c | 2 |
16 files changed, 524 insertions, 379 deletions
diff --git a/fs/proc/base.c b/fs/proc/base.c index 61526420d0ee..5538c4aee8fa 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2494,11 +2494,9 @@ static const struct file_operations proc_map_files_operations = { #if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS) struct timers_private { - struct pid *pid; - struct task_struct *task; - struct sighand_struct *sighand; - struct pid_namespace *ns; - unsigned long flags; + struct pid *pid; + struct task_struct *task; + struct pid_namespace *ns; }; static void *timers_start(struct seq_file *m, loff_t *pos) @@ -2509,54 +2507,48 @@ static void *timers_start(struct seq_file *m, loff_t *pos) if (!tp->task) return ERR_PTR(-ESRCH); - tp->sighand = lock_task_sighand(tp->task, &tp->flags); - if (!tp->sighand) - return ERR_PTR(-ESRCH); - - return seq_hlist_start(&tp->task->signal->posix_timers, *pos); + rcu_read_lock(); + return seq_hlist_start_rcu(&tp->task->signal->posix_timers, *pos); } static void *timers_next(struct seq_file *m, void *v, loff_t *pos) { struct timers_private *tp = m->private; - return seq_hlist_next(v, &tp->task->signal->posix_timers, pos); + + return seq_hlist_next_rcu(v, &tp->task->signal->posix_timers, pos); } static void timers_stop(struct seq_file *m, void *v) { struct timers_private *tp = m->private; - if (tp->sighand) { - unlock_task_sighand(tp->task, &tp->flags); - tp->sighand = NULL; - } - if (tp->task) { put_task_struct(tp->task); tp->task = NULL; + rcu_read_unlock(); } } static int show_timer(struct seq_file *m, void *v) { - struct k_itimer *timer; - struct timers_private *tp = m->private; - int notify; static const char * const nstr[] = { - [SIGEV_SIGNAL] = "signal", - [SIGEV_NONE] = "none", - [SIGEV_THREAD] = "thread", + [SIGEV_SIGNAL] = "signal", + [SIGEV_NONE] = "none", + [SIGEV_THREAD] = "thread", }; - timer = hlist_entry((struct hlist_node *)v, struct k_itimer, list); - notify = timer->it_sigev_notify; + struct k_itimer *timer = hlist_entry((struct hlist_node *)v, struct k_itimer, list); + struct timers_private *tp = m->private; + int notify = timer->it_sigev_notify; + + guard(spinlock_irq)(&timer->it_lock); + if (!posixtimer_valid(timer)) + return 0; seq_printf(m, "ID: %d\n", timer->it_id); - seq_printf(m, "signal: %d/%px\n", - timer->sigq.info.si_signo, + seq_printf(m, "signal: %d/%px\n", timer->sigq.info.si_signo, timer->sigq.info.si_value.sival_ptr); - seq_printf(m, "notify: %s/%s.%d\n", - nstr[notify & ~SIGEV_THREAD_ID], + seq_printf(m, "notify: %s/%s.%d\n", nstr[notify & ~SIGEV_THREAD_ID], (notify & SIGEV_THREAD_ID) ? "tid" : "pid", pid_nr_ns(timer->it_pid, tp->ns)); seq_printf(m, "ClockID: %d\n", timer->it_clock); diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index f7750eab1832..2b32a5759b22 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -308,11 +308,21 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ #define __DEFINE_CLASS_IS_CONDITIONAL(_name, _is_cond) \ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond -#define DEFINE_GUARD(_name, _type, _lock, _unlock) \ +#define __DEFINE_GUARD_LOCK_PTR(_name, _exp) \ + static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \ + { return (void *)(__force unsigned long)*(_exp); } + +#define DEFINE_CLASS_IS_GUARD(_name) \ __DEFINE_CLASS_IS_CONDITIONAL(_name, false); \ + __DEFINE_GUARD_LOCK_PTR(_name, _T) + +#define DEFINE_CLASS_IS_COND_GUARD(_name) \ + __DEFINE_CLASS_IS_CONDITIONAL(_name, true); \ + __DEFINE_GUARD_LOCK_PTR(_name, _T) + +#define DEFINE_GUARD(_name, _type, _lock, _unlock) \ DEFINE_CLASS(_name, _type, if (_T) { _unlock; }, ({ _lock; _T; }), _type _T); \ - static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \ - { return (void *)(__force unsigned long)*_T; } + DEFINE_CLASS_IS_GUARD(_name) #define DEFINE_GUARD_COND(_name, _ext, _condlock) \ __DEFINE_CLASS_IS_CONDITIONAL(_name##_ext, true); \ @@ -392,11 +402,7 @@ static inline void class_##_name##_destructor(class_##_name##_t *_T) \ if (_T->lock) { _unlock; } \ } \ \ -static inline void *class_##_name##_lock_ptr(class_##_name##_t *_T) \ -{ \ - return (void *)(__force unsigned long)_T->lock; \ -} - +__DEFINE_GUARD_LOCK_PTR(_name, &_T->lock) #define __DEFINE_LOCK_GUARD_1(_name, _type, _lock) \ static inline class_##_name##_t class_##_name##_constructor(_type *l) \ diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index f7bfdcf0dda3..bdd55c1f0d73 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -333,6 +333,7 @@ static inline int hrtimer_callback_running(struct hrtimer *timer) static inline void hrtimer_update_function(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *)) { +#ifdef CONFIG_PROVE_LOCKING guard(raw_spinlock_irqsave)(&timer->base->cpu_base->lock); if (WARN_ON_ONCE(hrtimer_is_queued(timer))) @@ -340,7 +341,7 @@ static inline void hrtimer_update_function(struct hrtimer *timer, if (WARN_ON_ONCE(!function)) return; - +#endif timer->function = function; } diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index f11f10c97bd9..dd48c64b605e 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -114,6 +114,7 @@ bool posixtimer_init_sigqueue(struct sigqueue *q); void posixtimer_send_sigqueue(struct k_itimer *tmr); bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq); void posixtimer_free_timer(struct k_itimer *timer); +long posixtimer_create_prctl(unsigned long ctrl); /* Init task static initializer */ #define INIT_CPU_TIMERBASE(b) { \ @@ -140,6 +141,7 @@ static inline void posixtimer_rearm_itimer(struct task_struct *p) { } static inline bool posixtimer_deliver_signal(struct kernel_siginfo *info, struct sigqueue *timer_sigq) { return false; } static inline void posixtimer_free_timer(struct k_itimer *timer) { } +static inline long posixtimer_create_prctl(unsigned long ctrl) { return -EINVAL; } #endif #ifdef CONFIG_POSIX_CPU_TIMERS_TASK_WORK @@ -177,23 +179,26 @@ static inline void posix_cputimers_init_work(void) { } * @rcu: RCU head for freeing the timer. */ struct k_itimer { - struct hlist_node list; - struct hlist_node ignored_list; + /* 1st cacheline contains read-mostly fields */ struct hlist_node t_hash; - spinlock_t it_lock; - const struct k_clock *kclock; - clockid_t it_clock; + struct hlist_node list; timer_t it_id; + clockid_t it_clock; + int it_sigev_notify; + enum pid_type it_pid_type; + struct signal_struct *it_signal; + const struct k_clock *kclock; + + /* 2nd cacheline and above contain fields which are modified regularly */ + spinlock_t it_lock; int it_status; bool it_sig_periodic; s64 it_overrun; s64 it_overrun_last; unsigned int it_signal_seq; unsigned int it_sigqueue_seq; - int it_sigev_notify; - enum pid_type it_pid_type; ktime_t it_interval; - struct signal_struct *it_signal; + struct hlist_node ignored_list; union { struct pid *it_pid; struct task_struct *it_process; @@ -210,7 +215,7 @@ struct k_itimer { } alarm; } it; struct rcu_head rcu; -}; +} ____cacheline_aligned_in_smp; void run_posix_cpu_timers(void); void posix_cpu_timers_exit(struct task_struct *task); @@ -240,6 +245,13 @@ static inline void posixtimer_sigqueue_putref(struct sigqueue *q) posixtimer_putref(tmr); } + +static inline bool posixtimer_valid(const struct k_itimer *timer) +{ + unsigned long val = (unsigned long)timer->it_signal; + + return !(val & 0x1UL); +} #else /* CONFIG_POSIX_TIMERS */ static inline void posixtimer_sigqueue_getref(struct sigqueue *q) { } static inline void posixtimer_sigqueue_putref(struct sigqueue *q) { } diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index d5d03d919df8..1ef1edbaaf79 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -136,7 +136,8 @@ struct signal_struct { #ifdef CONFIG_POSIX_TIMERS /* POSIX.1b Interval Timers */ - unsigned int next_posix_timer_id; + unsigned int timer_create_restore_ids:1; + atomic_t next_posix_timer_id; struct hlist_head posix_timers; struct hlist_head ignored_posix_timers; diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 5c6080680cb2..15c18ef4eb11 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -353,4 +353,15 @@ struct prctl_mm_map { */ #define PR_LOCK_SHADOW_STACK_STATUS 76 +/* + * Controls the mode of timer_create() for CRIU restore operations. + * Enabling this allows CRIU to restore timers with explicit IDs. + * + * Don't use for normal operations as the result might be undefined. + */ +#define PR_TIMER_CREATE_RESTORE_IDS 77 +# define PR_TIMER_CREATE_RESTORE_IDS_OFF 0 +# define PR_TIMER_CREATE_RESTORE_IDS_ON 1 +# define PR_TIMER_CREATE_RESTORE_IDS_GET 2 + #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/signal.c b/kernel/signal.c index 027ad9e97417..86ba66d95da5 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2092,7 +2092,7 @@ static inline void posixtimer_sig_ignore(struct task_struct *tsk, struct sigqueu * from a non-periodic timer, then just drop the reference * count. Otherwise queue it on the ignored list. */ - if (tmr->it_signal && tmr->it_sig_periodic) + if (posixtimer_valid(tmr) && tmr->it_sig_periodic) hlist_add_head(&tmr->ignored_list, &tsk->signal->ignored_posix_timers); else posixtimer_putref(tmr); diff --git a/kernel/sys.c b/kernel/sys.c index 4efca8a97d62..c434968e9f5d 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2815,6 +2815,11 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, return -EINVAL; error = arch_lock_shadow_stack_status(me, arg2); break; + case PR_TIMER_CREATE_RESTORE_IDS: + if (arg3 || arg4 || arg5) + return -EINVAL; + error = posixtimer_create_prctl(arg2); + break; default: trace_task_prctl_unknown(option, arg2, arg3, arg4, arg5); error = -EINVAL; diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 2a7802ec480c..e0eeacbe2521 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -1510,7 +1510,7 @@ static int __init boot_override_clocksource(char* str) { mutex_lock(&clocksource_mutex); if (str) - strscpy(override_name, str, sizeof(override_name)); + strscpy(override_name, str); mutex_unlock(&clocksource_mutex); return 1; } diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index deb1aa32814e..453dc76c9348 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -117,16 +117,6 @@ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = .csd = CSD_INIT(retrigger_next_event, NULL) }; -static const int hrtimer_clock_to_base_table[MAX_CLOCKS] = { - /* Make sure we catch unsupported clockids */ - [0 ... MAX_CLOCKS - 1] = HRTIMER_MAX_CLOCK_BASES, - - [CLOCK_REALTIME] = HRTIMER_BASE_REALTIME, - [CLOCK_MONOTONIC] = HRTIMER_BASE_MONOTONIC, - [CLOCK_BOOTTIME] = HRTIMER_BASE_BOOTTIME, - [CLOCK_TAI] = HRTIMER_BASE_TAI, -}; - static inline bool hrtimer_base_is_online(struct hrtimer_cpu_base *base) { if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) @@ -1587,14 +1577,19 @@ u64 hrtimer_next_event_without(const struct hrtimer *exclude) static inline int hrtimer_clockid_to_base(clockid_t clock_id) { - if (likely(clock_id < MAX_CLOCKS)) { - int base = hrtimer_clock_to_base_table[clock_id]; - - if (likely(base != HRTIMER_MAX_CLOCK_BASES)) - return base; + switch (clock_id) { + case CLOCK_REALTIME: + return HRTIMER_BASE_REALTIME; + case CLOCK_MONOTONIC: + return HRTIMER_BASE_MONOTONIC; + case CLOCK_BOOTTIME: + return HRTIMER_BASE_BOOTTIME; + case CLOCK_TAI: + return HRTIMER_BASE_TAI; + default: + WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id); + return HRTIMER_BASE_MONOTONIC; } - WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id); - return HRTIMER_BASE_MONOTONIC; } static enum hrtimer_restart hrtimer_dummy_timeout(struct hrtimer *unused) diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index 1af0bb2cc45c..7f4e4fb7381e 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -90,26 +90,6 @@ static long posix_clock_ioctl(struct file *fp, return err; } -#ifdef CONFIG_COMPAT -static long posix_clock_compat_ioctl(struct file *fp, - unsigned int cmd, unsigned long arg) -{ - struct posix_clock_context *pccontext = fp->private_data; - struct posix_clock *clk = get_posix_clock(fp); - int err = -ENOTTY; - - if (!clk) - return -ENODEV; - - if (clk->ops.ioctl) - err = clk->ops.ioctl(pccontext, cmd, arg); - - put_posix_clock(clk); - - return err; -} -#endif - static int posix_clock_open(struct inode *inode, struct file *fp) { int err; @@ -171,11 +151,9 @@ static const struct file_operations posix_clock_file_operations = { .read = posix_clock_read, .poll = posix_clock_poll, .unlocked_ioctl = posix_clock_ioctl, + .compat_ioctl = posix_clock_ioctl, .open = posix_clock_open, .release = posix_clock_release, -#ifdef CONFIG_COMPAT - .compat_ioctl = posix_clock_compat_ioctl, -#endif }; int posix_clock_register(struct posix_clock *clk, struct device *dev) diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 1b675aee99a9..bc0bdf40eb50 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -9,28 +9,23 @@ * * These are all the functions necessary to implement POSIX clocks & timers */ -#include <linux/mm.h> +#include <linux/compat.h> +#include <linux/compiler.h> +#include <linux/init.h> +#include <linux/jhash.h> #include <linux/interrupt.h> -#include <linux/slab.h> -#include <linux/time.h> -#include <linux/mutex.h> -#include <linux/sched/task.h> - -#include <linux/uaccess.h> #include <linux/list.h> -#include <linux/init.h> -#include <linux/compiler.h> -#include <linux/hash.h> +#include <linux/memblock.h> +#include <linux/nospec.h> #include <linux/posix-clock.h> #include <linux/posix-timers.h> +#include <linux/prctl.h> +#include <linux/sched/task.h> +#include <linux/slab.h> #include <linux/syscalls.h> -#include <linux/wait.h> -#include <linux/workqueue.h> -#include <linux/export.h> -#include <linux/hashtable.h> -#include <linux/compat.h> -#include <linux/nospec.h> +#include <linux/time.h> #include <linux/time_namespace.h> +#include <linux/uaccess.h> #include "timekeeping.h" #include "posix-timers.h" @@ -46,39 +41,65 @@ static struct kmem_cache *posix_timers_cache; * This allows checkpoint/restore to reconstruct the exact timer IDs for * a process. */ -static DEFINE_HASHTABLE(posix_timers_hashtable, 9); -static DEFINE_SPINLOCK(hash_lock); +struct timer_hash_bucket { + spinlock_t lock; + struct hlist_head head; +}; + +static struct { + struct timer_hash_bucket *buckets; + unsigned long mask; +} __timer_data __ro_after_init __aligned(2*sizeof(long)); + +#define timer_buckets (__timer_data.buckets) +#define timer_hashmask (__timer_data.mask) static const struct k_clock * const posix_clocks[]; static const struct k_clock *clockid_to_kclock(const clockid_t id); static const struct k_clock clock_realtime, clock_monotonic; +#define TIMER_ANY_ID INT_MIN + /* SIGEV_THREAD_ID cannot share a bit with the other SIGEV values. */ #if SIGEV_THREAD_ID != (SIGEV_THREAD_ID & \ ~(SIGEV_SIGNAL | SIGEV_NONE | SIGEV_THREAD)) #error "SIGEV_THREAD_ID must not share bit with other SIGEV values!" #endif -static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags); +static struct k_itimer *__lock_timer(timer_t timer_id); -#define lock_timer(tid, flags) \ -({ struct k_itimer *__timr; \ - __cond_lock(&__timr->it_lock, __timr = __lock_timer(tid, flags)); \ - __timr; \ +#define lock_timer(tid) \ +({ struct k_itimer *__timr; \ + __cond_lock(&__timr->it_lock, __timr = __lock_timer(tid)); \ + __timr; \ }) -static int hash(struct signal_struct *sig, unsigned int nr) +static inline void unlock_timer(struct k_itimer *timr) { - return hash_32(hash32_ptr(sig) ^ nr, HASH_BITS(posix_timers_hashtable)); + if (likely((timr))) + spin_unlock_irq(&timr->it_lock); } -static struct k_itimer *__posix_timers_find(struct hlist_head *head, - struct signal_struct *sig, - timer_t id) +#define scoped_timer_get_or_fail(_id) \ + scoped_cond_guard(lock_timer, return -EINVAL, _id) + +#define scoped_timer (scope) + +DEFINE_CLASS(lock_timer, struct k_itimer *, unlock_timer(_T), __lock_timer(id), timer_t id); +DEFINE_CLASS_IS_COND_GUARD(lock_timer); + +static struct timer_hash_bucket *hash_bucket(struct signal_struct *sig, unsigned int nr) { + return &timer_buckets[jhash2((u32 *)&sig, sizeof(sig) / sizeof(u32), nr) & timer_hashmask]; +} + +static struct k_itimer *posix_timer_by_id(timer_t id) +{ + struct signal_struct *sig = current->signal; + struct timer_hash_bucket *bucket = hash_bucket(sig, id); struct k_itimer *timer; - hlist_for_each_entry_rcu(timer, head, t_hash, lockdep_is_held(&hash_lock)) { + hlist_for_each_entry_rcu(timer, &bucket->head, t_hash) { /* timer->it_signal can be set concurrently */ if ((READ_ONCE(timer->it_signal) == sig) && (timer->it_id == id)) return timer; @@ -86,46 +107,88 @@ static struct k_itimer *__posix_timers_find(struct hlist_head *head, return NULL; } -static struct k_itimer *posix_timer_by_id(timer_t id) +static inline struct signal_struct *posix_sig_owner(const struct k_itimer *timer) { - struct signal_struct *sig = current->signal; - struct hlist_head *head = &posix_timers_hashtable[hash(sig, id)]; + unsigned long val = (unsigned long)timer->it_signal; - return __posix_timers_find(head, sig, id); + /* + * Mask out bit 0, which acts as invalid marker to prevent + * posix_timer_by_id() detecting it as valid. + */ + return (struct signal_struct *)(val & ~1UL); } -static int posix_timer_add(struct k_itimer *timer) +static bool posix_timer_hashed(struct timer_hash_bucket *bucket, struct signal_struct *sig, + timer_t id) { - struct signal_struct *sig = current->signal; - struct hlist_head *head; - unsigned int cnt, id; + struct hlist_head *head = &bucket->head; + struct k_itimer *timer; - /* - * FIXME: Replace this by a per signal struct xarray once there is - * a plan to handle the resulting CRIU regression gracefully. - */ - for (cnt = 0; cnt <= INT_MAX; cnt++) { - spin_lock(&hash_lock); - id = sig->next_posix_timer_id; + hlist_for_each_entry_rcu(timer, head, t_hash, lockdep_is_held(&bucket->lock)) { + if ((posix_sig_owner(timer) == sig) && (timer->it_id == id)) + return true; + } + return false; +} - /* Write the next ID back. Clamp it to the positive space */ - sig->next_posix_timer_id = (id + 1) & INT_MAX; +static bool posix_timer_add_at(struct k_itimer *timer, struct signal_struct *sig, unsigned int id) +{ + struct timer_hash_bucket *bucket = hash_bucket(sig, id); - head = &posix_timers_hashtable[hash(sig, id)]; - if (!__posix_timers_find(head, sig, id)) { - hlist_add_head_rcu(&timer->t_hash, head); - spin_unlock(&hash_lock); - return id; + scoped_guard (spinlock, &bucket->lock) { + /* + * Validate under the lock as this could have raced against + * another thread ending up with the same ID, which is + * highly unlikely, but possible. + */ + if (!posix_timer_hashed(bucket, sig, id)) { + /* + * Set the timer ID and the signal pointer to make + * it identifiable in the hash table. The signal + * pointer has bit 0 set to indicate that it is not + * yet fully initialized. posix_timer_hashed() + * masks this bit out, but the syscall lookup fails + * to match due to it being set. This guarantees + * that there can't be duplicate timer IDs handed + * out. + */ + timer->it_id = (timer_t)id; + timer->it_signal = (struct signal_struct *)((unsigned long)sig | 1UL); + hlist_add_head_rcu(&timer->t_hash, &bucket->head); + return true; } - spin_unlock(&hash_lock); } - /* POSIX return code when no timer ID could be allocated */ - return -EAGAIN; + return false; } -static inline void unlock_timer(struct k_itimer *timr, unsigned long flags) +static int posix_timer_add(struct k_itimer *timer, int req_id) { - spin_unlock_irqrestore(&timr->it_lock, flags); + struct signal_struct *sig = current->signal; + + if (unlikely(req_id != TIMER_ANY_ID)) { + if (!posix_timer_add_at(timer, sig, req_id)) + return -EBUSY; + + /* + * Move the ID counter past the requested ID, so that after + * switching back to normal mode the IDs are outside of the + * exact allocated region. That avoids ID collisions on the + * next regular timer_create() invocations. + */ + atomic_set(&sig->next_posix_timer_id, req_id + 1); + return req_id; + } + + for (unsigned int cnt = 0; cnt <= INT_MAX; cnt++) { + /* Get the next timer ID and clamp it to positive space */ + unsigned int id = atomic_fetch_inc(&sig->next_posix_timer_id) & INT_MAX; + + if (posix_timer_add_at(timer, sig, id)) + return id; + cond_resched(); + } + /* POSIX return code when no timer ID could be allocated */ + return -EAGAIN; } static int posix_get_realtime_timespec(clockid_t which_clock, struct timespec64 *tp) @@ -222,9 +285,8 @@ static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec64 *tp) static __init int init_posix_timers(void) { - posix_timers_cache = kmem_cache_create("posix_timers_cache", - sizeof(struct k_itimer), 0, - SLAB_PANIC | SLAB_ACCOUNT, NULL); + posix_timers_cache = kmem_cache_create("posix_timers_cache", sizeof(struct k_itimer), + __alignof__(struct k_itimer), SLAB_ACCOUNT, NULL); return 0; } __initcall(init_posix_timers); @@ -259,7 +321,7 @@ static bool __posixtimer_deliver_signal(struct kernel_siginfo *info, struct k_it * since the signal was queued. In either case, don't rearm and * drop the signal. */ - if (timr->it_signal_seq != timr->it_sigqueue_seq || WARN_ON_ONCE(!timr->it_signal)) + if (timr->it_signal_seq != timr->it_sigqueue_seq || WARN_ON_ONCE(!posixtimer_valid(timr))) return false; if (!timr->it_interval || WARN_ON_ONCE(timr->it_status != POSIX_TIMER_REQUEUE_PENDING)) @@ -304,6 +366,9 @@ void posix_timer_queue_signal(struct k_itimer *timr) { lockdep_assert_held(&timr->it_lock); + if (!posixtimer_valid(timr)) + return; + timr->it_status = timr->it_interval ? POSIX_TIMER_REQUEUE_PENDING : POSIX_TIMER_DISARMED; posixtimer_send_sigqueue(timr); } @@ -324,6 +389,21 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) return HRTIMER_NORESTART; } +long posixtimer_create_prctl(unsigned long ctrl) +{ + switch (ctrl) { + case PR_TIMER_CREATE_RESTORE_IDS_OFF: + current->signal->timer_create_restore_ids = 0; + return 0; + case PR_TIMER_CREATE_RESTORE_IDS_ON: + current->signal->timer_create_restore_ids = 1; + return 0; + case PR_TIMER_CREATE_RESTORE_IDS_GET: + return current->signal->timer_create_restore_ids; + } + return -EINVAL; +} + static struct pid *good_sigevent(sigevent_t * event) { struct pid *pid = task_tgid(current); @@ -350,8 +430,12 @@ static struct pid *good_sigevent(sigevent_t * event) static struct k_itimer *alloc_posix_timer(void) { - struct k_itimer *tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL); + struct k_itimer *tmr; + if (unlikely(!posix_timers_cache)) + return NULL; + + tmr = kmem_cache_zalloc(posix_timers_cache, GFP_KERNEL); if (!tmr) return tmr; @@ -373,9 +457,10 @@ void posixtimer_free_timer(struct k_itimer *tmr) static void posix_timer_unhash_and_free(struct k_itimer *tmr) { - spin_lock(&hash_lock); - hlist_del_rcu(&tmr->t_hash); - spin_unlock(&hash_lock); + struct timer_hash_bucket *bucket = hash_bucket(posix_sig_owner(tmr), tmr->it_id); + + scoped_guard (spinlock, &bucket->lock) + hlist_del_rcu(&tmr->t_hash); posixtimer_putref(tmr); } @@ -390,6 +475,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, timer_t __user *created_timer_id) { const struct k_clock *kc = clockid_to_kclock(which_clock); + timer_t req_id = TIMER_ANY_ID; struct k_itimer *new_timer; int error, new_timer_id; @@ -404,26 +490,32 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, spin_lock_init(&new_timer->it_lock); + /* Special case for CRIU to restore timers with a given timer ID. */ + if (unlikely(current->signal->timer_create_restore_ids)) { + if (copy_from_user(&req_id, created_timer_id, sizeof(req_id))) + return -EFAULT; + /* Valid IDs are 0..INT_MAX */ + if ((unsigned int)req_id > INT_MAX) + return -EINVAL; + } + /* * Add the timer to the hash table. The timer is not yet valid - * because new_timer::it_signal is still NULL. The timer id is also - * not yet visible to user space. + * after insertion, but has a unique ID allocated. */ - new_timer_id = posix_timer_add(new_timer); + new_timer_id = posix_timer_add(new_timer, req_id); if (new_timer_id < 0) { posixtimer_free_timer(new_timer); return new_timer_id; } - new_timer->it_id = (timer_t) new_timer_id; new_timer->it_clock = which_clock; new_timer->kclock = kc; new_timer->it_overrun = -1LL; if (event) { - rcu_read_lock(); - new_timer->it_pid = get_pid(good_sigevent(event)); - rcu_read_unlock(); + scoped_guard (rcu) + new_timer->it_pid = get_pid(good_sigevent(event)); if (!new_timer->it_pid) { error = -EINVAL; goto out; @@ -434,7 +526,6 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, } else { new_timer->it_sigev_notify = SIGEV_SIGNAL; new_timer->sigq.info.si_signo = SIGALRM; - memset(&new_timer->sigq.info.si_value, 0, sizeof(sigval_t)); new_timer->sigq.info.si_value.sival_int = new_timer->it_id; new_timer->it_pid = get_pid(task_tgid(current)); } @@ -453,7 +544,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, } /* * After succesful copy out, the timer ID is visible to user space - * now but not yet valid because new_timer::signal is still NULL. + * now but not yet valid because new_timer::signal low order bit is 1. * * Complete the initialization with the clock specific create * callback. @@ -462,14 +553,25 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, if (error) goto out; - spin_lock_irq(¤t->sighand->siglock); - /* This makes the timer valid in the hash table */ - WRITE_ONCE(new_timer->it_signal, current->signal); - hlist_add_head(&new_timer->list, ¤t->signal->posix_timers); - spin_unlock_irq(¤t->sighand->siglock); /* - * After unlocking sighand::siglock @new_timer is subject to - * concurrent removal and cannot be touched anymore + * timer::it_lock ensures that __lock_timer() observes a fully + * initialized timer when it observes a valid timer::it_signal. + * + * sighand::siglock is required to protect signal::posix_timers. + */ + scoped_guard (spinlock_irq, &new_timer->it_lock) { + guard(spinlock)(¤t->sighand->siglock); + /* + * new_timer::it_signal contains the signal pointer with + * bit 0 set, which makes it invalid for syscall operations. + * Store the unmodified signal pointer to make it valid. + */ + WRITE_ONCE(new_timer->it_signal, current->signal); + hlist_add_head_rcu(&new_timer->list, ¤t->signal->posix_timers); + } + /* + * After unlocking @new_timer is subject to concurrent removal and + * cannot be touched anymore */ return 0; out: @@ -507,7 +609,7 @@ COMPAT_SYSCALL_DEFINE3(timer_create, clockid_t, which_clock, } #endif -static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags) +static struct k_itimer *__lock_timer(timer_t timer_id) { struct k_itimer *timr; @@ -522,11 +624,11 @@ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags) * The hash lookup and the timers are RCU protected. * * Timers are added to the hash in invalid state where - * timr::it_signal == NULL. timer::it_signal is only set after the - * rest of the initialization succeeded. + * timr::it_signal is marked invalid. timer::it_signal is only set + * after the rest of the initialization succeeded. * * Timer destruction happens in steps: - * 1) Set timr::it_signal to NULL with timr::it_lock held + * 1) Set timr::it_signal marked invalid with timr::it_lock held * 2) Release timr::it_lock * 3) Remove from the hash under hash_lock * 4) Put the reference count. @@ -543,25 +645,21 @@ static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags) * * The lookup validates locklessly that timr::it_signal == * current::it_signal and timr::it_id == @timer_id. timr::it_id - * can't change, but timr::it_signal becomes NULL during - * destruction. + * can't change, but timr::it_signal can become invalid during + * destruction, which makes the locked check fail. */ - rcu_read_lock(); + guard(rcu)(); timr = posix_timer_by_id(timer_id); if (timr) { - spin_lock_irqsave(&timr->it_lock, *flags); + spin_lock_irq(&timr->it_lock); /* * Validate under timr::it_lock that timr::it_signal is * still valid. Pairs with #1 above. */ - if (timr->it_signal == current->signal) { - rcu_read_unlock(); + if (timr->it_signal == current->signal) return timr; - } - spin_unlock_irqrestore(&timr->it_lock, *flags); + spin_unlock_irq(&timr->it_lock); } - rcu_read_unlock(); - return NULL; } @@ -652,24 +750,10 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting) static int do_timer_gettime(timer_t timer_id, struct itimerspec64 *setting) { - const struct k_clock *kc; - struct k_itimer *timr; - unsigned long flags; - int ret = 0; - - timr = lock_timer(timer_id, &flags); - if (!timr) - return -EINVAL; - memset(setting, 0, sizeof(*setting)); - kc = timr->kclock; - if (WARN_ON_ONCE(!kc || !kc->timer_get)) - ret = -EINVAL; - else - kc->timer_get(timr, setting); - - unlock_timer(timr, flags); - return ret; + scoped_timer_get_or_fail(timer_id) + scoped_timer->kclock->timer_get(scoped_timer, setting); + return 0; } /* Get the time remaining on a POSIX.1b interval timer. */ @@ -723,18 +807,8 @@ SYSCALL_DEFINE2(timer_gettime32, timer_t, timer_id, */ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id) { - struct k_itimer *timr; - unsigned long flags; - int overrun; - - timr = lock_timer(timer_id, &flags); - if (!timr) - return -EINVAL; - - overrun = timer_overrun_to_int(timr); - unlock_timer(timr, flags); - - return overrun; + scoped_timer_get_or_fail(timer_id) + return timer_overrun_to_int(scoped_timer); } static void common_hrtimer_arm(struct k_itimer *timr, ktime_t expires, @@ -791,26 +865,13 @@ static void common_timer_wait_running(struct k_itimer *timer) * when the task which tries to delete or disarm the timer has preempted * the task which runs the expiry in task work context. */ -static struct k_itimer *timer_wait_running(struct k_itimer *timer, - unsigned long *flags) +static void timer_wait_running(struct k_itimer *timer) { - const struct k_clock *kc = READ_ONCE(timer->kclock); - timer_t timer_id = READ_ONCE(timer->it_id); - - /* Prevent kfree(timer) after dropping the lock */ - rcu_read_lock(); - unlock_timer(timer, *flags); - /* * kc->timer_wait_running() might drop RCU lock. So @timer * cannot be touched anymore after the function returns! */ - if (!WARN_ON_ONCE(!kc->timer_wait_running)) - kc->timer_wait_running(timer); - - rcu_read_unlock(); - /* Relock the timer. It might be not longer hashed. */ - return lock_timer(timer_id, flags); + timer->kclock->timer_wait_running(timer); } /* @@ -865,15 +926,9 @@ int common_timer_set(struct k_itimer *timr, int flags, return 0; } -static int do_timer_settime(timer_t timer_id, int tmr_flags, - struct itimerspec64 *new_spec64, +static int do_timer_settime(timer_t timer_id, int tmr_flags, struct itimerspec64 *new_spec64, struct itimerspec64 *old_spec64) { - const struct k_clock *kc; - struct k_itimer *timr; - unsigned long flags; - int error; - if (!timespec64_valid(&new_spec64->it_interval) || !timespec64_valid(&new_spec64->it_value)) return -EINVAL; @@ -881,33 +936,28 @@ static int do_timer_settime(timer_t timer_id, int tmr_flags, if (old_spec64) memset(old_spec64, 0, sizeof(*old_spec64)); - timr = lock_timer(timer_id, &flags); -retry: - if (!timr) - return -EINVAL; + for (; ; old_spec64 = NULL) { + struct k_itimer *timr; - if (old_spec64) - old_spec64->it_interval = ktime_to_timespec64(timr->it_interval); + scoped_timer_get_or_fail(timer_id) { + timr = scoped_timer; - /* Prevent signal delivery and rearming. */ - timr->it_signal_seq++; + if (old_spec64) + old_spec64->it_interval = ktime_to_timespec64(timr->it_interval); - kc = timr->kclock; - if (WARN_ON_ONCE(!kc || !kc->timer_set)) - error = -EINVAL; - else - error = kc->timer_set(timr, tmr_flags, new_spec64, old_spec64); - - if (error == TIMER_RETRY) { - // We already got the old time... - old_spec64 = NULL; - /* Unlocks and relocks the timer if it still exists */ - timr = timer_wait_running(timr, &flags); - goto retry; - } - unlock_timer(timr, flags); + /* Prevent signal delivery and rearming. */ + timr->it_signal_seq++; - return error; + int ret = timr->kclock->timer_set(timr, tmr_flags, new_spec64, old_spec64); + if (ret != TIMER_RETRY) + return ret; + + /* Protect the timer from being freed when leaving the lock scope */ + rcu_read_lock(); + } + timer_wait_running(timr); + rcu_read_unlock(); + } } /* Set a POSIX.1b interval timer */ @@ -978,110 +1028,58 @@ static inline void posix_timer_cleanup_ignored(struct k_itimer *tmr) } } -static inline int timer_delete_hook(struct k_itimer *timer) +static void posix_timer_delete(struct k_itimer *timer) { - const struct k_clock *kc = timer->kclock; - - /* Prevent signal delivery and rearming. */ + /* + * Invalidate the timer, remove it from the linked list and remove + * it from the ignored list if pending. + * + * The invalidation must be written with siglock held so that the + * signal code observes the invalidated timer::it_signal in + * do_sigaction(), which prevents it from moving a pending signal + * of a deleted timer to the ignore list. + * + * The invalidation also prevents signal queueing, signal delivery + * and therefore rearming from the signal delivery path. + * + * A concurrent lookup can still find the timer in the hash, but it + * will check timer::it_signal with timer::it_lock held and observe + * bit 0 set, which invalidates it. That also prevents the timer ID + * from being handed out before this timer is completely gone. + */ timer->it_signal_seq++; - if (WARN_ON_ONCE(!kc || !kc->timer_del)) - return -EINVAL; - return kc->timer_del(timer); + scoped_guard (spinlock, ¤t->sighand->siglock) { + unsigned long sig = (unsigned long)timer->it_signal | 1UL; + + WRITE_ONCE(timer->it_signal, (struct signal_struct *)sig); + hlist_del_rcu(&timer->list); + posix_timer_cleanup_ignored(timer); + } + + while (timer->kclock->timer_del(timer) == TIMER_RETRY) { + guard(rcu)(); + spin_unlock_irq(&timer->it_lock); + timer_wait_running(timer); + spin_lock_irq(&timer->it_lock); + } } /* Delete a POSIX.1b interval timer. */ SYSCALL_DEFINE1(timer_delete, timer_t, timer_id) { struct k_itimer *timer; - unsigned long flags; - timer = lock_timer(timer_id, &flags); - -retry_delete: - if (!timer) - return -EINVAL; - - if (unlikely(timer_delete_hook(timer) == TIMER_RETRY)) { - /* Unlocks and relocks the timer if it still exists */ - timer = timer_wait_running(timer, &flags); - goto retry_delete; + scoped_timer_get_or_fail(timer_id) { + timer = scoped_timer; + posix_timer_delete(timer); } - - spin_lock(¤t->sighand->siglock); - hlist_del(&timer->list); - posix_timer_cleanup_ignored(timer); - /* - * A concurrent lookup could check timer::it_signal lockless. It - * will reevaluate with timer::it_lock held and observe the NULL. - * - * It must be written with siglock held so that the signal code - * observes timer->it_signal == NULL in do_sigaction(SIG_IGN), - * which prevents it from moving a pending signal of a deleted - * timer to the ignore list. - */ - WRITE_ONCE(timer->it_signal, NULL); - spin_unlock(¤t->sighand->siglock); - - unlock_timer(timer, flags); + /* Remove it from the hash, which frees up the timer ID */ posix_timer_unhash_and_free(timer); return 0; } /* - * Delete a timer if it is armed, remove it from the hash and schedule it - * for RCU freeing. - */ -static void itimer_delete(struct k_itimer *timer) -{ - unsigned long flags; - - /* - * irqsave is required to make timer_wait_running() work. - */ - spin_lock_irqsave(&timer->it_lock, flags); - -retry_delete: - /* - * Even if the timer is not longer accessible from other tasks - * it still might be armed and queued in the underlying timer - * mechanism. Worse, that timer mechanism might run the expiry - * function concurrently. - */ - if (timer_delete_hook(timer) == TIMER_RETRY) { - /* - * Timer is expired concurrently, prevent livelocks - * and pointless spinning on RT. - * - * timer_wait_running() drops timer::it_lock, which opens - * the possibility for another task to delete the timer. - * - * That's not possible here because this is invoked from - * do_exit() only for the last thread of the thread group. - * So no other task can access and delete that timer. - */ - if (WARN_ON_ONCE(timer_wait_running(timer, &flags) != timer)) - return; - - goto retry_delete; - } - hlist_del(&timer->list); - - posix_timer_cleanup_ignored(timer); - - /* - * Setting timer::it_signal to NULL is technically not required - * here as nothing can access the timer anymore legitimately via - * the hash table. Set it to NULL nevertheless so that all deletion - * paths are consistent. - */ - WRITE_ONCE(timer->it_signal, NULL); - - spin_unlock_irqrestore(&timer->it_lock, flags); - posix_timer_unhash_and_free(timer); -} - -/* * Invoked from do_exit() when the last thread of a thread group exits. * At that point no other task can access the timers of the dying * task anymore. @@ -1089,18 +1087,26 @@ retry_delete: void exit_itimers(struct task_struct *tsk) { struct hlist_head timers; + struct hlist_node *next; + struct k_itimer *timer; + + /* Clear restore mode for exec() */ + tsk->signal->timer_create_restore_ids = 0; if (hlist_empty(&tsk->signal->posix_timers)) return; /* Protect against concurrent read via /proc/$PID/timers */ - spin_lock_irq(&tsk->sighand->siglock); - hlist_move_list(&tsk->signal->posix_timers, &timers); - spin_unlock_irq(&tsk->sighand->siglock); + scoped_guard (spinlock_irq, &tsk->sighand->siglock) + hlist_move_list(&tsk->signal->posix_timers, &timers); /* The timers are not longer accessible via tsk::signal */ - while (!hlist_empty(&timers)) - itimer_delete(hlist_entry(timers.first, struct k_itimer, list)); + hlist_for_each_entry_safe(timer, next, &timers, list) { + scoped_guard (spinlock_irq, &timer->it_lock) + posix_timer_delete(timer); + posix_timer_unhash_and_free(timer); + cond_resched(); + } /* * There should be no timers on the ignored list. itimer_delete() has @@ -1545,3 +1551,26 @@ static const struct k_clock *clockid_to_kclock(const clockid_t id) return posix_clocks[array_index_nospec(idx, ARRAY_SIZE(posix_clocks))]; } + +static int __init posixtimer_init(void) +{ + unsigned long i, size; + unsigned int shift; + + if (IS_ENABLED(CONFIG_BASE_SMALL)) + size = 512; + else + size = roundup_pow_of_two(512 * num_possible_cpus()); + + timer_buckets = alloc_large_system_hash("posixtimers", sizeof(*timer_buckets), + size, 0, 0, &shift, NULL, size, size); + size = 1UL << shift; + timer_hashmask = size - 1; + + for (i = 0; i < size; i++) { + spin_lock_init(&timer_buckets[i].lock); + INIT_HLIST_HEAD(&timer_buckets[i].head); + } + return 0; +} +core_initcall(posixtimer_init); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 1e67d076f195..929846b8b45a 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -682,20 +682,19 @@ static void timekeeping_update_from_shadow(struct tk_data *tkd, unsigned int act } /** - * timekeeping_forward_now - update clock to the current time + * timekeeping_forward - update clock to given cycle now value * @tk: Pointer to the timekeeper to update + * @cycle_now: Current clocksource read value * * Forward the current clock to update its state since the last call to * update_wall_time(). This is useful before significant clock changes, * as it avoids having to deal with this time offset explicitly. */ -static void timekeeping_forward_now(struct timekeeper *tk) +static void timekeeping_forward(struct timekeeper *tk, u64 cycle_now) { - u64 cycle_now, delta; + u64 delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask, + tk->tkr_mono.clock->max_raw_delta); - cycle_now = tk_clock_read(&tk->tkr_mono); - delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask, - tk->tkr_mono.clock->max_raw_delta); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; @@ -711,6 +710,21 @@ static void timekeeping_forward_now(struct timekeeper *tk) } /** + * timekeeping_forward_now - update clock to the current time + * @tk: Pointer to the timekeeper to update + * + * Forward the current clock to update its state since the last call to + * update_wall_time(). This is useful before significant clock changes, + * as it avoids having to deal with this time offset explicitly. + */ +static void timekeeping_forward_now(struct timekeeper *tk) +{ + u64 cycle_now = tk_clock_read(&tk->tkr_mono); + + timekeeping_forward(tk, cycle_now); +} + +/** * ktime_get_real_ts64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * @@ -2151,6 +2165,54 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, return offset; } +static u64 timekeeping_accumulate(struct timekeeper *tk, u64 offset, + enum timekeeping_adv_mode mode, + unsigned int *clock_set) +{ + int shift = 0, maxshift; + + /* + * TK_ADV_FREQ indicates that adjtimex(2) directly set the + * frequency or the tick length. + * + * Accumulate the offset, so that the new multiplier starts from + * now. This is required as otherwise for offsets, which are + * smaller than tk::cycle_interval, timekeeping_adjust() could set + * xtime_nsec backwards, which subsequently causes time going + * backwards in the coarse time getters. But even for the case + * where offset is greater than tk::cycle_interval the periodic + * accumulation does not have much value. + * + * Also reset tk::ntp_error as it does not make sense to keep the + * old accumulated error around in this case. + */ + if (mode == TK_ADV_FREQ) { + timekeeping_forward(tk, tk->tkr_mono.cycle_last + offset); + tk->ntp_error = 0; + return 0; + } + + /* + * With NO_HZ we may have to accumulate many cycle_intervals + * (think "ticks") worth of time at once. To do this efficiently, + * we calculate the largest doubling multiple of cycle_intervals + * that is smaller than the offset. We then accumulate that + * chunk in one go, and then try to consume the next smaller + * doubled multiple. + */ + shift = ilog2(offset) - ilog2(tk->cycle_interval); + shift = max(0, shift); + /* Bound shift to one less than what overflows tick_length */ + maxshift = (64 - (ilog2(ntp_tick_length()) + 1)) - 1; + shift = min(shift, maxshift); + while (offset >= tk->cycle_interval) { + offset = logarithmic_accumulation(tk, offset, shift, clock_set); + if (offset < tk->cycle_interval << shift) + shift--; + } + return offset; +} + /* * timekeeping_advance - Updates the timekeeper to the current time and * current NTP tick length @@ -2160,7 +2222,6 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) struct timekeeper *tk = &tk_core.shadow_timekeeper; struct timekeeper *real_tk = &tk_core.timekeeper; unsigned int clock_set = 0; - int shift = 0, maxshift; u64 offset; guard(raw_spinlock_irqsave)(&tk_core.lock); @@ -2177,24 +2238,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) return false; - /* - * With NO_HZ we may have to accumulate many cycle_intervals - * (think "ticks") worth of time at once. To do this efficiently, - * we calculate the largest doubling multiple of cycle_intervals - * that is smaller than the offset. We then accumulate that - * chunk in one go, and then try to consume the next smaller - * doubled multiple. - */ - shift = ilog2(offset) - ilog2(tk->cycle_interval); - shift = max(0, shift); - /* Bound shift to one less than what overflows tick_length */ - maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; - shift = min(shift, maxshift); - while (offset >= tk->cycle_interval) { - offset = logarithmic_accumulation(tk, offset, shift, &clock_set); - if (offset < tk->cycle_interval<<shift) - shift--; - } + offset = timekeeping_accumulate(tk, offset, mode, &clock_set); /* Adjust the multiplier to correct NTP error */ timekeeping_adjust(tk, offset); diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index 1c311c46da50..cfbb46cc4e76 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -46,7 +46,7 @@ static void print_timer(struct seq_file *m, struct hrtimer *taddr, struct hrtimer *timer, int idx, u64 now) { - SEQ_printf(m, " #%d: <%pK>, %ps", idx, taddr, timer->function); + SEQ_printf(m, " #%d: <%p>, %ps", idx, taddr, timer->function); SEQ_printf(m, ", S:%02x", timer->state); SEQ_printf(m, "\n"); SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n", @@ -98,7 +98,7 @@ next_one: static void print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now) { - SEQ_printf(m, " .base: %pK\n", base); + SEQ_printf(m, " .base: %p\n", base); SEQ_printf(m, " .index: %d\n", base->index); SEQ_printf(m, " .resolution: %u nsecs\n", hrtimer_resolution); diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c index 9814b3a1c77d..f0eceb0faf34 100644 --- a/tools/testing/selftests/timers/posix_timers.c +++ b/tools/testing/selftests/timers/posix_timers.c @@ -7,6 +7,7 @@ * Kernel loop code stolen from Steven Rostedt <srostedt@redhat.com> */ #define _GNU_SOURCE +#include <sys/prctl.h> #include <sys/time.h> #include <sys/types.h> #include <stdio.h> @@ -599,14 +600,84 @@ static void check_overrun(int which, const char *name) "check_overrun %s\n", name); } +#include <sys/syscall.h> + +static int do_timer_create(int *id) +{ + return syscall(__NR_timer_create, CLOCK_MONOTONIC, NULL, id); +} + +static int do_timer_delete(int id) +{ + return syscall(__NR_timer_delete, id); +} + +#ifndef PR_TIMER_CREATE_RESTORE_IDS +# define PR_TIMER_CREATE_RESTORE_IDS 77 +# define PR_TIMER_CREATE_RESTORE_IDS_OFF 0 +# define PR_TIMER_CREATE_RESTORE_IDS_ON 1 +# define PR_TIMER_CREATE_RESTORE_IDS_GET 2 +#endif + +static void check_timer_create_exact(void) +{ + int id; + + if (prctl(PR_TIMER_CREATE_RESTORE_IDS, PR_TIMER_CREATE_RESTORE_IDS_ON, 0, 0, 0)) { + switch (errno) { + case EINVAL: + ksft_test_result_skip("check timer create exact, not supported\n"); + return; + default: + ksft_test_result_skip("check timer create exact, errno = %d\n", errno); + return; + } + } + + if (prctl(PR_TIMER_CREATE_RESTORE_IDS, PR_TIMER_CREATE_RESTORE_IDS_GET, 0, 0, 0) != 1) + fatal_error(NULL, "prctl(GET) failed\n"); + + id = 8; + if (do_timer_create(&id) < 0) + fatal_error(NULL, "timer_create()"); + + if (do_timer_delete(id)) + fatal_error(NULL, "timer_delete()"); + + if (prctl(PR_TIMER_CREATE_RESTORE_IDS, PR_TIMER_CREATE_RESTORE_IDS_OFF, 0, 0, 0)) + fatal_error(NULL, "prctl(OFF)"); + + if (prctl(PR_TIMER_CREATE_RESTORE_IDS, PR_TIMER_CREATE_RESTORE_IDS_GET, 0, 0, 0) != 0) + fatal_error(NULL, "prctl(GET) failed\n"); + + if (id != 8) { + ksft_test_result_fail("check timer create exact %d != 8\n", id); + return; + } + + /* Validate that it went back to normal mode and allocates ID 9 */ + if (do_timer_create(&id) < 0) + fatal_error(NULL, "timer_create()"); + + if (do_timer_delete(id)) + fatal_error(NULL, "timer_delete()"); + + if (id == 9) + ksft_test_result_pass("check timer create exact\n"); + else + ksft_test_result_fail("check timer create exact. Disabling failed.\n"); +} + int main(int argc, char **argv) { ksft_print_header(); - ksft_set_plan(18); + ksft_set_plan(19); ksft_print_msg("Testing posix timers. False negative may happen on CPU execution \n"); ksft_print_msg("based timers if other threads run on the CPU...\n"); + check_timer_create_exact(); + check_itimer(ITIMER_VIRTUAL, "ITIMER_VIRTUAL"); check_itimer(ITIMER_PROF, "ITIMER_PROF"); check_itimer(ITIMER_REAL, "ITIMER_REAL"); diff --git a/tools/testing/selftests/timers/skew_consistency.c b/tools/testing/selftests/timers/skew_consistency.c index 83450145fe65..46c391d7f45d 100644 --- a/tools/testing/selftests/timers/skew_consistency.c +++ b/tools/testing/selftests/timers/skew_consistency.c @@ -47,7 +47,7 @@ int main(int argc, char **argv) pid = fork(); if (!pid) - return system("./inconsistency-check -c 1 -t 600"); + return system("./inconsistency-check -t 60"); ppm = 500; ret = 0; |