#include <linux/list.h>
#include <linux/init.h>
#include <linux/compiler.h>
-#include <linux/idr.h>
+#include <linux/hash.h>
+#include <linux/posix-clock.h>
#include <linux/posix-timers.h>
#include <linux/syscalls.h>
#include <linux/wait.h>
#include <linux/workqueue.h>
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/hashtable.h>
/*
- * Management arrays for POSIX timers. Timers are kept in slab memory
- * Timer ids are allocated by an external routine that keeps track of the
- * id and the timer. The external interface is:
- *
- * void *idr_find(struct idr *idp, int id); to find timer_id <id>
- * int idr_get_new(struct idr *idp, void *ptr); to get a new id and
- * related it to <ptr>
- * void idr_remove(struct idr *idp, int id); to release <id>
- * void idr_init(struct idr *idp); to initialize <idp>
- * which we supply.
- * The idr_get_new *may* call slab for more memory so it must not be
- * called under a spin lock. Likewise idr_remore may release memory
- * (but it may be ok to do this under a lock...).
- * idr_find is just a memory look up and is quite fast. A -1 return
- * indicates that the requested id does not exist.
+ * Management arrays for POSIX timers. Timers are now kept in static hash table
+ * with 512 entries.
+ * Timer ids are allocated by local routine, which selects proper hash head by
+ * key, constructed from current->signal address and per signal struct counter.
+ * This keeps timer ids unique per process, but now they can intersect between
+ * processes.
*/
/*
* Lets keep our timers in a slab cache :-)
*/
static struct kmem_cache *posix_timers_cache;
-static struct idr posix_timers_id;
-static DEFINE_SPINLOCK(idr_lock);
+
+static DEFINE_HASHTABLE(posix_timers_hashtable, 9);
+static DEFINE_SPINLOCK(hash_lock);
/*
* we assume that the new SIGEV_THREAD_ID shares no bits with the other
/*
* CLOCKs: The POSIX standard calls for a couple of clocks and allows us
* to implement others. This structure defines the various
- * clocks and allows the possibility of adding others. We
- * provide an interface to add clocks to the table and expect
- * the "arch" code to add at least one clock that is high
- * resolution. Here we define the standard CLOCK_REALTIME as a
- * 1/HZ resolution clock.
+ * clocks.
*
* RESOLUTION: Clock resolution is used to round up timer and interval
* times, NOT to report clock times, which are reported with as
* necessary code is written. The standard says we should say
* something about this issue in the documentation...
*
- * FUNCTIONS: The CLOCKs structure defines possible functions to handle
- * various clock functions. For clocks that use the standard
- * system timer code these entries should be NULL. This will
- * allow dispatch without the overhead of indirect function
- * calls. CLOCKS that depend on other sources (e.g. WWV or GPS)
- * must supply functions here, even if the function just returns
- * ENOSYS. The standard POSIX timer management code assumes the
- * following: 1.) The k_itimer struct (sched.h) is used for the
- * timer. 2.) The list, it_lock, it_clock, it_id and it_pid
- * fields are not modified by timer code.
+ * FUNCTIONS: The CLOCKs structure defines possible functions to
+ * handle various clock functions.
*
- * At this time all functions EXCEPT clock_nanosleep can be
- * redirected by the CLOCKS structure. Clock_nanosleep is in
- * there, but the code ignores it.
+ * The standard POSIX timer management code assumes the
+ * following: 1.) The k_itimer struct (sched.h) is used for
+ * the timer. 2.) The list, it_lock, it_clock, it_id and
+ * it_pid fields are not modified by timer code.
*
* Permissions: It is assumed that the clock_settime() function defined
* for each clock will take care of permission checks. Some
__timr; \
})
-static inline void unlock_timer(struct k_itimer *timr, unsigned long flags)
+static int hash(struct signal_struct *sig, unsigned int nr)
{
- spin_unlock_irqrestore(&timr->it_lock, flags);
+ return hash_32(hash32_ptr(sig) ^ nr, HASH_BITS(posix_timers_hashtable));
}
-/*
- * Call the k_clock hook function if non-null, or the default function.
- */
-#define CLOCK_DISPATCH(clock, call, arglist) \
- ((clock) < 0 ? posix_cpu_##call arglist : \
- (posix_clocks[clock].call != NULL \
- ? (*posix_clocks[clock].call) arglist : common_##call arglist))
+static struct k_itimer *__posix_timers_find(struct hlist_head *head,
+ struct signal_struct *sig,
+ timer_t id)
+{
+ struct k_itimer *timer;
-/*
- * Return nonzero if we know a priori this clockid_t value is bogus.
- */
-static inline int invalid_clockid(const clockid_t which_clock)
+ hlist_for_each_entry_rcu(timer, head, t_hash) {
+ if ((timer->it_signal == sig) && (timer->it_id == id))
+ return timer;
+ }
+ return NULL;
+}
+
+static struct k_itimer *posix_timer_by_id(timer_t id)
{
- if (which_clock < 0) /* CPU clock, posix_cpu_* will check it */
- return 0;
- if ((unsigned) which_clock >= MAX_CLOCKS)
- return 1;
- if (posix_clocks[which_clock].clock_getres != NULL)
- return 0;
- return 1;
+ struct signal_struct *sig = current->signal;
+ struct hlist_head *head = &posix_timers_hashtable[hash(sig, id)];
+
+ return __posix_timers_find(head, sig, id);
+}
+
+static int posix_timer_add(struct k_itimer *timer)
+{
+ struct signal_struct *sig = current->signal;
+ int first_free_id = sig->posix_timer_id;
+ struct hlist_head *head;
+ int ret = -ENOENT;
+
+ do {
+ spin_lock(&hash_lock);
+ head = &posix_timers_hashtable[hash(sig, sig->posix_timer_id)];
+ if (!__posix_timers_find(head, sig, sig->posix_timer_id)) {
+ hlist_add_head_rcu(&timer->t_hash, head);
+ ret = sig->posix_timer_id;
+ }
+ if (++sig->posix_timer_id < 0)
+ sig->posix_timer_id = 0;
+ if ((sig->posix_timer_id == first_free_id) && (ret == -ENOENT))
+ /* Loop over all possible ids completed */
+ ret = -EAGAIN;
+ spin_unlock(&hash_lock);
+ } while (ret == -ENOENT);
+ return ret;
+}
+
+static inline void unlock_timer(struct k_itimer *timr, unsigned long flags)
+{
+ spin_unlock_irqrestore(&timr->it_lock, flags);
}
/* Get clock_realtime */
return do_sys_settimeofday(tp, NULL);
}
+static int posix_clock_realtime_adj(const clockid_t which_clock,
+ struct timex *t)
+{
+ return do_adjtimex(t);
+}
+
/*
* Get monotonic time for posix timers
*/
}
/*
- * Get monotonic time for posix timers
+ * Get monotonic-raw time for posix timers
*/
static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
{
*tp = ktime_to_timespec(KTIME_LOW_RES);
return 0;
}
+
+static int posix_get_boottime(const clockid_t which_clock, struct timespec *tp)
+{
+ get_monotonic_boottime(tp);
+ return 0;
+}
+
+static int posix_get_tai(clockid_t which_clock, struct timespec *tp)
+{
+ timekeeping_clocktai(tp);
+ return 0;
+}
+
/*
* Initialize everything, well, just everything in Posix clocks/timers ;)
*/
.clock_getres = hrtimer_get_res,
.clock_get = posix_clock_realtime_get,
.clock_set = posix_clock_realtime_set,
+ .clock_adj = posix_clock_realtime_adj,
.nsleep = common_nsleep,
.nsleep_restart = hrtimer_nanosleep_restart,
.timer_create = common_timer_create,
.timer_set = common_timer_set,
+ .timer_get = common_timer_get,
+ .timer_del = common_timer_del,
};
struct k_clock clock_monotonic = {
.clock_getres = hrtimer_get_res,
.nsleep_restart = hrtimer_nanosleep_restart,
.timer_create = common_timer_create,
.timer_set = common_timer_set,
+ .timer_get = common_timer_get,
+ .timer_del = common_timer_del,
};
struct k_clock clock_monotonic_raw = {
.clock_getres = hrtimer_get_res,
.clock_getres = posix_get_coarse_res,
.clock_get = posix_get_monotonic_coarse,
};
+ struct k_clock clock_tai = {
+ .clock_getres = hrtimer_get_res,
+ .clock_get = posix_get_tai,
+ .nsleep = common_nsleep,
+ .nsleep_restart = hrtimer_nanosleep_restart,
+ .timer_create = common_timer_create,
+ .timer_set = common_timer_set,
+ .timer_get = common_timer_get,
+ .timer_del = common_timer_del,
+ };
+ struct k_clock clock_boottime = {
+ .clock_getres = hrtimer_get_res,
+ .clock_get = posix_get_boottime,
+ .nsleep = common_nsleep,
+ .nsleep_restart = hrtimer_nanosleep_restart,
+ .timer_create = common_timer_create,
+ .timer_set = common_timer_set,
+ .timer_get = common_timer_get,
+ .timer_del = common_timer_del,
+ };
- register_posix_clock(CLOCK_REALTIME, &clock_realtime);
- register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic);
- register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
- register_posix_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
- register_posix_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
+ posix_timers_register_clock(CLOCK_REALTIME, &clock_realtime);
+ posix_timers_register_clock(CLOCK_MONOTONIC, &clock_monotonic);
+ posix_timers_register_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
+ posix_timers_register_clock(CLOCK_REALTIME_COARSE, &clock_realtime_coarse);
+ posix_timers_register_clock(CLOCK_MONOTONIC_COARSE, &clock_monotonic_coarse);
+ posix_timers_register_clock(CLOCK_BOOTTIME, &clock_boottime);
+ posix_timers_register_clock(CLOCK_TAI, &clock_tai);
posix_timers_cache = kmem_cache_create("posix_timers_cache",
sizeof (struct k_itimer), 0, SLAB_PANIC,
NULL);
- idr_init(&posix_timers_id);
return 0;
}
* restarted (i.e. we have flagged this in the sys_private entry of the
* info block).
*
- * To protect aginst the timer going away while the interrupt is queued,
+ * To protect against the timer going away while the interrupt is queued,
* we require that the it_requeue_pending flag be set.
*/
void do_schedule_next_timer(struct siginfo *info)
return task_pid(rtn);
}
-void register_posix_clock(const clockid_t clock_id, struct k_clock *new_clock)
+void posix_timers_register_clock(const clockid_t clock_id,
+ struct k_clock *new_clock)
{
if ((unsigned) clock_id >= MAX_CLOCKS) {
printk(KERN_WARNING "POSIX clock register failed for clock_id %d\n",
posix_clocks[clock_id] = *new_clock;
}
-EXPORT_SYMBOL_GPL(register_posix_clock);
+EXPORT_SYMBOL_GPL(posix_timers_register_clock);
static struct k_itimer * alloc_posix_timer(void)
{
return tmr;
}
+static void k_itimer_rcu_free(struct rcu_head *head)
+{
+ struct k_itimer *tmr = container_of(head, struct k_itimer, it.rcu);
+
+ kmem_cache_free(posix_timers_cache, tmr);
+}
+
#define IT_ID_SET 1
#define IT_ID_NOT_SET 0
static void release_posix_timer(struct k_itimer *tmr, int it_id_set)
{
if (it_id_set) {
unsigned long flags;
- spin_lock_irqsave(&idr_lock, flags);
- idr_remove(&posix_timers_id, tmr->it_id);
- spin_unlock_irqrestore(&idr_lock, flags);
+ spin_lock_irqsave(&hash_lock, flags);
+ hlist_del_rcu(&tmr->t_hash);
+ spin_unlock_irqrestore(&hash_lock, flags);
}
put_pid(tmr->it_pid);
sigqueue_free(tmr->sigq);
- kmem_cache_free(posix_timers_cache, tmr);
+ call_rcu(&tmr->it.rcu, k_itimer_rcu_free);
}
static struct k_clock *clockid_to_kclock(const clockid_t id)
{
if (id < 0)
- return &clock_posix_cpu;
+ return (id & CLOCKFD_MASK) == CLOCKFD ?
+ &clock_posix_dynamic : &clock_posix_cpu;
if (id >= MAX_CLOCKS || !posix_clocks[id].clock_getres)
return NULL;
return -EAGAIN;
spin_lock_init(&new_timer->it_lock);
- retry:
- if (unlikely(!idr_pre_get(&posix_timers_id, GFP_KERNEL))) {
- error = -EAGAIN;
- goto out;
- }
- spin_lock_irq(&idr_lock);
- error = idr_get_new(&posix_timers_id, new_timer, &new_timer_id);
- spin_unlock_irq(&idr_lock);
- if (error) {
- if (error == -EAGAIN)
- goto retry;
- /*
- * Weird looking, but we return EAGAIN if the IDR is
- * full (proper POSIX return value for this)
- */
- error = -EAGAIN;
+ new_timer_id = posix_timer_add(new_timer);
+ if (new_timer_id < 0) {
+ error = new_timer_id;
goto out;
}
static struct k_itimer *__lock_timer(timer_t timer_id, unsigned long *flags)
{
struct k_itimer *timr;
+
/*
- * Watch out here. We do a irqsave on the idr_lock and pass the
- * flags part over to the timer lock. Must not let interrupts in
- * while we are moving the lock.
+ * timer_t could be any type >= int and we want to make sure any
+ * @timer_id outside positive int range fails lookup.
*/
- spin_lock_irqsave(&idr_lock, *flags);
- timr = idr_find(&posix_timers_id, (int)timer_id);
+ if ((unsigned long long)timer_id > INT_MAX)
+ return NULL;
+
+ rcu_read_lock();
+ timr = posix_timer_by_id(timer_id);
if (timr) {
- spin_lock(&timr->it_lock);
+ spin_lock_irqsave(&timr->it_lock, *flags);
if (timr->it_signal == current->signal) {
- spin_unlock(&idr_lock);
+ rcu_read_unlock();
return timr;
}
- spin_unlock(&timr->it_lock);
+ spin_unlock_irqrestore(&timr->it_lock, *flags);
}
- spin_unlock_irqrestore(&idr_lock, *flags);
+ rcu_read_unlock();
return NULL;
}
SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
struct itimerspec __user *, setting)
{
- struct k_itimer *timr;
struct itimerspec cur_setting;
+ struct k_itimer *timr;
+ struct k_clock *kc;
unsigned long flags;
+ int ret = 0;
timr = lock_timer(timer_id, &flags);
if (!timr)
return -EINVAL;
- CLOCK_DISPATCH(timr->it_clock, timer_get, (timr, &cur_setting));
+ kc = clockid_to_kclock(timr->it_clock);
+ if (WARN_ON_ONCE(!kc || !kc->timer_get))
+ ret = -EINVAL;
+ else
+ kc->timer_get(timr, &cur_setting);
unlock_timer(timr, flags);
- if (copy_to_user(setting, &cur_setting, sizeof (cur_setting)))
+ if (!ret && copy_to_user(setting, &cur_setting, sizeof (cur_setting)))
return -EFAULT;
- return 0;
+ return ret;
}
/*
return error;
}
-static inline int common_timer_del(struct k_itimer *timer)
+static int common_timer_del(struct k_itimer *timer)
{
timer->it.real.interval.tv64 = 0;
static inline int timer_delete_hook(struct k_itimer *timer)
{
- return CLOCK_DISPATCH(timer->it_clock, timer_del, (timer));
+ struct k_clock *kc = clockid_to_kclock(timer->it_clock);
+
+ if (WARN_ON_ONCE(!kc || !kc->timer_del))
+ return -EINVAL;
+ return kc->timer_del(timer);
}
/* Delete a POSIX.1b interval timer. */
return error;
}
+SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock,
+ struct timex __user *, utx)
+{
+ struct k_clock *kc = clockid_to_kclock(which_clock);
+ struct timex ktx;
+ int err;
+
+ if (!kc)
+ return -EINVAL;
+ if (!kc->clock_adj)
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&ktx, utx, sizeof(ktx)))
+ return -EFAULT;
+
+ err = kc->clock_adj(which_clock, &ktx);
+
+ if (err >= 0 && copy_to_user(utx, &ktx, sizeof(ktx)))
+ return -EFAULT;
+
+ return err;
+}
+
SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock,
struct timespec __user *, tp)
{
*/
long clock_nanosleep_restart(struct restart_block *restart_block)
{
- clockid_t which_clock = restart_block->nanosleep.index;
+ clockid_t which_clock = restart_block->nanosleep.clockid;
struct k_clock *kc = clockid_to_kclock(which_clock);
if (WARN_ON_ONCE(!kc || !kc->nsleep_restart))