X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fposix-cpu-timers.c;h=7c3e1e6dfb5b5eef84f61f6259e764703846d9fd;hb=ac08c26492a0ad4d94a25bd47d5630cd38337069;hp=91a8942649413f48916196f4aed68deed9a1ae2b;hpb=708f430dcc50787d1c0b5c31962a5ff0dd8e35eb;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index 91a8942..7c3e1e6 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -7,7 +7,7 @@ #include #include -static int check_clock(clockid_t which_clock) +static int check_clock(const clockid_t which_clock) { int error = 0; struct task_struct *p; @@ -31,19 +31,19 @@ static int check_clock(clockid_t which_clock) } static inline union cpu_time_count -timespec_to_sample(clockid_t which_clock, const struct timespec *tp) +timespec_to_sample(const clockid_t which_clock, const struct timespec *tp) { union cpu_time_count ret; ret.sched = 0; /* high half always zero when .cpu used */ if (CPUCLOCK_WHICH(which_clock) == CPUCLOCK_SCHED) { - ret.sched = tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec; + ret.sched = (unsigned long long)tp->tv_sec * NSEC_PER_SEC + tp->tv_nsec; } else { ret.cpu = timespec_to_cputime(tp); } return ret; } -static void sample_to_timespec(clockid_t which_clock, +static void sample_to_timespec(const clockid_t which_clock, union cpu_time_count cpu, struct timespec *tp) { @@ -55,7 +55,7 @@ static void sample_to_timespec(clockid_t which_clock, } } -static inline int cpu_time_before(clockid_t which_clock, +static inline int cpu_time_before(const clockid_t which_clock, union cpu_time_count now, union cpu_time_count then) { @@ -65,7 +65,7 @@ static inline int cpu_time_before(clockid_t which_clock, return cputime_lt(now.cpu, then.cpu); } } -static inline void cpu_time_add(clockid_t which_clock, +static inline void cpu_time_add(const clockid_t which_clock, union cpu_time_count *acc, union cpu_time_count val) { @@ -75,7 +75,7 @@ static inline void cpu_time_add(clockid_t which_clock, acc->cpu = cputime_add(acc->cpu, val.cpu); } } -static inline union cpu_time_count cpu_time_sub(clockid_t which_clock, +static inline union cpu_time_count cpu_time_sub(const clockid_t which_clock, union cpu_time_count a, union cpu_time_count b) { @@ -88,6 +88,19 @@ static inline union cpu_time_count cpu_time_sub(clockid_t which_clock, } /* + * Divide and limit the result to res >= 1 + * + * This is necessary to prevent signal delivery starvation, when the result of + * the division would be rounded down to 0. + */ +static inline cputime_t cputime_div_non_zero(cputime_t time, unsigned long div) +{ + cputime_t res = cputime_div(time, div); + + return max_t(cputime_t, res, 1); +} + +/* * Update expiry time from increment, and increase overrun count, * given the current clock sample. */ @@ -151,7 +164,7 @@ static inline unsigned long long sched_ns(struct task_struct *p) return (p == current) ? current_sched_time(p) : p->sched_time; } -int posix_cpu_clock_getres(clockid_t which_clock, struct timespec *tp) +int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp) { int error = check_clock(which_clock); if (!error) { @@ -169,7 +182,7 @@ int posix_cpu_clock_getres(clockid_t which_clock, struct timespec *tp) return error; } -int posix_cpu_clock_set(clockid_t which_clock, const struct timespec *tp) +int posix_cpu_clock_set(const clockid_t which_clock, const struct timespec *tp) { /* * You can never reset a CPU clock, but we check for other errors @@ -186,7 +199,7 @@ int posix_cpu_clock_set(clockid_t which_clock, const struct timespec *tp) /* * Sample a per-thread clock for the given task. */ -static int cpu_clock_sample(clockid_t which_clock, struct task_struct *p, +static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, union cpu_time_count *cpu) { switch (CPUCLOCK_WHICH(which_clock)) { @@ -238,18 +251,7 @@ static int cpu_clock_sample_group_locked(unsigned int clock_idx, while ((t = next_thread(t)) != p) { cpu->sched += t->sched_time; } - if (p->tgid == current->tgid) { - /* - * We're sampling ourselves, so include the - * cycles not yet banked. We still omit - * other threads running on other CPUs, - * so the total can always be behind as - * much as max(nthreads-1,ncpus) * (NSEC_PER_SEC/HZ). - */ - cpu->sched += current_sched_time(current); - } else { - cpu->sched += p->sched_time; - } + cpu->sched += sched_ns(p); break; } return 0; @@ -259,7 +261,7 @@ static int cpu_clock_sample_group_locked(unsigned int clock_idx, * Sample a process (thread group) clock for the given group_leader task. * Must be called with tasklist_lock held for reading. */ -static int cpu_clock_sample_group(clockid_t which_clock, +static int cpu_clock_sample_group(const clockid_t which_clock, struct task_struct *p, union cpu_time_count *cpu) { @@ -273,7 +275,7 @@ static int cpu_clock_sample_group(clockid_t which_clock, } -int posix_cpu_clock_get(clockid_t which_clock, struct timespec *tp) +int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp) { const pid_t pid = CPUCLOCK_PID(which_clock); int error = -EINVAL; @@ -494,10 +496,10 @@ static void process_timer_rebalance(struct task_struct *p, BUG(); break; case CPUCLOCK_PROF: - left = cputime_div(cputime_sub(expires.cpu, val.cpu), - nthreads); + left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu), + nthreads); do { - if (!unlikely(t->flags & PF_EXITING)) { + if (likely(!(t->flags & PF_EXITING))) { ticks = cputime_add(prof_ticks(t), left); if (cputime_eq(t->it_prof_expires, cputime_zero) || @@ -509,10 +511,10 @@ static void process_timer_rebalance(struct task_struct *p, } while (t != p); break; case CPUCLOCK_VIRT: - left = cputime_div(cputime_sub(expires.cpu, val.cpu), - nthreads); + left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu), + nthreads); do { - if (!unlikely(t->flags & PF_EXITING)) { + if (likely(!(t->flags & PF_EXITING))) { ticks = cputime_add(virt_ticks(t), left); if (cputime_eq(t->it_virt_expires, cputime_zero) || @@ -526,8 +528,9 @@ static void process_timer_rebalance(struct task_struct *p, case CPUCLOCK_SCHED: nsleft = expires.sched - val.sched; do_div(nsleft, nthreads); + nsleft = max_t(unsigned long long, nsleft, 1); do { - if (!unlikely(t->flags & PF_EXITING)) { + if (likely(!(t->flags & PF_EXITING))) { ns = t->sched_time + nsleft; if (t->it_sched_expires == 0 || t->it_sched_expires > ns) { @@ -566,9 +569,6 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) struct cpu_timer_list *next; unsigned long i; - if (CPUCLOCK_PERTHREAD(timer->it_clock) && (p->flags & PF_EXITING)) - return; - head = (CPUCLOCK_PERTHREAD(timer->it_clock) ? p->cpu_timers : p->signal->cpu_timers); head += CPUCLOCK_WHICH(timer->it_clock); @@ -1173,17 +1173,21 @@ static void check_process_timers(struct task_struct *tsk, prof_left = cputime_sub(prof_expires, utime); prof_left = cputime_sub(prof_left, stime); - prof_left = cputime_div(prof_left, nthreads); + prof_left = cputime_div_non_zero(prof_left, nthreads); virt_left = cputime_sub(virt_expires, utime); - virt_left = cputime_div(virt_left, nthreads); + virt_left = cputime_div_non_zero(virt_left, nthreads); if (sched_expires) { sched_left = sched_expires - sched_time; do_div(sched_left, nthreads); + sched_left = max_t(unsigned long long, sched_left, 1); } else { sched_left = 0; } t = tsk; do { + if (unlikely(t->flags & PF_EXITING)) + continue; + ticks = cputime_add(cputime_add(t->utime, t->stime), prof_left); if (!cputime_eq(prof_expires, cputime_zero) && @@ -1204,11 +1208,7 @@ static void check_process_timers(struct task_struct *tsk, t->it_sched_expires > sched)) { t->it_sched_expires = sched; } - - do { - t = next_thread(t); - } while (unlikely(t->flags & PF_EXITING)); - } while (t != tsk); + } while ((t = next_thread(t)) != tsk); } } @@ -1300,30 +1300,30 @@ void run_posix_cpu_timers(struct task_struct *tsk) #undef UNEXPIRED - BUG_ON(tsk->exit_state); - /* * Double-check with locks held. */ read_lock(&tasklist_lock); - spin_lock(&tsk->sighand->siglock); + if (likely(tsk->signal != NULL)) { + spin_lock(&tsk->sighand->siglock); - /* - * Here we take off tsk->cpu_timers[N] and tsk->signal->cpu_timers[N] - * all the timers that are firing, and put them on the firing list. - */ - check_thread_timers(tsk, &firing); - check_process_timers(tsk, &firing); + /* + * Here we take off tsk->cpu_timers[N] and tsk->signal->cpu_timers[N] + * all the timers that are firing, and put them on the firing list. + */ + check_thread_timers(tsk, &firing); + check_process_timers(tsk, &firing); - /* - * We must release these locks before taking any timer's lock. - * There is a potential race with timer deletion here, as the - * siglock now protects our private firing list. We have set - * the firing flag in each timer, so that a deletion attempt - * that gets the timer lock before we do will give it up and - * spin until we've taken care of that timer below. - */ - spin_unlock(&tsk->sighand->siglock); + /* + * We must release these locks before taking any timer's lock. + * There is a potential race with timer deletion here, as the + * siglock now protects our private firing list. We have set + * the firing flag in each timer, so that a deletion attempt + * that gets the timer lock before we do will give it up and + * spin until we've taken care of that timer below. + */ + spin_unlock(&tsk->sighand->siglock); + } read_unlock(&tasklist_lock); /* @@ -1408,25 +1408,13 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, } } -static long posix_cpu_clock_nanosleep_restart(struct restart_block *); - -int posix_cpu_nsleep(clockid_t which_clock, int flags, - struct timespec *rqtp) +static int do_cpu_nanosleep(const clockid_t which_clock, int flags, + struct timespec *rqtp, struct itimerspec *it) { - struct restart_block *restart_block = - ¤t_thread_info()->restart_block; struct k_itimer timer; int error; /* - * Diagnose required errors first. - */ - if (CPUCLOCK_PERTHREAD(which_clock) && - (CPUCLOCK_PID(which_clock) == 0 || - CPUCLOCK_PID(which_clock) == current->pid)) - return -EINVAL; - - /* * Set up a temporary timer and then wait for it to go off. */ memset(&timer, 0, sizeof timer); @@ -1436,13 +1424,13 @@ int posix_cpu_nsleep(clockid_t which_clock, int flags, error = posix_cpu_timer_create(&timer); timer.it_process = current; if (!error) { - struct timespec __user *rmtp; static struct itimerspec zero_it; - struct itimerspec it = { .it_value = *rqtp, - .it_interval = {} }; + + memset(it, 0, sizeof *it); + it->it_value = *rqtp; spin_lock_irq(&timer.it_lock); - error = posix_cpu_timer_set(&timer, flags, &it, NULL); + error = posix_cpu_timer_set(&timer, flags, it, NULL); if (error) { spin_unlock_irq(&timer.it_lock); return error; @@ -1470,55 +1458,102 @@ int posix_cpu_nsleep(clockid_t which_clock, int flags, * We were interrupted by a signal. */ sample_to_timespec(which_clock, timer.it.cpu.expires, rqtp); - posix_cpu_timer_set(&timer, 0, &zero_it, &it); + posix_cpu_timer_set(&timer, 0, &zero_it, it); spin_unlock_irq(&timer.it_lock); - if ((it.it_value.tv_sec | it.it_value.tv_nsec) == 0) { + if ((it->it_value.tv_sec | it->it_value.tv_nsec) == 0) { /* * It actually did fire already. */ return 0; } + error = -ERESTART_RESTARTBLOCK; + } + + return error; +} + +int posix_cpu_nsleep(const clockid_t which_clock, int flags, + struct timespec *rqtp, struct timespec __user *rmtp) +{ + struct restart_block *restart_block = + ¤t_thread_info()->restart_block; + struct itimerspec it; + int error; + + /* + * Diagnose required errors first. + */ + if (CPUCLOCK_PERTHREAD(which_clock) && + (CPUCLOCK_PID(which_clock) == 0 || + CPUCLOCK_PID(which_clock) == current->pid)) + return -EINVAL; + + error = do_cpu_nanosleep(which_clock, flags, rqtp, &it); + + if (error == -ERESTART_RESTARTBLOCK) { + + if (flags & TIMER_ABSTIME) + return -ERESTARTNOHAND; /* - * Report back to the user the time still remaining. - */ - rmtp = (struct timespec __user *) restart_block->arg1; - if (rmtp != NULL && !(flags & TIMER_ABSTIME) && - copy_to_user(rmtp, &it.it_value, sizeof *rmtp)) + * Report back to the user the time still remaining. + */ + if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp)) return -EFAULT; - restart_block->fn = posix_cpu_clock_nanosleep_restart; - /* Caller already set restart_block->arg1 */ + restart_block->fn = posix_cpu_nsleep_restart; restart_block->arg0 = which_clock; + restart_block->arg1 = (unsigned long) rmtp; restart_block->arg2 = rqtp->tv_sec; restart_block->arg3 = rqtp->tv_nsec; - - error = -ERESTART_RESTARTBLOCK; } - return error; } -static long -posix_cpu_clock_nanosleep_restart(struct restart_block *restart_block) +long posix_cpu_nsleep_restart(struct restart_block *restart_block) { clockid_t which_clock = restart_block->arg0; - struct timespec t = { .tv_sec = restart_block->arg2, - .tv_nsec = restart_block->arg3 }; + struct timespec __user *rmtp; + struct timespec t; + struct itimerspec it; + int error; + + rmtp = (struct timespec __user *) restart_block->arg1; + t.tv_sec = restart_block->arg2; + t.tv_nsec = restart_block->arg3; + restart_block->fn = do_no_restart_syscall; - return posix_cpu_nsleep(which_clock, TIMER_ABSTIME, &t); + error = do_cpu_nanosleep(which_clock, TIMER_ABSTIME, &t, &it); + + if (error == -ERESTART_RESTARTBLOCK) { + /* + * Report back to the user the time still remaining. + */ + if (rmtp != NULL && copy_to_user(rmtp, &it.it_value, sizeof *rmtp)) + return -EFAULT; + + restart_block->fn = posix_cpu_nsleep_restart; + restart_block->arg0 = which_clock; + restart_block->arg1 = (unsigned long) rmtp; + restart_block->arg2 = t.tv_sec; + restart_block->arg3 = t.tv_nsec; + } + return error; + } #define PROCESS_CLOCK MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED) #define THREAD_CLOCK MAKE_THREAD_CPUCLOCK(0, CPUCLOCK_SCHED) -static int process_cpu_clock_getres(clockid_t which_clock, struct timespec *tp) +static int process_cpu_clock_getres(const clockid_t which_clock, + struct timespec *tp) { return posix_cpu_clock_getres(PROCESS_CLOCK, tp); } -static int process_cpu_clock_get(clockid_t which_clock, struct timespec *tp) +static int process_cpu_clock_get(const clockid_t which_clock, + struct timespec *tp) { return posix_cpu_clock_get(PROCESS_CLOCK, tp); } @@ -1527,16 +1562,23 @@ static int process_cpu_timer_create(struct k_itimer *timer) timer->it_clock = PROCESS_CLOCK; return posix_cpu_timer_create(timer); } -static int process_cpu_nsleep(clockid_t which_clock, int flags, - struct timespec *rqtp) +static int process_cpu_nsleep(const clockid_t which_clock, int flags, + struct timespec *rqtp, + struct timespec __user *rmtp) { - return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp); + return posix_cpu_nsleep(PROCESS_CLOCK, flags, rqtp, rmtp); } -static int thread_cpu_clock_getres(clockid_t which_clock, struct timespec *tp) +static long process_cpu_nsleep_restart(struct restart_block *restart_block) +{ + return -EINVAL; +} +static int thread_cpu_clock_getres(const clockid_t which_clock, + struct timespec *tp) { return posix_cpu_clock_getres(THREAD_CLOCK, tp); } -static int thread_cpu_clock_get(clockid_t which_clock, struct timespec *tp) +static int thread_cpu_clock_get(const clockid_t which_clock, + struct timespec *tp) { return posix_cpu_clock_get(THREAD_CLOCK, tp); } @@ -1545,8 +1587,12 @@ static int thread_cpu_timer_create(struct k_itimer *timer) timer->it_clock = THREAD_CLOCK; return posix_cpu_timer_create(timer); } -static int thread_cpu_nsleep(clockid_t which_clock, int flags, - struct timespec *rqtp) +static int thread_cpu_nsleep(const clockid_t which_clock, int flags, + struct timespec *rqtp, struct timespec __user *rmtp) +{ + return -EINVAL; +} +static long thread_cpu_nsleep_restart(struct restart_block *restart_block) { return -EINVAL; } @@ -1559,6 +1605,7 @@ static __init int init_posix_cpu_timers(void) .clock_set = do_posix_clock_nosettime, .timer_create = process_cpu_timer_create, .nsleep = process_cpu_nsleep, + .nsleep_restart = process_cpu_nsleep_restart, }; struct k_clock thread = { .clock_getres = thread_cpu_clock_getres, @@ -1566,6 +1613,7 @@ static __init int init_posix_cpu_timers(void) .clock_set = do_posix_clock_nosettime, .timer_create = thread_cpu_timer_create, .nsleep = thread_cpu_nsleep, + .nsleep_restart = thread_cpu_nsleep_restart, }; register_posix_clock(CLOCK_PROCESS_CPUTIME_ID, &process);