diff options
50 files changed, 1507 insertions, 1045 deletions
diff --git a/arch/alpha/kernel/osf_sys.c b/arch/alpha/kernel/osf_sys.c index 8509dad31204..8e19acbf2886 100644 --- a/arch/alpha/kernel/osf_sys.c +++ b/arch/alpha/kernel/osf_sys.c @@ -986,10 +986,12 @@ asmlinkage int osf_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval32 __user *tvp) { - s64 timeout = MAX_SCHEDULE_TIMEOUT; + struct timespec end_time, *to = NULL; if (tvp) { time_t sec, usec; + to = &end_time; + if (!access_ok(VERIFY_READ, tvp, sizeof(*tvp)) || __get_user(sec, &tvp->tv_sec) || __get_user(usec, &tvp->tv_usec)) { @@ -999,14 +1001,13 @@ osf_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, if (sec < 0 || usec < 0) return -EINVAL; - if ((unsigned long) sec < MAX_SELECT_SECONDS) { - timeout = (usec + 1000000/HZ - 1) / (1000000/HZ); - timeout += sec * (unsigned long) HZ; - } + if (poll_select_set_timeout(to, sec, usec * NSEC_PER_USEC)) + return -EINVAL; + } /* OSF does not copy back the remaining time. */ - return core_sys_select(n, inp, outp, exp, &timeout); + return core_sys_select(n, inp, outp, exp, to); } struct rusage32 { diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c index c0699f0e35a9..a312c9e9b9ef 100644 --- a/arch/ia64/kvm/kvm-ia64.c +++ b/arch/ia64/kvm/kvm-ia64.c @@ -1114,7 +1114,7 @@ static void kvm_migrate_hlt_timer(struct kvm_vcpu *vcpu) struct hrtimer *p_ht = &vcpu->arch.hlt_timer; if (hrtimer_cancel(p_ht)) - hrtimer_start(p_ht, p_ht->expires, HRTIMER_MODE_ABS); + hrtimer_start_expires(p_ht, HRTIMER_MODE_ABS); } static enum hrtimer_restart hlt_timer_fn(struct hrtimer *data) diff --git a/arch/powerpc/oprofile/cell/spu_profiler.c b/arch/powerpc/oprofile/cell/spu_profiler.c index 380d7e217531..02ffe060db51 100644 --- a/arch/powerpc/oprofile/cell/spu_profiler.c +++ b/arch/powerpc/oprofile/cell/spu_profiler.c @@ -196,7 +196,7 @@ int start_spu_profiling(unsigned int cycles_reset) pr_debug("timer resolution: %lu\n", TICK_NSEC); kt = ktime_set(0, profiling_interval); hrtimer_init(&timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - timer.expires = kt; + hrtimer_set_expires(&timer, kt); timer.function = profile_spus; /* Allocate arrays for collecting SPU PC samples */ diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 634132a9a512..944c435c0e33 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -204,10 +204,10 @@ static int __pit_timer_fn(struct kvm_kpit_state *ps) if (vcpu0 && waitqueue_active(&vcpu0->wq)) wake_up_interruptible(&vcpu0->wq); - pt->timer.expires = ktime_add_ns(pt->timer.expires, pt->period); - pt->scheduled = ktime_to_ns(pt->timer.expires); + hrtimer_add_expires_ns(&pt->timer, pt->period); + pt->scheduled = ktime_to_ns(hrtimer_get_expires(&pt->timer)); if (pt->period) - ps->channels[0].count_load_time = pt->timer.expires; + ps->channels[0].count_load_time = hrtimer_get_expires(&pt->timer); return (pt->period == 0 ? 0 : 1); } @@ -257,7 +257,7 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu) timer = &pit->pit_state.pit_timer.timer; if (hrtimer_cancel(timer)) - hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS); + hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } static void destroy_pit_timer(struct kvm_kpit_timer *pt) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 6571926bfd33..0fc3cab48943 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -946,9 +946,7 @@ static int __apic_timer_fn(struct kvm_lapic *apic) if (apic_lvtt_period(apic)) { result = 1; - apic->timer.dev.expires = ktime_add_ns( - apic->timer.dev.expires, - apic->timer.period); + hrtimer_add_expires_ns(&apic->timer.dev, apic->timer.period); } return result; } @@ -1117,7 +1115,7 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) timer = &apic->timer.dev; if (hrtimer_cancel(timer)) - hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS); + hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu) diff --git a/drivers/clocksource/acpi_pm.c b/drivers/clocksource/acpi_pm.c index 71d2ac4e3f46..c20171078d1d 100644 --- a/drivers/clocksource/acpi_pm.c +++ b/drivers/clocksource/acpi_pm.c @@ -237,9 +237,12 @@ static int __init parse_pmtmr(char *arg) if (strict_strtoul(arg, 16, &base)) return -EINVAL; - +#ifdef CONFIG_X86_64 + if (base > UINT_MAX) + return -ERANGE; +#endif printk(KERN_INFO "PMTMR IOPort override: 0x%04x -> 0x%04lx\n", - (unsigned int)pmtmr_ioport, base); + pmtmr_ioport, base); pmtmr_ioport = base; return 1; diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 5ce07b517c58..2e3148499368 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -16,6 +16,7 @@ #include <linux/cpu.h> #include <linux/cpuidle.h> #include <linux/ktime.h> +#include <linux/hrtimer.h> #include "cpuidle.h" @@ -60,6 +61,12 @@ static void cpuidle_idle_call(void) return; } + /* + * run any timers that can be run now, at this point + * before calculating the idle duration etc. + */ + hrtimer_peek_ahead_timers(); + /* ask the governor for the next state */ next_state = cpuidle_curr_governor->select(dev); if (need_resched()) diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c index 326db1e827c4..e3fe6838293a 100644 --- a/drivers/s390/crypto/ap_bus.c +++ b/drivers/s390/crypto/ap_bus.c @@ -659,9 +659,9 @@ static ssize_t poll_timeout_store(struct bus_type *bus, const char *buf, hr_time = ktime_set(0, poll_timeout); if (!hrtimer_is_queued(&ap_poll_timer) || - !hrtimer_forward(&ap_poll_timer, ap_poll_timer.expires, hr_time)) { - ap_poll_timer.expires = hr_time; - hrtimer_start(&ap_poll_timer, hr_time, HRTIMER_MODE_ABS); + !hrtimer_forward(&ap_poll_timer, hrtimer_get_expires(&ap_poll_timer), hr_time)) { + hrtimer_set_expires(&ap_poll_timer, hr_time); + hrtimer_start_expires(&ap_poll_timer, HRTIMER_MODE_ABS); } return count; } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index c76afa26edf7..83d72006e29d 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1333,20 +1333,15 @@ static void fill_prstatus(struct elf_prstatus *prstatus, prstatus->pr_pgrp = task_pgrp_vnr(p); prstatus->pr_sid = task_session_vnr(p); if (thread_group_leader(p)) { + struct task_cputime cputime; + /* - * This is the record for the group leader. Add in the - * cumulative times of previous dead threads. This total - * won't include the time of each live thread whose state - * is included in the core dump. The final total reported - * to our parent process when it calls wait4 will include - * those sums as well as the little bit more time it takes - * this and each other thread to finish dying after the - * core dump synchronization phase. + * This is the record for the group leader. It shows the + * group-wide total, not its individual thread total. */ - cputime_to_timeval(cputime_add(p->utime, p->signal->utime), - &prstatus->pr_utime); - cputime_to_timeval(cputime_add(p->stime, p->signal->stime), - &prstatus->pr_stime); + thread_group_cputime(p, &cputime); + cputime_to_timeval(cputime.utime, &prstatus->pr_utime); + cputime_to_timeval(cputime.stime, &prstatus->pr_stime); } else { cputime_to_timeval(p->utime, &prstatus->pr_utime); cputime_to_timeval(p->stime, &prstatus->pr_stime); diff --git a/fs/compat.c b/fs/compat.c index 5f9ec449c799..3b58c32be526 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1475,6 +1475,57 @@ out_ret: #define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t)) +static int poll_select_copy_remaining(struct timespec *end_time, void __user *p, + int timeval, int ret) +{ + struct timespec ts; + + if (!p) + return ret; + + if (current->personality & STICKY_TIMEOUTS) + goto sticky; + + /* No update for zero timeout */ + if (!end_time->tv_sec && !end_time->tv_nsec) + return ret; + + ktime_get_ts(&ts); + ts = timespec_sub(*end_time, ts); + if (ts.tv_sec < 0) + ts.tv_sec = ts.tv_nsec = 0; + + if (timeval) { + struct compat_timeval rtv; + + rtv.tv_sec = ts.tv_sec; + rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC; + + if (!copy_to_user(p, &rtv, sizeof(rtv))) + return ret; + } else { + struct compat_timespec rts; + + rts.tv_sec = ts.tv_sec; + rts.tv_nsec = ts.tv_nsec; + + if (!copy_to_user(p, &rts, sizeof(rts))) + return ret; + } + /* + * If an application puts its timeval in read-only memory, we + * don't want the Linux-specific update to the timeval to + * cause a fault after the select has completed + * successfully. However, because we're not updating the + * timeval, we can't restart the system call. + */ + +sticky: + if (ret == -ERESTARTNOHAND) + ret = -EINTR; + return ret; +} + /* * Ooo, nasty. We need here to frob 32-bit unsigned longs to * 64-bit unsigned longs. @@ -1556,7 +1607,8 @@ int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, ((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1) int compat_core_sys_select(int n, compat_ulong_t __user *inp, - compat_ulong_t __user *outp, compat_ulong_t __user *exp, s64 *timeout) + compat_ulong_t __user *outp, compat_ulong_t __user *exp, + struct timespec *end_time) { fd_set_bits fds; void *bits; @@ -1603,7 +1655,7 @@ int compat_core_sys_select(int n, compat_ulong_t __user *inp, zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); - ret = do_select(n, &fds, timeout); + ret = do_select(n, &fds, end_time); if (ret < 0) goto out; @@ -1629,7 +1681,7 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct compat_timeval __user *tvp) { - s64 timeout = -1; + struct timespec end_time, *to = NULL; struct compat_timeval tv; int ret; @@ -1637,43 +1689,14 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; - if (tv.tv_sec < 0 || tv.tv_usec < 0) + to = &end_time; + if (poll_select_set_timeout(to, tv.tv_sec, + tv.tv_usec * NSEC_PER_USEC)) return -EINVAL; - - /* Cast to u64 to make GCC stop complaining */ - if ((u64)tv.tv_sec >= (u64)MAX_INT64_SECONDS) - timeout = -1; /* infinite */ - else { - timeout = DIV_ROUND_UP(tv.tv_usec, 1000000/HZ); - timeout += tv.tv_sec * HZ; - } } - ret = compat_core_sys_select(n, inp, outp, exp, &timeout); - - if (tvp) { - struct compat_timeval rtv; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - rtv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)); - rtv.tv_sec = timeout; - if (compat_timeval_compare(&rtv, &tv) >= 0) - rtv = tv; - if (copy_to_user(tvp, &rtv, sizeof(rtv))) { -sticky: - /* - * If an application puts its timeval in read-only - * memory, we don't want the Linux-specific update to - * the timeval to cause a fault after the select has - * completed successfully. However, because we're not - * updating the timeval, we can't restart the system - * call. - */ - if (ret == -ERESTARTNOHAND) - ret = -EINTR; - } - } + ret = compat_core_sys_select(n, inp, outp, exp, to); + ret = poll_select_copy_remaining(&end_time, tvp, 1, ret); return ret; } @@ -1686,15 +1709,16 @@ asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp, { compat_sigset_t ss32; sigset_t ksigmask, sigsaved; - s64 timeout = MAX_SCHEDULE_TIMEOUT; struct compat_timespec ts; + struct timespec end_time, *to = NULL; int ret; if (tsp) { if (copy_from_user(&ts, tsp, sizeof(ts))) return -EFAULT; - if (ts.tv_sec < 0 || ts.tv_nsec < 0) + to = &end_time; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } @@ -1709,51 +1733,8 @@ asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp, sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); } - do { - if (tsp) { - if ((unsigned long)ts.tv_sec < MAX_SELECT_SECONDS) { - timeout = DIV_ROUND_UP(ts.tv_nsec, 1000000000/HZ); - timeout += ts.tv_sec * (unsigned long)HZ; - ts.tv_sec = 0; - ts.tv_nsec = 0; - } else { - ts.tv_sec -= MAX_SELECT_SECONDS; - timeout = MAX_SELECT_SECONDS * HZ; - } - } - - ret = compat_core_sys_select(n, inp, outp, exp, &timeout); - - } while (!ret && !timeout && tsp && (ts.tv_sec || ts.tv_nsec)); - - if (tsp) { - struct compat_timespec rts; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - - rts.tv_sec = timeout / HZ; - rts.tv_nsec = (timeout % HZ) * (NSEC_PER_SEC/HZ); - if (rts.tv_nsec >= NSEC_PER_SEC) { - rts.tv_sec++; - rts.tv_nsec -= NSEC_PER_SEC; - } - if (compat_timespec_compare(&rts, &ts) >= 0) - rts = ts; - if (copy_to_user(tsp, &rts, sizeof(rts))) { -sticky: - /* - * If an application puts its timeval in read-only - * memory, we don't want the Linux-specific update to - * the timeval to cause a fault after the select has - * completed successfully. However, because we're not - * updating the timeval, we can't restart the system - * call. - */ - if (ret == -ERESTARTNOHAND) - ret = -EINTR; - } - } + ret = compat_core_sys_select(n, inp, outp, exp, to); + ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); if (ret == -ERESTARTNOHAND) { /* @@ -1798,18 +1779,16 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, compat_sigset_t ss32; sigset_t ksigmask, sigsaved; struct compat_timespec ts; - s64 timeout = -1; + struct timespec end_time, *to = NULL; int ret; if (tsp) { if (copy_from_user(&ts, tsp, sizeof(ts))) return -EFAULT; - /* We assume that ts.tv_sec is always lower than - the number of seconds that can be expressed in - an s64. Otherwise the compiler bitches at us */ - timeout = DIV_ROUND_UP(ts.tv_nsec, 1000000000/HZ); - timeout += ts.tv_sec * HZ; + to = &end_time; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) + return -EINVAL; } if (sigmask) { @@ -1823,7 +1802,7 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); } - ret = do_sys_poll(ufds, nfds, &timeout); + ret = do_sys_poll(ufds, nfds, to); /* We can restart this syscall, usually */ if (ret == -EINTR) { @@ -1841,31 +1820,7 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, } else if (sigmask) sigprocmask(SIG_SETMASK, &sigsaved, NULL); - if (tsp && timeout >= 0) { - struct compat_timespec rts; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - /* Yes, we know it's actually an s64, but it's also positive. */ - rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) * - 1000; - rts.tv_sec = timeout; - if (compat_timespec_compare(&rts, &ts) >= 0) - rts = ts; - if (copy_to_user(tsp, &rts, sizeof(rts))) { -sticky: - /* - * If an application puts its timeval in read-only - * memory, we don't want the Linux-specific update to - * the timeval to cause a fault after the select has - * completed successfully. However, because we're not - * updating the timeval, we can't restart the system - * call. - */ - if (ret == -ERESTARTNOHAND && timeout >= 0) - ret = -EINTR; - } - } + ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); return ret; } diff --git a/fs/proc/array.c b/fs/proc/array.c index f4bc0e789539..bb9f4b05703d 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -388,20 +388,20 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns, /* add up live thread stats at the group level */ if (whole) { + struct task_cputime cputime; struct task_struct *t = task; do { min_flt += t->min_flt; maj_flt += t->maj_flt; - utime = cputime_add(utime, task_utime(t)); - stime = cputime_add(stime, task_stime(t)); gtime = cputime_add(gtime, task_gtime(t)); t = next_thread(t); } while (t != task); min_flt += sig->min_flt; maj_flt += sig->maj_flt; - utime = cputime_add(utime, sig->utime); - stime = cputime_add(stime, sig->stime); + thread_group_cputime(task, &cputime); + utime = cputime.utime; + stime = cputime.stime; gtime = cputime_add(gtime, sig->gtime); } diff --git a/fs/select.c b/fs/select.c index da0e88201c3a..448e44001286 100644 --- a/fs/select.c +++ b/fs/select.c @@ -24,9 +24,64 @@ #include <linux/fdtable.h> #include <linux/fs.h> #include <linux/rcupdate.h> +#include <linux/hrtimer.h> #include <asm/uaccess.h> + +/* + * Estimate expected accuracy in ns from a timeval. + * + * After quite a bit of churning around, we've settled on + * a simple thing of taking 0.1% of the timeout as the + * slack, with a cap of 100 msec. + * "nice" tasks get a 0.5% slack instead. + * + * Consider this comment an open invitation to come up with even + * better solutions.. + */ + +static long __estimate_accuracy(struct timespec *tv) +{ + long slack; + int divfactor = 1000; + + if (task_nice(current) > 0) + divfactor = divfactor / 5; + + slack = tv->tv_nsec / divfactor; + slack += tv->tv_sec * (NSEC_PER_SEC/divfactor); + + if (slack > 100 * NSEC_PER_MSEC) + slack = 100 * NSEC_PER_MSEC; + + if (slack < 0) + slack = 0; + return slack; +} + +static long estimate_accuracy(struct timespec *tv) +{ + unsigned long ret; + struct timespec now; + + /* + * Realtime tasks get a slack of 0 for obvious reasons. + */ + + if (rt_task(current)) + return 0; + + ktime_get_ts(&now); + now = timespec_sub(*tv, now); + ret = __estimate_accuracy(&now); + if (ret < current->timer_slack_ns) + return current->timer_slack_ns; + return ret; +} + + + struct poll_table_page { struct poll_table_page * next; struct poll_table_entry * entry; @@ -130,6 +185,79 @@ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address, add_wait_queue(wait_address, &entry->wait); } +/** + * poll_select_set_timeout - helper function to setup the timeout value + * @to: pointer to timespec variable for the final timeout + * @sec: seconds (from user space) + * @nsec: nanoseconds (from user space) + * + * Note, we do not use a timespec for the user space value here, That + * way we can use the function for timeval and compat interfaces as well. + * + * Returns -EINVAL if sec/nsec are not normalized. Otherwise 0. + */ +int poll_select_set_timeout(struct timespec *to, long sec, long nsec) +{ + struct timespec ts = {.tv_sec = sec, .tv_nsec = nsec}; + + if (!timespec_valid(&ts)) + return -EINVAL; + + /* Optimize for the zero timeout value here */ + if (!sec && !nsec) { + to->tv_sec = to->tv_nsec = 0; + } else { + ktime_get_ts(to); + *to = timespec_add_safe(*to, ts); + } + return 0; +} + +static int poll_select_copy_remaining(struct timespec *end_time, void __user *p, + int timeval, int ret) +{ + struct timespec rts; + struct timeval rtv; + + if (!p) + return ret; + + if (current->personality & STICKY_TIMEOUTS) + goto sticky; + + /* No update for zero timeout */ + if (!end_time->tv_sec && !end_time->tv_nsec) + return ret; + + ktime_get_ts(&rts); + rts = timespec_sub(*end_time, rts); + if (rts.tv_sec < 0) + rts.tv_sec = rts.tv_nsec = 0; + + if (timeval) { + rtv.tv_sec = rts.tv_sec; + rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC; + + if (!copy_to_user(p, &rtv, sizeof(rtv))) + return ret; + + } else if (!copy_to_user(p, &rts, sizeof(rts))) + return ret; + + /* + * If an application puts its timeval in read-only memory, we + * don't want the Linux-specific update to the timeval to + * cause a fault after the select has completed + * successfully. However, because we're not updating the + * timeval, we can't restart the system call. + */ + +sticky: + if (ret == -ERESTARTNOHAND) + ret = -EINTR; + return ret; +} + #define FDS_IN(fds, n) (fds->in + n) #define FDS_OUT(fds, n) (fds->out + n) #define FDS_EX(fds, n) (fds->ex + n) @@ -182,11 +310,13 @@ get_max: #define POLLOUT_SET (POLLWRBAND | POLLWRNORM | POLLOUT | POLLERR) #define POLLEX_SET (POLLPRI) -int do_select(int n, fd_set_bits *fds, s64 *timeout) +int do_select(int n, fd_set_bits *fds, struct timespec *end_time) { + ktime_t expire, *to = NULL; struct poll_wqueues table; poll_table *wait; - int retval, i; + int retval, i, timed_out = 0; + unsigned long slack = 0; rcu_read_lock(); retval = max_select_fd(n, fds); @@ -198,12 +328,17 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout) poll_initwait(&table); wait = &table.pt; - if (!*timeout) + if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { wait = NULL; + timed_out = 1; + } + + if (end_time && !timed_out) + slack = estimate_accuracy(end_time); + retval = 0; for (;;) { unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp; - long __timeout; set_current_state(TASK_INTERRUPTIBLE); @@ -259,27 +394,25 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout) cond_resched(); } wait = NULL; - if (retval || !*timeout || signal_pending(current)) + if (retval || timed_out || signal_pending(current)) break; if (table.error) { retval = table.error; break; } - if (*timeout < 0) { - /* Wait indefinitely */ - __timeout = MAX_SCHEDULE_TIMEOUT; - } else if (unlikely(*timeout >= (s64)MAX_SCHEDULE_TIMEOUT - 1)) { - /* Wait for longer than MAX_SCHEDULE_TIMEOUT. Do it in a loop */ - __timeout = MAX_SCHEDULE_TIMEOUT - 1; - *timeout -= __timeout; - } else { - __timeout = *timeout; - *timeout = 0; + /* + * If this is the first loop and we have a timeout + * given, then we convert to ktime_t and set the to + * pointer to the expiry value. + */ + if (end_time && !to) { + expire = timespec_to_ktime(*end_time); + to = &expire; } - __timeout = schedule_timeout(__timeout); - if (*timeout >= 0) - *timeout += __timeout; + + if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) + timed_out = 1; } __set_current_state(TASK_RUNNING); @@ -300,7 +433,7 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout) ((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1) int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, - fd_set __user *exp, s64 *timeout) + fd_set __user *exp, struct timespec *end_time) { fd_set_bits fds; void *bits; @@ -351,7 +484,7 @@ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); - ret = do_select(n, &fds, timeout); + ret = do_select(n, &fds, end_time); if (ret < 0) goto out; @@ -377,7 +510,7 @@ out_nofds: asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp) { - s64 timeout = -1; + struct timespec end_time, *to = NULL; struct timeval tv; int ret; @@ -385,43 +518,14 @@ asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp, if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; - if (tv.tv_sec < 0 || tv.tv_usec < 0) + to = &end_time; + if (poll_select_set_timeout(to, tv.tv_sec, + tv.tv_usec * NSEC_PER_USEC)) return -EINVAL; - - /* Cast to u64 to make GCC stop complaining */ - if ((u64)tv.tv_sec >= (u64)MAX_INT64_SECONDS) - timeout = -1; /* infinite */ - else { - timeout = DIV_ROUND_UP(tv.tv_usec, USEC_PER_SEC/HZ); - timeout += tv.tv_sec * HZ; - } } - ret = core_sys_select(n, inp, outp, exp, &timeout); - - if (tvp) { - struct timeval rtv; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - rtv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)); - rtv.tv_sec = timeout; - if (timeval_compare(&rtv, &tv) >= 0) - rtv = tv; - if (copy_to_user(tvp, &rtv, sizeof(rtv))) { -sticky: - /* - * If an application puts its timeval in read-only - * memory, we don't want the Linux-specific update to - * the timeval to cause a fault after the select has - * completed successfully. However, because we're not - * updating the timeval, we can't restart the system - * call. - */ - if (ret == -ERESTARTNOHAND) - ret = -EINTR; - } - } + ret = core_sys_select(n, inp, outp, exp, to); + ret = poll_select_copy_remaining(&end_time, tvp, 1, ret); return ret; } @@ -431,25 +535,17 @@ asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timespec __user *tsp, const sigset_t __user *sigmask, size_t sigsetsize) { - s64 timeout = MAX_SCHEDULE_TIMEOUT; sigset_t ksigmask, sigsaved; - struct timespec ts; + struct timespec ts, end_time, *to = NULL; int ret; if (tsp) { if (copy_from_user(&ts, tsp, sizeof(ts))) return -EFAULT; - if (ts.tv_sec < 0 || ts.tv_nsec < 0) + to = &end_time; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; - - /* Cast to u64 to make GCC stop complaining */ - if ((u64)ts.tv_sec >= (u64)MAX_INT64_SECONDS) - timeout = -1; /* infinite */ - else { - timeout = DIV_ROUND_UP(ts.tv_nsec, NSEC_PER_SEC/HZ); - timeout += ts.tv_sec * HZ; - } } if (sigmask) { @@ -463,32 +559,8 @@ asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp, sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); } - ret = core_sys_select(n, inp, outp, exp, &timeout); - - if (tsp) { - struct timespec rts; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) * - 1000; - rts.tv_sec = timeout; - if (timespec_compare(&rts, &ts) >= 0) - rts = ts; - if (copy_to_user(tsp, &rts, sizeof(rts))) { -sticky: - /* - * If an application puts its timeval in read-only - * memory, we don't want the Linux-specific update to - * the timeval to cause a fault after the select has - * completed successfully. However, because we're not - * updating the timeval, we can't restart the system - * call. - */ - if (ret == -ERESTARTNOHAND) - ret = -EINTR; - } - } + ret = core_sys_select(n, inp, outp, exp, &end_time); + ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); if (ret == -ERESTARTNOHAND) { /* @@ -574,18 +646,24 @@ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait) } static int do_poll(unsigned int nfds, struct poll_list *list, - struct poll_wqueues *wait, s64 *timeout) + struct poll_wqueues *wait, struct timespec *end_time) { - int count = 0; poll_table* pt = &wait->pt; + ktime_t expire, *to = NULL; + int timed_out = 0, count = 0; + unsigned long slack = 0; /* Optimise the no-wait case */ - if (!(*timeout)) + if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { pt = NULL; + timed_out = 1; + } + + if (end_time && !timed_out) + slack = estimate_accuracy(end_time); for (;;) { struct poll_list *walk; - long __timeout; set_current_state(TASK_INTERRUPTIBLE); for (walk = list; walk != NULL; walk = walk->next) { @@ -617,27 +695,21 @@ static int do_poll(unsigned int nfds, struct poll_list *list, if (signal_pending(current)) count = -EINTR; } - if (count || !*timeout) + if (count || timed_out) break; - if (*timeout < 0) { - /* Wait indefinitely */ - __timeout = MAX_SCHEDULE_TIMEOUT; - } else if (unlikely(*timeout >= (s64)MAX_SCHEDULE_TIMEOUT-1)) { - /* - * Wait for longer than MAX_SCHEDULE_TIMEOUT. Do it in - * a loop - */ - __timeout = MAX_SCHEDULE_TIMEOUT - 1; - *timeout -= __timeout; - } else { - __timeout = *timeout; - *timeout = 0; + /* + * If this is the first loop and we have a timeout + * given, then we convert to ktime_t and set the to + * pointer to the expiry value. + */ + if (end_time && !to) { + expire = timespec_to_ktime(*end_time); + to = &expire; } - __timeout = schedule_timeout(__timeout); - if (*timeout >= 0) - *timeout += __timeout; + if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) + timed_out = 1; } __set_current_state(TASK_RUNNING); return count; @@ -646,7 +718,8 @@ static int do_poll(unsigned int nfds, struct poll_list *list, #define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list)) / \ sizeof(struct pollfd)) -int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, s64 *timeout) +int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, + struct timespec *end_time) { struct poll_wqueues table; int err = -EFAULT, fdcount, len, size; @@ -686,7 +759,7 @@ int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, s64 *timeout) } poll_initwait(&table); - fdcount = do_poll(nfds, head, &table, timeout); + fdcount = do_poll(nfds, head, &table, end_time); poll_freewait(&table); for (walk = head; walk; walk = walk->next) { @@ -712,16 +785,21 @@ out_fds: static long do_restart_poll(struct restart_block *restart_block) { - struct pollfd __user *ufds = (struct pollfd __user*)restart_block->arg0; - int nfds = restart_block->arg1; - s64 timeout = ((s64)restart_block->arg3<<32) | (s64)restart_block->arg2; + struct pollfd __user *ufds = restart_block->poll.ufds; + int nfds = restart_block->poll.nfds; + struct timespec *to = NULL, end_time; int ret; - ret = do_sys_poll(ufds, nfds, &timeout); + if (restart_block->poll.has_timeout) { + end_time.tv_sec = restart_block->poll.tv_sec; + end_time.tv_nsec = restart_block->poll.tv_nsec; + to = &end_time; + } + + ret = do_sys_poll(ufds, nfds, to); + if (ret == -EINTR) { restart_block->fn = do_restart_poll; - restart_block->arg2 = timeout & 0xFFFFFFFF; - restart_block->arg3 = (u64)timeout >> 32; ret = -ERESTART_RESTARTBLOCK; } return ret; @@ -730,31 +808,32 @@ static long do_restart_poll(struct restart_block *restart_block) asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds, long timeout_msecs) { - s64 timeout_jiffies; + struct timespec end_time, *to = NULL; int ret; - if (timeout_msecs > 0) { -#if HZ > 1000 - /* We can only overflow if HZ > 1000 */ - if (timeout_msecs / 1000 > (s64)0x7fffffffffffffffULL / (s64)HZ) - timeout_jiffies = -1; - else -#endif - timeout_jiffies = msecs_to_jiffies(timeout_msecs) + 1; - } else { - /* Infinite (< 0) or no (0) timeout */ - timeout_jiffies = timeout_msecs; + if (timeout_msecs >= 0) { + to = &end_time; + poll_select_set_timeout(to, timeout_msecs / MSEC_PER_SEC, + NSEC_PER_MSEC * (timeout_msecs % MSEC_PER_SEC)); } - ret = do_sys_poll(ufds, nfds, &timeout_jiffies); + ret = do_sys_poll(ufds, nfds, to); + if (ret == -EINTR) { struct restart_block *restart_block; + restart_block = ¤t_thread_info()->restart_block; restart_block->fn = do_restart_poll; - restart_block->arg0 = (unsigned long)ufds; - restart_block->arg1 = nfds; - restart_block->arg2 = timeout_jiffies & 0xFFFFFFFF; - restart_block->arg3 = (u64)timeout_jiffies >> 32; + restart_block->poll.ufds = ufds; + restart_block->poll.nfds = nfds; + + if (timeout_msecs >= 0) { + restart_block->poll.tv_sec = end_time.tv_sec; + restart_block->poll.tv_nsec = end_time.tv_nsec; + restart_block->poll.has_timeout = 1; + } else + restart_block->poll.has_timeout = 0; + ret = -ERESTART_RESTARTBLOCK; } return ret; @@ -766,21 +845,16 @@ asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds, size_t sigsetsize) { sigset_t ksigmask, sigsaved; - struct timespec ts; - s64 timeout = -1; + struct timespec ts, end_time, *to = NULL; int ret; if (tsp) { if (copy_from_user(&ts, tsp, sizeof(ts))) return -EFAULT; - /* Cast to u64 to make GCC stop complaining */ - if ((u64)ts.tv_sec >= (u64)MAX_INT64_SECONDS) - timeout = -1; /* infinite */ - else { - timeout = DIV_ROUND_UP(ts.tv_nsec, NSEC_PER_SEC/HZ); - timeout += ts.tv_sec * HZ; - } + to = &end_time; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) + return -EINVAL; } if (sigmask) { @@ -794,7 +868,7 @@ asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds, sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); } - ret = do_sys_poll(ufds, nfds, &timeout); + ret = do_sys_poll(ufds, nfds, to); /* We can restart this syscall, usually */ if (ret == -EINTR) { @@ -812,31 +886,7 @@ asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds, } else if (sigmask) sigprocmask(SIG_SETMASK, &sigsaved, NULL); - if (tsp && timeout >= 0) { - struct timespec rts; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - /* Yes, we know it's actually an s64, but it's also positive. */ - rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) * - 1000; - rts.tv_sec = timeout; - if (timespec_compare(&rts, &ts) >= 0) - rts = ts; - if (copy_to_user(tsp, &rts, sizeof(rts))) { - sticky: - /* - * If an application puts its timeval in read-only - * memory, we don't want the Linux-specific update to - * the timeval to cause a fault after the select has - * completed successfully. However, because we're not - * updating the timeval, we can't restart the system - * call. - */ - if (ret == -ERESTARTNOHAND && timeout >= 0) - ret = -EINTR; - } - } + ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); return ret; } diff --git a/fs/timerfd.c b/fs/timerfd.c index c502c60e4f54..0862f0e49d0c 100644 --- a/fs/timerfd.c +++ b/fs/timerfd.c @@ -52,11 +52,9 @@ static enum hrtimer_restart timerfd_tmrproc(struct hrtimer *htmr) static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx) { - ktime_t now, remaining; - - now = ctx->tmr.base->get_time(); - remaining = ktime_sub(ctx->tmr.expires, now); + ktime_t remaining; + remaining = hrtimer_expires_remaining(&ctx->tmr); return remaining.tv64 < 0 ? ktime_set(0, 0): remaining; } @@ -74,7 +72,7 @@ static void timerfd_setup(struct timerfd_ctx *ctx, int flags, ctx->ticks = 0; ctx->tintv = timespec_to_ktime(ktmr->it_interval); hrtimer_init(&ctx->tmr, ctx->clockid, htmode); - ctx->tmr.expires = texp; + hrtimer_set_expires(&ctx->tmr, texp); ctx->tmr.function = timerfd_tmrproc; if (texp.tv64 != 0) hrtimer_start(&ctx->tmr, texp, htmode); diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h index 55e434feec99..f88d32f8ff7c 100644 --- a/include/linux/clocksource.h +++ b/include/linux/clocksource.h @@ -45,7 +45,8 @@ struct clocksource; * @read: returns a cycle value * @mask: bitmask for two's complement * subtraction of non 64 bit counters - * @mult: cycle to nanosecond multiplier + * @mult: cycle to nanosecond multiplier (adjusted by NTP) + * @mult_orig: cycle to nanosecond multiplier (unadjusted by NTP) * @shift: cycle to nanosecond divisor (power of two) * @flags: flags describing special properties * @vread: vsyscall based read @@ -63,6 +64,7 @@ struct clocksource { cycle_t (*read)(void); cycle_t mask; u32 mult; + u32 mult_orig; u32 shift; unsigned long flags; cycle_t (*vread)(void); @@ -77,6 +79,7 @@ struct clocksource { /* timekeeping specific data, ignore */ cycle_t cycle_interval; u64 xtime_interval; + u32 raw_interval; /* * Second part is written at each timer interrupt * Keep it in a different cache line to dirty no @@ -85,6 +88,7 @@ struct clocksource { cycle_t cycle_last ____cacheline_aligned_in_smp; u64 xtime_nsec; s64 error; + struct timespec raw_time; #ifdef CONFIG_CLOCKSOURCE_WATCHDOG /* Watchdog related data, used by the framework */ @@ -201,17 +205,19 @@ static inline void clocksource_calculate_interval(struct clocksource *c, { u64 tmp; - /* XXX - All of this could use a whole lot of optimization */ + /* Do the ns -> cycle conversion first, using original mult */ tmp = length_nsec; tmp <<= c->shift; - tmp += c->mult/2; - do_div(tmp, c->mult); + tmp += c->mult_orig/2; + do_div(tmp, c->mult_orig); c->cycle_interval = (cycle_t)tmp; if (c->cycle_interval == 0) c->cycle_interval = 1; + /* Go back from cycles -> shifted ns, this time use ntp adjused mult */ c->xtime_interval = (u64)c->cycle_interval * c->mult; + c->raw_interval = ((u64)c->cycle_interval * c->mult_orig) >> c->shift; } diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 2f245fe63bda..179e3ea5e7ec 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -121,16 +121,17 @@ enum hrtimer_cb_mode { */ struct hrtimer { struct rb_node node; - ktime_t expires; + ktime_t _expires; + ktime_t _softexpires; enum hrtimer_restart (*function)(struct hrtimer *); struct hrtimer_clock_base *base; unsigned long state; - enum hrtimer_cb_mode cb_mode; struct list_head cb_entry; + enum hrtimer_cb_mode cb_mode; #ifdef CONFIG_TIMER_STATS + int start_pid; void *start_site; char start_comm[16]; - int start_pid; #endif }; @@ -155,10 +156,8 @@ struct hrtimer_sleeper { * @first: pointer to the timer node which expires first * @resolution: the resolution of the clock, in nanoseconds * @get_time: function to retrieve the current time of the clock - * @get_softirq_time: function to retrieve the current time from the softirq * @softirq_time: the time when running the hrtimer queue in the softirq * @offset: offset of this clock to the monotonic base - * @reprogram: function to reprogram the timer event */ struct hrtimer_clock_base { struct hrtimer_cpu_base *cpu_base; @@ -167,13 +166,9 @@ struct hrtimer_clock_base { struct rb_node *first; ktime_t resolution; ktime_t (*get_time)(void); - ktime_t (*get_softirq_time)(void); ktime_t softirq_time; #ifdef CONFIG_HIGH_RES_TIMERS ktime_t offset; - int (*reprogram)(struct hrtimer *t, - struct hrtimer_clock_base *b, - ktime_t n); #endif }; @@ -207,6 +202,71 @@ struct hrtimer_cpu_base { #endif }; +static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time) +{ + timer->_expires = time; + timer->_softexpires = time; +} + +static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time, ktime_t delta) +{ + timer->_softexpires = time; + timer->_expires = ktime_add_safe(time, delta); +} + +static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, unsigned long delta) +{ + timer->_softexpires = time; + timer->_expires = ktime_add_safe(time, ns_to_ktime(delta)); +} + +static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64) +{ + timer->_expires.tv64 = tv64; + timer->_softexpires.tv64 = tv64; +} + +static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time) +{ + timer->_expires = ktime_add_safe(timer->_expires, time); + timer->_softexpires = ktime_add_safe(timer->_softexpires, time); +} + +static inline void hrtimer_add_expires_ns(struct hrtimer *timer, unsigned long ns) +{ + timer->_expires = ktime_add_ns(timer->_expires, ns); + timer->_softexpires = ktime_add_ns(timer->_softexpires, ns); +} + +static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer) +{ + return timer->_expires; +} + +static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer) +{ + return timer->_softexpires; +} + +static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer) +{ + return timer->_expires.tv64; +} +static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer) +{ + return timer->_softexpires.tv64; +} + +static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer) +{ + return ktime_to_ns(timer->_expires); +} + +static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer) +{ + return ktime_sub(timer->_expires, timer->base->get_time()); +} + #ifdef CONFIG_HIGH_RES_TIMERS struct clock_event_device; @@ -227,6 +287,8 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer) return timer->base->cpu_base->hres_active; } +extern void hrtimer_peek_ahead_timers(void); + /* * The resolution of the clocks. The resolution value is returned in * the clock_getres() system call to give application programmers an @@ -249,6 +311,7 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer) * is expired in the next softirq when the clock was advanced. */ static inline void clock_was_set(void) { } +static inline void hrtimer_peek_ahead_timers(void) { } static inline void hres_timers_resume(void) { } @@ -270,6 +333,10 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer) extern ktime_t ktime_get(void); extern ktime_t ktime_get_real(void); + +DECLARE_PER_CPU(struct tick_device, tick_cpu_device); + + /* Exported timer functions: */ /* Initialize timers: */ @@ -294,12 +361,25 @@ static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } /* Basic timer operations: */ extern int hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode); +extern int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, + unsigned long range_ns, const enum hrtimer_mode mode); extern int hrtimer_cancel(struct hrtimer *timer); extern int hrtimer_try_to_cancel(struct hrtimer *timer); +static inline int hrtimer_start_expires(struct hrtimer *timer, + enum hrtimer_mode mode) +{ + unsigned long delta; + ktime_t soft, hard; + soft = hrtimer_get_softexpires(timer); + hard = hrtimer_get_expires(timer); + delta = ktime_to_ns(ktime_sub(hard, soft)); + return hrtimer_start_range_ns(timer, soft, delta, mode); +} + static inline int hrtimer_restart(struct hrtimer *timer) { - return hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS); + return hrtimer_start_expires(timer, HRTIMER_MODE_ABS); } /* Query timers: */ @@ -356,6 +436,10 @@ extern long hrtimer_nanosleep_restart(struct restart_block *restart_block); extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *tsk); +extern int schedule_hrtimeout_range(ktime_t *expires, unsigned long delta, + const enum hrtimer_mode mode); +extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode); + /* Soft interrupt function to run the hrtimer queues: */ extern void hrtimer_run_queues(void); extern void hrtimer_run_pending(void); diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 021d8e720c79..23fd8909b9e5 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -170,6 +170,7 @@ extern struct group_info init_groups; .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \ .fs_excl = ATOMIC_INIT(0), \ .pi_lock = __SPIN_LOCK_UNLOCKED(tsk.pi_lock), \ + .timer_slack_ns = 50000, /* 50 usec default slack */ \ .pids = { \ [PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \ [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \ diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index cf9f40a91c9c..cac3750cd65e 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -52,6 +52,7 @@ static inline int kstat_irqs(int irq) return sum; } +extern unsigned long long task_delta_exec(struct task_struct *); extern void account_user_time(struct task_struct *, cputime_t); extern void account_user_time_scaled(struct task_struct *, cputime_t); extern void account_system_time(struct task_struct *, int, cputime_t); diff --git a/include/linux/poll.h b/include/linux/poll.h index ef453828877a..badd98ab06f6 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -114,11 +114,13 @@ void zero_fd_set(unsigned long nr, unsigned long *fdset) #define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1) -extern int do_select(int n, fd_set_bits *fds, s64 *timeout); +extern int do_select(int n, fd_set_bits *fds, struct timespec *end_time); extern int do_sys_poll(struct pollfd __user * ufds, unsigned int nfds, - s64 *timeout); + struct timespec *end_time); extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp, - fd_set __user *exp, s64 *timeout); + fd_set __user *exp, struct timespec *end_time); + +extern int poll_select_set_timeout(struct timespec *to, long sec, long nsec); #endif /* KERNEL */ diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h index a7dd38f30ade..a7c721355549 100644 --- a/include/linux/posix-timers.h +++ b/include/linux/posix-timers.h @@ -45,8 +45,6 @@ struct k_itimer { int it_requeue_pending; /* waiting to requeue this timer */ #define REQUEUE_PENDING 1 int it_sigev_notify; /* notify word of sigevent struct */ - int it_sigev_signo; /* signo word of sigevent struct */ - sigval_t it_sigev_value; /* value word of sigevent struct */ struct task_struct *it_process; /* process to send signal to */ struct sigqueue *sigq; /* signal queue entry. */ union { @@ -115,4 +113,6 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx, long clock_nanosleep_restart(struct restart_block *restart_block); +void update_rlimit_cpu(unsigned long rlim_new); + #endif diff --git a/include/linux/prctl.h b/include/linux/prctl.h index 5ad79198d6f9..48d887e3c6e7 100644 --- a/include/linux/prctl.h +++ b/include/linux/prctl.h @@ -78,4 +78,11 @@ #define PR_GET_SECUREBITS 27 #define PR_SET_SECUREBITS 28 +/* + * Get/set the timerslack as used by poll/select/nanosleep + * A value of 0 means "use default" + */ +#define PR_SET_TIMERSLACK 29 +#define PR_GET_TIMERSLACK 30 + #endif /* _LINUX_PRCTL_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 1a7e8461db5a..b7b4dccd3d0a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -425,6 +425,39 @@ struct pacct_struct { unsigned long ac_minflt, ac_majflt; }; +/** + * struct task_cputime - collected CPU time counts + * @utime: time spent in user mode, in &cputime_t units + * @stime: time spent in kernel mode, in &cputime_t units + * @sum_exec_runtime: total time spent on the CPU, in nanoseconds + * + * This structure groups together three kinds of CPU time that are + * tracked for threads and thread groups. Most things considering + * CPU time want to group these counts together and treat all three + * of them in parallel. + */ +struct task_cputime { + cputime_t utime; + cputime_t stime; + unsigned long long sum_exec_runtime; +}; +/* Alternate field names when used to cache expirations. */ +#define prof_exp stime +#define virt_exp utime +#define sched_exp sum_exec_runtime + +/** + * struct thread_group_cputime - thread group interval timer counts + * @totals: thread group interval timers; substructure for + * uniprocessor kernel, per-cpu for SMP kernel. + * + * This structure contains the version of task_cputime, above, that is + * used for thread group CPU clock calculations. + */ +struct thread_group_cputime { + struct task_cputime *totals; +}; + /* * NOTE! "signal_struct" does not have it's own * locking, because a shared signal_struct always @@ -470,6 +503,17 @@ struct signal_struct { cputime_t it_prof_expires, it_virt_expires; cputime_t it_prof_incr, it_virt_incr; + /* + * Thread group totals for process CPU clocks. + * See thread_group_cputime(), et al, for details. + */ + struct thread_group_cputime cputime; + + /* Earliest-expiration cache. */ + struct task_cputime cputime_expires; + + struct list_head cpu_timers[3]; + /* job control IDs */ /* @@ -500,7 +544,7 @@ struct signal_struct { * Live threads maintain their own counters and add to these * in __exit_signal, except for the group leader. */ - cputime_t utime, stime, cutime, cstime; + cputime_t cutime, cstime; cputime_t gtime; cputime_t cgtime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; @@ -509,14 +553,6 @@ struct signal_struct { struct task_io_accounting ioac; /* - * Cumulative ns of scheduled CPU time for dead threads in the - * group, not including a zombie group leader. (This only differs - * from jiffies_to_ns(utime + stime) if sched_clock uses something - * other than jiffies.) - */ - unsigned long long sum_sched_runtime; - - /* * We don't bother to synchronize most readers of this at all, * because there is no reader checking a limit that actually needs * to get both rlim_cur and rlim_max atomically, and either one @@ -527,8 +563,6 @@ struct signal_struct { */ struct rlimit rlim[RLIM_NLIMITS]; - struct list_head cpu_timers[3]; - /* keep the process-shared keyrings here so that they do the right * thing in threads created with CLONE_THREAD */ #ifdef CONFIG_KEYS @@ -1136,8 +1170,7 @@ struct task_struct { /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */ unsigned long min_flt, maj_flt; - cputime_t it_prof_expires, it_virt_expires; - unsigned long long it_sched_expires; + struct task_cputime cputime_expires; struct list_head cpu_timers[3]; /* process credentials */ @@ -1303,6 +1336,12 @@ struct task_struct { int latency_record_count; struct latency_record latency_record[LT_SAVECOUNT]; #endif + /* + * time slack values; these are used to round up poll() and + * select() etc timeout values. These are in nanoseconds. + */ + unsigned long timer_slack_ns; + unsigned long default_timer_slack_ns; }; /* @@ -1587,6 +1626,7 @@ extern unsigned long long cpu_clock(int cpu); extern unsigned long long task_sched_runtime(struct task_struct *task); +extern unsigned long long thread_group_sched_runtime(struct task_struct *task); /* sched_exec is called by processes performing an exec */ #ifdef CONFIG_SMP @@ -2097,6 +2137,30 @@ static inline int spin_needbreak(spinlock_t *lock) } /* + * Thread group CPU time accounting. + */ + +extern int thread_group_cputime_alloc(struct task_struct *); +extern void thread_group_cputime(struct task_struct *, struct task_cputime *); + +static inline void thread_group_cputime_init(struct signal_struct *sig) +{ + sig->cputime.totals = NULL; +} + +static inline int thread_group_cputime_clone_thread(struct task_struct *curr) +{ + if (curr->signal->cputime.totals) + return 0; + return thread_group_cputime_alloc(curr); +} + +static inline void thread_group_cputime_free(struct signal_struct *sig) +{ + free_percpu(sig->cputime.totals); +} + +/* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. * This is required every time the blocked sigset_t changes. diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index 38a56477f27a..e6b820f8b56b 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -38,6 +38,14 @@ struct restart_block { #endif u64 expires; } nanosleep; + /* For poll */ + struct { + struct pollfd __user *ufds; + int nfds; + int has_timeout; + unsigned long tv_sec; + unsigned long tv_nsec; + } poll; }; }; diff --git a/include/linux/time.h b/include/linux/time.h index 51e883df0fa5..ce321ac5c8f8 100644 --- a/include/linux/time.h +++ b/include/linux/time.h @@ -40,6 +40,8 @@ extern struct timezone sys_tz; #define NSEC_PER_SEC 1000000000L #define FSEC_PER_SEC 1000000000000000L +#define TIME_T_MAX (time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1) + static inline int timespec_equal(const struct timespec *a, const struct timespec *b) { @@ -74,6 +76,8 @@ extern unsigned long mktime(const unsigned int year, const unsigned int mon, const unsigned int min, const unsigned int sec); extern void set_normalized_timespec(struct timespec *ts, time_t sec, long nsec); +extern struct timespec timespec_add_safe(const struct timespec lhs, + const struct timespec rhs); /* * sub = lhs - rhs, in normalized form @@ -119,6 +123,7 @@ extern int do_setitimer(int which, struct itimerval *value, extern unsigned int alarm_setitimer(unsigned int seconds); extern int do_getitimer(int which, struct itimerval *value); extern void getnstimeofday(struct timespec *tv); +extern void getrawmonotonic(struct timespec *ts); extern void getboottime(struct timespec *ts); extern void monotonic_to_bootbased(struct timespec *ts); @@ -127,6 +132,9 @@ extern int timekeeping_valid_for_hres(void); extern void update_wall_time(void); extern void update_xtime_cache(u64 nsec); +struct tms; +extern void do_sys_times(struct tms *); + /** * timespec_to_ns - Convert timespec to nanoseconds * @ts: pointer to the timespec variable to be converted @@ -216,6 +224,7 @@ struct itimerval { #define CLOCK_MONOTONIC 1 #define CLOCK_PROCESS_CPUTIME_ID 2 #define CLOCK_THREAD_CPUTIME_ID 3 +#define CLOCK_MONOTONIC_RAW 4 /* * The IDs of various hardware clocks: diff --git a/include/linux/timex.h b/include/linux/timex.h index fc6035d29d56..9007313b5b71 100644 --- a/include/linux/timex.h +++ b/include/linux/timex.h @@ -82,7 +82,7 @@ */ #define SHIFT_USEC 16 /* frequency offset scale (shift) */ #define PPM_SCALE (NSEC_PER_USEC << (NTP_SCALE_SHIFT - SHIFT_USEC)) -#define PPM_SCALE_INV_SHIFT 20 +#define PPM_SCALE_INV_SHIFT 19 #define PPM_SCALE_INV ((1ll << (PPM_SCALE_INV_SHIFT + NTP_SCALE_SHIFT)) / \ PPM_SCALE + 1) @@ -141,8 +141,15 @@ struct timex { #define ADJ_MICRO 0x1000 /* select microsecond resolution */ #define ADJ_NANO 0x2000 /* select nanosecond resolution */ #define ADJ_TICK 0x4000 /* tick value */ + +#ifdef __KERNEL__ +#define ADJ_ADJTIME 0x8000 /* switch between adjtime/adjtimex modes */ +#define ADJ_OFFSET_SINGLESHOT 0x0001 /* old-fashioned adjtime */ +#define ADJ_OFFSET_READONLY 0x2000 /* read-only adjtime */ +#else #define ADJ_OFFSET_SINGLESHOT 0x8001 /* old-fashioned adjtime */ -#define ADJ_OFFSET_SS_READ 0xa001 /* read-only adjtime */ +#define ADJ_OFFSET_SS_READ 0xa001 /* read-only adjtime */ +#endif /* xntp 3.4 compatibility names */ #define MOD_OFFSET ADJ_OFFSET diff --git a/kernel/compat.c b/kernel/compat.c index 143990e48cb9..8eafe3eb50d9 100644 --- a/kernel/compat.c +++ b/kernel/compat.c @@ -23,6 +23,7 @@ #include <linux/timex.h> #include <linux/migrate.h> #include <linux/posix-timers.h> +#include <linux/times.h> #include <asm/uaccess.h> @@ -208,49 +209,23 @@ asmlinkage long compat_sys_setitimer(int which, return 0; } +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) { - /* - * In the SMP world we might just be unlucky and have one of - * the times increment as we use it. Since the value is an - * atomically safe type this is just fine. Conceptually its - * as if the syscall took an instant longer to occur. - */ if (tbuf) { + struct tms tms; struct compat_tms tmp; - struct task_struct *tsk = current; - struct task_struct *t; - cputime_t utime, stime, cutime, cstime; - - read_lock(&tasklist_lock); - utime = tsk->signal->utime; - stime = tsk->signal->stime; - t = tsk; - do { - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); - t = next_thread(t); - } while (t != tsk); - - /* - * While we have tasklist_lock read-locked, no dying thread - * can be updating current->signal->[us]time. Instead, - * we got their counts included in the live thread loop. - * However, another thread can come in right now and - * do a wait call that updates current->signal->c[us]time. - * To make sure we always see that pair updated atomically, - * we take the siglock around fetching them. - */ - spin_lock_irq(&tsk->sighand->siglock); - cutime = tsk->signal->cutime; - cstime = tsk->signal->cstime; - spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); - - tmp.tms_utime = compat_jiffies_to_clock_t(cputime_to_jiffies(utime)); - tmp.tms_stime = compat_jiffies_to_clock_t(cputime_to_jiffies(stime)); - tmp.tms_cutime = compat_jiffies_to_clock_t(cputime_to_jiffies(cutime)); - tmp.tms_cstime = compat_jiffies_to_clock_t(cputime_to_jiffies(cstime)); + + do_sys_times(&tms); + /* Convert our struct tms to the compat version. */ + tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime); + tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime); + tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime); + tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime); if (copy_to_user(tbuf, &tmp, sizeof(tmp))) return -EFAULT; } diff --git a/kernel/exit.c b/kernel/exit.c index 9d2f87b7055d..b361006e1244 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -113,8 +113,6 @@ static void __exit_signal(struct task_struct *tsk) * We won't ever get here for the group leader, since it * will have been the last reference on the signal_struct. */ - sig->utime = cputime_add(sig->utime, task_utime(tsk)); - sig->stime = cputime_add(sig->stime, task_stime(tsk)); sig->gtime = cputime_add(sig->gtime, task_gtime(tsk)); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; @@ -123,7 +121,6 @@ static void __exit_signal(struct task_struct *tsk) sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); - sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig = NULL; /* Marker for below. */ } @@ -1304,6 +1301,7 @@ static int wait_task_zombie(struct task_struct *p, int options, if (likely(!traced)) { struct signal_struct *psig; struct signal_struct *sig; + struct task_cputime cputime; /* * The resource counters for the group leader are in its @@ -1319,20 +1317,23 @@ static int wait_task_zombie(struct task_struct *p, int options, * need to protect the access to p->parent->signal fields, * as other threads in the parent group can be right * here reaping other children at the same time. + * + * We use thread_group_cputime() to get times for the thread + * group, which consolidates times for all threads in the + * group including the group leader. */ spin_lock_irq(&p->parent->sighand->siglock); psig = p->parent->signal; sig = p->signal; + thread_group_cputime(p, &cputime); psig->cutime = cputime_add(psig->cutime, - cputime_add(p->utime, - cputime_add(sig->utime, - sig->cutime))); + cputime_add(cputime.utime, + sig->cutime)); psig->cstime = cputime_add(psig->cstime, - cputime_add(p->stime, - cputime_add(sig->stime, - sig->cstime))); + cputime_add(cputime.stime, + sig->cstime)); psig->cgtime = cputime_add(psig->cgtime, cputime_add(p->gtime, diff --git a/kernel/fork.c b/kernel/fork.c index 33afd46a67cb..cb0f48180279 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -765,15 +765,44 @@ void __cleanup_sighand(struct sighand_struct *sighand) kmem_cache_free(sighand_cachep, sighand); } + +/* + * Initialize POSIX timer handling for a thread group. + */ +static void posix_cpu_timers_init_group(struct signal_struct *sig) +{ + /* Thread group counters. */ + thread_group_cputime_init(sig); + + /* Expiration times and increments. */ + sig->it_virt_expires = cputime_zero; + sig->it_virt_incr = cputime_zero; + sig->it_prof_expires = cputime_zero; + sig->it_prof_incr = cputime_zero; + + /* Cached expiration times. */ + sig->cputime_expires.prof_exp = cputime_zero; + sig->cputime_expires.virt_exp = cputime_zero; + sig->cputime_expires.sched_exp = 0; + + /* The timer lists. */ + INIT_LIST_HEAD(&sig->cpu_timers[0]); + INIT_LIST_HEAD(&sig->cpu_timers[1]); + INIT_LIST_HEAD(&sig->cpu_timers[2]); +} + static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; int ret; if (clone_flags & CLONE_THREAD) { - atomic_inc(¤t->signal->count); - atomic_inc(¤t->signal->live); - return 0; + ret = thread_group_cputime_clone_thread(current); + if (likely(!ret)) { + atomic_inc(¤t->signal->count); + atomic_inc(¤t->signal->live); + } + return ret; } sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; @@ -801,40 +830,25 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) sig->it_real_incr.tv64 = 0; sig->real_timer.function = it_real_fn; - sig->it_virt_expires = cputime_zero; - sig->it_virt_incr = cputime_zero; - sig->it_prof_expires = cputime_zero; - sig->it_prof_incr = cputime_zero; - sig->leader = 0; /* session leadership doesn't inherit */ sig->tty_old_pgrp = NULL; sig->tty = NULL; - sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero; + sig->cutime = sig->cstime = cputime_zero; sig->gtime = cputime_zero; sig->cgtime = cputime_zero; sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0; sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0; sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0; task_io_accounting_init(&sig->ioac); - sig->sum_sched_runtime = 0; - INIT_LIST_HEAD(&sig->cpu_timers[0]); - INIT_LIST_HEAD(&sig->cpu_timers[1]); - INIT_LIST_HEAD(&sig->cpu_timers[2]); taskstats_tgid_init(sig); task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); - if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) { - /* - * New sole thread in the process gets an expiry time - * of the whole CPU time limit. - */ - tsk->it_prof_expires = - secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur); - } + posix_cpu_timers_init_group(sig); + acct_init_pacct(&sig->pacct); tty_audit_fork(sig); @@ -844,6 +858,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) void __cleanup_signal(struct signal_struct *sig) { + thread_group_cputime_free(sig); exit_thread_group_keys(sig); tty_kref_put(sig->tty); kmem_cache_free(signal_cachep, sig); @@ -894,6 +909,19 @@ void mm_init_owner(struct mm_struct *mm, struct task_struct *p) #endif /* CONFIG_MM_OWNER */ /* + * Initialize POSIX timer handling for a single task. + */ +static void posix_cpu_timers_init(struct task_struct *tsk) +{ + tsk->cputime_expires.prof_exp = cputime_zero; + tsk->cputime_expires.virt_exp = cputime_zero; + tsk->cputime_expires.sched_exp = 0; + INIT_LIST_HEAD(&tsk->cpu_timers[0]); + INIT_LIST_HEAD(&tsk->cpu_timers[1]); + INIT_LIST_HEAD(&tsk->cpu_timers[2]); +} + +/* * This creates a new process as a copy of the old one, * but does not actually start it yet. * @@ -995,6 +1023,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->prev_utime = cputime_zero; p->prev_stime = cputime_zero; + p->default_timer_slack_ns = current->timer_slack_ns; + #ifdef CONFIG_DETECT_SOFTLOCKUP p->last_switch_count = 0; p->last_switch_timestamp = 0; @@ -1003,12 +1033,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, task_io_accounting_init(&p->ioac); acct_clear_integrals(p); - p->it_virt_expires = cputime_zero; - p->it_prof_expires = cputime_zero; - p->it_sched_expires = 0; - INIT_LIST_HEAD(&p->cpu_timers[0]); - INIT_LIST_HEAD(&p->cpu_timers[1]); - INIT_LIST_HEAD(&p->cpu_timers[2]); + posix_cpu_timers_init(p); p->lock_depth = -1; /* -1 = no lock */ do_posix_clock_monotonic_gettime(&p->start_time); @@ -1209,21 +1234,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); - - if (!cputime_eq(current->signal->it_virt_expires, - cputime_zero) || - !cputime_eq(current->signal->it_prof_expires, - cputime_zero) || - current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY || - !list_empty(¤t->signal->cpu_timers[0]) || - !list_empty(¤t->signal->cpu_timers[1]) || - !list_empty(¤t->signal->cpu_timers[2])) { - /* - * Have child wake up on its first tick to check - * for process CPU timers. - */ - p->it_prof_expires = jiffies_to_cputime(1); - } } if (likely(p->pid)) { diff --git a/kernel/futex.c b/kernel/futex.c index 62cbd648e28a..e10c5c8786a6 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -1229,13 +1229,16 @@ static int futex_wait(u32 __user *uaddr, int fshared, if (!abs_time) schedule(); else { + unsigned long slack; + slack = current->timer_slack_ns; + if (rt_task(current)) + slack = 0; hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); hrtimer_init_sleeper(&t, current); - t.timer.expires = *abs_time; + hrtimer_set_expires_range_ns(&t.timer, *abs_time, slack); - hrtimer_start(&t.timer, t.timer.expires, - HRTIMER_MODE_ABS); + hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS); if (!hrtimer_active(&t.timer)) t.task = NULL; @@ -1337,7 +1340,7 @@ static int futex_lock_pi(u32 __user *uaddr, int fshared, hrtimer_init_on_stack(&to->timer, CLOCK_REALTIME, HRTIMER_MODE_ABS); hrtimer_init_sleeper(to, current); - to->timer.expires = *time; + hrtimer_set_expires(&to->timer, *time); } q.pi_state = NULL; diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index cdec83e722fa..3d4d8d12ac15 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -517,7 +517,7 @@ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base) if (!base->first) continue; timer = rb_entry(base->first, struct hrtimer, node); - expires = ktime_sub(timer->expires, base->offset); + expires = ktime_sub(hrtimer_get_expires(timer), base->offset); if (expires.tv64 < cpu_base->expires_next.tv64) cpu_base->expires_next = expires; } @@ -539,10 +539,10 @@ static int hrtimer_reprogram(struct hrtimer *timer, struct hrtimer_clock_base *base) { ktime_t *expires_next = &__get_cpu_var(hrtimer_bases).expires_next; - ktime_t expires = ktime_sub(timer->expires, base->offset); + ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset); int res; - WARN_ON_ONCE(timer->expires.tv64 < 0); + WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0); /* * When the callback is running, we do not reprogram the clock event @@ -795,7 +795,7 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) u64 orun = 1; ktime_t delta; - delta = ktime_sub(now, timer->expires); + delta = ktime_sub(now, hrtimer_get_expires(timer)); if (delta.tv64 < 0) return 0; @@ -807,8 +807,8 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) s64 incr = ktime_to_ns(interval); orun = ktime_divns(delta, incr); - timer->expires = ktime_add_ns(timer->expires, incr * orun); - if (timer->expires.tv64 > now.tv64) + hrtimer_add_expires_ns(timer, incr * orun); + if (hrtimer_get_expires_tv64(timer) > now.tv64) return orun; /* * This (and the ktime_add() below) is the @@ -816,7 +816,7 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) */ orun++; } - timer->expires = ktime_add_safe(timer->expires, interval); + hrtimer_add_expires(timer, interval); return orun; } @@ -848,7 +848,8 @@ static void enqueue_hrtimer(struct hrtimer *timer, * We dont care about collisions. Nodes with * the same expiry time stay together. */ - if (timer->expires.tv64 < entry->expires.tv64) { + if (hrtimer_get_expires_tv64(timer) < + hrtimer_get_expires_tv64(entry)) { link = &(*link)->rb_left; } else { link = &(*link)->rb_right; @@ -945,9 +946,10 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base) } /** - * hrtimer_start - (re)start an relative timer on the current CPU + * hrtimer_start_range_ns - (re)start an relative timer on the current CPU * @timer: the timer to be added * @tim: expiry time + * @delta_ns: "slack" range for the timer * @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL) * * Returns: @@ -955,7 +957,8 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base) * 1 when the timer was active */ int -hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) +hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_ns, + const enum hrtimer_mode mode) { struct hrtimer_clock_base *base, *new_base; unsigned long flags; @@ -983,7 +986,7 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) #endif } - timer->expires = tim; + hrtimer_set_expires_range_ns(timer, tim, delta_ns); timer_stats_hrtimer_set_start_info(timer); @@ -1016,8 +1019,26 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) return ret; } +EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); + +/** + * hrtimer_start - (re)start an relative timer on the current CPU + * @timer: the timer to be added + * @tim: expiry time + * @mode: expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL) + * + * Returns: + * 0 on success + * 1 when the timer was active + */ +int +hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) +{ + return hrtimer_start_range_ns(timer, tim, 0, mode); +} EXPORT_SYMBOL_GPL(hrtimer_start); + /** * hrtimer_try_to_cancel - try to deactivate a timer * @timer: hrtimer to stop @@ -1077,7 +1098,7 @@ ktime_t hrtimer_get_remaining(const struct hrtimer *timer) ktime_t rem; base = lock_hrtimer_base(timer, &flags); - rem = ktime_sub(timer->expires, base->get_time()); + rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; @@ -1109,7 +1130,7 @@ ktime_t hrtimer_get_next_event(void) continue; timer = rb_entry(base->first, struct hrtimer, node); - delta.tv64 = timer->expires.tv64; + delta.tv64 = hrtimer_get_expires_tv64(timer); delta = ktime_sub(delta, base->get_time()); if (delta.tv64 < mindelta.tv64) mindelta.tv64 = delta.tv64; @@ -1310,10 +1331,23 @@ void hrtimer_interrupt(struct clock_event_device *dev) timer = rb_entry(node, struct hrtimer, node); - if (basenow.tv64 < timer->expires.tv64) { + /* + * The immediate goal for using the softexpires is + * minimizing wakeups, not running timers at the + * earliest interrupt after their soft expiration. + * This allows us to avoid using a Priority Search + * Tree, which can answer a stabbing querry for + * overlapping intervals and instead use the simple + * BST we already have. + * We don't add extra wakeups by delaying timers that + * are right-of a not yet expired timer, because that + * timer will have to trigger a wakeup anyway. + */ + + if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) { ktime_t expires; - expires = ktime_sub(timer->expires, + expires = ktime_sub(hrtimer_get_expires(timer), base->offset); if (expires.tv64 < expires_next.tv64) expires_next = expires; @@ -1349,6 +1383,36 @@ void hrtimer_interrupt(struct clock_event_device *dev) raise_softirq(HRTIMER_SOFTIRQ); } +/** + * hrtimer_peek_ahead_timers -- run soft-expired timers now + * + * hrtimer_peek_ahead_timers will peek at the timer queue of + * the current cpu and check if there are any timers for which + * the soft expires time has passed. If any such timers exist, + * they are run immediately and then removed from the timer queue. + * + */ +void hrtimer_peek_ahead_timers(void) +{ + unsigned long flags; + struct tick_device *td; + struct clock_event_device *dev; + + if (!hrtimer_hres_active()) + return; + + local_irq_save(flags); + td = &__get_cpu_var(tick_cpu_device); + if (!td) + goto out; + dev = td->evtdev; + if (!dev) + goto out; + hrtimer_interrupt(dev); +out: + local_irq_restore(flags); +} + static void run_hrtimer_softirq(struct softirq_action *h) { run_hrtimer_pending(&__get_cpu_var(hrtimer_bases)); @@ -1403,9 +1467,7 @@ void hrtimer_run_queues(void) if (!base->first) continue; - if (base->get_softirq_time) - base->softirq_time = base->get_softirq_time(); - else if (gettime) { + if (gettime) { hrtimer_get_softirq_time(cpu_base); gettime = 0; } @@ -1416,7 +1478,8 @@ void hrtimer_run_queues(void) struct hrtimer *timer; timer = rb_entry(node, struct hrtimer, node); - if (base->softirq_time.tv64 <= timer->expires.tv64) + if (base->softirq_time.tv64 <= + hrtimer_get_expires_tv64(timer)) break; if (timer->cb_mode == HRTIMER_CB_SOFTIRQ) { @@ -1464,7 +1527,7 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod do { set_current_state(TASK_INTERRUPTIBLE); - hrtimer_start(&t->timer, t->timer.expires, mode); + hrtimer_start_expires(&t->timer, mode); if (!hrtimer_active(&t->timer)) t->task = NULL; @@ -1486,7 +1549,7 @@ static int update_rmtp(struct hrtimer *timer, struct timespec __user *rmtp) struct timespec rmt; ktime_t rem; - rem = ktime_sub(timer->expires, timer->base->get_time()); + rem = hrtimer_expires_remaining(timer); if (rem.tv64 <= 0) return 0; rmt = ktime_to_timespec(rem); @@ -1505,7 +1568,7 @@ long __sched hrtimer_nanosleep_restart(struct restart_block *restart) hrtimer_init_on_stack(&t.timer, restart->nanosleep.index, HRTIMER_MODE_ABS); - t.timer.expires.tv64 = restart->nanosleep.expires; + hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); if (do_nanosleep(&t, HRTIMER_MODE_ABS)) goto out; @@ -1530,9 +1593,14 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, struct restart_block *restart; struct hrtimer_sleeper t; int ret = 0; + unsigned long slack; + + slack = current->timer_slack_ns; + if (rt_task(current)) + slack = 0; hrtimer_init_on_stack(&t.timer, clockid, mode); - t.timer.expires = timespec_to_ktime(*rqtp); + hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack); if (do_nanosleep(&t, mode)) goto out; @@ -1552,7 +1620,7 @@ long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp, restart->fn = hrtimer_nanosleep_restart; restart->nanosleep.index = t.timer.base->index; restart->nanosleep.rmtp = rmtp; - restart->nanosleep.expires = t.timer.expires.tv64; + restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); ret = -ERESTART_RESTARTBLOCK; out: @@ -1688,9 +1756,11 @@ static void migrate_hrtimers(int cpu) new_base = &get_cpu_var(hrtimer_bases); tick_cancel_sched_timer(cpu); - - local_irq_disable(); - spin_lock(&new_base->lock); + /* + * The caller is globally serialized and nobody else + * takes two locks at once, deadlock is not possible. + */ + spin_lock_irq(&new_base->lock); spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { @@ -1703,8 +1773,7 @@ static void migrate_hrtimers(int cpu) raise = 1; spin_unlock(&old_base->lock); - spin_unlock(&new_base->lock); - local_irq_enable(); + spin_unlock_irq(&new_base->lock); put_cpu_var(hrtimer_bases); if (raise) @@ -1753,3 +1822,103 @@ void __init hrtimers_init(void) #endif } +/** + * schedule_hrtimeout_range - sleep until timeout + * @expires: timeout value (ktime_t) + * @delta: slack in expires timeout (ktime_t) + * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL + * + * Make the current task sleep until the given expiry time has + * elapsed. The routine will return immediately unless + * the current task state has been set (see set_current_state()). + * + * The @delta argument gives the kernel the freedom to schedule the + * actual wakeup to a time that is both power and performance friendly. + * The kernel give the normal best effort behavior for "@expires+@delta", + * but may decide to fire the timer earlier, but no earlier than @expires. + * + * You can set the task state as follows - + * + * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to + * pass before the routine returns. + * + * %TASK_INTERRUPTIBLE - the routine may return early if a signal is + * delivered to the current task. + * + * The current task state is guaranteed to be TASK_RUNNING when this + * routine returns. + * + * Returns 0 when the timer has expired otherwise -EINTR + */ +int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta, + const enum hrtimer_mode mode) +{ + struct hrtimer_sleeper t; + + /* + * Optimize when a zero timeout value is given. It does not + * matter whether this is an absolute or a relative time. + */ + if (expires && !expires->tv64) { + __set_current_state(TASK_RUNNING); + return 0; + } + + /* + * A NULL parameter means "inifinte" + */ + if (!expires) { + schedule(); + __set_current_state(TASK_RUNNING); + return -EINTR; + } + + hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode); + hrtimer_set_expires_range_ns(&t.timer, *expires, delta); + + hrtimer_init_sleeper(&t, current); + + hrtimer_start_expires(&t.timer, mode); + if (!hrtimer_active(&t.timer)) + t.task = NULL; + + if (likely(t.task)) + schedule(); + + hrtimer_cancel(&t.timer); + destroy_hrtimer_on_stack(&t.timer); + + __set_current_state(TASK_RUNNING); + + return !t.task ? 0 : -EINTR; +} +EXPORT_SYMBOL_GPL(schedule_hrtimeout_range); + +/** + * schedule_hrtimeout - sleep until timeout + * @expires: timeout value (ktime_t) + * @mode: timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL + * + * Make the current task sleep until the given expiry time has + * elapsed. The routine will return immediately unless + * the current task state has been set (see set_current_state()). + * + * You can set the task state as follows - + * + * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to + * pass before the routine returns. + * + * %TASK_INTERRUPTIBLE - the routine may return early if a signal is + * delivered to the current task. + * + * The current task state is guaranteed to be TASK_RUNNING when this + * routine returns. + * + * Returns 0 when the timer has expired otherwise -EINTR + */ +int __sched schedule_hrtimeout(ktime_t *expires, + const enum hrtimer_mode mode) +{ + return schedule_hrtimeout_range(expires, 0, mode); +} +EXPORT_SYMBOL_GPL(schedule_hrtimeout); diff --git a/kernel/itimer.c b/kernel/itimer.c index ab982747d9bd..db7c358b9a02 100644 --- a/kernel/itimer.c +++ b/kernel/itimer.c @@ -55,17 +55,15 @@ int do_getitimer(int which, struct itimerval *value) spin_unlock_irq(&tsk->sighand->siglock); break; case ITIMER_VIRTUAL: - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_virt_expires; cinterval = tsk->signal->it_virt_incr; if (!cputime_eq(cval, cputime_zero)) { - struct task_struct *t = tsk; - cputime_t utime = tsk->signal->utime; - do { - utime = cputime_add(utime, t->utime); - t = next_thread(t); - } while (t != tsk); + struct task_cputime cputime; + cputime_t utime; + + thread_group_cputime(tsk, &cputime); + utime = cputime.utime; if (cputime_le(cval, utime)) { /* about to fire */ cval = jiffies_to_cputime(1); } else { @@ -73,25 +71,19 @@ int do_getitimer(int which, struct itimerval *value) } } spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); cputime_to_timeval(cval, &value->it_value); cputime_to_timeval(cinterval, &value->it_interval); break; case ITIMER_PROF: - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_prof_expires; cinterval = tsk->signal->it_prof_incr; if (!cputime_eq(cval, cputime_zero)) { - struct task_struct *t = tsk; - cputime_t ptime = cputime_add(tsk->signal->utime, - tsk->signal->stime); - do { - ptime = cputime_add(ptime, - cputime_add(t->utime, - t->stime)); - t = next_thread(t); - } while (t != tsk); + struct task_cputime times; + cputime_t ptime; + + thread_group_cputime(tsk, ×); + ptime = cputime_add(times.utime, times.stime); if (cputime_le(cval, ptime)) { /* about to fire */ cval = jiffies_to_cputime(1); } else { @@ -99,7 +91,6 @@ int do_getitimer(int which, struct itimerval *value) } } spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); cputime_to_timeval(cval, &value->it_value); cputime_to_timeval(cinterval, &value->it_interval); break; @@ -185,7 +176,6 @@ again: case ITIMER_VIRTUAL: nval = timeval_to_cputime(&value->it_value); ninterval = timeval_to_cputime(&value->it_interval); - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_virt_expires; cinterval = tsk->signal->it_virt_incr; @@ -200,7 +190,6 @@ again: tsk->signal->it_virt_expires = nval; tsk->signal->it_virt_incr = ninterval; spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); if (ovalue) { cputime_to_timeval(cval, &ovalue->it_value); cputime_to_timeval(cinterval, &ovalue->it_interval); @@ -209,7 +198,6 @@ again: case ITIMER_PROF: nval = timeval_to_cputime(&value->it_value); ninterval = timeval_to_cputime(&value->it_interval); - read_lock(&tasklist_lock); spin_lock_irq(&tsk->sighand->siglock); cval = tsk->signal->it_prof_expires; cinterval = tsk->signal->it_prof_incr; @@ -224,7 +212,6 @@ again: tsk->signal->it_prof_expires = nval; tsk->signal->it_prof_incr = ninterval; spin_unlock_irq(&tsk->sighand->siglock); - read_unlock(&tasklist_lock); if (ovalue) { cputime_to_timeval(cval, &ovalue->it_value); cputime_to_timeval(cinterval, &ovalue->it_interval); diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c index c42a03aef36f..153dcb2639c3 100644 --- a/kernel/posix-cpu-timers.c +++ b/kernel/posix-cpu-timers.c @@ -7,6 +7,93 @@ #include <linux/errno.h> #include <linux/math64.h> #include <asm/uaccess.h> +#include <linux/kernel_stat.h> + +/* + * Allocate the thread_group_cputime structure appropriately and fill in the + * current values of the fields. Called from copy_signal() via + * thread_group_cputime_clone_thread() when adding a second or subsequent + * thread to a thread group. Assumes interrupts are enabled when called. + */ +int thread_group_cputime_alloc(struct task_struct *tsk) +{ + struct signal_struct *sig = tsk->signal; + struct task_cputime *cputime; + + /* + * If we have multiple threads and we don't already have a + * per-CPU task_cputime struct (checked in the caller), allocate + * one and fill it in with the times accumulated so far. We may + * race with another thread so recheck after we pick up the sighand + * lock. + */ + cputime = alloc_percpu(struct task_cputime); + if (cputime == NULL) + return -ENOMEM; + spin_lock_irq(&tsk->sighand->siglock); + if (sig->cputime.totals) { + spin_unlock_irq(&tsk->sighand->siglock); + free_percpu(cputime); + return 0; + } + sig->cputime.totals = cputime; + cputime = per_cpu_ptr(sig->cputime.totals, smp_processor_id()); + cputime->utime = tsk->utime; + cputime->stime = tsk->stime; + cputime->sum_exec_runtime = tsk->se.sum_exec_runtime; + spin_unlock_irq(&tsk->sighand->siglock); + return 0; +} + +/** + * thread_group_cputime - Sum the thread group time fields across all CPUs. + * + * @tsk: The task we use to identify the thread group. + * @times: task_cputime structure in which we return the summed fields. + * + * Walk the list of CPUs to sum the per-CPU time fields in the thread group + * time structure. + */ +void thread_group_cputime( + struct task_struct *tsk, + struct task_cputime *times) +{ + struct signal_struct *sig; + int i; + struct task_cputime *tot; + + sig = tsk->signal; + if (unlikely(!sig) || !sig->cputime.totals) { + times->utime = tsk->utime; + times->stime = tsk->stime; + times->sum_exec_runtime = tsk->se.sum_exec_runtime; + return; + } + times->stime = times->utime = cputime_zero; + times->sum_exec_runtime = 0; + for_each_possible_cpu(i) { + tot = per_cpu_ptr(tsk->signal->cputime.totals, i); + times->utime = cputime_add(times->utime, tot->utime); + times->stime = cputime_add(times->stime, tot->stime); + times->sum_exec_runtime += tot->sum_exec_runtime; + } +} + +/* + * Called after updating RLIMIT_CPU to set timer expiration if necessary. + */ +void update_rlimit_cpu(unsigned long rlim_new) +{ + cputime_t cputime; + + cputime = secs_to_cputime(rlim_new); + if (cputime_eq(current->signal->it_prof_expires, cputime_zero) || + cputime_lt(current->signal->it_prof_expires, cputime)) { + spin_lock_irq(¤t->sighand->siglock); + set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL); + spin_unlock_irq(¤t->sighand->siglock); + } +} static int check_clock(const clockid_t which_clock) { @@ -158,10 +245,6 @@ static inline cputime_t virt_ticks(struct task_struct *p) { return p->utime; } -static inline unsigned long long sched_ns(struct task_struct *p) -{ - return task_sched_runtime(p); -} int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp) { @@ -211,7 +294,7 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, cpu->cpu = virt_ticks(p); break; case CPUCLOCK_SCHED: - cpu->sched = sched_ns(p); + cpu->sched = p->se.sum_exec_runtime + task_delta_exec(p); break; } return 0; @@ -220,59 +303,30 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p, /* * Sample a process (thread group) clock for the given group_leader task. * Must be called with tasklist_lock held for reading. - * Must be called with tasklist_lock held for reading, and p->sighand->siglock. */ -static int cpu_clock_sample_group_locked(unsigned int clock_idx, - struct task_struct *p, - union cpu_time_count *cpu) +static int cpu_clock_sample_group(const clockid_t which_clock, + struct task_struct *p, + union cpu_time_count *cpu) { - struct task_struct *t = p; - switch (clock_idx) { + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + switch (which_clock) { default: return -EINVAL; case CPUCLOCK_PROF: - cpu->cpu = cputime_add(p->signal->utime, p->signal->stime); - do { - cpu->cpu = cputime_add(cpu->cpu, prof_ticks(t)); - t = next_thread(t); - } while (t != p); + cpu->cpu = cputime_add(cputime.utime, cputime.stime); break; case CPUCLOCK_VIRT: - cpu->cpu = p->signal->utime; - do { - cpu->cpu = cputime_add(cpu->cpu, virt_ticks(t)); - t = next_thread(t); - } while (t != p); + cpu->cpu = cputime.utime; break; case CPUCLOCK_SCHED: - cpu->sched = p->signal->sum_sched_runtime; - /* Add in each other live thread. */ - while ((t = next_thread(t)) != p) { - cpu->sched += t->se.sum_exec_runtime; - } - cpu->sched += sched_ns(p); + cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p); break; } return 0; } -/* - * 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(const clockid_t which_clock, - struct task_struct *p, - union cpu_time_count *cpu) -{ - int ret; - unsigned long flags; - spin_lock_irqsave(&p->sighand->siglock, flags); - ret = cpu_clock_sample_group_locked(CPUCLOCK_WHICH(which_clock), p, - cpu); - spin_unlock_irqrestore(&p->sighand->siglock, flags); - return ret; -} - int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp) { @@ -471,80 +525,11 @@ void posix_cpu_timers_exit(struct task_struct *tsk) } void posix_cpu_timers_exit_group(struct task_struct *tsk) { - cleanup_timers(tsk->signal->cpu_timers, - cputime_add(tsk->utime, tsk->signal->utime), - cputime_add(tsk->stime, tsk->signal->stime), - tsk->se.sum_exec_runtime + tsk->signal->sum_sched_runtime); -} + struct task_cputime cputime; - -/* - * Set the expiry times of all the threads in the process so one of them - * will go off before the process cumulative expiry total is reached. - */ -static void process_timer_rebalance(struct task_struct *p, - unsigned int clock_idx, - union cpu_time_count expires, - union cpu_time_count val) -{ - cputime_t ticks, left; - unsigned long long ns, nsleft; - struct task_struct *t = p; - unsigned int nthreads = atomic_read(&p->signal->live); - - if (!nthreads) - return; - - switch (clock_idx) { - default: - BUG(); - break; - case CPUCLOCK_PROF: - left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu), - nthreads); - do { - if (likely(!(t->flags & PF_EXITING))) { - ticks = cputime_add(prof_ticks(t), left); - if (cputime_eq(t->it_prof_expires, - cputime_zero) || - cputime_gt(t->it_prof_expires, ticks)) { - t->it_prof_expires = ticks; - } - } - t = next_thread(t); - } while (t != p); - break; - case CPUCLOCK_VIRT: - left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu), - nthreads); - do { - if (likely(!(t->flags & PF_EXITING))) { - ticks = cputime_add(virt_ticks(t), left); - if (cputime_eq(t->it_virt_expires, - cputime_zero) || - cputime_gt(t->it_virt_expires, ticks)) { - t->it_virt_expires = ticks; - } - } - t = next_thread(t); - } while (t != p); - break; - case CPUCLOCK_SCHED: - nsleft = expires.sched - val.sched; - do_div(nsleft, nthreads); - nsleft = max_t(unsigned long long, nsleft, 1); - do { - if (likely(!(t->flags & PF_EXITING))) { - ns = t->se.sum_exec_runtime + nsleft; - if (t->it_sched_expires == 0 || - t->it_sched_expires > ns) { - t->it_sched_expires = ns; - } - } - t = next_thread(t); - } while (t != p); - break; - } + thread_group_cputime(tsk, &cputime); + cleanup_timers(tsk->signal->cpu_timers, + cputime.utime, cputime.stime, cputime.sum_exec_runtime); } static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now) @@ -608,29 +593,32 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) default: BUG(); case CPUCLOCK_PROF: - if (cputime_eq(p->it_prof_expires, + if (cputime_eq(p->cputime_expires.prof_exp, cputime_zero) || - cputime_gt(p->it_prof_expires, + cputime_gt(p->cputime_expires.prof_exp, nt->expires.cpu)) - p->it_prof_expires = nt->expires.cpu; + p->cputime_expires.prof_exp = + nt->expires.cpu; break; case CPUCLOCK_VIRT: - if (cputime_eq(p->it_virt_expires, + if (cputime_eq(p->cputime_expires.virt_exp, cputime_zero) || - cputime_gt(p->it_virt_expires, + cputime_gt(p->cputime_expires.virt_exp, nt->expires.cpu)) - p->it_virt_expires = nt->expires.cpu; + p->cputime_expires.virt_exp = + nt->expires.cpu; break; case CPUCLOCK_SCHED: - if (p->it_sched_expires == 0 || - p->it_sched_expires > nt->expires.sched) - p->it_sched_expires = nt->expires.sched; + if (p->cputime_expires.sched_exp == 0 || + p->cputime_expires.sched_exp > + nt->expires.sched) + p->cputime_expires.sched_exp = + nt->expires.sched; break; } } else { /* - * For a process timer, we must balance - * all the live threads' expirations. + * For a process timer, set the cached expiration time. */ switch (CPUCLOCK_WHICH(timer->it_clock)) { default: @@ -641,7 +629,9 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) cputime_lt(p->signal->it_virt_expires, timer->it.cpu.expires.cpu)) break; - goto rebalance; + p->signal->cputime_expires.virt_exp = + timer->it.cpu.expires.cpu; + break; case CPUCLOCK_PROF: if (!cputime_eq(p->signal->it_prof_expires, cputime_zero) && @@ -652,13 +642,12 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now) if (i != RLIM_INFINITY && i <= cputime_to_secs(timer->it.cpu.expires.cpu)) break; - goto rebalance; + p->signal->cputime_expires.prof_exp = + timer->it.cpu.expires.cpu; + break; case CPUCLOCK_SCHED: - rebalance: - process_timer_rebalance( - timer->it.cpu.task, - CPUCLOCK_WHICH(timer->it_clock), - timer->it.cpu.expires, now); + p->signal->cputime_expires.sched_exp = + timer->it.cpu.expires.sched; break; } } @@ -969,13 +958,13 @@ static void check_thread_timers(struct task_struct *tsk, struct signal_struct *const sig = tsk->signal; maxfire = 20; - tsk->it_prof_expires = cputime_zero; + tsk->cputime_expires.prof_exp = cputime_zero; while (!list_empty(timers)) { struct cpu_timer_list *t = list_first_entry(timers, struct cpu_timer_list, entry); if (!--maxfire || cputime_lt(prof_ticks(tsk), t->expires.cpu)) { - tsk->it_prof_expires = t->expires.cpu; + tsk->cputime_expires.prof_exp = t->expires.cpu; break; } t->firing = 1; @@ -984,13 +973,13 @@ static void check_thread_timers(struct task_struct *tsk, ++timers; maxfire = 20; - tsk->it_virt_expires = cputime_zero; + tsk->cputime_expires.virt_exp = cputime_zero; while (!list_empty(timers)) { struct cpu_timer_list *t = list_first_entry(timers, struct cpu_timer_list, entry); if (!--maxfire || cputime_lt(virt_ticks(tsk), t->expires.cpu)) { - tsk->it_virt_expires = t->expires.cpu; + tsk->cputime_expires.virt_exp = t->expires.cpu; break; } t->firing = 1; @@ -999,13 +988,13 @@ static void check_thread_timers(struct task_struct *tsk, ++timers; maxfire = 20; - tsk->it_sched_expires = 0; + tsk->cputime_expires.sched_exp = 0; while (!list_empty(timers)) { struct cpu_timer_list *t = list_first_entry(timers, struct cpu_timer_list, entry); if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) { - tsk->it_sched_expires = t->expires.sched; + tsk->cputime_expires.sched_exp = t->expires.sched; break; } t->firing = 1; @@ -1055,10 +1044,10 @@ static void check_process_timers(struct task_struct *tsk, { int maxfire; struct signal_struct *const sig = tsk->signal; - cputime_t utime, stime, ptime, virt_expires, prof_expires; + cputime_t utime, ptime, virt_expires, prof_expires; unsigned long long sum_sched_runtime, sched_expires; - struct task_struct *t; struct list_head *timers = sig->cpu_timers; + struct task_cputime cputime; /* * Don't sample the current process CPU clocks if there are no timers. @@ -1074,18 +1063,10 @@ static void check_process_timers(struct task_struct *tsk, /* * Collect the current process totals. */ - utime = sig->utime; - stime = sig->stime; - sum_sched_runtime = sig->sum_sched_runtime; - t = tsk; - do { - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); - sum_sched_runtime += t->se.sum_exec_runtime; - t = next_thread(t); - } while (t != tsk); - ptime = cputime_add(utime, stime); - + thread_group_cputime(tsk, &cputime); + utime = cputime.utime; + ptime = cputime_add(utime, cputime.stime); + sum_sched_runtime = cputime.sum_exec_runtime; maxfire = 20; prof_expires = cputime_zero; while (!list_empty(timers)) { @@ -1193,60 +1174,18 @@ static void check_process_timers(struct task_struct *tsk, } } - if (!cputime_eq(prof_expires, cputime_zero) || - !cputime_eq(virt_expires, cputime_zero) || - sched_expires != 0) { - /* - * Rebalance the threads' expiry times for the remaining - * process CPU timers. - */ - - cputime_t prof_left, virt_left, ticks; - unsigned long long sched_left, sched; - const unsigned int nthreads = atomic_read(&sig->live); - - if (!nthreads) - return; - - prof_left = cputime_sub(prof_expires, utime); - prof_left = cputime_sub(prof_left, stime); - prof_left = cputime_div_non_zero(prof_left, nthreads); - virt_left = cputime_sub(virt_expires, utime); - virt_left = cputime_div_non_zero(virt_left, nthreads); - if (sched_expires) { - sched_left = sched_expires - sum_sched_runtime; - 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) && - (cputime_eq(t->it_prof_expires, cputime_zero) || - cputime_gt(t->it_prof_expires, ticks))) { - t->it_prof_expires = ticks; - } - - ticks = cputime_add(t->utime, virt_left); - if (!cputime_eq(virt_expires, cputime_zero) && - (cputime_eq(t->it_virt_expires, cputime_zero) || - cputime_gt(t->it_virt_expires, ticks))) { - t->it_virt_expires = ticks; - } - - sched = t->se.sum_exec_runtime + sched_left; - if (sched_expires && (t->it_sched_expires == 0 || - t->it_sched_expires > sched)) { - t->it_sched_expires = sched; - } - } while ((t = next_thread(t)) != tsk); - } + if (!cputime_eq(prof_expires, cputime_zero) && + (cputime_eq(sig->cputime_expires.prof_exp, cputime_zero) || + cputime_gt(sig->cputime_expires.prof_exp, prof_expires))) + sig->cputime_expires.prof_exp = prof_expires; + if (!cputime_eq(virt_expires, cputime_zero) && + (cputime_eq(sig->cputime_expires.virt_exp, cputime_zero) || + cputime_gt(sig->cputime_expires.virt_exp, virt_expires))) + sig->cputime_expires.virt_exp = virt_expires; + if (sched_expires != 0 && + (sig->cputime_expires.sched_exp == 0 || + sig->cputime_expires.sched_exp > sched_expires)) + sig->cputime_expires.sched_exp = sched_expires; } /* @@ -1314,6 +1253,86 @@ out: ++timer->it_requeue_pending; } +/** + * task_cputime_zero - Check a task_cputime struct for all zero fields. + * + * @cputime: The struct to compare. + * + * Checks @cputime to see if all fields are zero. Returns true if all fields + * are zero, false if any field is nonzero. + */ +static inline int task_cputime_zero(const struct task_cputime *cputime) +{ + if (cputime_eq(cputime->utime, cputime_zero) && + cputime_eq(cputime->stime, cputime_zero) && + cputime->sum_exec_runtime == 0) + return 1; + return 0; +} + +/** + * task_cputime_expired - Compare two task_cputime entities. + * + * @sample: The task_cputime structure to be checked for expiration. + * @expires: Expiration times, against which @sample will be checked. + * + * Checks @sample against @expires to see if any field of @sample has expired. + * Returns true if any field of the former is greater than the corresponding + * field of the latter if the latter field is set. Otherwise returns false. + */ +static inline int task_cputime_expired(const struct task_cputime *sample, + const struct task_cputime *expires) +{ + if (!cputime_eq(expires->utime, cputime_zero) && + cputime_ge(sample->utime, expires->utime)) + return 1; + if (!cputime_eq(expires->stime, cputime_zero) && + cputime_ge(cputime_add(sample->utime, sample->stime), + expires->stime)) + return 1; + if (expires->sum_exec_runtime != 0 && + sample->sum_exec_runtime >= expires->sum_exec_runtime) + return 1; + return 0; +} + +/** + * fastpath_timer_check - POSIX CPU timers fast path. + * + * @tsk: The task (thread) being checked. + * + * Check the task and thread group timers. If both are zero (there are no + * timers set) return false. Otherwise snapshot the task and thread group + * timers and compare them with the corresponding expiration times. Return + * true if a timer has expired, else return false. + */ +static inline int fastpath_timer_check(struct task_struct *tsk) +{ + struct signal_struct *sig = tsk->signal; + + if (unlikely(!sig)) + return 0; + + if (!task_cputime_zero(&tsk->cputime_expires)) { + struct task_cputime task_sample = { + .utime = tsk->utime, + .stime = tsk->stime, + .sum_exec_runtime = tsk->se.sum_exec_runtime + }; + + if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) + return 1; + } + if (!task_cputime_zero(&sig->cputime_expires)) { + struct task_cputime group_sample; + + thread_group_cputime(tsk, &group_sample); + if (task_cputime_expired(&group_sample, &sig->cputime_expires)) + return 1; + } + return 0; +} + /* * This is called from the timer interrupt handler. The irq handler has * already updated our counts. We need to check if any timers fire now. @@ -1326,42 +1345,31 @@ void run_posix_cpu_timers(struct task_struct *tsk) BUG_ON(!irqs_disabled()); -#define UNEXPIRED(clock) \ - (cputime_eq(tsk->it_##clock##_expires, cputime_zero) || \ - cputime_lt(clock##_ticks(tsk), tsk->it_##clock##_expires)) - - if (UNEXPIRED(prof) && UNEXPIRED(virt) && - (tsk->it_sched_expires == 0 || - tsk->se.sum_exec_runtime < tsk->it_sched_expires)) + /* + * The fast path checks that there are no expired thread or thread + * group timers. If that's so, just return. + */ + if (!fastpath_timer_check(tsk)) return; -#undef UNEXPIRED - + spin_lock(&tsk->sighand->siglock); /* - * Double-check with locks held. + * Here we take off tsk->signal->cpu_timers[N] and + * tsk->cpu_timers[N] all the timers that are firing, and + * put them on the firing list. */ - read_lock(&tasklist_lock); - if (likely(tsk->signal != NULL)) { - spin_lock(&tsk->sighand->siglock); + 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); - } - read_unlock(&tasklist_lock); + /* + * 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); /* * Now that all the timers on our list have the firing flag, @@ -1389,10 +1397,9 @@ void run_posix_cpu_timers(struct task_struct *tsk) /* * Set one of the process-wide special case CPU timers. - * The tasklist_lock and tsk->sighand->siglock must be held by the caller. - * The oldval argument is null for the RLIMIT_CPU timer, where *newval is - * absolute; non-null for ITIMER_*, where *newval is relative and we update - * it to be absolute, *oldval is absolute and we update it to be relative. + * The tsk->sighand->siglock must be held by the caller. + * The *newval argument is relative and we update it to be absolute, *oldval + * is absolute and we update it to be relative. */ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, cputime_t *newval, cputime_t *oldval) @@ -1401,7 +1408,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, struct list_head *head; BUG_ON(clock_idx == CPUCLOCK_SCHED); - cpu_clock_sample_group_locked(clock_idx, tsk, &now); + cpu_clock_sample_group(clock_idx, tsk, &now); if (oldval) { if (!cputime_eq(*oldval, cputime_zero)) { @@ -1435,13 +1442,14 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx, cputime_ge(list_first_entry(head, struct cpu_timer_list, entry)->expires.cpu, *newval)) { - /* - * Rejigger each thread's expiry time so that one will - * notice before we hit the process-cumulative expiry time. - */ - union cpu_time_count expires = { .sched = 0 }; - expires.cpu = *newval; - process_timer_rebalance(tsk, clock_idx, expires, now); + switch (clock_idx) { + case CPUCLOCK_PROF: + tsk->signal->cputime_expires.prof_exp = *newval; + break; + case CPUCLOCK_VIRT: + tsk->signal->cputime_expires.virt_exp = *newval; + break; + } } } diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c index 5131e5471169..5e79c662294b 100644 --- a/kernel/posix-timers.c +++ b/kernel/posix-timers.c @@ -223,6 +223,15 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp) } /* + * Get monotonic time for posix timers + */ +static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp) +{ + getrawmonotonic(tp); + return 0; +} + +/* * Initialize everything, well, just everything in Posix clocks/timers ;) */ static __init int init_posix_timers(void) @@ -235,9 +244,15 @@ static __init int init_posix_timers(void) .clock_get = posix_ktime_get_ts, .clock_set = do_posix_clock_nosettime, }; + struct k_clock clock_monotonic_raw = { + .clock_getres = hrtimer_get_res, + .clock_get = posix_get_monotonic_raw, + .clock_set = do_posix_clock_nosettime, + }; register_posix_clock(CLOCK_REALTIME, &clock_realtime); register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic); + register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw); posix_timers_cache = kmem_cache_create("posix_timers_cache", sizeof (struct k_itimer), 0, SLAB_PANIC, @@ -298,6 +313,7 @@ void do_schedule_next_timer(struct siginfo *info) int posix_timer_event(struct k_itimer *timr, int si_private) { + int shared, ret; /* * FIXME: if ->sigq is queued we can race with * dequeue_signal()->do_schedule_next_timer(). @@ -311,25 +327,10 @@ int posix_timer_event(struct k_itimer *timr, int si_private) */ timr->sigq->info.si_sys_private = si_private; - timr->sigq->info.si_signo = timr->it_sigev_signo; - timr->sigq->info.si_code = SI_TIMER; - timr->sigq->info.si_tid = timr->it_id; - timr->sigq->info.si_value = timr->it_sigev_value; - - if (timr->it_sigev_notify & SIGEV_THREAD_ID) { - struct task_struct *leader; - int ret = send_sigqueue(timr->sigq, timr->it_process, 0); - - if (likely(ret >= 0)) - return ret; - - timr->it_sigev_notify = SIGEV_SIGNAL; - leader = timr->it_process->group_leader; - put_task_struct(timr->it_process); - timr->it_process = leader; - } - - return send_sigqueue(timr->sigq, timr->it_process, 1); + shared = !(timr->it_sigev_notify & SIGEV_THREAD_ID); + ret = send_sigqueue(timr->sigq, timr->it_process, shared); + /* If we failed to send the signal the timer stops. */ + return ret > 0; } EXPORT_SYMBOL_GPL(posix_timer_event); @@ -468,11 +469,9 @@ sys_timer_create(const clockid_t which_clock, struct sigevent __user *timer_event_spec, timer_t __user * created_timer_id) { - int error = 0; - struct k_itimer *new_timer = NULL; - int new_timer_id; - struct task_struct *process = NULL; - unsigned long flags; + struct k_itimer *new_timer; + int error, new_timer_id; + struct task_struct *process; sigevent_t event; int it_id_set = IT_ID_NOT_SET; @@ -490,12 +489,11 @@ sys_timer_create(const clockid_t which_clock, goto out; } spin_lock_irq(&idr_lock); - error = idr_get_new(&posix_timers_id, (void *) new_timer, - &new_timer_id); + error = idr_get_new(&posix_timers_id, new_timer, &new_timer_id); spin_unlock_irq(&idr_lock); - if (error == -EAGAIN) - goto retry; - else if (error) { + if (error) { + if (error == -EAGAIN) + goto retry; /* * Weird looking, but we return EAGAIN if the IDR is * full (proper POSIX return value for this) @@ -526,67 +524,43 @@ sys_timer_create(const clockid_t which_clock, error = -EFAULT; goto out; } - new_timer->it_sigev_notify = event.sigev_notify; - new_timer->it_sigev_signo = event.sigev_signo; - new_timer->it_sigev_value = event.sigev_value; - - read_lock(&tasklist_lock); - if ((process = good_sigevent(&event))) { - /* - * We may be setting up this process for another - * thread. It may be exiting. To catch this - * case the we check the PF_EXITING flag. If - * the flag is not set, the siglock will catch - * him before it is too late (in exit_itimers). - * - * The exec case is a bit more invloved but easy - * to code. If the process is in our thread - * group (and it must be or we would not allow - * it here) and is doing an exec, it will cause - * us to be killed. In this case it will wait - * for us to die which means we can finish this - * linkage with our last gasp. I.e. no code :) - */ - spin_lock_irqsave(&process->sighand->siglock, flags); - if (!(process->flags & PF_EXITING)) { - new_timer->it_process = process; - list_add(&new_timer->list, - &process->signal->posix_timers); - if (new_timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID)) - get_task_struct(process); - spin_unlock_irqrestore(&process->sighand->siglock, flags); - } else { - spin_unlock_irqrestore(&process->sighand->siglock, flags); - process = NULL; - } - } - read_unlock(&tasklist_lock); + rcu_read_lock(); + process = good_sigevent(&event); + if (process) + get_task_struct(process); + rcu_read_unlock(); if (!process) { error = -EINVAL; goto out; } } else { - new_timer->it_sigev_notify = SIGEV_SIGNAL; - new_timer->it_sigev_signo = SIGALRM; - new_timer->it_sigev_value.sival_int = new_timer->it_id; + event.sigev_notify = SIGEV_SIGNAL; + event.sigev_signo = SIGALRM; + event.sigev_value.sival_int = new_timer->it_id; process = current->group_leader; - spin_lock_irqsave(&process->sighand->siglock, flags); - new_timer->it_process = process; - list_add(&new_timer->list, &process->signal->posix_timers); - spin_unlock_irqrestore(&process->sighand->siglock, flags); + get_task_struct(process); } + new_timer->it_sigev_notify = event.sigev_notify; + new_timer->sigq->info.si_signo = event.sigev_signo; + new_timer->sigq->info.si_value = event.sigev_value; + new_timer->sigq->info.si_tid = new_timer->it_id; + new_timer->sigq->info.si_code = SI_TIMER; + + spin_lock_irq(¤t->sighand->siglock); + new_timer->it_process = process; + list_add(&new_timer->list, ¤t->signal->posix_timers); + spin_unlock_irq(¤t->sighand->siglock); + + return 0; /* * In the case of the timer belonging to another task, after * the task is unlocked, the timer is owned by the other task * and may cease to exist at any time. Don't use or modify * new_timer after the unlock call. */ - out: - if (error) - release_posix_timer(new_timer, it_id_set); - + release_posix_timer(new_timer, it_id_set); return error; } @@ -597,7 +571,7 @@ out: * the find to the timer lock. To avoid a dead lock, the timer id MUST * be release with out holding the timer lock. */ -static struct k_itimer * lock_timer(timer_t timer_id, unsigned long *flags) +static struct k_itimer *lock_timer(timer_t timer_id, unsigned long *flags) { struct k_itimer *timr; /* @@ -605,23 +579,20 @@ static struct k_itimer * lock_timer(timer_t timer_id, unsigned long *flags) * flags part over to the timer lock. Must not let interrupts in * while we are moving the lock. */ - spin_lock_irqsave(&idr_lock, *flags); - timr = (struct k_itimer *) idr_find(&posix_timers_id, (int) timer_id); + timr = idr_find(&posix_timers_id, (int)timer_id); if (timr) { spin_lock(&timr->it_lock); - - if ((timr->it_id != timer_id) || !(timr->it_process) || - !same_thread_group(timr->it_process, current)) { - spin_unlock(&timr->it_lock); - spin_unlock_irqrestore(&idr_lock, *flags); - timr = NULL; - } else + if (timr->it_process && + same_thread_group(timr->it_process, current)) { spin_unlock(&idr_lock); - } else - spin_unlock_irqrestore(&idr_lock, *flags); + return timr; + } + spin_unlock(&timr->it_lock); + } + spin_unlock_irqrestore(&idr_lock, *flags); - return timr; + return NULL; } /* @@ -668,7 +639,7 @@ common_timer_get(struct k_itimer *timr, struct itimerspec *cur_setting) (timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) timr->it_overrun += (unsigned int) hrtimer_forward(timer, now, iv); - remaining = ktime_sub(timer->expires, now); + remaining = ktime_sub(hrtimer_get_expires(timer), now); /* Return 0 only, when the timer is expired and not pending */ if (remaining.tv64 <= 0) { /* @@ -762,7 +733,7 @@ common_timer_set(struct k_itimer *timr, int flags, hrtimer_init(&timr->it.real.timer, timr->it_clock, mode); timr->it.real.timer.function = posix_timer_fn; - timer->expires = timespec_to_ktime(new_setting->it_value); + hrtimer_set_expires(timer, timespec_to_ktime(new_setting->it_value)); /* Convert interval */ timr->it.real.interval = timespec_to_ktime(new_setting->it_interval); @@ -771,14 +742,12 @@ common_timer_set(struct k_itimer *timr, int flags, if (((timr->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE)) { /* Setup correct expiry time for relative timers */ if (mode == HRTIMER_MODE_REL) { - timer->expires = - ktime_add_safe(timer->expires, - timer->base->get_time()); + hrtimer_add_expires(timer, timer->base->get_time()); } return 0; } - hrtimer_start(timer, timer->expires, mode); + hrtimer_start_expires(timer, mode); return 0; } @@ -862,8 +831,7 @@ retry_delete: * This keeps any tasks waiting on the spin lock from thinking * they got something (see the lock code above). */ - if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID)) - put_task_struct(timer->it_process); + put_task_struct(timer->it_process); timer->it_process = NULL; unlock_timer(timer, flags); @@ -890,8 +858,7 @@ retry_delete: * This keeps any tasks waiting on the spin lock from thinking * they got something (see the lock code above). */ - if (timer->it_sigev_notify == (SIGEV_SIGNAL|SIGEV_THREAD_ID)) - put_task_struct(timer->it_process); + put_task_struct(timer->it_process); timer->it_process = NULL; unlock_timer(timer, flags); diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c index 6522ae5b14a2..69d9cb921ffa 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -631,8 +631,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, /* Setup the timer, when timeout != NULL */ if (unlikely(timeout)) { - hrtimer_start(&timeout->timer, timeout->timer.expires, - HRTIMER_MODE_ABS); + hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS); if (!hrtimer_active(&timeout->timer)) timeout->task = NULL; } diff --git a/kernel/sched.c b/kernel/sched.c index 812334c874b8..57b19cce681d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -227,9 +227,8 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) now = hrtimer_cb_get_time(&rt_b->rt_period_timer); hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period); - hrtimer_start(&rt_b->rt_period_timer, - rt_b->rt_period_timer.expires, - HRTIMER_MODE_ABS); + hrtimer_start_expires(&rt_b->rt_period_timer, + HRTIMER_MODE_ABS); } spin_unlock(&rt_b->rt_runtime_lock); } @@ -1064,7 +1063,7 @@ static void hrtick_start(struct rq *rq, u64 delay) struct hrtimer *timer = &rq->hrtick_timer; ktime_t time = ktime_add_ns(timer->base->get_time(), delay); - timer->expires = time; + hrtimer_set_expires(timer, time); if (rq == this_rq()) { hrtimer_restart(timer); @@ -4047,23 +4046,26 @@ DEFINE_PER_CPU(struct kernel_stat, kstat); EXPORT_PER_CPU_SYMBOL(kstat); /* - * Return p->sum_exec_runtime plus any more ns on the sched_clock - * that have not yet been banked in case the task is currently running. + * Return any ns on the sched_clock that have not yet been banked in + * @p in case that task is currently running. */ -unsigned long long task_sched_runtime(struct task_struct *p) +unsigned long long task_delta_exec(struct task_struct *p) { unsigned long flags; - u64 ns, delta_exec; struct rq *rq; + u64 ns = 0; rq = task_rq_lock(p, &flags); - ns = p->se.sum_exec_runtime; + if (task_current(rq, p)) { + u64 delta_exec; + update_rq_clock(rq); delta_exec = rq->clock - p->se.exec_start; if ((s64)delta_exec > 0) - ns += delta_exec; + ns = delta_exec; } + task_rq_unlock(rq, &flags); return ns; @@ -4080,6 +4082,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime) cputime64_t tmp; p->utime = cputime_add(p->utime, cputime); + account_group_user_time(p, cputime); /* Add user time to cpustat. */ tmp = cputime_to_cputime64(cputime); @@ -4104,6 +4107,7 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime) tmp = cputime_to_cputime64(cputime); p->utime = cputime_add(p->utime, cputime); + account_group_user_time(p, cputime); p->gtime = cputime_add(p->gtime, cputime); cpustat->user = cputime64_add(cpustat->user, tmp); @@ -4139,6 +4143,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset, } p->stime = cputime_add(p->stime, cputime); + account_group_system_time(p, cputime); /* Add system time to cpustat. */ tmp = cputime_to_cputime64(cputime); @@ -4180,6 +4185,7 @@ void account_steal_time(struct task_struct *p, cputime_t steal) if (p == rq->idle) { p->stime = cputime_add(p->stime, steal); + account_group_system_time(p, steal); if (atomic_read(&rq->nr_iowait) > 0) cpustat->iowait = cputime64_add(cpustat->iowait, tmp); else diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 18fd17172eb6..f604dae71316 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -449,6 +449,7 @@ static void update_curr(struct cfs_rq *cfs_rq) struct task_struct *curtask = task_of(curr); cpuacct_charge(curtask, delta_exec); + account_group_exec_runtime(curtask, delta_exec); } } diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index cdf5740ab03e..b446dc87494f 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -526,6 +526,8 @@ static void update_curr_rt(struct rq *rq) schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec)); curr->se.sum_exec_runtime += delta_exec; + account_group_exec_runtime(curr, delta_exec); + curr->se.exec_start = rq->clock; cpuacct_charge(curr, delta_exec); @@ -1458,7 +1460,7 @@ static void watchdog(struct rq *rq, struct task_struct *p) p->rt.timeout++; next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ); if (p->rt.timeout > next) - p->it_sched_expires = p->se.sum_exec_runtime; + p->cputime_expires.sched_exp = p->se.sum_exec_runtime; } } diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h index 8385d43987e2..b8c156979cf2 100644 --- a/kernel/sched_stats.h +++ b/kernel/sched_stats.h @@ -270,3 +270,89 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next) #define sched_info_switch(t, next) do { } while (0) #endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */ +/* + * The following are functions that support scheduler-internal time accounting. + * These functions are generally called at the timer tick. None of this depends + * on CONFIG_SCHEDSTATS. + */ + +/** + * account_group_user_time - Maintain utime for a thread group. + * + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the utime field of the + * thread_group_cputime structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the utime field there. + */ +static inline void account_group_user_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (unlikely(!sig)) + return; + if (sig->cputime.totals) { + struct task_cputime *times; + + times = per_cpu_ptr(sig->cputime.totals, get_cpu()); + times->utime = cputime_add(times->utime, cputime); + put_cpu_no_resched(); + } +} + +/** + * account_group_system_time - Maintain stime for a thread group. + * + * @tsk: Pointer to task structure. + * @cputime: Time value by which to increment the stime field of the + * thread_group_cputime structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the stime field there. + */ +static inline void account_group_system_time(struct task_struct *tsk, + cputime_t cputime) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (unlikely(!sig)) + return; + if (sig->cputime.totals) { + struct task_cputime *times; + + times = per_cpu_ptr(sig->cputime.totals, get_cpu()); + times->stime = cputime_add(times->stime, cputime); + put_cpu_no_resched(); + } +} + +/** + * account_group_exec_runtime - Maintain exec runtime for a thread group. + * + * @tsk: Pointer to task structure. + * @ns: Time value by which to increment the sum_exec_runtime field + * of the thread_group_cputime structure. + * + * If thread group time is being maintained, get the structure for the + * running CPU and update the sum_exec_runtime field there. + */ +static inline void account_group_exec_runtime(struct task_struct *tsk, + unsigned long long ns) +{ + struct signal_struct *sig; + + sig = tsk->signal; + if (unlikely(!sig)) + return; + if (sig->cputime.totals) { + struct task_cputime *times; + + times = per_cpu_ptr(sig->cputime.totals, get_cpu()); + times->sum_exec_runtime += ns; + put_cpu_no_resched(); + } +} diff --git a/kernel/signal.c b/kernel/signal.c index bf40ecc87b26..105217da5c82 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -1341,6 +1341,7 @@ int do_notify_parent(struct task_struct *tsk, int sig) struct siginfo info; unsigned long flags; struct sighand_struct *psig; + struct task_cputime cputime; int ret = sig; BUG_ON(sig == -1); @@ -1371,10 +1372,9 @@ int do_notify_parent(struct task_struct *tsk, int sig) info.si_uid = tsk->uid; - info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime, - tsk->signal->utime)); - info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime, - tsk->signal->stime)); + thread_group_cputime(tsk, &cputime); + info.si_utime = cputime_to_jiffies(cputime.utime); + info.si_stime = cputime_to_jiffies(cputime.stime); info.si_status = tsk->exit_code & 0x7f; if (tsk->exit_code & 0x80) diff --git a/kernel/sys.c b/kernel/sys.c index 0bc8fa3c2288..31deba8f7d16 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -853,38 +853,28 @@ asmlinkage long sys_setfsgid(gid_t gid) return old_fsgid; } +void do_sys_times(struct tms *tms) +{ + struct task_cputime cputime; + cputime_t cutime, cstime; + + spin_lock_irq(¤t->sighand->siglock); + thread_group_cputime(current, &cputime); + cutime = current->signal->cutime; + cstime = current->signal->cstime; + spin_unlock_irq(¤t->sighand->siglock); + tms->tms_utime = cputime_to_clock_t(cputime.utime); + tms->tms_stime = cputime_to_clock_t(cputime.stime); + tms->tms_cutime = cputime_to_clock_t(cutime); + tms->tms_cstime = cputime_to_clock_t(cstime); +} + asmlinkage long sys_times(struct tms __user * tbuf) { - /* - * In the SMP world we might just be unlucky and have one of - * the times increment as we use it. Since the value is an - * atomically safe type this is just fine. Conceptually its - * as if the syscall took an instant longer to occur. - */ if (tbuf) { struct tms tmp; - struct task_struct *tsk = current; - struct task_struct *t; - cputime_t utime, stime, cutime, cstime; - - spin_lock_irq(&tsk->sighand->siglock); - utime = tsk->signal->utime; - stime = tsk->signal->stime; - t = tsk; - do { - utime = cputime_add(utime, t->utime); - stime = cputime_add(stime, t->stime); - t = next_thread(t); - } while (t != tsk); - - cutime = tsk->signal->cutime; - cstime = tsk->signal->cstime; - spin_unlock_irq(&tsk->sighand->siglock); - - tmp.tms_utime = cputime_to_clock_t(utime); - tmp.tms_stime = cputime_to_clock_t(stime); - tmp.tms_cutime = cputime_to_clock_t(cutime); - tmp.tms_cstime = cputime_to_clock_t(cstime); + + do_sys_times(&tmp); if (copy_to_user(tbuf, &tmp, sizeof(struct tms))) return -EFAULT; } @@ -1449,7 +1439,6 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim) { struct rlimit new_rlim, *old_rlim; - unsigned long it_prof_secs; int retval; if (resource >= RLIM_NLIMITS) @@ -1503,18 +1492,7 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim) if (new_rlim.rlim_cur == RLIM_INFINITY) goto out; - it_prof_secs = cputime_to_secs(current->signal->it_prof_expires); - if (it_prof_secs == 0 || new_rlim.rlim_cur <= it_prof_secs) { - unsigned long rlim_cur = new_rlim.rlim_cur; - cputime_t cputime; - - cputime = secs_to_cputime(rlim_cur); - read_lock(&tasklist_lock); - spin_lock_irq(¤t->sighand->siglock); - set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL); - spin_unlock_irq(¤t->sighand->siglock); - read_unlock(&tasklist_lock); - } + update_rlimit_cpu(new_rlim.rlim_cur); out: return 0; } @@ -1552,11 +1530,8 @@ out: * */ -static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r, - cputime_t *utimep, cputime_t *stimep) +static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r) { - *utimep = cputime_add(*utimep, t->utime); - *stimep = cputime_add(*stimep, t->stime); r->ru_nvcsw += t->nvcsw; r->ru_nivcsw += t->nivcsw; r->ru_minflt += t->min_flt; @@ -1570,12 +1545,13 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) struct task_struct *t; unsigned long flags; cputime_t utime, stime; + struct task_cputime cputime; memset((char *) r, 0, sizeof *r); utime = stime = cputime_zero; if (who == RUSAGE_THREAD) { - accumulate_thread_rusage(p, r, &utime, &stime); + accumulate_thread_rusage(p, r); goto out; } @@ -1598,8 +1574,9 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) break; case RUSAGE_SELF: - utime = cputime_add(utime, p->signal->utime); - stime = cputime_add(stime, p->signal->stime); + thread_group_cputime(p, &cputime); + utime = cputime_add(utime, cputime.utime); + stime = cputime_add(stime, cputime.stime); r->ru_nvcsw += p->signal->nvcsw; r->ru_nivcsw += p->signal->nivcsw; r->ru_minflt += p->signal->min_flt; @@ -1608,7 +1585,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r) r->ru_oublock += p->signal->oublock; t = p; do { - accumulate_thread_rusage(t, r, &utime, &stime); + accumulate_thread_rusage(t, r); t = next_thread(t); } while (t != p); break; @@ -1739,6 +1716,16 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, case PR_SET_TSC: error = SET_TSC_CTL(arg2); break; + case PR_GET_TIMERSLACK: + error = current->timer_slack_ns; + break; + case PR_SET_TIMERSLACK: + if (arg2 <= 0) + current->timer_slack_ns = + current->default_timer_slack_ns; + else + current->timer_slack_ns = arg2; + break; default: error = -EINVAL; break; diff --git a/kernel/time.c b/kernel/time.c index 6a08660b4fac..d63a4336fad6 100644 --- a/kernel/time.c +++ b/kernel/time.c @@ -669,3 +669,21 @@ EXPORT_SYMBOL(get_jiffies_64); #endif EXPORT_SYMBOL(jiffies); + +/* + * Add two timespec values and do a safety check for overflow. + * It's assumed that both values are valid (>= 0) + */ +struct timespec timespec_add_safe(const struct timespec lhs, + const struct timespec rhs) +{ + struct timespec res; + + set_normalized_timespec(&res, lhs.tv_sec + rhs.tv_sec, + lhs.tv_nsec + rhs.tv_nsec); + + if (res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec) + res.tv_sec = TIME_T_MAX; + + return res; +} diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 093d4acf993b..9ed2eec97526 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -325,6 +325,9 @@ int clocksource_register(struct clocksource *c) unsigned long flags; int ret; + /* save mult_orig on registration */ + c->mult_orig = c->mult; + spin_lock_irqsave(&clocksource_lock, flags); ret = clocksource_enqueue(c); if (!ret) diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index 4c256fdb8875..1ca99557e929 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -61,6 +61,7 @@ struct clocksource clocksource_jiffies = { .read = jiffies_read, .mask = 0xffffffff, /*32bits*/ .mult = NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */ + .mult_orig = NSEC_PER_JIFFY << JIFFIES_SHIFT, .shift = JIFFIES_SHIFT, }; diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 1ad46f3df6e7..8ff15e5d486b 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -10,13 +10,13 @@ #include <linux/mm.h> #include <linux/time.h> -#include <linux/timer.h> #include <linux/timex.h> #include <linux/jiffies.h> #include <linux/hrtimer.h> #include <linux/capability.h> #include <linux/math64.h> #include <linux/clocksource.h> +#include <linux/workqueue.h> #include <asm/timex.h> /* @@ -142,8 +142,7 @@ static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer) time_state = TIME_OOP; printk(KERN_NOTICE "Clock: " "inserting leap second 23:59:60 UTC\n"); - leap_timer.expires = ktime_add_ns(leap_timer.expires, - NSEC_PER_SEC); + hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC); res = HRTIMER_RESTART; break; case TIME_DEL: @@ -218,11 +217,11 @@ void second_overflow(void) /* Disable the cmos update - used by virtualization and embedded */ int no_sync_cmos_clock __read_mostly; -static void sync_cmos_clock(unsigned long dummy); +static void sync_cmos_clock(struct work_struct *work); -static DEFINE_TIMER(sync_cmos_timer, sync_cmos_clock, 0, 0); +static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock); -static void sync_cmos_clock(unsigned long dummy) +static void sync_cmos_clock(struct work_struct *work) { struct timespec now, next; int fail = 1; @@ -258,13 +257,13 @@ static void sync_cmos_clock(unsigned long dummy) next.tv_sec++; next.tv_nsec -= NSEC_PER_SEC; } - mod_timer(&sync_cmos_timer, jiffies + timespec_to_jiffies(&next)); + schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next)); } static void notify_cmos_timer(void) { if (!no_sync_cmos_clock) - mod_timer(&sync_cmos_timer, jiffies + 1); + schedule_delayed_work(&sync_cmos_work, 0); } #else @@ -277,38 +276,50 @@ static inline void notify_cmos_timer(void) { } int do_adjtimex(struct timex *txc) { struct timespec ts; - long save_adjust, sec; int result; - /* In order to modify anything, you gotta be super-user! */ - if (txc->modes && !capable(CAP_SYS_TIME)) - return -EPERM; - - /* Now we validate the data before disabling interrupts */ - - if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) { + /* Validate the data before disabling interrupts */ + if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ - if (txc->modes & ~ADJ_OFFSET_SS_READ) + if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) return -EINVAL; + if (!(txc->modes & ADJ_OFFSET_READONLY) && + !capable(CAP_SYS_TIME)) + return -EPERM; + } else { + /* In order to modify anything, you gotta be super-user! */ + if (txc->modes && !capable(CAP_SYS_TIME)) + return -EPERM; + + /* if the quartz is off by more than 10% something is VERY wrong! */ + if (txc->modes & ADJ_TICK && + (txc->tick < 900000/USER_HZ || + txc->tick > 1100000/USER_HZ)) + return -EINVAL; + + if (txc->modes & ADJ_STATUS && time_state != TIME_OK) + hrtimer_cancel(&leap_timer); } - /* if the quartz is off by more than 10% something is VERY wrong ! */ - if (txc->modes & ADJ_TICK) - if (txc->tick < 900000/USER_HZ || - txc->tick > 1100000/USER_HZ) - return -EINVAL; - - if (time_state != TIME_OK && txc->modes & ADJ_STATUS) - hrtimer_cancel(&leap_timer); getnstimeofday(&ts); write_seqlock_irq(&xtime_lock); - /* Save for later - semantics of adjtime is to return old value */ - save_adjust = time_adjust; - /* If there are input parameters, then process them */ + if (txc->modes & ADJ_ADJTIME) { + long save_adjust = time_adjust; + + if (!(txc->modes & ADJ_OFFSET_READONLY)) { + /* adjtime() is independent from ntp_adjtime() */ + time_adjust = txc->offset; + ntp_update_frequency(); + } + txc->offset = save_adjust; + goto adj_done; + } if (txc->modes) { + long sec; + if (txc->modes & ADJ_STATUS) { if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { @@ -375,13 +386,8 @@ int do_adjtimex(struct timex *txc) if (txc->modes & ADJ_TAI && txc->constant > 0) time_tai = txc->constant; - if (txc->modes & ADJ_OFFSET) { - if (txc->modes == ADJ_OFFSET_SINGLESHOT) - /* adjtime() is independent from ntp_adjtime() */ - time_adjust = txc->offset; - else - ntp_update_offset(txc->offset); - } + if (txc->modes & ADJ_OFFSET) + ntp_update_offset(txc->offset); if (txc->modes & ADJ_TICK) tick_usec = txc->tick; @@ -389,22 +395,18 @@ int do_adjtimex(struct timex *txc) ntp_update_frequency(); } + txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, + NTP_SCALE_SHIFT); + if (!(time_status & STA_NANO)) + txc->offset /= NSEC_PER_USEC; + +adj_done: result = time_state; /* mostly `TIME_OK' */ if (time_status & (STA_UNSYNC|STA_CLOCKERR)) result = TIME_ERROR; - if ((txc->modes == ADJ_OFFSET_SINGLESHOT) || - (txc->modes == ADJ_OFFSET_SS_READ)) - txc->offset = save_adjust; - else { - txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, - NTP_SCALE_SHIFT); - if (!(time_status & STA_NANO)) - txc->offset /= NSEC_PER_USEC; - } - txc->freq = shift_right((s32)(time_freq >> PPM_SCALE_INV_SHIFT) * - (s64)PPM_SCALE_INV, - NTP_SCALE_SHIFT); + txc->freq = shift_right((time_freq >> PPM_SCALE_INV_SHIFT) * + (s64)PPM_SCALE_INV, NTP_SCALE_SHIFT); txc->maxerror = time_maxerror; txc->esterror = time_esterror; txc->status = time_status; diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index b711ffcb106c..a547be11cf97 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -300,7 +300,7 @@ void tick_nohz_stop_sched_tick(int inidle) goto out; } - ts->idle_tick = ts->sched_timer.expires; + ts->idle_tick = hrtimer_get_expires(&ts->sched_timer); ts->tick_stopped = 1; ts->idle_jiffies = last_jiffies; rcu_enter_nohz(); @@ -431,21 +431,21 @@ void tick_nohz_restart_sched_tick(void) ts->tick_stopped = 0; ts->idle_exittime = now; hrtimer_cancel(&ts->sched_timer); - ts->sched_timer.expires = ts->idle_tick; + hrtimer_set_expires(&ts->sched_timer, ts->idle_tick); while (1) { /* Forward the time to expire in the future */ hrtimer_forward(&ts->sched_timer, now, tick_period); if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { - hrtimer_start(&ts->sched_timer, - ts->sched_timer.expires, + hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS); /* Check, if the timer was already in the past */ if (hrtimer_active(&ts->sched_timer)) break; } else { - if (!tick_program_event(ts->sched_timer.expires, 0)) + if (!tick_program_event( + hrtimer_get_expires(&ts->sched_timer), 0)) break; } /* Update jiffies and reread time */ @@ -458,7 +458,7 @@ void tick_nohz_restart_sched_tick(void) static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now) { hrtimer_forward(&ts->sched_timer, now, tick_period); - return tick_program_event(ts->sched_timer.expires, 0); + return tick_program_event(hrtimer_get_expires(&ts->sched_timer), 0); } /* @@ -541,7 +541,7 @@ static void tick_nohz_switch_to_nohz(void) next = tick_init_jiffy_update(); for (;;) { - ts->sched_timer.expires = next; + hrtimer_set_expires(&ts->sched_timer, next); if (!tick_program_event(next, 0)) break; next = ktime_add(next, tick_period); @@ -637,16 +637,15 @@ void tick_setup_sched_timer(void) ts->sched_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU; /* Get the next period (per cpu) */ - ts->sched_timer.expires = tick_init_jiffy_update(); + hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update()); offset = ktime_to_ns(tick_period) >> 1; do_div(offset, num_possible_cpus()); offset *= smp_processor_id(); - ts->sched_timer.expires = ktime_add_ns(ts->sched_timer.expires, offset); + hrtimer_add_expires_ns(&ts->sched_timer, offset); for (;;) { hrtimer_forward(&ts->sched_timer, now, tick_period); - hrtimer_start(&ts->sched_timer, ts->sched_timer.expires, - HRTIMER_MODE_ABS); + hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS); /* Check, if the timer was already in the past */ if (hrtimer_active(&ts->sched_timer)) break; diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index e91c29f961c9..e7acfb482a68 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -58,27 +58,26 @@ struct clocksource *clock; #ifdef CONFIG_GENERIC_TIME /** - * __get_nsec_offset - Returns nanoseconds since last call to periodic_hook + * clocksource_forward_now - update clock to the current time * - * private function, must hold xtime_lock lock when being - * called. Returns the number of nanoseconds since the - * last call to update_wall_time() (adjusted by NTP scaling) + * 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 inline s64 __get_nsec_offset(void) +static void clocksource_forward_now(void) { cycle_t cycle_now, cycle_delta; - s64 ns_offset; + s64 nsec; - /* read clocksource: */ cycle_now = clocksource_read(clock); - - /* calculate the delta since the last update_wall_time: */ cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + clock->cycle_last = cycle_now; - /* convert to nanoseconds: */ - ns_offset = cyc2ns(clock, cycle_delta); + nsec = cyc2ns(clock, cycle_delta); + timespec_add_ns(&xtime, nsec); - return ns_offset; + nsec = ((s64)cycle_delta * clock->mult_orig) >> clock->shift; + clock->raw_time.tv_nsec += nsec; } /** @@ -89,6 +88,7 @@ static inline s64 __get_nsec_offset(void) */ void getnstimeofday(struct timespec *ts) { + cycle_t cycle_now, cycle_delta; unsigned long seq; s64 nsecs; @@ -96,7 +96,15 @@ void getnstimeofday(struct timespec *ts) seq = read_seqbegin(&xtime_lock); *ts = xtime; - nsecs = __get_nsec_offset(); + + /* read clocksource: */ + cycle_now = clocksource_read(clock); + + /* calculate the delta since the last update_wall_time: */ + cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + + /* convert to nanoseconds: */ + nsecs = cyc2ns(clock, cycle_delta); } while (read_seqretry(&xtime_lock, seq)); @@ -129,22 +137,22 @@ EXPORT_SYMBOL(do_gettimeofday); */ int do_settimeofday(struct timespec *tv) { + struct timespec ts_delta; unsigned long flags; - time_t wtm_sec, sec = tv->tv_sec; - long wtm_nsec, nsec = tv->tv_nsec; if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) return -EINVAL; write_seqlock_irqsave(&xtime_lock, flags); - nsec -= __get_nsec_offset(); + clocksource_forward_now(); + + ts_delta.tv_sec = tv->tv_sec - xtime.tv_sec; + ts_delta.tv_nsec = tv->tv_nsec - xtime.tv_nsec; + wall_to_monotonic = timespec_sub(wall_to_monotonic, ts_delta); - wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); - wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); + xtime = *tv; - set_normalized_timespec(&xtime, sec, nsec); - set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); update_xtime_cache(0); clock->error = 0; @@ -170,22 +178,19 @@ EXPORT_SYMBOL(do_settimeofday); static void change_clocksource(void) { struct clocksource *new; - cycle_t now; - u64 nsec; new = clocksource_get_next(); if (clock == new) return; - new->cycle_last = 0; - now = clocksource_read(new); - nsec = __get_nsec_offset(); - timespec_add_ns(&xtime, nsec); + clocksource_forward_now(); - clock = new; - clock->cycle_last = now; + new->raw_time = clock->raw_time; + clock = new; + clock->cycle_last = 0; + clock->cycle_last = clocksource_read(new); clock->error = 0; clock->xtime_nsec = 0; clocksource_calculate_interval(clock, NTP_INTERVAL_LENGTH); @@ -200,11 +205,44 @@ static void change_clocksource(void) */ } #else +static inline void clocksource_forward_now(void) { } static inline void change_clocksource(void) { } -static inline s64 __get_nsec_offset(void) { return 0; } #endif /** + * getrawmonotonic - Returns the raw monotonic time in a timespec + * @ts: pointer to the timespec to be set + * + * Returns the raw monotonic time (completely un-modified by ntp) + */ +void getrawmonotonic(struct timespec *ts) +{ + unsigned long seq; + s64 nsecs; + cycle_t cycle_now, cycle_delta; + + do { + seq = read_seqbegin(&xtime_lock); + + /* read clocksource: */ + cycle_now = clocksource_read(clock); + + /* calculate the delta since the last update_wall_time: */ + cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; + + /* convert to nanoseconds: */ + nsecs = ((s64)cycle_delta * clock->mult_orig) >> clock->shift; + + *ts = clock->raw_time; + + } while (read_seqretry(&xtime_lock, seq)); + + timespec_add_ns(ts, nsecs); +} +EXPORT_SYMBOL(getrawmonotonic); + + +/** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres */ int timekeeping_valid_for_hres(void) @@ -265,8 +303,6 @@ void __init timekeeping_init(void) static int timekeeping_suspended; /* time in seconds when suspend began */ static unsigned long timekeeping_suspend_time; -/* xtime offset when we went into suspend */ -static s64 timekeeping_suspend_nsecs; /** * timekeeping_resume - Resumes the generic timekeeping subsystem. @@ -292,8 +328,6 @@ static int timekeeping_resume(struct sys_device *dev) wall_to_monotonic.tv_sec -= sleep_length; total_sleep_time += sleep_length; } - /* Make sure that we have the correct xtime reference */ - timespec_add_ns(&xtime, timekeeping_suspend_nsecs); update_xtime_cache(0); /* re-base the last cycle value */ clock->cycle_last = 0; @@ -319,8 +353,7 @@ static int timekeeping_suspend(struct sys_device *dev, pm_message_t state) timekeeping_suspend_time = read_persistent_clock(); write_seqlock_irqsave(&xtime_lock, flags); - /* Get the current xtime offset */ - timekeeping_suspend_nsecs = __get_nsec_offset(); + clocksource_forward_now(); timekeeping_suspended = 1; write_sequnlock_irqrestore(&xtime_lock, flags); @@ -454,23 +487,29 @@ void update_wall_time(void) #else offset = clock->cycle_interval; #endif - clock->xtime_nsec += (s64)xtime.tv_nsec << clock->shift; + clock->xtime_nsec = (s64)xtime.tv_nsec << clock->shift; /* normally this loop will run just once, however in the * case of lost or late ticks, it will accumulate correctly. */ while (offset >= clock->cycle_interval) { /* accumulate one interval */ - clock->xtime_nsec += clock->xtime_interval; - clock->cycle_last += clock->cycle_interval; offset -= clock->cycle_interval; + clock->cycle_last += clock->cycle_interval; + clock->xtime_nsec += clock->xtime_interval; if (clock->xtime_nsec >= (u64)NSEC_PER_SEC << clock->shift) { clock->xtime_nsec -= (u64)NSEC_PER_SEC << clock->shift; xtime.tv_sec++; second_overflow(); } + clock->raw_time.tv_nsec += clock->raw_interval; + if (clock->raw_time.tv_nsec >= NSEC_PER_SEC) { + clock->raw_time.tv_nsec -= NSEC_PER_SEC; + clock->raw_time.tv_sec++; + } + /* accumulate error between NTP and clock interval */ clock->error += tick_length; clock->error -= clock->xtime_interval << (NTP_SCALE_SHIFT - clock->shift); @@ -479,9 +518,12 @@ void update_wall_time(void) /* correct the clock when NTP error is too big */ clocksource_adjust(offset); - /* store full nanoseconds into xtime */ - xtime.tv_nsec = (s64)clock->xtime_nsec >> clock->shift; + /* store full nanoseconds into xtime after rounding it up and + * add the remainder to the error difference. + */ + xtime.tv_nsec = ((s64)clock->xtime_nsec >> clock->shift) + 1; clock->xtime_nsec -= (s64)xtime.tv_nsec << clock->shift; + clock->error += clock->xtime_nsec << (NTP_SCALE_SHIFT - clock->shift); update_xtime_cache(cyc2ns(clock, offset)); diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index a40e20fd0001..122ee751d2d1 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -65,9 +65,11 @@ print_timer(struct seq_file *m, struct hrtimer *timer, int idx, u64 now) SEQ_printf(m, ", %s/%d", tmp, timer->start_pid); #endif SEQ_printf(m, "\n"); - SEQ_printf(m, " # expires at %Lu nsecs [in %Ld nsecs]\n", - (unsigned long long)ktime_to_ns(timer->expires), - (long long)(ktime_to_ns(timer->expires) - now)); + SEQ_printf(m, " # expires at %Lu-%Lu nsecs [in %Ld to %Ld nsecs]\n", + (unsigned long long)ktime_to_ns(hrtimer_get_softexpires(timer)), + (unsigned long long)ktime_to_ns(hrtimer_get_expires(timer)), + (long long)(ktime_to_ns(hrtimer_get_softexpires(timer)) - now), + (long long)(ktime_to_ns(hrtimer_get_expires(timer)) - now)); } static void diff --git a/kernel/timer.c b/kernel/timer.c index 510fe69351ca..56becf373c58 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1436,9 +1436,11 @@ static void __cpuinit migrate_timers(int cpu) BUG_ON(cpu_online(cpu)); old_base = per_cpu(tvec_bases, cpu); new_base = get_cpu_var(tvec_bases); - - local_irq_disable(); - spin_lock(&new_base->lock); + /* + * The caller is globally serialized and nobody else + * takes two locks at once, deadlock is not possible. + */ + spin_lock_irq(&new_base->lock); spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING); BUG_ON(old_base->running_timer); @@ -1453,8 +1455,7 @@ static void __cpuinit migrate_timers(int cpu) } spin_unlock(&old_base->lock); - spin_unlock(&new_base->lock); - local_irq_enable(); + spin_unlock_irq(&new_base->lock); put_cpu_var(tvec_bases); } #endif /* CONFIG_HOTPLUG_CPU */ diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 8b06fa900482..03e389e8d945 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -545,9 +545,10 @@ static void cbq_ovl_delay(struct cbq_class *cl) expires = ktime_set(0, 0); expires = ktime_add_ns(expires, PSCHED_US2NS(sched)); if (hrtimer_try_to_cancel(&q->delay_timer) && - ktime_to_ns(ktime_sub(q->delay_timer.expires, - expires)) > 0) - q->delay_timer.expires = expires; + ktime_to_ns(ktime_sub( + hrtimer_get_expires(&q->delay_timer), + expires)) > 0) + hrtimer_set_expires(&q->delay_timer, expires); hrtimer_restart(&q->delay_timer); cl->delayed = 1; cl->xstats.overactions++; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 576e51199079..3e3fde7c1d2b 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -75,6 +75,7 @@ #include <linux/string.h> #include <linux/selinux.h> #include <linux/mutex.h> +#include <linux/posix-timers.h> #include "avc.h" #include "objsec.h" @@ -2322,13 +2323,7 @@ static void selinux_bprm_post_apply_creds(struct linux_binprm *bprm) initrlim = init_task.signal->rlim+i; rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur); } - if (current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) { - /* - * This will cause RLIMIT_CPU calculations - * to be refigured. - */ - current->it_prof_expires = jiffies_to_cputime(1); - } + update_rlimit_cpu(rlim->rlim_cur); } /* Wake up the parent if it is waiting so that it can diff --git a/sound/drivers/pcsp/pcsp_lib.c b/sound/drivers/pcsp/pcsp_lib.c index e341f3f83b6a..1f42e4063118 100644 --- a/sound/drivers/pcsp/pcsp_lib.c +++ b/sound/drivers/pcsp/pcsp_lib.c @@ -34,7 +34,7 @@ enum hrtimer_restart pcsp_do_timer(struct hrtimer *handle) chip->thalf = 0; if (!atomic_read(&chip->timer_active)) return HRTIMER_NORESTART; - hrtimer_forward(&chip->timer, chip->timer.expires, + hrtimer_forward(&chip->timer, hrtimer_get_expires(&chip->timer), ktime_set(0, chip->ns_rem)); return HRTIMER_RESTART; } @@ -118,7 +118,8 @@ enum hrtimer_restart pcsp_do_timer(struct hrtimer *handle) chip->ns_rem = PCSP_PERIOD_NS(); ns = (chip->thalf ? PCSP_CALC_NS(timer_cnt) : chip->ns_rem); chip->ns_rem -= ns; - hrtimer_forward(&chip->timer, chip->timer.expires, ktime_set(0, ns)); + hrtimer_forward(&chip->timer, hrtimer_get_expires(&chip->timer), + ktime_set(0, ns)); return HRTIMER_RESTART; exit_nr_unlock2: |