From b773ad40aca5bd755ba886620842f16e8fef6d75 Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sun, 31 Aug 2008 08:16:57 -0700 Subject: select: add poll_select_set_timeout() and poll_select_copy_remaining() helpers This patch adds 2 helpers that will be used for the hrtimer based select/poll: poll_select_set_timeout() is a helper that takes a timeout (as a second, nanosecond pair) and turns that into a "struct timespec" that represents the absolute end time. This is a common operation in the many select() and poll() variants and needs various, common, sanity checks. poll_select_copy_remaining() is a helper that takes care of copying the remaining time to userspace, as select(), pselect() and ppoll() do. This function comes in both a natural and a compat implementation (due to datastructure differences). Signed-off-by: Thomas Gleixner Signed-off-by: Arjan van de Ven --- fs/compat.c | 51 +++++++++++++++++++++++++++++++++++++++++ fs/select.c | 75 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 126 insertions(+) (limited to 'fs') diff --git a/fs/compat.c b/fs/compat.c index 075d0509970..424767c954a 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1436,6 +1436,57 @@ 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. diff --git a/fs/select.c b/fs/select.c index da0e88201c3..1180a620778 100644 --- a/fs/select.c +++ b/fs/select.c @@ -130,6 +130,81 @@ 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) -- cgit v1.2.3-70-g09d2 From 8ff3e8e85fa6c312051134b3953e397feb639f51 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Sun, 31 Aug 2008 08:26:40 -0700 Subject: select: switch select() and poll() over to hrtimers With lots of help, input and cleanups from Thomas Gleixner This patch switches select() and poll() over to hrtimers. The core of the patch is replacing the "s64 timeout" with a "struct timespec end_time" in all the plumbing. But most of the diffstat comes from using the just introduced helpers: poll_select_set_timeout poll_select_copy_remaining timespec_add_safe which make manipulating the timespec easier and less error-prone. Signed-off-by: Arjan van de Ven Signed-off-by: Thomas Gleixner --- fs/compat.c | 136 ++++---------------------- fs/select.c | 263 +++++++++++++++++---------------------------------- include/linux/poll.h | 6 +- 3 files changed, 111 insertions(+), 294 deletions(-) (limited to 'fs') diff --git a/fs/compat.c b/fs/compat.c index 424767c954a..133ed7f5d68 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1568,7 +1568,8 @@ 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; @@ -1615,7 +1616,7 @@ 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; @@ -1641,7 +1642,7 @@ 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; @@ -1649,43 +1650,14 @@ 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; } @@ -1698,15 +1670,16 @@ 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; } @@ -1721,51 +1694,8 @@ 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) { /* @@ -1810,18 +1740,16 @@ 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) { @@ -1835,7 +1763,7 @@ 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) { @@ -1853,31 +1781,7 @@ 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/select.c b/fs/select.c index 1180a620778..f6dceb56793 100644 --- a/fs/select.c +++ b/fs/select.c @@ -24,6 +24,7 @@ #include #include #include +#include #include @@ -203,8 +204,6 @@ sticky: 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) @@ -257,11 +256,12 @@ 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; rcu_read_lock(); retval = max_select_fd(n, fds); @@ -273,12 +273,14 @@ 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; + } + retval = 0; for (;;) { unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp; - long __timeout; set_current_state(TASK_INTERRUPTIBLE); @@ -334,27 +336,25 @@ 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(to, HRTIMER_MODE_ABS)) + timed_out = 1; } __set_current_state(TASK_RUNNING); @@ -375,7 +375,7 @@ 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; @@ -426,7 +426,7 @@ 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; @@ -452,7 +452,7 @@ 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; @@ -460,43 +460,14 @@ 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; } @@ -506,25 +477,17 @@ 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) { @@ -538,32 +501,8 @@ 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) { /* @@ -649,18 +588,20 @@ 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; /* Optimise the no-wait case */ - if (!(*timeout)) + if (end_time && !end_time->tv_sec && !end_time->tv_nsec) { pt = NULL; + timed_out = 1; + } for (;;) { struct poll_list *walk; - long __timeout; set_current_state(TASK_INTERRUPTIBLE); for (walk = list; walk != NULL; walk = walk->next) { @@ -692,27 +633,21 @@ 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(to, HRTIMER_MODE_ABS)) + timed_out = 1; } __set_current_state(TASK_RUNNING); return count; @@ -721,7 +656,8 @@ 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; @@ -761,7 +697,7 @@ 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) { @@ -787,16 +723,21 @@ 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; @@ -805,31 +746,32 @@ 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; @@ -841,21 +783,16 @@ 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) { @@ -869,7 +806,7 @@ 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) { @@ -887,31 +824,7 @@ 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/include/linux/poll.h b/include/linux/poll.h index f65de5128a9..badd98ab06f 100644 --- a/include/linux/poll.h +++ b/include/linux/poll.h @@ -114,11 +114,11 @@ 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); -- cgit v1.2.3-70-g09d2 From 76369470b7e5f97fc1a8af83c45b9ff739b08cb6 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Mon, 1 Sep 2008 15:00:14 -0700 Subject: hrtimer: convert timerfd to the new hrtimer apis In order to be able to do range hrtimers we need to use accessor functions to the "expire" member of the hrtimer struct. This patch converts timerfd to these accessors. Signed-off-by: Arjan van de Ven --- fs/timerfd.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/timerfd.c b/fs/timerfd.c index c502c60e4f5..0862f0e49d0 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); -- cgit v1.2.3-70-g09d2 From 90d6e24a3686325edea7748b966e138c9923017d Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Mon, 1 Sep 2008 15:55:35 -0700 Subject: hrtimer: make select() and poll() use the hrtimer range feature This patch makes the select() and poll() hrtimers use the new range feature and settings from the task struct. In addition, this includes the estimate_accuracy() function that Linus posted to lkml, but changed entirely based on other peoples lkml feedback. Signed-off-by: Arjan van de Ven --- fs/select.c | 64 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 62 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/select.c b/fs/select.c index f6dceb56793..5e61b43d076 100644 --- a/fs/select.c +++ b/fs/select.c @@ -28,6 +28,58 @@ #include + +/* + * 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 unsigned long __estimate_accuracy(struct timespec *tv) +{ + unsigned long slack; + int divfactor = 1000; + + if (task_nice(current)) + 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; + return slack; +} + +static unsigned long estimate_accuracy(struct timespec *tv) +{ + unsigned long ret; + struct timespec now; + + /* + * Realtime tasks get a slack of 0 for obvious reasons. + */ + + if (current->policy == SCHED_FIFO || + current->policy == SCHED_RR) + 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; @@ -262,6 +314,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) struct poll_wqueues table; poll_table *wait; int retval, i, timed_out = 0; + unsigned long slack = 0; rcu_read_lock(); retval = max_select_fd(n, fds); @@ -278,6 +331,9 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) timed_out = 1; } + if (end_time) + slack = estimate_accuracy(end_time); + retval = 0; for (;;) { unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp; @@ -353,7 +409,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) to = &expire; } - if (!schedule_hrtimeout(to, HRTIMER_MODE_ABS)) + if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) timed_out = 1; } __set_current_state(TASK_RUNNING); @@ -593,6 +649,7 @@ static int do_poll(unsigned int nfds, struct poll_list *list, 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 (end_time && !end_time->tv_sec && !end_time->tv_nsec) { @@ -600,6 +657,9 @@ static int do_poll(unsigned int nfds, struct poll_list *list, timed_out = 1; } + if (end_time) + slack = estimate_accuracy(end_time); + for (;;) { struct poll_list *walk; @@ -646,7 +706,7 @@ static int do_poll(unsigned int nfds, struct poll_list *list, to = &expire; } - if (!schedule_hrtimeout(to, HRTIMER_MODE_ABS)) + if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS)) timed_out = 1; } __set_current_state(TASK_RUNNING); -- cgit v1.2.3-70-g09d2 From 4ce105d30e08fb8a1783c55a0e48aa3fa200c455 Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Sun, 7 Sep 2008 15:31:39 -0700 Subject: hrtimer: incorporate feedback from Peter Zijlstra (based on lkml review) * use rt_task() * task_nice() has a sign Signed-off-by: Arjan van de Ven --- fs/select.c | 5 ++--- include/linux/hrtimer.h | 2 +- 2 files changed, 3 insertions(+), 4 deletions(-) (limited to 'fs') diff --git a/fs/select.c b/fs/select.c index 5e61b43d076..fdd8584e536 100644 --- a/fs/select.c +++ b/fs/select.c @@ -46,7 +46,7 @@ static unsigned long __estimate_accuracy(struct timespec *tv) unsigned long slack; int divfactor = 1000; - if (task_nice(current)) + if (task_nice(current) > 0) divfactor = divfactor / 5; slack = tv->tv_nsec / divfactor; @@ -66,8 +66,7 @@ static unsigned long estimate_accuracy(struct timespec *tv) * Realtime tasks get a slack of 0 for obvious reasons. */ - if (current->policy == SCHED_FIFO || - current->policy == SCHED_RR) + if (rt_task(current)) return 0; ktime_get_ts(&now); diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h index 1c0473e8ecb..95db11f62ff 100644 --- a/include/linux/hrtimer.h +++ b/include/linux/hrtimer.h @@ -363,7 +363,7 @@ static inline int hrtimer_start_expires(struct hrtimer *timer, soft = hrtimer_get_softexpires(timer); hard = hrtimer_get_expires(timer); delta = ktime_to_ns(ktime_sub(hard, soft)); - return hrtimer_start_range_ns(timer, hrtimer_get_expires(timer), delta, mode); + return hrtimer_start_range_ns(timer, soft, delta, mode); } static inline int hrtimer_restart(struct hrtimer *timer) -- cgit v1.2.3-70-g09d2 From 96d2ab484e7a9bafdab44b8c7d1ef5944319b18c Mon Sep 17 00:00:00 2001 From: Arjan van de Ven Date: Sun, 7 Sep 2008 16:08:55 -0700 Subject: hrtimer: fix signed/unsigned bug in slack estimator the slack estimator used unsigned math; however for very short delay it's possible that by the time you calculate the timeout, it's already passed and you get a negative time/slack... in an unsigned variable... which then gets turned into a 100 msec delay rather than zero. This patch fixes this by using a signed typee in the right places. Signed-off-by: Arjan van de Ven --- fs/select.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/select.c b/fs/select.c index fdd8584e536..448e4400128 100644 --- a/fs/select.c +++ b/fs/select.c @@ -41,9 +41,9 @@ * better solutions.. */ -static unsigned long __estimate_accuracy(struct timespec *tv) +static long __estimate_accuracy(struct timespec *tv) { - unsigned long slack; + long slack; int divfactor = 1000; if (task_nice(current) > 0) @@ -54,10 +54,13 @@ static unsigned long __estimate_accuracy(struct timespec *tv) if (slack > 100 * NSEC_PER_MSEC) slack = 100 * NSEC_PER_MSEC; + + if (slack < 0) + slack = 0; return slack; } -static unsigned long estimate_accuracy(struct timespec *tv) +static long estimate_accuracy(struct timespec *tv) { unsigned long ret; struct timespec now; @@ -330,7 +333,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec *end_time) timed_out = 1; } - if (end_time) + if (end_time && !timed_out) slack = estimate_accuracy(end_time); retval = 0; @@ -656,7 +659,7 @@ static int do_poll(unsigned int nfds, struct poll_list *list, timed_out = 1; } - if (end_time) + if (end_time && !timed_out) slack = estimate_accuracy(end_time); for (;;) { -- cgit v1.2.3-70-g09d2