Force this on for -next/mm testing purposes.

[linux-2.6/next.git] / fs / select.c

/*
 * This file contains the procedures for the handling of select and poll
 *
 * Created for Linux based loosely upon Mathius Lattner's minix
 * patches by Peter MacDonald. Heavily edited by Linus.
 *
 *  4 February 1994
 *     COFF/ELF binary emulation. If the process has the STICKY_TIMEOUTS
 *     flag set in its personality we do *not* modify the given timeout
 *     parameter to reflect time remaining.
 *
 *  24 January 2000
 *     Changed sys_poll()/do_poll() to use PAGE_SIZE chunk-based allocation 
 *     of fds to overcome nfds < 16390 descriptors limit (Tigran Aivazian).
 */

#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/syscalls.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/personality.h> /* for STICKY_TIMEOUTS */
#include <linux/file.h>
#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..
 */

#define MAX_SLACK       (100 * NSEC_PER_MSEC)

static long __estimate_accuracy(struct timespec *tv)
{
        long slack;
        int divfactor = 1000;

        if (tv->tv_sec < 0)
                return 0;

        if (task_nice(current) > 0)
                divfactor = divfactor / 5;

        if (tv->tv_sec > MAX_SLACK / (NSEC_PER_SEC/divfactor))
                return MAX_SLACK;

        slack = tv->tv_nsec / divfactor;
        slack += tv->tv_sec * (NSEC_PER_SEC/divfactor);

        if (slack > MAX_SLACK)
                return MAX_SLACK;

        return slack;
}

long select_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;
        struct poll_table_entry entries[0];
};

#define POLL_TABLE_FULL(table) \
        ((unsigned long)((table)->entry+1) > PAGE_SIZE + (unsigned long)(table))

/*
 * Ok, Peter made a complicated, but straightforward multiple_wait() function.
 * I have rewritten this, taking some shortcuts: This code may not be easy to
 * follow, but it should be free of race-conditions, and it's practical. If you
 * understand what I'm doing here, then you understand how the linux
 * sleep/wakeup mechanism works.
 *
 * Two very simple procedures, poll_wait() and poll_freewait() make all the
 * work.  poll_wait() is an inline-function defined in <linux/poll.h>,
 * as all select/poll functions have to call it to add an entry to the
 * poll table.
 */
static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
                       poll_table *p);

void poll_initwait(struct poll_wqueues *pwq)
{
        init_poll_funcptr(&pwq->pt, __pollwait);
        pwq->polling_task = current;
        pwq->triggered = 0;
        pwq->error = 0;
        pwq->table = NULL;
        pwq->inline_index = 0;
}
EXPORT_SYMBOL(poll_initwait);

static void free_poll_entry(struct poll_table_entry *entry)
{
        remove_wait_queue(entry->wait_address, &entry->wait);
        fput(entry->filp);
}

void poll_freewait(struct poll_wqueues *pwq)
{
        struct poll_table_page * p = pwq->table;
        int i;
        for (i = 0; i < pwq->inline_index; i++)
                free_poll_entry(pwq->inline_entries + i);
        while (p) {
                struct poll_table_entry * entry;
                struct poll_table_page *old;

                entry = p->entry;
                do {
                        entry--;
                        free_poll_entry(entry);
                } while (entry > p->entries);
                old = p;
                p = p->next;
                free_page((unsigned long) old);
        }
}
EXPORT_SYMBOL(poll_freewait);

static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p)
{
        struct poll_table_page *table = p->table;

        if (p->inline_index < N_INLINE_POLL_ENTRIES)
                return p->inline_entries + p->inline_index++;

        if (!table || POLL_TABLE_FULL(table)) {
                struct poll_table_page *new_table;

                new_table = (struct poll_table_page *) __get_free_page(GFP_KERNEL);
                if (!new_table) {
                        p->error = -ENOMEM;
                        return NULL;
                }
                new_table->entry = new_table->entries;
                new_table->next = table;
                p->table = new_table;
                table = new_table;
        }

        return table->entry++;
}

static int __pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
        struct poll_wqueues *pwq = wait->private;
        DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task);

        /*
         * Although this function is called under waitqueue lock, LOCK
         * doesn't imply write barrier and the users expect write
         * barrier semantics on wakeup functions.  The following
         * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
         * and is paired with set_mb() in poll_schedule_timeout.
         */
        smp_wmb();
        pwq->triggered = 1;

        /*
         * Perform the default wake up operation using a dummy
         * waitqueue.
         *
         * TODO: This is hacky but there currently is no interface to
         * pass in @sync.  @sync is scheduled to be removed and once
         * that happens, wake_up_process() can be used directly.
         */
        return default_wake_function(&dummy_wait, mode, sync, key);
}

static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
        struct poll_table_entry *entry;

        entry = container_of(wait, struct poll_table_entry, wait);
        if (key && !((unsigned long)key & entry->key))
                return 0;
        return __pollwake(wait, mode, sync, key);
}

/* Add a new entry */
static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
                                poll_table *p)
{
        struct poll_wqueues *pwq = container_of(p, struct poll_wqueues, pt);
        struct poll_table_entry *entry = poll_get_entry(pwq);
        if (!entry)
                return;
        get_file(filp);
        entry->filp = filp;
        entry->wait_address = wait_address;
        entry->key = p->key;
        init_waitqueue_func_entry(&entry->wait, pollwake);
        entry->wait.private = pwq;
        add_wait_queue(wait_address, &entry->wait);
}

int poll_schedule_timeout(struct poll_wqueues *pwq, int state,
                          ktime_t *expires, unsigned long slack)
{
        int rc = -EINTR;

        set_current_state(state);
        if (!pwq->triggered)
                rc = schedule_hrtimeout_range(expires, slack, HRTIMER_MODE_ABS);
        __set_current_state(TASK_RUNNING);

        /*
         * Prepare for the next iteration.
         *
         * The following set_mb() serves two purposes.  First, it's
         * the counterpart rmb of the wmb in pollwake() such that data
         * written before wake up is always visible after wake up.
         * Second, the full barrier guarantees that triggered clearing
         * doesn't pass event check of the next iteration.  Note that
         * this problem doesn't exist for the first iteration as
         * add_wait_queue() has full barrier semantics.
         */
        set_mb(pwq->triggered, 0);

        return rc;
}
EXPORT_SYMBOL(poll_schedule_timeout);

/**
 * 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) {
                if (sizeof(rtv) > sizeof(rtv.tv_sec) + sizeof(rtv.tv_usec))
                        memset(&rtv, 0, sizeof(rtv));
                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)

#define BITS(fds, n)    (*FDS_IN(fds, n)|*FDS_OUT(fds, n)|*FDS_EX(fds, n))

static int max_select_fd(unsigned long n, fd_set_bits *fds)
{
        unsigned long *open_fds;
        unsigned long set;
        int max;
        struct fdtable *fdt;

        /* handle last in-complete long-word first */
        set = ~(~0UL << (n & (__NFDBITS-1)));
        n /= __NFDBITS;
        fdt = files_fdtable(current->files);
        open_fds = fdt->open_fds->fds_bits+n;
        max = 0;
        if (set) {
                set &= BITS(fds, n);
                if (set) {
                        if (!(set & ~*open_fds))
                                goto get_max;
                        return -EBADF;
                }
        }
        while (n) {
                open_fds--;
                n--;
                set = BITS(fds, n);
                if (!set)
                        continue;
                if (set & ~*open_fds)
                        return -EBADF;
                if (max)
                        continue;
get_max:
                do {
                        max++;
                        set >>= 1;
                } while (set);
                max += n * __NFDBITS;
        }

        return max;
}

#define POLLIN_SET (POLLRDNORM | POLLRDBAND | POLLIN | POLLHUP | POLLERR)
#define POLLOUT_SET (POLLWRBAND | POLLWRNORM | POLLOUT | POLLERR)
#define POLLEX_SET (POLLPRI)

static inline void wait_key_set(poll_table *wait, unsigned long in,
                                unsigned long out, unsigned long bit)
{
        if (wait) {
                wait->key = POLLEX_SET;
                if (in & bit)
                        wait->key |= POLLIN_SET;
                if (out & bit)
                        wait->key |= POLLOUT_SET;
        }
}

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, timed_out = 0;
        unsigned long slack = 0;

        rcu_read_lock();
        retval = max_select_fd(n, fds);
        rcu_read_unlock();

        if (retval < 0)
                return retval;
        n = retval;

        poll_initwait(&table);
        wait = &table.pt;
        if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
                wait = NULL;
                timed_out = 1;
        }

        if (end_time && !timed_out)
                slack = select_estimate_accuracy(end_time);

        retval = 0;
        for (;;) {
                unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp;

                inp = fds->in; outp = fds->out; exp = fds->ex;
                rinp = fds->res_in; routp = fds->res_out; rexp = fds->res_ex;

                for (i = 0; i < n; ++rinp, ++routp, ++rexp) {
                        unsigned long in, out, ex, all_bits, bit = 1, mask, j;
                        unsigned long res_in = 0, res_out = 0, res_ex = 0;
                        const struct file_operations *f_op = NULL;
                        struct file *file = NULL;

                        in = *inp++; out = *outp++; ex = *exp++;
                        all_bits = in | out | ex;
                        if (all_bits == 0) {
                                i += __NFDBITS;
                                continue;
                        }

                        for (j = 0; j < __NFDBITS; ++j, ++i, bit <<= 1) {
                                int fput_needed;
                                if (i >= n)
                                        break;
                                if (!(bit & all_bits))
                                        continue;
                                file = fget_light(i, &fput_needed);
                                if (file) {
                                        f_op = file->f_op;
                                        mask = DEFAULT_POLLMASK;
                                        if (f_op && f_op->poll) {
                                                wait_key_set(wait, in, out, bit);
                                                mask = (*f_op->poll)(file, wait);
                                        }
                                        fput_light(file, fput_needed);
                                        if ((mask & POLLIN_SET) && (in & bit)) {
                                                res_in |= bit;
                                                retval++;
                                                wait = NULL;
                                        }
                                        if ((mask & POLLOUT_SET) && (out & bit)) {
                                                res_out |= bit;
                                                retval++;
                                                wait = NULL;
                                        }
                                        if ((mask & POLLEX_SET) && (ex & bit)) {
                                                res_ex |= bit;
                                                retval++;
                                                wait = NULL;
                                        }
                                }
                        }
                        if (res_in)
                                *rinp = res_in;
                        if (res_out)
                                *routp = res_out;
                        if (res_ex)
                                *rexp = res_ex;
                        cond_resched();
                }
                wait = NULL;
                if (retval || timed_out || signal_pending(current))
                        break;
                if (table.error) {
                        retval = table.error;
                        break;
                }

                /*
                 * 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;
                }

                if (!poll_schedule_timeout(&table, TASK_INTERRUPTIBLE,
                                           to, slack))
                        timed_out = 1;
        }

        poll_freewait(&table);

        return retval;
}

/*
 * We can actually return ERESTARTSYS instead of EINTR, but I'd
 * like to be certain this leads to no problems. So I return
 * EINTR just for safety.
 *
 * Update: ERESTARTSYS breaks at least the xview clock binary, so
 * I'm trying ERESTARTNOHAND which restart only when you want to.
 */
int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
                           fd_set __user *exp, struct timespec *end_time)
{
        fd_set_bits fds;
        void *bits;
        int ret, max_fds;
        unsigned int size;
        struct fdtable *fdt;
        /* Allocate small arguments on the stack to save memory and be faster */
        long stack_fds[SELECT_STACK_ALLOC/sizeof(long)];

        ret = -EINVAL;
        if (n < 0)
                goto out_nofds;

        /* max_fds can increase, so grab it once to avoid race */
        rcu_read_lock();
        fdt = files_fdtable(current->files);
        max_fds = fdt->max_fds;
        rcu_read_unlock();
        if (n > max_fds)
                n = max_fds;

        /*
         * We need 6 bitmaps (in/out/ex for both incoming and outgoing),
         * since we used fdset we need to allocate memory in units of
         * long-words. 
         */
        size = FDS_BYTES(n);
        bits = stack_fds;
        if (size > sizeof(stack_fds) / 6) {
                /* Not enough space in on-stack array; must use kmalloc */
                ret = -ENOMEM;
                bits = kmalloc(6 * size, GFP_KERNEL);
                if (!bits)
                        goto out_nofds;
        }
        fds.in      = bits;
        fds.out     = bits +   size;
        fds.ex      = bits + 2*size;
        fds.res_in  = bits + 3*size;
        fds.res_out = bits + 4*size;
        fds.res_ex  = bits + 5*size;

        if ((ret = get_fd_set(n, inp, fds.in)) ||
            (ret = get_fd_set(n, outp, fds.out)) ||
            (ret = get_fd_set(n, exp, fds.ex)))
                goto out;
        zero_fd_set(n, fds.res_in);
        zero_fd_set(n, fds.res_out);
        zero_fd_set(n, fds.res_ex);

        ret = do_select(n, &fds, end_time);

        if (ret < 0)
                goto out;
        if (!ret) {
                ret = -ERESTARTNOHAND;
                if (signal_pending(current))
                        goto out;
                ret = 0;
        }

        if (set_fd_set(n, inp, fds.res_in) ||
            set_fd_set(n, outp, fds.res_out) ||
            set_fd_set(n, exp, fds.res_ex))
                ret = -EFAULT;

out:
        if (bits != stack_fds)
                kfree(bits);
out_nofds:
        return ret;
}

SYSCALL_DEFINE5(select, int, n, fd_set __user *, inp, fd_set __user *, outp,
                fd_set __user *, exp, struct timeval __user *, tvp)
{
        struct timespec end_time, *to = NULL;
        struct timeval tv;
        int ret;

        if (tvp) {
                if (copy_from_user(&tv, tvp, sizeof(tv)))
                        return -EFAULT;

                to = &end_time;
                if (poll_select_set_timeout(to,
                                tv.tv_sec + (tv.tv_usec / USEC_PER_SEC),
                                (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC))
                        return -EINVAL;
        }

        ret = core_sys_select(n, inp, outp, exp, to);
        ret = poll_select_copy_remaining(&end_time, tvp, 1, ret);

        return ret;
}

#ifdef HAVE_SET_RESTORE_SIGMASK
static long do_pselect(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)
{
        sigset_t ksigmask, sigsaved;
        struct timespec ts, end_time, *to = NULL;
        int ret;

        if (tsp) {
                if (copy_from_user(&ts, tsp, sizeof(ts)))
                        return -EFAULT;

                to = &end_time;
                if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
                        return -EINVAL;
        }

        if (sigmask) {
                /* XXX: Don't preclude handling different sized sigset_t's.  */
                if (sigsetsize != sizeof(sigset_t))
                        return -EINVAL;
                if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
                        return -EFAULT;

                sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
                sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
        }

        ret = core_sys_select(n, inp, outp, exp, to);
        ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);

        if (ret == -ERESTARTNOHAND) {
                /*
                 * Don't restore the signal mask yet. Let do_signal() deliver
                 * the signal on the way back to userspace, before the signal
                 * mask is restored.
                 */
                if (sigmask) {
                        memcpy(&current->saved_sigmask, &sigsaved,
                                        sizeof(sigsaved));
                        set_restore_sigmask();
                }
        } else if (sigmask)
                sigprocmask(SIG_SETMASK, &sigsaved, NULL);

        return ret;
}

/*
 * Most architectures can't handle 7-argument syscalls. So we provide a
 * 6-argument version where the sixth argument is a pointer to a structure
 * which has a pointer to the sigset_t itself followed by a size_t containing
 * the sigset size.
 */
SYSCALL_DEFINE6(pselect6, int, n, fd_set __user *, inp, fd_set __user *, outp,
                fd_set __user *, exp, struct timespec __user *, tsp,
                void __user *, sig)
{
        size_t sigsetsize = 0;
        sigset_t __user *up = NULL;

        if (sig) {
                if (!access_ok(VERIFY_READ, sig, sizeof(void *)+sizeof(size_t))
                    || __get_user(up, (sigset_t __user * __user *)sig)
                    || __get_user(sigsetsize,
                                (size_t __user *)(sig+sizeof(void *))))
                        return -EFAULT;
        }

        return do_pselect(n, inp, outp, exp, tsp, up, sigsetsize);
}
#endif /* HAVE_SET_RESTORE_SIGMASK */

#ifdef __ARCH_WANT_SYS_OLD_SELECT
struct sel_arg_struct {
        unsigned long n;
        fd_set __user *inp, *outp, *exp;
        struct timeval __user *tvp;
};

SYSCALL_DEFINE1(old_select, struct sel_arg_struct __user *, arg)
{
        struct sel_arg_struct a;

        if (copy_from_user(&a, arg, sizeof(a)))
                return -EFAULT;
        return sys_select(a.n, a.inp, a.outp, a.exp, a.tvp);
}
#endif

struct poll_list {
        struct poll_list *next;
        int len;
        struct pollfd entries[0];
};

#define POLLFD_PER_PAGE  ((PAGE_SIZE-sizeof(struct poll_list)) / sizeof(struct pollfd))

/*
 * Fish for pollable events on the pollfd->fd file descriptor. We're only
 * interested in events matching the pollfd->events mask, and the result
 * matching that mask is both recorded in pollfd->revents and returned. The
 * pwait poll_table will be used by the fd-provided poll handler for waiting,
 * if non-NULL.
 */
static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait)
{
        unsigned int mask;
        int fd;

        mask = 0;
        fd = pollfd->fd;
        if (fd >= 0) {
                int fput_needed;
                struct file * file;

                file = fget_light(fd, &fput_needed);
                mask = POLLNVAL;
                if (file != NULL) {
                        mask = DEFAULT_POLLMASK;
                        if (file->f_op && file->f_op->poll) {
                                if (pwait)
                                        pwait->key = pollfd->events |
                                                        POLLERR | POLLHUP;
                                mask = file->f_op->poll(file, pwait);
                        }
                        /* Mask out unneeded events. */
                        mask &= pollfd->events | POLLERR | POLLHUP;
                        fput_light(file, fput_needed);
                }
        }
        pollfd->revents = mask;

        return mask;
}

static int do_poll(unsigned int nfds,  struct poll_list *list,
                   struct poll_wqueues *wait, struct timespec *end_time)
{
        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) {
                pt = NULL;
                timed_out = 1;
        }

        if (end_time && !timed_out)
                slack = select_estimate_accuracy(end_time);

        for (;;) {
                struct poll_list *walk;

                for (walk = list; walk != NULL; walk = walk->next) {
                        struct pollfd * pfd, * pfd_end;

                        pfd = walk->entries;
                        pfd_end = pfd + walk->len;
                        for (; pfd != pfd_end; pfd++) {
                                /*
                                 * Fish for events. If we found one, record it
                                 * and kill the poll_table, so we don't
                                 * needlessly register any other waiters after
                                 * this. They'll get immediately deregistered
                                 * when we break out and return.
                                 */
                                if (do_pollfd(pfd, pt)) {
                                        count++;
                                        pt = NULL;
                                }
                        }
                }
                /*
                 * All waiters have already been registered, so don't provide
                 * a poll_table to them on the next loop iteration.
                 */
                pt = NULL;
                if (!count) {
                        count = wait->error;
                        if (signal_pending(current))
                                count = -EINTR;
                }
                if (count || timed_out)
                        break;

                /*
                 * 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;
                }

                if (!poll_schedule_timeout(wait, TASK_INTERRUPTIBLE, to, slack))
                        timed_out = 1;
        }
        return count;
}

#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,
                struct timespec *end_time)
{
        struct poll_wqueues table;
        int err = -EFAULT, fdcount, len, size;
        /* Allocate small arguments on the stack to save memory and be
           faster - use long to make sure the buffer is aligned properly
           on 64 bit archs to avoid unaligned access */
        long stack_pps[POLL_STACK_ALLOC/sizeof(long)];
        struct poll_list *const head = (struct poll_list *)stack_pps;
        struct poll_list *walk = head;
        unsigned long todo = nfds;

        if (nfds > rlimit(RLIMIT_NOFILE))
                return -EINVAL;

        len = min_t(unsigned int, nfds, N_STACK_PPS);
        for (;;) {
                walk->next = NULL;
                walk->len = len;
                if (!len)
                        break;

                if (copy_from_user(walk->entries, ufds + nfds-todo,
                                        sizeof(struct pollfd) * walk->len))
                        goto out_fds;

                todo -= walk->len;
                if (!todo)
                        break;

                len = min(todo, POLLFD_PER_PAGE);
                size = sizeof(struct poll_list) + sizeof(struct pollfd) * len;
                walk = walk->next = kmalloc(size, GFP_KERNEL);
                if (!walk) {
                        err = -ENOMEM;
                        goto out_fds;
                }
        }

        poll_initwait(&table);
        fdcount = do_poll(nfds, head, &table, end_time);
        poll_freewait(&table);

        for (walk = head; walk; walk = walk->next) {
                struct pollfd *fds = walk->entries;
                int j;

                for (j = 0; j < walk->len; j++, ufds++)
                        if (__put_user(fds[j].revents, &ufds->revents))
                                goto out_fds;
        }

        err = fdcount;
out_fds:
        walk = head->next;
        while (walk) {
                struct poll_list *pos = walk;
                walk = walk->next;
                kfree(pos);
        }

        return err;
}

static long do_restart_poll(struct restart_block *restart_block)
{
        struct pollfd __user *ufds = restart_block->poll.ufds;
        int nfds = restart_block->poll.nfds;
        struct timespec *to = NULL, end_time;
        int ret;

        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;
                ret = -ERESTART_RESTARTBLOCK;
        }
        return ret;
}

SYSCALL_DEFINE3(poll, struct pollfd __user *, ufds, unsigned int, nfds,
                long, timeout_msecs)
{
        struct timespec end_time, *to = NULL;
        int ret;

        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, to);

        if (ret == -EINTR) {
                struct restart_block *restart_block;

                restart_block = &current_thread_info()->restart_block;
                restart_block->fn = do_restart_poll;
                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;
}

#ifdef HAVE_SET_RESTORE_SIGMASK
SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds,
                struct timespec __user *, tsp, const sigset_t __user *, sigmask,
                size_t, sigsetsize)
{
        sigset_t ksigmask, sigsaved;
        struct timespec ts, end_time, *to = NULL;
        int ret;

        if (tsp) {
                if (copy_from_user(&ts, tsp, sizeof(ts)))
                        return -EFAULT;

                to = &end_time;
                if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
                        return -EINVAL;
        }

        if (sigmask) {
                /* XXX: Don't preclude handling different sized sigset_t's.  */
                if (sigsetsize != sizeof(sigset_t))
                        return -EINVAL;
                if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
                        return -EFAULT;

                sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
                sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
        }

        ret = do_sys_poll(ufds, nfds, to);

        /* We can restart this syscall, usually */
        if (ret == -EINTR) {
                /*
                 * Don't restore the signal mask yet. Let do_signal() deliver
                 * the signal on the way back to userspace, before the signal
                 * mask is restored.
                 */
                if (sigmask) {
                        memcpy(&current->saved_sigmask, &sigsaved,
                                        sizeof(sigsaved));
                        set_restore_sigmask();
                }
                ret = -ERESTARTNOHAND;
        } else if (sigmask)
                sigprocmask(SIG_SETMASK, &sigsaved, NULL);

        ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);

        return ret;
}
#endif /* HAVE_SET_RESTORE_SIGMASK */