2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* 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).
|
|
|
|
*/
|
|
|
|
|
2007-05-08 15:29:02 +08:00
|
|
|
#include <linux/kernel.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#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>
|
2008-04-24 19:44:08 +08:00
|
|
|
#include <linux/fdtable.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/fs.h>
|
2005-09-10 04:04:14 +08:00
|
|
|
#include <linux/rcupdate.h>
|
2008-08-31 23:26:40 +08:00
|
|
|
#include <linux/hrtimer.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
|
|
|
|
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.
|
|
|
|
*/
|
2005-05-06 07:16:09 +08:00
|
|
|
static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
|
|
|
|
poll_table *p);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
void poll_initwait(struct poll_wqueues *pwq)
|
|
|
|
{
|
|
|
|
init_poll_funcptr(&pwq->pt, __pollwait);
|
|
|
|
pwq->error = 0;
|
|
|
|
pwq->table = NULL;
|
2006-03-28 17:56:33 +08:00
|
|
|
pwq->inline_index = 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(poll_initwait);
|
|
|
|
|
2006-03-28 17:56:33 +08:00
|
|
|
static void free_poll_entry(struct poll_table_entry *entry)
|
|
|
|
{
|
2007-05-09 13:10:02 +08:00
|
|
|
remove_wait_queue(entry->wait_address, &entry->wait);
|
2006-03-28 17:56:33 +08:00
|
|
|
fput(entry->filp);
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
void poll_freewait(struct poll_wqueues *pwq)
|
|
|
|
{
|
|
|
|
struct poll_table_page * p = pwq->table;
|
2006-03-28 17:56:33 +08:00
|
|
|
int i;
|
|
|
|
for (i = 0; i < pwq->inline_index; i++)
|
|
|
|
free_poll_entry(pwq->inline_entries + i);
|
2005-04-17 06:20:36 +08:00
|
|
|
while (p) {
|
|
|
|
struct poll_table_entry * entry;
|
|
|
|
struct poll_table_page *old;
|
|
|
|
|
|
|
|
entry = p->entry;
|
|
|
|
do {
|
|
|
|
entry--;
|
2006-03-28 17:56:33 +08:00
|
|
|
free_poll_entry(entry);
|
2005-04-17 06:20:36 +08:00
|
|
|
} while (entry > p->entries);
|
|
|
|
old = p;
|
|
|
|
p = p->next;
|
|
|
|
free_page((unsigned long) old);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL(poll_freewait);
|
|
|
|
|
2006-03-28 17:56:33 +08:00
|
|
|
static struct poll_table_entry *poll_get_entry(poll_table *_p)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
struct poll_wqueues *p = container_of(_p, struct poll_wqueues, pt);
|
|
|
|
struct poll_table_page *table = p->table;
|
|
|
|
|
2006-03-28 17:56:33 +08:00
|
|
|
if (p->inline_index < N_INLINE_POLL_ENTRIES)
|
|
|
|
return p->inline_entries + p->inline_index++;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
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;
|
|
|
|
__set_current_state(TASK_RUNNING);
|
2006-03-28 17:56:33 +08:00
|
|
|
return NULL;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
new_table->entry = new_table->entries;
|
|
|
|
new_table->next = table;
|
|
|
|
p->table = new_table;
|
|
|
|
table = new_table;
|
|
|
|
}
|
|
|
|
|
2006-03-28 17:56:33 +08:00
|
|
|
return table->entry++;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Add a new entry */
|
|
|
|
static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
|
|
|
|
poll_table *p)
|
|
|
|
{
|
|
|
|
struct poll_table_entry *entry = poll_get_entry(p);
|
|
|
|
if (!entry)
|
|
|
|
return;
|
|
|
|
get_file(filp);
|
|
|
|
entry->filp = filp;
|
|
|
|
entry->wait_address = wait_address;
|
|
|
|
init_waitqueue_entry(&entry->wait, current);
|
2007-05-09 13:10:02 +08:00
|
|
|
add_wait_queue(wait_address, &entry->wait);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2008-08-31 23:16:57 +08:00
|
|
|
/**
|
|
|
|
* 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;
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#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;
|
2005-09-10 04:04:10 +08:00
|
|
|
struct fdtable *fdt;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* handle last in-complete long-word first */
|
|
|
|
set = ~(~0UL << (n & (__NFDBITS-1)));
|
|
|
|
n /= __NFDBITS;
|
2005-09-10 04:04:10 +08:00
|
|
|
fdt = files_fdtable(current->files);
|
|
|
|
open_fds = fdt->open_fds->fds_bits+n;
|
2005-04-17 06:20:36 +08:00
|
|
|
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)
|
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-08-31 23:26:40 +08:00
|
|
|
ktime_t expire, *to = NULL;
|
2005-04-17 06:20:36 +08:00
|
|
|
struct poll_wqueues table;
|
|
|
|
poll_table *wait;
|
2008-08-31 23:26:40 +08:00
|
|
|
int retval, i, timed_out = 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2005-09-10 04:04:14 +08:00
|
|
|
rcu_read_lock();
|
2005-04-17 06:20:36 +08:00
|
|
|
retval = max_select_fd(n, fds);
|
2005-09-10 04:04:14 +08:00
|
|
|
rcu_read_unlock();
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
if (retval < 0)
|
|
|
|
return retval;
|
|
|
|
n = retval;
|
|
|
|
|
|
|
|
poll_initwait(&table);
|
|
|
|
wait = &table.pt;
|
2008-08-31 23:26:40 +08:00
|
|
|
if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
|
2005-04-17 06:20:36 +08:00
|
|
|
wait = NULL;
|
2008-08-31 23:26:40 +08:00
|
|
|
timed_out = 1;
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
retval = 0;
|
|
|
|
for (;;) {
|
|
|
|
unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp;
|
|
|
|
|
|
|
|
set_current_state(TASK_INTERRUPTIBLE);
|
|
|
|
|
|
|
|
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;
|
2006-03-28 17:56:41 +08:00
|
|
|
const struct file_operations *f_op = NULL;
|
2005-04-17 06:20:36 +08:00
|
|
|
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) {
|
2006-03-28 17:56:34 +08:00
|
|
|
int fput_needed;
|
2005-04-17 06:20:36 +08:00
|
|
|
if (i >= n)
|
|
|
|
break;
|
|
|
|
if (!(bit & all_bits))
|
|
|
|
continue;
|
2006-03-28 17:56:34 +08:00
|
|
|
file = fget_light(i, &fput_needed);
|
2005-04-17 06:20:36 +08:00
|
|
|
if (file) {
|
|
|
|
f_op = file->f_op;
|
|
|
|
mask = DEFAULT_POLLMASK;
|
|
|
|
if (f_op && f_op->poll)
|
|
|
|
mask = (*f_op->poll)(file, retval ? NULL : wait);
|
2006-03-28 17:56:34 +08:00
|
|
|
fput_light(file, fput_needed);
|
2005-04-17 06:20:36 +08:00
|
|
|
if ((mask & POLLIN_SET) && (in & bit)) {
|
|
|
|
res_in |= bit;
|
|
|
|
retval++;
|
|
|
|
}
|
|
|
|
if ((mask & POLLOUT_SET) && (out & bit)) {
|
|
|
|
res_out |= bit;
|
|
|
|
retval++;
|
|
|
|
}
|
|
|
|
if ((mask & POLLEX_SET) && (ex & bit)) {
|
|
|
|
res_ex |= bit;
|
|
|
|
retval++;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (res_in)
|
|
|
|
*rinp = res_in;
|
|
|
|
if (res_out)
|
|
|
|
*routp = res_out;
|
|
|
|
if (res_ex)
|
|
|
|
*rexp = res_ex;
|
2008-06-23 03:23:15 +08:00
|
|
|
cond_resched();
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
wait = NULL;
|
2008-08-31 23:26:40 +08:00
|
|
|
if (retval || timed_out || signal_pending(current))
|
2005-04-17 06:20:36 +08:00
|
|
|
break;
|
2008-04-22 06:15:06 +08:00
|
|
|
if (table.error) {
|
2005-04-17 06:20:36 +08:00
|
|
|
retval = table.error;
|
|
|
|
break;
|
|
|
|
}
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
/*
|
|
|
|
* 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;
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
}
|
2008-08-31 23:26:40 +08:00
|
|
|
|
|
|
|
if (!schedule_hrtimeout(to, HRTIMER_MODE_ABS))
|
|
|
|
timed_out = 1;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
__set_current_state(TASK_RUNNING);
|
|
|
|
|
|
|
|
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.
|
|
|
|
*/
|
|
|
|
#define MAX_SELECT_SECONDS \
|
|
|
|
((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1)
|
|
|
|
|
2008-04-24 02:05:15 +08:00
|
|
|
int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
|
2008-08-31 23:26:40 +08:00
|
|
|
fd_set __user *exp, struct timespec *end_time)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
fd_set_bits fds;
|
2006-04-11 13:52:46 +08:00
|
|
|
void *bits;
|
2006-12-10 18:21:12 +08:00
|
|
|
int ret, max_fds;
|
2006-04-11 13:54:08 +08:00
|
|
|
unsigned int size;
|
2005-09-10 04:04:10 +08:00
|
|
|
struct fdtable *fdt;
|
2006-03-28 17:56:33 +08:00
|
|
|
/* Allocate small arguments on the stack to save memory and be faster */
|
2006-04-01 00:18:57 +08:00
|
|
|
long stack_fds[SELECT_STACK_ALLOC/sizeof(long)];
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
ret = -EINVAL;
|
|
|
|
if (n < 0)
|
|
|
|
goto out_nofds;
|
|
|
|
|
2006-12-10 18:21:12 +08:00
|
|
|
/* max_fds can increase, so grab it once to avoid race */
|
2005-09-10 04:04:14 +08:00
|
|
|
rcu_read_lock();
|
2005-09-10 04:04:10 +08:00
|
|
|
fdt = files_fdtable(current->files);
|
2006-12-10 18:21:12 +08:00
|
|
|
max_fds = fdt->max_fds;
|
2005-09-10 04:04:14 +08:00
|
|
|
rcu_read_unlock();
|
2006-12-10 18:21:12 +08:00
|
|
|
if (n > max_fds)
|
|
|
|
n = max_fds;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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);
|
2006-04-11 13:54:08 +08:00
|
|
|
bits = stack_fds;
|
|
|
|
if (size > sizeof(stack_fds) / 6) {
|
|
|
|
/* Not enough space in on-stack array; must use kmalloc */
|
|
|
|
ret = -ENOMEM;
|
2006-03-28 17:56:33 +08:00
|
|
|
bits = kmalloc(6 * size, GFP_KERNEL);
|
2006-04-11 13:54:08 +08:00
|
|
|
if (!bits)
|
|
|
|
goto out_nofds;
|
|
|
|
}
|
2006-04-11 13:52:46 +08:00
|
|
|
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;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
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);
|
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
ret = do_select(n, &fds, end_time);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
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:
|
2006-03-28 17:56:33 +08:00
|
|
|
if (bits != stack_fds)
|
|
|
|
kfree(bits);
|
2005-04-17 06:20:36 +08:00
|
|
|
out_nofds:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp,
|
|
|
|
fd_set __user *exp, struct timeval __user *tvp)
|
|
|
|
{
|
2008-08-31 23:26:40 +08:00
|
|
|
struct timespec end_time, *to = NULL;
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
struct timeval tv;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (tvp) {
|
|
|
|
if (copy_from_user(&tv, tvp, sizeof(tv)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
to = &end_time;
|
|
|
|
if (poll_select_set_timeout(to, tv.tv_sec,
|
|
|
|
tv.tv_usec * NSEC_PER_USEC))
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
ret = core_sys_select(n, inp, outp, exp, to);
|
|
|
|
ret = poll_select_copy_remaining(&end_time, tvp, 1, ret);
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2008-04-30 15:53:09 +08:00
|
|
|
#ifdef HAVE_SET_RESTORE_SIGMASK
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
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)
|
|
|
|
{
|
|
|
|
sigset_t ksigmask, sigsaved;
|
2008-08-31 23:26:40 +08:00
|
|
|
struct timespec ts, end_time, *to = NULL;
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (tsp) {
|
|
|
|
if (copy_from_user(&ts, tsp, sizeof(ts)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
to = &end_time;
|
|
|
|
if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
ret = core_sys_select(n, inp, outp, exp, &end_time);
|
|
|
|
ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
|
|
|
|
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(¤t->saved_sigmask, &sigsaved,
|
|
|
|
sizeof(sigsaved));
|
2008-04-30 15:53:06 +08:00
|
|
|
set_restore_sigmask();
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
}
|
|
|
|
} 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.
|
|
|
|
*/
|
|
|
|
asmlinkage long sys_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))
|
2006-02-01 18:26:09 +08:00
|
|
|
|| __get_user(up, (sigset_t __user * __user *)sig)
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
|| __get_user(sigsetsize,
|
2006-02-01 18:26:09 +08:00
|
|
|
(size_t __user *)(sig+sizeof(void *))))
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
return -EFAULT;
|
|
|
|
}
|
|
|
|
|
|
|
|
return sys_pselect7(n, inp, outp, exp, tsp, up, sigsetsize);
|
|
|
|
}
|
2008-04-30 15:53:09 +08:00
|
|
|
#endif /* HAVE_SET_RESTORE_SIGMASK */
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
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))
|
|
|
|
|
2006-06-23 17:05:16 +08:00
|
|
|
/*
|
|
|
|
* 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)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2006-06-23 17:05:16 +08:00
|
|
|
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)
|
|
|
|
mask = file->f_op->poll(file, pwait);
|
|
|
|
/* Mask out unneeded events. */
|
|
|
|
mask &= pollfd->events | POLLERR | POLLHUP;
|
|
|
|
fput_light(file, fput_needed);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
}
|
2006-06-23 17:05:16 +08:00
|
|
|
pollfd->revents = mask;
|
|
|
|
|
|
|
|
return mask;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int do_poll(unsigned int nfds, struct poll_list *list,
|
2008-08-31 23:26:40 +08:00
|
|
|
struct poll_wqueues *wait, struct timespec *end_time)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
poll_table* pt = &wait->pt;
|
2008-08-31 23:26:40 +08:00
|
|
|
ktime_t expire, *to = NULL;
|
|
|
|
int timed_out = 0, count = 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
/* Optimise the no-wait case */
|
2008-08-31 23:26:40 +08:00
|
|
|
if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
|
2005-04-17 06:20:36 +08:00
|
|
|
pt = NULL;
|
2008-08-31 23:26:40 +08:00
|
|
|
timed_out = 1;
|
|
|
|
}
|
2007-10-17 14:26:18 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
for (;;) {
|
|
|
|
struct poll_list *walk;
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
set_current_state(TASK_INTERRUPTIBLE);
|
2006-06-23 17:05:16 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2006-06-23 17:05:16 +08:00
|
|
|
/*
|
|
|
|
* All waiters have already been registered, so don't provide
|
|
|
|
* a poll_table to them on the next loop iteration.
|
|
|
|
*/
|
2005-04-17 06:20:36 +08:00
|
|
|
pt = NULL;
|
2007-10-17 14:26:18 +08:00
|
|
|
if (!count) {
|
|
|
|
count = wait->error;
|
|
|
|
if (signal_pending(current))
|
|
|
|
count = -EINTR;
|
|
|
|
}
|
2008-08-31 23:26:40 +08:00
|
|
|
if (count || timed_out)
|
2005-04-17 06:20:36 +08:00
|
|
|
break;
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
/*
|
|
|
|
* 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;
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
}
|
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
if (!schedule_hrtimeout(to, HRTIMER_MODE_ABS))
|
|
|
|
timed_out = 1;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
__set_current_state(TASK_RUNNING);
|
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
2006-03-28 17:56:33 +08:00
|
|
|
#define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list)) / \
|
|
|
|
sizeof(struct pollfd))
|
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
|
|
|
|
struct timespec *end_time)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
|
|
|
struct poll_wqueues table;
|
2007-10-17 14:26:17 +08:00
|
|
|
int err = -EFAULT, fdcount, len, size;
|
2006-04-01 00:18:57 +08:00
|
|
|
/* 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)];
|
2007-10-17 14:26:17 +08:00
|
|
|
struct poll_list *const head = (struct poll_list *)stack_pps;
|
|
|
|
struct poll_list *walk = head;
|
|
|
|
unsigned long todo = nfds;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
[PATCH] enforce RLIMIT_NOFILE in poll()
POSIX states that poll() shall fail with EINVAL if nfds > OPEN_MAX. In
this context, POSIX is referring to sysconf(OPEN_MAX), which is the value
of current->signal->rlim[RLIMIT_NOFILE].rlim_cur in the linux kernel, not
the compile-time constant which happens to also be named OPEN_MAX. In the
current code, an application may poll up to max_fdset file descriptors,
even if this exceeds RLIMIT_NOFILE. The current code also breaks
applications which poll more than max_fdset descriptors, which worked circa
2.4.18 when the check was against NR_OPEN, which is 1024*1024. This patch
enforces the limit precisely as POSIX defines, even if RLIMIT_NOFILE has
been changed at run time with ulimit -n.
To elaborate on the rationale for this, there are three cases:
1) RLIMIT_NOFILE is at the default value of 1024
In this (default) case, the patch changes nothing. Calls with nfds > 1024
fail with EINVAL both before and after the patch, and calls with nfds <=
1024 pass the check both before and after the patch, since 1024 is the
initial value of max_fdset.
2) RLIMIT_NOFILE has been raised above the default
In this case, poll() becomes more permissive, allowing polling up to
RLIMIT_NOFILE file descriptors even if less than 1024 have been opened.
The patch won't introduce new errors here. If an application somehow
depends on poll() failing when it polls with duplicate or invalid file
descriptors, it's already broken, since this is already allowed below 1024,
and will also work above 1024 if enough file descriptors have been open at
some point to cause max_fdset to have been increased above nfds.
3) RLIMIT_NOFILE has been lowered below the default
In this case, the system administrator or the user has gone out of their
way to protect the system from inefficient (or malicious) applications
wasting kernel memory. The current code allows polling up to 1024 file
descriptors even if RLIMIT_NOFILE is much lower, which is not what the user
or administrator intended. Well-written applications which only poll
valid, unique file descriptors will never notice the difference, because
they'll hit the limit on open() first. If an application gets broken
because of the patch in this case, then it was already poorly/maliciously
designed, and allowing it to work in the past was a violation of POSIX and
a DoS risk on low-resource systems.
With this patch, poll() will permit exactly what POSIX suggests, no more,
no less, and for any run-time value set with ulimit -n, not just 256 or
1024. There are existing apps which which poll a large number of file
descriptors, some of which may be invalid, and if those numbers stradle
1024, they currently fail with or without the patch in -mm, though they
worked fine under 2.4.18.
Signed-off-by: Chris Snook <csnook@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-29 17:01:33 +08:00
|
|
|
if (nfds > current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
|
2005-04-17 06:20:36 +08:00
|
|
|
return -EINVAL;
|
|
|
|
|
2007-10-17 14:26:17 +08:00
|
|
|
len = min_t(unsigned int, nfds, N_STACK_PPS);
|
|
|
|
for (;;) {
|
|
|
|
walk->next = NULL;
|
|
|
|
walk->len = len;
|
|
|
|
if (!len)
|
|
|
|
break;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-10-17 14:26:17 +08:00
|
|
|
if (copy_from_user(walk->entries, ufds + nfds-todo,
|
|
|
|
sizeof(struct pollfd) * walk->len))
|
|
|
|
goto out_fds;
|
|
|
|
|
|
|
|
todo -= walk->len;
|
|
|
|
if (!todo)
|
|
|
|
break;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-10-17 14:26:17 +08:00
|
|
|
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;
|
2005-04-17 06:20:36 +08:00
|
|
|
goto out_fds;
|
|
|
|
}
|
|
|
|
}
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
|
2007-10-17 14:26:17 +08:00
|
|
|
poll_initwait(&table);
|
2008-08-31 23:26:40 +08:00
|
|
|
fdcount = do_poll(nfds, head, &table, end_time);
|
2007-10-17 14:26:17 +08:00
|
|
|
poll_freewait(&table);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-10-17 14:26:17 +08:00
|
|
|
for (walk = head; walk; walk = walk->next) {
|
2005-04-17 06:20:36 +08:00
|
|
|
struct pollfd *fds = walk->entries;
|
|
|
|
int j;
|
|
|
|
|
2007-10-17 14:26:17 +08:00
|
|
|
for (j = 0; j < walk->len; j++, ufds++)
|
|
|
|
if (__put_user(fds[j].revents, &ufds->revents))
|
2005-04-17 06:20:36 +08:00
|
|
|
goto out_fds;
|
|
|
|
}
|
2007-10-17 14:26:17 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
err = fdcount;
|
|
|
|
out_fds:
|
2007-10-17 14:26:17 +08:00
|
|
|
walk = head->next;
|
|
|
|
while (walk) {
|
|
|
|
struct poll_list *pos = walk;
|
|
|
|
walk = walk->next;
|
|
|
|
kfree(pos);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
2007-10-17 14:26:17 +08:00
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
return err;
|
|
|
|
}
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
|
2007-10-17 14:27:18 +08:00
|
|
|
static long do_restart_poll(struct restart_block *restart_block)
|
|
|
|
{
|
2008-08-31 23:26:40 +08:00
|
|
|
struct pollfd __user *ufds = restart_block->poll.ufds;
|
|
|
|
int nfds = restart_block->poll.nfds;
|
|
|
|
struct timespec *to = NULL, end_time;
|
2007-10-17 14:27:18 +08:00
|
|
|
int ret;
|
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
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);
|
|
|
|
|
2007-10-17 14:27:18 +08:00
|
|
|
if (ret == -EINTR) {
|
|
|
|
restart_block->fn = do_restart_poll;
|
|
|
|
ret = -ERESTART_RESTARTBLOCK;
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds,
|
|
|
|
long timeout_msecs)
|
|
|
|
{
|
2008-08-31 23:26:40 +08:00
|
|
|
struct timespec end_time, *to = NULL;
|
2007-10-17 14:27:18 +08:00
|
|
|
int ret;
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
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));
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
}
|
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
ret = do_sys_poll(ufds, nfds, to);
|
|
|
|
|
2007-10-17 14:27:18 +08:00
|
|
|
if (ret == -EINTR) {
|
|
|
|
struct restart_block *restart_block;
|
2008-08-31 23:26:40 +08:00
|
|
|
|
2007-10-17 14:27:18 +08:00
|
|
|
restart_block = ¤t_thread_info()->restart_block;
|
|
|
|
restart_block->fn = do_restart_poll;
|
2008-08-31 23:26:40 +08:00
|
|
|
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;
|
|
|
|
|
2007-10-17 14:27:18 +08:00
|
|
|
ret = -ERESTART_RESTARTBLOCK;
|
|
|
|
}
|
|
|
|
return ret;
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
}
|
|
|
|
|
2008-04-30 15:53:09 +08:00
|
|
|
#ifdef HAVE_SET_RESTORE_SIGMASK
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds,
|
|
|
|
struct timespec __user *tsp, const sigset_t __user *sigmask,
|
|
|
|
size_t sigsetsize)
|
|
|
|
{
|
|
|
|
sigset_t ksigmask, sigsaved;
|
2008-08-31 23:26:40 +08:00
|
|
|
struct timespec ts, end_time, *to = NULL;
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (tsp) {
|
|
|
|
if (copy_from_user(&ts, tsp, sizeof(ts)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
to = &end_time;
|
|
|
|
if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
|
|
|
|
return -EINVAL;
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
ret = do_sys_poll(ufds, nfds, to);
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
|
|
|
|
/* 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(¤t->saved_sigmask, &sigsaved,
|
|
|
|
sizeof(sigsaved));
|
2008-04-30 15:53:06 +08:00
|
|
|
set_restore_sigmask();
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
}
|
|
|
|
ret = -ERESTARTNOHAND;
|
|
|
|
} else if (sigmask)
|
|
|
|
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
|
|
|
|
|
2008-08-31 23:26:40 +08:00
|
|
|
ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
|
[PATCH] Add pselect/ppoll system call implementation
The following implementation of ppoll() and pselect() system calls
depends on the architecture providing a TIF_RESTORE_SIGMASK flag in the
thread_info.
These system calls have to change the signal mask during their
operation, and signal handlers must be invoked using the new, temporary
signal mask. The old signal mask must be restored either upon successful
exit from the system call, or upon returning from the invoked signal
handler if the system call is interrupted. We can't simply restore the
original signal mask and return to userspace, since the restored signal
mask may actually block the signal which interrupted the system call.
The TIF_RESTORE_SIGMASK flag deals with this by causing the syscall exit
path to trap into do_signal() just as TIF_SIGPENDING does, and by
causing do_signal() to use the saved signal mask instead of the current
signal mask when setting up the stack frame for the signal handler -- or
by causing do_signal() to simply restore the saved signal mask in the
case where there is no handler to be invoked.
The first patch implements the sys_pselect() and sys_ppoll() system
calls, which are present only if TIF_RESTORE_SIGMASK is defined. That
#ifdef should go away in time when all architectures have implemented
it. The second patch implements TIF_RESTORE_SIGMASK for the PowerPC
kernel (in the -mm tree), and the third patch then removes the
arch-specific implementations of sys_rt_sigsuspend() and replaces them
with generic versions using the same trick.
The fourth and fifth patches, provided by David Howells, implement
TIF_RESTORE_SIGMASK for FR-V and i386 respectively, and the sixth patch
adds the syscalls to the i386 syscall table.
This patch:
Add the pselect() and ppoll() system calls, providing core routines usable by
the original select() and poll() system calls and also the new calls (with
their semantics w.r.t timeouts).
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-01-19 09:44:05 +08:00
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
2008-04-30 15:53:09 +08:00
|
|
|
#endif /* HAVE_SET_RESTORE_SIGMASK */
|