forked from Minki/linux
b835996f62
With the use of RCU in files structure, the look-up of files using fds can now be lock-free. The lookup is protected by rcu_read_lock()/rcu_read_unlock(). This patch changes the readers to use lock-free lookup. Signed-off-by: Maneesh Soni <maneesh@in.ibm.com> Signed-off-by: Ravikiran Thirumalai <kiran_th@gmail.com> Signed-off-by: Dipankar Sarma <dipankar@in.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
550 lines
12 KiB
C
550 lines
12 KiB
C
/*
|
|
* This file contains the procedures for the handling of select and poll
|
|
*
|
|
* Created for Linux based loosely upon Mathius Lattner's minix
|
|
* patches by Peter MacDonald. Heavily edited by Linus.
|
|
*
|
|
* 4 February 1994
|
|
* COFF/ELF binary emulation. If the process has the STICKY_TIMEOUTS
|
|
* flag set in its personality we do *not* modify the given timeout
|
|
* parameter to reflect time remaining.
|
|
*
|
|
* 24 January 2000
|
|
* Changed sys_poll()/do_poll() to use PAGE_SIZE chunk-based allocation
|
|
* of fds to overcome nfds < 16390 descriptors limit (Tigran Aivazian).
|
|
*/
|
|
|
|
#include <linux/syscalls.h>
|
|
#include <linux/module.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/smp_lock.h>
|
|
#include <linux/poll.h>
|
|
#include <linux/personality.h> /* for STICKY_TIMEOUTS */
|
|
#include <linux/file.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/rcupdate.h>
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
#define ROUND_UP(x,y) (((x)+(y)-1)/(y))
|
|
#define DEFAULT_POLLMASK (POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM)
|
|
|
|
struct poll_table_entry {
|
|
struct file * filp;
|
|
wait_queue_t wait;
|
|
wait_queue_head_t * wait_address;
|
|
};
|
|
|
|
struct poll_table_page {
|
|
struct poll_table_page * next;
|
|
struct poll_table_entry * entry;
|
|
struct poll_table_entry entries[0];
|
|
};
|
|
|
|
#define POLL_TABLE_FULL(table) \
|
|
((unsigned long)((table)->entry+1) > PAGE_SIZE + (unsigned long)(table))
|
|
|
|
/*
|
|
* Ok, Peter made a complicated, but straightforward multiple_wait() function.
|
|
* I have rewritten this, taking some shortcuts: This code may not be easy to
|
|
* follow, but it should be free of race-conditions, and it's practical. If you
|
|
* understand what I'm doing here, then you understand how the linux
|
|
* sleep/wakeup mechanism works.
|
|
*
|
|
* Two very simple procedures, poll_wait() and poll_freewait() make all the
|
|
* work. poll_wait() is an inline-function defined in <linux/poll.h>,
|
|
* as all select/poll functions have to call it to add an entry to the
|
|
* poll table.
|
|
*/
|
|
static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
|
|
poll_table *p);
|
|
|
|
void poll_initwait(struct poll_wqueues *pwq)
|
|
{
|
|
init_poll_funcptr(&pwq->pt, __pollwait);
|
|
pwq->error = 0;
|
|
pwq->table = NULL;
|
|
}
|
|
|
|
EXPORT_SYMBOL(poll_initwait);
|
|
|
|
void poll_freewait(struct poll_wqueues *pwq)
|
|
{
|
|
struct poll_table_page * p = pwq->table;
|
|
while (p) {
|
|
struct poll_table_entry * entry;
|
|
struct poll_table_page *old;
|
|
|
|
entry = p->entry;
|
|
do {
|
|
entry--;
|
|
remove_wait_queue(entry->wait_address,&entry->wait);
|
|
fput(entry->filp);
|
|
} while (entry > p->entries);
|
|
old = p;
|
|
p = p->next;
|
|
free_page((unsigned long) old);
|
|
}
|
|
}
|
|
|
|
EXPORT_SYMBOL(poll_freewait);
|
|
|
|
static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
|
|
poll_table *_p)
|
|
{
|
|
struct poll_wqueues *p = container_of(_p, struct poll_wqueues, pt);
|
|
struct poll_table_page *table = p->table;
|
|
|
|
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);
|
|
return;
|
|
}
|
|
new_table->entry = new_table->entries;
|
|
new_table->next = table;
|
|
p->table = new_table;
|
|
table = new_table;
|
|
}
|
|
|
|
/* Add a new entry */
|
|
{
|
|
struct poll_table_entry * entry = table->entry;
|
|
table->entry = entry+1;
|
|
get_file(filp);
|
|
entry->filp = filp;
|
|
entry->wait_address = wait_address;
|
|
init_waitqueue_entry(&entry->wait, current);
|
|
add_wait_queue(wait_address,&entry->wait);
|
|
}
|
|
}
|
|
|
|
#define FDS_IN(fds, n) (fds->in + n)
|
|
#define FDS_OUT(fds, n) (fds->out + n)
|
|
#define FDS_EX(fds, n) (fds->ex + n)
|
|
|
|
#define BITS(fds, n) (*FDS_IN(fds, n)|*FDS_OUT(fds, n)|*FDS_EX(fds, n))
|
|
|
|
static int max_select_fd(unsigned long n, fd_set_bits *fds)
|
|
{
|
|
unsigned long *open_fds;
|
|
unsigned long set;
|
|
int max;
|
|
struct fdtable *fdt;
|
|
|
|
/* handle last in-complete long-word first */
|
|
set = ~(~0UL << (n & (__NFDBITS-1)));
|
|
n /= __NFDBITS;
|
|
fdt = files_fdtable(current->files);
|
|
open_fds = fdt->open_fds->fds_bits+n;
|
|
max = 0;
|
|
if (set) {
|
|
set &= BITS(fds, n);
|
|
if (set) {
|
|
if (!(set & ~*open_fds))
|
|
goto get_max;
|
|
return -EBADF;
|
|
}
|
|
}
|
|
while (n) {
|
|
open_fds--;
|
|
n--;
|
|
set = BITS(fds, n);
|
|
if (!set)
|
|
continue;
|
|
if (set & ~*open_fds)
|
|
return -EBADF;
|
|
if (max)
|
|
continue;
|
|
get_max:
|
|
do {
|
|
max++;
|
|
set >>= 1;
|
|
} while (set);
|
|
max += n * __NFDBITS;
|
|
}
|
|
|
|
return max;
|
|
}
|
|
|
|
#define BIT(i) (1UL << ((i)&(__NFDBITS-1)))
|
|
#define MEM(i,m) ((m)+(unsigned)(i)/__NFDBITS)
|
|
#define ISSET(i,m) (((i)&*(m)) != 0)
|
|
#define SET(i,m) (*(m) |= (i))
|
|
|
|
#define POLLIN_SET (POLLRDNORM | POLLRDBAND | POLLIN | POLLHUP | POLLERR)
|
|
#define POLLOUT_SET (POLLWRBAND | POLLWRNORM | POLLOUT | POLLERR)
|
|
#define POLLEX_SET (POLLPRI)
|
|
|
|
int do_select(int n, fd_set_bits *fds, long *timeout)
|
|
{
|
|
struct poll_wqueues table;
|
|
poll_table *wait;
|
|
int retval, i;
|
|
long __timeout = *timeout;
|
|
|
|
rcu_read_lock();
|
|
retval = max_select_fd(n, fds);
|
|
rcu_read_unlock();
|
|
|
|
if (retval < 0)
|
|
return retval;
|
|
n = retval;
|
|
|
|
poll_initwait(&table);
|
|
wait = &table.pt;
|
|
if (!__timeout)
|
|
wait = NULL;
|
|
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;
|
|
struct file_operations *f_op = NULL;
|
|
struct file *file = NULL;
|
|
|
|
in = *inp++; out = *outp++; ex = *exp++;
|
|
all_bits = in | out | ex;
|
|
if (all_bits == 0) {
|
|
i += __NFDBITS;
|
|
continue;
|
|
}
|
|
|
|
for (j = 0; j < __NFDBITS; ++j, ++i, bit <<= 1) {
|
|
if (i >= n)
|
|
break;
|
|
if (!(bit & all_bits))
|
|
continue;
|
|
file = fget(i);
|
|
if (file) {
|
|
f_op = file->f_op;
|
|
mask = DEFAULT_POLLMASK;
|
|
if (f_op && f_op->poll)
|
|
mask = (*f_op->poll)(file, retval ? NULL : wait);
|
|
fput(file);
|
|
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++;
|
|
}
|
|
}
|
|
cond_resched();
|
|
}
|
|
if (res_in)
|
|
*rinp = res_in;
|
|
if (res_out)
|
|
*routp = res_out;
|
|
if (res_ex)
|
|
*rexp = res_ex;
|
|
}
|
|
wait = NULL;
|
|
if (retval || !__timeout || signal_pending(current))
|
|
break;
|
|
if(table.error) {
|
|
retval = table.error;
|
|
break;
|
|
}
|
|
__timeout = schedule_timeout(__timeout);
|
|
}
|
|
__set_current_state(TASK_RUNNING);
|
|
|
|
poll_freewait(&table);
|
|
|
|
/*
|
|
* Up-to-date the caller timeout.
|
|
*/
|
|
*timeout = __timeout;
|
|
return retval;
|
|
}
|
|
|
|
static void *select_bits_alloc(int size)
|
|
{
|
|
return kmalloc(6 * size, GFP_KERNEL);
|
|
}
|
|
|
|
static void select_bits_free(void *bits, int size)
|
|
{
|
|
kfree(bits);
|
|
}
|
|
|
|
/*
|
|
* 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)
|
|
|
|
asmlinkage long
|
|
sys_select(int n, fd_set __user *inp, fd_set __user *outp, fd_set __user *exp, struct timeval __user *tvp)
|
|
{
|
|
fd_set_bits fds;
|
|
char *bits;
|
|
long timeout;
|
|
int ret, size, max_fdset;
|
|
struct fdtable *fdt;
|
|
|
|
timeout = MAX_SCHEDULE_TIMEOUT;
|
|
if (tvp) {
|
|
time_t sec, usec;
|
|
|
|
if (!access_ok(VERIFY_READ, tvp, sizeof(*tvp))
|
|
|| __get_user(sec, &tvp->tv_sec)
|
|
|| __get_user(usec, &tvp->tv_usec)) {
|
|
ret = -EFAULT;
|
|
goto out_nofds;
|
|
}
|
|
|
|
ret = -EINVAL;
|
|
if (sec < 0 || usec < 0)
|
|
goto out_nofds;
|
|
|
|
if ((unsigned long) sec < MAX_SELECT_SECONDS) {
|
|
timeout = ROUND_UP(usec, 1000000/HZ);
|
|
timeout += sec * (unsigned long) HZ;
|
|
}
|
|
}
|
|
|
|
ret = -EINVAL;
|
|
if (n < 0)
|
|
goto out_nofds;
|
|
|
|
/* max_fdset can increase, so grab it once to avoid race */
|
|
rcu_read_lock();
|
|
fdt = files_fdtable(current->files);
|
|
max_fdset = fdt->max_fdset;
|
|
rcu_read_unlock();
|
|
if (n > max_fdset)
|
|
n = max_fdset;
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
ret = -ENOMEM;
|
|
size = FDS_BYTES(n);
|
|
bits = select_bits_alloc(size);
|
|
if (!bits)
|
|
goto out_nofds;
|
|
fds.in = (unsigned long *) bits;
|
|
fds.out = (unsigned long *) (bits + size);
|
|
fds.ex = (unsigned long *) (bits + 2*size);
|
|
fds.res_in = (unsigned long *) (bits + 3*size);
|
|
fds.res_out = (unsigned long *) (bits + 4*size);
|
|
fds.res_ex = (unsigned long *) (bits + 5*size);
|
|
|
|
if ((ret = get_fd_set(n, inp, fds.in)) ||
|
|
(ret = get_fd_set(n, outp, fds.out)) ||
|
|
(ret = get_fd_set(n, exp, fds.ex)))
|
|
goto out;
|
|
zero_fd_set(n, fds.res_in);
|
|
zero_fd_set(n, fds.res_out);
|
|
zero_fd_set(n, fds.res_ex);
|
|
|
|
ret = do_select(n, &fds, &timeout);
|
|
|
|
if (tvp && !(current->personality & STICKY_TIMEOUTS)) {
|
|
time_t sec = 0, usec = 0;
|
|
if (timeout) {
|
|
sec = timeout / HZ;
|
|
usec = timeout % HZ;
|
|
usec *= (1000000/HZ);
|
|
}
|
|
put_user(sec, &tvp->tv_sec);
|
|
put_user(usec, &tvp->tv_usec);
|
|
}
|
|
|
|
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:
|
|
select_bits_free(bits, size);
|
|
out_nofds:
|
|
return ret;
|
|
}
|
|
|
|
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))
|
|
|
|
static void do_pollfd(unsigned int num, struct pollfd * fdpage,
|
|
poll_table ** pwait, int *count)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < num; i++) {
|
|
int fd;
|
|
unsigned int mask;
|
|
struct pollfd *fdp;
|
|
|
|
mask = 0;
|
|
fdp = fdpage+i;
|
|
fd = fdp->fd;
|
|
if (fd >= 0) {
|
|
struct file * file = fget(fd);
|
|
mask = POLLNVAL;
|
|
if (file != NULL) {
|
|
mask = DEFAULT_POLLMASK;
|
|
if (file->f_op && file->f_op->poll)
|
|
mask = file->f_op->poll(file, *pwait);
|
|
mask &= fdp->events | POLLERR | POLLHUP;
|
|
fput(file);
|
|
}
|
|
if (mask) {
|
|
*pwait = NULL;
|
|
(*count)++;
|
|
}
|
|
}
|
|
fdp->revents = mask;
|
|
}
|
|
}
|
|
|
|
static int do_poll(unsigned int nfds, struct poll_list *list,
|
|
struct poll_wqueues *wait, long timeout)
|
|
{
|
|
int count = 0;
|
|
poll_table* pt = &wait->pt;
|
|
|
|
if (!timeout)
|
|
pt = NULL;
|
|
|
|
for (;;) {
|
|
struct poll_list *walk;
|
|
set_current_state(TASK_INTERRUPTIBLE);
|
|
walk = list;
|
|
while(walk != NULL) {
|
|
do_pollfd( walk->len, walk->entries, &pt, &count);
|
|
walk = walk->next;
|
|
}
|
|
pt = NULL;
|
|
if (count || !timeout || signal_pending(current))
|
|
break;
|
|
count = wait->error;
|
|
if (count)
|
|
break;
|
|
timeout = schedule_timeout(timeout);
|
|
}
|
|
__set_current_state(TASK_RUNNING);
|
|
return count;
|
|
}
|
|
|
|
asmlinkage long sys_poll(struct pollfd __user * ufds, unsigned int nfds, long timeout)
|
|
{
|
|
struct poll_wqueues table;
|
|
int fdcount, err;
|
|
unsigned int i;
|
|
struct poll_list *head;
|
|
struct poll_list *walk;
|
|
struct fdtable *fdt;
|
|
int max_fdset;
|
|
|
|
/* Do a sanity check on nfds ... */
|
|
rcu_read_lock();
|
|
fdt = files_fdtable(current->files);
|
|
max_fdset = fdt->max_fdset;
|
|
rcu_read_unlock();
|
|
if (nfds > max_fdset && nfds > OPEN_MAX)
|
|
return -EINVAL;
|
|
|
|
if (timeout) {
|
|
/* Careful about overflow in the intermediate values */
|
|
if ((unsigned long) timeout < MAX_SCHEDULE_TIMEOUT / HZ)
|
|
timeout = (unsigned long)(timeout*HZ+999)/1000+1;
|
|
else /* Negative or overflow */
|
|
timeout = MAX_SCHEDULE_TIMEOUT;
|
|
}
|
|
|
|
poll_initwait(&table);
|
|
|
|
head = NULL;
|
|
walk = NULL;
|
|
i = nfds;
|
|
err = -ENOMEM;
|
|
while(i!=0) {
|
|
struct poll_list *pp;
|
|
pp = kmalloc(sizeof(struct poll_list)+
|
|
sizeof(struct pollfd)*
|
|
(i>POLLFD_PER_PAGE?POLLFD_PER_PAGE:i),
|
|
GFP_KERNEL);
|
|
if(pp==NULL)
|
|
goto out_fds;
|
|
pp->next=NULL;
|
|
pp->len = (i>POLLFD_PER_PAGE?POLLFD_PER_PAGE:i);
|
|
if (head == NULL)
|
|
head = pp;
|
|
else
|
|
walk->next = pp;
|
|
|
|
walk = pp;
|
|
if (copy_from_user(pp->entries, ufds + nfds-i,
|
|
sizeof(struct pollfd)*pp->len)) {
|
|
err = -EFAULT;
|
|
goto out_fds;
|
|
}
|
|
i -= pp->len;
|
|
}
|
|
fdcount = do_poll(nfds, head, &table, timeout);
|
|
|
|
/* OK, now copy the revents fields back to user space. */
|
|
walk = head;
|
|
err = -EFAULT;
|
|
while(walk != NULL) {
|
|
struct pollfd *fds = walk->entries;
|
|
int j;
|
|
|
|
for (j=0; j < walk->len; j++, ufds++) {
|
|
if(__put_user(fds[j].revents, &ufds->revents))
|
|
goto out_fds;
|
|
}
|
|
walk = walk->next;
|
|
}
|
|
err = fdcount;
|
|
if (!fdcount && signal_pending(current))
|
|
err = -EINTR;
|
|
out_fds:
|
|
walk = head;
|
|
while(walk!=NULL) {
|
|
struct poll_list *pp = walk->next;
|
|
kfree(walk);
|
|
walk = pp;
|
|
}
|
|
poll_freewait(&table);
|
|
return err;
|
|
}
|