select.c 19.8 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24
/*
 * 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>
25
#include <linux/rcupdate.h>
L
Linus Torvalds 已提交
26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52

#include <asm/uaccess.h>

#define ROUND_UP(x,y) (((x)+(y)-1)/(y))
#define DEFAULT_POLLMASK (POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM)

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.
 */
A
Adrian Bunk 已提交
53 54
static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
		       poll_table *p);
L
Linus Torvalds 已提交
55 56 57 58 59 60

void poll_initwait(struct poll_wqueues *pwq)
{
	init_poll_funcptr(&pwq->pt, __pollwait);
	pwq->error = 0;
	pwq->table = NULL;
61
	pwq->inline_index = 0;
L
Linus Torvalds 已提交
62 63 64 65
}

EXPORT_SYMBOL(poll_initwait);

66 67 68 69 70 71
static void free_poll_entry(struct poll_table_entry *entry)
{
	remove_wait_queue(entry->wait_address,&entry->wait);
	fput(entry->filp);
}

L
Linus Torvalds 已提交
72 73 74
void poll_freewait(struct poll_wqueues *pwq)
{
	struct poll_table_page * p = pwq->table;
75 76 77
	int i;
	for (i = 0; i < pwq->inline_index; i++)
		free_poll_entry(pwq->inline_entries + i);
L
Linus Torvalds 已提交
78 79 80 81 82 83 84
	while (p) {
		struct poll_table_entry * entry;
		struct poll_table_page *old;

		entry = p->entry;
		do {
			entry--;
85
			free_poll_entry(entry);
L
Linus Torvalds 已提交
86 87 88 89 90 91 92 93 94
		} while (entry > p->entries);
		old = p;
		p = p->next;
		free_page((unsigned long) old);
	}
}

EXPORT_SYMBOL(poll_freewait);

95
static struct poll_table_entry *poll_get_entry(poll_table *_p)
L
Linus Torvalds 已提交
96 97 98 99
{
	struct poll_wqueues *p = container_of(_p, struct poll_wqueues, pt);
	struct poll_table_page *table = p->table;

100 101 102
	if (p->inline_index < N_INLINE_POLL_ENTRIES)
		return p->inline_entries + p->inline_index++;

L
Linus Torvalds 已提交
103 104 105 106 107 108 109
	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);
110
			return NULL;
L
Linus Torvalds 已提交
111 112 113 114 115 116 117
		}
		new_table->entry = new_table->entries;
		new_table->next = table;
		p->table = new_table;
		table = new_table;
	}

118 119 120 121 122 123 124 125 126 127 128 129 130 131 132
	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);
	add_wait_queue(wait_address,&entry->wait);
L
Linus Torvalds 已提交
133 134 135 136 137 138 139 140 141 142 143 144 145
}

#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;
146
	struct fdtable *fdt;
L
Linus Torvalds 已提交
147 148 149 150

	/* handle last in-complete long-word first */
	set = ~(~0UL << (n & (__NFDBITS-1)));
	n /= __NFDBITS;
151 152
	fdt = files_fdtable(current->files);
	open_fds = fdt->open_fds->fds_bits+n;
L
Linus Torvalds 已提交
153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191
	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)

192
int do_select(int n, fd_set_bits *fds, s64 *timeout)
L
Linus Torvalds 已提交
193 194 195 196 197
{
	struct poll_wqueues table;
	poll_table *wait;
	int retval, i;

198
	rcu_read_lock();
L
Linus Torvalds 已提交
199
	retval = max_select_fd(n, fds);
200
	rcu_read_unlock();
L
Linus Torvalds 已提交
201 202 203 204 205 206 207

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

	poll_initwait(&table);
	wait = &table.pt;
208
	if (!*timeout)
L
Linus Torvalds 已提交
209 210 211 212
		wait = NULL;
	retval = 0;
	for (;;) {
		unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp;
213
		long __timeout;
L
Linus Torvalds 已提交
214 215 216 217 218 219 220 221 222

		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;
223
			const struct file_operations *f_op = NULL;
L
Linus Torvalds 已提交
224 225 226 227 228 229 230 231 232 233
			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) {
234
				int fput_needed;
L
Linus Torvalds 已提交
235 236 237 238
				if (i >= n)
					break;
				if (!(bit & all_bits))
					continue;
239
				file = fget_light(i, &fput_needed);
L
Linus Torvalds 已提交
240 241 242 243 244
				if (file) {
					f_op = file->f_op;
					mask = DEFAULT_POLLMASK;
					if (f_op && f_op->poll)
						mask = (*f_op->poll)(file, retval ? NULL : wait);
245
					fput_light(file, fput_needed);
L
Linus Torvalds 已提交
246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268
					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;
269
		if (retval || !*timeout || signal_pending(current))
L
Linus Torvalds 已提交
270 271 272 273 274
			break;
		if(table.error) {
			retval = table.error;
			break;
		}
275 276 277 278 279 280 281 282 283 284 285 286

		if (*timeout < 0) {
			/* Wait indefinitely */
			__timeout = MAX_SCHEDULE_TIMEOUT;
		} else if (unlikely(*timeout >= (s64)MAX_SCHEDULE_TIMEOUT - 1)) {
			/* Wait for longer than MAX_SCHEDULE_TIMEOUT. Do it in a loop */
			__timeout = MAX_SCHEDULE_TIMEOUT - 1;
			*timeout -= __timeout;
		} else {
			__timeout = *timeout;
			*timeout = 0;
		}
L
Linus Torvalds 已提交
287
		__timeout = schedule_timeout(__timeout);
288 289
		if (*timeout >= 0)
			*timeout += __timeout;
L
Linus Torvalds 已提交
290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308
	}
	__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)

309 310
static int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
			   fd_set __user *exp, s64 *timeout)
L
Linus Torvalds 已提交
311 312
{
	fd_set_bits fds;
A
Andrew Morton 已提交
313
	void *bits;
314 315
	int ret, max_fdset;
	unsigned int size;
316
	struct fdtable *fdt;
317
	/* Allocate small arguments on the stack to save memory and be faster */
318
	long stack_fds[SELECT_STACK_ALLOC/sizeof(long)];
L
Linus Torvalds 已提交
319 320 321 322 323 324

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

	/* max_fdset can increase, so grab it once to avoid race */
325
	rcu_read_lock();
326 327
	fdt = files_fdtable(current->files);
	max_fdset = fdt->max_fdset;
328
	rcu_read_unlock();
L
Linus Torvalds 已提交
329 330 331 332 333 334 335 336 337
	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. 
	 */
	size = FDS_BYTES(n);
338 339 340 341
	bits = stack_fds;
	if (size > sizeof(stack_fds) / 6) {
		/* Not enough space in on-stack array; must use kmalloc */
		ret = -ENOMEM;
342
		bits = kmalloc(6 * size, GFP_KERNEL);
343 344 345
		if (!bits)
			goto out_nofds;
	}
A
Andrew Morton 已提交
346 347 348 349 350 351
	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;
L
Linus Torvalds 已提交
352 353 354 355 356 357 358 359 360

	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);

361
	ret = do_select(n, &fds, timeout);
L
Linus Torvalds 已提交
362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377

	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:
378 379
	if (bits != stack_fds)
		kfree(bits);
L
Linus Torvalds 已提交
380 381 382 383
out_nofds:
	return ret;
}

384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409
asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp,
			fd_set __user *exp, struct timeval __user *tvp)
{
	s64 timeout = -1;
	struct timeval tv;
	int ret;

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

		if (tv.tv_sec < 0 || tv.tv_usec < 0)
			return -EINVAL;

		/* Cast to u64 to make GCC stop complaining */
		if ((u64)tv.tv_sec >= (u64)MAX_INT64_SECONDS)
			timeout = -1;	/* infinite */
		else {
			timeout = ROUND_UP(tv.tv_usec, USEC_PER_SEC/HZ);
			timeout += tv.tv_sec * HZ;
		}
	}

	ret = core_sys_select(n, inp, outp, exp, &timeout);

	if (tvp) {
410 411
		struct timeval rtv;

412 413
		if (current->personality & STICKY_TIMEOUTS)
			goto sticky;
414 415
		rtv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ));
		rtv.tv_sec = timeout;
416
		if (timeval_compare(&rtv, &tv) >= 0)
417 418
			rtv = tv;
		if (copy_to_user(tvp, &rtv, sizeof(rtv))) {
419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475
sticky:
			/*
			 * If an application puts its timeval in read-only
			 * memory, we don't want the Linux-specific update to
			 * the timeval to cause a fault after the select has
			 * completed successfully. However, because we're not
			 * updating the timeval, we can't restart the system
			 * call.
			 */
			if (ret == -ERESTARTNOHAND)
				ret = -EINTR;
		}
	}

	return ret;
}

#ifdef TIF_RESTORE_SIGMASK
asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp,
		fd_set __user *exp, struct timespec __user *tsp,
		const sigset_t __user *sigmask, size_t sigsetsize)
{
	s64 timeout = MAX_SCHEDULE_TIMEOUT;
	sigset_t ksigmask, sigsaved;
	struct timespec ts;
	int ret;

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

		if (ts.tv_sec < 0 || ts.tv_nsec < 0)
			return -EINVAL;

		/* Cast to u64 to make GCC stop complaining */
		if ((u64)ts.tv_sec >= (u64)MAX_INT64_SECONDS)
			timeout = -1;	/* infinite */
		else {
			timeout = ROUND_UP(ts.tv_nsec, NSEC_PER_SEC/HZ);
			timeout += ts.tv_sec * HZ;
		}
	}

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

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

	ret = core_sys_select(n, inp, outp, exp, &timeout);

	if (tsp) {
476 477
		struct timespec rts;

478 479
		if (current->personality & STICKY_TIMEOUTS)
			goto sticky;
480 481 482
		rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) *
						1000;
		rts.tv_sec = timeout;
483
		if (timespec_compare(&rts, &ts) >= 0)
484 485
			rts = ts;
		if (copy_to_user(tsp, &rts, sizeof(rts))) {
486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530
sticky:
			/*
			 * If an application puts its timeval in read-only
			 * memory, we don't want the Linux-specific update to
			 * the timeval to cause a fault after the select has
			 * completed successfully. However, because we're not
			 * updating the timeval, we can't restart the system
			 * call.
			 */
			if (ret == -ERESTARTNOHAND)
				ret = -EINTR;
		}
	}

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

	return ret;
}

/*
 * Most architectures can't handle 7-argument syscalls. So we provide a
 * 6-argument version where the sixth argument is a pointer to a structure
 * which has a pointer to the sigset_t itself followed by a size_t containing
 * the sigset size.
 */
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))
531
		    || __get_user(up, (sigset_t __user * __user *)sig)
532
		    || __get_user(sigsetsize,
533
				(size_t __user *)(sig+sizeof(void *))))
534 535 536 537 538 539 540
			return -EFAULT;
	}

	return sys_pselect7(n, inp, outp, exp, tsp, up, sigsetsize);
}
#endif /* TIF_RESTORE_SIGMASK */

L
Linus Torvalds 已提交
541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562
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) {
563 564
			int fput_needed;
			struct file * file = fget_light(fd, &fput_needed);
L
Linus Torvalds 已提交
565 566 567 568 569 570
			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;
571
				fput_light(file, fput_needed);
L
Linus Torvalds 已提交
572 573 574 575 576 577 578 579 580 581 582
			}
			if (mask) {
				*pwait = NULL;
				(*count)++;
			}
		}
		fdp->revents = mask;
	}
}

static int do_poll(unsigned int nfds,  struct poll_list *list,
583
		   struct poll_wqueues *wait, s64 *timeout)
L
Linus Torvalds 已提交
584 585 586 587
{
	int count = 0;
	poll_table* pt = &wait->pt;

588 589
	/* Optimise the no-wait case */
	if (!(*timeout))
L
Linus Torvalds 已提交
590 591 592 593
		pt = NULL;
 
	for (;;) {
		struct poll_list *walk;
594 595
		long __timeout;

L
Linus Torvalds 已提交
596 597 598 599 600 601 602
		set_current_state(TASK_INTERRUPTIBLE);
		walk = list;
		while(walk != NULL) {
			do_pollfd( walk->len, walk->entries, &pt, &count);
			walk = walk->next;
		}
		pt = NULL;
603
		if (count || !*timeout || signal_pending(current))
L
Linus Torvalds 已提交
604 605 606 607
			break;
		count = wait->error;
		if (count)
			break;
608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626

		if (*timeout < 0) {
			/* Wait indefinitely */
			__timeout = MAX_SCHEDULE_TIMEOUT;
		} else if (unlikely(*timeout >= (s64)MAX_SCHEDULE_TIMEOUT-1)) {
			/*
			 * Wait for longer than MAX_SCHEDULE_TIMEOUT. Do it in
			 * a loop
			 */
			__timeout = MAX_SCHEDULE_TIMEOUT - 1;
			*timeout -= __timeout;
		} else {
			__timeout = *timeout;
			*timeout = 0;
		}

		__timeout = schedule_timeout(__timeout);
		if (*timeout >= 0)
			*timeout += __timeout;
L
Linus Torvalds 已提交
627 628 629 630 631
	}
	__set_current_state(TASK_RUNNING);
	return count;
}

632 633 634
#define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list))  / \
			sizeof(struct pollfd))

635
int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, s64 *timeout)
L
Linus Torvalds 已提交
636 637 638 639 640 641
{
	struct poll_wqueues table;
 	int fdcount, err;
 	unsigned int i;
	struct poll_list *head;
 	struct poll_list *walk;
642
	struct fdtable *fdt;
643
	int max_fdset;
644 645 646 647
	/* 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)];
648
	struct poll_list *stack_pp = NULL;
L
Linus Torvalds 已提交
649 650

	/* Do a sanity check on nfds ... */
651
	rcu_read_lock();
652
	fdt = files_fdtable(current->files);
653 654 655
	max_fdset = fdt->max_fdset;
	rcu_read_unlock();
	if (nfds > max_fdset && nfds > OPEN_MAX)
L
Linus Torvalds 已提交
656 657 658 659 660 661 662 663 664 665
		return -EINVAL;

	poll_initwait(&table);

	head = NULL;
	walk = NULL;
	i = nfds;
	err = -ENOMEM;
	while(i!=0) {
		struct poll_list *pp;
666 667 668 669 670 671 672 673 674 675 676 677 678 679 680
		int num, size;
		if (stack_pp == NULL)
			num = N_STACK_PPS;
		else
			num = POLLFD_PER_PAGE;
		if (num > i)
			num = i;
		size = sizeof(struct poll_list) + sizeof(struct pollfd)*num;
		if (!stack_pp)
			stack_pp = pp = (struct poll_list *)stack_pps;
		else {
			pp = kmalloc(size, GFP_KERNEL);
			if (!pp)
				goto out_fds;
		}
L
Linus Torvalds 已提交
681
		pp->next=NULL;
682
		pp->len = num;
L
Linus Torvalds 已提交
683 684 685 686 687 688 689
		if (head == NULL)
			head = pp;
		else
			walk->next = pp;

		walk = pp;
		if (copy_from_user(pp->entries, ufds + nfds-i, 
690
				sizeof(struct pollfd)*num)) {
L
Linus Torvalds 已提交
691 692 693 694 695
			err = -EFAULT;
			goto out_fds;
		}
		i -= pp->len;
	}
696

L
Linus Torvalds 已提交
697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718
	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;
719 720
		if (walk != stack_pp)
			kfree(walk);
L
Linus Torvalds 已提交
721 722 723 724 725
		walk = pp;
	}
	poll_freewait(&table);
	return err;
}
726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797

asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds,
			long timeout_msecs)
{
	s64 timeout_jiffies = 0;

	if (timeout_msecs) {
#if HZ > 1000
		/* We can only overflow if HZ > 1000 */
		if (timeout_msecs / 1000 > (s64)0x7fffffffffffffffULL / (s64)HZ)
			timeout_jiffies = -1;
		else
#endif
			timeout_jiffies = msecs_to_jiffies(timeout_msecs);
	}

	return do_sys_poll(ufds, nfds, &timeout_jiffies);
}

#ifdef TIF_RESTORE_SIGMASK
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;
	struct timespec ts;
	s64 timeout = -1;
	int ret;

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

		/* Cast to u64 to make GCC stop complaining */
		if ((u64)ts.tv_sec >= (u64)MAX_INT64_SECONDS)
			timeout = -1;	/* infinite */
		else {
			timeout = ROUND_UP(ts.tv_nsec, NSEC_PER_SEC/HZ);
			timeout += ts.tv_sec * HZ;
		}
	}

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

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

	ret = do_sys_poll(ufds, nfds, &timeout);

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

	if (tsp && timeout >= 0) {
798 799
		struct timespec rts;

800 801 802
		if (current->personality & STICKY_TIMEOUTS)
			goto sticky;
		/* Yes, we know it's actually an s64, but it's also positive. */
803 804 805
		rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) *
						1000;
		rts.tv_sec = timeout;
806
		if (timespec_compare(&rts, &ts) >= 0)
807 808
			rts = ts;
		if (copy_to_user(tsp, &rts, sizeof(rts))) {
809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825
		sticky:
			/*
			 * If an application puts its timeval in read-only
			 * memory, we don't want the Linux-specific update to
			 * the timeval to cause a fault after the select has
			 * completed successfully. However, because we're not
			 * updating the timeval, we can't restart the system
			 * call.
			 */
			if (ret == -ERESTARTNOHAND && timeout >= 0)
				ret = -EINTR;
		}
	}

	return ret;
}
#endif /* TIF_RESTORE_SIGMASK */