summaryrefslogtreecommitdiffstats
path: root/fs/binfmt_flat.c
diff options
context:
space:
mode:
authorMike Frysinger <vapier@gentoo.org>2010-06-04 17:14:55 -0400
committerLinus Torvalds <torvalds@linux-foundation.org>2010-06-04 18:21:45 -0400
commit1da083c9b23dafd6bcb08dcfec443e66e90efff0 (patch)
tree2514790b650c125bf29715b01e16ccbb4206e820 /fs/binfmt_flat.c
parent2e94de8acbe524d919f1ea8807913d7b005e1578 (diff)
flat: fix unmap len in load error path
The data chunk is mmaped with 'len' which remains unchanged, so use that when unmapping in the error path rather than trying to recalculate (and incorrectly so) the value used originally. Signed-off-by: Mike Frysinger <vapier@gentoo.org> Acked-by: David McCullough <davidm@snapgear.com> Acked-by: Greg Ungerer <gerg@uclinux.org> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Michal Simek <monstr@monstr.eu> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Acked-by: David Howells <dhowells@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'fs/binfmt_flat.c')
-rw-r--r--fs/binfmt_flat.c2
1 files changed, 1 insertions, 1 deletions
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index b8656225b34b..b6ab27ccf214 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -596,7 +596,7 @@ static int load_flat_file(struct linux_binprm * bprm,
596 if (IS_ERR_VALUE(result)) { 596 if (IS_ERR_VALUE(result)) {
597 printk("Unable to read data+bss, errno %d\n", (int)-result); 597 printk("Unable to read data+bss, errno %d\n", (int)-result);
598 do_munmap(current->mm, textpos, text_len); 598 do_munmap(current->mm, textpos, text_len);
599 do_munmap(current->mm, realdatastart, data_len + extra); 599 do_munmap(current->mm, realdatastart, len);
600 ret = result; 600 ret = result;
601 goto err; 601 goto err;
602 } 602 }
id='n263' href='#n263'>263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719
/*
 * taskstats.c - Export per-task statistics to userland
 *
 * Copyright (C) Shailabh Nagar, IBM Corp. 2006
 *           (C) Balbir Singh,   IBM Corp. 2006
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 */

#include <linux/kernel.h>
#include <linux/taskstats_kern.h>
#include <linux/tsacct_kern.h>
#include <linux/delayacct.h>
#include <linux/cpumask.h>
#include <linux/percpu.h>
#include <linux/slab.h>
#include <linux/cgroupstats.h>
#include <linux/cgroup.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/pid_namespace.h>
#include <net/genetlink.h>
#include <linux/atomic.h>

/*
 * Maximum length of a cpumask that can be specified in
 * the TASKSTATS_CMD_ATTR_REGISTER/DEREGISTER_CPUMASK attribute
 */
#define TASKSTATS_CPUMASK_MAXLEN	(100+6*NR_CPUS)

static DEFINE_PER_CPU(__u32, taskstats_seqnum);
static int family_registered;
struct kmem_cache *taskstats_cache;

static struct genl_family family = {
	.id		= GENL_ID_GENERATE,
	.name		= TASKSTATS_GENL_NAME,
	.version	= TASKSTATS_GENL_VERSION,
	.maxattr	= TASKSTATS_CMD_ATTR_MAX,
};

static const struct nla_policy taskstats_cmd_get_policy[TASKSTATS_CMD_ATTR_MAX+1] = {
	[TASKSTATS_CMD_ATTR_PID]  = { .type = NLA_U32 },
	[TASKSTATS_CMD_ATTR_TGID] = { .type = NLA_U32 },
	[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK] = { .type = NLA_STRING },
	[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK] = { .type = NLA_STRING },};

static const struct nla_policy cgroupstats_cmd_get_policy[CGROUPSTATS_CMD_ATTR_MAX+1] = {
	[CGROUPSTATS_CMD_ATTR_FD] = { .type = NLA_U32 },
};

struct listener {
	struct list_head list;
	pid_t pid;
	char valid;
};

struct listener_list {
	struct rw_semaphore sem;
	struct list_head list;
};
static DEFINE_PER_CPU(struct listener_list, listener_array);

enum actions {
	REGISTER,
	DEREGISTER,
	CPU_DONT_CARE
};

static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp,
				size_t size)
{
	struct sk_buff *skb;
	void *reply;

	/*
	 * If new attributes are added, please revisit this allocation
	 */
	skb = genlmsg_new(size, GFP_KERNEL);
	if (!skb)
		return -ENOMEM;

	if (!info) {
		int seq = this_cpu_inc_return(taskstats_seqnum) - 1;

		reply = genlmsg_put(skb, 0, seq, &family, 0, cmd);
	} else
		reply = genlmsg_put_reply(skb, info, &family, 0, cmd);
	if (reply == NULL) {
		nlmsg_free(skb);
		return -EINVAL;
	}

	*skbp = skb;
	return 0;
}

/*
 * Send taskstats data in @skb to listener with nl_pid @pid
 */
static int send_reply(struct sk_buff *skb, struct genl_info *info)
{
	struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb));
	void *reply = genlmsg_data(genlhdr);
	int rc;

	rc = genlmsg_end(skb, reply);
	if (rc < 0) {
		nlmsg_free(skb);
		return rc;
	}

	return genlmsg_reply(skb, info);
}

/*
 * Send taskstats data in @skb to listeners registered for @cpu's exit data
 */
static void send_cpu_listeners(struct sk_buff *skb,
					struct listener_list *listeners)
{
	struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb));
	struct listener *s, *tmp;
	struct sk_buff *skb_next, *skb_cur = skb;
	void *reply = genlmsg_data(genlhdr);
	int rc, delcount = 0;

	rc = genlmsg_end(skb, reply);
	if (rc < 0) {
		nlmsg_free(skb);
		return;
	}

	rc = 0;
	down_read(&listeners->sem);
	list_for_each_entry(s, &listeners->list, list) {
		skb_next = NULL;
		if (!list_is_last(&s->list, &listeners->list)) {
			skb_next = skb_clone(skb_cur, GFP_KERNEL);
			if (!skb_next)
				break;
		}
		rc = genlmsg_unicast(&init_net, skb_cur, s->pid);
		if (rc == -ECONNREFUSED) {
			s->valid = 0;
			delcount++;
		}
		skb_cur = skb_next;
	}
	up_read(&listeners->sem);

	if (skb_cur)
		nlmsg_free(skb_cur);

	if (!delcount)
		return;

	/* Delete invalidated entries */
	down_write(&listeners->sem);
	list_for_each_entry_safe(s, tmp, &listeners->list, list) {
		if (!s->valid) {
			list_del(&s->list);
			kfree(s);
		}
	}
	up_write(&listeners->sem);
}

static void fill_stats(struct user_namespace *user_ns,
		       struct pid_namespace *pid_ns,
		       struct task_struct *tsk, struct taskstats *stats)
{
	memset(stats, 0, sizeof(*stats));
	/*
	 * Each accounting subsystem adds calls to its functions to
	 * fill in relevant parts of struct taskstsats as follows
	 *
	 *	per-task-foo(stats, tsk);
	 */

	delayacct_add_tsk(stats, tsk);

	/* fill in basic acct fields */
	stats->version = TASKSTATS_VERSION;
	stats->nvcsw = tsk->nvcsw;
	stats->nivcsw = tsk->nivcsw;
	bacct_add_tsk(user_ns, pid_ns, stats, tsk);

	/* fill in extended acct fields */
	xacct_add_tsk(stats, tsk);
}

static int fill_stats_for_pid(pid_t pid, struct taskstats *stats)
{
	struct task_struct *tsk;

	rcu_read_lock();
	tsk = find_task_by_vpid(pid);
	if (tsk)
		get_task_struct(tsk);
	rcu_read_unlock();
	if (!tsk)
		return -ESRCH;
	fill_stats(current_user_ns(), task_active_pid_ns(current), tsk, stats);
	put_task_struct(tsk);
	return 0;
}

static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats)
{
	struct task_struct *tsk, *first;
	unsigned long flags;
	int rc = -ESRCH;

	/*
	 * Add additional stats from live tasks except zombie thread group
	 * leaders who are already counted with the dead tasks
	 */
	rcu_read_lock();
	first = find_task_by_vpid(tgid);

	if (!first || !lock_task_sighand(first, &flags))
		goto out;

	if (first->signal->stats)
		memcpy(stats, first->signal->stats, sizeof(*stats));
	else
		memset(stats, 0, sizeof(*stats));

	tsk = first;
	do {
		if (tsk->exit_state)
			continue;
		/*
		 * Accounting subsystem can call its functions here to
		 * fill in relevant parts of struct taskstsats as follows
		 *
		 *	per-task-foo(stats, tsk);
		 */
		delayacct_add_tsk(stats, tsk);

		stats->nvcsw += tsk->nvcsw;
		stats->nivcsw += tsk->nivcsw;
	} while_each_thread(first, tsk);

	unlock_task_sighand(first, &flags);
	rc = 0;
out:
	rcu_read_unlock();

	stats->version = TASKSTATS_VERSION;
	/*
	 * Accounting subsystems can also add calls here to modify
	 * fields of taskstats.
	 */
	return rc;
}

static void fill_tgid_exit(struct task_struct *tsk)
{
	unsigned long flags;

	spin_lock_irqsave(&tsk->sighand->siglock, flags);
	if (!tsk->signal->stats)
		goto ret;

	/*
	 * Each accounting subsystem calls its functions here to
	 * accumalate its per-task stats for tsk, into the per-tgid structure
	 *
	 *	per-task-foo(tsk->signal->stats, tsk);
	 */
	delayacct_add_tsk(tsk->signal->stats, tsk);
ret:
	spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
	return;
}

static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd)
{
	struct listener_list *listeners;
	struct listener *s, *tmp, *s2;
	unsigned int cpu;
	int ret = 0;

	if (!cpumask_subset(mask, cpu_possible_mask))
		return -EINVAL;

	if (current_user_ns() != &init_user_ns)
		return -EINVAL;

	if (task_active_pid_ns(current) != &init_pid_ns)
		return -EINVAL;

	if (isadd == REGISTER) {
		for_each_cpu(cpu, mask) {
			s = kmalloc_node(sizeof(struct listener),
					GFP_KERNEL, cpu_to_node(cpu));
			if (!s) {
				ret = -ENOMEM;
				goto cleanup;
			}
			s->pid = pid;
			s->valid = 1;

			listeners = &per_cpu(listener_array, cpu);
			down_write(&listeners->sem);
			list_for_each_entry(s2, &listeners->list, list) {
				if (s2->pid == pid && s2->valid)
					goto exists;
			}
			list_add(&s->list, &listeners->list);
			s = NULL;
exists:
			up_write(&listeners->sem);
			kfree(s); /* nop if NULL */
		}
		return 0;
	}

	/* Deregister or cleanup */
cleanup:
	for_each_cpu(cpu, mask) {
		listeners = &per_cpu(listener_array, cpu);
		down_write(&listeners->sem);
		list_for_each_entry_safe(s, tmp, &listeners->list, list) {
			if (s->pid == pid) {
				list_del(&s->list);
				kfree(s);
				break;
			}
		}
		up_write(&listeners->sem);
	}
	return ret;
}

static int parse(struct nlattr *na, struct cpumask *mask)
{
	char *data;
	int len;
	int ret;

	if (na == NULL)
		return 1;
	len = nla_len(na);
	if (len > TASKSTATS_CPUMASK_MAXLEN)
		return -E2BIG;
	if (len < 1)
		return -EINVAL;
	data = kmalloc(len, GFP_KERNEL);
	if (!data)
		return -ENOMEM;
	nla_strlcpy(data, na, len);
	ret = cpulist_parse(data, mask);
	kfree(data);
	return ret;
}

#if defined(CONFIG_64BIT) && !defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
#define TASKSTATS_NEEDS_PADDING 1
#endif

static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid)
{
	struct nlattr *na, *ret;
	int aggr;

	aggr = (type == TASKSTATS_TYPE_PID)
			? TASKSTATS_TYPE_AGGR_PID
			: TASKSTATS_TYPE_AGGR_TGID;

	/*
	 * The taskstats structure is internally aligned on 8 byte
	 * boundaries but the layout of the aggregrate reply, with
	 * two NLA headers and the pid (each 4 bytes), actually
	 * force the entire structure to be unaligned. This causes
	 * the kernel to issue unaligned access warnings on some
	 * architectures like ia64. Unfortunately, some software out there
	 * doesn't properly unroll the NLA packet and assumes that the start
	 * of the taskstats structure will always be 20 bytes from the start
	 * of the netlink payload. Aligning the start of the taskstats
	 * structure breaks this software, which we don't want. So, for now
	 * the alignment only happens on architectures that require it
	 * and those users will have to update to fixed versions of those
	 * packages. Space is reserved in the packet only when needed.
	 * This ifdef should be removed in several years e.g. 2012 once
	 * we can be confident that fixed versions are installed on most
	 * systems. We add the padding before the aggregate since the
	 * aggregate is already a defined type.
	 */
#ifdef TASKSTATS_NEEDS_PADDING
	if (nla_put(skb, TASKSTATS_TYPE_NULL, 0, NULL) < 0)
		goto err;
#endif
	na = nla_nest_start(skb, aggr);
	if (!na)
		goto err;

	if (nla_put(skb, type, sizeof(pid), &pid) < 0) {
		nla_nest_cancel(skb, na);
		goto err;
	}
	ret = nla_reserve(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats));
	if (!ret) {
		nla_nest_cancel(skb, na);
		goto err;
	}
	nla_nest_end(skb, na);

	return nla_data(ret);
err:
	return NULL;
}

static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
{
	int rc = 0;
	struct sk_buff *rep_skb;
	struct cgroupstats *stats;
	struct nlattr *na;
	size_t size;
	u32 fd;
	struct fd f;

	na = info->attrs[CGROUPSTATS_CMD_ATTR_FD];
	if (!na)
		return -EINVAL;

	fd = nla_get_u32(info->attrs[CGROUPSTATS_CMD_ATTR_FD]);
	f = fdget(fd);
	if (!f.file)
		return 0;

	size = nla_total_size(sizeof(struct cgroupstats));

	rc = prepare_reply(info, CGROUPSTATS_CMD_NEW, &rep_skb,
				size);
	if (rc < 0)
		goto err;

	na = nla_reserve(rep_skb, CGROUPSTATS_TYPE_CGROUP_STATS,
				sizeof(struct cgroupstats));
	if (na == NULL) {
		nlmsg_free(rep_skb);
		rc = -EMSGSIZE;
		goto err;
	}

	stats = nla_data(na);
	memset(stats, 0, sizeof(*stats));

	rc = cgroupstats_build(stats, f.file->f_dentry);
	if (rc < 0) {
		nlmsg_free(rep_skb);
		goto err;
	}

	rc = send_reply(rep_skb, info);

err:
	fdput(f);
	return rc;
}

static int cmd_attr_register_cpumask(struct genl_info *info)
{
	cpumask_var_t mask;
	int rc;

	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
		return -ENOMEM;
	rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask);
	if (rc < 0)
		goto out;
	rc = add_del_listener(info->snd_portid, mask, REGISTER);
out:
	free_cpumask_var(mask);
	return rc;
}

static int cmd_attr_deregister_cpumask(struct genl_info *info)
{
	cpumask_var_t mask;
	int rc;

	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
		return -ENOMEM;
	rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask);
	if (rc < 0)
		goto out;
	rc = add_del_listener(info->snd_portid, mask, DEREGISTER);
out:
	free_cpumask_var(mask);
	return rc;
}

static size_t taskstats_packet_size(void)
{
	size_t size;

	size = nla_total_size(sizeof(u32)) +
		nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
#ifdef TASKSTATS_NEEDS_PADDING
	size += nla_total_size(0); /* Padding for alignment */
#endif
	return size;
}

static int cmd_attr_pid(struct genl_info *info)
{
	struct taskstats *stats;
	struct sk_buff *rep_skb;
	size_t size;
	u32 pid;
	int rc;

	size = taskstats_packet_size();

	rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size);
	if (rc < 0)
		return rc;

	rc = -EINVAL;
	pid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_PID]);
	stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid);
	if (!stats)
		goto err;

	rc = fill_stats_for_pid(pid, stats);
	if (rc < 0)
		goto err;
	return send_reply(rep_skb, info);
err:
	nlmsg_free(rep_skb);
	return rc;
}

static int cmd_attr_tgid(struct genl_info *info)
{
	struct taskstats *stats;
	struct sk_buff *rep_skb;
	size_t size;
	u32 tgid;
	int rc;

	size = taskstats_packet_size();