linux/block/ioprio.c
Omar Sandoval 8ba8682107 block: fix use-after-free in sys_ioprio_get()
get_task_ioprio() accesses the task->io_context without holding the task
lock and thus can race with exit_io_context(), leading to a
use-after-free. The reproducer below hits this within a few seconds on
my 4-core QEMU VM:

#define _GNU_SOURCE
#include <assert.h>
#include <unistd.h>
#include <sys/syscall.h>
#include <sys/wait.h>

int main(int argc, char **argv)
{
	pid_t pid, child;
	long nproc, i;

	/* ioprio_set(IOPRIO_WHO_PROCESS, 0, IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0)); */
	syscall(SYS_ioprio_set, 1, 0, 0x6000);

	nproc = sysconf(_SC_NPROCESSORS_ONLN);

	for (i = 0; i < nproc; i++) {
		pid = fork();
		assert(pid != -1);
		if (pid == 0) {
			for (;;) {
				pid = fork();
				assert(pid != -1);
				if (pid == 0) {
					_exit(0);
				} else {
					child = wait(NULL);
					assert(child == pid);
				}
			}
		}

		pid = fork();
		assert(pid != -1);
		if (pid == 0) {
			for (;;) {
				/* ioprio_get(IOPRIO_WHO_PGRP, 0); */
				syscall(SYS_ioprio_get, 2, 0);
			}
		}
	}

	for (;;) {
		/* ioprio_get(IOPRIO_WHO_PGRP, 0); */
		syscall(SYS_ioprio_get, 2, 0);
	}

	return 0;
}

This gets us KASAN dumps like this:

[   35.526914] ==================================================================
[   35.530009] BUG: KASAN: out-of-bounds in get_task_ioprio+0x7b/0x90 at addr ffff880066f34e6c
[   35.530009] Read of size 2 by task ioprio-gpf/363
[   35.530009] =============================================================================
[   35.530009] BUG blkdev_ioc (Not tainted): kasan: bad access detected
[   35.530009] -----------------------------------------------------------------------------

[   35.530009] Disabling lock debugging due to kernel taint
[   35.530009] INFO: Allocated in create_task_io_context+0x2b/0x370 age=0 cpu=0 pid=360
[   35.530009] 	___slab_alloc+0x55d/0x5a0
[   35.530009] 	__slab_alloc.isra.20+0x2b/0x40
[   35.530009] 	kmem_cache_alloc_node+0x84/0x200
[   35.530009] 	create_task_io_context+0x2b/0x370
[   35.530009] 	get_task_io_context+0x92/0xb0
[   35.530009] 	copy_process.part.8+0x5029/0x5660
[   35.530009] 	_do_fork+0x155/0x7e0
[   35.530009] 	SyS_clone+0x19/0x20
[   35.530009] 	do_syscall_64+0x195/0x3a0
[   35.530009] 	return_from_SYSCALL_64+0x0/0x6a
[   35.530009] INFO: Freed in put_io_context+0xe7/0x120 age=0 cpu=0 pid=1060
[   35.530009] 	__slab_free+0x27b/0x3d0
[   35.530009] 	kmem_cache_free+0x1fb/0x220
[   35.530009] 	put_io_context+0xe7/0x120
[   35.530009] 	put_io_context_active+0x238/0x380
[   35.530009] 	exit_io_context+0x66/0x80
[   35.530009] 	do_exit+0x158e/0x2b90
[   35.530009] 	do_group_exit+0xe5/0x2b0
[   35.530009] 	SyS_exit_group+0x1d/0x20
[   35.530009] 	entry_SYSCALL_64_fastpath+0x1a/0xa4
[   35.530009] INFO: Slab 0xffffea00019bcd00 objects=20 used=4 fp=0xffff880066f34ff0 flags=0x1fffe0000004080
[   35.530009] INFO: Object 0xffff880066f34e58 @offset=3672 fp=0x0000000000000001
[   35.530009] ==================================================================

Fix it by grabbing the task lock while we poke at the io_context.

Cc: stable@vger.kernel.org
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
2016-07-01 08:39:24 -06:00

248 lines
5.1 KiB
C

/*
* fs/ioprio.c
*
* Copyright (C) 2004 Jens Axboe <axboe@kernel.dk>
*
* Helper functions for setting/querying io priorities of processes. The
* system calls closely mimmick getpriority/setpriority, see the man page for
* those. The prio argument is a composite of prio class and prio data, where
* the data argument has meaning within that class. The standard scheduling
* classes have 8 distinct prio levels, with 0 being the highest prio and 7
* being the lowest.
*
* IOW, setting BE scheduling class with prio 2 is done ala:
*
* unsigned int prio = (IOPRIO_CLASS_BE << IOPRIO_CLASS_SHIFT) | 2;
*
* ioprio_set(PRIO_PROCESS, pid, prio);
*
* See also Documentation/block/ioprio.txt
*
*/
#include <linux/gfp.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/ioprio.h>
#include <linux/blkdev.h>
#include <linux/capability.h>
#include <linux/syscalls.h>
#include <linux/security.h>
#include <linux/pid_namespace.h>
int set_task_ioprio(struct task_struct *task, int ioprio)
{
int err;
struct io_context *ioc;
const struct cred *cred = current_cred(), *tcred;
rcu_read_lock();
tcred = __task_cred(task);
if (!uid_eq(tcred->uid, cred->euid) &&
!uid_eq(tcred->uid, cred->uid) && !capable(CAP_SYS_NICE)) {
rcu_read_unlock();
return -EPERM;
}
rcu_read_unlock();
err = security_task_setioprio(task, ioprio);
if (err)
return err;
ioc = get_task_io_context(task, GFP_ATOMIC, NUMA_NO_NODE);
if (ioc) {
ioc->ioprio = ioprio;
put_io_context(ioc);
}
return err;
}
EXPORT_SYMBOL_GPL(set_task_ioprio);
SYSCALL_DEFINE3(ioprio_set, int, which, int, who, int, ioprio)
{
int class = IOPRIO_PRIO_CLASS(ioprio);
int data = IOPRIO_PRIO_DATA(ioprio);
struct task_struct *p, *g;
struct user_struct *user;
struct pid *pgrp;
kuid_t uid;
int ret;
switch (class) {
case IOPRIO_CLASS_RT:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
/* fall through, rt has prio field too */
case IOPRIO_CLASS_BE:
if (data >= IOPRIO_BE_NR || data < 0)
return -EINVAL;
break;
case IOPRIO_CLASS_IDLE:
break;
case IOPRIO_CLASS_NONE:
if (data)
return -EINVAL;
break;
default:
return -EINVAL;
}
ret = -ESRCH;
rcu_read_lock();
switch (which) {
case IOPRIO_WHO_PROCESS:
if (!who)
p = current;
else
p = find_task_by_vpid(who);
if (p)
ret = set_task_ioprio(p, ioprio);
break;
case IOPRIO_WHO_PGRP:
if (!who)
pgrp = task_pgrp(current);
else
pgrp = find_vpid(who);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
ret = set_task_ioprio(p, ioprio);
if (ret)
break;
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case IOPRIO_WHO_USER:
uid = make_kuid(current_user_ns(), who);
if (!uid_valid(uid))
break;
if (!who)
user = current_user();
else
user = find_user(uid);
if (!user)
break;
do_each_thread(g, p) {
if (!uid_eq(task_uid(p), uid) ||
!task_pid_vnr(p))
continue;
ret = set_task_ioprio(p, ioprio);
if (ret)
goto free_uid;
} while_each_thread(g, p);
free_uid:
if (who)
free_uid(user);
break;
default:
ret = -EINVAL;
}
rcu_read_unlock();
return ret;
}
static int get_task_ioprio(struct task_struct *p)
{
int ret;
ret = security_task_getioprio(p);
if (ret)
goto out;
ret = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, IOPRIO_NORM);
task_lock(p);
if (p->io_context)
ret = p->io_context->ioprio;
task_unlock(p);
out:
return ret;
}
int ioprio_best(unsigned short aprio, unsigned short bprio)
{
unsigned short aclass;
unsigned short bclass;
if (!ioprio_valid(aprio))
aprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
if (!ioprio_valid(bprio))
bprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
aclass = IOPRIO_PRIO_CLASS(aprio);
bclass = IOPRIO_PRIO_CLASS(bprio);
if (aclass == bclass)
return min(aprio, bprio);
if (aclass > bclass)
return bprio;
else
return aprio;
}
SYSCALL_DEFINE2(ioprio_get, int, which, int, who)
{
struct task_struct *g, *p;
struct user_struct *user;
struct pid *pgrp;
kuid_t uid;
int ret = -ESRCH;
int tmpio;
rcu_read_lock();
switch (which) {
case IOPRIO_WHO_PROCESS:
if (!who)
p = current;
else
p = find_task_by_vpid(who);
if (p)
ret = get_task_ioprio(p);
break;
case IOPRIO_WHO_PGRP:
if (!who)
pgrp = task_pgrp(current);
else
pgrp = find_vpid(who);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
tmpio = get_task_ioprio(p);
if (tmpio < 0)
continue;
if (ret == -ESRCH)
ret = tmpio;
else
ret = ioprio_best(ret, tmpio);
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
break;
case IOPRIO_WHO_USER:
uid = make_kuid(current_user_ns(), who);
if (!who)
user = current_user();
else
user = find_user(uid);
if (!user)
break;
do_each_thread(g, p) {
if (!uid_eq(task_uid(p), user->uid) ||
!task_pid_vnr(p))
continue;
tmpio = get_task_ioprio(p);
if (tmpio < 0)
continue;
if (ret == -ESRCH)
ret = tmpio;
else
ret = ioprio_best(ret, tmpio);
} while_each_thread(g, p);
if (who)
free_uid(user);
break;
default:
ret = -EINVAL;
}
rcu_read_unlock();
return ret;
}