Revision 6f6acb00514c10be35529402f36ad7a288f08c2e authored by Michal Hocko on 22 May 2014, 18:54:19 UTC, committed by Linus Torvalds on 23 May 2014, 16:37:29 UTC
Commit 284f39afeaa4 ("mm: memcg: push !mm handling out to page cache
charge function") explicitly checks for page cache charges without any
mm context (from kernel thread context[1]).

This seemed to be the only possible case where memory could be charged
without mm context so commit 03583f1a631c ("memcg: remove unnecessary
!mm check from try_get_mem_cgroup_from_mm()") removed the mm check from
get_mem_cgroup_from_mm().  This however caused another NULL ptr
dereference during early boot when loopback kernel thread splices to
tmpfs as reported by Stephan Kulow:

  BUG: unable to handle kernel NULL pointer dereference at 0000000000000360
  IP: get_mem_cgroup_from_mm.isra.42+0x2b/0x60
  Oops: 0000 [#1] SMP
  Modules linked in: btrfs dm_multipath dm_mod scsi_dh multipath raid10 raid456 async_raid6_recov async_memcpy async_pq raid6_pq async_xor xor async_tx raid1 raid0 md_mod parport_pc parport nls_utf8 isofs usb_storage iscsi_ibft iscsi_boot_sysfs arc4 ecb fan thermal nfs lockd fscache nls_iso8859_1 nls_cp437 sg st hid_generic usbhid af_packet sunrpc sr_mod cdrom ata_generic uhci_hcd virtio_net virtio_blk ehci_hcd usbcore ata_piix floppy processor button usb_common virtio_pci virtio_ring virtio edd squashfs loop ppa]
  CPU: 0 PID: 97 Comm: loop1 Not tainted 3.15.0-rc5-5-default #1
  Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
  Call Trace:
    __mem_cgroup_try_charge_swapin+0x40/0xe0
    mem_cgroup_charge_file+0x8b/0xd0
    shmem_getpage_gfp+0x66b/0x7b0
    shmem_file_splice_read+0x18f/0x430
    splice_direct_to_actor+0xa2/0x1c0
    do_lo_receive+0x5a/0x60 [loop]
    loop_thread+0x298/0x720 [loop]
    kthread+0xc6/0xe0
    ret_from_fork+0x7c/0xb0

Also Branimir Maksimovic reported the following oops which is tiggered
for the swapcache charge path from the accounting code for kernel threads:

  CPU: 1 PID: 160 Comm: kworker/u8:5 Tainted: P           OE 3.15.0-rc5-core2-custom #159
  Hardware name: System manufacturer System Product Name/MAXIMUSV GENE, BIOS 1903 08/19/2013
  task: ffff880404e349b0 ti: ffff88040486a000 task.ti: ffff88040486a000
  RIP: get_mem_cgroup_from_mm.isra.42+0x2b/0x60
  Call Trace:
    __mem_cgroup_try_charge_swapin+0x45/0xf0
    mem_cgroup_charge_file+0x9c/0xe0
    shmem_getpage_gfp+0x62c/0x770
    shmem_write_begin+0x38/0x40
    generic_perform_write+0xc5/0x1c0
    __generic_file_aio_write+0x1d1/0x3f0
    generic_file_aio_write+0x4f/0xc0
    do_sync_write+0x5a/0x90
    do_acct_process+0x4b1/0x550
    acct_process+0x6d/0xa0
    do_exit+0x827/0xa70
    kthread+0xc3/0xf0

This patch fixes the issue by reintroducing mm check into
get_mem_cgroup_from_mm.  We could do the same trick in
__mem_cgroup_try_charge_swapin as we do for the regular page cache path
but it is not worth troubles.  The check is not that expensive and it is
better to have get_mem_cgroup_from_mm more robust.

[1] - http://marc.info/?l=linux-mm&m=139463617808941&w=2

Fixes: 03583f1a631c ("memcg: remove unnecessary !mm check from try_get_mem_cgroup_from_mm()")
Reported-and-tested-by: Stephan Kulow <coolo@suse.com>
Reported-by: Branimir Maksimovic <branimir.maksimovic@gmail.com>
Signed-off-by: Michal Hocko <mhocko@suse.cz>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent 55231e5
Raw File
futex_compat.c
/*
 * linux/kernel/futex_compat.c
 *
 * Futex compatibililty routines.
 *
 * Copyright 2006, Red Hat, Inc., Ingo Molnar
 */

#include <linux/linkage.h>
#include <linux/compat.h>
#include <linux/nsproxy.h>
#include <linux/futex.h>
#include <linux/ptrace.h>
#include <linux/syscalls.h>

#include <asm/uaccess.h>


/*
 * Fetch a robust-list pointer. Bit 0 signals PI futexes:
 */
static inline int
fetch_robust_entry(compat_uptr_t *uentry, struct robust_list __user **entry,
		   compat_uptr_t __user *head, unsigned int *pi)
{
	if (get_user(*uentry, head))
		return -EFAULT;

	*entry = compat_ptr((*uentry) & ~1);
	*pi = (unsigned int)(*uentry) & 1;

	return 0;
}

static void __user *futex_uaddr(struct robust_list __user *entry,
				compat_long_t futex_offset)
{
	compat_uptr_t base = ptr_to_compat(entry);
	void __user *uaddr = compat_ptr(base + futex_offset);

	return uaddr;
}

/*
 * Walk curr->robust_list (very carefully, it's a userspace list!)
 * and mark any locks found there dead, and notify any waiters.
 *
 * We silently return on any sign of list-walking problem.
 */
void compat_exit_robust_list(struct task_struct *curr)
{
	struct compat_robust_list_head __user *head = curr->compat_robust_list;
	struct robust_list __user *entry, *next_entry, *pending;
	unsigned int limit = ROBUST_LIST_LIMIT, pi, pip;
	unsigned int uninitialized_var(next_pi);
	compat_uptr_t uentry, next_uentry, upending;
	compat_long_t futex_offset;
	int rc;

	if (!futex_cmpxchg_enabled)
		return;

	/*
	 * Fetch the list head (which was registered earlier, via
	 * sys_set_robust_list()):
	 */
	if (fetch_robust_entry(&uentry, &entry, &head->list.next, &pi))
		return;
	/*
	 * Fetch the relative futex offset:
	 */
	if (get_user(futex_offset, &head->futex_offset))
		return;
	/*
	 * Fetch any possibly pending lock-add first, and handle it
	 * if it exists:
	 */
	if (fetch_robust_entry(&upending, &pending,
			       &head->list_op_pending, &pip))
		return;

	next_entry = NULL;	/* avoid warning with gcc */
	while (entry != (struct robust_list __user *) &head->list) {
		/*
		 * Fetch the next entry in the list before calling
		 * handle_futex_death:
		 */
		rc = fetch_robust_entry(&next_uentry, &next_entry,
			(compat_uptr_t __user *)&entry->next, &next_pi);
		/*
		 * A pending lock might already be on the list, so
		 * dont process it twice:
		 */
		if (entry != pending) {
			void __user *uaddr = futex_uaddr(entry, futex_offset);

			if (handle_futex_death(uaddr, curr, pi))
				return;
		}
		if (rc)
			return;
		uentry = next_uentry;
		entry = next_entry;
		pi = next_pi;
		/*
		 * Avoid excessively long or circular lists:
		 */
		if (!--limit)
			break;

		cond_resched();
	}
	if (pending) {
		void __user *uaddr = futex_uaddr(pending, futex_offset);

		handle_futex_death(uaddr, curr, pip);
	}
}

COMPAT_SYSCALL_DEFINE2(set_robust_list,
		struct compat_robust_list_head __user *, head,
		compat_size_t, len)
{
	if (!futex_cmpxchg_enabled)
		return -ENOSYS;

	if (unlikely(len != sizeof(*head)))
		return -EINVAL;

	current->compat_robust_list = head;

	return 0;
}

COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid,
			compat_uptr_t __user *, head_ptr,
			compat_size_t __user *, len_ptr)
{
	struct compat_robust_list_head __user *head;
	unsigned long ret;
	struct task_struct *p;

	if (!futex_cmpxchg_enabled)
		return -ENOSYS;

	rcu_read_lock();

	ret = -ESRCH;
	if (!pid)
		p = current;
	else {
		p = find_task_by_vpid(pid);
		if (!p)
			goto err_unlock;
	}

	ret = -EPERM;
	if (!ptrace_may_access(p, PTRACE_MODE_READ))
		goto err_unlock;

	head = p->compat_robust_list;
	rcu_read_unlock();

	if (put_user(sizeof(*head), len_ptr))
		return -EFAULT;
	return put_user(ptr_to_compat(head), head_ptr);

err_unlock:
	rcu_read_unlock();

	return ret;
}

COMPAT_SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val,
		struct compat_timespec __user *, utime, u32 __user *, uaddr2,
		u32, val3)
{
	struct timespec ts;
	ktime_t t, *tp = NULL;
	int val2 = 0;
	int cmd = op & FUTEX_CMD_MASK;

	if (utime && (cmd == FUTEX_WAIT || cmd == FUTEX_LOCK_PI ||
		      cmd == FUTEX_WAIT_BITSET ||
		      cmd == FUTEX_WAIT_REQUEUE_PI)) {
		if (compat_get_timespec(&ts, utime))
			return -EFAULT;
		if (!timespec_valid(&ts))
			return -EINVAL;

		t = timespec_to_ktime(ts);
		if (cmd == FUTEX_WAIT)
			t = ktime_add_safe(ktime_get(), t);
		tp = &t;
	}
	if (cmd == FUTEX_REQUEUE || cmd == FUTEX_CMP_REQUEUE ||
	    cmd == FUTEX_CMP_REQUEUE_PI || cmd == FUTEX_WAKE_OP)
		val2 = (int) (unsigned long) utime;

	return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
}
back to top