Hello,
The following program:
// autogenerated by syzkaller (http://github.com/google/syzkaller)
#include <syscall.h>
#include <string.h>
#include <stdint.h>
#include <pthread.h>
#define SYS_memfd_create 319
long fd;
void *thr(void *p)
{
syscall(SYS_ftruncate, fd, 0x8ul, 0, 0, 0, 0);
return 0;
}
int main()
{
pthread_t th;
syscall(SYS_mmap, 0x20000000ul, 0x10000ul, 0x3ul, 0x32ul,
0xfffffffffffffffful, 0x0ul);
memcpy((void*)0x20000f96, "\x23\x65\x6d\x31\x07\x2b\x27\x29\x00", 9);
fd = syscall(SYS_memfd_create, 0x20000f96ul, 0x2ul, 0, 0, 0, 0);
syscall(SYS_fallocate, fd, 0x0ul, 0x31d89288ul, 0x4ul, 0, 0);
syscall(SYS_mmap, 0x20061000ul, 0xc00000ul,
0x1a9d91e04768640bul, 0x11ul, fd, 0x0ul);
pthread_create(&th, 0, thr, 0);
syscall(SYS_fstat, fd, 0x20550fcful, 0, 0, 0, 0);
pthread_join(th, 0);
return 0;
}
triggers WARNING in shmem_evict_inode:
------------[ cut here ]------------
WARNING: CPU: 0 PID: 10442 at mm/shmem.c:625 shmem_evict_inode+0x335/0x480()
Modules linked in:
CPU: 1 PID: 8944 Comm: executor Not tainted 4.3.0+ #39
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
00000000ffffffff ffff88006c6afab8 ffffffff81aad406 0000000000000000
ffff88006e39ac80 ffffffff83091660 ffff88006c6afaf8 ffffffff81100829
ffffffff814192e5 ffffffff83091660 0000000000000271 ffff88003d075aa8
Call Trace:
[<ffffffff81100a59>] warn_slowpath_null+0x29/0x30 kernel/panic.c:480
[<ffffffff814192e5>] shmem_evict_inode+0x335/0x480 mm/shmem.c:625
[<ffffffff8151560e>] evict+0x26e/0x580 fs/inode.c:542
[< inline >] iput_final fs/inode.c:1477
[<ffffffff81515f30>] iput+0x4a0/0x790 fs/inode.c:1504
[< inline >] dentry_iput fs/dcache.c:358
[<ffffffff8150667e>] __dentry_kill+0x4fe/0x700 fs/dcache.c:543
[< inline >] dentry_kill fs/dcache.c:587
[<ffffffff8150be7b>] dput+0x6ab/0x7a0 fs/dcache.c:796
[<ffffffff814c499b>] __fput+0x3fb/0x6e0 fs/file_table.c:226
[<ffffffff814c4d05>] ____fput+0x15/0x20 fs/file_table.c:244
[<ffffffff8115ab23>] task_work_run+0x163/0x1f0 kernel/task_work.c:115
[< inline >] exit_task_work include/linux/task_work.h:21
[<ffffffff81105049>] do_exit+0x7f9/0x2b80 kernel/exit.c:748
[<ffffffff8110b268>] do_group_exit+0x108/0x320 kernel/exit.c:878
[< inline >] SYSC_exit_group kernel/exit.c:889
[<ffffffff8110b49d>] SyS_exit_group+0x1d/0x20 kernel/exit.c:887
---[ end trace 43da88a03e29c2a5 ]---
Run the program in a loop, as the WARNING seems to be triggered by a race.
On commit d1e41ff11941784f469f17795a4d9425c2eb4b7a (Nov 5).
But I was also able to reproduce it on a 3.11-based kernel.
On Mon, Nov 9, 2015 at 9:55 AM, Dmitry Vyukov <[email protected]> wrote:
> Hello,
>
> The following program:
>
> // autogenerated by syzkaller (http://github.com/google/syzkaller)
> #include <syscall.h>
> #include <string.h>
> #include <stdint.h>
> #include <pthread.h>
>
> #define SYS_memfd_create 319
>
> long fd;
>
> void *thr(void *p)
> {
> syscall(SYS_ftruncate, fd, 0x8ul, 0, 0, 0, 0);
> return 0;
> }
>
> int main()
> {
> pthread_t th;
>
> syscall(SYS_mmap, 0x20000000ul, 0x10000ul, 0x3ul, 0x32ul,
> 0xfffffffffffffffful, 0x0ul);
> memcpy((void*)0x20000f96, "\x23\x65\x6d\x31\x07\x2b\x27\x29\x00", 9);
> fd = syscall(SYS_memfd_create, 0x20000f96ul, 0x2ul, 0, 0, 0, 0);
> syscall(SYS_fallocate, fd, 0x0ul, 0x31d89288ul, 0x4ul, 0, 0);
> syscall(SYS_mmap, 0x20061000ul, 0xc00000ul,
> 0x1a9d91e04768640bul, 0x11ul, fd, 0x0ul);
> pthread_create(&th, 0, thr, 0);
> syscall(SYS_fstat, fd, 0x20550fcful, 0, 0, 0, 0);
> pthread_join(th, 0);
> return 0;
> }
>
>
> triggers WARNING in shmem_evict_inode:
>
> ------------[ cut here ]------------
> WARNING: CPU: 0 PID: 10442 at mm/shmem.c:625 shmem_evict_inode+0x335/0x480()
> Modules linked in:
> CPU: 1 PID: 8944 Comm: executor Not tainted 4.3.0+ #39
> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
> 00000000ffffffff ffff88006c6afab8 ffffffff81aad406 0000000000000000
> ffff88006e39ac80 ffffffff83091660 ffff88006c6afaf8 ffffffff81100829
> ffffffff814192e5 ffffffff83091660 0000000000000271 ffff88003d075aa8
> Call Trace:
> [<ffffffff81100a59>] warn_slowpath_null+0x29/0x30 kernel/panic.c:480
> [<ffffffff814192e5>] shmem_evict_inode+0x335/0x480 mm/shmem.c:625
> [<ffffffff8151560e>] evict+0x26e/0x580 fs/inode.c:542
> [< inline >] iput_final fs/inode.c:1477
> [<ffffffff81515f30>] iput+0x4a0/0x790 fs/inode.c:1504
> [< inline >] dentry_iput fs/dcache.c:358
> [<ffffffff8150667e>] __dentry_kill+0x4fe/0x700 fs/dcache.c:543
> [< inline >] dentry_kill fs/dcache.c:587
> [<ffffffff8150be7b>] dput+0x6ab/0x7a0 fs/dcache.c:796
> [<ffffffff814c499b>] __fput+0x3fb/0x6e0 fs/file_table.c:226
> [<ffffffff814c4d05>] ____fput+0x15/0x20 fs/file_table.c:244
> [<ffffffff8115ab23>] task_work_run+0x163/0x1f0 kernel/task_work.c:115
> [< inline >] exit_task_work include/linux/task_work.h:21
> [<ffffffff81105049>] do_exit+0x7f9/0x2b80 kernel/exit.c:748
> [<ffffffff8110b268>] do_group_exit+0x108/0x320 kernel/exit.c:878
> [< inline >] SYSC_exit_group kernel/exit.c:889
> [<ffffffff8110b49d>] SyS_exit_group+0x1d/0x20 kernel/exit.c:887
> ---[ end trace 43da88a03e29c2a5 ]---
>
>
> Run the program in a loop, as the WARNING seems to be triggered by a race.
>
> On commit d1e41ff11941784f469f17795a4d9425c2eb4b7a (Nov 5).
> But I was also able to reproduce it on a 3.11-based kernel.
Hello,
This is still happening periodically for me. Is anybody looking at this?
On Mon, 23 Nov 2015, Dmitry Vyukov wrote:
> On Mon, Nov 9, 2015 at 9:55 AM, Dmitry Vyukov <[email protected]> wrote:
> > Hello,
> >
> > The following program:
> >
> > // autogenerated by syzkaller (http://github.com/google/syzkaller)
> > #include <syscall.h>
> > #include <string.h>
> > #include <stdint.h>
> > #include <pthread.h>
> >
> > #define SYS_memfd_create 319
> >
> > long fd;
> >
> > void *thr(void *p)
> > {
> > syscall(SYS_ftruncate, fd, 0x8ul, 0, 0, 0, 0);
> > return 0;
> > }
> >
> > int main()
> > {
> > pthread_t th;
> >
> > syscall(SYS_mmap, 0x20000000ul, 0x10000ul, 0x3ul, 0x32ul,
> > 0xfffffffffffffffful, 0x0ul);
> > memcpy((void*)0x20000f96, "\x23\x65\x6d\x31\x07\x2b\x27\x29\x00", 9);
> > fd = syscall(SYS_memfd_create, 0x20000f96ul, 0x2ul, 0, 0, 0, 0);
> > syscall(SYS_fallocate, fd, 0x0ul, 0x31d89288ul, 0x4ul, 0, 0);
> > syscall(SYS_mmap, 0x20061000ul, 0xc00000ul,
> > 0x1a9d91e04768640bul, 0x11ul, fd, 0x0ul);
> > pthread_create(&th, 0, thr, 0);
> > syscall(SYS_fstat, fd, 0x20550fcful, 0, 0, 0, 0);
> > pthread_join(th, 0);
> > return 0;
> > }
> >
> >
> > triggers WARNING in shmem_evict_inode:
> >
> > ------------[ cut here ]------------
> > WARNING: CPU: 0 PID: 10442 at mm/shmem.c:625 shmem_evict_inode+0x335/0x480()
> > Modules linked in:
> > CPU: 1 PID: 8944 Comm: executor Not tainted 4.3.0+ #39
> > Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
> > 00000000ffffffff ffff88006c6afab8 ffffffff81aad406 0000000000000000
> > ffff88006e39ac80 ffffffff83091660 ffff88006c6afaf8 ffffffff81100829
> > ffffffff814192e5 ffffffff83091660 0000000000000271 ffff88003d075aa8
> > Call Trace:
> > [<ffffffff81100a59>] warn_slowpath_null+0x29/0x30 kernel/panic.c:480
> > [<ffffffff814192e5>] shmem_evict_inode+0x335/0x480 mm/shmem.c:625
> > [<ffffffff8151560e>] evict+0x26e/0x580 fs/inode.c:542
> > [< inline >] iput_final fs/inode.c:1477
> > [<ffffffff81515f30>] iput+0x4a0/0x790 fs/inode.c:1504
> > [< inline >] dentry_iput fs/dcache.c:358
> > [<ffffffff8150667e>] __dentry_kill+0x4fe/0x700 fs/dcache.c:543
> > [< inline >] dentry_kill fs/dcache.c:587
> > [<ffffffff8150be7b>] dput+0x6ab/0x7a0 fs/dcache.c:796
> > [<ffffffff814c499b>] __fput+0x3fb/0x6e0 fs/file_table.c:226
> > [<ffffffff814c4d05>] ____fput+0x15/0x20 fs/file_table.c:244
> > [<ffffffff8115ab23>] task_work_run+0x163/0x1f0 kernel/task_work.c:115
> > [< inline >] exit_task_work include/linux/task_work.h:21
> > [<ffffffff81105049>] do_exit+0x7f9/0x2b80 kernel/exit.c:748
> > [<ffffffff8110b268>] do_group_exit+0x108/0x320 kernel/exit.c:878
> > [< inline >] SYSC_exit_group kernel/exit.c:889
> > [<ffffffff8110b49d>] SyS_exit_group+0x1d/0x20 kernel/exit.c:887
> > ---[ end trace 43da88a03e29c2a5 ]---
> >
> >
> > Run the program in a loop, as the WARNING seems to be triggered by a race.
> >
> > On commit d1e41ff11941784f469f17795a4d9425c2eb4b7a (Nov 5).
> > But I was also able to reproduce it on a 3.11-based kernel.
>
>
> Hello,
>
> This is still happening periodically for me. Is anybody looking at this?
It was more interesting than I expected, thanks.
I believe you will find that this fixes it.
[PATCH] tmpfs: fix shmem_evict_inode warnings on i_blocks
Dmitry Vyukov provides a little program, autogenerated by syzkaller,
which races a fault on a mapping of a sparse memfd object, against
truncation of that object below the fault address: run repeatedly
for a few minutes, it reliably generates shmem_evict_inode()'s
WARN_ON(inode->i_blocks).
(But there's nothing specific to memfd here, nor to the fstat which it
happened to use to generate the fault: though that looked suspicious,
since a shmem_recalc_inode() had been added there recently. The same
problem can be reproduced with open+unlink in place of memfd_create,
and with fstatfs in place of fstat.)
v3.7 commit 0f3c42f522dc ("tmpfs: change final i_blocks BUG to WARNING")
explains one cause of such a warning (a race with shmem_writepage to swap),
and possible solutions; but we never took it further, and this syzkaller
incident turns out to have a different cause.
shmem_getpage_gfp()'s error recovery, when a freshly allocated page is
then found to be beyond eof, looks plausible - decrementing the alloced
count that was just before incremented - but in fact can go wrong, if a
racing thread (the truncator, for example) gets its shmem_recalc_inode()
in just after our delete_from_page_cache(). delete_from_page_cache()
decrements nrpages, that shmem_recalc_inode() will balance the books
by decrementing alloced itself, then our decrement of alloced take it
one too low: leading to the WARNING when the object is finally evicted.
Once the new page has been exposed in the page cache, shmem_getpage_gfp()
must leave it to shmem_recalc_inode() itself to get the accounting right
in all cases (and not fall through from "trunc:" to "decused:"). Adjust
that error recovery block; and the reinitialization of info and sbinfo
can be removed too.
While we're here, fix shmem_writepage() to avoid the original issue:
it will be safe against a racing shmem_recalc_inode(), if it merely
increments swapped before the shmem_delete_from_page_cache() which
decrements nrpages (but it must then do its own shmem_recalc_inode()
before that, while still in balance, instead of after). (Aside: why
do we shmem_recalc_inode() here in the swap path? Because its raison
d'etre is to cope with clean sparse shmem pages being reclaimed behind
our back: so here when swapping is a good place to look for that case.)
But I've not now managed to reproduce this bug, even without the patch.
I don't see why I didn't do that earlier: perhaps inhibited by the
preference to eliminate shmem_recalc_inode() altogether. Driven by this
incident, I do now have a patch to do so at last; but still want to sit
on it for a bit, there's a couple of questions yet to be resolved.
Reported-by: Dmitry Vyukov <[email protected]>
Signed-off-by: Hugh Dickins <[email protected]>
---
Cc stable? I don't think that's necessary, but might be proved wrong:
along with the warning, the bug does allow one page beyond the limit
to be allocated from a size-limited tmpfs mount.
mm/shmem.c | 34 ++++++++++++++--------------------
1 file changed, 14 insertions(+), 20 deletions(-)
--- 4.4-rc3/mm/shmem.c 2015-11-15 21:06:56.513752469 -0800
+++ linux/mm/shmem.c 2015-11-30 17:38:42.337790242 -0800
@@ -843,14 +843,14 @@ static int shmem_writepage(struct page *
list_add_tail(&info->swaplist, &shmem_swaplist);
if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
- swap_shmem_alloc(swap);
- shmem_delete_from_page_cache(page, swp_to_radix_entry(swap));
-
spin_lock(&info->lock);
- info->swapped++;
shmem_recalc_inode(inode);
+ info->swapped++;
spin_unlock(&info->lock);
+ swap_shmem_alloc(swap);
+ shmem_delete_from_page_cache(page, swp_to_radix_entry(swap));
+
mutex_unlock(&shmem_swaplist_mutex);
BUG_ON(page_mapped(page));
swap_writepage(page, wbc);
@@ -1078,7 +1078,7 @@ repeat:
if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&
((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
error = -EINVAL;
- goto failed;
+ goto unlock;
}
if (page && sgp == SGP_WRITE)
@@ -1246,11 +1246,15 @@ clear:
/* Perhaps the file has been truncated since we checked */
if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&
((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
+ if (alloced) {
+ ClearPageDirty(page);
+ delete_from_page_cache(page);
+ spin_lock(&info->lock);
+ shmem_recalc_inode(inode);
+ spin_unlock(&info->lock);
+ }
error = -EINVAL;
- if (alloced)
- goto trunc;
- else
- goto failed;
+ goto unlock;
}
*pagep = page;
return 0;
@@ -1258,23 +1262,13 @@ clear:
/*
* Error recovery.
*/
-trunc:
- info = SHMEM_I(inode);
- ClearPageDirty(page);
- delete_from_page_cache(page);
- spin_lock(&info->lock);
- info->alloced--;
- inode->i_blocks -= BLOCKS_PER_PAGE;
- spin_unlock(&info->lock);
decused:
- sbinfo = SHMEM_SB(inode->i_sb);
if (sbinfo->max_blocks)
percpu_counter_add(&sbinfo->used_blocks, -1);
unacct:
shmem_unacct_blocks(info->flags, 1);
failed:
- if (swap.val && error != -EINVAL &&
- !shmem_confirm_swap(mapping, index, swap))
+ if (swap.val && !shmem_confirm_swap(mapping, index, swap))
error = -EEXIST;
unlock:
if (page) {
On 12/02/15 10:29, Hugh Dickins wrote:
> On Mon, 23 Nov 2015, Dmitry Vyukov wrote:
>> On Mon, Nov 9, 2015 at 9:55 AM, Dmitry Vyukov <[email protected]> wrote:
[snip]
>>> triggers WARNING in shmem_evict_inode:
>>>
>>> ------------[ cut here ]------------
>>> WARNING: CPU: 0 PID: 10442 at mm/shmem.c:625 shmem_evict_inode+0x335/0x480()
>>> Modules linked in:
>>> CPU: 1 PID: 8944 Comm: executor Not tainted 4.3.0+ #39
>>> Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011
>>> 00000000ffffffff ffff88006c6afab8 ffffffff81aad406 0000000000000000
>>> ffff88006e39ac80 ffffffff83091660 ffff88006c6afaf8 ffffffff81100829
>>> ffffffff814192e5 ffffffff83091660 0000000000000271 ffff88003d075aa8
>>> Call Trace:
>>> [<ffffffff81100a59>] warn_slowpath_null+0x29/0x30 kernel/panic.c:480
>>> [<ffffffff814192e5>] shmem_evict_inode+0x335/0x480 mm/shmem.c:625
>>> [<ffffffff8151560e>] evict+0x26e/0x580 fs/inode.c:542
>>> [< inline >] iput_final fs/inode.c:1477
[snip]
> It was more interesting than I expected, thanks.
> I believe you will find that this fixes it.
>
> [PATCH] tmpfs: fix shmem_evict_inode warnings on i_blocks
Since I just saw this in Linus' tree, here's another retrospective bug
report and Thank You for fixing it. :-)
The problem is quite real, even though I'm probably the only other person
to ever report it, see: http://www.spinics.net/lists/linux-fsdevel/msg83567.html
> Cc stable? I don't think that's necessary, but might be proved wrong:
> along with the warning, the bug does allow one page beyond the limit
> to be allocated from a size-limited tmpfs mount.
It applies and works fine, so it probably wouldn't hurt. I'm using it in my
4.1++ tree as we speak, no problems.
-h