[v2] Btrfs: fix out of bounds array access while reading extent buffer
diff mbox

Message ID 20170809163114.19539-1-bo.li.liu@oracle.com
State New
Headers show

Commit Message

Liu Bo Aug. 9, 2017, 4:31 p.m. UTC
There is a cornel case that slip through the checkers in functions
reading extent buffer, ie.

if (start < eb->len) and (start + len > eb->len),
then

a) map_private_extent_buffer() returns immediately because
it's thinking the range spans across two pages,

b) and the checkers in read_extent_buffer(), WARN_ON(start > eb->len)
and WARN_ON(start + len > eb->start + eb->len), both are OK in this
corner case, but it'd actually try to access the eb->pages out of
bounds because of (start + len > eb->len).

The case is found by switching extent inline ref type from shared data
ref to non-shared data ref, which is a kind of metadata corruption.

It'd use the wrong helper to access the eb,
eg. btrfs_extent_data_ref_root(eb, ref) is used but the %ref passing
here is "struct btrfs_shared_data_ref".  And if the extent item
happens to be the first item in the eb, then offset/length will get
over eb->len which ends up an invalid memory access.

This is adding proper checks in order to avoid invalid memory access,
ie. 'general protection fault', before it's too late.

Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
---

v2: Improve the commit log to clarify that this can only happen if
metadata is corrupted.

 fs/btrfs/extent_io.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

Comments

Filipe Manana Aug. 9, 2017, 5:35 p.m. UTC | #1
On Wed, Aug 9, 2017 at 5:31 PM, Liu Bo <bo.li.liu@oracle.com> wrote:
> There is a cornel case that slip through the checkers in functions
> reading extent buffer, ie.
>
> if (start < eb->len) and (start + len > eb->len),
> then
>
> a) map_private_extent_buffer() returns immediately because
> it's thinking the range spans across two pages,
>
> b) and the checkers in read_extent_buffer(), WARN_ON(start > eb->len)
> and WARN_ON(start + len > eb->start + eb->len), both are OK in this
> corner case, but it'd actually try to access the eb->pages out of
> bounds because of (start + len > eb->len).
>
> The case is found by switching extent inline ref type from shared data
> ref to non-shared data ref, which is a kind of metadata corruption.
>
> It'd use the wrong helper to access the eb,
> eg. btrfs_extent_data_ref_root(eb, ref) is used but the %ref passing
> here is "struct btrfs_shared_data_ref".  And if the extent item
> happens to be the first item in the eb, then offset/length will get
> over eb->len which ends up an invalid memory access.
>
> This is adding proper checks in order to avoid invalid memory access,
> ie. 'general protection fault', before it's too late.
>
> Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>

> ---
>
> v2: Improve the commit log to clarify that this can only happen if
> metadata is corrupted.

Thanks for adding the clarification!

>
>  fs/btrfs/extent_io.c | 22 ++++++++++++++--------
>  1 file changed, 14 insertions(+), 8 deletions(-)
>
> diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
> index 0aff9b2..d198e87 100644
> --- a/fs/btrfs/extent_io.c
> +++ b/fs/btrfs/extent_io.c
> @@ -5416,13 +5416,19 @@ void read_extent_buffer(struct extent_buffer *eb, void *dstv,
>         char *dst = (char *)dstv;
>         size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
>         unsigned long i = (start_offset + start) >> PAGE_SHIFT;
> +       unsigned long num_pages = num_extent_pages(eb->start, eb->len);
>
> -       WARN_ON(start > eb->len);
> -       WARN_ON(start + len > eb->start + eb->len);
> +       if (start + len > eb->len) {
> +               WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n",
> +                    eb->start, eb->len, start, len);
> +               memset(dst, 0, len);
> +               return;
> +       }
>
>         offset = (start_offset + start) & (PAGE_SIZE - 1);
>
>         while (len > 0) {
> +               ASSERT(i < num_pages);
>                 page = eb->pages[i];
>
>                 cur = min(len, (PAGE_SIZE - offset));
> @@ -5491,6 +5497,12 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
>         unsigned long end_i = (start_offset + start + min_len - 1) >>
>                 PAGE_SHIFT;
>
> +       if (start + min_len > eb->len) {
> +               WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n",
> +                      eb->start, eb->len, start, min_len);
> +               return -EINVAL;
> +       }
> +
>         if (i != end_i)
>                 return 1;
>
> @@ -5502,12 +5514,6 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
>                 *map_start = ((u64)i << PAGE_SHIFT) - start_offset;
>         }
>
> -       if (start + min_len > eb->len) {
> -               WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n",
> -                      eb->start, eb->len, start, min_len);
> -               return -EINVAL;
> -       }
> -
>         p = eb->pages[i];
>         kaddr = page_address(p);
>         *map = kaddr + offset;
> --
> 2.9.4
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
Filipe Manana Aug. 9, 2017, 5:40 p.m. UTC | #2
On Wed, Aug 9, 2017 at 5:31 PM, Liu Bo <bo.li.liu@oracle.com> wrote:
> There is a cornel case that slip through the checkers in functions
> reading extent buffer, ie.
>
> if (start < eb->len) and (start + len > eb->len),
> then
>
> a) map_private_extent_buffer() returns immediately because
> it's thinking the range spans across two pages,
>
> b) and the checkers in read_extent_buffer(), WARN_ON(start > eb->len)
> and WARN_ON(start + len > eb->start + eb->len), both are OK in this
> corner case, but it'd actually try to access the eb->pages out of
> bounds because of (start + len > eb->len).
>
> The case is found by switching extent inline ref type from shared data
> ref to non-shared data ref, which is a kind of metadata corruption.
>
> It'd use the wrong helper to access the eb,
> eg. btrfs_extent_data_ref_root(eb, ref) is used but the %ref passing
> here is "struct btrfs_shared_data_ref".  And if the extent item
> happens to be the first item in the eb, then offset/length will get
> over eb->len which ends up an invalid memory access.
>
> This is adding proper checks in order to avoid invalid memory access,
> ie. 'general protection fault', before it's too late.
>
> Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
> ---
>
> v2: Improve the commit log to clarify that this can only happen if
> metadata is corrupted.
>
>  fs/btrfs/extent_io.c | 22 ++++++++++++++--------
>  1 file changed, 14 insertions(+), 8 deletions(-)
>
> diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
> index 0aff9b2..d198e87 100644
> --- a/fs/btrfs/extent_io.c
> +++ b/fs/btrfs/extent_io.c
> @@ -5416,13 +5416,19 @@ void read_extent_buffer(struct extent_buffer *eb, void *dstv,
>         char *dst = (char *)dstv;
>         size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
>         unsigned long i = (start_offset + start) >> PAGE_SHIFT;
> +       unsigned long num_pages = num_extent_pages(eb->start, eb->len);

Forgot to note that if CONFIG_BTRFS_ASSERT is not set, this variable
is unused and the compiler and static checkers will emit a warning.
Other than that all looks fine. Thanks.

>
> -       WARN_ON(start > eb->len);
> -       WARN_ON(start + len > eb->start + eb->len);
> +       if (start + len > eb->len) {
> +               WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n",
> +                    eb->start, eb->len, start, len);
> +               memset(dst, 0, len);
> +               return;
> +       }
>
>         offset = (start_offset + start) & (PAGE_SIZE - 1);
>
>         while (len > 0) {
> +               ASSERT(i < num_pages);
>                 page = eb->pages[i];
>
>                 cur = min(len, (PAGE_SIZE - offset));
> @@ -5491,6 +5497,12 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
>         unsigned long end_i = (start_offset + start + min_len - 1) >>
>                 PAGE_SHIFT;
>
> +       if (start + min_len > eb->len) {
> +               WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n",
> +                      eb->start, eb->len, start, min_len);
> +               return -EINVAL;
> +       }
> +
>         if (i != end_i)
>                 return 1;
>
> @@ -5502,12 +5514,6 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
>                 *map_start = ((u64)i << PAGE_SHIFT) - start_offset;
>         }
>
> -       if (start + min_len > eb->len) {
> -               WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n",
> -                      eb->start, eb->len, start, min_len);
> -               return -EINVAL;
> -       }
> -
>         p = eb->pages[i];
>         kaddr = page_address(p);
>         *map = kaddr + offset;
> --
> 2.9.4
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
Liu Bo Aug. 9, 2017, 6:03 p.m. UTC | #3
On Wed, Aug 09, 2017 at 06:40:04PM +0100, Filipe Manana wrote:
> On Wed, Aug 9, 2017 at 5:31 PM, Liu Bo <bo.li.liu@oracle.com> wrote:
> > There is a cornel case that slip through the checkers in functions
> > reading extent buffer, ie.
> >
> > if (start < eb->len) and (start + len > eb->len),
> > then
> >
> > a) map_private_extent_buffer() returns immediately because
> > it's thinking the range spans across two pages,
> >
> > b) and the checkers in read_extent_buffer(), WARN_ON(start > eb->len)
> > and WARN_ON(start + len > eb->start + eb->len), both are OK in this
> > corner case, but it'd actually try to access the eb->pages out of
> > bounds because of (start + len > eb->len).
> >
> > The case is found by switching extent inline ref type from shared data
> > ref to non-shared data ref, which is a kind of metadata corruption.
> >
> > It'd use the wrong helper to access the eb,
> > eg. btrfs_extent_data_ref_root(eb, ref) is used but the %ref passing
> > here is "struct btrfs_shared_data_ref".  And if the extent item
> > happens to be the first item in the eb, then offset/length will get
> > over eb->len which ends up an invalid memory access.
> >
> > This is adding proper checks in order to avoid invalid memory access,
> > ie. 'general protection fault', before it's too late.
> >
> > Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
> > ---
> >
> > v2: Improve the commit log to clarify that this can only happen if
> > metadata is corrupted.
> >
> >  fs/btrfs/extent_io.c | 22 ++++++++++++++--------
> >  1 file changed, 14 insertions(+), 8 deletions(-)
> >
> > diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
> > index 0aff9b2..d198e87 100644
> > --- a/fs/btrfs/extent_io.c
> > +++ b/fs/btrfs/extent_io.c
> > @@ -5416,13 +5416,19 @@ void read_extent_buffer(struct extent_buffer *eb, void *dstv,
> >         char *dst = (char *)dstv;
> >         size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
> >         unsigned long i = (start_offset + start) >> PAGE_SHIFT;
> > +       unsigned long num_pages = num_extent_pages(eb->start, eb->len);
> 
> Forgot to note that if CONFIG_BTRFS_ASSERT is not set, this variable
> is unused and the compiler and static checkers will emit a warning.
> Other than that all looks fine. Thanks.
>

True, then lets remove it, I don't think we could reach that ASSERT if
(start + len > eb->len).

thanks,

-liubo

> >
> > -       WARN_ON(start > eb->len);
> > -       WARN_ON(start + len > eb->start + eb->len);
> > +       if (start + len > eb->len) {
> > +               WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n",
> > +                    eb->start, eb->len, start, len);
> > +               memset(dst, 0, len);
> > +               return;
> > +       }
> >
> >         offset = (start_offset + start) & (PAGE_SIZE - 1);
> >
> >         while (len > 0) {
> > +               ASSERT(i < num_pages);
> >                 page = eb->pages[i];
> >
> >                 cur = min(len, (PAGE_SIZE - offset));
> > @@ -5491,6 +5497,12 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
> >         unsigned long end_i = (start_offset + start + min_len - 1) >>
> >                 PAGE_SHIFT;
> >
> > +       if (start + min_len > eb->len) {
> > +               WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n",
> > +                      eb->start, eb->len, start, min_len);
> > +               return -EINVAL;
> > +       }
> > +
> >         if (i != end_i)
> >                 return 1;
> >
> > @@ -5502,12 +5514,6 @@ int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
> >                 *map_start = ((u64)i << PAGE_SHIFT) - start_offset;
> >         }
> >
> > -       if (start + min_len > eb->len) {
> > -               WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n",
> > -                      eb->start, eb->len, start, min_len);
> > -               return -EINVAL;
> > -       }
> > -
> >         p = eb->pages[i];
> >         kaddr = page_address(p);
> >         *map = kaddr + offset;
> > --
> > 2.9.4
> >
> > --
> > To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
> > the body of a message to majordomo@vger.kernel.org
> > More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 
> 
> 
> -- 
> Filipe David Manana,
> 
> “Whether you think you can, or you think you can't — you're right.”
> --
> To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch
diff mbox

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 0aff9b2..d198e87 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -5416,13 +5416,19 @@  void read_extent_buffer(struct extent_buffer *eb, void *dstv,
 	char *dst = (char *)dstv;
 	size_t start_offset = eb->start & ((u64)PAGE_SIZE - 1);
 	unsigned long i = (start_offset + start) >> PAGE_SHIFT;
+	unsigned long num_pages = num_extent_pages(eb->start, eb->len);
 
-	WARN_ON(start > eb->len);
-	WARN_ON(start + len > eb->start + eb->len);
+	if (start + len > eb->len) {
+		WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n",
+		     eb->start, eb->len, start, len);
+		memset(dst, 0, len);
+		return;
+	}
 
 	offset = (start_offset + start) & (PAGE_SIZE - 1);
 
 	while (len > 0) {
+		ASSERT(i < num_pages);
 		page = eb->pages[i];
 
 		cur = min(len, (PAGE_SIZE - offset));
@@ -5491,6 +5497,12 @@  int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 	unsigned long end_i = (start_offset + start + min_len - 1) >>
 		PAGE_SHIFT;
 
+	if (start + min_len > eb->len) {
+		WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n",
+		       eb->start, eb->len, start, min_len);
+		return -EINVAL;
+	}
+
 	if (i != end_i)
 		return 1;
 
@@ -5502,12 +5514,6 @@  int map_private_extent_buffer(struct extent_buffer *eb, unsigned long start,
 		*map_start = ((u64)i << PAGE_SHIFT) - start_offset;
 	}
 
-	if (start + min_len > eb->len) {
-		WARN(1, KERN_ERR "btrfs bad mapping eb start %llu len %lu, wanted %lu %lu\n",
-		       eb->start, eb->len, start, min_len);
-		return -EINVAL;
-	}
-
 	p = eb->pages[i];
 	kaddr = page_address(p);
 	*map = kaddr + offset;