In case of flex_bg feature (which is by default enabled), extents for
any given inode might span across blocks from two different block group.
ext4_mb_mark_bb() only reads the buffer_head of block bitmap once for the
starting block group, but it fails to read it again when the extent length
boundary overflows to another block group. Then in this below loop it
accesses memory beyond the block group bitmap buffer_head and results
into a data abort.
for (i = 0; i < clen; i++)
if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state)
already++;
This patch adds this functionality for checking block group boundary in
ext4_mb_mark_bb() and update the buffer_head(bitmap_bh) for every different
block group.
w/o this patch, I was easily able to hit a data access abort using Power platform.
<...>
[ 74.327662] EXT4-fs error (device loop3): ext4_mb_generate_buddy:1141: group 11, block bitmap and bg descriptor inconsistent: 21248 vs 23294 free clusters
[ 74.533214] EXT4-fs (loop3): shut down requested (2)
[ 74.536705] Aborting journal on device loop3-8.
[ 74.702705] BUG: Unable to handle kernel data access on read at 0xc00000005e980000
[ 74.703727] Faulting instruction address: 0xc0000000007bffb8
cpu 0xd: Vector: 300 (Data Access) at [c000000015db7060]
pc: c0000000007bffb8: ext4_mb_mark_bb+0x198/0x5a0
lr: c0000000007bfeec: ext4_mb_mark_bb+0xcc/0x5a0
sp: c000000015db7300
msr: 800000000280b033
dar: c00000005e980000
dsisr: 40000000
current = 0xc000000027af6880
paca = 0xc00000003ffd5200 irqmask: 0x03 irq_happened: 0x01
pid = 5167, comm = mount
<...>
enter ? for help
[c000000015db7380] c000000000782708 ext4_ext_clear_bb+0x378/0x410
[c000000015db7400] c000000000813f14 ext4_fc_replay+0x1794/0x2000
[c000000015db7580] c000000000833f7c do_one_pass+0xe9c/0x12a0
[c000000015db7710] c000000000834504 jbd2_journal_recover+0x184/0x2d0
[c000000015db77c0] c000000000841398 jbd2_journal_load+0x188/0x4a0
[c000000015db7880] c000000000804de8 ext4_fill_super+0x2638/0x3e10
[c000000015db7a40] c0000000005f8404 get_tree_bdev+0x2b4/0x350
[c000000015db7ae0] c0000000007ef058 ext4_get_tree+0x28/0x40
[c000000015db7b00] c0000000005f6344 vfs_get_tree+0x44/0x100
[c000000015db7b70] c00000000063c408 path_mount+0xdd8/0xe70
[c000000015db7c40] c00000000063c8f0 sys_mount+0x450/0x550
[c000000015db7d50] c000000000035770 system_call_exception+0x4a0/0x4e0
[c000000015db7e10] c00000000000c74c system_call_common+0xec/0x250
--- Exception: c00 (System Call) at 00007ffff7dbfaa4
Fixes: 8016e29f4362e28 ("ext4: fast commit recovery path")
Signed-off-by: Ritesh Harjani <[email protected]>
---
fs/ext4/mballoc.c | 30 +++++++++++++++++++++++++++---
1 file changed, 27 insertions(+), 3 deletions(-)
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index c781974df9d0..8d23108cf9d7 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3899,12 +3899,29 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_group_t group;
ext4_grpblk_t blkoff;
- int i, clen, err;
+ int i, err;
int already;
+ unsigned int clen, overflow;
- clen = EXT4_B2C(sbi, len);
-
+again:
+ overflow = 0;
ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
+
+ /*
+ * Check to see if we are freeing blocks across a group
+ * boundary.
+ * In case of flex_bg, this can happen that (block, len) may span across
+ * more than one group. In that case we need to get the corresponding
+ * group metadata to work with. For this we have goto again loop.
+ */
+ if (EXT4_C2B(sbi, blkoff) + len > EXT4_BLOCKS_PER_GROUP(sb)) {
+ overflow = EXT4_C2B(sbi, blkoff) + len -
+ EXT4_BLOCKS_PER_GROUP(sb);
+ len -= overflow;
+ }
+
+ clen = EXT4_NUM_B2C(sbi, len);
+
bitmap_bh = ext4_read_block_bitmap(sb, group);
if (IS_ERR(bitmap_bh)) {
err = PTR_ERR(bitmap_bh);
@@ -3960,6 +3977,13 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
sync_dirty_buffer(gdp_bh);
+ if (overflow && !err) {
+ block += len;
+ len = overflow;
+ put_bh(bitmap_bh);
+ goto again;
+ }
+
out_err:
brelse(bitmap_bh);
}
--
2.31.1
On Mon 31-01-22 20:46:50, Ritesh Harjani wrote:
> In case of flex_bg feature (which is by default enabled), extents for
> any given inode might span across blocks from two different block group.
> ext4_mb_mark_bb() only reads the buffer_head of block bitmap once for the
> starting block group, but it fails to read it again when the extent length
> boundary overflows to another block group. Then in this below loop it
> accesses memory beyond the block group bitmap buffer_head and results
> into a data abort.
>
> for (i = 0; i < clen; i++)
> if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state)
> already++;
>
> This patch adds this functionality for checking block group boundary in
> ext4_mb_mark_bb() and update the buffer_head(bitmap_bh) for every different
> block group.
>
> w/o this patch, I was easily able to hit a data access abort using Power platform.
>
> <...>
> [ 74.327662] EXT4-fs error (device loop3): ext4_mb_generate_buddy:1141: group 11, block bitmap and bg descriptor inconsistent: 21248 vs 23294 free clusters
> [ 74.533214] EXT4-fs (loop3): shut down requested (2)
> [ 74.536705] Aborting journal on device loop3-8.
> [ 74.702705] BUG: Unable to handle kernel data access on read at 0xc00000005e980000
> [ 74.703727] Faulting instruction address: 0xc0000000007bffb8
> cpu 0xd: Vector: 300 (Data Access) at [c000000015db7060]
> pc: c0000000007bffb8: ext4_mb_mark_bb+0x198/0x5a0
> lr: c0000000007bfeec: ext4_mb_mark_bb+0xcc/0x5a0
> sp: c000000015db7300
> msr: 800000000280b033
> dar: c00000005e980000
> dsisr: 40000000
> current = 0xc000000027af6880
> paca = 0xc00000003ffd5200 irqmask: 0x03 irq_happened: 0x01
> pid = 5167, comm = mount
> <...>
> enter ? for help
> [c000000015db7380] c000000000782708 ext4_ext_clear_bb+0x378/0x410
> [c000000015db7400] c000000000813f14 ext4_fc_replay+0x1794/0x2000
> [c000000015db7580] c000000000833f7c do_one_pass+0xe9c/0x12a0
> [c000000015db7710] c000000000834504 jbd2_journal_recover+0x184/0x2d0
> [c000000015db77c0] c000000000841398 jbd2_journal_load+0x188/0x4a0
> [c000000015db7880] c000000000804de8 ext4_fill_super+0x2638/0x3e10
> [c000000015db7a40] c0000000005f8404 get_tree_bdev+0x2b4/0x350
> [c000000015db7ae0] c0000000007ef058 ext4_get_tree+0x28/0x40
> [c000000015db7b00] c0000000005f6344 vfs_get_tree+0x44/0x100
> [c000000015db7b70] c00000000063c408 path_mount+0xdd8/0xe70
> [c000000015db7c40] c00000000063c8f0 sys_mount+0x450/0x550
> [c000000015db7d50] c000000000035770 system_call_exception+0x4a0/0x4e0
> [c000000015db7e10] c00000000000c74c system_call_common+0xec/0x250
> --- Exception: c00 (System Call) at 00007ffff7dbfaa4
>
> Fixes: 8016e29f4362e28 ("ext4: fast commit recovery path")
> Signed-off-by: Ritesh Harjani <[email protected]>
> ---
> fs/ext4/mballoc.c | 30 +++++++++++++++++++++++++++---
> 1 file changed, 27 insertions(+), 3 deletions(-)
>
> diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
> index c781974df9d0..8d23108cf9d7 100644
> --- a/fs/ext4/mballoc.c
> +++ b/fs/ext4/mballoc.c
> @@ -3899,12 +3899,29 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
> struct ext4_sb_info *sbi = EXT4_SB(sb);
> ext4_group_t group;
> ext4_grpblk_t blkoff;
> - int i, clen, err;
> + int i, err;
> int already;
> + unsigned int clen, overflow;
>
> - clen = EXT4_B2C(sbi, len);
> -
> +again:
And maybe structure this as a while loop? Like:
while (len > 0) {
...
}
> + overflow = 0;
> ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
> +
> + /*
> + * Check to see if we are freeing blocks across a group
> + * boundary.
> + * In case of flex_bg, this can happen that (block, len) may span across
> + * more than one group. In that case we need to get the corresponding
> + * group metadata to work with. For this we have goto again loop.
> + */
> + if (EXT4_C2B(sbi, blkoff) + len > EXT4_BLOCKS_PER_GROUP(sb)) {
> + overflow = EXT4_C2B(sbi, blkoff) + len -
> + EXT4_BLOCKS_PER_GROUP(sb);
> + len -= overflow;
Why not just:
thisgrp_len = min_t(int, len,
EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff));
clen = EXT4_NUM_B2C(sbi, thisgrp_len);
It seems easier to understand to me.
Honza
> + }
> +
> + clen = EXT4_NUM_B2C(sbi, len);
> +
> bitmap_bh = ext4_read_block_bitmap(sb, group);
> if (IS_ERR(bitmap_bh)) {
> err = PTR_ERR(bitmap_bh);
> @@ -3960,6 +3977,13 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
> err = ext4_handle_dirty_metadata(NULL, NULL, gdp_bh);
> sync_dirty_buffer(gdp_bh);
>
> + if (overflow && !err) {
> + block += len;
> + len = overflow;
> + put_bh(bitmap_bh);
> + goto again;
> + }
> +
> out_err:
> brelse(bitmap_bh);
> }
> --
> 2.31.1
>
--
Jan Kara <[email protected]>
SUSE Labs, CR
On 22/02/01 12:21PM, Jan Kara wrote:
> On Mon 31-01-22 20:46:50, Ritesh Harjani wrote:
> > In case of flex_bg feature (which is by default enabled), extents for
> > any given inode might span across blocks from two different block group.
> > ext4_mb_mark_bb() only reads the buffer_head of block bitmap once for the
> > starting block group, but it fails to read it again when the extent length
> > boundary overflows to another block group. Then in this below loop it
> > accesses memory beyond the block group bitmap buffer_head and results
> > into a data abort.
> >
> > for (i = 0; i < clen; i++)
> > if (!mb_test_bit(blkoff + i, bitmap_bh->b_data) == !state)
> > already++;
> >
> > This patch adds this functionality for checking block group boundary in
> > ext4_mb_mark_bb() and update the buffer_head(bitmap_bh) for every different
> > block group.
> >
> > w/o this patch, I was easily able to hit a data access abort using Power platform.
> >
> > <...>
> > [ 74.327662] EXT4-fs error (device loop3): ext4_mb_generate_buddy:1141: group 11, block bitmap and bg descriptor inconsistent: 21248 vs 23294 free clusters
> > [ 74.533214] EXT4-fs (loop3): shut down requested (2)
> > [ 74.536705] Aborting journal on device loop3-8.
> > [ 74.702705] BUG: Unable to handle kernel data access on read at 0xc00000005e980000
> > [ 74.703727] Faulting instruction address: 0xc0000000007bffb8
> > cpu 0xd: Vector: 300 (Data Access) at [c000000015db7060]
> > pc: c0000000007bffb8: ext4_mb_mark_bb+0x198/0x5a0
> > lr: c0000000007bfeec: ext4_mb_mark_bb+0xcc/0x5a0
> > sp: c000000015db7300
> > msr: 800000000280b033
> > dar: c00000005e980000
> > dsisr: 40000000
> > current = 0xc000000027af6880
> > paca = 0xc00000003ffd5200 irqmask: 0x03 irq_happened: 0x01
> > pid = 5167, comm = mount
> > <...>
> > enter ? for help
> > [c000000015db7380] c000000000782708 ext4_ext_clear_bb+0x378/0x410
> > [c000000015db7400] c000000000813f14 ext4_fc_replay+0x1794/0x2000
> > [c000000015db7580] c000000000833f7c do_one_pass+0xe9c/0x12a0
> > [c000000015db7710] c000000000834504 jbd2_journal_recover+0x184/0x2d0
> > [c000000015db77c0] c000000000841398 jbd2_journal_load+0x188/0x4a0
> > [c000000015db7880] c000000000804de8 ext4_fill_super+0x2638/0x3e10
> > [c000000015db7a40] c0000000005f8404 get_tree_bdev+0x2b4/0x350
> > [c000000015db7ae0] c0000000007ef058 ext4_get_tree+0x28/0x40
> > [c000000015db7b00] c0000000005f6344 vfs_get_tree+0x44/0x100
> > [c000000015db7b70] c00000000063c408 path_mount+0xdd8/0xe70
> > [c000000015db7c40] c00000000063c8f0 sys_mount+0x450/0x550
> > [c000000015db7d50] c000000000035770 system_call_exception+0x4a0/0x4e0
> > [c000000015db7e10] c00000000000c74c system_call_common+0xec/0x250
> > --- Exception: c00 (System Call) at 00007ffff7dbfaa4
> >
> > Fixes: 8016e29f4362e28 ("ext4: fast commit recovery path")
> > Signed-off-by: Ritesh Harjani <[email protected]>
> > ---
> > fs/ext4/mballoc.c | 30 +++++++++++++++++++++++++++---
> > 1 file changed, 27 insertions(+), 3 deletions(-)
> >
> > diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
> > index c781974df9d0..8d23108cf9d7 100644
> > --- a/fs/ext4/mballoc.c
> > +++ b/fs/ext4/mballoc.c
> > @@ -3899,12 +3899,29 @@ void ext4_mb_mark_bb(struct super_block *sb, ext4_fsblk_t block,
> > struct ext4_sb_info *sbi = EXT4_SB(sb);
> > ext4_group_t group;
> > ext4_grpblk_t blkoff;
> > - int i, clen, err;
> > + int i, err;
> > int already;
> > + unsigned int clen, overflow;
> >
> > - clen = EXT4_B2C(sbi, len);
> > -
> > +again:
>
> And maybe structure this as a while loop? Like:
>
> while (len > 0) {
> ...
> }
Sure, will check.
>
> > + overflow = 0;
> > ext4_get_group_no_and_offset(sb, block, &group, &blkoff);
> > +
> > + /*
> > + * Check to see if we are freeing blocks across a group
> > + * boundary.
> > + * In case of flex_bg, this can happen that (block, len) may span across
> > + * more than one group. In that case we need to get the corresponding
> > + * group metadata to work with. For this we have goto again loop.
> > + */
> > + if (EXT4_C2B(sbi, blkoff) + len > EXT4_BLOCKS_PER_GROUP(sb)) {
> > + overflow = EXT4_C2B(sbi, blkoff) + len -
> > + EXT4_BLOCKS_PER_GROUP(sb);
> > + len -= overflow;
>
> Why not just:
>
> thisgrp_len = min_t(int, len,
> EXT4_BLOCKS_PER_GROUP(sb) - EXT4_C2B(sbi, blkoff));
> clen = EXT4_NUM_B2C(sbi, thisgrp_len);
>
> It seems easier to understand to me.
Agree, will make this change.
-ritesh