Multiblock allocator calls BUG_ON in many case if the free and used
blocks count obtained looking at the bitmap is different from what
the allocator internally accounted for. Use ext4_error in such case
and don't panic the system.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
---
fs/ext4/mballoc.c | 49 +++++++++++++++++++++++++++++++++++--------------
1 files changed, 35 insertions(+), 14 deletions(-)
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 06d1f52..7af22ee 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -680,7 +680,6 @@ static void *mb_find_buddy(struct ext4_buddy *e4b, int order, int *max)
{
char *bb;
- /* FIXME!! is this needed */
BUG_ON(EXT4_MB_BITMAP(e4b) == EXT4_MB_BUDDY(e4b));
BUG_ON(max == NULL);
@@ -964,9 +963,13 @@ static void ext4_mb_generate_buddy(struct super_block *sb,
grp->bb_fragments = fragments;
if (free != grp->bb_free) {
- printk(KERN_DEBUG
+ ext4_error(sb, __FUNCTION__,
"EXT4-fs: group %lu: %u blocks in bitmap, %u in gd\n",
group, free, grp->bb_free);
+ /*
+ * If we intent to contine we consider the group descritor
+ * corrupt and update the bb_free using bitmap value
+ */
grp->bb_free = free;
}
@@ -1821,13 +1824,30 @@ static void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
i = ext4_find_next_zero_bit(bitmap,
EXT4_BLOCKS_PER_GROUP(sb), i);
if (i >= EXT4_BLOCKS_PER_GROUP(sb)) {
- BUG_ON(free != 0);
+ /*
+ * IF we have corrupt bitmap we won't find any
+ * free blocks even though group info says we
+ * we have free blocks
+ */
+ ext4_error(sb, __FUNCTION__, "%d free blocks as per "
+ "group info. But bitmap says 0\n",
+ free);
break;
}
mb_find_extent(e4b, 0, i, ac->ac_g_ex.fe_len, &ex);
BUG_ON(ex.fe_len <= 0);
- BUG_ON(free < ex.fe_len);
+ if (free < ex.fe_len) {
+ ext4_error(sb, __FUNCTION__, "%d free blocks as per "
+ "group info. But got %d blocks\n",
+ free, ex.fe_len);
+ /*
+ * The number of free blocks differs. This mostly
+ * indicate that the bitmap is corrupt. So exit
+ * without claiming the space.
+ */
+ break;
+ }
ext4_mb_measure_extent(ac, &ex, e4b);
@@ -3354,13 +3374,10 @@ static void ext4_mb_use_group_pa(struct ext4_allocation_context *ac,
ac->ac_pa = pa;
/* we don't correct pa_pstart or pa_plen here to avoid
- * possible race when tte group is being loaded concurrently
+ * possible race when the group is being loaded concurrently
* instead we correct pa later, after blocks are marked
- * in on-disk bitmap -- see ext4_mb_release_context() */
- /*
- * FIXME!! but the other CPUs can look at this particular
- * pa and think that it have enought free blocks if we
- * don't update pa_free here right ?
+ * in on-disk bitmap -- see ext4_mb_release_context()
+ * Other CPUs are prevented from allocating from this pa by lg_mutex
*/
mb_debug("use %u/%u from group pa %p\n", pa->pa_lstart-len, len, pa);
}
@@ -3743,13 +3760,17 @@ static int ext4_mb_release_inode_pa(struct ext4_buddy *e4b,
bit = next + 1;
}
if (free != pa->pa_free) {
- printk(KERN_ERR "pa %p: logic %lu, phys. %lu, len %lu\n",
+ printk(KERN_CRIT "pa %p: logic %lu, phys. %lu, len %lu\n",
pa, (unsigned long) pa->pa_lstart,
(unsigned long) pa->pa_pstart,
(unsigned long) pa->pa_len);
- printk(KERN_ERR "free %u, pa_free %u\n", free, pa->pa_free);
+ ext4_error(sb, __FUNCTION__, "free %u, pa_free %u\n",
+ free, pa->pa_free);
+ /*
+ * pa is already deleted so we use the value obtained
+ * from the bitmap and continue.
+ */
}
- BUG_ON(free != pa->pa_free);
atomic_add(free, &sbi->s_mb_discarded);
return err;
@@ -4405,7 +4426,7 @@ void ext4_mb_free_blocks(handle_t *handle, struct inode *inode,
unsigned long block, unsigned long count,
int metadata, unsigned long *freed)
{
- struct buffer_head *bitmap_bh = 0;
+ struct buffer_head *bitmap_bh = NULL;
struct super_block *sb = inode->i_sb;
struct ext4_allocation_context ac;
struct ext4_group_desc *gdp;
--
1.5.4.23.gef5b9-dirty
-
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
