Viewing: ext4-mballoc-extra-checks.patch
commit f2f28f1d09c0a00b3fc569422f881931d857fac9
Author: Alex Zhuravlev <alex.zhuravlev@sun.com>
AuthorDate: Tue Oct 28 17:59:09 2008 +0000
Subject: ext4: detect on-disk corruption of block bitmap
Detect on-disk corruption of block bitmap and better checking of
preallocated blocks.
Bugzilla-ID: b=16680
Signed-off-by: Alex Zhuravlev <alex.zhuravlev@sun.com>
Reviewed-by: Kalpak Shah <kalpak.shah@sun.com>
Signed-off-by: Andreas Dilger <andreas.dilger@sun.com>
---
fs/ext4/ext4.h | 1 +
fs/ext4/mballoc.c | 105 ++++++++++++++++++++++++++++++++++++++++------
fs/ext4/mballoc.h | 2 +-
3 files changed, 94 insertions(+), 14 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index dfbb9dd1..504531e0 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3465,6 +3465,7 @@ struct ext4_group_info {
ext4_grpblk_t bb_largest_free_order;/* order of largest frag in BG */
ext4_group_t bb_group; /* Group number */
struct list_head bb_prealloc_list;
+ unsigned long bb_prealloc_nr;
#ifdef DOUBLE_CHECK
void *bb_bitmap;
#endif
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index b669bbec..f9a09807 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -416,7 +416,7 @@ static const char * const ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = {
"ext4_groupinfo_64k", "ext4_groupinfo_128k"
};
-static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
+static int ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
ext4_group_t group);
static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac);
@@ -1181,7 +1181,7 @@ mb_set_largest_free_order(struct super_block *sb, struct ext4_group_info *grp)
}
static noinline_for_stack
-void ext4_mb_generate_buddy(struct super_block *sb,
+int ext4_mb_generate_buddy(struct super_block *sb,
void *buddy, void *bitmap, ext4_group_t group,
struct ext4_group_info *grp)
{
@@ -1225,6 +1225,7 @@ void ext4_mb_generate_buddy(struct super_block *sb,
grp->bb_free = free;
ext4_mark_group_bitmap_corrupted(sb, group,
EXT4_GROUP_INFO_BBITMAP_CORRUPT);
+ return -EIO;
}
mb_set_largest_free_order(sb, grp);
mb_update_avg_fragment_size(sb, grp);
@@ -1234,6 +1235,8 @@ void ext4_mb_generate_buddy(struct super_block *sb,
period = get_cycles() - period;
atomic_inc(&sbi->s_mb_buddies_generated);
atomic64_add(period, &sbi->s_mb_generation_time);
+
+ return 0;
}
static void mb_regenerate_buddy(struct ext4_buddy *e4b)
@@ -1355,7 +1358,7 @@ static int ext4_mb_init_cache(struct folio *folio, char *incore, gfp_t gfp)
}
first_block = folio->index * blocks_per_page;
- for (i = 0; i < blocks_per_page; i++) {
+ for (i = 0; i < blocks_per_page && err == 0; i++) {
group = (first_block + i) >> 1;
if (group >= ngroups)
break;
@@ -1403,7 +1406,7 @@ static int ext4_mb_init_cache(struct folio *folio, char *incore, gfp_t gfp)
ext4_lock_group(sb, group);
/* init the buddy */
memset(data, 0xff, blocksize);
- ext4_mb_generate_buddy(sb, data, incore, group, grinfo);
+ err = ext4_mb_generate_buddy(sb, data, incore, group, grinfo);
ext4_unlock_group(sb, group);
incore = NULL;
} else {
@@ -1418,7 +1421,7 @@ static int ext4_mb_init_cache(struct folio *folio, char *incore, gfp_t gfp)
memcpy(data, bitmap, blocksize);
/* mark all preallocated blks used in in-core bitmap */
- ext4_mb_generate_from_pa(sb, data, group);
+ err = ext4_mb_generate_from_pa(sb, data, group);
WARN_ON_ONCE(!RB_EMPTY_ROOT(&grinfo->bb_free_root));
ext4_unlock_group(sb, group);
@@ -1428,7 +1431,8 @@ static int ext4_mb_init_cache(struct folio *folio, char *incore, gfp_t gfp)
incore = data;
}
}
- folio_mark_uptodate(folio);
+ if (likely(err == 0))
+ folio_mark_uptodate(folio);
out:
if (bh) {
@@ -3030,8 +3034,10 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
{
struct super_block *sb = pde_data(file_inode(seq->file));
ext4_group_t group = (ext4_group_t) ((unsigned long) v);
+ struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
int i, err;
char nbuf[16];
+ int free = 0;
struct ext4_buddy e4b;
struct ext4_group_info *grinfo;
unsigned char blocksize_bits = min_t(unsigned char,
@@ -3040,9 +3046,12 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
DEFINE_RAW_FLEX(struct ext4_group_info, sg, bb_counters,
EXT4_MAX_BLOCK_LOG_SIZE + 2);
+ if (gdp)
+ free = ext4_free_group_clusters(sb, gdp);
+
group--;
if (group == 0)
- seq_puts(seq, "#group: free frags first ["
+ seq_puts(seq, "#group: bfree gfree frags first pa ["
" 2^0 2^1 2^2 2^3 2^4 2^5 2^6 "
" 2^7 2^8 2^9 2^10 2^11 2^12 2^13 ]\n");
@@ -3067,8 +3076,10 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
* these are safe to access even after the buddy has been unloaded
*/
memcpy(sg, grinfo, i);
- seq_printf(seq, "#%-5u: %-5u %-5u %-5u [", group, sg->bb_free,
- sg->bb_fragments, sg->bb_first_free);
+ seq_printf(seq, "#%-5lu: %-5u %-5u %-5u %-5u %-5lu [",
+ (long unsigned int)group, sg->bb_free, free,
+ sg->bb_fragments, sg->bb_first_free,
+ sg->bb_prealloc_nr);
for (i = 0; i <= 13; i++)
seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ?
sg->bb_counters[i] : 0);
@@ -5084,25 +5095,75 @@ try_group_pa:
return false;
}
+/*
+ * check free blocks in bitmap match free block in group descriptor
+ * do this before taking preallocated blocks into account to be able
+ * to detect on-disk corruptions. The group lock should be hold by the
+ * caller.
+ */
+static
+int ext4_mb_check_ondisk_bitmap(struct super_block *sb, void *bitmap,
+ struct ext4_group_desc *gdp, int group)
+{
+ unsigned short max = EXT4_CLUSTERS_PER_GROUP(sb);
+ unsigned short i, first, free = 0;
+ unsigned short free_in_gdp = ext4_free_group_clusters(sb, gdp);
+
+ if (free_in_gdp == 0 && gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT))
+ return 0;
+
+ i = mb_find_next_zero_bit(bitmap, max, 0);
+
+ while (i < max) {
+ first = i;
+ i = mb_find_next_bit(bitmap, max, i);
+ if (i > max)
+ i = max;
+ free += i - first;
+ if (i < max)
+ i = mb_find_next_zero_bit(bitmap, max, i);
+ }
+
+ if (free != free_in_gdp) {
+ ext4_error(sb, "on-disk bitmap for group %d"
+ "corrupted: %u blocks free in bitmap, %u - in gd\n",
+ group, free, free_in_gdp);
+ return -EIO;
+ }
+ return 0;
+}
+
/*
* the function goes through all preallocation in this group and marks them
* used in in-core bitmap. buddy must be generated from this bitmap
* Need to be called with ext4 group lock held
*/
static noinline_for_stack
-void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
+int ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
ext4_group_t group)
{
struct ext4_group_info *grp = ext4_get_group_info(sb, group);
struct ext4_prealloc_space *pa;
+ struct ext4_group_desc *gdp;
struct list_head *cur;
ext4_group_t groupnr;
ext4_grpblk_t start;
int preallocated = 0;
+ int skip = 0, count = 0;
+ int err;
int len;
if (!grp)
- return;
+ return -EIO;
+
+ gdp = ext4_get_group_desc(sb, group, NULL);
+ if (gdp == NULL)
+ return -EIO;
+
+ /* before applying preallocations, check bitmap consistency */
+ err = ext4_mb_check_ondisk_bitmap(sb, bitmap, gdp, group);
+ if (err)
+ return err;
/* all form of preallocation discards first load group,
* so the only competing code is preallocation use.
@@ -5119,13 +5180,23 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
&groupnr, &start);
len = pa->pa_len;
spin_unlock(&pa->pa_lock);
- if (unlikely(len == 0))
+ if (unlikely(len == 0)) {
+ skip++;
continue;
+ }
BUG_ON(groupnr != group);
mb_set_bits(bitmap, start, len);
preallocated += len;
+ count++;
+ }
+ if (count + skip != grp->bb_prealloc_nr) {
+ ext4_error(sb, "lost preallocations: "
+ "count %d, bb_prealloc_nr %lu, skip %d\n",
+ count, grp->bb_prealloc_nr, skip);
+ return -EIO;
}
mb_debug(sb, "preallocated %d for group %u\n", preallocated, group);
+ return 0;
}
static void ext4_mb_mark_pa_deleted(struct super_block *sb,
@@ -5216,6 +5287,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac,
*/
ext4_lock_group(sb, grp);
list_del(&pa->pa_group_list);
+ ext4_get_group_info(sb, grp)->bb_prealloc_nr--;
ext4_unlock_group(sb, grp);
if (pa->pa_type == MB_INODE_PA) {
@@ -5349,6 +5421,7 @@ adjust_bex:
pa->pa_inode = ac->ac_inode;
list_add(&pa->pa_group_list, &grp->bb_prealloc_list);
+ grp->bb_prealloc_nr++;
write_lock(pa->pa_node_lock.inode_lock);
ext4_mb_pa_rb_insert(&ei->i_prealloc_node, &pa->pa_node.inode_node);
@@ -5402,6 +5475,7 @@ ext4_mb_new_group_pa(struct ext4_allocation_context *ac)
pa->pa_inode = NULL;
list_add(&pa->pa_group_list, &grp->bb_prealloc_list);
+ grp->bb_prealloc_nr++;
/*
* We will later add the new pa to the right bucket
@@ -5568,6 +5642,8 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
spin_unlock(&pa->pa_lock);
+ BUG_ON(grp->bb_prealloc_nr == 0);
+ grp->bb_prealloc_nr--;
list_del(&pa->pa_group_list);
list_add(&pa->u.pa_tmp_list, &list);
}
@@ -5699,7 +5775,7 @@ repeat:
if (err) {
ext4_error_err(sb, -err, "Error %d loading buddy information for %u",
err, group);
- continue;
+ return;
}
bitmap_bh = ext4_read_block_bitmap(sb, group);
@@ -5712,6 +5788,8 @@ repeat:
}
ext4_lock_group(sb, group);
+ BUG_ON(e4b.bd_info->bb_prealloc_nr == 0);
+ e4b.bd_info->bb_prealloc_nr--;
list_del(&pa->pa_group_list);
ext4_mb_release_inode_pa(&e4b, bitmap_bh, pa);
ext4_unlock_group(sb, group);
@@ -6016,6 +6094,7 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
}
ext4_lock_group(sb, group);
list_del(&pa->pa_group_list);
+ ext4_get_group_info(sb, group)->bb_prealloc_nr--;
ext4_mb_release_group_pa(&e4b, pa);
ext4_unlock_group(sb, group);
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index f8280de3..6b8821d3 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -66,7 +66,7 @@
/*
* for which requests use 2^N search using buddies
*/
-#define MB_DEFAULT_ORDER2_REQS 2
+#define MB_DEFAULT_ORDER2_REQS 8
/*
* default group prealloc size 512 blocks
--
2.45.2
