aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/extents.c116
-rw-r--r--fs/ext4/extents_status.c14
-rw-r--r--fs/ext4/extents_status.h6
-rw-r--r--fs/ext4/inode.c65
-rw-r--r--fs/ext4/mballoc.c90
-rw-r--r--fs/ext4/resize.c3
-rw-r--r--fs/ext4/super.c12
7 files changed, 182 insertions, 124 deletions
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 193b13630ac1..9e1259272791 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2222,7 +2222,7 @@ static int ext4_fill_es_cache_info(struct inode *inode,
/*
- * ext4_ext_determine_hole - determine hole around given block
+ * ext4_ext_find_hole - find hole around given block according to the given path
* @inode: inode we lookup in
* @path: path in extent tree to @lblk
* @lblk: pointer to logical block around which we want to determine hole
@@ -2234,9 +2234,9 @@ static int ext4_fill_es_cache_info(struct inode *inode,
* The function returns the length of a hole starting at @lblk. We update @lblk
* to the beginning of the hole if we managed to find it.
*/
-static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode,
- struct ext4_ext_path *path,
- ext4_lblk_t *lblk)
+static ext4_lblk_t ext4_ext_find_hole(struct inode *inode,
+ struct ext4_ext_path *path,
+ ext4_lblk_t *lblk)
{
int depth = ext_depth(inode);
struct ext4_extent *ex;
@@ -2264,30 +2264,6 @@ static ext4_lblk_t ext4_ext_determine_hole(struct inode *inode,
}
/*
- * ext4_ext_put_gap_in_cache:
- * calculate boundaries of the gap that the requested block fits into
- * and cache this gap
- */
-static void
-ext4_ext_put_gap_in_cache(struct inode *inode, ext4_lblk_t hole_start,
- ext4_lblk_t hole_len)
-{
- struct extent_status es;
-
- ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start,
- hole_start + hole_len - 1, &es);
- if (es.es_len) {
- /* There's delayed extent containing lblock? */
- if (es.es_lblk <= hole_start)
- return;
- hole_len = min(es.es_lblk - hole_start, hole_len);
- }
- ext_debug(inode, " -> %u:%u\n", hole_start, hole_len);
- ext4_es_insert_extent(inode, hole_start, hole_len, ~0,
- EXTENT_STATUS_HOLE);
-}
-
-/*
* ext4_ext_rm_idx:
* removes index from the index block.
*/
@@ -3131,8 +3107,9 @@ static int ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex)
if (ee_len == 0)
return 0;
- return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock,
- EXTENT_STATUS_WRITTEN);
+ ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock,
+ EXTENT_STATUS_WRITTEN);
+ return 0;
}
/* FIXME!! we need to try to merge to left or right after zero-out */
@@ -4058,6 +4035,69 @@ static int get_implied_cluster_alloc(struct super_block *sb,
return 0;
}
+/*
+ * Determine hole length around the given logical block, first try to
+ * locate and expand the hole from the given @path, and then adjust it
+ * if it's partially or completely converted to delayed extents, insert
+ * it into the extent cache tree if it's indeed a hole, finally return
+ * the length of the determined extent.
+ */
+static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode,
+ struct ext4_ext_path *path,
+ ext4_lblk_t lblk)
+{
+ ext4_lblk_t hole_start, len;
+ struct extent_status es;
+
+ hole_start = lblk;
+ len = ext4_ext_find_hole(inode, path, &hole_start);
+again:
+ ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start,
+ hole_start + len - 1, &es);
+ if (!es.es_len)
+ goto insert_hole;
+
+ /*
+ * There's a delalloc extent in the hole, handle it if the delalloc
+ * extent is in front of, behind and straddle the queried range.
+ */
+ if (lblk >= es.es_lblk + es.es_len) {
+ /*
+ * The delalloc extent is in front of the queried range,
+ * find again from the queried start block.
+ */
+ len -= lblk - hole_start;
+ hole_start = lblk;
+ goto again;
+ } else if (in_range(lblk, es.es_lblk, es.es_len)) {
+ /*
+ * The delalloc extent containing lblk, it must have been
+ * added after ext4_map_blocks() checked the extent status
+ * tree, adjust the length to the delalloc extent's after
+ * lblk.
+ */
+ len = es.es_lblk + es.es_len - lblk;
+ return len;
+ } else {
+ /*
+ * The delalloc extent is partially or completely behind
+ * the queried range, update hole length until the
+ * beginning of the delalloc extent.
+ */
+ len = min(es.es_lblk - hole_start, len);
+ }
+
+insert_hole:
+ /* Put just found gap into cache to speed up subsequent requests */
+ ext_debug(inode, " -> %u:%u\n", hole_start, len);
+ ext4_es_insert_extent(inode, hole_start, len, ~0, EXTENT_STATUS_HOLE);
+
+ /* Update hole_len to reflect hole size after lblk */
+ if (hole_start != lblk)
+ len -= lblk - hole_start;
+
+ return len;
+}
/*
* Block allocation/map/preallocation routine for extents based files
@@ -4175,22 +4215,12 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
* we couldn't try to create block if create flag is zero
*/
if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) {
- ext4_lblk_t hole_start, hole_len;
+ ext4_lblk_t len;
- hole_start = map->m_lblk;
- hole_len = ext4_ext_determine_hole(inode, path, &hole_start);
- /*
- * put just found gap into cache to speed up
- * subsequent requests
- */
- ext4_ext_put_gap_in_cache(inode, hole_start, hole_len);
+ len = ext4_ext_determine_insert_hole(inode, path, map->m_lblk);
- /* Update hole_len to reflect hole size after map->m_lblk */
- if (hole_start != map->m_lblk)
- hole_len -= map->m_lblk - hole_start;
map->m_pblk = 0;
- map->m_len = min_t(unsigned int, map->m_len, hole_len);
-
+ map->m_len = min_t(unsigned int, map->m_len, len);
goto out;
}
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index cccbdfd49a86..f37e62546745 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -846,12 +846,10 @@ out:
/*
* ext4_es_insert_extent() adds information to an inode's extent
* status tree.
- *
- * Return 0 on success, error code on failure.
*/
-int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
- ext4_lblk_t len, ext4_fsblk_t pblk,
- unsigned int status)
+void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
+ ext4_lblk_t len, ext4_fsblk_t pblk,
+ unsigned int status)
{
struct extent_status newes;
ext4_lblk_t end = lblk + len - 1;
@@ -863,13 +861,13 @@ int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
bool revise_pending = false;
if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
- return 0;
+ return;
es_debug("add [%u/%u) %llu %x to extent status tree of inode %lu\n",
lblk, len, pblk, status, inode->i_ino);
if (!len)
- return 0;
+ return;
BUG_ON(end < lblk);
@@ -938,7 +936,7 @@ error:
goto retry;
ext4_es_print_tree(inode);
- return 0;
+ return;
}
/*
diff --git a/fs/ext4/extents_status.h b/fs/ext4/extents_status.h
index 4ec30a798260..481ec4381bee 100644
--- a/fs/ext4/extents_status.h
+++ b/fs/ext4/extents_status.h
@@ -127,9 +127,9 @@ extern int __init ext4_init_es(void);
extern void ext4_exit_es(void);
extern void ext4_es_init_tree(struct ext4_es_tree *tree);
-extern int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
- ext4_lblk_t len, ext4_fsblk_t pblk,
- unsigned int status);
+extern void ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
+ ext4_lblk_t len, ext4_fsblk_t pblk,
+ unsigned int status);
extern void ext4_es_cache_extent(struct inode *inode, ext4_lblk_t lblk,
ext4_lblk_t len, ext4_fsblk_t pblk,
unsigned int status);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 365c4d3a434a..8b48ed351c4b 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -589,10 +589,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk,
map->m_lblk + map->m_len - 1))
status |= EXTENT_STATUS_DELAYED;
- ret = ext4_es_insert_extent(inode, map->m_lblk,
- map->m_len, map->m_pblk, status);
- if (ret < 0)
- retval = ret;
+ ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+ map->m_pblk, status);
}
up_read((&EXT4_I(inode)->i_data_sem));
@@ -701,12 +699,8 @@ found:
ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk,
map->m_lblk + map->m_len - 1))
status |= EXTENT_STATUS_DELAYED;
- ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
- map->m_pblk, status);
- if (ret < 0) {
- retval = ret;
- goto out_sem;
- }
+ ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+ map->m_pblk, status);
}
out_sem:
@@ -1734,11 +1728,8 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
/* Lookup extent status tree firstly */
if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) {
- if (ext4_es_is_hole(&es)) {
- retval = 0;
- down_read(&EXT4_I(inode)->i_data_sem);
+ if (ext4_es_is_hole(&es))
goto add_delayed;
- }
/*
* Delayed extent could be allocated by fallocate.
@@ -1780,27 +1771,11 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
retval = ext4_ext_map_blocks(NULL, inode, map, 0);
else
retval = ext4_ind_map_blocks(NULL, inode, map, 0);
-
-add_delayed:
- if (retval == 0) {
- int ret;
-
- /*
- * XXX: __block_prepare_write() unmaps passed block,
- * is it OK?
- */
-
- ret = ext4_insert_delayed_block(inode, map->m_lblk);
- if (ret != 0) {
- retval = ret;
- goto out_unlock;
- }
-
- map_bh(bh, inode->i_sb, invalid_block);
- set_buffer_new(bh);
- set_buffer_delay(bh);
- } else if (retval > 0) {
- int ret;
+ if (retval < 0) {
+ up_read(&EXT4_I(inode)->i_data_sem);
+ return retval;
+ }
+ if (retval > 0) {
unsigned int status;
if (unlikely(retval != map->m_len)) {
@@ -1813,15 +1788,23 @@ add_delayed:
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
- ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
- map->m_pblk, status);
- if (ret != 0)
- retval = ret;
+ ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+ map->m_pblk, status);
+ up_read(&EXT4_I(inode)->i_data_sem);
+ return retval;
}
+ up_read(&EXT4_I(inode)->i_data_sem);
-out_unlock:
- up_read((&EXT4_I(inode)->i_data_sem));
+add_delayed:
+ down_write(&EXT4_I(inode)->i_data_sem);
+ retval = ext4_insert_delayed_block(inode, map->m_lblk);
+ up_write(&EXT4_I(inode)->i_data_sem);
+ if (retval)
+ return retval;
+ map_bh(bh, inode->i_sb, invalid_block);
+ set_buffer_new(bh);
+ set_buffer_delay(bh);
return retval;
}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 9bec75847b85..c1d632725c2c 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -823,6 +823,24 @@ void ext4_mb_generate_buddy(struct super_block *sb,
atomic64_add(period, &sbi->s_mb_generation_time);
}
+static void mb_regenerate_buddy(struct ext4_buddy *e4b)
+{
+ int count;
+ int order = 1;
+ void *buddy;
+
+ while ((buddy = mb_find_buddy(e4b, order++, &count)))
+ ext4_set_bits(buddy, 0, count);
+
+ e4b->bd_info->bb_fragments = 0;
+ memset(e4b->bd_info->bb_counters, 0,
+ sizeof(*e4b->bd_info->bb_counters) *
+ (e4b->bd_sb->s_blocksize_bits + 2));
+
+ ext4_mb_generate_buddy(e4b->bd_sb, e4b->bd_buddy,
+ e4b->bd_bitmap, e4b->bd_group, e4b->bd_info);
+}
+
/* The buddy information is attached the buddy cache inode
* for convenience. The information regarding each group
* is loaded via ext4_mb_load_buddy. The information involve
@@ -1476,11 +1494,6 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
mb_check_buddy(e4b);
mb_free_blocks_double(inode, e4b, first, count);
- this_cpu_inc(discard_pa_seq);
- e4b->bd_info->bb_free += count;
- if (first < e4b->bd_info->bb_first_free)
- e4b->bd_info->bb_first_free = first;
-
/* access memory sequentially: check left neighbour,
* clear range and then check right neighbour
*/
@@ -1494,21 +1507,31 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
struct ext4_sb_info *sbi = EXT4_SB(sb);
ext4_fsblk_t blocknr;
+ /*
+ * Fastcommit replay can free already freed blocks which
+ * corrupts allocation info. Regenerate it.
+ */
+ if (sbi->s_mount_state & EXT4_FC_REPLAY) {
+ mb_regenerate_buddy(e4b);
+ goto check;
+ }
+
blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
blocknr += EXT4_C2B(sbi, block);
- if (!(sbi->s_mount_state & EXT4_FC_REPLAY)) {
- ext4_grp_locked_error(sb, e4b->bd_group,
- inode ? inode->i_ino : 0,
- blocknr,
- "freeing already freed block (bit %u); block bitmap corrupt.",
- block);
- ext4_mark_group_bitmap_corrupted(
- sb, e4b->bd_group,
+ ext4_grp_locked_error(sb, e4b->bd_group,
+ inode ? inode->i_ino : 0, blocknr,
+ "freeing already freed block (bit %u); block bitmap corrupt.",
+ block);
+ ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
EXT4_GROUP_INFO_BBITMAP_CORRUPT);
- }
- goto done;
+ return;
}
+ this_cpu_inc(discard_pa_seq);
+ e4b->bd_info->bb_free += count;
+ if (first < e4b->bd_info->bb_first_free)
+ e4b->bd_info->bb_first_free = first;
+
/* let's maintain fragments counter */
if (left_is_free && right_is_free)
e4b->bd_info->bb_fragments--;
@@ -1533,8 +1556,8 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
if (first <= last)
mb_buddy_mark_free(e4b, first >> 1, last >> 1);
-done:
mb_set_largest_free_order(sb, e4b->bd_info);
+check:
mb_check_buddy(e4b);
}
@@ -1854,6 +1877,9 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac,
return err;
ext4_lock_group(ac->ac_sb, group);
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+ goto out;
+
max = mb_find_extent(e4b, ex.fe_start, ex.fe_len, &ex);
if (max > 0) {
@@ -1861,6 +1887,7 @@ int ext4_mb_try_best_found(struct ext4_allocation_context *ac,
ext4_mb_use_best_found(ac, e4b);
}
+out:
ext4_unlock_group(ac->ac_sb, group);
ext4_mb_unload_buddy(e4b);
@@ -1889,12 +1916,10 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
if (err)
return err;
- if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info))) {
- ext4_mb_unload_buddy(e4b);
- return 0;
- }
-
ext4_lock_group(ac->ac_sb, group);
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+ goto out;
+
max = mb_find_extent(e4b, ac->ac_g_ex.fe_start,
ac->ac_g_ex.fe_len, &ex);
ex.fe_logical = 0xDEADFA11; /* debug value */
@@ -1927,6 +1952,7 @@ int ext4_mb_find_by_goal(struct ext4_allocation_context *ac,
ac->ac_b_ex = ex;
ext4_mb_use_best_found(ac, e4b);
}
+out:
ext4_unlock_group(ac->ac_sb, group);
ext4_mb_unload_buddy(e4b);
@@ -2565,7 +2591,10 @@ static int ext4_mb_seq_groups_show(struct seq_file *seq, void *v)
for (i = 0; i <= 13; i++)
seq_printf(seq, " %-5u", i <= blocksize_bits + 1 ?
sg.info.bb_counters[i] : 0);
- seq_puts(seq, " ]\n");
+ seq_puts(seq, " ]");
+ if (EXT4_MB_GRP_BBITMAP_CORRUPT(&sg.info))
+ seq_puts(seq, " Block bitmap corrupted!");
+ seq_puts(seq, "\n");
return 0;
}
@@ -4136,10 +4165,16 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
.fe_len = ac->ac_g_ex.fe_len,
};
loff_t orig_goal_end = extent_logical_end(sbi, &ex);
+ loff_t o_ex_end = extent_logical_end(sbi, &ac->ac_o_ex);
- /* we can't allocate as much as normalizer wants.
- * so, found space must get proper lstart
- * to cover original request */
+ /*
+ * We can't allocate as much as normalizer wants, so we try
+ * to get proper lstart to cover the original request, except
+ * when the goal doesn't cover the original request as below:
+ *
+ * orig_ex:2045/2055(10), isize:8417280 -> normalized:0/2048
+ * best_ex:0/200(200) -> adjusted: 1848/2048(200)
+ */
BUG_ON(ac->ac_g_ex.fe_logical > ac->ac_o_ex.fe_logical);
BUG_ON(ac->ac_g_ex.fe_len < ac->ac_o_ex.fe_len);
@@ -4151,7 +4186,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
* 1. Check if best ex can be kept at end of goal and still
* cover original start
* 2. Else, check if best ex can be kept at start of goal and
- * still cover original start
+ * still cover original end
* 3. Else, keep the best ex at start of original request.
*/
ex.fe_len = ac->ac_b_ex.fe_len;
@@ -4161,7 +4196,7 @@ ext4_mb_new_inode_pa(struct ext4_allocation_context *ac)
goto adjust_bex;
ex.fe_logical = ac->ac_g_ex.fe_logical;
- if (ac->ac_o_ex.fe_logical < extent_logical_end(sbi, &ex))
+ if (o_ex_end <= extent_logical_end(sbi, &ex))
goto adjust_bex;
ex.fe_logical = ac->ac_o_ex.fe_logical;
@@ -4169,7 +4204,6 @@ adjust_bex:
ac->ac_b_ex.fe_logical = ex.fe_logical;
BUG_ON(ac->ac_o_ex.fe_logical < ac->ac_b_ex.fe_logical);
- BUG_ON(ac->ac_o_ex.fe_len > ac->ac_b_ex.fe_len);
BUG_ON(extent_logical_end(sbi, &ex) > orig_goal_end);
}
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 06e0eaf2ea4e..5d45ec29e61a 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1545,7 +1545,8 @@ exit_journal:
int gdb_num = group / EXT4_DESC_PER_BLOCK(sb);
int gdb_num_end = ((group + flex_gd->count - 1) /
EXT4_DESC_PER_BLOCK(sb));
- int meta_bg = ext4_has_feature_meta_bg(sb);
+ int meta_bg = ext4_has_feature_meta_bg(sb) &&
+ gdb_num >= le32_to_cpu(es->s_first_meta_bg);
sector_t padding_blocks = meta_bg ? 0 : sbi->s_sbh->b_blocknr -
ext4_group_first_block_no(sb, 0);
sector_t old_gdb = 0;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index e386d67cff9d..0149d3c2cfd7 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -6205,6 +6205,10 @@ static int ext4_write_dquot(struct dquot *dquot)
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_commit(dquot);
+ if (ret < 0)
+ ext4_error_err(dquot->dq_sb, -ret,
+ "Failed to commit dquot type %d",
+ dquot->dq_id.type);
err = ext4_journal_stop(handle);
if (!ret)
ret = err;
@@ -6221,6 +6225,10 @@ static int ext4_acquire_dquot(struct dquot *dquot)
if (IS_ERR(handle))
return PTR_ERR(handle);
ret = dquot_acquire(dquot);
+ if (ret < 0)
+ ext4_error_err(dquot->dq_sb, -ret,
+ "Failed to acquire dquot type %d",
+ dquot->dq_id.type);
err = ext4_journal_stop(handle);
if (!ret)
ret = err;
@@ -6240,6 +6248,10 @@ static int ext4_release_dquot(struct dquot *dquot)
return PTR_ERR(handle);
}
ret = dquot_release(dquot);
+ if (ret < 0)
+ ext4_error_err(dquot->dq_sb, -ret,
+ "Failed to release dquot type %d",
+ dquot->dq_id.type);
err = ext4_journal_stop(handle);
if (!ret)
ret = err;
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-05-23 11:11:15 +0000