summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-02-04 07:33:01 +0000
committerLinus Torvalds <torvalds@linux-foundation.org>2024-02-04 07:33:01 +0000
commit3f24fcdacd40c70dd2949c1cfd8cc2e75942a9e3 (patch)
tree1a867f42a6d4454e061a9913808ef52fb51e7a25
parent9e28c7a23bac7452935d1768fbfedad113586f9b (diff)
parentec9d669eba4c276d00af88951947fe0e82a6b84c (diff)
Merge tag 'for-linus-6.8-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 fixes from Ted Ts'o: "Miscellaneous bug fixes and cleanups in ext4's multi-block allocator and extent handling code" * tag 'for-linus-6.8-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (23 commits) ext4: make ext4_set_iomap() recognize IOMAP_DELALLOC map type ext4: make ext4_map_blocks() distinguish delalloc only extent ext4: add a hole extent entry in cache after punch ext4: correct the hole length returned by ext4_map_blocks() ext4: convert to exclusive lock while inserting delalloc extents ext4: refactor ext4_da_map_blocks() ext4: remove 'needed' in trace_ext4_discard_preallocations ext4: remove unnecessary parameter "needed" in ext4_discard_preallocations ext4: remove unused return value of ext4_mb_release_group_pa ext4: remove unused return value of ext4_mb_release_inode_pa ext4: remove unused return value of ext4_mb_release ext4: remove unused ext4_allocation_context::ac_groups_considered ext4: remove unneeded return value of ext4_mb_release_context ext4: remove unused parameter ngroup in ext4_mb_choose_next_group_*() ext4: remove unused return value of __mb_check_buddy ext4: mark the group block bitmap as corrupted before reporting an error ext4: avoid allocating blocks from corrupted group in ext4_mb_find_by_goal() ext4: avoid allocating blocks from corrupted group in ext4_mb_try_best_found() ext4: avoid dividing by 0 in mb_update_avg_fragment_size() when block bitmap corrupt ext4: avoid bb_free and bb_fragments inconsistency in mb_free_blocks() ...
-rw-r--r--fs/ext4/ext4.h8
-rw-r--r--fs/ext4/extents.c124
-rw-r--r--fs/ext4/file.c2
-rw-r--r--fs/ext4/indirect.c2
-rw-r--r--fs/ext4/inode.c90
-rw-r--r--fs/ext4/ioctl.c2
-rw-r--r--fs/ext4/mballoc.c140
-rw-r--r--fs/ext4/mballoc.h1
-rw-r--r--fs/ext4/move_extent.c10
-rw-r--r--fs/ext4/super.c2
-rw-r--r--include/trace/events/ext4.h11
11 files changed, 203 insertions, 189 deletions
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index a5d784872303..023571f8dd1b 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -252,8 +252,10 @@ struct ext4_allocation_request {
#define EXT4_MAP_MAPPED BIT(BH_Mapped)
#define EXT4_MAP_UNWRITTEN BIT(BH_Unwritten)
#define EXT4_MAP_BOUNDARY BIT(BH_Boundary)
+#define EXT4_MAP_DELAYED BIT(BH_Delay)
#define EXT4_MAP_FLAGS (EXT4_MAP_NEW | EXT4_MAP_MAPPED |\
- EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY)
+ EXT4_MAP_UNWRITTEN | EXT4_MAP_BOUNDARY |\
+ EXT4_MAP_DELAYED)
struct ext4_map_blocks {
ext4_fsblk_t m_pblk;
@@ -2912,10 +2914,10 @@ extern const struct seq_operations ext4_mb_seq_groups_ops;
extern const struct seq_operations ext4_mb_seq_structs_summary_ops;
extern int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset);
extern int ext4_mb_init(struct super_block *);
-extern int ext4_mb_release(struct super_block *);
+extern void ext4_mb_release(struct super_block *);
extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
struct ext4_allocation_request *, int *);
-extern void ext4_discard_preallocations(struct inode *, unsigned int);
+extern void ext4_discard_preallocations(struct inode *);
extern int __init ext4_init_mballoc(void);
extern void ext4_exit_mballoc(void);
extern ext4_group_t ext4_mb_prefetch(struct super_block *sb,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 01299b55a567..7669d154c05e 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -100,7 +100,7 @@ static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped)
* i_rwsem. So we can safely drop the i_data_sem here.
*/
BUG_ON(EXT4_JOURNAL(inode) == NULL);
- ext4_discard_preallocations(inode, 0);
+ ext4_discard_preallocations(inode);
up_write(&EXT4_I(inode)->i_data_sem);
*dropped = 1;
return 0;
@@ -2229,7 +2229,7 @@ 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
@@ -2241,9 +2241,9 @@ 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;
@@ -2271,30 +2271,6 @@ 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.
*/
@@ -4062,6 +4038,72 @@ 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 so we are not holding i_rwsem and delalloc info is
+ * only stabilized by i_data_sem we are going to release
+ * soon. Don't modify the extent status tree and report
+ * extent as a hole, just 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
@@ -4179,22 +4221,12 @@ 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;
}
@@ -4313,7 +4345,7 @@ got_allocated_blocks:
* not a good idea to call discard here directly,
* but otherwise we'd need to call it every free().
*/
- ext4_discard_preallocations(inode, 0);
+ ext4_discard_preallocations(inode);
if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE)
fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE;
ext4_free_blocks(handle, inode, NULL, newblock,
@@ -5357,7 +5389,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)
ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle);
down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode, 0);
+ ext4_discard_preallocations(inode);
ext4_es_remove_extent(inode, punch_start, EXT_MAX_BLOCKS - punch_start);
ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1);
@@ -5365,7 +5397,7 @@ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len)
up_write(&EXT4_I(inode)->i_data_sem);
goto out_stop;
}
- ext4_discard_preallocations(inode, 0);
+ ext4_discard_preallocations(inode);
ret = ext4_ext_shift_extents(inode, handle, punch_stop,
punch_stop - punch_start, SHIFT_LEFT);
@@ -5497,7 +5529,7 @@ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len)
goto out_stop;
down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode, 0);
+ ext4_discard_preallocations(inode);
path = ext4_find_extent(inode, offset_lblk, NULL, 0);
if (IS_ERR(path)) {
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 6aa15dafc677..54d6ff22585c 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -174,7 +174,7 @@ static int ext4_release_file(struct inode *inode, struct file *filp)
(atomic_read(&inode->i_writecount) == 1) &&
!EXT4_I(inode)->i_reserved_data_blocks) {
down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode, 0);
+ ext4_discard_preallocations(inode);
up_write(&EXT4_I(inode)->i_data_sem);
}
if (is_dx(inode) && filp->private_data)
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index a9f3716119d3..d8ca7f64f952 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -714,7 +714,7 @@ static int ext4_ind_trunc_restart_fn(handle_t *handle, struct inode *inode,
* i_rwsem. So we can safely drop the i_data_sem here.
*/
BUG_ON(EXT4_JOURNAL(inode) == NULL);
- ext4_discard_preallocations(inode, 0);
+ ext4_discard_preallocations(inode);
up_write(&EXT4_I(inode)->i_data_sem);
*dropped = 1;
return 0;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 5af1b0b8680e..2ccf3b5e3a7c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -371,7 +371,7 @@ void ext4_da_update_reserve_space(struct inode *inode,
*/
if ((ei->i_reserved_data_blocks == 0) &&
!inode_is_open_for_write(inode))
- ext4_discard_preallocations(inode, 0);
+ ext4_discard_preallocations(inode);
}
static int __check_block_validity(struct inode *inode, const char *func,
@@ -515,6 +515,8 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
map->m_len = retval;
} else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) {
map->m_pblk = 0;
+ map->m_flags |= ext4_es_is_delayed(&es) ?
+ EXT4_MAP_DELAYED : 0;
retval = es.es_len - (map->m_lblk - es.es_lblk);
if (retval > map->m_len)
retval = map->m_len;
@@ -1703,11 +1705,8 @@ 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.
@@ -1749,26 +1748,11 @@ 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) {
+ 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)) {
@@ -1783,11 +1767,21 @@ add_delayed:
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
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;
}
@@ -3268,6 +3262,9 @@ static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
iomap->addr = (u64) map->m_pblk << blkbits;
if (flags & IOMAP_DAX)
iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off;
+ } else if (map->m_flags & EXT4_MAP_DELAYED) {
+ iomap->type = IOMAP_DELALLOC;
+ iomap->addr = IOMAP_NULL_ADDR;
} else {
iomap->type = IOMAP_HOLE;
iomap->addr = IOMAP_NULL_ADDR;
@@ -3430,35 +3427,11 @@ const struct iomap_ops ext4_iomap_overwrite_ops = {
.iomap_end = ext4_iomap_end,
};
-static bool ext4_iomap_is_delalloc(struct inode *inode,
- struct ext4_map_blocks *map)
-{
- struct extent_status es;
- ext4_lblk_t offset = 0, end = map->m_lblk + map->m_len - 1;
-
- ext4_es_find_extent_range(inode, &ext4_es_is_delayed,
- map->m_lblk, end, &es);
-
- if (!es.es_len || es.es_lblk > end)
- return false;
-
- if (es.es_lblk > map->m_lblk) {
- map->m_len = es.es_lblk - map->m_lblk;
- return false;
- }
-
- offset = map->m_lblk - es.es_lblk;
- map->m_len = es.es_len - offset;
-
- return true;
-}
-
static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
loff_t length, unsigned int flags,
struct iomap *iomap, struct iomap *srcmap)
{
int ret;
- bool delalloc = false;
struct ext4_map_blocks map;
u8 blkbits = inode->i_blkbits;
@@ -3499,13 +3472,8 @@ static int ext4_iomap_begin_report(struct inode *inode, loff_t offset,
ret = ext4_map_blocks(NULL, inode, &map, 0);
if (ret < 0)
return ret;
- if (ret == 0)
- delalloc = ext4_iomap_is_delalloc(inode, &map);
-
set_iomap:
ext4_set_iomap(inode, iomap, &map, offset, length, flags);
- if (delalloc && iomap->type == IOMAP_HOLE)
- iomap->type = IOMAP_DELALLOC;
return 0;
}
@@ -4015,12 +3983,12 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
/* If there are blocks to remove, do it */
if (stop_block > first_block) {
+ ext4_lblk_t hole_len = stop_block - first_block;
down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode, 0);
+ ext4_discard_preallocations(inode);
- ext4_es_remove_extent(inode, first_block,
- stop_block - first_block);
+ ext4_es_remove_extent(inode, first_block, hole_len);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ret = ext4_ext_remove_space(inode, first_block,
@@ -4029,6 +3997,8 @@ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
ret = ext4_ind_remove_space(handle, inode, first_block,
stop_block);
+ ext4_es_insert_extent(inode, first_block, hole_len, ~0,
+ EXTENT_STATUS_HOLE);
up_write(&EXT4_I(inode)->i_data_sem);
}
ext4_fc_track_range(handle, inode, first_block, stop_block);
@@ -4170,7 +4140,7 @@ int ext4_truncate(struct inode *inode)
down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode, 0);
+ ext4_discard_preallocations(inode);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
err = ext4_ext_truncate(handle, inode);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index aa6be510eb8f..7160a71044c8 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -467,7 +467,7 @@ static long swap_inode_boot_loader(struct super_block *sb,
ext4_reset_inode_seed(inode);
ext4_reset_inode_seed(inode_bl);
- ext4_discard_preallocations(inode, 0);
+ ext4_discard_preallocations(inode);
err = ext4_mark_inode_dirty(handle, inode);
if (err < 0) {
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index f44f668e407f..e4f7cf9d89c4 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -564,14 +564,14 @@ static void mb_free_blocks_double(struct inode *inode, struct ext4_buddy *e4b,
blocknr = ext4_group_first_block_no(sb, e4b->bd_group);
blocknr += EXT4_C2B(EXT4_SB(sb), first + i);
+ ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+ EXT4_GROUP_INFO_BBITMAP_CORRUPT);
ext4_grp_locked_error(sb, e4b->bd_group,
inode ? inode->i_ino : 0,
blocknr,
"freeing block already freed "
"(bit %u)",
first + i);
- ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
- EXT4_GROUP_INFO_BBITMAP_CORRUPT);
}
mb_clear_bit(first + i, e4b->bd_info->bb_bitmap);
}
@@ -677,7 +677,7 @@ do { \
} \
} while (0)
-static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
+static void __mb_check_buddy(struct ext4_buddy *e4b, char *file,
const char *function, int line)
{
struct super_block *sb = e4b->bd_sb;
@@ -696,7 +696,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
void *buddy2;
if (e4b->bd_info->bb_check_counter++ % 10)
- return 0;
+ return;
while (order > 1) {
buddy = mb_find_buddy(e4b, order, &max);
@@ -758,7 +758,7 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
grp = ext4_get_group_info(sb, e4b->bd_group);
if (!grp)
- return NULL;
+ return;
list_for_each(cur, &grp->bb_prealloc_list) {
ext4_group_t groupnr;
struct ext4_prealloc_space *pa;
@@ -768,7 +768,6 @@ static int __mb_check_buddy(struct ext4_buddy *e4b, char *file,
for (i = 0; i < pa->pa_len; i++)
MB_CHECK_ASSERT(mb_test_bit(k + i, buddy));
}
- return 0;
}
#undef MB_CHECK_ASSERT
#define mb_check_buddy(e4b) __mb_check_buddy(e4b, \
@@ -842,7 +841,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp)
struct ext4_sb_info *sbi = EXT4_SB(sb);
int new_order;
- if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_free == 0)
+ if (!test_opt2(sb, MB_OPTIMIZE_SCAN) || grp->bb_fragments == 0)
return;
new_order = mb_avg_fragment_size_order(sb,
@@ -871,7 +870,7 @@ mb_update_avg_fragment_size(struct super_block *sb, struct ext4_group_info *grp)
* cr level needs an update.
*/
static void ext4_mb_choose_next_group_p2_aligned(struct ext4_allocation_context *ac,
- enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+ enum criteria *new_cr, ext4_group_t *group)
{
struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
struct ext4_group_info *iter;
@@ -945,7 +944,7 @@ ext4_mb_find_good_group_avg_frag_lists(struct ext4_allocation_context *ac, int o
* order. Updates *new_cr if cr level needs an update.
*/
static void ext4_mb_choose_next_group_goal_fast(struct ext4_allocation_context *ac,
- enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+ enum criteria *new_cr, ext4_group_t *group)
{
struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
struct ext4_group_info *grp = NULL;
@@ -990,7 +989,7 @@ static void ext4_mb_choose_next_group_goal_fast(struct ext4_allocation_context *
* much and fall to CR_GOAL_LEN_SLOW in that case.
*/
static void ext4_mb_choose_next_group_best_avail(struct ext4_allocation_context *ac,
- enum criteria *new_cr, ext4_group_t *group, ext4_group_t ngroups)
+ enum criteria *new_cr, ext4_group_t *group)
{
struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
struct ext4_group_info *grp = NULL;
@@ -1125,11 +1124,11 @@ static void ext4_mb_choose_next_group(struct ext4_allocation_context *ac,
}
if (*new_cr == CR_POWER2_ALIGNED) {
- ext4_mb_choose_next_group_p2_aligned(ac, new_cr, group, ngroups);
+ ext4_mb_choose_next_group_p2_aligned(ac, new_cr, group);
} else if (*new_cr == CR_GOAL_LEN_FAST) {
- ext4_mb_choose_next_group_goal_fast(ac, new_cr, group, ngroups);
+ ext4_mb_choose_next_group_goal_fast(ac, new_cr, group);
} else if (*new_cr == CR_BEST_AVAIL_LEN) {
- ext4_mb_choose_next_group_best_avail(ac, new_cr, group, ngroups);
+ ext4_mb_choose_next_group_best_avail(ac, new_cr, group);
} else {
/*
* TODO: For CR=2, we can arrange groups in an rb tree sorted by
@@ -1233,6 +1232,24 @@ 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)))
+ mb_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
@@ -1891,11 +1908,6 @@ 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
*/
@@ -1909,21 +1921,31 @@ 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_mark_group_bitmap_corrupted(sb, e4b->bd_group,
EXT4_GROUP_INFO_BBITMAP_CORRUPT);
- }
- goto done;
+ ext4_grp_locked_error(sb, e4b->bd_group,
+ inode ? inode->i_ino : 0, blocknr,
+ "freeing already freed block (bit %u); block bitmap corrupt.",
+ block);
+ 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--;
@@ -1948,9 +1970,9 @@ 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);
mb_update_avg_fragment_size(sb, e4b->bd_info);
+check:
mb_check_buddy(e4b);
}
@@ -2276,6 +2298,9 @@ void ext4_mb_try_best_found(struct ext4_allocation_context *ac,
return;
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) {
@@ -2283,6 +2308,7 @@ void 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);
}
@@ -2309,12 +2335,10 @@ 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 */
@@ -2347,6 +2371,7 @@ 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);
@@ -2380,12 +2405,12 @@ void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac,
k = mb_find_next_zero_bit(buddy, max, 0);
if (k >= max) {
+ ext4_mark_group_bitmap_corrupted(ac->ac_sb,
+ e4b->bd_group,
+ EXT4_GROUP_INFO_BBITMAP_CORRUPT);
ext4_grp_locked_error(ac->ac_sb, e4b->bd_group, 0, 0,
"%d free clusters of order %d. But found 0",
grp->bb_counters[i], i);
- ext4_mark_group_bitmap_corrupted(ac->ac_sb,
- e4b->bd_group,
- EXT4_GROUP_INFO_BBITMAP_CORRUPT);
break;
}
ac->ac_found++;
@@ -2436,12 +2461,12 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
* free blocks even though group info says we
* have free blocks
*/
+ ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+ EXT4_GROUP_INFO_BBITMAP_CORRUPT);
ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
"%d free clusters as per "
"group info. But bitmap says 0",
free);
- ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
- EXT4_GROUP_INFO_BBITMAP_CORRUPT);
break;
}
@@ -2467,12 +2492,12 @@ void ext4_mb_complex_scan_group(struct ext4_allocation_context *ac,
if (WARN_ON(ex.fe_len <= 0))
break;
if (free < ex.fe_len) {
+ ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
+ EXT4_GROUP_INFO_BBITMAP_CORRUPT);
ext4_grp_locked_error(sb, e4b->bd_group, 0, 0,
"%d free clusters as per "
"group info. But got %d blocks",
free, ex.fe_len);
- ext4_mark_group_bitmap_corrupted(sb, e4b->bd_group,
- EXT4_GROUP_INFO_BBITMAP_CORRUPT);
/*
* The number of free blocks differs. This mostly
* indicate that the bitmap is corrupt. So exit
@@ -3725,7 +3750,7 @@ static int ext4_mb_cleanup_pa(struct ext4_group_info *grp)
return count;
}
-int ext4_mb_release(struct super_block *sb)
+void ext4_mb_release(struct super_block *sb)
{
ext4_group_t ngroups = ext4_get_groups_count(sb);
ext4_group_t i;
@@ -3801,8 +3826,6 @@ int ext4_mb_release(struct super_block *sb)
}
free_percpu(sbi->s_locality_groups);
-
- return 0;
}
static inline int ext4_issue_discard(struct super_block *sb,
@@ -5284,7 +5307,7 @@ static void ext4_mb_new_preallocation(struct ext4_allocation_context *ac)
* the caller MUST hold group/inode locks.
* TODO: optimize the case when there are no in-core structures yet
*/
-static noinline_for_stack int
+static noinline_for_stack void
ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
struct ext4_prealloc_space *pa)
{
@@ -5334,11 +5357,9 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
*/
}
atomic_add(free, &sbi->s_mb_discarded);
-
- return 0;
}
-static noinline_for_stack int
+static noinline_for_stack void
ext4_mb_release_group_pa(struct ext4_buddy *e4b,
struct ext4_prealloc_space *pa)
{
@@ -5352,13 +5373,11 @@ ext4_mb_release_group_pa(struct ext4_buddy *e4b,
if (unlikely(group != e4b->bd_group && pa->pa_len != 0)) {
ext4_warning(sb, "bad group: expected %u, group %u, pa_start %llu",
e4b->bd_group, group, pa->pa_pstart);
- return 0;
+ return;
}
mb_free_blocks(pa->pa_inode, e4b, bit, pa->pa_len);
atomic_add(pa->pa_len, &EXT4_SB(sb)->s_mb_discarded);
trace_ext4_mballoc_discard(sb, NULL, group, bit, pa->pa_len);
-
- return 0;
}
/*
@@ -5479,7 +5498,7 @@ out_dbg:
*
* FIXME!! Make sure it is valid at all the call sites
*/
-void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
+void ext4_discard_preallocations(struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct super_block *sb = inode->i_sb;
@@ -5491,9 +5510,8 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
struct rb_node *iter;
int err;
- if (!S_ISREG(inode->i_mode)) {
+ if (!S_ISREG(inode->i_mode))
return;
- }
if (EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY)
return;
@@ -5501,15 +5519,12 @@ void ext4_discard_preallocations(struct inode *inode, unsigned int needed)
mb_debug(sb, "discard preallocation for inode %lu\n",
inode->i_ino);
trace_ext4_discard_preallocations(inode,
- atomic_read(&ei->i_prealloc_active), needed);
-
- if (needed == 0)
- needed = UINT_MAX;
+ atomic_read(&ei->i_prealloc_active));
repeat:
/* first, collect all pa's in the inode */
write_lock(&ei->i_prealloc_lock);
- for (iter = rb_first(&ei->i_prealloc_node); iter && needed;
+ for (iter = rb_first(&ei->i_prealloc_node); iter;
iter = rb_next(iter)) {
pa = rb_entry(iter, struct ext4_prealloc_space,
pa_node.inode_node);
@@ -5533,7 +5548,6 @@ repeat:
spin_unlock(&pa->pa_lock);
rb_erase(&pa->pa_node.inode_node, &ei->i_prealloc_node);
list_add(&pa->u.pa_tmp_list, &list);
- needed--;
continue;
}
@@ -5943,7 +5957,7 @@ static void ext4_mb_add_n_trim(struct ext4_allocation_context *ac)
/*
* release all resource we used in allocation
*/
-static int ext4_mb_release_context(struct ext4_allocation_context *ac)
+static void ext4_mb_release_context(struct ext4_allocation_context *ac)
{
struct ext4_sb_info *sbi = EXT4_SB(ac->ac_sb);
struct ext4_prealloc_space *pa = ac->ac_pa;
@@ -5980,7 +5994,6 @@ static int ext4_mb_release_context(struct ext4_allocation_context *ac)
if (ac->ac_flags & EXT4_MB_HINT_GROUP_ALLOC)
mutex_unlock(&ac->ac_lg->lg_mutex);
ext4_mb_collect_stats(ac);
- return 0;
}
static int ext4_mb_discard_preallocations(struct super_block *sb, int needed)
@@ -6761,6 +6774,9 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
bool set_trimmed = false;
void *bitmap;
+ if (unlikely(EXT4_MB_GRP_BBITMAP_CORRUPT(e4b->bd_info)))
+ return 0;
+
last = ext4_last_grp_cluster(sb, e4b->bd_group);
bitmap = e4b->bd_bitmap;
if (start == 0 && max >= last)
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index d7aeb5da7d86..56938532b4ce 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -192,7 +192,6 @@ struct ext4_allocation_context {
*/
ext4_grpblk_t ac_orig_goal_len;
- __u32 ac_groups_considered;
__u32 ac_flags; /* allocation hints */
__u16 ac_groups_scanned;
__u16 ac_groups_linear_remaining;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 3aa57376d9c2..7cd4afa4de1d 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -618,6 +618,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
goto out;
o_end = o_start + len;
+ *moved_len = 0;
while (o_start < o_end) {
struct ext4_extent *ex;
ext4_lblk_t cur_blk, next_blk;
@@ -672,7 +673,7 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
*/
ext4_double_up_write_data_sem(orig_inode, donor_inode);
/* Swap original branches with new branches */
- move_extent_per_page(o_filp, donor_inode,
+ *moved_len += move_extent_per_page(o_filp, donor_inode,
orig_page_index, donor_page_index,
offset_in_page, cur_len,
unwritten, &ret);
@@ -682,14 +683,11 @@ ext4_move_extents(struct file *o_filp, struct file *d_filp, __u64 orig_blk,
o_start += cur_len;
d_start += cur_len;
}
- *moved_len = o_start - orig_blk;
- if (*moved_len > len)
- *moved_len = len;
out:
if (*moved_len) {
- ext4_discard_preallocations(orig_inode, 0);
- ext4_discard_preallocations(donor_inode, 0);
+ ext4_discard_preallocations(orig_inode);
+ ext4_discard_preallocations(donor_inode);
}
ext4_free_ext_path(path);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index dcba0f85dfe2..0f931d0c227d 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1525,7 +1525,7 @@ void ext4_clear_inode(struct inode *inode)
ext4_fc_del(inode);
invalidate_inode_buffers(inode);
clear_inode(inode);
- ext4_discard_preallocations(inode, 0);
+ ext4_discard_preallocations(inode);
ext4_es_remove_extent(inode, 0, EXT_MAX_BLOCKS);
dquot_drop(inode);
if (EXT4_I(inode)->jinode) {
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index 65029dfb92fb..a697f4b77162 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -772,15 +772,14 @@ TRACE_EVENT(ext4_mb_release_group_pa,
);
TRACE_EVENT(ext4_discard_preallocations,
- TP_PROTO(struct inode *inode, unsigned int len, unsigned int needed),
+ TP_PROTO(struct inode *inode, unsigned int len),
- TP_ARGS(inode, len, needed),
+ TP_ARGS(inode, len),
TP_STRUCT__entry(
__field( dev_t, dev )
__field( ino_t, ino )
__field( unsigned int, len )
- __field( unsigned int, needed )
),
@@ -788,13 +787,11 @@ TRACE_EVENT(ext4_discard_preallocations,
__entry->dev = inode->i_sb->s_dev;
__entry->ino = inode->i_ino;
__entry->len = len;
- __entry->needed = needed;
),
- TP_printk("dev %d,%d ino %lu len: %u needed %u",
+ TP_printk("dev %d,%d ino %lu len: %u",
MAJOR(__entry->dev), MINOR(__entry->dev),
- (unsigned long) __entry->ino, __entry->len,
- __entry->needed)
+ (unsigned long) __entry->ino, __entry->len)
);
TRACE_EVENT(ext4_mb_discard_preallocations,