aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/ext4.h8
-rw-r--r--fs/ext4/ext4_jbd2.c5
-rw-r--r--fs/ext4/extents.c130
-rw-r--r--fs/ext4/file.c2
-rw-r--r--fs/ext4/indirect.c2
-rw-r--r--fs/ext4/inline.c3
-rw-r--r--fs/ext4/inode.c125
-rw-r--r--fs/ext4/ioctl.c6
-rw-r--r--fs/ext4/mballoc.c205
-rw-r--r--fs/ext4/mballoc.h1
-rw-r--r--fs/ext4/move_extent.c10
-rw-r--r--fs/ext4/namei.c23
-rw-r--r--fs/ext4/page-io.c2
-rw-r--r--fs/ext4/resize.c49
-rw-r--r--fs/ext4/super.c21
-rw-r--r--fs/ext4/symlink.c8
16 files changed, 322 insertions, 278 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/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index d1a2e6624401..5d8055161acd 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -235,8 +235,6 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line,
might_sleep();
- ext4_check_bdev_write_error(sb);
-
if (ext4_handle_valid(handle)) {
err = jbd2_journal_get_write_access(handle, bh);
if (err) {
@@ -244,7 +242,8 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line,
handle, err);
return err;
}
- }
+ } else
+ ext4_check_bdev_write_error(sb);
if (trigger_type == EXT4_JTR_NONE || !ext4_has_metadata_csum(sb))
return 0;
BUG_ON(trigger_type >= EXT4_JOURNAL_TRIGGER_COUNT);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index d5efe076d3d3..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,
@@ -4523,7 +4555,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
* Round up offset. This is not fallocate, we need to zero out
* blocks, so convert interior block aligned part of the range to
* unwritten and possibly manually zero out unaligned parts of the
- * range.
+ * range. Here, start and partial_begin are inclusive, end and
+ * partial_end are exclusive.
*/
start = round_up(offset, 1 << blkbits);
end = round_down((offset + len), 1 << blkbits);
@@ -4609,7 +4642,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
* disk in case of crash before zeroing trans is committed.
*/
if (ext4_should_journal_data(inode)) {
- ret = filemap_write_and_wait_range(mapping, start, end);
+ ret = filemap_write_and_wait_range(mapping, start,
+ end - 1);
if (ret) {
filemap_invalidate_unlock(mapping);
goto out_mutex;
@@ -5355,7 +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);
@@ -5363,7 +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);
@@ -5495,7 +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/inline.c b/fs/ext4/inline.c
index 9a84a5f9fef4..d5bd1e3a5d36 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -502,9 +502,8 @@ static int ext4_read_inline_folio(struct inode *inode, struct folio *folio)
BUG_ON(len > PAGE_SIZE);
kaddr = kmap_local_folio(folio, 0);
ret = ext4_read_inline_data(inode, kaddr, len, &iloc);
- flush_dcache_folio(folio);
+ kaddr = folio_zero_tail(folio, len, kaddr + len);
kunmap_local(kaddr);
- folio_zero_segment(folio, len, folio_size(folio));
folio_mark_uptodate(folio);
brelse(iloc.bh);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 61277f7f8722..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;
@@ -1261,7 +1263,7 @@ static int write_end_fn(handle_t *handle, struct inode *inode,
* We need to pick up the new inode size which generic_commit_write gave us
* `file' can be NULL - eg, when called from page_symlink().
*
- * ext4 never places buffers on inode->i_mapping->private_list. metadata
+ * ext4 never places buffers on inode->i_mapping->i_private_list. metadata
* buffers are managed internally.
*/
static int ext4_write_end(struct file *file,
@@ -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;
}
@@ -2947,7 +2941,7 @@ static int ext4_da_should_update_i_disksize(struct folio *folio,
static int ext4_da_do_write_end(struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
- struct page *page)
+ struct folio *folio)
{
struct inode *inode = mapping->host;
loff_t old_size = inode->i_size;
@@ -2958,12 +2952,13 @@ static int ext4_da_do_write_end(struct address_space *mapping,
* block_write_end() will mark the inode as dirty with I_DIRTY_PAGES
* flag, which all that's needed to trigger page writeback.
*/
- copied = block_write_end(NULL, mapping, pos, len, copied, page, NULL);
+ copied = block_write_end(NULL, mapping, pos, len, copied,
+ &folio->page, NULL);
new_i_size = pos + copied;
/*
- * It's important to update i_size while still holding page lock,
- * because page writeout could otherwise come in and zero beyond
+ * It's important to update i_size while still holding folio lock,
+ * because folio writeout could otherwise come in and zero beyond
* i_size.
*
* Since we are holding inode lock, we are sure i_disksize <=
@@ -2981,14 +2976,14 @@ static int ext4_da_do_write_end(struct address_space *mapping,
i_size_write(inode, new_i_size);
end = (new_i_size - 1) & (PAGE_SIZE - 1);
- if (copied && ext4_da_should_update_i_disksize(page_folio(page), end)) {
+ if (copied && ext4_da_should_update_i_disksize(folio, end)) {
ext4_update_i_disksize(inode, new_i_size);
disksize_changed = true;
}
}
- unlock_page(page);
- put_page(page);
+ folio_unlock(folio);
+ folio_put(folio);
if (old_size < pos)
pagecache_isize_extended(inode, old_size, pos);
@@ -3027,10 +3022,10 @@ static int ext4_da_write_end(struct file *file,
return ext4_write_inline_data_end(inode, pos, len, copied,
folio);
- if (unlikely(copied < len) && !PageUptodate(page))
+ if (unlikely(copied < len) && !folio_test_uptodate(folio))
copied = 0;
- return ext4_da_do_write_end(mapping, pos, len, copied, &folio->page);
+ return ext4_da_do_write_end(mapping, pos, len, copied, folio);
}
/*
@@ -3213,7 +3208,7 @@ static bool ext4_inode_datasync_dirty(struct inode *inode)
}
/* Any metadata buffers to write? */
- if (!list_empty(&inode->i_mapping->private_list))
+ if (!list_empty(&inode->i_mapping->i_private_list))
return true;
return inode->i_state & I_DIRTY_DATASYNC;
}
@@ -3267,6 +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;
@@ -3429,35 +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;
@@ -3498,13 +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;
}
@@ -3564,7 +3533,7 @@ static const struct address_space_operations ext4_aops = {
.direct_IO = noop_direct_IO,
.migrate_folio = buffer_migrate_folio,
.is_partially_uptodate = block_is_partially_uptodate,
- .error_remove_page = generic_error_remove_page,
+ .error_remove_folio = generic_error_remove_folio,
.swap_activate = ext4_iomap_swap_activate,
};
@@ -3581,7 +3550,7 @@ static const struct address_space_operations ext4_journalled_aops = {
.direct_IO = noop_direct_IO,
.migrate_folio = buffer_migrate_folio_norefs,
.is_partially_uptodate = block_is_partially_uptodate,
- .error_remove_page = generic_error_remove_page,
+ .error_remove_folio = generic_error_remove_folio,
.swap_activate = ext4_iomap_swap_activate,
};
@@ -3598,7 +3567,7 @@ static const struct address_space_operations ext4_da_aops = {
.direct_IO = noop_direct_IO,
.migrate_folio = buffer_migrate_folio,
.is_partially_uptodate = block_is_partially_uptodate,
- .error_remove_page = generic_error_remove_page,
+ .error_remove_folio = generic_error_remove_folio,
.swap_activate = ext4_iomap_swap_activate,
};
@@ -3630,6 +3599,12 @@ void ext4_set_aops(struct inode *inode)
inode->i_mapping->a_ops = &ext4_aops;
}
+/*
+ * Here we can't skip an unwritten buffer even though it usually reads zero
+ * because it might have data in pagecache (eg, if called from ext4_zero_range,
+ * ext4_punch_hole, etc) which needs to be properly zeroed out. Otherwise a
+ * racing writeback can come later and flush the stale pagecache to disk.
+ */
static int __ext4_block_zero_page_range(handle_t *handle,
struct address_space *mapping, loff_t from, loff_t length)
{
@@ -4008,12 +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,
@@ -4022,6 +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);
@@ -4163,7 +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 4f931f80cb34..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) {
@@ -819,11 +819,11 @@ int ext4_force_shutdown(struct super_block *sb, u32 flags)
switch (flags) {
case EXT4_GOING_FLAGS_DEFAULT:
- ret = freeze_bdev(sb->s_bdev);
+ ret = bdev_freeze(sb->s_bdev);
if (ret)
return ret;
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
- thaw_bdev(sb->s_bdev);
+ bdev_thaw(sb->s_bdev);
break;
case EXT4_GOING_FLAGS_LOGFLUSH:
set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index d72b5e3c92ec..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
@@ -1456,9 +1473,8 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
return 0;
}
- block++;
- pnum = block / blocks_per_page;
- page = find_or_create_page(inode->i_mapping, pnum, gfp);
+ /* blocks_per_page == 1, hence we need another page for the buddy */
+ page = find_or_create_page(inode->i_mapping, block + 1, gfp);
if (!page)
return -ENOMEM;
BUG_ON(page->mapping != inode->i_mapping);
@@ -1892,11 +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
*/
@@ -1910,21 +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--;
@@ -1949,17 +1970,16 @@ 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);
}
static int mb_find_extent(struct ext4_buddy *e4b, int block,
int needed, struct ext4_free_extent *ex)
{
- int next = block;
- int max, order;
+ int max, order, next;
void *buddy;
assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
@@ -1977,16 +1997,12 @@ static int mb_find_extent(struct ext4_buddy *e4b, int block,
/* find actual order */
order = mb_find_order_for_block(e4b, block);
- block = block >> order;
- ex->fe_len = 1 << order;
- ex->fe_start = block << order;
+ ex->fe_len = (1 << order) - (block & ((1 << order) - 1));
+ ex->fe_start = block;
ex->fe_group = e4b->bd_group;
- /* calc difference from given start */
- next = next - ex->fe_start;
- ex->fe_len -= next;
- ex->fe_start += next;
+ block = block >> order;
while (needed > ex->fe_len &&
mb_find_buddy(e4b, order, &max)) {
@@ -2282,6 +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) {
@@ -2289,6 +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);
}
@@ -2315,12 +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 */
@@ -2353,6 +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);
@@ -2386,12 +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++;
@@ -2442,12 +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;
}
@@ -2473,12 +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
@@ -2895,14 +2914,19 @@ repeat:
ac->ac_groups_scanned++;
if (cr == CR_POWER2_ALIGNED)
ext4_mb_simple_scan_group(ac, &e4b);
- else if ((cr == CR_GOAL_LEN_FAST ||
- cr == CR_BEST_AVAIL_LEN) &&
- sbi->s_stripe &&
- !(ac->ac_g_ex.fe_len %
- EXT4_B2C(sbi, sbi->s_stripe)))
- ext4_mb_scan_aligned(ac, &e4b);
- else
- ext4_mb_complex_scan_group(ac, &e4b);
+ else {
+ bool is_stripe_aligned = sbi->s_stripe &&
+ !(ac->ac_g_ex.fe_len %
+ EXT4_B2C(sbi, sbi->s_stripe));
+
+ if ((cr == CR_GOAL_LEN_FAST ||
+ cr == CR_BEST_AVAIL_LEN) &&
+ is_stripe_aligned)
+ ext4_mb_scan_aligned(ac, &e4b);
+
+ if (ac->ac_status == AC_STATUS_CONTINUE)
+ ext4_mb_complex_scan_group(ac, &e4b);
+ }
ext4_unlock_group(sb, group);
ext4_mb_unload_buddy(&e4b);
@@ -3726,7 +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;
@@ -3802,8 +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,
@@ -5285,7 +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)
{
@@ -5335,11 +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)
{
@@ -5353,13 +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;
}
/*
@@ -5480,7 +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;
@@ -5492,9 +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;
@@ -5502,15 +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);
@@ -5534,7 +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;
}
@@ -5944,7 +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;
@@ -5981,7 +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)
@@ -6735,11 +6747,16 @@ __acquires(bitlock)
static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb,
ext4_group_t grp)
{
- if (grp < ext4_get_groups_count(sb))
- return EXT4_CLUSTERS_PER_GROUP(sb) - 1;
- return (ext4_blocks_count(EXT4_SB(sb)->s_es) -
- ext4_group_first_block_no(sb, grp) - 1) >>
- EXT4_CLUSTER_BITS(sb);
+ unsigned long nr_clusters_in_group;
+
+ if (grp < (ext4_get_groups_count(sb) - 1))
+ nr_clusters_in_group = EXT4_CLUSTERS_PER_GROUP(sb);
+ else
+ nr_clusters_in_group = (ext4_blocks_count(EXT4_SB(sb)->s_es) -
+ ext4_group_first_block_no(sb, grp))
+ >> EXT4_CLUSTER_BITS(sb);
+
+ return nr_clusters_in_group - 1;
}
static bool ext4_trim_interrupted(void)
@@ -6753,13 +6770,18 @@ static int ext4_try_to_trim_range(struct super_block *sb,
__acquires(ext4_group_lock_ptr(sb, e4b->bd_group))
__releases(ext4_group_lock_ptr(sb, e4b->bd_group))
{
- ext4_grpblk_t next, count, free_count;
+ ext4_grpblk_t next, count, free_count, last, origin_start;
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 >= ext4_last_grp_cluster(sb, e4b->bd_group))
+ if (start == 0 && max >= last)
set_trimmed = true;
+ origin_start = start;
start = max(e4b->bd_info->bb_first_free, start);
count = 0;
free_count = 0;
@@ -6768,7 +6790,10 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
start = mb_find_next_zero_bit(bitmap, max + 1, start);
if (start > max)
break;
- next = mb_find_next_bit(bitmap, max + 1, start);
+
+ next = mb_find_next_bit(bitmap, last + 1, start);
+ if (origin_start == 0 && next >= last)
+ set_trimmed = true;
if ((next - start) >= minblocks) {
int ret = ext4_trim_extent(sb, start, next - start, e4b);
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/namei.c b/fs/ext4/namei.c
index d252935f9c8a..05b647e6bc19 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -2388,8 +2388,6 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
sb = dir->i_sb;
blocksize = sb->s_blocksize;
- if (!dentry->d_name.len)
- return -EINVAL;
if (fscrypt_is_nokey_name(dentry))
return -ENOKEY;
@@ -3591,10 +3589,14 @@ struct ext4_renament {
int dir_inlined;
};
-static int ext4_rename_dir_prepare(handle_t *handle, struct ext4_renament *ent)
+static int ext4_rename_dir_prepare(handle_t *handle, struct ext4_renament *ent, bool is_cross)
{
int retval;
+ ent->is_dir = true;
+ if (!is_cross)
+ return 0;
+
ent->dir_bh = ext4_get_first_dir_block(handle, ent->inode,
&retval, &ent->parent_de,
&ent->dir_inlined);
@@ -3612,6 +3614,9 @@ static int ext4_rename_dir_finish(handle_t *handle, struct ext4_renament *ent,
{
int retval;
+ if (!ent->dir_bh)
+ return 0;
+
ent->parent_de->inode = cpu_to_le32(dir_ino);
BUFFER_TRACE(ent->dir_bh, "call ext4_handle_dirty_metadata");
if (!ent->dir_inlined) {
@@ -3900,7 +3905,7 @@ static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir,
if (new.dir != old.dir && EXT4_DIR_LINK_MAX(new.dir))
goto end_rename;
}
- retval = ext4_rename_dir_prepare(handle, &old);
+ retval = ext4_rename_dir_prepare(handle, &old, new.dir != old.dir);
if (retval)
goto end_rename;
}
@@ -3964,7 +3969,7 @@ static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir,
}
inode_set_mtime_to_ts(old.dir, inode_set_ctime_current(old.dir));
ext4_update_dx_flag(old.dir);
- if (old.dir_bh) {
+ if (old.is_dir) {
retval = ext4_rename_dir_finish(handle, &old, new.dir->i_ino);
if (retval)
goto end_rename;
@@ -3987,7 +3992,7 @@ static int ext4_rename(struct mnt_idmap *idmap, struct inode *old_dir,
if (unlikely(retval))
goto end_rename;
- if (S_ISDIR(old.inode->i_mode)) {
+ if (old.is_dir) {
/*
* We disable fast commits here that's because the
* replay code is not yet capable of changing dot dot
@@ -4114,14 +4119,12 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
ext4_handle_sync(handle);
if (S_ISDIR(old.inode->i_mode)) {
- old.is_dir = true;
- retval = ext4_rename_dir_prepare(handle, &old);
+ retval = ext4_rename_dir_prepare(handle, &old, new.dir != old.dir);
if (retval)
goto end_rename;
}
if (S_ISDIR(new.inode->i_mode)) {
- new.is_dir = true;
- retval = ext4_rename_dir_prepare(handle, &new);
+ retval = ext4_rename_dir_prepare(handle, &new, new.dir != old.dir);
if (retval)
goto end_rename;
}
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index dfdd7e5cf038..312bc6813357 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -444,7 +444,7 @@ int ext4_bio_write_folio(struct ext4_io_submit *io, struct folio *folio,
folio_clear_error(folio);
/*
- * Comments copied from block_write_full_page:
+ * Comments copied from block_write_full_folio:
*
* The folio straddles i_size. It must be zeroed out on each and every
* writepage invocation because it may be mmapped. "A file is mapped
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 4fe061edefdd..4d4a5a32e310 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -218,35 +218,53 @@ struct ext4_new_flex_group_data {
in the flex group */
__u16 *bg_flags; /* block group flags of groups
in @groups */
+ ext4_group_t resize_bg; /* number of allocated
+ new_group_data */
ext4_group_t count; /* number of groups in @groups
*/
};
/*
+ * Avoiding memory allocation failures due to too many groups added each time.
+ */
+#define MAX_RESIZE_BG 16384
+
+/*
* alloc_flex_gd() allocates a ext4_new_flex_group_data with size of
* @flexbg_size.
*
* Returns NULL on failure otherwise address of the allocated structure.
*/
-static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size)
+static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned int flexbg_size,
+ ext4_group_t o_group, ext4_group_t n_group)
{
+ ext4_group_t last_group;
struct ext4_new_flex_group_data *flex_gd;
flex_gd = kmalloc(sizeof(*flex_gd), GFP_NOFS);
if (flex_gd == NULL)
goto out3;
- if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data))
- goto out2;
- flex_gd->count = flexbg_size;
+ if (unlikely(flexbg_size > MAX_RESIZE_BG))
+ flex_gd->resize_bg = MAX_RESIZE_BG;
+ else
+ flex_gd->resize_bg = flexbg_size;
+
+ /* Avoid allocating large 'groups' array if not needed */
+ last_group = o_group | (flex_gd->resize_bg - 1);
+ if (n_group <= last_group)
+ flex_gd->resize_bg = 1 << fls(n_group - o_group + 1);
+ else if (n_group - last_group < flex_gd->resize_bg)
+ flex_gd->resize_bg = 1 << max(fls(last_group - o_group + 1),
+ fls(n_group - last_group));
- flex_gd->groups = kmalloc_array(flexbg_size,
+ flex_gd->groups = kmalloc_array(flex_gd->resize_bg,
sizeof(struct ext4_new_group_data),
GFP_NOFS);
if (flex_gd->groups == NULL)
goto out2;
- flex_gd->bg_flags = kmalloc_array(flexbg_size, sizeof(__u16),
+ flex_gd->bg_flags = kmalloc_array(flex_gd->resize_bg, sizeof(__u16),
GFP_NOFS);
if (flex_gd->bg_flags == NULL)
goto out1;
@@ -283,7 +301,7 @@ static void free_flex_gd(struct ext4_new_flex_group_data *flex_gd)
*/
static int ext4_alloc_group_tables(struct super_block *sb,
struct ext4_new_flex_group_data *flex_gd,
- int flexbg_size)
+ unsigned int flexbg_size)
{
struct ext4_new_group_data *group_data = flex_gd->groups;
ext4_fsblk_t start_blk;
@@ -384,12 +402,12 @@ next_group:
group = group_data[0].group;
printk(KERN_DEBUG "EXT4-fs: adding a flex group with "
- "%d groups, flexbg size is %d:\n", flex_gd->count,
+ "%u groups, flexbg size is %u:\n", flex_gd->count,
flexbg_size);
for (i = 0; i < flex_gd->count; i++) {
ext4_debug(
- "adding %s group %u: %u blocks (%d free, %d mdata blocks)\n",
+ "adding %s group %u: %u blocks (%u free, %u mdata blocks)\n",
ext4_bg_has_super(sb, group + i) ? "normal" :
"no-super", group + i,
group_data[i].blocks_count,
@@ -1605,8 +1623,7 @@ exit:
static int ext4_setup_next_flex_gd(struct super_block *sb,
struct ext4_new_flex_group_data *flex_gd,
- ext4_fsblk_t n_blocks_count,
- unsigned long flexbg_size)
+ ext4_fsblk_t n_blocks_count)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
@@ -1630,7 +1647,7 @@ static int ext4_setup_next_flex_gd(struct super_block *sb,
BUG_ON(last);
ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &last);
- last_group = group | (flexbg_size - 1);
+ last_group = group | (flex_gd->resize_bg - 1);
if (last_group > n_group)
last_group = n_group;
@@ -1990,8 +2007,9 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
ext4_fsblk_t o_blocks_count;
ext4_fsblk_t n_blocks_count_retry = 0;
unsigned long last_update_time = 0;
- int err = 0, flexbg_size = 1 << sbi->s_log_groups_per_flex;
+ int err = 0;
int meta_bg;
+ unsigned int flexbg_size = ext4_flex_bg_size(sbi);
/* See if the device is actually as big as what was requested */
bh = ext4_sb_bread(sb, n_blocks_count - 1, 0);
@@ -2123,7 +2141,7 @@ retry:
if (err)
goto out;
- flex_gd = alloc_flex_gd(flexbg_size);
+ flex_gd = alloc_flex_gd(flexbg_size, o_group, n_group);
if (flex_gd == NULL) {
err = -ENOMEM;
goto out;
@@ -2132,8 +2150,7 @@ retry:
/* Add flex groups. Note that a regular group is a
* flex group with 1 group.
*/
- while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count,
- flexbg_size)) {
+ while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count)) {
if (time_is_before_jiffies(last_update_time + HZ * 10)) {
if (last_update_time)
ext4_msg(sb, KERN_INFO,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index c5fcf377ab1f..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) {
@@ -2793,15 +2793,6 @@ static int ext4_check_opt_consistency(struct fs_context *fc,
return -EINVAL;
}
- if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DIOREAD_NOLOCK)) {
- int blocksize =
- BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
- if (blocksize < PAGE_SIZE)
- ext4_msg(NULL, KERN_WARNING, "Warning: mounting with an "
- "experimental mount option 'dioread_nolock' "
- "for blocksize < PAGE_SIZE");
- }
-
err = ext4_check_test_dummy_encryption(fc, sb);
if (err)
return err;
@@ -4410,7 +4401,7 @@ static void ext4_set_def_opts(struct super_block *sb,
((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0))
set_opt(sb, DELALLOC);
- if (sb->s_blocksize == PAGE_SIZE)
+ if (sb->s_blocksize <= PAGE_SIZE)
set_opt(sb, DIOREAD_NOLOCK);
}
@@ -5864,11 +5855,9 @@ static struct bdev_handle *ext4_get_journal_blkdev(struct super_block *sb,
struct ext4_super_block *es;
int errno;
- /* see get_tree_bdev why this is needed and safe */
- up_write(&sb->s_umount);
- bdev_handle = bdev_open_by_dev(j_dev, BLK_OPEN_READ | BLK_OPEN_WRITE,
- sb, &fs_holder_ops);
- down_write(&sb->s_umount);
+ bdev_handle = bdev_open_by_dev(j_dev,
+ BLK_OPEN_READ | BLK_OPEN_WRITE | BLK_OPEN_RESTRICT_WRITES,
+ sb, &fs_holder_ops);
if (IS_ERR(bdev_handle)) {
ext4_msg(sb, KERN_ERR,
"failed to open journal device unknown-block(%u,%u) %ld",
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index 75bf1f88843c..645240cc0229 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -92,10 +92,12 @@ static const char *ext4_get_link(struct dentry *dentry, struct inode *inode,
if (!dentry) {
bh = ext4_getblk(NULL, inode, 0, EXT4_GET_BLOCKS_CACHED_NOWAIT);
- if (IS_ERR(bh))
- return ERR_CAST(bh);
- if (!bh || !ext4_buffer_uptodate(bh))
+ if (IS_ERR(bh) || !bh)
return ERR_PTR(-ECHILD);
+ if (!ext4_buffer_uptodate(bh)) {
+ brelse(bh);
+ return ERR_PTR(-ECHILD);
+ }
} else {
bh = ext4_bread(NULL, inode, 0, 0);
if (IS_ERR(bh))
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-05-04 16:31:20 +0000