summaryrefslogtreecommitdiffstats
path: root/fs/ext4/inode.c
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-18 18:50:03 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-18 18:50:03 +0000
commit01a69402cf9d38ff180345d55c2ee51c7e89fbc7 (patch)
treeb406c5242a088c4f59c6e4b719b783f43aca6ae9 /fs/ext4/inode.c
parentAdding upstream version 6.7.12. (diff)
downloadlinux-upstream/6.8.9.tar.xz
linux-upstream/6.8.9.zip
Adding upstream version 6.8.9.upstream/6.8.9
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'fs/ext4/inode.c')
-rw-r--r--fs/ext4/inode.c125
1 files changed, 51 insertions, 74 deletions
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 61277f7f87..2ccf3b5e3a 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);