From 9370bb92b2d16684ee45cf24e879c93c509162da Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Thu, 19 Dec 2024 01:47:39 +0000
Subject: [PATCH] add wifi6 8852be driver
---
kernel/fs/ext4/inode.c | 2176 +++++++++++++++++++++++++++------------------------------
1 files changed, 1,030 insertions(+), 1,146 deletions(-)
diff --git a/kernel/fs/ext4/inode.c b/kernel/fs/ext4/inode.c
index 4113b94..c1c6e0c 100644
--- a/kernel/fs/ext4/inode.c
+++ b/kernel/fs/ext4/inode.c
@@ -49,8 +49,6 @@
#include <trace/events/ext4.h>
#include <trace/events/android_fs.h>
-#define MPAGE_DA_EXTENT_TAIL 0x01
-
static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw,
struct ext4_inode_info *ei)
{
@@ -104,8 +102,8 @@
return provided == calculated;
}
-static void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
- struct ext4_inode_info *ei)
+void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw,
+ struct ext4_inode_info *ei)
{
__u32 csum;
@@ -165,32 +163,6 @@
}
/*
- * Restart the transaction associated with *handle. This does a commit,
- * so before we call here everything must be consistently dirtied against
- * this transaction.
- */
-int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
- int nblocks)
-{
- int ret;
-
- /*
- * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this
- * moment, get_block can be called only for blocks inside i_size since
- * page cache has been already dropped and writes are blocked by
- * i_mutex. So we can safely drop the i_data_sem here.
- */
- BUG_ON(EXT4_JOURNAL(inode) == NULL);
- jbd_debug(2, "restarting handle %p\n", handle);
- up_write(&EXT4_I(inode)->i_data_sem);
- ret = ext4_journal_restart(handle, nblocks);
- down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode);
-
- return ret;
-}
-
-/*
* Called at the last iput() if i_nlink is zero.
*/
void ext4_evict_inode(struct inode *inode)
@@ -208,6 +180,8 @@
trace_ext4_evict_inode(inode);
+ if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)
+ ext4_evict_ea_inode(inode);
if (inode->i_nlink) {
/*
* When journalling data dirty buffers are tracked only in the
@@ -249,6 +223,16 @@
if (ext4_should_order_data(inode))
ext4_begin_ordered_truncate(inode, 0);
truncate_inode_pages_final(&inode->i_data);
+
+ /*
+ * For inodes with journalled data, transaction commit could have
+ * dirtied the inode. And for inodes with dioread_nolock, unwritten
+ * extents converting worker could merge extents and also have dirtied
+ * the inode. Flush worker is ignoring it because of I_FREEING flag but
+ * we still need to remove the inode from the writeback lists.
+ */
+ if (!list_empty_careful(&inode->i_io_list))
+ inode_io_list_del(inode);
/*
* Protect us against freezing - iput() caller didn't have to have any
@@ -305,9 +289,9 @@
if (inode->i_blocks) {
err = ext4_truncate(inode);
if (err) {
- ext4_error(inode->i_sb,
- "couldn't truncate inode %lu (err %d)",
- inode->i_ino, err);
+ ext4_error_err(inode->i_sb, -err,
+ "couldn't truncate inode %lu (err %d)",
+ inode->i_ino, err);
goto stop_handle;
}
}
@@ -355,6 +339,14 @@
ext4_xattr_inode_array_free(ea_inode_array);
return;
no_delete:
+ /*
+ * Check out some where else accidentally dirty the evicting inode,
+ * which may probably cause inode use-after-free issues later.
+ */
+ WARN_ON_ONCE(!list_empty_careful(&inode->i_io_list));
+
+ if (!list_empty(&EXT4_I(inode)->i_fc_list))
+ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM);
ext4_clear_inode(inode); /* We must guarantee clearing of inode... */
}
@@ -410,8 +402,8 @@
* inode's preallocations.
*/
if ((ei->i_reserved_data_blocks == 0) &&
- (atomic_read(&inode->i_writecount) == 0))
- ext4_discard_preallocations(inode);
+ !inode_is_open_for_write(inode))
+ ext4_discard_preallocations(inode, 0);
}
static int __check_block_validity(struct inode *inode, const char *func,
@@ -437,7 +429,7 @@
{
int ret;
- if (IS_ENCRYPTED(inode))
+ if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode))
return fscrypt_zeroout_range(inode, lblk, pblk, len);
ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS);
@@ -469,11 +461,9 @@
*/
down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
- retval = ext4_ext_map_blocks(handle, inode, map, flags &
- EXT4_GET_BLOCKS_KEEP_SIZE);
+ retval = ext4_ext_map_blocks(handle, inode, map, 0);
} else {
- retval = ext4_ind_map_blocks(handle, inode, map, flags &
- EXT4_GET_BLOCKS_KEEP_SIZE);
+ retval = ext4_ind_map_blocks(handle, inode, map, 0);
}
up_read((&EXT4_I(inode)->i_data_sem));
@@ -530,9 +520,8 @@
#endif
map->m_flags = 0;
- ext_debug("ext4_map_blocks(): inode %lu, flag %d, max_blocks %u,"
- "logical block %lu\n", inode->i_ino, flags, map->m_len,
- (unsigned long) map->m_lblk);
+ ext_debug(inode, "flag 0x%x, max_blocks %u, logical block %lu\n",
+ flags, map->m_len, (unsigned long) map->m_lblk);
/*
* ext4_map_blocks returns an int, and m_len is an unsigned int
@@ -545,7 +534,8 @@
return -EFSCORRUPTED;
/* Lookup extent status tree firstly */
- if (ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
+ if (!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) &&
+ ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) {
map->m_pblk = ext4_es_pblock(&es) +
map->m_lblk - es.es_lblk;
@@ -563,7 +553,7 @@
map->m_len = retval;
retval = 0;
} else {
- BUG_ON(1);
+ BUG();
}
#ifdef ES_AGGRESSIVE_TEST
ext4_map_blocks_es_recheck(handle, inode, map,
@@ -578,11 +568,9 @@
*/
down_read(&EXT4_I(inode)->i_data_sem);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
- retval = ext4_ext_map_blocks(handle, inode, map, flags &
- EXT4_GET_BLOCKS_KEEP_SIZE);
+ retval = ext4_ext_map_blocks(handle, inode, map, 0);
} else {
- retval = ext4_ind_map_blocks(handle, inode, map, flags &
- EXT4_GET_BLOCKS_KEEP_SIZE);
+ retval = ext4_ind_map_blocks(handle, inode, map, 0);
}
if (retval > 0) {
unsigned int status;
@@ -599,8 +587,8 @@
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
!(status & EXTENT_STATUS_WRITTEN) &&
- ext4_find_delalloc_range(inode, map->m_lblk,
- map->m_lblk + map->m_len - 1))
+ ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk,
+ map->m_lblk + map->m_len - 1))
status |= EXTENT_STATUS_DELAYED;
ret = ext4_es_insert_extent(inode, map->m_lblk,
map->m_len, map->m_pblk, status);
@@ -667,16 +655,6 @@
*/
ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
}
-
- /*
- * Update reserved blocks/metadata blocks after successful
- * block allocation which had been deferred till now. We don't
- * support fallocate for non extent files. So we can update
- * reserve space here.
- */
- if ((retval > 0) &&
- (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE))
- ext4_da_update_reserve_space(inode, retval, 1);
}
if (retval > 0) {
@@ -700,8 +678,6 @@
if (flags & EXT4_GET_BLOCKS_ZERO &&
map->m_flags & EXT4_MAP_MAPPED &&
map->m_flags & EXT4_MAP_NEW) {
- clean_bdev_aliases(inode->i_sb->s_bdev, map->m_pblk,
- map->m_len);
ret = ext4_issue_zeroout(inode, map->m_lblk,
map->m_pblk, map->m_len);
if (ret) {
@@ -715,7 +691,7 @@
* extent status tree.
*/
if ((flags & EXT4_GET_BLOCKS_PRE_IO) &&
- ext4_es_lookup_extent(inode, map->m_lblk, &es)) {
+ ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
if (ext4_es_is_written(&es))
goto out_sem;
}
@@ -723,8 +699,8 @@
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
if (!(flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) &&
!(status & EXTENT_STATUS_WRITTEN) &&
- ext4_find_delalloc_range(inode, map->m_lblk,
- map->m_lblk + map->m_len - 1))
+ ext4_es_scan_range(inode, &ext4_es_is_delayed, map->m_lblk,
+ map->m_lblk + map->m_len - 1))
status |= EXTENT_STATUS_DELAYED;
ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
map->m_pblk, status);
@@ -765,6 +741,12 @@
return ret;
}
}
+ if (retval > 0 && (map->m_flags & EXT4_MAP_UNWRITTEN ||
+ map->m_flags & EXT4_MAP_MAPPED))
+ ext4_fc_track_range(handle, inode, map->m_lblk,
+ map->m_lblk + map->m_len - 1);
+ if (retval < 0)
+ ext_debug(inode, "failed with err %d\n", retval);
return retval;
}
@@ -847,136 +829,6 @@
#define DIO_MAX_BLOCKS 4096
/*
- * Get blocks function for the cases that need to start a transaction -
- * generally difference cases of direct IO and DAX IO. It also handles retries
- * in case of ENOSPC.
- */
-static int ext4_get_block_trans(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int flags)
-{
- int dio_credits;
- handle_t *handle;
- int retries = 0;
- int ret;
-
- /* Trim mapping request to maximum we can map at once for DIO */
- if (bh_result->b_size >> inode->i_blkbits > DIO_MAX_BLOCKS)
- bh_result->b_size = DIO_MAX_BLOCKS << inode->i_blkbits;
- dio_credits = ext4_chunk_trans_blocks(inode,
- bh_result->b_size >> inode->i_blkbits);
-retry:
- handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
-
- ret = _ext4_get_block(inode, iblock, bh_result, flags);
- ext4_journal_stop(handle);
-
- if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
- return ret;
-}
-
-/* Get block function for DIO reads and writes to inodes without extents */
-int ext4_dio_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh, int create)
-{
- /* We don't expect handle for direct IO */
- WARN_ON_ONCE(ext4_journal_current_handle());
-
- if (!create)
- return _ext4_get_block(inode, iblock, bh, 0);
- return ext4_get_block_trans(inode, iblock, bh, EXT4_GET_BLOCKS_CREATE);
-}
-
-/*
- * Get block function for AIO DIO writes when we create unwritten extent if
- * blocks are not allocated yet. The extent will be converted to written
- * after IO is complete.
- */
-static int ext4_dio_get_block_unwritten_async(struct inode *inode,
- sector_t iblock, struct buffer_head *bh_result, int create)
-{
- int ret;
-
- /* We don't expect handle for direct IO */
- WARN_ON_ONCE(ext4_journal_current_handle());
-
- ret = ext4_get_block_trans(inode, iblock, bh_result,
- EXT4_GET_BLOCKS_IO_CREATE_EXT);
-
- /*
- * When doing DIO using unwritten extents, we need io_end to convert
- * unwritten extents to written on IO completion. We allocate io_end
- * once we spot unwritten extent and store it in b_private. Generic
- * DIO code keeps b_private set and furthermore passes the value to
- * our completion callback in 'private' argument.
- */
- if (!ret && buffer_unwritten(bh_result)) {
- if (!bh_result->b_private) {
- ext4_io_end_t *io_end;
-
- io_end = ext4_init_io_end(inode, GFP_KERNEL);
- if (!io_end)
- return -ENOMEM;
- bh_result->b_private = io_end;
- ext4_set_io_unwritten_flag(inode, io_end);
- }
- set_buffer_defer_completion(bh_result);
- }
-
- return ret;
-}
-
-/*
- * Get block function for non-AIO DIO writes when we create unwritten extent if
- * blocks are not allocated yet. The extent will be converted to written
- * after IO is complete by ext4_direct_IO_write().
- */
-static int ext4_dio_get_block_unwritten_sync(struct inode *inode,
- sector_t iblock, struct buffer_head *bh_result, int create)
-{
- int ret;
-
- /* We don't expect handle for direct IO */
- WARN_ON_ONCE(ext4_journal_current_handle());
-
- ret = ext4_get_block_trans(inode, iblock, bh_result,
- EXT4_GET_BLOCKS_IO_CREATE_EXT);
-
- /*
- * Mark inode as having pending DIO writes to unwritten extents.
- * ext4_direct_IO_write() checks this flag and converts extents to
- * written.
- */
- if (!ret && buffer_unwritten(bh_result))
- ext4_set_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
-
- return ret;
-}
-
-static int ext4_dio_get_block_overwrite(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
-{
- int ret;
-
- ext4_debug("ext4_dio_get_block_overwrite: inode %lu, create flag %d\n",
- inode->i_ino, create);
- /* We don't expect handle for direct IO */
- WARN_ON_ONCE(ext4_journal_current_handle());
-
- ret = _ext4_get_block(inode, iblock, bh_result, 0);
- /*
- * Blocks should have been preallocated! ext4_file_write_iter() checks
- * that.
- */
- WARN_ON_ONCE(!buffer_mapped(bh_result) || buffer_unwritten(bh_result));
-
- return ret;
-}
-
-
-/*
* `handle' can be NULL if create is zero
*/
struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode,
@@ -987,7 +839,8 @@
int create = map_flags & EXT4_GET_BLOCKS_CREATE;
int err;
- J_ASSERT(handle != NULL || create == 0);
+ J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+ || handle != NULL || create == 0);
map.m_lblk = block;
map.m_len = 1;
@@ -1003,7 +856,8 @@
return ERR_PTR(-ENOMEM);
if (map.m_flags & EXT4_MAP_NEW) {
J_ASSERT(create != 0);
- J_ASSERT(handle != NULL);
+ J_ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+ || (handle != NULL));
/*
* Now that we do not always journal data, we should
@@ -1040,18 +894,20 @@
ext4_lblk_t block, int map_flags)
{
struct buffer_head *bh;
+ int ret;
bh = ext4_getblk(handle, inode, block, map_flags);
if (IS_ERR(bh))
return bh;
- if (!bh || buffer_uptodate(bh))
+ if (!bh || ext4_buffer_uptodate(bh))
return bh;
- ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1, &bh);
- wait_on_buffer(bh);
- if (buffer_uptodate(bh))
- return bh;
- put_bh(bh);
- return ERR_PTR(-EIO);
+
+ ret = ext4_read_bh_lock(bh, REQ_META | REQ_PRIO, true);
+ if (ret) {
+ put_bh(bh);
+ return ERR_PTR(ret);
+ }
+ return bh;
}
/* Read a contiguous batch of blocks. */
@@ -1071,9 +927,8 @@
for (i = 0; i < bh_count; i++)
/* Note that NULL bhs[i] is valid because of holes. */
- if (bhs[i] && !buffer_uptodate(bhs[i]))
- ll_rw_block(REQ_OP_READ, REQ_META | REQ_PRIO, 1,
- &bhs[i]);
+ if (bhs[i] && !ext4_buffer_uptodate(bhs[i]))
+ ext4_read_bh_lock(bhs[i], REQ_META | REQ_PRIO, false);
if (!wait)
return 0;
@@ -1190,8 +1045,9 @@
int err = 0;
unsigned blocksize = inode->i_sb->s_blocksize;
unsigned bbits;
- struct buffer_head *bh, *head, *wait[2], **wait_bh = wait;
- bool decrypt = false;
+ struct buffer_head *bh, *head, *wait[2];
+ int nr_wait = 0;
+ int i;
BUG_ON(!PageLocked(page));
BUG_ON(from > PAGE_SIZE);
@@ -1222,7 +1078,6 @@
if (err)
break;
if (buffer_new(bh)) {
- clean_bdev_bh_alias(bh);
if (PageUptodate(page)) {
clear_buffer_new(bh);
set_buffer_uptodate(bh);
@@ -1243,23 +1098,33 @@
if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
!buffer_unwritten(bh) &&
(block_start < from || block_end > to)) {
- ll_rw_block(REQ_OP_READ, 0, 1, &bh);
- *wait_bh++ = bh;
- decrypt = fscrypt_inode_uses_fs_layer_crypto(inode);
+ ext4_read_bh_lock(bh, 0, false);
+ wait[nr_wait++] = bh;
}
}
/*
* If we issued read requests, let them complete.
*/
- while (wait_bh > wait) {
- wait_on_buffer(*--wait_bh);
- if (!buffer_uptodate(*wait_bh))
+ for (i = 0; i < nr_wait; i++) {
+ wait_on_buffer(wait[i]);
+ if (!buffer_uptodate(wait[i]))
err = -EIO;
}
- if (unlikely(err))
+ if (unlikely(err)) {
page_zero_new_buffers(page, from, to);
- else if (decrypt)
- err = fscrypt_decrypt_pagecache_blocks(page, PAGE_SIZE, 0);
+ } else if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
+ for (i = 0; i < nr_wait; i++) {
+ int err2;
+
+ err2 = fscrypt_decrypt_pagecache_blocks(page, blocksize,
+ bh_offset(wait[i]));
+ if (err2) {
+ clear_buffer_uptodate(wait[i]);
+ err = err2;
+ }
+ }
+ }
+
return err;
}
#endif
@@ -1319,6 +1184,13 @@
page = grab_cache_page_write_begin(mapping, index, flags);
if (!page)
return -ENOMEM;
+ /*
+ * The same as page allocation, we prealloc buffer heads before
+ * starting the handle.
+ */
+ if (!page_has_buffers(page))
+ create_empty_buffers(page, inode->i_sb->s_blocksize, 0);
+
unlock_page(page);
retry_journal:
@@ -1433,7 +1305,8 @@
trace_android_fs_datawrite_end(inode, pos, len);
trace_ext4_write_end(inode, pos, len, copied);
- if (inline_data) {
+ if (inline_data &&
+ ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
ret = ext4_write_inline_data_end(inode, pos, len,
copied, page);
if (ret < 0) {
@@ -1442,6 +1315,7 @@
goto errout;
}
copied = ret;
+ ret = 0;
} else
copied = block_write_end(file, mapping, pos,
len, copied, page, fsdata);
@@ -1466,15 +1340,16 @@
* filesystems.
*/
if (i_size_changed || inline_data)
- ext4_mark_inode_dirty(handle, inode);
+ ret = ext4_mark_inode_dirty(handle, inode);
+errout:
if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode))
/* if we have allocated more blocks and copied
* less. We will have blocks allocated outside
* inode->i_size. So truncate them
*/
ext4_orphan_add(handle, inode);
-errout:
+
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
@@ -1558,6 +1433,7 @@
goto errout;
}
copied = ret;
+ ret = 0;
} else if (unlikely(copied < len) && !PageUptodate(page)) {
copied = 0;
ext4_journalled_zero_new_buffers(handle, page, from, to);
@@ -1587,6 +1463,7 @@
ret = ret2;
}
+errout:
if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode))
/* if we have allocated more blocks and copied
* less. We will have blocks allocated outside
@@ -1594,7 +1471,6 @@
*/
ext4_orphan_add(handle, inode);
-errout:
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
@@ -1643,7 +1519,7 @@
return 0; /* success */
}
-static void ext4_da_release_space(struct inode *inode, int to_free)
+void ext4_da_release_space(struct inode *inode, int to_free)
{
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
@@ -1678,64 +1554,6 @@
dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free));
}
-static void ext4_da_page_release_reservation(struct page *page,
- unsigned int offset,
- unsigned int length)
-{
- int to_release = 0, contiguous_blks = 0;
- struct buffer_head *head, *bh;
- unsigned int curr_off = 0;
- struct inode *inode = page->mapping->host;
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- unsigned int stop = offset + length;
- int num_clusters;
- ext4_fsblk_t lblk;
-
- BUG_ON(stop > PAGE_SIZE || stop < length);
-
- head = page_buffers(page);
- bh = head;
- do {
- unsigned int next_off = curr_off + bh->b_size;
-
- if (next_off > stop)
- break;
-
- if ((offset <= curr_off) && (buffer_delay(bh))) {
- to_release++;
- contiguous_blks++;
- clear_buffer_delay(bh);
- } else if (contiguous_blks) {
- lblk = page->index <<
- (PAGE_SHIFT - inode->i_blkbits);
- lblk += (curr_off >> inode->i_blkbits) -
- contiguous_blks;
- ext4_es_remove_extent(inode, lblk, contiguous_blks);
- contiguous_blks = 0;
- }
- curr_off = next_off;
- } while ((bh = bh->b_this_page) != head);
-
- if (contiguous_blks) {
- lblk = page->index << (PAGE_SHIFT - inode->i_blkbits);
- lblk += (curr_off >> inode->i_blkbits) - contiguous_blks;
- ext4_es_remove_extent(inode, lblk, contiguous_blks);
- }
-
- /* If we have released all the blocks belonging to a cluster, then we
- * need to release the reserved space for that cluster. */
- num_clusters = EXT4_NUM_B2C(sbi, to_release);
- while (num_clusters > 0) {
- lblk = (page->index << (PAGE_SHIFT - inode->i_blkbits)) +
- ((num_clusters - 1) << sbi->s_cluster_bits);
- if (sbi->s_cluster_ratio == 1 ||
- !ext4_find_delalloc_cluster(inode, lblk))
- ext4_da_release_space(inode, 1);
-
- num_clusters--;
- }
-}
-
/*
* Delayed allocation stuff
*/
@@ -1755,6 +1573,7 @@
struct ext4_map_blocks map;
struct ext4_io_submit io_submit; /* IO submission data */
unsigned int do_map:1;
+ unsigned int scanned_until_end:1;
};
static void mpage_release_unused_pages(struct mpage_da_data *mpd,
@@ -1770,13 +1589,21 @@
if (mpd->first_page >= mpd->next_page)
return;
+ mpd->scanned_until_end = 0;
index = mpd->first_page;
end = mpd->next_page - 1;
if (invalidate) {
ext4_lblk_t start, last;
start = index << (PAGE_SHIFT - inode->i_blkbits);
last = end << (PAGE_SHIFT - inode->i_blkbits);
+
+ /*
+ * avoid racing with extent status tree scans made by
+ * ext4_insert_delayed_block()
+ */
+ down_write(&EXT4_I(inode)->i_data_sem);
ext4_es_remove_extent(inode, start, last - start + 1);
+ up_write(&EXT4_I(inode)->i_data_sem);
}
pagevec_init(&pvec);
@@ -1829,6 +1656,70 @@
}
/*
+ * ext4_insert_delayed_block - adds a delayed block to the extents status
+ * tree, incrementing the reserved cluster/block
+ * count or making a pending reservation
+ * where needed
+ *
+ * @inode - file containing the newly added block
+ * @lblk - logical block to be added
+ *
+ * Returns 0 on success, negative error code on failure.
+ */
+static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+ int ret;
+ bool allocated = false;
+ bool reserved = false;
+
+ /*
+ * If the cluster containing lblk is shared with a delayed,
+ * written, or unwritten extent in a bigalloc file system, it's
+ * already been accounted for and does not need to be reserved.
+ * A pending reservation must be made for the cluster if it's
+ * shared with a written or unwritten extent and doesn't already
+ * have one. Written and unwritten extents can be purged from the
+ * extents status tree if the system is under memory pressure, so
+ * it's necessary to examine the extent tree if a search of the
+ * extents status tree doesn't get a match.
+ */
+ if (sbi->s_cluster_ratio == 1) {
+ ret = ext4_da_reserve_space(inode);
+ if (ret != 0) /* ENOSPC */
+ goto errout;
+ reserved = true;
+ } else { /* bigalloc */
+ if (!ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk)) {
+ if (!ext4_es_scan_clu(inode,
+ &ext4_es_is_mapped, lblk)) {
+ ret = ext4_clu_mapped(inode,
+ EXT4_B2C(sbi, lblk));
+ if (ret < 0)
+ goto errout;
+ if (ret == 0) {
+ ret = ext4_da_reserve_space(inode);
+ if (ret != 0) /* ENOSPC */
+ goto errout;
+ reserved = true;
+ } else {
+ allocated = true;
+ }
+ } else {
+ allocated = true;
+ }
+ }
+ }
+
+ ret = ext4_es_insert_delayed_block(inode, lblk, allocated);
+ if (ret && reserved)
+ ext4_da_release_space(inode, 1);
+
+errout:
+ return ret;
+}
+
+/*
* This function is grabs code from the very beginning of
* ext4_map_blocks, but assumes that the caller is from delayed write
* time. This function looks up the requested blocks and sets the
@@ -1851,12 +1742,11 @@
invalid_block = ~0;
map->m_flags = 0;
- ext_debug("ext4_da_map_blocks(): inode %lu, max_blocks %u,"
- "logical block %lu\n", inode->i_ino, map->m_len,
+ ext_debug(inode, "max_blocks %u, logical block %lu\n", map->m_len,
(unsigned long) map->m_lblk);
/* Lookup extent status tree firstly */
- if (ext4_es_lookup_extent(inode, iblock, &es)) {
+ 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);
@@ -1884,7 +1774,7 @@
else if (ext4_es_is_unwritten(&es))
map->m_flags |= EXT4_MAP_UNWRITTEN;
else
- BUG_ON(1);
+ BUG();
#ifdef ES_AGGRESSIVE_TEST
ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0);
@@ -1907,28 +1797,14 @@
add_delayed:
if (retval == 0) {
int ret;
+
/*
* XXX: __block_prepare_write() unmaps passed block,
* is it OK?
*/
- /*
- * If the block was allocated from previously allocated cluster,
- * then we don't need to reserve it again. However we still need
- * to reserve metadata for every block we're going to write.
- */
- if (EXT4_SB(inode->i_sb)->s_cluster_ratio == 1 ||
- !ext4_find_delalloc_cluster(inode, map->m_lblk)) {
- ret = ext4_da_reserve_space(inode);
- if (ret) {
- /* not enough space to reserve */
- retval = ret;
- goto out_unlock;
- }
- }
- ret = ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
- ~0, EXTENT_STATUS_DELAYED);
- if (ret) {
+ ret = ext4_insert_delayed_block(inode, map->m_lblk);
+ if (ret != 0) {
retval = ret;
goto out_unlock;
}
@@ -2088,6 +1964,9 @@
}
if (ret == 0)
ret = err;
+ err = ext4_jbd2_inode_add_write(handle, inode, page_offset(page), len);
+ if (ret == 0)
+ ret = err;
EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid;
err = ext4_journal_stop(handle);
if (!ret)
@@ -2169,6 +2048,15 @@
len = size & ~PAGE_MASK;
else
len = PAGE_SIZE;
+
+ /* Should never happen but for bugs in other kernel subsystems */
+ if (!page_has_buffers(page)) {
+ ext4_warning_inode(inode,
+ "page %lu does not have buffers attached", page->index);
+ ClearPageDirty(page);
+ unlock_page(page);
+ return 0;
+ }
page_bufs = page_buffers(page);
/*
@@ -2262,7 +2150,7 @@
return err;
}
-#define BH_FLAGS ((1 << BH_Unwritten) | (1 << BH_Delay))
+#define BH_FLAGS (BIT(BH_Unwritten) | BIT(BH_Delay))
/*
* mballoc gives us at most this number of blocks...
@@ -2372,7 +2260,84 @@
if (err < 0)
return err;
}
- return lblk < blocks;
+ if (lblk >= blocks) {
+ mpd->scanned_until_end = 1;
+ return 0;
+ }
+ return 1;
+}
+
+/*
+ * mpage_process_page - update page buffers corresponding to changed extent and
+ * may submit fully mapped page for IO
+ *
+ * @mpd - description of extent to map, on return next extent to map
+ * @m_lblk - logical block mapping.
+ * @m_pblk - corresponding physical mapping.
+ * @map_bh - determines on return whether this page requires any further
+ * mapping or not.
+ * Scan given page buffers corresponding to changed extent and update buffer
+ * state according to new extent state.
+ * We map delalloc buffers to their physical location, clear unwritten bits.
+ * If the given page is not fully mapped, we update @map to the next extent in
+ * the given page that needs mapping & return @map_bh as true.
+ */
+static int mpage_process_page(struct mpage_da_data *mpd, struct page *page,
+ ext4_lblk_t *m_lblk, ext4_fsblk_t *m_pblk,
+ bool *map_bh)
+{
+ struct buffer_head *head, *bh;
+ ext4_io_end_t *io_end = mpd->io_submit.io_end;
+ ext4_lblk_t lblk = *m_lblk;
+ ext4_fsblk_t pblock = *m_pblk;
+ int err = 0;
+ int blkbits = mpd->inode->i_blkbits;
+ ssize_t io_end_size = 0;
+ struct ext4_io_end_vec *io_end_vec = ext4_last_io_end_vec(io_end);
+
+ bh = head = page_buffers(page);
+ do {
+ if (lblk < mpd->map.m_lblk)
+ continue;
+ if (lblk >= mpd->map.m_lblk + mpd->map.m_len) {
+ /*
+ * Buffer after end of mapped extent.
+ * Find next buffer in the page to map.
+ */
+ mpd->map.m_len = 0;
+ mpd->map.m_flags = 0;
+ io_end_vec->size += io_end_size;
+ io_end_size = 0;
+
+ err = mpage_process_page_bufs(mpd, head, bh, lblk);
+ if (err > 0)
+ err = 0;
+ if (!err && mpd->map.m_len && mpd->map.m_lblk > lblk) {
+ io_end_vec = ext4_alloc_io_end_vec(io_end);
+ if (IS_ERR(io_end_vec)) {
+ err = PTR_ERR(io_end_vec);
+ goto out;
+ }
+ io_end_vec->offset = (loff_t)mpd->map.m_lblk << blkbits;
+ }
+ *map_bh = true;
+ goto out;
+ }
+ if (buffer_delay(bh)) {
+ clear_buffer_delay(bh);
+ bh->b_blocknr = pblock++;
+ }
+ clear_buffer_unwritten(bh);
+ io_end_size += (1 << blkbits);
+ } while (lblk++, (bh = bh->b_this_page) != head);
+
+ io_end_vec->size += io_end_size;
+ io_end_size = 0;
+ *map_bh = false;
+out:
+ *m_lblk = lblk;
+ *m_pblk = pblock;
+ return err;
}
/*
@@ -2394,12 +2359,12 @@
struct pagevec pvec;
int nr_pages, i;
struct inode *inode = mpd->inode;
- struct buffer_head *head, *bh;
int bpp_bits = PAGE_SHIFT - inode->i_blkbits;
pgoff_t start, end;
ext4_lblk_t lblk;
- sector_t pblock;
+ ext4_fsblk_t pblock;
int err;
+ bool map_bh = false;
start = mpd->map.m_lblk >> bpp_bits;
end = (mpd->map.m_lblk + mpd->map.m_len - 1) >> bpp_bits;
@@ -2415,50 +2380,19 @@
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
- bh = head = page_buffers(page);
- do {
- if (lblk < mpd->map.m_lblk)
- continue;
- if (lblk >= mpd->map.m_lblk + mpd->map.m_len) {
- /*
- * Buffer after end of mapped extent.
- * Find next buffer in the page to map.
- */
- mpd->map.m_len = 0;
- mpd->map.m_flags = 0;
- /*
- * FIXME: If dioread_nolock supports
- * blocksize < pagesize, we need to make
- * sure we add size mapped so far to
- * io_end->size as the following call
- * can submit the page for IO.
- */
- err = mpage_process_page_bufs(mpd, head,
- bh, lblk);
- pagevec_release(&pvec);
- if (err > 0)
- err = 0;
- return err;
- }
- if (buffer_delay(bh)) {
- clear_buffer_delay(bh);
- bh->b_blocknr = pblock++;
- }
- clear_buffer_unwritten(bh);
- } while (lblk++, (bh = bh->b_this_page) != head);
-
+ err = mpage_process_page(mpd, page, &lblk, &pblock,
+ &map_bh);
/*
- * FIXME: This is going to break if dioread_nolock
- * supports blocksize < pagesize as we will try to
- * convert potentially unmapped parts of inode.
+ * If map_bh is true, means page may require further bh
+ * mapping, or maybe the page was submitted for IO.
+ * So we return to call further extent mapping.
*/
- mpd->io_submit.io_end->size += PAGE_SIZE;
+ if (err < 0 || map_bh)
+ goto out;
/* Page fully mapped - let IO run! */
err = mpage_submit_page(mpd, page);
- if (err < 0) {
- pagevec_release(&pvec);
- return err;
- }
+ if (err < 0)
+ goto out;
}
pagevec_release(&pvec);
}
@@ -2466,6 +2400,9 @@
mpd->map.m_len = 0;
mpd->map.m_flags = 0;
return 0;
+out:
+ pagevec_release(&pvec);
+ return err;
}
static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd)
@@ -2497,7 +2434,7 @@
dioread_nolock = ext4_should_dioread_nolock(inode);
if (dioread_nolock)
get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
- if (map->m_flags & (1 << BH_Delay))
+ if (map->m_flags & BIT(BH_Delay))
get_blocks_flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE;
err = ext4_map_blocks(handle, inode, map, get_blocks_flags);
@@ -2513,10 +2450,6 @@
}
BUG_ON(map->m_len == 0);
- if (map->m_flags & EXT4_MAP_NEW) {
- clean_bdev_aliases(inode->i_sb->s_bdev, map->m_pblk,
- map->m_len);
- }
return 0;
}
@@ -2549,16 +2482,20 @@
int err;
loff_t disksize;
int progress = 0;
+ ext4_io_end_t *io_end = mpd->io_submit.io_end;
+ struct ext4_io_end_vec *io_end_vec;
- mpd->io_submit.io_end->offset =
- ((loff_t)map->m_lblk) << inode->i_blkbits;
+ io_end_vec = ext4_alloc_io_end_vec(io_end);
+ if (IS_ERR(io_end_vec))
+ return PTR_ERR(io_end_vec);
+ io_end_vec->offset = ((loff_t)map->m_lblk) << inode->i_blkbits;
do {
err = mpage_map_one_extent(handle, mpd);
if (err < 0) {
struct super_block *sb = inode->i_sb;
if (ext4_forced_shutdown(EXT4_SB(sb)) ||
- EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+ ext4_test_mount_flag(sb, EXT4_MF_FS_ABORTED))
goto invalidate_dirty_pages;
/*
* Let the uper layers retry transient errors.
@@ -2615,10 +2552,11 @@
EXT4_I(inode)->i_disksize = disksize;
up_write(&EXT4_I(inode)->i_data_sem);
err2 = ext4_mark_inode_dirty(handle, inode);
- if (err2)
- ext4_error(inode->i_sb,
- "Failed to mark inode %lu dirty",
- inode->i_ino);
+ if (err2) {
+ ext4_error_err(inode->i_sb, -err2,
+ "Failed to mark inode %lu dirty",
+ inode->i_ino);
+ }
if (!err)
err = err2;
}
@@ -2666,7 +2604,7 @@
long left = mpd->wbc->nr_to_write;
pgoff_t index = mpd->first_page;
pgoff_t end = mpd->last_page;
- int tag;
+ xa_mark_t tag;
int i, err = 0;
int blkbits = mpd->inode->i_blkbits;
ext4_lblk_t lblk;
@@ -2684,7 +2622,7 @@
nr_pages = pagevec_lookup_range_tag(&pvec, mapping, &index, end,
tag);
if (nr_pages == 0)
- goto out;
+ break;
for (i = 0; i < nr_pages; i++) {
struct page *page = pvec.pages[i];
@@ -2723,6 +2661,22 @@
wait_on_page_writeback(page);
BUG_ON(PageWriteback(page));
+ /*
+ * Should never happen but for buggy code in
+ * other subsystems that call
+ * set_page_dirty() without properly warning
+ * the file system first. See [1] for more
+ * information.
+ *
+ * [1] https://lore.kernel.org/linux-mm/20180103100430.GE4911@quack2.suse.cz
+ */
+ if (!page_has_buffers(page)) {
+ ext4_warning_inode(mpd->inode, "page %lu does not have buffers attached", page->index);
+ ClearPageDirty(page);
+ unlock_page(page);
+ continue;
+ }
+
if (mpd->map.m_len == 0)
mpd->first_page = page->index;
mpd->next_page = page->index + 1;
@@ -2739,6 +2693,7 @@
pagevec_release(&pvec);
cond_resched();
}
+ mpd->scanned_until_end = 1;
return 0;
out:
pagevec_release(&pvec);
@@ -2757,7 +2712,6 @@
struct inode *inode = mapping->host;
int needed_blocks, rsv_blocks = 0, ret = 0;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
- bool done;
struct blk_plug plug;
bool give_up_on_write = false;
@@ -2791,18 +2745,9 @@
* the stack trace.
*/
if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) ||
- sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
+ ext4_test_mount_flag(inode->i_sb, EXT4_MF_FS_ABORTED))) {
ret = -EROFS;
goto out_writepages;
- }
-
- if (ext4_should_dioread_nolock(inode)) {
- /*
- * We may need to convert up to one extent per block in
- * the page and we may dirty the inode.
- */
- rsv_blocks = 1 + ext4_chunk_trans_blocks(inode,
- PAGE_SIZE >> inode->i_blkbits);
}
/*
@@ -2821,6 +2766,15 @@
EXT4_STATE_MAY_INLINE_DATA));
ext4_destroy_inline_data(handle, inode);
ext4_journal_stop(handle);
+ }
+
+ if (ext4_should_dioread_nolock(inode)) {
+ /*
+ * We may need to convert up to one extent per block in
+ * the page and we may dirty the inode.
+ */
+ rsv_blocks = 1 + ext4_chunk_trans_blocks(inode,
+ PAGE_SIZE >> inode->i_blkbits);
}
if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
@@ -2843,7 +2797,6 @@
retry:
if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)
tag_pages_for_writeback(mapping, mpd.first_page, mpd.last_page);
- done = false;
blk_start_plug(&plug);
/*
@@ -2853,22 +2806,23 @@
* started.
*/
mpd.do_map = 0;
+ mpd.scanned_until_end = 0;
mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
if (!mpd.io_submit.io_end) {
ret = -ENOMEM;
goto unplug;
}
ret = mpage_prepare_extent_to_map(&mpd);
+ /* Unlock pages we didn't use */
+ mpage_release_unused_pages(&mpd, false);
/* Submit prepared bio */
ext4_io_submit(&mpd.io_submit);
ext4_put_io_end_defer(mpd.io_submit.io_end);
mpd.io_submit.io_end = NULL;
- /* Unlock pages we didn't use */
- mpage_release_unused_pages(&mpd, false);
if (ret < 0)
goto unplug;
- while (!done && mpd.first_page <= mpd.last_page) {
+ while (!mpd.scanned_until_end && wbc->nr_to_write > 0) {
/* For each extent of pages we use new io_end */
mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
if (!mpd.io_submit.io_end) {
@@ -2903,26 +2857,15 @@
trace_ext4_da_write_pages(inode, mpd.first_page, mpd.wbc);
ret = mpage_prepare_extent_to_map(&mpd);
- if (!ret) {
- if (mpd.map.m_len)
- ret = mpage_map_and_submit_extent(handle, &mpd,
+ if (!ret && mpd.map.m_len)
+ ret = mpage_map_and_submit_extent(handle, &mpd,
&give_up_on_write);
- else {
- /*
- * We scanned the whole range (or exhausted
- * nr_to_write), submitted what was mapped and
- * didn't find anything needing mapping. We are
- * done.
- */
- done = true;
- }
- }
/*
* Caution: If the handle is synchronous,
* ext4_journal_stop() can wait for transaction commit
* to finish which may depend on writeback of pages to
* complete or on page lock to be released. In that
- * case, we have to wait until after after we have
+ * case, we have to wait until after we have
* submitted all the IO, released page locks we hold,
* and dropped io_end reference (for extent conversion
* to be able to complete) before stopping the handle.
@@ -2932,10 +2875,11 @@
handle = NULL;
mpd.do_map = 0;
}
- /* Submit prepared bio */
- ext4_io_submit(&mpd.io_submit);
/* Unlock pages we didn't use */
mpage_release_unused_pages(&mpd, give_up_on_write);
+ /* Submit prepared bio */
+ ext4_io_submit(&mpd.io_submit);
+
/*
* Drop our io_end reference we got from init. We have
* to be careful and use deferred io_end finishing if
@@ -3002,7 +2946,7 @@
percpu_down_read(&sbi->s_writepages_rwsem);
trace_ext4_writepages(inode, wbc);
- ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev, wbc);
+ ret = dax_writeback_mapping_range(mapping, sbi->s_daxdev, wbc);
trace_ext4_writepages_result(inode, wbc, ret,
nr_to_write - wbc->nr_to_write);
percpu_up_read(&sbi->s_writepages_rwsem);
@@ -3212,58 +3156,42 @@
end = start + copied - 1;
/*
- * generic_write_end() will run mark_inode_dirty() if i_size
- * changes. So let's piggyback the i_disksize mark_inode_dirty
- * into that.
+ * Since we are holding inode lock, we are sure i_disksize <=
+ * i_size. We also know that if i_disksize < i_size, there are
+ * delalloc writes pending in the range upto i_size. If the end of
+ * the current write is <= i_size, there's no need to touch
+ * i_disksize since writeback will push i_disksize upto i_size
+ * eventually. If the end of the current write is > i_size and
+ * inside an allocated block (ext4_da_should_update_i_disksize()
+ * check), we need to update i_disksize here as neither
+ * ext4_writepage() nor certain ext4_writepages() paths not
+ * allocating blocks update i_disksize.
+ *
+ * Note that we defer inode dirtying to generic_write_end() /
+ * ext4_da_write_inline_data_end().
*/
new_i_size = pos + copied;
- if (copied && new_i_size > EXT4_I(inode)->i_disksize) {
+ if (copied && new_i_size > inode->i_size) {
if (ext4_has_inline_data(inode) ||
- ext4_da_should_update_i_disksize(page, end)) {
+ ext4_da_should_update_i_disksize(page, end))
ext4_update_i_disksize(inode, new_i_size);
- /* We need to mark inode dirty even if
- * new_i_size is less that inode->i_size
- * bu greater than i_disksize.(hint delalloc)
- */
- ext4_mark_inode_dirty(handle, inode);
- }
}
if (write_mode != CONVERT_INLINE_DATA &&
ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) &&
ext4_has_inline_data(inode))
- ret2 = ext4_da_write_inline_data_end(inode, pos, len, copied,
+ ret = ext4_da_write_inline_data_end(inode, pos, len, copied,
page);
else
- ret2 = generic_write_end(file, mapping, pos, len, copied,
+ ret = generic_write_end(file, mapping, pos, len, copied,
page, fsdata);
- copied = ret2;
- if (ret2 < 0)
- ret = ret2;
+ copied = ret;
ret2 = ext4_journal_stop(handle);
- if (!ret)
+ if (unlikely(ret2 && !ret))
ret = ret2;
return ret ? ret : copied;
-}
-
-static void ext4_da_invalidatepage(struct page *page, unsigned int offset,
- unsigned int length)
-{
- /*
- * Drop reserved blocks
- */
- BUG_ON(!PageLocked(page));
- if (!page_has_buffers(page))
- goto out;
-
- ext4_da_page_release_reservation(page, offset, length);
-
-out:
- ext4_invalidatepage(page, offset, length);
-
- return;
}
/*
@@ -3328,13 +3256,15 @@
{
struct inode *inode = mapping->host;
journal_t *journal;
+ sector_t ret = 0;
int err;
+ inode_lock_shared(inode);
/*
* We can get here for an inline file via the FIBMAP ioctl
*/
if (ext4_has_inline_data(inode))
- return 0;
+ goto out;
if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) &&
test_opt(inode->i_sb, DELALLOC)) {
@@ -3373,10 +3303,14 @@
jbd2_journal_unlock_updates(journal);
if (err)
- return 0;
+ goto out;
}
- return generic_block_bmap(mapping, block, ext4_get_block);
+ ret = iomap_bmap(mapping, block, &ext4_iomap_ops);
+
+out:
+ inode_unlock_shared(inode);
+ return ret;
}
static int ext4_readpage(struct file *file, struct page *page)
@@ -3390,23 +3324,20 @@
ret = ext4_readpage_inline(inode, page);
if (ret == -EAGAIN)
- return ext4_mpage_readpages(page->mapping, NULL, page, 1,
- false);
+ return ext4_mpage_readpages(inode, NULL, page);
return ret;
}
-static int
-ext4_readpages(struct file *file, struct address_space *mapping,
- struct list_head *pages, unsigned nr_pages)
+static void ext4_readahead(struct readahead_control *rac)
{
- struct inode *inode = mapping->host;
+ struct inode *inode = rac->mapping->host;
- /* If the file has inline data, no need to do readpages. */
+ /* If the file has inline data, no need to do readahead. */
if (ext4_has_inline_data(inode))
- return 0;
+ return;
- return ext4_mpage_readpages(mapping, pages, NULL, nr_pages, true);
+ ext4_mpage_readpages(inode, rac, NULL);
}
static void ext4_invalidatepage(struct page *page, unsigned int offset,
@@ -3455,7 +3386,7 @@
if (PageChecked(page))
return 0;
if (journal)
- return jbd2_journal_try_to_free_buffers(journal, page, wait);
+ return jbd2_journal_try_to_free_buffers(journal, page);
else
return try_to_free_buffers(page);
}
@@ -3464,216 +3395,215 @@
{
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
- if (journal)
- return !jbd2_transaction_committed(journal,
- EXT4_I(inode)->i_datasync_tid);
+ if (journal) {
+ if (jbd2_transaction_committed(journal,
+ EXT4_I(inode)->i_datasync_tid))
+ return false;
+ if (test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT))
+ return !list_empty(&EXT4_I(inode)->i_fc_list);
+ return true;
+ }
+
/* Any metadata buffers to write? */
if (!list_empty(&inode->i_mapping->private_list))
return true;
return inode->i_state & I_DIRTY_DATASYNC;
}
-static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
- unsigned flags, struct iomap *iomap)
+static void ext4_set_iomap(struct inode *inode, struct iomap *iomap,
+ struct ext4_map_blocks *map, loff_t offset,
+ loff_t length)
{
- struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- unsigned int blkbits = inode->i_blkbits;
- unsigned long first_block, last_block;
- struct ext4_map_blocks map;
- bool delalloc = false;
- int ret;
-
- if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
- return -EINVAL;
- first_block = offset >> blkbits;
- last_block = min_t(loff_t, (offset + length - 1) >> blkbits,
- EXT4_MAX_LOGICAL_BLOCK);
-
- if (flags & IOMAP_REPORT) {
- if (ext4_has_inline_data(inode)) {
- ret = ext4_inline_data_iomap(inode, iomap);
- if (ret != -EAGAIN) {
- if (ret == 0 && offset >= iomap->length)
- ret = -ENOENT;
- return ret;
- }
- }
- } else {
- if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
- return -ERANGE;
- }
-
- map.m_lblk = first_block;
- map.m_len = last_block - first_block + 1;
-
- if (flags & IOMAP_REPORT) {
- ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret < 0)
- return ret;
-
- if (ret == 0) {
- ext4_lblk_t end = map.m_lblk + map.m_len - 1;
- struct extent_status es;
-
- ext4_es_find_delayed_extent_range(inode, map.m_lblk, end, &es);
-
- if (!es.es_len || es.es_lblk > end) {
- /* entire range is a hole */
- } else if (es.es_lblk > map.m_lblk) {
- /* range starts with a hole */
- map.m_len = es.es_lblk - map.m_lblk;
- } else {
- ext4_lblk_t offs = 0;
-
- if (es.es_lblk < map.m_lblk)
- offs = map.m_lblk - es.es_lblk;
- map.m_lblk = es.es_lblk + offs;
- map.m_len = es.es_len - offs;
- delalloc = true;
- }
- }
- } else if (flags & IOMAP_WRITE) {
- int dio_credits;
- handle_t *handle;
- int retries = 0;
-
- /* Trim mapping request to maximum we can map at once for DIO */
- if (map.m_len > DIO_MAX_BLOCKS)
- map.m_len = DIO_MAX_BLOCKS;
- dio_credits = ext4_chunk_trans_blocks(inode, map.m_len);
-retry:
- /*
- * Either we allocate blocks and then we don't get unwritten
- * extent so we have reserved enough credits, or the blocks
- * are already allocated and unwritten and in that case
- * extent conversion fits in the credits as well.
- */
- handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS,
- dio_credits);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
-
- ret = ext4_map_blocks(handle, inode, &map,
- EXT4_GET_BLOCKS_CREATE_ZERO);
- if (ret < 0) {
- ext4_journal_stop(handle);
- if (ret == -ENOSPC &&
- ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
- return ret;
- }
-
- /*
- * If we added blocks beyond i_size, we need to make sure they
- * will get truncated if we crash before updating i_size in
- * ext4_iomap_end(). For faults we don't need to do that (and
- * even cannot because for orphan list operations inode_lock is
- * required) - if we happen to instantiate block beyond i_size,
- * it is because we race with truncate which has already added
- * the inode to the orphan list.
- */
- if (!(flags & IOMAP_FAULT) && first_block + map.m_len >
- (i_size_read(inode) + (1 << blkbits) - 1) >> blkbits) {
- int err;
-
- err = ext4_orphan_add(handle, inode);
- if (err < 0) {
- ext4_journal_stop(handle);
- return err;
- }
- }
- ext4_journal_stop(handle);
- } else {
- ret = ext4_map_blocks(NULL, inode, &map, 0);
- if (ret < 0)
- return ret;
- }
+ u8 blkbits = inode->i_blkbits;
/*
* Writes that span EOF might trigger an I/O size update on completion,
- * so consider them to be dirty for the purposes of O_DSYNC, even if
- * there is no other metadata changes being made or are pending here.
+ * so consider them to be dirty for the purpose of O_DSYNC, even if
+ * there is no other metadata changes being made or are pending.
*/
iomap->flags = 0;
if (ext4_inode_datasync_dirty(inode) ||
offset + length > i_size_read(inode))
iomap->flags |= IOMAP_F_DIRTY;
- iomap->bdev = inode->i_sb->s_bdev;
- iomap->dax_dev = sbi->s_daxdev;
- iomap->offset = (u64)first_block << blkbits;
- iomap->length = (u64)map.m_len << blkbits;
- if (ret == 0) {
- iomap->type = delalloc ? IOMAP_DELALLOC : IOMAP_HOLE;
- iomap->addr = IOMAP_NULL_ADDR;
- } else {
- if (map.m_flags & EXT4_MAP_MAPPED) {
- iomap->type = IOMAP_MAPPED;
- } else if (map.m_flags & EXT4_MAP_UNWRITTEN) {
- iomap->type = IOMAP_UNWRITTEN;
- } else {
- WARN_ON_ONCE(1);
- return -EIO;
- }
- iomap->addr = (u64)map.m_pblk << blkbits;
- }
-
- if (map.m_flags & EXT4_MAP_NEW)
+ if (map->m_flags & EXT4_MAP_NEW)
iomap->flags |= IOMAP_F_NEW;
+ iomap->bdev = inode->i_sb->s_bdev;
+ iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev;
+ iomap->offset = (u64) map->m_lblk << blkbits;
+ iomap->length = (u64) map->m_len << blkbits;
+
+ if ((map->m_flags & EXT4_MAP_MAPPED) &&
+ !ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ iomap->flags |= IOMAP_F_MERGED;
+
+ /*
+ * Flags passed to ext4_map_blocks() for direct I/O writes can result
+ * in m_flags having both EXT4_MAP_MAPPED and EXT4_MAP_UNWRITTEN bits
+ * set. In order for any allocated unwritten extents to be converted
+ * into written extents correctly within the ->end_io() handler, we
+ * need to ensure that the iomap->type is set appropriately. Hence, the
+ * reason why we need to check whether the EXT4_MAP_UNWRITTEN bit has
+ * been set first.
+ */
+ if (map->m_flags & EXT4_MAP_UNWRITTEN) {
+ iomap->type = IOMAP_UNWRITTEN;
+ iomap->addr = (u64) map->m_pblk << blkbits;
+ } else if (map->m_flags & EXT4_MAP_MAPPED) {
+ iomap->type = IOMAP_MAPPED;
+ iomap->addr = (u64) map->m_pblk << blkbits;
+ } else {
+ iomap->type = IOMAP_HOLE;
+ iomap->addr = IOMAP_NULL_ADDR;
+ }
+}
+
+static int ext4_iomap_alloc(struct inode *inode, struct ext4_map_blocks *map,
+ unsigned int flags)
+{
+ handle_t *handle;
+ u8 blkbits = inode->i_blkbits;
+ int ret, dio_credits, m_flags = 0, retries = 0;
+
+ /*
+ * Trim the mapping request to the maximum value that we can map at
+ * once for direct I/O.
+ */
+ if (map->m_len > DIO_MAX_BLOCKS)
+ map->m_len = DIO_MAX_BLOCKS;
+ dio_credits = ext4_chunk_trans_blocks(inode, map->m_len);
+
+retry:
+ /*
+ * Either we allocate blocks and then don't get an unwritten extent, so
+ * in that case we have reserved enough credits. Or, the blocks are
+ * already allocated and unwritten. In that case, the extent conversion
+ * fits into the credits as well.
+ */
+ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits);
+ if (IS_ERR(handle))
+ return PTR_ERR(handle);
+
+ /*
+ * DAX and direct I/O are the only two operations that are currently
+ * supported with IOMAP_WRITE.
+ */
+ WARN_ON(!IS_DAX(inode) && !(flags & IOMAP_DIRECT));
+ if (IS_DAX(inode))
+ m_flags = EXT4_GET_BLOCKS_CREATE_ZERO;
+ /*
+ * We use i_size instead of i_disksize here because delalloc writeback
+ * can complete at any point during the I/O and subsequently push the
+ * i_disksize out to i_size. This could be beyond where direct I/O is
+ * happening and thus expose allocated blocks to direct I/O reads.
+ */
+ else if (((loff_t)map->m_lblk << blkbits) >= i_size_read(inode))
+ m_flags = EXT4_GET_BLOCKS_CREATE;
+ else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+ m_flags = EXT4_GET_BLOCKS_IO_CREATE_EXT;
+
+ ret = ext4_map_blocks(handle, inode, map, m_flags);
+
+ /*
+ * We cannot fill holes in indirect tree based inodes as that could
+ * expose stale data in the case of a crash. Use the magic error code
+ * to fallback to buffered I/O.
+ */
+ if (!m_flags && !ret)
+ ret = -ENOTBLK;
+
+ ext4_journal_stop(handle);
+ if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+ goto retry;
+
+ return ret;
+}
+
+
+static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
+ unsigned flags, struct iomap *iomap, struct iomap *srcmap)
+{
+ int ret;
+ struct ext4_map_blocks map;
+ u8 blkbits = inode->i_blkbits;
+
+ if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
+ return -EINVAL;
+
+ if (WARN_ON_ONCE(ext4_has_inline_data(inode)))
+ return -ERANGE;
+
+ /*
+ * Calculate the first and last logical blocks respectively.
+ */
+ map.m_lblk = offset >> blkbits;
+ map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
+ EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1;
+
+ if (flags & IOMAP_WRITE) {
+ /*
+ * We check here if the blocks are already allocated, then we
+ * don't need to start a journal txn and we can directly return
+ * the mapping information. This could boost performance
+ * especially in multi-threaded overwrite requests.
+ */
+ if (offset + length <= i_size_read(inode)) {
+ ret = ext4_map_blocks(NULL, inode, &map, 0);
+ if (ret > 0 && (map.m_flags & EXT4_MAP_MAPPED))
+ goto out;
+ }
+ ret = ext4_iomap_alloc(inode, &map, flags);
+ } else {
+ ret = ext4_map_blocks(NULL, inode, &map, 0);
+ }
+
+ if (ret < 0)
+ return ret;
+out:
+
+ /*
+ * When inline encryption is enabled, sometimes I/O to an encrypted file
+ * has to be broken up to guarantee DUN contiguity. Handle this by
+ * limiting the length of the mapping returned.
+ */
+ map.m_len = fscrypt_limit_io_blocks(inode, map.m_lblk, map.m_len);
+
+ ext4_set_iomap(inode, iomap, &map, offset, length);
+
return 0;
+}
+
+static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset,
+ loff_t length, unsigned flags, struct iomap *iomap,
+ struct iomap *srcmap)
+{
+ int ret;
+
+ /*
+ * Even for writes we don't need to allocate blocks, so just pretend
+ * we are reading to save overhead of starting a transaction.
+ */
+ flags &= ~IOMAP_WRITE;
+ ret = ext4_iomap_begin(inode, offset, length, flags, iomap, srcmap);
+ WARN_ON_ONCE(!ret && iomap->type != IOMAP_MAPPED);
+ return ret;
}
static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
ssize_t written, unsigned flags, struct iomap *iomap)
{
- int ret = 0;
- handle_t *handle;
- int blkbits = inode->i_blkbits;
- bool truncate = false;
-
- if (!(flags & IOMAP_WRITE) || (flags & IOMAP_FAULT))
- return 0;
-
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto orphan_del;
- }
- if (ext4_update_inode_size(inode, offset + written))
- ext4_mark_inode_dirty(handle, inode);
/*
- * We may need to truncate allocated but not written blocks beyond EOF.
+ * Check to see whether an error occurred while writing out the data to
+ * the allocated blocks. If so, return the magic error code so that we
+ * fallback to buffered I/O and attempt to complete the remainder of
+ * the I/O. Any blocks that may have been allocated in preparation for
+ * the direct I/O will be reused during buffered I/O.
*/
- if (iomap->offset + iomap->length >
- ALIGN(inode->i_size, 1 << blkbits)) {
- ext4_lblk_t written_blk, end_blk;
+ if (flags & (IOMAP_WRITE | IOMAP_DIRECT) && written == 0)
+ return -ENOTBLK;
- written_blk = (offset + written) >> blkbits;
- end_blk = (offset + length) >> blkbits;
- if (written_blk < end_blk && ext4_can_truncate(inode))
- truncate = true;
- }
- /*
- * Remove inode from orphan list if we were extending a inode and
- * everything went fine.
- */
- if (!truncate && inode->i_nlink &&
- !list_empty(&EXT4_I(inode)->i_orphan))
- ext4_orphan_del(handle, inode);
- ext4_journal_stop(handle);
- if (truncate) {
- ext4_truncate_failed_write(inode);
-orphan_del:
- /*
- * If truncate failed early the inode might still be on the
- * orphan list; we need to make sure the inode is removed from
- * the orphan list in that case.
- */
- if (inode->i_nlink)
- ext4_orphan_del(NULL, inode);
- }
- return ret;
+ return 0;
}
const struct iomap_ops ext4_iomap_ops = {
@@ -3681,310 +3611,94 @@
.iomap_end = ext4_iomap_end,
};
-static int ext4_end_io_dio(struct kiocb *iocb, loff_t offset,
- ssize_t size, void *private)
+const struct iomap_ops ext4_iomap_overwrite_ops = {
+ .iomap_begin = ext4_iomap_overwrite_begin,
+ .iomap_end = ext4_iomap_end,
+};
+
+static bool ext4_iomap_is_delalloc(struct inode *inode,
+ struct ext4_map_blocks *map)
{
- ext4_io_end_t *io_end = private;
+ struct extent_status es;
+ ext4_lblk_t offset = 0, end = map->m_lblk + map->m_len - 1;
- /* if not async direct IO just return */
- if (!io_end)
- return 0;
+ ext4_es_find_extent_range(inode, &ext4_es_is_delayed,
+ map->m_lblk, end, &es);
- ext_debug("ext4_end_io_dio(): io_end 0x%p "
- "for inode %lu, iocb 0x%p, offset %llu, size %zd\n",
- io_end, io_end->inode->i_ino, iocb, offset, size);
+ 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;
+
+ if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK)
+ return -EINVAL;
+
+ if (ext4_has_inline_data(inode)) {
+ ret = ext4_inline_data_iomap(inode, iomap);
+ if (ret != -EAGAIN) {
+ if (ret == 0 && offset >= iomap->length)
+ ret = -ENOENT;
+ return ret;
+ }
+ }
/*
- * Error during AIO DIO. We cannot convert unwritten extents as the
- * data was not written. Just clear the unwritten flag and drop io_end.
+ * Calculate the first and last logical block respectively.
*/
- if (size <= 0) {
- ext4_clear_io_unwritten_flag(io_end);
- size = 0;
+ map.m_lblk = offset >> blkbits;
+ map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits,
+ EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1;
+
+ /*
+ * Fiemap callers may call for offset beyond s_bitmap_maxbytes.
+ * So handle it here itself instead of querying ext4_map_blocks().
+ * Since ext4_map_blocks() will warn about it and will return
+ * -EIO error.
+ */
+ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+ if (offset >= sbi->s_bitmap_maxbytes) {
+ map.m_flags = 0;
+ goto set_iomap;
+ }
}
- io_end->offset = offset;
- io_end->size = size;
- ext4_put_io_end(io_end);
+
+ 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);
+ if (delalloc && iomap->type == IOMAP_HOLE)
+ iomap->type = IOMAP_DELALLOC;
return 0;
}
-/*
- * Handling of direct IO writes.
- *
- * For ext4 extent files, ext4 will do direct-io write even to holes,
- * preallocated extents, and those write extend the file, no need to
- * fall back to buffered IO.
- *
- * For holes, we fallocate those blocks, mark them as unwritten
- * If those blocks were preallocated, we mark sure they are split, but
- * still keep the range to write as unwritten.
- *
- * The unwritten extents will be converted to written when DIO is completed.
- * For async direct IO, since the IO may still pending when return, we
- * set up an end_io call back function, which will do the conversion
- * when async direct IO completed.
- *
- * If the O_DIRECT write will extend the file then add this inode to the
- * orphan list. So recovery will truncate it back to the original size
- * if the machine crashes during the write.
- *
- */
-static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
-{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- struct ext4_inode_info *ei = EXT4_I(inode);
- ssize_t ret;
- loff_t offset = iocb->ki_pos;
- size_t count = iov_iter_count(iter);
- int overwrite = 0;
- get_block_t *get_block_func = NULL;
- int dio_flags = 0;
- loff_t final_size = offset + count;
- int orphan = 0;
- handle_t *handle;
-
- if (final_size > inode->i_size || final_size > ei->i_disksize) {
- /* Credits for sb + inode write */
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
- }
- ret = ext4_orphan_add(handle, inode);
- if (ret) {
- ext4_journal_stop(handle);
- goto out;
- }
- orphan = 1;
- ext4_update_i_disksize(inode, inode->i_size);
- ext4_journal_stop(handle);
- }
-
- BUG_ON(iocb->private == NULL);
-
- /*
- * Make all waiters for direct IO properly wait also for extent
- * conversion. This also disallows race between truncate() and
- * overwrite DIO as i_dio_count needs to be incremented under i_mutex.
- */
- inode_dio_begin(inode);
-
- /* If we do a overwrite dio, i_mutex locking can be released */
- overwrite = *((int *)iocb->private);
-
- if (overwrite)
- inode_unlock(inode);
-
- /*
- * For extent mapped files we could direct write to holes and fallocate.
- *
- * Allocated blocks to fill the hole are marked as unwritten to prevent
- * parallel buffered read to expose the stale data before DIO complete
- * the data IO.
- *
- * As to previously fallocated extents, ext4 get_block will just simply
- * mark the buffer mapped but still keep the extents unwritten.
- *
- * For non AIO case, we will convert those unwritten extents to written
- * after return back from blockdev_direct_IO. That way we save us from
- * allocating io_end structure and also the overhead of offloading
- * the extent convertion to a workqueue.
- *
- * For async DIO, the conversion needs to be deferred when the
- * IO is completed. The ext4 end_io callback function will be
- * called to take care of the conversion work. Here for async
- * case, we allocate an io_end structure to hook to the iocb.
- */
- iocb->private = NULL;
- if (overwrite)
- get_block_func = ext4_dio_get_block_overwrite;
- else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) ||
- round_down(offset, i_blocksize(inode)) >= inode->i_size) {
- get_block_func = ext4_dio_get_block;
- dio_flags = DIO_LOCKING | DIO_SKIP_HOLES;
- } else if (is_sync_kiocb(iocb)) {
- get_block_func = ext4_dio_get_block_unwritten_sync;
- dio_flags = DIO_LOCKING;
- } else {
- get_block_func = ext4_dio_get_block_unwritten_async;
- dio_flags = DIO_LOCKING;
- }
- ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
- get_block_func, ext4_end_io_dio, NULL,
- dio_flags);
-
- if (ret > 0 && !overwrite && ext4_test_inode_state(inode,
- EXT4_STATE_DIO_UNWRITTEN)) {
- int err;
- /*
- * for non AIO case, since the IO is already
- * completed, we could do the conversion right here
- */
- err = ext4_convert_unwritten_extents(NULL, inode,
- offset, ret);
- if (err < 0)
- ret = err;
- ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
- }
-
- inode_dio_end(inode);
- /* take i_mutex locking again if we do a ovewrite dio */
- if (overwrite)
- inode_lock(inode);
-
- if (ret < 0 && final_size > inode->i_size)
- ext4_truncate_failed_write(inode);
-
- /* Handle extending of i_size after direct IO write */
- if (orphan) {
- int err;
-
- /* Credits for sb + inode write */
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
- if (IS_ERR(handle)) {
- /*
- * We wrote the data but cannot extend
- * i_size. Bail out. In async io case, we do
- * not return error here because we have
- * already submmitted the corresponding
- * bio. Returning error here makes the caller
- * think that this IO is done and failed
- * resulting in race with bio's completion
- * handler.
- */
- if (!ret)
- ret = PTR_ERR(handle);
- if (inode->i_nlink)
- ext4_orphan_del(NULL, inode);
-
- goto out;
- }
- if (inode->i_nlink)
- ext4_orphan_del(handle, inode);
- if (ret > 0) {
- loff_t end = offset + ret;
- if (end > inode->i_size || end > ei->i_disksize) {
- ext4_update_i_disksize(inode, end);
- if (end > inode->i_size)
- i_size_write(inode, end);
- /*
- * We're going to return a positive `ret'
- * here due to non-zero-length I/O, so there's
- * no way of reporting error returns from
- * ext4_mark_inode_dirty() to userspace. So
- * ignore it.
- */
- ext4_mark_inode_dirty(handle, inode);
- }
- }
- err = ext4_journal_stop(handle);
- if (ret == 0)
- ret = err;
- }
-out:
- return ret;
-}
-
-static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
-{
- struct address_space *mapping = iocb->ki_filp->f_mapping;
- struct inode *inode = mapping->host;
- size_t count = iov_iter_count(iter);
- ssize_t ret;
- loff_t offset = iocb->ki_pos;
- loff_t size = i_size_read(inode);
-
- if (offset >= size)
- return 0;
-
- /*
- * Shared inode_lock is enough for us - it protects against concurrent
- * writes & truncates and since we take care of writing back page cache,
- * we are protected against page writeback as well.
- */
- if (iocb->ki_flags & IOCB_NOWAIT) {
- if (!inode_trylock_shared(inode))
- return -EAGAIN;
- } else {
- inode_lock_shared(inode);
- }
-
- ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
- iocb->ki_pos + count - 1);
- if (ret)
- goto out_unlock;
- ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
- iter, ext4_dio_get_block, NULL, NULL, 0);
-out_unlock:
- inode_unlock_shared(inode);
- return ret;
-}
-
-static ssize_t ext4_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- size_t count = iov_iter_count(iter);
- loff_t offset = iocb->ki_pos;
- ssize_t ret;
- int rw = iov_iter_rw(iter);
-
- if (!fscrypt_dio_supported(iocb, iter))
- return 0;
-
- if (fsverity_active(inode))
- return 0;
-
- /*
- * If we are doing data journalling we don't support O_DIRECT
- */
- if (ext4_should_journal_data(inode))
- return 0;
-
- /* Let buffer I/O handle the inline data case. */
- if (ext4_has_inline_data(inode))
- return 0;
-
- if (trace_android_fs_dataread_start_enabled() &&
- (rw == READ)) {
- char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
-
- path = android_fstrace_get_pathname(pathbuf,
- MAX_TRACE_PATHBUF_LEN,
- inode);
- trace_android_fs_dataread_start(inode, offset, count,
- current->pid, path,
- current->comm);
- }
- if (trace_android_fs_datawrite_start_enabled() &&
- (rw == WRITE)) {
- char *path, pathbuf[MAX_TRACE_PATHBUF_LEN];
-
- path = android_fstrace_get_pathname(pathbuf,
- MAX_TRACE_PATHBUF_LEN,
- inode);
- trace_android_fs_datawrite_start(inode, offset, count,
- current->pid, path,
- current->comm);
- }
- trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
- if (iov_iter_rw(iter) == READ)
- ret = ext4_direct_IO_read(iocb, iter);
- else
- ret = ext4_direct_IO_write(iocb, iter);
- trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
-
- if (trace_android_fs_dataread_start_enabled() &&
- (rw == READ))
- trace_android_fs_dataread_end(inode, offset, count);
- if (trace_android_fs_datawrite_start_enabled() &&
- (rw == WRITE))
- trace_android_fs_datawrite_end(inode, offset, count);
-
- return ret;
-}
+const struct iomap_ops ext4_iomap_report_ops = {
+ .iomap_begin = ext4_iomap_begin_report,
+};
/*
* Pages can be marked dirty completely asynchronously from ext4's journalling
@@ -4012,9 +3726,16 @@
return __set_page_dirty_buffers(page);
}
+static int ext4_iomap_swap_activate(struct swap_info_struct *sis,
+ struct file *file, sector_t *span)
+{
+ return iomap_swapfile_activate(sis, file, span,
+ &ext4_iomap_report_ops);
+}
+
static const struct address_space_operations ext4_aops = {
.readpage = ext4_readpage,
- .readpages = ext4_readpages,
+ .readahead = ext4_readahead,
.writepage = ext4_writepage,
.writepages = ext4_writepages,
.write_begin = ext4_write_begin,
@@ -4023,15 +3744,16 @@
.bmap = ext4_bmap,
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
- .direct_IO = ext4_direct_IO,
+ .direct_IO = noop_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
+ .swap_activate = ext4_iomap_swap_activate,
};
static const struct address_space_operations ext4_journalled_aops = {
.readpage = ext4_readpage,
- .readpages = ext4_readpages,
+ .readahead = ext4_readahead,
.writepage = ext4_writepage,
.writepages = ext4_writepages,
.write_begin = ext4_write_begin,
@@ -4040,26 +3762,28 @@
.bmap = ext4_bmap,
.invalidatepage = ext4_journalled_invalidatepage,
.releasepage = ext4_releasepage,
- .direct_IO = ext4_direct_IO,
+ .direct_IO = noop_direct_IO,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
+ .swap_activate = ext4_iomap_swap_activate,
};
static const struct address_space_operations ext4_da_aops = {
.readpage = ext4_readpage,
- .readpages = ext4_readpages,
+ .readahead = ext4_readahead,
.writepage = ext4_writepage,
.writepages = ext4_writepages,
.write_begin = ext4_da_write_begin,
.write_end = ext4_da_write_end,
.set_page_dirty = ext4_set_page_dirty,
.bmap = ext4_bmap,
- .invalidatepage = ext4_da_invalidatepage,
+ .invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
- .direct_IO = ext4_direct_IO,
+ .direct_IO = noop_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
.error_remove_page = generic_error_remove_page,
+ .swap_activate = ext4_iomap_swap_activate,
};
static const struct address_space_operations ext4_dax_aops = {
@@ -4068,6 +3792,7 @@
.set_page_dirty = noop_set_page_dirty,
.bmap = ext4_bmap,
.invalidatepage = noop_invalidatepage,
+ .swap_activate = ext4_iomap_swap_activate,
};
void ext4_set_aops(struct inode *inode)
@@ -4141,18 +3866,18 @@
set_buffer_uptodate(bh);
if (!buffer_uptodate(bh)) {
- err = -EIO;
- ll_rw_block(REQ_OP_READ, 0, 1, &bh);
- wait_on_buffer(bh);
- /* Uhhuh. Read error. Complain and punt. */
- if (!buffer_uptodate(bh))
+ err = ext4_read_bh_lock(bh, 0, true);
+ if (err)
goto unlock;
if (fscrypt_inode_uses_fs_layer_crypto(inode)) {
/* We expect the key to be set. */
BUG_ON(!fscrypt_has_encryption_key(inode));
- BUG_ON(blocksize != PAGE_SIZE);
- WARN_ON_ONCE(fscrypt_decrypt_pagecache_blocks(
- page, PAGE_SIZE, 0));
+ err = fscrypt_decrypt_pagecache_blocks(page, blocksize,
+ bh_offset(bh));
+ if (err) {
+ clear_buffer_uptodate(bh);
+ goto unlock;
+ }
}
}
if (ext4_should_journal_data(inode)) {
@@ -4185,7 +3910,7 @@
* starting from file offset 'from'. The range to be zero'd must
* be contained with in one block. If the specified range exceeds
* the end of the block it will be shortened to end of the block
- * that cooresponds to 'from'
+ * that corresponds to 'from'
*/
static int ext4_block_zero_page_range(handle_t *handle,
struct address_space *mapping, loff_t from, loff_t length)
@@ -4292,6 +4017,8 @@
loff_t len)
{
handle_t *handle;
+ int ret;
+
loff_t size = i_size_read(inode);
WARN_ON(!inode_is_locked(inode));
@@ -4305,10 +4032,10 @@
if (IS_ERR(handle))
return PTR_ERR(handle);
ext4_update_i_disksize(inode, size);
- ext4_mark_inode_dirty(handle, inode);
+ ret = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
- return 0;
+ return ret;
}
static void ext4_wait_dax_page(struct ext4_inode_info *ei)
@@ -4352,29 +4079,19 @@
* Returns: 0 on success or negative on failure
*/
-int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
+int ext4_punch_hole(struct file *file, loff_t offset, loff_t length)
{
+ struct inode *inode = file_inode(file);
struct super_block *sb = inode->i_sb;
ext4_lblk_t first_block, stop_block;
struct address_space *mapping = inode->i_mapping;
- loff_t first_block_offset, last_block_offset;
+ loff_t first_block_offset, last_block_offset, max_length;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
handle_t *handle;
unsigned int credits;
- int ret = 0;
-
- if (!S_ISREG(inode->i_mode))
- return -EOPNOTSUPP;
+ int ret = 0, ret2 = 0;
trace_ext4_punch_hole(inode, offset, length, 0);
-
- ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
- if (ext4_has_inline_data(inode)) {
- down_write(&EXT4_I(inode)->i_mmap_sem);
- ret = ext4_convert_inline_data(inode);
- up_write(&EXT4_I(inode)->i_mmap_sem);
- if (ret)
- return ret;
- }
/*
* Write out all dirty pages to avoid race conditions
@@ -4403,6 +4120,14 @@
offset;
}
+ /*
+ * For punch hole the length + offset needs to be within one block
+ * before last range. Adjust the length if it goes beyond that limit.
+ */
+ max_length = sbi->s_bitmap_maxbytes - inode->i_sb->s_blocksize;
+ if (offset + length > max_length)
+ length = max_length - offset;
+
if (offset & (sb->s_blocksize - 1) ||
(offset + length) & (sb->s_blocksize - 1)) {
/*
@@ -4417,6 +4142,10 @@
/* Wait all existing dio workers, newcomers will block on i_mutex */
inode_dio_wait(inode);
+
+ ret = file_modified(file);
+ if (ret)
+ goto out_mutex;
/*
* Prevent page faults from reinstantiating pages we have released from
@@ -4464,7 +4193,7 @@
if (stop_block > first_block) {
down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode);
+ ext4_discard_preallocations(inode, 0);
ret = ext4_es_remove_extent(inode, first_block,
stop_block - first_block);
@@ -4482,11 +4211,14 @@
up_write(&EXT4_I(inode)->i_data_sem);
}
+ ext4_fc_track_range(handle, inode, first_block, stop_block);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
inode->i_mtime = inode->i_ctime = current_time(inode);
- ext4_mark_inode_dirty(handle, inode);
+ ret2 = ext4_mark_inode_dirty(handle, inode);
+ if (unlikely(ret2))
+ ret = ret2;
if (ret >= 0)
ext4_update_inode_fsync_trans(handle, inode, 1);
out_stop:
@@ -4555,7 +4287,7 @@
{
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int credits;
- int err = 0;
+ int err = 0, err2;
handle_t *handle;
struct address_space *mapping = inode->i_mapping;
@@ -4569,9 +4301,7 @@
trace_ext4_truncate_enter(inode);
if (!ext4_can_truncate(inode))
- return 0;
-
- ext4_clear_inode_flag(inode, EXT4_INODE_EOFBLOCKS);
+ goto out_trace;
if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
@@ -4580,16 +4310,15 @@
int has_inline = 1;
err = ext4_inline_data_truncate(inode, &has_inline);
- if (err)
- return err;
- if (has_inline)
- return 0;
+ if (err || has_inline)
+ goto out_trace;
}
/* If we zero-out tail of the page, we have to create jinode for jbd2 */
if (inode->i_size & (inode->i_sb->s_blocksize - 1)) {
- if (ext4_inode_attach_jinode(inode) < 0)
- return 0;
+ err = ext4_inode_attach_jinode(inode);
+ if (err)
+ goto out_trace;
}
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
@@ -4598,8 +4327,10 @@
credits = ext4_blocks_for_truncate(inode);
handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
- if (IS_ERR(handle))
- return PTR_ERR(handle);
+ if (IS_ERR(handle)) {
+ err = PTR_ERR(handle);
+ goto out_trace;
+ }
if (inode->i_size & (inode->i_sb->s_blocksize - 1))
ext4_block_truncate_page(handle, mapping, inode->i_size);
@@ -4619,7 +4350,7 @@
down_write(&EXT4_I(inode)->i_data_sem);
- ext4_discard_preallocations(inode);
+ ext4_discard_preallocations(inode, 0);
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
err = ext4_ext_truncate(handle, inode);
@@ -4645,9 +4376,12 @@
ext4_orphan_del(handle, inode);
inode->i_mtime = inode->i_ctime = current_time(inode);
- ext4_mark_inode_dirty(handle, inode);
+ err2 = ext4_mark_inode_dirty(handle, inode);
+ if (unlikely(err2 && !err))
+ err = err2;
ext4_journal_stop(handle);
+out_trace:
trace_ext4_truncate_exit(inode);
return err;
}
@@ -4658,21 +4392,22 @@
* data in memory that is needed to recreate the on-disk version of this
* inode.
*/
-static int __ext4_get_inode_loc(struct inode *inode,
- struct ext4_iloc *iloc, int in_mem)
+static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino,
+ struct ext4_iloc *iloc, int in_mem,
+ ext4_fsblk_t *ret_block)
{
struct ext4_group_desc *gdp;
struct buffer_head *bh;
- struct super_block *sb = inode->i_sb;
ext4_fsblk_t block;
+ struct blk_plug plug;
int inodes_per_block, inode_offset;
iloc->bh = NULL;
- if (inode->i_ino < EXT4_ROOT_INO ||
- inode->i_ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
+ if (ino < EXT4_ROOT_INO ||
+ ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))
return -EFSCORRUPTED;
- iloc->block_group = (inode->i_ino - 1) / EXT4_INODES_PER_GROUP(sb);
+ iloc->block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
gdp = ext4_get_group_desc(sb, iloc->block_group, NULL);
if (!gdp)
return -EIO;
@@ -4681,27 +4416,28 @@
* Figure out the offset within the block group inode table
*/
inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
- inode_offset = ((inode->i_ino - 1) %
+ inode_offset = ((ino - 1) %
EXT4_INODES_PER_GROUP(sb));
- block = ext4_inode_table(sb, gdp) + (inode_offset / inodes_per_block);
iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb);
+
+ block = ext4_inode_table(sb, gdp);
+ if ((block <= le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) ||
+ (block >= ext4_blocks_count(EXT4_SB(sb)->s_es))) {
+ ext4_error(sb, "Invalid inode table block %llu in "
+ "block_group %u", block, iloc->block_group);
+ return -EFSCORRUPTED;
+ }
+ block += (inode_offset / inodes_per_block);
bh = sb_getblk(sb, block);
if (unlikely(!bh))
return -ENOMEM;
+ if (ext4_simulate_fail(sb, EXT4_SIM_INODE_EIO))
+ goto simulate_eio;
if (!buffer_uptodate(bh)) {
lock_buffer(bh);
- /*
- * If the buffer has the write error flag, we have failed
- * to write out another inode in the same block. In this
- * case, we don't have to read the block because we may
- * read the old inode data successfully.
- */
- if (buffer_write_io_error(bh) && !buffer_uptodate(bh))
- set_buffer_uptodate(bh);
-
- if (buffer_uptodate(bh)) {
+ if (ext4_buffer_uptodate(bh)) {
/* someone brought it uptodate while we waited */
unlock_buffer(bh);
goto has_buffer;
@@ -4753,6 +4489,7 @@
* If we need to do any I/O, try to pre-readahead extra
* blocks from the inode table.
*/
+ blk_start_plug(&plug);
if (EXT4_SB(sb)->s_inode_readahead_blks) {
ext4_fsblk_t b, end, table;
unsigned num;
@@ -4771,7 +4508,7 @@
if (end > table)
end = table;
while (b <= end)
- sb_breadahead_unmovable(sb, b++);
+ ext4_sb_breadahead_unmovable(sb, b++);
}
/*
@@ -4779,14 +4516,14 @@
* has in-inode xattrs, or we don't have this inode in memory.
* Read the block from disk.
*/
- trace_ext4_load_inode(inode);
- get_bh(bh);
- bh->b_end_io = end_buffer_read_sync;
- submit_bh(REQ_OP_READ, REQ_META | REQ_PRIO, bh);
+ trace_ext4_load_inode(sb, ino);
+ ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO, NULL);
+ blk_finish_plug(&plug);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
- EXT4_ERROR_INODE_BLOCK(inode, block,
- "unable to read itable block");
+ simulate_eio:
+ if (ret_block)
+ *ret_block = block;
brelse(bh);
return -EIO;
}
@@ -4796,16 +4533,50 @@
return 0;
}
-int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
+static int __ext4_get_inode_loc_noinmem(struct inode *inode,
+ struct ext4_iloc *iloc)
{
- /* We have all inode data except xattrs in memory here. */
- return __ext4_get_inode_loc(inode, iloc,
- !ext4_test_inode_state(inode, EXT4_STATE_XATTR));
+ ext4_fsblk_t err_blk = 0;
+ int ret;
+
+ ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, iloc, 0,
+ &err_blk);
+
+ if (ret == -EIO)
+ ext4_error_inode_block(inode, err_blk, EIO,
+ "unable to read itable block");
+
+ return ret;
}
-static bool ext4_should_use_dax(struct inode *inode)
+int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc)
{
- if (!test_opt(inode->i_sb, DAX))
+ ext4_fsblk_t err_blk = 0;
+ int ret;
+
+ /* We have all inode data except xattrs in memory here. */
+ ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, iloc,
+ !ext4_test_inode_state(inode, EXT4_STATE_XATTR), &err_blk);
+
+ if (ret == -EIO)
+ ext4_error_inode_block(inode, err_blk, EIO,
+ "unable to read itable block");
+
+ return ret;
+}
+
+
+int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino,
+ struct ext4_iloc *iloc)
+{
+ return __ext4_get_inode_loc(sb, ino, iloc, 0, NULL);
+}
+
+static bool ext4_should_enable_dax(struct inode *inode)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+ if (test_opt2(inode->i_sb, DAX_NEVER))
return false;
if (!S_ISREG(inode->i_mode))
return false;
@@ -4817,13 +4588,20 @@
return false;
if (ext4_test_inode_flag(inode, EXT4_INODE_VERITY))
return false;
- return true;
+ if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags))
+ return false;
+ if (test_opt(inode->i_sb, DAX_ALWAYS))
+ return true;
+
+ return ext4_test_inode_flag(inode, EXT4_INODE_DAX);
}
-void ext4_set_inode_flags(struct inode *inode)
+void ext4_set_inode_flags(struct inode *inode, bool init)
{
unsigned int flags = EXT4_I(inode)->i_flags;
unsigned int new_fl = 0;
+
+ WARN_ON_ONCE(IS_DAX(inode) && init);
if (flags & EXT4_SYNC_FL)
new_fl |= S_SYNC;
@@ -4835,8 +4613,13 @@
new_fl |= S_NOATIME;
if (flags & EXT4_DIRSYNC_FL)
new_fl |= S_DIRSYNC;
- if (ext4_should_use_dax(inode))
+
+ /* Because of the way inode_set_flags() works we must preserve S_DAX
+ * here if already set. */
+ new_fl |= (inode->i_flags & S_DAX);
+ if (init && ext4_should_enable_dax(inode))
new_fl |= S_DAX;
+
if (flags & EXT4_ENCRYPT_FL)
new_fl |= S_ENCRYPTED;
if (flags & EXT4_CASEFOLD_FL)
@@ -4877,11 +4660,15 @@
__le32 *magic = (void *)raw_inode +
EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize;
- if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize + sizeof(__le32) <=
- EXT4_INODE_SIZE(inode->i_sb) &&
+ if (EXT4_INODE_HAS_XATTR_SPACE(inode) &&
*magic == cpu_to_le32(EXT4_XATTR_MAGIC)) {
+ int err;
+
ext4_set_inode_state(inode, EXT4_STATE_XATTR);
- return ext4_find_inline_data_nolock(inode);
+ err = ext4_find_inline_data_nolock(inode);
+ if (!err && ext4_has_inline_data(inode))
+ ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
+ return err;
} else
EXT4_I(inode)->i_inline_off = 0;
return 0;
@@ -4915,6 +4702,24 @@
return inode_peek_iversion(inode);
}
+static const char *check_igot_inode(struct inode *inode, ext4_iget_flags flags)
+
+{
+ if (flags & EXT4_IGET_EA_INODE) {
+ if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
+ return "missing EA_INODE flag";
+ if (ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
+ EXT4_I(inode)->i_file_acl)
+ return "ea_inode with extended attributes";
+ } else {
+ if ((EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
+ return "unexpected EA_INODE flag";
+ }
+ if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD))
+ return "unexpected bad inode w/o EXT4_IGET_BAD";
+ return NULL;
+}
+
struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
ext4_iget_flags flags, const char *function,
unsigned int line)
@@ -4923,6 +4728,7 @@
struct ext4_inode *raw_inode;
struct ext4_inode_info *ei;
struct inode *inode;
+ const char *err_str;
journal_t *journal = EXT4_SB(sb)->s_journal;
long ret;
loff_t size;
@@ -4937,7 +4743,7 @@
(ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count))) {
if (flags & EXT4_IGET_HANDLE)
return ERR_PTR(-ESTALE);
- __ext4_error(sb, function, line,
+ __ext4_error(sb, function, line, EFSCORRUPTED, 0,
"inode #%lu: comm %s: iget: illegal inode #",
ino, current->comm);
return ERR_PTR(-EFSCORRUPTED);
@@ -4946,23 +4752,22 @@
inode = iget_locked(sb, ino);
if (!inode)
return ERR_PTR(-ENOMEM);
- if (!(inode->i_state & I_NEW))
+ if (!(inode->i_state & I_NEW)) {
+ if ((err_str = check_igot_inode(inode, flags)) != NULL) {
+ ext4_error_inode(inode, function, line, 0, err_str);
+ iput(inode);
+ return ERR_PTR(-EFSCORRUPTED);
+ }
return inode;
+ }
ei = EXT4_I(inode);
iloc.bh = NULL;
- ret = __ext4_get_inode_loc(inode, &iloc, 0);
+ ret = __ext4_get_inode_loc_noinmem(inode, &iloc);
if (ret < 0)
goto bad_inode;
raw_inode = ext4_raw_inode(&iloc);
-
- if ((ino == EXT4_ROOT_INO) && (raw_inode->i_links_count == 0)) {
- ext4_error_inode(inode, function, line, 0,
- "iget: root inode unallocated");
- ret = -EFSCORRUPTED;
- goto bad_inode;
- }
if ((flags & EXT4_IGET_HANDLE) &&
(raw_inode->i_links_count == 0) && (raw_inode->i_mode == 0)) {
@@ -4998,9 +4803,11 @@
sizeof(gen));
}
- if (!ext4_inode_csum_verify(inode, raw_inode, ei)) {
- ext4_error_inode(inode, function, line, 0,
- "iget: checksum invalid");
+ if ((!ext4_inode_csum_verify(inode, raw_inode, ei) ||
+ ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) &&
+ (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))) {
+ ext4_error_inode_err(inode, function, line, 0,
+ EFSBADCRC, "iget: checksum invalid");
ret = -EFSBADCRC;
goto bad_inode;
}
@@ -5034,11 +4841,16 @@
* NeilBrown 1999oct15
*/
if (inode->i_nlink == 0) {
- if ((inode->i_mode == 0 ||
+ if ((inode->i_mode == 0 || flags & EXT4_IGET_SPECIAL ||
!(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) &&
ino != EXT4_BOOT_LOADER_INO) {
- /* this inode is deleted */
- ret = -ESTALE;
+ /* this inode is deleted or unallocated */
+ if (flags & EXT4_IGET_SPECIAL) {
+ ext4_error_inode(inode, function, line, 0,
+ "iget: special inode unallocated");
+ ret = -EFSCORRUPTED;
+ } else
+ ret = -ESTALE;
goto bad_inode;
}
/* The only unlinked inodes we let through here have
@@ -5049,7 +4861,7 @@
* not initialized on a new filesystem. */
}
ei->i_flags = le32_to_cpu(raw_inode->i_flags);
- ext4_set_inode_flags(inode);
+ ext4_set_inode_flags(inode, true);
inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo);
if (ext4_has_feature_64bit(sb))
@@ -5088,6 +4900,7 @@
for (block = 0; block < EXT4_N_BLOCKS; block++)
ei->i_data[block] = raw_inode->i_block[block];
INIT_LIST_HEAD(&ei->i_orphan);
+ ext4_fc_init_inode(&ei->vfs_inode);
/*
* Set transaction id's of transactions that have to be committed
@@ -5153,9 +4966,10 @@
goto bad_inode;
} else if (!ext4_has_inline_data(inode)) {
/* validate the block references in the inode */
- if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
- (S_ISLNK(inode->i_mode) &&
- !ext4_inode_is_fast_symlink(inode))) {
+ if (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) &&
+ (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+ (S_ISLNK(inode->i_mode) &&
+ !ext4_inode_is_fast_symlink(inode)))) {
if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
ret = ext4_ext_check_inode(inode);
else
@@ -5212,10 +5026,15 @@
goto bad_inode;
}
if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb))
- EXT4_ERROR_INODE(inode,
+ ext4_error_inode(inode, function, line, 0,
"casefold flag without casefold feature");
- brelse(iloc.bh);
+ if ((err_str = check_igot_inode(inode, flags)) != NULL) {
+ ext4_error_inode(inode, function, line, 0, err_str);
+ ret = -EFSCORRUPTED;
+ goto bad_inode;
+ }
+ brelse(iloc.bh);
unlock_new_inode(inode);
return inode;
@@ -5264,21 +5083,22 @@
return 0;
}
-struct other_inode {
- unsigned long orig_ino;
- struct ext4_inode *raw_inode;
-};
-
-static int other_inode_match(struct inode * inode, unsigned long ino,
- void *data)
+static void __ext4_update_other_inode_time(struct super_block *sb,
+ unsigned long orig_ino,
+ unsigned long ino,
+ struct ext4_inode *raw_inode)
{
- struct other_inode *oi = (struct other_inode *) data;
+ struct inode *inode;
- if ((inode->i_ino != ino) ||
- (inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW |
+ inode = find_inode_by_ino_rcu(sb, ino);
+ if (!inode)
+ return;
+
+ if ((inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW |
I_DIRTY_INODE)) ||
((inode->i_state & I_DIRTY_TIME) == 0))
- return 0;
+ return;
+
spin_lock(&inode->i_lock);
if (((inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW |
I_DIRTY_INODE)) == 0) &&
@@ -5289,16 +5109,15 @@
spin_unlock(&inode->i_lock);
spin_lock(&ei->i_raw_lock);
- EXT4_INODE_SET_XTIME(i_ctime, inode, oi->raw_inode);
- EXT4_INODE_SET_XTIME(i_mtime, inode, oi->raw_inode);
- EXT4_INODE_SET_XTIME(i_atime, inode, oi->raw_inode);
- ext4_inode_csum_set(inode, oi->raw_inode, ei);
+ EXT4_INODE_SET_XTIME(i_ctime, inode, raw_inode);
+ EXT4_INODE_SET_XTIME(i_mtime, inode, raw_inode);
+ EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
+ ext4_inode_csum_set(inode, raw_inode, ei);
spin_unlock(&ei->i_raw_lock);
- trace_ext4_other_inode_update_time(inode, oi->orig_ino);
- return -1;
+ trace_ext4_other_inode_update_time(inode, orig_ino);
+ return;
}
spin_unlock(&inode->i_lock);
- return -1;
}
/*
@@ -5308,24 +5127,24 @@
static void ext4_update_other_inodes_time(struct super_block *sb,
unsigned long orig_ino, char *buf)
{
- struct other_inode oi;
unsigned long ino;
int i, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block;
int inode_size = EXT4_INODE_SIZE(sb);
- oi.orig_ino = orig_ino;
/*
* Calculate the first inode in the inode table block. Inode
* numbers are one-based. That is, the first inode in a block
* (assuming 4k blocks and 256 byte inodes) is (n*16 + 1).
*/
ino = ((orig_ino - 1) & ~(inodes_per_block - 1)) + 1;
+ rcu_read_lock();
for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) {
if (ino == orig_ino)
continue;
- oi.raw_inode = (struct ext4_inode *) buf;
- (void) find_inode_nowait(sb, ino, other_inode_match, &oi);
+ __ext4_update_other_inode_time(sb, orig_ino, ino,
+ (struct ext4_inode *)buf);
}
+ rcu_read_unlock();
}
/*
@@ -5535,12 +5354,12 @@
if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync)
return 0;
- err = jbd2_complete_transaction(EXT4_SB(inode->i_sb)->s_journal,
+ err = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal,
EXT4_I(inode)->i_sync_tid);
} else {
struct ext4_iloc iloc;
- err = __ext4_get_inode_loc(inode, &iloc, 0);
+ err = __ext4_get_inode_loc_noinmem(inode, &iloc);
if (err)
return err;
/*
@@ -5550,8 +5369,8 @@
if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync)
sync_dirty_buffer(iloc.bh);
if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) {
- EXT4_ERROR_INODE_BLOCK(inode, iloc.bh->b_blocknr,
- "IO error syncing inode");
+ ext4_error_inode_block(inode, iloc.bh->b_blocknr, EIO,
+ "IO error syncing inode");
err = -EIO;
}
brelse(iloc.bh);
@@ -5664,6 +5483,7 @@
if (error)
return error;
}
+
if ((ia_valid & ATTR_UID && !uid_eq(attr->ia_uid, inode->i_uid)) ||
(ia_valid & ATTR_GID && !gid_eq(attr->ia_gid, inode->i_gid))) {
handle_t *handle;
@@ -5697,37 +5517,58 @@
inode->i_gid = attr->ia_gid;
error = ext4_mark_inode_dirty(handle, inode);
ext4_journal_stop(handle);
+ if (unlikely(error)) {
+ return error;
+ }
}
if (attr->ia_valid & ATTR_SIZE) {
handle_t *handle;
loff_t oldsize = inode->i_size;
- int shrink = (attr->ia_size <= inode->i_size);
+ loff_t old_disksize;
+ int shrink = (attr->ia_size < inode->i_size);
if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
- if (attr->ia_size > sbi->s_bitmap_maxbytes)
+ if (attr->ia_size > sbi->s_bitmap_maxbytes) {
return -EFBIG;
+ }
}
- if (!S_ISREG(inode->i_mode))
+ if (!S_ISREG(inode->i_mode)) {
return -EINVAL;
+ }
if (IS_I_VERSION(inode) && attr->ia_size != inode->i_size)
inode_inc_iversion(inode);
- if (ext4_should_order_data(inode) &&
- (attr->ia_size < inode->i_size)) {
- error = ext4_begin_ordered_truncate(inode,
+ if (shrink) {
+ if (ext4_should_order_data(inode)) {
+ error = ext4_begin_ordered_truncate(inode,
attr->ia_size);
- if (error)
- goto err_out;
+ if (error)
+ goto err_out;
+ }
+ /*
+ * Blocks are going to be removed from the inode. Wait
+ * for dio in flight.
+ */
+ inode_dio_wait(inode);
}
+
+ down_write(&EXT4_I(inode)->i_mmap_sem);
+
+ rc = ext4_break_layouts(inode);
+ if (rc) {
+ up_write(&EXT4_I(inode)->i_mmap_sem);
+ goto err_out;
+ }
+
if (attr->ia_size != inode->i_size) {
handle = ext4_journal_start(inode, EXT4_HT_INODE, 3);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
- goto err_out;
+ goto out_mmap_sem;
}
if (ext4_handle_valid(handle) && shrink) {
error = ext4_orphan_add(handle, inode);
@@ -5741,7 +5582,22 @@
inode->i_mtime = current_time(inode);
inode->i_ctime = inode->i_mtime;
}
+
+ if (shrink)
+ ext4_fc_track_range(handle, inode,
+ (attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
+ inode->i_sb->s_blocksize_bits,
+ EXT_MAX_BLOCKS - 1);
+ else
+ ext4_fc_track_range(
+ handle, inode,
+ (oldsize > 0 ? oldsize - 1 : oldsize) >>
+ inode->i_sb->s_blocksize_bits,
+ (attr->ia_size > 0 ? attr->ia_size - 1 : 0) >>
+ inode->i_sb->s_blocksize_bits);
+
down_write(&EXT4_I(inode)->i_data_sem);
+ old_disksize = EXT4_I(inode)->i_disksize;
EXT4_I(inode)->i_disksize = attr->ia_size;
rc = ext4_mark_inode_dirty(handle, inode);
if (!error)
@@ -5753,32 +5609,18 @@
*/
if (!error)
i_size_write(inode, attr->ia_size);
+ else
+ EXT4_I(inode)->i_disksize = old_disksize;
up_write(&EXT4_I(inode)->i_data_sem);
ext4_journal_stop(handle);
- if (error) {
- if (orphan && inode->i_nlink)
- ext4_orphan_del(NULL, inode);
- goto err_out;
+ if (error)
+ goto out_mmap_sem;
+ if (!shrink) {
+ pagecache_isize_extended(inode, oldsize,
+ inode->i_size);
+ } else if (ext4_should_journal_data(inode)) {
+ ext4_wait_for_tail_page_commit(inode);
}
- }
- if (!shrink) {
- pagecache_isize_extended(inode, oldsize, inode->i_size);
- } else {
- /*
- * Blocks are going to be removed from the inode. Wait
- * for dio in flight.
- */
- inode_dio_wait(inode);
- }
- if (orphan && ext4_should_journal_data(inode))
- ext4_wait_for_tail_page_commit(inode);
- down_write(&EXT4_I(inode)->i_mmap_sem);
-
- rc = ext4_break_layouts(inode);
- if (rc) {
- up_write(&EXT4_I(inode)->i_mmap_sem);
- error = rc;
- goto err_out;
}
/*
@@ -5786,11 +5628,16 @@
* in data=journal mode to make pages freeable.
*/
truncate_pagecache(inode, inode->i_size);
- if (shrink) {
+ /*
+ * Call ext4_truncate() even if i_size didn't change to
+ * truncate possible preallocated blocks.
+ */
+ if (attr->ia_size <= oldsize) {
rc = ext4_truncate(inode);
if (rc)
error = rc;
}
+out_mmap_sem:
up_write(&EXT4_I(inode)->i_mmap_sem);
}
@@ -5810,7 +5657,8 @@
rc = posix_acl_chmod(inode, inode->i_mode);
err_out:
- ext4_std_error(inode->i_sb, error);
+ if (error)
+ ext4_std_error(inode->i_sb, error);
if (!error)
error = rc;
return error;
@@ -5824,7 +5672,8 @@
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int flags;
- if (EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
+ if ((request_mask & STATX_BTIME) &&
+ EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
stat->result_mask |= STATX_BTIME;
stat->btime.tv_sec = ei->i_crtime.tv_sec;
stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
@@ -5993,7 +5842,14 @@
put_bh(iloc->bh);
return -EIO;
}
- if (IS_I_VERSION(inode))
+ ext4_fc_track_inode(handle, inode);
+
+ /*
+ * ea_inodes are using i_version for storing reference count, don't
+ * mess with it
+ */
+ if (IS_I_VERSION(inode) &&
+ !(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL))
inode_inc_iversion(inode);
/* the do_update_inode consumes one bh->b_count */
@@ -6070,6 +5926,14 @@
return 0;
}
+ /*
+ * We may need to allocate external xattr block so we need quotas
+ * initialized. Here we can be called with various locks held so we
+ * cannot affort to initialize quotas ourselves. So just bail.
+ */
+ if (dquot_initialize_needed(inode))
+ return -EAGAIN;
+
/* try to expand with EAs present */
error = ext4_expand_extra_isize_ea(inode, new_extra_isize,
raw_inode, handle);
@@ -6107,9 +5971,8 @@
* If this is felt to be critical, then e2fsck should be run to
* force a large enough s_min_extra_isize.
*/
- if (ext4_handle_valid(handle) &&
- jbd2_journal_extend(handle,
- EXT4_DATA_TRANS_BLOCKS(inode->i_sb)) != 0)
+ if (ext4_journal_extend(handle,
+ EXT4_DATA_TRANS_BLOCKS(inode->i_sb), 0) != 0)
return -ENOSPC;
if (ext4_write_trylock_xattr(inode, &no_expand) == 0)
@@ -6178,7 +6041,8 @@
* Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync)
* we start and wait on commits.
*/
-int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode)
+int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode,
+ const char *func, unsigned int line)
{
struct ext4_iloc iloc;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
@@ -6188,13 +6052,18 @@
trace_ext4_mark_inode_dirty(inode, _RET_IP_);
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
- return err;
+ goto out;
if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize)
ext4_try_to_expand_extra_isize(inode, sbi->s_want_extra_isize,
iloc, handle);
- return ext4_mark_iloc_dirty(handle, inode, &iloc);
+ err = ext4_mark_iloc_dirty(handle, inode, &iloc);
+out:
+ if (unlikely(err))
+ ext4_error_inode_err(inode, func, line, 0, err,
+ "mark_inode_dirty error");
+ return err;
}
/*
@@ -6231,36 +6100,6 @@
out:
return;
}
-
-#if 0
-/*
- * Bind an inode's backing buffer_head into this transaction, to prevent
- * it from being flushed to disk early. Unlike
- * ext4_reserve_inode_write, this leaves behind no bh reference and
- * returns no iloc structure, so the caller needs to repeat the iloc
- * lookup to mark the inode dirty later.
- */
-static int ext4_pin_inode(handle_t *handle, struct inode *inode)
-{
- struct ext4_iloc iloc;
-
- int err = 0;
- if (handle) {
- err = ext4_get_inode_loc(inode, &iloc);
- if (!err) {
- BUFFER_TRACE(iloc.bh, "get_write_access");
- err = jbd2_journal_get_write_access(handle, iloc.bh);
- if (!err)
- err = ext4_handle_dirty_metadata(handle,
- NULL,
- iloc.bh);
- brelse(iloc.bh);
- }
- }
- ext4_std_error(inode->i_sb, err);
- return err;
-}
-#endif
int ext4_change_inode_journal_flag(struct inode *inode, int val)
{
@@ -6341,6 +6180,8 @@
if (IS_ERR(handle))
return PTR_ERR(handle);
+ ext4_fc_mark_ineligible(inode->i_sb,
+ EXT4_FC_REASON_JOURNAL_FLAG_CHANGE);
err = ext4_mark_inode_dirty(handle, inode);
ext4_handle_sync(handle);
ext4_journal_stop(handle);
@@ -6354,13 +6195,14 @@
return !buffer_mapped(bh);
}
-int ext4_page_mkwrite(struct vm_fault *vmf)
+vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
struct page *page = vmf->page;
loff_t size;
unsigned long len;
- int ret;
+ int err;
+ vm_fault_t ret;
struct file *file = vma->vm_file;
struct inode *inode = file_inode(file);
struct address_space *mapping = inode->i_mapping;
@@ -6376,18 +6218,26 @@
down_read(&EXT4_I(inode)->i_mmap_sem);
- ret = ext4_convert_inline_data(inode);
- if (ret)
+ err = ext4_convert_inline_data(inode);
+ if (err)
goto out_ret;
+
+ /*
+ * On data journalling we skip straight to the transaction handle:
+ * there's no delalloc; page truncated will be checked later; the
+ * early return w/ all buffers mapped (calculates size/len) can't
+ * be used; and there's no dioread_nolock, so only ext4_get_block.
+ */
+ if (ext4_should_journal_data(inode))
+ goto retry_alloc;
/* Delalloc case is easy... */
if (test_opt(inode->i_sb, DELALLOC) &&
- !ext4_should_journal_data(inode) &&
!ext4_nonda_switch(inode->i_sb)) {
do {
- ret = block_page_mkwrite(vma, vmf,
+ err = block_page_mkwrite(vma, vmf,
ext4_da_get_block_prep);
- } while (ret == -ENOSPC &&
+ } while (err == -ENOSPC &&
ext4_should_retry_alloc(inode->i_sb, &retries));
goto out_ret;
}
@@ -6408,6 +6258,9 @@
/*
* Return if we have all the buffers mapped. This avoids the need to do
* journal_start/journal_stop which can block and take a long time
+ *
+ * This cannot be done for data journalling, as we have to add the
+ * inode to the transaction's list to writeprotect pages on commit.
*/
if (page_has_buffers(page)) {
if (!ext4_walk_page_buffers(NULL, page_buffers(page),
@@ -6432,36 +6285,67 @@
ret = VM_FAULT_SIGBUS;
goto out;
}
- ret = block_page_mkwrite(vma, vmf, get_block);
- if (!ret && ext4_should_journal_data(inode)) {
- if (ext4_walk_page_buffers(handle, page_buffers(page), 0,
- PAGE_SIZE, NULL, do_journal_get_write_access)) {
- unlock_page(page);
- ret = VM_FAULT_SIGBUS;
- ext4_journal_stop(handle);
- goto out;
+ /*
+ * Data journalling can't use block_page_mkwrite() because it
+ * will set_buffer_dirty() before do_journal_get_write_access()
+ * thus might hit warning messages for dirty metadata buffers.
+ */
+ if (!ext4_should_journal_data(inode)) {
+ err = block_page_mkwrite(vma, vmf, get_block);
+ } else {
+ lock_page(page);
+ size = i_size_read(inode);
+ /* Page got truncated from under us? */
+ if (page->mapping != mapping || page_offset(page) > size) {
+ ret = VM_FAULT_NOPAGE;
+ goto out_error;
}
- ext4_set_inode_state(inode, EXT4_STATE_JDATA);
+
+ if (page->index == size >> PAGE_SHIFT)
+ len = size & ~PAGE_MASK;
+ else
+ len = PAGE_SIZE;
+
+ err = __block_write_begin(page, 0, len, ext4_get_block);
+ if (!err) {
+ ret = VM_FAULT_SIGBUS;
+ if (ext4_walk_page_buffers(handle, page_buffers(page),
+ 0, len, NULL, do_journal_get_write_access))
+ goto out_error;
+ if (ext4_walk_page_buffers(handle, page_buffers(page),
+ 0, len, NULL, write_end_fn))
+ goto out_error;
+ if (ext4_jbd2_inode_add_write(handle, inode,
+ page_offset(page), len))
+ goto out_error;
+ ext4_set_inode_state(inode, EXT4_STATE_JDATA);
+ } else {
+ unlock_page(page);
+ }
}
ext4_journal_stop(handle);
- if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
+ if (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry_alloc;
out_ret:
- ret = block_page_mkwrite_return(ret);
+ ret = block_page_mkwrite_return(err);
out:
up_read(&EXT4_I(inode)->i_mmap_sem);
sb_end_pagefault(inode->i_sb);
return ret;
+out_error:
+ unlock_page(page);
+ ext4_journal_stop(handle);
+ goto out;
}
-int ext4_filemap_fault(struct vm_fault *vmf)
+vm_fault_t ext4_filemap_fault(struct vm_fault *vmf)
{
struct inode *inode = file_inode(vmf->vma->vm_file);
- int err;
+ vm_fault_t ret;
down_read(&EXT4_I(inode)->i_mmap_sem);
- err = filemap_fault(vmf);
+ ret = filemap_fault(vmf);
up_read(&EXT4_I(inode)->i_mmap_sem);
- return err;
+ return ret;
}
--
Gitblit v1.6.2