diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index d1a2e662440178e87c8240a1fa70f5cdf4731cef..5d8055161acdb5d85375f2dacb4706ea6ef14fa4 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -235,8 +235,6 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line,
might_sleep();
- ext4_check_bdev_write_error(sb);
-
if (ext4_handle_valid(handle)) {
err = jbd2_journal_get_write_access(handle, bh);
if (err) {
@@ -244,7 +242,8 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line,
handle, err);
return err;
}
- }
+ } else
+ ext4_check_bdev_write_error(sb);
if (trigger_type == EXT4_JTR_NONE || !ext4_has_metadata_csum(sb))
return 0;
BUG_ON(trigger_type >= EXT4_JOURNAL_TRIGGER_COUNT);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index d5efe076d3d3fbb36a6d4ef5c3ea2e1f904c8366..01299b55a567aa41fe7147c3d625e5087b11a0fc 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4523,7 +4523,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
* Round up offset. This is not fallocate, we need to zero out
* blocks, so convert interior block aligned part of the range to
* unwritten and possibly manually zero out unaligned parts of the
- * range.
+ * range. Here, start and partial_begin are inclusive, end and
+ * partial_end are exclusive.
*/
start = round_up(offset, 1 << blkbits);
end = round_down((offset + len), 1 << blkbits);
@@ -4609,7 +4610,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
* disk in case of crash before zeroing trans is committed.
*/
if (ext4_should_journal_data(inode)) {
- ret = filemap_write_and_wait_range(mapping, start, end);
+ ret = filemap_write_and_wait_range(mapping, start,
+ end - 1);
if (ret) {
filemap_invalidate_unlock(mapping);
goto out_mutex;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 83ee4e0f46f4d7f360d8c0508f435d084e298866..5af1b0b8680e9fa5f34f94f4a49127b554691f00 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2947,7 +2947,7 @@ static int ext4_da_should_update_i_disksize(struct folio *folio,
static int ext4_da_do_write_end(struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
- struct page *page)
+ struct folio *folio)
{
struct inode *inode = mapping->host;
loff_t old_size = inode->i_size;
@@ -2958,12 +2958,13 @@ static int ext4_da_do_write_end(struct address_space *mapping,
* block_write_end() will mark the inode as dirty with I_DIRTY_PAGES
* flag, which all that's needed to trigger page writeback.
*/
- copied = block_write_end(NULL, mapping, pos, len, copied, page, NULL);
+ copied = block_write_end(NULL, mapping, pos, len, copied,
+ &folio->page, NULL);
new_i_size = pos + copied;
/*
- * It's important to update i_size while still holding page lock,
- * because page writeout could otherwise come in and zero beyond
+ * It's important to update i_size while still holding folio lock,
+ * because folio writeout could otherwise come in and zero beyond
* i_size.
*
* Since we are holding inode lock, we are sure i_disksize <=
@@ -2981,14 +2982,14 @@ static int ext4_da_do_write_end(struct address_space *mapping,
i_size_write(inode, new_i_size);
end = (new_i_size - 1) & (PAGE_SIZE - 1);
- if (copied && ext4_da_should_update_i_disksize(page_folio(page), end)) {
+ if (copied && ext4_da_should_update_i_disksize(folio, end)) {
ext4_update_i_disksize(inode, new_i_size);
disksize_changed = true;
}
}
- unlock_page(page);
- put_page(page);
+ folio_unlock(folio);
+ folio_put(folio);
if (old_size < pos)
pagecache_isize_extended(inode, old_size, pos);
@@ -3027,10 +3028,10 @@ static int ext4_da_write_end(struct file *file,
return ext4_write_inline_data_end(inode, pos, len, copied,
folio);
- if (unlikely(copied < len) && !PageUptodate(page))
+ if (unlikely(copied < len) && !folio_test_uptodate(folio))
copied = 0;
- return ext4_da_do_write_end(mapping, pos, len, copied, &folio->page);
+ return ext4_da_do_write_end(mapping, pos, len, copied, folio);
}
/*
@@ -3630,6 +3631,12 @@ void ext4_set_aops(struct inode *inode)
inode->i_mapping->a_ops = &ext4_aops;
}
+/*
+ * Here we can't skip an unwritten buffer even though it usually reads zero
+ * because it might have data in pagecache (eg, if called from ext4_zero_range,
+ * ext4_punch_hole, etc) which needs to be properly zeroed out. Otherwise a
+ * racing writeback can come later and flush the stale pagecache to disk.
+ */
static int __ext4_block_zero_page_range(handle_t *handle,
struct address_space *mapping, loff_t from, loff_t length)
{
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index d72b5e3c92ec4088b878246f431059906d8cf931..f44f668e407f2bda9fe325631c9a4ab62649b9dc 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1456,9 +1456,8 @@ static int ext4_mb_get_buddy_page_lock(struct super_block *sb,
return 0;
}
- block++;
- pnum = block / blocks_per_page;
- page = find_or_create_page(inode->i_mapping, pnum, gfp);
+ /* blocks_per_page == 1, hence we need another page for the buddy */
+ page = find_or_create_page(inode->i_mapping, block + 1, gfp);
if (!page)
return -ENOMEM;
BUG_ON(page->mapping != inode->i_mapping);
@@ -1958,8 +1957,7 @@ static void mb_free_blocks(struct inode *inode, struct ext4_buddy *e4b,
static int mb_find_extent(struct ext4_buddy *e4b, int block,
int needed, struct ext4_free_extent *ex)
{
- int next = block;
- int max, order;
+ int max, order, next;
void *buddy;
assert_spin_locked(ext4_group_lock_ptr(e4b->bd_sb, e4b->bd_group));
@@ -1977,16 +1975,12 @@ static int mb_find_extent(struct ext4_buddy *e4b, int block,
/* find actual order */
order = mb_find_order_for_block(e4b, block);
- block = block >> order;
- ex->fe_len = 1 << order;
- ex->fe_start = block << order;
+ ex->fe_len = (1 << order) - (block & ((1 << order) - 1));
+ ex->fe_start = block;
ex->fe_group = e4b->bd_group;
- /* calc difference from given start */
- next = next - ex->fe_start;
- ex->fe_len -= next;
- ex->fe_start += next;
+ block = block >> order;
while (needed > ex->fe_len &&
mb_find_buddy(e4b, order, &max)) {
@@ -2895,14 +2889,19 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
ac->ac_groups_scanned++;
if (cr == CR_POWER2_ALIGNED)
ext4_mb_simple_scan_group(ac, &e4b);
- else if ((cr == CR_GOAL_LEN_FAST ||
- cr == CR_BEST_AVAIL_LEN) &&
- sbi->s_stripe &&
- !(ac->ac_g_ex.fe_len %
- EXT4_B2C(sbi, sbi->s_stripe)))
- ext4_mb_scan_aligned(ac, &e4b);
- else
- ext4_mb_complex_scan_group(ac, &e4b);
+ else {
+ bool is_stripe_aligned = sbi->s_stripe &&
+ !(ac->ac_g_ex.fe_len %
+ EXT4_B2C(sbi, sbi->s_stripe));
+
+ if ((cr == CR_GOAL_LEN_FAST ||
+ cr == CR_BEST_AVAIL_LEN) &&
+ is_stripe_aligned)
+ ext4_mb_scan_aligned(ac, &e4b);
+
+ if (ac->ac_status == AC_STATUS_CONTINUE)
+ ext4_mb_complex_scan_group(ac, &e4b);
+ }
ext4_unlock_group(sb, group);
ext4_mb_unload_buddy(&e4b);
@@ -6735,11 +6734,16 @@ __acquires(bitlock)
static ext4_grpblk_t ext4_last_grp_cluster(struct super_block *sb,
ext4_group_t grp)
{
- if (grp < ext4_get_groups_count(sb))
- return EXT4_CLUSTERS_PER_GROUP(sb) - 1;
- return (ext4_blocks_count(EXT4_SB(sb)->s_es) -
- ext4_group_first_block_no(sb, grp) - 1) >>
- EXT4_CLUSTER_BITS(sb);
+ unsigned long nr_clusters_in_group;
+
+ if (grp < (ext4_get_groups_count(sb) - 1))
+ nr_clusters_in_group = EXT4_CLUSTERS_PER_GROUP(sb);
+ else
+ nr_clusters_in_group = (ext4_blocks_count(EXT4_SB(sb)->s_es) -
+ ext4_group_first_block_no(sb, grp))
+ >> EXT4_CLUSTER_BITS(sb);
+
+ return nr_clusters_in_group - 1;
}
static bool ext4_trim_interrupted(void)
@@ -6753,13 +6757,15 @@ static int ext4_try_to_trim_range(struct super_block *sb,
__acquires(ext4_group_lock_ptr(sb, e4b->bd_group))
__releases(ext4_group_lock_ptr(sb, e4b->bd_group))
{
- ext4_grpblk_t next, count, free_count;
+ ext4_grpblk_t next, count, free_count, last, origin_start;
bool set_trimmed = false;
void *bitmap;
+ last = ext4_last_grp_cluster(sb, e4b->bd_group);
bitmap = e4b->bd_bitmap;
- if (start == 0 && max >= ext4_last_grp_cluster(sb, e4b->bd_group))
+ if (start == 0 && max >= last)
set_trimmed = true;
+ origin_start = start;
start = max(e4b->bd_info->bb_first_free, start);
count = 0;
free_count = 0;
@@ -6768,7 +6774,10 @@ __releases(ext4_group_lock_ptr(sb, e4b->bd_group))
start = mb_find_next_zero_bit(bitmap, max + 1, start);
if (start > max)
break;
- next = mb_find_next_bit(bitmap, max + 1, start);
+
+ next = mb_find_next_bit(bitmap, last + 1, start);
+ if (origin_start == 0 && next >= last)
+ set_trimmed = true;
if ((next - start) >= minblocks) {
int ret = ext4_trim_extent(sb, start, next - start, e4b);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 4fe061edefddecc0fa1ac522bf8a2ff216315380..4d4a5a32e310d43bb57f6d8bd2561debe882b724 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -218,35 +218,53 @@ struct ext4_new_flex_group_data {
in the flex group */
__u16 *bg_flags; /* block group flags of groups
in @groups */
+ ext4_group_t resize_bg; /* number of allocated
+ new_group_data */
ext4_group_t count; /* number of groups in @groups
*/
};
+/*
+ * Avoiding memory allocation failures due to too many groups added each time.
+ */
+#define MAX_RESIZE_BG 16384
+
/*
* alloc_flex_gd() allocates a ext4_new_flex_group_data with size of
* @flexbg_size.
*
* Returns NULL on failure otherwise address of the allocated structure.
*/
-static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned long flexbg_size)
+static struct ext4_new_flex_group_data *alloc_flex_gd(unsigned int flexbg_size,
+ ext4_group_t o_group, ext4_group_t n_group)
{
+ ext4_group_t last_group;
struct ext4_new_flex_group_data *flex_gd;
flex_gd = kmalloc(sizeof(*flex_gd), GFP_NOFS);
if (flex_gd == NULL)
goto out3;
- if (flexbg_size >= UINT_MAX / sizeof(struct ext4_new_group_data))
- goto out2;
- flex_gd->count = flexbg_size;
+ if (unlikely(flexbg_size > MAX_RESIZE_BG))
+ flex_gd->resize_bg = MAX_RESIZE_BG;
+ else
+ flex_gd->resize_bg = flexbg_size;
+
+ /* Avoid allocating large 'groups' array if not needed */
+ last_group = o_group | (flex_gd->resize_bg - 1);
+ if (n_group <= last_group)
+ flex_gd->resize_bg = 1 << fls(n_group - o_group + 1);
+ else if (n_group - last_group < flex_gd->resize_bg)
+ flex_gd->resize_bg = 1 << max(fls(last_group - o_group + 1),
+ fls(n_group - last_group));
- flex_gd->groups = kmalloc_array(flexbg_size,
+ flex_gd->groups = kmalloc_array(flex_gd->resize_bg,
sizeof(struct ext4_new_group_data),
GFP_NOFS);
if (flex_gd->groups == NULL)
goto out2;
- flex_gd->bg_flags = kmalloc_array(flexbg_size, sizeof(__u16),
+ flex_gd->bg_flags = kmalloc_array(flex_gd->resize_bg, sizeof(__u16),
GFP_NOFS);
if (flex_gd->bg_flags == NULL)
goto out1;
@@ -283,7 +301,7 @@ static void free_flex_gd(struct ext4_new_flex_group_data *flex_gd)
*/
static int ext4_alloc_group_tables(struct super_block *sb,
struct ext4_new_flex_group_data *flex_gd,
- int flexbg_size)
+ unsigned int flexbg_size)
{
struct ext4_new_group_data *group_data = flex_gd->groups;
ext4_fsblk_t start_blk;
@@ -384,12 +402,12 @@ static int ext4_alloc_group_tables(struct super_block *sb,
group = group_data[0].group;
printk(KERN_DEBUG "EXT4-fs: adding a flex group with "
- "%d groups, flexbg size is %d:\n", flex_gd->count,
+ "%u groups, flexbg size is %u:\n", flex_gd->count,
flexbg_size);
for (i = 0; i < flex_gd->count; i++) {
ext4_debug(
- "adding %s group %u: %u blocks (%d free, %d mdata blocks)\n",
+ "adding %s group %u: %u blocks (%u free, %u mdata blocks)\n",
ext4_bg_has_super(sb, group + i) ? "normal" :
"no-super", group + i,
group_data[i].blocks_count,
@@ -1605,8 +1623,7 @@ static int ext4_flex_group_add(struct super_block *sb,
static int ext4_setup_next_flex_gd(struct super_block *sb,
struct ext4_new_flex_group_data *flex_gd,
- ext4_fsblk_t n_blocks_count,
- unsigned long flexbg_size)
+ ext4_fsblk_t n_blocks_count)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
@@ -1630,7 +1647,7 @@ static int ext4_setup_next_flex_gd(struct super_block *sb,
BUG_ON(last);
ext4_get_group_no_and_offset(sb, n_blocks_count - 1, &n_group, &last);
- last_group = group | (flexbg_size - 1);
+ last_group = group | (flex_gd->resize_bg - 1);
if (last_group > n_group)
last_group = n_group;
@@ -1990,8 +2007,9 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
ext4_fsblk_t o_blocks_count;
ext4_fsblk_t n_blocks_count_retry = 0;
unsigned long last_update_time = 0;
- int err = 0, flexbg_size = 1 << sbi->s_log_groups_per_flex;
+ int err = 0;
int meta_bg;
+ unsigned int flexbg_size = ext4_flex_bg_size(sbi);
/* See if the device is actually as big as what was requested */
bh = ext4_sb_bread(sb, n_blocks_count - 1, 0);
@@ -2123,7 +2141,7 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
if (err)
goto out;
- flex_gd = alloc_flex_gd(flexbg_size);
+ flex_gd = alloc_flex_gd(flexbg_size, o_group, n_group);
if (flex_gd == NULL) {
err = -ENOMEM;
goto out;
@@ -2132,8 +2150,7 @@ int ext4_resize_fs(struct super_block *sb, ext4_fsblk_t n_blocks_count)
/* Add flex groups. Note that a regular group is a
* flex group with 1 group.
*/
- while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count,
- flexbg_size)) {
+ while (ext4_setup_next_flex_gd(sb, flex_gd, n_blocks_count)) {
if (time_is_before_jiffies(last_update_time + HZ * 10)) {
if (last_update_time)
ext4_msg(sb, KERN_INFO,
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0980845c8b8f103acc906e21d0f2c9a9f2f64ab6..dcba0f85dfe245ab83598d5a451783b02044be52 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2793,15 +2793,6 @@ static int ext4_check_opt_consistency(struct fs_context *fc,
return -EINVAL;
}
- if (ctx_test_mount_opt(ctx, EXT4_MOUNT_DIOREAD_NOLOCK)) {
- int blocksize =
- BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);
- if (blocksize < PAGE_SIZE)
- ext4_msg(NULL, KERN_WARNING, "Warning: mounting with an "
- "experimental mount option 'dioread_nolock' "
- "for blocksize < PAGE_SIZE");
- }
-
err = ext4_check_test_dummy_encryption(fc, sb);
if (err)
return err;
@@ -4410,7 +4401,7 @@ static void ext4_set_def_opts(struct super_block *sb,
((def_mount_opts & EXT4_DEFM_NODELALLOC) == 0))
set_opt(sb, DELALLOC);
- if (sb->s_blocksize == PAGE_SIZE)
+ if (sb->s_blocksize <= PAGE_SIZE)
set_opt(sb, DIOREAD_NOLOCK);
}
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 118699fff2f900ccd9a1857dcbe175b81efac988..1c97e64c478496bee8dd0615ad6ea261a2426d56 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -556,7 +556,6 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
struct transaction_chp_stats_s *stats;
transaction_t *transaction;
journal_t *journal;
- struct buffer_head *bh = jh2bh(jh);
JBUFFER_TRACE(jh, "entry");
@@ -569,16 +568,6 @@ int __jbd2_journal_remove_checkpoint(struct journal_head *jh)
JBUFFER_TRACE(jh, "removing from transaction");
- /*
- * If we have failed to write the buffer out to disk, the filesystem
- * may become inconsistent. We cannot abort the journal here since
- * we hold j_list_lock and we have to be careful about races with
- * jbd2_journal_destroy(). So mark the writeback IO error in the
- * journal here and we abort the journal later from a better context.
- */
- if (buffer_write_io_error(bh))
- set_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags);
-
__buffer_unlink(jh);
jh->b_cp_transaction = NULL;
percpu_counter_dec(&journal->j_checkpoint_jh_count);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 206cb53ef2b06813a7344da309e0d811dd3e808c..b6c114c11b97877e7f86a9366ef63bad0d81bf01 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -1534,6 +1534,7 @@ static journal_t *journal_init_common(struct block_device *bdev,
journal->j_fs_dev = fs_dev;
journal->j_blk_offset = start;
journal->j_total_len = len;
+ jbd2_init_fs_dev_write_error(journal);
err = journal_load_superblock(journal);
if (err)
@@ -1861,7 +1862,7 @@ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
if (is_journal_aborted(journal))
return -EIO;
- if (test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags)) {
+ if (jbd2_check_fs_dev_write_error(journal)) {
jbd2_journal_abort(journal, -EIO);
return -EIO;
}
@@ -2159,12 +2160,12 @@ int jbd2_journal_destroy(journal_t *journal)
/*
* OK, all checkpoint transactions have been checked, now check the
- * write out io error flag and abort the journal if some buffer failed
- * to write back to the original location, otherwise the filesystem
- * may become inconsistent.
+ * writeback errseq of fs dev and abort the journal if some buffer
+ * failed to write back to the original location, otherwise the
+ * filesystem may become inconsistent.
*/
if (!is_journal_aborted(journal) &&
- test_bit(JBD2_CHECKPOINT_IO_ERROR, &journal->j_atomic_flags))
+ jbd2_check_fs_dev_write_error(journal))
jbd2_journal_abort(journal, -EIO);
if (journal->j_sb_buffer) {
diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
index 01f744cb97a401d0d13305983f5ea5617921c599..1f7664984d6e47b2ede19c00bdcf09672ccad7f5 100644
--- a/fs/jbd2/recovery.c
+++ b/fs/jbd2/recovery.c
@@ -289,8 +289,6 @@ int jbd2_journal_recover(journal_t *journal)
journal_superblock_t * sb;
struct recovery_info info;
- errseq_t wb_err;
- struct address_space *mapping;
memset(&info, 0, sizeof(info));
sb = journal->j_superblock;
@@ -308,9 +306,6 @@ int jbd2_journal_recover(journal_t *journal)
return 0;
}
- wb_err = 0;
- mapping = journal->j_fs_dev->bd_inode->i_mapping;
- errseq_check_and_advance(&mapping->wb_err, &wb_err);
err = do_one_pass(journal, &info, PASS_SCAN);
if (!err)
err = do_one_pass(journal, &info, PASS_REVOKE);
@@ -334,7 +329,7 @@ int jbd2_journal_recover(journal_t *journal)
err2 = sync_blockdev(journal->j_fs_dev);
if (!err)
err = err2;
- err2 = errseq_check_and_advance(&mapping->wb_err, &wb_err);
+ err2 = jbd2_check_fs_dev_write_error(journal);
if (!err)
err = err2;
/* Make sure all replayed data is on permanent storage */
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 5f08b5fd105a311584ffd1694667eb187f0e3975..cb0b8d6fc0c6dbfc98fca854d737bb979188c5c4 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -1231,11 +1231,25 @@ static bool jbd2_write_access_granted(handle_t *handle, struct buffer_head *bh,
int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh)
{
struct journal_head *jh;
+ journal_t *journal;
int rc;
if (is_handle_aborted(handle))
return -EROFS;
+ journal = handle->h_transaction->t_journal;
+ if (jbd2_check_fs_dev_write_error(journal)) {
+ /*
+ * If the fs dev has writeback errors, it may have failed
+ * to async write out metadata buffers in the background.
+ * In this case, we could read old data from disk and write
+ * it out again, which may lead to on-disk filesystem
+ * inconsistency. Aborting journal can avoid it happen.
+ */
+ jbd2_journal_abort(journal, -EIO);
+ return -EIO;
+ }
+
if (jbd2_write_access_granted(handle, bh, false))
return 0;
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index beb30719ee161bad0e01db32edfd14e610a6634c..971f3e826e15280ef00df8906398a9c83efbf6e4 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -755,11 +755,6 @@ struct journal_s
*/
unsigned long j_flags;
- /**
- * @j_atomic_flags: Atomic journaling state flags.
- */
- unsigned long j_atomic_flags;
-
/**
* @j_errno:
*
@@ -998,6 +993,13 @@ struct journal_s
*/
struct block_device *j_fs_dev;
+ /**
+ * @j_fs_dev_wb_err:
+ *
+ * Records the errseq of the client fs's backing block device.
+ */
+ errseq_t j_fs_dev_wb_err;
+
/**
* @j_total_len: Total maximum capacity of the journal region on disk.
*/
@@ -1399,12 +1401,6 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT)
#define JBD2_JOURNAL_FLUSH_VALID (JBD2_JOURNAL_FLUSH_DISCARD | \
JBD2_JOURNAL_FLUSH_ZEROOUT)
-/*
- * Journal atomic flag definitions
- */
-#define JBD2_CHECKPOINT_IO_ERROR 0x001 /* Detect io error while writing
- * buffer back to disk */
-
/*
* Function declarations for the journaling transaction and buffer
* management
@@ -1698,6 +1694,25 @@ static inline void jbd2_journal_abort_handle(handle_t *handle)
handle->h_aborted = 1;
}
+static inline void jbd2_init_fs_dev_write_error(journal_t *journal)
+{
+ struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping;
+
+ /*
+ * Save the original wb_err value of client fs's bdev mapping which
+ * could be used to detect the client fs's metadata async write error.
+ */
+ errseq_check_and_advance(&mapping->wb_err, &journal->j_fs_dev_wb_err);
+}
+
+static inline int jbd2_check_fs_dev_write_error(journal_t *journal)
+{
+ struct address_space *mapping = journal->j_fs_dev->bd_inode->i_mapping;
+
+ return errseq_check(&mapping->wb_err,
+ READ_ONCE(journal->j_fs_dev_wb_err));
+}
+
#endif /* __KERNEL__ */
/* Comparison functions for transaction IDs: perform comparisons using