aboutsummaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/bio.c37
-rw-r--r--fs/btrfs/bio.h3
-rw-r--r--fs/btrfs/ctree.h13
-rw-r--r--fs/btrfs/defrag.c10
-rw-r--r--fs/btrfs/delayed-ref.c4
-rw-r--r--fs/btrfs/extent_io.c7
-rw-r--r--fs/btrfs/extent_map.c7
-rw-r--r--fs/btrfs/file.c25
-rw-r--r--fs/btrfs/inode.c12
-rw-r--r--fs/btrfs/ordered-data.c4
-rw-r--r--fs/btrfs/super.c28
-rw-r--r--fs/btrfs/volumes.c1
12 files changed, 56 insertions, 95 deletions
diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
index fec5c6cde0a7..7e0f9600b80c 100644
--- a/fs/btrfs/bio.c
+++ b/fs/btrfs/bio.c
@@ -49,6 +49,7 @@ void btrfs_bio_init(struct btrfs_bio *bbio, struct btrfs_fs_info *fs_info,
bbio->end_io = end_io;
bbio->private = private;
atomic_set(&bbio->pending_ios, 1);
+ WRITE_ONCE(bbio->status, BLK_STS_OK);
}
/*
@@ -113,41 +114,29 @@ static void __btrfs_bio_end_io(struct btrfs_bio *bbio)
}
}
-static void btrfs_orig_write_end_io(struct bio *bio);
-
-static void btrfs_bbio_propagate_error(struct btrfs_bio *bbio,
- struct btrfs_bio *orig_bbio)
-{
- /*
- * For writes we tolerate nr_mirrors - 1 write failures, so we can't
- * just blindly propagate a write failure here. Instead increment the
- * error count in the original I/O context so that it is guaranteed to
- * be larger than the error tolerance.
- */
- if (bbio->bio.bi_end_io == &btrfs_orig_write_end_io) {
- struct btrfs_io_stripe *orig_stripe = orig_bbio->bio.bi_private;
- struct btrfs_io_context *orig_bioc = orig_stripe->bioc;
-
- atomic_add(orig_bioc->max_errors, &orig_bioc->error);
- } else {
- orig_bbio->bio.bi_status = bbio->bio.bi_status;
- }
-}
-
void btrfs_bio_end_io(struct btrfs_bio *bbio, blk_status_t status)
{
bbio->bio.bi_status = status;
if (bbio->bio.bi_pool == &btrfs_clone_bioset) {
struct btrfs_bio *orig_bbio = bbio->private;
- if (bbio->bio.bi_status)
- btrfs_bbio_propagate_error(bbio, orig_bbio);
btrfs_cleanup_bio(bbio);
bbio = orig_bbio;
}
- if (atomic_dec_and_test(&bbio->pending_ios))
+ /*
+ * At this point, bbio always points to the original btrfs_bio. Save
+ * the first error in it.
+ */
+ if (status != BLK_STS_OK)
+ cmpxchg(&bbio->status, BLK_STS_OK, status);
+
+ if (atomic_dec_and_test(&bbio->pending_ios)) {
+ /* Load split bio's error which might be set above. */
+ if (status == BLK_STS_OK)
+ bbio->bio.bi_status = READ_ONCE(bbio->status);
__btrfs_bio_end_io(bbio);
+ }
}
static int next_repair_mirror(struct btrfs_failed_bio *fbio, int cur_mirror)
diff --git a/fs/btrfs/bio.h b/fs/btrfs/bio.h
index e48612340745..e2fe16074ad6 100644
--- a/fs/btrfs/bio.h
+++ b/fs/btrfs/bio.h
@@ -79,6 +79,9 @@ struct btrfs_bio {
/* File system that this I/O operates on. */
struct btrfs_fs_info *fs_info;
+ /* Save the first error status of split bio. */
+ blk_status_t status;
+
/*
* This member must come last, bio_alloc_bioset will allocate enough
* bytes for entire btrfs_bio but relies on bio being last.
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 317a3712270f..307dedf95c70 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -744,16 +744,11 @@ const char *btrfs_super_csum_driver(u16 csum_type);
size_t __attribute_const__ btrfs_get_num_csums(void);
/*
- * We use page status Private2 to indicate there is an ordered extent with
+ * We use folio flag owner_2 to indicate there is an ordered extent with
* unfinished IO.
- *
- * Rename the Private2 accessors to Ordered, to improve readability.
*/
-#define PageOrdered(page) PagePrivate2(page)
-#define SetPageOrdered(page) SetPagePrivate2(page)
-#define ClearPageOrdered(page) ClearPagePrivate2(page)
-#define folio_test_ordered(folio) folio_test_private_2(folio)
-#define folio_set_ordered(folio) folio_set_private_2(folio)
-#define folio_clear_ordered(folio) folio_clear_private_2(folio)
+#define folio_test_ordered(folio) folio_test_owner_2(folio)
+#define folio_set_ordered(folio) folio_set_owner_2(folio)
+#define folio_clear_ordered(folio) folio_clear_owner_2(folio)
#endif
diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c
index b95ef44c326b..968dae953948 100644
--- a/fs/btrfs/defrag.c
+++ b/fs/btrfs/defrag.c
@@ -763,12 +763,12 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start,
* We can get a merged extent, in that case, we need to re-search
* tree to get the original em for defrag.
*
- * If @newer_than is 0 or em::generation < newer_than, we can trust
- * this em, as either we don't care about the generation, or the
- * merged extent map will be rejected anyway.
+ * This is because even if we have adjacent extents that are contiguous
+ * and compatible (same type and flags), we still want to defrag them
+ * so that we use less metadata (extent items in the extent tree and
+ * file extent items in the inode's subvolume tree).
*/
- if (em && (em->flags & EXTENT_FLAG_MERGED) &&
- newer_than && em->generation >= newer_than) {
+ if (em && (em->flags & EXTENT_FLAG_MERGED)) {
free_extent_map(em);
em = NULL;
}
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 115b90d29b1d..cab94d141f66 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -298,7 +298,7 @@ static int comp_refs(struct btrfs_delayed_ref_node *ref1,
if (ref1->ref_root < ref2->ref_root)
return -1;
if (ref1->ref_root > ref2->ref_root)
- return -1;
+ return 1;
if (ref1->type == BTRFS_EXTENT_DATA_REF_KEY)
ret = comp_data_refs(ref1, ref2);
}
@@ -649,7 +649,7 @@ static bool insert_delayed_ref(struct btrfs_trans_handle *trans,
&href->ref_add_list);
else if (ref->action == BTRFS_DROP_DELAYED_REF) {
ASSERT(!list_empty(&exist->add_list));
- list_del(&exist->add_list);
+ list_del_init(&exist->add_list);
} else {
ASSERT(0);
}
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 872cca54cc6c..42c9899d9241 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -786,7 +786,7 @@ static void submit_extent_folio(struct btrfs_bio_ctrl *bio_ctrl,
}
if (bio_ctrl->wbc)
- wbc_account_cgroup_owner(bio_ctrl->wbc, &folio->page,
+ wbc_account_cgroup_owner(bio_ctrl->wbc, folio,
len);
size -= len;
@@ -1708,7 +1708,7 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb,
ret = bio_add_folio(&bbio->bio, folio, eb->len,
eb->start - folio_pos(folio));
ASSERT(ret);
- wbc_account_cgroup_owner(wbc, folio_page(folio, 0), eb->len);
+ wbc_account_cgroup_owner(wbc, folio, eb->len);
folio_unlock(folio);
} else {
int num_folios = num_extent_folios(eb);
@@ -1722,8 +1722,7 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb,
folio_start_writeback(folio);
ret = bio_add_folio(&bbio->bio, folio, eb->folio_size, 0);
ASSERT(ret);
- wbc_account_cgroup_owner(wbc, folio_page(folio, 0),
- eb->folio_size);
+ wbc_account_cgroup_owner(wbc, folio, eb->folio_size);
wbc->nr_to_write -= folio_nr_pages(folio);
folio_unlock(folio);
}
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 668c617444a5..1d93e1202c33 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -230,7 +230,12 @@ static bool mergeable_maps(const struct extent_map *prev, const struct extent_ma
if (extent_map_end(prev) != next->start)
return false;
- if (prev->flags != next->flags)
+ /*
+ * The merged flag is not an on-disk flag, it just indicates we had the
+ * extent maps of 2 (or more) adjacent extents merged, so factor it out.
+ */
+ if ((prev->flags & ~EXTENT_FLAG_MERGED) !=
+ (next->flags & ~EXTENT_FLAG_MERGED))
return false;
if (next->disk_bytenr < EXTENT_MAP_LAST_BYTE - 1)
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 4fb521d91b06..e5384ceb8acf 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1120,26 +1120,6 @@ void btrfs_check_nocow_unlock(struct btrfs_inode *inode)
btrfs_drew_write_unlock(&inode->root->snapshot_lock);
}
-static void update_time_for_write(struct inode *inode)
-{
- struct timespec64 now, ts;
-
- if (IS_NOCMTIME(inode))
- return;
-
- now = current_time(inode);
- ts = inode_get_mtime(inode);
- if (!timespec64_equal(&ts, &now))
- inode_set_mtime_to_ts(inode, now);
-
- ts = inode_get_ctime(inode);
- if (!timespec64_equal(&ts, &now))
- inode_set_ctime_to_ts(inode, now);
-
- if (IS_I_VERSION(inode))
- inode_inc_iversion(inode);
-}
-
int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from, size_t count)
{
struct file *file = iocb->ki_filp;
@@ -1170,7 +1150,10 @@ int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from, size_t count)
* need to start yet another transaction to update the inode as we will
* update the inode when we finish writing whatever data we write.
*/
- update_time_for_write(inode);
+ if (!IS_NOCMTIME(inode)) {
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
+ inode_inc_iversion(inode);
+ }
start_pos = round_down(pos, fs_info->sectorsize);
oldsize = i_size_read(inode);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index da51edbad6a0..e41bc7842577 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1513,7 +1513,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
* (which the caller expects to stay locked), don't clear any
* dirty bits and don't set any writeback bits
*
- * Do set the Ordered (Private2) bit so we know this page was
+ * Do set the Ordered flag so we know this page was
* properly setup for writepage.
*/
page_ops = (keep_locked ? 0 : PAGE_UNLOCK);
@@ -1618,7 +1618,7 @@ out_unlock:
clear_bits |= EXTENT_CLEAR_DATA_RESV;
extent_clear_unlock_delalloc(inode, start, end, locked_folio,
&cached, clear_bits, page_ops);
- btrfs_qgroup_free_data(inode, NULL, start, cur_alloc_size, NULL);
+ btrfs_qgroup_free_data(inode, NULL, start, end - start + 1, NULL);
}
return ret;
}
@@ -1729,7 +1729,7 @@ static bool run_delalloc_compressed(struct btrfs_inode *inode,
* need full accuracy. Just account the whole thing
* against the first page.
*/
- wbc_account_cgroup_owner(wbc, &locked_folio->page,
+ wbc_account_cgroup_owner(wbc, locked_folio,
cur_end - start);
async_chunk[i].locked_folio = locked_folio;
locked_folio = NULL;
@@ -7294,7 +7294,7 @@ static void btrfs_invalidate_folio(struct folio *folio, size_t offset,
*
* But already submitted bio can still be finished on this folio.
* Furthermore, endio function won't skip folio which has Ordered
- * (Private2) already cleared, so it's possible for endio and
+ * already cleared, so it's possible for endio and
* invalidate_folio to do the same ordered extent accounting twice
* on one folio.
*
@@ -7360,7 +7360,7 @@ static void btrfs_invalidate_folio(struct folio *folio, size_t offset,
range_len = range_end + 1 - cur;
if (!btrfs_folio_test_ordered(fs_info, folio, cur, range_len)) {
/*
- * If Ordered (Private2) is cleared, it means endio has
+ * If Ordered is cleared, it means endio has
* already been executed for the range.
* We can't delete the extent states as
* btrfs_finish_ordered_io() may still use some of them.
@@ -7433,7 +7433,7 @@ next:
}
/*
* We have iterated through all ordered extents of the page, the page
- * should not have Ordered (Private2) anymore, or the above iteration
+ * should not have Ordered anymore, or the above iteration
* did something wrong.
*/
ASSERT(!folio_test_ordered(folio));
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 2104d60c2161..95c8499a159a 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -346,10 +346,10 @@ static bool can_finish_ordered_extent(struct btrfs_ordered_extent *ordered,
ASSERT(file_offset + len <= folio_pos(folio) + folio_size(folio));
/*
- * Ordered (Private2) bit indicates whether we still have
+ * Ordered flag indicates whether we still have
* pending io unfinished for the ordered extent.
*
- * If there's no such bit, we need to skip to next range.
+ * If it's not set, we need to skip to next range.
*/
if (!btrfs_folio_test_ordered(fs_info, folio, file_offset, len))
return false;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 926d7a9ed99d..881d62d81b9f 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1979,25 +1979,10 @@ error:
* fsconfig(FSCONFIG_SET_FLAG, "ro"). This option is seen by the filesystem
* in fc->sb_flags.
*
- * This disambiguation has rather positive consequences. Mounting a subvolume
- * ro will not also turn the superblock ro. Only the mount for the subvolume
- * will become ro.
- *
- * So, if the superblock creation request comes from the new mount API the
- * caller must have explicitly done:
- *
- * fsconfig(FSCONFIG_SET_FLAG, "ro")
- * fsmount/mount_setattr(MOUNT_ATTR_RDONLY)
- *
- * IOW, at some point the caller must have explicitly turned the whole
- * superblock ro and we shouldn't just undo it like we did for the old mount
- * API. In any case, it lets us avoid the hack in the new mount API.
- *
- * Consequently, the remounting hack must only be used for requests originating
- * from the old mount API and should be marked for full deprecation so it can be
- * turned off in a couple of years.
- *
- * The new mount API has no reason to support this hack.
+ * But, currently the util-linux mount command already utilizes the new mount
+ * API and is still setting fsconfig(FSCONFIG_SET_FLAG, "ro") no matter if it's
+ * btrfs or not, setting the whole super block RO. To make per-subvolume mounting
+ * work with different options work we need to keep backward compatibility.
*/
static struct vfsmount *btrfs_reconfigure_for_mount(struct fs_context *fc)
{
@@ -2019,7 +2004,7 @@ static struct vfsmount *btrfs_reconfigure_for_mount(struct fs_context *fc)
if (IS_ERR(mnt))
return mnt;
- if (!fc->oldapi || !ro2rw)
+ if (!ro2rw)
return mnt;
/* We need to convert to rw, call reconfigure. */
@@ -2206,7 +2191,8 @@ static struct file_system_type btrfs_fs_type = {
.init_fs_context = btrfs_init_fs_context,
.parameters = btrfs_fs_parameters,
.kill_sb = btrfs_kill_super,
- .fs_flags = FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA | FS_ALLOW_IDMAP,
+ .fs_flags = FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA |
+ FS_ALLOW_IDMAP | FS_MGTIME,
};
MODULE_ALIAS_FS("btrfs");
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 8f340ad1d938..eb51b609190f 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1105,6 +1105,7 @@ static void btrfs_close_one_device(struct btrfs_device *device)
if (device->bdev) {
fs_devices->open_devices--;
device->bdev = NULL;
+ device->bdev_file = NULL;
}
clear_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state);
btrfs_destroy_dev_zone_info(device);
generated by cgit (git 2.34.1) at 2025-06-03 08:07:51 +0000