summaryrefslogtreecommitdiff
path: root/fs/btrfs/inode.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/inode.c')
-rw-r--r--fs/btrfs/inode.c806
1 files changed, 500 insertions, 306 deletions
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index aabdcb9f234f..06dea7c89bbd 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -86,7 +86,6 @@ static const struct extent_io_ops btrfs_extent_io_ops;
static struct kmem_cache *btrfs_inode_cachep;
struct kmem_cache *btrfs_trans_handle_cachep;
-struct kmem_cache *btrfs_transaction_cachep;
struct kmem_cache *btrfs_path_cachep;
struct kmem_cache *btrfs_free_space_cachep;
@@ -115,6 +114,31 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
u64 ram_bytes, int compress_type,
int type);
+static void __endio_write_update_ordered(struct inode *inode,
+ const u64 offset, const u64 bytes,
+ const bool uptodate);
+
+/*
+ * Cleanup all submitted ordered extents in specified range to handle errors
+ * from the fill_dellaloc() callback.
+ *
+ * NOTE: caller must ensure that when an error happens, it can not call
+ * extent_clear_unlock_delalloc() to clear both the bits EXTENT_DO_ACCOUNTING
+ * and EXTENT_DELALLOC simultaneously, because that causes the reserved metadata
+ * to be released, which we want to happen only when finishing the ordered
+ * extent (btrfs_finish_ordered_io()). Also note that the caller of the
+ * fill_delalloc() callback already does proper cleanup for the first page of
+ * the range, that is, it invokes the callback writepage_end_io_hook() for the
+ * range of the first page.
+ */
+static inline void btrfs_cleanup_ordered_extents(struct inode *inode,
+ const u64 offset,
+ const u64 bytes)
+{
+ return __endio_write_update_ordered(inode, offset + PAGE_SIZE,
+ bytes - PAGE_SIZE, false);
+}
+
static int btrfs_dirty_inode(struct inode *inode);
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
@@ -153,7 +177,6 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
char *kaddr;
unsigned long ptr;
struct btrfs_file_extent_item *ei;
- int err = 0;
int ret;
size_t cur_size = size;
unsigned long offset;
@@ -175,10 +198,8 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
path->leave_spinning = 1;
ret = btrfs_insert_empty_item(trans, root, path, &key,
datasize);
- if (ret) {
- err = ret;
+ if (ret)
goto fail;
- }
}
leaf = path->nodes[0];
ei = btrfs_item_ptr(leaf, path->slots[0],
@@ -233,9 +254,8 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
BTRFS_I(inode)->disk_i_size = inode->i_size;
ret = btrfs_update_inode(trans, root, inode);
- return ret;
fail:
- return err;
+ return ret;
}
@@ -325,7 +345,7 @@ out:
* And at reserve time, it's always aligned to page size, so
* just free one page here.
*/
- btrfs_qgroup_free_data(inode, 0, PAGE_SIZE);
+ btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE);
btrfs_free_path(path);
btrfs_end_transaction(trans);
return ret;
@@ -547,7 +567,7 @@ cont:
}
if (ret <= 0) {
unsigned long clear_flags = EXTENT_DELALLOC |
- EXTENT_DEFRAG;
+ EXTENT_DELALLOC_NEW | EXTENT_DEFRAG;
unsigned long page_error_op;
clear_flags |= (ret < 0) ? EXTENT_DO_ACCOUNTING : 0;
@@ -565,8 +585,10 @@ cont:
PAGE_SET_WRITEBACK |
page_error_op |
PAGE_END_WRITEBACK);
- btrfs_free_reserved_data_space_noquota(inode, start,
- end - start + 1);
+ if (ret == 0)
+ btrfs_free_reserved_data_space_noquota(inode,
+ start,
+ end - start + 1);
goto free_pages_out;
}
}
@@ -581,12 +603,11 @@ cont:
/*
* one last check to make sure the compression is really a
- * win, compare the page count read with the blocks on disk
+ * win, compare the page count read with the blocks on disk,
+ * compression must free at least one sector size
*/
total_in = ALIGN(total_in, PAGE_SIZE);
- if (total_compressed >= total_in) {
- will_compress = 0;
- } else {
+ if (total_compressed + blocksize <= total_in) {
num_bytes = total_in;
*num_added += 1;
@@ -815,13 +836,12 @@ retry:
NULL, EXTENT_LOCKED | EXTENT_DELALLOC,
PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
PAGE_SET_WRITEBACK);
- ret = btrfs_submit_compressed_write(inode,
+ if (btrfs_submit_compressed_write(inode,
async_extent->start,
async_extent->ram_size,
ins.objectid,
ins.offset, async_extent->pages,
- async_extent->nr_pages);
- if (ret) {
+ async_extent->nr_pages)) {
struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
struct page *p = async_extent->pages[0];
const u64 start = async_extent->start;
@@ -852,6 +872,7 @@ out_free:
async_extent->start +
async_extent->ram_size - 1,
NULL, EXTENT_LOCKED | EXTENT_DELALLOC |
+ EXTENT_DELALLOC_NEW |
EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK |
@@ -918,10 +939,13 @@ static noinline int cow_file_range(struct inode *inode,
u64 num_bytes;
unsigned long ram_size;
u64 disk_num_bytes;
- u64 cur_alloc_size;
+ u64 cur_alloc_size = 0;
u64 blocksize = fs_info->sectorsize;
struct btrfs_key ins;
struct extent_map *em;
+ unsigned clear_bits;
+ unsigned long page_ops;
+ bool extent_reserved = false;
int ret = 0;
if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
@@ -944,6 +968,7 @@ static noinline int cow_file_range(struct inode *inode,
extent_clear_unlock_delalloc(inode, start, end,
delalloc_end, NULL,
EXTENT_LOCKED | EXTENT_DELALLOC |
+ EXTENT_DELALLOC_NEW |
EXTENT_DEFRAG, PAGE_UNLOCK |
PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
PAGE_END_WRITEBACK);
@@ -966,14 +991,14 @@ static noinline int cow_file_range(struct inode *inode,
start + num_bytes - 1, 0);
while (disk_num_bytes > 0) {
- unsigned long op;
-
cur_alloc_size = disk_num_bytes;
ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
fs_info->sectorsize, 0, alloc_hint,
&ins, 1, 1);
if (ret < 0)
goto out_unlock;
+ cur_alloc_size = ins.offset;
+ extent_reserved = true;
ram_size = ins.offset;
em = create_io_em(inode, start, ins.offset, /* len */
@@ -988,7 +1013,6 @@ static noinline int cow_file_range(struct inode *inode,
goto out_reserve;
free_extent_map(em);
- cur_alloc_size = ins.offset;
ret = btrfs_add_ordered_extent(inode, start, ins.objectid,
ram_size, cur_alloc_size, 0);
if (ret)
@@ -998,15 +1022,24 @@ static noinline int cow_file_range(struct inode *inode,
BTRFS_DATA_RELOC_TREE_OBJECTID) {
ret = btrfs_reloc_clone_csums(inode, start,
cur_alloc_size);
+ /*
+ * Only drop cache here, and process as normal.
+ *
+ * We must not allow extent_clear_unlock_delalloc()
+ * at out_unlock label to free meta of this ordered
+ * extent, as its meta should be freed by
+ * btrfs_finish_ordered_io().
+ *
+ * So we must continue until @start is increased to
+ * skip current ordered extent.
+ */
if (ret)
- goto out_drop_extent_cache;
+ btrfs_drop_extent_cache(BTRFS_I(inode), start,
+ start + ram_size - 1, 0);
}
btrfs_dec_block_group_reservations(fs_info, ins.objectid);
- if (disk_num_bytes < cur_alloc_size)
- break;
-
/* we're not doing compressed IO, don't unlock the first
* page (which the caller expects to stay locked), don't
* clear any dirty bits and don't set any writeback bits
@@ -1014,18 +1047,30 @@ static noinline int cow_file_range(struct inode *inode,
* Do set the Private2 bit so we know this page was properly
* setup for writepage
*/
- op = unlock ? PAGE_UNLOCK : 0;
- op |= PAGE_SET_PRIVATE2;
+ page_ops = unlock ? PAGE_UNLOCK : 0;
+ page_ops |= PAGE_SET_PRIVATE2;
extent_clear_unlock_delalloc(inode, start,
start + ram_size - 1,
delalloc_end, locked_page,
EXTENT_LOCKED | EXTENT_DELALLOC,
- op);
- disk_num_bytes -= cur_alloc_size;
+ page_ops);
+ if (disk_num_bytes < cur_alloc_size)
+ disk_num_bytes = 0;
+ else
+ disk_num_bytes -= cur_alloc_size;
num_bytes -= cur_alloc_size;
alloc_hint = ins.objectid + ins.offset;
start += cur_alloc_size;
+ extent_reserved = false;
+
+ /*
+ * btrfs_reloc_clone_csums() error, since start is increased
+ * extent_clear_unlock_delalloc() at out_unlock label won't
+ * free metadata of current ordered extent, we're OK to exit.
+ */
+ if (ret)
+ goto out_unlock;
}
out:
return ret;
@@ -1036,12 +1081,35 @@ out_reserve:
btrfs_dec_block_group_reservations(fs_info, ins.objectid);
btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
out_unlock:
+ clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
+ EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV;
+ page_ops = PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
+ PAGE_END_WRITEBACK;
+ /*
+ * If we reserved an extent for our delalloc range (or a subrange) and
+ * failed to create the respective ordered extent, then it means that
+ * when we reserved the extent we decremented the extent's size from
+ * the data space_info's bytes_may_use counter and incremented the
+ * space_info's bytes_reserved counter by the same amount. We must make
+ * sure extent_clear_unlock_delalloc() does not try to decrement again
+ * the data space_info's bytes_may_use counter, therefore we do not pass
+ * it the flag EXTENT_CLEAR_DATA_RESV.
+ */
+ if (extent_reserved) {
+ extent_clear_unlock_delalloc(inode, start,
+ start + cur_alloc_size,
+ start + cur_alloc_size,
+ locked_page,
+ clear_bits,
+ page_ops);
+ start += cur_alloc_size;
+ if (start >= end)
+ goto out;
+ }
extent_clear_unlock_delalloc(inode, start, end, delalloc_end,
locked_page,
- EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
- EXTENT_DELALLOC | EXTENT_DEFRAG,
- PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
- PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK);
+ clear_bits | EXTENT_CLEAR_DATA_RESV,
+ page_ops);
goto out;
}
@@ -1414,15 +1482,14 @@ out_check:
BUG_ON(ret); /* -ENOMEM */
if (root->root_key.objectid ==
- BTRFS_DATA_RELOC_TREE_OBJECTID) {
+ BTRFS_DATA_RELOC_TREE_OBJECTID)
+ /*
+ * Error handled later, as we must prevent
+ * extent_clear_unlock_delalloc() in error handler
+ * from freeing metadata of created ordered extent.
+ */
ret = btrfs_reloc_clone_csums(inode, cur_offset,
num_bytes);
- if (ret) {
- if (!nolock && nocow)
- btrfs_end_write_no_snapshoting(root);
- goto error;
- }
- }
extent_clear_unlock_delalloc(inode, cur_offset,
cur_offset + num_bytes - 1, end,
@@ -1434,6 +1501,14 @@ out_check:
if (!nolock && nocow)
btrfs_end_write_no_snapshoting(root);
cur_offset = extent_end;
+
+ /*
+ * btrfs_reloc_clone_csums() error, now we're OK to call error
+ * handler, as metadata for created ordered extent will only
+ * be freed by btrfs_finish_ordered_io().
+ */
+ if (ret)
+ goto error;
if (cur_offset > end)
break;
}
@@ -1487,10 +1562,11 @@ static inline int need_force_cow(struct inode *inode, u64 start, u64 end)
/*
* extent_io.c call back to do delayed allocation processing
*/
-static int run_delalloc_range(struct inode *inode, struct page *locked_page,
+static int run_delalloc_range(void *private_data, struct page *locked_page,
u64 start, u64 end, int *page_started,
unsigned long *nr_written)
{
+ struct inode *inode = private_data;
int ret;
int force_cow = need_force_cow(inode, start, end);
@@ -1509,12 +1585,15 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page,
ret = cow_file_range_async(inode, locked_page, start, end,
page_started, nr_written);
}
+ if (ret)
+ btrfs_cleanup_ordered_extents(inode, start, end - start + 1);
return ret;
}
-static void btrfs_split_extent_hook(struct inode *inode,
+static void btrfs_split_extent_hook(void *private_data,
struct extent_state *orig, u64 split)
{
+ struct inode *inode = private_data;
u64 size;
/* not delalloc, ignore it */
@@ -1549,10 +1628,11 @@ static void btrfs_split_extent_hook(struct inode *inode,
* extents, such as when we are doing sequential writes, so we can properly
* account for the metadata space we'll need.
*/
-static void btrfs_merge_extent_hook(struct inode *inode,
+static void btrfs_merge_extent_hook(void *private_data,
struct extent_state *new,
struct extent_state *other)
{
+ struct inode *inode = private_data;
u64 new_size, old_size;
u32 num_extents;
@@ -1652,9 +1732,10 @@ static void btrfs_del_delalloc_inode(struct btrfs_root *root,
* bytes in this file, and to maintain the list of inodes that
* have pending delalloc work to be done.
*/
-static void btrfs_set_bit_hook(struct inode *inode,
+static void btrfs_set_bit_hook(void *private_data,
struct extent_state *state, unsigned *bits)
{
+ struct inode *inode = private_data;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -1693,15 +1774,24 @@ static void btrfs_set_bit_hook(struct inode *inode,
btrfs_add_delalloc_inodes(root, inode);
spin_unlock(&BTRFS_I(inode)->lock);
}
+
+ if (!(state->state & EXTENT_DELALLOC_NEW) &&
+ (*bits & EXTENT_DELALLOC_NEW)) {
+ spin_lock(&BTRFS_I(inode)->lock);
+ BTRFS_I(inode)->new_delalloc_bytes += state->end + 1 -
+ state->start;
+ spin_unlock(&BTRFS_I(inode)->lock);
+ }
}
/*
* extent_io.c clear_bit_hook, see set_bit_hook for why
*/
-static void btrfs_clear_bit_hook(struct btrfs_inode *inode,
+static void btrfs_clear_bit_hook(void *private_data,
struct extent_state *state,
unsigned *bits)
{
+ struct btrfs_inode *inode = BTRFS_I((struct inode *)private_data);
struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
u64 len = state->end + 1 - state->start;
u32 num_extents = count_max_extents(len);
@@ -1722,7 +1812,7 @@ static void btrfs_clear_bit_hook(struct btrfs_inode *inode,
if (*bits & EXTENT_FIRST_DELALLOC) {
*bits &= ~EXTENT_FIRST_DELALLOC;
- } else if (!(*bits & EXTENT_DO_ACCOUNTING)) {
+ } else if (!(*bits & EXTENT_CLEAR_META_RESV)) {
spin_lock(&inode->lock);
inode->outstanding_extents -= num_extents;
spin_unlock(&inode->lock);
@@ -1733,7 +1823,7 @@ static void btrfs_clear_bit_hook(struct btrfs_inode *inode,
* don't need to call dellalloc_release_metadata if there is an
* error.
*/
- if (*bits & EXTENT_DO_ACCOUNTING &&
+ if (*bits & EXTENT_CLEAR_META_RESV &&
root != fs_info->tree_root)
btrfs_delalloc_release_metadata(inode, len);
@@ -1741,10 +1831,9 @@ static void btrfs_clear_bit_hook(struct btrfs_inode *inode,
if (btrfs_is_testing(fs_info))
return;
- if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
- && do_list && !(state->state & EXTENT_NORESERVE)
- && (*bits & (EXTENT_DO_ACCOUNTING |
- EXTENT_CLEAR_DATA_RESV)))
+ if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID &&
+ do_list && !(state->state & EXTENT_NORESERVE) &&
+ (*bits & EXTENT_CLEAR_DATA_RESV))
btrfs_free_reserved_data_space_noquota(
&inode->vfs_inode,
state->start, len);
@@ -1759,6 +1848,14 @@ static void btrfs_clear_bit_hook(struct btrfs_inode *inode,
btrfs_del_delalloc_inode(root, inode);
spin_unlock(&inode->lock);
}
+
+ if ((state->state & EXTENT_DELALLOC_NEW) &&
+ (*bits & EXTENT_DELALLOC_NEW)) {
+ spin_lock(&inode->lock);
+ ASSERT(inode->new_delalloc_bytes >= len);
+ inode->new_delalloc_bytes -= len;
+ spin_unlock(&inode->lock);
+ }
}
/*
@@ -1802,11 +1899,12 @@ int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
* At IO completion time the cums attached on the ordered extent record
* are inserted into the btree
*/
-static int __btrfs_submit_bio_start(struct inode *inode, struct bio *bio,
+static blk_status_t __btrfs_submit_bio_start(void *private_data, struct bio *bio,
int mirror_num, unsigned long bio_flags,
u64 bio_offset)
{
- int ret = 0;
+ struct inode *inode = private_data;
+ blk_status_t ret = 0;
ret = btrfs_csum_one_bio(inode, bio, 0, 0);
BUG_ON(ret); /* -ENOMEM */
@@ -1821,16 +1919,17 @@ static int __btrfs_submit_bio_start(struct inode *inode, struct bio *bio,
* At IO completion time the cums attached on the ordered extent record
* are inserted into the btree
*/
-static int __btrfs_submit_bio_done(struct inode *inode, struct bio *bio,
+static blk_status_t __btrfs_submit_bio_done(void *private_data, struct bio *bio,
int mirror_num, unsigned long bio_flags,
u64 bio_offset)
{
+ struct inode *inode = private_data;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
- int ret;
+ blk_status_t ret;
ret = btrfs_map_bio(fs_info, bio, mirror_num, 1);
if (ret) {
- bio->bi_error = ret;
+ bio->bi_status = ret;
bio_endio(bio);
}
return ret;
@@ -1840,14 +1939,15 @@ static int __btrfs_submit_bio_done(struct inode *inode, struct bio *bio,
* extent_io.c submission hook. This does the right thing for csum calculation
* on write, or reading the csums from the tree before a read
*/
-static int btrfs_submit_bio_hook(struct inode *inode, struct bio *bio,
- int mirror_num, unsigned long bio_flags,
- u64 bio_offset)
+static blk_status_t btrfs_submit_bio_hook(void *private_data, struct bio *bio,
+ int mirror_num, unsigned long bio_flags,
+ u64 bio_offset)
{
+ struct inode *inode = private_data;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_root *root = BTRFS_I(inode)->root;
enum btrfs_wq_endio_type metadata = BTRFS_WQ_ENDIO_DATA;
- int ret = 0;
+ blk_status_t ret = 0;
int skip_sum;
int async = !atomic_read(&BTRFS_I(inode)->sync_writers);
@@ -1877,8 +1977,8 @@ static int btrfs_submit_bio_hook(struct inode *inode, struct bio *bio,
if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID)
goto mapit;
/* we're doing a write, do the async checksumming */
- ret = btrfs_wq_submit_bio(fs_info, inode, bio, mirror_num,
- bio_flags, bio_offset,
+ ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, bio_flags,
+ bio_offset, inode,
__btrfs_submit_bio_start,
__btrfs_submit_bio_done);
goto out;
@@ -1892,8 +1992,8 @@ mapit:
ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
out:
- if (ret < 0) {
- bio->bi_error = ret;
+ if (ret) {
+ bio->bi_status = ret;
bio_endio(bio);
}
return ret;
@@ -1936,6 +2036,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work)
struct btrfs_writepage_fixup *fixup;
struct btrfs_ordered_extent *ordered;
struct extent_state *cached_state = NULL;
+ struct extent_changeset *data_reserved = NULL;
struct page *page;
struct inode *inode;
u64 page_start;
@@ -1973,7 +2074,7 @@ again:
goto again;
}
- ret = btrfs_delalloc_reserve_space(inode, page_start,
+ ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
PAGE_SIZE);
if (ret) {
mapping_set_error(page->mapping, ret);
@@ -1993,6 +2094,7 @@ out_page:
unlock_page(page);
put_page(page);
kfree(fixup);
+ extent_changeset_free(data_reserved);
}
/*
@@ -2044,6 +2146,7 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
struct btrfs_path *path;
struct extent_buffer *leaf;
struct btrfs_key ins;
+ u64 qg_released;
int extent_inserted = 0;
int ret;
@@ -2099,13 +2202,17 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
ins.objectid = disk_bytenr;
ins.offset = disk_num_bytes;
ins.type = BTRFS_EXTENT_ITEM_KEY;
- ret = btrfs_alloc_reserved_file_extent(trans, root->root_key.objectid,
- btrfs_ino(BTRFS_I(inode)), file_pos, ram_bytes, &ins);
+
/*
* Release the reserved range from inode dirty range map, as it is
* already moved into delayed_ref_head
*/
- btrfs_qgroup_release_data(inode, file_pos, ram_bytes);
+ ret = btrfs_qgroup_release_data(inode, file_pos, ram_bytes);
+ if (ret < 0)
+ goto out;
+ qg_released = ret;
+ ret = btrfs_alloc_reserved_file_extent(trans, root->root_key.objectid,
+ btrfs_ino(BTRFS_I(inode)), file_pos, qg_released, &ins);
out:
btrfs_free_path(path);
@@ -2791,6 +2898,13 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
u64 logical_len = ordered_extent->len;
bool nolock;
bool truncated = false;
+ bool range_locked = false;
+ bool clear_new_delalloc_bytes = false;
+
+ if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
+ !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags) &&
+ !test_bit(BTRFS_ORDERED_DIRECT, &ordered_extent->flags))
+ clear_new_delalloc_bytes = true;
nolock = btrfs_is_free_space_inode(BTRFS_I(inode));
@@ -2820,7 +2934,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
* space for NOCOW range.
* As NOCOW won't cause a new delayed ref, just free the space
*/
- btrfs_qgroup_free_data(inode, ordered_extent->file_offset,
+ btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset,
ordered_extent->len);
btrfs_ordered_update_i_size(inode, 0, ordered_extent);
if (nolock)
@@ -2839,13 +2953,14 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
goto out;
}
+ range_locked = true;
lock_extent_bits(io_tree, ordered_extent->file_offset,
ordered_extent->file_offset + ordered_extent->len - 1,
&cached_state);
ret = test_range_bit(io_tree, ordered_extent->file_offset,
ordered_extent->file_offset + ordered_extent->len - 1,
- EXTENT_DEFRAG, 1, cached_state);
+ EXTENT_DEFRAG, 0, cached_state);
if (ret) {
u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item);
if (0 && last_snapshot >= BTRFS_I(inode)->generation)
@@ -2864,7 +2979,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
trans = NULL;
- goto out_unlock;
+ goto out;
}
trans->block_rsv = &fs_info->delalloc_block_rsv;
@@ -2896,7 +3011,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
trans->transid);
if (ret < 0) {
btrfs_abort_transaction(trans, ret);
- goto out_unlock;
+ goto out;
}
add_pending_csums(trans, inode, &ordered_extent->list);
@@ -2905,14 +3020,26 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
ret = btrfs_update_inode_fallback(trans, root, inode);
if (ret) { /* -ENOMEM or corruption */
btrfs_abort_transaction(trans, ret);
- goto out_unlock;
+ goto out;
}
ret = 0;
-out_unlock:
- unlock_extent_cached(io_tree, ordered_extent->file_offset,
- ordered_extent->file_offset +
- ordered_extent->len - 1, &cached_state, GFP_NOFS);
out:
+ if (range_locked || clear_new_delalloc_bytes) {
+ unsigned int clear_bits = 0;
+
+ if (range_locked)
+ clear_bits |= EXTENT_LOCKED;
+ if (clear_new_delalloc_bytes)
+ clear_bits |= EXTENT_DELALLOC_NEW;
+ clear_extent_bit(&BTRFS_I(inode)->io_tree,
+ ordered_extent->file_offset,
+ ordered_extent->file_offset +
+ ordered_extent->len - 1,
+ clear_bits,
+ (clear_bits & EXTENT_LOCKED) ? 1 : 0,
+ 0, &cached_state, GFP_NOFS);
+ }
+
if (root != fs_info->tree_root)
btrfs_delalloc_release_metadata(BTRFS_I(inode),
ordered_extent->len);
@@ -4401,9 +4528,17 @@ search_again:
if (extent_type != BTRFS_FILE_EXTENT_INLINE) {
item_end +=
btrfs_file_extent_num_bytes(leaf, fi);
+
+ trace_btrfs_truncate_show_fi_regular(
+ BTRFS_I(inode), leaf, fi,
+ found_key.offset);
} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
item_end += btrfs_file_extent_inline_len(leaf,
path->slots[0], fi);
+
+ trace_btrfs_truncate_show_fi_inline(
+ BTRFS_I(inode), leaf, fi, path->slots[0],
+ found_key.offset);
}
item_end--;
}
@@ -4603,13 +4738,6 @@ error:
btrfs_free_path(path);
- if (err == 0) {
- /* only inline file may have last_size != new_size */
- if (new_size >= fs_info->sectorsize ||
- new_size > fs_info->max_inline)
- ASSERT(last_size == new_size);
- }
-
if (be_nice && bytes_deleted > SZ_32M) {
unsigned long updates = trans->delayed_ref_updates;
if (updates) {
@@ -4642,6 +4770,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct btrfs_ordered_extent *ordered;
struct extent_state *cached_state = NULL;
+ struct extent_changeset *data_reserved = NULL;
char *kaddr;
u32 blocksize = fs_info->sectorsize;
pgoff_t index = from >> PAGE_SHIFT;
@@ -4656,7 +4785,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
(!len || ((len & (blocksize - 1)) == 0)))
goto out;
- ret = btrfs_delalloc_reserve_space(inode,
+ ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
round_down(from, blocksize), blocksize);
if (ret)
goto out;
@@ -4664,7 +4793,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
again:
page = find_or_create_page(mapping, index, mask);
if (!page) {
- btrfs_delalloc_release_space(inode,
+ btrfs_delalloc_release_space(inode, data_reserved,
round_down(from, blocksize),
blocksize);
ret = -ENOMEM;
@@ -4736,11 +4865,12 @@ again:
out_unlock:
if (ret)
- btrfs_delalloc_release_space(inode, block_start,
+ btrfs_delalloc_release_space(inode, data_reserved, block_start,
blocksize);
unlock_page(page);
put_page(page);
out:
+ extent_changeset_free(data_reserved);
return ret;
}
@@ -5135,7 +5265,7 @@ static void evict_inode_truncate_pages(struct inode *inode)
* Note, end is the bytenr of last byte, so we need + 1 here.
*/
if (state->state & EXTENT_DELALLOC)
- btrfs_qgroup_free_data(inode, start, end - start + 1);
+ btrfs_qgroup_free_data(inode, NULL, start, end - start + 1);
clear_extent_bit(io_tree, start, end,
EXTENT_LOCKED | EXTENT_DIRTY |
@@ -5748,7 +5878,6 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
struct inode *inode = file_inode(file);
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_root *root = BTRFS_I(inode)->root;
- struct btrfs_item *item;
struct btrfs_dir_item *di;
struct btrfs_key key;
struct btrfs_key found_key;
@@ -5799,7 +5928,6 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
continue;
}
- item = btrfs_item_nr(slot);
btrfs_item_key_to_cpu(leaf, &found_key, slot);
if (found_key.objectid != key.objectid)
@@ -5814,7 +5942,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
ctx->pos = found_key.offset;
di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
- if (verify_dir_item(fs_info, leaf, di))
+ if (verify_dir_item(fs_info, leaf, slot, di))
goto next;
name_len = btrfs_dir_name_len(leaf, di);
@@ -6735,7 +6863,6 @@ static noinline int uncompress_inline(struct btrfs_path *path,
*
* This also copies inline extents directly into the page.
*/
-
struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
struct page *page,
size_t pg_offset, u64 start, u64 len,
@@ -6835,11 +6962,18 @@ again:
found_type == BTRFS_FILE_EXTENT_PREALLOC) {
extent_end = extent_start +
btrfs_file_extent_num_bytes(leaf, item);
+
+ trace_btrfs_get_extent_show_fi_regular(inode, leaf, item,
+ extent_start);
} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
size_t size;
size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
extent_end = ALIGN(extent_start + size,
fs_info->sectorsize);
+
+ trace_btrfs_get_extent_show_fi_inline(inode, leaf, item,
+ path->slots[0],
+ extent_start);
}
next:
if (start >= extent_end) {
@@ -7037,19 +7171,17 @@ struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
em = btrfs_get_extent(inode, page, pg_offset, start, len, create);
if (IS_ERR(em))
return em;
- if (em) {
- /*
- * if our em maps to
- * - a hole or
- * - a pre-alloc extent,
- * there might actually be delalloc bytes behind it.
- */
- if (em->block_start != EXTENT_MAP_HOLE &&
- !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
- return em;
- else
- hole_em = em;
- }
+ /*
+ * If our em maps to:
+ * - a hole or
+ * - a pre-alloc extent,
+ * there might actually be delalloc bytes behind it.
+ */
+ if (em->block_start != EXTENT_MAP_HOLE &&
+ !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+ return em;
+ else
+ hole_em = em;
/* check to see if we've wrapped (len == -1 or similar) */
end = start + len;
@@ -7356,11 +7488,11 @@ out:
bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
{
struct radix_tree_root *root = &inode->i_mapping->page_tree;
- int found = false;
+ bool found = false;
void **pagep = NULL;
struct page *page = NULL;
- int start_idx;
- int end_idx;
+ unsigned long start_idx;
+ unsigned long end_idx;
start_idx = start >> PAGE_SHIFT;
@@ -7854,9 +7986,12 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
bio_end_io_t *repair_endio, void *repair_arg)
{
struct io_failure_record *failrec;
+ struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+ struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
struct bio *bio;
int isector;
int read_mode = 0;
+ int segs;
int ret;
BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
@@ -7868,13 +8003,13 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
ret = btrfs_check_dio_repairable(inode, failed_bio, failrec,
failed_mirror);
if (!ret) {
- free_io_failure(BTRFS_I(inode), failrec);
+ free_io_failure(failure_tree, io_tree, failrec);
return -EIO;
}
- if ((failed_bio->bi_vcnt > 1)
- || (failed_bio->bi_io_vec->bv_len
- > btrfs_inode_sectorsize(inode)))
+ segs = bio_segments(failed_bio);
+ if (segs > 1 ||
+ (failed_bio->bi_io_vec->bv_len > btrfs_inode_sectorsize(inode)))
read_mode |= REQ_FAILFAST_DEV;
isector = start - btrfs_io_bio(failed_bio)->logical;
@@ -7882,7 +8017,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
pgoff, isector, repair_endio, repair_arg);
if (!bio) {
- free_io_failure(BTRFS_I(inode), failrec);
+ free_io_failure(failure_tree, io_tree, failrec);
return -EIO;
}
bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
@@ -7893,7 +8028,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
ret = submit_dio_repair_bio(inode, bio, failrec->this_mirror);
if (ret) {
- free_io_failure(BTRFS_I(inode), failrec);
+ free_io_failure(failure_tree, io_tree, failrec);
bio_put(bio);
}
@@ -7910,19 +8045,24 @@ struct btrfs_retry_complete {
static void btrfs_retry_endio_nocsum(struct bio *bio)
{
struct btrfs_retry_complete *done = bio->bi_private;
+ struct inode *inode = done->inode;
struct bio_vec *bvec;
+ struct extent_io_tree *io_tree, *failure_tree;
int i;
- if (bio->bi_error)
+ if (bio->bi_status)
goto end;
ASSERT(bio->bi_vcnt == 1);
- ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode));
+ io_tree = &BTRFS_I(inode)->io_tree;
+ failure_tree = &BTRFS_I(inode)->io_failure_tree;
+ ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode));
done->uptodate = 1;
bio_for_each_segment_all(bvec, bio, i)
- clean_io_failure(BTRFS_I(done->inode), done->start,
- bvec->bv_page, 0);
+ clean_io_failure(BTRFS_I(inode)->root->fs_info, failure_tree,
+ io_tree, done->start, bvec->bv_page,
+ btrfs_ino(BTRFS_I(inode)), 0);
end:
complete(&done->done);
bio_put(bio);
@@ -7932,36 +8072,40 @@ static int __btrfs_correct_data_nocsum(struct inode *inode,
struct btrfs_io_bio *io_bio)
{
struct btrfs_fs_info *fs_info;
- struct bio_vec *bvec;
+ struct bio_vec bvec;
+ struct bvec_iter iter;
struct btrfs_retry_complete done;
u64 start;
unsigned int pgoff;
u32 sectorsize;
int nr_sectors;
- int i;
int ret;
+ int err = 0;
fs_info = BTRFS_I(inode)->root->fs_info;
sectorsize = fs_info->sectorsize;
start = io_bio->logical;
done.inode = inode;
+ io_bio->bio.bi_iter = io_bio->iter;
- bio_for_each_segment_all(bvec, &io_bio->bio, i) {
- nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
- pgoff = bvec->bv_offset;
+ bio_for_each_segment(bvec, &io_bio->bio, iter) {
+ nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len);
+ pgoff = bvec.bv_offset;
next_block_or_try_again:
done.uptodate = 0;
done.start = start;
init_completion(&done.done);
- ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+ ret = dio_read_error(inode, &io_bio->bio, bvec.bv_page,
pgoff, start, start + sectorsize - 1,
io_bio->mirror_num,
btrfs_retry_endio_nocsum, &done);
- if (ret)
- return ret;
+ if (ret) {
+ err = ret;
+ goto next;
+ }
wait_for_completion(&done.done);
@@ -7970,6 +8114,7 @@ next_block_or_try_again:
goto next_block_or_try_again;
}
+next:
start += sectorsize;
nr_sectors--;
@@ -7980,19 +8125,21 @@ next_block_or_try_again:
}
}
- return 0;
+ return err;
}
static void btrfs_retry_endio(struct bio *bio)
{
struct btrfs_retry_complete *done = bio->bi_private;
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+ struct extent_io_tree *io_tree, *failure_tree;
+ struct inode *inode = done->inode;
struct bio_vec *bvec;
int uptodate;
int ret;
int i;
- if (bio->bi_error)
+ if (bio->bi_status)
goto end;
uptodate = 1;
@@ -8000,13 +8147,19 @@ static void btrfs_retry_endio(struct bio *bio)
ASSERT(bio->bi_vcnt == 1);
ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode));
+ io_tree = &BTRFS_I(inode)->io_tree;
+ failure_tree = &BTRFS_I(inode)->io_failure_tree;
+
bio_for_each_segment_all(bvec, bio, i) {
- ret = __readpage_endio_check(done->inode, io_bio, i,
- bvec->bv_page, bvec->bv_offset,
- done->start, bvec->bv_len);
+ ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page,
+ bvec->bv_offset, done->start,
+ bvec->bv_len);
if (!ret)
- clean_io_failure(BTRFS_I(done->inode), done->start,
- bvec->bv_page, bvec->bv_offset);
+ clean_io_failure(BTRFS_I(inode)->root->fs_info,
+ failure_tree, io_tree, done->start,
+ bvec->bv_page,
+ btrfs_ino(BTRFS_I(inode)),
+ bvec->bv_offset);
else
uptodate = 0;
}
@@ -8017,11 +8170,12 @@ end:
bio_put(bio);
}
-static int __btrfs_subio_endio_read(struct inode *inode,
- struct btrfs_io_bio *io_bio, int err)
+static blk_status_t __btrfs_subio_endio_read(struct inode *inode,
+ struct btrfs_io_bio *io_bio, blk_status_t err)
{
struct btrfs_fs_info *fs_info;
- struct bio_vec *bvec;
+ struct bio_vec bvec;
+ struct bvec_iter iter;
struct btrfs_retry_complete done;
u64 start;
u64 offset = 0;
@@ -8029,7 +8183,7 @@ static int __btrfs_subio_endio_read(struct inode *inode,
int nr_sectors;
unsigned int pgoff;
int csum_pos;
- int i;
+ bool uptodate = (err == 0);
int ret;
fs_info = BTRFS_I(inode)->root->fs_info;
@@ -8038,29 +8192,31 @@ static int __btrfs_subio_endio_read(struct inode *inode,
err = 0;
start = io_bio->logical;
done.inode = inode;
+ io_bio->bio.bi_iter = io_bio->iter;
- bio_for_each_segment_all(bvec, &io_bio->bio, i) {
- nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
+ bio_for_each_segment(bvec, &io_bio->bio, iter) {
+ nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len);
- pgoff = bvec->bv_offset;
+ pgoff = bvec.bv_offset;
next_block:
- csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset);
- ret = __readpage_endio_check(inode, io_bio, csum_pos,
- bvec->bv_page, pgoff, start,
- sectorsize);
- if (likely(!ret))
- goto next;
+ if (uptodate) {
+ csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset);
+ ret = __readpage_endio_check(inode, io_bio, csum_pos,
+ bvec.bv_page, pgoff, start, sectorsize);
+ if (likely(!ret))
+ goto next;
+ }
try_again:
done.uptodate = 0;
done.start = start;
init_completion(&done.done);
- ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+ ret = dio_read_error(inode, &io_bio->bio, bvec.bv_page,
pgoff, start, start + sectorsize - 1,
io_bio->mirror_num,
btrfs_retry_endio, &done);
if (ret) {
- err = ret;
+ err = errno_to_blk_status(ret);
goto next;
}
@@ -8087,8 +8243,8 @@ next:
return err;
}
-static int btrfs_subio_endio_read(struct inode *inode,
- struct btrfs_io_bio *io_bio, int err)
+static blk_status_t btrfs_subio_endio_read(struct inode *inode,
+ struct btrfs_io_bio *io_bio, blk_status_t err)
{
bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
@@ -8108,10 +8264,13 @@ static void btrfs_endio_direct_read(struct bio *bio)
struct inode *inode = dip->inode;
struct bio *dio_bio;
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
- int err = bio->bi_error;
+ blk_status_t err = bio->bi_status;
- if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED)
+ if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) {
err = btrfs_subio_endio_read(inode, io_bio, err);
+ if (!err)
+ bio->bi_status = 0;
+ }
unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
dip->logical_offset + dip->bytes - 1);
@@ -8119,25 +8278,34 @@ static void btrfs_endio_direct_read(struct bio *bio)
kfree(dip);
- dio_bio->bi_error = bio->bi_error;
- dio_end_io(dio_bio, bio->bi_error);
+ dio_bio->bi_status = bio->bi_status;
+ dio_end_io(dio_bio);
if (io_bio->end_io)
- io_bio->end_io(io_bio, err);
+ io_bio->end_io(io_bio, blk_status_to_errno(err));
bio_put(bio);
}
-static void btrfs_endio_direct_write_update_ordered(struct inode *inode,
- const u64 offset,
- const u64 bytes,
- const int uptodate)
+static void __endio_write_update_ordered(struct inode *inode,
+ const u64 offset, const u64 bytes,
+ const bool uptodate)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_ordered_extent *ordered = NULL;
+ struct btrfs_workqueue *wq;
+ btrfs_work_func_t func;
u64 ordered_offset = offset;
u64 ordered_bytes = bytes;
int ret;
+ if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+ wq = fs_info->endio_freespace_worker;
+ func = btrfs_freespace_write_helper;
+ } else {
+ wq = fs_info->endio_write_workers;
+ func = btrfs_endio_write_helper;
+ }
+
again:
ret = btrfs_dec_test_first_ordered_pending(inode, &ordered,
&ordered_offset,
@@ -8146,9 +8314,8 @@ again:
if (!ret)
goto out_test;
- btrfs_init_work(&ordered->work, btrfs_endio_write_helper,
- finish_ordered_fn, NULL, NULL);
- btrfs_queue_work(fs_info->endio_write_workers, &ordered->work);
+ btrfs_init_work(&ordered->work, func, finish_ordered_fn, NULL, NULL);
+ btrfs_queue_work(wq, &ordered->work);
out_test:
/*
* our bio might span multiple ordered extents. If we haven't
@@ -8166,23 +8333,22 @@ static void btrfs_endio_direct_write(struct bio *bio)
struct btrfs_dio_private *dip = bio->bi_private;
struct bio *dio_bio = dip->dio_bio;
- btrfs_endio_direct_write_update_ordered(dip->inode,
- dip->logical_offset,
- dip->bytes,
- !bio->bi_error);
+ __endio_write_update_ordered(dip->inode, dip->logical_offset,
+ dip->bytes, !bio->bi_status);
kfree(dip);
- dio_bio->bi_error = bio->bi_error;
- dio_end_io(dio_bio, bio->bi_error);
+ dio_bio->bi_status = bio->bi_status;
+ dio_end_io(dio_bio);
bio_put(bio);
}
-static int __btrfs_submit_bio_start_direct_io(struct inode *inode,
+static blk_status_t __btrfs_submit_bio_start_direct_io(void *private_data,
struct bio *bio, int mirror_num,
unsigned long bio_flags, u64 offset)
{
- int ret;
+ struct inode *inode = private_data;
+ blk_status_t ret;
ret = btrfs_csum_one_bio(inode, bio, offset, 1);
BUG_ON(ret); /* -ENOMEM */
return 0;
@@ -8191,7 +8357,7 @@ static int __btrfs_submit_bio_start_direct_io(struct inode *inode,
static void btrfs_end_dio_bio(struct bio *bio)
{
struct btrfs_dio_private *dip = bio->bi_private;
- int err = bio->bi_error;
+ blk_status_t err = bio->bi_status;
if (err)
btrfs_warn(BTRFS_I(dip->inode)->root->fs_info,
@@ -8221,31 +8387,21 @@ static void btrfs_end_dio_bio(struct bio *bio)
if (dip->errors) {
bio_io_error(dip->orig_bio);
} else {
- dip->dio_bio->bi_error = 0;
+ dip->dio_bio->bi_status = 0;
bio_endio(dip->orig_bio);
}
out:
bio_put(bio);
}
-static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev,
- u64 first_sector, gfp_t gfp_flags)
-{
- struct bio *bio;
- bio = btrfs_bio_alloc(bdev, first_sector, BIO_MAX_PAGES, gfp_flags);
- if (bio)
- bio_associate_current(bio);
- return bio;
-}
-
-static inline int btrfs_lookup_and_bind_dio_csum(struct inode *inode,
+static inline blk_status_t btrfs_lookup_and_bind_dio_csum(struct inode *inode,
struct btrfs_dio_private *dip,
struct bio *bio,
u64 file_offset)
{
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
struct btrfs_io_bio *orig_io_bio = btrfs_io_bio(dip->orig_bio);
- int ret;
+ blk_status_t ret;
/*
* We load all the csum data we need when we submit
@@ -8276,7 +8432,7 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_dio_private *dip = bio->bi_private;
bool write = bio_op(bio) == REQ_OP_WRITE;
- int ret;
+ blk_status_t ret;
if (async_submit)
async_submit = !atomic_read(&BTRFS_I(inode)->sync_writers);
@@ -8293,8 +8449,8 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
goto map;
if (write && async_submit) {
- ret = btrfs_wq_submit_bio(fs_info, inode, bio, 0, 0,
- file_offset,
+ ret = btrfs_wq_submit_bio(fs_info, bio, 0, 0,
+ file_offset, inode,
__btrfs_submit_bio_start_direct_io,
__btrfs_submit_bio_done);
goto err;
@@ -8324,103 +8480,83 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
{
struct inode *inode = dip->inode;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
- struct btrfs_root *root = BTRFS_I(inode)->root;
struct bio *bio;
struct bio *orig_bio = dip->orig_bio;
- struct bio_vec *bvec;
u64 start_sector = orig_bio->bi_iter.bi_sector;
u64 file_offset = dip->logical_offset;
- u64 submit_len = 0;
u64 map_length;
- u32 blocksize = fs_info->sectorsize;
int async_submit = 0;
- int nr_sectors;
+ u64 submit_len;
+ int clone_offset = 0;
+ int clone_len;
int ret;
- int i, j;
map_length = orig_bio->bi_iter.bi_size;
+ submit_len = map_length;
ret = btrfs_map_block(fs_info, btrfs_op(orig_bio), start_sector << 9,
&map_length, NULL, 0);
if (ret)
return -EIO;
- if (map_length >= orig_bio->bi_iter.bi_size) {
+ if (map_length >= submit_len) {
bio = orig_bio;
dip->flags |= BTRFS_DIO_ORIG_BIO_SUBMITTED;
goto submit;
}
/* async crcs make it difficult to collect full stripe writes. */
- if (btrfs_get_alloc_profile(root, 1) & BTRFS_BLOCK_GROUP_RAID56_MASK)
+ if (btrfs_data_alloc_profile(fs_info) & BTRFS_BLOCK_GROUP_RAID56_MASK)
async_submit = 0;
else
async_submit = 1;
- bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
- if (!bio)
- return -ENOMEM;
-
- bio->bi_opf = orig_bio->bi_opf;
- bio->bi_private = dip;
- bio->bi_end_io = btrfs_end_dio_bio;
- btrfs_io_bio(bio)->logical = file_offset;
+ /* bio split */
+ ASSERT(map_length <= INT_MAX);
atomic_inc(&dip->pending_bios);
+ do {
+ clone_len = min_t(int, submit_len, map_length);
- bio_for_each_segment_all(bvec, orig_bio, j) {
- nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
- i = 0;
-next_block:
- if (unlikely(map_length < submit_len + blocksize ||
- bio_add_page(bio, bvec->bv_page, blocksize,
- bvec->bv_offset + (i * blocksize)) < blocksize)) {
- /*
- * inc the count before we submit the bio so
- * we know the end IO handler won't happen before
- * we inc the count. Otherwise, the dip might get freed
- * before we're done setting it up
- */
- atomic_inc(&dip->pending_bios);
- ret = __btrfs_submit_dio_bio(bio, inode,
- file_offset, skip_sum,
- async_submit);
- if (ret) {
- bio_put(bio);
- atomic_dec(&dip->pending_bios);
- goto out_err;
- }
-
- start_sector += submit_len >> 9;
- file_offset += submit_len;
+ /*
+ * This will never fail as it's passing GPF_NOFS and
+ * the allocation is backed by btrfs_bioset.
+ */
+ bio = btrfs_bio_clone_partial(orig_bio, clone_offset,
+ clone_len);
+ bio->bi_private = dip;
+ bio->bi_end_io = btrfs_end_dio_bio;
+ btrfs_io_bio(bio)->logical = file_offset;
+
+ ASSERT(submit_len >= clone_len);
+ submit_len -= clone_len;
+ if (submit_len == 0)
+ break;
- submit_len = 0;
+ /*
+ * Increase the count before we submit the bio so we know
+ * the end IO handler won't happen before we increase the
+ * count. Otherwise, the dip might get freed before we're
+ * done setting it up.
+ */
+ atomic_inc(&dip->pending_bios);
- bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev,
- start_sector, GFP_NOFS);
- if (!bio)
- goto out_err;
- bio->bi_opf = orig_bio->bi_opf;
- bio->bi_private = dip;
- bio->bi_end_io = btrfs_end_dio_bio;
- btrfs_io_bio(bio)->logical = file_offset;
+ ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum,
+ async_submit);
+ if (ret) {
+ bio_put(bio);
+ atomic_dec(&dip->pending_bios);
+ goto out_err;
+ }
- map_length = orig_bio->bi_iter.bi_size;
- ret = btrfs_map_block(fs_info, btrfs_op(orig_bio),
- start_sector << 9,
- &map_length, NULL, 0);
- if (ret) {
- bio_put(bio);
- goto out_err;
- }
+ clone_offset += clone_len;
+ start_sector += clone_len >> 9;
+ file_offset += clone_len;
- goto next_block;
- } else {
- submit_len += blocksize;
- if (--nr_sectors) {
- i++;
- goto next_block;
- }
- }
- }
+ map_length = submit_len;
+ ret = btrfs_map_block(fs_info, btrfs_op(orig_bio),
+ start_sector << 9, &map_length, NULL, 0);
+ if (ret)
+ goto out_err;
+ } while (submit_len > 0);
submit:
ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum,
@@ -8447,19 +8583,15 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
loff_t file_offset)
{
struct btrfs_dio_private *dip = NULL;
- struct bio *io_bio = NULL;
- struct btrfs_io_bio *btrfs_bio;
+ struct bio *bio = NULL;
+ struct btrfs_io_bio *io_bio;
int skip_sum;
bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
int ret = 0;
skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
- io_bio = btrfs_bio_clone(dio_bio, GFP_NOFS);
- if (!io_bio) {
- ret = -ENOMEM;
- goto free_ordered;
- }
+ bio = btrfs_bio_clone(dio_bio);
dip = kzalloc(sizeof(*dip), GFP_NOFS);
if (!dip) {
@@ -8472,17 +8604,17 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
dip->logical_offset = file_offset;
dip->bytes = dio_bio->bi_iter.bi_size;
dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
- io_bio->bi_private = dip;
- dip->orig_bio = io_bio;
+ bio->bi_private = dip;
+ dip->orig_bio = bio;
dip->dio_bio = dio_bio;
atomic_set(&dip->pending_bios, 0);
- btrfs_bio = btrfs_io_bio(io_bio);
- btrfs_bio->logical = file_offset;
+ io_bio = btrfs_io_bio(bio);
+ io_bio->logical = file_offset;
if (write) {
- io_bio->bi_end_io = btrfs_endio_direct_write;
+ bio->bi_end_io = btrfs_endio_direct_write;
} else {
- io_bio->bi_end_io = btrfs_endio_direct_read;
+ bio->bi_end_io = btrfs_endio_direct_read;
dip->subio_endio = btrfs_subio_endio_read;
}
@@ -8505,8 +8637,8 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
if (!ret)
return;
- if (btrfs_bio->end_io)
- btrfs_bio->end_io(btrfs_bio, ret);
+ if (io_bio->end_io)
+ io_bio->end_io(io_bio, ret);
free_ordered:
/*
@@ -8518,35 +8650,34 @@ free_ordered:
* same as btrfs_endio_direct_[write|read] because we can't call these
* callbacks - they require an allocated dip and a clone of dio_bio.
*/
- if (io_bio && dip) {
- io_bio->bi_error = -EIO;
- bio_endio(io_bio);
+ if (bio && dip) {
+ bio_io_error(bio);
/*
- * The end io callbacks free our dip, do the final put on io_bio
+ * The end io callbacks free our dip, do the final put on bio
* and all the cleanup and final put for dio_bio (through
* dio_end_io()).
*/
dip = NULL;
- io_bio = NULL;
+ bio = NULL;
} else {
if (write)
- btrfs_endio_direct_write_update_ordered(inode,
+ __endio_write_update_ordered(inode,
file_offset,
dio_bio->bi_iter.bi_size,
- 0);
+ false);
else
unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
file_offset + dio_bio->bi_iter.bi_size - 1);
- dio_bio->bi_error = -EIO;
+ dio_bio->bi_status = BLK_STS_IOERR;
/*
* Releases and cleans up our dio_bio, no need to bio_put()
* nor bio_endio()/bio_io_error() against dio_bio.
*/
- dio_end_io(dio_bio, ret);
+ dio_end_io(dio_bio);
}
- if (io_bio)
- bio_put(io_bio);
+ if (bio)
+ bio_put(bio);
kfree(dip);
}
@@ -8590,6 +8721,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
struct inode *inode = file->f_mapping->host;
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_dio_data dio_data = { 0 };
+ struct extent_changeset *data_reserved = NULL;
loff_t offset = iocb->ki_pos;
size_t count = 0;
int flags = 0;
@@ -8625,8 +8757,12 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
dio_data.overwrite = 1;
inode_unlock(inode);
relock = true;
+ } else if (iocb->ki_flags & IOCB_NOWAIT) {
+ ret = -EAGAIN;
+ goto out;
}
- ret = btrfs_delalloc_reserve_space(inode, offset, count);
+ ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
+ offset, count);
if (ret)
goto out;
dio_data.outstanding_extents = count_max_extents(count);
@@ -8658,8 +8794,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
current->journal_info = NULL;
if (ret < 0 && ret != -EIOCBQUEUED) {
if (dio_data.reserve)
- btrfs_delalloc_release_space(inode, offset,
- dio_data.reserve);
+ btrfs_delalloc_release_space(inode, data_reserved,
+ offset, dio_data.reserve);
/*
* On error we might have left some ordered extents
* without submitting corresponding bios for them, so
@@ -8668,14 +8804,14 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
*/
if (dio_data.unsubmitted_oe_range_start <
dio_data.unsubmitted_oe_range_end)
- btrfs_endio_direct_write_update_ordered(inode,
+ __endio_write_update_ordered(inode,
dio_data.unsubmitted_oe_range_start,
dio_data.unsubmitted_oe_range_end -
dio_data.unsubmitted_oe_range_start,
- 0);
+ false);
} else if (ret >= 0 && (size_t)ret < count)
- btrfs_delalloc_release_space(inode, offset,
- count - (size_t)ret);
+ btrfs_delalloc_release_space(inode, data_reserved,
+ offset, count - (size_t)ret);
}
out:
if (wakeup)
@@ -8683,6 +8819,7 @@ out:
if (relock)
inode_lock(inode);
+ extent_changeset_free(data_reserved);
return ret;
}
@@ -8819,6 +8956,7 @@ again:
if (!inode_evicting)
clear_extent_bit(tree, start, end,
EXTENT_DIRTY | EXTENT_DELALLOC |
+ EXTENT_DELALLOC_NEW |
EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
EXTENT_DEFRAG, 1, 0, &cached_state,
GFP_NOFS);
@@ -8872,12 +9010,12 @@ again:
* free the entire extent.
*/
if (PageDirty(page))
- btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
+ btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE);
if (!inode_evicting) {
clear_extent_bit(tree, page_start, page_end,
EXTENT_LOCKED | EXTENT_DIRTY |
- EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
- EXTENT_DEFRAG, 1, 1,
+ EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
+ EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 1, 1,
&cached_state, GFP_NOFS);
__btrfs_releasepage(page, GFP_NOFS);
@@ -8914,6 +9052,7 @@ int btrfs_page_mkwrite(struct vm_fault *vmf)
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
struct btrfs_ordered_extent *ordered;
struct extent_state *cached_state = NULL;
+ struct extent_changeset *data_reserved = NULL;
char *kaddr;
unsigned long zero_start;
loff_t size;
@@ -8939,7 +9078,7 @@ int btrfs_page_mkwrite(struct vm_fault *vmf)
* end up waiting indefinitely to get a lock on the page currently
* being processed by btrfs_page_mkwrite() function.
*/
- ret = btrfs_delalloc_reserve_space(inode, page_start,
+ ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
reserved_space);
if (!ret) {
ret = file_update_time(vmf->vma->vm_file);
@@ -8993,8 +9132,8 @@ again:
spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->outstanding_extents++;
spin_unlock(&BTRFS_I(inode)->lock);
- btrfs_delalloc_release_space(inode, page_start,
- PAGE_SIZE - reserved_space);
+ btrfs_delalloc_release_space(inode, data_reserved,
+ page_start, PAGE_SIZE - reserved_space);
}
}
@@ -9045,13 +9184,16 @@ again:
out_unlock:
if (!ret) {
sb_end_pagefault(inode->i_sb);
+ extent_changeset_free(data_reserved);
return VM_FAULT_LOCKED;
}
unlock_page(page);
out:
- btrfs_delalloc_release_space(inode, page_start, reserved_space);
+ btrfs_delalloc_release_space(inode, data_reserved, page_start,
+ reserved_space);
out_noreserve:
sb_end_pagefault(inode->i_sb);
+ extent_changeset_free(data_reserved);
return ret;
}
@@ -9248,6 +9390,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
ei->last_sub_trans = 0;
ei->logged_trans = 0;
ei->delalloc_bytes = 0;
+ ei->new_delalloc_bytes = 0;
ei->defrag_bytes = 0;
ei->disk_i_size = 0;
ei->flags = 0;
@@ -9272,8 +9415,8 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
inode = &ei->vfs_inode;
extent_map_tree_init(&ei->extent_tree);
- extent_io_tree_init(&ei->io_tree, &inode->i_data);
- extent_io_tree_init(&ei->io_failure_tree, &inode->i_data);
+ extent_io_tree_init(&ei->io_tree, inode);
+ extent_io_tree_init(&ei->io_failure_tree, inode);
ei->io_tree.track_uptodate = 1;
ei->io_failure_tree.track_uptodate = 1;
atomic_set(&ei->sync_writers, 0);
@@ -9313,6 +9456,7 @@ void btrfs_destroy_inode(struct inode *inode)
WARN_ON(BTRFS_I(inode)->outstanding_extents);
WARN_ON(BTRFS_I(inode)->reserved_extents);
WARN_ON(BTRFS_I(inode)->delalloc_bytes);
+ WARN_ON(BTRFS_I(inode)->new_delalloc_bytes);
WARN_ON(BTRFS_I(inode)->csum_bytes);
WARN_ON(BTRFS_I(inode)->defrag_bytes);
@@ -9381,7 +9525,6 @@ void btrfs_destroy_cachep(void)
rcu_barrier();
kmem_cache_destroy(btrfs_inode_cachep);
kmem_cache_destroy(btrfs_trans_handle_cachep);
- kmem_cache_destroy(btrfs_transaction_cachep);
kmem_cache_destroy(btrfs_path_cachep);
kmem_cache_destroy(btrfs_free_space_cachep);
}
@@ -9401,12 +9544,6 @@ int btrfs_init_cachep(void)
if (!btrfs_trans_handle_cachep)
goto fail;
- btrfs_transaction_cachep = kmem_cache_create("btrfs_transaction",
- sizeof(struct btrfs_transaction), 0,
- SLAB_TEMPORARY | SLAB_MEM_SPREAD, NULL);
- if (!btrfs_transaction_cachep)
- goto fail;
-
btrfs_path_cachep = kmem_cache_create("btrfs_path",
sizeof(struct btrfs_path), 0,
SLAB_MEM_SPREAD, NULL);
@@ -9431,12 +9568,30 @@ static int btrfs_getattr(const struct path *path, struct kstat *stat,
u64 delalloc_bytes;
struct inode *inode = d_inode(path->dentry);
u32 blocksize = inode->i_sb->s_blocksize;
+ u32 bi_flags = BTRFS_I(inode)->flags;
+
+ stat->result_mask |= STATX_BTIME;
+ stat->btime.tv_sec = BTRFS_I(inode)->i_otime.tv_sec;
+ stat->btime.tv_nsec = BTRFS_I(inode)->i_otime.tv_nsec;
+ if (bi_flags & BTRFS_INODE_APPEND)
+ stat->attributes |= STATX_ATTR_APPEND;
+ if (bi_flags & BTRFS_INODE_COMPRESS)
+ stat->attributes |= STATX_ATTR_COMPRESSED;
+ if (bi_flags & BTRFS_INODE_IMMUTABLE)
+ stat->attributes |= STATX_ATTR_IMMUTABLE;
+ if (bi_flags & BTRFS_INODE_NODUMP)
+ stat->attributes |= STATX_ATTR_NODUMP;
+
+ stat->attributes_mask |= (STATX_ATTR_APPEND |
+ STATX_ATTR_COMPRESSED |
+ STATX_ATTR_IMMUTABLE |
+ STATX_ATTR_NODUMP);
generic_fillattr(inode, stat);
stat->dev = BTRFS_I(inode)->root->anon_dev;
spin_lock(&BTRFS_I(inode)->lock);
- delalloc_bytes = BTRFS_I(inode)->delalloc_bytes;
+ delalloc_bytes = BTRFS_I(inode)->new_delalloc_bytes;
spin_unlock(&BTRFS_I(inode)->lock);
stat->blocks = (ALIGN(inode_get_bytes(inode), blocksize) +
ALIGN(delalloc_bytes, blocksize)) >> 9;
@@ -10405,7 +10560,7 @@ next:
btrfs_end_transaction(trans);
}
if (cur_offset < end)
- btrfs_free_reserved_data_space(inode, cur_offset,
+ btrfs_free_reserved_data_space(inode, NULL, cur_offset,
end - cur_offset + 1);
return ret;
}
@@ -10526,6 +10681,42 @@ static int btrfs_readpage_io_failed_hook(struct page *page, int failed_mirror)
return -EAGAIN;
}
+static struct btrfs_fs_info *iotree_fs_info(void *private_data)
+{
+ struct inode *inode = private_data;
+ return btrfs_sb(inode->i_sb);
+}
+
+static void btrfs_check_extent_io_range(void *private_data, const char *caller,
+ u64 start, u64 end)
+{
+ struct inode *inode = private_data;
+ u64 isize;
+
+ isize = i_size_read(inode);
+ if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) {
+ btrfs_debug_rl(BTRFS_I(inode)->root->fs_info,
+ "%s: ino %llu isize %llu odd range [%llu,%llu]",
+ caller, btrfs_ino(BTRFS_I(inode)), isize, start, end);
+ }
+}
+
+void btrfs_set_range_writeback(void *private_data, u64 start, u64 end)
+{
+ struct inode *inode = private_data;
+ unsigned long index = start >> PAGE_SHIFT;
+ unsigned long end_index = end >> PAGE_SHIFT;
+ struct page *page;
+
+ while (index <= end_index) {
+ page = find_get_page(inode->i_mapping, index);
+ ASSERT(page); /* Pages should be in the extent_io_tree */
+ set_page_writeback(page);
+ put_page(page);
+ index++;
+ }
+}
+
static const struct inode_operations btrfs_dir_inode_operations = {
.getattr = btrfs_getattr,
.lookup = btrfs_lookup,
@@ -10569,6 +10760,8 @@ static const struct extent_io_ops btrfs_extent_io_ops = {
.readpage_end_io_hook = btrfs_readpage_end_io_hook,
.merge_bio_hook = btrfs_merge_bio_hook,
.readpage_io_failed_hook = btrfs_readpage_io_failed_hook,
+ .tree_fs_info = iotree_fs_info,
+ .set_range_writeback = btrfs_set_range_writeback,
/* optional callbacks */
.fill_delalloc = run_delalloc_range,
@@ -10578,6 +10771,7 @@ static const struct extent_io_ops btrfs_extent_io_ops = {
.clear_bit_hook = btrfs_clear_bit_hook,
.merge_extent_hook = btrfs_merge_extent_hook,
.split_extent_hook = btrfs_split_extent_hook,
+ .check_extent_io_range = btrfs_check_extent_io_range,
};
/*
generated by cgit v1.2.1 (git 2.18.0) at 2025-04-26 09:50:04 +0000