return -EIO; /* we fixed nothing */
}
-static void end_workqueue_bio(struct bio *bio, int err)
+static void end_workqueue_bio(struct bio *bio)
{
struct btrfs_end_io_wq *end_io_wq = bio->bi_private;
struct btrfs_fs_info *fs_info;
btrfs_work_func_t func;
fs_info = end_io_wq->info;
- end_io_wq->error = err;
+ end_io_wq->error = bio->bi_error;
if (bio->bi_rw & REQ_WRITE) {
if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) {
/* If an error occured we just want to clean up the bio and move on */
if (async->error) {
- bio_endio(async->bio, async->error);
+ async->bio->bi_error = async->error;
+ bio_endio(async->bio);
return;
}
* submission context. Just jump into btrfs_map_bio
*/
ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, mirror_num, 1);
- if (ret)
- bio_endio(bio, ret);
+ if (ret) {
+ bio->bi_error = ret;
+ bio_endio(bio);
+ }
return ret;
}
__btree_submit_bio_done);
}
- if (ret) {
+ if (ret)
+ goto out_w_error;
+ return 0;
+
out_w_error:
- bio_endio(bio, ret);
- }
+ bio->bi_error = ret;
+ bio_endio(bio);
return ret;
}
{
struct bio *bio;
struct btrfs_end_io_wq *end_io_wq;
- int error;
end_io_wq = container_of(work, struct btrfs_end_io_wq, work);
bio = end_io_wq->bio;
- error = end_io_wq->error;
+ bio->bi_error = end_io_wq->error;
bio->bi_private = end_io_wq->private;
bio->bi_end_io = end_io_wq->end_io;
kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
- bio_endio(bio, error);
+ bio_endio(bio);
}
static int cleaner_kthread(void *arg)
* endio for the write_dev_flush, this will wake anyone waiting
* for the barrier when it is done
*/
-static void btrfs_end_empty_barrier(struct bio *bio, int err)
+static void btrfs_end_empty_barrier(struct bio *bio)
{
- if (err)
- clear_bit(BIO_UPTODATE, &bio->bi_flags);
if (bio->bi_private)
complete(bio->bi_private);
bio_put(bio);
wait_for_completion(&device->flush_wait);
- if (!bio_flagged(bio, BIO_UPTODATE)) {
- ret = -EIO;
+ if (bio->bi_error) {
+ ret = bio->bi_error;
btrfs_dev_stat_inc_and_print(device,
BTRFS_DEV_STAT_FLUSH_ERRS);
}
* block groups queued for removal, the deletion will be
* skipped when we quit the cleaner thread.
*/
- mutex_lock(&root->fs_info->cleaner_mutex);
btrfs_delete_unused_bgs(root->fs_info);
- mutex_unlock(&root->fs_info->cleaner_mutex);
ret = btrfs_commit_super(root);
if (ret)
* Scheduling is not allowed, so the extent state tree is expected
* to have one and only one object corresponding to this IO.
*/
-static void end_bio_extent_writepage(struct bio *bio, int err)
+static void end_bio_extent_writepage(struct bio *bio)
{
struct bio_vec *bvec;
u64 start;
start = page_offset(page);
end = start + bvec->bv_offset + bvec->bv_len - 1;
- if (end_extent_writepage(page, err, start, end))
+ if (end_extent_writepage(page, bio->bi_error, start, end))
continue;
end_page_writeback(page);
* Scheduling is not allowed, so the extent state tree is expected
* to have one and only one object corresponding to this IO.
*/
-static void end_bio_extent_readpage(struct bio *bio, int err)
+static void end_bio_extent_readpage(struct bio *bio)
{
struct bio_vec *bvec;
- int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
+ int uptodate = !bio->bi_error;
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
struct extent_io_tree *tree;
u64 offset = 0;
int ret;
int i;
- if (err)
- uptodate = 0;
-
bio_for_each_segment_all(bvec, bio, i) {
struct page *page = bvec->bv_page;
struct inode *inode = page->mapping->host;
pr_debug("end_bio_extent_readpage: bi_sector=%llu, err=%d, "
- "mirror=%u\n", (u64)bio->bi_iter.bi_sector, err,
- io_bio->mirror_num);
+ "mirror=%u\n", (u64)bio->bi_iter.bi_sector,
+ bio->bi_error, io_bio->mirror_num);
tree = &BTRFS_I(inode)->io_tree;
/* We always issue full-page reads, but if some block
if (tree->ops && tree->ops->readpage_io_failed_hook) {
ret = tree->ops->readpage_io_failed_hook(page, mirror);
- if (!ret && !err &&
- test_bit(BIO_UPTODATE, &bio->bi_flags))
+ if (!ret && !bio->bi_error)
uptodate = 1;
} else {
/*
ret = bio_readpage_error(bio, offset, page, start, end,
mirror);
if (ret == 0) {
- uptodate =
- test_bit(BIO_UPTODATE, &bio->bi_flags);
- if (err)
- uptodate = 0;
+ uptodate = !bio->bi_error;
offset += len;
continue;
}
endio_readpage_release_extent(tree, extent_start, extent_len,
uptodate);
if (io_bio->end_io)
- io_bio->end_io(io_bio, err);
+ io_bio->end_io(io_bio, bio->bi_error);
bio_put(bio);
}
bio_end_io_t end_io_func,
int mirror_num,
unsigned long prev_bio_flags,
- unsigned long bio_flags)
+ unsigned long bio_flags,
+ bool force_bio_submit)
{
int ret = 0;
struct bio *bio;
- int nr;
int contig = 0;
- int this_compressed = bio_flags & EXTENT_BIO_COMPRESSED;
int old_compressed = prev_bio_flags & EXTENT_BIO_COMPRESSED;
size_t page_size = min_t(size_t, size, PAGE_CACHE_SIZE);
contig = bio_end_sector(bio) == sector;
if (prev_bio_flags != bio_flags || !contig ||
+ force_bio_submit ||
merge_bio(rw, tree, page, offset, page_size, bio, bio_flags) ||
bio_add_page(bio, page, page_size, offset) < page_size) {
ret = submit_one_bio(rw, bio, mirror_num,
return 0;
}
}
- if (this_compressed)
- nr = BIO_MAX_PAGES;
- else
- nr = bio_get_nr_vecs(bdev);
- bio = btrfs_bio_alloc(bdev, sector, nr, GFP_NOFS | __GFP_HIGH);
+ bio = btrfs_bio_alloc(bdev, sector, BIO_MAX_PAGES,
+ GFP_NOFS | __GFP_HIGH);
if (!bio)
return -ENOMEM;
get_extent_t *get_extent,
struct extent_map **em_cached,
struct bio **bio, int mirror_num,
- unsigned long *bio_flags, int rw)
+ unsigned long *bio_flags, int rw,
+ u64 *prev_em_start)
{
struct inode *inode = page->mapping->host;
u64 start = page_offset(page);
}
while (cur <= end) {
unsigned long pnr = (last_byte >> PAGE_CACHE_SHIFT) + 1;
+ bool force_bio_submit = false;
if (cur >= last_byte) {
char *userpage;
block_start = em->block_start;
if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
block_start = EXTENT_MAP_HOLE;
+
+ /*
+ * If we have a file range that points to a compressed extent
+ * and it's followed by a consecutive file range that points to
+ * to the same compressed extent (possibly with a different
+ * offset and/or length, so it either points to the whole extent
+ * or only part of it), we must make sure we do not submit a
+ * single bio to populate the pages for the 2 ranges because
+ * this makes the compressed extent read zero out the pages
+ * belonging to the 2nd range. Imagine the following scenario:
+ *
+ * File layout
+ * [0 - 8K] [8K - 24K]
+ * | |
+ * | |
+ * points to extent X, points to extent X,
+ * offset 4K, length of 8K offset 0, length 16K
+ *
+ * [extent X, compressed length = 4K uncompressed length = 16K]
+ *
+ * If the bio to read the compressed extent covers both ranges,
+ * it will decompress extent X into the pages belonging to the
+ * first range and then it will stop, zeroing out the remaining
+ * pages that belong to the other range that points to extent X.
+ * So here we make sure we submit 2 bios, one for the first
+ * range and another one for the third range. Both will target
+ * the same physical extent from disk, but we can't currently
+ * make the compressed bio endio callback populate the pages
+ * for both ranges because each compressed bio is tightly
+ * coupled with a single extent map, and each range can have
+ * an extent map with a different offset value relative to the
+ * uncompressed data of our extent and different lengths. This
+ * is a corner case so we prioritize correctness over
+ * non-optimal behavior (submitting 2 bios for the same extent).
+ */
+ if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) &&
+ prev_em_start && *prev_em_start != (u64)-1 &&
+ *prev_em_start != em->orig_start)
+ force_bio_submit = true;
+
+ if (prev_em_start)
+ *prev_em_start = em->orig_start;
+
free_extent_map(em);
em = NULL;
bdev, bio, pnr,
end_bio_extent_readpage, mirror_num,
*bio_flags,
- this_bio_flag);
+ this_bio_flag,
+ force_bio_submit);
if (!ret) {
nr++;
*bio_flags = this_bio_flag;
struct inode *inode;
struct btrfs_ordered_extent *ordered;
int index;
+ u64 prev_em_start = (u64)-1;
inode = pages[0]->mapping->host;
while (1) {
for (index = 0; index < nr_pages; index++) {
__do_readpage(tree, pages[index], get_extent, em_cached, bio,
- mirror_num, bio_flags, rw);
+ mirror_num, bio_flags, rw, &prev_em_start);
page_cache_release(pages[index]);
}
}
}
ret = __do_readpage(tree, page, get_extent, NULL, bio, mirror_num,
- bio_flags, rw);
+ bio_flags, rw, NULL);
return ret;
}
int ret;
ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num,
- &bio_flags, READ);
+ &bio_flags, READ, NULL);
if (bio)
ret = submit_one_bio(READ, bio, mirror_num, bio_flags);
return ret;
sector, iosize, pg_offset,
bdev, &epd->bio, max_nr,
end_bio_extent_writepage,
- 0, 0, 0);
+ 0, 0, 0, false);
if (ret)
SetPageError(page);
}
}
}
-static void end_bio_extent_buffer_writepage(struct bio *bio, int err)
+static void end_bio_extent_buffer_writepage(struct bio *bio)
{
struct bio_vec *bvec;
struct extent_buffer *eb;
BUG_ON(!eb);
done = atomic_dec_and_test(&eb->io_pages);
- if (err || test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) {
+ if (bio->bi_error ||
+ test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) {
ClearPageUptodate(page);
set_btree_ioerr(page);
}
ret = submit_extent_page(rw, tree, wbc, p, offset >> 9,
PAGE_CACHE_SIZE, 0, bdev, &epd->bio,
-1, end_bio_extent_buffer_writepage,
- 0, epd->bio_flags, bio_flags);
+ 0, epd->bio_flags, bio_flags, false);
epd->bio_flags = bio_flags;
if (ret) {
set_btree_ioerr(p);
int ret;
ret = btrfs_map_bio(root, rw, bio, mirror_num, 1);
- if (ret)
- bio_endio(bio, ret);
+ if (ret) {
+ bio->bi_error = ret;
+ bio_endio(bio);
+ }
return ret;
}
ret = btrfs_map_bio(root, rw, bio, mirror_num, 0);
out:
- if (ret < 0)
- bio_endio(bio, ret);
+ if (ret < 0) {
+ bio->bi_error = ret;
+ bio_endio(bio);
+ }
return ret;
}
goto no_delete;
}
/* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */
- btrfs_wait_ordered_range(inode, 0, (u64)-1);
+ if (!special_file(inode->i_mode))
+ btrfs_wait_ordered_range(inode, 0, (u64)-1);
btrfs_free_io_failure_record(inode, 0, (u64)-1);
return em;
}
+ struct btrfs_dio_data {
+ u64 outstanding_extents;
+ u64 reserve;
+ };
static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
struct extent_map *em;
struct btrfs_root *root = BTRFS_I(inode)->root;
struct extent_state *cached_state = NULL;
+ struct btrfs_dio_data *dio_data = NULL;
u64 start = iblock << inode->i_blkbits;
u64 lockstart, lockend;
u64 len = bh_result->b_size;
- u64 *outstanding_extents = NULL;
int unlock_bits = EXTENT_LOCKED;
int ret = 0;
* that anything that needs to check if there's a transction doesn't get
* confused.
*/
- outstanding_extents = current->journal_info;
+ dio_data = current->journal_info;
current->journal_info = NULL;
}
* within our reservation, otherwise we need to adjust our inode
* counter appropriately.
*/
- if (*outstanding_extents) {
- (*outstanding_extents)--;
+ if (dio_data->outstanding_extents) {
+ (dio_data->outstanding_extents)--;
} else {
spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->outstanding_extents++;
spin_unlock(&BTRFS_I(inode)->lock);
}
- current->journal_info = outstanding_extents;
btrfs_free_reserved_data_space(inode, len);
- set_bit(BTRFS_INODE_DIO_READY, &BTRFS_I(inode)->runtime_flags);
+ WARN_ON(dio_data->reserve < len);
+ dio_data->reserve -= len;
+ current->journal_info = dio_data;
}
/*
unlock_err:
clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
unlock_bits, 1, 0, &cached_state, GFP_NOFS);
- if (outstanding_extents)
- current->journal_info = outstanding_extents;
+ if (dio_data)
+ current->journal_info = dio_data;
return ret;
}
int uptodate;
};
-static void btrfs_retry_endio_nocsum(struct bio *bio, int err)
+static void btrfs_retry_endio_nocsum(struct bio *bio)
{
struct btrfs_retry_complete *done = bio->bi_private;
struct bio_vec *bvec;
int i;
- if (err)
+ if (bio->bi_error)
goto end;
done->uptodate = 1;
return 0;
}
-static void btrfs_retry_endio(struct bio *bio, int 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);
int ret;
int i;
- if (err)
+ if (bio->bi_error)
goto end;
uptodate = 1;
}
}
-static void btrfs_endio_direct_read(struct bio *bio, int err)
+static void btrfs_endio_direct_read(struct bio *bio)
{
struct btrfs_dio_private *dip = bio->bi_private;
struct inode *inode = dip->inode;
struct bio *dio_bio;
struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
+ int err = bio->bi_error;
if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED)
err = btrfs_subio_endio_read(inode, io_bio, err);
kfree(dip);
- /* If we had a csum failure make sure to clear the uptodate flag */
- if (err)
- clear_bit(BIO_UPTODATE, &dio_bio->bi_flags);
- dio_end_io(dio_bio, err);
+ dio_end_io(dio_bio, bio->bi_error);
if (io_bio->end_io)
io_bio->end_io(io_bio, err);
bio_put(bio);
}
-static void btrfs_endio_direct_write(struct bio *bio, int err)
+static void btrfs_endio_direct_write(struct bio *bio)
{
struct btrfs_dio_private *dip = bio->bi_private;
struct inode *inode = dip->inode;
again:
ret = btrfs_dec_test_first_ordered_pending(inode, &ordered,
&ordered_offset,
- ordered_bytes, !err);
+ ordered_bytes,
+ !bio->bi_error);
if (!ret)
goto out_test;
kfree(dip);
- /* If we had an error make sure to clear the uptodate flag */
- if (err)
- clear_bit(BIO_UPTODATE, &dio_bio->bi_flags);
- dio_end_io(dio_bio, err);
+ dio_end_io(dio_bio, bio->bi_error);
bio_put(bio);
}
return 0;
}
-static void btrfs_end_dio_bio(struct bio *bio, int err)
+static void btrfs_end_dio_bio(struct bio *bio)
{
struct btrfs_dio_private *dip = bio->bi_private;
+ int err = bio->bi_error;
if (err)
btrfs_warn(BTRFS_I(dip->inode)->root->fs_info,
if (dip->errors) {
bio_io_error(dip->orig_bio);
} else {
- set_bit(BIO_UPTODATE, &dip->dio_bio->bi_flags);
- bio_endio(dip->orig_bio, 0);
+ dip->dio_bio->bi_error = 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)
{
- int nr_vecs = bio_get_nr_vecs(bdev);
struct bio *bio;
- bio = btrfs_bio_alloc(bdev, first_sector, nr_vecs, gfp_flags);
+ bio = btrfs_bio_alloc(bdev, first_sector, BIO_MAX_PAGES, gfp_flags);
if (bio)
bio_associate_current(bio);
return bio;
* callbacks - they require an allocated dip and a clone of dio_bio.
*/
if (io_bio && dip) {
- bio_endio(io_bio, ret);
+ io_bio->bi_error = -EIO;
+ bio_endio(io_bio);
/*
* The end io callbacks free our dip, do the final put on io_bio
* and all the cleanup and final put for dio_bio (through
unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
file_offset + dio_bio->bi_iter.bi_size - 1);
}
- clear_bit(BIO_UPTODATE, &dio_bio->bi_flags);
+ dio_bio->bi_error = -EIO;
/*
* Releases and cleans up our dio_bio, no need to bio_put()
* nor bio_endio()/bio_io_error() against dio_bio.
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
- u64 outstanding_extents = 0;
+ struct btrfs_root *root = BTRFS_I(inode)->root;
+ struct btrfs_dio_data dio_data = { 0 };
size_t count = 0;
int flags = 0;
bool wakeup = true;
ret = btrfs_delalloc_reserve_space(inode, count);
if (ret)
goto out;
- outstanding_extents = div64_u64(count +
+ dio_data.outstanding_extents = div64_u64(count +
BTRFS_MAX_EXTENT_SIZE - 1,
BTRFS_MAX_EXTENT_SIZE);
* do the accounting properly if we go over the number we
* originally calculated. Abuse current->journal_info for this.
*/
- current->journal_info = &outstanding_extents;
+ dio_data.reserve = round_up(count, root->sectorsize);
+ current->journal_info = &dio_data;
} else if (test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
&BTRFS_I(inode)->runtime_flags)) {
inode_dio_end(inode);
if (iov_iter_rw(iter) == WRITE) {
current->journal_info = NULL;
if (ret < 0 && ret != -EIOCBQUEUED) {
- /*
- * If the error comes from submitting stage,
- * btrfs_get_blocsk_direct() has free'd data space,
- * and metadata space will be handled by
- * finish_ordered_fn, don't do that again to make
- * sure bytes_may_use is correct.
- */
- if (!test_and_clear_bit(BTRFS_INODE_DIO_READY,
- &BTRFS_I(inode)->runtime_flags))
- btrfs_delalloc_release_space(inode, count);
+ if (dio_data.reserve)
+ btrfs_delalloc_release_space(inode,
+ dio_data.reserve);
} else if (ret >= 0 && (size_t)ret < count)
btrfs_delalloc_release_space(inode,
count - (size_t)ret);
* groups on disk until we're mounted read-write again
* unless we clean them up here.
*/
- mutex_lock(&root->fs_info->cleaner_mutex);
btrfs_delete_unused_bgs(fs_info);
- mutex_unlock(&root->fs_info->cleaner_mutex);
btrfs_dev_replace_suspend_for_unmount(fs_info);
btrfs_scrub_cancel(fs_info);
static void btrfs_interface_exit(void)
{
- if (misc_deregister(&btrfs_misc) < 0)
- printk(KERN_INFO "BTRFS: misc_deregister failed for control device\n");
+ misc_deregister(&btrfs_misc);
}
static void btrfs_print_info(void)
btrfs_unpin_free_ino(root);
clear_btree_io_tree(&root->dirty_log_pages);
}
+
+ /* We can free old roots now. */
+ spin_lock(&trans->dropped_roots_lock);
+ while (!list_empty(&trans->dropped_roots)) {
+ root = list_first_entry(&trans->dropped_roots,
+ struct btrfs_root, root_list);
+ list_del_init(&root->root_list);
+ spin_unlock(&trans->dropped_roots_lock);
+ btrfs_drop_and_free_fs_root(fs_info, root);
+ spin_lock(&trans->dropped_roots_lock);
+ }
+ spin_unlock(&trans->dropped_roots_lock);
up_write(&fs_info->commit_root_sem);
}
INIT_LIST_HEAD(&cur_trans->pending_ordered);
INIT_LIST_HEAD(&cur_trans->dirty_bgs);
INIT_LIST_HEAD(&cur_trans->io_bgs);
+ INIT_LIST_HEAD(&cur_trans->dropped_roots);
mutex_init(&cur_trans->cache_write_mutex);
cur_trans->num_dirty_bgs = 0;
spin_lock_init(&cur_trans->dirty_bgs_lock);
INIT_LIST_HEAD(&cur_trans->deleted_bgs);
spin_lock_init(&cur_trans->deleted_bgs_lock);
+ spin_lock_init(&cur_trans->dropped_roots_lock);
list_add_tail(&cur_trans->list, &fs_info->trans_list);
extent_io_tree_init(&cur_trans->dirty_pages,
fs_info->btree_inode->i_mapping);
}
+ void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root)
+ {
+ struct btrfs_transaction *cur_trans = trans->transaction;
+
+ /* Add ourselves to the transaction dropped list */
+ spin_lock(&cur_trans->dropped_roots_lock);
+ list_add_tail(&root->root_list, &cur_trans->dropped_roots);
+ spin_unlock(&cur_trans->dropped_roots_lock);
+
+ /* Make sure we don't try to update the root at commit time */
+ spin_lock(&root->fs_info->fs_roots_radix_lock);
+ radix_tree_tag_clear(&root->fs_info->fs_roots_radix,
+ (unsigned long)root->root_key.objectid,
+ BTRFS_ROOT_TRANS_TAG);
+ spin_unlock(&root->fs_info->fs_roots_radix_lock);
+ }
+
int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
* Tell lockdep about it.
*/
if (ac->newtrans->type & __TRANS_FREEZABLE)
- rwsem_acquire_read(
- &ac->root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1],
- 0, 1, _THIS_IP_);
+ __sb_writers_acquired(ac->root->fs_info->sb, SB_FREEZE_FS);
current->journal_info = ac->newtrans;
* async commit thread will be the one to unlock it.
*/
if (ac->newtrans->type & __TRANS_FREEZABLE)
- rwsem_release(
- &root->fs_info->sb->s_writers.lock_map[SB_FREEZE_FS-1],
- 1, _THIS_IP_);
+ __sb_writers_release(root->fs_info->sb, SB_FREEZE_FS);
schedule_work(&ac->work);