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.c400
1 files changed, 237 insertions, 163 deletions
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 94b0df3fb3c8..67b49b94c9cd 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -49,6 +49,7 @@
#include "qgroup.h"
#include "delalloc-space.h"
#include "block-group.h"
+#include "space-info.h"
struct btrfs_iget_args {
struct btrfs_key *location;
@@ -640,12 +641,18 @@ cont:
page_error_op |
PAGE_END_WRITEBACK);
- for (i = 0; i < nr_pages; i++) {
- WARN_ON(pages[i]->mapping);
- put_page(pages[i]);
+ /*
+ * Ensure we only free the compressed pages if we have
+ * them allocated, as we can still reach here with
+ * inode_need_compress() == false.
+ */
+ if (pages) {
+ for (i = 0; i < nr_pages; i++) {
+ WARN_ON(pages[i]->mapping);
+ put_page(pages[i]);
+ }
+ kfree(pages);
}
- kfree(pages);
-
return 0;
}
}
@@ -974,6 +981,7 @@ static noinline int cow_file_range(struct inode *inode,
u64 num_bytes;
unsigned long ram_size;
u64 cur_alloc_size = 0;
+ u64 min_alloc_size;
u64 blocksize = fs_info->sectorsize;
struct btrfs_key ins;
struct extent_map *em;
@@ -1024,10 +1032,26 @@ static noinline int cow_file_range(struct inode *inode,
btrfs_drop_extent_cache(BTRFS_I(inode), start,
start + num_bytes - 1, 0);
+ /*
+ * Relocation relies on the relocated extents to have exactly the same
+ * size as the original extents. Normally writeback for relocation data
+ * extents follows a NOCOW path because relocation preallocates the
+ * extents. However, due to an operation such as scrub turning a block
+ * group to RO mode, it may fallback to COW mode, so we must make sure
+ * an extent allocated during COW has exactly the requested size and can
+ * not be split into smaller extents, otherwise relocation breaks and
+ * fails during the stage where it updates the bytenr of file extent
+ * items.
+ */
+ if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID)
+ min_alloc_size = num_bytes;
+ else
+ min_alloc_size = fs_info->sectorsize;
+
while (num_bytes > 0) {
cur_alloc_size = num_bytes;
ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
- fs_info->sectorsize, 0, alloc_hint,
+ min_alloc_size, 0, alloc_hint,
&ins, 1, 1);
if (ret < 0)
goto out_unlock;
@@ -1132,7 +1156,7 @@ out_unlock:
*/
if (extent_reserved) {
extent_clear_unlock_delalloc(inode, start,
- start + cur_alloc_size,
+ start + cur_alloc_size - 1,
locked_page,
clear_bits,
page_ops);
@@ -1322,6 +1346,73 @@ static noinline int csum_exist_in_range(struct btrfs_fs_info *fs_info,
return 1;
}
+static int fallback_to_cow(struct inode *inode, struct page *locked_page,
+ const u64 start, const u64 end,
+ int *page_started, unsigned long *nr_written)
+{
+ const bool is_space_ino = btrfs_is_free_space_inode(BTRFS_I(inode));
+ const bool is_reloc_ino = (BTRFS_I(inode)->root->root_key.objectid ==
+ BTRFS_DATA_RELOC_TREE_OBJECTID);
+ const u64 range_bytes = end + 1 - start;
+ struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+ u64 range_start = start;
+ u64 count;
+
+ /*
+ * If EXTENT_NORESERVE is set it means that when the buffered write was
+ * made we had not enough available data space and therefore we did not
+ * reserve data space for it, since we though we could do NOCOW for the
+ * respective file range (either there is prealloc extent or the inode
+ * has the NOCOW bit set).
+ *
+ * However when we need to fallback to COW mode (because for example the
+ * block group for the corresponding extent was turned to RO mode by a
+ * scrub or relocation) we need to do the following:
+ *
+ * 1) We increment the bytes_may_use counter of the data space info.
+ * If COW succeeds, it allocates a new data extent and after doing
+ * that it decrements the space info's bytes_may_use counter and
+ * increments its bytes_reserved counter by the same amount (we do
+ * this at btrfs_add_reserved_bytes()). So we need to increment the
+ * bytes_may_use counter to compensate (when space is reserved at
+ * buffered write time, the bytes_may_use counter is incremented);
+ *
+ * 2) We clear the EXTENT_NORESERVE bit from the range. We do this so
+ * that if the COW path fails for any reason, it decrements (through
+ * extent_clear_unlock_delalloc()) the bytes_may_use counter of the
+ * data space info, which we incremented in the step above.
+ *
+ * If we need to fallback to cow and the inode corresponds to a free
+ * space cache inode or an inode of the data relocation tree, we must
+ * also increment bytes_may_use of the data space_info for the same
+ * reason. Space caches and relocated data extents always get a prealloc
+ * extent for them, however scrub or balance may have set the block
+ * group that contains that extent to RO mode and therefore force COW
+ * when starting writeback.
+ */
+ count = count_range_bits(io_tree, &range_start, end, range_bytes,
+ EXTENT_NORESERVE, 0);
+ if (count > 0 || is_space_ino || is_reloc_ino) {
+ u64 bytes = count;
+ struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+ struct btrfs_space_info *sinfo = fs_info->data_sinfo;
+
+ if (is_space_ino || is_reloc_ino)
+ bytes = range_bytes;
+
+ spin_lock(&sinfo->lock);
+ btrfs_space_info_update_bytes_may_use(fs_info, sinfo, bytes);
+ spin_unlock(&sinfo->lock);
+
+ if (count > 0)
+ clear_extent_bit(io_tree, start, end, EXTENT_NORESERVE,
+ 0, 0, NULL);
+ }
+
+ return cow_file_range(inode, locked_page, start, end, page_started,
+ nr_written, 1);
+}
+
/*
* when nowcow writeback call back. This checks for snapshots or COW copies
* of the extents that exist in the file, and COWs the file as required.
@@ -1487,7 +1578,7 @@ next_slot:
goto out_check;
ret = btrfs_cross_ref_exist(root, ino,
found_key.offset -
- extent_offset, disk_bytenr);
+ extent_offset, disk_bytenr, false);
if (ret) {
/*
* ret could be -EIO if the above fails to read
@@ -1569,15 +1660,11 @@ out_check:
* NOCOW, following one which needs to be COW'ed
*/
if (cow_start != (u64)-1) {
- ret = cow_file_range(inode, locked_page,
- cow_start, found_key.offset - 1,
- page_started, nr_written, 1);
- if (ret) {
- if (nocow)
- btrfs_dec_nocow_writers(fs_info,
- disk_bytenr);
+ ret = fallback_to_cow(inode, locked_page, cow_start,
+ found_key.offset - 1,
+ page_started, nr_written);
+ if (ret)
goto error;
- }
cow_start = (u64)-1;
}
@@ -1593,9 +1680,6 @@ out_check:
ram_bytes, BTRFS_COMPRESS_NONE,
BTRFS_ORDERED_PREALLOC);
if (IS_ERR(em)) {
- if (nocow)
- btrfs_dec_nocow_writers(fs_info,
- disk_bytenr);
ret = PTR_ERR(em);
goto error;
}
@@ -1660,8 +1744,8 @@ out_check:
if (cow_start != (u64)-1) {
cur_offset = end;
- ret = cow_file_range(inode, locked_page, cow_start, end,
- page_started, nr_written, 1);
+ ret = fallback_to_cow(inode, locked_page, cow_start, end,
+ page_started, nr_written);
if (ret)
goto error;
}
@@ -4250,7 +4334,7 @@ static struct btrfs_trans_handle *__unlink_start_trans(struct inode *dir)
* 1 for the inode ref
* 1 for the inode
*/
- return btrfs_start_transaction_fallback_global_rsv(root, 5, 5);
+ return btrfs_start_transaction_fallback_global_rsv(root, 5);
}
static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
@@ -4603,6 +4687,8 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
}
}
+ free_anon_bdev(dest->anon_dev);
+ dest->anon_dev = 0;
out_end_trans:
trans->block_rsv = NULL;
trans->bytes_reserved = 0;
@@ -5047,11 +5133,13 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
struct extent_state *cached_state = NULL;
struct extent_changeset *data_reserved = NULL;
char *kaddr;
+ bool only_release_metadata = false;
u32 blocksize = fs_info->sectorsize;
pgoff_t index = from >> PAGE_SHIFT;
unsigned offset = from & (blocksize - 1);
struct page *page;
gfp_t mask = btrfs_alloc_write_mask(mapping);
+ size_t write_bytes = blocksize;
int ret = 0;
u64 block_start;
u64 block_end;
@@ -5063,11 +5151,27 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
block_start = round_down(from, blocksize);
block_end = block_start + blocksize - 1;
- ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
- block_start, blocksize);
- if (ret)
- goto out;
+ ret = btrfs_check_data_free_space(inode, &data_reserved, block_start,
+ blocksize);
+ if (ret < 0) {
+ if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+ BTRFS_INODE_PREALLOC)) &&
+ btrfs_check_can_nocow(BTRFS_I(inode), block_start,
+ &write_bytes) > 0) {
+ /* For nocow case, no need to reserve data space */
+ only_release_metadata = true;
+ } else {
+ goto out;
+ }
+ }
+ ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), blocksize);
+ if (ret < 0) {
+ if (!only_release_metadata)
+ btrfs_free_reserved_data_space(inode, data_reserved,
+ block_start, blocksize);
+ goto out;
+ }
again:
page = find_or_create_page(mapping, index, mask);
if (!page) {
@@ -5136,14 +5240,26 @@ again:
set_page_dirty(page);
unlock_extent_cached(io_tree, block_start, block_end, &cached_state);
+ if (only_release_metadata)
+ set_extent_bit(&BTRFS_I(inode)->io_tree, block_start,
+ block_end, EXTENT_NORESERVE, NULL, NULL,
+ GFP_NOFS);
+
out_unlock:
- if (ret)
- btrfs_delalloc_release_space(inode, data_reserved, block_start,
- blocksize, true);
+ if (ret) {
+ if (only_release_metadata)
+ btrfs_delalloc_release_metadata(BTRFS_I(inode),
+ blocksize, true);
+ else
+ btrfs_delalloc_release_space(inode, data_reserved,
+ block_start, blocksize, true);
+ }
btrfs_delalloc_release_extents(BTRFS_I(inode), blocksize);
unlock_page(page);
put_page(page);
out:
+ if (only_release_metadata)
+ btrfs_end_write_no_snapshotting(BTRFS_I(inode)->root);
extent_changeset_free(data_reserved);
return ret;
}
@@ -7108,7 +7224,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
/* Only regular file could have regular/prealloc extent */
if (!S_ISREG(inode->vfs_inode.i_mode)) {
- ret = -EUCLEAN;
+ err = -EUCLEAN;
btrfs_crit(fs_info,
"regular/prealloc extent found for non-regular inode %llu",
btrfs_ino(inode));
@@ -7443,7 +7559,7 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
*/
noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
u64 *orig_start, u64 *orig_block_len,
- u64 *ram_bytes)
+ u64 *ram_bytes, bool strict)
{
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
struct btrfs_path *path;
@@ -7521,8 +7637,9 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
* Do the same check as in btrfs_cross_ref_exist but without the
* unnecessary search.
*/
- if (btrfs_file_extent_generation(leaf, fi) <=
- btrfs_root_last_snapshot(&root->root_item))
+ if (!strict &&
+ (btrfs_file_extent_generation(leaf, fi) <=
+ btrfs_root_last_snapshot(&root->root_item)))
goto out;
backref_offset = btrfs_file_extent_offset(leaf, fi);
@@ -7558,7 +7675,8 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
*/
ret = btrfs_cross_ref_exist(root, btrfs_ino(BTRFS_I(inode)),
- key.offset - backref_offset, disk_bytenr);
+ key.offset - backref_offset, disk_bytenr,
+ strict);
if (ret) {
ret = 0;
goto out;
@@ -7779,7 +7897,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
block_start = em->block_start + (start - em->start);
if (can_nocow_extent(inode, start, &len, &orig_start,
- &orig_block_len, &ram_bytes) == 1 &&
+ &orig_block_len, &ram_bytes, false) == 1 &&
btrfs_inc_nocow_writers(fs_info, block_start)) {
struct extent_map *em2;
@@ -8498,14 +8616,64 @@ err:
return ret;
}
-static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
+/*
+ * If this succeeds, the btrfs_dio_private is responsible for cleaning up locked
+ * or ordered extents whether or not we submit any bios.
+ */
+static struct btrfs_dio_private *btrfs_create_dio_private(struct bio *dio_bio,
+ struct inode *inode,
+ loff_t file_offset)
{
- struct inode *inode = dip->inode;
+ const bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
+ struct btrfs_dio_private *dip;
+ struct bio *bio;
+
+ dip = kzalloc(sizeof(*dip), GFP_NOFS);
+ if (!dip)
+ return NULL;
+
+ bio = btrfs_bio_clone(dio_bio);
+ bio->bi_private = dip;
+ btrfs_io_bio(bio)->logical = file_offset;
+
+ dip->private = dio_bio->bi_private;
+ dip->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;
+ dip->orig_bio = bio;
+ dip->dio_bio = dio_bio;
+ atomic_set(&dip->pending_bios, 1);
+
+ if (write) {
+ struct btrfs_dio_data *dio_data = current->journal_info;
+
+ /*
+ * Setting range start and end to the same value means that
+ * no cleanup will happen in btrfs_direct_IO
+ */
+ dio_data->unsubmitted_oe_range_end = dip->logical_offset +
+ dip->bytes;
+ dio_data->unsubmitted_oe_range_start =
+ dio_data->unsubmitted_oe_range_end;
+
+ bio->bi_end_io = btrfs_endio_direct_write;
+ } else {
+ bio->bi_end_io = btrfs_endio_direct_read;
+ dip->subio_endio = btrfs_subio_endio_read;
+ }
+ return dip;
+}
+
+static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
+ loff_t file_offset)
+{
+ const bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+ struct btrfs_dio_private *dip;
struct bio *bio;
- struct bio *orig_bio = dip->orig_bio;
- u64 start_sector = orig_bio->bi_iter.bi_sector;
- u64 file_offset = dip->logical_offset;
+ struct bio *orig_bio;
+ u64 start_sector;
int async_submit = 0;
u64 submit_len;
int clone_offset = 0;
@@ -8514,11 +8682,24 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
blk_status_t status;
struct btrfs_io_geometry geom;
+ dip = btrfs_create_dio_private(dio_bio, inode, file_offset);
+ if (!dip) {
+ if (!write) {
+ unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
+ file_offset + dio_bio->bi_iter.bi_size - 1);
+ }
+ dio_bio->bi_status = BLK_STS_RESOURCE;
+ dio_end_io(dio_bio);
+ return;
+ }
+
+ orig_bio = dip->orig_bio;
+ start_sector = orig_bio->bi_iter.bi_sector;
submit_len = orig_bio->bi_iter.bi_size;
ret = btrfs_get_io_geometry(fs_info, btrfs_op(orig_bio),
start_sector << 9, submit_len, &geom);
if (ret)
- return -EIO;
+ goto out_err;
if (geom.len >= submit_len) {
bio = orig_bio;
@@ -8534,7 +8715,6 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
/* bio split */
ASSERT(geom.len <= INT_MAX);
- atomic_inc(&dip->pending_bios);
do {
clone_len = min_t(int, submit_len, geom.len);
@@ -8582,9 +8762,10 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip)
submit:
status = btrfs_submit_dio_bio(bio, inode, file_offset, async_submit);
if (!status)
- return 0;
+ return;
- bio_put(bio);
+ if (bio != orig_bio)
+ bio_put(bio);
out_err:
dip->errors = 1;
/*
@@ -8595,107 +8776,6 @@ out_err:
*/
if (atomic_dec_and_test(&dip->pending_bios))
bio_io_error(dip->orig_bio);
-
- /* bio_end_io() will handle error, so we needn't return it */
- return 0;
-}
-
-static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
- loff_t file_offset)
-{
- struct btrfs_dio_private *dip = NULL;
- struct bio *bio = NULL;
- struct btrfs_io_bio *io_bio;
- bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
- int ret = 0;
-
- bio = btrfs_bio_clone(dio_bio);
-
- dip = kzalloc(sizeof(*dip), GFP_NOFS);
- if (!dip) {
- ret = -ENOMEM;
- goto free_ordered;
- }
-
- dip->private = dio_bio->bi_private;
- dip->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;
- bio->bi_private = dip;
- dip->orig_bio = bio;
- dip->dio_bio = dio_bio;
- atomic_set(&dip->pending_bios, 0);
- io_bio = btrfs_io_bio(bio);
- io_bio->logical = file_offset;
-
- if (write) {
- bio->bi_end_io = btrfs_endio_direct_write;
- } else {
- bio->bi_end_io = btrfs_endio_direct_read;
- dip->subio_endio = btrfs_subio_endio_read;
- }
-
- /*
- * Reset the range for unsubmitted ordered extents (to a 0 length range)
- * even if we fail to submit a bio, because in such case we do the
- * corresponding error handling below and it must not be done a second
- * time by btrfs_direct_IO().
- */
- if (write) {
- struct btrfs_dio_data *dio_data = current->journal_info;
-
- dio_data->unsubmitted_oe_range_end = dip->logical_offset +
- dip->bytes;
- dio_data->unsubmitted_oe_range_start =
- dio_data->unsubmitted_oe_range_end;
- }
-
- ret = btrfs_submit_direct_hook(dip);
- if (!ret)
- return;
-
- btrfs_io_bio_free_csum(io_bio);
-
-free_ordered:
- /*
- * If we arrived here it means either we failed to submit the dip
- * or we either failed to clone the dio_bio or failed to allocate the
- * dip. If we cloned the dio_bio and allocated the dip, we can just
- * call bio_endio against our io_bio so that we get proper resource
- * cleanup if we fail to submit the dip, otherwise, we must do the
- * 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 (bio && dip) {
- bio_io_error(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;
- bio = NULL;
- } else {
- if (write)
- __endio_write_update_ordered(inode,
- file_offset,
- dio_bio->bi_iter.bi_size,
- false);
- else
- unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
- file_offset + dio_bio->bi_iter.bi_size - 1);
-
- 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);
- }
- if (bio)
- bio_put(bio);
- kfree(dip);
}
static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
@@ -8772,9 +8852,6 @@ 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, &data_reserved,
offset, count);
@@ -8997,20 +9074,17 @@ again:
/*
* Qgroup reserved space handler
* Page here will be either
- * 1) Already written to disk
- * In this case, its reserved space is released from data rsv map
- * and will be freed by delayed_ref handler finally.
- * So even we call qgroup_free_data(), it won't decrease reserved
- * space.
- * 2) Not written to disk
- * This means the reserved space should be freed here. However,
- * if a truncate invalidates the page (by clearing PageDirty)
- * and the page is accounted for while allocating extent
- * in btrfs_check_data_free_space() we let delayed_ref to
- * free the entire extent.
+ * 1) Already written to disk or ordered extent already submitted
+ * Then its QGROUP_RESERVED bit in io_tree is already cleaned.
+ * Qgroup will be handled by its qgroup_record then.
+ * btrfs_qgroup_free_data() call will do nothing here.
+ *
+ * 2) Not written to disk yet
+ * Then btrfs_qgroup_free_data() call will clear the QGROUP_RESERVED
+ * bit of its io_tree, and free the qgroup reserved data space.
+ * Since the IO will never happen for this page.
*/
- if (PageDirty(page))
- btrfs_qgroup_free_data(inode, NULL, 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_DELALLOC | EXTENT_DELALLOC_NEW |
@@ -9485,7 +9559,7 @@ void btrfs_destroy_inode(struct inode *inode)
btrfs_put_ordered_extent(ordered);
}
}
- btrfs_qgroup_check_reserved_leak(inode);
+ btrfs_qgroup_check_reserved_leak(BTRFS_I(inode));
inode_tree_del(inode);
btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0);
}
@@ -10947,7 +11021,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
free_extent_map(em);
em = NULL;
- ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL);
+ ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL, true);
if (ret < 0) {
goto out;
} else if (ret) {