aboutsummaryrefslogtreecommitdiff
path: root/fs/btrfs/inode.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/inode.c')
-rw-r--r--fs/btrfs/inode.c176
1 files changed, 133 insertions, 43 deletions
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 16d9e8e191e6..4b5398c9f62b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -88,7 +88,7 @@ static unsigned char btrfs_type_by_mode[S_IFMT >> S_SHIFT] = {
[S_IFLNK >> S_SHIFT] = BTRFS_FT_SYMLINK,
};
-static int btrfs_setsize(struct inode *inode, loff_t newsize);
+static int btrfs_setsize(struct inode *inode, struct iattr *attr);
static int btrfs_truncate(struct inode *inode);
static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent);
static noinline int cow_file_range(struct inode *inode,
@@ -265,6 +265,7 @@ static noinline int cow_file_range_inline(struct btrfs_trans_handle *trans,
return 1;
}
+ set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags);
btrfs_delalloc_release_metadata(inode, end + 1 - start);
btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0);
return 0;
@@ -351,6 +352,7 @@ static noinline int compress_file_range(struct inode *inode,
int i;
int will_compress;
int compress_type = root->fs_info->compress_type;
+ int redirty = 0;
/* if this is a small write inside eof, kick off a defrag */
if ((end - start + 1) < 16 * 1024 &&
@@ -413,6 +415,17 @@ again:
if (BTRFS_I(inode)->force_compress)
compress_type = BTRFS_I(inode)->force_compress;
+ /*
+ * we need to call clear_page_dirty_for_io on each
+ * page in the range. Otherwise applications with the file
+ * mmap'd can wander in and change the page contents while
+ * we are compressing them.
+ *
+ * If the compression fails for any reason, we set the pages
+ * dirty again later on.
+ */
+ extent_range_clear_dirty_for_io(inode, start, end);
+ redirty = 1;
ret = btrfs_compress_pages(compress_type,
inode->i_mapping, start,
total_compressed, pages,
@@ -554,6 +567,8 @@ cleanup_and_bail_uncompressed:
__set_page_dirty_nobuffers(locked_page);
/* unlocked later on in the async handlers */
}
+ if (redirty)
+ extent_range_redirty_for_io(inode, start, end);
add_async_extent(async_cow, start, end - start + 1,
0, NULL, 0, BTRFS_COMPRESS_NONE);
*num_added += 1;
@@ -2469,6 +2484,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
*/
set_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
&BTRFS_I(inode)->runtime_flags);
+ atomic_inc(&root->orphan_inodes);
/* if we have links, this was a truncate, lets do that */
if (inode->i_nlink) {
@@ -2478,7 +2494,21 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
continue;
}
nr_truncate++;
+
+ /* 1 for the orphan item deletion. */
+ trans = btrfs_start_transaction(root, 1);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out;
+ }
+ ret = btrfs_orphan_add(trans, inode);
+ btrfs_end_transaction(trans, root);
+ if (ret)
+ goto out;
+
ret = btrfs_truncate(inode);
+ if (ret)
+ btrfs_orphan_del(NULL, inode);
} else {
nr_unlink++;
}
@@ -3665,6 +3695,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
block_end - cur_offset, 0);
if (IS_ERR(em)) {
err = PTR_ERR(em);
+ em = NULL;
break;
}
last_byte = min(extent_map_end(em), block_end);
@@ -3748,16 +3779,27 @@ next:
return err;
}
-static int btrfs_setsize(struct inode *inode, loff_t newsize)
+static int btrfs_setsize(struct inode *inode, struct iattr *attr)
{
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
loff_t oldsize = i_size_read(inode);
+ loff_t newsize = attr->ia_size;
+ int mask = attr->ia_valid;
int ret;
if (newsize == oldsize)
return 0;
+ /*
+ * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
+ * special case where we need to update the times despite not having
+ * these flags set. For all other operations the VFS set these flags
+ * explicitly if it wants a timestamp update.
+ */
+ if (newsize != oldsize && (!(mask & (ATTR_CTIME | ATTR_MTIME))))
+ inode->i_ctime = inode->i_mtime = current_fs_time(inode->i_sb);
+
if (newsize > oldsize) {
truncate_pagecache(inode, oldsize, newsize);
ret = btrfs_cont_expand(inode, oldsize, newsize);
@@ -3783,9 +3825,34 @@ static int btrfs_setsize(struct inode *inode, loff_t newsize)
set_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
&BTRFS_I(inode)->runtime_flags);
+ /*
+ * 1 for the orphan item we're going to add
+ * 1 for the orphan item deletion.
+ */
+ trans = btrfs_start_transaction(root, 2);
+ if (IS_ERR(trans))
+ return PTR_ERR(trans);
+
+ /*
+ * We need to do this in case we fail at _any_ point during the
+ * actual truncate. Once we do the truncate_setsize we could
+ * invalidate pages which forces any outstanding ordered io to
+ * be instantly completed which will give us extents that need
+ * to be truncated. If we fail to get an orphan inode down we
+ * could have left over extents that were never meant to live,
+ * so we need to garuntee from this point on that everything
+ * will be consistent.
+ */
+ ret = btrfs_orphan_add(trans, inode);
+ btrfs_end_transaction(trans, root);
+ if (ret)
+ return ret;
+
/* we don't support swapfiles, so vmtruncate shouldn't fail */
truncate_setsize(inode, newsize);
ret = btrfs_truncate(inode);
+ if (ret && inode->i_nlink)
+ btrfs_orphan_del(NULL, inode);
}
return ret;
@@ -3805,7 +3872,7 @@ static int btrfs_setattr(struct dentry *dentry, struct iattr *attr)
return err;
if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
- err = btrfs_setsize(inode, attr->ia_size);
+ err = btrfs_setsize(inode, attr);
if (err)
return err;
}
@@ -5572,10 +5639,13 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag
return em;
if (em) {
/*
- * if our em maps to a hole, there might
- * actually be delalloc bytes behind it
+ * 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)
+ if (em->block_start != EXTENT_MAP_HOLE &&
+ !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
return em;
else
hole_em = em;
@@ -5657,6 +5727,8 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag
*/
em->block_start = hole_em->block_start;
em->block_len = hole_len;
+ if (test_bit(EXTENT_FLAG_PREALLOC, &hole_em->flags))
+ set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
} else {
em->start = range_start;
em->len = found;
@@ -5722,7 +5794,9 @@ out:
* block must be cow'd
*/
static noinline int can_nocow_odirect(struct btrfs_trans_handle *trans,
- struct inode *inode, u64 offset, u64 len)
+ struct inode *inode, u64 offset, u64 *len,
+ u64 *orig_start, u64 *orig_block_len,
+ u64 *ram_bytes)
{
struct btrfs_path *path;
int ret;
@@ -5779,8 +5853,12 @@ static noinline int can_nocow_odirect(struct btrfs_trans_handle *trans,
disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
backref_offset = btrfs_file_extent_offset(leaf, fi);
+ *orig_start = key.offset - backref_offset;
+ *orig_block_len = btrfs_file_extent_disk_num_bytes(leaf, fi);
+ *ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi);
+
extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, fi);
- if (extent_end < offset + len) {
+ if (extent_end < offset + *len) {
/* extent doesn't include our full range, must cow */
goto out;
}
@@ -5804,13 +5882,14 @@ static noinline int can_nocow_odirect(struct btrfs_trans_handle *trans,
*/
disk_bytenr += backref_offset;
disk_bytenr += offset - key.offset;
- num_bytes = min(offset + len, extent_end) - offset;
+ num_bytes = min(offset + *len, extent_end) - offset;
if (csum_exist_in_range(root, disk_bytenr, num_bytes))
goto out;
/*
* all of the above have passed, it is safe to overwrite this extent
* without cow
*/
+ *len = num_bytes;
ret = 1;
out:
btrfs_free_path(path);
@@ -6020,7 +6099,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
em->block_start != EXTENT_MAP_HOLE)) {
int type;
int ret;
- u64 block_start;
+ u64 block_start, orig_start, orig_block_len, ram_bytes;
if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
type = BTRFS_ORDERED_PREALLOC;
@@ -6038,10 +6117,8 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
if (IS_ERR(trans))
goto must_cow;
- if (can_nocow_odirect(trans, inode, start, len) == 1) {
- u64 orig_start = em->orig_start;
- u64 orig_block_len = em->orig_block_len;
-
+ if (can_nocow_odirect(trans, inode, start, &len, &orig_start,
+ &orig_block_len, &ram_bytes) == 1) {
if (type == BTRFS_ORDERED_PREALLOC) {
free_extent_map(em);
em = create_pinned_em(inode, start, len,
@@ -6915,11 +6992,9 @@ static int btrfs_truncate(struct inode *inode)
/*
* 1 for the truncate slack space
- * 1 for the orphan item we're going to add
- * 1 for the orphan item deletion
* 1 for updating the inode.
*/
- trans = btrfs_start_transaction(root, 4);
+ trans = btrfs_start_transaction(root, 2);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
goto out;
@@ -6930,12 +7005,6 @@ static int btrfs_truncate(struct inode *inode)
min_size);
BUG_ON(ret);
- ret = btrfs_orphan_add(trans, inode);
- if (ret) {
- btrfs_end_transaction(trans, root);
- goto out;
- }
-
/*
* setattr is responsible for setting the ordered_data_close flag,
* but that is only tested during the last file release. That
@@ -7004,12 +7073,6 @@ static int btrfs_truncate(struct inode *inode)
ret = btrfs_orphan_del(trans, inode);
if (ret)
err = ret;
- } else if (ret && inode->i_nlink > 0) {
- /*
- * Failed to do the truncate, remove us from the in memory
- * orphan list.
- */
- ret = btrfs_orphan_del(NULL, inode);
}
if (trans) {
@@ -7531,41 +7594,61 @@ void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work)
*/
int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
{
- struct list_head *head = &root->fs_info->delalloc_inodes;
struct btrfs_inode *binode;
struct inode *inode;
struct btrfs_delalloc_work *work, *next;
struct list_head works;
+ struct list_head splice;
int ret = 0;
if (root->fs_info->sb->s_flags & MS_RDONLY)
return -EROFS;
INIT_LIST_HEAD(&works);
-
+ INIT_LIST_HEAD(&splice);
+again:
spin_lock(&root->fs_info->delalloc_lock);
- while (!list_empty(head)) {
- binode = list_entry(head->next, struct btrfs_inode,
+ list_splice_init(&root->fs_info->delalloc_inodes, &splice);
+ while (!list_empty(&splice)) {
+ binode = list_entry(splice.next, struct btrfs_inode,
delalloc_inodes);
+
+ list_del_init(&binode->delalloc_inodes);
+
inode = igrab(&binode->vfs_inode);
if (!inode)
- list_del_init(&binode->delalloc_inodes);
+ continue;
+
+ list_add_tail(&binode->delalloc_inodes,
+ &root->fs_info->delalloc_inodes);
spin_unlock(&root->fs_info->delalloc_lock);
- if (inode) {
- work = btrfs_alloc_delalloc_work(inode, 0, delay_iput);
- if (!work) {
- ret = -ENOMEM;
- goto out;
- }
- list_add_tail(&work->list, &works);
- btrfs_queue_worker(&root->fs_info->flush_workers,
- &work->work);
+
+ work = btrfs_alloc_delalloc_work(inode, 0, delay_iput);
+ if (unlikely(!work)) {
+ ret = -ENOMEM;
+ goto out;
}
+ list_add_tail(&work->list, &works);
+ btrfs_queue_worker(&root->fs_info->flush_workers,
+ &work->work);
+
cond_resched();
spin_lock(&root->fs_info->delalloc_lock);
}
spin_unlock(&root->fs_info->delalloc_lock);
+ list_for_each_entry_safe(work, next, &works, list) {
+ list_del_init(&work->list);
+ btrfs_wait_and_free_delalloc_work(work);
+ }
+
+ spin_lock(&root->fs_info->delalloc_lock);
+ if (!list_empty(&root->fs_info->delalloc_inodes)) {
+ spin_unlock(&root->fs_info->delalloc_lock);
+ goto again;
+ }
+ spin_unlock(&root->fs_info->delalloc_lock);
+
/* the filemap_flush will queue IO into the worker threads, but
* we have to make sure the IO is actually started and that
* ordered extents get created before we return
@@ -7578,11 +7661,18 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput)
atomic_read(&root->fs_info->async_delalloc_pages) == 0));
}
atomic_dec(&root->fs_info->async_submit_draining);
+ return 0;
out:
list_for_each_entry_safe(work, next, &works, list) {
list_del_init(&work->list);
btrfs_wait_and_free_delalloc_work(work);
}
+
+ if (!list_empty_careful(&splice)) {
+ spin_lock(&root->fs_info->delalloc_lock);
+ list_splice_tail(&splice, &root->fs_info->delalloc_inodes);
+ spin_unlock(&root->fs_info->delalloc_lock);
+ }
return ret;
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-13 14:26:04 +0000