#include <linux/slab.h>
#include <linux/ratelimit.h>
#include <linux/mount.h>
+#include <linux/btrfs.h>
#include "compat.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
-#include "ioctl.h"
#include "print-tree.h"
#include "ordered-data.h"
#include "xattr.h"
[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,
if (list_empty(&async_cow->extents))
return 0;
-
+again:
while (!list_empty(&async_cow->extents)) {
async_extent = list_entry(async_cow->extents.next,
struct async_extent, list);
async_extent->ram_size - 1,
btrfs_get_extent,
WB_SYNC_ALL);
+ else if (ret)
+ unlock_page(async_cow->locked_page);
kfree(async_extent);
cond_resched();
continue;
if (ret) {
int i;
+
for (i = 0; i < async_extent->nr_pages; i++) {
WARN_ON(async_extent->pages[i]->mapping);
page_cache_release(async_extent->pages[i]);
kfree(async_extent->pages);
async_extent->nr_pages = 0;
async_extent->pages = NULL;
- unlock_extent(io_tree, async_extent->start,
- async_extent->start +
- async_extent->ram_size - 1);
+
if (ret == -ENOSPC)
goto retry;
- goto out_free; /* JDM: Requeue? */
+ goto out_free;
}
/*
async_extent->ram_size - 1, 0);
em = alloc_extent_map();
- BUG_ON(!em); /* -ENOMEM */
+ if (!em)
+ goto out_free_reserve;
em->start = async_extent->start;
em->len = async_extent->ram_size;
em->orig_start = em->start;
+ em->mod_start = em->start;
+ em->mod_len = em->len;
em->block_start = ins.objectid;
em->block_len = ins.offset;
async_extent->ram_size - 1, 0);
}
+ if (ret)
+ goto out_free_reserve;
+
ret = btrfs_add_ordered_extent_compress(inode,
async_extent->start,
ins.objectid,
ins.offset,
BTRFS_ORDERED_COMPRESSED,
async_extent->compress_type);
- BUG_ON(ret); /* -ENOMEM */
+ if (ret)
+ goto out_free_reserve;
/*
* clear dirty, set writeback and unlock the pages.
ins.objectid,
ins.offset, async_extent->pages,
async_extent->nr_pages);
-
- BUG_ON(ret); /* -ENOMEM */
alloc_hint = ins.objectid + ins.offset;
kfree(async_extent);
+ if (ret)
+ goto out;
cond_resched();
}
ret = 0;
out:
return ret;
+out_free_reserve:
+ btrfs_free_reserved_extent(root, ins.objectid, ins.offset);
out_free:
+ extent_clear_unlock_delalloc(inode, &BTRFS_I(inode)->io_tree,
+ async_extent->start,
+ async_extent->start +
+ async_extent->ram_size - 1,
+ NULL, EXTENT_CLEAR_UNLOCK_PAGE |
+ EXTENT_CLEAR_UNLOCK |
+ EXTENT_CLEAR_DELALLOC |
+ EXTENT_CLEAR_DIRTY |
+ EXTENT_SET_WRITEBACK |
+ EXTENT_END_WRITEBACK);
kfree(async_extent);
- goto out;
+ goto again;
}
static u64 get_extent_allocation_hint(struct inode *inode, u64 start,
em->orig_start = em->start;
ram_size = ins.offset;
em->len = ins.offset;
+ em->mod_start = em->start;
+ em->mod_len = em->len;
em->block_start = ins.objectid;
em->block_len = ins.offset;
em->block_start = disk_bytenr;
em->orig_block_len = disk_num_bytes;
em->bdev = root->fs_info->fs_devices->latest_bdev;
+ em->mod_start = em->start;
+ em->mod_len = em->len;
set_bit(EXTENT_FLAG_PINNED, &em->flags);
set_bit(EXTENT_FLAG_FILLING, &em->flags);
em->generation = -1;
spin_unlock(&BTRFS_I(inode)->lock);
}
- spin_lock(&root->fs_info->delalloc_lock);
+ __percpu_counter_add(&root->fs_info->delalloc_bytes, len,
+ root->fs_info->delalloc_batch);
+ spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->delalloc_bytes += len;
- root->fs_info->delalloc_bytes += len;
- if (do_list && list_empty(&BTRFS_I(inode)->delalloc_inodes)) {
- list_add_tail(&BTRFS_I(inode)->delalloc_inodes,
- &root->fs_info->delalloc_inodes);
+ if (do_list && !test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
+ &BTRFS_I(inode)->runtime_flags)) {
+ spin_lock(&root->fs_info->delalloc_lock);
+ if (list_empty(&BTRFS_I(inode)->delalloc_inodes)) {
+ list_add_tail(&BTRFS_I(inode)->delalloc_inodes,
+ &root->fs_info->delalloc_inodes);
+ set_bit(BTRFS_INODE_IN_DELALLOC_LIST,
+ &BTRFS_I(inode)->runtime_flags);
+ }
+ spin_unlock(&root->fs_info->delalloc_lock);
}
- spin_unlock(&root->fs_info->delalloc_lock);
+ spin_unlock(&BTRFS_I(inode)->lock);
}
}
&& do_list)
btrfs_free_reserved_data_space(inode, len);
- spin_lock(&root->fs_info->delalloc_lock);
- root->fs_info->delalloc_bytes -= len;
+ __percpu_counter_add(&root->fs_info->delalloc_bytes, -len,
+ root->fs_info->delalloc_batch);
+ spin_lock(&BTRFS_I(inode)->lock);
BTRFS_I(inode)->delalloc_bytes -= len;
-
if (do_list && BTRFS_I(inode)->delalloc_bytes == 0 &&
- !list_empty(&BTRFS_I(inode)->delalloc_inodes)) {
- list_del_init(&BTRFS_I(inode)->delalloc_inodes);
+ test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
+ &BTRFS_I(inode)->runtime_flags)) {
+ spin_lock(&root->fs_info->delalloc_lock);
+ if (!list_empty(&BTRFS_I(inode)->delalloc_inodes)) {
+ list_del_init(&BTRFS_I(inode)->delalloc_inodes);
+ clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
+ &BTRFS_I(inode)->runtime_flags);
+ }
+ spin_unlock(&root->fs_info->delalloc_lock);
}
- spin_unlock(&root->fs_info->delalloc_lock);
+ spin_unlock(&BTRFS_I(inode)->lock);
}
}
if (trans)
btrfs_end_transaction(trans, root);
- if (ret)
+ if (ret) {
clear_extent_uptodate(io_tree, ordered_extent->file_offset,
ordered_extent->file_offset +
ordered_extent->len - 1, NULL, GFP_NOFS);
+ /*
+ * If the ordered extent had an IOERR or something else went
+ * wrong we need to return the space for this ordered extent
+ * back to the allocator.
+ */
+ if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
+ !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags))
+ btrfs_free_reserved_extent(root, ordered_extent->start,
+ ordered_extent->disk_len);
+ }
+
+
/*
* This needs to be done to make sure anybody waiting knows we are done
* updating everything for this ordered extent.
static int btrfs_readpage_end_io_hook(struct page *page, u64 start, u64 end,
struct extent_state *state, int mirror)
{
- size_t offset = start - ((u64)page->index << PAGE_CACHE_SHIFT);
+ size_t offset = start - page_offset(page);
struct inode *inode = page->mapping->host;
struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
char *kaddr;
}
}
-enum btrfs_orphan_cleanup_state {
- ORPHAN_CLEANUP_STARTED = 1,
- ORPHAN_CLEANUP_DONE = 2,
-};
-
/*
* This is called in transaction commit time. If there are no orphan
* files in the subvolume, it removes orphan item and frees block_rsv
*/
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) {
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++;
}
struct btrfs_inode_item *item,
struct inode *inode)
{
- btrfs_set_inode_uid(leaf, item, i_uid_read(inode));
- btrfs_set_inode_gid(leaf, item, i_gid_read(inode));
- btrfs_set_inode_size(leaf, item, BTRFS_I(inode)->disk_i_size);
- btrfs_set_inode_mode(leaf, item, inode->i_mode);
- btrfs_set_inode_nlink(leaf, item, inode->i_nlink);
+ struct btrfs_map_token token;
- btrfs_set_timespec_sec(leaf, btrfs_inode_atime(item),
- inode->i_atime.tv_sec);
- btrfs_set_timespec_nsec(leaf, btrfs_inode_atime(item),
- inode->i_atime.tv_nsec);
+ btrfs_init_map_token(&token);
- btrfs_set_timespec_sec(leaf, btrfs_inode_mtime(item),
- inode->i_mtime.tv_sec);
- btrfs_set_timespec_nsec(leaf, btrfs_inode_mtime(item),
- inode->i_mtime.tv_nsec);
+ btrfs_set_token_inode_uid(leaf, item, i_uid_read(inode), &token);
+ btrfs_set_token_inode_gid(leaf, item, i_gid_read(inode), &token);
+ btrfs_set_token_inode_size(leaf, item, BTRFS_I(inode)->disk_i_size,
+ &token);
+ btrfs_set_token_inode_mode(leaf, item, inode->i_mode, &token);
+ btrfs_set_token_inode_nlink(leaf, item, inode->i_nlink, &token);
- btrfs_set_timespec_sec(leaf, btrfs_inode_ctime(item),
- inode->i_ctime.tv_sec);
- btrfs_set_timespec_nsec(leaf, btrfs_inode_ctime(item),
- inode->i_ctime.tv_nsec);
+ btrfs_set_token_timespec_sec(leaf, btrfs_inode_atime(item),
+ inode->i_atime.tv_sec, &token);
+ btrfs_set_token_timespec_nsec(leaf, btrfs_inode_atime(item),
+ inode->i_atime.tv_nsec, &token);
- btrfs_set_inode_nbytes(leaf, item, inode_get_bytes(inode));
- btrfs_set_inode_generation(leaf, item, BTRFS_I(inode)->generation);
- btrfs_set_inode_sequence(leaf, item, inode->i_version);
- btrfs_set_inode_transid(leaf, item, trans->transid);
- btrfs_set_inode_rdev(leaf, item, inode->i_rdev);
- btrfs_set_inode_flags(leaf, item, BTRFS_I(inode)->flags);
- btrfs_set_inode_block_group(leaf, item, 0);
+ btrfs_set_token_timespec_sec(leaf, btrfs_inode_mtime(item),
+ inode->i_mtime.tv_sec, &token);
+ btrfs_set_token_timespec_nsec(leaf, btrfs_inode_mtime(item),
+ inode->i_mtime.tv_nsec, &token);
+
+ btrfs_set_token_timespec_sec(leaf, btrfs_inode_ctime(item),
+ inode->i_ctime.tv_sec, &token);
+ btrfs_set_token_timespec_nsec(leaf, btrfs_inode_ctime(item),
+ inode->i_ctime.tv_nsec, &token);
+
+ btrfs_set_token_inode_nbytes(leaf, item, inode_get_bytes(inode),
+ &token);
+ btrfs_set_token_inode_generation(leaf, item, BTRFS_I(inode)->generation,
+ &token);
+ btrfs_set_token_inode_sequence(leaf, item, inode->i_version, &token);
+ btrfs_set_token_inode_transid(leaf, item, trans->transid, &token);
+ btrfs_set_token_inode_rdev(leaf, item, inode->i_rdev, &token);
+ btrfs_set_token_inode_flags(leaf, item, BTRFS_I(inode)->flags, &token);
+ btrfs_set_token_inode_block_group(leaf, item, 0, &token);
}
/*
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);
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);
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);
+
+ /* Disable nonlocked read DIO to avoid the end less truncate */
+ btrfs_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+ btrfs_inode_resume_unlocked_dio(inode);
+
ret = btrfs_truncate(inode);
+ if (ret && inode->i_nlink)
+ btrfs_orphan_del(NULL, inode);
}
return ret;
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;
}
goto no_delete;
}
+ ret = btrfs_commit_inode_delayed_inode(inode);
+ if (ret) {
+ btrfs_orphan_del(NULL, inode);
+ goto no_delete;
+ }
+
rsv = btrfs_alloc_block_rsv(root, BTRFS_BLOCK_RSV_TEMP);
if (!rsv) {
btrfs_orphan_del(NULL, inode);
goto no_delete;
}
- trans = btrfs_start_transaction_lflush(root, 1);
+ trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
btrfs_orphan_del(NULL, inode);
btrfs_free_block_rsv(root, rsv);
break;
trans->block_rsv = &root->fs_info->trans_block_rsv;
- ret = btrfs_update_inode(trans, root, inode);
- BUG_ON(ret);
-
btrfs_end_transaction(trans, root);
trans = NULL;
btrfs_btree_balance_dirty(root);
goto out_unlock;
}
- err = btrfs_update_inode(trans, root, inode);
- if (err) {
- drop_inode = 1;
- goto out_unlock;
- }
-
/*
* If the active LSM wants to access the inode during
* d_instantiate it needs these. Smack checks to see
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;
*/
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;
em->start = start;
em->orig_start = orig_start;
+ em->mod_start = start;
+ em->mod_len = len;
em->len = len;
em->block_len = block_len;
em->block_start = block_start;
u64 len = bh_result->b_size;
struct btrfs_trans_handle *trans;
int unlock_bits = EXTENT_LOCKED;
- int ret;
+ int ret = 0;
if (create) {
- ret = btrfs_delalloc_reserve_space(inode, len);
- if (ret)
- return ret;
+ spin_lock(&BTRFS_I(inode)->lock);
+ BTRFS_I(inode)->outstanding_extents++;
+ spin_unlock(&BTRFS_I(inode)->lock);
unlock_bits |= EXTENT_DELALLOC | EXTENT_DIRTY;
- } else {
+ } else
len = min_t(u64, len, root->sectorsize);
- }
lockstart = start;
lockend = start + len - 1;
if (lock_extent_direct(inode, lockstart, lockend, &cached_state, create))
return -ENOTBLK;
- if (create) {
- ret = set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
- lockend, EXTENT_DELALLOC, NULL,
- &cached_state, GFP_NOFS);
- if (ret)
- goto unlock_err;
- }
-
em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
if (IS_ERR(em)) {
ret = PTR_ERR(em);
if (!create && (em->block_start == EXTENT_MAP_HOLE ||
test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
free_extent_map(em);
- ret = 0;
goto unlock_err;
}
*/
if (start + len > i_size_read(inode))
i_size_write(inode, start + len);
+
+ ret = set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
+ lockstart + len - 1, EXTENT_DELALLOC, NULL,
+ &cached_state, GFP_NOFS);
+ BUG_ON(ret);
}
/*
* aren't using if there is any left over space.
*/
if (lockstart < lockend) {
- if (create && len < lockend - lockstart) {
- clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
- lockstart + len - 1,
- unlock_bits | EXTENT_DEFRAG, 1, 0,
- &cached_state, GFP_NOFS);
- /*
- * Beside unlock, we also need to cleanup reserved space
- * for the left range by attaching EXTENT_DO_ACCOUNTING.
- */
- clear_extent_bit(&BTRFS_I(inode)->io_tree,
- lockstart + len, lockend,
- unlock_bits | EXTENT_DO_ACCOUNTING |
- EXTENT_DEFRAG, 1, 0, NULL, GFP_NOFS);
- } else {
- clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
- lockend, unlock_bits, 1, 0,
- &cached_state, GFP_NOFS);
- }
+ clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
+ lockend, unlock_bits, 1, 0,
+ &cached_state, GFP_NOFS);
} else {
free_extent_state(cached_state);
}
return 0;
unlock_err:
- if (create)
- unlock_bits |= EXTENT_DO_ACCOUNTING;
-
clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend,
unlock_bits, 1, 0, &cached_state, GFP_NOFS);
return ret;
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ size_t count = 0;
+ int flags = 0;
+ bool wakeup = true;
+ bool relock = false;
+ ssize_t ret;
if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iov,
offset, nr_segs))
return 0;
- return __blockdev_direct_IO(rw, iocb, inode,
- BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
- iov, offset, nr_segs, btrfs_get_blocks_direct, NULL,
- btrfs_submit_direct, 0);
+ atomic_inc(&inode->i_dio_count);
+ smp_mb__after_atomic_inc();
+
+ if (rw & WRITE) {
+ count = iov_length(iov, nr_segs);
+ /*
+ * If the write DIO is beyond the EOF, we need update
+ * the isize, but it is protected by i_mutex. So we can
+ * not unlock the i_mutex at this case.
+ */
+ if (offset + count <= inode->i_size) {
+ mutex_unlock(&inode->i_mutex);
+ relock = true;
+ }
+ ret = btrfs_delalloc_reserve_space(inode, count);
+ if (ret)
+ goto out;
+ } else if (unlikely(test_bit(BTRFS_INODE_READDIO_NEED_LOCK,
+ &BTRFS_I(inode)->runtime_flags))) {
+ inode_dio_done(inode);
+ flags = DIO_LOCKING | DIO_SKIP_HOLES;
+ wakeup = false;
+ }
+
+ ret = __blockdev_direct_IO(rw, iocb, inode,
+ BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev,
+ iov, offset, nr_segs, btrfs_get_blocks_direct, NULL,
+ btrfs_submit_direct, flags);
+ if (rw & WRITE) {
+ if (ret < 0 && ret != -EIOCBQUEUED)
+ btrfs_delalloc_release_space(inode, count);
+ else if (ret > 0 && (size_t)ret < count) {
+ spin_lock(&BTRFS_I(inode)->lock);
+ BTRFS_I(inode)->outstanding_extents++;
+ spin_unlock(&BTRFS_I(inode)->lock);
+ btrfs_delalloc_release_space(inode,
+ count - (size_t)ret);
+ }
+ btrfs_delalloc_release_metadata(inode, 0);
+ }
+out:
+ if (wakeup)
+ inode_dio_done(inode);
+ if (relock)
+ mutex_lock(&inode->i_mutex);
+
+ return ret;
}
#define BTRFS_FIEMAP_FLAGS (FIEMAP_FLAG_SYNC)
return;
}
lock_extent_bits(tree, page_start, page_end, 0, &cached_state);
- ordered = btrfs_lookup_ordered_extent(inode,
- page_offset(page));
+ ordered = btrfs_lookup_ordered_extent(inode, page_offset(page));
if (ordered) {
/*
* IO on this page will never be started, so we need
/*
* 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;
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
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) {
{
struct btrfs_root *root = BTRFS_I(inode)->root;
+ /* the snap/subvol tree is on deleting */
if (btrfs_root_refs(&root->root_item) == 0 &&
- !btrfs_is_free_space_inode(inode))
+ root != root->fs_info->tree_root)
return 1;
else
return generic_drop_inode(inode);
static int btrfs_getattr(struct vfsmount *mnt,
struct dentry *dentry, struct kstat *stat)
{
+ u64 delalloc_bytes;
struct inode *inode = dentry->d_inode;
u32 blocksize = inode->i_sb->s_blocksize;
generic_fillattr(inode, stat);
stat->dev = BTRFS_I(inode)->root->anon_dev;
stat->blksize = PAGE_CACHE_SIZE;
+
+ spin_lock(&BTRFS_I(inode)->lock);
+ delalloc_bytes = BTRFS_I(inode)->delalloc_bytes;
+ spin_unlock(&BTRFS_I(inode)->lock);
stat->blocks = (ALIGN(inode_get_bytes(inode), blocksize) +
- ALIGN(BTRFS_I(inode)->delalloc_bytes, blocksize)) >> 9;
+ ALIGN(delalloc_bytes, blocksize)) >> 9;
return 0;
}
*/
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);
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);
+ if (!inode) {
+ clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
+ &binode->runtime_flags);
+ 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);
+ }
+
/* 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
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;
}
projects / linux.git / blobdiff