summaryrefslogtreecommitdiff
path: root/fs/btrfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs')
-rw-r--r--fs/btrfs/async-thread.c2
-rw-r--r--fs/btrfs/backref.c10
-rw-r--r--fs/btrfs/ctree.h2
-rw-r--r--fs/btrfs/delayed-inode.c3
-rw-r--r--fs/btrfs/delayed-inode.h2
-rw-r--r--fs/btrfs/disk-io.c34
-rw-r--r--fs/btrfs/extent-tree.c13
-rw-r--r--fs/btrfs/inode-map.c9
-rw-r--r--fs/btrfs/inode-map.h1
-rw-r--r--fs/btrfs/inode.c47
-rw-r--r--fs/btrfs/ioctl.c123
-rw-r--r--fs/btrfs/root-tree.c10
-rw-r--r--fs/btrfs/send.c16
-rw-r--r--fs/btrfs/super.c24
-rw-r--r--fs/btrfs/volumes.c29
15 files changed, 258 insertions, 67 deletions
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 3e36e4adc4a3..9aba42b78253 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -328,8 +328,8 @@ static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq,
list_add_tail(&work->ordered_list, &wq->ordered_list);
spin_unlock_irqrestore(&wq->list_lock, flags);
}
- queue_work(wq->normal_wq, &work->normal_work);
trace_btrfs_work_queued(work);
+ queue_work(wq->normal_wq, &work->normal_work);
}
void btrfs_queue_work(struct btrfs_workqueue *wq,
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index d453d62ab0c6..e2f659dc5745 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1417,7 +1417,8 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
read_extent_buffer(eb, dest + bytes_left,
name_off, name_len);
if (eb != eb_in) {
- btrfs_tree_read_unlock_blocking(eb);
+ if (!path->skip_locking)
+ btrfs_tree_read_unlock_blocking(eb);
free_extent_buffer(eb);
}
ret = btrfs_find_item(fs_root, path, parent, 0,
@@ -1437,9 +1438,10 @@ char *btrfs_ref_to_path(struct btrfs_root *fs_root, struct btrfs_path *path,
eb = path->nodes[0];
/* make sure we can use eb after releasing the path */
if (eb != eb_in) {
- atomic_inc(&eb->refs);
- btrfs_tree_read_lock(eb);
- btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+ if (!path->skip_locking)
+ btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
+ path->nodes[0] = NULL;
+ path->locks[0] = 0;
}
btrfs_release_path(path);
iref = btrfs_item_ptr(eb, slot, struct btrfs_inode_ref);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 35489e7129a7..385b449fd7ed 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1572,7 +1572,7 @@ struct btrfs_fs_info {
spinlock_t delayed_iput_lock;
struct list_head delayed_iputs;
- struct rw_semaphore delayed_iput_sem;
+ struct mutex cleaner_delayed_iput_mutex;
/* this protects tree_mod_seq_list */
spinlock_t tree_mod_seq_lock;
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index e0941fbb913c..02b934d0ee65 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1694,7 +1694,7 @@ int btrfs_should_delete_dir_index(struct list_head *del_list,
*
*/
int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
- struct list_head *ins_list)
+ struct list_head *ins_list, bool *emitted)
{
struct btrfs_dir_item *di;
struct btrfs_delayed_item *curr, *next;
@@ -1738,6 +1738,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
if (over)
return 1;
+ *emitted = true;
}
return 0;
}
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index f70119f25421..0167853c84ae 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -144,7 +144,7 @@ void btrfs_put_delayed_items(struct list_head *ins_list,
int btrfs_should_delete_dir_index(struct list_head *del_list,
u64 index);
int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
- struct list_head *ins_list);
+ struct list_head *ins_list, bool *emitted);
/* for init */
int __init btrfs_delayed_inode_init(void);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 974be09e7556..41fb43183406 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1582,8 +1582,23 @@ int btrfs_init_fs_root(struct btrfs_root *root)
ret = get_anon_bdev(&root->anon_dev);
if (ret)
goto free_writers;
+
+ mutex_lock(&root->objectid_mutex);
+ ret = btrfs_find_highest_objectid(root,
+ &root->highest_objectid);
+ if (ret) {
+ mutex_unlock(&root->objectid_mutex);
+ goto free_root_dev;
+ }
+
+ ASSERT(root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+ mutex_unlock(&root->objectid_mutex);
+
return 0;
+free_root_dev:
+ free_anon_bdev(root->anon_dev);
free_writers:
btrfs_free_subvolume_writers(root->subv_writers);
fail:
@@ -1762,7 +1777,6 @@ static int cleaner_kthread(void *arg)
int again;
struct btrfs_trans_handle *trans;
- set_freezable();
do {
again = 0;
@@ -1782,7 +1796,10 @@ static int cleaner_kthread(void *arg)
goto sleep;
}
+ mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex);
btrfs_run_delayed_iputs(root);
+ mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex);
+
again = btrfs_clean_one_deleted_snapshot(root);
mutex_unlock(&root->fs_info->cleaner_mutex);
@@ -2542,8 +2559,8 @@ int open_ctree(struct super_block *sb,
mutex_init(&fs_info->delete_unused_bgs_mutex);
mutex_init(&fs_info->reloc_mutex);
mutex_init(&fs_info->delalloc_root_mutex);
+ mutex_init(&fs_info->cleaner_delayed_iput_mutex);
seqlock_init(&fs_info->profiles_lock);
- init_rwsem(&fs_info->delayed_iput_sem);
INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
INIT_LIST_HEAD(&fs_info->space_info);
@@ -2668,6 +2685,7 @@ int open_ctree(struct super_block *sb,
if (btrfs_check_super_csum(bh->b_data)) {
printk(KERN_ERR "BTRFS: superblock checksum mismatch\n");
err = -EINVAL;
+ brelse(bh);
goto fail_alloc;
}
@@ -2900,6 +2918,18 @@ retry_root_backup:
tree_root->commit_root = btrfs_root_node(tree_root);
btrfs_set_root_refs(&tree_root->root_item, 1);
+ mutex_lock(&tree_root->objectid_mutex);
+ ret = btrfs_find_highest_objectid(tree_root,
+ &tree_root->highest_objectid);
+ if (ret) {
+ mutex_unlock(&tree_root->objectid_mutex);
+ goto recovery_tree_root;
+ }
+
+ ASSERT(tree_root->highest_objectid <= BTRFS_LAST_FREE_OBJECTID);
+
+ mutex_unlock(&tree_root->objectid_mutex);
+
ret = btrfs_read_roots(fs_info, tree_root);
if (ret)
goto recovery_tree_root;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index c4661db2b72a..2368cac1115a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4086,8 +4086,10 @@ commit_trans:
!atomic_read(&root->fs_info->open_ioctl_trans)) {
need_commit--;
- if (need_commit > 0)
+ if (need_commit > 0) {
+ btrfs_start_delalloc_roots(fs_info, 0, -1);
btrfs_wait_ordered_roots(fs_info, -1);
+ }
trans = btrfs_join_transaction(root);
if (IS_ERR(trans))
@@ -4100,11 +4102,12 @@ commit_trans:
if (ret)
return ret;
/*
- * make sure that all running delayed iput are
- * done
+ * The cleaner kthread might still be doing iput
+ * operations. Wait for it to finish so that
+ * more space is released.
*/
- down_write(&root->fs_info->delayed_iput_sem);
- up_write(&root->fs_info->delayed_iput_sem);
+ mutex_lock(&root->fs_info->cleaner_delayed_iput_mutex);
+ mutex_unlock(&root->fs_info->cleaner_delayed_iput_mutex);
goto again;
} else {
btrfs_end_transaction(trans, root);
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 767a6056ac45..07573dc1614a 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -515,7 +515,7 @@ out:
return ret;
}
-static int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
+int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid)
{
struct btrfs_path *path;
int ret;
@@ -555,13 +555,6 @@ int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid)
int ret;
mutex_lock(&root->objectid_mutex);
- if (unlikely(root->highest_objectid < BTRFS_FIRST_FREE_OBJECTID)) {
- ret = btrfs_find_highest_objectid(root,
- &root->highest_objectid);
- if (ret)
- goto out;
- }
-
if (unlikely(root->highest_objectid >= BTRFS_LAST_FREE_OBJECTID)) {
ret = -ENOSPC;
goto out;
diff --git a/fs/btrfs/inode-map.h b/fs/btrfs/inode-map.h
index ddb347bfee23..c8e864b2d530 100644
--- a/fs/btrfs/inode-map.h
+++ b/fs/btrfs/inode-map.h
@@ -9,5 +9,6 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
struct btrfs_trans_handle *trans);
int btrfs_find_free_objectid(struct btrfs_root *root, u64 *objectid);
+int btrfs_find_highest_objectid(struct btrfs_root *root, u64 *objectid);
#endif
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a70c5790f8f5..4bc9dbf29a73 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3142,8 +3142,6 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root)
if (empty)
return;
- down_read(&fs_info->delayed_iput_sem);
-
spin_lock(&fs_info->delayed_iput_lock);
list_splice_init(&fs_info->delayed_iputs, &list);
spin_unlock(&fs_info->delayed_iput_lock);
@@ -3154,8 +3152,6 @@ void btrfs_run_delayed_iputs(struct btrfs_root *root)
iput(delayed->inode);
kfree(delayed);
}
-
- up_read(&root->fs_info->delayed_iput_sem);
}
/*
@@ -5741,6 +5737,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
char *name_ptr;
int name_len;
int is_curr = 0; /* ctx->pos points to the current index? */
+ bool emitted;
/* FIXME, use a real flag for deciding about the key type */
if (root->fs_info->tree_root == root)
@@ -5769,6 +5766,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
if (ret < 0)
goto err;
+ emitted = false;
while (1) {
leaf = path->nodes[0];
slot = path->slots[0];
@@ -5848,6 +5846,7 @@ skip:
if (over)
goto nopos;
+ emitted = true;
di_len = btrfs_dir_name_len(leaf, di) +
btrfs_dir_data_len(leaf, di) + sizeof(*di);
di_cur += di_len;
@@ -5860,11 +5859,20 @@ next:
if (key_type == BTRFS_DIR_INDEX_KEY) {
if (is_curr)
ctx->pos++;
- ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list);
+ ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list, &emitted);
if (ret)
goto nopos;
}
+ /*
+ * If we haven't emitted any dir entry, we must not touch ctx->pos as
+ * it was was set to the termination value in previous call. We assume
+ * that "." and ".." were emitted if we reach this point and set the
+ * termination value as well for an empty directory.
+ */
+ if (ctx->pos > 2 && !emitted)
+ goto nopos;
+
/* Reached end of directory/root. Bump pos past the last item. */
ctx->pos++;
@@ -6481,7 +6489,7 @@ out_unlock_inode:
static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
struct dentry *dentry)
{
- struct btrfs_trans_handle *trans;
+ struct btrfs_trans_handle *trans = NULL;
struct btrfs_root *root = BTRFS_I(dir)->root;
struct inode *inode = d_inode(old_dentry);
u64 index;
@@ -6507,6 +6515,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
trans = btrfs_start_transaction(root, 5);
if (IS_ERR(trans)) {
err = PTR_ERR(trans);
+ trans = NULL;
goto fail;
}
@@ -6540,9 +6549,10 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
btrfs_log_new_name(trans, inode, NULL, parent);
}
- btrfs_end_transaction(trans, root);
btrfs_balance_delayed_items(root);
fail:
+ if (trans)
+ btrfs_end_transaction(trans, root);
if (drop_inode) {
inode_dec_link_count(inode);
iput(inode);
@@ -7985,6 +7995,7 @@ 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);
if (io_bio->end_io)
@@ -8030,6 +8041,7 @@ out_test:
kfree(dip);
+ dio_bio->bi_error = bio->bi_error;
dio_end_io(dio_bio, bio->bi_error);
bio_put(bio);
}
@@ -8534,15 +8546,28 @@ int btrfs_readpage(struct file *file, struct page *page)
static int btrfs_writepage(struct page *page, struct writeback_control *wbc)
{
struct extent_io_tree *tree;
-
+ struct inode *inode = page->mapping->host;
+ int ret;
if (current->flags & PF_MEMALLOC) {
redirty_page_for_writepage(wbc, page);
unlock_page(page);
return 0;
}
+
+ /*
+ * If we are under memory pressure we will call this directly from the
+ * VM, we need to make sure we have the inode referenced for the ordered
+ * extent. If not just return like we didn't do anything.
+ */
+ if (!igrab(inode)) {
+ redirty_page_for_writepage(wbc, page);
+ return AOP_WRITEPAGE_ACTIVATE;
+ }
tree = &BTRFS_I(page->mapping->host)->io_tree;
- return extent_write_full_page(tree, page, btrfs_get_extent, wbc);
+ ret = extent_write_full_page(tree, page, btrfs_get_extent, wbc);
+ btrfs_add_delayed_iput(inode);
+ return ret;
}
static int btrfs_writepages(struct address_space *mapping,
@@ -9636,9 +9661,11 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
/*
* 2 items for inode item and ref
* 2 items for dir items
+ * 1 item for updating parent inode item
+ * 1 item for the inline extent item
* 1 item for xattr if selinux is on
*/
- trans = btrfs_start_transaction(root, 5);
+ trans = btrfs_start_transaction(root, 7);
if (IS_ERR(trans))
return PTR_ERR(trans);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index da94138eb85e..f07d01bc4875 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -568,6 +568,10 @@ static noinline int create_subvol(struct inode *dir,
goto fail;
}
+ mutex_lock(&new_root->objectid_mutex);
+ new_root->highest_objectid = new_dirid;
+ mutex_unlock(&new_root->objectid_mutex);
+
/*
* insert the directory item
*/
@@ -2782,24 +2786,29 @@ out:
static struct page *extent_same_get_page(struct inode *inode, pgoff_t index)
{
struct page *page;
- struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
page = grab_cache_page(inode->i_mapping, index);
if (!page)
- return NULL;
+ return ERR_PTR(-ENOMEM);
if (!PageUptodate(page)) {
- if (extent_read_full_page_nolock(tree, page, btrfs_get_extent,
- 0))
- return NULL;
+ int ret;
+
+ ret = btrfs_readpage(NULL, page);
+ if (ret)
+ return ERR_PTR(ret);
lock_page(page);
if (!PageUptodate(page)) {
unlock_page(page);
page_cache_release(page);
- return NULL;
+ return ERR_PTR(-EIO);
+ }
+ if (page->mapping != inode->i_mapping) {
+ unlock_page(page);
+ page_cache_release(page);
+ return ERR_PTR(-EAGAIN);
}
}
- unlock_page(page);
return page;
}
@@ -2811,17 +2820,31 @@ static int gather_extent_pages(struct inode *inode, struct page **pages,
pgoff_t index = off >> PAGE_CACHE_SHIFT;
for (i = 0; i < num_pages; i++) {
+again:
pages[i] = extent_same_get_page(inode, index + i);
- if (!pages[i])
- return -ENOMEM;
+ if (IS_ERR(pages[i])) {
+ int err = PTR_ERR(pages[i]);
+
+ if (err == -EAGAIN)
+ goto again;
+ pages[i] = NULL;
+ return err;
+ }
}
return 0;
}
-static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
+static int lock_extent_range(struct inode *inode, u64 off, u64 len,
+ bool retry_range_locking)
{
- /* do any pending delalloc/csum calc on src, one way or
- another, and lock file content */
+ /*
+ * Do any pending delalloc/csum calculations on inode, one way or
+ * another, and lock file content.
+ * The locking order is:
+ *
+ * 1) pages
+ * 2) range in the inode's io tree
+ */
while (1) {
struct btrfs_ordered_extent *ordered;
lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
@@ -2839,8 +2862,11 @@ static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
if (ordered)
btrfs_put_ordered_extent(ordered);
+ if (!retry_range_locking)
+ return -EAGAIN;
btrfs_wait_ordered_range(inode, off, len);
}
+ return 0;
}
static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2)
@@ -2865,15 +2891,24 @@ static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
}
-static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
- struct inode *inode2, u64 loff2, u64 len)
+static int btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
+ struct inode *inode2, u64 loff2, u64 len,
+ bool retry_range_locking)
{
+ int ret;
+
if (inode1 < inode2) {
swap(inode1, inode2);
swap(loff1, loff2);
}
- lock_extent_range(inode1, loff1, len);
- lock_extent_range(inode2, loff2, len);
+ ret = lock_extent_range(inode1, loff1, len, retry_range_locking);
+ if (ret)
+ return ret;
+ ret = lock_extent_range(inode2, loff2, len, retry_range_locking);
+ if (ret)
+ unlock_extent(&BTRFS_I(inode1)->io_tree, loff1,
+ loff1 + len - 1);
+ return ret;
}
struct cmp_pages {
@@ -2889,11 +2924,15 @@ static void btrfs_cmp_data_free(struct cmp_pages *cmp)
for (i = 0; i < cmp->num_pages; i++) {
pg = cmp->src_pages[i];
- if (pg)
+ if (pg) {
+ unlock_page(pg);
page_cache_release(pg);
+ }
pg = cmp->dst_pages[i];
- if (pg)
+ if (pg) {
+ unlock_page(pg);
page_cache_release(pg);
+ }
}
kfree(cmp->src_pages);
kfree(cmp->dst_pages);
@@ -2954,6 +2993,8 @@ static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
src_page = cmp->src_pages[i];
dst_page = cmp->dst_pages[i];
+ ASSERT(PageLocked(src_page));
+ ASSERT(PageLocked(dst_page));
addr = kmap_atomic(src_page);
dst_addr = kmap_atomic(dst_page);
@@ -3066,14 +3107,46 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
goto out_unlock;
}
+again:
ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp);
if (ret)
goto out_unlock;
if (same_inode)
- lock_extent_range(src, same_lock_start, same_lock_len);
+ ret = lock_extent_range(src, same_lock_start, same_lock_len,
+ false);
else
- btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
+ ret = btrfs_double_extent_lock(src, loff, dst, dst_loff, len,
+ false);
+ /*
+ * If one of the inodes has dirty pages in the respective range or
+ * ordered extents, we need to flush dellaloc and wait for all ordered
+ * extents in the range. We must unlock the pages and the ranges in the
+ * io trees to avoid deadlocks when flushing delalloc (requires locking
+ * pages) and when waiting for ordered extents to complete (they require
+ * range locking).
+ */
+ if (ret == -EAGAIN) {
+ /*
+ * Ranges in the io trees already unlocked. Now unlock all
+ * pages before waiting for all IO to complete.
+ */
+ btrfs_cmp_data_free(&cmp);
+ if (same_inode) {
+ btrfs_wait_ordered_range(src, same_lock_start,
+ same_lock_len);
+ } else {
+ btrfs_wait_ordered_range(src, loff, len);
+ btrfs_wait_ordered_range(dst, dst_loff, len);
+ }
+ goto again;
+ }
+ ASSERT(ret == 0);
+ if (WARN_ON(ret)) {
+ /* ranges in the io trees already unlocked */
+ btrfs_cmp_data_free(&cmp);
+ return ret;
+ }
/* pass original length for comparison so we stay within i_size */
ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp);
@@ -3895,9 +3968,15 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
u64 lock_start = min_t(u64, off, destoff);
u64 lock_len = max_t(u64, off, destoff) + len - lock_start;
- lock_extent_range(src, lock_start, lock_len);
+ ret = lock_extent_range(src, lock_start, lock_len, true);
} else {
- btrfs_double_extent_lock(src, off, inode, destoff, len);
+ ret = btrfs_double_extent_lock(src, off, inode, destoff, len,
+ true);
+ }
+ ASSERT(ret == 0);
+ if (WARN_ON(ret)) {
+ /* ranges in the io trees already unlocked */
+ goto out_unlock;
}
ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 7cf8509deda7..2c849b08a91b 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -310,8 +310,16 @@ int btrfs_find_orphan_roots(struct btrfs_root *tree_root)
set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);
err = btrfs_insert_fs_root(root->fs_info, root);
+ /*
+ * The root might have been inserted already, as before we look
+ * for orphan roots, log replay might have happened, which
+ * triggers a transaction commit and qgroup accounting, which
+ * in turn reads and inserts fs roots while doing backref
+ * walking.
+ */
+ if (err == -EEXIST)
+ err = 0;
if (err) {
- BUG_ON(err == -EEXIST);
btrfs_free_fs_root(root);
break;
}
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 355a458cba1a..63a6152be04b 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1469,7 +1469,21 @@ static int read_symlink(struct btrfs_root *root,
ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
if (ret < 0)
goto out;
- BUG_ON(ret);
+ if (ret) {
+ /*
+ * An empty symlink inode. Can happen in rare error paths when
+ * creating a symlink (transaction committed before the inode
+ * eviction handler removed the symlink inode items and a crash
+ * happened in between or the subvol was snapshoted in between).
+ * Print an informative message to dmesg/syslog so that the user
+ * can delete the symlink.
+ */
+ btrfs_err(root->fs_info,
+ "Found empty symlink inode %llu at root %llu",
+ ino, root->root_key.objectid);
+ ret = -EIO;
+ goto out;
+ }
ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
struct btrfs_file_extent_item);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 24154e422945..fe609b81dd1b 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1956,6 +1956,8 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
* there are other factors that may change the result (like a new metadata
* chunk).
*
+ * If metadata is exhausted, f_bavail will be 0.
+ *
* FIXME: not accurate for mixed block groups, total and free/used are ok,
* available appears slightly larger.
*/
@@ -1967,11 +1969,13 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
struct btrfs_space_info *found;
u64 total_used = 0;
u64 total_free_data = 0;
+ u64 total_free_meta = 0;
int bits = dentry->d_sb->s_blocksize_bits;
__be32 *fsid = (__be32 *)fs_info->fsid;
unsigned factor = 1;
struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
int ret;
+ u64 thresh = 0;
/*
* holding chunk_muext to avoid allocating new chunks, holding
@@ -1997,6 +2001,8 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
}
}
}
+ if (found->flags & BTRFS_BLOCK_GROUP_METADATA)
+ total_free_meta += found->disk_total - found->disk_used;
total_used += found->disk_used;
}
@@ -2019,6 +2025,24 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_bavail += div_u64(total_free_data, factor);
buf->f_bavail = buf->f_bavail >> bits;
+ /*
+ * We calculate the remaining metadata space minus global reserve. If
+ * this is (supposedly) smaller than zero, there's no space. But this
+ * does not hold in practice, the exhausted state happens where's still
+ * some positive delta. So we apply some guesswork and compare the
+ * delta to a 4M threshold. (Practically observed delta was ~2M.)
+ *
+ * We probably cannot calculate the exact threshold value because this
+ * depends on the internal reservations requested by various
+ * operations, so some operations that consume a few metadata will
+ * succeed even if the Avail is zero. But this is better than the other
+ * way around.
+ */
+ thresh = 4 * 1024 * 1024;
+
+ if (total_free_meta - thresh < block_rsv->size)
+ buf->f_bavail = 0;
+
buf->f_type = BTRFS_SUPER_MAGIC;
buf->f_bsize = dentry->d_sb->s_blocksize;
buf->f_namelen = BTRFS_NAME_LEN;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a23399e8e3ab..9c62a6f9757a 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -232,6 +232,7 @@ static struct btrfs_device *__alloc_device(void)
spin_lock_init(&dev->reada_lock);
atomic_set(&dev->reada_in_flight, 0);
atomic_set(&dev->dev_stats_ccnt, 0);
+ btrfs_device_data_ordered_init(dev);
INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
@@ -1257,6 +1258,15 @@ int find_free_dev_extent_start(struct btrfs_transaction *transaction,
int ret;
int slot;
struct extent_buffer *l;
+ u64 min_search_start;
+
+ /*
+ * We don't want to overwrite the superblock on the drive nor any area
+ * used by the boot loader (grub for example), so we make sure to start
+ * at an offset of at least 1MB.
+ */
+ min_search_start = max(root->fs_info->alloc_start, 1024ull * 1024);
+ search_start = max(search_start, min_search_start);
path = btrfs_alloc_path();
if (!path)
@@ -1397,18 +1407,9 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans,
struct btrfs_device *device, u64 num_bytes,
u64 *start, u64 *len)
{
- struct btrfs_root *root = device->dev_root;
- u64 search_start;
-
/* FIXME use last free of some kind */
-
- /*
- * we don't want to overwrite the superblock on the drive,
- * so we make sure to start at an offset of at least 1MB
- */
- search_start = max(root->fs_info->alloc_start, 1024ull * 1024);
return find_free_dev_extent_start(trans->transaction, device,
- num_bytes, search_start, start, len);
+ num_bytes, 0, start, len);
}
static int btrfs_free_dev_extent(struct btrfs_trans_handle *trans,
@@ -6512,6 +6513,14 @@ int btrfs_read_sys_array(struct btrfs_root *root)
goto out_short_read;
num_stripes = btrfs_chunk_num_stripes(sb, chunk);
+ if (!num_stripes) {
+ printk(KERN_ERR
+ "BTRFS: invalid number of stripes %u in sys_array at offset %u\n",
+ num_stripes, cur_offset);
+ ret = -EIO;
+ break;
+ }
+
len = btrfs_chunk_item_size(num_stripes);
if (cur_offset + len > array_size)
goto out_short_read;
generated by cgit v1.2.3 (git 2.0.4) at 2024-06-22 13:11:22 +0000