13 files changed, 53 insertions, 30 deletions

diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig
index a66768ebc8d1..80e9c18ea64f 100644
--- a/fs/btrfs/Kconfig
+++ b/fs/btrfs/Kconfig
@@ -8,6 +8,7 @@ config BTRFS_FS
         select LZO_DECOMPRESS
         select RAID6_PQ
         select XOR_BLOCKS
+        select SRCU
 
         help
           Btrfs is a general purpose copy-on-write filesystem with extents,
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 2d3e32ebfd15..8729cf68d2fe 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1552,7 +1552,6 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
 {
         int ret;
         int type;
-        struct btrfs_tree_block_info *info;
         struct btrfs_extent_inline_ref *eiref;
 
         if (*ptr == (unsigned long)-1)
@@ -1573,9 +1572,17 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb,
         }
 
         /* we can treat both ref types equally here */
-        info = (struct btrfs_tree_block_info *)(ei + 1);
         *out_root = btrfs_extent_inline_ref_offset(eb, eiref);
-        *out_level = btrfs_tree_block_level(eb, info);
+
+        if (key->type == BTRFS_EXTENT_ITEM_KEY) {
+                struct btrfs_tree_block_info *info;
+
+                info = (struct btrfs_tree_block_info *)(ei + 1);
+                *out_level = btrfs_tree_block_level(eb, info);
+        } else {
+                ASSERT(key->type == BTRFS_METADATA_ITEM_KEY);
+                *out_level = (u8)key->offset;
+        }
 
         if (ret == 1)
                 *ptr = (unsigned long)-1;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 7e607416755a..0b180708bf79 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1171,6 +1171,7 @@ struct btrfs_space_info {
         struct percpu_counter total_bytes_pinned;
 
         struct list_head list;
+        /* Protected by the spinlock 'lock'. */
         struct list_head ro_bgs;
 
         struct rw_semaphore groups_sem;
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 054577bddaf2..de4e70fb3cbb 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1857,6 +1857,14 @@ int btrfs_delayed_delete_inode_ref(struct inode *inode)
 {
         struct btrfs_delayed_node *delayed_node;
 
+        /*
+         * we don't do delayed inode updates during log recovery because it
+         * leads to enospc problems.  This means we also can't do
+         * delayed inode refs
+         */
+        if (BTRFS_I(inode)->root->fs_info->log_root_recovering)
+                return -EAGAIN;
+
         delayed_node = btrfs_get_or_create_delayed_node(inode);
         if (IS_ERR(delayed_node))
                 return PTR_ERR(delayed_node);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8c63419a7f70..1afb18226da8 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1715,12 +1715,11 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
 {
         int err;
 
-        bdi->capabilities = BDI_CAP_MAP_COPY;
-        err = bdi_setup_and_register(bdi, "btrfs", BDI_CAP_MAP_COPY);
+        err = bdi_setup_and_register(bdi, "btrfs");
         if (err)
                 return err;
 
-        bdi->ra_pages   = default_backing_dev_info.ra_pages;
+        bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE;
         bdi->congested_fn       = btrfs_congested_fn;
         bdi->congested_data     = info;
         return 0;
@@ -2319,7 +2318,6 @@ int open_ctree(struct super_block *sb,
          */
         fs_info->btree_inode->i_size = OFFSET_MAX;
         fs_info->btree_inode->i_mapping->a_ops = &btree_aops;
-        fs_info->btree_inode->i_mapping->backing_dev_info = &fs_info->bdi;
 
         RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node);
         extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index a80b97100d90..a684086c3c81 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3139,9 +3139,11 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
         struct extent_buffer *leaf;
 
         ret = btrfs_search_slot(trans, extent_root, &cache->key, path, 0, 1);
-        if (ret < 0)
+        if (ret) {
+                if (ret > 0)
+                        ret = -ENOENT;
                 goto fail;
-        BUG_ON(ret); /* Corruption */
+        }
 
         leaf = path->nodes[0];
         bi = btrfs_item_ptr_offset(leaf, path->slots[0]);
@@ -3149,11 +3151,9 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
         btrfs_mark_buffer_dirty(leaf);
         btrfs_release_path(path);
 fail:
-        if (ret) {
+        if (ret)
                 btrfs_abort_transaction(trans, root, ret);
-                return ret;
-        }
-        return 0;
+        return ret;
 
 }
 
@@ -9422,7 +9422,6 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
          * are still on the list after taking the semaphore
          */
         list_del_init(&block_group->list);
-        list_del_init(&block_group->ro_list);
         if (list_empty(&block_group->space_info->block_groups[index])) {
                 kobj = block_group->space_info->block_group_kobjs[index];
                 block_group->space_info->block_group_kobjs[index] = NULL;
@@ -9464,6 +9463,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
         btrfs_remove_free_space_cache(block_group);
 
         spin_lock(&block_group->space_info->lock);
+        list_del_init(&block_group->ro_list);
         block_group->space_info->total_bytes -= block_group->key.offset;
         block_group->space_info->bytes_readonly -= block_group->key.offset;
         block_group->space_info->disk_total -= block_group->key.offset * factor;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 4ebabd237153..c73df6a7c9b6 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1407,8 +1407,8 @@ int extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
         while (index <= end_index) {
                 page = find_get_page(inode->i_mapping, index);
                 BUG_ON(!page); /* Pages should be in the extent_io_tree */
-                account_page_redirty(page);
                 __set_page_dirty_nobuffers(page);
+                account_page_redirty(page);
                 page_cache_release(page);
                 index++;
         }
@@ -2190,7 +2190,7 @@ void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end)
 
                 next = next_state(state);
 
-                failrec = (struct io_failure_record *)state->private;
+                failrec = (struct io_failure_record *)(unsigned long)state->private;
                 free_extent_state(state);
                 kfree(failrec);
 
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index e4090259569b..b78bbbac900d 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1746,7 +1746,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 
         mutex_lock(&inode->i_mutex);
 
-        current->backing_dev_info = inode->i_mapping->backing_dev_info;
+        current->backing_dev_info = inode_to_bdi(inode);
         err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode));
         if (err) {
                 mutex_unlock(&inode->i_mutex);
@@ -2081,7 +2081,6 @@ static const struct vm_operations_struct btrfs_file_vm_ops = {
         .fault          = filemap_fault,
         .map_pages      = filemap_map_pages,
         .page_mkwrite   = btrfs_page_mkwrite,
-        .remap_pages    = generic_file_remap_pages,
 };
 
 static int btrfs_file_mmap(struct file  *filp, struct vm_area_struct *vma)
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e687bb0dc73a..54bcf639d1cf 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3608,7 +3608,6 @@ cache_acl:
         switch (inode->i_mode & S_IFMT) {
         case S_IFREG:
                 inode->i_mapping->a_ops = &btrfs_aops;
-                inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
                 BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
                 inode->i_fop = &btrfs_file_operations;
                 inode->i_op = &btrfs_file_inode_operations;
@@ -3623,7 +3622,6 @@ cache_acl:
         case S_IFLNK:
                 inode->i_op = &btrfs_symlink_inode_operations;
                 inode->i_mapping->a_ops = &btrfs_symlink_aops;
-                inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
                 break;
         default:
                 inode->i_op = &btrfs_special_inode_operations;
@@ -6088,7 +6086,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
         inode->i_fop = &btrfs_file_operations;
         inode->i_op = &btrfs_file_inode_operations;
         inode->i_mapping->a_ops = &btrfs_aops;
-        inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
 
         err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
         if (err)
@@ -6255,8 +6252,10 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 out_fail:
         btrfs_end_transaction(trans, root);
-        if (drop_on_err)
+        if (drop_on_err) {
+                inode_dec_link_count(inode);
                 iput(inode);
+        }
         btrfs_balance_delayed_items(root);
         btrfs_btree_balance_dirty(root);
         return err;
@@ -9201,7 +9200,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
         inode->i_fop = &btrfs_file_operations;
         inode->i_op = &btrfs_file_inode_operations;
         inode->i_mapping->a_ops = &btrfs_aops;
-        inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
         BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 
         err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
@@ -9245,7 +9243,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 
         inode->i_op = &btrfs_symlink_inode_operations;
         inode->i_mapping->a_ops = &btrfs_symlink_aops;
-        inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
         inode_set_bytes(inode, name_len);
         btrfs_i_size_write(inode, name_len);
         err = btrfs_update_inode(trans, root, inode);
@@ -9457,7 +9454,6 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
         inode->i_op = &btrfs_file_inode_operations;
 
         inode->i_mapping->a_ops = &btrfs_aops;
-        inode->i_mapping->backing_dev_info = &root->fs_info->bdi;
         BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 
         ret = btrfs_init_inode_security(trans, inode, dir, NULL);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index f2bb13a23f86..e427cb7ee12c 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -2607,9 +2607,9 @@ static int scrub_extent_for_parity(struct scrub_parity *sparity,
                 ret = scrub_pages_for_parity(sparity, logical, l, physical, dev,
                                              flags, gen, mirror_num,
                                              have_csum ? csum : NULL);
-skip:
                 if (ret)
                         return ret;
+skip:
                 len -= l;
                 logical += l;
                 physical += l;
@@ -3053,7 +3053,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 
         ppath = btrfs_alloc_path();
         if (!ppath) {
-                btrfs_free_path(ppath);
+                btrfs_free_path(path);
                 return -ENOMEM;
         }
 
@@ -3065,6 +3065,8 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
         path->search_commit_root = 1;
         path->skip_locking = 1;
 
+        ppath->search_commit_root = 1;
+        ppath->skip_locking = 1;
         /*
          * trigger the readahead for extent tree csum tree and wait for
          * completion. During readahead, the scrub is officially paused
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 60f7cbe815e9..6f49b2872a64 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1000,10 +1000,20 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
                          */
                         if (fs_info->pending_changes == 0)
                                 return 0;
+                        /*
+                         * A non-blocking test if the fs is frozen. We must not
+                         * start a new transaction here otherwise a deadlock
+                         * happens. The pending operations are delayed to the
+                         * next commit after thawing.
+                         */
+                        if (__sb_start_write(sb, SB_FREEZE_WRITE, false))
+                                __sb_end_write(sb, SB_FREEZE_WRITE);
+                        else
+                                return 0;
                         trans = btrfs_start_transaction(root, 0);
-                } else {
-                        return PTR_ERR(trans);
                 }
+                if (IS_ERR(trans))
+                        return PTR_ERR(trans);
         }
         return btrfs_commit_transaction(trans, root);
 }
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index a605d4e2f2bc..e88b59d13439 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -2118,7 +2118,7 @@ void btrfs_apply_pending_changes(struct btrfs_fs_info *fs_info)
         unsigned long prev;
         unsigned long bit;
 
-        prev = cmpxchg(&fs_info->pending_changes, 0, 0);
+        prev = xchg(&fs_info->pending_changes, 0);
         if (!prev)
                 return;
 
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 9a02da16f2be..1a9585d4380a 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2591,6 +2591,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
         }
 
         if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) {
+                blk_finish_plug(&plug);
                 mutex_unlock(&log_root_tree->log_mutex);
                 ret = root_log_ctx.log_ret;
                 goto out;