Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs updates from Chris Mason:
 "The largest set of changes here come from Miao Xie.  He's cleaning up
  and improving read recovery/repair for raid, and has a number of
  related fixes.

  I've merged another set of fsync fixes from Filipe, and he's also
  improved the way we handle metadata write errors to make sure we force
  the FS readonly if things go wrong.

  Otherwise we have a collection of fixes and cleanups.  Dave Sterba
  gets a cookie for removing the most lines (thanks Dave)"

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs: (139 commits)
  btrfs: Fix compile error when CONFIG_SECURITY is not set.
  Btrfs: fix compiles when CONFIG_BTRFS_FS_RUN_SANITY_TESTS is off
  btrfs: Make btrfs handle security mount options internally to avoid losing security label.
  Btrfs: send, don't delay dir move if there's a new parent inode
  btrfs: add more superblock checks
  Btrfs: fix race in WAIT_SYNC ioctl
  Btrfs: be aware of btree inode write errors to avoid fs corruption
  Btrfs: remove redundant btrfs_verify_qgroup_counts declaration.
  btrfs: fix shadow warning on cmp
  Btrfs: fix compilation errors under DEBUG
  Btrfs: fix crash of btrfs_release_extent_buffer_page
  Btrfs: add missing end_page_writeback on submit_extent_page failure
  btrfs: Fix the wrong condition judgment about subset extent map
  Btrfs: fix build_backref_tree issue with multiple shared blocks
  Btrfs: cleanup error handling in build_backref_tree
  btrfs: move checks for DUMMY_ROOT into a helper
  btrfs: new define for the inline extent data start
  btrfs: kill extent_buffer_page helper
  btrfs: drop constant param from btrfs_release_extent_buffer_page
  btrfs: hide typecast to definition of BTRFS_SEND_TRANS_STUB
  ...

1 files changed, 150 insertions, 109 deletions

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index d0262ceb85e1..1475979e5718 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -97,7 +97,8 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
                            struct btrfs_root *root, struct inode *inode,
                            int inode_only,
                            const loff_t start,
-                           const loff_t end);
+                           const loff_t end,
+                           struct btrfs_log_ctx *ctx);
 static int link_to_fixup_dir(struct btrfs_trans_handle *trans,
                              struct btrfs_root *root,
                              struct btrfs_path *path, u64 objectid);
@@ -1498,7 +1499,7 @@ static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans,
                 return -EIO;
 
         key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID;
-        btrfs_set_key_type(&key, BTRFS_ORPHAN_ITEM_KEY);
+        key.type = BTRFS_ORPHAN_ITEM_KEY;
         key.offset = objectid;
 
         ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
@@ -1637,6 +1638,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans,
             found_key.type == log_key.type &&
             found_key.offset == log_key.offset &&
             btrfs_dir_type(path->nodes[0], dst_di) == log_type) {
+                update_size = false;
                 goto out;
         }
 
@@ -2157,7 +2159,7 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 
                 bytenr = btrfs_node_blockptr(cur, path->slots[*level]);
                 ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
-                blocksize = btrfs_level_size(root, *level - 1);
+                blocksize = root->nodesize;
 
                 parent = path->nodes[*level];
                 root_owner = btrfs_header_owner(parent);
@@ -2983,8 +2985,6 @@ static noinline int log_dir_items(struct btrfs_trans_handle *trans,
         min_key.type = key_type;
         min_key.offset = min_offset;
 
-        path->keep_locks = 1;
-
         ret = btrfs_search_forward(root, &min_key, path, trans->transid);
 
         /*
@@ -3364,7 +3364,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
                  * or deletes of this inode don't have to relog the inode
                  * again
                  */
-                if (btrfs_key_type(ins_keys + i) == BTRFS_EXTENT_DATA_KEY &&
+                if (ins_keys[i].type == BTRFS_EXTENT_DATA_KEY &&
                     !skip_csum) {
                         int found_type;
                         extent = btrfs_item_ptr(src, start_slot + i,
@@ -3573,107 +3573,33 @@ static int extent_cmp(void *priv, struct list_head *a, struct list_head *b)
         return 0;
 }
 
-static int log_one_extent(struct btrfs_trans_handle *trans,
-                          struct inode *inode, struct btrfs_root *root,
-                          struct extent_map *em, struct btrfs_path *path,
-                          struct list_head *logged_list)
+static int wait_ordered_extents(struct btrfs_trans_handle *trans,
+                                struct inode *inode,
+                                struct btrfs_root *root,
+                                const struct extent_map *em,
+                                const struct list_head *logged_list,
+                                bool *ordered_io_error)
 {
-        struct btrfs_root *log = root->log_root;
-        struct btrfs_file_extent_item *fi;
-        struct extent_buffer *leaf;
         struct btrfs_ordered_extent *ordered;
-        struct list_head ordered_sums;
-        struct btrfs_map_token token;
-        struct btrfs_key key;
+        struct btrfs_root *log = root->log_root;
         u64 mod_start = em->mod_start;
         u64 mod_len = em->mod_len;
+        const bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
         u64 csum_offset;
         u64 csum_len;
-        u64 extent_offset = em->start - em->orig_start;
-        u64 block_len;
-        int ret;
-        bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
-        int extent_inserted = 0;
-
-        INIT_LIST_HEAD(&ordered_sums);
-        btrfs_init_map_token(&token);
-
-        ret = __btrfs_drop_extents(trans, log, inode, path, em->start,
-                                   em->start + em->len, NULL, 0, 1,
-                                   sizeof(*fi), &extent_inserted);
-        if (ret)
-                return ret;
-
-        if (!extent_inserted) {
-                key.objectid = btrfs_ino(inode);
-                key.type = BTRFS_EXTENT_DATA_KEY;
-                key.offset = em->start;
-
-                ret = btrfs_insert_empty_item(trans, log, path, &key,
-                                              sizeof(*fi));
-                if (ret)
-                        return ret;
-        }
-        leaf = path->nodes[0];
-        fi = btrfs_item_ptr(leaf, path->slots[0],
-                            struct btrfs_file_extent_item);
-
-        btrfs_set_token_file_extent_generation(leaf, fi, em->generation,
-                                               &token);
-        if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
-                skip_csum = true;
-                btrfs_set_token_file_extent_type(leaf, fi,
-                                                 BTRFS_FILE_EXTENT_PREALLOC,
-                                                 &token);
-        } else {
-                btrfs_set_token_file_extent_type(leaf, fi,
-                                                 BTRFS_FILE_EXTENT_REG,
-                                                 &token);
-                if (em->block_start == EXTENT_MAP_HOLE)
-                        skip_csum = true;
-        }
-
-        block_len = max(em->block_len, em->orig_block_len);
-        if (em->compress_type != BTRFS_COMPRESS_NONE) {
-                btrfs_set_token_file_extent_disk_bytenr(leaf, fi,
-                                                        em->block_start,
-                                                        &token);
-                btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, block_len,
-                                                           &token);
-        } else if (em->block_start < EXTENT_MAP_LAST_BYTE) {
-                btrfs_set_token_file_extent_disk_bytenr(leaf, fi,
-                                                        em->block_start -
-                                                        extent_offset, &token);
-                btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, block_len,
-                                                           &token);
-        } else {
-                btrfs_set_token_file_extent_disk_bytenr(leaf, fi, 0, &token);
-                btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, 0,
-                                                           &token);
-        }
-
-        btrfs_set_token_file_extent_offset(leaf, fi,
-                                           em->start - em->orig_start,
-                                           &token);
-        btrfs_set_token_file_extent_num_bytes(leaf, fi, em->len, &token);
-        btrfs_set_token_file_extent_ram_bytes(leaf, fi, em->ram_bytes, &token);
-        btrfs_set_token_file_extent_compression(leaf, fi, em->compress_type,
-                                                &token);
-        btrfs_set_token_file_extent_encryption(leaf, fi, 0, &token);
-        btrfs_set_token_file_extent_other_encoding(leaf, fi, 0, &token);
-        btrfs_mark_buffer_dirty(leaf);
+        LIST_HEAD(ordered_sums);
+        int ret = 0;
 
-        btrfs_release_path(path);
-        if (ret) {
-                return ret;
-        }
+        *ordered_io_error = false;
 
-        if (skip_csum)
+        if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
+            em->block_start == EXTENT_MAP_HOLE)
                 return 0;
 
         /*
-         * First check and see if our csums are on our outstanding ordered
-         * extents.
+         * Wait far any ordered extent that covers our extent map. If it
+         * finishes without an error, first check and see if our csums are on
+         * our outstanding ordered extents.
          */
         list_for_each_entry(ordered, logged_list, log_list) {
                 struct btrfs_ordered_sum *sum;
@@ -3685,6 +3611,24 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
                     mod_start + mod_len <= ordered->file_offset)
                         continue;
 
+                if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) &&
+                    !test_bit(BTRFS_ORDERED_IOERR, &ordered->flags) &&
+                    !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) {
+                        const u64 start = ordered->file_offset;
+                        const u64 end = ordered->file_offset + ordered->len - 1;
+
+                        WARN_ON(ordered->inode != inode);
+                        filemap_fdatawrite_range(inode->i_mapping, start, end);
+                }
+
+                wait_event(ordered->wait,
+                           (test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) ||
+                            test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)));
+
+                if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)) {
+                        *ordered_io_error = true;
+                        break;
+                }
                 /*
                  * We are going to copy all the csums on this ordered extent, so
                  * go ahead and adjust mod_start and mod_len in case this
@@ -3716,6 +3660,9 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
                         }
                 }
 
+                if (skip_csum)
+                        continue;
+
                 /*
                  * To keep us from looping for the above case of an ordered
                  * extent that falls inside of the logged extent.
@@ -3733,18 +3680,16 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
                 list_for_each_entry(sum, &ordered->list, list) {
                         ret = btrfs_csum_file_blocks(trans, log, sum);
                         if (ret)
-                                goto unlocked;
+                                break;
                 }
-
         }
-unlocked:
 
-        if (!mod_len || ret)
+        if (*ordered_io_error || !mod_len || ret || skip_csum)
                 return ret;
 
         if (em->compress_type) {
                 csum_offset = 0;
-                csum_len = block_len;
+                csum_len = max(em->block_len, em->orig_block_len);
         } else {
                 csum_offset = mod_start - em->start;
                 csum_len = mod_len;
@@ -3771,11 +3716,106 @@ unlocked:
         return ret;
 }
 
+static int log_one_extent(struct btrfs_trans_handle *trans,
+                          struct inode *inode, struct btrfs_root *root,
+                          const struct extent_map *em,
+                          struct btrfs_path *path,
+                          const struct list_head *logged_list,
+                          struct btrfs_log_ctx *ctx)
+{
+        struct btrfs_root *log = root->log_root;
+        struct btrfs_file_extent_item *fi;
+        struct extent_buffer *leaf;
+        struct btrfs_map_token token;
+        struct btrfs_key key;
+        u64 extent_offset = em->start - em->orig_start;
+        u64 block_len;
+        int ret;
+        int extent_inserted = 0;
+        bool ordered_io_err = false;
+
+        ret = wait_ordered_extents(trans, inode, root, em, logged_list,
+                                   &ordered_io_err);
+        if (ret)
+                return ret;
+
+        if (ordered_io_err) {
+                ctx->io_err = -EIO;
+                return 0;
+        }
+
+        btrfs_init_map_token(&token);
+
+        ret = __btrfs_drop_extents(trans, log, inode, path, em->start,
+                                   em->start + em->len, NULL, 0, 1,
+                                   sizeof(*fi), &extent_inserted);
+        if (ret)
+                return ret;
+
+        if (!extent_inserted) {
+                key.objectid = btrfs_ino(inode);
+                key.type = BTRFS_EXTENT_DATA_KEY;
+                key.offset = em->start;
+
+                ret = btrfs_insert_empty_item(trans, log, path, &key,
+                                              sizeof(*fi));
+                if (ret)
+                        return ret;
+        }
+        leaf = path->nodes[0];
+        fi = btrfs_item_ptr(leaf, path->slots[0],
+                            struct btrfs_file_extent_item);
+
+        btrfs_set_token_file_extent_generation(leaf, fi, em->generation,
+                                               &token);
+        if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+                btrfs_set_token_file_extent_type(leaf, fi,
+                                                 BTRFS_FILE_EXTENT_PREALLOC,
+                                                 &token);
+        else
+                btrfs_set_token_file_extent_type(leaf, fi,
+                                                 BTRFS_FILE_EXTENT_REG,
+                                                 &token);
+
+        block_len = max(em->block_len, em->orig_block_len);
+        if (em->compress_type != BTRFS_COMPRESS_NONE) {
+                btrfs_set_token_file_extent_disk_bytenr(leaf, fi,
+                                                        em->block_start,
+                                                        &token);
+                btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, block_len,
+                                                           &token);
+        } else if (em->block_start < EXTENT_MAP_LAST_BYTE) {
+                btrfs_set_token_file_extent_disk_bytenr(leaf, fi,
+                                                        em->block_start -
+                                                        extent_offset, &token);
+                btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, block_len,
+                                                           &token);
+        } else {
+                btrfs_set_token_file_extent_disk_bytenr(leaf, fi, 0, &token);
+                btrfs_set_token_file_extent_disk_num_bytes(leaf, fi, 0,
+                                                           &token);
+        }
+
+        btrfs_set_token_file_extent_offset(leaf, fi, extent_offset, &token);
+        btrfs_set_token_file_extent_num_bytes(leaf, fi, em->len, &token);
+        btrfs_set_token_file_extent_ram_bytes(leaf, fi, em->ram_bytes, &token);
+        btrfs_set_token_file_extent_compression(leaf, fi, em->compress_type,
+                                                &token);
+        btrfs_set_token_file_extent_encryption(leaf, fi, 0, &token);
+        btrfs_set_token_file_extent_other_encoding(leaf, fi, 0, &token);
+        btrfs_mark_buffer_dirty(leaf);
+
+        btrfs_release_path(path);
+
+        return ret;
+}
+
 static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
                                      struct btrfs_root *root,
                                      struct inode *inode,
                                      struct btrfs_path *path,
-                                     struct list_head *logged_list)
+                                     struct list_head *logged_list,
+                                     struct btrfs_log_ctx *ctx)
 {
         struct extent_map *em, *n;
         struct list_head extents;
@@ -3833,7 +3873,8 @@ process:
 
                 write_unlock(&tree->lock);
 
-                ret = log_one_extent(trans, inode, root, em, path, logged_list);
+                ret = log_one_extent(trans, inode, root, em, path, logged_list,
+                                     ctx);
                 write_lock(&tree->lock);
                 clear_em_logging(tree, em);
                 free_extent_map(em);
@@ -3863,7 +3904,8 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
                            struct btrfs_root *root, struct inode *inode,
                            int inode_only,
                            const loff_t start,
-                           const loff_t end)
+                           const loff_t end,
+                           struct btrfs_log_ctx *ctx)
 {
         struct btrfs_path *path;
         struct btrfs_path *dst_path;
@@ -3964,7 +4006,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
                 err = ret;
                 goto out_unlock;
         }
-        path->keep_locks = 1;
 
         while (1) {
                 ins_nr = 0;
@@ -4049,7 +4090,7 @@ log_extents:
         btrfs_release_path(dst_path);
         if (fast_search) {
                 ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
-                                                &logged_list);
+                                                &logged_list, ctx);
                 if (ret) {
                         err = ret;
                         goto out_unlock;
@@ -4239,7 +4280,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
         if (ret)
                 goto end_no_trans;
 
-        ret = btrfs_log_inode(trans, root, inode, inode_only, start, end);
+        ret = btrfs_log_inode(trans, root, inode, inode_only, start, end, ctx);
         if (ret)
                 goto end_trans;
 
@@ -4268,7 +4309,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
                 if (BTRFS_I(inode)->generation >
                     root->fs_info->last_trans_committed) {
                         ret = btrfs_log_inode(trans, root, inode, inode_only,
-                                              0, LLONG_MAX);
+                                              0, LLONG_MAX, ctx);
                         if (ret)
                                 goto end_trans;
                 }
@@ -4360,7 +4401,7 @@ int btrfs_recover_log_trees(struct btrfs_root *log_root_tree)
 again:
         key.objectid = BTRFS_TREE_LOG_OBJECTID;
         key.offset = (u64)-1;
-        btrfs_set_key_type(&key, BTRFS_ROOT_ITEM_KEY);
+        key.type = BTRFS_ROOT_ITEM_KEY;
 
         while (1) {
                 ret = btrfs_search_slot(NULL, log_root_tree, &key, path, 0, 0);