From b25f0d0012d11f2fb3df855fb62b86e5f63fdd68 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Wed, 11 Apr 2018 11:21:17 +0300 Subject: btrfs: Use while loop instead of labels in __endio_write_update_ordered Currently __endio_write_update_ordered uses labels to implement what is essentially a simple while loop. This makes the code more cumbersome to follow than it actually has to be. No functional changes. No xfstest regressions were found during testing. Signed-off-by: Nikolay Borisov Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/inode.c | 52 +++++++++++++++++++++++++--------------------------- 1 file changed, 25 insertions(+), 27 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 0b86cf10cf2a..be17cfdcbcf5 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8131,7 +8131,6 @@ static void __endio_write_update_ordered(struct inode *inode, u64 ordered_offset = offset; u64 ordered_bytes = bytes; u64 last_offset; - int ret; if (btrfs_is_free_space_inode(BTRFS_I(inode))) { wq = fs_info->endio_freespace_worker; @@ -8141,32 +8140,31 @@ static void __endio_write_update_ordered(struct inode *inode, func = btrfs_endio_write_helper; } -again: - last_offset = ordered_offset; - ret = btrfs_dec_test_first_ordered_pending(inode, &ordered, - &ordered_offset, - ordered_bytes, - uptodate); - if (!ret) - goto out_test; - - btrfs_init_work(&ordered->work, func, finish_ordered_fn, NULL, NULL); - btrfs_queue_work(wq, &ordered->work); -out_test: - /* - * If btrfs_dec_test_ordered_pending does not find any ordered extent - * in the range, we can exit. - */ - if (ordered_offset == last_offset) - return; - /* - * our bio might span multiple ordered extents. If we haven't - * completed the accounting for the whole dio, go back and try again - */ - if (ordered_offset < offset + bytes) { - ordered_bytes = offset + bytes - ordered_offset; - ordered = NULL; - goto again; + while (ordered_offset < offset + bytes) { + last_offset = ordered_offset; + if (btrfs_dec_test_first_ordered_pending(inode, &ordered, + &ordered_offset, + ordered_bytes, + uptodate)) { + btrfs_init_work(&ordered->work, func, + finish_ordered_fn, + NULL, NULL); + btrfs_queue_work(wq, &ordered->work); + } + /* + * If btrfs_dec_test_ordered_pending does not find any ordered + * extent in the range, we can exit. + */ + if (ordered_offset == last_offset) + return; + /* + * Our bio might span multiple ordered extents. In this case + * we keep goin until we have accounted the whole dio. + */ + if (ordered_offset < offset + bytes) { + ordered_bytes = offset + bytes - ordered_offset; + ordered = NULL; + } } } -- cgit v1.2.3 From f46b24c9457143a367c6707eac82d546e2bcf280 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Tue, 3 Apr 2018 21:45:57 +0200 Subject: btrfs: use fs_info for btrfs_handle_em_exist tracepoint We really want to know to which filesystem the extent map events belong, but as it cannot be reached from the extent_map pointers, we need to pass it down the callchain. Reviewed-by: Nikolay Borisov Signed-off-by: David Sterba --- fs/btrfs/extent_map.c | 6 ++++-- fs/btrfs/extent_map.h | 3 ++- fs/btrfs/inode.c | 2 +- fs/btrfs/tests/extent-map-tests.c | 8 ++++---- include/trace/events/btrfs.h | 12 +++++++----- 5 files changed, 18 insertions(+), 13 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 1b8a078f92eb..6648d55e5339 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -518,6 +518,7 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree, /** * btrfs_add_extent_mapping - add extent mapping into em_tree + * @fs_info - used for tracepoint * @em_tree - the extent tree into which we want to insert the extent mapping * @em_in - extent we are inserting * @start - start of the logical range btrfs_get_extent() is requesting @@ -535,7 +536,8 @@ static noinline int merge_extent_mapping(struct extent_map_tree *em_tree, * Return 0 on success, otherwise -EEXIST. * */ -int btrfs_add_extent_mapping(struct extent_map_tree *em_tree, +int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info, + struct extent_map_tree *em_tree, struct extent_map **em_in, u64 start, u64 len) { int ret; @@ -553,7 +555,7 @@ int btrfs_add_extent_mapping(struct extent_map_tree *em_tree, existing = search_extent_mapping(em_tree, start, len); - trace_btrfs_handle_em_exist(existing, em, start, len); + trace_btrfs_handle_em_exist(fs_info, existing, em, start, len); /* * existing will always be non-NULL, since there must be diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h index 5fcb80a6ce37..25d985e7532a 100644 --- a/fs/btrfs/extent_map.h +++ b/fs/btrfs/extent_map.h @@ -92,7 +92,8 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len, u64 gen void clear_em_logging(struct extent_map_tree *tree, struct extent_map *em); struct extent_map *search_extent_mapping(struct extent_map_tree *tree, u64 start, u64 len); -int btrfs_add_extent_mapping(struct extent_map_tree *em_tree, +int btrfs_add_extent_mapping(struct btrfs_fs_info *fs_info, + struct extent_map_tree *em_tree, struct extent_map **em_in, u64 start, u64 len); #endif diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index be17cfdcbcf5..f4447986263a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7083,7 +7083,7 @@ insert: err = 0; write_lock(&em_tree->lock); - err = btrfs_add_extent_mapping(em_tree, &em, start, len); + err = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len); write_unlock(&em_tree->lock); out: diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c index 8a39de4453e4..9c051c4a3315 100644 --- a/fs/btrfs/tests/extent-map-tests.c +++ b/fs/btrfs/tests/extent-map-tests.c @@ -91,7 +91,7 @@ static void test_case_1(struct btrfs_fs_info *fs_info, em->len = len; em->block_start = start; em->block_len = len; - ret = btrfs_add_extent_mapping(em_tree, &em, em->start, em->len); + ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len); if (ret) test_msg("case1 [%llu %llu]: ret %d\n", start, start + len, ret); if (em && @@ -155,7 +155,7 @@ static void test_case_2(struct btrfs_fs_info *fs_info, em->len = SZ_1K; em->block_start = EXTENT_MAP_INLINE; em->block_len = (u64)-1; - ret = btrfs_add_extent_mapping(em_tree, &em, em->start, em->len); + ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, em->start, em->len); if (ret) test_msg("case2 [0 1K]: ret %d\n", ret); if (em && @@ -201,7 +201,7 @@ static void __test_case_3(struct btrfs_fs_info *fs_info, em->len = SZ_16K; em->block_start = 0; em->block_len = SZ_16K; - ret = btrfs_add_extent_mapping(em_tree, &em, start, len); + ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len); if (ret) test_msg("case3 [0x%llx 0x%llx): ret %d\n", start, start + len, ret); @@ -288,7 +288,7 @@ static void __test_case_4(struct btrfs_fs_info *fs_info, em->len = SZ_32K; em->block_start = 0; em->block_len = SZ_32K; - ret = btrfs_add_extent_mapping(em_tree, &em, start, len); + ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len); if (ret) test_msg("case4 [0x%llx 0x%llx): ret %d\n", start, len, ret); diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 9be469706d30..d78d8ab4bc86 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -256,11 +256,13 @@ TRACE_EVENT_CONDITION(btrfs_get_extent, TRACE_EVENT(btrfs_handle_em_exist, - TP_PROTO(const struct extent_map *existing, const struct extent_map *map, u64 start, u64 len), + TP_PROTO(struct btrfs_fs_info *fs_info, + const struct extent_map *existing, const struct extent_map *map, + u64 start, u64 len), - TP_ARGS(existing, map, start, len), + TP_ARGS(fs_info, existing, map, start, len), - TP_STRUCT__entry( + TP_STRUCT__entry_btrfs( __field( u64, e_start ) __field( u64, e_len ) __field( u64, map_start ) @@ -269,7 +271,7 @@ TRACE_EVENT(btrfs_handle_em_exist, __field( u64, len ) ), - TP_fast_assign( + TP_fast_assign_btrfs(fs_info, __entry->e_start = existing->start; __entry->e_len = existing->len; __entry->map_start = map->start; @@ -278,7 +280,7 @@ TRACE_EVENT(btrfs_handle_em_exist, __entry->len = len; ), - TP_printk("start=%llu len=%llu " + TP_printk_btrfs("start=%llu len=%llu " "existing(start=%llu len=%llu) " "em(start=%llu len=%llu)", __entry->start, -- cgit v1.2.3 From ec42f167348a1949ac309532aa34760cfc96c92f Mon Sep 17 00:00:00 2001 From: Misono Tomohiro Date: Wed, 18 Apr 2018 11:34:13 +0900 Subject: btrfs: Move may_destroy_subvol() from ioctl.c to inode.c This is a preparation work to refactor btrfs_ioctl_snap_destroy() and to allow rmdir(2) to delete an empty subvolume. Signed-off-by: Tomohiro Misono Reviewed-by: David Sterba [ minor update of the function comment ] Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 1 + fs/btrfs/inode.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/ioctl.c | 54 ------------------------------------------------------ 3 files changed, 56 insertions(+), 54 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 15e34172cdf0..fe7e5177119d 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3197,6 +3197,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *dir, u64 objectid, const char *name, int name_len); +noinline int may_destroy_subvol(struct btrfs_root *root); int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, int front); int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f4447986263a..1e51ca4489da 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4326,6 +4326,61 @@ out: return ret; } +/* + * Helper to check if the subvolume references other subvolumes or if it's + * default. + */ +noinline int may_destroy_subvol(struct btrfs_root *root) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_path *path; + struct btrfs_dir_item *di; + struct btrfs_key key; + u64 dir_id; + int ret; + + path = btrfs_alloc_path(); + if (!path) + return -ENOMEM; + + /* Make sure this root isn't set as the default subvol */ + dir_id = btrfs_super_root_dir(fs_info->super_copy); + di = btrfs_lookup_dir_item(NULL, fs_info->tree_root, path, + dir_id, "default", 7, 0); + if (di && !IS_ERR(di)) { + btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key); + if (key.objectid == root->root_key.objectid) { + ret = -EPERM; + btrfs_err(fs_info, + "deleting default subvolume %llu is not allowed", + key.objectid); + goto out; + } + btrfs_release_path(path); + } + + key.objectid = root->root_key.objectid; + key.type = BTRFS_ROOT_REF_KEY; + key.offset = (u64)-1; + + ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0); + if (ret < 0) + goto out; + BUG_ON(ret == 0); + + ret = 0; + if (path->slots[0] > 0) { + path->slots[0]--; + btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); + if (key.objectid == root->root_key.objectid && + key.type == BTRFS_ROOT_REF_KEY) + ret = -ENOTEMPTY; + } +out: + btrfs_free_path(path); + return ret; +} + static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 61a58214681c..592ef10a6604 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1832,60 +1832,6 @@ out: return ret; } -/* - * helper to check if the subvolume references other subvolumes - */ -static noinline int may_destroy_subvol(struct btrfs_root *root) -{ - struct btrfs_fs_info *fs_info = root->fs_info; - struct btrfs_path *path; - struct btrfs_dir_item *di; - struct btrfs_key key; - u64 dir_id; - int ret; - - path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; - - /* Make sure this root isn't set as the default subvol */ - dir_id = btrfs_super_root_dir(fs_info->super_copy); - di = btrfs_lookup_dir_item(NULL, fs_info->tree_root, path, - dir_id, "default", 7, 0); - if (di && !IS_ERR(di)) { - btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key); - if (key.objectid == root->root_key.objectid) { - ret = -EPERM; - btrfs_err(fs_info, - "deleting default subvolume %llu is not allowed", - key.objectid); - goto out; - } - btrfs_release_path(path); - } - - key.objectid = root->root_key.objectid; - key.type = BTRFS_ROOT_REF_KEY; - key.offset = (u64)-1; - - ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0); - if (ret < 0) - goto out; - BUG_ON(ret == 0); - - ret = 0; - if (path->slots[0] > 0) { - path->slots[0]--; - btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); - if (key.objectid == root->root_key.objectid && - key.type == BTRFS_ROOT_REF_KEY) - ret = -ENOTEMPTY; - } -out: - btrfs_free_path(path); - return ret; -} - static noinline int key_in_sk(struct btrfs_key *key, struct btrfs_ioctl_search_key *sk) { -- cgit v1.2.3 From f60a2364a4eee4d8c335775a3a0c39aa955aa6b7 Mon Sep 17 00:00:00 2001 From: Misono Tomohiro Date: Wed, 18 Apr 2018 11:34:52 +0900 Subject: btrfs: Factor out the main deletion process from btrfs_ioctl_snap_destroy() Factor out the second half of btrfs_ioctl_snap_destroy() as btrfs_delete_subvolume(), which performs some subvolume specific checks before deletion: 1. send is not in progress 2. the subvolume is not the default subvolume 3. the subvolume does not contain other subvolumes and actual deletion process. btrfs_delete_subvolume() requires inode_lock for both @dir and inode of @dentry. The remaining part of btrfs_ioctl_snap_destroy() is mainly permission checks. Note that call of d_delete() is not included in btrfs_delete_subvolume() as this function will also be used by btrfs_rmdir() to delete an empty subvolume and in that case d_delete() is called in VFS layer. As a result, btrfs_unlink_subvol() and may_destroy_subvol() become static functions. No functional changes. Signed-off-by: Tomohiro Misono Reviewed-by: David Sterba [ minor comment updates ] Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 6 +-- fs/btrfs/inode.c | 143 ++++++++++++++++++++++++++++++++++++++++++++++++++++++- fs/btrfs/ioctl.c | 131 +------------------------------------------------- 3 files changed, 144 insertions(+), 136 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index fe7e5177119d..3a382ed94030 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3193,11 +3193,7 @@ int btrfs_unlink_inode(struct btrfs_trans_handle *trans, int btrfs_add_link(struct btrfs_trans_handle *trans, struct btrfs_inode *parent_inode, struct btrfs_inode *inode, const char *name, int name_len, int add_backref, u64 index); -int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - struct inode *dir, u64 objectid, - const char *name, int name_len); -noinline int may_destroy_subvol(struct btrfs_root *root); +int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry); int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len, int front); int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 1e51ca4489da..6e03e7991a5d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4245,7 +4245,7 @@ out: return ret; } -int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, +static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *dir, u64 objectid, const char *name, int name_len) @@ -4330,7 +4330,7 @@ out: * Helper to check if the subvolume references other subvolumes or if it's * default. */ -noinline int may_destroy_subvol(struct btrfs_root *root) +static noinline int may_destroy_subvol(struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_path *path; @@ -4381,6 +4381,145 @@ out: return ret; } +int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) +{ + struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb); + struct btrfs_root *root = BTRFS_I(dir)->root; + struct inode *inode = d_inode(dentry); + struct btrfs_root *dest = BTRFS_I(inode)->root; + struct btrfs_trans_handle *trans; + struct btrfs_block_rsv block_rsv; + u64 root_flags; + u64 qgroup_reserved; + int ret; + int err; + + /* + * Don't allow to delete a subvolume with send in progress. This is + * inside the inode lock so the error handling that has to drop the bit + * again is not run concurrently. + */ + spin_lock(&dest->root_item_lock); + root_flags = btrfs_root_flags(&dest->root_item); + if (dest->send_in_progress == 0) { + btrfs_set_root_flags(&dest->root_item, + root_flags | BTRFS_ROOT_SUBVOL_DEAD); + spin_unlock(&dest->root_item_lock); + } else { + spin_unlock(&dest->root_item_lock); + btrfs_warn(fs_info, + "attempt to delete subvolume %llu during send", + dest->root_key.objectid); + return -EPERM; + } + + down_write(&fs_info->subvol_sem); + + err = may_destroy_subvol(dest); + if (err) + goto out_up_write; + + btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP); + /* + * One for dir inode, + * two for dir entries, + * two for root ref/backref. + */ + err = btrfs_subvolume_reserve_metadata(root, &block_rsv, + 5, &qgroup_reserved, true); + if (err) + goto out_up_write; + + trans = btrfs_start_transaction(root, 0); + if (IS_ERR(trans)) { + err = PTR_ERR(trans); + goto out_release; + } + trans->block_rsv = &block_rsv; + trans->bytes_reserved = block_rsv.size; + + btrfs_record_snapshot_destroy(trans, BTRFS_I(dir)); + + ret = btrfs_unlink_subvol(trans, root, dir, + dest->root_key.objectid, + dentry->d_name.name, + dentry->d_name.len); + if (ret) { + err = ret; + btrfs_abort_transaction(trans, ret); + goto out_end_trans; + } + + btrfs_record_root_in_trans(trans, dest); + + memset(&dest->root_item.drop_progress, 0, + sizeof(dest->root_item.drop_progress)); + dest->root_item.drop_level = 0; + btrfs_set_root_refs(&dest->root_item, 0); + + if (!test_and_set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &dest->state)) { + ret = btrfs_insert_orphan_item(trans, + fs_info->tree_root, + dest->root_key.objectid); + if (ret) { + btrfs_abort_transaction(trans, ret); + err = ret; + goto out_end_trans; + } + } + + ret = btrfs_uuid_tree_rem(trans, fs_info, dest->root_item.uuid, + BTRFS_UUID_KEY_SUBVOL, + dest->root_key.objectid); + if (ret && ret != -ENOENT) { + btrfs_abort_transaction(trans, ret); + err = ret; + goto out_end_trans; + } + if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) { + ret = btrfs_uuid_tree_rem(trans, fs_info, + dest->root_item.received_uuid, + BTRFS_UUID_KEY_RECEIVED_SUBVOL, + dest->root_key.objectid); + if (ret && ret != -ENOENT) { + btrfs_abort_transaction(trans, ret); + err = ret; + goto out_end_trans; + } + } + +out_end_trans: + trans->block_rsv = NULL; + trans->bytes_reserved = 0; + ret = btrfs_end_transaction(trans); + if (ret && !err) + err = ret; + inode->i_flags |= S_DEAD; +out_release: + btrfs_subvolume_release_metadata(fs_info, &block_rsv); +out_up_write: + up_write(&fs_info->subvol_sem); + if (err) { + spin_lock(&dest->root_item_lock); + root_flags = btrfs_root_flags(&dest->root_item); + btrfs_set_root_flags(&dest->root_item, + root_flags & ~BTRFS_ROOT_SUBVOL_DEAD); + spin_unlock(&dest->root_item_lock); + } else { + d_invalidate(dentry); + btrfs_invalidate_inodes(dest); + ASSERT(dest->send_in_progress == 0); + + /* the last ref */ + if (dest->ino_cache_inode) { + iput(dest->ino_cache_inode); + dest->ino_cache_inode = NULL; + } + } + + return err; +} + static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(dentry); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 592ef10a6604..7beec1bf6d4b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2255,12 +2255,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_root *dest = NULL; struct btrfs_ioctl_vol_args *vol_args; - struct btrfs_trans_handle *trans; - struct btrfs_block_rsv block_rsv; - u64 root_flags; - u64 qgroup_reserved; int namelen; - int ret; int err = 0; if (!S_ISDIR(dir->i_mode)) @@ -2344,133 +2339,11 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, } inode_lock(inode); - - /* - * Don't allow to delete a subvolume with send in progress. This is - * inside the i_mutex so the error handling that has to drop the bit - * again is not run concurrently. - */ - spin_lock(&dest->root_item_lock); - root_flags = btrfs_root_flags(&dest->root_item); - if (dest->send_in_progress == 0) { - btrfs_set_root_flags(&dest->root_item, - root_flags | BTRFS_ROOT_SUBVOL_DEAD); - spin_unlock(&dest->root_item_lock); - } else { - spin_unlock(&dest->root_item_lock); - btrfs_warn(fs_info, - "Attempt to delete subvolume %llu during send", - dest->root_key.objectid); - err = -EPERM; - goto out_unlock_inode; - } - - down_write(&fs_info->subvol_sem); - - err = may_destroy_subvol(dest); - if (err) - goto out_up_write; - - btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP); - /* - * One for dir inode, two for dir entries, two for root - * ref/backref. - */ - err = btrfs_subvolume_reserve_metadata(root, &block_rsv, - 5, &qgroup_reserved, true); - if (err) - goto out_up_write; - - trans = btrfs_start_transaction(root, 0); - if (IS_ERR(trans)) { - err = PTR_ERR(trans); - goto out_release; - } - trans->block_rsv = &block_rsv; - trans->bytes_reserved = block_rsv.size; - - btrfs_record_snapshot_destroy(trans, BTRFS_I(dir)); - - ret = btrfs_unlink_subvol(trans, root, dir, - dest->root_key.objectid, - dentry->d_name.name, - dentry->d_name.len); - if (ret) { - err = ret; - btrfs_abort_transaction(trans, ret); - goto out_end_trans; - } - - btrfs_record_root_in_trans(trans, dest); - - memset(&dest->root_item.drop_progress, 0, - sizeof(dest->root_item.drop_progress)); - dest->root_item.drop_level = 0; - btrfs_set_root_refs(&dest->root_item, 0); - - if (!test_and_set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &dest->state)) { - ret = btrfs_insert_orphan_item(trans, - fs_info->tree_root, - dest->root_key.objectid); - if (ret) { - btrfs_abort_transaction(trans, ret); - err = ret; - goto out_end_trans; - } - } - - ret = btrfs_uuid_tree_rem(trans, fs_info, dest->root_item.uuid, - BTRFS_UUID_KEY_SUBVOL, - dest->root_key.objectid); - if (ret && ret != -ENOENT) { - btrfs_abort_transaction(trans, ret); - err = ret; - goto out_end_trans; - } - if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) { - ret = btrfs_uuid_tree_rem(trans, fs_info, - dest->root_item.received_uuid, - BTRFS_UUID_KEY_RECEIVED_SUBVOL, - dest->root_key.objectid); - if (ret && ret != -ENOENT) { - btrfs_abort_transaction(trans, ret); - err = ret; - goto out_end_trans; - } - } - -out_end_trans: - trans->block_rsv = NULL; - trans->bytes_reserved = 0; - ret = btrfs_end_transaction(trans); - if (ret && !err) - err = ret; - inode->i_flags |= S_DEAD; -out_release: - btrfs_subvolume_release_metadata(fs_info, &block_rsv); -out_up_write: - up_write(&fs_info->subvol_sem); - if (err) { - spin_lock(&dest->root_item_lock); - root_flags = btrfs_root_flags(&dest->root_item); - btrfs_set_root_flags(&dest->root_item, - root_flags & ~BTRFS_ROOT_SUBVOL_DEAD); - spin_unlock(&dest->root_item_lock); - } -out_unlock_inode: + err = btrfs_delete_subvolume(dir, dentry); inode_unlock(inode); - if (!err) { - d_invalidate(dentry); - btrfs_invalidate_inodes(dest); + if (!err) d_delete(dentry); - ASSERT(dest->send_in_progress == 0); - /* the last ref */ - if (dest->ino_cache_inode) { - iput(dest->ino_cache_inode); - dest->ino_cache_inode = NULL; - } - } out_dput: dput(dentry); out_unlock_dir: -- cgit v1.2.3 From a79a464d5675dbca49d6121425e8eb3571da29f7 Mon Sep 17 00:00:00 2001 From: Misono Tomohiro Date: Wed, 18 Apr 2018 11:35:31 +0900 Subject: btrfs: Allow rmdir(2) to delete an empty subvolume Change the behavior of rmdir(2) and allow it to delete an empty subvolume by using btrfs_delete_subvolume() which is used by btrfs_ioctl_snap_destroy(). This is a change in behaviour and has been requested by users. Deleting the subvolume by ioctl requires root permissions while the rmdir way does works with standard tools and syscalls for all users that can access the subvolume. The main usecase is to allow 'rm -rf /path/with/subvols' to simply work. We were not able to find any nasty usability surprises, the intention is to do the destructive rm. Without allowing rmdir, this would have to be followed by the ioctl subvolume deletion, which is more of an annoyance. Implementation details: The required lock for @dir and inode of @dentry is already acquired in vfs layer. We need some check before deleting a subvolume. Permission check is done in vfs layer, emptiness check is in btrfs_rmdir() and additional check (i.e. neither the subvolume is a default subvolume nor send is in progress) is in btrfs_delete_subvolume(). Note that in btrfs_ioctl_snap_destroy(), d_delete() is called after btrfs_delete_subvolume(). For rmdir(2), d_delete() is called in vfs layer later. Tested-by: Goffredo Baroncelli Signed-off-by: Tomohiro Misono Reviewed-by: David Sterba [ enhance changelog ] Signed-off-by: David Sterba --- fs/btrfs/inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6e03e7991a5d..d722a30b0b74 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4531,7 +4531,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry) if (inode->i_size > BTRFS_EMPTY_DIR_SIZE) return -ENOTEMPTY; if (btrfs_ino(BTRFS_I(inode)) == BTRFS_FIRST_FREE_OBJECTID) - return -EPERM; + return btrfs_delete_subvolume(dir, dentry); trans = __unlink_start_trans(dir); if (IS_ERR(trans)) -- cgit v1.2.3 From 477a30ba5f8dfb3fe951ed0352277bb26a616cb8 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Thu, 19 Apr 2018 10:46:34 +0300 Subject: btrfs: Sink extent_tree arguments in try_release_extent_mapping This function already gets the page from which the two extent trees are referenced. Simplify its signature by moving the code getting the trees inside the function. No functional changes. Signed-off-by: Nikolay Borisov Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 6 +++--- fs/btrfs/extent_io.h | 4 +--- fs/btrfs/inode.c | 8 +------- 3 files changed, 5 insertions(+), 13 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 9a521e5e297d..c7ae18f8db90 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4238,13 +4238,13 @@ static int try_release_extent_state(struct extent_map_tree *map, * in the range corresponding to the page, both state records and extent * map records are removed */ -int try_release_extent_mapping(struct extent_map_tree *map, - struct extent_io_tree *tree, struct page *page, - gfp_t mask) +int try_release_extent_mapping(struct page *page, gfp_t mask) { struct extent_map *em; u64 start = page_offset(page); u64 end = start + PAGE_SIZE - 1; + struct extent_io_tree *tree = &BTRFS_I(page->mapping->host)->io_tree; + struct extent_map_tree *map = &BTRFS_I(page->mapping->host)->extent_tree; if (gfpflags_allow_blocking(mask) && page->mapping->host->i_size > SZ_16M) { diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index c5e80d60d71b..29d47383b113 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -270,9 +270,7 @@ typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode, int create); void extent_io_tree_init(struct extent_io_tree *tree, void *private_data); -int try_release_extent_mapping(struct extent_map_tree *map, - struct extent_io_tree *tree, struct page *page, - gfp_t mask); +int try_release_extent_mapping(struct page *page, gfp_t mask); int try_release_extent_buffer(struct page *page); int lock_extent_bits(struct extent_io_tree *tree, u64 start, u64 end, struct extent_state **cached); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d722a30b0b74..6853cd836a41 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8913,13 +8913,7 @@ btrfs_readpages(struct file *file, struct address_space *mapping, } static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags) { - struct extent_io_tree *tree; - struct extent_map_tree *map; - int ret; - - tree = &BTRFS_I(page->mapping->host)->io_tree; - map = &BTRFS_I(page->mapping->host)->extent_tree; - ret = try_release_extent_mapping(map, tree, page, gfp_flags); + int ret = try_release_extent_mapping(page, gfp_flags); if (ret == 1) { ClearPagePrivate(page); set_page_private(page, 0); -- cgit v1.2.3 From 2a3ff0adc92069122a75c3e37271d7ab7ce0dc1c Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Thu, 19 Apr 2018 10:46:36 +0300 Subject: btrfs: Remove redundant tree argument from extent_readpages This function is called only from btrfs_readpage and is already passed the mapping. Simplify its signature by moving the code obtaining reference to the extent tree in the function. No functional changes. Signed-off-by: Nikolay Borisov Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 6 +++--- fs/btrfs/extent_io.h | 5 ++--- fs/btrfs/inode.c | 5 ++--- 3 files changed, 7 insertions(+), 9 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index d1a4434152da..20bb056b7eca 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4126,9 +4126,8 @@ int extent_writepages(struct extent_io_tree *tree, return ret; } -int extent_readpages(struct extent_io_tree *tree, - struct address_space *mapping, - struct list_head *pages, unsigned nr_pages) +int extent_readpages(struct address_space *mapping, struct list_head *pages, + unsigned nr_pages) { struct bio *bio = NULL; unsigned page_idx; @@ -4136,6 +4135,7 @@ int extent_readpages(struct extent_io_tree *tree, struct page *pagepool[16]; struct page *page; struct extent_map *em_cached = NULL; + struct extent_io_tree *tree = &BTRFS_I(mapping->host)->io_tree; int nr = 0; u64 prev_em_start = (u64)-1; diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 29d47383b113..752ad87e40d5 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -416,9 +416,8 @@ int extent_writepages(struct extent_io_tree *tree, struct writeback_control *wbc); int btree_write_cache_pages(struct address_space *mapping, struct writeback_control *wbc); -int extent_readpages(struct extent_io_tree *tree, - struct address_space *mapping, - struct list_head *pages, unsigned nr_pages); +int extent_readpages(struct address_space *mapping, struct list_head *pages, + unsigned nr_pages); int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); void set_page_extent_mapped(struct page *page); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6853cd836a41..53ba8e8f1148 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8907,10 +8907,9 @@ static int btrfs_readpages(struct file *file, struct address_space *mapping, struct list_head *pages, unsigned nr_pages) { - struct extent_io_tree *tree; - tree = &BTRFS_I(mapping->host)->io_tree; - return extent_readpages(tree, mapping, pages, nr_pages); + return extent_readpages(mapping, pages, nr_pages); } + static int __btrfs_releasepage(struct page *page, gfp_t gfp_flags) { int ret = try_release_extent_mapping(page, gfp_flags); -- cgit v1.2.3 From 81f1d39035dfc58b265b3ad68e2dcbb61b7d8263 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Thu, 19 Apr 2018 10:46:37 +0300 Subject: btrfs: Use list_empty instead of list_empty_careful list_empty_careful usually is a signal of something tricky going on. Its usage in btrfs is actually not needed since both lists it's used on are local to a function and cannot be modified concurrently. So switch to plain list_empty. No functional changes. Signed-off-by: Nikolay Borisov Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/inode.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 53ba8e8f1148..0aadf17c528f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -10254,7 +10254,7 @@ out: btrfs_wait_and_free_delalloc_work(work); } - if (!list_empty_careful(&splice)) { + if (!list_empty(&splice)) { spin_lock(&root->delalloc_lock); list_splice_tail(&splice, &root->delalloc_inodes); spin_unlock(&root->delalloc_lock); @@ -10316,7 +10316,7 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput, ret = 0; out: - if (!list_empty_careful(&splice)) { + if (!list_empty(&splice)) { spin_lock(&fs_info->delalloc_root_lock); list_splice_tail(&splice, &fs_info->delalloc_roots); spin_unlock(&fs_info->delalloc_root_lock); -- cgit v1.2.3 From 8ae225a8a4f9054ffc6566e14aaf05dfc559743e Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Thu, 19 Apr 2018 10:46:38 +0300 Subject: btrfs: Remove tree argument from extent_writepages It can be directly referenced from the passed address_space so do that. No functional changes. Signed-off-by: Nikolay Borisov Signed-off-by: David Sterba --- fs/btrfs/extent_io.c | 5 ++--- fs/btrfs/extent_io.h | 3 +-- fs/btrfs/inode.c | 5 +---- 3 files changed, 4 insertions(+), 9 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 20bb056b7eca..af2f0408c6e4 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4109,14 +4109,13 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end, return ret; } -int extent_writepages(struct extent_io_tree *tree, - struct address_space *mapping, +int extent_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret = 0; struct extent_page_data epd = { .bio = NULL, - .tree = tree, + .tree = &BTRFS_I(mapping->host)->io_tree, .extent_locked = 0, .sync_io = wbc->sync_mode == WB_SYNC_ALL, }; diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 752ad87e40d5..0bfd4aeb822d 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -411,8 +411,7 @@ int extent_invalidatepage(struct extent_io_tree *tree, int extent_write_full_page(struct page *page, struct writeback_control *wbc); int extent_write_locked_range(struct inode *inode, u64 start, u64 end, int mode); -int extent_writepages(struct extent_io_tree *tree, - struct address_space *mapping, +int extent_writepages(struct address_space *mapping, struct writeback_control *wbc); int btree_write_cache_pages(struct address_space *mapping, struct writeback_control *wbc); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 0aadf17c528f..775249f03dd3 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8897,10 +8897,7 @@ static int btrfs_writepage(struct page *page, struct writeback_control *wbc) static int btrfs_writepages(struct address_space *mapping, struct writeback_control *wbc) { - struct extent_io_tree *tree; - - tree = &BTRFS_I(mapping->host)->io_tree; - return extent_writepages(tree, mapping, wbc); + return extent_writepages(mapping, wbc); } static int -- cgit v1.2.3 From 40012f96b6765e588d8ffd7508d492339f2b9212 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Thu, 19 Apr 2018 10:46:39 +0300 Subject: btrfs: Remove btrfs_wait_and_free_delalloc_work This function is called from only 1 place and is effectively a wrapper over wait_completion/kfree. It doesn't really bring any value having those two calls in a separate function. Just open code it and remove it. No functional changes. Signed-off-by: Nikolay Borisov Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 1 - fs/btrfs/inode.c | 9 ++------- 2 files changed, 2 insertions(+), 8 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3a382ed94030..de86f2217816 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3173,7 +3173,6 @@ struct btrfs_delalloc_work { struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode, int delay_iput); -void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work); struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode, struct page *page, size_t pg_offset, u64 start, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 775249f03dd3..ce2f9288df3e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -10186,12 +10186,6 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode, return work; } -void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work) -{ - wait_for_completion(&work->completion); - kfree(work); -} - /* * some fairly slow code that needs optimization. This walks the list * of all the inodes with pending delalloc and forces them to disk. @@ -10248,7 +10242,8 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput, out: list_for_each_entry_safe(work, next, &works, list) { list_del_init(&work->list); - btrfs_wait_and_free_delalloc_work(work); + wait_for_completion(&work->completion); + kfree(work); } if (!list_empty(&splice)) { -- cgit v1.2.3 From 82b3e53b8da19b25ef36b68316374df47f8fa268 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 23 Apr 2018 10:54:13 +0300 Subject: btrfs: Remove delayed_iput parameter of btrfs_start_delalloc_roots This parameter was introduced alongside the function in eb73c1b7cea7 ("Btrfs: introduce per-subvolume delalloc inode list") to avoid deadlocks since this function was used in the transaction commit path. However, commit 8d875f95da43 ("btrfs: disable strict file flushes for renames and truncates") removed that usage, rendering the parameter obsolete. Signed-off-by: Nikolay Borisov Reviewed-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 3 +-- fs/btrfs/dev-replace.c | 2 +- fs/btrfs/extent-tree.c | 4 ++-- fs/btrfs/inode.c | 5 ++--- fs/btrfs/ioctl.c | 2 +- 5 files changed, 7 insertions(+), 9 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 9cc90f407cae..0d15d98a964a 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3205,8 +3205,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, u32 min_type); int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput); -int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput, - int nr); +int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr); int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end, unsigned int extra_bits, struct extent_state **cached_state, int dedupe); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index d097701d494d..12f703e127dd 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -594,7 +594,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, * flush all outstanding I/O and inode extent mappings before the * copy operation is declared as being finished */ - ret = btrfs_start_delalloc_roots(fs_info, 0, -1); + ret = btrfs_start_delalloc_roots(fs_info, -1); if (ret) { mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return ret; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 888a47894c30..38dd98bc50d7 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4343,7 +4343,7 @@ commit_trans: need_commit--; if (need_commit > 0) { - btrfs_start_delalloc_roots(fs_info, 0, -1); + btrfs_start_delalloc_roots(fs_info, -1); btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1); } @@ -4796,7 +4796,7 @@ static void btrfs_writeback_inodes_sb_nr(struct btrfs_fs_info *fs_info, * the filesystem is readonly(all dirty pages are written to * the disk). */ - btrfs_start_delalloc_roots(fs_info, 0, nr_items); + btrfs_start_delalloc_roots(fs_info, nr_items); if (!current->journal_info) btrfs_wait_ordered_roots(fs_info, nr_items, 0, (u64)-1); } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index ce2f9288df3e..c2bb7c8e1fda 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -10269,8 +10269,7 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput) return ret; } -int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput, - int nr) +int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr) { struct btrfs_root *root; struct list_head splice; @@ -10293,7 +10292,7 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int delay_iput, &fs_info->delalloc_roots); spin_unlock(&fs_info->delalloc_root_lock); - ret = __start_delalloc_inodes(root, delay_iput, nr); + ret = __start_delalloc_inodes(root, 0, nr); btrfs_put_fs_root(root); if (ret < 0) goto out; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 397f026b1e4c..67db5f6b0476 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -5307,7 +5307,7 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_SYNC: { int ret; - ret = btrfs_start_delalloc_roots(fs_info, 0, -1); + ret = btrfs_start_delalloc_roots(fs_info, -1); if (ret) return ret; ret = btrfs_sync_fs(inode->i_sb, 1); -- cgit v1.2.3 From 76f32e240ee6a3c1903ce8f1e934b43f2971bffc Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 23 Apr 2018 10:54:14 +0300 Subject: btrfs: Remove delayed_iput parameter from btrfs_start_delalloc_inodes It's always set to 0, so just remove it and collapse the constant value to the only function we are passing it. Signed-off-by: Nikolay Borisov Reviewed-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 2 +- fs/btrfs/inode.c | 4 ++-- fs/btrfs/ioctl.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0d15d98a964a..0dbb5a19d977 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3204,7 +3204,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, struct inode *inode, u64 new_size, u32 min_type); -int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput); +int btrfs_start_delalloc_inodes(struct btrfs_root *root); int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr); int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end, unsigned int extra_bits, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c2bb7c8e1fda..c6ff72a1ff10 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -10255,7 +10255,7 @@ out: return ret; } -int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput) +int btrfs_start_delalloc_inodes(struct btrfs_root *root) { struct btrfs_fs_info *fs_info = root->fs_info; int ret; @@ -10263,7 +10263,7 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root, int delay_iput) if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) return -EROFS; - ret = __start_delalloc_inodes(root, delay_iput, -1); + ret = __start_delalloc_inodes(root, 0, -1); if (ret > 0) ret = 0; return ret; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 67db5f6b0476..b708f12292b6 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -640,7 +640,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, wait_event(root->subv_writers->wait, percpu_counter_sum(&root->subv_writers->counter) == 0); - ret = btrfs_start_delalloc_inodes(root, 0); + ret = btrfs_start_delalloc_inodes(root); if (ret) goto dec_and_free; -- cgit v1.2.3 From 4fbb514785154ac2eff2a85d60fc0974207171b2 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 23 Apr 2018 10:54:15 +0300 Subject: btrfs: Remove delay_iput parameter from __start_delalloc_inodes It's always set to 0 so remove it. Signed-off-by: Nikolay Borisov Reviewed-by: Qu Wenruo [ rename to start_delalloc_inodes ] Signed-off-by: David Sterba --- fs/btrfs/inode.c | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c6ff72a1ff10..20a385b0668f 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -10190,8 +10190,7 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode, * some fairly slow code that needs optimization. This walks the list * of all the inodes with pending delalloc and forces them to disk. */ -static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput, - int nr) +static int start_delalloc_inodes(struct btrfs_root *root, int nr) { struct btrfs_inode *binode; struct inode *inode; @@ -10219,12 +10218,9 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput, } spin_unlock(&root->delalloc_lock); - work = btrfs_alloc_delalloc_work(inode, delay_iput); + work = btrfs_alloc_delalloc_work(inode, 0); if (!work) { - if (delay_iput) - btrfs_add_delayed_iput(inode); - else - iput(inode); + iput(inode); ret = -ENOMEM; goto out; } @@ -10263,7 +10259,7 @@ int btrfs_start_delalloc_inodes(struct btrfs_root *root) if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) return -EROFS; - ret = __start_delalloc_inodes(root, 0, -1); + ret = start_delalloc_inodes(root, -1); if (ret > 0) ret = 0; return ret; @@ -10292,7 +10288,7 @@ int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr) &fs_info->delalloc_roots); spin_unlock(&fs_info->delalloc_root_lock); - ret = __start_delalloc_inodes(root, 0, nr); + ret = start_delalloc_inodes(root, nr); btrfs_put_fs_root(root); if (ret < 0) goto out; -- cgit v1.2.3 From 076da91cd9ec4032f88bb30a162d576e9e46c2d6 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Mon, 23 Apr 2018 10:54:16 +0300 Subject: btrfs: Remove delayed_iput member from btrfs_delalloc_work When allocating a delalloc work we are always setting the delayed_iput to 0. So remove the delay_iput member of btrfs_delalloc_work, as a result also remove it as a parameter from btrfs_alloc_delalloc_work since it's not used anymore. Signed-off-by: Nikolay Borisov Reviewed-by: Qu Wenruo Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 4 +--- fs/btrfs/inode.c | 11 +++-------- 2 files changed, 4 insertions(+), 11 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0dbb5a19d977..6cdc6d0e8525 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3169,14 +3169,12 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode, /* inode.c */ struct btrfs_delalloc_work { struct inode *inode; - int delay_iput; struct completion completion; struct list_head list; struct btrfs_work work; }; -struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode, - int delay_iput); +struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode); struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode, struct page *page, size_t pg_offset, u64 start, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 20a385b0668f..4e10bb1f300e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -10159,15 +10159,11 @@ static void btrfs_run_delalloc_work(struct btrfs_work *work) &BTRFS_I(inode)->runtime_flags)) filemap_flush(inode->i_mapping); - if (delalloc_work->delay_iput) - btrfs_add_delayed_iput(inode); - else - iput(inode); + iput(inode); complete(&delalloc_work->completion); } -struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode, - int delay_iput) +struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode) { struct btrfs_delalloc_work *work; @@ -10178,7 +10174,6 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode, init_completion(&work->completion); INIT_LIST_HEAD(&work->list); work->inode = inode; - work->delay_iput = delay_iput; WARN_ON_ONCE(!inode); btrfs_init_work(&work->work, btrfs_flush_delalloc_helper, btrfs_run_delalloc_work, NULL, NULL); @@ -10218,7 +10213,7 @@ static int start_delalloc_inodes(struct btrfs_root *root, int nr) } spin_unlock(&root->delalloc_lock); - work = btrfs_alloc_delalloc_work(inode, 0); + work = btrfs_alloc_delalloc_work(inode); if (!work) { iput(inode); ret = -ENOMEM; -- cgit v1.2.3 From 3a2f8c07e1d60739eb6b90ffba41bd1d0de33fc2 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Tue, 24 Apr 2018 17:23:59 +0300 Subject: btrfs: Unexport btrfs_alloc_delalloc_work It's used only in inode.c so makes no sense to have it exported. Also move the definition of btrfs_delalloc_work to inode.c since it's used only this file. Signed-off-by: Nikolay Borisov Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 9 --------- fs/btrfs/inode.c | 9 ++++++++- 2 files changed, 8 insertions(+), 10 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 6cdc6d0e8525..27aa9b58b001 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3167,15 +3167,6 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode, struct extent_map *em); /* inode.c */ -struct btrfs_delalloc_work { - struct inode *inode; - struct completion completion; - struct list_head list; - struct btrfs_work work; -}; - -struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode); - struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode, struct page *page, size_t pg_offset, u64 start, u64 len, int create); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 4e10bb1f300e..29374d31f1de 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -10146,6 +10146,13 @@ static int btrfs_rename2(struct inode *old_dir, struct dentry *old_dentry, return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry, flags); } +struct btrfs_delalloc_work { + struct inode *inode; + struct completion completion; + struct list_head list; + struct btrfs_work work; +}; + static void btrfs_run_delalloc_work(struct btrfs_work *work) { struct btrfs_delalloc_work *delalloc_work; @@ -10163,7 +10170,7 @@ static void btrfs_run_delalloc_work(struct btrfs_work *work) complete(&delalloc_work->completion); } -struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode) +static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode) { struct btrfs_delalloc_work *work; -- cgit v1.2.3 From 7c8a0d363aca1447a0e82e31c54d220e3ecd6a87 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Fri, 27 Apr 2018 12:21:52 +0300 Subject: btrfs: Add assert in __btrfs_del_delalloc_inode The invariant is that when nr_delalloc_inodes is 0 then the root mustn't have any inodes on its delalloc inodes list. Signed-off-by: Nikolay Borisov Signed-off-by: David Sterba --- fs/btrfs/inode.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 29374d31f1de..a7529827d89c 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1754,6 +1754,7 @@ void __btrfs_del_delalloc_inode(struct btrfs_root *root, &inode->runtime_flags); root->nr_delalloc_inodes--; if (!root->nr_delalloc_inodes) { + ASSERT(list_empty(&root->delalloc_inodes)); spin_lock(&fs_info->delalloc_root_lock); BUG_ON(list_empty(&root->delalloc_root)); list_del_init(&root->delalloc_root); -- cgit v1.2.3 From 7a1b1e70280a9e0185a8ef80a8b4dbf4dc87772a Mon Sep 17 00:00:00 2001 From: Al Viro Date: Sun, 13 May 2018 19:03:18 +0100 Subject: btrfs: take the last remnants of ->d_fsdata use out [spotted while going through ->d_fsdata handling around d_splice_alias(); don't really care which tree that goes through] The only thing even looking at ->d_fsdata in there (since 2012) had been kfree(dentry->d_fsdata) in btrfs_dentry_delete(). Which, incidentally, is all btrfs_dentry_delete() does. Signed-off-by: Al Viro Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/inode.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a7529827d89c..6757fe136177 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6045,11 +6045,6 @@ static int btrfs_dentry_delete(const struct dentry *dentry) return 0; } -static void btrfs_dentry_release(struct dentry *dentry) -{ - kfree(dentry->d_fsdata); -} - static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { @@ -10844,5 +10839,4 @@ static const struct inode_operations btrfs_symlink_inode_operations = { const struct dentry_operations btrfs_dentry_operations = { .d_delete = btrfs_dentry_delete, - .d_release = btrfs_dentry_release, }; -- cgit v1.2.3 From 093258e6ebaf178bb25da514f0d1f744968cc900 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Mon, 26 Feb 2018 16:15:17 +0100 Subject: btrfs: replace waitqueue_actvie with cond_wake_up Use the wrappers and reduce the amount of low-level details about the waitqueue management. Reviewed-by: Nikolay Borisov Signed-off-by: David Sterba --- fs/btrfs/compression.c | 7 +------ fs/btrfs/delayed-inode.c | 9 +++------ fs/btrfs/dev-replace.c | 10 ++++------ fs/btrfs/extent-tree.c | 7 +------ fs/btrfs/inode.c | 9 +++------ fs/btrfs/locking.c | 34 +++++++++++----------------------- fs/btrfs/ordered-data.c | 14 ++++---------- fs/btrfs/transaction.c | 7 +------ fs/btrfs/tree-log.c | 34 ++++++++++++---------------------- 9 files changed, 40 insertions(+), 91 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 1061575a7d25..d3e447b45bf7 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -990,12 +990,7 @@ static void __free_workspace(int type, struct list_head *workspace, btrfs_compress_op[idx]->free_workspace(workspace); atomic_dec(total_ws); wake: - /* - * Make sure counter is updated before we wake up waiters. - */ - smp_mb(); - if (waitqueue_active(ws_wait)) - wake_up(ws_wait); + cond_wake_up(ws_wait); } static void free_workspace(int type, struct list_head *ws) diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index a8d492dbd3e7..fe6caa7e698b 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -460,13 +460,10 @@ static void finish_one_item(struct btrfs_delayed_root *delayed_root) { int seq = atomic_inc_return(&delayed_root->items_seq); - /* - * atomic_dec_return implies a barrier for waitqueue_active - */ + /* atomic_dec_return implies a barrier */ if ((atomic_dec_return(&delayed_root->items) < - BTRFS_DELAYED_BACKGROUND || seq % BTRFS_DELAYED_BATCH == 0) && - waitqueue_active(&delayed_root->wait)) - wake_up(&delayed_root->wait); + BTRFS_DELAYED_BACKGROUND || seq % BTRFS_DELAYED_BATCH == 0)) + cond_wake_up_nomb(&delayed_root->wait); } static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item) diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 12f703e127dd..89946285203d 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -1009,9 +1009,9 @@ void btrfs_dev_replace_clear_lock_blocking( ASSERT(atomic_read(&dev_replace->read_locks) > 0); ASSERT(atomic_read(&dev_replace->blocking_readers) > 0); read_lock(&dev_replace->lock); - if (atomic_dec_and_test(&dev_replace->blocking_readers) && - waitqueue_active(&dev_replace->read_lock_wq)) - wake_up(&dev_replace->read_lock_wq); + /* Barrier implied by atomic_dec_and_test */ + if (atomic_dec_and_test(&dev_replace->blocking_readers)) + cond_wake_up_nomb(&dev_replace->read_lock_wq); } void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info) @@ -1022,9 +1022,7 @@ void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info) void btrfs_bio_counter_sub(struct btrfs_fs_info *fs_info, s64 amount) { percpu_counter_sub(&fs_info->bio_counter, amount); - - if (waitqueue_active(&fs_info->replace_wait)) - wake_up(&fs_info->replace_wait); + cond_wake_up_nomb(&fs_info->replace_wait); } void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 5be54cedb56f..fa2ed14532c1 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -11081,12 +11081,7 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range) void btrfs_end_write_no_snapshotting(struct btrfs_root *root) { percpu_counter_dec(&root->subv_writers->counter); - /* - * Make sure counter is updated before we wake up waiters. - */ - smp_mb(); - if (waitqueue_active(&root->subv_writers->wait)) - wake_up(&root->subv_writers->wait); + cond_wake_up(&root->subv_writers->wait); } int btrfs_start_write_no_snapshotting(struct btrfs_root *root) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6757fe136177..563e63fa2fce 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1156,13 +1156,10 @@ static noinline void async_cow_submit(struct btrfs_work *work) nr_pages = (async_cow->end - async_cow->start + PAGE_SIZE) >> PAGE_SHIFT; - /* - * atomic_sub_return implies a barrier for waitqueue_active - */ + /* atomic_sub_return implies a barrier */ if (atomic_sub_return(nr_pages, &fs_info->async_delalloc_pages) < - 5 * SZ_1M && - waitqueue_active(&fs_info->async_submit_wait)) - wake_up(&fs_info->async_submit_wait); + 5 * SZ_1M) + cond_wake_up_nomb(&fs_info->async_submit_wait); if (async_cow->inode) submit_compressed_extents(async_cow->inode, async_cow); diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index e4faefac9d16..1da768e5ef75 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -66,22 +66,16 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw) write_lock(&eb->lock); WARN_ON(atomic_read(&eb->spinning_writers)); atomic_inc(&eb->spinning_writers); - /* - * atomic_dec_and_test implies a barrier for waitqueue_active - */ - if (atomic_dec_and_test(&eb->blocking_writers) && - waitqueue_active(&eb->write_lock_wq)) - wake_up(&eb->write_lock_wq); + /* atomic_dec_and_test implies a barrier */ + if (atomic_dec_and_test(&eb->blocking_writers)) + cond_wake_up_nomb(&eb->write_lock_wq); } else if (rw == BTRFS_READ_LOCK_BLOCKING) { BUG_ON(atomic_read(&eb->blocking_readers) == 0); read_lock(&eb->lock); atomic_inc(&eb->spinning_readers); - /* - * atomic_dec_and_test implies a barrier for waitqueue_active - */ - if (atomic_dec_and_test(&eb->blocking_readers) && - waitqueue_active(&eb->read_lock_wq)) - wake_up(&eb->read_lock_wq); + /* atomic_dec_and_test implies a barrier */ + if (atomic_dec_and_test(&eb->blocking_readers)) + cond_wake_up_nomb(&eb->read_lock_wq); } } @@ -221,12 +215,9 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb) } btrfs_assert_tree_read_locked(eb); WARN_ON(atomic_read(&eb->blocking_readers) == 0); - /* - * atomic_dec_and_test implies a barrier for waitqueue_active - */ - if (atomic_dec_and_test(&eb->blocking_readers) && - waitqueue_active(&eb->read_lock_wq)) - wake_up(&eb->read_lock_wq); + /* atomic_dec_and_test implies a barrier */ + if (atomic_dec_and_test(&eb->blocking_readers)) + cond_wake_up_nomb(&eb->read_lock_wq); atomic_dec(&eb->read_locks); } @@ -275,12 +266,9 @@ void btrfs_tree_unlock(struct extent_buffer *eb) if (blockers) { WARN_ON(atomic_read(&eb->spinning_writers)); atomic_dec(&eb->blocking_writers); - /* - * Make sure counter is updated before we wake up waiters. - */ + /* Use the lighter barrier after atomic */ smp_mb__after_atomic(); - if (waitqueue_active(&eb->write_lock_wq)) - wake_up(&eb->write_lock_wq); + cond_wake_up_nomb(&eb->write_lock_wq); } else { WARN_ON(atomic_read(&eb->spinning_writers) != 1); atomic_dec(&eb->spinning_writers); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 6db8bb2f2c28..2e1a1694a33d 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -343,11 +343,8 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode, if (entry->bytes_left == 0) { ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); - /* - * Implicit memory barrier after test_and_set_bit - */ - if (waitqueue_active(&entry->wait)) - wake_up(&entry->wait); + /* test_and_set_bit implies a barrier */ + cond_wake_up_nomb(&entry->wait); } else { ret = 1; } @@ -410,11 +407,8 @@ have_entry: if (entry->bytes_left == 0) { ret = test_and_set_bit(BTRFS_ORDERED_IO_DONE, &entry->flags); - /* - * Implicit memory barrier after test_and_set_bit - */ - if (waitqueue_active(&entry->wait)) - wake_up(&entry->wait); + /* test_and_set_bit implies a barrier */ + cond_wake_up_nomb(&entry->wait); } else { ret = 1; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index c944b4769e3c..ff841abb756e 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -877,12 +877,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, atomic_dec(&cur_trans->num_writers); extwriter_counter_dec(cur_trans, trans->type); - /* - * Make sure counter is updated before we wake up waiters. - */ - smp_mb(); - if (waitqueue_active(&cur_trans->writer_wait)) - wake_up(&cur_trans->writer_wait); + cond_wake_up(&cur_trans->writer_wait); btrfs_put_transaction(cur_trans); if (current->journal_info == trans) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 2009cea65d89..f8220ec02036 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -222,11 +222,8 @@ int btrfs_pin_log_trans(struct btrfs_root *root) void btrfs_end_log_trans(struct btrfs_root *root) { if (atomic_dec_and_test(&root->log_writers)) { - /* - * Implicit memory barrier after atomic_dec_and_test - */ - if (waitqueue_active(&root->log_writer_wait)) - wake_up(&root->log_writer_wait); + /* atomic_dec_and_test implies a barrier */ + cond_wake_up_nomb(&root->log_writer_wait); } } @@ -2988,11 +2985,8 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, mutex_lock(&log_root_tree->log_mutex); if (atomic_dec_and_test(&log_root_tree->log_writers)) { - /* - * Implicit memory barrier after atomic_dec_and_test - */ - if (waitqueue_active(&log_root_tree->log_writer_wait)) - wake_up(&log_root_tree->log_writer_wait); + /* atomic_dec_and_test implies a barrier */ + cond_wake_up_nomb(&log_root_tree->log_writer_wait); } if (ret) { @@ -3116,13 +3110,11 @@ out_wake_log_root: mutex_unlock(&log_root_tree->log_mutex); /* - * The barrier before waitqueue_active is needed so all the updates - * above are seen by the woken threads. It might not be necessary, but - * proving that seems to be hard. + * The barrier before waitqueue_active (in cond_wake_up) is needed so + * all the updates above are seen by the woken threads. It might not be + * necessary, but proving that seems to be hard. */ - smp_mb(); - if (waitqueue_active(&log_root_tree->log_commit_wait[index2])) - wake_up(&log_root_tree->log_commit_wait[index2]); + cond_wake_up(&log_root_tree->log_commit_wait[index2]); out: mutex_lock(&root->log_mutex); btrfs_remove_all_log_ctxs(root, index1, ret); @@ -3131,13 +3123,11 @@ out: mutex_unlock(&root->log_mutex); /* - * The barrier before waitqueue_active is needed so all the updates - * above are seen by the woken threads. It might not be necessary, but - * proving that seems to be hard. + * The barrier before waitqueue_active (in cond_wake_up) is needed so + * all the updates above are seen by the woken threads. It might not be + * necessary, but proving that seems to be hard. */ - smp_mb(); - if (waitqueue_active(&root->log_commit_wait[index1])) - wake_up(&root->log_commit_wait[index1]); + cond_wake_up(&root->log_commit_wait[index1]); return ret; } -- cgit v1.2.3 From 20a68004022d5b894efdf5959ebd538b8e91ec73 Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Fri, 27 Apr 2018 14:36:24 +0300 Subject: btrfs: Unexport and rename btrfs_invalidate_inodes This function is no longer used outside of inode.c so just make it static. At the same time give a more becoming name, since it's not really invalidating the inodes but just calling d_prune_alias. Last, but not least - move the function above the sole caller to avoid introducing yet-another-pointless forward declaration. Signed-off-by: Nikolay Borisov Reviewed-by: David Sterba Reviewed-by: Anand Jain Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 1 - fs/btrfs/inode.c | 129 ++++++++++++++++++++++++++++--------------------------- 2 files changed, 65 insertions(+), 65 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3d6b2dc86c8f..bfa96697209a 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3231,7 +3231,6 @@ int btrfs_orphan_cleanup(struct btrfs_root *root); void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size); -void btrfs_invalidate_inodes(struct btrfs_root *root); void btrfs_add_delayed_iput(struct inode *inode); void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info); int btrfs_prealloc_file_range(struct inode *inode, int mode, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 563e63fa2fce..766bd286869d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4379,6 +4379,70 @@ out: return ret; } +/* Delete all dentries for inodes belonging to the root */ +static void btrfs_prune_dentries(struct btrfs_root *root) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + struct rb_node *node; + struct rb_node *prev; + struct btrfs_inode *entry; + struct inode *inode; + u64 objectid = 0; + + if (!test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) + WARN_ON(btrfs_root_refs(&root->root_item) != 0); + + spin_lock(&root->inode_lock); +again: + node = root->inode_tree.rb_node; + prev = NULL; + while (node) { + prev = node; + entry = rb_entry(node, struct btrfs_inode, rb_node); + + if (objectid < btrfs_ino(BTRFS_I(&entry->vfs_inode))) + node = node->rb_left; + else if (objectid > btrfs_ino(BTRFS_I(&entry->vfs_inode))) + node = node->rb_right; + else + break; + } + if (!node) { + while (prev) { + entry = rb_entry(prev, struct btrfs_inode, rb_node); + if (objectid <= btrfs_ino(BTRFS_I(&entry->vfs_inode))) { + node = prev; + break; + } + prev = rb_next(prev); + } + } + while (node) { + entry = rb_entry(node, struct btrfs_inode, rb_node); + objectid = btrfs_ino(BTRFS_I(&entry->vfs_inode)) + 1; + inode = igrab(&entry->vfs_inode); + if (inode) { + spin_unlock(&root->inode_lock); + if (atomic_read(&inode->i_count) > 1) + d_prune_aliases(inode); + /* + * btrfs_drop_inode will have it removed from the inode + * cache when its usage count hits zero. + */ + iput(inode); + cond_resched(); + spin_lock(&root->inode_lock); + goto again; + } + + if (cond_resched_lock(&root->inode_lock)) + goto again; + + node = rb_next(node); + } + spin_unlock(&root->inode_lock); +} + int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) { struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb); @@ -4505,7 +4569,7 @@ out_up_write: spin_unlock(&dest->root_item_lock); } else { d_invalidate(dentry); - btrfs_invalidate_inodes(dest); + btrfs_prune_dentries(dest); ASSERT(dest->send_in_progress == 0); /* the last ref */ @@ -5818,69 +5882,6 @@ static void inode_tree_del(struct inode *inode) } } -void btrfs_invalidate_inodes(struct btrfs_root *root) -{ - struct btrfs_fs_info *fs_info = root->fs_info; - struct rb_node *node; - struct rb_node *prev; - struct btrfs_inode *entry; - struct inode *inode; - u64 objectid = 0; - - if (!test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) - WARN_ON(btrfs_root_refs(&root->root_item) != 0); - - spin_lock(&root->inode_lock); -again: - node = root->inode_tree.rb_node; - prev = NULL; - while (node) { - prev = node; - entry = rb_entry(node, struct btrfs_inode, rb_node); - - if (objectid < btrfs_ino(BTRFS_I(&entry->vfs_inode))) - node = node->rb_left; - else if (objectid > btrfs_ino(BTRFS_I(&entry->vfs_inode))) - node = node->rb_right; - else - break; - } - if (!node) { - while (prev) { - entry = rb_entry(prev, struct btrfs_inode, rb_node); - if (objectid <= btrfs_ino(BTRFS_I(&entry->vfs_inode))) { - node = prev; - break; - } - prev = rb_next(prev); - } - } - while (node) { - entry = rb_entry(node, struct btrfs_inode, rb_node); - objectid = btrfs_ino(BTRFS_I(&entry->vfs_inode)) + 1; - inode = igrab(&entry->vfs_inode); - if (inode) { - spin_unlock(&root->inode_lock); - if (atomic_read(&inode->i_count) > 1) - d_prune_aliases(inode); - /* - * btrfs_drop_inode will have it removed from - * the inode cache when its usage count - * hits zero. - */ - iput(inode); - cond_resched(); - spin_lock(&root->inode_lock); - goto again; - } - - if (cond_resched_lock(&root->inode_lock)) - goto again; - - node = rb_next(node); - } - spin_unlock(&root->inode_lock); -} static int btrfs_init_locked_inode(struct inode *inode, void *p) { -- cgit v1.2.3 From 7b6a221e5b21fdd4fd0f8a2ebf3f251338a10fea Mon Sep 17 00:00:00 2001 From: David Sterba Date: Mon, 26 Mar 2018 18:40:21 +0200 Subject: btrfs: rename btrfs_update_iflags to reflect which flags it touches The btrfs inode flag flavour is now simply called 'inode flags' and the vfs inode are i_flags. Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 2 +- fs/btrfs/inode.c | 4 ++-- fs/btrfs/ioctl.c | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index bfa96697209a..71aecf0b7cf5 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3249,7 +3249,7 @@ void btrfs_test_inode_set_ops(struct inode *inode); long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg); int btrfs_ioctl_get_supported_features(void __user *arg); -void btrfs_update_iflags(struct inode *inode); +void btrfs_sync_inode_flags_to_i_flags(struct inode *inode); int btrfs_is_empty_uuid(u8 *uuid); int btrfs_defrag_file(struct inode *inode, struct file *file, struct btrfs_ioctl_defrag_range_args *range, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 766bd286869d..cbcda4e296f8 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3929,7 +3929,7 @@ cache_acl: break; } - btrfs_update_iflags(inode); + btrfs_sync_inode_flags_to_i_flags(inode); return 0; make_bad: @@ -6458,7 +6458,7 @@ static void btrfs_inherit_iflags(struct inode *inode, struct inode *dir) BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM; } - btrfs_update_iflags(inode); + btrfs_sync_inode_flags_to_i_flags(inode); } static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 48e2ddff32bd..47e7e2822c60 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -136,7 +136,7 @@ static unsigned int btrfs_flags_to_ioctl(unsigned int flags) /* * Update inode->i_flags based on the btrfs internal flags. */ -void btrfs_update_iflags(struct inode *inode) +void btrfs_sync_inode_flags_to_i_flags(struct inode *inode) { struct btrfs_inode *ip = BTRFS_I(inode); unsigned int new_fl = 0; @@ -317,7 +317,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) goto out_drop; } - btrfs_update_iflags(inode); + btrfs_sync_inode_flags_to_i_flags(inode); inode_inc_iversion(inode); inode->i_ctime = current_time(inode); ret = btrfs_update_inode(trans, root, inode); -- cgit v1.2.3 From d1342aadbd9fcc82fd6e24c7f0443a43fe4714c7 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 11 May 2018 13:13:29 -0700 Subject: Btrfs: update stale comments referencing vmtruncate() Commit a41ad394a03b ("Btrfs: convert to the new truncate sequence") changed btrfs_setsize() to call truncate_setsize() instead of vmtruncate() but didn't update the comment above it. truncate_setsize() never fails (the IS_SWAPFILE() check happens elsewhere), so remove the comment. Additionally, the comment above btrfs_page_mkwrite() references vmtruncate(), but truncate_setsize() does the size write and page locking now. Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- fs/btrfs/inode.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index cbcda4e296f8..a1d352fbe647 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5369,7 +5369,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) 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 */ @@ -9044,8 +9043,8 @@ again: * * We are not allowed to take the i_mutex here so we have to play games to * protect against truncate races as the page could now be beyond EOF. Because - * vmtruncate() writes the inode size before removing pages, once we have the - * page lock we can determine safely if the page is beyond EOF. If it is not + * truncate_setsize() writes the inode size before removing pages, once we have + * the page lock we can determine safely if the page is beyond EOF. If it is not * beyond EOF, then the page is guaranteed safe against truncation until we * unlock the page. */ -- cgit v1.2.3 From fd86a3a31506fe4602ad056bc06a16f20e8eb30f Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 11 May 2018 13:13:30 -0700 Subject: Btrfs: fix error handling in btrfs_truncate_inode_items() btrfs_truncate_inode_items() uses two variables for error handling, ret and err. These are not handled consistently, leading to a couple of bugs. - Errors from btrfs_del_items() are handled but not propagated to the caller - If btrfs_run_delayed_refs() fails and aborts the transaction, we continue running Just use ret everywhere and simplify things a bit, fixing both of these issues. Fixes: 79787eaab461 ("btrfs: replace many BUG_ONs with proper error handling") Fixes: 1262133b8d6f ("Btrfs: account for crcs in delayed ref processing") Reviewed-by: Nikolay Borisov Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- fs/btrfs/inode.c | 55 ++++++++++++++++++++++++++++--------------------------- 1 file changed, 28 insertions(+), 27 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index a1d352fbe647..e0863deea1a5 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4705,7 +4705,6 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, int pending_del_slot = 0; int extent_type = -1; int ret; - int err = 0; u64 ino = btrfs_ino(BTRFS_I(inode)); u64 bytes_deleted = 0; bool be_nice = false; @@ -4757,22 +4756,19 @@ search_again: * up a huge file in a single leaf. Most of the time that * bytes_deleted is > 0, it will be huge by the time we get here */ - if (be_nice && bytes_deleted > SZ_32M) { - if (btrfs_should_end_transaction(trans)) { - err = -EAGAIN; - goto error; - } + if (be_nice && bytes_deleted > SZ_32M && + btrfs_should_end_transaction(trans)) { + ret = -EAGAIN; + goto out; } - path->leave_spinning = 1; ret = btrfs_search_slot(trans, root, &key, path, -1, 1); - if (ret < 0) { - err = ret; + if (ret < 0) goto out; - } if (ret > 0) { + ret = 0; /* there are no items in the tree for us to truncate, we're * done */ @@ -4883,7 +4879,7 @@ search_again: * We have to bail so the last_size is set to * just before this extent. */ - err = NEED_TRUNCATE_BLOCK; + ret = NEED_TRUNCATE_BLOCK; break; } @@ -4950,7 +4946,7 @@ delete: pending_del_nr); if (ret) { btrfs_abort_transaction(trans, ret); - goto error; + break; } pending_del_nr = 0; } @@ -4961,8 +4957,8 @@ delete: trans->delayed_ref_updates = 0; ret = btrfs_run_delayed_refs(trans, updates * 2); - if (ret && !err) - err = ret; + if (ret) + break; } } /* @@ -4970,8 +4966,8 @@ delete: * and let the transaction restart */ if (should_end) { - err = -EAGAIN; - goto error; + ret = -EAGAIN; + break; } goto search_again; } else { @@ -4979,32 +4975,37 @@ delete: } } out: - if (pending_del_nr) { - ret = btrfs_del_items(trans, root, path, pending_del_slot, + if (ret >= 0 && pending_del_nr) { + int err; + + err = btrfs_del_items(trans, root, path, pending_del_slot, pending_del_nr); - if (ret) - btrfs_abort_transaction(trans, ret); + if (err) { + btrfs_abort_transaction(trans, err); + ret = err; + } } -error: if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { ASSERT(last_size >= new_size); - if (!err && last_size > new_size) + if (!ret && last_size > new_size) last_size = new_size; btrfs_ordered_update_i_size(inode, last_size, NULL); } btrfs_free_path(path); - if (be_nice && bytes_deleted > SZ_32M) { + if (be_nice && bytes_deleted > SZ_32M && (ret >= 0 || ret == -EAGAIN)) { unsigned long updates = trans->delayed_ref_updates; + int err; + if (updates) { trans->delayed_ref_updates = 0; - ret = btrfs_run_delayed_refs(trans, updates * 2); - if (ret && !err) - err = ret; + err = btrfs_run_delayed_refs(trans, updates * 2); + if (err) + ret = err; } } - return err; + return ret; } /* -- cgit v1.2.3 From 0552210997badb6a60740a26ff9d976a416510f0 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 11 May 2018 13:13:31 -0700 Subject: Btrfs: don't BUG_ON() in btrfs_truncate_inode_items() btrfs_free_extent() can fail because of ENOMEM. There's no reason to panic here, we can just abort the transaction. Fixes: f4b9aa8d3b87 ("btrfs_truncate") Reviewed-by: Nikolay Borisov Signed-off-by: Omar Sandoval Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/inode.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index e0863deea1a5..c966fd6e2cef 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4918,7 +4918,10 @@ delete: extent_num_bytes, 0, btrfs_header_owner(leaf), ino, extent_offset); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, ret); + break; + } if (btrfs_should_throttle_delayed_refs(trans, fs_info)) btrfs_async_run_delayed_refs(fs_info, trans->delayed_ref_updates * 2, -- cgit v1.2.3 From f7e9e8fc792fe2f823ff7d64d23f4363b3f2203a Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 11 May 2018 13:13:32 -0700 Subject: Btrfs: stop creating orphan items for truncate Currently, we insert an orphan item during a truncate so that if there's a crash, we don't leak extents past the on-disk i_size. However, since commit 7f4f6e0a3f6d ("Btrfs: only update disk_i_size as we remove extents"), we keep disk_i_size in sync with the extent items as we truncate, so orphan cleanup will never have any extents to remove. Don't bother with the superfluous orphan item. Reviewed-by: Josef Bacik Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- fs/btrfs/free-space-cache.c | 6 +- fs/btrfs/inode.c | 159 ++++++++++++++------------------------------ 2 files changed, 51 insertions(+), 114 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index e5b569bebc73..d5f80cb300be 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -253,10 +253,8 @@ int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans, truncate_pagecache(inode, 0); /* - * We don't need an orphan item because truncating the free space cache - * will never be split across transactions. - * We don't need to check for -EAGAIN because we're a free space - * cache inode + * We skip the throttling logic for free space cache inodes, so we don't + * need to check for -EAGAIN. */ ret = btrfs_truncate_inode_items(trans, root, inode, 0, BTRFS_EXTENT_DATA_KEY); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c966fd6e2cef..74caec73b7c2 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3346,8 +3346,8 @@ void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans, } /* - * This creates an orphan entry for the given inode in case something goes - * wrong in the middle of an unlink/truncate. + * This creates an orphan entry for the given inode in case something goes wrong + * in the middle of an unlink. * * NOTE: caller of this function should reserve 5 units of metadata for * this function. @@ -3410,7 +3410,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, } } - /* insert an orphan item to track this unlinked/truncated file */ + /* insert an orphan item to track this unlinked file */ if (insert) { ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode)); if (ret) { @@ -3439,8 +3439,8 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, } /* - * We have done the truncate/delete so we can go ahead and remove the orphan - * item for this particular inode. + * We have done the delete so we can go ahead and remove the orphan item for + * this particular inode. */ static int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct btrfs_inode *inode) @@ -3484,7 +3484,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) struct btrfs_trans_handle *trans; struct inode *inode; u64 last_objectid = 0; - int ret = 0, nr_unlink = 0, nr_truncate = 0; + int ret = 0, nr_unlink = 0; if (cmpxchg(&root->orphan_cleanup_state, 0, ORPHAN_CLEANUP_STARTED)) return 0; @@ -3584,12 +3584,31 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) key.offset = found_key.objectid - 1; continue; } + } + /* - * Inode is already gone but the orphan item is still there, - * kill the orphan item. + * If we have an inode with links, there are a couple of + * possibilities. Old kernels (before v3.12) used to create an + * orphan item for truncate indicating that there were possibly + * extent items past i_size that needed to be deleted. In v3.12, + * truncate was changed to update i_size in sync with the extent + * items, but the (useless) orphan item was still created. Since + * v4.18, we don't create the orphan item for truncate at all. + * + * So, this item could mean that we need to do a truncate, but + * only if this filesystem was last used on a pre-v3.12 kernel + * and was not cleanly unmounted. The odds of that are quite + * slim, and it's a pain to do the truncate now, so just delete + * the orphan item. + * + * It's also possible that this orphan item was supposed to be + * deleted but wasn't. The inode number may have been reused, + * but either way, we can delete the orphan item. */ - if (ret == -ENOENT) { + if (ret == -ENOENT || inode->i_nlink) { + if (!ret) + iput(inode); trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { ret = PTR_ERR(trans); @@ -3613,34 +3632,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) &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) { - if (WARN_ON(!S_ISREG(inode->i_mode))) { - iput(inode); - continue; - } - nr_truncate++; - - /* 1 for the orphan item deletion. */ - trans = btrfs_start_transaction(root, 1); - if (IS_ERR(trans)) { - iput(inode); - ret = PTR_ERR(trans); - goto out; - } - ret = btrfs_orphan_add(trans, BTRFS_I(inode)); - btrfs_end_transaction(trans); - if (ret) { - iput(inode); - goto out; - } - - ret = btrfs_truncate(inode, false); - if (ret) - btrfs_orphan_del(NULL, BTRFS_I(inode)); - } else { - nr_unlink++; - } + nr_unlink++; /* this will do delete_inode and everything for us */ iput(inode); @@ -3665,8 +3657,6 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) if (nr_unlink) btrfs_debug(fs_info, "unlinked %d orphans", nr_unlink); - if (nr_truncate) - btrfs_debug(fs_info, "truncated %d orphans", nr_truncate); out: if (ret) @@ -5350,29 +5340,6 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) 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 guarantee from this point on that everything - * will be consistent. - */ - ret = btrfs_orphan_add(trans, BTRFS_I(inode)); - btrfs_end_transaction(trans); - if (ret) - return ret; - truncate_setsize(inode, newsize); /* Disable nonlocked read DIO to avoid the end less truncate */ @@ -5384,29 +5351,16 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr) if (ret && inode->i_nlink) { int err; - /* To get a stable disk_i_size */ - err = btrfs_wait_ordered_range(inode, 0, (u64)-1); - if (err) { - btrfs_orphan_del(NULL, BTRFS_I(inode)); - return err; - } - /* - * failed to truncate, disk_i_size is only adjusted down - * as we remove extents, so it should represent the true - * size of the inode, so reset the in memory size and - * delete our orphan entry. + * Truncate failed, so fix up the in-memory size. We + * adjusted disk_i_size down as we removed extents, so + * wait for disk_i_size to be stable and then update the + * in-memory size to match. */ - trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) { - btrfs_orphan_del(NULL, BTRFS_I(inode)); - return ret; - } - i_size_write(inode, BTRFS_I(inode)->disk_i_size); - err = btrfs_orphan_del(trans, BTRFS_I(inode)); + err = btrfs_wait_ordered_range(inode, 0, (u64)-1); if (err) - btrfs_abort_transaction(trans, err); - btrfs_end_transaction(trans); + return err; + i_size_write(inode, BTRFS_I(inode)->disk_i_size); } } @@ -9224,39 +9178,31 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback) } /* - * Yes ladies and gentlemen, this is indeed ugly. The fact is we have - * 3 things going on here - * - * 1) We need to reserve space for our orphan item and the space to - * delete our orphan item. Lord knows we don't want to have a dangling - * orphan item because we didn't reserve space to remove it. + * Yes ladies and gentlemen, this is indeed ugly. We have a couple of + * things going on here: * - * 2) We need to reserve space to update our inode. + * 1) We need to reserve space to update our inode. * - * 3) We need to have something to cache all the space that is going to + * 2) We need to have something to cache all the space that is going to * be free'd up by the truncate operation, but also have some slack * space reserved in case it uses space during the truncate (thank you * very much snapshotting). * - * And we need these to all be separate. The fact is we can use a lot of + * And we need these to be separate. The fact is we can use a lot of * space doing the truncate, and we have no earthly idea how much space * we will use, so we need the truncate reservation to be separate so it - * doesn't end up using space reserved for updating the inode or - * removing the orphan item. We also need to be able to stop the - * transaction and start a new one, which means we need to be able to - * update the inode several times, and we have no idea of knowing how - * many times that will be, so we can't just reserve 1 item for the - * entirety of the operation, so that has to be done separately as well. - * Then there is the orphan item, which does indeed need to be held on - * to for the whole operation, and we need nobody to touch this reserved - * space except the orphan code. + * doesn't end up using space reserved for updating the inode. We also + * need to be able to stop the transaction and start a new one, which + * means we need to be able to update the inode several times, and we + * have no idea of knowing how many times that will be, so we can't just + * reserve 1 item for the entirety of the operation, so that has to be + * done separately as well. * * So that leaves us with * - * 1) root->orphan_block_rsv - for the orphan deletion. - * 2) rsv - for the truncate reservation, which we will steal from the + * 1) rsv - for the truncate reservation, which we will steal from the * transaction reservation. - * 3) fs_info->trans_block_rsv - this will have 1 items worth left for + * 2) fs_info->trans_block_rsv - this will have 1 items worth left for * updating the inode. */ rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP); @@ -9345,13 +9291,6 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback) btrfs_ordered_update_i_size(inode, inode->i_size, NULL); } - if (ret == 0 && inode->i_nlink > 0) { - trans->block_rsv = root->orphan_block_rsv; - ret = btrfs_orphan_del(trans, BTRFS_I(inode)); - if (ret) - err = ret; - } - if (trans) { trans->block_rsv = &fs_info->trans_block_rsv; ret = btrfs_update_inode(trans, root, inode); -- cgit v1.2.3 From 7b40b695b4d06666c4665f6b5718085f2c6a5da2 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 11 May 2018 13:13:33 -0700 Subject: Btrfs: get rid of BTRFS_INODE_HAS_ORPHAN_ITEM Now that we don't add orphan items for truncate, there can't be races on adding or deleting an orphan item, so this bit is unnecessary. Reviewed-by: Nikolay Borisov Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- fs/btrfs/btrfs_inode.h | 1 - fs/btrfs/inode.c | 76 +++++++++++++------------------------------------- 2 files changed, 20 insertions(+), 57 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 234bae55b85d..cb7dc0aa4253 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -23,7 +23,6 @@ #define BTRFS_INODE_ORPHAN_META_RESERVED 1 #define BTRFS_INODE_DUMMY 2 #define BTRFS_INODE_IN_DEFRAG 3 -#define BTRFS_INODE_HAS_ORPHAN_ITEM 4 #define BTRFS_INODE_HAS_ASYNC_EXTENT 5 #define BTRFS_INODE_NEEDS_FULL_SYNC 6 #define BTRFS_INODE_COPY_EVERYTHING 7 diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 74caec73b7c2..c78e91619c76 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3359,7 +3359,6 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct btrfs_root *root = inode->root; struct btrfs_block_rsv *block_rsv = NULL; int reserve = 0; - bool insert = false; int ret; if (!root->orphan_block_rsv) { @@ -3369,10 +3368,6 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, return -ENOMEM; } - if (!test_and_set_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, - &inode->runtime_flags)) - insert = true; - if (!test_and_set_bit(BTRFS_INODE_ORPHAN_META_RESERVED, &inode->runtime_flags)) reserve = 1; @@ -3386,8 +3381,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, block_rsv = NULL; } - if (insert) - atomic_inc(&root->orphan_inodes); + atomic_inc(&root->orphan_inodes); spin_unlock(&root->orphan_lock); /* grab metadata reservation from transaction handle */ @@ -3403,36 +3397,28 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, atomic_dec(&root->orphan_inodes); clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, &inode->runtime_flags); - if (insert) - clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, - &inode->runtime_flags); return ret; } } /* insert an orphan item to track this unlinked file */ - if (insert) { - ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode)); - if (ret) { - if (reserve) { - clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, - &inode->runtime_flags); - btrfs_orphan_release_metadata(inode); - } - /* - * btrfs_orphan_commit_root may race with us and set - * ->orphan_block_rsv to zero, in order to avoid that, - * decrease ->orphan_inodes after everything is done. - */ - atomic_dec(&root->orphan_inodes); - if (ret != -EEXIST) { - clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, - &inode->runtime_flags); - btrfs_abort_transaction(trans, ret); - return ret; - } + ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode)); + if (ret) { + if (reserve) { + clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, + &inode->runtime_flags); + btrfs_orphan_release_metadata(inode); + } + /* + * btrfs_orphan_commit_root may race with us and set + * ->orphan_block_rsv to zero, in order to avoid that, + * decrease ->orphan_inodes after everything is done. + */ + atomic_dec(&root->orphan_inodes); + if (ret != -EEXIST) { + btrfs_abort_transaction(trans, ret); + return ret; } - ret = 0; } return 0; @@ -3446,14 +3432,9 @@ static int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct btrfs_inode *inode) { struct btrfs_root *root = inode->root; - int delete_item = 0; int ret = 0; - if (test_and_clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, - &inode->runtime_flags)) - delete_item = 1; - - if (delete_item && trans) + if (trans) ret = btrfs_del_orphan_item(trans, root, btrfs_ino(inode)); if (test_and_clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, @@ -3465,8 +3446,7 @@ static int btrfs_orphan_del(struct btrfs_trans_handle *trans, * to zero, in order to avoid that, decrease ->orphan_inodes after * everything is done. */ - if (delete_item) - atomic_dec(&root->orphan_inodes); + atomic_dec(&root->orphan_inodes); return ret; } @@ -3624,12 +3604,6 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) continue; } - /* - * add this inode to the orphan list so btrfs_orphan_del does - * the proper thing when we hit it - */ - set_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, - &BTRFS_I(inode)->runtime_flags); atomic_inc(&root->orphan_inodes); nr_unlink++; @@ -5527,11 +5501,8 @@ void btrfs_evict_inode(struct inode *inode) btrfs_free_io_failure_record(BTRFS_I(inode), 0, (u64)-1); - if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) { - BUG_ON(test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, - &BTRFS_I(inode)->runtime_flags)); + if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) goto no_delete; - } if (inode->i_nlink > 0) { BUG_ON(btrfs_root_refs(&root->root_item) != 0 && @@ -9442,13 +9413,6 @@ void btrfs_destroy_inode(struct inode *inode) if (!root) goto free; - if (test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM, - &BTRFS_I(inode)->runtime_flags)) { - btrfs_info(fs_info, "inode %llu still on the orphan list", - btrfs_ino(BTRFS_I(inode))); - atomic_dec(&root->orphan_inodes); - } - while (1) { ordered = btrfs_lookup_first_ordered_extent(inode, (u64)-1); if (!ordered) -- cgit v1.2.3 From 05a5bd7c4decf828f79b62863e520c9ff86eef72 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 11 May 2018 13:13:34 -0700 Subject: Btrfs: delete dead code in btrfs_orphan_commit_root() btrfs_orphan_commit_root() tries to delete an orphan item for a subvolume in the tree root, but we don't actually insert that item in the first place. See commit 0a0d4415e338 ("Btrfs: delete dead code in btrfs_orphan_add()"). We can get rid of it. Reviewed-by: Josef Bacik Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- fs/btrfs/inode.c | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c78e91619c76..06506cd00e4a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3307,7 +3307,6 @@ void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans, { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_block_rsv *block_rsv; - int ret; if (atomic_read(&root->orphan_inodes) || root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE) @@ -3328,17 +3327,6 @@ void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans, root->orphan_block_rsv = NULL; spin_unlock(&root->orphan_lock); - if (test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state) && - btrfs_root_refs(&root->root_item) > 0) { - ret = btrfs_del_orphan_item(trans, fs_info->tree_root, - root->root_key.objectid); - if (ret) - btrfs_abort_transaction(trans, ret); - else - clear_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, - &root->state); - } - if (block_rsv) { WARN_ON(block_rsv->size > 0); btrfs_free_block_rsv(fs_info, block_rsv); -- cgit v1.2.3 From c08db7d8d295a4f3a10faaca376de011afff7950 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 11 May 2018 13:13:35 -0700 Subject: Btrfs: don't return ino to ino cache if inode item removal fails In btrfs_evict_inode(), if btrfs_truncate_inode_items() fails, the inode item will still be in the tree but we still return the ino to the ino cache. That will blow up later when someone tries to allocate that ino, so don't return it to the cache. Fixes: 581bb050941b ("Btrfs: Cache free inode numbers in memory") Reviewed-by: Josef Bacik Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- fs/btrfs/inode.c | 25 +++++++++++++------------ 1 file changed, 13 insertions(+), 12 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 06506cd00e4a..73783492a0d1 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5593,13 +5593,18 @@ void btrfs_evict_inode(struct inode *inode) trans->block_rsv = rsv; ret = btrfs_truncate_inode_items(trans, root, inode, 0, 0); - if (ret != -ENOSPC && ret != -EAGAIN) + if (ret) { + trans->block_rsv = &fs_info->trans_block_rsv; + btrfs_end_transaction(trans); + btrfs_btree_balance_dirty(fs_info); + if (ret != -ENOSPC && ret != -EAGAIN) { + btrfs_orphan_del(NULL, BTRFS_I(inode)); + btrfs_free_block_rsv(fs_info, rsv); + goto no_delete; + } + } else { break; - - trans->block_rsv = &fs_info->trans_block_rsv; - btrfs_end_transaction(trans); - trans = NULL; - btrfs_btree_balance_dirty(fs_info); + } } btrfs_free_block_rsv(fs_info, rsv); @@ -5608,12 +5613,8 @@ void btrfs_evict_inode(struct inode *inode) * Errors here aren't a big deal, it just means we leave orphan items * in the tree. They will be cleaned up on the next mount. */ - if (ret == 0) { - trans->block_rsv = root->orphan_block_rsv; - btrfs_orphan_del(trans, BTRFS_I(inode)); - } else { - btrfs_orphan_del(NULL, BTRFS_I(inode)); - } + trans->block_rsv = root->orphan_block_rsv; + btrfs_orphan_del(trans, BTRFS_I(inode)); trans->block_rsv = &fs_info->trans_block_rsv; if (!(root == fs_info->tree_root || -- cgit v1.2.3 From 4b9d7b59bfcb62a7d438876eac5a054db32904dd Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 11 May 2018 13:13:36 -0700 Subject: Btrfs: refactor btrfs_evict_inode() reserve refill dance The truncate loop in btrfs_evict_inode() does two things at once: - It refills the temporary block reserve, potentially stealing from the global reserve or committing - It calls btrfs_truncate_inode_items() The tangle of continues hides the fact that these two steps are actually separate. Split the first step out into a separate function both for clarity and so that we can reuse it in a later patch. Reviewed-by: Nikolay Borisov Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- fs/btrfs/inode.c | 113 +++++++++++++++++++++---------------------------------- 1 file changed, 42 insertions(+), 71 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 73783492a0d1..f70284acb6ac 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5452,13 +5452,52 @@ static void evict_inode_truncate_pages(struct inode *inode) spin_unlock(&io_tree->lock); } +static struct btrfs_trans_handle *evict_refill_and_join(struct btrfs_root *root, + struct btrfs_block_rsv *rsv, + u64 min_size) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; + int failures = 0; + + for (;;) { + struct btrfs_trans_handle *trans; + int ret; + + ret = btrfs_block_rsv_refill(root, rsv, min_size, + BTRFS_RESERVE_FLUSH_LIMIT); + + if (ret && ++failures > 2) { + btrfs_warn(fs_info, + "could not allocate space for a delete; will truncate on mount"); + return ERR_PTR(-ENOSPC); + } + + trans = btrfs_join_transaction(root); + if (IS_ERR(trans) || !ret) + return trans; + + /* + * Try to steal from the global reserve if there is space for + * it. + */ + if (!btrfs_check_space_for_delayed_refs(trans, fs_info) && + !btrfs_block_rsv_migrate(global_rsv, rsv, min_size, 0)) + return trans; + + /* If not, commit and try again. */ + ret = btrfs_commit_transaction(trans); + if (ret) + return ERR_PTR(ret); + } +} + void btrfs_evict_inode(struct inode *inode) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(inode)->root; - struct btrfs_block_rsv *rsv, *global_rsv; - int steal_from_global = 0; + struct btrfs_block_rsv *rsv; u64 min_size; int ret; @@ -5511,85 +5550,17 @@ void btrfs_evict_inode(struct inode *inode) } rsv->size = min_size; rsv->failfast = 1; - global_rsv = &fs_info->global_block_rsv; btrfs_i_size_write(BTRFS_I(inode), 0); - /* - * This is a bit simpler than btrfs_truncate since we've already - * reserved our space for our orphan item in the unlink, so we just - * need to reserve some slack space in case we add bytes and update - * inode item when doing the truncate. - */ while (1) { - ret = btrfs_block_rsv_refill(root, rsv, min_size, - BTRFS_RESERVE_FLUSH_LIMIT); - - /* - * Try and steal from the global reserve since we will - * likely not use this space anyway, we want to try as - * hard as possible to get this to work. - */ - if (ret) - steal_from_global++; - else - steal_from_global = 0; - ret = 0; - - /* - * steal_from_global == 0: we reserved stuff, hooray! - * steal_from_global == 1: we didn't reserve stuff, boo! - * steal_from_global == 2: we've committed, still not a lot of - * room but maybe we'll have room in the global reserve this - * time. - * steal_from_global == 3: abandon all hope! - */ - if (steal_from_global > 2) { - btrfs_warn(fs_info, - "Could not get space for a delete, will truncate on mount %d", - ret); - btrfs_orphan_del(NULL, BTRFS_I(inode)); - btrfs_free_block_rsv(fs_info, rsv); - goto no_delete; - } - - trans = btrfs_join_transaction(root); + trans = evict_refill_and_join(root, rsv, min_size); if (IS_ERR(trans)) { btrfs_orphan_del(NULL, BTRFS_I(inode)); btrfs_free_block_rsv(fs_info, rsv); goto no_delete; } - /* - * We can't just steal from the global reserve, we need to make - * sure there is room to do it, if not we need to commit and try - * again. - */ - if (steal_from_global) { - if (!btrfs_check_space_for_delayed_refs(trans, fs_info)) - ret = btrfs_block_rsv_migrate(global_rsv, rsv, - min_size, 0); - else - ret = -ENOSPC; - } - - /* - * Couldn't steal from the global reserve, we have too much - * pending stuff built up, commit the transaction and try it - * again. - */ - if (ret) { - ret = btrfs_commit_transaction(trans); - if (ret) { - btrfs_orphan_del(NULL, BTRFS_I(inode)); - btrfs_free_block_rsv(fs_info, rsv); - goto no_delete; - } - continue; - } else { - steal_from_global = 0; - } - trans->block_rsv = rsv; ret = btrfs_truncate_inode_items(trans, root, inode, 0, 0); -- cgit v1.2.3 From 27919067f182c35f825406ad76a0e2e5644d33af Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 11 May 2018 13:13:37 -0700 Subject: Btrfs: fix ENOSPC caused by orphan items reservations Currently, we keep space reserved for all inode orphan items until the inode is evicted (i.e., all references to it are dropped). We hit an issue where an application would keep a bunch of deleted files open (by design) and thus keep a large amount of space reserved, causing ENOSPC errors when other operations tried to reserve space. This long-standing reservation isn't absolutely necessary for a couple of reasons: - We can almost always make the reservation we need or steal from the global reserve for the orphan item - If we can't, it's not the end of the world if we drop the orphan item on the floor and let the next mount clean it up So, get rid of persistent reservation and just reserve space in btrfs_evict_inode(). Reviewed-by: Nikolay Borisov Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- fs/btrfs/inode.c | 158 +++++++++++++------------------------------------------ 1 file changed, 38 insertions(+), 120 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f70284acb6ac..f8af40d02595 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3336,77 +3336,16 @@ void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans, /* * This creates an orphan entry for the given inode in case something goes wrong * in the middle of an unlink. - * - * NOTE: caller of this function should reserve 5 units of metadata for - * this function. */ int btrfs_orphan_add(struct btrfs_trans_handle *trans, - struct btrfs_inode *inode) + struct btrfs_inode *inode) { - struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); - struct btrfs_root *root = inode->root; - struct btrfs_block_rsv *block_rsv = NULL; - int reserve = 0; int ret; - if (!root->orphan_block_rsv) { - block_rsv = btrfs_alloc_block_rsv(fs_info, - BTRFS_BLOCK_RSV_TEMP); - if (!block_rsv) - return -ENOMEM; - } - - if (!test_and_set_bit(BTRFS_INODE_ORPHAN_META_RESERVED, - &inode->runtime_flags)) - reserve = 1; - - spin_lock(&root->orphan_lock); - /* If someone has created ->orphan_block_rsv, be happy to use it. */ - if (!root->orphan_block_rsv) { - root->orphan_block_rsv = block_rsv; - } else if (block_rsv) { - btrfs_free_block_rsv(fs_info, block_rsv); - block_rsv = NULL; - } - - atomic_inc(&root->orphan_inodes); - spin_unlock(&root->orphan_lock); - - /* grab metadata reservation from transaction handle */ - if (reserve) { - ret = btrfs_orphan_reserve_metadata(trans, inode); - ASSERT(!ret); - if (ret) { - /* - * dec doesn't need spin_lock as ->orphan_block_rsv - * would be released only if ->orphan_inodes is - * zero. - */ - atomic_dec(&root->orphan_inodes); - clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, - &inode->runtime_flags); - return ret; - } - } - - /* insert an orphan item to track this unlinked file */ - ret = btrfs_insert_orphan_item(trans, root, btrfs_ino(inode)); - if (ret) { - if (reserve) { - clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, - &inode->runtime_flags); - btrfs_orphan_release_metadata(inode); - } - /* - * btrfs_orphan_commit_root may race with us and set - * ->orphan_block_rsv to zero, in order to avoid that, - * decrease ->orphan_inodes after everything is done. - */ - atomic_dec(&root->orphan_inodes); - if (ret != -EEXIST) { - btrfs_abort_transaction(trans, ret); - return ret; - } + ret = btrfs_insert_orphan_item(trans, inode->root, btrfs_ino(inode)); + if (ret && ret != -EEXIST) { + btrfs_abort_transaction(trans, ret); + return ret; } return 0; @@ -3419,24 +3358,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, static int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct btrfs_inode *inode) { - struct btrfs_root *root = inode->root; - int ret = 0; - - if (trans) - ret = btrfs_del_orphan_item(trans, root, btrfs_ino(inode)); - - if (test_and_clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED, - &inode->runtime_flags)) - btrfs_orphan_release_metadata(inode); - - /* - * btrfs_orphan_commit_root may race with us and set ->orphan_block_rsv - * to zero, in order to avoid that, decrease ->orphan_inodes after - * everything is done. - */ - atomic_dec(&root->orphan_inodes); - - return ret; + return btrfs_del_orphan_item(trans, inode->root, btrfs_ino(inode)); } /* @@ -3592,8 +3514,6 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) continue; } - atomic_inc(&root->orphan_inodes); - nr_unlink++; /* this will do delete_inode and everything for us */ @@ -5518,10 +5438,8 @@ void btrfs_evict_inode(struct inode *inode) btrfs_is_free_space_inode(BTRFS_I(inode)))) goto no_delete; - if (is_bad_inode(inode)) { - btrfs_orphan_del(NULL, BTRFS_I(inode)); + if (is_bad_inode(inode)) goto no_delete; - } /* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */ if (!special_file(inode->i_mode)) btrfs_wait_ordered_range(inode, 0, (u64)-1); @@ -5538,16 +5456,12 @@ void btrfs_evict_inode(struct inode *inode) } ret = btrfs_commit_inode_delayed_inode(BTRFS_I(inode)); - if (ret) { - btrfs_orphan_del(NULL, BTRFS_I(inode)); + if (ret) goto no_delete; - } rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP); - if (!rsv) { - btrfs_orphan_del(NULL, BTRFS_I(inode)); + if (!rsv) goto no_delete; - } rsv->size = min_size; rsv->failfast = 1; @@ -5555,46 +5469,50 @@ void btrfs_evict_inode(struct inode *inode) while (1) { trans = evict_refill_and_join(root, rsv, min_size); - if (IS_ERR(trans)) { - btrfs_orphan_del(NULL, BTRFS_I(inode)); - btrfs_free_block_rsv(fs_info, rsv); - goto no_delete; - } + if (IS_ERR(trans)) + goto free_rsv; trans->block_rsv = rsv; ret = btrfs_truncate_inode_items(trans, root, inode, 0, 0); - if (ret) { - trans->block_rsv = &fs_info->trans_block_rsv; - btrfs_end_transaction(trans); - btrfs_btree_balance_dirty(fs_info); - if (ret != -ENOSPC && ret != -EAGAIN) { - btrfs_orphan_del(NULL, BTRFS_I(inode)); - btrfs_free_block_rsv(fs_info, rsv); - goto no_delete; - } - } else { + trans->block_rsv = &fs_info->trans_block_rsv; + btrfs_end_transaction(trans); + btrfs_btree_balance_dirty(fs_info); + if (ret && ret != -ENOSPC && ret != -EAGAIN) + goto free_rsv; + else if (!ret) break; - } } - btrfs_free_block_rsv(fs_info, rsv); - /* - * Errors here aren't a big deal, it just means we leave orphan items - * in the tree. They will be cleaned up on the next mount. + * Errors here aren't a big deal, it just means we leave orphan items in + * the tree. They will be cleaned up on the next mount. If the inode + * number gets reused, cleanup deletes the orphan item without doing + * anything, and unlink reuses the existing orphan item. + * + * If it turns out that we are dropping too many of these, we might want + * to add a mechanism for retrying these after a commit. */ - trans->block_rsv = root->orphan_block_rsv; - btrfs_orphan_del(trans, BTRFS_I(inode)); + trans = evict_refill_and_join(root, rsv, min_size); + if (!IS_ERR(trans)) { + trans->block_rsv = rsv; + btrfs_orphan_del(trans, BTRFS_I(inode)); + trans->block_rsv = &fs_info->trans_block_rsv; + btrfs_end_transaction(trans); + } - trans->block_rsv = &fs_info->trans_block_rsv; if (!(root == fs_info->tree_root || root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)) btrfs_return_ino(root, btrfs_ino(BTRFS_I(inode))); - btrfs_end_transaction(trans); - btrfs_btree_balance_dirty(fs_info); +free_rsv: + btrfs_free_block_rsv(fs_info, rsv); no_delete: + /* + * If we didn't successfully delete, the orphan item will still be in + * the tree and we'll retry on the next mount. Again, we might also want + * to retry these periodically in the future. + */ btrfs_remove_delayed_node(BTRFS_I(inode)); clear_inode(inode); } -- cgit v1.2.3 From a575ceeb1338e7eae6d14e223b077b3c6fd3bb6b Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 11 May 2018 13:13:38 -0700 Subject: Btrfs: get rid of unused orphan infrastructure Now that we don't keep long-standing reservations for orphan items, root->orphan_block_rsv isn't used. We can git rid of it, along with: - root->orphan_lock, which was used to protect root->orphan_block_rsv - root->orphan_inodes, which was used as a refcount for root->orphan_block_rsv - BTRFS_INODE_ORPHAN_META_RESERVED, which was used to track reservations in root->orphan_block_rsv - btrfs_orphan_commit_root(), which was the last user of any of these and does nothing else Reviewed-by: Nikolay Borisov Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- fs/btrfs/btrfs_inode.h | 1 - fs/btrfs/ctree.h | 8 -------- fs/btrfs/disk-io.c | 9 --------- fs/btrfs/extent-tree.c | 38 -------------------------------------- fs/btrfs/inode.c | 43 +------------------------------------------ fs/btrfs/transaction.c | 1 - 6 files changed, 1 insertion(+), 99 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index cb7dc0aa4253..4807cde0313d 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -20,7 +20,6 @@ * new data the application may have written before commit. */ #define BTRFS_INODE_ORDERED_DATA_CLOSE 0 -#define BTRFS_INODE_ORPHAN_META_RESERVED 1 #define BTRFS_INODE_DUMMY 2 #define BTRFS_INODE_IN_DEFRAG 3 #define BTRFS_INODE_HAS_ASYNC_EXTENT 5 diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 71aecf0b7cf5..bbb358143ded 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1223,9 +1223,6 @@ struct btrfs_root { spinlock_t log_extents_lock[2]; struct list_head logged_list[2]; - spinlock_t orphan_lock; - atomic_t orphan_inodes; - struct btrfs_block_rsv *orphan_block_rsv; int orphan_cleanup_state; spinlock_t inode_lock; @@ -2768,9 +2765,6 @@ void btrfs_delalloc_release_space(struct inode *inode, void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start, u64 len); void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans); -int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans, - struct btrfs_inode *inode); -void btrfs_orphan_release_metadata(struct btrfs_inode *inode); int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, struct btrfs_block_rsv *rsv, int nitems, @@ -3228,8 +3222,6 @@ int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct btrfs_inode *inode); int btrfs_orphan_cleanup(struct btrfs_root *root); -void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans, - struct btrfs_root *root); int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size); void btrfs_add_delayed_iput(struct inode *inode); void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index a16385091572..d8d3b73680ef 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1184,7 +1184,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, root->inode_tree = RB_ROOT; INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC); root->block_rsv = NULL; - root->orphan_block_rsv = NULL; INIT_LIST_HEAD(&root->dirty_list); INIT_LIST_HEAD(&root->root_list); @@ -1194,7 +1193,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, INIT_LIST_HEAD(&root->ordered_root); INIT_LIST_HEAD(&root->logged_list[0]); INIT_LIST_HEAD(&root->logged_list[1]); - spin_lock_init(&root->orphan_lock); spin_lock_init(&root->inode_lock); spin_lock_init(&root->delalloc_lock); spin_lock_init(&root->ordered_extent_lock); @@ -1215,7 +1213,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info, atomic_set(&root->log_commit[1], 0); atomic_set(&root->log_writers, 0); atomic_set(&root->log_batch, 0); - atomic_set(&root->orphan_inodes, 0); refcount_set(&root->refs, 1); atomic_set(&root->will_be_snapshotted, 0); root->log_transid = 0; @@ -3884,8 +3881,6 @@ static void free_fs_root(struct btrfs_root *root) { iput(root->ino_cache_inode); WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree)); - btrfs_free_block_rsv(root->fs_info, root->orphan_block_rsv); - root->orphan_block_rsv = NULL; if (root->anon_dev) free_anon_bdev(root->anon_dev); if (root->subv_writers) @@ -3976,7 +3971,6 @@ int btrfs_commit_super(struct btrfs_fs_info *fs_info) void close_ctree(struct btrfs_fs_info *fs_info) { - struct btrfs_root *root = fs_info->tree_root; int ret; set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags); @@ -4072,9 +4066,6 @@ void close_ctree(struct btrfs_fs_info *fs_info) btrfs_free_stripe_hash_table(fs_info); btrfs_free_ref_cache(fs_info); - __btrfs_free_block_rsv(root->orphan_block_rsv); - root->orphan_block_rsv = NULL; - while (!list_empty(&fs_info->pinned_chunks)) { struct extent_map *em; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 47edb3af3f9f..ccf2690f7ca1 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5949,44 +5949,6 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) trans->chunk_bytes_reserved = 0; } -/* Can only return 0 or -ENOSPC */ -int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans, - struct btrfs_inode *inode) -{ - struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); - struct btrfs_root *root = inode->root; - /* - * We always use trans->block_rsv here as we will have reserved space - * for our orphan when starting the transaction, using get_block_rsv() - * here will sometimes make us choose the wrong block rsv as we could be - * doing a reloc inode for a non refcounted root. - */ - struct btrfs_block_rsv *src_rsv = trans->block_rsv; - struct btrfs_block_rsv *dst_rsv = root->orphan_block_rsv; - - /* - * We need to hold space in order to delete our orphan item once we've - * added it, so this takes the reservation so we can release it later - * when we are truly done with the orphan item. - */ - u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1); - - trace_btrfs_space_reservation(fs_info, "orphan", btrfs_ino(inode), - num_bytes, 1); - return btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1); -} - -void btrfs_orphan_release_metadata(struct btrfs_inode *inode) -{ - struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb); - struct btrfs_root *root = inode->root; - u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1); - - trace_btrfs_space_reservation(fs_info, "orphan", btrfs_ino(inode), - num_bytes, 0); - btrfs_block_rsv_release(fs_info, root->orphan_block_rsv, num_bytes); -} - /* * btrfs_subvolume_reserve_metadata() - reserve space for subvolume operation * root: the root of the parent directory diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f8af40d02595..b247ea31c436 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3297,42 +3297,6 @@ void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info) spin_unlock(&fs_info->delayed_iput_lock); } -/* - * This is called in transaction commit time. If there are no orphan - * files in the subvolume, it removes orphan item and frees block_rsv - * structure. - */ -void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans, - struct btrfs_root *root) -{ - struct btrfs_fs_info *fs_info = root->fs_info; - struct btrfs_block_rsv *block_rsv; - - if (atomic_read(&root->orphan_inodes) || - root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE) - return; - - spin_lock(&root->orphan_lock); - if (atomic_read(&root->orphan_inodes)) { - spin_unlock(&root->orphan_lock); - return; - } - - if (root->orphan_cleanup_state != ORPHAN_CLEANUP_DONE) { - spin_unlock(&root->orphan_lock); - return; - } - - block_rsv = root->orphan_block_rsv; - root->orphan_block_rsv = NULL; - spin_unlock(&root->orphan_lock); - - if (block_rsv) { - WARN_ON(block_rsv->size > 0); - btrfs_free_block_rsv(fs_info, block_rsv); - } -} - /* * This creates an orphan entry for the given inode in case something goes wrong * in the middle of an unlink. @@ -3526,12 +3490,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) root->orphan_cleanup_state = ORPHAN_CLEANUP_DONE; - if (root->orphan_block_rsv) - btrfs_block_rsv_release(fs_info, root->orphan_block_rsv, - (u64)-1); - - if (root->orphan_block_rsv || - test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state)) { + if (test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state)) { trans = btrfs_join_transaction(root); if (!IS_ERR(trans)) btrfs_end_transaction(trans); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index ff841abb756e..2544acc33045 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1245,7 +1245,6 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans) btrfs_free_log(trans, root); btrfs_update_reloc_root(trans, root); - btrfs_orphan_commit_root(trans, root); btrfs_save_ino_cache(root, trans); -- cgit v1.2.3 From 399b0bbf5f680797d3599fa14f16706ffc470145 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 11 May 2018 13:13:40 -0700 Subject: Btrfs: reserve space for O_TMPFILE orphan item deletion btrfs_link() calls btrfs_orphan_del() if it's linking an O_TMPFILE but it doesn't reserve space to do so. Even before the removal of the orphan_block_rsv it wasn't using it. Fixes: ef3b9af50bfa ("Btrfs: implement inode_operations callback tmpfile") Reviewed-by: Filipe Manana Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- fs/btrfs/inode.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b247ea31c436..6e9cb5338964 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6658,8 +6658,9 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, * 2 items for inode and inode ref * 2 items for dir items * 1 item for parent inode + * 1 item for orphan item deletion if O_TMPFILE */ - trans = btrfs_start_transaction(root, 5); + trans = btrfs_start_transaction(root, inode->i_nlink ? 5 : 6); if (IS_ERR(trans)) { err = PTR_ERR(trans); trans = NULL; -- cgit v1.2.3 From d19577912d57c143bb592a061e3dbd7b6f78f71a Mon Sep 17 00:00:00 2001 From: Lu Fengqi Date: Tue, 29 May 2018 15:01:54 +0800 Subject: btrfs: Remove fs_info argument from btrfs_uuid_tree_rem This function always takes a transaction handle which contains a reference to the fs_info. Use that and remove the extra argument. Signed-off-by: Lu Fengqi Reviewed-by: Nikolay Borisov [ rename the function ] Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 3 +-- fs/btrfs/inode.c | 4 ++-- fs/btrfs/ioctl.c | 3 +-- fs/btrfs/uuid-tree.c | 6 +++--- 4 files changed, 7 insertions(+), 9 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3dc1db981be7..9a62bc59cc39 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3042,8 +3042,7 @@ void btrfs_update_root_times(struct btrfs_trans_handle *trans, /* uuid-tree.c */ int btrfs_uuid_tree_add(struct btrfs_trans_handle *trans, u8 *uuid, u8 type, u64 subid); -int btrfs_uuid_tree_rem(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u8 *uuid, u8 type, +int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, u8 *uuid, u8 type, u64 subid); int btrfs_uuid_tree_iterate(struct btrfs_fs_info *fs_info, int (*check_func)(struct btrfs_fs_info *, u8 *, u8, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6e9cb5338964..5d370bbdf826 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4361,7 +4361,7 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) } } - ret = btrfs_uuid_tree_rem(trans, fs_info, dest->root_item.uuid, + ret = btrfs_uuid_tree_remove(trans, dest->root_item.uuid, BTRFS_UUID_KEY_SUBVOL, dest->root_key.objectid); if (ret && ret != -ENOENT) { @@ -4370,7 +4370,7 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) goto out_end_trans; } if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) { - ret = btrfs_uuid_tree_rem(trans, fs_info, + ret = btrfs_uuid_tree_remove(trans, dest->root_item.received_uuid, BTRFS_UUID_KEY_RECEIVED_SUBVOL, dest->root_key.objectid); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 4ba8cabedeec..a58ab372091e 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -5018,8 +5018,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, BTRFS_UUID_SIZE); if (received_uuid_changed && !btrfs_is_empty_uuid(root_item->received_uuid)) { - ret = btrfs_uuid_tree_rem(trans, fs_info, - root_item->received_uuid, + ret = btrfs_uuid_tree_remove(trans, root_item->received_uuid, BTRFS_UUID_KEY_RECEIVED_SUBVOL, root->root_key.objectid); if (ret && ret != -ENOENT) { diff --git a/fs/btrfs/uuid-tree.c b/fs/btrfs/uuid-tree.c index 8be956ed4603..3b2ae342e649 100644 --- a/fs/btrfs/uuid-tree.c +++ b/fs/btrfs/uuid-tree.c @@ -144,10 +144,10 @@ out: return ret; } -int btrfs_uuid_tree_rem(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u8 *uuid, u8 type, +int btrfs_uuid_tree_remove(struct btrfs_trans_handle *trans, u8 *uuid, u8 type, u64 subid) { + struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_root *uuid_root = fs_info->uuid_root; int ret; struct btrfs_path *path = NULL; @@ -239,7 +239,7 @@ static int btrfs_uuid_iter_rem(struct btrfs_root *uuid_root, u8 *uuid, u8 type, goto out; } - ret = btrfs_uuid_tree_rem(trans, uuid_root->fs_info, uuid, type, subid); + ret = btrfs_uuid_tree_remove(trans, uuid, type, subid); btrfs_end_transaction(trans); out: -- cgit v1.2.3 From 78d4295b1eeed4d857f11333caac8b4894ac4412 Mon Sep 17 00:00:00 2001 From: Ethan Lien Date: Thu, 17 May 2018 14:58:29 +0800 Subject: btrfs: lift some btrfs_cross_ref_exist checks in nocow path In nocow path, we check if the extent is snapshotted in btrfs_cross_ref_exist(). We can do the similar check earlier and avoid unnecessary search into extent tree. A fio test on a Intel D-1531, 16GB RAM, SSD RAID-5 machine as follows: [global] group_reporting time_based thread=1 ioengine=libaio bs=4k iodepth=32 size=64G runtime=180 numjobs=8 rw=randwrite [file1] filename=/mnt/nocow/testfile IOPS result: unpatched patched 1 fio round: 46670 46958 snapshot 2 fio round: 51826 54498 3 fio round: 59767 61289 After snapshot, the first fio get about 5% performance gain. As we continually write to the same file, all writes will resume to nocow mode and eventually we have no performance gain. Signed-off-by: Ethan Lien Reviewed-by: David Sterba [ update comments ] Signed-off-by: David Sterba --- fs/btrfs/inode.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5d370bbdf826..27293ff7174d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1370,6 +1370,13 @@ next_slot: btrfs_file_extent_encryption(leaf, fi) || btrfs_file_extent_other_encoding(leaf, fi)) goto out_check; + /* + * Do the same check as in btrfs_cross_ref_exist but + * without the unnecessary search. + */ + if (btrfs_file_extent_generation(leaf, fi) <= + btrfs_root_last_snapshot(&root->root_item)) + goto out_check; if (extent_type == BTRFS_FILE_EXTENT_REG && !force) goto out_check; if (btrfs_extent_readonly(fs_info, disk_bytenr)) @@ -7322,6 +7329,14 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len, btrfs_file_extent_other_encoding(leaf, fi)) goto out; + /* + * Do the same check as in btrfs_cross_ref_exist but without the + * unnecessary search. + */ + if (btrfs_file_extent_generation(leaf, fi) <= + btrfs_root_last_snapshot(&root->root_item)) + goto out; + backref_offset = btrfs_file_extent_offset(leaf, fi); if (orig_start) { -- cgit v1.2.3 From e73e81b6d0114d4a303205a952ab2e87c44bd279 Mon Sep 17 00:00:00 2001 From: Ethan Lien Date: Mon, 28 May 2018 13:48:20 +0800 Subject: btrfs: balance dirty metadata pages in btrfs_finish_ordered_io [Problem description and how we fix it] We should balance dirty metadata pages at the end of btrfs_finish_ordered_io, since a small, unmergeable random write can potentially produce dirty metadata which is multiple times larger than the data itself. For example, a small, unmergeable 4KiB write may produce: 16KiB dirty leaf (and possibly 16KiB dirty node) in subvolume tree 16KiB dirty leaf (and possibly 16KiB dirty node) in checksum tree 16KiB dirty leaf (and possibly 16KiB dirty node) in extent tree Although we do call balance dirty pages in write side, but in the buffered write path, most metadata are dirtied only after we reach the dirty background limit (which by far only counts dirty data pages) and wakeup the flusher thread. If there are many small, unmergeable random writes spread in a large btree, we'll find a burst of dirty pages exceeds the dirty_bytes limit after we wakeup the flusher thread - which is not what we expect. In our machine, it caused out-of-memory problem since a page cannot be dropped if it is marked dirty. Someone may worry about we may sleep in btrfs_btree_balance_dirty_nodelay, but since we do btrfs_finish_ordered_io in a separate worker, it will not stop the flusher consuming dirty pages. Also, we use different worker for metadata writeback endio, sleep in btrfs_finish_ordered_io help us throttle the size of dirty metadata pages. [Reproduce steps] To reproduce the problem, we need to do 4KiB write randomly spread in a large btree. In our 2GiB RAM machine: 1) Create 4 subvolumes. 2) Run fio on each subvolume: [global] direct=0 rw=randwrite ioengine=libaio bs=4k iodepth=16 numjobs=1 group_reporting size=128G runtime=1800 norandommap time_based randrepeat=0 3) Take snapshot on each subvolume and repeat fio on existing files. 4) Repeat step (3) until we get large btrees. In our case, by observing btrfs_root_item->bytes_used, we have 2GiB of metadata in each subvolume tree and 12GiB of metadata in extent tree. 5) Stop all fio, take snapshot again, and wait until all delayed work is completed. 6) Start all fio. Few seconds later we hit OOM when the flusher starts to work. It can be reproduced even when using nocow write. Signed-off-by: Ethan Lien Reviewed-by: David Sterba [ add comment ] Signed-off-by: David Sterba --- fs/btrfs/inode.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 27293ff7174d..c431ae05cbe4 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3163,6 +3163,9 @@ out: /* once for the tree */ btrfs_put_ordered_extent(ordered_extent); + /* Try to release some metadata so we don't get an OOM but don't wait */ + btrfs_btree_balance_dirty_nodelay(fs_info); + return ret; } -- cgit v1.2.3 From c4c129db5da8f070147f1757e16196d377ccf20b Mon Sep 17 00:00:00 2001 From: Gu JinXiang Date: Wed, 30 May 2018 11:00:38 +0800 Subject: btrfs: drop unused parameter qgroup_reserved Since commit 7775c8184ec0 ("btrfs: remove unused parameter from btrfs_subvolume_release_metadata") parameter qgroup_reserved is not used by caller of function btrfs_subvolume_reserve_metadata. So remove it. Signed-off-by: Gu JinXiang Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 3 +-- fs/btrfs/extent-tree.c | 7 ++----- fs/btrfs/inode.c | 4 +--- fs/btrfs/ioctl.c | 5 +---- 4 files changed, 5 insertions(+), 14 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 9a62bc59cc39..f4bf7874c24a 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2767,8 +2767,7 @@ void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start, void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans); int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, struct btrfs_block_rsv *rsv, - int nitems, - u64 *qgroup_reserved, bool use_global_rsv); + int nitems, bool use_global_rsv); void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info, struct btrfs_block_rsv *rsv); void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 7ebb05fe2cd8..9a65df02a13f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5947,7 +5947,6 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans) int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, struct btrfs_block_rsv *rsv, int items, - u64 *qgroup_reserved, bool use_global_rsv) { u64 num_bytes; @@ -5965,8 +5964,6 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, num_bytes = 0; } - *qgroup_reserved = num_bytes; - num_bytes = btrfs_calc_trans_metadata_size(fs_info, items); rsv->space_info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA); @@ -5976,8 +5973,8 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, if (ret == -ENOSPC && use_global_rsv) ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes, 1); - if (ret && *qgroup_reserved) - btrfs_qgroup_free_meta_prealloc(root, *qgroup_reserved); + if (ret && num_bytes) + btrfs_qgroup_free_meta_prealloc(root, num_bytes); return ret; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c431ae05cbe4..7148abaf1da3 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4293,7 +4293,6 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) struct btrfs_trans_handle *trans; struct btrfs_block_rsv block_rsv; u64 root_flags; - u64 qgroup_reserved; int ret; int err; @@ -4328,8 +4327,7 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry) * two for dir entries, * two for root ref/backref. */ - err = btrfs_subvolume_reserve_metadata(root, &block_rsv, - 5, &qgroup_reserved, true); + err = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true); if (err) goto out_up_write; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a58ab372091e..4db2446c7015 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -569,7 +569,6 @@ static noinline int create_subvol(struct inode *dir, u64 objectid; u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID; u64 index = 0; - u64 qgroup_reserved; uuid_le new_uuid; root_item = kzalloc(sizeof(*root_item), GFP_KERNEL); @@ -594,8 +593,7 @@ static noinline int create_subvol(struct inode *dir, * The same as the snapshot creation, please see the comment * of create_snapshot(). */ - ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, - 8, &qgroup_reserved, false); + ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 8, false); if (ret) goto fail_free; @@ -803,7 +801,6 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, */ ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root, &pending_snapshot->block_rsv, 8, - &pending_snapshot->qgroup_reserved, false); if (ret) goto dec_and_free; -- cgit v1.2.3 From 090a127afa8f73e9618d4058d6755f7ec7453dd6 Mon Sep 17 00:00:00 2001 From: Su Yue Date: Wed, 30 May 2018 16:48:56 +0800 Subject: btrfs: return error value if create_io_em failed in cow_file_range In cow_file_range(), create_io_em() may fail, but its return value is not recorded. Then return value may be 0 even it failed which is a wrong behavior. Let cow_file_range() return PTR_ERR(em) if create_io_em() failed. Fixes: 6f9994dbabe5 ("Btrfs: create a helper to create em for IO") CC: stable@vger.kernel.org # 4.11+ Signed-off-by: Su Yue Reviewed-by: Nikolay Borisov Signed-off-by: David Sterba --- fs/btrfs/inode.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 7148abaf1da3..f81a48c47fe0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1018,8 +1018,10 @@ static noinline int cow_file_range(struct inode *inode, ram_size, /* ram_bytes */ BTRFS_COMPRESS_NONE, /* compress_type */ BTRFS_ORDERED_REGULAR /* type */); - if (IS_ERR(em)) + if (IS_ERR(em)) { + ret = PTR_ERR(em); goto out_reserve; + } free_extent_map(em); ret = btrfs_add_ordered_extent(inode, start, ins.objectid, -- cgit v1.2.3 From 1c8d0175df47364aa55c568b65ed7a3aee5b9a6d Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Wed, 2 May 2018 15:19:32 +0300 Subject: btrfs: Factor out read portion of btrfs_get_blocks_direct Currently this function handles both the READ and WRITE dio cases. This is facilitated by a bunch of 'if' statements, a goto short-circuit statement and a very perverse aliasing of "!created"(READ) case by setting lockstart = lockend and checking for lockstart < lockend for detecting the write. Let's simplify this mess by extracting the READ-only code into a separate __btrfs_get_block_direct_read function. This is only the first step, the next one will be to factor out the write side as well. The end goal will be to have the common locking/ unlocking code in btrfs_get_blocks_direct and then it will call either the read|write subvariants. No functional changes. Signed-off-by: Nikolay Borisov Signed-off-by: David Sterba --- fs/btrfs/inode.c | 56 +++++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 43 insertions(+), 13 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f81a48c47fe0..4f8fb1130cf3 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7540,6 +7540,27 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len, return em; } + +static int btrfs_get_blocks_direct_read(struct extent_map *em, + struct buffer_head *bh_result, + struct inode *inode, + u64 start, u64 len) +{ + if (em->block_start == EXTENT_MAP_HOLE || + test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) + return -ENOENT; + + len = min(len, em->len - (start - em->start)); + + bh_result->b_blocknr = (em->block_start + (start - em->start)) >> + inode->i_blkbits; + bh_result->b_size = len; + bh_result->b_bdev = em->bdev; + set_buffer_mapped(bh_result); + + return 0; +} + static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { @@ -7608,11 +7629,29 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, goto unlock_err; } - /* Just a good old fashioned hole, return */ - if (!create && (em->block_start == EXTENT_MAP_HOLE || - test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) { + if (!create) { + ret = btrfs_get_blocks_direct_read(em, bh_result, inode, + start, len); + /* Can be negative only if we read from a hole */ + if (ret < 0) { + ret = 0; + free_extent_map(em); + goto unlock_err; + } + /* + * We need to unlock only the end area that we aren't using. + * The rest is going to be unlocked by the endio routine. + */ + lockstart = start + bh_result->b_size; + if (lockstart < lockend) { + clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, + lockend, unlock_bits, 1, 0, + &cached_state); + } else { + free_extent_state(cached_state); + } free_extent_map(em); - goto unlock_err; + return 0; } /* @@ -7624,12 +7663,6 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, * just use the extent. * */ - if (!create) { - len = min(len, em->len - (start - em->start)); - lockstart = start + len; - goto unlock; - } - if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) || ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) && em->block_start != EXTENT_MAP_HOLE)) { @@ -7716,10 +7749,7 @@ unlock: clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, unlock_bits, 1, 0, &cached_state); - } else { - free_extent_state(cached_state); } - free_extent_map(em); return 0; -- cgit v1.2.3 From c5794e51784a0a96dd82e8f955570a7eccf27e5d Mon Sep 17 00:00:00 2001 From: Nikolay Borisov Date: Wed, 2 May 2018 15:19:33 +0300 Subject: btrfs: Factor out write portion of btrfs_get_blocks_direct Now that the read side is extracted into its own function, do the same to the write side. This leaves btrfs_get_blocks_direct_write with the sole purpose of handling common locking required. Also flip the condition in btrfs_get_blocks_direct_write so that the write case comes first and we check for if (Create) rather than if (!create). This is purely subjective but I believe makes reading a bit more "linear". No functional changes. Signed-off-by: Nikolay Borisov Signed-off-by: David Sterba --- fs/btrfs/inode.c | 207 +++++++++++++++++++++++++++++-------------------------- 1 file changed, 108 insertions(+), 99 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 4f8fb1130cf3..880431ae5e59 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7561,6 +7561,104 @@ static int btrfs_get_blocks_direct_read(struct extent_map *em, return 0; } +static int btrfs_get_blocks_direct_write(struct extent_map **map, + struct buffer_head *bh_result, + struct inode *inode, + struct btrfs_dio_data *dio_data, + u64 start, u64 len) +{ + struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + struct extent_map *em = *map; + int ret = 0; + + /* + * We don't allocate a new extent in the following cases + * + * 1) The inode is marked as NODATACOW. In this case we'll just use the + * existing extent. + * 2) The extent is marked as PREALLOC. We're good to go here and can + * just use the extent. + * + */ + if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) || + ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) && + em->block_start != EXTENT_MAP_HOLE)) { + int type; + u64 block_start, orig_start, orig_block_len, ram_bytes; + + if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) + type = BTRFS_ORDERED_PREALLOC; + else + type = BTRFS_ORDERED_NOCOW; + len = min(len, em->len - (start - em->start)); + block_start = em->block_start + (start - em->start); + + if (can_nocow_extent(inode, start, &len, &orig_start, + &orig_block_len, &ram_bytes) == 1 && + btrfs_inc_nocow_writers(fs_info, block_start)) { + struct extent_map *em2; + + em2 = btrfs_create_dio_extent(inode, start, len, + orig_start, block_start, + len, orig_block_len, + ram_bytes, type); + btrfs_dec_nocow_writers(fs_info, block_start); + if (type == BTRFS_ORDERED_PREALLOC) { + free_extent_map(em); + *map = em = em2; + } + + if (em2 && IS_ERR(em2)) { + ret = PTR_ERR(em2); + goto out; + } + /* + * For inode marked NODATACOW or extent marked PREALLOC, + * use the existing or preallocated extent, so does not + * need to adjust btrfs_space_info's bytes_may_use. + */ + btrfs_free_reserved_data_space_noquota(inode, start, + len); + goto skip_cow; + } + } + + /* this will cow the extent */ + len = bh_result->b_size; + free_extent_map(em); + *map = em = btrfs_new_extent_direct(inode, start, len); + if (IS_ERR(em)) { + ret = PTR_ERR(em); + goto out; + } + + len = min(len, em->len - (start - em->start)); + +skip_cow: + bh_result->b_blocknr = (em->block_start + (start - em->start)) >> + inode->i_blkbits; + bh_result->b_size = len; + bh_result->b_bdev = em->bdev; + set_buffer_mapped(bh_result); + + if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) + set_buffer_new(bh_result); + + /* + * Need to update the i_size under the extent lock so buffered + * readers will get the updated i_size when we unlock. + */ + if (!dio_data->overwrite && start + len > i_size_read(inode)) + i_size_write(inode, start + len); + + WARN_ON(dio_data->reserve < len); + dio_data->reserve -= len; + dio_data->unsubmitted_oe_range_end = start + len; + current->journal_info = dio_data; +out: + return ret; +} + static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { @@ -7629,7 +7727,16 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, goto unlock_err; } - if (!create) { + if (create) { + ret = btrfs_get_blocks_direct_write(&em, bh_result, inode, + dio_data, start, len); + if (ret < 0) + goto unlock_err; + + /* clear and unlock the entire range */ + clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, + unlock_bits, 1, 0, &cached_state); + } else { ret = btrfs_get_blocks_direct_read(em, bh_result, inode, start, len); /* Can be negative only if we read from a hole */ @@ -7650,106 +7757,8 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, } else { free_extent_state(cached_state); } - free_extent_map(em); - return 0; } - /* - * We don't allocate a new extent in the following cases - * - * 1) The inode is marked as NODATACOW. In this case we'll just use the - * existing extent. - * 2) The extent is marked as PREALLOC. We're good to go here and can - * just use the extent. - * - */ - if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) || - ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) && - em->block_start != EXTENT_MAP_HOLE)) { - int type; - u64 block_start, orig_start, orig_block_len, ram_bytes; - - if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) - type = BTRFS_ORDERED_PREALLOC; - else - type = BTRFS_ORDERED_NOCOW; - len = min(len, em->len - (start - em->start)); - block_start = em->block_start + (start - em->start); - - if (can_nocow_extent(inode, start, &len, &orig_start, - &orig_block_len, &ram_bytes) == 1 && - btrfs_inc_nocow_writers(fs_info, block_start)) { - struct extent_map *em2; - - em2 = btrfs_create_dio_extent(inode, start, len, - orig_start, block_start, - len, orig_block_len, - ram_bytes, type); - btrfs_dec_nocow_writers(fs_info, block_start); - if (type == BTRFS_ORDERED_PREALLOC) { - free_extent_map(em); - em = em2; - } - if (em2 && IS_ERR(em2)) { - ret = PTR_ERR(em2); - goto unlock_err; - } - /* - * For inode marked NODATACOW or extent marked PREALLOC, - * use the existing or preallocated extent, so does not - * need to adjust btrfs_space_info's bytes_may_use. - */ - btrfs_free_reserved_data_space_noquota(inode, - start, len); - goto unlock; - } - } - - /* - * this will cow the extent, reset the len in case we changed - * it above - */ - len = bh_result->b_size; - free_extent_map(em); - em = btrfs_new_extent_direct(inode, start, len); - if (IS_ERR(em)) { - ret = PTR_ERR(em); - goto unlock_err; - } - len = min(len, em->len - (start - em->start)); -unlock: - bh_result->b_blocknr = (em->block_start + (start - em->start)) >> - inode->i_blkbits; - bh_result->b_size = len; - bh_result->b_bdev = em->bdev; - set_buffer_mapped(bh_result); - if (create) { - if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) - set_buffer_new(bh_result); - - /* - * Need to update the i_size under the extent lock so buffered - * readers will get the updated i_size when we unlock. - */ - if (!dio_data->overwrite && start + len > i_size_read(inode)) - i_size_write(inode, start + len); - - WARN_ON(dio_data->reserve < len); - dio_data->reserve -= len; - dio_data->unsubmitted_oe_range_end = start + len; - current->journal_info = dio_data; - } - - /* - * In the case of write we need to clear and unlock the entire range, - * in the case of read we need to unlock only the end area that we - * aren't using if there is any left over space. - */ - if (lockstart < lockend) { - clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, - lockend, unlock_bits, 1, 0, - &cached_state); - } free_extent_map(em); return 0; -- cgit v1.2.3 From ad7e1a740d940cf7da1beb332a1095bcda40c747 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Tue, 22 May 2018 09:59:50 -0700 Subject: Btrfs: clean up error handling in btrfs_truncate() btrfs_truncate() uses two variables for error handling, ret and err (if this sounds familiar, it's because btrfs_truncate_inode_items() did something similar). This is error prone, as was made evident by "Btrfs: fix error handling in btrfs_truncate()". We only have err because we don't want to mask an error if we call btrfs_update_inode() and btrfs_end_transaction(), so let's make that its own scoped return variable and use ret everywhere else. Reviewed-by: Nikolay Borisov Signed-off-by: Omar Sandoval Signed-off-by: David Sterba --- fs/btrfs/inode.c | 33 ++++++++++++++------------------- 1 file changed, 14 insertions(+), 19 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 880431ae5e59..89b208201783 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -9030,8 +9030,7 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback) struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_block_rsv *rsv; - int ret = 0; - int err = 0; + int ret; struct btrfs_trans_handle *trans; u64 mask = fs_info->sectorsize - 1; u64 min_size = btrfs_calc_trunc_metadata_size(fs_info, 1); @@ -9083,7 +9082,7 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback) */ trans = btrfs_start_transaction(root, 2); if (IS_ERR(trans)) { - err = PTR_ERR(trans); + ret = PTR_ERR(trans); goto out; } @@ -9107,24 +9106,19 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback) inode->i_size, BTRFS_EXTENT_DATA_KEY); trans->block_rsv = &fs_info->trans_block_rsv; - if (ret != -ENOSPC && ret != -EAGAIN) { - if (ret < 0) - err = ret; + if (ret != -ENOSPC && ret != -EAGAIN) break; - } ret = btrfs_update_inode(trans, root, inode); - if (ret) { - err = ret; + if (ret) break; - } btrfs_end_transaction(trans); btrfs_btree_balance_dirty(fs_info); trans = btrfs_start_transaction(root, 2); if (IS_ERR(trans)) { - ret = err = PTR_ERR(trans); + ret = PTR_ERR(trans); trans = NULL; break; } @@ -9158,21 +9152,22 @@ static int btrfs_truncate(struct inode *inode, bool skip_writeback) } if (trans) { + int ret2; + trans->block_rsv = &fs_info->trans_block_rsv; - ret = btrfs_update_inode(trans, root, inode); - if (ret && !err) - err = ret; + ret2 = btrfs_update_inode(trans, root, inode); + if (ret2 && !ret) + ret = ret2; - ret = btrfs_end_transaction(trans); + ret2 = btrfs_end_transaction(trans); + if (ret2 && !ret) + ret = ret2; btrfs_btree_balance_dirty(fs_info); } out: btrfs_free_block_rsv(fs_info, rsv); - if (ret && !err) - err = ret; - - return err; + return ret; } /* -- cgit v1.2.3 From 95582b00838837fc07e042979320caf917ce3fe6 Mon Sep 17 00:00:00 2001 From: Deepa Dinamani Date: Tue, 8 May 2018 19:36:02 -0700 Subject: vfs: change inode times to use struct timespec64 struct timespec is not y2038 safe. Transition vfs to use y2038 safe struct timespec64 instead. The change was made with the help of the following cocinelle script. This catches about 80% of the changes. All the header file and logic changes are included in the first 5 rules. The rest are trivial substitutions. I avoid changing any of the function signatures or any other filesystem specific data structures to keep the patch simple for review. The script can be a little shorter by combining different cases. But, this version was sufficient for my usecase. virtual patch @ depends on patch @ identifier now; @@ - struct timespec + struct timespec64 current_time ( ... ) { - struct timespec now = current_kernel_time(); + struct timespec64 now = current_kernel_time64(); ... - return timespec_trunc( + return timespec64_trunc( ... ); } @ depends on patch @ identifier xtime; @@ struct \( iattr \| inode \| kstat \) { ... - struct timespec xtime; + struct timespec64 xtime; ... } @ depends on patch @ identifier t; @@ struct inode_operations { ... int (*update_time) (..., - struct timespec t, + struct timespec64 t, ...); ... } @ depends on patch @ identifier t; identifier fn_update_time =~ "update_time$"; @@ fn_update_time (..., - struct timespec *t, + struct timespec64 *t, ...) { ... } @ depends on patch @ identifier t; @@ lease_get_mtime( ... , - struct timespec *t + struct timespec64 *t ) { ... } @te depends on patch forall@ identifier ts; local idexpression struct inode *inode_node; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn_update_time =~ "update_time$"; identifier fn; expression e, E3; local idexpression struct inode *node1; local idexpression struct inode *node2; local idexpression struct iattr *attr1; local idexpression struct iattr *attr2; local idexpression struct iattr attr; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; @@ ( ( - struct timespec ts; + struct timespec64 ts; | - struct timespec ts = current_time(inode_node); + struct timespec64 ts = current_time(inode_node); ) <+... when != ts ( - timespec_equal(&inode_node->i_xtime, &ts) + timespec64_equal(&inode_node->i_xtime, &ts) | - timespec_equal(&ts, &inode_node->i_xtime) + timespec64_equal(&ts, &inode_node->i_xtime) | - timespec_compare(&inode_node->i_xtime, &ts) + timespec64_compare(&inode_node->i_xtime, &ts) | - timespec_compare(&ts, &inode_node->i_xtime) + timespec64_compare(&ts, &inode_node->i_xtime) | ts = current_time(e) | fn_update_time(..., &ts,...) | inode_node->i_xtime = ts | node1->i_xtime = ts | ts = inode_node->i_xtime | <+... attr1->ia_xtime ...+> = ts | ts = attr1->ia_xtime | ts.tv_sec | ts.tv_nsec | btrfs_set_stack_timespec_sec(..., ts.tv_sec) | btrfs_set_stack_timespec_nsec(..., ts.tv_nsec) | - ts = timespec64_to_timespec( + ts = ... -) | - ts = ktime_to_timespec( + ts = ktime_to_timespec64( ...) | - ts = E3 + ts = timespec_to_timespec64(E3) | - ktime_get_real_ts(&ts) + ktime_get_real_ts64(&ts) | fn(..., - ts + timespec64_to_timespec(ts) ,...) ) ...+> ( <... when != ts - return ts; + return timespec64_to_timespec(ts); ...> ) | - timespec_equal(&node1->i_xtime1, &node2->i_xtime2) + timespec64_equal(&node1->i_xtime2, &node2->i_xtime2) | - timespec_equal(&node1->i_xtime1, &attr2->ia_xtime2) + timespec64_equal(&node1->i_xtime2, &attr2->ia_xtime2) | - timespec_compare(&node1->i_xtime1, &node2->i_xtime2) + timespec64_compare(&node1->i_xtime1, &node2->i_xtime2) | node1->i_xtime1 = - timespec_trunc(attr1->ia_xtime1, + timespec64_trunc(attr1->ia_xtime1, ...) | - attr1->ia_xtime1 = timespec_trunc(attr2->ia_xtime2, + attr1->ia_xtime1 = timespec64_trunc(attr2->ia_xtime2, ...) | - ktime_get_real_ts(&attr1->ia_xtime1) + ktime_get_real_ts64(&attr1->ia_xtime1) | - ktime_get_real_ts(&attr.ia_xtime1) + ktime_get_real_ts64(&attr.ia_xtime1) ) @ depends on patch @ struct inode *node; struct iattr *attr; identifier fn; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; expression e; @@ ( - fn(node->i_xtime); + fn(timespec64_to_timespec(node->i_xtime)); | fn(..., - node->i_xtime); + timespec64_to_timespec(node->i_xtime)); | - e = fn(attr->ia_xtime); + e = fn(timespec64_to_timespec(attr->ia_xtime)); ) @ depends on patch forall @ struct inode *node; struct iattr *attr; identifier i_xtime =~ "^i_[acm]time$"; identifier ia_xtime =~ "^ia_[acm]time$"; identifier fn; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); fn (..., - &attr->ia_xtime, + &ts, ...); ) ...+> } @ depends on patch forall @ struct inode *node; struct iattr *attr; struct kstat *stat; identifier ia_xtime =~ "^ia_[acm]time$"; identifier i_xtime =~ "^i_[acm]time$"; identifier xtime =~ "^[acm]time$"; identifier fn, ret; @@ { + struct timespec ts; <+... ( + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime, + &ts, ...); | + ts = timespec64_to_timespec(node->i_xtime); ret = fn (..., - &node->i_xtime); + &ts); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime, + &ts, ...); | + ts = timespec64_to_timespec(attr->ia_xtime); ret = fn (..., - &attr->ia_xtime); + &ts); | + ts = timespec64_to_timespec(stat->xtime); ret = fn (..., - &stat->xtime); + &ts); ) ...+> } @ depends on patch @ struct inode *node; struct inode *node2; identifier i_xtime1 =~ "^i_[acm]time$"; identifier i_xtime2 =~ "^i_[acm]time$"; identifier i_xtime3 =~ "^i_[acm]time$"; struct iattr *attrp; struct iattr *attrp2; struct iattr attr ; identifier ia_xtime1 =~ "^ia_[acm]time$"; identifier ia_xtime2 =~ "^ia_[acm]time$"; struct kstat *stat; struct kstat stat1; struct timespec64 ts; identifier xtime =~ "^[acmb]time$"; expression e; @@ ( ( node->i_xtime2 \| attrp->ia_xtime2 \| attr.ia_xtime2 \) = node->i_xtime1 ; | node->i_xtime2 = \( node2->i_xtime1 \| timespec64_trunc(...) \); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | node->i_xtime1 = node->i_xtime3 = \(ts \| current_time(...) \); | stat->xtime = node2->i_xtime1; | stat1.xtime = node2->i_xtime1; | ( node->i_xtime2 \| attrp->ia_xtime2 \) = attrp->ia_xtime1 ; | ( attrp->ia_xtime1 \| attr.ia_xtime1 \) = attrp2->ia_xtime2; | - e = node->i_xtime1; + e = timespec64_to_timespec( node->i_xtime1 ); | - e = attrp->ia_xtime1; + e = timespec64_to_timespec( attrp->ia_xtime1 ); | node->i_xtime1 = current_time(...); | node->i_xtime2 = node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | node->i_xtime1 = node->i_xtime3 = - e; + timespec_to_timespec64(e); | - node->i_xtime1 = e; + node->i_xtime1 = timespec_to_timespec64(e); ) Signed-off-by: Deepa Dinamani Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: Cc: --- drivers/tty/tty_io.c | 15 ++++++++++--- drivers/usb/gadget/function/f_fs.c | 2 +- fs/adfs/inode.c | 7 ++++-- fs/afs/fsclient.c | 2 +- fs/attr.c | 14 ++++++------ fs/bad_inode.c | 2 +- fs/btrfs/file.c | 6 +++--- fs/btrfs/inode.c | 8 +++---- fs/btrfs/ioctl.c | 4 ++-- fs/btrfs/root-tree.c | 4 ++-- fs/btrfs/transaction.c | 2 +- fs/ceph/addr.c | 12 ++++++----- fs/ceph/cache.c | 4 ++-- fs/ceph/caps.c | 6 +++--- fs/ceph/file.c | 6 +++--- fs/ceph/inode.c | 44 +++++++++++++++++++++----------------- fs/ceph/mds_client.c | 7 ++++-- fs/ceph/snap.c | 6 +++--- fs/cifs/cache.c | 4 ++-- fs/cifs/fscache.c | 8 +++---- fs/cifs/inode.c | 26 +++++++++++----------- fs/coda/coda_linux.c | 12 +++++------ fs/configfs/inode.c | 12 +++++------ fs/cramfs/inode.c | 2 +- fs/ext4/ext4.h | 34 +++++++++++++++++------------ fs/ext4/ialloc.c | 4 ++-- fs/ext4/namei.c | 2 +- fs/f2fs/f2fs.h | 10 ++++++--- fs/f2fs/file.c | 12 +++++------ fs/f2fs/inode.c | 12 +++++------ fs/f2fs/namei.c | 4 ++-- fs/fat/inode.c | 20 +++++++++++------ fs/fat/namei_msdos.c | 21 +++++++++++------- fs/fat/namei_vfat.c | 22 ++++++++++++------- fs/fuse/inode.c | 2 +- fs/gfs2/dir.c | 6 +++--- fs/gfs2/glops.c | 4 ++-- fs/hfs/inode.c | 4 ++-- fs/hfsplus/inode.c | 12 +++++------ fs/hostfs/hostfs_kern.c | 12 +++++------ fs/inode.c | 34 ++++++++++++++--------------- fs/jffs2/dir.c | 18 ++++++++-------- fs/jffs2/file.c | 2 +- fs/jffs2/fs.c | 12 +++++------ fs/kernfs/dir.c | 4 ++-- fs/kernfs/inode.c | 8 +++---- fs/locks.c | 2 +- fs/nfs/callback_proc.c | 4 ++-- fs/nfs/fscache-index.c | 4 ++-- fs/nfs/fscache.c | 12 +++++------ fs/nfs/inode.c | 39 +++++++++++++++++++-------------- fs/nfs/nfs2xdr.c | 25 +++++++++++++--------- fs/nfs/nfs3xdr.c | 8 +++++-- fs/nfs/nfs4xdr.c | 7 ++++-- fs/nfsd/blocklayout.c | 8 ++++--- fs/nfsd/nfs3xdr.c | 14 +++++++----- fs/nfsd/nfs4xdr.c | 7 ++++-- fs/nfsd/nfsxdr.c | 2 +- fs/ntfs/inode.c | 30 +++++++++++++------------- fs/ocfs2/dlmglue.c | 20 +++++++++++------ fs/ocfs2/file.c | 6 +++--- fs/orangefs/inode.c | 2 +- fs/orangefs/orangefs-kernel.h | 2 +- fs/overlayfs/inode.c | 2 +- fs/overlayfs/overlayfs.h | 2 +- fs/proc/uptime.c | 2 +- fs/pstore/inode.c | 3 +-- fs/reiserfs/namei.c | 2 +- fs/reiserfs/xattr.c | 4 ++-- fs/ubifs/dir.c | 4 ++-- fs/ubifs/file.c | 23 ++++++++++---------- fs/ubifs/ubifs.h | 2 +- fs/udf/ialloc.c | 4 ++-- fs/udf/inode.c | 43 ++++++++++++++++++++++++------------- fs/xfs/xfs_inode.c | 2 +- fs/xfs/xfs_iops.c | 2 +- fs/xfs/xfs_trans_inode.c | 2 +- include/linux/fs.h | 23 ++++++++++---------- include/linux/stat.h | 8 +++---- 79 files changed, 448 insertions(+), 346 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c index 7c838b90a31d..aba59521ad48 100644 --- a/drivers/tty/tty_io.c +++ b/drivers/tty/tty_io.c @@ -867,8 +867,13 @@ static ssize_t tty_read(struct file *file, char __user *buf, size_t count, i = -EIO; tty_ldisc_deref(ld); - if (i > 0) - tty_update_time(&inode->i_atime); + if (i > 0) { + struct timespec ts; + + ts = timespec64_to_timespec(inode->i_atime); + tty_update_time(&ts); + inode->i_atime = timespec_to_timespec64(ts); + } return i; } @@ -969,7 +974,11 @@ static inline ssize_t do_tty_write( cond_resched(); } if (written) { - tty_update_time(&file_inode(file)->i_mtime); + struct timespec ts; + + ts = timespec64_to_timespec(file_inode(file)->i_mtime); + tty_update_time(&ts); + file_inode(file)->i_mtime = timespec_to_timespec64(ts); ret = written; } out: diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index 0294e4f18873..d8a532fb935d 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -1297,7 +1297,7 @@ ffs_sb_make_inode(struct super_block *sb, void *data, inode = new_inode(sb); if (likely(inode)) { - struct timespec ts = current_time(inode); + struct timespec64 ts = current_time(inode); inode->i_ino = get_next_ino(); inode->i_mode = perms->mode; diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index 8dbd36f5e581..c836c425ca94 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -199,7 +199,7 @@ adfs_adfs2unix_time(struct timespec *tv, struct inode *inode) return; cur_time: - *tv = current_time(inode); + *tv = timespec64_to_timespec(current_time(inode)); return; too_early: @@ -242,6 +242,7 @@ adfs_unix2adfs_time(struct inode *inode, unsigned int secs) struct inode * adfs_iget(struct super_block *sb, struct object_info *obj) { + struct timespec ts; struct inode *inode; inode = new_inode(sb); @@ -270,7 +271,9 @@ adfs_iget(struct super_block *sb, struct object_info *obj) ADFS_I(inode)->stamped = ((obj->loadaddr & 0xfff00000) == 0xfff00000); inode->i_mode = adfs_atts2mode(sb, inode); - adfs_adfs2unix_time(&inode->i_mtime, inode); + ts = timespec64_to_timespec(inode->i_mtime); + adfs_adfs2unix_time(&ts, inode); + inode->i_mtime = timespec_to_timespec64(ts); inode->i_atime = inode->i_mtime; inode->i_ctime = inode->i_mtime; diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c index b273e1d60478..5907601aafd0 100644 --- a/fs/afs/fsclient.c +++ b/fs/afs/fsclient.c @@ -72,7 +72,7 @@ void afs_update_inode_from_status(struct afs_vnode *vnode, const afs_dataversion_t *expected_version, u8 flags) { - struct timespec t; + struct timespec64 t; umode_t mode; t.tv_sec = status->mtime_client; diff --git a/fs/attr.c b/fs/attr.c index 12ffdb6fb63c..63b17ef9e5ac 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -163,14 +163,14 @@ void setattr_copy(struct inode *inode, const struct iattr *attr) if (ia_valid & ATTR_GID) inode->i_gid = attr->ia_gid; if (ia_valid & ATTR_ATIME) - inode->i_atime = timespec_trunc(attr->ia_atime, - inode->i_sb->s_time_gran); + inode->i_atime = timespec64_trunc(attr->ia_atime, + inode->i_sb->s_time_gran); if (ia_valid & ATTR_MTIME) - inode->i_mtime = timespec_trunc(attr->ia_mtime, - inode->i_sb->s_time_gran); + inode->i_mtime = timespec64_trunc(attr->ia_mtime, + inode->i_sb->s_time_gran); if (ia_valid & ATTR_CTIME) - inode->i_ctime = timespec_trunc(attr->ia_ctime, - inode->i_sb->s_time_gran); + inode->i_ctime = timespec64_trunc(attr->ia_ctime, + inode->i_sb->s_time_gran); if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; @@ -207,7 +207,7 @@ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **de struct inode *inode = dentry->d_inode; umode_t mode = inode->i_mode; int error; - struct timespec now; + struct timespec64 now; unsigned int ia_valid = attr->ia_valid; WARN_ON_ONCE(!inode_is_locked(inode)); diff --git a/fs/bad_inode.c b/fs/bad_inode.c index 213b51dbbb60..125e8bbd22a2 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -126,7 +126,7 @@ static int bad_inode_fiemap(struct inode *inode, return -EIO; } -static int bad_inode_update_time(struct inode *inode, struct timespec *time, +static int bad_inode_update_time(struct inode *inode, struct timespec64 *time, int flags) { return -EIO; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index f660ba1e5e58..51e77d72068a 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1842,16 +1842,16 @@ out: static void update_time_for_write(struct inode *inode) { - struct timespec now; + struct timespec64 now; if (IS_NOCMTIME(inode)) return; now = current_time(inode); - if (!timespec_equal(&inode->i_mtime, &now)) + if (!timespec64_equal(&inode->i_mtime, &now)) inode->i_mtime = now; - if (!timespec_equal(&inode->i_ctime, &now)) + if (!timespec64_equal(&inode->i_ctime, &now)) inode->i_ctime = now; if (IS_I_VERSION(inode)) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 8e604e7071f1..233a2bf70351 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5777,7 +5777,7 @@ static struct inode *new_simple_dir(struct super_block *s, inode->i_mtime = current_time(inode); inode->i_atime = inode->i_mtime; inode->i_ctime = inode->i_mtime; - BTRFS_I(inode)->i_otime = inode->i_mtime; + BTRFS_I(inode)->i_otime = timespec64_to_timespec(inode->i_mtime); return inode; } @@ -6131,7 +6131,7 @@ static int btrfs_dirty_inode(struct inode *inode) * This is a copy of file_update_time. We need this so we can return error on * ENOSPC for updating the inode in the case of file write and mmap writes. */ -static int btrfs_update_time(struct inode *inode, struct timespec *now, +static int btrfs_update_time(struct inode *inode, struct timespec64 *now, int flags) { struct btrfs_root *root = BTRFS_I(inode)->root; @@ -6386,7 +6386,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans, inode->i_mtime = current_time(inode); inode->i_atime = inode->i_mtime; inode->i_ctime = inode->i_mtime; - BTRFS_I(inode)->i_otime = inode->i_mtime; + BTRFS_I(inode)->i_otime = timespec64_to_timespec(inode->i_mtime); inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); @@ -9471,7 +9471,7 @@ static int btrfs_rename_exchange(struct inode *old_dir, struct btrfs_root *dest = BTRFS_I(new_dir)->root; struct inode *new_inode = new_dentry->d_inode; struct inode *old_inode = old_dentry->d_inode; - struct timespec ctime = current_time(old_inode); + struct timespec64 ctime = current_time(old_inode); struct dentry *parent; u64 old_ino = btrfs_ino(BTRFS_I(old_inode)); u64 new_ino = btrfs_ino(BTRFS_I(new_inode)); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 632e26d6f7ce..09c6bec14956 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -417,7 +417,7 @@ static noinline int create_subvol(struct inode *dir, struct btrfs_root *root = BTRFS_I(dir)->root; struct btrfs_root *new_root; struct btrfs_block_rsv block_rsv; - struct timespec cur_time = current_time(dir); + struct timespec64 cur_time = current_time(dir); struct inode *inode; int ret; int err; @@ -4996,7 +4996,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file, struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_root_item *root_item = &root->root_item; struct btrfs_trans_handle *trans; - struct timespec ct = current_time(inode); + struct timespec64 ct = current_time(inode); int ret = 0; int received_uuid_changed; diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 6db3bda44aa5..c451285976ac 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -485,9 +485,9 @@ void btrfs_update_root_times(struct btrfs_trans_handle *trans, struct btrfs_root *root) { struct btrfs_root_item *item = &root->root_item; - struct timespec ct; + struct timespec64 ct; - ktime_get_real_ts(&ct); + ktime_get_real_ts64(&ct); spin_lock(&root->root_item_lock); btrfs_set_root_ctransid(item, trans->transid); btrfs_set_stack_timespec_sec(&item->ctime, ct.tv_sec); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index c944b4769e3c..7ac0d05571ca 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1428,7 +1428,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, struct dentry *dentry; struct extent_buffer *tmp; struct extent_buffer *old; - struct timespec cur_time; + struct timespec64 cur_time; int ret = 0; u64 to_reserve = 0; u64 index = 0; diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 5f7ad3d0df2e..0133ea2b784a 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -574,6 +574,7 @@ static u64 get_writepages_data_length(struct inode *inode, */ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) { + struct timespec ts; struct inode *inode; struct ceph_inode_info *ci; struct ceph_fs_client *fsc; @@ -624,11 +625,12 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc) set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC); set_page_writeback(page); + ts = timespec64_to_timespec(inode->i_mtime); err = ceph_osdc_writepages(&fsc->client->osdc, ceph_vino(inode), &ci->i_layout, snapc, page_off, len, ceph_wbc.truncate_seq, ceph_wbc.truncate_size, - &inode->i_mtime, &page, 1); + &ts, &page, 1); if (err < 0) { struct writeback_control tmp_wbc; if (!wbc) @@ -1131,7 +1133,7 @@ new_request: pages = NULL; } - req->r_mtime = inode->i_mtime; + req->r_mtime = timespec64_to_timespec(inode->i_mtime); rc = ceph_osdc_start_request(&fsc->client->osdc, req, true); BUG_ON(rc); req = NULL; @@ -1731,7 +1733,7 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page) goto out; } - req->r_mtime = inode->i_mtime; + req->r_mtime = timespec64_to_timespec(inode->i_mtime); err = ceph_osdc_start_request(&fsc->client->osdc, req, false); if (!err) err = ceph_osdc_wait_request(&fsc->client->osdc, req); @@ -1773,7 +1775,7 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page) goto out_put; } - req->r_mtime = inode->i_mtime; + req->r_mtime = timespec64_to_timespec(inode->i_mtime); err = ceph_osdc_start_request(&fsc->client->osdc, req, false); if (!err) err = ceph_osdc_wait_request(&fsc->client->osdc, req); @@ -1934,7 +1936,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci, 0, false, true); err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false); - wr_req->r_mtime = ci->vfs_inode.i_mtime; + wr_req->r_mtime = timespec64_to_timespec(ci->vfs_inode.i_mtime); wr_req->r_abort_on_full = true; err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false); diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c index bb524c880b1e..362900e42424 100644 --- a/fs/ceph/cache.c +++ b/fs/ceph/cache.c @@ -130,7 +130,7 @@ static enum fscache_checkaux ceph_fscache_inode_check_aux( memset(&aux, 0, sizeof(aux)); aux.version = ci->i_version; - aux.mtime = inode->i_mtime; + aux.mtime = timespec64_to_timespec(inode->i_mtime); if (memcmp(data, &aux, sizeof(aux)) != 0) return FSCACHE_CHECKAUX_OBSOLETE; @@ -163,7 +163,7 @@ void ceph_fscache_register_inode_cookie(struct inode *inode) if (!ci->fscache) { memset(&aux, 0, sizeof(aux)); aux.version = ci->i_version; - aux.mtime = inode->i_mtime; + aux.mtime = timespec64_to_timespec(inode->i_mtime); ci->fscache = fscache_acquire_cookie(fsc->fscache, &ceph_fscache_inode_object_def, &ci->i_vino, sizeof(ci->i_vino), diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 23dbfae16156..96b2ce936daa 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1358,9 +1358,9 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap, arg.xattr_buf = NULL; } - arg.mtime = inode->i_mtime; - arg.atime = inode->i_atime; - arg.ctime = inode->i_ctime; + arg.mtime = timespec64_to_timespec(inode->i_mtime); + arg.atime = timespec64_to_timespec(inode->i_atime); + arg.ctime = timespec64_to_timespec(inode->i_ctime); arg.op = op; arg.caps = cap->implemented; diff --git a/fs/ceph/file.c b/fs/ceph/file.c index cf0e45b10121..e962d672baf2 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -924,7 +924,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, int num_pages = 0; int flags; int ret; - struct timespec mtime = current_time(inode); + struct timespec mtime = timespec64_to_timespec(current_time(inode)); size_t count = iov_iter_count(iter); loff_t pos = iocb->ki_pos; bool write = iov_iter_rw(iter) == WRITE; @@ -1132,7 +1132,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos, int flags; int ret; bool check_caps = false; - struct timespec mtime = current_time(inode); + struct timespec mtime = timespec64_to_timespec(current_time(inode)); size_t count = iov_iter_count(from); if (ceph_snap(file_inode(file)) != CEPH_NOSNAP) @@ -1664,7 +1664,7 @@ static int ceph_zero_partial_object(struct inode *inode, goto out; } - req->r_mtime = inode->i_mtime; + req->r_mtime = timespec64_to_timespec(inode->i_mtime); ret = ceph_osdc_start_request(&fsc->client->osdc, req, false); if (!ret) { ret = ceph_osdc_wait_request(&fsc->client->osdc, req); diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 676065a1ea62..700fd652cc77 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -662,6 +662,9 @@ void ceph_fill_file_time(struct inode *inode, int issued, struct timespec *mtime, struct timespec *atime) { struct ceph_inode_info *ci = ceph_inode(inode); + struct timespec64 ctime64 = timespec_to_timespec64(*ctime); + struct timespec64 mtime64 = timespec_to_timespec64(*mtime); + struct timespec64 atime64 = timespec_to_timespec64(*atime); int warn = 0; if (issued & (CEPH_CAP_FILE_EXCL| @@ -670,11 +673,11 @@ void ceph_fill_file_time(struct inode *inode, int issued, CEPH_CAP_AUTH_EXCL| CEPH_CAP_XATTR_EXCL)) { if (ci->i_version == 0 || - timespec_compare(ctime, &inode->i_ctime) > 0) { + timespec64_compare(&ctime64, &inode->i_ctime) > 0) { dout("ctime %lld.%09ld -> %lld.%09ld inc w/ cap\n", (long long)inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec, (long long)ctime->tv_sec, ctime->tv_nsec); - inode->i_ctime = *ctime; + inode->i_ctime = ctime64; } if (ci->i_version == 0 || ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) > 0) { @@ -685,24 +688,24 @@ void ceph_fill_file_time(struct inode *inode, int issued, (long long)mtime->tv_sec, mtime->tv_nsec, ci->i_time_warp_seq, (int)time_warp_seq); - inode->i_mtime = *mtime; - inode->i_atime = *atime; + inode->i_mtime = mtime64; + inode->i_atime = atime64; ci->i_time_warp_seq = time_warp_seq; } else if (time_warp_seq == ci->i_time_warp_seq) { /* nobody did utimes(); take the max */ - if (timespec_compare(mtime, &inode->i_mtime) > 0) { + if (timespec64_compare(&mtime64, &inode->i_mtime) > 0) { dout("mtime %lld.%09ld -> %lld.%09ld inc\n", (long long)inode->i_mtime.tv_sec, inode->i_mtime.tv_nsec, (long long)mtime->tv_sec, mtime->tv_nsec); - inode->i_mtime = *mtime; + inode->i_mtime = mtime64; } - if (timespec_compare(atime, &inode->i_atime) > 0) { + if (timespec64_compare(&atime64, &inode->i_atime) > 0) { dout("atime %lld.%09ld -> %lld.%09ld inc\n", (long long)inode->i_atime.tv_sec, inode->i_atime.tv_nsec, (long long)atime->tv_sec, atime->tv_nsec); - inode->i_atime = *atime; + inode->i_atime = atime64; } } else if (issued & CEPH_CAP_FILE_EXCL) { /* we did a utimes(); ignore mds values */ @@ -712,9 +715,9 @@ void ceph_fill_file_time(struct inode *inode, int issued, } else { /* we have no write|excl caps; whatever the MDS says is true */ if (ceph_seq_cmp(time_warp_seq, ci->i_time_warp_seq) >= 0) { - inode->i_ctime = *ctime; - inode->i_mtime = *mtime; - inode->i_atime = *atime; + inode->i_ctime = ctime64; + inode->i_mtime = mtime64; + inode->i_atime = atime64; ci->i_time_warp_seq = time_warp_seq; } else { warn = 1; @@ -1941,6 +1944,7 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) int err = 0; int inode_dirty_flags = 0; bool lock_snap_rwsem = false; + struct timespec ts; prealloc_cf = ceph_alloc_cap_flush(); if (!prealloc_cf) @@ -2023,14 +2027,14 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) inode->i_atime = attr->ia_atime; dirtied |= CEPH_CAP_FILE_EXCL; } else if ((issued & CEPH_CAP_FILE_WR) && - timespec_compare(&inode->i_atime, + timespec64_compare(&inode->i_atime, &attr->ia_atime) < 0) { inode->i_atime = attr->ia_atime; dirtied |= CEPH_CAP_FILE_WR; } else if ((issued & CEPH_CAP_FILE_SHARED) == 0 || - !timespec_equal(&inode->i_atime, &attr->ia_atime)) { - ceph_encode_timespec(&req->r_args.setattr.atime, - &attr->ia_atime); + !timespec64_equal(&inode->i_atime, &attr->ia_atime)) { + ts = timespec64_to_timespec(attr->ia_atime); + ceph_encode_timespec(&req->r_args.setattr.atime, &ts); mask |= CEPH_SETATTR_ATIME; release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR; @@ -2045,14 +2049,14 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) inode->i_mtime = attr->ia_mtime; dirtied |= CEPH_CAP_FILE_EXCL; } else if ((issued & CEPH_CAP_FILE_WR) && - timespec_compare(&inode->i_mtime, + timespec64_compare(&inode->i_mtime, &attr->ia_mtime) < 0) { inode->i_mtime = attr->ia_mtime; dirtied |= CEPH_CAP_FILE_WR; } else if ((issued & CEPH_CAP_FILE_SHARED) == 0 || - !timespec_equal(&inode->i_mtime, &attr->ia_mtime)) { - ceph_encode_timespec(&req->r_args.setattr.mtime, - &attr->ia_mtime); + !timespec64_equal(&inode->i_mtime, &attr->ia_mtime)) { + ts = timespec64_to_timespec(attr->ia_mtime); + ceph_encode_timespec(&req->r_args.setattr.mtime, &ts); mask |= CEPH_SETATTR_MTIME; release |= CEPH_CAP_FILE_SHARED | CEPH_CAP_FILE_RD | CEPH_CAP_FILE_WR; @@ -2126,7 +2130,7 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr) req->r_inode_drop = release; req->r_args.setattr.mask = cpu_to_le32(mask); req->r_num_caps = 1; - req->r_stamp = attr->ia_ctime; + req->r_stamp = timespec64_to_timespec(attr->ia_ctime); err = ceph_mdsc_do_request(mdsc, NULL, req); } dout("setattr %p result=%d (%s locally, %d remote)\n", inode, err, diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 5ece2e6ad154..9460a92ce56d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2958,12 +2958,15 @@ static int encode_caps_cb(struct inode *inode, struct ceph_cap *cap, rec.v2.flock_len = (__force __le32) ((ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) ? 0 : 1); } else { + struct timespec ts; rec.v1.cap_id = cpu_to_le64(cap->cap_id); rec.v1.wanted = cpu_to_le32(__ceph_caps_wanted(ci)); rec.v1.issued = cpu_to_le32(cap->issued); rec.v1.size = cpu_to_le64(inode->i_size); - ceph_encode_timespec(&rec.v1.mtime, &inode->i_mtime); - ceph_encode_timespec(&rec.v1.atime, &inode->i_atime); + ts = timespec64_to_timespec(inode->i_mtime); + ceph_encode_timespec(&rec.v1.mtime, &ts); + ts = timespec64_to_timespec(inode->i_atime); + ceph_encode_timespec(&rec.v1.atime, &ts); rec.v1.snaprealm = cpu_to_le64(ci->i_snap_realm->ino); rec.v1.pathbase = cpu_to_le64(pathbase); } diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c index 041c27ea8de1..af81555c14fd 100644 --- a/fs/ceph/snap.c +++ b/fs/ceph/snap.c @@ -594,9 +594,9 @@ int __ceph_finish_cap_snap(struct ceph_inode_info *ci, BUG_ON(capsnap->writing); capsnap->size = inode->i_size; - capsnap->mtime = inode->i_mtime; - capsnap->atime = inode->i_atime; - capsnap->ctime = inode->i_ctime; + capsnap->mtime = timespec64_to_timespec(inode->i_mtime); + capsnap->atime = timespec64_to_timespec(inode->i_atime); + capsnap->ctime = timespec64_to_timespec(inode->i_ctime); capsnap->time_warp_seq = ci->i_time_warp_seq; capsnap->truncate_size = ci->i_truncate_size; capsnap->truncate_seq = ci->i_truncate_seq; diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c index edf5f40898bf..e1553d1e0e50 100644 --- a/fs/cifs/cache.c +++ b/fs/cifs/cache.c @@ -128,8 +128,8 @@ fscache_checkaux cifs_fscache_inode_check_aux(void *cookie_netfs_data, memset(&auxdata, 0, sizeof(auxdata)); auxdata.eof = cifsi->server_eof; - auxdata.last_write_time = cifsi->vfs_inode.i_mtime; - auxdata.last_change_time = cifsi->vfs_inode.i_ctime; + auxdata.last_write_time = timespec64_to_timespec(cifsi->vfs_inode.i_mtime); + auxdata.last_change_time = timespec64_to_timespec(cifsi->vfs_inode.i_ctime); if (memcmp(data, &auxdata, datalen) != 0) return FSCACHE_CHECKAUX_OBSOLETE; diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index 25d3f66b2d50..85145a763021 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -129,8 +129,8 @@ static void cifs_fscache_acquire_inode_cookie(struct cifsInodeInfo *cifsi, memset(&auxdata, 0, sizeof(auxdata)); auxdata.eof = cifsi->server_eof; - auxdata.last_write_time = cifsi->vfs_inode.i_mtime; - auxdata.last_change_time = cifsi->vfs_inode.i_ctime; + auxdata.last_write_time = timespec64_to_timespec(cifsi->vfs_inode.i_mtime); + auxdata.last_change_time = timespec64_to_timespec(cifsi->vfs_inode.i_ctime); cifsi->fscache = fscache_acquire_cookie(tcon->fscache, @@ -166,8 +166,8 @@ void cifs_fscache_release_inode_cookie(struct inode *inode) if (cifsi->fscache) { memset(&auxdata, 0, sizeof(auxdata)); auxdata.eof = cifsi->server_eof; - auxdata.last_write_time = cifsi->vfs_inode.i_mtime; - auxdata.last_change_time = cifsi->vfs_inode.i_ctime; + auxdata.last_write_time = timespec64_to_timespec(cifsi->vfs_inode.i_mtime); + auxdata.last_change_time = timespec64_to_timespec(cifsi->vfs_inode.i_ctime); cifs_dbg(FYI, "%s: (0x%p)\n", __func__, cifsi->fscache); fscache_relinquish_cookie(cifsi->fscache, &auxdata, false); diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 3c371f7f5963..6be9a7cfaf0e 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -95,6 +95,7 @@ static void cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr) { struct cifsInodeInfo *cifs_i = CIFS_I(inode); + struct timespec ts; cifs_dbg(FYI, "%s: revalidating inode %llu\n", __func__, cifs_i->uniqueid); @@ -113,7 +114,8 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr) } /* revalidate if mtime or size have changed */ - if (timespec_equal(&inode->i_mtime, &fattr->cf_mtime) && + ts = timespec64_to_timespec(inode->i_mtime); + if (timespec_equal(&ts, &fattr->cf_mtime) && cifs_i->server_eof == fattr->cf_eof) { cifs_dbg(FYI, "%s: inode %llu is unchanged\n", __func__, cifs_i->uniqueid); @@ -162,9 +164,9 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr) cifs_revalidate_cache(inode, fattr); spin_lock(&inode->i_lock); - inode->i_atime = fattr->cf_atime; - inode->i_mtime = fattr->cf_mtime; - inode->i_ctime = fattr->cf_ctime; + inode->i_atime = timespec_to_timespec64(fattr->cf_atime); + inode->i_mtime = timespec_to_timespec64(fattr->cf_mtime); + inode->i_ctime = timespec_to_timespec64(fattr->cf_ctime); inode->i_rdev = fattr->cf_rdev; cifs_nlink_fattr_to_inode(inode, fattr); inode->i_uid = fattr->cf_uid; @@ -1122,14 +1124,14 @@ cifs_set_file_info(struct inode *inode, struct iattr *attrs, unsigned int xid, if (attrs->ia_valid & ATTR_ATIME) { set_time = true; info_buf.LastAccessTime = - cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_atime)); + cpu_to_le64(cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_atime))); } else info_buf.LastAccessTime = 0; if (attrs->ia_valid & ATTR_MTIME) { set_time = true; info_buf.LastWriteTime = - cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_mtime)); + cpu_to_le64(cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_mtime))); } else info_buf.LastWriteTime = 0; @@ -1142,7 +1144,7 @@ cifs_set_file_info(struct inode *inode, struct iattr *attrs, unsigned int xid, if (set_time && (attrs->ia_valid & ATTR_CTIME)) { cifs_dbg(FYI, "CIFS - CTIME changed\n"); info_buf.ChangeTime = - cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_ctime)); + cpu_to_le64(cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_ctime))); } else info_buf.ChangeTime = 0; @@ -2059,8 +2061,8 @@ int cifs_getattr(const struct path *path, struct kstat *stat, /* old CIFS Unix Extensions doesn't return create time */ if (CIFS_I(inode)->createtime) { stat->result_mask |= STATX_BTIME; - stat->btime = - cifs_NTtimeToUnix(cpu_to_le64(CIFS_I(inode)->createtime)); + stat->btime = timespec_to_timespec64( + cifs_NTtimeToUnix(cpu_to_le64(CIFS_I(inode)->createtime))); } stat->attributes_mask |= (STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED); @@ -2262,17 +2264,17 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs) args->gid = INVALID_GID; /* no change */ if (attrs->ia_valid & ATTR_ATIME) - args->atime = cifs_UnixTimeToNT(attrs->ia_atime); + args->atime = cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_atime)); else args->atime = NO_CHANGE_64; if (attrs->ia_valid & ATTR_MTIME) - args->mtime = cifs_UnixTimeToNT(attrs->ia_mtime); + args->mtime = cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_mtime)); else args->mtime = NO_CHANGE_64; if (attrs->ia_valid & ATTR_CTIME) - args->ctime = cifs_UnixTimeToNT(attrs->ia_ctime); + args->ctime = cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_ctime)); else args->ctime = NO_CHANGE_64; diff --git a/fs/coda/coda_linux.c b/fs/coda/coda_linux.c index ca599df0dcb1..f3d543dd9a98 100644 --- a/fs/coda/coda_linux.c +++ b/fs/coda/coda_linux.c @@ -105,11 +105,11 @@ void coda_vattr_to_iattr(struct inode *inode, struct coda_vattr *attr) if (attr->va_size != -1) inode->i_blocks = (attr->va_size + 511) >> 9; if (attr->va_atime.tv_sec != -1) - inode->i_atime = attr->va_atime; + inode->i_atime = timespec_to_timespec64(attr->va_atime); if (attr->va_mtime.tv_sec != -1) - inode->i_mtime = attr->va_mtime; + inode->i_mtime = timespec_to_timespec64(attr->va_mtime); if (attr->va_ctime.tv_sec != -1) - inode->i_ctime = attr->va_ctime; + inode->i_ctime = timespec_to_timespec64(attr->va_ctime); } @@ -175,13 +175,13 @@ void coda_iattr_to_vattr(struct iattr *iattr, struct coda_vattr *vattr) vattr->va_size = iattr->ia_size; } if ( valid & ATTR_ATIME ) { - vattr->va_atime = iattr->ia_atime; + vattr->va_atime = timespec64_to_timespec(iattr->ia_atime); } if ( valid & ATTR_MTIME ) { - vattr->va_mtime = iattr->ia_mtime; + vattr->va_mtime = timespec64_to_timespec(iattr->ia_mtime); } if ( valid & ATTR_CTIME ) { - vattr->va_ctime = iattr->ia_ctime; + vattr->va_ctime = timespec64_to_timespec(iattr->ia_ctime); } } diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index ad718e5e37bb..28ef9e528853 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -90,14 +90,14 @@ int configfs_setattr(struct dentry * dentry, struct iattr * iattr) if (ia_valid & ATTR_GID) sd_iattr->ia_gid = iattr->ia_gid; if (ia_valid & ATTR_ATIME) - sd_iattr->ia_atime = timespec_trunc(iattr->ia_atime, - inode->i_sb->s_time_gran); + sd_iattr->ia_atime = timespec64_trunc(iattr->ia_atime, + inode->i_sb->s_time_gran); if (ia_valid & ATTR_MTIME) - sd_iattr->ia_mtime = timespec_trunc(iattr->ia_mtime, - inode->i_sb->s_time_gran); + sd_iattr->ia_mtime = timespec64_trunc(iattr->ia_mtime, + inode->i_sb->s_time_gran); if (ia_valid & ATTR_CTIME) - sd_iattr->ia_ctime = timespec_trunc(iattr->ia_ctime, - inode->i_sb->s_time_gran); + sd_iattr->ia_ctime = timespec64_trunc(iattr->ia_ctime, + inode->i_sb->s_time_gran); if (ia_valid & ATTR_MODE) { umode_t mode = iattr->ia_mode; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 017b0ab19bc4..d7a600e00f28 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -90,7 +90,7 @@ static struct inode *get_cramfs_inode(struct super_block *sb, const struct cramfs_inode *cramfs_inode, unsigned int offset) { struct inode *inode; - static struct timespec zerotime; + static struct timespec64 zerotime; inode = iget_locked(sb, cramino(cramfs_inode, offset)); if (!inode) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index a42e71203e53..f76d0777f7ad 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -817,12 +817,14 @@ static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra) time->tv_nsec = (le32_to_cpu(extra) & EXT4_NSEC_MASK) >> EXT4_EPOCH_BITS; } -#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \ -do { \ - (raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec); \ - if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) \ - (raw_inode)->xtime ## _extra = \ - ext4_encode_extra_time(&(inode)->xtime); \ +#define EXT4_INODE_SET_XTIME(xtime, inode, raw_inode) \ +do { \ + (raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec); \ + if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) {\ + struct timespec ts = timespec64_to_timespec((inode)->xtime); \ + (raw_inode)->xtime ## _extra = \ + ext4_encode_extra_time(&ts); \ + } \ } while (0) #define EXT4_EINODE_SET_XTIME(xtime, einode, raw_inode) \ @@ -834,16 +836,20 @@ do { \ ext4_encode_extra_time(&(einode)->xtime); \ } while (0) -#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode) \ -do { \ - (inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime); \ - if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) \ - ext4_decode_extra_time(&(inode)->xtime, \ - raw_inode->xtime ## _extra); \ - else \ - (inode)->xtime.tv_nsec = 0; \ +#define EXT4_INODE_GET_XTIME(xtime, inode, raw_inode) \ +do { \ + (inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime); \ + if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) { \ + struct timespec ts = timespec64_to_timespec((inode)->xtime); \ + ext4_decode_extra_time(&ts, \ + raw_inode->xtime ## _extra); \ + (inode)->xtime = timespec_to_timespec64(ts); \ + } \ + else \ + (inode)->xtime.tv_nsec = 0; \ } while (0) + #define EXT4_EINODE_GET_XTIME(xtime, einode, raw_inode) \ do { \ if (EXT4_FITS_IN_INODE(raw_inode, einode, xtime)) \ diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index df92e3ec9913..751e1be2c652 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -1078,8 +1078,8 @@ got: inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb); /* This is the optimal IO size (for stat), not the fs block size */ inode->i_blocks = 0; - inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime = - current_time(inode); + inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); + ei->i_crtime = timespec64_to_timespec(inode->i_mtime); memset(ei->i_data, 0, sizeof(ei->i_data)); ei->i_dir_start_lookup = 0; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index b1f21e3a0763..2feb546dfcaf 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -3675,7 +3675,7 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry, }; u8 new_file_type; int retval; - struct timespec ctime; + struct timespec64 ctime; if ((ext4_test_inode_flag(new_dir, EXT4_INODE_PROJINHERIT) && !projid_eq(EXT4_I(new_dir)->i_projid, diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 1df7f10476d6..57e663b37dc8 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -2460,6 +2460,7 @@ static inline void clear_file(struct inode *inode, int type) static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync) { + struct timespec ts; bool ret; if (dsync) { @@ -2475,11 +2476,14 @@ static inline bool f2fs_skip_inode_update(struct inode *inode, int dsync) i_size_read(inode) & ~PAGE_MASK) return false; - if (!timespec_equal(F2FS_I(inode)->i_disk_time, &inode->i_atime)) + ts = timespec64_to_timespec(inode->i_atime); + if (!timespec_equal(F2FS_I(inode)->i_disk_time, &ts)) return false; - if (!timespec_equal(F2FS_I(inode)->i_disk_time + 1, &inode->i_ctime)) + ts = timespec64_to_timespec(inode->i_ctime); + if (!timespec_equal(F2FS_I(inode)->i_disk_time + 1, &ts)) return false; - if (!timespec_equal(F2FS_I(inode)->i_disk_time + 2, &inode->i_mtime)) + ts = timespec64_to_timespec(inode->i_mtime); + if (!timespec_equal(F2FS_I(inode)->i_disk_time + 2, &ts)) return false; if (!timespec_equal(F2FS_I(inode)->i_disk_time + 3, &F2FS_I(inode)->i_crtime)) diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 6b94f19b3fa8..5f353302fdc6 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -724,14 +724,14 @@ static void __setattr_copy(struct inode *inode, const struct iattr *attr) if (ia_valid & ATTR_GID) inode->i_gid = attr->ia_gid; if (ia_valid & ATTR_ATIME) - inode->i_atime = timespec_trunc(attr->ia_atime, - inode->i_sb->s_time_gran); + inode->i_atime = timespec64_trunc(attr->ia_atime, + inode->i_sb->s_time_gran); if (ia_valid & ATTR_MTIME) - inode->i_mtime = timespec_trunc(attr->ia_mtime, - inode->i_sb->s_time_gran); + inode->i_mtime = timespec64_trunc(attr->ia_mtime, + inode->i_sb->s_time_gran); if (ia_valid & ATTR_CTIME) - inode->i_ctime = timespec_trunc(attr->ia_ctime, - inode->i_sb->s_time_gran); + inode->i_ctime = timespec64_trunc(attr->ia_ctime, + inode->i_sb->s_time_gran); if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index e0d9e8f27ed2..2360a9d9a09e 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -284,9 +284,9 @@ static int do_read_inode(struct inode *inode) fi->i_crtime.tv_nsec = le32_to_cpu(ri->i_crtime_nsec); } - F2FS_I(inode)->i_disk_time[0] = inode->i_atime; - F2FS_I(inode)->i_disk_time[1] = inode->i_ctime; - F2FS_I(inode)->i_disk_time[2] = inode->i_mtime; + F2FS_I(inode)->i_disk_time[0] = timespec64_to_timespec(inode->i_atime); + F2FS_I(inode)->i_disk_time[1] = timespec64_to_timespec(inode->i_ctime); + F2FS_I(inode)->i_disk_time[2] = timespec64_to_timespec(inode->i_mtime); F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime; f2fs_put_page(node_page, 1); @@ -448,9 +448,9 @@ void update_inode(struct inode *inode, struct page *node_page) if (inode->i_nlink == 0) clear_inline_node(node_page); - F2FS_I(inode)->i_disk_time[0] = inode->i_atime; - F2FS_I(inode)->i_disk_time[1] = inode->i_ctime; - F2FS_I(inode)->i_disk_time[2] = inode->i_mtime; + F2FS_I(inode)->i_disk_time[0] = timespec64_to_timespec(inode->i_atime); + F2FS_I(inode)->i_disk_time[1] = timespec64_to_timespec(inode->i_ctime); + F2FS_I(inode)->i_disk_time[2] = timespec64_to_timespec(inode->i_mtime); F2FS_I(inode)->i_disk_time[3] = F2FS_I(inode)->i_crtime; } diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index d5098efe577c..ae10fe34f63d 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -50,8 +50,8 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode) inode->i_ino = ino; inode->i_blocks = 0; - inode->i_mtime = inode->i_atime = inode->i_ctime = - F2FS_I(inode)->i_crtime = current_time(inode); + inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); + F2FS_I(inode)->i_crtime = timespec64_to_timespec(inode->i_mtime); inode->i_generation = sbi->s_next_generation++; err = insert_inode_locked(inode); diff --git a/fs/fat/inode.c b/fs/fat/inode.c index ffbbf0520d9e..13271ea2b453 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -502,6 +502,7 @@ static int fat_validate_dir(struct inode *dir) /* doesn't deal with root inode */ int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) { + struct timespec ts; struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); int error; @@ -552,11 +553,14 @@ int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) & ~((loff_t)sbi->cluster_size - 1)) >> 9; - fat_time_fat2unix(sbi, &inode->i_mtime, de->time, de->date, 0); + fat_time_fat2unix(sbi, &ts, de->time, de->date, 0); + inode->i_mtime = timespec_to_timespec64(ts); if (sbi->options.isvfat) { - fat_time_fat2unix(sbi, &inode->i_ctime, de->ctime, + fat_time_fat2unix(sbi, &ts, de->ctime, de->cdate, de->ctime_cs); - fat_time_fat2unix(sbi, &inode->i_atime, 0, de->adate, 0); + inode->i_ctime = timespec_to_timespec64(ts); + fat_time_fat2unix(sbi, &ts, 0, de->adate, 0); + inode->i_atime = timespec_to_timespec64(ts); } else inode->i_ctime = inode->i_atime = inode->i_mtime; @@ -825,6 +829,7 @@ static int fat_statfs(struct dentry *dentry, struct kstatfs *buf) static int __fat_write_inode(struct inode *inode, int wait) { + struct timespec ts; struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); struct buffer_head *bh; @@ -862,13 +867,16 @@ retry: raw_entry->size = cpu_to_le32(inode->i_size); raw_entry->attr = fat_make_attrs(inode); fat_set_start(raw_entry, MSDOS_I(inode)->i_logstart); - fat_time_unix2fat(sbi, &inode->i_mtime, &raw_entry->time, + ts = timespec64_to_timespec(inode->i_mtime); + fat_time_unix2fat(sbi, &ts, &raw_entry->time, &raw_entry->date, NULL); if (sbi->options.isvfat) { __le16 atime; - fat_time_unix2fat(sbi, &inode->i_ctime, &raw_entry->ctime, + ts = timespec64_to_timespec(inode->i_ctime); + fat_time_unix2fat(sbi, &ts, &raw_entry->ctime, &raw_entry->cdate, &raw_entry->ctime_cs); - fat_time_unix2fat(sbi, &inode->i_atime, &atime, + ts = timespec64_to_timespec(inode->i_atime); + fat_time_unix2fat(sbi, &ts, &atime, &raw_entry->adate, NULL); } spin_unlock(&sbi->inode_hash_lock); diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index 582ca731a6c9..df6eb551f713 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -250,7 +250,7 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name, if (err) return err; - dir->i_ctime = dir->i_mtime = *ts; + dir->i_ctime = dir->i_mtime = timespec_to_timespec64(*ts); if (IS_DIRSYNC(dir)) (void)fat_sync_inode(dir); else @@ -266,7 +266,8 @@ static int msdos_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct super_block *sb = dir->i_sb; struct inode *inode = NULL; struct fat_slot_info sinfo; - struct timespec ts; + struct timespec64 ts; + struct timespec t; unsigned char msdos_name[MSDOS_NAME]; int err, is_hid; @@ -285,7 +286,8 @@ static int msdos_create(struct inode *dir, struct dentry *dentry, umode_t mode, } ts = current_time(dir); - err = msdos_add_entry(dir, msdos_name, 0, is_hid, 0, &ts, &sinfo); + t = timespec64_to_timespec(ts); + err = msdos_add_entry(dir, msdos_name, 0, is_hid, 0, &t, &sinfo); if (err) goto out; inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); @@ -348,7 +350,8 @@ static int msdos_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) struct fat_slot_info sinfo; struct inode *inode; unsigned char msdos_name[MSDOS_NAME]; - struct timespec ts; + struct timespec64 ts; + struct timespec t; int err, is_hid, cluster; mutex_lock(&MSDOS_SB(sb)->s_lock); @@ -366,12 +369,13 @@ static int msdos_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) } ts = current_time(dir); - cluster = fat_alloc_new_dir(dir, &ts); + t = timespec64_to_timespec(ts); + cluster = fat_alloc_new_dir(dir, &t); if (cluster < 0) { err = cluster; goto out; } - err = msdos_add_entry(dir, msdos_name, 1, is_hid, cluster, &ts, &sinfo); + err = msdos_add_entry(dir, msdos_name, 1, is_hid, cluster, &t, &sinfo); if (err) goto out_free; inc_nlink(dir); @@ -436,7 +440,7 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, struct msdos_dir_entry *dotdot_de; struct inode *old_inode, *new_inode; struct fat_slot_info old_sinfo, sinfo; - struct timespec ts; + struct timespec64 ts; loff_t new_i_pos; int err, old_attrs, is_dir, update_dotdot, corrupt = 0; @@ -503,8 +507,9 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, new_i_pos = MSDOS_I(new_inode)->i_pos; fat_detach(new_inode); } else { + struct timespec t = timespec64_to_timespec(ts); err = msdos_add_entry(new_dir, new_name, is_dir, is_hid, 0, - &ts, &sinfo); + &t, &sinfo); if (err) goto out; new_i_pos = sinfo.i_pos; diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 2649759c478a..caa229423327 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -678,7 +678,7 @@ static int vfat_add_entry(struct inode *dir, const struct qstr *qname, goto cleanup; /* update timestamp */ - dir->i_ctime = dir->i_mtime = dir->i_atime = *ts; + dir->i_ctime = dir->i_mtime = dir->i_atime = timespec_to_timespec64(*ts); if (IS_DIRSYNC(dir)) (void)fat_sync_inode(dir); else @@ -772,13 +772,15 @@ static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode, struct super_block *sb = dir->i_sb; struct inode *inode; struct fat_slot_info sinfo; - struct timespec ts; + struct timespec64 ts; + struct timespec t; int err; mutex_lock(&MSDOS_SB(sb)->s_lock); ts = current_time(dir); - err = vfat_add_entry(dir, &dentry->d_name, 0, 0, &ts, &sinfo); + t = timespec64_to_timespec(ts); + err = vfat_add_entry(dir, &dentry->d_name, 0, 0, &t, &sinfo); if (err) goto out; inode_inc_iversion(dir); @@ -861,18 +863,20 @@ static int vfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) struct super_block *sb = dir->i_sb; struct inode *inode; struct fat_slot_info sinfo; - struct timespec ts; + struct timespec64 ts; + struct timespec t; int err, cluster; mutex_lock(&MSDOS_SB(sb)->s_lock); ts = current_time(dir); - cluster = fat_alloc_new_dir(dir, &ts); + t = timespec64_to_timespec(ts); + cluster = fat_alloc_new_dir(dir, &t); if (cluster < 0) { err = cluster; goto out; } - err = vfat_add_entry(dir, &dentry->d_name, 1, cluster, &ts, &sinfo); + err = vfat_add_entry(dir, &dentry->d_name, 1, cluster, &t, &sinfo); if (err) goto out_free; inode_inc_iversion(dir); @@ -910,7 +914,8 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry, struct msdos_dir_entry *dotdot_de; struct inode *old_inode, *new_inode; struct fat_slot_info old_sinfo, sinfo; - struct timespec ts; + struct timespec64 ts; + struct timespec t; loff_t new_i_pos; int err, is_dir, update_dotdot, corrupt = 0; struct super_block *sb = old_dir->i_sb; @@ -945,8 +950,9 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry, new_i_pos = MSDOS_I(new_inode)->i_pos; fat_detach(new_inode); } else { + t = timespec64_to_timespec(ts); err = vfat_add_entry(new_dir, &new_dentry->d_name, is_dir, 0, - &ts, &sinfo); + &t, &sinfo); if (err) goto out; new_i_pos = sinfo.i_pos; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index ef309958e060..e9e938947723 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -217,7 +217,7 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, return; } - old_mtime = inode->i_mtime; + old_mtime = timespec64_to_timespec(inode->i_mtime); fuse_change_attributes_common(inode, attr, attr_valid); oldsize = inode->i_size; diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c index d9fb0ad6cc30..c22090e97ff0 100644 --- a/fs/gfs2/dir.c +++ b/fs/gfs2/dir.c @@ -871,7 +871,7 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh, struct buffer_head *bh; struct gfs2_leaf *leaf; struct gfs2_dirent *dent; - struct timespec tv = current_time(inode); + struct timespec64 tv = current_time(inode); error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL); if (error) @@ -1802,7 +1802,7 @@ int gfs2_dir_add(struct inode *inode, const struct qstr *name, struct gfs2_inode *ip = GFS2_I(inode); struct buffer_head *bh = da->bh; struct gfs2_dirent *dent = da->dent; - struct timespec tv; + struct timespec64 tv; struct gfs2_leaf *leaf; int error; @@ -1880,7 +1880,7 @@ int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry) const struct qstr *name = &dentry->d_name; struct gfs2_dirent *dent, *prev = NULL; struct buffer_head *bh; - struct timespec tv = current_time(&dip->i_inode); + struct timespec64 tv = current_time(&dip->i_inode); /* Returns _either_ the entry (if its first in block) or the previous entry otherwise */ diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c index d8782a7a1e7d..c63bee9adb6a 100644 --- a/fs/gfs2/glops.c +++ b/fs/gfs2/glops.c @@ -338,7 +338,7 @@ static int inode_go_demote_ok(const struct gfs2_glock *gl) static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) { const struct gfs2_dinode *str = buf; - struct timespec atime; + struct timespec64 atime; u16 height, depth; if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr))) @@ -361,7 +361,7 @@ static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf) gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks)); atime.tv_sec = be64_to_cpu(str->di_atime); atime.tv_nsec = be32_to_cpu(str->di_atime_nsec); - if (timespec_compare(&ip->i_inode.i_atime, &atime) < 0) + if (timespec64_compare(&ip->i_inode.i_atime, &atime) < 0) ip->i_inode.i_atime = atime; ip->i_inode.i_mtime.tv_sec = be64_to_cpu(str->di_mtime); ip->i_inode.i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 2538b49cc349..8ea683f01cda 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -351,7 +351,7 @@ static int hfs_read_inode(struct inode *inode, void *data) inode->i_mode &= ~hsb->s_file_umask; inode->i_mode |= S_IFREG; inode->i_ctime = inode->i_atime = inode->i_mtime = - hfs_m_to_utime(rec->file.MdDat); + timespec_to_timespec64(hfs_m_to_utime(rec->file.MdDat)); inode->i_op = &hfs_file_inode_operations; inode->i_fop = &hfs_file_operations; inode->i_mapping->a_ops = &hfs_aops; @@ -362,7 +362,7 @@ static int hfs_read_inode(struct inode *inode, void *data) HFS_I(inode)->fs_blocks = 0; inode->i_mode = S_IFDIR | (S_IRWXUGO & ~hsb->s_dir_umask); inode->i_ctime = inode->i_atime = inode->i_mtime = - hfs_m_to_utime(rec->dir.MdDat); + timespec_to_timespec64(hfs_m_to_utime(rec->dir.MdDat)); inode->i_op = &hfs_dir_inode_operations; inode->i_fop = &hfs_dir_operations; break; diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index c0c8d433864f..c824f702feec 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -493,9 +493,9 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) hfsplus_get_perms(inode, &folder->permissions, 1); set_nlink(inode, 1); inode->i_size = 2 + be32_to_cpu(folder->valence); - inode->i_atime = hfsp_mt2ut(folder->access_date); - inode->i_mtime = hfsp_mt2ut(folder->content_mod_date); - inode->i_ctime = hfsp_mt2ut(folder->attribute_mod_date); + inode->i_atime = timespec_to_timespec64(hfsp_mt2ut(folder->access_date)); + inode->i_mtime = timespec_to_timespec64(hfsp_mt2ut(folder->content_mod_date)); + inode->i_ctime = timespec_to_timespec64(hfsp_mt2ut(folder->attribute_mod_date)); HFSPLUS_I(inode)->create_date = folder->create_date; HFSPLUS_I(inode)->fs_blocks = 0; if (folder->flags & cpu_to_be16(HFSPLUS_HAS_FOLDER_COUNT)) { @@ -531,9 +531,9 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) init_special_inode(inode, inode->i_mode, be32_to_cpu(file->permissions.dev)); } - inode->i_atime = hfsp_mt2ut(file->access_date); - inode->i_mtime = hfsp_mt2ut(file->content_mod_date); - inode->i_ctime = hfsp_mt2ut(file->attribute_mod_date); + inode->i_atime = timespec_to_timespec64(hfsp_mt2ut(file->access_date)); + inode->i_mtime = timespec_to_timespec64(hfsp_mt2ut(file->content_mod_date)); + inode->i_ctime = timespec_to_timespec64(hfsp_mt2ut(file->attribute_mod_date)); HFSPLUS_I(inode)->create_date = file->create_date; } else { pr_err("bad catalog entry used to create inode\n"); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 3cd85eb5bbb1..2597b290c2a5 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -555,9 +555,9 @@ static int read_name(struct inode *ino, char *name) set_nlink(ino, st.nlink); i_uid_write(ino, st.uid); i_gid_write(ino, st.gid); - ino->i_atime = st.atime; - ino->i_mtime = st.mtime; - ino->i_ctime = st.ctime; + ino->i_atime = timespec_to_timespec64(st.atime); + ino->i_mtime = timespec_to_timespec64(st.mtime); + ino->i_ctime = timespec_to_timespec64(st.ctime); ino->i_size = st.size; ino->i_blocks = st.blocks; return 0; @@ -838,15 +838,15 @@ static int hostfs_setattr(struct dentry *dentry, struct iattr *attr) } if (attr->ia_valid & ATTR_ATIME) { attrs.ia_valid |= HOSTFS_ATTR_ATIME; - attrs.ia_atime = attr->ia_atime; + attrs.ia_atime = timespec64_to_timespec(attr->ia_atime); } if (attr->ia_valid & ATTR_MTIME) { attrs.ia_valid |= HOSTFS_ATTR_MTIME; - attrs.ia_mtime = attr->ia_mtime; + attrs.ia_mtime = timespec64_to_timespec(attr->ia_mtime); } if (attr->ia_valid & ATTR_CTIME) { attrs.ia_valid |= HOSTFS_ATTR_CTIME; - attrs.ia_ctime = attr->ia_ctime; + attrs.ia_ctime = timespec64_to_timespec(attr->ia_ctime); } if (attr->ia_valid & ATTR_ATIME_SET) { attrs.ia_valid |= HOSTFS_ATTR_ATIME_SET; diff --git a/fs/inode.c b/fs/inode.c index 93af998ee290..9fe1f941be02 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1590,8 +1590,8 @@ static void update_ovl_inode_times(struct dentry *dentry, struct inode *inode, if (upperdentry) { struct inode *realinode = d_inode(upperdentry); - if ((!timespec_equal(&inode->i_mtime, &realinode->i_mtime) || - !timespec_equal(&inode->i_ctime, &realinode->i_ctime))) { + if ((!timespec64_equal(&inode->i_mtime, &realinode->i_mtime) || + !timespec64_equal(&inode->i_ctime, &realinode->i_ctime))) { inode->i_mtime = realinode->i_mtime; inode->i_ctime = realinode->i_ctime; } @@ -1614,12 +1614,12 @@ static int relatime_need_update(const struct path *path, struct inode *inode, /* * Is mtime younger than atime? If yes, update atime: */ - if (timespec_compare(&inode->i_mtime, &inode->i_atime) >= 0) + if (timespec64_compare(&inode->i_mtime, &inode->i_atime) >= 0) return 1; /* * Is ctime younger than atime? If yes, update atime: */ - if (timespec_compare(&inode->i_ctime, &inode->i_atime) >= 0) + if (timespec64_compare(&inode->i_ctime, &inode->i_atime) >= 0) return 1; /* @@ -1634,7 +1634,7 @@ static int relatime_need_update(const struct path *path, struct inode *inode, return 0; } -int generic_update_time(struct inode *inode, struct timespec *time, int flags) +int generic_update_time(struct inode *inode, struct timespec64 *time, int flags) { int iflags = I_DIRTY_TIME; bool dirty = false; @@ -1662,9 +1662,9 @@ EXPORT_SYMBOL(generic_update_time); * This does the actual work of updating an inodes time or version. Must have * had called mnt_want_write() before calling this. */ -static int update_time(struct inode *inode, struct timespec *time, int flags) +static int update_time(struct inode *inode, struct timespec64 *time, int flags) { - int (*update_time)(struct inode *, struct timespec *, int); + int (*update_time)(struct inode *, struct timespec64 *, int); update_time = inode->i_op->update_time ? inode->i_op->update_time : generic_update_time; @@ -1685,7 +1685,7 @@ bool __atime_needs_update(const struct path *path, struct inode *inode, bool rcu) { struct vfsmount *mnt = path->mnt; - struct timespec now; + struct timespec64 now; if (inode->i_flags & S_NOATIME) return false; @@ -1708,10 +1708,10 @@ bool __atime_needs_update(const struct path *path, struct inode *inode, now = current_time(inode); - if (!relatime_need_update(path, inode, now, rcu)) + if (!relatime_need_update(path, inode, timespec64_to_timespec(now), rcu)) return false; - if (timespec_equal(&inode->i_atime, &now)) + if (timespec64_equal(&inode->i_atime, &now)) return false; return true; @@ -1721,7 +1721,7 @@ void touch_atime(const struct path *path) { struct vfsmount *mnt = path->mnt; struct inode *inode = d_inode(path->dentry); - struct timespec now; + struct timespec64 now; if (!__atime_needs_update(path, inode, false)) return; @@ -1855,7 +1855,7 @@ EXPORT_SYMBOL(file_remove_privs); int file_update_time(struct file *file) { struct inode *inode = file_inode(file); - struct timespec now; + struct timespec64 now; int sync_it = 0; int ret; @@ -1864,10 +1864,10 @@ int file_update_time(struct file *file) return 0; now = current_time(inode); - if (!timespec_equal(&inode->i_mtime, &now)) + if (!timespec64_equal(&inode->i_mtime, &now)) sync_it = S_MTIME; - if (!timespec_equal(&inode->i_ctime, &now)) + if (!timespec64_equal(&inode->i_ctime, &now)) sync_it |= S_CTIME; if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode)) @@ -2144,15 +2144,15 @@ EXPORT_SYMBOL(timespec64_trunc); * Note that inode and inode->sb cannot be NULL. * Otherwise, the function warns and returns time without truncation. */ -struct timespec current_time(struct inode *inode) +struct timespec64 current_time(struct inode *inode) { - struct timespec now = current_kernel_time(); + struct timespec64 now = current_kernel_time64(); if (unlikely(!inode->i_sb)) { WARN(1, "current_time() called with uninitialized super_block in the inode"); return now; } - return timespec_trunc(now, inode->i_sb->s_time_gran); + return timespec64_trunc(now, inode->i_sb->s_time_gran); } EXPORT_SYMBOL(current_time); diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c index 0a754f38462e..4ef97805eb27 100644 --- a/fs/jffs2/dir.c +++ b/fs/jffs2/dir.c @@ -201,7 +201,7 @@ static int jffs2_create(struct inode *dir_i, struct dentry *dentry, if (ret) goto fail; - dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(ri->ctime)); + dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->ctime))); jffs2_free_raw_inode(ri); @@ -235,7 +235,7 @@ static int jffs2_unlink(struct inode *dir_i, struct dentry *dentry) if (dead_f->inocache) set_nlink(d_inode(dentry), dead_f->inocache->pino_nlink); if (!ret) - dir_i->i_mtime = dir_i->i_ctime = ITIME(now); + dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(now)); return ret; } /***********************************************************************/ @@ -269,7 +269,7 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de set_nlink(d_inode(old_dentry), ++f->inocache->pino_nlink); mutex_unlock(&f->sem); d_instantiate(dentry, d_inode(old_dentry)); - dir_i->i_mtime = dir_i->i_ctime = ITIME(now); + dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(now)); ihold(d_inode(old_dentry)); } return ret; @@ -419,7 +419,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char goto fail; } - dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime)); + dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(rd->mctime))); jffs2_free_raw_dirent(rd); @@ -563,7 +563,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode goto fail; } - dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime)); + dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(rd->mctime))); inc_nlink(dir_i); jffs2_free_raw_dirent(rd); @@ -601,7 +601,7 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry) ret = jffs2_do_unlink(c, dir_f, dentry->d_name.name, dentry->d_name.len, f, now); if (!ret) { - dir_i->i_mtime = dir_i->i_ctime = ITIME(now); + dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(now)); clear_nlink(d_inode(dentry)); drop_nlink(dir_i); } @@ -736,7 +736,7 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode goto fail; } - dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime)); + dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(rd->mctime))); jffs2_free_raw_dirent(rd); @@ -857,14 +857,14 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry, * caller won't do it on its own since we are returning an error. */ d_invalidate(new_dentry); - new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now); + new_dir_i->i_mtime = new_dir_i->i_ctime = timespec_to_timespec64(ITIME(now)); return ret; } if (d_is_dir(old_dentry)) drop_nlink(old_dir_i); - new_dir_i->i_mtime = new_dir_i->i_ctime = old_dir_i->i_mtime = old_dir_i->i_ctime = ITIME(now); + new_dir_i->i_mtime = new_dir_i->i_ctime = old_dir_i->i_mtime = old_dir_i->i_ctime = timespec_to_timespec64(ITIME(now)); return 0; } diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index bd0428bebe9b..481afd4c2e1a 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -308,7 +308,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping, inode->i_size = pos + writtenlen; inode->i_blocks = (inode->i_size + 511) >> 9; - inode->i_ctime = inode->i_mtime = ITIME(je32_to_cpu(ri->ctime)); + inode->i_ctime = inode->i_mtime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->ctime))); } } diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index eab04eca95a3..0ecfb8ea38cd 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -146,9 +146,9 @@ int jffs2_do_setattr (struct inode *inode, struct iattr *iattr) return PTR_ERR(new_metadata); } /* It worked. Update the inode */ - inode->i_atime = ITIME(je32_to_cpu(ri->atime)); - inode->i_ctime = ITIME(je32_to_cpu(ri->ctime)); - inode->i_mtime = ITIME(je32_to_cpu(ri->mtime)); + inode->i_atime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->atime))); + inode->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->ctime))); + inode->i_mtime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->mtime))); inode->i_mode = jemode_to_cpu(ri->mode); i_uid_write(inode, je16_to_cpu(ri->uid)); i_gid_write(inode, je16_to_cpu(ri->gid)); @@ -280,9 +280,9 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino) i_uid_write(inode, je16_to_cpu(latest_node.uid)); i_gid_write(inode, je16_to_cpu(latest_node.gid)); inode->i_size = je32_to_cpu(latest_node.isize); - inode->i_atime = ITIME(je32_to_cpu(latest_node.atime)); - inode->i_mtime = ITIME(je32_to_cpu(latest_node.mtime)); - inode->i_ctime = ITIME(je32_to_cpu(latest_node.ctime)); + inode->i_atime = timespec_to_timespec64(ITIME(je32_to_cpu(latest_node.atime))); + inode->i_mtime = timespec_to_timespec64(ITIME(je32_to_cpu(latest_node.mtime))); + inode->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(latest_node.ctime))); set_nlink(inode, f->inocache->pino_nlink); diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 89d1dc19340b..d66cc0777303 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -779,7 +779,7 @@ int kernfs_add_one(struct kernfs_node *kn) ps_iattr = parent->iattr; if (ps_iattr) { struct iattr *ps_iattrs = &ps_iattr->ia_iattr; - ktime_get_real_ts(&ps_iattrs->ia_ctime); + ktime_get_real_ts64(&ps_iattrs->ia_ctime); ps_iattrs->ia_mtime = ps_iattrs->ia_ctime; } @@ -1306,7 +1306,7 @@ static void __kernfs_remove(struct kernfs_node *kn) /* update timestamps on the parent */ if (ps_iattr) { - ktime_get_real_ts(&ps_iattr->ia_iattr.ia_ctime); + ktime_get_real_ts64(&ps_iattr->ia_iattr.ia_ctime); ps_iattr->ia_iattr.ia_mtime = ps_iattr->ia_iattr.ia_ctime; } diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c index a34303981deb..3d73fe9d56e2 100644 --- a/fs/kernfs/inode.c +++ b/fs/kernfs/inode.c @@ -52,7 +52,7 @@ static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn) iattrs->ia_uid = GLOBAL_ROOT_UID; iattrs->ia_gid = GLOBAL_ROOT_GID; - ktime_get_real_ts(&iattrs->ia_atime); + ktime_get_real_ts64(&iattrs->ia_atime); iattrs->ia_mtime = iattrs->ia_atime; iattrs->ia_ctime = iattrs->ia_atime; @@ -176,9 +176,9 @@ static inline void set_inode_attr(struct inode *inode, struct iattr *iattr) struct super_block *sb = inode->i_sb; inode->i_uid = iattr->ia_uid; inode->i_gid = iattr->ia_gid; - inode->i_atime = timespec_trunc(iattr->ia_atime, sb->s_time_gran); - inode->i_mtime = timespec_trunc(iattr->ia_mtime, sb->s_time_gran); - inode->i_ctime = timespec_trunc(iattr->ia_ctime, sb->s_time_gran); + inode->i_atime = timespec64_trunc(iattr->ia_atime, sb->s_time_gran); + inode->i_mtime = timespec64_trunc(iattr->ia_mtime, sb->s_time_gran); + inode->i_ctime = timespec64_trunc(iattr->ia_ctime, sb->s_time_gran); } static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode) diff --git a/fs/locks.c b/fs/locks.c index 62bbe8b31f26..7356c405ec46 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1562,7 +1562,7 @@ EXPORT_SYMBOL(__break_lease); * exclusive leases. The justification is that if someone has an * exclusive lease, then they could be modifying it. */ -void lease_get_mtime(struct inode *inode, struct timespec *time) +void lease_get_mtime(struct inode *inode, struct timespec64 *time) { bool has_lease = false; struct file_lock_context *ctx; diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index a50d7813e3ea..9d24aabcd8bb 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -54,8 +54,8 @@ __be32 nfs4_callback_getattr(void *argp, void *resp, res->change_attr = delegation->change_attr; if (nfs_have_writebacks(inode)) res->change_attr++; - res->ctime = inode->i_ctime; - res->mtime = inode->i_mtime; + res->ctime = timespec64_to_timespec(inode->i_ctime); + res->mtime = timespec64_to_timespec(inode->i_mtime); res->bitmap[0] = (FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE) & args->bitmap[0]; res->bitmap[1] = (FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY) & diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c index 1c5d8d31fc0a..666415d13d52 100644 --- a/fs/nfs/fscache-index.c +++ b/fs/nfs/fscache-index.c @@ -88,8 +88,8 @@ enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data, return FSCACHE_CHECKAUX_OBSOLETE; memset(&auxdata, 0, sizeof(auxdata)); - auxdata.mtime = nfsi->vfs_inode.i_mtime; - auxdata.ctime = nfsi->vfs_inode.i_ctime; + auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime); + auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime); if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c index b55fc7920c3b..4dc887813c71 100644 --- a/fs/nfs/fscache.c +++ b/fs/nfs/fscache.c @@ -237,8 +237,8 @@ void nfs_fscache_init_inode(struct inode *inode) return; memset(&auxdata, 0, sizeof(auxdata)); - auxdata.mtime = nfsi->vfs_inode.i_mtime; - auxdata.ctime = nfsi->vfs_inode.i_ctime; + auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime); + auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime); if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4) auxdata.change_attr = inode_peek_iversion_raw(&nfsi->vfs_inode); @@ -262,8 +262,8 @@ void nfs_fscache_clear_inode(struct inode *inode) dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n", nfsi, cookie); memset(&auxdata, 0, sizeof(auxdata)); - auxdata.mtime = nfsi->vfs_inode.i_mtime; - auxdata.ctime = nfsi->vfs_inode.i_ctime; + auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime); + auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime); fscache_relinquish_cookie(cookie, &auxdata, false); nfsi->fscache = NULL; } @@ -304,8 +304,8 @@ void nfs_fscache_open_file(struct inode *inode, struct file *filp) return; memset(&auxdata, 0, sizeof(auxdata)); - auxdata.mtime = nfsi->vfs_inode.i_mtime; - auxdata.ctime = nfsi->vfs_inode.i_ctime; + auxdata.mtime = timespec64_to_timespec(nfsi->vfs_inode.i_mtime); + auxdata.ctime = timespec64_to_timespec(nfsi->vfs_inode.i_ctime); if (inode_is_open_for_write(inode)) { dfprintk(FSCACHE, "NFS: nfsi 0x%p disabling cache\n", nfsi); diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 55b62254dd7c..138941a97327 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -494,15 +494,15 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st nfsi->read_cache_jiffies = fattr->time_start; nfsi->attr_gencount = fattr->gencount; if (fattr->valid & NFS_ATTR_FATTR_ATIME) - inode->i_atime = fattr->atime; + inode->i_atime = timespec_to_timespec64(fattr->atime); else if (nfs_server_capable(inode, NFS_CAP_ATIME)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATIME); if (fattr->valid & NFS_ATTR_FATTR_MTIME) - inode->i_mtime = fattr->mtime; + inode->i_mtime = timespec_to_timespec64(fattr->mtime); else if (nfs_server_capable(inode, NFS_CAP_MTIME)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_MTIME); if (fattr->valid & NFS_ATTR_FATTR_CTIME) - inode->i_ctime = fattr->ctime; + inode->i_ctime = timespec_to_timespec64(fattr->ctime); else if (nfs_server_capable(inode, NFS_CAP_CTIME)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME); if (fattr->valid & NFS_ATTR_FATTR_CHANGE) @@ -1304,6 +1304,8 @@ static bool nfs_file_has_buffered_writers(struct nfs_inode *nfsi) static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) { + struct timespec ts; + if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE) && (fattr->valid & NFS_ATTR_FATTR_CHANGE) && inode_eq_iversion_raw(inode, fattr->pre_change_attr)) { @@ -1312,16 +1314,18 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); } /* If we have atomic WCC data, we may update some attributes */ + ts = timespec64_to_timespec(inode->i_ctime); if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME) && (fattr->valid & NFS_ATTR_FATTR_CTIME) - && timespec_equal(&inode->i_ctime, &fattr->pre_ctime)) { - inode->i_ctime = fattr->ctime; + && timespec_equal(&ts, &fattr->pre_ctime)) { + inode->i_ctime = timespec_to_timespec64(fattr->ctime); } + ts = timespec64_to_timespec(inode->i_mtime); if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME) && (fattr->valid & NFS_ATTR_FATTR_MTIME) - && timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) { - inode->i_mtime = fattr->mtime; + && timespec_equal(&ts, &fattr->pre_mtime)) { + inode->i_mtime = timespec_to_timespec64(fattr->mtime); if (S_ISDIR(inode->i_mode)) nfs_set_cache_invalid(inode, NFS_INO_INVALID_DATA); } @@ -1347,7 +1351,7 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat struct nfs_inode *nfsi = NFS_I(inode); loff_t cur_size, new_isize; unsigned long invalid = 0; - + struct timespec ts; if (nfs_have_delegated_attributes(inode)) return 0; @@ -1363,10 +1367,12 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat invalid |= NFS_INO_INVALID_CHANGE | NFS_INO_REVAL_PAGECACHE; - if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&inode->i_mtime, &fattr->mtime)) + ts = timespec64_to_timespec(inode->i_mtime); + if ((fattr->valid & NFS_ATTR_FATTR_MTIME) && !timespec_equal(&ts, &fattr->mtime)) invalid |= NFS_INO_INVALID_MTIME; - if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec_equal(&inode->i_ctime, &fattr->ctime)) + ts = timespec64_to_timespec(inode->i_ctime); + if ((fattr->valid & NFS_ATTR_FATTR_CTIME) && !timespec_equal(&ts, &fattr->ctime)) invalid |= NFS_INO_INVALID_CTIME; if (fattr->valid & NFS_ATTR_FATTR_SIZE) { @@ -1396,7 +1402,8 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat if ((fattr->valid & NFS_ATTR_FATTR_NLINK) && inode->i_nlink != fattr->nlink) invalid |= NFS_INO_INVALID_OTHER; - if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec_equal(&inode->i_atime, &fattr->atime)) + ts = timespec64_to_timespec(inode->i_atime); + if ((fattr->valid & NFS_ATTR_FATTR_ATIME) && !timespec_equal(&ts, &fattr->atime)) invalid |= NFS_INO_INVALID_ATIME; if (invalid != 0) @@ -1667,12 +1674,12 @@ int nfs_post_op_update_inode_force_wcc_locked(struct inode *inode, struct nfs_fa } if ((fattr->valid & NFS_ATTR_FATTR_CTIME) != 0 && (fattr->valid & NFS_ATTR_FATTR_PRECTIME) == 0) { - fattr->pre_ctime = inode->i_ctime; + fattr->pre_ctime = timespec64_to_timespec(inode->i_ctime); fattr->valid |= NFS_ATTR_FATTR_PRECTIME; } if ((fattr->valid & NFS_ATTR_FATTR_MTIME) != 0 && (fattr->valid & NFS_ATTR_FATTR_PREMTIME) == 0) { - fattr->pre_mtime = inode->i_mtime; + fattr->pre_mtime = timespec64_to_timespec(inode->i_mtime); fattr->valid |= NFS_ATTR_FATTR_PREMTIME; } if ((fattr->valid & NFS_ATTR_FATTR_SIZE) != 0 && @@ -1829,7 +1836,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) } if (fattr->valid & NFS_ATTR_FATTR_MTIME) { - inode->i_mtime = fattr->mtime; + inode->i_mtime = timespec_to_timespec64(fattr->mtime); } else if (server->caps & NFS_CAP_MTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_MTIME @@ -1838,7 +1845,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) } if (fattr->valid & NFS_ATTR_FATTR_CTIME) { - inode->i_ctime = fattr->ctime; + inode->i_ctime = timespec_to_timespec64(fattr->ctime); } else if (server->caps & NFS_CAP_CTIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_CTIME @@ -1875,7 +1882,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if (fattr->valid & NFS_ATTR_FATTR_ATIME) - inode->i_atime = fattr->atime; + inode->i_atime = timespec_to_timespec64(fattr->atime); else if (server->caps & NFS_CAP_ATIME) { nfsi->cache_validity |= save_cache_validity & (NFS_INO_INVALID_ATIME diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 85e4b4a233f9..350675e3ed47 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -354,6 +354,7 @@ static __be32 *xdr_time_not_set(__be32 *p) static void encode_sattr(struct xdr_stream *xdr, const struct iattr *attr) { + struct timespec ts; __be32 *p; p = xdr_reserve_space(xdr, NFS_sattr_sz << 2); @@ -375,17 +376,21 @@ static void encode_sattr(struct xdr_stream *xdr, const struct iattr *attr) else *p++ = cpu_to_be32(NFS2_SATTR_NOT_SET); - if (attr->ia_valid & ATTR_ATIME_SET) - p = xdr_encode_time(p, &attr->ia_atime); - else if (attr->ia_valid & ATTR_ATIME) - p = xdr_encode_current_server_time(p, &attr->ia_atime); - else + if (attr->ia_valid & ATTR_ATIME_SET) { + ts = timespec64_to_timespec(attr->ia_atime); + p = xdr_encode_time(p, &ts); + } else if (attr->ia_valid & ATTR_ATIME) { + ts = timespec64_to_timespec(attr->ia_atime); + p = xdr_encode_current_server_time(p, &ts); + } else p = xdr_time_not_set(p); - if (attr->ia_valid & ATTR_MTIME_SET) - xdr_encode_time(p, &attr->ia_mtime); - else if (attr->ia_valid & ATTR_MTIME) - xdr_encode_current_server_time(p, &attr->ia_mtime); - else + if (attr->ia_valid & ATTR_MTIME_SET) { + ts = timespec64_to_timespec(attr->ia_atime); + xdr_encode_time(p, &ts); + } else if (attr->ia_valid & ATTR_MTIME) { + ts = timespec64_to_timespec(attr->ia_mtime); + xdr_encode_current_server_time(p, &ts); + } else xdr_time_not_set(p); } diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 09ee36dd8426..64e4fa33d89f 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -561,6 +561,7 @@ static __be32 *xdr_decode_nfstime3(__be32 *p, struct timespec *timep) */ static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr) { + struct timespec ts; u32 nbytes; __be32 *p; @@ -610,8 +611,10 @@ static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr) *p++ = xdr_zero; if (attr->ia_valid & ATTR_ATIME_SET) { + struct timespec ts; *p++ = xdr_two; - p = xdr_encode_nfstime3(p, &attr->ia_atime); + ts = timespec64_to_timespec(attr->ia_atime); + p = xdr_encode_nfstime3(p, &ts); } else if (attr->ia_valid & ATTR_ATIME) { *p++ = xdr_one; } else @@ -619,7 +622,8 @@ static void encode_sattr3(struct xdr_stream *xdr, const struct iattr *attr) if (attr->ia_valid & ATTR_MTIME_SET) { *p++ = xdr_two; - xdr_encode_nfstime3(p, &attr->ia_mtime); + ts = timespec64_to_timespec(attr->ia_mtime); + xdr_encode_nfstime3(p, &ts); } else if (attr->ia_valid & ATTR_MTIME) { *p = xdr_one; } else diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 9b7392032321..481426e9e6f0 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -1057,6 +1057,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const struct nfs_server *server, const uint32_t attrmask[]) { + struct timespec ts; char owner_name[IDMAP_NAMESZ]; char owner_group[IDMAP_NAMESZ]; int owner_namelen = 0; @@ -1145,14 +1146,16 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, if (bmval[1] & FATTR4_WORD1_TIME_ACCESS_SET) { if (iap->ia_valid & ATTR_ATIME_SET) { *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME); - p = xdr_encode_nfstime4(p, &iap->ia_atime); + ts = timespec64_to_timespec(iap->ia_atime); + p = xdr_encode_nfstime4(p, &ts); } else *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME); } if (bmval[1] & FATTR4_WORD1_TIME_MODIFY_SET) { if (iap->ia_valid & ATTR_MTIME_SET) { *p++ = cpu_to_be32(NFS4_SET_TO_CLIENT_TIME); - p = xdr_encode_nfstime4(p, &iap->ia_mtime); + ts = timespec64_to_timespec(iap->ia_mtime); + p = xdr_encode_nfstime4(p, &ts); } else *p++ = cpu_to_be32(NFS4_SET_TO_SERVER_TIME); } diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index 70b8bf781fce..72b21eaffc50 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -121,13 +121,15 @@ nfsd4_block_commit_blocks(struct inode *inode, struct nfsd4_layoutcommit *lcp, { loff_t new_size = lcp->lc_last_wr + 1; struct iattr iattr = { .ia_valid = 0 }; + struct timespec ts; int error; + ts = timespec64_to_timespec(inode->i_mtime); if (lcp->lc_mtime.tv_nsec == UTIME_NOW || - timespec_compare(&lcp->lc_mtime, &inode->i_mtime) < 0) - lcp->lc_mtime = current_time(inode); + timespec_compare(&lcp->lc_mtime, &ts) < 0) + lcp->lc_mtime = timespec64_to_timespec(current_time(inode)); iattr.ia_valid |= ATTR_ATIME | ATTR_CTIME | ATTR_MTIME; - iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = lcp->lc_mtime; + iattr.ia_atime = iattr.ia_ctime = iattr.ia_mtime = timespec_to_timespec64(lcp->lc_mtime); if (new_size > i_size_read(inode)) { iattr.ia_valid |= ATTR_SIZE; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 3192b544a441..9b973f4f7d01 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -165,6 +165,7 @@ static __be32 * encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat) { + struct timespec ts; *p++ = htonl(nfs3_ftypes[(stat->mode & S_IFMT) >> 12]); *p++ = htonl((u32) (stat->mode & S_IALLUGO)); *p++ = htonl((u32) stat->nlink); @@ -180,9 +181,12 @@ encode_fattr3(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, *p++ = htonl((u32) MINOR(stat->rdev)); p = encode_fsid(p, fhp); p = xdr_encode_hyper(p, stat->ino); - p = encode_time3(p, &stat->atime); - p = encode_time3(p, &stat->mtime); - p = encode_time3(p, &stat->ctime); + ts = timespec64_to_timespec(stat->atime); + p = encode_time3(p, &ts); + ts = timespec64_to_timespec(stat->mtime); + p = encode_time3(p, &ts); + ts = timespec64_to_timespec(stat->ctime); + p = encode_time3(p, &ts); return p; } @@ -271,8 +275,8 @@ void fill_pre_wcc(struct svc_fh *fhp) stat.size = inode->i_size; } - fhp->fh_pre_mtime = stat.mtime; - fhp->fh_pre_ctime = stat.ctime; + fhp->fh_pre_mtime = timespec64_to_timespec(stat.mtime); + fhp->fh_pre_ctime = timespec64_to_timespec(stat.ctime); fhp->fh_pre_size = stat.size; fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode); fhp->fh_pre_saved = true; diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 1d048dd95464..c09323c3b419 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -320,6 +320,7 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, struct iattr *iattr, struct nfs4_acl **acl, struct xdr_netobj *label, int *umask) { + struct timespec ts; int expected_len, len = 0; u32 dummy32; char *buf; @@ -421,7 +422,8 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, switch (dummy32) { case NFS4_SET_TO_CLIENT_TIME: len += 12; - status = nfsd4_decode_time(argp, &iattr->ia_atime); + status = nfsd4_decode_time(argp, &ts); + iattr->ia_atime = timespec_to_timespec64(ts); if (status) return status; iattr->ia_valid |= (ATTR_ATIME | ATTR_ATIME_SET); @@ -440,7 +442,8 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, switch (dummy32) { case NFS4_SET_TO_CLIENT_TIME: len += 12; - status = nfsd4_decode_time(argp, &iattr->ia_mtime); + status = nfsd4_decode_time(argp, &ts); + iattr->ia_mtime = timespec_to_timespec64(ts); if (status) return status; iattr->ia_valid |= (ATTR_MTIME | ATTR_MTIME_SET); diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index a43e8260520a..6b2e8b73d36e 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -131,7 +131,7 @@ encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, { struct dentry *dentry = fhp->fh_dentry; int type; - struct timespec time; + struct timespec64 time; u32 f; type = (stat->mode & S_IFMT); diff --git a/fs/ntfs/inode.c b/fs/ntfs/inode.c index 1c1ee489284b..decaf75d1cd5 100644 --- a/fs/ntfs/inode.c +++ b/fs/ntfs/inode.c @@ -667,18 +667,18 @@ static int ntfs_read_locked_inode(struct inode *vi) * mtime is the last change of the data within the file. Not changed * when only metadata is changed, e.g. a rename doesn't affect mtime. */ - vi->i_mtime = ntfs2utc(si->last_data_change_time); + vi->i_mtime = timespec_to_timespec64(ntfs2utc(si->last_data_change_time)); /* * ctime is the last change of the metadata of the file. This obviously * always changes, when mtime is changed. ctime can be changed on its * own, mtime is then not changed, e.g. when a file is renamed. */ - vi->i_ctime = ntfs2utc(si->last_mft_change_time); + vi->i_ctime = timespec_to_timespec64(ntfs2utc(si->last_mft_change_time)); /* * Last access to the data within the file. Not changed during a rename * for example but changed whenever the file is written to. */ - vi->i_atime = ntfs2utc(si->last_access_time); + vi->i_atime = timespec_to_timespec64(ntfs2utc(si->last_access_time)); /* Find the attribute list attribute if present. */ ntfs_attr_reinit_search_ctx(ctx); @@ -2804,11 +2804,11 @@ done: * for real. */ if (!IS_NOCMTIME(VFS_I(base_ni)) && !IS_RDONLY(VFS_I(base_ni))) { - struct timespec now = current_time(VFS_I(base_ni)); + struct timespec64 now = current_time(VFS_I(base_ni)); int sync_it = 0; - if (!timespec_equal(&VFS_I(base_ni)->i_mtime, &now) || - !timespec_equal(&VFS_I(base_ni)->i_ctime, &now)) + if (!timespec64_equal(&VFS_I(base_ni)->i_mtime, &now) || + !timespec64_equal(&VFS_I(base_ni)->i_ctime, &now)) sync_it = 1; VFS_I(base_ni)->i_mtime = now; VFS_I(base_ni)->i_ctime = now; @@ -2923,14 +2923,14 @@ int ntfs_setattr(struct dentry *dentry, struct iattr *attr) } } if (ia_valid & ATTR_ATIME) - vi->i_atime = timespec_trunc(attr->ia_atime, - vi->i_sb->s_time_gran); + vi->i_atime = timespec64_trunc(attr->ia_atime, + vi->i_sb->s_time_gran); if (ia_valid & ATTR_MTIME) - vi->i_mtime = timespec_trunc(attr->ia_mtime, - vi->i_sb->s_time_gran); + vi->i_mtime = timespec64_trunc(attr->ia_mtime, + vi->i_sb->s_time_gran); if (ia_valid & ATTR_CTIME) - vi->i_ctime = timespec_trunc(attr->ia_ctime, - vi->i_sb->s_time_gran); + vi->i_ctime = timespec64_trunc(attr->ia_ctime, + vi->i_sb->s_time_gran); mark_inode_dirty(vi); out: return err; @@ -2997,7 +2997,7 @@ int __ntfs_write_inode(struct inode *vi, int sync) si = (STANDARD_INFORMATION*)((u8*)ctx->attr + le16_to_cpu(ctx->attr->data.resident.value_offset)); /* Update the access times if they have changed. */ - nt = utc2ntfs(vi->i_mtime); + nt = utc2ntfs(timespec64_to_timespec(vi->i_mtime)); if (si->last_data_change_time != nt) { ntfs_debug("Updating mtime for inode 0x%lx: old = 0x%llx, " "new = 0x%llx", vi->i_ino, (long long) @@ -3006,7 +3006,7 @@ int __ntfs_write_inode(struct inode *vi, int sync) si->last_data_change_time = nt; modified = true; } - nt = utc2ntfs(vi->i_ctime); + nt = utc2ntfs(timespec64_to_timespec(vi->i_ctime)); if (si->last_mft_change_time != nt) { ntfs_debug("Updating ctime for inode 0x%lx: old = 0x%llx, " "new = 0x%llx", vi->i_ino, (long long) @@ -3015,7 +3015,7 @@ int __ntfs_write_inode(struct inode *vi, int sync) si->last_mft_change_time = nt; modified = true; } - nt = utc2ntfs(vi->i_atime); + nt = utc2ntfs(timespec64_to_timespec(vi->i_atime)); if (si->last_access_time != nt) { ntfs_debug("Updating atime for inode 0x%lx: old = 0x%llx, " "new = 0x%llx", vi->i_ino, diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c index 97a972efab83..3eb665187d46 100644 --- a/fs/ocfs2/dlmglue.c +++ b/fs/ocfs2/dlmglue.c @@ -2141,6 +2141,7 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode) struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_lock_res *lockres = &oi->ip_inode_lockres; struct ocfs2_meta_lvb *lvb; + struct timespec ts; lvb = ocfs2_dlm_lvb(&lockres->l_lksb); @@ -2161,12 +2162,15 @@ static void __ocfs2_stuff_meta_lvb(struct inode *inode) lvb->lvb_igid = cpu_to_be32(i_gid_read(inode)); lvb->lvb_imode = cpu_to_be16(inode->i_mode); lvb->lvb_inlink = cpu_to_be16(inode->i_nlink); + ts = timespec64_to_timespec(inode->i_atime); lvb->lvb_iatime_packed = - cpu_to_be64(ocfs2_pack_timespec(&inode->i_atime)); + cpu_to_be64(ocfs2_pack_timespec(&ts)); + ts = timespec64_to_timespec(inode->i_ctime); lvb->lvb_ictime_packed = - cpu_to_be64(ocfs2_pack_timespec(&inode->i_ctime)); + cpu_to_be64(ocfs2_pack_timespec(&ts)); + ts = timespec64_to_timespec(inode->i_mtime); lvb->lvb_imtime_packed = - cpu_to_be64(ocfs2_pack_timespec(&inode->i_mtime)); + cpu_to_be64(ocfs2_pack_timespec(&ts)); lvb->lvb_iattr = cpu_to_be32(oi->ip_attr); lvb->lvb_idynfeatures = cpu_to_be16(oi->ip_dyn_features); lvb->lvb_igeneration = cpu_to_be32(inode->i_generation); @@ -2184,6 +2188,7 @@ static void ocfs2_unpack_timespec(struct timespec *spec, static void ocfs2_refresh_inode_from_lvb(struct inode *inode) { + struct timespec ts; struct ocfs2_inode_info *oi = OCFS2_I(inode); struct ocfs2_lock_res *lockres = &oi->ip_inode_lockres; struct ocfs2_meta_lvb *lvb; @@ -2211,12 +2216,15 @@ static void ocfs2_refresh_inode_from_lvb(struct inode *inode) i_gid_write(inode, be32_to_cpu(lvb->lvb_igid)); inode->i_mode = be16_to_cpu(lvb->lvb_imode); set_nlink(inode, be16_to_cpu(lvb->lvb_inlink)); - ocfs2_unpack_timespec(&inode->i_atime, + ocfs2_unpack_timespec(&ts, be64_to_cpu(lvb->lvb_iatime_packed)); - ocfs2_unpack_timespec(&inode->i_mtime, + inode->i_atime = timespec_to_timespec64(ts); + ocfs2_unpack_timespec(&ts, be64_to_cpu(lvb->lvb_imtime_packed)); - ocfs2_unpack_timespec(&inode->i_ctime, + inode->i_mtime = timespec_to_timespec64(ts); + ocfs2_unpack_timespec(&ts, be64_to_cpu(lvb->lvb_ictime_packed)); + inode->i_ctime = timespec_to_timespec64(ts); spin_unlock(&oi->ip_lock); } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 6ee94bc23f5b..4b32069d4390 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -222,7 +222,7 @@ static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end, int ocfs2_should_update_atime(struct inode *inode, struct vfsmount *vfsmnt) { - struct timespec now; + struct timespec64 now; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb)) @@ -248,8 +248,8 @@ int ocfs2_should_update_atime(struct inode *inode, return 0; if (vfsmnt->mnt_flags & MNT_RELATIME) { - if ((timespec_compare(&inode->i_atime, &inode->i_mtime) <= 0) || - (timespec_compare(&inode->i_atime, &inode->i_ctime) <= 0)) + if ((timespec64_compare(&inode->i_atime, &inode->i_mtime) <= 0) || + (timespec64_compare(&inode->i_atime, &inode->i_ctime) <= 0)) return 1; return 0; diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 79c61da8b1bc..7e3400b90bc9 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -290,7 +290,7 @@ int orangefs_permission(struct inode *inode, int mask) return generic_permission(inode, mask); } -int orangefs_update_time(struct inode *inode, struct timespec *time, int flags) +int orangefs_update_time(struct inode *inode, struct timespec64 *time, int flags) { struct iattr iattr; gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_update_time: %pU\n", diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h index c29bb0ebc6bb..7ed50ee3db8a 100644 --- a/fs/orangefs/orangefs-kernel.h +++ b/fs/orangefs/orangefs-kernel.h @@ -343,7 +343,7 @@ int orangefs_getattr(const struct path *path, struct kstat *stat, int orangefs_permission(struct inode *inode, int mask); -int orangefs_update_time(struct inode *, struct timespec *, int); +int orangefs_update_time(struct inode *, struct timespec64 *, int); /* * defined in xattr.c diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 6e3815fb006b..d7cca60f28e6 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -416,7 +416,7 @@ int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags) return err; } -int ovl_update_time(struct inode *inode, struct timespec *ts, int flags) +int ovl_update_time(struct inode *inode, struct timespec64 *ts, int flags) { if (flags & S_ATIME) { struct ovl_fs *ofs = inode->i_sb->s_fs_info; diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index e0b7de799f6b..9fe10247f9d4 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -331,7 +331,7 @@ int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); struct posix_acl *ovl_get_acl(struct inode *inode, int type); int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags); -int ovl_update_time(struct inode *inode, struct timespec *ts, int flags); +int ovl_update_time(struct inode *inode, struct timespec64 *ts, int flags); bool ovl_is_private_xattr(const char *name); struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev); diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c index 95a708d83721..f18e6f949e0c 100644 --- a/fs/proc/uptime.c +++ b/fs/proc/uptime.c @@ -10,7 +10,7 @@ static int uptime_proc_show(struct seq_file *m, void *v) { struct timespec uptime; - struct timespec idle; + struct timespec64 idle; u64 nsec; u32 rem; int i; diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c index 75afe5eb0574..5fcb845b9fec 100644 --- a/fs/pstore/inode.c +++ b/fs/pstore/inode.c @@ -392,8 +392,7 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record) inode->i_private = private; if (record->time.tv_sec) - inode->i_mtime = inode->i_ctime = - timespec64_to_timespec(record->time); + inode->i_mtime = inode->i_ctime = record->time; d_add(dentry, inode); diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index bd39a998843d..d2869ced6d39 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -1320,7 +1320,7 @@ static int reiserfs_rename(struct inode *old_dir, struct dentry *old_dentry, int jbegin_count; umode_t old_inode_mode; unsigned long savelink = 1; - struct timespec ctime; + struct timespec64 ctime; if (flags & ~RENAME_NOREPLACE) return -EINVAL; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 5dbf5324bdda..ff94fad477e4 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -451,10 +451,10 @@ int reiserfs_commit_write(struct file *f, struct page *page, static void update_ctime(struct inode *inode) { - struct timespec now = current_time(inode); + struct timespec64 now = current_time(inode); if (inode_unhashed(inode) || !inode->i_nlink || - timespec_equal(&inode->i_ctime, &now)) + timespec64_equal(&inode->i_ctime, &now)) return; inode->i_ctime = current_time(inode); diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 9d7fb88e172e..ba53517448b4 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -1289,7 +1289,7 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry, .dirtied_ino = 3 }; struct ubifs_budget_req ino_req = { .dirtied_ino = 1, .dirtied_ino_d = ALIGN(old_inode_ui->data_len, 8) }; - struct timespec time; + struct timespec64 time; unsigned int uninitialized_var(saved_nlink); struct fscrypt_name old_nm, new_nm; @@ -1517,7 +1517,7 @@ static int ubifs_xrename(struct inode *old_dir, struct dentry *old_dentry, int sync = IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir); struct inode *fst_inode = d_inode(old_dentry); struct inode *snd_inode = d_inode(new_dentry); - struct timespec time; + struct timespec64 time; int err; struct fscrypt_name fst_nm, snd_nm; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 1acb2ff505e6..ddb252109945 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1089,14 +1089,14 @@ static void do_attr_changes(struct inode *inode, const struct iattr *attr) if (attr->ia_valid & ATTR_GID) inode->i_gid = attr->ia_gid; if (attr->ia_valid & ATTR_ATIME) - inode->i_atime = timespec_trunc(attr->ia_atime, - inode->i_sb->s_time_gran); + inode->i_atime = timespec64_trunc(attr->ia_atime, + inode->i_sb->s_time_gran); if (attr->ia_valid & ATTR_MTIME) - inode->i_mtime = timespec_trunc(attr->ia_mtime, - inode->i_sb->s_time_gran); + inode->i_mtime = timespec64_trunc(attr->ia_mtime, + inode->i_sb->s_time_gran); if (attr->ia_valid & ATTR_CTIME) - inode->i_ctime = timespec_trunc(attr->ia_ctime, - inode->i_sb->s_time_gran); + inode->i_ctime = timespec64_trunc(attr->ia_ctime, + inode->i_sb->s_time_gran); if (attr->ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; @@ -1367,8 +1367,9 @@ out: static inline int mctime_update_needed(const struct inode *inode, const struct timespec *now) { - if (!timespec_equal(&inode->i_mtime, now) || - !timespec_equal(&inode->i_ctime, now)) + struct timespec64 now64 = timespec_to_timespec64(*now); + if (!timespec64_equal(&inode->i_mtime, &now64) || + !timespec64_equal(&inode->i_ctime, &now64)) return 1; return 0; } @@ -1380,7 +1381,7 @@ static inline int mctime_update_needed(const struct inode *inode, * * This function updates time of the inode. */ -int ubifs_update_time(struct inode *inode, struct timespec *time, +int ubifs_update_time(struct inode *inode, struct timespec64 *time, int flags) { struct ubifs_inode *ui = ubifs_inode(inode); @@ -1424,7 +1425,7 @@ int ubifs_update_time(struct inode *inode, struct timespec *time, */ static int update_mctime(struct inode *inode) { - struct timespec now = current_time(inode); + struct timespec now = timespec64_to_timespec(current_time(inode)); struct ubifs_inode *ui = ubifs_inode(inode); struct ubifs_info *c = inode->i_sb->s_fs_info; @@ -1518,7 +1519,7 @@ static int ubifs_vm_page_mkwrite(struct vm_fault *vmf) struct page *page = vmf->page; struct inode *inode = file_inode(vmf->vma->vm_file); struct ubifs_info *c = inode->i_sb->s_fs_info; - struct timespec now = current_time(inode); + struct timespec now = timespec64_to_timespec(current_time(inode)); struct ubifs_budget_req req = { .new_page = 1 }; int err, update_time; diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index 5ee7af879cc4..ac61ba9921c8 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1740,7 +1740,7 @@ int ubifs_calc_dark(const struct ubifs_info *c, int spc); int ubifs_fsync(struct file *file, loff_t start, loff_t end, int datasync); int ubifs_setattr(struct dentry *dentry, struct iattr *attr); #ifdef CONFIG_UBIFS_ATIME_SUPPORT -int ubifs_update_time(struct inode *inode, struct timespec *time, int flags); +int ubifs_update_time(struct inode *inode, struct timespec64 *time, int flags); #endif /* dir.c */ diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c index b7a0d4b4bda1..56569023783b 100644 --- a/fs/udf/ialloc.c +++ b/fs/udf/ialloc.c @@ -124,8 +124,8 @@ struct inode *udf_new_inode(struct inode *dir, umode_t mode) iinfo->i_alloc_type = ICBTAG_FLAG_AD_SHORT; else iinfo->i_alloc_type = ICBTAG_FLAG_AD_LONG; - inode->i_mtime = inode->i_atime = inode->i_ctime = - iinfo->i_crtime = current_time(inode); + inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); + iinfo->i_crtime = timespec64_to_timespec(inode->i_mtime); if (unlikely(insert_inode_locked(inode) < 0)) { make_bad_inode(inode); iput(inode); diff --git a/fs/udf/inode.c b/fs/udf/inode.c index df2378d6ebb4..7f39d17352c9 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1271,6 +1271,7 @@ static int udf_read_inode(struct inode *inode, bool hidden_inode) struct udf_inode_info *iinfo = UDF_I(inode); struct udf_sb_info *sbi = UDF_SB(inode->i_sb); struct kernel_lb_addr *iloc = &iinfo->i_location; + struct timespec ts; unsigned int link_count; unsigned int indirections = 0; int bs = inode->i_sb->s_blocksize; @@ -1443,9 +1444,12 @@ reread: inode->i_blocks = le64_to_cpu(fe->logicalBlocksRecorded) << (inode->i_sb->s_blocksize_bits - 9); - udf_disk_stamp_to_time(&inode->i_atime, fe->accessTime); - udf_disk_stamp_to_time(&inode->i_mtime, fe->modificationTime); - udf_disk_stamp_to_time(&inode->i_ctime, fe->attrTime); + udf_disk_stamp_to_time(&ts, fe->accessTime); + inode->i_atime = timespec_to_timespec64(ts); + udf_disk_stamp_to_time(&ts, fe->modificationTime); + inode->i_mtime = timespec_to_timespec64(ts); + udf_disk_stamp_to_time(&ts, fe->attrTime); + inode->i_ctime = timespec_to_timespec64(ts); iinfo->i_unique = le64_to_cpu(fe->uniqueID); iinfo->i_lenEAttr = le32_to_cpu(fe->lengthExtendedAttr); @@ -1455,10 +1459,13 @@ reread: inode->i_blocks = le64_to_cpu(efe->logicalBlocksRecorded) << (inode->i_sb->s_blocksize_bits - 9); - udf_disk_stamp_to_time(&inode->i_atime, efe->accessTime); - udf_disk_stamp_to_time(&inode->i_mtime, efe->modificationTime); + udf_disk_stamp_to_time(&ts, efe->accessTime); + inode->i_atime = timespec_to_timespec64(ts); + udf_disk_stamp_to_time(&ts, efe->modificationTime); + inode->i_mtime = timespec_to_timespec64(ts); udf_disk_stamp_to_time(&iinfo->i_crtime, efe->createTime); - udf_disk_stamp_to_time(&inode->i_ctime, efe->attrTime); + udf_disk_stamp_to_time(&ts, efe->attrTime); + inode->i_ctime = timespec_to_timespec64(ts); iinfo->i_unique = le64_to_cpu(efe->uniqueID); iinfo->i_lenEAttr = le32_to_cpu(efe->lengthExtendedAttr); @@ -1708,9 +1715,12 @@ static int udf_update_inode(struct inode *inode, int do_sync) inode->i_sb->s_blocksize - sizeof(struct fileEntry)); fe->logicalBlocksRecorded = cpu_to_le64(lb_recorded); - udf_time_to_disk_stamp(&fe->accessTime, inode->i_atime); - udf_time_to_disk_stamp(&fe->modificationTime, inode->i_mtime); - udf_time_to_disk_stamp(&fe->attrTime, inode->i_ctime); + udf_time_to_disk_stamp(&fe->accessTime, + timespec64_to_timespec(inode->i_atime)); + udf_time_to_disk_stamp(&fe->modificationTime, + timespec64_to_timespec(inode->i_mtime)); + udf_time_to_disk_stamp(&fe->attrTime, + timespec64_to_timespec(inode->i_ctime)); memset(&(fe->impIdent), 0, sizeof(struct regid)); strcpy(fe->impIdent.ident, UDF_ID_DEVELOPER); fe->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX; @@ -1729,14 +1739,17 @@ static int udf_update_inode(struct inode *inode, int do_sync) efe->objectSize = cpu_to_le64(inode->i_size); efe->logicalBlocksRecorded = cpu_to_le64(lb_recorded); - udf_adjust_time(iinfo, inode->i_atime); - udf_adjust_time(iinfo, inode->i_mtime); - udf_adjust_time(iinfo, inode->i_ctime); + udf_adjust_time(iinfo, timespec64_to_timespec(inode->i_atime)); + udf_adjust_time(iinfo, timespec64_to_timespec(inode->i_mtime)); + udf_adjust_time(iinfo, timespec64_to_timespec(inode->i_ctime)); - udf_time_to_disk_stamp(&efe->accessTime, inode->i_atime); - udf_time_to_disk_stamp(&efe->modificationTime, inode->i_mtime); + udf_time_to_disk_stamp(&efe->accessTime, + timespec64_to_timespec(inode->i_atime)); + udf_time_to_disk_stamp(&efe->modificationTime, + timespec64_to_timespec(inode->i_mtime)); udf_time_to_disk_stamp(&efe->createTime, iinfo->i_crtime); - udf_time_to_disk_stamp(&efe->attrTime, inode->i_ctime); + udf_time_to_disk_stamp(&efe->attrTime, + timespec64_to_timespec(inode->i_ctime)); memset(&(efe->impIdent), 0, sizeof(efe->impIdent)); strcpy(efe->impIdent.ident, UDF_ID_DEVELOPER); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 2b70c8b4cee2..0043812897af 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -773,7 +773,7 @@ xfs_ialloc( xfs_inode_t *ip; uint flags; int error; - struct timespec tv; + struct timespec64 tv; struct inode *inode; /* diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index a3ed3c811dfa..b89601b445c2 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -1050,7 +1050,7 @@ xfs_vn_setattr( STATIC int xfs_vn_update_time( struct inode *inode, - struct timespec *now, + struct timespec64 *now, int flags) { struct xfs_inode *ip = XFS_I(inode); diff --git a/fs/xfs/xfs_trans_inode.c b/fs/xfs/xfs_trans_inode.c index 07cea592dc01..a1b3ce132f2f 100644 --- a/fs/xfs/xfs_trans_inode.c +++ b/fs/xfs/xfs_trans_inode.c @@ -70,7 +70,7 @@ xfs_trans_ichgtime( int flags) { struct inode *inode = VFS_I(ip); - struct timespec tv; + struct timespec64 tv; ASSERT(tp); ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL)); diff --git a/include/linux/fs.h b/include/linux/fs.h index 7f6997e0dabf..f15329aa9cad 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -206,9 +206,9 @@ struct iattr { kuid_t ia_uid; kgid_t ia_gid; loff_t ia_size; - struct timespec ia_atime; - struct timespec ia_mtime; - struct timespec ia_ctime; + struct timespec64 ia_atime; + struct timespec64 ia_mtime; + struct timespec64 ia_ctime; /* * Not an attribute, but an auxiliary info for filesystems wanting to @@ -602,9 +602,9 @@ struct inode { }; dev_t i_rdev; loff_t i_size; - struct timespec i_atime; - struct timespec i_mtime; - struct timespec i_ctime; + struct timespec64 i_atime; + struct timespec64 i_mtime; + struct timespec64 i_ctime; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; unsigned int i_blkbits; @@ -1091,7 +1091,7 @@ extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); -extern void lease_get_mtime(struct inode *, struct timespec *time); +extern void lease_get_mtime(struct inode *, struct timespec64 *time); extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); extern int vfs_setlease(struct file *, long, struct file_lock **, void **); extern int lease_modify(struct file_lock *, int, struct list_head *); @@ -1206,7 +1206,8 @@ static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned return 0; } -static inline void lease_get_mtime(struct inode *inode, struct timespec *time) +static inline void lease_get_mtime(struct inode *inode, + struct timespec64 *time) { return; } @@ -1477,7 +1478,7 @@ static inline void i_gid_write(struct inode *inode, gid_t gid) } extern struct timespec64 timespec64_trunc(struct timespec64 t, unsigned gran); -extern struct timespec current_time(struct inode *inode); +extern struct timespec64 current_time(struct inode *inode); /* * Snapshotting support. @@ -1765,7 +1766,7 @@ struct inode_operations { ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); - int (*update_time)(struct inode *, struct timespec *, int); + int (*update_time)(struct inode *, struct timespec64 *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode, int *opened); @@ -2199,7 +2200,7 @@ extern int current_umask(void); extern void ihold(struct inode * inode); extern void iput(struct inode *); -extern int generic_update_time(struct inode *, struct timespec *, int); +extern int generic_update_time(struct inode *, struct timespec64 *, int); /* /sys/fs */ extern struct kobject *fs_kobj; diff --git a/include/linux/stat.h b/include/linux/stat.h index 22484e44544d..765573dc17d6 100644 --- a/include/linux/stat.h +++ b/include/linux/stat.h @@ -41,10 +41,10 @@ struct kstat { kuid_t uid; kgid_t gid; loff_t size; - struct timespec atime; - struct timespec mtime; - struct timespec ctime; - struct timespec btime; /* File creation time */ + struct timespec64 atime; + struct timespec64 mtime; + struct timespec64 ctime; + struct timespec64 btime; /* File creation time */ u64 blocks; }; -- cgit v1.2.3 From a528a24150870c5c16cbbbec69dba7e992b08456 Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Wed, 6 Jun 2018 19:54:44 +0530 Subject: btrfs: change return type of btrfs_page_mkwrite to vm_fault_t Use the new return type vm_fault_t for fault handler. For now, this is just documenting that the function returns a VM_FAULT value rather than an errno. Once all instances are converted, vm_fault_t will become a distinct type. Reference commit 1c8f422059ae ("mm: change return type to vm_fault_t") vmf_error() is the newly introduced inline function in 4.17-rc6. Signed-off-by: Souptick Joarder Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 2 +- fs/btrfs/inode.c | 26 ++++++++++++-------------- 2 files changed, 13 insertions(+), 15 deletions(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index f4bf7874c24a..118346aceea9 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3197,7 +3197,7 @@ int btrfs_merge_bio_hook(struct page *page, unsigned long offset, size_t size, struct bio *bio, unsigned long bio_flags); void btrfs_set_range_writeback(void *private_data, u64 start, u64 end); -int btrfs_page_mkwrite(struct vm_fault *vmf); +vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf); int btrfs_readpage(struct file *file, struct page *page); void btrfs_evict_inode(struct inode *inode); int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 89b208201783..c12b7a6e534a 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8872,7 +8872,7 @@ again: * beyond EOF, then the page is guaranteed safe against truncation until we * unlock the page. */ -int btrfs_page_mkwrite(struct vm_fault *vmf) +vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf) { struct page *page = vmf->page; struct inode *inode = file_inode(vmf->vma->vm_file); @@ -8884,7 +8884,8 @@ int btrfs_page_mkwrite(struct vm_fault *vmf) char *kaddr; unsigned long zero_start; loff_t size; - int ret; + vm_fault_t ret; + int ret2; int reserved = 0; u64 reserved_space; u64 page_start; @@ -8906,17 +8907,14 @@ int btrfs_page_mkwrite(struct vm_fault *vmf) * end up waiting indefinitely to get a lock on the page currently * being processed by btrfs_page_mkwrite() function. */ - ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start, + ret2 = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start, reserved_space); - if (!ret) { - ret = file_update_time(vmf->vma->vm_file); + if (!ret2) { + ret2 = file_update_time(vmf->vma->vm_file); reserved = 1; } - if (ret) { - if (ret == -ENOMEM) - ret = VM_FAULT_OOM; - else /* -ENOSPC, -EIO, etc */ - ret = VM_FAULT_SIGBUS; + if (ret2) { + ret = vmf_error(ret2); if (reserved) goto out; goto out_noreserve; @@ -8975,15 +8973,15 @@ again: EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0, &cached_state); - ret = btrfs_set_extent_delalloc(inode, page_start, end, 0, + ret2 = btrfs_set_extent_delalloc(inode, page_start, end, 0, &cached_state, 0); - if (ret) { + if (ret2) { unlock_extent_cached(io_tree, page_start, page_end, &cached_state); ret = VM_FAULT_SIGBUS; goto out_unlock; } - ret = 0; + ret2 = 0; /* page is wholly or partially inside EOF */ if (page_start + PAGE_SIZE > size) @@ -9008,7 +9006,7 @@ again: unlock_extent_cached(io_tree, page_start, page_end, &cached_state); out_unlock: - if (!ret) { + if (!ret2) { btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE, true); sb_end_pagefault(inode->i_sb); extent_changeset_free(data_reserved); -- cgit v1.2.3