From ece7d20e8be6730fbb29f4550de6b19b1a3a9387 Mon Sep 17 00:00:00 2001 From: Mike Fleetwood Date: Fri, 18 Nov 2011 18:55:01 +0000 Subject: Btrfs: Don't error on resizing FS to same size It seems overly harsh to fail a resize of a btrfs file system to the same size when a shrink or grow would succeed. User app GParted trips over this error. Allow it by bypassing the shrink or grow operation. Signed-off-by: Mike Fleetwood --- fs/btrfs/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a90e749ed6d2..72d461656f60 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1278,7 +1278,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, } ret = btrfs_grow_device(trans, device, new_size); btrfs_commit_transaction(trans, root); - } else { + } else if (new_size < old_size) { ret = btrfs_shrink_device(device, new_size); } -- cgit v1.2.3 From 306424cc880a0fbbdc99eee1f43d056a301a180f Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 14 Dec 2011 20:12:02 -0500 Subject: Btrfs: fix ctime update of on-disk inode To reproduce the bug: # touch /mnt/tmp # stat /mnt/tmp | grep Change Change: 2011-12-09 09:32:23.412105981 +0800 # chattr +i /mnt/tmp # stat /mnt/tmp | grep Change Change: 2011-12-09 09:32:43.198105295 +0800 # umount /mnt # mount /dev/loop1 /mnt # stat /mnt/tmp | grep Change Change: 2011-12-09 09:32:23.412105981 +0800 We should update ctime of in-memory inode before calling btrfs_update_inode(). Signed-off-by: Li Zefan Signed-off-by: Chris Mason --- fs/btrfs/ioctl.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 72d461656f60..40eaa9fdf07c 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -252,11 +252,11 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) trans = btrfs_join_transaction(root); BUG_ON(IS_ERR(trans)); + btrfs_update_iflags(inode); + inode->i_ctime = CURRENT_TIME; ret = btrfs_update_inode(trans, root, inode); BUG_ON(ret); - btrfs_update_iflags(inode); - inode->i_ctime = CURRENT_TIME; btrfs_end_transaction(trans, root); mnt_drop_write(file->f_path.mnt); -- cgit v1.2.3 From 660d3f6cde552323578b85fc5a09a6742f1fe804 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 9 Dec 2011 11:18:51 -0500 Subject: Btrfs: fix how we do delalloc reservations and how we free reservations on error Running xfstests 269 with some tracing my scripts kept spitting out errors about releasing bytes that we didn't actually have reserved. This took me down a huge rabbit hole and it turns out the way we deal with reserved_extents is wrong, we need to only be setting it if the reservation succeeds, otherwise the free() method will come in and unreserve space that isn't actually reserved yet, which can lead to other warnings and such. The math was all working out right in the end, but it caused all sorts of other issues in addition to making my scripts yell and scream and generally make it impossible for me to track down the original issue I was looking for. The other problem is with our error handling in the reservation code. There are two cases that we need to deal with 1) We raced with free. In this case free won't free anything because csum_bytes is modified before we dro the lock in our reservation path, so free rightly doesn't release any space because the reservation code may be depending on that reservation. However if we fail, we need the reservation side to do the free at that point since that space is no longer in use. So as it stands the code was doing this fine and it worked out, except in case #2 2) We don't race with free. Nobody comes in and changes anything, and our reservation fails. In this case we didn't reserve anything anyway and we just need to clean up csum_bytes but not free anything. So we keep track of csum_bytes before we drop the lock and if it hasn't changed we know we can just decrement csum_bytes and carry on. Because of the case where we can race with free()'s since we have to drop our spin_lock to do the reservation, I'm going to serialize all reservations with the i_mutex. We already get this for free in the heavy use paths, truncate and file write all hold the i_mutex, just needed to add it to page_mkwrite and various ioctl/balance things. With this patch my space leak scripts no longer scream bloody murder. Thanks, Signed-off-by: Josef Bacik --- fs/btrfs/extent-tree.c | 43 ++++++++++++++++++++++++++++++------------- fs/btrfs/inode.c | 10 ++++++++++ fs/btrfs/ioctl.c | 2 ++ fs/btrfs/relocation.c | 2 ++ 4 files changed, 44 insertions(+), 13 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 05e1386b8bec..4eb4d2748bec 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4203,12 +4203,17 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_block_rsv *block_rsv = &root->fs_info->delalloc_block_rsv; u64 to_reserve = 0; + u64 csum_bytes; unsigned nr_extents = 0; + int extra_reserve = 0; int flush = 1; int ret; + /* Need to be holding the i_mutex here if we aren't free space cache */ if (btrfs_is_free_space_inode(root, inode)) flush = 0; + else + WARN_ON(!mutex_is_locked(&inode->i_mutex)); if (flush && btrfs_transaction_in_commit(root->fs_info)) schedule_timeout(1); @@ -4219,11 +4224,9 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) BTRFS_I(inode)->outstanding_extents++; if (BTRFS_I(inode)->outstanding_extents > - BTRFS_I(inode)->reserved_extents) { + BTRFS_I(inode)->reserved_extents) nr_extents = BTRFS_I(inode)->outstanding_extents - BTRFS_I(inode)->reserved_extents; - BTRFS_I(inode)->reserved_extents += nr_extents; - } /* * Add an item to reserve for updating the inode when we complete the @@ -4231,11 +4234,12 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) */ if (!BTRFS_I(inode)->delalloc_meta_reserved) { nr_extents++; - BTRFS_I(inode)->delalloc_meta_reserved = 1; + extra_reserve = 1; } to_reserve = btrfs_calc_trans_metadata_size(root, nr_extents); to_reserve += calc_csum_metadata_size(inode, num_bytes, 1); + csum_bytes = BTRFS_I(inode)->csum_bytes; spin_unlock(&BTRFS_I(inode)->lock); ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush); @@ -4245,22 +4249,35 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) spin_lock(&BTRFS_I(inode)->lock); dropped = drop_outstanding_extent(inode); - to_free = calc_csum_metadata_size(inode, num_bytes, 0); - spin_unlock(&BTRFS_I(inode)->lock); - to_free += btrfs_calc_trans_metadata_size(root, dropped); - /* - * Somebody could have come in and twiddled with the - * reservation, so if we have to free more than we would have - * reserved from this reservation go ahead and release those - * bytes. + * If the inodes csum_bytes is the same as the original + * csum_bytes then we know we haven't raced with any free()ers + * so we can just reduce our inodes csum bytes and carry on. + * Otherwise we have to do the normal free thing to account for + * the case that the free side didn't free up its reserve + * because of this outstanding reservation. */ - to_free -= to_reserve; + if (BTRFS_I(inode)->csum_bytes == csum_bytes) + calc_csum_metadata_size(inode, num_bytes, 0); + else + to_free = calc_csum_metadata_size(inode, num_bytes, 0); + spin_unlock(&BTRFS_I(inode)->lock); + if (dropped) + to_free += btrfs_calc_trans_metadata_size(root, dropped); + if (to_free) btrfs_block_rsv_release(root, block_rsv, to_free); return ret; } + spin_lock(&BTRFS_I(inode)->lock); + if (extra_reserve) { + BTRFS_I(inode)->delalloc_meta_reserved = 1; + nr_extents--; + } + BTRFS_I(inode)->reserved_extents += nr_extents; + spin_unlock(&BTRFS_I(inode)->lock); + block_rsv_add_bytes(block_rsv, to_reserve, 1); return 0; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index eec33b9c953d..8938174e6bc1 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2192,7 +2192,14 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) continue; } nr_truncate++; + /* + * Need to hold the imutex for reservation purposes, not + * a huge deal here but I have a WARN_ON in + * btrfs_delalloc_reserve_space to catch offenders. + */ + mutex_lock(&inode->i_mutex); ret = btrfs_truncate(inode); + mutex_unlock(&inode->i_mutex); } else { nr_unlink++; } @@ -6342,7 +6349,10 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) u64 page_start; u64 page_end; + /* Need this to keep space reservations serialized */ + mutex_lock(&inode->i_mutex); ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE); + mutex_unlock(&inode->i_mutex); if (!ret) ret = btrfs_update_time(vma->vm_file); if (ret) { diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 72d461656f60..dd8891662355 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -858,8 +858,10 @@ static int cluster_pages_for_defrag(struct inode *inode, return 0; file_end = (isize - 1) >> PAGE_CACHE_SHIFT; + mutex_lock(&inode->i_mutex); ret = btrfs_delalloc_reserve_space(inode, num_pages << PAGE_CACHE_SHIFT); + mutex_unlock(&inode->i_mutex); if (ret) return ret; again: diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index dff29d5e151a..cfb55434a469 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2947,7 +2947,9 @@ static int relocate_file_extent_cluster(struct inode *inode, index = (cluster->start - offset) >> PAGE_CACHE_SHIFT; last_index = (cluster->end - offset) >> PAGE_CACHE_SHIFT; while (index <= last_index) { + mutex_lock(&inode->i_mutex); ret = btrfs_delalloc_reserve_metadata(inode, PAGE_CACHE_SIZE); + mutex_unlock(&inode->i_mutex); if (ret) goto out; -- cgit v1.2.3 From 66d7e7f09f77456fe68683247d77721032a00ee5 Mon Sep 17 00:00:00 2001 From: Arne Jansen Date: Mon, 12 Sep 2011 15:26:38 +0200 Subject: Btrfs: mark delayed refs as for cow Add a for_cow parameter to add_delayed_*_ref and pass the appropriate value from every call site. The for_cow parameter will later on be used to determine if a ref will change anything with respect to qgroups. Delayed refs coming from relocation are always counted as for_cow, as they don't change subvol quota. Also pass in the fs_info for later use. btrfs_find_all_roots() will use this as an optimization, as changes that are for_cow will not change anything with respect to which root points to a certain leaf. Thus, we don't need to add the current sequence number to those delayed refs. Signed-off-by: Arne Jansen Signed-off-by: Jan Schmidt --- fs/btrfs/ctree.c | 42 ++++++++++---------- fs/btrfs/ctree.h | 17 +++++---- fs/btrfs/delayed-ref.c | 50 ++++++++++++++---------- fs/btrfs/delayed-ref.h | 15 +++++--- fs/btrfs/disk-io.c | 3 +- fs/btrfs/extent-tree.c | 101 +++++++++++++++++++++++++++++-------------------- fs/btrfs/file.c | 10 ++--- fs/btrfs/inode.c | 2 +- fs/btrfs/ioctl.c | 5 ++- fs/btrfs/relocation.c | 18 +++++---- fs/btrfs/transaction.c | 4 +- fs/btrfs/tree-log.c | 2 +- 12 files changed, 155 insertions(+), 114 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index dede441bdeee..0639a555e16e 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -240,7 +240,7 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, cow = btrfs_alloc_free_block(trans, root, buf->len, 0, new_root_objectid, &disk_key, level, - buf->start, 0); + buf->start, 0, 1); if (IS_ERR(cow)) return PTR_ERR(cow); @@ -261,9 +261,9 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, WARN_ON(btrfs_header_generation(buf) > trans->transid); if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID) - ret = btrfs_inc_ref(trans, root, cow, 1); + ret = btrfs_inc_ref(trans, root, cow, 1, 1); else - ret = btrfs_inc_ref(trans, root, cow, 0); + ret = btrfs_inc_ref(trans, root, cow, 0, 1); if (ret) return ret; @@ -350,14 +350,14 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, if ((owner == root->root_key.objectid || root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) { - ret = btrfs_inc_ref(trans, root, buf, 1); + ret = btrfs_inc_ref(trans, root, buf, 1, 1); BUG_ON(ret); if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) { - ret = btrfs_dec_ref(trans, root, buf, 0); + ret = btrfs_dec_ref(trans, root, buf, 0, 1); BUG_ON(ret); - ret = btrfs_inc_ref(trans, root, cow, 1); + ret = btrfs_inc_ref(trans, root, cow, 1, 1); BUG_ON(ret); } new_flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF; @@ -365,9 +365,9 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) - ret = btrfs_inc_ref(trans, root, cow, 1); + ret = btrfs_inc_ref(trans, root, cow, 1, 1); else - ret = btrfs_inc_ref(trans, root, cow, 0); + ret = btrfs_inc_ref(trans, root, cow, 0, 1); BUG_ON(ret); } if (new_flags != 0) { @@ -381,11 +381,11 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, if (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF) { if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) - ret = btrfs_inc_ref(trans, root, cow, 1); + ret = btrfs_inc_ref(trans, root, cow, 1, 1); else - ret = btrfs_inc_ref(trans, root, cow, 0); + ret = btrfs_inc_ref(trans, root, cow, 0, 1); BUG_ON(ret); - ret = btrfs_dec_ref(trans, root, buf, 1); + ret = btrfs_dec_ref(trans, root, buf, 1, 1); BUG_ON(ret); } clean_tree_block(trans, root, buf); @@ -446,7 +446,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, cow = btrfs_alloc_free_block(trans, root, buf->len, parent_start, root->root_key.objectid, &disk_key, - level, search_start, empty_size); + level, search_start, empty_size, 1); if (IS_ERR(cow)) return PTR_ERR(cow); @@ -484,7 +484,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, rcu_assign_pointer(root->node, cow); btrfs_free_tree_block(trans, root, buf, parent_start, - last_ref); + last_ref, 1); free_extent_buffer(buf); add_root_to_dirty_list(root); } else { @@ -500,7 +500,7 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, trans->transid); btrfs_mark_buffer_dirty(parent); btrfs_free_tree_block(trans, root, buf, parent_start, - last_ref); + last_ref, 1); } if (unlock_orig) btrfs_tree_unlock(buf); @@ -957,7 +957,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, free_extent_buffer(mid); root_sub_used(root, mid->len); - btrfs_free_tree_block(trans, root, mid, 0, 1); + btrfs_free_tree_block(trans, root, mid, 0, 1, 0); /* once for the root ptr */ free_extent_buffer(mid); return 0; @@ -1015,7 +1015,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (wret) ret = wret; root_sub_used(root, right->len); - btrfs_free_tree_block(trans, root, right, 0, 1); + btrfs_free_tree_block(trans, root, right, 0, 1, 0); free_extent_buffer(right); right = NULL; } else { @@ -1055,7 +1055,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans, if (wret) ret = wret; root_sub_used(root, mid->len); - btrfs_free_tree_block(trans, root, mid, 0, 1); + btrfs_free_tree_block(trans, root, mid, 0, 1, 0); free_extent_buffer(mid); mid = NULL; } else { @@ -2089,7 +2089,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans, c = btrfs_alloc_free_block(trans, root, root->nodesize, 0, root->root_key.objectid, &lower_key, - level, root->node->start, 0); + level, root->node->start, 0, 0); if (IS_ERR(c)) return PTR_ERR(c); @@ -2216,7 +2216,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans, split = btrfs_alloc_free_block(trans, root, root->nodesize, 0, root->root_key.objectid, - &disk_key, level, c->start, 0); + &disk_key, level, c->start, 0, 0); if (IS_ERR(split)) return PTR_ERR(split); @@ -2970,7 +2970,7 @@ again: right = btrfs_alloc_free_block(trans, root, root->leafsize, 0, root->root_key.objectid, - &disk_key, 0, l->start, 0); + &disk_key, 0, l->start, 0, 0); if (IS_ERR(right)) return PTR_ERR(right); @@ -3781,7 +3781,7 @@ static noinline int btrfs_del_leaf(struct btrfs_trans_handle *trans, root_sub_used(root, leaf->len); - btrfs_free_tree_block(trans, root, leaf, 0, 1); + btrfs_free_tree_block(trans, root, leaf, 0, 1, 0); return 0; } /* diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3e4a07b79817..543f60bddb39 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2277,11 +2277,11 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, u32 blocksize, u64 parent, u64 root_objectid, struct btrfs_disk_key *key, int level, - u64 hint, u64 empty_size); + u64 hint, u64 empty_size, int for_cow); void btrfs_free_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, - u64 parent, int last_ref); + u64 parent, int last_ref, int for_cow); struct extent_buffer *btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u32 blocksize, @@ -2301,17 +2301,17 @@ int btrfs_reserve_extent(struct btrfs_trans_handle *trans, u64 search_end, struct btrfs_key *ins, u64 data); int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf, int full_backref); + struct extent_buffer *buf, int full_backref, int for_cow); int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf, int full_backref); + struct extent_buffer *buf, int full_backref, int for_cow); int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 flags, int is_data); int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, - u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset); + u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, + u64 owner, u64 offset, int for_cow); int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len); int btrfs_free_and_pin_reserved_extent(struct btrfs_root *root, @@ -2323,7 +2323,7 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans, int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset); + u64 root_objectid, u64 owner, u64 offset, int for_cow); int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans, struct btrfs_root *root); @@ -2492,7 +2492,8 @@ static inline int btrfs_next_item(struct btrfs_root *root, struct btrfs_path *p) int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path); int btrfs_leaf_free_space(struct btrfs_root *root, struct extent_buffer *leaf); void btrfs_drop_snapshot(struct btrfs_root *root, - struct btrfs_block_rsv *block_rsv, int update_ref); + struct btrfs_block_rsv *block_rsv, int update_ref, + int for_reloc); int btrfs_drop_subtree(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *node, diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index 125cf76fcd08..3a0f0ab804f4 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -390,7 +390,8 @@ update_existing_head_ref(struct btrfs_delayed_ref_node *existing, * this does all the dirty work in terms of maintaining the correct * overall modification count. */ -static noinline int add_delayed_ref_head(struct btrfs_trans_handle *trans, +static noinline int add_delayed_ref_head(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_node *ref, u64 bytenr, u64 num_bytes, int action, int is_data) @@ -468,10 +469,12 @@ static noinline int add_delayed_ref_head(struct btrfs_trans_handle *trans, /* * helper to insert a delayed tree ref into the rbtree. */ -static noinline int add_delayed_tree_ref(struct btrfs_trans_handle *trans, +static noinline int add_delayed_tree_ref(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_node *ref, u64 bytenr, u64 num_bytes, u64 parent, - u64 ref_root, int level, int action) + u64 ref_root, int level, int action, + int for_cow) { struct btrfs_delayed_ref_node *existing; struct btrfs_delayed_tree_ref *full_ref; @@ -522,11 +525,12 @@ static noinline int add_delayed_tree_ref(struct btrfs_trans_handle *trans, /* * helper to insert a delayed data ref into the rbtree. */ -static noinline int add_delayed_data_ref(struct btrfs_trans_handle *trans, +static noinline int add_delayed_data_ref(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_node *ref, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, u64 owner, u64 offset, - int action) + int action, int for_cow) { struct btrfs_delayed_ref_node *existing; struct btrfs_delayed_data_ref *full_ref; @@ -554,6 +558,7 @@ static noinline int add_delayed_data_ref(struct btrfs_trans_handle *trans, full_ref->root = ref_root; ref->type = BTRFS_EXTENT_DATA_REF_KEY; } + full_ref->objectid = owner; full_ref->offset = offset; @@ -580,10 +585,12 @@ static noinline int add_delayed_data_ref(struct btrfs_trans_handle *trans, * to make sure the delayed ref is eventually processed before this * transaction commits. */ -int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, +int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, int level, int action, - struct btrfs_delayed_extent_op *extent_op) + struct btrfs_delayed_extent_op *extent_op, + int for_cow) { struct btrfs_delayed_tree_ref *ref; struct btrfs_delayed_ref_head *head_ref; @@ -610,12 +617,13 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, * insert both the head node and the new ref without dropping * the spin lock */ - ret = add_delayed_ref_head(trans, &head_ref->node, bytenr, num_bytes, - action, 0); + ret = add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr, + num_bytes, action, 0); BUG_ON(ret); - ret = add_delayed_tree_ref(trans, &ref->node, bytenr, num_bytes, - parent, ref_root, level, action); + ret = add_delayed_tree_ref(fs_info, trans, &ref->node, bytenr, + num_bytes, parent, ref_root, level, action, + for_cow); BUG_ON(ret); spin_unlock(&delayed_refs->lock); return 0; @@ -624,11 +632,13 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, /* * add a delayed data ref. it's similar to btrfs_add_delayed_tree_ref. */ -int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, +int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, u64 owner, u64 offset, int action, - struct btrfs_delayed_extent_op *extent_op) + struct btrfs_delayed_extent_op *extent_op, + int for_cow) { struct btrfs_delayed_data_ref *ref; struct btrfs_delayed_ref_head *head_ref; @@ -655,18 +665,20 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, * insert both the head node and the new ref without dropping * the spin lock */ - ret = add_delayed_ref_head(trans, &head_ref->node, bytenr, num_bytes, - action, 1); + ret = add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr, + num_bytes, action, 1); BUG_ON(ret); - ret = add_delayed_data_ref(trans, &ref->node, bytenr, num_bytes, - parent, ref_root, owner, offset, action); + ret = add_delayed_data_ref(fs_info, trans, &ref->node, bytenr, + num_bytes, parent, ref_root, owner, offset, + action, for_cow); BUG_ON(ret); spin_unlock(&delayed_refs->lock); return 0; } -int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, +int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, struct btrfs_delayed_extent_op *extent_op) { @@ -683,7 +695,7 @@ int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, delayed_refs = &trans->transaction->delayed_refs; spin_lock(&delayed_refs->lock); - ret = add_delayed_ref_head(trans, &head_ref->node, bytenr, + ret = add_delayed_ref_head(fs_info, trans, &head_ref->node, bytenr, num_bytes, BTRFS_UPDATE_DELAYED_HEAD, extent_op->is_data); BUG_ON(ret); diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index e287e3b0eab0..8316bff18d30 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -151,16 +151,21 @@ static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref) } } -int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, +int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, int level, int action, - struct btrfs_delayed_extent_op *extent_op); -int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, + struct btrfs_delayed_extent_op *extent_op, + int for_cow); +int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, u64 parent, u64 ref_root, u64 owner, u64 offset, int action, - struct btrfs_delayed_extent_op *extent_op); -int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, + struct btrfs_delayed_extent_op *extent_op, + int for_cow); +int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, + struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, struct btrfs_delayed_extent_op *extent_op); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 94abc25392f6..6f8cd17c9a9f 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1243,7 +1243,8 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans, root->ref_cows = 0; leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0, - BTRFS_TREE_LOG_OBJECTID, NULL, 0, 0, 0); + BTRFS_TREE_LOG_OBJECTID, NULL, + 0, 0, 0, 0); if (IS_ERR(leaf)) { kfree(root); return ERR_CAST(leaf); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 813c6bb96c9a..dc8b9a834596 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1872,20 +1872,24 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset) + u64 root_objectid, u64 owner, u64 offset, int for_cow) { int ret; + struct btrfs_fs_info *fs_info = root->fs_info; + BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID && root_objectid == BTRFS_TREE_LOG_OBJECTID); if (owner < BTRFS_FIRST_FREE_OBJECTID) { - ret = btrfs_add_delayed_tree_ref(trans, bytenr, num_bytes, + ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr, + num_bytes, parent, root_objectid, (int)owner, - BTRFS_ADD_DELAYED_REF, NULL); + BTRFS_ADD_DELAYED_REF, NULL, for_cow); } else { - ret = btrfs_add_delayed_data_ref(trans, bytenr, num_bytes, + ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr, + num_bytes, parent, root_objectid, owner, offset, - BTRFS_ADD_DELAYED_REF, NULL); + BTRFS_ADD_DELAYED_REF, NULL, for_cow); } return ret; } @@ -2405,7 +2409,8 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans, extent_op->update_key = 0; extent_op->is_data = is_data ? 1 : 0; - ret = btrfs_add_delayed_extent_op(trans, bytenr, num_bytes, extent_op); + ret = btrfs_add_delayed_extent_op(root->fs_info, trans, bytenr, + num_bytes, extent_op); if (ret) kfree(extent_op); return ret; @@ -2590,7 +2595,7 @@ out: static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, - int full_backref, int inc) + int full_backref, int inc, int for_cow) { u64 bytenr; u64 num_bytes; @@ -2603,7 +2608,7 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, int level; int ret = 0; int (*process_func)(struct btrfs_trans_handle *, struct btrfs_root *, - u64, u64, u64, u64, u64, u64); + u64, u64, u64, u64, u64, u64, int); ref_root = btrfs_header_owner(buf); nritems = btrfs_header_nritems(buf); @@ -2640,14 +2645,15 @@ static int __btrfs_mod_ref(struct btrfs_trans_handle *trans, key.offset -= btrfs_file_extent_offset(buf, fi); ret = process_func(trans, root, bytenr, num_bytes, parent, ref_root, key.objectid, - key.offset); + key.offset, for_cow); if (ret) goto fail; } else { bytenr = btrfs_node_blockptr(buf, i); num_bytes = btrfs_level_size(root, level - 1); ret = process_func(trans, root, bytenr, num_bytes, - parent, ref_root, level - 1, 0); + parent, ref_root, level - 1, 0, + for_cow); if (ret) goto fail; } @@ -2659,15 +2665,15 @@ fail: } int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf, int full_backref) + struct extent_buffer *buf, int full_backref, int for_cow) { - return __btrfs_mod_ref(trans, root, buf, full_backref, 1); + return __btrfs_mod_ref(trans, root, buf, full_backref, 1, for_cow); } int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root, - struct extent_buffer *buf, int full_backref) + struct extent_buffer *buf, int full_backref, int for_cow) { - return __btrfs_mod_ref(trans, root, buf, full_backref, 0); + return __btrfs_mod_ref(trans, root, buf, full_backref, 0, for_cow); } static int write_one_cache_group(struct btrfs_trans_handle *trans, @@ -4937,16 +4943,17 @@ out: void btrfs_free_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, - u64 parent, int last_ref) + u64 parent, int last_ref, int for_cow) { struct btrfs_block_group_cache *cache = NULL; int ret; if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) { - ret = btrfs_add_delayed_tree_ref(trans, buf->start, buf->len, - parent, root->root_key.objectid, - btrfs_header_level(buf), - BTRFS_DROP_DELAYED_REF, NULL); + ret = btrfs_add_delayed_tree_ref(root->fs_info, trans, + buf->start, buf->len, + parent, root->root_key.objectid, + btrfs_header_level(buf), + BTRFS_DROP_DELAYED_REF, NULL, for_cow); BUG_ON(ret); } @@ -4981,12 +4988,12 @@ out: btrfs_put_block_group(cache); } -int btrfs_free_extent(struct btrfs_trans_handle *trans, - struct btrfs_root *root, - u64 bytenr, u64 num_bytes, u64 parent, - u64 root_objectid, u64 owner, u64 offset) +int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, + u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid, + u64 owner, u64 offset, int for_cow) { int ret; + struct btrfs_fs_info *fs_info = root->fs_info; /* * tree log blocks never actually go into the extent allocation @@ -4998,14 +5005,17 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans, btrfs_pin_extent(root, bytenr, num_bytes, 1); ret = 0; } else if (owner < BTRFS_FIRST_FREE_OBJECTID) { - ret = btrfs_add_delayed_tree_ref(trans, bytenr, num_bytes, + ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr, + num_bytes, parent, root_objectid, (int)owner, - BTRFS_DROP_DELAYED_REF, NULL); + BTRFS_DROP_DELAYED_REF, NULL, for_cow); BUG_ON(ret); } else { - ret = btrfs_add_delayed_data_ref(trans, bytenr, num_bytes, - parent, root_objectid, owner, - offset, BTRFS_DROP_DELAYED_REF, NULL); + ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr, + num_bytes, + parent, root_objectid, owner, + offset, BTRFS_DROP_DELAYED_REF, + NULL, for_cow); BUG_ON(ret); } return ret; @@ -5826,9 +5836,10 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans, BUG_ON(root_objectid == BTRFS_TREE_LOG_OBJECTID); - ret = btrfs_add_delayed_data_ref(trans, ins->objectid, ins->offset, - 0, root_objectid, owner, offset, - BTRFS_ADD_DELAYED_EXTENT, NULL); + ret = btrfs_add_delayed_data_ref(root->fs_info, trans, ins->objectid, + ins->offset, 0, + root_objectid, owner, offset, + BTRFS_ADD_DELAYED_EXTENT, NULL, 0); return ret; } @@ -5998,7 +6009,7 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans, struct btrfs_root *root, u32 blocksize, u64 parent, u64 root_objectid, struct btrfs_disk_key *key, int level, - u64 hint, u64 empty_size) + u64 hint, u64 empty_size, int for_cow) { struct btrfs_key ins; struct btrfs_block_rsv *block_rsv; @@ -6042,10 +6053,11 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans, extent_op->update_flags = 1; extent_op->is_data = 0; - ret = btrfs_add_delayed_tree_ref(trans, ins.objectid, + ret = btrfs_add_delayed_tree_ref(root->fs_info, trans, + ins.objectid, ins.offset, parent, root_objectid, level, BTRFS_ADD_DELAYED_EXTENT, - extent_op); + extent_op, for_cow); BUG_ON(ret); } return buf; @@ -6062,6 +6074,7 @@ struct walk_control { int keep_locks; int reada_slot; int reada_count; + int for_reloc; }; #define DROP_REFERENCE 1 @@ -6200,9 +6213,9 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans, /* wc->stage == UPDATE_BACKREF */ if (!(wc->flags[level] & flag)) { BUG_ON(!path->locks[level]); - ret = btrfs_inc_ref(trans, root, eb, 1); + ret = btrfs_inc_ref(trans, root, eb, 1, wc->for_reloc); BUG_ON(ret); - ret = btrfs_dec_ref(trans, root, eb, 0); + ret = btrfs_dec_ref(trans, root, eb, 0, wc->for_reloc); BUG_ON(ret); ret = btrfs_set_disk_extent_flags(trans, root, eb->start, eb->len, flag, 0); @@ -6346,7 +6359,7 @@ skip: } ret = btrfs_free_extent(trans, root, bytenr, blocksize, parent, - root->root_key.objectid, level - 1, 0); + root->root_key.objectid, level - 1, 0, 0); BUG_ON(ret); } btrfs_tree_unlock(next); @@ -6420,9 +6433,11 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, if (wc->refs[level] == 1) { if (level == 0) { if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF) - ret = btrfs_dec_ref(trans, root, eb, 1); + ret = btrfs_dec_ref(trans, root, eb, 1, + wc->for_reloc); else - ret = btrfs_dec_ref(trans, root, eb, 0); + ret = btrfs_dec_ref(trans, root, eb, 0, + wc->for_reloc); BUG_ON(ret); } /* make block locked assertion in clean_tree_block happy */ @@ -6449,7 +6464,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans, btrfs_header_owner(path->nodes[level + 1])); } - btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1); + btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1, 0); out: wc->refs[level] = 0; wc->flags[level] = 0; @@ -6533,7 +6548,8 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans, * blocks are properly updated. */ void btrfs_drop_snapshot(struct btrfs_root *root, - struct btrfs_block_rsv *block_rsv, int update_ref) + struct btrfs_block_rsv *block_rsv, int update_ref, + int for_reloc) { struct btrfs_path *path; struct btrfs_trans_handle *trans; @@ -6621,6 +6637,7 @@ void btrfs_drop_snapshot(struct btrfs_root *root, wc->stage = DROP_REFERENCE; wc->update_ref = update_ref; wc->keep_locks = 0; + wc->for_reloc = for_reloc; wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(root); while (1) { @@ -6705,6 +6722,7 @@ out: * drop subtree rooted at tree block 'node'. * * NOTE: this function will unlock and release tree block 'node' + * only used by relocation code */ int btrfs_drop_subtree(struct btrfs_trans_handle *trans, struct btrfs_root *root, @@ -6749,6 +6767,7 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans, wc->stage = DROP_REFERENCE; wc->update_ref = 0; wc->keep_locks = 1; + wc->for_reloc = 1; wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(root); while (1) { diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index f2e928289600..d2b60ed6c33f 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -678,7 +678,7 @@ next_slot: disk_bytenr, num_bytes, 0, root->root_key.objectid, new_key.objectid, - start - extent_offset); + start - extent_offset, 0); BUG_ON(ret); *hint_byte = disk_bytenr; } @@ -753,7 +753,7 @@ next_slot: disk_bytenr, num_bytes, 0, root->root_key.objectid, key.objectid, key.offset - - extent_offset); + extent_offset, 0); BUG_ON(ret); inode_sub_bytes(inode, extent_end - key.offset); @@ -962,7 +962,7 @@ again: ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0, root->root_key.objectid, - ino, orig_offset); + ino, orig_offset, 0); BUG_ON(ret); if (split == start) { @@ -989,7 +989,7 @@ again: del_nr++; ret = btrfs_free_extent(trans, root, bytenr, num_bytes, 0, root->root_key.objectid, - ino, orig_offset); + ino, orig_offset, 0); BUG_ON(ret); } other_start = 0; @@ -1006,7 +1006,7 @@ again: del_nr++; ret = btrfs_free_extent(trans, root, bytenr, num_bytes, 0, root->root_key.objectid, - ino, orig_offset); + ino, orig_offset, 0); BUG_ON(ret); } if (del_nr == 0) { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index c5ccec23984c..ea819386b864 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3139,7 +3139,7 @@ delete: ret = btrfs_free_extent(trans, root, extent_start, extent_num_bytes, 0, btrfs_header_owner(leaf), - ino, extent_offset); + ino, extent_offset, 0); BUG_ON(ret); } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 72d461656f60..c48f2e931ea0 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -358,7 +358,7 @@ static noinline int create_subvol(struct btrfs_root *root, return PTR_ERR(trans); leaf = btrfs_alloc_free_block(trans, root, root->leafsize, - 0, objectid, NULL, 0, 0, 0); + 0, objectid, NULL, 0, 0, 0, 0); if (IS_ERR(leaf)) { ret = PTR_ERR(leaf); goto fail; @@ -2425,7 +2425,8 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, disko, diskl, 0, root->root_key.objectid, btrfs_ino(inode), - new_key.offset - datao); + new_key.offset - datao, + 0); BUG_ON(ret); } } else if (type == BTRFS_FILE_EXTENT_INLINE) { diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index dff29d5e151a..8c1aae2c845d 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1604,12 +1604,12 @@ int replace_file_extents(struct btrfs_trans_handle *trans, ret = btrfs_inc_extent_ref(trans, root, new_bytenr, num_bytes, parent, btrfs_header_owner(leaf), - key.objectid, key.offset); + key.objectid, key.offset, 1); BUG_ON(ret); ret = btrfs_free_extent(trans, root, bytenr, num_bytes, parent, btrfs_header_owner(leaf), - key.objectid, key.offset); + key.objectid, key.offset, 1); BUG_ON(ret); } if (dirty) @@ -1778,21 +1778,23 @@ again: ret = btrfs_inc_extent_ref(trans, src, old_bytenr, blocksize, path->nodes[level]->start, - src->root_key.objectid, level - 1, 0); + src->root_key.objectid, level - 1, 0, + 1); BUG_ON(ret); ret = btrfs_inc_extent_ref(trans, dest, new_bytenr, blocksize, 0, dest->root_key.objectid, level - 1, - 0); + 0, 1); BUG_ON(ret); ret = btrfs_free_extent(trans, src, new_bytenr, blocksize, path->nodes[level]->start, - src->root_key.objectid, level - 1, 0); + src->root_key.objectid, level - 1, 0, + 1); BUG_ON(ret); ret = btrfs_free_extent(trans, dest, old_bytenr, blocksize, 0, dest->root_key.objectid, level - 1, - 0); + 0, 1); BUG_ON(ret); btrfs_unlock_up_safe(path, 0); @@ -2244,7 +2246,7 @@ again: } else { list_del_init(&reloc_root->root_list); } - btrfs_drop_snapshot(reloc_root, rc->block_rsv, 0); + btrfs_drop_snapshot(reloc_root, rc->block_rsv, 0, 1); } if (found) { @@ -2558,7 +2560,7 @@ static int do_relocation(struct btrfs_trans_handle *trans, node->eb->start, blocksize, upper->eb->start, btrfs_header_owner(upper->eb), - node->level, 0); + node->level, 0, 1); BUG_ON(ret); ret = btrfs_drop_subtree(trans, root, eb, upper->eb); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 81376d94cd3c..a2bfedcbcabc 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1393,9 +1393,9 @@ int btrfs_clean_old_snapshots(struct btrfs_root *root) if (btrfs_header_backref_rev(root->node) < BTRFS_MIXED_BACKREF_REV) - btrfs_drop_snapshot(root, NULL, 0); + btrfs_drop_snapshot(root, NULL, 0, 0); else - btrfs_drop_snapshot(root, NULL, 1); + btrfs_drop_snapshot(root, NULL, 1, 0); } return 0; } diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index f4d81c06d48f..fce7b9ec3bfa 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -589,7 +589,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans, ret = btrfs_inc_extent_ref(trans, root, ins.objectid, ins.offset, 0, root->root_key.objectid, - key->objectid, offset); + key->objectid, offset, 0); BUG_ON(ret); } else { /* -- cgit v1.2.3 From a561be7100cd610bd2e082f3211c1dfb45835817 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 23 Nov 2011 11:57:51 -0500 Subject: switch a bunch of places to mnt_want_write_file() it's both faster (in case when file has been opened for write) and cleaner. Signed-off-by: Al Viro --- fs/btrfs/ioctl.c | 10 +++++----- fs/ext2/ioctl.c | 6 +++--- fs/ext3/ioctl.c | 10 +++++----- fs/ext4/ioctl.c | 14 +++++++------- fs/fat/file.c | 2 +- fs/gfs2/file.c | 2 +- fs/hfsplus/ioctl.c | 2 +- fs/jfs/ioctl.c | 2 +- fs/nfsd/nfs4recover.c | 6 +++--- fs/nilfs2/ioctl.c | 12 ++++++------ fs/ocfs2/ioctl.c | 2 +- fs/ocfs2/move_extents.c | 2 +- fs/reiserfs/ioctl.c | 4 ++-- fs/ubifs/ioctl.c | 2 +- fs/xfs/xfs_ioctl.c | 4 ++-- fs/xfs/xfs_ioctl32.c | 4 ++-- 16 files changed, 42 insertions(+), 42 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index c04f02c7d5bb..20dd8f3b6c72 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -201,7 +201,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) } } - ret = mnt_want_write(file->f_path.mnt); + ret = mnt_want_write_file(file); if (ret) goto out_unlock; @@ -1855,7 +1855,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file, goto out; } - err = mnt_want_write(file->f_path.mnt); + err = mnt_want_write_file(file); if (err) goto out; @@ -1987,7 +1987,7 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) if (btrfs_root_readonly(root)) return -EROFS; - ret = mnt_want_write(file->f_path.mnt); + ret = mnt_want_write_file(file); if (ret) return ret; @@ -2195,7 +2195,7 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, if (btrfs_root_readonly(root)) return -EROFS; - ret = mnt_want_write(file->f_path.mnt); + ret = mnt_want_write_file(file); if (ret) return ret; @@ -2549,7 +2549,7 @@ static long btrfs_ioctl_trans_start(struct file *file) if (btrfs_root_readonly(root)) goto out; - ret = mnt_want_write(file->f_path.mnt); + ret = mnt_want_write_file(file); if (ret) goto out; diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c index f81e250ac5c4..61a3f9661728 100644 --- a/fs/ext2/ioctl.c +++ b/fs/ext2/ioctl.c @@ -35,7 +35,7 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case EXT2_IOC_SETFLAGS: { unsigned int oldflags; - ret = mnt_want_write(filp->f_path.mnt); + ret = mnt_want_write_file(filp); if (ret) return ret; @@ -91,7 +91,7 @@ setflags_out: case EXT2_IOC_SETVERSION: if (!inode_owner_or_capable(inode)) return -EPERM; - ret = mnt_want_write(filp->f_path.mnt); + ret = mnt_want_write_file(filp); if (ret) return ret; if (get_user(inode->i_generation, (int __user *) arg)) { @@ -121,7 +121,7 @@ setflags_out: if (get_user(rsv_window_size, (int __user *)arg)) return -EFAULT; - ret = mnt_want_write(filp->f_path.mnt); + ret = mnt_want_write_file(filp); if (ret) return ret; diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c index ba1b54e23cae..a02863a080d3 100644 --- a/fs/ext3/ioctl.c +++ b/fs/ext3/ioctl.c @@ -44,7 +44,7 @@ long ext3_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (get_user(flags, (int __user *) arg)) return -EFAULT; - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) return err; @@ -126,7 +126,7 @@ flags_out: if (!inode_owner_or_capable(inode)) return -EPERM; - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) return err; if (get_user(generation, (int __user *) arg)) { @@ -164,7 +164,7 @@ setversion_out: if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode)) return -ENOTTY; - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) return err; @@ -206,7 +206,7 @@ setrsvsz_out: if (!capable(CAP_SYS_RESOURCE)) return -EPERM; - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) return err; @@ -232,7 +232,7 @@ group_extend_out: if (!capable(CAP_SYS_RESOURCE)) return -EPERM; - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) return err; diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index a56796814d6a..9a49760b554d 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -45,7 +45,7 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (get_user(flags, (int __user *) arg)) return -EFAULT; - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) return err; @@ -150,7 +150,7 @@ flags_out: if (!inode_owner_or_capable(inode)) return -EPERM; - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) return err; if (get_user(generation, (int __user *) arg)) { @@ -192,7 +192,7 @@ setversion_out: return -EOPNOTSUPP; } - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) return err; @@ -240,7 +240,7 @@ setversion_out: return -EOPNOTSUPP; } - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) goto mext_out; @@ -277,7 +277,7 @@ mext_out: return -EOPNOTSUPP; } - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) return err; @@ -301,7 +301,7 @@ mext_out: if (!inode_owner_or_capable(inode)) return -EACCES; - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) return err; /* @@ -323,7 +323,7 @@ mext_out: if (!inode_owner_or_capable(inode)) return -EACCES; - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) return err; err = ext4_alloc_da_blocks(inode); diff --git a/fs/fat/file.c b/fs/fat/file.c index c118acf16e43..50746a1a0789 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -44,7 +44,7 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) goto out; mutex_lock(&inode->i_mutex); - err = mnt_want_write(file->f_path.mnt); + err = mnt_want_write_file(file); if (err) goto out_unlock_inode; diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index ce36a56dfeac..28fc6e3855f3 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -223,7 +223,7 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask) int error; u32 new_flags, flags; - error = mnt_want_write(filp->f_path.mnt); + error = mnt_want_write_file(filp); if (error) return error; diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c index fbaa6690c8e0..31d3fe576429 100644 --- a/fs/hfsplus/ioctl.c +++ b/fs/hfsplus/ioctl.c @@ -43,7 +43,7 @@ static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags) unsigned int flags; int err = 0; - err = mnt_want_write(file->f_path.mnt); + err = mnt_want_write_file(file); if (err) goto out; diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c index 6f98a1866776..73d9eaa91c05 100644 --- a/fs/jfs/ioctl.c +++ b/fs/jfs/ioctl.c @@ -68,7 +68,7 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) unsigned int oldflags; int err; - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) return err; diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index ed083b9a731b..a9aa2f161262 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -147,7 +147,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) status = -EEXIST; if (dentry->d_inode) goto out_put; - status = mnt_want_write(rec_file->f_path.mnt); + status = mnt_want_write_file(rec_file); if (status) goto out_put; status = vfs_mkdir(dir->d_inode, dentry, S_IRWXU); @@ -268,7 +268,7 @@ nfsd4_remove_clid_dir(struct nfs4_client *clp) if (!rec_file || !clp->cl_firststate) return; - status = mnt_want_write(rec_file->f_path.mnt); + status = mnt_want_write_file(rec_file); if (status) goto out; clp->cl_firststate = 0; @@ -311,7 +311,7 @@ nfsd4_recdir_purge_old(void) { if (!rec_file) return; - status = mnt_want_write(rec_file->f_path.mnt); + status = mnt_want_write_file(rec_file); if (status) goto out; status = nfsd4_list_rec_dir(purge_old); diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index ac258beeda3c..b7697d1ccd61 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -27,7 +27,7 @@ #include /* copy_from_user(), copy_to_user() */ #include #include /* compat_ptr() */ -#include /* mnt_want_write(), mnt_drop_write() */ +#include /* mnt_want_write_file(), mnt_drop_write() */ #include #include #include "nilfs.h" @@ -119,7 +119,7 @@ static int nilfs_ioctl_setflags(struct inode *inode, struct file *filp, if (get_user(flags, (int __user *)argp)) return -EFAULT; - ret = mnt_want_write(filp->f_path.mnt); + ret = mnt_want_write_file(filp); if (ret) return ret; @@ -174,7 +174,7 @@ static int nilfs_ioctl_change_cpmode(struct inode *inode, struct file *filp, if (!capable(CAP_SYS_ADMIN)) return -EPERM; - ret = mnt_want_write(filp->f_path.mnt); + ret = mnt_want_write_file(filp); if (ret) return ret; @@ -210,7 +210,7 @@ nilfs_ioctl_delete_checkpoint(struct inode *inode, struct file *filp, if (!capable(CAP_SYS_ADMIN)) return -EPERM; - ret = mnt_want_write(filp->f_path.mnt); + ret = mnt_want_write_file(filp); if (ret) return ret; @@ -591,7 +591,7 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp, if (!capable(CAP_SYS_ADMIN)) return -EPERM; - ret = mnt_want_write(filp->f_path.mnt); + ret = mnt_want_write_file(filp); if (ret) return ret; @@ -710,7 +710,7 @@ static int nilfs_ioctl_resize(struct inode *inode, struct file *filp, if (!capable(CAP_SYS_ADMIN)) goto out; - ret = mnt_want_write(filp->f_path.mnt); + ret = mnt_want_write_file(filp); if (ret) goto out; diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index 726ff265b296..892ace253f97 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -906,7 +906,7 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) if (get_user(flags, (int __user *) arg)) return -EFAULT; - status = mnt_want_write(filp->f_path.mnt); + status = mnt_want_write_file(filp); if (status) return status; status = ocfs2_set_inode_attr(inode, flags, diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 184c76b8c293..1d3bf83f8b85 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -1059,7 +1059,7 @@ int ocfs2_ioctl_move_extents(struct file *filp, void __user *argp) struct ocfs2_move_extents range; struct ocfs2_move_extents_context *context = NULL; - status = mnt_want_write(filp->f_path.mnt); + status = mnt_want_write_file(filp); if (status) return status; diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c index 4e153051bc75..0b94d7b2b11f 100644 --- a/fs/reiserfs/ioctl.c +++ b/fs/reiserfs/ioctl.c @@ -55,7 +55,7 @@ long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) break; } - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) break; @@ -107,7 +107,7 @@ setflags_out: err = -EPERM; break; } - err = mnt_want_write(filp->f_path.mnt); + err = mnt_want_write_file(filp); if (err) break; if (get_user(inode->i_generation, (int __user *)arg)) { diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c index 548acf494afd..e52c84598feb 100644 --- a/fs/ubifs/ioctl.c +++ b/fs/ubifs/ioctl.c @@ -173,7 +173,7 @@ long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) * Make sure the file-system is read-write and make sure it * will not become read-only while we are changing the flags. */ - err = mnt_want_write(file->f_path.mnt); + err = mnt_want_write_file(file); if (err) return err; dbg_gen("set flags: %#x, i_flags %#x", flags, inode->i_flags); diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index d99a90518909..b436e17c753e 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -559,7 +559,7 @@ xfs_attrmulti_by_handle( ops[i].am_flags); break; case ATTR_OP_SET: - ops[i].am_error = mnt_want_write(parfilp->f_path.mnt); + ops[i].am_error = mnt_want_write_file(parfilp); if (ops[i].am_error) break; ops[i].am_error = xfs_attrmulti_attr_set( @@ -569,7 +569,7 @@ xfs_attrmulti_by_handle( mnt_drop_write(parfilp->f_path.mnt); break; case ATTR_OP_REMOVE: - ops[i].am_error = mnt_want_write(parfilp->f_path.mnt); + ops[i].am_error = mnt_want_write_file(parfilp); if (ops[i].am_error) break; ops[i].am_error = xfs_attrmulti_attr_remove( diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index 54e623bfbb85..dd4ba1d4c582 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -454,7 +454,7 @@ xfs_compat_attrmulti_by_handle( &ops[i].am_length, ops[i].am_flags); break; case ATTR_OP_SET: - ops[i].am_error = mnt_want_write(parfilp->f_path.mnt); + ops[i].am_error = mnt_want_write_file(parfilp); if (ops[i].am_error) break; ops[i].am_error = xfs_attrmulti_attr_set( @@ -464,7 +464,7 @@ xfs_compat_attrmulti_by_handle( mnt_drop_write(parfilp->f_path.mnt); break; case ATTR_OP_REMOVE: - ops[i].am_error = mnt_want_write(parfilp->f_path.mnt); + ops[i].am_error = mnt_want_write_file(parfilp); if (ops[i].am_error) break; ops[i].am_error = xfs_attrmulti_attr_remove( -- cgit v1.2.3 From 2a79f17e4a641a2f463cb512cb0ec349844a147b Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 9 Dec 2011 08:06:57 -0500 Subject: vfs: mnt_drop_write_file() new helper (wrapper around mnt_drop_write()) to be used in pair with mnt_want_write_file(). Signed-off-by: Al Viro --- fs/btrfs/ioctl.c | 12 ++++++------ fs/ext2/ioctl.c | 6 +++--- fs/ext3/ioctl.c | 10 +++++----- fs/ext4/ioctl.c | 14 +++++++------- fs/fat/file.c | 2 +- fs/gfs2/file.c | 2 +- fs/hfsplus/ioctl.c | 2 +- fs/inode.c | 2 +- fs/jfs/ioctl.c | 2 +- fs/namespace.c | 6 ++++++ fs/ncpfs/ioctl.c | 2 +- fs/nfsd/nfs4recover.c | 6 +++--- fs/nilfs2/ioctl.c | 12 ++++++------ fs/ocfs2/ioctl.c | 2 +- fs/ocfs2/move_extents.c | 2 +- fs/open.c | 2 +- fs/reiserfs/ioctl.c | 4 ++-- fs/ubifs/ioctl.c | 2 +- fs/xattr.c | 4 ++-- fs/xfs/xfs_ioctl.c | 4 ++-- fs/xfs/xfs_ioctl32.c | 4 ++-- include/linux/mount.h | 1 + 22 files changed, 55 insertions(+), 48 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 20dd8f3b6c72..5441ff1480fd 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -259,7 +259,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) btrfs_end_transaction(trans, root); - mnt_drop_write(file->f_path.mnt); + mnt_drop_write_file(file); ret = 0; out_unlock: @@ -1971,7 +1971,7 @@ out_dput: dput(dentry); out_unlock_dir: mutex_unlock(&dir->i_mutex); - mnt_drop_write(file->f_path.mnt); + mnt_drop_write_file(file); out: kfree(vol_args); return err; @@ -2040,7 +2040,7 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp) ret = -EINVAL; } out: - mnt_drop_write(file->f_path.mnt); + mnt_drop_write_file(file); return ret; } @@ -2510,7 +2510,7 @@ out_unlock: out_fput: fput(src_file); out_drop_write: - mnt_drop_write(file->f_path.mnt); + mnt_drop_write_file(file); return ret; } @@ -2565,7 +2565,7 @@ static long btrfs_ioctl_trans_start(struct file *file) out_drop: atomic_dec(&root->fs_info->open_ioctl_trans); - mnt_drop_write(file->f_path.mnt); + mnt_drop_write_file(file); out: return ret; } @@ -2800,7 +2800,7 @@ long btrfs_ioctl_trans_end(struct file *file) atomic_dec(&root->fs_info->open_ioctl_trans); - mnt_drop_write(file->f_path.mnt); + mnt_drop_write_file(file); return 0; } diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c index 61a3f9661728..1089f760c847 100644 --- a/fs/ext2/ioctl.c +++ b/fs/ext2/ioctl.c @@ -83,7 +83,7 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); setflags_out: - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return ret; } case EXT2_IOC_GETVERSION: @@ -100,7 +100,7 @@ setflags_out: inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); } - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return ret; case EXT2_IOC_GETRSVSZ: if (test_opt(inode->i_sb, RESERVATION) @@ -145,7 +145,7 @@ setflags_out: rsv->rsv_goal_size = rsv_window_size; } mutex_unlock(&ei->truncate_mutex); - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return 0; } default: diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c index a02863a080d3..8e37c41a071b 100644 --- a/fs/ext3/ioctl.c +++ b/fs/ext3/ioctl.c @@ -110,7 +110,7 @@ flags_err: err = ext3_change_inode_journal_flag(inode, jflag); flags_out: mutex_unlock(&inode->i_mutex); - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return err; } case EXT3_IOC_GETVERSION: @@ -147,7 +147,7 @@ flags_out: } ext3_journal_stop(handle); setversion_out: - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return err; } case EXT3_IOC_GETRSVSZ: @@ -195,7 +195,7 @@ setversion_out: } mutex_unlock(&ei->truncate_mutex); setrsvsz_out: - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return err; } case EXT3_IOC_GROUP_EXTEND: { @@ -221,7 +221,7 @@ setrsvsz_out: if (err == 0) err = err2; group_extend_out: - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return err; } case EXT3_IOC_GROUP_ADD: { @@ -249,7 +249,7 @@ group_extend_out: if (err == 0) err = err2; group_add_out: - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return err; } case FITRIM: { diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 9a49760b554d..d37b3bb2a3b8 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -134,7 +134,7 @@ flags_err: err = ext4_ext_migrate(inode); flags_out: mutex_unlock(&inode->i_mutex); - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return err; } case EXT4_IOC_GETVERSION: @@ -171,7 +171,7 @@ flags_out: } ext4_journal_stop(handle); setversion_out: - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return err; } case EXT4_IOC_GROUP_EXTEND: { @@ -204,7 +204,7 @@ setversion_out: } if (err == 0) err = err2; - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); ext4_resize_end(sb); return err; @@ -246,7 +246,7 @@ setversion_out: err = ext4_move_extents(filp, donor_filp, me.orig_start, me.donor_start, me.len, &me.moved_len); - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); if (me.moved_len > 0) file_remove_suid(donor_filp); @@ -289,7 +289,7 @@ mext_out: } if (err == 0) err = err2; - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); ext4_resize_end(sb); return err; @@ -313,7 +313,7 @@ mext_out: mutex_lock(&(inode->i_mutex)); err = ext4_ext_migrate(inode); mutex_unlock(&(inode->i_mutex)); - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return err; } @@ -327,7 +327,7 @@ mext_out: if (err) return err; err = ext4_alloc_da_blocks(inode); - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return err; } diff --git a/fs/fat/file.c b/fs/fat/file.c index 50746a1a0789..d81d01a99b2c 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -108,7 +108,7 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) fat_save_attrs(inode, attr); mark_inode_dirty(inode); out_drop_write: - mnt_drop_write(file->f_path.mnt); + mnt_drop_write_file(file); out_unlock_inode: mutex_unlock(&inode->i_mutex); out: diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 28fc6e3855f3..b8927d4f3bf2 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -285,7 +285,7 @@ out_trans_end: out: gfs2_glock_dq_uninit(&gh); out_drop_write: - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return error; } diff --git a/fs/hfsplus/ioctl.c b/fs/hfsplus/ioctl.c index 31d3fe576429..f66c7655b3f7 100644 --- a/fs/hfsplus/ioctl.c +++ b/fs/hfsplus/ioctl.c @@ -94,7 +94,7 @@ static int hfsplus_ioctl_setflags(struct file *file, int __user *user_flags) out_unlock_inode: mutex_unlock(&inode->i_mutex); out_drop_write: - mnt_drop_write(file->f_path.mnt); + mnt_drop_write_file(file); out: return err; } diff --git a/fs/inode.c b/fs/inode.c index ee4e66b998f4..4fda5ee85518 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1508,7 +1508,7 @@ void file_update_time(struct file *file) if (sync_it & S_MTIME) inode->i_mtime = now; mark_inode_dirty_sync(inode); - mnt_drop_write(file->f_path.mnt); + mnt_drop_write_file(file); } EXPORT_SYMBOL(file_update_time); diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c index 73d9eaa91c05..f19d1e04a374 100644 --- a/fs/jfs/ioctl.c +++ b/fs/jfs/ioctl.c @@ -120,7 +120,7 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); setflags_out: - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return err; } default: diff --git a/fs/namespace.c b/fs/namespace.c index 7a8f949cec1b..86b4f6406470 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -392,6 +392,12 @@ void mnt_drop_write(struct vfsmount *mnt) } EXPORT_SYMBOL_GPL(mnt_drop_write); +void mnt_drop_write_file(struct file *file) +{ + mnt_drop_write(file->f_path.mnt); +} +EXPORT_SYMBOL(mnt_drop_write_file); + static int mnt_make_readonly(struct vfsmount *mnt) { int ret = 0; diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c index 790e92a9ec63..6958adfaff08 100644 --- a/fs/ncpfs/ioctl.c +++ b/fs/ncpfs/ioctl.c @@ -901,7 +901,7 @@ long ncp_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) ret = __ncp_ioctl(inode, cmd, arg); outDropWrite: if (need_drop_write) - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); out: return ret; } diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index a9aa2f161262..80a0be9ed008 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -151,7 +151,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) if (status) goto out_put; status = vfs_mkdir(dir->d_inode, dentry, S_IRWXU); - mnt_drop_write(rec_file->f_path.mnt); + mnt_drop_write_file(rec_file); out_put: dput(dentry); out_unlock: @@ -281,7 +281,7 @@ nfsd4_remove_clid_dir(struct nfs4_client *clp) nfs4_reset_creds(original_cred); if (status == 0) vfs_fsync(rec_file, 0); - mnt_drop_write(rec_file->f_path.mnt); + mnt_drop_write_file(rec_file); out: if (status) printk("NFSD: Failed to remove expired client state directory" @@ -317,7 +317,7 @@ nfsd4_recdir_purge_old(void) { status = nfsd4_list_rec_dir(purge_old); if (status == 0) vfs_fsync(rec_file, 0); - mnt_drop_write(rec_file->f_path.mnt); + mnt_drop_write_file(rec_file); out: if (status) printk("nfsd4: failed to purge old clients from recovery" diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index b7697d1ccd61..886649627c3d 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -27,7 +27,7 @@ #include /* copy_from_user(), copy_to_user() */ #include #include /* compat_ptr() */ -#include /* mnt_want_write_file(), mnt_drop_write() */ +#include /* mnt_want_write_file(), mnt_drop_write_file() */ #include #include #include "nilfs.h" @@ -154,7 +154,7 @@ static int nilfs_ioctl_setflags(struct inode *inode, struct file *filp, ret = nilfs_transaction_commit(inode->i_sb); out: mutex_unlock(&inode->i_mutex); - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return ret; } @@ -194,7 +194,7 @@ static int nilfs_ioctl_change_cpmode(struct inode *inode, struct file *filp, up_read(&inode->i_sb->s_umount); out: - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return ret; } @@ -225,7 +225,7 @@ nilfs_ioctl_delete_checkpoint(struct inode *inode, struct file *filp, else nilfs_transaction_commit(inode->i_sb); /* never fails */ out: - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return ret; } @@ -675,7 +675,7 @@ out_free: vfree(kbufs[n]); kfree(kbufs[4]); out: - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return ret; } @@ -721,7 +721,7 @@ static int nilfs_ioctl_resize(struct inode *inode, struct file *filp, ret = nilfs_resize_fs(inode->i_sb, newsize); out_drop_write: - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); out: return ret; } diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c index 892ace253f97..a6fda3c188aa 100644 --- a/fs/ocfs2/ioctl.c +++ b/fs/ocfs2/ioctl.c @@ -911,7 +911,7 @@ long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) return status; status = ocfs2_set_inode_attr(inode, flags, OCFS2_FL_MODIFIABLE); - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return status; case OCFS2_IOC_RESVSP: case OCFS2_IOC_RESVSP64: diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 1d3bf83f8b85..b1e3fce72ea4 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -1145,7 +1145,7 @@ out: kfree(context); - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); return status; } diff --git a/fs/open.c b/fs/open.c index 22c41b543f2d..4ef8d868a448 100644 --- a/fs/open.c +++ b/fs/open.c @@ -608,7 +608,7 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group) dentry = file->f_path.dentry; audit_inode(NULL, dentry); error = chown_common(&file->f_path, user, group); - mnt_drop_write(file->f_path.mnt); + mnt_drop_write_file(file); out_fput: fput(file); out: diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c index 0b94d7b2b11f..950e3d1b5c9e 100644 --- a/fs/reiserfs/ioctl.c +++ b/fs/reiserfs/ioctl.c @@ -96,7 +96,7 @@ long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); setflags_out: - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); break; } case REISERFS_IOC_GETVERSION: @@ -117,7 +117,7 @@ setflags_out: inode->i_ctime = CURRENT_TIME_SEC; mark_inode_dirty(inode); setversion_out: - mnt_drop_write(filp->f_path.mnt); + mnt_drop_write_file(filp); break; default: err = -ENOTTY; diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c index e52c84598feb..1a7e2d8bdbe9 100644 --- a/fs/ubifs/ioctl.c +++ b/fs/ubifs/ioctl.c @@ -178,7 +178,7 @@ long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return err; dbg_gen("set flags: %#x, i_flags %#x", flags, inode->i_flags); err = setflags(inode, flags); - mnt_drop_write(file->f_path.mnt); + mnt_drop_write_file(file); return err; } diff --git a/fs/xattr.c b/fs/xattr.c index 67583de8218c..82f43376c7cd 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -397,7 +397,7 @@ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name, error = mnt_want_write_file(f); if (!error) { error = setxattr(dentry, name, value, size, flags); - mnt_drop_write(f->f_path.mnt); + mnt_drop_write_file(f); } fput(f); return error; @@ -624,7 +624,7 @@ SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) error = mnt_want_write_file(f); if (!error) { error = removexattr(dentry, name); - mnt_drop_write(f->f_path.mnt); + mnt_drop_write_file(f); } fput(f); return error; diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index b436e17c753e..76f3ca5cfc36 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -566,7 +566,7 @@ xfs_attrmulti_by_handle( dentry->d_inode, attr_name, ops[i].am_attrvalue, ops[i].am_length, ops[i].am_flags); - mnt_drop_write(parfilp->f_path.mnt); + mnt_drop_write_file(parfilp); break; case ATTR_OP_REMOVE: ops[i].am_error = mnt_want_write_file(parfilp); @@ -575,7 +575,7 @@ xfs_attrmulti_by_handle( ops[i].am_error = xfs_attrmulti_attr_remove( dentry->d_inode, attr_name, ops[i].am_flags); - mnt_drop_write(parfilp->f_path.mnt); + mnt_drop_write_file(parfilp); break; default: ops[i].am_error = EINVAL; diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index dd4ba1d4c582..f9ccb7b7c043 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -461,7 +461,7 @@ xfs_compat_attrmulti_by_handle( dentry->d_inode, attr_name, compat_ptr(ops[i].am_attrvalue), ops[i].am_length, ops[i].am_flags); - mnt_drop_write(parfilp->f_path.mnt); + mnt_drop_write_file(parfilp); break; case ATTR_OP_REMOVE: ops[i].am_error = mnt_want_write_file(parfilp); @@ -470,7 +470,7 @@ xfs_compat_attrmulti_by_handle( ops[i].am_error = xfs_attrmulti_attr_remove( dentry->d_inode, attr_name, ops[i].am_flags); - mnt_drop_write(parfilp->f_path.mnt); + mnt_drop_write_file(parfilp); break; default: ops[i].am_error = EINVAL; diff --git a/include/linux/mount.h b/include/linux/mount.h index 65c1bb013836..00f5c4f2160b 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -94,6 +94,7 @@ extern int mnt_want_write(struct vfsmount *mnt); extern int mnt_want_write_file(struct file *file); extern int mnt_clone_write(struct vfsmount *mnt); extern void mnt_drop_write(struct vfsmount *mnt); +extern void mnt_drop_write_file(struct file *file); extern void mntput(struct vfsmount *mnt); extern struct vfsmount *mntget(struct vfsmount *mnt); extern void mnt_pin(struct vfsmount *mnt); -- cgit v1.2.3 From 4692cf58aa7b81f721c1653d48db99ea41421d58 Mon Sep 17 00:00:00 2001 From: Jan Schmidt Date: Fri, 2 Dec 2011 14:56:41 +0100 Subject: Btrfs: new backref walking code The old backref iteration code could only safely be used on commit roots. Besides this limitation, it had bugs in finding the roots for these references. This commit replaces large parts of it by btrfs_find_all_roots() which a) really finds all roots and the correct roots, b) works correctly under heavy file system load, c) considers delayed refs. Signed-off-by: Jan Schmidt --- fs/btrfs/backref.c | 354 +++++++++++++++-------------------------------------- fs/btrfs/ioctl.c | 8 +- fs/btrfs/scrub.c | 7 +- 3 files changed, 107 insertions(+), 262 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 03c30a1836f4..b9a843226de8 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -23,18 +23,6 @@ #include "transaction.h" #include "delayed-ref.h" -struct __data_ref { - struct list_head list; - u64 inum; - u64 root; - u64 extent_data_item_offset; -}; - -struct __shared_ref { - struct list_head list; - u64 disk_byte; -}; - /* * this structure records all encountered refs on the way up to the root */ @@ -964,8 +952,11 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical, btrfs_item_key_to_cpu(path->nodes[0], found_key, path->slots[0]); if (found_key->type != BTRFS_EXTENT_ITEM_KEY || found_key->objectid > logical || - found_key->objectid + found_key->offset <= logical) + found_key->objectid + found_key->offset <= logical) { + pr_debug("logical %llu is not within any extent\n", + (unsigned long long)logical); return -ENOENT; + } eb = path->nodes[0]; item_size = btrfs_item_size_nr(eb, path->slots[0]); @@ -974,6 +965,13 @@ int extent_from_logical(struct btrfs_fs_info *fs_info, u64 logical, ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item); flags = btrfs_extent_flags(eb, ei); + pr_debug("logical %llu is at position %llu within the extent (%llu " + "EXTENT_ITEM %llu) flags %#llx size %u\n", + (unsigned long long)logical, + (unsigned long long)(logical - found_key->objectid), + (unsigned long long)found_key->objectid, + (unsigned long long)found_key->offset, + (unsigned long long)flags, item_size); if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) return BTRFS_EXTENT_FLAG_TREE_BLOCK; if (flags & BTRFS_EXTENT_FLAG_DATA) @@ -1070,128 +1068,11 @@ int tree_backref_for_extent(unsigned long *ptr, struct extent_buffer *eb, return 0; } -static int __data_list_add(struct list_head *head, u64 inum, - u64 extent_data_item_offset, u64 root) -{ - struct __data_ref *ref; - - ref = kmalloc(sizeof(*ref), GFP_NOFS); - if (!ref) - return -ENOMEM; - - ref->inum = inum; - ref->extent_data_item_offset = extent_data_item_offset; - ref->root = root; - list_add_tail(&ref->list, head); - - return 0; -} - -static int __data_list_add_eb(struct list_head *head, struct extent_buffer *eb, - struct btrfs_extent_data_ref *dref) -{ - return __data_list_add(head, btrfs_extent_data_ref_objectid(eb, dref), - btrfs_extent_data_ref_offset(eb, dref), - btrfs_extent_data_ref_root(eb, dref)); -} - -static int __shared_list_add(struct list_head *head, u64 disk_byte) -{ - struct __shared_ref *ref; - - ref = kmalloc(sizeof(*ref), GFP_NOFS); - if (!ref) - return -ENOMEM; - - ref->disk_byte = disk_byte; - list_add_tail(&ref->list, head); - - return 0; -} - -static int __iter_shared_inline_ref_inodes(struct btrfs_fs_info *fs_info, - u64 logical, u64 inum, - u64 extent_data_item_offset, - u64 extent_offset, - struct btrfs_path *path, - struct list_head *data_refs, - iterate_extent_inodes_t *iterate, - void *ctx) -{ - u64 ref_root; - u32 item_size; - struct btrfs_key key; - struct extent_buffer *eb; - struct btrfs_extent_item *ei; - struct btrfs_extent_inline_ref *eiref; - struct __data_ref *ref; - int ret; - int type; - int last; - unsigned long ptr = 0; - - WARN_ON(!list_empty(data_refs)); - ret = extent_from_logical(fs_info, logical, path, &key); - if (ret & BTRFS_EXTENT_FLAG_DATA) - ret = -EIO; - if (ret < 0) - goto out; - - eb = path->nodes[0]; - ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item); - item_size = btrfs_item_size_nr(eb, path->slots[0]); - - ret = 0; - ref_root = 0; - /* - * as done in iterate_extent_inodes, we first build a list of refs to - * iterate, then free the path and then iterate them to avoid deadlocks. - */ - do { - last = __get_extent_inline_ref(&ptr, eb, ei, item_size, - &eiref, &type); - if (last < 0) { - ret = last; - goto out; - } - if (type == BTRFS_TREE_BLOCK_REF_KEY || - type == BTRFS_SHARED_BLOCK_REF_KEY) { - ref_root = btrfs_extent_inline_ref_offset(eb, eiref); - ret = __data_list_add(data_refs, inum, - extent_data_item_offset, - ref_root); - } - } while (!ret && !last); - - btrfs_release_path(path); - - if (ref_root == 0) { - printk(KERN_ERR "btrfs: failed to find tree block ref " - "for shared data backref %llu\n", logical); - WARN_ON(1); - ret = -EIO; - } - -out: - while (!list_empty(data_refs)) { - ref = list_first_entry(data_refs, struct __data_ref, list); - list_del(&ref->list); - if (!ret) - ret = iterate(ref->inum, extent_offset + - ref->extent_data_item_offset, - ref->root, ctx); - kfree(ref); - } - - return ret; -} - -static int __iter_shared_inline_ref(struct btrfs_fs_info *fs_info, - u64 logical, u64 orig_extent_item_objectid, - u64 extent_offset, struct btrfs_path *path, - struct list_head *data_refs, - iterate_extent_inodes_t *iterate, - void *ctx) +static int iterate_leaf_refs(struct btrfs_fs_info *fs_info, + struct btrfs_path *path, u64 logical, + u64 orig_extent_item_objectid, + u64 extent_item_pos, u64 root, + iterate_extent_inodes_t *iterate, void *ctx) { u64 disk_byte; struct btrfs_key key; @@ -1199,8 +1080,10 @@ static int __iter_shared_inline_ref(struct btrfs_fs_info *fs_info, struct extent_buffer *eb; int slot; int nritems; - int ret; - int found = 0; + int ret = 0; + int extent_type; + u64 data_offset; + u64 data_len; eb = read_tree_block(fs_info->tree_root, logical, fs_info->tree_root->leafsize, 0); @@ -1218,149 +1101,99 @@ static int __iter_shared_inline_ref(struct btrfs_fs_info *fs_info, if (key.type != BTRFS_EXTENT_DATA_KEY) continue; fi = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item); - if (!fi) { - free_extent_buffer(eb); - return -EIO; - } + extent_type = btrfs_file_extent_type(eb, fi); + if (extent_type == BTRFS_FILE_EXTENT_INLINE) + continue; + /* don't skip BTRFS_FILE_EXTENT_PREALLOC, we can handle that */ disk_byte = btrfs_file_extent_disk_bytenr(eb, fi); - if (disk_byte != orig_extent_item_objectid) { - if (found) - break; - else - continue; - } - ++found; - ret = __iter_shared_inline_ref_inodes(fs_info, logical, - key.objectid, - key.offset, - extent_offset, path, - data_refs, - iterate, ctx); - if (ret) - break; - } + if (disk_byte != orig_extent_item_objectid) + continue; - if (!found) { - printk(KERN_ERR "btrfs: failed to follow shared data backref " - "to parent %llu\n", logical); - WARN_ON(1); - ret = -EIO; + data_offset = btrfs_file_extent_offset(eb, fi); + data_len = btrfs_file_extent_num_bytes(eb, fi); + + if (extent_item_pos < data_offset || + extent_item_pos >= data_offset + data_len) + continue; + + pr_debug("ref for %llu resolved, key (%llu EXTEND_DATA %llu), " + "root %llu\n", orig_extent_item_objectid, + key.objectid, key.offset, root); + ret = iterate(key.objectid, + key.offset + (extent_item_pos - data_offset), + root, ctx); + if (ret) { + pr_debug("stopping iteration because ret=%d\n", ret); + break; + } } free_extent_buffer(eb); + return ret; } /* * calls iterate() for every inode that references the extent identified by - * the given parameters. will use the path given as a parameter and return it - * released. + * the given parameters. * when the iterator function returns a non-zero value, iteration stops. + * path is guaranteed to be in released state when iterate() is called. */ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, struct btrfs_path *path, - u64 extent_item_objectid, - u64 extent_offset, + u64 extent_item_objectid, u64 extent_item_pos, iterate_extent_inodes_t *iterate, void *ctx) { - unsigned long ptr = 0; - int last; int ret; - int type; - u64 logical; - u32 item_size; - struct btrfs_extent_inline_ref *eiref; - struct btrfs_extent_data_ref *dref; - struct extent_buffer *eb; - struct btrfs_extent_item *ei; - struct btrfs_key key; struct list_head data_refs = LIST_HEAD_INIT(data_refs); struct list_head shared_refs = LIST_HEAD_INIT(shared_refs); - struct __data_ref *ref_d; - struct __shared_ref *ref_s; + struct btrfs_trans_handle *trans; + struct ulist *refs; + struct ulist *roots; + struct ulist_node *ref_node = NULL; + struct ulist_node *root_node = NULL; + struct seq_list seq_elem; + struct btrfs_delayed_ref_root *delayed_refs; - eb = path->nodes[0]; - ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item); - item_size = btrfs_item_size_nr(eb, path->slots[0]); - - /* first we iterate the inline refs, ... */ - do { - last = __get_extent_inline_ref(&ptr, eb, ei, item_size, - &eiref, &type); - if (last == -ENOENT) { - ret = 0; - break; - } - if (last < 0) { - ret = last; - break; - } + trans = btrfs_join_transaction(fs_info->extent_root); + if (IS_ERR(trans)) + return PTR_ERR(trans); - if (type == BTRFS_EXTENT_DATA_REF_KEY) { - dref = (struct btrfs_extent_data_ref *)(&eiref->offset); - ret = __data_list_add_eb(&data_refs, eb, dref); - } else if (type == BTRFS_SHARED_DATA_REF_KEY) { - logical = btrfs_extent_inline_ref_offset(eb, eiref); - ret = __shared_list_add(&shared_refs, logical); - } - } while (!ret && !last); + pr_debug("resolving all inodes for extent %llu\n", + extent_item_objectid); - /* ... then we proceed to in-tree references and ... */ - while (!ret) { - ++path->slots[0]; - if (path->slots[0] > btrfs_header_nritems(eb)) { - ret = btrfs_next_leaf(fs_info->extent_root, path); - if (ret) { - if (ret == 1) - ret = 0; /* we're done */ - break; - } - eb = path->nodes[0]; - } - btrfs_item_key_to_cpu(eb, &key, path->slots[0]); - if (key.objectid != extent_item_objectid) - break; - if (key.type == BTRFS_EXTENT_DATA_REF_KEY) { - dref = btrfs_item_ptr(eb, path->slots[0], - struct btrfs_extent_data_ref); - ret = __data_list_add_eb(&data_refs, eb, dref); - } else if (key.type == BTRFS_SHARED_DATA_REF_KEY) { - ret = __shared_list_add(&shared_refs, key.offset); - } - } + delayed_refs = &trans->transaction->delayed_refs; + spin_lock(&delayed_refs->lock); + btrfs_get_delayed_seq(delayed_refs, &seq_elem); + spin_unlock(&delayed_refs->lock); - btrfs_release_path(path); + ret = btrfs_find_all_leafs(trans, fs_info, extent_item_objectid, + extent_item_pos, seq_elem.seq, + &refs); - /* - * ... only at the very end we can process the refs we found. this is - * because the iterator function we call is allowed to make tree lookups - * and we have to avoid deadlocks. additionally, we need more tree - * lookups ourselves for shared data refs. - */ - while (!list_empty(&data_refs)) { - ref_d = list_first_entry(&data_refs, struct __data_ref, list); - list_del(&ref_d->list); - if (!ret) - ret = iterate(ref_d->inum, extent_offset + - ref_d->extent_data_item_offset, - ref_d->root, ctx); - kfree(ref_d); - } + if (ret) + goto out; - while (!list_empty(&shared_refs)) { - ref_s = list_first_entry(&shared_refs, struct __shared_ref, - list); - list_del(&ref_s->list); - if (!ret) - ret = __iter_shared_inline_ref(fs_info, - ref_s->disk_byte, - extent_item_objectid, - extent_offset, path, - &data_refs, - iterate, ctx); - kfree(ref_s); + while (!ret && (ref_node = ulist_next(refs, ref_node))) { + ret = btrfs_find_all_roots(trans, fs_info, ref_node->val, -1, + seq_elem.seq, &roots); + if (ret) + break; + while (!ret && (root_node = ulist_next(roots, root_node))) { + pr_debug("root %llu references leaf %llu\n", + root_node->val, ref_node->val); + ret = iterate_leaf_refs(fs_info, path, ref_node->val, + extent_item_objectid, + extent_item_pos, root_node->val, + iterate, ctx); + } } + ulist_free(refs); + ulist_free(roots); +out: + btrfs_put_delayed_seq(delayed_refs, &seq_elem); + btrfs_end_transaction(trans, fs_info->extent_root); return ret; } @@ -1369,19 +1202,20 @@ int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info, iterate_extent_inodes_t *iterate, void *ctx) { int ret; - u64 offset; + u64 extent_item_pos; struct btrfs_key found_key; ret = extent_from_logical(fs_info, logical, path, &found_key); + btrfs_release_path(path); if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK) ret = -EINVAL; if (ret < 0) return ret; - offset = logical - found_key.objectid; + extent_item_pos = logical - found_key.objectid; ret = iterate_extent_inodes(fs_info, path, found_key.objectid, - offset, iterate, ctx); + extent_item_pos, iterate, ctx); return ret; } @@ -1426,6 +1260,10 @@ static int iterate_irefs(u64 inum, struct btrfs_root *fs_root, for (cur = 0; cur < btrfs_item_size(eb, item); cur += len) { name_len = btrfs_inode_ref_name_len(eb, iref); /* path must be released before calling iterate()! */ + pr_debug("following ref at offset %u for inode %llu in " + "tree %llu\n", cur, + (unsigned long long)found_key.objectid, + (unsigned long long)fs_root->objectid); ret = iterate(parent, iref, eb, ctx); if (ret) { free_extent_buffer(eb); @@ -1466,10 +1304,14 @@ static int inode_to_path(u64 inum, struct btrfs_inode_ref *iref, return PTR_ERR(fspath); if (fspath > fspath_min) { + pr_debug("path resolved: %s\n", fspath); ipath->fspath->val[i] = (u64)(unsigned long)fspath; ++ipath->fspath->elem_cnt; ipath->fspath->bytes_left = fspath - fspath_min; } else { + pr_debug("missed path, not enough space. missing bytes: %lu, " + "constructed so far: %s\n", + (unsigned long)(fspath_min - fspath), fspath_min); ++ipath->fspath->elem_missed; ipath->fspath->bytes_missing += fspath_min - fspath; ipath->fspath->bytes_left = 0; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index c48f2e931ea0..9b0526872b7b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2976,7 +2976,7 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root, { int ret = 0; int size; - u64 extent_offset; + u64 extent_item_pos; struct btrfs_ioctl_logical_ino_args *loi; struct btrfs_data_container *inodes = NULL; struct btrfs_path *path = NULL; @@ -3007,15 +3007,17 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_root *root, } ret = extent_from_logical(root->fs_info, loi->logical, path, &key); + btrfs_release_path(path); if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK) ret = -ENOENT; if (ret < 0) goto out; - extent_offset = loi->logical - key.objectid; + extent_item_pos = loi->logical - key.objectid; ret = iterate_extent_inodes(root->fs_info, path, key.objectid, - extent_offset, build_ino_list, inodes); + extent_item_pos, build_ino_list, + inodes); if (ret < 0) goto out; diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index c27bcb67f330..b5edff25a53f 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -309,7 +309,7 @@ static void scrub_print_warning(const char *errstr, struct scrub_bio *sbio, u8 ref_level; unsigned long ptr = 0; const int bufsize = 4096; - u64 extent_offset; + u64 extent_item_pos; path = btrfs_alloc_path(); @@ -329,12 +329,13 @@ static void scrub_print_warning(const char *errstr, struct scrub_bio *sbio, if (ret < 0) goto out; - extent_offset = swarn.logical - found_key.objectid; + extent_item_pos = swarn.logical - found_key.objectid; swarn.extent_item_size = found_key.offset; eb = path->nodes[0]; ei = btrfs_item_ptr(eb, path->slots[0], struct btrfs_extent_item); item_size = btrfs_item_size_nr(eb, path->slots[0]); + btrfs_release_path(path); if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK) { do { @@ -351,7 +352,7 @@ static void scrub_print_warning(const char *errstr, struct scrub_bio *sbio, } else { swarn.path = path; iterate_extent_inodes(fs_info, path, found_key.objectid, - extent_offset, + extent_item_pos, scrub_print_warning_inode, &swarn); } -- cgit v1.2.3 From 815745cf3e46681241ad8025602ffbf2a452d514 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 17 Nov 2011 15:40:49 -0500 Subject: btrfs: let ->s_fs_info point to fs_info, not root... the latter can be obtained from the former (by looking as ->tree_root) just as cheaply as we currently are doing the other way round. Signed-off-by: Al Viro --- fs/btrfs/ctree.h | 2 +- fs/btrfs/disk-io.c | 4 +-- fs/btrfs/export.c | 2 +- fs/btrfs/ioctl.c | 7 +++-- fs/btrfs/super.c | 75 +++++++++++++++++++++++++++--------------------------- 5 files changed, 45 insertions(+), 45 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 67385033323d..dbb999a38272 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2196,7 +2196,7 @@ static inline u32 btrfs_file_extent_inline_item_len(struct extent_buffer *eb, return btrfs_item_size(eb, e) - offset; } -static inline struct btrfs_root *btrfs_sb(struct super_block *sb) +static inline struct btrfs_fs_info *btrfs_sb(struct super_block *sb) { return sb->s_fs_info; } diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b6d11eb4e430..f7d8b9ba519b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1894,8 +1894,8 @@ int open_ctree(struct super_block *sb, struct btrfs_key location; struct buffer_head *bh; struct btrfs_super_block *disk_super; - struct btrfs_root *tree_root = btrfs_sb(sb); - struct btrfs_fs_info *fs_info = tree_root->fs_info; + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + struct btrfs_root *tree_root = fs_info->tree_root; struct btrfs_root *extent_root; struct btrfs_root *csum_root; struct btrfs_root *chunk_root; diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c index 1b8dc33778f9..5f77166fd01c 100644 --- a/fs/btrfs/export.c +++ b/fs/btrfs/export.c @@ -67,7 +67,7 @@ static struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, u64 root_objectid, u32 generation, int check_generation) { - struct btrfs_fs_info *fs_info = btrfs_sb(sb)->fs_info; + struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_root *root; struct inode *inode; struct btrfs_key key; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 5441ff1480fd..0c55f8f38091 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -276,14 +276,13 @@ static int btrfs_ioctl_getversion(struct file *file, int __user *arg) static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) { - struct btrfs_root *root = fdentry(file)->d_sb->s_fs_info; - struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_fs_info *fs_info = btrfs_sb(fdentry(file)->d_sb); struct btrfs_device *device; struct request_queue *q; struct fstrim_range range; u64 minlen = ULLONG_MAX; u64 num_devices = 0; - u64 total_bytes = btrfs_super_total_bytes(root->fs_info->super_copy); + u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy); int ret; if (!capable(CAP_SYS_ADMIN)) @@ -312,7 +311,7 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg) range.len = min(range.len, total_bytes - range.start); range.minlen = max(range.minlen, minlen); - ret = btrfs_trim_fs(root, &range); + ret = btrfs_trim_fs(fs_info->tree_root, &range); if (ret < 0) return ret; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 15c8ae571e40..305adf6dc09a 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -147,7 +147,7 @@ void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function, static void btrfs_put_super(struct super_block *sb) { - (void)close_ctree(btrfs_sb(sb)); + (void)close_ctree(btrfs_sb(sb)->tree_root); /* FIXME: need to fix VFS to return error? */ /* AV: return it _where_? ->put_super() can be triggered by any number * of async events, up to and including delivery of SIGKILL to the @@ -500,7 +500,8 @@ out: static struct dentry *get_default_root(struct super_block *sb, u64 subvol_objectid) { - struct btrfs_root *root = sb->s_fs_info; + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + struct btrfs_root *root = fs_info->tree_root; struct btrfs_root *new_root; struct btrfs_dir_item *di; struct btrfs_path *path; @@ -530,7 +531,7 @@ static struct dentry *get_default_root(struct super_block *sb, * will mount by default if we haven't been given a specific subvolume * to mount. */ - dir_id = btrfs_super_root_dir(root->fs_info->super_copy); + dir_id = btrfs_super_root_dir(fs_info->super_copy); di = btrfs_lookup_dir_item(NULL, root, path, dir_id, "default", 7, 0); if (IS_ERR(di)) { btrfs_free_path(path); @@ -544,7 +545,7 @@ static struct dentry *get_default_root(struct super_block *sb, */ btrfs_free_path(path); dir_id = BTRFS_FIRST_FREE_OBJECTID; - new_root = root->fs_info->fs_root; + new_root = fs_info->fs_root; goto setup_root; } @@ -552,7 +553,7 @@ static struct dentry *get_default_root(struct super_block *sb, btrfs_free_path(path); find_root: - new_root = btrfs_read_fs_root_no_name(root->fs_info, &location); + new_root = btrfs_read_fs_root_no_name(fs_info, &location); if (IS_ERR(new_root)) return ERR_CAST(new_root); @@ -588,8 +589,7 @@ static int btrfs_fill_super(struct super_block *sb, { struct inode *inode; struct dentry *root_dentry; - struct btrfs_root *tree_root = sb->s_fs_info; - struct btrfs_fs_info *fs_info = tree_root->fs_info; + struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_key key; int err; @@ -634,20 +634,21 @@ static int btrfs_fill_super(struct super_block *sb, return 0; fail_close: - close_ctree(tree_root); + close_ctree(fs_info->tree_root); return err; } int btrfs_sync_fs(struct super_block *sb, int wait) { struct btrfs_trans_handle *trans; - struct btrfs_root *root = btrfs_sb(sb); + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + struct btrfs_root *root = fs_info->tree_root; int ret; trace_btrfs_sync_fs(wait); if (!wait) { - filemap_flush(root->fs_info->btree_inode->i_mapping); + filemap_flush(fs_info->btree_inode->i_mapping); return 0; } @@ -663,8 +664,8 @@ int btrfs_sync_fs(struct super_block *sb, int wait) static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) { - struct btrfs_root *root = btrfs_sb(dentry->d_sb); - struct btrfs_fs_info *info = root->fs_info; + struct btrfs_fs_info *info = btrfs_sb(dentry->d_sb); + struct btrfs_root *root = info->tree_root; char *compress_type; if (btrfs_test_opt(root, DEGRADED)) @@ -727,10 +728,10 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) static int btrfs_test_super(struct super_block *s, void *data) { - struct btrfs_root *test_root = data; - struct btrfs_root *root = btrfs_sb(s); + struct btrfs_fs_info *p = data; + struct btrfs_fs_info *fs_info = btrfs_sb(s); - return root->fs_info->fs_devices == test_root->fs_info->fs_devices; + return fs_info->fs_devices == p->fs_devices; } static int btrfs_set_super(struct super_block *s, void *data) @@ -922,8 +923,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, } bdev = fs_devices->latest_bdev; - s = sget(fs_type, btrfs_test_super, btrfs_set_super, - fs_info->tree_root); + s = sget(fs_type, btrfs_test_super, btrfs_set_super, fs_info); if (IS_ERR(s)) { error = PTR_ERR(s); goto error_close_devices; @@ -939,7 +939,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags, s->s_flags = flags | MS_NOSEC; strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id)); - btrfs_sb(s)->fs_info->bdev_holder = fs_type; + btrfs_sb(s)->bdev_holder = fs_type; error = btrfs_fill_super(s, fs_devices, data, flags & MS_SILENT ? 1 : 0); } @@ -959,7 +959,8 @@ error_fs_info: static int btrfs_remount(struct super_block *sb, int *flags, char *data) { - struct btrfs_root *root = btrfs_sb(sb); + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + struct btrfs_root *root = fs_info->tree_root; int ret; ret = btrfs_parse_options(root, data); @@ -975,13 +976,13 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) ret = btrfs_commit_super(root); WARN_ON(ret); } else { - if (root->fs_info->fs_devices->rw_devices == 0) + if (fs_info->fs_devices->rw_devices == 0) return -EACCES; - if (btrfs_super_log_root(root->fs_info->super_copy) != 0) + if (btrfs_super_log_root(fs_info->super_copy) != 0) return -EINVAL; - ret = btrfs_cleanup_fs_roots(root->fs_info); + ret = btrfs_cleanup_fs_roots(fs_info); WARN_ON(ret); /* recover relocation */ @@ -1150,18 +1151,18 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) { - struct btrfs_root *root = btrfs_sb(dentry->d_sb); - struct btrfs_super_block *disk_super = root->fs_info->super_copy; - struct list_head *head = &root->fs_info->space_info; + struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb); + struct btrfs_super_block *disk_super = fs_info->super_copy; + struct list_head *head = &fs_info->space_info; struct btrfs_space_info *found; u64 total_used = 0; u64 total_free_data = 0; int bits = dentry->d_sb->s_blocksize_bits; - __be32 *fsid = (__be32 *)root->fs_info->fsid; + __be32 *fsid = (__be32 *)fs_info->fsid; int ret; /* holding chunk_muext to avoid allocating new chunks */ - mutex_lock(&root->fs_info->chunk_mutex); + mutex_lock(&fs_info->chunk_mutex); rcu_read_lock(); list_for_each_entry_rcu(found, head, list) { if (found->flags & BTRFS_BLOCK_GROUP_DATA) { @@ -1180,14 +1181,14 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bsize = dentry->d_sb->s_blocksize; buf->f_type = BTRFS_SUPER_MAGIC; buf->f_bavail = total_free_data; - ret = btrfs_calc_avail_data_space(root, &total_free_data); + ret = btrfs_calc_avail_data_space(fs_info->tree_root, &total_free_data); if (ret) { - mutex_unlock(&root->fs_info->chunk_mutex); + mutex_unlock(&fs_info->chunk_mutex); return ret; } buf->f_bavail += total_free_data; buf->f_bavail = buf->f_bavail >> bits; - mutex_unlock(&root->fs_info->chunk_mutex); + mutex_unlock(&fs_info->chunk_mutex); /* We treat it as constant endianness (it doesn't matter _which_) because we want the fsid to come out the same whether mounted @@ -1203,7 +1204,7 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) static void btrfs_kill_super(struct super_block *sb) { - struct btrfs_fs_info *fs_info = btrfs_sb(sb)->fs_info; + struct btrfs_fs_info *fs_info = btrfs_sb(sb); kill_anon_super(sb); free_fs_info(fs_info); } @@ -1246,17 +1247,17 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd, static int btrfs_freeze(struct super_block *sb) { - struct btrfs_root *root = btrfs_sb(sb); - mutex_lock(&root->fs_info->transaction_kthread_mutex); - mutex_lock(&root->fs_info->cleaner_mutex); + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + mutex_lock(&fs_info->transaction_kthread_mutex); + mutex_lock(&fs_info->cleaner_mutex); return 0; } static int btrfs_unfreeze(struct super_block *sb) { - struct btrfs_root *root = btrfs_sb(sb); - mutex_unlock(&root->fs_info->cleaner_mutex); - mutex_unlock(&root->fs_info->transaction_kthread_mutex); + struct btrfs_fs_info *fs_info = btrfs_sb(sb); + mutex_unlock(&fs_info->cleaner_mutex); + mutex_unlock(&fs_info->transaction_kthread_mutex); return 0; } -- cgit v1.2.3 From f062abf089ff705e09bbaa6fa1e2fd7688a0f2ea Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Thu, 29 Dec 2011 13:36:45 +0800 Subject: Btrfs: remove BUG_ON()s in btrfs_ioctl_setflags() We can recover from errors and return -errno to user space. Signed-off-by: Li Zefan --- fs/btrfs/ioctl.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index c04f02c7d5bb..9619fb03a5d6 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -176,6 +176,8 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) struct btrfs_trans_handle *trans; unsigned int flags, oldflags; int ret; + u64 ip_oldflags; + unsigned int i_oldflags; if (btrfs_root_readonly(root)) return -EROFS; @@ -192,6 +194,9 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) mutex_lock(&inode->i_mutex); + ip_oldflags = ip->flags; + i_oldflags = inode->i_flags; + flags = btrfs_mask_flags(inode->i_mode, flags); oldflags = btrfs_flags_to_ioctl(ip->flags); if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) { @@ -250,18 +255,23 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) } trans = btrfs_join_transaction(root); - BUG_ON(IS_ERR(trans)); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + goto out_drop; + } btrfs_update_iflags(inode); inode->i_ctime = CURRENT_TIME; ret = btrfs_update_inode(trans, root, inode); - BUG_ON(ret); btrfs_end_transaction(trans, root); + out_drop: + if (ret) { + ip->flags = ip_oldflags; + inode->i_flags = i_oldflags; + } mnt_drop_write(file->f_path.mnt); - - ret = 0; out_unlock: mutex_unlock(&inode->i_mutex); return ret; -- cgit v1.2.3 From 4da6f1a332f6c16b6594c7892f13c31459b9b1c8 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Thu, 29 Dec 2011 13:39:50 +0800 Subject: Btrfs: reserve metadata space in btrfs_ioctl_setflags() Check and reserve space for btrfs_update_inode(). Signed-off-by: Li Zefan --- fs/btrfs/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 9619fb03a5d6..fe8a60c865eb 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -254,7 +254,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg) ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS); } - trans = btrfs_join_transaction(root); + trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { ret = PTR_ERR(trans); goto out_drop; -- cgit v1.2.3 From c9e9f97bdfb64d06e9520f8e4f37674ac21cc9bc Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 16 Jan 2012 22:04:47 +0200 Subject: Btrfs: add basic restriper infrastructure Add basic restriper infrastructure: extended balancing ioctl and all related ioctl data structures, add data structure for tracking restriper's state to fs_info, etc. The semantics of the old balancing ioctl are fully preserved. Explicitly disallow any volume operations when balance is in progress. Signed-off-by: Ilya Dryomov --- fs/btrfs/ctree.h | 6 +++ fs/btrfs/disk-io.c | 4 ++ fs/btrfs/ioctl.c | 135 ++++++++++++++++++++++++++++++++++++++++++++++------- fs/btrfs/ioctl.h | 43 +++++++++++++++++ fs/btrfs/volumes.c | 120 +++++++++++++++++++++++++++++++++++++---------- fs/btrfs/volumes.h | 14 +++++- 6 files changed, 281 insertions(+), 41 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3f8f11e18b53..c4d98c8df5c5 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -934,6 +934,7 @@ struct btrfs_block_group_cache { struct reloc_control; struct btrfs_device; struct btrfs_fs_devices; +struct btrfs_balance_control; struct btrfs_delayed_root; struct btrfs_fs_info { u8 fsid[BTRFS_FSID_SIZE]; @@ -1159,6 +1160,11 @@ struct btrfs_fs_info { u64 avail_metadata_alloc_bits; u64 avail_system_alloc_bits; + /* restriper state */ + spinlock_t balance_lock; + struct mutex balance_mutex; + struct btrfs_balance_control *balance_ctl; + unsigned data_chunk_allocations; unsigned metadata_ratio; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index ce9d0fb3627d..190a1b24c902 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2002,6 +2002,10 @@ struct btrfs_root *open_ctree(struct super_block *sb, init_rwsem(&fs_info->scrub_super_lock); fs_info->scrub_workers_refcnt = 0; + spin_lock_init(&fs_info->balance_lock); + mutex_init(&fs_info->balance_mutex); + fs_info->balance_ctl = NULL; + sb->s_blocksize = 4096; sb->s_blocksize_bits = blksize_bits(4096); sb->s_bdi = &fs_info->bdi; diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index c04f02c7d5bb..d838d2cfb947 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1203,13 +1203,21 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, if (!capable(CAP_SYS_ADMIN)) return -EPERM; + mutex_lock(&root->fs_info->volume_mutex); + if (root->fs_info->balance_ctl) { + printk(KERN_INFO "btrfs: balance in progress\n"); + ret = -EINVAL; + goto out; + } + vol_args = memdup_user(arg, sizeof(*vol_args)); - if (IS_ERR(vol_args)) - return PTR_ERR(vol_args); + if (IS_ERR(vol_args)) { + ret = PTR_ERR(vol_args); + goto out; + } vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; - mutex_lock(&root->fs_info->volume_mutex); sizestr = vol_args->name; devstr = strchr(sizestr, ':'); if (devstr) { @@ -1226,7 +1234,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, printk(KERN_INFO "btrfs: resizer unable to find device %llu\n", (unsigned long long)devid); ret = -EINVAL; - goto out_unlock; + goto out_free; } if (!strcmp(sizestr, "max")) new_size = device->bdev->bd_inode->i_size; @@ -1241,7 +1249,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, new_size = memparse(sizestr, NULL); if (new_size == 0) { ret = -EINVAL; - goto out_unlock; + goto out_free; } } @@ -1250,7 +1258,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, if (mod < 0) { if (new_size > old_size) { ret = -EINVAL; - goto out_unlock; + goto out_free; } new_size = old_size - new_size; } else if (mod > 0) { @@ -1259,11 +1267,11 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, if (new_size < 256 * 1024 * 1024) { ret = -EINVAL; - goto out_unlock; + goto out_free; } if (new_size > device->bdev->bd_inode->i_size) { ret = -EFBIG; - goto out_unlock; + goto out_free; } do_div(new_size, root->sectorsize); @@ -1276,7 +1284,7 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { ret = PTR_ERR(trans); - goto out_unlock; + goto out_free; } ret = btrfs_grow_device(trans, device, new_size); btrfs_commit_transaction(trans, root); @@ -1284,9 +1292,10 @@ static noinline int btrfs_ioctl_resize(struct btrfs_root *root, ret = btrfs_shrink_device(device, new_size); } -out_unlock: - mutex_unlock(&root->fs_info->volume_mutex); +out_free: kfree(vol_args); +out: + mutex_unlock(&root->fs_info->volume_mutex); return ret; } @@ -2052,14 +2061,25 @@ static long btrfs_ioctl_add_dev(struct btrfs_root *root, void __user *arg) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + mutex_lock(&root->fs_info->volume_mutex); + if (root->fs_info->balance_ctl) { + printk(KERN_INFO "btrfs: balance in progress\n"); + ret = -EINVAL; + goto out; + } + vol_args = memdup_user(arg, sizeof(*vol_args)); - if (IS_ERR(vol_args)) - return PTR_ERR(vol_args); + if (IS_ERR(vol_args)) { + ret = PTR_ERR(vol_args); + goto out; + } vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; ret = btrfs_init_new_device(root, vol_args->name); kfree(vol_args); +out: + mutex_unlock(&root->fs_info->volume_mutex); return ret; } @@ -2074,14 +2094,25 @@ static long btrfs_ioctl_rm_dev(struct btrfs_root *root, void __user *arg) if (root->fs_info->sb->s_flags & MS_RDONLY) return -EROFS; + mutex_lock(&root->fs_info->volume_mutex); + if (root->fs_info->balance_ctl) { + printk(KERN_INFO "btrfs: balance in progress\n"); + ret = -EINVAL; + goto out; + } + vol_args = memdup_user(arg, sizeof(*vol_args)); - if (IS_ERR(vol_args)) - return PTR_ERR(vol_args); + if (IS_ERR(vol_args)) { + ret = PTR_ERR(vol_args); + goto out; + } vol_args->name[BTRFS_PATH_NAME_MAX] = '\0'; ret = btrfs_rm_device(root, vol_args->name); kfree(vol_args); +out: + mutex_unlock(&root->fs_info->volume_mutex); return ret; } @@ -3034,6 +3065,76 @@ out: return ret; } +void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, + struct btrfs_ioctl_balance_args *bargs) +{ + struct btrfs_balance_control *bctl = fs_info->balance_ctl; + + bargs->flags = bctl->flags; + + memcpy(&bargs->data, &bctl->data, sizeof(bargs->data)); + memcpy(&bargs->meta, &bctl->meta, sizeof(bargs->meta)); + memcpy(&bargs->sys, &bctl->sys, sizeof(bargs->sys)); +} + +static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_ioctl_balance_args *bargs; + struct btrfs_balance_control *bctl; + int ret; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (fs_info->sb->s_flags & MS_RDONLY) + return -EROFS; + + mutex_lock(&fs_info->volume_mutex); + mutex_lock(&fs_info->balance_mutex); + + if (arg) { + bargs = memdup_user(arg, sizeof(*bargs)); + if (IS_ERR(bargs)) { + ret = PTR_ERR(bargs); + goto out; + } + } else { + bargs = NULL; + } + + bctl = kzalloc(sizeof(*bctl), GFP_NOFS); + if (!bctl) { + ret = -ENOMEM; + goto out_bargs; + } + + bctl->fs_info = fs_info; + if (arg) { + memcpy(&bctl->data, &bargs->data, sizeof(bctl->data)); + memcpy(&bctl->meta, &bargs->meta, sizeof(bctl->meta)); + memcpy(&bctl->sys, &bargs->sys, sizeof(bctl->sys)); + + bctl->flags = bargs->flags; + } + + ret = btrfs_balance(bctl, bargs); + /* + * bctl is freed in __cancel_balance + */ + if (arg) { + if (copy_to_user(arg, bargs, sizeof(*bargs))) + ret = -EFAULT; + } + +out_bargs: + kfree(bargs); +out: + mutex_unlock(&fs_info->balance_mutex); + mutex_unlock(&fs_info->volume_mutex); + return ret; +} + long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -3078,7 +3179,7 @@ long btrfs_ioctl(struct file *file, unsigned int case BTRFS_IOC_DEV_INFO: return btrfs_ioctl_dev_info(root, argp); case BTRFS_IOC_BALANCE: - return btrfs_balance(root->fs_info->dev_root); + return btrfs_ioctl_balance(root, NULL); case BTRFS_IOC_CLONE: return btrfs_ioctl_clone(file, arg, 0, 0, 0); case BTRFS_IOC_CLONE_RANGE: @@ -3110,6 +3211,8 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_scrub_cancel(root, argp); case BTRFS_IOC_SCRUB_PROGRESS: return btrfs_ioctl_scrub_progress(root, argp); + case BTRFS_IOC_BALANCE_V2: + return btrfs_ioctl_balance(root, argp); } return -ENOTTY; diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index 252ae9915de8..c8b37d2c0d77 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -109,6 +109,47 @@ struct btrfs_ioctl_fs_info_args { __u64 reserved[124]; /* pad to 1k */ }; +/* + * this is packed, because it should be exactly the same as its disk + * byte order counterpart (struct btrfs_disk_balance_args) + */ +struct btrfs_balance_args { + __u64 profiles; + __u64 usage; + __u64 devid; + __u64 pstart; + __u64 pend; + __u64 vstart; + __u64 vend; + + __u64 target; + + __u64 flags; + + __u64 unused[8]; +} __attribute__ ((__packed__)); + +/* report balance progress to userspace */ +struct btrfs_balance_progress { + __u64 expected; /* estimated # of chunks that will be + * relocated to fulfill the request */ + __u64 considered; /* # of chunks we have considered so far */ + __u64 completed; /* # of chunks relocated so far */ +}; + +struct btrfs_ioctl_balance_args { + __u64 flags; /* in/out */ + __u64 state; /* out */ + + struct btrfs_balance_args data; /* in/out */ + struct btrfs_balance_args meta; /* in/out */ + struct btrfs_balance_args sys; /* in/out */ + + struct btrfs_balance_progress stat; /* out */ + + __u64 unused[72]; /* pad to 1k */ +}; + #define BTRFS_INO_LOOKUP_PATH_MAX 4080 struct btrfs_ioctl_ino_lookup_args { __u64 treeid; @@ -272,6 +313,8 @@ struct btrfs_ioctl_logical_ino_args { struct btrfs_ioctl_dev_info_args) #define BTRFS_IOC_FS_INFO _IOR(BTRFS_IOCTL_MAGIC, 31, \ struct btrfs_ioctl_fs_info_args) +#define BTRFS_IOC_BALANCE_V2 _IOWR(BTRFS_IOCTL_MAGIC, 32, \ + struct btrfs_ioctl_balance_args) #define BTRFS_IOC_INO_PATHS _IOWR(BTRFS_IOCTL_MAGIC, 35, \ struct btrfs_ioctl_ino_path_args) #define BTRFS_IOC_LOGICAL_INO _IOWR(BTRFS_IOCTL_MAGIC, 36, \ diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d5fdee56777f..9fc06e6bc51a 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1282,7 +1282,6 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) bool clear_super = false; mutex_lock(&uuid_mutex); - mutex_lock(&root->fs_info->volume_mutex); all_avail = root->fs_info->avail_data_alloc_bits | root->fs_info->avail_system_alloc_bits | @@ -1452,7 +1451,6 @@ error_close: if (bdev) blkdev_put(bdev, FMODE_READ | FMODE_EXCL); out: - mutex_unlock(&root->fs_info->volume_mutex); mutex_unlock(&uuid_mutex); return ret; error_undo: @@ -1629,7 +1627,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) } filemap_write_and_wait(bdev->bd_inode->i_mapping); - mutex_lock(&root->fs_info->volume_mutex); devices = &root->fs_info->fs_devices->devices; /* @@ -1757,8 +1754,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) ret = btrfs_relocate_sys_chunks(root); BUG_ON(ret); } -out: - mutex_unlock(&root->fs_info->volume_mutex); + return ret; error: blkdev_put(bdev, FMODE_EXCL); @@ -1766,7 +1762,7 @@ error: mutex_unlock(&uuid_mutex); up_write(&sb->s_umount); } - goto out; + return ret; } static noinline int btrfs_update_device(struct btrfs_trans_handle *trans, @@ -2077,6 +2073,35 @@ error: return ret; } +/* + * Should be called with both balance and volume mutexes held to + * serialize other volume operations (add_dev/rm_dev/resize) with + * restriper. Same goes for unset_balance_control. + */ +static void set_balance_control(struct btrfs_balance_control *bctl) +{ + struct btrfs_fs_info *fs_info = bctl->fs_info; + + BUG_ON(fs_info->balance_ctl); + + spin_lock(&fs_info->balance_lock); + fs_info->balance_ctl = bctl; + spin_unlock(&fs_info->balance_lock); +} + +static void unset_balance_control(struct btrfs_fs_info *fs_info) +{ + struct btrfs_balance_control *bctl = fs_info->balance_ctl; + + BUG_ON(!fs_info->balance_ctl); + + spin_lock(&fs_info->balance_lock); + fs_info->balance_ctl = NULL; + spin_unlock(&fs_info->balance_lock); + + kfree(bctl); +} + static u64 div_factor(u64 num, int factor) { if (factor == 10) @@ -2086,29 +2111,23 @@ static u64 div_factor(u64 num, int factor) return num; } -int btrfs_balance(struct btrfs_root *dev_root) +static int __btrfs_balance(struct btrfs_fs_info *fs_info) { - int ret; - struct list_head *devices = &dev_root->fs_info->fs_devices->devices; + struct btrfs_root *chunk_root = fs_info->chunk_root; + struct btrfs_root *dev_root = fs_info->dev_root; + struct list_head *devices; struct btrfs_device *device; u64 old_size; u64 size_to_free; struct btrfs_path *path; struct btrfs_key key; - struct btrfs_root *chunk_root = dev_root->fs_info->chunk_root; - struct btrfs_trans_handle *trans; struct btrfs_key found_key; - - if (dev_root->fs_info->sb->s_flags & MS_RDONLY) - return -EROFS; - - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - - mutex_lock(&dev_root->fs_info->volume_mutex); - dev_root = dev_root->fs_info->dev_root; + struct btrfs_trans_handle *trans; + int ret; + int enospc_errors = 0; /* step one make some room on all the devices */ + devices = &fs_info->fs_devices->devices; list_for_each_entry(device, devices, dev_list) { old_size = device->total_bytes; size_to_free = div_factor(old_size, 1); @@ -2151,12 +2170,14 @@ int btrfs_balance(struct btrfs_root *dev_root) * failed */ if (ret == 0) - break; + BUG(); /* FIXME break ? */ ret = btrfs_previous_item(chunk_root, path, 0, BTRFS_CHUNK_ITEM_KEY); - if (ret) + if (ret) { + ret = 0; break; + } btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]); @@ -2174,12 +2195,63 @@ int btrfs_balance(struct btrfs_root *dev_root) found_key.offset); if (ret && ret != -ENOSPC) goto error; + if (ret == -ENOSPC) + enospc_errors++; key.offset = found_key.offset - 1; } - ret = 0; + error: btrfs_free_path(path); - mutex_unlock(&dev_root->fs_info->volume_mutex); + if (enospc_errors) { + printk(KERN_INFO "btrfs: %d enospc errors during balance\n", + enospc_errors); + if (!ret) + ret = -ENOSPC; + } + + return ret; +} + +static void __cancel_balance(struct btrfs_fs_info *fs_info) +{ + unset_balance_control(fs_info); +} + +void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, + struct btrfs_ioctl_balance_args *bargs); + +/* + * Should be called with both balance and volume mutexes held + */ +int btrfs_balance(struct btrfs_balance_control *bctl, + struct btrfs_ioctl_balance_args *bargs) +{ + struct btrfs_fs_info *fs_info = bctl->fs_info; + int ret; + + if (btrfs_fs_closing(fs_info)) { + ret = -EINVAL; + goto out; + } + + set_balance_control(bctl); + + mutex_unlock(&fs_info->balance_mutex); + + ret = __btrfs_balance(fs_info); + + mutex_lock(&fs_info->balance_mutex); + + if (bargs) { + memset(bargs, 0, sizeof(*bargs)); + update_ioctl_balance_args(fs_info, bargs); + } + + __cancel_balance(fs_info); + + return ret; +out: + kfree(bctl); return ret; } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 78f2d4d4f37f..882582385283 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -186,6 +186,17 @@ struct map_lookup { #define map_lookup_size(n) (sizeof(struct map_lookup) + \ (sizeof(struct btrfs_bio_stripe) * (n))) +struct btrfs_balance_args; +struct btrfs_balance_control { + struct btrfs_fs_info *fs_info; + + struct btrfs_balance_args data; + struct btrfs_balance_args meta; + struct btrfs_balance_args sys; + + u64 flags; +}; + int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start, u64 end, u64 *length); @@ -228,7 +239,8 @@ struct btrfs_device *btrfs_find_device(struct btrfs_root *root, u64 devid, u8 *uuid, u8 *fsid); int btrfs_shrink_device(struct btrfs_device *device, u64 new_size); int btrfs_init_new_device(struct btrfs_root *root, char *path); -int btrfs_balance(struct btrfs_root *dev_root); +int btrfs_balance(struct btrfs_balance_control *bctl, + struct btrfs_ioctl_balance_args *bargs); int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset); int find_free_dev_extent(struct btrfs_trans_handle *trans, struct btrfs_device *device, u64 num_bytes, -- cgit v1.2.3 From f43ffb60fd94e98be02780944e182ade6653b916 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 16 Jan 2012 22:04:47 +0200 Subject: Btrfs: add basic infrastructure for selective balancing This allows to have a separate set of filters for each chunk type (data,meta,sys). The code however is generic and switch on chunk type is only done once. This commit also adds a type filter: it allows to balance for example meta and system chunks w/o touching data ones. Signed-off-by: Ilya Dryomov --- fs/btrfs/ioctl.c | 3 +++ fs/btrfs/volumes.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++++++++-- fs/btrfs/volumes.h | 11 ++++++++++ 3 files changed, 71 insertions(+), 2 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index d838d2cfb947..29b3a94933f0 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3116,6 +3116,9 @@ static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg) memcpy(&bctl->sys, &bargs->sys, sizeof(bctl->sys)); bctl->flags = bargs->flags; + } else { + /* balance everything - no filters */ + bctl->flags |= BTRFS_BALANCE_TYPE_MASK; } ret = btrfs_balance(bctl, bargs); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 9fc06e6bc51a..91bbf6e774c0 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2102,6 +2102,30 @@ static void unset_balance_control(struct btrfs_fs_info *fs_info) kfree(bctl); } +static int should_balance_chunk(struct btrfs_root *root, + struct extent_buffer *leaf, + struct btrfs_chunk *chunk, u64 chunk_offset) +{ + struct btrfs_balance_control *bctl = root->fs_info->balance_ctl; + struct btrfs_balance_args *bargs = NULL; + u64 chunk_type = btrfs_chunk_type(leaf, chunk); + + /* type filter */ + if (!((chunk_type & BTRFS_BLOCK_GROUP_TYPE_MASK) & + (bctl->flags & BTRFS_BALANCE_TYPE_MASK))) { + return 0; + } + + if (chunk_type & BTRFS_BLOCK_GROUP_DATA) + bargs = &bctl->data; + else if (chunk_type & BTRFS_BLOCK_GROUP_SYSTEM) + bargs = &bctl->sys; + else if (chunk_type & BTRFS_BLOCK_GROUP_METADATA) + bargs = &bctl->meta; + + return 1; +} + static u64 div_factor(u64 num, int factor) { if (factor == 10) @@ -2119,10 +2143,13 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) struct btrfs_device *device; u64 old_size; u64 size_to_free; + struct btrfs_chunk *chunk; struct btrfs_path *path; struct btrfs_key key; struct btrfs_key found_key; struct btrfs_trans_handle *trans; + struct extent_buffer *leaf; + int slot; int ret; int enospc_errors = 0; @@ -2179,8 +2206,10 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) break; } - btrfs_item_key_to_cpu(path->nodes[0], &found_key, - path->slots[0]); + leaf = path->nodes[0]; + slot = path->slots[0]; + btrfs_item_key_to_cpu(leaf, &found_key, slot); + if (found_key.objectid != key.objectid) break; @@ -2188,7 +2217,14 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) if (found_key.offset == 0) break; + chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); + + ret = should_balance_chunk(chunk_root, leaf, chunk, + found_key.offset); btrfs_release_path(path); + if (!ret) + goto loop; + ret = btrfs_relocate_chunk(chunk_root, chunk_root->root_key.objectid, found_key.objectid, @@ -2197,6 +2233,7 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) goto error; if (ret == -ENOSPC) enospc_errors++; +loop: key.offset = found_key.offset - 1; } @@ -2227,6 +2264,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl, struct btrfs_ioctl_balance_args *bargs) { struct btrfs_fs_info *fs_info = bctl->fs_info; + u64 allowed; int ret; if (btrfs_fs_closing(fs_info)) { @@ -2234,6 +2272,23 @@ int btrfs_balance(struct btrfs_balance_control *bctl, goto out; } + /* + * In case of mixed groups both data and meta should be picked, + * and identical options should be given for both of them. + */ + allowed = btrfs_super_incompat_flags(fs_info->super_copy); + if ((allowed & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) && + (bctl->flags & (BTRFS_BALANCE_DATA | BTRFS_BALANCE_METADATA))) { + if (!(bctl->flags & BTRFS_BALANCE_DATA) || + !(bctl->flags & BTRFS_BALANCE_METADATA) || + memcmp(&bctl->data, &bctl->meta, sizeof(bctl->data))) { + printk(KERN_ERR "btrfs: with mixed groups data and " + "metadata balance options must be the same\n"); + ret = -EINVAL; + goto out; + } + } + set_balance_control(bctl); mutex_unlock(&fs_info->balance_mutex); diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 882582385283..003e54216069 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -186,6 +186,17 @@ struct map_lookup { #define map_lookup_size(n) (sizeof(struct map_lookup) + \ (sizeof(struct btrfs_bio_stripe) * (n))) +/* + * Restriper's general type filter + */ +#define BTRFS_BALANCE_DATA (1ULL << 0) +#define BTRFS_BALANCE_SYSTEM (1ULL << 1) +#define BTRFS_BALANCE_METADATA (1ULL << 2) + +#define BTRFS_BALANCE_TYPE_MASK (BTRFS_BALANCE_DATA | \ + BTRFS_BALANCE_SYSTEM | \ + BTRFS_BALANCE_METADATA) + struct btrfs_balance_args; struct btrfs_balance_control { struct btrfs_fs_info *fs_info; -- cgit v1.2.3 From 837d5b6e46d1a4af5b6cc8f2fe83cb5de79a2961 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 16 Jan 2012 22:04:49 +0200 Subject: Btrfs: allow for pausing restriper Implement an ioctl for pausing restriper. This pauses the relocation, but balance is still considered to be "in progress": balance item is not deleted, other volume operations cannot be started, etc. If paused in the middle of profile changing operation we will continue making allocations with the target profile. Add a hook to close_ctree() to pause restriper and free its data structures on unmount. (It's safe to unmount when restriper is in "paused" state, we will resume with the same parameters on the next mount) Signed-off-by: Ilya Dryomov --- fs/btrfs/ctree.h | 4 ++++ fs/btrfs/disk-io.c | 6 ++++++ fs/btrfs/ioctl.c | 28 +++++++++++++++++++++++++++- fs/btrfs/ioctl.h | 7 +++++++ fs/btrfs/volumes.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++-- fs/btrfs/volumes.h | 1 + 6 files changed, 94 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 99eb2bcd9aa7..1afda75d5414 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1214,7 +1214,10 @@ struct btrfs_fs_info { /* restriper state */ spinlock_t balance_lock; struct mutex balance_mutex; + atomic_t balance_running; + atomic_t balance_pause_req; struct btrfs_balance_control *balance_ctl; + wait_queue_head_t balance_wait_q; unsigned data_chunk_allocations; unsigned metadata_ratio; @@ -2658,6 +2661,7 @@ static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info) } static inline void free_fs_info(struct btrfs_fs_info *fs_info) { + kfree(fs_info->balance_ctl); kfree(fs_info->delayed_root); kfree(fs_info->extent_root); kfree(fs_info->tree_root); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index eb7a11ac5b73..8ce837407800 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2004,7 +2004,10 @@ struct btrfs_root *open_ctree(struct super_block *sb, spin_lock_init(&fs_info->balance_lock); mutex_init(&fs_info->balance_mutex); + atomic_set(&fs_info->balance_running, 0); + atomic_set(&fs_info->balance_pause_req, 0); fs_info->balance_ctl = NULL; + init_waitqueue_head(&fs_info->balance_wait_q); sb->s_blocksize = 4096; sb->s_blocksize_bits = blksize_bits(4096); @@ -2980,6 +2983,9 @@ int close_ctree(struct btrfs_root *root) fs_info->closing = 1; smp_mb(); + /* pause restriper - we want to resume on mount */ + btrfs_pause_balance(root->fs_info); + btrfs_scrub_cancel(root); /* wait for any defraggers to finish */ diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 29b3a94933f0..f572c53dda4f 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3072,6 +3072,11 @@ void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, bargs->flags = bctl->flags; + if (atomic_read(&fs_info->balance_running)) + bargs->state |= BTRFS_BALANCE_STATE_RUNNING; + if (atomic_read(&fs_info->balance_pause_req)) + bargs->state |= BTRFS_BALANCE_STATE_PAUSE_REQ; + memcpy(&bargs->data, &bctl->data, sizeof(bargs->data)); memcpy(&bargs->meta, &bctl->meta, sizeof(bargs->meta)); memcpy(&bargs->sys, &bctl->sys, sizeof(bargs->sys)); @@ -3103,6 +3108,11 @@ static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg) bargs = NULL; } + if (fs_info->balance_ctl) { + ret = -EINPROGRESS; + goto out_bargs; + } + bctl = kzalloc(sizeof(*bctl), GFP_NOFS); if (!bctl) { ret = -ENOMEM; @@ -3123,7 +3133,8 @@ static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg) ret = btrfs_balance(bctl, bargs); /* - * bctl is freed in __cancel_balance + * bctl is freed in __cancel_balance or in free_fs_info if + * restriper was paused all the way until unmount */ if (arg) { if (copy_to_user(arg, bargs, sizeof(*bargs))) @@ -3138,6 +3149,19 @@ out: return ret; } +static long btrfs_ioctl_balance_ctl(struct btrfs_root *root, int cmd) +{ + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + switch (cmd) { + case BTRFS_BALANCE_CTL_PAUSE: + return btrfs_pause_balance(root->fs_info); + } + + return -EINVAL; +} + long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -3216,6 +3240,8 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_scrub_progress(root, argp); case BTRFS_IOC_BALANCE_V2: return btrfs_ioctl_balance(root, argp); + case BTRFS_IOC_BALANCE_CTL: + return btrfs_ioctl_balance_ctl(root, arg); } return -ENOTTY; diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index c8b37d2c0d77..e972e11a8d77 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -109,6 +109,9 @@ struct btrfs_ioctl_fs_info_args { __u64 reserved[124]; /* pad to 1k */ }; +/* balance control ioctl modes */ +#define BTRFS_BALANCE_CTL_PAUSE 1 + /* * this is packed, because it should be exactly the same as its disk * byte order counterpart (struct btrfs_disk_balance_args) @@ -137,6 +140,9 @@ struct btrfs_balance_progress { __u64 completed; /* # of chunks relocated so far */ }; +#define BTRFS_BALANCE_STATE_RUNNING (1ULL << 0) +#define BTRFS_BALANCE_STATE_PAUSE_REQ (1ULL << 1) + struct btrfs_ioctl_balance_args { __u64 flags; /* in/out */ __u64 state; /* out */ @@ -315,6 +321,7 @@ struct btrfs_ioctl_logical_ino_args { struct btrfs_ioctl_fs_info_args) #define BTRFS_IOC_BALANCE_V2 _IOWR(BTRFS_IOCTL_MAGIC, 32, \ struct btrfs_ioctl_balance_args) +#define BTRFS_IOC_BALANCE_CTL _IOW(BTRFS_IOCTL_MAGIC, 33, int) #define BTRFS_IOC_INO_PATHS _IOWR(BTRFS_IOCTL_MAGIC, 35, \ struct btrfs_ioctl_ino_path_args) #define BTRFS_IOC_LOGICAL_INO _IOWR(BTRFS_IOCTL_MAGIC, 36, \ diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index e0160607e6e2..d32660ce753d 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2492,6 +2492,11 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) key.type = BTRFS_CHUNK_ITEM_KEY; while (1) { + if (atomic_read(&fs_info->balance_pause_req)) { + ret = -ECANCELED; + goto error; + } + ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0); if (ret < 0) goto error; @@ -2553,6 +2558,11 @@ error: return ret; } +static inline int balance_need_close(struct btrfs_fs_info *fs_info) +{ + return atomic_read(&fs_info->balance_pause_req) == 0; +} + static void __cancel_balance(struct btrfs_fs_info *fs_info) { int ret; @@ -2575,7 +2585,8 @@ int btrfs_balance(struct btrfs_balance_control *bctl, u64 allowed; int ret; - if (btrfs_fs_closing(fs_info)) { + if (btrfs_fs_closing(fs_info) || + atomic_read(&fs_info->balance_pause_req)) { ret = -EINVAL; goto out; } @@ -2680,18 +2691,25 @@ do_balance: spin_unlock(&fs_info->balance_lock); } + atomic_inc(&fs_info->balance_running); mutex_unlock(&fs_info->balance_mutex); ret = __btrfs_balance(fs_info); mutex_lock(&fs_info->balance_mutex); + atomic_dec(&fs_info->balance_running); if (bargs) { memset(bargs, 0, sizeof(*bargs)); update_ioctl_balance_args(fs_info, bargs); } - __cancel_balance(fs_info); + if ((ret && ret != -ECANCELED && ret != -ENOSPC) || + balance_need_close(fs_info)) { + __cancel_balance(fs_info); + } + + wake_up(&fs_info->balance_wait_q); return ret; out: @@ -2785,6 +2803,35 @@ out: return ret; } +int btrfs_pause_balance(struct btrfs_fs_info *fs_info) +{ + int ret = 0; + + mutex_lock(&fs_info->balance_mutex); + if (!fs_info->balance_ctl) { + mutex_unlock(&fs_info->balance_mutex); + return -ENOTCONN; + } + + if (atomic_read(&fs_info->balance_running)) { + atomic_inc(&fs_info->balance_pause_req); + mutex_unlock(&fs_info->balance_mutex); + + wait_event(fs_info->balance_wait_q, + atomic_read(&fs_info->balance_running) == 0); + + mutex_lock(&fs_info->balance_mutex); + /* we are good with balance_ctl ripped off from under us */ + BUG_ON(atomic_read(&fs_info->balance_running)); + atomic_dec(&fs_info->balance_pause_req); + } else { + ret = -ENOTCONN; + } + + mutex_unlock(&fs_info->balance_mutex); + return ret; +} + /* * shrinking a device means finding all of the device extents past * the new size, and then following the back refs to the chunks. diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index cd25ea58ec35..80953afb12b9 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -273,6 +273,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *path); int btrfs_balance(struct btrfs_balance_control *bctl, struct btrfs_ioctl_balance_args *bargs); int btrfs_recover_balance(struct btrfs_root *tree_root); +int btrfs_pause_balance(struct btrfs_fs_info *fs_info); int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset); int find_free_dev_extent(struct btrfs_trans_handle *trans, struct btrfs_device *device, u64 num_bytes, -- cgit v1.2.3 From a7e99c691af553fc15ac46a51f130b7c59a65f76 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 16 Jan 2012 22:04:49 +0200 Subject: Btrfs: allow for canceling restriper Implement an ioctl for canceling restriper. Currently we wait until relocation of the current block group is finished, in future this can be done by triggering a commit. Balance item is deleted and no memory about the interrupted balance is kept. Signed-off-by: Ilya Dryomov --- fs/btrfs/ctree.h | 1 + fs/btrfs/disk-io.c | 1 + fs/btrfs/ioctl.c | 4 ++++ fs/btrfs/ioctl.h | 2 ++ fs/btrfs/volumes.c | 47 ++++++++++++++++++++++++++++++++++++++++++++--- fs/btrfs/volumes.h | 1 + 6 files changed, 53 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 1afda75d5414..dfc136cc07d7 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1216,6 +1216,7 @@ struct btrfs_fs_info { struct mutex balance_mutex; atomic_t balance_running; atomic_t balance_pause_req; + atomic_t balance_cancel_req; struct btrfs_balance_control *balance_ctl; wait_queue_head_t balance_wait_q; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 8ce837407800..c23b82d8ec08 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2006,6 +2006,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, mutex_init(&fs_info->balance_mutex); atomic_set(&fs_info->balance_running, 0); atomic_set(&fs_info->balance_pause_req, 0); + atomic_set(&fs_info->balance_cancel_req, 0); fs_info->balance_ctl = NULL; init_waitqueue_head(&fs_info->balance_wait_q); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index f572c53dda4f..60852217ce9a 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3076,6 +3076,8 @@ void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, bargs->state |= BTRFS_BALANCE_STATE_RUNNING; if (atomic_read(&fs_info->balance_pause_req)) bargs->state |= BTRFS_BALANCE_STATE_PAUSE_REQ; + if (atomic_read(&fs_info->balance_cancel_req)) + bargs->state |= BTRFS_BALANCE_STATE_CANCEL_REQ; memcpy(&bargs->data, &bctl->data, sizeof(bargs->data)); memcpy(&bargs->meta, &bctl->meta, sizeof(bargs->meta)); @@ -3157,6 +3159,8 @@ static long btrfs_ioctl_balance_ctl(struct btrfs_root *root, int cmd) switch (cmd) { case BTRFS_BALANCE_CTL_PAUSE: return btrfs_pause_balance(root->fs_info); + case BTRFS_BALANCE_CTL_CANCEL: + return btrfs_cancel_balance(root->fs_info); } return -EINVAL; diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index e972e11a8d77..cd19d10794b9 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -111,6 +111,7 @@ struct btrfs_ioctl_fs_info_args { /* balance control ioctl modes */ #define BTRFS_BALANCE_CTL_PAUSE 1 +#define BTRFS_BALANCE_CTL_CANCEL 2 /* * this is packed, because it should be exactly the same as its disk @@ -142,6 +143,7 @@ struct btrfs_balance_progress { #define BTRFS_BALANCE_STATE_RUNNING (1ULL << 0) #define BTRFS_BALANCE_STATE_PAUSE_REQ (1ULL << 1) +#define BTRFS_BALANCE_STATE_CANCEL_REQ (1ULL << 2) struct btrfs_ioctl_balance_args { __u64 flags; /* in/out */ diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index d32660ce753d..c32667318ae4 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2492,7 +2492,8 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) key.type = BTRFS_CHUNK_ITEM_KEY; while (1) { - if (atomic_read(&fs_info->balance_pause_req)) { + if (atomic_read(&fs_info->balance_pause_req) || + atomic_read(&fs_info->balance_cancel_req)) { ret = -ECANCELED; goto error; } @@ -2560,7 +2561,10 @@ error: static inline int balance_need_close(struct btrfs_fs_info *fs_info) { - return atomic_read(&fs_info->balance_pause_req) == 0; + /* cancel requested || normal exit path */ + return atomic_read(&fs_info->balance_cancel_req) || + (atomic_read(&fs_info->balance_pause_req) == 0 && + atomic_read(&fs_info->balance_cancel_req) == 0); } static void __cancel_balance(struct btrfs_fs_info *fs_info) @@ -2586,7 +2590,8 @@ int btrfs_balance(struct btrfs_balance_control *bctl, int ret; if (btrfs_fs_closing(fs_info) || - atomic_read(&fs_info->balance_pause_req)) { + atomic_read(&fs_info->balance_pause_req) || + atomic_read(&fs_info->balance_cancel_req)) { ret = -EINVAL; goto out; } @@ -2832,6 +2837,42 @@ int btrfs_pause_balance(struct btrfs_fs_info *fs_info) return ret; } +int btrfs_cancel_balance(struct btrfs_fs_info *fs_info) +{ + mutex_lock(&fs_info->balance_mutex); + if (!fs_info->balance_ctl) { + mutex_unlock(&fs_info->balance_mutex); + return -ENOTCONN; + } + + atomic_inc(&fs_info->balance_cancel_req); + /* + * if we are running just wait and return, balance item is + * deleted in btrfs_balance in this case + */ + if (atomic_read(&fs_info->balance_running)) { + mutex_unlock(&fs_info->balance_mutex); + wait_event(fs_info->balance_wait_q, + atomic_read(&fs_info->balance_running) == 0); + mutex_lock(&fs_info->balance_mutex); + } else { + /* __cancel_balance needs volume_mutex */ + mutex_unlock(&fs_info->balance_mutex); + mutex_lock(&fs_info->volume_mutex); + mutex_lock(&fs_info->balance_mutex); + + if (fs_info->balance_ctl) + __cancel_balance(fs_info); + + mutex_unlock(&fs_info->volume_mutex); + } + + BUG_ON(fs_info->balance_ctl || atomic_read(&fs_info->balance_running)); + atomic_dec(&fs_info->balance_cancel_req); + mutex_unlock(&fs_info->balance_mutex); + return 0; +} + /* * shrinking a device means finding all of the device extents past * the new size, and then following the back refs to the chunks. diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 80953afb12b9..caa9abd218ef 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -274,6 +274,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl, struct btrfs_ioctl_balance_args *bargs); int btrfs_recover_balance(struct btrfs_root *tree_root); int btrfs_pause_balance(struct btrfs_fs_info *fs_info); +int btrfs_cancel_balance(struct btrfs_fs_info *fs_info); int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset); int find_free_dev_extent(struct btrfs_trans_handle *trans, struct btrfs_device *device, u64 num_bytes, -- cgit v1.2.3 From de322263d3a6d4ffd4ed7c4d0c6536e9497aec9b Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 16 Jan 2012 22:04:49 +0200 Subject: Btrfs: allow for resuming restriper after it was paused Recognize BTRFS_BALANCE_RESUME flag passed from userspace. We use the same heuristics used when recovering balance after a crash to try to start where we left off last time. Signed-off-by: Ilya Dryomov --- fs/btrfs/ioctl.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 60852217ce9a..85e546ffe3c7 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3106,6 +3106,20 @@ static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg) ret = PTR_ERR(bargs); goto out; } + + if (bargs->flags & BTRFS_BALANCE_RESUME) { + if (!fs_info->balance_ctl) { + ret = -ENOTCONN; + goto out_bargs; + } + + bctl = fs_info->balance_ctl; + spin_lock(&fs_info->balance_lock); + bctl->flags |= BTRFS_BALANCE_RESUME; + spin_unlock(&fs_info->balance_lock); + + goto do_balance; + } } else { bargs = NULL; } @@ -3133,6 +3147,7 @@ static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg) bctl->flags |= BTRFS_BALANCE_TYPE_MASK; } +do_balance: ret = btrfs_balance(bctl, bargs); /* * bctl is freed in __cancel_balance or in free_fs_info if -- cgit v1.2.3 From 19a39dce3b9bf0244d19a446718ad6f7605ff099 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Mon, 16 Jan 2012 22:04:49 +0200 Subject: Btrfs: add balance progress reporting Signed-off-by: Ilya Dryomov --- fs/btrfs/ioctl.c | 45 ++++++++++++++++++++++++++++++++++++++++++++- fs/btrfs/ioctl.h | 2 ++ fs/btrfs/volumes.c | 39 +++++++++++++++++++++++++++++++++++---- fs/btrfs/volumes.h | 3 +++ 4 files changed, 84 insertions(+), 5 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 85e546ffe3c7..1e7a9bac31ab 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3065,7 +3065,7 @@ out: return ret; } -void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, +void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock, struct btrfs_ioctl_balance_args *bargs) { struct btrfs_balance_control *bctl = fs_info->balance_ctl; @@ -3082,6 +3082,14 @@ void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, memcpy(&bargs->data, &bctl->data, sizeof(bargs->data)); memcpy(&bargs->meta, &bctl->meta, sizeof(bargs->meta)); memcpy(&bargs->sys, &bctl->sys, sizeof(bargs->sys)); + + if (lock) { + spin_lock(&fs_info->balance_lock); + memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat)); + spin_unlock(&fs_info->balance_lock); + } else { + memcpy(&bargs->stat, &bctl->stat, sizeof(bargs->stat)); + } } static long btrfs_ioctl_balance(struct btrfs_root *root, void __user *arg) @@ -3181,6 +3189,39 @@ static long btrfs_ioctl_balance_ctl(struct btrfs_root *root, int cmd) return -EINVAL; } +static long btrfs_ioctl_balance_progress(struct btrfs_root *root, + void __user *arg) +{ + struct btrfs_fs_info *fs_info = root->fs_info; + struct btrfs_ioctl_balance_args *bargs; + int ret = 0; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + mutex_lock(&fs_info->balance_mutex); + if (!fs_info->balance_ctl) { + ret = -ENOTCONN; + goto out; + } + + bargs = kzalloc(sizeof(*bargs), GFP_NOFS); + if (!bargs) { + ret = -ENOMEM; + goto out; + } + + update_ioctl_balance_args(fs_info, 1, bargs); + + if (copy_to_user(arg, bargs, sizeof(*bargs))) + ret = -EFAULT; + + kfree(bargs); +out: + mutex_unlock(&fs_info->balance_mutex); + return ret; +} + long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { @@ -3261,6 +3302,8 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_balance(root, argp); case BTRFS_IOC_BALANCE_CTL: return btrfs_ioctl_balance_ctl(root, arg); + case BTRFS_IOC_BALANCE_PROGRESS: + return btrfs_ioctl_balance_progress(root, argp); } return -ENOTTY; diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h index cd19d10794b9..4f69028a68c4 100644 --- a/fs/btrfs/ioctl.h +++ b/fs/btrfs/ioctl.h @@ -324,6 +324,8 @@ struct btrfs_ioctl_logical_ino_args { #define BTRFS_IOC_BALANCE_V2 _IOWR(BTRFS_IOCTL_MAGIC, 32, \ struct btrfs_ioctl_balance_args) #define BTRFS_IOC_BALANCE_CTL _IOW(BTRFS_IOCTL_MAGIC, 33, int) +#define BTRFS_IOC_BALANCE_PROGRESS _IOR(BTRFS_IOCTL_MAGIC, 34, \ + struct btrfs_ioctl_balance_args) #define BTRFS_IOC_INO_PATHS _IOWR(BTRFS_IOCTL_MAGIC, 35, \ struct btrfs_ioctl_ino_path_args) #define BTRFS_IOC_LOGICAL_INO _IOWR(BTRFS_IOCTL_MAGIC, 36, \ diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index c32667318ae4..d73439b4d7da 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2441,6 +2441,7 @@ static u64 div_factor(u64 num, int factor) static int __btrfs_balance(struct btrfs_fs_info *fs_info) { + struct btrfs_balance_control *bctl = fs_info->balance_ctl; struct btrfs_root *chunk_root = fs_info->chunk_root; struct btrfs_root *dev_root = fs_info->dev_root; struct list_head *devices; @@ -2456,6 +2457,7 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) int slot; int ret; int enospc_errors = 0; + bool counting = true; /* step one make some room on all the devices */ devices = &fs_info->fs_devices->devices; @@ -2487,12 +2489,18 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) ret = -ENOMEM; goto error; } + + /* zero out stat counters */ + spin_lock(&fs_info->balance_lock); + memset(&bctl->stat, 0, sizeof(bctl->stat)); + spin_unlock(&fs_info->balance_lock); +again: key.objectid = BTRFS_FIRST_CHUNK_TREE_OBJECTID; key.offset = (u64)-1; key.type = BTRFS_CHUNK_ITEM_KEY; while (1) { - if (atomic_read(&fs_info->balance_pause_req) || + if ((!counting && atomic_read(&fs_info->balance_pause_req)) || atomic_read(&fs_info->balance_cancel_req)) { ret = -ECANCELED; goto error; @@ -2529,24 +2537,47 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); + if (!counting) { + spin_lock(&fs_info->balance_lock); + bctl->stat.considered++; + spin_unlock(&fs_info->balance_lock); + } + ret = should_balance_chunk(chunk_root, leaf, chunk, found_key.offset); btrfs_release_path(path); if (!ret) goto loop; + if (counting) { + spin_lock(&fs_info->balance_lock); + bctl->stat.expected++; + spin_unlock(&fs_info->balance_lock); + goto loop; + } + ret = btrfs_relocate_chunk(chunk_root, chunk_root->root_key.objectid, found_key.objectid, found_key.offset); if (ret && ret != -ENOSPC) goto error; - if (ret == -ENOSPC) + if (ret == -ENOSPC) { enospc_errors++; + } else { + spin_lock(&fs_info->balance_lock); + bctl->stat.completed++; + spin_unlock(&fs_info->balance_lock); + } loop: key.offset = found_key.offset - 1; } + if (counting) { + btrfs_release_path(path); + counting = false; + goto again; + } error: btrfs_free_path(path); if (enospc_errors) { @@ -2576,7 +2607,7 @@ static void __cancel_balance(struct btrfs_fs_info *fs_info) BUG_ON(ret); } -void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, +void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock, struct btrfs_ioctl_balance_args *bargs); /* @@ -2706,7 +2737,7 @@ do_balance: if (bargs) { memset(bargs, 0, sizeof(*bargs)); - update_ioctl_balance_args(fs_info, bargs); + update_ioctl_balance_args(fs_info, 0, bargs); } if ((ret && ret != -ECANCELED && ret != -ENOSPC) || diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index caa9abd218ef..6faec9dd1f93 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -218,6 +218,7 @@ struct map_lookup { #define BTRFS_BALANCE_ARGS_SOFT (1ULL << 9) struct btrfs_balance_args; +struct btrfs_balance_progress; struct btrfs_balance_control { struct btrfs_fs_info *fs_info; @@ -226,6 +227,8 @@ struct btrfs_balance_control { struct btrfs_balance_args sys; u64 flags; + + struct btrfs_balance_progress stat; }; int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start, -- cgit v1.2.3 From f248679e86fead40cc78e724c7181d6bec1a2046 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 13 Jan 2012 12:09:22 -0500 Subject: Btrfs: add a delalloc mutex to inodes for delalloc reservations I was using i_mutex for this, but we're getting bogus lockdep warnings by doing that and theres no real way to get rid of those, so just stop using i_mutex to protect delalloc metadata reservations and use a delalloc mutex instead. This shouldn't be contended often at all, only if you are writing and mmap writing to the file at the same time. Thanks, Signed-off-by: Josef Bacik --- fs/btrfs/btrfs_inode.h | 3 +++ fs/btrfs/extent-tree.c | 5 +++-- fs/btrfs/inode.c | 11 +---------- fs/btrfs/ioctl.c | 2 -- fs/btrfs/relocation.c | 2 -- 5 files changed, 7 insertions(+), 16 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 634608d2a6d0..9b9b15fd5204 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -51,6 +51,9 @@ struct btrfs_inode { /* held while logging the inode in tree-log.c */ struct mutex log_mutex; + /* held while doing delalloc reservations */ + struct mutex delalloc_mutex; + /* used to order data wrt metadata */ struct btrfs_ordered_inode_tree ordered_tree; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 556f9aa25bb7..e0ad5f0f895e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4345,12 +4345,11 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) /* Need to be holding the i_mutex here if we aren't free space cache */ if (btrfs_is_free_space_inode(root, inode)) flush = 0; - else - WARN_ON(!mutex_is_locked(&inode->i_mutex)); if (flush && btrfs_transaction_in_commit(root->fs_info)) schedule_timeout(1); + mutex_lock(&BTRFS_I(inode)->delalloc_mutex); num_bytes = ALIGN(num_bytes, root->sectorsize); spin_lock(&BTRFS_I(inode)->lock); @@ -4405,6 +4404,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) btrfs_ino(inode), to_free, 0); } + mutex_unlock(&BTRFS_I(inode)->delalloc_mutex); return ret; } @@ -4415,6 +4415,7 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) } BTRFS_I(inode)->reserved_extents += nr_extents; spin_unlock(&BTRFS_I(inode)->lock); + mutex_unlock(&BTRFS_I(inode)->delalloc_mutex); if (to_reserve) trace_btrfs_space_reservation(root->fs_info,"delalloc", diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 619742d37166..5977987abdb1 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2239,14 +2239,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) continue; } nr_truncate++; - /* - * Need to hold the imutex for reservation purposes, not - * a huge deal here but I have a WARN_ON in - * btrfs_delalloc_reserve_space to catch offenders. - */ - mutex_lock(&inode->i_mutex); ret = btrfs_truncate(inode); - mutex_unlock(&inode->i_mutex); } else { nr_unlink++; } @@ -6411,10 +6404,7 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) u64 page_start; u64 page_end; - /* Need this to keep space reservations serialized */ - mutex_lock(&inode->i_mutex); ret = btrfs_delalloc_reserve_space(inode, PAGE_CACHE_SIZE); - mutex_unlock(&inode->i_mutex); if (!ret) ret = btrfs_update_time(vma->vm_file); if (ret) { @@ -6758,6 +6748,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) extent_io_tree_init(&ei->io_tree, &inode->i_data); extent_io_tree_init(&ei->io_failure_tree, &inode->i_data); mutex_init(&ei->log_mutex); + mutex_init(&ei->delalloc_mutex); btrfs_ordered_inode_tree_init(&ei->ordered_tree); INIT_LIST_HEAD(&ei->i_orphan); INIT_LIST_HEAD(&ei->delalloc_inodes); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 7fdf22c2dc0d..6834be4c8709 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -868,10 +868,8 @@ static int cluster_pages_for_defrag(struct inode *inode, return 0; file_end = (isize - 1) >> PAGE_CACHE_SHIFT; - mutex_lock(&inode->i_mutex); ret = btrfs_delalloc_reserve_space(inode, num_pages << PAGE_CACHE_SHIFT); - mutex_unlock(&inode->i_mutex); if (ret) return ret; again: diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index efe9f792544d..8c1aae2c845d 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2949,9 +2949,7 @@ static int relocate_file_extent_cluster(struct inode *inode, index = (cluster->start - offset) >> PAGE_CACHE_SHIFT; last_index = (cluster->end - offset) >> PAGE_CACHE_SHIFT; while (index <= last_index) { - mutex_lock(&inode->i_mutex); ret = btrfs_delalloc_reserve_metadata(inode, PAGE_CACHE_SIZE); - mutex_unlock(&inode->i_mutex); if (ret) goto out; -- cgit v1.2.3 From 7ec31b548a17f773ab6289e795ed3a6820e8b56e Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Thu, 26 Jan 2012 15:01:12 -0500 Subject: Btrfs: do not defrag a file partially xfstests 218 complains that btrfs defrags a file partially: After: 1 Write backwards sync, but contiguous - should defrag to 1 extent Before: 10 -After: 1 +After: 2 To fix this, we need to set max_to_defrag count properly. Signed-off-by: Liu Bo Signed-off-by: Chris Mason --- fs/btrfs/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 6834be4c8709..0b06a5ca8afc 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1066,7 +1066,7 @@ int btrfs_defrag_file(struct inode *inode, struct file *file, i = range->start >> PAGE_CACHE_SHIFT; } if (!max_to_defrag) - max_to_defrag = last_index; + max_to_defrag = last_index + 1; /* * make writeback starts from i, so the defrag range can be -- cgit v1.2.3 From 600a45e1d5e376f679ff9ecc4ce9452710a6d27c Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Thu, 16 Feb 2012 15:01:24 +0800 Subject: Btrfs: fix deadlock on page lock when doing auto-defragment When I ran xfstests circularly on a auto-defragment btrfs, the deadlock happened. Steps to reproduce: [tty0] # export MOUNT_OPTIONS="-o autodefrag" # export TEST_DEV= # export TEST_DIR= # export SCRATCH_DEV= # export SCRATCH_MNT= # while [ 1 ] > do > ./check 091 127 263 > sleep 1 > done [tty1] # while [ 1 ] > do > echo 3 > /proc/sys/vm/drop_caches > done Several hours later, the test processes will hang on, and the deadlock will happen on page lock. The reason is that: Auto defrag task Flush thread Test task btrfs_writepages() add ordered extent (including page 1, 2) set page 1 writeback set page 2 writeback endio_fn() end page 2 writeback release page 2 lock page 1 alloc and lock page 2 page 2 is not uptodate btrfs_readpage() start ordered extent() btrfs_writepages() try to lock page 1 so deadlock happens. Fix this bug by unlocking the page which is in writeback, and re-locking it after the writeback end. Signed-off-by: Miao Xie --- fs/btrfs/ioctl.c | 53 +++++++++++++++++++++++++++++------------------------ 1 file changed, 29 insertions(+), 24 deletions(-) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 0b06a5ca8afc..e9bdb8b783e5 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -862,6 +862,7 @@ static int cluster_pages_for_defrag(struct inode *inode, int i_done; struct btrfs_ordered_extent *ordered; struct extent_state *cached_state = NULL; + struct extent_io_tree *tree; gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping); if (isize == 0) @@ -872,18 +873,34 @@ static int cluster_pages_for_defrag(struct inode *inode, num_pages << PAGE_CACHE_SHIFT); if (ret) return ret; -again: - ret = 0; i_done = 0; + tree = &BTRFS_I(inode)->io_tree; /* step one, lock all the pages */ for (i = 0; i < num_pages; i++) { struct page *page; +again: page = find_or_create_page(inode->i_mapping, - start_index + i, mask); + start_index + i, mask); if (!page) break; + page_start = page_offset(page); + page_end = page_start + PAGE_CACHE_SIZE - 1; + while (1) { + lock_extent(tree, page_start, page_end, GFP_NOFS); + ordered = btrfs_lookup_ordered_extent(inode, + page_start); + unlock_extent(tree, page_start, page_end, GFP_NOFS); + if (!ordered) + break; + + unlock_page(page); + btrfs_start_ordered_extent(inode, ordered, 1); + btrfs_put_ordered_extent(ordered); + lock_page(page); + } + if (!PageUptodate(page)) { btrfs_readpage(NULL, page); lock_page(page); @@ -894,15 +911,22 @@ again: break; } } + isize = i_size_read(inode); file_end = (isize - 1) >> PAGE_CACHE_SHIFT; - if (!isize || page->index > file_end || - page->mapping != inode->i_mapping) { + if (!isize || page->index > file_end) { /* whoops, we blew past eof, skip this page */ unlock_page(page); page_cache_release(page); break; } + + if (page->mapping != inode->i_mapping) { + unlock_page(page); + page_cache_release(page); + goto again; + } + pages[i] = page; i_done++; } @@ -925,25 +949,6 @@ again: lock_extent_bits(&BTRFS_I(inode)->io_tree, page_start, page_end - 1, 0, &cached_state, GFP_NOFS); - ordered = btrfs_lookup_first_ordered_extent(inode, page_end - 1); - if (ordered && - ordered->file_offset + ordered->len > page_start && - ordered->file_offset < page_end) { - btrfs_put_ordered_extent(ordered); - unlock_extent_cached(&BTRFS_I(inode)->io_tree, - page_start, page_end - 1, - &cached_state, GFP_NOFS); - for (i = 0; i < i_done; i++) { - unlock_page(pages[i]); - page_cache_release(pages[i]); - } - btrfs_wait_ordered_range(inode, page_start, - page_end - page_start); - goto again; - } - if (ordered) - btrfs_put_ordered_extent(ordered); - clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, page_end - 1, EXTENT_DIRTY | EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING, 0, 0, &cached_state, -- cgit v1.2.3 From 16780cabb877dbd0c8c5e9ff9bdebd6c5bdd1a7b Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Mon, 20 Feb 2012 22:14:55 -0500 Subject: Btrfs: add extra sanity checks on the path names in btrfs_mksubvol Signed-off-by: Chris Mason --- fs/btrfs/ioctl.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'fs/btrfs/ioctl.c') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index e9bdb8b783e5..05446f77f99b 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1333,6 +1333,12 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file, goto out; } + if (name[0] == '.' && + (namelen == 1 || (name[1] == '.' && namelen == 2))) { + ret = -EEXIST; + goto out; + } + if (subvol) { ret = btrfs_mksubvol(&file->f_path, name, namelen, NULL, transid, readonly); -- cgit v1.2.3