From ba8b0289333a70f0d69923fd63350d0b0201b904 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 27 Mar 2014 14:56:51 -0400 Subject: Btrfs: do not reset last_snapshot after relocation This was done to allow NO_COW to continue to be NO_COW after relocation but it is not right. When relocating we will convert blocks to FULL_BACKREF that we relocate. We can leave some of these full backref blocks behind if they are not cow'ed out during the relocation, like if we fail the relocation with ENOSPC and then just drop the reloc tree. Then when we go to cow the block again we won't lookup the extent flags because we won't think there has been a snapshot recently which means we will do our normal ref drop thing instead of adding back a tree ref and dropping the shared ref. This will cause btrfs_free_extent to blow up because it can't find the ref we are trying to free. This was found with my ref verifying tool. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/relocation.c | 21 --------------------- 1 file changed, 21 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index def428a..7f92ab1 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -2317,7 +2317,6 @@ void free_reloc_roots(struct list_head *list) static noinline_for_stack int merge_reloc_roots(struct reloc_control *rc) { - struct btrfs_trans_handle *trans; struct btrfs_root *root; struct btrfs_root *reloc_root; u64 last_snap; @@ -2375,26 +2374,6 @@ again: list_add_tail(&reloc_root->root_list, &reloc_roots); goto out; - } else if (!ret) { - /* - * recover the last snapshot tranid to avoid - * the space balance break NOCOW. - */ - root = read_fs_root(rc->extent_root->fs_info, - objectid); - if (IS_ERR(root)) - continue; - - trans = btrfs_join_transaction(root); - BUG_ON(IS_ERR(trans)); - - /* Check if the fs/file tree was snapshoted or not. */ - if (btrfs_root_last_snapshot(&root->root_item) == - otransid - 1) - btrfs_set_root_last_snapshot(&root->root_item, - last_snap); - - btrfs_end_transaction(trans, root); } } -- cgit v1.1 From 573a075567f0174551e2fad2a3164afd2af788f2 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 27 Mar 2014 19:41:34 -0400 Subject: Btrfs: check for an extent_op on the locked ref We could have possibly added an extent_op to the locked_ref while we dropped locked_ref->lock, so check for this case as well and loop around. Otherwise we could lose flag updates which would lead to extent tree corruption. Thanks, cc: stable@vger.kernel.org Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index c6b6a6e..e09db2c 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2444,7 +2444,8 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, spin_unlock(&locked_ref->lock); spin_lock(&delayed_refs->lock); spin_lock(&locked_ref->lock); - if (rb_first(&locked_ref->ref_root)) { + if (rb_first(&locked_ref->ref_root) || + locked_ref->extent_op) { spin_unlock(&locked_ref->lock); spin_unlock(&delayed_refs->lock); continue; -- cgit v1.1 From a26e8c9f75b0bfd8cccc9e8f110737b136eb5994 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 28 Mar 2014 17:07:27 -0400 Subject: Btrfs: don't clear uptodate if the eb is under IO So I have an awful exercise script that will run snapshot, balance and send/receive in parallel. This sometimes would crash spectacularly and when it came back up the fs would be completely hosed. Turns out this is because of a bad interaction of balance and send/receive. Send will hold onto its entire path for the whole send, but its blocks could get relocated out from underneath it, and because it doesn't old tree locks theres nothing to keep this from happening. So it will go to read in a slot with an old transid, and we could have re-allocated this block for something else and it could have a completely different transid. But because we think it is invalid we clear uptodate and re-read in the block. If we do this before we actually write out the new block we could write back stale data to the fs, and boom we're screwed. Now we definitely need to fix this disconnect between send and balance, but we really really need to not allow ourselves to accidently read in stale data over new data. So make sure we check if the extent buffer is not under io before clearing uptodate, this will kick back EIO to the caller instead of reading in stale data and keep us from corrupting the fs. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 20 +++++++++++++++++++- fs/btrfs/extent_io.c | 2 +- fs/btrfs/extent_io.h | 1 + fs/btrfs/send.c | 2 ++ fs/btrfs/transaction.c | 3 ++- fs/btrfs/transaction.h | 2 ++ 6 files changed, 27 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index d9698fd..98fe701 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -329,6 +329,8 @@ static int verify_parent_transid(struct extent_io_tree *io_tree, { struct extent_state *cached_state = NULL; int ret; + bool need_lock = (current->journal_info == + (void *)BTRFS_SEND_TRANS_STUB); if (!parent_transid || btrfs_header_generation(eb) == parent_transid) return 0; @@ -336,6 +338,11 @@ static int verify_parent_transid(struct extent_io_tree *io_tree, if (atomic) return -EAGAIN; + if (need_lock) { + btrfs_tree_read_lock(eb); + btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK); + } + lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1, 0, &cached_state); if (extent_buffer_uptodate(eb) && @@ -347,10 +354,21 @@ static int verify_parent_transid(struct extent_io_tree *io_tree, "found %llu\n", eb->start, parent_transid, btrfs_header_generation(eb)); ret = 1; - clear_extent_buffer_uptodate(eb); + + /* + * Things reading via commit roots that don't have normal protection, + * like send, can have a really old block in cache that may point at a + * block that has been free'd and re-allocated. So don't clear uptodate + * if we find an eb that is under IO (dirty/writeback) because we could + * end up reading in the stale data and then writing it back out and + * making everybody very sad. + */ + if (!extent_buffer_under_io(eb)) + clear_extent_buffer_uptodate(eb); out: unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1, &cached_state, GFP_NOFS); + btrfs_tree_read_unlock_blocking(eb); return ret; } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index fd78c84..d35a3ca 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -4315,7 +4315,7 @@ static void __free_extent_buffer(struct extent_buffer *eb) kmem_cache_free(extent_buffer_cache, eb); } -static int extent_buffer_under_io(struct extent_buffer *eb) +int extent_buffer_under_io(struct extent_buffer *eb) { return (atomic_read(&eb->io_pages) || test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) || diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 58b27e5..c488b45 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -320,6 +320,7 @@ int set_extent_buffer_dirty(struct extent_buffer *eb); int set_extent_buffer_uptodate(struct extent_buffer *eb); int clear_extent_buffer_uptodate(struct extent_buffer *eb); int extent_buffer_uptodate(struct extent_buffer *eb); +int extent_buffer_under_io(struct extent_buffer *eb); int map_private_extent_buffer(struct extent_buffer *eb, unsigned long offset, unsigned long min_len, char **map, unsigned long *map_start, diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 9b6da9d..d00534b 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -5718,7 +5718,9 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_) NULL); sort_clone_roots = 1; + current->journal_info = (void *)BTRFS_SEND_TRANS_STUB; ret = send_subvol(sctx); + current->journal_info = NULL; if (ret < 0) goto out; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index a04707f..038177c 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -375,7 +375,8 @@ start_transaction(struct btrfs_root *root, u64 num_items, unsigned int type, if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) return ERR_PTR(-EROFS); - if (current->journal_info) { + if (current->journal_info && + current->journal_info != (void *)BTRFS_SEND_TRANS_STUB) { WARN_ON(type & TRANS_EXTWRITERS); h = current->journal_info; h->use_count++; diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 6ac037e..2bcba89 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -78,6 +78,8 @@ struct btrfs_transaction { #define TRANS_EXTWRITERS (__TRANS_USERSPACE | __TRANS_START | \ __TRANS_ATTACH) +#define BTRFS_SEND_TRANS_STUB 1 + struct btrfs_trans_handle { u64 transid; u64 bytes_reserved; -- cgit v1.1 From 9e351cc862b098d8ec8f8022d110932490794925 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 13 Mar 2014 15:42:13 -0400 Subject: Btrfs: remove transaction from send Lets try this again. We can deadlock the box if we send on a box and try to write onto the same fs with the app that is trying to listen to the send pipe. This is because the writer could get stuck waiting for a transaction commit which is being blocked by the send. So fix this by making sure looking at the commit roots is always going to be consistent. We do this by keeping track of which roots need to have their commit roots swapped during commit, and then taking the commit_root_sem and swapping them all at once. Then make sure we take a read lock on the commit_root_sem in cases where we search the commit root to make sure we're always looking at a consistent view of the commit roots. Previously we had problems with this because we would swap a fs tree commit root and then swap the extent tree commit root independently which would cause the backref walking code to screw up sometimes. With this patch we no longer deadlock and pass all the weird send/receive corner cases. Thanks, Reportedy-by: Hugo Mills Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/backref.c | 33 +++++++++++++++---- fs/btrfs/ctree.c | 88 -------------------------------------------------- fs/btrfs/ctree.h | 3 +- fs/btrfs/disk-io.c | 3 +- fs/btrfs/extent-tree.c | 20 ++++++------ fs/btrfs/inode-map.c | 14 ++++---- fs/btrfs/send.c | 57 ++------------------------------ fs/btrfs/transaction.c | 45 ++++++++++++++++---------- fs/btrfs/transaction.h | 1 + 9 files changed, 77 insertions(+), 187 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index aad7201..10db21f 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -330,7 +330,10 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info, goto out; } - root_level = btrfs_old_root_level(root, time_seq); + if (path->search_commit_root) + root_level = btrfs_header_level(root->commit_root); + else + root_level = btrfs_old_root_level(root, time_seq); if (root_level + 1 == level) { srcu_read_unlock(&fs_info->subvol_srcu, index); @@ -1099,9 +1102,9 @@ static int btrfs_find_all_leafs(struct btrfs_trans_handle *trans, * * returns 0 on success, < 0 on error. */ -int btrfs_find_all_roots(struct btrfs_trans_handle *trans, - struct btrfs_fs_info *fs_info, u64 bytenr, - u64 time_seq, struct ulist **roots) +static int __btrfs_find_all_roots(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, u64 bytenr, + u64 time_seq, struct ulist **roots) { struct ulist *tmp; struct ulist_node *node = NULL; @@ -1137,6 +1140,20 @@ int btrfs_find_all_roots(struct btrfs_trans_handle *trans, return 0; } +int btrfs_find_all_roots(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, u64 bytenr, + u64 time_seq, struct ulist **roots) +{ + int ret; + + if (!trans) + down_read(&fs_info->commit_root_sem); + ret = __btrfs_find_all_roots(trans, fs_info, bytenr, time_seq, roots); + if (!trans) + up_read(&fs_info->commit_root_sem); + return ret; +} + /* * this makes the path point to (inum INODE_ITEM ioff) */ @@ -1516,6 +1533,8 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, if (IS_ERR(trans)) return PTR_ERR(trans); btrfs_get_tree_mod_seq(fs_info, &tree_mod_seq_elem); + } else { + down_read(&fs_info->commit_root_sem); } ret = btrfs_find_all_leafs(trans, fs_info, extent_item_objectid, @@ -1526,8 +1545,8 @@ int iterate_extent_inodes(struct btrfs_fs_info *fs_info, ULIST_ITER_INIT(&ref_uiter); while (!ret && (ref_node = ulist_next(refs, &ref_uiter))) { - ret = btrfs_find_all_roots(trans, fs_info, ref_node->val, - tree_mod_seq_elem.seq, &roots); + ret = __btrfs_find_all_roots(trans, fs_info, ref_node->val, + tree_mod_seq_elem.seq, &roots); if (ret) break; ULIST_ITER_INIT(&root_uiter); @@ -1549,6 +1568,8 @@ out: if (!search_commit_root) { btrfs_put_tree_mod_seq(fs_info, &tree_mod_seq_elem); btrfs_end_transaction(trans, fs_info->extent_root); + } else { + up_read(&fs_info->commit_root_sem); } return ret; diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 88d1b1e..9d89c16 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -5360,7 +5360,6 @@ int btrfs_compare_trees(struct btrfs_root *left_root, { int ret; int cmp; - struct btrfs_trans_handle *trans = NULL; struct btrfs_path *left_path = NULL; struct btrfs_path *right_path = NULL; struct btrfs_key left_key; @@ -5378,9 +5377,6 @@ int btrfs_compare_trees(struct btrfs_root *left_root, u64 right_blockptr; u64 left_gen; u64 right_gen; - u64 left_start_ctransid; - u64 right_start_ctransid; - u64 ctransid; left_path = btrfs_alloc_path(); if (!left_path) { @@ -5404,21 +5400,6 @@ int btrfs_compare_trees(struct btrfs_root *left_root, right_path->search_commit_root = 1; right_path->skip_locking = 1; - spin_lock(&left_root->root_item_lock); - left_start_ctransid = btrfs_root_ctransid(&left_root->root_item); - spin_unlock(&left_root->root_item_lock); - - spin_lock(&right_root->root_item_lock); - right_start_ctransid = btrfs_root_ctransid(&right_root->root_item); - spin_unlock(&right_root->root_item_lock); - - trans = btrfs_join_transaction(left_root); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - trans = NULL; - goto out; - } - /* * Strategy: Go to the first items of both trees. Then do * @@ -5482,67 +5463,6 @@ int btrfs_compare_trees(struct btrfs_root *left_root, advance_left = advance_right = 0; while (1) { - /* - * We need to make sure the transaction does not get committed - * while we do anything on commit roots. This means, we need to - * join and leave transactions for every item that we process. - */ - if (trans && btrfs_should_end_transaction(trans, left_root)) { - btrfs_release_path(left_path); - btrfs_release_path(right_path); - - ret = btrfs_end_transaction(trans, left_root); - trans = NULL; - if (ret < 0) - goto out; - } - /* now rejoin the transaction */ - if (!trans) { - trans = btrfs_join_transaction(left_root); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - trans = NULL; - goto out; - } - - spin_lock(&left_root->root_item_lock); - ctransid = btrfs_root_ctransid(&left_root->root_item); - spin_unlock(&left_root->root_item_lock); - if (ctransid != left_start_ctransid) - left_start_ctransid = 0; - - spin_lock(&right_root->root_item_lock); - ctransid = btrfs_root_ctransid(&right_root->root_item); - spin_unlock(&right_root->root_item_lock); - if (ctransid != right_start_ctransid) - right_start_ctransid = 0; - - if (!left_start_ctransid || !right_start_ctransid) { - WARN(1, KERN_WARNING - "BTRFS: btrfs_compare_tree detected " - "a change in one of the trees while " - "iterating. This is probably a " - "bug.\n"); - ret = -EIO; - goto out; - } - - /* - * the commit root may have changed, so start again - * where we stopped - */ - left_path->lowest_level = left_level; - right_path->lowest_level = right_level; - ret = btrfs_search_slot(NULL, left_root, - &left_key, left_path, 0, 0); - if (ret < 0) - goto out; - ret = btrfs_search_slot(NULL, right_root, - &right_key, right_path, 0, 0); - if (ret < 0) - goto out; - } - if (advance_left && !left_end_reached) { ret = tree_advance(left_root, left_path, &left_level, left_root_level, @@ -5672,14 +5592,6 @@ out: btrfs_free_path(left_path); btrfs_free_path(right_path); kfree(tmp_buf); - - if (trans) { - if (!ret) - ret = btrfs_end_transaction(trans, left_root); - else - btrfs_end_transaction(trans, left_root); - } - return ret; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 2a9d32e..4253ab2 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1440,7 +1440,7 @@ struct btrfs_fs_info { */ struct mutex ordered_extent_flush_mutex; - struct rw_semaphore extent_commit_sem; + struct rw_semaphore commit_root_sem; struct rw_semaphore cleanup_work_sem; @@ -1711,7 +1711,6 @@ struct btrfs_root { struct btrfs_block_rsv *block_rsv; /* free ino cache stuff */ - struct mutex fs_commit_mutex; struct btrfs_free_space_ctl *free_ino_ctl; enum btrfs_caching_type cached; spinlock_t cache_lock; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 98fe701..6d1ac7d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1567,7 +1567,6 @@ int btrfs_init_fs_root(struct btrfs_root *root) root->subv_writers = writers; btrfs_init_free_ino_ctl(root); - mutex_init(&root->fs_commit_mutex); spin_lock_init(&root->cache_lock); init_waitqueue_head(&root->cache_wait); @@ -2345,7 +2344,7 @@ int open_ctree(struct super_block *sb, mutex_init(&fs_info->transaction_kthread_mutex); mutex_init(&fs_info->cleaner_mutex); mutex_init(&fs_info->volume_mutex); - init_rwsem(&fs_info->extent_commit_sem); + init_rwsem(&fs_info->commit_root_sem); init_rwsem(&fs_info->cleanup_work_sem); init_rwsem(&fs_info->subvol_sem); sema_init(&fs_info->uuid_tree_rescan_sem, 1); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index e09db2c..4d2508b 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -419,7 +419,7 @@ static noinline void caching_thread(struct btrfs_work *work) again: mutex_lock(&caching_ctl->mutex); /* need to make sure the commit_root doesn't disappear */ - down_read(&fs_info->extent_commit_sem); + down_read(&fs_info->commit_root_sem); next: ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0); @@ -443,10 +443,10 @@ next: break; if (need_resched() || - rwsem_is_contended(&fs_info->extent_commit_sem)) { + rwsem_is_contended(&fs_info->commit_root_sem)) { caching_ctl->progress = last; btrfs_release_path(path); - up_read(&fs_info->extent_commit_sem); + up_read(&fs_info->commit_root_sem); mutex_unlock(&caching_ctl->mutex); cond_resched(); goto again; @@ -513,7 +513,7 @@ next: err: btrfs_free_path(path); - up_read(&fs_info->extent_commit_sem); + up_read(&fs_info->commit_root_sem); free_excluded_extents(extent_root, block_group); @@ -633,10 +633,10 @@ static int cache_block_group(struct btrfs_block_group_cache *cache, return 0; } - down_write(&fs_info->extent_commit_sem); + down_write(&fs_info->commit_root_sem); atomic_inc(&caching_ctl->count); list_add_tail(&caching_ctl->list, &fs_info->caching_block_groups); - up_write(&fs_info->extent_commit_sem); + up_write(&fs_info->commit_root_sem); btrfs_get_block_group(cache); @@ -5471,7 +5471,7 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, struct btrfs_block_group_cache *cache; struct btrfs_space_info *space_info; - down_write(&fs_info->extent_commit_sem); + down_write(&fs_info->commit_root_sem); list_for_each_entry_safe(caching_ctl, next, &fs_info->caching_block_groups, list) { @@ -5490,7 +5490,7 @@ void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans, else fs_info->pinned_extents = &fs_info->freed_extents[0]; - up_write(&fs_info->extent_commit_sem); + up_write(&fs_info->commit_root_sem); list_for_each_entry_rcu(space_info, &fs_info->space_info, list) percpu_counter_set(&space_info->total_bytes_pinned, 0); @@ -8256,14 +8256,14 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info) struct btrfs_caching_control *caching_ctl; struct rb_node *n; - down_write(&info->extent_commit_sem); + down_write(&info->commit_root_sem); while (!list_empty(&info->caching_block_groups)) { caching_ctl = list_entry(info->caching_block_groups.next, struct btrfs_caching_control, list); list_del(&caching_ctl->list); put_caching_control(caching_ctl); } - up_write(&info->extent_commit_sem); + up_write(&info->commit_root_sem); spin_lock(&info->block_group_cache_lock); while ((n = rb_last(&info->block_group_cache_tree)) != NULL) { diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c index ab485e5..cc8ca193 100644 --- a/fs/btrfs/inode-map.c +++ b/fs/btrfs/inode-map.c @@ -55,7 +55,7 @@ static int caching_kthread(void *data) key.type = BTRFS_INODE_ITEM_KEY; again: /* need to make sure the commit_root doesn't disappear */ - mutex_lock(&root->fs_commit_mutex); + down_read(&fs_info->commit_root_sem); ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) @@ -88,7 +88,7 @@ again: btrfs_item_key_to_cpu(leaf, &key, 0); btrfs_release_path(path); root->cache_progress = last; - mutex_unlock(&root->fs_commit_mutex); + up_read(&fs_info->commit_root_sem); schedule_timeout(1); goto again; } else @@ -127,7 +127,7 @@ next: btrfs_unpin_free_ino(root); out: wake_up(&root->cache_wait); - mutex_unlock(&root->fs_commit_mutex); + up_read(&fs_info->commit_root_sem); btrfs_free_path(path); @@ -223,11 +223,11 @@ again: * or the caching work is done. */ - mutex_lock(&root->fs_commit_mutex); + down_write(&root->fs_info->commit_root_sem); spin_lock(&root->cache_lock); if (root->cached == BTRFS_CACHE_FINISHED) { spin_unlock(&root->cache_lock); - mutex_unlock(&root->fs_commit_mutex); + up_write(&root->fs_info->commit_root_sem); goto again; } spin_unlock(&root->cache_lock); @@ -240,7 +240,7 @@ again: else __btrfs_add_free_space(pinned, objectid, 1); - mutex_unlock(&root->fs_commit_mutex); + up_write(&root->fs_info->commit_root_sem); } } @@ -250,7 +250,7 @@ again: * and others will just be dropped, because the commit root we were * searching has changed. * - * Must be called with root->fs_commit_mutex held + * Must be called with root->fs_info->commit_root_sem held */ void btrfs_unpin_free_ino(struct btrfs_root *root) { diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index d00534b..6b5f136 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1268,8 +1268,10 @@ static int find_extent_clone(struct send_ctx *sctx, } logical = disk_byte + btrfs_file_extent_offset(eb, fi); + down_read(&sctx->send_root->fs_info->commit_root_sem); ret = extent_from_logical(sctx->send_root->fs_info, disk_byte, tmp_path, &found_key, &flags); + up_read(&sctx->send_root->fs_info->commit_root_sem); btrfs_release_path(tmp_path); if (ret < 0) @@ -5367,57 +5369,21 @@ out: static int full_send_tree(struct send_ctx *sctx) { int ret; - struct btrfs_trans_handle *trans = NULL; struct btrfs_root *send_root = sctx->send_root; struct btrfs_key key; struct btrfs_key found_key; struct btrfs_path *path; struct extent_buffer *eb; int slot; - u64 start_ctransid; - u64 ctransid; path = alloc_path_for_send(); if (!path) return -ENOMEM; - spin_lock(&send_root->root_item_lock); - start_ctransid = btrfs_root_ctransid(&send_root->root_item); - spin_unlock(&send_root->root_item_lock); - key.objectid = BTRFS_FIRST_FREE_OBJECTID; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; -join_trans: - /* - * We need to make sure the transaction does not get committed - * while we do anything on commit roots. Join a transaction to prevent - * this. - */ - trans = btrfs_join_transaction(send_root); - if (IS_ERR(trans)) { - ret = PTR_ERR(trans); - trans = NULL; - goto out; - } - - /* - * Make sure the tree has not changed after re-joining. We detect this - * by comparing start_ctransid and ctransid. They should always match. - */ - spin_lock(&send_root->root_item_lock); - ctransid = btrfs_root_ctransid(&send_root->root_item); - spin_unlock(&send_root->root_item_lock); - - if (ctransid != start_ctransid) { - WARN(1, KERN_WARNING "BTRFS: the root that you're trying to " - "send was modified in between. This is " - "probably a bug.\n"); - ret = -EIO; - goto out; - } - ret = btrfs_search_slot_for_read(send_root, &key, path, 1, 0); if (ret < 0) goto out; @@ -5425,19 +5391,6 @@ join_trans: goto out_finish; while (1) { - /* - * When someone want to commit while we iterate, end the - * joined transaction and rejoin. - */ - if (btrfs_should_end_transaction(trans, send_root)) { - ret = btrfs_end_transaction(trans, send_root); - trans = NULL; - if (ret < 0) - goto out; - btrfs_release_path(path); - goto join_trans; - } - eb = path->nodes[0]; slot = path->slots[0]; btrfs_item_key_to_cpu(eb, &found_key, slot); @@ -5465,12 +5418,6 @@ out_finish: out: btrfs_free_path(path); - if (trans) { - if (!ret) - ret = btrfs_end_transaction(trans, send_root); - else - btrfs_end_transaction(trans, send_root); - } return ret; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 038177c..7579f6d 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -75,10 +75,21 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction) } } -static noinline void switch_commit_root(struct btrfs_root *root) +static noinline void switch_commit_roots(struct btrfs_transaction *trans, + struct btrfs_fs_info *fs_info) { - free_extent_buffer(root->commit_root); - root->commit_root = btrfs_root_node(root); + struct btrfs_root *root, *tmp; + + down_write(&fs_info->commit_root_sem); + list_for_each_entry_safe(root, tmp, &trans->switch_commits, + dirty_list) { + list_del_init(&root->dirty_list); + free_extent_buffer(root->commit_root); + root->commit_root = btrfs_root_node(root); + if (is_fstree(root->objectid)) + btrfs_unpin_free_ino(root); + } + up_write(&fs_info->commit_root_sem); } static inline void extwriter_counter_inc(struct btrfs_transaction *trans, @@ -208,6 +219,7 @@ loop: INIT_LIST_HEAD(&cur_trans->pending_snapshots); INIT_LIST_HEAD(&cur_trans->ordered_operations); INIT_LIST_HEAD(&cur_trans->pending_chunks); + INIT_LIST_HEAD(&cur_trans->switch_commits); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(&cur_trans->dirty_pages, fs_info->btree_inode->i_mapping); @@ -920,9 +932,6 @@ static int update_cowonly_root(struct btrfs_trans_handle *trans, return ret; } - if (root != root->fs_info->extent_root) - switch_commit_root(root); - return 0; } @@ -978,15 +987,16 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans, list_del_init(next); root = list_entry(next, struct btrfs_root, dirty_list); + if (root != fs_info->extent_root) + list_add_tail(&root->dirty_list, + &trans->transaction->switch_commits); ret = update_cowonly_root(trans, root); if (ret) return ret; } - down_write(&fs_info->extent_commit_sem); - switch_commit_root(fs_info->extent_root); - up_write(&fs_info->extent_commit_sem); - + list_add_tail(&fs_info->extent_root->dirty_list, + &trans->transaction->switch_commits); btrfs_after_dev_replace_commit(fs_info); return 0; @@ -1043,11 +1053,8 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans, smp_wmb(); if (root->commit_root != root->node) { - mutex_lock(&root->fs_commit_mutex); - switch_commit_root(root); - btrfs_unpin_free_ino(root); - mutex_unlock(&root->fs_commit_mutex); - + list_add_tail(&root->dirty_list, + &trans->transaction->switch_commits); btrfs_set_root_node(&root->root_item, root->node); } @@ -1858,11 +1865,15 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, btrfs_set_root_node(&root->fs_info->tree_root->root_item, root->fs_info->tree_root->node); - switch_commit_root(root->fs_info->tree_root); + list_add_tail(&root->fs_info->tree_root->dirty_list, + &cur_trans->switch_commits); btrfs_set_root_node(&root->fs_info->chunk_root->root_item, root->fs_info->chunk_root->node); - switch_commit_root(root->fs_info->chunk_root); + list_add_tail(&root->fs_info->chunk_root->dirty_list, + &cur_trans->switch_commits); + + switch_commit_roots(cur_trans, root->fs_info); assert_qgroups_uptodate(trans); update_super_roots(root); diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 2bcba89..b57b924 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -57,6 +57,7 @@ struct btrfs_transaction { struct list_head pending_snapshots; struct list_head ordered_operations; struct list_head pending_chunks; + struct list_head switch_commits; struct btrfs_delayed_ref_root delayed_refs; int aborted; }; -- cgit v1.1 From 3f8a18cc53bd1be26eb5b5247e1386ad0e21b623 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 28 Mar 2014 17:16:01 -0400 Subject: Btrfs: hold the commit_root_sem when getting the commit root during send We currently rely too heavily on roots being read-only to save us from just accessing root->commit_root. We can easily balance blocks out from underneath a read only root, so to save us from getting screwed make sure we only access root->commit_root under the commit root sem. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/ctree.c | 6 ++++++ fs/btrfs/ctree.h | 1 + fs/btrfs/send.c | 48 ++++++++++++++++++++++++++++++++---------------- 3 files changed, 39 insertions(+), 16 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 9d89c16..1bcfcdb 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2769,9 +2769,13 @@ again: * the commit roots are read only * so we always do read locks */ + if (p->need_commit_sem) + down_read(&root->fs_info->commit_root_sem); b = root->commit_root; extent_buffer_get(b); level = btrfs_header_level(b); + if (p->need_commit_sem) + up_read(&root->fs_info->commit_root_sem); if (!p->skip_locking) btrfs_tree_read_lock(b); } else { @@ -5436,6 +5440,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root, * the right if possible or go up and right. */ + down_read(&left_root->fs_info->commit_root_sem); left_level = btrfs_header_level(left_root->commit_root); left_root_level = left_level; left_path->nodes[left_level] = left_root->commit_root; @@ -5445,6 +5450,7 @@ int btrfs_compare_trees(struct btrfs_root *left_root, right_root_level = right_level; right_path->nodes[right_level] = right_root->commit_root; extent_buffer_get(right_path->nodes[right_level]); + up_read(&left_root->fs_info->commit_root_sem); if (left_level == 0) btrfs_item_key_to_cpu(left_path->nodes[left_level], diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 4253ab2..d8a669e 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -609,6 +609,7 @@ struct btrfs_path { unsigned int skip_locking:1; unsigned int leave_spinning:1; unsigned int search_commit_root:1; + unsigned int need_commit_sem:1; }; /* diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 6b5f136..ab34a23 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -493,6 +493,7 @@ static struct btrfs_path *alloc_path_for_send(void) return NULL; path->search_commit_root = 1; path->skip_locking = 1; + path->need_commit_sem = 1; return path; } @@ -771,29 +772,22 @@ out: /* * Helper function to retrieve some fields from an inode item. */ -static int get_inode_info(struct btrfs_root *root, - u64 ino, u64 *size, u64 *gen, - u64 *mode, u64 *uid, u64 *gid, - u64 *rdev) +static int __get_inode_info(struct btrfs_root *root, struct btrfs_path *path, + u64 ino, u64 *size, u64 *gen, u64 *mode, u64 *uid, + u64 *gid, u64 *rdev) { int ret; struct btrfs_inode_item *ii; struct btrfs_key key; - struct btrfs_path *path; - - path = alloc_path_for_send(); - if (!path) - return -ENOMEM; key.objectid = ino; key.type = BTRFS_INODE_ITEM_KEY; key.offset = 0; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); - if (ret < 0) - goto out; if (ret) { - ret = -ENOENT; - goto out; + if (ret > 0) + ret = -ENOENT; + return ret; } ii = btrfs_item_ptr(path->nodes[0], path->slots[0], @@ -811,7 +805,22 @@ static int get_inode_info(struct btrfs_root *root, if (rdev) *rdev = btrfs_inode_rdev(path->nodes[0], ii); -out: + return ret; +} + +static int get_inode_info(struct btrfs_root *root, + u64 ino, u64 *size, u64 *gen, + u64 *mode, u64 *uid, u64 *gid, + u64 *rdev) +{ + struct btrfs_path *path; + int ret; + + path = alloc_path_for_send(); + if (!path) + return -ENOMEM; + ret = __get_inode_info(root, path, ino, size, gen, mode, uid, gid, + rdev); btrfs_free_path(path); return ret; } @@ -1085,6 +1094,7 @@ out: struct backref_ctx { struct send_ctx *sctx; + struct btrfs_path *path; /* number of total found references */ u64 found; @@ -1155,8 +1165,9 @@ static int __iterate_backrefs(u64 ino, u64 offset, u64 root, void *ctx_) * There are inodes that have extents that lie behind its i_size. Don't * accept clones from these extents. */ - ret = get_inode_info(found->root, ino, &i_size, NULL, NULL, NULL, NULL, - NULL); + ret = __get_inode_info(found->root, bctx->path, ino, &i_size, NULL, NULL, + NULL, NULL, NULL); + btrfs_release_path(bctx->path); if (ret < 0) return ret; @@ -1235,12 +1246,17 @@ static int find_extent_clone(struct send_ctx *sctx, if (!tmp_path) return -ENOMEM; + /* We only use this path under the commit sem */ + tmp_path->need_commit_sem = 0; + backref_ctx = kmalloc(sizeof(*backref_ctx), GFP_NOFS); if (!backref_ctx) { ret = -ENOMEM; goto out; } + backref_ctx->path = tmp_path; + if (data_offset >= ino_size) { /* * There may be extents that lie behind the file's size. -- cgit v1.1 From ed55b6ac077fe7f9c6490ff55172c4b563562d7c Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Wed, 26 Mar 2014 14:11:26 -0400 Subject: btrfs: fix lockdep warning with reclaim lock inversion When encountering memory pressure, testers have run into the following lockdep warning. It was caused by __link_block_group calling kobject_add with the groups_sem held. kobject_add calls kvasprintf with GFP_KERNEL, which gets us into reclaim context. The kobject doesn't actually need to be added under the lock -- it just needs to ensure that it's only added for the first block group to be linked. ========================================================= [ INFO: possible irq lock inversion dependency detected ] 3.14.0-rc8-default #1 Not tainted --------------------------------------------------------- kswapd0/169 just changed the state of lock: (&delayed_node->mutex){+.+.-.}, at: [] __btrfs_release_delayed_node+0x3a/0x200 [btrfs] but this lock took another, RECLAIM_FS-unsafe lock in the past: (&found->groups_sem){+++++.} and interrupts could create inverse lock ordering between them. other info that might help us debug this: Possible interrupt unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&found->groups_sem); local_irq_disable(); lock(&delayed_node->mutex); lock(&found->groups_sem); lock(&delayed_node->mutex); *** DEADLOCK *** 2 locks held by kswapd0/169: #0: (shrinker_rwsem){++++..}, at: [] shrink_slab+0x3a/0x160 #1: (&type->s_umount_key#27){++++..}, at: [] grab_super_passive+0x3f/0x90 Signed-off-by: Jeff Mahoney Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 4d2508b..1341163 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -8337,9 +8337,15 @@ static void __link_block_group(struct btrfs_space_info *space_info, struct btrfs_block_group_cache *cache) { int index = get_block_group_index(cache); + bool first = false; down_write(&space_info->groups_sem); - if (list_empty(&space_info->block_groups[index])) { + if (list_empty(&space_info->block_groups[index])) + first = true; + list_add_tail(&cache->list, &space_info->block_groups[index]); + up_write(&space_info->groups_sem); + + if (first) { struct kobject *kobj = &space_info->block_group_kobjs[index]; int ret; @@ -8351,8 +8357,6 @@ static void __link_block_group(struct btrfs_space_info *space_info, kobject_put(&space_info->kobj); } } - list_add_tail(&cache->list, &space_info->block_groups[index]); - up_write(&space_info->groups_sem); } static struct btrfs_block_group_cache * -- cgit v1.1 From 60999ca4b4033ee199702a4ceb9f5b801f7962b9 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Wed, 26 Mar 2014 18:26:36 +0100 Subject: btrfs: make device scan less noisy Print the message only when the device is seen for the first time. Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/volumes.c | 35 ++++++++++++++++++++++++----------- 1 file changed, 24 insertions(+), 11 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b4660c4..558f46c 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -448,6 +448,14 @@ static void pending_bios_fn(struct btrfs_work *work) run_scheduled_bios(device); } +/* + * Add new device to list of registered devices + * + * Returns: + * 1 - first time device is seen + * 0 - device already known + * < 0 - error + */ static noinline int device_list_add(const char *path, struct btrfs_super_block *disk_super, u64 devid, struct btrfs_fs_devices **fs_devices_ret) @@ -455,6 +463,7 @@ static noinline int device_list_add(const char *path, struct btrfs_device *device; struct btrfs_fs_devices *fs_devices; struct rcu_string *name; + int ret = 0; u64 found_transid = btrfs_super_generation(disk_super); fs_devices = find_fsid(disk_super->fsid); @@ -495,6 +504,7 @@ static noinline int device_list_add(const char *path, fs_devices->num_devices++; mutex_unlock(&fs_devices->device_list_mutex); + ret = 1; device->fs_devices = fs_devices; } else if (!device->name || strcmp(device->name->str, path)) { name = rcu_string_strdup(path, GFP_NOFS); @@ -513,7 +523,8 @@ static noinline int device_list_add(const char *path, fs_devices->latest_trans = found_transid; } *fs_devices_ret = fs_devices; - return 0; + + return ret; } static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig) @@ -910,17 +921,19 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, transid = btrfs_super_generation(disk_super); total_devices = btrfs_super_num_devices(disk_super); - if (disk_super->label[0]) { - if (disk_super->label[BTRFS_LABEL_SIZE - 1]) - disk_super->label[BTRFS_LABEL_SIZE - 1] = '\0'; - printk(KERN_INFO "BTRFS: device label %s ", disk_super->label); - } else { - printk(KERN_INFO "BTRFS: device fsid %pU ", disk_super->fsid); - } - - printk(KERN_CONT "devid %llu transid %llu %s\n", devid, transid, path); - ret = device_list_add(path, disk_super, devid, fs_devices_ret); + if (ret > 0) { + if (disk_super->label[0]) { + if (disk_super->label[BTRFS_LABEL_SIZE - 1]) + disk_super->label[BTRFS_LABEL_SIZE - 1] = '\0'; + printk(KERN_INFO "BTRFS: device label %s ", disk_super->label); + } else { + printk(KERN_INFO "BTRFS: device fsid %pU ", disk_super->fsid); + } + + printk(KERN_CONT "devid %llu transid %llu %s\n", devid, transid, path); + ret = 0; + } if (!ret && fs_devices_ret) (*fs_devices_ret)->total_devices = total_devices; -- cgit v1.1 From 3ac0d7b96a268a98bd474cab8bce3a9f125aaccf Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Thu, 27 Mar 2014 02:51:58 +0000 Subject: btrfs: Change the expanding write sequence to fix snapshot related bug. When testing fsstress with snapshot making background, some snapshot following problem. Snapshot 270: inode 323: size 0 Snapshot 271: inode 323: size 349145 |-------Hole---|---------Empty gap-------|-------Hole-----| 0 122880 172032 349145 Snapshot 272: inode 323: size 349145 |-------Hole---|------------Data---------|-------Hole-----| 0 122880 172032 349145 The fsstress operation on inode 323 is the following: write: offset 126832 len 43124 truncate: size 349145 Since the write with offset is consist of 2 operations: 1. punch hole 2. write data Hole punching is faster than data write, so hole punching in write and truncate is done first and then buffered write, so the snapshot 271 got empty gap, which will not pass btrfsck. To fix the bug, this patch will change the write sequence which will first punch a hole covering the write end if a hole is needed. Reported-by: Gui Hecheng Signed-off-by: Qu Wenruo Signed-off-by: Chris Mason --- fs/btrfs/file.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 036f506c..23f6a9d 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1727,6 +1727,7 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, struct btrfs_root *root = BTRFS_I(inode)->root; loff_t *ppos = &iocb->ki_pos; u64 start_pos; + u64 end_pos; ssize_t num_written = 0; ssize_t err = 0; size_t count, ocount; @@ -1781,7 +1782,9 @@ static ssize_t btrfs_file_aio_write(struct kiocb *iocb, start_pos = round_down(pos, root->sectorsize); if (start_pos > i_size_read(inode)) { - err = btrfs_cont_expand(inode, i_size_read(inode), start_pos); + /* Expand hole size to cover write data, preventing empty gap */ + end_pos = round_up(pos + iov->iov_len, root->sectorsize); + err = btrfs_cont_expand(inode, i_size_read(inode), end_pos); if (err) { mutex_unlock(&inode->i_mutex); goto out; -- cgit v1.1 From e9894fd3e3b3c5ecaa096d32c2d2b79db8e64433 Mon Sep 17 00:00:00 2001 From: Wang Shilong Date: Thu, 27 Mar 2014 11:12:25 +0800 Subject: Btrfs: fix snapshot vs nocow writting While running fsstress and snapshots concurrently, we will hit something like followings: Thread 1 Thread 2 |->fallocate |->write pages |->join transaction |->add ordered extent |->end transaction |->flushing data |->creating pending snapshots |->write data into src root's fallocated space After above work flows finished, we will get a state that source and snapshot root share same space, but source root have written data into fallocated space, this will make fsck fail to verify checksums for snapshot root's preallocating file extent data.Nocow writting also has this same problem. Fix this problem by syncing snapshots with nocow writting: 1.for nocow writting,if there are pending snapshots, we will fall into COW way. 2.if there are pending nocow writes, snapshots for this root will be blocked until nocow writting finish. Reported-by: Gui Hecheng Signed-off-by: Wang Shilong Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 0ec8766..251db68 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -1271,6 +1271,15 @@ next_slot: disk_bytenr += cur_offset - found_key.offset; num_bytes = min(end + 1, extent_end) - cur_offset; /* + * if there are pending snapshots for this root, + * we fall into common COW way. + */ + if (!nolock) { + err = btrfs_start_nocow_write(root); + if (!err) + goto out_check; + } + /* * force cow if csum exists in the range. * this ensure that csum for a given extent are * either valid or do not exist. @@ -1289,6 +1298,8 @@ next_slot: out_check: if (extent_end <= start) { path->slots[0]++; + if (!nolock && nocow) + btrfs_end_nocow_write(root); goto next_slot; } if (!nocow) { @@ -1306,8 +1317,11 @@ out_check: ret = cow_file_range(inode, locked_page, cow_start, found_key.offset - 1, page_started, nr_written, 1); - if (ret) + if (ret) { + if (!nolock && nocow) + btrfs_end_nocow_write(root); goto error; + } cow_start = (u64)-1; } @@ -1354,8 +1368,11 @@ out_check: BTRFS_DATA_RELOC_TREE_OBJECTID) { ret = btrfs_reloc_clone_csums(inode, cur_offset, num_bytes); - if (ret) + if (ret) { + if (!nolock && nocow) + btrfs_end_nocow_write(root); goto error; + } } extent_clear_unlock_delalloc(inode, cur_offset, @@ -1363,6 +1380,8 @@ out_check: locked_page, EXTENT_LOCKED | EXTENT_DELALLOC, PAGE_UNLOCK | PAGE_SET_PRIVATE2); + if (!nolock && nocow) + btrfs_end_nocow_write(root); cur_offset = extent_end; if (cur_offset > end) break; -- cgit v1.1 From 84dbeb87d1439d3a6614c95e82429542434bafb9 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 28 Mar 2014 11:06:00 +0300 Subject: Btrfs: kmalloc() doesn't return an ERR_PTR The error handling was copy and pasted from memdup_user(). It should be checking for NULL obviously. Fixes: abccd00f8af2 ('btrfs: Fix 32/64-bit problem with BTRFS_SET_RECEIVED_SUBVOL ioctl') Signed-off-by: Dan Carpenter Signed-off-by: Chris Mason --- fs/btrfs/ioctl.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 6778fa3..5962236 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4553,9 +4553,8 @@ static long btrfs_ioctl_set_received_subvol_32(struct file *file, } args64 = kmalloc(sizeof(*args64), GFP_NOFS); - if (IS_ERR(args64)) { - ret = PTR_ERR(args64); - args64 = NULL; + if (!args64) { + ret = -ENOMEM; goto out; } -- cgit v1.1 From 766b5e5ae78dd04a93a275690a49e23d7dcb1f39 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Sun, 30 Mar 2014 23:02:53 +0100 Subject: Btrfs: send, fix data corruption due to incorrect hole detection During an incremental send, when we finish processing an inode (corresponding to a regular file) we would assume the gap between the end of the last processed file extent and the file's size corresponded to a file hole, and therefore incorrectly send a bunch of zero bytes to overwrite that region in the file. This affects only kernel 3.14. Reproducer: mkfs.btrfs -f /dev/sdc mount /dev/sdc /mnt xfs_io -f -c "falloc -k 0 268435456" /mnt/foo btrfs subvolume snapshot -r /mnt /mnt/mysnap0 xfs_io -c "pwrite -S 0x01 -b 9216 16190218 9216" /mnt/foo xfs_io -c "pwrite -S 0x02 -b 1121 198720104 1121" /mnt/foo xfs_io -c "pwrite -S 0x05 -b 9216 107887439 9216" /mnt/foo xfs_io -c "pwrite -S 0x06 -b 9216 225520207 9216" /mnt/foo xfs_io -c "pwrite -S 0x07 -b 67584 102138300 67584" /mnt/foo xfs_io -c "pwrite -S 0x08 -b 7000 94897484 7000" /mnt/foo xfs_io -c "pwrite -S 0x09 -b 113664 245083212 113664" /mnt/foo xfs_io -c "pwrite -S 0x10 -b 123 17937788 123" /mnt/foo xfs_io -c "pwrite -S 0x11 -b 39936 229573311 39936" /mnt/foo xfs_io -c "pwrite -S 0x12 -b 67584 174792222 67584" /mnt/foo xfs_io -c "pwrite -S 0x13 -b 9216 249253213 9216" /mnt/foo xfs_io -c "pwrite -S 0x16 -b 67584 150046083 67584" /mnt/foo xfs_io -c "pwrite -S 0x17 -b 39936 118246040 39936" /mnt/foo xfs_io -c "pwrite -S 0x18 -b 67584 215965442 67584" /mnt/foo xfs_io -c "pwrite -S 0x19 -b 33792 97096725 33792" /mnt/foo xfs_io -c "pwrite -S 0x20 -b 125952 166300596 125952" /mnt/foo xfs_io -c "pwrite -S 0x21 -b 123 1078957 123" /mnt/foo xfs_io -c "pwrite -S 0x25 -b 9216 212044492 9216" /mnt/foo xfs_io -c "pwrite -S 0x26 -b 7000 265037146 7000" /mnt/foo xfs_io -c "pwrite -S 0x27 -b 42757 215922685 42757" /mnt/foo xfs_io -c "pwrite -S 0x28 -b 7000 69865411 7000" /mnt/foo xfs_io -c "pwrite -S 0x29 -b 67584 67948958 67584" /mnt/foo xfs_io -c "pwrite -S 0x30 -b 39936 266967019 39936" /mnt/foo xfs_io -c "pwrite -S 0x31 -b 1121 19582453 1121" /mnt/foo xfs_io -c "pwrite -S 0x32 -b 17408 257710255 17408" /mnt/foo xfs_io -c "pwrite -S 0x33 -b 39936 3895518 39936" /mnt/foo xfs_io -c "pwrite -S 0x34 -b 125952 12045847 125952" /mnt/foo xfs_io -c "pwrite -S 0x35 -b 17408 19156379 17408" /mnt/foo xfs_io -c "pwrite -S 0x36 -b 39936 50160066 39936" /mnt/foo xfs_io -c "pwrite -S 0x37 -b 113664 9549793 113664" /mnt/foo xfs_io -c "pwrite -S 0x38 -b 105472 94391506 105472" /mnt/foo xfs_io -c "pwrite -S 0x39 -b 23552 143632863 23552" /mnt/foo xfs_io -c "pwrite -S 0x40 -b 39936 241283845 39936" /mnt/foo xfs_io -c "pwrite -S 0x41 -b 113664 199937606 113664" /mnt/foo xfs_io -c "pwrite -S 0x42 -b 67584 67380093 67584" /mnt/foo xfs_io -c "pwrite -S 0x43 -b 67584 26793129 67584" /mnt/foo xfs_io -c "pwrite -S 0x44 -b 39936 14421913 39936" /mnt/foo xfs_io -c "pwrite -S 0x45 -b 123 253097405 123" /mnt/foo xfs_io -c "pwrite -S 0x46 -b 1121 128233424 1121" /mnt/foo xfs_io -c "pwrite -S 0x47 -b 105472 91577959 105472" /mnt/foo xfs_io -c "pwrite -S 0x48 -b 1121 7245381 1121" /mnt/foo xfs_io -c "pwrite -S 0x49 -b 113664 182414694 113664" /mnt/foo xfs_io -c "pwrite -S 0x50 -b 9216 32750608 9216" /mnt/foo xfs_io -c "pwrite -S 0x51 -b 67584 266546049 67584" /mnt/foo xfs_io -c "pwrite -S 0x52 -b 67584 87969398 67584" /mnt/foo xfs_io -c "pwrite -S 0x53 -b 9216 260848797 9216" /mnt/foo xfs_io -c "pwrite -S 0x54 -b 39936 119461243 39936" /mnt/foo xfs_io -c "pwrite -S 0x55 -b 7000 200178693 7000" /mnt/foo xfs_io -c "pwrite -S 0x56 -b 9216 243316029 9216" /mnt/foo xfs_io -c "pwrite -S 0x57 -b 7000 209658229 7000" /mnt/foo xfs_io -c "pwrite -S 0x58 -b 101376 179745192 101376" /mnt/foo xfs_io -c "pwrite -S 0x59 -b 9216 64012300 9216" /mnt/foo xfs_io -c "pwrite -S 0x60 -b 125952 181705139 125952" /mnt/foo xfs_io -c "pwrite -S 0x61 -b 23552 235737348 23552" /mnt/foo xfs_io -c "pwrite -S 0x62 -b 113664 106021355 113664" /mnt/foo xfs_io -c "pwrite -S 0x63 -b 67584 135753552 67584" /mnt/foo xfs_io -c "pwrite -S 0x64 -b 23552 95730888 23552" /mnt/foo xfs_io -c "pwrite -S 0x65 -b 11 17311415 11" /mnt/foo xfs_io -c "pwrite -S 0x66 -b 33792 120695553 33792" /mnt/foo xfs_io -c "pwrite -S 0x67 -b 9216 17164631 9216" /mnt/foo xfs_io -c "pwrite -S 0x68 -b 9216 136065853 9216" /mnt/foo xfs_io -c "pwrite -S 0x69 -b 67584 37752198 67584" /mnt/foo xfs_io -c "pwrite -S 0x70 -b 101376 189717473 101376" /mnt/foo xfs_io -c "pwrite -S 0x71 -b 7000 227463698 7000" /mnt/foo xfs_io -c "pwrite -S 0x72 -b 9216 12655137 9216" /mnt/foo xfs_io -c "pwrite -S 0x73 -b 7000 7488866 7000" /mnt/foo xfs_io -c "pwrite -S 0x74 -b 113664 87813649 113664" /mnt/foo xfs_io -c "pwrite -S 0x75 -b 33792 25802183 33792" /mnt/foo xfs_io -c "pwrite -S 0x76 -b 39936 93524024 39936" /mnt/foo xfs_io -c "pwrite -S 0x77 -b 33792 113336388 33792" /mnt/foo xfs_io -c "pwrite -S 0x78 -b 105472 184955320 105472" /mnt/foo xfs_io -c "pwrite -S 0x79 -b 101376 225691598 101376" /mnt/foo xfs_io -c "pwrite -S 0x80 -b 23552 77023155 23552" /mnt/foo xfs_io -c "pwrite -S 0x81 -b 11 201888192 11" /mnt/foo xfs_io -c "pwrite -S 0x82 -b 11 115332492 11" /mnt/foo xfs_io -c "pwrite -S 0x83 -b 67584 230278015 67584" /mnt/foo xfs_io -c "pwrite -S 0x84 -b 11 120589073 11" /mnt/foo xfs_io -c "pwrite -S 0x85 -b 125952 202207819 125952" /mnt/foo xfs_io -c "pwrite -S 0x86 -b 113664 86672080 113664" /mnt/foo xfs_io -c "pwrite -S 0x87 -b 17408 208459603 17408" /mnt/foo xfs_io -c "pwrite -S 0x88 -b 7000 73372211 7000" /mnt/foo xfs_io -c "pwrite -S 0x89 -b 7000 42252122 7000" /mnt/foo xfs_io -c "pwrite -S 0x90 -b 23552 46784881 23552" /mnt/foo xfs_io -c "pwrite -S 0x91 -b 101376 63172351 101376" /mnt/foo xfs_io -c "pwrite -S 0x92 -b 23552 59341931 23552" /mnt/foo xfs_io -c "pwrite -S 0x93 -b 39936 239599283 39936" /mnt/foo xfs_io -c "pwrite -S 0x94 -b 67584 175643105 67584" /mnt/foo xfs_io -c "pwrite -S 0x97 -b 23552 105534880 23552" /mnt/foo xfs_io -c "pwrite -S 0x98 -b 113664 8236844 113664" /mnt/foo xfs_io -c "pwrite -S 0x99 -b 125952 144489686 125952" /mnt/foo xfs_io -c "pwrite -S 0xa0 -b 7000 73273112 7000" /mnt/foo xfs_io -c "pwrite -S 0xa1 -b 125952 194580243 125952" /mnt/foo xfs_io -c "pwrite -S 0xa2 -b 123 56296779 123" /mnt/foo xfs_io -c "pwrite -S 0xa3 -b 11 233066845 11" /mnt/foo xfs_io -c "pwrite -S 0xa4 -b 39936 197727090 39936" /mnt/foo xfs_io -c "pwrite -S 0xa5 -b 101376 53579812 101376" /mnt/foo xfs_io -c "pwrite -S 0xa6 -b 9216 85669738 9216" /mnt/foo xfs_io -c "pwrite -S 0xa7 -b 125952 21266322 125952" /mnt/foo xfs_io -c "pwrite -S 0xa8 -b 23552 125726568 23552" /mnt/foo xfs_io -c "pwrite -S 0xa9 -b 9216 18423680 9216" /mnt/foo xfs_io -c "pwrite -S 0xb0 -b 1121 165901483 1121" /mnt/foo btrfs subvolume snapshot -r /mnt /mnt/mysnap1 xfs_io -c "pwrite -S 0xff -b 10 16190218 10" /mnt/foo btrfs subvolume snapshot -r /mnt /mnt/mysnap2 md5sum /mnt/foo # returns 79e53f1466bfc09fd82b450689e6119e md5sum /mnt/mysnap2/foo # returns 79e53f1466bfc09fd82b450689e6119e too btrfs send /mnt/mysnap1 -f /tmp/1.snap btrfs send -p /mnt/mysnap1 /mnt/mysnap2 -f /tmp/2.snap mkfs.btrfs -f /dev/sdc mount /dev/sdc /mnt btrfs receive /mnt -f /tmp/1.snap btrfs receive /mnt -f /tmp/2.snap md5sum /mnt/mysnap2/foo # returns 2bb414c5155767cedccd7063e51beabd !! A testcase for xfstests follows soon too. Signed-off-by: Filipe David Borba Manana Signed-off-by: Chris Mason --- fs/btrfs/send.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index ab34a23..e8e9f35 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -4986,7 +4986,9 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end) if (S_ISREG(sctx->cur_inode_mode)) { if (need_send_hole(sctx)) { - if (sctx->cur_inode_last_extent == (u64)-1) { + if (sctx->cur_inode_last_extent == (u64)-1 || + sctx->cur_inode_last_extent < + sctx->cur_inode_size) { ret = get_last_extent(sctx, (u64)-1); if (ret) goto out; -- cgit v1.1 From 9a40f1222a372de77344d85d31f8fe0e1c0e60e7 Mon Sep 17 00:00:00 2001 From: Gui Hecheng Date: Mon, 31 Mar 2014 18:03:25 +0800 Subject: btrfs: filter invalid arg for btrfs resize Originally following cmds will work: # btrfs fi resize -10A # btrfs fi resize -10Gaha Filter the arg by checking the return pointer of memparse. Signed-off-by: Gui Hecheng Signed-off-by: Chris Mason --- fs/btrfs/ioctl.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 5962236..05f8df8 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1472,6 +1472,7 @@ static noinline int btrfs_ioctl_resize(struct file *file, struct btrfs_trans_handle *trans; struct btrfs_device *device = NULL; char *sizestr; + char *retptr; char *devstr = NULL; int ret = 0; int mod = 0; @@ -1539,8 +1540,8 @@ static noinline int btrfs_ioctl_resize(struct file *file, mod = 1; sizestr++; } - new_size = memparse(sizestr, NULL); - if (new_size == 0) { + new_size = memparse(sizestr, &retptr); + if (*retptr != '\0' || new_size == 0) { ret = -EINVAL; goto out_free; } -- cgit v1.1 From c715e155c94ba0b3657820d676ec3c7213a5ce81 Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 31 Mar 2014 14:52:14 +0100 Subject: Btrfs: send, build path string only once in send_hole There's no point building the path string in each iteration of the send_hole loop, as it produces always the same string. Signed-off-by: Filipe David Borba Manana Signed-off-by: Chris Mason --- fs/btrfs/send.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index e8e9f35..1ac3ca9 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -4436,6 +4436,9 @@ static int send_hole(struct send_ctx *sctx, u64 end) p = fs_path_alloc(); if (!p) return -ENOMEM; + ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p); + if (ret < 0) + goto tlv_put_failure; memset(sctx->read_buf, 0, BTRFS_SEND_READ_SIZE); while (offset < end) { len = min_t(u64, end - offset, BTRFS_SEND_READ_SIZE); @@ -4443,9 +4446,6 @@ static int send_hole(struct send_ctx *sctx, u64 end) ret = begin_cmd(sctx, BTRFS_SEND_C_WRITE); if (ret < 0) break; - ret = get_cur_path(sctx, sctx->cur_ino, sctx->cur_inode_gen, p); - if (ret < 0) - break; TLV_PUT_PATH(sctx, BTRFS_SEND_A_PATH, p); TLV_PUT_U64(sctx, BTRFS_SEND_A_FILE_OFFSET, offset); TLV_PUT(sctx, BTRFS_SEND_A_DATA, sctx->read_buf, len); -- cgit v1.1 From c50d3e71c3d0378bcc9e116f48dab4148854a7bb Mon Sep 17 00:00:00 2001 From: Filipe Manana Date: Mon, 31 Mar 2014 14:53:25 +0100 Subject: Btrfs: more efficient io tree navigation on wait_extent_bit If we don't reschedule use rb_next to find the next extent state instead of a full tree search, which is more efficient and safe since we didn't release the io tree's lock. Signed-off-by: Filipe David Borba Manana Signed-off-by: Chris Mason --- fs/btrfs/extent_io.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index d35a3ca..0c43896 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -749,6 +749,7 @@ again: * our range starts */ node = tree_search(tree, start); +process_node: if (!node) break; @@ -769,7 +770,10 @@ again: if (start > end) break; - cond_resched_lock(&tree->lock); + if (!cond_resched_lock(&tree->lock)) { + node = rb_next(node); + goto process_node; + } } out: spin_unlock(&tree->lock); -- cgit v1.1 From 68bb462d42a963169bf7acbe106aae08c17129a5 Mon Sep 17 00:00:00 2001 From: Wang Shilong Date: Tue, 1 Apr 2014 18:01:42 +0800 Subject: Btrfs: don't compress for a small write To compress a small file range(<=blocksize) that is not an inline extent can not save disk space at all. skip it can save us some cpu time. This patch can also fix wrong setting nocompression flag for inode, say a case when @total_in is 4096, and then we get @total_compressed 52,because we do aligment to page cache size firstly, and then we get into conclusion @total_in=@total_compressed thus we will clear this inode's compression flag. An exception comes from inserting inline extent failure but we still have @total_compressed < @total_in,so we will still reset inode's flag, this is ok, because we don't have good compression effect. Signed-off-by: Wang Shilong Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 251db68..fdb8f44 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -394,6 +394,14 @@ static noinline int compress_file_range(struct inode *inode, (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size)) btrfs_add_inode_defrag(NULL, inode); + /* + * skip compression for a small file range(<=blocksize) that + * isn't an inline extent, since it dosen't save disk space at all. + */ + if ((end - start + 1) <= blocksize && + (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size)) + goto cleanup_and_bail_uncompressed; + actual_end = min_t(u64, isize, end + 1); again: will_compress = 0; -- cgit v1.1 From 3b080b2564287be91605bfd1d5ee985696e61d3c Mon Sep 17 00:00:00 2001 From: Wang Shilong Date: Tue, 1 Apr 2014 18:01:43 +0800 Subject: Btrfs: scrub raid56 stripes in the right way Steps to reproduce: # mkfs.btrfs -f /dev/sda[8-11] -m raid5 -d raid5 # mount /dev/sda8 /mnt # btrfs scrub start -BR /mnt # echo $? <--unverified errors make return value be 3 This is because we don't setup right mapping between physical and logical address for raid56, which makes checksum mismatch. But we will find everthing is fine later when rechecking using btrfs_map_block(). This patch fixed the problem by settuping right mappings and we only verify data stripes' checksums. Signed-off-by: Wang Shilong Signed-off-by: Chris Mason --- fs/btrfs/scrub.c | 108 +++++++++++++++++++++++++++++++++++++++++++++---------- 1 file changed, 89 insertions(+), 19 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index db21a13..aee909f 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2235,6 +2235,47 @@ behind_scrub_pages: return 0; } +/* + * Given a physical address, this will calculate it's + * logical offset. if this is a parity stripe, it will return + * the most left data stripe's logical offset. + * + * return 0 if it is a data stripe, 1 means parity stripe. + */ +static int get_raid56_logic_offset(u64 physical, int num, + struct map_lookup *map, u64 *offset) +{ + int i; + int j = 0; + u64 stripe_nr; + u64 last_offset; + int stripe_index; + int rot; + + last_offset = (physical - map->stripes[num].physical) * + nr_data_stripes(map); + *offset = last_offset; + for (i = 0; i < nr_data_stripes(map); i++) { + *offset = last_offset + i * map->stripe_len; + + stripe_nr = *offset; + do_div(stripe_nr, map->stripe_len); + do_div(stripe_nr, nr_data_stripes(map)); + + /* Work out the disk rotation on this stripe-set */ + rot = do_div(stripe_nr, map->num_stripes); + /* calculate which stripe this data locates */ + rot += i; + stripe_index = do_div(rot, map->num_stripes); + if (stripe_index == num) + return 0; + if (stripe_index < num) + j++; + } + *offset = last_offset + j * map->stripe_len; + return 1; +} + static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, struct map_lookup *map, struct btrfs_device *scrub_dev, @@ -2256,6 +2297,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, u64 physical; u64 logical; u64 logic_end; + u64 physical_end; u64 generation; int mirror_num; struct reada_control *reada1; @@ -2269,16 +2311,10 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, u64 extent_len; struct btrfs_device *extent_dev; int extent_mirror_num; - int stop_loop; - - if (map->type & (BTRFS_BLOCK_GROUP_RAID5 | - BTRFS_BLOCK_GROUP_RAID6)) { - if (num >= nr_data_stripes(map)) { - return 0; - } - } + int stop_loop = 0; nstripes = length; + physical = map->stripes[num].physical; offset = 0; do_div(nstripes, map->stripe_len); if (map->type & BTRFS_BLOCK_GROUP_RAID0) { @@ -2296,6 +2332,11 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, } else if (map->type & BTRFS_BLOCK_GROUP_DUP) { increment = map->stripe_len; mirror_num = num % map->num_stripes + 1; + } else if (map->type & (BTRFS_BLOCK_GROUP_RAID5 | + BTRFS_BLOCK_GROUP_RAID6)) { + get_raid56_logic_offset(physical, num, map, &offset); + increment = map->stripe_len * nr_data_stripes(map); + mirror_num = 1; } else { increment = map->stripe_len; mirror_num = 1; @@ -2319,7 +2360,15 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, * to not hold off transaction commits */ logical = base + offset; - + physical_end = physical + nstripes * map->stripe_len; + if (map->type & (BTRFS_BLOCK_GROUP_RAID5 | + BTRFS_BLOCK_GROUP_RAID6)) { + get_raid56_logic_offset(physical_end, num, + map, &logic_end); + logic_end += base; + } else { + logic_end = logical + increment * nstripes; + } wait_event(sctx->list_wait, atomic_read(&sctx->bios_in_flight) == 0); scrub_blocked_if_needed(fs_info); @@ -2328,7 +2377,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, key_start.objectid = logical; key_start.type = BTRFS_EXTENT_ITEM_KEY; key_start.offset = (u64)0; - key_end.objectid = base + offset + nstripes * increment; + key_end.objectid = logic_end; key_end.type = BTRFS_METADATA_ITEM_KEY; key_end.offset = (u64)-1; reada1 = btrfs_reada_add(root, &key_start, &key_end); @@ -2338,7 +2387,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, key_start.offset = logical; key_end.objectid = BTRFS_EXTENT_CSUM_OBJECTID; key_end.type = BTRFS_EXTENT_CSUM_KEY; - key_end.offset = base + offset + nstripes * increment; + key_end.offset = logic_end; reada2 = btrfs_reada_add(csum_root, &key_start, &key_end); if (!IS_ERR(reada1)) @@ -2356,11 +2405,17 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx, /* * now find all extents for each stripe and scrub them */ - logical = base + offset; - physical = map->stripes[num].physical; - logic_end = logical + increment * nstripes; ret = 0; - while (logical < logic_end) { + while (physical < physical_end) { + /* for raid56, we skip parity stripe */ + if (map->type & (BTRFS_BLOCK_GROUP_RAID5 | + BTRFS_BLOCK_GROUP_RAID6)) { + ret = get_raid56_logic_offset(physical, num, + map, &logical); + logical += base; + if (ret) + goto skip; + } /* * canceled? */ @@ -2504,15 +2559,29 @@ again: scrub_free_csums(sctx); if (extent_logical + extent_len < key.objectid + bytes) { - logical += increment; - physical += map->stripe_len; - + if (map->type & (BTRFS_BLOCK_GROUP_RAID5 | + BTRFS_BLOCK_GROUP_RAID6)) { + /* + * loop until we find next data stripe + * or we have finished all stripes. + */ + do { + physical += map->stripe_len; + ret = get_raid56_logic_offset( + physical, num, + map, &logical); + logical += base; + } while (physical < physical_end && ret); + } else { + physical += map->stripe_len; + logical += increment; + } if (logical < key.objectid + bytes) { cond_resched(); goto again; } - if (logical >= logic_end) { + if (physical >= physical_end) { stop_loop = 1; break; } @@ -2521,6 +2590,7 @@ next: path->slots[0]++; } btrfs_release_path(path); +skip: logical += increment; physical += map->stripe_len; spin_lock(&sctx->stat_lock); -- cgit v1.1 From a1ecaabbf90cf4e93eb2b50aef3d07ab630c6fb1 Mon Sep 17 00:00:00 2001 From: Wang Shilong Date: Wed, 2 Apr 2014 19:53:32 +0800 Subject: Btrfs: fix unlock in __start_delalloc_inodes() This patch fix a regression caused by the following patch: Btrfs: don't flush all delalloc inodes when we doesn't get s_umount lock break while loop will make us call @spin_unlock() without calling @spin_lock() before, fix it. Signed-off-by: Wang Shilong Reviewed-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index fdb8f44..0c0bb45 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8500,19 +8500,20 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput, else iput(inode); ret = -ENOMEM; - break; + goto out; } list_add_tail(&work->list, &works); btrfs_queue_work(root->fs_info->flush_workers, &work->work); ret++; if (nr != -1 && ret >= nr) - break; + goto out; cond_resched(); spin_lock(&root->delalloc_lock); } spin_unlock(&root->delalloc_lock); +out: list_for_each_entry_safe(work, next, &works, list) { list_del_init(&work->list); btrfs_wait_and_free_delalloc_work(work); -- cgit v1.1 From 3a29bc0928003674f45b4fe625b4d0738a22c60d Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Mon, 7 Apr 2014 07:10:40 -0700 Subject: Btrfs: fix EINVAL checks in btrfs_clone btrfs_drop_extents can now return -EINVAL, but only one caller in btrfs_clone was checking for it. This adds it to the caller for inline extents, which is where we really need it. Signed-off-by: Chris Mason --- fs/btrfs/ioctl.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 05f8df8..89d5db7 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3163,8 +3163,9 @@ process_slot: new_key.offset + datal, 1); if (ret) { - btrfs_abort_transaction(trans, root, - ret); + if (ret != -EINVAL) + btrfs_abort_transaction(trans, + root, ret); btrfs_end_transaction(trans, root); goto out; } -- cgit v1.1 From c4a050bbbb5d7dab03aa720af36d8e91ed7f2ec8 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 14 Mar 2014 16:36:53 -0400 Subject: Btrfs: abort the transaction when we don't find our extent ref I'm not sure why we weren't aborting here in the first place, it is obviously a bad time from the fact that we print the leaf and yell loudly about it. Fix this up, otherwise we panic because our path could be pointing into oblivion. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 1341163..1306487 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -5745,6 +5745,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans, "unable to find ref byte nr %llu parent %llu root %llu owner %llu offset %llu", bytenr, parent, root_objectid, owner_objectid, owner_offset); + btrfs_abort_transaction(trans, extent_root, ret); + goto out; } else { btrfs_abort_transaction(trans, extent_root, ret); goto out; -- cgit v1.1 From 800ee2247f483b6d05ed47ef3bbc90b56451746c Mon Sep 17 00:00:00 2001 From: Sergei Trofimovich Date: Mon, 7 Apr 2014 10:55:46 +0300 Subject: btrfs: fix crash in remount(thread_pool=) case Reproducer: mount /dev/ubda /mnt mount -oremount,thread_pool=42 /mnt Gives a crash: ? btrfs_workqueue_set_max+0x0/0x70 btrfs_resize_thread_pool+0xe3/0xf0 ? sync_filesystem+0x0/0xc0 ? btrfs_resize_thread_pool+0x0/0xf0 btrfs_remount+0x1d2/0x570 ? kern_path+0x0/0x80 do_remount_sb+0xd9/0x1c0 do_mount+0x26a/0xbf0 ? kfree+0x0/0x1b0 SyS_mount+0xc4/0x110 It's a call btrfs_workqueue_set_max(fs_info->scrub_wr_completion_workers, new_pool_size); with fs_info->scrub_wr_completion_workers = NULL; as scrub wqs get created only on user's demand. Patch skips not-created-yet workqueues. Signed-off-by: Sergei Trofimovich CC: Qu Wenruo CC: Chris Mason CC: Josef Bacik CC: linux-btrfs@vger.kernel.org Signed-off-by: Chris Mason --- fs/btrfs/async-thread.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c index ecb5832..5a201d8 100644 --- a/fs/btrfs/async-thread.c +++ b/fs/btrfs/async-thread.c @@ -323,6 +323,8 @@ void btrfs_destroy_workqueue(struct btrfs_workqueue *wq) void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max) { + if (!wq) + return; wq->normal->max_active = max; if (wq->high) wq->high->max_active = max; -- cgit v1.1 From 36523e95129c0e69bf1592cd009261b1c6d96e77 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Fri, 7 Feb 2014 14:34:12 +0100 Subject: btrfs: export global block reserve size as space_info Introduce a block group type bit for a global reserve and fill the space info for SPACE_INFO ioctl. This should replace the newly added ioctl (01e219e8069516cdb98594d417b8bb8d906ed30d) to get just the 'size' part of the global reserve, while the actual usage can be now visible in the 'btrfs fi df' output during ENOSPC stress. The unpatched userspace tools will show the blockgroup as 'unknown'. CC: Jeff Mahoney CC: Josef Bacik Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 9 ++++++++- fs/btrfs/ioctl.c | 20 ++++++++++++++++++++ 2 files changed, 28 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index d8a669e..ad1a594 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -987,7 +987,8 @@ struct btrfs_dev_replace_item { #define BTRFS_BLOCK_GROUP_RAID10 (1ULL << 6) #define BTRFS_BLOCK_GROUP_RAID5 (1ULL << 7) #define BTRFS_BLOCK_GROUP_RAID6 (1ULL << 8) -#define BTRFS_BLOCK_GROUP_RESERVED BTRFS_AVAIL_ALLOC_BIT_SINGLE +#define BTRFS_BLOCK_GROUP_RESERVED (BTRFS_AVAIL_ALLOC_BIT_SINGLE | \ + BTRFS_SPACE_INFO_GLOBAL_RSV) enum btrfs_raid_types { BTRFS_RAID_RAID10, @@ -1019,6 +1020,12 @@ enum btrfs_raid_types { */ #define BTRFS_AVAIL_ALLOC_BIT_SINGLE (1ULL << 48) +/* + * A fake block group type that is used to communicate global block reserve + * size to userspace via the SPACE_INFO ioctl. + */ +#define BTRFS_SPACE_INFO_GLOBAL_RSV (1ULL << 49) + #define BTRFS_EXTENDED_PROFILE_MASK (BTRFS_BLOCK_GROUP_PROFILE_MASK | \ BTRFS_AVAIL_ALLOC_BIT_SINGLE) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 89d5db7..f2e8fcc 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3562,6 +3562,11 @@ static long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg) up_read(&info->groups_sem); } + /* + * Global block reserve, exported as a space_info + */ + slot_count++; + /* space_slots == 0 means they are asking for a count */ if (space_args.space_slots == 0) { space_args.total_spaces = slot_count; @@ -3620,6 +3625,21 @@ static long btrfs_ioctl_space_info(struct btrfs_root *root, void __user *arg) up_read(&info->groups_sem); } + /* + * Add global block reserve + */ + if (slot_count) { + struct btrfs_block_rsv *block_rsv = &root->fs_info->global_block_rsv; + + spin_lock(&block_rsv->lock); + space.total_bytes = block_rsv->size; + space.used_bytes = block_rsv->size - block_rsv->reserved; + spin_unlock(&block_rsv->lock); + space.flags = BTRFS_SPACE_INFO_GLOBAL_RSV; + memcpy(dest, &space, sizeof(space)); + space_args.total_spaces++; + } + user_dest = (struct btrfs_ioctl_space_info __user *) (arg + sizeof(struct btrfs_ioctl_space_args)); -- cgit v1.1 From 0723a0473fb48a1c93b113a28665b64ce5faf35a Mon Sep 17 00:00:00 2001 From: Harald Hoyer Date: Tue, 19 Nov 2013 11:36:05 +0100 Subject: btrfs: allow mounting btrfs subvolumes with different ro/rw options Given the following /etc/fstab entries: /dev/sda3 /mnt/foo btrfs subvol=foo,ro 0 0 /dev/sda3 /mnt/bar btrfs subvol=bar,rw 0 0 you can't issue: $ mount /mnt/foo $ mount /mnt/bar You would have to do: $ mount /mnt/foo $ mount -o remount,rw /mnt/foo $ mount --bind -o remount,ro /mnt/foo $ mount /mnt/bar or $ mount /mnt/bar $ mount --rw /mnt/foo $ mount --bind -o remount,ro /mnt/foo With this patch you can do $ mount /mnt/foo $ mount /mnt/bar $ cat /proc/self/mountinfo 49 33 0:41 /foo /mnt/foo ro,relatime shared:36 - btrfs /dev/sda3 rw,ssd,space_cache 87 33 0:41 /bar /mnt/bar rw,relatime shared:74 - btrfs /dev/sda3 rw,ssd,space_cache Signed-off-by: Chris Mason --- fs/btrfs/super.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index d4878dd..994c409 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -66,6 +66,8 @@ static const struct super_operations btrfs_super_ops; static struct file_system_type btrfs_fs_type; +static int btrfs_remount(struct super_block *sb, int *flags, char *data); + static const char *btrfs_decode_error(int errno) { char *errstr = "unknown"; @@ -1185,6 +1187,26 @@ static struct dentry *mount_subvol(const char *subvol_name, int flags, mnt = vfs_kern_mount(&btrfs_fs_type, flags, device_name, newargs); kfree(newargs); + + if (PTR_RET(mnt) == -EBUSY) { + if (flags & MS_RDONLY) { + mnt = vfs_kern_mount(&btrfs_fs_type, flags & ~MS_RDONLY, device_name, + newargs); + } else { + int r; + mnt = vfs_kern_mount(&btrfs_fs_type, flags | MS_RDONLY, device_name, + newargs); + if (IS_ERR(mnt)) + return ERR_CAST(mnt); + + r = btrfs_remount(mnt->mnt_sb, &flags, NULL); + if (r < 0) { + /* FIXME: release vfsmount mnt ??*/ + return ERR_PTR(r); + } + } + } + if (IS_ERR(mnt)) return ERR_CAST(mnt); -- cgit v1.1 From e4fbaee29272533a242f117d18712e2974520d2c Mon Sep 17 00:00:00 2001 From: Wang Shilong Date: Fri, 11 Apr 2014 18:32:25 +0800 Subject: Btrfs: fix compile warnings on on avr32 platform fs/btrfs/scrub.c: In function 'get_raid56_logic_offset': fs/btrfs/scrub.c:2269: warning: comparison of distinct pointer types lacks a cast fs/btrfs/scrub.c:2269: warning: right shift count >= width of type fs/btrfs/scrub.c:2269: warning: passing argument 1 of '__div64_32' from incompatible pointer type Since @rot is an int type, we should not use do_div(), fix it. Reported-by: kbuild test robot Signed-off-by: Wang Shilong Signed-off-by: Chris Mason --- fs/btrfs/scrub.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index aee909f..68a5a26 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -2266,7 +2266,7 @@ static int get_raid56_logic_offset(u64 physical, int num, rot = do_div(stripe_nr, map->num_stripes); /* calculate which stripe this data locates */ rot += i; - stripe_index = do_div(rot, map->num_stripes); + stripe_index = rot % map->num_stripes; if (stripe_index == num) return 0; if (stripe_index < num) -- cgit v1.1