From bfe8684869601dacfcb2cd69ef8cfd9045f62170 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 28 Oct 2011 14:13:29 +0200 Subject: filesystems: add set_nlink() Replace remaining direct i_nlink updates with a new set_nlink() updater function. Signed-off-by: Miklos Szeredi Tested-by: Toshiyuki Okajima Signed-off-by: Christoph Hellwig --- fs/btrfs/delayed-inode.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/delayed-inode.c') diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index b52c672f4c1..ae4d9cd1096 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1641,7 +1641,7 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev) inode->i_gid = btrfs_stack_inode_gid(inode_item); btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item)); inode->i_mode = btrfs_stack_inode_mode(inode_item); - inode->i_nlink = btrfs_stack_inode_nlink(inode_item); + set_nlink(inode, btrfs_stack_inode_nlink(inode_item)); inode_set_bytes(inode, btrfs_stack_inode_nbytes(inode_item)); BTRFS_I(inode)->generation = btrfs_stack_inode_generation(inode_item); BTRFS_I(inode)->sequence = btrfs_stack_inode_sequence(inode_item); -- cgit v1.2.3-70-g09d2 From 6d668dda0caec537fbf28c4d91e6d18181af3cff Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 3 Nov 2011 22:54:25 -0400 Subject: Btrfs: make a delayed_block_rsv for the delayed item insertion I've been hitting warnings in use_block_rsv when running the delayed insertion stuff. It's because we will readjust global block rsv based on what is in use, which means we could end up discarding reservations that are for the delayed insertion stuff. So instead create a seperate block rsv for the delayed insertion stuff. This will also make it easier to debug problems with the delayed insertion reservations since we will know that only the delayed insertion code touches this block_rsv. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 2 ++ fs/btrfs/delayed-inode.c | 14 +++++++------- fs/btrfs/disk-io.c | 1 + fs/btrfs/extent-tree.c | 3 +++ 4 files changed, 13 insertions(+), 7 deletions(-) (limited to 'fs/btrfs/delayed-inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 78f43d1102a..3002e5d4da0 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -957,6 +957,8 @@ struct btrfs_fs_info { struct btrfs_block_rsv trans_block_rsv; /* block reservation for chunk tree */ struct btrfs_block_rsv chunk_block_rsv; + /* block reservation for delayed operations */ + struct btrfs_block_rsv delayed_block_rsv; struct btrfs_block_rsv empty_block_rsv; diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index b52c672f4c1..fc4026af729 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -591,7 +591,7 @@ static int btrfs_delayed_item_reserve_metadata(struct btrfs_trans_handle *trans, return 0; src_rsv = trans->block_rsv; - dst_rsv = &root->fs_info->global_block_rsv; + dst_rsv = &root->fs_info->delayed_block_rsv; num_bytes = btrfs_calc_trans_metadata_size(root, 1); ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes); @@ -609,7 +609,7 @@ static void btrfs_delayed_item_release_metadata(struct btrfs_root *root, if (!item->bytes_reserved) return; - rsv = &root->fs_info->global_block_rsv; + rsv = &root->fs_info->delayed_block_rsv; btrfs_block_rsv_release(root, rsv, item->bytes_reserved); } @@ -628,7 +628,7 @@ static int btrfs_delayed_inode_reserve_metadata( return 0; src_rsv = trans->block_rsv; - dst_rsv = &root->fs_info->global_block_rsv; + dst_rsv = &root->fs_info->delayed_block_rsv; num_bytes = btrfs_calc_trans_metadata_size(root, 1); ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes); @@ -646,7 +646,7 @@ static void btrfs_delayed_inode_release_metadata(struct btrfs_root *root, if (!node->bytes_reserved) return; - rsv = &root->fs_info->global_block_rsv; + rsv = &root->fs_info->delayed_block_rsv; btrfs_block_rsv_release(root, rsv, node->bytes_reserved); node->bytes_reserved = 0; @@ -1026,7 +1026,7 @@ int btrfs_run_delayed_items(struct btrfs_trans_handle *trans, path->leave_spinning = 1; block_rsv = trans->block_rsv; - trans->block_rsv = &root->fs_info->global_block_rsv; + trans->block_rsv = &root->fs_info->delayed_block_rsv; delayed_root = btrfs_get_delayed_root(root); @@ -1069,7 +1069,7 @@ static int __btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans, path->leave_spinning = 1; block_rsv = trans->block_rsv; - trans->block_rsv = &node->root->fs_info->global_block_rsv; + trans->block_rsv = &node->root->fs_info->delayed_block_rsv; ret = btrfs_insert_delayed_items(trans, path, node->root, node); if (!ret) @@ -1149,7 +1149,7 @@ static void btrfs_async_run_delayed_node_done(struct btrfs_work *work) goto free_path; block_rsv = trans->block_rsv; - trans->block_rsv = &root->fs_info->global_block_rsv; + trans->block_rsv = &root->fs_info->delayed_block_rsv; ret = btrfs_insert_delayed_items(trans, path, root, delayed_node); if (!ret) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index a61f8a6cf21..23b6776477b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1891,6 +1891,7 @@ struct btrfs_root *open_ctree(struct super_block *sb, btrfs_init_block_rsv(&fs_info->trans_block_rsv); btrfs_init_block_rsv(&fs_info->chunk_block_rsv); btrfs_init_block_rsv(&fs_info->empty_block_rsv); + btrfs_init_block_rsv(&fs_info->delayed_block_rsv); atomic_set(&fs_info->nr_async_submits, 0); atomic_set(&fs_info->async_delalloc_pages, 0); atomic_set(&fs_info->async_submit_draining, 0); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 782eb3ea8ed..01c1f08b976 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3914,6 +3914,7 @@ static void init_global_block_rsv(struct btrfs_fs_info *fs_info) fs_info->delalloc_block_rsv.space_info = space_info; fs_info->trans_block_rsv.space_info = space_info; fs_info->empty_block_rsv.space_info = space_info; + fs_info->delayed_block_rsv.space_info = space_info; fs_info->extent_root->block_rsv = &fs_info->global_block_rsv; fs_info->csum_root->block_rsv = &fs_info->global_block_rsv; @@ -3933,6 +3934,8 @@ static void release_global_block_rsv(struct btrfs_fs_info *fs_info) WARN_ON(fs_info->trans_block_rsv.reserved > 0); WARN_ON(fs_info->chunk_block_rsv.size > 0); WARN_ON(fs_info->chunk_block_rsv.reserved > 0); + WARN_ON(fs_info->delayed_block_rsv.size > 0); + WARN_ON(fs_info->delayed_block_rsv.reserved > 0); } void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans, -- cgit v1.2.3-70-g09d2 From c06a0e120a4e381a1c291c1fce3c6155c5791cae Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 4 Nov 2011 19:56:02 -0400 Subject: Btrfs: fix delayed insertion reservation We all keep getting those stupid warnings from use_block_rsv when running stress.sh, and it's because the delayed insertion stuff is being stupid. It's not the delayed insertion stuffs fault, it's all just stupid. When marking an inode dirty for oh say updating the time on it, we just do a btrfs_join_transaction, which doesn't reserve any space. This is stupid because we're going to have to have space reserve to make this change, but we do it because it's fast because chances are we're going to call it over and over again and it doesn't matter. Well thanks to the delayed insertion stuff this is mostly the case, so we do actually need to make this reservation. So if trans->bytes_reserved is 0 then try to do a normal reservation. If not return ENOSPC which will make the btrfs_dirty_inode start a proper transaction which will let it do the whole ENOSPC dance and reserve enough space for the delayed insertion to steal the reservation from the transaction. The other stupid thing we do is not reserve space for the inode when writing to the thing. Usually this is ok since we have to update the time so we'd have already done all this work before we get to the endio stuff, so it doesn't matter. But this is stupid because we could write the data after the transaction commits where we changed the mtime of the inode so we have to cow all the way down to the inode anyway. This used to be masked by the delalloc reservation stuff, but because we delay the update it doesn't get masked in this case. So again the delayed insertion stuff bites us in the ass. So if our trans->block_rsv is delalloc, just steal the reservation from the delalloc reserve. Hopefully this won't bite us in the ass, but I've said that before. With this patch stress.sh no longer spits out those stupid warnings (famous last words). Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 3 +++ fs/btrfs/delayed-inode.c | 36 ++++++++++++++++++++++++++++-------- fs/btrfs/extent-tree.c | 18 ++++++++++++++++++ 3 files changed, 49 insertions(+), 8 deletions(-) (limited to 'fs/btrfs/delayed-inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3002e5d4da0..6bb34fc1ff2 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2353,6 +2353,9 @@ void btrfs_free_block_rsv(struct btrfs_root *root, int btrfs_block_rsv_add(struct btrfs_root *root, struct btrfs_block_rsv *block_rsv, u64 num_bytes); +int btrfs_block_rsv_add_noflush(struct btrfs_root *root, + struct btrfs_block_rsv *block_rsv, + u64 num_bytes); int btrfs_block_rsv_check(struct btrfs_root *root, struct btrfs_block_rsv *block_rsv, int min_factor); int btrfs_block_rsv_refill(struct btrfs_root *root, diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index fc4026af729..bbe8496d533 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -624,13 +624,36 @@ static int btrfs_delayed_inode_reserve_metadata( u64 num_bytes; int ret; - if (!trans->bytes_reserved) - return 0; - src_rsv = trans->block_rsv; dst_rsv = &root->fs_info->delayed_block_rsv; num_bytes = btrfs_calc_trans_metadata_size(root, 1); + + /* + * btrfs_dirty_inode will update the inode under btrfs_join_transaction + * which doesn't reserve space for speed. This is a problem since we + * still need to reserve space for this update, so try to reserve the + * space. + * + * Now if src_rsv == delalloc_block_rsv we'll let it just steal since + * we're accounted for. + */ + if (!trans->bytes_reserved && + src_rsv != &root->fs_info->delalloc_block_rsv) { + ret = btrfs_block_rsv_add_noflush(root, dst_rsv, num_bytes); + /* + * Since we're under a transaction reserve_metadata_bytes could + * try to commit the transaction which will make it return + * EAGAIN to make us stop the transaction we have, so return + * ENOSPC instead so that btrfs_dirty_inode knows what to do. + */ + if (ret == -EAGAIN) + ret = -ENOSPC; + if (!ret) + node->bytes_reserved = num_bytes; + return ret; + } + ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes); if (!ret) node->bytes_reserved = num_bytes; @@ -1686,11 +1709,8 @@ int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans, } ret = btrfs_delayed_inode_reserve_metadata(trans, root, delayed_node); - /* - * we must reserve enough space when we start a new transaction, - * so reserving metadata failure is impossible - */ - BUG_ON(ret); + if (ret) + goto release_node; fill_stack_inode_item(trans, &delayed_node->inode_item, inode); delayed_node->inode_dirty = 1; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 5b84205e768..23e936c3de7 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3814,6 +3814,24 @@ int btrfs_block_rsv_add(struct btrfs_root *root, return ret; } +int btrfs_block_rsv_add_noflush(struct btrfs_root *root, + struct btrfs_block_rsv *block_rsv, + u64 num_bytes) +{ + int ret; + + if (num_bytes == 0) + return 0; + + ret = reserve_metadata_bytes(root, block_rsv, num_bytes, 0); + if (!ret) { + block_rsv_add_bytes(block_rsv, num_bytes, 1); + return 0; + } + + return ret; +} + int btrfs_block_rsv_check(struct btrfs_root *root, struct btrfs_block_rsv *block_rsv, int min_factor) { -- cgit v1.2.3-70-g09d2 From 7fd2ae21a42d178982679b86086661292b4afe4a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 8 Nov 2011 15:47:34 -0500 Subject: Btrfs: fix our reservations for updating an inode when completing io People have been reporting ENOSPC crashes in finish_ordered_io. This is because we try to steal from the delalloc block rsv to satisfy a reservation to update the inode. The problem with this is we don't explicitly save space for updating the inode when doing delalloc. This is kind of a problem and we've gotten away with this because way back when we just stole from the delalloc reserve without any questions, and this worked out fine because generally speaking the leaf had been modified either by the mtime update when we did the original write or because we just updated the leaf when we inserted the file extent item, only on rare occasions had the leaf not actually been modified, and that was still ok because we'd just use a block or two out of the over-reservation that is delalloc. Then came the delayed inode stuff. This is amazing, except it wants a full reservation for updating the inode since it may do it at some point down the road after we've written the blocks and we have to recow everything again. This worked out because the delayed inode stuff just stole from the global reserve, that is until recently when I changed that because it caused other problems. So here we are, we're doing everything right and being screwed for it. So take an extra reservation for the inode at delalloc reservation time and carry it through the life of the delalloc reservation. If we need it we can steal it in the delayed inode stuff. If we have already stolen it try and do a normal metadata reservation. If that fails try to steal from the delalloc reservation. If _that_ fails we'll get a WARN_ON() so I can start thinking of a better way to solve this and in the meantime we'll steal from the global reserve. With this patch I ran xfstests 13 in a loop for a couple of hours and didn't see any problems. Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/btrfs_inode.h | 4 +-- fs/btrfs/delayed-inode.c | 65 +++++++++++++++++++++++++++++++++++++++++++++--- fs/btrfs/extent-tree.c | 22 +++++++++++++--- fs/btrfs/inode.c | 1 + 4 files changed, 83 insertions(+), 9 deletions(-) (limited to 'fs/btrfs/delayed-inode.c') diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index 5a5d325a393..634608d2a6d 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -147,14 +147,12 @@ struct btrfs_inode { * the btrfs file release call will add this inode to the * ordered operations list so that we make sure to flush out any * new data the application may have written before commit. - * - * yes, its silly to have a single bitflag, but we might grow more - * of these. */ unsigned ordered_data_close:1; unsigned orphan_meta_reserved:1; unsigned dummy_inode:1; unsigned in_defrag:1; + unsigned delalloc_meta_reserved:1; /* * always compress this one file diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index bbe8496d533..313ee14cf3b 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -617,12 +617,14 @@ static void btrfs_delayed_item_release_metadata(struct btrfs_root *root, static int btrfs_delayed_inode_reserve_metadata( struct btrfs_trans_handle *trans, struct btrfs_root *root, + struct inode *inode, struct btrfs_delayed_node *node) { struct btrfs_block_rsv *src_rsv; struct btrfs_block_rsv *dst_rsv; u64 num_bytes; int ret; + int release = false; src_rsv = trans->block_rsv; dst_rsv = &root->fs_info->delayed_block_rsv; @@ -652,11 +654,67 @@ static int btrfs_delayed_inode_reserve_metadata( if (!ret) node->bytes_reserved = num_bytes; return ret; + } else if (src_rsv == &root->fs_info->delalloc_block_rsv) { + spin_lock(&BTRFS_I(inode)->lock); + if (BTRFS_I(inode)->delalloc_meta_reserved) { + BTRFS_I(inode)->delalloc_meta_reserved = 0; + spin_unlock(&BTRFS_I(inode)->lock); + release = true; + goto migrate; + } + spin_unlock(&BTRFS_I(inode)->lock); + + /* Ok we didn't have space pre-reserved. This shouldn't happen + * too often but it can happen if we do delalloc to an existing + * inode which gets dirtied because of the time update, and then + * isn't touched again until after the transaction commits and + * then we try to write out the data. First try to be nice and + * reserve something strictly for us. If not be a pain and try + * to steal from the delalloc block rsv. + */ + ret = btrfs_block_rsv_add_noflush(root, dst_rsv, num_bytes); + if (!ret) + goto out; + + ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes); + if (!ret) + goto out; + + /* + * Ok this is a problem, let's just steal from the global rsv + * since this really shouldn't happen that often. + */ + WARN_ON(1); + ret = btrfs_block_rsv_migrate(&root->fs_info->global_block_rsv, + dst_rsv, num_bytes); + goto out; } +migrate: ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes); - if (!ret) - node->bytes_reserved = num_bytes; + if (unlikely(ret)) { + /* This shouldn't happen */ + BUG_ON(release); + return ret; + } + +out: + /* + * Migrate only takes a reservation, it doesn't touch the size of the + * block_rsv. This is to simplify people who don't normally have things + * migrated from their block rsv. If they go to release their + * reservation, that will decrease the size as well, so if migrate + * reduced size we'd end up with a negative size. But for the + * delalloc_meta_reserved stuff we will only know to drop 1 reservation, + * but we could in fact do this reserve/migrate dance several times + * between the time we did the original reservation and we'd clean it + * up. So to take care of this, release the space for the meta + * reservation here. I think it may be time for a documentation page on + * how block rsvs. work. + */ + if (release) + btrfs_block_rsv_release(root, src_rsv, num_bytes); + node->bytes_reserved = num_bytes; return ret; } @@ -1708,7 +1766,8 @@ int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans, goto release_node; } - ret = btrfs_delayed_inode_reserve_metadata(trans, root, delayed_node); + ret = btrfs_delayed_inode_reserve_metadata(trans, root, inode, + delayed_node); if (ret) goto release_node; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 18ea90c8943..0b044e509e9 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4063,23 +4063,30 @@ int btrfs_snap_reserve_metadata(struct btrfs_trans_handle *trans, */ static unsigned drop_outstanding_extent(struct inode *inode) { + unsigned drop_inode_space = 0; unsigned dropped_extents = 0; BUG_ON(!BTRFS_I(inode)->outstanding_extents); BTRFS_I(inode)->outstanding_extents--; + if (BTRFS_I(inode)->outstanding_extents == 0 && + BTRFS_I(inode)->delalloc_meta_reserved) { + drop_inode_space = 1; + BTRFS_I(inode)->delalloc_meta_reserved = 0; + } + /* * If we have more or the same amount of outsanding extents than we have * reserved then we need to leave the reserved extents count alone. */ if (BTRFS_I(inode)->outstanding_extents >= BTRFS_I(inode)->reserved_extents) - return 0; + return drop_inode_space; dropped_extents = BTRFS_I(inode)->reserved_extents - BTRFS_I(inode)->outstanding_extents; BTRFS_I(inode)->reserved_extents -= dropped_extents; - return dropped_extents; + return dropped_extents + drop_inode_space; } /** @@ -4165,9 +4172,18 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) nr_extents = BTRFS_I(inode)->outstanding_extents - BTRFS_I(inode)->reserved_extents; BTRFS_I(inode)->reserved_extents += nr_extents; + } - to_reserve = btrfs_calc_trans_metadata_size(root, nr_extents); + /* + * Add an item to reserve for updating the inode when we complete the + * delalloc io. + */ + if (!BTRFS_I(inode)->delalloc_meta_reserved) { + nr_extents++; + BTRFS_I(inode)->delalloc_meta_reserved = 1; } + + to_reserve = btrfs_calc_trans_metadata_size(root, nr_extents); to_reserve += calc_csum_metadata_size(inode, num_bytes, 1); spin_unlock(&BTRFS_I(inode)->lock); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f60e2490bd0..2b920596c12 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6607,6 +6607,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb) ei->orphan_meta_reserved = 0; ei->dummy_inode = 0; ei->in_defrag = 0; + ei->delalloc_meta_reserved = 0; ei->force_compress = BTRFS_COMPRESS_NONE; ei->delayed_node = NULL; -- cgit v1.2.3-70-g09d2 From 2115133f8b9a8dbdb217d14080814df07ce90479 Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Thu, 10 Nov 2011 20:39:08 -0500 Subject: Btrfs: tweak the delayed inode reservations again Josef sent along an incremental to the inode reservation code to make sure we try and fall back to directly updating the inode item if things go horribly wrong. This reworks that patch slightly, adding a fallback function that will always try to update the inode item directly without going through the delayed_inode code. Signed-off-by: Chris Mason --- fs/btrfs/delayed-inode.c | 9 +++---- fs/btrfs/inode.c | 64 +++++++++++++++++++++++++++++++++--------------- 2 files changed, 47 insertions(+), 26 deletions(-) (limited to 'fs/btrfs/delayed-inode.c') diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 313ee14cf3b..6a1a6800776 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -692,11 +692,6 @@ static int btrfs_delayed_inode_reserve_metadata( migrate: ret = btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes); - if (unlikely(ret)) { - /* This shouldn't happen */ - BUG_ON(release); - return ret; - } out: /* @@ -712,9 +707,11 @@ out: * reservation here. I think it may be time for a documentation page on * how block rsvs. work. */ + if (!ret) + node->bytes_reserved = num_bytes; + if (release) btrfs_block_rsv_release(root, src_rsv, num_bytes); - node->bytes_reserved = num_bytes; return ret; } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 2b920596c12..7d394335bcb 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -93,6 +93,8 @@ static noinline int cow_file_range(struct inode *inode, struct page *locked_page, u64 start, u64 end, int *page_started, unsigned long *nr_written, int unlock); +static noinline int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct inode *inode); static int btrfs_init_inode_security(struct btrfs_trans_handle *trans, struct inode *inode, struct inode *dir, @@ -1741,7 +1743,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) trans = btrfs_join_transaction(root); BUG_ON(IS_ERR(trans)); trans->block_rsv = &root->fs_info->delalloc_block_rsv; - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode_fallback(trans, root, inode); BUG_ON(ret); } goto out; @@ -1791,7 +1793,7 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end) ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent); if (!ret || !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) { - ret = btrfs_update_inode(trans, root, inode); + ret = btrfs_update_inode_fallback(trans, root, inode); BUG_ON(ret); } ret = 0; @@ -2426,7 +2428,7 @@ static void fill_inode_item(struct btrfs_trans_handle *trans, /* * copy everything in the in-memory inode into the btree. */ -noinline int btrfs_update_inode(struct btrfs_trans_handle *trans, +static noinline int btrfs_update_inode_item(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode) { struct btrfs_inode_item *inode_item; @@ -2434,21 +2436,6 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans, struct extent_buffer *leaf; int ret; - /* - * If the inode is a free space inode, we can deadlock during commit - * if we put it into the delayed code. - * - * The data relocation inode should also be directly updated - * without delay - */ - if (!btrfs_is_free_space_inode(root, inode) - && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) { - ret = btrfs_delayed_update_inode(trans, root, inode); - if (!ret) - btrfs_set_inode_last_trans(trans, inode); - return ret; - } - path = btrfs_alloc_path(); if (!path) return -ENOMEM; @@ -2476,6 +2463,43 @@ failed: return ret; } +/* + * copy everything in the in-memory inode into the btree. + */ +noinline int btrfs_update_inode(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct inode *inode) +{ + int ret; + + /* + * If the inode is a free space inode, we can deadlock during commit + * if we put it into the delayed code. + * + * The data relocation inode should also be directly updated + * without delay + */ + if (!btrfs_is_free_space_inode(root, inode) + && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID) { + ret = btrfs_delayed_update_inode(trans, root, inode); + if (!ret) + btrfs_set_inode_last_trans(trans, inode); + return ret; + } + + return btrfs_update_inode_item(trans, root, inode); +} + +static noinline int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct inode *inode) +{ + int ret; + + ret = btrfs_update_inode(trans, root, inode); + if (ret == -ENOSPC) + return btrfs_update_inode_item(trans, root, inode); + return ret; +} + /* * unlink helper that gets used here in inode.c and in the tree logging * recovery code. It remove a link in a directory with a given name, and @@ -5632,7 +5656,7 @@ again: if (test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags)) { ret = btrfs_ordered_update_i_size(inode, 0, ordered); if (!ret) - err = btrfs_update_inode(trans, root, inode); + err = btrfs_update_inode_fallback(trans, root, inode); goto out; } @@ -5670,7 +5694,7 @@ again: add_pending_csums(trans, inode, ordered->file_offset, &ordered->list); ret = btrfs_ordered_update_i_size(inode, 0, ordered); if (!ret || !test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags)) - btrfs_update_inode(trans, root, inode); + btrfs_update_inode_fallback(trans, root, inode); ret = 0; out_unlock: unlock_extent_cached(&BTRFS_I(inode)->io_tree, ordered->file_offset, -- cgit v1.2.3-70-g09d2