From 2ab1ba68aeaecd41c4b34f0eaf1d70a37367fb1a Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Thu, 4 Aug 2011 14:28:36 -0400 Subject: Btrfs: force unplugs when switching from high to regular priority bios Btrfs does bio submissions from a worker thread, and each device has a list of high priority bios and regular priority bios. Synchronous writes go to the high priority thread while async writes go to regular list. This commit brings back an explicit unplug any time we switch from high to regular priority, which makes it easier for the block layer to give us low latencies. Signed-off-by: Chris Mason --- fs/btrfs/volumes.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'fs/btrfs') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 53875ae73ad4..3c5f2fcd82c1 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -142,6 +142,7 @@ static noinline int run_scheduled_bios(struct btrfs_device *device) unsigned long limit; unsigned long last_waited = 0; int force_reg = 0; + int sync_pending; struct blk_plug plug; /* @@ -229,6 +230,22 @@ loop_lock: BUG_ON(atomic_read(&cur->bi_cnt) == 0); + /* + * if we're doing the sync list, record that our + * plug has some sync requests on it + * + * If we're doing the regular list and there are + * sync requests sitting around, unplug before + * we add more + */ + if (pending_bios == &device->pending_sync_bios) { + sync_pending = 1; + } else if (sync_pending) { + blk_finish_plug(&plug); + blk_start_plug(&plug); + sync_pending = 0; + } + submit_bio(cur->bi_rw, cur); num_run++; batch_run++; -- cgit v1.2.3 From d5e2003c2bcda93a8f2e668eb4642d70c9c38301 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 4 Aug 2011 14:52:27 +0000 Subject: Btrfs: detect wether a device supports discard We have a problem where if a user specifies discard but doesn't actually support it we will return EOPNOTSUPP from btrfs_discard_extent. This is a problem because this gets called (in a fashion) from the tree log recovery code, which has a nice little BUG_ON(ret) after it, which causes us to fail the tree log replay. So instead detect wether our devices support discard when we're adding them and then don't issue discards if we know that the device doesn't support it. And just for good measure set ret = 0 in btrfs_issue_discard just in case we still get EOPNOTSUPP so we don't screw anybody up like this again. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 12 ++++++++++-- fs/btrfs/volumes.c | 17 +++++++++++++++++ fs/btrfs/volumes.h | 2 ++ 3 files changed, 29 insertions(+), 2 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 66bac226944e..059dfa048cc0 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1782,6 +1782,9 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, for (i = 0; i < multi->num_stripes; i++, stripe++) { + if (!stripe->dev->can_discard) + continue; + ret = btrfs_issue_discard(stripe->dev->bdev, stripe->physical, stripe->length); @@ -1789,11 +1792,16 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, discarded_bytes += stripe->length; else if (ret != -EOPNOTSUPP) break; + + /* + * Just in case we get back EOPNOTSUPP for some reason, + * just ignore the return value so we don't screw up + * people calling discard_extent. + */ + ret = 0; } kfree(multi); } - if (discarded_bytes && ret == -EOPNOTSUPP) - ret = 0; if (actual_bytes) *actual_bytes = discarded_bytes; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 3c5f2fcd82c1..a595f8775c37 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -517,6 +517,9 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices) fs_devices->rw_devices--; } + if (device->can_discard) + fs_devices->num_can_discard--; + new_device = kmalloc(sizeof(*new_device), GFP_NOFS); BUG_ON(!new_device); memcpy(new_device, device, sizeof(*new_device)); @@ -525,6 +528,7 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices) new_device->bdev = NULL; new_device->writeable = 0; new_device->in_fs_metadata = 0; + new_device->can_discard = 0; list_replace_rcu(&device->dev_list, &new_device->dev_list); call_rcu(&device->rcu, free_device); @@ -564,6 +568,7 @@ int btrfs_close_devices(struct btrfs_fs_devices *fs_devices) static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices, fmode_t flags, void *holder) { + struct request_queue *q; struct block_device *bdev; struct list_head *head = &fs_devices->devices; struct btrfs_device *device; @@ -620,6 +625,12 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices, seeding = 0; } + q = bdev_get_queue(bdev); + if (blk_queue_discard(q)) { + device->can_discard = 1; + fs_devices->num_can_discard++; + } + device->bdev = bdev; device->in_fs_metadata = 0; device->mode = flags; @@ -1560,6 +1571,7 @@ error: int btrfs_init_new_device(struct btrfs_root *root, char *device_path) { + struct request_queue *q; struct btrfs_trans_handle *trans; struct btrfs_device *device; struct block_device *bdev; @@ -1629,6 +1641,9 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) lock_chunks(root); + q = bdev_get_queue(bdev); + if (blk_queue_discard(q)) + device->can_discard = 1; device->writeable = 1; device->work.func = pending_bios_fn; generate_random_uuid(device->uuid); @@ -1664,6 +1679,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) root->fs_info->fs_devices->num_devices++; root->fs_info->fs_devices->open_devices++; root->fs_info->fs_devices->rw_devices++; + if (device->can_discard) + root->fs_info->fs_devices->num_can_discard++; root->fs_info->fs_devices->total_rw_bytes += device->total_bytes; if (!blk_queue_nonrot(bdev_get_queue(bdev))) diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 7c12d61ae7ae..6d866db4e177 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -48,6 +48,7 @@ struct btrfs_device { int writeable; int in_fs_metadata; int missing; + int can_discard; spinlock_t io_lock; @@ -104,6 +105,7 @@ struct btrfs_fs_devices { u64 rw_devices; u64 missing_devices; u64 total_rw_bytes; + u64 num_can_discard; struct block_device *latest_bdev; /* all of the devices in the FS, protected by a mutex -- cgit v1.2.3 From 34f3e4f23ca3d259fe078f62a128d97ca83508ef Mon Sep 17 00:00:00 2001 From: liubo Date: Sat, 6 Aug 2011 08:35:23 +0000 Subject: Btrfs: fix an oops of log replay When btrfs recovers from a crash, it may hit the oops below: ------------[ cut here ]------------ kernel BUG at fs/btrfs/inode.c:4580! [...] RIP: 0010:[] [] btrfs_add_link+0x161/0x1c0 [btrfs] [...] Call Trace: [] ? btrfs_inode_ref_index+0x31/0x80 [btrfs] [] add_inode_ref+0x319/0x3f0 [btrfs] [] replay_one_buffer+0x2c7/0x390 [btrfs] [] walk_down_log_tree+0x32a/0x480 [btrfs] [] walk_log_tree+0xf5/0x240 [btrfs] [] btrfs_recover_log_trees+0x250/0x350 [btrfs] [] ? btrfs_recover_log_trees+0x350/0x350 [btrfs] [] open_ctree+0x1442/0x17d0 [btrfs] [...] This comes from that while replaying an inode ref item, we forget to check those old conflicting DIR_ITEM and DIR_INDEX items in fs/file tree, then we will come to conflict corners which lead to BUG_ON(). Signed-off-by: Liu Bo Tested-by: Andy Lutomirski Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index babee65f8eda..786639fca067 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -799,14 +799,15 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, struct extent_buffer *eb, int slot, struct btrfs_key *key) { - struct inode *dir; - int ret; struct btrfs_inode_ref *ref; + struct btrfs_dir_item *di; + struct inode *dir; struct inode *inode; - char *name; - int namelen; unsigned long ref_ptr; unsigned long ref_end; + char *name; + int namelen; + int ret; int search_done = 0; /* @@ -909,6 +910,25 @@ again: } btrfs_release_path(path); + /* look for a conflicting sequence number */ + di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir), + btrfs_inode_ref_index(eb, ref), + name, namelen, 0); + if (di && !IS_ERR(di)) { + ret = drop_one_dir_item(trans, root, path, dir, di); + BUG_ON(ret); + } + btrfs_release_path(path); + + /* look for a conflicing name */ + di = btrfs_lookup_dir_item(trans, root, path, btrfs_ino(dir), + name, namelen, 0); + if (di && !IS_ERR(di)) { + ret = drop_one_dir_item(trans, root, path, dir, di); + BUG_ON(ret); + } + btrfs_release_path(path); + insert: /* insert our name */ ret = btrfs_add_link(trans, dir, inode, name, namelen, 0, -- cgit v1.2.3 From 38c01b9605923cfdff5413e0a12e58ee8d962257 Mon Sep 17 00:00:00 2001 From: liubo Date: Tue, 2 Aug 2011 02:39:03 +0000 Subject: Btrfs: fix a bug of balance on full multi-disk partitions When balancing, we'll first try to shrink devices for some space, but if it is working on a full multi-disk partition with raid protection, we may encounter a bug, that is, while shrinking, total_bytes may be less than bytes_used, and btrfs may allocate a dev extent that accesses out of device's bounds. Then we will not be able to write or read the data which stores at the end of the device, and get the followings: device fsid 0939f071-7ea3-46c8-95df-f176d773bfb6 devid 1 transid 10 /dev/sdb5 Btrfs detected SSD devices, enabling SSD mode btrfs: relocating block group 476315648 flags 9 btrfs: found 4 extents attempt to access beyond end of device sdb5: rw=145, want=546176, limit=546147 attempt to access beyond end of device sdb5: rw=145, want=546304, limit=546147 attempt to access beyond end of device sdb5: rw=145, want=546432, limit=546147 attempt to access beyond end of device sdb5: rw=145, want=546560, limit=546147 attempt to access beyond end of device Signed-off-by: Liu Bo Signed-off-by: Chris Mason --- fs/btrfs/volumes.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a595f8775c37..46f9a208723d 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -863,6 +863,7 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans, max_hole_start = search_start; max_hole_size = 0; + hole_size = 0; if (search_start >= search_end) { ret = -ENOSPC; @@ -945,7 +946,14 @@ next: cond_resched(); } - hole_size = search_end- search_start; + /* + * At this point, search_start should be the end of + * allocated dev extents, and when shrinking the device, + * search_end may be smaller than search_start. + */ + if (search_end > search_start) + hole_size = search_end - search_start; + if (hole_size > max_hole_size) { max_hole_start = search_start; max_hole_size = hole_size; @@ -2447,9 +2455,10 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, total_avail = device->total_bytes - device->bytes_used; else total_avail = 0; - /* avail is off by max(alloc_start, 1MB), but that is the same - * for all devices, so it doesn't hurt the sorting later on - */ + + /* If there is no space on this device, skip it. */ + if (total_avail == 0) + continue; ret = find_free_dev_extent(trans, device, max_stripe_size * dev_stripes, -- cgit v1.2.3 From cdcb725c05fe0cb71777c66ddc2445fedbbb3c59 Mon Sep 17 00:00:00 2001 From: liubo Date: Wed, 3 Aug 2011 10:15:25 +0000 Subject: Btrfs: check if there is enough space for balancing smarter When checking if there is enough space for balancing a block group, since we do not take raid types into consideration, we do not account corrent amounts of space that we needed. This makes us do some extra work before we get ENOSPC. Signed-off-by: Liu Bo Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 41 +++++++++++++++++++++++++++++++++++------ 1 file changed, 35 insertions(+), 6 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 059dfa048cc0..a3e71b59f66e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -6728,6 +6728,10 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr) struct btrfs_space_info *space_info; struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices; struct btrfs_device *device; + u64 min_free; + int index; + int dev_nr = 0; + int dev_min = 1; int full = 0; int ret = 0; @@ -6737,8 +6741,10 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr) if (!block_group) return -1; + min_free = btrfs_block_group_used(&block_group->item); + /* no bytes used, we're good */ - if (!btrfs_block_group_used(&block_group->item)) + if (!min_free) goto out; space_info = block_group->space_info; @@ -6754,10 +6760,9 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr) * all of the extents from this block group. If we can, we're good */ if ((space_info->total_bytes != block_group->key.offset) && - (space_info->bytes_used + space_info->bytes_reserved + - space_info->bytes_pinned + space_info->bytes_readonly + - btrfs_block_group_used(&block_group->item) < - space_info->total_bytes)) { + (space_info->bytes_used + space_info->bytes_reserved + + space_info->bytes_pinned + space_info->bytes_readonly + + min_free < space_info->total_bytes)) { spin_unlock(&space_info->lock); goto out; } @@ -6774,9 +6779,29 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr) if (full) goto out; + /* + * index: + * 0: raid10 + * 1: raid1 + * 2: dup + * 3: raid0 + * 4: single + */ + index = get_block_group_index(block_group); + if (index == 0) { + dev_min = 4; + min_free /= 2; + } else if (index == 1) { + dev_min = 2; + } else if (index == 2) { + min_free *= 2; + } else if (index == 3) { + dev_min = fs_devices->rw_devices; + min_free /= dev_min; + } + mutex_lock(&root->fs_info->chunk_mutex); list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) { - u64 min_free = btrfs_block_group_used(&block_group->item); u64 dev_offset; /* @@ -6787,7 +6812,11 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr) ret = find_free_dev_extent(NULL, device, min_free, &dev_offset, NULL); if (!ret) + dev_nr++; + + if (dev_nr >= dev_min) break; + ret = -1; } } -- cgit v1.2.3 From cb1b69f4508a1e8c1a7907379eafceb7ae0325ef Mon Sep 17 00:00:00 2001 From: Tsutomu Itoh Date: Tue, 9 Aug 2011 07:11:13 +0000 Subject: Btrfs: forced readonly when btrfs_drop_snapshot() fails The filesystem turns readonly instead of returning the error to the caller when detected error in btrfs_drop_snapshot(). and, because the caller doesn't check the error, the function type is changed to 'void'. Signed-off-by: Tsutomu Itoh Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 4 ++-- fs/btrfs/extent-tree.c | 22 ++++++++++++++-------- 2 files changed, 16 insertions(+), 10 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index a6263bdab818..884293642a6c 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2367,8 +2367,8 @@ static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans, int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path); int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path); int btrfs_leaf_free_space(struct btrfs_root *root, struct extent_buffer *leaf); -int btrfs_drop_snapshot(struct btrfs_root *root, - struct btrfs_block_rsv *block_rsv, int update_ref); +void btrfs_drop_snapshot(struct btrfs_root *root, + struct btrfs_block_rsv *block_rsv, int update_ref); int btrfs_drop_subtree(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *node, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index a3e71b59f66e..80d6148f60ac 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -6277,8 +6277,8 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans, * also make sure backrefs for the shared block and all lower level * blocks are properly updated. */ -int btrfs_drop_snapshot(struct btrfs_root *root, - struct btrfs_block_rsv *block_rsv, int update_ref) +void btrfs_drop_snapshot(struct btrfs_root *root, + struct btrfs_block_rsv *block_rsv, int update_ref) { struct btrfs_path *path; struct btrfs_trans_handle *trans; @@ -6291,13 +6291,16 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int level; path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + if (!path) { + err = -ENOMEM; + goto out; + } wc = kzalloc(sizeof(*wc), GFP_NOFS); if (!wc) { btrfs_free_path(path); - return -ENOMEM; + err = -ENOMEM; + goto out; } trans = btrfs_start_transaction(tree_root, 0); @@ -6326,7 +6329,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, path->lowest_level = 0; if (ret < 0) { err = ret; - goto out; + goto out_free; } WARN_ON(ret > 0); @@ -6433,11 +6436,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root, free_extent_buffer(root->commit_root); kfree(root); } -out: +out_free: btrfs_end_transaction_throttle(trans, tree_root); kfree(wc); btrfs_free_path(path); - return err; +out: + if (err) + btrfs_std_error(root->fs_info, err); + return; } /* -- cgit v1.2.3 From c97c2916e25c56e878e3e94efd449e2d688fcb31 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 3 Aug 2011 08:11:41 +0000 Subject: Btrfs: use plain page_address() in header fields setget functions We've stopped using highmem for extent buffers. Signed-off-by: Li Zefan Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 884293642a6c..8b99c79ad1a7 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1415,17 +1415,15 @@ void btrfs_set_##name(struct extent_buffer *eb, type *s, u##bits val); #define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits) \ static inline u##bits btrfs_##name(struct extent_buffer *eb) \ { \ - type *p = kmap_atomic(eb->first_page, KM_USER0); \ + type *p = page_address(eb->first_page); \ u##bits res = le##bits##_to_cpu(p->member); \ - kunmap_atomic(p, KM_USER0); \ return res; \ } \ static inline void btrfs_set_##name(struct extent_buffer *eb, \ u##bits val) \ { \ - type *p = kmap_atomic(eb->first_page, KM_USER0); \ + type *p = page_address(eb->first_page); \ p->member = cpu_to_le##bits(val); \ - kunmap_atomic(p, KM_USER0); \ } #define BTRFS_SETGET_STACK_FUNCS(name, type, member, bits) \ -- cgit v1.2.3 From f4ac904c411b55e58bb240f332f93db2455f0010 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Fri, 5 Aug 2011 14:19:00 +0000 Subject: btrfs: memory leak in btrfs_add_inode_defrag() We don't use the defrag struct on this path. Signed-off-by: Dan Carpenter Signed-off-by: Chris Mason --- fs/btrfs/file.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs/btrfs') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 010aec8be824..0705d15542c6 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -150,6 +150,8 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, spin_lock(&root->fs_info->defrag_inodes_lock); if (!BTRFS_I(inode)->in_defrag) __btrfs_add_inode_defrag(inode, defrag); + else + kfree(defrag); spin_unlock(&root->fs_info->defrag_inodes_lock); return 0; } -- cgit v1.2.3 From bb3ac5a4dfc8eeb881206c77d9f925e320d9c41a Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Fri, 5 Aug 2011 09:32:35 +0000 Subject: Btrfs: fix wrong free space information Btrfs subtracted the size of the allocated space twice when it allocated the space from the bitmap in the cluster, it broke the free space information and led to oops finally. And this patch also fixes the bug that ctl->free_space was subtracted without lock. Reported-by: Liu Bo Signed-off-by: Miao Xie Signed-off-by: Chris Mason --- fs/btrfs/free-space-cache.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 6377713f639c..6a265b9f85f2 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1168,9 +1168,9 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl) div64_u64(extent_bytes, (sizeof(struct btrfs_free_space))); } -static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, - struct btrfs_free_space *info, u64 offset, - u64 bytes) +static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, + struct btrfs_free_space *info, + u64 offset, u64 bytes) { unsigned long start, count; @@ -1181,6 +1181,13 @@ static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, bitmap_clear(info->bitmap, start, count); info->bytes -= bytes; +} + +static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, + struct btrfs_free_space *info, u64 offset, + u64 bytes) +{ + __bitmap_clear_bits(ctl, info, offset, bytes); ctl->free_space -= bytes; } @@ -1984,7 +1991,7 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, return 0; ret = search_start; - bitmap_clear_bits(ctl, entry, ret, bytes); + __bitmap_clear_bits(ctl, entry, ret, bytes); return ret; } @@ -2039,7 +2046,6 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, continue; } } else { - ret = entry->offset; entry->offset += bytes; -- cgit v1.2.3 From 0e588859618be54ec100373f1b86296271ce5307 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Fri, 5 Aug 2011 09:32:37 +0000 Subject: Btrfs: fix uninitialized sync_pending sync_pending is uninitialized before it be used, fix it. Signed-off-by: Miao Xie Signed-off-by: Chris Mason --- fs/btrfs/volumes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 46f9a208723d..f2a4cc79da61 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -142,7 +142,7 @@ static noinline int run_scheduled_bios(struct btrfs_device *device) unsigned long limit; unsigned long last_waited = 0; int force_reg = 0; - int sync_pending; + int sync_pending = 0; struct blk_plug plug; /* -- cgit v1.2.3 From f81c9cdc567cd3160ff9e64868d9a1a7ee226480 Mon Sep 17 00:00:00 2001 From: Sage Weil Date: Wed, 10 Aug 2011 18:04:04 +0000 Subject: Btrfs: truncate pages from clone ioctl target range We need to truncate page cache pages for the clone ioctl target range or else we'll confuse ourselves to no end. If the old data was cached, we used to still see it (until remount). If the page was partially updated we used to get a mix of old and new data. Signed-off-by: Sage Weil Signed-off-by: Chris Mason --- fs/btrfs/ioctl.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'fs/btrfs') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 2bb08862a4f6..b3d249d6eba7 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2244,6 +2244,10 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, btrfs_wait_ordered_range(src, off, len); } + /* truncate page cache pages from target inode range */ + truncate_inode_pages_range(&inode->i_data, off, + ALIGN(off + len, PAGE_CACHE_SIZE) - 1); + /* clone data */ key.objectid = btrfs_ino(src); key.type = BTRFS_EXTENT_DATA_KEY; -- cgit v1.2.3 From f1e490a7ebe41e06324abbbcd86005b0af02a375 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 18 Aug 2011 10:36:39 -0400 Subject: Btrfs: set i_size properly when fallocating and we already xfstests exposed a problem with preallocate when it fallocates a range that already has an extent. We don't set the new i_size properly because we see that we already have an extent. This isn't right and we should update i_size if the space already exists. With this patch we now pass xfstests 075. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/file.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'fs/btrfs') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 0705d15542c6..15e5a1cd8764 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1631,11 +1631,15 @@ static long btrfs_fallocate(struct file *file, int mode, cur_offset = alloc_start; while (1) { + u64 actual_end; + em = btrfs_get_extent(inode, NULL, 0, cur_offset, alloc_end - cur_offset, 0); BUG_ON(IS_ERR_OR_NULL(em)); last_byte = min(extent_map_end(em), alloc_end); + actual_end = min_t(u64, extent_map_end(em), offset + len); last_byte = (last_byte + mask) & ~mask; + if (em->block_start == EXTENT_MAP_HOLE || (cur_offset >= inode->i_size && !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) { @@ -1648,6 +1652,16 @@ static long btrfs_fallocate(struct file *file, int mode, free_extent_map(em); break; } + } else if (actual_end > inode->i_size && + !(mode & FALLOC_FL_KEEP_SIZE)) { + /* + * We didn't need to allocate any more space, but we + * still extended the size of the file so we need to + * update i_size. + */ + inode->i_ctime = CURRENT_TIME; + i_size_write(inode, actual_end); + btrfs_ordered_update_i_size(inode, actual_end, NULL); } free_extent_map(em); -- cgit v1.2.3