From 143bede527b054a271053f41bfaca2b57baa9408 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Thu, 1 Mar 2012 14:56:26 +0100 Subject: btrfs: return void in functions without error conditions Signed-off-by: Jeff Mahoney --- fs/btrfs/volumes.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index ef41f285a475..1c5f8a4a2bbd 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -67,7 +67,7 @@ static void free_fs_devices(struct btrfs_fs_devices *fs_devices) kfree(fs_devices); } -int btrfs_cleanup_fs_uuids(void) +void btrfs_cleanup_fs_uuids(void) { struct btrfs_fs_devices *fs_devices; @@ -77,7 +77,6 @@ int btrfs_cleanup_fs_uuids(void) list_del(&fs_devices->list); free_fs_devices(fs_devices); } - return 0; } static noinline struct btrfs_device *__find_device(struct list_head *head, @@ -130,7 +129,7 @@ static void requeue_list(struct btrfs_pending_bios *pending_bios, * the list if the block device is congested. This way, multiple devices * can make progress from a single worker thread. */ -static noinline int run_scheduled_bios(struct btrfs_device *device) +static noinline void run_scheduled_bios(struct btrfs_device *device) { struct bio *pending; struct backing_dev_info *bdi; @@ -316,7 +315,6 @@ loop_lock: done: blk_finish_plug(&plug); - return 0; } static void pending_bios_fn(struct btrfs_work *work) @@ -455,7 +453,7 @@ error: return ERR_PTR(-ENOMEM); } -int btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices) +void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices) { struct btrfs_device *device, *next; @@ -503,7 +501,6 @@ again: fs_devices->latest_trans = latest_transid; mutex_unlock(&uuid_mutex); - return 0; } static void __free_device(struct work_struct *work) @@ -3967,7 +3964,7 @@ struct async_sched { * This will add one bio to the pending list for a device and make sure * the work struct is scheduled. */ -static noinline int schedule_bio(struct btrfs_root *root, +static noinline void schedule_bio(struct btrfs_root *root, struct btrfs_device *device, int rw, struct bio *bio) { @@ -3979,7 +3976,7 @@ static noinline int schedule_bio(struct btrfs_root *root, bio_get(bio); btrfsic_submit_bio(rw, bio); bio_put(bio); - return 0; + return; } /* @@ -4013,7 +4010,6 @@ static noinline int schedule_bio(struct btrfs_root *root, if (should_queue) btrfs_queue_worker(&root->fs_info->submit_workers, &device->work); - return 0; } int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, @@ -4215,7 +4211,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key, return 0; } -static int fill_device_from_item(struct extent_buffer *leaf, +static void fill_device_from_item(struct extent_buffer *leaf, struct btrfs_dev_item *dev_item, struct btrfs_device *device) { @@ -4232,8 +4228,6 @@ static int fill_device_from_item(struct extent_buffer *leaf, ptr = (unsigned long)btrfs_device_uuid(dev_item); read_extent_buffer(leaf, device->uuid, ptr, BTRFS_UUID_SIZE); - - return 0; } static int open_seed_devices(struct btrfs_root *root, u8 *fsid) -- cgit From 4ed1d16e944c61cfb8a78159548672e7df168d97 Mon Sep 17 00:00:00 2001 From: Mark Fasheh Date: Wed, 10 Aug 2011 12:32:10 -0700 Subject: btrfs: Don't BUG_ON errors in __finish_chunk_alloc() All callers of __finish_chunk_alloc() BUG_ON() return value, so it's trivial for us to always bubble up any errors caught in __finish_chunk_alloc() to be caught there. Signed-off-by: Mark Fasheh --- fs/btrfs/volumes.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 1c5f8a4a2bbd..c4ea7d8bea0f 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3417,16 +3417,18 @@ static int __finish_chunk_alloc(struct btrfs_trans_handle *trans, key.offset = chunk_offset; ret = btrfs_insert_item(trans, chunk_root, &key, chunk, item_size); - BUG_ON(ret); - if (map->type & BTRFS_BLOCK_GROUP_SYSTEM) { + if (ret == 0 && map->type & BTRFS_BLOCK_GROUP_SYSTEM) { + /* + * TODO: Cleanup of inserted chunk root in case of + * failure. + */ ret = btrfs_add_system_chunk(chunk_root, &key, chunk, item_size); - BUG_ON(ret); } kfree(chunk); - return 0; + return ret; } /* -- cgit From 2cdcecbc153c222fae1be6f8ddb320b29e3a5200 Mon Sep 17 00:00:00 2001 From: Mark Fasheh Date: Thu, 8 Sep 2011 17:14:32 -0700 Subject: btrfs: Don't BUG_ON insert errors in btrfs_alloc_dev_extent() The only caller of btrfs_alloc_dev_extent() is __btrfs_alloc_chunk() which already bugs on any error returned. We can remove the BUG_ON's in btrfs_alloc_dev_extent() then since __btrfs_alloc_chunk() will "catch" them anyway. Signed-off-by: Mark Fasheh --- fs/btrfs/volumes.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index c4ea7d8bea0f..281ff354f64f 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1075,7 +1075,8 @@ int btrfs_alloc_dev_extent(struct btrfs_trans_handle *trans, key.type = BTRFS_DEV_EXTENT_KEY; ret = btrfs_insert_empty_item(trans, root, path, &key, sizeof(*extent)); - BUG_ON(ret); + if (ret) + goto out; leaf = path->nodes[0]; extent = btrfs_item_ptr(leaf, path->slots[0], @@ -1090,6 +1091,7 @@ int btrfs_alloc_dev_extent(struct btrfs_trans_handle *trans, btrfs_set_dev_extent_length(leaf, extent, num_bytes); btrfs_mark_buffer_dirty(leaf); +out: btrfs_free_path(path); return ret; } -- cgit From 1dd4602fa74273c28b3577a58aa389f330e9a0dc Mon Sep 17 00:00:00 2001 From: Mark Fasheh Date: Thu, 8 Sep 2011 17:29:00 -0700 Subject: btrfs: Remove BUG_ON from __btrfs_alloc_chunk() We BUG_ON() error from add_extent_mapping(), but that error looks pretty easy to bubble back up - as far as I can tell there have not been any permanent modifications to fs state at that point. Signed-off-by: Mark Fasheh --- fs/btrfs/volumes.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 281ff354f64f..f002973959d0 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3327,8 +3327,9 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, write_lock(&em_tree->lock); ret = add_extent_mapping(em_tree, em); write_unlock(&em_tree->lock); - BUG_ON(ret); free_extent_map(em); + if (ret) + goto error; ret = btrfs_make_block_group(trans, extent_root, 0, type, BTRFS_FIRST_CHUNK_TREE_OBJECTID, -- cgit From 3acd395317f22b4346a139571cd4723408c5d4af Mon Sep 17 00:00:00 2001 From: Mark Fasheh Date: Thu, 8 Sep 2011 17:40:01 -0700 Subject: btrfs: Remove BUG_ON from __finish_chunk_alloc() btrfs_alloc_chunk() unconditionally BUGs on any error returned from __finish_chunk_alloc() so there's no need for two BUG_ON lines. Remove the one from __finish_chunk_alloc(). Signed-off-by: Mark Fasheh --- fs/btrfs/volumes.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index f002973959d0..394bf15ea18c 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3383,7 +3383,8 @@ static int __finish_chunk_alloc(struct btrfs_trans_handle *trans, device = map->stripes[index].dev; device->bytes_used += stripe_size; ret = btrfs_update_device(trans, device); - BUG_ON(ret); + if (ret) + goto out_free; index++; } @@ -3430,6 +3431,7 @@ static int __finish_chunk_alloc(struct btrfs_trans_handle *trans, item_size); } +out_free: kfree(chunk); return ret; } -- cgit From 79787eaab46121d4713ed03c8fc63b9ec3eaec76 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 12 Mar 2012 16:03:00 +0100 Subject: btrfs: replace many BUG_ONs with proper error handling btrfs currently handles most errors with BUG_ON. This patch is a work-in- progress but aims to handle most errors other than internal logic errors and ENOMEM more gracefully. This iteration prevents most crashes but can run into lockups with the page lock on occasion when the timing "works out." Signed-off-by: Jeff Mahoney --- fs/btrfs/volumes.c | 103 +++++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 76 insertions(+), 27 deletions(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 394bf15ea18c..57305e88ea82 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -549,10 +549,10 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices) fs_devices->num_can_discard--; new_device = kmalloc(sizeof(*new_device), GFP_NOFS); - BUG_ON(!new_device); + BUG_ON(!new_device); /* -ENOMEM */ memcpy(new_device, device, sizeof(*new_device)); new_device->name = kstrdup(device->name, GFP_NOFS); - BUG_ON(device->name && !new_device->name); + BUG_ON(device->name && !new_device->name); /* -ENOMEM */ new_device->bdev = NULL; new_device->writeable = 0; new_device->in_fs_metadata = 0; @@ -1036,8 +1036,10 @@ again: leaf = path->nodes[0]; extent = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dev_extent); + } else { + btrfs_error(root->fs_info, ret, "Slot search failed"); + goto out; } - BUG_ON(ret); if (device->bytes_used > 0) { u64 len = btrfs_dev_extent_length(leaf, extent); @@ -1047,7 +1049,10 @@ again: spin_unlock(&root->fs_info->free_chunk_lock); } ret = btrfs_del_item(trans, root, path); - + if (ret) { + btrfs_error(root->fs_info, ret, + "Failed to remove dev extent item"); + } out: btrfs_free_path(path); return ret; @@ -1117,7 +1122,7 @@ static noinline int find_next_chunk(struct btrfs_root *root, if (ret < 0) goto error; - BUG_ON(ret == 0); + BUG_ON(ret == 0); /* Corruption */ ret = btrfs_previous_item(root, path, 0, BTRFS_CHUNK_ITEM_KEY); if (ret) { @@ -1161,7 +1166,7 @@ static noinline int find_next_devid(struct btrfs_root *root, u64 *objectid) if (ret < 0) goto error; - BUG_ON(ret == 0); + BUG_ON(ret == 0); /* Corruption */ ret = btrfs_previous_item(root, path, BTRFS_DEV_ITEMS_OBJECTID, BTRFS_DEV_ITEM_KEY); @@ -1595,7 +1600,7 @@ next_slot: (unsigned long)btrfs_device_fsid(dev_item), BTRFS_UUID_SIZE); device = btrfs_find_device(root, devid, dev_uuid, fs_uuid); - BUG_ON(!device); + BUG_ON(!device); /* Logic error */ if (device->fs_devices->seeding) { btrfs_set_device_generation(leaf, dev_item, @@ -1705,7 +1710,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) if (seeding_dev) { sb->s_flags &= ~MS_RDONLY; ret = btrfs_prepare_sprout(root); - BUG_ON(ret); + BUG_ON(ret); /* -ENOMEM */ } device->fs_devices = root->fs_info->fs_devices; @@ -1743,11 +1748,15 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) if (seeding_dev) { ret = init_first_rw_device(trans, root, device); - BUG_ON(ret); + if (ret) + goto error_trans; ret = btrfs_finish_sprout(trans, root); - BUG_ON(ret); + if (ret) + goto error_trans; } else { ret = btrfs_add_device(trans, root, device); + if (ret) + goto error_trans; } /* @@ -1757,17 +1766,31 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) btrfs_clear_space_info_full(root->fs_info); unlock_chunks(root); - btrfs_commit_transaction(trans, root); + ret = btrfs_commit_transaction(trans, root); if (seeding_dev) { mutex_unlock(&uuid_mutex); up_write(&sb->s_umount); + if (ret) /* transaction commit */ + return ret; + ret = btrfs_relocate_sys_chunks(root); - BUG_ON(ret); + if (ret < 0) + btrfs_error(root->fs_info, ret, + "Failed to relocate sys chunks after " + "device initialization. This can be fixed " + "using the \"btrfs balance\" command."); } return ret; + +error_trans: + unlock_chunks(root); + btrfs_abort_transaction(trans, root, ret); + btrfs_end_transaction(trans, root); + kfree(device->name); + kfree(device); error: blkdev_put(bdev, FMODE_EXCL); if (seeding_dev) { @@ -1875,10 +1898,20 @@ static int btrfs_free_chunk(struct btrfs_trans_handle *trans, key.type = BTRFS_CHUNK_ITEM_KEY; ret = btrfs_search_slot(trans, root, &key, path, -1, 1); - BUG_ON(ret); + if (ret < 0) + goto out; + else if (ret > 0) { /* Logic error or corruption */ + btrfs_error(root->fs_info, -ENOENT, + "Failed lookup while freeing chunk."); + ret = -ENOENT; + goto out; + } ret = btrfs_del_item(trans, root, path); - + if (ret < 0) + btrfs_error(root->fs_info, ret, + "Failed to delete chunk item."); +out: btrfs_free_path(path); return ret; } @@ -2040,7 +2073,7 @@ again: ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0); if (ret < 0) goto error; - BUG_ON(ret == 0); + BUG_ON(ret == 0); /* Corruption */ ret = btrfs_previous_item(chunk_root, path, key.objectid, key.type); @@ -3334,7 +3367,8 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, ret = btrfs_make_block_group(trans, extent_root, 0, type, BTRFS_FIRST_CHUNK_TREE_OBJECTID, start, num_bytes); - BUG_ON(ret); + if (ret) + goto error; for (i = 0; i < map->num_stripes; ++i) { struct btrfs_device *device; @@ -3347,7 +3381,10 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, info->chunk_root->root_key.objectid, BTRFS_FIRST_CHUNK_TREE_OBJECTID, start, dev_offset, stripe_size); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, extent_root, ret); + goto error; + } } kfree(devices_info); @@ -3465,7 +3502,8 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, ret = __finish_chunk_alloc(trans, extent_root, map, chunk_offset, chunk_size, stripe_size); - BUG_ON(ret); + if (ret) + return ret; return 0; } @@ -3497,7 +3535,8 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans, ret = __btrfs_alloc_chunk(trans, extent_root, &map, &chunk_size, &stripe_size, chunk_offset, alloc_profile); - BUG_ON(ret); + if (ret) + return ret; sys_chunk_offset = chunk_offset + chunk_size; @@ -3508,10 +3547,12 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans, ret = __btrfs_alloc_chunk(trans, extent_root, &sys_map, &sys_chunk_size, &sys_stripe_size, sys_chunk_offset, alloc_profile); - BUG_ON(ret); + if (ret) + goto abort; ret = btrfs_add_device(trans, fs_info->chunk_root, device); - BUG_ON(ret); + if (ret) + goto abort; /* * Modifying chunk tree needs allocating new blocks from both @@ -3521,13 +3562,20 @@ static noinline int init_first_rw_device(struct btrfs_trans_handle *trans, */ ret = __finish_chunk_alloc(trans, extent_root, map, chunk_offset, chunk_size, stripe_size); - BUG_ON(ret); + if (ret) + goto abort; ret = __finish_chunk_alloc(trans, extent_root, sys_map, sys_chunk_offset, sys_chunk_size, sys_stripe_size); - BUG_ON(ret); + if (ret) + goto abort; + return 0; + +abort: + btrfs_abort_transaction(trans, root, ret); + return ret; } int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset) @@ -3878,7 +3926,7 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree, do_div(length, map->num_stripes); buf = kzalloc(sizeof(u64) * map->num_stripes, GFP_NOFS); - BUG_ON(!buf); + BUG_ON(!buf); /* -ENOMEM */ for (i = 0; i < map->num_stripes; i++) { if (devid && map->stripes[i].dev->devid != devid) @@ -4039,7 +4087,8 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, ret = btrfs_map_block(map_tree, rw, logical, &map_length, &bbio, mirror_num); - BUG_ON(ret); + if (ret) /* -ENOMEM */ + return ret; total_devs = bbio->num_stripes; if (map_length < length) { @@ -4058,7 +4107,7 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, while (dev_nr < total_devs) { if (dev_nr < total_devs - 1) { bio = bio_clone(first_bio, GFP_NOFS); - BUG_ON(!bio); + BUG_ON(!bio); /* -ENOMEM */ } else { bio = first_bio; } @@ -4212,7 +4261,7 @@ static int read_one_chunk(struct btrfs_root *root, struct btrfs_key *key, write_lock(&map_tree->map_tree.lock); ret = add_extent_mapping(&map_tree->map_tree, em); write_unlock(&map_tree->map_tree.lock); - BUG_ON(ret); + BUG_ON(ret); /* Tree corruption */ free_extent_map(em); return 0; -- cgit From 727011e07cbdf87772fcc1999cccd15cc915eb62 Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Fri, 6 Aug 2010 13:21:20 -0400 Subject: Btrfs: allow metadata blocks larger than the page size A few years ago the btrfs code to support blocks lager than the page size was disabled to fix a few corner cases in the page cache handling. This fixes the code to properly support large metadata blocks again. Since current kernels will crash early and often with larger metadata blocks, this adds an incompat bit so that older kernels can't mount it. This also does away with different blocksizes for nodes and leaves. You get a single block size for all tree blocks. Signed-off-by: Chris Mason --- fs/btrfs/volumes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index ef41f285a475..58aad63e1ad3 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4384,7 +4384,7 @@ int btrfs_read_sys_array(struct btrfs_root *root) * to silence the warning eg. on PowerPC 64. */ if (PAGE_CACHE_SIZE > BTRFS_SUPER_INFO_SIZE) - SetPageUptodate(sb->first_page); + SetPageUptodate(sb->pages[0]); write_extent_buffer(sb, super_copy, 0, BTRFS_SUPER_INFO_SIZE); array_size = btrfs_super_sys_array_size(super_copy); -- cgit From 899c81eac890bcfa5f3636f4c43f68e8393ac1f8 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 27 Mar 2012 17:09:16 +0300 Subject: Btrfs: add wrappers for working with alloc profiles Add functions to abstract the conversion between chunk and extended allocation profile formats and switch everybody to use them. Signed-off-by: Ilya Dryomov --- fs/btrfs/volumes.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 58aad63e1ad3..4b263a2009b0 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2250,15 +2250,13 @@ static void unset_balance_control(struct btrfs_fs_info *fs_info) * Balance filters. Return 1 if chunk should be filtered out * (should not be balanced). */ -static int chunk_profiles_filter(u64 chunk_profile, +static int chunk_profiles_filter(u64 chunk_type, struct btrfs_balance_args *bargs) { - chunk_profile &= BTRFS_BLOCK_GROUP_PROFILE_MASK; + chunk_type = chunk_to_extended(chunk_type) & + BTRFS_EXTENDED_PROFILE_MASK; - if (chunk_profile == 0) - chunk_profile = BTRFS_AVAIL_ALLOC_BIT_SINGLE; - - if (bargs->profiles & chunk_profile) + if (bargs->profiles & chunk_type) return 0; return 1; @@ -2365,18 +2363,16 @@ static int chunk_vrange_filter(struct extent_buffer *leaf, return 1; } -static int chunk_soft_convert_filter(u64 chunk_profile, +static int chunk_soft_convert_filter(u64 chunk_type, struct btrfs_balance_args *bargs) { if (!(bargs->flags & BTRFS_BALANCE_ARGS_CONVERT)) return 0; - chunk_profile &= BTRFS_BLOCK_GROUP_PROFILE_MASK; - - if (chunk_profile == 0) - chunk_profile = BTRFS_AVAIL_ALLOC_BIT_SINGLE; + chunk_type = chunk_to_extended(chunk_type) & + BTRFS_EXTENDED_PROFILE_MASK; - if (bargs->target & chunk_profile) + if (bargs->target == chunk_type) return 1; return 0; -- cgit From e8920a640be5d4ebe3fee0670639a81d4ffc904c Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 27 Mar 2012 17:09:17 +0300 Subject: Btrfs: make profile_is_valid() check more strict "0" is a valid value for an on-disk chunk profile, but it is not a valid extended profile. (We have a separate bit for single chunks in extended case) Also rename it to alloc_profile_is_valid() for clarity. Signed-off-by: Ilya Dryomov --- fs/btrfs/volumes.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 4b263a2009b0..e4ef0f2fdb73 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2669,7 +2669,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl, allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10); - if (!profile_is_valid(bctl->data.target, 1) || + if (!alloc_profile_is_valid(bctl->data.target, 1) || bctl->data.target & ~allowed) { printk(KERN_ERR "btrfs: unable to start balance with target " "data profile %llu\n", @@ -2677,7 +2677,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl, ret = -EINVAL; goto out; } - if (!profile_is_valid(bctl->meta.target, 1) || + if (!alloc_profile_is_valid(bctl->meta.target, 1) || bctl->meta.target & ~allowed) { printk(KERN_ERR "btrfs: unable to start balance with target " "metadata profile %llu\n", @@ -2685,7 +2685,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl, ret = -EINVAL; goto out; } - if (!profile_is_valid(bctl->sys.target, 1) || + if (!alloc_profile_is_valid(bctl->sys.target, 1) || bctl->sys.target & ~allowed) { printk(KERN_ERR "btrfs: unable to start balance with target " "system profile %llu\n", -- cgit From 0c460c0d70e10463e44bdf1d406e9c5ec03b1af6 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 27 Mar 2012 17:09:17 +0300 Subject: Btrfs: move alloc_profile_is_valid() to volumes.c Header file is not a good place to define functions. This also moves a call to alloc_profile_is_valid() down the stack and removes a redundant check from __btrfs_alloc_chunk() - alloc_profile_is_valid() takes it into account. Signed-off-by: Ilya Dryomov --- fs/btrfs/volumes.c | 30 +++++++++++++++++++++++++----- 1 file changed, 25 insertions(+), 5 deletions(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index e4ef0f2fdb73..def9e25f87f2 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2598,6 +2598,30 @@ error: return ret; } +/** + * alloc_profile_is_valid - see if a given profile is valid and reduced + * @flags: profile to validate + * @extended: if true @flags is treated as an extended profile + */ +static int alloc_profile_is_valid(u64 flags, int extended) +{ + u64 mask = (extended ? BTRFS_EXTENDED_PROFILE_MASK : + BTRFS_BLOCK_GROUP_PROFILE_MASK); + + flags &= ~BTRFS_BLOCK_GROUP_TYPE_MASK; + + /* 1) check that all other bits are zeroed */ + if (flags & ~mask) + return 0; + + /* 2) see if profile is reduced */ + if (flags == 0) + return !extended; /* "0" is valid for usual profiles */ + + /* true if exactly one bit set */ + return (flags & (flags - 1)) == 0; +} + static inline int balance_need_close(struct btrfs_fs_info *fs_info) { /* cancel requested || normal exit path */ @@ -3124,11 +3148,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, int i; int j; - if ((type & BTRFS_BLOCK_GROUP_RAID1) && - (type & BTRFS_BLOCK_GROUP_DUP)) { - WARN_ON(1); - type &= ~BTRFS_BLOCK_GROUP_DUP; - } + BUG_ON(!alloc_profile_is_valid(type, 0)); if (list_empty(&fs_devices->alloc_list)) return -ENOSPC; -- cgit From 6728b198deb02c187b5e5a99eb7d1cc9c8bc65e9 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 27 Mar 2012 17:09:17 +0300 Subject: Btrfs: validate target profiles only if we are going to use them Do not run sanity checks on all target profiles unless they all will be used. This came up because alloc_profile_is_valid() is now more strict than it used to be. Signed-off-by: Ilya Dryomov --- fs/btrfs/volumes.c | 27 +++++++++++---------------- 1 file changed, 11 insertions(+), 16 deletions(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index def9e25f87f2..28addea5b0f2 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2676,14 +2676,6 @@ int btrfs_balance(struct btrfs_balance_control *bctl, } } - /* - * Profile changing sanity checks. Skip them if a simple - * balance is requested. - */ - if (!((bctl->data.flags | bctl->sys.flags | bctl->meta.flags) & - BTRFS_BALANCE_ARGS_CONVERT)) - goto do_balance; - allowed = BTRFS_AVAIL_ALLOC_BIT_SINGLE; if (fs_info->fs_devices->num_devices == 1) allowed |= BTRFS_BLOCK_GROUP_DUP; @@ -2693,24 +2685,27 @@ int btrfs_balance(struct btrfs_balance_control *bctl, allowed |= (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10); - if (!alloc_profile_is_valid(bctl->data.target, 1) || - bctl->data.target & ~allowed) { + if ((bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) && + (!alloc_profile_is_valid(bctl->data.target, 1) || + (bctl->data.target & ~allowed))) { printk(KERN_ERR "btrfs: unable to start balance with target " "data profile %llu\n", (unsigned long long)bctl->data.target); ret = -EINVAL; goto out; } - if (!alloc_profile_is_valid(bctl->meta.target, 1) || - bctl->meta.target & ~allowed) { + if ((bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) && + (!alloc_profile_is_valid(bctl->meta.target, 1) || + (bctl->meta.target & ~allowed))) { printk(KERN_ERR "btrfs: unable to start balance with target " "metadata profile %llu\n", (unsigned long long)bctl->meta.target); ret = -EINVAL; goto out; } - if (!alloc_profile_is_valid(bctl->sys.target, 1) || - bctl->sys.target & ~allowed) { + if ((bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) && + (!alloc_profile_is_valid(bctl->sys.target, 1) || + (bctl->sys.target & ~allowed))) { printk(KERN_ERR "btrfs: unable to start balance with target " "system profile %llu\n", (unsigned long long)bctl->sys.target); @@ -2718,7 +2713,8 @@ int btrfs_balance(struct btrfs_balance_control *bctl, goto out; } - if (bctl->data.target & BTRFS_BLOCK_GROUP_DUP) { + if ((bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) && + (bctl->data.target & BTRFS_BLOCK_GROUP_DUP)) { printk(KERN_ERR "btrfs: dup for data is not allowed\n"); ret = -EINVAL; goto out; @@ -2744,7 +2740,6 @@ int btrfs_balance(struct btrfs_balance_control *bctl, } } -do_balance: ret = insert_balance_item(fs_info->tree_root, bctl); if (ret && ret != -EEXIST) goto out; -- cgit From e4837f8f3b5d08b8c708533a71439bfb40ede467 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 27 Mar 2012 17:09:17 +0300 Subject: Btrfs: allow dup for data chunks in mixed mode Generally we don't allow dup for data, but mixed chunks are special and people seem to think this has its use cases. Signed-off-by: Ilya Dryomov --- fs/btrfs/volumes.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 28addea5b0f2..bcc0acda8691 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2650,6 +2650,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl, { struct btrfs_fs_info *fs_info = bctl->fs_info; u64 allowed; + int mixed = 0; int ret; if (btrfs_fs_closing(fs_info) || @@ -2659,13 +2660,16 @@ int btrfs_balance(struct btrfs_balance_control *bctl, goto out; } + allowed = btrfs_super_incompat_flags(fs_info->super_copy); + if (allowed & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) + mixed = 1; + /* * In case of mixed groups both data and meta should be picked, * and identical options should be given for both of them. */ - allowed = btrfs_super_incompat_flags(fs_info->super_copy); - if ((allowed & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) && - (bctl->flags & (BTRFS_BALANCE_DATA | BTRFS_BALANCE_METADATA))) { + allowed = BTRFS_BALANCE_DATA | BTRFS_BALANCE_METADATA; + if (mixed && (bctl->flags & allowed)) { if (!(bctl->flags & BTRFS_BALANCE_DATA) || !(bctl->flags & BTRFS_BALANCE_METADATA) || memcmp(&bctl->data, &bctl->meta, sizeof(bctl->data))) { @@ -2713,7 +2717,8 @@ int btrfs_balance(struct btrfs_balance_control *bctl, goto out; } - if ((bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) && + /* allow dup'ed data chunks only in mixed mode */ + if (!mixed && (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) && (bctl->data.target & BTRFS_BLOCK_GROUP_DUP)) { printk(KERN_ERR "btrfs: dup for data is not allowed\n"); ret = -EINVAL; -- cgit From 213e64da90d14537cd63f7090d6c4d1fcc75d9f8 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Tue, 27 Mar 2012 17:09:18 +0300 Subject: Btrfs: fix infinite loop in btrfs_shrink_device() If relocate of block group 0 fails with ENOSPC we end up infinitely looping because key.offset -= 1 statement in that case brings us back to where we started. Signed-off-by: Ilya Dryomov --- fs/btrfs/volumes.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index bcc0acda8691..be2d4e0e6cfb 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2987,7 +2987,7 @@ again: key.offset = (u64)-1; key.type = BTRFS_DEV_EXTENT_KEY; - while (1) { + do { ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto done; @@ -3029,8 +3029,7 @@ again: goto done; if (ret == -ENOSPC) failed++; - key.offset -= 1; - } + } while (key.offset-- > 0); if (failed && !retried) { failed = 0; -- cgit From 3c4bb26b213e618473e486776483a5bad15ba6da Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Tue, 27 Mar 2012 18:56:56 -0400 Subject: Btrfs: flush out and clean up any block device pages during mount Btrfs puts the filesystem metadata into its own address space, and somehow the block device address space isn't getting onto disk properly before a mount. The end result is that a loop of mkfs and mounting the filesystem will sometimes find stale or incorrect data. This commit should fix it by sprinkling fdatawrites and invalidate_bdev calls around. This is a short term measure to make sure it is fixed. The block devices really should be flushed and cleaned up higher in the stack. Signed-off-by: Chris Mason --- fs/btrfs/volumes.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 68a1754fe367..a872b48be0ae 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -622,6 +622,8 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices, printk(KERN_INFO "open %s failed\n", device->name); goto error; } + filemap_write_and_wait(bdev->bd_inode->i_mapping); + invalidate_bdev(bdev); set_blocksize(bdev, 4096); bh = btrfs_read_dev_super(bdev); @@ -1354,6 +1356,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) } set_blocksize(bdev, 4096); + invalidate_bdev(bdev); bh = btrfs_read_dev_super(bdev); if (!bh) { ret = -EINVAL; -- cgit From b89203f74bdfcb15407d54d3f257b16a2ea19e62 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Thu, 12 Apr 2012 16:03:56 -0400 Subject: Btrfs: fix eof while discarding extents We miscalculate the length of extents we're discarding, and it leads to an eof of device. Reported-by: Daniel Blueman Signed-off-by: Liu Bo Signed-off-by: Chris Mason --- fs/btrfs/volumes.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a872b48be0ae..759d02486d7c 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3833,6 +3833,7 @@ static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw, int sub_stripes = 0; u64 stripes_per_dev = 0; u32 remaining_stripes = 0; + u32 last_stripe = 0; if (map->type & (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10)) { @@ -3846,6 +3847,8 @@ static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw, stripe_nr_orig, factor, &remaining_stripes); + div_u64_rem(stripe_nr_end - 1, factor, &last_stripe); + last_stripe *= sub_stripes; } for (i = 0; i < num_stripes; i++) { @@ -3858,16 +3861,29 @@ static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw, BTRFS_BLOCK_GROUP_RAID10)) { bbio->stripes[i].length = stripes_per_dev * map->stripe_len; + if (i / sub_stripes < remaining_stripes) bbio->stripes[i].length += map->stripe_len; + + /* + * Special for the first stripe and + * the last stripe: + * + * |-------|...|-------| + * |----------| + * off end_off + */ if (i < sub_stripes) bbio->stripes[i].length -= stripe_offset; - if ((i / sub_stripes + 1) % - sub_stripes == remaining_stripes) + + if (stripe_index >= last_stripe && + stripe_index <= (last_stripe + + sub_stripes - 1)) bbio->stripes[i].length -= stripe_end_offset; + if (i == sub_stripes - 1) stripe_offset = 0; } else -- cgit From 37db63a400d3bac467795aa43901065fd8d903b7 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Fri, 13 Apr 2012 17:05:08 +0300 Subject: Btrfs: fix max chunk size check in chunk allocator Fix a bug, where in case we need to adjust stripe_size so that the length of the resulting chunk is less than or equal to max_chunk_size, DUP chunks turn out to be only half as big as they could be. Cc: Arne Jansen Signed-off-by: Ilya Dryomov --- fs/btrfs/volumes.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 759d02486d7c..ce289af526f0 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3324,12 +3324,14 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, stripe_size = devices_info[ndevs-1].max_avail; num_stripes = ndevs * dev_stripes; - if (stripe_size * num_stripes > max_chunk_size * ncopies) { + if (stripe_size * ndevs > max_chunk_size * ncopies) { stripe_size = max_chunk_size * ncopies; - do_div(stripe_size, num_stripes); + do_div(stripe_size, ndevs); } do_div(stripe_size, dev_stripes); + + /* align to BTRFS_STRIPE_LEN */ do_div(stripe_size, BTRFS_STRIPE_LEN); stripe_size *= BTRFS_STRIPE_LEN; -- cgit From 48d282326b3ce5f435835f5fb0e3231c399f4f9a Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Sat, 14 Apr 2012 11:24:33 +0200 Subject: fs/btrfs/volumes.c: add missing free_fs_devices Free fs_devices as done in the error-handling code just below. Signed-off-by: Julia Lawall --- fs/btrfs/volumes.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index ce289af526f0..3b984173d25b 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4352,8 +4352,10 @@ static int open_seed_devices(struct btrfs_root *root, u8 *fsid) ret = __btrfs_open_devices(fs_devices, FMODE_READ, root->fs_info->bdev_holder); - if (ret) + if (ret) { + free_fs_devices(fs_devices); goto out; + } if (!fs_devices->seeding) { __btrfs_close_devices(fs_devices); -- cgit From 3e74317ad773ba9df36db1fa32848cba41ac4d1a Mon Sep 17 00:00:00 2001 From: Jan Schmidt Date: Fri, 27 Apr 2012 12:41:45 -0400 Subject: Btrfs: fix repair code for RAID10 btrfs_map_block sets mirror_num, so that the repair code knows eventually which device gave us the read error. For RAID10, mirror_num must be 1 or 2. Before this fix mirror_num was incorrectly related to our stripe index. Signed-off-by: Jan Schmidt Signed-off-by: Chris Mason --- fs/btrfs/volumes.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 3b984173d25b..1411b99555a4 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3807,10 +3807,11 @@ static int __btrfs_map_block(struct btrfs_mapping_tree *map_tree, int rw, else if (mirror_num) stripe_index += mirror_num - 1; else { + int old_stripe_index = stripe_index; stripe_index = find_live_mirror(map, stripe_index, map->sub_stripes, stripe_index + current->pid % map->sub_stripes); - mirror_num = stripe_index + 1; + mirror_num = stripe_index - old_stripe_index + 1; } } else { /* -- cgit From f8c5d0b443ff87c43ba690fa2b5bd2c9387d8624 Mon Sep 17 00:00:00 2001 From: Liu Bo Date: Thu, 10 May 2012 18:10:38 +0800 Subject: Btrfs: fix wrong error returned by adding a device Reproduce: $ mkfs.btrfs /dev/sdb7 $ mount /dev/sdb7 /mnt/btrfs -o ro $ btrfs dev add /dev/sdb8 /mnt/btrfs ERROR: error adding the device '/dev/sdb8' - Invalid argument Since we mount with readonly options, and /dev/sdb7 is not a seeding one, a readonly notification is preferred. Signed-off-by: Liu Bo Reviewed-by: Josef Bacik --- fs/btrfs/volumes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 1411b99555a4..48a06d1fc067 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1633,7 +1633,7 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) int ret = 0; if ((sb->s_flags & MS_RDONLY) && !root->fs_info->fs_devices->seeding) - return -EINVAL; + return -EROFS; bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL, root->fs_info->bdev_holder); -- cgit From 442a4f6308e694e0fa6025708bd5e4e424bbf51c Mon Sep 17 00:00:00 2001 From: Stefan Behrens Date: Fri, 25 May 2012 16:06:08 +0200 Subject: Btrfs: add device counters for detected IO and checksum errors The goal is to detect when drives start to get an increased error rate, when drives should be replaced soon. Therefore statistic counters are added that count IO errors (read, write and flush). Additionally, the software detected errors like checksum errors and corrupted blocks are counted. Signed-off-by: Stefan Behrens --- fs/btrfs/volumes.c | 94 ++++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 92 insertions(+), 2 deletions(-) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 48a06d1fc067..2915521f44ee 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include #include "compat.h" @@ -4001,13 +4002,58 @@ int btrfs_rmap_block(struct btrfs_mapping_tree *map_tree, return 0; } +static void *merge_stripe_index_into_bio_private(void *bi_private, + unsigned int stripe_index) +{ + /* + * with single, dup, RAID0, RAID1 and RAID10, stripe_index is + * at most 1. + * The alternative solution (instead of stealing bits from the + * pointer) would be to allocate an intermediate structure + * that contains the old private pointer plus the stripe_index. + */ + BUG_ON((((uintptr_t)bi_private) & 3) != 0); + BUG_ON(stripe_index > 3); + return (void *)(((uintptr_t)bi_private) | stripe_index); +} + +static struct btrfs_bio *extract_bbio_from_bio_private(void *bi_private) +{ + return (struct btrfs_bio *)(((uintptr_t)bi_private) & ~((uintptr_t)3)); +} + +static unsigned int extract_stripe_index_from_bio_private(void *bi_private) +{ + return (unsigned int)((uintptr_t)bi_private) & 3; +} + static void btrfs_end_bio(struct bio *bio, int err) { - struct btrfs_bio *bbio = bio->bi_private; + struct btrfs_bio *bbio = extract_bbio_from_bio_private(bio->bi_private); int is_orig_bio = 0; - if (err) + if (err) { atomic_inc(&bbio->error); + if (err == -EIO || err == -EREMOTEIO) { + unsigned int stripe_index = + extract_stripe_index_from_bio_private( + bio->bi_private); + struct btrfs_device *dev; + + BUG_ON(stripe_index >= bbio->num_stripes); + dev = bbio->stripes[stripe_index].dev; + if (bio->bi_rw & WRITE) + btrfs_dev_stat_inc(dev, + BTRFS_DEV_STAT_WRITE_ERRS); + else + btrfs_dev_stat_inc(dev, + BTRFS_DEV_STAT_READ_ERRS); + if ((bio->bi_rw & WRITE_FLUSH) == WRITE_FLUSH) + btrfs_dev_stat_inc(dev, + BTRFS_DEV_STAT_FLUSH_ERRS); + btrfs_dev_stat_print_on_error(dev); + } + } if (bio == bbio->orig_bio) is_orig_bio = 1; @@ -4149,6 +4195,8 @@ int btrfs_map_bio(struct btrfs_root *root, int rw, struct bio *bio, bio = first_bio; } bio->bi_private = bbio; + bio->bi_private = merge_stripe_index_into_bio_private( + bio->bi_private, (unsigned int)dev_nr); bio->bi_end_io = btrfs_end_bio; bio->bi_sector = bbio->stripes[dev_nr].physical >> 9; dev = bbio->stripes[dev_nr].dev; @@ -4509,6 +4557,28 @@ int btrfs_read_sys_array(struct btrfs_root *root) return ret; } +struct btrfs_device *btrfs_find_device_for_logical(struct btrfs_root *root, + u64 logical, int mirror_num) +{ + struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree; + int ret; + u64 map_length = 0; + struct btrfs_bio *bbio = NULL; + struct btrfs_device *device; + + BUG_ON(mirror_num == 0); + ret = btrfs_map_block(map_tree, WRITE, logical, &map_length, &bbio, + mirror_num); + if (ret) { + BUG_ON(bbio != NULL); + return NULL; + } + BUG_ON(mirror_num != bbio->mirror_num); + device = bbio->stripes[mirror_num - 1].dev; + kfree(bbio); + return device; +} + int btrfs_read_chunk_tree(struct btrfs_root *root) { struct btrfs_path *path; @@ -4583,3 +4653,23 @@ error: btrfs_free_path(path); return ret; } + +void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index) +{ + btrfs_dev_stat_inc(dev, index); + btrfs_dev_stat_print_on_error(dev); +} + +void btrfs_dev_stat_print_on_error(struct btrfs_device *dev) +{ + printk_ratelimited(KERN_ERR + "btrfs: bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n", + dev->name, + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS), + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS), + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_FLUSH_ERRS), + btrfs_dev_stat_read(dev, + BTRFS_DEV_STAT_CORRUPTION_ERRS), + btrfs_dev_stat_read(dev, + BTRFS_DEV_STAT_GENERATION_ERRS)); +} -- cgit From c11d2c236cc260b36ef644700fbe99bcc7e7da33 Mon Sep 17 00:00:00 2001 From: Stefan Behrens Date: Fri, 25 May 2012 16:06:09 +0200 Subject: Btrfs: add ioctl to get and reset the device stats An ioctl interface is added to get the device statistic counters. A second ioctl is added to atomically get and reset these counters. Signed-off-by: Stefan Behrens --- fs/btrfs/volumes.c | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 2915521f44ee..a112b758822e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4673,3 +4673,37 @@ void btrfs_dev_stat_print_on_error(struct btrfs_device *dev) btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_GENERATION_ERRS)); } + +int btrfs_get_dev_stats(struct btrfs_root *root, + struct btrfs_ioctl_get_dev_stats *stats, + int reset_after_read) +{ + struct btrfs_device *dev; + struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices; + int i; + + mutex_lock(&fs_devices->device_list_mutex); + dev = btrfs_find_device(root, stats->devid, NULL, NULL); + mutex_unlock(&fs_devices->device_list_mutex); + + if (!dev) { + printk(KERN_WARNING + "btrfs: get dev_stats failed, device not found\n"); + return -ENODEV; + } else if (reset_after_read) { + for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) { + if (stats->nr_items > i) + stats->values[i] = + btrfs_dev_stat_read_and_reset(dev, i); + else + btrfs_dev_stat_reset(dev, i); + } + } else { + for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) + if (stats->nr_items > i) + stats->values[i] = btrfs_dev_stat_read(dev, i); + } + if (stats->nr_items > BTRFS_DEV_STAT_VALUES_MAX) + stats->nr_items = BTRFS_DEV_STAT_VALUES_MAX; + return 0; +} -- cgit From 733f4fbbc1083aa343da739f46ee839705d6cfe3 Mon Sep 17 00:00:00 2001 From: Stefan Behrens Date: Fri, 25 May 2012 16:06:10 +0200 Subject: Btrfs: read device stats on mount, write modified ones during commit The device statistics are written into the device tree with each transaction commit. Only modified statistics are written. When a filesystem is mounted, the device statistics for each involved device are read from the device tree and used to initialize the counters. Signed-off-by: Stefan Behrens --- fs/btrfs/volumes.c | 176 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 176 insertions(+) (limited to 'fs/btrfs/volumes.c') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a112b758822e..7782020996fe 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -40,6 +40,8 @@ static int init_first_rw_device(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_device *device); static int btrfs_relocate_sys_chunks(struct btrfs_root *root); +static void __btrfs_reset_dev_stats(struct btrfs_device *dev); +static void btrfs_dev_stat_print_on_load(struct btrfs_device *device); static DEFINE_MUTEX(uuid_mutex); static LIST_HEAD(fs_uuids); @@ -362,6 +364,7 @@ static noinline int device_list_add(const char *path, return -ENOMEM; } device->devid = devid; + device->dev_stats_valid = 0; device->work.func = pending_bios_fn; memcpy(device->uuid, disk_super->dev_item.uuid, BTRFS_UUID_SIZE); @@ -4654,6 +4657,162 @@ error: return ret; } +static void __btrfs_reset_dev_stats(struct btrfs_device *dev) +{ + int i; + + for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) + btrfs_dev_stat_reset(dev, i); +} + +int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info) +{ + struct btrfs_key key; + struct btrfs_key found_key; + struct btrfs_root *dev_root = fs_info->dev_root; + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; + struct extent_buffer *eb; + int slot; + int ret = 0; + struct btrfs_device *device; + struct btrfs_path *path = NULL; + int i; + + path = btrfs_alloc_path(); + if (!path) { + ret = -ENOMEM; + goto out; + } + + mutex_lock(&fs_devices->device_list_mutex); + list_for_each_entry(device, &fs_devices->devices, dev_list) { + int item_size; + struct btrfs_dev_stats_item *ptr; + + key.objectid = 0; + key.type = BTRFS_DEV_STATS_KEY; + key.offset = device->devid; + ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0); + if (ret) { + printk(KERN_WARNING "btrfs: no dev_stats entry found for device %s (devid %llu) (OK on first mount after mkfs)\n", + device->name, (unsigned long long)device->devid); + __btrfs_reset_dev_stats(device); + device->dev_stats_valid = 1; + btrfs_release_path(path); + continue; + } + slot = path->slots[0]; + eb = path->nodes[0]; + btrfs_item_key_to_cpu(eb, &found_key, slot); + item_size = btrfs_item_size_nr(eb, slot); + + ptr = btrfs_item_ptr(eb, slot, + struct btrfs_dev_stats_item); + + for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) { + if (item_size >= (1 + i) * sizeof(__le64)) + btrfs_dev_stat_set(device, i, + btrfs_dev_stats_value(eb, ptr, i)); + else + btrfs_dev_stat_reset(device, i); + } + + device->dev_stats_valid = 1; + btrfs_dev_stat_print_on_load(device); + btrfs_release_path(path); + } + mutex_unlock(&fs_devices->device_list_mutex); + +out: + btrfs_free_path(path); + return ret < 0 ? ret : 0; +} + +static int update_dev_stat_item(struct btrfs_trans_handle *trans, + struct btrfs_root *dev_root, + struct btrfs_device *device) +{ + struct btrfs_path *path; + struct btrfs_key key; + struct extent_buffer *eb; + struct btrfs_dev_stats_item *ptr; + int ret; + int i; + + key.objectid = 0; + key.type = BTRFS_DEV_STATS_KEY; + key.offset = device->devid; + + path = btrfs_alloc_path(); + BUG_ON(!path); + ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1); + if (ret < 0) { + printk(KERN_WARNING "btrfs: error %d while searching for dev_stats item for device %s!\n", + ret, device->name); + goto out; + } + + if (ret == 0 && + btrfs_item_size_nr(path->nodes[0], path->slots[0]) < sizeof(*ptr)) { + /* need to delete old one and insert a new one */ + ret = btrfs_del_item(trans, dev_root, path); + if (ret != 0) { + printk(KERN_WARNING "btrfs: delete too small dev_stats item for device %s failed %d!\n", + device->name, ret); + goto out; + } + ret = 1; + } + + if (ret == 1) { + /* need to insert a new item */ + btrfs_release_path(path); + ret = btrfs_insert_empty_item(trans, dev_root, path, + &key, sizeof(*ptr)); + if (ret < 0) { + printk(KERN_WARNING "btrfs: insert dev_stats item for device %s failed %d!\n", + device->name, ret); + goto out; + } + } + + eb = path->nodes[0]; + ptr = btrfs_item_ptr(eb, path->slots[0], struct btrfs_dev_stats_item); + for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) + btrfs_set_dev_stats_value(eb, ptr, i, + btrfs_dev_stat_read(device, i)); + btrfs_mark_buffer_dirty(eb); + +out: + btrfs_free_path(path); + return ret; +} + +/* + * called from commit_transaction. Writes all changed device stats to disk. + */ +int btrfs_run_dev_stats(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info) +{ + struct btrfs_root *dev_root = fs_info->dev_root; + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; + struct btrfs_device *device; + int ret = 0; + + mutex_lock(&fs_devices->device_list_mutex); + list_for_each_entry(device, &fs_devices->devices, dev_list) { + if (!device->dev_stats_valid || !device->dev_stats_dirty) + continue; + + ret = update_dev_stat_item(trans, dev_root, device); + if (!ret) + device->dev_stats_dirty = 0; + } + mutex_unlock(&fs_devices->device_list_mutex); + + return ret; +} + void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index) { btrfs_dev_stat_inc(dev, index); @@ -4662,6 +4821,8 @@ void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index) void btrfs_dev_stat_print_on_error(struct btrfs_device *dev) { + if (!dev->dev_stats_valid) + return; printk_ratelimited(KERN_ERR "btrfs: bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n", dev->name, @@ -4674,6 +4835,17 @@ void btrfs_dev_stat_print_on_error(struct btrfs_device *dev) BTRFS_DEV_STAT_GENERATION_ERRS)); } +static void btrfs_dev_stat_print_on_load(struct btrfs_device *dev) +{ + printk(KERN_INFO "btrfs: bdev %s errs: wr %u, rd %u, flush %u, corrupt %u, gen %u\n", + dev->name, + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_WRITE_ERRS), + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_READ_ERRS), + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_FLUSH_ERRS), + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_CORRUPTION_ERRS), + btrfs_dev_stat_read(dev, BTRFS_DEV_STAT_GENERATION_ERRS)); +} + int btrfs_get_dev_stats(struct btrfs_root *root, struct btrfs_ioctl_get_dev_stats *stats, int reset_after_read) @@ -4690,6 +4862,10 @@ int btrfs_get_dev_stats(struct btrfs_root *root, printk(KERN_WARNING "btrfs: get dev_stats failed, device not found\n"); return -ENODEV; + } else if (!dev->dev_stats_valid) { + printk(KERN_WARNING + "btrfs: get dev_stats failed, not yet valid\n"); + return -ENODEV; } else if (reset_after_read) { for (i = 0; i < BTRFS_DEV_STAT_VALUES_MAX; i++) { if (stats->nr_items > i) -- cgit