From 83d4cfd4da57b6ff16296875a962de2158799de6 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 30 Aug 2013 15:09:51 -0400 Subject: Btrfs: fixup error handling in btrfs_reloc_cow If we failed to actually allocate the correct size of the extent to relocate we will end up in an infinite loop because we won't return an error, we'll just move on to the next extent. So fix this up by returning an error, and then fix all the callers to return an error up the stack rather than BUG_ON()'ing. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/ctree.c | 7 +++++-- fs/btrfs/ctree.h | 6 +++--- fs/btrfs/relocation.c | 41 ++++++++++++++++++++++++----------------- 3 files changed, 32 insertions(+), 22 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 64346721173f..61b5bcd57b7e 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -1005,8 +1005,11 @@ static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans, return ret; } - if (root->ref_cows) - btrfs_reloc_cow_block(trans, root, buf, cow); + if (root->ref_cows) { + ret = btrfs_reloc_cow_block(trans, root, buf, cow); + if (ret) + return ret; + } if (buf == root->node) { WARN_ON(parent && parent != buf); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3c1da6f98a4d..2491ba076b42 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3939,9 +3939,9 @@ int btrfs_update_reloc_root(struct btrfs_trans_handle *trans, struct btrfs_root *root); int btrfs_recover_relocation(struct btrfs_root *root); int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len); -void btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct extent_buffer *buf, - struct extent_buffer *cow); +int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct extent_buffer *buf, + struct extent_buffer *cow); void btrfs_reloc_pre_snapshot(struct btrfs_trans_handle *trans, struct btrfs_pending_snapshot *pending, u64 *bytes_to_reserve); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index aacc2121e87c..09b2b9a0a491 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -1548,7 +1548,7 @@ static int get_new_location(struct inode *reloc_inode, u64 *new_bytenr, btrfs_file_extent_other_encoding(leaf, fi)); if (num_bytes != btrfs_file_extent_disk_num_bytes(leaf, fi)) { - ret = 1; + ret = -EINVAL; goto out; } @@ -1579,7 +1579,7 @@ int replace_file_extents(struct btrfs_trans_handle *trans, u64 end; u32 nritems; u32 i; - int ret; + int ret = 0; int first = 1; int dirty = 0; @@ -1642,11 +1642,13 @@ int replace_file_extents(struct btrfs_trans_handle *trans, ret = get_new_location(rc->data_inode, &new_bytenr, bytenr, num_bytes); - if (ret > 0) { - WARN_ON(1); - continue; + if (ret) { + /* + * Don't have to abort since we've not changed anything + * in the file extent yet. + */ + break; } - BUG_ON(ret < 0); btrfs_set_file_extent_disk_bytenr(leaf, fi, new_bytenr); dirty = 1; @@ -1656,18 +1658,24 @@ int replace_file_extents(struct btrfs_trans_handle *trans, num_bytes, parent, btrfs_header_owner(leaf), key.objectid, key.offset, 1); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + break; + } ret = btrfs_free_extent(trans, root, bytenr, num_bytes, parent, btrfs_header_owner(leaf), key.objectid, key.offset, 1); - BUG_ON(ret); + if (ret) { + btrfs_abort_transaction(trans, root, ret); + break; + } } if (dirty) btrfs_mark_buffer_dirty(leaf); if (inode) btrfs_add_delayed_iput(inode); - return 0; + return ret; } static noinline_for_stack @@ -4499,19 +4507,19 @@ out: return ret; } -void btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, - struct btrfs_root *root, struct extent_buffer *buf, - struct extent_buffer *cow) +int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct extent_buffer *buf, + struct extent_buffer *cow) { struct reloc_control *rc; struct backref_node *node; int first_cow = 0; int level; - int ret; + int ret = 0; rc = root->fs_info->reloc_ctl; if (!rc) - return; + return 0; BUG_ON(rc->stage == UPDATE_DATA_PTRS && root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID); @@ -4547,10 +4555,9 @@ void btrfs_reloc_cow_block(struct btrfs_trans_handle *trans, rc->nodes_relocated += buf->len; } - if (level == 0 && first_cow && rc->stage == UPDATE_DATA_PTRS) { + if (level == 0 && first_cow && rc->stage == UPDATE_DATA_PTRS) ret = replace_file_extents(trans, rc, root, cow); - BUG_ON(ret); - } + return ret; } /* -- cgit v1.2.3-59-g8ed1b From 55e50e458e760f4d0c183978dcc20b07a7f6e20e Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Sun, 1 Sep 2013 18:56:44 +0300 Subject: Btrfs: do not add replace target to the alloc_list If replace was suspended by the umount, replace target device is added to the fs_devices->alloc_list during a later mount. This is obviously wrong. ->is_tgtdev_for_dev_replace is supposed to guard against that, but ->is_tgtdev_for_dev_replace is (and can only ever be) initialized *after* everything is opened and fs_devices lists are populated. Fix this by checking the devid instead: for replace targets it's always equal to BTRFS_DEV_REPLACE_DEVID. Cc: Stefan Behrens Signed-off-by: Ilya Dryomov Reviewed-by: Stefan Behrens Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/volumes.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 0db165ee4340..a0577352eb6e 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -796,7 +796,8 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices, fs_devices->rotating = 1; fs_devices->open_devices++; - if (device->writeable && !device->is_tgtdev_for_dev_replace) { + if (device->writeable && + device->devid != BTRFS_DEV_REPLACE_DEVID) { fs_devices->rw_devices++; list_add(&device->dev_alloc_list, &fs_devices->alloc_list); -- cgit v1.2.3-59-g8ed1b From cef2193729595686f787c5858aad69b4369de757 Mon Sep 17 00:00:00 2001 From: Filipe David Borba Manana Date: Mon, 2 Sep 2013 12:19:13 +0100 Subject: Btrfs: more efficient inode tree replace operation Instead of removing the current inode from the red black tree and then add the new one, just use the red black tree replace operation, which is more efficient. Signed-off-by: Filipe David Borba Manana Reviewed-by: Zach Brown Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 6091ba9d2494..abed81d93687 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -4688,11 +4688,11 @@ static void inode_tree_add(struct inode *inode) struct btrfs_inode *entry; struct rb_node **p; struct rb_node *parent; + struct rb_node *new = &BTRFS_I(inode)->rb_node; u64 ino = btrfs_ino(inode); if (inode_unhashed(inode)) return; -again: parent = NULL; spin_lock(&root->inode_lock); p = &root->inode_tree.rb_node; @@ -4707,14 +4707,14 @@ again: else { WARN_ON(!(entry->vfs_inode.i_state & (I_WILL_FREE | I_FREEING))); - rb_erase(parent, &root->inode_tree); + rb_replace_node(parent, new, &root->inode_tree); RB_CLEAR_NODE(parent); spin_unlock(&root->inode_lock); - goto again; + return; } } - rb_link_node(&BTRFS_I(inode)->rb_node, parent, p); - rb_insert_color(&BTRFS_I(inode)->rb_node, &root->inode_tree); + rb_link_node(new, parent, p); + rb_insert_color(new, &root->inode_tree); spin_unlock(&root->inode_lock); } -- cgit v1.2.3-59-g8ed1b From 79556c3d882a848c8faabddc487b033c4e78f7c5 Mon Sep 17 00:00:00 2001 From: Stefan Behrens Date: Tue, 3 Sep 2013 15:25:27 +0200 Subject: btrfs: show compiled-in config features at module load time We want to know if there are debugging features compiled in, this may affect performance. The message is printed before the sanity checks. (This commit message is a copy of David Sterba's commit message when he introduced btrfs_print_info()). Signed-off-by: Stefan Behrens Reviewed-by: David Sterba Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/super.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 3aab10ce63e8..58cb83f23b1a 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1762,6 +1762,9 @@ static void btrfs_print_info(void) #ifdef CONFIG_BTRFS_DEBUG ", debug=on" #endif +#ifdef CONFIG_BTRFS_ASSERT + ", assert=on" +#endif #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY ", integrity-checker=on" #endif -- cgit v1.2.3-59-g8ed1b From 13fd8da98f79317d26277360d510caa1edf9bab3 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Tue, 3 Sep 2013 18:28:57 +0200 Subject: btrfs: add lockdep and tracing annotations for uuid tree Signed-off-by: David Sterba Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 1 + include/trace/events/btrfs.h | 1 + 2 files changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 4cbb00af92ff..72cf08b2be85 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -157,6 +157,7 @@ static struct btrfs_lockdep_keyset { { .id = BTRFS_TREE_LOG_OBJECTID, .name_stem = "log" }, { .id = BTRFS_TREE_RELOC_OBJECTID, .name_stem = "treloc" }, { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc" }, + { .id = BTRFS_UUID_TREE_OBJECTID, .name_stem = "uuid" }, { .id = 0, .name_stem = "tree" }, }; diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h index 45702c3c3837..f18b3b76e01e 100644 --- a/include/trace/events/btrfs.h +++ b/include/trace/events/btrfs.h @@ -42,6 +42,7 @@ struct extent_buffer; { BTRFS_TREE_LOG_OBJECTID, "TREE_LOG" }, \ { BTRFS_QUOTA_TREE_OBJECTID, "QUOTA_TREE" }, \ { BTRFS_TREE_RELOC_OBJECTID, "TREE_RELOC" }, \ + { BTRFS_UUID_TREE_OBJECTID, "UUID_RELOC" }, \ { BTRFS_DATA_RELOC_TREE_OBJECTID, "DATA_RELOC_TREE" }) #define show_root_type(obj) \ -- cgit v1.2.3-59-g8ed1b From a482039889b85c45fc9616e65d560db7a35d4f54 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Mon, 9 Sep 2013 13:19:42 +0800 Subject: Btrfs: allocate the free space by the existed max extent size when ENOSPC By the current code, if the requested size is very large, and all the extents in the free space cache are small, we will waste lots of the cpu time to cut the requested size in half and search the cache again and again until it gets down to the size the allocator can return. In fact, we can know the max extent size in the cache after the first search, so we needn't cut the size in half repeatedly, and just use the max extent size directly. This way can save lots of cpu time and make the performance grow up when there are only fragments in the free space cache. According to my test, if there are only 4KB free space extents in the fs, and the total size of those extents are 256MB, we can reduce the execute time of the following test from 5.4s to 1.4s. dd if=/dev/zero of= bs=1MB count=1 oflag=sync Changelog v2 -> v3: - fix the problem that we skip the block group with the space which is less than we need. Changelog v1 -> v2: - address the problem that we return a wrong start position when searching the free space in a bitmap. Signed-off-by: Miao Xie Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 33 ++++++++++++++++------ fs/btrfs/free-space-cache.c | 67 +++++++++++++++++++++++++++++++-------------- fs/btrfs/free-space-cache.h | 5 ++-- 3 files changed, 74 insertions(+), 31 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index cfb3cf711b34..2f03181b777f 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -6117,10 +6117,13 @@ enum btrfs_loop_type { /* * walks the btree of allocated extents and find a hole of a given size. * The key ins is changed to record the hole: - * ins->objectid == block start + * ins->objectid == start position * ins->flags = BTRFS_EXTENT_ITEM_KEY - * ins->offset == number of blocks + * ins->offset == the size of the hole. * Any available blocks before search_start are skipped. + * + * If there is no suitable free space, we will record the max size of + * the free space extent currently. */ static noinline int find_free_extent(struct btrfs_root *orig_root, u64 num_bytes, u64 empty_size, @@ -6133,6 +6136,7 @@ static noinline int find_free_extent(struct btrfs_root *orig_root, struct btrfs_block_group_cache *block_group = NULL; struct btrfs_block_group_cache *used_block_group; u64 search_start = 0; + u64 max_extent_size = 0; int empty_cluster = 2 * 1024 * 1024; struct btrfs_space_info *space_info; int loop = 0; @@ -6292,7 +6296,10 @@ have_block_group: btrfs_get_block_group(used_block_group); offset = btrfs_alloc_from_cluster(used_block_group, - last_ptr, num_bytes, used_block_group->key.objectid); + last_ptr, + num_bytes, + used_block_group->key.objectid, + &max_extent_size); if (offset) { /* we have a block, we're done */ spin_unlock(&last_ptr->refill_lock); @@ -6355,8 +6362,10 @@ refill_cluster: * cluster */ offset = btrfs_alloc_from_cluster(block_group, - last_ptr, num_bytes, - search_start); + last_ptr, + num_bytes, + search_start, + &max_extent_size); if (offset) { /* we found one, proceed */ spin_unlock(&last_ptr->refill_lock); @@ -6391,13 +6400,18 @@ unclustered_alloc: if (cached && block_group->free_space_ctl->free_space < num_bytes + empty_cluster + empty_size) { + if (block_group->free_space_ctl->free_space > + max_extent_size) + max_extent_size = + block_group->free_space_ctl->free_space; spin_unlock(&block_group->free_space_ctl->tree_lock); goto loop; } spin_unlock(&block_group->free_space_ctl->tree_lock); offset = btrfs_find_space_for_alloc(block_group, search_start, - num_bytes, empty_size); + num_bytes, empty_size, + &max_extent_size); /* * If we didn't find a chunk, and we haven't failed on this * block group before, and this block group is in the middle of @@ -6515,7 +6529,8 @@ loop: ret = 0; } out: - + if (ret == -ENOSPC) + ins->offset = max_extent_size; return ret; } @@ -6573,8 +6588,8 @@ again: flags); if (ret == -ENOSPC) { - if (!final_tried) { - num_bytes = num_bytes >> 1; + if (!final_tried && ins->offset) { + num_bytes = min(num_bytes >> 1, ins->offset); num_bytes = round_down(num_bytes, root->sectorsize); num_bytes = max(num_bytes, min_alloc_size); if (num_bytes == min_alloc_size) diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index ef3bea7bb257..4f419bafd071 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1433,13 +1433,19 @@ static void bitmap_set_bits(struct btrfs_free_space_ctl *ctl, ctl->free_space += bytes; } +/* + * If we can not find suitable extent, we will use bytes to record + * the size of the max extent. + */ static int search_bitmap(struct btrfs_free_space_ctl *ctl, struct btrfs_free_space *bitmap_info, u64 *offset, u64 *bytes) { unsigned long found_bits = 0; + unsigned long max_bits = 0; unsigned long bits, i; unsigned long next_zero; + unsigned long extent_bits; i = offset_to_bit(bitmap_info->offset, ctl->unit, max_t(u64, *offset, bitmap_info->offset)); @@ -1448,9 +1454,12 @@ static int search_bitmap(struct btrfs_free_space_ctl *ctl, for_each_set_bit_from(i, bitmap_info->bitmap, BITS_PER_BITMAP) { next_zero = find_next_zero_bit(bitmap_info->bitmap, BITS_PER_BITMAP, i); - if ((next_zero - i) >= bits) { - found_bits = next_zero - i; + extent_bits = next_zero - i; + if (extent_bits >= bits) { + found_bits = extent_bits; break; + } else if (extent_bits > max_bits) { + max_bits = extent_bits; } i = next_zero; } @@ -1461,38 +1470,41 @@ static int search_bitmap(struct btrfs_free_space_ctl *ctl, return 0; } + *bytes = (u64)(max_bits) * ctl->unit; return -1; } +/* Cache the size of the max extent in bytes */ static struct btrfs_free_space * find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, - unsigned long align) + unsigned long align, u64 *max_extent_size) { struct btrfs_free_space *entry; struct rb_node *node; - u64 ctl_off; u64 tmp; u64 align_off; int ret; if (!ctl->free_space_offset.rb_node) - return NULL; + goto out; entry = tree_search_offset(ctl, offset_to_bitmap(ctl, *offset), 0, 1); if (!entry) - return NULL; + goto out; for (node = &entry->offset_index; node; node = rb_next(node)) { entry = rb_entry(node, struct btrfs_free_space, offset_index); - if (entry->bytes < *bytes) + if (entry->bytes < *bytes) { + if (entry->bytes > *max_extent_size) + *max_extent_size = entry->bytes; continue; + } /* make sure the space returned is big enough * to match our requested alignment */ if (*bytes >= align) { - ctl_off = entry->offset - ctl->start; - tmp = ctl_off + align - 1;; + tmp = entry->offset - ctl->start + align - 1; do_div(tmp, align); tmp = tmp * align + ctl->start; align_off = tmp - entry->offset; @@ -1501,14 +1513,22 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, tmp = entry->offset; } - if (entry->bytes < *bytes + align_off) + if (entry->bytes < *bytes + align_off) { + if (entry->bytes > *max_extent_size) + *max_extent_size = entry->bytes; continue; + } if (entry->bitmap) { - ret = search_bitmap(ctl, entry, &tmp, bytes); + u64 size = *bytes; + + ret = search_bitmap(ctl, entry, &tmp, &size); if (!ret) { *offset = tmp; + *bytes = size; return entry; + } else if (size > *max_extent_size) { + *max_extent_size = size; } continue; } @@ -1517,7 +1537,7 @@ find_free_space(struct btrfs_free_space_ctl *ctl, u64 *offset, u64 *bytes, *bytes = entry->bytes - align_off; return entry; } - +out: return NULL; } @@ -2118,7 +2138,8 @@ void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group) } u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, - u64 offset, u64 bytes, u64 empty_size) + u64 offset, u64 bytes, u64 empty_size, + u64 *max_extent_size) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *entry = NULL; @@ -2129,7 +2150,7 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, spin_lock(&ctl->tree_lock); entry = find_free_space(ctl, &offset, &bytes_search, - block_group->full_stripe_len); + block_group->full_stripe_len, max_extent_size); if (!entry) goto out; @@ -2139,7 +2160,6 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, if (!entry->bytes) free_bitmap(ctl, entry); } else { - unlink_free_space(ctl, entry); align_gap_len = offset - entry->offset; align_gap = entry->offset; @@ -2153,7 +2173,6 @@ u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, else link_free_space(ctl, entry); } - out: spin_unlock(&ctl->tree_lock); @@ -2208,7 +2227,8 @@ int btrfs_return_cluster_to_free_space( static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster, struct btrfs_free_space *entry, - u64 bytes, u64 min_start) + u64 bytes, u64 min_start, + u64 *max_extent_size) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; int err; @@ -2220,8 +2240,11 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, search_bytes = bytes; err = search_bitmap(ctl, entry, &search_start, &search_bytes); - if (err) + if (err) { + if (search_bytes > *max_extent_size) + *max_extent_size = search_bytes; return 0; + } ret = search_start; __bitmap_clear_bits(ctl, entry, ret, bytes); @@ -2236,7 +2259,7 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, */ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster, u64 bytes, - u64 min_start) + u64 min_start, u64 *max_extent_size) { struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; struct btrfs_free_space *entry = NULL; @@ -2256,6 +2279,9 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, entry = rb_entry(node, struct btrfs_free_space, offset_index); while(1) { + if (entry->bytes < bytes && entry->bytes > *max_extent_size) + *max_extent_size = entry->bytes; + if (entry->bytes < bytes || (!entry->bitmap && entry->offset < min_start)) { node = rb_next(&entry->offset_index); @@ -2269,7 +2295,8 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, if (entry->bitmap) { ret = btrfs_alloc_from_bitmap(block_group, cluster, entry, bytes, - cluster->window_start); + cluster->window_start, + max_extent_size); if (ret == 0) { node = rb_next(&entry->offset_index); if (!node) diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index c74904167476..e737f92cf6d0 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -94,7 +94,8 @@ void __btrfs_remove_free_space_cache(struct btrfs_free_space_ctl *ctl); void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group); u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group, - u64 offset, u64 bytes, u64 empty_size); + u64 offset, u64 bytes, u64 empty_size, + u64 *max_extent_size); u64 btrfs_find_ino_for_alloc(struct btrfs_root *fs_root); void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group, u64 bytes); @@ -105,7 +106,7 @@ int btrfs_find_space_cluster(struct btrfs_root *root, void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster); u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster, u64 bytes, - u64 min_start); + u64 min_start, u64 *max_extent_size); int btrfs_return_cluster_to_free_space( struct btrfs_block_group_cache *block_group, struct btrfs_free_cluster *cluster); -- cgit v1.2.3-59-g8ed1b From 573aecafca1cf7a974231b759197a1aebcf39c2a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 30 Aug 2013 14:38:49 -0400 Subject: Btrfs: actually limit the size of delalloc range So forever we have had this thing to limit the amount of delalloc pages we'll setup to be written out to 128mb. This is because we have to lock all the pages in this range, so anything above this gets a bit unweildly, and also without a limit we'll happily allocate gigantic chunks of disk space. Turns out our check for this wasn't quite right, we wouldn't actually limit the chunk we wanted to write out, we'd just stop looking for more space after we went over the limit. So if you do a giant 20gb dd on my box with lots of ram I could get 2gig extents. This is fine normally, except when you go to relocate these extents and we can't find enough space to relocate these moster extents, since we have to be able to allocate exactly the same sized extent to move it around. So fix this by actually enforcing the limit. With this patch I'm no longer seeing giant 1.5gb extents. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/extent_io.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 09582b81640c..c09a40db53db 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1481,10 +1481,12 @@ static noinline u64 find_delalloc_range(struct extent_io_tree *tree, *end = state->end; cur_start = state->end + 1; node = rb_next(node); - if (!node) - break; total_bytes += state->end - state->start + 1; - if (total_bytes >= max_bytes) + if (total_bytes >= max_bytes) { + *end = *start + max_bytes - 1; + break; + } + if (!node) break; } out: -- cgit v1.2.3-59-g8ed1b From de2b530bfb683fd75c31ab65ec42949f5f7a5b58 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 11 Sep 2013 09:36:30 -0400 Subject: Btrfs: actually log directory we are fsync()'ing If you just create a directory and then fsync that directory and then pull the power plug you will come back up and the directory will not be there. That is because we won't actually create directories if we've logged files inside of them since they will be created on replay, but in this check we will set our logged_trans of our current directory if it happens to be a directory, making us think it doesn't need to be logged. Fix the logic to only do this to parent directories. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 0d9613c3f5e5..aaa2e2b67478 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -3805,6 +3805,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, int ret = 0; struct btrfs_root *root; struct dentry *old_parent = NULL; + struct inode *orig_inode = inode; /* * for regular files, if its inode is already on disk, we don't @@ -3824,7 +3825,14 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans, } while (1) { - BTRFS_I(inode)->logged_trans = trans->transid; + /* + * If we are logging a directory then we start with our inode, + * not our parents inode, so we need to skipp setting the + * logged_trans so that further down in the log code we don't + * think this inode has already been logged. + */ + if (inode != orig_inode) + BTRFS_I(inode)->logged_trans = trans->transid; smp_mb(); if (BTRFS_I(inode)->last_unlink_trans > last_committed) { -- cgit v1.2.3-59-g8ed1b From a5874ce6ce4a3e4fc3db254ccf6d59d8501a56d8 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 11 Sep 2013 09:55:42 -0400 Subject: Btrfs: check roots last log commit when checking if an inode has been logged Liu introduced a local copy of the last log commit for an inode to make sure we actually log an inode even if a log commit has already taken place. In order to make sure we didn't relog the same inode multiple times he set this local copy to the current trans when we log the inode, because usually we log the inode and then sync the log. The exception to this is during rename, we will relog an inode if the name changed and it is already in the log. The problem with this is then we go to sync the inode, and our check to see if the inode has already been logged is tripped and we don't sync the log. To fix this we need to _also_ check against the roots last log commit, because it could be less than what is in our local copy of the log commit. This fixes a bug where we rename a file into a directory and then fsync the directory and then on remount the directory is no longer there. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/btrfs_inode.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h index d0ae226926ee..71f074e1870b 100644 --- a/fs/btrfs/btrfs_inode.h +++ b/fs/btrfs/btrfs_inode.h @@ -213,7 +213,10 @@ static inline bool btrfs_is_free_space_inode(struct inode *inode) static inline int btrfs_inode_in_log(struct inode *inode, u64 generation) { if (BTRFS_I(inode)->logged_trans == generation && - BTRFS_I(inode)->last_sub_trans <= BTRFS_I(inode)->last_log_commit) + BTRFS_I(inode)->last_sub_trans <= + BTRFS_I(inode)->last_log_commit && + BTRFS_I(inode)->last_sub_trans <= + BTRFS_I(inode)->root->last_log_commit) return 1; return 0; } -- cgit v1.2.3-59-g8ed1b From dd8e721773fdab5ccc7fde44ec57e30b563243b2 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 11 Sep 2013 11:57:23 -0400 Subject: Btrfs: replay dir_index items before other items A user reported a bug where his log would not replay because he was getting -EEXIST back. This was because he had a file moved into a directory that was logged. What happens is the file had a lower inode number, and so it is processed first when replaying the log, and so we add the inode ref in for the directory it was moved to. But then we process the directories DIR_INDEX item and try to add the inode ref for that inode and it fails because we already added it when we replayed the inode. To solve this problem we need to just process any DIR_INDEX items we have in the log first so this all is taken care of, and then we can replay the rest of the items. With this patch my reproducer can remount the file system properly instead of erroring out. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index aaa2e2b67478..c91309dea8da 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -93,7 +93,8 @@ */ #define LOG_WALK_PIN_ONLY 0 #define LOG_WALK_REPLAY_INODES 1 -#define LOG_WALK_REPLAY_ALL 2 +#define LOG_WALK_REPLAY_DIR_INDEX 2 +#define LOG_WALK_REPLAY_ALL 3 static int btrfs_log_inode(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode, @@ -2027,6 +2028,15 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, if (ret) break; } + + if (key.type == BTRFS_DIR_INDEX_KEY && + wc->stage == LOG_WALK_REPLAY_DIR_INDEX) { + ret = replay_one_dir_item(wc->trans, root, path, + eb, i, &key); + if (ret) + break; + } + if (wc->stage < LOG_WALK_REPLAY_ALL) continue; @@ -2048,8 +2058,7 @@ static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb, eb, i, &key); if (ret) break; - } else if (key.type == BTRFS_DIR_ITEM_KEY || - key.type == BTRFS_DIR_INDEX_KEY) { + } else if (key.type == BTRFS_DIR_ITEM_KEY) { ret = replay_one_dir_item(wc->trans, root, path, eb, i, &key); if (ret) -- cgit v1.2.3-59-g8ed1b From d555438b6e1dad139d26ab807f0af68a1fa47a86 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 11 Sep 2013 14:17:00 -0400 Subject: Btrfs: drop dir i_size when adding new names on replay So if we have dir_index items in the log that means we also have the inode item as well, which means that the inode's i_size is correct. However when we process dir_index'es we call btrfs_add_link() which will increase the directory's i_size for the new entry. To fix this we need to just set the dir items i_size to 0, and then as we find dir_index items we adjust the i_size. btrfs_add_link() will do it for new entries, and if the entry already exists we can just add the name_len to the i_size ourselves. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/tree-log.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index c91309dea8da..79f057c0619a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -394,6 +394,7 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, if (inode_item) { struct btrfs_inode_item *item; u64 nbytes; + u32 mode; item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_inode_item); @@ -401,9 +402,19 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item); btrfs_set_inode_nbytes(eb, item, nbytes); + + /* + * If this is a directory we need to reset the i_size to + * 0 so that we can set it up properly when replaying + * the rest of the items in this log. + */ + mode = btrfs_inode_mode(eb, item); + if (S_ISDIR(mode)) + btrfs_set_inode_size(eb, item, 0); } } else if (inode_item) { struct btrfs_inode_item *item; + u32 mode; /* * New inode, set nbytes to 0 so that the nbytes comes out @@ -411,6 +422,15 @@ static noinline int overwrite_item(struct btrfs_trans_handle *trans, */ item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item); btrfs_set_inode_nbytes(eb, item, 0); + + /* + * If this is a directory we need to reset the i_size to 0 so + * that we can set it up properly when replaying the rest of + * the items in this log. + */ + mode = btrfs_inode_mode(eb, item); + if (S_ISDIR(mode)) + btrfs_set_inode_size(eb, item, 0); } insert: btrfs_release_path(path); @@ -1497,6 +1517,7 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans, iput(inode); return -EIO; } + ret = btrfs_add_link(trans, dir, inode, name, name_len, 1, index); /* FIXME, put inode into FIXUP list */ @@ -1535,6 +1556,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, u8 log_type; int exists; int ret = 0; + bool update_size = (key->type == BTRFS_DIR_INDEX_KEY); dir = read_one_inode(root, key->objectid); if (!dir) @@ -1605,6 +1627,10 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, goto insert; out: btrfs_release_path(path); + if (!ret && update_size) { + btrfs_i_size_write(dir, dir->i_size + name_len * 2); + ret = btrfs_update_inode(trans, root, dir); + } kfree(name); iput(dir); return ret; @@ -1615,6 +1641,7 @@ insert: name, name_len, log_type, &log_key); if (ret && ret != -ENOENT) goto out; + update_size = false; ret = 0; goto out; } -- cgit v1.2.3-59-g8ed1b From 652f25a2921eb32a3e6f88aed3c59b494c1287c4 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Thu, 12 Sep 2013 16:58:28 -0400 Subject: Btrfs: improve replacing nocow extents Various people have hit a deadlock when running btrfs/011. This is because when replacing nocow extents we will take the i_mutex to make sure nobody messes with the file while we are replacing the extent. The problem is we are already holding a transaction open, which is a locking inversion, so instead we need to save these inodes we find and then process them outside of the transaction. Further we can't just lock the inode and assume we are good to go. We need to lock the extent range and then read back the extent cache for the inode to make sure the extent really still points at the physical block we want. If it doesn't we don't have to copy it. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/scrub.c | 112 ++++++++++++++++++++++++++++++++++++++++++++++++------- 1 file changed, 98 insertions(+), 14 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index 0afcd452fcb3..a18e0e23f6a6 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -158,12 +158,20 @@ struct scrub_fixup_nodatasum { int mirror_num; }; +struct scrub_nocow_inode { + u64 inum; + u64 offset; + u64 root; + struct list_head list; +}; + struct scrub_copy_nocow_ctx { struct scrub_ctx *sctx; u64 logical; u64 len; int mirror_num; u64 physical_for_dev_replace; + struct list_head inodes; struct btrfs_work work; }; @@ -245,7 +253,7 @@ static void scrub_wr_bio_end_io_worker(struct btrfs_work *work); static int write_page_nocow(struct scrub_ctx *sctx, u64 physical_for_dev_replace, struct page *page); static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, - void *ctx); + struct scrub_copy_nocow_ctx *ctx); static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len, int mirror_num, u64 physical_for_dev_replace); static void copy_nocow_pages_worker(struct btrfs_work *work); @@ -3126,12 +3134,30 @@ static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len, nocow_ctx->mirror_num = mirror_num; nocow_ctx->physical_for_dev_replace = physical_for_dev_replace; nocow_ctx->work.func = copy_nocow_pages_worker; + INIT_LIST_HEAD(&nocow_ctx->inodes); btrfs_queue_worker(&fs_info->scrub_nocow_workers, &nocow_ctx->work); return 0; } +static int record_inode_for_nocow(u64 inum, u64 offset, u64 root, void *ctx) +{ + struct scrub_copy_nocow_ctx *nocow_ctx = ctx; + struct scrub_nocow_inode *nocow_inode; + + nocow_inode = kzalloc(sizeof(*nocow_inode), GFP_NOFS); + if (!nocow_inode) + return -ENOMEM; + nocow_inode->inum = inum; + nocow_inode->offset = offset; + nocow_inode->root = root; + list_add_tail(&nocow_inode->list, &nocow_ctx->inodes); + return 0; +} + +#define COPY_COMPLETE 1 + static void copy_nocow_pages_worker(struct btrfs_work *work) { struct scrub_copy_nocow_ctx *nocow_ctx = @@ -3167,8 +3193,7 @@ static void copy_nocow_pages_worker(struct btrfs_work *work) } ret = iterate_inodes_from_logical(logical, fs_info, path, - copy_nocow_pages_for_inode, - nocow_ctx); + record_inode_for_nocow, nocow_ctx); if (ret != 0 && ret != -ENOENT) { pr_warn("iterate_inodes_from_logical() failed: log %llu, phys %llu, len %llu, mir %u, ret %d\n", logical, physical_for_dev_replace, len, mirror_num, @@ -3177,7 +3202,33 @@ static void copy_nocow_pages_worker(struct btrfs_work *work) goto out; } + btrfs_end_transaction(trans, root); + trans = NULL; + while (!list_empty(&nocow_ctx->inodes)) { + struct scrub_nocow_inode *entry; + entry = list_first_entry(&nocow_ctx->inodes, + struct scrub_nocow_inode, + list); + list_del_init(&entry->list); + ret = copy_nocow_pages_for_inode(entry->inum, entry->offset, + entry->root, nocow_ctx); + kfree(entry); + if (ret == COPY_COMPLETE) { + ret = 0; + break; + } else if (ret) { + break; + } + } out: + while (!list_empty(&nocow_ctx->inodes)) { + struct scrub_nocow_inode *entry; + entry = list_first_entry(&nocow_ctx->inodes, + struct scrub_nocow_inode, + list); + list_del_init(&entry->list); + kfree(entry); + } if (trans && !IS_ERR(trans)) btrfs_end_transaction(trans, root); if (not_written) @@ -3190,20 +3241,25 @@ out: scrub_pending_trans_workers_dec(sctx); } -static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, void *ctx) +static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, + struct scrub_copy_nocow_ctx *nocow_ctx) { - struct scrub_copy_nocow_ctx *nocow_ctx = ctx; struct btrfs_fs_info *fs_info = nocow_ctx->sctx->dev_root->fs_info; struct btrfs_key key; struct inode *inode; struct page *page; struct btrfs_root *local_root; + struct btrfs_ordered_extent *ordered; + struct extent_map *em; + struct extent_state *cached_state = NULL; + struct extent_io_tree *io_tree; u64 physical_for_dev_replace; - u64 len; + u64 len = nocow_ctx->len; + u64 lockstart = offset, lockend = offset + len - 1; unsigned long index; int srcu_index; - int ret; - int err; + int ret = 0; + int err = 0; key.objectid = root; key.type = BTRFS_ROOT_ITEM_KEY; @@ -3229,9 +3285,33 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, void *ctx) mutex_lock(&inode->i_mutex); inode_dio_wait(inode); - ret = 0; physical_for_dev_replace = nocow_ctx->physical_for_dev_replace; - len = nocow_ctx->len; + io_tree = &BTRFS_I(inode)->io_tree; + + lock_extent_bits(io_tree, lockstart, lockend, 0, &cached_state); + ordered = btrfs_lookup_ordered_range(inode, lockstart, len); + if (ordered) { + btrfs_put_ordered_extent(ordered); + goto out_unlock; + } + + em = btrfs_get_extent(inode, NULL, 0, lockstart, len, 0); + if (IS_ERR(em)) { + ret = PTR_ERR(em); + goto out_unlock; + } + + /* + * This extent does not actually cover the logical extent anymore, + * move on to the next inode. + */ + if (em->block_start > nocow_ctx->logical || + em->block_start + em->block_len < nocow_ctx->logical + len) { + free_extent_map(em); + goto out_unlock; + } + free_extent_map(em); + while (len >= PAGE_CACHE_SIZE) { index = offset >> PAGE_CACHE_SHIFT; again: @@ -3247,10 +3327,9 @@ again: goto next_page; } else { ClearPageError(page); - err = extent_read_full_page(&BTRFS_I(inode)-> - io_tree, - page, btrfs_get_extent, - nocow_ctx->mirror_num); + err = extent_read_full_page_nolock(io_tree, page, + btrfs_get_extent, + nocow_ctx->mirror_num); if (err) { ret = err; goto next_page; @@ -3264,6 +3343,7 @@ again: * page in the page cache. */ if (page->mapping != inode->i_mapping) { + unlock_page(page); page_cache_release(page); goto again; } @@ -3287,6 +3367,10 @@ next_page: physical_for_dev_replace += PAGE_CACHE_SIZE; len -= PAGE_CACHE_SIZE; } + ret = COPY_COMPLETE; +out_unlock: + unlock_extent_cached(io_tree, lockstart, lockend, &cached_state, + GFP_NOFS); out: mutex_unlock(&inode->i_mutex); iput(inode); -- cgit v1.2.3-59-g8ed1b From 14575aef4212d2cc02274bf1f5456f3e644f03f8 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 17 Sep 2013 10:48:00 -0400 Subject: Revert "Btrfs: rework the overcommit logic to be based on the total size" This reverts commit 70afa3998c9baed4186df38988246de1abdab56d. It is causing performance issues and wasn't actually correct. There were problems with the way we flushed delalloc and that was the real cause of the early enospc. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/extent-tree.c | 15 +++------------ 1 file changed, 3 insertions(+), 12 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 2f03181b777f..07f7f6942128 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3925,7 +3925,6 @@ static int can_overcommit(struct btrfs_root *root, u64 space_size; u64 avail; u64 used; - u64 to_add; used = space_info->bytes_used + space_info->bytes_reserved + space_info->bytes_pinned + space_info->bytes_readonly; @@ -3959,25 +3958,17 @@ static int can_overcommit(struct btrfs_root *root, BTRFS_BLOCK_GROUP_RAID10)) avail >>= 1; - to_add = space_info->total_bytes; - /* * If we aren't flushing all things, let us overcommit up to * 1/2th of the space. If we can flush, don't let us overcommit * too much, let it overcommit up to 1/8 of the space. */ if (flush == BTRFS_RESERVE_FLUSH_ALL) - to_add >>= 3; + avail >>= 3; else - to_add >>= 1; - - /* - * Limit the overcommit to the amount of free space we could possibly - * allocate for chunks. - */ - to_add = min(avail, to_add); + avail >>= 1; - if (used + bytes < space_info->total_bytes + to_add) + if (used + bytes < space_info->total_bytes + avail) return 1; return 0; } -- cgit v1.2.3-59-g8ed1b From c4fbb4300abd6f662c7d5049d01f868af9874069 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 17 Sep 2013 10:50:06 -0400 Subject: Btrfs: fix worst case calculator for space usage Forever ago I made the worst case calculator say that we could potentially split into 3 blocks for every level on the way down, which isn't right. If we split we're only going to get two new blocks, the one we originally cow'ed and the new one we're going to split. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 2491ba076b42..36490b92ee33 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3135,7 +3135,7 @@ static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_root *root, unsigned num_items) { return (root->leafsize + root->nodesize * (BTRFS_MAX_LEVEL - 1)) * - 3 * num_items; + 2 * num_items; } /* -- cgit v1.2.3-59-g8ed1b From f0de181c9b48a397c5a2fbe63dcdd2a26a872695 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 17 Sep 2013 10:55:51 -0400 Subject: Btrfs: kill delay_iput arg to the wait_ordered functions This is a left over of how we used to wait for ordered extents, which was to grab the inode and then run filemap flush on it. However if we have an ordered extent then we already are holding a ref on the inode, and we just use btrfs_start_ordered_extent anyway, so there is no reason to have an extra ref on the inode to start work on the ordered extent. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/dev-replace.c | 4 ++-- fs/btrfs/extent-tree.c | 6 +++--- fs/btrfs/ioctl.c | 2 +- fs/btrfs/ordered-data.c | 24 +++--------------------- fs/btrfs/ordered-data.h | 5 ++--- fs/btrfs/relocation.c | 2 +- fs/btrfs/super.c | 2 +- fs/btrfs/transaction.c | 2 +- 8 files changed, 14 insertions(+), 33 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index af800ef677a0..5d844438b2d4 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -400,7 +400,7 @@ int btrfs_dev_replace_start(struct btrfs_root *root, args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR; btrfs_dev_replace_unlock(dev_replace); - btrfs_wait_all_ordered_extents(root->fs_info, 0); + btrfs_wait_all_ordered_extents(root->fs_info); /* force writing the updated state information to disk */ trans = btrfs_start_transaction(root, 0); @@ -475,7 +475,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); return ret; } - btrfs_wait_all_ordered_extents(root->fs_info, 0); + btrfs_wait_all_ordered_extents(root->fs_info); trans = btrfs_start_transaction(root, 0); if (IS_ERR(trans)) { diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 07f7f6942128..88c6db611de3 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3991,7 +3991,7 @@ static void btrfs_writeback_inodes_sb_nr(struct btrfs_root *root, */ btrfs_start_all_delalloc_inodes(root->fs_info, 0); if (!current->journal_info) - btrfs_wait_all_ordered_extents(root->fs_info, 0); + btrfs_wait_all_ordered_extents(root->fs_info); } } @@ -4021,7 +4021,7 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig, if (delalloc_bytes == 0) { if (trans) return; - btrfs_wait_all_ordered_extents(root->fs_info, 0); + btrfs_wait_all_ordered_extents(root->fs_info); return; } @@ -4049,7 +4049,7 @@ static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig, loops++; if (wait_ordered && !trans) { - btrfs_wait_all_ordered_extents(root->fs_info, 0); + btrfs_wait_all_ordered_extents(root->fs_info); } else { time_left = schedule_timeout_killable(1); if (time_left) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 1a5b9462dd9a..fd6557e7118a 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -574,7 +574,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir, if (ret) return ret; - btrfs_wait_ordered_extents(root, 0); + btrfs_wait_ordered_extents(root); pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS); if (!pending_snapshot) diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 966b413a33b8..c702cb62f78a 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -563,11 +563,10 @@ static void btrfs_run_ordered_extent_work(struct btrfs_work *work) * wait for all the ordered extents in a root. This is done when balancing * space between drives. */ -void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput) +void btrfs_wait_ordered_extents(struct btrfs_root *root) { struct list_head splice, works; struct btrfs_ordered_extent *ordered, *next; - struct inode *inode; INIT_LIST_HEAD(&splice); INIT_LIST_HEAD(&works); @@ -580,15 +579,6 @@ void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput) root_extent_list); list_move_tail(&ordered->root_extent_list, &root->ordered_extents); - /* - * the inode may be getting freed (in sys_unlink path). - */ - inode = igrab(ordered->inode); - if (!inode) { - cond_resched_lock(&root->ordered_extent_lock); - continue; - } - atomic_inc(&ordered->refs); spin_unlock(&root->ordered_extent_lock); @@ -605,21 +595,13 @@ void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput) list_for_each_entry_safe(ordered, next, &works, work_list) { list_del_init(&ordered->work_list); wait_for_completion(&ordered->completion); - - inode = ordered->inode; btrfs_put_ordered_extent(ordered); - if (delay_iput) - btrfs_add_delayed_iput(inode); - else - iput(inode); - cond_resched(); } mutex_unlock(&root->fs_info->ordered_operations_mutex); } -void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info, - int delay_iput) +void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info) { struct btrfs_root *root; struct list_head splice; @@ -637,7 +619,7 @@ void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info, &fs_info->ordered_roots); spin_unlock(&fs_info->ordered_root_lock); - btrfs_wait_ordered_extents(root, delay_iput); + btrfs_wait_ordered_extents(root); btrfs_put_fs_root(root); spin_lock(&fs_info->ordered_root_lock); diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index d9a5aa097b4f..0c0b35612d7a 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -195,9 +195,8 @@ int btrfs_run_ordered_operations(struct btrfs_trans_handle *trans, void btrfs_add_ordered_operation(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct inode *inode); -void btrfs_wait_ordered_extents(struct btrfs_root *root, int delay_iput); -void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info, - int delay_iput); +void btrfs_wait_ordered_extents(struct btrfs_root *root); +void btrfs_wait_all_ordered_extents(struct btrfs_fs_info *fs_info); void btrfs_get_logged_extents(struct btrfs_root *log, struct inode *inode); void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid); void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 09b2b9a0a491..a5a26320503f 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4246,7 +4246,7 @@ int btrfs_relocate_block_group(struct btrfs_root *extent_root, u64 group_start) err = ret; goto out; } - btrfs_wait_all_ordered_extents(fs_info, 0); + btrfs_wait_all_ordered_extents(fs_info); while (1) { mutex_lock(&fs_info->cleaner_mutex); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 58cb83f23b1a..b341da3ee3ee 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -921,7 +921,7 @@ int btrfs_sync_fs(struct super_block *sb, int wait) return 0; } - btrfs_wait_all_ordered_extents(fs_info, 1); + btrfs_wait_all_ordered_extents(fs_info); trans = btrfs_attach_transaction_barrier(root); if (IS_ERR(trans)) { diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index cac4a3f76323..e7a95356df83 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1603,7 +1603,7 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info) static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info) { if (btrfs_test_opt(fs_info->tree_root, FLUSHONCOMMIT)) - btrfs_wait_all_ordered_extents(fs_info, 1); + btrfs_wait_all_ordered_extents(fs_info); } int btrfs_commit_transaction(struct btrfs_trans_handle *trans, -- cgit v1.2.3-59-g8ed1b From 363e4d354e51558629d13c5ae456f98c4b209576 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 17 Sep 2013 11:02:25 -0400 Subject: Btrfs: remove space_info->reservation_progress This isn't used for anything anymore, just remove it. Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 9 --------- fs/btrfs/extent-tree.c | 3 --- 2 files changed, 12 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 36490b92ee33..0506f40ede83 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1118,15 +1118,6 @@ struct btrfs_space_info { */ struct percpu_counter total_bytes_pinned; - /* - * we bump reservation progress every time we decrement - * bytes_reserved. This way people waiting for reservations - * know something good has happened and they can check - * for progress. The number here isn't to be trusted, it - * just shows reclaim activity - */ - unsigned long reservation_progress; - unsigned int full:1; /* indicates that we cannot allocate any more chunks for this space */ unsigned int chunk_alloc:1; /* set if we are allocating a chunk */ diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 88c6db611de3..d58bef130a41 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4456,7 +4456,6 @@ static void block_rsv_release_bytes(struct btrfs_fs_info *fs_info, space_info->bytes_may_use -= num_bytes; trace_btrfs_space_reservation(fs_info, "space_info", space_info->flags, num_bytes, 0); - space_info->reservation_progress++; spin_unlock(&space_info->lock); } } @@ -4657,7 +4656,6 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info) sinfo->bytes_may_use -= num_bytes; trace_btrfs_space_reservation(fs_info, "space_info", sinfo->flags, num_bytes, 0); - sinfo->reservation_progress++; block_rsv->reserved = block_rsv->size; block_rsv->full = 1; } @@ -5437,7 +5435,6 @@ static int btrfs_update_reserved_bytes(struct btrfs_block_group_cache *cache, space_info->bytes_readonly += num_bytes; cache->reserved -= num_bytes; space_info->bytes_reserved -= num_bytes; - space_info->reservation_progress++; } spin_unlock(&cache->lock); spin_unlock(&space_info->lock); -- cgit v1.2.3-59-g8ed1b From f4ab9ea706f2c6e4aad544145353b81afe7500e1 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 17 Sep 2013 11:25:44 -0400 Subject: Btrfs: iput inode on allocation failure We don't do the iput when we fail to allocate our delayed delalloc work in __start_delalloc_inodes, fix this. Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index abed81d93687..931036c6eb90 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8216,6 +8216,10 @@ static int __start_delalloc_inodes(struct btrfs_root *root, int delay_iput) work = btrfs_alloc_delalloc_work(inode, 0, delay_iput); if (unlikely(!work)) { + if (delay_iput) + btrfs_add_delayed_iput(inode); + else + iput(inode); ret = -ENOMEM; goto out; } -- cgit v1.2.3-59-g8ed1b From a724b4369097897db45d61108c0e976912e586c7 Mon Sep 17 00:00:00 2001 From: Stefan Behrens Date: Wed, 11 Sep 2013 09:59:22 +0200 Subject: Btrfs: add the missing mutex unlock in write_all_supers() The BUG() was replaced by btrfs_error() and return -EIO with the patch "get rid of one BUG() in write_all_supers()", but the missing mutex_unlock() was overlooked. The 0-DAY kernel build service from Intel reported the missing unlock which was found by the coccinelle tool: fs/btrfs/disk-io.c:3422:2-8: preceding lock on line 3374 Signed-off-by: Stefan Behrens Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 72cf08b2be85..4ae17ed13b32 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3416,6 +3416,7 @@ static int write_all_supers(struct btrfs_root *root, int max_mirrors) if (total_errors > max_errors) { printk(KERN_ERR "btrfs: %d errors while writing supers\n", total_errors); + mutex_unlock(&root->fs_info->fs_devices->device_list_mutex); /* FUA is masked off if unsupported and can't be the reason */ btrfs_error(root->fs_info, -EIO, -- cgit v1.2.3-59-g8ed1b From a0634be562c27ddee7c94bce4f765f8071244e07 Mon Sep 17 00:00:00 2001 From: Filipe David Borba Manana Date: Wed, 11 Sep 2013 20:36:44 +0100 Subject: Btrfs: don't leak transaction in btrfs_sync_file() In btrfs_sync_file(), if the call to btrfs_log_dentry_safe() returns a negative error (for e.g. -ENOMEM via btrfs_log_inode()), we would return without ending/freeing the transaction. Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/file.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 5ba87b0d2ef8..d12107e90987 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1859,8 +1859,8 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync) ret = btrfs_log_dentry_safe(trans, root, dentry); if (ret < 0) { - mutex_unlock(&inode->i_mutex); - goto out; + /* Fallthrough and commit/free transaction. */ + ret = 1; } /* we've logged all the items and now have a consistent -- cgit v1.2.3-59-g8ed1b From 1cecf579d161527f610ef0da852dd6122e434a49 Mon Sep 17 00:00:00 2001 From: chandan Date: Fri, 13 Sep 2013 19:34:10 +0530 Subject: Btrfs: btrfs_ioctl_default_subvol: Revert back to toplevel subvolume when arg is 0 This patch makes it possible to set BTRFS_FS_TREE_OBJECTID as the default subvolume by passing a subvolume id of 0. Signed-off-by: chandan Reviewed-by: David Sterba Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'fs') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index fd6557e7118a..fba259ab9994 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3310,7 +3310,7 @@ static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) } if (!objectid) - objectid = root->root_key.objectid; + objectid = BTRFS_FS_TREE_OBJECTID; location.objectid = objectid; location.type = BTRFS_ROOT_ITEM_KEY; -- cgit v1.2.3-59-g8ed1b From 6ef3de9c9252b186720122d3ae7122a81d49f8ee Mon Sep 17 00:00:00 2001 From: David Sterba Date: Fri, 13 Sep 2013 17:41:20 +0200 Subject: btrfs: refuse to remount read-write after abort It's still possible to flip the filesystem into RW mode after it's remounted RO due to an abort. There are lots of places that check for the superblock error bit and will not write data, but we should not let the filesystem appear read-write. Signed-off-by: David Sterba Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/super.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index b341da3ee3ee..6ab0df59b6c4 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1340,6 +1340,12 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) if (ret) goto restore; } else { + if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) { + btrfs_err(fs_info, + "Remounting read-write after error is not allowed\n"); + ret = -EINVAL; + goto restore; + } if (fs_info->fs_devices->rw_devices == 0) { ret = -EACCES; goto restore; -- cgit v1.2.3-59-g8ed1b From 5138cccf3470fcaa8a42df79a17f20c72f866158 Mon Sep 17 00:00:00 2001 From: Frank Holton Date: Fri, 13 Sep 2013 11:46:50 -0400 Subject: btrfs: Add btrfs: prefix to kernel log output The kernel log entries for device label %s and device fsid %pU are missing the btrfs: prefix. Add those here. Signed-off-by: Frank Holton Reviewed-by: David Sterba Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/volumes.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a0577352eb6e..043114749516 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -912,9 +912,9 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder, if (disk_super->label[0]) { if (disk_super->label[BTRFS_LABEL_SIZE - 1]) disk_super->label[BTRFS_LABEL_SIZE - 1] = '\0'; - printk(KERN_INFO "device label %s ", disk_super->label); + printk(KERN_INFO "btrfs: device label %s ", disk_super->label); } else { - printk(KERN_INFO "device fsid %pU ", disk_super->fsid); + printk(KERN_INFO "btrfs: device fsid %pU ", disk_super->fsid); } printk(KERN_CONT "devid %llu transid %llu %s\n", devid, transid, path); -- cgit v1.2.3-59-g8ed1b From 93fd63c2f001ca6797c6b15b696a484b165b4800 Mon Sep 17 00:00:00 2001 From: Guangyu Sun Date: Mon, 16 Sep 2013 10:42:03 -0700 Subject: Btrfs: dir_inode_operations should use btrfs_update_time also Commit 2bc5565286121d2a77ccd728eb3484dff2035b58 (Btrfs: don't update atime on RO subvolumes) ensures that the access time of an inode is not updated when the inode lives in a read-only subvolume. However, if a directory on a read-only subvolume is accessed, the atime is updated. This results in a write operation to a read-only subvolume. I believe that access times should never be updated on read-only subvolumes. To reproduce: # mkfs.btrfs -f /dev/dm-3 (...) # mount /dev/dm-3 /mnt # btrfs subvol create /mnt/sub Create subvolume '/mnt/sub' # mkdir /mnt/sub/dir # echo "abc" > /mnt/sub/dir/file # btrfs subvol snapshot -r /mnt/sub /mnt/rosnap Create a readonly snapshot of '/mnt/sub' in '/mnt/rosnap' # stat /mnt/rosnap/dir File: `/mnt/rosnap/dir' Size: 8 Blocks: 0 IO Block: 4096 directory Device: 16h/22d Inode: 257 Links: 1 Access: (0755/drwxr-xr-x) Uid: ( 0/ root) Gid: ( 0/ root) Access: 2013-09-11 07:21:49.389157126 -0400 Modify: 2013-09-11 07:22:02.330156079 -0400 Change: 2013-09-11 07:22:02.330156079 -0400 # ls /mnt/rosnap/dir file # stat /mnt/rosnap/dir File: `/mnt/rosnap/dir' Size: 8 Blocks: 0 IO Block: 4096 directory Device: 16h/22d Inode: 257 Links: 1 Access: (0755/drwxr-xr-x) Uid: ( 0/ root) Gid: ( 0/ root) Access: 2013-09-11 07:22:56.797151670 -0400 Modify: 2013-09-11 07:22:02.330156079 -0400 Change: 2013-09-11 07:22:02.330156079 -0400 Reported-by: Koen De Wit Signed-off-by: Guangyu Sun Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 931036c6eb90..8af6c03953ad 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -8617,11 +8617,13 @@ static const struct inode_operations btrfs_dir_inode_operations = { .removexattr = btrfs_removexattr, .permission = btrfs_permission, .get_acl = btrfs_get_acl, + .update_time = btrfs_update_time, }; static const struct inode_operations btrfs_dir_ro_inode_operations = { .lookup = btrfs_lookup, .permission = btrfs_permission, .get_acl = btrfs_get_acl, + .update_time = btrfs_update_time, }; static const struct file_operations btrfs_dir_file_operations = { -- cgit v1.2.3-59-g8ed1b From cbf8b8ca3ec799c11a4cbb29d812d84adf2990b0 Mon Sep 17 00:00:00 2001 From: Mark Fasheh Date: Tue, 17 Sep 2013 15:43:54 -0700 Subject: btrfs: change extent-same to copy entire argument struct btrfs_ioctl_file_extent_same() uses __put_user_unaligned() to copy some data back to it's argument struct. Unfortunately, not all architectures provide __put_user_unaligned(), so compiles break on them if btrfs is selected. Instead, just copy the whole struct in / out at the start and end of operations, respectively. Signed-off-by: Mark Fasheh Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/ioctl.c | 76 +++++++++++++++++++++++++++++++++----------------------- 1 file changed, 45 insertions(+), 31 deletions(-) (limited to 'fs') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index fba259ab9994..9d46f60cb943 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2696,9 +2696,9 @@ out_unlock: static long btrfs_ioctl_file_extent_same(struct file *file, void __user *argp) { - struct btrfs_ioctl_same_args *args = argp; - struct btrfs_ioctl_same_args same; - struct btrfs_ioctl_same_extent_info info; + struct btrfs_ioctl_same_args tmp; + struct btrfs_ioctl_same_args *same; + struct btrfs_ioctl_same_extent_info *info; struct inode *src = file->f_dentry->d_inode; struct file *dst_file = NULL; struct inode *dst; @@ -2706,6 +2706,7 @@ static long btrfs_ioctl_file_extent_same(struct file *file, u64 len; int i; int ret; + unsigned long size; u64 bs = BTRFS_I(src)->root->fs_info->sb->s_blocksize; bool is_admin = capable(CAP_SYS_ADMIN); @@ -2716,15 +2717,30 @@ static long btrfs_ioctl_file_extent_same(struct file *file, if (ret) return ret; - if (copy_from_user(&same, + if (copy_from_user(&tmp, (struct btrfs_ioctl_same_args __user *)argp, - sizeof(same))) { + sizeof(tmp))) { ret = -EFAULT; goto out; } - off = same.logical_offset; - len = same.length; + size = sizeof(tmp) + + tmp.dest_count * sizeof(struct btrfs_ioctl_same_extent_info); + + same = kmalloc(size, GFP_NOFS); + if (!same) { + ret = -EFAULT; + goto out; + } + + if (copy_from_user(same, + (struct btrfs_ioctl_same_args __user *)argp, size)) { + ret = -EFAULT; + goto out; + } + + off = same->logical_offset; + len = same->length; /* * Limit the total length we will dedupe for each operation. @@ -2752,27 +2768,28 @@ static long btrfs_ioctl_file_extent_same(struct file *file, if (!S_ISREG(src->i_mode)) goto out; - ret = 0; - for (i = 0; i < same.dest_count; i++) { - if (copy_from_user(&info, &args->info[i], sizeof(info))) { - ret = -EFAULT; - goto out; - } + /* pre-format output fields to sane values */ + for (i = 0; i < same->dest_count; i++) { + same->info[i].bytes_deduped = 0ULL; + same->info[i].status = 0; + } - info.bytes_deduped = 0; + ret = 0; + for (i = 0; i < same->dest_count; i++) { + info = &same->info[i]; - dst_file = fget(info.fd); + dst_file = fget(info->fd); if (!dst_file) { - info.status = -EBADF; + info->status = -EBADF; goto next; } if (!(is_admin || (dst_file->f_mode & FMODE_WRITE))) { - info.status = -EINVAL; + info->status = -EINVAL; goto next; } - info.status = -EXDEV; + info->status = -EXDEV; if (file->f_path.mnt != dst_file->f_path.mnt) goto next; @@ -2781,32 +2798,29 @@ static long btrfs_ioctl_file_extent_same(struct file *file, goto next; if (S_ISDIR(dst->i_mode)) { - info.status = -EISDIR; + info->status = -EISDIR; goto next; } if (!S_ISREG(dst->i_mode)) { - info.status = -EACCES; + info->status = -EACCES; goto next; } - info.status = btrfs_extent_same(src, off, len, dst, - info.logical_offset); - if (info.status == 0) - info.bytes_deduped += len; + info->status = btrfs_extent_same(src, off, len, dst, + info->logical_offset); + if (info->status == 0) + info->bytes_deduped += len; next: if (dst_file) fput(dst_file); - - if (__put_user_unaligned(info.status, &args->info[i].status) || - __put_user_unaligned(info.bytes_deduped, - &args->info[i].bytes_deduped)) { - ret = -EFAULT; - goto out; - } } + ret = copy_to_user(argp, same, size); + if (ret) + ret = -EFAULT; + out: mnt_drop_write_file(file); return ret; -- cgit v1.2.3-59-g8ed1b From 94aebfb2e7d83748d882992196cb05dd39ba1807 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 20 Sep 2013 22:33:20 -0400 Subject: Btrfs: create the uuid tree on remount rw Users have been complaining of the uuid tree stuff warning that there is no uuid root when trying to do snapshot operations. This is because if you mount -o ro we will not create the uuid tree. But then if you mount -o rw,remount we will still not create it and then any subsequent snapshot/subvol operations you try to do will fail gloriously. Fix this by creating the uuid_root on remount rw if it was not already there. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/super.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'fs') diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 6ab0df59b6c4..e913328d0f2a 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1383,6 +1383,16 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) pr_warn("btrfs: failed to resume dev_replace\n"); goto restore; } + + if (!fs_info->uuid_root) { + pr_info("btrfs: creating UUID tree\n"); + ret = btrfs_create_uuid_tree(fs_info); + if (ret) { + pr_warn("btrfs: failed to create the uuid tree" + "%d\n", ret); + goto restore; + } + } sb->s_flags &= ~MS_RDONLY; } out: -- cgit v1.2.3-59-g8ed1b