diff options
Diffstat (limited to 'fs')
38 files changed, 817 insertions, 450 deletions
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c index cb7f3fe..47cb267 100644 --- a/fs/btrfs/check-integrity.c +++ b/fs/btrfs/check-integrity.c @@ -326,9 +326,6 @@ static int btrfsic_handle_extent_data(struct btrfsic_state *state, static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len, struct btrfsic_block_data_ctx *block_ctx_out, int mirror_num); -static int btrfsic_map_superblock(struct btrfsic_state *state, u64 bytenr, - u32 len, struct block_device *bdev, - struct btrfsic_block_data_ctx *block_ctx_out); static void btrfsic_release_block_ctx(struct btrfsic_block_data_ctx *block_ctx); static int btrfsic_read_block(struct btrfsic_state *state, struct btrfsic_block_data_ctx *block_ctx); @@ -1326,24 +1323,25 @@ static int btrfsic_create_link_to_next_block( l = NULL; next_block->generation = BTRFSIC_GENERATION_UNKNOWN; } else { - if (next_block->logical_bytenr != next_bytenr && - !(!next_block->is_metadata && - 0 == next_block->logical_bytenr)) { - printk(KERN_INFO - "Referenced block @%llu (%s/%llu/%d)" - " found in hash table, %c," - " bytenr mismatch (!= stored %llu).\n", - next_bytenr, next_block_ctx->dev->name, - next_block_ctx->dev_bytenr, *mirror_nump, - btrfsic_get_block_type(state, next_block), - next_block->logical_bytenr); - } else if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE) - printk(KERN_INFO - "Referenced block @%llu (%s/%llu/%d)" - " found in hash table, %c.\n", - next_bytenr, next_block_ctx->dev->name, - next_block_ctx->dev_bytenr, *mirror_nump, - btrfsic_get_block_type(state, next_block)); + if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE) { + if (next_block->logical_bytenr != next_bytenr && + !(!next_block->is_metadata && + 0 == next_block->logical_bytenr)) + printk(KERN_INFO + "Referenced block @%llu (%s/%llu/%d) found in hash table, %c, bytenr mismatch (!= stored %llu).\n", + next_bytenr, next_block_ctx->dev->name, + next_block_ctx->dev_bytenr, *mirror_nump, + btrfsic_get_block_type(state, + next_block), + next_block->logical_bytenr); + else + printk(KERN_INFO + "Referenced block @%llu (%s/%llu/%d) found in hash table, %c.\n", + next_bytenr, next_block_ctx->dev->name, + next_block_ctx->dev_bytenr, *mirror_nump, + btrfsic_get_block_type(state, + next_block)); + } next_block->logical_bytenr = next_bytenr; next_block->mirror_num = *mirror_nump; @@ -1529,7 +1527,9 @@ static int btrfsic_handle_extent_data( return -1; } if (!block_was_created) { - if (next_block->logical_bytenr != next_bytenr && + if ((state->print_mask & + BTRFSIC_PRINT_MASK_VERBOSE) && + next_block->logical_bytenr != next_bytenr && !(!next_block->is_metadata && 0 == next_block->logical_bytenr)) { printk(KERN_INFO @@ -1607,25 +1607,6 @@ static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len, return ret; } -static int btrfsic_map_superblock(struct btrfsic_state *state, u64 bytenr, - u32 len, struct block_device *bdev, - struct btrfsic_block_data_ctx *block_ctx_out) -{ - block_ctx_out->dev = btrfsic_dev_state_lookup(bdev); - block_ctx_out->dev_bytenr = bytenr; - block_ctx_out->start = bytenr; - block_ctx_out->len = len; - block_ctx_out->datav = NULL; - block_ctx_out->pagev = NULL; - block_ctx_out->mem_to_free = NULL; - if (NULL != block_ctx_out->dev) { - return 0; - } else { - printk(KERN_INFO "btrfsic: error, cannot lookup dev (#2)!\n"); - return -ENXIO; - } -} - static void btrfsic_release_block_ctx(struct btrfsic_block_data_ctx *block_ctx) { if (block_ctx->mem_to_free) { @@ -1901,25 +1882,26 @@ again: dev_state, dev_bytenr); } - if (block->logical_bytenr != bytenr && - !(!block->is_metadata && - block->logical_bytenr == 0)) - printk(KERN_INFO - "Written block @%llu (%s/%llu/%d)" - " found in hash table, %c," - " bytenr mismatch" - " (!= stored %llu).\n", - bytenr, dev_state->name, dev_bytenr, - block->mirror_num, - btrfsic_get_block_type(state, block), - block->logical_bytenr); - else if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE) - printk(KERN_INFO - "Written block @%llu (%s/%llu/%d)" - " found in hash table, %c.\n", - bytenr, dev_state->name, dev_bytenr, - block->mirror_num, - btrfsic_get_block_type(state, block)); + if (state->print_mask & BTRFSIC_PRINT_MASK_VERBOSE) { + if (block->logical_bytenr != bytenr && + !(!block->is_metadata && + block->logical_bytenr == 0)) + printk(KERN_INFO + "Written block @%llu (%s/%llu/%d) found in hash table, %c, bytenr mismatch (!= stored %llu).\n", + bytenr, dev_state->name, + dev_bytenr, + block->mirror_num, + btrfsic_get_block_type(state, + block), + block->logical_bytenr); + else + printk(KERN_INFO + "Written block @%llu (%s/%llu/%d) found in hash table, %c.\n", + bytenr, dev_state->name, + dev_bytenr, block->mirror_num, + btrfsic_get_block_type(state, + block)); + } block->logical_bytenr = bytenr; } else { if (num_pages * PAGE_CACHE_SIZE < @@ -2002,24 +1984,13 @@ again: } } - if (block->is_superblock) - ret = btrfsic_map_superblock(state, bytenr, - processed_len, - bdev, &block_ctx); - else - ret = btrfsic_map_block(state, bytenr, processed_len, - &block_ctx, 0); - if (ret) { - printk(KERN_INFO - "btrfsic: btrfsic_map_block(root @%llu)" - " failed!\n", bytenr); - goto continue_loop; - } - block_ctx.datav = mapped_datav; - /* the following is required in case of writes to mirrors, - * use the same that was used for the lookup */ block_ctx.dev = dev_state; block_ctx.dev_bytenr = dev_bytenr; + block_ctx.start = bytenr; + block_ctx.len = processed_len; + block_ctx.pagev = NULL; + block_ctx.mem_to_free = NULL; + block_ctx.datav = mapped_datav; if (is_metadata || state->include_extent_data) { block->never_written = 0; @@ -2133,10 +2104,6 @@ again: /* this is getting ugly for the * include_extent_data case... */ bytenr = 0; /* unknown */ - block_ctx.start = bytenr; - block_ctx.len = processed_len; - block_ctx.mem_to_free = NULL; - block_ctx.pagev = NULL; } else { processed_len = state->metablock_size; bytenr = btrfs_stack_header_bytenr( @@ -2149,22 +2116,15 @@ again: "Written block @%llu (%s/%llu/?)" " !found in hash table, M.\n", bytenr, dev_state->name, dev_bytenr); - - ret = btrfsic_map_block(state, bytenr, processed_len, - &block_ctx, 0); - if (ret) { - printk(KERN_INFO - "btrfsic: btrfsic_map_block(root @%llu)" - " failed!\n", - dev_bytenr); - goto continue_loop; - } } - block_ctx.datav = mapped_datav; - /* the following is required in case of writes to mirrors, - * use the same that was used for the lookup */ + block_ctx.dev = dev_state; block_ctx.dev_bytenr = dev_bytenr; + block_ctx.start = bytenr; + block_ctx.len = processed_len; + block_ctx.pagev = NULL; + block_ctx.mem_to_free = NULL; + block_ctx.datav = mapped_datav; block = btrfsic_block_alloc(); if (NULL == block) { @@ -3130,10 +3090,13 @@ int btrfsic_mount(struct btrfs_root *root, root->sectorsize, PAGE_CACHE_SIZE); return -1; } - state = kzalloc(sizeof(*state), GFP_NOFS); - if (NULL == state) { - printk(KERN_INFO "btrfs check-integrity: kmalloc() failed!\n"); - return -1; + state = kzalloc(sizeof(*state), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT); + if (!state) { + state = vzalloc(sizeof(*state)); + if (!state) { + printk(KERN_INFO "btrfs check-integrity: vzalloc() failed!\n"); + return -1; + } } if (!btrfsic_is_initialized) { @@ -3277,5 +3240,8 @@ void btrfsic_unmount(struct btrfs_root *root, mutex_unlock(&btrfsic_mutex); - kfree(state); + if (is_vmalloc_addr(state)) + vfree(state); + else + kfree(state); } diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index d3220d3..1bf411b 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -224,16 +224,19 @@ out: * Clear the writeback bits on all of the file * pages for a compressed write */ -static noinline void end_compressed_writeback(struct inode *inode, u64 start, - unsigned long ram_size) +static noinline void end_compressed_writeback(struct inode *inode, + const struct compressed_bio *cb) { - unsigned long index = start >> PAGE_CACHE_SHIFT; - unsigned long end_index = (start + ram_size - 1) >> PAGE_CACHE_SHIFT; + unsigned long index = cb->start >> PAGE_CACHE_SHIFT; + unsigned long end_index = (cb->start + cb->len - 1) >> PAGE_CACHE_SHIFT; struct page *pages[16]; unsigned long nr_pages = end_index - index + 1; int i; int ret; + if (cb->errors) + mapping_set_error(inode->i_mapping, -EIO); + while (nr_pages > 0) { ret = find_get_pages_contig(inode->i_mapping, index, min_t(unsigned long, @@ -244,6 +247,8 @@ static noinline void end_compressed_writeback(struct inode *inode, u64 start, continue; } for (i = 0; i < ret; i++) { + if (cb->errors) + SetPageError(pages[i]); end_page_writeback(pages[i]); page_cache_release(pages[i]); } @@ -287,10 +292,11 @@ static void end_compressed_bio_write(struct bio *bio, int err) tree->ops->writepage_end_io_hook(cb->compressed_pages[0], cb->start, cb->start + cb->len - 1, - NULL, 1); + NULL, + err ? 0 : 1); cb->compressed_pages[0]->mapping = NULL; - end_compressed_writeback(inode, cb->start, cb->len); + end_compressed_writeback(inode, cb); /* note, our inode could be gone now */ /* diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 19bc616..8172341 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -2939,7 +2939,7 @@ done: */ if (!p->leave_spinning) btrfs_set_path_blocking(p); - if (ret < 0) + if (ret < 0 && !p->skip_release_on_error) btrfs_release_path(p); return ret; } diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 817fc19..9918ba3 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -607,6 +607,7 @@ struct btrfs_path { unsigned int leave_spinning:1; unsigned int search_commit_root:1; unsigned int need_commit_sem:1; + unsigned int skip_release_on_error:1; }; /* @@ -1170,6 +1171,7 @@ struct btrfs_space_info { struct percpu_counter total_bytes_pinned; struct list_head list; + struct list_head ro_bgs; struct rw_semaphore groups_sem; /* for block groups in our same type */ @@ -1305,6 +1307,9 @@ struct btrfs_block_group_cache { /* For delayed block group creation or deletion of empty block groups */ struct list_head bg_list; + + /* For read-only block groups */ + struct list_head ro_list; }; /* delayed seq elem */ @@ -3734,6 +3739,10 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, int verify_dir_item(struct btrfs_root *root, struct extent_buffer *leaf, struct btrfs_dir_item *dir_item); +struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, + struct btrfs_path *path, + const char *name, + int name_len); /* orphan.c */ int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans, @@ -3905,6 +3914,7 @@ int btrfs_prealloc_file_range_trans(struct inode *inode, struct btrfs_trans_handle *trans, int mode, u64 start, u64 num_bytes, u64 min_size, loff_t actual_len, u64 *alloc_hint); +int btrfs_inode_check_errors(struct inode *inode); extern const struct dentry_operations btrfs_dentry_operations; /* ioctl.c */ @@ -3949,6 +3959,7 @@ int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, struct extent_state **cached); +int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end); /* tree-defrag.c */ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 6f662b3..971c061 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -422,9 +422,15 @@ int btrfs_dev_replace_start(struct btrfs_root *root, &dev_replace->scrub_progress, 0, 1); ret = btrfs_dev_replace_finishing(root->fs_info, ret); - WARN_ON(ret); + /* don't warn if EINPROGRESS, someone else might be running scrub */ + if (ret == -EINPROGRESS) { + args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS; + ret = 0; + } else { + WARN_ON(ret); + } - return 0; + return ret; leave: dev_replace->srcdev = NULL; @@ -542,7 +548,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device); mutex_unlock(&dev_replace->lock_finishing_cancel_unmount); - return 0; + return scrub_ret; } printk_in_rcu(KERN_INFO diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index fc8df86..1752625 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -21,10 +21,6 @@ #include "hash.h" #include "transaction.h" -static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, - struct btrfs_path *path, - const char *name, int name_len); - /* * insert a name into a directory, doing overflow properly if there is a hash * collision. data_size indicates how big the item inserted should be. On @@ -383,9 +379,9 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans, * this walks through all the entries in a dir item and finds one * for a specific name. */ -static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, - struct btrfs_path *path, - const char *name, int name_len) +struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root, + struct btrfs_path *path, + const char *name, int name_len) { struct btrfs_dir_item *dir_item; unsigned long name_ptr; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 6b406e3..1e3e414 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3841,12 +3841,12 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, */ if (!IS_ALIGNED(btrfs_super_root(sb), 4096)) printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n", - sb->root); + btrfs_super_root(sb)); if (!IS_ALIGNED(btrfs_super_chunk_root(sb), 4096)) - printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n", - sb->chunk_root); + printk(KERN_WARNING "BTRFS: chunk_root block unaligned: %llu\n", + btrfs_super_chunk_root(sb)); if (!IS_ALIGNED(btrfs_super_log_root(sb), 4096)) - printk(KERN_WARNING "BTRFS: tree_root block unaligned: %llu\n", + printk(KERN_WARNING "BTRFS: log_root block unaligned: %llu\n", btrfs_super_log_root(sb)); if (memcmp(fs_info->fsid, sb->dev_item.fsid, BTRFS_UUID_SIZE) != 0) { @@ -4131,6 +4131,25 @@ again: return 0; } +static void btrfs_free_pending_ordered(struct btrfs_transaction *cur_trans, + struct btrfs_fs_info *fs_info) +{ + struct btrfs_ordered_extent *ordered; + + spin_lock(&fs_info->trans_lock); + while (!list_empty(&cur_trans->pending_ordered)) { + ordered = list_first_entry(&cur_trans->pending_ordered, + struct btrfs_ordered_extent, + trans_list); + list_del_init(&ordered->trans_list); + spin_unlock(&fs_info->trans_lock); + + btrfs_put_ordered_extent(ordered); + spin_lock(&fs_info->trans_lock); + } + spin_unlock(&fs_info->trans_lock); +} + void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, struct btrfs_root *root) { @@ -4142,6 +4161,7 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans, cur_trans->state = TRANS_STATE_UNBLOCKED; wake_up(&root->fs_info->transaction_wait); + btrfs_free_pending_ordered(cur_trans, root->fs_info); btrfs_destroy_delayed_inodes(root); btrfs_assert_delayed_root_empty(root); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 47c1ba1..cf3460e 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3504,6 +3504,7 @@ static int update_space_info(struct btrfs_fs_info *info, u64 flags, found->chunk_alloc = 0; found->flush = 0; init_waitqueue_head(&found->wait); + INIT_LIST_HEAD(&found->ro_bgs); ret = kobject_init_and_add(&found->kobj, &space_info_ktype, info->space_info_kobj, "%s", @@ -8511,6 +8512,7 @@ static int set_block_group_ro(struct btrfs_block_group_cache *cache, int force) min_allocable_bytes <= sinfo->total_bytes) { sinfo->bytes_readonly += num_bytes; cache->ro = 1; + list_add_tail(&cache->ro_list, &sinfo->ro_bgs); ret = 0; } out: @@ -8565,15 +8567,20 @@ int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, /* * helper to account the unused space of all the readonly block group in the - * list. takes mirrors into account. + * space_info. takes mirrors into account. */ -static u64 __btrfs_get_ro_block_group_free_space(struct list_head *groups_list) +u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo) { struct btrfs_block_group_cache *block_group; u64 free_bytes = 0; int factor; - list_for_each_entry(block_group, groups_list, list) { + /* It's df, we don't care if it's racey */ + if (list_empty(&sinfo->ro_bgs)) + return 0; + + spin_lock(&sinfo->lock); + list_for_each_entry(block_group, &sinfo->ro_bgs, ro_list) { spin_lock(&block_group->lock); if (!block_group->ro) { @@ -8594,26 +8601,6 @@ static u64 __btrfs_get_ro_block_group_free_space(struct list_head *groups_list) spin_unlock(&block_group->lock); } - - return free_bytes; -} - -/* - * helper to account the unused space of all the readonly block group in the - * space_info. takes mirrors into account. - */ -u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo) -{ - int i; - u64 free_bytes = 0; - - spin_lock(&sinfo->lock); - - for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) - if (!list_empty(&sinfo->block_groups[i])) - free_bytes += __btrfs_get_ro_block_group_free_space( - &sinfo->block_groups[i]); - spin_unlock(&sinfo->lock); return free_bytes; @@ -8633,6 +8620,7 @@ void btrfs_set_block_group_rw(struct btrfs_root *root, cache->bytes_super - btrfs_block_group_used(&cache->item); sinfo->bytes_readonly -= num_bytes; cache->ro = 0; + list_del_init(&cache->ro_list); spin_unlock(&cache->lock); spin_unlock(&sinfo->lock); } @@ -9002,6 +8990,7 @@ btrfs_create_block_group_cache(struct btrfs_root *root, u64 start, u64 size) INIT_LIST_HEAD(&cache->list); INIT_LIST_HEAD(&cache->cluster_list); INIT_LIST_HEAD(&cache->bg_list); + INIT_LIST_HEAD(&cache->ro_list); btrfs_init_free_space_ctl(cache); return cache; @@ -9411,6 +9400,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, * are still on the list after taking the semaphore */ list_del_init(&block_group->list); + list_del_init(&block_group->ro_list); if (list_empty(&block_group->space_info->block_groups[index])) { kobj = block_group->space_info->block_group_kobjs[index]; block_group->space_info->block_group_kobjs[index] = NULL; diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index bf3f424..4ebabd2 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -595,9 +595,14 @@ int clear_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, clear = 1; again: if (!prealloc && (mask & __GFP_WAIT)) { + /* + * Don't care for allocation failure here because we might end + * up not needing the pre-allocated extent state at all, which + * is the case if we only have in the tree extent states that + * cover our input range and don't cover too any other range. + * If we end up needing a new extent state we allocate it later. + */ prealloc = alloc_extent_state(mask); - if (!prealloc) - return -ENOMEM; } spin_lock(&tree->lock); @@ -796,17 +801,25 @@ static void set_state_bits(struct extent_io_tree *tree, state->state |= bits_to_set; } -static void cache_state(struct extent_state *state, - struct extent_state **cached_ptr) +static void cache_state_if_flags(struct extent_state *state, + struct extent_state **cached_ptr, + const u64 flags) { if (cached_ptr && !(*cached_ptr)) { - if (state->state & (EXTENT_IOBITS | EXTENT_BOUNDARY)) { + if (!flags || (state->state & flags)) { *cached_ptr = state; atomic_inc(&state->refs); } } } +static void cache_state(struct extent_state *state, + struct extent_state **cached_ptr) +{ + return cache_state_if_flags(state, cached_ptr, + EXTENT_IOBITS | EXTENT_BOUNDARY); +} + /* * set some bits on a range in the tree. This may require allocations or * sleeping, so the gfp mask is used to indicate what is allowed. @@ -1058,13 +1071,21 @@ int convert_extent_bit(struct extent_io_tree *tree, u64 start, u64 end, int err = 0; u64 last_start; u64 last_end; + bool first_iteration = true; btrfs_debug_check_extent_io_range(tree, start, end); again: if (!prealloc && (mask & __GFP_WAIT)) { + /* + * Best effort, don't worry if extent state allocation fails + * here for the first iteration. We might have a cached state + * that matches exactly the target range, in which case no + * extent state allocations are needed. We'll only know this + * after locking the tree. + */ prealloc = alloc_extent_state(mask); - if (!prealloc) + if (!prealloc && !first_iteration) return -ENOMEM; } @@ -1234,6 +1255,7 @@ search_again: spin_unlock(&tree->lock); if (mask & __GFP_WAIT) cond_resched(); + first_iteration = false; goto again; } @@ -1482,7 +1504,7 @@ int find_first_extent_bit(struct extent_io_tree *tree, u64 start, state = find_first_extent_bit_state(tree, start, bits); got_it: if (state) { - cache_state(state, cached_state); + cache_state_if_flags(state, cached_state, 0); *start_ret = state->start; *end_ret = state->end; ret = 0; @@ -1746,6 +1768,9 @@ int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end, if (page_ops == 0) return 0; + if ((page_ops & PAGE_SET_ERROR) && nr_pages > 0) + mapping_set_error(inode->i_mapping, -EIO); + while (nr_pages > 0) { ret = find_get_pages_contig(inode->i_mapping, index, min_t(unsigned long, @@ -1763,6 +1788,8 @@ int extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end, clear_page_dirty_for_io(pages[i]); if (page_ops & PAGE_SET_WRITEBACK) set_page_writeback(pages[i]); + if (page_ops & PAGE_SET_ERROR) + SetPageError(pages[i]); if (page_ops & PAGE_END_WRITEBACK) end_page_writeback(pages[i]); if (page_ops & PAGE_UNLOCK) diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h index 6d4b938..ece9ce8 100644 --- a/fs/btrfs/extent_io.h +++ b/fs/btrfs/extent_io.h @@ -49,6 +49,7 @@ #define PAGE_SET_WRITEBACK (1 << 2) #define PAGE_END_WRITEBACK (1 << 3) #define PAGE_SET_PRIVATE2 (1 << 4) +#define PAGE_SET_ERROR (1 << 5) /* * page->private values. Every page that is controlled by the extent diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index 225302b..6a98bdd 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -287,8 +287,6 @@ int unpin_extent_cache(struct extent_map_tree *tree, u64 start, u64 len, if (!em) goto out; - if (!test_bit(EXTENT_FLAG_LOGGING, &em->flags)) - list_move(&em->list, &tree->modified_extents); em->generation = gen; clear_bit(EXTENT_FLAG_PINNED, &em->flags); em->mod_start = em->start; diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index a18ceab..0fbf0e7 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1676,6 +1676,7 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, loff_t pos) { struct file *file = iocb->ki_filp; + struct inode *inode = file_inode(file); ssize_t written; ssize_t written_buffered; loff_t endbyte; @@ -1692,8 +1693,15 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, err = written_buffered; goto out; } + /* + * Ensure all data is persisted. We want the next direct IO read to be + * able to read what was just written. + */ endbyte = pos + written_buffered - 1; - err = filemap_write_and_wait_range(file->f_mapping, pos, endbyte); + err = btrfs_fdatawrite_range(inode, pos, endbyte); + if (err) + goto out; + err = filemap_fdatawait_range(inode->i_mapping, pos, endbyte); if (err) goto out; written += written_buffered; @@ -1854,10 +1862,7 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end) int ret; atomic_inc(&BTRFS_I(inode)->sync_writers); - ret = filemap_fdatawrite_range(inode->i_mapping, start, end); - if (!ret && test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, - &BTRFS_I(inode)->runtime_flags)) - ret = filemap_fdatawrite_range(inode->i_mapping, start, end); + ret = btrfs_fdatawrite_range(inode, start, end); atomic_dec(&BTRFS_I(inode)->sync_writers); return ret; @@ -2810,3 +2815,29 @@ int btrfs_auto_defrag_init(void) return 0; } + +int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end) +{ + int ret; + + /* + * So with compression we will find and lock a dirty page and clear the + * first one as dirty, setup an async extent, and immediately return + * with the entire range locked but with nobody actually marked with + * writeback. So we can't just filemap_write_and_wait_range() and + * expect it to work since it will just kick off a thread to do the + * actual work. So we need to call filemap_fdatawrite_range _again_ + * since it will wait on the page lock, which won't be unlocked until + * after the pages have been marked as writeback and so we're good to go + * from there. We have to do this otherwise we'll miss the ordered + * extents and that results in badness. Please Josef, do not think you + * know better and pull this out at some point in the future, it is + * right and you are wrong. + */ + ret = filemap_fdatawrite_range(inode->i_mapping, start, end); + if (!ret && test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, + &BTRFS_I(inode)->runtime_flags)) + ret = filemap_fdatawrite_range(inode->i_mapping, start, end); + + return ret; +} diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d23362f..a5374c2 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -382,7 +382,7 @@ static inline int inode_need_compress(struct inode *inode) * are written in the same order that the flusher thread sent them * down. */ -static noinline int compress_file_range(struct inode *inode, +static noinline void compress_file_range(struct inode *inode, struct page *locked_page, u64 start, u64 end, struct async_cow *async_cow, @@ -411,14 +411,6 @@ static noinline int compress_file_range(struct inode *inode, (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size)) btrfs_add_inode_defrag(NULL, inode); - /* - * skip compression for a small file range(<=blocksize) that - * isn't an inline extent, since it dosen't save disk space at all. - */ - if ((end - start + 1) <= blocksize && - (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size)) - goto cleanup_and_bail_uncompressed; - actual_end = min_t(u64, isize, end + 1); again: will_compress = 0; @@ -440,6 +432,14 @@ again: total_compressed = actual_end - start; + /* + * skip compression for a small file range(<=blocksize) that + * isn't an inline extent, since it dosen't save disk space at all. + */ + if (total_compressed <= blocksize && + (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size)) + goto cleanup_and_bail_uncompressed; + /* we want to make sure that amount of ram required to uncompress * an extent is reasonable, so we limit the total size in ram * of a compressed extent to 128k. This is a crucial number @@ -527,7 +527,10 @@ cont: if (ret <= 0) { unsigned long clear_flags = EXTENT_DELALLOC | EXTENT_DEFRAG; + unsigned long page_error_op; + clear_flags |= (ret < 0) ? EXTENT_DO_ACCOUNTING : 0; + page_error_op = ret < 0 ? PAGE_SET_ERROR : 0; /* * inline extent creation worked or returned error, @@ -538,6 +541,7 @@ cont: clear_flags, PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK | + page_error_op | PAGE_END_WRITEBACK); goto free_pages_out; } @@ -620,8 +624,7 @@ cleanup_and_bail_uncompressed: *num_added += 1; } -out: - return ret; + return; free_pages_out: for (i = 0; i < nr_pages_ret; i++) { @@ -629,8 +632,22 @@ free_pages_out: page_cache_release(pages[i]); } kfree(pages); +} - goto out; +static void free_async_extent_pages(struct async_extent *async_extent) +{ + int i; + + if (!async_extent->pages) + return; + + for (i = 0; i < async_extent->nr_pages; i++) { + WARN_ON(async_extent->pages[i]->mapping); + page_cache_release(async_extent->pages[i]); + } + kfree(async_extent->pages); + async_extent->nr_pages = 0; + async_extent->pages = NULL; } /* @@ -639,7 +656,7 @@ free_pages_out: * queued. We walk all the async extents created by compress_file_range * and send them down to the disk. */ -static noinline int submit_compressed_extents(struct inode *inode, +static noinline void submit_compressed_extents(struct inode *inode, struct async_cow *async_cow) { struct async_extent *async_extent; @@ -651,9 +668,6 @@ static noinline int submit_compressed_extents(struct inode *inode, struct extent_io_tree *io_tree; int ret = 0; - if (list_empty(&async_cow->extents)) - return 0; - again: while (!list_empty(&async_cow->extents)) { async_extent = list_entry(async_cow->extents.next, @@ -709,15 +723,7 @@ retry: async_extent->compressed_size, 0, alloc_hint, &ins, 1, 1); if (ret) { - int i; - - for (i = 0; i < async_extent->nr_pages; i++) { - WARN_ON(async_extent->pages[i]->mapping); - page_cache_release(async_extent->pages[i]); - } - kfree(async_extent->pages); - async_extent->nr_pages = 0; - async_extent->pages = NULL; + free_async_extent_pages(async_extent); if (ret == -ENOSPC) { unlock_extent(io_tree, async_extent->start, @@ -814,15 +820,26 @@ retry: ins.objectid, ins.offset, async_extent->pages, async_extent->nr_pages); + if (ret) { + struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; + struct page *p = async_extent->pages[0]; + const u64 start = async_extent->start; + const u64 end = start + async_extent->ram_size - 1; + + p->mapping = inode->i_mapping; + tree->ops->writepage_end_io_hook(p, start, end, + NULL, 0); + p->mapping = NULL; + extent_clear_unlock_delalloc(inode, start, end, NULL, 0, + PAGE_END_WRITEBACK | + PAGE_SET_ERROR); + free_async_extent_pages(async_extent); + } alloc_hint = ins.objectid + ins.offset; kfree(async_extent); - if (ret) - goto out; cond_resched(); } - ret = 0; -out: - return ret; + return; out_free_reserve: btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1); out_free: @@ -832,7 +849,9 @@ out_free: NULL, EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING, PAGE_UNLOCK | PAGE_CLEAR_DIRTY | - PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK); + PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK | + PAGE_SET_ERROR); + free_async_extent_pages(async_extent); kfree(async_extent); goto again; } @@ -7000,9 +7019,12 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend, btrfs_put_ordered_extent(ordered); } else { /* Screw you mmap */ - ret = filemap_write_and_wait_range(inode->i_mapping, - lockstart, - lockend); + ret = btrfs_fdatawrite_range(inode, lockstart, lockend); + if (ret) + break; + ret = filemap_fdatawait_range(inode->i_mapping, + lockstart, + lockend); if (ret) break; @@ -9442,6 +9464,21 @@ out_inode: } +/* Inspired by filemap_check_errors() */ +int btrfs_inode_check_errors(struct inode *inode) +{ + int ret = 0; + + if (test_bit(AS_ENOSPC, &inode->i_mapping->flags) && + test_and_clear_bit(AS_ENOSPC, &inode->i_mapping->flags)) + ret = -ENOSPC; + if (test_bit(AS_EIO, &inode->i_mapping->flags) && + test_and_clear_bit(AS_EIO, &inode->i_mapping->flags)) + ret = -EIO; + + return ret; +} + static const struct inode_operations btrfs_dir_inode_operations = { .getattr = btrfs_getattr, .lookup = btrfs_lookup, diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index ac734ec..534544e 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -220,6 +220,7 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset, INIT_LIST_HEAD(&entry->work_list); init_completion(&entry->completion); INIT_LIST_HEAD(&entry->log_list); + INIT_LIST_HEAD(&entry->trans_list); trace_btrfs_ordered_extent_add(inode, entry); @@ -431,19 +432,31 @@ out: /* Needs to either be called under a log transaction or the log_mutex */ void btrfs_get_logged_extents(struct inode *inode, - struct list_head *logged_list) + struct list_head *logged_list, + const loff_t start, + const loff_t end) { struct btrfs_ordered_inode_tree *tree; struct btrfs_ordered_extent *ordered; struct rb_node *n; + struct rb_node *prev; tree = &BTRFS_I(inode)->ordered_tree; spin_lock_irq(&tree->lock); - for (n = rb_first(&tree->tree); n; n = rb_next(n)) { + n = __tree_search(&tree->tree, end, &prev); + if (!n) + n = prev; + for (; n; n = rb_prev(n)) { ordered = rb_entry(n, struct btrfs_ordered_extent, rb_node); + if (ordered->file_offset > end) + continue; + if (entry_end(ordered) <= start) + break; if (!list_empty(&ordered->log_list)) continue; - list_add_tail(&ordered->log_list, logged_list); + if (test_bit(BTRFS_ORDERED_LOGGED, &ordered->flags)) + continue; + list_add(&ordered->log_list, logged_list); atomic_inc(&ordered->refs); } spin_unlock_irq(&tree->lock); @@ -472,7 +485,8 @@ void btrfs_submit_logged_extents(struct list_head *logged_list, spin_unlock_irq(&log->log_extents_lock[index]); } -void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid) +void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans, + struct btrfs_root *log, u64 transid) { struct btrfs_ordered_extent *ordered; int index = transid % 2; @@ -497,7 +511,8 @@ void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid) wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags)); - btrfs_put_ordered_extent(ordered); + if (!test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags)) + list_add_tail(&ordered->trans_list, &trans->ordered); spin_lock_irq(&log->log_extents_lock[index]); } spin_unlock_irq(&log->log_extents_lock[index]); @@ -725,30 +740,10 @@ int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len) /* start IO across the range first to instantiate any delalloc * extents */ - ret = filemap_fdatawrite_range(inode->i_mapping, start, orig_end); + ret = btrfs_fdatawrite_range(inode, start, orig_end); if (ret) return ret; - /* - * So with compression we will find and lock a dirty page and clear the - * first one as dirty, setup an async extent, and immediately return - * with the entire range locked but with nobody actually marked with - * writeback. So we can't just filemap_write_and_wait_range() and - * expect it to work since it will just kick off a thread to do the - * actual work. So we need to call filemap_fdatawrite_range _again_ - * since it will wait on the page lock, which won't be unlocked until - * after the pages have been marked as writeback and so we're good to go - * from there. We have to do this otherwise we'll miss the ordered - * extents and that results in badness. Please Josef, do not think you - * know better and pull this out at some point in the future, it is - * right and you are wrong. - */ - if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, - &BTRFS_I(inode)->runtime_flags)) { - ret = filemap_fdatawrite_range(inode->i_mapping, start, - orig_end); - if (ret) - return ret; - } + ret = filemap_fdatawait_range(inode->i_mapping, start, orig_end); if (ret) return ret; diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h index d81a274..e96cd4c 100644 --- a/fs/btrfs/ordered-data.h +++ b/fs/btrfs/ordered-data.h @@ -71,6 +71,8 @@ struct btrfs_ordered_sum { ordered extent */ #define BTRFS_ORDERED_TRUNCATED 9 /* Set when we have to truncate an extent */ +#define BTRFS_ORDERED_LOGGED 10 /* Set when we've waited on this ordered extent + * in the logging code. */ struct btrfs_ordered_extent { /* logical offset in the file */ u64 file_offset; @@ -121,6 +123,9 @@ struct btrfs_ordered_extent { /* If we need to wait on this to be done */ struct list_head log_list; + /* If the transaction needs to wait on this ordered extent */ + struct list_head trans_list; + /* used to wait for the BTRFS_ORDERED_COMPLETE bit */ wait_queue_head_t wait; @@ -193,11 +198,14 @@ int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr, int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr); void btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr); void btrfs_get_logged_extents(struct inode *inode, - struct list_head *logged_list); + struct list_head *logged_list, + const loff_t start, + const loff_t end); void btrfs_put_logged_extents(struct list_head *logged_list); void btrfs_submit_logged_extents(struct list_head *logged_list, struct btrfs_root *log); -void btrfs_wait_logged_extents(struct btrfs_root *log, u64 transid); +void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans, + struct btrfs_root *log, u64 transid); void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid); int __init ordered_data_init(void); void ordered_data_exit(void); diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c index efa0831..4325bb0 100644 --- a/fs/btrfs/scrub.c +++ b/fs/btrfs/scrub.c @@ -3310,6 +3310,50 @@ out: scrub_pending_trans_workers_dec(sctx); } +static int check_extent_to_block(struct inode *inode, u64 start, u64 len, + u64 logical) +{ + struct extent_state *cached_state = NULL; + struct btrfs_ordered_extent *ordered; + struct extent_io_tree *io_tree; + struct extent_map *em; + u64 lockstart = start, lockend = start + len - 1; + int ret = 0; + + 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); + ret = 1; + goto out_unlock; + } + + em = btrfs_get_extent(inode, NULL, 0, start, 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 > logical || + em->block_start + em->block_len < logical + len) { + free_extent_map(em); + ret = 1; + goto out_unlock; + } + free_extent_map(em); + +out_unlock: + unlock_extent_cached(io_tree, lockstart, lockend, &cached_state, + GFP_NOFS); + return ret; +} + static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, struct scrub_copy_nocow_ctx *nocow_ctx) { @@ -3318,13 +3362,10 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, 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 nocow_ctx_logical; u64 len = nocow_ctx->len; - u64 lockstart = offset, lockend = offset + len - 1; unsigned long index; int srcu_index; int ret = 0; @@ -3356,30 +3397,13 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root, physical_for_dev_replace = nocow_ctx->physical_for_dev_replace; io_tree = &BTRFS_I(inode)->io_tree; + nocow_ctx_logical = nocow_ctx->logical; - 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; + ret = check_extent_to_block(inode, offset, len, nocow_ctx_logical); + if (ret) { + ret = ret > 0 ? 0 : ret; + goto out; } - free_extent_map(em); while (len >= PAGE_CACHE_SIZE) { index = offset >> PAGE_CACHE_SHIFT; @@ -3396,7 +3420,7 @@ again: goto next_page; } else { ClearPageError(page); - err = extent_read_full_page_nolock(io_tree, page, + err = extent_read_full_page(io_tree, page, btrfs_get_extent, nocow_ctx->mirror_num); if (err) { @@ -3421,6 +3445,14 @@ again: goto next_page; } } + + ret = check_extent_to_block(inode, offset, len, + nocow_ctx_logical); + if (ret) { + ret = ret > 0 ? 0 : ret; + goto next_page; + } + err = write_page_nocow(nocow_ctx->sctx, physical_for_dev_replace, page); if (err) @@ -3434,12 +3466,10 @@ next_page: offset += PAGE_CACHE_SIZE; physical_for_dev_replace += PAGE_CACHE_SIZE; + nocow_ctx_logical += 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); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 65c75d9..391ec44 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1652,8 +1652,20 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) int i = 0, nr_devices; int ret; + /* + * We aren't under the device list lock, so this is racey-ish, but good + * enough for our purposes. + */ nr_devices = fs_info->fs_devices->open_devices; - BUG_ON(!nr_devices); + if (!nr_devices) { + smp_mb(); + nr_devices = fs_info->fs_devices->open_devices; + ASSERT(nr_devices); + if (!nr_devices) { + *free_bytes = 0; + return 0; + } + } devices_info = kmalloc_array(nr_devices, sizeof(*devices_info), GFP_NOFS); @@ -1678,11 +1690,17 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) else min_stripe_size = BTRFS_STRIPE_LEN; - list_for_each_entry(device, &fs_devices->devices, dev_list) { + if (fs_info->alloc_start) + mutex_lock(&fs_devices->device_list_mutex); + rcu_read_lock(); + list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) { if (!device->in_fs_metadata || !device->bdev || device->is_tgtdev_for_dev_replace) continue; + if (i >= nr_devices) + break; + avail_space = device->total_bytes - device->bytes_used; /* align with stripe_len */ @@ -1697,24 +1715,32 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) skip_space = 1024 * 1024; /* user can set the offset in fs_info->alloc_start. */ - if (fs_info->alloc_start + BTRFS_STRIPE_LEN <= - device->total_bytes) + if (fs_info->alloc_start && + fs_info->alloc_start + BTRFS_STRIPE_LEN <= + device->total_bytes) { + rcu_read_unlock(); skip_space = max(fs_info->alloc_start, skip_space); - /* - * btrfs can not use the free space in [0, skip_space - 1], - * we must subtract it from the total. In order to implement - * it, we account the used space in this range first. - */ - ret = btrfs_account_dev_extents_size(device, 0, skip_space - 1, - &used_space); - if (ret) { - kfree(devices_info); - return ret; - } + /* + * btrfs can not use the free space in + * [0, skip_space - 1], we must subtract it from the + * total. In order to implement it, we account the used + * space in this range first. + */ + ret = btrfs_account_dev_extents_size(device, 0, + skip_space - 1, + &used_space); + if (ret) { + kfree(devices_info); + mutex_unlock(&fs_devices->device_list_mutex); + return ret; + } - /* calc the free space in [0, skip_space - 1] */ - skip_space -= used_space; + rcu_read_lock(); + + /* calc the free space in [0, skip_space - 1] */ + skip_space -= used_space; + } /* * we can use the free space in [0, skip_space - 1], subtract @@ -1733,6 +1759,9 @@ static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes) i++; } + rcu_read_unlock(); + if (fs_info->alloc_start) + mutex_unlock(&fs_devices->device_list_mutex); nr_devices = i; @@ -1795,8 +1824,6 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) * holding chunk_muext to avoid allocating new chunks, holding * device_list_mutex to avoid the device being removed */ - mutex_lock(&fs_info->fs_devices->device_list_mutex); - mutex_lock(&fs_info->chunk_mutex); rcu_read_lock(); list_for_each_entry_rcu(found, head, list) { if (found->flags & BTRFS_BLOCK_GROUP_DATA) { @@ -1832,17 +1859,12 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_bfree -= block_rsv->size >> bits; spin_unlock(&block_rsv->lock); - buf->f_bavail = total_free_data; + buf->f_bavail = div_u64(total_free_data, factor); ret = btrfs_calc_avail_data_space(fs_info->tree_root, &total_free_data); - if (ret) { - mutex_unlock(&fs_info->chunk_mutex); - mutex_unlock(&fs_info->fs_devices->device_list_mutex); + if (ret) return ret; - } buf->f_bavail += div_u64(total_free_data, factor); buf->f_bavail = buf->f_bavail >> bits; - mutex_unlock(&fs_info->chunk_mutex); - mutex_unlock(&fs_info->fs_devices->device_list_mutex); buf->f_type = BTRFS_SUPER_MAGIC; buf->f_bsize = dentry->d_sb->s_blocksize; diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 9d8e2b8d..a605d4e 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -76,6 +76,32 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction) } } +static void clear_btree_io_tree(struct extent_io_tree *tree) +{ + spin_lock(&tree->lock); + while (!RB_EMPTY_ROOT(&tree->state)) { + struct rb_node *node; + struct extent_state *state; + + node = rb_first(&tree->state); + state = rb_entry(node, struct extent_state, rb_node); + rb_erase(&state->rb_node, &tree->state); + RB_CLEAR_NODE(&state->rb_node); + /* + * btree io trees aren't supposed to have tasks waiting for + * changes in the flags of extent states ever. + */ + ASSERT(!waitqueue_active(&state->wq)); + free_extent_state(state); + if (need_resched()) { + spin_unlock(&tree->lock); + cond_resched(); + spin_lock(&tree->lock); + } + } + spin_unlock(&tree->lock); +} + static noinline void switch_commit_roots(struct btrfs_transaction *trans, struct btrfs_fs_info *fs_info) { @@ -89,6 +115,7 @@ static noinline void switch_commit_roots(struct btrfs_transaction *trans, root->commit_root = btrfs_root_node(root); if (is_fstree(root->objectid)) btrfs_unpin_free_ino(root); + clear_btree_io_tree(&root->dirty_log_pages); } up_write(&fs_info->commit_root_sem); } @@ -220,6 +247,7 @@ loop: INIT_LIST_HEAD(&cur_trans->pending_snapshots); INIT_LIST_HEAD(&cur_trans->pending_chunks); INIT_LIST_HEAD(&cur_trans->switch_commits); + INIT_LIST_HEAD(&cur_trans->pending_ordered); list_add_tail(&cur_trans->list, &fs_info->trans_list); extent_io_tree_init(&cur_trans->dirty_pages, fs_info->btree_inode->i_mapping); @@ -488,6 +516,7 @@ again: h->sync = false; INIT_LIST_HEAD(&h->qgroup_ref_list); INIT_LIST_HEAD(&h->new_bgs); + INIT_LIST_HEAD(&h->ordered); smp_mb(); if (cur_trans->state >= TRANS_STATE_BLOCKED && @@ -719,6 +748,12 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans, if (!list_empty(&trans->new_bgs)) btrfs_create_pending_block_groups(trans, root); + if (!list_empty(&trans->ordered)) { + spin_lock(&info->trans_lock); + list_splice(&trans->ordered, &cur_trans->pending_ordered); + spin_unlock(&info->trans_lock); + } + trans->delayed_ref_updates = 0; if (!trans->sync) { must_run_delayed_refs = @@ -828,17 +863,39 @@ int btrfs_write_marked_extents(struct btrfs_root *root, while (!find_first_extent_bit(dirty_pages, start, &start, &end, mark, &cached_state)) { - convert_extent_bit(dirty_pages, start, end, EXTENT_NEED_WAIT, - mark, &cached_state, GFP_NOFS); - cached_state = NULL; - err = filemap_fdatawrite_range(mapping, start, end); + bool wait_writeback = false; + + err = convert_extent_bit(dirty_pages, start, end, + EXTENT_NEED_WAIT, + mark, &cached_state, GFP_NOFS); + /* + * convert_extent_bit can return -ENOMEM, which is most of the + * time a temporary error. So when it happens, ignore the error + * and wait for writeback of this range to finish - because we + * failed to set the bit EXTENT_NEED_WAIT for the range, a call + * to btrfs_wait_marked_extents() would not know that writeback + * for this range started and therefore wouldn't wait for it to + * finish - we don't want to commit a superblock that points to + * btree nodes/leafs for which writeback hasn't finished yet + * (and without errors). + * We cleanup any entries left in the io tree when committing + * the transaction (through clear_btree_io_tree()). + */ + if (err == -ENOMEM) { + err = 0; + wait_writeback = true; + } + if (!err) + err = filemap_fdatawrite_range(mapping, start, end); if (err) werr = err; + else if (wait_writeback) + werr = filemap_fdatawait_range(mapping, start, end); + free_extent_state(cached_state); + cached_state = NULL; cond_resched(); start = end + 1; } - if (err) - werr = err; return werr; } @@ -862,11 +919,25 @@ int btrfs_wait_marked_extents(struct btrfs_root *root, while (!find_first_extent_bit(dirty_pages, start, &start, &end, EXTENT_NEED_WAIT, &cached_state)) { - clear_extent_bit(dirty_pages, start, end, EXTENT_NEED_WAIT, - 0, 0, &cached_state, GFP_NOFS); - err = filemap_fdatawait_range(mapping, start, end); + /* + * Ignore -ENOMEM errors returned by clear_extent_bit(). + * When committing the transaction, we'll remove any entries + * left in the io tree. For a log commit, we don't remove them + * after committing the log because the tree can be accessed + * concurrently - we do it only at transaction commit time when + * it's safe to do it (through clear_btree_io_tree()). + */ + err = clear_extent_bit(dirty_pages, start, end, + EXTENT_NEED_WAIT, + 0, 0, &cached_state, GFP_NOFS); + if (err == -ENOMEM) + err = 0; + if (!err) + err = filemap_fdatawait_range(mapping, start, end); if (err) werr = err; + free_extent_state(cached_state); + cached_state = NULL; cond_resched(); start = end + 1; } @@ -919,17 +990,17 @@ static int btrfs_write_and_wait_marked_extents(struct btrfs_root *root, return 0; } -int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans, +static int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans, struct btrfs_root *root) { - if (!trans || !trans->transaction) { - struct inode *btree_inode; - btree_inode = root->fs_info->btree_inode; - return filemap_write_and_wait(btree_inode->i_mapping); - } - return btrfs_write_and_wait_marked_extents(root, + int ret; + + ret = btrfs_write_and_wait_marked_extents(root, &trans->transaction->dirty_pages, EXTENT_DIRTY); + clear_btree_io_tree(&trans->transaction->dirty_pages); + + return ret; } /* @@ -1652,6 +1723,28 @@ static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info) btrfs_wait_ordered_roots(fs_info, -1); } +static inline void +btrfs_wait_pending_ordered(struct btrfs_transaction *cur_trans, + struct btrfs_fs_info *fs_info) +{ + struct btrfs_ordered_extent *ordered; + + spin_lock(&fs_info->trans_lock); + while (!list_empty(&cur_trans->pending_ordered)) { + ordered = list_first_entry(&cur_trans->pending_ordered, + struct btrfs_ordered_extent, + trans_list); + list_del_init(&ordered->trans_list); + spin_unlock(&fs_info->trans_lock); + + wait_event(ordered->wait, test_bit(BTRFS_ORDERED_COMPLETE, + &ordered->flags)); + btrfs_put_ordered_extent(ordered); + spin_lock(&fs_info->trans_lock); + } + spin_unlock(&fs_info->trans_lock); +} + int btrfs_commit_transaction(struct btrfs_trans_handle *trans, struct btrfs_root *root) { @@ -1702,6 +1795,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, } spin_lock(&root->fs_info->trans_lock); + list_splice(&trans->ordered, &cur_trans->pending_ordered); if (cur_trans->state >= TRANS_STATE_COMMIT_START) { spin_unlock(&root->fs_info->trans_lock); atomic_inc(&cur_trans->use_count); @@ -1754,6 +1848,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans, btrfs_wait_delalloc_flush(root->fs_info); + btrfs_wait_pending_ordered(cur_trans, root->fs_info); + btrfs_scrub_pause(root); /* * Ok now we need to make sure to block out any other joins while we diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h index 75ebcfc..00ed29c 100644 --- a/fs/btrfs/transaction.h +++ b/fs/btrfs/transaction.h @@ -56,6 +56,7 @@ struct btrfs_transaction { wait_queue_head_t commit_wait; struct list_head pending_snapshots; struct list_head pending_chunks; + struct list_head pending_ordered; struct list_head switch_commits; struct btrfs_delayed_ref_root delayed_refs; int aborted; @@ -105,6 +106,7 @@ struct btrfs_trans_handle { */ struct btrfs_root *root; struct seq_list delayed_ref_elem; + struct list_head ordered; struct list_head qgroup_ref_list; struct list_head new_bgs; }; @@ -145,8 +147,6 @@ struct btrfs_trans_handle *btrfs_attach_transaction_barrier( struct btrfs_root *root); struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root); int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid); -int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans, - struct btrfs_root *root); void btrfs_add_dead_root(struct btrfs_root *root); int btrfs_defrag_root(struct btrfs_root *root); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 286213c..9a02da1 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -2599,12 +2599,14 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, index2 = root_log_ctx.log_transid % 2; if (atomic_read(&log_root_tree->log_commit[index2])) { blk_finish_plug(&plug); - btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark); + ret = btrfs_wait_marked_extents(log, &log->dirty_log_pages, + mark); + btrfs_wait_logged_extents(trans, log, log_transid); wait_log_commit(trans, log_root_tree, root_log_ctx.log_transid); - btrfs_free_logged_extents(log, log_transid); mutex_unlock(&log_root_tree->log_mutex); - ret = root_log_ctx.log_ret; + if (!ret) + ret = root_log_ctx.log_ret; goto out; } ASSERT(root_log_ctx.log_transid == log_root_tree->log_transid); @@ -2641,11 +2643,18 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans, mutex_unlock(&log_root_tree->log_mutex); goto out_wake_log_root; } - btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark); - btrfs_wait_marked_extents(log_root_tree, - &log_root_tree->dirty_log_pages, - EXTENT_NEW | EXTENT_DIRTY); - btrfs_wait_logged_extents(log, log_transid); + ret = btrfs_wait_marked_extents(log, &log->dirty_log_pages, mark); + if (!ret) + ret = btrfs_wait_marked_extents(log_root_tree, + &log_root_tree->dirty_log_pages, + EXTENT_NEW | EXTENT_DIRTY); + if (ret) { + btrfs_set_log_full_commit(root->fs_info, trans); + btrfs_free_logged_extents(log, log_transid); + mutex_unlock(&log_root_tree->log_mutex); + goto out_wake_log_root; + } + btrfs_wait_logged_extents(trans, log, log_transid); btrfs_set_super_log_root(root->fs_info->super_for_commit, log_root_tree->node->start); @@ -3626,6 +3635,12 @@ static int wait_ordered_extents(struct btrfs_trans_handle *trans, test_bit(BTRFS_ORDERED_IOERR, &ordered->flags))); if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)) { + /* + * Clear the AS_EIO/AS_ENOSPC flags from the inode's + * i_mapping flags, so that the next fsync won't get + * an outdated io error too. + */ + btrfs_inode_check_errors(inode); *ordered_io_error = true; break; } @@ -3766,7 +3781,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans, fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); - btrfs_set_token_file_extent_generation(leaf, fi, em->generation, + btrfs_set_token_file_extent_generation(leaf, fi, trans->transid, &token); if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) btrfs_set_token_file_extent_type(leaf, fi, @@ -3963,7 +3978,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans, mutex_lock(&BTRFS_I(inode)->log_mutex); - btrfs_get_logged_extents(inode, &logged_list); + btrfs_get_logged_extents(inode, &logged_list, start, end); /* * a brute force approach to making sure we get the most uptodate @@ -4089,6 +4104,21 @@ log_extents: btrfs_release_path(path); btrfs_release_path(dst_path); if (fast_search) { + /* + * Some ordered extents started by fsync might have completed + * before we collected the ordered extents in logged_list, which + * means they're gone, not in our logged_list nor in the inode's + * ordered tree. We want the application/user space to know an + * error happened while attempting to persist file data so that + * it can take proper action. If such error happened, we leave + * without writing to the log tree and the fsync must report the + * file data write error and not commit the current transaction. + */ + err = btrfs_inode_check_errors(inode); + if (err) { + ctx->io_err = err; + goto out_unlock; + } ret = btrfs_log_changed_extents(trans, root, inode, dst_path, &logged_list, ctx); if (ret) { diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index dcf2013..47b1946 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -29,6 +29,7 @@ #include "xattr.h" #include "disk-io.h" #include "props.h" +#include "locking.h" ssize_t __btrfs_getxattr(struct inode *inode, const char *name, @@ -91,7 +92,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans, struct inode *inode, const char *name, const void *value, size_t size, int flags) { - struct btrfs_dir_item *di; + struct btrfs_dir_item *di = NULL; struct btrfs_root *root = BTRFS_I(inode)->root; struct btrfs_path *path; size_t name_len = strlen(name); @@ -103,84 +104,119 @@ static int do_setxattr(struct btrfs_trans_handle *trans, path = btrfs_alloc_path(); if (!path) return -ENOMEM; + path->skip_release_on_error = 1; + + if (!value) { + di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), + name, name_len, -1); + if (!di && (flags & XATTR_REPLACE)) + ret = -ENODATA; + else if (di) + ret = btrfs_delete_one_dir_name(trans, root, path, di); + goto out; + } + /* + * For a replace we can't just do the insert blindly. + * Do a lookup first (read-only btrfs_search_slot), and return if xattr + * doesn't exist. If it exists, fall down below to the insert/replace + * path - we can't race with a concurrent xattr delete, because the VFS + * locks the inode's i_mutex before calling setxattr or removexattr. + */ if (flags & XATTR_REPLACE) { - di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), name, - name_len, -1); - if (IS_ERR(di)) { - ret = PTR_ERR(di); - goto out; - } else if (!di) { + ASSERT(mutex_is_locked(&inode->i_mutex)); + di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode), + name, name_len, 0); + if (!di) { ret = -ENODATA; goto out; } - ret = btrfs_delete_one_dir_name(trans, root, path, di); - if (ret) - goto out; btrfs_release_path(path); + di = NULL; + } + ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode), + name, name_len, value, size); + if (ret == -EOVERFLOW) { /* - * remove the attribute + * We have an existing item in a leaf, split_leaf couldn't + * expand it. That item might have or not a dir_item that + * matches our target xattr, so lets check. */ - if (!value) - goto out; - } else { - di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode), - name, name_len, 0); - if (IS_ERR(di)) { - ret = PTR_ERR(di); + ret = 0; + btrfs_assert_tree_locked(path->nodes[0]); + di = btrfs_match_dir_item_name(root, path, name, name_len); + if (!di && !(flags & XATTR_REPLACE)) { + ret = -ENOSPC; goto out; } - if (!di && !value) - goto out; - btrfs_release_path(path); + } else if (ret == -EEXIST) { + ret = 0; + di = btrfs_match_dir_item_name(root, path, name, name_len); + ASSERT(di); /* logic error */ + } else if (ret) { + goto out; } -again: - ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode), - name, name_len, value, size); - /* - * If we're setting an xattr to a new value but the new value is say - * exactly BTRFS_MAX_XATTR_SIZE, we could end up with EOVERFLOW getting - * back from split_leaf. This is because it thinks we'll be extending - * the existing item size, but we're asking for enough space to add the - * item itself. So if we get EOVERFLOW just set ret to EEXIST and let - * the rest of the function figure it out. - */ - if (ret == -EOVERFLOW) + if (di && (flags & XATTR_CREATE)) { ret = -EEXIST; + goto out; + } - if (ret == -EEXIST) { - if (flags & XATTR_CREATE) - goto out; + if (di) { /* - * We can't use the path we already have since we won't have the - * proper locking for a delete, so release the path and - * re-lookup to delete the thing. + * We're doing a replace, and it must be atomic, that is, at + * any point in time we have either the old or the new xattr + * value in the tree. We don't want readers (getxattr and + * listxattrs) to miss a value, this is specially important + * for ACLs. */ - btrfs_release_path(path); - di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), - name, name_len, -1); - if (IS_ERR(di)) { - ret = PTR_ERR(di); - goto out; - } else if (!di) { - /* Shouldn't happen but just in case... */ - btrfs_release_path(path); - goto again; + const int slot = path->slots[0]; + struct extent_buffer *leaf = path->nodes[0]; + const u16 old_data_len = btrfs_dir_data_len(leaf, di); + const u32 item_size = btrfs_item_size_nr(leaf, slot); + const u32 data_size = sizeof(*di) + name_len + size; + struct btrfs_item *item; + unsigned long data_ptr; + char *ptr; + + if (size > old_data_len) { + if (btrfs_leaf_free_space(root, leaf) < + (size - old_data_len)) { + ret = -ENOSPC; + goto out; + } } - ret = btrfs_delete_one_dir_name(trans, root, path, di); - if (ret) - goto out; + if (old_data_len + name_len + sizeof(*di) == item_size) { + /* No other xattrs packed in the same leaf item. */ + if (size > old_data_len) + btrfs_extend_item(root, path, + size - old_data_len); + else if (size < old_data_len) + btrfs_truncate_item(root, path, data_size, 1); + } else { + /* There are other xattrs packed in the same item. */ + ret = btrfs_delete_one_dir_name(trans, root, path, di); + if (ret) + goto out; + btrfs_extend_item(root, path, data_size); + } + item = btrfs_item_nr(slot); + ptr = btrfs_item_ptr(leaf, slot, char); + ptr += btrfs_item_size(leaf, item) - data_size; + di = (struct btrfs_dir_item *)ptr; + btrfs_set_dir_data_len(leaf, di, size); + data_ptr = ((unsigned long)(di + 1)) + name_len; + write_extent_buffer(leaf, value, data_ptr, size); + btrfs_mark_buffer_dirty(leaf); + } else { /* - * We have a value to set, so go back and try to insert it now. + * Insert, and we had space for the xattr, so path->slots[0] is + * where our xattr dir_item is and btrfs_insert_xattr_item() + * filled it. */ - if (value) { - btrfs_release_path(path); - goto again; - } } out: btrfs_free_path(path); diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 659f2ea..cefca66 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -2638,7 +2638,7 @@ static void handle_cap_flush_ack(struct inode *inode, u64 flush_tid, for (i = 0; i < CEPH_CAP_BITS; i++) if ((dirty & (1 << i)) && - flush_tid == ci->i_cap_flush_tid[i]) + (u16)flush_tid == ci->i_cap_flush_tid[i]) cleaned |= 1 << i; dout("handle_cap_flush_ack inode %p mds%d seq %d on %s cleaned %s," diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 5228f20..4f46f7a 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -378,7 +378,7 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync) loff_t offset = header->args.offset; size_t count = header->args.count; struct page **pages = header->args.pages; - int pg_index = pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT; + int pg_index = header->args.pgbase >> PAGE_CACHE_SHIFT; unsigned int pg_len; struct blk_plug plug; int i; diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c index e966c02..acbf9ca 100644 --- a/fs/nfs/blocklayout/rpc_pipefs.c +++ b/fs/nfs/blocklayout/rpc_pipefs.c @@ -65,17 +65,18 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b, dprintk("%s CREATING PIPEFS MESSAGE\n", __func__); + mutex_lock(&nn->bl_mutex); bl_pipe_msg.bl_wq = &nn->bl_wq; b->simple.len += 4; /* single volume */ if (b->simple.len > PAGE_SIZE) - return -EIO; + goto out_unlock; memset(msg, 0, sizeof(*msg)); msg->len = sizeof(*bl_msg) + b->simple.len; msg->data = kzalloc(msg->len, gfp_mask); if (!msg->data) - goto out; + goto out_free_data; bl_msg = msg->data; bl_msg->type = BL_DEVICE_MOUNT, @@ -87,7 +88,7 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b, rc = rpc_queue_upcall(nn->bl_device_pipe, msg); if (rc < 0) { remove_wait_queue(&nn->bl_wq, &wq); - goto out; + goto out_free_data; } set_current_state(TASK_UNINTERRUPTIBLE); @@ -97,12 +98,14 @@ bl_resolve_deviceid(struct nfs_server *server, struct pnfs_block_volume *b, if (reply->status != BL_DEVICE_REQUEST_PROC) { printk(KERN_WARNING "%s failed to decode device: %d\n", __func__, reply->status); - goto out; + goto out_free_data; } dev = MKDEV(reply->major, reply->minor); -out: +out_free_data: kfree(msg->data); +out_unlock: + mutex_unlock(&nn->bl_mutex); return dev; } @@ -232,6 +235,7 @@ static int nfs4blocklayout_net_init(struct net *net) struct nfs_net *nn = net_generic(net, nfs_net_id); struct dentry *dentry; + mutex_init(&nn->bl_mutex); init_waitqueue_head(&nn->bl_wq); nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0); if (IS_ERR(nn->bl_device_pipe)) diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 5853f53..7f3f606 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -125,6 +125,8 @@ again: continue; if (!test_bit(NFS_DELEGATED_STATE, &state->flags)) continue; + if (!nfs4_valid_open_stateid(state)) + continue; if (!nfs4_stateid_match(&state->stateid, stateid)) continue; get_nfs_open_context(ctx); @@ -193,7 +195,11 @@ static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation * { int res = 0; - res = nfs4_proc_delegreturn(inode, delegation->cred, &delegation->stateid, issync); + if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) + res = nfs4_proc_delegreturn(inode, + delegation->cred, + &delegation->stateid, + issync); nfs_free_delegation(delegation); return res; } @@ -380,11 +386,13 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation { struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; struct nfs_inode *nfsi = NFS_I(inode); - int err; + int err = 0; if (delegation == NULL) return 0; do { + if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) + break; err = nfs_delegation_claim_opens(inode, &delegation->stateid); if (!issync || err != -EAGAIN) break; @@ -605,10 +613,23 @@ static void nfs_client_mark_return_unused_delegation_types(struct nfs_client *cl rcu_read_unlock(); } +static void nfs_revoke_delegation(struct inode *inode) +{ + struct nfs_delegation *delegation; + rcu_read_lock(); + delegation = rcu_dereference(NFS_I(inode)->delegation); + if (delegation != NULL) { + set_bit(NFS_DELEGATION_REVOKED, &delegation->flags); + nfs_mark_return_delegation(NFS_SERVER(inode), delegation); + } + rcu_read_unlock(); +} + void nfs_remove_bad_delegation(struct inode *inode) { struct nfs_delegation *delegation; + nfs_revoke_delegation(inode); delegation = nfs_inode_detach_delegation(inode); if (delegation) { nfs_inode_find_state_and_recover(inode, &delegation->stateid); diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index 5c1cce3..e3c20a3 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -31,6 +31,7 @@ enum { NFS_DELEGATION_RETURN_IF_CLOSED, NFS_DELEGATION_REFERENCED, NFS_DELEGATION_RETURNING, + NFS_DELEGATION_REVOKED, }; int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res); diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 06e8cfc..6e62155 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1527,6 +1527,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry, case -ENOENT: d_drop(dentry); d_add(dentry, NULL); + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); break; case -EISDIR: case -ENOTDIR: diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 20cffc8..10bf072 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -266,6 +266,7 @@ static void nfs_direct_req_free(struct kref *kref) { struct nfs_direct_req *dreq = container_of(kref, struct nfs_direct_req, kref); + nfs_free_pnfs_ds_cinfo(&dreq->ds_cinfo); if (dreq->l_ctx != NULL) nfs_put_lock_context(dreq->l_ctx); if (dreq->ctx != NULL) diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c index 46fab1cb..7afb52f 100644 --- a/fs/nfs/filelayout/filelayout.c +++ b/fs/nfs/filelayout/filelayout.c @@ -145,9 +145,6 @@ static int filelayout_async_handle_error(struct rpc_task *task, case -NFS4ERR_DELEG_REVOKED: case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_BAD_STATEID: - if (state == NULL) - break; - nfs_remove_bad_delegation(state->inode); case -NFS4ERR_OPENMODE: if (state == NULL) break; diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 6388a59..00689a8 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -626,7 +626,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) { struct inode *inode = dentry->d_inode; int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME; - int err; + int err = 0; trace_nfs_getattr_enter(inode); /* Flush out writes to the server in order to update c/mtime. */ diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h index ef221fb..f0e06e4 100644 --- a/fs/nfs/netns.h +++ b/fs/nfs/netns.h @@ -19,6 +19,7 @@ struct nfs_net { struct rpc_pipe *bl_device_pipe; struct bl_dev_msg bl_mount_reply; wait_queue_head_t bl_wq; + struct mutex bl_mutex; struct list_head nfs_client_list; struct list_head nfs_volume_list; #if IS_ENABLED(CONFIG_NFS_V4) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 405bd95..69dc20a 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -370,11 +370,6 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc case -NFS4ERR_DELEG_REVOKED: case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_BAD_STATEID: - if (inode != NULL && nfs4_have_delegation(inode, FMODE_READ)) { - nfs_remove_bad_delegation(inode); - exception->retry = 1; - break; - } if (state == NULL) break; ret = nfs4_schedule_stateid_recovery(server, state); @@ -1654,7 +1649,7 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct nfs_inode_find_state_and_recover(state->inode, stateid); nfs4_schedule_stateid_recovery(server, state); - return 0; + return -EAGAIN; case -NFS4ERR_DELAY: case -NFS4ERR_GRACE: set_bit(NFS_DELEGATED_STATE, &state->flags); @@ -2109,46 +2104,60 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta return ret; } +static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state) +{ + nfs_remove_bad_delegation(state->inode); + write_seqlock(&state->seqlock); + nfs4_stateid_copy(&state->stateid, &state->open_stateid); + write_sequnlock(&state->seqlock); + clear_bit(NFS_DELEGATED_STATE, &state->flags); +} + +static void nfs40_clear_delegation_stateid(struct nfs4_state *state) +{ + if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL) + nfs_finish_clear_delegation_stateid(state); +} + +static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state) +{ + /* NFSv4.0 doesn't allow for delegation recovery on open expire */ + nfs40_clear_delegation_stateid(state); + return nfs4_open_expired(sp, state); +} + #if defined(CONFIG_NFS_V4_1) -static void nfs41_clear_delegation_stateid(struct nfs4_state *state) +static void nfs41_check_delegation_stateid(struct nfs4_state *state) { struct nfs_server *server = NFS_SERVER(state->inode); - nfs4_stateid *stateid = &state->stateid; + nfs4_stateid stateid; struct nfs_delegation *delegation; - struct rpc_cred *cred = NULL; - int status = -NFS4ERR_BAD_STATEID; - - /* If a state reset has been done, test_stateid is unneeded */ - if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) - return; + struct rpc_cred *cred; + int status; /* Get the delegation credential for use by test/free_stateid */ rcu_read_lock(); delegation = rcu_dereference(NFS_I(state->inode)->delegation); - if (delegation != NULL && - nfs4_stateid_match(&delegation->stateid, stateid)) { - cred = get_rpccred(delegation->cred); - rcu_read_unlock(); - status = nfs41_test_stateid(server, stateid, cred); - trace_nfs4_test_delegation_stateid(state, NULL, status); - } else + if (delegation == NULL) { rcu_read_unlock(); + return; + } + + nfs4_stateid_copy(&stateid, &delegation->stateid); + cred = get_rpccred(delegation->cred); + rcu_read_unlock(); + status = nfs41_test_stateid(server, &stateid, cred); + trace_nfs4_test_delegation_stateid(state, NULL, status); if (status != NFS_OK) { /* Free the stateid unless the server explicitly * informs us the stateid is unrecognized. */ if (status != -NFS4ERR_BAD_STATEID) - nfs41_free_stateid(server, stateid, cred); - nfs_remove_bad_delegation(state->inode); - - write_seqlock(&state->seqlock); - nfs4_stateid_copy(&state->stateid, &state->open_stateid); - write_sequnlock(&state->seqlock); - clear_bit(NFS_DELEGATED_STATE, &state->flags); + nfs41_free_stateid(server, &stateid, cred); + nfs_finish_clear_delegation_stateid(state); } - if (cred != NULL) - put_rpccred(cred); + put_rpccred(cred); } /** @@ -2192,7 +2201,7 @@ static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *st { int status; - nfs41_clear_delegation_stateid(state); + nfs41_check_delegation_stateid(state); status = nfs41_check_open_stateid(state); if (status != NFS_OK) status = nfs4_open_expired(sp, state); @@ -2231,19 +2240,8 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata, seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); ret = _nfs4_proc_open(opendata); - if (ret != 0) { - if (ret == -ENOENT) { - dentry = opendata->dentry; - if (dentry->d_inode) - d_delete(dentry); - else if (d_unhashed(dentry)) - d_add(dentry, NULL); - - nfs_set_verifier(dentry, - nfs_save_change_attribute(opendata->dir->d_inode)); - } + if (ret != 0) goto out; - } state = nfs4_opendata_to_nfs4_state(opendata); ret = PTR_ERR(state); @@ -4841,9 +4839,6 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, case -NFS4ERR_DELEG_REVOKED: case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_BAD_STATEID: - if (state == NULL) - break; - nfs_remove_bad_delegation(state->inode); case -NFS4ERR_OPENMODE: if (state == NULL) break; @@ -8341,7 +8336,7 @@ static const struct nfs4_state_recovery_ops nfs41_reboot_recovery_ops = { static const struct nfs4_state_recovery_ops nfs40_nograce_recovery_ops = { .owner_flag_bit = NFS_OWNER_RECLAIM_NOGRACE, .state_flag_bit = NFS_STATE_RECLAIM_NOGRACE, - .recover_open = nfs4_open_expired, + .recover_open = nfs40_open_expired, .recover_lock = nfs4_lock_expired, .establish_clid = nfs4_init_clientid, }; @@ -8408,8 +8403,7 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = { | NFS_CAP_CHANGE_ATTR | NFS_CAP_POSIX_LOCK | NFS_CAP_STATEID_NFSV41 - | NFS_CAP_ATOMIC_OPEN_V1 - | NFS_CAP_SEEK, + | NFS_CAP_ATOMIC_OPEN_V1, .init_client = nfs41_init_client, .shutdown_client = nfs41_shutdown_client, .match_stateid = nfs41_match_stateid, @@ -8431,7 +8425,8 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = { | NFS_CAP_CHANGE_ATTR | NFS_CAP_POSIX_LOCK | NFS_CAP_STATEID_NFSV41 - | NFS_CAP_ATOMIC_OPEN_V1, + | NFS_CAP_ATOMIC_OPEN_V1 + | NFS_CAP_SEEK, .init_client = nfs41_init_client, .shutdown_client = nfs41_shutdown_client, .match_stateid = nfs41_match_stateid, diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 1249384..f83b02d 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -715,8 +715,6 @@ static void nfs_inode_remove_request(struct nfs_page *req) if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) nfs_release_request(req); - else - WARN_ON_ONCE(1); } static void diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 9d3e9c5..89326ac 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -229,8 +229,16 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, &fsnotify_mark_srcu); } + /* + * We need to merge inode & vfsmount mark lists so that inode mark + * ignore masks are properly reflected for mount mark notifications. + * That's why this traversal is so complicated... + */ while (inode_node || vfsmount_node) { - inode_group = vfsmount_group = NULL; + inode_group = NULL; + inode_mark = NULL; + vfsmount_group = NULL; + vfsmount_mark = NULL; if (inode_node) { inode_mark = hlist_entry(srcu_dereference(inode_node, &fsnotify_mark_srcu), @@ -244,21 +252,19 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, vfsmount_group = vfsmount_mark->group; } - if (inode_group > vfsmount_group) { - /* handle inode */ - ret = send_to_group(to_tell, inode_mark, NULL, mask, - data, data_is, cookie, file_name); - /* we didn't use the vfsmount_mark */ - vfsmount_group = NULL; - } else if (vfsmount_group > inode_group) { - ret = send_to_group(to_tell, NULL, vfsmount_mark, mask, - data, data_is, cookie, file_name); - inode_group = NULL; - } else { - ret = send_to_group(to_tell, inode_mark, vfsmount_mark, - mask, data, data_is, cookie, - file_name); + if (inode_group && vfsmount_group) { + int cmp = fsnotify_compare_groups(inode_group, + vfsmount_group); + if (cmp > 0) { + inode_group = NULL; + inode_mark = NULL; + } else if (cmp < 0) { + vfsmount_group = NULL; + vfsmount_mark = NULL; + } } + ret = send_to_group(to_tell, inode_mark, vfsmount_mark, mask, + data, data_is, cookie, file_name); if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS)) goto out; diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h index 9c0898c..3b68b0a 100644 --- a/fs/notify/fsnotify.h +++ b/fs/notify/fsnotify.h @@ -12,6 +12,10 @@ extern void fsnotify_flush_notify(struct fsnotify_group *group); /* protects reads of inode and vfsmount marks list */ extern struct srcu_struct fsnotify_mark_srcu; +/* compare two groups for sorting of marks lists */ +extern int fsnotify_compare_groups(struct fsnotify_group *a, + struct fsnotify_group *b); + extern void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *fsn_mark, __u32 mask); /* add a mark to an inode */ diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c index e849714..dfbf544 100644 --- a/fs/notify/inode_mark.c +++ b/fs/notify/inode_mark.c @@ -194,6 +194,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark, { struct fsnotify_mark *lmark, *last = NULL; int ret = 0; + int cmp; mark->flags |= FSNOTIFY_MARK_FLAG_INODE; @@ -219,11 +220,8 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark, goto out; } - if (mark->group->priority < lmark->group->priority) - continue; - - if ((mark->group->priority == lmark->group->priority) && - (mark->group < lmark->group)) + cmp = fsnotify_compare_groups(lmark->group, mark->group); + if (cmp < 0) continue; hlist_add_before_rcu(&mark->i.i_list, &lmark->i.i_list); diff --git a/fs/notify/mark.c b/fs/notify/mark.c index d90deaa..34c38fa 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -210,6 +210,42 @@ void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mas } /* + * Sorting function for lists of fsnotify marks. + * + * Fanotify supports different notification classes (reflected as priority of + * notification group). Events shall be passed to notification groups in + * decreasing priority order. To achieve this marks in notification lists for + * inodes and vfsmounts are sorted so that priorities of corresponding groups + * are descending. + * + * Furthermore correct handling of the ignore mask requires processing inode + * and vfsmount marks of each group together. Using the group address as + * further sort criterion provides a unique sorting order and thus we can + * merge inode and vfsmount lists of marks in linear time and find groups + * present in both lists. + * + * A return value of 1 signifies that b has priority over a. + * A return value of 0 signifies that the two marks have to be handled together. + * A return value of -1 signifies that a has priority over b. + */ +int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b) +{ + if (a == b) + return 0; + if (!a) + return 1; + if (!b) + return -1; + if (a->priority < b->priority) + return 1; + if (a->priority > b->priority) + return -1; + if (a < b) + return 1; + return -1; +} + +/* * Attach an initialized mark to a given group and fs object. * These marks may be used for the fsnotify backend to determine which * event types should be delivered to which group. diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c index ac851e8..faefa72 100644 --- a/fs/notify/vfsmount_mark.c +++ b/fs/notify/vfsmount_mark.c @@ -153,6 +153,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark, struct mount *m = real_mount(mnt); struct fsnotify_mark *lmark, *last = NULL; int ret = 0; + int cmp; mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT; @@ -178,11 +179,8 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark, goto out; } - if (mark->group->priority < lmark->group->priority) - continue; - - if ((mark->group->priority == lmark->group->priority) && - (mark->group < lmark->group)) + cmp = fsnotify_compare_groups(lmark->group, mark->group); + if (cmp < 0) continue; hlist_add_before_rcu(&mark->m.m_list, &lmark->m.m_list); |
