diff options
Diffstat (limited to 'fs')
91 files changed, 947 insertions, 792 deletions
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c index 1feb68ecef95..842d00048a65 100644 --- a/fs/autofs4/expire.c +++ b/fs/autofs4/expire.c @@ -94,25 +94,21 @@ static struct dentry *get_next_positive_subdir(struct dentry *prev, { struct autofs_sb_info *sbi = autofs4_sbi(root->d_sb); struct list_head *next; - struct dentry *p, *q; + struct dentry *q; spin_lock(&sbi->lookup_lock); + spin_lock(&root->d_lock); - if (prev == NULL) { - spin_lock(&root->d_lock); + if (prev) + next = prev->d_u.d_child.next; + else { prev = dget_dlock(root); next = prev->d_subdirs.next; - p = prev; - goto start; } - p = prev; - spin_lock(&p->d_lock); -again: - next = p->d_u.d_child.next; -start: +cont: if (next == &root->d_subdirs) { - spin_unlock(&p->d_lock); + spin_unlock(&root->d_lock); spin_unlock(&sbi->lookup_lock); dput(prev); return NULL; @@ -121,16 +117,15 @@ start: q = list_entry(next, struct dentry, d_u.d_child); spin_lock_nested(&q->d_lock, DENTRY_D_LOCK_NESTED); - /* Negative dentry - try next */ - if (!simple_positive(q)) { - spin_unlock(&p->d_lock); - lock_set_subclass(&q->d_lock.dep_map, 0, _RET_IP_); - p = q; - goto again; + /* Already gone or negative dentry (under construction) - try next */ + if (q->d_count == 0 || !simple_positive(q)) { + spin_unlock(&q->d_lock); + next = q->d_u.d_child.next; + goto cont; } dget_dlock(q); spin_unlock(&q->d_lock); - spin_unlock(&p->d_lock); + spin_unlock(&root->d_lock); spin_unlock(&sbi->lookup_lock); dput(prev); @@ -404,11 +399,6 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb, DPRINTK("checking mountpoint %p %.*s", dentry, (int)dentry->d_name.len, dentry->d_name.name); - /* Path walk currently on this dentry? */ - ino_count = atomic_read(&ino->count) + 2; - if (dentry->d_count > ino_count) - goto next; - /* Can we umount this guy */ if (autofs4_mount_busy(mnt, dentry)) goto next; @@ -73,7 +73,7 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size) { unsigned int sz = sizeof(struct bio) + extra_size; struct kmem_cache *slab = NULL; - struct bio_slab *bslab; + struct bio_slab *bslab, *new_bio_slabs; unsigned int i, entry = -1; mutex_lock(&bio_slab_lock); @@ -97,11 +97,12 @@ static struct kmem_cache *bio_find_or_create_slab(unsigned int extra_size) if (bio_slab_nr == bio_slab_max && entry == -1) { bio_slab_max <<= 1; - bio_slabs = krealloc(bio_slabs, - bio_slab_max * sizeof(struct bio_slab), - GFP_KERNEL); - if (!bio_slabs) + new_bio_slabs = krealloc(bio_slabs, + bio_slab_max * sizeof(struct bio_slab), + GFP_KERNEL); + if (!new_bio_slabs) goto out_unlock; + bio_slabs = new_bio_slabs; } if (entry == -1) entry = bio_slab_nr++; @@ -1312,7 +1313,7 @@ EXPORT_SYMBOL(bio_copy_kern); * Note that this code is very hard to test under normal circumstances because * direct-io pins the pages with get_user_pages(). This makes * is_page_cache_freeable return false, and the VM will not clean the pages. - * But other code (eg, pdflush) could clean the pages if they are mapped + * But other code (eg, flusher threads) could clean the pages if they are mapped * pagecache. * * Simply disabling the call to bio_set_pages_dirty() is a good way to test the diff --git a/fs/block_dev.c b/fs/block_dev.c index 1e519195d45b..38e721b35d45 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1578,10 +1578,12 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; + struct blk_plug plug; ssize_t ret; BUG_ON(iocb->ki_pos != pos); + blk_start_plug(&plug); ret = __generic_file_aio_write(iocb, iov, nr_segs, &iocb->ki_pos); if (ret > 0 || ret == -EIOCBQUEUED) { ssize_t err; @@ -1590,6 +1592,7 @@ ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, if (err < 0 && ret > 0) ret = err; } + blk_finish_plug(&plug); return ret; } EXPORT_SYMBOL_GPL(blkdev_aio_write); diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index a256f3b2a845..ff6475f409d6 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1438,10 +1438,10 @@ int iterate_inodes_from_logical(u64 logical, struct btrfs_fs_info *fs_info, ret = extent_from_logical(fs_info, logical, path, &found_key); btrfs_release_path(path); - if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK) - ret = -EINVAL; if (ret < 0) return ret; + if (ret & BTRFS_EXTENT_FLAG_TREE_BLOCK) + return -EINVAL; extent_item_pos = logical - found_key.objectid; ret = iterate_extent_inodes(fs_info, found_key.objectid, diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 86eff48dab78..43d1c5a3a030 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -818,6 +818,7 @@ static void free_workspace(int type, struct list_head *workspace) btrfs_compress_op[idx]->free_workspace(workspace); atomic_dec(alloc_workspace); wake: + smp_mb(); if (waitqueue_active(workspace_wait)) wake_up(workspace_wait); } diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index 9d7621f271ff..6d183f60d63a 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -421,12 +421,6 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info, spin_unlock(&fs_info->tree_mod_seq_lock); /* - * we removed the lowest blocker from the blocker list, so there may be - * more processible delayed refs. - */ - wake_up(&fs_info->tree_mod_seq_wait); - - /* * anything that's lower than the lowest existing (read: blocked) * sequence number can be removed from the tree. */ @@ -631,6 +625,9 @@ __tree_mod_log_free_eb(struct btrfs_fs_info *fs_info, struct extent_buffer *eb) u32 nritems; int ret; + if (btrfs_header_level(eb) == 0) + return; + nritems = btrfs_header_nritems(eb); for (i = nritems - 1; i >= 0; i--) { ret = tree_mod_log_insert_key_locked(fs_info, eb, i, diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 4bab807227ad..0d195b507660 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1252,7 +1252,6 @@ struct btrfs_fs_info { atomic_t tree_mod_seq; struct list_head tree_mod_seq_list; struct seq_list tree_mod_seq_elem; - wait_queue_head_t tree_mod_seq_wait; /* this protects tree_mod_log */ rwlock_t tree_mod_log_lock; @@ -3192,7 +3191,7 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans, int btrfs_lookup_bio_sums(struct btrfs_root *root, struct inode *inode, struct bio *bio, u32 *dst); int btrfs_lookup_bio_sums_dio(struct btrfs_root *root, struct inode *inode, - struct bio *bio, u64 logical_offset, u32 *dst); + struct bio *bio, u64 logical_offset); int btrfs_insert_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 objectid, u64 pos, diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 335605c8ceab..07d5eeb1e6f1 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -512,8 +512,8 @@ static void __btrfs_remove_delayed_item(struct btrfs_delayed_item *delayed_item) rb_erase(&delayed_item->rb_node, root); delayed_item->delayed_node->count--; - atomic_dec(&delayed_root->items); - if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND && + if (atomic_dec_return(&delayed_root->items) < + BTRFS_DELAYED_BACKGROUND && waitqueue_active(&delayed_root->wait)) wake_up(&delayed_root->wait); } @@ -1028,9 +1028,10 @@ do_again: btrfs_release_delayed_item(prev); ret = 0; btrfs_release_path(path); - if (curr) + if (curr) { + mutex_unlock(&node->mutex); goto do_again; - else + } else goto delete_fail; } @@ -1055,8 +1056,7 @@ static void btrfs_release_delayed_inode(struct btrfs_delayed_node *delayed_node) delayed_node->count--; delayed_root = delayed_node->root->fs_info->delayed_root; - atomic_dec(&delayed_root->items); - if (atomic_read(&delayed_root->items) < + if (atomic_dec_return(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND && waitqueue_active(&delayed_root->wait)) wake_up(&delayed_root->wait); diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c index da7419ed01bb..ae9411773397 100644 --- a/fs/btrfs/delayed-ref.c +++ b/fs/btrfs/delayed-ref.c @@ -38,17 +38,14 @@ static int comp_tree_refs(struct btrfs_delayed_tree_ref *ref2, struct btrfs_delayed_tree_ref *ref1) { - if (ref1->node.type == BTRFS_TREE_BLOCK_REF_KEY) { - if (ref1->root < ref2->root) - return -1; - if (ref1->root > ref2->root) - return 1; - } else { - if (ref1->parent < ref2->parent) - return -1; - if (ref1->parent > ref2->parent) - return 1; - } + if (ref1->root < ref2->root) + return -1; + if (ref1->root > ref2->root) + return 1; + if (ref1->parent < ref2->parent) + return -1; + if (ref1->parent > ref2->parent) + return 1; return 0; } @@ -85,7 +82,8 @@ static int comp_data_refs(struct btrfs_delayed_data_ref *ref2, * type of the delayed backrefs and content of delayed backrefs. */ static int comp_entry(struct btrfs_delayed_ref_node *ref2, - struct btrfs_delayed_ref_node *ref1) + struct btrfs_delayed_ref_node *ref1, + bool compare_seq) { if (ref1->bytenr < ref2->bytenr) return -1; @@ -102,10 +100,12 @@ static int comp_entry(struct btrfs_delayed_ref_node *ref2, if (ref1->type > ref2->type) return 1; /* merging of sequenced refs is not allowed */ - if (ref1->seq < ref2->seq) - return -1; - if (ref1->seq > ref2->seq) - return 1; + if (compare_seq) { + if (ref1->seq < ref2->seq) + return -1; + if (ref1->seq > ref2->seq) + return 1; + } if (ref1->type == BTRFS_TREE_BLOCK_REF_KEY || ref1->type == BTRFS_SHARED_BLOCK_REF_KEY) { return comp_tree_refs(btrfs_delayed_node_to_tree_ref(ref2), @@ -139,7 +139,7 @@ static struct btrfs_delayed_ref_node *tree_insert(struct rb_root *root, entry = rb_entry(parent_node, struct btrfs_delayed_ref_node, rb_node); - cmp = comp_entry(entry, ins); + cmp = comp_entry(entry, ins, 1); if (cmp < 0) p = &(*p)->rb_left; else if (cmp > 0) @@ -233,6 +233,114 @@ int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans, return 0; } +static void inline drop_delayed_ref(struct btrfs_trans_handle *trans, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_delayed_ref_node *ref) +{ + rb_erase(&ref->rb_node, &delayed_refs->root); + ref->in_tree = 0; + btrfs_put_delayed_ref(ref); + delayed_refs->num_entries--; + if (trans->delayed_ref_updates) + trans->delayed_ref_updates--; +} + +static int merge_ref(struct btrfs_trans_handle *trans, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_delayed_ref_node *ref, u64 seq) +{ + struct rb_node *node; + int merged = 0; + int mod = 0; + int done = 0; + + node = rb_prev(&ref->rb_node); + while (node) { + struct btrfs_delayed_ref_node *next; + + next = rb_entry(node, struct btrfs_delayed_ref_node, rb_node); + node = rb_prev(node); + if (next->bytenr != ref->bytenr) + break; + if (seq && next->seq >= seq) + break; + if (comp_entry(ref, next, 0)) + continue; + + if (ref->action == next->action) { + mod = next->ref_mod; + } else { + if (ref->ref_mod < next->ref_mod) { + struct btrfs_delayed_ref_node *tmp; + + tmp = ref; + ref = next; + next = tmp; + done = 1; + } + mod = -next->ref_mod; + } + + merged++; + drop_delayed_ref(trans, delayed_refs, next); + ref->ref_mod += mod; + if (ref->ref_mod == 0) { + drop_delayed_ref(trans, delayed_refs, ref); + break; + } else { + /* + * You can't have multiples of the same ref on a tree + * block. + */ + WARN_ON(ref->type == BTRFS_TREE_BLOCK_REF_KEY || + ref->type == BTRFS_SHARED_BLOCK_REF_KEY); + } + + if (done) + break; + node = rb_prev(&ref->rb_node); + } + + return merged; +} + +void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_delayed_ref_head *head) +{ + struct rb_node *node; + u64 seq = 0; + + spin_lock(&fs_info->tree_mod_seq_lock); + if (!list_empty(&fs_info->tree_mod_seq_list)) { + struct seq_list *elem; + + elem = list_first_entry(&fs_info->tree_mod_seq_list, + struct seq_list, list); + seq = elem->seq; + } + spin_unlock(&fs_info->tree_mod_seq_lock); + + node = rb_prev(&head->node.rb_node); + while (node) { + struct btrfs_delayed_ref_node *ref; + + ref = rb_entry(node, struct btrfs_delayed_ref_node, + rb_node); + if (ref->bytenr != head->node.bytenr) + break; + + /* We can't merge refs that are outside of our seq count */ + if (seq && ref->seq >= seq) + break; + if (merge_ref(trans, delayed_refs, ref, seq)) + node = rb_prev(&head->node.rb_node); + else + node = rb_prev(node); + } +} + int btrfs_check_delayed_seq(struct btrfs_fs_info *fs_info, struct btrfs_delayed_ref_root *delayed_refs, u64 seq) @@ -336,18 +444,11 @@ update_existing_ref(struct btrfs_trans_handle *trans, * every changing the extent allocation tree. */ existing->ref_mod--; - if (existing->ref_mod == 0) { - rb_erase(&existing->rb_node, - &delayed_refs->root); - existing->in_tree = 0; - btrfs_put_delayed_ref(existing); - delayed_refs->num_entries--; - if (trans->delayed_ref_updates) - trans->delayed_ref_updates--; - } else { + if (existing->ref_mod == 0) + drop_delayed_ref(trans, delayed_refs, existing); + else WARN_ON(existing->type == BTRFS_TREE_BLOCK_REF_KEY || existing->type == BTRFS_SHARED_BLOCK_REF_KEY); - } } else { WARN_ON(existing->type == BTRFS_TREE_BLOCK_REF_KEY || existing->type == BTRFS_SHARED_BLOCK_REF_KEY); @@ -662,9 +763,6 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info, add_delayed_tree_ref(fs_info, trans, &ref->node, bytenr, num_bytes, parent, ref_root, level, action, for_cow); - if (!need_ref_seq(for_cow, ref_root) && - waitqueue_active(&fs_info->tree_mod_seq_wait)) - wake_up(&fs_info->tree_mod_seq_wait); spin_unlock(&delayed_refs->lock); if (need_ref_seq(for_cow, ref_root)) btrfs_qgroup_record_ref(trans, &ref->node, extent_op); @@ -713,9 +811,6 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info, add_delayed_data_ref(fs_info, trans, &ref->node, bytenr, num_bytes, parent, ref_root, owner, offset, action, for_cow); - if (!need_ref_seq(for_cow, ref_root) && - waitqueue_active(&fs_info->tree_mod_seq_wait)) - wake_up(&fs_info->tree_mod_seq_wait); spin_unlock(&delayed_refs->lock); if (need_ref_seq(for_cow, ref_root)) btrfs_qgroup_record_ref(trans, &ref->node, extent_op); @@ -744,8 +839,6 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, num_bytes, BTRFS_UPDATE_DELAYED_HEAD, extent_op->is_data); - if (waitqueue_active(&fs_info->tree_mod_seq_wait)) - wake_up(&fs_info->tree_mod_seq_wait); spin_unlock(&delayed_refs->lock); return 0; } diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 0d7c90c366b6..ab5300595847 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -167,6 +167,10 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, struct btrfs_delayed_extent_op *extent_op); +void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans, + struct btrfs_fs_info *fs_info, + struct btrfs_delayed_ref_root *delayed_refs, + struct btrfs_delayed_ref_head *head); struct btrfs_delayed_ref_head * btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 62e0cafd6e25..22e98e04c2ea 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -377,9 +377,13 @@ static int btree_read_extent_buffer_pages(struct btrfs_root *root, ret = read_extent_buffer_pages(io_tree, eb, start, WAIT_COMPLETE, btree_get_extent, mirror_num); - if (!ret && !verify_parent_transid(io_tree, eb, + if (!ret) { + if (!verify_parent_transid(io_tree, eb, parent_transid, 0)) - break; + break; + else + ret = -EIO; + } /* * This buffer's crc is fine, but its contents are corrupted, so @@ -754,9 +758,7 @@ static void run_one_async_done(struct btrfs_work *work) limit = btrfs_async_submit_limit(fs_info); limit = limit * 2 / 3; - atomic_dec(&fs_info->nr_async_submits); - - if (atomic_read(&fs_info->nr_async_submits) < limit && + if (atomic_dec_return(&fs_info->nr_async_submits) < limit && waitqueue_active(&fs_info->async_submit_wait)) wake_up(&fs_info->async_submit_wait); @@ -2032,8 +2034,6 @@ int open_ctree(struct super_block *sb, fs_info->free_chunk_space = 0; fs_info->tree_mod_log = RB_ROOT; - init_waitqueue_head(&fs_info->tree_mod_seq_wait); - /* readahead state */ INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT); spin_lock_init(&fs_info->reada_lock); @@ -2528,8 +2528,7 @@ retry_root_backup: goto fail_trans_kthread; /* do not make disk changes in broken FS */ - if (btrfs_super_log_root(disk_super) != 0 && - !(fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)) { + if (btrfs_super_log_root(disk_super) != 0) { u64 bytenr = btrfs_super_log_root(disk_super); if (fs_devices->rw_devices == 0) { @@ -3189,30 +3188,14 @@ int close_ctree(struct btrfs_root *root) /* clear out the rbtree of defraggable inodes */ btrfs_run_defrag_inodes(fs_info); - /* - * Here come 2 situations when btrfs is broken to flip readonly: - * - * 1. when btrfs flips readonly somewhere else before - * btrfs_commit_super, sb->s_flags has MS_RDONLY flag, - * and btrfs will skip to write sb directly to keep - * ERROR state on disk. - * - * 2. when btrfs flips readonly just in btrfs_commit_super, - * and in such case, btrfs cannot write sb via btrfs_commit_super, - * and since fs_state has been set BTRFS_SUPER_FLAG_ERROR flag, - * btrfs will cleanup all FS resources first and write sb then. - */ if (!(fs_info->sb->s_flags & MS_RDONLY)) { ret = btrfs_commit_super(root); if (ret) printk(KERN_ERR "btrfs: commit super ret %d\n", ret); } - if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) { - ret = btrfs_error_commit_super(root); - if (ret) - printk(KERN_ERR "btrfs: commit super ret %d\n", ret); - } + if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) + btrfs_error_commit_super(root); btrfs_put_block_group_cache(fs_info); @@ -3434,18 +3417,11 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info, if (read_only) return 0; - if (fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR) { - printk(KERN_WARNING "warning: mount fs with errors, " - "running btrfsck is recommended\n"); - } - return 0; } -int btrfs_error_commit_super(struct btrfs_root *root) +void btrfs_error_commit_super(struct btrfs_root *root) { - int ret; - mutex_lock(&root->fs_info->cleaner_mutex); btrfs_run_delayed_iputs(root); mutex_unlock(&root->fs_info->cleaner_mutex); @@ -3455,10 +3431,6 @@ int btrfs_error_commit_super(struct btrfs_root *root) /* cleanup FS via transaction */ btrfs_cleanup_transaction(root); - - ret = write_ctree_super(NULL, root, 0); - - return ret; } static void btrfs_destroy_ordered_operations(struct btrfs_root *root) @@ -3782,14 +3754,17 @@ int btrfs_cleanup_transaction(struct btrfs_root *root) /* FIXME: cleanup wait for commit */ t->in_commit = 1; t->blocked = 1; + smp_mb(); if (waitqueue_active(&root->fs_info->transaction_blocked_wait)) wake_up(&root->fs_info->transaction_blocked_wait); t->blocked = 0; + smp_mb(); if (waitqueue_active(&root->fs_info->transaction_wait)) wake_up(&root->fs_info->transaction_wait); t->commit_done = 1; + smp_mb(); if (waitqueue_active(&t->commit_wait)) wake_up(&t->commit_wait); diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index 95e147eea239..c5b00a735fef 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -54,7 +54,7 @@ int write_ctree_super(struct btrfs_trans_handle *trans, struct btrfs_root *root, int max_mirrors); struct buffer_head *btrfs_read_dev_super(struct block_device *bdev); int btrfs_commit_super(struct btrfs_root *root); -int btrfs_error_commit_super(struct btrfs_root *root); +void btrfs_error_commit_super(struct btrfs_root *root); struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize); struct btrfs_root *btrfs_read_fs_root_no_radix(struct btrfs_root *tree_root, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 4e1b153b7c47..ba58024d40d3 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -2252,6 +2252,16 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans, } /* + * We need to try and merge add/drops of the same ref since we + * can run into issues with relocate dropping the implicit ref + * and then it being added back again before the drop can + * finish. If we merged anything we need to re-loop so we can + * get a good ref. + */ + btrfs_merge_delayed_refs(trans, fs_info, delayed_refs, + locked_ref); + + /* * locked_ref is the head node, so we have to go one * node back for any delayed ref updates */ @@ -2318,12 +2328,23 @@ static noinline int run_clustered_refs(struct btrfs_trans_handle *trans, ref->in_tree = 0; rb_erase(&ref->rb_node, &delayed_refs->root); delayed_refs->num_entries--; - /* - * we modified num_entries, but as we're currently running - * delayed refs, skip - * wake_up(&delayed_refs->seq_wait); - * here. - */ + if (locked_ref) { + /* + * when we play the delayed ref, also correct the + * ref_mod on head + */ + switch (ref->action) { + case BTRFS_ADD_DELAYED_REF: + case BTRFS_ADD_DELAYED_EXTENT: + locked_ref->node.ref_mod -= ref->ref_mod; + break; + case BTRFS_DROP_DELAYED_REF: + locked_ref->node.ref_mod += ref->ref_mod; + break; + default: + WARN_ON(1); + } + } spin_unlock(&delayed_refs->lock); ret = run_one_delayed_ref(trans, root, ref, extent_op, @@ -2350,22 +2371,6 @@ next: return count; } -static void wait_for_more_refs(struct btrfs_fs_info *fs_info, - struct btrfs_delayed_ref_root *delayed_refs, - unsigned long num_refs, - struct list_head *first_seq) -{ - spin_unlock(&delayed_refs->lock); - pr_debug("waiting for more refs (num %ld, first %p)\n", - num_refs, first_seq); - wait_event(fs_info->tree_mod_seq_wait, - num_refs != delayed_refs->num_entries || - fs_info->tree_mod_seq_list.next != first_seq); - pr_debug("done waiting for more refs (num %ld, first %p)\n", - delayed_refs->num_entries, fs_info->tree_mod_seq_list.next); - spin_lock(&delayed_refs->lock); -} - #ifdef SCRAMBLE_DELAYED_REFS /* * Normally delayed refs get processed in ascending bytenr order. This @@ -2460,13 +2465,11 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, struct btrfs_delayed_ref_root *delayed_refs; struct btrfs_delayed_ref_node *ref; struct list_head cluster; - struct list_head *first_seq = NULL; int ret; u64 delayed_start; int run_all = count == (unsigned long)-1; int run_most = 0; - unsigned long num_refs = 0; - int consider_waiting; + int loops; /* We'll clean this up in btrfs_cleanup_transaction */ if (trans->aborted) @@ -2484,7 +2487,7 @@ int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans, delayed_refs = &trans->transaction->delayed_refs; INIT_LIST_HEAD(&cluster); again: - consider_waiting = 0; + loops = 0; spin_lock(&delayed_refs->lock); #ifdef SCRAMBLE_DELAYED_REFS @@ -2512,31 +2515,6 @@ again: if (ret) break; - if (delayed_start >= delayed_refs->run_delayed_start) { - if (consider_waiting == 0) { - /* - * btrfs_find_ref_cluster looped. let's do one - * more cycle. if we don't run any delayed ref - * during that cycle (because we can't because - * all of them are blocked) and if the number of - * refs doesn't change, we avoid busy waiting. - */ - consider_waiting = 1; - num_refs = delayed_refs->num_entries; - first_seq = root->fs_info->tree_mod_seq_list.next; - } else { - wait_for_more_refs(root->fs_info, delayed_refs, - num_refs, first_seq); - /* - * after waiting, things have changed. we - * dropped the lock and someone else might have - * run some refs, built new clusters and so on. - * therefore, we restart staleness detection. - */ - consider_waiting = 0; - } - } - ret = run_clustered_refs(trans, root, &cluster); if (ret < 0) { spin_unlock(&delayed_refs->lock); @@ -2549,9 +2527,26 @@ again: if (count == 0) break; - if (ret || delayed_refs->run_delayed_start == 0) { + if (delayed_start >= delayed_refs->run_delayed_start) { + if (loops == 0) { + /* + * btrfs_find_ref_cluster looped. let's do one + * more cycle. if we don't run any delayed ref + * during that cycle (because we can't because + * all of them are blocked), bail out. + */ + loops = 1; + } else { + /* + * no runnable refs left, stop trying + */ + BUG_ON(run_all); + break; + } + } + if (ret) { /* refs were run, let's reset staleness detection */ - consider_waiting = 0; + loops = 0; } } @@ -3007,17 +3002,16 @@ again: } spin_unlock(&block_group->lock); - num_pages = (int)div64_u64(block_group->key.offset, 1024 * 1024 * 1024); + /* + * Try to preallocate enough space based on how big the block group is. + * Keep in mind this has to include any pinned space which could end up + * taking up quite a bit since it's not folded into the other space + * cache. + */ + num_pages = (int)div64_u64(block_group->key.offset, 256 * 1024 * 1024); if (!num_pages) num_pages = 1; - /* - * Just to make absolutely sure we have enough space, we're going to - * preallocate 12 pages worth of space for each block group. In - * practice we ought to use at most 8, but we need extra space so we can - * add our header and have a terminator between the extents and the - * bitmaps. - */ num_pages *= 16; num_pages *= PAGE_CACHE_SIZE; @@ -4571,8 +4565,10 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes) if (root->fs_info->quota_enabled) { ret = btrfs_qgroup_reserve(root, num_bytes + nr_extents * root->leafsize); - if (ret) + if (ret) { + mutex_unlock(&BTRFS_I(inode)->delalloc_mutex); return ret; + } } ret = reserve_metadata_bytes(root, block_rsv, to_reserve, flush); @@ -5294,9 +5290,6 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans, rb_erase(&head->node.rb_node, &delayed_refs->root); delayed_refs->num_entries--; - smp_mb(); - if (waitqueue_active(&root->fs_info->tree_mod_seq_wait)) - wake_up(&root->fs_info->tree_mod_seq_wait); /* * we don't take a ref on the node because we're removing it from the diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 45c81bb4ac82..4c878476bb91 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2330,23 +2330,10 @@ static void end_bio_extent_readpage(struct bio *bio, int err) if (uptodate && tree->ops && tree->ops->readpage_end_io_hook) { ret = tree->ops->readpage_end_io_hook(page, start, end, state, mirror); - if (ret) { - /* no IO indicated but software detected errors - * in the block, either checksum errors or - * issues with the contents */ - struct btrfs_root *root = - BTRFS_I(page->mapping->host)->root; - struct btrfs_device *device; - + if (ret) uptodate = 0; - device = btrfs_find_device_for_logical( - root, start, mirror); - if (device) - btrfs_dev_stat_inc_and_print(device, - BTRFS_DEV_STAT_CORRUPTION_ERRS); - } else { + else clean_io_failure(start, page); - } } if (!uptodate && tree->ops && tree->ops->readpage_io_failed_hook) { diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c index b45b9de0c21d..857d93cd01dc 100644 --- a/fs/btrfs/file-item.c +++ b/fs/btrfs/file-item.c @@ -272,9 +272,9 @@ int btrfs_lookup_bio_sums(struct btrfs_root *root, struct inode *inode, } int btrfs_lookup_bio_sums_dio(struct btrfs_root *root, struct inode *inode, - struct bio *bio, u64 offset, u32 *dst) + struct bio *bio, u64 offset) { - return __btrfs_lookup_bio_sums(root, inode, bio, offset, dst, 1); + return __btrfs_lookup_bio_sums(root, inode, bio, offset, NULL, 1); } int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end, diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 83baec24946d..ec154f954646 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -324,7 +324,8 @@ static noinline int add_async_extent(struct async_cow *cow, * If this code finds it can't get good compression, it puts an * entry onto the work queue to write the uncompressed bytes. This * makes sure that both compressed inodes and uncompressed inodes - * are written in the same order that pdflush sent them down. + * are written in the same order that the flusher thread sent them + * down. */ static noinline int compress_file_range(struct inode *inode, struct page *locked_page, @@ -1007,9 +1008,7 @@ static noinline void async_cow_submit(struct btrfs_work *work) nr_pages = (async_cow->end - async_cow->start + PAGE_CACHE_SIZE) >> PAGE_CACHE_SHIFT; - atomic_sub(nr_pages, &root->fs_info->async_delalloc_pages); - - if (atomic_read(&root->fs_info->async_delalloc_pages) < + if (atomic_sub_return(nr_pages, &root->fs_info->async_delalloc_pages) < 5 * 1024 * 1024 && waitqueue_active(&root->fs_info->async_submit_wait)) wake_up(&root->fs_info->async_submit_wait); @@ -1884,8 +1883,11 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent) trans = btrfs_join_transaction_nolock(root); else trans = btrfs_join_transaction(root); - if (IS_ERR(trans)) - return PTR_ERR(trans); + if (IS_ERR(trans)) { + ret = PTR_ERR(trans); + trans = NULL; + goto out; + } trans->block_rsv = &root->fs_info->delalloc_block_rsv; ret = btrfs_update_inode_fallback(trans, root, inode); if (ret) /* -ENOMEM or corruption */ @@ -3173,7 +3175,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans, btrfs_i_size_write(dir, dir->i_size - name_len * 2); inode_inc_iversion(dir); dir->i_mtime = dir->i_ctime = CURRENT_TIME; - ret = btrfs_update_inode(trans, root, dir); + ret = btrfs_update_inode_fallback(trans, root, dir); if (ret) btrfs_abort_transaction(trans, root, ret); out: @@ -5773,18 +5775,112 @@ out: return ret; } +static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend, + struct extent_state **cached_state, int writing) +{ + struct btrfs_ordered_extent *ordered; + int ret = 0; + + while (1) { + lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, + 0, cached_state); + /* + * We're concerned with the entire range that we're going to be + * doing DIO to, so we need to make sure theres no ordered + * extents in this range. + */ + ordered = btrfs_lookup_ordered_range(inode, lockstart, + lockend - lockstart + 1); + + /* + * We need to make sure there are no buffered pages in this + * range either, we could have raced between the invalidate in + * generic_file_direct_write and locking the extent. The + * invalidate needs to happen so that reads after a write do not + * get stale data. + */ + if (!ordered && (!writing || + !test_range_bit(&BTRFS_I(inode)->io_tree, + lockstart, lockend, EXTENT_UPTODATE, 0, + *cached_state))) + break; + + unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, + cached_state, GFP_NOFS); + + if (ordered) { + btrfs_start_ordered_extent(inode, ordered, 1); + btrfs_put_ordered_extent(ordered); + } else { + /* Screw you mmap */ + ret = filemap_write_and_wait_range(inode->i_mapping, + lockstart, + lockend); + if (ret) + break; + + /* + * If we found a page that couldn't be invalidated just + * fall back to buffered. + */ + ret = invalidate_inode_pages2_range(inode->i_mapping, + lockstart >> PAGE_CACHE_SHIFT, + lockend >> PAGE_CACHE_SHIFT); + if (ret) + break; + } + + cond_resched(); + } + + return ret; +} + static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { struct extent_map *em; struct btrfs_root *root = BTRFS_I(inode)->root; + struct extent_state *cached_state = NULL; u64 start = iblock << inode->i_blkbits; + u64 lockstart, lockend; u64 len = bh_result->b_size; struct btrfs_trans_handle *trans; + int unlock_bits = EXTENT_LOCKED; + int ret; + + if (create) { + ret = btrfs_delalloc_reserve_space(inode, len); + if (ret) + return ret; + unlock_bits |= EXTENT_DELALLOC | EXTENT_DIRTY; + } else { + len = min_t(u64, len, root->sectorsize); + } + + lockstart = start; + lockend = start + len - 1; + + /* + * If this errors out it's because we couldn't invalidate pagecache for + * this range and we need to fallback to buffered. + */ + if (lock_extent_direct(inode, lockstart, lockend, &cached_state, create)) + return -ENOTBLK; + + if (create) { + ret = set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, + lockend, EXTENT_DELALLOC, NULL, + &cached_state, GFP_NOFS); + if (ret) + goto unlock_err; + } em = btrfs_get_extent(inode, NULL, 0, start, len, 0); - if (IS_ERR(em)) - return PTR_ERR(em); + if (IS_ERR(em)) { + ret = PTR_ERR(em); + goto unlock_err; + } /* * Ok for INLINE and COMPRESSED extents we need to fallback on buffered @@ -5803,17 +5899,16 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) || em->block_start == EXTENT_MAP_INLINE) { free_extent_map(em); - return -ENOTBLK; + ret = -ENOTBLK; + goto unlock_err; } /* Just a good old fashioned hole, return */ if (!create && (em->block_start == EXTENT_MAP_HOLE || test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) { free_extent_map(em); - /* DIO will do one hole at a time, so just unlock a sector */ - unlock_extent(&BTRFS_I(inode)->io_tree, start, - start + root->sectorsize - 1); - return 0; + ret = 0; + goto unlock_err; } /* @@ -5826,8 +5921,9 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, * */ if (!create) { - len = em->len - (start - em->start); - goto map; + len = min(len, em->len - (start - em->start)); + lockstart = start + len; + goto unlock; } if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) || @@ -5859,7 +5955,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, btrfs_end_transaction(trans, root); if (ret) { free_extent_map(em); - return ret; + goto unlock_err; } goto unlock; } @@ -5872,14 +5968,12 @@ must_cow: */ len = bh_result->b_size; em = btrfs_new_extent_direct(inode, em, start, len); - if (IS_ERR(em)) - return PTR_ERR(em); + if (IS_ERR(em)) { + ret = PTR_ERR(em); + goto unlock_err; + } len = min(len, em->len - (start - em->start)); unlock: - clear_extent_bit(&BTRFS_I(inode)->io_tree, start, start + len - 1, - EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DIRTY, 1, - 0, NULL, GFP_NOFS); -map: bh_result->b_blocknr = (em->block_start + (start - em->start)) >> inode->i_blkbits; bh_result->b_size = len; @@ -5897,9 +5991,44 @@ map: i_size_write(inode, start + len); } + /* + * In the case of write we need to clear and unlock the entire range, + * in the case of read we need to unlock only the end area that we + * aren't using if there is any left over space. + */ + if (lockstart < lockend) { + if (create && len < lockend - lockstart) { + clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, + lockstart + len - 1, unlock_bits, 1, 0, + &cached_state, GFP_NOFS); + /* + * Beside unlock, we also need to cleanup reserved space + * for the left range by attaching EXTENT_DO_ACCOUNTING. + */ + clear_extent_bit(&BTRFS_I(inode)->io_tree, + lockstart + len, lockend, + unlock_bits | EXTENT_DO_ACCOUNTING, + 1, 0, NULL, GFP_NOFS); + } else { + clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, + lockend, unlock_bits, 1, 0, + &cached_state, GFP_NOFS); + } + } else { + free_extent_state(cached_state); + } + free_extent_map(em); return 0; + +unlock_err: + if (create) + unlock_bits |= EXTENT_DO_ACCOUNTING; + + clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, + unlock_bits, 1, 0, &cached_state, GFP_NOFS); + return ret; } struct btrfs_dio_private { @@ -5907,7 +6036,6 @@ struct btrfs_dio_private { u64 logical_offset; u64 disk_bytenr; u64 bytes; - u32 *csums; void *private; /* number of bios pending for this dio */ @@ -5927,7 +6055,6 @@ static void btrfs_endio_direct_read(struct bio *bio, int err) struct inode *inode = dip->inode; struct btrfs_root *root = BTRFS_I(inode)->root; u64 start; - u32 *private = dip->csums; start = dip->logical_offset; do { @@ -5935,8 +6062,12 @@ static void btrfs_endio_direct_read(struct bio *bio, int err) struct page *page = bvec->bv_page; char *kaddr; u32 csum = ~(u32)0; + u64 private = ~(u32)0; unsigned long flags; + if (get_state_private(&BTRFS_I(inode)->io_tree, + start, &private)) + goto failed; local_irq_save(flags); kaddr = kmap_atomic(page); csum = btrfs_csum_data(root, kaddr + bvec->bv_offset, @@ -5946,18 +6077,18 @@ static void btrfs_endio_direct_read(struct bio *bio, int err) local_irq_restore(flags); flush_dcache_page(bvec->bv_page); - if (csum != *private) { + if (csum != private) { +failed: printk(KERN_ERR "btrfs csum failed ino %llu off" " %llu csum %u private %u\n", (unsigned long long)btrfs_ino(inode), (unsigned long long)start, - csum, *private); + csum, (unsigned)private); err = -EIO; } } start += bvec->bv_len; - private++; bvec++; } while (bvec <= bvec_end); @@ -5965,7 +6096,6 @@ static void btrfs_endio_direct_read(struct bio *bio, int err) dip->logical_offset + dip->bytes - 1); bio->bi_private = dip->private; - kfree(dip->csums); kfree(dip); /* If we had a csum failure make sure to clear the uptodate flag */ @@ -6071,7 +6201,7 @@ static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev, static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, int rw, u64 file_offset, int skip_sum, - u32 *csums, int async_submit) + int async_submit) { int write = rw & REQ_WRITE; struct btrfs_root *root = BTRFS_I(inode)->root; @@ -6104,8 +6234,7 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode, if (ret) goto err; } else if (!skip_sum) { - ret = btrfs_lookup_bio_sums_dio(root, inode, bio, - file_offset, csums); + ret = btrfs_lookup_bio_sums_dio(root, inode, bio, file_offset); if (ret) goto err; } @@ -6131,10 +6260,8 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, u64 submit_len = 0; u64 map_length; int nr_pages = 0; - u32 *csums = dip->csums; int ret = 0; int async_submit = 0; - int write = rw & REQ_WRITE; map_length = orig_bio->bi_size; ret = btrfs_map_block(map_tree, READ, start_sector << 9, @@ -6170,16 +6297,13 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, atomic_inc(&dip->pending_bios); ret = __btrfs_submit_dio_bio(bio, inode, rw, file_offset, skip_sum, - csums, async_submit); + async_submit); if (ret) { bio_put(bio); atomic_dec(&dip->pending_bios); goto out_err; } - /* Write's use the ordered csums */ - if (!write && !skip_sum) - csums = csums + nr_pages; start_sector += submit_len >> 9; file_offset += submit_len; @@ -6209,7 +6333,7 @@ static int btrfs_submit_direct_hook(int rw, struct btrfs_dio_private *dip, submit: ret = __btrfs_submit_dio_bio(bio, inode, rw, file_offset, skip_sum, - csums, async_submit); + async_submit); if (!ret) return 0; @@ -6245,17 +6369,6 @@ static void btrfs_submit_direct(int rw, struct bio *bio, struct inode *inode, ret = -ENOMEM; goto free_ordered; } - dip->csums = NULL; - - /* Write's use the ordered csum stuff, so we don't need dip->csums */ - if (!write && !skip_sum) { - dip->csums = kmalloc(sizeof(u32) * bio->bi_vcnt, GFP_NOFS); - if (!dip->csums) { - kfree(dip); - ret = -ENOMEM; - goto free_ordered; - } - } dip->private = bio->bi_private; dip->inode = inode; @@ -6340,132 +6453,22 @@ static ssize_t check_direct_IO(struct btrfs_root *root, int rw, struct kiocb *io out: return retval; } + static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t offset, unsigned long nr_segs) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; - struct btrfs_ordered_extent *ordered; - struct extent_state *cached_state = NULL; - u64 lockstart, lockend; - ssize_t ret; - int writing = rw & WRITE; - int write_bits = 0; - size_t count = iov_length(iov, nr_segs); if (check_direct_IO(BTRFS_I(inode)->root, rw, iocb, iov, - offset, nr_segs)) { + offset, nr_segs)) return 0; - } - - lockstart = offset; - lockend = offset + count - 1; - - if (writing) { - ret = btrfs_delalloc_reserve_space(inode, count); - if (ret) - goto out; - } - - while (1) { - lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend, - 0, &cached_state); - /* - * We're concerned with the entire range that we're going to be - * doing DIO to, so we need to make sure theres no ordered - * extents in this range. - */ - ordered = btrfs_lookup_ordered_range(inode, lockstart, - lockend - lockstart + 1); - - /* - * We need to make sure there are no buffered pages in this - * range either, we could have raced between the invalidate in - * generic_file_direct_write and locking the extent. The - * invalidate needs to happen so that reads after a write do not - * get stale data. - */ - if (!ordered && (!writing || - !test_range_bit(&BTRFS_I(inode)->io_tree, - lockstart, lockend, EXTENT_UPTODATE, 0, - cached_state))) - break; - - unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend, - &cached_state, GFP_NOFS); - - if (ordered) { - btrfs_start_ordered_extent(inode, ordered, 1); - btrfs_put_ordered_extent(ordered); - } else { - /* Screw you mmap */ - ret = filemap_write_and_wait_range(file->f_mapping, - lockstart, - lockend); - if (ret) - goto out; - - /* - * If we found a page that couldn't be invalidated just - * fall back to buffered. - */ - ret = invalidate_inode_pages2_range(file->f_mapping, - lockstart >> PAGE_CACHE_SHIFT, - lockend >> PAGE_CACHE_SHIFT); - if (ret) { - if (ret == -EBUSY) - ret = 0; - goto out; - } - } - - cond_resched(); - } - /* - * we don't use btrfs_set_extent_delalloc because we don't want - * the dirty or uptodate bits - */ - if (writing) { - write_bits = EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING; - ret = set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockend, - EXTENT_DELALLOC, NULL, &cached_state, - GFP_NOFS); - if (ret) { - clear_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, - lockend, EXTENT_LOCKED | write_bits, - 1, 0, &cached_state, GFP_NOFS); - goto out; - } - } - - free_extent_state(cached_state); - cached_state = NULL; - - ret = __blockdev_direct_IO(rw, iocb, inode, + return __blockdev_direct_IO(rw, iocb, inode, BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev, iov, offset, nr_segs, btrfs_get_blocks_direct, NULL, btrfs_submit_direct, 0); - - if (ret < 0 && ret != -EIOCBQUEUED) { - clear_extent_bit(&BTRFS_I(inode)->io_tree, offset, - offset + iov_length(iov, nr_segs) - 1, - EXTENT_LOCKED | write_bits, 1, 0, - &cached_state, GFP_NOFS); - } else if (ret >= 0 && ret < iov_length(iov, nr_segs)) { - /* - * We're falling back to buffered, unlock the section we didn't - * do IO on. - */ - clear_extent_bit(&BTRFS_I(inode)->io_tree, offset + ret, - offset + iov_length(iov, nr_segs) - 1, - EXTENT_LOCKED | write_bits, 1, 0, - &cached_state, GFP_NOFS); - } -out: - free_extent_state(cached_state); - return ret; } static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index bc2f6ffff3cf..9df50fa8a078 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -424,7 +424,7 @@ static noinline int create_subvol(struct btrfs_root *root, uuid_le_gen(&new_uuid); memcpy(root_item.uuid, new_uuid.b, BTRFS_UUID_SIZE); root_item.otime.sec = cpu_to_le64(cur_time.tv_sec); - root_item.otime.nsec = cpu_to_le64(cur_time.tv_nsec); + root_item.otime.nsec = cpu_to_le32(cur_time.tv_nsec); root_item.ctime = root_item.otime; btrfs_set_root_ctransid(&root_item, trans->transid); btrfs_set_root_otransid(&root_item, trans->transid); @@ -664,10 +664,6 @@ static noinline int btrfs_mksubvol(struct path *parent, struct dentry *dentry; int error; - error = mnt_want_write(parent->mnt); - if (error) - return error; - mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT); dentry = lookup_one_len(name, parent->dentry, namelen); @@ -703,7 +699,6 @@ out_dput: dput(dentry); out_unlock: mutex_unlock(&dir->i_mutex); - mnt_drop_write(parent->mnt); return error; } diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index a44eff074805..2a1762c66041 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -67,7 +67,7 @@ void btrfs_clear_lock_blocking_rw(struct extent_buffer *eb, int rw) { if (eb->lock_nested) { read_lock(&eb->lock); - if (&eb->lock_nested && current->pid == eb->lock_owner) { + if (eb->lock_nested && current->pid == eb->lock_owner) { read_unlock(&eb->lock); return; } diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 643335a4fe3c..051c7fe551dd 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -596,7 +596,7 @@ void btrfs_start_ordered_extent(struct inode *inode, /* * pages in the range can be dirty, clean or writeback. We * start IO on any dirty ones so the wait doesn't stall waiting - * for pdflush to find them + * for the flusher thread to find them */ if (!test_bit(BTRFS_ORDERED_DIRECT, &entry->flags)) filemap_fdatawrite_range(inode->i_mapping, start, end); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index bc424ae5a81a..38b42e7bc91d 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1364,13 +1364,17 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, spin_lock(&fs_info->qgroup_lock); dstgroup = add_qgroup_rb(fs_info, objectid); - if (!dstgroup) + if (IS_ERR(dstgroup)) { + ret = PTR_ERR(dstgroup); goto unlock; + } if (srcid) { srcgroup = find_qgroup_rb(fs_info, srcid); - if (!srcgroup) + if (!srcgroup) { + ret = -EINVAL; goto unlock; + } dstgroup->rfer = srcgroup->rfer - level_size; dstgroup->rfer_cmpr = srcgroup->rfer_cmpr - level_size; srcgroup->excl = level_size; @@ -1379,8 +1383,10 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, qgroup_dirty(fs_info, srcgroup); } - if (!inherit) + if (!inherit) { + ret = -EINVAL; goto unlock; + } i_qgroups = (u64 *)(inherit + 1); for (i = 0; i < inherit->num_qgroups; ++i) { diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c index 6bb465cca20f..10d8e4d88071 100644 --- a/fs/btrfs/root-tree.c +++ b/fs/btrfs/root-tree.c @@ -544,8 +544,8 @@ void btrfs_update_root_times(struct btrfs_trans_handle *trans, struct timespec ct = CURRENT_TIME; spin_lock(&root->root_times_lock); - item->ctransid = trans->transid; + item->ctransid = cpu_to_le64(trans->transid); item->ctime.sec = cpu_to_le64(ct.tv_sec); - item->ctime.nsec = cpu_to_le64(ct.tv_nsec); + item->ctime.nsec = cpu_to_le32(ct.tv_nsec); spin_unlock(&root->root_times_lock); } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 8c6e61d6eed5..83d6f9f9c220 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -100,10 +100,6 @@ static void __save_error_info(struct btrfs_fs_info *fs_info) fs_info->fs_state = BTRFS_SUPER_FLAG_ERROR; } -/* NOTE: - * We move write_super stuff at umount in order to avoid deadlock - * for umount hold all lock. - */ static void save_error_info(struct btrfs_fs_info *fs_info) { __save_error_info(fs_info); @@ -842,7 +838,6 @@ int btrfs_sync_fs(struct super_block *sb, int wait) struct btrfs_trans_handle *trans; struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_root *root = fs_info->tree_root; - int ret; trace_btrfs_sync_fs(wait); @@ -853,11 +848,17 @@ int btrfs_sync_fs(struct super_block *sb, int wait) btrfs_wait_ordered_extents(root, 0, 0); - trans = btrfs_start_transaction(root, 0); + spin_lock(&fs_info->trans_lock); + if (!fs_info->running_transaction) { + spin_unlock(&fs_info->trans_lock); + return 0; + } + spin_unlock(&fs_info->trans_lock); + + trans = btrfs_join_transaction(root); if (IS_ERR(trans)) return PTR_ERR(trans); - ret = btrfs_commit_transaction(trans, root); - return ret; + return btrfs_commit_transaction(trans, root); } static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) @@ -1534,6 +1535,8 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root) while (cur_devices) { head = &cur_devices->devices; list_for_each_entry(dev, head, dev_list) { + if (dev->missing) + continue; if (!first_dev || dev->devid < first_dev->devid) first_dev = dev; } diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 17be3dedacba..27c26004e050 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -1031,6 +1031,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, btrfs_i_size_write(parent_inode, parent_inode->i_size + dentry->d_name.len * 2); + parent_inode->i_mtime = parent_inode->i_ctime = CURRENT_TIME; ret = btrfs_update_inode(trans, parent_root, parent_inode); if (ret) goto abort_trans_dput; @@ -1066,7 +1067,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans, memcpy(new_root_item->parent_uuid, root->root_item.uuid, BTRFS_UUID_SIZE); new_root_item->otime.sec = cpu_to_le64(cur_time.tv_sec); - new_root_item->otime.nsec = cpu_to_le64(cur_time.tv_nsec); + new_root_item->otime.nsec = cpu_to_le32(cur_time.tv_nsec); btrfs_set_root_otransid(new_root_item, trans->transid); memset(&new_root_item->stime, 0, sizeof(new_root_item->stime)); memset(&new_root_item->rtime, 0, sizeof(new_root_item->rtime)); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index b8708f994e67..88b969aeeb71 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -227,9 +227,8 @@ loop_lock: cur = pending; pending = pending->bi_next; cur->bi_next = NULL; - atomic_dec(&fs_info->nr_async_bios); - if (atomic_read(&fs_info->nr_async_bios) < limit && + if (atomic_dec_return(&fs_info->nr_async_bios) < limit && waitqueue_active(&fs_info->async_submit_wait)) wake_up(&fs_info->async_submit_wait); @@ -569,9 +568,11 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices) memcpy(new_device, device, sizeof(*new_device)); /* Safe because we are under uuid_mutex */ - name = rcu_string_strdup(device->name->str, GFP_NOFS); - BUG_ON(device->name && !name); /* -ENOMEM */ - rcu_assign_pointer(new_device->name, name); + if (device->name) { + name = rcu_string_strdup(device->name->str, GFP_NOFS); + BUG_ON(device->name && !name); /* -ENOMEM */ + rcu_assign_pointer(new_device->name, name); + } new_device->bdev = NULL; new_device->writeable = 0; new_device->in_fs_metadata = 0; @@ -1744,10 +1745,6 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) device->fs_devices = root->fs_info->fs_devices; - /* - * we don't want write_supers to jump in here with our device - * half setup - */ mutex_lock(&root->fs_info->fs_devices->device_list_mutex); list_add_rcu(&device->dev_list, &root->fs_info->fs_devices->devices); list_add(&device->dev_alloc_list, @@ -4609,28 +4606,6 @@ int btrfs_read_sys_array(struct btrfs_root *root) return ret; } -struct btrfs_device *btrfs_find_device_for_logical(struct btrfs_root *root, - u64 logical, int mirror_num) -{ - struct btrfs_mapping_tree *map_tree = &root->fs_info->mapping_tree; - int ret; - u64 map_length = 0; - struct btrfs_bio *bbio = NULL; - struct btrfs_device *device; - - BUG_ON(mirror_num == 0); - ret = btrfs_map_block(map_tree, WRITE, logical, &map_length, &bbio, - mirror_num); - if (ret) { - BUG_ON(bbio != NULL); - return NULL; - } - BUG_ON(mirror_num != bbio->mirror_num); - device = bbio->stripes[mirror_num - 1].dev; - kfree(bbio); - return device; -} - int btrfs_read_chunk_tree(struct btrfs_root *root) { struct btrfs_path *path; diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 5479325987b3..53c06af92e8d 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -289,8 +289,6 @@ int btrfs_cancel_balance(struct btrfs_fs_info *fs_info); int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset); int find_free_dev_extent(struct btrfs_device *device, u64 num_bytes, u64 *start, u64 *max_avail); -struct btrfs_device *btrfs_find_device_for_logical(struct btrfs_root *root, - u64 logical, int mirror_num); void btrfs_dev_stat_print_on_error(struct btrfs_device *device); void btrfs_dev_stat_inc_and_print(struct btrfs_device *dev, int index); int btrfs_get_dev_stats(struct btrfs_root *root, diff --git a/fs/buffer.c b/fs/buffer.c index 9f6d2e41281d..58e2e7b77372 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -914,7 +914,7 @@ link_dev_buffers(struct page *page, struct buffer_head *head) /* * Initialise the state of a blockdev page's buffers. */ -static void +static sector_t init_page_buffers(struct page *page, struct block_device *bdev, sector_t block, int size) { @@ -936,33 +936,41 @@ init_page_buffers(struct page *page, struct block_device *bdev, block++; bh = bh->b_this_page; } while (bh != head); + + /* + * Caller needs to validate requested block against end of device. + */ + return end_block; } /* * Create the page-cache page that contains the requested block. * - * This is user purely for blockdev mappings. + * This is used purely for blockdev mappings. */ -static struct page * +static int grow_dev_page(struct block_device *bdev, sector_t block, - pgoff_t index, int size) + pgoff_t index, int size, int sizebits) { struct inode *inode = bdev->bd_inode; struct page *page; struct buffer_head *bh; + sector_t end_block; + int ret = 0; /* Will call free_more_memory() */ page = find_or_create_page(inode->i_mapping, index, (mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS)|__GFP_MOVABLE); if (!page) - return NULL; + return ret; BUG_ON(!PageLocked(page)); if (page_has_buffers(page)) { bh = page_buffers(page); if (bh->b_size == size) { - init_page_buffers(page, bdev, block, size); - return page; + end_block = init_page_buffers(page, bdev, + index << sizebits, size); + goto done; } if (!try_to_free_buffers(page)) goto failed; @@ -982,14 +990,14 @@ grow_dev_page(struct block_device *bdev, sector_t block, */ spin_lock(&inode->i_mapping->private_lock); link_dev_buffers(page, bh); - init_page_buffers(page, bdev, block, size); + end_block = init_page_buffers(page, bdev, index << sizebits, size); spin_unlock(&inode->i_mapping->private_lock); - return page; - +done: + ret = (block < end_block) ? 1 : -ENXIO; failed: unlock_page(page); page_cache_release(page); - return NULL; + return ret; } /* @@ -999,7 +1007,6 @@ failed: static int grow_buffers(struct block_device *bdev, sector_t block, int size) { - struct page *page; pgoff_t index; int sizebits; @@ -1023,22 +1030,14 @@ grow_buffers(struct block_device *bdev, sector_t block, int size) bdevname(bdev, b)); return -EIO; } - block = index << sizebits; + /* Create a page with the proper size buffers.. */ - page = grow_dev_page(bdev, block, index, size); - if (!page) - return 0; - unlock_page(page); - page_cache_release(page); - return 1; + return grow_dev_page(bdev, block, index, size, sizebits); } static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, int size) { - int ret; - struct buffer_head *bh; - /* Size must be multiple of hard sectorsize */ if (unlikely(size & (bdev_logical_block_size(bdev)-1) || (size < 512 || size > PAGE_SIZE))) { @@ -1051,21 +1050,20 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size) return NULL; } -retry: - bh = __find_get_block(bdev, block, size); - if (bh) - return bh; + for (;;) { + struct buffer_head *bh; + int ret; - ret = grow_buffers(bdev, block, size); - if (ret == 0) { - free_more_memory(); - goto retry; - } else if (ret > 0) { bh = __find_get_block(bdev, block, size); if (bh) return bh; + + ret = grow_buffers(bdev, block, size); + if (ret < 0) + return NULL; + if (ret == 0) + free_more_memory(); } - return NULL; } /* @@ -1321,10 +1319,6 @@ EXPORT_SYMBOL(__find_get_block); * which corresponds to the passed block_device, block and size. The * returned buffer has its reference count incremented. * - * __getblk() cannot fail - it just keeps trying. If you pass it an - * illegal block number, __getblk() will happily return a buffer_head - * which represents the non-existent block. Very weird. - * * __getblk() will lock up the machine if grow_dev_page's try_to_free_buffers() * attempt is failing. FIXME, perhaps? */ diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index fb962efdacee..6d59006bfa27 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -201,6 +201,7 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc) int err = -ENOMEM; dout("ceph_fs_debugfs_init\n"); + BUG_ON(!fsc->client->debugfs_dir); fsc->debugfs_congestion_kb = debugfs_create_file("writeback_congestion_kb", 0600, diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 9fff9f3b17e4..4b5762ef7c2b 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -992,11 +992,15 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, if (rinfo->head->is_dentry) { struct inode *dir = req->r_locked_dir; - err = fill_inode(dir, &rinfo->diri, rinfo->dirfrag, - session, req->r_request_started, -1, - &req->r_caps_reservation); - if (err < 0) - return err; + if (dir) { + err = fill_inode(dir, &rinfo->diri, rinfo->dirfrag, + session, req->r_request_started, -1, + &req->r_caps_reservation); + if (err < 0) + return err; + } else { + WARN_ON_ONCE(1); + } } /* @@ -1004,6 +1008,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req, * will have trouble splicing in the virtual snapdir later */ if (rinfo->head->is_dentry && !req->r_aborted && + req->r_locked_dir && (rinfo->head->is_target || strncmp(req->r_dentry->d_name.name, fsc->mount_options->snapdir_name, req->r_dentry->d_name.len))) { diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c index 8e3fb69fbe62..1396ceb46797 100644 --- a/fs/ceph/ioctl.c +++ b/fs/ceph/ioctl.c @@ -42,7 +42,8 @@ static long __validate_layout(struct ceph_mds_client *mdsc, /* validate striping parameters */ if ((l->object_size & ~PAGE_MASK) || (l->stripe_unit & ~PAGE_MASK) || - ((unsigned)l->object_size % (unsigned)l->stripe_unit)) + (l->stripe_unit != 0 && + ((unsigned)l->object_size % (unsigned)l->stripe_unit))) return -EINVAL; /* make sure it's a valid data pool */ diff --git a/fs/compat.c b/fs/compat.c index 6161255fac45..1bdb350ea5d3 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1155,11 +1155,14 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, struct file *file; int fput_needed; ssize_t ret; + loff_t pos; file = fget_light(fd, &fput_needed); if (!file) return -EBADF; - ret = compat_readv(file, vec, vlen, &file->f_pos); + pos = file->f_pos; + ret = compat_readv(file, vec, vlen, &pos); + file->f_pos = pos; fput_light(file, fput_needed); return ret; } @@ -1221,11 +1224,14 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, struct file *file; int fput_needed; ssize_t ret; + loff_t pos; file = fget_light(fd, &fput_needed); if (!file) return -EBADF; - ret = compat_writev(file, vec, vlen, &file->f_pos); + pos = file->f_pos; + ret = compat_writev(file, vec, vlen, &pos); + file->f_pos = pos; fput_light(file, fput_needed); return ret; } diff --git a/fs/direct-io.c b/fs/direct-io.c index 1faf4cb56f39..f86c720dba0e 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1062,6 +1062,7 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, unsigned long user_addr; size_t bytes; struct buffer_head map_bh = { 0, }; + struct blk_plug plug; if (rw & WRITE) rw = WRITE_ODIRECT; @@ -1177,6 +1178,8 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, PAGE_SIZE - user_addr / PAGE_SIZE); } + blk_start_plug(&plug); + for (seg = 0; seg < nr_segs; seg++) { user_addr = (unsigned long)iov[seg].iov_base; sdio.size += bytes = iov[seg].iov_len; @@ -1235,6 +1238,8 @@ do_blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, if (sdio.bio) dio_bio_submit(dio, &sdio); + blk_finish_plug(&plug); + /* * It is possible that, we return short IO due to end of file. * In that case, we need to release all the pages we got hold on. diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 1c8b55670804..eedec84c1809 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1654,8 +1654,8 @@ SYSCALL_DEFINE1(epoll_create1, int, flags) error = PTR_ERR(file); goto out_free_fd; } - fd_install(fd, file); ep->file = file; + fd_install(fd, file); return fd; out_free_fd: diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c index 5badb0c039de..1562c27a2fab 100644 --- a/fs/exofs/inode.c +++ b/fs/exofs/inode.c @@ -37,15 +37,12 @@ #define EXOFS_DBGMSG2(M...) do {} while (0) -enum {MAX_PAGES_KMALLOC = PAGE_SIZE / sizeof(struct page *), }; - unsigned exofs_max_io_pages(struct ore_layout *layout, unsigned expected_pages) { - unsigned pages = min_t(unsigned, expected_pages, MAX_PAGES_KMALLOC); + unsigned pages = min_t(unsigned, expected_pages, + layout->max_io_length / PAGE_SIZE); - /* TODO: easily support bio chaining */ - pages = min_t(unsigned, pages, layout->max_io_length / PAGE_SIZE); return pages; } @@ -101,7 +98,8 @@ static void _pcol_reset(struct page_collect *pcol) * it might not end here. don't be left with nothing */ if (!pcol->expected_pages) - pcol->expected_pages = MAX_PAGES_KMALLOC; + pcol->expected_pages = + exofs_max_io_pages(&pcol->sbi->layout, ~0); } static int pcol_try_alloc(struct page_collect *pcol) @@ -389,6 +387,8 @@ static int readpage_strip(void *data, struct page *page) size_t len; int ret; + BUG_ON(!PageLocked(page)); + /* FIXME: Just for debugging, will be removed */ if (PageUptodate(page)) EXOFS_ERR("PageUptodate(0x%lx, 0x%lx)\n", pcol->inode->i_ino, @@ -572,8 +572,16 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate) if (!pcol->that_locked_page || (pcol->that_locked_page->index != index)) { - struct page *page = find_get_page(pcol->inode->i_mapping, index); + struct page *page; + loff_t i_size = i_size_read(pcol->inode); + + if (offset >= i_size) { + *uptodate = true; + EXOFS_DBGMSG("offset >= i_size index=0x%lx\n", index); + return ZERO_PAGE(0); + } + page = find_get_page(pcol->inode->i_mapping, index); if (!page) { page = find_or_create_page(pcol->inode->i_mapping, index, GFP_NOFS); @@ -602,12 +610,13 @@ static void __r4w_put_page(void *priv, struct page *page) { struct page_collect *pcol = priv; - if (pcol->that_locked_page != page) { + if ((pcol->that_locked_page != page) && (ZERO_PAGE(0) != page)) { EXOFS_DBGMSG("index=0x%lx\n", page->index); page_cache_release(page); return; } - EXOFS_DBGMSG("that_locked_page index=0x%lx\n", page->index); + EXOFS_DBGMSG("that_locked_page index=0x%lx\n", + ZERO_PAGE(0) == page ? -1 : page->index); } static const struct _ore_r4w_op _r4w_op = { diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c index 24a49d47e935..1585db1aa365 100644 --- a/fs/exofs/ore.c +++ b/fs/exofs/ore.c @@ -837,11 +837,11 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp) bio->bi_rw |= REQ_WRITE; } - osd_req_write(or, _ios_obj(ios, dev), per_dev->offset, - bio, per_dev->length); + osd_req_write(or, _ios_obj(ios, cur_comp), + per_dev->offset, bio, per_dev->length); ORE_DBGMSG("write(0x%llx) offset=0x%llx " "length=0x%llx dev=%d\n", - _LLU(_ios_obj(ios, dev)->id), + _LLU(_ios_obj(ios, cur_comp)->id), _LLU(per_dev->offset), _LLU(per_dev->length), dev); } else if (ios->kern_buff) { @@ -853,20 +853,20 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp) (ios->si.unit_off + ios->length > ios->layout->stripe_unit)); - ret = osd_req_write_kern(or, _ios_obj(ios, per_dev->dev), + ret = osd_req_write_kern(or, _ios_obj(ios, cur_comp), per_dev->offset, ios->kern_buff, ios->length); if (unlikely(ret)) goto out; ORE_DBGMSG2("write_kern(0x%llx) offset=0x%llx " "length=0x%llx dev=%d\n", - _LLU(_ios_obj(ios, dev)->id), + _LLU(_ios_obj(ios, cur_comp)->id), _LLU(per_dev->offset), _LLU(ios->length), per_dev->dev); } else { - osd_req_set_attributes(or, _ios_obj(ios, dev)); + osd_req_set_attributes(or, _ios_obj(ios, cur_comp)); ORE_DBGMSG2("obj(0x%llx) set_attributes=%d dev=%d\n", - _LLU(_ios_obj(ios, dev)->id), + _LLU(_ios_obj(ios, cur_comp)->id), ios->out_attr_len, dev); } diff --git a/fs/exofs/super.c b/fs/exofs/super.c index 433783624d10..dde41a75c7c8 100644 --- a/fs/exofs/super.c +++ b/fs/exofs/super.c @@ -400,8 +400,6 @@ static int exofs_sync_fs(struct super_block *sb, int wait) ret = ore_write(ios); if (unlikely(ret)) EXOFS_ERR("%s: ore_write failed.\n", __func__); - else - sb->s_dirt = 0; unlock_super(sb); @@ -412,14 +410,6 @@ out: return ret; } -static void exofs_write_super(struct super_block *sb) -{ - if (!(sb->s_flags & MS_RDONLY)) - exofs_sync_fs(sb, 1); - else - sb->s_dirt = 0; -} - static void _exofs_print_device(const char *msg, const char *dev_path, struct osd_dev *od, u64 pid) { @@ -952,7 +942,6 @@ static const struct super_operations exofs_sops = { .write_inode = exofs_write_inode, .evict_inode = exofs_evict_inode, .put_super = exofs_put_super, - .write_super = exofs_write_super, .sync_fs = exofs_sync_fs, .statfs = exofs_statfs, }; diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c index 9a4a5c48b1c9..a07597307fd1 100644 --- a/fs/ext3/inode.c +++ b/fs/ext3/inode.c @@ -3459,14 +3459,6 @@ ext3_reserve_inode_write(handle_t *handle, struct inode *inode, * inode out, but prune_icache isn't a user-visible syncing function. * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync) * we start and wait on commits. - * - * Is this efficient/effective? Well, we're being nice to the system - * by cleaning up our inodes proactively so they can be reaped - * without I/O. But we are potentially leaving up to five seconds' - * worth of inodes floating about which prune_icache wants us to - * write out. One way to fix that would be to get prune_icache() - * to do a write_super() to free up some memory. It has the desired - * effect. */ int ext3_mark_inode_dirty(handle_t *handle, struct inode *inode) { diff --git a/fs/ext3/super.c b/fs/ext3/super.c index ff9bcdc5b0d5..8c892e93d8e7 100644 --- a/fs/ext3/super.c +++ b/fs/ext3/super.c @@ -64,11 +64,6 @@ static int ext3_freeze(struct super_block *sb); /* * Wrappers for journal_start/end. - * - * The only special thing we need to do here is to make sure that all - * journal_end calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. */ handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks) { @@ -90,12 +85,6 @@ handle_t *ext3_journal_start_sb(struct super_block *sb, int nblocks) return journal_start(journal, nblocks); } -/* - * The only special thing we need to do here is to make sure that all - * journal_stop calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. - */ int __ext3_journal_stop(const char *where, handle_t *handle) { struct super_block *sb; diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index d23b31ca9d7a..1b5089067d01 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -280,14 +280,18 @@ struct ext4_group_desc * ext4_get_group_desc(struct super_block *sb, return desc; } -static int ext4_valid_block_bitmap(struct super_block *sb, - struct ext4_group_desc *desc, - unsigned int block_group, - struct buffer_head *bh) +/* + * Return the block number which was discovered to be invalid, or 0 if + * the block bitmap is valid. + */ +static ext4_fsblk_t ext4_valid_block_bitmap(struct super_block *sb, + struct ext4_group_desc *desc, + unsigned int block_group, + struct buffer_head *bh) { ext4_grpblk_t offset; ext4_grpblk_t next_zero_bit; - ext4_fsblk_t bitmap_blk; + ext4_fsblk_t blk; ext4_fsblk_t group_first_block; if (EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FLEX_BG)) { @@ -297,37 +301,33 @@ static int ext4_valid_block_bitmap(struct super_block *sb, * or it has to also read the block group where the bitmaps * are located to verify they are set. */ - return 1; + return 0; } group_first_block = ext4_group_first_block_no(sb, block_group); /* check whether block bitmap block number is set */ - bitmap_blk = ext4_block_bitmap(sb, desc); - offset = bitmap_blk - group_first_block; + blk = ext4_block_bitmap(sb, desc); + offset = blk - group_first_block; if (!ext4_test_bit(offset, bh->b_data)) /* bad block bitmap */ - goto err_out; + return blk; /* check whether the inode bitmap block number is set */ - bitmap_blk = ext4_inode_bitmap(sb, desc); - offset = bitmap_blk - group_first_block; + blk = ext4_inode_bitmap(sb, desc); + offset = blk - group_first_block; if (!ext4_test_bit(offset, bh->b_data)) /* bad block bitmap */ - goto err_out; + return blk; /* check whether the inode table block number is set */ - bitmap_blk = ext4_inode_table(sb, desc); - offset = bitmap_blk - group_first_block; + blk = ext4_inode_table(sb, desc); + offset = blk - group_first_block; next_zero_bit = ext4_find_next_zero_bit(bh->b_data, offset + EXT4_SB(sb)->s_itb_per_group, offset); - if (next_zero_bit >= offset + EXT4_SB(sb)->s_itb_per_group) - /* good bitmap for inode tables */ - return 1; - -err_out: - ext4_error(sb, "Invalid block bitmap - block_group = %d, block = %llu", - block_group, bitmap_blk); + if (next_zero_bit < offset + EXT4_SB(sb)->s_itb_per_group) + /* bad bitmap for inode tables */ + return blk; return 0; } @@ -336,14 +336,26 @@ void ext4_validate_block_bitmap(struct super_block *sb, unsigned int block_group, struct buffer_head *bh) { + ext4_fsblk_t blk; + if (buffer_verified(bh)) return; ext4_lock_group(sb, block_group); - if (ext4_valid_block_bitmap(sb, desc, block_group, bh) && - ext4_block_bitmap_csum_verify(sb, block_group, desc, bh, - EXT4_BLOCKS_PER_GROUP(sb) / 8)) - set_buffer_verified(bh); + blk = ext4_valid_block_bitmap(sb, desc, block_group, bh); + if (unlikely(blk != 0)) { + ext4_unlock_group(sb, block_group); + ext4_error(sb, "bg %u: block %llu: invalid block bitmap", + block_group, blk); + return; + } + if (unlikely(!ext4_block_bitmap_csum_verify(sb, block_group, + desc, bh, EXT4_BLOCKS_PER_GROUP(sb) / 8))) { + ext4_unlock_group(sb, block_group); + ext4_error(sb, "bg %u: bad block bitmap checksum", block_group); + return; + } + set_buffer_verified(bh); ext4_unlock_group(sb, block_group); } diff --git a/fs/ext4/bitmap.c b/fs/ext4/bitmap.c index f8716eab9995..5c2d1813ebe9 100644 --- a/fs/ext4/bitmap.c +++ b/fs/ext4/bitmap.c @@ -79,7 +79,6 @@ int ext4_block_bitmap_csum_verify(struct super_block *sb, ext4_group_t group, if (provided == calculated) return 1; - ext4_error(sb, "Bad block bitmap checksum: block_group = %u", group); return 0; } diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index cd0c7ed06772..aabbb3f53683 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -2662,6 +2662,7 @@ cont: } path[0].p_depth = depth; path[0].p_hdr = ext_inode_hdr(inode); + i = 0; if (ext4_ext_check(inode, path[0].p_hdr, depth)) { err = -EIO; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 6324f74e0342..dff171c3a123 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1970,7 +1970,7 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate); * This function can get called via... * - ext4_da_writepages after taking page lock (have journal handle) * - journal_submit_inode_data_buffers (no journal handle) - * - shrink_page_list via pdflush (no journal handle) + * - shrink_page_list via the kswapd/direct reclaim (no journal handle) * - grab_page_cache when doing write_begin (have journal handle) * * We don't do any block allocation in this function. If we have page with @@ -4589,14 +4589,6 @@ static int ext4_expand_extra_isize(struct inode *inode, * inode out, but prune_icache isn't a user-visible syncing function. * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync) * we start and wait on commits. - * - * Is this efficient/effective? Well, we're being nice to the system - * by cleaning up our inodes proactively so they can be reaped - * without I/O. But we are potentially leaving up to five seconds' - * worth of inodes floating about which prune_icache wants us to - * write out. One way to fix that would be to get prune_icache() - * to do a write_super() to free up some memory. It has the desired - * effect. */ int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode) { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index d76ec8277d3f..c6e0cb3d1f4a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -326,11 +326,6 @@ static void ext4_put_nojournal(handle_t *handle) /* * Wrappers for jbd2_journal_start/end. - * - * The only special thing we need to do here is to make sure that all - * journal_end calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. */ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) { @@ -356,12 +351,6 @@ handle_t *ext4_journal_start_sb(struct super_block *sb, int nblocks) return jbd2_journal_start(journal, nblocks); } -/* - * The only special thing we need to do here is to make sure that all - * jbd2_journal_stop calls result in the superblock being marked dirty, so - * that sync() will call the filesystem's write_super callback if - * appropriate. - */ int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle) { struct super_block *sb; @@ -959,6 +948,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb) ei->i_reserved_meta_blocks = 0; ei->i_allocated_meta_blocks = 0; ei->i_da_metadata_calc_len = 0; + ei->i_da_metadata_calc_last_lblock = 0; spin_lock_init(&(ei->i_block_reservation_lock)); #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; @@ -3119,6 +3109,10 @@ static int count_overhead(struct super_block *sb, ext4_group_t grp, ext4_group_t i, ngroups = ext4_get_groups_count(sb); int s, j, count = 0; + if (!EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_BIGALLOC)) + return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) + + sbi->s_itb_per_group + 2); + first_block = le32_to_cpu(sbi->s_es->s_first_data_block) + (grp * EXT4_BLOCKS_PER_GROUP(sb)); last_block = first_block + EXT4_BLOCKS_PER_GROUP(sb) - 1; @@ -4430,6 +4424,7 @@ static void ext4_clear_journal_err(struct super_block *sb, ext4_commit_super(sb, 1); jbd2_journal_clear_err(journal); + jbd2_journal_update_sb_errno(journal); } } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 8964cf3999b2..324bc0850534 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -383,6 +383,9 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry, struct fuse_entry_out outentry; struct fuse_file *ff; + /* Userspace expects S_IFREG in create mode */ + BUG_ON((mode & S_IFMT) != S_IFREG); + forget = fuse_alloc_forget(); err = -ENOMEM; if (!forget) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 93d8d6c9494d..aba15f1b7ad2 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -703,13 +703,16 @@ static ssize_t fuse_file_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct inode *inode = iocb->ki_filp->f_mapping->host; + struct fuse_conn *fc = get_fuse_conn(inode); - if (pos + iov_length(iov, nr_segs) > i_size_read(inode)) { + /* + * In auto invalidate mode, always update attributes on read. + * Otherwise, only update if we attempt to read past EOF (to ensure + * i_size is up to date). + */ + if (fc->auto_inval_data || + (pos + iov_length(iov, nr_segs) > i_size_read(inode))) { int err; - /* - * If trying to read past EOF, make sure the i_size - * attribute is up-to-date. - */ err = fuse_update_attributes(inode, NULL, iocb->ki_filp, NULL); if (err) return err; @@ -1700,7 +1703,7 @@ static int fuse_verify_ioctl_iov(struct iovec *iov, size_t count) size_t n; u32 max = FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT; - for (n = 0; n < count; n++) { + for (n = 0; n < count; n++, iov++) { if (iov->iov_len > (size_t) max) return -ENOMEM; max -= iov->iov_len; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 771fb6322c07..e24dd74e3068 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -484,6 +484,9 @@ struct fuse_conn { /** Is fallocate not implemented by fs? */ unsigned no_fallocate:1; + /** Use enhanced/automatic page cache invalidation. */ + unsigned auto_inval_data:1; + /** The number of requests waiting for completion */ atomic_t num_waiting; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 1cd61652018c..ce0a2838ccd0 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -197,6 +197,7 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_inode *fi = get_fuse_inode(inode); loff_t oldsize; + struct timespec old_mtime; spin_lock(&fc->lock); if (attr_version != 0 && fi->attr_version > attr_version) { @@ -204,15 +205,35 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr, return; } + old_mtime = inode->i_mtime; fuse_change_attributes_common(inode, attr, attr_valid); oldsize = inode->i_size; i_size_write(inode, attr->size); spin_unlock(&fc->lock); - if (S_ISREG(inode->i_mode) && oldsize != attr->size) { - truncate_pagecache(inode, oldsize, attr->size); - invalidate_inode_pages2(inode->i_mapping); + if (S_ISREG(inode->i_mode)) { + bool inval = false; + + if (oldsize != attr->size) { + truncate_pagecache(inode, oldsize, attr->size); + inval = true; + } else if (fc->auto_inval_data) { + struct timespec new_mtime = { + .tv_sec = attr->mtime, + .tv_nsec = attr->mtimensec, + }; + + /* + * Auto inval mode also checks and invalidates if mtime + * has changed. + */ + if (!timespec_equal(&old_mtime, &new_mtime)) + inval = true; + } + + if (inval) + invalidate_inode_pages2(inode->i_mapping); } } @@ -834,6 +855,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req) fc->big_writes = 1; if (arg->flags & FUSE_DONT_MASK) fc->dont_mask = 1; + if (arg->flags & FUSE_AUTO_INVAL_DATA) + fc->auto_inval_data = 1; } else { ra_pages = fc->max_read / PAGE_CACHE_SIZE; fc->no_lock = 1; @@ -859,7 +882,8 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req) arg->max_readahead = fc->bdi.ra_pages * PAGE_CACHE_SIZE; arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC | FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK | - FUSE_FLOCK_LOCKS; + FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ | + FUSE_FLOCK_LOCKS | FUSE_IOCTL_DIR | FUSE_AUTO_INVAL_DATA; req->in.h.opcode = FUSE_INIT; req->in.numargs = 1; req->in.args[0].size = sizeof(*arg); diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c index 3a56c8d94de0..22255d96b27e 100644 --- a/fs/gfs2/meta_io.c +++ b/fs/gfs2/meta_io.c @@ -52,7 +52,7 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb /* * If it's a fully non-blocking write attempt and we cannot * lock the buffer then redirty the page. Note that this can - * potentially cause a busy-wait loop from pdflush and kswapd + * potentially cause a busy-wait loop from flusher thread and kswapd * activity, but those code paths have their own higher-level * throttling. */ diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index 5fd51a5833ff..b7ec224910c5 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -236,10 +236,10 @@ out: * hfs_mdb_commit() * * Description: - * This updates the MDB on disk (look also at hfs_write_super()). + * This updates the MDB on disk. * It does not check, if the superblock has been modified, or * if the filesystem has been mounted read-only. It is mainly - * called by hfs_write_super() and hfs_btree_extend(). + * called by hfs_sync_fs() and flush_mdb(). * Input Variable(s): * struct hfs_mdb *mdb: Pointer to the hfs MDB * int backup; diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c index 425c2f2cf170..a2862339323b 100644 --- a/fs/jbd/journal.c +++ b/fs/jbd/journal.c @@ -534,8 +534,8 @@ int journal_start_commit(journal_t *journal, tid_t *ptid) ret = 1; } else if (journal->j_committing_transaction) { /* - * If ext3_write_super() recently started a commit, then we - * have to wait for completion of that transaction + * If commit has been started, then we have to wait for + * completion of that transaction. */ if (ptid) *ptid = journal->j_committing_transaction->t_tid; @@ -1113,6 +1113,11 @@ static void mark_journal_empty(journal_t *journal) BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); spin_lock(&journal->j_state_lock); + /* Is it already empty? */ + if (sb->s_start == 0) { + spin_unlock(&journal->j_state_lock); + return; + } jbd_debug(1, "JBD: Marking journal as empty (seq %d)\n", journal->j_tail_sequence); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index e9a3c4c85594..e149b99a7ffb 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -612,8 +612,8 @@ int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid) ret = 1; } else if (journal->j_committing_transaction) { /* - * If ext3_write_super() recently started a commit, then we - * have to wait for completion of that transaction + * If commit has been started, then we have to wait for + * completion of that transaction. */ if (ptid) *ptid = journal->j_committing_transaction->t_tid; @@ -1377,7 +1377,7 @@ static void jbd2_mark_journal_empty(journal_t *journal) * Update a journal's errno. Write updated superblock to disk waiting for IO * to complete. */ -static void jbd2_journal_update_sb_errno(journal_t *journal) +void jbd2_journal_update_sb_errno(journal_t *journal) { journal_superblock_t *sb = journal->j_superblock; @@ -1390,6 +1390,7 @@ static void jbd2_journal_update_sb_errno(journal_t *journal) jbd2_write_superblock(journal, WRITE_SYNC); } +EXPORT_SYMBOL(jbd2_journal_update_sb_errno); /* * Read the superblock for a given journal, performing initial diff --git a/fs/logfs/dev_bdev.c b/fs/logfs/dev_bdev.c index df0de27c2733..e784a217b500 100644 --- a/fs/logfs/dev_bdev.c +++ b/fs/logfs/dev_bdev.c @@ -26,6 +26,7 @@ static int sync_request(struct page *page, struct block_device *bdev, int rw) struct completion complete; bio_init(&bio); + bio.bi_max_vecs = 1; bio.bi_io_vec = &bio_vec; bio_vec.bv_page = page; bio_vec.bv_len = PAGE_SIZE; @@ -95,12 +96,11 @@ static int __bdev_writeseg(struct super_block *sb, u64 ofs, pgoff_t index, struct address_space *mapping = super->s_mapping_inode->i_mapping; struct bio *bio; struct page *page; - struct request_queue *q = bdev_get_queue(sb->s_bdev); - unsigned int max_pages = queue_max_hw_sectors(q) >> (PAGE_SHIFT - 9); + unsigned int max_pages; int i; - if (max_pages > BIO_MAX_PAGES) - max_pages = BIO_MAX_PAGES; + max_pages = min(nr_pages, (size_t) bio_get_nr_vecs(super->s_bdev)); + bio = bio_alloc(GFP_NOFS, max_pages); BUG_ON(!bio); @@ -190,12 +190,11 @@ static int do_erase(struct super_block *sb, u64 ofs, pgoff_t index, { struct logfs_super *super = logfs_super(sb); struct bio *bio; - struct request_queue *q = bdev_get_queue(sb->s_bdev); - unsigned int max_pages = queue_max_hw_sectors(q) >> (PAGE_SHIFT - 9); + unsigned int max_pages; int i; - if (max_pages > BIO_MAX_PAGES) - max_pages = BIO_MAX_PAGES; + max_pages = min(nr_pages, (size_t) bio_get_nr_vecs(super->s_bdev)); + bio = bio_alloc(GFP_NOFS, max_pages); BUG_ON(!bio); diff --git a/fs/logfs/inode.c b/fs/logfs/inode.c index a422f42238b2..6984562738d3 100644 --- a/fs/logfs/inode.c +++ b/fs/logfs/inode.c @@ -156,10 +156,26 @@ static void __logfs_destroy_inode(struct inode *inode) call_rcu(&inode->i_rcu, logfs_i_callback); } +static void __logfs_destroy_meta_inode(struct inode *inode) +{ + struct logfs_inode *li = logfs_inode(inode); + BUG_ON(li->li_block); + call_rcu(&inode->i_rcu, logfs_i_callback); +} + static void logfs_destroy_inode(struct inode *inode) { struct logfs_inode *li = logfs_inode(inode); + if (inode->i_ino < LOGFS_RESERVED_INOS) { + /* + * The reserved inodes are never destroyed unless we are in + * unmont path. + */ + __logfs_destroy_meta_inode(inode); + return; + } + BUG_ON(list_empty(&li->li_freeing_list)); spin_lock(&logfs_inode_lock); li->li_refcount--; @@ -373,8 +389,8 @@ static void logfs_put_super(struct super_block *sb) { struct logfs_super *super = logfs_super(sb); /* kill the meta-inodes */ - iput(super->s_master_inode); iput(super->s_segfile_inode); + iput(super->s_master_inode); iput(super->s_mapping_inode); } diff --git a/fs/logfs/journal.c b/fs/logfs/journal.c index 1e1c369df22b..2a09b8d73989 100644 --- a/fs/logfs/journal.c +++ b/fs/logfs/journal.c @@ -565,7 +565,7 @@ static void write_wbuf(struct super_block *sb, struct logfs_area *area, index = ofs >> PAGE_SHIFT; page_ofs = ofs & (PAGE_SIZE - 1); - page = find_lock_page(mapping, index); + page = find_or_create_page(mapping, index, GFP_NOFS); BUG_ON(!page); memcpy(wbuf, page_address(page) + page_ofs, super->s_writesize); unlock_page(page); diff --git a/fs/logfs/readwrite.c b/fs/logfs/readwrite.c index f1cb512c5019..5be0abef603d 100644 --- a/fs/logfs/readwrite.c +++ b/fs/logfs/readwrite.c @@ -2189,7 +2189,6 @@ void logfs_evict_inode(struct inode *inode) return; } - BUG_ON(inode->i_ino < LOGFS_RESERVED_INOS); page = inode_to_page(inode); BUG_ON(!page); /* FIXME: Use emergency page */ logfs_put_write_page(page); diff --git a/fs/logfs/segment.c b/fs/logfs/segment.c index e28d090c98d6..038da0991794 100644 --- a/fs/logfs/segment.c +++ b/fs/logfs/segment.c @@ -886,7 +886,7 @@ static struct logfs_area *alloc_area(struct super_block *sb) static void map_invalidatepage(struct page *page, unsigned long l) { - BUG(); + return; } static int map_releasepage(struct page *page, gfp_t g) diff --git a/fs/namei.c b/fs/namei.c index 1b464390dde8..dd1ed1b8e98e 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -352,6 +352,7 @@ int __inode_permission(struct inode *inode, int mask) /** * sb_permission - Check superblock-level permissions * @sb: Superblock of inode to check permission on + * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Separate out file-system wide checks from inode-specific permission checks. @@ -656,6 +657,7 @@ int sysctl_protected_hardlinks __read_mostly = 1; /** * may_follow_link - Check symlink following for unsafe situations * @link: The path of the symlink + * @nd: nameidata pathwalk data * * In the case of the sysctl_protected_symlinks sysctl being enabled, * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is @@ -2414,7 +2416,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, goto out; } - mode = op->mode & S_IALLUGO; + mode = op->mode; if ((open_flag & O_CREAT) && !IS_POSIXACL(dir)) mode &= ~current_umask(); @@ -2452,7 +2454,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, } if (open_flag & O_CREAT) { - error = may_o_create(&nd->path, dentry, op->mode); + error = may_o_create(&nd->path, dentry, mode); if (error) { create_error = error; if (open_flag & O_EXCL) @@ -2489,6 +2491,10 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry, dput(dentry); dentry = file->f_path.dentry; } + if (create_error && dentry->d_inode == NULL) { + error = create_error; + goto out; + } goto looked_up; } diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 8bf3a3f6925a..b7db60897f91 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -12,19 +12,19 @@ nfs-$(CONFIG_ROOT_NFS) += nfsroot.o nfs-$(CONFIG_SYSCTL) += sysctl.o nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o -obj-$(CONFIG_NFS_V2) += nfs2.o -nfs2-y := nfs2super.o proc.o nfs2xdr.o +obj-$(CONFIG_NFS_V2) += nfsv2.o +nfsv2-y := nfs2super.o proc.o nfs2xdr.o -obj-$(CONFIG_NFS_V3) += nfs3.o -nfs3-y := nfs3super.o nfs3client.o nfs3proc.o nfs3xdr.o -nfs3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o +obj-$(CONFIG_NFS_V3) += nfsv3.o +nfsv3-y := nfs3super.o nfs3client.o nfs3proc.o nfs3xdr.o +nfsv3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o -obj-$(CONFIG_NFS_V4) += nfs4.o -nfs4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \ +obj-$(CONFIG_NFS_V4) += nfsv4.o +nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \ delegation.o idmap.o callback.o callback_xdr.o callback_proc.o \ nfs4namespace.o nfs4getroot.o nfs4client.o -nfs4-$(CONFIG_SYSCTL) += nfs4sysctl.o -nfs4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o +nfsv4-$(CONFIG_SYSCTL) += nfs4sysctl.o +nfsv4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 9fc0d9dfc91b..99694442b93f 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -105,7 +105,7 @@ struct nfs_subversion *get_nfs_version(unsigned int version) if (IS_ERR(nfs)) { mutex_lock(&nfs_version_mutex); - request_module("nfs%d", version); + request_module("nfsv%d", version); nfs = find_nfs_version(version); mutex_unlock(&nfs_version_mutex); } diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index b701358c39c3..a850079467d8 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -61,6 +61,12 @@ struct idmap { struct mutex idmap_mutex; }; +struct idmap_legacy_upcalldata { + struct rpc_pipe_msg pipe_msg; + struct idmap_msg idmap_msg; + struct idmap *idmap; +}; + /** * nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields * @fattr: fully initialised struct nfs_fattr @@ -324,6 +330,7 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen, ret = nfs_idmap_request_key(&key_type_id_resolver_legacy, name, namelen, type, data, data_size, idmap); + idmap->idmap_key_cons = NULL; mutex_unlock(&idmap->idmap_mutex); } return ret; @@ -380,11 +387,13 @@ static const match_table_t nfs_idmap_tokens = { static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *); static ssize_t idmap_pipe_downcall(struct file *, const char __user *, size_t); +static void idmap_release_pipe(struct inode *); static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *); static const struct rpc_pipe_ops idmap_upcall_ops = { .upcall = rpc_pipe_generic_upcall, .downcall = idmap_pipe_downcall, + .release_pipe = idmap_release_pipe, .destroy_msg = idmap_pipe_destroy_msg, }; @@ -616,7 +625,8 @@ void nfs_idmap_quit(void) nfs_idmap_quit_keyring(); } -static int nfs_idmap_prepare_message(char *desc, struct idmap_msg *im, +static int nfs_idmap_prepare_message(char *desc, struct idmap *idmap, + struct idmap_msg *im, struct rpc_pipe_msg *msg) { substring_t substr; @@ -659,6 +669,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, const char *op, void *aux) { + struct idmap_legacy_upcalldata *data; struct rpc_pipe_msg *msg; struct idmap_msg *im; struct idmap *idmap = (struct idmap *)aux; @@ -666,15 +677,15 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, int ret = -ENOMEM; /* msg and im are freed in idmap_pipe_destroy_msg */ - msg = kmalloc(sizeof(*msg), GFP_KERNEL); - if (!msg) - goto out0; - - im = kmalloc(sizeof(*im), GFP_KERNEL); - if (!im) + data = kmalloc(sizeof(*data), GFP_KERNEL); + if (!data) goto out1; - ret = nfs_idmap_prepare_message(key->description, im, msg); + msg = &data->pipe_msg; + im = &data->idmap_msg; + data->idmap = idmap; + + ret = nfs_idmap_prepare_message(key->description, idmap, im, msg); if (ret < 0) goto out2; @@ -683,15 +694,15 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, ret = rpc_queue_upcall(idmap->idmap_pipe, msg); if (ret < 0) - goto out2; + goto out3; return ret; +out3: + idmap->idmap_key_cons = NULL; out2: - kfree(im); + kfree(data); out1: - kfree(msg); -out0: complete_request_key(cons, ret); return ret; } @@ -749,9 +760,8 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) } if (!(im.im_status & IDMAP_STATUS_SUCCESS)) { - ret = mlen; - complete_request_key(cons, -ENOKEY); - goto out_incomplete; + ret = -ENOKEY; + goto out; } namelen_in = strnlen(im.im_name, IDMAP_NAMESZ); @@ -768,16 +778,32 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) out: complete_request_key(cons, ret); -out_incomplete: return ret; } static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg) { + struct idmap_legacy_upcalldata *data = container_of(msg, + struct idmap_legacy_upcalldata, + pipe_msg); + struct idmap *idmap = data->idmap; + struct key_construction *cons; + if (msg->errno) { + cons = ACCESS_ONCE(idmap->idmap_key_cons); + idmap->idmap_key_cons = NULL; + complete_request_key(cons, msg->errno); + } /* Free memory allocated in nfs_idmap_legacy_upcall() */ - kfree(msg->data); - kfree(msg); + kfree(data); +} + +static void +idmap_release_pipe(struct inode *inode) +{ + struct rpc_inode *rpci = RPC_I(inode); + struct idmap *idmap = (struct idmap *)rpci->private; + idmap->idmap_key_cons = NULL; } int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid) diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 0952c791df36..d6b3b5f2d779 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -69,7 +69,7 @@ do_proc_get_root(struct rpc_clnt *client, struct nfs_fh *fhandle, nfs_fattr_init(info->fattr); status = rpc_call_sync(client, &msg, 0); dprintk("%s: reply fsinfo: %d\n", __func__, status); - if (!(info->fattr->valid & NFS_ATTR_FATTR)) { + if (status == 0 && !(info->fattr->valid & NFS_ATTR_FATTR)) { msg.rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR]; msg.rpc_resp = info->fattr; status = rpc_call_sync(client, &msg, 0); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 3b950dd81e81..da0618aeeadb 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -205,6 +205,9 @@ extern const struct dentry_operations nfs4_dentry_operations; int nfs_atomic_open(struct inode *, struct dentry *, struct file *, unsigned, umode_t, int *); +/* super.c */ +extern struct file_system_type nfs4_fs_type; + /* nfs4namespace.c */ rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *); struct rpc_clnt *nfs4_create_sec_client(struct rpc_clnt *, struct inode *, struct qstr *); diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c index cbcdfaf32505..24eb663f8ed5 100644 --- a/fs/nfs/nfs4client.c +++ b/fs/nfs/nfs4client.c @@ -74,7 +74,7 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) return clp; error: - kfree(clp); + nfs_free_client(clp); return ERR_PTR(err); } diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index a99a8d948721..635274140b18 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3737,9 +3737,10 @@ out: static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size_t pgbase, size_t acl_len) { struct nfs4_cached_acl *acl; + size_t buflen = sizeof(*acl) + acl_len; - if (pages && acl_len <= PAGE_SIZE) { - acl = kmalloc(sizeof(*acl) + acl_len, GFP_KERNEL); + if (pages && buflen <= PAGE_SIZE) { + acl = kmalloc(buflen, GFP_KERNEL); if (acl == NULL) goto out; acl->cached = 1; @@ -3819,7 +3820,7 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu if (ret) goto out_free; - acl_len = res.acl_len - res.acl_data_offset; + acl_len = res.acl_len; if (acl_len > args.acl_len) nfs4_write_cached_acl(inode, NULL, 0, acl_len); else @@ -6223,11 +6224,58 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) dprintk("<-- %s\n", __func__); } +static size_t max_response_pages(struct nfs_server *server) +{ + u32 max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; + return nfs_page_array_len(0, max_resp_sz); +} + +static void nfs4_free_pages(struct page **pages, size_t size) +{ + int i; + + if (!pages) + return; + + for (i = 0; i < size; i++) { + if (!pages[i]) + break; + __free_page(pages[i]); + } + kfree(pages); +} + +static struct page **nfs4_alloc_pages(size_t size, gfp_t gfp_flags) +{ + struct page **pages; + int i; + + pages = kcalloc(size, sizeof(struct page *), gfp_flags); + if (!pages) { + dprintk("%s: can't alloc array of %zu pages\n", __func__, size); + return NULL; + } + + for (i = 0; i < size; i++) { + pages[i] = alloc_page(gfp_flags); + if (!pages[i]) { + dprintk("%s: failed to allocate page\n", __func__); + nfs4_free_pages(pages, size); + return NULL; + } + } + + return pages; +} + static void nfs4_layoutget_release(void *calldata) { struct nfs4_layoutget *lgp = calldata; + struct nfs_server *server = NFS_SERVER(lgp->args.inode); + size_t max_pages = max_response_pages(server); dprintk("--> %s\n", __func__); + nfs4_free_pages(lgp->args.layout.pages, max_pages); put_nfs_open_context(lgp->args.ctx); kfree(calldata); dprintk("<-- %s\n", __func__); @@ -6239,9 +6287,10 @@ static const struct rpc_call_ops nfs4_layoutget_call_ops = { .rpc_release = nfs4_layoutget_release, }; -int nfs4_proc_layoutget(struct nfs4_layoutget *lgp) +void nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) { struct nfs_server *server = NFS_SERVER(lgp->args.inode); + size_t max_pages = max_response_pages(server); struct rpc_task *task; struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTGET], @@ -6259,12 +6308,19 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp) dprintk("--> %s\n", __func__); + lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags); + if (!lgp->args.layout.pages) { + nfs4_layoutget_release(lgp); + return; + } + lgp->args.layout.pglen = max_pages * PAGE_SIZE; + lgp->res.layoutp = &lgp->args.layout; lgp->res.seq_res.sr_slot = NULL; nfs41_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0); task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) - return PTR_ERR(task); + return; status = nfs4_wait_for_completion_rpc_task(task); if (status == 0) status = task->tk_status; @@ -6272,7 +6328,7 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp) status = pnfs_layout_process(lgp); rpc_put_task(task); dprintk("<-- %s status=%d\n", __func__, status); - return status; + return; } static void @@ -6304,12 +6360,8 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) return; } spin_lock(&lo->plh_inode->i_lock); - if (task->tk_status == 0) { - if (lrp->res.lrs_present) { - pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); - } else - BUG_ON(!list_empty(&lo->plh_segs)); - } + if (task->tk_status == 0 && lrp->res.lrs_present) + pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); lo->plh_block_lgets--; spin_unlock(&lo->plh_inode->i_lock); dprintk("<-- %s\n", __func__); diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c index 12a31a9dbcdd..bd61221ad2c5 100644 --- a/fs/nfs/nfs4super.c +++ b/fs/nfs/nfs4super.c @@ -23,14 +23,6 @@ static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type, static struct dentry *nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data); -static struct file_system_type nfs4_fs_type = { - .owner = THIS_MODULE, - .name = "nfs4", - .mount = nfs_fs_mount, - .kill_sb = nfs_kill_super, - .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, -}; - static struct file_system_type nfs4_remote_fs_type = { .owner = THIS_MODULE, .name = "nfs4", @@ -344,14 +336,8 @@ static int __init init_nfs_v4(void) if (err) goto out1; - err = register_filesystem(&nfs4_fs_type); - if (err < 0) - goto out2; - register_nfs_version(&nfs_v4); return 0; -out2: - nfs4_unregister_sysctl(); out1: nfs_idmap_quit(); out: @@ -361,7 +347,6 @@ out: static void __exit exit_nfs_v4(void) { unregister_nfs_version(&nfs_v4); - unregister_filesystem(&nfs4_fs_type); nfs4_unregister_sysctl(); nfs_idmap_quit(); } diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index ca13483edd60..1bfbd67c556d 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -5045,22 +5045,19 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_getaclres *res) { unsigned int savep; - __be32 *bm_p; uint32_t attrlen, bitmap[3] = {0}; int status; - size_t page_len = xdr->buf->page_len; + unsigned int pg_offset; res->acl_len = 0; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) goto out; - bm_p = xdr->p; - res->acl_data_offset = be32_to_cpup(bm_p) + 2; - res->acl_data_offset <<= 2; - /* Check if the acl data starts beyond the allocated buffer */ - if (res->acl_data_offset > page_len) - return -ERANGE; + xdr_enter_page(xdr, xdr->buf->page_len); + + /* Calculate the offset of the page data */ + pg_offset = xdr->buf->head[0].iov_len; if ((status = decode_attr_bitmap(xdr, bitmap)) != 0) goto out; @@ -5074,23 +5071,20 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, /* The bitmap (xdr len + bitmaps) and the attr xdr len words * are stored with the acl data to handle the problem of * variable length bitmaps.*/ - xdr->p = bm_p; + res->acl_data_offset = xdr_stream_pos(xdr) - pg_offset; /* We ignore &savep and don't do consistency checks on * the attr length. Let userspace figure it out.... */ - attrlen += res->acl_data_offset; - if (attrlen > page_len) { + res->acl_len = attrlen; + if (attrlen > (xdr->nwords << 2)) { if (res->acl_flags & NFS4_ACL_LEN_REQUEST) { /* getxattr interface called with a NULL buf */ - res->acl_len = attrlen; goto out; } - dprintk("NFS: acl reply: attrlen %u > page_len %zu\n", - attrlen, page_len); + dprintk("NFS: acl reply: attrlen %u > page_len %u\n", + attrlen, xdr->nwords << 2); return -EINVAL; } - xdr_read_pages(xdr, attrlen); - res->acl_len = attrlen; } else status = -EOPNOTSUPP; diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index f50d3e8d6f22..ea6d111b03e9 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -570,17 +570,66 @@ static bool objio_pg_test(struct nfs_pageio_descriptor *pgio, return false; return pgio->pg_count + req->wb_bytes <= - OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length; + (unsigned long)pgio->pg_layout_private; +} + +void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + pnfs_generic_pg_init_read(pgio, req); + if (unlikely(pgio->pg_lseg == NULL)) + return; /* Not pNFS */ + + pgio->pg_layout_private = (void *) + OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length; +} + +static bool aligned_on_raid_stripe(u64 offset, struct ore_layout *layout, + unsigned long *stripe_end) +{ + u32 stripe_off; + unsigned stripe_size; + + if (layout->raid_algorithm == PNFS_OSD_RAID_0) + return true; + + stripe_size = layout->stripe_unit * + (layout->group_width - layout->parity); + + div_u64_rem(offset, stripe_size, &stripe_off); + if (!stripe_off) + return true; + + *stripe_end = stripe_size - stripe_off; + return false; +} + +void objio_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + unsigned long stripe_end = 0; + + pnfs_generic_pg_init_write(pgio, req); + if (unlikely(pgio->pg_lseg == NULL)) + return; /* Not pNFS */ + + if (req->wb_offset || + !aligned_on_raid_stripe(req->wb_index * PAGE_SIZE, + &OBJIO_LSEG(pgio->pg_lseg)->layout, + &stripe_end)) { + pgio->pg_layout_private = (void *)stripe_end; + } else { + pgio->pg_layout_private = (void *) + OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length; + } } static const struct nfs_pageio_ops objio_pg_read_ops = { - .pg_init = pnfs_generic_pg_init_read, + .pg_init = objio_init_read, .pg_test = objio_pg_test, .pg_doio = pnfs_generic_pg_readpages, }; static const struct nfs_pageio_ops objio_pg_write_ops = { - .pg_init = pnfs_generic_pg_init_write, + .pg_init = objio_init_write, .pg_test = objio_pg_test, .pg_doio = pnfs_generic_pg_writepages, }; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 1a6732ed04a4..311a79681e2b 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -49,6 +49,7 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, hdr->io_start = req_offset(hdr->req); hdr->good_bytes = desc->pg_count; hdr->dreq = desc->pg_dreq; + hdr->layout_private = desc->pg_layout_private; hdr->release = release; hdr->completion_ops = desc->pg_completion_ops; if (hdr->completion_ops->init_hdr) @@ -268,6 +269,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_error = 0; desc->pg_lseg = NULL; desc->pg_dreq = NULL; + desc->pg_layout_private = NULL; } EXPORT_SYMBOL_GPL(nfs_pageio_init); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 76875bfcf19c..2e00feacd4be 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -583,9 +583,6 @@ send_layoutget(struct pnfs_layout_hdr *lo, struct nfs_server *server = NFS_SERVER(ino); struct nfs4_layoutget *lgp; struct pnfs_layout_segment *lseg = NULL; - struct page **pages = NULL; - int i; - u32 max_resp_sz, max_pages; dprintk("--> %s\n", __func__); @@ -594,20 +591,6 @@ send_layoutget(struct pnfs_layout_hdr *lo, if (lgp == NULL) return NULL; - /* allocate pages for xdr post processing */ - max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; - max_pages = nfs_page_array_len(0, max_resp_sz); - - pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags); - if (!pages) - goto out_err_free; - - for (i = 0; i < max_pages; i++) { - pages[i] = alloc_page(gfp_flags); - if (!pages[i]) - goto out_err_free; - } - lgp->args.minlength = PAGE_CACHE_SIZE; if (lgp->args.minlength > range->length) lgp->args.minlength = range->length; @@ -616,39 +599,19 @@ send_layoutget(struct pnfs_layout_hdr *lo, lgp->args.type = server->pnfs_curr_ld->id; lgp->args.inode = ino; lgp->args.ctx = get_nfs_open_context(ctx); - lgp->args.layout.pages = pages; - lgp->args.layout.pglen = max_pages * PAGE_SIZE; lgp->lsegpp = &lseg; lgp->gfp_flags = gfp_flags; /* Synchronously retrieve layout information from server and * store in lseg. */ - nfs4_proc_layoutget(lgp); + nfs4_proc_layoutget(lgp, gfp_flags); if (!lseg) { /* remember that LAYOUTGET failed and suspend trying */ set_bit(lo_fail_bit(range->iomode), &lo->plh_flags); } - /* free xdr pages */ - for (i = 0; i < max_pages; i++) - __free_page(pages[i]); - kfree(pages); - return lseg; - -out_err_free: - /* free any allocated xdr pages, lgp as it's not used */ - if (pages) { - for (i = 0; i < max_pages; i++) { - if (!pages[i]) - break; - __free_page(pages[i]); - } - kfree(pages); - } - kfree(lgp); - return NULL; } /* diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 2c6c80503ba4..745aa1b39e7c 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -172,7 +172,7 @@ extern int nfs4_proc_getdevicelist(struct nfs_server *server, struct pnfs_devicelist *devlist); extern int nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *dev); -extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp); +extern void nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags); extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp); /* pnfs.c */ diff --git a/fs/nfs/super.c b/fs/nfs/super.c index ac6a3c55dce4..239aff7338eb 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -319,6 +319,34 @@ EXPORT_SYMBOL_GPL(nfs_sops); static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *); static int nfs4_validate_mount_data(void *options, struct nfs_parsed_mount_data *args, const char *dev_name); + +struct file_system_type nfs4_fs_type = { + .owner = THIS_MODULE, + .name = "nfs4", + .mount = nfs_fs_mount, + .kill_sb = nfs_kill_super, + .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, +}; +EXPORT_SYMBOL_GPL(nfs4_fs_type); + +static int __init register_nfs4_fs(void) +{ + return register_filesystem(&nfs4_fs_type); +} + +static void unregister_nfs4_fs(void) +{ + unregister_filesystem(&nfs4_fs_type); +} +#else +static int __init register_nfs4_fs(void) +{ + return 0; +} + +static void unregister_nfs4_fs(void) +{ +} #endif static struct shrinker acl_shrinker = { @@ -337,12 +365,18 @@ int __init register_nfs_fs(void) if (ret < 0) goto error_0; - ret = nfs_register_sysctl(); + ret = register_nfs4_fs(); if (ret < 0) goto error_1; + + ret = nfs_register_sysctl(); + if (ret < 0) + goto error_2; register_shrinker(&acl_shrinker); return 0; +error_2: + unregister_nfs4_fs(); error_1: unregister_filesystem(&nfs_fs_type); error_0: @@ -356,6 +390,7 @@ void __exit unregister_nfs_fs(void) { unregister_shrinker(&acl_shrinker); nfs_unregister_sysctl(); + unregister_nfs4_fs(); unregister_filesystem(&nfs_fs_type); } @@ -2645,4 +2680,6 @@ MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 " module_param(send_implementation_id, ushort, 0644); MODULE_PARM_DESC(send_implementation_id, "Send implementation ID with NFSv4.1 exchange_id"); +MODULE_ALIAS("nfs4"); + #endif /* CONFIG_NFS_V4 */ diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 5829d0ce7cfb..e3b55372726c 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -1814,19 +1814,19 @@ int __init nfs_init_writepagecache(void) nfs_wdata_mempool = mempool_create_slab_pool(MIN_POOL_WRITE, nfs_wdata_cachep); if (nfs_wdata_mempool == NULL) - return -ENOMEM; + goto out_destroy_write_cache; nfs_cdata_cachep = kmem_cache_create("nfs_commit_data", sizeof(struct nfs_commit_data), 0, SLAB_HWCACHE_ALIGN, NULL); if (nfs_cdata_cachep == NULL) - return -ENOMEM; + goto out_destroy_write_mempool; nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT, nfs_wdata_cachep); if (nfs_commit_mempool == NULL) - return -ENOMEM; + goto out_destroy_commit_cache; /* * NFS congestion size, scale with available memory. @@ -1849,11 +1849,20 @@ int __init nfs_init_writepagecache(void) nfs_congestion_kb = 256*1024; return 0; + +out_destroy_commit_cache: + kmem_cache_destroy(nfs_cdata_cachep); +out_destroy_write_mempool: + mempool_destroy(nfs_wdata_mempool); +out_destroy_write_cache: + kmem_cache_destroy(nfs_wdata_cachep); + return -ENOMEM; } void nfs_destroy_writepagecache(void) { mempool_destroy(nfs_commit_mempool); + kmem_cache_destroy(nfs_cdata_cachep); mempool_destroy(nfs_wdata_mempool); kmem_cache_destroy(nfs_wdata_cachep); } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index cbaf4f8bb7b7..4c7bd35b1876 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -651,12 +651,12 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c if (clp->cl_minorversion == 0) { if (!clp->cl_cred.cr_principal && - (clp->cl_flavor >= RPC_AUTH_GSS_KRB5)) + (clp->cl_cred.cr_flavor >= RPC_AUTH_GSS_KRB5)) return -EINVAL; args.client_name = clp->cl_cred.cr_principal; args.prognumber = conn->cb_prog, args.protocol = XPRT_TRANSPORT_TCP; - args.authflavor = clp->cl_flavor; + args.authflavor = clp->cl_cred.cr_flavor; clp->cl_cb_ident = conn->cb_ident; } else { if (!conn->cb_xprt) diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index e6173147f982..22bd0a66c356 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -231,7 +231,6 @@ struct nfs4_client { nfs4_verifier cl_verifier; /* generated by client */ time_t cl_time; /* time of last lease renewal */ struct sockaddr_storage cl_addr; /* client ipaddress */ - u32 cl_flavor; /* setclientid pseudoflavor */ struct svc_cred cl_cred; /* setclientid principal */ clientid_t cl_clientid; /* generated by server */ nfs4_verifier cl_confirm; /* generated by server */ diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 6522cac6057c..6a10812711c1 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -676,17 +676,13 @@ static const struct super_operations nilfs_sops = { .alloc_inode = nilfs_alloc_inode, .destroy_inode = nilfs_destroy_inode, .dirty_inode = nilfs_dirty_inode, - /* .write_inode = nilfs_write_inode, */ - /* .drop_inode = nilfs_drop_inode, */ .evict_inode = nilfs_evict_inode, .put_super = nilfs_put_super, - /* .write_super = nilfs_write_super, */ .sync_fs = nilfs_sync_fs, .freeze_fs = nilfs_freeze, .unfreeze_fs = nilfs_unfreeze, .statfs = nilfs_statfs, .remount_fs = nilfs_remount, - /* .umount_begin */ .show_options = nilfs_show_options }; diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h index 6eee4177807b..be1267a34cea 100644 --- a/fs/nilfs2/the_nilfs.h +++ b/fs/nilfs2/the_nilfs.h @@ -107,8 +107,6 @@ struct the_nilfs { * used for * - loading the latest checkpoint exclusively. * - allocating a new full segment. - * - protecting s_dirt in the super_block struct - * (see nilfs_write_super) and the following fields. */ struct buffer_head *ns_sbh[2]; struct nilfs_super_block *ns_sbp[2]; diff --git a/fs/open.c b/fs/open.c index f3d96e7e7b19..e1f2cdb91a4d 100644 --- a/fs/open.c +++ b/fs/open.c @@ -717,7 +717,7 @@ cleanup_all: * here, so just reset the state. */ file_reset_write(f); - mnt_drop_write(f->f_path.mnt); + __mnt_drop_write(f->f_path.mnt); } } cleanup_file: @@ -852,9 +852,10 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o int lookup_flags = 0; int acc_mode; - if (!(flags & O_CREAT)) - mode = 0; - op->mode = mode; + if (flags & O_CREAT) + op->mode = (mode & S_IALLUGO) | S_IFREG; + else + op->mode = 0; /* Must never be set by userspace */ flags &= ~FMODE_NONOTIFY; diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 36a29b753c79..c495a3055e2a 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -1589,10 +1589,10 @@ int __dquot_alloc_space(struct inode *inode, qsize_t number, int flags) goto out; } - down_read(&sb_dqopt(inode->i_sb)->dqptr_sem); for (cnt = 0; cnt < MAXQUOTAS; cnt++) warn[cnt].w_type = QUOTA_NL_NOWARN; + down_read(&sb_dqopt(inode->i_sb)->dqptr_sem); spin_lock(&dq_data_lock); for (cnt = 0; cnt < MAXQUOTAS; cnt++) { if (!dquots[cnt]) diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c index 4c0c7d163d15..a98b7740a0fc 100644 --- a/fs/reiserfs/bitmap.c +++ b/fs/reiserfs/bitmap.c @@ -1334,9 +1334,7 @@ struct buffer_head *reiserfs_read_bitmap_block(struct super_block *sb, else if (bitmap == 0) block = (REISERFS_DISK_OFFSET_IN_BYTES >> sb->s_blocksize_bits) + 1; - reiserfs_write_unlock(sb); bh = sb_bread(sb, block); - reiserfs_write_lock(sb); if (bh == NULL) reiserfs_warning(sb, "sh-2029: %s: bitmap block (#%u) " "reading failed", __func__, block); diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index a6d4268fb6c1..855da58db145 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -76,10 +76,10 @@ void reiserfs_evict_inode(struct inode *inode) ; } out: + reiserfs_write_unlock_once(inode->i_sb, depth); clear_inode(inode); /* note this must go after the journal_end to prevent deadlock */ dquot_drop(inode); inode->i_blocks = 0; - reiserfs_write_unlock_once(inode->i_sb, depth); return; no_delete: diff --git a/fs/super.c b/fs/super.c index b05cf47463d0..0902cfa6a12e 100644 --- a/fs/super.c +++ b/fs/super.c @@ -537,46 +537,6 @@ void drop_super(struct super_block *sb) EXPORT_SYMBOL(drop_super); /** - * sync_supers - helper for periodic superblock writeback - * - * Call the write_super method if present on all dirty superblocks in - * the system. This is for the periodic writeback used by most older - * filesystems. For data integrity superblock writeback use - * sync_filesystems() instead. - * - * Note: check the dirty flag before waiting, so we don't - * hold up the sync while mounting a device. (The newly - * mounted device won't need syncing.) - */ -void sync_supers(void) -{ - struct super_block *sb, *p = NULL; - - spin_lock(&sb_lock); - list_for_each_entry(sb, &super_blocks, s_list) { - if (hlist_unhashed(&sb->s_instances)) - continue; - if (sb->s_op->write_super && sb->s_dirt) { - sb->s_count++; - spin_unlock(&sb_lock); - - down_read(&sb->s_umount); - if (sb->s_root && sb->s_dirt && (sb->s_flags & MS_BORN)) - sb->s_op->write_super(sb); - up_read(&sb->s_umount); - - spin_lock(&sb_lock); - if (p) - __put_super(p); - p = sb; - } - } - if (p) - __put_super(p); - spin_unlock(&sb_lock); -} - -/** * iterate_supers - call function for all active superblocks * @f: function to call * @arg: argument to pass to it diff --git a/fs/ubifs/debug.h b/fs/ubifs/debug.h index 8b8cc4e945f4..760de723dadb 100644 --- a/fs/ubifs/debug.h +++ b/fs/ubifs/debug.h @@ -167,7 +167,7 @@ struct ubifs_global_debug_info { #define ubifs_dbg_msg(type, fmt, ...) \ pr_debug("UBIFS DBG " type ": " fmt "\n", ##__VA_ARGS__) -#define DBG_KEY_BUF_LEN 32 +#define DBG_KEY_BUF_LEN 48 #define ubifs_dbg_msg_key(type, key, fmt, ...) do { \ char __tmp_key_buf[DBG_KEY_BUF_LEN]; \ pr_debug("UBIFS DBG " type ": " fmt "%s\n", ##__VA_ARGS__, \ diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 35389ca2d267..7bd6e72afd11 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -37,11 +37,11 @@ * * A thing to keep in mind: inode @i_mutex is locked in most VFS operations we * implement. However, this is not true for 'ubifs_writepage()', which may be - * called with @i_mutex unlocked. For example, when pdflush is doing background - * write-back, it calls 'ubifs_writepage()' with unlocked @i_mutex. At "normal" - * work-paths the @i_mutex is locked in 'ubifs_writepage()', e.g. in the - * "sys_write -> alloc_pages -> direct reclaim path". So, in 'ubifs_writepage()' - * we are only guaranteed that the page is locked. + * called with @i_mutex unlocked. For example, when flusher thread is doing + * background write-back, it calls 'ubifs_writepage()' with unlocked @i_mutex. + * At "normal" work-paths the @i_mutex is locked in 'ubifs_writepage()', e.g. + * in the "sys_write -> alloc_pages -> direct reclaim path". So, in + * 'ubifs_writepage()' we are only guaranteed that the page is locked. * * Similarly, @i_mutex is not always locked in 'ubifs_readpage()', e.g., the * read-ahead path does not lock it ("sys_read -> generic_file_aio_read -> diff --git a/fs/ubifs/lpt.c b/fs/ubifs/lpt.c index ce33b2beb151..8640920766ed 100644 --- a/fs/ubifs/lpt.c +++ b/fs/ubifs/lpt.c @@ -1749,7 +1749,10 @@ int ubifs_lpt_init(struct ubifs_info *c, int rd, int wr) return 0; out_err: - ubifs_lpt_free(c, 0); + if (wr) + ubifs_lpt_free(c, 1); + if (rd) + ubifs_lpt_free(c, 0); return err; } diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c index c30d976b4be8..edeec499c048 100644 --- a/fs/ubifs/recovery.c +++ b/fs/ubifs/recovery.c @@ -788,7 +788,7 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum, corrupted_rescan: /* Re-scan the corrupted data with verbose messages */ - ubifs_err("corruptio %d", ret); + ubifs_err("corruption %d", ret); ubifs_scan_a_node(c, buf, len, lnum, offs, 1); corrupted: ubifs_scanned_corruption(c, lnum, offs, buf); diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c index eba46d4a7619..94d78fc5d4e0 100644 --- a/fs/ubifs/replay.c +++ b/fs/ubifs/replay.c @@ -1026,7 +1026,6 @@ int ubifs_replay_journal(struct ubifs_info *c) c->replaying = 1; lnum = c->ltail_lnum = c->lhead_lnum; - lnum = UBIFS_LOG_LNUM; do { err = replay_log_leb(c, lnum, 0, c->sbuf); if (err == 1) @@ -1035,7 +1034,7 @@ int ubifs_replay_journal(struct ubifs_info *c) if (err) goto out; lnum = ubifs_next_log_lnum(c, lnum); - } while (lnum != UBIFS_LOG_LNUM); + } while (lnum != c->ltail_lnum); err = replay_buds(c); if (err) diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c index 1c766c39c038..71a197f0f93d 100644 --- a/fs/ubifs/super.c +++ b/fs/ubifs/super.c @@ -303,7 +303,7 @@ static int ubifs_write_inode(struct inode *inode, struct writeback_control *wbc) mutex_lock(&ui->ui_mutex); /* * Due to races between write-back forced by budgeting - * (see 'sync_some_inodes()') and pdflush write-back, the inode may + * (see 'sync_some_inodes()') and background write-back, the inode may * have already been synchronized, do not do this again. This might * also happen if it was synchronized in an VFS operation, e.g. * 'ubifs_link()'. @@ -1157,9 +1157,6 @@ static int check_free_space(struct ubifs_info *c) * * This function mounts UBIFS file system. Returns zero in case of success and * a negative error code in case of failure. - * - * Note, the function does not de-allocate resources it it fails half way - * through, and the caller has to do this instead. */ static int mount_ubifs(struct ubifs_info *c) { diff --git a/fs/udf/inode.c b/fs/udf/inode.c index fafaad795cd6..aa233469b3c1 100644 --- a/fs/udf/inode.c +++ b/fs/udf/inode.c @@ -1124,14 +1124,17 @@ int udf_setsize(struct inode *inode, loff_t newsize) if (err) return err; down_write(&iinfo->i_data_sem); - } else + } else { iinfo->i_lenAlloc = newsize; + goto set_size; + } } err = udf_extend_file(inode, newsize); if (err) { up_write(&iinfo->i_data_sem); return err; } +set_size: truncate_setsize(inode, newsize); up_write(&iinfo->i_data_sem); } else { diff --git a/fs/udf/super.c b/fs/udf/super.c index dcbf98722afc..18fc038a438d 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1344,6 +1344,7 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, udf_err(sb, "error loading logical volume descriptor: " "Partition table too long (%u > %lu)\n", table_len, sb->s_blocksize - sizeof(*lvd)); + ret = 1; goto out_bh; } @@ -1388,8 +1389,10 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block, UDF_ID_SPARABLE, strlen(UDF_ID_SPARABLE))) { if (udf_load_sparable_map(sb, map, - (struct sparablePartitionMap *)gpm) < 0) + (struct sparablePartitionMap *)gpm) < 0) { + ret = 1; goto out_bh; + } } else if (!strncmp(upm2->partIdent.ident, UDF_ID_METADATA, strlen(UDF_ID_METADATA))) { @@ -2000,6 +2003,8 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent) if (!silent) pr_notice("Rescanning with blocksize %d\n", UDF_DEFAULT_BLOCKSIZE); + brelse(sbi->s_lvid_bh); + sbi->s_lvid_bh = NULL; uopt.blocksize = UDF_DEFAULT_BLOCKSIZE; ret = udf_load_vrs(sb, &uopt, silent, &fileset); } diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c index f9c3fe304a17..69cf4fcde03e 100644 --- a/fs/xfs/xfs_discard.c +++ b/fs/xfs/xfs_discard.c @@ -179,12 +179,14 @@ xfs_ioc_trim( * used by the fstrim application. In the end it really doesn't * matter as trimming blocks is an advisory interface. */ + if (range.start >= XFS_FSB_TO_B(mp, mp->m_sb.sb_dblocks) || + range.minlen > XFS_FSB_TO_B(mp, XFS_ALLOC_AG_MAX_USABLE(mp))) + return -XFS_ERROR(EINVAL); + start = BTOBB(range.start); end = start + BTOBBT(range.len) - 1; minlen = BTOBB(max_t(u64, granularity, range.minlen)); - if (XFS_BB_TO_FSB(mp, start) >= mp->m_sb.sb_dblocks) - return -XFS_ERROR(EINVAL); if (end > XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1) end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks)- 1; diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c index 21e37b55f7e5..5aceb3f8ecd6 100644 --- a/fs/xfs/xfs_ialloc.c +++ b/fs/xfs/xfs_ialloc.c @@ -962,23 +962,22 @@ xfs_dialloc( if (!pag->pagi_freecount && !okalloc) goto nextag; + /* + * Then read in the AGI buffer and recheck with the AGI buffer + * lock held. + */ error = xfs_ialloc_read_agi(mp, tp, agno, &agbp); if (error) goto out_error; - /* - * Once the AGI has been read in we have to recheck - * pagi_freecount with the AGI buffer lock held. - */ if (pag->pagi_freecount) { xfs_perag_put(pag); goto out_alloc; } - if (!okalloc) { - xfs_trans_brelse(tp, agbp); - goto nextag; - } + if (!okalloc) + goto nextag_relse_buffer; + error = xfs_ialloc_ag_alloc(tp, agbp, &ialloced); if (error) { @@ -1007,6 +1006,8 @@ xfs_dialloc( return 0; } +nextag_relse_buffer: + xfs_trans_brelse(tp, agbp); nextag: xfs_perag_put(pag); if (++agno == mp->m_sb.sb_agcount) diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index 92d4331cd4f1..ca28a4ba4b54 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -857,7 +857,7 @@ xfs_rtbuf_get( xfs_buf_t *bp; /* block buffer, result */ xfs_inode_t *ip; /* bitmap or summary inode */ xfs_bmbt_irec_t map; - int nmap; + int nmap = 1; int error; /* error value */ ip = issum ? mp->m_rsumip : mp->m_rbmip; |
