diff options
Diffstat (limited to 'fs')
87 files changed, 952 insertions, 515 deletions
diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index 4438637c8900..6d6fc85835d4 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -115,6 +115,10 @@ config BTRFS_EXPERIMENTAL - extent tree v2 - complex rework of extent tracking - - large folio support + - large folio and block size (> page size) support + + - shutdown ioctl and auto-degradation support + + - asynchronous checksum generation for data writes If unsure, say N. diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index ce6e9f8812e0..4b7d9015e0da 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -152,37 +152,39 @@ again: return ERR_PTR(-ENOMEM); btrfs_init_delayed_node(node, root, ino); + /* Cached in the inode and can be accessed. */ + refcount_set(&node->refs, 2); + btrfs_delayed_node_ref_tracker_alloc(node, tracker, GFP_NOFS); + btrfs_delayed_node_ref_tracker_alloc(node, &node->inode_cache_tracker, GFP_NOFS); + /* Allocate and reserve the slot, from now it can return a NULL from xa_load(). */ ret = xa_reserve(&root->delayed_nodes, ino, GFP_NOFS); - if (ret == -ENOMEM) { - btrfs_delayed_node_ref_tracker_dir_exit(node); - kmem_cache_free(delayed_node_cache, node); - return ERR_PTR(-ENOMEM); - } + if (ret == -ENOMEM) + goto cleanup; + xa_lock(&root->delayed_nodes); ptr = xa_load(&root->delayed_nodes, ino); if (ptr) { /* Somebody inserted it, go back and read it. */ xa_unlock(&root->delayed_nodes); - btrfs_delayed_node_ref_tracker_dir_exit(node); - kmem_cache_free(delayed_node_cache, node); - node = NULL; - goto again; + goto cleanup; } ptr = __xa_store(&root->delayed_nodes, ino, node, GFP_ATOMIC); ASSERT(xa_err(ptr) != -EINVAL); ASSERT(xa_err(ptr) != -ENOMEM); ASSERT(ptr == NULL); - - /* Cached in the inode and can be accessed. */ - refcount_set(&node->refs, 2); - btrfs_delayed_node_ref_tracker_alloc(node, tracker, GFP_ATOMIC); - btrfs_delayed_node_ref_tracker_alloc(node, &node->inode_cache_tracker, GFP_ATOMIC); - btrfs_inode->delayed_node = node; xa_unlock(&root->delayed_nodes); return node; +cleanup: + btrfs_delayed_node_ref_tracker_free(node, tracker); + btrfs_delayed_node_ref_tracker_free(node, &node->inode_cache_tracker); + btrfs_delayed_node_ref_tracker_dir_exit(node); + kmem_cache_free(delayed_node_cache, node); + if (ret) + return ERR_PTR(ret); + goto again; } /* diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 89149fac804c..89022e9f393b 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1661,7 +1661,7 @@ static void backup_super_roots(struct btrfs_fs_info *info) btrfs_set_backup_chunk_root_level(root_backup, btrfs_header_level(info->chunk_root->node)); - if (!btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE)) { + if (!btrfs_fs_incompat(info, EXTENT_TREE_V2)) { struct btrfs_root *extent_root = btrfs_extent_root(info, 0); struct btrfs_root *csum_root = btrfs_csum_root(info, 0); @@ -2255,6 +2255,7 @@ static int btrfs_read_roots(struct btrfs_fs_info *fs_info) BTRFS_DATA_RELOC_TREE_OBJECTID, true); if (IS_ERR(root)) { if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) { + location.objectid = BTRFS_DATA_RELOC_TREE_OBJECTID; ret = PTR_ERR(root); goto out; } @@ -3254,6 +3255,15 @@ int btrfs_check_features(struct btrfs_fs_info *fs_info, bool is_rw_mount) return 0; } +static bool fs_is_full_ro(const struct btrfs_fs_info *fs_info) +{ + if (!sb_rdonly(fs_info->sb)) + return false; + if (unlikely(fs_info->mount_opt & BTRFS_MOUNT_FULL_RO_MASK)) + return true; + return false; +} + int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices) { u32 sectorsize; @@ -3362,6 +3372,10 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_ERROR) WRITE_ONCE(fs_info->fs_error, -EUCLEAN); + /* If the fs has any rescue options, no transaction is allowed. */ + if (fs_is_full_ro(fs_info)) + WRITE_ONCE(fs_info->fs_error, -EROFS); + /* Set up fs_info before parsing mount options */ nodesize = btrfs_super_nodesize(disk_super); sectorsize = btrfs_super_sectorsize(disk_super); @@ -3488,6 +3502,10 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device fs_info->generation == btrfs_super_uuid_tree_generation(disk_super)) set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags); + if (unlikely(btrfs_verify_dev_items(fs_info))) { + ret = -EUCLEAN; + goto fail_block_groups; + } ret = btrfs_verify_dev_extents(fs_info); if (ret) { btrfs_err(fs_info, diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 629fd5af4286..a4b74023618d 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -1728,7 +1728,7 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, struct btrfs_ordered_extent *ordered; ordered = btrfs_lookup_first_ordered_range(inode, cur, - folio_end - cur); + fs_info->sectorsize); /* * We have just run delalloc before getting here, so * there must be an ordered extent. @@ -1742,7 +1742,7 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, btrfs_put_ordered_extent(ordered); btrfs_mark_ordered_io_finished(inode, folio, cur, - end - cur, true); + fs_info->sectorsize, true); /* * This range is beyond i_size, thus we don't need to * bother writing back. @@ -1751,8 +1751,8 @@ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, * writeback the sectors with subpage dirty bits, * causing writeback without ordered extent. */ - btrfs_folio_clear_dirty(fs_info, folio, cur, end - cur); - break; + btrfs_folio_clear_dirty(fs_info, folio, cur, fs_info->sectorsize); + continue; } ret = submit_one_sector(inode, folio, cur, bio_ctrl, i_size); if (unlikely(ret < 0)) { diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h index 0f7e1ef27891..8ffbc40ebe45 100644 --- a/fs/btrfs/fs.h +++ b/fs/btrfs/fs.h @@ -264,6 +264,14 @@ enum { BTRFS_MOUNT_REF_TRACKER = (1ULL << 33), }; +/* These mount options require a full read-only fs, no new transaction is allowed. */ +#define BTRFS_MOUNT_FULL_RO_MASK \ + (BTRFS_MOUNT_NOLOGREPLAY | \ + BTRFS_MOUNT_IGNOREBADROOTS | \ + BTRFS_MOUNT_IGNOREDATACSUMS | \ + BTRFS_MOUNT_IGNOREMETACSUMS | \ + BTRFS_MOUNT_IGNORESUPERFLAGS) + /* * Compat flags that we support. If any incompat flags are set other than the * ones specified below then we will fail to mount diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 317db7d10a21..a2b5b440637e 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -481,13 +481,15 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans, ASSERT(size <= sectorsize); /* - * The compressed size also needs to be no larger than a sector. - * That's also why we only need one page as the parameter. + * The compressed size also needs to be no larger than a page. + * That's also why we only need one folio as the parameter. */ - if (compressed_folio) + if (compressed_folio) { ASSERT(compressed_size <= sectorsize); - else + ASSERT(compressed_size <= PAGE_SIZE); + } else { ASSERT(compressed_size == 0); + } if (compressed_size && compressed_folio) cur_size = compressed_size; @@ -574,6 +576,18 @@ static bool can_cow_file_range_inline(struct btrfs_inode *inode, if (offset != 0) return false; + /* + * Even for bs > ps cases, cow_file_range_inline() can only accept a + * single folio. + * + * This can be problematic and cause access beyond page boundary if a + * page sized folio is passed into that function. + * And encoded write is doing exactly that. + * So here limits the inlined extent size to PAGE_SIZE. + */ + if (size > PAGE_SIZE || compressed_size > PAGE_SIZE) + return false; + /* Inline extents are limited to sectorsize. */ if (size > fs_info->sectorsize) return false; @@ -618,19 +632,22 @@ static noinline int __cow_file_range_inline(struct btrfs_inode *inode, struct btrfs_drop_extents_args drop_args = { 0 }; struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; - struct btrfs_trans_handle *trans; + struct btrfs_trans_handle *trans = NULL; u64 data_len = (compressed_size ?: size); int ret; struct btrfs_path *path; path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + if (!path) { + ret = -ENOMEM; + goto out; + } trans = btrfs_join_transaction(root); if (IS_ERR(trans)) { - btrfs_free_path(path); - return PTR_ERR(trans); + ret = PTR_ERR(trans); + trans = NULL; + goto out; } trans->block_rsv = &inode->block_rsv; @@ -674,10 +691,15 @@ out: * it won't count as data extent, free them directly here. * And at reserve time, it's always aligned to page size, so * just free one page here. + * + * If we fallback to non-inline (ret == 1) due to -ENOSPC, then we need + * to keep the data reservation. */ - btrfs_qgroup_free_data(inode, NULL, 0, fs_info->sectorsize, NULL); + if (ret <= 0) + btrfs_qgroup_free_data(inode, NULL, 0, fs_info->sectorsize, NULL); btrfs_free_path(path); - btrfs_end_transaction(trans); + if (trans) + btrfs_end_transaction(trans); return ret; } @@ -4026,11 +4048,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path btrfs_set_inode_mapping_order(inode); cache_index: - ret = btrfs_init_file_extent_tree(inode); - if (ret) - goto out; - btrfs_inode_set_file_extent_range(inode, 0, - round_up(i_size_read(vfs_inode), fs_info->sectorsize)); /* * If we were modified in the current generation and evicted from memory * and then re-read we need to do a full sync since we don't have any @@ -4117,6 +4134,20 @@ cache_acl: btrfs_ino(inode), btrfs_root_id(root), ret); } + /* + * We don't need the path anymore, so release it to avoid holding a read + * lock on a leaf while calling btrfs_init_file_extent_tree(), which can + * allocate memory that triggers reclaim (GFP_KERNEL) and cause a locking + * dependency. + */ + btrfs_release_path(path); + + ret = btrfs_init_file_extent_tree(inode); + if (ret) + goto out; + btrfs_inode_set_file_extent_range(inode, 0, + round_up(i_size_read(vfs_inode), fs_info->sectorsize)); + if (!maybe_acls) cache_no_acl(vfs_inode); @@ -4149,6 +4180,15 @@ cache_acl: return 0; out: + /* + * We may have a read locked leaf and iget_failed() triggers inode + * eviction which needs to release the delayed inode and that needs + * to lock the delayed inode's mutex. This can cause a ABBA deadlock + * with a task running delayed items, as that require first locking + * the delayed inode's mutex and then modifying its subvolume btree. + * So release the path before iget_failed(). + */ + btrfs_release_path(path); iget_failed(vfs_inode); return ret; } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index d9d8d9968a58..206587820fec 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -3208,9 +3208,15 @@ static int qgroup_snapshot_quick_inherit(struct btrfs_fs_info *fs_info, { struct btrfs_qgroup *src; struct btrfs_qgroup *parent; + struct btrfs_qgroup *qgroup; struct btrfs_qgroup_list *list; + LIST_HEAD(qgroup_list); + const u32 nodesize = fs_info->nodesize; int nr_parents = 0; + if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_FULL) + return 0; + src = find_qgroup_rb(fs_info, srcid); if (!src) return -ENOENT; @@ -3245,8 +3251,19 @@ static int qgroup_snapshot_quick_inherit(struct btrfs_fs_info *fs_info, if (parent->excl != parent->rfer) return 1; - parent->excl += fs_info->nodesize; - parent->rfer += fs_info->nodesize; + qgroup_iterator_add(&qgroup_list, parent); + list_for_each_entry(qgroup, &qgroup_list, iterator) { + qgroup->rfer += nodesize; + qgroup->rfer_cmpr += nodesize; + qgroup->excl += nodesize; + qgroup->excl_cmpr += nodesize; + qgroup_dirty(fs_info, qgroup); + + /* Append parent qgroups to @qgroup_list. */ + list_for_each_entry(list, &qgroup->groups, next_group) + qgroup_iterator_add(&qgroup_list, list->group); + } + qgroup_iterator_clean(&qgroup_list); return 0; } diff --git a/fs/btrfs/reflink.c b/fs/btrfs/reflink.c index b5fe95baf92e..58dc3e5057ce 100644 --- a/fs/btrfs/reflink.c +++ b/fs/btrfs/reflink.c @@ -705,7 +705,6 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, struct inode *src = file_inode(file_src); struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); int ret; - int wb_ret; u64 len = olen; u64 bs = fs_info->sectorsize; u64 end; @@ -750,25 +749,29 @@ static noinline int btrfs_clone_files(struct file *file, struct file *file_src, btrfs_lock_extent(&BTRFS_I(inode)->io_tree, destoff, end, &cached_state); ret = btrfs_clone(src, inode, off, olen, len, destoff, 0); btrfs_unlock_extent(&BTRFS_I(inode)->io_tree, destoff, end, &cached_state); + if (ret < 0) + return ret; /* * We may have copied an inline extent into a page of the destination - * range, so wait for writeback to complete before truncating pages + * range, so wait for writeback to complete before invalidating pages * from the page cache. This is a rare case. */ - wb_ret = btrfs_wait_ordered_range(BTRFS_I(inode), destoff, len); - ret = ret ? ret : wb_ret; + ret = btrfs_wait_ordered_range(BTRFS_I(inode), destoff, len); + if (ret < 0) + return ret; + /* - * Truncate page cache pages so that future reads will see the cloned - * data immediately and not the previous data. + * Invalidate page cache so that future reads will see the cloned data + * immediately and not the previous data. */ - truncate_inode_pages_range(&inode->i_data, - round_down(destoff, PAGE_SIZE), - round_up(destoff + len, PAGE_SIZE) - 1); + ret = filemap_invalidate_inode(inode, false, destoff, end); + if (ret < 0) + return ret; btrfs_btree_balance_dirty(fs_info); - return ret; + return 0; } static int btrfs_remap_file_range_prep(struct file *file_in, loff_t pos_in, diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 2522faa97478..d8127a7120c2 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -6383,6 +6383,8 @@ static int range_is_hole_in_parent(struct send_ctx *sctx, extent_end = btrfs_file_extent_end(path); if (extent_end <= start) goto next; + if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) + return 0; if (btrfs_file_extent_disk_bytenr(leaf, fi) == 0) { search_start = extent_end; goto next; diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 6babbe333741..3f08e450f796 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -306,18 +306,22 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags) 0); if (ret) - return ret; + goto out_free; } ret = btrfs_sysfs_add_space_info_type(space_info); if (ret) - return ret; + goto out_free; list_add(&space_info->list, &info->space_info); if (flags & BTRFS_BLOCK_GROUP_DATA) info->data_sinfo = space_info; return ret; + +out_free: + kfree(space_info); + return ret; } int btrfs_init_space_info(struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 1999533b52be..af56fdbba65d 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -736,14 +736,12 @@ bool btrfs_check_options(const struct btrfs_fs_info *info, */ void btrfs_set_free_space_cache_settings(struct btrfs_fs_info *fs_info) { - if (fs_info->sectorsize < PAGE_SIZE) { + if (fs_info->sectorsize != PAGE_SIZE && btrfs_test_opt(fs_info, SPACE_CACHE)) { + btrfs_info(fs_info, + "forcing free space tree for sector size %u with page size %lu", + fs_info->sectorsize, PAGE_SIZE); btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE); - if (!btrfs_test_opt(fs_info, FREE_SPACE_TREE)) { - btrfs_info(fs_info, - "forcing free space tree for sector size %u with page size %lu", - fs_info->sectorsize, PAGE_SIZE); - btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE); - } + btrfs_set_opt(fs_info->mount_opt, FREE_SPACE_TREE); } /* diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 1f64c132b387..4b3c2acac51a 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -26,7 +26,6 @@ #include "misc.h" #include "fs.h" #include "accessors.h" -#include "zoned.h" /* * Structure name Path @@ -1189,56 +1188,6 @@ static ssize_t btrfs_commit_stats_store(struct kobject *kobj, } BTRFS_ATTR_RW(, commit_stats, btrfs_commit_stats_show, btrfs_commit_stats_store); -static ssize_t btrfs_zoned_stats_show(struct kobject *kobj, - struct kobj_attribute *a, char *buf) -{ - struct btrfs_fs_info *fs_info = to_fs_info(kobj); - struct btrfs_block_group *bg; - size_t ret = 0; - - - if (!btrfs_is_zoned(fs_info)) - return ret; - - spin_lock(&fs_info->zone_active_bgs_lock); - ret += sysfs_emit_at(buf, ret, "active block-groups: %zu\n", - list_count_nodes(&fs_info->zone_active_bgs)); - spin_unlock(&fs_info->zone_active_bgs_lock); - - mutex_lock(&fs_info->reclaim_bgs_lock); - spin_lock(&fs_info->unused_bgs_lock); - ret += sysfs_emit_at(buf, ret, "\treclaimable: %zu\n", - list_count_nodes(&fs_info->reclaim_bgs)); - ret += sysfs_emit_at(buf, ret, "\tunused: %zu\n", - list_count_nodes(&fs_info->unused_bgs)); - spin_unlock(&fs_info->unused_bgs_lock); - mutex_unlock(&fs_info->reclaim_bgs_lock); - - ret += sysfs_emit_at(buf, ret, "\tneed reclaim: %s\n", - str_true_false(btrfs_zoned_should_reclaim(fs_info))); - - if (fs_info->data_reloc_bg) - ret += sysfs_emit_at(buf, ret, - "data relocation block-group: %llu\n", - fs_info->data_reloc_bg); - if (fs_info->treelog_bg) - ret += sysfs_emit_at(buf, ret, - "tree-log block-group: %llu\n", - fs_info->treelog_bg); - - spin_lock(&fs_info->zone_active_bgs_lock); - ret += sysfs_emit_at(buf, ret, "active zones:\n"); - list_for_each_entry(bg, &fs_info->zone_active_bgs, active_bg_list) { - ret += sysfs_emit_at(buf, ret, - "\tstart: %llu, wp: %llu used: %llu, reserved: %llu, unusable: %llu\n", - bg->start, bg->alloc_offset, bg->used, - bg->reserved, bg->zone_unusable); - } - spin_unlock(&fs_info->zone_active_bgs_lock); - return ret; -} -BTRFS_ATTR(, zoned_stats, btrfs_zoned_stats_show); - static ssize_t btrfs_clone_alignment_show(struct kobject *kobj, struct kobj_attribute *a, char *buf) { @@ -1651,7 +1600,6 @@ static const struct attribute *btrfs_attrs[] = { BTRFS_ATTR_PTR(, bg_reclaim_threshold), BTRFS_ATTR_PTR(, commit_stats), BTRFS_ATTR_PTR(, temp_fsid), - BTRFS_ATTR_PTR(, zoned_stats), #ifdef CONFIG_BTRFS_EXPERIMENTAL BTRFS_ATTR_PTR(, offload_csum), #endif diff --git a/fs/btrfs/tests/extent-map-tests.c b/fs/btrfs/tests/extent-map-tests.c index 0b9f25dd1a68..aabf825e8d7b 100644 --- a/fs/btrfs/tests/extent-map-tests.c +++ b/fs/btrfs/tests/extent-map-tests.c @@ -1059,6 +1059,7 @@ static int test_rmap_block(struct btrfs_fs_info *fs_info, if (out_stripe_len != BTRFS_STRIPE_LEN) { test_err("calculated stripe length doesn't match"); + ret = -EINVAL; goto out; } @@ -1066,12 +1067,14 @@ static int test_rmap_block(struct btrfs_fs_info *fs_info, for (i = 0; i < out_ndaddrs; i++) test_msg("mapped %llu", logical[i]); test_err("unexpected number of mapped addresses: %d", out_ndaddrs); + ret = -EINVAL; goto out; } for (i = 0; i < out_ndaddrs; i++) { if (logical[i] != test->mapped_logical[i]) { test_err("unexpected logical address mapped"); + ret = -EINVAL; goto out; } } diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c index e9124605974b..0fcc31beeffe 100644 --- a/fs/btrfs/tests/qgroup-tests.c +++ b/fs/btrfs/tests/qgroup-tests.c @@ -517,11 +517,11 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize) tmp_root->root_key.objectid = BTRFS_FS_TREE_OBJECTID; root->fs_info->fs_root = tmp_root; ret = btrfs_insert_fs_root(root->fs_info, tmp_root); + btrfs_put_root(tmp_root); if (ret) { test_err("couldn't insert fs root %d", ret); goto out; } - btrfs_put_root(tmp_root); tmp_root = btrfs_alloc_dummy_root(fs_info); if (IS_ERR(tmp_root)) { @@ -532,11 +532,11 @@ int btrfs_test_qgroups(u32 sectorsize, u32 nodesize) tmp_root->root_key.objectid = BTRFS_FIRST_FREE_OBJECTID; ret = btrfs_insert_fs_root(root->fs_info, tmp_root); + btrfs_put_root(tmp_root); if (ret) { - test_err("couldn't insert fs root %d", ret); + test_err("couldn't insert subvolume root %d", ret); goto out; } - btrfs_put_root(tmp_root); test_msg("running qgroup tests"); ret = test_no_shared_qgroup(root, sectorsize, nodesize); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 05ee4391c83a..bd03f465e2d3 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -520,13 +520,14 @@ static inline int is_transaction_blocked(struct btrfs_transaction *trans) * when this is done, it is safe to start a new transaction, but the current * transaction might not be fully on disk. */ -static void wait_current_trans(struct btrfs_fs_info *fs_info) +static void wait_current_trans(struct btrfs_fs_info *fs_info, unsigned int type) { struct btrfs_transaction *cur_trans; spin_lock(&fs_info->trans_lock); cur_trans = fs_info->running_transaction; - if (cur_trans && is_transaction_blocked(cur_trans)) { + if (cur_trans && is_transaction_blocked(cur_trans) && + (btrfs_blocked_trans_types[cur_trans->state] & type)) { refcount_inc(&cur_trans->use_count); spin_unlock(&fs_info->trans_lock); @@ -701,12 +702,12 @@ again: sb_start_intwrite(fs_info->sb); if (may_wait_transaction(fs_info, type)) - wait_current_trans(fs_info); + wait_current_trans(fs_info, type); do { ret = join_transaction(fs_info, type); if (ret == -EBUSY) { - wait_current_trans(fs_info); + wait_current_trans(fs_info, type); if (unlikely(type == TRANS_ATTACH || type == TRANS_JOIN_NOSTART)) ret = -ENOENT; @@ -1003,7 +1004,7 @@ out: void btrfs_throttle(struct btrfs_fs_info *fs_info) { - wait_current_trans(fs_info); + wait_current_trans(fs_info, TRANS_START); } bool btrfs_should_end_transaction(struct btrfs_trans_handle *trans) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 31edc93a383e..6cffcf0c3e7a 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -190,7 +190,7 @@ static void do_abort_log_replay(struct walk_control *wc, const char *function, btrfs_abort_transaction(wc->trans, error); - if (wc->subvol_path->nodes[0]) { + if (wc->subvol_path && wc->subvol_path->nodes[0]) { btrfs_crit(fs_info, "subvolume (root %llu) leaf currently being processed:", btrfs_root_id(wc->root)); @@ -2798,7 +2798,7 @@ static int replay_one_buffer(struct extent_buffer *eb, nritems = btrfs_header_nritems(eb); for (wc->log_slot = 0; wc->log_slot < nritems; wc->log_slot++) { - struct btrfs_inode_item *inode_item; + struct btrfs_inode_item *inode_item = NULL; btrfs_item_key_to_cpu(eb, &wc->log_key, wc->log_slot); @@ -6341,10 +6341,8 @@ again: * and no keys greater than that, so bail out. */ break; - } else if ((min_key->type == BTRFS_INODE_REF_KEY || - min_key->type == BTRFS_INODE_EXTREF_KEY) && - (inode->generation == trans->transid || - ctx->logging_conflict_inodes)) { + } else if (min_key->type == BTRFS_INODE_REF_KEY || + min_key->type == BTRFS_INODE_EXTREF_KEY) { u64 other_ino = 0; u64 other_parent = 0; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 13c514684cfb..8a08412f3529 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1364,7 +1364,9 @@ struct btrfs_super_block *btrfs_read_disk_super(struct block_device *bdev, (bytenr + BTRFS_SUPER_INFO_SIZE) >> PAGE_SHIFT); } + filemap_invalidate_lock(mapping); page = read_cache_page_gfp(mapping, bytenr >> PAGE_SHIFT, GFP_NOFS); + filemap_invalidate_unlock(mapping); if (IS_ERR(page)) return ERR_CAST(page); @@ -7257,6 +7259,7 @@ static int read_one_dev(struct extent_buffer *leaf, return -EINVAL; } } + set_bit(BTRFS_DEV_STATE_ITEM_FOUND, &device->dev_state); set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); if (test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state) && !test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) { @@ -8083,6 +8086,45 @@ int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info) } /* + * Ensure that all devices registered in the fs have their device items in the + * chunk tree. + * + * Return true if unexpected device is found. + * Return false otherwise. + */ +bool btrfs_verify_dev_items(const struct btrfs_fs_info *fs_info) +{ + struct btrfs_fs_devices *seed_devs; + struct btrfs_device *dev; + bool ret = false; + + mutex_lock(&uuid_mutex); + list_for_each_entry(dev, &fs_info->fs_devices->devices, dev_list) { + if (!test_bit(BTRFS_DEV_STATE_ITEM_FOUND, &dev->dev_state)) { + btrfs_err(fs_info, + "devid %llu path %s is registered but not found in chunk tree", + dev->devid, btrfs_dev_name(dev)); + ret = true; + } + } + list_for_each_entry(seed_devs, &fs_info->fs_devices->seed_list, seed_list) { + list_for_each_entry(dev, &seed_devs->devices, dev_list) { + if (!test_bit(BTRFS_DEV_STATE_ITEM_FOUND, &dev->dev_state)) { + btrfs_err(fs_info, + "devid %llu path %s is registered but not found in chunk tree", + dev->devid, btrfs_dev_name(dev)); + ret = true; + } + } + } + mutex_unlock(&uuid_mutex); + if (ret) + btrfs_err(fs_info, +"remove the above devices or use 'btrfs device scan --forget <dev>' to unregister them before mount"); + return ret; +} + +/* * Check whether the given block group or device is pinned by any inode being * used as a swapfile. */ diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 34b854c1a303..f20abeb16bce 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -100,6 +100,9 @@ enum btrfs_raid_types { #define BTRFS_DEV_STATE_FLUSH_SENT (4) #define BTRFS_DEV_STATE_NO_READA (5) +/* Set when the device item is found in chunk tree, used to catch unexpected registered device. */ +#define BTRFS_DEV_STATE_ITEM_FOUND (7) + /* Special value encoding failure to write primary super block. */ #define BTRFS_SUPER_PRIMARY_WRITE_ERROR (INT_MAX / 2) @@ -893,6 +896,7 @@ enum btrfs_raid_types __attribute_const__ btrfs_bg_flags_to_raid_index(u64 flags int btrfs_bg_type_to_factor(u64 flags); const char *btrfs_bg_type_to_raid_name(u64 flags); int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info); +bool btrfs_verify_dev_items(const struct btrfs_fs_info *fs_info); bool btrfs_repair_one_zone(struct btrfs_fs_info *fs_info, u64 logical); bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr); diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 4b263c328ed2..4005d21cf009 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -841,8 +841,10 @@ int __printf(2, 3) debugfs_change_name(struct dentry *dentry, const char *fmt, . rd.new_parent = rd.old_parent; rd.flags = RENAME_NOREPLACE; target = lookup_noperm_unlocked(&QSTR(new_name), rd.new_parent); - if (IS_ERR(target)) - return PTR_ERR(target); + if (IS_ERR(target)) { + error = PTR_ERR(target); + goto out_free; + } error = start_renaming_two_dentries(&rd, dentry, target); if (error) { @@ -862,6 +864,7 @@ int __printf(2, 3) debugfs_change_name(struct dentry *dentry, const char *fmt, . out: dput(rd.old_parent); dput(target); +out_free: kfree_const(new_name); return error; } diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 3978248247dc..8ab014db3e03 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -533,6 +533,7 @@ static struct dentry *ecryptfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, fsstack_copy_inode_size(dir, lower_dir); set_nlink(dir, lower_dir->i_nlink); out: + dput(lower_dir_dentry); end_creating(lower_dentry); if (d_really_is_negative(dentry)) d_drop(dentry); @@ -584,7 +585,7 @@ ecryptfs_mknod(struct mnt_idmap *idmap, struct inode *dir, fsstack_copy_attr_times(dir, lower_dir); fsstack_copy_inode_size(dir, lower_dir); out: - end_removing(lower_dentry); + end_creating(lower_dentry); if (d_really_is_negative(dentry)) d_drop(dentry); return rc; diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 937a215f626c..5136cda5972a 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -644,14 +644,21 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) * fs contexts (including its own) due to self-controlled RO * accesses/contexts and no side-effect changes that need to * context save & restore so it can reuse the current thread - * context. However, it still needs to bump `s_stack_depth` to - * avoid kernel stack overflow from nested filesystems. + * context. + * However, we still need to prevent kernel stack overflow due + * to filesystem nesting: just ensure that s_stack_depth is 0 + * to disallow mounting EROFS on stacked filesystems. + * Note: s_stack_depth is not incremented here for now, since + * EROFS is the only fs supporting file-backed mounts for now. + * It MUST change if another fs plans to support them, which + * may also require adjusting FILESYSTEM_MAX_STACK_DEPTH. */ if (erofs_is_fileio_mode(sbi)) { - sb->s_stack_depth = - file_inode(sbi->dif0.file)->i_sb->s_stack_depth + 1; - if (sb->s_stack_depth > FILESYSTEM_MAX_STACK_DEPTH) { - erofs_err(sb, "maximum fs stacking depth exceeded"); + inode = file_inode(sbi->dif0.file); + if ((inode->i_sb->s_op == &erofs_sops && + !inode->i_sb->s_bdev) || + inode->i_sb->s_stack_depth) { + erofs_err(sb, "file-backed mounts cannot be applied to stacked fses"); return -ENOTBLK; } } diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 65da21504632..3d31f7840ca0 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1262,7 +1262,7 @@ static int z_erofs_parse_in_bvecs(struct z_erofs_backend *be, bool *overlapped) return err; } -static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err) +static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, bool eio) { struct erofs_sb_info *const sbi = EROFS_SB(be->sb); struct z_erofs_pcluster *pcl = be->pcl; @@ -1270,7 +1270,7 @@ static int z_erofs_decompress_pcluster(struct z_erofs_backend *be, int err) const struct z_erofs_decompressor *alg = z_erofs_decomp[pcl->algorithmformat]; bool try_free = true; - int i, j, jtop, err2; + int i, j, jtop, err2, err = eio ? -EIO : 0; struct page *page; bool overlapped; const char *reason; @@ -1413,12 +1413,12 @@ static int z_erofs_decompress_queue(const struct z_erofs_decompressqueue *io, .pcl = io->head, }; struct z_erofs_pcluster *next; - int err = io->eio ? -EIO : 0; + int err = 0; for (; be.pcl != Z_EROFS_PCLUSTER_TAIL; be.pcl = next) { DBG_BUGON(!be.pcl); next = READ_ONCE(be.pcl->next); - err = z_erofs_decompress_pcluster(&be, err) ?: err; + err = z_erofs_decompress_pcluster(&be, io->eio) ?: err; } return err; } diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c index 0550fd30fd10..635fb8a52e0c 100644 --- a/fs/ext4/move_extent.c +++ b/fs/ext4/move_extent.c @@ -393,9 +393,11 @@ out: repair_branches: ret2 = 0; + ext4_double_down_write_data_sem(orig_inode, donor_inode); r_len = ext4_swap_extents(handle, donor_inode, orig_inode, mext->donor_lblk, orig_map->m_lblk, *m_len, 0, &ret2); + ext4_double_up_write_data_sem(orig_inode, donor_inode); if (ret2 || r_len != *m_len) { ext4_error_inode_block(orig_inode, (sector_t)(orig_map->m_lblk), EIO, "Unable to copy data block, data will be lost!"); diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 2e02efbddaac..4ed8ddf2a60b 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -1037,6 +1037,7 @@ static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, ext4_error_inode(ea_inode, __func__, __LINE__, 0, "EA inode %lu ref wraparound: ref_count=%lld ref_change=%d", ea_inode->i_ino, ref_count, ref_change); + brelse(iloc.bh); ret = -EFSCORRUPTED; goto out; } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 6800886c4d10..baa2f2141146 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2750,8 +2750,13 @@ static void wait_sb_inodes(struct super_block *sb) * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. + * + * If the mapping does not have data integrity semantics, + * there's no need to wait for the writeout to complete, as the + * mapping cannot guarantee that data is persistently stored. */ - if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) + if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK) || + mapping_no_data_integrity(mapping)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 01bc894e9c2b..3b2a171e652f 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -3200,8 +3200,10 @@ void fuse_init_file_inode(struct inode *inode, unsigned int flags) inode->i_fop = &fuse_file_operations; inode->i_data.a_ops = &fuse_file_aops; - if (fc->writeback_cache) + if (fc->writeback_cache) { mapping_set_writeback_may_deadlock_on_reclaim(&inode->i_data); + mapping_set_no_data_integrity(&inode->i_data); + } INIT_LIST_HEAD(&fi->write_files); INIT_LIST_HEAD(&fi->queued_writes); diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c index 97ebe457c00a..d27a0b1080a9 100644 --- a/fs/gfs2/lops.c +++ b/fs/gfs2/lops.c @@ -484,7 +484,7 @@ static struct bio *gfs2_chain_bio(struct bio *prev, unsigned int nr_iovecs) new = bio_alloc(prev->bi_bdev, nr_iovecs, prev->bi_opf, GFP_NOIO); bio_clone_blkg_association(new, prev); new->bi_iter.bi_sector = bio_end_sector(prev); - bio_chain(prev, new); + bio_chain(new, prev); submit_bio(prev); return new; } diff --git a/fs/inode.c b/fs/inode.c index 521383223d8a..379f4c19845c 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1593,6 +1593,9 @@ EXPORT_SYMBOL(igrab); * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test + * @isnew: return argument telling whether I_NEW was set when + * the inode was found in hash (the caller needs to + * wait for I_NEW to clear) * * Search for the inode specified by @hashval and @data in the inode cache. * If the inode is in the cache, the inode is returned with an incremented diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index e5c1ca440d93..fd9a2cf95620 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -832,7 +832,7 @@ static struct folio *__iomap_get_folio(struct iomap_iter *iter, if (!mapping_large_folio_support(iter->inode->i_mapping)) len = min_t(size_t, len, PAGE_SIZE - offset_in_page(pos)); - if (iter->fbatch) { + if (iter->iomap.flags & IOMAP_F_FOLIO_BATCH) { struct folio *folio = folio_batch_next(iter->fbatch); if (!folio) @@ -929,7 +929,7 @@ static int iomap_write_begin(struct iomap_iter *iter, * process so return and let the caller iterate and refill the batch. */ if (!folio) { - WARN_ON_ONCE(!iter->fbatch); + WARN_ON_ONCE(!(iter->iomap.flags & IOMAP_F_FOLIO_BATCH)); return 0; } @@ -1544,23 +1544,39 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero, return status; } -loff_t +/** + * iomap_fill_dirty_folios - fill a folio batch with dirty folios + * @iter: Iteration structure + * @start: Start offset of range. Updated based on lookup progress. + * @end: End offset of range + * @iomap_flags: Flags to set on the associated iomap to track the batch. + * + * Returns the folio count directly. Also returns the associated control flag if + * the the batch lookup is performed and the expected offset of a subsequent + * lookup via out params. The caller is responsible to set the flag on the + * associated iomap. + */ +unsigned int iomap_fill_dirty_folios( struct iomap_iter *iter, - loff_t offset, - loff_t length) + loff_t *start, + loff_t end, + unsigned int *iomap_flags) { struct address_space *mapping = iter->inode->i_mapping; - pgoff_t start = offset >> PAGE_SHIFT; - pgoff_t end = (offset + length - 1) >> PAGE_SHIFT; + pgoff_t pstart = *start >> PAGE_SHIFT; + pgoff_t pend = (end - 1) >> PAGE_SHIFT; + unsigned int count; - iter->fbatch = kmalloc(sizeof(struct folio_batch), GFP_KERNEL); - if (!iter->fbatch) - return offset + length; - folio_batch_init(iter->fbatch); + if (!iter->fbatch) { + *start = end; + return 0; + } - filemap_get_folios_dirty(mapping, &start, end, iter->fbatch); - return (start << PAGE_SHIFT); + count = filemap_get_folios_dirty(mapping, &pstart, pend, iter->fbatch); + *start = (pstart << PAGE_SHIFT); + *iomap_flags |= IOMAP_F_FOLIO_BATCH; + return count; } EXPORT_SYMBOL_GPL(iomap_fill_dirty_folios); @@ -1569,17 +1585,21 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops, void *private) { + struct folio_batch fbatch; struct iomap_iter iter = { .inode = inode, .pos = pos, .len = len, .flags = IOMAP_ZERO, .private = private, + .fbatch = &fbatch, }; struct address_space *mapping = inode->i_mapping; int ret; bool range_dirty; + folio_batch_init(&fbatch); + /* * To avoid an unconditional flush, check pagecache state and only flush * if dirty and the fs returns a mapping that might convert on @@ -1590,11 +1610,11 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, while ((ret = iomap_iter(&iter, ops)) > 0) { const struct iomap *srcmap = iomap_iter_srcmap(&iter); - if (WARN_ON_ONCE(iter.fbatch && + if (WARN_ON_ONCE((iter.iomap.flags & IOMAP_F_FOLIO_BATCH) && srcmap->type != IOMAP_UNWRITTEN)) return -EIO; - if (!iter.fbatch && + if (!(iter.iomap.flags & IOMAP_F_FOLIO_BATCH) && (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)) { s64 status; diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c index 8692e5e41c6d..c04796f6e57f 100644 --- a/fs/iomap/iter.c +++ b/fs/iomap/iter.c @@ -8,10 +8,10 @@ static inline void iomap_iter_reset_iomap(struct iomap_iter *iter) { - if (iter->fbatch) { + if (iter->iomap.flags & IOMAP_F_FOLIO_BATCH) { folio_batch_release(iter->fbatch); - kfree(iter->fbatch); - iter->fbatch = NULL; + folio_batch_reinit(iter->fbatch); + iter->iomap.flags &= ~IOMAP_F_FOLIO_BATCH; } iter->status = 0; diff --git a/fs/jffs2/wbuf.c b/fs/jffs2/wbuf.c index bb815a002984..3ab3f0ff7ebb 100644 --- a/fs/jffs2/wbuf.c +++ b/fs/jffs2/wbuf.c @@ -2,10 +2,10 @@ * JFFS2 -- Journalling Flash File System, Version 2. * * Copyright © 2001-2007 Red Hat, Inc. - * Copyright © 2004 Thomas Gleixner <tglx@linutronix.de> + * Copyright © 2004 Thomas Gleixner <tglx@kernel.org> * * Created by David Woodhouse <dwmw2@infradead.org> - * Modified debugged and enhanced by Thomas Gleixner <tglx@linutronix.de> + * Modified debugged and enhanced by Thomas Gleixner <tglx@kernel.org> * * For licensing information, see the file 'LICENCE' in this directory. * diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index 5c0efd6b239f..29baeeb97871 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -681,8 +681,10 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, return kn; err_out4: - simple_xattrs_free(&kn->iattr->xattrs, NULL); - kmem_cache_free(kernfs_iattrs_cache, kn->iattr); + if (kn->iattr) { + simple_xattrs_free(&kn->iattr->xattrs, NULL); + kmem_cache_free(kernfs_iattrs_cache, kn->iattr); + } err_out3: spin_lock(&root->kernfs_idr_lock); idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c index 109e5caae8c7..4b6f18d97734 100644 --- a/fs/lockd/svc4proc.c +++ b/fs/lockd/svc4proc.c @@ -97,7 +97,6 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; - struct nlm_lockowner *test_owner; __be32 rc = rpc_success; dprintk("lockd: TEST4 called\n"); @@ -107,7 +106,6 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) if ((resp->status = nlm4svc_retrieve_args(rqstp, argp, &host, &file))) return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success; - test_owner = argp->lock.fl.c.flc_owner; /* Now check for conflicting locks */ resp->status = nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock); @@ -116,7 +114,7 @@ __nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) else dprintk("lockd: TEST4 status %d\n", ntohl(resp->status)); - nlmsvc_put_lockowner(test_owner); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rc; diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c index 3a3d05cfe09a..6bce19fd024c 100644 --- a/fs/lockd/svclock.c +++ b/fs/lockd/svclock.c @@ -633,7 +633,13 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, } mode = lock_to_openmode(&lock->fl); - error = vfs_test_lock(file->f_file[mode], &lock->fl); + locks_init_lock(&conflock->fl); + /* vfs_test_lock only uses start, end, and owner, but tests flc_file */ + conflock->fl.c.flc_file = lock->fl.c.flc_file; + conflock->fl.fl_start = lock->fl.fl_start; + conflock->fl.fl_end = lock->fl.fl_end; + conflock->fl.c.flc_owner = lock->fl.c.flc_owner; + error = vfs_test_lock(file->f_file[mode], &conflock->fl); if (error) { /* We can't currently deal with deferred test requests */ if (error == FILE_LOCK_DEFERRED) @@ -643,22 +649,19 @@ nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file, goto out; } - if (lock->fl.c.flc_type == F_UNLCK) { + if (conflock->fl.c.flc_type == F_UNLCK) { ret = nlm_granted; goto out; } dprintk("lockd: conflicting lock(ty=%d, %Ld-%Ld)\n", - lock->fl.c.flc_type, (long long)lock->fl.fl_start, - (long long)lock->fl.fl_end); + conflock->fl.c.flc_type, (long long)conflock->fl.fl_start, + (long long)conflock->fl.fl_end); conflock->caller = "somehost"; /* FIXME */ conflock->len = strlen(conflock->caller); conflock->oh.len = 0; /* don't return OH info */ - conflock->svid = lock->fl.c.flc_pid; - conflock->fl.c.flc_type = lock->fl.c.flc_type; - conflock->fl.fl_start = lock->fl.fl_start; - conflock->fl.fl_end = lock->fl.fl_end; - locks_release_private(&lock->fl); + conflock->svid = conflock->fl.c.flc_pid; + locks_release_private(&conflock->fl); ret = nlm_lck_denied; out: diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c index f53d5177f267..5817ef272332 100644 --- a/fs/lockd/svcproc.c +++ b/fs/lockd/svcproc.c @@ -117,7 +117,6 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) struct nlm_args *argp = rqstp->rq_argp; struct nlm_host *host; struct nlm_file *file; - struct nlm_lockowner *test_owner; __be32 rc = rpc_success; dprintk("lockd: TEST called\n"); @@ -127,8 +126,6 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) if ((resp->status = nlmsvc_retrieve_args(rqstp, argp, &host, &file))) return resp->status == nlm_drop_reply ? rpc_drop_reply :rpc_success; - test_owner = argp->lock.fl.c.flc_owner; - /* Now check for conflicting locks */ resp->status = cast_status(nlmsvc_testlock(rqstp, file, host, &argp->lock, &resp->lock)); @@ -138,7 +135,7 @@ __nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp) dprintk("lockd: TEST status %d vers %d\n", ntohl(resp->status), rqstp->rq_vers); - nlmsvc_put_lockowner(test_owner); + nlmsvc_release_lockowner(&argp->lock); nlmsvc_release_host(host); nlm_release_file(file); return rc; diff --git a/fs/locks.c b/fs/locks.c index 9f565802a88c..7ea949d7ff45 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -369,10 +369,19 @@ locks_dispose_list(struct list_head *dispose) while (!list_empty(dispose)) { flc = list_first_entry(dispose, struct file_lock_core, flc_list); list_del_init(&flc->flc_list); - if (flc->flc_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) - locks_free_lease(file_lease(flc)); - else - locks_free_lock(file_lock(flc)); + locks_free_lock(file_lock(flc)); + } +} + +static void +lease_dispose_list(struct list_head *dispose) +{ + struct file_lock_core *flc; + + while (!list_empty(dispose)) { + flc = list_first_entry(dispose, struct file_lock_core, flc_list); + list_del_init(&flc->flc_list); + locks_free_lease(file_lease(flc)); } } @@ -576,10 +585,50 @@ lease_setup(struct file_lease *fl, void **priv) __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); } +/** + * lease_open_conflict - see if the given file points to an inode that has + * an existing open that would conflict with the + * desired lease. + * @filp: file to check + * @arg: type of lease that we're trying to acquire + * + * Check to see if there's an existing open fd on this file that would + * conflict with the lease we're trying to set. + */ +static int +lease_open_conflict(struct file *filp, const int arg) +{ + struct inode *inode = file_inode(filp); + int self_wcount = 0, self_rcount = 0; + + if (arg == F_RDLCK) + return inode_is_open_for_write(inode) ? -EAGAIN : 0; + else if (arg != F_WRLCK) + return 0; + + /* + * Make sure that only read/write count is from lease requestor. + * Note that this will result in denying write leases when i_writecount + * is negative, which is what we want. (We shouldn't grant write leases + * on files open for execution.) + */ + if (filp->f_mode & FMODE_WRITE) + self_wcount = 1; + else if (filp->f_mode & FMODE_READ) + self_rcount = 1; + + if (atomic_read(&inode->i_writecount) != self_wcount || + atomic_read(&inode->i_readcount) != self_rcount) + return -EAGAIN; + + return 0; +} + static const struct lease_manager_operations lease_manager_ops = { .lm_break = lease_break_callback, .lm_change = lease_modify, .lm_setup = lease_setup, + .lm_open_conflict = lease_open_conflict, }; /* @@ -1620,7 +1669,7 @@ restart: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->c.flc_wait, list_empty(&new_fl->c.flc_blocked_member), break_time); @@ -1643,7 +1692,7 @@ restart: out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); free_lock: locks_free_lease(new_fl); return error; @@ -1727,7 +1776,7 @@ static int __fcntl_getlease(struct file *filp, unsigned int flavor) spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); } return type; } @@ -1745,52 +1794,6 @@ int fcntl_getdeleg(struct file *filp, struct delegation *deleg) return 0; } -/** - * check_conflicting_open - see if the given file points to an inode that has - * an existing open that would conflict with the - * desired lease. - * @filp: file to check - * @arg: type of lease that we're trying to acquire - * @flags: current lock flags - * - * Check to see if there's an existing open fd on this file that would - * conflict with the lease we're trying to set. - */ -static int -check_conflicting_open(struct file *filp, const int arg, int flags) -{ - struct inode *inode = file_inode(filp); - int self_wcount = 0, self_rcount = 0; - - if (flags & FL_LAYOUT) - return 0; - if (flags & FL_DELEG) - /* We leave these checks to the caller */ - return 0; - - if (arg == F_RDLCK) - return inode_is_open_for_write(inode) ? -EAGAIN : 0; - else if (arg != F_WRLCK) - return 0; - - /* - * Make sure that only read/write count is from lease requestor. - * Note that this will result in denying write leases when i_writecount - * is negative, which is what we want. (We shouldn't grant write leases - * on files open for execution.) - */ - if (filp->f_mode & FMODE_WRITE) - self_wcount = 1; - else if (filp->f_mode & FMODE_READ) - self_rcount = 1; - - if (atomic_read(&inode->i_writecount) != self_wcount || - atomic_read(&inode->i_readcount) != self_rcount) - return -EAGAIN; - - return 0; -} - static int generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **priv) { @@ -1827,7 +1830,7 @@ generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **pr percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); - error = check_conflicting_open(filp, arg, lease->c.flc_flags); + error = lease->fl_lmops->lm_open_conflict(filp, arg); if (error) goto out; @@ -1884,7 +1887,7 @@ generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **pr * precedes these checks. */ smp_mb(); - error = check_conflicting_open(filp, arg, lease->c.flc_flags); + error = lease->fl_lmops->lm_open_conflict(filp, arg); if (error) { locks_unlink_lock_ctx(&lease->c); goto out; @@ -1896,7 +1899,7 @@ out_setup: out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); if (is_deleg) inode_unlock(inode); if (!error && !my_fl) @@ -1932,7 +1935,7 @@ static int generic_delete_lease(struct file *filp, void *owner) error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); return error; } @@ -2236,13 +2239,21 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) /** * vfs_test_lock - test file byte range lock * @filp: The file to test lock for - * @fl: The lock to test; also used to hold result + * @fl: The byte-range in the file to test; also used to hold result * + * On entry, @fl does not contain a lock, but identifies a range (fl_start, fl_end) + * in the file (c.flc_file), and an owner (c.flc_owner) for whom existing locks + * should be ignored. c.flc_type and c.flc_flags are ignored. + * Both fl_lmops and fl_ops in @fl must be NULL. * Returns -ERRNO on failure. Indicates presence of conflicting lock by - * setting conf->fl_type to something other than F_UNLCK. + * setting fl->fl_type to something other than F_UNLCK. + * + * If vfs_test_lock() does find a lock and return it, the caller must + * use locks_free_lock() or locks_release_private() on the returned lock. */ int vfs_test_lock(struct file *filp, struct file_lock *fl) { + WARN_ON_ONCE(fl->fl_ops || fl->fl_lmops); WARN_ON_ONCE(filp != fl->c.flc_file); if (filp->f_op->lock) return filp->f_op->lock(filp, F_GETLK, fl); @@ -2727,7 +2738,7 @@ locks_remove_lease(struct file *filp, struct file_lock_context *ctx) spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); } /* diff --git a/fs/namei.c b/fs/namei.c index bf0f66f0e9b9..cf16b6822dd3 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -830,11 +830,9 @@ static inline bool legitimize_path(struct nameidata *nd, static bool legitimize_links(struct nameidata *nd) { int i; - if (unlikely(nd->flags & LOOKUP_CACHED)) { - drop_links(nd); - nd->depth = 0; - return false; - } + + VFS_BUG_ON(nd->flags & LOOKUP_CACHED); + for (i = 0; i < nd->depth; i++) { struct saved *last = nd->stack + i; if (unlikely(!legitimize_path(nd, &last->link, last->seq))) { @@ -883,6 +881,11 @@ static bool try_to_unlazy(struct nameidata *nd) BUG_ON(!(nd->flags & LOOKUP_RCU)); + if (unlikely(nd->flags & LOOKUP_CACHED)) { + drop_links(nd); + nd->depth = 0; + goto out1; + } if (unlikely(nd->depth && !legitimize_links(nd))) goto out1; if (unlikely(!legitimize_path(nd, &nd->path, nd->seq))) @@ -918,6 +921,11 @@ static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry) int res; BUG_ON(!(nd->flags & LOOKUP_RCU)); + if (unlikely(nd->flags & LOOKUP_CACHED)) { + drop_links(nd); + nd->depth = 0; + goto out2; + } if (unlikely(nd->depth && !legitimize_links(nd))) goto out2; res = __legitimize_mnt(nd->path.mnt, nd->m_seq); @@ -2836,10 +2844,11 @@ static int filename_parentat(int dfd, struct filename *name, } /** - * start_dirop - begin a create or remove dirop, performing locking and lookup + * __start_dirop - begin a create or remove dirop, performing locking and lookup * @parent: the dentry of the parent in which the operation will occur * @name: a qstr holding the name within that parent * @lookup_flags: intent and other lookup flags. + * @state: task state bitmask * * The lookup is performed and necessary locks are taken so that, on success, * the returned dentry can be operated on safely. diff --git a/fs/netfs/read_collect.c b/fs/netfs/read_collect.c index a95e7aadafd0..7a0ffa675fb1 100644 --- a/fs/netfs/read_collect.c +++ b/fs/netfs/read_collect.c @@ -137,7 +137,7 @@ static void netfs_read_unlock_folios(struct netfs_io_request *rreq, rreq->front_folio_order = order; fsize = PAGE_SIZE << order; fpos = folio_pos(folio); - fend = umin(fpos + fsize, rreq->i_size); + fend = fpos + fsize; trace_netfs_collect_folio(rreq, folio, fend, collected_to); diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index ab76120705e2..134d7f760a33 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -417,8 +417,10 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, d->map = bl_map_simple; d->pr_key = v->scsi.pr_key; - if (d->len == 0) - return -ENODEV; + if (d->len == 0) { + error = -ENODEV; + goto out_blkdev_put; + } ops = bdev->bd_disk->fops->pr_ops; if (!ops) { diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index 2248e3ad089a..8a3857a49d84 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -149,7 +149,7 @@ static int nfs4_do_check_delegation(struct inode *inode, fmode_t type, int nfs4_have_delegation(struct inode *inode, fmode_t type, int flags) { if (S_ISDIR(inode->i_mode) && !directory_delegations) - nfs_inode_evict_delegation(inode); + nfs4_inode_set_return_delegation_on_close(inode); return nfs4_do_check_delegation(inode, type, flags, true); } @@ -581,6 +581,10 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation if (delegation == NULL) return 0; + /* Directory delegations don't require any state recovery */ + if (!S_ISREG(inode->i_mode)) + goto out_return; + if (!issync) mode |= O_NONBLOCK; /* Recall of any remaining application leases */ @@ -604,6 +608,7 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation goto out; } +out_return: err = nfs_do_return_delegation(inode, delegation, issync); out: /* Refcount matched in nfs_start_delegation_return_locked() */ diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index 23a78a742b61..8f9ea79b7882 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -1440,7 +1440,8 @@ static void nfs_set_verifier_locked(struct dentry *dentry, unsigned long verf) if (!dir || !nfs_verify_change_attribute(dir, verf)) return; - if (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ, 0)) + if (NFS_PROTO(dir)->have_delegation(dir, FMODE_READ, 0) || + (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ, 0))) nfs_set_verifier_delegated(&verf); dentry->d_time = verf; } @@ -1465,6 +1466,49 @@ void nfs_set_verifier(struct dentry *dentry, unsigned long verf) EXPORT_SYMBOL_GPL(nfs_set_verifier); #if IS_ENABLED(CONFIG_NFS_V4) +static void nfs_clear_verifier_file(struct inode *inode) +{ + struct dentry *alias; + struct inode *dir; + + hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { + spin_lock(&alias->d_lock); + dir = d_inode_rcu(alias->d_parent); + if (!dir || + !NFS_PROTO(dir)->have_delegation(dir, FMODE_READ, 0)) + nfs_unset_verifier_delegated(&alias->d_time); + spin_unlock(&alias->d_lock); + } +} + +static void nfs_clear_verifier_directory(struct inode *dir) +{ + struct dentry *this_parent; + struct dentry *dentry; + struct inode *inode; + + if (hlist_empty(&dir->i_dentry)) + return; + this_parent = + hlist_entry(dir->i_dentry.first, struct dentry, d_u.d_alias); + + spin_lock(&this_parent->d_lock); + nfs_unset_verifier_delegated(&this_parent->d_time); + dentry = d_first_child(this_parent); + hlist_for_each_entry_from(dentry, d_sib) { + if (unlikely(dentry->d_flags & DCACHE_DENTRY_CURSOR)) + continue; + inode = d_inode_rcu(dentry); + if (inode && + NFS_PROTO(inode)->have_delegation(inode, FMODE_READ, 0)) + continue; + spin_lock_nested(&dentry->d_lock, DENTRY_D_LOCK_NESTED); + nfs_unset_verifier_delegated(&dentry->d_time); + spin_unlock(&dentry->d_lock); + } + spin_unlock(&this_parent->d_lock); +} + /** * nfs_clear_verifier_delegated - clear the dir verifier delegation tag * @inode: pointer to inode @@ -1477,16 +1521,13 @@ EXPORT_SYMBOL_GPL(nfs_set_verifier); */ void nfs_clear_verifier_delegated(struct inode *inode) { - struct dentry *alias; - if (!inode) return; spin_lock(&inode->i_lock); - hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) { - spin_lock(&alias->d_lock); - nfs_unset_verifier_delegated(&alias->d_time); - spin_unlock(&alias->d_lock); - } + if (S_ISREG(inode->i_mode)) + nfs_clear_verifier_file(inode); + else if (S_ISDIR(inode->i_mode)) + nfs_clear_verifier_directory(inode); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL_GPL(nfs_clear_verifier_delegated); @@ -1516,14 +1557,6 @@ static int nfs_check_verifier(struct inode *dir, struct dentry *dentry, if (!nfs_dentry_verify_change(dir, dentry)) return 0; - /* - * If we have a directory delegation then we don't need to revalidate - * the directory. The delegation will either get recalled or we will - * receive a notification when it changes. - */ - if (nfs_have_directory_delegation(dir)) - return 0; - /* Revalidate nfsi->cache_change_attribute before we declare a match */ if (nfs_mapping_need_revalidate_inode(dir)) { if (rcu_walk) @@ -2217,13 +2250,6 @@ no_open: EXPORT_SYMBOL_GPL(nfs_atomic_open); static int -nfs_lookup_revalidate_delegated_parent(struct inode *dir, struct dentry *dentry, - struct inode *inode) -{ - return nfs_lookup_revalidate_done(dir, dentry, inode, 1); -} - -static int nfs4_lookup_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { @@ -2247,12 +2273,10 @@ nfs4_lookup_revalidate(struct inode *dir, const struct qstr *name, if (inode == NULL) goto full_reval; - if (nfs_verifier_is_delegated(dentry)) + if (nfs_verifier_is_delegated(dentry) || + nfs_have_directory_delegation(inode)) return nfs_lookup_revalidate_delegated(dir, dentry, inode); - if (nfs_have_directory_delegation(dir)) - return nfs_lookup_revalidate_delegated_parent(dir, dentry, inode); - /* NFS only supports OPEN on regular files */ if (!S_ISREG(inode->i_mode)) goto full_reval; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index d020aab40c64..d1c138a416cf 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -511,7 +511,8 @@ static bool nfs_release_folio(struct folio *folio, gfp_t gfp) if ((current_gfp_context(gfp) & GFP_KERNEL) != GFP_KERNEL || current_is_kswapd() || current_is_kcompactd()) return false; - if (nfs_wb_folio(folio->mapping->host, folio) < 0) + if (nfs_wb_folio_reclaim(folio->mapping->host, folio) < 0 || + folio_test_private(folio)) return false; } return nfs_fscache_release_folio(folio, gfp); diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c index c55ea8fa3bfa..c2d8a13a9dbd 100644 --- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c +++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c @@ -103,7 +103,7 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev, sizeof(struct nfs4_ff_ds_version), gfp_flags); if (!ds_versions) - goto out_scratch; + goto out_err_drain_dsaddrs; for (i = 0; i < version_count; i++) { /* 20 = version(4) + minor_version(4) + rsize(4) + wsize(4) + diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 84049f3cd340..de2cce1d08f4 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -716,7 +716,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, { struct inode *inode = d_inode(dentry); struct nfs_fattr *fattr; - loff_t oldsize = i_size_read(inode); + loff_t oldsize; int error = 0; kuid_t task_uid = current_fsuid(); kuid_t owner_uid = inode->i_uid; @@ -727,6 +727,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (attr->ia_valid & (ATTR_KILL_SUID | ATTR_KILL_SGID)) attr->ia_valid &= ~ATTR_MODE; + if (S_ISREG(inode->i_mode)) + nfs_file_block_o_direct(NFS_I(inode)); + + oldsize = i_size_read(inode); if (attr->ia_valid & ATTR_SIZE) { BUG_ON(!S_ISREG(inode->i_mode)); @@ -774,10 +778,8 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, trace_nfs_setattr_enter(inode); /* Write all dirty data */ - if (S_ISREG(inode->i_mode)) { - nfs_file_block_o_direct(NFS_I(inode)); + if (S_ISREG(inode->i_mode)) nfs_sync_inode(inode); - } fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) { diff --git a/fs/nfs/io.c b/fs/nfs/io.c index d275b0a250bf..8337f0ae852d 100644 --- a/fs/nfs/io.c +++ b/fs/nfs/io.c @@ -84,6 +84,7 @@ nfs_start_io_write(struct inode *inode) nfs_file_block_o_direct(NFS_I(inode)); return err; } +EXPORT_SYMBOL_GPL(nfs_start_io_write); /** * nfs_end_io_write - declare that the buffered write operation is done @@ -97,6 +98,7 @@ nfs_end_io_write(struct inode *inode) { up_write(&inode->i_rwsem); } +EXPORT_SYMBOL_GPL(nfs_end_io_write); /* Call with exclusively locked inode->i_rwsem */ static void nfs_block_buffered(struct nfs_inode *nfsi, struct inode *inode) diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c index a113bfdacfd6..41fbcb3f9167 100644 --- a/fs/nfs/localio.c +++ b/fs/nfs/localio.c @@ -461,6 +461,8 @@ nfs_local_iters_init(struct nfs_local_kiocb *iocb, int rw) v = 0; total = hdr->args.count; base = hdr->args.pgbase; + pagevec += base >> PAGE_SHIFT; + base &= ~PAGE_MASK; while (total && v < hdr->page_array.npages) { len = min_t(size_t, total, PAGE_SIZE - base); bvec_set_page(&iocb->bvec[v], *pagevec, len, base); @@ -618,7 +620,6 @@ static void nfs_local_call_read(struct work_struct *work) struct nfs_local_kiocb *iocb = container_of(work, struct nfs_local_kiocb, work); struct file *filp = iocb->kiocb.ki_filp; - bool force_done = false; ssize_t status; int n_iters; @@ -637,13 +638,13 @@ static void nfs_local_call_read(struct work_struct *work) scoped_with_creds(filp->f_cred) status = filp->f_op->read_iter(&iocb->kiocb, &iocb->iters[i]); - if (status != -EIOCBQUEUED) { - if (unlikely(status >= 0 && status < iocb->iters[i].count)) - force_done = true; /* Partial read */ - if (nfs_local_pgio_done(iocb, status, force_done)) { - nfs_local_read_iocb_done(iocb); - break; - } + if (status == -EIOCBQUEUED) + continue; + /* Break on completion, errors, or short reads */ + if (nfs_local_pgio_done(iocb, status, false) || status < 0 || + (size_t)status < iov_iter_count(&iocb->iters[i])) { + nfs_local_read_iocb_done(iocb); + break; } } } @@ -821,7 +822,6 @@ static void nfs_local_call_write(struct work_struct *work) container_of(work, struct nfs_local_kiocb, work); struct file *filp = iocb->kiocb.ki_filp; unsigned long old_flags = current->flags; - bool force_done = false; ssize_t status; int n_iters; @@ -843,13 +843,13 @@ static void nfs_local_call_write(struct work_struct *work) scoped_with_creds(filp->f_cred) status = filp->f_op->write_iter(&iocb->kiocb, &iocb->iters[i]); - if (status != -EIOCBQUEUED) { - if (unlikely(status >= 0 && status < iocb->iters[i].count)) - force_done = true; /* Partial write */ - if (nfs_local_pgio_done(iocb, status, force_done)) { - nfs_local_write_iocb_done(iocb); - break; - } + if (status == -EIOCBQUEUED) + continue; + /* Break on completion, errors, or short writes */ + if (nfs_local_pgio_done(iocb, status, false) || status < 0 || + (size_t)status < iov_iter_count(&iocb->iters[i])) { + nfs_local_write_iocb_done(iocb); + break; } } file_end_write(filp); diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index d537fb0c230e..c08520828708 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -114,7 +114,6 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, exception.inode = inode; exception.state = lock->open_context->state; - nfs_file_block_o_direct(NFS_I(inode)); err = nfs_sync_inode(inode); if (err) goto out; @@ -138,13 +137,17 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ALLOCATE], }; struct inode *inode = file_inode(filep); - loff_t oldsize = i_size_read(inode); + loff_t oldsize; int err; if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE)) return -EOPNOTSUPP; - inode_lock(inode); + err = nfs_start_io_write(inode); + if (err) + return err; + + oldsize = i_size_read(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); @@ -155,7 +158,7 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) NFS_SERVER(inode)->caps &= ~(NFS_CAP_ALLOCATE | NFS_CAP_ZERO_RANGE); - inode_unlock(inode); + nfs_end_io_write(inode); return err; } @@ -170,7 +173,9 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) if (!nfs_server_capable(inode, NFS_CAP_DEALLOCATE)) return -EOPNOTSUPP; - inode_lock(inode); + err = nfs_start_io_write(inode); + if (err) + return err; err = nfs42_proc_fallocate(&msg, filep, offset, len); if (err == 0) @@ -179,7 +184,7 @@ int nfs42_proc_deallocate(struct file *filep, loff_t offset, loff_t len) NFS_SERVER(inode)->caps &= ~(NFS_CAP_DEALLOCATE | NFS_CAP_ZERO_RANGE); - inode_unlock(inode); + nfs_end_io_write(inode); return err; } @@ -189,14 +194,17 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len) .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_ZERO_RANGE], }; struct inode *inode = file_inode(filep); - loff_t oldsize = i_size_read(inode); + loff_t oldsize; int err; if (!nfs_server_capable(inode, NFS_CAP_ZERO_RANGE)) return -EOPNOTSUPP; - inode_lock(inode); + err = nfs_start_io_write(inode); + if (err) + return err; + oldsize = i_size_read(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); if (err == 0) { nfs_truncate_last_folio(inode->i_mapping, oldsize, @@ -205,7 +213,7 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len) } else if (err == -EOPNOTSUPP) NFS_SERVER(inode)->caps &= ~NFS_CAP_ZERO_RANGE; - inode_unlock(inode); + nfs_end_io_write(inode); return err; } @@ -416,7 +424,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, struct nfs_server *src_server = NFS_SERVER(src_inode); loff_t pos_src = args->src_pos; loff_t pos_dst = args->dst_pos; - loff_t oldsize_dst = i_size_read(dst_inode); + loff_t oldsize_dst; size_t count = args->count; ssize_t status; @@ -461,6 +469,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, &src_lock->open_context->state->flags); set_bit(NFS_CLNT_DST_SSC_COPY_STATE, &dst_lock->open_context->state->flags); + oldsize_dst = i_size_read(dst_inode); status = nfs4_call_sync(dst_server->client, dst_server, &msg, &args->seq_args, &res->seq_res, 0); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index ec1ce593dea2..a0885ae55abc 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3894,8 +3894,8 @@ int nfs4_do_close(struct nfs4_state *state, gfp_t gfp_mask, int wait) calldata->res.seqid = calldata->arg.seqid; calldata->res.server = server; calldata->res.lr_ret = -NFS4ERR_NOMATCHING_LAYOUT; - calldata->lr.roc = pnfs_roc(state->inode, - &calldata->lr.arg, &calldata->lr.res, msg.rpc_cred); + calldata->lr.roc = pnfs_roc(state->inode, &calldata->lr.arg, + &calldata->lr.res, msg.rpc_cred, wait); if (calldata->lr.roc) { calldata->arg.lr_args = &calldata->lr.arg; calldata->res.lr_res = &calldata->lr.res; @@ -4494,6 +4494,25 @@ static bool should_request_dir_deleg(struct inode *inode) } #endif /* CONFIG_NFS_V4_1 */ +static void nfs4_call_getattr_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_call_sync_data *data = calldata; + nfs4_setup_sequence(data->seq_server->nfs_client, data->seq_args, + data->seq_res, task); +} + +static void nfs4_call_getattr_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_call_sync_data *data = calldata; + + nfs4_sequence_process(task, data->seq_res); +} + +static const struct rpc_call_ops nfs4_call_getattr_ops = { + .rpc_call_prepare = nfs4_call_getattr_prepare, + .rpc_call_done = nfs4_call_getattr_done, +}; + static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr, struct inode *inode) { @@ -4511,16 +4530,26 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, .rpc_argp = &args, .rpc_resp = &res, }; + struct nfs4_call_sync_data data = { + .seq_server = server, + .seq_args = &args.seq_args, + .seq_res = &res.seq_res, + }; + struct rpc_task_setup task_setup = { + .rpc_client = server->client, + .rpc_message = &msg, + .callback_ops = &nfs4_call_getattr_ops, + .callback_data = &data, + }; struct nfs4_gdd_res gdd_res; - unsigned short task_flags = 0; int status; if (nfs4_has_session(server->nfs_client)) - task_flags = RPC_TASK_MOVEABLE; + task_setup.flags = RPC_TASK_MOVEABLE; /* Is this is an attribute revalidation, subject to softreval? */ if (inode && (server->flags & NFS_MOUNT_SOFTREVAL)) - task_flags |= RPC_TASK_TIMEOUT; + task_setup.flags |= RPC_TASK_TIMEOUT; args.get_dir_deleg = should_request_dir_deleg(inode); if (args.get_dir_deleg) @@ -4530,22 +4559,24 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, nfs_fattr_init(fattr); nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0); - status = nfs4_do_call_sync(server->client, server, &msg, - &args.seq_args, &res.seq_res, task_flags); + status = nfs4_call_sync_custom(&task_setup); + if (args.get_dir_deleg) { switch (status) { case 0: if (gdd_res.status != GDD4_OK) break; - status = nfs_inode_set_delegation( - inode, current_cred(), FMODE_READ, - &gdd_res.deleg, 0, NFS4_OPEN_DELEGATE_READ); + nfs_inode_set_delegation(inode, current_cred(), + FMODE_READ, &gdd_res.deleg, 0, + NFS4_OPEN_DELEGATE_READ); break; case -ENOTSUPP: case -EOPNOTSUPP: server->caps &= ~NFS_CAP_DIR_DELEG; } } + + nfs4_sequence_free_slot(&res.seq_res); return status; } @@ -7005,7 +7036,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, const struct cred *cred, data->inode = nfs_igrab_and_active(inode); if (data->inode || issync) { data->lr.roc = pnfs_roc(inode, &data->lr.arg, &data->lr.res, - cred); + cred, issync); if (data->lr.roc) { data->args.lr_args = &data->lr.arg; data->res.lr_res = &data->lr.res; diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 01179f7de322..dba51c622cf3 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1445,6 +1445,8 @@ void nfs_inode_find_state_and_recover(struct inode *inode, struct nfs4_state *state; bool found = false; + if (!S_ISREG(inode->i_mode)) + goto out; rcu_read_lock(); list_for_each_entry_rcu(ctx, &nfsi->open_files, list) { state = ctx->state; @@ -1466,7 +1468,7 @@ void nfs_inode_find_state_and_recover(struct inode *inode, found = true; } rcu_read_unlock(); - +out: nfs_inode_find_delegation_state_and_recover(inode, stateid); if (found) nfs4_schedule_state_manager(clp); @@ -1478,6 +1480,8 @@ static void nfs4_state_mark_open_context_bad(struct nfs4_state *state, int err) struct nfs_inode *nfsi = NFS_I(inode); struct nfs_open_context *ctx; + if (!S_ISREG(inode->i_mode)) + return; rcu_read_lock(); list_for_each_entry_rcu(ctx, &nfsi->open_files, list) { if (ctx->state != state) diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 6ce55e8e6b67..9f9ce4a565ea 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -1062,6 +1062,9 @@ DECLARE_EVENT_CLASS(nfs_folio_event_done, DEFINE_NFS_FOLIO_EVENT(nfs_aop_readpage); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_aop_readpage_done); +DEFINE_NFS_FOLIO_EVENT(nfs_writeback_folio_reclaim); +DEFINE_NFS_FOLIO_EVENT_DONE(nfs_writeback_folio_reclaim_done); + DEFINE_NFS_FOLIO_EVENT(nfs_writeback_folio); DEFINE_NFS_FOLIO_EVENT_DONE(nfs_writeback_folio_done); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index b72d7cc36766..cff225721d1c 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -1533,10 +1533,9 @@ static int pnfs_layout_return_on_reboot(struct pnfs_layout_hdr *lo) PNFS_FL_LAYOUTRETURN_PRIVILEGED); } -bool pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred) +bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, const struct cred *cred, + bool sync) { struct nfs_inode *nfsi = NFS_I(ino); struct nfs_open_context *ctx; @@ -1547,7 +1546,7 @@ bool pnfs_roc(struct inode *ino, nfs4_stateid stateid; enum pnfs_iomode iomode = 0; bool layoutreturn = false, roc = false; - bool skip_read = false; + bool skip_read; if (!nfs_have_layout(ino)) return false; @@ -1560,20 +1559,14 @@ retry: lo = NULL; goto out_noroc; } - pnfs_get_layout_hdr(lo); - if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) { - spin_unlock(&ino->i_lock); - rcu_read_unlock(); - wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, - TASK_UNINTERRUPTIBLE); - pnfs_put_layout_hdr(lo); - goto retry; - } /* no roc if we hold a delegation */ + skip_read = false; if (nfs4_check_delegation(ino, FMODE_READ)) { - if (nfs4_check_delegation(ino, FMODE_WRITE)) + if (nfs4_check_delegation(ino, FMODE_WRITE)) { + lo = NULL; goto out_noroc; + } skip_read = true; } @@ -1582,12 +1575,43 @@ retry: if (state == NULL) continue; /* Don't return layout if there is open file state */ - if (state->state & FMODE_WRITE) + if (state->state & FMODE_WRITE) { + lo = NULL; goto out_noroc; + } if (state->state & FMODE_READ) skip_read = true; } + if (skip_read) { + bool writes = false; + + list_for_each_entry(lseg, &lo->plh_segs, pls_list) { + if (lseg->pls_range.iomode != IOMODE_READ) { + writes = true; + break; + } + } + if (!writes) { + lo = NULL; + goto out_noroc; + } + } + + pnfs_get_layout_hdr(lo); + if (test_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags)) { + if (!sync) { + pnfs_set_plh_return_info( + lo, skip_read ? IOMODE_RW : IOMODE_ANY, 0); + goto out_noroc; + } + spin_unlock(&ino->i_lock); + rcu_read_unlock(); + wait_on_bit(&lo->plh_flags, NFS_LAYOUT_RETURN, + TASK_UNINTERRUPTIBLE); + pnfs_put_layout_hdr(lo); + goto retry; + } list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list) { if (skip_read && lseg->pls_range.iomode == IOMODE_READ) @@ -1627,7 +1651,7 @@ retry: out_noroc: spin_unlock(&ino->i_lock); rcu_read_unlock(); - pnfs_layoutcommit_inode(ino, true); + pnfs_layoutcommit_inode(ino, sync); if (roc) { struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld; if (ld->prepare_layoutreturn) diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 91ff877185c8..3db8f13d8fe4 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -303,10 +303,9 @@ int pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo, u32 seq); int pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo, struct list_head *lseg_list); -bool pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred); +bool pnfs_roc(struct inode *ino, struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, const struct cred *cred, + bool sync); int pnfs_roc_done(struct rpc_task *task, struct nfs4_layoutreturn_args **argpp, struct nfs4_layoutreturn_res **respp, int *ret); void pnfs_roc_release(struct nfs4_layoutreturn_args *args, @@ -773,12 +772,10 @@ pnfs_layoutcommit_outstanding(struct inode *inode) return false; } - -static inline bool -pnfs_roc(struct inode *ino, - struct nfs4_layoutreturn_args *args, - struct nfs4_layoutreturn_res *res, - const struct cred *cred) +static inline bool pnfs_roc(struct inode *ino, + struct nfs4_layoutreturn_args *args, + struct nfs4_layoutreturn_res *res, + const struct cred *cred, bool sync) { return false; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 336c510f3750..bf412455e8ed 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -2025,6 +2025,39 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio) } /** + * nfs_wb_folio_reclaim - Write back all requests on one page + * @inode: pointer to page + * @folio: pointer to folio + * + * Assumes that the folio has been locked by the caller + */ +int nfs_wb_folio_reclaim(struct inode *inode, struct folio *folio) +{ + loff_t range_start = folio_pos(folio); + size_t len = folio_size(folio); + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = 0, + .range_start = range_start, + .range_end = range_start + len - 1, + .for_sync = 1, + }; + int ret; + + if (folio_test_writeback(folio)) + return -EBUSY; + if (folio_clear_dirty_for_io(folio)) { + trace_nfs_writeback_folio_reclaim(inode, range_start, len); + ret = nfs_writepage_locked(folio, &wbc); + trace_nfs_writeback_folio_reclaim_done(inode, range_start, len, + ret); + return ret; + } + nfs_commit_inode(inode, 0); + return 0; +} + +/** * nfs_wb_folio - Write back all requests on one page * @inode: pointer to page * @folio: pointer to folio diff --git a/fs/nfs_common/common.c b/fs/nfs_common/common.c index af09aed09fd2..0778743ae2c2 100644 --- a/fs/nfs_common/common.c +++ b/fs/nfs_common/common.c @@ -17,7 +17,6 @@ static const struct { { NFSERR_NOENT, -ENOENT }, { NFSERR_IO, -EIO }, { NFSERR_NXIO, -ENXIO }, -/* { NFSERR_EAGAIN, -EAGAIN }, */ { NFSERR_ACCES, -EACCES }, { NFSERR_EXIST, -EEXIST }, { NFSERR_XDEV, -EXDEV }, diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 9d55512d0cc9..2a1499f2ad19 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -1024,7 +1024,7 @@ exp_rootfh(struct net *net, struct auth_domain *clp, char *name, { struct svc_export *exp; struct path path; - struct inode *inode; + struct inode *inode __maybe_unused; struct svc_fh fh; int err; struct nfsd_net *nn = net_generic(net, nfsd_net_id); diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 3e2d0fde80a7..fe8338735e7c 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -66,6 +66,8 @@ struct nfsd_net { struct lock_manager nfsd4_manager; bool grace_ended; + bool grace_end_forced; + bool client_tracking_active; time64_t boot_time; struct dentry *nfsd_client_dir; diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 683bd1130afe..ad7af8cfcf1f 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -764,9 +764,28 @@ nfsd4_layout_lm_change(struct file_lease *onlist, int arg, return lease_modify(onlist, arg, dispose); } +/** + * nfsd4_layout_lm_open_conflict - see if the given file points to an inode that has + * an existing open that would conflict with the + * desired lease. + * @filp: file to check + * @arg: type of lease that we're trying to acquire + * + * The kernel will call into this operation to determine whether there + * are conflicting opens that may prevent the layout from being granted. + * For nfsd, that check is done at a higher level, so this trivially + * returns 0. + */ +static int +nfsd4_layout_lm_open_conflict(struct file *filp, int arg) +{ + return 0; +} + static const struct lease_manager_operations nfsd4_layouts_lm_ops = { - .lm_break = nfsd4_layout_lm_break, - .lm_change = nfsd4_layout_lm_change, + .lm_break = nfsd4_layout_lm_break, + .lm_change = nfsd4_layout_lm_change, + .lm_open_conflict = nfsd4_layout_lm_open_conflict, }; int diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index b74800917583..9ec08dd4fe82 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1502,7 +1502,7 @@ try_again: (schedule_timeout(20*HZ) == 0)) { finish_wait(&nn->nfsd_ssc_waitq, &wait); kfree(work); - return nfserr_eagain; + return nfserr_jukebox; } finish_wait(&nn->nfsd_ssc_waitq, &wait); goto try_again; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 808c24fb5c9a..d5e0f3a52d4f 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -84,7 +84,7 @@ static u64 current_sessionid = 1; /* forward declarations */ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner); static void nfs4_free_ol_stateid(struct nfs4_stid *stid); -void nfsd4_end_grace(struct nfsd_net *nn); +static void nfsd4_end_grace(struct nfsd_net *nn); static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); static void nfsd4_file_hash_remove(struct nfs4_file *fi); static void deleg_reaper(struct nfsd_net *nn); @@ -1218,13 +1218,15 @@ static void put_deleg_file(struct nfs4_file *fp) if (nf) nfsd_file_put(nf); - if (rnf) + if (rnf) { + nfsd_file_put(rnf); nfs4_file_put_access(fp, NFS4_SHARE_ACCESS_READ); + } } static void nfsd4_finalize_deleg_timestamps(struct nfs4_delegation *dp, struct file *f) { - struct iattr ia = { .ia_valid = ATTR_ATIME | ATTR_CTIME | ATTR_MTIME }; + struct iattr ia = { .ia_valid = ATTR_ATIME | ATTR_CTIME | ATTR_MTIME | ATTR_DELEG }; struct inode *inode = file_inode(f); int ret; @@ -1757,7 +1759,7 @@ static struct nfs4_stid *find_one_sb_stid(struct nfs4_client *clp, /** * nfsd4_revoke_states - revoke all nfsv4 states associated with given filesystem - * @net: used to identify instance of nfsd (there is one per net namespace) + * @nn: used to identify instance of nfsd (there is one per net namespace) * @sb: super_block used to identify target filesystem * * All nfs4 states (open, lock, delegation, layout) held by the server instance @@ -1769,16 +1771,15 @@ static struct nfs4_stid *find_one_sb_stid(struct nfs4_client *clp, * The clients which own the states will subsequently being notified that the * states have been "admin-revoked". */ -void nfsd4_revoke_states(struct net *net, struct super_block *sb) +void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb) { - struct nfsd_net *nn = net_generic(net, nfsd_net_id); unsigned int idhashval; unsigned int sc_types; sc_types = SC_TYPE_OPEN | SC_TYPE_LOCK | SC_TYPE_DELEG | SC_TYPE_LAYOUT; spin_lock(&nn->client_lock); - for (idhashval = 0; idhashval < CLIENT_HASH_MASK; idhashval++) { + for (idhashval = 0; idhashval < CLIENT_HASH_SIZE; idhashval++) { struct list_head *head = &nn->conf_id_hashtbl[idhashval]; struct nfs4_client *clp; retry: @@ -3097,8 +3098,10 @@ static int client_states_open(struct inode *inode, struct file *file) return -ENXIO; ret = seq_open(file, &states_seq_ops); - if (ret) + if (ret) { + drop_client(clp); return ret; + } s = file->private_data; s->private = clp; return 0; @@ -5552,10 +5555,29 @@ nfsd_change_deleg_cb(struct file_lease *onlist, int arg, return -EAGAIN; } +/** + * nfsd4_deleg_lm_open_conflict - see if the given file points to an inode that has + * an existing open that would conflict with the + * desired lease. + * @filp: file to check + * @arg: type of lease that we're trying to acquire + * + * The kernel will call into this operation to determine whether there + * are conflicting opens that may prevent the deleg from being granted. + * For nfsd, that check is done at a higher level, so this trivially + * returns 0. + */ +static int +nfsd4_deleg_lm_open_conflict(struct file *filp, int arg) +{ + return 0; +} + static const struct lease_manager_operations nfsd_lease_mng_ops = { .lm_breaker_owns_lease = nfsd_breaker_owns_lease, .lm_break = nfsd_break_deleg_cb, .lm_change = nfsd_change_deleg_cb, + .lm_open_conflict = nfsd4_deleg_lm_open_conflict, }; static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4_stateowner *so, u32 seqid) @@ -6231,10 +6253,14 @@ nfsd4_add_rdaccess_to_wrdeleg(struct svc_rqst *rqstp, struct nfsd4_open *open, fp = stp->st_stid.sc_file; spin_lock(&fp->fi_lock); __nfs4_file_get_access(fp, NFS4_SHARE_ACCESS_READ); - fp = stp->st_stid.sc_file; - fp->fi_fds[O_RDONLY] = nf; - fp->fi_rdeleg_file = nf; + if (!fp->fi_fds[O_RDONLY]) { + fp->fi_fds[O_RDONLY] = nf; + nf = NULL; + } + fp->fi_rdeleg_file = nfsd_file_get(fp->fi_fds[O_RDONLY]); spin_unlock(&fp->fi_lock); + if (nf) + nfsd_file_put(nf); } return true; } @@ -6562,7 +6588,7 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfs_ok; } -void +static void nfsd4_end_grace(struct nfsd_net *nn) { /* do nothing if grace period already ended */ @@ -6595,6 +6621,33 @@ nfsd4_end_grace(struct nfsd_net *nn) */ } +/** + * nfsd4_force_end_grace - forcibly end the NFSv4 grace period + * @nn: network namespace for the server instance to be updated + * + * Forces bypass of normal grace period completion, then schedules + * the laundromat to end the grace period immediately. Does not wait + * for the grace period to fully terminate before returning. + * + * Return values: + * %true: Grace termination schedule + * %false: No action was taken + */ +bool nfsd4_force_end_grace(struct nfsd_net *nn) +{ + if (!nn->client_tracking_ops) + return false; + spin_lock(&nn->client_lock); + if (nn->grace_ended || !nn->client_tracking_active) { + spin_unlock(&nn->client_lock); + return false; + } + WRITE_ONCE(nn->grace_end_forced, true); + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + spin_unlock(&nn->client_lock); + return true; +} + /* * If we've waited a lease period but there are still clients trying to * reclaim, wait a little longer to give them a chance to finish. @@ -6604,6 +6657,8 @@ static bool clients_still_reclaiming(struct nfsd_net *nn) time64_t double_grace_period_end = nn->boot_time + 2 * nn->nfsd4_lease; + if (READ_ONCE(nn->grace_end_forced)) + return false; if (nn->track_reclaim_completes && atomic_read(&nn->nr_reclaim_complete) == nn->reclaim_str_hashtbl_size) @@ -8924,6 +8979,8 @@ static int nfs4_state_create_net(struct net *net) nn->unconf_name_tree = RB_ROOT; nn->boot_time = ktime_get_real_seconds(); nn->grace_ended = false; + nn->grace_end_forced = false; + nn->client_tracking_active = false; nn->nfsd4_manager.block_opens = true; INIT_LIST_HEAD(&nn->nfsd4_manager.list); INIT_LIST_HEAD(&nn->client_lru); @@ -9004,6 +9061,10 @@ nfs4_state_start_net(struct net *net) return ret; locks_start_grace(net, &nn->nfsd4_manager); nfsd4_client_tracking_init(net); + /* safe for laundromat to run now */ + spin_lock(&nn->client_lock); + nn->client_tracking_active = true; + spin_unlock(&nn->client_lock); if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0) goto skip_grace; printk(KERN_INFO "NFSD: starting %lld-second grace period (net %x)\n", @@ -9052,6 +9113,9 @@ nfs4_state_shutdown_net(struct net *net) shrinker_free(nn->nfsd_client_shrinker); cancel_work_sync(&nn->nfsd_shrinker_work); + spin_lock(&nn->client_lock); + nn->client_tracking_active = false; + spin_unlock(&nn->client_lock); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 30ce5851fe4c..51ef97c25456 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -3375,6 +3375,11 @@ static __be32 nfsd4_encode_fattr4_suppattr_exclcreat(struct xdr_stream *xdr, u32 supp[3]; memcpy(supp, nfsd_suppattrs[resp->cstate.minorversion], sizeof(supp)); + if (!IS_POSIXACL(d_inode(args->dentry))) + supp[0] &= ~FATTR4_WORD0_ACL; + if (!args->contextsupport) + supp[2] &= ~FATTR4_WORD2_SECURITY_LABEL; + supp[0] &= NFSD_SUPPATTR_EXCLCREAT_WORD0; supp[1] &= NFSD_SUPPATTR_EXCLCREAT_WORD1; supp[2] &= NFSD_SUPPATTR_EXCLCREAT_WORD2; diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index 5ce9a49e76ba..084fc517e9e1 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -259,6 +259,7 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size) struct path path; char *fo_path; int error; + struct nfsd_net *nn; /* sanity check */ if (size == 0) @@ -285,7 +286,13 @@ static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size) * 3. Is that directory the root of an exported file system? */ error = nlmsvc_unlock_all_by_sb(path.dentry->d_sb); - nfsd4_revoke_states(netns(file), path.dentry->d_sb); + mutex_lock(&nfsd_mutex); + nn = net_generic(netns(file), nfsd_net_id); + if (nn->nfsd_serv) + nfsd4_revoke_states(nn, path.dentry->d_sb); + else + error = -EINVAL; + mutex_unlock(&nfsd_mutex); path_put(&path); return error; @@ -1082,10 +1089,9 @@ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size) case 'Y': case 'y': case '1': - if (!nn->nfsd_serv) + if (!nfsd4_force_end_grace(nn)) return -EBUSY; trace_nfsd_end_grace(netns(file)); - nfsd4_end_grace(nn); break; default: return -EINVAL; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index e4263326ca4a..b0283213a8f5 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -233,7 +233,6 @@ void nfsd_lockd_shutdown(void); #define nfserr_noent cpu_to_be32(NFSERR_NOENT) #define nfserr_io cpu_to_be32(NFSERR_IO) #define nfserr_nxio cpu_to_be32(NFSERR_NXIO) -#define nfserr_eagain cpu_to_be32(NFSERR_EAGAIN) #define nfserr_acces cpu_to_be32(NFSERR_ACCES) #define nfserr_exist cpu_to_be32(NFSERR_EXIST) #define nfserr_xdev cpu_to_be32(NFSERR_XDEV) @@ -547,8 +546,14 @@ static inline bool nfsd_attrs_supported(u32 minorversion, const u32 *bmval) #define NFSD_SUPPATTR_EXCLCREAT_WORD1 \ (NFSD_WRITEABLE_ATTRS_WORD1 & \ ~(FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET)) +/* + * The FATTR4_WORD2_TIME_DELEG attributes are not to be allowed for + * OPEN(create) with EXCLUSIVE4_1. It doesn't make sense to set a + * delegated timestamp on a new file. + */ #define NFSD_SUPPATTR_EXCLCREAT_WORD2 \ - NFSD_WRITEABLE_ATTRS_WORD2 + (NFSD_WRITEABLE_ATTRS_WORD2 & \ + ~(FATTR4_WORD2_TIME_DELEG_ACCESS | FATTR4_WORD2_TIME_DELEG_MODIFY)) extern int nfsd4_is_junction(struct dentry *dentry); extern int register_cld_notifier(void); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index b08ae85d53ef..f1cc223ecee2 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -406,26 +406,26 @@ static void nfsd_shutdown_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - if (!nn->nfsd_net_up) - return; - - percpu_ref_kill_and_confirm(&nn->nfsd_net_ref, nfsd_net_done); - wait_for_completion(&nn->nfsd_net_confirm_done); - - nfsd_export_flush(net); - nfs4_state_shutdown_net(net); - nfsd_reply_cache_shutdown(nn); - nfsd_file_cache_shutdown_net(net); - if (nn->lockd_up) { - lockd_down(net); - nn->lockd_up = false; + if (nn->nfsd_net_up) { + percpu_ref_kill_and_confirm(&nn->nfsd_net_ref, nfsd_net_done); + wait_for_completion(&nn->nfsd_net_confirm_done); + + nfsd_export_flush(net); + nfs4_state_shutdown_net(net); + nfsd_reply_cache_shutdown(nn); + nfsd_file_cache_shutdown_net(net); + if (nn->lockd_up) { + lockd_down(net); + nn->lockd_up = false; + } + wait_for_completion(&nn->nfsd_net_free_done); } - wait_for_completion(&nn->nfsd_net_free_done); percpu_ref_exit(&nn->nfsd_net_ref); + if (nn->nfsd_net_up) + nfsd_shutdown_generic(); nn->nfsd_net_up = false; - nfsd_shutdown_generic(); } static DEFINE_SPINLOCK(nfsd_notifier_lock); @@ -615,12 +615,15 @@ int nfsd_create_serv(struct net *net) serv = svc_create_pooled(nfsd_programs, ARRAY_SIZE(nfsd_programs), &nn->nfsd_svcstats, nfsd_max_blksize, nfsd); - if (serv == NULL) + if (serv == NULL) { + percpu_ref_exit(&nn->nfsd_net_ref); return -ENOMEM; + } error = svc_bind(serv, net); if (error < 0) { svc_destroy(&serv); + percpu_ref_exit(&nn->nfsd_net_ref); return error; } spin_lock(&nfsd_notifier_lock); diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index b052c1effdc5..508b7e36d846 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -841,15 +841,15 @@ static inline void get_nfs4_file(struct nfs4_file *fi) struct nfsd_file *find_any_file(struct nfs4_file *f); #ifdef CONFIG_NFSD_V4 -void nfsd4_revoke_states(struct net *net, struct super_block *sb); +void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb); #else -static inline void nfsd4_revoke_states(struct net *net, struct super_block *sb) +static inline void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb) { } #endif /* grace period management */ -void nfsd4_end_grace(struct nfsd_net *nn); +bool nfsd4_force_end_grace(struct nfsd_net *nn); /* nfs4recover operations */ extern int nfsd4_client_tracking_init(struct net *net); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 964cf922ad83..168d3ccc8155 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -2865,8 +2865,8 @@ nfsd_permission(struct svc_cred *cred, struct svc_export *exp, /* Allow read access to binaries even when mode 111 */ if (err == -EACCES && S_ISREG(inode->i_mode) && - (acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE) || - acc == (NFSD_MAY_READ | NFSD_MAY_READ_IF_EXEC))) + (((acc & NFSD_MAY_MASK) == NFSD_MAY_READ) && + (acc & (NFSD_MAY_OWNER_OVERRIDE | NFSD_MAY_READ_IF_EXEC)))) err = inode_permission(&nop_mnt_idmap, inode, MAY_EXEC); return err? nfserrno(err) : 0; diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index ded2900d423f..e192dca4a679 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -67,7 +67,8 @@ static inline bool nfsd_attrs_valid(struct nfsd_attrs *attrs) struct iattr *iap = attrs->na_iattr; return (iap->ia_valid || (attrs->na_seclabel && - attrs->na_seclabel->len)); + attrs->na_seclabel->len) || + attrs->na_pacl || attrs->na_dpacl); } __be32 nfserrno (int errno); diff --git a/fs/pidfs.c b/fs/pidfs.c index dba703d4ce4a..1e20e36e0ed5 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -517,14 +517,18 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) switch (cmd) { /* Namespaces that hang of nsproxy. */ case PIDFD_GET_CGROUP_NAMESPACE: +#ifdef CONFIG_CGROUPS if (!ns_ref_get(nsp->cgroup_ns)) break; ns_common = to_ns_common(nsp->cgroup_ns); +#endif break; case PIDFD_GET_IPC_NAMESPACE: +#ifdef CONFIG_IPC_NS if (!ns_ref_get(nsp->ipc_ns)) break; ns_common = to_ns_common(nsp->ipc_ns); +#endif break; case PIDFD_GET_MNT_NAMESPACE: if (!ns_ref_get(nsp->mnt_ns)) @@ -532,32 +536,43 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) ns_common = to_ns_common(nsp->mnt_ns); break; case PIDFD_GET_NET_NAMESPACE: +#ifdef CONFIG_NET_NS if (!ns_ref_get(nsp->net_ns)) break; ns_common = to_ns_common(nsp->net_ns); +#endif break; case PIDFD_GET_PID_FOR_CHILDREN_NAMESPACE: +#ifdef CONFIG_PID_NS if (!ns_ref_get(nsp->pid_ns_for_children)) break; ns_common = to_ns_common(nsp->pid_ns_for_children); +#endif break; case PIDFD_GET_TIME_NAMESPACE: +#ifdef CONFIG_TIME_NS if (!ns_ref_get(nsp->time_ns)) break; ns_common = to_ns_common(nsp->time_ns); +#endif break; case PIDFD_GET_TIME_FOR_CHILDREN_NAMESPACE: +#ifdef CONFIG_TIME_NS if (!ns_ref_get(nsp->time_ns_for_children)) break; ns_common = to_ns_common(nsp->time_ns_for_children); +#endif break; case PIDFD_GET_UTS_NAMESPACE: +#ifdef CONFIG_UTS_NS if (!ns_ref_get(nsp->uts_ns)) break; ns_common = to_ns_common(nsp->uts_ns); +#endif break; /* Namespaces that don't hang of nsproxy. */ case PIDFD_GET_USER_NAMESPACE: +#ifdef CONFIG_USER_NS scoped_guard(rcu) { struct user_namespace *user_ns; @@ -566,8 +581,10 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) break; ns_common = to_ns_common(user_ns); } +#endif break; case PIDFD_GET_PID_NAMESPACE: +#ifdef CONFIG_PID_NS scoped_guard(rcu) { struct pid_namespace *pid_ns; @@ -576,6 +593,7 @@ static long pidfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg) break; ns_common = to_ns_common(pid_ns); } +#endif break; default: return -ENOIOCTLCMD; diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c index c2de97e4ad59..d4291d3a9a48 100644 --- a/fs/smb/client/fs_context.c +++ b/fs/smb/client/fs_context.c @@ -1139,6 +1139,8 @@ static int smb3_reconfigure(struct fs_context *fc) rc = smb3_sync_session_ctx_passwords(cifs_sb, ses); if (rc) { mutex_unlock(&ses->session_mutex); + kfree_sensitive(new_password); + kfree_sensitive(new_password2); return rc; } diff --git a/fs/smb/client/ioctl.c b/fs/smb/client/ioctl.c index 0a9935ce05a5..d1b153209424 100644 --- a/fs/smb/client/ioctl.c +++ b/fs/smb/client/ioctl.c @@ -588,6 +588,9 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) break; default: cifs_dbg(FYI, "unsupported ioctl\n"); + trace_smb3_unsupported_ioctl(xid, + pSMBFile ? pSMBFile->fid.persistent_fid : 0, + command); break; } cifs_ioc_exit: diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index a16ded46b5a2..c1aaf77e187b 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -1905,6 +1905,12 @@ retry: src_off_prev = src_off; dst_off_prev = dst_off; + /* + * __counted_by_le(ChunkCount): set to allocated chunks before + * populating Chunks[] + */ + cc_req->ChunkCount = cpu_to_le32(chunk_count); + chunks = 0; copy_bytes = 0; copy_bytes_left = umin(total_bytes_left, tcon->max_bytes_copy); diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index b0fbc2df642e..a584a7743113 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -1579,6 +1579,7 @@ DEFINE_EVENT(smb3_ioctl_class, smb3_##name, \ TP_ARGS(xid, fid, command)) DEFINE_SMB3_IOCTL_EVENT(ioctl); +DEFINE_SMB3_IOCTL_EVENT(unsupported_ioctl); DECLARE_EVENT_CLASS(smb3_shutdown_class, TP_PROTO(__u32 flags, diff --git a/fs/smb/server/auth.c b/fs/smb/server/auth.c index f2767c4b5132..09af55b71153 100644 --- a/fs/smb/server/auth.c +++ b/fs/smb/server/auth.c @@ -714,7 +714,7 @@ void ksmbd_gen_smb311_encryptionkey(struct ksmbd_conn *conn, int ksmbd_gen_preauth_integrity_hash(struct ksmbd_conn *conn, char *buf, __u8 *pi_hash) { - struct smb2_hdr *rcv_hdr = smb2_get_msg(buf); + struct smb2_hdr *rcv_hdr = smb_get_msg(buf); char *all_bytes_msg = (char *)&rcv_hdr->ProtocolId; int msg_size = get_rfc1002_len(buf); struct sha512_ctx sha_ctx; @@ -841,7 +841,7 @@ int ksmbd_crypt_message(struct ksmbd_work *work, struct kvec *iov, unsigned int nvec, int enc) { struct ksmbd_conn *conn = work->conn; - struct smb2_transform_hdr *tr_hdr = smb2_get_msg(iov[0].iov_base); + struct smb2_transform_hdr *tr_hdr = smb_get_msg(iov[0].iov_base); unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20; int rc; struct scatterlist *sg; diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c index b6b4f1286b9c..6cac48c8fbe8 100644 --- a/fs/smb/server/connection.c +++ b/fs/smb/server/connection.c @@ -295,8 +295,9 @@ bool ksmbd_conn_alive(struct ksmbd_conn *conn) return true; } -#define SMB1_MIN_SUPPORTED_HEADER_SIZE (sizeof(struct smb_hdr)) -#define SMB2_MIN_SUPPORTED_HEADER_SIZE (sizeof(struct smb2_hdr) + 4) +/* "+2" for BCC field (ByteCount, 2 bytes) */ +#define SMB1_MIN_SUPPORTED_PDU_SIZE (sizeof(struct smb_hdr) + 2) +#define SMB2_MIN_SUPPORTED_PDU_SIZE (sizeof(struct smb2_pdu)) /** * ksmbd_conn_handler_loop() - session thread to listen on new smb requests @@ -363,7 +364,7 @@ recheck: if (pdu_size > MAX_STREAM_PROT_LEN) break; - if (pdu_size < SMB1_MIN_SUPPORTED_HEADER_SIZE) + if (pdu_size < SMB1_MIN_SUPPORTED_PDU_SIZE) break; /* 4 for rfc1002 length field */ @@ -394,9 +395,9 @@ recheck: if (!ksmbd_smb_request(conn)) break; - if (((struct smb2_hdr *)smb2_get_msg(conn->request_buf))->ProtocolId == + if (((struct smb2_hdr *)smb_get_msg(conn->request_buf))->ProtocolId == SMB2_PROTO_NUMBER) { - if (pdu_size < SMB2_MIN_SUPPORTED_HEADER_SIZE) + if (pdu_size < SMB2_MIN_SUPPORTED_PDU_SIZE) break; } diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c index 1f07ebf431d7..a5967ac46604 100644 --- a/fs/smb/server/oplock.c +++ b/fs/smb/server/oplock.c @@ -637,7 +637,7 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) goto out; } - rsp_hdr = smb2_get_msg(work->response_buf); + rsp_hdr = smb_get_msg(work->response_buf); memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; @@ -651,7 +651,7 @@ static void __smb2_oplock_break_noti(struct work_struct *wk) rsp_hdr->SessionId = 0; memset(rsp_hdr->Signature, 0, 16); - rsp = smb2_get_msg(work->response_buf); + rsp = smb_get_msg(work->response_buf); rsp->StructureSize = cpu_to_le16(24); if (!br_info->open_trunc && @@ -744,7 +744,7 @@ static void __smb2_lease_break_noti(struct work_struct *wk) goto out; } - rsp_hdr = smb2_get_msg(work->response_buf); + rsp_hdr = smb_get_msg(work->response_buf); memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; @@ -758,7 +758,7 @@ static void __smb2_lease_break_noti(struct work_struct *wk) rsp_hdr->SessionId = 0; memset(rsp_hdr->Signature, 0, 16); - rsp = smb2_get_msg(work->response_buf); + rsp = smb_get_msg(work->response_buf); rsp->StructureSize = cpu_to_le16(44); rsp->Epoch = br_info->epoch; rsp->Flags = 0; diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c index 3cea16050e4f..554ae90df906 100644 --- a/fs/smb/server/server.c +++ b/fs/smb/server/server.c @@ -95,7 +95,7 @@ static inline int check_conn_state(struct ksmbd_work *work) if (ksmbd_conn_exiting(work->conn) || ksmbd_conn_need_reconnect(work->conn)) { - rsp_hdr = work->response_buf; + rsp_hdr = smb_get_msg(work->response_buf); rsp_hdr->Status.CifsError = STATUS_CONNECTION_DISCONNECTED; return 1; } diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 8aa483800014..2fcd0d4d1fb0 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -47,8 +47,8 @@ static void __wbuf(struct ksmbd_work *work, void **req, void **rsp) *req = ksmbd_req_buf_next(work); *rsp = ksmbd_resp_buf_next(work); } else { - *req = smb2_get_msg(work->request_buf); - *rsp = smb2_get_msg(work->response_buf); + *req = smb_get_msg(work->request_buf); + *rsp = smb_get_msg(work->response_buf); } } @@ -146,7 +146,7 @@ void smb2_set_err_rsp(struct ksmbd_work *work) if (work->next_smb2_rcv_hdr_off) err_rsp = ksmbd_resp_buf_next(work); else - err_rsp = smb2_get_msg(work->response_buf); + err_rsp = smb_get_msg(work->response_buf); if (err_rsp->hdr.Status != STATUS_STOPPED_ON_SYMLINK) { int err; @@ -172,7 +172,7 @@ void smb2_set_err_rsp(struct ksmbd_work *work) */ bool is_smb2_neg_cmd(struct ksmbd_work *work) { - struct smb2_hdr *hdr = smb2_get_msg(work->request_buf); + struct smb2_hdr *hdr = smb_get_msg(work->request_buf); /* is it SMB2 header ? */ if (hdr->ProtocolId != SMB2_PROTO_NUMBER) @@ -196,7 +196,7 @@ bool is_smb2_neg_cmd(struct ksmbd_work *work) */ bool is_smb2_rsp(struct ksmbd_work *work) { - struct smb2_hdr *hdr = smb2_get_msg(work->response_buf); + struct smb2_hdr *hdr = smb_get_msg(work->response_buf); /* is it SMB2 header ? */ if (hdr->ProtocolId != SMB2_PROTO_NUMBER) @@ -222,7 +222,7 @@ u16 get_smb2_cmd_val(struct ksmbd_work *work) if (work->next_smb2_rcv_hdr_off) rcv_hdr = ksmbd_req_buf_next(work); else - rcv_hdr = smb2_get_msg(work->request_buf); + rcv_hdr = smb_get_msg(work->request_buf); return le16_to_cpu(rcv_hdr->Command); } @@ -235,7 +235,7 @@ void set_smb2_rsp_status(struct ksmbd_work *work, __le32 err) { struct smb2_hdr *rsp_hdr; - rsp_hdr = smb2_get_msg(work->response_buf); + rsp_hdr = smb_get_msg(work->response_buf); rsp_hdr->Status = err; work->iov_idx = 0; @@ -258,7 +258,7 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) struct ksmbd_conn *conn = work->conn; int err; - rsp_hdr = smb2_get_msg(work->response_buf); + rsp_hdr = smb_get_msg(work->response_buf); memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); rsp_hdr->ProtocolId = SMB2_PROTO_NUMBER; rsp_hdr->StructureSize = SMB2_HEADER_STRUCTURE_SIZE; @@ -272,7 +272,7 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) rsp_hdr->SessionId = 0; memset(rsp_hdr->Signature, 0, 16); - rsp = smb2_get_msg(work->response_buf); + rsp = smb_get_msg(work->response_buf); WARN_ON(ksmbd_conn_good(conn)); @@ -446,7 +446,7 @@ static void init_chained_smb2_rsp(struct ksmbd_work *work) */ bool is_chained_smb2_message(struct ksmbd_work *work) { - struct smb2_hdr *hdr = smb2_get_msg(work->request_buf); + struct smb2_hdr *hdr = smb_get_msg(work->request_buf); unsigned int len, next_cmd; if (hdr->ProtocolId != SMB2_PROTO_NUMBER) @@ -497,8 +497,8 @@ bool is_chained_smb2_message(struct ksmbd_work *work) */ int init_smb2_rsp_hdr(struct ksmbd_work *work) { - struct smb2_hdr *rsp_hdr = smb2_get_msg(work->response_buf); - struct smb2_hdr *rcv_hdr = smb2_get_msg(work->request_buf); + struct smb2_hdr *rsp_hdr = smb_get_msg(work->response_buf); + struct smb2_hdr *rcv_hdr = smb_get_msg(work->request_buf); memset(rsp_hdr, 0, sizeof(struct smb2_hdr) + 2); rsp_hdr->ProtocolId = rcv_hdr->ProtocolId; @@ -527,7 +527,7 @@ int init_smb2_rsp_hdr(struct ksmbd_work *work) */ int smb2_allocate_rsp_buf(struct ksmbd_work *work) { - struct smb2_hdr *hdr = smb2_get_msg(work->request_buf); + struct smb2_hdr *hdr = smb_get_msg(work->request_buf); size_t small_sz = MAX_CIFS_SMALL_BUFFER_SIZE; size_t large_sz = small_sz + work->conn->vals->max_trans_size; size_t sz = small_sz; @@ -543,7 +543,7 @@ int smb2_allocate_rsp_buf(struct ksmbd_work *work) offsetof(struct smb2_query_info_req, OutputBufferLength)) return -EINVAL; - req = smb2_get_msg(work->request_buf); + req = smb_get_msg(work->request_buf); if ((req->InfoType == SMB2_O_INFO_FILE && (req->FileInfoClass == FILE_FULL_EA_INFORMATION || req->FileInfoClass == FILE_ALL_INFORMATION)) || @@ -712,10 +712,10 @@ void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status) } in_work->conn = work->conn; - memcpy(smb2_get_msg(in_work->response_buf), ksmbd_resp_buf_next(work), + memcpy(smb_get_msg(in_work->response_buf), ksmbd_resp_buf_next(work), __SMB2_HEADER_STRUCTURE_SIZE); - rsp_hdr = smb2_get_msg(in_work->response_buf); + rsp_hdr = smb_get_msg(in_work->response_buf); rsp_hdr->Flags |= SMB2_FLAGS_ASYNC_COMMAND; rsp_hdr->Id.AsyncId = cpu_to_le64(work->async_id); smb2_set_err_rsp(in_work); @@ -1093,8 +1093,8 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, int smb2_handle_negotiate(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_negotiate_req *req = smb2_get_msg(work->request_buf); - struct smb2_negotiate_rsp *rsp = smb2_get_msg(work->response_buf); + struct smb2_negotiate_req *req = smb_get_msg(work->request_buf); + struct smb2_negotiate_rsp *rsp = smb_get_msg(work->response_buf); int rc = 0; unsigned int smb2_buf_len, smb2_neg_size, neg_ctxt_len = 0; __le32 status; @@ -2281,7 +2281,7 @@ static noinline int create_smb2_pipe(struct ksmbd_work *work) { struct smb2_create_rsp *rsp; struct smb2_create_req *req; - int id; + int id = -1; int err; char *name; @@ -2338,6 +2338,9 @@ out: break; } + if (id >= 0) + ksmbd_session_rpc_close(work->sess, id); + if (!IS_ERR(name)) kfree(name); @@ -2809,6 +2812,7 @@ static int parse_durable_handle_context(struct ksmbd_work *work, SMB2_CLIENT_GUID_SIZE)) { if (!(req->hdr.Flags & SMB2_FLAGS_REPLAY_OPERATION)) { err = -ENOEXEC; + ksmbd_put_durable_fd(dh_info->fp); goto out; } @@ -3006,10 +3010,10 @@ int smb2_open(struct ksmbd_work *work) file_info = FILE_OPENED; rc = ksmbd_vfs_getattr(&fp->filp->f_path, &stat); + ksmbd_put_durable_fd(fp); if (rc) goto err_out2; - ksmbd_put_durable_fd(fp); goto reconnected_fp; } } else if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) @@ -4923,8 +4927,10 @@ static int get_file_all_info(struct ksmbd_work *work, ret = vfs_getattr(&fp->filp->f_path, &stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); - if (ret) + if (ret) { + kfree(filename); return ret; + } ksmbd_debug(SMB, "filename = %s\n", filename); delete_pending = ksmbd_inode_pending_delete(fp); @@ -5967,7 +5973,7 @@ out: */ int smb2_echo(struct ksmbd_work *work) { - struct smb2_echo_rsp *rsp = smb2_get_msg(work->response_buf); + struct smb2_echo_rsp *rsp = smb_get_msg(work->response_buf); ksmbd_debug(SMB, "Received smb2 echo request\n"); @@ -6520,8 +6526,8 @@ int smb2_set_info(struct ksmbd_work *work) pid = work->compound_pfid; } } else { - req = smb2_get_msg(work->request_buf); - rsp = smb2_get_msg(work->response_buf); + req = smb_get_msg(work->request_buf); + rsp = smb_get_msg(work->response_buf); } if (!test_tree_conn_flag(work->tcon, KSMBD_TREE_CONN_FLAG_WRITABLE)) { @@ -6754,8 +6760,8 @@ int smb2_read(struct ksmbd_work *work) pid = work->compound_pfid; } } else { - req = smb2_get_msg(work->request_buf); - rsp = smb2_get_msg(work->response_buf); + req = smb_get_msg(work->request_buf); + rsp = smb_get_msg(work->response_buf); } if (!has_file_id(id)) { @@ -7183,7 +7189,7 @@ out: int smb2_cancel(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; - struct smb2_hdr *hdr = smb2_get_msg(work->request_buf); + struct smb2_hdr *hdr = smb_get_msg(work->request_buf); struct smb2_hdr *chdr; struct ksmbd_work *iter; struct list_head *command_list; @@ -7200,7 +7206,7 @@ int smb2_cancel(struct ksmbd_work *work) spin_lock(&conn->request_lock); list_for_each_entry(iter, command_list, async_request_entry) { - chdr = smb2_get_msg(iter->request_buf); + chdr = smb_get_msg(iter->request_buf); if (iter->async_id != le64_to_cpu(hdr->Id.AsyncId)) @@ -7221,7 +7227,7 @@ int smb2_cancel(struct ksmbd_work *work) spin_lock(&conn->request_lock); list_for_each_entry(iter, command_list, request_entry) { - chdr = smb2_get_msg(iter->request_buf); + chdr = smb_get_msg(iter->request_buf); if (chdr->MessageId != hdr->MessageId || iter == work) @@ -8151,8 +8157,8 @@ int smb2_ioctl(struct ksmbd_work *work) id = work->compound_fid; } } else { - req = smb2_get_msg(work->request_buf); - rsp = smb2_get_msg(work->response_buf); + req = smb_get_msg(work->request_buf); + rsp = smb_get_msg(work->response_buf); } if (!has_file_id(id)) @@ -8817,7 +8823,7 @@ int smb2_notify(struct ksmbd_work *work) */ bool smb2_is_sign_req(struct ksmbd_work *work, unsigned int command) { - struct smb2_hdr *rcv_hdr2 = smb2_get_msg(work->request_buf); + struct smb2_hdr *rcv_hdr2 = smb_get_msg(work->request_buf); if ((rcv_hdr2->Flags & SMB2_FLAGS_SIGNED) && command != SMB2_NEGOTIATE_HE && @@ -8842,7 +8848,7 @@ int smb2_check_sign_req(struct ksmbd_work *work) struct kvec iov[1]; size_t len; - hdr = smb2_get_msg(work->request_buf); + hdr = smb_get_msg(work->request_buf); if (work->next_smb2_rcv_hdr_off) hdr = ksmbd_req_buf_next(work); @@ -8916,7 +8922,7 @@ int smb3_check_sign_req(struct ksmbd_work *work) struct kvec iov[1]; size_t len; - hdr = smb2_get_msg(work->request_buf); + hdr = smb_get_msg(work->request_buf); if (work->next_smb2_rcv_hdr_off) hdr = ksmbd_req_buf_next(work); @@ -9049,7 +9055,7 @@ void smb3_preauth_hash_rsp(struct ksmbd_work *work) static void fill_transform_hdr(void *tr_buf, char *old_buf, __le16 cipher_type) { struct smb2_transform_hdr *tr_hdr = tr_buf + 4; - struct smb2_hdr *hdr = smb2_get_msg(old_buf); + struct smb2_hdr *hdr = smb_get_msg(old_buf); unsigned int orig_len = get_rfc1002_len(old_buf); /* tr_buf must be cleared by the caller */ @@ -9088,7 +9094,7 @@ int smb3_encrypt_resp(struct ksmbd_work *work) bool smb3_is_transform_hdr(void *buf) { - struct smb2_transform_hdr *trhdr = smb2_get_msg(buf); + struct smb2_transform_hdr *trhdr = smb_get_msg(buf); return trhdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM; } @@ -9100,7 +9106,7 @@ int smb3_decrypt_req(struct ksmbd_work *work) unsigned int pdu_length = get_rfc1002_len(buf); struct kvec iov[2]; int buf_data_size = pdu_length - sizeof(struct smb2_transform_hdr); - struct smb2_transform_hdr *tr_hdr = smb2_get_msg(buf); + struct smb2_transform_hdr *tr_hdr = smb_get_msg(buf); int rc = 0; if (pdu_length < sizeof(struct smb2_transform_hdr) || @@ -9141,7 +9147,7 @@ bool smb3_11_final_sess_setup_resp(struct ksmbd_work *work) { struct ksmbd_conn *conn = work->conn; struct ksmbd_session *sess = work->sess; - struct smb2_hdr *rsp = smb2_get_msg(work->response_buf); + struct smb2_hdr *rsp = smb_get_msg(work->response_buf); if (conn->dialect < SMB30_PROT_ID) return false; diff --git a/fs/smb/server/smb2pdu.h b/fs/smb/server/smb2pdu.h index 66cdc8e4a648..257c6d26df26 100644 --- a/fs/smb/server/smb2pdu.h +++ b/fs/smb/server/smb2pdu.h @@ -383,15 +383,6 @@ int smb2_ioctl(struct ksmbd_work *work); int smb2_oplock_break(struct ksmbd_work *work); int smb2_notify(struct ksmbd_work *ksmbd_work); -/* - * Get the body of the smb2 message excluding the 4 byte rfc1002 headers - * from request/response buffer. - */ -static inline void *smb2_get_msg(void *buf) -{ - return buf + 4; -} - #define POSIX_TYPE_FILE 0 #define POSIX_TYPE_DIR 1 #define POSIX_TYPE_SYMLINK 2 diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c index b23203a1c286..1cd7e738434d 100644 --- a/fs/smb/server/smb_common.c +++ b/fs/smb/server/smb_common.c @@ -140,7 +140,7 @@ int ksmbd_verify_smb_message(struct ksmbd_work *work) if (smb2_hdr->ProtocolId == SMB2_PROTO_NUMBER) return ksmbd_smb2_check_message(work); - hdr = work->request_buf; + hdr = smb_get_msg(work->request_buf); if (*(__le32 *)hdr->Protocol == SMB1_PROTO_NUMBER && hdr->Command == SMB_COM_NEGOTIATE) { work->conn->outstanding_credits++; @@ -163,7 +163,7 @@ bool ksmbd_smb_request(struct ksmbd_conn *conn) if (conn->request_buf[0] != 0) return false; - proto = (__le32 *)smb2_get_msg(conn->request_buf); + proto = (__le32 *)smb_get_msg(conn->request_buf); if (*proto == SMB2_COMPRESSION_TRANSFORM_ID) { pr_err_ratelimited("smb2 compression not support yet"); return false; @@ -259,14 +259,14 @@ int ksmbd_lookup_dialect_by_id(__le16 *cli_dialects, __le16 dialects_count) static int ksmbd_negotiate_smb_dialect(void *buf) { int smb_buf_length = get_rfc1002_len(buf); - __le32 proto = ((struct smb2_hdr *)smb2_get_msg(buf))->ProtocolId; + __le32 proto = ((struct smb2_hdr *)smb_get_msg(buf))->ProtocolId; if (proto == SMB2_PROTO_NUMBER) { struct smb2_negotiate_req *req; int smb2_neg_size = offsetof(struct smb2_negotiate_req, Dialects); - req = (struct smb2_negotiate_req *)smb2_get_msg(buf); + req = (struct smb2_negotiate_req *)smb_get_msg(buf); if (smb2_neg_size > smb_buf_length) goto err_out; @@ -278,15 +278,14 @@ static int ksmbd_negotiate_smb_dialect(void *buf) req->DialectCount); } - proto = *(__le32 *)((struct smb_hdr *)buf)->Protocol; if (proto == SMB1_PROTO_NUMBER) { struct smb_negotiate_req *req; - req = (struct smb_negotiate_req *)buf; + req = (struct smb_negotiate_req *)smb_get_msg(buf); if (le16_to_cpu(req->ByteCount) < 2) goto err_out; - if (offsetof(struct smb_negotiate_req, DialectsArray) - 4 + + if (offsetof(struct smb_negotiate_req, DialectsArray) + le16_to_cpu(req->ByteCount) > smb_buf_length) { goto err_out; } @@ -320,8 +319,8 @@ static u16 get_smb1_cmd_val(struct ksmbd_work *work) */ static int init_smb1_rsp_hdr(struct ksmbd_work *work) { - struct smb_hdr *rsp_hdr = (struct smb_hdr *)work->response_buf; - struct smb_hdr *rcv_hdr = (struct smb_hdr *)work->request_buf; + struct smb_hdr *rsp_hdr = (struct smb_hdr *)smb_get_msg(work->response_buf); + struct smb_hdr *rcv_hdr = (struct smb_hdr *)smb_get_msg(work->request_buf); rsp_hdr->Command = SMB_COM_NEGOTIATE; *(__le32 *)rsp_hdr->Protocol = SMB1_PROTO_NUMBER; @@ -412,9 +411,10 @@ static int init_smb1_server(struct ksmbd_conn *conn) int ksmbd_init_smb_server(struct ksmbd_conn *conn) { + struct smb_hdr *rcv_hdr = (struct smb_hdr *)smb_get_msg(conn->request_buf); __le32 proto; - proto = *(__le32 *)((struct smb_hdr *)conn->request_buf)->Protocol; + proto = *(__le32 *)rcv_hdr->Protocol; if (conn->need_neg == false) { if (proto == SMB1_PROTO_NUMBER) return -EINVAL; @@ -572,12 +572,12 @@ static int __smb2_negotiate(struct ksmbd_conn *conn) static int smb_handle_negotiate(struct ksmbd_work *work) { - struct smb_negotiate_rsp *neg_rsp = work->response_buf; + struct smb_negotiate_rsp *neg_rsp = smb_get_msg(work->response_buf); ksmbd_debug(SMB, "Unsupported SMB1 protocol\n"); - if (ksmbd_iov_pin_rsp(work, (void *)neg_rsp + 4, - sizeof(struct smb_negotiate_rsp) - 4)) + if (ksmbd_iov_pin_rsp(work, (void *)neg_rsp, + sizeof(struct smb_negotiate_rsp))) return -ENOMEM; neg_rsp->hdr.Status.CifsError = STATUS_SUCCESS; diff --git a/fs/smb/server/smb_common.h b/fs/smb/server/smb_common.h index 95bf1465387b..ddd6867c50b2 100644 --- a/fs/smb/server/smb_common.h +++ b/fs/smb/server/smb_common.h @@ -203,4 +203,13 @@ unsigned int ksmbd_server_side_copy_max_chunk_size(void); unsigned int ksmbd_server_side_copy_max_total_size(void); bool is_asterisk(char *p); __le32 smb_map_generic_desired_access(__le32 daccess); + +/* + * Get the body of the smb message excluding the 4 byte rfc1002 headers + * from request/response buffer. + */ +static inline void *smb_get_msg(void *buf) +{ + return buf + 4; +} #endif /* __SMB_SERVER_COMMON_H__ */ diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index f585359684d4..e4273932e7e4 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -1353,14 +1353,12 @@ static int get_sg_list(void *buf, int size, struct scatterlist *sg_list, int nen static int get_mapped_sg_list(struct ib_device *device, void *buf, int size, struct scatterlist *sg_list, int nentries, - enum dma_data_direction dir) + enum dma_data_direction dir, int *npages) { - int npages; - - npages = get_sg_list(buf, size, sg_list, nentries); - if (npages < 0) + *npages = get_sg_list(buf, size, sg_list, nentries); + if (*npages < 0) return -EINVAL; - return ib_dma_map_sg(device, sg_list, npages, dir); + return ib_dma_map_sg(device, sg_list, *npages, dir); } static int post_sendmsg(struct smbdirect_socket *sc, @@ -1431,12 +1429,13 @@ static int smb_direct_post_send_data(struct smbdirect_socket *sc, for (i = 0; i < niov; i++) { struct ib_sge *sge; int sg_cnt; + int npages; sg_init_table(sg, SMBDIRECT_SEND_IO_MAX_SGE - 1); sg_cnt = get_mapped_sg_list(sc->ib.dev, iov[i].iov_base, iov[i].iov_len, sg, SMBDIRECT_SEND_IO_MAX_SGE - 1, - DMA_TO_DEVICE); + DMA_TO_DEVICE, &npages); if (sg_cnt <= 0) { pr_err("failed to map buffer\n"); ret = -ENOMEM; @@ -1444,7 +1443,7 @@ static int smb_direct_post_send_data(struct smbdirect_socket *sc, } else if (sg_cnt + msg->num_sge > SMBDIRECT_SEND_IO_MAX_SGE) { pr_err("buffer not fitted into sges\n"); ret = -E2BIG; - ib_dma_unmap_sg(sc->ib.dev, sg, sg_cnt, + ib_dma_unmap_sg(sc->ib.dev, sg, npages, DMA_TO_DEVICE); goto err; } @@ -2708,6 +2707,7 @@ int ksmbd_rdma_init(void) { int ret; + smb_direct_port = SMB_DIRECT_PORT_INFINIBAND; smb_direct_listener.cm_id = NULL; ret = ib_register_client(&smb_direct_ib_client); diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c index f891344bd76b..b8e648b8300f 100644 --- a/fs/smb/server/vfs.c +++ b/fs/smb/server/vfs.c @@ -1227,7 +1227,7 @@ int ksmbd_vfs_kern_path(struct ksmbd_work *work, char *filepath, } /** - * ksmbd_vfs_kern_path_start_remove() - lookup a file and get path info prior to removal + * ksmbd_vfs_kern_path_start_removing() - lookup a file and get path info prior to removal * @work: work * @filepath: file path that is relative to share * @flags: lookup flags diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index d97295eaebe6..c19d6d713780 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -848,15 +848,16 @@ sparse_alloc: * invalid inode records, such as records that start at agbno 0 * or extend beyond the AG. * - * Set min agbno to the first aligned, non-zero agbno and max to - * the last aligned agbno that is at least one full chunk from - * the end of the AG. + * Set min agbno to the first chunk aligned, non-zero agbno and + * max to one less than the last chunk aligned agbno from the + * end of the AG. We subtract 1 from max so that the cluster + * allocation alignment takes over and allows allocation within + * the last full inode chunk in the AG. */ args.min_agbno = args.mp->m_sb.sb_inoalignmt; args.max_agbno = round_down(xfs_ag_block_count(args.mp, pag_agno(pag)), - args.mp->m_sb.sb_inoalignmt) - - igeo->ialloc_blks; + args.mp->m_sb.sb_inoalignmt) - 1; error = xfs_alloc_vextent_near_bno(&args, xfs_agbno_to_fsb(pag, diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c index 9186c58e83d5..be16efaa6925 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.c +++ b/fs/xfs/libxfs/xfs_rtgroup.c @@ -48,6 +48,31 @@ xfs_rtgroup_min_block( return 0; } +/* Compute the number of rt extents in this realtime group. */ +static xfs_rtxnum_t +__xfs_rtgroup_extents( + struct xfs_mount *mp, + xfs_rgnumber_t rgno, + xfs_rgnumber_t rgcount, + xfs_rtbxlen_t rextents) +{ + ASSERT(rgno < rgcount); + if (rgno == rgcount - 1) + return rextents - ((xfs_rtxnum_t)rgno * mp->m_sb.sb_rgextents); + + ASSERT(xfs_has_rtgroups(mp)); + return mp->m_sb.sb_rgextents; +} + +xfs_rtxnum_t +xfs_rtgroup_extents( + struct xfs_mount *mp, + xfs_rgnumber_t rgno) +{ + return __xfs_rtgroup_extents(mp, rgno, mp->m_sb.sb_rgcount, + mp->m_sb.sb_rextents); +} + /* Precompute this group's geometry */ void xfs_rtgroup_calc_geometry( @@ -58,7 +83,8 @@ xfs_rtgroup_calc_geometry( xfs_rtbxlen_t rextents) { rtg->rtg_extents = __xfs_rtgroup_extents(mp, rgno, rgcount, rextents); - rtg_group(rtg)->xg_block_count = rtg->rtg_extents * mp->m_sb.sb_rextsize; + rtg_group(rtg)->xg_block_count = + rtg->rtg_extents * mp->m_sb.sb_rextsize; rtg_group(rtg)->xg_min_gbno = xfs_rtgroup_min_block(mp, rgno); } @@ -136,31 +162,6 @@ out_unwind_new_rtgs: return error; } -/* Compute the number of rt extents in this realtime group. */ -xfs_rtxnum_t -__xfs_rtgroup_extents( - struct xfs_mount *mp, - xfs_rgnumber_t rgno, - xfs_rgnumber_t rgcount, - xfs_rtbxlen_t rextents) -{ - ASSERT(rgno < rgcount); - if (rgno == rgcount - 1) - return rextents - ((xfs_rtxnum_t)rgno * mp->m_sb.sb_rgextents); - - ASSERT(xfs_has_rtgroups(mp)); - return mp->m_sb.sb_rgextents; -} - -xfs_rtxnum_t -xfs_rtgroup_extents( - struct xfs_mount *mp, - xfs_rgnumber_t rgno) -{ - return __xfs_rtgroup_extents(mp, rgno, mp->m_sb.sb_rgcount, - mp->m_sb.sb_rextents); -} - /* * Update the rt extent count of the previous tail rtgroup if it changed during * recovery (i.e. recovery of a growfs). diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index 03f1e2493334..73cace4d25c7 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -285,8 +285,6 @@ void xfs_free_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno, int xfs_initialize_rtgroups(struct xfs_mount *mp, xfs_rgnumber_t first_rgno, xfs_rgnumber_t end_rgno, xfs_rtbxlen_t rextents); -xfs_rtxnum_t __xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno, - xfs_rgnumber_t rgcount, xfs_rtbxlen_t rextents); xfs_rtxnum_t xfs_rtgroup_extents(struct xfs_mount *mp, xfs_rgnumber_t rgno); void xfs_rtgroup_calc_geometry(struct xfs_mount *mp, struct xfs_rtgroup *rtg, xfs_rgnumber_t rgno, xfs_rgnumber_t rgcount, diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 04f39ea15898..37a1b33e9045 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -1831,7 +1831,6 @@ xfs_buffered_write_iomap_begin( */ if (flags & IOMAP_ZERO) { xfs_fileoff_t eof_fsb = XFS_B_TO_FSB(mp, XFS_ISIZE(ip)); - u64 end; if (isnullstartblock(imap.br_startblock) && offset_fsb >= eof_fsb) @@ -1851,12 +1850,14 @@ xfs_buffered_write_iomap_begin( */ if (imap.br_state == XFS_EXT_UNWRITTEN && offset_fsb < eof_fsb) { - loff_t len = min(count, - XFS_FSB_TO_B(mp, imap.br_blockcount)); + loff_t foffset = offset, fend; - end = iomap_fill_dirty_folios(iter, offset, len); + fend = offset + + min(count, XFS_FSB_TO_B(mp, imap.br_blockcount)); + iomap_fill_dirty_folios(iter, &foffset, fend, + &iomap_flags); end_fsb = min_t(xfs_fileoff_t, end_fsb, - XFS_B_TO_FSB(mp, end)); + XFS_B_TO_FSB(mp, foffset)); } xfs_trim_extent(&imap, offset_fsb, end_fsb - offset_fsb); diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index a311385b23d8..d4544ccafea5 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -1180,9 +1180,11 @@ xfs_log_cover( int error = 0; bool need_covered; - ASSERT((xlog_cil_empty(mp->m_log) && xlog_iclogs_empty(mp->m_log) && - !xfs_ail_min_lsn(mp->m_log->l_ailp)) || - xlog_is_shutdown(mp->m_log)); + if (!xlog_is_shutdown(mp->m_log)) { + ASSERT(xlog_cil_empty(mp->m_log)); + ASSERT(xlog_iclogs_empty(mp->m_log)); + ASSERT(!xfs_ail_min_lsn(mp->m_log->l_ailp)); + } if (!xfs_log_writable(mp)) return 0; diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c index e063f4f2f2e6..a12ffed12391 100644 --- a/fs/xfs/xfs_rtalloc.c +++ b/fs/xfs/xfs_rtalloc.c @@ -126,7 +126,7 @@ xfs_rtcopy_summary( error = 0; out: xfs_rtbuf_cache_relse(oargs); - return 0; + return error; } /* * Mark an extent specified by start and len allocated. @@ -1265,7 +1265,7 @@ xfs_growfs_check_rtgeom( uint32_t rem; if (rextsize != 1) - return -EINVAL; + goto out_inval; div_u64_rem(nmp->m_sb.sb_rblocks, gblocks, &rem); if (rem) { xfs_warn(mp, @@ -1326,7 +1326,7 @@ xfs_grow_last_rtg( return true; if (mp->m_sb.sb_rgcount == 0) return false; - return xfs_rtgroup_extents(mp, mp->m_sb.sb_rgcount - 1) <= + return xfs_rtgroup_extents(mp, mp->m_sb.sb_rgcount - 1) < mp->m_sb.sb_rgextents; } |