diff options
Diffstat (limited to 'fs')
65 files changed, 1111 insertions, 477 deletions
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 9bf282d2453c..499a9edf0ca3 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1795,7 +1795,14 @@ static int reclaim_bgs_cmp(void *unused, const struct list_head *a, bg1 = list_entry(a, struct btrfs_block_group, bg_list); bg2 = list_entry(b, struct btrfs_block_group, bg_list); - return bg1->used > bg2->used; + /* + * Some other task may be updating the ->used field concurrently, but it + * is not serious if we get a stale value or load/store tearing issues, + * as sorting the list of block groups to reclaim is not critical and an + * occasional imperfect order is ok. So silence KCSAN and avoid the + * overhead of locking or any other synchronization. + */ + return data_race(bg1->used > bg2->used); } static inline bool btrfs_should_reclaim(const struct btrfs_fs_info *fs_info) diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 0f8d8e275143..c0c1ddd46b67 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1843,7 +1843,6 @@ static void fill_stack_inode_item(struct btrfs_trans_handle *trans, int btrfs_fill_inode(struct btrfs_inode *inode, u32 *rdev) { - struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_delayed_node *delayed_node; struct btrfs_inode_item *inode_item; struct inode *vfs_inode = &inode->vfs_inode; @@ -1864,8 +1863,6 @@ int btrfs_fill_inode(struct btrfs_inode *inode, u32 *rdev) i_uid_write(vfs_inode, btrfs_stack_inode_uid(inode_item)); i_gid_write(vfs_inode, btrfs_stack_inode_gid(inode_item)); btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item)); - btrfs_inode_set_file_extent_range(inode, 0, - round_up(i_size_read(vfs_inode), fs_info->sectorsize)); vfs_inode->i_mode = btrfs_stack_inode_mode(inode_item); set_nlink(vfs_inode, btrfs_stack_inode_nlink(inode_item)); inode_set_bytes(vfs_inode, btrfs_stack_inode_nbytes(inode_item)); diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index c953297aa89a..b21cb72835cc 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -111,6 +111,24 @@ struct btrfs_bio_ctrl { */ unsigned long submit_bitmap; struct readahead_control *ractl; + + /* + * The start offset of the last used extent map by a read operation. + * + * This is for proper compressed read merge. + * U64_MAX means we are starting the read and have made no progress yet. + * + * The current btrfs_bio_is_contig() only uses disk_bytenr as + * the condition to check if the read can be merged with previous + * bio, which is not correct. E.g. two file extents pointing to the + * same extent but with different offset. + * + * So here we need to do extra checks to only merge reads that are + * covered by the same extent map. + * Just extent_map::start will be enough, as they are unique + * inside the same inode. + */ + u64 last_em_start; }; static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl) @@ -909,7 +927,7 @@ static void btrfs_readahead_expand(struct readahead_control *ractl, * return 0 on success, otherwise return error */ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached, - struct btrfs_bio_ctrl *bio_ctrl, u64 *prev_em_start) + struct btrfs_bio_ctrl *bio_ctrl) { struct inode *inode = folio->mapping->host; struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); @@ -1019,12 +1037,11 @@ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached, * non-optimal behavior (submitting 2 bios for the same extent). */ if (compress_type != BTRFS_COMPRESS_NONE && - prev_em_start && *prev_em_start != (u64)-1 && - *prev_em_start != em->start) + bio_ctrl->last_em_start != U64_MAX && + bio_ctrl->last_em_start != em->start) force_bio_submit = true; - if (prev_em_start) - *prev_em_start = em->start; + bio_ctrl->last_em_start = em->start; btrfs_free_extent_map(em); em = NULL; @@ -1238,12 +1255,15 @@ int btrfs_read_folio(struct file *file, struct folio *folio) const u64 start = folio_pos(folio); const u64 end = start + folio_size(folio) - 1; struct extent_state *cached_state = NULL; - struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ }; + struct btrfs_bio_ctrl bio_ctrl = { + .opf = REQ_OP_READ, + .last_em_start = U64_MAX, + }; struct extent_map *em_cached = NULL; int ret; lock_extents_for_read(inode, start, end, &cached_state); - ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl, NULL); + ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl); btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state); btrfs_free_extent_map(em_cached); @@ -2583,7 +2603,8 @@ void btrfs_readahead(struct readahead_control *rac) { struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ | REQ_RAHEAD, - .ractl = rac + .ractl = rac, + .last_em_start = U64_MAX, }; struct folio *folio; struct btrfs_inode *inode = BTRFS_I(rac->mapping->host); @@ -2591,12 +2612,11 @@ void btrfs_readahead(struct readahead_control *rac) const u64 end = start + readahead_length(rac) - 1; struct extent_state *cached_state = NULL; struct extent_map *em_cached = NULL; - u64 prev_em_start = (u64)-1; lock_extents_for_read(inode, start, end, &cached_state); while ((folio = readahead_folio(rac)) != NULL) - btrfs_do_readpage(folio, &em_cached, &bio_ctrl, &prev_em_start); + btrfs_do_readpage(folio, &em_cached, &bio_ctrl); btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index dd82dcc7b2b7..18db1053cdf0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3885,10 +3885,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path bool filled = false; int first_xattr_slot; - ret = btrfs_init_file_extent_tree(inode); - if (ret) - goto out; - ret = btrfs_fill_inode(inode, &rdev); if (!ret) filled = true; @@ -3920,8 +3916,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path i_uid_write(vfs_inode, btrfs_inode_uid(leaf, inode_item)); i_gid_write(vfs_inode, btrfs_inode_gid(leaf, inode_item)); btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item)); - btrfs_inode_set_file_extent_range(inode, 0, - round_up(i_size_read(vfs_inode), fs_info->sectorsize)); inode_set_atime(vfs_inode, btrfs_timespec_sec(leaf, &inode_item->atime), btrfs_timespec_nsec(leaf, &inode_item->atime)); @@ -3953,6 +3947,11 @@ 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 @@ -5696,7 +5695,17 @@ static void btrfs_del_inode_from_root(struct btrfs_inode *inode) bool empty = false; xa_lock(&root->inodes); - entry = __xa_erase(&root->inodes, btrfs_ino(inode)); + /* + * This btrfs_inode is being freed and has already been unhashed at this + * point. It's possible that another btrfs_inode has already been + * allocated for the same inode and inserted itself into the root, so + * don't delete it in that case. + * + * Note that this shouldn't need to allocate memory, so the gfp flags + * don't really matter. + */ + entry = __xa_cmpxchg(&root->inodes, btrfs_ino(inode), inode, NULL, + GFP_ATOMIC); if (entry == inode) empty = xa_empty(&root->inodes); xa_unlock(&root->inodes); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index ccaa9a3cf1ce..da102da169fd 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1455,6 +1455,7 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root, struct btrfs_qgroup *qgroup; LIST_HEAD(qgroup_list); u64 num_bytes = src->excl; + u64 num_bytes_cmpr = src->excl_cmpr; int ret = 0; qgroup = find_qgroup_rb(fs_info, ref_root); @@ -1466,11 +1467,12 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info, u64 ref_root, struct btrfs_qgroup_list *glist; qgroup->rfer += sign * num_bytes; - qgroup->rfer_cmpr += sign * num_bytes; + qgroup->rfer_cmpr += sign * num_bytes_cmpr; WARN_ON(sign < 0 && qgroup->excl < num_bytes); + WARN_ON(sign < 0 && qgroup->excl_cmpr < num_bytes_cmpr); qgroup->excl += sign * num_bytes; - qgroup->excl_cmpr += sign * num_bytes; + qgroup->excl_cmpr += sign * num_bytes_cmpr; if (sign > 0) qgroup_rsv_add_by_qgroup(fs_info, qgroup, src); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index a262b494a89f..df1f6cc3fe21 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -299,9 +299,12 @@ static int btrfs_parse_compress(struct btrfs_fs_context *ctx, btrfs_set_opt(ctx->mount_opt, COMPRESS); btrfs_clear_opt(ctx->mount_opt, NODATACOW); btrfs_clear_opt(ctx->mount_opt, NODATASUM); - } else if (btrfs_match_compress_type(string, "lzo", false)) { + } else if (btrfs_match_compress_type(string, "lzo", true)) { ctx->compress_type = BTRFS_COMPRESS_LZO; - ctx->compress_level = 0; + ctx->compress_level = btrfs_compress_str2level(BTRFS_COMPRESS_LZO, + string + 3); + if (string[3] == ':' && string[4]) + btrfs_warn(NULL, "Compression level ignored for LZO"); btrfs_set_opt(ctx->mount_opt, COMPRESS); btrfs_clear_opt(ctx->mount_opt, NODATACOW); btrfs_clear_opt(ctx->mount_opt, NODATASUM); @@ -1079,7 +1082,7 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry) seq_printf(seq, ",compress-force=%s", compress_type); else seq_printf(seq, ",compress=%s", compress_type); - if (info->compress_level) + if (info->compress_level && info->compress_type != BTRFS_COMPRESS_LZO) seq_printf(seq, ":%d", info->compress_level); } if (btrfs_test_opt(info, NOSSD)) diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 7d5d90845ca9..7a63afedd01e 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1964,7 +1964,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, search_key.objectid = log_key.objectid; search_key.type = BTRFS_INODE_EXTREF_KEY; - search_key.offset = key->objectid; + search_key.offset = btrfs_extref_hash(key->objectid, name.name, name.len); ret = backref_in_log(root->log_root, &search_key, key->objectid, &name); if (ret < 0) { goto out; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index fa7a929a0461..c6e3efd6f602 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2722,6 +2722,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path goto error; } + if (bdev_nr_bytes(file_bdev(bdev_file)) <= BTRFS_DEVICE_RANGE_RESERVED) { + ret = -EINVAL; + goto error; + } + if (fs_devices->seeding) { seeding_dev = true; down_write(&sb->s_umount); diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index ea662036f441..efc2a81f50e5 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -2582,9 +2582,9 @@ again: spin_lock(&space_info->lock); space_info->total_bytes -= bg->length; space_info->disk_total -= bg->length * factor; + space_info->disk_total -= bg->zone_unusable; /* There is no allocation ever happened. */ ASSERT(bg->used == 0); - ASSERT(bg->zone_unusable == 0); /* No super block in a block group on the zoned setup. */ ASSERT(bg->bytes_super == 0); spin_unlock(&space_info->lock); diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c index 8b202d789e93..322ed268f14a 100644 --- a/fs/ceph/addr.c +++ b/fs/ceph/addr.c @@ -1264,7 +1264,9 @@ static inline int move_dirty_folio_in_page_array(struct address_space *mapping, 0, gfp_flags); if (IS_ERR(pages[index])) { - if (PTR_ERR(pages[index]) == -EINVAL) { + int err = PTR_ERR(pages[index]); + + if (err == -EINVAL) { pr_err_client(cl, "inode->i_blkbits=%hhu\n", inode->i_blkbits); } @@ -1273,7 +1275,7 @@ static inline int move_dirty_folio_in_page_array(struct address_space *mapping, BUG_ON(ceph_wbc->locked_pages == 0); pages[index] = NULL; - return PTR_ERR(pages[index]); + return err; } } else { pages[index] = &folio->page; @@ -1687,6 +1689,7 @@ get_more_pages: process_folio_batch: rc = ceph_process_folio_batch(mapping, wbc, &ceph_wbc); + ceph_shift_unused_folios_left(&ceph_wbc.fbatch); if (rc) goto release_folios; @@ -1695,8 +1698,6 @@ process_folio_batch: goto release_folios; if (ceph_wbc.processed_in_fbatch) { - ceph_shift_unused_folios_left(&ceph_wbc.fbatch); - if (folio_batch_count(&ceph_wbc.fbatch) == 0 && ceph_wbc.locked_pages < ceph_wbc.max_pages) { doutc(cl, "reached end fbatch, trying for more\n"); diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c index fdd404fc8112..f3fe786b4143 100644 --- a/fs/ceph/debugfs.c +++ b/fs/ceph/debugfs.c @@ -55,8 +55,6 @@ static int mdsc_show(struct seq_file *s, void *p) struct ceph_mds_client *mdsc = fsc->mdsc; struct ceph_mds_request *req; struct rb_node *rp; - int pathlen = 0; - u64 pathbase; char *path; mutex_lock(&mdsc->mutex); @@ -81,8 +79,8 @@ static int mdsc_show(struct seq_file *s, void *p) if (req->r_inode) { seq_printf(s, " #%llx", ceph_ino(req->r_inode)); } else if (req->r_dentry) { - path = ceph_mdsc_build_path(mdsc, req->r_dentry, &pathlen, - &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0); if (IS_ERR(path)) path = NULL; spin_lock(&req->r_dentry->d_lock); @@ -91,7 +89,7 @@ static int mdsc_show(struct seq_file *s, void *p) req->r_dentry, path ? path : ""); spin_unlock(&req->r_dentry->d_lock); - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); } else if (req->r_path1) { seq_printf(s, " #%llx/%s", req->r_ino1.ino, req->r_path1); @@ -100,8 +98,8 @@ static int mdsc_show(struct seq_file *s, void *p) } if (req->r_old_dentry) { - path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &pathlen, - &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, req->r_old_dentry, &path_info, 0); if (IS_ERR(path)) path = NULL; spin_lock(&req->r_old_dentry->d_lock); @@ -111,7 +109,7 @@ static int mdsc_show(struct seq_file *s, void *p) req->r_old_dentry, path ? path : ""); spin_unlock(&req->r_old_dentry->d_lock); - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); } else if (req->r_path2 && req->r_op != CEPH_MDS_OP_SYMLINK) { if (req->r_ino2.ino) seq_printf(s, " #%llx/%s", req->r_ino2.ino, diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 8478e7e75df6..32973c62c1a2 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1271,10 +1271,8 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc, /* If op failed, mark everyone involved for errors */ if (result) { - int pathlen = 0; - u64 base = 0; - char *path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, - &base, 0); + struct ceph_path_info path_info = {0}; + char *path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0); /* mark error on parent + clear complete */ mapping_set_error(req->r_parent->i_mapping, result); @@ -1288,8 +1286,8 @@ static void ceph_async_unlink_cb(struct ceph_mds_client *mdsc, mapping_set_error(req->r_old_inode->i_mapping, result); pr_warn_client(cl, "failure path=(%llx)%s result=%d!\n", - base, IS_ERR(path) ? "<<bad>>" : path, result); - ceph_mdsc_free_path(path, pathlen); + path_info.vino.ino, IS_ERR(path) ? "<<bad>>" : path, result); + ceph_mdsc_free_path_info(&path_info); } out: iput(req->r_old_inode); @@ -1347,8 +1345,6 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) int err = -EROFS; int op; char *path; - int pathlen; - u64 pathbase; if (ceph_snap(dir) == CEPH_SNAPDIR) { /* rmdir .snap/foo is RMSNAP */ @@ -1367,14 +1363,15 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry) if (!dn) { try_async = false; } else { - path = ceph_mdsc_build_path(mdsc, dn, &pathlen, &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0); if (IS_ERR(path)) { try_async = false; err = 0; } else { err = ceph_mds_check_access(mdsc, path, MAY_WRITE); } - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); dput(dn); /* For none EACCES cases will let the MDS do the mds auth check */ diff --git a/fs/ceph/file.c b/fs/ceph/file.c index c02f100f8552..978acd3d4b32 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -368,8 +368,6 @@ int ceph_open(struct inode *inode, struct file *file) int flags, fmode, wanted; struct dentry *dentry; char *path; - int pathlen; - u64 pathbase; bool do_sync = false; int mask = MAY_READ; @@ -399,14 +397,15 @@ int ceph_open(struct inode *inode, struct file *file) if (!dentry) { do_sync = true; } else { - path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0); if (IS_ERR(path)) { do_sync = true; err = 0; } else { err = ceph_mds_check_access(mdsc, path, mask); } - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); dput(dentry); /* For none EACCES cases will let the MDS do the mds auth check */ @@ -614,15 +613,13 @@ static void ceph_async_create_cb(struct ceph_mds_client *mdsc, mapping_set_error(req->r_parent->i_mapping, result); if (result) { - int pathlen = 0; - u64 base = 0; - char *path = ceph_mdsc_build_path(mdsc, req->r_dentry, &pathlen, - &base, 0); + struct ceph_path_info path_info = {0}; + char *path = ceph_mdsc_build_path(mdsc, req->r_dentry, &path_info, 0); pr_warn_client(cl, "async create failure path=(%llx)%s result=%d!\n", - base, IS_ERR(path) ? "<<bad>>" : path, result); - ceph_mdsc_free_path(path, pathlen); + path_info.vino.ino, IS_ERR(path) ? "<<bad>>" : path, result); + ceph_mdsc_free_path_info(&path_info); ceph_dir_clear_complete(req->r_parent); if (!d_unhashed(dentry)) @@ -791,8 +788,6 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, int mask; int err; char *path; - int pathlen; - u64 pathbase; doutc(cl, "%p %llx.%llx dentry %p '%pd' %s flags %d mode 0%o\n", dir, ceph_vinop(dir), dentry, dentry, @@ -814,7 +809,8 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, if (!dn) { try_async = false; } else { - path = ceph_mdsc_build_path(mdsc, dn, &pathlen, &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, dn, &path_info, 0); if (IS_ERR(path)) { try_async = false; err = 0; @@ -826,7 +822,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry, mask |= MAY_WRITE; err = ceph_mds_check_access(mdsc, path, mask); } - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); dput(dn); /* For none EACCES cases will let the MDS do the mds auth check */ diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index fc543075b827..f67025465de0 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -55,6 +55,52 @@ static int ceph_set_ino_cb(struct inode *inode, void *data) return 0; } +/* + * Check if the parent inode matches the vino from directory reply info + */ +static inline bool ceph_vino_matches_parent(struct inode *parent, + struct ceph_vino vino) +{ + return ceph_ino(parent) == vino.ino && ceph_snap(parent) == vino.snap; +} + +/* + * Validate that the directory inode referenced by @req->r_parent matches the + * inode number and snapshot id contained in the reply's directory record. If + * they do not match – which can theoretically happen if the parent dentry was + * moved between the time the request was issued and the reply arrived – fall + * back to looking up the correct inode in the inode cache. + * + * A reference is *always* returned. Callers that receive a different inode + * than the original @parent are responsible for dropping the extra reference + * once the reply has been processed. + */ +static struct inode *ceph_get_reply_dir(struct super_block *sb, + struct inode *parent, + struct ceph_mds_reply_info_parsed *rinfo) +{ + struct ceph_vino vino; + + if (unlikely(!rinfo->diri.in)) + return parent; /* nothing to compare against */ + + /* If we didn't have a cached parent inode to begin with, just bail out. */ + if (!parent) + return NULL; + + vino.ino = le64_to_cpu(rinfo->diri.in->ino); + vino.snap = le64_to_cpu(rinfo->diri.in->snapid); + + if (likely(ceph_vino_matches_parent(parent, vino))) + return parent; /* matches – use the original reference */ + + /* Mismatch – this should be rare. Emit a WARN and obtain the correct inode. */ + WARN_ONCE(1, "ceph: reply dir mismatch (parent valid %llx.%llx reply %llx.%llx)\n", + ceph_ino(parent), ceph_snap(parent), vino.ino, vino.snap); + + return ceph_get_inode(sb, vino, NULL); +} + /** * ceph_new_inode - allocate a new inode in advance of an expected create * @dir: parent directory for new inode @@ -1523,6 +1569,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) struct ceph_vino tvino, dvino; struct ceph_fs_client *fsc = ceph_sb_to_fs_client(sb); struct ceph_client *cl = fsc->client; + struct inode *parent_dir = NULL; int err = 0; doutc(cl, "%p is_dentry %d is_target %d\n", req, @@ -1536,10 +1583,17 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) } if (rinfo->head->is_dentry) { - struct inode *dir = req->r_parent; - - if (dir) { - err = ceph_fill_inode(dir, NULL, &rinfo->diri, + /* + * r_parent may be stale, in cases when R_PARENT_LOCKED is not set, + * so we need to get the correct inode + */ + parent_dir = ceph_get_reply_dir(sb, req->r_parent, rinfo); + if (unlikely(IS_ERR(parent_dir))) { + err = PTR_ERR(parent_dir); + goto done; + } + if (parent_dir) { + err = ceph_fill_inode(parent_dir, NULL, &rinfo->diri, rinfo->dirfrag, session, -1, &req->r_caps_reservation); if (err < 0) @@ -1548,14 +1602,14 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) WARN_ON_ONCE(1); } - if (dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME && + if (parent_dir && req->r_op == CEPH_MDS_OP_LOOKUPNAME && test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) && !test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) { bool is_nokey = false; struct qstr dname; struct dentry *dn, *parent; struct fscrypt_str oname = FSTR_INIT(NULL, 0); - struct ceph_fname fname = { .dir = dir, + struct ceph_fname fname = { .dir = parent_dir, .name = rinfo->dname, .ctext = rinfo->altname, .name_len = rinfo->dname_len, @@ -1564,10 +1618,10 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) BUG_ON(!rinfo->head->is_target); BUG_ON(req->r_dentry); - parent = d_find_any_alias(dir); + parent = d_find_any_alias(parent_dir); BUG_ON(!parent); - err = ceph_fname_alloc_buffer(dir, &oname); + err = ceph_fname_alloc_buffer(parent_dir, &oname); if (err < 0) { dput(parent); goto done; @@ -1576,7 +1630,7 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req) err = ceph_fname_to_usr(&fname, NULL, &oname, &is_nokey); if (err < 0) { dput(parent); - ceph_fname_free_buffer(dir, &oname); + ceph_fname_free_buffer(parent_dir, &oname); goto done; } dname.name = oname.name; @@ -1595,7 +1649,7 @@ retry_lookup: dname.len, dname.name, dn); if (!dn) { dput(parent); - ceph_fname_free_buffer(dir, &oname); + ceph_fname_free_buffer(parent_dir, &oname); err = -ENOMEM; goto done; } @@ -1610,12 +1664,12 @@ retry_lookup: ceph_snap(d_inode(dn)) != tvino.snap)) { doutc(cl, " dn %p points to wrong inode %p\n", dn, d_inode(dn)); - ceph_dir_clear_ordered(dir); + ceph_dir_clear_ordered(parent_dir); d_delete(dn); dput(dn); goto retry_lookup; } - ceph_fname_free_buffer(dir, &oname); + ceph_fname_free_buffer(parent_dir, &oname); req->r_dentry = dn; dput(parent); @@ -1794,6 +1848,9 @@ retry_lookup: &dvino, ptvino); } done: + /* Drop extra ref from ceph_get_reply_dir() if it returned a new inode */ + if (unlikely(!IS_ERR_OR_NULL(parent_dir) && parent_dir != req->r_parent)) + iput(parent_dir); doutc(cl, "done err=%d\n", err); return err; } @@ -2487,22 +2544,21 @@ int __ceph_setattr(struct mnt_idmap *idmap, struct inode *inode, int truncate_retry = 20; /* The RMW will take around 50ms */ struct dentry *dentry; char *path; - int pathlen; - u64 pathbase; bool do_sync = false; dentry = d_find_alias(inode); if (!dentry) { do_sync = true; } else { - path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, 0); + struct ceph_path_info path_info; + path = ceph_mdsc_build_path(mdsc, dentry, &path_info, 0); if (IS_ERR(path)) { do_sync = true; err = 0; } else { err = ceph_mds_check_access(mdsc, path, MAY_WRITE); } - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); dput(dentry); /* For none EACCES cases will let the MDS do the mds auth check */ diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c index 0f497c39ff82..3bc72b47fe4d 100644 --- a/fs/ceph/mds_client.c +++ b/fs/ceph/mds_client.c @@ -2681,8 +2681,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen) * ceph_mdsc_build_path - build a path string to a given dentry * @mdsc: mds client * @dentry: dentry to which path should be built - * @plen: returned length of string - * @pbase: returned base inode number + * @path_info: output path, length, base ino+snap, and freepath ownership flag * @for_wire: is this path going to be sent to the MDS? * * Build a string that represents the path to the dentry. This is mostly called @@ -2700,7 +2699,7 @@ static u8 *get_fscrypt_altname(const struct ceph_mds_request *req, u32 *plen) * foo/.snap/bar -> foo//bar */ char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, struct dentry *dentry, - int *plen, u64 *pbase, int for_wire) + struct ceph_path_info *path_info, int for_wire) { struct ceph_client *cl = mdsc->fsc->client; struct dentry *cur; @@ -2810,16 +2809,28 @@ retry: return ERR_PTR(-ENAMETOOLONG); } - *pbase = base; - *plen = PATH_MAX - 1 - pos; + /* Initialize the output structure */ + memset(path_info, 0, sizeof(*path_info)); + + path_info->vino.ino = base; + path_info->pathlen = PATH_MAX - 1 - pos; + path_info->path = path + pos; + path_info->freepath = true; + + /* Set snap from dentry if available */ + if (d_inode(dentry)) + path_info->vino.snap = ceph_snap(d_inode(dentry)); + else + path_info->vino.snap = CEPH_NOSNAP; + doutc(cl, "on %p %d built %llx '%.*s'\n", dentry, d_count(dentry), - base, *plen, path + pos); + base, PATH_MAX - 1 - pos, path + pos); return path + pos; } static int build_dentry_path(struct ceph_mds_client *mdsc, struct dentry *dentry, - struct inode *dir, const char **ppath, int *ppathlen, - u64 *pino, bool *pfreepath, bool parent_locked) + struct inode *dir, struct ceph_path_info *path_info, + bool parent_locked) { char *path; @@ -2828,41 +2839,47 @@ static int build_dentry_path(struct ceph_mds_client *mdsc, struct dentry *dentry dir = d_inode_rcu(dentry->d_parent); if (dir && parent_locked && ceph_snap(dir) == CEPH_NOSNAP && !IS_ENCRYPTED(dir)) { - *pino = ceph_ino(dir); + path_info->vino.ino = ceph_ino(dir); + path_info->vino.snap = ceph_snap(dir); rcu_read_unlock(); - *ppath = dentry->d_name.name; - *ppathlen = dentry->d_name.len; + path_info->path = dentry->d_name.name; + path_info->pathlen = dentry->d_name.len; + path_info->freepath = false; return 0; } rcu_read_unlock(); - path = ceph_mdsc_build_path(mdsc, dentry, ppathlen, pino, 1); + path = ceph_mdsc_build_path(mdsc, dentry, path_info, 1); if (IS_ERR(path)) return PTR_ERR(path); - *ppath = path; - *pfreepath = true; + /* + * ceph_mdsc_build_path already fills path_info, including snap handling. + */ return 0; } -static int build_inode_path(struct inode *inode, - const char **ppath, int *ppathlen, u64 *pino, - bool *pfreepath) +static int build_inode_path(struct inode *inode, struct ceph_path_info *path_info) { struct ceph_mds_client *mdsc = ceph_sb_to_mdsc(inode->i_sb); struct dentry *dentry; char *path; if (ceph_snap(inode) == CEPH_NOSNAP) { - *pino = ceph_ino(inode); - *ppathlen = 0; + path_info->vino.ino = ceph_ino(inode); + path_info->vino.snap = ceph_snap(inode); + path_info->pathlen = 0; + path_info->freepath = false; return 0; } dentry = d_find_alias(inode); - path = ceph_mdsc_build_path(mdsc, dentry, ppathlen, pino, 1); + path = ceph_mdsc_build_path(mdsc, dentry, path_info, 1); dput(dentry); if (IS_ERR(path)) return PTR_ERR(path); - *ppath = path; - *pfreepath = true; + /* + * ceph_mdsc_build_path already fills path_info, including snap from dentry. + * Override with inode's snap since that's what this function is for. + */ + path_info->vino.snap = ceph_snap(inode); return 0; } @@ -2872,26 +2889,32 @@ static int build_inode_path(struct inode *inode, */ static int set_request_path_attr(struct ceph_mds_client *mdsc, struct inode *rinode, struct dentry *rdentry, struct inode *rdiri, - const char *rpath, u64 rino, const char **ppath, - int *pathlen, u64 *ino, bool *freepath, + const char *rpath, u64 rino, + struct ceph_path_info *path_info, bool parent_locked) { struct ceph_client *cl = mdsc->fsc->client; int r = 0; + /* Initialize the output structure */ + memset(path_info, 0, sizeof(*path_info)); + if (rinode) { - r = build_inode_path(rinode, ppath, pathlen, ino, freepath); + r = build_inode_path(rinode, path_info); doutc(cl, " inode %p %llx.%llx\n", rinode, ceph_ino(rinode), ceph_snap(rinode)); } else if (rdentry) { - r = build_dentry_path(mdsc, rdentry, rdiri, ppath, pathlen, ino, - freepath, parent_locked); - doutc(cl, " dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen, *ppath); + r = build_dentry_path(mdsc, rdentry, rdiri, path_info, parent_locked); + doutc(cl, " dentry %p %llx/%.*s\n", rdentry, path_info->vino.ino, + path_info->pathlen, path_info->path); } else if (rpath || rino) { - *ino = rino; - *ppath = rpath; - *pathlen = rpath ? strlen(rpath) : 0; - doutc(cl, " path %.*s\n", *pathlen, rpath); + path_info->vino.ino = rino; + path_info->vino.snap = CEPH_NOSNAP; + path_info->path = rpath; + path_info->pathlen = rpath ? strlen(rpath) : 0; + path_info->freepath = false; + + doutc(cl, " path %.*s\n", path_info->pathlen, rpath); } return r; @@ -2968,11 +2991,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, struct ceph_client *cl = mdsc->fsc->client; struct ceph_msg *msg; struct ceph_mds_request_head_legacy *lhead; - const char *path1 = NULL; - const char *path2 = NULL; - u64 ino1 = 0, ino2 = 0; - int pathlen1 = 0, pathlen2 = 0; - bool freepath1 = false, freepath2 = false; + struct ceph_path_info path_info1 = {0}; + struct ceph_path_info path_info2 = {0}; struct dentry *old_dentry = NULL; int len; u16 releases; @@ -2982,25 +3002,49 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, u16 request_head_version = mds_supported_head_version(session); kuid_t caller_fsuid = req->r_cred->fsuid; kgid_t caller_fsgid = req->r_cred->fsgid; + bool parent_locked = test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags); ret = set_request_path_attr(mdsc, req->r_inode, req->r_dentry, - req->r_parent, req->r_path1, req->r_ino1.ino, - &path1, &pathlen1, &ino1, &freepath1, - test_bit(CEPH_MDS_R_PARENT_LOCKED, - &req->r_req_flags)); + req->r_parent, req->r_path1, req->r_ino1.ino, + &path_info1, parent_locked); if (ret < 0) { msg = ERR_PTR(ret); goto out; } + /* + * When the parent directory's i_rwsem is *not* locked, req->r_parent may + * have become stale (e.g. after a concurrent rename) between the time the + * dentry was looked up and now. If we detect that the stored r_parent + * does not match the inode number we just encoded for the request, switch + * to the correct inode so that the MDS receives a valid parent reference. + */ + if (!parent_locked && req->r_parent && path_info1.vino.ino && + ceph_ino(req->r_parent) != path_info1.vino.ino) { + struct inode *old_parent = req->r_parent; + struct inode *correct_dir = ceph_get_inode(mdsc->fsc->sb, path_info1.vino, NULL); + if (!IS_ERR(correct_dir)) { + WARN_ONCE(1, "ceph: r_parent mismatch (had %llx wanted %llx) - updating\n", + ceph_ino(old_parent), path_info1.vino.ino); + /* + * Transfer CEPH_CAP_PIN from the old parent to the new one. + * The pin was taken earlier in ceph_mdsc_submit_request(). + */ + ceph_put_cap_refs(ceph_inode(old_parent), CEPH_CAP_PIN); + iput(old_parent); + req->r_parent = correct_dir; + ceph_get_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN); + } + } + /* If r_old_dentry is set, then assume that its parent is locked */ if (req->r_old_dentry && !(req->r_old_dentry->d_flags & DCACHE_DISCONNECTED)) old_dentry = req->r_old_dentry; ret = set_request_path_attr(mdsc, NULL, old_dentry, - req->r_old_dentry_dir, - req->r_path2, req->r_ino2.ino, - &path2, &pathlen2, &ino2, &freepath2, true); + req->r_old_dentry_dir, + req->r_path2, req->r_ino2.ino, + &path_info2, true); if (ret < 0) { msg = ERR_PTR(ret); goto out_free1; @@ -3031,7 +3075,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, /* filepaths */ len += 2 * (1 + sizeof(u32) + sizeof(u64)); - len += pathlen1 + pathlen2; + len += path_info1.pathlen + path_info2.pathlen; /* cap releases */ len += sizeof(struct ceph_mds_request_release) * @@ -3039,9 +3083,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, !!req->r_old_inode_drop + !!req->r_old_dentry_drop); if (req->r_dentry_drop) - len += pathlen1; + len += path_info1.pathlen; if (req->r_old_dentry_drop) - len += pathlen2; + len += path_info2.pathlen; /* MClientRequest tail */ @@ -3154,8 +3198,8 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, lhead->ino = cpu_to_le64(req->r_deleg_ino); lhead->args = req->r_args; - ceph_encode_filepath(&p, end, ino1, path1); - ceph_encode_filepath(&p, end, ino2, path2); + ceph_encode_filepath(&p, end, path_info1.vino.ino, path_info1.path); + ceph_encode_filepath(&p, end, path_info2.vino.ino, path_info2.path); /* make note of release offset, in case we need to replay */ req->r_request_release_offset = p - msg->front.iov_base; @@ -3218,11 +3262,9 @@ static struct ceph_msg *create_request_message(struct ceph_mds_session *session, msg->hdr.data_off = cpu_to_le16(0); out_free2: - if (freepath2) - ceph_mdsc_free_path((char *)path2, pathlen2); + ceph_mdsc_free_path_info(&path_info2); out_free1: - if (freepath1) - ceph_mdsc_free_path((char *)path1, pathlen1); + ceph_mdsc_free_path_info(&path_info1); out: return msg; out_err: @@ -4579,24 +4621,20 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) struct ceph_pagelist *pagelist = recon_state->pagelist; struct dentry *dentry; struct ceph_cap *cap; - char *path; - int pathlen = 0, err; - u64 pathbase; + struct ceph_path_info path_info = {0}; + int err; u64 snap_follows; dentry = d_find_primary(inode); if (dentry) { /* set pathbase to parent dir when msg_version >= 2 */ - path = ceph_mdsc_build_path(mdsc, dentry, &pathlen, &pathbase, + char *path = ceph_mdsc_build_path(mdsc, dentry, &path_info, recon_state->msg_version >= 2); dput(dentry); if (IS_ERR(path)) { err = PTR_ERR(path); goto out_err; } - } else { - path = NULL; - pathbase = 0; } spin_lock(&ci->i_ceph_lock); @@ -4629,7 +4667,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) rec.v2.wanted = cpu_to_le32(__ceph_caps_wanted(ci)); rec.v2.issued = cpu_to_le32(cap->issued); rec.v2.snaprealm = cpu_to_le64(ci->i_snap_realm->ino); - rec.v2.pathbase = cpu_to_le64(pathbase); + rec.v2.pathbase = cpu_to_le64(path_info.vino.ino); rec.v2.flock_len = (__force __le32) ((ci->i_ceph_flags & CEPH_I_ERROR_FILELOCK) ? 0 : 1); } else { @@ -4644,7 +4682,7 @@ static int reconnect_caps_cb(struct inode *inode, int mds, void *arg) ts = inode_get_atime(inode); ceph_encode_timespec64(&rec.v1.atime, &ts); rec.v1.snaprealm = cpu_to_le64(ci->i_snap_realm->ino); - rec.v1.pathbase = cpu_to_le64(pathbase); + rec.v1.pathbase = cpu_to_le64(path_info.vino.ino); } if (list_empty(&ci->i_cap_snaps)) { @@ -4706,7 +4744,7 @@ encode_again: sizeof(struct ceph_filelock); rec.v2.flock_len = cpu_to_le32(struct_len); - struct_len += sizeof(u32) + pathlen + sizeof(rec.v2); + struct_len += sizeof(u32) + path_info.pathlen + sizeof(rec.v2); if (struct_v >= 2) struct_len += sizeof(u64); /* snap_follows */ @@ -4730,7 +4768,7 @@ encode_again: ceph_pagelist_encode_8(pagelist, 1); ceph_pagelist_encode_32(pagelist, struct_len); } - ceph_pagelist_encode_string(pagelist, path, pathlen); + ceph_pagelist_encode_string(pagelist, (char *)path_info.path, path_info.pathlen); ceph_pagelist_append(pagelist, &rec, sizeof(rec.v2)); ceph_locks_to_pagelist(flocks, pagelist, num_fcntl_locks, num_flock_locks); @@ -4741,17 +4779,17 @@ out_freeflocks: } else { err = ceph_pagelist_reserve(pagelist, sizeof(u64) + sizeof(u32) + - pathlen + sizeof(rec.v1)); + path_info.pathlen + sizeof(rec.v1)); if (err) goto out_err; ceph_pagelist_encode_64(pagelist, ceph_ino(inode)); - ceph_pagelist_encode_string(pagelist, path, pathlen); + ceph_pagelist_encode_string(pagelist, (char *)path_info.path, path_info.pathlen); ceph_pagelist_append(pagelist, &rec, sizeof(rec.v1)); } out_err: - ceph_mdsc_free_path(path, pathlen); + ceph_mdsc_free_path_info(&path_info); if (!err) recon_state->nr_caps++; return err; diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h index 3e2a6fa7c19a..0428a5eaf28c 100644 --- a/fs/ceph/mds_client.h +++ b/fs/ceph/mds_client.h @@ -617,14 +617,24 @@ extern int ceph_mds_check_access(struct ceph_mds_client *mdsc, char *tpath, extern void ceph_mdsc_pre_umount(struct ceph_mds_client *mdsc); -static inline void ceph_mdsc_free_path(char *path, int len) +/* + * Structure to group path-related output parameters for build_*_path functions + */ +struct ceph_path_info { + const char *path; + int pathlen; + struct ceph_vino vino; + bool freepath; +}; + +static inline void ceph_mdsc_free_path_info(const struct ceph_path_info *path_info) { - if (!IS_ERR_OR_NULL(path)) - __putname(path - (PATH_MAX - 1 - len)); + if (path_info && path_info->freepath && !IS_ERR_OR_NULL(path_info->path)) + __putname((char *)path_info->path - (PATH_MAX - 1 - path_info->pathlen)); } extern char *ceph_mdsc_build_path(struct ceph_mds_client *mdsc, - struct dentry *dentry, int *plen, u64 *base, + struct dentry *dentry, struct ceph_path_info *path_info, int for_wire); extern void __ceph_mdsc_drop_dentry_lease(struct dentry *dentry); diff --git a/fs/coredump.c b/fs/coredump.c index 5dce257c67fc..60bc9685e149 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -1466,11 +1466,15 @@ static int proc_dostring_coredump(const struct ctl_table *table, int write, ssize_t retval; char old_core_pattern[CORENAME_MAX_SIZE]; + if (write) + return proc_dostring(table, write, buffer, lenp, ppos); + retval = strscpy(old_core_pattern, core_pattern, CORENAME_MAX_SIZE); error = proc_dostring(table, write, buffer, lenp, ppos); if (error) return error; + if (!check_coredump_socket()) { strscpy(core_pattern, old_core_pattern, retval + 1); return -EINVAL; diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h index 377ee12b8b96..3d5738f80072 100644 --- a/fs/erofs/erofs_fs.h +++ b/fs/erofs/erofs_fs.h @@ -12,10 +12,12 @@ /* to allow for x86 boot sectors and other oddities. */ #define EROFS_SUPER_OFFSET 1024 -#define EROFS_FEATURE_COMPAT_SB_CHKSUM 0x00000001 -#define EROFS_FEATURE_COMPAT_MTIME 0x00000002 -#define EROFS_FEATURE_COMPAT_XATTR_FILTER 0x00000004 +#define EROFS_FEATURE_COMPAT_SB_CHKSUM 0x00000001 +#define EROFS_FEATURE_COMPAT_MTIME 0x00000002 +#define EROFS_FEATURE_COMPAT_XATTR_FILTER 0x00000004 #define EROFS_FEATURE_COMPAT_SHARED_EA_IN_METABOX 0x00000008 +#define EROFS_FEATURE_COMPAT_PLAIN_XATTR_PFX 0x00000010 + /* * Any bits that aren't in EROFS_ALL_FEATURE_INCOMPAT should diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 4ccc5f0ee8df..9319c66e86c3 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -234,6 +234,7 @@ EROFS_FEATURE_FUNCS(metabox, incompat, INCOMPAT_METABOX) EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM) EROFS_FEATURE_FUNCS(xattr_filter, compat, COMPAT_XATTR_FILTER) EROFS_FEATURE_FUNCS(shared_ea_in_metabox, compat, COMPAT_SHARED_EA_IN_METABOX) +EROFS_FEATURE_FUNCS(plain_xattr_pfx, compat, COMPAT_PLAIN_XATTR_PFX) static inline u64 erofs_nid_to_ino64(struct erofs_sb_info *sbi, erofs_nid_t nid) { diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 1b529ace4db0..db13b40a78e0 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -1018,10 +1018,22 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) return 0; } +static void erofs_evict_inode(struct inode *inode) +{ +#ifdef CONFIG_FS_DAX + if (IS_DAX(inode)) + dax_break_layout_final(inode); +#endif + + truncate_inode_pages_final(&inode->i_data); + clear_inode(inode); +} + const struct super_operations erofs_sops = { .put_super = erofs_put_super, .alloc_inode = erofs_alloc_inode, .free_inode = erofs_free_inode, + .evict_inode = erofs_evict_inode, .statfs = erofs_statfs, .show_options = erofs_show_options, }; diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index eaa9efd766ee..396536d9a862 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -482,6 +482,7 @@ int erofs_xattr_prefixes_init(struct super_block *sb) erofs_off_t pos = (erofs_off_t)sbi->xattr_prefix_start << 2; struct erofs_xattr_prefix_item *pfs; int ret = 0, i, len; + bool plain = erofs_sb_has_plain_xattr_pfx(sbi); if (!sbi->xattr_prefix_count) return 0; @@ -490,9 +491,15 @@ int erofs_xattr_prefixes_init(struct super_block *sb) if (!pfs) return -ENOMEM; - if (sbi->packed_inode) - buf.mapping = sbi->packed_inode->i_mapping; - else + if (!plain) { + if (erofs_sb_has_metabox(sbi)) + (void)erofs_init_metabuf(&buf, sb, true); + else if (sbi->packed_inode) + buf.mapping = sbi->packed_inode->i_mapping; + else + plain = true; + } + if (plain) (void)erofs_init_metabuf(&buf, sb, false); for (i = 0; i < sbi->xattr_prefix_count; i++) { diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index a93efd95c555..798223e6da9c 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -394,10 +394,10 @@ static int z_erofs_map_blocks_fo(struct inode *inode, .map = map, .in_mbox = erofs_inode_in_metabox(inode), }; - int err = 0; - unsigned int endoff, afmt; + unsigned int endoff; unsigned long initial_lcn; unsigned long long ofs, end; + int err; ofs = flags & EROFS_GET_BLOCKS_FINDTAIL ? inode->i_size - 1 : map->m_la; if (fragment && !(flags & EROFS_GET_BLOCKS_FINDTAIL) && @@ -482,20 +482,15 @@ static int z_erofs_map_blocks_fo(struct inode *inode, err = -EFSCORRUPTED; goto unmap_out; } - afmt = vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER ? - Z_EROFS_COMPRESSION_INTERLACED : - Z_EROFS_COMPRESSION_SHIFTED; + if (vi->z_advise & Z_EROFS_ADVISE_INTERLACED_PCLUSTER) + map->m_algorithmformat = Z_EROFS_COMPRESSION_INTERLACED; + else + map->m_algorithmformat = Z_EROFS_COMPRESSION_SHIFTED; + } else if (m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) { + map->m_algorithmformat = vi->z_algorithmtype[1]; } else { - afmt = m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2 ? - vi->z_algorithmtype[1] : vi->z_algorithmtype[0]; - if (!(EROFS_I_SB(inode)->available_compr_algs & (1 << afmt))) { - erofs_err(sb, "inconsistent algorithmtype %u for nid %llu", - afmt, vi->nid); - err = -EFSCORRUPTED; - goto unmap_out; - } + map->m_algorithmformat = vi->z_algorithmtype[0]; } - map->m_algorithmformat = afmt; if ((flags & EROFS_GET_BLOCKS_FIEMAP) || ((flags & EROFS_GET_BLOCKS_READMORE) && @@ -626,9 +621,9 @@ static int z_erofs_fill_inode(struct inode *inode, struct erofs_map_blocks *map) { struct erofs_inode *const vi = EROFS_I(inode); struct super_block *const sb = inode->i_sb; - int err, headnr; - erofs_off_t pos; struct z_erofs_map_header *h; + erofs_off_t pos; + int err = 0; if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) { /* @@ -642,7 +637,6 @@ static int z_erofs_fill_inode(struct inode *inode, struct erofs_map_blocks *map) if (wait_on_bit_lock(&vi->flags, EROFS_I_BL_Z_BIT, TASK_KILLABLE)) return -ERESTARTSYS; - err = 0; if (test_bit(EROFS_I_Z_INITED_BIT, &vi->flags)) goto out_unlock; @@ -679,15 +673,6 @@ static int z_erofs_fill_inode(struct inode *inode, struct erofs_map_blocks *map) else if (vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER) vi->z_idata_size = le16_to_cpu(h->h_idata_size); - headnr = 0; - if (vi->z_algorithmtype[0] >= Z_EROFS_COMPRESSION_MAX || - vi->z_algorithmtype[++headnr] >= Z_EROFS_COMPRESSION_MAX) { - erofs_err(sb, "unknown HEAD%u format %u for nid %llu, please upgrade kernel", - headnr + 1, vi->z_algorithmtype[headnr], vi->nid); - err = -EOPNOTSUPP; - goto out_unlock; - } - if (!erofs_sb_has_big_pcluster(EROFS_SB(sb)) && vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 | Z_EROFS_ADVISE_BIG_PCLUSTER_2)) { @@ -726,6 +711,30 @@ out_unlock: return err; } +static int z_erofs_map_sanity_check(struct inode *inode, + struct erofs_map_blocks *map) +{ + struct erofs_sb_info *sbi = EROFS_I_SB(inode); + + if (!(map->m_flags & EROFS_MAP_ENCODED)) + return 0; + if (unlikely(map->m_algorithmformat >= Z_EROFS_COMPRESSION_RUNTIME_MAX)) { + erofs_err(inode->i_sb, "unknown algorithm %d @ pos %llu for nid %llu, please upgrade kernel", + map->m_algorithmformat, map->m_la, EROFS_I(inode)->nid); + return -EOPNOTSUPP; + } + if (unlikely(map->m_algorithmformat < Z_EROFS_COMPRESSION_MAX && + !(sbi->available_compr_algs & (1 << map->m_algorithmformat)))) { + erofs_err(inode->i_sb, "inconsistent algorithmtype %u for nid %llu", + map->m_algorithmformat, EROFS_I(inode)->nid); + return -EFSCORRUPTED; + } + if (unlikely(map->m_plen > Z_EROFS_PCLUSTER_MAX_SIZE || + map->m_llen > Z_EROFS_PCLUSTER_MAX_DSIZE)) + return -EOPNOTSUPP; + return 0; +} + int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map, int flags) { @@ -746,10 +755,8 @@ int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map, else err = z_erofs_map_blocks_fo(inode, map, flags); } - if (!err && (map->m_flags & EROFS_MAP_ENCODED) && - unlikely(map->m_plen > Z_EROFS_PCLUSTER_MAX_SIZE || - map->m_llen > Z_EROFS_PCLUSTER_MAX_DSIZE)) - err = -EOPNOTSUPP; + if (!err) + err = z_erofs_map_sanity_check(inode, map); if (err) map->m_llen = 0; } diff --git a/fs/exec.c b/fs/exec.c index 2a1e5e4042a1..e861a4b7ffda 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -2048,7 +2048,7 @@ static int proc_dointvec_minmax_coredump(const struct ctl_table *table, int writ { int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos); - if (!error) + if (!error && !write) validate_coredump_safety(); return error; } diff --git a/fs/fhandle.c b/fs/fhandle.c index 68a7d2861c58..a907ddfac4d5 100644 --- a/fs/fhandle.c +++ b/fs/fhandle.c @@ -208,6 +208,14 @@ static int vfs_dentry_acceptable(void *context, struct dentry *dentry) return 1; /* + * Verify that the decoded dentry itself has a valid id mapping. + * In case the decoded dentry is the mountfd root itself, this + * verifies that the mountfd inode itself has a valid id mapping. + */ + if (!privileged_wrt_inode_uidgid(user_ns, idmap, d_inode(dentry))) + return 0; + + /* * It's racy as we're not taking rename_lock but we're able to ignore * permissions and we just need an approximation whether we were able * to follow a path to the file. diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index e80cd8f2c049..5150aa25e64b 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1893,7 +1893,7 @@ static int fuse_retrieve(struct fuse_mount *fm, struct inode *inode, index = outarg->offset >> PAGE_SHIFT; - while (num) { + while (num && ap->num_folios < num_pages) { struct folio *folio; unsigned int folio_offset; unsigned int nr_bytes; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 2d817d7cab26..5c569c3cb53f 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1199,7 +1199,7 @@ static void fuse_fillattr(struct mnt_idmap *idmap, struct inode *inode, if (attr->blksize != 0) blkbits = ilog2(attr->blksize); else - blkbits = inode->i_sb->s_blocksize_bits; + blkbits = fc->blkbits; stat->blksize = 1 << blkbits; } @@ -1377,6 +1377,7 @@ retry: generic_fillattr(idmap, request_mask, inode, stat); stat->mode = fi->orig_i_mode; stat->ino = fi->orig_ino; + stat->blksize = 1 << fi->cached_i_blkbits; if (test_bit(FUSE_I_BTIME, &fi->state)) { stat->btime = fi->i_btime; stat->result_mask |= STATX_BTIME; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 5525a4520b0f..4adcf09d4b01 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -2960,7 +2960,7 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in, .nodeid_out = ff_out->nodeid, .fh_out = ff_out->fh, .off_out = pos_out, - .len = len, + .len = min_t(size_t, len, UINT_MAX & PAGE_MASK), .flags = flags }; struct fuse_write_out outarg; @@ -3026,6 +3026,9 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in, fc->no_copy_file_range = 1; err = -EOPNOTSUPP; } + if (!err && outarg.size > len) + err = -EIO; + if (err) goto out; diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index ec248d13c8bf..cc428d04be3e 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -210,6 +210,12 @@ struct fuse_inode { /** Reference to backing file in passthrough mode */ struct fuse_backing *fb; #endif + + /* + * The underlying inode->i_blkbits value will not be modified, + * so preserve the blocksize specified by the server. + */ + u8 cached_i_blkbits; }; /** FUSE inode state bits */ @@ -969,6 +975,14 @@ struct fuse_conn { /* Request timeout (in jiffies). 0 = no timeout */ unsigned int req_timeout; } timeout; + + /* + * This is a workaround until fuse uses iomap for reads. + * For fuseblk servers, this represents the blocksize passed in at + * mount time and for regular fuse servers, this is equivalent to + * inode->i_blkbits. + */ + u8 blkbits; }; /* diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 67c2318bfc42..7ddfd2b3cc9c 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -289,6 +289,11 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr, } } + if (attr->blksize) + fi->cached_i_blkbits = ilog2(attr->blksize); + else + fi->cached_i_blkbits = fc->blkbits; + /* * Don't set the sticky bit in i_mode, unless we want the VFS * to check permissions. This prevents failures due to the @@ -1805,10 +1810,21 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx) err = -EINVAL; if (!sb_set_blocksize(sb, ctx->blksize)) goto err; + /* + * This is a workaround until fuse hooks into iomap for reads. + * Use PAGE_SIZE for the blocksize else if the writeback cache + * is enabled, buffered writes go through iomap and a read may + * overwrite partially written data if blocksize < PAGE_SIZE + */ + fc->blkbits = sb->s_blocksize_bits; + if (ctx->blksize != PAGE_SIZE && + !sb_set_blocksize(sb, PAGE_SIZE)) + goto err; #endif } else { sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; + fc->blkbits = sb->s_blocksize_bits; } sb->s_subtype = ctx->subtype; diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c index 607ef735ad4a..eb97ac009e75 100644 --- a/fs/fuse/passthrough.c +++ b/fs/fuse/passthrough.c @@ -237,6 +237,11 @@ int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map) if (!file) goto out; + /* read/write/splice/mmap passthrough only relevant for regular files */ + res = d_is_dir(file->f_path.dentry) ? -EISDIR : -EINVAL; + if (!d_is_reg(file->f_path.dentry)) + goto out_fput; + backing_sb = file_inode(file)->i_sb; res = -ELOOP; if (backing_sb->s_stack_depth >= fc->max_stack_depth) diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c index c826e7ca49f5..76c8fd0bfc75 100644 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@ -1016,7 +1016,7 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, if (kaddr) *kaddr = fs->window_kaddr + offset; if (pfn) - *pfn = fs->window_phys_addr + offset; + *pfn = PHYS_PFN(fs->window_phys_addr + offset); return nr_pages > max_nr_pages ? max_nr_pages : nr_pages; } diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index a6c692cac616..9adf36e6364b 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -70,6 +70,24 @@ static struct kernfs_open_node *of_on(struct kernfs_open_file *of) !list_empty(&of->list)); } +/* Get active reference to kernfs node for an open file */ +static struct kernfs_open_file *kernfs_get_active_of(struct kernfs_open_file *of) +{ + /* Skip if file was already released */ + if (unlikely(of->released)) + return NULL; + + if (!kernfs_get_active(of->kn)) + return NULL; + + return of; +} + +static void kernfs_put_active_of(struct kernfs_open_file *of) +{ + return kernfs_put_active(of->kn); +} + /** * kernfs_deref_open_node_locked - Get kernfs_open_node corresponding to @kn * @@ -139,7 +157,7 @@ static void kernfs_seq_stop_active(struct seq_file *sf, void *v) if (ops->seq_stop) ops->seq_stop(sf, v); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); } static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) @@ -152,7 +170,7 @@ static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return ERR_PTR(-ENODEV); ops = kernfs_ops(of->kn); @@ -238,7 +256,7 @@ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) { + if (!kernfs_get_active_of(of)) { len = -ENODEV; mutex_unlock(&of->mutex); goto out_free; @@ -252,7 +270,7 @@ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) else len = -EINVAL; - kernfs_put_active(of->kn); + kernfs_put_active_of(of); mutex_unlock(&of->mutex); if (len < 0) @@ -323,7 +341,7 @@ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) { + if (!kernfs_get_active_of(of)) { mutex_unlock(&of->mutex); len = -ENODEV; goto out_free; @@ -335,7 +353,7 @@ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) else len = -EINVAL; - kernfs_put_active(of->kn); + kernfs_put_active_of(of); mutex_unlock(&of->mutex); if (len > 0) @@ -357,13 +375,13 @@ static void kernfs_vma_open(struct vm_area_struct *vma) if (!of->vm_ops) return; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return; if (of->vm_ops->open) of->vm_ops->open(vma); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); } static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) @@ -375,14 +393,14 @@ static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) if (!of->vm_ops) return VM_FAULT_SIGBUS; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return VM_FAULT_SIGBUS; ret = VM_FAULT_SIGBUS; if (of->vm_ops->fault) ret = of->vm_ops->fault(vmf); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); return ret; } @@ -395,7 +413,7 @@ static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) if (!of->vm_ops) return VM_FAULT_SIGBUS; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return VM_FAULT_SIGBUS; ret = 0; @@ -404,7 +422,7 @@ static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) else file_update_time(file); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); return ret; } @@ -418,14 +436,14 @@ static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr, if (!of->vm_ops) return -EINVAL; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return -EINVAL; ret = -EINVAL; if (of->vm_ops->access) ret = of->vm_ops->access(vma, addr, buf, len, write); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); return ret; } @@ -455,7 +473,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) mutex_lock(&of->mutex); rc = -ENODEV; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) goto out_unlock; ops = kernfs_ops(of->kn); @@ -490,7 +508,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) } vma->vm_ops = &kernfs_vm_ops; out_put: - kernfs_put_active(of->kn); + kernfs_put_active_of(of); out_unlock: mutex_unlock(&of->mutex); @@ -852,7 +870,7 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); __poll_t ret; - if (!kernfs_get_active(kn)) + if (!kernfs_get_active_of(of)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; if (kn->attr.ops->poll) @@ -860,7 +878,7 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) else ret = kernfs_generic_poll(of, wait); - kernfs_put_active(kn); + kernfs_put_active_of(of); return ret; } @@ -875,7 +893,7 @@ static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) { + if (!kernfs_get_active_of(of)) { mutex_unlock(&of->mutex); return -ENODEV; } @@ -886,7 +904,7 @@ static loff_t kernfs_fop_llseek(struct file *file, loff_t offset, int whence) else ret = generic_file_llseek(file, offset, whence); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); mutex_unlock(&of->mutex); return ret; } diff --git a/fs/namespace.c b/fs/namespace.c index ae6d1312b184..51f77c65c0c6 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2455,7 +2455,7 @@ struct vfsmount *clone_private_mount(const struct path *path) return ERR_PTR(-EINVAL); } - if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN)) + if (!ns_capable(old_mnt->mnt_ns->user_ns, CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); if (__has_locked_children(old_mnt, path->dentry)) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 8fb4a950dd55..4e3dcc157a83 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -888,6 +888,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, if (fsinfo->xattr_support) server->caps |= NFS_CAP_XATTR; + else + server->caps &= ~NFS_CAP_XATTR; #endif } diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 86e36c630f09..8059ece82468 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -28,6 +28,7 @@ #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/gfp.h> +#include <linux/rmap.h> #include <linux/swap.h> #include <linux/compaction.h> @@ -280,6 +281,37 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) } EXPORT_SYMBOL_GPL(nfs_file_fsync); +void nfs_truncate_last_folio(struct address_space *mapping, loff_t from, + loff_t to) +{ + struct folio *folio; + + if (from >= to) + return; + + folio = filemap_lock_folio(mapping, from >> PAGE_SHIFT); + if (IS_ERR(folio)) + return; + + if (folio_mkclean(folio)) + folio_mark_dirty(folio); + + if (folio_test_uptodate(folio)) { + loff_t fpos = folio_pos(folio); + size_t offset = from - fpos; + size_t end = folio_size(folio); + + if (to - fpos < end) + end = to - fpos; + folio_zero_segment(folio, offset, end); + trace_nfs_size_truncate_folio(mapping->host, to); + } + + folio_unlock(folio); + folio_put(folio); +} +EXPORT_SYMBOL_GPL(nfs_truncate_last_folio); + /* * Decide whether a read/modify/write cycle may be more efficient * then a modify/write/read cycle when writing to a page in the @@ -356,6 +388,7 @@ static int nfs_write_begin(const struct kiocb *iocb, dfprintk(PAGECACHE, "NFS: write_begin(%pD2(%lu), %u@%lld)\n", file, mapping->host->i_ino, len, (long long) pos); + nfs_truncate_last_folio(mapping, i_size_read(mapping->host), pos); fgp |= fgf_set_order(len); start: @@ -442,10 +475,11 @@ static void nfs_invalidate_folio(struct folio *folio, size_t offset, dfprintk(PAGECACHE, "NFS: invalidate_folio(%lu, %zu, %zu)\n", folio->index, offset, length); - if (offset != 0 || length < folio_size(folio)) - return; /* Cancel any unstarted writes on this page */ - nfs_wb_folio_cancel(inode, folio); + if (offset != 0 || length < folio_size(folio)) + nfs_wb_folio(inode, folio); + else + nfs_wb_folio_cancel(inode, folio); folio_wait_private_2(folio); /* [DEPRECATED] */ trace_nfs_invalidate_folio(inode, folio_pos(folio) + offset, length); } diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 8dc921d83538..9edb5f9b0c4e 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -293,7 +293,7 @@ ff_lseg_match_mirrors(struct pnfs_layout_segment *l1, struct pnfs_layout_segment *l2) { const struct nfs4_ff_layout_segment *fl1 = FF_LAYOUT_LSEG(l1); - const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l1); + const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l2); u32 i; if (fl1->mirror_array_cnt != fl2->mirror_array_cnt) @@ -773,8 +773,11 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg, continue; if (check_device && - nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node)) + nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node)) { + // reinitialize the error state in case if this is the last iteration + ds = ERR_PTR(-EINVAL); continue; + } *best_idx = idx; break; @@ -804,7 +807,7 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg, struct nfs4_pnfs_ds *ds; ds = ff_layout_choose_valid_ds_for_read(lseg, start_idx, best_idx); - if (ds) + if (!IS_ERR(ds)) return ds; return ff_layout_choose_any_ds_for_read(lseg, start_idx, best_idx); } @@ -818,7 +821,7 @@ ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio, ds = ff_layout_choose_best_ds_for_read(lseg, pgio->pg_mirror_idx, best_idx); - if (ds || !pgio->pg_mirror_idx) + if (!IS_ERR(ds) || !pgio->pg_mirror_idx) return ds; return ff_layout_choose_best_ds_for_read(lseg, 0, best_idx); } @@ -868,7 +871,7 @@ retry: req->wb_nio = 0; ds = ff_layout_get_ds_for_read(pgio, &ds_idx); - if (!ds) { + if (IS_ERR(ds)) { if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg)) goto out_mds; pnfs_generic_pg_cleanup(pgio); @@ -1072,11 +1075,13 @@ static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr) { u32 idx = hdr->pgio_mirror_idx + 1; u32 new_idx = 0; + struct nfs4_pnfs_ds *ds; - if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx)) - ff_layout_send_layouterror(hdr->lseg); - else + ds = ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx); + if (IS_ERR(ds)) pnfs_error_mark_layout_for_return(hdr->inode, hdr->lseg); + else + ff_layout_send_layouterror(hdr->lseg); pnfs_read_resend_pnfs(hdr, new_idx); } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 338ef77ae423..49df9debb1a6 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -716,6 +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); int error = 0; nfs_inc_stats(inode, NFSIOS_VFSSETATTR); @@ -731,7 +732,7 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, if (error) return error; - if (attr->ia_size == i_size_read(inode)) + if (attr->ia_size == oldsize) attr->ia_valid &= ~ATTR_SIZE; } @@ -767,8 +768,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, trace_nfs_setattr_enter(inode); /* Write all dirty data */ - if (S_ISREG(inode->i_mode)) + if (S_ISREG(inode->i_mode)) { + nfs_file_block_o_direct(NFS_I(inode)); nfs_sync_inode(inode); + } fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) { @@ -777,8 +780,12 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, } error = NFS_PROTO(inode)->setattr(dentry, fattr, attr); - if (error == 0) + if (error == 0) { + if (attr->ia_valid & ATTR_SIZE) + nfs_truncate_last_folio(inode->i_mapping, oldsize, + attr->ia_size); error = nfs_refresh_inode(inode, fattr); + } nfs_free_fattr(fattr); out: trace_nfs_setattr_exit(inode, error); diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 74d712b58423..c0a44f389f8f 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -437,6 +437,8 @@ int nfs_file_release(struct inode *, struct file *); int nfs_lock(struct file *, int, struct file_lock *); int nfs_flock(struct file *, int, struct file_lock *); int nfs_check_flags(int); +void nfs_truncate_last_folio(struct address_space *mapping, loff_t from, + loff_t to); /* inode.c */ extern struct workqueue_struct *nfsiod_workqueue; @@ -530,6 +532,16 @@ static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi) return test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0; } +/* Must be called with exclusively locked inode->i_rwsem */ +static inline void nfs_file_block_o_direct(struct nfs_inode *nfsi) +{ + if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) { + clear_bit(NFS_INO_ODIRECT, &nfsi->flags); + inode_dio_wait(&nfsi->vfs_inode); + } +} + + /* namespace.c */ #define NFS_PATH_CANONICAL 1 extern char *nfs_path(char **p, struct dentry *dentry, diff --git a/fs/nfs/io.c b/fs/nfs/io.c index 3388faf2acb9..d275b0a250bf 100644 --- a/fs/nfs/io.c +++ b/fs/nfs/io.c @@ -14,15 +14,6 @@ #include "internal.h" -/* Call with exclusively locked inode->i_rwsem */ -static void nfs_block_o_direct(struct nfs_inode *nfsi, struct inode *inode) -{ - if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) { - clear_bit(NFS_INO_ODIRECT, &nfsi->flags); - inode_dio_wait(inode); - } -} - /** * nfs_start_io_read - declare the file is being used for buffered reads * @inode: file inode @@ -57,7 +48,7 @@ nfs_start_io_read(struct inode *inode) err = down_write_killable(&inode->i_rwsem); if (err) return err; - nfs_block_o_direct(nfsi, inode); + nfs_file_block_o_direct(nfsi); downgrade_write(&inode->i_rwsem); return 0; @@ -90,7 +81,7 @@ nfs_start_io_write(struct inode *inode) err = down_write_killable(&inode->i_rwsem); if (!err) - nfs_block_o_direct(NFS_I(inode), inode); + nfs_file_block_o_direct(NFS_I(inode)); return err; } diff --git a/fs/nfs/localio.c b/fs/nfs/localio.c index bd5fca285899..97abf62f109d 100644 --- a/fs/nfs/localio.c +++ b/fs/nfs/localio.c @@ -180,10 +180,8 @@ static void nfs_local_probe(struct nfs_client *clp) return; } - if (nfs_client_is_local(clp)) { - /* If already enabled, disable and re-enable */ - nfs_localio_disable_client(clp); - } + if (nfs_client_is_local(clp)) + return; if (!nfs_uuid_begin(&clp->cl_uuid)) return; @@ -244,7 +242,8 @@ __nfs_local_open_fh(struct nfs_client *clp, const struct cred *cred, case -ENOMEM: case -ENXIO: case -ENOENT: - /* Revalidate localio, will disable if unsupported */ + /* Revalidate localio */ + nfs_localio_disable_client(clp); nfs_local_probe(clp); } } @@ -453,12 +452,13 @@ static void nfs_local_call_read(struct work_struct *work) nfs_local_iter_init(&iter, iocb, READ); status = filp->f_op->read_iter(&iocb->kiocb, &iter); + + revert_creds(save_cred); + if (status != -EIOCBQUEUED) { nfs_local_read_done(iocb, status); nfs_local_pgio_release(iocb); } - - revert_creds(save_cred); } static int @@ -648,14 +648,15 @@ static void nfs_local_call_write(struct work_struct *work) file_start_write(filp); status = filp->f_op->write_iter(&iocb->kiocb, &iter); file_end_write(filp); + + revert_creds(save_cred); + current->flags = old_flags; + if (status != -EIOCBQUEUED) { nfs_local_write_done(iocb, status); nfs_local_vfs_getattr(iocb); nfs_local_pgio_release(iocb); } - - revert_creds(save_cred); - current->flags = old_flags; } static int diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 01c01f45358b..6a0b5871ba3b 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -114,6 +114,7 @@ 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; @@ -137,6 +138,7 @@ 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); int err; if (!nfs_server_capable(inode, NFS_CAP_ALLOCATE)) @@ -145,7 +147,11 @@ int nfs42_proc_allocate(struct file *filep, loff_t offset, loff_t len) inode_lock(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); - if (err == -EOPNOTSUPP) + + if (err == 0) + nfs_truncate_last_folio(inode->i_mapping, oldsize, + offset + len); + else if (err == -EOPNOTSUPP) NFS_SERVER(inode)->caps &= ~(NFS_CAP_ALLOCATE | NFS_CAP_ZERO_RANGE); @@ -183,6 +189,7 @@ 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); int err; if (!nfs_server_capable(inode, NFS_CAP_ZERO_RANGE)) @@ -191,9 +198,11 @@ int nfs42_proc_zero_range(struct file *filep, loff_t offset, loff_t len) inode_lock(inode); err = nfs42_proc_fallocate(&msg, filep, offset, len); - if (err == 0) + if (err == 0) { + nfs_truncate_last_folio(inode->i_mapping, oldsize, + offset + len); truncate_pagecache_range(inode, offset, (offset + len) -1); - if (err == -EOPNOTSUPP) + } else if (err == -EOPNOTSUPP) NFS_SERVER(inode)->caps &= ~NFS_CAP_ZERO_RANGE; inode_unlock(inode); @@ -354,22 +363,27 @@ out: /** * nfs42_copy_dest_done - perform inode cache updates after clone/copy offload - * @inode: pointer to destination inode + * @file: pointer to destination file * @pos: destination offset * @len: copy length + * @oldsize: length of the file prior to clone/copy * * Punch a hole in the inode page cache, so that the NFS client will * know to retrieve new data. * Update the file size if necessary, and then mark the inode as having * invalid cached values for change attribute, ctime, mtime and space used. */ -static void nfs42_copy_dest_done(struct inode *inode, loff_t pos, loff_t len) +static void nfs42_copy_dest_done(struct file *file, loff_t pos, loff_t len, + loff_t oldsize) { + struct inode *inode = file_inode(file); + struct address_space *mapping = file->f_mapping; loff_t newsize = pos + len; loff_t end = newsize - 1; - WARN_ON_ONCE(invalidate_inode_pages2_range(inode->i_mapping, - pos >> PAGE_SHIFT, end >> PAGE_SHIFT)); + nfs_truncate_last_folio(mapping, oldsize, pos); + WARN_ON_ONCE(invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT, + end >> PAGE_SHIFT)); spin_lock(&inode->i_lock); if (newsize > i_size_read(inode)) @@ -402,6 +416,7 @@ 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); size_t count = args->count; ssize_t status; @@ -430,6 +445,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, return status; } + nfs_file_block_o_direct(NFS_I(dst_inode)); status = nfs_sync_inode(dst_inode); if (status) return status; @@ -475,7 +491,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, goto out; } - nfs42_copy_dest_done(dst_inode, pos_dst, res->write_res.count); + nfs42_copy_dest_done(dst, pos_dst, res->write_res.count, oldsize_dst); nfs_invalidate_atime(src_inode); status = res->write_res.count; out: @@ -1242,6 +1258,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, struct nfs42_clone_res res = { .server = server, }; + loff_t oldsize_dst = i_size_read(dst_inode); int status; msg->rpc_argp = &args; @@ -1276,7 +1293,7 @@ static int _nfs42_proc_clone(struct rpc_message *msg, struct file *src_f, /* a zero-length count means clone to EOF in src */ if (count == 0 && res.dst_fattr->valid & NFS_ATTR_FATTR_SIZE) count = nfs_size_to_loff_t(res.dst_fattr->size) - dst_offset; - nfs42_copy_dest_done(dst_inode, dst_offset, count); + nfs42_copy_dest_done(dst_f, dst_offset, count, oldsize_dst); status = nfs_post_op_update_inode(dst_inode, res.dst_fattr); } diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 1d6b5f4230c9..c9a0d1e420c6 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -278,9 +278,11 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off, lock_two_nondirectories(src_inode, dst_inode); /* flush all pending writes on both src and dst so that server * has the latest data */ + nfs_file_block_o_direct(NFS_I(src_inode)); ret = nfs_sync_inode(src_inode); if (ret) goto out_unlock; + nfs_file_block_o_direct(NFS_I(dst_inode)); ret = nfs_sync_inode(dst_inode); if (ret) goto out_unlock; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 7d2b67e06cc3..ce61253efd45 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -4013,8 +4013,10 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f res.attr_bitmask[2]; } memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask)); - server->caps &= ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS | - NFS_CAP_SYMLINKS| NFS_CAP_SECURITY_LABEL); + server->caps &= + ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS | + NFS_CAP_SECURITY_LABEL | NFS_CAP_FS_LOCATIONS | + NFS_CAP_OPEN_XOR | NFS_CAP_DELEGTIME); server->fattr_valid = NFS_ATTR_FATTR_V4; if (res.attr_bitmask[0] & FATTR4_WORD0_ACL && res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL) @@ -4092,7 +4094,6 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) }; int err; - nfs_server_set_init_caps(server); do { err = nfs4_handle_exception(server, _nfs4_server_capabilities(server, fhandle), diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h index 96b1323318c2..627115179795 100644 --- a/fs/nfs/nfstrace.h +++ b/fs/nfs/nfstrace.h @@ -272,6 +272,7 @@ DECLARE_EVENT_CLASS(nfs_update_size_class, TP_ARGS(inode, new_size)) DEFINE_NFS_UPDATE_SIZE_EVENT(truncate); +DEFINE_NFS_UPDATE_SIZE_EVENT(truncate_folio); DEFINE_NFS_UPDATE_SIZE_EVENT(wcc); DEFINE_NFS_UPDATE_SIZE_EVENT(update); DEFINE_NFS_UPDATE_SIZE_EVENT(grow); diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 8b7c04737967..647c53d1418a 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -237,59 +237,17 @@ static void nfs_mapping_set_error(struct folio *folio, int error) } /* - * nfs_page_group_search_locked - * @head - head request of page group - * @page_offset - offset into page + * nfs_page_covers_folio + * @req: struct nfs_page * - * Search page group with head @head to find a request that contains the - * page offset @page_offset. - * - * Returns a pointer to the first matching nfs request, or NULL if no - * match is found. - * - * Must be called with the page group lock held - */ -static struct nfs_page * -nfs_page_group_search_locked(struct nfs_page *head, unsigned int page_offset) -{ - struct nfs_page *req; - - req = head; - do { - if (page_offset >= req->wb_pgbase && - page_offset < (req->wb_pgbase + req->wb_bytes)) - return req; - - req = req->wb_this_page; - } while (req != head); - - return NULL; -} - -/* - * nfs_page_group_covers_page - * @head - head request of page group - * - * Return true if the page group with head @head covers the whole page, - * returns false otherwise + * Return true if the request covers the whole folio. + * Note that the caller should ensure all subrequests have been joined */ static bool nfs_page_group_covers_page(struct nfs_page *req) { unsigned int len = nfs_folio_length(nfs_page_to_folio(req)); - struct nfs_page *tmp; - unsigned int pos = 0; - - nfs_page_group_lock(req); - for (;;) { - tmp = nfs_page_group_search_locked(req->wb_head, pos); - if (!tmp) - break; - pos = tmp->wb_pgbase + tmp->wb_bytes; - } - - nfs_page_group_unlock(req); - return pos >= len; + return req->wb_pgbase == 0 && req->wb_bytes == len; } /* We can set the PG_uptodate flag if we see that a write request @@ -2045,6 +2003,7 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio) * release it */ nfs_inode_remove_request(req); nfs_unlock_and_release_request(req); + folio_cancel_dirty(folio); } return ret; diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c index d98e0d2de09f..3c39cfacb251 100644 --- a/fs/resctrl/ctrlmondata.c +++ b/fs/resctrl/ctrlmondata.c @@ -625,11 +625,11 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg) */ list_for_each_entry(d, &r->mon_domains, hdr.list) { if (d->ci_id == domid) { - rr.ci_id = d->ci_id; cpu = cpumask_any(&d->hdr.cpu_mask); ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); if (!ci) continue; + rr.ci = ci; mon_event_read(&rr, r, NULL, rdtgrp, &ci->shared_cpu_map, evtid, false); goto checkresult; diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h index 0a1eedba2b03..9a8cf6f11151 100644 --- a/fs/resctrl/internal.h +++ b/fs/resctrl/internal.h @@ -98,7 +98,7 @@ struct mon_data { * domains in @r sharing L3 @ci.id * @evtid: Which monitor event to read. * @first: Initialize MBM counter when true. - * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summing domains. + * @ci: Cacheinfo for L3. Only set when @d is NULL. Used when summing domains. * @err: Error encountered when reading counter. * @val: Returned value of event counter. If @rgrp is a parent resource group, * @val includes the sum of event counts from its child resource groups. @@ -112,7 +112,7 @@ struct rmid_read { struct rdt_mon_domain *d; enum resctrl_event_id evtid; bool first; - unsigned int ci_id; + struct cacheinfo *ci; int err; u64 val; void *arch_mon_ctx; diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index f5637855c3ac..7326c28a7908 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -361,7 +361,6 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) { int cpu = smp_processor_id(); struct rdt_mon_domain *d; - struct cacheinfo *ci; struct mbm_state *m; int err, ret; u64 tval = 0; @@ -389,8 +388,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) } /* Summing domains that share a cache, must be on a CPU for that cache. */ - ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE); - if (!ci || ci->id != rr->ci_id) + if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map)) return -EINVAL; /* @@ -402,7 +400,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) */ ret = -EINVAL; list_for_each_entry(d, &rr->r->mon_domains, hdr.list) { - if (d->ci_id != rr->ci_id) + if (d->ci_id != rr->ci->id) continue; err = resctrl_arch_rmid_read(rr->r, d, closid, rmid, rr->evtid, &tval, rr->arch_mon_ctx); diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c index beb4f18f05ef..2337cf795db3 100644 --- a/fs/smb/client/cifs_debug.c +++ b/fs/smb/client/cifs_debug.c @@ -304,6 +304,8 @@ static int cifs_debug_dirs_proc_show(struct seq_file *m, void *v) list_for_each(tmp1, &ses->tcon_list) { tcon = list_entry(tmp1, struct cifs_tcon, tcon_list); cfids = tcon->cfids; + if (!cfids) + continue; spin_lock(&cfids->cfid_list_lock); /* check lock ordering */ seq_printf(m, "Num entries: %d\n", cfids->num_entries); list_for_each_entry(cfid, &cfids->entries, entry) { @@ -319,8 +321,6 @@ static int cifs_debug_dirs_proc_show(struct seq_file *m, void *v) seq_printf(m, "\n"); } spin_unlock(&cfids->cfid_list_lock); - - } } } @@ -347,6 +347,22 @@ static __always_inline const char *compression_alg_str(__le16 alg) } } +static __always_inline const char *cipher_alg_str(__le16 cipher) +{ + switch (cipher) { + case SMB2_ENCRYPTION_AES128_CCM: + return "AES128-CCM"; + case SMB2_ENCRYPTION_AES128_GCM: + return "AES128-GCM"; + case SMB2_ENCRYPTION_AES256_CCM: + return "AES256-CCM"; + case SMB2_ENCRYPTION_AES256_GCM: + return "AES256-GCM"; + default: + return "UNKNOWN"; + } +} + static int cifs_debug_data_proc_show(struct seq_file *m, void *v) { struct mid_q_entry *mid_entry; @@ -539,6 +555,11 @@ skip_rdma: else seq_puts(m, "disabled (not supported by this server)"); + /* Show negotiated encryption cipher, even if not required */ + seq_puts(m, "\nEncryption: "); + if (server->cipher_type) + seq_printf(m, "Negotiated cipher (%s)", cipher_alg_str(server->cipher_type)); + seq_printf(m, "\n\n\tSessions: "); i = 0; list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) { @@ -576,12 +597,8 @@ skip_rdma: /* dump session id helpful for use with network trace */ seq_printf(m, " SessionId: 0x%llx", ses->Suid); - if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) { + if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) seq_puts(m, " encrypted"); - /* can help in debugging to show encryption type */ - if (server->cipher_type == SMB2_ENCRYPTION_AES256_GCM) - seq_puts(m, "(gcm256)"); - } if (ses->sign) seq_puts(m, " signed"); diff --git a/fs/smb/client/cifs_unicode.c b/fs/smb/client/cifs_unicode.c index 4cc6e0896fad..f8659d36793f 100644 --- a/fs/smb/client/cifs_unicode.c +++ b/fs/smb/client/cifs_unicode.c @@ -629,6 +629,9 @@ cifs_strndup_to_utf16(const char *src, const int maxlen, int *utf16_len, int len; __le16 *dst; + if (!src) + return NULL; + len = cifs_local_to_utf16_bytes(src, maxlen, cp); len += 2; /* NULL */ dst = kmalloc(len, GFP_KERNEL); diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 1e64a4fb6af0..0fae95cf81c4 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -87,7 +87,7 @@ #define SMB_INTERFACE_POLL_INTERVAL 600 /* maximum number of PDUs in one compound */ -#define MAX_COMPOUND 7 +#define MAX_COMPOUND 10 /* * Default number of credits to keep available for SMB3. @@ -1882,9 +1882,12 @@ static inline bool is_replayable_error(int error) /* cifs_get_writable_file() flags */ -#define FIND_WR_ANY 0 -#define FIND_WR_FSUID_ONLY 1 -#define FIND_WR_WITH_DELETE 2 +enum cifs_writable_file_flags { + FIND_WR_ANY = 0U, + FIND_WR_FSUID_ONLY = (1U << 0), + FIND_WR_WITH_DELETE = (1U << 1), + FIND_WR_NO_PENDING_DELETE = (1U << 2), +}; #define MID_FREE 0 #define MID_REQUEST_ALLOCATED 1 @@ -2343,6 +2346,8 @@ struct smb2_compound_vars { struct kvec qi_iov; struct kvec io_iov[SMB2_IOCTL_IOV_SIZE]; struct kvec si_iov[SMB2_SET_INFO_IOV_SIZE]; + struct kvec unlink_iov[SMB2_SET_INFO_IOV_SIZE]; + struct kvec rename_iov[SMB2_SET_INFO_IOV_SIZE]; struct kvec close_iov; struct smb2_file_rename_info_hdr rename_info; struct smb2_file_link_info_hdr link_info; diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 186e061068be..cb907e18cc35 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -998,7 +998,10 @@ int cifs_open(struct inode *inode, struct file *file) /* Get the cached handle as SMB2 close is deferred */ if (OPEN_FMODE(file->f_flags) & FMODE_WRITE) { - rc = cifs_get_writable_path(tcon, full_path, FIND_WR_FSUID_ONLY, &cfile); + rc = cifs_get_writable_path(tcon, full_path, + FIND_WR_FSUID_ONLY | + FIND_WR_NO_PENDING_DELETE, + &cfile); } else { rc = cifs_get_readable_path(tcon, full_path, &cfile); } @@ -2530,6 +2533,9 @@ refind_writable: continue; if (with_delete && !(open_file->fid.access & DELETE)) continue; + if ((flags & FIND_WR_NO_PENDING_DELETE) && + open_file->status_file_deleted) + continue; if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) { if (!open_file->invalidHandle) { /* found a good writable file */ @@ -2647,6 +2653,16 @@ cifs_get_readable_path(struct cifs_tcon *tcon, const char *name, spin_unlock(&tcon->open_file_lock); free_dentry_path(page); *ret_file = find_readable_file(cinode, 0); + if (*ret_file) { + spin_lock(&cinode->open_file_lock); + if ((*ret_file)->status_file_deleted) { + spin_unlock(&cinode->open_file_lock); + cifsFileInfo_put(*ret_file); + *ret_file = NULL; + } else { + spin_unlock(&cinode->open_file_lock); + } + } return *ret_file ? 0 : -ENOENT; } diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index fe453a4b3dc8..11d442e8b3d6 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -1931,7 +1931,7 @@ cifs_drop_nlink(struct inode *inode) * but will return the EACCES to the caller. Note that the VFS does not call * unlink on negative dentries currently. */ -int cifs_unlink(struct inode *dir, struct dentry *dentry) +static int __cifs_unlink(struct inode *dir, struct dentry *dentry, bool sillyrename) { int rc = 0; unsigned int xid; @@ -2003,7 +2003,11 @@ retry_std_delete: goto psx_del_no_retry; } - rc = server->ops->unlink(xid, tcon, full_path, cifs_sb, dentry); + if (sillyrename || (server->vals->protocol_id > SMB10_PROT_ID && + d_is_positive(dentry) && d_count(dentry) > 2)) + rc = -EBUSY; + else + rc = server->ops->unlink(xid, tcon, full_path, cifs_sb, dentry); psx_del_no_retry: if (!rc) { @@ -2071,6 +2075,11 @@ unlink_out: return rc; } +int cifs_unlink(struct inode *dir, struct dentry *dentry) +{ + return __cifs_unlink(dir, dentry, false); +} + static int cifs_mkdir_qinfo(struct inode *parent, struct dentry *dentry, umode_t mode, const char *full_path, struct cifs_sb_info *cifs_sb, @@ -2358,14 +2367,16 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry) rc = server->ops->rmdir(xid, tcon, full_path, cifs_sb); cifs_put_tlink(tlink); + cifsInode = CIFS_I(d_inode(direntry)); + if (!rc) { + set_bit(CIFS_INO_DELETE_PENDING, &cifsInode->flags); spin_lock(&d_inode(direntry)->i_lock); i_size_write(d_inode(direntry), 0); clear_nlink(d_inode(direntry)); spin_unlock(&d_inode(direntry)->i_lock); } - cifsInode = CIFS_I(d_inode(direntry)); /* force revalidate to go get info when needed */ cifsInode->time = 0; @@ -2458,8 +2469,11 @@ cifs_do_rename(const unsigned int xid, struct dentry *from_dentry, } #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ do_rename_exit: - if (rc == 0) + if (rc == 0) { d_move(from_dentry, to_dentry); + /* Force a new lookup */ + d_drop(from_dentry); + } cifs_put_tlink(tlink); return rc; } @@ -2470,6 +2484,7 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, struct dentry *target_dentry, unsigned int flags) { const char *from_name, *to_name; + struct TCP_Server_Info *server; void *page1, *page2; struct cifs_sb_info *cifs_sb; struct tcon_link *tlink; @@ -2505,6 +2520,7 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, if (IS_ERR(tlink)) return PTR_ERR(tlink); tcon = tlink_tcon(tlink); + server = tcon->ses->server; page1 = alloc_dentry_path(); page2 = alloc_dentry_path(); @@ -2591,19 +2607,53 @@ cifs_rename2(struct mnt_idmap *idmap, struct inode *source_dir, unlink_target: #endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */ - - /* Try unlinking the target dentry if it's not negative */ - if (d_really_is_positive(target_dentry) && (rc == -EACCES || rc == -EEXIST)) { - if (d_is_dir(target_dentry)) - tmprc = cifs_rmdir(target_dir, target_dentry); - else - tmprc = cifs_unlink(target_dir, target_dentry); - if (tmprc) - goto cifs_rename_exit; - rc = cifs_do_rename(xid, source_dentry, from_name, - target_dentry, to_name); - if (!rc) - rehash = false; + if (d_really_is_positive(target_dentry)) { + if (!rc) { + struct inode *inode = d_inode(target_dentry); + /* + * Samba and ksmbd servers allow renaming a target + * directory that is open, so make sure to update + * ->i_nlink and then mark it as delete pending. + */ + if (S_ISDIR(inode->i_mode)) { + drop_cached_dir_by_name(xid, tcon, to_name, cifs_sb); + spin_lock(&inode->i_lock); + i_size_write(inode, 0); + clear_nlink(inode); + spin_unlock(&inode->i_lock); + set_bit(CIFS_INO_DELETE_PENDING, &CIFS_I(inode)->flags); + CIFS_I(inode)->time = 0; /* force reval */ + inode_set_ctime_current(inode); + inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); + } + } else if (rc == -EACCES || rc == -EEXIST) { + /* + * Rename failed, possibly due to a busy target. + * Retry it by unliking the target first. + */ + if (d_is_dir(target_dentry)) { + tmprc = cifs_rmdir(target_dir, target_dentry); + } else { + tmprc = __cifs_unlink(target_dir, target_dentry, + server->vals->protocol_id > SMB10_PROT_ID); + } + if (tmprc) { + /* + * Some servers will return STATUS_ACCESS_DENIED + * or STATUS_DIRECTORY_NOT_EMPTY when failing to + * rename a non-empty directory. Make sure to + * propagate the appropriate error back to + * userspace. + */ + if (tmprc == -EEXIST || tmprc == -ENOTEMPTY) + rc = tmprc; + goto cifs_rename_exit; + } + rc = cifs_do_rename(xid, source_dentry, from_name, + target_dentry, to_name); + if (!rc) + rehash = false; + } } /* force revalidate to go get info when needed */ @@ -2629,6 +2679,8 @@ cifs_dentry_needs_reval(struct dentry *dentry) struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); struct cached_fid *cfid = NULL; + if (test_bit(CIFS_INO_DELETE_PENDING, &cifs_i->flags)) + return false; if (cifs_i->time == 0) return true; diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c index 7869cec58f52..10c84c095fe7 100644 --- a/fs/smb/client/reparse.c +++ b/fs/smb/client/reparse.c @@ -278,7 +278,7 @@ static int detect_directory_symlink_target(struct cifs_sb_info *cifs_sb, } /* - * For absolute symlinks it is not possible to determinate + * For absolute symlinks it is not possible to determine * if it should point to directory or file. */ if (symname[0] == '/') { diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c index 893a1ea8c000..a02d41d1ce4a 100644 --- a/fs/smb/client/smb1ops.c +++ b/fs/smb/client/smb1ops.c @@ -1005,7 +1005,7 @@ smb_set_file_info(struct inode *inode, const char *full_path, rc = -EOPNOTSUPP; } - /* Fallback to SMB_COM_SETATTR command when absolutelty needed. */ + /* Fallback to SMB_COM_SETATTR command when absolutely needed. */ if (rc == -EOPNOTSUPP) { cifs_dbg(FYI, "calling SetInformation since SetPathInfo for attrs/times not supported by this server\n"); rc = SMBSetInformation(xid, tcon, full_path, @@ -1039,7 +1039,7 @@ set_via_filehandle: cifsFileInfo_put(open_file); /* - * Setting the read-only bit is not honered on non-NT servers when done + * Setting the read-only bit is not honored on non-NT servers when done * via open-semantics. So for setting it, use SMB_COM_SETATTR command. * This command works only after the file is closed, so use it only when * operation was called without the filehandle. diff --git a/fs/smb/client/smb2glob.h b/fs/smb/client/smb2glob.h index 224495322a05..e56e4d402f13 100644 --- a/fs/smb/client/smb2glob.h +++ b/fs/smb/client/smb2glob.h @@ -30,10 +30,9 @@ enum smb2_compound_ops { SMB2_OP_QUERY_DIR, SMB2_OP_MKDIR, SMB2_OP_RENAME, - SMB2_OP_DELETE, SMB2_OP_HARDLINK, SMB2_OP_SET_EOF, - SMB2_OP_RMDIR, + SMB2_OP_UNLINK, SMB2_OP_POSIX_QUERY_INFO, SMB2_OP_SET_REPARSE, SMB2_OP_GET_REPARSE, diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c index 31c13fb5b85b..7cadc8ca4f55 100644 --- a/fs/smb/client/smb2inode.c +++ b/fs/smb/client/smb2inode.c @@ -346,9 +346,6 @@ replay_again: trace_smb3_posix_query_info_compound_enter(xid, tcon->tid, ses->Suid, full_path); break; - case SMB2_OP_DELETE: - trace_smb3_delete_enter(xid, tcon->tid, ses->Suid, full_path); - break; case SMB2_OP_MKDIR: /* * Directories are created through parameters in the @@ -356,23 +353,40 @@ replay_again: */ trace_smb3_mkdir_enter(xid, tcon->tid, ses->Suid, full_path); break; - case SMB2_OP_RMDIR: - rqst[num_rqst].rq_iov = &vars->si_iov[0]; + case SMB2_OP_UNLINK: + rqst[num_rqst].rq_iov = vars->unlink_iov; rqst[num_rqst].rq_nvec = 1; size[0] = 1; /* sizeof __u8 See MS-FSCC section 2.4.11 */ data[0] = &delete_pending[0]; - rc = SMB2_set_info_init(tcon, server, - &rqst[num_rqst], COMPOUND_FID, - COMPOUND_FID, current->tgid, - FILE_DISPOSITION_INFORMATION, - SMB2_O_INFO_FILE, 0, data, size); - if (rc) + if (cfile) { + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], + cfile->fid.persistent_fid, + cfile->fid.volatile_fid, + current->tgid, + FILE_DISPOSITION_INFORMATION, + SMB2_O_INFO_FILE, 0, + data, size); + } else { + rc = SMB2_set_info_init(tcon, server, + &rqst[num_rqst], + COMPOUND_FID, + COMPOUND_FID, + current->tgid, + FILE_DISPOSITION_INFORMATION, + SMB2_O_INFO_FILE, 0, + data, size); + } + if (!rc && (!cfile || num_rqst > 1)) { + smb2_set_next_command(tcon, &rqst[num_rqst]); + smb2_set_related(&rqst[num_rqst]); + } else if (rc) { goto finished; - smb2_set_next_command(tcon, &rqst[num_rqst]); - smb2_set_related(&rqst[num_rqst++]); - trace_smb3_rmdir_enter(xid, tcon->tid, ses->Suid, full_path); + } + num_rqst++; + trace_smb3_unlink_enter(xid, tcon->tid, ses->Suid, full_path); break; case SMB2_OP_SET_EOF: rqst[num_rqst].rq_iov = &vars->si_iov[0]; @@ -442,7 +456,7 @@ replay_again: ses->Suid, full_path); break; case SMB2_OP_RENAME: - rqst[num_rqst].rq_iov = &vars->si_iov[0]; + rqst[num_rqst].rq_iov = vars->rename_iov; rqst[num_rqst].rq_nvec = 2; len = in_iov[i].iov_len; @@ -732,19 +746,6 @@ finished: trace_smb3_posix_query_info_compound_done(xid, tcon->tid, ses->Suid); break; - case SMB2_OP_DELETE: - if (rc) - trace_smb3_delete_err(xid, tcon->tid, ses->Suid, rc); - else { - /* - * If dentry (hence, inode) is NULL, lease break is going to - * take care of degrading leases on handles for deleted files. - */ - if (inode) - cifs_mark_open_handles_for_deleted_file(inode, full_path); - trace_smb3_delete_done(xid, tcon->tid, ses->Suid); - } - break; case SMB2_OP_MKDIR: if (rc) trace_smb3_mkdir_err(xid, tcon->tid, ses->Suid, rc); @@ -765,11 +766,11 @@ finished: trace_smb3_rename_done(xid, tcon->tid, ses->Suid); SMB2_set_info_free(&rqst[num_rqst++]); break; - case SMB2_OP_RMDIR: - if (rc) - trace_smb3_rmdir_err(xid, tcon->tid, ses->Suid, rc); + case SMB2_OP_UNLINK: + if (!rc) + trace_smb3_unlink_done(xid, tcon->tid, ses->Suid); else - trace_smb3_rmdir_done(xid, tcon->tid, ses->Suid); + trace_smb3_unlink_err(xid, tcon->tid, ses->Suid, rc); SMB2_set_info_free(&rqst[num_rqst++]); break; case SMB2_OP_SET_EOF: @@ -1166,7 +1167,7 @@ smb2_rmdir(const unsigned int xid, struct cifs_tcon *tcon, const char *name, FILE_OPEN, CREATE_NOT_FILE, ACL_NO_MODE); return smb2_compound_op(xid, tcon, cifs_sb, name, &oparms, NULL, - &(int){SMB2_OP_RMDIR}, 1, + &(int){SMB2_OP_UNLINK}, 1, NULL, NULL, NULL, NULL); } @@ -1175,20 +1176,29 @@ smb2_unlink(const unsigned int xid, struct cifs_tcon *tcon, const char *name, struct cifs_sb_info *cifs_sb, struct dentry *dentry) { struct cifs_open_parms oparms; + struct inode *inode = NULL; + int rc; - oparms = CIFS_OPARMS(cifs_sb, tcon, name, - DELETE, FILE_OPEN, - CREATE_DELETE_ON_CLOSE | OPEN_REPARSE_POINT, - ACL_NO_MODE); - int rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms, - NULL, &(int){SMB2_OP_DELETE}, 1, - NULL, NULL, NULL, dentry); + if (dentry) + inode = d_inode(dentry); + + oparms = CIFS_OPARMS(cifs_sb, tcon, name, DELETE, + FILE_OPEN, OPEN_REPARSE_POINT, ACL_NO_MODE); + rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms, + NULL, &(int){SMB2_OP_UNLINK}, + 1, NULL, NULL, NULL, dentry); if (rc == -EINVAL) { cifs_dbg(FYI, "invalid lease key, resending request without lease"); rc = smb2_compound_op(xid, tcon, cifs_sb, name, &oparms, - NULL, &(int){SMB2_OP_DELETE}, 1, - NULL, NULL, NULL, NULL); + NULL, &(int){SMB2_OP_UNLINK}, + 1, NULL, NULL, NULL, NULL); } + /* + * If dentry (hence, inode) is NULL, lease break is going to + * take care of degrading leases on handles for deleted files. + */ + if (!rc && inode) + cifs_mark_open_handles_for_deleted_file(inode, name); return rc; } @@ -1441,3 +1451,113 @@ out: cifs_free_open_info(&data); return rc; } + +static inline __le16 *utf16_smb2_path(struct cifs_sb_info *cifs_sb, + const char *name, size_t namelen) +{ + int len; + + if (*name == '\\' || + (cifs_sb_master_tlink(cifs_sb) && + cifs_sb_master_tcon(cifs_sb)->posix_extensions && *name == '/')) + name++; + return cifs_strndup_to_utf16(name, namelen, &len, + cifs_sb->local_nls, + cifs_remap(cifs_sb)); +} + +int smb2_rename_pending_delete(const char *full_path, + struct dentry *dentry, + const unsigned int xid) +{ + struct cifs_sb_info *cifs_sb = CIFS_SB(d_inode(dentry)->i_sb); + struct cifsInodeInfo *cinode = CIFS_I(d_inode(dentry)); + __le16 *utf16_path __free(kfree) = NULL; + __u32 co = file_create_options(dentry); + int cmds[] = { + SMB2_OP_SET_INFO, + SMB2_OP_RENAME, + SMB2_OP_UNLINK, + }; + const int num_cmds = ARRAY_SIZE(cmds); + char *to_name __free(kfree) = NULL; + __u32 attrs = cinode->cifsAttrs; + struct cifs_open_parms oparms; + static atomic_t sillycounter; + struct cifsFileInfo *cfile; + struct tcon_link *tlink; + struct cifs_tcon *tcon; + struct kvec iov[2]; + const char *ppath; + void *page; + size_t len; + int rc; + + tlink = cifs_sb_tlink(cifs_sb); + if (IS_ERR(tlink)) + return PTR_ERR(tlink); + tcon = tlink_tcon(tlink); + + page = alloc_dentry_path(); + + ppath = build_path_from_dentry(dentry->d_parent, page); + if (IS_ERR(ppath)) { + rc = PTR_ERR(ppath); + goto out; + } + + len = strlen(ppath) + strlen("/.__smb1234") + 1; + to_name = kmalloc(len, GFP_KERNEL); + if (!to_name) { + rc = -ENOMEM; + goto out; + } + + scnprintf(to_name, len, "%s%c.__smb%04X", ppath, CIFS_DIR_SEP(cifs_sb), + atomic_inc_return(&sillycounter) & 0xffff); + + utf16_path = utf16_smb2_path(cifs_sb, to_name, len); + if (!utf16_path) { + rc = -ENOMEM; + goto out; + } + + drop_cached_dir_by_name(xid, tcon, full_path, cifs_sb); + oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, + DELETE | FILE_WRITE_ATTRIBUTES, + FILE_OPEN, co, ACL_NO_MODE); + + attrs &= ~ATTR_READONLY; + if (!attrs) + attrs = ATTR_NORMAL; + if (d_inode(dentry)->i_nlink <= 1) + attrs |= ATTR_HIDDEN; + iov[0].iov_base = &(FILE_BASIC_INFO) { + .Attributes = cpu_to_le32(attrs), + }; + iov[0].iov_len = sizeof(FILE_BASIC_INFO); + iov[1].iov_base = utf16_path; + iov[1].iov_len = sizeof(*utf16_path) * UniStrlen((wchar_t *)utf16_path); + + cifs_get_writable_path(tcon, full_path, FIND_WR_WITH_DELETE, &cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov, + cmds, num_cmds, cfile, NULL, NULL, dentry); + if (rc == -EINVAL) { + cifs_dbg(FYI, "invalid lease key, resending request without lease\n"); + cifs_get_writable_path(tcon, full_path, + FIND_WR_WITH_DELETE, &cfile); + rc = smb2_compound_op(xid, tcon, cifs_sb, full_path, &oparms, iov, + cmds, num_cmds, cfile, NULL, NULL, NULL); + } + if (!rc) { + set_bit(CIFS_INO_DELETE_PENDING, &cinode->flags); + } else { + cifs_tcon_dbg(FYI, "%s: failed to rename '%s' to '%s': %d\n", + __func__, full_path, to_name, rc); + rc = -EIO; + } +out: + cifs_put_tlink(tlink); + free_dentry_path(page); + return rc; +} diff --git a/fs/smb/client/smb2misc.c b/fs/smb/client/smb2misc.c index cddf273c14ae..89d933b4a8bc 100644 --- a/fs/smb/client/smb2misc.c +++ b/fs/smb/client/smb2misc.c @@ -614,6 +614,15 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server) struct cifs_tcon *tcon; struct cifs_pending_open *open; + /* Trace receipt of lease break request from server */ + trace_smb3_lease_break_enter(le32_to_cpu(rsp->CurrentLeaseState), + le32_to_cpu(rsp->Flags), + le16_to_cpu(rsp->Epoch), + le32_to_cpu(rsp->hdr.Id.SyncId.TreeId), + le64_to_cpu(rsp->hdr.SessionId), + *((u64 *)rsp->LeaseKey), + *((u64 *)&rsp->LeaseKey[8])); + cifs_dbg(FYI, "Checking for lease break\n"); /* If server is a channel, select the primary channel */ @@ -660,10 +669,12 @@ smb2_is_valid_lease_break(char *buffer, struct TCP_Server_Info *server) spin_unlock(&cifs_tcp_ses_lock); cifs_dbg(FYI, "Can not process lease break - no lease matched\n"); trace_smb3_lease_not_found(le32_to_cpu(rsp->CurrentLeaseState), - le32_to_cpu(rsp->hdr.Id.SyncId.TreeId), - le64_to_cpu(rsp->hdr.SessionId), - *((u64 *)rsp->LeaseKey), - *((u64 *)&rsp->LeaseKey[8])); + le32_to_cpu(rsp->Flags), + le16_to_cpu(rsp->Epoch), + le32_to_cpu(rsp->hdr.Id.SyncId.TreeId), + le64_to_cpu(rsp->hdr.SessionId), + *((u64 *)rsp->LeaseKey), + *((u64 *)&rsp->LeaseKey[8])); return false; } diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 94b1d7a395d5..e586f3f4b5c9 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -2640,13 +2640,35 @@ smb2_set_next_command(struct cifs_tcon *tcon, struct smb_rqst *rqst) } /* SMB headers in a compound are 8 byte aligned. */ - if (!IS_ALIGNED(len, 8)) { - num_padding = 8 - (len & 7); + if (IS_ALIGNED(len, 8)) + goto out; + + num_padding = 8 - (len & 7); + if (smb3_encryption_required(tcon)) { + int i; + + /* + * Flatten request into a single buffer with required padding as + * the encryption layer can't handle the padding iovs. + */ + for (i = 1; i < rqst->rq_nvec; i++) { + memcpy(rqst->rq_iov[0].iov_base + + rqst->rq_iov[0].iov_len, + rqst->rq_iov[i].iov_base, + rqst->rq_iov[i].iov_len); + rqst->rq_iov[0].iov_len += rqst->rq_iov[i].iov_len; + } + memset(rqst->rq_iov[0].iov_base + rqst->rq_iov[0].iov_len, + 0, num_padding); + rqst->rq_iov[0].iov_len += num_padding; + rqst->rq_nvec = 1; + } else { rqst->rq_iov[rqst->rq_nvec].iov_base = smb2_padding; rqst->rq_iov[rqst->rq_nvec].iov_len = num_padding; rqst->rq_nvec++; - len += num_padding; } + len += num_padding; +out: shdr->NextCommand = cpu_to_le32(len); } @@ -5376,6 +5398,7 @@ struct smb_version_operations smb20_operations = { .llseek = smb3_llseek, .is_status_io_timeout = smb2_is_status_io_timeout, .is_network_name_deleted = smb2_is_network_name_deleted, + .rename_pending_delete = smb2_rename_pending_delete, }; #endif /* CIFS_ALLOW_INSECURE_LEGACY */ @@ -5481,6 +5504,7 @@ struct smb_version_operations smb21_operations = { .llseek = smb3_llseek, .is_status_io_timeout = smb2_is_status_io_timeout, .is_network_name_deleted = smb2_is_network_name_deleted, + .rename_pending_delete = smb2_rename_pending_delete, }; struct smb_version_operations smb30_operations = { @@ -5597,6 +5621,7 @@ struct smb_version_operations smb30_operations = { .llseek = smb3_llseek, .is_status_io_timeout = smb2_is_status_io_timeout, .is_network_name_deleted = smb2_is_network_name_deleted, + .rename_pending_delete = smb2_rename_pending_delete, }; struct smb_version_operations smb311_operations = { @@ -5713,6 +5738,7 @@ struct smb_version_operations smb311_operations = { .llseek = smb3_llseek, .is_status_io_timeout = smb2_is_status_io_timeout, .is_network_name_deleted = smb2_is_network_name_deleted, + .rename_pending_delete = smb2_rename_pending_delete, }; #ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c index 2df93a75e3b8..c3b9d3f6210f 100644 --- a/fs/smb/client/smb2pdu.c +++ b/fs/smb/client/smb2pdu.c @@ -6192,11 +6192,11 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon, please_key_high = (__u64 *)(lease_key+8); if (rc) { cifs_stats_fail_inc(tcon, SMB2_OPLOCK_BREAK_HE); - trace_smb3_lease_err(le32_to_cpu(lease_state), tcon->tid, + trace_smb3_lease_ack_err(le32_to_cpu(lease_state), tcon->tid, ses->Suid, *please_key_low, *please_key_high, rc); cifs_dbg(FYI, "Send error in Lease Break = %d\n", rc); } else - trace_smb3_lease_done(le32_to_cpu(lease_state), tcon->tid, + trace_smb3_lease_ack_done(le32_to_cpu(lease_state), tcon->tid, ses->Suid, *please_key_low, *please_key_high); return rc; diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index 6e805ece6a7b..b3f1398c9f79 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -317,5 +317,8 @@ int posix_info_sid_size(const void *beg, const void *end); int smb2_make_nfs_node(unsigned int xid, struct inode *inode, struct dentry *dentry, struct cifs_tcon *tcon, const char *full_path, umode_t mode, dev_t dev); +int smb2_rename_pending_delete(const char *full_path, + struct dentry *dentry, + const unsigned int xid); #endif /* _SMB2PROTO_H */ diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h index 93e5b2bb9f28..fd650e2afc76 100644 --- a/fs/smb/client/trace.h +++ b/fs/smb/client/trace.h @@ -669,13 +669,12 @@ DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(query_info_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(posix_query_info_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(hardlink_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(rename_enter); -DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(rmdir_enter); +DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(unlink_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_eof_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_info_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(set_reparse_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(get_reparse_compound_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(query_wsl_ea_compound_enter); -DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(delete_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mkdir_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(tdis_enter); DEFINE_SMB3_INF_COMPOUND_ENTER_EVENT(mknod_enter); @@ -710,13 +709,12 @@ DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(query_info_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(posix_query_info_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(hardlink_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(rename_done); -DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(rmdir_done); +DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(unlink_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_eof_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_info_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(set_reparse_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(get_reparse_compound_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(query_wsl_ea_compound_done); -DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(delete_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(mkdir_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(tdis_done); DEFINE_SMB3_INF_COMPOUND_DONE_EVENT(mknod_done); @@ -756,14 +754,13 @@ DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(query_info_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(posix_query_info_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(hardlink_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(rename_err); -DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(rmdir_err); +DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(unlink_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_eof_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_info_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(set_reparse_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(get_reparse_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(query_wsl_ea_compound_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(mkdir_err); -DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(delete_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(tdis_err); DEFINE_SMB3_INF_COMPOUND_ERR_EVENT(mknod_err); @@ -1171,8 +1168,54 @@ DEFINE_EVENT(smb3_lease_done_class, smb3_##name, \ __u64 lease_key_high), \ TP_ARGS(lease_state, tid, sesid, lease_key_low, lease_key_high)) -DEFINE_SMB3_LEASE_DONE_EVENT(lease_done); -DEFINE_SMB3_LEASE_DONE_EVENT(lease_not_found); +DEFINE_SMB3_LEASE_DONE_EVENT(lease_ack_done); +/* Tracepoint when a lease break request is received/entered (includes epoch and flags) */ +DECLARE_EVENT_CLASS(smb3_lease_enter_class, + TP_PROTO(__u32 lease_state, + __u32 flags, + __u16 epoch, + __u32 tid, + __u64 sesid, + __u64 lease_key_low, + __u64 lease_key_high), + TP_ARGS(lease_state, flags, epoch, tid, sesid, lease_key_low, lease_key_high), + TP_STRUCT__entry( + __field(__u32, lease_state) + __field(__u32, flags) + __field(__u16, epoch) + __field(__u32, tid) + __field(__u64, sesid) + __field(__u64, lease_key_low) + __field(__u64, lease_key_high) + ), + TP_fast_assign( + __entry->lease_state = lease_state; + __entry->flags = flags; + __entry->epoch = epoch; + __entry->tid = tid; + __entry->sesid = sesid; + __entry->lease_key_low = lease_key_low; + __entry->lease_key_high = lease_key_high; + ), + TP_printk("sid=0x%llx tid=0x%x lease_key=0x%llx%llx lease_state=0x%x flags=0x%x epoch=%u", + __entry->sesid, __entry->tid, __entry->lease_key_high, + __entry->lease_key_low, __entry->lease_state, __entry->flags, __entry->epoch) +) + +#define DEFINE_SMB3_LEASE_ENTER_EVENT(name) \ +DEFINE_EVENT(smb3_lease_enter_class, smb3_##name, \ + TP_PROTO(__u32 lease_state, \ + __u32 flags, \ + __u16 epoch, \ + __u32 tid, \ + __u64 sesid, \ + __u64 lease_key_low, \ + __u64 lease_key_high), \ + TP_ARGS(lease_state, flags, epoch, tid, sesid, lease_key_low, lease_key_high)) + +DEFINE_SMB3_LEASE_ENTER_EVENT(lease_break_enter); +/* Lease not found: reuse lease_enter payload (includes epoch and flags) */ +DEFINE_SMB3_LEASE_ENTER_EVENT(lease_not_found); DECLARE_EVENT_CLASS(smb3_lease_err_class, TP_PROTO(__u32 lease_state, @@ -1213,7 +1256,7 @@ DEFINE_EVENT(smb3_lease_err_class, smb3_##name, \ int rc), \ TP_ARGS(lease_state, tid, sesid, lease_key_low, lease_key_high, rc)) -DEFINE_SMB3_LEASE_ERR_EVENT(lease_err); +DEFINE_SMB3_LEASE_ERR_EVENT(lease_ack_err); DECLARE_EVENT_CLASS(smb3_connect_class, TP_PROTO(char *hostname, diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 0d92ce49aed7..a565fc36cee6 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -2951,18 +2951,19 @@ int smb2_open(struct ksmbd_work *work) } ksmbd_debug(SMB, "converted name = %s\n", name); - if (strchr(name, ':')) { - if (!test_share_config_flag(work->tcon->share_conf, - KSMBD_SHARE_FLAG_STREAMS)) { - rc = -EBADF; - goto err_out2; - } - rc = parse_stream_name(name, &stream_name, &s_type); - if (rc < 0) - goto err_out2; - } if (posix_ctxt == false) { + if (strchr(name, ':')) { + if (!test_share_config_flag(work->tcon->share_conf, + KSMBD_SHARE_FLAG_STREAMS)) { + rc = -EBADF; + goto err_out2; + } + rc = parse_stream_name(name, &stream_name, &s_type); + if (rc < 0) + goto err_out2; + } + rc = ksmbd_validate_filename(name); if (rc < 0) goto err_out2; @@ -3443,6 +3444,8 @@ int smb2_open(struct ksmbd_work *work) fp->attrib_only = !(req->DesiredAccess & ~(FILE_READ_ATTRIBUTES_LE | FILE_WRITE_ATTRIBUTES_LE | FILE_SYNCHRONIZE_LE)); + fp->is_posix_ctxt = posix_ctxt; + /* fp should be searchable through ksmbd_inode.m_fp_list * after daccess, saccess, attrib_only, and stream are * initialized. @@ -5988,7 +5991,7 @@ static int smb2_rename(struct ksmbd_work *work, if (IS_ERR(new_name)) return PTR_ERR(new_name); - if (strchr(new_name, ':')) { + if (fp->is_posix_ctxt == false && strchr(new_name, ':')) { int s_type; char *xattr_stream_name, *stream_name = NULL; size_t xattr_stream_size; diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index 5466aa8c39b1..6550bd9f002c 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -554,7 +554,7 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) case SMB_DIRECT_MSG_DATA_TRANSFER: { struct smb_direct_data_transfer *data_transfer = (struct smb_direct_data_transfer *)recvmsg->packet; - unsigned int data_length; + u32 remaining_data_length, data_offset, data_length; int avail_recvmsg_count, receive_credits; if (wc->byte_len < @@ -564,15 +564,25 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc) return; } + remaining_data_length = le32_to_cpu(data_transfer->remaining_data_length); data_length = le32_to_cpu(data_transfer->data_length); - if (data_length) { - if (wc->byte_len < sizeof(struct smb_direct_data_transfer) + - (u64)data_length) { - put_recvmsg(t, recvmsg); - smb_direct_disconnect_rdma_connection(t); - return; - } + data_offset = le32_to_cpu(data_transfer->data_offset); + if (wc->byte_len < data_offset || + wc->byte_len < (u64)data_offset + data_length) { + put_recvmsg(t, recvmsg); + smb_direct_disconnect_rdma_connection(t); + return; + } + if (remaining_data_length > t->max_fragmented_recv_size || + data_length > t->max_fragmented_recv_size || + (u64)remaining_data_length + (u64)data_length > + (u64)t->max_fragmented_recv_size) { + put_recvmsg(t, recvmsg); + smb_direct_disconnect_rdma_connection(t); + return; + } + if (data_length) { if (t->full_packet_received) recvmsg->first_segment = true; @@ -1209,78 +1219,130 @@ static int smb_direct_writev(struct ksmbd_transport *t, bool need_invalidate, unsigned int remote_key) { struct smb_direct_transport *st = smb_trans_direct_transfort(t); - int remaining_data_length; - int start, i, j; - int max_iov_size = st->max_send_size - + size_t remaining_data_length; + size_t iov_idx; + size_t iov_ofs; + size_t max_iov_size = st->max_send_size - sizeof(struct smb_direct_data_transfer); int ret; - struct kvec vec; struct smb_direct_send_ctx send_ctx; + int error = 0; if (st->status != SMB_DIRECT_CS_CONNECTED) return -ENOTCONN; //FIXME: skip RFC1002 header.. + if (WARN_ON_ONCE(niovs <= 1 || iov[0].iov_len != 4)) + return -EINVAL; buflen -= 4; + iov_idx = 1; + iov_ofs = 0; remaining_data_length = buflen; ksmbd_debug(RDMA, "Sending smb (RDMA): smb_len=%u\n", buflen); smb_direct_send_ctx_init(st, &send_ctx, need_invalidate, remote_key); - start = i = 1; - buflen = 0; - while (true) { - buflen += iov[i].iov_len; - if (buflen > max_iov_size) { - if (i > start) { - remaining_data_length -= - (buflen - iov[i].iov_len); - ret = smb_direct_post_send_data(st, &send_ctx, - &iov[start], i - start, - remaining_data_length); - if (ret) + while (remaining_data_length) { + struct kvec vecs[SMB_DIRECT_MAX_SEND_SGES - 1]; /* minus smbdirect hdr */ + size_t possible_bytes = max_iov_size; + size_t possible_vecs; + size_t bytes = 0; + size_t nvecs = 0; + + /* + * For the last message remaining_data_length should be + * have been 0 already! + */ + if (WARN_ON_ONCE(iov_idx >= niovs)) { + error = -EINVAL; + goto done; + } + + /* + * We have 2 factors which limit the arguments we pass + * to smb_direct_post_send_data(): + * + * 1. The number of supported sges for the send, + * while one is reserved for the smbdirect header. + * And we currently need one SGE per page. + * 2. The number of negotiated payload bytes per send. + */ + possible_vecs = min_t(size_t, ARRAY_SIZE(vecs), niovs - iov_idx); + + while (iov_idx < niovs && possible_vecs && possible_bytes) { + struct kvec *v = &vecs[nvecs]; + int page_count; + + v->iov_base = ((u8 *)iov[iov_idx].iov_base) + iov_ofs; + v->iov_len = min_t(size_t, + iov[iov_idx].iov_len - iov_ofs, + possible_bytes); + page_count = get_buf_page_count(v->iov_base, v->iov_len); + if (page_count > possible_vecs) { + /* + * If the number of pages in the buffer + * is to much (because we currently require + * one SGE per page), we need to limit the + * length. + * + * We know possible_vecs is at least 1, + * so we always keep the first page. + * + * We need to calculate the number extra + * pages (epages) we can also keep. + * + * We calculate the number of bytes in the + * first page (fplen), this should never be + * larger than v->iov_len because page_count is + * at least 2, but adding a limitation feels + * better. + * + * Then we calculate the number of bytes (elen) + * we can keep for the extra pages. + */ + size_t epages = possible_vecs - 1; + size_t fpofs = offset_in_page(v->iov_base); + size_t fplen = min_t(size_t, PAGE_SIZE - fpofs, v->iov_len); + size_t elen = min_t(size_t, v->iov_len - fplen, epages*PAGE_SIZE); + + v->iov_len = fplen + elen; + page_count = get_buf_page_count(v->iov_base, v->iov_len); + if (WARN_ON_ONCE(page_count > possible_vecs)) { + /* + * Something went wrong in the above + * logic... + */ + error = -EINVAL; goto done; - } else { - /* iov[start] is too big, break it */ - int nvec = (buflen + max_iov_size - 1) / - max_iov_size; - - for (j = 0; j < nvec; j++) { - vec.iov_base = - (char *)iov[start].iov_base + - j * max_iov_size; - vec.iov_len = - min_t(int, max_iov_size, - buflen - max_iov_size * j); - remaining_data_length -= vec.iov_len; - ret = smb_direct_post_send_data(st, &send_ctx, &vec, 1, - remaining_data_length); - if (ret) - goto done; } - i++; - if (i == niovs) - break; } - start = i; - buflen = 0; - } else { - i++; - if (i == niovs) { - /* send out all remaining vecs */ - remaining_data_length -= buflen; - ret = smb_direct_post_send_data(st, &send_ctx, - &iov[start], i - start, - remaining_data_length); - if (ret) - goto done; - break; + possible_vecs -= page_count; + nvecs += 1; + possible_bytes -= v->iov_len; + bytes += v->iov_len; + + iov_ofs += v->iov_len; + if (iov_ofs >= iov[iov_idx].iov_len) { + iov_idx += 1; + iov_ofs = 0; } } + + remaining_data_length -= bytes; + + ret = smb_direct_post_send_data(st, &send_ctx, + vecs, nvecs, + remaining_data_length); + if (unlikely(ret)) { + error = ret; + goto done; + } } done: ret = smb_direct_flush_send_list(st, &send_ctx, true); + if (unlikely(!ret && error)) + ret = error; /* * As an optimization, we don't wait for individual I/O to finish @@ -1744,6 +1806,11 @@ static int smb_direct_init_params(struct smb_direct_transport *t, return -EINVAL; } + if (device->attrs.max_send_sge < SMB_DIRECT_MAX_SEND_SGES) { + pr_err("warning: device max_send_sge = %d too small\n", + device->attrs.max_send_sge); + return -EINVAL; + } if (device->attrs.max_recv_sge < SMB_DIRECT_MAX_RECV_SGES) { pr_err("warning: device max_recv_sge = %d too small\n", device->attrs.max_recv_sge); @@ -1767,7 +1834,7 @@ static int smb_direct_init_params(struct smb_direct_transport *t, cap->max_send_wr = max_send_wrs; cap->max_recv_wr = t->recv_credit_max; - cap->max_send_sge = max_sge_per_wr; + cap->max_send_sge = SMB_DIRECT_MAX_SEND_SGES; cap->max_recv_sge = SMB_DIRECT_MAX_RECV_SGES; cap->max_inline_data = 0; cap->max_rdma_ctxs = t->max_rw_credits; diff --git a/fs/smb/server/vfs_cache.h b/fs/smb/server/vfs_cache.h index 0708155b5caf..78b506c5ef03 100644 --- a/fs/smb/server/vfs_cache.h +++ b/fs/smb/server/vfs_cache.h @@ -112,6 +112,8 @@ struct ksmbd_file { bool is_durable; bool is_persistent; bool is_resilient; + + bool is_posix_ctxt; }; static inline void set_ctx_actor(struct dir_context *ctx, |