diff options
Diffstat (limited to 'fs')
50 files changed, 862 insertions, 480 deletions
diff --git a/fs/9p/vfs_dentry.c b/fs/9p/vfs_dentry.c index f3248a3e5402..c1acbc98465d 100644 --- a/fs/9p/vfs_dentry.c +++ b/fs/9p/vfs_dentry.c @@ -66,7 +66,6 @@ static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) struct p9_fid *fid; struct inode *inode; struct v9fs_inode *v9inode; - unsigned int cached; if (flags & LOOKUP_RCU) return -ECHILD; @@ -76,11 +75,7 @@ static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) goto out_valid; v9inode = V9FS_I(inode); - struct v9fs_session_info *v9ses = v9fs_inode2v9ses(inode); - - cached = v9ses->cache & (CACHE_META | CACHE_LOOSE); - - if (!cached || v9inode->cache_validity & V9FS_INO_INVALID_ATTR) { + if (v9inode->cache_validity & V9FS_INO_INVALID_ATTR) { int retval; struct v9fs_session_info *v9ses; @@ -114,6 +109,7 @@ static int __v9fs_lookup_revalidate(struct dentry *dentry, unsigned int flags) p9_debug(P9_DEBUG_VFS, "refresh inode: dentry = %pd (%p), got error %pe\n", dentry, dentry, ERR_PTR(retval)); + if (retval < 0) return retval; } } @@ -150,8 +146,6 @@ const struct dentry_operations v9fs_cached_dentry_operations = { }; const struct dentry_operations v9fs_dentry_operations = { - .d_revalidate = v9fs_lookup_revalidate, - .d_weak_revalidate = __v9fs_lookup_revalidate, .d_release = v9fs_dentry_release, .d_unalias_trylock = v9fs_dentry_unalias_trylock, .d_unalias_unlock = v9fs_dentry_unalias_unlock, diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 69f378a83775..d0c77ec31b1d 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -1339,14 +1339,8 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode) * Don't update inode if the file type is different */ umode = p9mode2unixmode(v9ses, st, &rdev); - if (inode_wrong_type(inode, umode)) { - /* - * Do this as a way of letting the caller know the inode should not - * be reused - */ - v9fs_invalidate_inode_attr(inode); + if (inode_wrong_type(inode, umode)) goto out; - } /* * We don't want to refresh inode->i_size, diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c index 0b404e8484d2..be297e335468 100644 --- a/fs/9p/vfs_inode_dotl.c +++ b/fs/9p/vfs_inode_dotl.c @@ -897,14 +897,8 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode) /* * Don't update inode if the file type is different */ - if (inode_wrong_type(inode, st->st_mode)) { - /* - * Do this as a way of letting the caller know the inode should not - * be reused - */ - v9fs_invalidate_inode_attr(inode); + if (inode_wrong_type(inode, st->st_mode)) goto out; - } /* * We don't want to refresh inode->i_size, diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 41e37f7f67cc..3df7b9d7fbe8 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -2110,9 +2110,9 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root) for (int i = 0; i < count; i++) { __btrfs_kill_delayed_node(delayed_nodes[i]); + btrfs_delayed_node_ref_tracker_dir_print(delayed_nodes[i]); btrfs_release_delayed_node(delayed_nodes[i], &delayed_node_trackers[i]); - btrfs_delayed_node_ref_tracker_dir_print(delayed_nodes[i]); } } } diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index 0d949edc0caf..b09d4ec8c77d 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -219,6 +219,13 @@ static inline void btrfs_delayed_node_ref_tracker_dir_print(struct btrfs_delayed if (!btrfs_test_opt(node->root->fs_info, REF_TRACKER)) return; + /* + * Only print if there are leaked references. The caller is + * holding one reference, so if refs == 1 there is no leak. + */ + if (refcount_read(&node->refs) == 1) + return; + ref_tracker_dir_print(&node->ref_dir.dir, BTRFS_DELAYED_NODE_REF_TRACKER_DISPLAY_LIMIT); } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 755ec6dfd51c..23273d0e6f22 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2228,6 +2228,14 @@ static noinline_for_stack void write_one_eb(struct extent_buffer *eb, wbc_account_cgroup_owner(wbc, folio, range_len); folio_unlock(folio); } + /* + * If the fs is already in error status, do not submit any writeback + * but immediately finish it. + */ + if (unlikely(BTRFS_FS_ERROR(fs_info))) { + btrfs_bio_end_io(bbio, errno_to_blk_status(BTRFS_FS_ERROR(fs_info))); + return; + } btrfs_submit_bbio(bbio, 0); } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 7efd1f8a1912..fa82def46e39 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -2854,12 +2854,22 @@ static int btrfs_fallocate_update_isize(struct inode *inode, { struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(inode)->root; + u64 range_start; + u64 range_end; int ret; int ret2; if (mode & FALLOC_FL_KEEP_SIZE || end <= i_size_read(inode)) return 0; + range_start = round_down(i_size_read(inode), root->fs_info->sectorsize); + range_end = round_up(end, root->fs_info->sectorsize); + + ret = btrfs_inode_set_file_extent_range(BTRFS_I(inode), range_start, + range_end - range_start); + if (ret) + return ret; + trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) return PTR_ERR(trans); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 3b1b3a0553ee..3df5f36185a0 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6873,7 +6873,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir, BTRFS_I(inode)->dir_index = 0ULL; inode_inc_iversion(inode); inode_set_ctime_current(inode); - set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags); ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), &fname.disk_name, 1, index); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 1175b8192cd7..31ad8580322a 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -1539,8 +1539,10 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src, u64 dst ASSERT(prealloc); /* Check the level of src and dst first */ - if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst)) + if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst)) { + kfree(prealloc); return -EINVAL; + } mutex_lock(&fs_info->qgroup_ioctl_lock); if (!fs_info->quota_root) { diff --git a/fs/btrfs/ref-verify.c b/fs/btrfs/ref-verify.c index de4cb0f3fbd0..e9224145d754 100644 --- a/fs/btrfs/ref-verify.c +++ b/fs/btrfs/ref-verify.c @@ -982,7 +982,7 @@ int btrfs_build_ref_tree(struct btrfs_fs_info *fs_info) extent_root = btrfs_extent_root(fs_info, 0); /* If the extent tree is damaged we cannot ignore it (IGNOREBADROOTS). */ - if (IS_ERR(extent_root)) { + if (!extent_root) { btrfs_warn(fs_info, "ref-verify: extent tree not available, disabling"); btrfs_clear_opt(fs_info->mount_opt, REF_VERIFY); return 0; diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 6144e66661f5..96a030d28e09 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -4102,6 +4102,48 @@ out: return ret; } +static int rbtree_check_dir_ref_comp(const void *k, const struct rb_node *node) +{ + const struct recorded_ref *data = k; + const struct recorded_ref *ref = rb_entry(node, struct recorded_ref, node); + + if (data->dir > ref->dir) + return 1; + if (data->dir < ref->dir) + return -1; + if (data->dir_gen > ref->dir_gen) + return 1; + if (data->dir_gen < ref->dir_gen) + return -1; + return 0; +} + +static bool rbtree_check_dir_ref_less(struct rb_node *node, const struct rb_node *parent) +{ + const struct recorded_ref *entry = rb_entry(node, struct recorded_ref, node); + + return rbtree_check_dir_ref_comp(entry, parent) < 0; +} + +static int record_check_dir_ref_in_tree(struct rb_root *root, + struct recorded_ref *ref, struct list_head *list) +{ + struct recorded_ref *tmp_ref; + int ret; + + if (rb_find(ref, root, rbtree_check_dir_ref_comp)) + return 0; + + ret = dup_ref(ref, list); + if (ret < 0) + return ret; + + tmp_ref = list_last_entry(list, struct recorded_ref, list); + rb_add(&tmp_ref->node, root, rbtree_check_dir_ref_less); + tmp_ref->root = root; + return 0; +} + static int rename_current_inode(struct send_ctx *sctx, struct fs_path *current_path, struct fs_path *new_path) @@ -4129,11 +4171,11 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) struct recorded_ref *cur; struct recorded_ref *cur2; LIST_HEAD(check_dirs); + struct rb_root rbtree_check_dirs = RB_ROOT; struct fs_path *valid_path = NULL; u64 ow_inode = 0; u64 ow_gen; u64 ow_mode; - u64 last_dir_ino_rm = 0; bool did_overwrite = false; bool is_orphan = false; bool can_rename = true; @@ -4437,7 +4479,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) goto out; } } - ret = dup_ref(cur, &check_dirs); + ret = record_check_dir_ref_in_tree(&rbtree_check_dirs, cur, &check_dirs); if (ret < 0) goto out; } @@ -4465,7 +4507,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) } list_for_each_entry(cur, &sctx->deleted_refs, list) { - ret = dup_ref(cur, &check_dirs); + ret = record_check_dir_ref_in_tree(&rbtree_check_dirs, cur, &check_dirs); if (ret < 0) goto out; } @@ -4475,7 +4517,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) * We have a moved dir. Add the old parent to check_dirs */ cur = list_first_entry(&sctx->deleted_refs, struct recorded_ref, list); - ret = dup_ref(cur, &check_dirs); + ret = record_check_dir_ref_in_tree(&rbtree_check_dirs, cur, &check_dirs); if (ret < 0) goto out; } else if (!S_ISDIR(sctx->cur_inode_mode)) { @@ -4509,7 +4551,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) if (is_current_inode_path(sctx, cur->full_path)) fs_path_reset(&sctx->cur_inode_path); } - ret = dup_ref(cur, &check_dirs); + ret = record_check_dir_ref_in_tree(&rbtree_check_dirs, cur, &check_dirs); if (ret < 0) goto out; } @@ -4552,8 +4594,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) ret = cache_dir_utimes(sctx, cur->dir, cur->dir_gen); if (ret < 0) goto out; - } else if (ret == inode_state_did_delete && - cur->dir != last_dir_ino_rm) { + } else if (ret == inode_state_did_delete) { ret = can_rmdir(sctx, cur->dir, cur->dir_gen); if (ret < 0) goto out; @@ -4565,7 +4606,6 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move) ret = send_rmdir(sctx, valid_path); if (ret < 0) goto out; - last_dir_ino_rm = cur->dir; } } } diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index aadc02374b2a..430e7419349c 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -2068,7 +2068,13 @@ static int btrfs_get_tree_subvol(struct fs_context *fc) fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL); fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL); if (!fs_info->super_copy || !fs_info->super_for_commit) { - btrfs_free_fs_info(fs_info); + /* + * Dont call btrfs_free_fs_info() to free it as it's still + * initialized partially. + */ + kfree(fs_info->super_copy); + kfree(fs_info->super_for_commit); + kvfree(fs_info); return -ENOMEM; } btrfs_init_fs_info(fs_info); diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 621e0df097e3..c90b2d2cb08f 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -7910,6 +7910,9 @@ void btrfs_log_new_name(struct btrfs_trans_handle *trans, bool log_pinned = false; int ret; + /* The inode has a new name (ref/extref), so make sure we log it. */ + set_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags); + btrfs_init_log_ctx(&ctx, inode); ctx.logging_new_name = true; diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index 5dee7c498bc8..ed6e926226b5 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -333,8 +333,7 @@ static bool bh_get_inode_and_lblk_num(const struct buffer_head *bh, inode = mapping->host; *inode_ret = inode; - *lblk_num_ret = ((u64)folio->index << (PAGE_SHIFT - inode->i_blkbits)) + - (bh_offset(bh) >> inode->i_blkbits); + *lblk_num_ret = (folio_pos(folio) + bh_offset(bh)) >> inode->i_blkbits; return true; } diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index e5581dbeb4c2..c8d8e129eb4b 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -55,10 +55,6 @@ static int z_erofs_load_full_lcluster(struct z_erofs_maprecorder *m, } else { m->partialref = !!(advise & Z_EROFS_LI_PARTIAL_REF); m->clusterofs = le16_to_cpu(di->di_clusterofs); - if (m->clusterofs >= 1 << vi->z_lclusterbits) { - DBG_BUGON(1); - return -EFSCORRUPTED; - } m->pblk = le32_to_cpu(di->di_u.blkaddr); } return 0; @@ -240,21 +236,29 @@ static int z_erofs_load_compact_lcluster(struct z_erofs_maprecorder *m, static int z_erofs_load_lcluster_from_disk(struct z_erofs_maprecorder *m, unsigned int lcn, bool lookahead) { + struct erofs_inode *vi = EROFS_I(m->inode); + int err; + + if (vi->datalayout == EROFS_INODE_COMPRESSED_COMPACT) { + err = z_erofs_load_compact_lcluster(m, lcn, lookahead); + } else { + DBG_BUGON(vi->datalayout != EROFS_INODE_COMPRESSED_FULL); + err = z_erofs_load_full_lcluster(m, lcn); + } + if (err) + return err; + if (m->type >= Z_EROFS_LCLUSTER_TYPE_MAX) { erofs_err(m->inode->i_sb, "unknown type %u @ lcn %u of nid %llu", - m->type, lcn, EROFS_I(m->inode)->nid); + m->type, lcn, EROFS_I(m->inode)->nid); DBG_BUGON(1); return -EOPNOTSUPP; + } else if (m->type != Z_EROFS_LCLUSTER_TYPE_NONHEAD && + m->clusterofs >= (1 << vi->z_lclusterbits)) { + DBG_BUGON(1); + return -EFSCORRUPTED; } - - switch (EROFS_I(m->inode)->datalayout) { - case EROFS_INODE_COMPRESSED_FULL: - return z_erofs_load_full_lcluster(m, lcn); - case EROFS_INODE_COMPRESSED_COMPACT: - return z_erofs_load_compact_lcluster(m, lcn, lookahead); - default: - return -EINVAL; - } + return 0; } static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, @@ -268,20 +272,19 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, unsigned long lcn = m->lcn - lookback_distance; int err; + if (!lookback_distance) + break; + err = z_erofs_load_lcluster_from_disk(m, lcn, false); if (err) return err; - if (m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) { lookback_distance = m->delta[0]; - if (!lookback_distance) - break; continue; - } else { - m->headtype = m->type; - m->map->m_la = (lcn << lclusterbits) | m->clusterofs; - return 0; } + m->headtype = m->type; + m->map->m_la = (lcn << lclusterbits) | m->clusterofs; + return 0; } erofs_err(sb, "bogus lookback distance %u @ lcn %lu of nid %llu", lookback_distance, m->lcn, vi->nid); @@ -431,13 +434,6 @@ static int z_erofs_map_blocks_fo(struct inode *inode, end = inode->i_size; } else { if (m.type != Z_EROFS_LCLUSTER_TYPE_NONHEAD) { - /* m.lcn should be >= 1 if endoff < m.clusterofs */ - if (!m.lcn) { - erofs_err(sb, "invalid logical cluster 0 at nid %llu", - vi->nid); - err = -EFSCORRUPTED; - goto unmap_out; - } end = (m.lcn << lclusterbits) | m.clusterofs; map->m_flags |= EROFS_MAP_FULL_MAPPED; m.delta[0] = 1; @@ -596,7 +592,7 @@ static int z_erofs_map_blocks_ext(struct inode *inode, vi->z_fragmentoff = map->m_plen; if (recsz > offsetof(struct z_erofs_extent, pstart_lo)) vi->z_fragmentoff |= map->m_pa << 32; - } else if (map->m_plen) { + } else if (map->m_plen & Z_EROFS_EXTENT_PLEN_MASK) { map->m_flags |= EROFS_MAP_MAPPED | EROFS_MAP_FULL_MAPPED | EROFS_MAP_ENCODED; fmt = map->m_plen >> Z_EROFS_EXTENT_PLEN_FMT_BIT; @@ -715,6 +711,7 @@ static int z_erofs_map_sanity_check(struct inode *inode, struct erofs_map_blocks *map) { struct erofs_sb_info *sbi = EROFS_I_SB(inode); + u64 pend; if (!(map->m_flags & EROFS_MAP_ENCODED)) return 0; @@ -732,6 +729,10 @@ static int z_erofs_map_sanity_check(struct inode *inode, if (unlikely(map->m_plen > Z_EROFS_PCLUSTER_MAX_SIZE || map->m_llen > Z_EROFS_PCLUSTER_MAX_DSIZE)) return -EOPNOTSUPP; + /* Filesystems beyond 48-bit physical block addresses are invalid */ + if (unlikely(check_add_overflow(map->m_pa, map->m_plen, &pend) || + (pend >> sbi->blkszbits) >= BIT_ULL(48))) + return -EFSCORRUPTED; return 0; } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 9c94ed8c3ab0..f42548ee9083 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -478,14 +478,6 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end, if (!hugetlb_vma_trylock_write(vma)) continue; - /* - * Skip VMAs without shareable locks. Per the design in commit - * 40549ba8f8e0, these will be handled by remove_inode_hugepages() - * called after this function with proper locking. - */ - if (!__vma_shareable_lock(vma)) - goto skip; - v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); @@ -496,7 +488,6 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end, * vmas. Therefore, lock is not held when calling * unmap_hugepage_range for private vmas. */ -skip: hugetlb_vma_unlock_write(vma); } } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index e466cf52d7d7..7f7e6bb23a90 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -988,10 +988,11 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, static void nfsd4_read_release(union nfsd4_op_u *u) { - if (u->read.rd_nf) + if (u->read.rd_nf) { + trace_nfsd_read_done(u->read.rd_rqstp, u->read.rd_fhp, + u->read.rd_offset, u->read.rd_length); nfsd_file_put(u->read.rd_nf); - trace_nfsd_read_done(u->read.rd_rqstp, u->read.rd_fhp, - u->read.rd_offset, u->read.rd_length); + } } static __be32 @@ -2892,10 +2893,20 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) rqstp->rq_lease_breaker = (void **)&cstate->clp; - trace_nfsd_compound(rqstp, args->tag, args->taglen, args->opcnt); + trace_nfsd_compound(rqstp, args->tag, args->taglen, args->client_opcnt); while (!status && resp->opcnt < args->opcnt) { op = &args->ops[resp->opcnt++]; + if (unlikely(resp->opcnt == NFSD_MAX_OPS_PER_COMPOUND)) { + /* If there are still more operations to process, + * stop here and report NFS4ERR_RESOURCE. */ + if (cstate->minorversion == 0 && + args->client_opcnt > resp->opcnt) { + op->status = nfserr_resource; + goto encode_op; + } + } + /* * The XDR decode routines may have pre-set op->status; * for example, if there is a miscellaneous XDR error @@ -2972,7 +2983,7 @@ encode_op: status = op->status; } - trace_nfsd_compound_status(args->opcnt, resp->opcnt, + trace_nfsd_compound_status(args->client_opcnt, resp->opcnt, status, nfsd4_op_name(op->opnum)); nfsd4_cstate_clear_replay(cstate); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 81fa7cc6c77b..c1b54322c412 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -3902,6 +3902,7 @@ static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfs ca->headerpadsz = 0; ca->maxreq_sz = min_t(u32, ca->maxreq_sz, maxrpc); ca->maxresp_sz = min_t(u32, ca->maxresp_sz, maxrpc); + ca->maxops = min_t(u32, ca->maxops, NFSD_MAX_OPS_PER_COMPOUND); ca->maxresp_cached = min_t(u32, ca->maxresp_cached, NFSD_SLOT_CACHE_SIZE + NFSD_MIN_HDR_SEQ_SZ); ca->maxreqs = min_t(u32, ca->maxreqs, NFSD_MAX_SLOTS_PER_SESSION); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index c0a3c6a7c8bb..6040a6145dad 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2488,8 +2488,10 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) if (xdr_stream_decode_u32(argp->xdr, &argp->minorversion) < 0) return false; - if (xdr_stream_decode_u32(argp->xdr, &argp->opcnt) < 0) + if (xdr_stream_decode_u32(argp->xdr, &argp->client_opcnt) < 0) return false; + argp->opcnt = min_t(u32, argp->client_opcnt, + NFSD_MAX_OPS_PER_COMPOUND); if (argp->opcnt > ARRAY_SIZE(argp->iops)) { argp->ops = vcalloc(argp->opcnt, sizeof(*argp->ops)); @@ -2628,10 +2630,8 @@ static __be32 nfsd4_encode_components_esc(struct xdr_stream *xdr, char sep, __be32 *p; __be32 pathlen; int pathlen_offset; - int strlen, count=0; char *str, *end, *next; - - dprintk("nfsd4_encode_components(%s)\n", components); + int count = 0; pathlen_offset = xdr->buf->len; p = xdr_reserve_space(xdr, 4); @@ -2658,9 +2658,8 @@ static __be32 nfsd4_encode_components_esc(struct xdr_stream *xdr, char sep, for (; *end && (*end != sep); end++) /* find sep or end of string */; - strlen = end - str; - if (strlen) { - if (xdr_stream_encode_opaque(xdr, str, strlen) < 0) + if (end > str) { + if (xdr_stream_encode_opaque(xdr, str, end - str) < 0) return nfserr_resource; count++; } else @@ -2939,6 +2938,12 @@ struct nfsd4_fattr_args { typedef __be32(*nfsd4_enc_attr)(struct xdr_stream *xdr, const struct nfsd4_fattr_args *args); +static __be32 nfsd4_encode_fattr4__inval(struct xdr_stream *xdr, + const struct nfsd4_fattr_args *args) +{ + return nfserr_inval; +} + static __be32 nfsd4_encode_fattr4__noop(struct xdr_stream *xdr, const struct nfsd4_fattr_args *args) { @@ -3560,6 +3565,8 @@ static const nfsd4_enc_attr nfsd4_enc_fattr4_encode_ops[] = { [FATTR4_MODE_UMASK] = nfsd4_encode_fattr4__noop, [FATTR4_XATTR_SUPPORT] = nfsd4_encode_fattr4_xattr_support, + [FATTR4_TIME_DELEG_ACCESS] = nfsd4_encode_fattr4__inval, + [FATTR4_TIME_DELEG_MODIFY] = nfsd4_encode_fattr4__inval, [FATTR4_OPEN_ARGUMENTS] = nfsd4_encode_fattr4_open_arguments, }; diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index ea87b42894dd..f19320018639 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -57,6 +57,9 @@ struct readdir_cd { __be32 err; /* 0, nfserr, or nfserr_eof */ }; +/* Maximum number of operations per session compound */ +#define NFSD_MAX_OPS_PER_COMPOUND 200 + struct nfsd_genl_rqstp { struct sockaddr rq_daddr; struct sockaddr rq_saddr; diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index d4b48602b2b0..ee0570cbdd9e 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -903,6 +903,7 @@ struct nfsd4_compoundargs { char * tag; u32 taglen; u32 minorversion; + u32 client_opcnt; u32 opcnt; bool splice_ok; struct nfsd4_op *ops; diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c index 1161eabf11ee..9cc7eb863643 100644 --- a/fs/notify/fdinfo.c +++ b/fs/notify/fdinfo.c @@ -17,6 +17,7 @@ #include "fanotify/fanotify.h" #include "fdinfo.h" #include "fsnotify.h" +#include "../internal.h" #if defined(CONFIG_PROC_FS) @@ -46,7 +47,12 @@ static void show_mark_fhandle(struct seq_file *m, struct inode *inode) size = f->handle_bytes >> 2; + if (!super_trylock_shared(inode->i_sb)) + return; + ret = exportfs_encode_fid(inode, (struct fid *)f->f_handle, &size); + up_read(&inode->i_sb->s_umount); + if ((ret == FILEID_INVALID) || (ret < 0)) return; diff --git a/fs/ocfs2/move_extents.c b/fs/ocfs2/move_extents.c index 86f2631e6360..10923bf7c8b8 100644 --- a/fs/ocfs2/move_extents.c +++ b/fs/ocfs2/move_extents.c @@ -867,6 +867,11 @@ static int __ocfs2_move_extents_range(struct buffer_head *di_bh, mlog_errno(ret); goto out; } + /* + * Invalidate extent cache after moving/defragging to prevent + * stale cached data with outdated extent flags. + */ + ocfs2_extent_map_trunc(inode, cpos); context->clusters_moved += alloc_size; next: diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c index 4076336fbba6..572a9925bd6c 100644 --- a/fs/resctrl/monitor.c +++ b/fs/resctrl/monitor.c @@ -1782,15 +1782,13 @@ int resctrl_mon_resource_init(void) mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID; if (r->mon.mbm_cntr_assignable) { - if (!resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) - resctrl_enable_mon_event(QOS_L3_MBM_TOTAL_EVENT_ID); - if (!resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) - resctrl_enable_mon_event(QOS_L3_MBM_LOCAL_EVENT_ID); - mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].evt_cfg = r->mon.mbm_cfg_mask; - mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID].evt_cfg = r->mon.mbm_cfg_mask & - (READS_TO_LOCAL_MEM | - READS_TO_LOCAL_S_MEM | - NON_TEMP_WRITE_TO_LOCAL_MEM); + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_TOTAL_EVENT_ID)) + mon_event_all[QOS_L3_MBM_TOTAL_EVENT_ID].evt_cfg = r->mon.mbm_cfg_mask; + if (resctrl_is_mon_event_enabled(QOS_L3_MBM_LOCAL_EVENT_ID)) + mon_event_all[QOS_L3_MBM_LOCAL_EVENT_ID].evt_cfg = r->mon.mbm_cfg_mask & + (READS_TO_LOCAL_MEM | + READS_TO_LOCAL_S_MEM | + NON_TEMP_WRITE_TO_LOCAL_MEM); r->mon.mbm_assign_on_mkdir = true; resctrl_file_fflags_init("num_mbm_cntrs", RFTYPE_MON_INFO | RFTYPE_RES_CACHE); diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c index 4f959f1e08d2..185ac41bd7e9 100644 --- a/fs/smb/client/cifsfs.c +++ b/fs/smb/client/cifsfs.c @@ -173,7 +173,7 @@ module_param(enable_oplocks, bool, 0644); MODULE_PARM_DESC(enable_oplocks, "Enable or disable oplocks. Default: y/Y/1"); module_param(enable_gcm_256, bool, 0644); -MODULE_PARM_DESC(enable_gcm_256, "Enable requesting strongest (256 bit) GCM encryption. Default: y/Y/0"); +MODULE_PARM_DESC(enable_gcm_256, "Enable requesting strongest (256 bit) GCM encryption. Default: y/Y/1"); module_param(require_gcm_256, bool, 0644); MODULE_PARM_DESC(require_gcm_256, "Require strongest (256 bit) GCM encryption. Default: n/N/0"); diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index 16a00a61fd2c..203e2aaa3c25 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -534,8 +534,6 @@ struct smb_version_operations { void (*new_lease_key)(struct cifs_fid *); int (*generate_signingkey)(struct cifs_ses *ses, struct TCP_Server_Info *server); - int (*calc_signature)(struct smb_rqst *, struct TCP_Server_Info *, - bool allocate_crypto); int (*set_integrity)(const unsigned int, struct cifs_tcon *tcon, struct cifsFileInfo *src_file); int (*enum_snapshots)(const unsigned int xid, struct cifs_tcon *tcon, @@ -732,7 +730,7 @@ struct TCP_Server_Info { bool nosharesock; bool tcp_nodelay; bool terminate; - unsigned int credits; /* send no more requests at once */ + int credits; /* send no more requests at once */ unsigned int max_credits; /* can override large 32000 default at mnt */ unsigned int in_flight; /* number of requests on the wire to server */ unsigned int max_in_flight; /* max number of requests that were on wire */ diff --git a/fs/smb/client/cifsproto.h b/fs/smb/client/cifsproto.h index 4976be2c47c1..3528c365a452 100644 --- a/fs/smb/client/cifsproto.h +++ b/fs/smb/client/cifsproto.h @@ -9,6 +9,7 @@ #define _CIFSPROTO_H #include <linux/nls.h> #include <linux/ctype.h> +#include "cifsglob.h" #include "trace.h" #ifdef CONFIG_CIFS_DFS_UPCALL #include "dfs_cache.h" @@ -615,6 +616,8 @@ extern int E_md4hash(const unsigned char *passwd, unsigned char *p16, extern struct TCP_Server_Info * cifs_find_tcp_session(struct smb3_fs_context *ctx); +struct cifs_tcon *cifs_setup_ipc(struct cifs_ses *ses, bool seal); + void __cifs_put_smb_ses(struct cifs_ses *ses); extern struct cifs_ses * diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 2881efcbe09a..7da194f29fef 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -1311,6 +1311,8 @@ cifs_readv_callback(struct mid_q_entry *mid) .rreq_debug_id = rdata->rreq->debug_id, .rreq_debug_index = rdata->subreq.debug_index, }; + unsigned int rreq_debug_id = rdata->rreq->debug_id; + unsigned int subreq_debug_index = rdata->subreq.debug_index; cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu\n", __func__, mid->mid, mid->mid_state, rdata->result, @@ -1374,6 +1376,9 @@ do_retry: __set_bit(NETFS_SREQ_MADE_PROGRESS, &rdata->subreq.flags); } + trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value, + server->credits, server->in_flight, + 0, cifs_trace_rw_credits_read_response_clear); rdata->credits.value = 0; rdata->subreq.error = rdata->result; rdata->subreq.transferred += rdata->got_bytes; @@ -1381,6 +1386,9 @@ do_retry: netfs_read_subreq_terminated(&rdata->subreq); release_mid(mid); add_credits(server, &credits, 0); + trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0, + server->credits, server->in_flight, + credits.value, cifs_trace_rw_credits_read_response_add); } /* cifs_async_readv - send an async write, and set up mid to handle result */ diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index dd12f3eb61dc..55cb4b0cbd48 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -310,6 +310,8 @@ cifs_abort_connection(struct TCP_Server_Info *server) server->ssocket->flags); sock_release(server->ssocket); server->ssocket = NULL; + } else if (cifs_rdma_enabled(server)) { + smbd_destroy(server); } server->sequence_number = 0; server->session_estab = false; @@ -338,12 +340,6 @@ cifs_abort_connection(struct TCP_Server_Info *server) mid_execute_callback(mid); release_mid(mid); } - - if (cifs_rdma_enabled(server)) { - cifs_server_lock(server); - smbd_destroy(server); - cifs_server_unlock(server); - } } static bool cifs_tcp_ses_needs_reconnect(struct TCP_Server_Info *server, int num_targets) @@ -2015,39 +2011,31 @@ static int match_session(struct cifs_ses *ses, /** * cifs_setup_ipc - helper to setup the IPC tcon for the session * @ses: smb session to issue the request on - * @ctx: the superblock configuration context to use for building the - * new tree connection for the IPC (interprocess communication RPC) + * @seal: if encryption is requested * * A new IPC connection is made and stored in the session * tcon_ipc. The IPC tcon has the same lifetime as the session. */ -static int -cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx) +struct cifs_tcon *cifs_setup_ipc(struct cifs_ses *ses, bool seal) { int rc = 0, xid; struct cifs_tcon *tcon; char unc[SERVER_NAME_LENGTH + sizeof("//x/IPC$")] = {0}; - bool seal = false; struct TCP_Server_Info *server = ses->server; /* * If the mount request that resulted in the creation of the * session requires encryption, force IPC to be encrypted too. */ - if (ctx->seal) { - if (server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) - seal = true; - else { - cifs_server_dbg(VFS, - "IPC: server doesn't support encryption\n"); - return -EOPNOTSUPP; - } + if (seal && !(server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION)) { + cifs_server_dbg(VFS, "IPC: server doesn't support encryption\n"); + return ERR_PTR(-EOPNOTSUPP); } /* no need to setup directory caching on IPC share, so pass in false */ tcon = tcon_info_alloc(false, netfs_trace_tcon_ref_new_ipc); if (tcon == NULL) - return -ENOMEM; + return ERR_PTR(-ENOMEM); spin_lock(&server->srv_lock); scnprintf(unc, sizeof(unc), "\\\\%s\\IPC$", server->hostname); @@ -2057,13 +2045,13 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx) tcon->ses = ses; tcon->ipc = true; tcon->seal = seal; - rc = server->ops->tree_connect(xid, ses, unc, tcon, ctx->local_nls); + rc = server->ops->tree_connect(xid, ses, unc, tcon, ses->local_nls); free_xid(xid); if (rc) { - cifs_server_dbg(VFS, "failed to connect to IPC (rc=%d)\n", rc); + cifs_server_dbg(VFS | ONCE, "failed to connect to IPC (rc=%d)\n", rc); tconInfoFree(tcon, netfs_trace_tcon_ref_free_ipc_fail); - goto out; + return ERR_PTR(rc); } cifs_dbg(FYI, "IPC tcon rc=%d ipc tid=0x%x\n", rc, tcon->tid); @@ -2071,9 +2059,7 @@ cifs_setup_ipc(struct cifs_ses *ses, struct smb3_fs_context *ctx) spin_lock(&tcon->tc_lock); tcon->status = TID_GOOD; spin_unlock(&tcon->tc_lock); - ses->tcon_ipc = tcon; -out: - return rc; + return tcon; } static struct cifs_ses * @@ -2347,6 +2333,7 @@ cifs_get_smb_ses(struct TCP_Server_Info *server, struct smb3_fs_context *ctx) { struct sockaddr_in6 *addr6 = (struct sockaddr_in6 *)&server->dstaddr; struct sockaddr_in *addr = (struct sockaddr_in *)&server->dstaddr; + struct cifs_tcon *ipc; struct cifs_ses *ses; unsigned int xid; int retries = 0; @@ -2525,7 +2512,12 @@ retry_new_session: list_add(&ses->smb_ses_list, &server->smb_ses_list); spin_unlock(&cifs_tcp_ses_lock); - cifs_setup_ipc(ses, ctx); + ipc = cifs_setup_ipc(ses, ctx->seal); + spin_lock(&cifs_tcp_ses_lock); + spin_lock(&ses->ses_lock); + ses->tcon_ipc = !IS_ERR(ipc) ? ipc : NULL; + spin_unlock(&ses->ses_lock); + spin_unlock(&cifs_tcp_ses_lock); free_xid(xid); diff --git a/fs/smb/client/dfs_cache.c b/fs/smb/client/dfs_cache.c index 4dada26d56b5..f2ad0ccd08a7 100644 --- a/fs/smb/client/dfs_cache.c +++ b/fs/smb/client/dfs_cache.c @@ -1120,24 +1120,63 @@ static bool target_share_equal(struct cifs_tcon *tcon, const char *s1) return match; } -static bool is_ses_good(struct cifs_ses *ses) +static bool is_ses_good(struct cifs_tcon *tcon, struct cifs_ses *ses) { struct TCP_Server_Info *server = ses->server; - struct cifs_tcon *tcon = ses->tcon_ipc; + struct cifs_tcon *ipc = NULL; bool ret; + spin_lock(&cifs_tcp_ses_lock); spin_lock(&ses->ses_lock); spin_lock(&ses->chan_lock); + ret = !cifs_chan_needs_reconnect(ses, server) && - ses->ses_status == SES_GOOD && - !tcon->need_reconnect; + ses->ses_status == SES_GOOD; + spin_unlock(&ses->chan_lock); + + if (!ret) + goto out; + + if (likely(ses->tcon_ipc)) { + if (ses->tcon_ipc->need_reconnect) { + ret = false; + goto out; + } + } else { + spin_unlock(&ses->ses_lock); + spin_unlock(&cifs_tcp_ses_lock); + + ipc = cifs_setup_ipc(ses, tcon->seal); + + spin_lock(&cifs_tcp_ses_lock); + spin_lock(&ses->ses_lock); + if (!IS_ERR(ipc)) { + if (!ses->tcon_ipc) { + ses->tcon_ipc = ipc; + ipc = NULL; + } + } else { + ret = false; + ipc = NULL; + } + } + +out: spin_unlock(&ses->ses_lock); + spin_unlock(&cifs_tcp_ses_lock); + if (ipc && server->ops->tree_disconnect) { + unsigned int xid = get_xid(); + + (void)server->ops->tree_disconnect(xid, ipc); + _free_xid(xid); + } + tconInfoFree(ipc, netfs_trace_tcon_ref_free_ipc); return ret; } /* Refresh dfs referral of @ses */ -static void refresh_ses_referral(struct cifs_ses *ses) +static void refresh_ses_referral(struct cifs_tcon *tcon, struct cifs_ses *ses) { struct cache_entry *ce; unsigned int xid; @@ -1153,7 +1192,7 @@ static void refresh_ses_referral(struct cifs_ses *ses) } ses = CIFS_DFS_ROOT_SES(ses); - if (!is_ses_good(ses)) { + if (!is_ses_good(tcon, ses)) { cifs_dbg(FYI, "%s: skip cache refresh due to disconnected ipc\n", __func__); goto out; @@ -1241,7 +1280,7 @@ static void refresh_tcon_referral(struct cifs_tcon *tcon, bool force_refresh) up_read(&htable_rw_lock); ses = CIFS_DFS_ROOT_SES(ses); - if (!is_ses_good(ses)) { + if (!is_ses_good(tcon, ses)) { cifs_dbg(FYI, "%s: skip cache refresh due to disconnected ipc\n", __func__); goto out; @@ -1309,7 +1348,7 @@ void dfs_cache_refresh(struct work_struct *work) tcon = container_of(work, struct cifs_tcon, dfs_cache_work.work); list_for_each_entry(ses, &tcon->dfs_ses_list, dlist) - refresh_ses_referral(ses); + refresh_ses_referral(tcon, ses); refresh_tcon_referral(tcon, false); queue_delayed_work(dfscache_wq, &tcon->dfs_cache_work, diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c index 098a79b7a959..cac355364e43 100644 --- a/fs/smb/client/inode.c +++ b/fs/smb/client/inode.c @@ -2484,11 +2484,8 @@ 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; } diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 95cd484cfbba..1e39f2165e42 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -2799,11 +2799,12 @@ smb2_query_info_compound(const unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid fid; int rc; __le16 *utf16_path; - struct cached_fid *cfid = NULL; + struct cached_fid *cfid; int retries = 0, cur_sleep = 1; replay_again: /* reinitialize for possible replay */ + cfid = NULL; flags = CIFS_CP_CREATE_CLOSE_OP; oplock = SMB2_OPLOCK_LEVEL_NONE; server = cifs_pick_channel(ses); @@ -5446,7 +5447,6 @@ struct smb_version_operations smb20_operations = { .get_lease_key = smb2_get_lease_key, .set_lease_key = smb2_set_lease_key, .new_lease_key = smb2_new_lease_key, - .calc_signature = smb2_calc_signature, .is_read_op = smb2_is_read_op, .set_oplock_level = smb2_set_oplock_level, .create_lease_buf = smb2_create_lease_buf, @@ -5550,7 +5550,6 @@ struct smb_version_operations smb21_operations = { .get_lease_key = smb2_get_lease_key, .set_lease_key = smb2_set_lease_key, .new_lease_key = smb2_new_lease_key, - .calc_signature = smb2_calc_signature, .is_read_op = smb21_is_read_op, .set_oplock_level = smb21_set_oplock_level, .create_lease_buf = smb2_create_lease_buf, @@ -5660,7 +5659,6 @@ struct smb_version_operations smb30_operations = { .set_lease_key = smb2_set_lease_key, .new_lease_key = smb2_new_lease_key, .generate_signingkey = generate_smb30signingkey, - .calc_signature = smb3_calc_signature, .set_integrity = smb3_set_integrity, .is_read_op = smb21_is_read_op, .set_oplock_level = smb3_set_oplock_level, @@ -5777,7 +5775,6 @@ struct smb_version_operations smb311_operations = { .set_lease_key = smb2_set_lease_key, .new_lease_key = smb2_new_lease_key, .generate_signingkey = generate_smb311signingkey, - .calc_signature = smb3_calc_signature, .set_integrity = smb3_set_integrity, .is_read_op = smb21_is_read_op, .set_oplock_level = smb3_set_oplock_level, diff --git a/fs/smb/client/smb2proto.h b/fs/smb/client/smb2proto.h index 6eb86d134abc..5241daaae543 100644 --- a/fs/smb/client/smb2proto.h +++ b/fs/smb/client/smb2proto.h @@ -39,12 +39,6 @@ extern struct mid_q_entry *smb2_setup_async_request( struct TCP_Server_Info *server, struct smb_rqst *rqst); extern struct cifs_tcon *smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid); -extern int smb2_calc_signature(struct smb_rqst *rqst, - struct TCP_Server_Info *server, - bool allocate_crypto); -extern int smb3_calc_signature(struct smb_rqst *rqst, - struct TCP_Server_Info *server, - bool allocate_crypto); extern void smb2_echo_request(struct work_struct *work); extern __le32 smb2_get_lease_state(struct cifsInodeInfo *cinode); extern bool smb2_is_valid_oplock_break(char *buffer, diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index ad6068e17a2a..6a9b80385b86 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -209,9 +209,9 @@ smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32 tid) return tcon; } -int +static int smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, - bool allocate_crypto) + bool allocate_crypto) { int rc; unsigned char smb2_signature[SMB2_HMACSHA256_SIZE]; @@ -465,9 +465,9 @@ generate_smb311signingkey(struct cifs_ses *ses, return generate_smb3signingkey(ses, server, &triplet); } -int +static int smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, - bool allocate_crypto) + bool allocate_crypto) { int rc; unsigned char smb3_signature[SMB2_CMACAES_SIZE]; @@ -477,6 +477,9 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server, struct smb_rqst drqst; u8 key[SMB3_SIGN_KEY_SIZE]; + if (server->vals->protocol_id <= SMB21_PROT_ID) + return smb2_calc_signature(rqst, server, allocate_crypto); + rc = smb3_get_sign_key(le64_to_cpu(shdr->SessionId), server, key); if (unlikely(rc)) { cifs_server_dbg(FYI, "%s: Could not get signing key\n", __func__); @@ -547,7 +550,6 @@ out: static int smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server) { - int rc = 0; struct smb2_hdr *shdr; struct smb2_sess_setup_req *ssr; bool is_binding; @@ -574,9 +576,7 @@ smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server) return 0; } - rc = server->ops->calc_signature(rqst, server, false); - - return rc; + return smb3_calc_signature(rqst, server, false); } int @@ -612,7 +612,7 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server) memset(shdr->Signature, 0, SMB2_SIGNATURE_SIZE); - rc = server->ops->calc_signature(rqst, server, true); + rc = smb3_calc_signature(rqst, server, true); if (rc) return rc; diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c index 49e2df3ad1f0..85a4c55b61b8 100644 --- a/fs/smb/client/smbdirect.c +++ b/fs/smb/client/smbdirect.c @@ -172,6 +172,7 @@ static void smbd_disconnect_wake_up_all(struct smbdirect_socket *sc) * in order to notice the broken connection. */ wake_up_all(&sc->status_wait); + wake_up_all(&sc->send_io.lcredits.wait_queue); wake_up_all(&sc->send_io.credits.wait_queue); wake_up_all(&sc->send_io.pending.dec_wait_queue); wake_up_all(&sc->send_io.pending.zero_wait_queue); @@ -495,6 +496,7 @@ static void send_done(struct ib_cq *cq, struct ib_wc *wc) struct smbdirect_send_io *request = container_of(wc->wr_cqe, struct smbdirect_send_io, cqe); struct smbdirect_socket *sc = request->socket; + int lcredits = 0; log_rdma_send(INFO, "smbdirect_send_io 0x%p completed wc->status=%s\n", request, ib_wc_status_msg(wc->status)); @@ -504,22 +506,24 @@ static void send_done(struct ib_cq *cq, struct ib_wc *wc) request->sge[i].addr, request->sge[i].length, DMA_TO_DEVICE); + mempool_free(request, sc->send_io.mem.pool); + lcredits += 1; if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_SEND) { if (wc->status != IB_WC_WR_FLUSH_ERR) log_rdma_send(ERR, "wc->status=%s wc->opcode=%d\n", ib_wc_status_msg(wc->status), wc->opcode); - mempool_free(request, sc->send_io.mem.pool); smbd_disconnect_rdma_connection(sc); return; } + atomic_add(lcredits, &sc->send_io.lcredits.count); + wake_up(&sc->send_io.lcredits.wait_queue); + if (atomic_dec_and_test(&sc->send_io.pending.count)) wake_up(&sc->send_io.pending.zero_wait_queue); wake_up(&sc->send_io.pending.dec_wait_queue); - - mempool_free(request, sc->send_io.mem.pool); } static void dump_smbdirect_negotiate_resp(struct smbdirect_negotiate_resp *resp) @@ -567,6 +571,7 @@ static bool process_negotiation_response( log_rdma_event(ERR, "error: credits_granted==0\n"); return false; } + atomic_set(&sc->send_io.lcredits.count, sp->send_credit_target); atomic_set(&sc->send_io.credits.count, le16_to_cpu(packet->credits_granted)); if (le32_to_cpu(packet->preferred_send_size) > sp->max_recv_size) { @@ -1114,6 +1119,24 @@ static int smbd_post_send_iter(struct smbdirect_socket *sc, struct smbdirect_data_transfer *packet; int new_credits = 0; +wait_lcredit: + /* Wait for local send credits */ + rc = wait_event_interruptible(sc->send_io.lcredits.wait_queue, + atomic_read(&sc->send_io.lcredits.count) > 0 || + sc->status != SMBDIRECT_SOCKET_CONNECTED); + if (rc) + goto err_wait_lcredit; + + if (sc->status != SMBDIRECT_SOCKET_CONNECTED) { + log_outgoing(ERR, "disconnected not sending on wait_credit\n"); + rc = -EAGAIN; + goto err_wait_lcredit; + } + if (unlikely(atomic_dec_return(&sc->send_io.lcredits.count) < 0)) { + atomic_inc(&sc->send_io.lcredits.count); + goto wait_lcredit; + } + wait_credit: /* Wait for send credits. A SMBD packet needs one credit */ rc = wait_event_interruptible(sc->send_io.credits.wait_queue, @@ -1132,23 +1155,6 @@ wait_credit: goto wait_credit; } -wait_send_queue: - wait_event(sc->send_io.pending.dec_wait_queue, - atomic_read(&sc->send_io.pending.count) < sp->send_credit_target || - sc->status != SMBDIRECT_SOCKET_CONNECTED); - - if (sc->status != SMBDIRECT_SOCKET_CONNECTED) { - log_outgoing(ERR, "disconnected not sending on wait_send_queue\n"); - rc = -EAGAIN; - goto err_wait_send_queue; - } - - if (unlikely(atomic_inc_return(&sc->send_io.pending.count) > - sp->send_credit_target)) { - atomic_dec(&sc->send_io.pending.count); - goto wait_send_queue; - } - request = mempool_alloc(sc->send_io.mem.pool, GFP_KERNEL); if (!request) { rc = -ENOMEM; @@ -1229,10 +1235,21 @@ wait_send_queue: le32_to_cpu(packet->data_length), le32_to_cpu(packet->remaining_data_length)); + /* + * Now that we got a local and a remote credit + * we add us as pending + */ + atomic_inc(&sc->send_io.pending.count); + rc = smbd_post_send(sc, request); if (!rc) return 0; + if (atomic_dec_and_test(&sc->send_io.pending.count)) + wake_up(&sc->send_io.pending.zero_wait_queue); + + wake_up(&sc->send_io.pending.dec_wait_queue); + err_dma: for (i = 0; i < request->num_sge; i++) if (request->sge[i].addr) @@ -1246,14 +1263,14 @@ err_dma: atomic_sub(new_credits, &sc->recv_io.credits.count); err_alloc: - if (atomic_dec_and_test(&sc->send_io.pending.count)) - wake_up(&sc->send_io.pending.zero_wait_queue); - -err_wait_send_queue: - /* roll back send credits and pending */ atomic_inc(&sc->send_io.credits.count); + wake_up(&sc->send_io.credits.wait_queue); err_wait_credit: + atomic_inc(&sc->send_io.lcredits.count); + wake_up(&sc->send_io.lcredits.wait_queue); + +err_wait_lcredit: return rc; } @@ -1767,6 +1784,7 @@ static struct smbd_connection *_smbd_get_connection( struct smbdirect_socket *sc; struct smbdirect_socket_parameters *sp; struct rdma_conn_param conn_param; + struct ib_qp_cap qp_cap; struct ib_qp_init_attr qp_attr; struct sockaddr_in *addr_in = (struct sockaddr_in *) dstaddr; struct ib_port_immutable port_immutable; @@ -1838,6 +1856,25 @@ static struct smbd_connection *_smbd_get_connection( goto config_failed; } + sp->responder_resources = + min_t(u8, sp->responder_resources, + sc->ib.dev->attrs.max_qp_rd_atom); + log_rdma_mr(INFO, "responder_resources=%d\n", + sp->responder_resources); + + /* + * We use allocate sp->responder_resources * 2 MRs + * and each MR needs WRs for REG and INV, so + * we use '* 4'. + * + * +1 for ib_drain_qp() + */ + memset(&qp_cap, 0, sizeof(qp_cap)); + qp_cap.max_send_wr = sp->send_credit_target + sp->responder_resources * 4 + 1; + qp_cap.max_recv_wr = sp->recv_credit_max + 1; + qp_cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; + qp_cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; + sc->ib.pd = ib_alloc_pd(sc->ib.dev, 0); if (IS_ERR(sc->ib.pd)) { rc = PTR_ERR(sc->ib.pd); @@ -1848,7 +1885,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.send_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->send_credit_target, IB_POLL_SOFTIRQ); + qp_cap.max_send_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.send_cq)) { sc->ib.send_cq = NULL; goto alloc_cq_failed; @@ -1856,7 +1893,7 @@ static struct smbd_connection *_smbd_get_connection( sc->ib.recv_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->recv_credit_max, IB_POLL_SOFTIRQ); + qp_cap.max_recv_wr, IB_POLL_SOFTIRQ); if (IS_ERR(sc->ib.recv_cq)) { sc->ib.recv_cq = NULL; goto alloc_cq_failed; @@ -1865,11 +1902,7 @@ static struct smbd_connection *_smbd_get_connection( memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.event_handler = smbd_qp_async_error_upcall; qp_attr.qp_context = sc; - qp_attr.cap.max_send_wr = sp->send_credit_target; - qp_attr.cap.max_recv_wr = sp->recv_credit_max; - qp_attr.cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; - qp_attr.cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; - qp_attr.cap.max_inline_data = 0; + qp_attr.cap = qp_cap; qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR; qp_attr.qp_type = IB_QPT_RC; qp_attr.send_cq = sc->ib.send_cq; @@ -1883,12 +1916,6 @@ static struct smbd_connection *_smbd_get_connection( } sc->ib.qp = sc->rdma.cm_id->qp; - sp->responder_resources = - min_t(u8, sp->responder_resources, - sc->ib.dev->attrs.max_qp_rd_atom); - log_rdma_mr(INFO, "responder_resources=%d\n", - sp->responder_resources); - memset(&conn_param, 0, sizeof(conn_param)); conn_param.initiator_depth = sp->initiator_depth; conn_param.responder_resources = sp->responder_resources; diff --git a/fs/smb/client/trace.c b/fs/smb/client/trace.c index 465483787193..16b0e719731f 100644 --- a/fs/smb/client/trace.c +++ b/fs/smb/client/trace.c @@ -4,5 +4,6 @@ * * Author(s): Steve French <stfrench@microsoft.com> */ +#include "cifsglob.h" #define CREATE_TRACE_POINTS #include "trace.h" diff --git a/fs/smb/common/smbdirect/smbdirect_socket.h b/fs/smb/common/smbdirect/smbdirect_socket.h index 361db7f9f623..ee5a90d691c8 100644 --- a/fs/smb/common/smbdirect/smbdirect_socket.h +++ b/fs/smb/common/smbdirect/smbdirect_socket.h @@ -142,7 +142,15 @@ struct smbdirect_socket { } mem; /* - * The credit state for the send side + * The local credit state for ib_post_send() + */ + struct { + atomic_t count; + wait_queue_head_t wait_queue; + } lcredits; + + /* + * The remote credit state for the send side */ struct { atomic_t count; @@ -337,6 +345,9 @@ static __always_inline void smbdirect_socket_init(struct smbdirect_socket *sc) INIT_DELAYED_WORK(&sc->idle.timer_work, __smbdirect_socket_disabled_work); disable_delayed_work_sync(&sc->idle.timer_work); + atomic_set(&sc->send_io.lcredits.count, 0); + init_waitqueue_head(&sc->send_io.lcredits.wait_queue); + atomic_set(&sc->send_io.credits.count, 0); init_waitqueue_head(&sc->send_io.credits.wait_queue); diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c index 46f87fd1ce1c..2c08cccfa680 100644 --- a/fs/smb/server/transport_ipc.c +++ b/fs/smb/server/transport_ipc.c @@ -263,10 +263,16 @@ static void ipc_msg_handle_free(int handle) static int handle_response(int type, void *payload, size_t sz) { - unsigned int handle = *(unsigned int *)payload; + unsigned int handle; struct ipc_msg_table_entry *entry; int ret = 0; + /* Prevent 4-byte read beyond declared payload size */ + if (sz < sizeof(unsigned int)) + return -EINVAL; + + handle = *(unsigned int *)payload; + ipc_update_last_active(); down_read(&ipc_msg_table_lock); hash_for_each_possible(ipc_msg_table, entry, ipc_table_hlist, handle) { diff --git a/fs/smb/server/transport_rdma.c b/fs/smb/server/transport_rdma.c index a201c5871a77..7d86553fcc7c 100644 --- a/fs/smb/server/transport_rdma.c +++ b/fs/smb/server/transport_rdma.c @@ -219,6 +219,7 @@ static void smb_direct_disconnect_wake_up_all(struct smbdirect_socket *sc) * in order to notice the broken connection. */ wake_up_all(&sc->status_wait); + wake_up_all(&sc->send_io.lcredits.wait_queue); wake_up_all(&sc->send_io.credits.wait_queue); wake_up_all(&sc->send_io.pending.zero_wait_queue); wake_up_all(&sc->recv_io.reassembly.wait_queue); @@ -417,9 +418,6 @@ static struct smb_direct_transport *alloc_transport(struct rdma_cm_id *cm_id) sc->ib.dev = sc->rdma.cm_id->device; - INIT_WORK(&sc->recv_io.posted.refill_work, - smb_direct_post_recv_credits); - INIT_WORK(&sc->idle.immediate_work, smb_direct_send_immediate_work); INIT_DELAYED_WORK(&sc->idle.timer_work, smb_direct_idle_connection_timer); conn = ksmbd_conn_alloc(); @@ -450,11 +448,10 @@ static void free_transport(struct smb_direct_transport *t) struct smbdirect_recv_io *recvmsg; disable_work_sync(&sc->disconnect_work); - if (sc->status < SMBDIRECT_SOCKET_DISCONNECTING) { + if (sc->status < SMBDIRECT_SOCKET_DISCONNECTING) smb_direct_disconnect_rdma_work(&sc->disconnect_work); - wait_event_interruptible(sc->status_wait, - sc->status == SMBDIRECT_SOCKET_DISCONNECTED); - } + if (sc->status < SMBDIRECT_SOCKET_DISCONNECTED) + wait_event(sc->status_wait, sc->status == SMBDIRECT_SOCKET_DISCONNECTED); /* * Wake up all waiters in all wait queues @@ -469,9 +466,11 @@ static void free_transport(struct smb_direct_transport *t) disable_delayed_work_sync(&sc->idle.timer_work); disable_work_sync(&sc->idle.immediate_work); + if (sc->rdma.cm_id) + rdma_lock_handler(sc->rdma.cm_id); + if (sc->ib.qp) { ib_drain_qp(sc->ib.qp); - ib_mr_pool_destroy(sc->ib.qp, &sc->ib.qp->rdma_mrs); sc->ib.qp = NULL; rdma_destroy_qp(sc->rdma.cm_id); } @@ -498,8 +497,10 @@ static void free_transport(struct smb_direct_transport *t) ib_free_cq(sc->ib.recv_cq); if (sc->ib.pd) ib_dealloc_pd(sc->ib.pd); - if (sc->rdma.cm_id) + if (sc->rdma.cm_id) { + rdma_unlock_handler(sc->rdma.cm_id); rdma_destroy_id(sc->rdma.cm_id); + } smb_direct_destroy_pools(sc); ksmbd_conn_free(KSMBD_TRANS(t)->conn); @@ -524,6 +525,12 @@ static void smb_direct_free_sendmsg(struct smbdirect_socket *sc, { int i; + /* + * The list needs to be empty! + * The caller should take care of it. + */ + WARN_ON_ONCE(!list_empty(&msg->sibling_list)); + if (msg->num_sge > 0) { ib_dma_unmap_single(sc->ib.dev, msg->sge[0].addr, msg->sge[0].length, @@ -909,9 +916,9 @@ static void smb_direct_post_recv_credits(struct work_struct *work) static void send_done(struct ib_cq *cq, struct ib_wc *wc) { - struct smbdirect_send_io *sendmsg, *sibling; + struct smbdirect_send_io *sendmsg, *sibling, *next; struct smbdirect_socket *sc; - struct list_head *pos, *prev, *end; + int lcredits = 0; sendmsg = container_of(wc->wr_cqe, struct smbdirect_send_io, cqe); sc = sendmsg->socket; @@ -920,27 +927,31 @@ static void send_done(struct ib_cq *cq, struct ib_wc *wc) ib_wc_status_msg(wc->status), wc->status, wc->opcode); + /* + * Free possible siblings and then the main send_io + */ + list_for_each_entry_safe(sibling, next, &sendmsg->sibling_list, sibling_list) { + list_del_init(&sibling->sibling_list); + smb_direct_free_sendmsg(sc, sibling); + lcredits += 1; + } + /* Note this frees wc->wr_cqe, but not wc */ + smb_direct_free_sendmsg(sc, sendmsg); + lcredits += 1; + if (wc->status != IB_WC_SUCCESS || wc->opcode != IB_WC_SEND) { pr_err("Send error. status='%s (%d)', opcode=%d\n", ib_wc_status_msg(wc->status), wc->status, wc->opcode); smb_direct_disconnect_rdma_connection(sc); + return; } + atomic_add(lcredits, &sc->send_io.lcredits.count); + wake_up(&sc->send_io.lcredits.wait_queue); + if (atomic_dec_and_test(&sc->send_io.pending.count)) wake_up(&sc->send_io.pending.zero_wait_queue); - - /* iterate and free the list of messages in reverse. the list's head - * is invalid. - */ - for (pos = &sendmsg->sibling_list, prev = pos->prev, end = sendmsg->sibling_list.next; - prev != end; pos = prev, prev = prev->prev) { - sibling = container_of(pos, struct smbdirect_send_io, sibling_list); - smb_direct_free_sendmsg(sc, sibling); - } - - sibling = container_of(pos, struct smbdirect_send_io, sibling_list); - smb_direct_free_sendmsg(sc, sibling); } static int manage_credits_prior_sending(struct smbdirect_socket *sc) @@ -988,8 +999,6 @@ static int smb_direct_post_send(struct smbdirect_socket *sc, ret = ib_post_send(sc->ib.qp, wr, NULL); if (ret) { pr_err("failed to post send: %d\n", ret); - if (atomic_dec_and_test(&sc->send_io.pending.count)) - wake_up(&sc->send_io.pending.zero_wait_queue); smb_direct_disconnect_rdma_connection(sc); } return ret; @@ -1032,19 +1041,29 @@ static int smb_direct_flush_send_list(struct smbdirect_socket *sc, last->wr.send_flags = IB_SEND_SIGNALED; last->wr.wr_cqe = &last->cqe; + /* + * Remove last from send_ctx->msg_list + * and splice the rest of send_ctx->msg_list + * to last->sibling_list. + * + * send_ctx->msg_list is a valid empty list + * at the end. + */ + list_del_init(&last->sibling_list); + list_splice_tail_init(&send_ctx->msg_list, &last->sibling_list); + send_ctx->wr_cnt = 0; + ret = smb_direct_post_send(sc, &first->wr); - if (!ret) { - smb_direct_send_ctx_init(send_ctx, - send_ctx->need_invalidate_rkey, - send_ctx->remote_key); - } else { - atomic_add(send_ctx->wr_cnt, &sc->send_io.credits.count); - wake_up(&sc->send_io.credits.wait_queue); - list_for_each_entry_safe(first, last, &send_ctx->msg_list, - sibling_list) { - smb_direct_free_sendmsg(sc, first); + if (ret) { + struct smbdirect_send_io *sibling, *next; + + list_for_each_entry_safe(sibling, next, &last->sibling_list, sibling_list) { + list_del_init(&sibling->sibling_list); + smb_direct_free_sendmsg(sc, sibling); } + smb_direct_free_sendmsg(sc, last); } + return ret; } @@ -1070,6 +1089,23 @@ static int wait_for_credits(struct smbdirect_socket *sc, } while (true); } +static int wait_for_send_lcredit(struct smbdirect_socket *sc, + struct smbdirect_send_batch *send_ctx) +{ + if (send_ctx && (atomic_read(&sc->send_io.lcredits.count) <= 1)) { + int ret; + + ret = smb_direct_flush_send_list(sc, send_ctx, false); + if (ret) + return ret; + } + + return wait_for_credits(sc, + &sc->send_io.lcredits.wait_queue, + &sc->send_io.lcredits.count, + 1); +} + static int wait_for_send_credits(struct smbdirect_socket *sc, struct smbdirect_send_batch *send_ctx) { @@ -1257,9 +1293,13 @@ static int smb_direct_post_send_data(struct smbdirect_socket *sc, int data_length; struct scatterlist sg[SMBDIRECT_SEND_IO_MAX_SGE - 1]; + ret = wait_for_send_lcredit(sc, send_ctx); + if (ret) + goto lcredit_failed; + ret = wait_for_send_credits(sc, send_ctx); if (ret) - return ret; + goto credit_failed; data_length = 0; for (i = 0; i < niov; i++) @@ -1267,10 +1307,8 @@ static int smb_direct_post_send_data(struct smbdirect_socket *sc, ret = smb_direct_create_header(sc, data_length, remaining_data_length, &msg); - if (ret) { - atomic_inc(&sc->send_io.credits.count); - return ret; - } + if (ret) + goto header_failed; for (i = 0; i < niov; i++) { struct ib_sge *sge; @@ -1308,7 +1346,11 @@ static int smb_direct_post_send_data(struct smbdirect_socket *sc, return 0; err: smb_direct_free_sendmsg(sc, msg); +header_failed: atomic_inc(&sc->send_io.credits.count); +credit_failed: + atomic_inc(&sc->send_io.lcredits.count); +lcredit_failed: return ret; } @@ -1687,10 +1729,10 @@ static int smb_direct_cm_handler(struct rdma_cm_id *cm_id, } case RDMA_CM_EVENT_DEVICE_REMOVAL: case RDMA_CM_EVENT_DISCONNECTED: { - ib_drain_qp(sc->ib.qp); - sc->status = SMBDIRECT_SOCKET_DISCONNECTED; smb_direct_disconnect_rdma_work(&sc->disconnect_work); + if (sc->ib.qp) + ib_drain_qp(sc->ib.qp); break; } case RDMA_CM_EVENT_CONNECT_ERROR: { @@ -1864,27 +1906,17 @@ static int smb_direct_prepare_negotiation(struct smbdirect_socket *sc) goto out_err; } - smb_direct_post_recv_credits(&sc->recv_io.posted.refill_work); return 0; out_err: put_recvmsg(sc, recvmsg); return ret; } -static unsigned int smb_direct_get_max_fr_pages(struct smbdirect_socket *sc) -{ - return min_t(unsigned int, - sc->ib.dev->attrs.max_fast_reg_page_list_len, - 256); -} - -static int smb_direct_init_params(struct smbdirect_socket *sc, - struct ib_qp_cap *cap) +static int smb_direct_init_params(struct smbdirect_socket *sc) { struct smbdirect_socket_parameters *sp = &sc->parameters; - struct ib_device *device = sc->ib.dev; - int max_send_sges, max_rw_wrs, max_send_wrs; - unsigned int max_sge_per_wr, wrs_per_credit; + int max_send_sges; + unsigned int maxpages; /* need 3 more sge. because a SMB_DIRECT header, SMB2 header, * SMB2 response could be mapped. @@ -1895,67 +1927,20 @@ static int smb_direct_init_params(struct smbdirect_socket *sc, return -EINVAL; } - /* Calculate the number of work requests for RDMA R/W. - * The maximum number of pages which can be registered - * with one Memory region can be transferred with one - * R/W credit. And at least 4 work requests for each credit - * are needed for MR registration, RDMA R/W, local & remote - * MR invalidation. - */ - sc->rw_io.credits.num_pages = smb_direct_get_max_fr_pages(sc); - sc->rw_io.credits.max = DIV_ROUND_UP(sp->max_read_write_size, - (sc->rw_io.credits.num_pages - 1) * - PAGE_SIZE); - - max_sge_per_wr = min_t(unsigned int, device->attrs.max_send_sge, - device->attrs.max_sge_rd); - max_sge_per_wr = max_t(unsigned int, max_sge_per_wr, - max_send_sges); - wrs_per_credit = max_t(unsigned int, 4, - DIV_ROUND_UP(sc->rw_io.credits.num_pages, - max_sge_per_wr) + 1); - max_rw_wrs = sc->rw_io.credits.max * wrs_per_credit; - - max_send_wrs = sp->send_credit_target + max_rw_wrs; - if (max_send_wrs > device->attrs.max_cqe || - max_send_wrs > device->attrs.max_qp_wr) { - pr_err("consider lowering send_credit_target = %d\n", - sp->send_credit_target); - pr_err("Possible CQE overrun, device reporting max_cqe %d max_qp_wr %d\n", - device->attrs.max_cqe, device->attrs.max_qp_wr); - return -EINVAL; - } + atomic_set(&sc->send_io.lcredits.count, sp->send_credit_target); - if (sp->recv_credit_max > device->attrs.max_cqe || - sp->recv_credit_max > device->attrs.max_qp_wr) { - pr_err("consider lowering receive_credit_max = %d\n", - sp->recv_credit_max); - pr_err("Possible CQE overrun, device reporting max_cpe %d max_qp_wr %d\n", - device->attrs.max_cqe, device->attrs.max_qp_wr); - return -EINVAL; - } - - if (device->attrs.max_send_sge < SMBDIRECT_SEND_IO_MAX_SGE) { - pr_err("warning: device max_send_sge = %d too small\n", - device->attrs.max_send_sge); - return -EINVAL; - } - if (device->attrs.max_recv_sge < SMBDIRECT_RECV_IO_MAX_SGE) { - pr_err("warning: device max_recv_sge = %d too small\n", - device->attrs.max_recv_sge); - return -EINVAL; - } + maxpages = DIV_ROUND_UP(sp->max_read_write_size, PAGE_SIZE); + sc->rw_io.credits.max = rdma_rw_mr_factor(sc->ib.dev, + sc->rdma.cm_id->port_num, + maxpages); + sc->rw_io.credits.num_pages = DIV_ROUND_UP(maxpages, sc->rw_io.credits.max); + /* add one extra in order to handle unaligned pages */ + sc->rw_io.credits.max += 1; sc->recv_io.credits.target = 1; atomic_set(&sc->rw_io.credits.count, sc->rw_io.credits.max); - cap->max_send_wr = max_send_wrs; - cap->max_recv_wr = sp->recv_credit_max; - cap->max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; - cap->max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; - cap->max_inline_data = 0; - cap->max_rdma_ctxs = sc->rw_io.credits.max; return 0; } @@ -2029,13 +2014,129 @@ err: return -ENOMEM; } -static int smb_direct_create_qpair(struct smbdirect_socket *sc, - struct ib_qp_cap *cap) +static u32 smb_direct_rdma_rw_send_wrs(struct ib_device *dev, const struct ib_qp_init_attr *attr) +{ + /* + * This could be split out of rdma_rw_init_qp() + * and be a helper function next to rdma_rw_mr_factor() + * + * We can't check unlikely(rdma_rw_force_mr) here, + * but that is most likely 0 anyway. + */ + u32 factor; + + WARN_ON_ONCE(attr->port_num == 0); + + /* + * Each context needs at least one RDMA READ or WRITE WR. + * + * For some hardware we might need more, eventually we should ask the + * HCA driver for a multiplier here. + */ + factor = 1; + + /* + * If the device needs MRs to perform RDMA READ or WRITE operations, + * we'll need two additional MRs for the registrations and the + * invalidation. + */ + if (rdma_protocol_iwarp(dev, attr->port_num) || dev->attrs.max_sgl_rd) + factor += 2; /* inv + reg */ + + return factor * attr->cap.max_rdma_ctxs; +} + +static int smb_direct_create_qpair(struct smbdirect_socket *sc) { struct smbdirect_socket_parameters *sp = &sc->parameters; int ret; + struct ib_qp_cap qp_cap; struct ib_qp_init_attr qp_attr; - int pages_per_rw; + u32 max_send_wr; + u32 rdma_send_wr; + + /* + * Note that {rdma,ib}_create_qp() will call + * rdma_rw_init_qp() if cap->max_rdma_ctxs is not 0. + * It will adjust cap->max_send_wr to the required + * number of additional WRs for the RDMA RW operations. + * It will cap cap->max_send_wr to the device limit. + * + * +1 for ib_drain_qp + */ + qp_cap.max_send_wr = sp->send_credit_target + 1; + qp_cap.max_recv_wr = sp->recv_credit_max + 1; + qp_cap.max_send_sge = SMBDIRECT_SEND_IO_MAX_SGE; + qp_cap.max_recv_sge = SMBDIRECT_RECV_IO_MAX_SGE; + qp_cap.max_inline_data = 0; + qp_cap.max_rdma_ctxs = sc->rw_io.credits.max; + + /* + * Find out the number of max_send_wr + * after rdma_rw_init_qp() adjusted it. + * + * We only do it on a temporary variable, + * as rdma_create_qp() will trigger + * rdma_rw_init_qp() again. + */ + memset(&qp_attr, 0, sizeof(qp_attr)); + qp_attr.cap = qp_cap; + qp_attr.port_num = sc->rdma.cm_id->port_num; + rdma_send_wr = smb_direct_rdma_rw_send_wrs(sc->ib.dev, &qp_attr); + max_send_wr = qp_cap.max_send_wr + rdma_send_wr; + + if (qp_cap.max_send_wr > sc->ib.dev->attrs.max_cqe || + qp_cap.max_send_wr > sc->ib.dev->attrs.max_qp_wr) { + pr_err("Possible CQE overrun: max_send_wr %d\n", + qp_cap.max_send_wr); + pr_err("device %.*s reporting max_cqe %d max_qp_wr %d\n", + IB_DEVICE_NAME_MAX, + sc->ib.dev->name, + sc->ib.dev->attrs.max_cqe, + sc->ib.dev->attrs.max_qp_wr); + pr_err("consider lowering send_credit_target = %d\n", + sp->send_credit_target); + return -EINVAL; + } + + if (qp_cap.max_rdma_ctxs && + (max_send_wr >= sc->ib.dev->attrs.max_cqe || + max_send_wr >= sc->ib.dev->attrs.max_qp_wr)) { + pr_err("Possible CQE overrun: rdma_send_wr %d + max_send_wr %d = %d\n", + rdma_send_wr, qp_cap.max_send_wr, max_send_wr); + pr_err("device %.*s reporting max_cqe %d max_qp_wr %d\n", + IB_DEVICE_NAME_MAX, + sc->ib.dev->name, + sc->ib.dev->attrs.max_cqe, + sc->ib.dev->attrs.max_qp_wr); + pr_err("consider lowering send_credit_target = %d, max_rdma_ctxs = %d\n", + sp->send_credit_target, qp_cap.max_rdma_ctxs); + return -EINVAL; + } + + if (qp_cap.max_recv_wr > sc->ib.dev->attrs.max_cqe || + qp_cap.max_recv_wr > sc->ib.dev->attrs.max_qp_wr) { + pr_err("Possible CQE overrun: max_recv_wr %d\n", + qp_cap.max_recv_wr); + pr_err("device %.*s reporting max_cqe %d max_qp_wr %d\n", + IB_DEVICE_NAME_MAX, + sc->ib.dev->name, + sc->ib.dev->attrs.max_cqe, + sc->ib.dev->attrs.max_qp_wr); + pr_err("consider lowering receive_credit_max = %d\n", + sp->recv_credit_max); + return -EINVAL; + } + + if (qp_cap.max_send_sge > sc->ib.dev->attrs.max_send_sge || + qp_cap.max_recv_sge > sc->ib.dev->attrs.max_recv_sge) { + pr_err("device %.*s max_send_sge/max_recv_sge = %d/%d too small\n", + IB_DEVICE_NAME_MAX, + sc->ib.dev->name, + sc->ib.dev->attrs.max_send_sge, + sc->ib.dev->attrs.max_recv_sge); + return -EINVAL; + } sc->ib.pd = ib_alloc_pd(sc->ib.dev, 0); if (IS_ERR(sc->ib.pd)) { @@ -2046,8 +2147,7 @@ static int smb_direct_create_qpair(struct smbdirect_socket *sc, } sc->ib.send_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->send_credit_target + - cap->max_rdma_ctxs, + max_send_wr, IB_POLL_WORKQUEUE); if (IS_ERR(sc->ib.send_cq)) { pr_err("Can't create RDMA send CQ\n"); @@ -2057,7 +2157,7 @@ static int smb_direct_create_qpair(struct smbdirect_socket *sc, } sc->ib.recv_cq = ib_alloc_cq_any(sc->ib.dev, sc, - sp->recv_credit_max, + qp_cap.max_recv_wr, IB_POLL_WORKQUEUE); if (IS_ERR(sc->ib.recv_cq)) { pr_err("Can't create RDMA recv CQ\n"); @@ -2066,10 +2166,18 @@ static int smb_direct_create_qpair(struct smbdirect_socket *sc, goto err; } + /* + * We reset completely here! + * As the above use was just temporary + * to calc max_send_wr and rdma_send_wr. + * + * rdma_create_qp() will trigger rdma_rw_init_qp() + * again if max_rdma_ctxs is not 0. + */ memset(&qp_attr, 0, sizeof(qp_attr)); qp_attr.event_handler = smb_direct_qpair_handler; qp_attr.qp_context = sc; - qp_attr.cap = *cap; + qp_attr.cap = qp_cap; qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR; qp_attr.qp_type = IB_QPT_RC; qp_attr.send_cq = sc->ib.send_cq; @@ -2085,18 +2193,6 @@ static int smb_direct_create_qpair(struct smbdirect_socket *sc, sc->ib.qp = sc->rdma.cm_id->qp; sc->rdma.cm_id->event_handler = smb_direct_cm_handler; - pages_per_rw = DIV_ROUND_UP(sp->max_read_write_size, PAGE_SIZE) + 1; - if (pages_per_rw > sc->ib.dev->attrs.max_sgl_rd) { - ret = ib_mr_pool_init(sc->ib.qp, &sc->ib.qp->rdma_mrs, - sc->rw_io.credits.max, IB_MR_TYPE_MEM_REG, - sc->rw_io.credits.num_pages, 0); - if (ret) { - pr_err("failed to init mr pool count %zu pages %zu\n", - sc->rw_io.credits.max, sc->rw_io.credits.num_pages); - goto err; - } - } - return 0; err: if (sc->ib.qp) { @@ -2154,8 +2250,8 @@ static int smb_direct_prepare(struct ksmbd_transport *t) return -ECONNABORTED; ret = smb_direct_check_recvmsg(recvmsg); - if (ret == -ECONNABORTED) - goto out; + if (ret) + goto put; req = (struct smbdirect_negotiate_req *)recvmsg->packet; sp->max_recv_size = min_t(int, sp->max_recv_size, @@ -2170,23 +2266,46 @@ static int smb_direct_prepare(struct ksmbd_transport *t) sc->recv_io.credits.target = min_t(u16, sc->recv_io.credits.target, sp->recv_credit_max); sc->recv_io.credits.target = max_t(u16, sc->recv_io.credits.target, 1); - ret = smb_direct_send_negotiate_response(sc, ret); -out: +put: spin_lock_irqsave(&sc->recv_io.reassembly.lock, flags); sc->recv_io.reassembly.queue_length--; list_del(&recvmsg->list); spin_unlock_irqrestore(&sc->recv_io.reassembly.lock, flags); put_recvmsg(sc, recvmsg); + if (ret == -ECONNABORTED) + return ret; + + if (ret) + goto respond; + + /* + * We negotiated with success, so we need to refill the recv queue. + * We do that with sc->idle.immediate_work still being disabled + * via smbdirect_socket_init(), so that queue_work(sc->workqueue, + * &sc->idle.immediate_work) in smb_direct_post_recv_credits() + * is a no-op. + * + * The message that grants the credits to the client is + * the negotiate response. + */ + INIT_WORK(&sc->recv_io.posted.refill_work, smb_direct_post_recv_credits); + smb_direct_post_recv_credits(&sc->recv_io.posted.refill_work); + if (unlikely(sc->first_error)) + return sc->first_error; + INIT_WORK(&sc->idle.immediate_work, smb_direct_send_immediate_work); + +respond: + ret = smb_direct_send_negotiate_response(sc, ret); + return ret; } static int smb_direct_connect(struct smbdirect_socket *sc) { - struct ib_qp_cap qp_cap; int ret; - ret = smb_direct_init_params(sc, &qp_cap); + ret = smb_direct_init_params(sc); if (ret) { pr_err("Can't configure RDMA parameters\n"); return ret; @@ -2198,7 +2317,7 @@ static int smb_direct_connect(struct smbdirect_socket *sc) return ret; } - ret = smb_direct_create_qpair(sc, &qp_cap); + ret = smb_direct_create_qpair(sc); if (ret) { pr_err("Can't accept RDMA client: %d\n", ret); return ret; diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c index 2d78e94072a0..e142bac4f9f8 100644 --- a/fs/sysfs/group.c +++ b/fs/sysfs/group.c @@ -498,17 +498,26 @@ int compat_only_sysfs_link_entry_to_kobj(struct kobject *kobj, } EXPORT_SYMBOL_GPL(compat_only_sysfs_link_entry_to_kobj); -static int sysfs_group_attrs_change_owner(struct kernfs_node *grp_kn, +static int sysfs_group_attrs_change_owner(struct kobject *kobj, + struct kernfs_node *grp_kn, const struct attribute_group *grp, struct iattr *newattrs) { struct kernfs_node *kn; - int error; + int error, i; + umode_t mode; if (grp->attrs) { struct attribute *const *attr; - for (attr = grp->attrs; *attr; attr++) { + for (i = 0, attr = grp->attrs; *attr; i++, attr++) { + if (grp->is_visible) { + mode = grp->is_visible(kobj, *attr, i); + if (mode & SYSFS_GROUP_INVISIBLE) + break; + if (!mode) + continue; + } kn = kernfs_find_and_get(grp_kn, (*attr)->name); if (!kn) return -ENOENT; @@ -523,7 +532,14 @@ static int sysfs_group_attrs_change_owner(struct kernfs_node *grp_kn, if (grp->bin_attrs) { const struct bin_attribute *const *bin_attr; - for (bin_attr = grp->bin_attrs; *bin_attr; bin_attr++) { + for (i = 0, bin_attr = grp->bin_attrs; *bin_attr; i++, bin_attr++) { + if (grp->is_bin_visible) { + mode = grp->is_bin_visible(kobj, *bin_attr, i); + if (mode & SYSFS_GROUP_INVISIBLE) + break; + if (!mode) + continue; + } kn = kernfs_find_and_get(grp_kn, (*bin_attr)->attr.name); if (!kn) return -ENOENT; @@ -573,7 +589,7 @@ int sysfs_group_change_owner(struct kobject *kobj, error = kernfs_setattr(grp_kn, &newattrs); if (!error) - error = sysfs_group_attrs_change_owner(grp_kn, grp, &newattrs); + error = sysfs_group_attrs_change_owner(kobj, grp_kn, grp, &newattrs); kernfs_put(grp_kn); diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig index 8930d5254e1d..b99da294e9a3 100644 --- a/fs/xfs/Kconfig +++ b/fs/xfs/Kconfig @@ -119,6 +119,15 @@ config XFS_RT See the xfs man page in section 5 for additional information. + This option is mandatory to support zoned block devices. For these + devices, the realtime subvolume must be backed by a zoned block + device and a regular block device used as the main device (for + metadata). If the zoned block device is a host-managed SMR hard-disk + containing conventional zones at the beginning of its address space, + XFS will use the disk conventional zones as the main device and the + remaining sequential write required zones as the backing storage for + the realtime subvolume. + If unsure, say N. config XFS_DRAIN_INTENTS @@ -156,7 +165,7 @@ config XFS_ONLINE_SCRUB_STATS bool "XFS online metadata check usage data collection" default y depends on XFS_ONLINE_SCRUB - select DEBUG_FS + depends on DEBUG_FS help If you say Y here, the kernel will gather usage data about the online metadata check subsystem. This includes the number diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h index d36a6ae0abe5..d4fcf591e63d 100644 --- a/fs/xfs/libxfs/xfs_rtgroup.h +++ b/fs/xfs/libxfs/xfs_rtgroup.h @@ -50,6 +50,12 @@ struct xfs_rtgroup { uint8_t *rtg_rsum_cache; struct xfs_open_zone *rtg_open_zone; }; + + /* + * Count of outstanding GC operations for zoned XFS. Any RTG with a + * non-zero rtg_gccount will not be picked as new GC victim. + */ + atomic_t rtg_gccount; }; /* diff --git a/fs/xfs/scrub/nlinks.c b/fs/xfs/scrub/nlinks.c index 26721fab5cab..091c79e432e5 100644 --- a/fs/xfs/scrub/nlinks.c +++ b/fs/xfs/scrub/nlinks.c @@ -376,6 +376,36 @@ out_incomplete: return error; } +static uint +xchk_nlinks_ilock_dir( + struct xfs_inode *ip) +{ + uint lock_mode = XFS_ILOCK_SHARED; + + /* + * We're going to scan the directory entries, so we must be ready to + * pull the data fork mappings into memory if they aren't already. + */ + if (xfs_need_iread_extents(&ip->i_df)) + lock_mode = XFS_ILOCK_EXCL; + + /* + * We're going to scan the parent pointers, so we must be ready to + * pull the attr fork mappings into memory if they aren't already. + */ + if (xfs_has_parent(ip->i_mount) && xfs_inode_has_attr_fork(ip) && + xfs_need_iread_extents(&ip->i_af)) + lock_mode = XFS_ILOCK_EXCL; + + /* + * Take the IOLOCK so that other threads cannot start a directory + * update while we're scanning. + */ + lock_mode |= XFS_IOLOCK_SHARED; + xfs_ilock(ip, lock_mode); + return lock_mode; +} + /* Walk a directory to bump the observed link counts of the children. */ STATIC int xchk_nlinks_collect_dir( @@ -394,8 +424,7 @@ xchk_nlinks_collect_dir( return 0; /* Prevent anyone from changing this directory while we walk it. */ - xfs_ilock(dp, XFS_IOLOCK_SHARED); - lock_mode = xfs_ilock_data_map_shared(dp); + lock_mode = xchk_nlinks_ilock_dir(dp); /* * The dotdot entry of an unlinked directory still points to the last @@ -452,7 +481,6 @@ out_abort: xchk_iscan_abort(&xnc->collect_iscan); out_unlock: xfs_iunlock(dp, lock_mode); - xfs_iunlock(dp, XFS_IOLOCK_SHARED); return error; } diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c index 773d959965dc..47edf3041631 100644 --- a/fs/xfs/xfs_buf.c +++ b/fs/xfs/xfs_buf.c @@ -1751,7 +1751,7 @@ xfs_init_buftarg( const char *descr) { /* The maximum size of the buftarg is only known once the sb is read. */ - btp->bt_nr_sectors = (xfs_daddr_t)-1; + btp->bt_nr_sectors = XFS_BUF_DADDR_MAX; /* Set up device logical sector size mask */ btp->bt_logical_sectorsize = logical_sectorsize; diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index 8fa7bdf59c91..e25cd2a160f3 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -22,6 +22,7 @@ extern struct kmem_cache *xfs_buf_cache; */ struct xfs_buf; +#define XFS_BUF_DADDR_MAX ((xfs_daddr_t) S64_MAX) #define XFS_BUF_DADDR_NULL ((xfs_daddr_t) (-1LL)) #define XBF_READ (1u << 0) /* buffer intended for reading from device */ diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index f046d1215b04..b871dfde372b 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -236,7 +236,6 @@ typedef struct xfs_mount { bool m_update_sb; /* sb needs update in mount */ unsigned int m_max_open_zones; unsigned int m_zonegc_low_space; - struct xfs_mru_cache *m_zone_cache; /* Inode to open zone cache */ /* max_atomic_write mount option value */ unsigned long long m_awu_max_bytes; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index e85a156dc17d..1067ebb3b001 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -102,7 +102,7 @@ static const struct constant_table dax_param_enums[] = { * Table driven mount option parser. */ enum { - Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev, + Op_deprecated, Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev, Opt_wsync, Opt_noalign, Opt_swalloc, Opt_sunit, Opt_swidth, Opt_nouuid, Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups, Opt_allocsize, Opt_norecovery, Opt_inode64, Opt_inode32, @@ -114,7 +114,21 @@ enum { Opt_lifetime, Opt_nolifetime, Opt_max_atomic_write, }; +#define fsparam_dead(NAME) \ + __fsparam(NULL, (NAME), Op_deprecated, fs_param_deprecated, NULL) + static const struct fs_parameter_spec xfs_fs_parameters[] = { + /* + * These mount options were supposed to be deprecated in September 2025 + * but the deprecation warning was buggy, so not all users were + * notified. The deprecation is now obnoxiously loud and postponed to + * September 2030. + */ + fsparam_dead("attr2"), + fsparam_dead("noattr2"), + fsparam_dead("ikeep"), + fsparam_dead("noikeep"), + fsparam_u32("logbufs", Opt_logbufs), fsparam_string("logbsize", Opt_logbsize), fsparam_string("logdev", Opt_logdev), @@ -786,6 +800,12 @@ xfs_fs_evict_inode( truncate_inode_pages_final(&inode->i_data); clear_inode(inode); + + if (IS_ENABLED(CONFIG_XFS_RT) && + S_ISREG(inode->i_mode) && inode->i_private) { + xfs_open_zone_put(inode->i_private); + inode->i_private = NULL; + } } static void @@ -1373,16 +1393,25 @@ suffix_kstrtoull( static inline void xfs_fs_warn_deprecated( struct fs_context *fc, - struct fs_parameter *param, - uint64_t flag, - bool value) + struct fs_parameter *param) { - /* Don't print the warning if reconfiguring and current mount point - * already had the flag set + /* + * Always warn about someone passing in a deprecated mount option. + * Previously we wouldn't print the warning if we were reconfiguring + * and current mount point already had the flag set, but that was not + * the right thing to do. + * + * Many distributions mount the root filesystem with no options in the + * initramfs and rely on mount -a to remount the root fs with the + * options in fstab. However, the old behavior meant that there would + * never be a warning about deprecated mount options for the root fs in + * /etc/fstab. On a single-fs system, that means no warning at all. + * + * Compounding this problem are distribution scripts that copy + * /proc/mounts to fstab, which means that we can't remove mount + * options unless we're 100% sure they have only ever been advertised + * in /proc/mounts in response to explicitly provided mount options. */ - if ((fc->purpose & FS_CONTEXT_FOR_RECONFIGURE) && - !!(XFS_M(fc->root->d_sb)->m_features & flag) == value) - return; xfs_warn(fc->s_fs_info, "%s mount option is deprecated.", param->key); } @@ -1408,6 +1437,9 @@ xfs_fs_parse_param( return opt; switch (opt) { + case Op_deprecated: + xfs_fs_warn_deprecated(fc, param); + return 0; case Opt_logbufs: parsing_mp->m_logbufs = result.uint_32; return 0; @@ -1528,7 +1560,6 @@ xfs_fs_parse_param( xfs_mount_set_dax_mode(parsing_mp, result.uint_32); return 0; #endif - /* Following mount options will be removed in September 2025 */ case Opt_max_open_zones: parsing_mp->m_max_open_zones = result.uint_32; return 0; @@ -2221,7 +2252,7 @@ xfs_init_fs_context( struct xfs_mount *mp; int i; - mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL | __GFP_NOFAIL); + mp = kzalloc(sizeof(struct xfs_mount), GFP_KERNEL); if (!mp) return -ENOMEM; diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c index 1147bacb2da8..040402240807 100644 --- a/fs/xfs/xfs_zone_alloc.c +++ b/fs/xfs/xfs_zone_alloc.c @@ -26,14 +26,22 @@ #include "xfs_trace.h" #include "xfs_mru_cache.h" +static void +xfs_open_zone_free_rcu( + struct callback_head *cb) +{ + struct xfs_open_zone *oz = container_of(cb, typeof(*oz), oz_rcu); + + xfs_rtgroup_rele(oz->oz_rtg); + kfree(oz); +} + void xfs_open_zone_put( struct xfs_open_zone *oz) { - if (atomic_dec_and_test(&oz->oz_ref)) { - xfs_rtgroup_rele(oz->oz_rtg); - kfree(oz); - } + if (atomic_dec_and_test(&oz->oz_ref)) + call_rcu(&oz->oz_rcu, xfs_open_zone_free_rcu); } static inline uint32_t @@ -238,6 +246,14 @@ xfs_zoned_map_extent( * If a data write raced with this GC write, keep the existing data in * the data fork, mark our newly written GC extent as reclaimable, then * move on to the next extent. + * + * Note that this can also happen when racing with operations that do + * not actually invalidate the data, but just move it to a different + * inode (XFS_IOC_EXCHANGE_RANGE), or to a different offset inside the + * inode (FALLOC_FL_COLLAPSE_RANGE / FALLOC_FL_INSERT_RANGE). If the + * data was just moved around, GC fails to free the zone, but the zone + * becomes a GC candidate again as soon as all previous GC I/O has + * finished and these blocks will be moved out eventually. */ if (old_startblock != NULLFSBLOCK && old_startblock != data.br_startblock) @@ -614,14 +630,25 @@ static inline enum rw_hint xfs_inode_write_hint(struct xfs_inode *ip) } /* - * Try to pack inodes that are written back after they were closed tight instead - * of trying to open new zones for them or spread them to the least recently - * used zone. This optimizes the data layout for workloads that untar or copy - * a lot of small files. Right now this does not separate multiple such + * Try to tightly pack small files that are written back after they were closed + * instead of trying to open new zones for them or spread them to the least + * recently used zone. This optimizes the data layout for workloads that untar + * or copy a lot of small files. Right now this does not separate multiple such * streams. */ static inline bool xfs_zoned_pack_tight(struct xfs_inode *ip) { + struct xfs_mount *mp = ip->i_mount; + size_t zone_capacity = + XFS_FSB_TO_B(mp, mp->m_groups[XG_TYPE_RTG].blocks); + + /* + * Do not pack write files that are already using a full zone to avoid + * fragmentation. + */ + if (i_size_read(VFS_I(ip)) >= zone_capacity) + return false; + return !inode_is_open_for_write(VFS_I(ip)) && !(ip->i_diflags & XFS_DIFLAG_APPEND); } @@ -746,97 +773,54 @@ xfs_mark_rtg_boundary( } /* - * Cache the last zone written to for an inode so that it is considered first - * for subsequent writes. - */ -struct xfs_zone_cache_item { - struct xfs_mru_cache_elem mru; - struct xfs_open_zone *oz; -}; - -static inline struct xfs_zone_cache_item * -xfs_zone_cache_item(struct xfs_mru_cache_elem *mru) -{ - return container_of(mru, struct xfs_zone_cache_item, mru); -} - -static void -xfs_zone_cache_free_func( - void *data, - struct xfs_mru_cache_elem *mru) -{ - struct xfs_zone_cache_item *item = xfs_zone_cache_item(mru); - - xfs_open_zone_put(item->oz); - kfree(item); -} - -/* * Check if we have a cached last open zone available for the inode and * if yes return a reference to it. */ static struct xfs_open_zone * -xfs_cached_zone( - struct xfs_mount *mp, - struct xfs_inode *ip) +xfs_get_cached_zone( + struct xfs_inode *ip) { - struct xfs_mru_cache_elem *mru; - struct xfs_open_zone *oz; + struct xfs_open_zone *oz; - mru = xfs_mru_cache_lookup(mp->m_zone_cache, ip->i_ino); - if (!mru) - return NULL; - oz = xfs_zone_cache_item(mru)->oz; + rcu_read_lock(); + oz = VFS_I(ip)->i_private; if (oz) { /* * GC only steals open zones at mount time, so no GC zones * should end up in the cache. */ ASSERT(!oz->oz_is_gc); - ASSERT(atomic_read(&oz->oz_ref) > 0); - atomic_inc(&oz->oz_ref); + if (!atomic_inc_not_zero(&oz->oz_ref)) + oz = NULL; } - xfs_mru_cache_done(mp->m_zone_cache); + rcu_read_unlock(); + return oz; } /* - * Update the last used zone cache for a given inode. + * Stash our zone in the inode so that is is reused for future allocations. * - * The caller must have a reference on the open zone. + * The open_zone structure will be pinned until either the inode is freed or + * until the cached open zone is replaced with a different one because the + * current one was full when we tried to use it. This means we keep any + * open zone around forever as long as any inode that used it for the last + * write is cached, which slightly increases the memory use of cached inodes + * that were every written to, but significantly simplifies the cached zone + * lookup. Because the open_zone is clearly marked as full when all data + * in the underlying RTG was written, the caching is always safe. */ static void -xfs_zone_cache_create_association( - struct xfs_inode *ip, - struct xfs_open_zone *oz) +xfs_set_cached_zone( + struct xfs_inode *ip, + struct xfs_open_zone *oz) { - struct xfs_mount *mp = ip->i_mount; - struct xfs_zone_cache_item *item = NULL; - struct xfs_mru_cache_elem *mru; + struct xfs_open_zone *old_oz; - ASSERT(atomic_read(&oz->oz_ref) > 0); atomic_inc(&oz->oz_ref); - - mru = xfs_mru_cache_lookup(mp->m_zone_cache, ip->i_ino); - if (mru) { - /* - * If we have an association already, update it to point to the - * new zone. - */ - item = xfs_zone_cache_item(mru); - xfs_open_zone_put(item->oz); - item->oz = oz; - xfs_mru_cache_done(mp->m_zone_cache); - return; - } - - item = kmalloc(sizeof(*item), GFP_KERNEL); - if (!item) { - xfs_open_zone_put(oz); - return; - } - item->oz = oz; - xfs_mru_cache_insert(mp->m_zone_cache, ip->i_ino, &item->mru); + old_oz = xchg(&VFS_I(ip)->i_private, oz); + if (old_oz) + xfs_open_zone_put(old_oz); } static void @@ -880,15 +864,14 @@ xfs_zone_alloc_and_submit( * the inode is still associated with a zone and use that if so. */ if (!*oz) - *oz = xfs_cached_zone(mp, ip); + *oz = xfs_get_cached_zone(ip); if (!*oz) { select_zone: *oz = xfs_select_zone(mp, write_hint, pack_tight); if (!*oz) goto out_error; - - xfs_zone_cache_create_association(ip, *oz); + xfs_set_cached_zone(ip, *oz); } alloc_len = xfs_zone_alloc_blocks(*oz, XFS_B_TO_FSB(mp, ioend->io_size), @@ -966,6 +949,12 @@ xfs_free_open_zones( xfs_open_zone_put(oz); } spin_unlock(&zi->zi_open_zones_lock); + + /* + * Wait for all open zones to be freed so that they drop the group + * references: + */ + rcu_barrier(); } struct xfs_init_zones { @@ -1279,14 +1268,6 @@ xfs_mount_zones( error = xfs_zone_gc_mount(mp); if (error) goto out_free_zone_info; - - /* - * Set up a mru cache to track inode to open zone for data placement - * purposes. The magic values for group count and life time is the - * same as the defaults for file streams, which seems sane enough. - */ - xfs_mru_cache_create(&mp->m_zone_cache, mp, - 5000, 10, xfs_zone_cache_free_func); return 0; out_free_zone_info: @@ -1300,5 +1281,4 @@ xfs_unmount_zones( { xfs_zone_gc_unmount(mp); xfs_free_zone_info(mp->m_zone_info); - xfs_mru_cache_destroy(mp->m_zone_cache); } diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c index 064cd1a857a0..4ade54445532 100644 --- a/fs/xfs/xfs_zone_gc.c +++ b/fs/xfs/xfs_zone_gc.c @@ -114,6 +114,8 @@ struct xfs_gc_bio { /* Open Zone being written to */ struct xfs_open_zone *oz; + struct xfs_rtgroup *victim_rtg; + /* Bio used for reads and writes, including the bvec used by it */ struct bio_vec bv; struct bio bio; /* must be last */ @@ -264,6 +266,7 @@ xfs_zone_gc_iter_init( iter->rec_count = 0; iter->rec_idx = 0; iter->victim_rtg = victim_rtg; + atomic_inc(&victim_rtg->rtg_gccount); } /* @@ -362,6 +365,7 @@ xfs_zone_gc_query( return 0; done: + atomic_dec(&iter->victim_rtg->rtg_gccount); xfs_rtgroup_rele(iter->victim_rtg); iter->victim_rtg = NULL; return 0; @@ -451,6 +455,20 @@ xfs_zone_gc_pick_victim_from( if (!rtg) continue; + /* + * If the zone is already undergoing GC, don't pick it again. + * + * This prevents us from picking one of the zones for which we + * already submitted GC I/O, but for which the remapping hasn't + * concluded yet. This won't cause data corruption, but + * increases write amplification and slows down GC, so this is + * a bad thing. + */ + if (atomic_read(&rtg->rtg_gccount)) { + xfs_rtgroup_rele(rtg); + continue; + } + /* skip zones that are just waiting for a reset */ if (rtg_rmap(rtg)->i_used_blocks == 0 || rtg_rmap(rtg)->i_used_blocks >= victim_used) { @@ -491,21 +509,6 @@ xfs_zone_gc_select_victim( struct xfs_rtgroup *victim_rtg = NULL; unsigned int bucket; - if (xfs_is_shutdown(mp)) - return false; - - if (iter->victim_rtg) - return true; - - /* - * Don't start new work if we are asked to stop or park. - */ - if (kthread_should_stop() || kthread_should_park()) - return false; - - if (!xfs_zoned_need_gc(mp)) - return false; - spin_lock(&zi->zi_used_buckets_lock); for (bucket = 0; bucket < XFS_ZONE_USED_BUCKETS; bucket++) { victim_rtg = xfs_zone_gc_pick_victim_from(mp, bucket); @@ -703,6 +706,9 @@ xfs_zone_gc_start_chunk( chunk->scratch = &data->scratch[data->scratch_idx]; chunk->data = data; chunk->oz = oz; + chunk->victim_rtg = iter->victim_rtg; + atomic_inc(&chunk->victim_rtg->rtg_group.xg_active_ref); + atomic_inc(&chunk->victim_rtg->rtg_gccount); bio->bi_iter.bi_sector = xfs_rtb_to_daddr(mp, chunk->old_startblock); bio->bi_end_io = xfs_zone_gc_end_io; @@ -725,6 +731,8 @@ static void xfs_zone_gc_free_chunk( struct xfs_gc_bio *chunk) { + atomic_dec(&chunk->victim_rtg->rtg_gccount); + xfs_rtgroup_rele(chunk->victim_rtg); list_del(&chunk->entry); xfs_open_zone_put(chunk->oz); xfs_irele(chunk->ip); @@ -785,6 +793,10 @@ xfs_zone_gc_split_write( split_chunk->oz = chunk->oz; atomic_inc(&chunk->oz->oz_ref); + split_chunk->victim_rtg = chunk->victim_rtg; + atomic_inc(&chunk->victim_rtg->rtg_group.xg_active_ref); + atomic_inc(&chunk->victim_rtg->rtg_gccount); + chunk->offset += split_len; chunk->len -= split_len; chunk->old_startblock += XFS_B_TO_FSB(data->mp, split_len); @@ -975,6 +987,27 @@ xfs_zone_gc_reset_zones( } while (next); } +static bool +xfs_zone_gc_should_start_new_work( + struct xfs_zone_gc_data *data) +{ + if (xfs_is_shutdown(data->mp)) + return false; + if (!xfs_zone_gc_space_available(data)) + return false; + + if (!data->iter.victim_rtg) { + if (kthread_should_stop() || kthread_should_park()) + return false; + if (!xfs_zoned_need_gc(data->mp)) + return false; + if (!xfs_zone_gc_select_victim(data)) + return false; + } + + return true; +} + /* * Handle the work to read and write data for GC and to reset the zones, * including handling all completions. @@ -982,7 +1015,7 @@ xfs_zone_gc_reset_zones( * Note that the order of the chunks is preserved so that we don't undo the * optimal order established by xfs_zone_gc_query(). */ -static bool +static void xfs_zone_gc_handle_work( struct xfs_zone_gc_data *data) { @@ -996,30 +1029,22 @@ xfs_zone_gc_handle_work( zi->zi_reset_list = NULL; spin_unlock(&zi->zi_reset_list_lock); - if (!xfs_zone_gc_select_victim(data) || - !xfs_zone_gc_space_available(data)) { - if (list_empty(&data->reading) && - list_empty(&data->writing) && - list_empty(&data->resetting) && - !reset_list) - return false; - } - - __set_current_state(TASK_RUNNING); - try_to_freeze(); - - if (reset_list) + if (reset_list) { + set_current_state(TASK_RUNNING); xfs_zone_gc_reset_zones(data, reset_list); + } list_for_each_entry_safe(chunk, next, &data->resetting, entry) { if (READ_ONCE(chunk->state) != XFS_GC_BIO_DONE) break; + set_current_state(TASK_RUNNING); xfs_zone_gc_finish_reset(chunk); } list_for_each_entry_safe(chunk, next, &data->writing, entry) { if (READ_ONCE(chunk->state) != XFS_GC_BIO_DONE) break; + set_current_state(TASK_RUNNING); xfs_zone_gc_finish_chunk(chunk); } @@ -1027,15 +1052,18 @@ xfs_zone_gc_handle_work( list_for_each_entry_safe(chunk, next, &data->reading, entry) { if (READ_ONCE(chunk->state) != XFS_GC_BIO_DONE) break; + set_current_state(TASK_RUNNING); xfs_zone_gc_write_chunk(chunk); } blk_finish_plug(&plug); - blk_start_plug(&plug); - while (xfs_zone_gc_start_chunk(data)) - ; - blk_finish_plug(&plug); - return true; + if (xfs_zone_gc_should_start_new_work(data)) { + set_current_state(TASK_RUNNING); + blk_start_plug(&plug); + while (xfs_zone_gc_start_chunk(data)) + ; + blk_finish_plug(&plug); + } } /* @@ -1059,8 +1087,18 @@ xfs_zoned_gcd( for (;;) { set_current_state(TASK_INTERRUPTIBLE | TASK_FREEZABLE); xfs_set_zonegc_running(mp); - if (xfs_zone_gc_handle_work(data)) + + xfs_zone_gc_handle_work(data); + + /* + * Only sleep if nothing set the state to running. Else check for + * work again as someone might have queued up more work and woken + * us in the meantime. + */ + if (get_current_state() == TASK_RUNNING) { + try_to_freeze(); continue; + } if (list_empty(&data->reading) && list_empty(&data->writing) && diff --git a/fs/xfs/xfs_zone_priv.h b/fs/xfs/xfs_zone_priv.h index 35e6de3d25ed..4322e26dd99a 100644 --- a/fs/xfs/xfs_zone_priv.h +++ b/fs/xfs/xfs_zone_priv.h @@ -44,6 +44,8 @@ struct xfs_open_zone { * the life time of an open zone. */ struct xfs_rtgroup *oz_rtg; + + struct rcu_head oz_rcu; }; /* |