diff options
Diffstat (limited to 'fs')
53 files changed, 459 insertions, 274 deletions
diff --git a/fs/afs/write.c b/fs/afs/write.c index 6bcf1475511b..4763132ca57e 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -616,8 +616,7 @@ static ssize_t afs_write_back_from_locked_folio(struct address_space *mapping, _debug("write discard %x @%llx [%llx]", len, start, i_size); /* The dirty region was entirely beyond the EOF. */ - fscache_clear_page_bits(afs_vnode_cache(vnode), - mapping, start, len, caching); + fscache_clear_page_bits(mapping, start, len, caching); afs_pages_written_back(vnode, start, len); ret = 0; } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 6556e13ed95f..63c7ebb0da89 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -1117,11 +1117,11 @@ out_free_interp: * independently randomized mmap region (0 load_bias * without MAP_FIXED nor MAP_FIXED_NOREPLACE). */ - alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum); - if (interpreter || alignment > ELF_MIN_ALIGN) { + if (interpreter) { load_bias = ELF_ET_DYN_BASE; if (current->flags & PF_RANDOMIZE) load_bias += arch_mmap_rnd(); + alignment = maximum_alignment(elf_phdata, elf_ex->e_phnum); if (alignment) load_bias &= ~(alignment - 1); elf_flags |= MAP_FIXED_NOREPLACE; diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index c22d287e020b..0dd6de994199 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -2503,12 +2503,6 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran return ERR_PTR(ret); } - /* - * New block group is likely to be used soon. Try to activate it now. - * Failure is OK for now. - */ - btrfs_zone_activate(cache); - ret = exclude_super_stripes(cache); if (ret) { /* We may have excluded something, so call this just in case */ @@ -2946,7 +2940,6 @@ int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans) struct btrfs_path *path = NULL; LIST_HEAD(dirty); struct list_head *io = &cur_trans->io_bgs; - int num_started = 0; int loops = 0; spin_lock(&cur_trans->dirty_bgs_lock); @@ -3012,7 +3005,6 @@ again: cache->io_ctl.inode = NULL; ret = btrfs_write_out_cache(trans, cache, path); if (ret == 0 && cache->io_ctl.inode) { - num_started++; should_put = 0; /* @@ -3113,7 +3105,6 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) int should_put; struct btrfs_path *path; struct list_head *io = &cur_trans->io_bgs; - int num_started = 0; path = btrfs_alloc_path(); if (!path) @@ -3171,7 +3162,6 @@ int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans) cache->io_ctl.inode = NULL; ret = btrfs_write_out_cache(trans, cache, path); if (ret == 0 && cache->io_ctl.inode) { - num_started++; should_put = 0; list_add_tail(&cache->io_list, io); } else { @@ -3455,7 +3445,7 @@ int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type) return btrfs_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE); } -static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) +static struct btrfs_block_group *do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) { struct btrfs_block_group *bg; int ret; @@ -3542,7 +3532,11 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags) out: btrfs_trans_release_chunk_metadata(trans); - return ret; + if (ret) + return ERR_PTR(ret); + + btrfs_get_block_group(bg); + return bg; } /* @@ -3657,10 +3651,17 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, { struct btrfs_fs_info *fs_info = trans->fs_info; struct btrfs_space_info *space_info; + struct btrfs_block_group *ret_bg; bool wait_for_alloc = false; bool should_alloc = false; + bool from_extent_allocation = false; int ret = 0; + if (force == CHUNK_ALLOC_FORCE_FOR_EXTENT) { + from_extent_allocation = true; + force = CHUNK_ALLOC_FORCE; + } + /* Don't re-enter if we're already allocating a chunk */ if (trans->allocating_chunk) return -ENOSPC; @@ -3750,9 +3751,22 @@ int btrfs_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags, force_metadata_allocation(fs_info); } - ret = do_chunk_alloc(trans, flags); + ret_bg = do_chunk_alloc(trans, flags); trans->allocating_chunk = false; + if (IS_ERR(ret_bg)) { + ret = PTR_ERR(ret_bg); + } else if (from_extent_allocation) { + /* + * New block group is likely to be used soon. Try to activate + * it now. Failure is OK for now. + */ + btrfs_zone_activate(ret_bg); + } + + if (!ret) + btrfs_put_block_group(ret_bg); + spin_lock(&space_info->lock); if (ret < 0) { if (ret == -ENOSPC) diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 93aabc68bb6a..e8308f2ad07d 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -35,11 +35,15 @@ enum btrfs_discard_state { * the FS with empty chunks * * CHUNK_ALLOC_FORCE means it must try to allocate one + * + * CHUNK_ALLOC_FORCE_FOR_EXTENT like CHUNK_ALLOC_FORCE but called from + * find_free_extent() that also activaes the zone */ enum btrfs_chunk_alloc_enum { CHUNK_ALLOC_NO_FORCE, CHUNK_ALLOC_LIMITED, CHUNK_ALLOC_FORCE, + CHUNK_ALLOC_FORCE_FOR_EXTENT, }; struct btrfs_caching_control { diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index be476f094300..19bf36d8ffea 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -537,6 +537,9 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, cb->orig_bio = NULL; cb->nr_pages = nr_pages; + if (blkcg_css) + kthread_associate_blkcg(blkcg_css); + while (cur_disk_bytenr < disk_start + compressed_len) { u64 offset = cur_disk_bytenr - disk_start; unsigned int index = offset >> PAGE_SHIFT; @@ -555,6 +558,8 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, bio = NULL; goto finish_cb; } + if (blkcg_css) + bio->bi_opf |= REQ_CGROUP_PUNT; } /* * We should never reach next_stripe_start start as we will @@ -612,6 +617,9 @@ blk_status_t btrfs_submit_compressed_write(struct btrfs_inode *inode, u64 start, return 0; finish_cb: + if (blkcg_css) + kthread_associate_blkcg(NULL); + if (bio) { bio->bi_status = ret; bio_endio(bio); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b30309f187cf..126f244cdf88 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1850,9 +1850,10 @@ again: ret = btrfs_insert_fs_root(fs_info, root); if (ret) { - btrfs_put_root(root); - if (ret == -EEXIST) + if (ret == -EEXIST) { + btrfs_put_root(root); goto again; + } goto fail; } return root; diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index f477035a2ac2..6aa92f84f465 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -4082,7 +4082,7 @@ static int find_free_extent_update_loop(struct btrfs_fs_info *fs_info, } ret = btrfs_chunk_alloc(trans, ffe_ctl->flags, - CHUNK_ALLOC_FORCE); + CHUNK_ALLOC_FORCE_FOR_EXTENT); /* Do not bail out on ENOSPC since we can do more. */ if (ret == -ENOSPC) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 17d5557f98ec..5082b9c70f8c 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -2016,8 +2016,7 @@ int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page * to use run_delalloc_nocow() here, like for regular * preallocated inodes. */ - ASSERT(!zoned || - (zoned && btrfs_is_data_reloc_root(inode->root))); + ASSERT(!zoned || btrfs_is_data_reloc_root(inode->root)); ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, nr_written); } else if (!inode_can_compress(inode) || @@ -7444,6 +7443,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, u64 block_start, orig_start, orig_block_len, ram_bytes; bool can_nocow = false; bool space_reserved = false; + u64 prev_len; int ret = 0; /* @@ -7471,6 +7471,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, can_nocow = true; } + prev_len = len; if (can_nocow) { struct extent_map *em2; @@ -7500,8 +7501,6 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, goto out; } } else { - const u64 prev_len = len; - /* Our caller expects us to free the input extent map. */ free_extent_map(em); *map = NULL; @@ -7532,7 +7531,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map, * We have created our ordered extent, so we can now release our reservation * for an outstanding extent. */ - btrfs_delalloc_release_extents(BTRFS_I(inode), len); + btrfs_delalloc_release_extents(BTRFS_I(inode), prev_len); /* * Need to update the i_size under the extent lock so buffered diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index f46e71061942..be6c24577dbe 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -5456,8 +5456,6 @@ long btrfs_ioctl(struct file *file, unsigned int return btrfs_ioctl_fs_info(fs_info, argp); case BTRFS_IOC_DEV_INFO: return btrfs_ioctl_dev_info(fs_info, argp); - case BTRFS_IOC_BALANCE: - return btrfs_ioctl_balance(file, NULL); case BTRFS_IOC_TREE_SEARCH: return btrfs_ioctl_tree_search(inode, argp); case BTRFS_IOC_TREE_SEARCH_V2: diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 2cfbc74a3b4e..a8cc736731fd 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4430,10 +4430,12 @@ static int balance_kthread(void *data) struct btrfs_fs_info *fs_info = data; int ret = 0; + sb_start_write(fs_info->sb); mutex_lock(&fs_info->balance_mutex); if (fs_info->balance_ctl) ret = btrfs_balance(fs_info, fs_info->balance_ctl, NULL); mutex_unlock(&fs_info->balance_mutex); + sb_end_write(fs_info->sb); return ret; } diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c index f256c8aff7bb..ca9f3e4ec4b3 100644 --- a/fs/cachefiles/namei.c +++ b/fs/cachefiles/namei.c @@ -57,6 +57,16 @@ static void __cachefiles_unmark_inode_in_use(struct cachefiles_object *object, trace_cachefiles_mark_inactive(object, inode); } +static void cachefiles_do_unmark_inode_in_use(struct cachefiles_object *object, + struct dentry *dentry) +{ + struct inode *inode = d_backing_inode(dentry); + + inode_lock(inode); + __cachefiles_unmark_inode_in_use(object, dentry); + inode_unlock(inode); +} + /* * Unmark a backing inode and tell cachefilesd that there's something that can * be culled. @@ -68,9 +78,7 @@ void cachefiles_unmark_inode_in_use(struct cachefiles_object *object, struct inode *inode = file_inode(file); if (inode) { - inode_lock(inode); - __cachefiles_unmark_inode_in_use(object, file->f_path.dentry); - inode_unlock(inode); + cachefiles_do_unmark_inode_in_use(object, file->f_path.dentry); if (!test_bit(CACHEFILES_OBJECT_USING_TMPFILE, &object->flags)) { atomic_long_add(inode->i_blocks, &cache->b_released); @@ -484,7 +492,7 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) object, d_backing_inode(path.dentry), ret, cachefiles_trace_trunc_error); file = ERR_PTR(ret); - goto out_dput; + goto out_unuse; } } @@ -494,15 +502,20 @@ struct file *cachefiles_create_tmpfile(struct cachefiles_object *object) trace_cachefiles_vfs_error(object, d_backing_inode(path.dentry), PTR_ERR(file), cachefiles_trace_open_error); - goto out_dput; + goto out_unuse; } if (unlikely(!file->f_op->read_iter) || unlikely(!file->f_op->write_iter)) { fput(file); pr_notice("Cache does not support read_iter and write_iter\n"); file = ERR_PTR(-EINVAL); + goto out_unuse; } + goto out_dput; + +out_unuse: + cachefiles_do_unmark_inode_in_use(object, path.dentry); out_dput: dput(path.dentry); out: @@ -590,14 +603,16 @@ static bool cachefiles_open_file(struct cachefiles_object *object, check_failed: fscache_cookie_lookup_negative(object->cookie); cachefiles_unmark_inode_in_use(object, file); - if (ret == -ESTALE) { - fput(file); - dput(dentry); + fput(file); + dput(dentry); + if (ret == -ESTALE) return cachefiles_create_file(object); - } + return false; + error_fput: fput(file); error: + cachefiles_do_unmark_inode_in_use(object, dentry); dput(dentry); return false; } diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c index 35465109d9c4..00b087c14995 100644 --- a/fs/cachefiles/xattr.c +++ b/fs/cachefiles/xattr.c @@ -203,7 +203,7 @@ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume) if (!buf) return false; buf->reserved = cpu_to_be32(0); - memcpy(buf->data, p, len); + memcpy(buf->data, p, volume->vcookie->coherency_len); ret = cachefiles_inject_write_error(); if (ret == 0) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index a47fa44b6d52..2b1a1c029c75 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -266,22 +266,24 @@ static void cifs_kill_sb(struct super_block *sb) * before we kill the sb. */ if (cifs_sb->root) { + for (node = rb_first(root); node; node = rb_next(node)) { + tlink = rb_entry(node, struct tcon_link, tl_rbnode); + tcon = tlink_tcon(tlink); + if (IS_ERR(tcon)) + continue; + cfid = &tcon->crfid; + mutex_lock(&cfid->fid_mutex); + if (cfid->dentry) { + dput(cfid->dentry); + cfid->dentry = NULL; + } + mutex_unlock(&cfid->fid_mutex); + } + + /* finally release root dentry */ dput(cifs_sb->root); cifs_sb->root = NULL; } - node = rb_first(root); - while (node != NULL) { - tlink = rb_entry(node, struct tcon_link, tl_rbnode); - tcon = tlink_tcon(tlink); - cfid = &tcon->crfid; - mutex_lock(&cfid->fid_mutex); - if (cfid->dentry) { - dput(cfid->dentry); - cfid->dentry = NULL; - } - mutex_unlock(&cfid->fid_mutex); - node = rb_next(node); - } kill_anon_super(sb); cifs_umount(cifs_sb); @@ -944,7 +946,7 @@ cifs_loose_read_iter(struct kiocb *iocb, struct iov_iter *iter) ssize_t rc; struct inode *inode = file_inode(iocb->ki_filp); - if (iocb->ki_filp->f_flags & O_DIRECT) + if (iocb->ki_flags & IOCB_DIRECT) return cifs_user_readv(iocb, iter); rc = cifs_revalidate_mapping(inode); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 54155eb4faac..42e14f408856 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -534,12 +534,19 @@ int cifs_reconnect(struct TCP_Server_Info *server, bool mark_smb_session) { /* If tcp session is not an dfs connection, then reconnect to last target server */ spin_lock(&cifs_tcp_ses_lock); - if (!server->is_dfs_conn || !server->origin_fullpath || !server->leaf_fullpath) { + if (!server->is_dfs_conn) { spin_unlock(&cifs_tcp_ses_lock); return __cifs_reconnect(server, mark_smb_session); } spin_unlock(&cifs_tcp_ses_lock); + mutex_lock(&server->refpath_lock); + if (!server->origin_fullpath || !server->leaf_fullpath) { + mutex_unlock(&server->refpath_lock); + return __cifs_reconnect(server, mark_smb_session); + } + mutex_unlock(&server->refpath_lock); + return reconnect_dfs_server(server); } #else @@ -1049,7 +1056,7 @@ smb2_add_credits_from_hdr(char *buffer, struct TCP_Server_Info *server) spin_unlock(&server->req_lock); wake_up(&server->request_q); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_hdr_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, le16_to_cpu(shdr->CreditRequest), in_flight); cifs_server_dbg(FYI, "%s: added %u credits total=%d\n", @@ -3675,9 +3682,11 @@ static void setup_server_referral_paths(struct mount_ctx *mnt_ctx) { struct TCP_Server_Info *server = mnt_ctx->server; + mutex_lock(&server->refpath_lock); server->origin_fullpath = mnt_ctx->origin_fullpath; server->leaf_fullpath = mnt_ctx->leaf_fullpath; server->current_fullpath = mnt_ctx->leaf_fullpath; + mutex_unlock(&server->refpath_lock); mnt_ctx->origin_fullpath = mnt_ctx->leaf_fullpath = NULL; } diff --git a/fs/cifs/dfs_cache.c b/fs/cifs/dfs_cache.c index 30e040da4f09..956f8e5cf3e7 100644 --- a/fs/cifs/dfs_cache.c +++ b/fs/cifs/dfs_cache.c @@ -1422,12 +1422,14 @@ static int refresh_tcon(struct cifs_ses **sessions, struct cifs_tcon *tcon, bool struct TCP_Server_Info *server = tcon->ses->server; mutex_lock(&server->refpath_lock); - if (strcasecmp(server->leaf_fullpath, server->origin_fullpath)) - __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, force_refresh); + if (server->origin_fullpath) { + if (server->leaf_fullpath && strcasecmp(server->leaf_fullpath, + server->origin_fullpath)) + __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, force_refresh); + __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, force_refresh); + } mutex_unlock(&server->refpath_lock); - __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, force_refresh); - return 0; } @@ -1530,11 +1532,14 @@ static void refresh_mounts(struct cifs_ses **sessions) list_del_init(&tcon->ulist); mutex_lock(&server->refpath_lock); - if (strcasecmp(server->leaf_fullpath, server->origin_fullpath)) - __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, false); + if (server->origin_fullpath) { + if (server->leaf_fullpath && strcasecmp(server->leaf_fullpath, + server->origin_fullpath)) + __refresh_tcon(server->leaf_fullpath + 1, sessions, tcon, false); + __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, false); + } mutex_unlock(&server->refpath_lock); - __refresh_tcon(server->origin_fullpath + 1, sessions, tcon, false); cifs_put_tcon(tcon); } } diff --git a/fs/cifs/link.c b/fs/cifs/link.c index 852e54ee82c2..bbdf3281559c 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -85,6 +85,9 @@ parse_mf_symlink(const u8 *buf, unsigned int buf_len, unsigned int *_link_len, if (rc != 1) return -EINVAL; + if (link_len > CIFS_MF_SYMLINK_LINK_MAXLEN) + return -EINVAL; + rc = symlink_hash(link_len, link_str, md5_hash); if (rc) { cifs_dbg(FYI, "%s: MD5 hash failure: %d\n", __func__, rc); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index db23f5b404ba..d6aaeff4a30a 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -86,6 +86,9 @@ smb2_add_credits(struct TCP_Server_Info *server, if (*val > 65000) { *val = 65000; /* Don't get near 64K credits, avoid srv bugs */ pr_warn_once("server overflowed SMB3 credits\n"); + trace_smb3_overflow_credits(server->CurrentMid, + server->conn_id, server->hostname, *val, + add, server->in_flight); } server->in_flight--; if (server->in_flight == 0 && @@ -251,7 +254,7 @@ smb2_wait_mtu_credits(struct TCP_Server_Info *server, unsigned int size, in_flight = server->in_flight; spin_unlock(&server->req_lock); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_wait_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, -(credits->value), in_flight); cifs_dbg(FYI, "%s: removed %u credits total=%d\n", __func__, credits->value, scredits); @@ -300,7 +303,7 @@ smb2_adjust_credits(struct TCP_Server_Info *server, spin_unlock(&server->req_lock); wake_up(&server->request_q); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_adj_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, credits->value - new_val, in_flight); cifs_dbg(FYI, "%s: adjust added %u credits total=%d\n", @@ -1855,9 +1858,17 @@ smb2_copychunk_range(const unsigned int xid, int chunks_copied = 0; bool chunk_sizes_updated = false; ssize_t bytes_written, total_bytes_written = 0; + struct inode *inode; pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL); + /* + * We need to flush all unwritten data before we can send the + * copychunk ioctl to the server. + */ + inode = d_inode(trgtfile->dentry); + filemap_write_and_wait(inode->i_mapping); + if (pcchunk == NULL) return -ENOMEM; @@ -2492,7 +2503,7 @@ smb2_is_status_pending(char *buf, struct TCP_Server_Info *server) spin_unlock(&server->req_lock); wake_up(&server->request_q); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_pend_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, le16_to_cpu(shdr->CreditRequest), in_flight); cifs_dbg(FYI, "%s: status pending add %u credits total=%d\n", diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h index 6cecf302dcfd..bc279616c513 100644 --- a/fs/cifs/trace.h +++ b/fs/cifs/trace.h @@ -1006,6 +1006,13 @@ DEFINE_SMB3_CREDIT_EVENT(credit_timeout); DEFINE_SMB3_CREDIT_EVENT(insufficient_credits); DEFINE_SMB3_CREDIT_EVENT(too_many_credits); DEFINE_SMB3_CREDIT_EVENT(add_credits); +DEFINE_SMB3_CREDIT_EVENT(adj_credits); +DEFINE_SMB3_CREDIT_EVENT(hdr_credits); +DEFINE_SMB3_CREDIT_EVENT(nblk_credits); +DEFINE_SMB3_CREDIT_EVENT(pend_credits); +DEFINE_SMB3_CREDIT_EVENT(wait_credits); +DEFINE_SMB3_CREDIT_EVENT(waitff_credits); +DEFINE_SMB3_CREDIT_EVENT(overflow_credits); DEFINE_SMB3_CREDIT_EVENT(set_credits); #endif /* _CIFS_TRACE_H */ diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index eeb1a699bd6f..c667e6ddfe2f 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -464,13 +464,12 @@ smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, return -EIO; } - tr_hdr = kmalloc(sizeof(*tr_hdr), GFP_NOFS); + tr_hdr = kzalloc(sizeof(*tr_hdr), GFP_NOFS); if (!tr_hdr) return -ENOMEM; memset(&cur_rqst[0], 0, sizeof(cur_rqst)); memset(&iov, 0, sizeof(iov)); - memset(tr_hdr, 0, sizeof(*tr_hdr)); iov.iov_base = tr_hdr; iov.iov_len = sizeof(*tr_hdr); @@ -542,7 +541,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, in_flight = server->in_flight; spin_unlock(&server->req_lock); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_nblk_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, -1, in_flight); cifs_dbg(FYI, "%s: remove %u credits total=%d\n", __func__, 1, scredits); @@ -648,7 +647,7 @@ wait_for_free_credits(struct TCP_Server_Info *server, const int num_credits, in_flight = server->in_flight; spin_unlock(&server->req_lock); - trace_smb3_add_credits(server->CurrentMid, + trace_smb3_waitff_credits(server->CurrentMid, server->conn_id, server->hostname, scredits, -(num_credits), in_flight); cifs_dbg(FYI, "%s: remove %u credits total=%d\n", diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 0ed880f42525..e6dea6dfca16 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1066,12 +1066,9 @@ static void z_erofs_decompress_kickoff(struct z_erofs_decompressqueue *io, /* wake up the caller thread for sync decompression */ if (sync) { - unsigned long flags; - - spin_lock_irqsave(&io->u.wait.lock, flags); if (!atomic_add_return(bios, &io->pending_bios)) - wake_up_locked(&io->u.wait); - spin_unlock_irqrestore(&io->u.wait.lock, flags); + complete(&io->u.done); + return; } @@ -1217,7 +1214,7 @@ jobqueue_init(struct super_block *sb, } else { fg_out: q = fgq; - init_waitqueue_head(&fgq->u.wait); + init_completion(&fgq->u.done); atomic_set(&fgq->pending_bios, 0); } q->sb = sb; @@ -1419,8 +1416,7 @@ static void z_erofs_runqueue(struct super_block *sb, return; /* wait until all bios are completed */ - io_wait_event(io[JQ_SUBMIT].u.wait, - !atomic_read(&io[JQ_SUBMIT].pending_bios)); + wait_for_completion_io(&io[JQ_SUBMIT].u.done); /* handle synchronous decompress queue in the caller context */ z_erofs_decompress_queue(&io[JQ_SUBMIT], pagepool); diff --git a/fs/erofs/zdata.h b/fs/erofs/zdata.h index e043216b545f..800b11c53f57 100644 --- a/fs/erofs/zdata.h +++ b/fs/erofs/zdata.h @@ -97,7 +97,7 @@ struct z_erofs_decompressqueue { z_erofs_next_pcluster_t head; union { - wait_queue_head_t wait; + struct completion done; struct work_struct work; } u; }; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 3f87cca49f0c..a743b1e3b89e 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2273,6 +2273,10 @@ static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi) * Structure of a directory entry */ #define EXT4_NAME_LEN 255 +/* + * Base length of the ext4 directory entry excluding the name length + */ +#define EXT4_BASE_DIR_LEN (sizeof(struct ext4_dir_entry_2) - EXT4_NAME_LEN) struct ext4_dir_entry { __le32 inode; /* Inode number */ @@ -3032,7 +3036,7 @@ extern int ext4_inode_attach_jinode(struct inode *inode); extern int ext4_can_truncate(struct inode *inode); extern int ext4_truncate(struct inode *); extern int ext4_break_layouts(struct inode *); -extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length); +extern int ext4_punch_hole(struct file *file, loff_t offset, loff_t length); extern void ext4_set_inode_flags(struct inode *, bool init); extern int ext4_alloc_da_blocks(struct inode *inode); extern void ext4_set_aops(struct inode *inode); @@ -3064,6 +3068,7 @@ int ext4_fileattr_set(struct user_namespace *mnt_userns, struct dentry *dentry, struct fileattr *fa); int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa); extern void ext4_reset_inode_seed(struct inode *inode); +int ext4_update_overhead(struct super_block *sb); /* migrate.c */ extern int ext4_ext_migrate(struct inode *); diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 0d98cf402282..e473fde6b64b 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -4500,9 +4500,9 @@ retry: return ret > 0 ? ret2 : ret; } -static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len); +static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len); -static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len); +static int ext4_insert_range(struct file *file, loff_t offset, loff_t len); static long ext4_zero_range(struct file *file, loff_t offset, loff_t len, int mode) @@ -4574,6 +4574,10 @@ static long ext4_zero_range(struct file *file, loff_t offset, /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* Preallocate the range including the unaligned edges */ if (partial_begin || partial_end) { ret = ext4_alloc_file_blocks(file, @@ -4690,7 +4694,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) return -EOPNOTSUPP; if (mode & FALLOC_FL_PUNCH_HOLE) { - ret = ext4_punch_hole(inode, offset, len); + ret = ext4_punch_hole(file, offset, len); goto exit; } @@ -4699,12 +4703,12 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) goto exit; if (mode & FALLOC_FL_COLLAPSE_RANGE) { - ret = ext4_collapse_range(inode, offset, len); + ret = ext4_collapse_range(file, offset, len); goto exit; } if (mode & FALLOC_FL_INSERT_RANGE) { - ret = ext4_insert_range(inode, offset, len); + ret = ext4_insert_range(file, offset, len); goto exit; } @@ -4740,6 +4744,10 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out; + ret = ext4_alloc_file_blocks(file, lblk, max_blocks, new_size, flags); if (ret) goto out; @@ -5241,8 +5249,9 @@ out: * This implements the fallocate's collapse range functionality for ext4 * Returns: 0 and non-zero on error. */ -static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; ext4_lblk_t punch_start, punch_stop; @@ -5294,6 +5303,10 @@ static int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len) /* Wait for existing dio to complete */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. @@ -5387,8 +5400,9 @@ out_mutex: * by len bytes. * Returns 0 on success, error otherwise. */ -static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) +static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; handle_t *handle; @@ -5445,6 +5459,10 @@ static int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len) /* Wait for existing dio to complete */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 13740f2d0e61..646ece9b3455 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3953,12 +3953,14 @@ int ext4_break_layouts(struct inode *inode) * Returns: 0 on success or negative on failure */ -int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) +int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) { + struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; ext4_lblk_t first_block, stop_block; struct address_space *mapping = inode->i_mapping; - loff_t first_block_offset, last_block_offset; + loff_t first_block_offset, last_block_offset, max_length; + struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); handle_t *handle; unsigned int credits; int ret = 0, ret2 = 0; @@ -4001,6 +4003,14 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) offset; } + /* + * For punch hole the length + offset needs to be within one block + * before last range. Adjust the length if it goes beyond that limit. + */ + max_length = sbi->s_bitmap_maxbytes - inode->i_sb->s_blocksize; + if (offset + length > max_length) + length = max_length - offset; + if (offset & (sb->s_blocksize - 1) || (offset + length) & (sb->s_blocksize - 1)) { /* @@ -4016,6 +4026,10 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length) /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); + ret = file_modified(file); + if (ret) + goto out_mutex; + /* * Prevent page faults from reinstantiating pages we have released from * page cache. diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index 992229ca2d83..ba44fa1be70a 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -1652,3 +1652,19 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return ext4_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); } #endif + +static void set_overhead(struct ext4_super_block *es, const void *arg) +{ + es->s_overhead_clusters = cpu_to_le32(*((unsigned long *) arg)); +} + +int ext4_update_overhead(struct super_block *sb) +{ + struct ext4_sb_info *sbi = EXT4_SB(sb); + + if (sb_rdonly(sb) || sbi->s_overhead == 0 || + sbi->s_overhead == le32_to_cpu(sbi->s_es->s_overhead_clusters)) + return 0; + + return ext4_update_superblocks_fn(sb, set_overhead, &sbi->s_overhead); +} diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index e37da8d5cd0c..767b4bfe39c3 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1466,10 +1466,10 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, de = (struct ext4_dir_entry_2 *)search_buf; dlimit = search_buf + buf_size; - while ((char *) de < dlimit) { + while ((char *) de < dlimit - EXT4_BASE_DIR_LEN) { /* this code is executed quadratically often */ /* do minimal checking `by hand' */ - if ((char *) de + de->name_len <= dlimit && + if (de->name + de->name_len <= dlimit && ext4_match(dir, fname, de)) { /* found a match - just to be sure, do * a full check */ diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 495ce59fb4ad..14695e2b5042 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -134,8 +134,10 @@ static void ext4_finish_bio(struct bio *bio) continue; } clear_buffer_async_write(bh); - if (bio->bi_status) + if (bio->bi_status) { + set_buffer_write_io_error(bh); buffer_io_error(bh); + } } while ((bh = bh->b_this_page) != head); spin_unlock_irqrestore(&head->b_uptodate_lock, flags); if (!under_io) { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 81749eaddf4c..1466fbdbc8e3 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1199,20 +1199,25 @@ static void ext4_put_super(struct super_block *sb) int aborted = 0; int i, err; - ext4_unregister_li_request(sb); - ext4_quota_off_umount(sb); - - flush_work(&sbi->s_error_work); - destroy_workqueue(sbi->rsv_conversion_wq); - ext4_release_orphan_info(sb); - /* * Unregister sysfs before destroying jbd2 journal. * Since we could still access attr_journal_task attribute via sysfs * path which could have sbi->s_journal->j_task as NULL + * Unregister sysfs before flush sbi->s_error_work. + * Since user may read /proc/fs/ext4/xx/mb_groups during umount, If + * read metadata verify failed then will queue error work. + * flush_stashed_error_work will call start_this_handle may trigger + * BUG_ON. */ ext4_unregister_sysfs(sb); + ext4_unregister_li_request(sb); + ext4_quota_off_umount(sb); + + flush_work(&sbi->s_error_work); + destroy_workqueue(sbi->rsv_conversion_wq); + ext4_release_orphan_info(sb); + if (sbi->s_journal) { aborted = is_journal_aborted(sbi->s_journal); err = jbd2_journal_destroy(sbi->s_journal); @@ -4172,9 +4177,11 @@ static int count_overhead(struct super_block *sb, ext4_group_t grp, ext4_fsblk_t first_block, last_block, b; ext4_group_t i, ngroups = ext4_get_groups_count(sb); int s, j, count = 0; + int has_super = ext4_bg_has_super(sb, grp); if (!ext4_has_feature_bigalloc(sb)) - return (ext4_bg_has_super(sb, grp) + ext4_bg_num_gdb(sb, grp) + + return (has_super + ext4_bg_num_gdb(sb, grp) + + (has_super ? le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) : 0) + sbi->s_itb_per_group + 2); first_block = le32_to_cpu(sbi->s_es->s_first_data_block) + @@ -5282,9 +5289,18 @@ no_journal: * Get the # of file system overhead blocks from the * superblock if present. */ - if (es->s_overhead_clusters) - sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); - else { + sbi->s_overhead = le32_to_cpu(es->s_overhead_clusters); + /* ignore the precalculated value if it is ridiculous */ + if (sbi->s_overhead > ext4_blocks_count(es)) + sbi->s_overhead = 0; + /* + * If the bigalloc feature is not enabled recalculating the + * overhead doesn't take long, so we might as well just redo + * it to make sure we are using the correct value. + */ + if (!ext4_has_feature_bigalloc(sb)) + sbi->s_overhead = 0; + if (sbi->s_overhead == 0) { err = ext4_calculate_overhead(sb); if (err) goto failed_mount_wq; @@ -5602,6 +5618,8 @@ static int ext4_fill_super(struct super_block *sb, struct fs_context *fc) ext4_msg(sb, KERN_INFO, "mounted filesystem with%s. " "Quota mode: %s.", descr, ext4_quota_mode(sb)); + /* Update the s_overhead_clusters if necessary */ + ext4_update_overhead(sb); return 0; free_sbi: diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig index 76316c4a3fb7..b313a978ae0a 100644 --- a/fs/fscache/Kconfig +++ b/fs/fscache/Kconfig @@ -38,6 +38,3 @@ config FSCACHE_DEBUG enabled by setting bits in /sys/modules/fscache/parameter/debug. See Documentation/filesystems/caching/fscache.rst for more information. - -config FSCACHE_OLD_API - bool diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c index 2749933852a9..d645f8b302a2 100644 --- a/fs/fscache/cache.c +++ b/fs/fscache/cache.c @@ -214,7 +214,7 @@ void fscache_relinquish_cache(struct fscache_cache *cache) cache->ops = NULL; cache->cache_priv = NULL; - smp_store_release(&cache->state, FSCACHE_CACHE_IS_NOT_PRESENT); + fscache_set_cache_state(cache, FSCACHE_CACHE_IS_NOT_PRESENT); fscache_put_cache(cache, where); } EXPORT_SYMBOL(fscache_relinquish_cache); diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 9bb1ab5fe5ed..9d3cf0111709 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -30,7 +30,7 @@ static DEFINE_SPINLOCK(fscache_cookie_lru_lock); DEFINE_TIMER(fscache_cookie_lru_timer, fscache_cookie_lru_timed_out); static DECLARE_WORK(fscache_cookie_lru_work, fscache_cookie_lru_worker); static const char fscache_cookie_states[FSCACHE_COOKIE_STATE__NR] = "-LCAIFUWRD"; -unsigned int fscache_lru_cookie_timeout = 10 * HZ; +static unsigned int fscache_lru_cookie_timeout = 10 * HZ; void fscache_print_cookie(struct fscache_cookie *cookie, char prefix) { @@ -1069,6 +1069,7 @@ void __fscache_invalidate(struct fscache_cookie *cookie, } EXPORT_SYMBOL(__fscache_invalidate); +#ifdef CONFIG_PROC_FS /* * Generate a list of extant cookies in /proc/fs/fscache/cookies */ @@ -1145,3 +1146,4 @@ const struct seq_operations fscache_cookies_seq_ops = { .stop = fscache_cookies_seq_stop, .show = fscache_cookies_seq_show, }; +#endif diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h index ed1c9ed737f2..1336f517e9b1 100644 --- a/fs/fscache/internal.h +++ b/fs/fscache/internal.h @@ -56,7 +56,9 @@ static inline bool fscache_set_cache_state_maybe(struct fscache_cache *cache, * cookie.c */ extern struct kmem_cache *fscache_cookie_jar; +#ifdef CONFIG_PROC_FS extern const struct seq_operations fscache_cookies_seq_ops; +#endif extern struct timer_list fscache_cookie_lru_timer; extern void fscache_print_cookie(struct fscache_cookie *cookie, char prefix); @@ -137,7 +139,9 @@ int fscache_stats_show(struct seq_file *m, void *v); /* * volume.c */ +#ifdef CONFIG_PROC_FS extern const struct seq_operations fscache_volumes_seq_ops; +#endif struct fscache_volume *fscache_get_volume(struct fscache_volume *volume, enum fscache_volume_trace where); diff --git a/fs/fscache/io.c b/fs/fscache/io.c index c8c7fe9e9a6e..3af3b08a9bb3 100644 --- a/fs/fscache/io.c +++ b/fs/fscache/io.c @@ -235,8 +235,7 @@ static void fscache_wreq_done(void *priv, ssize_t transferred_or_error, { struct fscache_write_request *wreq = priv; - fscache_clear_page_bits(fscache_cres_cookie(&wreq->cache_resources), - wreq->mapping, wreq->start, wreq->len, + fscache_clear_page_bits(wreq->mapping, wreq->start, wreq->len, wreq->set_bits); if (wreq->term_func) @@ -296,7 +295,7 @@ abandon_end: abandon_free: kfree(wreq); abandon: - fscache_clear_page_bits(cookie, mapping, start, len, cond); + fscache_clear_page_bits(mapping, start, len, cond); if (term_func) term_func(term_func_priv, ret, false); } diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 99c7477cee5c..dd3a088db11d 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -206,7 +206,7 @@ hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, info.flags = 0; info.length = len; info.low_limit = current->mm->mmap_base; - info.high_limit = TASK_SIZE; + info.high_limit = arch_get_mmap_end(addr); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; return vm_unmapped_area(&info); @@ -222,7 +222,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = max(PAGE_SIZE, mmap_min_addr); - info.high_limit = current->mm->mmap_base; + info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base); info.align_mask = PAGE_MASK & ~huge_page_mask(h); info.align_offset = 0; addr = vm_unmapped_area(&info); @@ -237,7 +237,7 @@ hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = current->mm->mmap_base; - info.high_limit = TASK_SIZE; + info.high_limit = arch_get_mmap_end(addr); addr = vm_unmapped_area(&info); } @@ -251,6 +251,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct hstate *h = hstate_file(file); + const unsigned long mmap_end = arch_get_mmap_end(addr); if (len & ~huge_page_mask(h)) return -EINVAL; @@ -266,7 +267,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr, if (addr) { addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); - if (TASK_SIZE - len >= addr && + if (mmap_end - len >= addr && (!vma || addr + len <= vm_start_gap(vma))) return addr; } diff --git a/fs/io-wq.h b/fs/io-wq.h index 04d374e65e54..dbecd27656c7 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -155,7 +155,6 @@ struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack) struct io_wq_work { struct io_wq_work_node list; unsigned flags; - int fd; }; static inline struct io_wq_work *wq_next_work(struct io_wq_work *work) diff --git a/fs/io_uring.c b/fs/io_uring.c index 659f8ecba5b7..7625b29153b9 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -907,7 +907,11 @@ struct io_kiocb { u64 user_data; u32 result; - u32 cflags; + /* fd initially, then cflags for completion */ + union { + u32 cflags; + int fd; + }; struct io_ring_ctx *ctx; struct task_struct *task; @@ -916,8 +920,12 @@ struct io_kiocb { /* store used ubuf, so we can prevent reloading */ struct io_mapped_ubuf *imu; - /* used by request caches, completion batching and iopoll */ - struct io_wq_work_node comp_list; + union { + /* used by request caches, completion batching and iopoll */ + struct io_wq_work_node comp_list; + /* cache ->apoll->events */ + int apoll_events; + }; atomic_t refs; atomic_t poll_refs; struct io_task_work io_task_work; @@ -2789,11 +2797,10 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin) /* order with io_complete_rw_iopoll(), e.g. ->result updates */ if (!smp_load_acquire(&req->iopoll_completed)) break; + nr_events++; if (unlikely(req->flags & REQ_F_CQE_SKIP)) continue; - __io_fill_cqe_req(req, req->result, io_put_kbuf(req, 0)); - nr_events++; } if (unlikely(!nr_events)) @@ -3183,19 +3190,18 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret) static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req) { struct kiocb *kiocb = &req->rw.kiocb; - bool is_stream = req->file->f_mode & FMODE_STREAM; - if (kiocb->ki_pos == -1) { - if (!is_stream) { - req->flags |= REQ_F_CUR_POS; - kiocb->ki_pos = req->file->f_pos; - return &kiocb->ki_pos; - } else { - kiocb->ki_pos = 0; - return NULL; - } + if (kiocb->ki_pos != -1) + return &kiocb->ki_pos; + + if (!(req->file->f_mode & FMODE_STREAM)) { + req->flags |= REQ_F_CUR_POS; + kiocb->ki_pos = req->file->f_pos; + return &kiocb->ki_pos; } - return is_stream ? NULL : &kiocb->ki_pos; + + kiocb->ki_pos = 0; + return NULL; } static void kiocb_done(struct io_kiocb *req, ssize_t ret, @@ -3825,8 +3831,10 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) iovec = NULL; } ret = io_rw_init_file(req, FMODE_READ); - if (unlikely(ret)) + if (unlikely(ret)) { + kfree(iovec); return ret; + } req->result = iov_iter_count(&s->iter); if (force_nonblock) { @@ -3951,8 +3959,10 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) iovec = NULL; } ret = io_rw_init_file(req, FMODE_WRITE); - if (unlikely(ret)) + if (unlikely(ret)) { + kfree(iovec); return ret; + } req->result = iov_iter_count(&s->iter); if (force_nonblock) { @@ -4351,7 +4361,7 @@ static int io_tee(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; if (sp->flags & SPLICE_F_FD_IN_FIXED) - in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED); + in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags); else in = io_file_get_normal(req, sp->splice_fd_in); if (!in) { @@ -4393,7 +4403,7 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; if (sp->flags & SPLICE_F_FD_IN_FIXED) - in = io_file_get_fixed(req, sp->splice_fd_in, IO_URING_F_UNLOCKED); + in = io_file_get_fixed(req, sp->splice_fd_in, issue_flags); else in = io_file_get_normal(req, sp->splice_fd_in); if (!in) { @@ -5834,7 +5844,6 @@ static void io_poll_remove_entries(struct io_kiocb *req) static int io_poll_check_events(struct io_kiocb *req, bool locked) { struct io_ring_ctx *ctx = req->ctx; - struct io_poll_iocb *poll = io_poll_get_single(req); int v; /* req->task == current here, checking PF_EXITING is safe */ @@ -5851,17 +5860,17 @@ static int io_poll_check_events(struct io_kiocb *req, bool locked) return -ECANCELED; if (!req->result) { - struct poll_table_struct pt = { ._key = req->cflags }; + struct poll_table_struct pt = { ._key = req->apoll_events }; + unsigned flags = locked ? 0 : IO_URING_F_UNLOCKED; - if (unlikely(!io_assign_file(req, IO_URING_F_UNLOCKED))) - req->result = -EBADF; - else - req->result = vfs_poll(req->file, &pt) & req->cflags; + if (unlikely(!io_assign_file(req, flags))) + return -EBADF; + req->result = vfs_poll(req->file, &pt) & req->apoll_events; } /* multishot, just fill an CQE and proceed */ - if (req->result && !(req->cflags & EPOLLONESHOT)) { - __poll_t mask = mangle_poll(req->result & poll->events); + if (req->result && !(req->apoll_events & EPOLLONESHOT)) { + __poll_t mask = mangle_poll(req->result & req->apoll_events); bool filled; spin_lock(&ctx->completion_lock); @@ -5939,7 +5948,7 @@ static void __io_poll_execute(struct io_kiocb *req, int mask, int events) * CPU. We want to avoid pulling in req->apoll->events for that * case. */ - req->cflags = events; + req->apoll_events = events; if (req->opcode == IORING_OP_POLL_ADD) req->io_task_work.func = io_poll_task_func; else @@ -6331,7 +6340,7 @@ static int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe return -EINVAL; io_req_set_refcount(req); - req->cflags = poll->events = io_poll_parse_events(sqe, flags); + req->apoll_events = poll->events = io_poll_parse_events(sqe, flags); return 0; } @@ -6833,6 +6842,7 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) up.nr = 0; up.tags = 0; up.resv = 0; + up.resv2 = 0; io_ring_submit_lock(ctx, needs_lock); ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE, @@ -7088,9 +7098,9 @@ static bool io_assign_file(struct io_kiocb *req, unsigned int issue_flags) return true; if (req->flags & REQ_F_FIXED_FILE) - req->file = io_file_get_fixed(req, req->work.fd, issue_flags); + req->file = io_file_get_fixed(req, req->fd, issue_flags); else - req->file = io_file_get_normal(req, req->work.fd); + req->file = io_file_get_normal(req, req->fd); if (req->file) return true; @@ -7104,13 +7114,14 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) const struct cred *creds = NULL; int ret; + if (unlikely(!io_assign_file(req, issue_flags))) + return -EBADF; + if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred())) creds = override_creds(req->creds); if (!io_op_defs[req->opcode].audit_skip) audit_uring_entry(req->opcode); - if (unlikely(!io_assign_file(req, issue_flags))) - return -EBADF; switch (req->opcode) { case IORING_OP_NOP: @@ -7271,16 +7282,18 @@ static void io_wq_submit_work(struct io_wq_work *work) if (timeout) io_queue_linked_timeout(timeout); - if (!io_assign_file(req, issue_flags)) { - err = -EBADF; - work->flags |= IO_WQ_WORK_CANCEL; - } /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ if (work->flags & IO_WQ_WORK_CANCEL) { +fail: io_req_task_queue_fail(req, err); return; } + if (!io_assign_file(req, issue_flags)) { + err = -EBADF; + work->flags |= IO_WQ_WORK_CANCEL; + goto fail; + } if (req->flags & REQ_F_FORCE_ASYNC) { bool opcode_poll = def->pollin || def->pollout; @@ -7628,7 +7641,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (io_op_defs[opcode].needs_file) { struct io_submit_state *state = &ctx->submit_state; - req->work.fd = READ_ONCE(sqe->fd); + req->fd = READ_ONCE(sqe->fd); /* * Plug now if we have more than 2 IO left after this, and the @@ -10524,6 +10537,11 @@ static int io_ringfd_register(struct io_ring_ctx *ctx, void __user *__arg, break; } + if (reg.resv) { + ret = -EINVAL; + break; + } + if (reg.offset == -1U) { start = 0; end = IO_RINGFD_REG_MAX; @@ -10570,7 +10588,7 @@ static int io_ringfd_unregister(struct io_ring_ctx *ctx, void __user *__arg, ret = -EFAULT; break; } - if (reg.offset >= IO_RINGFD_REG_MAX) { + if (reg.resv || reg.offset >= IO_RINGFD_REG_MAX) { ret = -EINVAL; break; } @@ -10697,6 +10715,8 @@ static int io_get_ext_arg(unsigned flags, const void __user *argp, size_t *argsz return -EINVAL; if (copy_from_user(&arg, argp, sizeof(arg))) return -EFAULT; + if (arg.pad) + return -EINVAL; *sig = u64_to_user_ptr(arg.sigmask); *argsz = arg.sigmask_sz; *ts = u64_to_user_ptr(arg.ts); @@ -11178,7 +11198,8 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, IORING_FEAT_CUR_PERSONALITY | IORING_FEAT_FAST_POLL | IORING_FEAT_POLL_32BITS | IORING_FEAT_SQPOLL_NONFIXED | IORING_FEAT_EXT_ARG | IORING_FEAT_NATIVE_WORKERS | - IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP; + IORING_FEAT_RSRC_TAGS | IORING_FEAT_CQE_SKIP | + IORING_FEAT_LINKED_FILE; if (copy_to_user(params, p, sizeof(*p))) { ret = -EFAULT; @@ -11389,8 +11410,6 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, __u32 tmp; int err; - if (up->resv) - return -EINVAL; if (check_add_overflow(up->offset, nr_args, &tmp)) return -EOVERFLOW; err = io_rsrc_node_switch_start(ctx); @@ -11416,6 +11435,8 @@ static int io_register_files_update(struct io_ring_ctx *ctx, void __user *arg, memset(&up, 0, sizeof(up)); if (copy_from_user(&up, arg, sizeof(struct io_uring_rsrc_update))) return -EFAULT; + if (up.resv || up.resv2) + return -EINVAL; return __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, nr_args); } @@ -11428,7 +11449,7 @@ static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, return -EINVAL; if (copy_from_user(&up, arg, sizeof(up))) return -EFAULT; - if (!up.nr || up.resv) + if (!up.nr || up.resv || up.resv2) return -EINVAL; return __io_register_rsrc_update(ctx, type, &up, up.nr); } diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c index 5b9408e3b370..ac7f067b7bdd 100644 --- a/fs/jbd2/commit.c +++ b/fs/jbd2/commit.c @@ -488,7 +488,6 @@ void jbd2_journal_commit_transaction(journal_t *journal) jbd2_journal_wait_updates(journal); commit_transaction->t_state = T_SWITCH; - write_unlock(&journal->j_state_lock); J_ASSERT (atomic_read(&commit_transaction->t_outstanding_credits) <= journal->j_max_transaction_buffers); @@ -508,6 +507,8 @@ void jbd2_journal_commit_transaction(journal_t *journal) * has reserved. This is consistent with the existing behaviour * that multiple jbd2_journal_get_write_access() calls to the same * buffer are perfectly permissible. + * We use journal->j_state_lock here to serialize processing of + * t_reserved_list with eviction of buffers from journal_unmap_buffer(). */ while (commit_transaction->t_reserved_list) { jh = commit_transaction->t_reserved_list; @@ -527,6 +528,7 @@ void jbd2_journal_commit_transaction(journal_t *journal) jbd2_journal_refile_buffer(journal, jh); } + write_unlock(&journal->j_state_lock); /* * Now try to drop any written-back buffers from the journal's * checkpoint lists. We do this *before* commit because it potentially diff --git a/fs/ksmbd/misc.c b/fs/ksmbd/misc.c index 60e7ac62c917..1e2076a53bed 100644 --- a/fs/ksmbd/misc.c +++ b/fs/ksmbd/misc.c @@ -158,19 +158,41 @@ out: * Return : windows path string or error */ -char *convert_to_nt_pathname(char *filename) +char *convert_to_nt_pathname(struct ksmbd_share_config *share, + struct path *path) { - char *ab_pathname; + char *pathname, *ab_pathname, *nt_pathname; + int share_path_len = share->path_sz; - if (strlen(filename) == 0) - filename = "\\"; + pathname = kmalloc(PATH_MAX, GFP_KERNEL); + if (!pathname) + return ERR_PTR(-EACCES); - ab_pathname = kstrdup(filename, GFP_KERNEL); - if (!ab_pathname) - return NULL; + ab_pathname = d_path(path, pathname, PATH_MAX); + if (IS_ERR(ab_pathname)) { + nt_pathname = ERR_PTR(-EACCES); + goto free_pathname; + } + + if (strncmp(ab_pathname, share->path, share_path_len)) { + nt_pathname = ERR_PTR(-EACCES); + goto free_pathname; + } + + nt_pathname = kzalloc(strlen(&ab_pathname[share_path_len]) + 2, GFP_KERNEL); + if (!nt_pathname) { + nt_pathname = ERR_PTR(-ENOMEM); + goto free_pathname; + } + if (ab_pathname[share_path_len] == '\0') + strcpy(nt_pathname, "/"); + strcat(nt_pathname, &ab_pathname[share_path_len]); + + ksmbd_conv_path_to_windows(nt_pathname); - ksmbd_conv_path_to_windows(ab_pathname); - return ab_pathname; +free_pathname: + kfree(pathname); + return nt_pathname; } int get_nlink(struct kstat *st) diff --git a/fs/ksmbd/misc.h b/fs/ksmbd/misc.h index 253366bd0951..aae2a252945f 100644 --- a/fs/ksmbd/misc.h +++ b/fs/ksmbd/misc.h @@ -14,7 +14,8 @@ struct ksmbd_file; int match_pattern(const char *str, size_t len, const char *pattern); int ksmbd_validate_filename(char *filename); int parse_stream_name(char *filename, char **stream_name, int *s_type); -char *convert_to_nt_pathname(char *filename); +char *convert_to_nt_pathname(struct ksmbd_share_config *share, + struct path *path); int get_nlink(struct kstat *st); void ksmbd_conv_path_to_unix(char *path); void ksmbd_strip_last_slash(char *path); diff --git a/fs/ksmbd/oplock.c b/fs/ksmbd/oplock.c index 23871b18a429..8b5560574d4c 100644 --- a/fs/ksmbd/oplock.c +++ b/fs/ksmbd/oplock.c @@ -1694,33 +1694,3 @@ out: read_unlock(&lease_list_lock); return ret_op; } - -int smb2_check_durable_oplock(struct ksmbd_file *fp, - struct lease_ctx_info *lctx, char *name) -{ - struct oplock_info *opinfo = opinfo_get(fp); - int ret = 0; - - if (opinfo && opinfo->is_lease) { - if (!lctx) { - pr_err("open does not include lease\n"); - ret = -EBADF; - goto out; - } - if (memcmp(opinfo->o_lease->lease_key, lctx->lease_key, - SMB2_LEASE_KEY_SIZE)) { - pr_err("invalid lease key\n"); - ret = -EBADF; - goto out; - } - if (name && strcmp(fp->filename, name)) { - pr_err("invalid name reconnect %s\n", name); - ret = -EINVAL; - goto out; - } - } -out: - if (opinfo) - opinfo_put(opinfo); - return ret; -} diff --git a/fs/ksmbd/oplock.h b/fs/ksmbd/oplock.h index 0cf7a2b5bbc0..09753448f779 100644 --- a/fs/ksmbd/oplock.h +++ b/fs/ksmbd/oplock.h @@ -124,6 +124,4 @@ struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn, int find_same_lease_key(struct ksmbd_session *sess, struct ksmbd_inode *ci, struct lease_ctx_info *lctx); void destroy_lease_table(struct ksmbd_conn *conn); -int smb2_check_durable_oplock(struct ksmbd_file *fp, - struct lease_ctx_info *lctx, char *name); #endif /* __KSMBD_OPLOCK_H */ diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 3bf6c56c654c..16c803a9d996 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -11,6 +11,7 @@ #include <linux/statfs.h> #include <linux/ethtool.h> #include <linux/falloc.h> +#include <linux/mount.h> #include "glob.h" #include "smbfsctl.h" @@ -2918,7 +2919,6 @@ int smb2_open(struct ksmbd_work *work) goto err_out; } - fp->filename = name; fp->cdoption = req->CreateDisposition; fp->daccess = daccess; fp->saccess = req->ShareAccess; @@ -3270,14 +3270,13 @@ err_out1: if (!rsp->hdr.Status) rsp->hdr.Status = STATUS_UNEXPECTED_IO_ERROR; - if (!fp || !fp->filename) - kfree(name); if (fp) ksmbd_fd_put(work, fp); smb2_set_err_rsp(work); ksmbd_debug(SMB, "Error response: %x\n", rsp->hdr.Status); } + kfree(name); kfree(lc); return 0; @@ -3895,8 +3894,6 @@ int smb2_query_dir(struct ksmbd_work *work) ksmbd_debug(SMB, "Search pattern is %s\n", srch_ptr); } - ksmbd_debug(SMB, "Directory name is %s\n", dir_fp->filename); - if (srch_flag & SMB2_REOPEN || srch_flag & SMB2_RESTART_SCANS) { ksmbd_debug(SMB, "Restart directory scan\n"); generic_file_llseek(dir_fp->filp, 0, SEEK_SET); @@ -4390,9 +4387,9 @@ static int get_file_all_info(struct ksmbd_work *work, return -EACCES; } - filename = convert_to_nt_pathname(fp->filename); - if (!filename) - return -ENOMEM; + filename = convert_to_nt_pathname(work->tcon->share_conf, &fp->filp->f_path); + if (IS_ERR(filename)) + return PTR_ERR(filename); inode = file_inode(fp->filp); generic_fillattr(file_mnt_user_ns(fp->filp), inode, &stat); @@ -4999,15 +4996,17 @@ static int smb2_get_info_filesystem(struct ksmbd_work *work, case FS_SECTOR_SIZE_INFORMATION: { struct smb3_fs_ss_info *info; + unsigned int sector_size = + min_t(unsigned int, path.mnt->mnt_sb->s_blocksize, 4096); info = (struct smb3_fs_ss_info *)(rsp->Buffer); - info->LogicalBytesPerSector = cpu_to_le32(stfs.f_bsize); + info->LogicalBytesPerSector = cpu_to_le32(sector_size); info->PhysicalBytesPerSectorForAtomicity = - cpu_to_le32(stfs.f_bsize); - info->PhysicalBytesPerSectorForPerf = cpu_to_le32(stfs.f_bsize); + cpu_to_le32(sector_size); + info->PhysicalBytesPerSectorForPerf = cpu_to_le32(sector_size); info->FSEffPhysicalBytesPerSectorForAtomicity = - cpu_to_le32(stfs.f_bsize); + cpu_to_le32(sector_size); info->Flags = cpu_to_le32(SSINFO_FLAGS_ALIGNED_DEVICE | SSINFO_FLAGS_PARTITION_ALIGNED_ON_DEVICE); info->ByteOffsetForSectorAlignment = 0; @@ -5683,8 +5682,7 @@ static int set_file_allocation_info(struct ksmbd_work *work, size = i_size_read(inode); rc = ksmbd_vfs_truncate(work, fp, alloc_blks * 512); if (rc) { - pr_err("truncate failed! filename : %s, err %d\n", - fp->filename, rc); + pr_err("truncate failed!, err %d\n", rc); return rc; } if (size < alloc_blks * 512) @@ -5714,12 +5712,10 @@ static int set_end_of_file_info(struct ksmbd_work *work, struct ksmbd_file *fp, * truncated range. */ if (inode->i_sb->s_magic != MSDOS_SUPER_MAGIC) { - ksmbd_debug(SMB, "filename : %s truncated to newsize %lld\n", - fp->filename, newsize); + ksmbd_debug(SMB, "truncated to newsize %lld\n", newsize); rc = ksmbd_vfs_truncate(work, fp, newsize); if (rc) { - ksmbd_debug(SMB, "truncate failed! filename : %s err %d\n", - fp->filename, rc); + ksmbd_debug(SMB, "truncate failed!, err %d\n", rc); if (rc != -EAGAIN) rc = -EBADF; return rc; @@ -5765,8 +5761,10 @@ static int set_rename_info(struct ksmbd_work *work, struct ksmbd_file *fp, if (parent_fp) { if (parent_fp->daccess & FILE_DELETE_LE) { pr_err("parent dir is opened with delete access\n"); + ksmbd_fd_put(work, parent_fp); return -ESHARE; } + ksmbd_fd_put(work, parent_fp); } next: return smb2_rename(work, fp, user_ns, rename_info, diff --git a/fs/ksmbd/vfs.c b/fs/ksmbd/vfs.c index 9cebb6ba555b..dcdd07c6efff 100644 --- a/fs/ksmbd/vfs.c +++ b/fs/ksmbd/vfs.c @@ -398,8 +398,7 @@ int ksmbd_vfs_read(struct ksmbd_work *work, struct ksmbd_file *fp, size_t count, nbytes = kernel_read(filp, rbuf, count, pos); if (nbytes < 0) { - pr_err("smb read failed for (%s), err = %zd\n", - fp->filename, nbytes); + pr_err("smb read failed, err = %zd\n", nbytes); return nbytes; } @@ -875,8 +874,7 @@ int ksmbd_vfs_truncate(struct ksmbd_work *work, err = vfs_truncate(&filp->f_path, size); if (err) - pr_err("truncate failed for filename : %s err %d\n", - fp->filename, err); + pr_err("truncate failed, err %d\n", err); return err; } diff --git a/fs/ksmbd/vfs_cache.c b/fs/ksmbd/vfs_cache.c index 29c1db66bd0f..c4d59d2735f0 100644 --- a/fs/ksmbd/vfs_cache.c +++ b/fs/ksmbd/vfs_cache.c @@ -328,7 +328,6 @@ static void __ksmbd_close_fd(struct ksmbd_file_table *ft, struct ksmbd_file *fp) kfree(smb_lock); } - kfree(fp->filename); if (ksmbd_stream_fd(fp)) kfree(fp->stream.name); kmem_cache_free(filp_cache, fp); @@ -497,6 +496,7 @@ struct ksmbd_file *ksmbd_lookup_fd_inode(struct inode *inode) list_for_each_entry(lfp, &ci->m_fp_list, node) { if (inode == file_inode(lfp->filp)) { atomic_dec(&ci->m_count); + lfp = ksmbd_fp_get(lfp); read_unlock(&ci->m_lock); return lfp; } diff --git a/fs/ksmbd/vfs_cache.h b/fs/ksmbd/vfs_cache.h index 36239ce31afd..fcb13413fa8d 100644 --- a/fs/ksmbd/vfs_cache.h +++ b/fs/ksmbd/vfs_cache.h @@ -62,7 +62,6 @@ struct ksmbd_inode { struct ksmbd_file { struct file *filp; - char *filename; u64 persistent_id; u64 volatile_id; diff --git a/fs/namei.c b/fs/namei.c index 3f1829b3ab5b..509657fdf4f5 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3673,18 +3673,14 @@ static struct dentry *filename_create(int dfd, struct filename *name, { struct dentry *dentry = ERR_PTR(-EEXIST); struct qstr last; + bool want_dir = lookup_flags & LOOKUP_DIRECTORY; + unsigned int reval_flag = lookup_flags & LOOKUP_REVAL; + unsigned int create_flags = LOOKUP_CREATE | LOOKUP_EXCL; int type; int err2; int error; - bool is_dir = (lookup_flags & LOOKUP_DIRECTORY); - /* - * Note that only LOOKUP_REVAL and LOOKUP_DIRECTORY matter here. Any - * other flags passed in are ignored! - */ - lookup_flags &= LOOKUP_REVAL; - - error = filename_parentat(dfd, name, lookup_flags, path, &last, &type); + error = filename_parentat(dfd, name, reval_flag, path, &last, &type); if (error) return ERR_PTR(error); @@ -3698,11 +3694,13 @@ static struct dentry *filename_create(int dfd, struct filename *name, /* don't fail immediately if it's r/o, at least try to report other errors */ err2 = mnt_want_write(path->mnt); /* - * Do the final lookup. + * Do the final lookup. Suppress 'create' if there is a trailing + * '/', and a directory wasn't requested. */ - lookup_flags |= LOOKUP_CREATE | LOOKUP_EXCL; + if (last.name[last.len] && !want_dir) + create_flags = 0; inode_lock_nested(path->dentry->d_inode, I_MUTEX_PARENT); - dentry = __lookup_hash(&last, path->dentry, lookup_flags); + dentry = __lookup_hash(&last, path->dentry, reval_flag | create_flags); if (IS_ERR(dentry)) goto unlock; @@ -3716,7 +3714,7 @@ static struct dentry *filename_create(int dfd, struct filename *name, * all is fine. Let's be bastards - you had / on the end, you've * been asking for (non-existent) directory. -ENOENT for you. */ - if (unlikely(!is_dir && last.name[last.len])) { + if (unlikely(!create_flags)) { error = -ENOENT; goto fail; } diff --git a/fs/namespace.c b/fs/namespace.c index a0a36bfa3aa0..afe2b64b14f1 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -4058,10 +4058,22 @@ static int mount_setattr_prepare(struct mount_kattr *kattr, struct mount *mnt) if (err) { struct mount *p; - for (p = mnt; p != m; p = next_mnt(p, mnt)) { + /* + * If we had to call mnt_hold_writers() MNT_WRITE_HOLD will + * be set in @mnt_flags. The loop unsets MNT_WRITE_HOLD for all + * mounts and needs to take care to include the first mount. + */ + for (p = mnt; p; p = next_mnt(p, mnt)) { /* If we had to hold writers unblock them. */ if (p->mnt.mnt_flags & MNT_WRITE_HOLD) mnt_unhold_writers(p); + + /* + * We're done once the first mount we changed got + * MNT_WRITE_HOLD unset. + */ + if (p == m) + break; } } return err; diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index c08882f5867b..2c1b027774d4 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -237,6 +237,13 @@ nfsd_file_check_write_error(struct nfsd_file *nf) } static void +nfsd_file_flush(struct nfsd_file *nf) +{ + if (nf->nf_file && vfs_fsync(nf->nf_file, 1) != 0) + nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id)); +} + +static void nfsd_file_do_unhash(struct nfsd_file *nf) { lockdep_assert_held(&nfsd_file_hashtbl[nf->nf_hashval].nfb_lock); @@ -295,19 +302,15 @@ nfsd_file_put_noref(struct nfsd_file *nf) void nfsd_file_put(struct nfsd_file *nf) { - bool is_hashed; - set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags); - if (refcount_read(&nf->nf_ref) > 2 || !nf->nf_file) { + if (test_bit(NFSD_FILE_HASHED, &nf->nf_flags) == 0) { + nfsd_file_flush(nf); nfsd_file_put_noref(nf); - return; + } else { + nfsd_file_put_noref(nf); + if (nf->nf_file) + nfsd_file_schedule_laundrette(); } - - filemap_flush(nf->nf_file->f_mapping); - is_hashed = test_bit(NFSD_FILE_HASHED, &nf->nf_flags) != 0; - nfsd_file_put_noref(nf); - if (is_hashed) - nfsd_file_schedule_laundrette(); if (atomic_long_read(&nfsd_filecache_count) >= NFSD_FILE_LRU_LIMIT) nfsd_file_gc(); } @@ -328,6 +331,7 @@ nfsd_file_dispose_list(struct list_head *dispose) while(!list_empty(dispose)) { nf = list_first_entry(dispose, struct nfsd_file, nf_lru); list_del(&nf->nf_lru); + nfsd_file_flush(nf); nfsd_file_put_noref(nf); } } @@ -341,6 +345,7 @@ nfsd_file_dispose_list_sync(struct list_head *dispose) while(!list_empty(dispose)) { nf = list_first_entry(dispose, struct nfsd_file, nf_lru); list_del(&nf->nf_lru); + nfsd_file_flush(nf); if (!refcount_dec_and_test(&nf->nf_ref)) continue; if (nfsd_file_free(nf)) diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 367551bddfc6..b5760801d377 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -249,34 +249,34 @@ nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, struct xdr_stream *xdr) int w; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; if (dentry == NULL || d_really_is_negative(dentry)) - return 1; + return true; inode = d_inode(dentry); if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->mask) < 0) - return 0; + return false; rqstp->rq_res.page_len = w = nfsacl_size( (resp->mask & NFS_ACL) ? resp->acl_access : NULL, (resp->mask & NFS_DFACL) ? resp->acl_default : NULL); while (w > 0) { if (!*(rqstp->rq_next_page++)) - return 1; + return true; w -= PAGE_SIZE; } if (!nfs_stream_encode_acl(xdr, inode, resp->acl_access, resp->mask & NFS_ACL, 0)) - return 0; + return false; if (!nfs_stream_encode_acl(xdr, inode, resp->acl_default, resp->mask & NFS_DFACL, NFS_ACL_DEFAULT)) - return 0; + return false; - return 1; + return true; } /* ACCESS */ @@ -286,17 +286,17 @@ nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, struct xdr_stream *xdr) struct nfsd3_accessres *resp = rqstp->rq_resp; if (!svcxdr_encode_stat(xdr, resp->status)) - return 0; + return false; switch (resp->status) { case nfs_ok: if (!svcxdr_encode_fattr(rqstp, xdr, &resp->fh, &resp->stat)) - return 0; + return false; if (xdr_stream_encode_u32(xdr, resp->access) < 0) - return 0; + return false; break; } - return 1; + return true; } /* diff --git a/fs/pipe.c b/fs/pipe.c index 9648ac15164a..e140ea150bbb 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -804,7 +804,7 @@ struct pipe_inode_info *alloc_pipe_info(void) if (too_many_pipe_buffers_hard(user_bufs) && pipe_is_unprivileged_user()) goto out_revert_acct; - pipe->bufs = kvcalloc(pipe_bufs, sizeof(struct pipe_buffer), + pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), GFP_KERNEL_ACCOUNT); if (pipe->bufs) { @@ -849,7 +849,7 @@ void free_pipe_info(struct pipe_inode_info *pipe) #endif if (pipe->tmp_page) __free_page(pipe->tmp_page); - kvfree(pipe->bufs); + kfree(pipe->bufs); kfree(pipe); } @@ -1264,7 +1264,8 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) if (nr_slots < n) return -EBUSY; - bufs = kvcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT); + bufs = kcalloc(nr_slots, sizeof(*bufs), + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) return -ENOMEM; @@ -1291,7 +1292,7 @@ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) head = n; tail = 0; - kvfree(pipe->bufs); + kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; if (pipe->max_usage > nr_slots) diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 80acb6885cf9..962d32468eb4 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -759,9 +759,14 @@ static void posix_acl_fix_xattr_userns( } void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { struct user_namespace *user_ns = current_user_ns(); + + /* Leave ids untouched on non-idmapped mounts. */ + if (no_idmapping(mnt_userns, i_user_ns(inode))) + mnt_userns = &init_user_ns; if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns)) return; posix_acl_fix_xattr_userns(&init_user_ns, user_ns, mnt_userns, value, @@ -769,9 +774,14 @@ void posix_acl_fix_xattr_from_user(struct user_namespace *mnt_userns, } void posix_acl_fix_xattr_to_user(struct user_namespace *mnt_userns, + struct inode *inode, void *value, size_t size) { struct user_namespace *user_ns = current_user_ns(); + + /* Leave ids untouched on non-idmapped mounts. */ + if (no_idmapping(mnt_userns, i_user_ns(inode))) + mnt_userns = &init_user_ns; if ((user_ns == &init_user_ns) && (mnt_userns == &init_user_ns)) return; posix_acl_fix_xattr_userns(user_ns, &init_user_ns, mnt_userns, value, diff --git a/fs/stat.c b/fs/stat.c index 7f734be0e57e..5c2c94464e8b 100644 --- a/fs/stat.c +++ b/fs/stat.c @@ -348,9 +348,6 @@ SYSCALL_DEFINE2(fstat, unsigned int, fd, struct __old_kernel_stat __user *, stat # define choose_32_64(a,b) b #endif -#define valid_dev(x) choose_32_64(old_valid_dev(x),true) -#define encode_dev(x) choose_32_64(old_encode_dev,new_encode_dev)(x) - #ifndef INIT_STRUCT_STAT_PADDING # define INIT_STRUCT_STAT_PADDING(st) memset(&st, 0, sizeof(st)) #endif @@ -359,7 +356,9 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) { struct stat tmp; - if (!valid_dev(stat->dev) || !valid_dev(stat->rdev)) + if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) + return -EOVERFLOW; + if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; #if BITS_PER_LONG == 32 if (stat->size > MAX_NON_LFS) @@ -367,7 +366,7 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) #endif INIT_STRUCT_STAT_PADDING(tmp); - tmp.st_dev = encode_dev(stat->dev); + tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; @@ -377,7 +376,7 @@ static int cp_new_stat(struct kstat *stat, struct stat __user *statbuf) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); - tmp.st_rdev = encode_dev(stat->rdev); + tmp.st_rdev = new_encode_dev(stat->rdev); tmp.st_size = stat->size; tmp.st_atime = stat->atime.tv_sec; tmp.st_mtime = stat->mtime.tv_sec; @@ -665,11 +664,13 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) { struct compat_stat tmp; - if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev)) + if (sizeof(tmp.st_dev) < 4 && !old_valid_dev(stat->dev)) + return -EOVERFLOW; + if (sizeof(tmp.st_rdev) < 4 && !old_valid_dev(stat->rdev)) return -EOVERFLOW; memset(&tmp, 0, sizeof(tmp)); - tmp.st_dev = old_encode_dev(stat->dev); + tmp.st_dev = new_encode_dev(stat->dev); tmp.st_ino = stat->ino; if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) return -EOVERFLOW; @@ -679,7 +680,7 @@ static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) return -EOVERFLOW; SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); - tmp.st_rdev = old_encode_dev(stat->rdev); + tmp.st_rdev = new_encode_dev(stat->rdev); if ((u64) stat->size > MAX_NON_LFS) return -EOVERFLOW; tmp.st_size = stat->size; diff --git a/fs/xattr.c b/fs/xattr.c index 5c8c5175b385..998045165916 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -569,7 +569,8 @@ setxattr(struct user_namespace *mnt_userns, struct dentry *d, } if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) - posix_acl_fix_xattr_from_user(mnt_userns, kvalue, size); + posix_acl_fix_xattr_from_user(mnt_userns, d_inode(d), + kvalue, size); } error = vfs_setxattr(mnt_userns, d, kname, kvalue, size, flags); @@ -667,7 +668,8 @@ getxattr(struct user_namespace *mnt_userns, struct dentry *d, if (error > 0) { if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) - posix_acl_fix_xattr_to_user(mnt_userns, kvalue, error); + posix_acl_fix_xattr_to_user(mnt_userns, d_inode(d), + kvalue, error); if (size && copy_to_user(value, kvalue, error)) error = -EFAULT; } else if (error == -ERANGE && size >= XATTR_SIZE_MAX) { |