diff options
Diffstat (limited to 'fs')
118 files changed, 1590 insertions, 1165 deletions
diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index 50f7f3f6b55e..e00cf8109b3f 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -35,10 +35,12 @@ ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name, return retval; } if (attr_size > buffer_size) { - if (!buffer_size) /* request to get the attr_size */ - retval = attr_size; - else + if (buffer_size) retval = -ERANGE; + else if (attr_size > SSIZE_MAX) + retval = -EOVERFLOW; + else /* request to get the attr_size */ + retval = attr_size; } else { iov_iter_truncate(&to, attr_size); retval = p9_client_read(attr_fid, 0, &to, &err); @@ -183,10 +185,6 @@ static struct xattr_handler v9fs_xattr_security_handler = { const struct xattr_handler *v9fs_xattr_handlers[] = { &v9fs_xattr_user_handler, &v9fs_xattr_trusted_handler, -#ifdef CONFIG_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif #ifdef CONFIG_9P_FS_SECURITY &v9fs_xattr_security_handler, #endif diff --git a/fs/attr.c b/fs/attr.c index aca9ff7aed33..d60dc1edb526 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -47,6 +47,7 @@ int setattr_should_drop_sgid(struct mnt_idmap *idmap, return ATTR_KILL_SGID; return 0; } +EXPORT_SYMBOL(setattr_should_drop_sgid); /** * setattr_should_drop_suidgid - determine whether the set{g,u}id bit needs to diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index 90e40d5ceccd..e54f0884802a 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -1921,8 +1921,7 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr, level = -1; ULIST_ITER_INIT(&uiter); while (1) { - bool is_shared; - bool cached; + const unsigned long prev_ref_count = ctx->refs.nnodes; walk_ctx.bytenr = bytenr; ret = find_parent_nodes(&walk_ctx, &shared); @@ -1940,21 +1939,36 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr, ret = 0; /* - * If our data extent was not directly shared (without multiple - * reference items), than it might have a single reference item - * with a count > 1 for the same offset, which means there are 2 - * (or more) file extent items that point to the data extent - - * this happens when a file extent item needs to be split and - * then one item gets moved to another leaf due to a b+tree leaf - * split when inserting some item. In this case the file extent - * items may be located in different leaves and therefore some - * of the leaves may be referenced through shared subtrees while - * others are not. Since our extent buffer cache only works for - * a single path (by far the most common case and simpler to - * deal with), we can not use it if we have multiple leaves - * (which implies multiple paths). + * More than one extent buffer (bytenr) may have been added to + * the ctx->refs ulist, in which case we have to check multiple + * tree paths in case the first one is not shared, so we can not + * use the path cache which is made for a single path. Multiple + * extent buffers at the current level happen when: + * + * 1) level -1, the data extent: If our data extent was not + * directly shared (without multiple reference items), then + * it might have a single reference item with a count > 1 for + * the same offset, which means there are 2 (or more) file + * extent items that point to the data extent - this happens + * when a file extent item needs to be split and then one + * item gets moved to another leaf due to a b+tree leaf split + * when inserting some item. In this case the file extent + * items may be located in different leaves and therefore + * some of the leaves may be referenced through shared + * subtrees while others are not. Since our extent buffer + * cache only works for a single path (by far the most common + * case and simpler to deal with), we can not use it if we + * have multiple leaves (which implies multiple paths). + * + * 2) level >= 0, a tree node/leaf: We can have a mix of direct + * and indirect references on a b+tree node/leaf, so we have + * to check multiple paths, and the extent buffer (the + * current bytenr) may be shared or not. One example is + * during relocation as we may get a shared tree block ref + * (direct ref) and a non-shared tree block ref (indirect + * ref) for the same node/leaf. */ - if (level == -1 && ctx->refs.nnodes > 1) + if ((ctx->refs.nnodes - prev_ref_count) > 1) ctx->use_path_cache = false; if (level >= 0) @@ -1964,12 +1978,17 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr, if (!node) break; bytenr = node->val; - level++; - cached = lookup_backref_shared_cache(ctx, root, bytenr, level, - &is_shared); - if (cached) { - ret = (is_shared ? 1 : 0); - break; + if (ctx->use_path_cache) { + bool is_shared; + bool cached; + + level++; + cached = lookup_backref_shared_cache(ctx, root, bytenr, + level, &is_shared); + if (cached) { + ret = (is_shared ? 1 : 0); + break; + } } shared.share_count = 0; shared.have_delayed_delete_refs = false; @@ -1977,6 +1996,28 @@ int btrfs_is_data_extent_shared(struct btrfs_inode *inode, u64 bytenr, } /* + * If the path cache is disabled, then it means at some tree level we + * got multiple parents due to a mix of direct and indirect backrefs or + * multiple leaves with file extent items pointing to the same data + * extent. We have to invalidate the cache and cache only the sharedness + * result for the levels where we got only one node/reference. + */ + if (!ctx->use_path_cache) { + int i = 0; + + level--; + if (ret >= 0 && level >= 0) { + bytenr = ctx->path_cache_entries[level].bytenr; + ctx->use_path_cache = true; + store_backref_shared_cache(ctx, root, bytenr, level, ret); + i = level + 1; + } + + for ( ; i < BTRFS_MAX_LEVEL; i++) + ctx->path_cache_entries[i].bytenr = 0; + } + + /* * Cache the sharedness result for the data extent if we know our inode * has more than 1 file extent item that refers to the data extent. */ diff --git a/fs/btrfs/discard.c b/fs/btrfs/discard.c index 317aeff6c1da..a6d77fe41e1a 100644 --- a/fs/btrfs/discard.c +++ b/fs/btrfs/discard.c @@ -56,11 +56,9 @@ #define BTRFS_DISCARD_DELAY (120ULL * NSEC_PER_SEC) #define BTRFS_DISCARD_UNUSED_DELAY (10ULL * NSEC_PER_SEC) -/* Target completion latency of discarding all discardable extents */ -#define BTRFS_DISCARD_TARGET_MSEC (6 * 60 * 60UL * MSEC_PER_SEC) #define BTRFS_DISCARD_MIN_DELAY_MSEC (1UL) #define BTRFS_DISCARD_MAX_DELAY_MSEC (1000UL) -#define BTRFS_DISCARD_MAX_IOPS (10U) +#define BTRFS_DISCARD_MAX_IOPS (1000U) /* Monotonically decreasing minimum length filters after index 0 */ static int discard_minlen[BTRFS_NR_DISCARD_LISTS] = { @@ -577,6 +575,7 @@ void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl) s32 discardable_extents; s64 discardable_bytes; u32 iops_limit; + unsigned long min_delay = BTRFS_DISCARD_MIN_DELAY_MSEC; unsigned long delay; discardable_extents = atomic_read(&discard_ctl->discardable_extents); @@ -607,13 +606,19 @@ void btrfs_discard_calc_delay(struct btrfs_discard_ctl *discard_ctl) } iops_limit = READ_ONCE(discard_ctl->iops_limit); - if (iops_limit) + + if (iops_limit) { delay = MSEC_PER_SEC / iops_limit; - else - delay = BTRFS_DISCARD_TARGET_MSEC / discardable_extents; + } else { + /* + * Unset iops_limit means go as fast as possible, so allow a + * delay of 0. + */ + delay = 0; + min_delay = 0; + } - delay = clamp(delay, BTRFS_DISCARD_MIN_DELAY_MSEC, - BTRFS_DISCARD_MAX_DELAY_MSEC); + delay = clamp(delay, min_delay, BTRFS_DISCARD_MAX_DELAY_MSEC); discard_ctl->delay_ms = delay; spin_unlock(&discard_ctl->lock); diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index b53f0e30ce2b..9e1596bb208d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2250,6 +2250,20 @@ static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type) fs_info->csum_shash = csum_shash; + /* + * Check if the checksum implementation is a fast accelerated one. + * As-is this is a bit of a hack and should be replaced once the csum + * implementations provide that information themselves. + */ + switch (csum_type) { + case BTRFS_CSUM_TYPE_CRC32: + if (!strstr(crypto_shash_driver_name(csum_shash), "generic")) + set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); + break; + default: + break; + } + btrfs_info(fs_info, "using %s (%s) checksum algorithm", btrfs_super_csum_name(csum_type), crypto_shash_driver_name(csum_shash)); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 5cc5a1faaef5..f649647392e0 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -3730,10 +3730,15 @@ static int check_direct_read(struct btrfs_fs_info *fs_info, if (!iter_is_iovec(iter)) return 0; - for (seg = 0; seg < iter->nr_segs; seg++) - for (i = seg + 1; i < iter->nr_segs; i++) - if (iter->iov[seg].iov_base == iter->iov[i].iov_base) + for (seg = 0; seg < iter->nr_segs; seg++) { + for (i = seg + 1; i < iter->nr_segs; i++) { + const struct iovec *iov1 = iter_iov(iter) + seg; + const struct iovec *iov2 = iter_iov(iter) + i; + + if (iov1->iov_base == iov2->iov_base) return -EINVAL; + } + } return 0; } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a0ef1a1784c7..ba769a1eb87a 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -3732,7 +3732,9 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg) } /* update qgroup status and info */ + mutex_lock(&fs_info->qgroup_ioctl_lock); err = btrfs_run_qgroups(trans); + mutex_unlock(&fs_info->qgroup_ioctl_lock); if (err < 0) btrfs_handle_fs_error(fs_info, err, "failed to update qgroup status and info"); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 52a7d2fa2284..f41da7ac360d 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2828,13 +2828,22 @@ cleanup: } /* - * called from commit_transaction. Writes all changed qgroups to disk. + * Writes all changed qgroups to disk. + * Called by the transaction commit path and the qgroup assign ioctl. */ int btrfs_run_qgroups(struct btrfs_trans_handle *trans) { struct btrfs_fs_info *fs_info = trans->fs_info; int ret = 0; + /* + * In case we are called from the qgroup assign ioctl, assert that we + * are holding the qgroup_ioctl_lock, otherwise we can race with a quota + * disable operation (ioctl) and access a freed quota root. + */ + if (trans->transaction->state != TRANS_STATE_COMMIT_DOING) + lockdep_assert_held(&fs_info->qgroup_ioctl_lock); + if (!fs_info->quota_root) return ret; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 581845bc206a..366fb4cde145 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1516,8 +1516,6 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type, shrinker_debugfs_rename(&s->s_shrink, "sb-%s:%s", fs_type->name, s->s_id); btrfs_sb(s)->bdev_holder = fs_type; - if (!strstr(crc32c_impl(), "generic")) - set_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags); error = btrfs_fill_super(s, fs_devices, data); } if (!error) @@ -1631,6 +1629,8 @@ static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info, btrfs_workqueue_set_max(fs_info->hipri_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size); + workqueue_set_max_active(fs_info->endio_workers, new_pool_size); + workqueue_set_max_active(fs_info->endio_meta_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->endio_write_workers, new_pool_size); btrfs_workqueue_set_max(fs_info->endio_freespace_worker, new_pool_size); btrfs_workqueue_set_max(fs_info->delayed_workers, new_pool_size); diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c index 18329ebcb1cb..b8d5b1fa9a03 100644 --- a/fs/btrfs/transaction.c +++ b/fs/btrfs/transaction.c @@ -2035,7 +2035,20 @@ static void cleanup_transaction(struct btrfs_trans_handle *trans, int err) if (current->journal_info == trans) current->journal_info = NULL; - btrfs_scrub_cancel(fs_info); + + /* + * If relocation is running, we can't cancel scrub because that will + * result in a deadlock. Before relocating a block group, relocation + * pauses scrub, then starts and commits a transaction before unpausing + * scrub. If the transaction commit is being done by the relocation + * task or triggered by another task and the relocation task is waiting + * for the commit, and we end up here due to an error in the commit + * path, then calling btrfs_scrub_cancel() will deadlock, as we are + * asking for scrub to stop while having it asked to be paused higher + * above in relocation code. + */ + if (!test_bit(BTRFS_FS_RELOC_RUNNING, &fs_info->flags)) + btrfs_scrub_cancel(fs_info); kmem_cache_free(btrfs_trans_handle_cachep, trans); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 6d0124b6e79e..c6d592870400 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1366,8 +1366,17 @@ struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags, * So, we need to add a special mount option to scan for * later supers, using BTRFS_SUPER_MIRROR_MAX instead */ - flags |= FMODE_EXCL; + /* + * Avoid using flag |= FMODE_EXCL here, as the systemd-udev may + * initiate the device scan which may race with the user's mount + * or mkfs command, resulting in failure. + * Since the device scan is solely for reading purposes, there is + * no need for FMODE_EXCL. Additionally, the devices are read again + * during the mount process. It is ok to get some inconsistent + * values temporarily, as the device paths of the fsid are the only + * required information for assembling the volume. + */ bdev = blkdev_get_by_path(path, flags, holder); if (IS_ERR(bdev)) return ERR_CAST(bdev); @@ -3266,8 +3275,15 @@ int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset) btrfs_scrub_pause(fs_info); ret = btrfs_relocate_block_group(fs_info, chunk_offset); btrfs_scrub_continue(fs_info); - if (ret) + if (ret) { + /* + * If we had a transaction abort, stop all running scrubs. + * See transaction.c:cleanup_transaction() why we do it here. + */ + if (BTRFS_FS_ERROR(fs_info)) + btrfs_scrub_cancel(fs_info); return ret; + } block_group = btrfs_lookup_block_group(fs_info, chunk_offset); if (!block_group) diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c index 0ebeaf4e81f9..fc4b20c2688a 100644 --- a/fs/btrfs/xattr.c +++ b/fs/btrfs/xattr.c @@ -444,10 +444,6 @@ static const struct xattr_handler btrfs_btrfs_xattr_handler = { const struct xattr_handler *btrfs_xattr_handlers[] = { &btrfs_security_xattr_handler, -#ifdef CONFIG_BTRFS_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif &btrfs_trusted_xattr_handler, &btrfs_user_xattr_handler, &btrfs_btrfs_xattr_handler, diff --git a/fs/buffer.c b/fs/buffer.c index 9e1e2add541e..10390f53f3f5 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2581,7 +2581,7 @@ int block_truncate_page(struct address_space *mapping, struct inode *inode = mapping->host; struct page *page; struct buffer_head *bh; - int err; + int err = 0; blocksize = i_blocksize(inode); length = offset & (blocksize - 1); @@ -2594,9 +2594,8 @@ int block_truncate_page(struct address_space *mapping, iblock = (sector_t)index << (PAGE_SHIFT - inode->i_blkbits); page = grab_cache_page(mapping, index); - err = -ENOMEM; if (!page) - goto out; + return -ENOMEM; if (!page_has_buffers(page)) create_empty_buffers(page, blocksize, 0); @@ -2610,7 +2609,6 @@ int block_truncate_page(struct address_space *mapping, pos += blocksize; } - err = 0; if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); @@ -2634,12 +2632,11 @@ int block_truncate_page(struct address_space *mapping, zero_user(page, offset, length); mark_buffer_dirty(bh); - err = 0; unlock: unlock_page(page); put_page(page); -out: + return err; } EXPORT_SYMBOL(block_truncate_page); diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c index f65b07cc33a2..1fe1b62abebd 100644 --- a/fs/ceph/xattr.c +++ b/fs/ceph/xattr.c @@ -1411,10 +1411,6 @@ void ceph_release_acl_sec_ctx(struct ceph_acl_sec_ctx *as_ctx) * attributes are handled directly. */ const struct xattr_handler *ceph_xattr_handlers[] = { -#ifdef CONFIG_CEPH_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif &ceph_other_xattr_handler, NULL, }; diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c index cb40074feb3e..0329a907bdfe 100644 --- a/fs/cifs/cifs_dfs_ref.c +++ b/fs/cifs/cifs_dfs_ref.c @@ -171,8 +171,6 @@ static struct vfsmount *cifs_dfs_do_automount(struct path *path) mnt = ERR_CAST(full_path); goto out; } - - convert_delimiter(full_path, '/'); cifs_dbg(FYI, "%s: full_path: %s\n", __func__, full_path); tmp = *cur_ctx; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 71fe0a0a7992..415176b2cf32 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -124,7 +124,10 @@ extern const struct dentry_operations cifs_ci_dentry_ops; #ifdef CONFIG_CIFS_DFS_UPCALL extern struct vfsmount *cifs_dfs_d_automount(struct path *path); #else -#define cifs_dfs_d_automount NULL +static inline struct vfsmount *cifs_dfs_d_automount(struct path *path) +{ + return ERR_PTR(-EREMOTE); +} #endif /* Functions related to symlinks */ diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index 38a697eca305..9d963caec35c 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -71,7 +71,7 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) int rc; struct cifs_ses *ses; struct TCP_Server_Info *server; - struct nls_table *nls_codepage; + struct nls_table *nls_codepage = NULL; /* * SMBs NegProt, SessSetup, uLogoff do not have tcon yet so check for @@ -99,6 +99,7 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) } spin_unlock(&tcon->tc_lock); +again: rc = cifs_wait_for_server_reconnect(server, tcon->retry); if (rc) return rc; @@ -110,8 +111,7 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) } spin_unlock(&ses->chan_lock); - nls_codepage = load_nls_default(); - + mutex_lock(&ses->session_mutex); /* * Recheck after acquire mutex. If another thread is negotiating * and the server never sends an answer the socket will be closed @@ -120,29 +120,38 @@ cifs_reconnect_tcon(struct cifs_tcon *tcon, int smb_command) spin_lock(&server->srv_lock); if (server->tcpStatus == CifsNeedReconnect) { spin_unlock(&server->srv_lock); + mutex_unlock(&ses->session_mutex); + + if (tcon->retry) + goto again; rc = -EHOSTDOWN; goto out; } spin_unlock(&server->srv_lock); + nls_codepage = load_nls_default(); + /* * need to prevent multiple threads trying to simultaneously * reconnect the same SMB session */ + spin_lock(&ses->ses_lock); spin_lock(&ses->chan_lock); - if (!cifs_chan_needs_reconnect(ses, server)) { + if (!cifs_chan_needs_reconnect(ses, server) && + ses->ses_status == SES_GOOD) { spin_unlock(&ses->chan_lock); + spin_unlock(&ses->ses_lock); /* this means that we only need to tree connect */ if (tcon->need_reconnect) goto skip_sess_setup; - rc = -EHOSTDOWN; + mutex_unlock(&ses->session_mutex); goto out; } spin_unlock(&ses->chan_lock); + spin_unlock(&ses->ses_lock); - mutex_lock(&ses->session_mutex); rc = cifs_negotiate_protocol(0, ses, server); if (!rc) rc = cifs_setup_session(0, ses, server, nls_codepage); @@ -4373,8 +4382,13 @@ CIFSGetDFSRefer(const unsigned int xid, struct cifs_ses *ses, return -ENODEV; getDFSRetry: - rc = smb_init(SMB_COM_TRANSACTION2, 15, ses->tcon_ipc, (void **) &pSMB, - (void **) &pSMBr); + /* + * Use smb_init_no_reconnect() instead of smb_init() as + * CIFSGetDFSRefer() may be called from cifs_reconnect_tcon() and thus + * causing an infinite recursion. + */ + rc = smb_init_no_reconnect(SMB_COM_TRANSACTION2, 15, ses->tcon_ipc, + (void **)&pSMB, (void **)&pSMBr); if (rc) return rc; diff --git a/fs/cifs/dfs.h b/fs/cifs/dfs.h index 13f26e01f7b9..0b8cbf721fff 100644 --- a/fs/cifs/dfs.h +++ b/fs/cifs/dfs.h @@ -34,19 +34,33 @@ static inline int dfs_get_referral(struct cifs_mount_ctx *mnt_ctx, const char *p cifs_remap(cifs_sb), path, ref, tl); } +/* Return DFS full path out of a dentry set for automount */ static inline char *dfs_get_automount_devname(struct dentry *dentry, void *page) { struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb); struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb); struct TCP_Server_Info *server = tcon->ses->server; + size_t len; + char *s; if (unlikely(!server->origin_fullpath)) return ERR_PTR(-EREMOTE); - return __build_path_from_dentry_optional_prefix(dentry, page, - server->origin_fullpath, - strlen(server->origin_fullpath), - true); + s = dentry_path_raw(dentry, page, PATH_MAX); + if (IS_ERR(s)) + return s; + /* for root, we want "" */ + if (!s[1]) + s++; + + len = strlen(server->origin_fullpath); + if (s < (char *)page + len) + return ERR_PTR(-ENAMETOOLONG); + + s -= len; + memcpy(s, server->origin_fullpath, len); + convert_delimiter(s, '/'); + return s; } static inline void dfs_put_root_smb_sessions(struct list_head *head) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 6831a9949c43..b33d2e7b0f98 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4010,7 +4010,6 @@ static void collect_uncached_read_data(struct cifs_aio_ctx *ctx) { struct cifs_readdata *rdata, *tmp; - struct iov_iter *to = &ctx->iter; struct cifs_sb_info *cifs_sb; int rc; @@ -4076,9 +4075,6 @@ again: kref_put(&rdata->refcount, cifs_readdata_release); } - if (!ctx->direct_io) - ctx->total_len = ctx->len - iov_iter_count(to); - /* mask nodata case */ if (rc == -ENODATA) rc = 0; diff --git a/fs/cifs/fs_context.c b/fs/cifs/fs_context.c index 6d13f8207e96..ace11a1a7c8a 100644 --- a/fs/cifs/fs_context.c +++ b/fs/cifs/fs_context.c @@ -441,13 +441,14 @@ out: * but there are some bugs that prevent rename from working if there are * multiple delimiters. * - * Returns a sanitized duplicate of @path. The caller is responsible for - * cleaning up the original. + * Returns a sanitized duplicate of @path. @gfp indicates the GFP_* flags + * for kstrdup. + * The caller is responsible for freeing the original. */ #define IS_DELIM(c) ((c) == '/' || (c) == '\\') -static char *sanitize_path(char *path) +char *cifs_sanitize_prepath(char *prepath, gfp_t gfp) { - char *cursor1 = path, *cursor2 = path; + char *cursor1 = prepath, *cursor2 = prepath; /* skip all prepended delimiters */ while (IS_DELIM(*cursor1)) @@ -469,7 +470,7 @@ static char *sanitize_path(char *path) cursor2--; *(cursor2) = '\0'; - return kstrdup(path, GFP_KERNEL); + return kstrdup(prepath, gfp); } /* @@ -531,7 +532,7 @@ smb3_parse_devname(const char *devname, struct smb3_fs_context *ctx) if (!*pos) return 0; - ctx->prepath = sanitize_path(pos); + ctx->prepath = cifs_sanitize_prepath(pos, GFP_KERNEL); if (!ctx->prepath) return -ENOMEM; diff --git a/fs/cifs/fs_context.h b/fs/cifs/fs_context.h index 3de00e7127ec..f4eaf8558902 100644 --- a/fs/cifs/fs_context.h +++ b/fs/cifs/fs_context.h @@ -287,4 +287,7 @@ extern void smb3_update_mnt_flags(struct cifs_sb_info *cifs_sb); */ #define SMB3_MAX_DCLOSETIMEO (1 << 30) #define SMB3_DEF_DCLOSETIMEO (1 * HZ) /* even 1 sec enough to help eg open/write/close/open/read */ + +extern char *cifs_sanitize_prepath(char *prepath, gfp_t gfp); + #endif diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index b44fb51968bf..7f085ed2d866 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -1195,7 +1195,7 @@ int cifs_update_super_prepath(struct cifs_sb_info *cifs_sb, char *prefix) kfree(cifs_sb->prepath); if (prefix && *prefix) { - cifs_sb->prepath = kstrdup(prefix, GFP_ATOMIC); + cifs_sb->prepath = cifs_sanitize_prepath(prefix, GFP_ATOMIC); if (!cifs_sb->prepath) return -ENOMEM; diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index 6bd2aa6af18f..366f0c3b799b 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -310,7 +310,6 @@ out: case SMB2_READ: case SMB2_WRITE: case SMB2_LOCK: - case SMB2_IOCTL: case SMB2_QUERY_DIRECTORY: case SMB2_CHANGE_NOTIFY: case SMB2_QUERY_INFO: @@ -588,11 +587,15 @@ assemble_neg_contexts(struct smb2_negotiate_req *req, } +/* If invalid preauth context warn but use what we requested, SHA-512 */ static void decode_preauth_context(struct smb2_preauth_neg_context *ctxt) { unsigned int len = le16_to_cpu(ctxt->DataLength); - /* If invalid preauth context warn but use what we requested, SHA-512 */ + /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one HashAlgorithms member is accounted for. + */ if (len < MIN_PREAUTH_CTXT_DATA_LEN) { pr_warn_once("server sent bad preauth context\n"); return; @@ -611,7 +614,11 @@ static void decode_compress_ctx(struct TCP_Server_Info *server, { unsigned int len = le16_to_cpu(ctxt->DataLength); - /* sizeof compress context is a one element compression capbility struct */ + /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one CompressionAlgorithms member is accounted + * for. + */ if (len < 10) { pr_warn_once("server sent bad compression cntxt\n"); return; @@ -633,6 +640,11 @@ static int decode_encrypt_ctx(struct TCP_Server_Info *server, unsigned int len = le16_to_cpu(ctxt->DataLength); cifs_dbg(FYI, "decode SMB3.11 encryption neg context of len %d\n", len); + /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one Cipher flexible array member is accounted + * for. + */ if (len < MIN_ENCRYPT_CTXT_DATA_LEN) { pr_warn_once("server sent bad crypto ctxt len\n"); return -EINVAL; @@ -679,6 +691,11 @@ static void decode_signing_ctx(struct TCP_Server_Info *server, { unsigned int len = le16_to_cpu(pctxt->DataLength); + /* + * Caller checked that DataLength remains within SMB boundary. We still + * need to confirm that one SigningAlgorithms flexible array member is + * accounted for. + */ if ((len < 4) || (len > 16)) { pr_warn_once("server sent bad signing negcontext\n"); return; @@ -720,14 +737,19 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp, for (i = 0; i < ctxt_cnt; i++) { int clen; /* check that offset is not beyond end of SMB */ - if (len_of_ctxts == 0) - break; - if (len_of_ctxts < sizeof(struct smb2_neg_context)) break; pctx = (struct smb2_neg_context *)(offset + (char *)rsp); - clen = le16_to_cpu(pctx->DataLength); + clen = sizeof(struct smb2_neg_context) + + le16_to_cpu(pctx->DataLength); + /* + * 2.2.4 SMB2 NEGOTIATE Response + * Subsequent negotiate contexts MUST appear at the first 8-byte + * aligned offset following the previous negotiate context. + */ + if (i + 1 != ctxt_cnt) + clen = ALIGN(clen, 8); if (clen > len_of_ctxts) break; @@ -748,12 +770,10 @@ static int smb311_decode_neg_context(struct smb2_negotiate_rsp *rsp, else cifs_server_dbg(VFS, "unknown negcontext of type %d ignored\n", le16_to_cpu(pctx->ContextType)); - if (rc) break; - /* offsets must be 8 byte aligned */ - clen = ALIGN(clen, 8); - offset += clen + sizeof(struct smb2_neg_context); + + offset += clen; len_of_ctxts -= clen; } return rc; @@ -4160,10 +4180,12 @@ smb2_readv_callback(struct mid_q_entry *mid) struct smb2_hdr *shdr = (struct smb2_hdr *)rdata->iov[0].iov_base; struct cifs_credits credits = { .value = 0, .instance = 0 }; - struct smb_rqst rqst = { .rq_iov = &rdata->iov[1], - .rq_nvec = 1, - .rq_iter = rdata->iter, - .rq_iter_size = iov_iter_count(&rdata->iter), }; + struct smb_rqst rqst = { .rq_iov = &rdata->iov[1], .rq_nvec = 1 }; + + if (rdata->got_bytes) { + rqst.rq_iter = rdata->iter; + rqst.rq_iter_size = iov_iter_count(&rdata->iter); + }; WARN_ONCE(rdata->server != mid->server, "rdata server %p != mid server %p", diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index 50e762fa1a14..4ad5531686d8 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -487,9 +487,5 @@ const struct xattr_handler *cifs_xattr_handlers[] = { &smb3_ntsd_xattr_handler, /* alias for above since avoiding "cifs" */ &cifs_cifs_ntsd_full_xattr_handler, &smb3_ntsd_full_xattr_handler, /* alias for above since avoiding "cifs" */ -#ifdef CONFIG_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif NULL }; diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c index 4afcbbe63e68..18677cd4e62f 100644 --- a/fs/configfs/dir.c +++ b/fs/configfs/dir.c @@ -1599,12 +1599,6 @@ static int configfs_dir_close(struct inode *inode, struct file *file) return 0; } -/* Relationship between s_mode and the DT_xxx types */ -static inline unsigned char dt_type(struct configfs_dirent *sd) -{ - return (sd->s_mode >> 12) & 15; -} - static int configfs_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; @@ -1654,7 +1648,8 @@ static int configfs_readdir(struct file *file, struct dir_context *ctx) name = configfs_get_name(next); len = strlen(name); - if (!dir_emit(ctx, name, len, ino, dt_type(next))) + if (!dir_emit(ctx, name, len, ino, + fs_umode_to_dtype(next->s_mode))) return 0; spin_lock(&configfs_dirent_lock); @@ -781,6 +781,33 @@ out: return ret; } +static int __dax_clear_dirty_range(struct address_space *mapping, + pgoff_t start, pgoff_t end) +{ + XA_STATE(xas, &mapping->i_pages, start); + unsigned int scanned = 0; + void *entry; + + xas_lock_irq(&xas); + xas_for_each(&xas, entry, end) { + entry = get_unlocked_entry(&xas, 0); + xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); + xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); + put_unlocked_entry(&xas, entry, WAKE_NEXT); + + if (++scanned % XA_CHECK_SCHED) + continue; + + xas_pause(&xas); + xas_unlock_irq(&xas); + cond_resched(); + xas_lock_irq(&xas); + } + xas_unlock_irq(&xas); + + return 0; +} + /* * Delete DAX entry at @index from @mapping. Wait for it * to be unlocked before deleting it. @@ -1258,15 +1285,20 @@ static s64 dax_unshare_iter(struct iomap_iter *iter) /* don't bother with blocks that are not shared to start with */ if (!(iomap->flags & IOMAP_F_SHARED)) return length; - /* don't bother with holes or unwritten extents */ - if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN) - return length; id = dax_read_lock(); ret = dax_iomap_direct_access(iomap, pos, length, &daddr, NULL); if (ret < 0) goto out_unlock; + /* zero the distance if srcmap is HOLE or UNWRITTEN */ + if (srcmap->flags & IOMAP_F_SHARED || srcmap->type == IOMAP_UNWRITTEN) { + memset(daddr, 0, length); + dax_flush(iomap->dax_dev, daddr, length); + ret = length; + goto out_unlock; + } + ret = dax_iomap_direct_access(srcmap, pos, length, &saddr, NULL); if (ret < 0) goto out_unlock; @@ -1435,6 +1467,16 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi, * written by write(2) is visible in mmap. */ if (iomap->flags & IOMAP_F_NEW || cow) { + /* + * Filesystem allows CoW on non-shared extents. The src extents + * may have been mmapped with dirty mark before. To be able to + * invalidate its dax entries, we need to clear the dirty mark + * in advance. + */ + if (cow) + __dax_clear_dirty_range(iomi->inode->i_mapping, + pos >> PAGE_SHIFT, + (end - 1) >> PAGE_SHIFT); invalidate_inode_pages2_range(iomi->inode->i_mapping, pos >> PAGE_SHIFT, (end - 1) >> PAGE_SHIFT); @@ -2022,8 +2064,8 @@ int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff, while ((ret = iomap_iter(&src_iter, ops)) > 0 && (ret = iomap_iter(&dst_iter, ops)) > 0) { - compared = dax_range_compare_iter(&src_iter, &dst_iter, len, - same); + compared = dax_range_compare_iter(&src_iter, &dst_iter, + min(src_iter.len, dst_iter.len), same); if (compared < 0) return ret; src_iter.processed = dst_iter.processed = compared; diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 4f25015aa534..fe3db0eda8e4 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -72,24 +72,6 @@ static struct ctl_table pty_table[] = { {} }; -static struct ctl_table pty_kern_table[] = { - { - .procname = "pty", - .mode = 0555, - .child = pty_table, - }, - {} -}; - -static struct ctl_table pty_root_table[] = { - { - .procname = "kernel", - .mode = 0555, - .child = pty_kern_table, - }, - {} -}; - struct pts_mount_opts { int setuid; int setgid; @@ -630,7 +612,7 @@ static int __init init_devpts_fs(void) { int err = register_filesystem(&devpts_fs_type); if (!err) { - register_sysctl_table(pty_root_table); + register_sysctl("kernel/pty", pty_table); } return err; } diff --git a/fs/direct-io.c b/fs/direct-io.c index ab0d7ea89813..0b380bb8a81e 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -86,7 +86,6 @@ struct dio_submit { sector_t final_block_in_request;/* doesn't change */ int boundary; /* prev block is at a boundary */ get_block_t *get_block; /* block mapping function */ - dio_submit_t *submit_io; /* IO submition function */ loff_t logical_offset_in_bio; /* current first logical block in bio */ sector_t final_block_in_bio; /* current final block in bio + 1 */ @@ -431,10 +430,7 @@ static inline void dio_bio_submit(struct dio *dio, struct dio_submit *sdio) dio->bio_disk = bio->bi_bdev->bd_disk; - if (sdio->submit_io) - sdio->submit_io(bio, dio->inode, sdio->logical_offset_in_bio); - else - submit_bio(bio); + submit_bio(bio); sdio->bio = NULL; sdio->boundary = 0; @@ -1098,7 +1094,7 @@ static inline int drop_refcount(struct dio *dio) ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, get_block_t get_block, dio_iodone_t end_io, - dio_submit_t submit_io, int flags) + int flags) { unsigned i_blkbits = READ_ONCE(inode->i_blkbits); unsigned blkbits = i_blkbits; @@ -1215,7 +1211,6 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, sdio.get_block = get_block; dio->end_io = end_io; - sdio.submit_io = submit_io; sdio.final_block_in_bio = -1; sdio.next_block_for_io = -1; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 144ace9e0dd9..83274915ba6d 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -1210,10 +1210,6 @@ static const struct xattr_handler ecryptfs_xattr_handler = { }; const struct xattr_handler *ecryptfs_xattr_handlers[] = { -#ifdef CONFIG_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif &ecryptfs_xattr_handler, NULL }; diff --git a/fs/erofs/data.c b/fs/erofs/data.c index c08c0f578bc6..6fe9a779fa91 100644 --- a/fs/erofs/data.c +++ b/fs/erofs/data.c @@ -27,11 +27,15 @@ void erofs_put_metabuf(struct erofs_buf *buf) buf->page = NULL; } -void *erofs_bread(struct erofs_buf *buf, struct inode *inode, - erofs_blk_t blkaddr, enum erofs_kmap_type type) +/* + * Derive the block size from inode->i_blkbits to make compatible with + * anonymous inode in fscache mode. + */ +void *erofs_bread(struct erofs_buf *buf, erofs_blk_t blkaddr, + enum erofs_kmap_type type) { - struct address_space *const mapping = inode->i_mapping; - erofs_off_t offset = blknr_to_addr(blkaddr); + struct inode *inode = buf->inode; + erofs_off_t offset = (erofs_off_t)blkaddr << inode->i_blkbits; pgoff_t index = offset >> PAGE_SHIFT; struct page *page = buf->page; struct folio *folio; @@ -41,7 +45,7 @@ void *erofs_bread(struct erofs_buf *buf, struct inode *inode, erofs_put_metabuf(buf); nofs_flag = memalloc_nofs_save(); - folio = read_cache_folio(mapping, index, NULL, NULL); + folio = read_cache_folio(inode->i_mapping, index, NULL, NULL); memalloc_nofs_restore(nofs_flag); if (IS_ERR(folio)) return folio; @@ -63,14 +67,19 @@ void *erofs_bread(struct erofs_buf *buf, struct inode *inode, return buf->base + (offset & ~PAGE_MASK); } -void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, - erofs_blk_t blkaddr, enum erofs_kmap_type type) +void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb) { if (erofs_is_fscache_mode(sb)) - return erofs_bread(buf, EROFS_SB(sb)->s_fscache->inode, - blkaddr, type); + buf->inode = EROFS_SB(sb)->s_fscache->inode; + else + buf->inode = sb->s_bdev->bd_inode; +} - return erofs_bread(buf, sb->s_bdev->bd_inode, blkaddr, type); +void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, + erofs_blk_t blkaddr, enum erofs_kmap_type type) +{ + erofs_init_metabuf(buf, sb); + return erofs_bread(buf, blkaddr, type); } static int erofs_map_blocks_flatmode(struct inode *inode, @@ -79,33 +88,32 @@ static int erofs_map_blocks_flatmode(struct inode *inode, erofs_blk_t nblocks, lastblk; u64 offset = map->m_la; struct erofs_inode *vi = EROFS_I(inode); + struct super_block *sb = inode->i_sb; bool tailendpacking = (vi->datalayout == EROFS_INODE_FLAT_INLINE); - nblocks = DIV_ROUND_UP(inode->i_size, EROFS_BLKSIZ); + nblocks = erofs_iblks(inode); lastblk = nblocks - tailendpacking; /* there is no hole in flatmode */ map->m_flags = EROFS_MAP_MAPPED; - if (offset < blknr_to_addr(lastblk)) { - map->m_pa = blknr_to_addr(vi->raw_blkaddr) + map->m_la; - map->m_plen = blknr_to_addr(lastblk) - offset; + if (offset < erofs_pos(sb, lastblk)) { + map->m_pa = erofs_pos(sb, vi->raw_blkaddr) + map->m_la; + map->m_plen = erofs_pos(sb, lastblk) - offset; } else if (tailendpacking) { map->m_pa = erofs_iloc(inode) + vi->inode_isize + - vi->xattr_isize + erofs_blkoff(offset); + vi->xattr_isize + erofs_blkoff(sb, offset); map->m_plen = inode->i_size - offset; /* inline data should be located in the same meta block */ - if (erofs_blkoff(map->m_pa) + map->m_plen > EROFS_BLKSIZ) { - erofs_err(inode->i_sb, - "inline data cross block boundary @ nid %llu", + if (erofs_blkoff(sb, map->m_pa) + map->m_plen > sb->s_blocksize) { + erofs_err(sb, "inline data cross block boundary @ nid %llu", vi->nid); DBG_BUGON(1); return -EFSCORRUPTED; } map->m_flags |= EROFS_MAP_META; } else { - erofs_err(inode->i_sb, - "internal error @ nid: %llu (size %llu), m_la 0x%llx", + erofs_err(sb, "internal error @ nid: %llu (size %llu), m_la 0x%llx", vi->nid, inode->i_size, map->m_la); DBG_BUGON(1); return -EIO; @@ -148,29 +156,29 @@ int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map) pos = ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, unit) + unit * chunknr; - kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), EROFS_KMAP); + kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(sb, pos), EROFS_KMAP); if (IS_ERR(kaddr)) { err = PTR_ERR(kaddr); goto out; } map->m_la = chunknr << vi->chunkbits; map->m_plen = min_t(erofs_off_t, 1UL << vi->chunkbits, - roundup(inode->i_size - map->m_la, EROFS_BLKSIZ)); + round_up(inode->i_size - map->m_la, sb->s_blocksize)); /* handle block map */ if (!(vi->chunkformat & EROFS_CHUNK_FORMAT_INDEXES)) { - __le32 *blkaddr = kaddr + erofs_blkoff(pos); + __le32 *blkaddr = kaddr + erofs_blkoff(sb, pos); if (le32_to_cpu(*blkaddr) == EROFS_NULL_ADDR) { map->m_flags = 0; } else { - map->m_pa = blknr_to_addr(le32_to_cpu(*blkaddr)); + map->m_pa = erofs_pos(sb, le32_to_cpu(*blkaddr)); map->m_flags = EROFS_MAP_MAPPED; } goto out_unlock; } /* parse chunk indexes */ - idx = kaddr + erofs_blkoff(pos); + idx = kaddr + erofs_blkoff(sb, pos); switch (le32_to_cpu(idx->blkaddr)) { case EROFS_NULL_ADDR: map->m_flags = 0; @@ -178,7 +186,7 @@ int erofs_map_blocks(struct inode *inode, struct erofs_map_blocks *map) default: map->m_deviceid = le16_to_cpu(idx->device_id) & EROFS_SB(sb)->device_id_mask; - map->m_pa = blknr_to_addr(le32_to_cpu(idx->blkaddr)); + map->m_pa = erofs_pos(sb, le32_to_cpu(idx->blkaddr)); map->m_flags = EROFS_MAP_MAPPED; break; } @@ -197,7 +205,6 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) struct erofs_device_info *dif; int id; - /* primary device by default */ map->m_bdev = sb->s_bdev; map->m_daxdev = EROFS_SB(sb)->dax_dev; map->m_dax_part_off = EROFS_SB(sb)->dax_part_off; @@ -210,20 +217,25 @@ int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *map) up_read(&devs->rwsem); return -ENODEV; } + if (devs->flatdev) { + map->m_pa += erofs_pos(sb, dif->mapped_blkaddr); + up_read(&devs->rwsem); + return 0; + } map->m_bdev = dif->bdev; map->m_daxdev = dif->dax_dev; map->m_dax_part_off = dif->dax_part_off; map->m_fscache = dif->fscache; up_read(&devs->rwsem); - } else if (devs->extra_devices) { + } else if (devs->extra_devices && !devs->flatdev) { down_read(&devs->rwsem); idr_for_each_entry(&devs->tree, dif, id) { erofs_off_t startoff, length; if (!dif->mapped_blkaddr) continue; - startoff = blknr_to_addr(dif->mapped_blkaddr); - length = blknr_to_addr(dif->blocks); + startoff = erofs_pos(sb, dif->mapped_blkaddr); + length = erofs_pos(sb, dif->blocks); if (map->m_pa >= startoff && map->m_pa < startoff + length) { @@ -244,6 +256,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, unsigned int flags, struct iomap *iomap, struct iomap *srcmap) { int ret; + struct super_block *sb = inode->i_sb; struct erofs_map_blocks map; struct erofs_map_dev mdev; @@ -258,7 +271,7 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, .m_deviceid = map.m_deviceid, .m_pa = map.m_pa, }; - ret = erofs_map_dev(inode->i_sb, &mdev); + ret = erofs_map_dev(sb, &mdev); if (ret) return ret; @@ -284,11 +297,11 @@ static int erofs_iomap_begin(struct inode *inode, loff_t offset, loff_t length, struct erofs_buf buf = __EROFS_BUF_INITIALIZER; iomap->type = IOMAP_INLINE; - ptr = erofs_read_metabuf(&buf, inode->i_sb, - erofs_blknr(mdev.m_pa), EROFS_KMAP); + ptr = erofs_read_metabuf(&buf, sb, + erofs_blknr(sb, mdev.m_pa), EROFS_KMAP); if (IS_ERR(ptr)) return PTR_ERR(ptr); - iomap->inline_data = ptr + erofs_blkoff(mdev.m_pa); + iomap->inline_data = ptr + erofs_blkoff(sb, mdev.m_pa); iomap->private = buf.base; } else { iomap->type = IOMAP_MAPPED; diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 51b7ac7166d9..7021e2cf6146 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -42,7 +42,7 @@ int z_erofs_load_lz4_config(struct super_block *sb, if (!sbi->lz4.max_pclusterblks) { sbi->lz4.max_pclusterblks = 1; /* reserved case */ } else if (sbi->lz4.max_pclusterblks > - Z_EROFS_PCLUSTER_MAX_SIZE / EROFS_BLKSIZ) { + erofs_blknr(sb, Z_EROFS_PCLUSTER_MAX_SIZE)) { erofs_err(sb, "too large lz4 pclusterblks %u", sbi->lz4.max_pclusterblks); return -EINVAL; @@ -221,13 +221,13 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx, support_0padding = true; ret = z_erofs_fixup_insize(rq, headpage + rq->pageofs_in, min_t(unsigned int, rq->inputsize, - EROFS_BLKSIZ - rq->pageofs_in)); + rq->sb->s_blocksize - rq->pageofs_in)); if (ret) { kunmap_atomic(headpage); return ret; } may_inplace = !((rq->pageofs_in + rq->inputsize) & - (EROFS_BLKSIZ - 1)); + (rq->sb->s_blocksize - 1)); } inputmargin = rq->pageofs_in; diff --git a/fs/erofs/decompressor_lzma.c b/fs/erofs/decompressor_lzma.c index d38e19c11270..73091fbe3ea4 100644 --- a/fs/erofs/decompressor_lzma.c +++ b/fs/erofs/decompressor_lzma.c @@ -166,8 +166,8 @@ int z_erofs_lzma_decompress(struct z_erofs_decompress_req *rq, /* 1. get the exact LZMA compressed size */ kin = kmap(*rq->in); err = z_erofs_fixup_insize(rq, kin + rq->pageofs_in, - min_t(unsigned int, rq->inputsize, - EROFS_BLKSIZ - rq->pageofs_in)); + min_t(unsigned int, rq->inputsize, + rq->sb->s_blocksize - rq->pageofs_in)); if (err) { kunmap(*rq->in); return err; diff --git a/fs/erofs/dir.c b/fs/erofs/dir.c index 6970b09b8307..b80abec0531a 100644 --- a/fs/erofs/dir.c +++ b/fs/erofs/dir.c @@ -50,44 +50,43 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx) { struct inode *dir = file_inode(f); struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + struct super_block *sb = dir->i_sb; + unsigned long bsz = sb->s_blocksize; const size_t dirsize = i_size_read(dir); - unsigned int i = ctx->pos / EROFS_BLKSIZ; - unsigned int ofs = ctx->pos % EROFS_BLKSIZ; + unsigned int i = erofs_blknr(sb, ctx->pos); + unsigned int ofs = erofs_blkoff(sb, ctx->pos); int err = 0; bool initial = true; + buf.inode = dir; while (ctx->pos < dirsize) { struct erofs_dirent *de; unsigned int nameoff, maxsize; - de = erofs_bread(&buf, dir, i, EROFS_KMAP); + de = erofs_bread(&buf, i, EROFS_KMAP); if (IS_ERR(de)) { - erofs_err(dir->i_sb, - "fail to readdir of logical block %u of nid %llu", + erofs_err(sb, "fail to readdir of logical block %u of nid %llu", i, EROFS_I(dir)->nid); err = PTR_ERR(de); break; } nameoff = le16_to_cpu(de->nameoff); - if (nameoff < sizeof(struct erofs_dirent) || - nameoff >= EROFS_BLKSIZ) { - erofs_err(dir->i_sb, - "invalid de[0].nameoff %u @ nid %llu", + if (nameoff < sizeof(struct erofs_dirent) || nameoff >= bsz) { + erofs_err(sb, "invalid de[0].nameoff %u @ nid %llu", nameoff, EROFS_I(dir)->nid); err = -EFSCORRUPTED; break; } - maxsize = min_t(unsigned int, - dirsize - ctx->pos + ofs, EROFS_BLKSIZ); + maxsize = min_t(unsigned int, dirsize - ctx->pos + ofs, bsz); /* search dirents at the arbitrary position */ if (initial) { initial = false; ofs = roundup(ofs, sizeof(struct erofs_dirent)); - ctx->pos = blknr_to_addr(i) + ofs; + ctx->pos = erofs_pos(sb, i) + ofs; if (ofs >= nameoff) goto skip_this; } @@ -97,7 +96,7 @@ static int erofs_readdir(struct file *f, struct dir_context *ctx) if (err) break; skip_this: - ctx->pos = blknr_to_addr(i) + maxsize; + ctx->pos = erofs_pos(sb, i) + maxsize; ++i; ofs = 0; } diff --git a/fs/erofs/erofs_fs.h b/fs/erofs/erofs_fs.h index dbcd24371002..2c7b16e340fe 100644 --- a/fs/erofs/erofs_fs.h +++ b/fs/erofs/erofs_fs.h @@ -27,6 +27,7 @@ #define EROFS_FEATURE_INCOMPAT_ZTAILPACKING 0x00000010 #define EROFS_FEATURE_INCOMPAT_FRAGMENTS 0x00000020 #define EROFS_FEATURE_INCOMPAT_DEDUPE 0x00000020 +#define EROFS_FEATURE_INCOMPAT_XATTR_PREFIXES 0x00000040 #define EROFS_ALL_FEATURE_INCOMPAT \ (EROFS_FEATURE_INCOMPAT_ZERO_PADDING | \ EROFS_FEATURE_INCOMPAT_COMPR_CFGS | \ @@ -36,7 +37,8 @@ EROFS_FEATURE_INCOMPAT_COMPR_HEAD2 | \ EROFS_FEATURE_INCOMPAT_ZTAILPACKING | \ EROFS_FEATURE_INCOMPAT_FRAGMENTS | \ - EROFS_FEATURE_INCOMPAT_DEDUPE) + EROFS_FEATURE_INCOMPAT_DEDUPE | \ + EROFS_FEATURE_INCOMPAT_XATTR_PREFIXES) #define EROFS_SB_EXTSLOT_SIZE 16 @@ -53,7 +55,7 @@ struct erofs_super_block { __le32 magic; /* file system magic number */ __le32 checksum; /* crc32c(super_block) */ __le32 feature_compat; - __u8 blkszbits; /* support block_size == PAGE_SIZE only */ + __u8 blkszbits; /* filesystem block size in bit shift */ __u8 sb_extslots; /* superblock size = 128 + sb_extslots * 16 */ __le16 root_nid; /* nid of root directory */ @@ -75,49 +77,46 @@ struct erofs_super_block { } __packed u1; __le16 extra_devices; /* # of devices besides the primary device */ __le16 devt_slotoff; /* startoff = devt_slotoff * devt_slotsize */ - __u8 reserved[6]; + __u8 dirblkbits; /* directory block size in bit shift */ + __u8 xattr_prefix_count; /* # of long xattr name prefixes */ + __le32 xattr_prefix_start; /* start of long xattr prefixes */ __le64 packed_nid; /* nid of the special packed inode */ __u8 reserved2[24]; }; /* - * erofs inode datalayout (i_format in on-disk inode): + * EROFS inode datalayout (i_format in on-disk inode): * 0 - uncompressed flat inode without tail-packing inline data: - * inode, [xattrs], ... | ... | no-holed data * 1 - compressed inode with non-compact indexes: - * inode, [xattrs], [map_header], extents ... | ... * 2 - uncompressed flat inode with tail-packing inline data: - * inode, [xattrs], tailpacking data, ... | ... | no-holed data * 3 - compressed inode with compact indexes: - * inode, [xattrs], map_header, extents ... | ... * 4 - chunk-based inode with (optional) multi-device support: - * inode, [xattrs], chunk indexes ... | ... * 5~7 - reserved */ enum { EROFS_INODE_FLAT_PLAIN = 0, - EROFS_INODE_FLAT_COMPRESSION_LEGACY = 1, + EROFS_INODE_COMPRESSED_FULL = 1, EROFS_INODE_FLAT_INLINE = 2, - EROFS_INODE_FLAT_COMPRESSION = 3, + EROFS_INODE_COMPRESSED_COMPACT = 3, EROFS_INODE_CHUNK_BASED = 4, EROFS_INODE_DATALAYOUT_MAX }; static inline bool erofs_inode_is_data_compressed(unsigned int datamode) { - return datamode == EROFS_INODE_FLAT_COMPRESSION || - datamode == EROFS_INODE_FLAT_COMPRESSION_LEGACY; + return datamode == EROFS_INODE_COMPRESSED_COMPACT || + datamode == EROFS_INODE_COMPRESSED_FULL; } /* bit definitions of inode i_format */ -#define EROFS_I_VERSION_BITS 1 -#define EROFS_I_DATALAYOUT_BITS 3 +#define EROFS_I_VERSION_MASK 0x01 +#define EROFS_I_DATALAYOUT_MASK 0x07 #define EROFS_I_VERSION_BIT 0 #define EROFS_I_DATALAYOUT_BIT 1 +#define EROFS_I_ALL_BIT 4 -#define EROFS_I_ALL \ - ((1 << (EROFS_I_DATALAYOUT_BIT + EROFS_I_DATALAYOUT_BITS)) - 1) +#define EROFS_I_ALL ((1 << EROFS_I_ALL_BIT) - 1) /* indicate chunk blkbits, thus 'chunksize = blocksize << chunk blkbits' */ #define EROFS_CHUNK_FORMAT_BLKBITS_MASK 0x001F @@ -127,11 +126,30 @@ static inline bool erofs_inode_is_data_compressed(unsigned int datamode) #define EROFS_CHUNK_FORMAT_ALL \ (EROFS_CHUNK_FORMAT_BLKBITS_MASK | EROFS_CHUNK_FORMAT_INDEXES) +/* 32-byte on-disk inode */ +#define EROFS_INODE_LAYOUT_COMPACT 0 +/* 64-byte on-disk inode */ +#define EROFS_INODE_LAYOUT_EXTENDED 1 + struct erofs_inode_chunk_info { __le16 format; /* chunk blkbits, etc. */ __le16 reserved; }; +union erofs_inode_i_u { + /* total compressed blocks for compressed inodes */ + __le32 compressed_blocks; + + /* block address for uncompressed flat inodes */ + __le32 raw_blkaddr; + + /* for device files, used to indicate old/new device # */ + __le32 rdev; + + /* for chunk-based files, it contains the summary info */ + struct erofs_inode_chunk_info c; +}; + /* 32-byte reduced form of an ondisk inode */ struct erofs_inode_compact { __le16 i_format; /* inode format hints */ @@ -142,29 +160,14 @@ struct erofs_inode_compact { __le16 i_nlink; __le32 i_size; __le32 i_reserved; - union { - /* total compressed blocks for compressed inodes */ - __le32 compressed_blocks; - /* block address for uncompressed flat inodes */ - __le32 raw_blkaddr; - - /* for device files, used to indicate old/new device # */ - __le32 rdev; - - /* for chunk-based files, it contains the summary info */ - struct erofs_inode_chunk_info c; - } i_u; - __le32 i_ino; /* only used for 32-bit stat compatibility */ + union erofs_inode_i_u i_u; + + __le32 i_ino; /* only used for 32-bit stat compatibility */ __le16 i_uid; __le16 i_gid; __le32 i_reserved2; }; -/* 32-byte on-disk inode */ -#define EROFS_INODE_LAYOUT_COMPACT 0 -/* 64-byte on-disk inode */ -#define EROFS_INODE_LAYOUT_EXTENDED 1 - /* 64-byte complete form of an ondisk inode */ struct erofs_inode_extended { __le16 i_format; /* inode format hints */ @@ -174,22 +177,9 @@ struct erofs_inode_extended { __le16 i_mode; __le16 i_reserved; __le64 i_size; - union { - /* total compressed blocks for compressed inodes */ - __le32 compressed_blocks; - /* block address for uncompressed flat inodes */ - __le32 raw_blkaddr; - - /* for device files, used to indicate old/new device # */ - __le32 rdev; - - /* for chunk-based files, it contains the summary info */ - struct erofs_inode_chunk_info c; - } i_u; - - /* only used for 32-bit stat compatibility */ - __le32 i_ino; + union erofs_inode_i_u i_u; + __le32 i_ino; /* only used for 32-bit stat compatibility */ __le32 i_uid; __le32 i_gid; __le64 i_mtime; @@ -198,10 +188,6 @@ struct erofs_inode_extended { __u8 i_reserved2[16]; }; -#define EROFS_MAX_SHARED_XATTRS (128) -/* h_shared_count between 129 ... 255 are special # */ -#define EROFS_SHARED_XATTR_EXTENT (255) - /* * inline xattrs (n == i_xattr_icount): * erofs_xattr_ibody_header(1) + (n - 1) * 4 bytes @@ -228,6 +214,13 @@ struct erofs_xattr_ibody_header { #define EROFS_XATTR_INDEX_LUSTRE 5 #define EROFS_XATTR_INDEX_SECURITY 6 +/* + * bit 7 of e_name_index is set when it refers to a long xattr name prefix, + * while the remained lower bits represent the index of the prefix. + */ +#define EROFS_XATTR_LONG_PREFIX 0x80 +#define EROFS_XATTR_LONG_PREFIX_MASK 0x7f + /* xattr entry (for both inline & shared xattrs) */ struct erofs_xattr_entry { __u8 e_name_len; /* length of name */ @@ -237,6 +230,12 @@ struct erofs_xattr_entry { char e_name[]; /* attribute name */ }; +/* long xattr name prefix */ +struct erofs_xattr_long_prefix { + __u8 base_index; /* short xattr name prefix index */ + char infix[]; /* infix apart from short prefix */ +}; + static inline unsigned int erofs_xattr_ibody_size(__le16 i_xattr_icount) { if (!i_xattr_icount) @@ -267,6 +266,22 @@ struct erofs_inode_chunk_index { __le32 blkaddr; /* start block address of this inode chunk */ }; +/* dirent sorts in alphabet order, thus we can do binary search */ +struct erofs_dirent { + __le64 nid; /* node number */ + __le16 nameoff; /* start offset of file name */ + __u8 file_type; /* file type */ + __u8 reserved; /* reserved */ +} __packed; + +/* + * EROFS file types should match generic FT_* types and + * it seems no need to add BUILD_BUG_ONs since potential + * unmatchness will break other fses as well... + */ + +#define EROFS_NAME_LEN 255 + /* maximum supported size of a physical compression cluster */ #define Z_EROFS_PCLUSTER_MAX_SIZE (1024 * 1024) @@ -336,10 +351,8 @@ struct z_erofs_map_header { __u8 h_clusterbits; }; -#define Z_EROFS_VLE_LEGACY_HEADER_PADDING 8 - /* - * Fixed-sized output compression on-disk logical cluster type: + * On-disk logical cluster type: * 0 - literal (uncompressed) lcluster * 1,3 - compressed lcluster (for HEAD lclusters) * 2 - compressed lcluster (for NONHEAD lclusters) @@ -363,27 +376,27 @@ struct z_erofs_map_header { * di_u.delta[1] = distance to the next HEAD lcluster */ enum { - Z_EROFS_VLE_CLUSTER_TYPE_PLAIN = 0, - Z_EROFS_VLE_CLUSTER_TYPE_HEAD1 = 1, - Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD = 2, - Z_EROFS_VLE_CLUSTER_TYPE_HEAD2 = 3, - Z_EROFS_VLE_CLUSTER_TYPE_MAX + Z_EROFS_LCLUSTER_TYPE_PLAIN = 0, + Z_EROFS_LCLUSTER_TYPE_HEAD1 = 1, + Z_EROFS_LCLUSTER_TYPE_NONHEAD = 2, + Z_EROFS_LCLUSTER_TYPE_HEAD2 = 3, + Z_EROFS_LCLUSTER_TYPE_MAX }; -#define Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS 2 -#define Z_EROFS_VLE_DI_CLUSTER_TYPE_BIT 0 +#define Z_EROFS_LI_LCLUSTER_TYPE_BITS 2 +#define Z_EROFS_LI_LCLUSTER_TYPE_BIT 0 /* (noncompact only, HEAD) This pcluster refers to partial decompressed data */ -#define Z_EROFS_VLE_DI_PARTIAL_REF (1 << 15) +#define Z_EROFS_LI_PARTIAL_REF (1 << 15) /* * D0_CBLKCNT will be marked _only_ at the 1st non-head lcluster to store the * compressed block count of a compressed extent (in logical clusters, aka. * block count of a pcluster). */ -#define Z_EROFS_VLE_DI_D0_CBLKCNT (1 << 11) +#define Z_EROFS_LI_D0_CBLKCNT (1 << 11) -struct z_erofs_vle_decompressed_index { +struct z_erofs_lcluster_index { __le16 di_advise; /* where to decompress in the head lcluster */ __le16 di_clusterofs; @@ -400,25 +413,8 @@ struct z_erofs_vle_decompressed_index { } di_u; }; -#define Z_EROFS_VLE_LEGACY_INDEX_ALIGN(size) \ - (round_up(size, sizeof(struct z_erofs_vle_decompressed_index)) + \ - sizeof(struct z_erofs_map_header) + Z_EROFS_VLE_LEGACY_HEADER_PADDING) - -/* dirent sorts in alphabet order, thus we can do binary search */ -struct erofs_dirent { - __le64 nid; /* node number */ - __le16 nameoff; /* start offset of file name */ - __u8 file_type; /* file type */ - __u8 reserved; /* reserved */ -} __packed; - -/* - * EROFS file types should match generic FT_* types and - * it seems no need to add BUILD_BUG_ONs since potential - * unmatchness will break other fses as well... - */ - -#define EROFS_NAME_LEN 255 +#define Z_EROFS_FULL_INDEX_ALIGN(end) \ + (ALIGN(end, 8) + sizeof(struct z_erofs_map_header) + 8) /* check the EROFS on-disk layout strictly at compile time */ static inline void erofs_check_ondisk_layout_definitions(void) @@ -435,15 +431,15 @@ static inline void erofs_check_ondisk_layout_definitions(void) BUILD_BUG_ON(sizeof(struct erofs_inode_chunk_info) != 4); BUILD_BUG_ON(sizeof(struct erofs_inode_chunk_index) != 8); BUILD_BUG_ON(sizeof(struct z_erofs_map_header) != 8); - BUILD_BUG_ON(sizeof(struct z_erofs_vle_decompressed_index) != 8); + BUILD_BUG_ON(sizeof(struct z_erofs_lcluster_index) != 8); BUILD_BUG_ON(sizeof(struct erofs_dirent) != 12); /* keep in sync between 2 index structures for better extendibility */ BUILD_BUG_ON(sizeof(struct erofs_inode_chunk_index) != - sizeof(struct z_erofs_vle_decompressed_index)); + sizeof(struct z_erofs_lcluster_index)); BUILD_BUG_ON(sizeof(struct erofs_deviceslot) != 128); - BUILD_BUG_ON(BIT(Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS) < - Z_EROFS_VLE_CLUSTER_TYPE_MAX - 1); + BUILD_BUG_ON(BIT(Z_EROFS_LI_LCLUSTER_TYPE_BITS) < + Z_EROFS_LCLUSTER_TYPE_MAX - 1); /* exclude old compiler versions like gcc 7.5.0 */ BUILD_BUG_ON(__builtin_constant_p(fmh) ? fmh != cpu_to_le64(1ULL << 63) : 0); diff --git a/fs/erofs/fscache.c b/fs/erofs/fscache.c index 96a87c023128..87ff35bff8d5 100644 --- a/fs/erofs/fscache.c +++ b/fs/erofs/fscache.c @@ -209,8 +209,8 @@ static int erofs_fscache_data_read_slice(struct erofs_fscache_request *primary) void *src; /* For tail packing layout, the offset may be non-zero. */ - offset = erofs_blkoff(map.m_pa); - blknr = erofs_blknr(map.m_pa); + offset = erofs_blkoff(sb, map.m_pa); + blknr = erofs_blknr(sb, map.m_pa); size = map.m_llen; src = erofs_read_metabuf(&buf, sb, blknr, EROFS_KMAP); @@ -460,6 +460,7 @@ static struct erofs_fscache *erofs_fscache_acquire_cookie(struct super_block *sb inode->i_size = OFFSET_MAX; inode->i_mapping->a_ops = &erofs_fscache_meta_aops; mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); + inode->i_blkbits = EROFS_SB(sb)->blkszbits; inode->i_private = ctx; ctx->cookie = cookie; diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index 4be7dda3cd24..d70b12b81507 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -23,11 +23,8 @@ static void *erofs_read_inode(struct erofs_buf *buf, unsigned int ifmt; int err; - blkaddr = erofs_blknr(inode_loc); - *ofs = erofs_blkoff(inode_loc); - - erofs_dbg("%s, reading inode nid %llu at %u of blkaddr %u", - __func__, vi->nid, *ofs, blkaddr); + blkaddr = erofs_blknr(sb, inode_loc); + *ofs = erofs_blkoff(sb, inode_loc); kaddr = erofs_read_metabuf(buf, sb, blkaddr, EROFS_KMAP); if (IS_ERR(kaddr)) { @@ -58,11 +55,11 @@ static void *erofs_read_inode(struct erofs_buf *buf, case EROFS_INODE_LAYOUT_EXTENDED: vi->inode_isize = sizeof(struct erofs_inode_extended); /* check if the extended inode acrosses block boundary */ - if (*ofs + vi->inode_isize <= EROFS_BLKSIZ) { + if (*ofs + vi->inode_isize <= sb->s_blocksize) { *ofs += vi->inode_isize; die = (struct erofs_inode_extended *)dic; } else { - const unsigned int gotten = EROFS_BLKSIZ - *ofs; + const unsigned int gotten = sb->s_blocksize - *ofs; copied = kmalloc(vi->inode_isize, GFP_NOFS); if (!copied) { @@ -176,7 +173,7 @@ static void *erofs_read_inode(struct erofs_buf *buf, err = -EOPNOTSUPP; goto err_out; } - vi->chunkbits = LOG_BLOCK_SIZE + + vi->chunkbits = sb->s_blocksize_bits + (vi->chunkformat & EROFS_CHUNK_FORMAT_BLKBITS_MASK); } inode->i_mtime.tv_sec = inode->i_ctime.tv_sec; @@ -188,11 +185,12 @@ static void *erofs_read_inode(struct erofs_buf *buf, if (test_opt(&sbi->opt, DAX_ALWAYS) && S_ISREG(inode->i_mode) && vi->datalayout == EROFS_INODE_FLAT_PLAIN) inode->i_flags |= S_DAX; + if (!nblks) /* measure inode.i_blocks as generic filesystems */ - inode->i_blocks = roundup(inode->i_size, EROFS_BLKSIZ) >> 9; + inode->i_blocks = round_up(inode->i_size, sb->s_blocksize) >> 9; else - inode->i_blocks = nblks << LOG_SECTORS_PER_BLOCK; + inode->i_blocks = nblks << (sb->s_blocksize_bits - 9); return kaddr; bogusimode: @@ -210,11 +208,12 @@ static int erofs_fill_symlink(struct inode *inode, void *kaddr, unsigned int m_pofs) { struct erofs_inode *vi = EROFS_I(inode); + unsigned int bsz = i_blocksize(inode); char *lnk; /* if it cannot be handled with fast symlink scheme */ if (vi->datalayout != EROFS_INODE_FLAT_INLINE || - inode->i_size >= EROFS_BLKSIZ || inode->i_size < 0) { + inode->i_size >= bsz || inode->i_size < 0) { inode->i_op = &erofs_symlink_iops; return 0; } @@ -225,7 +224,7 @@ static int erofs_fill_symlink(struct inode *inode, void *kaddr, m_pofs += vi->xattr_isize; /* inline symlink data shouldn't cross block boundary */ - if (m_pofs + inode->i_size > EROFS_BLKSIZ) { + if (m_pofs + inode->i_size > bsz) { kfree(lnk); erofs_err(inode->i_sb, "inline data cross block boundary @ nid %llu", @@ -289,10 +288,15 @@ static int erofs_fill_inode(struct inode *inode) } if (erofs_inode_is_data_compressed(vi->datalayout)) { - if (!erofs_is_fscache_mode(inode->i_sb)) - err = z_erofs_fill_inode(inode); - else - err = -EOPNOTSUPP; +#ifdef CONFIG_EROFS_FS_ZIP + if (!erofs_is_fscache_mode(inode->i_sb) && + inode->i_sb->s_blocksize_bits == PAGE_SHIFT) { + inode->i_mapping->a_ops = &z_erofs_aops; + err = 0; + goto out_unlock; + } +#endif + err = -EOPNOTSUPP; goto out_unlock; } inode->i_mapping->a_ops = &erofs_raw_access_aops; diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 1db018f8c2e8..af0431a40647 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -31,10 +31,8 @@ __printf(3, 4) void _erofs_info(struct super_block *sb, #define erofs_info(sb, fmt, ...) \ _erofs_info(sb, __func__, fmt "\n", ##__VA_ARGS__) #ifdef CONFIG_EROFS_FS_DEBUG -#define erofs_dbg(x, ...) pr_debug(x "\n", ##__VA_ARGS__) #define DBG_BUGON BUG_ON #else -#define erofs_dbg(x, ...) ((void)0) #define DBG_BUGON(x) ((void)(x)) #endif /* !CONFIG_EROFS_FS_DEBUG */ @@ -81,6 +79,7 @@ struct erofs_dev_context { struct rw_semaphore rwsem; unsigned int extra_devices; + bool flatdev; }; struct erofs_fs_context { @@ -116,6 +115,11 @@ struct erofs_fscache { char *name; }; +struct erofs_xattr_prefix_item { + struct erofs_xattr_long_prefix *prefix; + u8 infix_len; +}; + struct erofs_sb_info { struct erofs_mount_opts opt; /* options */ #ifdef CONFIG_EROFS_FS_ZIP @@ -133,8 +137,8 @@ struct erofs_sb_info { struct inode *managed_cache; struct erofs_sb_lz4_info lz4; - struct inode *packed_inode; #endif /* CONFIG_EROFS_FS_ZIP */ + struct inode *packed_inode; struct erofs_dev_context *devs; struct dax_device *dax_dev; u64 dax_part_off; @@ -144,11 +148,14 @@ struct erofs_sb_info { u32 meta_blkaddr; #ifdef CONFIG_EROFS_FS_XATTR u32 xattr_blkaddr; + u32 xattr_prefix_start; + u8 xattr_prefix_count; + struct erofs_xattr_prefix_item *xattr_prefixes; #endif u16 device_id_mask; /* valid bits of device id to be used */ - /* inode slot unit size in bit shift */ - unsigned char islotbits; + unsigned char islotbits; /* inode slot unit size in bit shift */ + unsigned char blkszbits; /* filesystem block size in bit shift */ u32 sb_size; /* total superblock size */ u32 build_time_nsec; @@ -156,6 +163,7 @@ struct erofs_sb_info { /* what we really care is nid, rather than ino.. */ erofs_nid_t root_nid; + erofs_nid_t packed_nid; /* used for statfs, f_files - f_favail */ u64 inos; @@ -240,27 +248,13 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp) VAL != EROFS_LOCKED_MAGIC); } -/* we strictly follow PAGE_SIZE and no buffer head yet */ -#define LOG_BLOCK_SIZE PAGE_SHIFT - -#undef LOG_SECTORS_PER_BLOCK -#define LOG_SECTORS_PER_BLOCK (PAGE_SHIFT - 9) - -#undef SECTORS_PER_BLOCK -#define SECTORS_PER_BLOCK (1 << SECTORS_PER_BLOCK) - -#define EROFS_BLKSIZ (1 << LOG_BLOCK_SIZE) - -#if (EROFS_BLKSIZ % 4096 || !EROFS_BLKSIZ) -#error erofs cannot be used in this platform -#endif - enum erofs_kmap_type { EROFS_NO_KMAP, /* don't map the buffer */ EROFS_KMAP, /* use kmap_local_page() to map the buffer */ }; struct erofs_buf { + struct inode *inode; struct page *page; void *base; enum erofs_kmap_type kmap_type; @@ -269,9 +263,10 @@ struct erofs_buf { #define ROOT_NID(sb) ((sb)->root_nid) -#define erofs_blknr(addr) ((addr) / EROFS_BLKSIZ) -#define erofs_blkoff(addr) ((addr) % EROFS_BLKSIZ) -#define blknr_to_addr(nr) ((erofs_off_t)(nr) * EROFS_BLKSIZ) +#define erofs_blknr(sb, addr) ((addr) >> (sb)->s_blocksize_bits) +#define erofs_blkoff(sb, addr) ((addr) & ((sb)->s_blocksize - 1)) +#define erofs_pos(sb, blk) ((erofs_off_t)(blk) << (sb)->s_blocksize_bits) +#define erofs_iblks(i) (round_up((i)->i_size, i_blocksize(i)) >> (i)->i_blkbits) #define EROFS_FEATURE_FUNCS(name, compat, feature) \ static inline bool erofs_sb_has_##name(struct erofs_sb_info *sbi) \ @@ -288,6 +283,7 @@ EROFS_FEATURE_FUNCS(compr_head2, incompat, INCOMPAT_COMPR_HEAD2) EROFS_FEATURE_FUNCS(ztailpacking, incompat, INCOMPAT_ZTAILPACKING) EROFS_FEATURE_FUNCS(fragments, incompat, INCOMPAT_FRAGMENTS) EROFS_FEATURE_FUNCS(dedupe, incompat, INCOMPAT_DEDUPE) +EROFS_FEATURE_FUNCS(xattr_prefixes, incompat, INCOMPAT_XATTR_PREFIXES) EROFS_FEATURE_FUNCS(sb_chksum, compat, COMPAT_SB_CHKSUM) /* atomic flag definitions */ @@ -306,7 +302,7 @@ struct erofs_inode { unsigned char datalayout; unsigned char inode_isize; - unsigned short xattr_isize; + unsigned int xattr_isize; unsigned int xattr_shared_count; unsigned int *xattr_shared_xattrs; @@ -343,28 +339,18 @@ static inline erofs_off_t erofs_iloc(struct inode *inode) { struct erofs_sb_info *sbi = EROFS_I_SB(inode); - return blknr_to_addr(sbi->meta_blkaddr) + + return erofs_pos(inode->i_sb, sbi->meta_blkaddr) + (EROFS_I(inode)->nid << sbi->islotbits); } -static inline unsigned int erofs_bitrange(unsigned int value, unsigned int bit, - unsigned int bits) -{ - - return (value >> bit) & ((1 << bits) - 1); -} - - -static inline unsigned int erofs_inode_version(unsigned int value) +static inline unsigned int erofs_inode_version(unsigned int ifmt) { - return erofs_bitrange(value, EROFS_I_VERSION_BIT, - EROFS_I_VERSION_BITS); + return (ifmt >> EROFS_I_VERSION_BIT) & EROFS_I_VERSION_MASK; } -static inline unsigned int erofs_inode_datalayout(unsigned int value) +static inline unsigned int erofs_inode_datalayout(unsigned int ifmt) { - return erofs_bitrange(value, EROFS_I_DATALAYOUT_BIT, - EROFS_I_DATALAYOUT_BITS); + return (ifmt >> EROFS_I_DATALAYOUT_BIT) & EROFS_I_DATALAYOUT_MASK; } /* @@ -451,10 +437,13 @@ extern const struct iomap_ops z_erofs_iomap_report_ops; #define EROFS_REG_COOKIE_SHARE 0x0001 #define EROFS_REG_COOKIE_NEED_NOEXIST 0x0002 +void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, + erofs_off_t *offset, int *lengthp); void erofs_unmap_metabuf(struct erofs_buf *buf); void erofs_put_metabuf(struct erofs_buf *buf); -void *erofs_bread(struct erofs_buf *buf, struct inode *inode, - erofs_blk_t blkaddr, enum erofs_kmap_type type); +void *erofs_bread(struct erofs_buf *buf, erofs_blk_t blkaddr, + enum erofs_kmap_type type); +void erofs_init_metabuf(struct erofs_buf *buf, struct super_block *sb); void *erofs_read_metabuf(struct erofs_buf *buf, struct super_block *sb, erofs_blk_t blkaddr, enum erofs_kmap_type type); int erofs_map_dev(struct super_block *sb, struct erofs_map_dev *dev); @@ -521,7 +510,6 @@ int erofs_try_to_free_cached_page(struct page *page); int z_erofs_load_lz4_config(struct super_block *sb, struct erofs_super_block *dsb, struct z_erofs_lz4_cfgs *lz4, int len); -int z_erofs_fill_inode(struct inode *inode); int z_erofs_map_blocks_iter(struct inode *inode, struct erofs_map_blocks *map, int flags); #else @@ -541,7 +529,6 @@ static inline int z_erofs_load_lz4_config(struct super_block *sb, } return 0; } -static inline int z_erofs_fill_inode(struct inode *inode) { return -EOPNOTSUPP; } #endif /* !CONFIG_EROFS_FS_ZIP */ #ifdef CONFIG_EROFS_FS_ZIP_LZMA diff --git a/fs/erofs/namei.c b/fs/erofs/namei.c index 966eabc61c13..d4f631d39f0f 100644 --- a/fs/erofs/namei.c +++ b/fs/erofs/namei.c @@ -89,7 +89,8 @@ static struct erofs_dirent *find_target_dirent(struct erofs_qstr *name, static void *erofs_find_target_block(struct erofs_buf *target, struct inode *dir, struct erofs_qstr *name, int *_ndirents) { - int head = 0, back = DIV_ROUND_UP(dir->i_size, EROFS_BLKSIZ) - 1; + unsigned int bsz = i_blocksize(dir); + int head = 0, back = erofs_iblks(dir) - 1; unsigned int startprfx = 0, endprfx = 0; void *candidate = ERR_PTR(-ENOENT); @@ -98,10 +99,10 @@ static void *erofs_find_target_block(struct erofs_buf *target, struct erofs_buf buf = __EROFS_BUF_INITIALIZER; struct erofs_dirent *de; - de = erofs_bread(&buf, dir, mid, EROFS_KMAP); + buf.inode = dir; + de = erofs_bread(&buf, mid, EROFS_KMAP); if (!IS_ERR(de)) { - const int nameoff = nameoff_from_disk(de->nameoff, - EROFS_BLKSIZ); + const int nameoff = nameoff_from_disk(de->nameoff, bsz); const int ndirents = nameoff / sizeof(*de); int diff; unsigned int matched; @@ -121,11 +122,10 @@ static void *erofs_find_target_block(struct erofs_buf *target, dname.name = (u8 *)de + nameoff; if (ndirents == 1) - dname.end = (u8 *)de + EROFS_BLKSIZ; + dname.end = (u8 *)de + bsz; else dname.end = (u8 *)de + - nameoff_from_disk(de[1].nameoff, - EROFS_BLKSIZ); + nameoff_from_disk(de[1].nameoff, bsz); /* string comparison without already matched prefix */ diff = erofs_dirnamecmp(name, &dname, &matched); @@ -171,6 +171,7 @@ int erofs_namei(struct inode *dir, const struct qstr *name, erofs_nid_t *nid, qn.name = name->name; qn.end = name->name + name->len; + buf.inode = dir; ndirents = 0; de = erofs_find_target_block(&buf, dir, &qn, &ndirents); @@ -178,7 +179,8 @@ int erofs_namei(struct inode *dir, const struct qstr *name, erofs_nid_t *nid, return PTR_ERR(de); if (ndirents) - de = find_target_dirent(&qn, (u8 *)de, EROFS_BLKSIZ, ndirents); + de = find_target_dirent(&qn, (u8 *)de, i_blocksize(dir), + ndirents); if (!IS_ERR(de)) { *nid = le64_to_cpu(de->nid); @@ -203,16 +205,13 @@ static struct dentry *erofs_lookup(struct inode *dir, struct dentry *dentry, err = erofs_namei(dir, &dentry->d_name, &nid, &d_type); - if (err == -ENOENT) { + if (err == -ENOENT) /* negative dentry */ inode = NULL; - } else if (err) { + else if (err) inode = ERR_PTR(err); - } else { - erofs_dbg("%s, %pd (nid %llu) found, d_type %u", __func__, - dentry, nid, d_type); + else inode = erofs_iget(dir->i_sb, nid); - } return d_splice_alias(inode, dentry); } diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 19b1ae79cec4..811ab66d805e 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -52,18 +52,21 @@ void _erofs_info(struct super_block *sb, const char *function, static int erofs_superblock_csum_verify(struct super_block *sb, void *sbdata) { + size_t len = 1 << EROFS_SB(sb)->blkszbits; struct erofs_super_block *dsb; u32 expected_crc, crc; - dsb = kmemdup(sbdata + EROFS_SUPER_OFFSET, - EROFS_BLKSIZ - EROFS_SUPER_OFFSET, GFP_KERNEL); + if (len > EROFS_SUPER_OFFSET) + len -= EROFS_SUPER_OFFSET; + + dsb = kmemdup(sbdata + EROFS_SUPER_OFFSET, len, GFP_KERNEL); if (!dsb) return -ENOMEM; expected_crc = le32_to_cpu(dsb->checksum); dsb->checksum = 0; /* to allow for x86 boot sectors and other oddities. */ - crc = crc32c(~0, dsb, EROFS_BLKSIZ - EROFS_SUPER_OFFSET); + crc = crc32c(~0, dsb, len); kfree(dsb); if (crc != expected_crc) { @@ -123,20 +126,19 @@ static bool check_layout_compatibility(struct super_block *sb, return true; } -#ifdef CONFIG_EROFS_FS_ZIP /* read variable-sized metadata, offset will be aligned by 4-byte */ -static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, - erofs_off_t *offset, int *lengthp) +void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, + erofs_off_t *offset, int *lengthp) { u8 *buffer, *ptr; int len, i, cnt; *offset = round_up(*offset, 4); - ptr = erofs_read_metabuf(buf, sb, erofs_blknr(*offset), EROFS_KMAP); + ptr = erofs_bread(buf, erofs_blknr(sb, *offset), EROFS_KMAP); if (IS_ERR(ptr)) return ptr; - len = le16_to_cpu(*(__le16 *)&ptr[erofs_blkoff(*offset)]); + len = le16_to_cpu(*(__le16 *)&ptr[erofs_blkoff(sb, *offset)]); if (!len) len = U16_MAX + 1; buffer = kmalloc(len, GFP_KERNEL); @@ -146,19 +148,20 @@ static void *erofs_read_metadata(struct super_block *sb, struct erofs_buf *buf, *lengthp = len; for (i = 0; i < len; i += cnt) { - cnt = min(EROFS_BLKSIZ - (int)erofs_blkoff(*offset), len - i); - ptr = erofs_read_metabuf(buf, sb, erofs_blknr(*offset), - EROFS_KMAP); + cnt = min_t(int, sb->s_blocksize - erofs_blkoff(sb, *offset), + len - i); + ptr = erofs_bread(buf, erofs_blknr(sb, *offset), EROFS_KMAP); if (IS_ERR(ptr)) { kfree(buffer); return ptr; } - memcpy(buffer + i, ptr + erofs_blkoff(*offset), cnt); + memcpy(buffer + i, ptr + erofs_blkoff(sb, *offset), cnt); *offset += cnt; } return buffer; } +#ifdef CONFIG_EROFS_FS_ZIP static int erofs_load_compr_cfgs(struct super_block *sb, struct erofs_super_block *dsb) { @@ -175,6 +178,7 @@ static int erofs_load_compr_cfgs(struct super_block *sb, return -EINVAL; } + erofs_init_metabuf(&buf, sb); offset = EROFS_SUPER_OFFSET + sbi->sb_size; alg = 0; for (algs = sbi->available_compr_algs; algs; algs >>= 1, ++alg) { @@ -228,10 +232,10 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, struct block_device *bdev; void *ptr; - ptr = erofs_read_metabuf(buf, sb, erofs_blknr(*pos), EROFS_KMAP); + ptr = erofs_read_metabuf(buf, sb, erofs_blknr(sb, *pos), EROFS_KMAP); if (IS_ERR(ptr)) return PTR_ERR(ptr); - dis = ptr + erofs_blkoff(*pos); + dis = ptr + erofs_blkoff(sb, *pos); if (!dif->path) { if (!dis->tag[0]) { @@ -248,7 +252,7 @@ static int erofs_init_device(struct erofs_buf *buf, struct super_block *sb, if (IS_ERR(fscache)) return PTR_ERR(fscache); dif->fscache = fscache; - } else { + } else if (!sbi->devs->flatdev) { bdev = blkdev_get_by_path(dif->path, FMODE_READ | FMODE_EXCL, sb->s_type); if (IS_ERR(bdev)) @@ -290,6 +294,9 @@ static int erofs_scan_devices(struct super_block *sb, if (!ondisk_extradevs) return 0; + if (!sbi->devs->extra_devices && !erofs_is_fscache_mode(sb)) + sbi->devs->flatdev = true; + sbi->device_id_mask = roundup_pow_of_two(ondisk_extradevs + 1) - 1; pos = le16_to_cpu(dsb->devt_slotoff) * EROFS_DEVT_SLOT_SIZE; down_read(&sbi->devs->rwsem); @@ -329,7 +336,6 @@ static int erofs_read_superblock(struct super_block *sb) struct erofs_sb_info *sbi; struct erofs_buf buf = __EROFS_BUF_INITIALIZER; struct erofs_super_block *dsb; - unsigned int blkszbits; void *data; int ret; @@ -348,6 +354,16 @@ static int erofs_read_superblock(struct super_block *sb) goto out; } + sbi->blkszbits = dsb->blkszbits; + if (sbi->blkszbits < 9 || sbi->blkszbits > PAGE_SHIFT) { + erofs_err(sb, "blkszbits %u isn't supported", sbi->blkszbits); + goto out; + } + if (dsb->dirblkbits) { + erofs_err(sb, "dirblkbits %u isn't supported", dsb->dirblkbits); + goto out; + } + sbi->feature_compat = le32_to_cpu(dsb->feature_compat); if (erofs_sb_has_sb_chksum(sbi)) { ret = erofs_superblock_csum_verify(sb, data); @@ -356,19 +372,11 @@ static int erofs_read_superblock(struct super_block *sb) } ret = -EINVAL; - blkszbits = dsb->blkszbits; - /* 9(512 bytes) + LOG_SECTORS_PER_BLOCK == LOG_BLOCK_SIZE */ - if (blkszbits != LOG_BLOCK_SIZE) { - erofs_err(sb, "blkszbits %u isn't supported on this platform", - blkszbits); - goto out; - } - if (!check_layout_compatibility(sb, dsb)) goto out; sbi->sb_size = 128 + dsb->sb_extslots * EROFS_SB_EXTSLOT_SIZE; - if (sbi->sb_size > EROFS_BLKSIZ) { + if (sbi->sb_size > PAGE_SIZE - EROFS_SUPER_OFFSET) { erofs_err(sb, "invalid sb_extslots %u (more than a fs block)", sbi->sb_size); goto out; @@ -377,20 +385,12 @@ static int erofs_read_superblock(struct super_block *sb) sbi->meta_blkaddr = le32_to_cpu(dsb->meta_blkaddr); #ifdef CONFIG_EROFS_FS_XATTR sbi->xattr_blkaddr = le32_to_cpu(dsb->xattr_blkaddr); + sbi->xattr_prefix_start = le32_to_cpu(dsb->xattr_prefix_start); + sbi->xattr_prefix_count = dsb->xattr_prefix_count; #endif sbi->islotbits = ilog2(sizeof(struct erofs_inode_compact)); sbi->root_nid = le16_to_cpu(dsb->root_nid); -#ifdef CONFIG_EROFS_FS_ZIP - sbi->packed_inode = NULL; - if (erofs_sb_has_fragments(sbi) && dsb->packed_nid) { - sbi->packed_inode = - erofs_iget(sb, le64_to_cpu(dsb->packed_nid)); - if (IS_ERR(sbi->packed_inode)) { - ret = PTR_ERR(sbi->packed_inode); - goto out; - } - } -#endif + sbi->packed_nid = le64_to_cpu(dsb->packed_nid); sbi->inos = le64_to_cpu(dsb->inos); sbi->build_time = le64_to_cpu(dsb->build_time); @@ -417,8 +417,6 @@ static int erofs_read_superblock(struct super_block *sb) /* handle multiple devices */ ret = erofs_scan_devices(sb, dsb); - if (erofs_sb_has_ztailpacking(sbi)) - erofs_info(sb, "EXPERIMENTAL compressed inline data feature in use. Use at your own risk!"); if (erofs_is_fscache_mode(sb)) erofs_info(sb, "EXPERIMENTAL fscache-based on-demand read feature in use. Use at your own risk!"); if (erofs_sb_has_fragments(sbi)) @@ -733,9 +731,10 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) sbi->domain_id = ctx->domain_id; ctx->domain_id = NULL; + sbi->blkszbits = PAGE_SHIFT; if (erofs_is_fscache_mode(sb)) { - sb->s_blocksize = EROFS_BLKSIZ; - sb->s_blocksize_bits = LOG_BLOCK_SIZE; + sb->s_blocksize = PAGE_SIZE; + sb->s_blocksize_bits = PAGE_SHIFT; err = erofs_fscache_register_fs(sb); if (err) @@ -745,8 +744,8 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) if (err) return err; } else { - if (!sb_set_blocksize(sb, EROFS_BLKSIZ)) { - erofs_err(sb, "failed to set erofs blksize"); + if (!sb_set_blocksize(sb, PAGE_SIZE)) { + errorfc(fc, "failed to set initial blksize"); return -EINVAL; } @@ -759,12 +758,24 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) if (err) return err; - if (test_opt(&sbi->opt, DAX_ALWAYS)) { - BUILD_BUG_ON(EROFS_BLKSIZ != PAGE_SIZE); + if (sb->s_blocksize_bits != sbi->blkszbits) { + if (erofs_is_fscache_mode(sb)) { + errorfc(fc, "unsupported blksize for fscache mode"); + return -EINVAL; + } + if (!sb_set_blocksize(sb, 1 << sbi->blkszbits)) { + errorfc(fc, "failed to set erofs blksize"); + return -EINVAL; + } + } + if (test_opt(&sbi->opt, DAX_ALWAYS)) { if (!sbi->dax_dev) { errorfc(fc, "DAX unsupported by block device. Turning off DAX."); clear_opt(&sbi->opt, DAX_ALWAYS); + } else if (sbi->blkszbits != PAGE_SHIFT) { + errorfc(fc, "unsupported blocksize for DAX"); + clear_opt(&sbi->opt, DAX_ALWAYS); } } @@ -799,10 +810,22 @@ static int erofs_fc_fill_super(struct super_block *sb, struct fs_context *fc) erofs_shrinker_register(sb); /* sb->s_umount is already locked, SB_ACTIVE and SB_BORN are not set */ + if (erofs_sb_has_fragments(sbi) && sbi->packed_nid) { + sbi->packed_inode = erofs_iget(sb, sbi->packed_nid); + if (IS_ERR(sbi->packed_inode)) { + err = PTR_ERR(sbi->packed_inode); + sbi->packed_inode = NULL; + return err; + } + } err = erofs_init_managed_cache(sb); if (err) return err; + err = erofs_xattr_prefixes_init(sb); + if (err) + return err; + err = erofs_register_sysfs(sb); if (err) return err; @@ -962,12 +985,13 @@ static void erofs_put_super(struct super_block *sb) erofs_unregister_sysfs(sb); erofs_shrinker_unregister(sb); + erofs_xattr_prefixes_cleanup(sb); #ifdef CONFIG_EROFS_FS_ZIP iput(sbi->managed_cache); sbi->managed_cache = NULL; +#endif iput(sbi->packed_inode); sbi->packed_inode = NULL; -#endif erofs_free_dev_context(sbi->devs); sbi->devs = NULL; erofs_fscache_unregister_fs(sb); @@ -1060,7 +1084,7 @@ static int erofs_statfs(struct dentry *dentry, struct kstatfs *buf) id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = sb->s_magic; - buf->f_bsize = EROFS_BLKSIZ; + buf->f_bsize = sb->s_blocksize; buf->f_blocks = sbi->total_blocks; buf->f_bfree = buf->f_bavail = 0; diff --git a/fs/erofs/xattr.c b/fs/erofs/xattr.c index 60729b1220b6..cd80499351e0 100644 --- a/fs/erofs/xattr.c +++ b/fs/erofs/xattr.c @@ -7,6 +7,19 @@ #include <linux/security.h> #include "xattr.h" +static inline erofs_blk_t erofs_xattr_blkaddr(struct super_block *sb, + unsigned int xattr_id) +{ + return EROFS_SB(sb)->xattr_blkaddr + + erofs_blknr(sb, xattr_id * sizeof(__u32)); +} + +static inline unsigned int erofs_xattr_blkoff(struct super_block *sb, + unsigned int xattr_id) +{ + return erofs_blkoff(sb, xattr_id * sizeof(__u32)); +} + struct xattr_iter { struct super_block *sb; struct erofs_buf buf; @@ -16,7 +29,7 @@ struct xattr_iter { unsigned int ofs; }; -static int init_inode_xattrs(struct inode *inode) +static int erofs_init_inode_xattrs(struct inode *inode) { struct erofs_inode *const vi = EROFS_I(inode); struct xattr_iter it; @@ -68,8 +81,8 @@ static int init_inode_xattrs(struct inode *inode) } it.buf = __EROFS_BUF_INITIALIZER; - it.blkaddr = erofs_blknr(erofs_iloc(inode) + vi->inode_isize); - it.ofs = erofs_blkoff(erofs_iloc(inode) + vi->inode_isize); + it.blkaddr = erofs_blknr(sb, erofs_iloc(inode) + vi->inode_isize); + it.ofs = erofs_blkoff(sb, erofs_iloc(inode) + vi->inode_isize); /* read in shared xattr array (non-atomic, see kmalloc below) */ it.kaddr = erofs_read_metabuf(&it.buf, sb, it.blkaddr, EROFS_KMAP); @@ -92,9 +105,9 @@ static int init_inode_xattrs(struct inode *inode) it.ofs += sizeof(struct erofs_xattr_ibody_header); for (i = 0; i < vi->xattr_shared_count; ++i) { - if (it.ofs >= EROFS_BLKSIZ) { + if (it.ofs >= sb->s_blocksize) { /* cannot be unaligned */ - DBG_BUGON(it.ofs != EROFS_BLKSIZ); + DBG_BUGON(it.ofs != sb->s_blocksize); it.kaddr = erofs_read_metabuf(&it.buf, sb, ++it.blkaddr, EROFS_KMAP); @@ -139,15 +152,15 @@ struct xattr_iter_handlers { static inline int xattr_iter_fixup(struct xattr_iter *it) { - if (it->ofs < EROFS_BLKSIZ) + if (it->ofs < it->sb->s_blocksize) return 0; - it->blkaddr += erofs_blknr(it->ofs); + it->blkaddr += erofs_blknr(it->sb, it->ofs); it->kaddr = erofs_read_metabuf(&it->buf, it->sb, it->blkaddr, EROFS_KMAP); if (IS_ERR(it->kaddr)) return PTR_ERR(it->kaddr); - it->ofs = erofs_blkoff(it->ofs); + it->ofs = erofs_blkoff(it->sb, it->ofs); return 0; } @@ -157,7 +170,8 @@ static int inline_xattr_iter_begin(struct xattr_iter *it, struct erofs_inode *const vi = EROFS_I(inode); unsigned int xattr_header_sz, inline_xattr_ofs; - xattr_header_sz = inlinexattr_header_size(inode); + xattr_header_sz = sizeof(struct erofs_xattr_ibody_header) + + sizeof(u32) * vi->xattr_shared_count; if (xattr_header_sz >= vi->xattr_isize) { DBG_BUGON(xattr_header_sz > vi->xattr_isize); return -ENOATTR; @@ -165,8 +179,8 @@ static int inline_xattr_iter_begin(struct xattr_iter *it, inline_xattr_ofs = vi->inode_isize + xattr_header_sz; - it->blkaddr = erofs_blknr(erofs_iloc(inode) + inline_xattr_ofs); - it->ofs = erofs_blkoff(erofs_iloc(inode) + inline_xattr_ofs); + it->blkaddr = erofs_blknr(it->sb, erofs_iloc(inode) + inline_xattr_ofs); + it->ofs = erofs_blkoff(it->sb, erofs_iloc(inode) + inline_xattr_ofs); it->kaddr = erofs_read_metabuf(&it->buf, inode->i_sb, it->blkaddr, EROFS_KMAP); if (IS_ERR(it->kaddr)) @@ -222,8 +236,8 @@ static int xattr_foreach(struct xattr_iter *it, processed = 0; while (processed < entry.e_name_len) { - if (it->ofs >= EROFS_BLKSIZ) { - DBG_BUGON(it->ofs > EROFS_BLKSIZ); + if (it->ofs >= it->sb->s_blocksize) { + DBG_BUGON(it->ofs > it->sb->s_blocksize); err = xattr_iter_fixup(it); if (err) @@ -231,7 +245,7 @@ static int xattr_foreach(struct xattr_iter *it, it->ofs = 0; } - slice = min_t(unsigned int, EROFS_BLKSIZ - it->ofs, + slice = min_t(unsigned int, it->sb->s_blocksize - it->ofs, entry.e_name_len - processed); /* handle name */ @@ -257,8 +271,8 @@ static int xattr_foreach(struct xattr_iter *it, } while (processed < value_sz) { - if (it->ofs >= EROFS_BLKSIZ) { - DBG_BUGON(it->ofs > EROFS_BLKSIZ); + if (it->ofs >= it->sb->s_blocksize) { + DBG_BUGON(it->ofs > it->sb->s_blocksize); err = xattr_iter_fixup(it); if (err) @@ -266,7 +280,7 @@ static int xattr_foreach(struct xattr_iter *it, it->ofs = 0; } - slice = min_t(unsigned int, EROFS_BLKSIZ - it->ofs, + slice = min_t(unsigned int, it->sb->s_blocksize - it->ofs, value_sz - processed); op->value(it, processed, it->kaddr + it->ofs, slice); it->ofs += slice; @@ -283,17 +297,45 @@ struct getxattr_iter { struct xattr_iter it; char *buffer; - int buffer_size, index; + int buffer_size, index, infix_len; struct qstr name; }; +static int erofs_xattr_long_entrymatch(struct getxattr_iter *it, + struct erofs_xattr_entry *entry) +{ + struct erofs_sb_info *sbi = EROFS_SB(it->it.sb); + struct erofs_xattr_prefix_item *pf = sbi->xattr_prefixes + + (entry->e_name_index & EROFS_XATTR_LONG_PREFIX_MASK); + + if (pf >= sbi->xattr_prefixes + sbi->xattr_prefix_count) + return -ENOATTR; + + if (it->index != pf->prefix->base_index || + it->name.len != entry->e_name_len + pf->infix_len) + return -ENOATTR; + + if (memcmp(it->name.name, pf->prefix->infix, pf->infix_len)) + return -ENOATTR; + + it->infix_len = pf->infix_len; + return 0; +} + static int xattr_entrymatch(struct xattr_iter *_it, struct erofs_xattr_entry *entry) { struct getxattr_iter *it = container_of(_it, struct getxattr_iter, it); - return (it->index != entry->e_name_index || - it->name.len != entry->e_name_len) ? -ENOATTR : 0; + /* should also match the infix for long name prefixes */ + if (entry->e_name_index & EROFS_XATTR_LONG_PREFIX) + return erofs_xattr_long_entrymatch(it, entry); + + if (it->index != entry->e_name_index || + it->name.len != entry->e_name_len) + return -ENOATTR; + it->infix_len = 0; + return 0; } static int xattr_namematch(struct xattr_iter *_it, @@ -301,7 +343,9 @@ static int xattr_namematch(struct xattr_iter *_it, { struct getxattr_iter *it = container_of(_it, struct getxattr_iter, it); - return memcmp(buf, it->name.name + processed, len) ? -ENOATTR : 0; + if (memcmp(buf, it->name.name + it->infix_len + processed, len)) + return -ENOATTR; + return 0; } static int xattr_checkbuffer(struct xattr_iter *_it, @@ -351,21 +395,18 @@ static int inline_getxattr(struct inode *inode, struct getxattr_iter *it) static int shared_getxattr(struct inode *inode, struct getxattr_iter *it) { struct erofs_inode *const vi = EROFS_I(inode); - struct super_block *const sb = inode->i_sb; - struct erofs_sb_info *const sbi = EROFS_SB(sb); - unsigned int i; + struct super_block *const sb = it->it.sb; + unsigned int i, xsid; int ret = -ENOATTR; for (i = 0; i < vi->xattr_shared_count; ++i) { - erofs_blk_t blkaddr = - xattrblock_addr(sbi, vi->xattr_shared_xattrs[i]); - - it->it.ofs = xattrblock_offset(sbi, vi->xattr_shared_xattrs[i]); - it->it.kaddr = erofs_read_metabuf(&it->it.buf, sb, blkaddr, - EROFS_KMAP); + xsid = vi->xattr_shared_xattrs[i]; + it->it.blkaddr = erofs_xattr_blkaddr(sb, xsid); + it->it.ofs = erofs_xattr_blkoff(sb, xsid); + it->it.kaddr = erofs_read_metabuf(&it->it.buf, sb, + it->it.blkaddr, EROFS_KMAP); if (IS_ERR(it->it.kaddr)) return PTR_ERR(it->it.kaddr); - it->it.blkaddr = blkaddr; ret = xattr_foreach(&it->it, &find_xattr_handlers, NULL); if (ret != -ENOATTR) @@ -394,7 +435,7 @@ int erofs_getxattr(struct inode *inode, int index, if (!name) return -EINVAL; - ret = init_inode_xattrs(inode); + ret = erofs_init_inode_xattrs(inode); if (ret) return ret; @@ -421,20 +462,9 @@ static int erofs_xattr_generic_get(const struct xattr_handler *handler, struct dentry *unused, struct inode *inode, const char *name, void *buffer, size_t size) { - struct erofs_sb_info *const sbi = EROFS_I_SB(inode); - - switch (handler->flags) { - case EROFS_XATTR_INDEX_USER: - if (!test_opt(&sbi->opt, XATTR_USER)) - return -EOPNOTSUPP; - break; - case EROFS_XATTR_INDEX_TRUSTED: - break; - case EROFS_XATTR_INDEX_SECURITY: - break; - default: - return -EINVAL; - } + if (handler->flags == EROFS_XATTR_INDEX_USER && + !test_opt(&EROFS_I_SB(inode)->opt, XATTR_USER)) + return -EOPNOTSUPP; return erofs_getxattr(inode, handler->flags, name, buffer, size); } @@ -463,10 +493,6 @@ const struct xattr_handler __maybe_unused erofs_xattr_security_handler = { const struct xattr_handler *erofs_xattr_handlers[] = { &erofs_xattr_user_handler, -#ifdef CONFIG_EROFS_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif &erofs_xattr_trusted_handler, #ifdef CONFIG_EROFS_FS_SECURITY &erofs_xattr_security_handler, @@ -487,29 +513,40 @@ static int xattr_entrylist(struct xattr_iter *_it, { struct listxattr_iter *it = container_of(_it, struct listxattr_iter, it); - unsigned int prefix_len; - const char *prefix; - - const struct xattr_handler *h = - erofs_xattr_handler(entry->e_name_index); + unsigned int base_index = entry->e_name_index; + unsigned int prefix_len, infix_len = 0; + const char *prefix, *infix = NULL; + + if (entry->e_name_index & EROFS_XATTR_LONG_PREFIX) { + struct erofs_sb_info *sbi = EROFS_SB(_it->sb); + struct erofs_xattr_prefix_item *pf = sbi->xattr_prefixes + + (entry->e_name_index & EROFS_XATTR_LONG_PREFIX_MASK); + + if (pf >= sbi->xattr_prefixes + sbi->xattr_prefix_count) + return 1; + infix = pf->prefix->infix; + infix_len = pf->infix_len; + base_index = pf->prefix->base_index; + } - if (!h || (h->list && !h->list(it->dentry))) + prefix = erofs_xattr_prefix(base_index, it->dentry); + if (!prefix) return 1; - - prefix = xattr_prefix(h); prefix_len = strlen(prefix); if (!it->buffer) { - it->buffer_ofs += prefix_len + entry->e_name_len + 1; + it->buffer_ofs += prefix_len + infix_len + + entry->e_name_len + 1; return 1; } - if (it->buffer_ofs + prefix_len + if (it->buffer_ofs + prefix_len + infix_len + + entry->e_name_len + 1 > it->buffer_size) return -ERANGE; memcpy(it->buffer + it->buffer_ofs, prefix, prefix_len); - it->buffer_ofs += prefix_len; + memcpy(it->buffer + it->buffer_ofs + prefix_len, infix, infix_len); + it->buffer_ofs += prefix_len + infix_len; return 0; } @@ -563,21 +600,18 @@ static int shared_listxattr(struct listxattr_iter *it) { struct inode *const inode = d_inode(it->dentry); struct erofs_inode *const vi = EROFS_I(inode); - struct super_block *const sb = inode->i_sb; - struct erofs_sb_info *const sbi = EROFS_SB(sb); - unsigned int i; + struct super_block *const sb = it->it.sb; + unsigned int i, xsid; int ret = 0; for (i = 0; i < vi->xattr_shared_count; ++i) { - erofs_blk_t blkaddr = - xattrblock_addr(sbi, vi->xattr_shared_xattrs[i]); - - it->it.ofs = xattrblock_offset(sbi, vi->xattr_shared_xattrs[i]); - it->it.kaddr = erofs_read_metabuf(&it->it.buf, sb, blkaddr, - EROFS_KMAP); + xsid = vi->xattr_shared_xattrs[i]; + it->it.blkaddr = erofs_xattr_blkaddr(sb, xsid); + it->it.ofs = erofs_xattr_blkoff(sb, xsid); + it->it.kaddr = erofs_read_metabuf(&it->it.buf, sb, + it->it.blkaddr, EROFS_KMAP); if (IS_ERR(it->it.kaddr)) return PTR_ERR(it->it.kaddr); - it->it.blkaddr = blkaddr; ret = xattr_foreach(&it->it, &list_xattr_handlers, NULL); if (ret) @@ -592,7 +626,7 @@ ssize_t erofs_listxattr(struct dentry *dentry, int ret; struct listxattr_iter it; - ret = init_inode_xattrs(d_inode(dentry)); + ret = erofs_init_inode_xattrs(d_inode(dentry)); if (ret == -ENOATTR) return 0; if (ret) @@ -613,6 +647,62 @@ ssize_t erofs_listxattr(struct dentry *dentry, return ret; } +void erofs_xattr_prefixes_cleanup(struct super_block *sb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + int i; + + if (sbi->xattr_prefixes) { + for (i = 0; i < sbi->xattr_prefix_count; i++) + kfree(sbi->xattr_prefixes[i].prefix); + kfree(sbi->xattr_prefixes); + sbi->xattr_prefixes = NULL; + } +} + +int erofs_xattr_prefixes_init(struct super_block *sb) +{ + struct erofs_sb_info *sbi = EROFS_SB(sb); + struct erofs_buf buf = __EROFS_BUF_INITIALIZER; + erofs_off_t pos = (erofs_off_t)sbi->xattr_prefix_start << 2; + struct erofs_xattr_prefix_item *pfs; + int ret = 0, i, len; + + if (!sbi->xattr_prefix_count) + return 0; + + pfs = kzalloc(sbi->xattr_prefix_count * sizeof(*pfs), GFP_KERNEL); + if (!pfs) + return -ENOMEM; + + if (erofs_sb_has_fragments(sbi)) + buf.inode = sbi->packed_inode; + else + erofs_init_metabuf(&buf, sb); + + for (i = 0; i < sbi->xattr_prefix_count; i++) { + void *ptr = erofs_read_metadata(sb, &buf, &pos, &len); + + if (IS_ERR(ptr)) { + ret = PTR_ERR(ptr); + break; + } else if (len < sizeof(*pfs->prefix) || + len > EROFS_NAME_LEN + sizeof(*pfs->prefix)) { + kfree(ptr); + ret = -EFSCORRUPTED; + break; + } + pfs[i].prefix = ptr; + pfs[i].infix_len = len - sizeof(struct erofs_xattr_long_prefix); + } + + erofs_put_metabuf(&buf); + sbi->xattr_prefixes = pfs; + if (ret) + erofs_xattr_prefixes_cleanup(sb); + return ret; +} + #ifdef CONFIG_EROFS_FS_POSIX_ACL struct posix_acl *erofs_get_acl(struct inode *inode, int type, bool rcu) { diff --git a/fs/erofs/xattr.h b/fs/erofs/xattr.h index 0a43c9ee9f8f..f16283cb8c93 100644 --- a/fs/erofs/xattr.h +++ b/fs/erofs/xattr.h @@ -13,43 +13,21 @@ /* Attribute not found */ #define ENOATTR ENODATA -static inline unsigned int inlinexattr_header_size(struct inode *inode) -{ - return sizeof(struct erofs_xattr_ibody_header) + - sizeof(u32) * EROFS_I(inode)->xattr_shared_count; -} - -static inline erofs_blk_t xattrblock_addr(struct erofs_sb_info *sbi, - unsigned int xattr_id) -{ -#ifdef CONFIG_EROFS_FS_XATTR - return sbi->xattr_blkaddr + - xattr_id * sizeof(__u32) / EROFS_BLKSIZ; -#else - return 0; -#endif -} - -static inline unsigned int xattrblock_offset(struct erofs_sb_info *sbi, - unsigned int xattr_id) -{ - return (xattr_id * sizeof(__u32)) % EROFS_BLKSIZ; -} - #ifdef CONFIG_EROFS_FS_XATTR extern const struct xattr_handler erofs_xattr_user_handler; extern const struct xattr_handler erofs_xattr_trusted_handler; extern const struct xattr_handler erofs_xattr_security_handler; -static inline const struct xattr_handler *erofs_xattr_handler(unsigned int idx) +static inline const char *erofs_xattr_prefix(unsigned int idx, + struct dentry *dentry) { + const struct xattr_handler *handler = NULL; + static const struct xattr_handler *xattr_handler_map[] = { [EROFS_XATTR_INDEX_USER] = &erofs_xattr_user_handler, #ifdef CONFIG_EROFS_FS_POSIX_ACL - [EROFS_XATTR_INDEX_POSIX_ACL_ACCESS] = - &posix_acl_access_xattr_handler, - [EROFS_XATTR_INDEX_POSIX_ACL_DEFAULT] = - &posix_acl_default_xattr_handler, + [EROFS_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, + [EROFS_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default, #endif [EROFS_XATTR_INDEX_TRUSTED] = &erofs_xattr_trusted_handler, #ifdef CONFIG_EROFS_FS_SECURITY @@ -57,15 +35,24 @@ static inline const struct xattr_handler *erofs_xattr_handler(unsigned int idx) #endif }; - return idx && idx < ARRAY_SIZE(xattr_handler_map) ? - xattr_handler_map[idx] : NULL; + if (idx && idx < ARRAY_SIZE(xattr_handler_map)) + handler = xattr_handler_map[idx]; + + if (!xattr_handler_can_list(handler, dentry)) + return NULL; + + return xattr_prefix(handler); } extern const struct xattr_handler *erofs_xattr_handlers[]; +int erofs_xattr_prefixes_init(struct super_block *sb); +void erofs_xattr_prefixes_cleanup(struct super_block *sb); int erofs_getxattr(struct inode *, int, const char *, void *, size_t); ssize_t erofs_listxattr(struct dentry *, char *, size_t); #else +static inline int erofs_xattr_prefixes_init(struct super_block *sb) { return 0; } +static inline void erofs_xattr_prefixes_cleanup(struct super_block *sb) {} static inline int erofs_getxattr(struct inode *inode, int index, const char *name, void *buffer, size_t buffer_size) diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index f1708c77a991..45f21db2303a 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -807,7 +807,7 @@ static int z_erofs_register_pcluster(struct z_erofs_decompress_frontend *fe) if (ztailpacking) { pcl->obj.index = 0; /* which indicates ztailpacking */ - pcl->pageofs_in = erofs_blkoff(map->m_pa); + pcl->pageofs_in = erofs_blkoff(fe->inode->i_sb, map->m_pa); pcl->tailpacking_size = map->m_plen; } else { pcl->obj.index = map->m_pa >> PAGE_SHIFT; @@ -930,6 +930,7 @@ static int z_erofs_read_fragment(struct inode *inode, erofs_off_t pos, struct page *page, unsigned int pageofs, unsigned int len) { + struct super_block *sb = inode->i_sb; struct inode *packed_inode = EROFS_I_SB(inode)->packed_inode; struct erofs_buf buf = __EROFS_BUF_INITIALIZER; u8 *src, *dst; @@ -938,19 +939,19 @@ static int z_erofs_read_fragment(struct inode *inode, erofs_off_t pos, if (!packed_inode) return -EFSCORRUPTED; + buf.inode = packed_inode; pos += EROFS_I(inode)->z_fragmentoff; for (i = 0; i < len; i += cnt) { cnt = min_t(unsigned int, len - i, - EROFS_BLKSIZ - erofs_blkoff(pos)); - src = erofs_bread(&buf, packed_inode, - erofs_blknr(pos), EROFS_KMAP); + sb->s_blocksize - erofs_blkoff(sb, pos)); + src = erofs_bread(&buf, erofs_blknr(sb, pos), EROFS_KMAP); if (IS_ERR(src)) { erofs_put_metabuf(&buf); return PTR_ERR(src); } dst = kmap_local_page(page); - memcpy(dst + pageofs + i, src + erofs_blkoff(pos), cnt); + memcpy(dst + pageofs + i, src + erofs_blkoff(sb, pos), cnt); kunmap_local(dst); pos += cnt; } @@ -978,8 +979,6 @@ repeat: if (offset + cur < map->m_la || offset + cur >= map->m_la + map->m_llen) { - erofs_dbg("out-of-range map @ pos %llu", offset + cur); - if (z_erofs_collector_end(fe)) fe->backmost = false; map->m_la = offset + cur; @@ -1005,7 +1004,8 @@ repeat: void *mp; mp = erofs_read_metabuf(&fe->map.buf, inode->i_sb, - erofs_blknr(map->m_pa), EROFS_NO_KMAP); + erofs_blknr(inode->i_sb, map->m_pa), + EROFS_NO_KMAP); if (IS_ERR(mp)) { err = PTR_ERR(mp); erofs_err(inode->i_sb, @@ -1103,9 +1103,6 @@ out: if (err) z_erofs_page_mark_eio(page); z_erofs_onlinepage_endio(page); - - erofs_dbg("%s, finish page: %pK spiltted: %u map->m_llen %llu", - __func__, page, spiltted, map->m_llen); return err; } @@ -1726,11 +1723,11 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f, /* no device id here, thus it will always succeed */ mdev = (struct erofs_map_dev) { - .m_pa = blknr_to_addr(pcl->obj.index), + .m_pa = erofs_pos(sb, pcl->obj.index), }; (void)erofs_map_dev(sb, &mdev); - cur = erofs_blknr(mdev.m_pa); + cur = erofs_blknr(sb, mdev.m_pa); end = cur + pcl->pclusterpages; do { @@ -1764,7 +1761,7 @@ submit_bio_retry: last_bdev = mdev.m_bdev; bio->bi_iter.bi_sector = (sector_t)cur << - LOG_SECTORS_PER_BLOCK; + (sb->s_blocksize_bits - 9); bio->bi_private = q[JQ_SUBMIT]; if (f->readahead) bio->bi_opf |= REQ_RAHEAD; diff --git a/fs/erofs/zmap.c b/fs/erofs/zmap.c index 655da4d739cb..d37c5c89c728 100644 --- a/fs/erofs/zmap.c +++ b/fs/erofs/zmap.c @@ -7,24 +7,6 @@ #include <asm/unaligned.h> #include <trace/events/erofs.h> -int z_erofs_fill_inode(struct inode *inode) -{ - struct erofs_inode *const vi = EROFS_I(inode); - struct erofs_sb_info *sbi = EROFS_SB(inode->i_sb); - - if (!erofs_sb_has_big_pcluster(sbi) && - !erofs_sb_has_ztailpacking(sbi) && !erofs_sb_has_fragments(sbi) && - vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY) { - vi->z_advise = 0; - vi->z_algorithmtype[0] = 0; - vi->z_algorithmtype[1] = 0; - vi->z_logical_clusterbits = LOG_BLOCK_SIZE; - set_bit(EROFS_I_Z_INITED_BIT, &vi->flags); - } - inode->i_mapping->a_ops = &z_erofs_aops; - return 0; -} - struct z_erofs_maprecorder { struct inode *inode; struct erofs_map_blocks *map; @@ -45,47 +27,50 @@ static int legacy_load_cluster_from_disk(struct z_erofs_maprecorder *m, { struct inode *const inode = m->inode; struct erofs_inode *const vi = EROFS_I(inode); - const erofs_off_t pos = - Z_EROFS_VLE_LEGACY_INDEX_ALIGN(erofs_iloc(inode) + - vi->inode_isize + vi->xattr_isize) + - lcn * sizeof(struct z_erofs_vle_decompressed_index); - struct z_erofs_vle_decompressed_index *di; + const erofs_off_t pos = Z_EROFS_FULL_INDEX_ALIGN(erofs_iloc(inode) + + vi->inode_isize + vi->xattr_isize) + + lcn * sizeof(struct z_erofs_lcluster_index); + struct z_erofs_lcluster_index *di; unsigned int advise, type; m->kaddr = erofs_read_metabuf(&m->map->buf, inode->i_sb, - erofs_blknr(pos), EROFS_KMAP); + erofs_blknr(inode->i_sb, pos), EROFS_KMAP); if (IS_ERR(m->kaddr)) return PTR_ERR(m->kaddr); - m->nextpackoff = pos + sizeof(struct z_erofs_vle_decompressed_index); + m->nextpackoff = pos + sizeof(struct z_erofs_lcluster_index); m->lcn = lcn; - di = m->kaddr + erofs_blkoff(pos); + di = m->kaddr + erofs_blkoff(inode->i_sb, pos); advise = le16_to_cpu(di->di_advise); - type = (advise >> Z_EROFS_VLE_DI_CLUSTER_TYPE_BIT) & - ((1 << Z_EROFS_VLE_DI_CLUSTER_TYPE_BITS) - 1); + type = (advise >> Z_EROFS_LI_LCLUSTER_TYPE_BIT) & + ((1 << Z_EROFS_LI_LCLUSTER_TYPE_BITS) - 1); switch (type) { - case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: + case Z_EROFS_LCLUSTER_TYPE_NONHEAD: m->clusterofs = 1 << vi->z_logical_clusterbits; m->delta[0] = le16_to_cpu(di->di_u.delta[0]); - if (m->delta[0] & Z_EROFS_VLE_DI_D0_CBLKCNT) { + if (m->delta[0] & Z_EROFS_LI_D0_CBLKCNT) { if (!(vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 | Z_EROFS_ADVISE_BIG_PCLUSTER_2))) { DBG_BUGON(1); return -EFSCORRUPTED; } m->compressedblks = m->delta[0] & - ~Z_EROFS_VLE_DI_D0_CBLKCNT; + ~Z_EROFS_LI_D0_CBLKCNT; m->delta[0] = 1; } m->delta[1] = le16_to_cpu(di->di_u.delta[1]); break; - case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2: - if (advise & Z_EROFS_VLE_DI_PARTIAL_REF) + case Z_EROFS_LCLUSTER_TYPE_PLAIN: + case Z_EROFS_LCLUSTER_TYPE_HEAD1: + case Z_EROFS_LCLUSTER_TYPE_HEAD2: + if (advise & Z_EROFS_LI_PARTIAL_REF) m->partialref = true; m->clusterofs = le16_to_cpu(di->di_clusterofs); + if (m->clusterofs >= 1 << vi->z_logical_clusterbits) { + DBG_BUGON(1); + return -EFSCORRUPTED; + } m->pblk = le32_to_cpu(di->di_u.blkaddr); break; default: @@ -121,13 +106,13 @@ static int get_compacted_la_distance(unsigned int lclusterbits, lo = decode_compactedbits(lclusterbits, lomask, in, encodebits * i, &type); - if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) + if (type != Z_EROFS_LCLUSTER_TYPE_NONHEAD) return d1; ++d1; } while (++i < vcnt); - /* vcnt - 1 (Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) item */ - if (!(lo & Z_EROFS_VLE_DI_D0_CBLKCNT)) + /* vcnt - 1 (Z_EROFS_LCLUSTER_TYPE_NONHEAD) item */ + if (!(lo & Z_EROFS_LI_D0_CBLKCNT)) d1 += lo - 1; return d1; } @@ -156,7 +141,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, (vcnt << amortizedshift); big_pcluster = vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1; encodebits = ((vcnt << amortizedshift) - sizeof(__le32)) * 8 / vcnt; - eofs = erofs_blkoff(pos); + eofs = erofs_blkoff(m->inode->i_sb, pos); base = round_down(eofs, vcnt << amortizedshift); in = m->kaddr + base; @@ -165,19 +150,19 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, lo = decode_compactedbits(lclusterbits, lomask, in, encodebits * i, &type); m->type = type; - if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) { + if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) { m->clusterofs = 1 << lclusterbits; /* figure out lookahead_distance: delta[1] if needed */ if (lookahead) m->delta[1] = get_compacted_la_distance(lclusterbits, encodebits, vcnt, in, i); - if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) { + if (lo & Z_EROFS_LI_D0_CBLKCNT) { if (!big_pcluster) { DBG_BUGON(1); return -EFSCORRUPTED; } - m->compressedblks = lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT; + m->compressedblks = lo & ~Z_EROFS_LI_D0_CBLKCNT; m->delta[0] = 1; return 0; } else if (i + 1 != (int)vcnt) { @@ -191,9 +176,9 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, */ lo = decode_compactedbits(lclusterbits, lomask, in, encodebits * (i - 1), &type); - if (type != Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) + if (type != Z_EROFS_LCLUSTER_TYPE_NONHEAD) lo = 0; - else if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) + else if (lo & Z_EROFS_LI_D0_CBLKCNT) lo = 1; m->delta[0] = lo + 1; return 0; @@ -207,7 +192,7 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, --i; lo = decode_compactedbits(lclusterbits, lomask, in, encodebits * i, &type); - if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) + if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) i -= lo; if (i >= 0) @@ -219,10 +204,10 @@ static int unpack_compacted_index(struct z_erofs_maprecorder *m, --i; lo = decode_compactedbits(lclusterbits, lomask, in, encodebits * i, &type); - if (type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) { - if (lo & Z_EROFS_VLE_DI_D0_CBLKCNT) { + if (type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) { + if (lo & Z_EROFS_LI_D0_CBLKCNT) { --i; - nblk += lo & ~Z_EROFS_VLE_DI_D0_CBLKCNT; + nblk += lo & ~Z_EROFS_LI_D0_CBLKCNT; continue; } /* bigpcluster shouldn't have plain d0 == 1 */ @@ -249,7 +234,7 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m, const unsigned int lclusterbits = vi->z_logical_clusterbits; const erofs_off_t ebase = sizeof(struct z_erofs_map_header) + ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, 8); - const unsigned int totalidx = DIV_ROUND_UP(inode->i_size, EROFS_BLKSIZ); + unsigned int totalidx = erofs_iblks(inode); unsigned int compacted_4b_initial, compacted_2b; unsigned int amortizedshift; erofs_off_t pos; @@ -290,7 +275,7 @@ static int compacted_load_cluster_from_disk(struct z_erofs_maprecorder *m, out: pos += lcn * (1 << amortizedshift); m->kaddr = erofs_read_metabuf(&m->map->buf, inode->i_sb, - erofs_blknr(pos), EROFS_KMAP); + erofs_blknr(inode->i_sb, pos), EROFS_KMAP); if (IS_ERR(m->kaddr)) return PTR_ERR(m->kaddr); return unpack_compacted_index(m, amortizedshift, pos, lookahead); @@ -301,10 +286,10 @@ static int z_erofs_load_cluster_from_disk(struct z_erofs_maprecorder *m, { const unsigned int datamode = EROFS_I(m->inode)->datalayout; - if (datamode == EROFS_INODE_FLAT_COMPRESSION_LEGACY) + if (datamode == EROFS_INODE_COMPRESSED_FULL) return legacy_load_cluster_from_disk(m, lcn); - if (datamode == EROFS_INODE_FLAT_COMPRESSION) + if (datamode == EROFS_INODE_COMPRESSED_COMPACT) return compacted_load_cluster_from_disk(m, lcn, lookahead); return -EINVAL; @@ -326,7 +311,7 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, return err; switch (m->type) { - case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: + case Z_EROFS_LCLUSTER_TYPE_NONHEAD: if (!m->delta[0]) { erofs_err(m->inode->i_sb, "invalid lookback distance 0 @ nid %llu", @@ -336,9 +321,9 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, } lookback_distance = m->delta[0]; continue; - case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2: + case Z_EROFS_LCLUSTER_TYPE_PLAIN: + case Z_EROFS_LCLUSTER_TYPE_HEAD1: + case Z_EROFS_LCLUSTER_TYPE_HEAD2: m->headtype = m->type; m->map->m_la = (lcn << lclusterbits) | m->clusterofs; return 0; @@ -360,21 +345,22 @@ static int z_erofs_extent_lookback(struct z_erofs_maprecorder *m, static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, unsigned int initial_lcn) { + struct super_block *sb = m->inode->i_sb; struct erofs_inode *const vi = EROFS_I(m->inode); struct erofs_map_blocks *const map = m->map; const unsigned int lclusterbits = vi->z_logical_clusterbits; unsigned long lcn; int err; - DBG_BUGON(m->type != Z_EROFS_VLE_CLUSTER_TYPE_PLAIN && - m->type != Z_EROFS_VLE_CLUSTER_TYPE_HEAD1 && - m->type != Z_EROFS_VLE_CLUSTER_TYPE_HEAD2); + DBG_BUGON(m->type != Z_EROFS_LCLUSTER_TYPE_PLAIN && + m->type != Z_EROFS_LCLUSTER_TYPE_HEAD1 && + m->type != Z_EROFS_LCLUSTER_TYPE_HEAD2); DBG_BUGON(m->type != m->headtype); - if (m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN || - ((m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD1) && + if (m->headtype == Z_EROFS_LCLUSTER_TYPE_PLAIN || + ((m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD1) && !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1)) || - ((m->headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) && + ((m->headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) && !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2))) { map->m_plen = 1ULL << lclusterbits; return 0; @@ -396,19 +382,19 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, * BUG_ON in the debugging mode only for developers to notice that. */ DBG_BUGON(lcn == initial_lcn && - m->type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD); + m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD); switch (m->type) { - case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2: + case Z_EROFS_LCLUSTER_TYPE_PLAIN: + case Z_EROFS_LCLUSTER_TYPE_HEAD1: + case Z_EROFS_LCLUSTER_TYPE_HEAD2: /* * if the 1st NONHEAD lcluster is actually PLAIN or HEAD type * rather than CBLKCNT, it's a 1 lcluster-sized pcluster. */ - m->compressedblks = 1 << (lclusterbits - LOG_BLOCK_SIZE); + m->compressedblks = 1 << (lclusterbits - sb->s_blocksize_bits); break; - case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: + case Z_EROFS_LCLUSTER_TYPE_NONHEAD: if (m->delta[0] != 1) goto err_bonus_cblkcnt; if (m->compressedblks) @@ -422,7 +408,7 @@ static int z_erofs_get_extent_compressedlen(struct z_erofs_maprecorder *m, return -EFSCORRUPTED; } out: - map->m_plen = (u64)m->compressedblks << LOG_BLOCK_SIZE; + map->m_plen = erofs_pos(sb, m->compressedblks); return 0; err_bonus_cblkcnt: erofs_err(m->inode->i_sb, @@ -452,12 +438,12 @@ static int z_erofs_get_extent_decompressedlen(struct z_erofs_maprecorder *m) if (err) return err; - if (m->type == Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD) { + if (m->type == Z_EROFS_LCLUSTER_TYPE_NONHEAD) { DBG_BUGON(!m->delta[1] && m->clusterofs != 1 << lclusterbits); - } else if (m->type == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN || - m->type == Z_EROFS_VLE_CLUSTER_TYPE_HEAD1 || - m->type == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) { + } else if (m->type == Z_EROFS_LCLUSTER_TYPE_PLAIN || + m->type == Z_EROFS_LCLUSTER_TYPE_HEAD1 || + m->type == Z_EROFS_LCLUSTER_TYPE_HEAD2) { /* go on until the next HEAD lcluster */ if (lcn != headlcn) break; @@ -476,8 +462,7 @@ static int z_erofs_get_extent_decompressedlen(struct z_erofs_maprecorder *m) } static int z_erofs_do_map_blocks(struct inode *inode, - struct erofs_map_blocks *map, - int flags) + struct erofs_map_blocks *map, int flags) { struct erofs_inode *const vi = EROFS_I(inode); bool ztailpacking = vi->z_advise & Z_EROFS_ADVISE_INLINE_PCLUSTER; @@ -507,9 +492,9 @@ static int z_erofs_do_map_blocks(struct inode *inode, end = (m.lcn + 1ULL) << lclusterbits; switch (m.type) { - case Z_EROFS_VLE_CLUSTER_TYPE_PLAIN: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD1: - case Z_EROFS_VLE_CLUSTER_TYPE_HEAD2: + case Z_EROFS_LCLUSTER_TYPE_PLAIN: + case Z_EROFS_LCLUSTER_TYPE_HEAD1: + case Z_EROFS_LCLUSTER_TYPE_HEAD2: if (endoff >= m.clusterofs) { m.headtype = m.type; map->m_la = (m.lcn << lclusterbits) | m.clusterofs; @@ -534,7 +519,7 @@ static int z_erofs_do_map_blocks(struct inode *inode, map->m_flags |= EROFS_MAP_FULL_MAPPED; m.delta[0] = 1; fallthrough; - case Z_EROFS_VLE_CLUSTER_TYPE_NONHEAD: + case Z_EROFS_LCLUSTER_TYPE_NONHEAD: /* get the corresponding first chunk */ err = z_erofs_extent_lookback(&m, m.delta[0]); if (err) @@ -555,7 +540,7 @@ static int z_erofs_do_map_blocks(struct inode *inode, vi->z_tailextent_headlcn = m.lcn; /* for non-compact indexes, fragmentoff is 64 bits */ if (fragment && - vi->datalayout == EROFS_INODE_FLAT_COMPRESSION_LEGACY) + vi->datalayout == EROFS_INODE_COMPRESSED_FULL) vi->z_fragmentoff |= (u64)m.pblk << 32; } if (ztailpacking && m.lcn == vi->z_tailextent_headlcn) { @@ -565,13 +550,13 @@ static int z_erofs_do_map_blocks(struct inode *inode, } else if (fragment && m.lcn == vi->z_tailextent_headlcn) { map->m_flags |= EROFS_MAP_FRAGMENT; } else { - map->m_pa = blknr_to_addr(m.pblk); + map->m_pa = erofs_pos(inode->i_sb, m.pblk); err = z_erofs_get_extent_compressedlen(&m, initial_lcn); if (err) goto unmap_out; } - if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_PLAIN) { + if (m.headtype == Z_EROFS_LCLUSTER_TYPE_PLAIN) { if (map->m_llen > map->m_plen) { DBG_BUGON(1); err = -EFSCORRUPTED; @@ -583,7 +568,7 @@ static int z_erofs_do_map_blocks(struct inode *inode, else map->m_algorithmformat = Z_EROFS_COMPRESSION_SHIFTED; - } else if (m.headtype == Z_EROFS_VLE_CLUSTER_TYPE_HEAD2) { + } else if (m.headtype == Z_EROFS_LCLUSTER_TYPE_HEAD2) { map->m_algorithmformat = vi->z_algorithmtype[1]; } else { map->m_algorithmformat = vi->z_algorithmtype[0]; @@ -592,7 +577,7 @@ static int z_erofs_do_map_blocks(struct inode *inode, if ((flags & EROFS_GET_BLOCKS_FIEMAP) || ((flags & EROFS_GET_BLOCKS_READMORE) && map->m_algorithmformat == Z_EROFS_COMPRESSION_LZMA && - map->m_llen >= EROFS_BLKSIZ)) { + map->m_llen >= i_blocksize(inode))) { err = z_erofs_get_extent_decompressedlen(&m); if (!err) map->m_flags |= EROFS_MAP_FULL_MAPPED; @@ -600,9 +585,6 @@ static int z_erofs_do_map_blocks(struct inode *inode, unmap_out: erofs_unmap_metabuf(&m.map->buf); - erofs_dbg("%s, m_la %llu m_pa %llu m_llen %llu m_plen %llu m_flags 0%o", - __func__, map->m_la, map->m_pa, - map->m_llen, map->m_plen, map->m_flags); return err; } @@ -633,13 +615,13 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) goto out_unlock; pos = ALIGN(erofs_iloc(inode) + vi->inode_isize + vi->xattr_isize, 8); - kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(pos), EROFS_KMAP); + kaddr = erofs_read_metabuf(&buf, sb, erofs_blknr(sb, pos), EROFS_KMAP); if (IS_ERR(kaddr)) { err = PTR_ERR(kaddr); goto out_unlock; } - h = kaddr + erofs_blkoff(pos); + h = kaddr + erofs_blkoff(sb, pos); /* * if the highest bit of the 8-byte map header is set, the whole file * is stored in the packed inode. The rest bits keeps z_fragmentoff. @@ -663,7 +645,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) goto out_put_metabuf; } - vi->z_logical_clusterbits = LOG_BLOCK_SIZE + (h->h_clusterbits & 7); + vi->z_logical_clusterbits = sb->s_blocksize_bits + (h->h_clusterbits & 7); if (!erofs_sb_has_big_pcluster(EROFS_SB(sb)) && vi->z_advise & (Z_EROFS_ADVISE_BIG_PCLUSTER_1 | Z_EROFS_ADVISE_BIG_PCLUSTER_2)) { @@ -672,7 +654,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) err = -EFSCORRUPTED; goto out_put_metabuf; } - if (vi->datalayout == EROFS_INODE_FLAT_COMPRESSION && + if (vi->datalayout == EROFS_INODE_COMPRESSED_COMPACT && !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_1) ^ !(vi->z_advise & Z_EROFS_ADVISE_BIG_PCLUSTER_2)) { erofs_err(sb, "big pcluster head1/2 of compact indexes should be consistent for nid %llu", @@ -692,7 +674,7 @@ static int z_erofs_fill_inode_lazy(struct inode *inode) erofs_put_metabuf(&map.buf); if (!map.m_plen || - erofs_blkoff(map.m_pa) + map.m_plen > EROFS_BLKSIZ) { + erofs_blkoff(sb, map.m_pa) + map.m_plen > sb->s_blocksize) { erofs_err(sb, "invalid tail-packing pclustersize %llu", map.m_plen); err = -EFSCORRUPTED; diff --git a/fs/eventfd.c b/fs/eventfd.c index 249ca6c0b784..95850a13ce8d 100644 --- a/fs/eventfd.c +++ b/fs/eventfd.c @@ -228,7 +228,6 @@ static ssize_t eventfd_read(struct kiocb *iocb, struct iov_iter *to) struct file *file = iocb->ki_filp; struct eventfd_ctx *ctx = file->private_data; __u64 ucnt = 0; - DECLARE_WAITQUEUE(wait, current); if (iov_iter_count(to) < sizeof(ucnt)) return -EINVAL; @@ -239,23 +238,11 @@ static ssize_t eventfd_read(struct kiocb *iocb, struct iov_iter *to) spin_unlock_irq(&ctx->wqh.lock); return -EAGAIN; } - __add_wait_queue(&ctx->wqh, &wait); - for (;;) { - set_current_state(TASK_INTERRUPTIBLE); - if (ctx->count) - break; - if (signal_pending(current)) { - __remove_wait_queue(&ctx->wqh, &wait); - __set_current_state(TASK_RUNNING); - spin_unlock_irq(&ctx->wqh.lock); - return -ERESTARTSYS; - } + + if (wait_event_interruptible_locked_irq(ctx->wqh, ctx->count)) { spin_unlock_irq(&ctx->wqh.lock); - schedule(); - spin_lock_irq(&ctx->wqh.lock); + return -ERESTARTSYS; } - __remove_wait_queue(&ctx->wqh, &wait); - __set_current_state(TASK_RUNNING); } eventfd_ctx_do_read(ctx, &ucnt); current->in_eventfd = 1; @@ -275,7 +262,6 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c struct eventfd_ctx *ctx = file->private_data; ssize_t res; __u64 ucnt; - DECLARE_WAITQUEUE(wait, current); if (count < sizeof(ucnt)) return -EINVAL; @@ -288,23 +274,10 @@ static ssize_t eventfd_write(struct file *file, const char __user *buf, size_t c if (ULLONG_MAX - ctx->count > ucnt) res = sizeof(ucnt); else if (!(file->f_flags & O_NONBLOCK)) { - __add_wait_queue(&ctx->wqh, &wait); - for (res = 0;;) { - set_current_state(TASK_INTERRUPTIBLE); - if (ULLONG_MAX - ctx->count > ucnt) { - res = sizeof(ucnt); - break; - } - if (signal_pending(current)) { - res = -ERESTARTSYS; - break; - } - spin_unlock_irq(&ctx->wqh.lock); - schedule(); - spin_lock_irq(&ctx->wqh.lock); - } - __remove_wait_queue(&ctx->wqh, &wait); - __set_current_state(TASK_RUNNING); + res = wait_event_interruptible_locked_irq(ctx->wqh, + ULLONG_MAX - ctx->count > ucnt); + if (!res) + res = sizeof(ucnt); } if (likely(res > 0)) { ctx->count += ucnt; diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 64659b110973..4f757a71f99b 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -483,8 +483,8 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) * (efd1) notices that it may have some event ready, so it needs to wake up * the waiters on its poll wait list (efd2). So it calls ep_poll_safewake() * that ends up in another wake_up(), after having checked about the - * recursion constraints. That are, no more than EP_MAX_POLLWAKE_NESTS, to - * avoid stack blasting. + * recursion constraints. That are, no more than EP_MAX_NESTS, to avoid + * stack blasting. * * When CONFIG_DEBUG_LOCK_ALLOC is enabled, make sure lockdep can handle * this special case of epoll. @@ -2042,6 +2042,19 @@ SYSCALL_DEFINE1(epoll_create, int, size) return do_epoll_create(0); } +#ifdef CONFIG_PM_SLEEP +static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) +{ + if ((epev->events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND)) + epev->events &= ~EPOLLWAKEUP; +} +#else +static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) +{ + epev->events &= ~EPOLLWAKEUP; +} +#endif + static inline int epoll_mutex_lock(struct mutex *mutex, int depth, bool nonblock) { diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c index 641abfa4b718..b126af5f8b15 100644 --- a/fs/ext2/xattr.c +++ b/fs/ext2/xattr.c @@ -101,8 +101,8 @@ static void ext2_xattr_rehash(struct ext2_xattr_header *, static const struct xattr_handler *ext2_xattr_handler_map[] = { [EXT2_XATTR_INDEX_USER] = &ext2_xattr_user_handler, #ifdef CONFIG_EXT2_FS_POSIX_ACL - [EXT2_XATTR_INDEX_POSIX_ACL_ACCESS] = &posix_acl_access_xattr_handler, - [EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler, + [EXT2_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, + [EXT2_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default, #endif [EXT2_XATTR_INDEX_TRUSTED] = &ext2_xattr_trusted_handler, #ifdef CONFIG_EXT2_FS_SECURITY @@ -113,10 +113,6 @@ static const struct xattr_handler *ext2_xattr_handler_map[] = { const struct xattr_handler *ext2_xattr_handlers[] = { &ext2_xattr_user_handler, &ext2_xattr_trusted_handler, -#ifdef CONFIG_EXT2_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif #ifdef CONFIG_EXT2_FS_SECURITY &ext2_xattr_security_handler, #endif @@ -125,14 +121,18 @@ const struct xattr_handler *ext2_xattr_handlers[] = { #define EA_BLOCK_CACHE(inode) (EXT2_SB(inode->i_sb)->s_ea_block_cache) -static inline const struct xattr_handler * -ext2_xattr_handler(int name_index) +static inline const char *ext2_xattr_prefix(int name_index, + struct dentry *dentry) { const struct xattr_handler *handler = NULL; if (name_index > 0 && name_index < ARRAY_SIZE(ext2_xattr_handler_map)) handler = ext2_xattr_handler_map[name_index]; - return handler; + + if (!xattr_handler_can_list(handler, dentry)) + return NULL; + + return xattr_prefix(handler); } static bool @@ -333,11 +333,10 @@ bad_block: /* list the attribute names */ for (entry = FIRST_ENTRY(bh); !IS_LAST_ENTRY(entry); entry = EXT2_XATTR_NEXT(entry)) { - const struct xattr_handler *handler = - ext2_xattr_handler(entry->e_name_index); + const char *prefix; - if (handler && (!handler->list || handler->list(dentry))) { - const char *prefix = handler->prefix ?: handler->name; + prefix = ext2_xattr_prefix(entry->e_name_index, dentry); + if (prefix) { size_t prefix_len = strlen(prefix); size_t size = prefix_len + entry->e_name_len + 1; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index f43e526112ae..76d1ef0efbf4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2500,7 +2500,7 @@ static void ext4_apply_quota_options(struct fs_context *fc, qname = rcu_replace_pointer(sbi->s_qf_names[i], qname, lockdep_is_held(&sb->s_umount)); if (qname) - kfree_rcu(qname); + kfree_rcu_mightsleep(qname); } } diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c index 767454d74cd6..dadad29bd81b 100644 --- a/fs/ext4/xattr.c +++ b/fs/ext4/xattr.c @@ -88,8 +88,8 @@ static void ext4_xattr_rehash(struct ext4_xattr_header *); static const struct xattr_handler * const ext4_xattr_handler_map[] = { [EXT4_XATTR_INDEX_USER] = &ext4_xattr_user_handler, #ifdef CONFIG_EXT4_FS_POSIX_ACL - [EXT4_XATTR_INDEX_POSIX_ACL_ACCESS] = &posix_acl_access_xattr_handler, - [EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler, + [EXT4_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, + [EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default, #endif [EXT4_XATTR_INDEX_TRUSTED] = &ext4_xattr_trusted_handler, #ifdef CONFIG_EXT4_FS_SECURITY @@ -101,10 +101,6 @@ static const struct xattr_handler * const ext4_xattr_handler_map[] = { const struct xattr_handler *ext4_xattr_handlers[] = { &ext4_xattr_user_handler, &ext4_xattr_trusted_handler, -#ifdef CONFIG_EXT4_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif #ifdef CONFIG_EXT4_FS_SECURITY &ext4_xattr_security_handler, #endif @@ -173,14 +169,18 @@ static void ext4_xattr_block_csum_set(struct inode *inode, bh->b_blocknr, BHDR(bh)); } -static inline const struct xattr_handler * -ext4_xattr_handler(int name_index) +static inline const char *ext4_xattr_prefix(int name_index, + struct dentry *dentry) { const struct xattr_handler *handler = NULL; if (name_index > 0 && name_index < ARRAY_SIZE(ext4_xattr_handler_map)) handler = ext4_xattr_handler_map[name_index]; - return handler; + + if (!xattr_handler_can_list(handler, dentry)) + return NULL; + + return xattr_prefix(handler); } static int @@ -740,11 +740,10 @@ ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry, size_t rest = buffer_size; for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { - const struct xattr_handler *handler = - ext4_xattr_handler(entry->e_name_index); + const char *prefix; - if (handler && (!handler->list || handler->list(dentry))) { - const char *prefix = handler->prefix ?: handler->name; + prefix = ext4_xattr_prefix(entry->e_name_index, dentry); + if (prefix) { size_t prefix_len = strlen(prefix); size_t size = prefix_len + entry->e_name_len + 1; diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c index d92edbbdc30e..213805d3592c 100644 --- a/fs/f2fs/xattr.c +++ b/fs/f2fs/xattr.c @@ -192,8 +192,8 @@ const struct xattr_handler f2fs_xattr_security_handler = { static const struct xattr_handler *f2fs_xattr_handler_map[] = { [F2FS_XATTR_INDEX_USER] = &f2fs_xattr_user_handler, #ifdef CONFIG_F2FS_FS_POSIX_ACL - [F2FS_XATTR_INDEX_POSIX_ACL_ACCESS] = &posix_acl_access_xattr_handler, - [F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT] = &posix_acl_default_xattr_handler, + [F2FS_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, + [F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default, #endif [F2FS_XATTR_INDEX_TRUSTED] = &f2fs_xattr_trusted_handler, #ifdef CONFIG_F2FS_FS_SECURITY @@ -204,10 +204,6 @@ static const struct xattr_handler *f2fs_xattr_handler_map[] = { const struct xattr_handler *f2fs_xattr_handlers[] = { &f2fs_xattr_user_handler, -#ifdef CONFIG_F2FS_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif &f2fs_xattr_trusted_handler, #ifdef CONFIG_F2FS_FS_SECURITY &f2fs_xattr_security_handler, @@ -216,13 +212,18 @@ const struct xattr_handler *f2fs_xattr_handlers[] = { NULL, }; -static inline const struct xattr_handler *f2fs_xattr_handler(int index) +static inline const char *f2fs_xattr_prefix(int index, + struct dentry *dentry) { const struct xattr_handler *handler = NULL; if (index > 0 && index < ARRAY_SIZE(f2fs_xattr_handler_map)) handler = f2fs_xattr_handler_map[index]; - return handler; + + if (!xattr_handler_can_list(handler, dentry)) + return NULL; + + return xattr_prefix(handler); } static struct f2fs_xattr_entry *__find_xattr(void *base_addr, @@ -573,12 +574,12 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) last_base_addr = (void *)base_addr + XATTR_SIZE(inode); list_for_each_xattr(entry, base_addr) { - const struct xattr_handler *handler = - f2fs_xattr_handler(entry->e_name_index); const char *prefix; size_t prefix_len; size_t size; + prefix = f2fs_xattr_prefix(entry->e_name_index, dentry); + if ((void *)(entry) + sizeof(__u32) > last_base_addr || (void *)XATTR_NEXT_ENTRY(entry) > last_base_addr) { f2fs_err(F2FS_I_SB(inode), "inode (%lu) has corrupted xattr", @@ -590,10 +591,9 @@ ssize_t f2fs_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) goto cleanup; } - if (!handler || (handler->list && !handler->list(dentry))) + if (!prefix) continue; - prefix = xattr_prefix(handler); prefix_len = strlen(prefix); size = prefix_len + entry->e_name_len + 1; if (buffer) { diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 195dc23e0d83..1db3e3c24b43 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -978,6 +978,16 @@ restart: continue; } + /* + * If wb_tryget fails, the wb has been shutdown, skip it. + * + * Pin @wb so that it stays on @bdi->wb_list. This allows + * continuing iteration from @wb after dropping and + * regrabbing rcu read lock. + */ + if (!wb_tryget(wb)) + continue; + /* alloc failed, execute synchronously using on-stack fallback */ work = &fallback_work; *work = *base_work; @@ -986,13 +996,6 @@ restart: work->done = &fallback_work_done; wb_queue_work(wb, work); - - /* - * Pin @wb so that it stays on @bdi->wb_list. This allows - * continuing iteration from @wb after dropping and - * regrabbing rcu read lock. - */ - wb_get(wb); last_wb = wb; rcu_read_unlock(); diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index eb4f88e3dc97..1a8f82f478cb 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -2257,30 +2257,31 @@ static long fuse_dev_ioctl(struct file *file, unsigned int cmd, int res; int oldfd; struct fuse_dev *fud = NULL; + struct fd f; switch (cmd) { case FUSE_DEV_IOC_CLONE: - res = -EFAULT; - if (!get_user(oldfd, (__u32 __user *)arg)) { - struct file *old = fget(oldfd); - - res = -EINVAL; - if (old) { - /* - * Check against file->f_op because CUSE - * uses the same ioctl handler. - */ - if (old->f_op == file->f_op) - fud = fuse_get_dev(old); - - if (fud) { - mutex_lock(&fuse_mutex); - res = fuse_device_clone(fud->fc, file); - mutex_unlock(&fuse_mutex); - } - fput(old); - } + if (get_user(oldfd, (__u32 __user *)arg)) + return -EFAULT; + + f = fdget(oldfd); + if (!f.file) + return -EINVAL; + + /* + * Check against file->f_op because CUSE + * uses the same ioctl handler. + */ + if (f.file->f_op == file->f_op) + fud = fuse_get_dev(f.file); + + res = -EINVAL; + if (fud) { + mutex_lock(&fuse_mutex); + res = fuse_device_clone(fud->fc, file); + mutex_unlock(&fuse_mutex); } + fdput(f); break; default: res = -ENOTTY; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index de37a3a06a71..89d97f6188e0 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1419,7 +1419,7 @@ out: static inline unsigned long fuse_get_user_addr(const struct iov_iter *ii) { - return (unsigned long)ii->iov->iov_base + ii->iov_offset; + return (unsigned long)iter_iov(ii)->iov_base + ii->iov_offset; } static inline size_t fuse_get_frag_size(const struct iov_iter *ii, diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c index adf6d17cf033..93b36d026bb4 100644 --- a/fs/gfs2/xattr.c +++ b/fs/gfs2/xattr.c @@ -1501,8 +1501,6 @@ const struct xattr_handler *gfs2_xattr_handlers_max[] = { /* GFS2_FS_FORMAT_MIN */ &gfs2_xattr_user_handler, &gfs2_xattr_security_handler, - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, NULL, }; diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index abb91f5fae92..b21660475ac1 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -511,7 +511,11 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) if (type == HFSPLUS_FOLDER) { struct hfsplus_cat_folder *folder = &entry.folder; - WARN_ON(fd->entrylength < sizeof(struct hfsplus_cat_folder)); + if (fd->entrylength < sizeof(struct hfsplus_cat_folder)) { + pr_err("bad catalog folder entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd->bnode, &entry, fd->entryoffset, sizeof(struct hfsplus_cat_folder)); hfsplus_get_perms(inode, &folder->permissions, 1); @@ -531,7 +535,11 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) } else if (type == HFSPLUS_FILE) { struct hfsplus_cat_file *file = &entry.file; - WARN_ON(fd->entrylength < sizeof(struct hfsplus_cat_file)); + if (fd->entrylength < sizeof(struct hfsplus_cat_file)) { + pr_err("bad catalog file entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd->bnode, &entry, fd->entryoffset, sizeof(struct hfsplus_cat_file)); @@ -562,6 +570,7 @@ int hfsplus_cat_read_inode(struct inode *inode, struct hfs_find_data *fd) pr_err("bad catalog entry used to create inode\n"); res = -EIO; } +out: return res; } @@ -570,6 +579,7 @@ int hfsplus_cat_write_inode(struct inode *inode) struct inode *main_inode = inode; struct hfs_find_data fd; hfsplus_cat_entry entry; + int res = 0; if (HFSPLUS_IS_RSRC(inode)) main_inode = HFSPLUS_I(inode)->rsrc_inode; @@ -588,7 +598,11 @@ int hfsplus_cat_write_inode(struct inode *inode) if (S_ISDIR(main_inode->i_mode)) { struct hfsplus_cat_folder *folder = &entry.folder; - WARN_ON(fd.entrylength < sizeof(struct hfsplus_cat_folder)); + if (fd.entrylength < sizeof(struct hfsplus_cat_folder)) { + pr_err("bad catalog folder entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, sizeof(struct hfsplus_cat_folder)); /* simple node checks? */ @@ -613,7 +627,11 @@ int hfsplus_cat_write_inode(struct inode *inode) } else { struct hfsplus_cat_file *file = &entry.file; - WARN_ON(fd.entrylength < sizeof(struct hfsplus_cat_file)); + if (fd.entrylength < sizeof(struct hfsplus_cat_file)) { + pr_err("bad catalog file entry\n"); + res = -EIO; + goto out; + } hfs_bnode_read(fd.bnode, &entry, fd.entryoffset, sizeof(struct hfsplus_cat_file)); hfsplus_inode_write_fork(inode, &file->data_fork); @@ -634,7 +652,7 @@ int hfsplus_cat_write_inode(struct inode *inode) set_bit(HFSPLUS_I_CAT_DIRTY, &HFSPLUS_I(inode)->flags); out: hfs_find_exit(&fd); - return 0; + return res; } int hfsplus_fileattr_get(struct dentry *dentry, struct fileattr *fa) diff --git a/fs/inode.c b/fs/inode.c index 4558dc2f1355..3ec5a8f7b644 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -1804,8 +1804,8 @@ EXPORT_SYMBOL(bmap); /* * With relative atime, only update atime if the previous atime is - * earlier than either the ctime or mtime or if at least a day has - * passed since the last atime update. + * earlier than or equal to either the ctime or mtime, + * or if at least a day has passed since the last atime update. */ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode, struct timespec64 now) @@ -1814,12 +1814,12 @@ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode, if (!(mnt->mnt_flags & MNT_RELATIME)) return 1; /* - * Is mtime younger than atime? If yes, update atime: + * Is mtime younger than or equal to atime? If yes, update atime: */ if (timespec64_compare(&inode->i_mtime, &inode->i_atime) >= 0) return 1; /* - * Is ctime younger than atime? If yes, update atime: + * Is ctime younger than or equal to atime? If yes, update atime: */ if (timespec64_compare(&inode->i_ctime, &inode->i_atime) >= 0) return 1; diff --git a/fs/internal.h b/fs/internal.h index dc4eb91a577a..ab36ed8fa41c 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -259,8 +259,6 @@ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *po /* * fs/attr.c */ -int setattr_should_drop_sgid(struct mnt_idmap *idmap, - const struct inode *inode); struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns); struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap); void mnt_idmap_put(struct mnt_idmap *idmap); diff --git a/fs/jffs2/xattr.c b/fs/jffs2/xattr.c index da3e18503c65..aa4048a27f31 100644 --- a/fs/jffs2/xattr.c +++ b/fs/jffs2/xattr.c @@ -920,16 +920,13 @@ const struct xattr_handler *jffs2_xattr_handlers[] = { #ifdef CONFIG_JFFS2_FS_SECURITY &jffs2_security_xattr_handler, #endif -#ifdef CONFIG_JFFS2_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif &jffs2_trusted_xattr_handler, NULL }; -static const struct xattr_handler *xprefix_to_handler(int xprefix) { - const struct xattr_handler *ret; +static const char *jffs2_xattr_prefix(int xprefix, struct dentry *dentry) +{ + const struct xattr_handler *ret = NULL; switch (xprefix) { case JFFS2_XPREFIX_USER: @@ -942,20 +939,23 @@ static const struct xattr_handler *xprefix_to_handler(int xprefix) { #endif #ifdef CONFIG_JFFS2_FS_POSIX_ACL case JFFS2_XPREFIX_ACL_ACCESS: - ret = &posix_acl_access_xattr_handler; + ret = &nop_posix_acl_access; break; case JFFS2_XPREFIX_ACL_DEFAULT: - ret = &posix_acl_default_xattr_handler; + ret = &nop_posix_acl_default; break; #endif case JFFS2_XPREFIX_TRUSTED: ret = &jffs2_trusted_xattr_handler; break; default: - ret = NULL; - break; + return NULL; } - return ret; + + if (!xattr_handler_can_list(ret, dentry)) + return NULL; + + return xattr_prefix(ret); } ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size) @@ -966,7 +966,6 @@ ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size) struct jffs2_inode_cache *ic = f->inocache; struct jffs2_xattr_ref *ref, **pref; struct jffs2_xattr_datum *xd; - const struct xattr_handler *xhandle; const char *prefix; ssize_t prefix_len, len, rc; int retry = 0; @@ -998,10 +997,10 @@ ssize_t jffs2_listxattr(struct dentry *dentry, char *buffer, size_t size) goto out; } } - xhandle = xprefix_to_handler(xd->xprefix); - if (!xhandle || (xhandle->list && !xhandle->list(dentry))) + + prefix = jffs2_xattr_prefix(xd->xprefix, dentry); + if (!prefix) continue; - prefix = xhandle->prefix ?: xhandle->name; prefix_len = strlen(prefix); rc = prefix_len + xd->name_len + 1; diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c index 2e8461ce74de..961569c11159 100644 --- a/fs/jfs/jfs_metapage.c +++ b/fs/jfs/jfs_metapage.c @@ -691,6 +691,35 @@ void grab_metapage(struct metapage * mp) unlock_page(mp->page); } +static int metapage_write_one(struct page *page) +{ + struct folio *folio = page_folio(page); + struct address_space *mapping = folio->mapping; + struct writeback_control wbc = { + .sync_mode = WB_SYNC_ALL, + .nr_to_write = folio_nr_pages(folio), + }; + int ret = 0; + + BUG_ON(!folio_test_locked(folio)); + + folio_wait_writeback(folio); + + if (folio_clear_dirty_for_io(folio)) { + folio_get(folio); + ret = metapage_writepage(page, &wbc); + if (ret == 0) + folio_wait_writeback(folio); + folio_put(folio); + } else { + folio_unlock(folio); + } + + if (!ret) + ret = filemap_check_errors(mapping); + return ret; +} + void force_metapage(struct metapage *mp) { struct page *page = mp->page; @@ -700,8 +729,8 @@ void force_metapage(struct metapage *mp) get_page(page); lock_page(page); set_page_dirty(page); - if (write_one_page(page)) - jfs_error(mp->sb, "write_one_page() failed\n"); + if (metapage_write_one(page)) + jfs_error(mp->sb, "metapage_write_one() failed\n"); clear_bit(META_forcewrite, &mp->flag); put_page(page); } @@ -746,9 +775,9 @@ void release_metapage(struct metapage * mp) set_page_dirty(page); if (test_bit(META_sync, &mp->flag)) { clear_bit(META_sync, &mp->flag); - if (write_one_page(page)) - jfs_error(mp->sb, "write_one_page() failed\n"); - lock_page(page); /* write_one_page unlocks the page */ + if (metapage_write_one(page)) + jfs_error(mp->sb, "metapage_write_one() failed\n"); + lock_page(page); } } else if (mp->lsn) /* discard_metapage doesn't remove it */ remove_from_logsync(mp); diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c index f817798fa1eb..931e50018f88 100644 --- a/fs/jfs/xattr.c +++ b/fs/jfs/xattr.c @@ -986,10 +986,6 @@ static const struct xattr_handler jfs_trusted_xattr_handler = { }; const struct xattr_handler *jfs_xattr_handlers[] = { -#ifdef CONFIG_JFS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif &jfs_os2_xattr_handler, &jfs_user_xattr_handler, &jfs_security_xattr_handler, diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c index ef00b5fe8cee..90de0e498371 100644 --- a/fs/kernfs/dir.c +++ b/fs/kernfs/dir.c @@ -1748,12 +1748,6 @@ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, return error; } -/* Relationship between mode and the DT_xxx types */ -static inline unsigned char dt_type(struct kernfs_node *kn) -{ - return (kn->mode >> 12) & 15; -} - static int kernfs_dir_fop_release(struct inode *inode, struct file *filp) { kernfs_put(filp->private_data); @@ -1831,7 +1825,7 @@ static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) pos; pos = kernfs_dir_next_pos(ns, parent, ctx->pos, pos)) { const char *name = pos->name; - unsigned int type = dt_type(pos); + unsigned int type = fs_umode_to_dtype(pos->mode); int len = strlen(name); ino_t ino = kernfs_ino(pos); diff --git a/fs/ksmbd/connection.c b/fs/ksmbd/connection.c index 115a67d2cf78..365ac32af505 100644 --- a/fs/ksmbd/connection.c +++ b/fs/ksmbd/connection.c @@ -112,10 +112,8 @@ void ksmbd_conn_enqueue_request(struct ksmbd_work *work) struct ksmbd_conn *conn = work->conn; struct list_head *requests_queue = NULL; - if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) { + if (conn->ops->get_cmd_val(work) != SMB2_CANCEL_HE) requests_queue = &conn->requests; - work->synchronous = true; - } if (requests_queue) { atomic_inc(&conn->req_running); @@ -136,14 +134,14 @@ int ksmbd_conn_try_dequeue_request(struct ksmbd_work *work) if (!work->multiRsp) atomic_dec(&conn->req_running); - spin_lock(&conn->request_lock); if (!work->multiRsp) { + spin_lock(&conn->request_lock); list_del_init(&work->request_entry); - if (!work->synchronous) - list_del_init(&work->async_request_entry); + spin_unlock(&conn->request_lock); + if (work->asynchronous) + release_async_work(work); ret = 0; } - spin_unlock(&conn->request_lock); wake_up_all(&conn->req_running_q); return ret; @@ -326,10 +324,7 @@ int ksmbd_conn_handler_loop(void *p) /* 4 for rfc1002 length field */ size = pdu_size + 4; - conn->request_buf = kvmalloc(size, - GFP_KERNEL | - __GFP_NOWARN | - __GFP_NORETRY); + conn->request_buf = kvmalloc(size, GFP_KERNEL); if (!conn->request_buf) break; diff --git a/fs/ksmbd/ksmbd_work.h b/fs/ksmbd/ksmbd_work.h index 3234f2cf6327..f8ae6144c0ae 100644 --- a/fs/ksmbd/ksmbd_work.h +++ b/fs/ksmbd/ksmbd_work.h @@ -68,7 +68,7 @@ struct ksmbd_work { /* Request is encrypted */ bool encrypted:1; /* Is this SYNC or ASYNC ksmbd_work */ - bool synchronous:1; + bool asynchronous:1; bool need_invalidate_rkey:1; unsigned int remote_key; diff --git a/fs/ksmbd/server.c b/fs/ksmbd/server.c index 394b6ceac431..0d8242789dc8 100644 --- a/fs/ksmbd/server.c +++ b/fs/ksmbd/server.c @@ -289,10 +289,7 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn) work->request_buf = conn->request_buf; conn->request_buf = NULL; - if (ksmbd_init_smb_server(work)) { - ksmbd_free_work_struct(work); - return -EINVAL; - } + ksmbd_init_smb_server(work); ksmbd_conn_enqueue_request(work); atomic_inc(&conn->r_count); diff --git a/fs/ksmbd/smb2pdu.c b/fs/ksmbd/smb2pdu.c index 97c9d1b5bcc0..67b7e766a06b 100644 --- a/fs/ksmbd/smb2pdu.c +++ b/fs/ksmbd/smb2pdu.c @@ -229,9 +229,6 @@ int init_smb2_neg_rsp(struct ksmbd_work *work) struct smb2_negotiate_rsp *rsp; struct ksmbd_conn *conn = work->conn; - if (conn->need_neg == false) - return -EINVAL; - *(__be32 *)work->response_buf = cpu_to_be32(conn->vals->header_size); @@ -498,12 +495,6 @@ int init_smb2_rsp_hdr(struct ksmbd_work *work) rsp_hdr->SessionId = rcv_hdr->SessionId; memcpy(rsp_hdr->Signature, rcv_hdr->Signature, 16); - work->synchronous = true; - if (work->async_id) { - ksmbd_release_id(&conn->async_ida, work->async_id); - work->async_id = 0; - } - return 0; } @@ -644,7 +635,7 @@ int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg) pr_err("Failed to alloc async message id\n"); return id; } - work->synchronous = false; + work->asynchronous = true; work->async_id = id; rsp_hdr->Id.AsyncId = cpu_to_le64(id); @@ -664,6 +655,24 @@ int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg) return 0; } +void release_async_work(struct ksmbd_work *work) +{ + struct ksmbd_conn *conn = work->conn; + + spin_lock(&conn->request_lock); + list_del_init(&work->async_request_entry); + spin_unlock(&conn->request_lock); + + work->asynchronous = 0; + work->cancel_fn = NULL; + kfree(work->cancel_argv); + work->cancel_argv = NULL; + if (work->async_id) { + ksmbd_release_id(&conn->async_ida, work->async_id); + work->async_id = 0; + } +} + void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status) { struct smb2_hdr *rsp_hdr; @@ -867,17 +876,21 @@ static void assemble_neg_contexts(struct ksmbd_conn *conn, } static __le32 decode_preauth_ctxt(struct ksmbd_conn *conn, - struct smb2_preauth_neg_context *pneg_ctxt) + struct smb2_preauth_neg_context *pneg_ctxt, + int len_of_ctxts) { - __le32 err = STATUS_NO_PREAUTH_INTEGRITY_HASH_OVERLAP; + /* + * sizeof(smb2_preauth_neg_context) assumes SMB311_SALT_SIZE Salt, + * which may not be present. Only check for used HashAlgorithms[1]. + */ + if (len_of_ctxts < MIN_PREAUTH_CTXT_DATA_LEN) + return STATUS_INVALID_PARAMETER; - if (pneg_ctxt->HashAlgorithms == SMB2_PREAUTH_INTEGRITY_SHA512) { - conn->preauth_info->Preauth_HashId = - SMB2_PREAUTH_INTEGRITY_SHA512; - err = STATUS_SUCCESS; - } + if (pneg_ctxt->HashAlgorithms != SMB2_PREAUTH_INTEGRITY_SHA512) + return STATUS_NO_PREAUTH_INTEGRITY_HASH_OVERLAP; - return err; + conn->preauth_info->Preauth_HashId = SMB2_PREAUTH_INTEGRITY_SHA512; + return STATUS_SUCCESS; } static void decode_encrypt_ctxt(struct ksmbd_conn *conn, @@ -1005,7 +1018,8 @@ static __le32 deassemble_neg_contexts(struct ksmbd_conn *conn, break; status = decode_preauth_ctxt(conn, - (struct smb2_preauth_neg_context *)pctx); + (struct smb2_preauth_neg_context *)pctx, + len_of_ctxts); if (status != STATUS_SUCCESS) break; } else if (pctx->ContextType == SMB2_ENCRYPTION_CAPABILITIES) { @@ -7045,13 +7059,9 @@ skip: ksmbd_vfs_posix_lock_wait(flock); - spin_lock(&work->conn->request_lock); spin_lock(&fp->f_lock); list_del(&work->fp_entry); - work->cancel_fn = NULL; - kfree(argv); spin_unlock(&fp->f_lock); - spin_unlock(&work->conn->request_lock); if (work->state != KSMBD_WORK_ACTIVE) { list_del(&smb_lock->llist); @@ -7069,6 +7079,7 @@ skip: work->send_no_response = 1; goto out; } + init_smb2_rsp_hdr(work); smb2_set_err_rsp(work); rsp->hdr.Status = @@ -7081,7 +7092,7 @@ skip: spin_lock(&work->conn->llist_lock); list_del(&smb_lock->clist); spin_unlock(&work->conn->llist_lock); - + release_async_work(work); goto retry; } else if (!rc) { spin_lock(&work->conn->llist_lock); diff --git a/fs/ksmbd/smb2pdu.h b/fs/ksmbd/smb2pdu.h index 0c8a770fe318..9420dd2813fb 100644 --- a/fs/ksmbd/smb2pdu.h +++ b/fs/ksmbd/smb2pdu.h @@ -486,6 +486,7 @@ int find_matching_smb2_dialect(int start_index, __le16 *cli_dialects, struct file_lock *smb_flock_init(struct file *f); int setup_async_work(struct ksmbd_work *work, void (*fn)(void **), void **arg); +void release_async_work(struct ksmbd_work *work); void smb2_send_interim_resp(struct ksmbd_work *work, __le32 status); struct channel *lookup_chann_list(struct ksmbd_session *sess, struct ksmbd_conn *conn); diff --git a/fs/ksmbd/smb_common.c b/fs/ksmbd/smb_common.c index 9c1ce6d199ce..af0c2a9b8529 100644 --- a/fs/ksmbd/smb_common.c +++ b/fs/ksmbd/smb_common.c @@ -283,20 +283,121 @@ err_out: return BAD_PROT_ID; } -int ksmbd_init_smb_server(struct ksmbd_work *work) +#define SMB_COM_NEGOTIATE_EX 0x0 + +/** + * get_smb1_cmd_val() - get smb command value from smb header + * @work: smb work containing smb header + * + * Return: smb command value + */ +static u16 get_smb1_cmd_val(struct ksmbd_work *work) { - struct ksmbd_conn *conn = work->conn; + return SMB_COM_NEGOTIATE_EX; +} - if (conn->need_neg == false) +/** + * init_smb1_rsp_hdr() - initialize smb negotiate response header + * @work: smb work containing smb request + * + * Return: 0 on success, otherwise -EINVAL + */ +static int init_smb1_rsp_hdr(struct ksmbd_work *work) +{ + struct smb_hdr *rsp_hdr = (struct smb_hdr *)work->response_buf; + struct smb_hdr *rcv_hdr = (struct smb_hdr *)work->request_buf; + + /* + * Remove 4 byte direct TCP header. + */ + *(__be32 *)work->response_buf = + cpu_to_be32(sizeof(struct smb_hdr) - 4); + + rsp_hdr->Command = SMB_COM_NEGOTIATE; + *(__le32 *)rsp_hdr->Protocol = SMB1_PROTO_NUMBER; + rsp_hdr->Flags = SMBFLG_RESPONSE; + rsp_hdr->Flags2 = SMBFLG2_UNICODE | SMBFLG2_ERR_STATUS | + SMBFLG2_EXT_SEC | SMBFLG2_IS_LONG_NAME; + rsp_hdr->Pid = rcv_hdr->Pid; + rsp_hdr->Mid = rcv_hdr->Mid; + return 0; +} + +/** + * smb1_check_user_session() - check for valid session for a user + * @work: smb work containing smb request buffer + * + * Return: 0 on success, otherwise error + */ +static int smb1_check_user_session(struct ksmbd_work *work) +{ + unsigned int cmd = work->conn->ops->get_cmd_val(work); + + if (cmd == SMB_COM_NEGOTIATE_EX) return 0; - init_smb3_11_server(conn); + return -EINVAL; +} + +/** + * smb1_allocate_rsp_buf() - allocate response buffer for a command + * @work: smb work containing smb request + * + * Return: 0 on success, otherwise -ENOMEM + */ +static int smb1_allocate_rsp_buf(struct ksmbd_work *work) +{ + work->response_buf = kmalloc(MAX_CIFS_SMALL_BUFFER_SIZE, + GFP_KERNEL | __GFP_ZERO); + work->response_sz = MAX_CIFS_SMALL_BUFFER_SIZE; + + if (!work->response_buf) { + pr_err("Failed to allocate %u bytes buffer\n", + MAX_CIFS_SMALL_BUFFER_SIZE); + return -ENOMEM; + } - if (conn->ops->get_cmd_val(work) != SMB_COM_NEGOTIATE) - conn->need_neg = false; return 0; } +static struct smb_version_ops smb1_server_ops = { + .get_cmd_val = get_smb1_cmd_val, + .init_rsp_hdr = init_smb1_rsp_hdr, + .allocate_rsp_buf = smb1_allocate_rsp_buf, + .check_user_session = smb1_check_user_session, +}; + +static int smb1_negotiate(struct ksmbd_work *work) +{ + return ksmbd_smb_negotiate_common(work, SMB_COM_NEGOTIATE); +} + +static struct smb_version_cmds smb1_server_cmds[1] = { + [SMB_COM_NEGOTIATE_EX] = { .proc = smb1_negotiate, }, +}; + +static void init_smb1_server(struct ksmbd_conn *conn) +{ + conn->ops = &smb1_server_ops; + conn->cmds = smb1_server_cmds; + conn->max_cmds = ARRAY_SIZE(smb1_server_cmds); +} + +void ksmbd_init_smb_server(struct ksmbd_work *work) +{ + struct ksmbd_conn *conn = work->conn; + __le32 proto; + + if (conn->need_neg == false) + return; + + proto = *(__le32 *)((struct smb_hdr *)work->request_buf)->Protocol; + if (proto == SMB1_PROTO_NUMBER) + init_smb1_server(conn); + else + init_smb3_11_server(conn); +} + int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, int info_level, struct ksmbd_file *dir, struct ksmbd_dir_info *d_info, @@ -444,20 +545,10 @@ static int smb_handle_negotiate(struct ksmbd_work *work) ksmbd_debug(SMB, "Unsupported SMB1 protocol\n"); - /* - * Remove 4 byte direct TCP header, add 2 byte bcc and - * 2 byte DialectIndex. - */ - *(__be32 *)work->response_buf = - cpu_to_be32(sizeof(struct smb_hdr) - 4 + 2 + 2); + /* Add 2 byte bcc and 2 byte DialectIndex. */ + inc_rfc1001_len(work->response_buf, 4); neg_rsp->hdr.Status.CifsError = STATUS_SUCCESS; - neg_rsp->hdr.Command = SMB_COM_NEGOTIATE; - *(__le32 *)neg_rsp->hdr.Protocol = SMB1_PROTO_NUMBER; - neg_rsp->hdr.Flags = SMBFLG_RESPONSE; - neg_rsp->hdr.Flags2 = SMBFLG2_UNICODE | SMBFLG2_ERR_STATUS | - SMBFLG2_EXT_SEC | SMBFLG2_IS_LONG_NAME; - neg_rsp->hdr.WordCount = 1; neg_rsp->DialectIndex = cpu_to_le16(work->conn->dialect); neg_rsp->ByteCount = 0; @@ -474,23 +565,12 @@ int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command) ksmbd_debug(SMB, "conn->dialect 0x%x\n", conn->dialect); if (command == SMB2_NEGOTIATE_HE) { - struct smb2_hdr *smb2_hdr = smb2_get_msg(work->request_buf); - - if (smb2_hdr->ProtocolId != SMB2_PROTO_NUMBER) { - ksmbd_debug(SMB, "Downgrade to SMB1 negotiation\n"); - command = SMB_COM_NEGOTIATE; - } - } - - if (command == SMB2_NEGOTIATE_HE) { ret = smb2_handle_negotiate(work); - init_smb2_neg_rsp(work); return ret; } if (command == SMB_COM_NEGOTIATE) { if (__smb2_negotiate(conn)) { - conn->need_neg = true; init_smb3_11_server(conn); init_smb2_neg_rsp(work); ksmbd_debug(SMB, "Upgrade to SMB2 negotiation\n"); diff --git a/fs/ksmbd/smb_common.h b/fs/ksmbd/smb_common.h index d30ce4c1a151..9130d2e3cd78 100644 --- a/fs/ksmbd/smb_common.h +++ b/fs/ksmbd/smb_common.h @@ -427,7 +427,7 @@ bool ksmbd_smb_request(struct ksmbd_conn *conn); int ksmbd_lookup_dialect_by_id(__le16 *cli_dialects, __le16 dialects_count); -int ksmbd_init_smb_server(struct ksmbd_work *work); +void ksmbd_init_smb_server(struct ksmbd_work *work); struct ksmbd_kstat; int ksmbd_populate_dot_dotdot_entries(struct ksmbd_work *work, diff --git a/fs/ksmbd/unicode.c b/fs/ksmbd/unicode.c index a0db699ddafd..9ae676906ed3 100644 --- a/fs/ksmbd/unicode.c +++ b/fs/ksmbd/unicode.c @@ -114,24 +114,6 @@ cp_convert: } /* - * is_char_allowed() - check for valid character - * @ch: input character to be checked - * - * Return: 1 if char is allowed, otherwise 0 - */ -static inline int is_char_allowed(char *ch) -{ - /* check for control chars, wildcards etc. */ - if (!(*ch & 0x80) && - (*ch <= 0x1f || - *ch == '?' || *ch == '"' || *ch == '<' || - *ch == '>' || *ch == '|')) - return 0; - - return 1; -} - -/* * smb_from_utf16() - convert utf16le string to local charset * @to: destination buffer * @from: source buffer diff --git a/fs/libfs.c b/fs/libfs.c index 4eda519c3002..89cf614a3271 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -174,12 +174,6 @@ loff_t dcache_dir_lseek(struct file *file, loff_t offset, int whence) } EXPORT_SYMBOL(dcache_dir_lseek); -/* Relationship between i_mode and the DT_xxx types */ -static inline unsigned char dt_type(struct inode *inode) -{ - return (inode->i_mode >> 12) & 15; -} - /* * Directory is locked and all positive dentries in it are safe, since * for ramfs-type trees they can't go away without unlink() or rmdir(), @@ -206,7 +200,8 @@ int dcache_readdir(struct file *file, struct dir_context *ctx) while ((next = scan_positives(cursor, p, 1, next)) != NULL) { if (!dir_emit(ctx, next->d_name.name, next->d_name.len, - d_inode(next)->i_ino, dt_type(d_inode(next)))) + d_inode(next)->i_ino, + fs_umode_to_dtype(d_inode(next)->i_mode))) break; ctx->pos++; p = &next->d_child; diff --git a/fs/namei.c b/fs/namei.c index edfedfbccaef..f04f7be58933 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3574,9 +3574,9 @@ static int do_open(struct nameidata *nd, /** * vfs_tmpfile - create tmpfile * @idmap: idmap of the mount the inode was found from - * @dentry: pointer to dentry of the base directory + * @parentpath: pointer to the path of the base directory + * @file: file descriptor of the new tmpfile * @mode: mode of the new tmpfile - * @open_flag: flags * * Create a temporary file. * diff --git a/fs/namespace.c b/fs/namespace.c index bc0f15257b49..54847db5b819 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -2617,15 +2617,12 @@ static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount * (ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) { char *buf = (char *)__get_free_page(GFP_KERNEL); char *mntpath = buf ? d_path(mountpoint, buf, PAGE_SIZE) : ERR_PTR(-ENOMEM); - struct tm tm; - time64_to_tm(sb->s_time_max, 0, &tm); - - pr_warn("%s filesystem being %s at %s supports timestamps until %04ld (0x%llx)\n", + pr_warn("%s filesystem being %s at %s supports timestamps until %ptTd (0x%llx)\n", sb->s_type->name, is_mounted(mnt) ? "remounted" : "mounted", - mntpath, - tm.tm_year+1900, (unsigned long long)sb->s_time_max); + mntpath, &sb->s_time_max, + (unsigned long long)sb->s_time_max); free_page((unsigned long)buf); sb->s_iflags |= SB_I_TS_EXPIRY_WARNED; @@ -4183,9 +4180,9 @@ out: unlock_mount_hash(); if (kattr->propagation) { - namespace_unlock(); if (err) cleanup_group_ids(mnt, NULL); + namespace_unlock(); } return err; @@ -4197,7 +4194,7 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, int err = 0; struct ns_common *ns; struct user_namespace *mnt_userns; - struct file *file; + struct fd f; if (!((attr->attr_set | attr->attr_clr) & MOUNT_ATTR_IDMAP)) return 0; @@ -4213,16 +4210,16 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, if (attr->userns_fd > INT_MAX) return -EINVAL; - file = fget(attr->userns_fd); - if (!file) + f = fdget(attr->userns_fd); + if (!f.file) return -EBADF; - if (!proc_ns_file(file)) { + if (!proc_ns_file(f.file)) { err = -EINVAL; goto out_fput; } - ns = get_proc_ns(file_inode(file)); + ns = get_proc_ns(file_inode(f.file)); if (ns->ops->type != CLONE_NEWUSER) { err = -EINVAL; goto out_fput; @@ -4251,7 +4248,7 @@ static int build_mount_idmapped(const struct mount_attr *attr, size_t usize, kattr->mnt_userns = get_user_ns(mnt_userns); out_fput: - fput(file); + fdput(f); return err; } diff --git a/fs/netfs/iterator.c b/fs/netfs/iterator.c index e9a45dea748a..8a4c86687429 100644 --- a/fs/netfs/iterator.c +++ b/fs/netfs/iterator.c @@ -139,7 +139,7 @@ static ssize_t netfs_extract_user_to_sg(struct iov_iter *iter, size_t seg = min_t(size_t, PAGE_SIZE - off, len); *pages++ = NULL; - sg_set_page(sg, page, len, off); + sg_set_page(sg, page, seg, off); sgtable->nents++; sg++; len -= seg; diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index 450d6c3bc05e..c1c7ed2fd860 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -75,7 +75,6 @@ config NFS_V3_ACL config NFS_V4 tristate "NFS client support for NFS version 4" depends on NFS_FS - select RPCSEC_GSS_KRB5 select KEYS help This option enables support for version 4 of the NFS protocol diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 222a28320e1c..97a76706fd54 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -717,9 +717,7 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr, if ((attr->ia_valid & ATTR_KILL_SUID) != 0 && inode->i_mode & S_ISUID) inode->i_mode &= ~S_ISUID; - if ((attr->ia_valid & ATTR_KILL_SGID) != 0 && - (inode->i_mode & (S_ISGID | S_IXGRP)) == - (S_ISGID | S_IXGRP)) + if (setattr_should_drop_sgid(&nop_mnt_idmap, inode)) inode->i_mode &= ~S_ISGID; if ((attr->ia_valid & ATTR_MODE) != 0) { int mode = attr->ia_mode & S_IALLUGO; diff --git a/fs/nfs/nfs3_fs.h b/fs/nfs/nfs3_fs.h index 4fa37dc038b5..b333ea119ef5 100644 --- a/fs/nfs/nfs3_fs.h +++ b/fs/nfs/nfs3_fs.h @@ -17,7 +17,6 @@ extern int nfs3_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, extern int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, struct posix_acl *dfacl); extern ssize_t nfs3_listxattr(struct dentry *, char *, size_t); -extern const struct xattr_handler *nfs3_xattr_handlers[]; #else static inline int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, struct posix_acl *dfacl) diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 1247f544a440..349cc4f60a28 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -300,12 +300,6 @@ fail: goto out; } -const struct xattr_handler *nfs3_xattr_handlers[] = { - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, - NULL, -}; - static int nfs3_list_one_acl(struct inode *inode, int type, const char *name, void *data, size_t size, ssize_t *result) diff --git a/fs/nfs/nfs3super.c b/fs/nfs/nfs3super.c index 7c5809431e61..8a9be9e47f76 100644 --- a/fs/nfs/nfs3super.c +++ b/fs/nfs/nfs3super.c @@ -14,9 +14,6 @@ struct nfs_subversion nfs_v3 = { .rpc_vers = &nfs_version3, .rpc_ops = &nfs_v3_clientops, .sops = &nfs_sops, -#ifdef CONFIG_NFS_V3_ACL - .xattr = nfs3_xattr_handlers, -#endif }; static int __init init_nfs_v3(void) diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 22a93ae46cd7..5607b1e2b821 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -1980,8 +1980,7 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data) if (!data->rpc_done) { if (data->rpc_status) return ERR_PTR(data->rpc_status); - /* cached opens have already been processed */ - goto update; + return nfs4_try_open_cached(data); } ret = nfs_refresh_inode(inode, &data->f_attr); @@ -1990,7 +1989,7 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data) if (data->o_res.delegation_type != 0) nfs4_opendata_check_deleg(data, state); -update: + if (!update_open_stateid(state, &data->o_res.stateid, NULL, data->o_arg.fmode)) return ERR_PTR(-EAGAIN); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 05ae23657527..397c096d874e 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -1274,9 +1274,6 @@ int nfs_get_tree_common(struct fs_context *fc) if (ctx->clone_data.sb->s_flags & SB_SYNCHRONOUS) fc->sb_flags |= SB_SYNCHRONOUS; - if (server->caps & NFS_CAP_SECURITY_LABEL) - fc->lsm_flags |= SECURITY_LSM_NATIVE_LABELS; - /* Get a superblock - note that we may end up sharing one that already exists */ fc->s_fs_info = server; s = sget_fc(fc, compare_super, nfs_set_super); diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c index 04697f8dc37d..01d7fd108cf3 100644 --- a/fs/nfsd/blocklayout.c +++ b/fs/nfsd/blocklayout.c @@ -297,6 +297,7 @@ nfsd4_block_get_device_info_scsi(struct super_block *sb, out_free_dev: kfree(dev); + gdp->gd_device = NULL; return ret; } diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 2a815f5a52c4..4039ffcf90ba 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -946,8 +946,8 @@ static const struct cred *get_backchannel_cred(struct nfs4_client *clp, struct r if (!kcred) return NULL; - kcred->uid = ses->se_cb_sec.uid; - kcred->gid = ses->se_cb_sec.gid; + kcred->fsuid = ses->se_cb_sec.uid; + kcred->fsgid = ses->se_cb_sec.gid; return kcred; } } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index e12e5a4ad502..76db2fe29624 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2476,10 +2476,12 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) for (i = 0; i < argp->opcnt; i++) { op = &argp->ops[i]; op->replay = NULL; + op->opdesc = NULL; if (xdr_stream_decode_u32(argp->xdr, &op->opnum) < 0) return false; if (nfsd4_opnum_in_range(argp, op)) { + op->opdesc = OPDESC(op); op->status = nfsd4_dec_ops[op->opnum](argp, &op->u); if (op->status != nfs_ok) trace_nfsd_compound_decode_err(argp->rqstp, @@ -2490,7 +2492,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) op->opnum = OP_ILLEGAL; op->status = nfserr_op_illegal; } - op->opdesc = OPDESC(op); + /* * We'll try to cache the result in the DRC if any one * op in the compound wants to be cached: @@ -3444,8 +3446,7 @@ out_acl: p = xdr_reserve_space(xdr, 4); if (!p) goto out_resource; - err = xattr_supported_namespace(d_inode(dentry), - XATTR_USER_PREFIX); + err = xattr_supports_user_prefix(d_inode(dentry)); *p++ = cpu_to_be32(err == 0); } @@ -5400,10 +5401,8 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) __be32 *p; p = xdr_reserve_space(xdr, 8); - if (!p) { - WARN_ON_ONCE(1); - return; - } + if (!p) + goto release; *p++ = cpu_to_be32(op->opnum); post_err_offset = xdr->buf->len; @@ -5418,8 +5417,6 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) op->status = encoder(resp, op->status, &op->u); if (op->status) trace_nfsd_compound_encode_err(rqstp, op->opnum, op->status); - if (opdesc && opdesc->op_release) - opdesc->op_release(&op->u); xdr_commit_encode(xdr); /* nfsd4_check_resp_size guarantees enough room for error status */ @@ -5460,6 +5457,9 @@ nfsd4_encode_operation(struct nfsd4_compoundres *resp, struct nfsd4_op *op) } status: *p = op->status; +release: + if (opdesc && opdesc->op_release) + opdesc->op_release(&op->u); } /* diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c index 2681a449edc1..13592e82eaf6 100644 --- a/fs/nilfs2/btree.c +++ b/fs/nilfs2/btree.c @@ -2219,6 +2219,7 @@ static int nilfs_btree_assign_p(struct nilfs_bmap *btree, /* on-disk format */ binfo->bi_dat.bi_blkoff = cpu_to_le64(key); binfo->bi_dat.bi_level = level; + memset(binfo->bi_dat.bi_pad, 0, sizeof(binfo->bi_dat.bi_pad)); return 0; } diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c index a35f2795b242..4c85914f2abc 100644 --- a/fs/nilfs2/direct.c +++ b/fs/nilfs2/direct.c @@ -314,6 +314,7 @@ static int nilfs_direct_assign_p(struct nilfs_bmap *direct, binfo->bi_dat.bi_blkoff = cpu_to_le64(key); binfo->bi_dat.bi_level = 0; + memset(binfo->bi_dat.bi_pad, 0, sizeof(binfo->bi_dat.bi_pad)); return 0; } diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c index 19446a8243d7..228659612c0d 100644 --- a/fs/nilfs2/segment.c +++ b/fs/nilfs2/segment.c @@ -430,6 +430,23 @@ static int nilfs_segctor_reset_segment_buffer(struct nilfs_sc_info *sci) return 0; } +/** + * nilfs_segctor_zeropad_segsum - zero pad the rest of the segment summary area + * @sci: segment constructor object + * + * nilfs_segctor_zeropad_segsum() zero-fills unallocated space at the end of + * the current segment summary block. + */ +static void nilfs_segctor_zeropad_segsum(struct nilfs_sc_info *sci) +{ + struct nilfs_segsum_pointer *ssp; + + ssp = sci->sc_blk_cnt > 0 ? &sci->sc_binfo_ptr : &sci->sc_finfo_ptr; + if (ssp->offset < ssp->bh->b_size) + memset(ssp->bh->b_data + ssp->offset, 0, + ssp->bh->b_size - ssp->offset); +} + static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci) { sci->sc_nblk_this_inc += sci->sc_curseg->sb_sum.nblocks; @@ -438,6 +455,7 @@ static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci) * The current segment is filled up * (internal code) */ + nilfs_segctor_zeropad_segsum(sci); sci->sc_curseg = NILFS_NEXT_SEGBUF(sci->sc_curseg); return nilfs_segctor_reset_segment_buffer(sci); } @@ -542,6 +560,7 @@ static int nilfs_segctor_add_file_block(struct nilfs_sc_info *sci, goto retry; } if (unlikely(required)) { + nilfs_segctor_zeropad_segsum(sci); err = nilfs_segbuf_extend_segsum(segbuf); if (unlikely(err)) goto failed; @@ -1533,6 +1552,7 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci, nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA); sci->sc_stage = prev_stage; } + nilfs_segctor_zeropad_segsum(sci); nilfs_segctor_truncate_segments(sci, sci->sc_curseg, nilfs->ns_sufile); return 0; @@ -2609,11 +2629,10 @@ static int nilfs_segctor_thread(void *arg) goto loop; end_thread: - spin_unlock(&sci->sc_state_lock); - /* end sync. */ sci->sc_task = NULL; wake_up(&sci->sc_wait_task); /* for nilfs_segctor_kill_thread() */ + spin_unlock(&sci->sc_state_lock); return 0; } diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index 1422b8ba24ed..77f1e5778d1c 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -482,6 +482,7 @@ static void nilfs_put_super(struct super_block *sb) up_write(&nilfs->ns_sem); } + nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); @@ -1105,6 +1106,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent) nilfs_put_root(fsroot); failed_unload: + nilfs_sysfs_delete_device_group(nilfs); iput(nilfs->ns_sufile); iput(nilfs->ns_cpfile); iput(nilfs->ns_dat); diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index 3a4c9c150cbf..2894152a6b25 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -87,7 +87,6 @@ void destroy_nilfs(struct the_nilfs *nilfs) { might_sleep(); if (nilfs_init(nilfs)) { - nilfs_sysfs_delete_device_group(nilfs); brelse(nilfs->ns_sbh[0]); brelse(nilfs->ns_sbh[1]); } @@ -305,6 +304,10 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) goto failed; } + err = nilfs_sysfs_create_device_group(sb); + if (unlikely(err)) + goto sysfs_error; + if (valid_fs) goto skip_recovery; @@ -366,6 +369,9 @@ int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb) goto failed; failed_unload: + nilfs_sysfs_delete_device_group(nilfs); + + sysfs_error: iput(nilfs->ns_cpfile); iput(nilfs->ns_sufile); iput(nilfs->ns_dat); @@ -697,10 +703,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data) if (err) goto failed_sbh; - err = nilfs_sysfs_create_device_group(sb); - if (err) - goto failed_sbh; - set_nilfs_init(nilfs); err = 0; out: diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index 8f430bfad487..22fb1cf7e1fc 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -663,7 +663,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, struct fanotify_info *info = fanotify_event_info(event); unsigned int info_mode = FAN_GROUP_FLAG(group, FANOTIFY_INFO_MODES); unsigned int pidfd_mode = info_mode & FAN_REPORT_PIDFD; - struct file *f = NULL; + struct file *f = NULL, *pidfd_file = NULL; int ret, pidfd = FAN_NOPIDFD, fd = FAN_NOFD; pr_debug("%s: group=%p event=%p\n", __func__, group, event); @@ -718,7 +718,7 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, !pid_has_task(event->pid, PIDTYPE_TGID)) { pidfd = FAN_NOPIDFD; } else { - pidfd = pidfd_create(event->pid, 0); + pidfd = pidfd_prepare(event->pid, 0, &pidfd_file); if (pidfd < 0) pidfd = FAN_EPIDFD; } @@ -751,6 +751,9 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group, if (f) fd_install(fd, f); + if (pidfd_file) + fd_install(pidfd, pidfd_file); + return metadata.event_len; out_close_fd: @@ -759,8 +762,10 @@ out_close_fd: fput(f); } - if (pidfd >= 0) - close_fd(pidfd); + if (pidfd >= 0) { + put_unused_fd(pidfd); + fput(pidfd_file); + } return ret; } diff --git a/fs/nsfs.c b/fs/nsfs.c index f8df60b3b901..f602a96a1afe 100644 --- a/fs/nsfs.c +++ b/fs/nsfs.c @@ -235,24 +235,6 @@ bool proc_ns_file(const struct file *file) return file->f_op == &ns_file_operations; } -struct file *proc_ns_fget(int fd) -{ - struct file *file; - - file = fget(fd); - if (!file) - return ERR_PTR(-EBADF); - - if (file->f_op != &ns_file_operations) - goto out_invalid; - - return file; - -out_invalid: - fput(file); - return ERR_PTR(-EINVAL); -} - /** * ns_match() - Returns true if current namespace matches dev/ino provided. * @ns: current namespace diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index ff64302e87e5..7324cf924932 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -1033,10 +1033,6 @@ static const struct xattr_handler ntfs_other_xattr_handler = { }; const struct xattr_handler *ntfs_xattr_handlers[] = { -#ifdef CONFIG_NTFS3_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif &ntfs_other_xattr_handler, NULL, }; diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c index 0394505fdce3..8dfc284e85f0 100644 --- a/fs/ocfs2/aops.c +++ b/fs/ocfs2/aops.c @@ -2463,7 +2463,7 @@ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter) return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter, get_block, - ocfs2_dio_end_io, NULL, 0); + ocfs2_dio_end_io, 0); } const struct address_space_operations ocfs2_aops = { diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index 9175dbc47201..17c52225b87d 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -242,6 +242,7 @@ static int ocfs2_mknod(struct mnt_idmap *idmap, int want_meta = 0; int xattr_credits = 0; struct ocfs2_security_xattr_info si = { + .name = NULL, .enable = 1, }; int did_quota_inode = 0; @@ -1805,6 +1806,7 @@ static int ocfs2_symlink(struct mnt_idmap *idmap, int want_clusters = 0; int xattr_credits = 0; struct ocfs2_security_xattr_info si = { + .name = NULL, .enable = 1, }; int did_quota = 0, did_quota_inode = 0; diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 5a656dc683f1..564ab48d03ef 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -2952,10 +2952,11 @@ retry: */ if (PAGE_SIZE <= OCFS2_SB(sb)->s_clustersize) { if (PageDirty(page)) { - /* - * write_on_page will unlock the page on return - */ - ret = write_one_page(page); + unlock_page(page); + put_page(page); + + ret = filemap_write_and_wait_range(mapping, + offset, map_end - 1); goto retry; } } diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c index 389308efe854..4ac77ff6e676 100644 --- a/fs/ocfs2/xattr.c +++ b/fs/ocfs2/xattr.c @@ -89,21 +89,17 @@ static struct ocfs2_xattr_def_value_root def_xv = { const struct xattr_handler *ocfs2_xattr_handlers[] = { &ocfs2_xattr_user_handler, - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, &ocfs2_xattr_trusted_handler, &ocfs2_xattr_security_handler, NULL }; static const struct xattr_handler *ocfs2_xattr_handler_map[OCFS2_XATTR_MAX] = { - [OCFS2_XATTR_INDEX_USER] = &ocfs2_xattr_user_handler, - [OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS] - = &posix_acl_access_xattr_handler, - [OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT] - = &posix_acl_default_xattr_handler, - [OCFS2_XATTR_INDEX_TRUSTED] = &ocfs2_xattr_trusted_handler, - [OCFS2_XATTR_INDEX_SECURITY] = &ocfs2_xattr_security_handler, + [OCFS2_XATTR_INDEX_USER] = &ocfs2_xattr_user_handler, + [OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, + [OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default, + [OCFS2_XATTR_INDEX_TRUSTED] = &ocfs2_xattr_trusted_handler, + [OCFS2_XATTR_INDEX_SECURITY] = &ocfs2_xattr_security_handler, }; struct ocfs2_xattr_info { @@ -7259,9 +7255,21 @@ static int ocfs2_xattr_security_set(const struct xattr_handler *handler, static int ocfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array, void *fs_info) { + struct ocfs2_security_xattr_info *si = fs_info; const struct xattr *xattr; int err = 0; + if (si) { + si->value = kmemdup(xattr_array->value, xattr_array->value_len, + GFP_KERNEL); + if (!si->value) + return -ENOMEM; + + si->name = xattr_array->name; + si->value_len = xattr_array->value_len; + return 0; + } + for (xattr = xattr_array; xattr->name != NULL; xattr++) { err = ocfs2_xattr_set(inode, OCFS2_XATTR_INDEX_SECURITY, xattr->name, xattr->value, @@ -7277,13 +7285,23 @@ int ocfs2_init_security_get(struct inode *inode, const struct qstr *qstr, struct ocfs2_security_xattr_info *si) { + int ret; + /* check whether ocfs2 support feature xattr */ if (!ocfs2_supports_xattr(OCFS2_SB(dir->i_sb))) return -EOPNOTSUPP; - if (si) - return security_old_inode_init_security(inode, dir, qstr, - &si->name, &si->value, - &si->value_len); + if (si) { + ret = security_inode_init_security(inode, dir, qstr, + &ocfs2_initxattrs, si); + /* + * security_inode_init_security() does not return -EOPNOTSUPP, + * we have to check the xattr ourselves. + */ + if (!ret && !si->name) + si->enable = 0; + + return ret; + } return security_inode_init_security(inode, dir, qstr, &ocfs2_initxattrs, NULL); diff --git a/fs/open.c b/fs/open.c index 4401a73d4032..4478adcc4f3a 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1196,13 +1196,21 @@ inline int build_open_flags(const struct open_how *how, struct open_flags *op) } /* - * In order to ensure programs get explicit errors when trying to use - * O_TMPFILE on old kernels, O_TMPFILE is implemented such that it - * looks like (O_DIRECTORY|O_RDWR & ~O_CREAT) to old kernels. But we - * have to require userspace to explicitly set it. + * Block bugs where O_DIRECTORY | O_CREAT created regular files. + * Note, that blocking O_DIRECTORY | O_CREAT here also protects + * O_TMPFILE below which requires O_DIRECTORY being raised. */ + if ((flags & (O_DIRECTORY | O_CREAT)) == (O_DIRECTORY | O_CREAT)) + return -EINVAL; + + /* Now handle the creative implementation of O_TMPFILE. */ if (flags & __O_TMPFILE) { - if ((flags & O_TMPFILE_MASK) != O_TMPFILE) + /* + * In order to ensure programs get explicit errors when trying + * to use O_TMPFILE on old kernels we enforce that O_DIRECTORY + * is raised alongside __O_TMPFILE. + */ + if (!(flags & O_DIRECTORY)) return -EINVAL; if (!(acc_mode & MAY_WRITE)) return -EINVAL; diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c index 6ecad4f94ae6..68b62689a63e 100644 --- a/fs/orangefs/xattr.c +++ b/fs/orangefs/xattr.c @@ -555,8 +555,6 @@ static const struct xattr_handler orangefs_xattr_default_handler = { }; const struct xattr_handler *orangefs_xattr_handlers[] = { - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, &orangefs_xattr_default_handler, NULL }; diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index c14e90764e35..f658cc8ea492 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -81,8 +81,7 @@ int ovl_copy_xattr(struct super_block *sb, const struct path *oldpath, struct de int error = 0; size_t slen; - if (!(old->d_inode->i_opflags & IOP_XATTR) || - !(new->d_inode->i_opflags & IOP_XATTR)) + if (!old->d_inode->i_op->listxattr || !new->d_inode->i_op->listxattr) return 0; list_size = vfs_listxattr(old, NULL, 0); diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index f1d9f75f8786..f97ad8b40dbb 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1055,20 +1055,12 @@ static const struct xattr_handler ovl_other_xattr_handler = { }; static const struct xattr_handler *ovl_trusted_xattr_handlers[] = { -#ifdef CONFIG_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif &ovl_own_trusted_xattr_handler, &ovl_other_xattr_handler, NULL }; static const struct xattr_handler *ovl_user_xattr_handlers[] = { -#ifdef CONFIG_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif &ovl_own_user_xattr_handler, &ovl_other_xattr_handler, NULL diff --git a/fs/pnode.c b/fs/pnode.c index 468e4e65a615..3cede8b18c8b 100644 --- a/fs/pnode.c +++ b/fs/pnode.c @@ -214,7 +214,6 @@ static struct mount *next_group(struct mount *m, struct mount *origin) /* all accesses are serialized by namespace_sem */ static struct mount *last_dest, *first_source, *last_source, *dest_master; -static struct mountpoint *mp; static struct hlist_head *list; static inline bool peers(struct mount *m1, struct mount *m2) @@ -222,7 +221,7 @@ static inline bool peers(struct mount *m1, struct mount *m2) return m1->mnt_group_id == m2->mnt_group_id && m1->mnt_group_id; } -static int propagate_one(struct mount *m) +static int propagate_one(struct mount *m, struct mountpoint *dest_mp) { struct mount *child; int type; @@ -230,7 +229,7 @@ static int propagate_one(struct mount *m) if (IS_MNT_NEW(m)) return 0; /* skip if mountpoint isn't covered by it */ - if (!is_subdir(mp->m_dentry, m->mnt.mnt_root)) + if (!is_subdir(dest_mp->m_dentry, m->mnt.mnt_root)) return 0; if (peers(m, last_dest)) { type = CL_MAKE_SHARED; @@ -262,7 +261,7 @@ static int propagate_one(struct mount *m) if (IS_ERR(child)) return PTR_ERR(child); read_seqlock_excl(&mount_lock); - mnt_set_mountpoint(m, mp, child); + mnt_set_mountpoint(m, dest_mp, child); if (m->mnt_master != dest_master) SET_MNT_MARK(m->mnt_master); read_sequnlock_excl(&mount_lock); @@ -299,13 +298,12 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, last_dest = dest_mnt; first_source = source_mnt; last_source = source_mnt; - mp = dest_mp; list = tree_list; dest_master = dest_mnt->mnt_master; /* all peers of dest_mnt, except dest_mnt itself */ for (n = next_peer(dest_mnt); n != dest_mnt; n = next_peer(n)) { - ret = propagate_one(n); + ret = propagate_one(n, dest_mp); if (ret) goto out; } @@ -316,7 +314,7 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp, /* everything in that slave group */ n = m; do { - ret = propagate_one(n); + ret = propagate_one(n, dest_mp); if (ret) goto out; n = next_peer(n); diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 5a76fb35923a..7fa1b738bbab 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -957,25 +957,62 @@ set_posix_acl(struct mnt_idmap *idmap, struct dentry *dentry, } EXPORT_SYMBOL(set_posix_acl); +int posix_acl_listxattr(struct inode *inode, char **buffer, + ssize_t *remaining_size) +{ + int err; + + if (!IS_POSIXACL(inode)) + return 0; + + if (inode->i_acl) { + err = xattr_list_one(buffer, remaining_size, + XATTR_NAME_POSIX_ACL_ACCESS); + if (err) + return err; + } + + if (inode->i_default_acl) { + err = xattr_list_one(buffer, remaining_size, + XATTR_NAME_POSIX_ACL_DEFAULT); + if (err) + return err; + } + + return 0; +} + static bool posix_acl_xattr_list(struct dentry *dentry) { return IS_POSIXACL(d_backing_inode(dentry)); } -const struct xattr_handler posix_acl_access_xattr_handler = { +/* + * nop_posix_acl_access - legacy xattr handler for access POSIX ACLs + * + * This is the legacy POSIX ACL access xattr handler. It is used by some + * filesystems to implement their ->listxattr() inode operation. New code + * should never use them. + */ +const struct xattr_handler nop_posix_acl_access = { .name = XATTR_NAME_POSIX_ACL_ACCESS, - .flags = ACL_TYPE_ACCESS, .list = posix_acl_xattr_list, }; -EXPORT_SYMBOL_GPL(posix_acl_access_xattr_handler); +EXPORT_SYMBOL_GPL(nop_posix_acl_access); -const struct xattr_handler posix_acl_default_xattr_handler = { +/* + * nop_posix_acl_default - legacy xattr handler for default POSIX ACLs + * + * This is the legacy POSIX ACL default xattr handler. It is used by some + * filesystems to implement their ->listxattr() inode operation. New code + * should never use them. + */ +const struct xattr_handler nop_posix_acl_default = { .name = XATTR_NAME_POSIX_ACL_DEFAULT, - .flags = ACL_TYPE_DEFAULT, .list = posix_acl_xattr_list, }; -EXPORT_SYMBOL_GPL(posix_acl_default_xattr_handler); +EXPORT_SYMBOL_GPL(nop_posix_acl_default); int simple_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) @@ -1094,12 +1131,10 @@ retry_deleg: if (error) goto out_inode_unlock; - if (inode->i_opflags & IOP_XATTR) + if (likely(!is_bad_inode(inode))) error = set_posix_acl(idmap, dentry, acl_type, kacl); - else if (unlikely(is_bad_inode(inode))) - error = -EIO; else - error = -EOPNOTSUPP; + error = -EIO; if (!error) { fsnotify_xattr(dentry); evm_inode_post_set_acl(dentry, acl_name, kacl); @@ -1204,12 +1239,10 @@ retry_deleg: if (error) goto out_inode_unlock; - if (inode->i_opflags & IOP_XATTR) + if (likely(!is_bad_inode(inode))) error = set_posix_acl(idmap, dentry, acl_type, NULL); - else if (unlikely(is_bad_inode(inode))) - error = -EIO; else - error = -EOPNOTSUPP; + error = -EIO; if (!error) { fsnotify_xattr(dentry); evm_inode_post_remove_acl(idmap, dentry, acl_name); diff --git a/fs/qnx4/README b/fs/qnx4/README deleted file mode 100644 index 1f1e320d91da..000000000000 --- a/fs/qnx4/README +++ /dev/null @@ -1,9 +0,0 @@ - - This is a snapshot of the QNX4 filesystem for Linux. - Please send diffs and remarks to <al@alarsen.net> . - -Credits : - -Richard "Scuba" A. Frowijn <scuba@wxs.nl> -Frank "Jedi/Sector One" Denis <j@pureftpd.org> -Anders Larsen <al@alarsen.net> (Maintainer) diff --git a/fs/qnx6/README b/fs/qnx6/README deleted file mode 100644 index 116d622026cc..000000000000 --- a/fs/qnx6/README +++ /dev/null @@ -1,8 +0,0 @@ - - This is a snapshot of the QNX6 filesystem for Linux. - Please send diffs and remarks to <chaosman@ontika.net> . - -Credits : - -Al Viro <viro@ZenIV.linux.org.uk> (endless patience with me & support ;)) -Kai Bankett <chaosman@ontika.net> (Maintainer) diff --git a/fs/read_write.c b/fs/read_write.c index 7a2ff6157eda..a21ba3be7dbe 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -749,15 +749,14 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, return -EOPNOTSUPP; while (iov_iter_count(iter)) { - struct iovec iovec = iov_iter_iovec(iter); ssize_t nr; if (type == READ) { - nr = filp->f_op->read(filp, iovec.iov_base, - iovec.iov_len, ppos); + nr = filp->f_op->read(filp, iter_iov_addr(iter), + iter_iov_len(iter), ppos); } else { - nr = filp->f_op->write(filp, iovec.iov_base, - iovec.iov_len, ppos); + nr = filp->f_op->write(filp, iter_iov_addr(iter), + iter_iov_len(iter), ppos); } if (nr < 0) { @@ -766,7 +765,7 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, break; } ret += nr; - if (nr != iovec.iov_len) + if (nr != iter_iov_len(iter)) break; iov_iter_advance(iter, nr); } diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 467d13da198f..b54cc7048f02 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -261,3 +261,10 @@ const struct inode_operations reiserfs_file_inode_operations = { .fileattr_get = reiserfs_fileattr_get, .fileattr_set = reiserfs_fileattr_set, }; + +const struct inode_operations reiserfs_priv_file_inode_operations = { + .setattr = reiserfs_setattr, + .permission = reiserfs_permission, + .fileattr_get = reiserfs_fileattr_get, + .fileattr_set = reiserfs_fileattr_set, +}; diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index d54cab854f60..d8debbb6105f 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -2087,10 +2087,8 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, * Mark it private if we're creating the privroot * or something under it. */ - if (IS_PRIVATE(dir) || dentry == REISERFS_SB(sb)->priv_root) { - inode->i_flags |= S_PRIVATE; - inode->i_opflags &= ~IOP_XATTR; - } + if (IS_PRIVATE(dir) || dentry == REISERFS_SB(sb)->priv_root) + reiserfs_init_priv_inode(inode); if (reiserfs_posixacl(inode->i_sb)) { reiserfs_write_unlock(inode->i_sb); diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index 42d2c20e1345..52240cc891cf 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -378,13 +378,11 @@ static struct dentry *reiserfs_lookup(struct inode *dir, struct dentry *dentry, /* * Propagate the private flag so we know we're - * in the priv tree. Also clear IOP_XATTR + * in the priv tree. Also clear xattr support * since we don't have xattrs on xattr files. */ - if (IS_PRIVATE(dir)) { - inode->i_flags |= S_PRIVATE; - inode->i_opflags &= ~IOP_XATTR; - } + if (IS_PRIVATE(dir)) + reiserfs_init_priv_inode(inode); } reiserfs_write_unlock(dir->i_sb); if (retval == IO_ERROR) { @@ -1649,6 +1647,48 @@ static int reiserfs_rename(struct mnt_idmap *idmap, return retval; } +static const struct inode_operations reiserfs_priv_dir_inode_operations = { + .create = reiserfs_create, + .lookup = reiserfs_lookup, + .link = reiserfs_link, + .unlink = reiserfs_unlink, + .symlink = reiserfs_symlink, + .mkdir = reiserfs_mkdir, + .rmdir = reiserfs_rmdir, + .mknod = reiserfs_mknod, + .rename = reiserfs_rename, + .setattr = reiserfs_setattr, + .permission = reiserfs_permission, + .fileattr_get = reiserfs_fileattr_get, + .fileattr_set = reiserfs_fileattr_set, +}; + +static const struct inode_operations reiserfs_priv_symlink_inode_operations = { + .get_link = page_get_link, + .setattr = reiserfs_setattr, + .permission = reiserfs_permission, +}; + +static const struct inode_operations reiserfs_priv_special_inode_operations = { + .setattr = reiserfs_setattr, + .permission = reiserfs_permission, +}; + +void reiserfs_init_priv_inode(struct inode *inode) +{ + inode->i_flags |= S_PRIVATE; + inode->i_opflags &= ~IOP_XATTR; + + if (S_ISREG(inode->i_mode)) + inode->i_op = &reiserfs_priv_file_inode_operations; + else if (S_ISDIR(inode->i_mode)) + inode->i_op = &reiserfs_priv_dir_inode_operations; + else if (S_ISLNK(inode->i_mode)) + inode->i_op = &reiserfs_priv_symlink_inode_operations; + else + inode->i_op = &reiserfs_priv_special_inode_operations; +} + /* directories can handle most operations... */ const struct inode_operations reiserfs_dir_inode_operations = { .create = reiserfs_create, diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h index 98e6f53c2fe0..1bccf6a2e908 100644 --- a/fs/reiserfs/reiserfs.h +++ b/fs/reiserfs/reiserfs.h @@ -3106,6 +3106,7 @@ int reiserfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, int __reiserfs_write_begin(struct page *page, unsigned from, unsigned len); /* namei.c */ +void reiserfs_init_priv_inode(struct inode *inode); void set_de_name_and_namelen(struct reiserfs_dir_entry *de); int search_by_entry_key(struct super_block *sb, const struct cpu_key *key, struct treepath *path, struct reiserfs_dir_entry *de); @@ -3175,6 +3176,7 @@ void reiserfs_unmap_buffer(struct buffer_head *); /* file.c */ extern const struct inode_operations reiserfs_file_inode_operations; +extern const struct inode_operations reiserfs_priv_file_inode_operations; extern const struct file_operations reiserfs_file_operations; extern const struct address_space_operations reiserfs_address_space_operations; diff --git a/fs/reiserfs/xattr.c b/fs/reiserfs/xattr.c index 06d810c72c52..651027967159 100644 --- a/fs/reiserfs/xattr.c +++ b/fs/reiserfs/xattr.c @@ -52,6 +52,7 @@ #include <linux/quotaops.h> #include <linux/security.h> #include <linux/posix_acl_xattr.h> +#include <linux/xattr.h> #define PRIVROOT_NAME ".reiserfs_priv" #define XAROOT_NAME "xattrs" @@ -770,23 +771,34 @@ out: (handler) != NULL; \ (handler) = *(handlers)++) +static inline bool reiserfs_posix_acl_list(const char *name, + struct dentry *dentry) +{ + return (posix_acl_type(name) >= 0) && + IS_POSIXACL(d_backing_inode(dentry)); +} + /* This is the implementation for the xattr plugin infrastructure */ -static inline const struct xattr_handler * -find_xattr_handler_prefix(const struct xattr_handler **handlers, - const char *name) +static inline bool reiserfs_xattr_list(const struct xattr_handler **handlers, + const char *name, struct dentry *dentry) { - const struct xattr_handler *xah; + if (handlers) { + const struct xattr_handler *xah = NULL; - if (!handlers) - return NULL; + for_each_xattr_handler(handlers, xah) { + const char *prefix = xattr_prefix(xah); - for_each_xattr_handler(handlers, xah) { - const char *prefix = xattr_prefix(xah); - if (strncmp(prefix, name, strlen(prefix)) == 0) - break; + if (strncmp(prefix, name, strlen(prefix))) + continue; + + if (!xattr_handler_can_list(xah, dentry)) + return false; + + return true; + } } - return xah; + return reiserfs_posix_acl_list(name, dentry); } struct listxattr_buf { @@ -807,12 +819,8 @@ static bool listxattr_filler(struct dir_context *ctx, const char *name, if (name[0] != '.' || (namelen != 1 && (name[1] != '.' || namelen != 2))) { - const struct xattr_handler *handler; - - handler = find_xattr_handler_prefix(b->dentry->d_sb->s_xattr, - name); - if (!handler /* Unsupported xattr name */ || - (handler->list && !handler->list(b->dentry))) + if (!reiserfs_xattr_list(b->dentry->d_sb->s_xattr, name, + b->dentry)) return true; size = namelen + 1; if (b->buf) { @@ -888,8 +896,7 @@ static int create_privroot(struct dentry *dentry) return -EOPNOTSUPP; } - d_inode(dentry)->i_flags |= S_PRIVATE; - d_inode(dentry)->i_opflags &= ~IOP_XATTR; + reiserfs_init_priv_inode(d_inode(dentry)); reiserfs_info(dentry->d_sb, "Created %s - reserved for xattr " "storage.\n", PRIVROOT_NAME); @@ -911,10 +918,6 @@ const struct xattr_handler *reiserfs_xattr_handlers[] = { #ifdef CONFIG_REISERFS_FS_SECURITY &reiserfs_xattr_security_handler, #endif -#ifdef CONFIG_REISERFS_FS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif NULL }; @@ -975,10 +978,8 @@ int reiserfs_lookup_privroot(struct super_block *s) if (!IS_ERR(dentry)) { REISERFS_SB(s)->priv_root = dentry; d_set_d_op(dentry, &xattr_lookup_poison_ops); - if (d_really_is_positive(dentry)) { - d_inode(dentry)->i_flags |= S_PRIVATE; - d_inode(dentry)->i_opflags &= ~IOP_XATTR; - } + if (d_really_is_positive(dentry)) + reiserfs_init_priv_inode(d_inode(dentry)); } else err = PTR_ERR(dentry); inode_unlock(d_inode(s->s_root)); diff --git a/fs/reiserfs/xattr_security.c b/fs/reiserfs/xattr_security.c index 41c0ea84fbff..6e0a099dd788 100644 --- a/fs/reiserfs/xattr_security.c +++ b/fs/reiserfs/xattr_security.c @@ -39,6 +39,22 @@ static bool security_list(struct dentry *dentry) return !IS_PRIVATE(d_inode(dentry)); } +static int +reiserfs_initxattrs(struct inode *inode, const struct xattr *xattr_array, + void *fs_info) +{ + struct reiserfs_security_handle *sec = fs_info; + + sec->value = kmemdup(xattr_array->value, xattr_array->value_len, + GFP_KERNEL); + if (!sec->value) + return -ENOMEM; + + sec->name = xattr_array->name; + sec->length = xattr_array->value_len; + return 0; +} + /* Initializes the security context for a new inode and returns the number * of blocks needed for the transaction. If successful, reiserfs_security * must be released using reiserfs_security_free when the caller is done. */ @@ -56,12 +72,9 @@ int reiserfs_security_init(struct inode *dir, struct inode *inode, if (IS_PRIVATE(dir)) return 0; - error = security_old_inode_init_security(inode, dir, qstr, &sec->name, - &sec->value, &sec->length); + error = security_inode_init_security(inode, dir, qstr, + &reiserfs_initxattrs, sec); if (error) { - if (error == -EOPNOTSUPP) - error = 0; - sec->name = NULL; sec->value = NULL; sec->length = 0; @@ -82,11 +95,15 @@ int reiserfs_security_write(struct reiserfs_transaction_handle *th, struct inode *inode, struct reiserfs_security_handle *sec) { + char xattr_name[XATTR_NAME_MAX + 1] = XATTR_SECURITY_PREFIX; int error; - if (strlen(sec->name) < sizeof(XATTR_SECURITY_PREFIX)) + + if (XATTR_SECURITY_PREFIX_LEN + strlen(sec->name) > XATTR_NAME_MAX) return -EINVAL; - error = reiserfs_xattr_set_handle(th, inode, sec->name, sec->value, + strlcat(xattr_name, sec->name, sizeof(xattr_name)); + + error = reiserfs_xattr_set_handle(th, inode, xattr_name, sec->value, sec->length, XATTR_CREATE); if (error == -ENODATA || error == -EOPNOTSUPP) error = 0; diff --git a/fs/splice.c b/fs/splice.c index 2c3dec2b6dfa..0af8d150394f 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -30,6 +30,7 @@ #include <linux/export.h> #include <linux/syscalls.h> #include <linux/uio.h> +#include <linux/fsnotify.h> #include <linux/security.h> #include <linux/gfp.h> #include <linux/socket.h> @@ -1165,6 +1166,9 @@ long do_splice(struct file *in, loff_t *off_in, struct file *out, ret = do_splice_from(ipipe, out, &offset, len, flags); file_end_write(out); + if (ret > 0) + fsnotify_modify(out); + if (!off_out) out->f_pos = offset; else @@ -1188,6 +1192,10 @@ long do_splice(struct file *in, loff_t *off_in, struct file *out, flags |= SPLICE_F_NONBLOCK; ret = splice_file_to_pipe(in, opipe, &offset, len, flags); + + if (ret > 0) + fsnotify_access(in); + if (!off_in) in->f_pos = offset; else diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c index 999bceb99974..cdb3d632c63d 100644 --- a/fs/sysv/dir.c +++ b/fs/sysv/dir.c @@ -28,12 +28,6 @@ const struct file_operations sysv_dir_operations = { .fsync = generic_file_fsync, }; -inline void dir_put_page(struct page *page, void *page_addr) -{ - kunmap_local((void *)((unsigned long)page_addr & PAGE_MASK)); - put_page(page); -} - static void dir_commit_chunk(struct page *page, loff_t pos, unsigned len) { struct address_space *mapping = page->mapping; @@ -58,7 +52,7 @@ static int sysv_handle_dirsync(struct inode *dir) } /* - * Calls to dir_get_page()/dir_put_page() must be nested according to the + * Calls to dir_get_page()/put_and_unmap_page() must be nested according to the * rules documented in mm/highmem.rst. * * NOTE: sysv_find_entry() and sysv_dotdot() act as calls to dir_get_page() @@ -109,11 +103,11 @@ static int sysv_readdir(struct file *file, struct dir_context *ctx) if (!dir_emit(ctx, name, strnlen(name,SYSV_NAMELEN), fs16_to_cpu(SYSV_SB(sb), de->inode), DT_UNKNOWN)) { - dir_put_page(page, kaddr); + put_and_unmap_page(page, kaddr); return 0; } } - dir_put_page(page, kaddr); + put_and_unmap_page(page, kaddr); } return 0; } @@ -137,7 +131,7 @@ static inline int namecompare(int len, int maxlen, * itself (as a parameter - res_dir). It does NOT read the inode of the * entry - you'll have to do that yourself if you want to. * - * On Success dir_put_page() should be called on *res_page. + * On Success put_and_unmap_page() should be called on *res_page. * * sysv_find_entry() acts as a call to dir_get_page() and must be treated * accordingly for nesting purposes. @@ -172,7 +166,7 @@ struct sysv_dir_entry *sysv_find_entry(struct dentry *dentry, struct page **res_ name, de->name)) goto found; } - dir_put_page(page, kaddr); + put_and_unmap_page(page, kaddr); } if (++n >= npages) @@ -215,7 +209,7 @@ int sysv_add_link(struct dentry *dentry, struct inode *inode) goto out_page; de++; } - dir_put_page(page, kaddr); + put_and_unmap_page(page, kaddr); } BUG(); return -EINVAL; @@ -234,7 +228,7 @@ got_it: mark_inode_dirty(dir); err = sysv_handle_dirsync(dir); out_page: - dir_put_page(page, kaddr); + put_and_unmap_page(page, kaddr); return err; out_unlock: unlock_page(page); @@ -327,12 +321,12 @@ int sysv_empty_dir(struct inode * inode) if (de->name[1] != '.' || de->name[2]) goto not_empty; } - dir_put_page(page, kaddr); + put_and_unmap_page(page, kaddr); } return 1; not_empty: - dir_put_page(page, kaddr); + put_and_unmap_page(page, kaddr); return 0; } @@ -358,7 +352,7 @@ int sysv_set_link(struct sysv_dir_entry *de, struct page *page, } /* - * Calls to dir_get_page()/dir_put_page() must be nested according to the + * Calls to dir_get_page()/put_and_unmap_page() must be nested according to the * rules documented in mm/highmem.rst. * * sysv_dotdot() acts as a call to dir_get_page() and must be treated @@ -382,7 +376,7 @@ ino_t sysv_inode_by_name(struct dentry *dentry) if (de) { res = fs16_to_cpu(SYSV_SB(dentry->d_sb), de->inode); - dir_put_page(page, de); + put_and_unmap_page(page, de); } return res; } diff --git a/fs/sysv/namei.c b/fs/sysv/namei.c index a25862773d82..2b2dba4c4f56 100644 --- a/fs/sysv/namei.c +++ b/fs/sysv/namei.c @@ -164,7 +164,7 @@ static int sysv_unlink(struct inode * dir, struct dentry * dentry) inode->i_ctime = dir->i_ctime; inode_dec_link_count(inode); } - dir_put_page(page, de); + put_and_unmap_page(page, de); return err; } @@ -227,7 +227,7 @@ static int sysv_rename(struct mnt_idmap *idmap, struct inode *old_dir, if (!new_de) goto out_dir; err = sysv_set_link(new_de, new_page, old_inode); - dir_put_page(new_page, new_de); + put_and_unmap_page(new_page, new_de); if (err) goto out_dir; new_inode->i_ctime = current_time(new_inode); @@ -256,9 +256,9 @@ static int sysv_rename(struct mnt_idmap *idmap, struct inode *old_dir, out_dir: if (dir_de) - dir_put_page(dir_page, dir_de); + put_and_unmap_page(dir_page, dir_de); out_old: - dir_put_page(old_page, old_de); + put_and_unmap_page(old_page, old_de); out: return err; } diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h index f2c36ea42df6..e3f988b469ee 100644 --- a/fs/sysv/sysv.h +++ b/fs/sysv/sysv.h @@ -148,7 +148,6 @@ extern void sysv_destroy_icache(void); /* dir.c */ -extern void dir_put_page(struct page *page, void *vaddr); extern struct sysv_dir_entry *sysv_find_entry(struct dentry *, struct page **); extern int sysv_add_link(struct dentry *, struct inode *); extern int sysv_delete_entry(struct sysv_dir_entry *, struct page *); diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index 391efaf1d528..379d75796a5c 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -42,11 +42,10 @@ static inline int ufs_match(struct super_block *sb, int len, return !memcmp(name, de->d_name, len); } -static int ufs_commit_chunk(struct page *page, loff_t pos, unsigned len) +static void ufs_commit_chunk(struct page *page, loff_t pos, unsigned len) { struct address_space *mapping = page->mapping; struct inode *dir = mapping->host; - int err = 0; inode_inc_iversion(dir); block_write_end(NULL, mapping, pos, len, len, page, NULL); @@ -54,10 +53,16 @@ static int ufs_commit_chunk(struct page *page, loff_t pos, unsigned len) i_size_write(dir, pos+len); mark_inode_dirty(dir); } - if (IS_DIRSYNC(dir)) - err = write_one_page(page); - else - unlock_page(page); + unlock_page(page); +} + +static int ufs_handle_dirsync(struct inode *dir) +{ + int err; + + err = filemap_write_and_wait(dir->i_mapping); + if (!err) + err = sync_inode_metadata(dir, 1); return err; } @@ -99,11 +104,12 @@ void ufs_set_link(struct inode *dir, struct ufs_dir_entry *de, de->d_ino = cpu_to_fs32(dir->i_sb, inode->i_ino); ufs_set_de_type(dir->i_sb, de, inode->i_mode); - err = ufs_commit_chunk(page, pos, len); + ufs_commit_chunk(page, pos, len); ufs_put_page(page); if (update_times) dir->i_mtime = dir->i_ctime = current_time(dir); mark_inode_dirty(dir); + ufs_handle_dirsync(dir); } @@ -390,10 +396,11 @@ got_it: de->d_ino = cpu_to_fs32(sb, inode->i_ino); ufs_set_de_type(sb, de, inode->i_mode); - err = ufs_commit_chunk(page, pos, rec_len); + ufs_commit_chunk(page, pos, rec_len); dir->i_mtime = dir->i_ctime = current_time(dir); mark_inode_dirty(dir); + err = ufs_handle_dirsync(dir); /* OFFSET_CACHE */ out_put: ufs_put_page(page); @@ -531,9 +538,10 @@ int ufs_delete_entry(struct inode *inode, struct ufs_dir_entry *dir, if (pde) pde->d_reclen = cpu_to_fs16(sb, to - from); dir->d_ino = 0; - err = ufs_commit_chunk(page, pos, to - from); + ufs_commit_chunk(page, pos, to - from); inode->i_ctime = inode->i_mtime = current_time(inode); mark_inode_dirty(inode); + err = ufs_handle_dirsync(inode); out: ufs_put_page(page); UFSD("EXIT\n"); @@ -579,7 +587,8 @@ int ufs_make_empty(struct inode * inode, struct inode *dir) strcpy (de->d_name, ".."); kunmap(page); - err = ufs_commit_chunk(page, 0, chunk_size); + ufs_commit_chunk(page, 0, chunk_size); + err = ufs_handle_dirsync(inode); fail: put_page(page); return err; diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 44d1ee429eb0..40f9e1a2ebdd 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -1955,8 +1955,10 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx, ret = -EFAULT; if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api))) goto out; - /* Ignore unsupported features (userspace built against newer kernel) */ - features = uffdio_api.features & UFFD_API_FEATURES; + features = uffdio_api.features; + ret = -EINVAL; + if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES)) + goto err_out; ret = -EPERM; if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE)) goto err_out; diff --git a/fs/xattr.c b/fs/xattr.c index 14a7eb3c8fa8..fcf67d80d7f9 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -160,11 +160,10 @@ xattr_permission(struct mnt_idmap *idmap, struct inode *inode, * Look for any handler that deals with the specified namespace. */ int -xattr_supported_namespace(struct inode *inode, const char *prefix) +xattr_supports_user_prefix(struct inode *inode) { const struct xattr_handler **handlers = inode->i_sb->s_xattr; const struct xattr_handler *handler; - size_t preflen; if (!(inode->i_opflags & IOP_XATTR)) { if (unlikely(is_bad_inode(inode))) @@ -172,16 +171,15 @@ xattr_supported_namespace(struct inode *inode, const char *prefix) return -EOPNOTSUPP; } - preflen = strlen(prefix); - for_each_xattr_handler(handlers, handler) { - if (!strncmp(xattr_prefix(handler), prefix, preflen)) + if (!strncmp(xattr_prefix(handler), XATTR_USER_PREFIX, + XATTR_USER_PREFIX_LEN)) return 0; } return -EOPNOTSUPP; } -EXPORT_SYMBOL(xattr_supported_namespace); +EXPORT_SYMBOL(xattr_supports_user_prefix); int __vfs_setxattr(struct mnt_idmap *idmap, struct dentry *dentry, @@ -460,6 +458,28 @@ nolsm: } EXPORT_SYMBOL_GPL(vfs_getxattr); +/** + * vfs_listxattr - retrieve \0 separated list of xattr names + * @dentry: the dentry from whose inode the xattr names are retrieved + * @list: buffer to store xattr names into + * @size: size of the buffer + * + * This function returns the names of all xattrs associated with the + * inode of @dentry. + * + * Note, for legacy reasons the vfs_listxattr() function lists POSIX + * ACLs as well. Since POSIX ACLs are decoupled from IOP_XATTR the + * vfs_listxattr() function doesn't check for this flag since a + * filesystem could implement POSIX ACLs without implementing any other + * xattrs. + * + * However, since all codepaths that remove IOP_XATTR also assign of + * inode operations that either don't implement or implement a stub + * ->listxattr() operation. + * + * Return: On success, the size of the buffer that was used. On error a + * negative error code. + */ ssize_t vfs_listxattr(struct dentry *dentry, char *list, size_t size) { @@ -469,7 +489,8 @@ vfs_listxattr(struct dentry *dentry, char *list, size_t size) error = security_inode_listxattr(dentry); if (error) return error; - if (inode->i_op->listxattr && (inode->i_opflags & IOP_XATTR)) { + + if (inode->i_op->listxattr) { error = inode->i_op->listxattr(dentry, list, size); } else { error = security_inode_listsecurity(inode, list, size); @@ -949,6 +970,21 @@ SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name) return error; } +int xattr_list_one(char **buffer, ssize_t *remaining_size, const char *name) +{ + size_t len; + + len = strlen(name) + 1; + if (*buffer) { + if (*remaining_size < len) + return -ERANGE; + memcpy(*buffer, name, len); + *buffer += len; + } + *remaining_size -= len; + return 0; +} + /* * Combine the results of the list() operation from every xattr_handler in the * list. @@ -957,33 +993,22 @@ ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { const struct xattr_handler *handler, **handlers = dentry->d_sb->s_xattr; - unsigned int size = 0; - - if (!buffer) { - for_each_xattr_handler(handlers, handler) { - if (!handler->name || - (handler->list && !handler->list(dentry))) - continue; - size += strlen(handler->name) + 1; - } - } else { - char *buf = buffer; - size_t len; - - for_each_xattr_handler(handlers, handler) { - if (!handler->name || - (handler->list && !handler->list(dentry))) - continue; - len = strlen(handler->name); - if (len + 1 > buffer_size) - return -ERANGE; - memcpy(buf, handler->name, len + 1); - buf += len + 1; - buffer_size -= len + 1; - } - size = buf - buffer; + ssize_t remaining_size = buffer_size; + int err = 0; + + err = posix_acl_listxattr(d_inode(dentry), &buffer, &remaining_size); + if (err) + return err; + + for_each_xattr_handler(handlers, handler) { + if (!handler->name || (handler->list && !handler->list(dentry))) + continue; + err = xattr_list_one(&buffer, &remaining_size, handler->name); + if (err) + return err; } - return size; + + return err ? err : buffer_size - remaining_size; } EXPORT_SYMBOL(generic_listxattr); @@ -1245,20 +1270,6 @@ static bool xattr_is_trusted(const char *name) return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN); } -static int xattr_list_one(char **buffer, ssize_t *remaining_size, - const char *name) -{ - size_t len = strlen(name) + 1; - if (*buffer) { - if (*remaining_size < len) - return -ERANGE; - memcpy(*buffer, name, len); - *buffer += len; - } - *remaining_size -= len; - return 0; -} - /** * simple_xattr_list - list all xattr objects * @inode: inode from which to get the xattrs @@ -1287,22 +1298,9 @@ ssize_t simple_xattr_list(struct inode *inode, struct simple_xattrs *xattrs, ssize_t remaining_size = size; int err = 0; -#ifdef CONFIG_FS_POSIX_ACL - if (IS_POSIXACL(inode)) { - if (inode->i_acl) { - err = xattr_list_one(&buffer, &remaining_size, - XATTR_NAME_POSIX_ACL_ACCESS); - if (err) - return err; - } - if (inode->i_default_acl) { - err = xattr_list_one(&buffer, &remaining_size, - XATTR_NAME_POSIX_ACL_DEFAULT); - if (err) - return err; - } - } -#endif + err = posix_acl_listxattr(inode, &buffer, &remaining_size); + if (err) + return err; read_lock(&xattrs->lock); for (rbp = rb_first(&xattrs->rb_root); rbp; rbp = rb_next(rbp)) { diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index 7b9a0ed1b11f..43e5c219aaed 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -179,10 +179,6 @@ const struct xattr_handler *xfs_xattr_handlers[] = { &xfs_xattr_user_handler, &xfs_xattr_trusted_handler, &xfs_xattr_security_handler, -#ifdef CONFIG_XFS_POSIX_ACL - &posix_acl_access_xattr_handler, - &posix_acl_default_xattr_handler, -#endif NULL }; diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c index 617e4f9db42e..132f01d3461f 100644 --- a/fs/zonefs/file.c +++ b/fs/zonefs/file.c @@ -382,6 +382,7 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) struct zonefs_zone *z = zonefs_inode_zone(inode); struct block_device *bdev = inode->i_sb->s_bdev; unsigned int max = bdev_max_zone_append_sectors(bdev); + pgoff_t start, end; struct bio *bio; ssize_t size = 0; int nr_pages; @@ -390,6 +391,19 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from) max = ALIGN_DOWN(max << SECTOR_SHIFT, inode->i_sb->s_blocksize); iov_iter_truncate(from, max); + /* + * If the inode block size (zone write granularity) is smaller than the + * page size, we may be appending data belonging to the last page of the + * inode straddling inode->i_size, with that page already cached due to + * a buffered read or readahead. So make sure to invalidate that page. + * This will always be a no-op for the case where the block size is + * equal to the page size. + */ + start = iocb->ki_pos >> PAGE_SHIFT; + end = (iocb->ki_pos + iov_iter_count(from) - 1) >> PAGE_SHIFT; + if (invalidate_inode_pages2_range(inode->i_mapping, start, end)) + return -EBUSY; + nr_pages = iov_iter_npages(from, BIO_MAX_VECS); if (!nr_pages) return 0; @@ -567,11 +581,21 @@ static ssize_t zonefs_file_dio_write(struct kiocb *iocb, struct iov_iter *from) append = sync; } - if (append) + if (append) { ret = zonefs_file_dio_append(iocb, from); - else + } else { + /* + * iomap_dio_rw() may return ENOTBLK if there was an issue with + * page invalidation. Overwrite that error code with EBUSY to + * be consistent with zonefs_file_dio_append() return value for + * similar issues. + */ ret = iomap_dio_rw(iocb, from, &zonefs_write_iomap_ops, &zonefs_write_dio_ops, 0, NULL, 0); + if (ret == -ENOTBLK) + ret = -EBUSY; + } + if (zonefs_zone_is_seq(z) && (ret > 0 || ret == -EIOCBQUEUED)) { if (ret > 0) |