diff options
Diffstat (limited to 'fs')
35 files changed, 395 insertions, 185 deletions
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h index 8d3c278a7591..4263cac24b32 100644 --- a/fs/crypto/fscrypt_private.h +++ b/fs/crypto/fscrypt_private.h @@ -236,7 +236,7 @@ struct fscrypt_symlink_data { * @tfm: crypto API transform object * @blk_key: key for blk-crypto * - * Normally only one of the fields will be non-NULL. + * Only one of the fields is non-NULL. */ struct fscrypt_prepared_key { struct crypto_sync_skcipher *tfm; @@ -245,6 +245,15 @@ struct fscrypt_prepared_key { #endif }; +/* An entry in the linked list ->mk_mode_keys */ +struct fscrypt_mode_key { + struct fscrypt_prepared_key key; + struct list_head link; + u8 hkdf_context; + u8 mode_num; + u8 data_unit_bits; +}; + /* * fscrypt_inode_info - the "encryption key" for an inode * @@ -430,20 +439,12 @@ int fscrypt_derive_sw_secret(struct super_block *sb, * @prep_key, depending on which encryption implementation the file will use. */ static inline bool -fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key, +fscrypt_is_key_prepared(const struct fscrypt_prepared_key *prep_key, const struct fscrypt_inode_info *ci) { - /* - * The two smp_load_acquire()'s here pair with the smp_store_release()'s - * in fscrypt_prepare_inline_crypt_key() and fscrypt_prepare_key(). - * I.e., in some cases (namely, if this prep_key is a per-mode - * encryption key) another task can publish blk_key or tfm concurrently, - * executing a RELEASE barrier. We need to use smp_load_acquire() here - * to safely ACQUIRE the memory the other task published. - */ if (fscrypt_using_inline_encryption(ci)) - return smp_load_acquire(&prep_key->blk_key) != NULL; - return smp_load_acquire(&prep_key->tfm) != NULL; + return prep_key->blk_key != NULL; + return prep_key->tfm != NULL; } #else /* CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ @@ -486,10 +487,10 @@ fscrypt_derive_sw_secret(struct super_block *sb, } static inline bool -fscrypt_is_key_prepared(struct fscrypt_prepared_key *prep_key, +fscrypt_is_key_prepared(const struct fscrypt_prepared_key *prep_key, const struct fscrypt_inode_info *ci) { - return smp_load_acquire(&prep_key->tfm) != NULL; + return prep_key->tfm != NULL; } #endif /* !CONFIG_FS_ENCRYPTION_INLINE_CRYPT */ @@ -577,8 +578,8 @@ struct fscrypt_master_key { /* * Active and structural reference counts. An active ref guarantees * that the struct continues to exist, continues to be in the keyring - * ->s_master_keys, and that any embedded subkeys (e.g. - * ->mk_direct_keys) that have been prepared continue to exist. + * ->s_master_keys, and that any non-file-scoped subkeys (e.g. + * ->mk_mode_keys) that have been prepared continue to exist. * A structural ref only guarantees that the struct continues to exist. * * There is one active ref associated with ->mk_present being true, and @@ -632,12 +633,21 @@ struct fscrypt_master_key { spinlock_t mk_decrypted_inodes_lock; /* - * Per-mode encryption keys for the various types of encryption policies - * that use them. Allocated and derived on-demand. + * A list of 'struct fscrypt_mode_key' for the (hkdf_context, mode_num, + * data_unit_bits, inlinecrypt) combinations that are in use for this + * master key, for hkdf_context in [HKDF_CONTEXT_DIRECT_KEY, + * HKDF_CONTEXT_IV_INO_LBLK_32_KEY, HKDF_CONTEXT_IV_INO_LBLK_64_KEY]. + * + * This is a linked list and not a hash table because in practice + * there's just a single encryption policy per master key, using + * _at most_ 2 nodes in this list. Per-file keys don't use this at all. + * + * This list is append-only until the master key is fully removed, at + * which time the list is cleared. Before then, + * fscrypt_mode_key_setup_mutex synchronizes appends, and searches use + * the RCU read lock together with ->mk_sem held for read. */ - struct fscrypt_prepared_key mk_direct_keys[FSCRYPT_MODE_MAX + 1]; - struct fscrypt_prepared_key mk_iv_ino_lblk_64_keys[FSCRYPT_MODE_MAX + 1]; - struct fscrypt_prepared_key mk_iv_ino_lblk_32_keys[FSCRYPT_MODE_MAX + 1]; + struct list_head mk_mode_keys; /* Hash key for inode numbers. Initialized only when needed. */ siphash_key_t mk_ino_hash_key; diff --git a/fs/crypto/inline_crypt.c b/fs/crypto/inline_crypt.c index 37d42d357925..47324062fee5 100644 --- a/fs/crypto/inline_crypt.c +++ b/fs/crypto/inline_crypt.c @@ -198,13 +198,7 @@ int fscrypt_prepare_inline_crypt_key(struct fscrypt_prepared_key *prep_key, goto fail; } - /* - * Pairs with the smp_load_acquire() in fscrypt_is_key_prepared(). - * I.e., here we publish ->blk_key with a RELEASE barrier so that - * concurrent tasks can ACQUIRE it. Note that this concurrency is only - * possible for per-mode keys, not for per-file keys. - */ - smp_store_release(&prep_key->blk_key, blk_key); + prep_key->blk_key = blk_key; return 0; fail: diff --git a/fs/crypto/keyring.c b/fs/crypto/keyring.c index be8e6e8011f2..5fe0d985a58d 100644 --- a/fs/crypto/keyring.c +++ b/fs/crypto/keyring.c @@ -87,14 +87,14 @@ void fscrypt_put_master_key(struct fscrypt_master_key *mk) void fscrypt_put_master_key_activeref(struct super_block *sb, struct fscrypt_master_key *mk) { - size_t i; + struct fscrypt_mode_key *node, *tmp; if (!refcount_dec_and_test(&mk->mk_active_refs)) return; /* * No active references left, so complete the full removal of this * fscrypt_master_key struct by removing it from the keyring and - * destroying any subkeys embedded in it. + * destroying any non-file-scoped subkeys. */ if (WARN_ON_ONCE(!sb->s_master_keys)) @@ -110,13 +110,16 @@ void fscrypt_put_master_key_activeref(struct super_block *sb, WARN_ON_ONCE(mk->mk_present); WARN_ON_ONCE(!list_empty(&mk->mk_decrypted_inodes)); - for (i = 0; i <= FSCRYPT_MODE_MAX; i++) { - fscrypt_destroy_prepared_key( - sb, &mk->mk_direct_keys[i]); - fscrypt_destroy_prepared_key( - sb, &mk->mk_iv_ino_lblk_64_keys[i]); - fscrypt_destroy_prepared_key( - sb, &mk->mk_iv_ino_lblk_32_keys[i]); + /* + * Destroy any non-file-scoped subkeys. Since ->mk_active_refs == 0, + * they're no longer referenced by any inodes. Nor can key setup run + * and use them again. So they're no longer needed. (This implies no + * concurrent readers, so we don't need list_del_rcu() for example.) + */ + list_for_each_entry_safe(node, tmp, &mk->mk_mode_keys, link) { + fscrypt_destroy_prepared_key(sb, &node->key); + list_del(&node->link); + kfree(node); } memzero_explicit(&mk->mk_ino_hash_key, sizeof(mk->mk_ino_hash_key)); @@ -445,6 +448,8 @@ static int add_new_master_key(struct super_block *sb, INIT_LIST_HEAD(&mk->mk_decrypted_inodes); spin_lock_init(&mk->mk_decrypted_inodes_lock); + INIT_LIST_HEAD(&mk->mk_mode_keys); + if (mk_spec->type == FSCRYPT_KEY_SPEC_TYPE_IDENTIFIER) { err = allocate_master_key_users_keyring(mk); if (err) diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index ce327bfdada4..f905f9f94bdd 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -163,13 +163,7 @@ int fscrypt_prepare_key(struct fscrypt_prepared_key *prep_key, tfm = fscrypt_allocate_skcipher(ci->ci_mode, raw_key, ci->ci_inode); if (IS_ERR(tfm)) return PTR_ERR(tfm); - /* - * Pairs with the smp_load_acquire() in fscrypt_is_key_prepared(). - * I.e., here we publish ->tfm with a RELEASE barrier so that - * concurrent tasks can ACQUIRE it. Note that this concurrency is only - * possible for per-mode keys, not for per-file keys. - */ - smp_store_release(&prep_key->tfm, tfm); + prep_key->tfm = tfm; return 0; } @@ -190,9 +184,37 @@ int fscrypt_set_per_file_enc_key(struct fscrypt_inode_info *ci, return fscrypt_prepare_key(&ci->ci_enc_key, raw_key, ci); } +/* + * Find the fscrypt_prepared_key (if any) for a particular (mk, hkdf_context, + * mode_num, data_unit_bits, inlinecrypt) combination. + * + * The caller must hold ->mk_sem for reading and ->mk_present must be true, + * ensuring that ->mk_mode_keys is still append-only. + */ +static struct fscrypt_prepared_key * +fscrypt_find_mode_key(struct fscrypt_master_key *mk, u8 hkdf_context, + u8 mode_num, const struct fscrypt_inode_info *ci) +{ + struct fscrypt_mode_key *node; + + /* + * The RCU read lock here is used only to synchronize with concurrent + * list_add_tail_rcu(). Concurrent deletions are impossible here, so + * returning a pointer to a node without taking any refcount is safe. + */ + guard(rcu)(); + list_for_each_entry_rcu(node, &mk->mk_mode_keys, link) { + if (node->hkdf_context == hkdf_context && + node->mode_num == mode_num && + node->data_unit_bits == ci->ci_data_unit_bits && + fscrypt_is_key_prepared(&node->key, ci)) + return &node->key; + } + return NULL; +} + static int setup_per_mode_enc_key(struct fscrypt_inode_info *ci, struct fscrypt_master_key *mk, - struct fscrypt_prepared_key *keys, u8 hkdf_context, bool include_fs_uuid) { const struct inode *inode = ci->ci_inode; @@ -200,7 +222,8 @@ static int setup_per_mode_enc_key(struct fscrypt_inode_info *ci, struct fscrypt_mode *mode = ci->ci_mode; const u8 mode_num = mode - fscrypt_modes; struct fscrypt_prepared_key *prep_key; - u8 mode_key[FSCRYPT_MAX_RAW_KEY_SIZE]; + struct fscrypt_mode_key *new_node; + u8 raw_mode_key[FSCRYPT_MAX_RAW_KEY_SIZE]; u8 hkdf_info[sizeof(mode_num) + sizeof(sb->s_uuid)]; unsigned int hkdf_infolen = 0; bool use_hw_wrapped_key = false; @@ -223,48 +246,56 @@ static int setup_per_mode_enc_key(struct fscrypt_inode_info *ci, use_hw_wrapped_key = true; } - prep_key = &keys[mode_num]; - if (fscrypt_is_key_prepared(prep_key, ci)) { + prep_key = fscrypt_find_mode_key(mk, hkdf_context, mode_num, ci); + if (prep_key) { ci->ci_enc_key = *prep_key; return 0; } - mutex_lock(&fscrypt_mode_key_setup_mutex); + guard(mutex)(&fscrypt_mode_key_setup_mutex); - if (fscrypt_is_key_prepared(prep_key, ci)) - goto done_unlock; + prep_key = fscrypt_find_mode_key(mk, hkdf_context, mode_num, ci); + if (prep_key) { + ci->ci_enc_key = *prep_key; + return 0; + } + + new_node = kzalloc_obj(*new_node); + if (!new_node) + return -ENOMEM; + new_node->hkdf_context = hkdf_context; + new_node->mode_num = mode_num; + new_node->data_unit_bits = ci->ci_data_unit_bits; + prep_key = &new_node->key; if (use_hw_wrapped_key) { err = fscrypt_prepare_inline_crypt_key(prep_key, mk->mk_secret.bytes, mk->mk_secret.size, true, ci); - if (err) - goto out_unlock; - goto done_unlock; + } else { + static_assert(sizeof(mode_num) == 1); + static_assert(sizeof(sb->s_uuid) == 16); + static_assert(sizeof(hkdf_info) == 17); + hkdf_info[hkdf_infolen++] = mode_num; + if (include_fs_uuid) { + memcpy(&hkdf_info[hkdf_infolen], &sb->s_uuid, + sizeof(sb->s_uuid)); + hkdf_infolen += sizeof(sb->s_uuid); + } + fscrypt_hkdf_expand(&mk->mk_secret.hkdf, hkdf_context, + hkdf_info, hkdf_infolen, raw_mode_key, + mode->keysize); + err = fscrypt_prepare_key(prep_key, raw_mode_key, ci); + memzero_explicit(raw_mode_key, mode->keysize); } - - BUILD_BUG_ON(sizeof(mode_num) != 1); - BUILD_BUG_ON(sizeof(sb->s_uuid) != 16); - BUILD_BUG_ON(sizeof(hkdf_info) != 17); - hkdf_info[hkdf_infolen++] = mode_num; - if (include_fs_uuid) { - memcpy(&hkdf_info[hkdf_infolen], &sb->s_uuid, - sizeof(sb->s_uuid)); - hkdf_infolen += sizeof(sb->s_uuid); + if (err) { + kfree(new_node); + return err; } - fscrypt_hkdf_expand(&mk->mk_secret.hkdf, hkdf_context, hkdf_info, - hkdf_infolen, mode_key, mode->keysize); - err = fscrypt_prepare_key(prep_key, mode_key, ci); - memzero_explicit(mode_key, mode->keysize); - if (err) - goto out_unlock; -done_unlock: + list_add_tail_rcu(&new_node->link, &mk->mk_mode_keys); ci->ci_enc_key = *prep_key; - err = 0; -out_unlock: - mutex_unlock(&fscrypt_mode_key_setup_mutex); - return err; + return 0; } /* @@ -311,8 +342,8 @@ static int fscrypt_setup_iv_ino_lblk_32_key(struct fscrypt_inode_info *ci, { int err; - err = setup_per_mode_enc_key(ci, mk, mk->mk_iv_ino_lblk_32_keys, - HKDF_CONTEXT_IV_INO_LBLK_32_KEY, true); + err = setup_per_mode_enc_key(ci, mk, HKDF_CONTEXT_IV_INO_LBLK_32_KEY, + true); if (err) return err; @@ -364,8 +395,8 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_inode_info *ci, * encryption key. This ensures that the master key is * consistently used only for HKDF, avoiding key reuse issues. */ - err = setup_per_mode_enc_key(ci, mk, mk->mk_direct_keys, - HKDF_CONTEXT_DIRECT_KEY, false); + err = setup_per_mode_enc_key(ci, mk, HKDF_CONTEXT_DIRECT_KEY, + false); } else if (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64) { /* @@ -374,9 +405,8 @@ static int fscrypt_setup_v2_file_key(struct fscrypt_inode_info *ci, * the IVs. This format is optimized for use with inline * encryption hardware compliant with the UFS standard. */ - err = setup_per_mode_enc_key(ci, mk, mk->mk_iv_ino_lblk_64_keys, - HKDF_CONTEXT_IV_INO_LBLK_64_KEY, - true); + err = setup_per_mode_enc_key( + ci, mk, HKDF_CONTEXT_IV_INO_LBLK_64_KEY, true); } else if (ci->ci_policy.v2.flags & FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32) { err = fscrypt_setup_iv_ino_lblk_32_key(ci, mk); diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c index ac008ccaa97d..561fd2349218 100644 --- a/fs/exfat/dir.c +++ b/fs/exfat/dir.c @@ -1027,12 +1027,12 @@ rewind: continue; } - brelse(bh); if (entry_type == TYPE_EXTEND) { unsigned short entry_uniname[16], unichar; if (step != DIRENT_STEP_NAME || name_len >= MAX_NAME_LENGTH) { + brelse(bh); step = DIRENT_STEP_FILE; continue; } @@ -1043,6 +1043,7 @@ rewind: uniname += EXFAT_FILE_NAME_LEN; len = exfat_extract_uni_name(ep, entry_uniname); + brelse(bh); name_len += len; unichar = *(uniname+len); @@ -1061,6 +1062,7 @@ rewind: continue; } + brelse(bh); if (entry_type & (TYPE_CRITICAL_SEC | TYPE_BENIGN_SEC)) { if (step == DIRENT_STEP_SECD) { diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c index fa8d81a30fb9..d3253549173e 100644 --- a/fs/f2fs/acl.c +++ b/fs/f2fs/acl.c @@ -47,6 +47,7 @@ static inline int f2fs_acl_count(size_t size) static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) { int i, count; + int err = -EINVAL; struct posix_acl *acl; struct f2fs_acl_header *hdr = (struct f2fs_acl_header *)value; struct f2fs_acl_entry *entry = (struct f2fs_acl_entry *)(hdr + 1); @@ -70,8 +71,11 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) for (i = 0; i < count; i++) { - if ((char *)entry > end) + if (unlikely((char *)entry + + sizeof(struct f2fs_acl_entry_short) > end)) { + err = -EFSCORRUPTED; goto fail; + } acl->a_entries[i].e_tag = le16_to_cpu(entry->e_tag); acl->a_entries[i].e_perm = le16_to_cpu(entry->e_perm); @@ -86,6 +90,11 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) break; case ACL_USER: + if (unlikely((char *)entry + + sizeof(struct f2fs_acl_entry) > end)) { + err = -EFSCORRUPTED; + goto fail; + } acl->a_entries[i].e_uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id)); @@ -93,6 +102,11 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) sizeof(struct f2fs_acl_entry)); break; case ACL_GROUP: + if (unlikely((char *)entry + + sizeof(struct f2fs_acl_entry) > end)) { + err = -EFSCORRUPTED; + goto fail; + } acl->a_entries[i].e_gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id)); @@ -108,7 +122,7 @@ static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) return acl; fail: posix_acl_release(acl); - return ERR_PTR(-EINVAL); + return ERR_PTR(err); } static void *f2fs_acl_to_disk(struct f2fs_sb_info *sbi, diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c index c00a6b6ebcbd..064f5b537423 100644 --- a/fs/f2fs/checkpoint.c +++ b/fs/f2fs/checkpoint.c @@ -943,6 +943,7 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi) for (i = 0; i < orphan_blocks; i++) { struct folio *folio; struct f2fs_orphan_block *orphan_blk; + unsigned int entry_count; folio = f2fs_get_meta_folio(sbi, start_blk + i); if (IS_ERR(folio)) { @@ -951,7 +952,18 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi) } orphan_blk = folio_address(folio); - for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) { + entry_count = le32_to_cpu(orphan_blk->entry_count); + if (entry_count > F2FS_ORPHANS_PER_BLOCK) { + f2fs_err(sbi, "invalid orphan inode entry count %u", + entry_count); + set_sbi_flag(sbi, SBI_NEED_FSCK); + f2fs_handle_error(sbi, ERROR_INCONSISTENT_ORPHAN); + err = -EFSCORRUPTED; + f2fs_folio_put(folio, true); + goto out; + } + + for (j = 0; j < entry_count; j++) { nid_t ino = le32_to_cpu(orphan_blk->ino[j]); err = recover_orphan_inode(sbi, ino); diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 8d4f1e75dee3..e24b74859427 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2495,7 +2495,7 @@ static int f2fs_read_data_large_folio(struct inode *inode, unsigned nrpages; struct f2fs_folio_state *ffs; int ret = 0; - bool folio_in_bio; + bool folio_in_bio = false; if (!IS_IMMUTABLE(inode) || f2fs_compressed_file(inode)) { if (folio) @@ -2611,18 +2611,17 @@ submit_and_realloc: } trace_f2fs_read_folio(folio, DATA); err_out: - if (!folio_in_bio) { + if (!folio_in_bio) folio_end_read(folio, !ret); - if (ret) - return ret; - } + if (ret) + goto out; if (rac) { folio = readahead_folio(rac); goto next_folio; } out: f2fs_submit_read_bio(F2FS_I_SB(inode), bio, DATA); - if (ret) { + if (ret && folio_in_bio) { /* Wait bios and clear uptodate. */ folio_lock(folio); folio_clear_uptodate(folio); @@ -3822,13 +3821,14 @@ unlock_out: static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi, struct folio *folio, loff_t pos, unsigned int len, - block_t *blk_addr, bool *node_changed, bool *use_cow) + block_t *blk_addr, bool *node_changed) { struct inode *inode = folio->mapping->host; struct inode *cow_inode = F2FS_I(inode)->cow_inode; pgoff_t index = folio->index; int err = 0; block_t ori_blk_addr = NULL_ADDR; + bool cow_has_reserved_block = false; /* If pos is beyond the end of file, reserve a new block in COW inode */ if ((pos & PAGE_MASK) >= i_size_read(inode)) @@ -3836,12 +3836,14 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi, /* Look for the block in COW inode first */ err = __find_data_block(cow_inode, index, blk_addr); - if (err) { + if (err) return err; - } else if (*blk_addr != NULL_ADDR) { - *use_cow = true; + + if (__is_valid_data_blkaddr(*blk_addr)) return 0; - } + + if (*blk_addr == NEW_ADDR) + cow_has_reserved_block = true; if (is_inode_flag_set(inode, FI_ATOMIC_REPLACE)) goto reserve_block; @@ -3853,10 +3855,13 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi, reserve_block: /* Finally, we should reserve a new block in COW inode for the update */ - err = __reserve_data_block(cow_inode, index, blk_addr, node_changed); - if (err) - return err; - inc_atomic_write_cnt(inode); + if (!cow_has_reserved_block) { + err = __reserve_data_block(cow_inode, index, blk_addr, + node_changed); + if (err) + return err; + inc_atomic_write_cnt(inode); + } if (ori_blk_addr != NULL_ADDR) *blk_addr = ori_blk_addr; @@ -3873,7 +3878,6 @@ static int f2fs_write_begin(const struct kiocb *iocb, struct folio *folio; pgoff_t index = pos >> PAGE_SHIFT; bool need_balance = false; - bool use_cow = false; block_t blkaddr = NULL_ADDR; int err = 0; @@ -3936,7 +3940,7 @@ repeat: if (f2fs_is_atomic_file(inode)) err = prepare_atomic_write_begin(sbi, folio, pos, len, - &blkaddr, &need_balance, &use_cow); + &blkaddr, &need_balance); else err = prepare_write_begin(sbi, folio, pos, len, &blkaddr, &need_balance); @@ -3976,8 +3980,15 @@ repeat: err = -EFSCORRUPTED; goto put_folio; } - f2fs_submit_page_read(use_cow ? F2FS_I(inode)->cow_inode : - inode, + /* + * Although the block may be stored in the COW inode, the folio + * belongs to @inode and its data was encrypted (or not) using + * @inode's context (see f2fs_encrypt_one_page()). Read with + * @inode so the post-read decryption decision matches the + * folio's owner; otherwise an unencrypted @inode whose COW inode + * is encrypted hits a NULL ->i_crypt_info on decryption. + */ + f2fs_submit_page_read(inode, NULL, /* can't write to fsverity files */ folio, blkaddr, 0, true); diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c index d2e006420f04..61f6b9714366 100644 --- a/fs/f2fs/extent_cache.c +++ b/fs/f2fs/extent_cache.c @@ -119,10 +119,9 @@ static bool __may_extent_tree(struct inode *inode, enum extent_type type) if (!__init_may_extent_tree(inode, type)) return false; - if (is_inode_flag_set(inode, FI_NO_EXTENT)) - return false; - if (type == EX_READ) { + if (is_inode_flag_set(inode, FI_NO_EXTENT)) + return false; if (is_inode_flag_set(inode, FI_COMPRESSED_FILE) && !f2fs_sb_has_readonly(F2FS_I_SB(inode))) return false; @@ -645,14 +644,10 @@ static unsigned int __destroy_extent_node(struct inode *inode, while (atomic_read(&et->node_cnt)) { write_lock(&et->lock); - if (!is_inode_flag_set(inode, FI_NO_EXTENT)) - set_inode_flag(inode, FI_NO_EXTENT); node_cnt += __free_extent_tree(sbi, et, nr_shrink); write_unlock(&et->lock); } - f2fs_bug_on(sbi, atomic_read(&et->node_cnt)); - return node_cnt; } @@ -691,12 +686,12 @@ static void __update_extent_tree_range(struct inode *inode, write_lock(&et->lock); - if (is_inode_flag_set(inode, FI_NO_EXTENT)) { - write_unlock(&et->lock); - return; - } - if (type == EX_READ) { + if (is_inode_flag_set(inode, FI_NO_EXTENT)) { + write_unlock(&et->lock); + return; + } + prev = et->largest; dei.len = 0; diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 91f506e7c9cf..069595fc5e1a 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1583,6 +1583,7 @@ enum node_type { NODE_TYPE_INODE, NODE_TYPE_XATTR, NODE_TYPE_NON_INODE, + NODE_TYPE_NON_IXNODE, /* non inode and xnode */ }; /* a threshold of maximum elapsed time in critical region to print tracepoint */ diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index fb12c5c9affd..ade4fde2ef0e 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -1098,6 +1098,8 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, return -EPERM; if ((attr->ia_valid & ATTR_SIZE)) { + if (mapping_large_folio_support(inode->i_mapping)) + return -EOPNOTSUPP; if (!f2fs_is_compress_backend_ready(inode) || IS_DEVICE_ALIASING(inode)) return -EOPNOTSUPP; @@ -1914,8 +1916,15 @@ static int f2fs_expand_inode_data(struct inode *inode, loff_t offset, if (f2fs_is_pinned_file(inode)) { block_t sec_blks = CAP_BLKS_PER_SEC(sbi); - block_t sec_len = roundup(map.m_len, sec_blks); + block_t sec_len; + if (map.m_lblk % sec_blks) { + map.m_lblk = rounddown(map.m_lblk, sec_blks); + map.m_len = pg_end - map.m_lblk; + if (off_end) + map.m_len++; + } + sec_len = roundup(map.m_len, sec_blks); map.m_len = sec_blks; next_alloc: f2fs_down_write(&sbi->pin_sem); diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c index ba93010924c0..11228349b003 100644 --- a/fs/f2fs/gc.c +++ b/fs/f2fs/gc.c @@ -1220,8 +1220,8 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum, static int ra_data_block(struct inode *inode, pgoff_t index) { struct f2fs_sb_info *sbi = F2FS_I_SB(inode); - struct address_space *mapping = f2fs_is_cow_file(inode) ? - F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping; + struct address_space *mapping = inode->i_mapping; + struct inode *atomic_inode = NULL; struct dnode_of_data dn; struct folio *folio, *efolio; struct f2fs_io_info fio = { @@ -1236,9 +1236,22 @@ static int ra_data_block(struct inode *inode, pgoff_t index) }; int err = 0; + f2fs_down_read(&F2FS_I(inode)->i_sem); + if (f2fs_is_cow_file(inode)) { + atomic_inode = igrab(F2FS_I(inode)->atomic_inode); + if (!atomic_inode) { + f2fs_up_read(&F2FS_I(inode)->i_sem); + return -EBUSY; + } + mapping = atomic_inode->i_mapping; + } + f2fs_up_read(&F2FS_I(inode)->i_sem); + folio = f2fs_grab_cache_folio(mapping, index, true); - if (IS_ERR(folio)) - return PTR_ERR(folio); + if (IS_ERR(folio)) { + err = PTR_ERR(folio); + goto out_iput; + } if (f2fs_lookup_read_extent_cache_block(inode, index, &dn.data_blkaddr)) { @@ -1299,11 +1312,16 @@ got_it: f2fs_update_iostat(sbi, inode, FS_DATA_READ_IO, F2FS_BLKSIZE); f2fs_update_iostat(sbi, NULL, FS_GDATA_READ_IO, F2FS_BLKSIZE); + if (atomic_inode) + iput(atomic_inode); return 0; put_encrypted_page: f2fs_put_page(fio.encrypted_page, true); put_folio: f2fs_folio_put(folio, true); +out_iput: + if (atomic_inode) + iput(atomic_inode); return err; } @@ -1314,8 +1332,8 @@ put_folio: static int move_data_block(struct inode *inode, block_t bidx, int gc_type, unsigned int segno, int off) { - struct address_space *mapping = f2fs_is_cow_file(inode) ? - F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping; + struct address_space *mapping = inode->i_mapping; + struct inode *atomic_inode = NULL; struct f2fs_io_info fio = { .sbi = F2FS_I_SB(inode), .ino = inode->i_ino, @@ -1337,10 +1355,23 @@ static int move_data_block(struct inode *inode, block_t bidx, (fio.sbi->gc_mode != GC_URGENT_HIGH) ? CURSEG_ALL_DATA_ATGC : CURSEG_COLD_DATA; + f2fs_down_read(&F2FS_I(inode)->i_sem); + if (f2fs_is_cow_file(inode)) { + atomic_inode = igrab(F2FS_I(inode)->atomic_inode); + if (!atomic_inode) { + f2fs_up_read(&F2FS_I(inode)->i_sem); + return -EBUSY; + } + mapping = atomic_inode->i_mapping; + } + f2fs_up_read(&F2FS_I(inode)->i_sem); + /* do not read out */ folio = f2fs_grab_cache_folio(mapping, bidx, false); - if (IS_ERR(folio)) - return PTR_ERR(folio); + if (IS_ERR(folio)) { + err = PTR_ERR(folio); + goto out_iput; + } if (!check_valid_map(F2FS_I_SB(inode), segno, off)) { err = -ENOENT; @@ -1468,11 +1499,10 @@ up_out: put_out: f2fs_put_dnode(&dn); out: - if (!folio_test_uptodate(folio)) - __folio_set_dropbehind(folio); - folio_unlock(folio); - folio_end_dropbehind(folio); - folio_put(folio); + f2fs_folio_put(folio, true); +out_iput: + if (atomic_inode) + iput(atomic_inode); return err; } diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c index c6dcda447882..5f0cf81e49f0 100644 --- a/fs/f2fs/inode.c +++ b/fs/f2fs/inode.c @@ -324,9 +324,9 @@ static bool sanity_check_inode(struct inode *inode, struct folio *node_folio) } if (f2fs_sb_has_flexible_inline_xattr(sbi) && - f2fs_has_inline_xattr(inode) && - (fi->i_inline_xattr_size < MIN_INLINE_XATTR_SIZE || - fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE)) { + (fi->i_inline_xattr_size > MAX_INLINE_XATTR_SIZE || + (f2fs_has_inline_xattr(inode) && + fi->i_inline_xattr_size < MIN_INLINE_XATTR_SIZE))) { f2fs_warn(sbi, "%s: inode (ino=%llx) has corrupted i_inline_xattr_size: %d, min: %zu, max: %lu", __func__, inode->i_ino, fi->i_inline_xattr_size, MIN_INLINE_XATTR_SIZE, MAX_INLINE_XATTR_SIZE); @@ -561,8 +561,13 @@ static int do_read_inode(struct inode *inode) static bool is_meta_ino(struct f2fs_sb_info *sbi, unsigned int ino) { - return ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi) || - ino == F2FS_COMPRESS_INO(sbi); + if (ino == F2FS_NODE_INO(sbi) || ino == F2FS_META_INO(sbi)) + return true; +#ifdef CONFIG_F2FS_FS_COMPRESSION + if (test_opt(sbi, COMPRESS_CACHE) && ino == F2FS_COMPRESS_INO(sbi)) + return true; +#endif + return false; } struct inode *f2fs_iget(struct super_block *sb, unsigned long ino) @@ -858,10 +863,15 @@ void f2fs_evict_inode(struct inode *inode) f2fs_abort_atomic_write(inode, true); if (fi->cow_inode && f2fs_is_cow_file(fi->cow_inode)) { - clear_inode_flag(fi->cow_inode, FI_COW_FILE); - F2FS_I(fi->cow_inode)->atomic_inode = NULL; - iput(fi->cow_inode); + struct inode *cow_inode = fi->cow_inode; + + f2fs_down_write(&F2FS_I(cow_inode)->i_sem); + clear_inode_flag(cow_inode, FI_COW_FILE); + F2FS_I(cow_inode)->atomic_inode = NULL; fi->cow_inode = NULL; + f2fs_up_write(&F2FS_I(cow_inode)->i_sem); + + iput(cow_inode); } trace_f2fs_evict_inode(inode); diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c index 4e5bd9e4cfc3..01d860e7e169 100644 --- a/fs/f2fs/node.c +++ b/fs/f2fs/node.c @@ -1541,6 +1541,10 @@ int f2fs_sanity_check_node_footer(struct f2fs_sb_info *sbi, if (is_inode) goto out_err; break; + case NODE_TYPE_NON_IXNODE: + if (is_inode || is_xnode) + goto out_err; + break; default: break; } @@ -1634,7 +1638,7 @@ static struct folio *f2fs_get_node_folio_ra(struct folio *parent, int start) struct f2fs_sb_info *sbi = F2FS_F_SB(parent); nid_t nid = get_nid(parent, start, false); - return __get_node_folio(sbi, nid, parent, start, NODE_TYPE_REGULAR); + return __get_node_folio(sbi, nid, parent, start, NODE_TYPE_NON_IXNODE); } static void flush_inline_data(struct f2fs_sb_info *sbi, nid_t ino) @@ -1875,7 +1879,7 @@ int f2fs_write_single_node_folio(struct folio *node_folio, int sync_mode, } if (!__write_node_folio(node_folio, false, false, NULL, - &wbc, false, FS_GC_NODE_IO, NULL)) + &wbc, false, io_type, NULL)) err = -EAGAIN; goto release_folio; out_folio: diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c index a2ea121331f1..4d854556b529 100644 --- a/fs/gfs2/super.c +++ b/fs/gfs2/super.c @@ -643,6 +643,7 @@ restart: gfs2_delete_debugfs_file(sdp); gfs2_sys_fs_del(sdp); + rcu_barrier(); free_sbd(sdp); } diff --git a/fs/nfs/client.c b/fs/nfs/client.c index be02bb227741..0781b15e7e05 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -1074,6 +1074,7 @@ struct nfs_server *nfs_alloc_server(void) server->io_stats = nfs_alloc_iostats(); if (!server->io_stats) { + ida_free(&s_sysfs_ids, server->s_sysfs_id); kfree(server); return NULL; } diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 8b1559171fe3..e22a8e0daf2c 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -551,6 +551,10 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh, if (!p) goto out_err_free; fh_count = be32_to_cpup(p); + if (fh_count == 0) { + rc = -EINVAL; + goto out_err_free; + } dss_info->fh_versions = kzalloc_objs(struct nfs_fh, fh_count, gfp_flags); diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index a9b8d482d289..c354b7b90293 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -5302,10 +5302,9 @@ static struct dentry *nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, do { alias = _nfs4_proc_mkdir(dir, dentry, sattr, label, &err); trace_nfs4_mkdir(dir, &dentry->d_name, err); + err = nfs4_handle_exception(NFS_SERVER(dir), err, &exception); if (err) - alias = ERR_PTR(nfs4_handle_exception(NFS_SERVER(dir), - err, - &exception)); + alias = ERR_PTR(err); } while (exception.retry); nfs4_label_release_security(label); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 743467e9ba20..aee523134c0f 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2229,11 +2229,11 @@ lookup_again: dprintk("%s wait for layoutreturn\n", __func__); lseg = ERR_PTR(pnfs_prepare_to_retry_layoutget(lo)); if (!IS_ERR(lseg)) { - pnfs_put_layout_hdr(lo); dprintk("%s retrying\n", __func__); trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, PNFS_UPDATE_LAYOUT_RETRY); + pnfs_put_layout_hdr(lo); goto lookup_again; } trace_pnfs_update_layout(ino, pos, count, iomode, lo, lseg, diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index 12632a706da8..0ff43dbcb7cd 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -1075,14 +1075,14 @@ nfs4_decode_mp_ds_addr(struct net *net, struct xdr_stream *xdr, gfp_t gfp_flags) /* r_netid */ nlen = xdr_stream_decode_string_dup(xdr, &netid, XDR_MAX_NETOBJ, gfp_flags); - if (unlikely(nlen < 0)) + if (unlikely(nlen <= 0)) goto out_err; /* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */ /* port is ".ABC.DEF", 8 chars max */ rlen = xdr_stream_decode_string_dup(xdr, &buf, INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN + 8, gfp_flags); - if (unlikely(rlen < 0)) + if (unlikely(rlen <= 0)) goto out_free_netid; /* replace port '.' with '-' */ diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 0ac538c76180..76305b86c1a9 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -131,10 +131,7 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) resp->status = fh_getattr(fh, &resp->stat); out: - /* argp->acl_{access,default} may have been allocated in - nfssvc_decode_setaclargs. */ - posix_acl_release(argp->acl_access); - posix_acl_release(argp->acl_default); + /* argp->acl_{access,default} are released in nfsaclsvc_release_setacl. */ return rpc_success; out_drop_lock: @@ -310,6 +307,16 @@ static void nfsaclsvc_release_access(struct svc_rqst *rqstp) fh_put(&resp->fh); } +static void nfsaclsvc_release_setacl(struct svc_rqst *rqstp) +{ + struct nfsd3_setaclargs *argp = rqstp->rq_argp; + struct nfsd_attrstat *resp = rqstp->rq_resp; + + fh_put(&resp->fh); + posix_acl_release(argp->acl_access); + posix_acl_release(argp->acl_default); +} + #define ST 1 /* status*/ #define AT 21 /* attributes */ #define pAT (1+AT) /* post attributes - conditional */ @@ -343,7 +350,7 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { .pc_func = nfsacld_proc_setacl, .pc_decode = nfsaclsvc_decode_setaclargs, .pc_encode = nfssvc_encode_attrstatres, - .pc_release = nfssvc_release_attrstat, + .pc_release = nfsaclsvc_release_setacl, .pc_argsize = sizeof(struct nfsd3_setaclargs), .pc_argzero = sizeof(struct nfsd3_setaclargs), .pc_ressize = sizeof(struct nfsd_attrstat), diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 7b5433bd3019..e87731380be8 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -118,10 +118,7 @@ out_drop_lock: out_errno: resp->status = nfserrno(error); out: - /* argp->acl_{access,default} may have been allocated in - nfs3svc_decode_setaclargs. */ - posix_acl_release(argp->acl_access); - posix_acl_release(argp->acl_default); + /* argp->acl_{access,default} are released in nfs3svc_release_setacl. */ return rpc_success; } @@ -223,6 +220,16 @@ static void nfs3svc_release_getacl(struct svc_rqst *rqstp) posix_acl_release(resp->acl_default); } +static void nfs3svc_release_setacl(struct svc_rqst *rqstp) +{ + struct nfsd3_setaclargs *argp = rqstp->rq_argp; + struct nfsd3_attrstat *resp = rqstp->rq_resp; + + fh_put(&resp->fh); + posix_acl_release(argp->acl_access); + posix_acl_release(argp->acl_default); +} + #define ST 1 /* status*/ #define AT 21 /* attributes */ #define pAT (1+AT) /* post attributes - conditional */ @@ -256,7 +263,7 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = { .pc_func = nfsd3_proc_setacl, .pc_decode = nfs3svc_decode_setaclargs, .pc_encode = nfs3svc_encode_setaclres, - .pc_release = nfs3svc_release_fhandle, + .pc_release = nfs3svc_release_setacl, .pc_argsize = sizeof(struct nfsd3_setaclargs), .pc_argzero = sizeof(struct nfsd3_setaclargs), .pc_ressize = sizeof(struct nfsd3_attrstat), diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 69e41105efdd..8e2929cffa7c 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -264,10 +264,12 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, ls->ls_file = find_any_file(fp); BUG_ON(!ls->ls_file); + ls->ls_fenced = false; + ls->ls_fence_delay = 0; + INIT_DELAYED_WORK(&ls->ls_fence_work, nfsd4_layout_fence_worker); + if (nfsd4_layout_setlease(ls)) { - nfsd_file_put(ls->ls_file); - put_nfs4_file(fp); - kmem_cache_free(nfs4_layout_stateid_cache, ls); + nfs4_put_stid(stp); return NULL; } @@ -280,10 +282,6 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate, list_add(&ls->ls_perfile, &fp->fi_lo_states); spin_unlock(&fp->fi_lock); - ls->ls_fenced = false; - ls->ls_fence_delay = 0; - INIT_DELAYED_WORK(&ls->ls_fence_work, nfsd4_layout_fence_worker); - trace_nfsd_layoutstate_alloc(&ls->ls_stid.sc_stateid); return ls; } diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index ab39ec885440..8561540ab2db 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -253,7 +253,7 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, .na_iattr = iap, .na_seclabel = &open->op_label, }; - struct dentry *parent, *child; + struct dentry *parent, *child = ERR_PTR(-EINVAL); __u32 v_mtime, v_atime; struct inode *inode; __be32 status; @@ -277,10 +277,14 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, if (open->op_acl) { if (open->op_dpacl || open->op_pacl) { status = nfserr_inval; - goto out_write; + goto out; + } + if (is_create_with_attrs(open)) { + status = nfsd4_acl_to_attr(NF4REG, open->op_acl, + &attrs); + if (status) + goto out; } - if (is_create_with_attrs(open)) - nfsd4_acl_to_attr(NF4REG, open->op_acl, &attrs); } else if (is_create_with_attrs(open)) { /* The dpacl and pacl will get released by nfsd_attrs_free(). */ attrs.na_dpacl = open->op_dpacl; @@ -293,7 +297,7 @@ nfsd4_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, &QSTR_LEN(open->op_fname, open->op_fnamelen)); if (IS_ERR(child)) { status = nfserrno(PTR_ERR(child)); - goto out_write; + goto out; } if (d_really_is_negative(child)) { @@ -407,7 +411,6 @@ set_attr: out: end_creating(child); nfsd_attrs_free(&attrs); -out_write: fh_drop_write(fhp); return status; } @@ -837,7 +840,7 @@ nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out_aftermask; if (create->cr_acl) { - if (create->cr_dpacl || create->cr_pacl) { + if (attrs.na_dpacl || attrs.na_pacl) { status = nfserr_inval; goto out_aftermask; } @@ -1470,7 +1473,7 @@ void nfsd4_async_copy_reaper(struct nfsd_net *nn) list_for_each_safe(pos, next, &clp->async_copies) { copy = list_entry(pos, struct nfsd4_copy, copies); if (test_bit(NFSD4_COPY_F_OFFLOAD_DONE, ©->cp_flags)) { - if (--copy->cp_ttl) { + if (!--copy->cp_ttl) { list_del_init(©->copies); list_add(©->copies, &reaplist); } diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index b338473d6e52..6ea25a52d2f4 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -718,7 +718,8 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg, return PTR_ERR(namecopy); name.data = namecopy; name.len = namelen; - get_user(princhashlen, &ci->cc_princhash.cp_len); + if (get_user(princhashlen, &ci->cc_princhash.cp_len)) + return -EFAULT; if (princhashlen > 0) { princhashcopy = memdup_user( &ci->cc_princhash.cp_data, diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 6837b63d9864..d875e98d4dcb 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -5169,6 +5169,7 @@ retry: /* Replace unconfirmed owners without checking for replay. */ release_openowner(oo); oo = NULL; + goto retry; } if (oo) { if (new) diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 2a0946c630e1..2da83053fa10 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2008,10 +2008,11 @@ static __be32 nfsd4_decode_secinfo_no_name(struct nfsd4_compoundargs *argp, union nfsd4_op_u *u) { struct nfsd4_secinfo_no_name *sin = &u->secinfo_no_name; + + sin->sin_exp = NULL; if (xdr_stream_decode_u32(argp->xdr, &sin->sin_style) < 0) return nfserr_bad_xdr; - sin->sin_exp = NULL; return nfs_ok; } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index eafdf7b7890f..2c557a998961 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1508,8 +1508,10 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, nfsd_stats_io_write_add(nn, exp, *cnt); fsnotify_modify(file); host_err = filemap_check_wb_err(file->f_mapping, since); - if (host_err < 0) + if (host_err < 0) { + commit_reset_write_verifier(nn, rqstp, host_err); goto out_nfserr; + } if (stable && fhp->fh_use_wgather) { host_err = wait_for_concurrent_writes(file); @@ -1689,6 +1691,8 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, nfsd_copy_write_verifier(verf, nn); err2 = filemap_check_wb_err(nf->nf_file->f_mapping, since); + if (err2 < 0) + commit_reset_write_verifier(nn, rqstp, err2); err = nfserrno(err2); break; case -EINVAL: diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index e8bea22b81a7..264cf8404385 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -707,12 +707,21 @@ static int ntfs_ioctl_get_volume_label(struct file *filp, unsigned long arg) { struct ntfs_volume *vol = NTFS_SB(file_inode(filp)->i_sb); char __user *buf = (char __user *)arg; + char label[FSLABEL_MAX]; + ssize_t len; + mutex_lock(&vol->volume_label_lock); if (!vol->volume_label) { - if (copy_to_user(buf, "", 1)) - return -EFAULT; - } else if (copy_to_user(buf, vol->volume_label, - MIN(FSLABEL_MAX, strlen(vol->volume_label) + 1))) + label[0] = '\0'; + len = 0; + } else { + len = strscpy(label, vol->volume_label, sizeof(label)); + if (len == -E2BIG) + len = FSLABEL_MAX - 1; + } + mutex_unlock(&vol->volume_label_lock); + + if (copy_to_user(buf, label, len + 1)) return -EFAULT; return 0; } diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 9e321cc2febe..cb880cb6e388 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -460,17 +460,23 @@ int ntfs_write_volume_label(struct ntfs_volume *vol, char *label) ret = ntfs_resident_attr_record_add(vol_ni, AT_VOLUME_NAME, AT_UNNAMED, 0, (u8 *)uname, uname_len * sizeof(__le16), 0); out: - mutex_unlock(&vol_ni->mrec_lock); - kvfree(uname); - if (ret >= 0) { - kfree(vol->volume_label); + char *old_label; + + mutex_lock(&vol->volume_label_lock); + old_label = vol->volume_label; vol->volume_label = new_label; + mutex_unlock(&vol->volume_label_lock); + + kfree(old_label); mark_inode_dirty_sync(vol->vol_ino); ret = 0; - } else { - kfree(new_label); } + mutex_unlock(&vol_ni->mrec_lock); + kvfree(uname); + + if (ret < 0) + kfree(new_label); return ret; } @@ -2631,6 +2637,7 @@ static int ntfs_init_fs_context(struct fs_context *fc) NVolSetCaseSensitive(vol); init_rwsem(&vol->mftbmp_lock); init_rwsem(&vol->lcnbmp_lock); + mutex_init(&vol->volume_label_lock); fc->s_fs_info = vol; fc->ops = &ntfs_context_ops; diff --git a/fs/ntfs/volume.h b/fs/ntfs/volume.h index af41427ec622..99e642f475f7 100644 --- a/fs/ntfs/volume.h +++ b/fs/ntfs/volume.h @@ -72,6 +72,7 @@ * @vol_flags: Volume flags. * @major_ver: Ntfs major version of volume. * @minor_ver: Ntfs minor version of volume. + * @volume_label_lock: protects @volume_label. * @volume_label: volume label. * @root_ino: The VFS inode of the root directory. * @secure_ino: The VFS inode of $Secure (NTFS3.0+ only, otherwise NULL). @@ -133,6 +134,7 @@ struct ntfs_volume { struct inode *logfile_ino; struct inode *lcnbmp_ino; struct rw_semaphore lcnbmp_lock; + struct mutex volume_label_lock; struct inode *vol_ino; __le16 vol_flags; u8 major_ver; diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 9eeac0ab2b71..372cf2f2e89b 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -851,6 +851,12 @@ out: return err; } +static bool ntfs_is_reserved_lxattr(const char *name) +{ + return !strcmp(name, "$LXUID") || !strcmp(name, "$LXGID") || + !strcmp(name, "$LXMOD") || !strcmp(name, "$LXDEV"); +} + /* * ntfs_setxattr - inode_operations::setxattr */ @@ -955,6 +961,12 @@ set_new_fa: goto out; } + /* Do not allow non privileged users to change $LXUID/$LXGID... */ + if (ntfs_is_reserved_lxattr(name) && !capable(CAP_SYS_ADMIN)) { + err = -EPERM; + goto out; + } + /* Deal with NTFS extended attribute. */ err = ntfs_set_ea(inode, name, strlen(name), value, size, flags, 0, NULL); diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c index d284e0e37252..a4a2b87a45fe 100644 --- a/fs/ocfs2/suballoc.c +++ b/fs/ocfs2/suballoc.c @@ -231,8 +231,16 @@ static int ocfs2_validate_gd_parent(struct super_block *sb, int resize) { unsigned int max_bits; + unsigned int max_bitmap_bits; + unsigned int max_bitmap_size; + int suballocator; struct ocfs2_group_desc *gd = (struct ocfs2_group_desc *)bh->b_data; + suballocator = le64_to_cpu(di->i_blkno) != OCFS2_SB(sb)->bitmap_blkno; + max_bitmap_size = ocfs2_group_bitmap_size(sb, suballocator, + OCFS2_SB(sb)->s_feature_incompat); + max_bitmap_bits = max_bitmap_size * 8; + if (di->i_blkno != gd->bg_parent_dinode) { do_error("Group descriptor #%llu has bad parent pointer (%llu, expected %llu)\n", (unsigned long long)bh->b_blocknr, @@ -240,6 +248,20 @@ static int ocfs2_validate_gd_parent(struct super_block *sb, (unsigned long long)le64_to_cpu(di->i_blkno)); } + if (le16_to_cpu(gd->bg_size) > max_bitmap_size) { + do_error("Group descriptor #%llu has bitmap size %u but physical max of %u\n", + (unsigned long long)bh->b_blocknr, + le16_to_cpu(gd->bg_size), + max_bitmap_size); + } + + if (le16_to_cpu(gd->bg_bits) > max_bitmap_bits) { + do_error("Group descriptor #%llu has bit count %u but physical max of %u\n", + (unsigned long long)bh->b_blocknr, + le16_to_cpu(gd->bg_bits), + max_bitmap_bits); + } + max_bits = le16_to_cpu(di->id2.i_chain.cl_cpg) * le16_to_cpu(di->id2.i_chain.cl_bpc); if (le16_to_cpu(gd->bg_bits) > max_bits) { do_error("Group descriptor #%llu has bit count of %u\n", diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c index 664b1b4a3233..340ea98fa494 100644 --- a/fs/smb/server/smbacl.c +++ b/fs/smb/server/smbacl.c @@ -1477,7 +1477,9 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path, break; aces_size -= ace_size; - if (ace->sid.num_subauth > SID_MAX_SUB_AUTHORITIES) + if (ace->sid.num_subauth > SID_MAX_SUB_AUTHORITIES || + ace_size < offsetof(struct smb_ace, sid) + CIFS_SID_BASE_SIZE + + sizeof(__le32) * ace->sid.num_subauth) break; if (!compare_sids(&sid, &ace->sid) || diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 4b53dc4a3266..390e4b7d9cb9 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -786,6 +786,8 @@ void mremap_userfaultfd_fail(struct vm_userfaultfd_ctx *vm_ctx) if (!ctx) return; + atomic_dec(&ctx->mmap_changing); + VM_WARN_ON_ONCE(atomic_read(&ctx->mmap_changing) < 0); userfaultfd_ctx_put(ctx); } |